Rewritten the build system, added lem UTF-8 version.
This commit is contained in:
Maciej Prill
parent
7bed30fe7b
commit
5f4d9c3b32
|
|
@ -0,0 +1,129 @@
|
|||
include config.mak
|
||||
|
||||
CUR_DIR=$(shell pwd)
|
||||
SRC_DIR=$(CUR_DIR)/src
|
||||
|
||||
TARGETS = components configuration share libraries
|
||||
|
||||
ifeq ($(BUILD_DOC), yes)
|
||||
TARGETS += documentation
|
||||
endif
|
||||
|
||||
.PHONY: all
|
||||
all: $(TARGETS)
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# main section
|
||||
# ------------------------------------------------------------------
|
||||
.PHONY: components
|
||||
components:
|
||||
cd $(SRC_DIR)/lib && make; cd $(CUR_DIR)
|
||||
|
||||
@for cmp in $(COMPONENTS); do\
|
||||
cd $(SRC_DIR)/$$cmp && make; cd $(CUR_DIR); \
|
||||
done
|
||||
|
||||
.PHONY: documentation
|
||||
documentation:
|
||||
cd $(CUR_DIR)/doc && make; cd $(CUR_DIR)
|
||||
|
||||
.PHONY: configuration
|
||||
configuration:
|
||||
|
||||
.PHONY: libraries
|
||||
libraries:
|
||||
|
||||
.PHONY: share
|
||||
share:
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# cleanup section
|
||||
# ------------------------------------------------------------------
|
||||
.PHONY: clean
|
||||
clean: clean_components clean_documentation
|
||||
@echo "All files cleaned successfully!"
|
||||
|
||||
.PHONY: clean_components
|
||||
clean_components:
|
||||
@for cmp in $(COMPONENTS); do \
|
||||
cd $(SRC_DIR)/$$cmp && make clean; cd $(CUR_DIR); \
|
||||
done
|
||||
cd $(SRC_DIR)/lib && make clean; cd $(CUR_DIR);
|
||||
|
||||
.PHONY: clean_documentation
|
||||
clean_documentation:
|
||||
cd $(CUR_DIR)/doc && make clean; cd $(CUR_DIR)
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# install section
|
||||
# ------------------------------------------------------------------
|
||||
.PHONY: install
|
||||
install: all install_dirs install_components install_configuration install_libraries install_documentation install_share
|
||||
|
||||
.PHONY: install_dirs
|
||||
install_dirs:
|
||||
install -d $(PREFIX) \
|
||||
$(BIN_DIR) \
|
||||
$(CONF_DIR) \
|
||||
$(LANG_DIR) \
|
||||
$(LIB_DIR) \
|
||||
$(DOC_DIR) \
|
||||
$(SHARE_DIR)/info
|
||||
|
||||
.PHONY: install_components
|
||||
install_components: components
|
||||
@for cmp in $(COMPONENTS); do \
|
||||
cd $(SRC_DIR)/$$cmp && make install; cd $(CUR_DIR); \
|
||||
done
|
||||
|
||||
.PHONY: install_configuration
|
||||
install_configuration: configuration
|
||||
cd $(CUR_DIR)/conf && make install; cd $(CUR_DIR)
|
||||
|
||||
.PHONY: install_libraries
|
||||
install_libraries: libraries
|
||||
cd $(CUR_DIR)/lib && make install; cd $(CUR_DIR)
|
||||
|
||||
.PHONY: install_documentation
|
||||
install_documentation: documentation
|
||||
cd $(CUR_DIR)/doc && make install; cd $(CUR_DIR)
|
||||
|
||||
.PHONY: install_share
|
||||
install_share: share
|
||||
cd $(CUR_DIR)/share && make install; cd $(CUR_DIR)
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# uninstall section
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
.PHONY: uninstall
|
||||
uninstall: uninstall_share uninstall_documentation uninstall_libraries uninstall_configuration uninstall_components uninstall_dirs
|
||||
|
||||
.PHONY: uninstall_components
|
||||
uninstall_components:
|
||||
@for cmp in $(COMPONENTS); do \
|
||||
cd $(SRC_DIR)/$$cmp && make uninstall; cd $(CUR_DIR); \
|
||||
done
|
||||
|
||||
.PHONY: uninstall_configuration
|
||||
uninstall_configuration:
|
||||
cd $(CUR_DIR)/conf && make uninstall; cd $(CUR_DIR)
|
||||
|
||||
.PHONY: uninstall_libraries
|
||||
uninstall_libraries:
|
||||
cd $(CUR_DIR)/lib && make uninstall; cd $(CUR_DIR)
|
||||
|
||||
.PHONY: uninstall_documentation
|
||||
uninstall_documentation:
|
||||
cd $(CUR_DIR)/doc && make uninstall; cd $(CUR_DIR)
|
||||
|
||||
.PHONY: uninstall_share
|
||||
uninstall_share:
|
||||
cd $(CUR_DIR)/share && make uninstall; cd $(CUR_DIR)
|
||||
|
||||
.PHONY: uninstall_dirs
|
||||
uninstall_dirs: uninstall_configuration uninstall_documentation uninstall_share uninstall_libraries
|
||||
rmdir $(CONF_DIR)
|
||||
rmdir $(DOC_DIR)
|
||||
rmdir $(LANG_DIR)
|
||||
rmdir $(LIB_DIR)
|
||||
|
|
@ -0,0 +1,35 @@
|
|||
include ../config.mak
|
||||
|
||||
.PHONY: install
|
||||
install:
|
||||
ifdef CONF_DIR
|
||||
install -m 0644 compiledic.conf $(CONF_DIR)
|
||||
install -m 0644 cor.conf $(CONF_DIR)
|
||||
install -m 0644 dgc.conf $(CONF_DIR)
|
||||
install -m 0644 dgp.conf $(CONF_DIR)
|
||||
install -m 0644 gph.conf $(CONF_DIR)
|
||||
install -m 0644 grp.conf $(CONF_DIR)
|
||||
install -m 0644 gue.conf $(CONF_DIR)
|
||||
install -m 0644 kor.conf $(CONF_DIR)
|
||||
install -m 0644 lem.conf $(CONF_DIR)
|
||||
install -m 0644 mar.conf $(CONF_DIR)
|
||||
install -m 0644 ser.conf $(CONF_DIR)
|
||||
install -m 0644 utt.conf $(CONF_DIR)
|
||||
endif
|
||||
|
||||
.PHONY: uninstall
|
||||
uninstall:
|
||||
ifdef CONF_DIR
|
||||
rm $(CONF_DIR)/compiledic.conf
|
||||
rm $(CONF_DIR)/cor.conf
|
||||
rm $(CONF_DIR)/dgc.conf
|
||||
rm $(CONF_DIR)/dgp.conf
|
||||
rm $(CONF_DIR)/gph.conf
|
||||
rm $(CONF_DIR)/grp.conf
|
||||
rm $(CONF_DIR)/gue.conf
|
||||
rm $(CONF_DIR)/kor.conf
|
||||
rm $(CONF_DIR)/lem.conf
|
||||
rm $(CONF_DIR)/mar.conf
|
||||
rm $(CONF_DIR)/ser.conf
|
||||
rm $(CONF_DIR)/utt.conf
|
||||
endif
|
||||
|
|
@ -0,0 +1,46 @@
|
|||
|
||||
# some variables
|
||||
|
||||
# path, where all nessesary files are placed
|
||||
# (they will be processed for making distribution)
|
||||
export UTT_DIST_DIR=$(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}
|
||||
|
||||
|
|
@ -0,0 +1,15 @@
|
|||
|
||||
while(<STDIN>) {
|
||||
chomp;
|
||||
$app = $_;
|
||||
$path = `which $app 2>/dev/null`;
|
||||
$err = $?;
|
||||
print $app.": ";
|
||||
if($err != 0) {
|
||||
print "failed ($err)\n";
|
||||
}
|
||||
else {
|
||||
print $path;
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -0,0 +1 @@
|
|||
I put here some description.
|
||||
|
|
@ -0,0 +1 @@
|
|||
Tu umieszczę opis po polsku.
|
||||
|
|
@ -0,0 +1,29 @@
|
|||
|
||||
|
||||
while(<STDIN>) {
|
||||
chomp;
|
||||
# najpierw nazwa pliku zrodlowego out
|
||||
if($_ =~ /^[^:]*\:\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
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,16 @@
|
|||
#!/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
|
||||
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
#!/bin/sh
|
||||
|
||||
grep -r -e "\`" ../../src | grep -v -e "\.svn\/" | perl find_perl_deps.pl | sort | uniq > dep_list.txt
|
||||
|
|
@ -0,0 +1,14 @@
|
|||
#!/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
|
||||
|
|
@ -0,0 +1 @@
|
|||
2
|
||||
|
|
@ -0,0 +1 @@
|
|||
0.9
|
||||
|
|
@ -0,0 +1,86 @@
|
|||
#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
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
This directory contains files necessery to create deb package.
|
||||
|
||||
apt-get install dpkg-dev debhelper devscripts fakeroot linda
|
||||
|
|
@ -0,0 +1,8 @@
|
|||
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’’.
|
||||
|
|
@ -0,0 +1,264 @@
|
|||
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.
|
||||
|
|
@ -0,0 +1,51 @@
|
|||
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.
|
||||
|
||||
|
|
@ -0,0 +1,26 @@
|
|||
# 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 ${_RPM_FROOT}
|
||||
|
||||
|
|
@ -0,0 +1,16 @@
|
|||
This directory contains files necessary to produce rpm package.
|
||||
|
||||
First, you must have variable UTT_DIST_DIR defined properly.
|
||||
This variable should be defined by main Makefile.
|
||||
|
||||
To create rpm file, just write:
|
||||
make
|
||||
|
||||
The created package should appears in default RPM directory.
|
||||
(in my computer it is /usr/src/redhat/RPMS/$arch/ directory)
|
||||
|
||||
To determine the rpm output directory, execute:
|
||||
rpm --showrc | grep _rmpdir
|
||||
|
||||
You need access privilage to this directory to create rmp.
|
||||
|
||||
|
|
@ -0,0 +1,81 @@
|
|||
#
|
||||
# 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)
|
||||
/*
|
||||
|
|
@ -0,0 +1,74 @@
|
|||
/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)
|
||||
|
|
@ -0,0 +1,5 @@
|
|||
Here you can find some information about how to install utt.
|
||||
|
||||
You should just unpack archive and then execute
|
||||
make test
|
||||
make install
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
# 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 ${_TARBALL_ROOT}
|
||||
|
||||
|
|
@ -0,0 +1,18 @@
|
|||
UTT_LIB_DIR=${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}
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
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.
|
||||
|
|
@ -0,0 +1,45 @@
|
|||
include ../config.mak
|
||||
|
||||
all: utt.info utt.dvi utt.html utt.pdf utt.ps
|
||||
|
||||
utt.info: utt.texinfo
|
||||
$(MAKEINFO) $< -o $@
|
||||
|
||||
utt.dvi: utt.texinfo
|
||||
$(TEXI2DVI) --build=clean $< -o $@
|
||||
|
||||
utt.html: utt.texinfo
|
||||
$(MAKEINFO) --html --no-split $< -o $@
|
||||
|
||||
utt.pdf: utt.texinfo
|
||||
$(TEXI2PDF) --build=clean $< -o $@
|
||||
|
||||
utt.ps: utt.dvi
|
||||
$(DVIPS) $< -o $@
|
||||
|
||||
.PHONY: install
|
||||
install:
|
||||
ifdef SHARE_DIR
|
||||
install -m 0644 utt.info $(SHARE_DIR)/info
|
||||
endif
|
||||
ifdef DOC_DIR
|
||||
install -m 0644 utt.dvi $(DOC_DIR)
|
||||
install -m 0644 utt.html $(DOC_DIR)
|
||||
install -m 0644 utt.pdf $(DOC_DIR)
|
||||
install -m 0644 utt.ps $(DOC_DIR)
|
||||
endif
|
||||
|
||||
.PHONY: uninstall
|
||||
uninstall:
|
||||
ifdef SHARE_DIR
|
||||
rm $(SHARE_DIR)/info/utt.info
|
||||
endif
|
||||
ifdef DOC_DIR
|
||||
rm $(DOC_DIR)/utt.dvi
|
||||
rm $(DOC_DIR)/utt.html
|
||||
rm $(DOC_DIR)/utt.pdf
|
||||
rm $(DOC_DIR)/utt.ps
|
||||
endif
|
||||
|
||||
clean:
|
||||
rm utt.info utt.dvi utt.html utt.pdf utt.ps || true
|
||||
|
|
@ -0,0 +1,19 @@
|
|||
include ../config.mak
|
||||
|
||||
.PHONY: install
|
||||
install:
|
||||
ifdef LIB_DIR
|
||||
install -m 0755 attr.pm $(LIB_DIR)
|
||||
install -m 0755 seg.rb $(LIB_DIR)
|
||||
install -m 0755 ser.l.template $(LIB_DIR)
|
||||
install -m 0755 terms.m4 $(LIB_DIR)
|
||||
endif
|
||||
|
||||
.PHONY: uninstall
|
||||
uninstall:
|
||||
ifdef LIB_DIR
|
||||
rm $(LIB_DIR)/attr.pm
|
||||
rm $(LIB_DIR)/seg.rb
|
||||
rm $(LIB_DIR)/ser.l.template
|
||||
rm $(LIB_DIR)/terms.m4
|
||||
endif
|
||||
|
|
@ -0,0 +1,133 @@
|
|||
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 [<cat>, <avs>],
|
||||
# gdzie <avs> jest referencja do hasza, zawierajacego pary
|
||||
# atrybut=>hasz warto¶ci (pary warto¶æ=>1), czyli np.
|
||||
|
||||
# [
|
||||
# 'ADJ',
|
||||
# {
|
||||
# 'KOLEDZY' => {
|
||||
# '<alojzy>' => 1,
|
||||
# '<karol>' => 1,
|
||||
# '<jan>' => 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;
|
||||
|
|
@ -0,0 +1,31 @@
|
|||
|
||||
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
|
||||
|
|
@ -0,0 +1,30 @@
|
|||
%{
|
||||
#include<string.h>
|
||||
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;
|
||||
|
|
@ -0,0 +1,52 @@
|
|||
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)
|
||||
|
|
@ -0,0 +1,31 @@
|
|||
include ../config.mak
|
||||
|
||||
.PHONY: install
|
||||
install:
|
||||
ifdef LANG_DIR
|
||||
install -d $(LANG_DIR)/pl_PL.ISO-8859-2
|
||||
install -d $(LANG_DIR)/pl_PL.UTF-8
|
||||
install -m 0644 pl_PL.ISO-8859-2/cor.bin $(LANG_DIR)/pl_PL.ISO-8859-2
|
||||
install -m 0644 pl_PL.ISO-8859-2/gue.bin $(LANG_DIR)/pl_PL.ISO-8859-2
|
||||
install -m 0644 pl_PL.ISO-8859-2/lem.bin $(LANG_DIR)/pl_PL.ISO-8859-2
|
||||
install -m 0644 pl_PL.ISO-8859-2/pl_PL.ISO-8859-2.sym $(LANG_DIR)/pl_PL.ISO-8859-2
|
||||
install -m 0644 pl_PL.UTF-8/lem.bin $(LANG_DIR)/pl_PL.UTF-8
|
||||
install -m 0644 cats.dgc $(LANG_DIR)
|
||||
install -m 0644 gram.dgc $(LANG_DIR)
|
||||
install -m 0644 weights.kor $(LANG_DIR)
|
||||
endif
|
||||
|
||||
.PHONY: uninstall
|
||||
uninstall:
|
||||
ifdef LANG_DIR
|
||||
rm $(LANG_DIR)/weights.kor
|
||||
rm $(LANG_DIR)/gram.dgc
|
||||
rm $(LANG_DIR)/cats.dgc
|
||||
rm $(LANG_DIR)/pl_PL.UTF-8/lem.bin
|
||||
rm $(LANG_DIR)/pl_PL.ISO-8859-2/pl_PL.ISO-8859-2.sym
|
||||
rm $(LANG_DIR)/pl_PL.ISO-8859-2/lem.bin
|
||||
rm $(LANG_DIR)/pl_PL.ISO-8859-2/gue.bin
|
||||
rm $(LANG_DIR)/pl_PL.ISO-8859-2/cor.bin
|
||||
rmdir $(LANG_DIR)/pl_PL.ISO-8859-2
|
||||
rmdir $(LANG_DIR)/pl_PL.UTF-8
|
||||
endif
|
||||
|
|
@ -0,0 +1,696 @@
|
|||
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
|
||||
|
|
@ -0,0 +1,124 @@
|
|||
#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. książka Marii, ojciec kolegi
|
||||
ROLE restr # (bardzo <- duży)
|
||||
ROLE part # partykuła
|
||||
ROLE coord # koordynacja (powiązanie 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
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
|
@ -0,0 +1,8 @@
|
|||
lcase a ą 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 ż é ö ü ä
|
||||
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 Ż
|
||||
letter lcase ucase
|
||||
digit 0 1 2 3 4 5 6 7 8 9
|
||||
punct , . @ / ' ~ ; _ - + ? \
|
||||
all letter digit signs sem
|
||||
Binary file not shown.
|
|
@ -0,0 +1,21 @@
|
|||
%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 ¼ 0.25
|
||||
x ¼ 0.30
|
||||
|
||||
|
|
@ -0,0 +1,8 @@
|
|||
# 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
|
||||
|
|
@ -0,0 +1,18 @@
|
|||
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
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,39 @@
|
|||
#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
|
||||
package "guess"
|
||||
version "0.1"
|
||||
|
||||
option "color" l "Show guessed descriptions in colour." flag off
|
||||
|
||||
|
|
@ -0,0 +1,248 @@
|
|||
/** @file cmdline.h
|
||||
* @brief The header file for the command line option parser
|
||||
* generated by GNU Gengetopt version 2.22.4
|
||||
* http://www.gnu.org/software/gengetopt.
|
||||
* DO NOT modify this file, since it can be overwritten
|
||||
* @author GNU Gengetopt by Lorenzo Bettini */
|
||||
|
||||
#ifndef CMDLINE_H
|
||||
#define CMDLINE_H
|
||||
|
||||
/* If we use autoconf. */
|
||||
#ifdef HAVE_CONFIG_H
|
||||
#include "config.h"
|
||||
#endif
|
||||
|
||||
#include <stdio.h> /* for FILE */
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif /* __cplusplus */
|
||||
|
||||
#ifndef CMDLINE_PARSER_PACKAGE
|
||||
/** @brief the program name (used for printing errors) */
|
||||
#define CMDLINE_PARSER_PACKAGE "guess"
|
||||
#endif
|
||||
|
||||
#ifndef CMDLINE_PARSER_PACKAGE_NAME
|
||||
/** @brief the complete program name (used for help and version) */
|
||||
#define CMDLINE_PARSER_PACKAGE_NAME "guess"
|
||||
#endif
|
||||
|
||||
#ifndef CMDLINE_PARSER_VERSION
|
||||
/** @brief the program version */
|
||||
#define CMDLINE_PARSER_VERSION "0.1"
|
||||
#endif
|
||||
|
||||
/** @brief Where the command line options are stored */
|
||||
struct gengetopt_args_info
|
||||
{
|
||||
const char *help_help; /**< @brief Print help and exit help description. */
|
||||
const char *full_help_help; /**< @brief Print help, including hidden options, and exit help description. */
|
||||
const char *version_help; /**< @brief Print version and exit help description. */
|
||||
char * input_arg; /**< @brief Input file. */
|
||||
char * input_orig; /**< @brief Input file original value given at command line. */
|
||||
const char *input_help; /**< @brief Input file help description. */
|
||||
char * output_arg; /**< @brief Output file for succesfully processed segments. */
|
||||
char * output_orig; /**< @brief Output file for succesfully processed segments original value given at command line. */
|
||||
const char *output_help; /**< @brief Output file for succesfully processed segments help description. */
|
||||
char * fail_arg; /**< @brief Output file for unsuccesfully processed segments . */
|
||||
char * fail_orig; /**< @brief Output file for unsuccesfully processed segments original value given at command line. */
|
||||
const char *fail_help; /**< @brief Output file for unsuccesfully processed segments help description. */
|
||||
int only_fail_flag; /**< @brief Print only segments the program failed to process (default=off). */
|
||||
const char *only_fail_help; /**< @brief Print only segments the program failed to process help description. */
|
||||
int no_fail_flag; /**< @brief Print only segments the program processed (default=off). */
|
||||
const char *no_fail_help; /**< @brief Print only segments the program processed help description. */
|
||||
int copy_flag; /**< @brief Copy succesfully processed segments to standard output (default=off). */
|
||||
const char *copy_help; /**< @brief Copy succesfully processed segments to standard output help description. */
|
||||
char ** process_arg; /**< @brief Process segments with this tag. */
|
||||
char ** process_orig; /**< @brief Process segments with this tag original value given at command line. */
|
||||
unsigned int process_min; /**< @brief Process segments with this tag's minimum occurreces */
|
||||
unsigned int process_max; /**< @brief Process segments with this tag's maximum occurreces */
|
||||
const char *process_help; /**< @brief Process segments with this tag help description. */
|
||||
char ** select_arg; /**< @brief Select only segments with this field. */
|
||||
char ** select_orig; /**< @brief Select only segments with this field original value given at command line. */
|
||||
unsigned int select_min; /**< @brief Select only segments with this field's minimum occurreces */
|
||||
unsigned int select_max; /**< @brief Select only segments with this field's maximum occurreces */
|
||||
const char *select_help; /**< @brief Select only segments with this field help description. */
|
||||
char ** ignore_arg; /**< @brief Select only segments without this field. */
|
||||
char ** ignore_orig; /**< @brief Select only segments without this field original value given at command line. */
|
||||
unsigned int ignore_min; /**< @brief Select only segments without this field's minimum occurreces */
|
||||
unsigned int ignore_max; /**< @brief Select only segments without this field's maximum occurreces */
|
||||
const char *ignore_help; /**< @brief Select only segments without this field help description. */
|
||||
char * output_field_arg; /**< @brief Output field name. */
|
||||
char * output_field_orig; /**< @brief Output field name original value given at command line. */
|
||||
const char *output_field_help; /**< @brief Output field name help description. */
|
||||
char ** input_field_arg; /**< @brief Input field name. */
|
||||
char ** input_field_orig; /**< @brief Input field name original value given at command line. */
|
||||
unsigned int input_field_min; /**< @brief Input field name's minimum occurreces */
|
||||
unsigned int input_field_max; /**< @brief Input field name's maximum occurreces */
|
||||
const char *input_field_help; /**< @brief Input field name help description. */
|
||||
int interactive_flag; /**< @brief Toggle interactive mode (default=off). */
|
||||
const char *interactive_help; /**< @brief Toggle interactive mode help description. */
|
||||
char * config_arg; /**< @brief Configuration file. */
|
||||
char * config_orig; /**< @brief Configuration file original value given at command line. */
|
||||
const char *config_help; /**< @brief Configuration file help description. */
|
||||
int one_field_flag; /**< @brief Print all results in one segments (creates ambiguous annotation) (default=off). */
|
||||
const char *one_field_help; /**< @brief Print all results in one segments (creates ambiguous annotation) help description. */
|
||||
int one_line_flag; /**< @brief Print annotation alternatives as additional fields (default=off). */
|
||||
const char *one_line_help; /**< @brief Print annotation alternatives as additional fields help description. */
|
||||
char * language_arg; /**< @brief Language.. */
|
||||
char * language_orig; /**< @brief Language. original value given at command line. */
|
||||
const char *language_help; /**< @brief Language. help description. */
|
||||
int color_flag; /**< @brief Show guessed descriptions in colour. (default=off). */
|
||||
const char *color_help; /**< @brief Show guessed descriptions in colour. help description. */
|
||||
|
||||
unsigned int help_given ; /**< @brief Whether help was given. */
|
||||
unsigned int full_help_given ; /**< @brief Whether full-help was given. */
|
||||
unsigned int version_given ; /**< @brief Whether version was given. */
|
||||
unsigned int input_given ; /**< @brief Whether input was given. */
|
||||
unsigned int output_given ; /**< @brief Whether output was given. */
|
||||
unsigned int fail_given ; /**< @brief Whether fail was given. */
|
||||
unsigned int only_fail_given ; /**< @brief Whether only-fail was given. */
|
||||
unsigned int no_fail_given ; /**< @brief Whether no-fail was given. */
|
||||
unsigned int copy_given ; /**< @brief Whether copy was given. */
|
||||
unsigned int process_given ; /**< @brief Whether process was given. */
|
||||
unsigned int select_given ; /**< @brief Whether select was given. */
|
||||
unsigned int ignore_given ; /**< @brief Whether ignore was given. */
|
||||
unsigned int output_field_given ; /**< @brief Whether output-field was given. */
|
||||
unsigned int input_field_given ; /**< @brief Whether input-field was given. */
|
||||
unsigned int interactive_given ; /**< @brief Whether interactive was given. */
|
||||
unsigned int config_given ; /**< @brief Whether config was given. */
|
||||
unsigned int one_field_given ; /**< @brief Whether one-field was given. */
|
||||
unsigned int one_line_given ; /**< @brief Whether one-line was given. */
|
||||
unsigned int language_given ; /**< @brief Whether language was given. */
|
||||
unsigned int color_given ; /**< @brief Whether color was given. */
|
||||
|
||||
} ;
|
||||
|
||||
/** @brief The additional parameters to pass to parser functions */
|
||||
struct cmdline_parser_params
|
||||
{
|
||||
int override; /**< @brief whether to override possibly already present options (default 0) */
|
||||
int initialize; /**< @brief whether to initialize the option structure gengetopt_args_info (default 1) */
|
||||
int check_required; /**< @brief whether to check that all required options were provided (default 1) */
|
||||
int check_ambiguity; /**< @brief whether to check for options already specified in the option structure gengetopt_args_info (default 0) */
|
||||
int print_errors; /**< @brief whether getopt_long should print an error message for a bad option (default 1) */
|
||||
} ;
|
||||
|
||||
/** @brief the purpose string of the program */
|
||||
extern const char *gengetopt_args_info_purpose;
|
||||
/** @brief the usage string of the program */
|
||||
extern const char *gengetopt_args_info_usage;
|
||||
/** @brief all the lines making the help output */
|
||||
extern const char *gengetopt_args_info_help[];
|
||||
/** @brief all the lines making the full help output (including hidden options) */
|
||||
extern const char *gengetopt_args_info_full_help[];
|
||||
|
||||
/**
|
||||
* The command line parser
|
||||
* @param argc the number of command line options
|
||||
* @param argv the command line options
|
||||
* @param args_info the structure where option information will be stored
|
||||
* @return 0 if everything went fine, NON 0 if an error took place
|
||||
*/
|
||||
int cmdline_parser (int argc, char **argv,
|
||||
struct gengetopt_args_info *args_info);
|
||||
|
||||
/**
|
||||
* The command line parser (version with additional parameters - deprecated)
|
||||
* @param argc the number of command line options
|
||||
* @param argv the command line options
|
||||
* @param args_info the structure where option information will be stored
|
||||
* @param override whether to override possibly already present options
|
||||
* @param initialize whether to initialize the option structure my_args_info
|
||||
* @param check_required whether to check that all required options were provided
|
||||
* @return 0 if everything went fine, NON 0 if an error took place
|
||||
* @deprecated use cmdline_parser_ext() instead
|
||||
*/
|
||||
int cmdline_parser2 (int argc, char **argv,
|
||||
struct gengetopt_args_info *args_info,
|
||||
int override, int initialize, int check_required);
|
||||
|
||||
/**
|
||||
* The command line parser (version with additional parameters)
|
||||
* @param argc the number of command line options
|
||||
* @param argv the command line options
|
||||
* @param args_info the structure where option information will be stored
|
||||
* @param params additional parameters for the parser
|
||||
* @return 0 if everything went fine, NON 0 if an error took place
|
||||
*/
|
||||
int cmdline_parser_ext (int argc, char **argv,
|
||||
struct gengetopt_args_info *args_info,
|
||||
struct cmdline_parser_params *params);
|
||||
|
||||
/**
|
||||
* Save the contents of the option struct into an already open FILE stream.
|
||||
* @param outfile the stream where to dump options
|
||||
* @param args_info the option struct to dump
|
||||
* @return 0 if everything went fine, NON 0 if an error took place
|
||||
*/
|
||||
int cmdline_parser_dump(FILE *outfile,
|
||||
struct gengetopt_args_info *args_info);
|
||||
|
||||
/**
|
||||
* Save the contents of the option struct into a (text) file.
|
||||
* This file can be read by the config file parser (if generated by gengetopt)
|
||||
* @param filename the file where to save
|
||||
* @param args_info the option struct to save
|
||||
* @return 0 if everything went fine, NON 0 if an error took place
|
||||
*/
|
||||
int cmdline_parser_file_save(const char *filename,
|
||||
struct gengetopt_args_info *args_info);
|
||||
|
||||
/**
|
||||
* Print the help
|
||||
*/
|
||||
void cmdline_parser_print_help(void);
|
||||
/**
|
||||
* Print the full help (including hidden options)
|
||||
*/
|
||||
void cmdline_parser_print_full_help(void);
|
||||
/**
|
||||
* Print the version
|
||||
*/
|
||||
void cmdline_parser_print_version(void);
|
||||
|
||||
/**
|
||||
* Initializes all the fields a cmdline_parser_params structure
|
||||
* to their default values
|
||||
* @param params the structure to initialize
|
||||
*/
|
||||
void cmdline_parser_params_init(struct cmdline_parser_params *params);
|
||||
|
||||
/**
|
||||
* Allocates dynamically a cmdline_parser_params structure and initializes
|
||||
* all its fields to their default values
|
||||
* @return the created and initialized cmdline_parser_params structure
|
||||
*/
|
||||
struct cmdline_parser_params *cmdline_parser_params_create(void);
|
||||
|
||||
/**
|
||||
* Initializes the passed gengetopt_args_info structure's fields
|
||||
* (also set default values for options that have a default)
|
||||
* @param args_info the structure to initialize
|
||||
*/
|
||||
void cmdline_parser_init (struct gengetopt_args_info *args_info);
|
||||
/**
|
||||
* Deallocates the string fields of the gengetopt_args_info structure
|
||||
* (but does not deallocate the structure itself)
|
||||
* @param args_info the structure to deallocate
|
||||
*/
|
||||
void cmdline_parser_free (struct gengetopt_args_info *args_info);
|
||||
|
||||
/**
|
||||
* Checks that all the required options were specified
|
||||
* @param args_info the structure to check
|
||||
* @param prog_name the name of the program that will be used to print
|
||||
* possible errors
|
||||
* @return
|
||||
*/
|
||||
int cmdline_parser_required (struct gengetopt_args_info *args_info,
|
||||
const char *prog_name);
|
||||
|
||||
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
#endif /* __cplusplus */
|
||||
#endif /* CMDLINE_H */
|
||||
|
|
@ -0,0 +1,34 @@
|
|||
#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
|
||||
|
|
@ -0,0 +1,5 @@
|
|||
package "guess"
|
||||
version "0.1"
|
||||
|
||||
option "color" l "Show guessed descriptions in colour." flag off
|
||||
|
||||
|
|
@ -0,0 +1,229 @@
|
|||
#include <cstdlib>
|
||||
#include <cstring>
|
||||
#include <sys/types.h>
|
||||
#include <sys/stat.h>
|
||||
#include <unistd.h>
|
||||
#include "common.h"
|
||||
#include <cstdio>
|
||||
#include <clocale>
|
||||
|
||||
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;
|
||||
}
|
||||
|
|
@ -0,0 +1,516 @@
|
|||
#ifndef __COMMON_H
|
||||
#define __COMMON_H
|
||||
|
||||
#include <cstdio>
|
||||
#include <cctype>
|
||||
#include <cstring>
|
||||
#include <cstdlib>
|
||||
|
||||
#include <cwchar>
|
||||
#include <cwctype>
|
||||
|
||||
#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¶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
|
||||
-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;
|
||||
}
|
||||
}
|
||||
|
||||
inline int getfield(wchar_t* seg, const wchar_t* pref, wchar_t* val)
|
||||
{
|
||||
|
||||
wchar_t* p=seg;
|
||||
wchar_t* p0;
|
||||
while(iswspace(*p)) ++p;
|
||||
|
||||
// field "1"
|
||||
p0=p; while(iswdigit(*p)) ++p;
|
||||
if(*pref==L'1')
|
||||
if(p!=p0)
|
||||
{
|
||||
wcsncpy(val,p0,p-p0);
|
||||
val[p-p0]=L'\0';
|
||||
return 1;
|
||||
}
|
||||
else
|
||||
return 0;
|
||||
while(iswspace(*p)) ++p;
|
||||
|
||||
// field "2"
|
||||
p0=p; while(iswdigit(*p)) ++p;
|
||||
if(*pref==L'2') if(p!=p0) { wcsncpy(val,p0,p-p0); val[p-p0]=L'\0'; return 1; } else return 0;
|
||||
while(iswspace(*p)) ++p;
|
||||
// field "3"
|
||||
p0=p; while(iswgraph(*p)) ++p;
|
||||
if(*pref==L'3') if(p!=p0) { wcsncpy(val,p0,p-p0); val[p-p0]=L'\0'; return 1; } else return 0;
|
||||
|
||||
while(iswspace(*p)) ++p;
|
||||
p0=p; while(iswgraph(*p)) ++p;
|
||||
|
||||
if(*pref==L'4') if(p!=p0) { wcsncpy(val,p0,p-p0); val[p-p0]=L'\0'; return 1; } else return 0;
|
||||
while(iswspace(*p)) ++p;
|
||||
|
||||
// annotation fields
|
||||
do p=wcsstr(p,pref); while(p!=NULL && *(p-1)!=L' ' && *(p-1)!=L'\t');
|
||||
if(p==NULL) return 0;
|
||||
else
|
||||
{
|
||||
p+=wcslen(pref);
|
||||
int len=wcscspn(p,FIELD_SEP L"\n\r\f\0");
|
||||
wcsncpy(val,p,len);
|
||||
val[len]=L'\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<args.process_given; ++i)
|
||||
if(strcmp(args.process_arg[i],buf)==0)
|
||||
{
|
||||
ret=true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
if(ret==false) return false;
|
||||
|
||||
for(int i=0; i<args.select_given; ++i)
|
||||
{
|
||||
fieldprefix(args.select_arg[i],pref); // !!! ŁATKA - ZOPTYMALIZOWAĆ !!!
|
||||
if(! getfield(seg,pref,buf))
|
||||
return false;
|
||||
}
|
||||
for(int i=0; i<args.ignore_given; ++i)
|
||||
{
|
||||
fieldprefix(args.ignore_arg[i],pref); // !!! ŁATKA - ZOPTYMALIZOWAĆ !!!
|
||||
if(getfield(seg,pref,buf))
|
||||
return false;
|
||||
}
|
||||
|
||||
if(args.input_field_given & !getfield(seg,input_field_prefix,buf))
|
||||
return false;
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
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) >= 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<args.process_given; ++i)
|
||||
if(strcmp(args.process_arg[i],s.tag)==0)
|
||||
{
|
||||
ret=true;
|
||||
break;
|
||||
}
|
||||
|
||||
for(int i=0; i<args.select_given; ++i)
|
||||
if(! s.getfield(args.select_arg[i]))
|
||||
ret=false;
|
||||
|
||||
for(int i=0; i<args.ignore_given; ++i)
|
||||
if(s.getfield(args.ignore_arg[i]))
|
||||
ret=false;
|
||||
|
||||
return ret;
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
* FUNKCJE OBSLUGUJACE WEJSCIE/WYJSCIE
|
||||
*/
|
||||
// napisy zostaj na miejscu (w line), tylko wskazniki sa ustawian
|
||||
// i zara dopisywane zera s dopisywane
|
||||
|
||||
inline
|
||||
bool Segment::parse(char* line)
|
||||
{
|
||||
auxn=0;
|
||||
char* field;
|
||||
if((field=strtok(line,FIELD_SEP))!=NULL)
|
||||
filepos=atoi(field); // nie sprawdzana poprawnosc
|
||||
else
|
||||
return false;
|
||||
if((field=strtok(NULL,FIELD_SEP))!=NULL)
|
||||
len=atoi(field); // nie sprawdzana poprawnosc
|
||||
else return false;
|
||||
if((tag=strtok(NULL,FIELD_SEP))==NULL) return false;
|
||||
if((form=strtok(NULL,FIELD_SEP))==NULL)
|
||||
return true;
|
||||
else
|
||||
if(form[0] == EMPTYFORM && form[1] =='\0')
|
||||
form=NULL;
|
||||
|
||||
while((aux[auxn]=strtok(NULL,FIELD_SEP))!=NULL) ++auxn;
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
|
||||
inline char* Segment::getfield(char* f)
|
||||
{
|
||||
int flen=strlen(f);
|
||||
if(isalnum(*f))
|
||||
{
|
||||
for(int i=0; i<auxn; ++i)
|
||||
if(strncmp(aux[i],f,flen)==0 && aux[i][flen]==INFIELD_SEP)
|
||||
return aux[i]+flen+1;
|
||||
} else
|
||||
{
|
||||
for(int i=0; i<auxn; ++i)
|
||||
{
|
||||
if(*f==*(aux[i]))
|
||||
return aux[i]+1;
|
||||
}
|
||||
}
|
||||
return NULL;
|
||||
}
|
||||
|
||||
inline bool Segment::clearfields() {
|
||||
for (int i=0; i<auxn; ++i) {
|
||||
// free(aux[i]);
|
||||
aux[i] = NULL;
|
||||
}
|
||||
auxn=0;
|
||||
return true;
|
||||
}
|
||||
|
||||
inline // NIEEFEKTYWNE
|
||||
void Segment::print(char* line)
|
||||
{
|
||||
sprintf(line,"%04d %02d %s", filepos, len, tag);
|
||||
if(form)
|
||||
{
|
||||
strcat(line," ");
|
||||
strcat(line,form);
|
||||
}
|
||||
else
|
||||
if(auxn)
|
||||
strcat(line," *");
|
||||
|
||||
for(int i=0; i<auxn; ++i)
|
||||
{
|
||||
strcat(line," ");
|
||||
strcat(line,aux[i]);
|
||||
}
|
||||
|
||||
strcat(line,"\n");
|
||||
}
|
||||
|
||||
|
||||
inline
|
||||
bool Segment::addfield(char* s)
|
||||
{
|
||||
if(auxn<MAXAUX)
|
||||
{
|
||||
aux[auxn++]=s;
|
||||
return true;
|
||||
}
|
||||
else
|
||||
return false;
|
||||
}
|
||||
|
||||
/**************************************************
|
||||
* funkcje pomocne w operacjach na plikach *
|
||||
* konfiguracyjnych *
|
||||
**************************************************/
|
||||
|
||||
// sprawdza istnienie pliku
|
||||
int file_accessible(const char* path);
|
||||
|
||||
// sprawdza istnienie pliku konfiguracyjnego
|
||||
int config_file(const char* dir, const char* filename);
|
||||
|
||||
/**************************************************/
|
||||
|
||||
/* Pobiera wejscie
|
||||
* parametry:
|
||||
* - args - tablica stringow okresnajacych pola wejsciowe
|
||||
* - args_len - rozmiar args
|
||||
* - seg - segment
|
||||
* wartosc - wskaznik do wejscia
|
||||
*/
|
||||
inline char* getInput(char** args, int args_len, Segment seg) {
|
||||
char* formp = NULL;
|
||||
for (int i=0; i<args_len; ++i) {
|
||||
if ('4' == args[i][0])
|
||||
return seg.form;
|
||||
if ((formp = seg.getfield(args[i])) != NULL) {
|
||||
return formp;
|
||||
}
|
||||
}
|
||||
return formp;
|
||||
}
|
||||
|
||||
#endif
|
||||
|
|
@ -0,0 +1,20 @@
|
|||
#include <stdlib.h>
|
||||
|
||||
#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);
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,25 @@
|
|||
include ../../config.mak
|
||||
|
||||
all: compiledic
|
||||
|
||||
.PHONY: compiledic
|
||||
compiledic:
|
||||
|
||||
.PHONY: install
|
||||
install:
|
||||
ifdef BIN_DIR
|
||||
install -m 0755 compiledic $(BIN_DIR)
|
||||
install -m 0755 text2fst.py $(BIN_DIR)
|
||||
install -m 0755 symbols.py $(BIN_DIR)
|
||||
endif
|
||||
|
||||
.PHONY: uninstall
|
||||
uninstall:
|
||||
ifdef BIN_DIR
|
||||
rm $(BIN_DIR)/compiledic
|
||||
rm $(BIN_DIR)/text2fst.py
|
||||
rm $(BIN_DIR)/symbols.py
|
||||
endif
|
||||
|
||||
.PHONY: clean
|
||||
clean:
|
||||
|
|
@ -0,0 +1,214 @@
|
|||
#! /usr/bin/env perl
|
||||
|
||||
#package: UAM Text Tools
|
||||
#component: compiledic
|
||||
#version: 1.3
|
||||
#author: Tomasz Obrebski
|
||||
#author: Krzysztof Szarzyñski (2012 migration to OpenFST format)
|
||||
|
||||
use utf8;
|
||||
|
||||
use strict;
|
||||
use locale;
|
||||
use File::HomeDir;
|
||||
use File::Basename;
|
||||
use File::Temp;
|
||||
use File::Copy;
|
||||
use Getopt::Long;
|
||||
|
||||
|
||||
|
||||
my $linesPerFile = 20000;
|
||||
|
||||
|
||||
|
||||
Getopt::Long::Configure('no_ignore_case_always');
|
||||
my $help=0;
|
||||
GetOptions("help|h" => \$help);
|
||||
|
||||
if($help)
|
||||
{
|
||||
print <<'END'
|
||||
Usage: compiledic dictionaryfile.dic
|
||||
|
||||
The dictionary file must be UTF8 without Byte Order Mark (BOM).
|
||||
To remove BOM see removeBom.sh
|
||||
|
||||
Options:
|
||||
--help -h Help.
|
||||
END
|
||||
;
|
||||
exit 0;
|
||||
}
|
||||
|
||||
##################################################
|
||||
|
||||
@ARGV > 0 or die("Source dictionary not given.\n");
|
||||
|
||||
my $file = shift;
|
||||
|
||||
-f $file or die("Source dictionary not found.\n");
|
||||
|
||||
$file =~ /(.*)\.dic/ or die("The input file must have .dic extension.\n");
|
||||
|
||||
my $filenameprefix = $1;
|
||||
|
||||
##################################################
|
||||
|
||||
# Tworzymy katalog tymczasowy, gdzie wszystko bedzie umieszczane.
|
||||
my $tmp_root = File::Temp::tempdir( CLEANUP => 1 );
|
||||
print "Using temp dir: $tmp_root\n";
|
||||
|
||||
|
||||
##################################################
|
||||
# Tworzymy tabele symboli:
|
||||
print "Generating the symbols table\t\t";
|
||||
`python ./symbols.py > $tmp_root/symbols`;# or die "Failed!\n";
|
||||
print "OK\n";
|
||||
|
||||
|
||||
##################################################
|
||||
# Dzielenie pliku slownika:
|
||||
print "Dividing the dictionary file\t\t";
|
||||
|
||||
open(IN, $file);
|
||||
|
||||
my $lineCount = 0;
|
||||
my $fileCount = 0;
|
||||
|
||||
open(FILE, ">$tmp_root/slo_$fileCount");
|
||||
|
||||
while (<IN>) {
|
||||
if (++$lineCount >= $linesPerFile) {
|
||||
$fileCount++;
|
||||
$lineCount = 0;
|
||||
close(FILE);
|
||||
open(FILE, ">$tmp_root/slo_".$fileCount);
|
||||
}
|
||||
print(FILE $_);
|
||||
}
|
||||
print "OK\n";
|
||||
|
||||
##################################################
|
||||
# Budujemy male automaty:
|
||||
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++;
|
||||
`python text2fst.py < $tmp_root/slo_$i > $tmp_root/slownik_$i.fst`;
|
||||
#`fstcompile --acceptor $tmp_root/slownik_$i.fst $tmp_root/slownikC_$i.fst`;
|
||||
`fstcompile --acceptor --isymbols=$tmp_root/symbols $tmp_root/slownik_$i.fst $tmp_root/slownikC_$i.fst`;
|
||||
move("$tmp_root/slownikC_$i.fst", "$tmp_root/slownik_$i.bin") or die "Cant create slownik_$i.bin\n";
|
||||
}
|
||||
if ($dots < 32) {
|
||||
for (my $i=0; $i<32 - $dots; $i++) {
|
||||
print ".";
|
||||
}
|
||||
}
|
||||
|
||||
print "OK\n";
|
||||
|
||||
##################################################
|
||||
# Usuwamy czesci slownika:
|
||||
print "Deleteing $tmp_root/slo_ text files\t\t";
|
||||
unlink <$tmp_root/slo_*> or die "Faiiled\n";
|
||||
print "OK\n";
|
||||
|
||||
|
||||
##################################################
|
||||
# Budowanie koncowego automatu:
|
||||
print "Building final automaton";
|
||||
|
||||
#35 kropek...
|
||||
my $ndots=33;
|
||||
$filesPerDot = $fileCount/$ndots;
|
||||
$files=$filesPerDot;
|
||||
$dots=0;
|
||||
|
||||
|
||||
my $out_fst = "slownik.bin";
|
||||
my $tmp_fst = "slownik_T.bin";
|
||||
|
||||
|
||||
######################################################################
|
||||
# Budowanie jednego automatu
|
||||
######################################################################
|
||||
move("$tmp_root/slownik_0.bin", "$tmp_root/$out_fst") or die "Failed to move slownik_0.bin -> $out_fst\n";
|
||||
for (my $i=1; $i<=$fileCount; $i++) {
|
||||
|
||||
if ($files >= $filesPerDot) {
|
||||
$files = 0;
|
||||
print ".";
|
||||
$dots++;
|
||||
}
|
||||
$files++;
|
||||
`fstunion $tmp_root/$out_fst $tmp_root/slownik_$i.bin $tmp_root/$tmp_fst`;
|
||||
move("$tmp_root/$tmp_fst", "$tmp_root/$out_fst") or die "Failed at union: slownik_$i\n";
|
||||
`fstrmepsilon $tmp_root/$out_fst $tmp_root/$tmp_fst`;
|
||||
move("$tmp_root/$tmp_fst", "$tmp_root/$out_fst") or die "Failed at rmepsilon: slownik_$i\n";
|
||||
`fstdeterminize $tmp_root/$out_fst $tmp_root/$tmp_fst`;
|
||||
move("$tmp_root/$tmp_fst", "$tmp_root/$out_fst") or die "Failed at minimization: slownik_$i\n";
|
||||
`fstminimize $tmp_root/$out_fst $tmp_root/$tmp_fst`;
|
||||
|
||||
|
||||
move("$tmp_root/$tmp_fst", "$tmp_root/$out_fst") || die "Unable to move $tmp_root/$tmp_fst -> $out_fst!\n";
|
||||
|
||||
}
|
||||
|
||||
if ($dots < $ndots) {
|
||||
for (my $i=0; $i<$ndots - $dots; $i++) {
|
||||
print ".";
|
||||
}
|
||||
}
|
||||
|
||||
print "OK\n";
|
||||
|
||||
|
||||
|
||||
######################################################################
|
||||
# Minimalizacja automatu:
|
||||
######################################################################
|
||||
print "removing epsilon-transitions\t\t";
|
||||
`fstrmepsilon $tmp_root/$out_fst $tmp_root/$tmp_fst`;
|
||||
move("$tmp_root/$tmp_fst", "$tmp_root/$out_fst") or die "Failed\n";
|
||||
print "OK\n";
|
||||
|
||||
print "determinizing automaton\t\t";
|
||||
`fstdeterminize $tmp_root/$out_fst $tmp_root/$tmp_fst`;
|
||||
move("$tmp_root/$tmp_fst", "$tmp_root/$out_fst") or die "Failed\n";
|
||||
print "OK\n";
|
||||
|
||||
print "minimizing automaton\t\t";
|
||||
`fstminimize $tmp_root/$out_fst $tmp_root/$tmp_fst`;
|
||||
move("$tmp_root/$tmp_fst", "$tmp_root/$out_fst") or die "Failed\n";
|
||||
print "OK\n";
|
||||
|
||||
|
||||
|
||||
|
||||
print "moving the FST to compiledic directory\t\t";
|
||||
use Cwd;
|
||||
my $workdir = getcwd($0);
|
||||
move("$tmp_root/$out_fst", "$workdir/dictionary.bin") or die "Failed\n";
|
||||
print "OK\n";
|
||||
|
||||
########################################################
|
||||
# Sprzatanie:
|
||||
print "removing temporary files\t\t";
|
||||
|
||||
unlink <$tmp_root/*> or die "Failed\nCan't delete contents of $tmp_root \n";
|
||||
unlink ($tmp_root);
|
||||
print "OK\n";
|
||||
|
||||
print "Finished!\n";
|
||||
|
|
@ -0,0 +1,4 @@
|
|||
#!/usr/bin/env bash
|
||||
|
||||
# Remove bom from file.
|
||||
awk '{if(NR==1)sub(/^\xef\xbb\xbf/,"");print}' $1
|
||||
|
|
@ -0,0 +1,12 @@
|
|||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import sys
|
||||
import locale
|
||||
encoding = locale.getdefaultlocale()[1]
|
||||
|
||||
|
||||
sys.stdout.write(u"<eps>\t0\n".encode(encoding))
|
||||
for i in range(33,60000):
|
||||
line = u"%s\t%s\n"%(unichr(i), i)
|
||||
sys.stdout.write(line.encode(encoding))
|
||||
|
|
@ -0,0 +1,39 @@
|
|||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
"""-----------------------------------------------------------------------------
|
||||
# Name: text2FST
|
||||
# Purpose: A tool for translating a dictionary file into a OpenFST format.
|
||||
#
|
||||
# Author: Krzysztof Szarzynski <szarznyski.wmi.amu.edu.pl>
|
||||
#
|
||||
# Created: 19/11/2012
|
||||
# Copyright: (c) UAM Text Tools 2012
|
||||
# Licence: Simplified BSD License
|
||||
# Usage:
|
||||
# cat dictionary.dic | ./text2fst > output.fst
|
||||
# Warning: the dictionary.dic file must be UTF8 _without_ BOM
|
||||
#
|
||||
# TODO: Checking the BOM and removing it from the dictionary.file
|
||||
-----------------------------------------------------------------------------"""
|
||||
|
||||
import sys
|
||||
import locale
|
||||
|
||||
encoding = locale.getdefaultlocale()[1]
|
||||
|
||||
def prn(str):
|
||||
sys.stdout.write(str.encode(encoding))
|
||||
|
||||
begState = 0
|
||||
endState = 1
|
||||
eps = u"<eps>"
|
||||
currentState = begState
|
||||
for line in sys.stdin:
|
||||
prn(u"%s %s %s\n"%(begState, currentState, eps))
|
||||
line = line.decode('UTF-8')
|
||||
for letter in line:
|
||||
prn(u"%s %s %s\n"%(currentState, currentState+1, letter))
|
||||
currentState+=1
|
||||
prn(u"%s %s %s\n"%(currentState, endState, eps))
|
||||
print endState
|
||||
|
||||
|
|
@ -0,0 +1,56 @@
|
|||
include ../../config.mak
|
||||
|
||||
ifeq ($(BUILD_STATIC), yes)
|
||||
LDFLAGS += -static
|
||||
endif
|
||||
|
||||
LDFLAGS +=
|
||||
CXXFLAGS += -O2 -fpermissive
|
||||
|
||||
LIB_PATH=../lib
|
||||
COMMON_PATH=../common
|
||||
CMDLINE_FILE='"../cor/cmdline.h"'
|
||||
|
||||
all: cor
|
||||
|
||||
cor: main.cc corr.o $(LIB_PATH)/word.o \
|
||||
$(LIB_PATH)/auttools.o cmdline.c common_cor.o common.o
|
||||
$(CXX) $(CXXFLAGS) -D _CMDLINE_FILE=$(CMDLINE_FILE) main.cc corr.o common.o \
|
||||
$(LIB_PATH)/word.o $(LIB_PATH)/auttools.o cmdline.c common_cor.o \
|
||||
-o cor $(LDFLAGS)
|
||||
|
||||
corr.o: corr.cc corr.hh
|
||||
$(CXX) $(CXXFLAGS) -c corr.cc
|
||||
|
||||
common.o: $(COMMON_PATH)/cmdline_common.ggo $(COMMON_PATH)/common.cc \
|
||||
$(COMMON_PATH)/common.h
|
||||
$(CXX) $(CXXFLAGS) -c -D _CMDLINE_FILE=$(CMDLINE_FILE) $(COMMON_PATH)/common.cc
|
||||
|
||||
common_cor.o: cmdline.h common_cor.cc common_cor.h
|
||||
$(CXX) $(CXXFLAGS) -c -D _CMDLINE_FILE=$(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
|
||||
|
||||
.PHONY: install
|
||||
install:
|
||||
ifdef BIN_DIR
|
||||
install -m 0755 cor $(BIN_DIR)
|
||||
endif
|
||||
|
||||
.PHONY: uninstall
|
||||
uninstall:
|
||||
ifdef BIN_DIR
|
||||
rm $(BIN_DIR)/cor
|
||||
endif
|
||||
|
||||
clean: clean.cmdline
|
||||
rm *.o || true
|
||||
rm cor || true
|
||||
|
||||
clean.cmdline:
|
||||
rm cmdline.* || true
|
||||
|
||||
|
|
@ -0,0 +1,8 @@
|
|||
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
|
||||
|
|
@ -0,0 +1,29 @@
|
|||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
#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);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,19 @@
|
|||
#ifndef __COMMON_COR_H
|
||||
#define __COMMON_COR_H
|
||||
|
||||
#include <stdio.h>
|
||||
|
||||
//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
|
||||
|
|
@ -0,0 +1,142 @@
|
|||
//---------------------------------------------------------------------------
|
||||
|
||||
#include "corr.hh"
|
||||
|
||||
#define MAXPATH 256
|
||||
|
||||
#define min(x,y) ((x<y)?(x):(y))
|
||||
#define max(x,y) ((x>y)?(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]<ce)//if(H[(k)+2][(j)+2]<ce)
|
||||
ce=H2[k][j];//ce=H[(k)+2][(j)+2];
|
||||
}
|
||||
return ce;
|
||||
}
|
||||
|
||||
/*
|
||||
void Corr::recomputeH(int j)
|
||||
{
|
||||
for(int i=0;i<=m;i++)
|
||||
H[(i)+2][(j)+2]=ed(i,j);
|
||||
}
|
||||
*/
|
||||
|
||||
void Corr::recomputeH(int j)
|
||||
{
|
||||
int lo=max(0,j-t-2);
|
||||
int hi=min(m,j+t+2);
|
||||
for(int i=lo;i<=hi;++i)
|
||||
H2[i][j]=ed(i,j);//H[(i)+2][(j)+2]=ed(i,j);
|
||||
}
|
||||
|
||||
|
||||
int Corr::correct(const char* w, Words& tab)
|
||||
{
|
||||
long int path[MAXPATH]={0};
|
||||
int i; // row index (X)
|
||||
int j; // column index (Y)
|
||||
long state=0;
|
||||
|
||||
strcpy(X,w);
|
||||
m=strlen(X)-1;
|
||||
n=m+t;
|
||||
|
||||
for(i=(-2);i<=m;i++)
|
||||
H[(i)+2][(-2)+2]=n;
|
||||
for(i=(-1);i<=m;i++)
|
||||
H[(i)+2][(-1)+2]=(i)+1;
|
||||
for(j=(-2);j<=n;j++)
|
||||
H[(-2)+2][(j)+2]=n;
|
||||
for(j=(-1);j<=n;j++)
|
||||
H[(-1)+2][(j)+2]=(j)+1;
|
||||
|
||||
for(j=0; j<=n; ++j)
|
||||
for(i=0; i<=m; ++i)
|
||||
H[i+2][j+2]=t+1;
|
||||
|
||||
int more=1;
|
||||
bool cont=false;
|
||||
|
||||
strcpy(Y,"");
|
||||
j=0;
|
||||
state=0;
|
||||
int count=0;
|
||||
while(more)
|
||||
{
|
||||
if(!empty(state))
|
||||
{
|
||||
Y[j]=input(state);
|
||||
recomputeH(j);
|
||||
if(cuted(j)<=t)
|
||||
{
|
||||
int edd;
|
||||
if(final(next(state)) && (edd=H[(m)+2][(j)+2])<=t)
|
||||
{
|
||||
char* out=new char[j+2];
|
||||
strncpy(out,Y,j+1);
|
||||
out[j+1]='\0';
|
||||
// if(cont) putchar(' ');
|
||||
cont=true;
|
||||
// printf("%i,%s", edd,out);
|
||||
// cout << out << "(" << edd << ")" << endl;
|
||||
tab.add(out);
|
||||
count++;
|
||||
}
|
||||
path[j++]=state;
|
||||
state=next(state);
|
||||
continue;
|
||||
}
|
||||
else
|
||||
if(continued(state))
|
||||
{
|
||||
state++;
|
||||
continue;
|
||||
}
|
||||
}
|
||||
//backtracking
|
||||
do
|
||||
if(j>0)
|
||||
j--;
|
||||
else
|
||||
more=0;
|
||||
while(more && !continued(path[j]));
|
||||
state=path[j]+1;
|
||||
}
|
||||
return count;
|
||||
}
|
||||
|
||||
|
||||
//---------------------------------------------------------------------------
|
||||
|
||||
|
|
@ -0,0 +1,34 @@
|
|||
//---------------------------------------------------------------------------
|
||||
#ifndef _corr_hh
|
||||
#define _corr_hh
|
||||
//---------------------------------------------------------------------------
|
||||
|
||||
#include "../lib/tfti.h"
|
||||
#include "../lib/word.h"
|
||||
|
||||
class Corr : public TFTiv<char,char>
|
||||
{
|
||||
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<char,char>(a), H2((int(*)[100])&H[2][2]) { };
|
||||
|
||||
int correct(const char* w, Words& tab);
|
||||
};
|
||||
|
||||
//---------------------------------------------------------------------------
|
||||
#endif
|
||||
|
|
@ -0,0 +1,155 @@
|
|||
#include <stdlib.h>
|
||||
#include <ctype.h>
|
||||
#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 <locale.h>
|
||||
|
||||
|
||||
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<args.input_field_given; ++i) {
|
||||
// printf("\t%d. %s\n", i, args.input_field_arg[i]);
|
||||
//}
|
||||
|
||||
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
|
||||
{
|
||||
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(); ++i)
|
||||
{
|
||||
seg.form=tab[i].form();
|
||||
restorecasing(seg.form,seg.form,formcasing);
|
||||
seg.print(outline);
|
||||
fputs(outline, outputf);
|
||||
}
|
||||
--seg.auxn;
|
||||
}
|
||||
else
|
||||
{
|
||||
if(one_line)
|
||||
{
|
||||
char* p=corfield;
|
||||
for(int i=0; i<tab.count(); ++i)
|
||||
{
|
||||
restorecasing(tab[i].form(),tab[i].form(),formcasing);
|
||||
p += sprintf(p," %s%s",output_field_prefix,tab[i].form());
|
||||
}
|
||||
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=0; i<tab.count(); ++i)
|
||||
{
|
||||
restorecasing(tab[i].form(),tab[i].form(),formcasing);
|
||||
p += sprintf(p,(i==0)?"%s":";%s",tab[i].form());
|
||||
}
|
||||
|
||||
sprintf(p,"\n");
|
||||
|
||||
strcpy(outline,line);
|
||||
outline[strlen(outline)-1]='\0';
|
||||
strcat(outline,corfield);
|
||||
fputs(outline, outputf);
|
||||
}
|
||||
else
|
||||
{
|
||||
for(int i=0; i<tab.count(); ++i)
|
||||
{
|
||||
restorecasing(tab[i].form(),tab[i].form(),formcasing);
|
||||
sprintf(corfield," %s%s\n",output_field_prefix,tab[i].form());
|
||||
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);
|
||||
}
|
||||
|
|
@ -0,0 +1,72 @@
|
|||
include ../../config.mak
|
||||
|
||||
SHELL = /bin/sh
|
||||
LIB_PATH=../../lib
|
||||
COMMON_PATH=../common
|
||||
CMDLINE_FILE='"../dgp/cmdline.h"'
|
||||
|
||||
#vpath %.o .
|
||||
|
||||
ifeq ($(BUILD_STATIC), yes)
|
||||
LDFLAGS += -static
|
||||
endif
|
||||
|
||||
CXXFLAGS += -O2
|
||||
|
||||
sources = main.cc grammar.cc symbol.cc mgraph.cc sgraph.cc dgp0.cc cmdline.cc \
|
||||
$(COMMON_PATH)/common.cc global.cc
|
||||
|
||||
bin = dgp
|
||||
|
||||
# plik *.o sa umieszczane w podkatalogu o
|
||||
objs = $(sources:%.cc=%.o)
|
||||
|
||||
${bin}: ${objs}
|
||||
$(CXX) $(CXXFLAGS) -D _CMDLINE_FILE=$(CMDLINE_FILE) -o $@ ${objs} $(LDFLAGS)
|
||||
|
||||
include $(sources:.cc=.d)
|
||||
|
||||
%.o: %.cc
|
||||
$(CXX) -D _CMDLINE_FILE=$(CMDLINE_FILE) -c ${CXXFLAGS} -o $@ $<
|
||||
|
||||
%.d: %.cc
|
||||
$(CC) -MM $(CPPFLAGS) -D _CMDLINE_FILE=$(CMDLINE_FILE) $< > $@.$$$$; \
|
||||
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
|
||||
|
||||
.PHONY: install
|
||||
install:
|
||||
ifdef BIN_DIR
|
||||
install -m 0755 dgp $(BIN_DIR)
|
||||
install -m 0755 dgc $(BIN_DIR)
|
||||
install -m 0755 canonize $(BIN_DIR)
|
||||
install -m 0755 tre $(BIN_DIR)
|
||||
endif
|
||||
|
||||
.PHONY: uninstall
|
||||
uninstall:
|
||||
ifdef BIN_DIR
|
||||
rm $(BIN_DIR)/dgp
|
||||
rm $(BIN_DIR)/dgc
|
||||
rm $(BIN_DIR)/canonize
|
||||
rm $(BIN_DIR)/tre
|
||||
endif
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
|
||||
gram.dgp: gram.dgc
|
||||
dgc -c cats.dgc < gram.dgc > gram.dgp
|
||||
|
|
@ -0,0 +1,50 @@
|
|||
#!/usr/bin/perl
|
||||
|
||||
#package: UAM TExt Tools
|
||||
#component: canonize
|
||||
#version: 1.0
|
||||
#author: Tomasz Obrebski
|
||||
|
||||
use lib "/usr/local/lib/utt";
|
||||
use lib "$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 );
|
||||
}
|
||||
|
|
@ -0,0 +1,52 @@
|
|||
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"
|
||||
#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
|
||||
|
|
@ -0,0 +1,18 @@
|
|||
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"
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
#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
|
||||
|
|
@ -0,0 +1,292 @@
|
|||
#!/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, $file)){
|
||||
while (<CONFIG>) {
|
||||
chomp;
|
||||
s/#.*//;
|
||||
s/^\s+//;
|
||||
s/\s+$//;
|
||||
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: $gramfile!");
|
||||
}
|
||||
|
||||
while(<INPUT>)
|
||||
{
|
||||
s/#.*//;
|
||||
s/^\s+//;
|
||||
s/\s+$//;
|
||||
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(<DICFILE>)
|
||||
{
|
||||
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 $file |";
|
||||
while(<CATFILE>)
|
||||
{
|
||||
tr/ \t\n//d;
|
||||
next if !$_ || exists $cats{$_};
|
||||
print OUTPUT "CAT $_\n";
|
||||
++$ncat;
|
||||
$cats{$_}=attr::parse($_);
|
||||
}
|
||||
close CATFILE;
|
||||
}
|
||||
|
||||
|
|
@ -0,0 +1,217 @@
|
|||
#include "dgp0.hh"
|
||||
#include "global.hh"
|
||||
|
||||
extern Grammar grammar;
|
||||
extern MGraph mgraph;
|
||||
extern SGraph sgraph;
|
||||
|
||||
SNode* snodes;
|
||||
|
||||
extern bool debug;
|
||||
|
||||
list<int> nodelist;
|
||||
list<int>::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<MAXNODES>& newheadLH, bitset<MAXNODES>& newheadLV)
|
||||
{
|
||||
for(vector<int>::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<int>::iterator h, list<int>::iterator d, Role r)
|
||||
{
|
||||
NodeProp &oldheadprop = snodes[*h].prop;
|
||||
NodeProp newheadprop;
|
||||
bitset<MAXNODES> newheadLV;
|
||||
bitset<MAXNODES> newheadLH;
|
||||
bitset<MAXNODES> 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<int>::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<int>::iterator h, list<int>::iterator d, Role r)
|
||||
{
|
||||
NodeProp &oldheadprop = snodes[*h].prop;
|
||||
NodeProp newheadprop;
|
||||
bitset<MAXNODES> newheadLV;
|
||||
bitset<MAXNODES> newheadLH;
|
||||
bitset<MAXNODES> 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<int>::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<int>::iterator j)
|
||||
{
|
||||
for(list<int>::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<int>::iterator j)
|
||||
{
|
||||
for(list<int>::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<int>::iterator i = nodelist.begin();
|
||||
for(++i; i!=nodelist.end(); ++i)
|
||||
{
|
||||
for(vector<Arc>::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<Arc>::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<mgraph.n ; ++m)
|
||||
{
|
||||
int basenode = sgraph.add_base_snode(mgraph.nodes+m); // ma zwracaæ SNode*
|
||||
set_initial_constraints(basenode);
|
||||
nodelist.push_back(basenode);
|
||||
|
||||
if(debug) {sgraph.print_node_debug(stderr,"B ",basenode);} // STDOUT!!!
|
||||
|
||||
list<int>::iterator cursor=processed;
|
||||
while(++cursor != nodelist.end())
|
||||
{
|
||||
try_connect_dependents(cursor);
|
||||
try_connect_heads(cursor);
|
||||
processed=cursor;
|
||||
}
|
||||
}
|
||||
reverse_links();
|
||||
}
|
||||
|
|
@ -0,0 +1,12 @@
|
|||
#ifndef _DGP0_HH
|
||||
#define _DGP0_HH
|
||||
|
||||
#include "grammar.hh"
|
||||
#include "sgraph.hh"
|
||||
#include "mgraph.hh"
|
||||
|
||||
// API
|
||||
|
||||
void dgp0();
|
||||
|
||||
#endif
|
||||
|
|
@ -0,0 +1,5 @@
|
|||
|
||||
#include "global.hh"
|
||||
|
||||
bool debug = false;
|
||||
|
||||
|
|
@ -0,0 +1 @@
|
|||
extern bool debug;
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
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
|
||||
|
||||
|
|
@ -0,0 +1,181 @@
|
|||
|
||||
#include <stdio.h>
|
||||
|
||||
#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; i<cats_sz; ++i)
|
||||
connect[i].resize(cats_sz);
|
||||
obl.resize(cats_sz);
|
||||
}
|
||||
}
|
||||
|
||||
void Grammar::add_type(const char* s)
|
||||
{
|
||||
Role::add(s);
|
||||
if(Role::count()>types_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<Role::count(); ++i)
|
||||
if(lt[i][s])
|
||||
set_lt(i,t);
|
||||
for(int i=0; i<Role::count(); ++i)
|
||||
if(lt[t][i])
|
||||
set_lt(s,i);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
void Grammar::compute_gt()
|
||||
{
|
||||
for(Role s=0; s<Role::count(); ++s)
|
||||
for(Role t=0; t<Role::count(); ++t)
|
||||
if(lt[s][t])
|
||||
gt[t].set(s);
|
||||
}
|
||||
|
||||
|
||||
bool Grammar::read(FILE* f)
|
||||
{
|
||||
int lineno=0;
|
||||
char line[MAXLINE]; // line has the structure: key [arg1 [arg2 [arg3]]]
|
||||
char key[MAXLINE];
|
||||
char arg1[MAXLINE];
|
||||
char arg2[MAXLINE];
|
||||
char arg3[MAXLINE];
|
||||
|
||||
while(fgets(line,MAXLINE,f))
|
||||
{
|
||||
lineno++;
|
||||
int fields=sscanf(line,"%s %s %s %s",key,arg1,arg2,arg3);
|
||||
|
||||
if(fields<1 || key[0]=='#') continue; // skip empty lines and comments
|
||||
|
||||
if (strcmp(key,"CAT")==0 && fields>=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<Cat::count(); ++i)
|
||||
fprintf(f,"CAT\t%s\n",i.str());
|
||||
|
||||
for(Role i=1; i<Role::count(); ++i)
|
||||
fprintf(f,"ROLE\t%s\n",i.str());
|
||||
|
||||
for(Role i=1; i<Role::count(); ++i)
|
||||
if(sgl.test(i)) fprintf(f,"SGL\t%s\n",i.str());
|
||||
|
||||
for(Role i=1; i<Role::count(); ++i)
|
||||
if(left.test(i)) fprintf(f,"LEFT\t%s\n",i.str());
|
||||
|
||||
for(Role i=1; i<Role::count(); ++i)
|
||||
if(right.test(i)) fprintf(f,"RIGHT\t%s\n",i.str());
|
||||
|
||||
for(Cat c=1; c<Cat::count(); ++c)
|
||||
for(Role r=1; r<Role::count(); ++r)
|
||||
if(obl[c].test(r)) fprintf(f,"REQ\t%s\t%s\n",c.str(),r.str());
|
||||
|
||||
for(Cat c=1; c<Cat::count(); ++c)
|
||||
for(Cat d=1; d<Cat::count(); ++d)
|
||||
for(Role t=1; t<Role::count(); ++t)
|
||||
if(connect[c][d].count(t))
|
||||
fprintf(f,"LINK\t%s\t%s\t%s\n",c.str(),d.str(),t.str());
|
||||
|
||||
for(Flag i=1; i<Flag::count(); ++i)
|
||||
fprintf(f,"FLAG\t%s\n",i.str());
|
||||
}
|
||||
|
||||
|
|
@ -0,0 +1,79 @@
|
|||
#ifndef _GRAMMAR_HH
|
||||
#define _GRAMMAR_HH
|
||||
|
||||
#include <bitset>
|
||||
#include <vector>
|
||||
#include <list>
|
||||
#include <set>
|
||||
|
||||
#include "const.hh"
|
||||
#include "thesymbols.hh"
|
||||
#include "sgraph.hh"
|
||||
|
||||
|
||||
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
|
||||
|
|
@ -0,0 +1,121 @@
|
|||
|
||||
/**
|
||||
* 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<segcount; ++si)
|
||||
{
|
||||
if(seg_mnode[si]>=0)
|
||||
{
|
||||
MNode& m=mgraph.nodes[seg_mnode[si]];
|
||||
for(vector<int>::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);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,54 @@
|
|||
|
||||
#include "mgraph.hh"
|
||||
#include "thesymbols.hh"
|
||||
#include "const.hh"
|
||||
|
||||
#include <stdio.h>
|
||||
|
||||
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++;
|
||||
}
|
||||
|
||||
|
|
@ -0,0 +1,34 @@
|
|||
#ifndef _MGRAPH_HH
|
||||
#define _MGRAPH_HH
|
||||
|
||||
#include <vector>
|
||||
|
||||
#include "const.hh"
|
||||
#include "thesymbols.hh"
|
||||
#include "../common/common.h"
|
||||
|
||||
class MNode
|
||||
{
|
||||
public:
|
||||
|
||||
char type[MAXFORMLEN];
|
||||
Cat cat;
|
||||
int pos;
|
||||
vector<MNode*> pred;
|
||||
vector<int> snodes;
|
||||
|
||||
void clear() { snodes.clear(); };
|
||||
};
|
||||
|
||||
class MGraph
|
||||
{
|
||||
public:
|
||||
|
||||
MNode nodes[MAXNODES];
|
||||
int n;
|
||||
|
||||
void clear() { n=0; };
|
||||
int add_node(char* seg);
|
||||
};
|
||||
|
||||
#endif
|
||||
|
|
@ -0,0 +1,165 @@
|
|||
#include "global.hh"
|
||||
#include "sgraph.hh"
|
||||
#include "mgraph.hh"
|
||||
#include "grammar.hh"
|
||||
#include "const.hh"
|
||||
#include <stdio.h>
|
||||
|
||||
|
||||
int SGraph::add_base_snode(MNode* mn)
|
||||
{
|
||||
int nodeind=n;
|
||||
SNode &node=nodes[n];
|
||||
|
||||
node.clear();
|
||||
|
||||
node.mnode=mn;
|
||||
|
||||
for(vector<MNode*>::iterator pm=node.mnode->pred.begin(); pm!=node.mnode->pred.end(); ++pm)
|
||||
for(vector<int>::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<Arc>::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<Arc>::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<MNode*>::iterator pm=node.mnode->pred.begin(); pm!=node.mnode->pred.end(); ++pm)
|
||||
for(vector<int>::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);
|
||||
}
|
||||
|
|
@ -0,0 +1,108 @@
|
|||
#ifndef _SGRAPH_HH
|
||||
#define _SGRAPH_HH
|
||||
|
||||
#include <stdio.h>
|
||||
|
||||
#include <list>
|
||||
#include <vector>
|
||||
#include <bitset>
|
||||
|
||||
#include "const.hh"
|
||||
#include "thesymbols.hh"
|
||||
|
||||
|
||||
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<MAXTYPES> required;
|
||||
bitset<MAXTYPES> 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<MAXNODES> LV;
|
||||
bitset<MAXNODES> LH;
|
||||
bitset<MAXNODES> LD;
|
||||
bool in_LH;
|
||||
|
||||
vector<Arc> heads;
|
||||
vector<Arc> 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<int> 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
|
||||
|
|
@ -0,0 +1,39 @@
|
|||
#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<int space>
|
||||
//Symbols Symbol<space>::defs;
|
||||
|
|
@ -0,0 +1,143 @@
|
|||
#ifndef _SYMBOL_HH
|
||||
#define _SYMBOL_HH
|
||||
|
||||
#include <ext/hash_map>
|
||||
//#include <ext/hash_fun.h>
|
||||
#include <string>
|
||||
#include <string.h>
|
||||
#include <fstream>
|
||||
#include <vector>
|
||||
#include <iostream>
|
||||
|
||||
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<const char*,int,hash<const char*>,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<const char*> 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 <int space>
|
||||
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<space> 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<count())?defs[val]:NULL; };
|
||||
|
||||
/// Symbol to int& conversion.
|
||||
/** Provides a way to iterate through symbols, eg:
|
||||
* for(Symbol<0> 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 <int space>
|
||||
void Symbol<space>::print()
|
||||
{
|
||||
for(Symbol i=0; i<count(); ++i)
|
||||
cout << (int)i << ": " << (const char*)i << endl;
|
||||
}
|
||||
|
||||
template<int space>
|
||||
Symbols Symbol<space>::defs;
|
||||
|
||||
template<int space>
|
||||
bool operator<(const Symbol<space>& s, const Symbol<space>& t)
|
||||
{
|
||||
return (int)s < (int)t;
|
||||
}
|
||||
|
||||
#endif
|
||||
|
|
@ -0,0 +1,29 @@
|
|||
#ifndef __THESYMBOLS__HH
|
||||
#define __THESYMBOLS__HH
|
||||
|
||||
#include "symbol.hh"
|
||||
#include "const.hh"
|
||||
|
||||
#include <list>
|
||||
#include <set>
|
||||
#include <bitset>
|
||||
|
||||
typedef Symbol<1> Cat;
|
||||
|
||||
typedef Symbol<2> Role;
|
||||
typedef list<Role> RoleList;
|
||||
typedef list<Role>::iterator RoleListIter;
|
||||
typedef bitset<MAXTYPES> RoleSet;
|
||||
typedef set<Role> Roles;
|
||||
typedef Roles::iterator RolesIter;
|
||||
|
||||
typedef Symbol<3> Constr;
|
||||
typedef list<Constr> ConstrList;
|
||||
typedef list<Constr>::iterator ConstrListIter;
|
||||
|
||||
typedef Symbol<4> Rel;
|
||||
|
||||
typedef Symbol<5> Flag;
|
||||
typedef bitset<MAXFLAGS> FlagSet;
|
||||
|
||||
#endif
|
||||
|
|
@ -0,0 +1,304 @@
|
|||
#!/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)
|
||||
|
|
@ -0,0 +1,2 @@
|
|||
#include "uttcommon.h"
|
||||
|
||||
|
|
@ -0,0 +1,146 @@
|
|||
#ifndef __COMMON_H
|
||||
#define __COMMON_H
|
||||
|
||||
#include <stdio.h>
|
||||
|
||||
/**************************************************
|
||||
* 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
|
||||
|
|
@ -0,0 +1,25 @@
|
|||
include ../../config.mak
|
||||
|
||||
ifeq ($(BUILD_STATIC), yes)
|
||||
LDFLAGS += -static
|
||||
endif
|
||||
|
||||
CFLAGS +=-O2
|
||||
|
||||
fla:
|
||||
$(CC) $(CFLAGS) fla.c -o fla $(LDFLAGS)
|
||||
|
||||
.PHONY: install
|
||||
install:
|
||||
ifdef BIN_DIR
|
||||
install -m 0755 fla $(BIN_DIR)
|
||||
endif
|
||||
|
||||
.PHONY: uninstall
|
||||
uninstall:
|
||||
ifdef BIN_DIR
|
||||
rm $(BIN_DIR)/fla
|
||||
endif
|
||||
|
||||
clean:
|
||||
rm fla || true
|
||||
|
|
@ -0,0 +1,68 @@
|
|||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
#include <regex.h>
|
||||
|
||||
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;
|
||||
|
||||
}
|
||||
|
||||
|
|
@ -0,0 +1,18 @@
|
|||
include ../../config.mak
|
||||
|
||||
gph:
|
||||
|
||||
.PHONY: install
|
||||
install:
|
||||
ifdef BIN_DIR
|
||||
install -m 0755 gph $(BIN_DIR)
|
||||
endif
|
||||
|
||||
|
||||
.PHONY: uninstall
|
||||
uninstall:
|
||||
ifdef BIN_DIR
|
||||
rm $(BIN_DIR)/gph
|
||||
endif
|
||||
|
||||
clean:
|
||||
|
|
@ -0,0 +1,162 @@
|
|||
#!/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, $file)){
|
||||
while (<CONFIG>) {
|
||||
chomp;
|
||||
s/#.*//;
|
||||
s/^\s+//;
|
||||
s/\s+$//;
|
||||
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(<INPUT>)
|
||||
{
|
||||
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";
|
||||
}
|
||||
|
||||
|
|
@ -0,0 +1,17 @@
|
|||
include ../../config.mak
|
||||
|
||||
grp:
|
||||
|
||||
.PHONY: install
|
||||
install:
|
||||
ifdef BIN_DIR
|
||||
install -m 0755 grp $(BIN_DIR)
|
||||
endif
|
||||
|
||||
.PHONY: uninstall
|
||||
uninstall:
|
||||
ifdef BIN_DIR
|
||||
rm $(BIN_DIR)/grp
|
||||
endif
|
||||
|
||||
clean:
|
||||
|
|
@ -0,0 +1,170 @@
|
|||
#!/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, $file)){
|
||||
while (<CONFIG>) {
|
||||
chomp;
|
||||
s/#.*//;
|
||||
s/^\s+//;
|
||||
s/\s+$//;
|
||||
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£ÑÓ¦¬¯0-9_]/g;
|
||||
$grepre =~ s/\\W/[^a-z±æê³ñ󶼿A-Z¡ÆÊ£ÑÓ¦¬¯0-9_ [:cntrl:]]/g;
|
||||
# extensions
|
||||
$grepre =~ s/\\l/[a-z±æê³ñ󶼿]/g; #lowercase letter
|
||||
$grepre =~ s/\\L/[A-Z¡ÆÊ£ÑÓ¦¬¯]/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.$postproc;
|
||||
|
|
@ -0,0 +1,55 @@
|
|||
include ../../config.mak
|
||||
|
||||
ifeq ($(BUILD_STATIC), yes)
|
||||
LDFLAGS += -static
|
||||
endif
|
||||
|
||||
LDFLAGS +=
|
||||
CXXFLAGS += -O2 -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
|
||||
$(CXX) $(CXXFLAGS) main.cc guess.o \
|
||||
$(LIB_PATH)/auttools.o $(LIB_PATH)/word.o cmdline.c common.o common_guess.o \
|
||||
-o gue $(LDFLAGS)
|
||||
|
||||
guess.o: guess.h guess.cc
|
||||
$(CXX) $(CXXFLAGS) -c guess.cc
|
||||
|
||||
common_guess.o: cmdline.h common_guess.cc common_guess.h
|
||||
$(CXX) $(CXXFLAGS) -c common_guess.cc
|
||||
|
||||
common.o: $(COMMON_PATH)/cmdline_common.ggo $(COMMON_PATH)/common.cc \
|
||||
$(COMMON_PATH)/common.h
|
||||
$(CXX) $(CXXFLAGS) -c -D _CMDLINE_FILE=$(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
|
||||
|
||||
.PHONY: install
|
||||
install:
|
||||
ifdef BIN_DIR
|
||||
install -m 0755 gue $(BIN_DIR)
|
||||
endif
|
||||
|
||||
.PHONY: uninstall
|
||||
uninstall:
|
||||
ifdef BIN_DIR
|
||||
rm $(BIN_DIR)/gue
|
||||
endif
|
||||
|
|
@ -0,0 +1,12 @@
|
|||
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
|
||||
|
||||
|
|
@ -0,0 +1,60 @@
|
|||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
#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;
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,20 @@
|
|||
#ifndef __COMMON_GUESS_H
|
||||
#define __COMMON_GUESS_H
|
||||
|
||||
#include <stdio.h>
|
||||
#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
|
||||
|
|
@ -0,0 +1,138 @@
|
|||
|
||||
#include "guess.h"
|
||||
|
||||
#include <cstring>
|
||||
#include <iostream>
|
||||
#include <cstdlib>
|
||||
#include <cassert>
|
||||
#include <ctime>
|
||||
|
||||
#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 '_'
|
||||
|
||||
Guess::Guess(const char* suf_file)
|
||||
: _suf(suf_file) {
|
||||
/* _suf = NULL;
|
||||
_pref = NULL;
|
||||
|
||||
if (strlen(suf_file) > 0)
|
||||
_suf = new TFTiv<char, char>(suf_file);
|
||||
if (strlen(pref_file) > 0)
|
||||
_pref = new TFTiv<char, char>(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;
|
||||
|
||||
}
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue