Index: THORS =================================================================== --- AUTHORS (revision f6cae61954da5c1cf41a3b46faaeabf0466d5ef7) +++ (revision ) @@ -1,7 +1,0 @@ -Tomasz Obrębski -Michał Stolarski -Justyna Walkowska -Pawel Konieczka -Marcin Walas -Paweł Wereński -Mateusz Hromada Index: README =================================================================== --- README (revision 25b4022527844f2a169a0239ce99bef49be1ccb0) +++ README (revision c21bdd6340b1c3b3deeec44810ac38561acb1cc5) @@ -1,1 +1,33 @@ -http://utt.wmi.amu.edu.pl +TO COMPILE UTT YOU WILL NEED: +make +gengetopt +gcc +g++ +flex +openfst library +python + +TO BUILD DOCUMENTATION YOU WILL NEED: +texi2html +texinfo +some kind of TeX package, like texlive + +TO RUN UTT PROGRAMS YOU WILL NEED: + +perl module File::HomeDir + +COMMANDS TO BE RUN IN THIS DIRECTORY: + +% configure + +% make + +compiles all of the components + +% make install + +installes the package in your system in the directory defined by PREFIX in the configure +options + +when --enable-utf8 is specified in configure options then if there's a directory with +_utf8 suffix in the source directory it will be compiled instead of the normal version Index: ld/app/Makefile =================================================================== --- _old/app/Makefile (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,151 +1,0 @@ -# main makefile - -# ****************************** -# * Local variables -# ****************************** -CUR_DIR=$(shell pwd) -SRC_DIR=$(CUR_DIR)/src -OUTPUT_DIR=$(CUR_DIR)/output - -# ****************************** -# * Global for make globals -# ****************************** - -export UTT_DIR=${OUTPUT_DIR} - -# executables -export UTT_BIN_DIR=${UTT_DIR}/bin -# configuration files -export UTT_CONF_DIR=${UTT_DIR}/etc/utt -# language/encoding specific stuff -# any extra files for some programs, like: weights.kor, cats.dgc, gram.dgc, etc. -export UTT_LANG_DIR=${UTT_DIR}/share/utt -# some files like ser.l.template, terms.m4 -export UTT_LIB_DIR=${UTT_DIR}/lib/utt -# stuff like documantation (man, info), docs: FAQ, COPYRIGHT, NEWS, README -export UTT_SHARE_DIR=${UTT_DIR}/share - -############################## - -# list of components to be included in the distribution -COMPONENTS = compiledic cor dgp fla gph grp gue kon kor kot lem mar rm12 rs12 sen-l sen-nl ser tags tok.l unfla - -############################## - -# ------------------------------------------------------------------ -# sekcja kompilacji (kompiluje i wgrywa do OUTPUT_DIR) -# ------------------------------------------------------------------ -.PHONY: compile -compile: dirs components - @echo "Make compiled successfully!" - -.PHONY: dirs -dirs: - if [ -d ${UTT_DIR} ]; then rm -r ${UTT_DIR}; fi - mkdir -p ${UTT_DIR} - mkdir -p ${UTT_BIN_DIR} - mkdir -p ${UTT_CONF_DIR} - mkdir -p ${UTT_LANG_DIR} - mkdir -p ${UTT_LIB_DIR} - mkdir -p ${UTT_SHARE_DIR}/utt - mkdir -p ${UTT_SHARE_DIR}/doc/utt - mkdir -p ${UTT_SHARE_DIR}/info - mkdir -p ${UTT_SHARE_DIR}/man/man3 - -.PHONY: components -components: - cd $(SRC_DIR)/lib && make; cd $(CUR_DIR) - - @for cmp in $(COMPONENTS); do\ - cd $(SRC_DIR)/$$cmp && make && make copy; cd $(CUR_DIR); \ - done - - -# ------------------------------------------------------------------ -# sekcja sprzatania (kasuje binaria z katalogow SRC/COMPONENTS) -# ------------------------------------------------------------------ -.PHONY: clean -clean: clean_components clean_doc clean_dist - @echo "All files cleaned successfully!" - -.PHONY: clean_components -clean_components: - @for cmp in $(COMPONENTS); do \ - cd $(SRC_DIR)/$$cmp && make clean ; cd $(CUR_DIR); \ - done - cd $(SRC_DIR)/lib && make clean; cd $(CUR_DIR); - -.PHONY: clean_doc -clean_doc: - cd $(CUR_DIR)/doc && make clean; cd $(CUR_DIR) - -.PHONY: clean_dist -clean_dist: - - -# ------------------------------------------------------------------ -# sekcja przygotowania paczki (programow wraz z dodatkowymi plikami) -# ------------------------------------------------------------------ -.PHONY: build -build: compile build_conf build_share build_lib build_doc - @echo "All files builded successfully!" - -.PHONY: build_conf -build_conf: - cp $(CUR_DIR)/conf/*.conf $(UTT_CONF_DIR)/ - -.PHONY: build_lib -build_lib: - cp $(CUR_DIR)/lib/* $(UTT_LIB_DIR)/ - -.PHONY: build_doc -build_doc: - cd $(CUR_DIR)/doc && make && make copy; cd $(CUR_DIR) - -.PHONY: build_share -build_share: - cp $(CUR_DIR)/share/* $(UTT_LANG_DIR)/ - - -# ------------------------------------------------------------------ -# sekcja tworzenia dystrybucji (tarballa, rpm, deb) -# ------------------------------------------------------------------ -.PHONY: distribute -distribute: build dist_tarball dist_rpm - @echo "All distributions created successfully!" - -.PHONY: dist_tarball -dist_tarball: build - cd $(CUR_DIR)/dist && make tarball; cd $(CUR_DIR) - -.PHONY: dist_rpm -dist_rpm: build - cd $(CUR_DIR)/dist && make rpm; cd $(CUR_DIR) - -.PHONY: dist_deb -dist_deb: build - cd $(CUR_DIR)/dist && make deb; cd $(CUR_DIR) - - -# ------------------------------------------------------------------ -# sekcja testowania (kasuje tarballa z TARBALL_TEST_DIR, -# kompiluje, robi paczke, -# tworzy tarballa i wgrywa go do TARBALL_TEST_DIR) -# ------------------------------------------------------------------ -#install: all -# cd ${UTT_DIR} && make install; cd ${CUR_DIR} - -#uninstall: -# cd ${UTT_DIR} && make uninstall; cd ${DIR} - -#reinstall: -# cd ${UTT_DIR} && make reinstall; cd ${DIR} - -#dist: all -# tar -czvf $(UTT_DIST_NAME).tgz $(UTT_DIR) - - -#clean_dist: -# if [ -d $(UTT_DIST_DIR) ]; then rm -r $(UTT_DIST_DIR); else true; fi -# if [ -f $(UTT_DIST_FILE).tar.bz2 ]; then rm $(UTT_DIST_FILE).tar.bz2; else true; fi -# if [ -f $(UTT_DIST_PMDB_FILE).tar.bz2 ]; then rm $(UTT_DIST_PMDB_FILE).tar.bz2; else true; fi Index: ld/app/README.developers =================================================================== --- _old/app/README.developers (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,25 +1,0 @@ -TO COMPILE UTT YOU WILL NEED: -make -gengetopt -g++ -flex - -TO RUN UTT PROGRAMS YOU WILL NEED: - -perl module File::HomeDir - -COMMANDS TO BE RUN IN THIS DIRECTORY: - -% make - -compiles all the components, moves all files destinated for -distribution in the directory [the value of UTT_DIR_NAME variable in -Makefile] (currently utt-0.9) - -% make install - -installes the package in your system in the directory ~/.utt - -% make dist_tarball - -prepares distribution file named ${UTT_DIR_NAME}.tgz (currently utt-0.9.tgz) Index: ld/app/TODO =================================================================== --- _old/app/TODO (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,25 +1,0 @@ -BARDZO WAZNE: -* -* instalka slownikow -* programy maja wykrywac brak slownikow -> "No language module installed" - na podst zmiennej language w utt.conf, "Cannot open dict...." gdy po prostu - nie znajdzie pliku slownika -* tresc na stronie -* statyczne laczenie bibl 32-bit (miejsce kompilacji) -* przemyslec sposob wybierania jezyka / slownika po zainstalowaniu roznych dystrybucji [PK, TO] -* gue nie sortuje wynikow, opcja weights dziala na odwrot -* kor nie wykonuje zamian -> , np. ÅŒ rz - -WAZNE: -* zamienic kota na lepszego (Kubis) [TO] -* sen - unikac dwukrotnego wstawiania BOSow i EOSow [TO] -* polaczyc sen'y [TO] -* generowanie i sprawdzanie zaleznosci dla tarballa [PK] -* Zadania zwiazane z rozbudowa ser (src/ser/TODO). -* Nowa funkcjonalnosc dla kot? con? - kazde zdanie w nowym wierszu -* opcja info w dgp powinna miec domyslna wartosc d lub h -* przyspieszyc process_seg() -> obliczanie prefiksow pol z opcji -s i -S raz na poczatku programu, a nie w kolko -* kor: nie dziala opcja distance -* zunifikowac opcje cor i kor -* uporzadkowac sprawe zaleznosci miedzy modulem jezykowym a wyborem tagow (tag2re) - Index: ld/app/dist/Makefile =================================================================== --- _old/app/dist/Makefile (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,46 +1,0 @@ - -# some variables - -# path, where all nessesary files are placed -# (they will be processed for making distribution) -export UTT_DIST_DIR=$(UTT_DIR) -# path, where distribution package will be placed -export UTT_DIST_OUTPUT=$(UTT_DIR)/.. -#temp path for making distribution -export UTT_DIST_TMP=$(shell pwd)/dist_tmp - - -# ----------------------------------------------------------- -# default task should display options -.PHONY: default -defaul: - @echo "Using: make tarball|rpm|deb" - - -# ----------------------------------------------------------- -# this task should compile utt (if nesessery) and create tar.gz version -.PHONY: tarball -tarball: - cd tarball && make - -# ----------------------------------------------------------- -# this task should compile utt (if nesessery) and create rpm version -.PHONY: rpm -rpm: - @#we build rpm (see spec/README for details) - cd spec && make - -# ----------------------------------------------------------- -# this task should compile utt (if nesessery) and create deb version -.PHONY: deb -deb: - @#we build deb (see deb/README for details) - cd deb && make - -# ----------------------------------------------------------- -# this task should remove compiled files and directories -.PHONY: clean -clean: - # finally the line below should be uncomment - rm -fr ${UTT_DIST_TMP} - Index: ld/app/dist/common/check_dependenties.pl =================================================================== --- _old/app/dist/common/check_dependenties.pl (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,15 +1,0 @@ - -while() { - chomp; - $app = $_; - $path = `which $app 2>/dev/null`; - $err = $?; - print $app.": "; - if($err != 0) { - print "failed ($err)\n"; - } - else { - print $path; - } -} - Index: ld/app/dist/common/description.def =================================================================== --- _old/app/dist/common/description.def (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,1 +1,0 @@ -I put here some description. Index: ld/app/dist/common/description.pl.def =================================================================== --- _old/app/dist/common/description.pl.def (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,1 +1,0 @@ -Tu umieszczę opis po polsku. Index: ld/app/dist/common/find_perl_deps.pl =================================================================== --- _old/app/dist/common/find_perl_deps.pl (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,29 +1,0 @@ - - -while() { - chomp; - # najpierw nazwa pliku zrodlowego out - if($_ =~ /^[^:]*\:\s*(.*)$/) { - my $line = $1; -# print "TEXT: $line\n"; - # teraz tylko samo polecenie - if($line =~ /\`\s*(.+)\s*\`/) { - my $cmd = $1; -# print "CMD: $cmd\n"; - # teraz splitujemy potoki - my @progs = split(/\s*\|\s*/, $cmd); - foreach (@progs) { -# print "$_\n"; - # ucinamy agrumenty programu - # oraz linie, zawierajace nie-programy (--replace, $tmpfile_x, /g, \\, itp.) - if($_ =~ /^([^\$\\\/\s\']+)(\s.*)?$/) { - my $app = $1; -# print "APP: $app\n"; -# my $res = `which $app`; -# print "WYNIK: $res\n"; - print "$app\n"; - } - } # foreach - } - } -} Index: ld/app/dist/common/find_rpm_deps.sh =================================================================== --- _old/app/dist/common/find_rpm_deps.sh (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,16 +1,0 @@ -#!/bin/sh - -# sprawdzamy czy podano argument -if test $# -lt 1; then echo RPM file name expected!; exit -1; fi - -# sprawdzamy czy to plik, potem, czy rpm -if test -f $1; \ -then - if test "rpm" = `ls $1 | tail -c 4`; \ - then - rpm -q -R -p $1; \ - else echo "It's not a RPM file!"; \ - fi -else echo RPM file not found!; \ -fi - Index: ld/app/dist/common/make_deps.sh =================================================================== --- _old/app/dist/common/make_deps.sh (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,3 +1,0 @@ -#!/bin/sh - -grep -r -e "\`" ../../src | grep -v -e "\.svn\/" | perl find_perl_deps.pl | sort | uniq > dep_list.txt Index: ld/app/dist/common/prepare_conf.sh =================================================================== --- _old/app/dist/common/prepare_conf.sh (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,14 +1,0 @@ -#!/bin/sh - -if test 3 -ne $# -then - echo "Usage: " `basename $0` src_conf_dir dest_conf_dir replacement -else - POLEC="s/PATH_PREFIX/$3/g" - - for FN in `ls $1/*.conf` - do - BN=`basename ${FN}` - sed ${POLEC} ${FN} > $2/${BN} - done -fi Index: ld/app/dist/common/release.def =================================================================== --- _old/app/dist/common/release.def (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,1 +1,0 @@ -2 Index: ld/app/dist/common/version.def =================================================================== --- _old/app/dist/common/version.def (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,1 +1,0 @@ -0.9 Index: ld/app/dist/deb/Makefile =================================================================== --- _old/app/dist/deb/Makefile (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,86 +1,0 @@ -#default task - -DIR=$(shell pwd) - -ifndef UTT_DIST_DIR - UTT_DIST_DIR=${DIR} -endif - -ifndef UTT_DIST_OUTPUT - UTT_DIST_OUTPUT=${DIR} -endif - -# here there're few properties -_PRODUCT_NAME=utt -_UTT_VER=$(shell cat ../common/version.def) -_UTT_REL=$(shell cat ../common/release.def) -_DEB_FROOT=$(DIR)/deb_root -_UTT_DIR=${_DEB_FROOT}/usr/local/$(_PRODUCT_NAME).$(_UTT_VER)-$(_UTT_REL) - -.PHONY: default -default: make_control make_postinst make_prerm - # first, we prepare some directory structure - mkdir -p $(_DEB_FROOT)/DEBIAN - mkdir -p $(_UTT_DIR) - - # next, we copy deb package files - mv ./control $(_DEB_FROOT)/DEBIAN/ - mv ./postinst $(_DEB_FROOT)/DEBIAN/ - mv ./prerm $(_DEB_FROOT)/DEBIAN/ - cd ${_DEB_FROOT} && tar -cvvf control.tar.gz DEBIAN/ - cd ${DIR}; - rm -fr ${_DEB_FROOT}/DEBIAN/ - - # we copy all necessery files (binaries) - cp -r ${UTT_DIST_DIR}/* ${_UTT_DIR}/ - cp ./changelog ${_UTT_DIR}/share/doc/$(_PRODUCT_NAME)/ -# gzip --best $(_DEB_ROOT)/usr/share/doc/$(_PRODUCT_NAME)/changelog - cp ./changelog.Debian $(_UTT_DIR)/share/doc/$(_PRODUCT_NAME)/ -# gzip --best $(_DEB_ROOT)/usr/share/doc/$(_PRODUCT_NAME)/changelog.Debian - cp ../files/* ${_UTT_DIR}/share/doc/${_PRODUCT_NAME}/ - cp ../common/utt_make_config.pl ${_UTT_DIR}/bin/ - chmod 755 ${_UTT_DIR}/bin/utt_make_config.pl - - - -# # next we make man/doc archives -# gzip --best $(_DEB_ROOT)/usr/share/man/man1/$(_PRODUCT_NAME).1 - - find $(_DEB_FROOT) -type d | xargs chmod 755 # this is necessary on Debian Woody, don't ask me why - - # finally, we buid deb package - fakeroot dpkg-deb --build $(_DEB_FROOT) - mv $(_DEB_FROOT).deb $(_PRODUCT_NAME)_$(_UTT_VER)-$(_UTT_REL).all.deb - rm -rf ${_DEB_FROOT} - - - -.PHONY: make_control -make_control: - echo "Package: $(_PRODUCT_NAME)" > control - echo "Version: $(_UTT_VER)" >> control - echo "Section: web" >> control - echo "Priority: optional" >> control - echo "Architecture: all" >> control - echo "Essential: no" >> control - - echo "Depends: " >> control -# here we read this information from file ../common/requirements.def - #libwww-perl, acme-base (>= 1.2) <= wymagania pakietowe - - echo "Pre-Depends: perl" >> control - - echo "Maintainer: Adam Mickiewicz University" >> control - echo "Provides: $(_PRODUCT_NAME)" >> control - echo -n "Description: " >> control - cat ../common/description.def >> control - -.PHONY: make_postinst -make_postinst: - echo "#!/bin/sh" > postinst - echo "$(_INSTALL_DIR)/create_utt_config.pl" >> postinst - echo "rm -f $(_INSTALL_DIR)/create_utt_config.pl" >> postinst - -.PHONY: make_prerm -make_prerm: - echo "#!/bin/sh" > prerm Index: ld/app/dist/deb/README =================================================================== --- _old/app/dist/deb/README (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,3 +1,0 @@ -This directory contains files necessery to create deb package. - -apt-get install dpkg-dev debhelper devscripts fakeroot linda Index: ld/app/dist/files/COPYRIGHT =================================================================== --- _old/app/dist/files/COPYRIGHT (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,8 +1,0 @@ -Copyright (C) 2005 - 2008 Tomasz Obrebski, Michal Stolarski, Justyna Walkowska, Pawel Konieczka - -Permission is granted to copy, distribute and/or modify this document -under the terms of the GNU Free Documentation License, Version 1.2 -or any later version published by the Free Software Foundation; -with no Invariant Sections, no Front-Cover Texts, and no Back-Cover -Texts. A copy of the license is included in the section entitled ‘‘GNU -Free Documentation License’’. Index: ld/app/dist/files/LICENCE =================================================================== --- _old/app/dist/files/LICENCE (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,264 +1,0 @@ -GNU Free Documentation License -Version 1.2, November 2002 -Copyright (c) 2000,2001,2002 Free Software Foundation, Inc. -51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA - -Everyone is permitted to copy and distribute verbatim copies -of this license document, but changing it is not allowed. - - 0. PREAMBLE - The purpose of this License is to make a manual, textbook, or other functional and - useful document free in the sense of freedom: to assure everyone the effective freedom - to copy and redistribute it, with or without modifying it, either commercially or noncommercially. - Secondarily, this License preserves for the author and publisher a way - to get credit for their work, while not being considered responsible for modifications - made by others. - This License is a kind of “copyleft”, which means that derivative works of the document - must themselves be free in the same sense. It complements the GNU General Public - License, which is a copyleft license designed for free software. - We have designed this License in order to use it for manuals for free software, because - free software needs free documentation: a free program should come with manuals - providing the same freedoms that the software does. But this License is not limited to - software manuals; it can be used for any textual work, regardless of subject matter or - whether it is published as a printed book. We recommend this License principally for - works whose purpose is instruction or reference. - 1. APPLICABILITY AND DEFINITIONS - This License applies to any manual or other work, in any medium, that contains a - notice placed by the copyright holder saying it can be distributed under the terms - of this License. Such a notice grants a world-wide, royalty-free license, unlimited in - duration, to use that work under the conditions stated herein. The “Document”, - below, refers to any such manual or work. Any member of the public is a licensee, and - is addressed as “you”. You accept the license if you copy, modify or distribute the work - in a way requiring permission under copyright law. - A “Modified Version” of the Document means any work containing the Document or - a portion of it, either copied verbatim, or with modifications and/or translated into - another language. - A “Secondary Section” is a named appendix or a front-matter section of the Document - that deals exclusively with the relationship of the publishers or authors of the Document - to the Document’s overall subject (or to related matters) and contains nothing that - could fall directly within that overall subject. (Thus, if the Document is in part a - textbook of mathematics, a Secondary Section may not explain any mathematics.) The - relationship could be a matter of historical connection with the subject or with related - matters, or of legal, commercial, philosophical, ethical or political position regarding - them. - The “Invariant Sections” are certain Secondary Sections whose titles are designated, as - being those of Invariant Sections, in the notice that says that the Document is released - under this License. If a section does not fit the above definition of Secondary then it is - not allowed to be designated as Invariant. The Document may contain zero Invariant - Sections. If the Document does not identify any Invariant Sections then there are none. - The “Cover Texts” are certain short passages of text that are listed, as Front-Cover - Texts or Back-Cover Texts, in the notice that says that the Document is released under - this License. A Front-Cover Text may be at most 5 words, and a Back-Cover Text may - be at most 25 words. - A “Transparent” copy of the Document means a machine-readable copy, represented - in a format whose specification is available to the general public, that is suitable for - revising the document straightforwardly with generic text editors or (for images composed - of pixels) generic paint programs or (for drawings) some widely available drawing - editor, and that is suitable for input to text formatters or for automatic translation to - a variety of formats suitable for input to text formatters. A copy made in an otherwise - Transparent file format whose markup, or absence of markup, has been arranged to - thwart or discourage subsequent modification by readers is not Transparent. An image - format is not Transparent if used for any substantial amount of text. A copy that is - not “Transparent” is called “Opaque”. - Examples of suitable formats for Transparent copies include plain ascii without - markup, Texinfo input format, LaTEX input format, SGML or XML using a publicly - available DTD, and standard-conforming simple HTML, PostScript or PDF designed - for human modification. Examples of transparent image formats include PNG, XCF - and JPG. Opaque formats include proprietary formats that can be read and edited - only by proprietary word processors, SGML or XML for which the DTD and/or - processing tools are not generally available, and the machine-generated HTML, - PostScript or PDF produced by some word processors for output purposes only. - The “Title Page” means, for a printed book, the title page itself, plus such following - pages as are needed to hold, legibly, the material this License requires to appear in the - title page. For works in formats which do not have any title page as such, “Title Page” - means the text near the most prominent appearance of the work’s title, preceding the - beginning of the body of the text. - A section “Entitled XYZ” means a named subunit of the Document whose title either - is precisely XYZ or contains XYZ in parentheses following text that translates XYZ in - another language. (Here XYZ stands for a specific section name mentioned below, such - as “Acknowledgements”, “Dedications”, “Endorsements”, or “History”.) To “Preserve - the Title” of such a section when you modify the Document means that it remains a - section “Entitled XYZ” according to this definition. - The Document may include Warranty Disclaimers next to the notice which states that - this License applies to the Document. These Warranty Disclaimers are considered to - be included by reference in this License, but only as regards disclaiming warranties: - any other implication that these Warranty Disclaimers may have is void and has no - effect on the meaning of this License. - 2. VERBATIM COPYING - You may copy and distribute the Document in any medium, either commercially or - noncommercially, provided that this License, the copyright notices, and the license - notice saying this License applies to the Document are reproduced in all copies, and - that you add no other conditions whatsoever to those of this License. You may not use - technical measures to obstruct or control the reading or further copying of the copies - you make or distribute. However, you may accept compensation in exchange for copies. - If you distribute a large enough number of copies you must also follow the conditions - in section 3. - You may also lend copies, under the same conditions stated above, and you may publicly - display copies. - 3. COPYING IN QUANTITY - If you publish printed copies (or copies in media that commonly have printed covers) of - the Document, numbering more than 100, and the Document’s license notice requires - Cover Texts, you must enclose the copies in covers that carry, clearly and legibly, all - these Cover Texts: Front-Cover Texts on the front cover, and Back-Cover Texts on - the back cover. Both covers must also clearly and legibly identify you as the publisher - of these copies. The front cover must present the full title with all words of the title - equally prominent and visible. You may add other material on the covers in addition. - Copying with changes limited to the covers, as long as they preserve the title of the - Document and satisfy these conditions, can be treated as verbatim copying in other - respects. - If the required texts for either cover are too voluminous to fit legibly, you should put - the first ones listed (as many as fit reasonably) on the actual cover, and continue the - rest onto adjacent pages. - If you publish or distribute Opaque copies of the Document numbering more than 100, - you must either include a machine-readable Transparent copy along with each Opaque - copy, or state in or with each Opaque copy a computer-network location from which - the general network-using public has access to download using public-standard network - protocols a complete Transparent copy of the Document, free of added material. If - you use the latter option, you must take reasonably prudent steps, when you begin - distribution of Opaque copies in quantity, to ensure that this Transparent copy will - remain thus accessible at the stated location until at least one year after the last time - you distribute an Opaque copy (directly or through your agents or retailers) of that - edition to the public. - It is requested, but not required, that you contact the authors of the Document well - before redistributing any large number of copies, to give them a chance to provide you - with an updated version of the Document. - 4. MODIFICATIONS - You may copy and distribute a Modified Version of the Document under the conditions - of sections 2 and 3 above, provided that you release the Modified Version under precisely - this License, with the Modified Version filling the role of the Document, thus licensing - distribution and modification of the Modified Version to whoever possesses a copy of - it. In addition, you must do these things in the Modified Version: - A. Use in the Title Page (and on the covers, if any) a title distinct from that of the - Document, and from those of previous versions (which should, if there were any, - be listed in the History section of the Document). You may use the same title as - a previous version if the original publisher of that version gives permission. - B. List on the Title Page, as authors, one or more persons or entities responsible for - authorship of the modifications in the Modified Version, together with at least five - of the principal authors of the Document (all of its principal authors, if it has fewer - than five), unless they release you from this requirement. - C. State on the Title page the name of the publisher of the Modified Version, as the - publisher. - D. Preserve all the copyright notices of the Document. - E. Add an appropriate copyright notice for your modifications adjacent to the other - copyright notices. - F. Include, immediately after the copyright notices, a license notice giving the public - permission to use the Modified Version under the terms of this License, in the form - shown in the Addendum below. - G. Preserve in that license notice the full lists of Invariant Sections and required Cover - Texts given in the Document’s license notice. - H. Include an unaltered copy of this License. - I. Preserve the section Entitled “History”, Preserve its Title, and add to it an item - stating at least the title, year, new authors, and publisher of the Modified Version - as given on the Title Page. If there is no section Entitled “History” in the Document, - create one stating the title, year, authors, and publisher of the Document - as given on its Title Page, then add an item describing the Modified Version as - stated in the previous sentence. - J. Preserve the network location, if any, given in the Document for public access to - a Transparent copy of the Document, and likewise the network locations given in - the Document for previous versions it was based on. These may be placed in the - “History” section. You may omit a network location for a work that was published - at least four years before the Document itself, or if the original publisher of the - version it refers to gives permission. - K. For any section Entitled “Acknowledgements” or “Dedications”, Preserve the Title - of the section, and preserve in the section all the substance and tone of each of the - contributor acknowledgements and/or dedications given therein. - L. Preserve all the Invariant Sections of the Document, unaltered in their text and - in their titles. Section numbers or the equivalent are not considered part of the - section titles. - M. Delete any section Entitled “Endorsements”. Such a section may not be included - in the Modified Version. - N. Do not retitle any existing section to be Entitled “Endorsements” or to conflict in - title with any Invariant Section. - O. Preserve any Warranty Disclaimers. - If the Modified Version includes new front-matter sections or appendices that qualify - as Secondary Sections and contain no material copied from the Document, you may at - your option designate some or all of these sections as invariant. To do this, add their - titles to the list of Invariant Sections in the Modified Version’s license notice. These - titles must be distinct from any other section titles. - You may add a section Entitled “Endorsements”, provided it contains nothing but - endorsements of your Modified Version by various parties—for example, statements of - peer review or that the text has been approved by an organization as the authoritative - definition of a standard. - You may add a passage of up to five words as a Front-Cover Text, and a passage of up - to 25 words as a Back-Cover Text, to the end of the list of Cover Texts in the Modified - Version. Only one passage of Front-Cover Text and one of Back-Cover Text may be - added by (or through arrangements made by) any one entity. If the Document already - includes a cover text for the same cover, previously added by you or by arrangement - made by the same entity you are acting on behalf of, you may not add another; but - you may replace the old one, on explicit permission from the previous publisher that - added the old one. - The author(s) and publisher(s) of the Document do not by this License give permission - to use their names for publicity for or to assert or imply endorsement of any Modified - Version. - 5. COMBINING DOCUMENTS - You may combine the Document with other documents released under this License, - under the terms defined in section 4 above for modified versions, provided that you - include in the combination all of the Invariant Sections of all of the original documents, - unmodified, and list them all as Invariant Sections of your combined work in its license - notice, and that you preserve all their Warranty Disclaimers. - The combined work need only contain one copy of this License, and multiple identical - Invariant Sections may be replaced with a single copy. If there are multiple Invariant - Sections with the same name but different contents, make the title of each such section - unique by adding at the end of it, in parentheses, the name of the original author or - publisher of that section if known, or else a unique number. Make the same adjustment - to the section titles in the list of Invariant Sections in the license notice of the combined - work. - In the combination, you must combine any sections Entitled “History” in the various - original documents, forming one section Entitled “History”; likewise combine any - sections Entitled “Acknowledgements”, and any sections Entitled “Dedications”. You - must delete all sections Entitled “Endorsements.” - 6. COLLECTIONS OF DOCUMENTS - You may make a collection consisting of the Document and other documents released - under this License, and replace the individual copies of this License in the various - documents with a single copy that is included in the collection, provided that you - follow the rules of this License for verbatim copying of each of the documents in all - other respects. - You may extract a single document from such a collection, and distribute it individually - under this License, provided you insert a copy of this License into the extracted - document, and follow this License in all other respects regarding verbatim copying of - that document. - 7. AGGREGATION WITH INDEPENDENT WORKS - A compilation of the Document or its derivatives with other separate and independent - documents or works, in or on a volume of a storage or distribution medium, is called - an “aggregate” if the copyright resulting from the compilation is not used to limit the - legal rights of the compilation’s users beyond what the individual works permit. When - the Document is included in an aggregate, this License does not apply to the other - works in the aggregate which are not themselves derivative works of the Document. - If the Cover Text requirement of section 3 is applicable to these copies of the Document, - then if the Document is less than one half of the entire aggregate, the Document’s Cover - Texts may be placed on covers that bracket the Document within the aggregate, or the - electronic equivalent of covers if the Document is in electronic form. Otherwise they - must appear on printed covers that bracket the whole aggregate. - 8. TRANSLATION - Translation is considered a kind of modification, so you may distribute translations - of the Document under the terms of section 4. Replacing Invariant Sections with - translations requires special permission from their copyright holders, but you may - include translations of some or all Invariant Sections in addition to the original versions - of these Invariant Sections. You may include a translation of this License, and all the - license notices in the Document, and any Warranty Disclaimers, provided that you - also include the original English version of this License and the original versions of - those notices and disclaimers. In case of a disagreement between the translation and - the original version of this License or a notice or disclaimer, the original version will - prevail. - If a section in the Document is Entitled “Acknowledgements”, “Dedications”, or “History”, - the requirement (section 4) to Preserve its Title (section 1) will typically require - changing the actual title. - 9. TERMINATION - You may not copy, modify, sublicense, or distribute the Document except as expressly - provided for under this License. Any other attempt to copy, modify, sublicense or - distribute the Document is void, and will automatically terminate your rights under - this License. However, parties who have received copies, or rights, from you under this - License will not have their licenses terminated so long as such parties remain in full - compliance. - 10. FUTURE REVISIONS OF THIS LICENSE - The Free Software Foundation may publish new, revised versions of the GNU Free - Documentation License from time to time. Such new versions will be similar in spirit - to the present version, but may differ in detail to address new problems or concerns. - See http://www.gnu.org/copyleft/. - Each version of the License is given a distinguishing version number. If the Document - specifies that a particular numbered version of this License “or any later version” - applies to it, you have the option of following the terms and conditions either of that - specified version or of any later version that has been published (not as a draft) by - the Free Software Foundation. If the Document does not specify a version number of - this License, you may choose any version ever published (not as a draft) by the Free - Software Foundation. Index: ld/app/dist/files/README =================================================================== --- _old/app/dist/files/README (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,51 +1,0 @@ -General information -********************* - -UAM Text Tools (UTT) is a package of language processing tools -developed at Adam Mickiewicz University. Its functionality includes: -* tokenization -* dictionary-based morphological analysis -* heuristic morphological analysis of unknown words -* spelling correction -* pattern search -* sentence splitting -* generation of concordance tables - -The toolkit is destined for processing of raw (not annotated) -unrestricted text for any conceivable purpose. - - -Installation -************** - -1) unpack the UTT tar archive -2) in the same directory, unpack the tar archives of all UTT dictionary modules you have -3) run - make install - in the root directory of the installation -4) add the bin directory to the PATH variable - - -Requirements -************* - -* File::HomeDir - - the Perl package File::HomeDir must be installed - (to install the package, run 'perl -MCPAN -e shell' and write - 'install File::HomeDir' after the 'cpan>' prompt appears) - -* flex - - to run the ser component, flex must be installed in your system - -* ruby - - to run the tre component, ruby must be installed in your system - -* locale pl_PL.iso-8852-2 - - the locales pl_PL.iso-8859-2 (pl_PL in short) must be installed - and set while using UTT with the Polish module. The text you - process with UTT must be encoded in iso-8859-2. - Index: ld/app/dist/spec/Makefile =================================================================== --- _old/app/dist/spec/Makefile (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,26 +1,0 @@ -# this makefile will build rpm - -DIR=$(shell pwd) - -ifndef UTT_DIST_DIR - UTT_DIST_DIR=${DIR} -endif - -_RPM_FROOT=${DIR}/rmp_root -_UTT_ROOT=${_RPM_FROOT}/usr/local -# default task -.PHONY: rpm -rpm: - if test -d ${_RPM_FROOT}; then rm -fr ${_RMP_FROOT}; fi - mkdir -p ${_UTT_ROOT} - cp -rf ${UTT_DIST_DIR}/* ${_UTT_ROOT}/ - mkdir -p ${_UTT_ROOT}/cnf - mv ${_UTT_ROOT}/etc/utt/*.conf ${_UTT_ROOT}/cnf/ - ${DIR}/../common/prepare_conf.sh ${_UTT_ROOT}/cnf ${_UTT_ROOT}/etc/utt \\\/usr\\\/local - rm -rf ${_UTT_ROOT}/cnf - - cp ../files/* ${_UTT_ROOT}/ - cd ${_RPM_FROOT}; rpmbuild -bb ${DIR}/utt.spec - - rm -rf ${_RPM_FROOT} - Index: ld/app/dist/spec/README =================================================================== --- _old/app/dist/spec/README (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,16 +1,0 @@ -This directory contains files necessary to produce rpm package. - -First, you must have variable UTT_DIST_DIR defined properly. -This variable should be defined by main Makefile. - -To create rpm file, just write: -make - -The created package should appears in default RPM directory. -(in my computer it is /usr/src/redhat/RPMS/$arch/ directory) - -To determine the rpm output directory, execute: -rpm --showrc | grep _rmpdir - -You need access privilage to this directory to create rmp. - Index: ld/app/dist/spec/utt.spec =================================================================== --- _old/app/dist/spec/utt.spec (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,81 +1,0 @@ -# -# Default RPM header. -# -# START_RPM_STD_HEADER: - - -# -# RPM properties -# -%define _this_product UAM Text Tools -%define _this_summary Some tools for text processing -%define _this_name utt -%define _this_version %(cat ../../common/version.def) -%define _this_release %(cat ../../common/release.def) -%define _this_copyright Adam Mickiewicz University, Poland - -# -# Default RPM header. -# -# END_RPM_STD_HEADER: -# -------------------------------------------------------------------- - -Summary: %_this_summary -Name: %_this_name -Version: %_this_version -Release: %_this_release -#Copyright: %_this_copyright -License: GPL -Group: Development/Tools -URL: http://utt.amu.edu.pl -Vendor: Adam Mickiewicz University -BuildRoot: %(pwd) -#BuildArch: i586 -# requirements for utt application -#AutoReq: no -#AutoReqProv: no - -#Requires: glibc >= 2.1.3 -#Requires: libgcc1 >= 3.0 -#Requires: libgcc >= 3.0 -#Requires: libstdc++6 >= 3.4.1 -#Requires: libstdc++ >= 3.4.1 - -%description -%(cat ../../common/description.def) - -%description -l pl -%(cat ../../common/description.pl.def) - - -# ------------------------------------------------------------- -# preparing sources for compilation -%prep - -# source compilation -%build - -# rpm building -%install - -# cleaning after rpm build -%clean - -# ------------------------------------------------------------- -#before installation -%pre - -#after installation -%post -# we need to create utt.conf file - -#before uninstallation -%preun - -#after uninstallation -%postun - -# ------------------------------------------------------------- -%files -%defattr(-,root,root) -/* Index: ld/app/dist/struktura.txt =================================================================== --- _old/app/dist/struktura.txt (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,74 +1,0 @@ -/usr/local/bin/aut2fsa -/usr/local/bin/canonize -/usr/local/bin/compiledic -/usr/local/bin/con -/usr/local/bin/cor -/usr/local/bin/dgc -/usr/local/bin/dgp -/usr/local/bin/fla -/usr/local/bin/fsm2aut -/usr/local/bin/go ? -/usr/local/bin/Makefile.go ? -/usr/local/bin/gph -/usr/local/bin/grp -/usr/local/bin/gue -/usr/local/bin/kot -/usr/local/bin/lem -/usr/local/bin/mar -/usr/local/bin/sen -/usr/local/bin/sen-nl -/usr/local/bin/ser -/usr/local/bin/tok -/usr/local/bin/tre.rb -/usr/local/bin/unfla -/usr/local/bin/ipi.tag2re -/usr/local/bin/uam.tag2re - - -# R.D. sugeruje /etc/utt -# lokalnie: ~/.utt lub (trendy) ~/.config/utt -/usr/local/etc/utt/con.conf -/usr/local/etc/utt/cor.conf -/usr/local/etc/utt/dgc.conf -/usr/local/etc/utt/fla.conf -/usr/local/etc/utt/grp.conf -/usr/local/etc/utt/gue.conf -/usr/local/etc/utt/kor.conf -/usr/local/etc/utt/kot.conf -/usr/local/etc/utt/lem.conf -/usr/local/etc/utt/mar.conf -/usr/local/etc/utt/sen.conf -/usr/local/etc/utt/ser.conf -/usr/local/etc/utt/tok.conf -/usr/local/etc/utt/unfla.conf -/usr/local/etc/utt/utt.conf - -/usr/local/share/utt/weights.kor -/usr/local/share/utt/cats.dgc -/usr/local/share/utt/gram.dgc -# lokalnie: wszystkie pliki beda umieszczone w ~/.local/share/utt/ - -/usr/local/share/utt/pl_PL.ISO-8859-2/pl_PL.ISO-8859-2.sym -/usr/local/share/utt/pl_PL.ISO-8859-2/cor.bin -/usr/local/share/utt/pl_PL.ISO-8859-2/gue.bin -/usr/local/share/utt/pl_PL.ISO-8859-2/lem.bin -/usr/local/share/utt/pl_PL.UTF-8/pl_PL.UTF-8.sym -/usr/local/share/utt/pl_PL.UTF-8/cor.bin -/usr/local/share/utt/pl_PL.UTF-8/gue.bin -/usr/local/share/utt/pl_PL.UTF-8/lem.bin -# lokalnie: wszystkie slowniki beda umieszczone w ~/.local/share/utt/ - -/usr/local/lib/utt/ser.l.template -/usr/local/lib/utt/terms.m4 -/usr/local/lib/utt/seg.rb -/usr/local/lib/attr.pm -# lokalnie: wszystkie pliki beda umieszczone w ~/.local/lib/utt/ - -/usr/local/share/doc/utt/FAQ -/usr/local/share/doc/utt/COPYRIGHT -/usr/local/share/doc/utt/NEWS -/usr/local/share/doc/utt/README -/usr/local/share/info/utt.info.gz -/usr/local/share/man/man3/utt.gz - -~/.utt/*.conf (wszystko z /usr/local/etc/utt) Index: ld/app/dist/tarball/INSTALL =================================================================== --- _old/app/dist/tarball/INSTALL (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,5 +1,0 @@ -Here you can find some information about how to install utt. - -You should just unpack archive and then execute -make test -make install Index: ld/app/dist/tarball/Makefile =================================================================== --- _old/app/dist/tarball/Makefile (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,48 +1,0 @@ -# This makefile allows build tarball distribution for utt. - -# -# Some variables -# - -DIR=$(shell pwd) - -# Directory with utt binaries -ifndef UTT_DIST_DIR - UTT_DIST_DIR=${DIR} -endif - -# Where put result -ifndef UTT_DIST_OUTPUT - UTT_DIST_OUTPUT=${DIR} -endif - -# Common info about version and release -_UTT_VER=$(shell cat ../common/version.def) -_UTT_REL=$(shell cat ../common/release.def) - -# Temp vars -_TARBALL_ROOT=$(DIR)/utt-$(_UTT_VER).$(_UTT_REL) -_TAR_FILE_NAME=utt.$(_UTT_VER)_$(_UTT_REL).tar.gz - -#defualt task -.PHONY: default -default: - @echo Build directory: ${UTT_DIST_DIR} - @echo Output directory for tarball: ${UTT_DIST_OUTPUT} - mkdir -p ${_TARBALL_ROOT} - cp -fr ${UTT_DIST_DIR}/* ${_TARBALL_ROOT} - @# we add some extra files - @# config files - mkdir -p ${_TARBALL_ROOT}/cnf - mv ${_TARBALL_ROOT}/etc/utt/*.conf ${_TARBALL_ROOT}/cnf/ - ${DIR}/../common/prepare_conf.sh ${_TARBALL_ROOT}/cnf ${_TARBALL_ROOT}/etc/utt \~\\\/.local - rm -rf ${_TARBALL_ROOT}/cnf - cp ./INSTALL ${_TARBALL_ROOT}/ - cp ./Makefile.tarball ${_TARBALL_ROOT}/Makefile - cp ../files/* ${_TARBALL_ROOT}/ - - - tar -czf ${UTT_DIST_OUTPUT}/${_TAR_FILE_NAME} utt* - - rm -rf ${_TARBALL_ROOT} - Index: ld/app/dist/tarball/Makefile.tarball =================================================================== --- _old/app/dist/tarball/Makefile.tarball (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,18 +1,0 @@ -UTT_LIB_DIR=${HOME}/.local/lib/utt -UTT_SHARE_DIR=${HOME}/.local/share/utt -UTT_CONF_DIR=${HOME}/.utt - -.PHONY: install -install: - mkdir -p ${UTT_LIB_DIR} - cp -r lib/utt/* ${UTT_LIB_DIR} - mkdir -p ${UTT_SHARE_DIR} - cp -r share/utt/* ${UTT_SHARE_DIR} - mkdir -p ${UTT_CONF_DIR} - cp -r etc/utt/* ${UTT_CONF_DIR} - -.PHONY: uninstall -uninstall: - rm -r ${UTT_LIB_DIR} - rm -r ${UTT_SHARE_DIR} - rm -r ${CONF_DIR} Index: ld/app/dist/tarball/README =================================================================== --- _old/app/dist/tarball/README (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,6 +1,0 @@ -This directory contains Makefile, which allows to create tar.gz archive. - -To create archive, just write: -make - -Warning: you need define variable UTT_DIST_DIR. Index: ld/app/lib/attr.pm =================================================================== --- _old/app/lib/attr.pm (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,133 +1,0 @@ -package attr; - -use locale; -use strict; - -use Data::Dumper; - -our $pos_re = qr/(?:[[:upper:]]+)/; -our $attr_re = qr/(?:[[:upper:]]+)/; -our $val_re = qr/(?:[[:lower:][:digit:]+?!*-]|<[^>\n]+>)/; -our $av_re = qr/(?:$attr_re$val_re+)/; -our $avlist_re = qr/(?:$av_re+)/; -our $cat_re = qr/(?:$pos_re(?:\/$avlist_re)?)/; - -sub match(\@\@) -{ - my ($cat1,$avs1)= @{shift @_}; - my ($cat2,$avs2)= @{shift @_}; - - if($cat1 ne $cat2 && $cat1 ne '*' && $cat2 ne '*') - { - return 0; - } - else - { - ATTR:for my $attr (keys %$avs1) - { - if(exists $avs2->{$attr}) - { - for my $val (keys %{$avs1->{$attr}}) - { - next ATTR if $avs2->{$attr}->{$val}; - } - return 0; - last ATTR; - } - } - } - - return 1; -} - -sub agree(\@\@$) -{ - my $val1 = $_[0]->[1]->{$_[2]}; - my $val2 = $_[1]->[1]->{$_[2]}; - - return 1 if !$val1 || !$val2; - - for my $v (keys %$val1) - { - return 1 if exists $val2->{$v}; - } - return 0; -} - -# funkcja parse -# arg: deskrypcja -# warto¶æ: referencja do tablicy [, ], -# gdzie jest referencja do hasza, zawierajacego pary -# atrybut=>hasz warto¶ci (pary warto¶æ=>1), czyli np. - -# [ -# 'ADJ', -# { -# 'KOLEDZY' => { -# '' => 1, -# '' => 1, -# '' => 1 -# }, -# 'C' => { -# 'p' => 1, -# 'a' => 1, -# 'i' => 1 -# }, -# 'N' => { -# 'p' => 1 -# } -# } -# ]; - -sub parse ($) -{ - my ($dstr)=@_; - my $avs={}; - my ($cat,$attrlist) = split '/', $dstr; - ATTR: -# while( $attrlist =~ /([[:upper:]]+)((?:[[:lower:][:digit:]+?!*-]|<[^>\n]+>)+)/g ) - while( $attrlist =~ /($attr_re)($val_re+)/g ) - { - my ($attrstr,$valstr)=($1,$2); - my %vals; - while($valstr =~ /$val_re/g) - { - my $val = $&; - next ATTR if $val eq '*'; - $val =~ s/^<([[:lower:]])>$/$1/; - $vals{$val}=1; - } - - $avs->{$attrstr} = \%vals; # dlaczego to dziala? %vals jest lokalne - } - [$cat, $avs]; -} - -# funkcja unparse -# arg: jak warto¶æ parse -# warto¶æ: deskrypcja - napis - -sub unparse (\@) -{ - my ($cat,$avs)= @{shift @_}; - my $dstr=$cat; - my @attrs = keys %$avs; - if(@attrs) - { - $dstr .= '/'; - for my $attr ( sort @attrs ) - { - $dstr .= $attr . (join '', sort keys %{$avs->{$attr}}); - } - } - $dstr; -} - - -sub canonize ($) -{ - unparse @{parse @_[0]} ; -} - - -1; Index: ld/app/lib/seg.rb =================================================================== --- _old/app/lib/seg.rb (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,31 +1,0 @@ - -class Seg - - def initialize(s="") - @line=s - self - end - - def to_s - @line.chomp - end - - def set(s) - @line=s - self - end - - def field(key) - if key.class==Fixnum - @line.split[key-1] - elsif key.class==String - @line =~ /\s#{key}:(\S+)/; $1 - end - end - alias [] field - - def fields - @line.split - end - -end Index: ld/app/lib/ser.l.template =================================================================== --- _old/app/lib/ser.l.template (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,30 +1,0 @@ -%{ - #include - int n=0; -%} - -%% - -PATTERN { - int start, end, len; - char *lastseg, *tmp; - if(yytext[yyleng-1]!='\n') - {fprintf(stderr,"ser: pattern matches incomplete line\n"); exit(1);} - n++; - sscanf(yytext,"%d %d",&start,&len); - yytext[yyleng-1]='\0'; - if(tmp=strrchr(yytext,'\n')) - { - lastseg=tmp+1; - sscanf(lastseg,"%d %d", &end, &len); - } - else - end=start; - yytext[yyleng-1]='\n'; - printf("%04d 00 BOM * ser:%d\n",start,n); - ECHO; - printf("%04d 00 EOM * ser:%d\n",end+len,n); - } - - -.*\n DEFAULTACTION; Index: ld/app/lib/terms.m4 =================================================================== --- _old/app/lib/terms.m4 (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,52 +1,0 @@ -divert(-1) -#-------------------------------------------------------------------------- - -# Macros defined here may be used in pattern specifications -# You can modify this file according to your needs. - -# ENDOFSEGMENT and MORFIELD are macros expanded to, respectively, -# end of segment marker (dependes on the format: flattened or not) -# and the name of the annotation field containing morphological -# information (standard value is 'lem'). These values are controlled -# by programs using this file to expand search patterns (ser, grp, ...). - -# seg(type,form,annotation) - -define(`seg',`(\s*((\d+\s+)(\d+\s+)?)?dnl -ifelse($1, `',`(\S+)', `($1)')\s+dnl -ifelse($2, `',`(\S+)', `($2)')dnl -ifelse($3, `',`((\s+\S+)*)', `(\s+($3))')\s*ENDOFSEGMENT)') - -# form(f) - segment containing the form f - -define(`form', `seg(,$1)') - -# field(f) segment containing auxiliary field f - -define(`field', `seg(,,`(\S+\s+)*($1)(\s+\S+)*')') - -# word, space, punct, number segments (assuming W, S, P, N segment types) - -define(`space', `seg(`S',`$1')') -define(`word', `seg(`W',`$1')') -define(`punct', `seg(`P',`$1')') -define(`number', `seg(`N',`$1')') - -# macros specific to PMDB format - -define(`lexeme', `field(`MORFIELD:(\S+;)?$1,\S+')') -define(`cat', `field(`MORFIELD:\S+,$1([,;]\S+)?')') - - -# Place here your macro definitions. - - - - - - - - - -#-------------------------------------------------------------------------- -divert(0) Index: ld/app/share/cats.dgc =================================================================== --- _old/app/share/cats.dgc (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,696 +1,0 @@ -ADJ/DcNpCaGp -ADJ/DcNpCd -ADJ/DcNpCgl -ADJ/DcNpCi -ADJ/DcNpCnavGaifn -ADJ/DcNpCnvGp -ADJ/DcNsCaGi -ADJ/DcNsCaGpa -ADJ/DcNsCaiGf -ADJ/DcNsCavGf -ADJ/DcNsCdGpain -ADJ/DcNsCgdlGf -ADJ/DcNsCgGpain -ADJ/DcNsCilGpain -ADJ/DcNsCnavGn -ADJ/DcNsCnvGpai -ADJ/DpNpCaGp -ADJ/DpNpCd -ADJ/DpNpCgl -ADJ/DpNpCi -ADJ/DpNpCnavGaifn -ADJ/DpNpCnvGp -ADJ/DpNsCaGi -ADJ/DpNsCaGpa -ADJ/DpNsCaiGf -ADJ/DpNsCavGf -ADJ/DpNsCdGpain -ADJ/DpNsCgdlGf -ADJ/DpNsCgGpain -ADJ/DpNsCilGpain -ADJ/DpNsCnavGn -ADJ/DpNsCnvGpai -ADJ/DsNpCaGp -ADJ/DsNpCd -ADJ/DsNpCgl -ADJ/DsNpCi -ADJ/DsNpCnavGaifn -ADJ/DsNpCnvGp -ADJ/DsNsCaGi -ADJ/DsNsCaGpa -ADJ/DsNsCaiGf -ADJ/DsNsCavGf -ADJ/DsNsCdGpain -ADJ/DsNsCgdlGf -ADJ/DsNsCgGpain -ADJ/DsNsCilGpain -ADJ/DsNsCnavGn -ADJ/DsNsCnvGpai -ADJNUM/NpCaGp -ADJNUM/NpCd -ADJNUM/NpCgl -ADJNUM/NpCi -ADJNUM/NpCnavGaifn -ADJNUM/NpCnvGp -ADJNUM/NsCaGi -ADJNUM/NsCaGpa -ADJNUM/NsCaiGf -ADJNUM/NsCavGf -ADJNUM/NsCdGpain -ADJNUM/NsCgdlGf -ADJNUM/NsCgGpain -ADJNUM/NsCilGpain -ADJNUM/NsCnavGn -ADJNUM/NsCnvGpai -ADJPAP/NpCaGp -ADJPAP/NpCd -ADJPAP/NpCgl -ADJPAP/NpCi -ADJPAP/NpCnavGaifn -ADJPAP/NpCnvGp -ADJPAP/NsCaGi -ADJPAP/NsCaGpa -ADJPAP/NsCaiGf -ADJPAP/NsCavGf -ADJPAP/NsCdGpain -ADJPAP/NsCgdlGf -ADJPAP/NsCgGpain -ADJPAP/NsCilGpain -ADJPAP/NsCnavGn -ADJPAP/NsCnvGpai -ADJPP/NpCaGp -ADJPP/NpCd -ADJPP/NpCgl -ADJPP/NpCi -ADJPP/NpCnavGaifn -ADJPP/NpCnvGp -ADJPP/NsCaGi -ADJPP/NsCaGpa -ADJPP/NsCaiGf -ADJPP/NsCavGf -ADJPP/NsCdGpain -ADJPP/NsCgdlGf -ADJPP/NsCgGpain -ADJPP/NsCilGpain -ADJPP/NsCnavGn -ADJPP/NsCnvGpai -ADJPRO/NpCaGp -ADJPRO/NpCd -ADJPRO/NpCgl -ADJPRO/NpCi -ADJPRO/NpCnavGaifn -ADJPRO/NpCnvGp -ADJPRO/NsCaGi -ADJPRO/NsCaGpa -ADJPRO/NsCaiGf -ADJPRO/NsCavGf -ADJPRO/NsCdGpain -ADJPRO/NsCgdlGf -ADJPRO/NsCgGpain -ADJPRO/NsCilGpain -ADJPRO/NsCnavGn -ADJPRO/NsCnvGpai -ADJPRO/ZdNpCaGp -ADJPRO/ZdNpCd -ADJPRO/ZdNpCgl -ADJPRO/ZdNpCi -ADJPRO/ZdNpCnavGaifn -ADJPRO/ZdNpCnvGp -ADJPRO/ZdNsCaGi -ADJPRO/ZdNsCaGpa -ADJPRO/ZdNsCaiGf -ADJPRO/ZdNsCavGf -ADJPRO/ZdNsCdGpain -ADJPRO/ZdNsCgdlGf -ADJPRO/ZdNsCgGpain -ADJPRO/ZdNsCilGpain -ADJPRO/ZdNsCnavGn -ADJPRO/ZdNsCnvGpai -ADJPRO/ZgNpCaGp -ADJPRO/ZgNpCd -ADJPRO/ZgNpCgl -ADJPRO/ZgNpCi -ADJPRO/ZgNpCnavGaifn -ADJPRO/ZgNpCnvGp -ADJPRO/ZgNsCaGi -ADJPRO/ZgNsCaGpa -ADJPRO/ZgNsCaiGf -ADJPRO/ZgNsCavGf -ADJPRO/ZgNsCdGpain -ADJPRO/ZgNsCgdlGf -ADJPRO/ZgNsCgGpain -ADJPRO/ZgNsCilGpain -ADJPRO/ZgNsCnavGn -ADJPRO/ZgNsCnvGpai -ADJPRO/ZiNpCaGp -ADJPRO/ZiNpCd -ADJPRO/ZiNpCgl -ADJPRO/ZiNpCi -ADJPRO/ZiNpCnavGaifn -ADJPRO/ZiNpCnvGp -ADJPRO/ZiNsCaGi -ADJPRO/ZiNsCaGpa -ADJPRO/ZiNsCaiGf -ADJPRO/ZiNsCavGf -ADJPRO/ZiNsCdGpain -ADJPRO/ZiNsCgdlGf -ADJPRO/ZiNsCgGpain -ADJPRO/ZiNsCilGpain -ADJPRO/ZiNsCnavGn -ADJPRO/ZiNsCnvGpai -ADJPRO/ZnNpCaGp -ADJPRO/ZnNpCd -ADJPRO/ZnNpCgl -ADJPRO/ZnNpCi -ADJPRO/ZnNpCnavGaifn -ADJPRO/ZnNpCnvGp -ADJPRO/ZnNsCaGi -ADJPRO/ZnNsCaGpa -ADJPRO/ZnNsCaiGf -ADJPRO/ZnNsCavGf -ADJPRO/ZnNsCdGpain -ADJPRO/ZnNsCgdlGf -ADJPRO/ZnNsCgGpain -ADJPRO/ZnNsCilGpain -ADJPRO/ZnNsCnavGn -ADJPRO/ZnNsCnvGpai -ADJPRO/ZqNpCaGp -ADJPRO/ZqNpCd -ADJPRO/ZqNpCgl -ADJPRO/ZqNpCi -ADJPRO/ZqNpCnavGaifn -ADJPRO/ZqNpCnvGp -ADJPRO/ZqNsCaGi -ADJPRO/ZqNsCaGpa -ADJPRO/ZqNsCaiGf -ADJPRO/ZqNsCavGf -ADJPRO/ZqNsCdGpain -ADJPRO/ZqNsCgdlGf -ADJPRO/ZqNsCgGpain -ADJPRO/ZqNsCilGpain -ADJPRO/ZqNsCnavGn -ADJPRO/ZqNsCnvGpai -ADJPRO/ZqrNpCaGp -ADJPRO/ZqrNpCd -ADJPRO/ZqrNpCgl -ADJPRO/ZqrNpCi -ADJPRO/ZqrNpCnavGaifn -ADJPRO/ZqrNpCnvGp -ADJPRO/ZqrNsCaGi -ADJPRO/ZqrNsCaGpa -ADJPRO/ZqrNsCaiGf -ADJPRO/ZqrNsCavGf -ADJPRO/ZqrNsCdGpain -ADJPRO/ZqrNsCgdlGf -ADJPRO/ZqrNsCgGpain -ADJPRO/ZqrNsCilGpain -ADJPRO/ZqrNsCnavGn -ADJPRO/ZqrNsCnvGpai -ADJPRO/ZsNpCaGp -ADJPRO/ZsNpCd -ADJPRO/ZsNpCgl -ADJPRO/ZsNpCi -ADJPRO/ZsNpCnavGaifn -ADJPRO/ZsNpCnvGp -ADJPRO/ZsNsCaGi -ADJPRO/ZsNsCaGpa -ADJPRO/ZsNsCaiGf -ADJPRO/ZsNsCavGf -ADJPRO/ZsNsCdGpain -ADJPRO/ZsNsCgdlGf -ADJPRO/ZsNsCgGpain -ADJPRO/ZsNsCilGpain -ADJPRO/ZsNsCnavGn -ADJPRO/ZsNsCnvGpai -ADJPRP/NpCaGp -ADJPRP/NpCd -ADJPRP/NpCgl -ADJPRP/NpCi -ADJPRP/NpCnavGaifn -ADJPRP/NpCnvGp -ADJPRP/NsCaGi -ADJPRP/NsCaGpa -ADJPRP/NsCaiGf -ADJPRP/NsCavGf -ADJPRP/NsCdGpain -ADJPRP/NsCgdlGf -ADJPRP/NsCgGpain -ADJPRP/NsCilGpain -ADJPRP/NsCnavGn -ADJPRP/NsCnvGpai -ADVANP -ADV/Dc -ADV/Dp -ADV/Ds -ADVNUM -ADVPRO -ADVPRO/Zd -ADVPRO/Zi -ADVPRO/Zn -ADVPRO/Zq -ADVPRO/Zqr -ADVPRO/Zr -ADVPRP -APP -BYC/Vb -BYC/VpMcNpP1Gaifn -BYC/VpMcNpP1Gp -BYC/VpMcNpP2Gaifn -BYC/VpMcNpP2Gp -BYC/VpMcNpP3Gaifn -BYC/VpMcNpP3Gp -BYC/VpMcNsP1Gf -BYC/VpMcNsP1Gpai -BYC/VpMcNsP2Gf -BYC/VpMcNsP2Gpai -BYC/VpMcNsP3Gf -BYC/VpMcNsP3Gn -BYC/VpMcNsP3Gpai -BYC/VpMdTaNpP1Gaifn -BYC/VpMdTaNpP1Gp -BYC/VpMdTaNpP2Gaifn -BYC/VpMdTaNpP2Gp -BYC/VpMdTaNpP3Gaifn -BYC/VpMdTaNpP3Gp -BYC/VpMdTaNsP1Gf -BYC/VpMdTaNsP1Gpai -BYC/VpMdTaNsP2Gf -BYC/VpMdTaNsP2Gpai -BYC/VpMdTaNsP3Gf -BYC/VpMdTaNsP3Gn -BYC/VpMdTaNsP3Gpai -BYC/VpMdTrfNpP1 -BYC/VpMdTrfNpP2 -BYC/VpMdTrfNpP3 -BYC/VpMdTrfNsP1 -BYC/VpMdTrfNsP2 -BYC/VpMdTrfNsP3 -BYC/VpMiNpP1 -BYC/VpMiNpP2 -BYC/VpMiNsP2 -CONJ -EXCL -N/GaNpCa -N/GaNpCd -N/GaNpCg -N/GaNpCi -N/GaNpCl -N/GaNpCn -N/GaNpCv -N/GaNsCa -N/GaNsCd -N/GaNsCg -N/GaNsCi -N/GaNsCl -N/GaNsCn -N/GaNsCv -N/GfNpCa -N/GfNpCd -N/GfNpCg -N/GfNpCi -N/GfNpCl -N/GfNpCn -N/GfNpCv -N/GfNsCa -N/GfNsCd -N/GfNsCg -N/GfNsCi -N/GfNsCl -N/GfNsCn -N/GfNsCv -N/GiNpCa -N/GiNpCd -N/GiNpCg -N/GiNpCi -N/GiNpCl -N/GiNpCn -N/GiNpCv -N/GiNsCa -N/GiNsCd -N/GiNsCg -N/GiNsCi -N/GiNsCl -N/GiNsCn -N/GiNsCv -N/GnNpCa -N/GnNpCd -N/GnNpCg -N/GnNpCi -N/GnNpCl -N/GnNpCn -N/GnNpCv -N/GnNsCa -N/GnNsCd -N/GnNsCg -N/GnNsCi -N/GnNsCl -N/GnNsCn -N/GnNsCv -N/G?NpCa -N/G*NpCa -N/G?NpCd -N/G*NpCd -N/G?NpCg -N/G*NpCg -N/G?NpCi -N/G*NpCi -N/G?NpCl -N/G*NpCl -N/G?NpCn -N/G*NpCn -N/G?NpCv -N/G*NpCv -N/G?NsCa -N/G?NsCd -N/G?NsCg -N/G?NsCi -N/G?NsCl -N/G?NsCn -N/G?NsCv -N/GpNpCa -N/GpNpCd -N/GpNpCg -N/GpNpCi -N/GpNpCl -N/GpNpCn -N/GpNpCv -N/GpNsCa -N/GpNsCd -N/GpNsCg -N/GpNsCi -N/GpNsCl -N/GpNsCn -N/GpNsCv -NPRO/ZdGnNsCa -NPRO/ZdGnNsCd -NPRO/ZdGnNsCg -NPRO/ZdGnNsCi -NPRO/ZdGnNsCl -NPRO/ZdGnNsCn -NPRO/ZgGnNsCa -NPRO/ZgGnNsCd -NPRO/ZgGnNsCg -NPRO/ZgGnNsCi -NPRO/ZgGnNsCl -NPRO/ZgGnNsCn -NPRO/ZgGpNpCa -NPRO/ZgGpNpCd -NPRO/ZgGpNpCg -NPRO/ZgGpNpCi -NPRO/ZgGpNpCl -NPRO/ZgGpNpCn -NPRO/ZiGnNsCa -NPRO/ZiGnNsCd -NPRO/ZiGnNsCg -NPRO/ZiGnNsCi -NPRO/ZiGnNsCl -NPRO/ZiGnNsCn -NPRO/ZiGpNsCa -NPRO/ZiGpNsCd -NPRO/ZiGpNsCg -NPRO/ZiGpNsCi -NPRO/ZiGpNsCl -NPRO/ZiGpNsCn -NPRO/ZnGnNsCa -NPRO/ZnGnNsCd -NPRO/ZnGnNsCg -NPRO/ZnGnNsCi -NPRO/ZnGnNsCl -NPRO/ZnGnNsCn -NPRO/ZnGpNsCa -NPRO/ZnGpNsCd -NPRO/ZnGpNsCg -NPRO/ZnGpNsCi -NPRO/ZnGpNsCl -NPRO/ZnGpNsCn -NPRO/ZpGaifnNpCa -NPRO/ZpGaifnNpCd -NPRO/ZpGaifnNpCg -NPRO/ZpGaifnNpCi -NPRO/ZpGaifnNpCl -NPRO/ZpGaifnNpCn -NPRO/ZpGfNsCa -NPRO/ZpGfNsCd -NPRO/ZpGfNsCg -NPRO/ZpGfNsCi -NPRO/ZpGfNsCl -NPRO/ZpGfNsCn -NPRO/ZpGnNsCa -NPRO/ZpGnNsCd -NPRO/ZpGnNsCg -NPRO/ZpGnNsCi -NPRO/ZpGnNsCl -NPRO/ZpGnNsCn -NPRO/ZpG*NpCa -NPRO/ZpG*NpCd -NPRO/ZpG*NpCg -NPRO/ZpG*NpCi -NPRO/ZpG*NpCl -NPRO/ZpG*NpCn -NPRO/ZpG*NsCa -NPRO/ZpG*NsCd -NPRO/ZpG*NsCg -NPRO/ZpG*NsCi -NPRO/ZpG*NsCl -NPRO/ZpG*NsCn -NPRO/ZpGpaiNsCa -NPRO/ZpGpaiNsCd -NPRO/ZpGpaiNsCg -NPRO/ZpGpaiNsCi -NPRO/ZpGpaiNsCl -NPRO/ZpGpaiNsCn -NPRO/ZpGpNpCa -NPRO/ZpGpNpCd -NPRO/ZpGpNpCg -NPRO/ZpGpNpCi -NPRO/ZpGpNpCl -NPRO/ZpGpNpCn -NPRO/ZqGnNsCa -NPRO/ZqGnNsCd -NPRO/ZqGnNsCg -NPRO/ZqGnNsCi -NPRO/ZqGnNsCl -NPRO/ZqGnNsCn -NPRO/ZqGpNsCa -NPRO/ZqGpNsCd -NPRO/ZqGpNsCg -NPRO/ZqGpNsCi -NPRO/ZqGpNsCl -NPRO/ZqGpNsCn -NPRO/ZqrGnNsCa -NPRO/ZqrGnNsCd -NPRO/ZqrGnNsCg -NPRO/ZqrGnNsCi -NPRO/ZqrGnNsCl -NPRO/ZqrGnNsCn -NPRO/ZqrGpNsCa -NPRO/ZqrGpNsCd -NPRO/ZqrGpNsCg -NPRO/ZqrGpNsCi -NPRO/ZqrGpNsCl -NPRO/ZqrGpNsCn -NPRO/ZxG*N*Ca -NPRO/ZxG*N*Cd -NPRO/ZxG*N*Cg -NPRO/ZxG*N*Ci -NPRO/ZxG*N*Cl -NUMCOL/Ca -NUMCOL/Cd -NUMCOL/Cg -NUMCOL/Ci -NUMCOL/Cl -NUMCOL/Cn -NUMCRD/Ca -NUMCRD/CaGaifn -NUMCRD/CaGain -NUMCRD/CaGf -NUMCRD/CaGp -NUMCRD/Cd -NUMCRD/Cg -NUMCRD/Ci -NUMCRD/CiGf -NUMCRD/CiGpain -NUMCRD/Cl -NUMCRD/Cn -NUMCRD/CnGaifn -NUMCRD/CnGain -NUMCRD/CnGf -NUMCRD/CnGp -NUMCRD/ZiCaGaifn -NUMCRD/ZiCaGain -NUMCRD/ZiCaGf -NUMCRD/ZiCaGp -NUMCRD/ZiCd -NUMCRD/ZiCg -NUMCRD/ZiCi -NUMCRD/ZiCiGf -NUMCRD/ZiCiGpain -NUMCRD/ZiCl -NUMCRD/ZiCnGaifn -NUMCRD/ZiCnGain -NUMCRD/ZiCnGf -NUMCRD/ZiCnGp -NUMCRD/ZqiCaGaifn -NUMCRD/ZqiCaGp -NUMCRD/ZqiCd -NUMCRD/ZqiCg -NUMCRD/ZqiCi -NUMCRD/ZqiCl -NUMCRD/ZqiCnGaifn -NUMCRD/ZqiCnGp -NUMORD/NpCaGp -NUMORD/NpCd -NUMORD/NpCgl -NUMORD/NpCi -NUMORD/NpCnavGaifn -NUMORD/NpCnvGp -NUMORD/NsCaGi -NUMORD/NsCaGpa -NUMORD/NsCaiGf -NUMORD/NsCavGf -NUMORD/NsCdGpain -NUMORD/NsCgdlGf -NUMORD/NsCgGpain -NUMORD/NsCilGpain -NUMORD/NsCnavGn -NUMORD/NsCnvGpai -NUMPAR -NUMPAR/Dc -NUMPAR/Dp -NUMPAR/Ds -NUMPAR/Ns -NUMPAR/NsGf -NUMPAR/NsGpain -NV/Ca -NV/Cd -NV/Cg -NV/Ci -NV/Cl -NV/Cn -ONO -P -PART -P/Ca -P/Cai -P/Cal -P/Cd -P/Cg -P/Cga -P/Cgai -P/Cgd -P/Cgi -P/Ci -P/Cl -PPRO/Zp -V/AiVb -V/AiViTa -V/AiVpMcNpP1Gaifn -V/AiVpMcNpP1Gp -V/AiVpMcNpP2Gaifn -V/AiVpMcNpP2Gp -V/AiVpMcNpP3Gaifn -V/AiVpMcNpP3Gp -V/AiVpMcNsP1Gf -V/AiVpMcNsP1Gpai -V/AiVpMcNsP2Gf -V/AiVpMcNsP2Gpai -V/AiVpMcNsP3Gf -V/AiVpMcNsP3Gn -V/AiVpMcNsP3Gpai -V/AiVpMdTaNpP1Gaifn -V/AiVpMdTaNpP1Gp -V/AiVpMdTaNpP2Gaifn -V/AiVpMdTaNpP2Gp -V/AiVpMdTaNpP3Gaifn -V/AiVpMdTaNpP3Gp -V/AiVpMdTaNsP1Gf -V/AiVpMdTaNsP1Gpai -V/AiVpMdTaNsP2Gf -V/AiVpMdTaNsP2Gpai -V/AiVpMdTaNsP3Gf -V/AiVpMdTaNsP3Gn -V/AiVpMdTaNsP3Gpai -V/AiVpMdTrfNpP1 -V/AiVpMdTrfNpP2 -V/AiVpMdTrfNpP3 -V/AiVpMdTrfNsP1 -V/AiVpMdTrfNsP2 -V/AiVpMdTrfNsP3 -V/AiVpMiNpP1 -V/AiVpMiNpP2 -V/AiVpMiNsP2 -V/ApVb -V/ApViTa -V/ApVpMcNpP1Gaifn -V/ApVpMcNpP1Gp -V/ApVpMcNpP2Gaifn -V/ApVpMcNpP2Gp -V/ApVpMcNpP3Gaifn -V/ApVpMcNpP3Gp -V/ApVpMcNsP1Gf -V/ApVpMcNsP1Gpai -V/ApVpMcNsP2Gf -V/ApVpMcNsP2Gpai -V/ApVpMcNsP3Gf -V/ApVpMcNsP3Gn -V/ApVpMcNsP3Gpai -V/ApVpMdTaNpP1Gaifn -V/ApVpMdTaNpP1Gp -V/ApVpMdTaNpP2Gaifn -V/ApVpMdTaNpP2Gp -V/ApVpMdTaNpP3Gaifn -V/ApVpMdTaNpP3Gp -V/ApVpMdTaNsP1Gf -V/ApVpMdTaNsP1Gpai -V/ApVpMdTaNsP2Gf -V/ApVpMdTaNsP2Gpai -V/ApVpMdTaNsP3Gf -V/ApVpMdTaNsP3Gn -V/ApVpMdTaNsP3Gpai -V/ApVpMdTrfNpP1 -V/ApVpMdTrfNpP2 -V/ApVpMdTrfNpP3 -V/ApVpMdTrfNsP1 -V/ApVpMdTrfNsP2 -V/ApVpMdTrfNsP3 -V/ApVpMiNpP1 -V/ApVpMiNpP2 -V/ApVpMiNsP2 -V/GiVb -V/GiViTa -V/GiVpMcNpP1Gaifn -V/GiVpMcNpP1Gp -V/GiVpMcNpP2Gaifn -V/GiVpMcNpP2Gp -V/GiVpMcNpP3Gaifn -V/GiVpMcNpP3Gp -V/GiVpMcNsP1Gf -V/GiVpMcNsP1Gpai -V/GiVpMcNsP2Gf -V/GiVpMcNsP2Gpai -V/GiVpMcNsP3Gf -V/GiVpMcNsP3Gn -V/GiVpMcNsP3Gpai -V/GiVpMdTaNpP1Gaifn -V/GiVpMdTaNpP1Gp -V/GiVpMdTaNpP2Gaifn -V/GiVpMdTaNpP2Gp -V/GiVpMdTaNpP3Gaifn -V/GiVpMdTaNpP3Gp -V/GiVpMdTaNsP1Gf -V/GiVpMdTaNsP1Gpai -V/GiVpMdTaNsP2Gf -V/GiVpMdTaNsP2Gpai -V/GiVpMdTaNsP3Gf -V/GiVpMdTaNsP3Gn -V/GiVpMdTaNsP3Gpai -V/GiVpMdTrfNpP1 -V/GiVpMdTrfNpP2 -V/GiVpMdTrfNpP3 -V/GiVpMdTrfNsP1 -V/GiVpMdTrfNsP2 -V/GiVpMdTrfNsP3 -V/GiVpMiNpP1 -V/GiVpMiNpP2 -V/GiVpMiNsP2 -VNI Index: ld/app/share/gram.dgc =================================================================== --- _old/app/share/gram.dgc (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,126 +1,0 @@ -#FLAG REL - -#UP REL - -#ORDER * pcmpl -#ORDER .. -#ORDER subj .. * .. cmpl -#ORDER refl .. * -#ORDER * refl - -#CONSTR cmpl_g => ~cmpl_a -#CONSTR cmpl_inf => ~(cmpl_g|cmpl_d|cmpl_a|cmpl_p|cmpl_ze|cmpl_s) -#CONSTR subj_pred => subj -#constr cmpl_pred => cmpl - - - -#subj -ROLE subj # deklaracja roli (typ zaleznosci) podmiot -AGR subj N # zgodnosc podrzednika z nadrzednikiem co do liczby -AGR subj G # zgodnosc podrzednika z nadrzednikiem co do rodzaju -GOV subj */Cn # wymaganie by podrzednik byl w mianowniku - -# pary kategorii, jakie mozna polaczyc zaleznoscia typu podmiot - -# nadrzednik podrzednik -LINK V/VpP3,BYC/VpP3 N,NPRO subj - -# (przecinek znaczy lub) - -ROLE cmpl_ga # dopelnienie w bierniku/dopelniaczu -ROLE cmpl_d # w celowniku -ROLE cmpl_i # w narzedniku -ROLE cmpl_inf # w bezokoliczniku -ROLE cmpl_s # bedace zdaniem -ROLE cmpl_ze # bedace zdaniem poprzedzonym 'ze' -ROLE aux # -ROLE mod # modyfikator (okolicznik/przydawka) (niewymagane określenie) (biały kot) -ROLE prep # modyfikator w postaci frazy przyimkowej -ROLE pcmpl # dopełnienie przyimka (wymagany rzeczownik) -ROLE ccmpl # dopełnienie spójnika (wymagany drugi człon konstrukcji spójnikowej) -ROLE poss # np. ksiÄ -ÅŒka Marii, ojciec kolegi -ROLE restr # (bardzo <- duÅŒy) -ROLE part # partykuła -ROLE coord # koordynacja (powiÄ -zanie pierwszego członu konstrukcji współrzędnej - # ze spójnikiem współrzędnym centralnym ( Oto [pies -> i] kot. ) - - -AGR aux N -AGR aux G - -AGR mod N -AGR mod C -AGR mod G - -AGR pcmpl C - -GOV cmpl_ga */Cga -GOV cmpl_d */Cd -GOV cmpl_i */Ci -GOV poss */Cg - -SGL subj -SGL cmpl_ga -SGL cmpl_d -SGL cmpl_i -SGL cmpl_inf -SGL aux -SGL pcmpl -SGL ccmpl -SGL poss -SGL restr - -REQ P pcmpl -REQ CONJ ccmpl - -RIGHT pcmpl -RIGHT ccmpl -RIGHT cmpl_ze -RIGHT poss - - -#cmpl_* -LINK V,ADVPRP,ADVANP,ADJPRP,ADJPAP,NV N,NPRO cmpl_ga -LINK V,ADVPRP,ADVANP,ADJPRP,ADJPAP,NV N,NPRO cmpl_d -LINK V,ADVPRP,ADVANP,ADJPRP,ADJPAP,NV N,NPRO cmpl_i -LINK V,ADVPRP,ADVANP,ADJPRP,ADJPAP,NV V/Vb cmpl_inf -LINK V,ADVPRP,ADVANP,ADJPRP,ADJPAP,NV CONJ cmpl_ze - -#aux -#czas przyszly analityczny -LINK BYC/VpMdTf V/AiVpP3,V/AiVb aux -#czas zaprzeszly(?) -LINK BYC/VpMc V/VpP3 aux -#BYC jako lacznik w (jest bialy, jest zaszlachtowany, jest pilotem) -LINK BYC ADJPAP/Cn,ADJ/Cn,N/Ci aux - -#mod - -LINK V ADV,ADVPRP,ADVANP,ADVPRO mod -LINK N,NV ADJ,ADJPAP,ADJPRP,ADJPRO mod - - -#prep -LINK N,V P prep - -#pcmpl -LINK P N,NV pcmpl - - -#poss -LINK N N,NV,NPRO poss - - -#ccmpl -LINK CONJ V/Vp ccmpl - - -#restr -LINK ADJ ADV restr - - -#part -LINK V PART part Index: ld/app/share/weights.kor =================================================================== --- _old/app/share/weights.kor (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,21 +1,0 @@ -%stdcor 1 -%xchg 1 -¿ rz 0.5 -ch h 0.5 -u ó 0.5 -u o 0.75 -om ¹ 0.5 -om a 0.75 -en ê 0.5 -en ê 0.75 -a ¹ 0.25 -c æ 0.25 -e ê 0.25 -l ³ 0.25 -n ñ 0.25 -o ó 0.25 -s ¶ 0.25 -z ¿ 0.25 -z Œ 0.25 -x Œ 0.30 - Index: ld/app/src/common/Makefile =================================================================== --- _old/app/src/common/Makefile (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,8 +1,0 @@ -# main: cmdline.c main_template.cc -# g++ -o main cmdline.c common.cc main_template.cc - -# cmdline.c cmdline.h : cmdline.ggo -# gengetopt -i cmdline.ggo - -# cmdline.ggo: cmdline_common.ggo cmdline_program.ggo -# cat cmdline_common.ggo cmdline_program.ggo > cmdline.ggo Index: ld/app/src/common/README =================================================================== --- _old/app/src/common/README (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,18 +1,0 @@ -Propozycja ujednolicenia dzialania klocka na poziomie -funkcji main. Parametry meta - zdefiniowane dla -wszystkich, poza tok, programow, definiujace ich zachowanie -w systemie klockow. - -cmdline_common.ggo - deklaracje parametrow meta - -cmdline_program.ggo - przyklad deklaracji parametrow programu - nazwa docelowa np. cmdline_guess.ggo - -common.cc - zmienne globalne zawierajace informacje - przekazane przez parametry meta -common.h - -main_template.cc - szkielet funkcji main - -Makefile - sposob kompilacji - Index: ld/app/src/common/cmdline_common.ggo =================================================================== --- _old/app/src/common/cmdline_common.ggo (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,34 +1,0 @@ -#section "Common UTT options" - - -option "input" f "Input file" string no - -option "output" o "Output file for succesfully processed segments" string no - -option "fail" e "Output file for unsuccesfully processed segments " string no - -option "only-fail" - "Print only segments the program failed to process" flag off hidden - -option "no-fail" - "Print only segments the program processed" flag off hidden - -option "copy" c "Copy succesfully processed segments to standard output" flag off - -option "process" p "Process segments with this tag" string no multiple - -option "select" s "Select only segments with this field" string no multiple - -option "ignore" S "Select only segments without this field" string no multiple - -option "output-field" O "Output field name" string no - -option "input-field" I "Input field name" string no multiple - -option "interactive" i "Toggle interactive mode" flag off - -option "config" - "Configuration file" string typestr="FILENAME" no - -option "one-field" 1 "Print all results in one segments (creates ambiguous annotation)" flag off - -option "one-line" - "Print annotation alternatives as additional fields" flag off - -option "language" - "Language." string no Index: ld/app/src/common/cmdline_program.ggo =================================================================== --- _old/app/src/common/cmdline_program.ggo (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,5 +1,0 @@ -package "guess" -version "0.1" - -option "color" l "Show guessed descriptions in colour." flag off - Index: ld/app/src/common/common.cc =================================================================== --- _old/app/src/common/common.cc (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,230 +1,0 @@ -#include -#include -#include -#include -#include -#include "common.h" - -#include -#include - -FILE* inputf=stdin; -FILE* outputf=stdout; -FILE* failedf=stdout; -bool copy_processed=0; -bool one_field=false; -bool one_line=false; -char output_field_prefix[FIELD_PREFIX_MAXLEN]; -char input_field_prefix[FIELD_PREFIX_MAXLEN]; - -extern int argc; -extern char **argv; - - -// tilde (home dir) expansion in path -int expand_path(char* inpath, char* outpath) -{ - if(inpath[0]=='~') - sprintf(outpath,"%s%s",getenv("HOME"),inpath+1); - else - strcpy(outpath,inpath); - return 0; // no problem -} - - - - -void set_program_name(char program_name[], char* argv0) -{ - if (char* p_name = strrchr(argv0, '/')) - strcpy(program_name,p_name+1); - else - strcpy(program_name,argv0); -} - - - -extern void process_config_files(gengetopt_args_info* args, char* argv0) -{ - - char program_name[256]; - char config_file[256]; - char config_file_tmp[256]; - - set_program_name(program_name,argv0); - - // obsługa pliku konfiguracyjnego podanego w linii komend - if (args->config_given) { - if (file_accessible(args->config_arg) == 0) { - if (cmdline_parser_configfile(args->config_arg, - args, - 0, // 0 - nie nadpisuj wartości parametrów - 0, // 0 - nie inicjuj - 0) != 0) { - fprintf(stderr, "Error in config file (%s)\n", args->config_arg); - exit(1); - } - } - } - - if(args->one_line_given && !one_line) one_line=true, one_field=false; - if(args->one_field_given && !one_field) one_line=false, one_field=true; - - // obsluga pliku konfiguracyjnego uzytkownika dla programu - sprintf(config_file_tmp, "%s/%s.conf", USER_CONFIG_DIR, program_name); - expand_path(config_file_tmp, config_file); - if (file_accessible(config_file) == 0) { - if (cmdline_parser_configfile(config_file, - args, - 0, // 0 - nie nadpisuj danych - 0, // 0 - nie inicjuj struktury - 0) != 0) { - fprintf(stderr, "Error in config file (%s)\n", config_file); - exit(1); - } - } - - if(args->one_line_given && !one_line) one_line=true, one_field=false; - if(args->one_field_given && !one_field) one_line=false, one_field=true; - - - // obsluga pliku konfiguracyjnego uzytkownika globalnego - sprintf(config_file_tmp, "%s/utt.conf", USER_CONFIG_DIR); - expand_path(config_file_tmp, config_file); - if (file_accessible(config_file) == 0) { - if (cmdline_parser_configfile(config_file, - args, - 0, // 0 - nie nadpisuj danych - 0, // 0 - nie inicjuj struktury - 0) != 0) { - fprintf(stderr, "Error in config file (%s)\n", config_file); - exit(1); - } - } - - if(args->one_line_given && !one_line) one_line=true, one_field=false; - if(args->one_field_given && !one_field) one_line=false, one_field=true; - - - - // obsluga systemowego pliku konfiguracyjnego dla programu - sprintf(config_file, "%s/%s.conf", SYSTEM_CONFIG_DIR, program_name); - if (file_accessible(config_file) == 0) { - if (cmdline_parser_configfile(config_file, - args, - 0, // 0 - nie zmieniaj danych wczesniejszych - 0, // 0 - nie inicjuj struktury - 0 // 0 - nie sprawdzaj wymaganych parametrow - ) != 0) { - fprintf(stderr, "Error in config file (%s)\n", config_file); - exit(1); - } - } - - if(args->one_line_given && !one_line) one_line=true, one_field=false; - if(args->one_field_given && !one_field) one_line=false, one_field=true; - - - // obsluga systemowego pliku konfiguracyjnego globalnego - sprintf(config_file, "%s/utt.conf", SYSTEM_CONFIG_DIR); - if (file_accessible(config_file) == 0) { - if (cmdline_parser_configfile(config_file, - args, - 0, // 0 - nie zmieniaj danych wczesniejszych - 0, // 0 - nie inicjuj struktury - 0 // 0 - nie sprawdzaj wymaganych parametrow - ) != 0) { - fprintf(stderr, "Error in config file (%s)\n", config_file); - exit(1); - } - } - - if(args->one_line_given && !one_line) one_line=true, one_field=false; - if(args->one_field_given && !one_field) one_line=false, one_field=true; - -} - - -void process_common_options(gengetopt_args_info* args, char* argv0) -{ - char program_name[256]; - - set_program_name(program_name,argv0); - - setlocale(LC_CTYPE,""); - setlocale(LC_COLLATE, ""); - - if(args->help_given) - cmdline_parser_print_help (); - - if(args->input_given) - if(!(inputf=fopen(args->input_arg,"r"))) - { - fprintf(stderr,"No such file: %s.\n", args->input_arg); - exit(1); - } - - if(args->output_given) - if(!(outputf=fopen(args->output_arg,"w"))) - { - fprintf(stderr,"Cannot open output file: %s.\n", args->output_arg); - exit(1); - } - - if(args->fail_given) - if(!(failedf=fopen(args->fail_arg,"w"))) - { - fprintf(stderr,"Cannot open output file: %s.\n", args->fail_arg); - exit(1); - } - - if(args->input_field_given) - fieldprefix(args->input_field_arg[0],input_field_prefix); - else - strcpy(input_field_prefix, "4"); - - if(args->output_field_given) - fieldprefix(args->output_field_arg,output_field_prefix); - else - sprintf(output_field_prefix, "%s%c", program_name, INFIELD_SEP); - - if ((args->copy_given)) - copy_processed=true; -} - -// sprawdza istnienie pliku -int file_accessible(const char* path) { - return access(path, R_OK); -} - -// sprawdza istnienie pliku konfiguracyjnego -int config_file_exists(const char* dir, const char* filename) { - struct stat dir_stat; - struct stat file_stat; - - char* path = (char*)malloc(strlen(dir) + strlen(filename) + 2); // + '\0' + '/' - - sprintf(path, "%s/%s", dir, filename); - - if (stat(dir, &dir_stat) != 0) - return -1; - - if (stat(path, &file_stat) != 0) - return -1; - - if (!S_ISDIR(dir_stat.st_mode)) - return -1; // katalog nie jest katalogiem - - if (!S_ISREG(file_stat.st_mode)) - return -1; // plik konfiguracyjny nie jest plikiem - - if (access(dir, X_OK) != 0) - return -1; // nie mamy prawa zmienic katalogu - - if (access(path, R_OK) != 0) - return -1; // nie mamy prawa odczytu pliku - - free(path); - - return 0; -} Index: ld/app/src/common/common.h =================================================================== --- _old/app/src/common/common.h (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,467 +1,0 @@ -#ifndef __COMMON_H -#define __COMMON_H - -#include -#include -#include -#include - -#include "../lib/const.h" - -#ifndef _CMDLINE_FILE -#error _CMDLINE_FILE constant not defined! -#else -#include _CMDLINE_FILE -#endif - - -/************************************************** - * Stale dotyczace wejscia/wyjscia - */ - -#define EMPTYFORM '*' -#define INFIELD_SEP ':' -#define MAXAUX 16 -#define FIELD_SEP " \t\n" -#define FIELD_PREFIX_MAXLEN 32 - - -// katalogi z plikami konfiguracyjnymi -// nowe -// stare - do wyrzucenia -// #define CONFIG_DIR ".utt/conf" - -// nazwa zmiennej okreslajaca sciezke do danych - -// #define UTT_DIR_VAR "UTT_DIR" - -// sciezka do plikow z danymi (np UTT_DIR/pliki) wzgledem $HOME! - -// #define UTT_DIR_DEFAULT ".utt/pl/" - -/**************************************************/ - - -extern FILE* inputf; -extern FILE* outputf; -extern FILE* failedf; - -extern char* input_filename; -extern char* output_filename; -extern char* failed_filename; -extern bool one_line; -extern bool one_field; - -extern char input_field_prefix[]; -extern char output_field_prefix[]; - -extern bool copy_processed; -extern bool append_output; -extern bool append_failed; - -//sciezka do katalogu z danymi -extern char utt_dir[]; - -extern void process_common_options(gengetopt_args_info* args, char* argv0); -extern void process_config_files(gengetopt_args_info* args, char* argv0); - -extern int expand_path(char* inpath, char* outpath); - -/************************************************** - * problems with casing */ -// sprawdzenie wielkosci liter -// warto¶Ê zwracana: -// 0 - wszystkie ma³e litery -// 1 - pierwsza wielka, reszta male -// 2 - wszystkie wielkie -// 3 - inne -inline int casing(char* s) -{ - int ret = isupper(*s) ? 1 : 0; - while(*++s != '\0') - { - if(isupper(*s)) - { - if(ret==1) ret=2; - else if(ret==0) ret=3; - } - else - { - if(ret==2) ret=3; - } - } - return ret; -} - -// -inline void tolowers(char* s, char* d) -{ - *d=tolower(*s); - while(*s != '\0') * ++d = tolower(* ++s); -} - - -// przepisuje s do d -// nadajac wielko¶Ê liter zgodnie z warto¶ci± casing -// casing - warto¶Ê zwracana przez casing() -// je¶li casing==3 przepisuje bez zmian (za ma³o informacji) -inline void restorecasing(char *s, char *d, int casing) -{ - switch(casing) - { - case 0: - case 3: - *d=*s; - while(*s != '\0') * ++d = * ++s; - break; - case 1: - *d=toupper(*s); - while(*s != '\0') * ++d = * ++s; - break; - case 2: - *d=toupper(*s); - while(*s != '\0') * ++d = toupper(* ++s); - break; - } -} - -/**************************************************/ - -/* -parameters: - -seg - segment - -pref - field name or "1", "2", "3", "4" for the first four fields - +val - field contents -return value: - 1 if specified field exists, 0 otherwise -*/ - -inline int getfield(char* seg, const char* pref, char* val) -{ - - char* p=seg; - char* p0; - - while(isspace(*p)) ++p; - - // field "1" - p0=p; while(isdigit(*p)) ++p; - if(*pref=='1') if(p!=p0) { strncpy(val,p0,p-p0); val[p-p0]='\0'; return 1; } else return 0; - - while(isspace(*p)) ++p; - - // field "2" - p0=p; while(isdigit(*p)) ++p; - if(*pref=='2') if(p!=p0) { strncpy(val,p0,p-p0); val[p-p0]='\0'; return 1; } else return 0; - - while(isspace(*p)) ++p; - - // field "3" - p0=p; while(isgraph(*p)) ++p; - if(*pref=='3') if(p!=p0) { strncpy(val,p0,p-p0); val[p-p0]='\0'; return 1; } else return 0; - - while(isspace(*p)) ++p; - - // field "4" - p0=p; while(isgraph(*p)) ++p; - if(*pref=='4') if(p!=p0) { strncpy(val,p0,p-p0); val[p-p0]='\0'; return 1; } else return 0; - - while(isspace(*p)) ++p; - - // annotation fields - do p=strstr(p,pref); while(p!=NULL && *(p-1)!=' ' && *(p-1)!='\t'); - - if(p==NULL) return 0; - else - { - p+=strlen(pref); - int len=strcspn(p,FIELD_SEP "\n\r\f\0"); - strncpy(val,p,len); - val[len]='\0'; - return 1; - } -} - - -/* -parameters: - -name - field name, long or short - +prefix - field name with ':' appended if long name -return value: - 1 if correct field name, 0 otherwise -examples: -name prefix r.v. -lem lem: 1 -@ @ 1 -:: 'undef' 0 -a,b 'undef' 0 -*/ -inline -int fieldprefix(char *name, char *prefix) -{ - if (ispunct(name[0]) && name[1]=='\0') // correct short name - { - strcpy(prefix, name); return 1; - } - - int i=0; - while(name[i]!='\0' && isalnum(name[i])) ++i; - - if(name[i]=='\0' && i>0) // correct long name - { - sprintf(prefix,"%s:",name); return 1; - } - - // incorrect - return 0; -} - -inline -bool process_seg(char* seg, gengetopt_args_info& args) -{ - char buf[256]; - char pref[FIELD_PREFIX_MAXLEN]; - bool ret = !args.process_given; - if(args.process_given) - { - getfield(seg,"3",buf); - for(int i=0; i= MAX_LINE) return 0; // bezpieczniej, ale wolniej - - int seglen=strlen(seg); - sprintf(seg+(seglen-1)," %s%s\n",pref,val); - return 1; -} - -/**************************************************/ - -struct Seg -{ - int filepos, len; - char* tag; - char* form; - char* aux[MAXAUX]; - int auxn; - - bool parse(char* line); - char* getfield(char* fieldname); - void print(char* line); - bool addfield(char* s); - bool clearfields(); -}; - -/**************************************************/ - -/* definicja struktury wejscia/wyjscia - */ -struct Segment -{ - int filepos, len; - char* tag; - char* form; - char* aux[MAXAUX]; - int auxn; - - bool parse(char* line); - char* getfield(char* fieldname); - void print(char* line); - bool addfield(char* s); - bool clearfields(); -}; - -/* - * Sprawdza czy nalezy przetwarzac dany segment. - */ - -inline -bool process_seg(Segment& s, gengetopt_args_info& args) -{ - bool ret = !args.process_given; - - for(int i=0; i - -#include "common.h" - -main(int argc, char* argv[]) -{ - gengetopt_args_info args; - - if(cmdline_parser(argc,argv,&args) != 0) - exit(1); - - process_common_options(args); - - // - // TU KOD - // - - cmdline_parser_free(&args); - -} Index: ld/app/src/compdic/Makefile =================================================================== --- _old/app/src/compdic/Makefile (revision 8f395c89a98d5a9fe007ace2318d64f6a3a4c8f3) +++ (revision ) @@ -1,20 +1,0 @@ -CFLAG1 = -Wno-deprecated -O3 -fpermissive -CFLAG_ST = -Wno-deprecated -O3 -fpermissive -static - -all: compdic aut2fsa - -compdic: - - -aut2fsa: aut2fsa.cc - g++ $(CFLAG1) -o aut2fsa aut2fsa.cc - - -copy: -ifdef UTT_BIN_DIR - cp compdic fsm2aut aut2fsa lst2fstext ${UTT_BIN_DIR} -endif - -clean: - rm aut2fsa - Index: ld/app/src/compdic/aut2fsa.cc =================================================================== --- _old/app/src/compdic/aut2fsa.cc (revision 93afab8cc25b5217cf3a7c44c862904d3b265a6c) +++ (revision ) @@ -1,18 +1,0 @@ - -#include -#include - -#include "../lib/tfti.h" - -#include - -using namespace std; - -int main() -{ - TFTiv a; - a.read(); - a.save(); - - return 0; -} Index: ld/app/src/compdic/compdic =================================================================== --- _old/app/src/compdic/compdic (revision 8f395c89a98d5a9fe007ace2318d64f6a3a4c8f3) +++ (revision ) @@ -1,179 +1,0 @@ - -no_of_parts=0 - -while [ $# -gt 2 ] -do - case $1 - in - -p) - no_of_parts=$2 - shift 2 - ;; - - *) - echo "The arguments to use are" - echo "-p: number of parts" - shift 1 - ;; - esac -done - -if [ $# -lt 2 ] -then - echo - echo "compdic is a tool to compile lists of automaton paths (words) into the automaton format" - echo "suitable for use with lem, gue, cor, and kor components" - echo - echo "Usage:" - echo " compdic [-p ] " - echo "where" - echo " - file containig a list of words, one per line, iso-8859-2 encoded" - echo " - a file to which the compiled automaton (lem/gue/cor/kor format) should be written" - exit 0 -fi - -if [ $no_of_parts -eq 0 ] -then - no_of_parts=$(( `cat $1 | wc -l` / 75000 + 1 )) -fi - - -echo number of parts: $no_of_parts - - -tempdir=`mktemp -d /tmp/compdic.XXXXXX` - -alphabet=`tempfile -d $tempdir` - -cat < $alphabet - 0 -a 1 -A 2 -ä 3 -± 4 -¡ 5 -b 6 -B 7 -c 8 -C 9 -æ 10 -Æ 11 -d 12 -D 13 -e 14 -E 15 -é 16 -ê 17 -Ê 18 -f 19 -F 20 -g 21 -G 22 -h 23 -H 24 -i 25 -I 26 -j 27 -J 28 -k 29 -K 30 -l 31 -L 32 -³ 33 -£ 34 -m 35 -M 36 -n 37 -N 38 -ñ 39 -Ñ 40 -o 41 -O 42 -ö 43 -ó 44 -Ó 45 -p 46 -P 47 -q 48 -Q 49 -r 50 -R 51 -s 52 -S 53 -¶ 54 -Š 55 -t 56 -T 57 -u 58 -U 59 -ü 60 -v 61 -V 62 -w 63 -W 64 -x 65 -X 66 -y 67 -Y 68 -z 69 -Z 70 -Œ 71 -¬ 72 -¿ 73 -¯ 74 -0 75 -1 76 -2 77 -3 78 -4 79 -5 80 -6 81 -7 82 -8 83 -9 84 -_ 85 -- 86 -? 87 -! 88 -~ 89 -; 90 -, 91 -/ 92 -* 93 -+ 94 -EOF - - -no_of_lines=$(( (`cat $1 | wc -l` / $no_of_parts) + 1 )) - -split -l $no_of_lines $1 $tempdir/part. - -automaton=$tempdir/output.fst - -cat < $automaton -EOF - -n=0 - -for f in $tempdir/part.* -do - temp1=`tempfile -d $tempdir` - temp2=`tempfile -d $tempdir` - temp3=`tempfile -d $tempdir` - - n=$(( $n + 1 )) - echo processing part $n - - cat $f |\ - lst2fstext |\ - fstcompile --acceptor --isymbols=$alphabet --keep_isymbols |\ - fstrmepsilon |\ - fstdeterminize > $temp1 - fstminimize $temp1 $temp2 - - fstunion $automaton $temp2 | fstrmepsilon | fstdeterminize > $temp3 - fstminimize $temp3 $automaton -done - -cat $automaton | fsttopsort | fstprint --acceptor | fsm2aut | aut2fsa > $2 -rm -r $tempdir Index: ld/app/src/compdic/fsm2aut =================================================================== --- _old/app/src/compdic/fsm2aut (revision 93afab8cc25b5217cf3a7c44c862904d3b265a6c) +++ (revision ) @@ -1,44 +1,0 @@ -#!/usr/bin/perl - -my $currstate=-1; -my @states; -my @final; -my $tn=0; - -while(<>) -{ - if(/^\s*([0-9]+)\s+([0-9]+)\s+(.)(\s*)?$/) - { - push @{$states[$1]}, ($3, $2); - $#states=$2 if $#states<$2; - $tn++; - } - elsif(/^\s*([0-9]+)\s*$/) - { - $final[$1]=1; - $#states=$1 if $#states<$1; - } - else - { - die("Input error."); - } -} - -print scalar(@states)," ",$tn," char void\n"; - -my $i=0; -my $width=int(log(@states+1)/log(10)); -foreach $stateref (@states) -{ - $f = ($final[$i]?"+":"-"); - printf "%${width}d %s",$i++,$f; - while(@$stateref) - { - $c=shift @$stateref; - $s=shift @$stateref; - print " $c $s"; - } - print "\n"; -} - - Index: ld/app/src/compdic/lst2fstext =================================================================== --- _old/app/src/compdic/lst2fstext (revision 93afab8cc25b5217cf3a7c44c862904d3b265a6c) +++ (revision ) @@ -1,20 +1,0 @@ -#!/usr/bin/env perl - -use locale; - -$s=1; - -$f=1; -while(<>) -{ - chomp; - @cs = split(''); - ++$s; - print "0 $s \n"; - while($c = shift @cs) - { - print $s . ' ' . ++$s . " $c\n"; - } - print "$s $f \n"; -} -print "$f\n"; Index: ld/app/src/compiledic/Makefile =================================================================== --- _old/app/src/compiledic/Makefile (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,21 +1,0 @@ -CFLAG1 = -m32 -Wno-deprecated -O3 -fpermissive -CFLAG_ST = -Wno-deprecated -O3 -fpermissive -static - -all: compiledic aut2fsa - -compiledic: - - -aut2fsa: aut2fsa.cc - #g++ -m32 -Wno-deprecated -O3 -fpermissive -static -o aut2fsa aut2fsa.cc - g++ $(CFLAG1) -o aut2fsa aut2fsa.cc - - -copy: -ifdef UTT_BIN_DIR - cp compiledic fsm2aut aut2fsa ${UTT_BIN_DIR} -endif - -clean: - rm aut2fsa - Index: ld/app/src/compiledic/TODO =================================================================== --- _old/app/src/compiledic/TODO (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,5 +1,0 @@ -* pliki tymczasowe: - - pliki symboli lab i scl - - pliki powstajace podczas kompilacji slownika - - gdzie maja byc tworzone? tak jak teraz nie moze byc! Index: ld/app/src/compiledic/aut2fsa.cc =================================================================== --- _old/app/src/compiledic/aut2fsa.cc (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,18 +1,0 @@ - -#include -#include - -#include "../lib/tfti.h" - -#include - -using namespace std; - -int main() -{ - TFTiv a; - a.read(); - a.save(); - - return 0; -} Index: ld/app/src/compiledic/compiledic =================================================================== --- _old/app/src/compiledic/compiledic (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,242 +1,0 @@ -#! /usr/bin/env perl - -#package: UAM Text Tools -#component: compiledic -#version: 1.0 -#author: Tomasz Obrebski - -use strict; -use locale; -use File::HomeDir; -use File::Basename; -use File::Temp; -use File::Copy; -use Getopt::Long; - - -my $linesPerFile = 20000; - - -my $systemconfigfile='/usr/local/etc/utt/compiledic.conf'; -my $userconfigfile=home()."/.utt/compiledic.conf"; - -Getopt::Long::Configure('no_ignore_case_always'); - -#my $symfile='~/.utt/pl/pl_PL.iso-8859-2.sym'; -my $symbols=0; -my $help=0; - - - -#read configuration files########################### -my $file; -foreach $file ($systemconfigfile, $userconfigfile){ - if(open(CONFIG, $file)){ - while () { - chomp; - s/#.*//; - s/^\s+//; - s/\s+$//; - next unless length; - my ($name, $value) = split(/\s*=\s*/, $_, 2); - if($name eq "symbols"){ - $symbols=$value; - } - elsif(($name eq "help")or($name eq "h")){ - $help=1; - } - - } - close CONFIG; - } -} -######################################################### - -GetOptions("symbols=s" => \$symbols, - "help|h" => \$help); - -if($help) -{ - print <<'END' -Usage: compiledic [OPTIONS] dictionaryfile - -Options: - --help -h Help. - --symbols=FILE Symbol file. -END -; - exit 0; -} - -################################################## - --f $symbols or die("Symbol file not found."); - -@ARGV > 0 or die("Source dictionary not given."); - -my $file = shift; - --f $file or die("Source dictionary not found."); - -$file =~ /(.*)\.dic/ or die("The input file must have .dic extension."); - -my $filenameprefix = $1; - -################################################## - -# Tworzymy katalog tymczasowy, gdzie wszystko bedzie umieszczane. -my $tmp_root = File::Temp::tempdir( CLEANUP => 1 ); - -(undef, my $symfile) = File::Temp::tempfile( DIR => $tmp_root, SUFFIX => ".sym" ); -my $symfilenoext=$symfile; -$symfilenoext =~ s/\.sym$//; -my $labfile = $symfilenoext . '.lab'; -my $sclfile = $symfilenoext . '.scl'; - -copy($symbols, $symfile); - -# Przygotowanie etykiet - -`lexmakelab $symfilenoext`; - - -# Analiza pliku slownika - -print "preparing file..........................................."; -#print "... sed section .....\n"; -(undef, my $file_sed) = File::Temp::tempfile( DIR => $tmp_root, SUFFIX => ".sed" ); -`sed -r "s/([[:punct:]])/\[\\1\]/g" < $file > $file_sed`; - -print "OK\n"; - -#dzielimy plik na wiele czesci, uruchamiamy lexcomplex dla kazdej -#czesci osobno, nastepnie laczymy to za pomoca programu fsmunion - -#print "Dziele slownik na mniejsze czesci..."; - -open(IN, $file_sed); - -my $lineCount = 0; -my $fileCount = 0; - -open(FILE, ">$tmp_root/slo_$fileCount"); - -while () { - - if (++$lineCount >= $linesPerFile) { - $fileCount++; - $lineCount = 0; - - close(FILE); -# print "Tworze nowy plik tymczasowy: slo_".$fileCount."\n"; - open(FILE, ">$tmp_root/slo_".$fileCount); - } - - print(FILE $_); -} - -#print "OK\n"; - -print "building partial automata"; - -#32 kropki, fileCount plikow -my $filesPerDot = $fileCount/32; -my $files=$filesPerDot; -my $dots=0; - -for (my $i=0; $i<=$fileCount; $i++) { - - if ($files >= $filesPerDot) { - $files = 0; - print "."; - $dots++; - } - $files++; - - `lexcomplex -l $labfile -S $sclfile < $tmp_root/slo_$i > $tmp_root/slownik_$i.fsm`; - -} -if ($dots < 32) { - for (my $i=0; $i<32 - $dots; $i++) { - print "."; - } -} - -print "OK\n"; - -unlink <$tmp_root/slo_*>; - -print "building final automaton"; - -#35 kropek... -my $ndots=33; -$filesPerDot = $fileCount/$ndots; -$files=$filesPerDot; -$dots=0; - -copy("$tmp_root/slownik_0.fsm", "$tmp_root/slownik1.fsm"); - -for (my $i=1; $i<=$fileCount; $i++) { - - if ($files >= $filesPerDot) { - $files = 0; - print "."; - $dots++; - } - $files++; - - `fsmunion $tmp_root/slownik_$i slownik1.fsm > $tmp_root/slownik2.fsm`; - - move("$tmp_root/slownik2.fsm", "$tmp_root/slownik1.fsm") || die "Unable to move $tmp_root/slownik2.fsm!\n"; -} - -if ($dots < $ndots) { - for (my $i=0; $i<$ndots - $dots; $i++) { - print "."; - } -} - -#`fsmunion $tmp_root/* > $tmp_root/slownik1.fsm`; - -print "OK\n"; - -print "removing epsilon-transitions............................."; - -`fsmrmepsilon $tmp_root/slownik1.fsm > $tmp_root/slownik2.fsm`; - -unlink ("$tmp_root/slownik1.fsm"); - -print "OK\n"; - -print "determinizing automaton.................................."; - -`fsmdeterminize $tmp_root/slownik2.fsm > $tmp_root/slownik1.fsm`; - -unlink ("$tmp_root/slownik2.fsm"); - -print "OK\n"; - -print "minimizing automaton....................................."; - -`fsmminimize $tmp_root/slownik1.fsm > $tmp_root/slownik.fsm`; - -#`rm slownik1.fsm`; - -print "OK\n"; - -print "converting fsm format to bin............................."; - -`fsmprint -i $labfile $tmp_root/slownik.fsm > $tmp_root/slownik.txt`; - -`fsm2aut $tmp_root/slownik.txt > $tmp_root/slownik.aut`; - -`aut2fsa < $tmp_root/slownik.aut > $filenameprefix.bin`; - -print "OK\n"; - -print "removing temporary files................................."; - -unlink <$tmp_root/*>; -unlink ($tmp_root); - -print "OK\n"; Index: ld/app/src/compiledic/fsm2aut =================================================================== --- _old/app/src/compiledic/fsm2aut (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,44 +1,0 @@ -#!/usr/bin/perl - -my $currstate=-1; -my @states; -my @final; -my $tn=0; - -while(<>) -{ - if(/^\s*([0-9]+)\s+([0-9]+)\s+(.)(\s*)?$/) - { - push @{$states[$1]}, ($3, $2); - $#states=$2 if $#states<$2; - $tn++; - } - elsif(/^\s*([0-9]+)\s*$/) - { - $final[$1]=1; - $#states=$1 if $#states<$1; - } - else - { - die("Input error."); - } -} - -print scalar(@states)," ",$tn," char void\n"; - -my $i=0; -my $width=int(log(@states+1)/log(10)); -foreach $stateref (@states) -{ - $f = ($final[$i]?"+":"-"); - printf "%${width}d %s",$i++,$f; - while(@$stateref) - { - $c=shift @$stateref; - $s=shift @$stateref; - print " $c $s"; - } - print "\n"; -} - - Index: ld/app/src/cor/Makefile =================================================================== --- _old/app/src/cor/Makefile (revision 7bed30fe7b80d29bc4822f7fd44163fa37a454fd) +++ (revision ) @@ -1,41 +1,0 @@ -PAR=-Wno-deprecated -fpermissive -static -PAR2=-c -Wno-deprecated -fpermissive -LIB_PATH=../lib -COMMON_PATH=../common -CMDLINE_FILE='"../cor/cmdline.h"' - - -cor: main.cc corr.o $(LIB_PATH)/word.o \ - $(LIB_PATH)/auttools.o cmdline.c common_cor.o common.o - g++ $(PAR) -D _CMDLINE_FILE=$(CMDLINE_FILE) main.cc corr.o common.o \ - $(LIB_PATH)/word.o $(LIB_PATH)/auttools.o cmdline.c common_cor.o \ - -o cor - -corr.o: corr.cc corr.hh - g++ $(PAR2) corr.cc - -common.o: $(COMMON_PATH)/cmdline_common.ggo $(COMMON_PATH)/common.cc \ - $(COMMON_PATH)/common.h - g++ $(PAR2) -D _CMDLINE_FILE=$(CMDLINE_FILE) $(COMMON_PATH)/common.cc - -common_cor.o: cmdline.h common_cor.cc common_cor.h - g++ $(PAR2) -D _CMDLINE_FILE=$(CMDLINE_FILE) common_cor.cc - -cmdline.c cmdline.h: cmdline.ggo - gengetopt -i cmdline.ggo --conf-parser - -cmdline.ggo: cmdline_cor.ggo $(COMMON_PATH)/cmdline_common.ggo - cat cmdline_cor.ggo $(COMMON_PATH)/cmdline_common.ggo > cmdline.ggo - -copy: -ifdef UTT_BIN_DIR - cp cor ${UTT_BIN_DIR} -endif - -clean: clean.cmdline - rm *.o || true - rm cor || true - -clean.cmdline: - rm cmdline.* || true - Index: ld/app/src/cor/cmdline_cor.ggo =================================================================== --- _old/app/src/cor/cmdline_cor.ggo (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,8 +1,0 @@ -package "cor" -version "0.1" - -option "dictionary-home" - "Dictionary home dir." string typestr="FILENAME" no hidden -option "dictionary" d "Dictionary" string typestr="FILENAME" default="cor.bin" no -option "distance" n "Maximal edit distance." int default="1" no -option "replace" r "Replace original form with corrected form, place original form in the cor field. This option has no effect in single mode" flag off hidden -#option "single" - "Place all alternatives in the same line" flag off Index: ld/app/src/cor/common_cor.cc =================================================================== --- _old/app/src/cor/common_cor.cc (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,29 +1,0 @@ -#include -#include -#include "common_cor.h" - -char dictionary[256]; - -void process_cor_options(gengetopt_args_info* args) -{ - if(args->dictionary_given) - { - expand_path(args->dictionary_arg,dictionary); - if(file_accessible(dictionary)!=0) - { - fprintf(stderr,"Cannot open the dictionary file: %s\nAborting.\n",dictionary); - exit(1); - } - } - else if (args->dictionary_home_given && args->language_given) - { - char buf[255]; - expand_path(args->dictionary_home_arg, buf); - sprintf(dictionary,"%s/%s/cor.bin",buf,args->language_arg); - if(file_accessible(dictionary)!=0) - { - fprintf(stderr,"Cannot open the dictionary file: %s\nAborting.\n",dictionary); - exit(1); - } - } -} Index: ld/app/src/cor/common_cor.h =================================================================== --- _old/app/src/cor/common_cor.h (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,19 +1,0 @@ -#ifndef __COMMON_COR_H -#define __COMMON_COR_H - -#include - -//do wyrzucenia - definicja w Makefile! #define _CMDLINE_FILE "../cor/cmdline.h" -#include "../common/common.h" - -#include "cmdline.h" - -#define DICT_FILE "cor.bin" - -extern int change_count; - -extern void process_cor_options(gengetopt_args_info* args); - -extern char dictionary[]; - -#endif Index: ld/app/src/cor/corr.cc =================================================================== --- _old/app/src/cor/corr.cc (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,142 +1,0 @@ -//--------------------------------------------------------------------------- - -#include "corr.hh" - -#define MAXPATH 256 - -#define min(x,y) ((xy)?(x):(y)) - - -int Corr::ed(int i,int j) -{ - if(i==-1) - return j+1; - if(j==-1) - return i+1; - if(i==-2 || j==-2) - return n+1; - - if(X[i]==Y[j]) - return H2[i-1][j-1]; - if(X[i-1]==Y[j] && X[i]==Y[j-1]) - return 1+min(H2[i-2][j-2],min(H2[i][j-1],H2[i-1][j])); - return 1+min(H2[i-1][j-1],min(H2[i][j-1],H2[i-1][j])); - -/* - if(X[i]==Y[j]) - return H[(i-1)+2][(j-1)+2]; - if(X[i-1]==Y[j] && X[i]==Y[j-1]) - return 1+min(H[(i-2)+2][(j-2)+2],min(H[(i)+2][(j-1)+2],H[(i-1)+2][(j)+2])); - return 1+min(H[(i-1)+2][(j-1)+2],min(H[(i)+2][(j-1)+2],H[(i-1)+2][(j)+2])); -*/ -} - -int Corr::cuted(int j) -{ - int l=max(0,j-t); - int u=min(m,j+t); - int ce=j+t; - for(int k=l;k<=u;k++) - { - if(H2[k][j]0) - j--; - else - more=0; - while(more && !continued(path[j])); - state=path[j]+1; - } - return count; -} - - -//--------------------------------------------------------------------------- - Index: ld/app/src/cor/corr.hh =================================================================== --- _old/app/src/cor/corr.hh (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,34 +1,0 @@ -//--------------------------------------------------------------------------- -#ifndef _corr_hh -#define _corr_hh -//--------------------------------------------------------------------------- - -#include "../lib/tfti.h" -#include "../lib/word.h" - -class Corr : public TFTiv -{ -private: - int H[100][100]; - char X[100]; // misspelled string - char Y[100]; // (possibly partial) candidate string - int m; // length of X - int n; // maximal length of Y - - int ed(int,int); - int cuted(int); - void recomputeH(int); - -public: - int (*H2)[100]; - - int t; // threshold - - Corr() : H2((int(*)[100])&H[2][2]) {}; - Corr(const char* a) : TFTiv(a), H2((int(*)[100])&H[2][2]) { }; - - int correct(const char* w, Words& tab); -}; - -//--------------------------------------------------------------------------- -#endif Index: ld/app/src/cor/main.cc =================================================================== --- _old/app/src/cor/main.cc (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,155 +1,0 @@ -#include -#include -#include "../lib/iotools.h" -//do wyrzucenia - definicja w Makefile! #define _CMDLINE_FILE "../cor/cmdline.h" -#include "../common/common.h" -#include "common_cor.h" -#include "corr.hh" -#include "cmdline.h" -#include - - -int main(int argc, char** argv) { - -// setlocale(LC_CTYPE,""); -// setlocale(LC_COLLATE,""); - - gengetopt_args_info args; - - if(cmdline_parser(argc, argv, &args) != 0) - exit(1); - - process_config_files(&args,argv[0]); - process_common_options(&args,argv[0]); - process_cor_options(&args); - - Corr cor; - - cor.load(dictionary); - cor.t=args.distance_arg; - - char line[MAX_LINE+1]; - long line_count = 0; - - Segment seg; - Words tab; - char form1[MAX_LINE]; - char* form; - int formcasing; - char corfield[MAX_LINE]=""; - - while (fgets(line, MAX_LINE, inputf)) - { -// strcpy(outline,line); - ++line_count; - -// if(!seg.parse(line)) -// { -// fprintf(stderr,"Input error in line %d.\n",line_count); -// exit(1); -// } - - char outline[128]; - //printf("Starting cor... searching for %d fields\n", args.input_field_given); - //for (int i=0; i $@.$$$$; \ - sed 's,\($*\)\.o[ :]*,\1.o $@ : ,g' < $@.$$$$ > $@; \ - rm -f $@.$$$$ - -# stare: -# cmdline.cc cmdline.h : cmdline.ggo -# gengetopt --c-extension=cc -i cmdline.ggo -# nowe -cmdline.cc cmdline.h: cmdline.ggo - gengetopt -i cmdline.ggo --c-extension=cc --conf-parser - -cmdline.ggo: cmdline_dgp.ggo ../common/cmdline_common.ggo - cat cmdline_dgp.ggo ../common/cmdline_common.ggo > cmdline.ggo -# endnowe - - -clean: - rm ${bin} ${objs} cmdline.cc cmdline.h - rm -rf *.d - -prof: dgp - gprof dgp ~/tmp/dgp-pl/gmon.out > dgp.prof - -copy: -ifdef UTT_BIN_DIR - cp dgp dgc canonize tre $(UTT_BIN_DIR)/ -endif Index: ld/app/src/dgp/Makefile.user =================================================================== --- _old/app/src/dgp/Makefile.user (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,3 +1,0 @@ - -gram.dgp: gram.dgc - dgc -c cats.dgc < gram.dgc > gram.dgp Index: ld/app/src/dgp/canonize =================================================================== --- _old/app/src/dgp/canonize (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,50 +1,0 @@ -#!/usr/bin/perl - -#package: UAM TExt Tools -#component: canonize -#version: 1.0 -#author: Tomasz Obrebski - -use lib "/usr/local/lib/utt"; -use lib "$ENV{'HOME'}/.local/lib/utt"; - -use strict; -use Getopt::Long; -use attr; - - -my $help; - -GetOptions("help|h" => \$help); - -if($help) -{ - print <<'END' - -Transforms syntactic categories to their canonical form. - -Usage: canonize - -Options: - --help -h Help. - -END -; - exit 0; -} - -#$|=1; - -my %tra; - -while(<>) -{ - s/$attr::pos_re\/$attr::avlist_re/trans($&)/ge; - print; -} - -sub trans -{ - my $cat=shift; - exists($tra{$cat}) ? $tra{$cat} : ( $tra{$cat} = attr::canonize $cat ); -} Index: ld/app/src/dgp/cmdline_dgp.ggo =================================================================== --- _old/app/src/dgp/cmdline_dgp.ggo (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,18 +1,0 @@ -package "dgp" -version "0.1" - -option "grammar" g "Grammar file" - string no typestr="filename" - -option "long" l "Long output" - flag off - -option "debug" d "Debug mode." - flag off - -option "info" - "Print info. -h - heads d - dependents -s - sets -c - constraints n - node/arc counts t - parse time -" -string no default="h" Index: ld/app/src/dgp/const.hh =================================================================== --- _old/app/src/dgp/const.hh (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,13 +1,0 @@ -#ifndef CONST_HH -#define CONST_HH - -#define MAXTYPES 32 -#define MAXFLAGS 64 -#define MAXNODES 1024 -#define MAXCONSTRS 32 -#define MAXLINE 256 -#define MAXFORMLEN 64 -#define MAXDESCRLEN 80 -#define FIELDSEP " \n\t" - -#endif Index: ld/app/src/dgp/dgc =================================================================== --- _old/app/src/dgp/dgc (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,292 +1,0 @@ -#!/usr/bin/perl - -#package: UAM Text Tools -#component: dgc (dg compiler) -#version: 1.0 -#author: Tomasz Obrebski - -# wymaga niejawnie programu canonize!!!! -use lib "/usr/local/lib/utt"; -use lib "$ENV{'HOME'}/.local/lib/utt"; - -use strict; -use Getopt::Long; -use Data::Dumper; -use attr; -use File::HomeDir; - -my $systemconfigfile='/usr/local/etc/utt/dgc.conf'; -my $userconfigfile=home()."/.utt/dgc.conf"; - -Getopt::Long::Configure('no_ignore_case_always'); - -my $help=0; -my $catfile=0; -my $dicfile=0; -my $gramfile=0; -my $outputfile=0; - -#read configuration files########################### -my $file; -foreach $file ($systemconfigfile, $userconfigfile){ - if(open(CONFIG, $file)){ - while () { - chomp; - s/#.*//; - s/^\s+//; - s/\s+$//; - next unless length; - my ($name, $value) = split(/\s*=\s*/, $_, 2); - if(($name eq "categories")or($name eq "c")){ - $catfile=$value; - } - elsif(($name eq "dictionary")or($name eq "d")){ - $dicfile=$value; - } - elsif(($name eq "grammar")or($name eq "g")){ - $gramfile=$value; - } - elsif(($name eq "outputfile")or($name eq "o")){ - $outputfile=$value; - } - elsif(($name eq "help")or($name eq "h")){ - $help=1; - } - - } - close CONFIG; - } -} -######################################################### - -GetOptions("help|h" => \$help, - "categories|c=s" => \$catfile, - "dictionary|d=s" => \$dicfile, - "grammar|g=s" => \$gramfile, - "outputfile|o=s" => \$outputfile); - -my $homedir = $ENV{'HOME'}; -$catfile =~ s/~/$homedir/; -$dicfile =~ s/~/$homedir/; -$gramfile =~ s/~/$homedir/; -$outputfile =~ s/~/$homedir/; - - -if($help) -{ - print <<'END' -Usage: dgc [OPTIONS] - -Options: - --categories -c filename List of syntactic categories. - --dictionary -d filename Dictionary. - --grammar -g filename List of grammar rules. - --outputfile -o filename Output file name. - --help -h Help. -END -; - exit 0; -} - -die("At least one of --cats and --dic must be given.\n") if !$catfile && !$dicfile; - -my $ncat=0; -my $nrole=0; -my $nsgl=0; -my $nleft=0; -my $nright=0; -my $nreq=0; -my $nlink=0; -my $nflag=0; - -my %cats; -my %roles; -my %agr; -my %gov; - -if(!$outputfile) { - *OUTPUT = *STDOUT; -} -elsif($outputfile eq "-") { - *OUTPUT = *STDOUT; -} -else { - open(OUTPUT, ">$outputfile") or die("Can't open output file: $outputfile!"); -} - - -loadcats($catfile) if $catfile; -extractcats($dicfile) if $dicfile; - - -my $cats_re = qr/(?:$attr::cat_re\s*(?:,\s*$attr::cat_re)*)/; - -# class parse_class: -# /$attr::cat_re/g; - - -if(!$gramfile) { - *INPUT = *STDIN; -} -elsif($gramfile eq "-"){ - *INPUT = *STDIN; -} -else { - open(INPUT, $gramfile) or die("Unable to open: $gramfile!"); -} - -while() -{ - s/#.*//; - s/^\s+//; - s/\s+$//; - if(/^AGR\s+(\S+)\s+(\S+)$/) - { - push @{$agr{$1}}, $2; - } - elsif(/^GOV\s+(\S+)\s+(\S+)$/) - { - push @{$gov{$1}}, attr::parse($2); - } - elsif(/^ROLE\s+\S+$/) - { - $roles{$_}=1; - print OUTPUT "$_\n"; - } - elsif(/^SGL\s+\S+$/) - { - ++$nsgl; - print OUTPUT "$_\n"; - } - elsif(/^REQ\s+(\S+)\s+(\S+)$/) - { - print OUTPUT "#$_\n"; - my $cat = attr::parse $1; - for my $atomcat (keys %cats) - { - if(attr::match @$cat, @{$cats{$atomcat}}) - { - print OUTPUT "REQ ".$atomcat." $2\n"; - ++$nreq; - } - } - } - elsif(/^LEFT\s+\S+$/) - { - ++$nleft; - print OUTPUT "$_\n"; - } - elsif(/^RIGHT\s+\S+$/) - { - ++$nright; - print OUTPUT "$_\n"; - } - elsif(my ($hs,$ds,$r) = /^LINK\s+($cats_re)\s+($cats_re)\s+(\S+)$/) - { - print OUTPUT "#$_\n"; - for my $h ($hs =~ /$attr::cat_re/g) - { - for my $d ($ds =~ /$attr::cat_re/g) - { - addlinks($h,$d,$r); - } - } - } - elsif(/^FLAG\s+\S+$/) - { - ++$nflag; - print OUTPUT "$_\n" - } - elsif(/^$/) { - # pomijamy puste linie oraz komentarze - } - else - { - print STDERR "Illegal format: $_\n"; - } -} - - -sub addlinks -{ - my ($h,$d,$r) = @_; - - for my $a (@{$agr{$r}}) { print OUTPUT "#AGR $r $a\n"; } - for my $c (@{$gov{$r}}) { print OUTPUT "#GOV $r ".attr::unparse(@$c)."\n"; } - my $head = attr::parse $h; - my $dep = attr::parse $d; - - for my $atomhead (keys %cats) - { - if(attr::match @$head, @{$cats{$atomhead}}) - { - DEP: - for my $atomdep (keys %cats) - { - next DEP if ! attr::match @$dep, @{$cats{$atomdep}}; - - for my $a (@{$agr{$r}}) - { - next DEP if ! attr::agree(@{$cats{$atomhead}},@{$cats{$atomdep}},$a); - } - - for my $c (@{$gov{$r}}) - { - next DEP if ! attr::match(@$c,@{$cats{$atomdep}}); - } - - print OUTPUT "LINK "; - print OUTPUT $atomhead." "; - print OUTPUT $atomdep." $r\n"; - ++$nlink; - - } - } - } -} - - -printf STDERR "%6d CAT statements\n", 0+keys(%cats); -printf STDERR "%6d ROLE statements\n", 0+keys(%roles); -printf STDERR "%6d SGL statements\n", $nsgl; -printf STDERR "%6d REQ statements\n", $nreq; -printf STDERR "%6d LEFT statements\n", $nleft; -printf STDERR "%6d RIGHT statements\n", $nright; -printf STDERR "%6d LINK statements\n", $nlink; -printf STDERR "%6d FLAG statements\n", $nflag; - - -sub extractcats -{ - my $file = shift; - open DICFILE, "canonize $file |"; - while() - { - while(/,([^[:space:];]+)/g) - { - my $cat=$1; - next if !$cat || exists $cats{$cat}; - $ncat++; - print OUTPUT "CAT $1\n"; - $cats{$cat}=attr::parse($cat); - } - } - close DICFILE; -} - - -sub loadcats -{ - my $file = shift; - open CATFILE, "canonize $file |"; - while() - { - tr/ \t\n//d; - next if !$_ || exists $cats{$_}; - print OUTPUT "CAT $_\n"; - ++$ncat; - $cats{$_}=attr::parse($_); - } - close CATFILE; -} - Index: ld/app/src/dgp/dgp0.cc =================================================================== --- _old/app/src/dgp/dgp0.cc (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,217 +1,0 @@ -#include "dgp0.hh" -#include "global.hh" - -extern Grammar grammar; -extern MGraph mgraph; -extern SGraph sgraph; - -SNode* snodes; - -extern bool debug; - -list nodelist; -list::iterator processed; - - -void set_initial_constraints(int node) -{ - snodes[node].prop.forbidden.reset(); - snodes[node].prop.required=grammar.obl[snodes[node].mnode->cat]; -} - - -bool changing_constraints(int head, Role role) -{ - return grammar.sgl[role] || snodes[head].prop.required[role]; -} - -void apply_constraints(int head, Role role) -{ - if(grammar.sgl[role]) snodes[head].prop.forbidden.set(role); - snodes[head].prop.required.reset(role); -} - -NodeProp compute_prop_left(NodeProp headprop, Role role) -{ - NodeProp ret=headprop; - if(grammar.sgl[role]) ret.forbidden.set(role); - ret.required.reset(role); - return ret; -} - -NodeProp compute_prop_right(NodeProp headprop, Role role) -{ - NodeProp ret=headprop; - - if(grammar.sgl[role]) ret.forbidden.set(role); - ret.required.reset(role); - return ret; -} - -int get_node(MNode& mnode, NodeProp p, bitset& newheadLH, bitset& newheadLV) -{ - for(vector::iterator ps=mnode.snodes.begin(); ps!=mnode.snodes.end(); ++ps) - if(snodes[*ps].prop==p && snodes[*ps].LH==newheadLH && snodes[*ps].LV==newheadLV) - return *ps; - return -1; -} - -void connect_left(list::iterator h, list::iterator d, Role r) -{ - NodeProp &oldheadprop = snodes[*h].prop; - NodeProp newheadprop; - bitset newheadLV; - bitset newheadLH; - bitset newheadLD; - - newheadprop=compute_prop_left(oldheadprop,r); - - int newheadind; - if(oldheadprop==newheadprop) - newheadind = *h; - else - { - newheadLH = snodes[*h].LH; - newheadLV = snodes[*d].LV; - newheadLD = snodes[*h].LD; - - newheadind = get_node(*(snodes[*h].mnode), newheadprop, newheadLH, newheadLV); - if( newheadind < 0 ) - { - newheadind = sgraph.clone(*h,newheadprop); - list::iterator nextit=h; ++nextit; - nodelist.insert(nextit,newheadind); - snodes[newheadind].LH=newheadLH; - snodes[newheadind].in_LH=true; - snodes[newheadind].LV.reset(); - snodes[newheadind].LD = newheadLD; - - if(debug) sgraph.print_node_debug(stderr," C ",newheadind); - } - else - snodes[newheadind].LD |= newheadLD; // TYLKO DLA LD - } - - snodes[newheadind].deps.push_back(Arc(*d,r,*h)); - - if(snodes[*d].saturated()) snodes[newheadind].LV |= snodes[*d].LV; - snodes[newheadind].LD.set(*d); - if(snodes[*d].saturated()) snodes[newheadind].LD |= snodes[*d].LD; - - if(debug) - sgraph.print_arc(stderr,*d,newheadind,r,0), sgraph.print_node_debug(stderr," U ",newheadind); -} - - -void connect_right(list::iterator h, list::iterator d, Role r) -{ - NodeProp &oldheadprop = snodes[*h].prop; - NodeProp newheadprop; - bitset newheadLV; - bitset newheadLH; - bitset newheadLD; - int newheadind; - - newheadprop = compute_prop_right(oldheadprop,r); - if(oldheadprop==newheadprop) - newheadind = *h; - else - { - newheadLH = snodes[*h].LH; - newheadLV = snodes[*h].LV; - newheadLD = snodes[*h].LD; - - newheadind = get_node(*(snodes[*h].mnode), newheadprop, newheadLH, newheadLV); - if( newheadind < 0 ) - { - newheadind = sgraph.clone(*h,newheadprop); - snodes[newheadind].LH=newheadLH; - snodes[newheadind].in_LH=false; - snodes[newheadind].LV=newheadLV; - snodes[newheadind].LD=newheadLD; - list::iterator nextit=h; ++nextit; - nodelist.insert(nextit,newheadind); - - if(debug) sgraph.print_node_debug(stderr," C ",newheadind); - } - else - snodes[newheadind].LD |= newheadLD; // TYLKO DLA LD - } - - snodes[*d].heads.push_back(Arc(newheadind,r,*h)); - - snodes[*d].LH.set(newheadind); - - if(snodes[newheadind].saturated()) snodes[*d].LH |= snodes[newheadind].LH; - - if(debug) - sgraph.print_arc(stderr,newheadind,*d,r,1), sgraph.print_node_debug(stderr," U ",*d); - -} - - -void try_connect_dependents(list::iterator j) -{ - for(list::iterator i(j); i!=nodelist.begin(); --i) - if(sgraph.visible(*i,*j) && sgraph.saturated(*i)) - { - Roles& ji_roles = grammar.connect[snodes[*j].mnode->cat][snodes[*i].mnode->cat]; - for(RolesIter r=ji_roles.begin(); r!=ji_roles.end();++r) - if(grammar.check_constr(snodes[*j].prop,snodes[*i].prop,0,*r)) - connect_left(j,i,*r); - } -} - - -void try_connect_heads(list::iterator j) -{ - for(list::iterator i(j); i!=nodelist.begin(); --i) - if(sgraph.visible(*i,*j)) - { - Roles& ij_roles = grammar.connect[snodes[*i].mnode->cat][snodes[*j].mnode->cat]; - for(RolesIter r=ij_roles.begin(); r!=ij_roles.end();++r) - if(grammar.check_constr(snodes[*i].prop,snodes[*j].prop,1,*r)) - connect_right(i,j,*r); - } -} - - -void reverse_links() -{ - list::iterator i = nodelist.begin(); - for(++i; i!=nodelist.end(); ++i) - { - for(vector::iterator da=sgraph.nodes[*i].deps.begin()--; da!=sgraph.nodes[*i].deps.end(); ++da) - sgraph.nodes[da->dst].heads.push_back(Arc(*i,da->role,da->anc)); - for(vector::iterator ha=sgraph.nodes[*i].heads.begin(); ha!=sgraph.nodes[*i].heads.end(); ++ha) - sgraph.nodes[ha->dst].deps.push_back(Arc(*i,ha->role,ha->anc)); - } -} - - -void dgp0() -{ - snodes=sgraph.nodes; - - nodelist.clear(); - nodelist.push_back(0); // BOS - processed=nodelist.begin(); - - for(int m=0; m::iterator cursor=processed; - while(++cursor != nodelist.end()) - { - try_connect_dependents(cursor); - try_connect_heads(cursor); - processed=cursor; - } - } - reverse_links(); -} Index: ld/app/src/dgp/dgp0.hh =================================================================== --- _old/app/src/dgp/dgp0.hh (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,12 +1,0 @@ -#ifndef _DGP0_HH -#define _DGP0_HH - -#include "grammar.hh" -#include "sgraph.hh" -#include "mgraph.hh" - -// API - -void dgp0(); - -#endif Index: ld/app/src/dgp/global.cc =================================================================== --- _old/app/src/dgp/global.cc (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,5 +1,0 @@ - -#include "global.hh" - -bool debug = false; - Index: ld/app/src/dgp/global.hh =================================================================== --- _old/app/src/dgp/global.hh (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,1 +1,0 @@ -extern bool debug; Index: ld/app/src/dgp/go =================================================================== --- _old/app/src/dgp/go (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,13 +1,0 @@ -if test -f Makefile.go; -then - make -f Makefile.go gram.dgp; - tok |\ - lem -p W |\ - canonize |\ - sen |\ - gph -p W -p BOS -p EOS -r BOS |\ - dgp -i ds -p W -p BOS -p EOS -g gram.dgp -else - echo "Invalid configuration! Run utt_make_config.pl first." -fi - Index: ld/app/src/dgp/grammar.cc =================================================================== --- _old/app/src/dgp/grammar.cc (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,181 +1,0 @@ - -#include - -#include "grammar.hh" - -bool (*constraint[MAXCONSTRS])(int head, int dep); - - -int chk_type(const char* s, int lineno) // SIDE EFECTS! -{ - if(Role::index(s)>0) return 1; - - fprintf(stderr,"%8d: Invalid type '%s'. Line ignored.\n",lineno,s); - return 0; -} - -int chk_cat(const char* s, int lineno) -{ - if(Cat::index(s)>0) return 1; - - fprintf(stderr,"%8d: Invalid category '%s'. Line ignored.\n",lineno,s); - return 0; -} - -void Grammar::add_category(const char* s) -{ - Cat::add(s); - if(Cat::count()>cats_sz) - { - cats_sz += 16; - connect.resize(cats_sz); - for(int i=0; itypes_sz) - { - types_sz += 16; - lt.resize(types_sz); - gt.resize(types_sz); - } -} - -void Grammar::add_flag(const char* s) -{ - Flag::add(s); - if(Flag::count()>flags_sz) - { - flags_sz += 16; - pass.resize(flags_sz); - } -} - - -void Grammar::set_lt(Role s, Role t) -{ - lt[s].set(t); - gt[t].set(s); - if(s==0||(int)t==0) - return; - else - { - for(int i=0; i=2) - { - add_category(arg1); - } - else if(strcmp(key,"ROLE")==0 && fields>=2) - { - add_type(arg1); - } - else if(strcmp(key,"SGL")==0 && fields>=2) - { - if(chk_type(arg1,lineno)) - set_sgl(arg1); - } - else if(strcmp(key,"LEFT")==0 && fields>=2) - { - if(chk_type(arg1,lineno)) - set_left(arg1); - } - else if(strcmp(key,"RIGHT")==0 && fields>=2) - { - if(chk_type(arg1,lineno)) - set_right(arg1); - } - else if(strcmp(key,"REQ")==0 && fields>=3) - { - if(chk_cat(arg1,lineno) + chk_type(arg2,lineno) == 2) - set_obl(arg1,arg2); - } - else if(strcmp(key,"LINK")==0 && fields>=4) - { - if(chk_cat(arg1,lineno) + chk_cat(arg2,lineno) + chk_type(arg3,lineno) == 3) - set_connect(arg1,arg2,arg3); - } - // FLAG DECLARATION - else if(strcmp(key,"FLAG")==0 && fields>=2) - { - add_flag(arg1); - } - - else fprintf(stderr,"Invalid line %d. Ignored.\n", lineno); - } - -// compute_gt(); - - return true; - -} - -void Grammar::write(FILE* f) -{ - for(Cat i=1; i -#include -#include -#include - -#include "const.hh" -#include "thesymbols.hh" -#include "sgraph.hh" - - -using namespace std; - -class Link -{ - Role role; - FlagSet hflags; - FlagSet dflags; -}; - - -class Grammar -{ - - public: - - // enum CONSTR { SGL, OBL, LEFT, RIGHT, INIT, NONINIT, FIN, NONFIN }; - - Grammar() : types_sz(0), cats_sz(0), flags_sz(0) {} ; - - int types_sz; - int cats_sz; - int flags_sz; - - vector< vector< Roles > > connect; - RoleSet sgl; - vector< RoleSet > obl; - RoleSet left; - RoleSet right; - vector< RoleSet > lt; - vector< RoleSet > gt; - - - // vector< vector< vector< - vector< FlagSet > set; - vector< FlagSet > pass; - - bool read(FILE* f); - void write(FILE* f); - - void add_category(const char* s); - void add_type(const char* s); - void add_flag(const char* s); - - void set_sgl(Role r) { sgl.set(r); } - void set_obl(Cat c, Role r) { obl[c].set(r); } - void set_left(Role r) { left.set(r); } - void set_right(Role r) { right.set(r); } - void set_order(Role r, Role s) { lt[s].set(r); } - void set_connect(Cat c, Cat d, Role r) { connect[c][d].insert(r); } - void set_lt(Role r, Role s); - void compute_gt(); - - - bool check_constr(NodeProp& hprop, NodeProp& dprop, int dir, Role role); - -}; - -inline bool Grammar::check_constr(NodeProp& hprop, NodeProp& dprop, int dir, Role role) -{ - return - !hprop.forbidden[role] && - ( !right[role] || dir==1 ) && - ( !left[role] || dir==0 ) - ; -} - - -#endif Index: ld/app/src/dgp/main.cc =================================================================== --- _old/app/src/dgp/main.cc (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,121 +1,0 @@ - -/** - * Package: UAM Text Tools - * Component: dgp (dg parser) - * Version: 1.0 - * Author: Tomasz Obrebski - */ - -#include "global.hh" -#include "mgraph.hh" -#include "sgraph.hh" -#include "grammar.hh" -#include "dgp0.hh" -#include "../common/common.h" -#include "cmdline.h" - -#define MAXSEGMENTS 500 - -char segment[MAXSEGMENTS][MAXLINE]; -int segcount=0; -char seg_mnode[MAXSEGMENTS]; -char grammarfile[255]; - - -Grammar grammar; -MGraph mgraph; -SGraph sgraph; - -FILE* grammarf; -FILE* debugf=stdout; -unsigned int info=0U; - -void output(); - -main(int argc, char* argv[]) -{ - gengetopt_args_info args; - - if(cmdline_parser(argc,argv,&args) != 0) - exit(1); - - process_config_files(&args,argv[0]); - process_common_options(&args,argv[0]); - - if(!args.grammar_given) - fprintf(stderr,"dgp: no grammar given\n"); - - expand_path(args.grammar_arg,grammarfile); - - if(!(grammarf=fopen(grammarfile,"r"))) - fprintf(stderr,"dgp: grammar file not found: %s.\n", grammarfile), exit(1); - - if(args.debug_given) debug=true; - - for(char* c=args.info_arg; *c!='\0' ; ++c) - switch(*c) - { - case 'h': info|=SGraph::HEADS; break; - case 'd': info|=SGraph::DEPS; break; - case 's': info|=SGraph::SETS; break; - case 'c': info|=SGraph::CONSTRAINTS; break; - } - - grammar.read(grammarf); - fclose(grammarf); - - mgraph.clear(); - sgraph.clear(); - - char line[1000]; - while (fgets(line, MAXLINE+1, inputf)) - { - line[strlen(line)-1] = '\0'; - strcpy(segment[segcount],line); - - char segtype[80]; - - seg_mnode[segcount] = process_seg(line, args) ? mgraph.add_node(line) : -1; - - segcount++; - - getfield(line,"3",segtype); - if(strcmp(segtype,"EOS")==0) - { - dgp0(); // parametry!!! MGraph, SGraph, Grammar - output(); - - mgraph.clear(); - sgraph.clear(); - segcount=0; - } - // if(args.interactive_flag) { fflush(outputf); fflush(failedf); } - } - - fclose(inputf); - fclose(outputf); - cmdline_parser_free(&args); - exit(0); -} - -void output() -{ - for(int si=0; si=0) - { - MNode& m=mgraph.nodes[seg_mnode[si]]; - for(vector::iterator s=m.snodes.begin(); s!=m.snodes.end(); ++s) - { - fputs(segment[si],outputf); - sgraph.print_node(outputf, *s, info); - fputc('\n',outputf); - } - } - else - { - fputs(segment[si],outputf); - fputc('\n',outputf); - } - } -} Index: ld/app/src/dgp/mgraph.cc =================================================================== --- _old/app/src/dgp/mgraph.cc (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,54 +1,0 @@ - -#include "mgraph.hh" -#include "thesymbols.hh" -#include "const.hh" - -#include - -int MGraph::add_node(char* seg) -{ - nodes[n].clear(); - - char field1[80], field3[80], descr[256], gph[256]; - char* cat; - - getfield(seg,"1",field1); - nodes[n].pos=atoi(field1); - - getfield(seg,"3",field3); - if(!getfield(seg,"lem",descr)) strcpy(descr,"?,?"); - - cat=descr; - while(*cat!=',' && *cat ) ++cat; - if(*cat) ++cat; - -// Cat::add(cat); - if(Cat::index(cat)>0) - nodes[n].cat=cat; - else - nodes[n].cat="NULL"; - - nodes[n].pred.clear(); - - char* tok; - int previd; - - if(!getfield(seg,"gph",gph)) - { - fprintf(stderr,"No gph field. Aborting (sorry).\n"); - exit(1); - } - - char* ids=strtok(gph,":"); - if(n!=atoi(ids)){fprintf(stderr,"Invalid node id in line ?. Program aborted.\n"); exit(1); } - - char *preds; - while(preds=strtok(NULL,",")) - { - previd=atoi(preds); - nodes[n].pred.push_back(&nodes[previd]); - } - - return n++; -} - Index: ld/app/src/dgp/mgraph.hh =================================================================== --- _old/app/src/dgp/mgraph.hh (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,37 +1,0 @@ -#ifndef _MGRAPH_HH -#define _MGRAPH_HH - -#include - -#include "const.hh" -#include "thesymbols.hh" -#include "../common/common.h" - - -using namespace std; - -class MNode -{ -public: - - char type[MAXFORMLEN]; - Cat cat; - int pos; - vector pred; - vector snodes; - - void clear() { snodes.clear(); }; -}; - -class MGraph -{ - public: - - MNode nodes[MAXNODES]; - int n; - - void clear() { n=0; }; - int add_node(char* seg); -}; - -#endif Index: ld/app/src/dgp/sgraph.cc =================================================================== --- _old/app/src/dgp/sgraph.cc (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,165 +1,0 @@ -#include "global.hh" -#include "sgraph.hh" -#include "mgraph.hh" -#include "grammar.hh" -#include "const.hh" -#include - - -int SGraph::add_base_snode(MNode* mn) -{ - int nodeind=n; - SNode &node=nodes[n]; - - node.clear(); - - node.mnode=mn; - - for(vector::iterator pm=node.mnode->pred.begin(); pm!=node.mnode->pred.end(); ++pm) - for(vector::iterator ps=(*pm)->snodes.begin(); ps!=(*pm)->snodes.end(); ++ps) - if(nodes[*ps].in_LH) - { - node.LV.set(*ps); - if(nodes[*ps].saturated()) node.LV |= nodes[*ps].LH; - } - - mn->snodes.push_back(nodeind); - ++n; - - node.in_LH=true; - - return nodeind; -} - - -void SGraph::update_left(int headind, int depind) -{ - SNode &head=nodes[headind], &dep=nodes[depind]; - - if(dep.saturated()) head.LV |= dep.LV, head.LD |= dep.LD; -} - - -void SGraph::update_right(int headind, int depind) -{ - SNode &head=nodes[headind], &dep=nodes[depind]; - - dep.LH.set(headind); - if(head.saturated()) - dep.LH |= head.LH; -} - - -int SGraph::clone(int ancind, NodeProp newprop) -{ - int newind = n++; - SNode &newnode=nodes[newind]; - SNode &ancnode = nodes[ancind]; - - newnode.clear(); - newnode.prop=newprop; - newnode.mnode=ancnode.mnode; - newnode.mnode->snodes.push_back(newind); - return newind; -} - - -//------------------------------------------------------------------------- -//------------------------------------------------------------------------- - - -int SGraph::print_node(FILE* f, int n, unsigned int info) -{ - char buf[1000]; - sprint_node(buf,n,info); - fputs(buf,f); -} - -int SGraph::sprint_node(char* buf, int nodeind, unsigned int info) -{ - char* buf0=buf; - char descr[256]; - char nodeinfo[16]; - - SNode &node=nodes[nodeind]; - - buf+=sprintf(buf," dgp:%d",nodeind); - buf+=sprintf(buf, saturated(nodeind) ? ";s" : ";u"); - - bool cont=false; - if (info&HEADS) - { - buf+=sprintf(buf,";"); - for(vector::iterator h=node.heads.begin(); h!=node.heads.end(); ++h) - { - if(cont) buf+=sprintf(buf,","); else cont=true; - buf+=sprintf(buf,"++%s-%d/%d",h->role.str(),h->dst,h->anc); - } - } - - if (info&DEPS) - { - buf+=sprintf(buf,";"); - for(vector::iterator d=node.deps.begin(); d!=node.deps.end(); ++d) - { - // if(! nodes[d->dst].saturated()) continue; // NIE DRUKUJ NIENASYCONYCH PODRZEDNIKOW - if(cont) buf+=sprintf(buf,","); else cont=true; - buf+=sprintf(buf,"--%s-%d/%d",d->role.str(),d->dst,d->anc); - } - } - - if (info&SETS) - { - int ord=0; - buf+=sprintf(buf,";{"); - for(vector::iterator pm=node.mnode->pred.begin(); pm!=node.mnode->pred.end(); ++pm) - for(vector::iterator ps=(*pm)->snodes.begin(); ps!=(*pm)->snodes.end(); ++ps) - buf+=sprintf(buf, ord++ ? ",%d" : "%d", *ps); - buf+=sprintf(buf,"};{"); - ord=0;for(int j=0; j<=n; ++j) if(node.LV[j]) buf+=sprintf(buf, ord++ ? ",%d" : "%d", j); - buf+=sprintf(buf,"};{"); - ord=0;for(int j=0; j<=n; ++j) if(node.LH[j]) buf+=sprintf(buf, ord++ ? ",%d" : "%d", j); - buf+=sprintf(buf,"};{"); - ord=0;for(int j=0; j<=n; ++j) if(node.LD[j]) buf+=sprintf(buf, ord++ ? ",%d" : "%d", j); - buf+=sprintf(buf,"}"); - } - - if (info&CONSTRAINTS)// buf+=sprint_node_constraints(buf,n); - { - buf+=sprintf(buf,";"); - int cont=0; - for(Role i=1; i<=Role::count(); ++i) - if(node.prop.forbidden[i]) buf+=sprintf(buf,"%s!%s",(cont++)?",":"",i.str()); - for(Role i=1; i<=Role::count(); ++i) - if(node.prop.required[i]) buf+=sprintf(buf,"%s&%s",(cont++)?",":"",i.str()); - } - -// buf+=sprintf(buf,"\n"); - - return buf-buf0; -} - - -int SGraph::sprint_node_debug(char* buf, const char* pref, int n) -{ - char *buf0 = buf; - buf+=sprintf(buf,"#%s",pref); - buf+=sprint_node(buf,n,HEADS|DEPS|SETS|CONSTRAINTS); - buf+=sprintf(buf,"\n"); - return buf-buf0; -} - -int SGraph::print_node_debug(FILE* f, const char* pref, int n) -{ - char buf[1000]; - sprint_node_debug(buf,pref,n); - fputs(buf,f); -} - -void SGraph::print_arc(FILE* f, int left, int right, Role role, int dir) // 0 - left, 1 - right -{ - fprintf(f,"# %s:%s.%02d %s %s.%02d\n", - role.str(),nodes[left].mnode->type,left, - dir ? "-->" : "<--", - nodes[right].mnode->type,right); -} Index: ld/app/src/dgp/sgraph.hh =================================================================== --- _old/app/src/dgp/sgraph.hh (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,110 +1,0 @@ -#ifndef _SGRAPH_HH -#define _SGRAPH_HH - -#include - -#include -#include -#include - -#include "const.hh" -#include "thesymbols.hh" - - -using namespace std; - -class MNode; - - -struct Arc -{ - int dst; - Role role; - int anc; - - Arc(int d, Role r, int a) : dst(d), role(r), anc(a) {}; - }; - - -struct NodeProp -{ - bitset required; - bitset forbidden; - - bool operator==(const NodeProp& p) - { return required==p.required && forbidden==p.forbidden; } - - void clear() - { required.reset(), forbidden.reset(); } - -}; - - -struct SNode -{ - - MNode* mnode; - - NodeProp prop; - - bitset LV; - bitset LH; - bitset LD; - bool in_LH; - - vector heads; - vector deps; - - void clear() { prop.clear(), LV.reset(), LD.reset(), LH.reset(), heads.clear(), deps.clear(); } - bool saturated() { return prop.required.none(); } -}; - - - -class SGraph -{ -public: - - SNode nodes[MAXNODES]; - int n; // number of nodes - - enum Output { HEADS=1, DEPS=2, SETS=4, CONSTRAINTS=8 }; - - SGraph() : n(0) {} - - void clear() { n=0; } - - int add_base_snode(MNode* mn); - int clone(int ancind, NodeProp newprop); - void update_left(int headind, int depind); - void update_right(int headind, int depind); - - bool visible(int left, int right); - bool saturated(int node); - - //-------------------------------------------------------------------- - - void read(FILE* f); - void write(FILE* f, list nodelist, unsigned int info); - - int sprint_node(char* buf, int n, unsigned int info); - int print_node(FILE* f, int n, unsigned int info); - int sprint_node_debug(char* buf, const char* pref, int n); - int print_node_debug(FILE* f, const char* pref, int n); - - void print_arc(FILE* f, int left, int right, Role role, int dir); // 0 - left, 1 - right - -}; - - -inline bool SGraph::visible(int left, int right) -{ - return nodes[right].LV[left]; -} - -inline bool SGraph::saturated(int node) -{ - return nodes[node].saturated(); -} - -#endif Index: ld/app/src/dgp/symbol.cc =================================================================== --- _old/app/src/dgp/symbol.cc (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,39 +1,0 @@ -#include "symbol.hh" - -// CLASS symbols - -//int Symbols::_no_of_spaces=0; - -Symbols::~Symbols() -{ - while(!table.empty()) - { - free((void*)table.back()); - table.pop_back(); - } -} - -void Symbols::load(const char* filename) -{ - ifstream f(filename); - char s[100]; - while(f) - { - f >> s >> ws; - if(strlen(s)) add(s); - } -} - -void Symbols::add(const char* sym) -{ - if(hash.count(sym)==0) - { - char* symdup=strdup(sym); - hash[symdup]=table.size(); - table.push_back(symdup); - } -} - - -//template -//Symbols Symbol::defs; Index: ld/app/src/dgp/symbol.hh =================================================================== --- _old/app/src/dgp/symbol.hh (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,143 +1,0 @@ -#ifndef _SYMBOL_HH -#define _SYMBOL_HH - -#include -//#include -#include -#include -#include -#include -#include - -using namespace std; - -using __gnu_cxx::hash_map; -using __gnu_cxx::hash; - - -// Key comparison for the cstr_hash hash table -struct eqstr -{ - bool operator()(const char * s, const char* t) const - { return strcmp(s,t)==0; } -}; - - -// Hash table for storing symbols - -typedef hash_map,eqstr> cstr_hash; - -// Symbol table. Provides access to symbols through their index or name. - -class Symbols -{ - public: - - Symbols() { add("NULL"); }; - ~Symbols(); - - void load(const char* filename); - - int operator[](const char* s) { return hash[s]; }; - - const char* operator[](int i) { return table[i]; }; - - void add(const char* c); - - int count() { return table.size(); }; - - private: - - std::vector table; - cstr_hash hash; - -}; - -////////////////////////////////////////////////////////////////////// - -/// Symbol class template. -/** The template argument determines the symbol space. - Each space is created with symbol "NULL" with indexed 0 already in. -*/ - -template -class Symbol -{ - public: - - /// Load the contents of the symbol table from file. - static void define(const char *filename) - { defs.load(filename); } - - /// Add symbol s. - /** The string is duplicated. - */ - static Symbol add(const char* s) { defs.add(s); } - - /// Number of symbols. - static int count() { return defs.count(); }; - - /// First symbol. - static int first() { return 1; } - - /// Last symbol. - static int last() { return defs.count()+1; } - - /// Last symbol. - static int index(const char* s) { return defs[s]; } - - /// Just for tests. - static void print(); - - /// 0-argument constructor, default value is 0 ("NULL"). - Symbol() : val(0) {}; - - /// Constructing a symbol from its index. - /** No check is performed. - */ - - Symbol(int v) : val(v) {}; - - /// Constructing a symbol from its name (string to Symbol conversion). - /** If s is not a symbol name, the value of 0 ("NULL") is assigned. - */ - - Symbol(const char * s) : val(defs[s]) {}; - - /// Symbol to char* conversion. If symbol is invalid, NULL is returned. - const char* str() const { return (val>=0 && val s=1; s; s++ ) ... - s=0; while(++s) ... - */ - (operator int)() const { return val; }; - - Symbol operator++() {val++; return *this;} - - // bool operator<(Symbol& s) { return val < s.val; } - - - private: - static Symbols defs; - int val; -}; - -template -void Symbol::print() -{ - for(Symbol i=0; i -Symbols Symbol::defs; - -template -bool operator<(const Symbol& s, const Symbol& t) -{ - return (int)s < (int)t; -} - -#endif Index: ld/app/src/dgp/thesymbols.hh =================================================================== --- _old/app/src/dgp/thesymbols.hh (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,32 +1,0 @@ -#ifndef __THESYMBOLS__HH -#define __THESYMBOLS__HH - -#include "symbol.hh" -#include "const.hh" - -#include -#include -#include - - -using namespace std; - -typedef Symbol<1> Cat; - -typedef Symbol<2> Role; -typedef list RoleList; -typedef list::iterator RoleListIter; -typedef bitset RoleSet; -typedef set Roles; -typedef Roles::iterator RolesIter; - -typedef Symbol<3> Constr; -typedef list ConstrList; -typedef list::iterator ConstrListIter; - -typedef Symbol<4> Rel; - -typedef Symbol<5> Flag; -typedef bitset FlagSet; - -#endif Index: ld/app/src/dgp/tre =================================================================== --- _old/app/src/dgp/tre (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,304 +1,0 @@ -#!/usr/bin/ruby -I /usr/local/lib/utt -I $HOME/.local/lib/utt - -$: << "#{ENV['HOME']}/.local/lib/utt" -$: << "/usr/local/lib/utt" - -require 'getoptlong' -require 'seg.rb' - -opts = GetoptLong.new( -[ '--help', '-h', GetoptLong::NO_ARGUMENT ], -[ '--debug', '-d', GetoptLong::NO_ARGUMENT ], -[ '--format', '-F', GetoptLong::REQUIRED_ARGUMENT ], -[ '--info', '-I', GetoptLong::REQUIRED_ARGUMENT ], -[ '--only-trees','-t', GetoptLong::NO_ARGUMENT ]) - -$helptext= -"The program generates trees from the graph output by dgp. dgp must\n"+ -"must be run with '-i ds' option.\n\n"+ -"Command: tre [options]\n\n"+ -"Options:\n"+ -"--help -h Print help (this text) and exit.\n"+ -"--debug -d Verbose output. For developers only.\n"+ -"--format=s -F s Output format. Recognized values:\n"+ -" a root + list of arcs\n"+ -" p parenthesized notation\n"+ -" h human readable indented tree format\n"+ -" Multiple values are allowed. (default p)\n"+ -"--info=s -I s Information printed. Recognized values:\n"+ -" n node identifier\n"+ -" f surface form\n"+ -" m morphological information\n"+ -" l arc labels\n"+ -"--only-trees -t Do not copy input. Print trees only.\n" - -$DEBUG=false -$FORMAT='p' -$INFO='DEFAULT' -$ONLYTREES=false - -opts.each do |opt, arg| - case opt - when '--help' - print $helptext - exit 0 - when '--debug' - $DEBUG=true - when '--format' - $FORMAT=arg - when '--info' - $INFO=arg - when '--only-trees' - $ONLYTREES=true - else - print "Unknown option #{opt}. Ignored.\n" - end -end - -if $INFO=='DEFAULT' - case $FORMAT - when 'p','a' - $INFO='nl' - when 'h' - $INFO='fmnl' - end -end - -$dgpsep=';' - -def tre(input) - $gphid=[] - $form=[] - $lem=[] - nodes=[] - count=0 - seg=Seg.new - for line in input - print line unless $ONLYTREES - seg.set(line) - if dgp=seg['dgp'] - if nodes==[] && seg[3]!='BOS' - print "A sentence must start with BOS segment. Aborting.\n" - return - end - - id=dgp[/^\d+/].to_i - - if gph=seg['gph'] - $gphid[id]=gph[/^\d+/].to_i - else - print "No gph field. Aborting.\n" - return - end - - $form[$gphid[id]]=seg[4] - $lem[$gphid[id]]=seg['lem'] - - nodes[id] = [seg[1].to_i,dgp] - - if seg[3]=='EOS' - $pref = "#{seg[1]} #{seg[2]} SYN *" - parsegraph(nodes) - printgraph if $DEBUG - $thetrees=[] - gentrees2 - for t in $thetrees - count += 1 - t1=ground(t) - case $FORMAT - when /a/ - print "#{$pref} tre:#{count} arc:" - printarcs(t1[0],t1[1]) - print "\n" - when /p/ - print "#{$pref} tre:#{count} par:" - printpar(t1[0],t1[1]) - print "\n" - when /h/ - print "#\n# tree #{count}\n# ------\n" - printtree(t1[0],t1[1],0) - end - end - nodes=[] - end - end - end -end - - -def nodeinfo(id) - info="" - if $INFO =~ /n/ - info += id.to_s - info += '.' if $INFO =~ /[fm]/ - end - if $INFO =~ /f/ - info += $form[id] - info += ';' if $INFO =~ /m/ - end - if $INFO =~ /m/ - info += $lem[id] - end - info -end - - -def printarcs(root,arcs) - print nodeinfo(root) - for a in arcs - print ';' - print "#{a[2]}:" if $INFO =~ /l/ - print nodeinfo(a[0])+'-'+nodeinfo(a[1]) - end -end - -def printtree(root,arcs,o) - if o==0 - print "# %-16s" % "root: " - end - print nodeinfo(root),"\n" - for arc in arcs.select{ |a| a[0]==root }.sort{|a,b| a[1]<=>b[1] } - print '# '," "*(o+1) - print "%-16s" % (arc[2]+": ") - printtree(arc[1],arcs,o+1) - end -end - -def printpar(root,arcs) - print nodeinfo(root) - deps = arcs.select{ |a| a[0]==root }.sort{|a,b| a[1]<=>b[1] } - unless deps == [] - print '(' - cont=false - for arc in deps - if cont then print ',' else cont=true end - print arc[2],':' if $INFO =~ /l/ - printpar(arc[1],arcs) - end - print ')' - end -end - - -def parsegraph(nodes) - - $n =nodes.length - $sat =[]; - - $vis =[]; - $succ=[]; - $lhs =[]; - $arcs=[]; - $pos=[] - - for dgp in nodes - - parts = dgp[1].split($dgpsep,6) - - if parts[3]==nil || parts[4]==nil || parts[5]==nil - $stderr.print "ERR: tre requires dgp be called with '--info s' option. Aborting.\n" - exit - end - - i = parts[0].to_i - $pos[i] = dgp[0].to_i - $sat << i if parts[1]=="s" - $arcs |= parts[2].split(',').map{ |a| case a - when /\-\-(\w+)-(\d+)\/(\d+)/ - [i, $2.to_i, $1, $3.to_i] - when /\+\+(\d+)-(\w+)\/(\d+)/ - [$1.to_i, i, $2, $3.to_i] - end } - $succ |= parts[3][1..-2].split(',').map{|x| [x.to_i,i]} - $vis |= parts[4][1..-2].split(',').map{|x| [x.to_i,i]} - $lhs |= parts[5][1..-2].split(',').map{|x| [x.to_i,i]} + [[i,i]] - - end -end - - -def ground(t) - [ $gphid[t[0]] , t[1].map{|a| [$gphid[a[0]],$gphid[a[1]],a[2]]} ] -end - - -def gentrees2() - $thetrees=[]; - bos=0; eos=$n-1; - roots = (1...eos).select{|i| $vis.include? [i,eos]}.select{|i| $vis.include? [bos,i]} - if $DEBUG then print "ROOTS: #{roots.inspect}\n" end - for i in roots - $theroot=i - for r in buildR(i , eos, []) - (rmin,rmax,rtree) = r - buildR(bos, rmin, rtree) - end - end -end - - -def buildR(min, max, tree) - if $DEBUG then print "buildR--#{min}--#{max}--#{tree.inspect}\n" end - trees=[] - for a in $arcs.select{|a| a[0]==max && $vis.include?([min,a[1]]) } - if $DEBUG then print "ARC: #{a.inspect}\n" end - for r in buildR(a[1],a[3],tree+[a]) - (rmin,rmax,rarcs) = r - for l in buildR(min,rmin,rarcs) - (lmin,lmax,larcs) = l - trees << [lmin,rmax,larcs] - end - end - end - for i in (0...$n).select{|i| $succ.include?([i,max])}.select{|i| $lhs.include?([min,i])} - for l in buildL(min,i,tree) - (lmin,lmax,larcs) = l - trees << [lmin,lmax,larcs] - end - end - trees -end - - -def buildL(min,max,tree) - if $DEBUG then print "buildL--#{min}--#{max}--#{tree.inspect}\n" end - if $pos[min]==$pos[max] - if min==0 && max==0 - $thetrees.push [$theroot,tree] - if $DEBUG then print "adding tree: #{tree.inspect}\n" end - end - return [[max,max,tree]] - end - trees=[] - for arc in $arcs.select{|a| a[1]==max && $lhs.include?([min,a[0]]) } - if $DEBUG then print "ARC: #{arc.inspect}\n" end - for r in buildR(arc[3],max,tree+[arc]) - (rmin,rmax,rarcs) = r - for l in buildL(min,rmin,rarcs) - (lmin,lmax,larcs) = l - trees << [lmin,lmax,larcs] - end - end - end - trees -end - - -def printgraph() - - print "N: #{$n}\n" - print "SAT: #{set_to_s($sat)}\n" - print "SUCC: #{rel_to_s($succ)}\n" - print "VIS: #{rel_to_s($vis)}\n" - print "LHS: #{rel_to_s($lhs)}\n" - print "ARCS: #{arcs_to_s($arcs)}\n" -end - -def set_to_s(s) "{#{s.join(',')}}" end -def rel_to_s(r) "{#{r.map{|p| "(#{p[0]},#{p[1]})"}.join(',')}}" end -def arc_to_s(q) "-#{q[0]}-#{q[2]}-#{q[1]}/#{q[3]}" end -def arcs_to_s(a) "{#{a.map{|q| arc_to_s(q)}.join(',')}}" end - -###################################################################### - -tre($stdin) Index: ld/app/src/dgp/uttcommon.c =================================================================== --- _old/app/src/dgp/uttcommon.c (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,2 +1,0 @@ -#include "uttcommon.h" - Index: ld/app/src/dgp/uttcommon.h =================================================================== --- _old/app/src/dgp/uttcommon.h (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,146 +1,0 @@ -#ifndef __COMMON_H -#define __COMMON_H - -#include - -/************************************************** - * Stale dotyczace wejscia/wyjscia - */ - -#define MAXLINE 1024 - -#define EMPTYFORM '*' -#define INFIELD_SEP ':' -#define MAXAUX 16 -#define FIELD_SEP " \t\n" - - -/***************************************************************/ -/* problems with casing */ -/* sprawdzenie wielkosci liter */ -/* warto¶æ zwracana: */ -/* 0 - wszystkie ma³e litery, 1 - pierwsza wielka, reszta male */ -/* 2 - wszystkie wielkie, 3 - inne */ -/***************************************************************/ -inline int casing(char* s) -{ - int ret = isupper(*s) ? 1 : 0; - while(*++s != '\0') - { - if(isupper(*s)) - { - if(ret==1) ret=2; - else if(ret==0) ret=3; - } - else - { - if(ret==2) ret=3; - } - } - return ret; -} - -// -inline void tolowers(char* s, char* d) -{ - *d=tolower(*s); - while(*s != '\0') * ++d = tolower(* ++s); -} - - -// przepisuje s do d -// nadajac wielko¶æ liter zgodnie z warto¶ci± casing -// casing - warto¶æ zwracana przez casing() -// je¶li casing==3 przepisuje bez zmian (za ma³o informacji) -inline void restorecasing(char *s, char *d, int casing) -{ - switch(casing) - { - case 0: - case 3: - *d=*s; - while(*s != '\0') * ++d = * ++s; - break; - case 1: - *d=toupper(*s); - while(*s != '\0') * ++d = * ++s; - break; - case 2: - *d=toupper(*s); - while(*s != '\0') * ++d = toupper(* ++s); - break; - } -} - - -/**************************************************/ -/* -parameters: - -seg - segment - -name - field name - +val - field contents -return value: - 1 if specified field exists, 0 otherwise -*/ - -inline int getfield(char* seg, const char* pref, char* val) -{ - char* p=seg; - - while(isspace(*p)) ++p; - - pos: - if(isdigit(*p) or *p=='*') while(!isspace(*p)) ++p; - else goto type; - - while(isspace(*p)) ++p; - - len: - if(isdigit(*p) or *p=='*') while(!isspace(*p)) ++p; - else goto type; - - while(isspace(*p)) ++p; - - type: - while(isspace(*p)) ++p; while(!isspace(*p)) ++p; - - while(isspace(*p)) ++p; - - form: - while(isspace(*p)) ++p; while(!isspace(*p)) ++p; - - annotation: - do p=strstr(p,pref); while(p!=NULL && *(p-1)!=' ' && *(p-1)!='\t'); - - if(p==NULL) return 0; - else - { - p+=strlen(pref); - int len=strcspn(p,FIELD_SEP "\n\r\f\0"); - strncpy(val,p,len); - val[len]='\0'; - return 1; - } -} - - -/* -parameters: - +seg - segment - -pref - prefix of the new field - -val - contents of the new field -return value: - 1 - success, 0 - fail (limit on segment length exceeded) -*/ -inline int addfield(char *seg, const char *pref, const char *val) - // zalozenie, ze seg konczy sie znakiem \n -{ - if(strlen(seg)+strlen(pref)+strlen(val) >= MAXLINE) return 0; // bezpieczniej, ale wolniej - - int seglen=strlen(seg); - sprintf(seg+(seglen-1)," %s%s\n",pref,val); - return 1; -} - - -#endif Index: ld/app/src/gue/Makefile =================================================================== --- _old/app/src/gue/Makefile (revision 7bed30fe7b80d29bc4822f7fd44163fa37a454fd) +++ (revision ) @@ -1,42 +1,0 @@ -PAR=-Wno-deprecated -O3 -fpermissive -static -PAR2=-c -Wno-deprecated -O3 -fpermissive -LIB_PATH=../lib -COMMON_PATH=../common -CMDLINE_FILE='"../gue/cmdline.h"' - - -gue: main.cc guess.o $(LIB_PATH)/auttools.o $(LIB_PATH)/word.o \ - cmdline.c common_guess.o common.o - g++ $(PAR) main.cc guess.o \ - $(LIB_PATH)/auttools.o $(LIB_PATH)/word.o cmdline.c common.o common_guess.o \ - -o gue - -guess.o: guess.h guess.cc - g++ $(PAR2) guess.cc - -common_guess.o: cmdline.h common_guess.cc common_guess.h - g++ $(PAR2) common_guess.cc - -common.o: $(COMMON_PATH)/cmdline_common.ggo $(COMMON_PATH)/common.cc \ - $(COMMON_PATH)/common.h - g++ $(PAR2) -D _CMDLINE_FILE=$(CMDLINE_FILE) $(COMMON_PATH)/common.cc - -cmdline.c cmdline.h: cmdline.ggo - gengetopt -i cmdline.ggo --conf-parser - -cmdline.ggo: cmdline_guess.ggo $(COMMON_PATH)/cmdline_common.ggo - cat cmdline_guess.ggo $(COMMON_PATH)/cmdline_common.ggo > cmdline.ggo - - -clean: clean.cmdline - rm *.o || true - rm gue || true - - -clean.cmdline: - rm cmdline.* || true - -copy: -ifdef UTT_BIN_DIR - cp gue ${UTT_BIN_DIR} -endif Index: ld/app/src/gue/cmdline_guess.ggo =================================================================== --- _old/app/src/gue/cmdline_guess.ggo (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,12 +1,0 @@ -package "guess" -version "0.1" - -option "guess_count" n "Guess up to n descriptions" int default="0" no -option "delta" - "Stop displaying answers after fall of weight" float default="0.2" no -option "cut-off" - "Do not display answers with less weight than cut-off" int default="200" no -option "dictionary-home" - "dh" string typestr="FILENAME" no hidden -option "dictionary" d "File with dictionary information" string typestr="filename" default="gue.bin" no -option "per-info" v "Display performance information" flag off -option "weights" w "Print weights" flag off -option "no-uppercase" - "Do not process form containing uppercase letters" flag off - Index: ld/app/src/gue/common_guess.cc =================================================================== --- _old/app/src/gue/common_guess.cc (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,60 +1,0 @@ -#include -#include -#include "common_guess.h" - -int guess_count=0; -double delta=0.1; -int cut_off=100; -char dictionary[255]; -bool per_info=false; -bool weights=false; - -void process_guess_options(gengetopt_args_info* args) -{ - - if(args->dictionary_given) - { - expand_path(args->dictionary_arg,dictionary); - if(file_accessible(dictionary)!=0) - { - fprintf(stderr,"Cannot open the dictionary file: %s\nAborting.\n",dictionary); - exit(1); - } - } - else if (args->dictionary_home_given && args->language_given) - { - char buf[255]; - expand_path(args->dictionary_home_arg, buf); - sprintf(dictionary,"%s/%s/gue.bin",buf,args->language_arg); - if(file_accessible(dictionary)!=0) - { - fprintf(stderr,"Cannot open the dictionary file: %s\nAborting.\n",dictionary); - exit(1); - } - } - - if(args->guess_count_given) - guess_count=args->guess_count_arg; - else - guess_count=0; - - if(guess_count==0) - guess_count=100; - - if(args->delta_given) - delta=args->delta_arg; - else - delta=0.1; - - if(args->cut_off_given) - cut_off=args->cut_off_arg; - else - cut_off=100; - - if(args->per_info_given) - per_info=args->per_info_flag; - - if(args->weights_given) - weights=true; - -} Index: ld/app/src/gue/common_guess.h =================================================================== --- _old/app/src/gue/common_guess.h (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,20 +1,0 @@ -#ifndef __COMMON_GUESS_H -#define __COMMON_GUESS_H - -#include -#define _CMDLINE_FILE "../gue/cmdline.h" -#include "../common/common.h" -#include "cmdline.h" - -#define DIC_FILE "gue.bin" - -extern int guess_count; -extern double delta; -extern int cut_off; -extern char dictionary[]; -extern bool per_info; -extern bool weights; - -void process_guess_options(gengetopt_args_info* args); - -#endif Index: ld/app/src/gue/guess.cc =================================================================== --- _old/app/src/gue/guess.cc (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,142 +1,0 @@ - -#include "guess.h" - -#include -#include -#include -#include -#include - -#define DICT 1 -#define COR 2 -#define DICT_P 3 -#define COR_P 4 - -#define W_PRE 0.1 -#define W_SUF 0.9 - -#define PREF_SIGN '_' - - -using namespace std; - - -Guess::Guess(const char* suf_file) - : _suf(suf_file) { - /* _suf = NULL; - _pref = NULL; - - if (strlen(suf_file) > 0) - _suf = new TFTiv(suf_file); - if (strlen(pref_file) > 0) - _pref = new TFTiv(corp_file); - */ -} - - - char buf[MAX_LINE]; - char out[MAX_LINE]; - char* buf0_s = buf; - char* word_t = NULL; - long state_s = 0; - unsigned length_s = buf0_s - buf; - long len = 0; - int i=0; - -int Guess::ana(const char* word, Words& result) { - - assert(word && &result); - - /* Word zawiera wyraz, ktory mamy zbadac. - * Nalezy przepisac go w odwrotnej kolejnosci do bufora, - * znalezc najdluzszy prefiks pasujacy do tego bufora - * separatorem jest '/' - za tym znakiem znajduje sie - * prawdopodobienstwo wystapienia danego opisu */ - - buf0_s = buf; - word_t = strdup(word); - - if (reverse(word, buf) != 0) - return -1; - - - - state_s = -1; - // printf("#buf0_s=%s, ", buf0_s); - state_s = _suf.pref(buf0_s, PREF_SIGN); - // printf("#word=%s, buf0_s=%s\t", word, buf0_s); - /* jezeli state_s != -1 to oznacza, ze w slowniku jest zawarta - * informacja o prefiksie tego slowa. - * nie jest ona odwrocona, wiec porownujemy do word a nie do buf - */ - // printf("state_s=%d\t", state_s); - if (state_s != -1) { - state_s = _suf.pref(word_t, '~', state_s); - // printf("state_s(wp)=%d, word_t=%s, word=%s\n", state_s, word_t, word); - } - if (state_s == -1) { - // if (_suf != NULL) - buf0_s = buf; - state_s = _suf.pref(buf0_s, '~'); - // printf("state_s=%d\n", state_s); - } - - length_s = buf0_s - buf; - - /* state jest stanem, od ktorego zaczyna sie sciezka opisujaca - * prawdopodobienstwo przeciwienstwa wystapienia opisu - * znajdujacego sie dalej na tej sciezce. - * Im mniejsza wartosc liczby tym wieksze prawdopodobienstwo */ - - len = 0; - i=0; - - // if (_suf != NULL) - len = _suf.cont(state_s, out); - while (len > 0) { - i++; - add_word_prob(result, word, out, length_s, DICT); - len = _suf.cont(-1, out); - } - - return i; - -} - - -int Guess::add_word_prob(Words& tab, const char* word, const char* path, unsigned len, int source) { - - /* Dodaje do tablicy tab wyraz word wraz - * z prawdopodobienstwem i opisem zawartym - * w sciezce path */ - - // printf("add_word_prob("); - // fflush(stdout); - char p[MAX_LINE]; - - strcpy(p, path); - - int probLen = strcspn(p, ";"); - char prob[probLen+1]; - strncpy(prob, p, probLen); - prob[probLen] = '\0'; - - char* desc = p + probLen+1; // +2 bo pomijamy jeszcze znak ';' - - int i = tab.add(word, desc); - - if (source==DICT) { - tab[i].len_suf(len); - tab[i].w_suf(atof(prob)); // + W_PRE*tab[i].w_suf())); - // tab[i].w_suf((float)(W_SUF*(1000-atof(prob)) + W_PRE*tab[i].w_suf())); - } -// if (source==COR) { -// tab[i].len_pref(len); -// tab[i].w_pref(W_SUF*(1000-atof(prob)) + W_PRE*tab[i].w_pref()); -// } -// printf(")\n"); -// fflush(stdout); - - return i; - -} Index: ld/app/src/gue/guess.h =================================================================== --- _old/app/src/gue/guess.h (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,56 +1,0 @@ - -#include "../lib/tfti.h" -#include "../lib/word.h" - -#include - -/************************************************************** - * Zawiera definicje klasy Guess. * - * * - * Klasa ta pozwala na okreslenie opisu slowa nie * - * znajdujacego sie w slowniku wraz z prawdopodobienstwem * - * jego wystapienia. * - *************************************************************/ - -class Guess { - - public: - - // nazawa pliku slownika w parametrze - Guess(const char* suf_file); - - // zwraca tablice opisow slowa wraz z prawdopodobienstwem ich wystapienia - int ana(const char* word, Words& result); - - long time_overall; - - private: - - // sufiksy - TFTiv _suf; - - // prefiksy - TFTiv _pref; - - //odwraca ciag znakow - int reverse(const char* src, char* dest) { - - // assert((src != NULL) && (dest != NULL)); - - const char* c = src; - - int len = strlen(src); - - for (int i=1; i<=len; ++i) { - dest[i-1] = src[len-i]; - } - - dest[len] = '\0'; - - return 0; - } - - //dodaje nowy element do tablicy WordsProb - int add_word_prob(Words& tab, const char* word, const char* path, unsigned len, int source); - -}; Index: ld/app/src/gue/main.cc =================================================================== --- _old/app/src/gue/main.cc (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,237 +1,0 @@ -#include -#include -#include "../lib/iotools.h" -#define _CMDLINE_FILE "../gue/cmdline.h" -#define CONFIGFILE1 "/home/ynka/utt/utt-0.9/conf/gue.conf" -#define CONFIGFILE2 "/home/ynka/utt/utt-0.9/conf/gue.conf" -#include "../common/common.h" -#include "common_guess.h" -#include "guess.h" -#include "cmdline.h" - -#define W_SUFF 0.6 -#define W_PREF 0.4 - - -int main(int argc, char** argv) { - - // int non_standard_config=0; - - gengetopt_args_info args; - - if(cmdline_parser(argc, argv, &args) != 0) - exit(1); - - process_config_files(&args,argv[0]); - process_common_options(&args,argv[0]); - process_guess_options(&args); - - char line[MAX_LINE]; - char outline[MAX_LINE]; - char parms[MAX_LINE], desc[MAX_LINE], lemma[MAX_LINE]; - long line_count = 0; - - Guess guess(dictionary); - int words_count=0; - time_t start_time = time(NULL); - - // Segment seg; - Words tab; - while (fgets(line, MAX_LINE, inputf)) - { - line_count++; - int start, len; - - // line[strlen(line)-1] = '\0'; - - if (!process_seg(line, args)) - fputs(line,outputf); - else - { - char form[MAX_FORM]; - words_count++; - tab.clear(); - getfield(line,input_field_prefix,form); - if (form==NULL) continue;//BZDURA - - guess.ana(form, tab); - - if ((tab.count()==0) && (!args.no_fail_flag)) // no guesses - analysis was unsuccessful - fputs(line, failedf); - else - { - -// if (copy_processed) -// fputs(line, stdout); -// continue; -// } - // we've got some guesses. Do we want to print it? -// if (args.only_fail_flag) -// continue; - - float last_weight=0; - int i=0; - int count=0; - unsigned first=1; - char* parms_end = parms; - char last_lemma[MAX_LINE]; - - count = 1; - - tab.sort(); - - while (count < tab.count() && count <= guess_count) - if (first || tab[count].w_suf() >= cut_off && tab[count].w_suf() >= delta * last_weight) - { - first=0; - last_weight = tab[i].w_suf(); - count++; - } - else - break; - - // drukujemy count pierwszych z tab - - - if(one_line) - { - char* descp=desc; - for (int i=0; i< count; ++i) - { - descp += sprintf(descp," %s%s,%s", output_field_prefix, tab[i].lemma(), tab[i].descr()); - if(weights) descp += sprintf(descp,":%d",(int)tab[i].w_suf()); - } - strcpy(outline,line); - outline[strlen(outline)-1]='\0'; - strcat(outline,desc); - strcat(outline,"\n"); - fputs(outline, outputf); - if (copy_processed) - fputs(line,outputf); - } - else if(one_field) - { - char* descp=desc; - for (int i=0; i< count; ++i) - if(i==0) - { - descp += sprintf(descp," %s%s,%s", output_field_prefix, tab[i].lemma(), tab[i].descr()); - if(weights) descp += sprintf(descp,":%d",(int)tab[i].w_suf()); - } - else - { - if(strcmp(tab[i].lemma(),tab[i-1].lemma())==0) - descp += sprintf(descp,",%s",tab[i].descr()); - else - descp += sprintf(descp,";%s,%s",tab[i].lemma(),tab[i].descr()); - if(weights) descp += sprintf(descp,":%d",(int)tab[i].w_suf()); - } - - strcpy(outline,line); - outline[strlen(outline)-1]='\0'; - strcat(outline,desc); - strcat(outline,"\n"); - fputs(outline, outputf); - if (copy_processed) - fputs(line,outputf); - } - else - { - for (int i=0; i< count; ++i) - { - // kolejne opisy - kolejne linie. - char* descp=desc; - descp += sprintf(desc, " %s%s,%s", output_field_prefix, tab[i].lemma(), tab[i].descr()); - if(weights) descp += sprintf(descp,":%d",(int)tab[i].w_suf()); - descp += sprintf(descp,"\n"); - strcpy(outline,line); - outline[strlen(outline)-1]='\0'; - strcat(outline,desc); - fputs(outline, outputf); - } - if (copy_processed) - fputs(line,outputf); - } - } - } - if(args.interactive_flag) - fflush(outputf), fflush(failedf); - - } - cmdline_parser_free(&args); -} - - - - - - - - -// while ((i=tab.next()) != -1 && count++ cmdline.ggo - -copy: -ifdef UTT_BIN_DIR - cp kor ${UTT_BIN_DIR} -endif - -clean: clean.cmdline - rm *.o || true - rm kor || true - -clean.cmdline: - rm cmdline.* || true - Index: ld/app/src/kor/cmdline_cor.ggo =================================================================== --- _old/app/src/kor/cmdline_cor.ggo (revision 7bed30fe7b80d29bc4822f7fd44163fa37a454fd) +++ (revision ) @@ -1,13 +1,0 @@ -package "kor" -version "0.1" - -option "dictionary-home" - "Dictionary home dir." string typestr="FILENAME" no hidden -option "dictionary" d "Dictionary" string typestr="FILENAME" default="cor.bin" no -option "distance" D "Maximal edit distance." int default="1" no -option "replace" r "Replace original form with corrected form, place original form in the cor field. This option has no effect in single mode" flag off -#option "single" - "Place all alternatives in the same line" flag off -option "weights" w "File with translation rules." string typestr="FILENAME" default="weight.cor" no -option "threshold" t "Edit distance threshold" float default="1" no -option "show-scores" - "Show scores" flag off -option "count" n "Print only count best results" int no - Index: ld/app/src/kor/common_cor.cc =================================================================== --- _old/app/src/kor/common_cor.cc (revision 7bed30fe7b80d29bc4822f7fd44163fa37a454fd) +++ (revision ) @@ -1,48 +1,0 @@ -#include -#include -#include "common_cor.h" - -#define MAX_PATH_LENGTH 255 - -char dictionary[MAX_PATH_LENGTH]; -char file_weights[MAX_PATH_LENGTH]; -float threshold; -bool show_scores = false; -int result_count; - -void process_cor_options(gengetopt_args_info* args) -{ - if(args->dictionary_given) - { - expand_path(args->dictionary_arg,dictionary); - if(file_accessible(dictionary)!=0) - { - fprintf(stderr,"Cannot open the dictionary file: %s\nAborting.\n",dictionary); - exit(1); - } - } - else if (args->dictionary_home_given && args->language_given) - { - char buf[MAX_PATH_LENGTH]; - expand_path(args->dictionary_home_arg, buf); - sprintf(dictionary,"%s/%s/cor.bin",buf,args->language_arg); - if(file_accessible(dictionary)!=0) - { - fprintf(stderr,"Cannot open the dictionary file: %s\nAborting.\n",dictionary); - exit(1); - } - } - - expand_path(args->weights_arg, file_weights); - - threshold = args->threshold_arg; - - show_scores = args->show_scores_flag; - - if(args->count_given) { - result_count = args->count_arg; - } - else { - result_count = 0; - } -} Index: ld/app/src/kor/common_cor.h =================================================================== --- _old/app/src/kor/common_cor.h (revision 7bed30fe7b80d29bc4822f7fd44163fa37a454fd) +++ (revision ) @@ -1,25 +1,0 @@ -#ifndef __COMMON_COR_H -#define __COMMON_COR_H - -// SEKCJA STALYCH - -#define MAX_LEN 2 -#define PREC 1000 -#define Weight int - -// SEKCJA INCLUDOW -#include "../common/common.h" -#include "cmdline.h" - - -// SEKCJA GENGETOPT -extern int change_count; -extern void process_cor_options(gengetopt_args_info* args); -extern char dictionary[]; -extern char file_weights[]; -extern float threshold; -extern bool show_scores; -extern int result_count; - -#endif - Index: ld/app/src/kor/corlist.cc =================================================================== --- _old/app/src/kor/corlist.cc (revision 7bed30fe7b80d29bc4822f7fd44163fa37a454fd) +++ (revision ) @@ -1,70 +1,0 @@ -#include -#include -#include "corlist.h" - -#define min(x,y) ((xMAX_LEN) { printf("ERROR in file %s: the string '%s' exceeds maximum length of %d characters.\n",Name,a,MAX_LEN); fclose(f); return -1; } - if (w.lb>MAX_LEN) { printf("ERROR in file %s: the string '%s' exceeds maximum length of %d characters.\n",Name,b,MAX_LEN); fclose(f); return -1; } - strcpy(w.a,a), strcpy(w.b,b); - total++; - List = (CorWeight*)realloc(List,total*sizeof(CorWeight)); - List[total-1]=w; - // printf("%s\t<->\t%s\t%1.2f\n",w.a,w.b,((float)w.w/PREC)); - } - } - fclose(f); - // printf("Total: %d\n\n",total); - return(total); -} Index: ld/app/src/kor/corlist.h =================================================================== --- _old/app/src/kor/corlist.h (revision 7bed30fe7b80d29bc4822f7fd44163fa37a454fd) +++ (revision ) @@ -1,20 +1,0 @@ -#ifndef _CORLIST_H -#define _CORLIST_H - -//#include -#include "common_cor.h" - -typedef struct { char a[MAX_LEN+1],b[MAX_LEN+1]; Weight w; short la,lb; } CorWeight; - -class CorList -{ - private: - CorWeight *List; - int total; - public: - Weight cor_stdcor, cor_xchg; - int loadCWL(char *Name); - Weight GetValue(char X[100], char Y[100], Weight (*H2)[100], int i, int j); -}; - -#endif Index: ld/app/src/kor/corr.cc =================================================================== --- _old/app/src/kor/corr.cc (revision 7bed30fe7b80d29bc4822f7fd44163fa37a454fd) +++ (revision ) @@ -1,163 +1,0 @@ -//--------------------------------------------------------------------------- -#include "common_cor.h" -#include "corr.hh" - -#define MAXPATH 256 - -#define min(x,y) ((xy)?(x):(y)) - - -Weight Corr::ed(int i,int j) -{ - if(i==-1) - return (j+1)*CL.cor_stdcor; // moje* Nie wiem czy tak bêdzie dobrze, ale uzna³em, ¿e poza tablic¹ powinny byæ wartosci przemno¿one przez wagê standardowej zmiany litery - if(j==-1) - return (i+1)*CL.cor_stdcor; // moje* - if(i==-2 || j==-2) - return (n+1)*CL.cor_stdcor; // moje* - - if(X[i]==Y[j]) - return min(H2[i-1][j-1], min(CL.cor_stdcor+min(H2[i][j-1],H2[i-1][j]),CL.GetValue(X,Y,H2,i,j))); - if(X[i-1]==Y[j] && X[i]==Y[j-1]) - return min(min(CL.cor_xchg+H2[i-2][j-2],CL.cor_stdcor+min(H2[i][j-1],H2[i-1][j])), CL.GetValue(X,Y,H2,i,j)); - return min(CL.cor_stdcor+min(H2[i-1][j-1],min(H2[i][j-1],H2[i-1][j])), CL.GetValue(X,Y,H2,i,j)); - -/* // wersja z wagami ale dla floatów - if(X[i]==Y[j])//zielone-> <- niebieskie -> <- rózowe -> - return min(H2[i-1][j-1], min(1+min(H2[i][j-1],H2[i-1][j]),CL.GetValue(X,Y,H2,i,j))); - if(X[i-1]==Y[j] && X[i]==Y[j-1]) - return min(1+min(H2[i-2][j-2],min(H2[i][j-1],H2[i-1][j])), CL.GetValue(X,Y,H2,i,j)); - return min(1+min(H2[i-1][j-1],min(H2[i][j-1],H2[i-1][j])), CL.GetValue(X,Y,H2,i,j)); -*/ - -/* // normalna wersja - if(X[i]==Y[j]) - return H2[i-1][j-1]; - if(X[i-1]==Y[j] && X[i]==Y[j-1]) - return 1+min(H2[i-2][j-2],min(H2[i][j-1],H2[i-1][j])); - return 1+min(H2[i-1][j-1],min(H2[i][j-1],H2[i-1][j])); -*/ - -/* - if(X[i]==Y[j]) - return H[(i-1)+2][(j-1)+2]; - if(X[i-1]==Y[j] && X[i]==Y[j-1]) - return 1+min(H[(i-2)+2][(j-2)+2],min(H[(i)+2][(j-1)+2],H[(i-1)+2][(j)+2])); - return 1+min(H[(i-1)+2][(j-1)+2],min(H[(i)+2][(j-1)+2],H[(i-1)+2][(j)+2])); -*/ -} - -int Corr::load2(char *Name) // moje -{ - return CL.loadCWL(Name); -} - -Weight Corr::cuted(int j) -{ - int l=max(0,j-t); - int u=min(m,j+t); - Weight ce=(j+t)*PREC; // moje* - for(int k=l;k<=u;k++) - { - if(H2[k][j]0) - j--; - else - more=0; - while(more && !continued(path[j])); - state=path[j]+1; - } - return count; -} - - -//--------------------------------------------------------------------------- - Index: ld/app/src/kor/corr.hh =================================================================== --- _old/app/src/kor/corr.hh (revision 7bed30fe7b80d29bc4822f7fd44163fa37a454fd) +++ (revision ) @@ -1,39 +1,0 @@ -//--------------------------------------------------------------------------- -#ifndef _corr_hh -#define _corr_hh -//--------------------------------------------------------------------------- - -#include "../lib/tfti.h" -#include "../lib/word.h" -#include "corlist.h" -#include "../common/common.h" - -class Corr : public TFTiv -{ -private: - Weight H[100][100]; - char X[100]; // misspelled string - char Y[100]; // (possibly partial) candidate string - int m; // length of X - int n; // maximal length of Y - - Weight ed(int,int); - Weight cuted(int); - void recomputeH(int); - - -public: - Weight (*H2)[100]; // moje: zmiana z int na Weight (float) - int t; // threshold - CorList CL; // moje - - Corr() : H2((Weight(*)[100])&H[2][2]) {}; // moje (int->float) - Corr(const char* a) : TFTiv(a), H2((Weight(*)[100])&H[2][2]) { }; - - int correct(const char* w, Words& tab); - - int load2(char *Name); // moje -}; - -//--------------------------------------------------------------------------- -#endif Index: ld/app/src/kor/main.cc =================================================================== --- _old/app/src/kor/main.cc (revision 7bed30fe7b80d29bc4822f7fd44163fa37a454fd) +++ (revision ) @@ -1,174 +1,0 @@ -#include -#include -#include "../lib/iotools.h" -#include "common_cor.h" -#include "corr.hh" -#include - - -int main(int argc, char** argv) { - -// setlocale(LC_CTYPE,""); -// setlocale(LC_COLLATE,""); - - gengetopt_args_info args; - - if(cmdline_parser(argc, argv, &args) != 0) - exit(1); - - process_config_files(&args,argv[0]); - process_common_options(&args,argv[0]); - process_cor_options(&args); - - Corr cor; - - //!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! -// strcpy(dictionary,"cor.bin"); - - cor.load(dictionary); - cor.t=args.distance_arg; - - //>>>>>>>>>>>>>>> - cor.CL.cor_stdcor=1*PREC; - cor.CL.cor_xchg=1*PREC; - if (cor.load2(file_weights)==-1) return -1; // moje - cor.t=1*PREC; // ODLEGLOSC EDYCYJNA - //<<<<<<<<<<<<<< - - char line[MAX_LINE+1]; - long line_count = 0; - - Segment seg; - Words tab; - char form1[MAX_LINE]; - char* form; - int formcasing; - char corfield[MAX_LINE]=""; - - while (fgets(line, MAX_LINE, inputf)) - { - ++line_count; - char outline[128]; - - if (!process_seg(line, args)) - fputs(line, outputf); - else - { - char form[MAX_FORM]; - - tab.clear(); - getfield(line,input_field_prefix,form); - if (form==NULL) continue; - - formcasing=3; - cor.correct(form, tab); - - if( tab.count() == 0 ) - { - formcasing=casing(form); - if( formcasing == 1 || formcasing == 2) - tolowers(form, form1), cor.correct(form1, tab); - } - - if ( tab.count() == 0) - fputs(line, failedf); - else - { - tab.sort(); - - int max_cnt = 0; - if(result_count < 1) { - max_cnt = tab.count(); - } - else { - max_cnt = (tab.count() < result_count) ? tab.count() : result_count; - } - - if(args.replace_flag) - { - char corfield[128]; - strcpy(corfield, input_field_prefix); - strcat(corfield, form); - seg.aux[seg.auxn]=corfield; - ++seg.auxn; - for(int i=0; i= tab.count()-max_cnt; --i) - { - if(tab[i].w_suf() > threshold) continue; - restorecasing(tab[i].form(),tab[i].form(),formcasing); - p += sprintf(p," %s%s",output_field_prefix,tab[i].form()); - if(show_scores) { - p += sprintf(p,",%1.2f",tab[i].w_suf()); - } - } - sprintf(p,"\n"); - - strcpy(outline,line); - outline[strlen(outline)-1]='\0'; - strcat(outline,corfield); - fputs(outline, outputf); - } - else if(one_field) - { - char* p=corfield; - p += sprintf(p," %s",output_field_prefix); - for(int i=tab.count()-1; i >= tab.count()-max_cnt; --i) - { - if(tab[i].w_suf() > threshold) continue; - restorecasing(tab[i].form(),tab[i].form(),formcasing); - p += sprintf(p,(i==0)?"%s":";%s",tab[i].form()); - if(show_scores) { - p += sprintf(p,",%1.2f",tab[i].w_suf()); - } - } - - sprintf(p,"\n"); - - strcpy(outline,line); - outline[strlen(outline)-1]='\0'; - strcat(outline,corfield); - fputs(outline, outputf); - } - else - { - for(int i=tab.count()-1; i >= tab.count()-max_cnt; --i) - { - if(tab[i].w_suf() > threshold) continue; - restorecasing(tab[i].form(),tab[i].form(),formcasing); - char* p = corfield; - p += sprintf(p," %s%s",output_field_prefix,tab[i].form()); - if(show_scores) { - p += sprintf(p,",%1.2f",tab[i].w_suf()); - } - p += sprintf(p, "\n"); - strcpy(outline,line); - outline[strlen(outline)-1]='\0'; - strcat(outline,corfield); - fputs(outline, outputf); - } - } - } - } - } - - if(args.interactive_flag) - { - fflush(outputf); - fflush(failedf); - } - } - cmdline_parser_free(&args); -} Index: ld/app/src/lem/Makefile =================================================================== --- _old/app/src/lem/Makefile (revision 7bed30fe7b80d29bc4822f7fd44163fa37a454fd) +++ (revision ) @@ -1,56 +1,0 @@ -PAR=-Wno-deprecated -O3 -fpermissive -static -PAR2=-c -Wno-deprecated -O3 -fpermissive -static -LIB_PATH=../lib -COMMON_PATH=../common -CMDLINE_FILE='"../lem/cmdline.h"' - - -lem: main.cc lem.o $(LIB_PATH)/auttools.o $(LIB_PATH)/word.o \ - cmdline.c common_lem.o common.o symtab.o - g++ $(PAR) -D _CMDLINE_FILE=$(CMDLINE_FILE) \ - main.cc lem.o $(LIB_PATH)/auttools.o \ - $(LIB_PATH)/word.o cmdline.c common.o common_lem.o \ - symtab.o -o lem - -lem.o: lem.h lem.cc - g++ $(PAR2) -D _CMDLINE_FILE=$(CMDLINE_FILE) lem.cc - -# alphabet.o: $(LIB_PATH)/alphabet.h $(LIB_PATH)/alphabet.cc -# g++ $(PAR2) $(LIB_PATH)/alphabet.cc - -# auttools.o: $(LIB_PATH)/auttools.h $(LIB_PATH)/auttools.cc -# g++ $(PAR2) $(LIB_PATH)/auttools.cc - -# word.o: $(LIB_PATH)/word.h $(LIB_PATH)/word.cc -# g++ $(PAR2) $(LIB_PATH)/word.cc - -# erro.o: $(LIB_PATH)/erro.h $(LIB_PATH)/erro.cc -# g++ $(PAR2) $(LIB_PATH)/erro.cc - -common.o: $(COMMON_PATH)/cmdline_common.ggo $(COMMON_PATH)/common.cc \ - $(COMMON_PATH)/common.h - g++ $(PAR2) -D _CMDLINE_FILE=$(CMDLINE_FILE) $(COMMON_PATH)/common.cc - -common_lem.o: cmdline.h common_lem.h common_lem.cc - g++ $(PAR2) -D _CMDLINE_FILE=$(CMDLINE_FILE) common_lem.cc - -cmdline.c cmdline.h: cmdline.ggo - gengetopt -i cmdline.ggo --conf-parser - -cmdline.ggo: cmdline_lem.ggo ../common/cmdline_common.ggo - cat cmdline_lem.ggo ../common/cmdline_common.ggo > cmdline.ggo - -symtab.o: $(LIB_PATH)/symtab.h $(LIB_PATH)/symtab.cc - g++ $(PAR2) $(LIB_PATH)/symtab.cc - -clean: clean.cmdline - rm *.o || true - rm lem || true - -clean.cmdline: - rm cmdline.* || true - -copy: -ifdef UTT_BIN_DIR - cp lem $(UTT_BIN_DIR) -endif Index: ld/app/src/lem/cmdline_lem.ggo =================================================================== --- _old/app/src/lem/cmdline_lem.ggo (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,5 +1,0 @@ -package "lem" -version "0.1" - -option "dictionary-home" - "D.h." string typestr="FILENAME" hidden no -option "dictionary" d "Dictionary" string typestr="FILENAME" default="lem.bin" no Index: ld/app/src/lem/common_lem.cc =================================================================== --- _old/app/src/lem/common_lem.cc (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,51 +1,0 @@ -#include -#include -#include "common_lem.h" - -char dictionary[255]; - -void process_lem_options(gengetopt_args_info* args) -{ - - if(args->dictionary_given) - { - expand_path(args->dictionary_arg,dictionary); - if(file_accessible(dictionary)!=0) - { - fprintf(stderr,"Cannot open the dictionary file: %s\nAborting.\n",dictionary); - exit(1); - } - } - else if (args->dictionary_home_given && args->language_given) - { - char buf[255]; - expand_path(args->dictionary_home_arg, buf); - sprintf(dictionary,"%s/%s/lem.bin",buf,args->language_arg); - if(file_accessible(dictionary)!=0) - { - fprintf(stderr,"Cannot open the dictionary file: %s\nAborting.\n",dictionary); - exit(1); - } - } -} - - -// STARE -// if(args.dictionary_given) -// strcpy(dictionary, args.dictionary_arg); -// else { -// char path[256]; -// //sprintf(path, "/etc/utt/data/%s/%s", args.locale_arg, DICT_FILE); -// //if (file_accessible(path) == 0) -// // strcpy(dictionary, path); -// //else { -// sprintf(path, "%s/%s", utt_dir, DICT_FILE); -// if (file_accessible(path) == 0) -// strcpy(dictionary, path); -// else { -// fprintf(stderr, "Cannot find dictionary!\n"); -// exit(1); -// } -// //} -// } - Index: ld/app/src/lem/common_lem.h =================================================================== --- _old/app/src/lem/common_lem.h (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,15 +1,0 @@ -#ifndef __COMMON_LEM__H -#define __COMMON_LEM__H - -#include -#include "../common/common.h" - -#include "cmdline.h" - -#define DICT_FILE "lem.bin" - -extern char dictionary[]; - -extern void process_lem_options(gengetopt_args_info* args); - -#endif Index: ld/app/src/lem/lem.cc =================================================================== --- _old/app/src/lem/lem.cc (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,153 +1,0 @@ -#include "lem.h" - -#include -#include - - -/* Znajduje opisy slownikowe dla wyrazu. - * Parametry: - * form - wyraz, - * tab - referencja do tablicy Words (miejsce na wyniki) - * Wartosc: - * liczba dodanych opisow - */ -int Lem::ana(const char* form, Words& tab) { - - // sprawdzamy czy parametry wywolania sa poprawne - assert(form && &tab); - int count0 = tab.count(); - long l; - if ((l=_dict.next(_dict.gtra(0, form, FT::ftMAXPATH), ';'))>=0) - add_to_table(tab, form, l); - return tab.count()-count0; -} - - -/* Szukamy opisu slownikowego nastepnego wyrazu w buforze. - * Parametry: - * buf - bufor - * tab - miejsce na wyniki - * Wartosc: - * ilosc dodanych opisow - */ -int Lem::pref(char* buf, Words& tab) { - - // sprawdzamy czy parametry wywolania sa poprawne - assert(buf && &tab); - - int count0 = tab.count(); - long l; - char* buf0 = buf; - - if((l=_dict.pref(buf, ';'))>=0) { - char form[MAX_FORM]; - int len=buf-buf0; - form[len]='\0'; - add_to_table(tab,form,l); - } - return tab.count() - count0; -} - -/* Dodaje kolejne opisy do tablicy wynikow. - * Parametry: - * tab - tablica wynikow, - * f - wyraz, - * s - stan, na ktorym zaczyna sie pierwszy opis - */ -void Lem::add_to_table(Words& tab, const char* f, long s) { - - // sprawdzenie parametrow - assert(&tab); - assert(f); - - char des[FT::ftMAXPATH]; - - while (_dict.cont(s, des)) { - char* des1; - if ((des1=strtok(des, ";")) != NULL) - do { - if (tab.count() >= MAX_ALT) break; - tab.add(f, des1); - des1=strtok(NULL, ";"); - } while (des1!=NULL); - s=-1; - } -} - -void Lem::prn_dict() -{ - - char des[FT::ftMAXPATH]; - - long s=0; - - while (_dict.cont(s, des)) - { - printf("%s\n",des); - s=-1; - } -} - - -AuxLem::AuxLem(const char* filename) - : Lem(), _dict(SIZE) -{ - FILE* f; - char buf[MAX_LINE+2]; - f=fopen(filename,"r"); - for(long i=0; i=MAX_LINE-1) continue; // BEZ isalpha! - buf[l-1]='\0'; - char* sep=strchr(buf,';'); - if(sep==NULL) continue; - *sep='\0'; - long formind=_dict.add(buf); - if(formind>=0) - { - char* desc=strdup(sep+1); - info[formind]=desc; - } - else - fprintf(stderr,"AuxLem: Form not added: %s;%s.\n", buf,sep+1); - } - fclose(f); -}; - -//--------------------------------------------------------------------------- - -AuxLem::~AuxLem() -{ -// for(long i=0; i<_dict.count(); ++i) -// free(info[_dict.hashindex(i)]); - for(long i=0; i=0) - { - strcpy(des,info[ind]); - char* des1; - if((des1=strtok(des,";"))!=NULL) - do - { - if(tab.cnt>=MAXALT) break; - tab.add(form,des1); - des1=strtok(NULL,";"); - } while(des1!=NULL); - } - return tab.count()-count0; -} - -//--------------------------------------------------------------------------- - Index: ld/app/src/lem/lem.h =================================================================== --- _old/app/src/lem/lem.h (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,50 +1,0 @@ -#include "../lib/tfti.h" -#include "../lib/word.h" -#include "../lib/symtab.h" -#include "../lib/const.h" - -class Lem { - - protected: - // Alphabet& _alpha; - - // slownik - TFTiv _dict; - - void add_to_table(Words& tab, const char* f, long s); - - public: - - Lem() {}; - Lem(const char* d) - : _dict(d) {}; - virtual int ana(const char* form, Words& tab); - int pref(char* form, Words& tab); - void prn_dict(); - -}; - - -class AuxLem : public Lem { -public: - - static const int SIZE=1500000; - // static const int MAXLINE=1000; - static const int MAXALT=256; - - AuxLem(const char* filename); - ~AuxLem(); - -// int ana(const char* form, Grams& tab); - int ana(const char* form, Words& tab); - -// operator bool() { return _dict && info; } - -private: - SymbolTable _dict; - char* info[SIZE]; - -}; - - - Index: ld/app/src/lem/main.cc =================================================================== --- _old/app/src/lem/main.cc (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,131 +1,0 @@ -#include "../lib/iotools.h" -//do wyrzucenia - definicja w Makefile! #define _CMDLINE_FILE "../lem/cmdline.h" -#include "../common/common.h" -#include "common_lem.h" -#include "lem.h" -#include "cmdline.h" -#include - -int main(int argc, char** argv) { - -// setlocale(LC_CTYPE,""); //PO CO TO? -// setlocale(LC_COLLATE,""); // - - gengetopt_args_info args; - - if(cmdline_parser(argc, argv, &args) != 0) - exit(1); - - process_config_files(&args,argv[0]); - process_common_options(&args,argv[0]); - process_lem_options(&args); - - char line[MAX_LINE+1]; - char outline[MAX_LINE+1]; - char parms[MAX_LINE+1], desc[MAX_LINE+1], lemma[MAX_LINE+1]; - long line_count = 0; - - Lem* lem; - - if(strcmp(dictionary+strlen(dictionary)-4,".bin")==0) - lem = new Lem(dictionary); - else if(strcmp(dictionary+strlen(dictionary)-4,".dic")==0) - lem = new AuxLem(dictionary); - else - fprintf(stderr,"lem: Invalid dictionary file extension.\n"); - - Words tab; -// Segment seg; - - while (fgets(line, MAX_LINE, inputf)) - { - ++line_count; - int start, len; - - if (!process_seg(line, args)) // TO POWINNO BYC WCZESNIEJ ZABEZPIECZONE - fputs(line, outputf); - else - { - char form[MAX_FORM]; - - tab.clear(); - getfield(line,input_field_prefix,form); - - if (form==NULL) continue;//BZDURA - - lem->ana(form, tab); - if(tab.count()==0) - { - char form1[MAX_FORM]; // tymczasowo tak, trzeba zmienic ana - char* p; - strcpy(form1,form); - for(p=form1;*p;++p) *p=tolower(*p); - p=form1; - lem->ana(p,tab); - } - - if (tab.count() == 0) - fputs(line, failedf); - else - { // mamy jakies opisy w slowniku - - if(one_line) - { - char* descp=desc; - for (int i=0; i< tab.count(); ++i) - { - descp += sprintf(descp," %s%s,%s", output_field_prefix, tab[i].lemma(), tab[i].descr()); - } - strcpy(outline,line); - outline[strlen(outline)-1]='\0'; - strcat(outline,desc); - strcat(outline,"\n"); - fputs(outline, outputf); - if (copy_processed) - fputs(line,outputf); - } - else if(one_field) - { - char* descp=desc; - for (int i=0; i< tab.count(); ++i) - if(i==0) - descp += sprintf(descp," %s%s,%s", output_field_prefix, tab[i].lemma(), tab[i].descr()); - else - { - if(strcmp(tab[i].lemma(),tab[i-1].lemma())==0) - descp += sprintf(descp,",%s",tab[i].descr()); - else - descp += sprintf(descp,";%s,%s",tab[i].lemma(),tab[i].descr()); - } - - strcpy(outline,line); - outline[strlen(outline)-1]='\0'; - strcat(outline,desc); - strcat(outline,"\n"); - fputs(outline, outputf); - if (copy_processed) - fputs(line,outputf); - } - else - { - for (int i=0; i< tab.count(); ++i) - { - // kolejne opisy - kolejne linie. - sprintf(desc, " %s%s,%s\n", output_field_prefix, tab[i].lemma(), tab[i].descr()); - strcpy(outline,line); - outline[strlen(outline)-1]='\0'; - strcat(outline,desc); - fputs(outline, outputf); - } - if (copy_processed) - fputs(line,outputf); - } - } - } - - if(args.interactive_flag) - fflush(outputf), fflush(failedf); - - } - cmdline_parser_free(&args); -} Index: ld/app/src/lib/Makefile =================================================================== --- _old/app/src/lib/Makefile (revision 7bed30fe7b80d29bc4822f7fd44163fa37a454fd) +++ (revision ) @@ -1,21 +1,0 @@ -PAR=-Wno-deprecated -O3 -PAR2=-c -Wno-deprecated -O3 -fpermissive -# -static -LIB_PATH=../lib -COMMON_PATH=../common - -main: auttools.o word.o copy - -auttools.o: auttools.h auttools.cc - g++ $(PAR2) auttools.cc - -word.o: word.h word.cc - g++ $(PAR2) word.cc - -clean: - rm *.o - -copy: -#ifdef UTT_LIB_DIR -# cp -r perl $(UTT_LIB_DIR)/ -#endif Index: ld/app/src/lib/auttools.cc =================================================================== --- _old/app/src/lib/auttools.cc (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,164 +1,0 @@ -#include "auttools.h" -//#include "/src/cpp-comm/plx/Plx.h" - -void fullform(const char* b, const char* d, char* f) -{ - int i,j=0; - int n1, n2=0; - bool g=false; - char s1[200], s2[200], temps[200]; - while(d[j]>='0' && d[j]<='9')j++; - strncpy(temps,d,j); temps[j]='\0'; - n1=atoi(temps); - i=j; - while(!ispunct(d[j]) || d[j]=='*') j++; - strncpy(s1,d+i,j-i); - s1[j-i]='\0'; - if(d[j++]=='-') - { - i=j; - while(d[j]>='0' && d[j]<='9')j++; - strncpy(temps,d+i,j-i); temps[j]='\0'; - n2=atoi(temps); - i=j; - while(!ispunct(d[j]) || d[j]=='*') j++; - strncpy(s2,d+i,j-i); - s2[j-i]='\0'; - g=true; - } - - int blen=strlen(b); - if(g) - if(n1+n2<=blen) - { - strcpy(f,s1); - strcat(f,b+n1); - f[strlen(f)-n2]='\0'; - strcat(f,s2); - } - else - strcpy(f,""); - else - if(n1<=blen) - { - strcpy(f,b); - f[strlen(f)-n1]='\0'; - strcat(f,s1); - } - else - strcpy(f,""); -} - -void compose(char* stem, char* ending, char* form) -{ - bool suffix=true; - while(*stem) - if(*stem=='*') - { - strcpy(form,ending); - form+=strlen(ending); - suffix=false; - stem++; - } - else - *(form++)=*(stem++); - if(suffix) - { - strcpy(form,ending); - form+=strlen(ending); - } - *form='\0'; -} - -void autodescr(const char* f, const char* des, char* lemma, char* pos, char* attr) -{ - char lemd[MAXWORDLEN]; - int o,l=strcspn(des,","); - strncpy(lemd,des,l); - lemd[l]='\0'; - fullform(f,lemd,lemma); - o=l+1; - l=strcspn(des+o,"/:"); - strncpy(pos,des+o,l); - pos[l]='\0'; - o=o+l; - if(des[o]=='/') - { - o++; - strcpy(attr,des+o); - } - else - attr[0]='\0'; -} - - -int common_prefix(const char* s, const char* t) -{ - int n=0; - while(*s==*t && *s!='\0') - { s++,t++;n++; } - return n; -} - -int strdiff(const char* s, const char* t, - int& frontcut, char* prefix, int& endcut, char* suffix) -{ - int slen=strlen(s); - int tlen=strlen(t); - int ss, ss_max=0; /* ss - s shift */ - int ts, ts_max=0; /* ts - t shift */ - int common, common_max=0; - for(ss=0;sscommon_max - && (common>4 || (ss==0 && ts==0 && common>1)) ) - { - ss_max=ss; - ts_max=ts; - common_max=common; - } - // print "--", tsmax,"\n" - printf("--%d\n", ts_max); - frontcut=ss_max; - strncpy(prefix,t,ts_max); prefix[ts_max]='\0'; - endcut=slen-ss_max-common_max; - strcpy(suffix,t+ts_max+common_max); - return common_max; -} - -void fprndiff(FILE* f, const char* s, const char* t) -{ - int frontcut,endcut; - char pref[MAXWORDLEN],suff[MAXWORDLEN]; - strdiff(s,t,frontcut,pref,endcut,suff); - if(frontcut!=0 || pref[0]!='\0') - fprintf(f,"%d%s-%d%s",frontcut,pref,endcut,suff); - else - fprintf(f,"%d%s",endcut,suff); -} - -void sprndiff(char* outstr, const char* s, const char* t) -{ - int frontcut,endcut; - char pref[MAXWORDLEN],suff[MAXWORDLEN]; - strdiff(s,t,frontcut,pref,endcut,suff); - if(frontcut!=0 || pref[0]!='\0') - sprintf(outstr,"%d%s-%d%s",frontcut,pref,endcut,suff); - else - sprintf(outstr,"%d%s",endcut,suff); -} - - -void despos(const char* des, char* pos) -{ - int di=0; - int pi=0; - while(des[di]!=',' && des[di]!='\0') ++di; - if(des[di]==',') - { - ++di; - while(isupper(des[di])) pos[pi++]=des[di++]; - } - pos[pi]='\0'; -} - Index: ld/app/src/lib/auttools.h =================================================================== --- _old/app/src/lib/auttools.h (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,39 +1,0 @@ - -#ifndef _Auttools_h -#define _Auttools_h - -#include -#include -#include -#include - -/* #define ISALPHAG(c) ((c>='A' && c<='Z') || (c>='a' && c<='z') || \ */ -/* c=='¡' || c=='±' || c=='Æ' || c=='æ' || \ */ -/* c=='Ê' || c=='ê' || c=='£' || c=='³' || \ */ -/* c=='Ñ' || c=='ñ' || c=='Ó' || c=='ó' || \ */ -/* c=='Š' || c=='¶' || c=='¬' || c=='Œ' || \ */ -/* c=='¯' || c=='¿' || c=='*') */ - -#define MAXWORDLEN 64 - -extern void fullform(const char* b, const char* d, // in - char* f); // out - -extern void compose(char* stem, char* ending, // in - char* form); // out - -extern void autodescr(const char* f, const char* des, // in - char* lemma, char* pos, char* attr); // out - -extern int strdiff(char* s, char* t, // in - int& frontcut, char* prefix, // out - int& endcut, char* suffix); // out - -extern void fprndiff(FILE* f, const char* s, const char* t);// in - -extern void sprndiff(char* outstr, const char* s, const char* t); // in - -extern void despos(const char* des, // in - char* pos); // out - -#endif Index: ld/app/src/lib/const.h =================================================================== --- _old/app/src/lib/const.h (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,24 +1,0 @@ - - - -// maksymalna dlugosc wyrazu -#define MAX_FORM 80 - -// maksymalna dlugosc opisu -#define MAX_DESC 80 - -// maksymalna dlogosc lini w pliku przejsciowym -#define MAX_LINE 1024 - -// separator pol w pliku posrednim -#define FIELD_SEP " \t\n" - -// maksymalna liczba alternatywnych opisow -#define MAX_ALT 256 - -// plik ze slownikiem dla guessa -#define GUESS_DICT_FILE "slownik.fsa" - -// katalogi z plikami konfiguracyjnymi -#define SYSTEM_CONFIG_DIR "/usr/local/etc/utt" -#define USER_CONFIG_DIR "~/.utt" Index: ld/app/src/lib/iotools.h =================================================================== --- _old/app/src/lib/iotools.h (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,53 +1,0 @@ -#include "const.h" -#include -#include -#include -#include -#include - - -// napisy zostaj na miejscu (w line), tylko wskazniki sa ustawian -// i zara dopisywane zera s dopisywane - -inline -int parsetok(char* line, int* a, int* b, char** c, char** d, char** e, char** f) -{ - char* field; - if((field=strtok(line,FIELD_SEP))!=NULL) - *a=atoi(field); // nie sprawdzana poprawnosc - else - return 0; - if((field=strtok(NULL,FIELD_SEP))!=NULL) - *b=atoi(field); // nie sprawdzana poprawnosc - else return 1; - if((*c=strtok(NULL,FIELD_SEP))==NULL) return 2; - if((*d=strtok(NULL,FIELD_SEP))==NULL) return 3; - if((*e=strtok(NULL,FIELD_SEP))==NULL) return 4; - if((*f=strtok(NULL,FIELD_SEP))==NULL) return 6; - return 6; -} - -// napisy s kopiowane -inline -int scantok(const char* line, int* a, int* b, char* c, char* d, char* e=NULL, char* f=NULL) -{ - return sscanf(line," %d %d %s %s %s %s", a, b, c, d, e, f); -} - -inline -int printtok(char* line, int a, int b, char* c, char* d, char* e, char* f, char* parms) -{ - sprintf(line,"%04d %02d %s %s %s %s `%s\n", a, b, c, d, e, f, parms); -} - -inline -int printtok(char* line, int a, int b, char* c, char* d, char* e, char* f) -{ - sprintf(line,"%04d %02d %s %s %s %s\n", a, b, c, d, e, f); -} - -inline -int printtok(char* line, int a, int b, char* c, char* d) -{ - sprintf(line,"%04d %02d %s %s\n", a, b, c, d); -} Index: ld/app/src/lib/matchdescr.cc =================================================================== --- _old/app/src/lib/matchdescr.cc (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,86 +1,0 @@ -#include -#include - -inline -bool inline_matchattr(const char* a, const char* b) -{ - const char *p, *q; // pomocnicze wskazniki - while(*a && *b) - { - p=a; q=b; - while(isupper(*p) && isupper(*q)) // rowny prefiks - if(*p==*q) ++p, ++q; - else if(*p<*q) // a jest mniejszy - { - // przesywamy a do nastepnego atr - a=p; - while(isupper(*a)) ++a; while(islower(*a)) ++a; - goto end; - } - else - { - // przesuwamy b do nastepnego atr - b=q; - while(isupper(*b)) ++b; while(islower(*b)) ++b; - goto end; - } - - if(islower(*p) && islower(*q)) // rowne atrybuty - { - a=p; b=q; // przesuwamy wskaznik, sprawdzamy wartosci - while(*a != *b) - { - if(*a > *b && !islower(*++b)) return false; - if(*a < *b && !islower(*++a)) return false; - } - // znaleziono rowna wartosc, przesywamy a i b do nast atr - while(isupper(*a)) ++a; while(islower(*a)) ++a; - while(isupper(*b)) ++b; while(islower(*b)) ++b; - goto end; - } - - if(islower(*p)) // a jest krotszy, czyli mniejszy - { // przesuwamy a do nastepnego atrybutu - a=p; - while(islower(*a)) ++a; - goto end; - } - - if(islower(*q)) // b jest krotszy, czyli mniejszy - { // przesuwamy b do nastepnego atrybutu - b=q; - while(islower(*b)) ++b; - goto end; - } - end: ; - } - return true; -} - - -bool matchattr(const char* a, const char* b) -{ - return inline_matchattr(a,b); -} - -bool matchdescr(const char* a, const char* b) -{ - while(isupper(*a) && isupper(*b) && *a==*b) ++a, ++b; - if(*a=='\0') - if(*b=='\0' || *b=='/') return true; - else return false; - - if(*a=='/') - if(*b=='\0') return true; - else if(*b=='/') return inline_matchattr(++a, ++b); - - return false; -} - - -int main() -{ - char a[100], b[100]; - while(scanf("%s %s", a, b)==2) - printf("%s & %s = %d\n", a, b, matchdescr(a,b)); -} Index: ld/app/src/lib/matchdescr.h =================================================================== --- _old/app/src/lib/matchdescr.h (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,10 +1,0 @@ - -// obie funkcje wymagaja by deskrypcje byly w postaci kanonicznej -// obslugiwane sa tylko krotkie (jednoliterowe) atrybuty - -// test czy zgadzaja sie deskrypcje -bool matchdescr(const char* a, const char* b); - -// test czy zgadaja sie same atrybuty (czyli to, co po ukosniku) -bool matchattr(const char* a, const char* b); - Index: ld/app/src/lib/symtab.cc =================================================================== --- _old/app/src/lib/symtab.cc (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,171 +1,0 @@ -#include "symtab.h" -#include -#include -#include -#include -//--------------------------------------------------------------------------- - -SymbolTable::SymbolTable(int n, int (*h)(const char*,int), const char* filename) - : _mx(n), _cnt(0), hash(h) -{ - _sz=first(n); - _key=new char*[_sz]; - _defind=new int[_sz]; - _hashind=new int[_sz]; - _def=new char*[_mx]; - for(int i=0; i<_sz; i++) _key[i]=NULL; - if(filename) - add_from_file(filename); -} - -//--------------------------------------------------------------------------- - -SymbolTable::SymbolTable(int n, const char* filename) - : _mx(n), _cnt(0), hash(hash1) -{ - _sz=first(n); - _key=new char*[_sz]; - _defind=new int[_sz]; - _hashind=new int[_sz]; - _def=new char*[_mx]; - for(int i=0; i<_sz; ++i) _key[i]=NULL; - if(filename) - add_from_file(filename); -} - -//--------------------------------------------------------------------------- - -SymbolTable::~SymbolTable() -{ - clear(); - delete[] _key; - delete[] _defind; - delete[] _hashind; - delete[] _def; -} - -//--------------------------------------------------------------------------- - -void SymbolTable::clear() -{ - for(int i=0; i<_sz; ++i) - if(_key[i]) - free(_key[i]); -} - -//--------------------------------------------------------------------------- - -bool SymbolTable::add_from_file(const char* filename) -{ - FILE* in=fopen(filename,"r"); - char buf[MAXKEYLEN+1]; - - if(in) - while(fscanf(in,"%s",buf)==1) - { - if(strlen(buf)==MAXKEYLEN || add(buf)<0) - return false; - } - return true; -} - -//--------------------------------------------------------------------------- - -int SymbolTable::add(const char* s) -{ - if(_cnt<_mx) - { - int ind=hash(s,_sz); - while(_key[ind]) - if(strcmp(_key[ind],s)) - ind=++ind%_sz; - else - return _defind[ind]; - _key[ind]=strdup(s); - _defind[ind]=_cnt; - _hashind[_cnt]=ind; - _def[_cnt]=_key[ind]; - _cnt++; - return _cnt-1; - } - else - return -1; -} - -//--------------------------------------------------------------------------- - -int SymbolTable::operator[](const char* s) -{ - int ind=hash(s,_sz); - while(_key[ind]) - if(strcmp(_key[ind],s)==0) - return _defind[ind]; - else - ind=++ind % _sz; - return -1; -} - -//--------------------------------------------------------------------------- - -int SymbolTable::first(unsigned int n) -{ - int fi=n; - int bound=(n/2 < MAXKEYLEN)? n/2 : MAXKEYLEN; - bool found; - do - { - found=true; - if(fi++ == MAXINT) return -1; - for(int i=2; i=4) - return abs((*((int*)(s+(l/2-2)))+(int)(*s * s[l-1])) % _sz); - else - { - int i=0; - strcpy((char*)&i,s); - return abs((i+(int)(*s * s[l-1])) % _sz); - } -} - -//--------------------------------------------------------------------------- - -int hash2(const char* s, int _sz) -{ - int l=strlen(s); - if(l>=6) - { - unsigned int i1,i2,i3; - strncpy((char*)&i1,s,sizeof(int)); - strncpy((char*)&i2,s+(l/2-2),sizeof(int)); - strncpy((char*)&i3,s+(l-4),sizeof(int)); - return abs((i1+i2+i3) % _sz); - } - else - { - int i=0; - strncpy((char*)&i,s,sizeof(int)); - return abs((i+(int)(*s * s[l-1])) % _sz); - } -} - -//--------------------------------------------------------------------------- - Index: ld/app/src/lib/symtab.h =================================================================== --- _old/app/src/lib/symtab.h (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,52 +1,0 @@ -#ifndef _HashTable_h -#define _HashTable_h -//--------------------------------------------------------------------------- -#include -#include -//--------------------------------------------------------------------------- -int hash1(const char* s, int sz); -int hash2(const char* s, int sz); -//--------------------------------------------------------------------------- - -class SymbolTable -{ - int _mx; - int _sz; - int _cnt; - char** _key; - char** _def; - int* _defind; - int* _hashind; // s¹ tu redundancje - -public: - static const unsigned int MAXKEYLEN=2000; - - SymbolTable(int n, int (*h)(const char*,int), const char* filename=NULL); - SymbolTable(int n, const char* filename=NULL); - ~SymbolTable(); - - void clear(); - - int (*hash)(const char*, int); - - bool add_from_file(const char* filename); - - int add(const char* s); - int operator[](const char* s); - const char* operator[](int i){if(i<0||i>=_cnt)return NULL;else return _def[i];} - int index(const char* s) { return this->operator[](s); }; - int index(int i) { if(i<0||i>=_cnt) return -1; else return i; }; - int hash_index(int i) { return _hashind[i]; } - const char* symbol(int i) { if(i<0||i>=_cnt)return NULL; else return _def[i];} - - int capacity() { return _mx; } - int size() { return _sz; } - int count() { return _cnt; } - float search_rate(); - -private: - static int first(unsigned int n); -}; - -//--------------------------------------------------------------------------- -#endif Index: ld/app/src/lib/tft.h =================================================================== --- _old/app/src/lib/tft.h (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,881 +1,0 @@ -#ifndef _TFT_h -#define _TFT_h -//--------------------------------------------------------------------------- -#include -#include -#include -#include - -#include - -//#include "top.h" -#include "ttrans.h" - -using namespace std; -//--------------------------------------------------------------------------- - -/// Klasa bazowa przetwornika skoñczonego. -/** - \remark Po co ta klasa? Co dotyczy samych przej¶æ, przenie¶æ do TTrans, - resztê wcieliæ do TFT. -*/ -class FT -{ -public: - FT() : copy_default(false), print_mode(OO), ttn(0) {}; - -//print mode - enum OUTPUT { II, ///< tylko symbole wej¶ciowe - OO, ///< tylko symbole wyj¶ciowe - IOIO, ///< symbol wyj¶ciowy po wej¶ciowym - OIOI, ///< symbol wyj¶ciowy przed wej¶ciowym - IIOO, ///< ca³e wej¶cie, potem ca³e wyj¶cie - OOII ///< ca³e wyj¶cie, potem ca³e wej¶cie - - }; - -/// maks d³ugo¶æ ¶cie¿ki - static const unsigned int ftMAXPATH=500; - -/// maks d³ugo¶æ opisu typu symbolu we/wy -/** - \remark Przenie¶æ do TTrans -*/ - static const unsigned int ftTYPELEN=32; - -/// specjalny symbol dla warto¶ci 'epsilon' -/** - \remark Przenie¶æ do TTrans -*/ - static const char ftEPSILON='~'; - -/// specialny symbol dla warto¶ci 'default' -/** - \remark Przenie¶æ do TTrans -*/ - static const char ftDEFAULT='@'; - -/// domy¶lny symbol wyj¶ciowy (true-'@', flase-'~') -/** - \remark Przenie¶æ do TTrans(???) -*/ - bool copy_default; - -/// tryb wyj¶cia - OUTPUT print_mode; - -/// false, je¶li automat nie ma przej¶æ - operator bool() { return (bool)ttn; }; - - virtual const char* intype() { return itype; }; - virtual const char* outtype() { return otype; }; - -protected: - -/// liczba elementów tablicy tt - unsigned long ttn; - -/// liczba stanów - unsigned long states; - -/// liczba przej¶æ - unsigned long transitions; - -/// typ symboli wej¶ciowych (napis) -/** - \remark Przenie¶æ do TTrans(???) -*/ - char itype[ftTYPELEN]; - -/// typ symboli wyj¶ciowych (napis) -/** - \remark Przenie¶æ do TTrans(???) -*/ - char otype[ftTYPELEN]; -}; - -//--------------------------------------------------------------------------- - -/// Szablon przetwornika skoñczonego -/** - \param I - typ symbolu wej¶ciowego - \param Ipass - typ, jaki ma byæ u¿yty przy przekazywaniu symbolu we jako parametru - do funkcji (metody), równy \a I lub \a I& - \param O - typ symbolu wyj¶ciowego - \param Opass - typ, jaki ma byæ u¿yty przy przekazywaniu symbolu wy jako parametru - do funkcji (metody), równy \a O lub \a O& - \param - typ przej¶cia, musi byæ podklas± TTrans -*/ -template -class TFT : public FT -{ - - -public: - - TFT() : FT(), tt(NULL) { setiotypes(); }; - -/** -\name Metody poziomu 1 -Poziom przej¶æ. -*/ - -//@{ - -/// Test, czy przej¶cie \a t akceptuje symbol \a in. - bool accepts(long t, Ipass in) const; - -/// Test, czy lista przej¶æ dla aktualnego stanu jest kontynuowana po \a t. - bool continued(long t) const; - -/// Stan, do którego prowadzi przej¶cie \a t. -/** - \pre !empty(t) -*/ - long next(long t) const; - -/// Symbol wej¶ciowy przej¶cia \a t. - Ipass input(long t) const; - -/// Symbol wyj¶ciowy przej¶cia \a t. - Opass output(long t) const; - -/// Zwraca \c true, je¶li symbolem we przej¶cia \a t jest epsilon. - bool epsi(long t) const; - -/// Zwraca \c true, je¶li symbolem we przej¶cia \a t jest symbol domy¶lny. - bool defi(long t) const; - -/// Zwraca \c true, je¶li symbolem wy przej¶cia \a t jest epsilon. - bool epso(long t) const; - -/// Zwraca \c true, je¶li symbolem wy przej¶cia \a t jest symbol domy¶lny. - bool defo(long t) const; - -/// Indeks przej¶cia przez \a in. - long tra(long t, Ipass in) const; - -/// Indeks przej¶cia przez \a in - non-deterministic. - long tra_nd(long t, Ipass in, long nth) const; - -//@} - -/** -\name Poziom 2 -Poziom stanów. Stan (indeks stanu) = indeks jego pierwszego przej¶cia -*/ -//@{ -/// Zwraca \c true je¶li stan \a s jest pusty (nie ma z niego przej¶æ). - bool empty(long s) const { return tt[s].empty(); } - -/// Zwraca \c true je¶li stan \a s jest stanem koñcowym. - bool final(long s) const { return tt[s].final(); } - - long next(long t, Ipass in) const; - -//long trans(const I* si, I* so, long& olen) const; - - long gtra(long s, const I* w, long maxpath=ftMAXPATH) const; - -//@} - -/** -\name Poziom 3 -Poziom ... -*/ -//@{ - long cont(long s=-1, I* c=NULL) const; - - long match(const I* w=NULL, long* p=NULL) const; - - long match_nd(const I* w=NULL, long* p=NULL) const; - - long lgstmatch(const I* w, long* p, long& plen, long maxpath=ftMAXPATH) const; - - /*NOWE*/ - - long lgstpath(I*& buf, long*& path, long start=0) const; - - long pref(I*& buf, I sep, long start=0) const; - -//@} - -protected: - - TT* tt; // tablica przej¶æ - - long prn(const I* si, long* p, O* so) const; - - void prntt(ostream& os); - - void sort(); - - void setiotypes(); // NIE DZIA£A (dlaczego???) - -// friend ostream& operator<<(ostream&,const CDFA&); -// friend istream& operator>>(istream&,CDFA&); - -private: - long prn_oo(const I* si, long* p, O* so) const; - long prn_ioio(const I* si, long* p, O* so) const; - long prn_oioi(const I* si, long* p, O* so) const; - long prn_iioo(const I* si, long* p, O* so) const; - long prn_ooii(const I* si, long* p, O* so) const; -}; - - -//--------------------------------------------------------------------------- -//--------------------------------------------------------------------------- - -/** - stan = indeks pierwszego przej¶cia - - state(t) = stan, do którego nale¿y t - - symbol zerowy = symbol s, dla którego (bool)s zwraca \c false, - w przypadku znaków - '\0' -*/ - -//--------------------------------------------------------------------------- -//--------------------------------------------------------------------------- - - -template -inline -bool TFT::accepts(long t, Ipass in) const -{ return tt[t].accepts(in); } - -/// Test whether the transition list continues after \a t. -template -inline -bool TFT::continued(long t) const -{ return tt[t].continued(); } - -/** - \pre !empty(t) -*/ -template -inline -long TFT::next(long t) const -{ return tt[t].next(); } - -template -inline -Ipass TFT::input(long t) const -{ return tt[t].in(); } - -template -inline -Opass TFT::output(long t) const -{ return tt[t].out(); } - -template -inline -bool TFT::epsi(long t) const -{ return tt[t].epsi(); } - -template -inline -bool TFT::defi(long t) const -{ return tt[t].defi(); } - -template -inline -bool TFT::epso(long t) const -{ return tt[t].epso(); } - -template -inline -bool TFT::defo(long t) const -{ return tt[t].defo(); } - -/** - \param +t - indeks przej¶cia - \param +in - symbol we - \return Indeks przj¶cia (>=\a t) dla bie¿±cego stanu, które - akceptuje symbol we \a in lub -1, je¶li nie ma takiego przej¶cia -*/ -template -long TFT::tra(long t, Ipass in) const -{ - if(t<0 || t>=ttn) - return -1; - - if(empty(t)) return -1; - while(!accepts(t,in)) - if(continued(t)) - t++; - else - return -1; - return t; -} - -//--------------------------------------------------------------------------- -/// Indeks przej¶cia - wersja dla automatu niedeterministycznego. -/** - \param +t - indeks przej¶cia - \param +in - symbol we - \return Indeks przj¶cia (>=\a t) dla bie¿±cego stanu, które - akceptuje symbol we \a in lub -1, je¶li nie ma takiego przej¶cia - Je¶li nth==0, t1>=t, w przeciwnym razie t1>t. -*/ -template -long TFT::tra_nd(long t, Ipass in, long nth) const -{ - if(t<0 || t>=ttn) - return -1; - - if(nth) - if(continued(t)) - t++; - else - return -1; - else - { if(empty(t)) return -1; } - - while(!accepts(t,in)) - if(continued(t)) - t++; - else - return -1; - - return t; -} - -//} - -//--------------------------------------------------------------------------- -//---------------------------------------------------------------------------- - - -/// Funkcja przej¶cia. -/** - \param t - stan - \param in - symbol we - \return Stan, do którego mo¿na przej¶æ z \a t po wp³ywem symbolu \a in - lub -1, je¶li nie ma przej¶cia przez \a in - -*/ -template -long TFT::next(long t, Ipass in) const -{ - if(t<0 || (unsigned long)t>=ttn) - return -1; - - if(empty(t)) return -1; - while(!accepts(t,in)) - if(continued(t)) - t++; - else { - return -1; - } - - return next(t); -} - -//--------------------------------------------------------------------------- - -//---------------------------------------------------------------------------- -/// Uogólniona funkcja przejscia. -/** - \param +s - stan - \param +w - wskaŒnik pierwszego elementu ci±gu symboli we, zakoñczonego symbolem zerowym - \param maxpath maksymalna d³ugo¶æ ¶cie¿ki, domy¶lnie ftMAXPATH - \return stan osi±galny z \a s pod wp³ywem \a w (na ¶cie¿ce mog± siê pojawiæ - epsilon-przej¶cia -*/ -template -long TFT::gtra(long s, const I* w, long maxpath) const -{ - if(s<0 || (unsigned long)s>=ttn) - return -1; - - long i=0; - while(*w) - { - if(i>maxpath || empty(s)) return -1; - while(!accepts(s,*w)) - if(continued(s)) - s++; - else - return -1; - if(!epsi(s)) w++; - s=next(s); - i++; - } - return s; -} - -//---------------------------------------------------------------------------- - -/// Kontynuacja. -/** -... -\param +s stan, je¶li -1 - poszukiwane jest nastêpne rozwi±zanie -\param -c ci±g symboli we ze ¶cie¿ki prowadz±cej z \a s do - stanu koñcowego -\return d³ugo¶æ ci±gu \a c (= d³ugo¶æ ¶cie¿ki) -\remark DZIA£A TYLKO DLA ZNAKÓW!!! - EPSILON-PRZEJŠCIA NIEDOZWOLONE!!! -*/ -template -long TFT::cont(long s, I* c) const -{ - static unsigned long path[ftMAXPATH]={0}; - static unsigned long i=0; - static bool more=false; - - bool found=false; - - if(s!=-1) - { - if(s<0 || (unsigned long)s>=ttn) - more=false; - else - { - i=0; - c[0]=0; - path[0]=s; - more=true; - if(final(s)) - found=true; - } - } - - while(more && !found) - { - if(!empty(path[i]) && i0) - c[--i]=0; - else - more=false; - }while(more && !continued(path[i])); - path[i]=path[i]+1; - } - if(final(path[i])) - { - found=true; - c[i]=0; - } - } - return i; -} - -//---------------------------------------------------------------------------- -/// Dopasowannie. -/** - \remark Nie zaimplementowane. -*/ -template -long TFT::match(const I* w, long* p) const -{} - -//---------------------------------------------------------------------------- -/// Dopasowanie niedeterministyczne. -/** - \param +w - wskaŒnik pierwszego elementu ci±gu symboli we, zakoñczonego symbolem zerowym, - je¶li NULL - poszukiwane jest nastêpne rozwi±zanie - \param -p ci±g przej¶æ zakoñczony -1 - \return d³ugo¶æ dopasowania (PO CO?) -*/ -template -long TFT::match_nd(const I* w, long* p) const -{ - static bool more=false; - static I *w0, *wc; - static long s=0, *p0, *pc, *pc_bound; - - bool found=false; - - if(w) - { - wc=w0=w; - pc=p0=p; - more=true; - pc_bound=pc+ftMAXPATH; - if(final(s=0)) - { - *pc=-1; return 0; - } - } - - while(more) - { - if(*wc && pc=0) - { if(!epsi(*pc)) wc++; s=next(*pc); pc++; } - else - while(true) - { - if(pc==p0) { more=false; return -1; } - if(!epsi(*(--pc))) wc--; - if((*pc=trand(*pc,*wc,1))>=0) - { if(!epsi(*pc)) wc++; s=next(*pc); pc++; break; } - } - if(final(s)) { *pc=-1; return wc-w0; } - } - return -1; -} - -//---------------------------------------------------------------------------- -/// Najd³u¿sze dopasowanie. -/** - \param +w wskaŒnik pierwszego elementu ci±gu symboli wej¶ciowych - \param -p ¶cie¿ka - \param -plen d³ugo¶æ ¶cie¿ki - \param +maxpath maks dd³ugo¶æ ¶cie¿ki, domy¶lnie FT::ftMAXPATH - \return d³ugo¶æ skonsumowanego wej¶cia -*/ -template -long TFT - ::lgstmatch(const I* w, long* p, long& plen, long maxpath) const -{ - long s=0; - long t; - long i=0; - const char* w0=w; - long ilen=0; - while(*w && i=0) - { - if(!epsi(t)) w++; - s=next(t); - i++; - *(p++)=t; - if(final(s)) { plen=i; ilen=w-w0; } - } - *p=-1; - return ilen; -} - -//---------------------------------------------------------------------------- -/// Najd³u¿sza ¶cie¿ka. -/** - \param +buf wskaŒnik pierwszego elementu ci±gu symboli wej¶ciowych - \param -buf pozycja jeden za skonsumowanym prefiksem - \param +path wskaŒnik pierwszego elementu wektora przej¶æ - \param -path wskaŒnik jeden za ostatnim przej¶ciem - \return d³ugo¶æ skonsumowanego prefiksu (PO CO? LEPIEJ D£ ŠCIE¯KI) -*/ -template -long TFT - ::lgstpath(I*& buf, long*& path, long start) const -{ - long s=start; - long t; - const char* buf0=buf; - const long* pathlimit=path+FT::ftMAXPATH; - while(*buf && path=0) - { - if(!epsi(t)) buf++; - s=next(t); - *(path++)=t; - } - return buf-buf0; -} - -//---------------------------------------------------------------------------- -/// Najd³u¿szy prefiks. -/** - \param +buf wskaŒnik pierwszego elementu ci±gu symboli wej¶ciowych - \param -buf pozycja jeden za skonsumowanym prefiksem - \param +sep separator - \return stan po przej¶ciu przez \a sep - \remark Dzia³a tylko dla automatów deterministycznych, minimalnych, eps-wolnych, - gdzie d³. ¶cie¿ki == d³. dopasowania. -*/ -template -long TFT - ::pref(I*& buf, I sep, long start) const -{ - static long pathtab[ftMAXPATH]; - // static long* path=pathtab; - long* path=pathtab; - static bool more; - - long s; - if(*buf) // pierwsze wywo³anie - { - if(!lgstpath(buf,path,start)) - return -1; - --path; - more=true; - } - else // kolejne wywo³anie - --buf,--path; - while(more) - if(path>=pathtab) - if((s=next(next(*path),sep))>=0) { - return s; - } - else - --buf, --path; - else - { - more=false; - return -1; - } - return -1; -} - -//---------------------------------------------------------------------------- - -/* -template -long TFT::trans(const I* si, O* so, long& olen) const -{ - long p[ftMAXPATH]; - long ilen; - long plen; - if((ilen=lgstmatch(si,p,plen))>0) - olen=prn(si,p,so); - else - ilen=olen=0; - return ilen; -} -*/ -//---------------------------------------------------------------------------- - -template -long TFT::prn(const I* si, long* p, O* so) const -{ - switch(print_mode) - { - case OO: return prn_oo(si,p,so); - case IOIO: return prn_ioio(si,p,so); - case OIOI: return prn_oioi(si,p,so); - case IIOO: return prn_iioo(si,p,so); - case OOII: return prn_ooii(si,p,so); - } -} - -//---------------------------------------------------------------------------- - -template -long TFT::prn_oo(const I* si, long* p, O* so) const -{ - char* so0=so; - while(*p>=0) - { - long t=*p; - if(!epso(t)) - { - if(defo(t)) - *(so++)=*si; - else - *(so++)=output(t); - } - if(!epsi(t)) si++; - p++; - - } - return so-so0; -} - -//---------------------------------------------------------------------------- - - -template -long TFT::prn_ioio(const I* si, long* p, O* so) const -{ - char* so0=so; - while(*p>=0) - { - long t=*p; - if(!epsi(t)) - *(so++)=*si; - if(!epso(t)) - if(defo(t)) - *(so++)=*si; - else - *(so++)=output(t); - if(!epsi(t)) si++; - p++; - } - return so-so0; -} - - -//---------------------------------------------------------------------------- - -template -long TFT::prn_oioi(const I* si, long* p, O* so) const -{ - char* so0=so; - while(*p>=0) - { - long t=*p; - if(!epso(t)) - { - if(defo(t)) - *(so++)=*si; - else - *(so++)=output(t); - } - if(!epsi(t)) - *(so++)=*(si++); - p++; - } - return so-so0; -} - -//---------------------------------------------------------------------------- - -template -long TFT::prn_iioo(const I* si, long* p, O* so) const -{ - const char* si0=si; - long* p0=p; - char* so0=so; - while(*p>=0) - { - long t=*p; - if(!epsi(t)) - { - *(so++)=*si; - si++; - } - p++; - } - si=si0; - p=p0; - while(*p>=0) - { - long t=*p; - if(!epso(t)) - if(defo(t)) - *(so++)=*si; - else - *(so++)=output(t); - if(!epsi(t)) si++; - p++; - } - return so-so0; -} - -//---------------------------------------------------------------------------- - -template -long TFT::prn_ooii(const I* si, long* p, O* so) const -{ - - const char* si0=si; - long* p0=p; - char* so0=so; - while(*p>=0) - { - long t=*p; - if(!epso(t)) - { - if(defo(t)) - *(so++)=*si; - else - *(so++)=output(t); - } - if(!epsi(t)) si++; - p++; - } - si=si0; - p=p0; - while(*p>=0) - { - long t=*p; - if(!epsi(t)) - *(so++)=*(si++); - p++; - } - return so-so0; -} - -//--------------------------------------------------------------------------- - -template -void TFT::sort() -{ - long t=0; - while(t1) - { - long eps=-1; - long def=-1; - for(int i=0; i=0 && epseps) def--; - if(def>=0 && def=0) - { - memmove(tt+t0+def+1,tt+t0+def,tn-eps-2); - tt[t-2]=temp; - } - else - { - memmove(tt+t0+def+1,tt+t0+def,tn-eps-2); - tt[t-1]=temp; - } - } - while(t0 -void TFT::setiotypes() -{ - int i=0; - const char* it=typeid(I).name(); - while(*it) - if(*it==' ') - { it++; continue; } - else - itype[i++]=*(it++); - itype[i]='\0'; - - i=0; - const char* ot=typeid(O).name(); - while(*ot) - if(*ot==' ') - { ot++; continue; } - else - otype[i++]=*(ot++); - otype[i]='\0'; -}; - -//--------------------------------------------------------------------------- - -template -void TFT::prntt(ostream& os) -{ - for(long i=0; i -#include -#include -//#include - -#include "tft.h" -//--------------------------------------------------------------------------- - - -using namespace std; - - -template -class TFTi : public TFT > -{ -public: - TFTi() : TFT >() {}; - TFTi(const char* filename) - : TFT >() { load(filename); }; - - void read(const char* filename); - void read(istream& is=cin); - void write(const char* filename); - void write(ostream& os=cout); - void load(const char* filename); - void load(FILE* f=stdin); - void save(const char* filename); - void save(FILE* f=stdout); - void clear(); - using TFT >::ttn; - using TFT >::states; - using TFT >::transitions; - using TFT >::itype; - using TFT >::ftTYPELEN; - using TFT >::otype; - using TFT >::tt; - using TFT >::copy_default; - using TFT >::print_mode; - - -// friend istream& operator>>(istream&, TFTi&); -// friend ostream& operator<<(ostream&, const TFTi&); -}; - -//--------------------------------------------------------------------------- - -template -void TFTi::read(const char* filename) -{ - ifstream is(filename); - if(!is) { fprintf(stderr,"Failed to open input file."); exit(1); } - read(is); -} - -template -void TFTi::read(istream& is) -{ - long *si; // state-index relation - long ci=0; // current index - char ch; // character read; - int empty=0; // no of states with 0 trans? - char intype[FT::ftTYPELEN]; - char outtype[FT::ftTYPELEN]; - - clear(); - - is >> states >> transitions >> intype >> outtype; - -// if(strcmp(intype,itype)!=0 || -// strcmp(outtype,otype)!=0 && strcmp(outtype,"void")!=0) -// { is.clear(ios::badbit); goto end; }; - - while(is.peek()==' ' || is.peek()=='\t') is.get(ch); - while(is.peek()!='\n') - { - char s[20]; - is >> s; - if(strcmp(s,"COPY")==0 && strcmp(intype,outtype)==0) copy_default=true; - else if(strcmp(s,"NOCOPY")==0) copy_default=false; - else if(strcmp(s,"II")==0) print_mode=FT::II; - else if(strcmp(s,"OO")==0) print_mode=FT::OO; - else if(strcmp(s,"IOIO")==0) print_mode=FT::IOIO; - else if(strcmp(s,"OIOI")==0) print_mode=FT::OIOI; - else if(strcmp(s,"IIOO")==0) print_mode=FT::IIOO; - else if(strcmp(s,"OIOI")==0) print_mode=FT::OIOI; - while(is.peek()==' ' || is.peek()=='\t') is.get(ch); - } - - ttn=transitions+2; // 1 state without trans., 1 additional - si=new long[states]; - tt=new TTrans_i[ttn]; - - for(long cs=0;cs> cscheck; - if(cs!=cscheck) goto end; - - while(is.peek()==' ' || is.peek()=='\t') is.get(ch); - - is.get(ch); - if(!is) goto end; - switch(ch) - { - case '-': tt[ci].final(false); break; - case '+': tt[ci].final(true); break; - default: goto end; - } - tc=0, tt[ci].continued(false); - - while(is.peek()==' ' || is.peek()=='\t') is.get(ch); - while(is && is.peek()!='\n') - { - switch(is.peek()) - { - case '~': tt[ci].epsi(true); tt[ci].defi(true); is.get(ch); - break; - case '@': tt[ci].epsi(false); tt[ci].defi(true); is.get(ch); - break; - default : tt[ci].geti(is); - } - if(!is) goto end; - if(is.peek()=='/') - { - is.get(ch); - switch(is.peek()) - { - case '~': tt[ci].epso(true); tt[ci].defo(true); is.get(ch); - break; - case '@': tt[ci].epso(false); tt[ci].defo(true); is.get(ch); - break; - default : tt[ci].geto(is); - } - } - else - { - tt[ci].defo(true); - if(copy_default) tt[ci].epso(false); else tt[ci].epso(true); - } - if(!is) goto end; - - unsigned long transition; - is >> transition; - tt[ci].next(transition); - - tt[ci].continued(false); - tt[ci].empty(false); - - if(tc>0) tt[ci-1].continued(true); - tc++,ci++; - } - if(tc==0) - { - if(++empty>2) { fprintf(stderr, "Nondeterministic automaton."); exit(1); } - tt[ci].empty(true); - ci++; - } - is.get(ch); - if(ch!='\n') { is.clear(ios::badbit); goto end; } - } - - ttn=transitions+empty; - if(ttn!=ci) { is.clear(ios::badbit); goto end; }; - for(long i=0;i -void TFTi::write(const char* filename) -{ - ofstream os(filename); - if(!os) err("Failed to open output file."); - write(os); -} - -template -void TFTi::write(ostream& os) -{ - os << states << ' ' << transitions << ' '; -// os << itype << ' ' << otype << ' '; - os << "char void"; -// os << (copy_default ? "COPY" : "NOCOPY") << ' '; -// switch(print_mode) -// { -// case FT::II : os << "II"; break; -// case FT::OO : os << "OO"; break; -// case FT::IOIO: os << "IOIO"; break; -// case FT::OIOI: os << "OIOI"; break; -// case FT::IIOO: os << "IIOO"; break; -// case FT::OOII: os << "OOII"; -// } - os << '\n'; - - long* si=new long[ttn]; - long cs=0; - for(long i=0;i -void TFTi::load(const char* filename) -{ - FILE* f; - if(*filename) - f=fopen(filename,"rb"); - else - f=stdin; - if(!f) { fprintf(stderr, "Cannot open automaton file."); return; } - load(f); -} - -template -void TFTi::load(FILE* f) -{ - - clear(); - - if(fread(&ttn,sizeof(ttn),1,f)!=1) { fprintf(stderr, "Binary input error."); return;} - if(fread(&states,sizeof(states),1,f)!=1) { fprintf(stderr, "Binary input error."); return;} - if(fread(&transitions,sizeof(transitions),1,f)!=1) { fprintf(stderr, "Binary input error."); return;} - if(fread(itype,sizeof(char),ftTYPELEN,f)!=ftTYPELEN) { fprintf(stderr, "Binary input error."); return;} - if(fread(otype,sizeof(char),ftTYPELEN,f)!=ftTYPELEN) { fprintf(stderr, "Binary input error."); return;} - if(fread(©_default,sizeof(copy_default),1,f)!=1) { fprintf(stderr, "Binary input error."); return;} - if(fread(&print_mode,sizeof(print_mode),1,f)!=1) { fprintf(stderr, "Binary input error."); return;} - if((tt=new TTrans_i[ttn])==NULL) { fprintf(stderr, "Cannot allocate memory for tt."); return;} - if(fread(tt,sizeof(TTrans_i),ttn,f)!=ttn) { fprintf(stderr, "Binary input error."); return; } - fclose(f); - - -} - -//--------------------------------------------------------------------------- - -template -void TFTi::save(const char* filename) -{ - FILE* f; - if(*filename) - f=fopen(filename,"wb"); - else - f=stdout; - if(!f) err("Cannot open file."); - save(f); -} - -template -void TFTi::save(FILE* f) -{ - if(fwrite(&ttn,sizeof(ttn),1,f)!=1) { fprintf(stderr,"Binary output error."); exit(1); } - if(fwrite(&states,sizeof(states),1,f)!=1) { fprintf(stderr,"Binary output error."); exit(1); } - if(fwrite(&transitions,sizeof(transitions),1,f)!=1) { fprintf(stderr,"Binary output error."); exit(1); } - if(fwrite(itype,sizeof(char),ftTYPELEN,f)!=ftTYPELEN) { fprintf(stderr,"Binary output error."); exit(1); } - if(fwrite(otype,sizeof(char),ftTYPELEN,f)!=ftTYPELEN) { fprintf(stderr,"Binary output error."); exit(1); } - if(fwrite(©_default,sizeof(copy_default),1,f)!=1) { fprintf(stderr,"Binary output error."); exit(1); } - if(fwrite(&print_mode,sizeof(print_mode),1,f)!=1) { fprintf(stderr,"Binary output error."); exit(1); } - if(fwrite(tt,sizeof(TTrans_i),ttn,f)!=ttn) { fprintf(stderr,"Binary output error."); exit(1); } - fclose(f); -} - -//--------------------------------------------------------------------------- - -template -void TFTi::clear() -{ - if(tt) delete[] tt; - ttn=0; -} - -//--------------------------------------------------------------------------- -/* -template -istream& operator>>(istream& is, TFTi& ft) -{ - long *si; // state-index relation - long ci=0; // current index - char ch; // character read; - int empty=0; // no of states with 0 trans? - char intype[FT::ftTYPELEN]; - char outtype[FT::ftTYPELEN]; - - ft.clear(); - - is >> ft.states >> ft.transitions >> intype >> outtype; - - if(strcmp(intype,ft.itype)!=0 || - strcmp(outtype,ft.otype)!=0 && strcmp(outtype,"void")!=0) - { is.clear(ios::badbit); return is; }; - - while(is.peek()==' ' || is.peek()=='\t') is.get(ch); - while(is.peek()!='\n') - { - char s[20]; - is >> s; - if(strcmp(s,"COPY")==0 && strcmp(intype,outtype)==0) ft.copy_default=true; - else if(strcmp(s,"NOCOPY")==0) ft.copy_default=false; - else if(strcmp(s,"II")==0) ft.print_mode=FT::II; - else if(strcmp(s,"OO")==0) ft.print_mode=FT::OO; - else if(strcmp(s,"IOIO")==0) ft.print_mode=FT::IOIO; - else if(strcmp(s,"OIOI")==0) ft.print_mode=FT::OIOI; - else if(strcmp(s,"IIOO")==0) ft.print_mode=FT::IIOO; - else if(strcmp(s,"OIOI")==0) ft.print_mode=FT::OIOI; - while(is.peek()==' ' || is.peek()=='\t') is.get(ch); - } - - ft.ttn=ft.transitions+2; // 1 state without trans., 1 additional - si=new long[ft.states]; - ft.tt=new TTrans_i[ft.ttn]; - - for(long cs=0;cs> ch; while(ch!='+' && ch!='-'); - switch(ch) - { - case '-': ft.tt[ci].final(false); break; - case '+': ft.tt[ci].final(true); break; - default: return is; - } - tc=0, ft.tt[ci].continued(false); - while((is.get(ch),ch==' ')) - { - if(!is) return is; - switch(is.peek()) - { - case '~': ft.tt[ci].epsi(true); ft.tt[ci].defi(true); is.get(ch); - break; - case '@': ft.tt[ci].epsi(false); ft.tt[ci].defi(true); is.get(ch); - break; - default : ft.tt[ci].geti(is); - } - if(!is) return is; - if(is.peek()=='/') - { - is.get(ch); - switch(is.peek()) - { - case '~': ft.tt[ci].epso(true); ft.tt[ci].defo(true); is.get(ch); - break; - case '@': ft.tt[ci].epso(false); ft.tt[ci].defo(true); is.get(ch); - break; - default : ft.tt[ci].geto(is); - } - } - else - { - ft.tt[ci].defo(true); - if(ft.copy_default) ft.tt[ci].epso(false); else ft.tt[ci].epso(true); - } - if(!is) return is; - - unsigned long transition; - is >> transition; - ft.tt[ci].next(transition); - - ft.tt[ci].continued(false); - - ft.tt[ci].empty(false); - if(tc>0) ft.tt[ci-1].continued(true); - tc++,ci++; - } - if(tc==0) - { - if(++empty>2) err("Nondeterministic automaton."); - ft.tt[ci].empty(true); - ci++; - } - if(ch!='\n') { is.clear(ios::badbit); return is; } - } - - ft.ttn=ft.transitions+empty; - if(ft.ttn!=ci) { is.clear(ios::badbit); return is; }; - for(long i=0;i -ostream& operator<<(ostream& os, const TFTi& ft) -{ - os << ft.states << ' ' << ft.transitions << ' ' - << ft.itype << ' ' << ft.otype << ' '; - os << (ft.copy_default ? "COPY" : "NOCOPY") << ' '; - switch(ft.print_mode) - { - case FT::II : os << "II"; break; - case FT::OO : os << "OO"; break; - case FT::IOIO: os << "IOIO"; break; - case FT::OIOI: os << "OIOI"; break; - case FT::IIOO: os << "IIOO"; break; - case FT::OOII: os << "OOII"; - } - os << ' ' << '\n'; - - long* si=new long[ft.ttn]; - long cs=0; - for(long i=0;i -class TFTiv : public TFTi -{ -public: - TFTiv() : TFTi() {}; - TFTiv(const char* filename) : TFTi(filename) {}; -}; - -//--------------------------------------------------------------------------- - -template -class TFTir : public TFTi -{ -public: - TFTir() : TFTi() {}; -}; - -//--------------------------------------------------------------------------- -#endif Index: ld/app/src/lib/ttrans.h =================================================================== --- _old/app/src/lib/ttrans.h (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,207 +1,0 @@ -#ifndef _TTransi_h -#define _TTransi_h -//--------------------------------------------------------------------------- -#include -//--------------------------------------------------------------------------- - - -using namespace std; - -//! The template for a transition with input and output symbols stored internally. -/*! - A state is identified with the set of its outgoing transitions. - The state index is the index of the first transition for it. - A state with no outgoing transition is represented as an empty transition. -*/ -template -class TTrans_i -{ -public: -//private: -//! Input symbol - I i; -//! Output symbol - O o; - -public: - -//! state is final - static const unsigned char BITf=0x01; -//! transition list is continued - static const unsigned char BITc=0x02; -//! no transition - static const unsigned char BITe=0x04; -//! epsilon input - static const unsigned char BITepsi=0x08; -//! default input - static const unsigned char BITdefi=0x10; -//! epsilon output - static const unsigned char BITepso=0x20; -//! default output - static const unsigned char BITdefo=0x40; - -//! Flags - unsigned char flags; - -//! The index of the next state - long nxt; - -//! Input symbol. -//! \return The input symbol of the transition. - Ipass in() const { return i; } - -//! Output symbol. -//! \return The output symbol of the transition. - Opass out() const { return o; } - -//! Set the input symbol. -//! \param in input symbol - void in(Ipass in) { i=in; } - -//! Set the output symbol. -//! \param out output symbol - void out(Opass out) { o=out; } - -//! remark Is this needed? - I& iref() { return i; } - -//! remark Is this needed? - O& oref() { return o; } - -//! Test whether an input symbol is accepted. -//! \remark Simplified. Should rely on a test function provided by the user. - bool accepts(Ipass in) { return defi() || in==i; } - -//! Next state. -//! \return Destination state of the transition. - long next() const { return nxt; }; - -//! Set the next state. -//! \param t destination state of the transition - void next(long t) { nxt=t; }; - -//! Is the state final? -//! \return \c true if the state is final, false otherwise. - bool final() const { return flags&BITf; }; - -//! Set the \b final flag. -//! \param b \c true if the state is final, \c false otherwise. - void final(bool b) { if(b) flags|=BITf; else flags&=~BITf; }; - -//! Is the transition list continued? -//! \return \c true if the transition is not the last transition for the state, -//! \c false otherwise. - bool continued() const { return flags&BITc; }; - -//! Set the \b continuation flag. -//! \param b \c true if the transition is not the last one for the state, \c false otherwise. - void continued(bool b) { if(b) flags|=BITc; else flags&=~BITc; }; - -//! Is the transition empty? -//! \return \c true if the transition is empty (represents a state with no outgoing transitions), -//! \c false otherwise. - bool empty() const { return flags&BITe; }; - -//! Set the \b empty flag. -//! \param b \c true if the transition is empty, \c false otherwise. - void empty(bool b) { if(b) flags|=BITe; else flags&=~BITe; }; - - bool epsi() const { return flags&BITepsi; }; - void epsi(bool b) { if(b) flags|=BITepsi; else flags&=~BITepsi; }; - - bool defi() const { return flags&BITdefi; }; - void defi(bool b) { if(b) flags|=BITdefi; else flags&=~BITdefi; }; - - bool epso() const { return flags&BITepso; }; - void epso(bool b) { if(b) flags|=BITepso; else flags&=~BITepso; }; - - bool defo() const { return flags&BITdefo; }; - void defo(bool b) { if(b) flags|=BITdefo; else flags&=~BITdefo; }; - - void geti(istream&); - void geto(istream&); - -// friend ostream& operator<<(ostream& os, const TTrans_i& t); - -}; - -//--------------------------------------------------------------------------- - -template -void getsym(istream& is, char& c) -{ - is >> c; - if(c=='\\') - { - is.get(c); - switch(c) - { - case 'n':c='\n';break; - case 't':c='\t';break; - } - } -} - -template -void getsym(istream& is, T& s) -{ is >> s; } - -//--------------------------------------------------------------------------- - -template -void TTrans_i::geti(istream& is) -{ getsym(is,iref()); }; - -template -void TTrans_i::geto(istream& is) -{ getsym(is,oref()); }; - -//--------------------------------------------------------------------------- -/* -template -ostream& operator<<(ostream& os, const TTrans_i& t) -{ - os << (t.final() ? '+' : '-'); - os << ' '; - - if(!t.empty()) - { - if(t.defi()) - os << (t.epsi() ? '~' : '@'); - else - switch(t.in()) - { - case ' ': os << "\\ "; break; - case '\n': os << "\\n"; break; - case '\t': os << "\\t"; break; - default: os << t.in(); - } - - os << '/'; - - if(t.defo()) - os << (t.epso() ? '~' : '@'); - else - switch(t.out()) - { - case ' ': os << "\\ "; break; - case '\n': os << "\\n"; break; - case '\t': os << "\\t"; break; - default: os << t.out(); - } - - os << ' ' << t.next(); - } - - os << '\n'; - - if(!t.continued()) - os << '\n'; - - return os; -} -*/ - -//--------------------------------------------------------------------------- -#endif - Index: ld/app/src/lib/word.cc =================================================================== --- _old/app/src/lib/word.cc (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,250 +1,0 @@ -//--------------------------------------------------------------------------- -#include "word.h" -#include "auttools.h" -#include -//--------------------------------------------------------------------------- - -using namespace std; - -//--------------------------------------------------------------------------- - -void Word::autodescr(const char* fo, const char* de) -{ - strcpy(f,fo); - // len=strlen(f); - - char lemd[MAXDESCRLEN]; - int i=strcspn(de,","); - strncpy(lemd,de,i); - lemd[i]='\0'; - if(isdigit(lemd[0])) - fullform(f,lemd,l); // je¶li lemat zakodowany - else - strcpy(l,lemd); // je¶li lemat w pe³nej postaci - strcpy(d,de+i+1); -} - -//--------------------------------------------------------------------------- -bool Word::cmp_w(Word a, Word b) { - return (a.w_suf() > b.w_suf()); -} -//--------------------------------------------------------------------------- -bool Word::cmp_w_rev(Word a, Word b) { - return (a.w_suf() < b.w_suf()); -} -//--------------------------------------------------------------------------- -bool cmp_w_fun(Word a, Word b) { - return (a.w_suf() > b.w_suf()); -} -//--------------------------------------------------------------------------- -bool cmp_w_rev_fun(Word a, Word b) { - return (a.w_suf() < b.w_suf()); -} -//--------------------------------------------------------------------------- - -istream& operator>>(istream& is, Word& w) -{ - char temp[Word::MAXLEN+1]; - char c; - - int i=0; - while(i'; - return os; -} - -//--------------------------------------------------------------------------- -Words::~Words() { - // for (int i=0; imax && !tab[i].returned) { - max = w; - result = i; - } - } - if (result != -1) - tab[result].returned = 1; - return result; -} - -//--------------------------------------------------------------------------- -void Words::sort() { -// sort(tab.begin(), tab.end(), Word::cmp_w); //NIE DZIALA -} - -//--------------------------------------------------------------------------- -void Words::sort_rev() { -// sort(tab.begin(), tab.end(), cmp_w_rev_fun); // NIE DZIALA -} - -//--------------------------------------------------------------------------- - -int Words::add(const char* fo) -{ - int i = find(fo); - if(i!=-1) { - return i; - } - - if (cnt>=tab.capacity()-1) - tab.resize(tab.size()*2); - - - Word o; - o.form(fo); - o.w_suf(0.0); - tab.push_back(o); -// tab[cnt].form(fo); -// tab[cnt].w_suf(0.0); - - - // if(cntform(fo); - tab[cnt]->w_suf(0.0); - tab[cnt]->w_pref(0.0);*/ - return cnt++; - // } - //return -1; -} - -//--------------------------------------------------------------------------- - - //TYMCZASOWO TAK(DLA CORA) -int Words::add(const char* fo, float weight) -{ - int i = find(fo); - if(i!=-1) { - return i; - } - - if (cnt>=tab.capacity()-1) - tab.resize(tab.size()*2); - - Word o; - o.form(fo); - o.w_suf(weight); - tab.push_back(o); -// tab[cnt].form(fo); -// tab[cnt].w_suf(weight); - - return cnt++; - // } - //return -1; -} - -//--------------------------------------------------------------------------- - -int Words::add(const char* fo, const char* des) -{ - char d[Word::MAXDESCRLEN]; - int l=strcspn(des,","); - int ok=1; - if( *(des+l) == ',' ) - { - strcpy(d,des+l+1); - // printf("\t%s->%s,\n", des, d); - int i=find(fo, d); - if(i!=-1) - return i; - } - else - ok=0; - - if (cnt>=tab.capacity()-1) - tab.resize(tab.size()*2); - - tab[cnt].form(fo); - if(ok) - tab[cnt].autodescr(fo, des); - else - tab[cnt].autodescr(fo, "?,?"); - - tab[cnt].w_suf(0.0); - tab[cnt].returned = 0; - /* - // if(cntform(fo); - tab[cnt]->autodescr(fo,des); - tab[cnt]->w_suf(0.0); - tab[cnt]->w_pref(0.0); - // printf("ok!\n");*/ - return cnt++; - // } - // printf("hm\n"); - return -1; -} - -//--------------------------------------------------------------------------- -void Words::prn(ostream& os) -{ - for(int i=0; i"; -} - -//--------------------------------------------------------------------------- - -ostream& operator<<(ostream& os, Words& tab) -{ - /* for(int i=0; i - -#include - -#include -//--------------------------------------------------------------------------- - -using namespace std; - - - -class Word -{ -public: - static const int MAXLEN=64; // dac do global - static const int MAXDESCRLEN=80; // dac do global - -private: - /// word form - char f[MAX_FORM]; // w wolnej chwili nazwy mozna zamienic na dluzsze - - /// length - int _len_suf; // dlugosc dopasowania koncowki... - // int _len_pref; // ... i prefiksu - - /// lemma - char l[MAX_FORM]; - - /// description - char d[MAX_DESC]; - - /// weight (probability) - float _w_suf; - // float _w_pref; -public: - static bool cmp_w(Word a, Word b); - static bool cmp_w_rev(Word a, Word b); - - Word() : _len_suf(-1) { *f='\0'; returned=0; }; - Word(const char* fo, const char* des) : _len_suf(-1) { autodescr(fo,des); _w_suf=1.0; returned=0; }; - - Word(const Word& w); - - char* form() { return f; } // przywrocic const - char* lemma() { return l; } // przywrocic const - char* descr() { return d; } - float w_suf() { return _w_suf; }; - int len_suf() { return _len_suf; } - - - void form(const char* s) { strcpy(f,s); } - void lemma(const char* s) { strcpy(l,s); } - void descr(const char* s) { strcpy(d,s); }; - void w_suf(float x) { _w_suf=x; }; - void len_suf(int n) { _len_suf=n; }; - - bool operator==(const Word& w); - bool operator!=(const Word& w); - int cmp(const Word&); - int cmpi(const Word&); - - char* operator!() { return f; }; - - operator bool() { return _len_suf>0; }; - - char* str() { return f; } - - void autodescr(const char* fo, const char* des); - - friend istream& operator>>(istream& is, Word& m); - friend ostream& operator<<(ostream& os, Word& m); - - bool returned; - -}; - - -inline Word::Word(const Word& word) -{ strcpy(f,word.f); strcpy(l,word.l); strcpy(d,word.d); _len_suf=word._len_suf; _w_suf=word._w_suf; returned = 0; } - -//--------------------------------------------------------------------------- - -inline bool Word::operator==(const Word& w) -{return _len_suf==w._len_suf && - !strcmp(f,w.f) && !strcmp(l,w.l) && !strcmp(d,w.d); } - -//--------------------------------------------------------------------------- - -inline bool Word::operator!=(const Word& w) -{return _len_suf!=w._len_suf || - strcmp(f,w.f) || strcmp(l,w.l) || strcmp(d,w.d);} - -//--------------------------------------------------------------------------- - -inline int Word::cmp(const Word& w) { return strcmp(f,w.f); } - -//--------------------------------------------------------------------------- - -//inline int Word::cmpi(const Word& w) { return PL.cmpi(f,w.f); } - -//--------------------------------------------------------------------------- - - - - -bool cmp_w_fun(Word a, Word b); -bool cmp_w_rev_fun(Word a, Word b); - - -//--------------------------------------------------------------------------- -//--------------------------------------------------------------------------- - -class Words -{ - private: - int find(const char* word); - int find(const char* word, const char* descr); - public: - - static const int MAX=1024; - - Words() : cnt(0) {tab.resize(MAX); }; - ~Words(); - Word& operator[](int i) { return tab[i]; } - int count() const { return cnt; } - void clear() { cnt=0; tab.clear(); } - int add(const char* fo); - int add(const char* fo, float weight); - int add(const char* fo, const char* des); - - /* zwraca index nastepnego wyniku, podczas pierwszego wywolania - * zwraca index wyniku o najwiekszej wadze, przy drugim wywolaniu - * wynik z druga najwyzsza waga, itd. - * Jezeli nie ma juz wynikow - zwraca -1. - */ - int next(); - - void sort(); - void sort_rev(); - - void prn(ostream& os); - -// friend class Lem; -// friend class AuxLem; - friend ostream& operator<<(ostream& os, Words& tab); - vector tab; - int cnt; - -}; - -//--------------------------------------------------------------------------- - -#endif - Index: ld/app/src/sen-nl/Makefile =================================================================== --- _old/app/src/sen-nl/Makefile (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,9 +1,0 @@ - -sen-nl: - -copy: -ifdef UTT_BIN_DIR - cp sen-nl ${UTT_BIN_DIR} -endif - -clean: Index: ld/app/src/tags/Makefile =================================================================== --- _old/app/src/tags/Makefile (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,8 +1,0 @@ -main: - -copy: -ifdef UTT_BIN_DIR - cp *.tag2re ${UTT_BIN_DIR} -endif - -clean: Index: ld/app/src/tags/README =================================================================== --- _old/app/src/tags/README (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,5 +1,0 @@ -In this directory files specific to different tag formats are stored. - -TAGSET.tag2re are command-line programs which translate a tag constraint -specification into a character-level regular expression matching -all tags in the TAGSET format meeting the specified constraint. Index: ld/app/src/tags/ipi.tag2re =================================================================== --- _old/app/src/tags/ipi.tag2re (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,1 +1,0 @@ -#TODO Index: ld/app/src/tok.c/Makefile =================================================================== --- _old/app/src/tok.c/Makefile (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,37 +1,0 @@ -PAR=-Wno-deprecated -O3 -PAR2=-c -Wno-deprecated -O3 -LIB_PATH=../lib -CMDLINE_FILE='"../tok.c/cmdline.h"' - - -tok: tok.o cmdline.c common_tok.o common.o - g++ $(PAR) -D _CMDLINE_FILE=$(CMDLINE_FILE) \ - tok.c cmdline.c common.o common_tok.o -o tok - -tok.o: tok.c cmdline.h - g++ $(PAR2) -D _CMDLINE_FILE=$(CMDLINE_FILE) tok.c - -common_tok.o: cmdline.h common_tok.cc common_tok.h - g++ $(PAR2) -D _CMDLINE_FILE=$(CMDLINE_FILE) common_tok.cc - -common.o: $(COMMON_PATH)/cmdline_common.ggo $(COMMON_PATH)/common.cc \ - $(COMMON_PATH)/common.h - g++ $(PAR2) -D _CMDLINE_FILE=$(CMDLINE_FILE) $(COMMON_PATH)/common.cc - -cmdline.ggo: cmdline_tok.ggo ../common/cmdline_common.ggo - cat cmdline_tok.ggo ../common/cmdline_common.ggo > cmdline.ggo - -cmdline.c cmdline.h: cmdline.ggo - gengetopt -i cmdline.ggo --conf-parser - -copy: -ifdef UTT_BIN_DIR - cp tok ${UTT_BIN_DIR}/ -endif - - -clean: clean.cmdline - rm *.o - -clean.cmdline: - rm cmdline.* Index: ld/app/src/tok.c/cmdline_tok.ggo =================================================================== --- _old/app/src/tok.c/cmdline_tok.ggo (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,4 +1,0 @@ -package "tok" -version "0.1" - - Index: ld/app/src/tok.c/common_tok.cc =================================================================== --- _old/app/src/tok.c/common_tok.cc (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,27 +1,0 @@ -#include -#include -#include "common_tok.h" - -char dictionary[255]; - -void process_tok_options(gengetopt_args_info args) -{ - if(args.dictionary_given) - strcpy(dictionary, args.dictionary_arg); - else { - char path[256]; - sprintf(path, "/etc/utt/%s", DICT_FILE); - if (file_accessible(path) == 0) - strcpy(dictionary, path); - else { - sprintf(path, "%s/.utt/%s", getenv("HOME"), DICT_FILE); - if (file_accessible(path) == 0) - strcpy(dictionary, path); - else { - fprintf(stderr, "Cannot find dictionary!\n"); - exit(1); - } - } - } - -} Index: ld/app/src/tok.c/common_tok.h =================================================================== --- _old/app/src/tok.c/common_tok.h (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,15 +1,0 @@ -#ifndef __COMMON_TOK__H -#define __COMMON_TOK__H - -#include -#include "../common/common.h" - -#include "cmdline.h" - -#define DICT_FILE "data/tok.bin" - -extern char dictionary[]; - -extern void process_tok_options(gengetopt_args_info args); - -#endif Index: ld/app/src/tok.c/tok.c =================================================================== --- _old/app/src/tok.c/tok.c (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,83 +1,0 @@ - -#include -#include -#include -#include - - -#include -//#include "../lib/iotools.h" - -#include "cmdline.h" - - -char buf[257]; -int filepos=0; -char* tokstart; -char* tokend; -char tmp; -char tag; - - -gengetopt_args_info args; - - -inline -void printtoken(char tag) -{ - tmp=*tokend; - *tokend='\0'; - printf("%04d %02d %c %s\n", filepos, tokend-tokstart, tag, tokstart); - *tokend=tmp; - filepos+=tokend-tokstart; - tokstart=tokend; - if(args.interactive_flag) fflush(stdout); -} - -main(int argc, char** argv) -{ - - if (cmdline_parser(argc, argv, &args) != 0) - exit(1); - - printf("inter:%d\n",args.interactive_flag); - - // process_common_options(&args, argv[0]); - // process_tok_options(args); - - setlocale(LC_CTYPE,""); - setlocale(LC_COLLATE,""); - - while(fgets(buf,256,stdin)) - { - - tokstart=tokend=buf; - while(*tokend) - { - char *prev=tokend; - ++tokend; - if(isalpha(*prev) && !isalpha(*tokend)) - printtoken('W'); - else if(isdigit(*prev) && !isdigit(*tokend)) - printtoken('N'); - else if(isspace(*prev)) - { - switch(*prev) - { - case ' ': *prev='_'; break; - case '\t':*prev='t'; break; - case '\r':*prev='r'; break; - case '\f':*prev='f'; break; - case '\n':*prev='n'; - } - if(!isspace(*tokend)) - printtoken('S'); - } - else if(ispunct(*prev)) - printtoken('P'); - } - } - - cmdline_parser_free(&args); -} - Index: ld/app/src/tok/Makefile =================================================================== --- _old/app/src/tok/Makefile (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,6 +1,0 @@ -tok: - -copy: -ifdef UTT_BIN_DIR - cp tok ${UTT_BIN_DIR} -endif Index: ld/app/src/tok/tok =================================================================== --- _old/app/src/tok/tok (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,125 +1,0 @@ -#!/usr/bin/perl - -#package: UAM Text Tools -#component: tok (tokenizer) -#version: 1.0 -#author: Tomasz Obrebski - -use strict; -use locale; -use Getopt::Long; -use File::HomeDir; - -my $max_form_length = 50; - -my $interactive=0; -my $help; - -my $systemconfigfile='/usr/local/etc/utt/tok.conf'; -#my $userconfigfile="$ENV{'HOME'}/.utt/tok.conf"; -my $userconfigfile=home()."/.utt/tok.conf"; - -#read configuration files########################### -my $file; -foreach $file ($systemconfigfile, $userconfigfile){ - if(open(CONFIG, $file)){ - while () { - chomp; - s/#.*//; - s/^\s+//; - s/\s+$//; - next unless length; - my ($name, $value) = split(/\s*=\s*/, $_, 2); - if(($name eq "interactive")or($name eq "i")){ - $interactive=1; - } - elsif(($name eq "help")or($name eq "h")){ - $help=1; - } - } - close CONFIG; - } -} -#########################################################s - -GetOptions("interactive|i" => \$interactive, - "help|h" => \$help); - -if($help) -{ - print <<'END' -Usage: tok [OPTIONS] - -Options: - --interactive Interactive (no output buffering). - --help -h Help. -END -; - exit 0; -} - - -$| = $interactive; - -my $offset = 0; - -while(<>) -{ - 1 while - / [[:alpha:]]+ (?{seg('W',$&)}) - | \d+ (?{seg('N',$&)}) - | \s+ (?{seg('S',$&)}) - | [[:punct:]] (?{seg('P',$&)}) - | . (?{seg('B',$&)}) - /gxo; -} - -# | [^[:print:]] (?{seg("B",$&)}) - -sub min { - my ($val1, $val2) = @_; - if($val1 < $val2) { - return $val1; - } - else { - return $val2; - } -} - - -sub seg -{ - my ($tag,$match) = @_; - my $length = length $match; - my $idx = 0; - while($idx < $length) { - my $l = min $max_form_length, $length - $idx; - my $m = substr $match, $idx, $l; - - printf "%04d %02d %s ", $offset + $idx, $l, $tag; - if($tag eq 'S') - { - for(my $i=0; $i<$l; ++$i) - { - my $c = substr $m, $i, 1; - print '_' if $c eq ' '; - print '\n' if $c eq "\n"; - print '\t' if $c eq "\t"; - print '\r' if $c eq "\r"; - print '\f' if $c eq "\f"; - } - } - elsif($tag eq 'B') - { - printf "\\x%02X", ord($m); - } - else - { - print $m; - } - print "\n"; - $idx += $l; - } # while($idx < $length) - $offset += $length; -} #sub seg - Index: ld/lang/Makefile =================================================================== --- _old/lang/Makefile (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,40 +1,0 @@ - -CUR_DIR=$(shell pwd) - -#directory with dictionary source -export UTT_DIC_SRC_HOME=${CUR_DIR}/src -#directory with configuration files -export UTT_DIC_CONF_HOME=${CUR_DIR}/conf -#directory where compiled dictionaries will be placed -export UTT_DIC_BIN=$(CUR_DIR)/dic -#directory where distribution will be placed -export UTT_DIC_OUTPUT=${CUR_DIR} - -export LANG_MODULES=pl_PL.ISO-8852-2 pl_PL.UTF-8 - -# path to dictionary compiler -DIC_COMPILER=../app/src/compiledic/compiledic - - - -.PHONY: compile -compile: - #$DIC_COMPILER ... - - - -.PHONY: distribute -distribute: compile dist_tarball - @echo "Distribution ready!" - - -.PHONY: dist_tarball -dist_tarball: - cd dist && make tarball; cd ${CUR_DIR}; - - -.PHONY: dist_tarball_pl_PL.ISO-8859-2 -dist_tarball: - export DIC_LANG=pl_PL.ISO-8859-2 && \ - cd dist && make tarball; cd ${CUR_DIR}; - Index: ld/lang/README =================================================================== --- _old/lang/README (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,1 +1,0 @@ -the directory contains Index: ld/lang/README.developers =================================================================== --- _old/lang/README.developers (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,10 +1,0 @@ -To create dictionary distribution, use: - make dist_tarball -or - make dist_tarball DIC_LANG=pl_PL.ISO-8859-2 - -The fisrt version will create tarball for all dictionaries, -the second only for selected language and encoding. -The tarball file will be placed in current directory. - -Next distribution will be prepared soon. Index: ld/lang/conf/pl_PL.ISO-8859-2/pl_PL.ISO-8859-2.sym =================================================================== --- _old/lang/conf/pl_PL.ISO-8859-2/pl_PL.ISO-8859-2.sym (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,8 +1,0 @@ -lcase a ± b c æ d e ê f g h i j k l ³ m n ñ o ó -lcase p q r s ¶ t u v w x y z Œ ¿ é ö ü ä -ucase A ¡ B C Æ D E Ê F G H I J K L £ M N Ñ O Ó -ucase P Q R S Š T U V W X Y Z ¬ ¯ -letter lcase ucase -digit 0 1 2 3 4 5 6 7 8 9 -punct , . @ / ' ~ ; _ - + ? \ -all letter digit signs sem Index: ld/lang/conf/pl_PL.UTF-8/pl_PL.utf-8.sym =================================================================== --- _old/lang/conf/pl_PL.UTF-8/pl_PL.utf-8.sym (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,9 +1,0 @@ -lcase a Ä - b c ć d e ę f g h i j k l ł m n ń o ó -lcase p q r s ś t u v w x y z ź ÅŒ é ö ÃŒ À -ucase A Ą B C Ć D E Ę F G H I J K L Ł M N Ń O Ó -ucase P Q R S Ś T U V W X Y Z Ź Å» -letter lcase ucase -digit 0 1 2 3 4 5 6 7 8 9 -punct , . @ / ' ~ ; _ - + ? \ -all letter digit signs sem Index: ld/lang/dist/Makefile =================================================================== --- _old/lang/dist/Makefile (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,37 +1,0 @@ - -# some variables - -# ----------------------------------------------------------- -# default task should display options -.PHONY: default -defaul: - @echo "Using: make tarball|rpm|deb" - - -# ----------------------------------------------------------- -# this task will create tar.gz distribution -.PHONY: tarball -tarball: - cd tarball && make - -# ----------------------------------------------------------- -# this task should compile utt (if nesessery) and create rpm version -.PHONY: rpm -rpm: - @#we build rpm (see spec/README for details) - cd spec && make - -# ----------------------------------------------------------- -# this task should compile utt (if nesessery) and create deb version -.PHONY: deb -deb: - @#we build deb (see deb/README for details) - cd deb && make - -# ----------------------------------------------------------- -# this task should remove compiled files and directories -.PHONY: clean -clean: - # finally the line below should be uncomment - #rm -fr ${UTT_DIST_TMP} - Index: ld/lang/dist/tarball/Makefile =================================================================== --- _old/lang/dist/tarball/Makefile (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,41 +1,0 @@ -# This makefile builds tarball distribution for utt dictionary. - -# -# Some variables -# -DIR=$(shell pwd) - -# Common info about version and release -_UTT_VER=$(shell cat ../../../app/dist/common/version.def) -_UTT_REL=$(shell cat ../../../app/dist/common/release.def) - -# Temp vars -_TARBALL_ROOT=$(DIR)/utt-$(_UTT_VER).$(_UTT_REL) -_UTT_DIC_HOME=share/utt -_TAR_FILE_NAME=utt.$(_UTT_VER)_$(_UTT_REL) - - -#defualt task -.PHONY: default -default: - @echo Build directory: ${UTT_DIC_BIN} - @echo Output directory for tarball: ${UTT_DIC_OUTPUT} - mkdir -p ${_TARBALL_ROOT}/${_UTT_DIC_HOME} - if [[ -n "${DIC_LANG}" && -d ${UTT_DIC_BIN}/${DIC_LANG} ]]; \ - then \ - echo "Tworze dystrybucje ${DIC_LANG}"; \ - mkdir -p ${_TARBALL_ROOT}/${_UTT_DIC_HOME}/${DIC_LANG}; \ - cp -fr ${UTT_DIC_BIN}/${DIC_LANG}/* ${_TARBALL_ROOT}/${_UTT_DIC_HOME}/${DIC_LANG}/; \ - cp -fr ${UTT_DIC_CONF_HOME}/${DIC_LANG}/* ${_TARBALL_ROOT}/${_UTT_DIC_HOME}/${DIC_LANG}/; \ - rm -rf ${_TARBALL_ROOT}/${_UTT_DIC_HOME}/${DIC_LANG}/.svn ; \ - tar -czf ${UTT_DIC_OUTPUT}/${_TAR_FILE_NAME}.${DIC_LANG}.tar.gz utt*; \ - else \ - echo "Tworze pelna dystrybucje!"; \ - cp -fr ${UTT_DIC_BIN}/* ${_TARBALL_ROOT}/${_UTT_DIC_HOME}/; \ - cp -fr ${UTT_DIC_CONF_HOME}/* ${_TARBALL_ROOT}/${_UTT_DIC_HOME}/; \ - find ${_TARBALL_ROOT}/${_UTT_DIC_HOME} -type d -path '*/.svn' -exec rm -rf {} \; ; \ - tar -czf ${UTT_DIC_OUTPUT}/${_TAR_FILE_NAME}.all.tar.gz utt*; \ - fi - - rm -rf ${_TARBALL_ROOT} - Index: ld/nawszelkiwypadek/tools/cor_dic/makeLabels.pl =================================================================== --- _old/nawszelkiwypadek/tools/cor_dic/makeLabels.pl (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,11 +1,0 @@ -#!/usr/bin/perl - -use locale; - -print "lcase a ± b c æ d e ê f g h i j k l ³ m n ñ o ó p q r s ¶ t u v w x y z Œ ¿ é ö ü ä\n"; -print "ucase A ¡ B C Æ D E Ê F G H I J K L £ M N Ñ O Ó P Q R S Š T U V W X Y Z ¬ ¯\n"; -print "letter lcase ucase\n"; -print "digit 0 1 2 3 4 5 6 7 8 9\n"; -print "signs , . @ \/ \'\n _"; -print "sem ~ ; - \\ \n"; -print "all letter digit signs sem\n"; Index: ld/nawszelkiwypadek/tools/cor_dic/prep.pl =================================================================== --- _old/nawszelkiwypadek/tools/cor_dic/prep.pl (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,67 +1,0 @@ -#! /usr/bin/perl - -use locale; -use strict; - -my $file = shift; - -if ($file eq "") { - print "Podaj nazwê pliku.\n"; - exit(0); -} - - -`makeLabels.pl > labels.sym`; - -`lexmakelab labels`; - -print "Pobieram informacje ze s³ownika.........................."; - -`cut -d \\; -f 1 <$file > temp1`; - -`sort -u < temp1 > temp2`; - -print "OK\n"; - -print "Kompilujê automat........................................"; - -`lexcomplex -l labels.lab -S labels.scl temp1`; - -print "OK\n"; - -print "Usuwam epsilon-przejscia................................."; - -`fsmrmepsilon temp1> temp2`; - -print "OK\n"; - -print "Determinizujê automat...................................."; - -`fsmdeterminize temp2 > temp1`; - -print "OK\n"; - -print "Minimalizujê automat....................................."; - -`fsmminimize temp1> temp2`; - -print "OK\n"; - -print "Konwertujê automat do formatu fsa........................"; - -`fsmprint -i labels.lab temp2> temp1`; - -`../fsm2aut temp1> temp2`; - -`../aut2fsa < temp2> cor.dic`; - -print "OK\n"; - -print "Czyszczê pliki pomocnicze................................"; - -`rm temp2`; -`rm temp1`; -`rm labels.*`; - -print "OK\n"; - Index: ld/nawszelkiwypadek/tools/dist/Makefile =================================================================== --- _old/nawszelkiwypadek/tools/dist/Makefile (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,47 +1,0 @@ -# main makefile - -BIN=bin -SRC=src -DIR=$(shell pwd) -############################## -# CONFIGURATION - -# UTT_BIN_DIR - directory for executables -# UTT_SHARE_DIR - directory for data and stuff -# UTT_DOC_DIR - directory for documentation - -# example (site installation) -# UTT_BIN_DIR=/usr/local/bin -# UTT_DOC_DIR=/usr/share/doc/utt - -UTT_BIN_DIR=~/utt/bin -UTT_SHARE_DIR=~/.utt -UTT_DOC_DIR=~/utt/doc -UTT_LIB_DIR=$(UTT_SHARE_DIR)/lib -############################## - -install: make_dirs install_dta install_lib #install_doc install_components - @echo "Installation completed successfully!" - -install_components: - cp -r bin/* $(UTT_BIN_DIR)/ - -install_dta: - if [ -d data ]; then cp -r data/* $(UTT_SHARE_DIR)/; fi - -install_doc: - cp -r doc/* $(UTT_DOC_DIR)/ - -install_lib: - cp -r lib/* $(UTT_LIB_DIR)/ - -make_dirs: - #if [ -d $(UTT_BIN_DIR) ]; then true; else mkdir -p $(UTT_BIN_DIR); fi - if [ -d $(UTT_SHARE_DIR) ]; then true; else mkdir -p $(UTT_SHARE_DIR); fi - if [ -d $(UTT_LIB_DIR) ]; then true; else mkdir -p $(UTT_LIB_DIR); fi - #if [ -d $(UTT_DOC_DIR) ]; then true; else mkdir -p $(UTT_DOC_DIR); fi - -uninstall: - rm -r $(UTT_SHARE_DIR) - #rm -r $(UTT_BIN_DIR) - #rm -r $(UTT_DOC_DIR) Index: ld/nawszelkiwypadek/tools/dist/README =================================================================== --- _old/nawszelkiwypadek/tools/dist/README (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,5 +1,0 @@ -Instalacja: - -1) Przeniesc katalog .utt do swojego katalogu domowego. -2) Dopisac do $PATH sciezke do katalogu bin. - Index: ld/nawszelkiwypadek/tools/fsm2aut =================================================================== --- _old/nawszelkiwypadek/tools/fsm2aut (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,44 +1,0 @@ -#!/usr/bin/perl - -my $currstate=-1; -my @states; -my @final; -my $tn=0; - -while(<>) -{ - if(/^\s*([0-9]+)\s+([0-9]+)\s+(.)(\s*)?$/) - { - push @{$states[$1]}, ($3, $2); - $#states=$2 if $#states<$2; - $tn++; - } - elsif(/^\s*([0-9]+)\s*$/) - { - $final[$1]=1; - $#states=$1 if $#states<$1; - } - else - { - die("Input error."); - } -} - -print scalar(@states)," ",$tn," char void\n"; - -my $i=0; -my $width=int(log(@states+1)/log(10)); -foreach $stateref (@states) -{ - $f = ($final[$i]?"+":"-"); - printf "%${width}d %s",$i++,$f; - while(@$stateref) - { - $c=shift @$stateref; - $s=shift @$stateref; - print " $c $s"; - } - print "\n"; -} - - Index: ld/nawszelkiwypadek/tools/gue_dic/README =================================================================== --- _old/nawszelkiwypadek/tools/gue_dic/README (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,28 +1,0 @@ -How to prepare gue dictionary? - -1. Preparing input file. - -Lines in input file should look like this: - -prefix*suffix~weight;description - -where: -prefix - is the prefix of a word -suffix - is the suffix of a word -weight - is the weight saying how importand information in this line is -description - is a description of the word - (in any format - description will be in output of gue) - - -2. Compiling a dictionary. - -Let's say we have input file named "dict.in". -Commands compiling dictionary: - -prep_user_dict.pl < dict.in > dict.temp -compile_user_dict.pl dict.temp - -Those should create file called "gue.bin" which is dictionary -for gue component. - -Good luck. Index: ld/nawszelkiwypadek/tools/gue_dic/attr.pm =================================================================== --- _old/nawszelkiwypadek/tools/gue_dic/attr.pm (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,110 +1,0 @@ -package attr; - -use locale; -use strict; - - -sub match(\@\@) -{ - my ($cat1,$avs1)= @{shift @_}; - my ($cat2,$avs2)= @{shift @_}; - - if($cat1 ne $cat2) - { - return 0; - } - else - { - ATTR:for my $attr (keys %$avs1) - { - if($avs2->{$attr}) - { - for my $val (keys %{$avs1->{$attr}}) - { - next ATTR if $avs2->{$attr}->{$val}; - } - return 0; - last ATTR; - } - } - } - - return 1; -} - -# funkcja parse -# arg: deskrypcja -# warto¶æ: referencja do tablicy [, ], -# gdzie jest referencja do hasza, zawierajacego pary -# atrybut=>hasz warto¶ci (pary warto¶æ=>1), czyli np. - -# [ -# 'ADJ', -# { -# 'KOLEDZY' => { -# '' => 1, -# '' => 1, -# '' => 1 -# }, -# 'C' => { -# 'p' => 1, -# 'a' => 1, -# 'i' => 1 -# }, -# 'N' => { -# 'p' => 1 -# } -# } -# ]; - -sub parse ($) -{ - my ($dstr)=@_; - my $avs={}; - my ($cat,$attrlist) = split '/', $dstr; - attr: - while( $attrlist =~ /([[:upper:]]+)((?:[[:lower:]+?!*-]|<[^>\n]+>)+)/g ) - { - my ($attrstr,$valstr)=($1,$2); - my %vals; - while($valstr =~ /[[:lower:]+?!*-]|<[^>\n]+>/g) - { - my $val = $&; - next attr if $val eq '*'; - $val =~ s/^<([[:lower:]])>$/$1/; - $vals{$val}=1; - } - - $avs->{$attrstr} = \%vals; # dlaczego to dziala? %vals jest lokalne - } - [$cat, $avs]; -} - -# funkcja unparse -# arg: jak warto¶æ parse -# warto¶æ: deskrypcja - napis - -sub unparse (\@) -{ - my ($cat,$avs)= @{shift @_}; - my $dstr=$cat; - my @attrs = keys %$avs; - if(@attrs) - { - $dstr .= '/'; - for my $attr ( sort @attrs ) - { - $dstr .= $attr . (join '', sort keys %{$avs->{$attr}}); - } - } - $dstr; -} - - -sub canonize ($) -{ - unparse @{parse @_[0]} ; -} - - -1; Index: ld/nawszelkiwypadek/tools/gue_dic/canon.pl =================================================================== --- _old/nawszelkiwypadek/tools/gue_dic/canon.pl (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,9 +1,0 @@ -#!/usr/bin/perl - -use locale; -use attr; - -while (<>) { - s/,(.*)$/','.attr::canonize($1)/e; - print; -} Index: ld/nawszelkiwypadek/tools/gue_dic/compile_user_dict.pl =================================================================== --- _old/nawszelkiwypadek/tools/gue_dic/compile_user_dict.pl (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,197 +1,0 @@ -#! /usr/bin/env perl - -use locale; -#use strict; - -# -################################################## -$linesPerFile = 20000; - -if (@ARGV < 1) { - print "usage: prep_user_dict.pl dictionary_file\n"; - exit; -} - -$file = shift; # @ARGV; - -# Przygotowanie etykiet - -`makeLabels.pl > labels.sym`; - -`lexmakelab labels`; - -# Analiza pliku s³ownika - - -print "Kanonizujê opisy........................................."; - -`canon.pl <$file >temp1`; - -print "OK\n"; - -print "Sortujê plik............................................."; - -`sort -t \\~ -k1,1 -k2,2nr temp2`; - -print "OK\n"; - -print "Minimalizujê plik s³ownika..............................."; - -#`rmDup.pl < temp2 > temp1`; -#`rmDup2.pl < temp1 > temp2`; - -`cp temp1 temp2`; - -`rm temp1`; - -print "OK\n"; - -print "Czyszczê pliki..........................................."; - -`sed -r "s/([[:punct:]])/[\\1]/g" < temp2 > temp1`; - -`cp temp1 temp2`; -`rm temp1`; - -print "OK\n"; - -#dzielimy plik na wiele czê¶ci, uruchamiamy lexcomplex dla ka¿dej -#czê¶ci osobno, nastêpnie ³±czymy to za pomoc± programu fsmunion - -print "Dzielê s³ownik na mniejsze czê¶ci........................"; - -open(IN, "./temp2"); - -$lineCount = 0; -$fileCount = 0; - -`mkdir LemTEMP`; - -open(FILE, ">LemTEMP/slo_0"); - -while () { - - if (++$lineCount >= $linesPerFile) { - $fileCount++; - $lineCount = 0; - - close(FILE); -# print "Tworzê nowy plik tymczasowy: slo_".$fileCount."\n"; - open(FILE, ">LemTEMP/slo_".$fileCount); - } - - print(FILE $_); -} - -print "OK\n"; - -print "Tworzê automaty po¶rednie"; - -#32 kropki, fileCount plikow -$filesPerDot = $fileCount/32; -$files=$filesPerDot; -$dots=0; - -for ($i=0; $i<=$fileCount; $i++) { - - if ($files >= $filesPerDot) { - $files = 0; - print "."; - $dots++; - } - $files++; - - $command = "lexcomplex -l labels.lab -S labels.scl < LemTEMP/slo_".$i." > LemTEMP/slownik_".$i.".fsm"; - - `$command`; - -} -if ($dots < 32) { - for ($i=0; $i<32 - $dots; $i++) { - print "."; - } -} - -print "OK\n"; - -`rm LemTEMP/slo_*`; - -print "Tworzê automat koñcowy"; - -#35 kropek... -$filesPerDot = $fileCount/35; -$files=$filesPerDot; -$dots=0; - -`cp LemTEMP/slownik_0.fsm slownik1.fsm`; - -for ($i=1; $i<=$filecount; $i++) { - - if ($files >= $filesPerDot) { - $files = 0; - print "."; - $dots++; - } - $files++; - - $command = "fsmunion LemTEMP/slownik_".$i." slownik1.fsm > slownik2.fsm"; - - `$command`; - - `mv slownik2.fsm slownik1.fsm`; -} - -if ($dots < 35) { - for ($i=0; $i<35 - $dots; $i++) { - print "."; - } -} - -`fsmunion LemTEMP/* > slownik1.fsm`; - -print "OK\n"; - -print "Usuwam epsilon-przejscia................................."; - -`fsmrmepsilon slownik1.fsm > slownik2.fsm`; - -`rm slownik1.fsm`; - -print "OK\n"; - -print "Determinizujê automat...................................."; - -`fsmdeterminize slownik2.fsm > slownik1.fsm`; - -`rm slownik2.fsm`; - -print "OK\n"; - -print "Minimalizujê automat....................................."; - -`fsmminimize slownik1.fsm > slownik.fsm`; - -`rm slownik1.fsm`; - -print "OK\n"; - -print "Konwertujê automat do formatu fsa........................"; - -`fsmprint -i labels.lab slownik.fsm > slownik.txt`; - -`../fsm2aut slownik.txt > slownik.aut`; - -`../aut2fsa < slownik.aut > gue.bin`; - -print "OK\n"; - -print "Czyszczê pliki pomocnicze................................"; - -`rm LemTEMP/*`; -`rmdir LemTEMP`; -`rm temp2`; -`rm slownik.fsm`; -`rm slownik.txt`; -`rm slownik.aut`; - -print "OK\n"; Index: ld/nawszelkiwypadek/tools/gue_dic/count_prefs.pl =================================================================== --- _old/nawszelkiwypadek/tools/gue_dic/count_prefs.pl (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,86 +1,0 @@ -#! /usr/bin/perl - -use locale; -use strict; - -my @prefs; - -sub addPref { - - my $pref = shift; - my $desc = shift; - my $i; - for ($i=0; $i< @prefs; ++$i) { - my @tab = @{$prefs[$i]}; - if (${@{$prefs[$i]}}[0] =~ /^$pref/) { - ${@{$prefs[$i]}}[1]{$desc}++; - return; - } - } - my @new; - my %hash; - - $hash{$desc}++; - push(@new, $pref); - push(@new, \%hash); - - push(@prefs, \@new); -} - -sub printPrefs { - - my $i; - for $i (@prefs) { - my @tab = @$i; -# print $tab[0]."\t"; - my $pref = $tab[0]; - my %hash = %{$tab[1]}; - my @keys = keys(%hash); -# print(@keys."\n"); - my $sum = 0; - my $key; - for $key (@keys) { - $sum += $hash{$key}; - } - for $key (@keys) { - print $pref."\t"; - print $key."\t"; - print $hash{$key}."\t"; - print $sum."\n"; - } - } -} - -if (@ARGV < 2) { - print "USAGE: count_prefs.pl MIN_PREF_LEN MAX_PREF_LEN\n"; - exit; -} - -my $MIN = shift; -my $MAX = shift; -my $PART = shift; - -if ($MIN > $MAX) { - print "MIN_PREF_LEN > MAX_PREF_LEN! ($MIN > $MAX)\n"; - exit; -} -my $begin = ""; -while (<>) { - my $len = $MIN; - $_ =~ /(\w+);(.*)$/; - my $pref = $1; - my $desc = $2; - if ($begin eq "") { - $begin = substr($pref, 0, $MIN); - } - if ($pref !~ /^$begin.*/) { - printPrefs(); - undef(@prefs); - $begin = ""; - } - while ($len <= $MAX) { - addPref(substr($pref, 0, $len++), $desc); - } -} - -printPrefs(); Index: ld/nawszelkiwypadek/tools/gue_dic/cut_prefs.pl =================================================================== --- _old/nawszelkiwypadek/tools/gue_dic/cut_prefs.pl (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,60 +1,0 @@ -#! /usr/bin/perl - -use locale; -use strict; - -if (@ARGV < 3) { - print "USAGE: cut_prefs.pl CUT_OFF TOTAL_PER ABS_CUT\n\n"; - print "Obcina wpisy ma³o wa¿ne, opis nie jest uwzglêdniany\n"; - print "je¿eli zachodzi jeden z warunków:\n"; - print " - jezeli liczba wystapien danego opisu jest mniejsza\n"; - print " od \$CUT_OFF*(liczba wystapien poprzedniego opisu)\n"; - print " - jezeli liczba wystapien danego opisu jest mniejsza\n"; - print " od \$TOTAL_PER*(suma wszystkich wystapien)\n"; - print " - jezeli liczba wystapien danego opisu jest mniejsza\n"; - print " od \$ABS_CUT\n"; - exit; -} - -# jezeli liczba wystapien danego opisu jest mniejsza -# od $CUT_OFF*(liczba wystapien poprzedniego opisu) - opis nie jest uwzgledniany -my $CUT_OFF = shift; - -# jezeli liczba wystapien danego opisu jest mniejsza -# od $TOTAL_PER*(suma wszystkich wystapien) - opis nie jest uwzgledniany -my $TOTAL_PER = shift; - -# jezeli liczba wystapien danego opisu jest mniejsza -# od $ABS_CUT - opis nie jest uwzgledniany -my $ABS_CUT = shift; - -my $pref = ""; -my $oldPref = " "; -my $countTotal = -1; -my $count = -1; - -while (<>) { - - if (($count == -1) && ($_ =~ /^$oldPref\t.*/)) { - next; - } - - if ($pref =~ //) { - $_ =~ /^(\w+)\t.+\t(\d+)\t(\d+)/; - $pref = $1; - $count = $2; - $countTotal = $3; -# print "\$pref=$pref\t\$count=$count\t\$countTotal=$countTotal\n"; - } - $_ =~ /\w+\t.+\t(\d+)\t\d+/; - my $c = $1; -# print "\$c=$c\t\$CUT_OFF*\$count=$CUT_OFF*$count\t\$TOTAL_PER*\$countTotal=".$TOTAL_PER*$countTotal."\n"; - if (($CUT_OFF*$count < $c) && ($TOTAL_PER*$countTotal < $c) && ($ABS_CUT < $c)) { - $count = $c; - print $_; - } else { - $count = -1; - $oldPref = $pref; - $pref = ""; - } -} Index: ld/nawszelkiwypadek/tools/gue_dic/labels.lab =================================================================== --- _old/nawszelkiwypadek/tools/gue_dic/labels.lab (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,95 +1,0 @@ - 0 -a 1 -± 2 -b 3 -c 4 -æ 5 -d 6 -e 7 -ê 8 -f 9 -g 10 -h 11 -i 12 -j 13 -k 14 -l 15 -³ 16 -m 17 -n 18 -ñ 19 -o 20 -ó 21 -p 22 -q 23 -r 24 -s 25 -¶ 26 -t 27 -u 28 -v 29 -w 30 -x 31 -y 32 -z 33 -Œ 34 -¿ 35 -é 36 -ö 37 -ü 38 -ä 39 -A 40 -¡ 41 -B 42 -C 43 -Æ 44 -D 45 -E 46 -Ê 47 -F 48 -G 49 -H 50 -I 51 -J 52 -K 53 -L 54 -£ 55 -M 56 -N 57 -Ñ 58 -O 59 -Ó 60 -P 61 -Q 62 -R 63 -S 64 -Š 65 -T 66 -U 67 -V 68 -W 69 -X 70 -Y 71 -Z 72 -¬ 73 -¯ 74 -0 75 -1 76 -2 77 -3 78 -4 79 -5 80 -6 81 -7 82 -8 83 -9 84 -, 85 -. 86 -@ 87 -/ 88 -' 89 -_ 90 -~ 91 -; 92 -- 93 -\ 94 Index: ld/nawszelkiwypadek/tools/gue_dic/labels.scl =================================================================== --- _old/nawszelkiwypadek/tools/gue_dic/labels.scl (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,356 +1,0 @@ -lcase 1 -lcase 2 -lcase 3 -lcase 4 -lcase 5 -lcase 6 -lcase 7 -lcase 8 -lcase 9 -lcase 10 -lcase 11 -lcase 12 -lcase 13 -lcase 14 -lcase 15 -lcase 16 -lcase 17 -lcase 18 -lcase 19 -lcase 20 -lcase 21 -lcase 22 -lcase 23 -lcase 24 -lcase 25 -lcase 26 -lcase 27 -lcase 28 -lcase 29 -lcase 30 -lcase 31 -lcase 32 -lcase 33 -lcase 34 -lcase 35 -lcase 36 -lcase 37 -lcase 38 -lcase 39 -sem 91 -sem 92 -sem 93 -sem 94 - 1 - 2 - 3 - 4 - 5 - 6 - 7 - 8 - 9 - 10 - 11 - 12 - 13 - 14 - 15 - 16 - 17 - 18 - 19 - 20 - 21 - 22 - 23 - 24 - 25 - 26 - 27 - 28 - 29 - 30 - 31 - 32 - 33 - 34 - 35 - 36 - 37 - 38 - 39 - 40 - 41 - 42 - 43 - 44 - 45 - 46 - 47 - 48 - 49 - 50 - 51 - 52 - 53 - 54 - 55 - 56 - 57 - 58 - 59 - 60 - 61 - 62 - 63 - 64 - 65 - 66 - 67 - 68 - 69 - 70 - 71 - 72 - 73 - 74 - 75 - 76 - 77 - 78 - 79 - 80 - 81 - 82 - 83 - 84 - 85 - 86 - 87 - 88 - 89 - 90 - 91 - 92 - 93 - 94 -ucase 40 -ucase 41 -ucase 42 -ucase 43 -ucase 44 -ucase 45 -ucase 46 -ucase 47 -ucase 48 -ucase 49 -ucase 50 -ucase 51 -ucase 52 -ucase 53 -ucase 54 -ucase 55 -ucase 56 -ucase 57 -ucase 58 -ucase 59 -ucase 60 -ucase 61 -ucase 62 -ucase 63 -ucase 64 -ucase 65 -ucase 66 -ucase 67 -ucase 68 -ucase 69 -ucase 70 -ucase 71 -ucase 72 -ucase 73 -ucase 74 -letter 1 -letter 2 -letter 3 -letter 4 -letter 5 -letter 6 -letter 7 -letter 8 -letter 9 -letter 10 -letter 11 -letter 12 -letter 13 -letter 14 -letter 15 -letter 16 -letter 17 -letter 18 -letter 19 -letter 20 -letter 21 -letter 22 -letter 23 -letter 24 -letter 25 -letter 26 -letter 27 -letter 28 -letter 29 -letter 30 -letter 31 -letter 32 -letter 33 -letter 34 -letter 35 -letter 36 -letter 37 -letter 38 -letter 39 -letter 40 -letter 41 -letter 42 -letter 43 -letter 44 -letter 45 -letter 46 -letter 47 -letter 48 -letter 49 -letter 50 -letter 51 -letter 52 -letter 53 -letter 54 -letter 55 -letter 56 -letter 57 -letter 58 -letter 59 -letter 60 -letter 61 -letter 62 -letter 63 -letter 64 -letter 65 -letter 66 -letter 67 -letter 68 -letter 69 -letter 70 -letter 71 -letter 72 -letter 73 -letter 74 -all 1 -all 2 -all 3 -all 4 -all 5 -all 6 -all 7 -all 8 -all 9 -all 10 -all 11 -all 12 -all 13 -all 14 -all 15 -all 16 -all 17 -all 18 -all 19 -all 20 -all 21 -all 22 -all 23 -all 24 -all 25 -all 26 -all 27 -all 28 -all 29 -all 30 -all 31 -all 32 -all 33 -all 34 -all 35 -all 36 -all 37 -all 38 -all 39 -all 40 -all 41 -all 42 -all 43 -all 44 -all 45 -all 46 -all 47 -all 48 -all 49 -all 50 -all 51 -all 52 -all 53 -all 54 -all 55 -all 56 -all 57 -all 58 -all 59 -all 60 -all 61 -all 62 -all 63 -all 64 -all 65 -all 66 -all 67 -all 68 -all 69 -all 70 -all 71 -all 72 -all 73 -all 74 -all 75 -all 76 -all 77 -all 78 -all 79 -all 80 -all 81 -all 82 -all 83 -all 84 -all 85 -all 86 -all 87 -all 88 -all 89 -all 90 -all 91 -all 92 -all 93 -all 94 -digit 75 -digit 76 -digit 77 -digit 78 -digit 79 -digit 80 -digit 81 -digit 82 -digit 83 -digit 84 -signs 85 -signs 86 -signs 87 -signs 88 -signs 89 -signs 90 Index: ld/nawszelkiwypadek/tools/gue_dic/labels.sym =================================================================== --- _old/nawszelkiwypadek/tools/gue_dic/labels.sym (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,7 +1,0 @@ -lcase a ± b c æ d e ê f g h i j k l ³ m n ñ o ó p q r s ¶ t u v w x y z Œ ¿ é ö ü ä -ucase A ¡ B C Æ D E Ê F G H I J K L £ M N Ñ O Ó P Q R S Š T U V W X Y Z ¬ ¯ -letter lcase ucase -digit 0 1 2 3 4 5 6 7 8 9 -signs , . @ / ' _ -sem ~ ; - \ -all letter digit signs sem Index: ld/nawszelkiwypadek/tools/gue_dic/makeLabels.pl =================================================================== --- _old/nawszelkiwypadek/tools/gue_dic/makeLabels.pl (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,11 +1,0 @@ -#!/usr/bin/perl - -use locale; - -print "lcase a ± b c æ d e ê f g h i j k l ³ m n ñ o ó p q r s ¶ t u v w x y z Œ ¿ é ö ü ä\n"; -print "ucase A ¡ B C Æ D E Ê F G H I J K L £ M N Ñ O Ó P Q R S Š T U V W X Y Z ¬ ¯\n"; -print "letter lcase ucase\n"; -print "digit 0 1 2 3 4 5 6 7 8 9\n"; -print "signs , . @ \/ \' _\n"; -print "sem ~ ; - \\ \n"; -print "all letter digit signs sem\n"; Index: ld/nawszelkiwypadek/tools/gue_dic/prep.pl =================================================================== --- _old/nawszelkiwypadek/tools/gue_dic/prep.pl (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,213 +1,0 @@ -#! /usr/bin/perl - -use locale; - -$linesPerFile = 20000; - -if (@ARGV < 1) { - print "usage: prep.pl dictionary_file\n"; - exit; -} - -$file = shift; # @ARGV; -$kind = shift; - -if ($kind eq "") { - $kind="suf"; -} - -# Przygotowanie etykiet - -`makeLabels.pl > labels.sym`; - -`lexmakelab labels`; - -# Analiza pliku s³ownika - - -print "Kanonizujê opisy........................................."; - -`canon.pl <$file >temp2`; - -print "OK\n"; - -print "Analizuje prefiksy......................................."; - -`count_prefs.pl 2 4 < temp2 > prefs`; -`sort -k1,1 -k3,3nr prefs > prefsS`; -`cut_prefs.pl 0.5 0.01 100 prefsS > prefs`; -`rm prefsS`; - -print "OK\n"; - -print "Analizujê plik s³ownika"; - -if ($kind eq "pre") { - print "(pre)............................."; - `stat_pre.pl temp2 > temp1`; -} else { - print "(suf)............................."; - `stat.pl prefs < temp2 > temp1`; -} - -print "OK\n"; - -# zmniejszamy plik... - -print "Sortujê plik............................................."; - -`sort -t \\~ -k1,1 -k2,2nr temp2`; - -print "OK\n"; - -print "Minimalizujê plik s³ownika..............................."; - -`rmDup.pl < temp2 > temp1`; -#`rmDup2.pl < temp1 > temp2`; - -`cp temp1 temp2`; - -`rm temp1`; - -print "OK\n"; - -#dzielimy plik na wiele czê¶ci, uruchamiamy lexcomplex dla ka¿dej -#czê¶ci osobno, nastêpnie ³±czymy to za pomoc± programu fsmunion - -print "Dzielê s³ownik na mniejsze czê¶ci........................"; - -open(IN, "./temp2"); - -$lineCount = 0; -$fileCount = 0; - -`mkdir LemTEMP`; - -open(FILE, ">LemTEMP/slo_0"); - -while () { - - if (++$lineCount >= $linesPerFile) { - $fileCount++; - $lineCount = 0; - - close(FILE); -# print "Tworzê nowy plik tymczasowy: slo_".$fileCount."\n"; - open(FILE, ">LemTEMP/slo_".$fileCount); - } - - print(FILE $_); -} - -print "OK\n"; - -print "Tworzê automaty po¶rednie"; - -#32 kropki, fileCount plikow -$filesPerDot = $fileCount/32; -$files=$filesPerDot; -$dots=0; - -for ($i=0; $i<=$fileCount; $i++) { - - if ($files >= $filesPerDot) { - $files = 0; - print "."; - $dots++; - } - $files++; - - $command = "lexcomplex -l labels.lab -S labels.scl < LemTEMP/slo_".$i." > LemTEMP/slownik_".$i.".fsm"; - - `$command`; - -} -if ($dots < 32) { - for ($i=0; $i<32 - $dots; $i++) { - print "."; - } -} - -print "OK\n"; - -`rm LemTEMP/slo_*`; - -print "Tworzê automat koñcowy"; - -#35 kropek... -$filesPerDot = $fileCount/35; -$files=$filesPerDot; -$dots=0; - -`cp LemTEMP/slownik_0.fsm slownik1.fsm`; - -for ($i=1; $i<=$filecount; $i++) { - - if ($files >= $filesPerDot) { - $files = 0; - print "."; - $dots++; - } - $files++; - - $command = "fsmunion LemTEMP/slownik_".$i." slownik1.fsm > slownik2.fsm"; - - `$command`; - - `mv slownik2.fsm slownik1.fsm`; -} - -if ($dots < 35) { - for ($i=0; $i<35 - $dots; $i++) { - print "."; - } -} - -`fsmunion LemTEMP/* > slownik1.fsm`; - -print "OK\n"; - -print "Usuwam epsilon-przejscia................................."; - -`fsmrmepsilon slownik1.fsm > slownik2.fsm`; - -`rm slownik1.fsm`; - -print "OK\n"; - -print "Determinizujê automat...................................."; - -`fsmdeterminize slownik2.fsm > slownik1.fsm`; - -`rm slownik2.fsm`; - -print "OK\n"; - -print "Minimalizujê automat....................................."; - -`fsmminimize slownik1.fsm > slownik.fsm`; - -`rm slownik1.fsm`; - -print "OK\n"; - -print "Konwertujê automat do formatu fsa........................"; - -`fsmprint -i labels.lab slownik.fsm > slownik.txt`; - -`../fsm2aut slownik.txt > slownik.aut`; - -`../aut2fsa < slownik.aut > gue.bin`; - -print "OK\n"; - -print "Czyszczê pliki pomocnicze................................"; - -`rm LemTEMP/*`; -`rmdir LemTEMP`; -`rm temp2`; -`rm slownik.fsm`; -`rm slownik.txt`; -`rm slownik.aut`; - -print "OK\n"; Index: ld/nawszelkiwypadek/tools/gue_dic/prep_user_dict.pl =================================================================== --- _old/nawszelkiwypadek/tools/gue_dic/prep_user_dict.pl (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,31 +1,0 @@ -#! /usr/bin/env perl - -use locale; -use strict; - -################################################## -# Skrypt transformuje s³ownik u¿ytkownika # -# do s³ownika rozumianego przez gue. # -# Format wej¶ciowy: # -# pref*kon~waga;opis # -# Format wyj¶ciowy: # -# nok_pref~waga;opis # -# # -# Prefiks mo¿e byæ pusty, koñcówka te¿ # -################################################## - -while (<>) { - /^(\w*)\*(\w*)(~.*)$/; - my $pref = $1; - my $kon = $2; - my $desc = $3; - - print reverse(split("",$kon)); - - if ($pref != "") { - print "_$pref"; - } - print "$desc\n"; - - -} Index: ld/nawszelkiwypadek/tools/gue_dic/rmDup.pl =================================================================== --- _old/nawszelkiwypadek/tools/gue_dic/rmDup.pl (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,55 +1,0 @@ -#!/usr/bin/perl - -# Usuwa zbêdne powtórzenia scie¿ek - -use locale; - -#if (@ARGV < 1) { -# print "USAGE: remDup.pl num\n\tGdzie \"num\" jest ilo¶ci± powtórzeñ, które zostawiamy\n"; -# exit(0); -#} - - - -#ilo¶æ powtórzeñ, które zostawiamy -$max = 10; - -# przyjmujemy, ze na wej¶ciu znajduje siê plik posortowany, -# po koñcówkach oraz po prawdopodobieñstwie - -$line = <>; - -while (($line !~ m/^$/) || ($line =~ m/^\n$/)) { - - $count = 0; - - while ($line =~ m/^\n$/) { - $line = <>; - } - - $line =~ /^([^~]+)~.*/; - $theEnd = $1; - $end = $1; - - while (($end =~ m/$theEnd/) && ($count++ < $max)) { - print $line; - $line = <>; - $line =~ /^([^~]+)~.*/; - $end = $1; - } - - # tutaj mamy dwie mo¿liwo¶ci: - # 1. wypisali¶my ju¿ max lini - musimy wywaliæ kolejne linie, które - # zawieraj± koñcówkê theEnd, - # 2. pasuj±cych lini by³o mniej ni¿ max, wtedy nic nie musimy robiæ - # - w zmiennej line znajduje siê kolejna linia... - - if ($count == $max + 1) { - while ($oldEnd =~ m/$theEnd/) { - $line = <>; - $line =~ /^([^~]+)~.*/; - $oldEnd = $1; - } - } - -} Index: ld/nawszelkiwypadek/tools/gue_dic/stat.pl =================================================================== --- _old/nawszelkiwypadek/tools/gue_dic/stat.pl (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,165 +1,0 @@ -#! /usr/bin/perl - -use locale; - -###################################################### -# na wej¶ciu znajduje siê plik zawieraj±cy linie # -# postaci: # -# slowo;opis # -# # -# na wyj¶ciu ma siê znaleŒæ plik zawieraj±cy linie: # -# koñcówka(rev);prawdopodobieñstwo;opis # -# gdzie: # -# - koñcówka(rev) jest koñcówk± wyrazu zapisan± # -# w odwrotnej kolejno¶ci, dla ka¿dego wyrazu # -# w s³owniku wypisujemy koñcówki o d³ugo¶ciach # -# od 1 do d³ugo¶ci wyrazu, # -# - prawdopodobieñstwo jest prawdopodobieñstwem # -# wyst±pienia danego opisu dla danej koñcówki # -# (obliczonym na podstwie statystycznej analizy # -# s³ownika), np: 250 oznacza, ze opis popjawia sie # -# 1 raz na 4 wyst±pienia koñcówki. # -# Zapisana zostaje odwrotno¶æ prawdopodobieñstwa # -# aby scie¿ka najbardziej prawdopodobna mia³a # -# najmniejszy koszt. # -###################################################### - -###### -#STALE -# -# Jak bardzo prawdopodobna musi byæ dana ¶cie¿ka, aby -# braæ j± pod uwagê? (w promilach) -$MIN_PROB = 0; -# -# Maksymalna ilo¶æ powtórzeñ danej koñcówki (brane od -# najbardziej prawdopodbnej w dó³ -$MAX_PATH = 10; -# -# Znak odzielajacy koncowke od prefiksu -$PREF_SIGN = '_'; -###### -# Zmienne globalne -# -# Tablica okreslajaca, ktore prefiksy nalezy uwzlednic -# w wyjsciowym pliku. -# Klucz - ciag znakow prefiks$PREF_SIGNopis. -# Wartosc: 1 - jezeli nalezy uwzglednic, 0 w przeciwnym przypadku -my %prefs; -# -# maksymalna dlugosc analizowanego prefiksu -my $MAX_PREF = 0; -###### - -########################################################### -# FUNKCJE - -# wczytuje prefiksy do tablicy hashowej -# parametry: -# - nazwa pliku, z ktorego nalezy pobrac prefiksy -# Plik w formacie: -# prefiks\topis...\n -sub load_prefs { - - my $file = shift; - open(IN, $file); - - while () { - $_ =~ /^(\w+)\t([^\t]+)\t/; - my $key = "$1$PREF_SIGN$2"; - my $len = length($1); - if ($len > $MAX_PREF) { - $MAX_PREF = $len; - } - $prefs{$key} = 1; - } -} - -########################################################### - -# Jezeli podano parametr to jest to nazwa pliku z prefiksami - -if (@ARGV > 0) { -# print "Laduje prefiksy ($ARGV[0])\n"; - load_prefs(shift); -# print "Zaladowane:\n"; -# for $key (keys(%prefs)) { -# print "$key\t$prefs{$key}\n"; -# } -# print "++++++++++++++++++++++++++++++++++++++++++++++++++\n"; -} - -@input = <>; - -#$max = 0; - -#for $m (@input) { -# $m =~ /(\w+);.*$/; -# if (length($1) > $max) { -# $max = length($1); -# } -#} - -$n = 2; #$max; - -$go = 1; - -while ($go) { - - my %koncowki; - my $sumy; - - $go = 0; - for $m (@input) { - if ($m =~ /(\w{$n});(.*)$/) { - $go = 1; - my $ending = $1; - my $desc = $2; - for (my $i=$MAX_PREF; $i>0; $i--) { - $m =~ /^(\w{$i}).*/; - my $key = "$1$PREF_SIGN$desc"; - if ($prefs{$key} == 1) { - $ending .= "$PREF_SIGN$1"; - last; - } - } - $koncowki{$ending.";".$desc}++; - $sumy{$ending}++; - } - } - - print "\n"; - - for $koncowka (keys %koncowki) { - $koncowka =~ /^(.*);(.*)$/; - my $ending = $1; - my $opis = $2; - $p = $koncowki{$koncowka} / $sumy{$ending}; - $p *= 1000; #wartosc w promilach - - if ($p <= $MIN_PROB) { - next; - } - - #if ($p == 1000) { - # $p--; - #} - - #$p = 1000 - $p; #odwrotnosc - my $old = $2; - $ending =~ /^(\w+)$PREF_SIGN(\w+)/; - - my $rev = reverse($1); - - if ($2 !~ /^$old$/) { - $rev .= "$PREF_SIGN$2"; - } - - # opakowujemy znak '-' znakami [] ;) dla lextools - $opis =~ s/-/\[-\]/; - - printf "%s~%.0f;%s\n", $rev, $p, $opis; - } - - $n++; - -} Index: ld/nawszelkiwypadek/tools/gue_dic/stat_pre.pl =================================================================== --- _old/nawszelkiwypadek/tools/gue_dic/stat_pre.pl (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,95 +1,0 @@ -#! /usr/bin/perl - -use locale; - -###################################################### -# na wej¶ciu znajduje siê plik zawieraj±cy linie # -# postaci: # -# slowo;opis # -# # -# na wyj¶ciu ma siê znaleŒæ plik zawieraj±cy linie: # -# koñcówka(rev);prawdopodobieñstwo;opis # -# gdzie: # -# - koñcówka(rev) jest koñcówk± wyrazu zapisan± # -# w odwrotnej kolejno¶ci, dla ka¿dego wyrazu # -# w s³owniku wypisujemy koñcówki o d³ugo¶ciach # -# od 1 do d³ugo¶ci wyrazu, # -# - prawdopodobieñstwo jest prawdopodobieñstwem # -# wyst±pienia danego opisu dla danej koñcówki # -# (obliczonym na podstwie statystycznej analizy # -# s³ownika), np: 250 oznacza, ze opis popjawia sie # -# 1 raz na 4 wyst±pienia koñcówki. # -# Zapisana zostaje odwrotno¶æ prawdopodobieñstwa # -# aby scie¿ka najbardziej prawdopodobna mia³a # -# najmniejszy koszt. # -###################################################### - -###### -#STALE -# -# Jak bardzo prawdopodobna musi byæ dana ¶cie¿ka, aby -# braæ j± pod uwagê? (w promilach) -$MIN_PROB = 0; -# -# Maksymalna ilo¶æ powtórzeñ danej koñcówki (brane od -# najbardziej prawdopodbnej w dó³ -$MAX_PATH = 10; -# -###### - -@input = <>; - -#$max = 0; - -#for $m (@input) { -# $m =~ /(\w+);.*$/; -# if (length($1) > $max) { -# $max = length($1); -# } -#} - -$n = 1; #$max; - -$go = 1; - -while ($n<7) { - - my %prefiksy; - my $sumy; - - $go = 0; - for $m (@input) { - if ($m =~ /^(\w{$n})\w*;(.*)$/) { - $go = 1; - $prefiksy{$1.";".$2}++; - $sumy{$1}++; - } - } - - print "\n"; - - for $prefiks (keys %prefiksy) { - $prefiks =~ /^(.*);(.*)$/; - $p = $prefiksy{$prefiks} / $sumy{$1}; - $p *= 1000; #wartosc w promilach - - if ($p <= $MIN_PROB) { - next; - } - - #if ($p == 1000) { - # $p--; - #} - - $p = 1000 - $p; #odwrotnosc -# $rev = reverse($1); - # opakowujemy znak '-' znakami [] ;) - $opis = $2; - $opis =~ s/-/\[-\]/; - - printf "%s~%.0f;%s\n", $1, $p, $opis; - } - - $n++; - -} Index: ld/nawszelkiwypadek/tools/lem_dic/makeLabels.pl =================================================================== --- _old/nawszelkiwypadek/tools/lem_dic/makeLabels.pl (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,11 +1,0 @@ -#!/usr/bin/perl - -use locale; - -print "lcase a ± b c æ d e ê f g h i j k l ³ m n ñ o ó p q r s ¶ t u v w x y z Œ ¿ é ö ü ä\n"; -print "ucase A ¡ B C Æ D E Ê F G H I J K L £ M N Ñ O Ó P Q R S Š T U V W X Y Z ¬ ¯\n"; -print "letter lcase ucase\n"; -print "digit 0 1 2 3 4 5 6 7 8 9\n"; -print "signs , . @ \/ \'\n"; -print "sem ~ ; _ - + ? \\ \n"; -print "all letter digit signs sem\n"; Index: ld/nawszelkiwypadek/tools/lem_dic/prep.pl =================================================================== --- _old/nawszelkiwypadek/tools/lem_dic/prep.pl (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,75 +1,0 @@ -#! /usr/bin/perl - -use locale; -use strict; - -my $file = shift; -my $filename; - -if ($file eq "") { - print "Podaj nazwê pliku.\n"; - exit(1); -} - -if ($file =~ /(.*)\.dic/) -{ - $filename = $1; -} -else -{ - print "The input file must have .dic extension."; - exit(1); -} - -`makeLabels.pl > labels.sym`; - -`lexmakelab labels`; - -print "Kanonizujê opisy........................................."; - -#`canon.pl <$file >temp2`; - -print "Kompilujê automat........................................"; - -`lexcomplex -l labels.lab -S labels.scl <$file > temp1`; - -print "OK\n"; - -print "Usuwam epsilon-przejscia................................."; - -`fsmrmepsilon temp1> temp2`; - -print "OK\n"; - -print "Determinizujê automat...................................."; - -`fsmdeterminize temp2 > temp1`; - -print "OK\n"; - -print "Minimalizujê automat....................................."; - -`fsmminimize temp1> temp2`; - -print "OK\n"; - -print "Konwertujê automat do formatu fsa........................"; - -`fsmprint -i labels.lab temp2> temp1`; - -`cp temp1 pofsmprint`; - -`../fsm2aut temp1> temp2`; - -`./aut2fsa.nowy < temp2> $filename.bin`; - -print "OK\n"; - -print "Czyszczê pliki pomocnicze................................"; - -`rm temp2`; -`rm temp1`; -#`rm labels.*`; - -print "OK\n"; - Index: ld/www/authors.php =================================================================== --- _old/www/authors.php (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,10 +1,0 @@ -UAM Text Tools - '.AUTHORS_TITLE."\n"; -$context = AUTHORS_CONTENT; - -getMainPage($title, $context); - -?> Index: ld/www/cmn_frame.php =================================================================== --- _old/www/cmn_frame.php (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,57 +1,0 @@ -\n"; - echo "\n"; - echo "\n"; - echo "\n"; - if(isset($header)) { - # jesli pominieto znacznik tytulu - dodajemy sami - if (stristr($header, '') === false) { - echo '<title>'.DEFAULT_PAGE_TITLE."\n"; - } - echo $header; - } - else { - echo ''.DEFAULT_PAGE_TITLE."\n"; - } - echo "\n"; - echo "\n"; - echo "\n"; - echo "\n"; - echo " \n"; - echo "\n"; - echo "\n"; - echo " \n"; - echo " \n"; - echo " \n"; - echo " \n"; - echo "
".PAGE_HEADER."
\n"; - echo " \n"; - $menu = array("index.php" => MENU_MAIN_PAGE, - "help.php" => MENU_HELP, - "licence.php" => MENU_LICENSE, - "authors.php" => MENU_AUTHORS, - "down.php" => MENU_DOWNLOADS); - - foreach($menu as $page=>$descr) { - echo " \n"; - echo " \n"; - echo " \n"; - } - echo "
\n"; - echo $descr."\n"; - echo "
\n"; - echo " 		\n"; - echo $content; - echo "  
\n"; - echo "\n"; -} - -?> Index: ld/www/css/utt.css =================================================================== --- _old/www/css/utt.css (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,105 +1,0 @@ -BODY { - FONT-FAMILY: Verdana, Arial, Helvetica; - FONT-SIZE: 13px; - background-color: #CCFF99; -/* -#FFF8DC pomaranczowy -#F5F5DC be¿owy -#F0F8FF jasnoniebieski - - font-style: italic; - font-weight: bold; - text-decoration: underline; -*/ -} - -.page_table { - width: 100%; - border: 0px solid black; - margin-top: 30px; -} - -.page_title { - text-align: center; - font-size: 30px; - font-weight: bold; - padding-bottom: 20px; -} - -.page_menu { - width: 20%; - vertical-align: top; -} - -.main_menu { - border: 0 solid black; - width: 80%; -} - -.main_menu_cell { - border-width:2px; - border-style: outset; -/* text-align: center; */ -/* margin-left: 200px; */ - padding-left: 10px; - font-weight: bold; - color: #006600; /*#336600;*/ - text-decoration: none; - font-family: monospace; -} - -.page_content { - vertical-align: top; - padding: 10px; - background-color: #FFFFFF; - height: 400px; -} - -.page_left_margin { - width: 10%; -} - -.distribution { -/* padding: 30px; */ -/* margin: 30px; */ - border-spacing: 10px; -} - -.distribution .app, .distribution .dict { - border-spacing: 10px; -} - -.distribution .product { -/* background-color: #CCCC66;*/ - font-size: larger; - text-transform: capitalize; - font-weight: bold; -} - -.distribution .product td { - border-bottom: solid 2px #669933; -} - -.distribution .dist_type { -/* background-color: orange; */ - font-family: Courier New; /* monospace;*/ - text-transform: uppercase; - font-size: smaller; - border-bottom: solid 1px #669933; - width: 30%; -} - -.distribution .dist_item { - font-size: smaller; - vertical-align: top; -} - -.distribution .dist_item img { - width: 16px; - vertical-align: bottom; -} - -.distribution .dist_item a { - text-decoration: none; - color: blue; -} Index: ld/www/dbconst.php =================================================================== --- _old/www/dbconst.php (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,9 +1,0 @@ - Index: ld/www/down.php =================================================================== --- _old/www/down.php (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,92 +1,0 @@ - array(), - 'utt-dict' => array() - ); - -$dn = "files/"; -if ($dh = opendir($dn)) { - while (($file = readdir($dh)) !== false) { - if(true == is_file($dn.$file)) { - if(preg_match('/^utt\-dict\-.+?\.(.+)$/', $file, $dopasowania)) { - $arch_type = $dopasowania[1]; - if(! array_key_exists($arch_type, $archiwa['utt-dict'])) { - $archiwa['utt-dict'][$arch_type] = array(); - } - $archiwa['utt-dict'][$arch_type][] = $file; - } - else if(preg_match('/^utt\-\d.+?\.(.+)$/', $file, $dopasowania)) { - $arch_type = $dopasowania[1]; - if(! array_key_exists($arch_type, $archiwa['utt'])) { - $archiwa['utt'][$arch_type] = array(); - } - $archiwa['utt'][$arch_type][] = $file; - } - } // if is file - } // while - closedir($dh); -} // if opendir -//print_r($archiwa); - -$title = 'UAM Text Tools - '.DOWNLOAD_SELECTFILE_PAGE_TITLE."\n"; - -$content = "

".DOWNLOAD_SELECTFILE_CAPTION.":

\n"; -$content .= ''; -# aplikacja -$content .= '\n"; -$content .= '\n"; -$content .= '
'.DOWNLOAD_SELECTFILE_APP_CAPTION."
'; -if(count(array_keys($archiwa['utt'])) > 0) { - $content .= ''; - $content .= "\n"; - foreach (array_keys($archiwa['utt']) as $dist_type) { - $content .= '\n"; - $content .= "\n"; - } - $content .= "
'.DOWNLOAD_SELECTFILE_DISTRIBUTION_TYPE." $dist_type 
\n"; - $arr = $archiwa['utt'][$dist_type]; - rsort($arr); - foreach($arr as $app) { - $content .= "\n\n"; - } - $content .= "
\n"; - $content .= ""; - $content .= ""; - $content .= $app." (".(filesize($dn.$app)/1024)." KB)\n"; - $content .= "
\n
\n"; -} -else { - $content .= DOWNLOAD_SELECTFILE_NO_FILE."\n"; -} - -# slowniki -$content .= '
'.DOWNLOAD_SELECTFILE_DICT_CAPTION."
'; -if(count(array_keys($archiwa['utt-dict'])) > 0) { - $content .= ''; - $content .= "\n"; - foreach (array_keys($archiwa['utt-dict']) as $dist_type) { - $content .= '\n"; - $content .= "\n"; - } - $content .= "
'.DOWNLOAD_SELECTFILE_DISTRIBUTION_TYPE." $dist_type 
\n"; - $arr = $archiwa['utt-dict'][$dist_type]; - rsort($arr); - foreach($arr as $dict) { - $content .= "\n\n"; - } - $content .= "
\n"; - $content .= ""; - $content .= ""; - $content .= $dict." (".(filesize($dn.$dict)/1024)." KB)\n"; - $content .= "
\n
\n"; -} -else { - $content .= DOWNLOAD_SELECTFILE_NO_FILE."\n"; -} -$content .= '
'; -$content .= "\n"; - -getMainPage($title, $content); -?> Index: ld/www/down_form.php =================================================================== --- _old/www/down_form.php (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,24 +1,0 @@ -UAM Text Tools - '.DOWNLOAD_FORM_PAGE_TITLE."\n"; - - $content = "

".DOWNLOAD_FORM_CAPTION."

\n". - "\n". - "\n". - "\n". - "\n". - "\n". - "\n". - "\n". - "\n". - "
".DOWNLOAD_FORM_FIELD_FIRSTNAME.":
".DOWNLOAD_FORM_FIELD_NAME.":
".DOWNLOAD_FORM_FIELD_ORGANIZATION.":
".DOWNLOAD_FORM_FIELD_COUNTRY.":
".DOWNLOAD_FORM_FIELD_EMAIL.":
\n". - "
\n"; - getMainPage($title, $content); - } - else { - header('Location: http://'.$_SERVER['HTTP_HOST'].dirname($_SERVER['PHP_SELF']).'/down.php'); - } -?> Index: ld/www/down_thanks.php =================================================================== --- _old/www/down_thanks.php (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,63 +1,0 @@ -\n"; - mysql_query($sql) - or die(DB_ERROR.': '.mysql_error().' ('.mysql_errno().')'); - - mysql_close($link); -} - - -// main part -// print_r($_SERVER); -// print_r($_POST); - if(isset($_POST['_filename'])) { - save_user(); - $head = 'UAM Text Tools - '.DOWNLOAD_THANKS_PAGE_TITLE."\n"; - $head .= "\n"; - $content = DOWNLOAD_THANKS_CAPTION."
\n". - "
".DOWNLOAD_THANKS_EXTRA_LINK. - " ".$_POST['_filename'].".
\n". - "".DOWNLOAD_THANKS_MAINPAGE_LINK."\n"; - - getMainPage($head, $content); - } - else { - header('Location: http://'.$_SERVER['HTTP_HOST'].dirname($_SERVER['PHP_SELF']).'/down.php'); - } - -?> Index: ld/www/help.php =================================================================== --- _old/www/help.php (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,10 +1,0 @@ -UAM Text Tools - '.HELP_PAGE_TITLE."\n"; -$context = HELP_PAGE_CONTENT; - -getMainPage($title, $context); - -?> Index: ld/www/index.php =================================================================== --- _old/www/index.php (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,10 +1,0 @@ -UAM Text Tools - '.MAIN_PAGE_TITLE."\n"; -$context = "

\"uam

\n".MAIN_PAGE_CONTENT; - -getMainPage($title, $context); - -?> Index: ld/www/js/menu.js =================================================================== --- _old/www/js/menu.js (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,13 +1,0 @@ -function menu_select_element(el_menu, is_selected) { - - if(is_selected) { - el_menu.style.background = '#00FF66'; - el_menu.style.cursor = 'hand'; // for IE - el_menu.style.cursor = 'pointer'; - } - else { - el_menu.style.background = '#CCFF99'; - el_menu.style.cursor = 'default'; - } - return true; -} Index: ld/www/lang/locale.en =================================================================== --- _old/www/lang/locale.en (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,6 +1,0 @@ - Index: ld/www/lang/locale.pl =================================================================== --- _old/www/lang/locale.pl (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,83 +1,0 @@ -\n". - "Witamy na naszej stronie.\n". - "

\n". - "

O stronie
\n". - "Budowanie stron, ze wzglêdu na to, ¿e ka¿da przegl±darka na swój specyficzny sposób reaguje na niektóre polecenia, nie jest wcale proste. Nie wystarczy tylko tworzyæ zgodnie ze standardami, ale trzeba tak¿e zatroszczyæ siê o to, ¿eby w starszych przegl±darkach, ci±gle u¿ywanych (przede wszystkim Internet Explorer), strona prezentowa³a siê dobrze.

\n". - "

Celem powstania tej strony by³o zebranie wszystkich aktualnych informacji dotycz±cych jêzyków HTML, XHTML, CSS oraz DOM w jednym miejscu. Znajdziesz tutaj zarówno informacje typowe, z oficjalnych specyfikacji, ale tak¿e, w formie ciekawostki, liczne rozszerzenia przegl±darek.

\n". - "

W chwili obecnej znajduj± siê tutaj informacje o 119 znacznikach HTML oraz 187 atrybutach stylów. W przysz³o¶ci systematycznie bêd± dodawane polecenia ze specyfikacji XHTML 2.0, Web Applications 1.0 oraz CSS 3.0

\n". - "

Polecane: Profesjonalne tworzenie stron www

\n"); - -# O autorach -define('AUTHORS_TITLE', 'O autorach'); -define('AUTHORS_CONTENT', "

Tu bêdziemy my!

\n"); - -# Do pobrania 1/3 -define('DOWNLOAD_SELECTFILE_PAGE_TITLE', 'Do pobrania 1/3'); -define('DOWNLOAD_SELECTFILE_CAPTION', 'Dostêpne w archiwum pliki'); -define('DOWNLOAD_SELECTFILE_NO_FILE', 'B³±d! Nie znaleziono ¿adnego pliku!'); -define('DOWNLOAD_SELECTFILE_APP_CAPTION', 'Dostêpne wersje narzêdzi UTT'); -define('DOWNLOAD_SELECTFILE_DICT_CAPTION', 'Dostêpne wersje s³owników'); -define('DOWNLOAD_SELECTFILE_DISTRIBUTION_TYPE', 'Dystrybucja'); - -# Do pobrania 2/3 -define('DOWNLOAD_FORM_PAGE_TITLE', 'Do pobrania 2/3'); -define('DOWNLOAD_FORM_CAPTION', 'Przed pobraniem pliku wype³nij poni¿szy formularz'); -define('DOWNLOAD_FORM_FIELD_FIRSTNAME', 'Imiê'); -define('DOWNLOAD_FORM_FIELD_NAME', 'Nazwisko'); -define('DOWNLOAD_FORM_FIELD_ORGANIZATION', 'Organizacja'); -define('DOWNLOAD_FORM_FIELD_COUNTRY', 'Kraj'); -define('DOWNLOAD_FORM_FIELD_EMAIL', 'Adres emailowy'); -define('DOWNLOAD_FORM_FIELD_NEXT', 'Dalej'); - -# Do pobrania 3/3 -define('DOWNLOAD_THANKS_PAGE_TITLE', 'Do pobrania 3/3'); -define('DOWNLOAD_THANKS_CAPTION', 'Dziêkujemy za zainteresowanie narzêdziami UTT!'); -define('DOWNLOAD_THANKS_EXTRA_LINK', 'Je¶li pobieranie pliku nie rozpoczê³o siê automatycznie, kliknij link'); -define('DOWNLOAD_THANKS_MAINPAGE_LINK', 'Wróæ do Strony g³ównej'); - -# Pomoc -define('HELP_PAGE_TITLE', 'Pomoc'); -define('HELP_PAGE_CONTENT', "

\n". - "Pomocy!!! -

-

O stronie
- Budowanie stron, ze wzglêdu na to, ¿e ka¿da przegl±darka na swój specyficzny sposób reaguje na niektóre polecenia, nie jest wcale proste. Nie wystarczy tylko tworzyæ zgodnie ze standardami, ale trzeba tak¿e zatroszczyæ siê o to, ¿eby w starszych przegl±darkach, ci±gle u¿ywanych (przede wszystkim Internet Explorer), strona prezentowa³a siê dobrze.

-

Celem powstania tej strony by³o zebranie wszystkich aktualnych informacji dotycz±cych jêzyków HTML, XHTML, CSS oraz DOM w jednym miejscu. Znajdziesz tutaj zarówno informacje typowe, z oficjalnych specyfikacji, ale tak¿e, w formie ciekawostki, liczne rozszerzenia przegl±darek.

-

W chwili obecnej znajduj± siê tutaj informacje o 119 znacznikach HTML oraz 187 atrybutach stylów. W przysz³o¶ci systematycznie bêd± dodawane polecenia ze specyfikacji XHTML 2.0, Web Applications 1.0 oraz CSS 3.0

-

Polecane: Profesjonalne tworzenie stron www

-

O stronie
- Budowanie stron, ze wzglêdu na to, ¿e ka¿da przegl±darka na swój specyficzny sposób reaguje na niektóre polecenia, nie jest wcale proste. Nie wystarczy tylko tworzyæ zgodnie ze standardami, ale trzeba tak¿e zatroszczyæ siê o to, ¿eby w starszych przegl±darkach, ci±gle u¿ywanych (przede wszystkim Internet Explorer), strona prezentowa³a siê dobrze.

-

Celem powstania tej strony by³o zebranie wszystkich aktualnych informacji dotycz±cych jêzyków HTML, XHTML, CSS oraz DOM w jednym miejscu. Znajdziesz tutaj zarówno informacje typowe, z oficjalnych specyfikacji, ale tak¿e, w formie ciekawostki, liczne rozszerzenia przegl±darek.

-

W chwili obecnej znajduj± siê tutaj informacje o 119 znacznikach HTML oraz 187 atrybutach stylów. W przysz³o¶ci systematycznie bêd± dodawane polecenia ze specyfikacji XHTML 2.0, Web Applications 1.0 oraz CSS 3.0

-

Polecane: Profesjonalne tworzenie stron www

-

O stronie
- Budowanie stron, ze wzglêdu na to, ¿e ka¿da przegl±darka na swój specyficzny sposób reaguje na niektóre polecenia, nie jest wcale proste. Nie wystarczy tylko tworzyæ zgodnie ze standardami, ale trzeba tak¿e zatroszczyæ siê o to, ¿eby w starszych przegl±darkach, ci±gle u¿ywanych (przede wszystkim Internet Explorer), strona prezentowa³a siê dobrze.

-

Celem powstania tej strony by³o zebranie wszystkich aktualnych informacji dotycz±cych jêzyków HTML, XHTML, CSS oraz DOM w jednym miejscu. Znajdziesz tutaj zarówno informacje typowe, z oficjalnych specyfikacji, ale tak¿e, w formie ciekawostki, liczne rozszerzenia przegl±darek.

-

W chwili obecnej znajduj± siê tutaj informacje o 119 znacznikach HTML oraz 187 atrybutach stylów. W przysz³o¶ci systematycznie bêd± dodawane polecenia ze specyfikacji XHTML 2.0, Web Applications 1.0 oraz CSS 3.0

-

Polecane: Profesjonalne tworzenie stron www

\n"); - -# Licencja -define('LICENSE_PAGE_TITLE', 'Licencja'); -define('LICENSE_PAGE_CONTENT', "

UTeTe jest debe¶ciarskie!

\n"); - -?> Index: ld/www/licence.php =================================================================== --- _old/www/licence.php (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,10 +1,0 @@ -UAM Text Tools - '.LICENSE_PAGE_TITLE."\n"; -$context = LICENSE_PAGE_CONTENT; - -getMainPage($title, $context); - -?> Index: ld/www/locale.php =================================================================== --- _old/www/locale.php (revision 57728c1d40118b66361f4d949f1ad6409070f9c6) +++ (revision ) @@ -1,5 +1,0 @@ - Index: to/defaults =================================================================== --- auto/defaults (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,76 +1,0 @@ -#!/bin/sh - -DEFAULT_PROJECT_NAME='utt' -DEFAULT_PROJECT_FULLNAME='UAM Text Tools' -DEFAULT_PROJECT_COPYRIGHT='Copyright (C) UTT Team' -DEFAULT_PROJECT_VERSION='0.9.3' -DEFAULT_PROJECT_PAGE='http://utt.wmi.amu.edu.pl' -DEFAULT_PROJECT_MAIL='utt@wmid.amu.edu.pl' - -DEFAULT_INSTALL='/usr/bin/install' -DEFAULT_SHELL='/bin/sh' -DEFAULT_CC='/usr/bin/gcc' -DEFAULT_BISON='/usr/bin/bison' -DEFAULT_FLEX='/usr/bin/flex' -DEFAULT_RM='/bin/rm -f' -DEFAULT_RMDIR='/bin/rm -rf' -DEFAULT_TEST='/usr/bin/test' -DEFAULT_MAKE='/usr/bin/make' -DEFAULT_GREP='/bin/grep' -DEFAULT_CUT='/usr/bin/cut' -DEFAULT_SORT='/usr/bin/sort' -DEFAULT_PR='/usr/bin/pr' -DEFAULT_CP='/bin/cp' -DEFAULT_CHMOD='/bin/chmod' -DEFAULT_MAKEINFO='/usr/bin/makeinfo' -DEFAULT_TEXI2DVI='/usr/bin/texi2dvi' -DEFAULT_TEXI2PDF='/usr/bin/texi2pdf' -DEFAULT_DVIPS='/usr/bin/dvips' - -DEFAULT_CFLAGS='-g -O2 -Wall' -DEFAULT_LDFLAGS='' -DEFAULT_LDLIBS='' -DEFAULT_BFLAGS='' -DEFAULT_FFLAGS='' - -DEFAULT_DESTDIR= - -DEFAULT_prefix='/usr/local' -DEFAULT_exec_prefix='$(prefix)' -DEFAULT_bindir='$(exec_prefix)/bin' -DEFAULT_sbindir='$(exec_prefix)/sbin' -DEFAULT_libexecdir='$(exec_prefix)/libexec' -DEFAULT_datarootdir='$(prefix)/share' -DEFAULT_datadir='$(datarootdir)' -DEFAULT_sysconfdir='$(prefix)/etc' -DEFAULT_sharedstatedir='$(prefix)/com' -DEFAULT_localstatedir='$(prefix)/var' -DEFAULT_docdir='$(datarootdir)/doc/$(PROJECT_NAME)' -DEFAULT_infodir='$(datarootdir)/info' -DEFAULT_htmldir='$(docdir)' -DEFAULT_dvidir='$(docdir)' -DEFAULT_pdfdir='$(docdir)' -DEFAULT_psdir='$(docdir)' -DEFAULT_libdir='$(exec_prefix)/lib' -DEFAULT_localedir='$(datarootdir)/locale' -DEFAULT_mandir='$(datarootdir)/man' -DEFAULT_man1dir='$(mandir)/man1' -DEFAULT_man2dir='$(mandir)/man2' -DEFAULT_man3dir='$(mandir)/man3' -DEFAULT_man4dir='$(mandir)/man4' -DEFAULT_man5dir='$(mandir)/man5' -DEFAULT_man6dir='$(mandir)/man6' -DEFAULT_man7dir='$(mandir)/man7' -DEFAULT_man8dir='$(mandir)/man8' -DEFAULT_man9dir='$(mandir)/man9' -DEFAULT_manext='.1' -DEFAULT_man1ext='.1' -DEFAULT_man2ext='.2' -DEFAULT_man3ext='.3' -DEFAULT_man4ext='.4' -DEFAULT_man5ext='.5' -DEFAULT_man6ext='.6' -DEFAULT_man7ext='.7' -DEFAULT_man8ext='.8' -DEFAULT_man9ext='.9' - Index: to/options =================================================================== --- auto/options (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,260 +1,0 @@ -#!/bin/sh - -help=no -quiet=no - -if [ -z "$PROJECT_NAME" ]; then PROJECT_NAME=$DEFAULT_PROJECT_NAME; fi -if [ -z "$PROJECT_FULLNAME" ]; then PROJECT_FULLNAME=$DEFAULT_PROJECT_FULLNAME; fi -if [ -z "$PROJECT_COPYRIGHT" ]; then PROJECT_COPYRIGHT=$DEFAULT_PROJECT_COPYRIGHT; fi -if [ -z "$PROJECT_VERSION" ]; then PROJECT_VERSION=$DEFAULT_PROJECT_VERSION; fi -if [ -z "$PROJECT_PAGE" ]; then PROJECT_PAGE=$DEFAULT_PROJECT_PAGE; fi -if [ -z "$PROJECT_MAIL" ]; then PROJECT_MAIL=$DEFAULT_PROJECT_MAIL; fi - -if [ -z "$INSTALL" ]; then INSTALL=$DEFAULT_INSTALL; fi -if [ -z "$SHELL" ]; then SHELL=$DEFAULT_SHELL; fi -if [ -z "$CC" ]; then CC=$DEFAULT_CC; fi -if [ -z "$BISON" ]; then BISON=$DEFAULT_BISON; fi -if [ -z "$FLEX" ]; then FLEX=$DEFAULT_FLEX; fi -if [ -z "$RM" ]; then RM=$DEFAULT_RM; fi -if [ -z "$RMDIR" ]; then RMDIR=$DEFAULT_RMDIR; fi -if [ -z "$TEST" ]; then TEST=$DEFAULT_TEST; fi -if [ -z "$MAKE" ]; then MAKE=$DEFAULT_MAKE; fi -if [ -z "$GREP" ]; then GREP=$DEFAULT_GREP; fi -if [ -z "$CUT" ]; then CUT=$DEFAULT_CUT; fi -if [ -z "$SORT" ]; then SORT=$DEFAULT_SORT; fi -if [ -z "$PR" ]; then PR=$DEFAULT_PR; fi -if [ -z "$CP" ]; then CP=$DEFAULT_CP; fi -if [ -z "$CHMOD" ]; then CHMOD=$DEFAULT_CHMOD; fi -if [ -z "$MAKEINFO" ]; then MAKEINFO=$DEFAULT_MAKEINFO; fi -if [ -z "$TEXI2DVI" ]; then TEXI2DVI=$DEFAULT_TEXI2DVI; fi -if [ -z "$TEXI2PDF" ]; then TEXI2PDF=$DEFAULT_TEXI2PDF; fi -if [ -z "$DVIPS" ]; then DVIPS=$DEFAULT_DVIPS; fi - -if [ -z "$CFLAGS" ]; then CFLAGS=$DEFAULT_CFLAGS; fi -if [ -z "$LDFLAGS" ]; then LDFLAGS=$DEFAULT_LDFLAGS; fi -if [ -z "$LDLIBS" ]; then LDLIBS=$DEFAULT_LDLIBS; fi -if [ -z "$BFLAGS" ]; then BFLAGS=$DEFAULT_BFLAGS; fi -if [ -z "$FFLAGS" ]; then FFLAGS=$DEFAULT_FFLAGS; fi - -if [ -z "$DESTDIR" ]; then DESTDIR=$DEFAULT_DESTDIR; fi - -if [ -z "$prefix" ]; then prefix=$DEFAULT_prefix; fi -if [ -z "$exec_prefix" ]; then exec_prefix=$DEFAULT_exec_prefix; fi -if [ -z "$bindir" ]; then bindir=$DEFAULT_bindir; fi -if [ -z "$sbindir" ]; then sbindir=$DEFAULT_sbindir; fi -if [ -z "$libexecdir" ]; then libexecdir=$DEFAULT_libexecdir; fi -if [ -z "$datarootdir" ]; then datarootdir=$DEFAULT_datarootdir; fi -if [ -z "$datadir" ]; then datadir=$DEFAULT_datadir; fi -if [ -z "$sysconfdir" ]; then sysconfdir=$DEFAULT_sysconfdir; fi -if [ -z "$sharedstatedir" ]; then sharedstatedir=$DEFAULT_sharedstatedir; fi -if [ -z "$localstatedir" ]; then localstatedir=$DEFAULT_localstatedir; fi -if [ -z "$docdir" ]; then docdir=$DEFAULT_docdir; fi -if [ -z "$infodir" ]; then infodir=$DEFAULT_infodir; fi -if [ -z "$htmldir" ]; then htmldir=$DEFAULT_htmldir; fi -if [ -z "$dvidir" ]; then dvidir=$DEFAULT_dvidir; fi -if [ -z "$pdfdir" ]; then pdfdir=$DEFAULT_pdfdir; fi -if [ -z "$psdir" ]; then psdir=$DEFAULT_psdir; fi -if [ -z "$libdir" ]; then libdir=$DEFAULT_libdir; fi -if [ -z "$localedir" ]; then localedir=$DEFAULT_localedir; fi -if [ -z "$mandir" ]; then mandir=$DEFAULT_mandir; fi -if [ -z "$man1dir" ]; then man1dir=$DEFAULT_man1dir; fi -if [ -z "$man2dir" ]; then man2dir=$DEFAULT_man2dir; fi -if [ -z "$man3dir" ]; then man3dir=$DEFAULT_man3dir; fi -if [ -z "$man4dir" ]; then man4dir=$DEFAULT_man4dir; fi -if [ -z "$man5dir" ]; then man5dir=$DEFAULT_man5dir; fi -if [ -z "$man6dir" ]; then man6dir=$DEFAULT_man6dir; fi -if [ -z "$man7dir" ]; then man7dir=$DEFAULT_man7dir; fi -if [ -z "$man8dir" ]; then man8dir=$DEFAULT_man8dir; fi -if [ -z "$man9dir" ]; then man9dir=$DEFAULT_man9dir; fi -if [ -z "$manext" ]; then manext=$DEFAULT_manext; fi -if [ -z "$man1ext" ]; then man1ext=$DEFAULT_man1ext; fi -if [ -z "$man2ext" ]; then man2ext=$DEFAULT_man2ext; fi -if [ -z "$man3ext" ]; then man3ext=$DEFAULT_man3ext; fi -if [ -z "$man4ext" ]; then man4ext=$DEFAULT_man4ext; fi -if [ -z "$man5ext" ]; then man5ext=$DEFAULT_man5ext; fi -if [ -z "$man6ext" ]; then man6ext=$DEFAULT_man6ext; fi -if [ -z "$man7ext" ]; then man7ext=$DEFAULT_man7ext; fi -if [ -z "$man8ext" ]; then man8ext=$DEFAULT_man8ext; fi -if [ -z "$man9ext" ]; then man9ext=$DEFAULT_man9ext; fi - - -for option -do - case "$option" in - -*=*) value=$(echo "$option" | sed -e 's/[-_a-zA-Z0-9]*=//') ;; - *=*) value=$(echo "$option" | sed -e 's/[_A-Z0-9]*=//') ;; - *) value="" ;; - esac - - case "$option" in - --help) help=yes ;; - --quiet) quiet=yes ;; - - DESTDIR=*) DESTDIR="$value" ;; - --prefix=*) prefix="$value" ;; - --exec-prefix=*) exec_prefix="$value" ;; - --bindir=*) bindir="$value" ;; - --sbindir=*) sbindir="$value" ;; - --libexecdir=*) libexecdir="$value" ;; - --datarootdir=*) datarootdir="$value" ;; - --datadir=*) datadir="$value" ;; - --sysconfdir=*) sysconfdir="$value" ;; - --sharedstatedir=*) sharedstatedir="$value" ;; - --localstatedir=*) localstatedir="$value" ;; - --docdir=*) docdir="$value" ;; - --infodir=*) infodir="$value" ;; - --htmldir=*) htmldir="$value" ;; - --dvidir=*) dvidir="$value" ;; - --pdfdir=*) pdfdir="$value" ;; - --psdir=*) psdir="$value" ;; - --libdir=*) libdir="$value" ;; - --localedir=*) localedir="$value" ;; - --mandir=*) mandir="$value" ;; - --man1dir=*) man1dir="$value" ;; - --man2dir=*) man2dir="$value" ;; - --man3dir=*) man3dir="$value" ;; - --man4dir=*) man4dir="$value" ;; - --man5dir=*) man5dir="$value" ;; - --man6dir=*) man6dir="$value" ;; - --man7dir=*) man7dir="$value" ;; - --man8dir=*) man8dir="$value" ;; - --man9dir=*) man9dir="$value" ;; - --manext=*) manext="$value" ;; - --man1ext=*) man1ext="$value" ;; - --man2ext=*) man2ext="$value" ;; - --man3ext=*) man3ext="$value" ;; - --man4ext=*) man4ext="$value" ;; - --man5ext=*) man5ext="$value" ;; - --man6ext=*) man6ext="$value" ;; - --man7ext=*) man7ext="$value" ;; - --man8ext=*) man8ext="$value" ;; - --man9ext=*) man9ext="$value" ;; - - INSTALL=*) INSTALL="$value" ;; - SHELL=*) SHELL="$value" ;; - CC=*) CC="$value" ;; - BISON=*) BISON="$value" ;; - FLEX=*) FLEX="$value" ;; - RM=*) RM="$value" ;; - RMDIR=*) RMDIR="$value" ;; - TEST=*) TEST="$value" ;; - MAKE=*) MAKE="$value" ;; - GREP=*) GREP="$value" ;; - CUT=*) CUT="$value" ;; - SORT=*) SORT="$value" ;; - PR=*) PR="$value" ;; - CP=*) CP="$value" ;; - CHMOD=*) CHMOD="$value" ;; - MAKEINFO=*) MAKEINFO="$value" ;; - TEXI2DVI=*) TEXI2DVI="$value" ;; - TEXI2PDF=*) TEXI2PDF="$value" ;; - DVIPS=*) DVIPS="$value" ;; - - CFLAGS=*) CFLAGS="$value" ;; - LDFLAGS=*) LDFLAGS="$value" ;; - LDLIBS=*) LDLIBS="$value" ;; - BFLAGS=*) BFLAGS="$value" ;; - FFLAGS=*) FFLAGS="$value" ;; - esac -done - -if [ "$help" = "yes" ]; then - -cat << HELP_END - -Configure script for $PROJECT_NAME $PROJECT_VERSION to adapt to many kinds of systems. - -Usage: - - ./configure [OPTION]... [VAR=VALUE]... - -To assign environment variables (e.g., CC, CFLAGS...), specify them as -VAR=VALUE. See below for descriptions of some of the useful variables. - -Options: - - --help display this help and exit - -Installation directories: - - --prefix=PATH install architecture-independent files in PATH - --exec-prefix=PATH install architecture-dependent files in PATH - -Fine tuning of the installation directories: - - --bindir=PATH user executables - --sbindir=PATH system admin executables - --libexecdir=PATH program executables - --datarootdir=PATH read-only arch.-independent data root - --datadir=PATH read-only architecture-independent data - --sysconfdir=PATH read-only single-machine data - --sharedstatedir=PATH modifiable architecture-independent data - --localstatedir=PATH modifiable single-machine data - --docdir=DIR documentation root - --infodir=DIR info documentation - --htmldir=DIR html documentation - --dvidir=DIR dvi documentation - --pdfdir=DIR pdf documentation - --psdir=DIR ps documentation - --libdir=DIR object code libraries - --localedir=DIR locale-dependent data - --mandir=DIR man documentation - --man1dir=DIR section 1 man documentation - --man2dir=DIR section 2 man documentation - --man3dir=DIR section 3 man documentation - --man4dir=DIR section 4 man documentation - --man5dir=DIR section 5 man documentation - --man6dir=DIR section 6 man documentation - --man7dir=DIR section 7 man documentation - --man8dir=DIR section 8 man documentation - --man9dir=DIR section 9 man documentation - --manext=EXT man extension - --man1ext=EXT section 1 man extension - --man2ext=EXT section 2 man extension - --man3ext=EXT section 3 man extension - --man4ext=EXT section 4 man extension - --man5ext=EXT section 5 man extension - --man6ext=EXT section 6 man extension - --man7ext=EXT section 7 man extension - --man8ext=EXT section 8 man extension - --man9ext=EXT section 9 man extension - -Some influential environment variables: - - INSTALL install command - SHELL shell command - CC C compiler command - BISON Bison compiler command - RM rm command - RMDIR rmdir command - TEST test command - MAKE make command - GREP grep command - CUT cut command - SORT sort command - PR pr command - CP cp command - CHMOD chmod command - MAKEINFO makeinfo command - TEXI2DVI texi2dvi command - TEXI2PDF texi2pdf command - DVIPS dvips command - - - CFLAGS C compiler flags - LDFLAGS linker flags, e.g. -L if you have - libraries in a nonstandard directory - LDLIBS libraries to pass to the linker, e.g. -l - BFLAGS Bison compiler flags - FFLAGS Flex compiler flags - -Use these variables to override default values. - -Report bugs to <$PROJECT_MAIL>. -More details at $PROJECT_PAGE. - -HELP_END - - exit 1 -fi - Index: to/output/Makefile =================================================================== --- auto/output/Makefile (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,313 +1,0 @@ -#!/bin/sh - -cat << EOF > Makefile -# Default target -.DEFAULT_GOAL = all - -PROJECT_NAME = $PROJECT_NAME -PROJECT_FULLNAME = $PROJECT_FULLNAME -PROJECT_COPYRIGHT = $PROJECT_COPYRIGHT -PROJECT_VERSION = $PROJECT_VERSION -PROEJCT_PAGE = $PROJECT_PAGE -PROJECT_MAIL = $PROJECT_MAIL - -INSTALL = $INSTALL -INSTALL_PROGRAM = \$(INSTALL) -INSTALL_PROGRAM_STRIP = \$(INSTALL) -s -INSTALL_DATA = \$(INSTALL) -m 644 -INSTALL_DIR = \$(INSTALL) -d -SHELL = $SHELL -CC = $CC -BISON = $BISON -FLEX = $FLEX -RM = $RM -RMDIR = $RMDIR -TEST = $TEST -MAKE = $MAKE -GREP = $GREP -CUT = $CUT -SORT = $SORT -PR = $PR -CP = $CP -CHMOD = $CHMOD -MAKEINFO = $MAKEINFO -TEXI2DVI = $TEXI2DVI -TEXI2PDF = $TEXI2PDF -DVIPS = $DVIPS - -CFLAGS = $CFLAGS -LDFLAGS = $LDFLAGS -LDLIBS = $LDLIBS -BFLAGS = $BFLAGS -FFLAGS = $FFLAGS - -DESTDIR = $DESTDIR - -prefix = $prefix -exec_prefix = $exec_prefix -bindir = $bindir -sbindir = $sbindir -libexecdir = $libexecdir -datarootdir = $datarootdir -datadir = $datadir -sysconfdir = $sysconfdir -sharedstatedir = $sharedstatedir -localstatedir = $localstatedir -docdir = $docdir -infodir = $infodir -htmldir = $htmldir -dvidir = $dvidir -pdfdir = $pdfdir -psdir = $psdir -libdir = $libdir -localedir = $localedir -mandir = $mandir -man1dir = $man1dir -man2dir = $man2dir -man3dir = $man3dir -man4dir = $man4dir -man5dir = $man5dir -man6dir = $man6dir -man7dir = $man7dir -man8dir = $man8dir -man9dir = $man9dir -manext = $manext -man1ext = $man1ext -man2ext = $man2ext -man3ext = $man3ext -man4ext = $man4ext -man5ext = $man5ext -man6ext = $man6ext -man7ext = $man7ext -man8ext = $man8ext -man9ext = $man9ext - -ALL_CFLAGS = \$(CFLAGS) -ALL_LDFLAGS = \$(LDFLAGS) -ALL_LDLIBS = \$(LDLIBS) -ALL_BFLAGS = \$(BFLAGS) -ALL_FFLAGS = -t \$(FFLAGS) - -vpath %.c ./src -vpath %.l ./src -vpath %.ggo ./src -vpath %.pl ./src -vpath %.sed ./src -vpath %.sh ./src -vpath %.texinfo ./doc - -PROGRAMS_SCRIPT = gph kot unfla grp mar ser kon rm12 uam.tag2re sen-nl -PROGRAMS_EXEC = tok sen fla rs12 -PROGRAMS = \$(PROGRAMS_SCRIPT) \$(PROGRAMS_EXEC) -DOC_FILES = utt.info utt.dvi utt.html utt.pdf utt.ps - -TOK_OBJ_FILES = tok.o tok_cmdline.o -TOK_FLEX_FILES = tok.l -TOK_GGO_FILES = tok_cmdline.ggo -tok: \$(TOK_OBJ_FILES) -tok.o: tok.c -tok.o: tok_cmdline.h -tok.c: tok.l -tok_cmdline.o: tok_cmdline.c tok_cmdline.h -tok_cmdline.c: tok_cmdline.ggo -tok_cmdline.h: tok_cmdline.ggo - -SEN_OBJ_FILES = sen.o -SEN_FLEX_FILES = sen.l -sen: \$(SEN_OBJ_FILES) -sen.o: sen.c -sen.c: sen.l - -FLA_OBJ_FILES = fla.o -fla: \$(FLA_OBJ_FILES) -fla.o: fla.c - -GPH_PERL_FILES = gph.pl -gph: \$(GPH_PERL_FILES) - -UAMTAG2RE_PERL_FILES = uam.tag2re.pl -uam.tag2re: \$(UAMTAG2RE_PERL_FILES) - -KOT_PERL_FILES = kot.pl -kot: \$(KOT_PERL_FILES) - -UNFLA_SH_FILES = unfla.sh -unfla: \$(UNFLA_SH_FILES) - -GRP_PERL_FILES = grp.pl -grp: \$(GRP_PERL_FILES) - -MAR_PERL_FILES = mar.pl -mar: \$(MAR_PERL_FILES) - -SER_PERL_FILES = ser.pl -ser: \$(SER_PERL_FILES) - -KON_PERL_FILES = kon.pl -kon: \$(KON_PERL_FILES) - -RM12_SED_FILES = rm12.sed -rm12: \$(RM12_SED_FILES) - -SENNL_SED_FILES = sen-nl.sed -sen-nl: \$(SENNL_SED_FILES) - -RS12_OBJ_FILES = rs12.o -rs12: \$(RS12_OBJ_FILES) -rs12.o: rs12.c - -CONFIG_FILES = src/config.h Makefile - -.SUFFIXES: -.SUFFIXES: .l .y .h .c .pl .o .texinfo .info .dvi .html .pdf .ps - -.PHONY: help -help: - @\$(MAKE) --print-data-base --question | \\ - \$(GREP) '^[^.%][-A-Za-z0-9_]*:' | \\ - \$(CUT) -f 1 -d : | \\ - \$(GREP) -v '^Makefile\$\$' | \\ - \$(SORT) | \\ - \$(PR) --omit-pagination --width=80 --columns=4 - -.PHONY: all -all: \$(PROGRAMS) - -.PHONY: doc -doc: info dvi html pdf ps - -.PHONY: info -info: utt.info - -.PHONY: dvi -dvi: utt.dvi - -.PHONY: html -html: utt.html - -.PHONY: pdf -pdf: utt.pdf - -.PHONY: ps -ps: utt.ps - -.PHONY: install-all -install-all: install install-doc - -.PHONY: installdirs -installdirs: - \$(INSTALL_DIR) \$(DESTDIR)\$(prefix) \\ - \$(DESTDIR)\$(exec_prefix) \\ - \$(DESTDIR)\$(bindir) \\ - \$(DESTDIR)\$(datarootdir) \\ - \$(DESTDIR)\$(datadir) \\ - \$(DESTDIR)\$(docdir) \\ - \$(DESTDIR)\$(infodir) \\ - \$(DESTDIR)\$(htmldir) \\ - \$(DESTDIR)\$(dvidir) \\ - \$(DESTDIR)\$(pdfdir) \\ - \$(DESTDIR)\$(psdir) \\ - -.PHONY: install -install: installdirs - \$(INSTALL_PROGRAM) \$(PROGRAMS) \$(DESTDIR)\$(bindir) - -.PHONY: install-strip -install-strip: installdirs - \$(INSTALL_PROGRAM) \$(PROGRAMS_SCRIPT) \$(DESTDIR)\$(bindir) - \$(INSTALL_PROGRAM_STRIP) \$(PROGRAMS_EXEC) \$(DESTDIR)\$(bindir) - -.PHONY: install-doc -install-doc: install-info install-dvi install-html install-pdf install-ps - -.PHONY: install-info -install-info: installdirs - \$(INSTALL_DATA) utt.info \$(DESTDIR)\$(infodir) - -.PHONY: install-dvi -install-dvi: installdirs - \$(INSTALL_DATA) utt.dvi \$(DESTDIR)\$(dvidir) - -.PHONY: install-html -install-html: installdirs - \$(INSTALL_DATA) utt.html \$(DESTDIR)\$(htmldir) - -.PHONY: install-pdf -install-pdf: installdirs - \$(INSTALL_DATA) utt.pdf \$(DESTDIR)\$(pdfdir) - -.PHONY: install-ps -install-ps: installdirs - \$(INSTALL_DATA) utt.ps \$(DESTDIR)\$(psdir) - -.PHONY: uninstall -uninstall: - \$(RM) \$(foreach file,\$(PROGRAMS),\$(DESTDIR)\$(bindir)/\$(file)) - \$(RM) \$(DESTDIR)\$(infodir)/utt.info - \$(RM) \$(DESTDIR)\$(dvidir)/utt.dvi - \$(RM) \$(DESTDIR)\$(htmldir)/utt.html - \$(RM) \$(DESTDIR)\$(pdfdir)/utt.pdf - \$(RM) \$(DESTDIR)\$(psdir)/utt.ps - \$(RMDIR) \$(DESTDIR)\$(docdir) - -.PHONY: clean -clean: - \$(RM) \$(PROGRAMS) - \$(RM) \$(TOK_OBJ_FILES) - \$(RM) \$(patsubst %.l,%.c,\$(TOK_FLEX_FILES)) - \$(RM) \$(patsubst %.ggo,%.c,\$(TOK_GGO_FILES)) - \$(RM) \$(patsubst %.ggo,%.h,\$(TOK_GGO_FILES)) - \$(RM) \$(SEN_OBJ_FILES) - \$(RM) \$(patsubst %.l,%.c,\$(SEN_FLEX_FILES)) - \$(RM) \$(FLA_OBJ_FILES) - \$(RM) \$(RS12_OBJ_FILES) - \$(RM) \$(DOC_FILES) - -.PHONY: distclean -distclean: clean - \$(RM) \$(CONFIG_FILES) - -%.o: %.c - \$(CC) -c \$< -o \$@ \$(ALL_CFLAGS) - -%.c: %.l - \$(FLEX) -t \$< > \$@ - -%.c: %.ggo - gengetopt --input \$< --file-name \$(basename \$@) --conf-parser - -%.h: %.ggo - gengetopt --input \$< --file-name \$(basename \$@) --conf-parser - -%: %.o - \$(CC) \$? -o \$@ \$(ALL_LDFLAGS) \$(ALL_CFLAGS) \$(ALL_LDLIBS) - -%: %.pl - \$(CP) \$< \$@ - \$(CHMOD) a+x \$@ - -%: %.sh - \$(CP) \$< \$@ - \$(CHMOD) a+x \$@ - -%: %.sed - \$(CP) \$< \$@ - \$(CHMOD) a+x \$@ - -%.info: %.texinfo - \$(MAKEINFO) \$< -o \$@ - -%.dvi: %.texinfo - \$(TEXI2DVI) --build=clean \$< -o \$@ - -%.html: %.texinfo - \$(MAKEINFO) --html --no-split \$< -o \$@ - -%.pdf: %.texinfo - \$(TEXI2PDF) --build=clean \$< -o \$@ - -%.ps: %.dvi - \$(DVIPS) \$< -o \$@ - -EOF - Index: to/output/config_h =================================================================== --- auto/output/config_h (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,16 +1,0 @@ -#!/bin/sh - -cat << EOF > ./src/config.h -#ifndef CONFIG_H -#define CONFIG_H - -#define PROJECT_NAME "$PROJECT_NAME" -#define PROJECT_FULLNAME "$PROJECT_FULLNAME" -#define PROJECT_COPYRIGHT "$PROJECT_COPYRIGHT" -#define PROJECT_VERSION "$PROJECT_VERSION" -#define PROJECT_PAGE "$PROJECT_PAGE" -#define PROJECT_MAIL "$PROJECT_MAIL" - -#endif /* CONFIG_H */ -EOF - Index: to/summary =================================================================== --- auto/summary (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ (revision ) @@ -1,83 +1,0 @@ -#!/bin/sh - -if [ "$quiet" = "yes" ]; then return; fi - -cat << SUMMARY_END - -Project name : $PROJECT_NAME -Project fullname : $PROJECT_FULLNAME -Project copyright : $PROJECT_COPYRIGHT -Project version : $PROJECT_VERSION -Project page : $PROJECT_PAGE -Project mail : $PROJECT_MAIL - -Configuration summary - - DESTDIR : $DESTDIR - - prefix : $prefix - exec_prefix : $exec_prefix - bindir : $bindir - sbindir : $sbindir - libexecdir : $libexecdir - datarootdir : $datarootdir - datadir : $datadir - sysconfdir : $sysconfdir - sharedstatedir : $sharedstatedir - localstatedir : $localstatedir - docdir : $docdir - infodir : $infodir - htmldir : $htmldir - dvidir : $dvidir - pdfdir : $pdfdir - psdir : $psdir - libdir : $libdir - localedir : $localedir - mandir : $mandir - man1dir : $man1dir - man2dir : $man2dir - man3dir : $man3dir - man4dir : $man4dir - man5dir : $man5dir - man6dir : $man6dir - man7dir : $man7dir - man8dir : $man8dir - man9dir : $man9dir - manext : $manext - man1ext : $man1ext - man2ext : $man2ext - man3ext : $man3ext - man4ext : $man4ext - man5ext : $man5ext - man6ext : $man6ext - man7ext : $man7ext - man8ext : $man8ext - man9ext : $man9ext - - INSTALL : $INSTALL - SHELL : $SHELL - CC : $CC - BISON : $BISON - FLEX : $FLEX - RM : $RM - RMDIR : $RMDIR - TEST : $TEST - MAKE : $MAKE - GREP : $GREP - CUT : $CUT - SORT : $SORT - PR : $PR - CP : $CP - CHMOD : $CHMOD - MAKEINFO : $MAKEINFO - TEXI2DVI : $TEXI2DVI - TEXI2PDF : $TEXI2PDF - DVIPS : $DVIPS - - CFLAGS : $CFLAGS - LDFLAGS : $LDFLAGS - LDLIBS : $LDLIBS - BFLAGS : $BFLAGS - FFLAGS : $FFLAGS - -SUMMARY_END Index: configure =================================================================== --- configure (revision a6e708f37f1025d3fd1cd8a7fe87a6029d723cbe) +++ configure (revision c21bdd6340b1c3b3deeec44810ac38561acb1cc5) @@ -1,23 +1,290 @@ #!/bin/sh -. ./auto/defaults -. ./auto/options - -if [ -f ./src/config.h ]; then - echo ERROR: config.h exists - exit -fi - -if [ -f ./Makefile ]; then - echo ERROR: Makefile exists - exit -fi - -if [ ! -d ./src ]; then - mkdir ./src -fi - -. ./auto/output/config_h -. ./auto/output/Makefile - -. ./auto/summary +# utt configure file +# creates config.mak which is used by other makefiles + +# variables for dynamically selecting whether to compile utf8 versions +CUR_DIR=$(pwd) +SRC_DIR="${CUR_DIR}/src" + +# list of components to compile +CMPLIST="compiledic cor dgp fla gph grp gue kon kor kot lem mar rm12 rs12 sen-nl ser tags tok.c tok.l tok.pl unfla" +COMP= + + +# sets all variables to a defined value +set_all(){ + value=$1 + shift + for var in $*; do + eval $var=$value + done +} + +# enables a feature +enable(){ + set_all yes $* +} + +# disables a feature +disable(){ + set_all no $* +} + +# checks whether a feature is enabled +enabled(){ + eval test "x\$$1" = "xyes" +} + +# checks whether a feature is disabled +disabled(){ + eval test "x\$$1" = "xno" +} + +show_help(){ + echo "Usage configure [options]" + echo "Options: [defaults in brackets after descriptions]" + echo "All \"enable\" options have \"disable\" counterparts" + echo + echo " --help print this message" + echo " --prefix=PREFIX install in PREFIX [$PREFIX]" + echo " --bindir=BINDIR install binaries in BINDIR [$bindir]" + echo " --confdir=CONFDIR install configuration in CONFDIR [$confdir]" + echo " --sharedir=SHAREDIR install shared in SHAREDIR [$sharedir]" + echo " --docdir=DOCDIR install doc in DOCDIR [$docdir]" + echo " --langdir=LANGDIR install lang in LANGDIR [$langdir]" + echo " --libdir=LIBDIR install libraries in LIBDIR [$libdir]" + echo + echo " --enable-static build static versions [no]" + echo " --enable-doc build documentation [yes]" + echo " --enable-utf8 build UTF-8 versions of applications [no]" + echo + echo " --cc=CC use C compiler CC [$cc_default]" + echo " --cxx=CXX use C++ compiler CXX [$cxx_default]" + echo " --gengetopt=GGO use gengetopt GGO [$gengetopt_default]" + echo " --flex=FLEX use flex FLEX [$flex_default]" + echo " --makeinfo=MAKEINFO use makeinfo MAKEINFO [$makeinfo_default]" + echo " --texi2dvi=TEXI2DVI use texi2dvi TEXI2DVI [$texi2dvi_default]" + echo " --texi2pdf=TEXI2PDF use texi2pdf TEXI2PDF [$texi2pdf_default]" + echo " --dvips=DVIPS use dvips DVIPS [$dvips_default]" + exit 1 +} + +die_unknown(){ + echo "Unknown option \"$1\"." + echo "See $0 --help for availible options." + exit 1 +} + +# +# default values +PREFIX="/usr/local" + +bindir="${PREFIX}/bin" +confdir="/etc/utt" +sharedir="${PREFIX}/share" +docdir="${PREFIX}/share/doc/utt" +langdir="${PREFIX}/share/utt" +libdir="${PREFIX}/lib/utt" + +cc_default="gcc" +cxx_default="g++" +gengetopt_default="gengetopt" +flex_default="flex" +makeinfo_default="makeinfo" +texi2dvi_default="texi2dvi" +texi2pdf_default="texi2pdf" +dvips_default="dvips" + +# default switch values +DEFAULT=" +" + +DEFAULT_NO="static +utf8 +" + +DEFAULT_YES="doc +" + +CMDLINE_SELECT="$DEFAULT + $DEFAULT_NO + $DEFAULT_YES +" + +enable $DEFAULT_YES +disable $DEFAULT_NO + +for opt do + optval="${opt#*=}" + case "$opt" in + --help) + show_help + ;; + --prefix=*) + PREFIX="$optval" + bindir="$optval/bin" + sharedir="$optval/share" + docdir="$optval/share/doc/utt" + langdir="$optval/share/utt" + libdir="$optval/lib/utt" + ;; + --bindir=*) + bindir="$optval" + ;; + --confdir=*) + confdir="$optval" + ;; + --sharedir=*) + sharedir="$optval" + ;; + --docdir=*) + docdir="$optval" + ;; + --langdir=*) + langdir="$optval" + ;; + --libdir=*) + libdir="$optval" + ;; + --cc=*) + cc="$optval" + ;; + --cxx=*) + cxx="$optval" + ;; + --gengetopt=*) + gengetopt="$optval" + ;; + --flex=*) + flex="$optval" + ;; + --makeinfo=*) + makeinfo="$optval" + ;; + --texi2dvi=*) + texi2dvi="$optval" + ;; + --texi2pdf=*) + texi2pdf="$optval" + ;; + --dvips=*) + dvips="$optval" + ;; + --enable-?*|--disable-?*) + eval `echo "$opt" | sed 's/--/action=/;s/-/ option=/;s/-/_/g'` + echo "$CMDLINE_SELECT" | grep -q "^ *$option\$" || die_unknown $opt + $action $option + ;; + *) + die_unknown $opt + ;; + esac +done + +if ! test -z $cc; then + cc_default="${cc}" +fi +cc="${cc_default}" + +if ! test -z $cxx; then + cxx_default="${cxx}" +fi + +cxx="${cxx_default}" + +if ! test -z $gengetopt; then + gengetopt_default="${gengetopt}" +fi + +gengetopt="${gengetopt_default}" + +if ! test -z $flex; then + flex_default="$flex" +fi + +flex="${flex_default}" + +enabled doc && { + if ! test -z $makeinfo; then + makeinfo_default="${makeinfo}" + fi + if ! test -z $texi2dvi; then + texi2dvi_default="${texi2dvi}" + fi + if ! test -z $texi2pdf; then + texi2pdf_default="${texi2pdf}" + fi + if ! test -z $dvips; then + dvips_default="${dvips}" + fi + + makeinfo="${makeinfo_default}" + texi2dvi="${texi2dvi_default}" + texi2pdf="${texi2pdf_default}" + dvips="${dvips_default}" +} + +# generating config.mak + +echo "# Automatically generated by configure" > config.mak +echo "PREFIX=$PREFIX" >> config.mak +echo "BIN_DIR=$bindir" >> config.mak +echo "CONF_DIR=$confdir" >> config.mak +echo "SHARE_DIR=$sharedir" >> config.mak +echo "DOC_DIR=$docdir" >> config.mak +echo "LANG_DIR=$langdir" >> config.mak +echo "LIB_DIR=$libdir" >> config.mak +echo "CC=$cc" >> config.mak +echo "CXX=$cxx" >> config.mak +echo "GENGETOPT=$gengetopt" >> config.mak +echo "FLEX=$flex" >> config.mak +enabled doc && { + echo "MAKEINFO=$makeinfo" >> config.mak + echo "TEXI2DVI=$texi2dvi" >> config.mak + echo "TEXI2PDF=$texi2pdf" >> config.mak + echo "DVIPS=$dvips" >> config.mak +} +echo "BUILD_UTF8=$utf8" >> config.mak +echo "BUILD_STATIC=$static" >> config.mak +echo "BUILD_DOC=$doc" >> config.mak + +enabled utf8 && { + for cmp in $CMPLIST; do + if [ -d "${SRC_DIR}/${cmp}_utf8" ]; then + COMPONENTS="${COMPONENTS} ${cmp}_utf8" + else + COMPONENTS="${COMPONENTS} ${cmp}" + fi + done +} + +disabled utf8 && { + for cmp in $CMPLIST; do + COMPONENTS="${COMPONENTS} ${cmp}" + done +} +COMPONENTS=$(echo $COMPONENTS | cut -c1-) +echo "COMPONENTS=$COMPONENTS" >> config.mak + +# echoing the configuration to console +echo "prefix: $PREFIX" +echo "bindir: $bindir" +echo "confdir: $confdir" +echo "sharedir: $sharedir" +echo "docdir: $docdir" +echo "langdir: $langdir" +echo "libdir: $libdir" +enabled doc && { +echo "makeinfo: $makeinfo" +echo "texi2dvi: $texi2dvi" +echo "texi2pdf: $texi2pdf" +echo "dvips: $dvips" +} +echo "cc: $cc" +echo "cxx: $cxx" +echo "gengetopt: $gengetopt" +echo "flex: $flex" +echo "utf8: $utf8" +echo "static: $static" +echo "doc: $doc" Index: c/fla.c =================================================================== --- src/fla.c (revision 9e0afb505e266b0a64e2c91b685b3361c9c3bfb3) +++ (revision ) @@ -1,68 +1,0 @@ -#include -#include -#include -#include - -char buf[5000]; - -int main(int argc, char **argv) -{ - - char *pattern; - char eoln; - regex_t re; - - int firstline = 1; - - if( argc < 2 ) - { -/* pattern="[ \t]*([0-9]+[ \t]+){2}EOS([ \t].*)?"; */ - pattern = "[ \t]*BOS([ \t].*)?"; - } - else - { - pattern = argv[1]; - } - - if( argc < 3 ) - { - eoln = '\f'; - } - else - { - eoln = atoi(argv[2]); - } - - if( 0 != regcomp(&re, pattern, REG_EXTENDED|REG_NOSUB) ) - { - fprintf(stderr, "Invalid pattern.\n"); - return 1; - } - - while( fgets(buf, 5000, stdin) ) - { - buf[strlen(buf)-1] = '\0'; - if( firstline ) - { - firstline = 0; - } - else - { - if( 0 == regexec(&re, buf, (size_t)0, NULL, 0) ) - { - putchar('\n'); - } - else - { - putchar(eoln); - } - } - fputs(buf, stdout); - } - - putchar('\n'); - - return 0; - -} - Index: c/gph.pl =================================================================== --- src/gph.pl (revision e4cec26b9f4157c18cc9809b9570c3f2eb14cc03) +++ (revision ) @@ -1,162 +1,0 @@ -#!/usr/bin/perl - -#package: UAM Text Tools -#component: gph -#version: 1.0 -#author: Tomasz Obrebski - -use strict; -use Getopt::Long; -use File::HomeDir; - - - - - -my $systemconfigfile='/usr/local/etc/utt/gph.conf'; -my $userconfigfile=home()."/.utt/gph.conf"; - -Getopt::Long::Configure('no_ignore_case_always'); - -my $help=0; -my $inputfile=0; -my $outputfile=0; -my @process=(); -my $reset; -my $interactive=0; - -#read configuration files########################### -my $file; -my @process_conf=(); -foreach $file ($systemconfigfile, $userconfigfile){ - if(open(CONFIG, $file)){ - while () { - chomp; - s/#.*//; - s/^\s+//; - s/\s+$//; - next unless length; - my ($name, $value) = split(/\s*=\s*/, $_, 2); - if(($name eq "inputfile")or($name eq "f")){ - $inputfile=$value; - } - elsif(($name eq "outputfile")or($name eq "o")){ - $outputfile=$value; - } - elsif(($name eq "process")or($name eq "p")){ - push @process_conf, $value; - } - elsif(($name eq "reset")or($name eq "r")){ - $reset=$value; - } - elsif(($name eq "interactive")or($name eq "i")){ - $interactive=1; - } - elsif(($name eq "help")or($name eq "h")){ - $help=1; - } - - } - close CONFIG; - } -} -######################################################### - - - -GetOptions("process|p=s" => \@process, - "inputfile|f=s" => \$inputfile, - "outputfile|o=s" => \$outputfile, - "help|h" => \$help, - "reset|r=s" => \$reset, - "interactive|i" => \$interactive); - -@process = @process_conf if @process<1; - -if($help) -{ - print <<'END' -Usage: gph [OPTIONS] - -Options: - --process=TYPE -p TYPE Process segments of type TYPE. - --reset=TYPE -r TYPE Start new graph at tags of type TYPE. - --inputfile=FILE -f FILE Input file. - --outputfile=FILE -o FILE Output file. - --interactive -i Toggle interactive mode (default=off). -END -; - exit 0; -} - - -$|=1 if $interactive; - - -if(!$inputfile or $inputfile eq "-") { - *INPUT = *STDIN; -} -else { - open(INPUT, "$inputfile") or die("Can't open input file: $inputfile!"); -} - -if(!$outputfile or $outputfile eq "-") { - *OUTPUT = *STDOUT; -} -else { - open(OUTPUT, "$outputfile") or die("Can't open output file: $outputfile!"); -} - -my @prev; -my $n=0; - -while() -{ - chomp; - my $do=0; - - my @line = split /\s+/; - - if($line[2] eq $reset) - { - $n=0; - @prev = (); - } - - for my $p (@process) - { - $do=1 if $line[2] eq $p; - } - - my $gph = ''; - if($do) - { - my @preds = (); - shift @prev while @prev+0 && $prev[0]->[1] + $prev[0]->[2] < $line[0]; - for my $p (@prev) - { - push(@preds, $p->[0]) if $p->[1] + $p->[2] == $line[0]; - } - push @prev, [$n, $line[0], $line[1]]; - - $gph=' gph:'.$n.':'.join(',',@preds); - - $n++; - } - else - { - for my $p (@prev) - { - if($p->[1]+$p->[2] == $line[0]) - { - $p->[2] += $line[1]; - } - } - - $gph=''; - - } - - print OUTPUT $_.$gph."\n"; -} - Index: c/grp.pl =================================================================== --- src/grp.pl (revision ac9a049dc70613b4b6ef600978b199a291eed2f0) +++ (revision ) @@ -1,170 +1,0 @@ -#!/usr/bin/perl - -#package: UAM Text Tools -#component name: grp -#version: 1.0 -#author: Tomasz Obrebski - -use strict; -use Getopt::Long; -use File::HomeDir; - -# katalog zawierajacy terms.m4 -my $LIB_DIR="/usr/local/lib/utt"; - -my $systemconfigfile="/usr/local/etc/utt/grp.conf"; -my $userconfigfile=home()."/.utt/grp.conf"; - -Getopt::Long::Configure('no_ignore_case_always'); - -my $help=0; -my $pattern=0; -my $matches_only=0; -my $macrofile=0; -my $define=0; -my $show_command=0; -my $action="pgP"; -my $eos="seg(EOS)"; -my $morfield='lem'; -my $tags=0; - -#read configuration files########################### -my $file; -foreach $file ($systemconfigfile, $userconfigfile){ - if(open(CONFIG, $file)){ - while () { - chomp; - s/#.*//; - s/^\s+//; - s/\s+$//; - next unless length; - my ($name, $value) = split(/\s*=\s*/, $_, 2); - if(($name eq "pattern")or($name eq "e")){ - $pattern=$value; - } - elsif(($name eq "eos")or($name eq "E")){ - $eos=$value; - } - elsif($name eq "morph"){ - $morfield=$value; - } - elsif($name eq "macros"){ - $macrofile=$value; - } - elsif($name eq "define"){ - $define=$value; - } - elsif($name eq "command"){ - $show_command=1; - } - elsif($name eq "action"){ - $action; - } - elsif($name eq "tags"){ - $tags=$value; - } - elsif(($name eq "help")or($name eq "h")){ - $help=1; - } - - } - close CONFIG; - } -} -######################################################### - -GetOptions("pattern|e=s" => \$pattern, - "eos|E=s" => \$eos, - "morph=s" => \$morfield, - "macros=s" => \$macrofile, - "define=s" => \$macrofile, - "command" => \$show_command, - "action=s" => \$action, - "tags=s" => \$tags, - "help|h" => \$help); - -if($help) -{ - print <<'END' -Usage: gre [OPTIONS] [file ..] - -Options: - --pattern -e PATTERN Pattern. - --eos -E PATTERN Segment serving as sentence delimiter. - --morph=STRING Field containing morphological information (default 'lem'). - --macros=FILE Read macrodefinitions from FILE. - --define=FILE Add macrodefinitions from FILE. - --action -a [u][p][g][P] Perform only indicated actions. - u - uncompress with 'lzop -cd' - p - preprocess - g - grep - P - postprocess - (default pgP) - --tags=STRING Morphosyntactic tag format. - --command Print the shell command to be executed and exit. - --help -h Help. -END -; - exit 0; -} - -die("$0: no pattern given.\n") unless $pattern || $action !~ /g/; - -die("$0: macro file not found") unless - $macrofile or - -e "$LIB_DIR/terms.m4" and $macrofile="$LIB_DIR/terms.m4"; - -die("$0: undefined tagset format (tags option missing)") unless - $tags; - -die("$0: $tags.tag2re program not found") unless - 1; #JAK NAPISAC WARUNEK??? - - -my $uncompress = ($action =~ /u/) ? ' lzop -cd | ' : ''; -my $preproc = ($action =~ /p/) ? ' fla | ' : ''; - -my $postproc = ($action =~ /P/) ? ' | unfla ' : ''; - - -# discarding spaces -$pattern =~ s/\s+/\\`'/g; #` -# quoting escaped commas -$pattern =~ s/\\,/\\`\\`\\,''/g; -# quoting commas in {m,n} r.e. operator -$pattern =~ s/(\{\d*),(\d*\})/\1\\`\\`,''\2/g; - -my $grepre = `echo \"$pattern\" | m4 --define=ENDOFSEGMENT='[[:cntrl:]]' --define=MORFIELD=$morfield $macrofile - 2>/dev/null`; - -die("Incorrect pattern (m4).") if $? >> 8; - - -chomp $grepre; - -# <> expansion - -$grepre =~ s/<([^>]+)>/`echo $1 | $tags.tag2re`/ge; - -$grepre =~ s/\./[^ [:cntrl:]]/g; - -$grepre =~ s/\\s/[ ]/g; -$grepre =~ s/\\S/[^ [:cntrl:]]/g; -$grepre =~ s/\\d/[0-9]/g; -$grepre =~ s/\\D/[^0-9 [:cntrl:]]/g; -$grepre =~ s/\\w/[a-z±æê³ñ󶌿A-Z¡ÆÊ£ÑÓŠ¬¯0-9_]/g; -$grepre =~ s/\\W/[^a-z±æê³ñ󶌿A-Z¡ÆÊ£ÑÓŠ¬¯0-9_ [:cntrl:]]/g; -# extensions -$grepre =~ s/\\l/[a-z±æê³ñ󶌿]/g; #lowercase letter -$grepre =~ s/\\L/[A-Z¡ÆÊ£ÑÓŠ¬¯]/g; #upercase letter - -my $grep_command = ($action =~ /g/) ? "egrep '$grepre'" : " cat "; - -if($show_command) -{ - print $grep_command."\n"; - exit 0; -} - -#print $preproc.$grep_command.$postproc."\n"; - -exec $preproc.$grep_command.$postproc; Index: c/kon.pl =================================================================== --- src/kon.pl (revision 8e1730ce813e73fcd85ac2bc9142259b49434f09) +++ (revision ) @@ -1,557 +1,0 @@ -#!/usr/bin/perl -w - -#package: UAM Text Tools -#component: kon (search context) -#version: 1.0 -#author: Justyna Walkowska - -use strict; -use Getopt::Long; -use locale; -use File::HomeDir; - -Getopt::Long::Configure('no_ignore_case_always'); - -my $l='30c'; -my $r='30c'; -my $trim=0; -my $white=0; -my $bon='[0-9]+ [0-9]+ BOM .*'; -my $eon='[0-9]+ [0-9]+ EOM .*'; -my $bod='['; -my $eod=']'; -my $column=0; -my $ignore=0; -my $help=0; - -my $systemconfigfile='/usr/local/etc/utt/kon.conf'; -#my $userconfigfile="$ENV{'HOME'}/.utt/kon.conf"; -my $userconfigfile=home()."/.utt/kon.conf"; - -#read configuration files########################### -my $file; -foreach $file ($systemconfigfile, $userconfigfile){ - if(open(CONFIG, $file)){ - while () { - chomp; - s/#.*//; - s/^\s+//; - s/\s+$//; - next unless length; - my ($name, $value) = split(/\s*=\s*/, $_, 2); - if(($name eq "left")or($name eq "l")){ - $l=$value; - } - elsif(($name eq "right")or($name eq "r")){ - $r=$value; - } - elsif(($name eq "trim")or($name eq "t")){ - $trim=1; - } - elsif(($name eq "white")or($name eq "w")){ - $white=1; - } - elsif($name eq "bom"){ - $bon=$value; - } - elsif($name eq "eom"){ - $eon=$value; - } - elsif($name eq "bod"){ - $bod=$value; - } - elsif($name eq "eod"){ - $eod=$value; - } - elsif(($name eq "column")or($name eq "c")){ - $column=$value; - } - elsif(($name eq "ignore")or($name eq "i")){ - $ignore=1; - } - elsif(($name eq "help")or($name eq "h")){ - $help=1; - } - - } - close CONFIG; - } -} -######################################################### - -GetOptions("left|l=s" => \$l, - "right|r=s" => \$r, - "trim|t" => \$trim, - "white|w" => \$white, - "bom=s" => \$bon, - "eom=s" => \$eon, - "bod=s" => \$bod, - "eod=s" => \$eod, - "column|c=s" => \$column, - "ignore|i" => \$ignore, - "help|h" => \$help); - -if(!($column=~/^[0-9]+$/)){$column=0;} - -if($help) -{ - print <<'END' -Options: - --help -h Help. - --left -l Left context info (default='30c') - Examples: - -l=5c: left context is 5 characters - -l=5w: left context is 5 words - -l=5s: left context is 5 non-empty input lines - -l='\s*\S+\sr\S+BOS': left context starts with the given regex - --right -r Right context info (default='30c') - --trim -t Clear incomplete words from output - --white -w DO NOT change all white characters into spaces - --column -c Left column minimal width in characters (default = 0) - --ignore -i Ignore input inconsistency - --bon Beginning of selected segment - (regex, default='[0-9]+ [0-9]+ BOM .*') - --eon End of selected segment - (regex, default='[0-9]+ [0-9]+ EOM .*') - --bod Selected segment beginning display (default='[') - --eod Selected segment end display (default=']') - -END -; - exit 0; -} - - -my $seg_no=0; -my $seg_size=0; - -my $left_type; -my $left_size; -my $right_type; -my $right_size; - -set_lr_types($l, $r, \$left_type,\$left_size,\$right_type,\$right_size, $trim); - - -my $inn=0; -my $after_bos=0; -my $before_eos=0; - -my @LEFT; #tablica skalarów -my @CENTER; #tablica skalarów -my @RIGHT; - -my @current_center; -my @current_left; #skalar dla c, w pp. tablica -my @current_left_words; -my @current_right_words_number; - - -while(<>){ - my $line = $_; - chomp $line; - my @line = split / /, $line; - my $line_s=@line; - - if(!line_format_ok(@line)){next;} - - if(!$white){white_into_spaces(\@line);} - else{if($line[2] eq "S"){symbols_into_white(\$line[3]);}} - - if(!input_consistent(\$seg_no,\$seg_size,$line[0],$line[1],$ignore)){ - eof_or_inconsistency(\@LEFT,\@CENTER,\@RIGHT,$bod,$eod,$white,$column,$trim,$left_type,$right_type); - @current_center=(); - @current_left=(); - @current_left_words=(); - @current_right_words_number=(); - $after_bos=0; - $before_eos=0; - } - - remember_current_left($left_type,$left_size,\@current_left,\@line, \@current_left_words, $line, \$after_bos, \$before_eos); - remember_center($line,\@line,\$inn,\@current_center,$white,\@CENTER,\@current_left,\@LEFT, \$after_bos, \$before_eos, \@RIGHT, \@current_right_words_number); - remember_right($right_type,$left_type,$right_size,\@line,\@LEFT,\@CENTER,\@RIGHT,$bod,$eod,$white,$column,$trim,\@current_right_words_number, $line, \$before_eos); -} - -eof_or_inconsistency(\@LEFT,\@CENTER,\@RIGHT,$bod,$eod,$white,$column,$trim,$left_type,$right_type); -exit(0); - -#################procedury############################### - -sub line_format_ok{ - my @line = @_; - my $size = @line; - if($size<4){return 0;} - if($line[0]!~/[0-9]+/){return 0;} - if($line[1]!~/[0-9]+/){return 0;} - return 1; - } - -sub white_into_spaces{ - my $line_ref=shift; - if(@{$line_ref}[2] eq "S"){ - @{$line_ref}[3]=" "; - } - } - -sub symbols_into_white{ - my $string_ref=shift; - ${$string_ref} =~ s/\\n/\n/g; - ${$string_ref} =~ s/\\t/\t/g; - ${$string_ref} =~ s/_/ /g; - } - -sub white_into_symbols{ - my $string_ref=shift; - ${$string_ref} =~ s/\n/\\n/g; - ${$string_ref} =~ s/\t/\\t/g; - ${$string_ref} =~ s/ /_/g; - } - -sub input_consistent{ - my $seg_no_ref = shift; - my $seg_size_ref = shift; - my $line0 = shift; - my $line1 = shift; - my $ig = shift; - my $ok=1; - - if(${$seg_no_ref}!=0&&(!$ig)){ - my $distance = $line0-${$seg_size_ref}; - if($distance!=${$seg_no_ref}){$ok=0;} - } - ${$seg_no_ref}=$line0; - ${$seg_size_ref}=$line1; - return $ok; - } - -sub set_lr_types{ - my $left = shift; - my $right = shift; - my $left_type_ref =shift; - my $left_size_ref =shift; - my $right_type_ref =shift; - my $right_size_ref =shift; - my $do_trim=shift; - - if($left=~/[0-9]+c/){ - ${$left_type_ref}='c'; - ${$left_size_ref}=get_number($left); - if($do_trim){${$left_size_ref}++;} - } - else{ - if($left=~/[0-9]+w/){ - ${$left_type_ref}='w'; - ${$left_size_ref}=get_number($left); - } - else{ - if($left=~/[0-9]+s/){ - ${$left_type_ref}='s'; - ${$left_size_ref}=get_number($left); - } - else{ - ${$left_type_ref}=$left; - } - } - } - -if($right=~/[0-9]+c/){ - ${$right_type_ref}='c'; - ${$right_size_ref}=get_number($right); - if($do_trim){${$right_size_ref}++;} - } - else{ - if($right=~/[0-9]+w/){ - ${$right_type_ref}='w'; - ${$right_size_ref}=get_number($right); - } - else{ - if($right=~/[0-9]+s/){ - ${$right_type_ref}='s'; - ${$right_size_ref}=get_number($right); - } - else{ - ${$right_type_ref}=$right; - } - } - } - } - -sub get_number{ - my $string = shift; - my @letters = split(//,$string); - my $i=0; - while($letters[$i]=~/[0-9]/){$i++;} - my $j; - my $number=0; - my $ten=1; - for($j=$i-1;$j>=0;$j--){ - $number+=$letters[$j]*$ten; - $ten*=10; - } - return $number; - } - -sub remember_center{ - my $lin = shift; - my $lin_ref = shift; - my $inn_ref = shift; - my $current_center_ref = shift; - my $white_info = shift; - my $CENTER_REF = shift; - my $current_left_ref = shift; - my $LEFT_REF = shift; - my $after_bos_ref = shift; - my $before_eos_ref = shift; - my $RIGHT_REF = shift; - my $current_words_right_number_ref = shift; - - if((!${$inn_ref}) && $lin=~/$bon/){ - ${$inn_ref}=1; - @{$current_center_ref}=(); - ${$after_bos_ref}=0; - - push(@{$LEFT_REF},join('',@{$current_left_ref})); - - } - if(${$inn_ref} && $lin=~/$eon/){ - ${$inn_ref}=0; - push(@{$CENTER_REF},join('',@{$current_center_ref})); - ${$before_eos_ref}=1; - my @new_table; - push(@{$RIGHT_REF},\@new_table); - push(@{$current_words_right_number_ref},0); - } - if($inn && index($lin,'*')==-1){ - white_into_symbols(\${$lin_ref}[3]); - if($white_info){push(@{$current_center_ref},${$lin_ref}[3]);} - else{push(@{$current_center_ref},${$lin_ref}[3]);} - } - } - -sub remember_current_left{ -my $type=shift; -my $size=shift; -my $ref=shift; -my $line_ref=shift; - if($type eq 'c'){ - if(!(${$line_ref}[3] eq '*')){ - push(@{$ref},split('',${$line_ref}[3])); - my $lsize = @{$ref}; - if($lsize>$size){splice(@{$ref},0,$lsize-$size);} - } - } - else{ - if($type eq 'w'){ - my $words_ref = shift; - if(!(${$line_ref}[3] eq '*')){ - push(@{$ref},${$line_ref}[3]); - if(${$line_ref}[2] eq 'W'){ - push(@{$words_ref},${$line_ref}[3]); - } - my $lsize = @{$words_ref}; - if($lsize>$size){ - my $word = ${$words_ref}[1]; - splice(@{$words_ref},0,1); - while(!(${$ref}[0] eq $word)){splice(@{$ref},0,1); } - } - } - - } - else{ - if($type eq 's'){ - if(!(${$line_ref}[3] eq '*')){ - push(@{$ref},${$line_ref}[3]); - my $lsize = @{$ref}; - if($lsize>$size){splice(@{$ref},0,$lsize-$size);} - } - } - else{#bos/eos - shift; - my $line = shift; - my $after_bos_ref = shift; - my $before_eos_ref = shift; - if($line=~/$type/){ - ${$after_bos_ref}=1; - @{$ref}=(); - } - if(${$after_bos_ref} && !(${$line_ref}[3] eq '*')){ - push(@{$ref},${$line_ref}[3]); - } - } - } - } - } - -sub remember_right{ -my $type=shift; -my $type_left=shift; -my $size=shift; -my $line_ref=shift; -my $LEFT_REF=shift; -my $CENTER_REF=shift; -my $RIGHT_REF=shift; -my $bod=shift; -my $eod=shift; -my $w=shift; -my $c=shift; -my $t=shift; - - if($type eq 'c'){ - if(!(${$line_ref}[3] eq '*')){ - my $right_size = @{$RIGHT_REF}; - for(my $i=0; $i<$right_size; $i++){ - push(@{${$RIGHT_REF}[$i]}, split('',${$line_ref}[3])); - my $lsize = @{${$RIGHT_REF}[$i]}; - if($lsize>=$size){ - splice(@{${$RIGHT_REF}[$i]},$size-1); #wypisz i usun - print_and_remove($i,$LEFT_REF,$CENTER_REF,$RIGHT_REF,$bod,$eod,$w,$c,$t,$type_left,$type); - $right_size = @{$RIGHT_REF}; - $i--; - } - } - } - } - else{ - if($type eq 'w'){ - my $words_number_ref = shift; - if(!(${$line_ref}[3] eq '*')){ - my $right_size = @{$RIGHT_REF}; - for(my $i=0; $i<$right_size; $i++){ - push(@{${$RIGHT_REF}[$i]},${$line_ref}[3]); - if(${$line_ref}[2] eq 'W'){ - ${$words_number_ref}[$i]=${$words_number_ref}[$i]+1; - if(${$words_number_ref}[$i]==$size){ - print_and_remove($i,$LEFT_REF,$CENTER_REF,$RIGHT_REF,$bod,$eod,$w,$c,$t,$type_left,$type); - $right_size = @{$RIGHT_REF}; - $i--; - splice(@{$words_number_ref},$i,1); - } - } - } - } - } - else{ - if($type eq 's'){ - if(!(${$line_ref}[3] eq '*')){ - my $right_s = @{$RIGHT_REF}; - for(my $i=0; $i<$right_s; $i++){ - push(@{${$RIGHT_REF}[$i]},${$line_ref}[3]); - my $rsize=@{${$RIGHT_REF}[$i]}; - if($rsize==$size){ - print_and_remove($i,$LEFT_REF,$CENTER_REF,$RIGHT_REF,$bod,$eod,$w,$c,$t,$type_left,$type); - $right_s = @{$RIGHT_REF}; - $i--; - } - } - } - } - else{#bos/eos - shift; - my $line = shift; - my $before_eos_ref = shift; - if(${$before_eos_ref}){ - if(!(${$line_ref}[3] eq '*')){ - #tylko 1 pozycja - push(@{${$RIGHT_REF}[0]},${$line_ref}[3]); - } - if($line=~/$type/){ - ${$before_eos_ref}=0; - print_and_remove(0,$LEFT_REF,$CENTER_REF,$RIGHT_REF,$bod,$eod,$w,$c,$t,$type_left,$type); - } - } - } - } - } -} - -sub print_and_remove{ - my $index = shift; - my $LEFT_REF = shift; - my $CENTER_REF = shift; - my $RIGHT_REF = shift; - my $bdis = shift; - my $edis = shift; - my $white = shift; - my $column = shift; - my $trim = shift; - my $left_type = shift; - my $right_type = shift; - - my $left_string = "${$LEFT_REF}[$index]"; - my $right_string = join('',@{${$RIGHT_REF}[$index]}); - - if($trim){ - if($left_type eq "c"){$left_string=trim_left($left_string);} - if($right_type eq "c"){$right_string=trim_right($right_string);} - } - - if(length($left_string)<$column){$left_string=" "x($column-length($left_string)).$left_string;} - - if($white){ - white_into_symbols(\$left_string); - white_into_symbols(\$right_string); -#ponizsza linijka dodana 18 listopada - white_into_symbols(\${$CENTER_REF}[$index]); - } - - print $left_string; - print $bdis; - -#ponizsza 3 linijki (tj. 1 blok) dodana 18 listopada - if(!$white){ - symbols_into_white(\${$CENTER_REF}[$index]); - } - - print "${$CENTER_REF}[$index]"; - print $edis; - print $right_string; - print "\n"; - - splice(@{$LEFT_REF},$index,1); - splice(@{$CENTER_REF},$index,1); - splice(@{$RIGHT_REF},$index,1); - } - -sub trim_left{ - my $string = shift; - if(substr($string,0,1) eq " "){return substr($string,1);} - my $position = index($string," "); - my $temp_position = index($string,"\n"); - if(!$temp_position==-1&&($position==-1||$temp_position<$position)){$position=$temp_position;} - $temp_position = index($string,"\t"); - if(!$temp_position==-1&&($position==-1||$temp_position<$position)){$position=$temp_position;} - return substr($string,$position+1); - } - -sub trim_right{ - my $string = shift; - my $length = length($string); - if(substr($string,$length-1,1) eq " "){return substr($string,0,$length-1);} - my $position = rindex($string," "); - my $temp_position = rindex($string,"\n"); - if($temp_position>$position){$position=$temp_position;} - $temp_position = rindex($string,"\t"); - if($temp_position>$position){$position=$temp_position;} - return substr($string,0,$position); - } - -sub eof_or_inconsistency{ - my $LEFT_REF = shift; - my $CENTER_REF = shift; - my $RIGHT_REF = shift; - my $bdis = shift; - my $edis = shift; - my $white = shift; - my $column = shift; - my $trim = shift; - my $left_type = shift; - my $right_type = shift; - - my $length = @{$CENTER_REF}; - for(my $i=0;$i<$length;$i++){ - print_and_remove(0,$LEFT_REF,$CENTER_REF,$RIGHT_REF,$bdis,$edis,$white,$column,$trim,$left_type,$right_type); - $length = @{$CENTER_REF}; - $i--; - } - } Index: c/kot.pl =================================================================== --- src/kot.pl (revision 3a2ae91d9423fabcf92fcfb2b04614a3c5a3696a) +++ (revision ) @@ -1,102 +1,0 @@ -#!/usr/bin/perl - -#package: UAM Text Tools -#component: kot -#version: 1.0 -#author: Tomasz Obrebski - -use strict; -use Getopt::Long; -use File::HomeDir; - -my $help=0; -my $gap_fill="\n-----\n"; -my $spaces=0; - -my $systemconfigfile='/usr/local/etc/utt/kot.conf'; -#my $userconfigfile="$ENV{'HOME'}/.utt/kot.conf"; -my $userconfigfile=home()."/.utt/kot.conf"; - -#read configuration files########################### -my $file; -foreach $file ($systemconfigfile, $userconfigfile){ - if(open(CONFIG, $file)){ - while () { - chomp; - s/#.*//; - s/^\s+//; - s/\s+$//; - next unless length; - my ($name, $value) = split(/\s*=\s*/, $_, 2); - if(($name eq "gap-fill")or($name eq "g")){ - $gap_fill=$value; - } - elsif(($name eq "spaces")or($name eq "s")){ - $spaces=1; - } - elsif(($name eq "help")or($name eq "h")){ - $help=1; - } - - } - close CONFIG; - } -} -######################################################### - -GetOptions("gap-fill|g=s" => \$gap_fill, - "spaces|r" => \$spaces, - "help|h" => \$help); - -if($help) -{ - print <<'END' -Usage: ser [OPTIONS] [file ..] - -Options: - --gap-fill -g Help. - --spaces -r - --define=FILE Read macrodefinitions from FILE. - --flex-template=FILE Read flex code template from FILE. - --only-matching -m Print only fragments matching PATTERN. - --flex Print only the generated flex code and exit. -END -; - exit 0; -} - - -$gap_fill =~ s/\\t/\t/g; -$gap_fill =~ s/\\n/\n/g; -$gap_fill =~ s/\\r/\r/g; -$gap_fill =~ s/\\f/\f/g; - -my $prevend=-1; -my $count=0; - -while(<>) -{ - my ($start,$len,$type,$form) = /^\s*(\d+)\s+(\d+)\s+(\S+)\s+(\S+)/; - - if($start > $prevend) - { - print $gap_fill unless $count++ == 0; - } - - $prevend=$start+$len; - - next if $len==0;# || $form eq "*"; - - $form =~ s/\\\*/*/g; - - if($type eq 'S' && ! $spaces) - { - $form =~ s/_/ /g; - $form =~ s/\\t/\t/g; - $form =~ s/\\n/\n/g; - $form =~ s/\\r/\r/g; - $form =~ s/\\f/\f/g; - } - - print $form; -} Index: c/mar.pl =================================================================== --- src/mar.pl (revision dc2176950fd43bdb6684b7730f37aaa88239b818) +++ (revision ) @@ -1,336 +1,0 @@ -#!/usr/bin/perl - -#package: UAM Text Tools -#component: mar -#version: 1.0 -#author: Marcin Walas - -#this program tags the tokenized file with given tags -#tags can be given in any order and configuration through the expression -#which is one of the parametres of the script -#contact: d287572@atos.wmid.amu.edu.pl, walasiek@gmail.com - -my $version = '1.0'; - -use lib "/usr/local/lib/utt"; -use lib "$ENV{'HOME'}/.local/lib/utt"; - -use strict; -use Getopt::Long; -use File::HomeDir; - -use attr; - - -my $LIB_DIR="/usr/local/lib/utt"; -my $systemconfigfile='/usr/local/etc/utt/mar.conf'; -my $userconfigfile=home()."/.utt/mar.conf"; - -Getopt::Long::Configure('no_ignore_case_always'); - -my $help=0; -my $pattern=0; -my $macrofile=0; -my $define=0; -my $command=0; -my $action="pgP"; -my $eos="seg(EOS)"; -my $explicit_space=0; -my $morfield='lem'; -my $tags=0; -my $show_version = 0; - -#read configuration files########################### -my $file; -foreach $file ($systemconfigfile, $userconfigfile){ - if(open(CONFIG, $file)){ - while () { - chomp; - s/#.*//; - s/^\s+//; - s/\s+$//; - next unless length; - my ($name, $value) = split(/\s*=\s*/, $_, 2); - if(($name eq "pattern")or($name eq "e")){ - $pattern=$value; - } - elsif($name eq "eos"){ - $eos=$value; - } - elsif($name eq "macros"){ - $macrofile=$value; - } - elsif($name eq "tags"){ - $tags=$value; - } - elsif($name eq "morph"){ - $morfield=$value; - } - elsif($name eq "command"){ - $command=1; - } - elsif($name eq "action"){ - $action=$value; - } - elsif($name eq "space"){ - $explicit_space=1; - } - elsif(($name eq "help")or($name eq "h")){ - $help=1; - } - - } - close CONFIG; - } -} -######################################################### - -GetOptions("pattern|e=s" => \$pattern, - "eos|E=s" => \$eos, - "macros=s" => \$macrofile, - "define=s" => \$macrofile, - "command" => \$command, - "action=s" => \$action, - "help|h" => \$help, - "space|s" => \$explicit_space, - "version|v" => \$show_version, - ); - - - -if($show_version){ - print "Version: $version\n"; - exit 0; -} - -if($help) -{ - print <<'END' -Usage: mar [OPTIONS] [file ..] - -Options: - --pattern -e PATTERN Pattern. - --eos -E PATTERN Segment serving as sentence beginning marker. [TODO] - --macros=FILE Read macrodefinitions from FILE. [TODO] - --define=FILE Add macrodefinitions from FILE. [TODO] - --action -a [p][s][P] Perform only indicated actions. - p - preprocess - s - search - P - postprocess - (default psP) - --command Print generated shell command and exit. - --help -h Print help. - --version -v Script version - -In patern you can put any tag. Tags should begin with the @ character. -They don't have to be closed. -They can't contain white spaces! - -Note: If you don't define any custom tags, whole pattern will be taged with - default tags (begining of match and end of match) - -Tags examples: - -mar -e '@BEG cat() @END' - it will find any adjectives in the text and tag them with surrounding tags -mar -e 'cat() @MYTAG cat()' - this will find two neighbouring adjectives and parcel them with tag MYTAG - -Some example patterns: -'word(domu)' - form of the word domu -'lexeme(dom)' - any form of lexeme dom -'space' - space -'cat()' - adjective - -You can use * in patterns to make zero or more counts of word. - -END -; - exit 0; -} - -die("$0: no pattern given. Run with -h to get help.\n") unless $pattern || $action !~ /g/; - -die("$0: macro file not found") unless - $macrofile or - -e "$LIB_DIR/terms.m4" and $macrofile="$LIB_DIR/terms.m4"; - -my $preproc = ($action =~ /p/) ? ' fla | ' : ''; - -my $postproc = ($action =~ /P/) ? ' | unfla ' : ''; - - -#this is our help function to cut the re to get another tag -#it takes only one argument which is our patern (after m4 processing) -#returns: the first root-level brace with content -sub cutRe -{ - my $i = 0; - my $level = 0; - my $text = $_[0]; - my $temp; - for( $i =0; $i < (length $text);$i++) - { - $temp = substr($text, $i,1); - if( $temp eq "(") - {#we have an opening - $level++; - } - elsif ( $temp eq ")") - {#we close - $level--; - } - if ( $level == 0) - { - $temp = substr($text,0,$i+1); - last; - } - } - $temp; -} - -#the same function as above althought it returns everything after the -#first root level brace -sub restRe -{ - my $i = 0; - my $level = 0; - my $text = $_[0]; - my $temp; - for( $i =0; $i < (length $text);$i++) - { - $temp = substr($text, $i,1); - if( $temp eq "(") - {#we have an opening - $level++; - } - elsif ( $temp eq ")") - {#we close - $level--; - } - if ( $level == 0) - { #we cut everything in the begining - $temp = substr($text,$i+1); - last; - } - } - $temp; -} - - -#here we are preparing re for extended matching -my @tags; - -#we must find what our the tags -#some pattern adjustment -my $end = 0; -my $temp = " ".$pattern." "; -$temp =~ s/(\@[^ ]*) (\@[^ ]* )/\1 \2/g; -$pattern = $temp; - -while ($end != 1) -{ - #we seek for the first tag in pattern - if ($temp =~ /^.*?\@(.*?) /) - { - #we add this to tags array - push (@tags, $1); - #and cut the pattern - $temp =~ s/^.*?\@(.*?) / /; - #print $temp."\n"; - } - else - { - #if we dont find any tags we end - $end = 1; - } -} - -#here we have our patern with tags removed (we set sections of ()) between tags -my $patternmod = "( ".$pattern." )"; -$patternmod =~ s/\s@.*?\s/\)\(/g; - -#discarding spaces -$patternmod =~ s/\s+/\\`'/g; #` -# quoting escaped commas -$patternmod =~ s/\\,/\\`\\`\\,''/g; -# quoting commas in {m,n} r.e. operator -$patternmod =~ s/(\{\d*),(\d*\})/\1\\`\\`,''\2/g; -#print "After m4:".$re."\n"; - -my $re = `echo \"$patternmod\" | m4 --define=ENDOFSEGMENT='[[:cntrl:]]' --define=MORFIELD=$morfield $macrofile - 2>/dev/null`; - -die("Incorrect pattern (m4).") if $? >> 8; - - -chomp $re; - -# <> expansion - -$re =~ s/<([^>]+)>/`echo $1 | $tags.tag2re`/ge; - -# Perl-like special sequences -$re =~ s/\./[^ [:cntrl:]]/g; -$re =~ s/\\s/[ ]/g; -$re =~ s/\\S/[^ [:cntrl:]]/g; -$re =~ s/\\d/[0-9]/g; -$re =~ s/\\D/[^0-9 [:cntrl:]]/g; -$re =~ s/\\w/[a-z±æê³ñ󶌿A-Z¡ÆÊ£ÑÓŠ¬¯0-9_]/g; -$re =~ s/\\W/[^a-z±æê³ñ󶌿A-Z¡ÆÊ£ÑÓŠ¬¯0-9_ [:cntrl:]]/g; -# extensions -$re =~ s/\\l/[a-z±æê³ñ󶌿]/g; #lowercase letter -$re =~ s/\\L/[A-Z¡ÆÊ£ÑÓŠ¬¯]/g; #upercase letter - -my $sedcommand; -my $grepcommand; - -#now we must built a sed script from our re -#we do this by cuting our re each tag until we cut them all -#if an user dint input any tags we do our default -my $defBOM = "BOM"; -my $defEOM = "EOM"; -my $defTempTagBeg = "####TempTAGBEG####"; -my $defTempTagEnd = "####TempTAGEND####"; - -if (@tags == 0) -{ - $sedcommand = "sed -r 's/($re)/\\500 $defBOM *\\f\\1###EOM###/g; s/###EOM###([0-9]+)/\\1 00 $defEOM *\\f\\1/g'"; -} -else #we have custom tags -{ - #first tag is easy to tag :) - my $sedscript="sed -r 's/($re)/\\600 $defTempTagBeg *\\f\\1###EOM###/g;s/###EOM###([0-9]+)/\\1 00 $defTempTagEnd *\\f\\1/g;"; - #after first step we have temp tagged parts of input matching re - #now we need to insert our custom tags - #we will find temp tags and process our input - - my $i = 0; - #copy of re which will be cut - my $rec = $re; - my $restre = $re; - - for ($i = 0 ; $i < @tags ; $i++) - { - #re cutting - $rec = cutRe($restre); - $restre = restRe($restre); - if ($rec =~ / *\( *\) */) - { - $sedscript = $sedscript."s/([0-9]+) 00 $defTempTagBeg \\*\\f([0-9]+)/\\2 00 $tags[$i] *\\f\\2 00 $defTempTagBeg *\\f\\2/g;"; - } - else - { - $sedscript = $sedscript."s/[0-9]+ 00 $defTempTagBeg \\*\\f($rec)/\\1###EOM###/g;s/###EOM###([0-9]+)/\\1 00 $tags[$i] *\\f\\1 00 $defTempTagBeg *\\f\\1/g;"; - } - - } - - $sedcommand = $sedscript."s/[0-9]+ 00 $defTempTagBeg \\*\\f//g;s/[0-9]+ 00 $defTempTagEnd \\*\\f//g'"; -} - -if($command) -{ - print $sedcommand."\n"; - exit 0; -} -exec $preproc.$sedcommand.$postproc; Index: c/rm12.sed =================================================================== --- src/rm12.sed (revision 4518a0b7b6b78168b5b4cc330fc97d43cb5c9183) +++ (revision ) @@ -1,10 +1,0 @@ -#!/bin/sed -rf - -#package: UAM Text Tools -#component: rm12 -#version: 1.0 -#author: Tomasz Obrebski - - -/[0-9]+[ \t]+[0-9]+[ \t]+BOS/! -s/[0-9]+[ \t]+[0-9]+[ \t]// Index: c/rs12.c =================================================================== --- src/rs12.c (revision b5884b3fd633a968051fc3f1574733eea13b0230) +++ (revision ) @@ -1,66 +1,0 @@ -#include -#include -#include - -#define MAXLINE 1000 - -int main() -{ - char buf[MAXLINE]; - char outbuf[MAXLINE]; - char form[MAXLINE]; - int len; - int curpos; - int nextpos=0; - int a; - int b; - - while( fgets(buf, MAXLINE, stdin) ) - { - int n = sscanf(buf, "%d %d", &a, &b); - if( 2 == n ) - { - nextpos = a + b; - fputs(buf, stdout); - } - else - { - if( 1 == n ) - { - curpos = a; - sscanf(buf, "%*d %*s %s", form); - } - else - { - curpos = nextpos; - sscanf(buf, "%*s %s", form); - } - - if( '*' == *form ) - { - len = 0; - } - else - { - char *f = form; - for( len = 0; *f; ++f ) - { - if( '\\' != *f) - { - ++len; - } - } - } - - char *buf1 = buf; - while( !isalpha(*buf1) ) - { - ++buf1; - } - sprintf(outbuf, "%04i %02i %s", curpos, len, buf1); - fputs(outbuf, stdout); - nextpos = curpos + len; - } - } - return 0; -} Index: c/sen-nl.sed =================================================================== --- src/sen-nl.sed (revision 743cc4f1c9fc321b759aedbaf8f52e759740d371) +++ (revision ) @@ -1,6 +1,0 @@ -#!/bin/sed -rf - -1 s/^(([0-9]+)[ \t][0-9]+[ \t].*)$/\2 00 BOS \*\n\1/ -t -$! s/(([0-9]+)[ \t][0-9]+[ \t][[:alpha:]]+[ \t]+[[:print:]]*\\n.*)$/\2 00 EOS *\n\2 00 BOS *\n\1/ -$ s/^(([0-9]+) .*)$/\1\n\2 00 EOS */' Index: c/sen.l =================================================================== --- src/sen.l (revision 1e551bdd1bf6aaf003fd1ba34eca63b8fcc7b5ba) +++ (revision ) @@ -1,95 +1,0 @@ -%{ - - void print_EOS(void); - void set_position(void); - - int pos=0; - int len=0; - -%} - -ul [A-Z¡ÆÊ£ÑÓŠ¯¬] -ll [a-z±æê³ñ󶿌] -l ul|ll -n [0-9]+ -s [ \t]+ - - -ab1 (mgr|in¿|prof|hab|doc|dyr|kier|zast) -ab2 (ul|pl|al) - -abrv (ab1|ab2) - -SEG .*\n -N {n}{s}{n}{s}N{s}.*\n -S {n}{s}{n}{s}S{s}.*\n -P {n}{s}{n}{s}P{s}.*\n -W {n}{s}{n}{s}W{s}.*\n -UL {n}{s}{n}{s}W{s}{ul}.*\n -Cap {n}{s}{n}{s}W{s}{ul}{ll}*.*\n -POINT {n}{s}{n}{s}P{s}\.({s}.*)?\n -QMARK {n}{s}{n}{s}P{s}\?({s}.*)?\n -EXCL {n}{s}{n}{s}P{s}\!({s}.*)?\n -DASH {n}{s}{n}{s}P{s}\-({s}.*)?\n -POINTS {POINT}+ - -ABRV {n}{s}{n}{s}W{s}{abrv}({s}.*)?\n - -EOS {POINT}|{POINTS}|{QMARK}|{EXCL} - - -%% - - -{N}({POINT}{N})+ { ECHO; set_position(); } -({UL}{POINT}{S}?)+{Cap} { ECHO; set_position(); } -{ABRV}{POINT} { ECHO; set_position(); } - - -{P}/{S}{DASH} { ECHO; set_position(); print_EOS(); } -{EOS}/{S}({Cap}|{P}|{N}) { ECHO; set_position(); print_EOS(); } - -.* { ECHO; set_position(); } - -<> { printf("%04d 00 EOS *\n",pos+len); exit(1); } - -%% - -int main() -{ - printf("0000 00 BOS *\n"); - yylex(); - return 0; -} - -int yywrap() -{ - return 1; -} - -void set_position() -{ - char *lastseg; - char *tmp; - - yytext[yyleng-1] = '\0'; - - tmp = strrchr(yytext, '\n'); - if( tmp ) - { - lastseg = tmp + 1; - } - else - { - lastseg = yytext; - } - - sscanf(lastseg, "%d %d", &pos, &len); - yytext[yyleng-1] = '\n'; - -} - -void print_EOS() -{ - printf("%04d 00 EOS *\n%04d 00 BOS *\n", pos+len, pos+len); -} Index: c/ser.pl =================================================================== --- src/ser.pl (revision 8c8a2529e10decc5c52225e87ea7fb8ce9bf37bb) +++ (revision ) @@ -1,198 +1,0 @@ -#!/usr/bin/perl - -#package: UAM Text Tools -#component: ser (pattern search tool) -#version: 1.0 -#author: Tomasz Obrebski - -use strict; -use Getopt::Long; -use File::Temp; -use File::HomeDir; - -my $LIB_DIR="/usr/local/lib/utt"; -my $systemconfigfile='/usr/local/etc/utt/ser.conf'; -my $userconfigfile=home()."/.utt/ser.conf"; - -Getopt::Long::Configure('no_ignore_case_always'); - -my $help=0; -my $pattern=0; -my $only_matching=0; -my $no_markers=0; -my $macros=0; -my $flextemplate=0; -my $flex=0; -my $morfield='lem'; -my $tags=0; - -#read configuration files########################### -my $file; -foreach $file ($systemconfigfile, $userconfigfile){ - if(open(CONFIG, $file)){ - while () { - chomp; - s/#.*//; - s/^\s+//; - s/\s+$//; - next unless length; - my ($name, $value) = split(/\s*=\s*/, $_, 2); - if(($name eq "pattern")or($name eq "e")){ - $pattern=$value; - } - elsif($name eq "morph"){ - $morfield=$value; - } - elsif(($name eq "only-matching")or($name eq "m")){ - $only_matching=1; - } - elsif(($name eq "no-markers")or($name eq "M")){ - $no_markers=1; - } - elsif($name eq "macros"){ - $macros=$value; - } - elsif($name eq "flex-template"){ - $flextemplate=$value; - } - elsif($name eq "tags"){ - $tags=$value; - } - elsif($name eq "flex"){ - $flex=1; - } - elsif(($name eq "help")or($name eq "h")){ - $help=1; - } - - } - close CONFIG; - } -} -######################################################### - -GetOptions("pattern|e=s" => \$pattern, - "morph=s" => \$morfield, - "only-matching|m" => \$only_matching, - "no-markers|M" => \$no_markers, - "macros=s" => \$macros, - "flex-template=s" => \$flextemplate, - "tags=s" => \$tags, - "flex" => \$flex, - "help|h" => \$help); - -if($help) -{ - print <<'END' -Usage: ser [OPTIONS] [file ..] - -Options: - --help -h Help. - --pattern=PATTERN -e PATTERN Search pattern. - --morph=STRING Field containing morphological information (default 'lem'). - --macros=FILE Read macrodefinitions from FILE. - --flex-template=FILE Read flex code template from FILE. - --tags=STRING Morphosyntactic tag format. - --only-matching -m Print only fragments matching PATTERN. - --no-markers -M Do not print BOM and EOM markers [TODO]. - --flex Print only the generated flex code and exit. -END -; - exit 0; -} - - -die("$0: no pattern given.\n") unless $pattern; - -die("$0: flex template file not found") unless - $flextemplate or - -e "$LIB_DIR/ser.l.template" and $flextemplate="$LIB_DIR/ser.l.template"; - -die("$0: macro file not found") unless - $macros or - -e "$LIB_DIR/terms.m4" and $macros="$LIB_DIR/terms.m4"; - -die("$0: $tags.tag2re program not found") unless - 1; #JAK NAPISAC WARUNEK??? - -die("$0: undefined tagset format (tags option missing)") unless - $tags; - - -#$pattern =~ s/cat\(([^)]+)\)/'cat('.pre($1).')'/ge; -# quoting escaped commas /NIE DZIA£A/ -$pattern =~ s/\\,/\\`\\`\\,''/g; - -# protecting backslash -$pattern =~ s/\\/\\\\\\/g; - -# discarding spaces -$pattern =~ s/\s+/\\`'/g; #` - - -my $flexpattern = `echo \"$pattern\" | m4 --define=ENDOFSEGMENT=\\\\n --define=MORFIELD=$morfield $macros - 2>/dev/null`; - -die("Incorrect pattern (m4).") if $? >> 8; - - -chomp $flexpattern; - -# <> expansion -$flexpattern =~ s/<([^>]+)>/`echo $1 | $tags.tag2re`/ge; - -# restricting the value of the . special symbol -$flexpattern =~ s/\./[^ \\t\\n\\r\\f]/g; - -# perl-like shortcuts for character classes -# perl exact -$flexpattern =~ s/\\s/[ \\t]/g; -$flexpattern =~ s/\\S/[^ \\t\\n\\r\\f]/g; -$flexpattern =~ s/\\d/[0-9]/g; -$flexpattern =~ s/\\D/[^0-9 \\t\\n\\r\\f]/g; -$flexpattern =~ s/\\w/[a-z±æê³ñ󶌿A-Z¡ÆÊ£ÑÓŠ¬¯0-9_]/g; -$flexpattern =~ s/\\W/[^a-z±æê³ñ󶌿A-Z¡ÆÊ£ÑÓŠ¬¯0-9_ \\t\\n\\r\\f]/g; -# extensions -$flexpattern =~ s/\\l/[a-z±æê³ñ󶌿]/g; #lowercase letter -$flexpattern =~ s/\\L/[A-Z¡ÆÊ£ÑÓŠ¬¯]/g; #upercase letter - -# protecting slash -$flexpattern =~ s/\//\\\//g; - -my $defaultaction = ($only_matching) ? '' : 'ECHO'; - -# docelowo posrednie pliki powinny byc w jakims tempie !!! - -(undef, my $tmpfile_l) = File::Temp::tempfile(SUFFIX=>'.l'); -(undef, my $tmpfile_c) = File::Temp::tempfile(SUFFIX=>'.c'); -(undef, my $tmpfile_x) = File::Temp::tempfile(); - -# w tych `` nie dziala -#`m4 "--define=PATTERN=$flexpattern" "--define=DEFAULTACTION=$defaultaction" $flextemplate > $tmpfile_l`; - -system "m4 \"--define=PATTERN=$flexpattern\" \"--define=DEFAULTACTION=$defaultaction\" $flextemplate > $tmpfile_l"; - -if($flex) -{ - # w tych `` nie dziala - system "cat $tmpfile_l"; -# if(open(FLEX, $tmpfile_l)) { -# while() { -# print @_; -# } -# close FLEX; -# } -# else { -# print "Unable to open file $tmpfile_l\n"; -# } - exit(0); -} - -`flex -o$tmpfile_c $tmpfile_l`; -`cc -O3 -o $tmpfile_x $tmpfile_c -lfl`; -#`$tmpfile_x`; - -system "$tmpfile_x"; - -unlink $tmpfile_l; -unlink $tmpfile_c; -unlink $tmpfile_x; Index: c/tok_cmdline.ggo =================================================================== --- src/tok_cmdline.ggo (revision 12743b9e8ce96f3f0d743ab0459dacbc0fe2690c) +++ (revision ) @@ -1,4 +1,0 @@ -package "tok" -version "0.1" - -option "interactive" i "Interactive mode." flag off Index: c/uam.tag2re.pl =================================================================== --- src/uam.tag2re.pl (revision a26cf421b204b6586fa67d9ae592df09abca8cc3) +++ (revision ) @@ -1,89 +1,0 @@ -#!/usr/bin/perl - -#package: UAM Text Tools -#component: tags for utt -#version: 1.0 -#author: Tomasz Obrebski - -use strict; -use locale; - -my $input = <>; -chomp $input; - -our $pos_re = qr/(?:[[:upper:]]+)/; -our $attr_re = qr/(?:[[:upper:]]+)/; -our $val_re = qr/(?:[[:lower:][:digit:]+?!*-]|<[^>\n]+>)/; -our $av_re = qr/(?:$attr_re$val_re+)/; -our $avlist_re = qr/(?:$av_re+)/; -our $cat_re = qr/(?:$pos_re(?:\/$avlist_re)?)/; - -print pre($input); - -sub parse ($) -{ - my ($dstr)=@_; - my $avs={}; - my ($cat,$attrlist) = split '/', $dstr; - ATTR: - while( $attrlist =~ /($attr_re)($val_re+)/g ) - { - my ($attrstr,$valstr)=($1,$2); - my %vals; - while($valstr =~ /$val_re/g) - { - my $val = $&; - next ATTR if $val eq '*'; - $val =~ s/^<([[:lower:]])>$/$1/; - $vals{$val}=1; - } - - $avs->{$attrstr} = \%vals; # dlaczego to dziala? %vals jest lokalne - } - [$cat, $avs]; -} - -sub unparse (\@) -{ - my ($cat,$avs)= @{shift @_}; - my $dstr=$cat; - my @attrs = keys %$avs; - if(@attrs) - { - $dstr .= '/'; - for my $attr ( sort @attrs ) - { - $dstr .= $attr . (join '', sort keys %{$avs->{$attr}}); - } - } - $dstr; -} - -sub canonize ($) -{ - unparse @{parse shift} ; -} - -sub pre -{ - my $pos_res = '[[:upper:]]+'; - my $attr_res = '[[:upper:]]+'; - my $val_res = '[[:lower:][:digit:]+?!*-]|<[^>\n[:cntrl:]]+>'; - my $av_res = "$attr_res($val_res)+"; - my $avlist_res = "($av_res)+"; - - my $pat = canonize(shift); - my $ret; - my ($pos,$avlist) = split /\//, $pat; - $ret = $pos.'(\/'; - while ($avlist =~ /($attr_res)(${val_res}+)/g) - { - my $attr = $1; - my $vals = $2; - my $vals = "($val_res)*(".join('|',($vals =~ /$val_res/g)).")($val_res)*"; - $ret .= "($av_res)*$attr$vals"; - } - $ret .= "($av_res)*)?"; - return $ret; -} - Index: c/unfla.sh =================================================================== --- src/unfla.sh (revision 1e572e12c518a2f97f350cb98dcfe5c90e673e48) +++ (revision ) @@ -1,8 +1,0 @@ -#!/bin/sh - -#package: UAM Text Tools -#component: unfla -#version: 1.0 -#author: Tomasz Obrebski - -exec tr '\014' '\012'