sync 2.8.3 into CVS
This commit is contained in:
Caolán McNamara
parent
058b24a9c3
commit
39bf406090
7
AUTHORS
7
AUTHORS
|
|
@ -6,12 +6,11 @@ and http://packages.debian.org/unstable/source/libhnj
|
|||
|
||||
This subset of Libhnj was extended by
|
||||
Peter Novodvorsky <nidd at alt-linux dot org> (OOo integration),
|
||||
László Németh <nemeth at OOo> (non-standard and compound hyphenation
|
||||
with Unicode support),
|
||||
László Németh <nemeth at numbertext dot org> (non-standard and compound
|
||||
hyphenation with Unicode support),
|
||||
Nanning Buitenhuis <nanning at elvenkind dot com> (substrings.c)
|
||||
|
||||
Write bug reports to László Németh or to the lingu-dev mailing list of
|
||||
OpenOffice.org (after subscription: http://lingucomponent.openoffice.org)
|
||||
Write bug reports to László Németh or in the bug tracker of hunspell.sf.net.
|
||||
|
||||
---
|
||||
Please contact Raph Levien for information about licensing for
|
||||
|
|
|
|||
49
ChangeLog
49
ChangeLog
|
|
@ -1,16 +1,49 @@
|
|||
2011-10-10 László Németh <nemeth at numbertext dot org>:
|
||||
* hyphen.c:
|
||||
- fix NOHYPHEN (hyphenation vector
|
||||
modified by 0 instead of '0')
|
||||
- fix non-balanced hyphenation of LibreOffice/OOo 3.3 by
|
||||
1-1/=,1,1 alternative pattern (removing hyphen)
|
||||
- set default COMPOUNDHYPHENMIN=3 at hyphen and apostrophes
|
||||
- fix VERBOSE to support multilevel patterns
|
||||
|
||||
* example.c: new option: -n to print hyphenation vector
|
||||
|
||||
2011-10-07 László Németh <nemeth at numbertext dot org>:
|
||||
* hyphen.c: use explicite compoundhyphenmin values of the
|
||||
dictionary also for the implicite NOHYPHEN hyphenation
|
||||
|
||||
2011-10-06 László Németh <nemeth at numbertext dot org>:
|
||||
* hyphen.c: force minimal lefthyphenmin and righthyphenmin values
|
||||
of the dictionary
|
||||
|
||||
2011-10-04 László Németh <nemeth at numbertext dot org>:
|
||||
* hyphen.c: ignore leading and ending numbers (eg. fix
|
||||
hyphenation of words with manual or field-based
|
||||
indexes in LibreOffice/OpenOffice.org)
|
||||
* tests/num.*: new test files
|
||||
|
||||
* hyphen.c: default NOHYPHEN separators: hyphen and
|
||||
ASCII apostrophe + (only in UTF-8 encoding) endash (U+2013)
|
||||
and typographical apostrophe (U+2019): fix hyphenation of
|
||||
words with hyphens, n-dashes or apostrophes in LibreOffice/OOo.
|
||||
* README.compound: description
|
||||
|
||||
* hyph_en_US.dic: remove explicite NOHYPHEN declaration
|
||||
|
||||
2010-12-01 László Németh <nemeth at OOo>:
|
||||
* hyphen.c: NOHYPHEN fix for a special case (NOHYPHEN
|
||||
character in starting position, eg. "-example")
|
||||
* hyphen.c: NOHYPHEN fix for a special case (NOHYPHEN
|
||||
character in starting position, eg. "-example")
|
||||
|
||||
2010-11-27 László Németh <nemeth at OOo>:
|
||||
* hyphen.c: add NOHYPHEN feature
|
||||
to handle special hyphenation at hyphens and apostrophes,
|
||||
see README.compound
|
||||
* hyphen.c: add NOHYPHEN feature
|
||||
to handle special hyphenation at hyphens and apostrophes,
|
||||
see README.compound
|
||||
|
||||
* tests/{rhmin, hyphen}: new test files
|
||||
* tests/{rhmin, hyphen}: new test files
|
||||
|
||||
* ooopatch.sed. hyph_en_US.dic: replace and improve old hack
|
||||
with NOHYPHEN
|
||||
* ooopatch.sed. hyph_en_US.dic: replace and improve old hack
|
||||
with NOHYPHEN
|
||||
|
||||
2010-07-18 Caolán McNamara <cmc at OOo>:
|
||||
* remove csutil.* as more trouble that its
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@ SUBDIRS= doc tests
|
|||
|
||||
lib_LTLIBRARIES = libhyphen.la
|
||||
libhyphen_la_SOURCES = hnjalloc.c hyphen.c
|
||||
libhyphen_la_LDFLAGS = -version-info 2:0:2
|
||||
libhyphen_la_LDFLAGS = -version-info 2:1:2
|
||||
include_HEADERS = hyphen.h
|
||||
noinst_HEADERS = hnjalloc.h
|
||||
|
||||
|
|
@ -21,7 +21,7 @@ hyph_DATA = hyph_en_US.dic
|
|||
EXTRA_DIST = checkme.lst hyphen.tex tbhyphext.tex tbhyphext.sh \
|
||||
README.compound README.hyphen README.nonstandard substrings.pl hyphen.patch \
|
||||
COPYING.MPL COPYING.LGPL hyph_en_US.dic README_hyph_en_US.txt lig.awk \
|
||||
ligpatch.txt ooopatch.sed
|
||||
ligpatch.txt
|
||||
|
||||
hyphen.us3:
|
||||
cp -f $(srcdir)/hyphen.tex hyphen.us
|
||||
|
|
@ -31,8 +31,7 @@ hyphen.us3:
|
|||
cat $(srcdir)/ligpatch.txt >>hyphen.us3
|
||||
|
||||
hyph_en_US.dic: hyphen.us3
|
||||
perl $(srcdir)/substrings.pl hyphen.us3 hyphen.us4 UTF-8 2 3 >/dev/null
|
||||
cat hyphen.us4 | $(SED) -f $(srcdir)/ooopatch.sed >hyph_en_US.dic
|
||||
perl $(srcdir)/substrings.pl hyphen.us3 hyph_en_US.dic UTF-8 2 3 >/dev/null
|
||||
|
||||
clean-local:
|
||||
rm -rf hyphen.us* hyph_en_US.dic
|
||||
|
|
|
|||
93
Makefile.in
93
Makefile.in
|
|
@ -1,9 +1,9 @@
|
|||
# Makefile.in generated by automake 1.11.3 from Makefile.am.
|
||||
# Makefile.in generated by automake 1.11.1 from Makefile.am.
|
||||
# @configure_input@
|
||||
|
||||
# Copyright (C) 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002,
|
||||
# 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software
|
||||
# Foundation, Inc.
|
||||
# 2003, 2004, 2005, 2006, 2007, 2008, 2009 Free Software Foundation,
|
||||
# Inc.
|
||||
# This Makefile.in is free software; the Free Software Foundation
|
||||
# gives unlimited permission to copy and/or distribute it,
|
||||
# with or without modifications, as long as this notice is preserved.
|
||||
|
|
@ -75,12 +75,6 @@ am__nobase_list = $(am__nobase_strip_setup); \
|
|||
am__base_list = \
|
||||
sed '$$!N;$$!N;$$!N;$$!N;$$!N;$$!N;$$!N;s/\n/ /g' | \
|
||||
sed '$$!N;$$!N;$$!N;$$!N;s/\n/ /g'
|
||||
am__uninstall_files_from_dir = { \
|
||||
test -z "$$files" \
|
||||
|| { test ! -d "$$dir" && test ! -f "$$dir" && test ! -r "$$dir"; } \
|
||||
|| { echo " ( cd '$$dir' && rm -f" $$files ")"; \
|
||||
$(am__cd) "$$dir" && rm -f $$files; }; \
|
||||
}
|
||||
am__installdirs = "$(DESTDIR)$(libdir)" "$(DESTDIR)$(bindir)" \
|
||||
"$(DESTDIR)$(hyphdir)" "$(DESTDIR)$(includedir)"
|
||||
LTLIBRARIES = $(lib_LTLIBRARIES)
|
||||
|
|
@ -136,11 +130,9 @@ DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST)
|
|||
distdir = $(PACKAGE)-$(VERSION)
|
||||
top_distdir = $(distdir)
|
||||
am__remove_distdir = \
|
||||
if test -d "$(distdir)"; then \
|
||||
find "$(distdir)" -type d ! -perm -200 -exec chmod u+w {} ';' \
|
||||
&& rm -rf "$(distdir)" \
|
||||
|| { sleep 5 && rm -rf "$(distdir)"; }; \
|
||||
else :; fi
|
||||
{ test ! -d "$(distdir)" \
|
||||
|| { find "$(distdir)" -type d ! -perm -200 -exec chmod u+w {} ';' \
|
||||
&& rm -fr "$(distdir)"; }; }
|
||||
am__relativize = \
|
||||
dir0=`pwd`; \
|
||||
sed_first='s,^\([^/]*\)/.*$$,\1,'; \
|
||||
|
|
@ -169,8 +161,6 @@ am__relativize = \
|
|||
DIST_ARCHIVES = $(distdir).tar.gz
|
||||
GZIP_ENV = --best
|
||||
distuninstallcheck_listfiles = find . -type f -print
|
||||
am__distuninstallcheck_listfiles = $(distuninstallcheck_listfiles) \
|
||||
| sed 's|^\./|$(prefix)/|' | grep -v '$(infodir)/dir$$'
|
||||
distcleancheck_listfiles = find . -type f -print
|
||||
ACLOCAL = @ACLOCAL@
|
||||
AMTAR = @AMTAR@
|
||||
|
|
@ -187,7 +177,6 @@ CPPFLAGS = @CPPFLAGS@
|
|||
CYGPATH_W = @CYGPATH_W@
|
||||
DEFS = @DEFS@
|
||||
DEPDIR = @DEPDIR@
|
||||
DLLTOOL = @DLLTOOL@
|
||||
DSYMUTIL = @DSYMUTIL@
|
||||
DUMPBIN = @DUMPBIN@
|
||||
ECHO_C = @ECHO_C@
|
||||
|
|
@ -211,7 +200,6 @@ LIPO = @LIPO@
|
|||
LN_S = @LN_S@
|
||||
LTLIBOBJS = @LTLIBOBJS@
|
||||
MAKEINFO = @MAKEINFO@
|
||||
MANIFEST_TOOL = @MANIFEST_TOOL@
|
||||
MKDIR_P = @MKDIR_P@
|
||||
NM = @NM@
|
||||
NMEDIT = @NMEDIT@
|
||||
|
|
@ -237,7 +225,6 @@ abs_builddir = @abs_builddir@
|
|||
abs_srcdir = @abs_srcdir@
|
||||
abs_top_builddir = @abs_top_builddir@
|
||||
abs_top_srcdir = @abs_top_srcdir@
|
||||
ac_ct_AR = @ac_ct_AR@
|
||||
ac_ct_CC = @ac_ct_CC@
|
||||
ac_ct_DUMPBIN = @ac_ct_DUMPBIN@
|
||||
am__include = @am__include@
|
||||
|
|
@ -270,6 +257,7 @@ libdir = @libdir@
|
|||
libexecdir = @libexecdir@
|
||||
localedir = @localedir@
|
||||
localstatedir = @localstatedir@
|
||||
lt_ECHO = @lt_ECHO@
|
||||
mandir = @mandir@
|
||||
mkdir_p = @mkdir_p@
|
||||
oldincludedir = @oldincludedir@
|
||||
|
|
@ -288,7 +276,7 @@ top_srcdir = @top_srcdir@
|
|||
SUBDIRS = doc tests
|
||||
lib_LTLIBRARIES = libhyphen.la
|
||||
libhyphen_la_SOURCES = hnjalloc.c hyphen.c
|
||||
libhyphen_la_LDFLAGS = -version-info 2:0:2
|
||||
libhyphen_la_LDFLAGS = -version-info 2:1:2
|
||||
include_HEADERS = hyphen.h
|
||||
noinst_HEADERS = hnjalloc.h
|
||||
substrings_SOURCES = substrings.c
|
||||
|
|
@ -302,13 +290,13 @@ hyph_DATA = hyph_en_US.dic
|
|||
EXTRA_DIST = checkme.lst hyphen.tex tbhyphext.tex tbhyphext.sh \
|
||||
README.compound README.hyphen README.nonstandard substrings.pl hyphen.patch \
|
||||
COPYING.MPL COPYING.LGPL hyph_en_US.dic README_hyph_en_US.txt lig.awk \
|
||||
ligpatch.txt ooopatch.sed
|
||||
ligpatch.txt
|
||||
|
||||
all: all-recursive
|
||||
|
||||
.SUFFIXES:
|
||||
.SUFFIXES: .c .lo .o .obj
|
||||
am--refresh: Makefile
|
||||
am--refresh:
|
||||
@:
|
||||
$(srcdir)/Makefile.in: $(srcdir)/Makefile.am $(am__configure_deps)
|
||||
@for dep in $?; do \
|
||||
|
|
@ -373,7 +361,7 @@ clean-libLTLIBRARIES:
|
|||
echo "rm -f \"$${dir}/so_locations\""; \
|
||||
rm -f "$${dir}/so_locations"; \
|
||||
done
|
||||
libhyphen.la: $(libhyphen_la_OBJECTS) $(libhyphen_la_DEPENDENCIES) $(EXTRA_libhyphen_la_DEPENDENCIES)
|
||||
libhyphen.la: $(libhyphen_la_OBJECTS) $(libhyphen_la_DEPENDENCIES)
|
||||
$(libhyphen_la_LINK) -rpath $(libdir) $(libhyphen_la_OBJECTS) $(libhyphen_la_LIBADD) $(LIBS)
|
||||
|
||||
clean-noinstPROGRAMS:
|
||||
|
|
@ -384,10 +372,10 @@ clean-noinstPROGRAMS:
|
|||
list=`for p in $$list; do echo "$$p"; done | sed 's/$(EXEEXT)$$//'`; \
|
||||
echo " rm -f" $$list; \
|
||||
rm -f $$list
|
||||
example$(EXEEXT): $(example_OBJECTS) $(example_DEPENDENCIES) $(EXTRA_example_DEPENDENCIES)
|
||||
example$(EXEEXT): $(example_OBJECTS) $(example_DEPENDENCIES)
|
||||
@rm -f example$(EXEEXT)
|
||||
$(LINK) $(example_OBJECTS) $(example_LDADD) $(LIBS)
|
||||
substrings$(EXEEXT): $(substrings_OBJECTS) $(substrings_DEPENDENCIES) $(EXTRA_substrings_DEPENDENCIES)
|
||||
substrings$(EXEEXT): $(substrings_OBJECTS) $(substrings_DEPENDENCIES)
|
||||
@rm -f substrings$(EXEEXT)
|
||||
$(LINK) $(substrings_OBJECTS) $(substrings_LDADD) $(LIBS)
|
||||
install-binSCRIPTS: $(bin_SCRIPTS)
|
||||
|
|
@ -421,7 +409,9 @@ uninstall-binSCRIPTS:
|
|||
@list='$(bin_SCRIPTS)'; test -n "$(bindir)" || exit 0; \
|
||||
files=`for p in $$list; do echo "$$p"; done | \
|
||||
sed -e 's,.*/,,;$(transform)'`; \
|
||||
dir='$(DESTDIR)$(bindir)'; $(am__uninstall_files_from_dir)
|
||||
test -n "$$list" || exit 0; \
|
||||
echo " ( cd '$(DESTDIR)$(bindir)' && rm -f" $$files ")"; \
|
||||
cd "$(DESTDIR)$(bindir)" && rm -f $$files
|
||||
|
||||
mostlyclean-compile:
|
||||
-rm -f *.$(OBJEXT)
|
||||
|
|
@ -480,7 +470,9 @@ uninstall-hyphDATA:
|
|||
@$(NORMAL_UNINSTALL)
|
||||
@list='$(hyph_DATA)'; test -n "$(hyphdir)" || list=; \
|
||||
files=`for p in $$list; do echo $$p; done | sed -e 's|^.*/||'`; \
|
||||
dir='$(DESTDIR)$(hyphdir)'; $(am__uninstall_files_from_dir)
|
||||
test -n "$$files" || exit 0; \
|
||||
echo " ( cd '$(DESTDIR)$(hyphdir)' && rm -f" $$files ")"; \
|
||||
cd "$(DESTDIR)$(hyphdir)" && rm -f $$files
|
||||
install-includeHEADERS: $(include_HEADERS)
|
||||
@$(NORMAL_INSTALL)
|
||||
test -z "$(includedir)" || $(MKDIR_P) "$(DESTDIR)$(includedir)"
|
||||
|
|
@ -498,7 +490,9 @@ uninstall-includeHEADERS:
|
|||
@$(NORMAL_UNINSTALL)
|
||||
@list='$(include_HEADERS)'; test -n "$(includedir)" || list=; \
|
||||
files=`for p in $$list; do echo $$p; done | sed -e 's|^.*/||'`; \
|
||||
dir='$(DESTDIR)$(includedir)'; $(am__uninstall_files_from_dir)
|
||||
test -n "$$files" || exit 0; \
|
||||
echo " ( cd '$(DESTDIR)$(includedir)' && rm -f" $$files ")"; \
|
||||
cd "$(DESTDIR)$(includedir)" && rm -f $$files
|
||||
|
||||
# This directory's subdirectories are mostly independent; you can cd
|
||||
# into them and run `make' without going through this Makefile.
|
||||
|
|
@ -707,11 +701,7 @@ dist-gzip: distdir
|
|||
$(am__remove_distdir)
|
||||
|
||||
dist-bzip2: distdir
|
||||
tardir=$(distdir) && $(am__tar) | BZIP2=$${BZIP2--9} bzip2 -c >$(distdir).tar.bz2
|
||||
$(am__remove_distdir)
|
||||
|
||||
dist-lzip: distdir
|
||||
tardir=$(distdir) && $(am__tar) | lzip -c $${LZIP_OPT--9} >$(distdir).tar.lz
|
||||
tardir=$(distdir) && $(am__tar) | bzip2 -9 -c >$(distdir).tar.bz2
|
||||
$(am__remove_distdir)
|
||||
|
||||
dist-lzma: distdir
|
||||
|
|
@ -719,7 +709,7 @@ dist-lzma: distdir
|
|||
$(am__remove_distdir)
|
||||
|
||||
dist-xz: distdir
|
||||
tardir=$(distdir) && $(am__tar) | XZ_OPT=$${XZ_OPT--e} xz -c >$(distdir).tar.xz
|
||||
tardir=$(distdir) && $(am__tar) | xz -c >$(distdir).tar.xz
|
||||
$(am__remove_distdir)
|
||||
|
||||
dist-tarZ: distdir
|
||||
|
|
@ -750,8 +740,6 @@ distcheck: dist
|
|||
bzip2 -dc $(distdir).tar.bz2 | $(am__untar) ;;\
|
||||
*.tar.lzma*) \
|
||||
lzma -dc $(distdir).tar.lzma | $(am__untar) ;;\
|
||||
*.tar.lz*) \
|
||||
lzip -dc $(distdir).tar.lz | $(am__untar) ;;\
|
||||
*.tar.xz*) \
|
||||
xz -dc $(distdir).tar.xz | $(am__untar) ;;\
|
||||
*.tar.Z*) \
|
||||
|
|
@ -771,7 +759,6 @@ distcheck: dist
|
|||
&& am__cwd=`pwd` \
|
||||
&& $(am__cd) $(distdir)/_build \
|
||||
&& ../configure --srcdir=.. --prefix="$$dc_install_base" \
|
||||
$(AM_DISTCHECK_CONFIGURE_FLAGS) \
|
||||
$(DISTCHECK_CONFIGURE_FLAGS) \
|
||||
&& $(MAKE) $(AM_MAKEFLAGS) \
|
||||
&& $(MAKE) $(AM_MAKEFLAGS) dvi \
|
||||
|
|
@ -800,16 +787,8 @@ distcheck: dist
|
|||
list='$(DIST_ARCHIVES)'; for i in $$list; do echo $$i; done) | \
|
||||
sed -e 1h -e 1s/./=/g -e 1p -e 1x -e '$$p' -e '$$x'
|
||||
distuninstallcheck:
|
||||
@test -n '$(distuninstallcheck_dir)' || { \
|
||||
echo 'ERROR: trying to run $@ with an empty' \
|
||||
'$$(distuninstallcheck_dir)' >&2; \
|
||||
exit 1; \
|
||||
}; \
|
||||
$(am__cd) '$(distuninstallcheck_dir)' || { \
|
||||
echo 'ERROR: cannot chdir into $(distuninstallcheck_dir)' >&2; \
|
||||
exit 1; \
|
||||
}; \
|
||||
test `$(am__distuninstallcheck_listfiles) | wc -l` -eq 0 \
|
||||
@$(am__cd) '$(distuninstallcheck_dir)' \
|
||||
&& test `$(distuninstallcheck_listfiles) | wc -l` -le 1 \
|
||||
|| { echo "ERROR: files left after uninstall:" ; \
|
||||
if test -n "$(DESTDIR)"; then \
|
||||
echo " (check DESTDIR support)"; \
|
||||
|
|
@ -844,15 +823,10 @@ install-am: all-am
|
|||
|
||||
installcheck: installcheck-recursive
|
||||
install-strip:
|
||||
if test -z '$(STRIP)'; then \
|
||||
$(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \
|
||||
install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \
|
||||
install; \
|
||||
else \
|
||||
$(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \
|
||||
install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \
|
||||
"INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'" install; \
|
||||
fi
|
||||
$(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \
|
||||
install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \
|
||||
`test -z '$(STRIP)' || \
|
||||
echo "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'"` install
|
||||
mostlyclean-generic:
|
||||
|
||||
clean-generic:
|
||||
|
|
@ -946,8 +920,8 @@ uninstall-am: uninstall-binSCRIPTS uninstall-hyphDATA \
|
|||
all all-am am--refresh check check-am clean clean-generic \
|
||||
clean-libLTLIBRARIES clean-libtool clean-local \
|
||||
clean-noinstPROGRAMS ctags ctags-recursive dist dist-all \
|
||||
dist-bzip2 dist-gzip dist-lzip dist-lzma dist-shar dist-tarZ \
|
||||
dist-xz dist-zip distcheck distclean distclean-compile \
|
||||
dist-bzip2 dist-gzip dist-lzma dist-shar dist-tarZ dist-xz \
|
||||
dist-zip distcheck distclean distclean-compile \
|
||||
distclean-generic distclean-libtool distclean-tags \
|
||||
distcleancheck distdir distuninstallcheck dvi dvi-am html \
|
||||
html-am info info-am install install-am install-binSCRIPTS \
|
||||
|
|
@ -972,8 +946,7 @@ hyphen.us3:
|
|||
cat $(srcdir)/ligpatch.txt >>hyphen.us3
|
||||
|
||||
hyph_en_US.dic: hyphen.us3
|
||||
perl $(srcdir)/substrings.pl hyphen.us3 hyphen.us4 UTF-8 2 3 >/dev/null
|
||||
cat hyphen.us4 | $(SED) -f $(srcdir)/ooopatch.sed >hyph_en_US.dic
|
||||
perl $(srcdir)/substrings.pl hyphen.us3 hyph_en_US.dic UTF-8 2 3 >/dev/null
|
||||
|
||||
clean-local:
|
||||
rm -rf hyphen.us* hyph_en_US.dic
|
||||
|
|
|
|||
26
NEWS
26
NEWS
|
|
@ -1,4 +1,28 @@
|
|||
2010-12-01 Hyphen 2,7,1 bug fix release
|
||||
2011-10-10 Hyphen 2.8.3:
|
||||
- fix NOHYPHEN
|
||||
- fix unbalanced hyphenation of LibreOffice/OOo
|
||||
- set default COMPOUNDHYPHENMIN=3 at hyphens and apostrophes
|
||||
- fix VERBOSE in hyphen.c
|
||||
- new ./example option: -n to print hyphenation vector
|
||||
|
||||
2011-10-07 Hyphen 2.8.2:
|
||||
- fix for explicite COMPOUNDHYPHENMIN values
|
||||
|
||||
2011-10-06 Hyphen 2.8.1:
|
||||
- force minimal lefthyphenmin and righthyphenmin values of the dictionary
|
||||
(eg. righthyphenmin=3 of English dictionaries in LibreOffice/OOo,
|
||||
also the original TeX hyphenation patterns are correct only with this
|
||||
righthyphenmin value).
|
||||
|
||||
2011-10-04 Hyphen 2.8:
|
||||
- Ignore leading and ending numbers (eg. manual/field based indexes
|
||||
in LibreOffice/OOo)
|
||||
|
||||
- Fix LibreOffice/OpenOffice.org hyphenation errors at apostrophes and
|
||||
hyphens, n-dashes with default NOHYPHEN separators.
|
||||
Eg. *o'c=lock -> o'clock.
|
||||
|
||||
2010-12-01 Hyphen 2.7.1 bug fix release
|
||||
|
||||
2010-11-27 Hyphen 2.7 release:
|
||||
- The new hyphenation problem of OpenOffice.org 3.2, related to its
|
||||
|
|
|
|||
4
README
4
README
|
|
@ -2,7 +2,7 @@ Hyphen - hyphenation library to use converted TeX hyphenation patterns
|
|||
|
||||
(C) 1998 Raph Levien
|
||||
(C) 2001 ALTLinux, Moscow
|
||||
(C) 2006, 2007, 2008, 2010 László Németh
|
||||
(C) 2006, 2007, 2008, 2010, 2011 László Németh
|
||||
|
||||
This was part of libHnj library by Raph Levien.
|
||||
|
||||
|
|
@ -124,4 +124,4 @@ is released in binary form as jar files and in source form as zip files.
|
|||
See http://sourceforge.net/project/showfiles.php?group_id=119136
|
||||
|
||||
László Németh
|
||||
<nemeth (at) openoffice (dot) org>
|
||||
<nemeth (at) numbertext (dot) org>
|
||||
|
|
|
|||
|
|
@ -18,6 +18,16 @@ Description:
|
|||
and NOHYPHEN with the comma separated character (or character sequence)
|
||||
list forbid the (extra) hyphens at the hyphen and apostrophe characters.
|
||||
|
||||
Implicite NOHYPHEN declaration
|
||||
|
||||
Without explicite NEXTLEVEL declaration, Hyphen 2.8 uses the
|
||||
previous settings, plus in UTF-8 encoding, endash (U+2013) and
|
||||
typographical apostrophe (U+2019) are NOHYPHEN characters, too.
|
||||
|
||||
It's possible to enlarge the hyphenation distance from these
|
||||
NOHYPHEN characters by using COMPOUNDLEFTHYPHENMIN and
|
||||
COMPOUNDRIGHTHYPHENMIN attributes.
|
||||
|
||||
Compound word hyphenation
|
||||
|
||||
Hyphen library supports better compound word hyphenation and special
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load Diff
|
|
@ -1,5 +1,5 @@
|
|||
AC_INIT([hyphen],[2.7.1],[nemeth@openoffice.org])
|
||||
AM_INIT_AUTOMAKE(hyphen,2.7.1)
|
||||
AC_INIT([hyphen],[2.8.3],[nemeth@numbertext.org])
|
||||
AM_INIT_AUTOMAKE(hyphen,2.8.3)
|
||||
AC_PROG_CC
|
||||
AC_PROG_INSTALL
|
||||
AC_PROG_LIBTOOL
|
||||
|
|
|
|||
|
|
@ -1,9 +1,9 @@
|
|||
# Makefile.in generated by automake 1.11.3 from Makefile.am.
|
||||
# Makefile.in generated by automake 1.11.1 from Makefile.am.
|
||||
# @configure_input@
|
||||
|
||||
# Copyright (C) 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002,
|
||||
# 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software
|
||||
# Foundation, Inc.
|
||||
# 2003, 2004, 2005, 2006, 2007, 2008, 2009 Free Software Foundation,
|
||||
# Inc.
|
||||
# This Makefile.in is free software; the Free Software Foundation
|
||||
# gives unlimited permission to copy and/or distribute it,
|
||||
# with or without modifications, as long as this notice is preserved.
|
||||
|
|
@ -60,7 +60,6 @@ CPPFLAGS = @CPPFLAGS@
|
|||
CYGPATH_W = @CYGPATH_W@
|
||||
DEFS = @DEFS@
|
||||
DEPDIR = @DEPDIR@
|
||||
DLLTOOL = @DLLTOOL@
|
||||
DSYMUTIL = @DSYMUTIL@
|
||||
DUMPBIN = @DUMPBIN@
|
||||
ECHO_C = @ECHO_C@
|
||||
|
|
@ -84,7 +83,6 @@ LIPO = @LIPO@
|
|||
LN_S = @LN_S@
|
||||
LTLIBOBJS = @LTLIBOBJS@
|
||||
MAKEINFO = @MAKEINFO@
|
||||
MANIFEST_TOOL = @MANIFEST_TOOL@
|
||||
MKDIR_P = @MKDIR_P@
|
||||
NM = @NM@
|
||||
NMEDIT = @NMEDIT@
|
||||
|
|
@ -110,7 +108,6 @@ abs_builddir = @abs_builddir@
|
|||
abs_srcdir = @abs_srcdir@
|
||||
abs_top_builddir = @abs_top_builddir@
|
||||
abs_top_srcdir = @abs_top_srcdir@
|
||||
ac_ct_AR = @ac_ct_AR@
|
||||
ac_ct_CC = @ac_ct_CC@
|
||||
ac_ct_DUMPBIN = @ac_ct_DUMPBIN@
|
||||
am__include = @am__include@
|
||||
|
|
@ -143,6 +140,7 @@ libdir = @libdir@
|
|||
libexecdir = @libexecdir@
|
||||
localedir = @localedir@
|
||||
localstatedir = @localstatedir@
|
||||
lt_ECHO = @lt_ECHO@
|
||||
mandir = @mandir@
|
||||
mkdir_p = @mkdir_p@
|
||||
oldincludedir = @oldincludedir@
|
||||
|
|
@ -249,15 +247,10 @@ install-am: all-am
|
|||
|
||||
installcheck: installcheck-am
|
||||
install-strip:
|
||||
if test -z '$(STRIP)'; then \
|
||||
$(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \
|
||||
install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \
|
||||
install; \
|
||||
else \
|
||||
$(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \
|
||||
install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \
|
||||
"INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'" install; \
|
||||
fi
|
||||
$(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \
|
||||
install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \
|
||||
`test -z '$(STRIP)' || \
|
||||
echo "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'"` install
|
||||
mostlyclean-generic:
|
||||
|
||||
clean-generic:
|
||||
|
|
|
|||
|
|
@ -12,6 +12,7 @@ void help() {
|
|||
fprintf(stderr,"example [-d | -dd] hyphen_dictionary_file file_of_words_to_check\n");
|
||||
fprintf(stderr,"-o = use old algorithm (without non-standard hyphenation)\n");
|
||||
fprintf(stderr,"-d = hyphenation with listing of the possible hyphenations\n");
|
||||
fprintf(stderr,"-n = print hyphenation vector\n");
|
||||
}
|
||||
|
||||
/* get a pointer to the nth 8-bit or UTF-8 character of the word */
|
||||
|
|
@ -69,6 +70,7 @@ main(int argc, char** argv)
|
|||
char hword[BUFSIZE * 2];
|
||||
int arg = 1;
|
||||
int optd = 1;
|
||||
int optn = 0;
|
||||
int optdd = 0;
|
||||
char ** rep;
|
||||
int * pos;
|
||||
|
|
@ -82,6 +84,10 @@ main(int argc, char** argv)
|
|||
optd = 0;
|
||||
arg++;
|
||||
}
|
||||
if (strcmp(argv[arg], "-n") == 0) {
|
||||
optn = 1;
|
||||
arg++;
|
||||
}
|
||||
if (argv[arg] && strcmp(argv[arg], "-d") == 0) {
|
||||
optd = 1;
|
||||
optdd = 1;
|
||||
|
|
@ -152,6 +158,8 @@ main(int argc, char** argv)
|
|||
exit(1);
|
||||
}
|
||||
|
||||
if (optn) fprintf(stderr, "%s\n", hyphens);
|
||||
|
||||
if (!optd) {
|
||||
/* now backfill hyphens[] for any removed periods */
|
||||
for (c = n; c < k; c++) hyphens[c] = '0';
|
||||
|
|
@ -176,7 +184,6 @@ main(int argc, char** argv)
|
|||
fflush(stdout);
|
||||
free(hyphword);
|
||||
} else {
|
||||
/* fprintf(stderr, "vasz: %s", hyphens); */
|
||||
fprintf(stdout,"%s\n", hword);
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -1,13 +1,6 @@
|
|||
UTF-8
|
||||
LEFTHYPHENMIN 2
|
||||
RIGHTHYPHENMIN 3
|
||||
COMPOUNDLEFTHYPHENMIN 2
|
||||
COMPOUNDRIGHTHYPHENMIN 3
|
||||
NOHYPHEN -,',’
|
||||
1-1
|
||||
1'1
|
||||
1’1
|
||||
NEXTLEVEL
|
||||
.a2ch4
|
||||
.ad4der
|
||||
.a2d
|
||||
|
|
|
|||
259
hyphen.c
259
hyphen.c
|
|
@ -226,118 +226,61 @@ hnj_add_trans (HyphenDict *dict, int state1, int state2, char ch)
|
|||
}
|
||||
|
||||
#ifdef VERBOSE
|
||||
HashTab *global;
|
||||
HashTab *global[1];
|
||||
|
||||
static char *
|
||||
get_state_str (int state)
|
||||
get_state_str (int state, int level)
|
||||
{
|
||||
int i;
|
||||
HashEntry *e;
|
||||
|
||||
for (i = 0; i < HASH_SIZE; i++)
|
||||
for (e = global->entries[i]; e; e = e->next)
|
||||
for (e = global[level]->entries[i]; e; e = e->next)
|
||||
if (e->val == state)
|
||||
return e->key;
|
||||
return NULL;
|
||||
}
|
||||
#endif
|
||||
|
||||
HyphenDict *
|
||||
hnj_hyphen_load (const char *fn)
|
||||
{
|
||||
HyphenDict *dict[2];
|
||||
HashTab *hashtab;
|
||||
FILE *f;
|
||||
char buf[MAX_CHARS];
|
||||
void hnj_hyphen_load_line(char * buf, HyphenDict * dict, HashTab * hashtab) {
|
||||
int i, j;
|
||||
char word[MAX_CHARS];
|
||||
char pattern[MAX_CHARS];
|
||||
char * repl;
|
||||
signed char replindex;
|
||||
signed char replcut;
|
||||
int state_num = 0, last_state;
|
||||
int i, j, k;
|
||||
int state_num = 0;
|
||||
int last_state;
|
||||
char ch;
|
||||
int found;
|
||||
HashEntry *e;
|
||||
int nextlevel = 0;
|
||||
|
||||
f = fopen (fn, "r");
|
||||
if (f == NULL)
|
||||
return NULL;
|
||||
|
||||
// loading one or two dictionaries (separated by NEXTLEVEL keyword)
|
||||
for (k = 0; k == 0 || (k == 1 && nextlevel); k++) {
|
||||
hashtab = hnj_hash_new ();
|
||||
#ifdef VERBOSE
|
||||
global = hashtab;
|
||||
#endif
|
||||
hnj_hash_insert (hashtab, "", 0);
|
||||
dict[k] = hnj_malloc (sizeof(HyphenDict));
|
||||
dict[k]->num_states = 1;
|
||||
dict[k]->states = hnj_malloc (sizeof(HyphenState));
|
||||
dict[k]->states[0].match = NULL;
|
||||
dict[k]->states[0].repl = NULL;
|
||||
dict[k]->states[0].fallback_state = -1;
|
||||
dict[k]->states[0].num_trans = 0;
|
||||
dict[k]->states[0].trans = NULL;
|
||||
dict[k]->nextlevel = NULL;
|
||||
dict[k]->lhmin = 0;
|
||||
dict[k]->rhmin = 0;
|
||||
dict[k]->clhmin = 0;
|
||||
dict[k]->crhmin = 0;
|
||||
dict[k]->nohyphen = NULL;
|
||||
dict[k]->nohyphenl = 0;
|
||||
|
||||
/* read in character set info */
|
||||
if (k == 0) {
|
||||
for (i=0;i<MAX_NAME;i++) dict[k]->cset[i]= 0;
|
||||
if (fgets(dict[k]->cset, sizeof(dict[k]->cset),f) != NULL) {
|
||||
for (i=0;i<MAX_NAME;i++)
|
||||
if ((dict[k]->cset[i] == '\r') || (dict[k]->cset[i] == '\n'))
|
||||
dict[k]->cset[i] = 0;
|
||||
} else {
|
||||
dict[k]->cset[0] = 0;
|
||||
}
|
||||
dict[k]->utf8 = (strcmp(dict[k]->cset, "UTF-8") == 0);
|
||||
} else {
|
||||
strcpy(dict[k]->cset, dict[0]->cset);
|
||||
dict[k]->utf8 = dict[0]->utf8;
|
||||
}
|
||||
|
||||
while (fgets (buf, sizeof(buf), f) != NULL)
|
||||
{
|
||||
if (buf[0] != '%')
|
||||
{
|
||||
if (strncmp(buf, "NEXTLEVEL", 9) == 0) {
|
||||
nextlevel = 1;
|
||||
break;
|
||||
} else if (strncmp(buf, "LEFTHYPHENMIN", 13) == 0) {
|
||||
dict[k]->lhmin = atoi(buf + 13);
|
||||
continue;
|
||||
if (strncmp(buf, "LEFTHYPHENMIN", 13) == 0) {
|
||||
dict->lhmin = atoi(buf + 13);
|
||||
return;
|
||||
} else if (strncmp(buf, "RIGHTHYPHENMIN", 14) == 0) {
|
||||
dict[k]->rhmin = atoi(buf + 14);
|
||||
continue;
|
||||
dict->rhmin = atoi(buf + 14);
|
||||
return;
|
||||
} else if (strncmp(buf, "COMPOUNDLEFTHYPHENMIN", 21) == 0) {
|
||||
dict[k]->clhmin = atoi(buf + 21);
|
||||
continue;
|
||||
dict->clhmin = atoi(buf + 21);
|
||||
return;
|
||||
} else if (strncmp(buf, "COMPOUNDRIGHTHYPHENMIN", 22) == 0) {
|
||||
dict[k]->crhmin = atoi(buf + 22);
|
||||
continue;
|
||||
dict->crhmin = atoi(buf + 22);
|
||||
return;
|
||||
} else if (strncmp(buf, "NOHYPHEN", 8) == 0) {
|
||||
char * space = buf + 8;
|
||||
while (*space != '\0' && (*space == ' ' || *space == '\t')) space++;
|
||||
if (*buf != '\0') dict[k]->nohyphen = hnj_strdup(space);
|
||||
if (dict[k]->nohyphen) {
|
||||
char * nhe = dict[k]->nohyphen + strlen(dict[k]->nohyphen) - 1;
|
||||
if (*buf != '\0') dict->nohyphen = hnj_strdup(space);
|
||||
if (dict->nohyphen) {
|
||||
char * nhe = dict->nohyphen + strlen(dict->nohyphen) - 1;
|
||||
*nhe = 0;
|
||||
for (nhe = nhe - 1; nhe > dict[k]->nohyphen; nhe--) {
|
||||
for (nhe = nhe - 1; nhe > dict->nohyphen; nhe--) {
|
||||
if (*nhe == ',') {
|
||||
dict[k]->nohyphenl++;
|
||||
dict->nohyphenl++;
|
||||
*nhe = 0;
|
||||
}
|
||||
}
|
||||
}
|
||||
continue;
|
||||
return;
|
||||
}
|
||||
j = 0;
|
||||
pattern[j] = '0';
|
||||
|
|
@ -382,7 +325,7 @@ for (k = 0; k == 0 || (k == 1 && nextlevel); k++) {
|
|||
} else {
|
||||
if (*word == '.') i++;
|
||||
/* convert UTF-8 char. positions of discretionary hyph. replacements to 8-bit */
|
||||
if (dict[k]->utf8) {
|
||||
if (dict->utf8) {
|
||||
int pu = -1; /* unicode character position */
|
||||
int ps = -1; /* unicode start position (original replindex) */
|
||||
int pc = (*word == '.') ? 1: 0; /* 8-bit character position */
|
||||
|
|
@ -406,14 +349,14 @@ for (k = 0; k == 0 || (k == 1 && nextlevel); k++) {
|
|||
printf ("word %s pattern %s, j = %d repl: %s\n", word, pattern + i, j, repl);
|
||||
#endif
|
||||
found = hnj_hash_lookup (hashtab, word);
|
||||
state_num = hnj_get_state (dict[k], hashtab, word);
|
||||
dict[k]->states[state_num].match = hnj_strdup (pattern + i);
|
||||
dict[k]->states[state_num].repl = repl;
|
||||
dict[k]->states[state_num].replindex = replindex;
|
||||
state_num = hnj_get_state (dict, hashtab, word);
|
||||
dict->states[state_num].match = hnj_strdup (pattern + i);
|
||||
dict->states[state_num].repl = repl;
|
||||
dict->states[state_num].replindex = replindex;
|
||||
if (!replcut) {
|
||||
dict[k]->states[state_num].replcut = (signed char) strlen(word);
|
||||
dict->states[state_num].replcut = (signed char) strlen(word);
|
||||
} else {
|
||||
dict[k]->states[state_num].replcut = replcut;
|
||||
dict->states[state_num].replcut = replcut;
|
||||
}
|
||||
|
||||
/* now, put in the prefix transitions */
|
||||
|
|
@ -423,11 +366,85 @@ for (k = 0; k == 0 || (k == 1 && nextlevel); k++) {
|
|||
ch = word[j - 1];
|
||||
word[j - 1] = '\0';
|
||||
found = hnj_hash_lookup (hashtab, word);
|
||||
state_num = hnj_get_state (dict[k], hashtab, word);
|
||||
hnj_add_trans (dict[k], state_num, last_state, ch);
|
||||
state_num = hnj_get_state (dict, hashtab, word);
|
||||
hnj_add_trans (dict, state_num, last_state, ch);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
HyphenDict *
|
||||
hnj_hyphen_load (const char *fn)
|
||||
{
|
||||
HyphenDict *dict[2];
|
||||
HashTab *hashtab;
|
||||
FILE *f;
|
||||
char buf[MAX_CHARS];
|
||||
int nextlevel = 0;
|
||||
int i, j, k;
|
||||
HashEntry *e;
|
||||
int state_num = 0;
|
||||
|
||||
f = fopen (fn, "r");
|
||||
if (f == NULL)
|
||||
return NULL;
|
||||
|
||||
// loading one or two dictionaries (separated by NEXTLEVEL keyword)
|
||||
for (k = 0; k < 2; k++) {
|
||||
hashtab = hnj_hash_new ();
|
||||
#ifdef VERBOSE
|
||||
global[k] = hashtab;
|
||||
#endif
|
||||
hnj_hash_insert (hashtab, "", 0);
|
||||
dict[k] = hnj_malloc (sizeof(HyphenDict));
|
||||
dict[k]->num_states = 1;
|
||||
dict[k]->states = hnj_malloc (sizeof(HyphenState));
|
||||
dict[k]->states[0].match = NULL;
|
||||
dict[k]->states[0].repl = NULL;
|
||||
dict[k]->states[0].fallback_state = -1;
|
||||
dict[k]->states[0].num_trans = 0;
|
||||
dict[k]->states[0].trans = NULL;
|
||||
dict[k]->nextlevel = NULL;
|
||||
dict[k]->lhmin = 0;
|
||||
dict[k]->rhmin = 0;
|
||||
dict[k]->clhmin = 0;
|
||||
dict[k]->crhmin = 0;
|
||||
dict[k]->nohyphen = NULL;
|
||||
dict[k]->nohyphenl = 0;
|
||||
|
||||
/* read in character set info */
|
||||
if (k == 0) {
|
||||
for (i=0;i<MAX_NAME;i++) dict[k]->cset[i]= 0;
|
||||
if (fgets(dict[k]->cset, sizeof(dict[k]->cset),f) != NULL) {
|
||||
for (i=0;i<MAX_NAME;i++)
|
||||
if ((dict[k]->cset[i] == '\r') || (dict[k]->cset[i] == '\n'))
|
||||
dict[k]->cset[i] = 0;
|
||||
} else {
|
||||
dict[k]->cset[0] = 0;
|
||||
}
|
||||
dict[k]->utf8 = (strcmp(dict[k]->cset, "UTF-8") == 0);
|
||||
} else {
|
||||
strcpy(dict[k]->cset, dict[0]->cset);
|
||||
dict[k]->utf8 = dict[0]->utf8;
|
||||
}
|
||||
|
||||
if (k == 0 || nextlevel) {
|
||||
while (fgets (buf, sizeof(buf), f) != NULL) {
|
||||
if (strncmp(buf, "NEXTLEVEL", 9) == 0) {
|
||||
nextlevel = 1;
|
||||
break;
|
||||
} else if (buf[0] != '%') hnj_hyphen_load_line(buf, dict[k], hashtab);
|
||||
}
|
||||
} else if (k == 1) {
|
||||
/* default first level: hyphen and ASCII apostrophe */
|
||||
if (!dict[0]->utf8) hnj_hyphen_load_line("NOHYPHEN '\n", dict[k], hashtab);
|
||||
else hnj_hyphen_load_line("NOHYPHEN ',\xe2\x80\x93,\xe2\x80\x99\n", dict[k], hashtab);
|
||||
strcpy(buf, "1-1/=,1,1\n"); // buf rewritten by hnj_hyphen_load here
|
||||
hnj_hyphen_load_line(buf, dict[k], hashtab); /* remove hyphen */
|
||||
hnj_hyphen_load_line("1'1\n", dict[k], hashtab); /* ASCII apostrophe */
|
||||
if (dict[0]->utf8) {
|
||||
hnj_hyphen_load_line("1\xe2\x80\x93" "1\n", dict[k], hashtab); /* endash */
|
||||
hnj_hyphen_load_line("1\xe2\x80\x99" "1\n", dict[k], hashtab); /* apostrophe */
|
||||
}
|
||||
}
|
||||
|
||||
/* Could do unioning of matches here (instead of the preprocessor script).
|
||||
If we did, the pseudocode would look something like this:
|
||||
|
|
@ -479,7 +496,20 @@ for (k = 0; k == 0 || (k == 1 && nextlevel); k++) {
|
|||
state_num = 0;
|
||||
}
|
||||
fclose(f);
|
||||
if (k == 2) dict[0]->nextlevel = dict[1];
|
||||
if (nextlevel) dict[0]->nextlevel = dict[1];
|
||||
else {
|
||||
dict[1] -> nextlevel = dict[0];
|
||||
dict[1]->lhmin = dict[0]->lhmin;
|
||||
dict[1]->rhmin = dict[0]->rhmin;
|
||||
dict[1]->clhmin = (dict[0]->clhmin) ? dict[0]->clhmin : ((dict[0]->lhmin) ? dict[0]->lhmin : 3);
|
||||
dict[1]->crhmin = (dict[0]->crhmin) ? dict[0]->crhmin : ((dict[0]->rhmin) ? dict[0]->rhmin : 3);
|
||||
#ifdef VERBOSE
|
||||
HashTab *r = global[0];
|
||||
global[0] = global[1];
|
||||
global[1] = r;
|
||||
#endif
|
||||
return dict[1];
|
||||
}
|
||||
return dict[0];
|
||||
}
|
||||
|
||||
|
|
@ -530,8 +560,13 @@ int hnj_hyphen_hyphenate (HyphenDict *dict,
|
|||
j = 0;
|
||||
prep_word[j++] = '.';
|
||||
|
||||
for (i = 0; i < word_size; i++)
|
||||
for (i = 0; i < word_size; i++) {
|
||||
if (word[i] <= '9' && word[i] >= '0') {
|
||||
prep_word[j++] = '.';
|
||||
} else {
|
||||
prep_word[j++] = word[i];
|
||||
}
|
||||
}
|
||||
|
||||
prep_word[j++] = '.';
|
||||
prep_word[j] = '\0';
|
||||
|
|
@ -560,7 +595,7 @@ int hnj_hyphen_hyphenate (HyphenDict *dict,
|
|||
|
||||
#ifdef VERBOSE
|
||||
char *state_str;
|
||||
state_str = get_state_str (state);
|
||||
state_str = get_state_str (state, 0);
|
||||
|
||||
for (k = 0; k < i - strlen (state_str); k++)
|
||||
putchar (' ');
|
||||
|
|
@ -673,6 +708,9 @@ int hnj_hyphen_lhmin(int utf8, const char *word, int word_size, char * hyphens,
|
|||
i += hnj_ligature(word[2]);
|
||||
}
|
||||
|
||||
// ignore numbers
|
||||
for (j = 0; word[j] <= '9' && word[j] >= '0'; j++) i--;
|
||||
|
||||
for (j = 0; i < lhmin && word[j] != '\0'; i++) do {
|
||||
// check length of the non-standard part
|
||||
if (*rep && *pos && *cut && (*rep)[j]) {
|
||||
|
|
@ -699,9 +737,13 @@ int hnj_hyphen_lhmin(int utf8, const char *word, int word_size, char * hyphens,
|
|||
int hnj_hyphen_rhmin(int utf8, const char *word, int word_size, char * hyphens,
|
||||
char *** rep, int ** pos, int ** cut, int rhmin)
|
||||
{
|
||||
int i;
|
||||
int j = word_size - 2;
|
||||
for (i = 1; i < rhmin && j > 0; j--) {
|
||||
int i = 1;
|
||||
int j;
|
||||
|
||||
// ignore numbers
|
||||
for (j = word_size - 1; j > 0 && word[j] <= '9' && word[j] >= '0'; j--) i--;
|
||||
|
||||
for (j = word_size - 2; i < rhmin && j > 0; j--) {
|
||||
// check length of the non-standard part
|
||||
if (*rep && *pos && *cut && (*rep)[j]) {
|
||||
char * rh = strchr((*rep)[j], '=');
|
||||
|
|
@ -759,8 +801,15 @@ int hnj_hyphen_hyph_(HyphenDict *dict, const char *word, int word_size,
|
|||
j = 0;
|
||||
prep_word[j++] = '.';
|
||||
|
||||
for (i = 0; i < word_size; i++)
|
||||
for (i = 0; i < word_size; i++) {
|
||||
if (word[i] <= '9' && word[i] >= '0') {
|
||||
prep_word[j++] = '.';
|
||||
} else {
|
||||
prep_word[j++] = word[i];
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
prep_word[j++] = '.';
|
||||
prep_word[j] = '\0';
|
||||
|
|
@ -789,7 +838,7 @@ int hnj_hyphen_hyph_(HyphenDict *dict, const char *word, int word_size,
|
|||
|
||||
#ifdef VERBOSE
|
||||
char *state_str;
|
||||
state_str = get_state_str (state);
|
||||
state_str = get_state_str (state, 1);
|
||||
|
||||
for (k = 0; k < i - strlen (state_str); k++)
|
||||
putchar (' ');
|
||||
|
|
@ -1036,6 +1085,9 @@ int hnj_hyphen_norm(const char *word, int word_size, char * hyphens,
|
|||
}
|
||||
}
|
||||
hyphens[j + 1] = '\0';
|
||||
#ifdef VERBOSE
|
||||
printf ("nums: %s\n", hyphens);
|
||||
#endif
|
||||
return 0;
|
||||
}
|
||||
|
||||
|
|
@ -1077,8 +1129,8 @@ int hnj_hyphen_hyphenate2 (HyphenDict *dict,
|
|||
for (nhi = 0; nhi <= dict->nohyphenl; nhi++) {
|
||||
char * nhy = (char *) strstr(word, nh);
|
||||
while (nhy) {
|
||||
hyphens[nhy - word + strlen(nh) - 1] = 0;
|
||||
if (nhy - word - 1 >= 0) hyphens[nhy - word - 1] = 0;
|
||||
hyphens[nhy - word + strlen(nh) - 1] = '0';
|
||||
if (nhy - word - 1 >= 0) hyphens[nhy - word - 1] = '0';
|
||||
nhy = (char *) strstr(nhy + 1, nh);
|
||||
}
|
||||
nh = nh + strlen(nh) + 1;
|
||||
|
|
@ -1087,6 +1139,9 @@ int hnj_hyphen_hyphenate2 (HyphenDict *dict,
|
|||
|
||||
if (hyphword) hnj_hyphen_hyphword(word, word_size, hyphens, hyphword, rep, pos, cut);
|
||||
if (dict->utf8) return hnj_hyphen_norm(word, word_size, hyphens, rep, pos, cut);
|
||||
#ifdef VERBOSE
|
||||
printf ("nums: %s\n", hyphens);
|
||||
#endif
|
||||
return 0;
|
||||
}
|
||||
|
||||
|
|
@ -1096,8 +1151,10 @@ int hnj_hyphen_hyphenate3 (HyphenDict *dict,
|
|||
char *hyphword, char *** rep, int ** pos, int ** cut,
|
||||
int lhmin, int rhmin, int clhmin, int crhmin)
|
||||
{
|
||||
lhmin = (lhmin > 0 ? lhmin : dict->lhmin);
|
||||
rhmin = (rhmin > 0 ? rhmin : dict->rhmin);
|
||||
lhmin = (lhmin > dict->lhmin) ? lhmin : dict->lhmin;
|
||||
rhmin = (rhmin > dict->rhmin) ? rhmin : dict->rhmin;
|
||||
clhmin = (clhmin > dict->clhmin) ? clhmin : dict->clhmin;
|
||||
crhmin = (crhmin > dict->crhmin) ? crhmin : dict->crhmin;
|
||||
hnj_hyphen_hyph_(dict, word, word_size, hyphens, rep, pos, cut,
|
||||
clhmin, crhmin, 1, 1);
|
||||
hnj_hyphen_lhmin(dict->utf8, word, word_size, hyphens,
|
||||
|
|
|
|||
|
|
@ -21,7 +21,8 @@ settings4.test \
|
|||
lhmin.test \
|
||||
rhmin.test \
|
||||
lig.test \
|
||||
hyphen.test
|
||||
hyphen.test \
|
||||
num.test
|
||||
|
||||
distclean-local:
|
||||
-rm -rf testSubDir
|
||||
|
|
@ -120,4 +121,8 @@ lig.word \
|
|||
hyphen.hyph \
|
||||
hyphen.pat \
|
||||
hyphen.test \
|
||||
hyphen.word
|
||||
hyphen.word \
|
||||
num.hyph \
|
||||
num.pat \
|
||||
num.test \
|
||||
num.word
|
||||
|
|
|
|||
|
|
@ -1,9 +1,9 @@
|
|||
# Makefile.in generated by automake 1.11.3 from Makefile.am.
|
||||
# Makefile.in generated by automake 1.11.1 from Makefile.am.
|
||||
# @configure_input@
|
||||
|
||||
# Copyright (C) 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002,
|
||||
# 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software
|
||||
# Foundation, Inc.
|
||||
# 2003, 2004, 2005, 2006, 2007, 2008, 2009 Free Software Foundation,
|
||||
# Inc.
|
||||
# This Makefile.in is free software; the Free Software Foundation
|
||||
# gives unlimited permission to copy and/or distribute it,
|
||||
# with or without modifications, as long as this notice is preserved.
|
||||
|
|
@ -62,7 +62,6 @@ CPPFLAGS = @CPPFLAGS@
|
|||
CYGPATH_W = @CYGPATH_W@
|
||||
DEFS = @DEFS@
|
||||
DEPDIR = @DEPDIR@
|
||||
DLLTOOL = @DLLTOOL@
|
||||
DSYMUTIL = @DSYMUTIL@
|
||||
DUMPBIN = @DUMPBIN@
|
||||
ECHO_C = @ECHO_C@
|
||||
|
|
@ -86,7 +85,6 @@ LIPO = @LIPO@
|
|||
LN_S = @LN_S@
|
||||
LTLIBOBJS = @LTLIBOBJS@
|
||||
MAKEINFO = @MAKEINFO@
|
||||
MANIFEST_TOOL = @MANIFEST_TOOL@
|
||||
MKDIR_P = @MKDIR_P@
|
||||
NM = @NM@
|
||||
NMEDIT = @NMEDIT@
|
||||
|
|
@ -112,7 +110,6 @@ abs_builddir = @abs_builddir@
|
|||
abs_srcdir = @abs_srcdir@
|
||||
abs_top_builddir = @abs_top_builddir@
|
||||
abs_top_srcdir = @abs_top_srcdir@
|
||||
ac_ct_AR = @ac_ct_AR@
|
||||
ac_ct_CC = @ac_ct_CC@
|
||||
ac_ct_DUMPBIN = @ac_ct_DUMPBIN@
|
||||
am__include = @am__include@
|
||||
|
|
@ -145,6 +142,7 @@ libdir = @libdir@
|
|||
libexecdir = @libexecdir@
|
||||
localedir = @localedir@
|
||||
localstatedir = @localstatedir@
|
||||
lt_ECHO = @lt_ECHO@
|
||||
mandir = @mandir@
|
||||
mkdir_p = @mkdir_p@
|
||||
oldincludedir = @oldincludedir@
|
||||
|
|
@ -183,7 +181,8 @@ settings4.test \
|
|||
lhmin.test \
|
||||
rhmin.test \
|
||||
lig.test \
|
||||
hyphen.test
|
||||
hyphen.test \
|
||||
num.test
|
||||
|
||||
EXTRA_DIST = \
|
||||
test.sh \
|
||||
|
|
@ -279,7 +278,11 @@ lig.word \
|
|||
hyphen.hyph \
|
||||
hyphen.pat \
|
||||
hyphen.test \
|
||||
hyphen.word
|
||||
hyphen.word \
|
||||
num.hyph \
|
||||
num.pat \
|
||||
num.test \
|
||||
num.word
|
||||
|
||||
all: all-am
|
||||
|
||||
|
|
@ -408,15 +411,14 @@ check-TESTS: $(TESTS)
|
|||
fi; \
|
||||
dashes=`echo "$$dashes" | sed s/./=/g`; \
|
||||
if test "$$failed" -eq 0; then \
|
||||
col="$$grn"; \
|
||||
echo "$$grn$$dashes"; \
|
||||
else \
|
||||
col="$$red"; \
|
||||
echo "$$red$$dashes"; \
|
||||
fi; \
|
||||
echo "$${col}$$dashes$${std}"; \
|
||||
echo "$${col}$$banner$${std}"; \
|
||||
test -z "$$skipped" || echo "$${col}$$skipped$${std}"; \
|
||||
test -z "$$report" || echo "$${col}$$report$${std}"; \
|
||||
echo "$${col}$$dashes$${std}"; \
|
||||
echo "$$banner"; \
|
||||
test -z "$$skipped" || echo "$$skipped"; \
|
||||
test -z "$$report" || echo "$$report"; \
|
||||
echo "$$dashes$$std"; \
|
||||
test "$$failed" -eq 0; \
|
||||
else :; fi
|
||||
|
||||
|
|
@ -465,15 +467,10 @@ install-am: all-am
|
|||
|
||||
installcheck: installcheck-am
|
||||
install-strip:
|
||||
if test -z '$(STRIP)'; then \
|
||||
$(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \
|
||||
install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \
|
||||
install; \
|
||||
else \
|
||||
$(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \
|
||||
install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \
|
||||
"INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'" install; \
|
||||
fi
|
||||
$(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \
|
||||
install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \
|
||||
`test -z '$(STRIP)' || \
|
||||
echo "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'"` install
|
||||
mostlyclean-generic:
|
||||
|
||||
clean-generic:
|
||||
|
|
|
|||
|
|
@ -2839,7 +2839,7 @@ oc=tag=o=nal
|
|||
octets
|
||||
oddly
|
||||
odi=ous
|
||||
o'd=wyer
|
||||
o'dwyer
|
||||
of=fended
|
||||
of=fer
|
||||
of=fi=cer
|
||||
|
|
|
|||
|
|
@ -0,0 +1,9 @@
|
|||
foobar
|
||||
foobar=foobar
|
||||
barfoo=barfoo
|
||||
123foobar=foobar
|
||||
foobar=foobar123
|
||||
123foobar=foobar123
|
||||
123barfoo=barfoo
|
||||
barfoo=barfoo123
|
||||
123barfoo=barfoo123
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
UTF-8
|
||||
LEFTHYPHENMIN 4
|
||||
RIGHTHYPHENMIN 4
|
||||
foo1
|
||||
NEXTLEVEL
|
||||
bar1
|
||||
|
|
@ -0,0 +1,4 @@
|
|||
#!/bin/sh
|
||||
DIR="`dirname $0`"
|
||||
NAME="`basename $0 .test`"
|
||||
$DIR/test.sh $NAME.pat $NAME.word $NAME.hyph
|
||||
|
|
@ -0,0 +1,9 @@
|
|||
foobar
|
||||
foobarfoobar
|
||||
barfoobarfoo
|
||||
123foobarfoobar
|
||||
foobarfoobar123
|
||||
123foobarfoobar123
|
||||
123barfoobarfoo
|
||||
barfoobarfoo123
|
||||
123barfoobarfoo123
|
||||
|
|
@ -1,4 +1,5 @@
|
|||
UTF-8
|
||||
NEXTLEVEL
|
||||
l·1l/l=l,1,3
|
||||
e1ë/e=e,1,2
|
||||
a1atje./a=t,1,3
|
||||
|
|
|
|||
Loading…
Reference in New Issue