[Libreoffice-commits] .: 2 commits - i18npool/CustomTarget_breakiterator.mk i18npool/CustomTarget_collator.mk i18npool/CustomTarget_indexentry.mk i18npool/source
Caolán McNamara
caolan at kemper.freedesktop.org
Fri Jul 27 06:37:32 PDT 2012
i18npool/CustomTarget_breakiterator.mk | 24 ++-
i18npool/CustomTarget_collator.mk | 23 ++-
i18npool/CustomTarget_indexentry.mk | 17 +-
i18npool/source/breakiterator/data/dict_word_ca.txt | 148 --------------------
4 files changed, 54 insertions(+), 158 deletions(-)
New commits:
commit 585e64ff94646c9204126f6db86b80da86e8a9d6
Author: Caolán McNamara <caolanm at redhat.com>
Date: Fri Jul 27 13:29:44 2012 +0100
drop hopefully unnecessary catalan word breaking rules
various regression tests for the issues that prompted its inclusion all now
pass in its absence
Change-Id: Ia375322335b4272aa6c3d626b2d98bc64465bf1c
diff --git a/i18npool/CustomTarget_breakiterator.mk b/i18npool/CustomTarget_breakiterator.mk
index 621e8f1..f7df926 100644
--- a/i18npool/CustomTarget_breakiterator.mk
+++ b/i18npool/CustomTarget_breakiterator.mk
@@ -70,7 +70,6 @@ i18npool_BRKTXTS := \
char.brk \
count_word_fi.brk \
count_word.brk \
- dict_word_ca.brk \
dict_word_fi.brk \
dict_word_he.brk \
dict_word_hu.brk \
diff --git a/i18npool/source/breakiterator/data/dict_word_ca.txt b/i18npool/source/breakiterator/data/dict_word_ca.txt
deleted file mode 100644
index b1666f4..0000000
--- a/i18npool/source/breakiterator/data/dict_word_ca.txt
+++ /dev/null
@@ -1,148 +0,0 @@
-#
-# Copyright (C) 2002-2003, International Business Machines Corporation and others.
-# All Rights Reserved.
-#
-# file: dict_word.txt
-#
-# ICU Word Break Rules
-# See Unicode Standard Annex #29.
-# These rules are based on Version 4.0.0, dated 2003-04-17
-#
-
-
-
-####################################################################################
-#
-# Character class definitions from TR 29
-#
-####################################################################################
-$Katakana = [[:Script = KATAKANA:] [:name = KATAKANA-HIRAGANA PROLONGED SOUND MARK:]
- [:name = HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK:]
- [:name = HALFWIDTH KATAKANA VOICED SOUND MARK:]
- [:name = HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK:]];
-
-$Ideographic = [:Ideographic:];
-$Hangul = [:Script = HANGUL:];
-
-$ALetter = [[:Alphabetic:] [:name= COMMERCIAL AT:] [:name= HEBREW PUNCTUATION GERESH:]
- - $Ideographic
- - $Katakana
- - $Hangul
- - [:Script = Thai:]
- - [:Script = Lao:]
- - [:Script = Hiragana:]];
-
-$MidLetter = [[:name = APOSTROPHE:] [:name = GRAVE ACCENT:] \u0084 [:name = SOFT HYPHEN:] [:name = MIDDLE DOT:] [:name = GREEK TONOS:] [:name= FULL STOP:]
- [:name = HEBREW PUNCTUATION GERSHAYIM:] [:name = DOUBLE VERTICAL LINE:] [:name = LEFT SINGLE QUOTATION MARK:]
- [:name = RIGHT SINGLE QUOTATION MARK:] [:name = HYPHENATION POINT:] [:name = PRIME:]
- [:name = HYPHEN-MINUS:] ];
-
-$SufixLetter = [:name= FULL STOP:];
-
-
-$MidNum = [[:LineBreak = Infix_Numeric:] [:name= COMMERCIAL AT:] \u0084 [:name = GREEK TONOS:] [:name = ARABIC DECIMAL SEPARATOR:]
- [:name = LEFT SINGLE QUOTATION MARK:] [:name = RIGHT SINGLE QUOTATION MARK:] [:name = SINGLE HIGH-REVERSED-9 QUOTATION MARK:]
- [:name = PRIME:]];
-$Numeric = [:LineBreak = Numeric:];
-
-
-$TheZWSP = \u200b;
-
-#
-# Character Class Definitions.
-# The names are those from TR29.
-#
-$CR = \u000d;
-$LF = \u000a;
-$Control = [[[:Zl:] [:Zp:] [:Cc:] [:Cf:]] - $TheZWSP];
-$Extend = [[:Grapheme_Extend = TRUE:]];
-
-
-
-
-####################################################################################
-#
-# Word Break Rules. Definitions and Rules specific to word break begin Here.
-#
-####################################################################################
-
-$Format = [[:Cf:] - $TheZWSP];
-
-
-
-# Rule 3: Treat a grapheme cluster as if it were a single character.
-# Hangul Syllables are easier to deal with here than they are in Grapheme Clusters
-# because we don't need to find the boundaries between adjacent syllables -
-# they won't be word boundaries.
-#
-
-
-#
-# "Extended" definitions. Grapheme Cluster + Format Chars, treated like the base char.
-#
-$ALetterEx = $ALetter $Extend*;
-$NumericEx = $Numeric $Extend*;
-$MidNumEx = $MidNum $Extend*;
-$MidLetterEx = $MidLetter $Extend*;
-$SufixLetterEx= $SufixLetter $Extend*;
-$KatakanaEx = $Katakana $Extend*;
-$IdeographicEx= $Ideographic $Extend*;
-$HangulEx = $Hangul $Extend*;
-$FormatEx = $Format $Extend*;
-
-
-#
-# Numbers. Rules 8, 11, 12 form the TR.
-#
-$NumberSequence = $NumericEx ($FormatEx* $MidNumEx? $FormatEx* $NumericEx)*;
-$NumberSequence {100};
-
-#
-# Words. Alpha-numerics. Rule 5, 6, 7, 9, 10
-# - must include at least one letter.
-# - may include both letters and numbers.
-# - may include MideLetter, MidNumber punctuation.
-#
-$LetterSequence = $ALetterEx ($FormatEx* $MidLetterEx? $FormatEx* $ALetterEx)*; # rules #6, #7
-($NumberSequence $FormatEx*)? $LetterSequence ($FormatEx* ($NumberSequence | $LetterSequence))* $SufixLetterEx? {200};
-
-[[:P:][:S:]]*;
-
-#
-# Do not break between Katakana. Rule #13.
-#
-$KatakanaEx ($FormatEx* $KatakanaEx)* {300};
-[:Hiragana:] $Extend* {300};
-
-#
-# Ideographic Characters. Stand by themselves as words.
-# Separated from the "Everything Else" rule, below, only so that they
-# can be tagged with a return value. TODO: is this what we want?
-#
-$IdeographicEx ($FormatEx* $IdeographicEx)* {400};
-$HangulEx ($FormatEx* $HangulEx)* {400};
-
-#
-# Everything Else, with no tag.
-# Non-Control chars combine with $Extend (combining) chars.
-# Controls are do not.
-#
-[^$Control [:Ideographic:]] $Extend*;
-$CR $LF;
-
-#
-# Reverse Rules. Back up over any of the chars that can group together.
-# (Reverse rules do not need to be exact; they can back up too far,
-# but must back up at least enough, and must stop on a boundary.)
-#
-
-# NonStarters are the set of all characters that can appear at the 2nd - nth position of
-# a word. (They may also be the first.) The reverse rule skips over these, until it
-# reaches something that can only be the start (and probably only) char in a "word".
-# A space or punctuation meets the test.
-#
-$NonStarters = [$Numeric $ALetter $Katakana $Ideographic $Hangul [:P:] [:S:] $MidLetter $MidNum $SufixLetter $Extend $Format];
-
-#!.*;
-! ($NonStarters* | \n \r) .;
-
commit 82c25249e624cb54ca6d3293d1c3d0d8ebc208e0
Author: Caolán McNamara <caolanm at redhat.com>
Date: Fri Jul 27 14:11:08 2012 +0100
list dependencies explicitly
and make the list (by its makefile proxy) a dependency of the output
so that removing an entry will trigger a rebuild of the target and
incremental builds are possible
Change-Id: I18c8d5ea2140e61b2ef78e256871402be94b79e2
diff --git a/i18npool/CustomTarget_breakiterator.mk b/i18npool/CustomTarget_breakiterator.mk
index 3e0df9e..621e8f1 100644
--- a/i18npool/CustomTarget_breakiterator.mk
+++ b/i18npool/CustomTarget_breakiterator.mk
@@ -65,20 +65,35 @@ i18npool_GENCMNTARGET :=
i18npool_GENCMN := $(SYSTEM_GENCMN)
endif
-i18npool_BRKFILES := $(subst .txt,.brk,$(notdir \
- $(wildcard $(SRCDIR)/i18npool/source/breakiterator/data/*.txt)))
+i18npool_BRKTXTS := \
+ char_in.brk \
+ char.brk \
+ count_word_fi.brk \
+ count_word.brk \
+ dict_word_ca.brk \
+ dict_word_fi.brk \
+ dict_word_he.brk \
+ dict_word_hu.brk \
+ dict_word_nodash.brk \
+ dict_word_prepostdash.brk \
+ dict_word.brk \
+ edit_word_he.brk \
+ edit_word_hu.brk \
+ edit_word.brk \
+ line.brk \
+ sent.brk
# 'gencmn', 'genbrk' and 'genccode' are tools generated and delivered by icu project to process icu breakiterator rules.
# The output of gencmn generates warnings under Windows. We want to minimize the patches to external tools,
# so the output (OpenOffice_dat.c) is changed here to include a pragma to disable the warnings.
# Output of gencmn is redirected to OpenOffice_tmp.c with the -t switch.
-$(i18npool_BIDIR)/OpenOffice_dat.c : \
- $(patsubst %.brk,$(i18npool_BIDIR)/%_brk.c,$(i18npool_BRKFILES)) \
+$(i18npool_BIDIR)/OpenOffice_dat.c : $(SRCDIR)/i18npool/CustomTarget_breakiterator.mk \
+ $(patsubst %.brk,$(i18npool_BIDIR)/%_brk.c,$(i18npool_BRKTXTS)) \
$(i18npool_GENCMNTARGET)
$(call gb_Output_announce,$(subst $(WORKDIR)/,,$@),$(true),CMN,1)
$(call gb_Helper_abbreviate_dirs,\
RESPONSEFILE=$(shell $(gb_MKTEMP)) && \
- $(foreach brk,$(i18npool_BRKFILES),echo '$(brk)' >> $${RESPONSEFILE} && ) \
+ $(foreach brk,$(i18npool_BRKTXTS),echo '$(brk)' >> $${RESPONSEFILE} && ) \
$(i18npool_GENCMN) -n OpenOffice -t tmp -S -d $(i18npool_BIDIR)/ 0 $${RESPONSEFILE} && \
rm -f $${RESPONSEFILE} && \
echo '#ifdef _MSC_VER' > $@ && \
diff --git a/i18npool/CustomTarget_collator.mk b/i18npool/CustomTarget_collator.mk
index 95cf190..2613f67 100644
--- a/i18npool/CustomTarget_collator.mk
+++ b/i18npool/CustomTarget_collator.mk
@@ -29,9 +29,28 @@
$(eval $(call gb_CustomTarget_CustomTarget,i18npool/collator))
i18npool_CODIR := $(call gb_CustomTarget_get_workdir,i18npool/collator)
-i18npool_COTXTS := $(notdir $(wildcard $(SRCDIR)/i18npool/source/collator/data/*.txt))
+i18npool_COTXTS := \
+ ca_charset.txt \
+ dz_charset.txt \
+ hu_charset.txt \
+ ja_charset.txt \
+ ja_phonetic_alphanumeric_first.txt \
+ ja_phonetic_alphanumeric_last.txt \
+ ko_charset.txt \
+ ku_alphanumeric.txt \
+ ln_charset.txt \
+ my_dictionary.txt \
+ ne_charset.txt \
+ zh_charset.txt \
+ zh_pinyin.txt \
+ zh_radical.txt \
+ zh_stroke.txt \
+ zh_TW_charset.txt \
+ zh_TW_radical.txt \
+ zh_TW_stroke.txt \
+ zh_zhuyin.txt
-$(call gb_CustomTarget_get_target,i18npool/collator) : \
+$(call gb_CustomTarget_get_target,i18npool/collator) : $(SRCDIR)/i18npool/CustomTarget_collator.mk \
$(i18npool_CODIR)/lrl_include.hxx $(foreach txt,$(i18npool_COTXTS), \
$(patsubst %.txt,$(i18npool_CODIR)/collator_%.cxx,$(txt)))
diff --git a/i18npool/CustomTarget_indexentry.mk b/i18npool/CustomTarget_indexentry.mk
index 8a6a63c..03a8ff5 100644
--- a/i18npool/CustomTarget_indexentry.mk
+++ b/i18npool/CustomTarget_indexentry.mk
@@ -28,9 +28,20 @@
$(eval $(call gb_CustomTarget_CustomTarget,i18npool/indexentry))
-$(call gb_CustomTarget_get_target,i18npool/indexentry) : \
- $(patsubst %.txt,$(call gb_CustomTarget_get_workdir,i18npool/indexentry)/%.cxx,$(notdir \
- $(wildcard $(SRCDIR)/i18npool/source/indexentry/data/*.txt)))
+i18npool_IDXTXTS := \
+ indexdata_ko_dict.txt \
+ indexdata_zh_pinyin.txt \
+ indexdata_zh_radical.txt \
+ indexdata_zh_stroke.txt \
+ indexdata_zh_TW_radical.txt \
+ indexdata_zh_TW_stroke.txt \
+ indexdata_zh_zhuyin.txt \
+ ko_phonetic.txt \
+ zh_pinyin.txt \
+ zh_zhuyin.txt
+
+$(call gb_CustomTarget_get_target,i18npool/indexentry) : $(SRCDIR)/i18npool/CustomTarget_indexentry.mk \
+ $(patsubst %.txt,$(call gb_CustomTarget_get_workdir,i18npool/indexentry)/%.cxx,$(i18npool_IDXTXTS))
$(call gb_CustomTarget_get_workdir,i18npool/indexentry)/%.cxx : \
$(SRCDIR)/i18npool/source/indexentry/data/%.txt \
More information about the Libreoffice-commits
mailing list