[Libreoffice-commits] core.git: Branch 'libreoffice-7-0' - i18npool/CustomTarget_breakiterator.mk i18npool/source
Tor Lillqvist (via logerrit)
logerrit at kemper.freedesktop.org
Sat Dec 5 18:49:27 UTC 2020
i18npool/CustomTarget_breakiterator.mk | 1
i18npool/source/breakiterator/data/char.txt | 119 ----------------------------
2 files changed, 120 deletions(-)
New commits:
commit c808dc652ff5c899c4b7f1b676b5a0a0074db1da
Author: Tor Lillqvist <tml at collabora.com>
AuthorDate: Thu Nov 26 15:47:26 2020 +0200
Commit: Adolfo Jayme Barrientos <fitojb at ubuntu.com>
CommitDate: Sat Dec 5 19:48:54 2020 +0100
tdf#138481: Trust the built-in break iterator character data in ICU
Don't use our own char.txt.
Quite possibly we wouldn't need to use the other data in the
i18npool/source/breakiterator/data folder either. See the README file
there for the sad details.
Change-Id: I82923ae76407fdd3fa3642d818d43427fe4f5591
Reviewed-on: https://gerrit.libreoffice.org/c/core/+/106632
Tested-by: Jenkins
Reviewed-by: Tor Lillqvist <tml at collabora.com>
(cherry picked from commit 8578a1c9d167c19f1d8038fac5946b4b3cae305e)
Reviewed-on: https://gerrit.libreoffice.org/c/core/+/106688
Reviewed-by: Caolán McNamara <caolanm at redhat.com>
Reviewed-on: https://gerrit.libreoffice.org/c/core/+/107250
Reviewed-by: Adolfo Jayme Barrientos <fitojb at ubuntu.com>
diff --git a/i18npool/CustomTarget_breakiterator.mk b/i18npool/CustomTarget_breakiterator.mk
index dee46a31f0b1..e6d658f01405 100644
--- a/i18npool/CustomTarget_breakiterator.mk
+++ b/i18npool/CustomTarget_breakiterator.mk
@@ -51,7 +51,6 @@ endif
i18npool_BRKTXTS := \
$(if $(i18npool_breakiterator_want_in),char_in.brk) \
- char.brk \
count_word.brk \
$(call gb_Helper_optional_locale,he,dict_word_he.brk) \
$(call gb_Helper_optional_locale,hu,dict_word_hu.brk) \
diff --git a/i18npool/source/breakiterator/data/char.txt b/i18npool/source/breakiterator/data/char.txt
deleted file mode 100644
index 3b9f801a7ace..000000000000
--- a/i18npool/source/breakiterator/data/char.txt
+++ /dev/null
@@ -1,119 +0,0 @@
-#
-# Copyright (C) 2002-2009, International Business Machines Corporation and others.
-# All Rights Reserved.
-#
-# file: char.txt
-#
-# ICU Character Break Rules, also known as Grapheme Cluster Boundaries
-# See Unicode Standard Annex #29.
-# These rules are based on TR29 Revision 13, for Unicode Version 5.1
-# Modifications to SpacingMark and Prepend by M. Hosken.
-#
-
-#
-# Character Class Definitions.
-#
-$CR = [\p{Grapheme_Cluster_Break = CR}];
-$LF = [\p{Grapheme_Cluster_Break = LF}];
-$Control = [\p{Grapheme_Cluster_Break = Control}];
-$Prepend = [\p{Grapheme_Cluster_Break = Prepend}];
-$Extend = [\p{Grapheme_Cluster_Break = Extend}];
-$SpacingMark = [\p{Grapheme_Cluster_Break = SpacingMark}];
-# True Indic wants to move by syllables. Break up SpacingMark. This based on Unicode 6.0 data
-# In effect it is [\p{Grapheme_Cluster_Break = SpacingMark} - \u0E30 \u0E32 \u0E45 \u0EB0 \u0EB2 \u102B \u102C \u1038
-# \u1062-\u1064 \u1067-\u106D \u1083 \u1087-\u108C \u108F \u109A-\u109C \u19B0-\u19B4 \u19B8-\u19C0 \u19C8 \u19C9
-# \u1A61 \u1A63 \u1A64 \u1BE7 \u1BEA-\u1BEC \u1BEE \u1BF2 \u1BF3 \uAA7B
-$IndicSpacing = [\u0903 \u093B \u093E-\u0940 \u0949-\u094C \u094E \u094F \u0982 \u0983 \u09BF \u09C0 \u09C7 \u09C8 \u09CB \u09CC \u0A03 \u0A3E-\u0A40 \u0A83 \u0ABE-\u0AC0 \u0AC9 \u0ACB \u0ACC \u0B02 \u0B03 \u0B40 \u0B47 \u0B48 \u0B4B-\u0B4C \u0BBF \u0BC1 \u0BC2 \u0BC6-\u0BC8 \u0BCA-\u0BCC \u0C01-\u0C03 \u0C41-\u0C44 \u0C82 \u0C83 \u0CBE \u0CC0 \u0CC1 \u0CC3 \u0CC4 \u0CC7 \u0CC8 \u0CCA \u0CCB \u0D02 \u0D03 \u0D3F \u0D40 \u0D46-\u0D48 \u0D4A-\u0D4C \u0D82 \u0D83 \u0DD0 \u0DD1 \u0DD8-\u0DDE \u0F3E \u0F3F \u0F7F \u1923-\u1926 \u1929-\u192B \u1930 \u1931 \u1933-\u1938 \u1A19-\u1A1B \u1B04 \u1B35 \u1B3B \u1B3D-\u1B41 \u1B43 \u1B44 \u1B82 \u1BA1 \u1BA6 \u1BA7 \u1BAA \u1C24-\u1C2B \u1C34 \u1C35 \u1CE1 \u1CF2 \uA880 \uA881 \uA8B4-\uA8C3 \uA952 \uA953 \uA983 \uA9B4 \uA9B5 \uA9BA \uA9BB \uA9BD-\uA9C0 \uAA2F \uAA30 \uAA33 \uAA34 \uABE3 \uABE4 \uABE6 \uABE7 \uABE9 \uABEA \uABEC \U00011000 \U00011002 \U00011082 \U000110B0-\U000110B2 \U000110B7 \U000100B8 \U0001D166 \U0001D16D];
-# SEAsian (Thai, Lao, Burmese, Tai Lue, Tai Tham, Batak) are cluster based not syllable based
-$SEASpacing = [\u0E33 \u0EB3 \u1031 \u103B \u103C \u1056 \u1057 \u1084 \u17B6 \u17BE-\u17C5 \u17C7 \u17C8 \u1A55 \u1A57 \u1A6D-\u1A72 \uA823 \uA824 \uA827 \uAA4D];
-$BengaliLetter = [\u0985-\u09B9 \u09CE \u09DC-\u09E1 \u09F0-\u09F1];
-$BengaliSignVirama = \u09CD;
-$GujaratiLetter = [\u0A85-\u0A8C \u0A8F-\u0A90 \u0A93-\u0AB9 \u0AE0-\u0AE1];
-$GujaratiSignVirama = \u0ACD;
-$DevanagariLetter = [\u0904-\u0939 \u0958-\u0961 \u0972-\u097F];
-$DevanagariSignVirama = \u094D;
-$KannadaLetter = [\u0C85-\u0CB9 \u0CDE-\u0CE1];
-$KannadaSignVirama = \u0CCD;
-$MalayalamLetter = [\u0D05-\u0D39 \u0D60-\u0D61 \u0D7A-\u0D7F];
-$MalayalamSignVirama = \u0D4D;
-$OdiaLetter = [\u0B05-\u0B39 \u0B5C-\u0B61 \u0B71];
-$OdiaSignVirama = \u0B4D;
-$GurmukhiLetter = [\u0A05-\u0A39 \u0A59-\u0A5E];
-$GurmukhiSignVirama = \u0A4D;
-$TamilKa = \u0B95;
-$TamilSignVirama = \u0BCD;
-$TamilSsa = \u0BB7;
-$TeluguLetter = [\u0C05-\u0C39 \u0C58-\u0C61];
-$TeluguSignVirama = \u0C4D;
-
-#
-# Korean Syllable Definitions
-#
-$L = [\p{Grapheme_Cluster_Break = L}];
-$V = [\p{Grapheme_Cluster_Break = V}];
-$T = [\p{Grapheme_Cluster_Break = T}];
-
-$LV = [\p{Grapheme_Cluster_Break = LV}];
-$LVT = [\p{Grapheme_Cluster_Break = LVT}];
-
-
-## -------------------------------------------------
-!!chain;
-
-!!forward;
-
-$CR $LF;
-
-$BengaliLetter ($BengaliSignVirama $BengaliLetter?)+;
-$GujaratiLetter ($GujaratiSignVirama $GujaratiLetter?)+;
-$DevanagariLetter ($DevanagariSignVirama $DevanagariLetter?)+;
-$KannadaLetter ($KannadaSignVirama $KannadaLetter?)+;
-$MalayalamLetter ($MalayalamSignVirama $MalayalamLetter?)+;
-$OdiaLetter ($OdiaSignVirama $OdiaLetter?)+;
-$GurmukhiLetter ($GurmukhiSignVirama $GurmukhiLetter?)+;
-$TamilKa $TamilSignVirama $TamilSsa;
-$TeluguLetter ($TeluguSignVirama $TeluguLetter?)+;
-
-$L ($L | $V | $LV | $LVT);
-($LV | $V) ($V | $T);
-($LVT | $T) $T;
-
-[^$Control $CR $LF] $Extend;
-
-[^$Control $CR $LF] ($IndicSpacing | $SEASpacing);
-#[^$Control $CR $LF] $SpacingMark;
-# $Prepend [^$Control $CR $LF];
-
-
-## -------------------------------------------------
-
-!!reverse;
-$LF $CR;
-($BengaliLetter? $BengaliSignVirama)+ $BengaliLetter;
-($GujaratiLetter? $GujaratiSignVirama)+ $GujaratiLetter;
-($DevanagariLetter? $DevanagariSignVirama)+ $DevanagariLetter;
-($KannadaLetter? $KannadaSignVirama)+ $KannadaLetter;
-($MalayalamLetter? $MalayalamSignVirama)+ $MalayalamLetter;
-($OdiaLetter? $OdiaSignVirama)+ $OdiaLetter;
-($GurmukhiLetter? $GurmukhiSignVirama)+ $GurmukhiLetter;
-$TamilSsa $TamilSignVirama $TamilKa;
-($TeluguLetter? $TeluguSignVirama)+ $TeluguLetter;
-($L | $V | $LV | $LVT) $L;
-($V | $T) ($LV | $V);
-$T ($LVT | $T);
-
-$Extend [^$Control $CR $LF];
-($IndicSpacing | $SEASpacing) [^$Control $CR $LF];
-#$SpacingMark [^$Control $CR $LF];
-# [^$Control $CR $LF] $Prepend;
-
-
-## -------------------------------------------------
-
-!!safe_reverse;
-
-
-## -------------------------------------------------
-
-!!safe_forward;
-
More information about the Libreoffice-commits
mailing list