organicmaps/icu
13
Fork 0
mirror of https://github.com/unicode-org/icu.git synced 2025-04-14 17:24:01 +00:00
Code Issues 1 Projects Releases Wiki Activity Actions 1

Merge remote-tracking branch 'upstream/master' into unit-id

Browse source
This commit is contained in:
Shane F. Carr 2020-03-13 18:05:31 -05:00
commit 881ae36b94
3291 changed files with 35696 additions and 13921 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

17
.ci-builds/.azure-exhaustive-tests.yml
View file

@ -3,12 +3,6 @@
# Note: The exhaustive test configuration is in a separate file
# so that it can be run independently from the regular builds.
#
resources:
- repo: self
lfs: true
fetchDepth: 1
# Only run the exhaustive tests on the master and maint branches, and
# also batch up any pending changes so that we will only have at most
# one build running at a given time (since they take a long time).
@ -17,7 +11,7 @@ trigger:
branches:
include:
- master
- maint/*
- maint/maint-*
jobs:
#-------------------------------------------------------------------------
@ -30,15 +24,19 @@ jobs:
vmImage: 'Ubuntu 16.04'
demands: ant
steps:
- checkout: self
lfs: true
fetchDepth: 1
- script: |
echo "Building ICU4J" && cd icu4j && ant init && ant exhaustiveCheck
displayName: 'Build and Exhaustive Tests'
env:
BUILD: ICU4J
- script: |
cat `find out/junit-results -name "*.txt" -exec grep -l FAILED {} \;`
[ -d icu4j/out/junit-results ] && cd icu4j && cat `find out/junit-results -name "*.txt" -exec grep -l FAILED {} \;`
condition: failed() # only run if the build fails.
displayName: 'List failures (if any)'
timeoutInMinutes: 2
#-------------------------------------------------------------------------
# Note: The exhaustive tests take roughly 65 mins to complete on the
# Azure VMs.
@ -48,6 +46,9 @@ jobs:
pool:
vmImage: 'Ubuntu 16.04'
steps:
- checkout: self
lfs: true
fetchDepth: 1
- script: |
cd icu4c/source && ./runConfigureICU Linux && make -j2
displayName: 'Build'

75
.ci-builds/.azure-pipelines.yml
View file

@ -1,10 +1,5 @@
# Azure Pipelines (VSTS) configuration for CI builds for ICU.
resources:
- repo: self
lfs: true
fetchDepth: 1
jobs:
#-------------------------------------------------------------------------
- job: ICU4J_OpenJDK_Ubuntu_1604
@ -14,13 +9,16 @@ jobs:
vmImage: 'Ubuntu 16.04'
demands: ant
steps:
- checkout: self
lfs: true
fetchDepth: 1
- script: |
echo "Building ICU4J" && cd icu4j && ant init && ant check
displayName: 'Build and Test'
env:
BUILD: ICU4J
- script: |
cd icu4j && cat `find out/junit-results -name "*.txt" -exec grep -l FAILED {} \;`
[ -d icu4j/out/junit-results ] && cd icu4j && cat `find out/junit-results -name "*.txt" -exec grep -l FAILED {} \;`
condition: failed() # only run if the build fails.
displayName: 'List failures (if any)'
#-------------------------------------------------------------------------
@ -30,6 +28,9 @@ jobs:
pool:
vmImage: 'Ubuntu 16.04'
steps:
- checkout: self
lfs: true
fetchDepth: 1
- script: |
cd icu4c/source && ./runConfigureICU Linux && make -j2 check
displayName: 'Build and Test'
@ -43,6 +44,9 @@ jobs:
pool:
vmImage: 'Ubuntu 16.04'
steps:
- checkout: self
lfs: true
fetchDepth: 1
- script: |
export CPPFLAGS="-Werror -Wall -Wextra -Wextra-semi -Wundef -Wnon-virtual-dtor" && cd icu4c/source && ./runConfigureICU Linux && make -j2 tests
displayName: 'Build only (WarningsAsErrors)'
@ -56,6 +60,9 @@ jobs:
pool:
vmImage: 'Ubuntu 16.04'
steps:
- checkout: self
lfs: true
fetchDepth: 1
- script: |
cd icu4c/source && \
ICU_DATA_FILTER_FILE=../../.ci-builds/data-filter.json ./runConfigureICU Linux && \
@ -77,6 +84,9 @@ jobs:
- visualstudio
- Cmd
steps:
- checkout: self
lfs: true
fetchDepth: 1
- task: VSBuild@1
displayName: 'Build Solution'
inputs:
@ -111,6 +121,9 @@ jobs:
- visualstudio
- Cmd
steps:
- checkout: self
lfs: true
fetchDepth: 1
- task: VSBuild@1
displayName: 'Build Solution'
inputs:
@ -140,6 +153,9 @@ jobs:
- visualstudio
- Cmd
steps:
- checkout: self
lfs: true
fetchDepth: 1
- task: VSBuild@1
displayName: 'Build Solution'
inputs:
@ -181,6 +197,9 @@ jobs:
- visualstudio
- Cmd
steps:
- checkout: self
lfs: true
fetchDepth: 1
- powershell: |
$filterPath = $Env:BUILD_SOURCESDIRECTORY + "\.ci-builds\data-filter.json"
$vstsCommandString = "vso[task.setvariable variable=ICU_DATA_FILTER_FILE]" + $filterPath
@ -203,6 +222,9 @@ jobs:
- visualstudio
- Cmd
steps:
- checkout: self
lfs: true
fetchDepth: 1
- task: VSBuild@1
displayName: 'Build Solution'
inputs:
@ -215,41 +237,6 @@ jobs:
filename: icu4c/source/allinone/icucheck.bat
arguments: 'x86 Debug'
#-------------------------------------------------------------------------
# Using a manual install of Python 3, until the vs2015 image has it
# by default.
#
- job: ICU4C_MSVC_x64_Release_VS2015
displayName: 'C: MSVC 64-bit Release (VS 2015)'
timeoutInMinutes: 30
pool:
vmImage: 'vs2015-win2012r2'
demands:
- msbuild
- visualstudio
- Cmd
steps:
- powershell: 'Invoke-WebRequest https://www.python.org/ftp/python/3.7.2/python-3.7.2-amd64-webinstall.exe -OutFile c:\py3-setup.exe'
- script: |
c:\py3-setup.exe /quiet PrependPath=1 InstallAllUsers=1 Include_launcher=1 InstallLauncherAllUsers=1 Include_test=0 Include_doc=0 Include_dev=0 Include_debug=0 Include_tcltk=0 TargetDir=c:\py3
- script: |
@echo ##vso[task.prependpath]C:\py3
@echo ##vso[task.prependpath]C:\py3\Scripts
- script: |
python --version
py -3 --version
- task: VSBuild@1
displayName: 'Build Solution'
inputs:
solution: icu4c/source/allinone/allinone.sln
platform: x64
configuration: Release
msbuildArgs: '/p:SkipUWP=true'
- task: BatchScript@1
displayName: 'Run Tests (icucheck.bat)'
inputs:
filename: icu4c/source/allinone/icucheck.bat
arguments: 'x64 Release'
#-------------------------------------------------------------------------
- job: ICU4C_MSYS2_GCC_x86_64_Release
displayName: 'C: MSYS2 GCC x86_64 Release'
timeoutInMinutes: 45
@ -258,6 +245,9 @@ jobs:
demands:
- Cmd
steps:
- checkout: self
lfs: true
fetchDepth: 1
- script: |
choco install -y msys2
rem refreshenv
@ -288,6 +278,9 @@ jobs:
pool:
vmImage: 'macOS-10.14'
steps:
- checkout: self
lfs: true
fetchDepth: 1
- script: |
export CPPFLAGS="-Werror -Wall -Wextra -Wextra-semi -Wundef -Wnon-virtual-dtor" && cd icu4c/source && ./runConfigureICU MacOSX && make -j2 tests
displayName: 'Build only (WarningsAsErrors)'

73
.ci-builds/.azure-valgrind.yml Normal file
View file

@ -0,0 +1,73 @@
# Azure Pipelines configuration for Valgrind for ICU4C.
#
# Note: The valgrind test configuration is in a separate file
# so that it can be run independently from the regular builds.
#
# The Ubuntu images don't have valgrind installed by default, so we need
# install it first.
#
# Only run valgrind on the master and maint branches, and
# batch up any pending changes so that we will only have at most
# one build running at a given time (since it takes time).
trigger:
batch: true
branches:
include:
- master
- maint/maint-*
paths:
include:
- '*'
exclude:
- docs/*
- icu4j/*
- tools/*
- vendor/*
- .appveyor.xml
- .cpyskip.txt
- .travis.yml
- KEYS
- README.md
jobs:
#-------------------------------------------------------------------------
- job: ICU4C_Clang_Valgrind_Ubuntu_1604
displayName: 'C: Linux Clang Valgrind (Ubuntu 16.04)'
timeoutInMinutes: 60
pool:
vmImage: 'Ubuntu 16.04'
steps:
- checkout: self
lfs: true
fetchDepth: 1
- script: |
set -ex
sudo apt -y update
sudo apt install -y valgrind
displayName: 'Install valgrind'
timeoutInMinutes: 5
- script: |
cd icu4c/source && ./runConfigureICU --enable-debug Linux --disable-renaming --disable-layout --disable-layoutex && make -j2 tests
displayName: 'Build'
timeoutInMinutes: 10
env:
CC: clang
CXX: clang++
- script: |
cd icu4c/source/test/intltest && LD_LIBRARY_PATH=../../lib:../../stubdata:../../tools/ctestfw:$LD_LIBRARY_PATH valgrind --tool=memcheck --error-exitcode=1 --leak-check=full --show-reachable=yes ./intltest
displayName: 'Valgrind intltest'
timeoutInMinutes: 45
- script: |
cd icu4c/source/test/cintltst && LD_LIBRARY_PATH=../../lib:../../stubdata:../../tools/ctestfw:$LD_LIBRARY_PATH valgrind --tool=memcheck --error-exitcode=1 --leak-check=full --show-reachable=yes ./cintltst
displayName: 'Valgrind cintltst'
timeoutInMinutes: 15
- script: |
cd icu4c/source/test/iotest && LD_LIBRARY_PATH=../../lib:../../stubdata:../../tools/ctestfw:$LD_LIBRARY_PATH valgrind --tool=memcheck --error-exitcode=1 --leak-check=full --show-reachable=yes ./iotest
displayName: 'Valgrind iotest'
timeoutInMinutes: 5
- script: |
cd icu4c/source/tools/icuinfo && LD_LIBRARY_PATH=../../lib:../../stubdata:../../tools/ctestfw:$LD_LIBRARY_PATH valgrind --tool=memcheck --error-exitcode=1 --leak-check=full --show-reachable=yes ./icuinfo
displayName: 'Valgrind icuinfo'
timeoutInMinutes: 5
#-------------------------------------------------------------------------

83
KEYS
View file

@ -815,3 +815,86 @@ mrLU2gvbaFZtV1HwYC3bCNqlx68rchjSQwOI5sdocwWsWbvJ28yi5I0PcBmyBa0Y
TMuS5W4GIP4f7uR1uQ==
=Veoq
-----END PGP PUBLIC KEY BLOCK-----
pub rsa4096 2020-02-24 [SC] [caduca: 2021-02-23]
4569BBC09DA846FC91CBD21CE1BBA44593CF2AE0
uid [ absoluta ] Steven R. Loomis (codesign-qormi) <srloomis@us.ibm.com>
sig 3 E1BBA44593CF2AE0 2020-02-24 Steven R. Loomis (codesign-qormi) <srloomis@us.ibm.com>
sig 44CE7BF2825EA2CD 2020-02-28 ICU Project @IBM (International Components for Unicode Development at IBM) <icuintl@us.ibm.com>
uid [ absoluta ] Steven R. Loomis (qormi signing key) <srl295@gmail.com>
sig 3 E1BBA44593CF2AE0 2020-02-24 Steven R. Loomis (codesign-qormi) <srloomis@us.ibm.com>
sig 44CE7BF2825EA2CD 2020-02-28 ICU Project @IBM (International Components for Unicode Development at IBM) <icuintl@us.ibm.com>
sub rsa2048 2020-02-24 [E] [caduca: 2021-02-23]
sig E1BBA44593CF2AE0 2020-02-24 Steven R. Loomis (codesign-qormi) <srloomis@us.ibm.com>
-----BEGIN PGP PUBLIC KEY BLOCK-----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=DEHc
-----END PGP PUBLIC KEY BLOCK-----

7
README.md
View file

@ -8,13 +8,14 @@ The ICU project is under the stewardship of [The Unicode Consortium](https://www
![ICU Logo](./tools/images/iculogo_64.png)
### Build Status (master branch)
### Build Status (`master` branch)
Build | Status
------|-------
TravisCI | [![Build Status](https://travis-ci.org/unicode-org/icu.svg?branch=master)](https://travis-ci.org/unicode-org/icu)
Azure Pipelines | [![Build Status](https://unicode-icu.visualstudio.com/ICU/_apis/build/status/Azure%20CI?branchName=master)](https://unicode-icu.visualstudio.com/ICU/_build/latest?definitionId=21&branchName=master)
Azure Pipelines (Exhaustive Tests) | [![Build Status](https://unicode-icu.visualstudio.com/ICU/_apis/build/status/Azure%20CI%20%5BExhaustive%20Tests%5D?branchName=master)](https://unicode-icu.visualstudio.com/ICU/_build/latest?definitionId=24&branchName=master)
Azure Pipelines | [![Build Status](https://unicode-icu.visualstudio.com/ICU/_apis/build/status/CI?branchName=master)](https://unicode-icu.visualstudio.com/ICU/_build/latest?definitionId=21&branchName=master)
Azure Pipelines (Exhaustive Tests) | [![Build Status](https://unicode-icu.visualstudio.com/ICU/_apis/build/status/CI-Exhaustive-Master?branchName=master)](https://unicode-icu.visualstudio.com/ICU/_build/latest?definitionId=24&branchName=master)
Azure Pipelines (Valgrind ICU4C) | [![Build Status](https://unicode-icu.visualstudio.com/ICU/_apis/build/status/CI-Valgrind-Master?branchName=master)](https://unicode-icu.visualstudio.com/ICU/_build/latest?definitionId=30&branchName=master)
AppVeyor | [![Build status](https://ci.appveyor.com/api/projects/status/6ev1ssb6efahsvs2?svg=true)](https://ci.appveyor.com/project/unicode-org/icu)
Fuzzing | [![Fuzzing Status](https://oss-fuzz-build-logs.storage.googleapis.com/badges/icu.svg)](https://bugs.chromium.org/p/oss-fuzz/issues/list?sort=-opened&can=1&q=proj:icu)

6
icu4c/APIChangeReport.html
View file

@ -5,12 +5,12 @@
-->
<head>
<META http-equiv="Content-Type" content="text/html; charset=utf-8">
<title>ICU4C API Comparison: ICU 65 with ICU 66 (preview)</title>
<title>ICU4C API Comparison: ICU 65 with ICU 66</title>
<link type="text/css" href="icu4c.css" rel="stylesheet">
</head>
<body>
<a name="#_top"></a>
<h1>ICU4C API Comparison: ICU 65 with ICU 66 (preview)</h1>
<h1>ICU4C API Comparison: ICU 65 with ICU 66</h1>
<div id="toc">
<ul>
<li>
@ -1501,7 +1501,7 @@
<a href="#_top">(jump back to top)</a>
<hr>
<p>
<i><font size="-1">Contents generated by StableAPI tool on Tue Dec 03 15:47:14 PST 2019<br>
<i><font size="-1">Contents generated by StableAPI tool on Wed Feb 19 10:40:34 PST 2020<br>
Copyright &copy; 2017 and later: Unicode, Inc. and others.<br>
License &amp; terms of use: http://www.unicode.org/copyright.html
</font></i>

4
icu4c/APIChangeReport.md
View file

@ -5,7 +5,7 @@
License & terms of use: http://www.unicode.org/copyright.html
-->
# ICU4C API Comparison: ICU 65 with ICU 66 (preview)
# ICU4C API Comparison: ICU 65 with ICU 66
> _Note_ Markdown format of this document is new for ICU 65.
@ -520,7 +520,7 @@ This section shows cases where the signature was "simplified" for the sake of co
## Colophon
Contents generated by StableAPI tool on Tue Dec 03 15:19:41 PST 2019
Contents generated by StableAPI tool on Wed Feb 19 10:40:39 PST 2020
Copyright © 2019 and later: Unicode, Inc. and others.
License & terms of use: http://www.unicode.org/copyright.html

2
icu4c/LICENSE
View file

@ -1,6 +1,6 @@
COPYRIGHT AND PERMISSION NOTICE (ICU 58 and later)
Copyright © 1991-2019 Unicode, Inc. All rights reserved.
Copyright © 1991-2020 Unicode, Inc. All rights reserved.
Distributed under the Terms of Use in https://www.unicode.org/copyright.html.
Permission is hereby granted, free of charge, to any person obtaining

8
icu4c/readme.html
View file

@ -3,7 +3,7 @@
<html lang="en-US" xmlns="http://www.w3.org/1999/xhtml" xml:lang="en-US">
<head>
<title>ReadMe for ICU 66.0.1</title>
<title>ReadMe for ICU 66.1</title>
<meta name="COPYRIGHT" content=
"Copyright (C) 2016 and later: Unicode, Inc. and others. License &amp; terms of use: http://www.unicode.org/copyright.html"/>
<!-- meta name="COPYRIGHT" content=
@ -24,7 +24,7 @@
-->
<!-- <body> -->
<body class="milestone">
<body class="rc">
<p class="only-draft"><b>Note:</b> This is a draft readme.</p>
<h1>
@ -33,7 +33,7 @@
<span class="only-rc">Release Candidate</span>
<!-- <span class="only-milestone">(Milestone Release)</span> -->
<span class="only-milestone">(Preview Release)</span>
<abbr title="International Components for Unicode">ICU</abbr> 66.0.1 ReadMe
<abbr title="International Components for Unicode">ICU</abbr> 66.1 ReadMe
</h1>
<!-- Most of the time we shouldn't need to comment/uncomment this paragraph, just change the body class -->
@ -47,7 +47,7 @@
<p class="note only-rc">This is a release candidate version of ICU4C.
It is not recommended for production use.</p>
<p>Last updated: 2019-Nov-27<br/>
<p>Last updated: 2020-Feb-12<br/>
Copyright &copy; 2016 and later: Unicode, Inc. and others. License &amp; terms of use:
<a href="http://www.unicode.org/copyright.html">http://www.unicode.org/copyright.html</a><br/>
Copyright &copy; 1997-2016 International Business Machines Corporation and others.

35
icu4c/source/common/brkiter.cpp
View file

@ -38,6 +38,7 @@
#include "uresimp.h"
#include "uassert.h"
#include "ubrkimpl.h"
#include "utracimp.h"
#include "charstr.h"
// *****************************************************************************
@ -412,14 +413,23 @@ BreakIterator::makeInstance(const Locale& loc, int32_t kind, UErrorCode& status)
BreakIterator *result = NULL;
switch (kind) {
case UBRK_CHARACTER:
result = BreakIterator::buildInstance(loc, "grapheme", status);
{
UTRACE_ENTRY(UTRACE_UBRK_CREATE_CHARACTER);
result = BreakIterator::buildInstance(loc, "grapheme", status);
UTRACE_EXIT_STATUS(status);
}
break;
case UBRK_WORD:
result = BreakIterator::buildInstance(loc, "word", status);
{
UTRACE_ENTRY(UTRACE_UBRK_CREATE_WORD);
result = BreakIterator::buildInstance(loc, "word", status);
UTRACE_EXIT_STATUS(status);
}
break;
case UBRK_LINE:
uprv_strcpy(lbType, "line");
{
UTRACE_ENTRY(UTRACE_UBRK_CREATE_LINE);
uprv_strcpy(lbType, "line");
char lbKeyValue[kKeyValueLenMax] = {0};
UErrorCode kvStatus = U_ZERO_ERROR;
int32_t kLen = loc.getKeywordValue("lb", lbKeyValue, kKeyValueLenMax, kvStatus);
@ -427,13 +437,17 @@ BreakIterator::makeInstance(const Locale& loc, int32_t kind, UErrorCode& status)
uprv_strcat(lbType, "_");
uprv_strcat(lbType, lbKeyValue);
}
result = BreakIterator::buildInstance(loc, lbType, status);
UTRACE_DATA1(UTRACE_INFO, "lb=%s", lbKeyValue);
UTRACE_EXIT_STATUS(status);
}
result = BreakIterator::buildInstance(loc, lbType, status);
break;
case UBRK_SENTENCE:
result = BreakIterator::buildInstance(loc, "sentence", status);
#if !UCONFIG_NO_FILTERED_BREAK_ITERATION
{
UTRACE_ENTRY(UTRACE_UBRK_CREATE_SENTENCE);
result = BreakIterator::buildInstance(loc, "sentence", status);
#if !UCONFIG_NO_FILTERED_BREAK_ITERATION
char ssKeyValue[kKeyValueLenMax] = {0};
UErrorCode kvStatus = U_ZERO_ERROR;
int32_t kLen = loc.getKeywordValue("ss", ssKeyValue, kKeyValueLenMax, kvStatus);
@ -444,11 +458,16 @@ BreakIterator::makeInstance(const Locale& loc, int32_t kind, UErrorCode& status)
delete fbiBuilder;
}
}
}
#endif
UTRACE_EXIT_STATUS(status);
}
break;
case UBRK_TITLE:
result = BreakIterator::buildInstance(loc, "title", status);
{
UTRACE_ENTRY(UTRACE_UBRK_CREATE_TITLE);
result = BreakIterator::buildInstance(loc, "title", status);
UTRACE_EXIT_STATUS(status);
}
break;
default:
status = U_ILLEGAL_ARGUMENT_ERROR;

16
icu4c/source/common/dictbe.cpp
View file

@ -18,6 +18,7 @@
#include "unicode/uniset.h"
#include "unicode/chariter.h"
#include "unicode/ubrk.h"
#include "utracimp.h"
#include "uvectr32.h"
#include "uvector.h"
#include "uassert.h"
@ -194,6 +195,8 @@ ThaiBreakEngine::ThaiBreakEngine(DictionaryMatcher *adoptDictionary, UErrorCode
: DictionaryBreakEngine(),
fDictionary(adoptDictionary)
{
UTRACE_ENTRY(UTRACE_UBRK_CREATE_BREAK_ENGINE);
UTRACE_DATA1(UTRACE_INFO, "dictbe=%s", "Thai");
fThaiWordSet.applyPattern(UNICODE_STRING_SIMPLE("[[:Thai:]&[:LineBreak=SA:]]"), status);
if (U_SUCCESS(status)) {
setCharacters(fThaiWordSet);
@ -213,6 +216,7 @@ ThaiBreakEngine::ThaiBreakEngine(DictionaryMatcher *adoptDictionary, UErrorCode
fEndWordSet.compact();
fBeginWordSet.compact();
fSuffixSet.compact();
UTRACE_EXIT_STATUS(status);
}
ThaiBreakEngine::~ThaiBreakEngine() {
@ -436,6 +440,8 @@ LaoBreakEngine::LaoBreakEngine(DictionaryMatcher *adoptDictionary, UErrorCode &s
: DictionaryBreakEngine(),
fDictionary(adoptDictionary)
{
UTRACE_ENTRY(UTRACE_UBRK_CREATE_BREAK_ENGINE);
UTRACE_DATA1(UTRACE_INFO, "dictbe=%s", "Laoo");
fLaoWordSet.applyPattern(UNICODE_STRING_SIMPLE("[[:Laoo:]&[:LineBreak=SA:]]"), status);
if (U_SUCCESS(status)) {
setCharacters(fLaoWordSet);
@ -452,6 +458,7 @@ LaoBreakEngine::LaoBreakEngine(DictionaryMatcher *adoptDictionary, UErrorCode &s
fMarkSet.compact();
fEndWordSet.compact();
fBeginWordSet.compact();
UTRACE_EXIT_STATUS(status);
}
LaoBreakEngine::~LaoBreakEngine() {
@ -632,6 +639,8 @@ BurmeseBreakEngine::BurmeseBreakEngine(DictionaryMatcher *adoptDictionary, UErro
: DictionaryBreakEngine(),
fDictionary(adoptDictionary)
{
UTRACE_ENTRY(UTRACE_UBRK_CREATE_BREAK_ENGINE);
UTRACE_DATA1(UTRACE_INFO, "dictbe=%s", "Mymr");
fBurmeseWordSet.applyPattern(UNICODE_STRING_SIMPLE("[[:Mymr:]&[:LineBreak=SA:]]"), status);
if (U_SUCCESS(status)) {
setCharacters(fBurmeseWordSet);
@ -645,6 +654,7 @@ BurmeseBreakEngine::BurmeseBreakEngine(DictionaryMatcher *adoptDictionary, UErro
fMarkSet.compact();
fEndWordSet.compact();
fBeginWordSet.compact();
UTRACE_EXIT_STATUS(status);
}
BurmeseBreakEngine::~BurmeseBreakEngine() {
@ -825,6 +835,8 @@ KhmerBreakEngine::KhmerBreakEngine(DictionaryMatcher *adoptDictionary, UErrorCod
: DictionaryBreakEngine(),
fDictionary(adoptDictionary)
{
UTRACE_ENTRY(UTRACE_UBRK_CREATE_BREAK_ENGINE);
UTRACE_DATA1(UTRACE_INFO, "dictbe=%s", "Khmr");
fKhmerWordSet.applyPattern(UNICODE_STRING_SIMPLE("[[:Khmr:]&[:LineBreak=SA:]]"), status);
if (U_SUCCESS(status)) {
setCharacters(fKhmerWordSet);
@ -850,6 +862,7 @@ KhmerBreakEngine::KhmerBreakEngine(DictionaryMatcher *adoptDictionary, UErrorCod
fEndWordSet.compact();
fBeginWordSet.compact();
// fSuffixSet.compact();
UTRACE_EXIT_STATUS(status);
}
KhmerBreakEngine::~KhmerBreakEngine() {
@ -1045,6 +1058,8 @@ foundBest:
static const uint32_t kuint32max = 0xFFFFFFFF;
CjkBreakEngine::CjkBreakEngine(DictionaryMatcher *adoptDictionary, LanguageType type, UErrorCode &status)
: DictionaryBreakEngine(), fDictionary(adoptDictionary) {
UTRACE_ENTRY(UTRACE_UBRK_CREATE_BREAK_ENGINE);
UTRACE_DATA1(UTRACE_INFO, "dictbe=%s", "Hani");
// Korean dictionary only includes Hangul syllables
fHangulWordSet.applyPattern(UNICODE_STRING_SIMPLE("[\\uac00-\\ud7a3]"), status);
fHanWordSet.applyPattern(UNICODE_STRING_SIMPLE("[:Han:]"), status);
@ -1066,6 +1081,7 @@ CjkBreakEngine::CjkBreakEngine(DictionaryMatcher *adoptDictionary, LanguageType
setCharacters(cjSet);
}
}
UTRACE_EXIT_STATUS(status);
}
CjkBreakEngine::~CjkBreakEngine(){

272
icu4c/source/common/localematcher.cpp
View file

@ -12,6 +12,7 @@
#include "unicode/localematcher.h"
#include "unicode/locid.h"
#include "unicode/stringpiece.h"
#include "unicode/uloc.h"
#include "unicode/uobject.h"
#include "cstring.h"
#include "localeprioritylist.h"
@ -20,6 +21,7 @@
#include "lsr.h"
#include "uassert.h"
#include "uhash.h"
#include "ustr_imp.h"
#include "uvector.h"
#define UND_LSR LSR("und", "", "", LSR::EXPLICIT_LSR)
@ -308,20 +310,22 @@ UBool compareLSRs(const UHashTok t1, const UHashTok t2) {
return *lsr1 == *lsr2;
}
bool putIfAbsent(UHashtable *lsrToIndex, const LSR &lsr, int32_t i, UErrorCode &errorCode) {
if (U_FAILURE(errorCode)) { return false; }
U_ASSERT(i > 0);
int32_t index = uhash_geti(lsrToIndex, &lsr);
if (index != 0) {
return false;
} else {
uhash_puti(lsrToIndex, const_cast<LSR *>(&lsr), i, &errorCode);
return U_SUCCESS(errorCode);
}
}
} // namespace
int32_t LocaleMatcher::putIfAbsent(const LSR &lsr, int32_t i, int32_t suppLength,
UErrorCode &errorCode) {
if (U_FAILURE(errorCode)) { return suppLength; }
int32_t index = uhash_geti(supportedLsrToIndex, &lsr);
if (index == 0) {
uhash_puti(supportedLsrToIndex, const_cast<LSR *>(&lsr), i + 1, &errorCode);
if (U_SUCCESS(errorCode)) {
supportedLSRs[suppLength] = &lsr;
supportedIndexes[suppLength++] = i;
}
}
return suppLength;
}
LocaleMatcher::LocaleMatcher(const Builder &builder, UErrorCode &errorCode) :
likelySubtags(*XLikelySubtags::getSingleton(errorCode)),
localeDistance(*LocaleDistance::getSingleton(errorCode)),
@ -331,15 +335,27 @@ LocaleMatcher::LocaleMatcher(const Builder &builder, UErrorCode &errorCode) :
supportedLocales(nullptr), lsrs(nullptr), supportedLocalesLength(0),
supportedLsrToIndex(nullptr),
supportedLSRs(nullptr), supportedIndexes(nullptr), supportedLSRsLength(0),
ownedDefaultLocale(nullptr), defaultLocale(nullptr), defaultLocaleIndex(-1) {
ownedDefaultLocale(nullptr), defaultLocale(nullptr) {
if (U_FAILURE(errorCode)) { return; }
if (thresholdDistance < 0) {
thresholdDistance = localeDistance.getDefaultScriptDistance();
}
const Locale *def = builder.defaultLocale_;
LSR builderDefaultLSR;
const LSR *defLSR = nullptr;
if (def != nullptr) {
ownedDefaultLocale = def->clone();
if (ownedDefaultLocale == nullptr) {
errorCode = U_MEMORY_ALLOCATION_ERROR;
return;
}
def = ownedDefaultLocale;
builderDefaultLSR = getMaximalLsrOrUnd(likelySubtags, *def, errorCode);
if (U_FAILURE(errorCode)) { return; }
defLSR = &builderDefaultLSR;
}
supportedLocalesLength = builder.supportedLocales_ != nullptr ?
builder.supportedLocales_->size() : 0;
const Locale *def = builder.defaultLocale_;
int32_t idef = -1;
if (supportedLocalesLength > 0) {
// Store the supported locales in input order,
// so that when different types are used (e.g., language tag strings)
@ -356,15 +372,6 @@ LocaleMatcher::LocaleMatcher(const Builder &builder, UErrorCode &errorCode) :
}
// If the constructor fails partway, we need null pointers for destructibility.
uprv_memset(supportedLocales, 0, supportedLocalesLength * sizeof(const Locale *));
// Also find the first supported locale whose LSR is
// the same as that for the default locale.
LSR builderDefaultLSR;
const LSR *defLSR = nullptr;
if (def != nullptr) {
builderDefaultLSR = getMaximalLsrOrUnd(likelySubtags, *def, errorCode);
if (U_FAILURE(errorCode)) { return; }
defLSR = &builderDefaultLSR;
}
for (int32_t i = 0; i < supportedLocalesLength; ++i) {
const Locale &locale = *static_cast<Locale *>(builder.supportedLocales_->elementAt(i));
supportedLocales[i] = locale.clone();
@ -376,31 +383,14 @@ LocaleMatcher::LocaleMatcher(const Builder &builder, UErrorCode &errorCode) :
LSR &lsr = lsrs[i] = getMaximalLsrOrUnd(likelySubtags, supportedLocale, errorCode);
lsr.setHashCode();
if (U_FAILURE(errorCode)) { return; }
if (idef < 0 && defLSR != nullptr && lsr == *defLSR) {
idef = i;
defLSR = &lsr; // owned pointer to put into supportedLsrToIndex
if (*def == supportedLocale) {
def = &supportedLocale; // owned pointer to keep
}
}
}
// We need an unordered map from LSR to first supported locale with that LSR,
// and an ordered list of (LSR, supported index).
// We insert the supported locales in the following order:
// and an ordered list of (LSR, supported index) for
// the supported locales in the following order:
// 1. Default locale, if it is supported.
// 2. Priority locales (aka "paradigm locales") in builder order.
// 3. Remaining locales in builder order.
// In Java, we use a LinkedHashMap for both map & ordered lists.
// In C++, we use separate structures.
//
// We allocate arrays of LSRs and indexes,
// with as many slots as supported locales, for simplicity.
// We write the default and paradigm LSRs starting from the front of the arrays,
// and others starting from the back.
// At the end we reverse the non-paradigm LSRs.
// We end up wasting as many array slots as there are duplicate supported LSRs,
// but the amount of wasted space is small as long as there are few duplicates.
supportedLsrToIndex = uhash_openSize(hashLSR, compareLSRs, uhash_compareLong,
supportedLocalesLength, &errorCode);
if (U_FAILURE(errorCode)) { return; }
@ -412,79 +402,53 @@ LocaleMatcher::LocaleMatcher(const Builder &builder, UErrorCode &errorCode) :
errorCode = U_MEMORY_ALLOCATION_ERROR;
return;
}
int32_t paradigmIndex = 0;
int32_t otherIndex = supportedLocalesLength;
if (idef >= 0) {
uhash_puti(supportedLsrToIndex, const_cast<LSR *>(defLSR), idef + 1, &errorCode);
supportedLSRs[0] = defLSR;
supportedIndexes[0] = idef;
paradigmIndex = 1;
int32_t suppLength = 0;
// Determine insertion order.
// Add locales immediately that are equivalent to the default.
MaybeStackArray<int8_t, 100> order(supportedLocalesLength);
if (order.getAlias() == nullptr) {
errorCode = U_MEMORY_ALLOCATION_ERROR;
return;
}
int32_t numParadigms = 0;
for (int32_t i = 0; i < supportedLocalesLength; ++i) {
if (i == idef) { continue; }
const Locale &locale = *supportedLocales[i];
const LSR &lsr = lsrs[i];
if (defLSR == nullptr) {
U_ASSERT(i == 0);
def = &locale;
defLSR = &lsr;
idef = 0;
uhash_puti(supportedLsrToIndex, const_cast<LSR *>(&lsr), 0 + 1, &errorCode);
supportedLSRs[0] = &lsr;
supportedIndexes[0] = 0;
paradigmIndex = 1;
} else if (idef >= 0 && lsr == *defLSR) {
// lsr == *defLSR means that this supported locale is
// a duplicate of the default locale.
// Either an explicit default locale is supported, and we added it before the loop,
// or there is no explicit default locale, and this is
// a duplicate of the first supported locale.
// In both cases, idef >= 0 now, so otherwise we can skip the comparison.
// For a duplicate, putIfAbsent() is a no-op, so nothing to do.
suppLength = putIfAbsent(lsr, 0, suppLength, errorCode);
} else if (lsr.isEquivalentTo(*defLSR)) {
suppLength = putIfAbsent(lsr, i, suppLength, errorCode);
} else if (localeDistance.isParadigmLSR(lsr)) {
order[i] = 2;
++numParadigms;
} else {
if (putIfAbsent(supportedLsrToIndex, lsr, i + 1, errorCode)) {
if (localeDistance.isParadigmLSR(lsr)) {
supportedLSRs[paradigmIndex] = &lsr;
supportedIndexes[paradigmIndex++] = i;
} else {
supportedLSRs[--otherIndex] = &lsr;
supportedIndexes[otherIndex] = i;
}
}
order[i] = 3;
}
if (U_FAILURE(errorCode)) { return; }
}
// Reverse the non-paradigm LSRs to be in order, right after the paradigm LSRs.
// First fill the unused slots between paradigm LSRs and other LSRs.
// This gap is as large as the number of locales with duplicate LSRs.
int32_t i = paradigmIndex;
int32_t j = supportedLocalesLength - 1;
while (i < otherIndex && otherIndex <= j) {
supportedLSRs[i] = supportedLSRs[j];
supportedIndexes[i++] = supportedIndexes[j--];
// Add supported paradigm locales.
int32_t paradigmLimit = suppLength + numParadigms;
for (int32_t i = 0; i < supportedLocalesLength && suppLength < paradigmLimit; ++i) {
if (order[i] == 2) {
suppLength = putIfAbsent(lsrs[i], i, suppLength, errorCode);
}
}
// Swap remaining non-paradigm LSRs in place.
while (i < j) {
const LSR *tempLSR = supportedLSRs[i];
supportedLSRs[i] = supportedLSRs[j];
supportedLSRs[j] = tempLSR;
int32_t tempIndex = supportedIndexes[i];
supportedIndexes[i++] = supportedIndexes[j];
supportedIndexes[j--] = tempIndex;
// Add remaining supported locales.
for (int32_t i = 0; i < supportedLocalesLength; ++i) {
if (order[i] == 3) {
suppLength = putIfAbsent(lsrs[i], i, suppLength, errorCode);
}
}
supportedLSRsLength = supportedLocalesLength - (otherIndex - paradigmIndex);
supportedLSRsLength = suppLength;
// If supportedLSRsLength < supportedLocalesLength then
// we waste as many array slots as there are duplicate supported LSRs,
// but the amount of wasted space is small as long as there are few duplicates.
}
if (def != nullptr && (idef < 0 || def != supportedLocales[idef])) {
ownedDefaultLocale = def->clone();
if (ownedDefaultLocale == nullptr) {
errorCode = U_MEMORY_ALLOCATION_ERROR;
return;
}
def = ownedDefaultLocale;
}
defaultLocale = def;
defaultLocaleIndex = idef;
if (builder.demotion_ == ULOCMATCH_DEMOTION_REGION) {
demotionPerDesiredLocale = localeDistance.getDefaultDemotionPerDesiredLocale();
@ -503,8 +467,7 @@ LocaleMatcher::LocaleMatcher(LocaleMatcher &&src) U_NOEXCEPT :
supportedLSRs(src.supportedLSRs),
supportedIndexes(src.supportedIndexes),
supportedLSRsLength(src.supportedLSRsLength),
ownedDefaultLocale(src.ownedDefaultLocale), defaultLocale(src.defaultLocale),
defaultLocaleIndex(src.defaultLocaleIndex) {
ownedDefaultLocale(src.ownedDefaultLocale), defaultLocale(src.defaultLocale) {
src.supportedLocales = nullptr;
src.lsrs = nullptr;
src.supportedLocalesLength = 0;
@ -514,7 +477,6 @@ LocaleMatcher::LocaleMatcher(LocaleMatcher &&src) U_NOEXCEPT :
src.supportedLSRsLength = 0;
src.ownedDefaultLocale = nullptr;
src.defaultLocale = nullptr;
src.defaultLocaleIndex = -1;
}
LocaleMatcher::~LocaleMatcher() {
@ -544,7 +506,6 @@ LocaleMatcher &LocaleMatcher::operator=(LocaleMatcher &&src) U_NOEXCEPT {
supportedLSRsLength = src.supportedLSRsLength;
ownedDefaultLocale = src.ownedDefaultLocale;
defaultLocale = src.defaultLocale;
defaultLocaleIndex = src.defaultLocaleIndex;
src.supportedLocales = nullptr;
src.lsrs = nullptr;
@ -555,7 +516,6 @@ LocaleMatcher &LocaleMatcher::operator=(LocaleMatcher &&src) U_NOEXCEPT {
src.supportedLSRsLength = 0;
src.ownedDefaultLocale = nullptr;
src.defaultLocale = nullptr;
src.defaultLocaleIndex = -1;
return *this;
}
@ -642,13 +602,13 @@ const Locale *LocaleMatcher::getBestMatchForListString(
LocaleMatcher::Result LocaleMatcher::getBestMatchResult(
const Locale &desiredLocale, UErrorCode &errorCode) const {
if (U_FAILURE(errorCode)) {
return Result(nullptr, defaultLocale, -1, defaultLocaleIndex, FALSE);
return Result(nullptr, defaultLocale, -1, -1, FALSE);
}
int32_t suppIndex = getBestSuppIndex(
getMaximalLsrOrUnd(likelySubtags, desiredLocale, errorCode),
nullptr, errorCode);
if (U_FAILURE(errorCode) || suppIndex < 0) {
return Result(nullptr, defaultLocale, -1, defaultLocaleIndex, FALSE);
return Result(nullptr, defaultLocale, -1, -1, FALSE);
} else {
return Result(&desiredLocale, supportedLocales[suppIndex], 0, suppIndex, FALSE);
}
@ -657,12 +617,12 @@ LocaleMatcher::Result LocaleMatcher::getBestMatchResult(
LocaleMatcher::Result LocaleMatcher::getBestMatchResult(
Locale::Iterator &desiredLocales, UErrorCode &errorCode) const {
if (U_FAILURE(errorCode) || !desiredLocales.hasNext()) {
return Result(nullptr, defaultLocale, -1, defaultLocaleIndex, FALSE);
return Result(nullptr, defaultLocale, -1, -1, FALSE);
}
LocaleLsrIterator lsrIter(likelySubtags, desiredLocales, ULOCMATCH_TEMPORARY_LOCALES);
int32_t suppIndex = getBestSuppIndex(lsrIter.next(errorCode), &lsrIter, errorCode);
if (U_FAILURE(errorCode) || suppIndex < 0) {
return Result(nullptr, defaultLocale, -1, defaultLocaleIndex, FALSE);
return Result(nullptr, defaultLocale, -1, -1, FALSE);
} else {
return Result(lsrIter.orphanRemembered(), supportedLocales[suppIndex],
lsrIter.getBestDesiredIndex(), suppIndex, TRUE);
@ -696,8 +656,7 @@ int32_t LocaleMatcher::getBestSuppIndex(LSR desiredLSR, LocaleLsrIterator *remai
remainingIter->rememberCurrent(desiredIndex, errorCode);
if (U_FAILURE(errorCode)) { return -1; }
}
bestSupportedLsrIndex = bestIndexAndDistance >= 0 ?
LocaleDistance::getIndex(bestIndexAndDistance) : -1;
bestSupportedLsrIndex = LocaleDistance::getIndex(bestIndexAndDistance);
}
if ((bestShiftedDistance -= LocaleDistance::shiftDistance(demotionPerDesiredLocale)) <= 0) {
break;
@ -731,4 +690,97 @@ double LocaleMatcher::internalMatch(const Locale &desired, const Locale &support
U_NAMESPACE_END
// uloc_acceptLanguage() --------------------------------------------------- ***
U_NAMESPACE_USE
namespace {
class LocaleFromTag {
public:
LocaleFromTag() : locale(Locale::getRoot()) {}
const Locale &operator()(const char *tag) { return locale = Locale(tag); }
private:
// Store the locale in the converter, rather than return a reference to a temporary,
// or a value which could go out of scope with the caller's reference to it.
Locale locale;
};
int32_t acceptLanguage(UEnumeration &supportedLocales, Locale::Iterator &desiredLocales,
char *dest, int32_t capacity, UAcceptResult *acceptResult,
UErrorCode &errorCode) {
if (U_FAILURE(errorCode)) { return 0; }
LocaleMatcher::Builder builder;
const char *locString;
while ((locString = uenum_next(&supportedLocales, nullptr, &errorCode)) != nullptr) {
Locale loc(locString);
if (loc.isBogus()) {
errorCode = U_ILLEGAL_ARGUMENT_ERROR;
return 0;
}
builder.addSupportedLocale(loc);
}
LocaleMatcher matcher = builder.build(errorCode);
LocaleMatcher::Result result = matcher.getBestMatchResult(desiredLocales, errorCode);
if (U_FAILURE(errorCode)) { return 0; }
if (result.getDesiredIndex() >= 0) {
if (acceptResult != nullptr) {
*acceptResult = *result.getDesiredLocale() == *result.getSupportedLocale() ?
ULOC_ACCEPT_VALID : ULOC_ACCEPT_FALLBACK;
}
const char *bestStr = result.getSupportedLocale()->getName();
int32_t bestLength = (int32_t)uprv_strlen(bestStr);
if (bestLength <= capacity) {
uprv_memcpy(dest, bestStr, bestLength);
}
return u_terminateChars(dest, capacity, bestLength, &errorCode);
} else {
if (acceptResult != nullptr) {
*acceptResult = ULOC_ACCEPT_FAILED;
}
return u_terminateChars(dest, capacity, 0, &errorCode);
}
}
} // namespace
U_CAPI int32_t U_EXPORT2
uloc_acceptLanguage(char *result, int32_t resultAvailable,
UAcceptResult *outResult,
const char **acceptList, int32_t acceptListCount,
UEnumeration *availableLocales,
UErrorCode *status) {
if (U_FAILURE(*status)) { return 0; }
if ((result == nullptr ? resultAvailable != 0 : resultAvailable < 0) ||
(acceptList == nullptr ? acceptListCount != 0 : acceptListCount < 0) ||
availableLocales == nullptr) {
*status = U_ILLEGAL_ARGUMENT_ERROR;
return 0;
}
LocaleFromTag converter;
Locale::ConvertingIterator<const char **, LocaleFromTag> desiredLocales(
acceptList, acceptList + acceptListCount, converter);
return acceptLanguage(*availableLocales, desiredLocales,
result, resultAvailable, outResult, *status);
}
U_CAPI int32_t U_EXPORT2
uloc_acceptLanguageFromHTTP(char *result, int32_t resultAvailable,
UAcceptResult *outResult,
const char *httpAcceptLanguage,
UEnumeration *availableLocales,
UErrorCode *status) {
if (U_FAILURE(*status)) { return 0; }
if ((result == nullptr ? resultAvailable != 0 : resultAvailable < 0) ||
httpAcceptLanguage == nullptr || availableLocales == nullptr) {
*status = U_ILLEGAL_ARGUMENT_ERROR;
return 0;
}
LocalePriorityList list(httpAcceptLanguage, *status);
LocalePriorityList::Iterator desiredLocales = list.iterator();
return acceptLanguage(*availableLocales, desiredLocales,
result, resultAvailable, outResult, *status);
}
#endif // __LOCMATCHER_H__

2
icu4c/source/common/localeprioritylist.cpp
View file

@ -133,7 +133,7 @@ LocalePriorityList::LocalePriorityList(StringPiece s, UErrorCode &errorCode) {
if (U_FAILURE(errorCode)) { return; }
Locale locale = Locale(tag.data());
if (locale.isBogus()) {
errorCode = U_MEMORY_ALLOCATION_ERROR;
errorCode = U_ILLEGAL_ARGUMENT_ERROR;
return;
}
int32_t weight = WEIGHT_ONE;

2
icu4c/source/common/rbbi.cpp
View file

@ -1117,7 +1117,7 @@ static icu::UInitOnce gRBBIInitOnce = U_INITONCE_INITIALIZER;
* Release all static memory held by breakiterator.
*/
U_CDECL_BEGIN
static UBool U_CALLCONV rbbi_cleanup(void) {
UBool U_CALLCONV rbbi_cleanup(void) {
delete gLanguageBreakFactories;
gLanguageBreakFactories = nullptr;
delete gEmptyString;

2
icu4c/source/common/rbbidata.h
View file

@ -192,6 +192,8 @@ private:
U_NAMESPACE_END
U_CFUNC UBool rbbi_cleanup(void);
#endif /* C++ */
#endif

2
icu4c/source/common/ubidi_props_data.h
View file

@ -323,7 +323,7 @@ static const uint16_t ubidi_props_trieIndex[12536]={
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1,1,0xb1,0xb1,0xb1,0xb1,1,0xb1,0xb1,0xb1,0xb1,0xb1,0x81,0x41,0x41,0x41,
0x41,0x41,0x81,0x81,0x41,0x81,0x41,0x41,0x41,0x41,0x41,0x41,0x41,0x41,0x41,0x41,
0x81,0x41,1,1,1,0xb1,0xb1,0xb1,1,1,1,1,0x4d,0xd,0x4d,0x4d,
0x81,0x41,0x81,0x81,0x81,0xb1,0xb1,0xb1,1,1,1,1,0x4d,0xd,0x4d,0x4d,
0x4d,0x4d,0xd,0x8d,0x4d,0x8d,0x8d,0xd,0xd,0xd,0xd,0xd,1,1,1,1,
1,1,1,1,1,1,1,1,1,1,1,1,0xb1,0xb1,5,0xb1,
0xb1,0xb1,0xb1,0xb1,0xb1,0xb1,0xb1,0xb1,0xb1,0xb1,0xb1,0xb1,0xb1,0xb1,0xb1,0xb1,

2
icu4c/source/common/ucase_props_data.h
View file

@ -304,7 +304,7 @@ static const uint16_t ucase_props_trieIndex[12356]={
0x92,0xff91,0x92,0xff91,0x92,0xff91,0x92,0xff91,0x92,0xff91,0x92,0xff91,0x92,0xff91,0x92,0xff91,
0x92,0xff91,0x92,0xff91,0,0x1812,0x1812,0x1812,0x1812,0x1812,0x1812,0x1812,0x1812,0x1812,0x1812,0x1812,
0x1812,0x1812,0x1812,0x1812,0x1812,0x1812,0x1812,0x1812,0x1812,0x1812,0x1812,0x1812,0x1812,0x1812,0x1812,0,
0,4,0,0,0,0,0,0,1,0xe811,0xe811,0xe811,0xe811,0xe811,0xe811,0xe811,
0,4,0,0,0,0,0,4,1,0xe811,0xe811,0xe811,0xe811,0xe811,0xe811,0xe811,
0xe811,0xe811,0xe811,0xe811,0xe811,0xe811,0xe811,0xe811,0xe811,0xe811,0xe811,0xe811,0xe811,0xe811,0xe811,0xe811,
0xe811,0xe811,0xe811,0xe811,0xe811,0xe811,0xe811,0xe811,0xe811,0xe811,0xe811,0x1719,1,0,0,0,
0,0,0,0,0,0x64,0x44,0x44,0x44,0x44,0x64,0x44,0x44,0x44,0x64,0x64,

6
icu4c/source/common/ucasemap.cpp
View file

@ -687,13 +687,13 @@ void toUpper(uint32_t options,
if (change) {
ByteSinkUtil::appendTwoBytes(upper, sink);
if ((data & HAS_EITHER_DIALYTIKA) != 0) {
sink.Append(u8"\u0308", 2); // restore or add a dialytika
sink.Append(reinterpret_cast<const char*>(u8"\u0308"), 2); // restore or add a dialytika
}
if (addTonos) {
sink.Append(u8"\u0301", 2);
sink.Append(reinterpret_cast<const char*>(u8"\u0301"), 2);
}
while (numYpogegrammeni > 0) {
sink.Append(u8"\u0399", 2);
sink.Append(reinterpret_cast<const char*>(u8"\u0399"), 2);
--numYpogegrammeni;
}
}

1676
icu4c/source/common/uchar_props_data.h
View file

File diff suppressed because it is too large Load diff

4
icu4c/source/common/ucurr.cpp
View file

@ -866,7 +866,7 @@ getCurrencyNameCount(const char* loc, int32_t* total_currency_name_count, int32_
*total_currency_name_count = 0;
*total_currency_symbol_count = 0;
const UChar* s = NULL;
char locale[ULOC_FULLNAME_CAPACITY];
char locale[ULOC_FULLNAME_CAPACITY] = "";
uprv_strcpy(locale, loc);
const icu::Hashtable *currencySymbolsEquiv = getCurrSymbolsEquiv();
for (;;) {
@ -941,7 +941,7 @@ collectCurrencyNames(const char* locale,
// Look up the Currencies resource for the given locale.
UErrorCode ec2 = U_ZERO_ERROR;
char loc[ULOC_FULLNAME_CAPACITY];
char loc[ULOC_FULLNAME_CAPACITY] = "";
uloc_getName(locale, loc, sizeof(loc), &ec2);
if (U_FAILURE(ec2) || ec2 == U_STRING_NOT_TERMINATED_WARNING) {
ec = U_ILLEGAL_ARGUMENT_ERROR;

299
icu4c/source/common/uloc.cpp
View file

@ -157,7 +157,7 @@ static const char * const LANGUAGES[] = {
"nnh", "no", "nog", "non", "nov", "nqo", "nr", "nso",
"nus", "nv", "nwc", "ny", "nym", "nyn", "nyo", "nzi",
"oc", "oj", "om", "or", "os", "osa", "ota",
"pa", "pag", "pal", "pam", "pap", "pau", "pcd", "pdc",
"pa", "pag", "pal", "pam", "pap", "pau", "pcd", "pcm", "pdc",
"pdt", "peo", "pfl", "phn", "pi", "pl", "pms", "pnt",
"pon", "prg", "pro", "ps", "pt",
"qu", "quc", "qug",
@ -274,7 +274,7 @@ static const char * const LANGUAGES_3[] = {
"nnh", "nor", "nog", "non", "nov", "nqo", "nbl", "nso",
"nus", "nav", "nwc", "nya", "nym", "nyn", "nyo", "nzi",
"oci", "oji", "orm", "ori", "oss", "osa", "ota",
"pan", "pag", "pal", "pam", "pap", "pau", "pcd", "pdc",
"pan", "pag", "pal", "pam", "pap", "pau", "pcd", "pcm", "pdc",
"pdt", "peo", "pfl", "phn", "pli", "pol", "pms", "pnt",
"pon", "prg", "pro", "pus", "por",
"que", "quc", "qug",
@ -2127,301 +2127,6 @@ uloc_getISOCountries()
return COUNTRIES;
}
/* this function to be moved into cstring.c later */
static char gDecimal = 0;
static /* U_CAPI */
double
/* U_EXPORT2 */
_uloc_strtod(const char *start, char **end) {
char *decimal;
char *myEnd;
char buf[30];
double rv;
if (!gDecimal) {
char rep[5];
/* For machines that decide to change the decimal on you,
and try to be too smart with localization.
This normally should be just a '.'. */
sprintf(rep, "%+1.1f", 1.0);
gDecimal = rep[2];
}
if(gDecimal == '.') {
return uprv_strtod(start, end); /* fall through to OS */
} else {
uprv_strncpy(buf, start, 29);
buf[29]=0;
decimal = uprv_strchr(buf, '.');
if(decimal) {
*decimal = gDecimal;
} else {
return uprv_strtod(start, end); /* no decimal point */
}
rv = uprv_strtod(buf, &myEnd);
if(end) {
*end = (char*)(start+(myEnd-buf)); /* cast away const (to follow uprv_strtod API.) */
}
return rv;
}
}
typedef struct {
float q;
int32_t dummy; /* to avoid uninitialized memory copy from qsort */
char locale[ULOC_FULLNAME_CAPACITY+1];
} _acceptLangItem;
static int32_t U_CALLCONV
uloc_acceptLanguageCompare(const void * /*context*/, const void *a, const void *b)
{
const _acceptLangItem *aa = (const _acceptLangItem*)a;
const _acceptLangItem *bb = (const _acceptLangItem*)b;
int32_t rc = 0;
if(bb->q < aa->q) {
rc = -1; /* A > B */
} else if(bb->q > aa->q) {
rc = 1; /* A < B */
} else {
rc = 0; /* A = B */
}
if(rc==0) {
rc = uprv_stricmp(aa->locale, bb->locale);
}
#if defined(ULOC_DEBUG)
/* fprintf(stderr, "a:[%s:%g], b:[%s:%g] -> %d\n",
aa->locale, aa->q,
bb->locale, bb->q,
rc);*/
#endif
return rc;
}
/*
mt-mt, ja;q=0.76, en-us;q=0.95, en;q=0.92, en-gb;q=0.89, fr;q=0.87, iu-ca;q=0.84, iu;q=0.82, ja-jp;q=0.79, mt;q=0.97, de-de;q=0.74, de;q=0.71, es;q=0.68, it-it;q=0.66, it;q=0.63, vi-vn;q=0.61, vi;q=0.58, nl-nl;q=0.55, nl;q=0.53
*/
U_CAPI int32_t U_EXPORT2
uloc_acceptLanguageFromHTTP(char *result, int32_t resultAvailable, UAcceptResult *outResult,
const char *httpAcceptLanguage,
UEnumeration* availableLocales,
UErrorCode *status)
{
MaybeStackArray<_acceptLangItem, 4> items; // Struct for collecting items.
char tmp[ULOC_FULLNAME_CAPACITY +1];
int32_t n = 0;
const char *itemEnd;
const char *paramEnd;
const char *s;
const char *t;
int32_t res;
int32_t i;
int32_t l = (int32_t)uprv_strlen(httpAcceptLanguage);
if(U_FAILURE(*status)) {
return -1;
}
for(s=httpAcceptLanguage;s&&*s;) {
while(isspace(*s)) /* eat space at the beginning */
s++;
itemEnd=uprv_strchr(s,',');
paramEnd=uprv_strchr(s,';');
if(!itemEnd) {
itemEnd = httpAcceptLanguage+l; /* end of string */
}
if(paramEnd && paramEnd<itemEnd) {
/* semicolon (;) is closer than end (,) */
t = paramEnd+1;
if(*t=='q') {
t++;
}
while(isspace(*t)) {
t++;
}
if(*t=='=') {
t++;
}
while(isspace(*t)) {
t++;
}
items[n].q = (float)_uloc_strtod(t,NULL);
} else {
/* no semicolon - it's 1.0 */
items[n].q = 1.0f;
paramEnd = itemEnd;
}
items[n].dummy=0;
/* eat spaces prior to semi */
for(t=(paramEnd-1);(paramEnd>s)&&isspace(*t);t--)
;
int32_t slen = static_cast<int32_t>(((t+1)-s));
if(slen > ULOC_FULLNAME_CAPACITY) {
*status = U_BUFFER_OVERFLOW_ERROR;
return -1; // too big
}
uprv_strncpy(items[n].locale, s, slen);
items[n].locale[slen]=0; // terminate
int32_t clen = uloc_canonicalize(items[n].locale, tmp, UPRV_LENGTHOF(tmp)-1, status);
if(U_FAILURE(*status)) return -1;
if((clen!=slen) || (uprv_strncmp(items[n].locale, tmp, slen))) {
// canonicalization had an effect- copy back
uprv_strncpy(items[n].locale, tmp, clen);
items[n].locale[clen] = 0; // terminate
}
#if defined(ULOC_DEBUG)
/*fprintf(stderr,"%d: s <%s> q <%g>\n", n, j[n].locale, j[n].q);*/
#endif
n++;
s = itemEnd;
while(*s==',') { /* eat duplicate commas */
s++;
}
if(n>=items.getCapacity()) { // If we need more items
if(NULL == items.resize(items.getCapacity()*2, items.getCapacity())) {
*status = U_MEMORY_ALLOCATION_ERROR;
return -1;
}
#if defined(ULOC_DEBUG)
fprintf(stderr,"malloced at size %d\n", items.getCapacity());
#endif
}
}
uprv_sortArray(items.getAlias(), n, sizeof(items[0]), uloc_acceptLanguageCompare, NULL, TRUE, status);
if (U_FAILURE(*status)) {
return -1;
}
LocalMemory<const char*> strs(NULL);
if (strs.allocateInsteadAndReset(n) == NULL) {
*status = U_MEMORY_ALLOCATION_ERROR;
return -1;
}
for(i=0;i<n;i++) {
#if defined(ULOC_DEBUG)
/*fprintf(stderr,"%d: s <%s> q <%g>\n", i, j[i].locale, j[i].q);*/
#endif
strs[i]=items[i].locale;
}
res = uloc_acceptLanguage(result, resultAvailable, outResult,
strs.getAlias(), n, availableLocales, status);
return res;
}
U_CAPI int32_t U_EXPORT2
uloc_acceptLanguage(char *result, int32_t resultAvailable,
UAcceptResult *outResult, const char **acceptList,
int32_t acceptListCount,
UEnumeration* availableLocales,
UErrorCode *status)
{
int32_t i,j;
int32_t len;
int32_t maxLen=0;
char tmp[ULOC_FULLNAME_CAPACITY+1];
const char *l;
char **fallbackList;
if(U_FAILURE(*status)) {
return -1;
}
fallbackList = static_cast<char **>(uprv_malloc((size_t)(sizeof(fallbackList[0])*acceptListCount)));
if(fallbackList==NULL) {
*status = U_MEMORY_ALLOCATION_ERROR;
return -1;
}
for(i=0;i<acceptListCount;i++) {
#if defined(ULOC_DEBUG)
fprintf(stderr,"%02d: %s\n", i, acceptList[i]);
#endif
while((l=uenum_next(availableLocales, NULL, status)) != NULL) {
#if defined(ULOC_DEBUG)
fprintf(stderr," %s\n", l);
#endif
len = (int32_t)uprv_strlen(l);
if(!uprv_strcmp(acceptList[i], l)) {
if(outResult) {
*outResult = ULOC_ACCEPT_VALID;
}
#if defined(ULOC_DEBUG)
fprintf(stderr, "MATCH! %s\n", l);
#endif
if(len>0) {
uprv_strncpy(result, l, uprv_min(len, resultAvailable));
}
for(j=0;j<i;j++) {
uprv_free(fallbackList[j]);
}
uprv_free(fallbackList);
return u_terminateChars(result, resultAvailable, len, status);
}
if(len>maxLen) {
maxLen = len;
}
}
uenum_reset(availableLocales, status);
/* save off parent info */
if(uloc_getParent(acceptList[i], tmp, UPRV_LENGTHOF(tmp), status)!=0) {
fallbackList[i] = uprv_strdup(tmp);
} else {
fallbackList[i]=0;
}
}
for(maxLen--;maxLen>0;maxLen--) {
for(i=0;i<acceptListCount;i++) {
if(fallbackList[i] && ((int32_t)uprv_strlen(fallbackList[i])==maxLen)) {
#if defined(ULOC_DEBUG)
fprintf(stderr,"Try: [%s]", fallbackList[i]);
#endif
while((l=uenum_next(availableLocales, NULL, status)) != NULL) {
#if defined(ULOC_DEBUG)
fprintf(stderr," %s\n", l);
#endif
len = (int32_t)uprv_strlen(l);
if(!uprv_strcmp(fallbackList[i], l)) {
if(outResult) {
*outResult = ULOC_ACCEPT_FALLBACK;
}
#if defined(ULOC_DEBUG)
fprintf(stderr, "fallback MATCH! %s\n", l);
#endif
if(len>0) {
uprv_strncpy(result, l, uprv_min(len, resultAvailable));
}
for(j=0;j<acceptListCount;j++) {
uprv_free(fallbackList[j]);
}
uprv_free(fallbackList);
return u_terminateChars(result, resultAvailable, len, status);
}
}
uenum_reset(availableLocales, status);
if(uloc_getParent(fallbackList[i], tmp, UPRV_LENGTHOF(tmp), status)!=0) {
uprv_free(fallbackList[i]);
fallbackList[i] = uprv_strdup(tmp);
} else {
uprv_free(fallbackList[i]);
fallbackList[i]=0;
}
}
}
if(outResult) {
*outResult = ULOC_ACCEPT_FAILED;
}
}
for(i=0;i<acceptListCount;i++) {
uprv_free(fallbackList[i]);
}
uprv_free(fallbackList);
return -1;
}
U_CAPI const char* U_EXPORT2
uloc_toUnicodeLocaleKey(const char* keyword)
{

0
icu4c/source/common/umutex.h Executable file → Normal file
View file

3
icu4c/source/common/unames.cpp
View file

@ -1519,7 +1519,8 @@ U_CAPI UChar32 U_EXPORT2
u_charFromName(UCharNameChoice nameChoice,
const char *name,
UErrorCode *pErrorCode) {
char upper[120], lower[120];
char upper[120] = {0};
char lower[120] = {0};
FindName findName;
AlgorithmicRange *algRange;
uint32_t *p;

3
icu4c/source/common/unicode/localematcher.h
View file

@ -574,6 +574,8 @@ private:
LocaleMatcher(const LocaleMatcher &other) = delete;
LocaleMatcher &operator=(const LocaleMatcher &other) = delete;
int32_t putIfAbsent(const LSR &lsr, int32_t i, int32_t suppLength, UErrorCode &errorCode);
int32_t getBestSuppIndex(LSR desiredLSR, LocaleLsrIterator *remainingIter, UErrorCode &errorCode) const;
const XLikelySubtags &likelySubtags;
@ -595,7 +597,6 @@ private:
int32_t supportedLSRsLength;
Locale *ownedDefaultLocale;
const Locale *defaultLocale;
int32_t defaultLocaleIndex;
};
U_NAMESPACE_END

65
icu4c/source/common/unicode/utrace.h
View file

@ -177,6 +177,71 @@ typedef enum UTraceFunctionNumber {
UTRACE_RES_DATA_LIMIT,
#endif // U_HIDE_INTERNAL_API
#ifndef U_HIDE_DRAFT_API
/**
* The lowest break iterator location.
* @draft ICU 67
*/
UTRACE_UBRK_START=0x4000,
/**
* Indicates that a character instance of break iterator was created.
*
* @draft ICU 67
*/
UTRACE_UBRK_CREATE_CHARACTER = UTRACE_UBRK_START,
/**
* Indicates that a word instance of break iterator was created.
*
* @draft ICU 67
*/
UTRACE_UBRK_CREATE_WORD,
/**
* Indicates that a line instance of break iterator was created.
*
* Provides one C-style string to UTraceData: the lb value ("",
* "loose", "strict", or "normal").
*
* @draft ICU 67
*/
UTRACE_UBRK_CREATE_LINE,
/**
* Indicates that a sentence instance of break iterator was created.
*
* @draft ICU 67
*/
UTRACE_UBRK_CREATE_SENTENCE,
/**
* Indicates that a title instance of break iterator was created.
*
* @draft ICU 67
*/
UTRACE_UBRK_CREATE_TITLE,
/**
* Indicates that an internal dictionary break engine was created.
*
* Provides one C-style string to UTraceData: the script code of what
* the break engine cover ("Hani", "Khmr", "Laoo", "Mymr", or "Thai").
*
* @draft ICU 67
*/
UTRACE_UBRK_CREATE_BREAK_ENGINE,
#endif // U_HIDE_DRAFT_API
#ifndef U_HIDE_INTERNAL_API
/**
* One more than the highest normal break iterator trace location.
* @internal The numeric value may change over time, see ICU ticket #12420.
*/
UTRACE_UBRK_LIMIT,
#endif // U_HIDE_INTERNAL_API
} UTraceFunctionNumber;
/**

8
icu4c/source/common/unicode/uvernum.h
View file

@ -66,13 +66,13 @@
* This value will change in the subsequent releases of ICU
* @stable ICU 2.6
*/
#define U_ICU_VERSION_MINOR_NUM 0
#define U_ICU_VERSION_MINOR_NUM 1
/** The current ICU patchlevel version as an integer.
* This value will change in the subsequent releases of ICU
* @stable ICU 2.4
*/
#define U_ICU_VERSION_PATCHLEVEL_NUM 1
#define U_ICU_VERSION_PATCHLEVEL_NUM 0
/** The current ICU build level version as an integer.
* This value is for use by ICU clients. It defaults to 0.
@ -139,7 +139,7 @@
* This value will change in the subsequent releases of ICU
* @stable ICU 2.4
*/
#define U_ICU_VERSION "66.0.1"
#define U_ICU_VERSION "66.1"
/**
* The current ICU library major version number as a string, for library name suffixes.
@ -158,7 +158,7 @@
/** Data version in ICU4C.
* @internal ICU 4.4 Internal Use Only
**/
#define U_ICU_DATA_VERSION "66.0.1"
#define U_ICU_DATA_VERSION "66.1"
#endif /* U_HIDE_INTERNAL_API */
/*===========================================================================

4
icu4c/source/common/uresbund.cpp
View file

@ -2611,8 +2611,8 @@ ures_getFunctionalEquivalent(char *result, int32_t resultCapacity,
char defVal[1024] = ""; /* default value for given locale */
char defLoc[1024] = ""; /* default value for given locale */
char base[1024] = ""; /* base locale */
char found[1024];
char parent[1024];
char found[1024] = "";
char parent[1024] = "";
char full[1024] = "";
UResourceBundle bund1, bund2;
UResourceBundle *res = NULL;

4
icu4c/source/common/uscript.cpp
View file

@ -58,8 +58,8 @@ static int32_t
getCodesFromLocale(const char *locale,
UScriptCode *scripts, int32_t capacity, UErrorCode *err) {
UErrorCode internalErrorCode = U_ZERO_ERROR;
char lang[8];
char script[8];
char lang[8] = {0};
char script[8] = {0};
int32_t scriptLength;
if(U_FAILURE(*err)) { return 0; }
// Multi-script languages, equivalent to the LocaleScript data

5
icu4c/source/config/mh-mingw
View file

@ -102,7 +102,10 @@ LIBICU = $(STATIC_PREFIX_WHEN_USED)$(ICUPREFIX)
#SH#ICULIBS_COMMON_LIB_NAME_A="${LIBICU}${COMMON_STUBNAME}${ICULIBSUFFIX}.${A}"
#SH#ICULIBS_DATA="-l$(ICUPREFIX)$(DATA_STUBNAME)$(ICULIBSUFFIX)$(ICULIBSUFFIX_VERSION)"
#SH#ICULIBS_I18N="-l$(ICUPREFIX)$(I18N_STUBNAME)$(ICULIBSUFFIX)$(ICULIBSUFFIX_VERSION)"
ICULIBS_DT="-l$(ICUPREFIX)$(DATA_STUBNAME)$(ICULIBSUFFIX)$(ICULIBSUFFIX_VERSION)"
ICULIBS_I18N="-l$(ICUPREFIX)$(I18N_STUBNAME)$(ICULIBSUFFIX)$(ICULIBSUFFIX_VERSION)"
ICULIBS_IO="-l$(ICUPREFIX)$(IO_STUBNAME)$(ICULIBSUFFIX)$(ICULIBSUFFIX_VERSION)"
ICULIBS_UC="-l$(ICUPREFIX)$(COMMON_STUBNAME)$(ICULIBSUFFIX)$(ICULIBSUFFIX_VERSION)"
#SH#
#SH## ICULIBS is the set of libraries your application should link
#SH## with usually. Many applications will want to add ${ICULIBS_I18N} as well.

5
icu4c/source/config/mh-mingw64
View file

@ -102,7 +102,10 @@ LIBICU = $(STATIC_PREFIX_WHEN_USED)$(ICUPREFIX)
#SH#ICULIBS_COMMON_LIB_NAME_A="${LIBICU}${COMMON_STUBNAME}${ICULIBSUFFIX}.${A}"
#SH#ICULIBS_DATA="-l$(ICUPREFIX)$(DATA_STUBNAME)$(ICULIBSUFFIX)$(ICULIBSUFFIX_VERSION)"
#SH#ICULIBS_I18N="-l$(ICUPREFIX)$(I18N_STUBNAME)$(ICULIBSUFFIX)$(ICULIBSUFFIX_VERSION)"
ICULIBS_DT="-l$(ICUPREFIX)$(DATA_STUBNAME)$(ICULIBSUFFIX)$(ICULIBSUFFIX_VERSION)"
ICULIBS_I18N="-l$(ICUPREFIX)$(I18N_STUBNAME)$(ICULIBSUFFIX)$(ICULIBSUFFIX_VERSION)"
ICULIBS_IO="-l$(ICUPREFIX)$(IO_STUBNAME)$(ICULIBSUFFIX)$(ICULIBSUFFIX_VERSION)"
ICULIBS_UC="-l$(ICUPREFIX)$(COMMON_STUBNAME)$(ICULIBSUFFIX)$(ICULIBSUFFIX_VERSION)"
#SH#
#SH## ICULIBS is the set of libraries your application should link
#SH## with usually. Many applications will want to add ${ICULIBS_I18N} as well.

18
icu4c/source/configure vendored
View file

@ -1,6 +1,6 @@
#! /bin/sh
# Guess values for system-dependent variables and create Makefiles.
# Generated by GNU Autoconf 2.69 for ICU 66.0.1.
# Generated by GNU Autoconf 2.69 for ICU 66.1.
#
# Report bugs to <http://icu-project.org/bugs>.
#
@ -582,8 +582,8 @@ MAKEFLAGS=
# Identity of this package.
PACKAGE_NAME='ICU'
PACKAGE_TARNAME='International Components for Unicode'
PACKAGE_VERSION='66.0.1'
PACKAGE_STRING='ICU 66.0.1'
PACKAGE_VERSION='66.1'
PACKAGE_STRING='ICU 66.1'
PACKAGE_BUGREPORT='http://icu-project.org/bugs'
PACKAGE_URL='http://icu-project.org'
@ -1362,7 +1362,7 @@ if test "$ac_init_help" = "long"; then
# Omit some internal or obsolete options to make the list less imposing.
# This message is too long to be a string in the A/UX 3.1 sh.
cat <<_ACEOF
\`configure' configures ICU 66.0.1 to adapt to many kinds of systems.
\`configure' configures ICU 66.1 to adapt to many kinds of systems.
Usage: $0 [OPTION]... [VAR=VALUE]...
@ -1428,7 +1428,7 @@ fi
if test -n "$ac_init_help"; then
case $ac_init_help in
short | recursive ) echo "Configuration of ICU 66.0.1:";;
short | recursive ) echo "Configuration of ICU 66.1:";;
esac
cat <<\_ACEOF
@ -1566,7 +1566,7 @@ fi
test -n "$ac_init_help" && exit $ac_status
if $ac_init_version; then
cat <<\_ACEOF
ICU configure 66.0.1
ICU configure 66.1
generated by GNU Autoconf 2.69
Copyright (C) 2012 Free Software Foundation, Inc.
@ -2312,7 +2312,7 @@ cat >config.log <<_ACEOF
This file contains any messages produced by compilers while
running configure, to aid debugging if configure makes a mistake.
It was created by ICU $as_me 66.0.1, which was
It was created by ICU $as_me 66.1, which was
generated by GNU Autoconf 2.69. Invocation command line was
$ $0 $@
@ -8532,7 +8532,7 @@ cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1
# report actual input values of CONFIG_FILES etc. instead of their
# values after options handling.
ac_log="
This file was extended by ICU $as_me 66.0.1, which was
This file was extended by ICU $as_me 66.1, which was
generated by GNU Autoconf 2.69. Invocation command line was
CONFIG_FILES = $CONFIG_FILES
@ -8586,7 +8586,7 @@ _ACEOF
cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
ac_cs_config="`$as_echo "$ac_configure_args" | sed 's/^ //; s/[\\""\`\$]/\\\\&/g'`"
ac_cs_version="\\
ICU config.status 66.0.1
ICU config.status 66.1
configured by $0, generated by GNU Autoconf 2.69,
with options \\"\$ac_cs_config\\"

3
icu4c/source/data/Makefile.in
View file

@ -148,7 +148,8 @@ ICUDATA_ARCHIVE = $(firstword $(wildcard $(srcdir)/in/$(ICUDATA_BASENAME_VERSION
# and convert it to the current type.
ifneq ($(ICUDATA_ARCHIVE),)
ICUDATA_SOURCE_ARCHIVE = $(OUTDIR)/$(ICUDATA_PLATFORM_NAME).dat
$(ICUDATA_SOURCE_ARCHIVE): $(ICUDATA_ARCHIVE) $(OUTDIR)
$(ICUDATA_SOURCE_ARCHIVE): $(ICUDATA_ARCHIVE)
$(MKINSTALLDIRS) $(OUTDIR)
$(INVOKE) $(TOOLBINDIR)/icupkg -t$(ICUDATA_CHAR) $(ICUDATA_ARCHIVE) $(ICUDATA_SOURCE_ARCHIVE)
$(OUTDIR):

2
icu4c/source/data/brkitr/LOCALE_DEPS.json
View file

@ -2,5 +2,5 @@
// License & terms of use: http://www.unicode.org/copyright.html#License
{
"cldrVersion": "36.1"
"cldrVersion": "37"
}

2
icu4c/source/data/brkitr/de.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
de{
Version{"36.1"}
Version{"37"}
exceptions{
SentenceBreak:array{
"Port.",

2
icu4c/source/data/brkitr/el.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
el{
Version{"36.1"}
Version{"37"}
boundaries{
sentence:process(dependency){"sent_el.brk"}
}

2
icu4c/source/data/brkitr/en.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
en{
Version{"36.1"}
Version{"37"}
exceptions{
SentenceBreak:array{
"L.P.",

2
icu4c/source/data/brkitr/en_US.txt
View file

@ -1,5 +1,5 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
en_US{
Version{"36.1"}
Version{"37"}
}

2
icu4c/source/data/brkitr/en_US_POSIX.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
en_US_POSIX{
Version{"36.1"}
Version{"37"}
boundaries{
word:process(dependency){"word_POSIX.brk"}
}

2
icu4c/source/data/brkitr/es.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
es{
Version{"36.1"}
Version{"37"}
exceptions{
SentenceBreak:array{
"Rdos.",

2
icu4c/source/data/brkitr/fr.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
fr{
Version{"36.1"}
Version{"37"}
exceptions{
SentenceBreak:array{
"aux.",

2
icu4c/source/data/brkitr/it.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
it{
Version{"36.1"}
Version{"37"}
exceptions{
SentenceBreak:array{
"N.B.",

2
icu4c/source/data/brkitr/ja.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
ja{
Version{"36.1"}
Version{"37"}
boundaries{
line:process(dependency){"line_normal.brk"}
line_loose:process(dependency){"line_loose_cj.brk"}

2
icu4c/source/data/brkitr/pt.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
pt{
Version{"36.1"}
Version{"37"}
exceptions{
SentenceBreak:array{
"psicol.",

2
icu4c/source/data/brkitr/root.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
root{
Version{"36.1"}
Version{"37"}
boundaries{
grapheme:process(dependency){"char.brk"}
line:process(dependency){"line.brk"}

2
icu4c/source/data/brkitr/ru.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
ru{
Version{"36.1"}
Version{"37"}
exceptions{
SentenceBreak:array{
"\u0440\u0443\u0431.",

9
icu4c/source/data/brkitr/rules/word.txt
View file

@ -27,10 +27,12 @@
# Character Class Definitions.
#
$Han = [:Han:];
$CR = [\p{Word_Break = CR}];
$LF = [\p{Word_Break = LF}];
$Newline = [\p{Word_Break = Newline} ];
$Extend = [\p{Word_Break = Extend}];
$Newline = [\p{Word_Break = Newline}];
$Extend = [\p{Word_Break = Extend}-$Han];
$ZWJ = [\p{Word_Break = ZWJ}];
$Regional_Indicator = [\p{Word_Break = Regional_Indicator}];
$Format = [\p{Word_Break = Format}];
@ -42,12 +44,11 @@ $Double_Quote = [\p{Word_Break = Double_Quote}];
$MidNumLet = [\p{Word_Break = MidNumLet}];
$MidLetter = [\p{Word_Break = MidLetter}];
$MidNum = [\p{Word_Break = MidNum}];
$Numeric = [[\p{Word_Break = Numeric}] [\uFF10-\uff19]]; # Patch for ICU-12079
$Numeric = [\p{Word_Break = Numeric}];
$ExtendNumLet = [\p{Word_Break = ExtendNumLet}];
$WSegSpace = [\p{Word_Break = WSegSpace}];
$Extended_Pict = [\p{Extended_Pictographic}];
$Han = [:Han:];
$Hiragana = [:Hiragana:];
$Ideographic = [\p{Ideographic}];

9
icu4c/source/data/brkitr/rules/word_POSIX.txt
View file

@ -27,10 +27,12 @@
# Character Class Definitions.
#
$Han = [:Han:];
$CR = [\p{Word_Break = CR}];
$LF = [\p{Word_Break = LF}];
$Newline = [\p{Word_Break = Newline} ];
$Extend = [\p{Word_Break = Extend}];
$Newline = [\p{Word_Break = Newline}];
$Extend = [\p{Word_Break = Extend}-$Han];
$ZWJ = [\p{Word_Break = ZWJ}];
$Regional_Indicator = [\p{Word_Break = Regional_Indicator}];
$Format = [\p{Word_Break = Format}];
@ -42,12 +44,11 @@ $Double_Quote = [\p{Word_Break = Double_Quote}];
$MidNumLet = [\p{Word_Break = MidNumLet} - [.]];
$MidLetter = [\p{Word_Break = MidLetter} - [\:]];
$MidNum = [\p{Word_Break = MidNum} [.]];
$Numeric = [[\p{Word_Break = Numeric}] [\uFF10-\uff19]]; # Patch for ICU-12079
$Numeric = [\p{Word_Break = Numeric}];
$ExtendNumLet = [\p{Word_Break = ExtendNumLet}];
$WSegSpace = [\p{Word_Break = WSegSpace}];
$Extended_Pict = [\p{Extended_Pictographic}];
$Han = [:Han:];
$Hiragana = [:Hiragana:];
$Ideographic = [\p{Ideographic}];

2
icu4c/source/data/brkitr/zh.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
zh{
Version{"36.1"}
Version{"37"}
boundaries{
line:process(dependency){"line_cj.brk"}
line_loose:process(dependency){"line_loose_cj.brk"}

2
icu4c/source/data/brkitr/zh_Hant.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
zh_Hant{
Version{"36.1"}
Version{"37"}
boundaries{
line:process(dependency){"line_cj.brk"}
line_loose:process(dependency){"line_loose_cj.brk"}

2
icu4c/source/data/build.xml
View file

@ -414,7 +414,7 @@
<exclude name="zone/tzdbNames.txt" />
<include name="unit/*.txt" />
<include name="unit/resfiles.mk" />
</fileset>
</fileset>
<fileset id="collation" dir="${env.ICU4C_DIR}/source/data/coll">
<include name="*.txt" />
</fileset>

169
icu4c/source/data/cldr-icu-readme.txt
View file

@ -3,12 +3,17 @@
# Copyright (C) 2010-2014, International Business Machines Corporation and others.
# All Rights Reserved.
#
# Commands for regenerating ICU4C locale data (.txt files) from CLDR.
# Commands for regenerating ICU4C locale data (.txt files) from CLDR,
# updated to apply to CLDR 37 / ICU 67 and later versions.
#
# The process requires local copies of
# - CLDR (the source of most of the data, and some Java tools)
# - ICU4J (used only for checking the converted data)
# - ICU4C (the destination for the new data, and the source for some of it)
# - The complete ICU source tree, including:
# tools - includes the LdmlConverter build tool and associated config files
# icu4c - the target for converted CLDR data, and source for ICU4J data;
# includes tests for the converted data
# icu4j - the target for updated data jars; includes tests for the converted
# data
#
# For an official CLDR data integration into ICU, these should be clean, freshly
# checked-out. For released CLDR sources, an alternative to checking out sources
@ -17,10 +22,10 @@
# [http://cldr.unicode.org/index/downloads].
#
# The versions of each of these must match. Included with the release notes for
# ICU is the version number and/or a CLDR svn tag name for the revision of CLDR
# ICU is the version number and/or a CLDR git tag name for the revision of CLDR
# that was the source of the data for that release of ICU.
#
# Besides a standard JDK, the process also requires ant
# Besides a standard JDK, the process also requires ant and maven
# (http://ant.apache.org/),
# plus the xml-apis.jar from the Apache xalan package
# (http://xml.apache.org/xalan-j/downloads.html).
@ -50,17 +55,22 @@
#
# b) CLDR-related variables
#
# CLDR_DIR: Path to root of CLDR sources, below which are the common and
# tools directories.
# CLDR_DIR: For most of the process, this is the path to the to root of
# standard CLDR sources, below which are the common and
# tools directories. For running LdmlConverter, this needs to be
# temporarily reset to the parallel root for the production data,
# corresponding to $CLDR_TMP_DIR/production (see description of
# CLDR_TMP_DIR below).
# CLDR_CLASSES: Path to the CLDR Tools classes directory. If not set, defaults
# to $CLDR_DIR/tools/java/classes
#
# CLDR_TMP_DIR: Parent of temporary CLDR production data.
# Defaults to $CLDR_DIR/../cldr-aux (sibling to CLDR_DIR).
#
# *** NOTE ***: In CLDR release-36-beta, the GenerateProductionData
# tool no longer generates data into $CLDR_TMP_DIR/production; instead
# it generates data into $CLDR_DIR/../cldr-staging/production. However
# *** NOTE ***: In CLDR 36 and 37, the GenerateProductionData tool
# no longer generates data by default into $CLDR_TMP_DIR/production;
# instead it generates data into $CLDR_DIR/../cldr-staging/production
# (though there is a command-line option to override this). However
# the rest of the build still assumes that the generated data is in
# $CLDR_TMP_DIR/production. So CLDR_TMP_DIR must be defined to be
# $CLDR_DIR/../cldr-staging
@ -73,6 +83,9 @@
#
# ICU4J_ROOT: Path to root of ICU4J sources, below which is the main dir.
#
# TOOLS_ROOT: Path to root of ICU tools directory, below which is (e.g.) the
# cldr and unicodetools dirs.
#
#----
#
# If you are adding or removing locales, or specific kinds of locale data,
@ -80,7 +93,15 @@
# files are used in addition to the CLDR files as inputs to the CLDR data build
# process for ICU):
#
# icu4c/source/data/icu-config.xml - Update <locales> to add or remove
# The primary file to edit for ICU 67 and later is
#
# $TOOLS_ROOT/cldr/cldr-to-icu/build-icu-data.xml
#
# The files used in previous versions are the following. These are not used in
# the ICU-67-and-later process, but for now they should be kept up to date to
# enable parallel use of the older build process for verification.
#
# $ICU4C_DIR/source/data/icu-config.xml - Update <locales> to add or remove
# CLDR locales for inclusion in ICU. Update <paths> to prefer
# alt forms for certain paths, or to exclude certain paths; note
# that <paths> items can only have draft or alt attributes.
@ -91,7 +112,7 @@
# should also be included in <locales>, per PMC policy decision
# 2012-05-02 (see http://bugs.icu-project.org/trac/ticket/9298).
#
# icu4c/source/data/build.xml - If you are adding or removing break
# $ICU4C_DIR/source/data/build.xml - If you are adding or removing break
# iterators, you need to update <fileset id="brkitr" ...> under
# <target name="clean" ...> to clean the correct set of files.
#
@ -99,7 +120,7 @@
# updated the <remapper> sections to put these in the correct
# data subfolder for ICU.
#
# icu4c/source/data/xml/ - If you are adding a new locale, break
# $ICU4C_DIR/source/data/xml/ - If you are adding a new locale, break
# iterator, collation tailoring, or rule-based number formatter,
# you may need to add a corresponding xml file in (respectively)
# the main/, brkitr/, collation/, or rbnf/ subdirectory here.
@ -123,8 +144,8 @@
# keyboards/dtd/ldmlKeyboard.dtd - update cldrVersion
# tools/java/org/unicode/cldr/util/CLDRFile.java - update GEN_VERSION
#
# c) After everything is committed, you will need to tag the CLDR, ICU4J, and
# ICU4C sources that ended up being used for the integration; see step 17
# c) After everything is committed, you will need to tag the CLDR and ICU
# sources that ended up being used for the integration; see step 16
# below.
#
################################################################################
@ -143,56 +164,103 @@ export CLDR_DIR=$HOME/cldr-myfork
export ICU4C_DIR=$HOME/icu-myfork/icu4c
export ICU4J_ROOT=$HOME/icu-myfork/icu4j
export TOOLS_ROOT=$HOME/icu-myfork/tools
# 2. Build the CLDR Java tools and jar
cd $CLDR_DIR/tools/java
ant clean
ant all
ant jar
# 2a. Copy the CLDR jars into $TOOLS_ROOT/cldr/cldr-to-icu/lib/ maven repository;
# see $TOOLS_ROOT/cldr/cldr-to-icu/lib/README.txt
cd $TOOLS_ROOT/cldr/cldr-to-icu/lib/
mvn install:install-file \
-DgroupId=org.unicode.cldr \
-DartifactId=cldr-api \
-Dversion=0.1-SNAPSHOT \
-Dpackaging=jar \
-DgeneratePom=true \
-DlocalRepositoryPath=. \
-Dfile=$CLDR_DIR/tools/java/cldr.jar
cd $TOOLS_ROOT/cldr/cldr-to-icu/lib/
mvn install:install-file \
-DgroupId=com.ibm.icu \
-DartifactId=icu-utilities \
-Dversion=0.1-SNAPSHOT \
-Dpackaging=jar \
-DgeneratePom=true \
-DlocalRepositoryPath=. \
-Dfile=$CLDR_DIR/tools/java/libs/utilities.jar
cd $TOOLS_ROOT/cldr/cldr-to-icu/
mvn dependency:purge-local-repository -DsnapshotsOnly=true
# 3. Configure ICU4C, build and test without new data first, to verify that
# there are no pre-existing errors. Here <platform> is the runConfigureICU
# code for the platform you are building, e.g. Linux, MacOSX, Cygwin.
cd $ICU4C_DIR/source
./runConfigureICU <platform>
make all 2>&1 | tee /tmp/icu4c-oldData-makeAll.txt
make clean
make check 2>&1 | tee /tmp/icu4c-oldData-makeCheck.txt
# 4. Build the new ICU4C data files; these include .txt files and .py files.
# These new files will replace whatever was already present in the ICU4C sources.
# This process uses ant with ICU's data/build.xml and data/icu-config.xml to
# operate (via CLDR's ant/CLDRConverterTool.java and ant/CLDRBuild.java) the
# necessary CLDR tools including LDML2ICUConverter, ConvertTransforms, etc.
# This process will take several minutes.
# Keep a log so you can investigate anything that looks suspicious.
# 4a. Generate the CLDR production data. This process uses ant with ICU's
# data/build.xml
#
# Running "ant cleanprod" is necessary to clean out the production data directory
# (usually $CLDR_TMP_DIR/production ), required if any CLDR data has changed.
#
# Running "ant setup" is not required, but it will print useful errors to
# debug issues with your path when it fails.
#
cd $ICU4C_DIR/source/data
ant cleanprod
ant setup
ant clean
ant all 2>&1 | tee /tmp/cldr-newData-buildLog.txt
ant proddata 2>&1 | tee /tmp/cldr-newData-proddataLog.txt
# NOTE: if you change the CLDR data, please run "ant cleanprod" to clean out the
# temporary production data directory (usually $CLDR_DIR/../cldr-aux/production )
# 4b. Build the new ICU4C data files; these include .txt files and .py files.
# These new files will replace whatever was already present in the ICU4C sources.
# This process uses the LdmlConverter in $TOOLS_ROOT/cldr/cldr-to-icu/;
# see $TOOLS_ROOT/cldr/cldr-to-icu/README.txt
#
# This process will take several minutes, during most of which there will be no log
# output (so do not assume nothing is happening). Keep a log so you can investigate
# anything that looks suspicious.
#
# This also requires temporarily redefining CLDR_DIR.
#
# Note that "ant clean" should not be run before this. The build-icu-data.xml process
# will automatically run its own "clean" step to delete files it cannot determine to
# be ones that it would generate, except for pasts listed in <retain> elements such as
# coll/de__PHONEBOOK.txt, coll/de_.txt, etc.
#
# Before this step, make any necessary changes to
# build-icu-data.xml$TOOLS_ROOT/cldr/cldr-to-icu/ to add new locales, etc.
cd $TOOLS_ROOT/cldr/cldr-to-icu/
CLDR_DIR=$CLDR_TMP_DIR/production ant -f build-icu-data.xml | tee /tmp/cldr-newData-builddataLog.txt
# 5. Check which data files have modifications, which have been added or removed
# (if there are no changes, you may not need to proceed further). Make sure the
# list seems reasonable.
cd $ICU4C_DIR/source/data
git status
# 6. Fix any errors, investigate any warnings. Currently for example there are
# a few warnings of the following form in rbnf files:
# [cldr-build] Warning: no version match with: $Revision☹$
# 5a. You may also want to check which files were modified in CLDR production data:
cd $CLDR_TMP_DIR
git status
# 6. Fix any errors, investigate any warnings.
#
# Fixing may entail modifying CLDR source data or tools - for example,
# updating the validSubLocales for collation data (file a bug if appropriate).
# Repeat steps 4-5 until there are no build errors and no unexpected
# warnings.
# Fixing may entail modifying CLDR source data or TOOLS_ROOT config files or
# tooling.
# 7. Now rebuild ICU4C with the new data and run make check tests.
# Again, keep a log so you can investigate the errors.
@ -217,7 +285,9 @@ make check 2>&1 | tee /tmp/icu4c-newData-makeCheck.txt
# may fail.
# Repeat steps 4-7 until there are no errors.
# 9. Now run the make check tests in exhaustive mode:
# 9. You can also run the make check tests in exhaustive mode (these will also
# be run automatically on the master branch after the merge resulting from this
# integration):
cd $ICU4C_DIR/source
export INTLTEST_OPTS="-e"
@ -244,8 +314,8 @@ ICU_DATA_BUILDTOOL_OPTS=--include_uni_core_data ./runConfigureICU <platform>
# 12b. Now build the jar files.
cd $ICU4C_DIR/source/data
# The following 2 lines are required to include the unicore data:
make clean
make -j6
make clean
make -j6
make icu4j-data-install
cd $ICU4C_DIR/source/test/testdata
make icu4j-data-install
@ -283,18 +353,29 @@ ant check 2>&1 | tee /tmp/icu4j-newData-antCheck.txt
cd $HOME/icu/
cd ..
git status
# add or remove as necessary
# git add or remove as necessary
# commit
# 16. For an official CLDR data integration into ICU, now tag the CLDR and
# ICU sources with an appropriate CLDR milestone (you can check previous
# tags for format), e.g.:
svn copy svn+ssh://unicode.org/repos/cldr/trunk \
svn+ssh://unicode.org/repos/cldr/tags/release-NNN \
--parents -m "cldrbug nnnn: tag cldr sources for NNN"
cd $HOME/icu/
cd $CLDR_DIR
git tag ...
git push --tags
cd $HOME/icu
git tag ...
git push --tags
# 17. You should also commit and tag the update production data in CLDR_TMP_DIR
# using the same tag as for CLDR_DIR above:
cd $CLDR_TMP_DIR
# git add or remove as necessary
# commit
git tag ...
git push --tags

9
icu4c/source/data/coll/LOCALE_DEPS.json
View file

@ -2,7 +2,7 @@
// License & terms of use: http://www.unicode.org/copyright.html#License
{
"cldrVersion": "36.1",
"cldrVersion": "37",
"aliases": {
"ars": "ar_SA",
"in": "id",
@ -21,12 +21,17 @@
"sr_ME": "sr_Cyrl_ME",
"sr_RS": "sr_Cyrl_RS",
"yue": "zh_Hant",
"yue_CN": "yue_Hans_CN",
"yue_CN": "zh_Hans",
"yue_Hans": "zh_Hans",
"yue_Hans_CN": "zh_Hans",
"yue_Hant": "zh_Hant",
"zh_CN": "zh_Hans_CN",
"zh_HK": "zh_Hant_HK",
"zh_MO": "zh_Hant_MO",
"zh_SG": "zh_Hans_SG",
"zh_TW": "zh_Hant_TW"
},
"parents": {
"ff_Adlm": "root"
}
}

4
icu4c/source/data/coll/af.txt
View file

@ -1,11 +1,11 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
af{
Version{"36.1"}
Version{"37"}
collations{
standard{
Sequence{"&N<<<ʼn"}
Version{"36.1"}
Version{"37"}
}
}
}

4
icu4c/source/data/coll/am.txt
View file

@ -1,11 +1,11 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
am{
Version{"36.1"}
Version{"37"}
collations{
standard{
Sequence{"[reorder Ethi]"}
Version{"36.1"}
Version{"37"}
}
}
}

6
icu4c/source/data/coll/ar.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
ar{
Version{"36.1"}
Version{"37"}
collations{
compat{
Sequence{
@ -9,7 +9,7 @@ ar{
"&ت<<ة<<<ﺔ<<<ﺓ"
"&ي<<ى<<<ﯨ<<<ﯩ<<<ﻰ<<<ﻯ<<<ﲐ<<<ﱝ"
}
Version{"36.1"}
Version{"37"}
}
standard{
Sequence{
@ -397,7 +397,7 @@ ar{
"‎&ۓ‎=ﮰ‎=ﮱ"
"‎&ۀ‎=ﮤ‎=ﮥ"
}
Version{"36.1"}
Version{"37"}
}
}
}

2
icu4c/source/data/curr/ja_JP.txt → icu4c/source/data/coll/ar_SA.txt
View file

@ -3,6 +3,6 @@
/**
* generated alias target
*/
ja_JP{
ar_SA{
___{""}
}

2
icu4c/source/data/coll/ars.txt
View file

@ -1,5 +1,5 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
ars{
"%%ALIAS"{"ar"}
"%%ALIAS"{"ar_SA"}
}

4
icu4c/source/data/coll/as.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
as{
Version{"36.1"}
Version{"37"}
collations{
standard{
Sequence{
@ -11,7 +11,7 @@ as{
"&[before 1]ত<ৎ=ত্\u200D"
"&হ<ক্ষ"
}
Version{"36.1"}
Version{"37"}
}
}
}

6
icu4c/source/data/coll/az.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
az{
Version{"36.1"}
Version{"37"}
collations{
search{
Sequence{
@ -9,7 +9,7 @@ az{
"[import az-u-co-standard]"
"[reorder others]"
}
Version{"36.1"}
Version{"37"}
}
standard{
Sequence{
@ -26,7 +26,7 @@ az{
"&H<x<<<X"
"&Z<w<<<W"
}
Version{"36.1"}
Version{"37"}
}
}
}

4
icu4c/source/data/coll/be.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
be{
Version{"36.1"}
Version{"37"}
collations{
standard{
Sequence{
@ -9,7 +9,7 @@ be{
"&Е<ё<<<Ё"
"&у<ў<<<Ў"
}
Version{"36.1"}
Version{"37"}
}
}
}

4
icu4c/source/data/coll/bg.txt
View file

@ -1,11 +1,11 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
bg{
Version{"36.1"}
Version{"37"}
collations{
standard{
Sequence{"[reorder Cyrl]"}
Version{"36.1"}
Version{"37"}
}
}
}

6
icu4c/source/data/coll/bn.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
bn{
Version{"36.1"}
Version{"37"}
collations{
standard{
Sequence{
@ -9,7 +9,7 @@ bn{
"[reorder Beng Deva Guru Gujr Orya Taml Telu Knda Mlym Sinh]"
"&ঔ<ং<ঃ<ঁ"
}
Version{"36.1"}
Version{"37"}
}
traditional{
Sequence{
@ -629,7 +629,7 @@ bn{
"&যৌ<<<য়ৌ"
"&য্<<<য়্"
}
Version{"36.1"}
Version{"37"}
}
}
}

2
icu4c/source/data/coll/bo.txt
View file

@ -1,5 +1,5 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
bo{
Version{"36.1"}
Version{"37"}
}

6
icu4c/source/data/coll/bs.txt
View file

@ -1,15 +1,15 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
bs{
Version{"36.1"}
Version{"37"}
collations{
search{
Sequence{"[import hr-u-co-search]"}
Version{"36.1"}
Version{"37"}
}
standard{
Sequence{"[import hr]"}
Version{"36.1"}
Version{"37"}
}
}
}

4
icu4c/source/data/coll/bs_Cyrl.txt
View file

@ -1,11 +1,11 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
bs_Cyrl{
Version{"36.1"}
Version{"37"}
collations{
standard{
Sequence{"[import sr]"}
Version{"36.1"}
Version{"37"}
}
}
}

4
icu4c/source/data/coll/ca.txt
View file

@ -1,14 +1,14 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
ca{
Version{"36.1"}
Version{"37"}
collations{
search{
Sequence{
"[import und-u-co-search]"
"&L<ŀ=l·<<<Ŀ=L·"
}
Version{"36.1"}
Version{"37"}
}
}
}

4
icu4c/source/data/coll/ceb.txt
View file

@ -1,11 +1,11 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
ceb{
Version{"36.1"}
Version{"37"}
collations{
standard{
Sequence{"&N<ñ<<<Ñ<ng<<<Ng<<<NG"}
Version{"36.1"}
Version{"37"}
}
}
}

4
icu4c/source/data/coll/chr.txt
View file

@ -1,11 +1,11 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
chr{
Version{"36.1"}
Version{"37"}
collations{
standard{
Sequence{"[reorder Cher]"}
Version{"36.1"}
Version{"37"}
}
}
}

4
icu4c/source/data/coll/cs.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
cs{
Version{"36.1"}
Version{"37"}
collations{
standard{
Sequence{
@ -11,7 +11,7 @@ cs{
"&S<š<<<Š"
"&Z<ž<<<Ž"
}
Version{"36.1"}
Version{"37"}
}
}
}

4
icu4c/source/data/coll/cy.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
cy{
Version{"36.1"}
Version{"37"}
collations{
standard{
Sequence{
@ -14,7 +14,7 @@ cy{
"&R<rh<<<Rh<<<RH"
"&T<th<<<Th<<<TH"
}
Version{"36.1"}
Version{"37"}
}
}
}

6
icu4c/source/data/coll/da.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
da{
Version{"36.1"}
Version{"37"}
collations{
search{
Sequence{
@ -9,7 +9,7 @@ da{
"[import da-u-co-standard]"
"[caseFirst off]"
}
Version{"36.1"}
Version{"37"}
}
standard{
Sequence{
@ -21,7 +21,7 @@ da{
"&[before 1]ǀ<æ<<<Æ<<ä<<<Ä<ø<<<Ø<<ö<<<Ö<<ő<<<Ő<å<<<Å<<<aa<<<Aa<<<AA"
"&oe<<œ<<<Œ"
}
Version{"36.1"}
Version{"37"}
}
}
}

6
icu4c/source/data/coll/de.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
de{
Version{"36.1"}
Version{"37"}
collations{
phonebook{
Sequence{
@ -9,14 +9,14 @@ de{
"&OE<<ö<<<Ö"
"&UE<<ü<<<Ü"
}
Version{"36.1"}
Version{"37"}
}
search{
Sequence{
"[import und-u-co-search]"
"[import de-u-co-phonebk]"
}
Version{"36.1"}
Version{"37"}
}
}
}

4
icu4c/source/data/coll/de_AT.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
de_AT{
Version{"36.1"}
Version{"37"}
collations{
phonebook{
Sequence{
@ -10,7 +10,7 @@ de_AT{
"&u<ü<<<Ü"
"&ss<ß<<<ẞ"
}
Version{"36.1"}
Version{"37"}
}
}
}

4
icu4c/source/data/coll/dsb.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
dsb{
Version{"36.1"}
Version{"37"}
collations{
standard{
Sequence{
@ -14,7 +14,7 @@ dsb{
"&S<š<<<Š<ś<<<Ś"
"&Z<ž<<<Ž<ź<<<Ź"
}
Version{"36.1"}
Version{"37"}
}
}
}

2
icu4c/source/data/coll/dz.txt
View file

@ -1,5 +1,5 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
dz{
Version{"36.1"}
Version{"37"}
}

4
icu4c/source/data/coll/ee.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
ee{
Version{"36.1"}
Version{"37"}
collations{
standard{
Sequence{
@ -17,7 +17,7 @@ ee{
"&T<ts<<<Ts<<<TS"
"&V<ʋ<<<Ʋ"
}
Version{"36.1"}
Version{"37"}
}
}
}

4
icu4c/source/data/coll/el.txt
View file

@ -1,14 +1,14 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
el{
Version{"36.1"}
Version{"37"}
collations{
standard{
Sequence{
"[normalization on]"
"[reorder Grek]"
}
Version{"36.1"}
Version{"37"}
}
}
}

2
icu4c/source/data/coll/en.txt
View file

@ -1,5 +1,5 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
en{
Version{"36.1"}
Version{"37"}
}

2
icu4c/source/data/coll/en_US.txt
View file

@ -1,5 +1,5 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
en_US{
Version{"36.1"}
Version{"37"}
}

4
icu4c/source/data/coll/en_US_POSIX.txt
View file

@ -1,14 +1,14 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
en_US_POSIX{
Version{"36.1"}
Version{"37"}
collations{
standard{
Sequence{
"&A<*'\u0020'-'/'<*0-'@'<*ABCDEFGHIJKLMNOPQRSTUVWXYZ<*'['-'`'<*abcdefghijklmnopqrstuvwxyz"
"<*'{'-'\u007F'"
}
Version{"36.1"}
Version{"37"}
}
}
}

4
icu4c/source/data/coll/eo.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
eo{
Version{"36.1"}
Version{"37"}
collations{
standard{
Sequence{
@ -12,7 +12,7 @@ eo{
"&S<ŝ<<<Ŝ"
"&U<ŭ<<<Ŭ"
}
Version{"36.1"}
Version{"37"}
}
}
}

8
icu4c/source/data/coll/es.txt
View file

@ -1,18 +1,18 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
es{
Version{"36.1"}
Version{"37"}
collations{
search{
Sequence{
"[import und-u-co-search]"
"&N<ñ<<<Ñ"
}
Version{"36.1"}
Version{"37"}
}
standard{
Sequence{"&N<ñ<<<Ñ"}
Version{"36.1"}
Version{"37"}
}
traditional{
Sequence{
@ -20,7 +20,7 @@ es{
"&C<ch<<<Ch<<<CH"
"&l<ll<<<Ll<<<LL"
}
Version{"36.1"}
Version{"37"}
}
}
}

4
icu4c/source/data/coll/et.txt
View file

@ -1,14 +1,14 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
et{
Version{"36.1"}
Version{"37"}
collations{
standard{
Sequence{
"&[before 1]T<š<<<Š<z<<<Z<ž<<<Ž"
"&[before 1]X<õ<<<Õ<ä<<<Ä<ö<<<Ö<ü<<<Ü"
}
Version{"36.1"}
Version{"37"}
}
}
}

4
icu4c/source/data/coll/fa.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
fa{
Version{"36.1"}
Version{"37"}
collations{
standard{
Sequence{
@ -16,7 +16,7 @@ fa{
"&ۏ<ه<<ە<<ہ<<ة<<ۃ<<ۀ<<ھ"
"&ی<<*ىےيېۑۍێ"
}
Version{"36.1"}
Version{"37"}
}
}
}

4
icu4c/source/data/coll/fa_AF.txt
View file

@ -1,11 +1,11 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
fa_AF{
Version{"36.1"}
Version{"37"}
collations{
standard{
Sequence{"[import ps]"}
Version{"36.1"}
Version{"37"}
}
}
}

5
icu4c/source/data/coll/ff.txt Normal file
View file

@ -0,0 +1,5 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
ff{
Version{"37"}
}

149
icu4c/source/data/coll/ff_Adlm.txt Normal file
View file

@ -0,0 +1,149 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
ff_Adlm{
%%Parent{"root"}
Version{"37"}
collations{
standard{
Sequence{
"&𞤀<𞤀𞥄"
"&𞤀𞥄=𞤀𞤀"
"&𞤢<𞤢𞥄"
"&𞤢𞥄=𞤢𞤢"
"&𞤁<𞤁𞥆"
"&𞤁𞥆=𞤁𞤁"
"&𞤣<𞤣𞥆"
"&𞤣𞥆=𞤣𞤣"
"&𞤂<𞤂𞥆"
"&𞤂𞥆=𞤂𞤂"
"&𞤤<𞤤𞥆"
"&𞤤𞥆=𞤤𞤤"
"&𞤃<𞤃𞥆"
"&𞤃𞥆=𞤃𞤃"
"&𞤥<𞤥𞥆"
"&𞤥𞥆=𞤥𞤥"
"&𞤄<𞤄𞥆"
"&𞤄𞥆=𞤄𞤄"
"&𞤦<𞤦𞥆"
"&𞤦𞥆=𞤦𞤦"
"&𞤅<𞤅𞥆"
"&𞤅𞥆=𞤅𞤅"
"&𞤧<𞤧𞥆"
"&𞤧𞥆=𞤧𞤧"
"&𞤆<𞤆𞥆"
"&𞤆𞥆=𞤆𞤆"
"&𞤨<𞤨𞥆"
"&𞤨𞥆=𞤨𞤨"
"&𞤇<𞤇𞥆"
"&𞤇𞥆=𞤇𞤇"
"&𞤩<𞤩𞥆"
"&𞤩𞥆=𞤩𞤩"
"&𞤈<𞤈𞥆"
"&𞤈𞥆=𞤈𞤈"
"&𞤪<𞤪𞥆"
"&𞤪𞥆=𞤪𞤪"
"&𞤊<𞤊𞥆"
"&𞤊𞥆=𞤊𞤊"
"&𞤬<𞤬𞥆"
"&𞤬𞥆=𞤬𞤬"
"&𞤍<𞤍𞥆"
"&𞤍𞥆=𞤍𞤍"
"&𞤯<𞤯𞥆"
"&𞤯𞥆=𞤯𞤯"
"&𞤎<𞤎𞥆"
"&𞤎𞥆=𞤎𞤎"
"&𞤰<𞤰𞥆"
"&𞤰𞥆=𞤰𞤰"
"&𞤏<𞤏𞥆"
"&𞤏𞥆=𞤏𞤏"
"&𞤱<𞤱𞥆"
"&𞤱𞥆=𞤱𞤱"
"&𞤐<𞤐𞥆"
"&𞤐𞥆=𞤐𞤐"
"&𞤲<𞤲𞥆"
"&𞤲𞥆=𞤲𞤲"
"&𞤑<𞤑𞥆"
"&𞤑𞥆=𞤑𞤑"
"&𞤳<𞤳𞥆"
"&𞤳𞥆=𞤳𞤳"
"&𞤒<𞤒𞥆"
"&𞤒𞥆=𞤒𞤒"
"&𞤴<𞤴𞥆"
"&𞤴𞥆=𞤴𞤴"
"&𞤔<𞤔𞥆"
"&𞤔𞥆=𞤔𞤔"
"&𞤶<𞤶𞥆"
"&𞤶𞥆=𞤶𞤶"
"&𞤕<𞤕𞥆"
"&𞤕𞥆=𞤕𞤕"
"&𞤷<𞤷𞥆"
"&𞤷𞥆=𞤷𞤷"
"&𞤖<𞤖𞥆"
"&𞤖𞥆=𞤖𞤖"
"&𞤸<𞤸𞥆"
"&𞤸𞥆=𞤸𞤸"
"&𞤗<𞤗𞥆"
"&𞤗𞥆=𞤗𞤗"
"&𞤹<𞤹𞥆"
"&𞤹𞥆=𞤹𞤹"
"&𞤘<𞤘𞥆"
"&𞤘𞥆=𞤘𞤘"
"&𞤺<𞤺𞥆"
"&𞤺𞥆=𞤺𞤺"
"&𞤙<𞤙𞥆"
"&𞤙𞥆=𞤙𞤙"
"&𞤻<𞤻𞥆"
"&𞤻𞥆=𞤻𞤻"
"&𞤚<𞤚𞥆"
"&𞤚𞥆=𞤚𞤚"
"&𞤼<𞤼𞥆"
"&𞤼𞥆=𞤼𞤼"
"&𞤛<𞤛𞥆"
"&𞤛𞥆=𞤛𞤛"
"&𞤽<𞤽𞥆"
"&𞤽𞥆=𞤽𞤽"
"&𞤜<𞤜𞥆"
"&𞤜𞥆=𞤜𞤜"
"&𞤾<𞤾𞥆"
"&𞤾𞥆=𞤾𞤾"
"&𞤝<𞤝𞥆"
"&𞤝𞥆=𞤝𞤝"
"&𞤿<𞤿𞥆"
"&𞤿𞥆=𞤿𞤿"
"&𞤞<𞤞𞥆"
"&𞤞𞥆=𞤞𞤞"
"&𞥀<𞥀𞥆"
"&𞥀𞥆=𞥀𞥀"
"&𞤟<𞤟𞥆"
"&𞤟𞥆=𞤟𞤟"
"&𞥁<𞥁𞥆"
"&𞥁𞥆=𞥁𞥁"
"&𞤠<𞤠𞥆"
"&𞤠𞥆=𞤠𞤠"
"&𞥂<𞥂𞥆"
"&𞥂𞥆=𞥂𞥂"
"&𞤡<𞤡𞥆"
"&𞤡𞥆=𞤡𞤡"
"&𞥃<𞥃𞥆"
"&𞥃𞥆=𞥃𞥃"
"&𞤉<𞤉𞥅"
"&𞤉𞥅<<𞤉𞤉"
"&𞤫<𞤫𞥅"
"&𞤫𞥅<<𞤫𞤫"
"&𞤋<𞤋𞥅"
"&𞤋𞥅<<𞤋𞤋"
"&𞤭<𞤭𞥅"
"&𞤭𞥅<<𞤭𞤭"
"&𞤌<𞤌𞥅"
"&𞤌𞥅<<𞤌𞤌"
"&𞤮<𞤮𞥅"
"&𞤮𞥅<<𞤮𞤮"
"&𞤓<𞤓𞥅"
"&𞤓𞥅<<𞤓𞤓"
"&𞤵<𞤵𞥅"
"&𞤵𞥅<<𞤵𞤵"
}
Version{"37"}
}
}
}

8
icu4c/source/data/coll/fi.txt
View file

@ -1,14 +1,14 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
fi{
Version{"36.1"}
Version{"37"}
collations{
search{
Sequence{
"[import und-u-co-search]"
"[import fi-u-co-trad]"
}
Version{"36.1"}
Version{"37"}
}
standard{
Sequence{
@ -20,7 +20,7 @@ fi{
"&Z\u0335<<ʒ<<<Ʒ"
"&[before 1]ǀ<å<<<Å<ä<<<Ä<<æ<<<Æ<ö<<<Ö<<ø<<<Ø"
}
Version{"36.1"}
Version{"37"}
}
traditional{
Sequence{
@ -31,7 +31,7 @@ fi{
"&Y<<ü<<<Ü<<ű<<<Ű"
"&[before 1]ǀ<å<<<Å<ä<<<Ä<<æ<<<Æ<ö<<<Ö<<ø<<<Ø<<ő<<<Ő<<õ<<<Õ<<œ<<<Œ"
}
Version{"36.1"}
Version{"37"}
}
}
}

4
icu4c/source/data/coll/fil.txt
View file

@ -1,11 +1,11 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
fil{
Version{"36.1"}
Version{"37"}
collations{
standard{
Sequence{"&N<ñ<<<Ñ<ng<<<Ng<<<NG"}
Version{"36.1"}
Version{"37"}
}
}
}

6
icu4c/source/data/coll/fo.txt
View file

@ -1,14 +1,14 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
fo{
Version{"36.1"}
Version{"37"}
collations{
search{
Sequence{
"[import und-u-co-search]"
"[import fo-u-co-standard]"
}
Version{"36.1"}
Version{"37"}
}
standard{
Sequence{
@ -18,7 +18,7 @@ fo{
"&Y<<ü<<<Ü<<ű<<<Ű"
"&[before 1]ǀ<æ<<<Æ<<ä<<<Ä<<ę<<<Ę<ø<<<Ø<<ö<<<Ö<<ő<<<Ő<<œ<<<Œ<å<<<Å<<<aa<<<Aa<<<AA"
}
Version{"36.1"}
Version{"37"}
}
}
}

2
icu4c/source/data/coll/fr.txt
View file

@ -1,5 +1,5 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
fr{
Version{"36.1"}
Version{"37"}
}

4
icu4c/source/data/coll/fr_CA.txt
View file

@ -1,11 +1,11 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
fr_CA{
Version{"36.1"}
Version{"37"}
collations{
standard{
Sequence{"[backwards 2]"}
Version{"36.1"}
Version{"37"}
}
}
}

2
icu4c/source/data/coll/ga.txt
View file

@ -1,5 +1,5 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
ga{
Version{"36.1"}
Version{"37"}
}

6
icu4c/source/data/coll/gl.txt
View file

@ -1,15 +1,15 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
gl{
Version{"36.1"}
Version{"37"}
collations{
search{
Sequence{"[import es-u-co-search]"}
Version{"36.1"}
Version{"37"}
}
standard{
Sequence{"[import es]"}
Version{"36.1"}
Version{"37"}
}
}
}

4
icu4c/source/data/coll/gu.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
gu{
Version{"36.1"}
Version{"37"}
collations{
standard{
Sequence{
@ -9,7 +9,7 @@ gu{
"[reorder Gujr Deva Beng Guru Orya Taml Telu Knda Mlym Sinh]"
"&ૐ<ં<<ઁ<ઃ"
}
Version{"36.1"}
Version{"37"}
}
}
}

4
icu4c/source/data/coll/ha.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
ha{
Version{"36.1"}
Version{"37"}
collations{
standard{
Sequence{
@ -12,7 +12,7 @@ ha{
"&T<ts<<<Ts<<<TS"
"&Y<ƴ<<<ʼy<<<''y<<<Ƴ<<<ʼY<<<''Y"
}
Version{"36.1"}
Version{"37"}
}
}
}

4
icu4c/source/data/coll/haw.txt
View file

@ -1,14 +1,14 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
haw{
Version{"36.1"}
Version{"37"}
collations{
standard{
Sequence{
"&a<e<<<E<i<<<I<o<<<O<u<<<U"
"&w<ʻ"
}
Version{"36.1"}
Version{"37"}
}
}
}

6
icu4c/source/data/coll/he.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
he{
Version{"36.1"}
Version{"37"}
collations{
search{
Sequence{
@ -11,7 +11,7 @@ he{
"‎&״"
"<<'\u0022'"
}
Version{"36.1"}
Version{"37"}
}
standard{
Sequence{
@ -20,7 +20,7 @@ he{
"&[before 2]''<<׳"
"&[before 2]'\u0022'<<״"
}
Version{"36.1"}
Version{"37"}
}
}
}

4
icu4c/source/data/coll/hi.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
hi{
Version{"36.1"}
Version{"37"}
collations{
standard{
Sequence{
@ -9,7 +9,7 @@ hi{
"[reorder Deva Beng Guru Gujr Orya Taml Telu Knda Mlym Sinh]"
"&ॐ<ं<<ँ<ः"
}
Version{"36.1"}
Version{"37"}
}
}
}

6
icu4c/source/data/coll/hr.txt
View file

@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html#License
hr{
Version{"36.1"}
Version{"37"}
collations{
search{
Sequence{
@ -9,7 +9,7 @@ hr{
"[import hr-u-co-standard]"
"[reorder others]"
}
Version{"36.1"}
Version{"37"}
}
standard{
Sequence{
@ -21,7 +21,7 @@ hr{
"&S<š<<<Š"
"&Z<ž<<<Ž"
}
Version{"36.1"}
Version{"37"}
}
}
}

Some files were not shown because too many files have changed in this diff Show more