corysanin/tubestation
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Bug 1954425 - Part 2: Update in-tree ICU to 77. r=platform-i18n-reviewers,nordzilla

Browse Source 
Update ICU by running `./update-icu.sh https://github.com/unicode-org/icu.git maint/maint-77`.

Differential Revision: https://phabricator.services.mozilla.com/D241784
This commit is contained in:
André Bargull
2025-03-20 09:46:17 +00:00
parent 7be5a0750e
commit 40fab635a7
4632 changed files with 16753 additions and 13516 deletions
Download Patch File Download Diff File Expand all files Collapse all files

BIN
config/external/icu/data/icudt76l.dat → config/external/icu/data/icudt77l.dat vendored
View File

Binary file not shown.

10
intl/icu/GIT-INFO
View File

@@ -1,5 +1,7 @@
commit 8eca245c7484ac6cc179e3e5f7c1ea7680810f39
Author: Rahul Pandey <rp9.next@gmail.com>
Date: Mon Oct 21 16:21:38 2024 +0530
commit f23af97cf467a3ae761e5943a6caf793415ac857
Author: Markus Scherer <markus.icu@gmail.com>
Date: Wed Mar 12 16:40:58 2025 +0000
ICU-22724 BRS_76_GA Update version number to 76.1 (No more -SNAPSHOT)
ICU-22923 ICU 77 release page updates
See #3432

403
intl/icu/source/Doxyfile.in
View File

@@ -1,4 +1,4 @@
# Doxyfile 1.8.13
# Doxyfile 1.9.1
# Copyright (C) 2016 and later: Unicode, Inc. and others.
# License & terms of use: http://www.unicode.org/copyright.html
@@ -25,11 +25,11 @@
# Project related configuration options
#---------------------------------------------------------------------------
# This tag specifies the encoding used for all characters in the config file
# that follow. The default is UTF-8 which is also the encoding used for all text
# before the first occurrence of this tag. Doxygen uses libiconv (or the iconv
# built into libc) for the transcoding. See http://www.gnu.org/software/libiconv
# for the list of possible encodings.
# This tag specifies the encoding used for all characters in the configuration
# file that follow. The default is UTF-8 which is also the encoding used for all
# text before the first occurrence of this tag. Doxygen uses libiconv (or the
# iconv built into libc) for the transcoding. See
# https://www.gnu.org/software/libiconv/ for the list of possible encodings.
# The default value is: UTF-8.
DOXYFILE_ENCODING = UTF-8
@@ -101,6 +101,14 @@ ALLOW_UNICODE_NAMES = NO
OUTPUT_LANGUAGE = English
# The OUTPUT_TEXT_DIRECTION tag is used to specify the direction in which all
# documentation generated by doxygen is written. Doxygen will use this
# information to generate all generated output in the proper direction.
# Possible values are: None, LTR, RTL and Context.
# The default value is: None.
OUTPUT_TEXT_DIRECTION = None
# If the BRIEF_MEMBER_DESC tag is set to YES, doxygen will include brief member
# descriptions after the members that are listed in the file and class
# documentation (similar to Javadoc). Set to NO to disable this.
@@ -187,6 +195,16 @@ SHORT_NAMES = NO
JAVADOC_AUTOBRIEF = YES
# If the JAVADOC_BANNER tag is set to YES then doxygen will interpret a line
# such as
# /***************
# as being the beginning of a Javadoc-style comment "banner". If set to NO, the
# Javadoc-style will behave just like regular comments and it will not be
# interpreted by doxygen.
# The default value is: NO.
JAVADOC_BANNER = NO
# If the QT_AUTOBRIEF tag is set to YES then doxygen will interpret the first
# line (until the first dot) of a Qt-style comment as the brief description. If
# set to NO, the Qt-style will behave just like regular Qt-style comments (thus
@@ -207,6 +225,14 @@ QT_AUTOBRIEF = NO
MULTILINE_CPP_IS_BRIEF = NO
# By default Python docstrings are displayed as preformatted text and doxygen's
# special commands cannot be used. By setting PYTHON_DOCSTRING to NO the
# doxygen's special commands can be used and the contents of the docstring
# documentation blocks is shown as doxygen documentation.
# The default value is: YES.
PYTHON_DOCSTRING = YES
# If the INHERIT_DOCS tag is set to YES then an undocumented member inherits the
# documentation from any documented member that it re-implements.
# The default value is: YES.
@@ -234,7 +260,12 @@ TAB_SIZE = 8
# will allow you to put the command \sideeffect (or @sideeffect) in the
# documentation, which will result in a user-defined paragraph with heading
# "Side Effects:". You can put \n's in the value part of an alias to insert
# newlines.
# newlines (in the resulting output). You can put ^^ in the value part of an
# alias to insert a newline as if a physical newline was in the original file.
# When you need a literal { or } or , in the value part of an alias you have to
# escape them by means of a backslash (\), this can lead to conflicts with the
# commands \{ and \} for these it is advised to use the version @{ and @} or use
# a double escape (\\{ and \\})
ALIASES = "memo=\par Note:\n" \
"draft=\xrefitem draft \"Draft\" \"Draft List\" This API may be changed in the future versions and was introduced in" \
@@ -244,12 +275,6 @@ ALIASES = "memo=\par Note:\n" \
"system=\xrefitem system \"System\" \"System List\" \n Do not use unless you know what you are doing." \
"internal=\xrefitem internal \"Internal\" \"Internal List\" Do not use. This API is for internal use only."
# This tag can be used to specify a number of word-keyword mappings (TCL only).
# A mapping has the form "name=value". For example adding "class=itcl::class"
# will allow you to use the command class in the itcl::class meaning.
TCL_SUBST =
# Set the OPTIMIZE_OUTPUT_FOR_C tag to YES if your project consists of C sources
# only. Doxygen will then generate output that is more tailored for C. For
# instance, some of the names that are used will be different. The list of all
@@ -278,28 +303,40 @@ OPTIMIZE_FOR_FORTRAN = NO
OPTIMIZE_OUTPUT_VHDL = NO
# Set the OPTIMIZE_OUTPUT_SLICE tag to YES if your project consists of Slice
# sources only. Doxygen will then generate output that is more tailored for that
# language. For instance, namespaces will be presented as modules, types will be
# separated into more groups, etc.
# The default value is: NO.
OPTIMIZE_OUTPUT_SLICE = NO
# Doxygen selects the parser to use depending on the extension of the files it
# parses. With this tag you can assign which parser to use for a given
# extension. Doxygen has a built-in mapping, but you can override or extend it
# using this tag. The format is ext=language, where ext is a file extension, and
# language is one of the parsers supported by doxygen: IDL, Java, Javascript,
# C#, C, C++, D, PHP, Objective-C, Python, Fortran (fixed format Fortran:
# FortranFixed, free formatted Fortran: FortranFree, unknown formatted Fortran:
# Fortran. In the later case the parser tries to guess whether the code is fixed
# or free formatted code, this is the default for Fortran type files), VHDL. For
# instance to make doxygen treat .inc files as Fortran files (default is PHP),
# and .f files as C (default is Fortran), use: inc=Fortran f=C.
# language is one of the parsers supported by doxygen: IDL, Java, JavaScript,
# Csharp (C#), C, C++, D, PHP, md (Markdown), Objective-C, Python, Slice, VHDL,
# Fortran (fixed format Fortran: FortranFixed, free formatted Fortran:
# FortranFree, unknown formatted Fortran: Fortran. In the later case the parser
# tries to guess whether the code is fixed or free formatted code, this is the
# default for Fortran type files). For instance to make doxygen treat .inc files
# as Fortran files (default is PHP), and .f files as C (default is Fortran),
# use: inc=Fortran f=C.
#
# Note: For files without extension you can use no_extension as a placeholder.
#
# Note that for custom extensions you also need to set FILE_PATTERNS otherwise
# the files are not read by doxygen.
# the files are not read by doxygen. When specifying no_extension you should add
# * to the FILE_PATTERNS.
#
# Note see also the list of default file extension mappings.
EXTENSION_MAPPING =
# If the MARKDOWN_SUPPORT tag is enabled then doxygen pre-processes all comments
# according to the Markdown format, which allows for more readable
# documentation. See http://daringfireball.net/projects/markdown/ for details.
# documentation. See https://daringfireball.net/projects/markdown/ for details.
# The output of markdown processing is further processed by doxygen, so you can
# mix doxygen, HTML, and XML commands with Markdown formatting. Disable only in
# case of backward compatibilities issues.
@@ -311,7 +348,7 @@ MARKDOWN_SUPPORT = YES
# to that level are automatically included in the table of contents, even if
# they do not have an id attribute.
# Note: This feature currently applies only to Markdown headings.
# Minimum value: 0, maximum value: 99, default value: 0.
# Minimum value: 0, maximum value: 99, default value: 5.
# This tag requires that the tag MARKDOWN_SUPPORT is set to YES.
TOC_INCLUDE_HEADINGS = 0
@@ -341,7 +378,7 @@ BUILTIN_STL_SUPPORT = NO
CPP_CLI_SUPPORT = NO
# Set the SIP_SUPPORT tag to YES if your project consists of sip (see:
# http://www.riverbankcomputing.co.uk/software/sip/intro) sources only. Doxygen
# https://www.riverbankcomputing.com/software/sip/intro) sources only. Doxygen
# will parse them like normal C++ but will assume all classes use public instead
# of private inheritance when no explicit protection keyword is present.
# The default value is: NO.
@@ -427,6 +464,19 @@ TYPEDEF_HIDES_STRUCT = NO
LOOKUP_CACHE_SIZE = 0
# The NUM_PROC_THREADS specifies the number threads doxygen is allowed to use
# during processing. When set to 0 doxygen will based this on the number of
# cores available in the system. You can set it explicitly to a value larger
# than 0 to get more control over the balance between CPU load and processing
# speed. At this moment only the input processing can be done using multiple
# threads. Since this is still an experimental feature the default is set to 1,
# which efficively disables parallel processing. Please report any issues you
# encounter. Generating dot graphs in parallel is controlled by the
# DOT_NUM_THREADS setting.
# Minimum value: 0, maximum value: 32, default value: 1.
NUM_PROC_THREADS = 1
#---------------------------------------------------------------------------
# Build related configuration options
#---------------------------------------------------------------------------
@@ -447,6 +497,12 @@ EXTRACT_ALL = NO
EXTRACT_PRIVATE = NO
# If the EXTRACT_PRIV_VIRTUAL tag is set to YES, documented private virtual
# methods of a class will be included in the documentation.
# The default value is: NO.
EXTRACT_PRIV_VIRTUAL = NO
# If the EXTRACT_PACKAGE tag is set to YES, all members with package or internal
# scope will be included in the documentation.
# The default value is: NO.
@@ -484,6 +540,13 @@ EXTRACT_LOCAL_METHODS = NO
EXTRACT_ANON_NSPACES = NO
# If this flag is set to YES, the name of an unnamed parameter in a declaration
# will be determined by the corresponding definition. By default unnamed
# parameters remain unnamed in the output.
# The default value is: YES.
RESOLVE_UNNAMED_PARAMS = YES
# If the HIDE_UNDOC_MEMBERS tag is set to YES, doxygen will hide all
# undocumented members inside documented classes or files. If set to NO these
# members will be included in the various overviews, but no documentation
@@ -501,8 +564,8 @@ HIDE_UNDOC_MEMBERS = NO
HIDE_UNDOC_CLASSES = NO
# If the HIDE_FRIEND_COMPOUNDS tag is set to YES, doxygen will hide all friend
# (class|struct|union) declarations. If set to NO, these declarations will be
# included in the documentation.
# declarations. If set to NO, these declarations will be included in the
# documentation.
# The default value is: NO.
HIDE_FRIEND_COMPOUNDS = NO
@@ -521,11 +584,18 @@ HIDE_IN_BODY_DOCS = NO
INTERNAL_DOCS = YES
# If the CASE_SENSE_NAMES tag is set to NO then doxygen will only generate file
# names in lower-case letters. If set to YES, upper-case letters are also
# allowed. This is useful if you have classes or files whose names only differ
# in case and if your file system supports case sensitive file names. Windows
# and Mac users are advised to set this option to NO.
# With the correct setting of option CASE_SENSE_NAMES doxygen will better be
# able to match the capabilities of the underlying filesystem. In case the
# filesystem is case sensitive (i.e. it supports files in the same directory
# whose names only differ in casing), the option must be set to YES to properly
# deal with such files in case they appear in the input. For filesystems that
# are not case sensitive the option should be be set to NO to properly deal with
# output files written for symbols that only differ in casing, such as for two
# classes, one named CLASS and the other named Class, and to also support
# references to files without having to specify the exact matching casing. On
# Windows (including Cygwin) and MacOS, users should typically set this option
# to NO, whereas on Linux or other Unix flavors it should typically be set to
# YES.
# The default value is: system dependent.
CASE_SENSE_NAMES = YES
@@ -712,7 +782,7 @@ LAYOUT_FILE =
# The CITE_BIB_FILES tag can be used to specify one or more bib files containing
# the reference definitions. This must be a list of .bib files. The .bib
# extension is automatically appended if omitted. This requires the bibtex tool
# to be installed. See also http://en.wikipedia.org/wiki/BibTeX for more info.
# to be installed. See also https://en.wikipedia.org/wiki/BibTeX for more info.
# For LaTeX the style of the bibliography can be controlled using
# LATEX_BIB_STYLE. To use this feature you need bibtex and perl available in the
# search path. See also \cite for info how to create references.
@@ -757,13 +827,17 @@ WARN_IF_DOC_ERROR = YES
# This WARN_NO_PARAMDOC option can be enabled to get warnings for functions that
# are documented, but have no documentation for their parameters or return
# value. If set to NO, doxygen will only warn about wrong or incomplete
# parameter documentation, but not about the absence of documentation.
# parameter documentation, but not about the absence of documentation. If
# EXTRACT_ALL is set to YES then this flag will automatically be disabled.
# The default value is: NO.
WARN_NO_PARAMDOC = NO
# If the WARN_AS_ERROR tag is set to YES then doxygen will immediately stop when
# a warning is encountered.
# a warning is encountered. If the WARN_AS_ERROR tag is set to FAIL_ON_WARNINGS
# then doxygen will continue running as if WARN_AS_ERROR tag is set to NO, but
# at the end of the doxygen process doxygen will return with a non-zero status.
# Possible values are: NO, YES and FAIL_ON_WARNINGS.
# The default value is: NO.
WARN_AS_ERROR = NO
@@ -802,8 +876,8 @@ INPUT = @srcdir@/common/unicode \
# This tag can be used to specify the character encoding of the source files
# that doxygen parses. Internally doxygen uses the UTF-8 encoding. Doxygen uses
# libiconv (or the iconv built into libc) for the transcoding. See the libiconv
# documentation (see: http://www.gnu.org/software/libiconv) for the list of
# possible encodings.
# documentation (see:
# https://www.gnu.org/software/libiconv/) for the list of possible encodings.
# The default value is: UTF-8.
INPUT_ENCODING = UTF-8
@@ -816,11 +890,15 @@ INPUT_ENCODING = UTF-8
# need to set EXTENSION_MAPPING for the extension otherwise the files are not
# read by doxygen.
#
# Note the list of default checked file patterns might differ from the list of
# default file extension mappings.
#
# If left blank the following patterns are tested:*.c, *.cc, *.cxx, *.cpp,
# *.c++, *.java, *.ii, *.ixx, *.ipp, *.i++, *.inl, *.idl, *.ddl, *.odl, *.h,
# *.hh, *.hxx, *.hpp, *.h++, *.cs, *.d, *.php, *.php4, *.php5, *.phtml, *.inc,
# *.m, *.markdown, *.md, *.mm, *.dox, *.py, *.pyw, *.f90, *.f95, *.f03, *.f08,
# *.f, *.for, *.tcl, *.vhd, *.vhdl, *.ucf and *.qsf.
# *.m, *.markdown, *.md, *.mm, *.dox (to be provided as doxygen C comment),
# *.py, *.pyw, *.f90, *.f95, *.f03, *.f08, *.f18, *.f, *.for, *.vhd, *.vhdl,
# *.ucf, *.qsf and *.ice.
FILE_PATTERNS = *.h
@@ -979,7 +1057,7 @@ INLINE_SOURCES = NO
STRIP_CODE_COMMENTS = YES
# If the REFERENCED_BY_RELATION tag is set to YES then for each documented
# function all documented functions referencing it will be listed.
# entity all documented functions referencing it will be listed.
# The default value is: NO.
REFERENCED_BY_RELATION = YES
@@ -1011,12 +1089,12 @@ SOURCE_TOOLTIPS = YES
# If the USE_HTAGS tag is set to YES then the references to source code will
# point to the HTML generated by the htags(1) tool instead of doxygen built-in
# source browser. The htags tool is part of GNU's global source tagging system
# (see http://www.gnu.org/software/global/global.html). You will need version
# (see https://www.gnu.org/software/global/global.html). You will need version
# 4.8.6 or higher.
#
# To use it do the following:
# - Install the latest version of global
# - Enable SOURCE_BROWSER and USE_HTAGS in the config file
# - Enable SOURCE_BROWSER and USE_HTAGS in the configuration file
# - Make sure the INPUT points to the root of the source tree
# - Run doxygen as normal
#
@@ -1039,16 +1117,22 @@ USE_HTAGS = NO
VERBATIM_HEADERS = YES
# If the CLANG_ASSISTED_PARSING tag is set to YES then doxygen will use the
# clang parser (see: http://clang.llvm.org/) for more accurate parsing at the
# cost of reduced performance. This can be particularly helpful with template
# rich C++ code for which doxygen's built-in parser lacks the necessary type
# information.
# clang parser (see:
# http://clang.llvm.org/) for more accurate parsing at the cost of reduced
# performance. This can be particularly helpful with template rich C++ code for
# which doxygen's built-in parser lacks the necessary type information.
# Note: The availability of this option depends on whether or not doxygen was
# generated with the -Duse-libclang=ON option for CMake.
# generated with the -Duse_libclang=ON option for CMake.
# The default value is: NO.
CLANG_ASSISTED_PARSING = NO
# If clang assisted parsing is enabled and the CLANG_ADD_INC_PATHS tag is set to
# YES then doxygen will add the directory of each input to the include path.
# The default value is: YES.
CLANG_ADD_INC_PATHS = YES
# If clang assisted parsing is enabled you can provide the compiler with command
# line options that you would normally use when invoking the compiler. Note that
# the include paths will already be set by doxygen for the files and directories
@@ -1057,6 +1141,19 @@ CLANG_ASSISTED_PARSING = NO
CLANG_OPTIONS =
# If clang assisted parsing is enabled you can provide the clang parser with the
# path to the directory containing a file called compile_commands.json. This
# file is the compilation database (see:
# http://clang.llvm.org/docs/HowToSetupToolingForLLVM.html) containing the
# options used when the source files were built. This is equivalent to
# specifying the -p option to a clang tool, such as clang-check. These options
# will then be passed to the parser. Any options specified with CLANG_OPTIONS
# will be added as well.
# Note: The availability of this option depends on whether or not doxygen was
# generated with the -Duse_libclang=ON option for CMake.
CLANG_DATABASE_PATH =
#---------------------------------------------------------------------------
# Configuration options related to the alphabetical class index
#---------------------------------------------------------------------------
@@ -1068,13 +1165,6 @@ CLANG_OPTIONS =
ALPHABETICAL_INDEX = YES
# The COLS_IN_ALPHA_INDEX tag can be used to specify the number of columns in
# which the alphabetical index list will be split.
# Minimum value: 1, maximum value: 20, default value: 5.
# This tag requires that the tag ALPHABETICAL_INDEX is set to YES.
COLS_IN_ALPHA_INDEX = 5
# In case all classes in a project start with a common prefix, all classes will
# be put under the same header in the alphabetical index. The IGNORE_PREFIX tag
# can be used to specify a prefix (or a list of prefixes) that should be ignored
@@ -1175,7 +1265,7 @@ HTML_EXTRA_FILES =
# The HTML_COLORSTYLE_HUE tag controls the color of the HTML output. Doxygen
# will adjust the colors in the style sheet and background images according to
# this color. Hue is specified as an angle on a colorwheel, see
# http://en.wikipedia.org/wiki/Hue for more information. For instance the value
# https://en.wikipedia.org/wiki/Hue for more information. For instance the value
# 0 represents red, 60 is yellow, 120 is green, 180 is cyan, 240 is blue, 300
# purple, and 360 is red again.
# Minimum value: 0, maximum value: 359, default value: 220.
@@ -1211,6 +1301,17 @@ HTML_COLORSTYLE_GAMMA = 80
HTML_TIMESTAMP = NO
# If the HTML_DYNAMIC_MENUS tag is set to YES then the generated HTML
# documentation will contain a main index with vertical navigation menus that
# are dynamically created via JavaScript. If disabled, the navigation index will
# consists of multiple levels of tabs that are statically embedded in every HTML
# page. Disable this option to support browsers that do not have JavaScript,
# like the Qt help browser.
# The default value is: YES.
# This tag requires that the tag GENERATE_HTML is set to YES.
HTML_DYNAMIC_MENUS = YES
# If the HTML_DYNAMIC_SECTIONS tag is set to YES then the generated HTML
# documentation will contain sections that can be hidden and shown after the
# page has loaded.
@@ -1234,13 +1335,14 @@ HTML_INDEX_NUM_ENTRIES = 100
# If the GENERATE_DOCSET tag is set to YES, additional index files will be
# generated that can be used as input for Apple's Xcode 3 integrated development
# environment (see: http://developer.apple.com/tools/xcode/), introduced with
# OSX 10.5 (Leopard). To create a documentation set, doxygen will generate a
# Makefile in the HTML output directory. Running make will produce the docset in
# that directory and running make install will install the docset in
# environment (see:
# https://developer.apple.com/xcode/), introduced with OSX 10.5 (Leopard). To
# create a documentation set, doxygen will generate a Makefile in the HTML
# output directory. Running make will produce the docset in that directory and
# running make install will install the docset in
# ~/Library/Developer/Shared/Documentation/DocSets so that Xcode will find it at
# startup. See http://developer.apple.com/tools/creatingdocsetswithdoxygen.html
# for more information.
# startup. See https://developer.apple.com/library/archive/featuredarticles/Doxy
# genXcode/_index.html for more information.
# The default value is: NO.
# This tag requires that the tag GENERATE_HTML is set to YES.
@@ -1279,8 +1381,8 @@ DOCSET_PUBLISHER_NAME = Publisher
# If the GENERATE_HTMLHELP tag is set to YES then doxygen generates three
# additional HTML index files: index.hhp, index.hhc, and index.hhk. The
# index.hhp is a project file that can be read by Microsoft's HTML Help Workshop
# (see: http://www.microsoft.com/en-us/download/details.aspx?id=21138) on
# Windows.
# (see:
# https://www.microsoft.com/en-us/download/details.aspx?id=21138) on Windows.
#
# The HTML Help Workshop contains a compiler that can convert all HTML output
# generated by doxygen into a single compiled HTML file (.chm). Compiled HTML
@@ -1310,7 +1412,7 @@ CHM_FILE =
HHC_LOCATION =
# The GENERATE_CHI flag controls if a separate .chi index file is generated
# (YES) or that it should be included in the primary .chm file (NO).
# (YES) or that it should be included in the main .chm file (NO).
# The default value is: NO.
# This tag requires that the tag GENERATE_HTMLHELP is set to YES.
@@ -1355,7 +1457,8 @@ QCH_FILE =
# The QHP_NAMESPACE tag specifies the namespace to use when generating Qt Help
# Project output. For more information please see Qt Help Project / Namespace
# (see: http://qt-project.org/doc/qt-4.8/qthelpproject.html#namespace).
# (see:
# https://doc.qt.io/archives/qt-4.8/qthelpproject.html#namespace).
# The default value is: org.doxygen.Project.
# This tag requires that the tag GENERATE_QHP is set to YES.
@@ -1363,8 +1466,8 @@ QHP_NAMESPACE = org.doxygen.Project
# The QHP_VIRTUAL_FOLDER tag specifies the namespace to use when generating Qt
# Help Project output. For more information please see Qt Help Project / Virtual
# Folders (see: http://qt-project.org/doc/qt-4.8/qthelpproject.html#virtual-
# folders).
# Folders (see:
# https://doc.qt.io/archives/qt-4.8/qthelpproject.html#virtual-folders).
# The default value is: doc.
# This tag requires that the tag GENERATE_QHP is set to YES.
@@ -1372,30 +1475,30 @@ QHP_VIRTUAL_FOLDER = doc
# If the QHP_CUST_FILTER_NAME tag is set, it specifies the name of a custom
# filter to add. For more information please see Qt Help Project / Custom
# Filters (see: http://qt-project.org/doc/qt-4.8/qthelpproject.html#custom-
# filters).
# Filters (see:
# https://doc.qt.io/archives/qt-4.8/qthelpproject.html#custom-filters).
# This tag requires that the tag GENERATE_QHP is set to YES.
QHP_CUST_FILTER_NAME =
# The QHP_CUST_FILTER_ATTRS tag specifies the list of the attributes of the
# custom filter to add. For more information please see Qt Help Project / Custom
# Filters (see: http://qt-project.org/doc/qt-4.8/qthelpproject.html#custom-
# filters).
# Filters (see:
# https://doc.qt.io/archives/qt-4.8/qthelpproject.html#custom-filters).
# This tag requires that the tag GENERATE_QHP is set to YES.
QHP_CUST_FILTER_ATTRS =
# The QHP_SECT_FILTER_ATTRS tag specifies the list of the attributes this
# project's filter section matches. Qt Help Project / Filter Attributes (see:
# http://qt-project.org/doc/qt-4.8/qthelpproject.html#filter-attributes).
# https://doc.qt.io/archives/qt-4.8/qthelpproject.html#filter-attributes).
# This tag requires that the tag GENERATE_QHP is set to YES.
QHP_SECT_FILTER_ATTRS =
# The QHG_LOCATION tag can be used to specify the location of Qt's
# qhelpgenerator. If non-empty doxygen will try to run qhelpgenerator on the
# generated .qhp file.
# The QHG_LOCATION tag can be used to specify the location (absolute path
# including file name) of Qt's qhelpgenerator. If non-empty doxygen will try to
# run qhelpgenerator on the generated .qhp file.
# This tag requires that the tag GENERATE_QHP is set to YES.
QHG_LOCATION =
@@ -1472,6 +1575,17 @@ TREEVIEW_WIDTH = 250
EXT_LINKS_IN_WINDOW = NO
# If the HTML_FORMULA_FORMAT option is set to svg, doxygen will use the pdf2svg
# tool (see https://github.com/dawbarton/pdf2svg) or inkscape (see
# https://inkscape.org) to generate formulas as SVG images instead of PNGs for
# the HTML output. These images will generally look nicer at scaled resolutions.
# Possible values are: png (the default) and svg (looks nicer but requires the
# pdf2svg or inkscape tool).
# The default value is: png.
# This tag requires that the tag GENERATE_HTML is set to YES.
HTML_FORMULA_FORMAT = png
# Use this tag to change the font size of LaTeX formulas included as images in
# the HTML documentation. When you change the font size after a successful
# doxygen run you need to manually remove any form_*.png images from the HTML
@@ -1481,7 +1595,7 @@ EXT_LINKS_IN_WINDOW = NO
FORMULA_FONTSIZE = 10
# Use the FORMULA_TRANPARENT tag to determine whether or not the images
# Use the FORMULA_TRANSPARENT tag to determine whether or not the images
# generated for formulas are transparent PNGs. Transparent PNGs are not
# supported properly for IE 6.0, but are supported on all modern browsers.
#
@@ -1492,8 +1606,14 @@ FORMULA_FONTSIZE = 10
FORMULA_TRANSPARENT = YES
# The FORMULA_MACROFILE can contain LaTeX \newcommand and \renewcommand commands
# to create new LaTeX commands to be used in formulas as building blocks. See
# the section "Including formulas" for details.
FORMULA_MACROFILE =
# Enable the USE_MATHJAX option to render LaTeX formulas using MathJax (see
# http://www.mathjax.org) which uses client side Javascript for the rendering
# https://www.mathjax.org) which uses client side JavaScript for the rendering
# instead of using pre-rendered bitmaps. Use this if you do not have LaTeX
# installed or if you want to formulas look prettier in the HTML output. When
# enabled you may also need to install MathJax separately and configure the path
@@ -1505,7 +1625,7 @@ USE_MATHJAX = NO
# When MathJax is enabled you can set the default output format to be used for
# the MathJax output. See the MathJax site (see:
# http://docs.mathjax.org/en/latest/output.html) for more details.
# http://docs.mathjax.org/en/v2.7-latest/output.html) for more details.
# Possible values are: HTML-CSS (which is slower, but has the best
# compatibility), NativeMML (i.e. MathML) and SVG.
# The default value is: HTML-CSS.
@@ -1520,8 +1640,8 @@ MATHJAX_FORMAT = HTML-CSS
# MATHJAX_RELPATH should be ../mathjax. The default value points to the MathJax
# Content Delivery Network so you can quickly see the result without installing
# MathJax. However, it is strongly recommended to install a local copy of
# MathJax from http://www.mathjax.org before deployment.
# The default value is: http://cdn.mathjax.org/mathjax/latest.
# MathJax from https://www.mathjax.org before deployment.
# The default value is: https://cdn.jsdelivr.net/npm/mathjax@2.
# This tag requires that the tag USE_MATHJAX is set to YES.
MATHJAX_RELPATH = http://cdn.mathjax.org/mathjax/latest
@@ -1535,7 +1655,8 @@ MATHJAX_EXTENSIONS =
# The MATHJAX_CODEFILE tag can be used to specify a file with javascript pieces
# of code that will be used on startup of the MathJax code. See the MathJax site
# (see: http://docs.mathjax.org/en/latest/output.html) for more details. For an
# (see:
# http://docs.mathjax.org/en/v2.7-latest/output.html) for more details. For an
# example see the documentation.
# This tag requires that the tag USE_MATHJAX is set to YES.
@@ -1563,7 +1684,7 @@ MATHJAX_CODEFILE =
SEARCHENGINE = NO
# When the SERVER_BASED_SEARCH tag is enabled the search engine will be
# implemented using a web server instead of a web client using Javascript. There
# implemented using a web server instead of a web client using JavaScript. There
# are two flavors of web server based searching depending on the EXTERNAL_SEARCH
# setting. When disabled, doxygen will generate a PHP script for searching and
# an index file used by the script. When EXTERNAL_SEARCH is enabled the indexing
@@ -1582,7 +1703,8 @@ SERVER_BASED_SEARCH = NO
#
# Doxygen ships with an example indexer (doxyindexer) and search engine
# (doxysearch.cgi) which are based on the open source search engine library
# Xapian (see: http://xapian.org/).
# Xapian (see:
# https://xapian.org/).
#
# See the section "External Indexing and Searching" for details.
# The default value is: NO.
@@ -1595,8 +1717,9 @@ EXTERNAL_SEARCH = NO
#
# Doxygen ships with an example indexer (doxyindexer) and search engine
# (doxysearch.cgi) which are based on the open source search engine library
# Xapian (see: http://xapian.org/). See the section "External Indexing and
# Searching" for details.
# Xapian (see:
# https://xapian.org/). See the section "External Indexing and Searching" for
# details.
# This tag requires that the tag SEARCHENGINE is set to YES.
SEARCHENGINE_URL =
@@ -1647,21 +1770,35 @@ LATEX_OUTPUT = latex
# The LATEX_CMD_NAME tag can be used to specify the LaTeX command name to be
# invoked.
#
# Note that when enabling USE_PDFLATEX this option is only used for generating
# bitmaps for formulas in the HTML output, but not in the Makefile that is
# written to the output directory.
# The default file is: latex.
# Note that when not enabling USE_PDFLATEX the default is latex when enabling
# USE_PDFLATEX the default is pdflatex and when in the later case latex is
# chosen this is overwritten by pdflatex. For specific output languages the
# default can have been set differently, this depends on the implementation of
# the output language.
# This tag requires that the tag GENERATE_LATEX is set to YES.
LATEX_CMD_NAME = latex
# The MAKEINDEX_CMD_NAME tag can be used to specify the command name to generate
# index for LaTeX.
# Note: This tag is used in the Makefile / make.bat.
# See also: LATEX_MAKEINDEX_CMD for the part in the generated output file
# (.tex).
# The default file is: makeindex.
# This tag requires that the tag GENERATE_LATEX is set to YES.
MAKEINDEX_CMD_NAME = makeindex
# The LATEX_MAKEINDEX_CMD tag can be used to specify the command name to
# generate index for LaTeX. In case there is no backslash (\) as first character
# it will be automatically added in the LaTeX code.
# Note: This tag is used in the generated output file (.tex).
# See also: MAKEINDEX_CMD_NAME for the part in the Makefile / make.bat.
# The default value is: makeindex.
# This tag requires that the tag GENERATE_LATEX is set to YES.
LATEX_MAKEINDEX_CMD = makeindex
# If the COMPACT_LATEX tag is set to YES, doxygen generates more compact LaTeX
# documents. This may be useful for small projects and may help to save some
# trees in general.
@@ -1746,9 +1883,11 @@ LATEX_EXTRA_FILES =
PDF_HYPERLINKS = NO
# If the USE_PDFLATEX tag is set to YES, doxygen will use pdflatex to generate
# the PDF file directly from the LaTeX files. Set this option to YES, to get a
# higher quality PDF documentation.
# If the USE_PDFLATEX tag is set to YES, doxygen will use the engine as
# specified with LATEX_CMD_NAME to generate the PDF file directly from the LaTeX
# files. Set this option to YES, to get a higher quality PDF documentation.
#
# See also section LATEX_CMD_NAME for selecting the engine.
# The default value is: YES.
# This tag requires that the tag GENERATE_LATEX is set to YES.
@@ -1782,7 +1921,7 @@ LATEX_SOURCE_CODE = NO
# The LATEX_BIB_STYLE tag can be used to specify the style to use for the
# bibliography, e.g. plainnat, or ieeetr. See
# http://en.wikipedia.org/wiki/BibTeX and \cite for more info.
# https://en.wikipedia.org/wiki/BibTeX and \cite for more info.
# The default value is: plain.
# This tag requires that the tag GENERATE_LATEX is set to YES.
@@ -1796,6 +1935,14 @@ LATEX_BIB_STYLE = plain
LATEX_TIMESTAMP = NO
# The LATEX_EMOJI_DIRECTORY tag is used to specify the (relative or absolute)
# path from which the emoji images will be read. If a relative path is entered,
# it will be relative to the LATEX_OUTPUT directory. If left blank the
# LATEX_OUTPUT directory will be used.
# This tag requires that the tag GENERATE_LATEX is set to YES.
LATEX_EMOJI_DIRECTORY =
#---------------------------------------------------------------------------
# Configuration options related to the RTF output
#---------------------------------------------------------------------------
@@ -1835,9 +1982,9 @@ COMPACT_RTF = NO
RTF_HYPERLINKS = NO
# Load stylesheet definitions from file. Syntax is similar to doxygen's config
# file, i.e. a series of assignments. You only have to provide replacements,
# missing definitions are set to their default value.
# Load stylesheet definitions from file. Syntax is similar to doxygen's
# configuration file, i.e. a series of assignments. You only have to provide
# replacements, missing definitions are set to their default value.
#
# See also section "Doxygen usage" for information on how to generate the
# default style sheet that doxygen normally uses.
@@ -1846,8 +1993,8 @@ RTF_HYPERLINKS = NO
RTF_STYLESHEET_FILE =
# Set optional variables used in the generation of an RTF document. Syntax is
# similar to doxygen's config file. A template extensions file can be generated
# using doxygen -e rtf extensionFile.
# similar to doxygen's configuration file. A template extensions file can be
# generated using doxygen -e rtf extensionFile.
# This tag requires that the tag GENERATE_RTF is set to YES.
RTF_EXTENSIONS_FILE =
@@ -1933,6 +2080,13 @@ XML_OUTPUT = xml
XML_PROGRAMLISTING = YES
# If the XML_NS_MEMB_FILE_SCOPE tag is set to YES, doxygen will include
# namespace members in file scope as well, matching the HTML output.
# The default value is: NO.
# This tag requires that the tag GENERATE_XML is set to YES.
XML_NS_MEMB_FILE_SCOPE = NO
#---------------------------------------------------------------------------
# Configuration options related to the DOCBOOK output
#---------------------------------------------------------------------------
@@ -1965,9 +2119,9 @@ DOCBOOK_PROGRAMLISTING = NO
#---------------------------------------------------------------------------
# If the GENERATE_AUTOGEN_DEF tag is set to YES, doxygen will generate an
# AutoGen Definitions (see http://autogen.sf.net) file that captures the
# structure of the code including all documentation. Note that this feature is
# still experimental and incomplete at the moment.
# AutoGen Definitions (see http://autogen.sourceforge.net/) file that captures
# the structure of the code including all documentation. Note that this feature
# is still experimental and incomplete at the moment.
# The default value is: NO.
GENERATE_AUTOGEN_DEF = NO
@@ -2079,7 +2233,7 @@ PREDEFINED = U_EXPORT2= \
U_CDECL_BEGIN= \
U_CDECL_END= \
"U_NAMESPACE_BEGIN=namespace icu{" \
"U_NAMESPACE_END=}" \
U_NAMESPACE_END=} \
U_SHOW_CPLUSPLUS_API=1 \
U_DEFINE_LOCAL_OPEN_POINTER()= \
U_IN_DOXYGEN=1 \
@@ -2129,7 +2283,7 @@ TAGFILES =
# tag file that is based on the input files it reads. See section "Linking to
# external documentation" for more information about the usage of tag files.
GENERATE_TAGFILE = "@builddir@/doc/html/icudocs.tag"
GENERATE_TAGFILE = @builddir@/doc/html/icudocs.tag
# If the ALLEXTERNALS tag is set to YES, all external class will be listed in
# the class index. If set to NO, only the inherited external classes will be
@@ -2152,12 +2306,6 @@ EXTERNAL_GROUPS = YES
EXTERNAL_PAGES = YES
# The PERL_PATH should be the absolute path and name of the perl script
# interpreter (i.e. the result of 'which perl').
# The default file (with absolute path) is: /usr/bin/perl.
PERL_PATH = /usr/bin/perl
#---------------------------------------------------------------------------
# Configuration options related to the dot tool
#---------------------------------------------------------------------------
@@ -2171,15 +2319,6 @@ PERL_PATH = /usr/bin/perl
CLASS_DIAGRAMS = YES
# You can define message sequence charts within doxygen comments using the \msc
# command. Doxygen will then run the mscgen tool (see:
# http://www.mcternan.me.uk/mscgen/)) to produce the chart and insert it in the
# documentation. The MSCGEN_PATH tag allows you to specify the directory where
# the mscgen tool resides. If left empty the tool is assumed to be found in the
# default search path.
MSCGEN_PATH =
# You can include diagrams made with dia in doxygen documentation. Doxygen will
# then run dia to produce the diagram and insert it in the documentation. The
# DIA_PATH tag allows you to specify the directory where the dia binary resides.
@@ -2277,10 +2416,32 @@ UML_LOOK = NO
# but if the number exceeds 15, the total amount of fields shown is limited to
# 10.
# Minimum value: 0, maximum value: 100, default value: 10.
# This tag requires that the tag HAVE_DOT is set to YES.
# This tag requires that the tag UML_LOOK is set to YES.
UML_LIMIT_NUM_FIELDS = 10
# If the DOT_UML_DETAILS tag is set to NO, doxygen will show attributes and
# methods without types and arguments in the UML graphs. If the DOT_UML_DETAILS
# tag is set to YES, doxygen will add type and arguments for attributes and
# methods in the UML graphs. If the DOT_UML_DETAILS tag is set to NONE, doxygen
# will not generate fields with class member information in the UML graphs. The
# class diagrams will look similar to the default class diagrams but using UML
# notation for the relationships.
# Possible values are: NO, YES and NONE.
# The default value is: NO.
# This tag requires that the tag UML_LOOK is set to YES.
DOT_UML_DETAILS = NO
# The DOT_WRAP_THRESHOLD tag can be used to set the maximum number of characters
# to display on a single line. If the actual line length exceeds this threshold
# significantly it will wrapped across multiple lines. Some heuristics are apply
# to avoid ugly line breaks.
# Minimum value: 0, maximum value: 1000, default value: 17.
# This tag requires that the tag HAVE_DOT is set to YES.
DOT_WRAP_THRESHOLD = 17
# If the TEMPLATE_RELATIONS tag is set to YES then the inheritance and
# collaboration graphs will show the relations between templates and their
# instances.
@@ -2472,9 +2633,11 @@ DOT_MULTI_TARGETS = NO
GENERATE_LEGEND = YES
# If the DOT_CLEANUP tag is set to YES, doxygen will remove the intermediate dot
# If the DOT_CLEANUP tag is set to YES, doxygen will remove the intermediate
# files that are used to generate the various graphs.
#
# Note: This setting is not only used for dot files but also for msc and
# plantuml temporary files.
# The default value is: YES.
# This tag requires that the tag HAVE_DOT is set to YES.
DOT_CLEANUP = YES

4
intl/icu/source/Makefile.in
View File

@@ -133,7 +133,7 @@ doc/html/index.html: Doxyfile $(wildcard ./common/unicode/platform.h $(srcdir)/c
Doxyfile: $(srcdir)/Doxyfile.in
CONFIG_FILES=$@ CONFIG_HEADERS= $(SHELL) ./config.status
$(DOCZIP): doc
$(DOCZIP): doc-searchengine
-$(RMV) $(DOCZIP)
( cd doc/html ; zip -r ../../$(DOCZIP) * )
endif
@@ -210,7 +210,7 @@ endif
ifeq ($(DOXYGEN),)
install-doc:
else
install-doc: doc
install-doc: doc-searchengine
$(RM) -r $(DESTDIR)$(docdir)/$(docsubdir)
$(MKINSTALLDIRS) $(DESTDIR)$(docdir)/$(docsubdir)
$(INSTALL_DATA) $(docfiles) $(DESTDIR)$(docdir)/$(docsubdir)

2
intl/icu/source/acinclude.m4
View File

@@ -449,7 +449,7 @@ AC_DEFUN([AC_CHECK_64BIT_LIBS],
AC_DEFUN([AC_CHECK_STRICT_COMPILE],
[
AC_MSG_CHECKING([whether strict compiling is on])
AC_ARG_ENABLE(strict,[ --enable-strict compile with strict compiler options [default=yes]], [
AC_ARG_ENABLE(strict,[ --disable-strict do not compile with strict compiler options], [
if test "$enableval" = no
then
ac_use_strict_options=no

2
intl/icu/source/allinone/Build.Windows.IcuVersion.props
View File

@@ -3,6 +3,6 @@
<Project ToolsVersion="14.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<!-- This file is used to set the ICU Major Version number, which is used as a suffix on various file names in other Visual Studio projects. -->
<PropertyGroup>
<IcuMajorVersion>76</IcuMajorVersion>
<IcuMajorVersion>77</IcuMajorVersion>
</PropertyGroup>
</Project>

57
intl/icu/source/common/brkiter.cpp
View File

@@ -59,7 +59,7 @@ BreakIterator::buildInstance(const Locale& loc, const char *type, UErrorCode &st
{
char fnbuff[256];
char ext[4]={'\0'};
CharString actualLocale;
CharString actual;
int32_t size;
const char16_t* brkfname = nullptr;
UResourceBundle brkRulesStack;
@@ -94,7 +94,7 @@ BreakIterator::buildInstance(const Locale& loc, const char *type, UErrorCode &st
// Use the string if we found it
if (U_SUCCESS(status) && brkfname) {
actualLocale.append(ures_getLocaleInternal(brkName, &status), -1, status);
actual.append(ures_getLocaleInternal(brkName, &status), -1, status);
char16_t* extStart=u_strchr(brkfname, 0x002e);
int len = 0;
@@ -124,9 +124,8 @@ BreakIterator::buildInstance(const Locale& loc, const char *type, UErrorCode &st
U_LOCALE_BASED(locBased, *(BreakIterator*)result);
locBased.setLocaleIDs(ures_getLocaleByType(b, ULOC_VALID_LOCALE, &status),
actualLocale.data());
uprv_strncpy(result->requestLocale, loc.getName(), ULOC_FULLNAME_CAPACITY);
result->requestLocale[ULOC_FULLNAME_CAPACITY-1] = 0; // always terminate
actual.data(), status);
LocaleBased::setLocaleID(loc.getName(), result->requestLocale, status);
}
ures_close(b);
@@ -206,26 +205,32 @@ BreakIterator::getAvailableLocales(int32_t& count)
BreakIterator::BreakIterator()
{
*validLocale = *actualLocale = *requestLocale = 0;
}
BreakIterator::BreakIterator(const BreakIterator &other) : UObject(other) {
uprv_strncpy(actualLocale, other.actualLocale, sizeof(actualLocale));
uprv_strncpy(validLocale, other.validLocale, sizeof(validLocale));
uprv_strncpy(requestLocale, other.requestLocale, sizeof(requestLocale));
UErrorCode status = U_ZERO_ERROR;
U_LOCALE_BASED(locBased, *this);
locBased.setLocaleIDs(other.validLocale, other.actualLocale, status);
LocaleBased::setLocaleID(other.requestLocale, requestLocale, status);
U_ASSERT(U_SUCCESS(status));
}
BreakIterator &BreakIterator::operator =(const BreakIterator &other) {
if (this != &other) {
uprv_strncpy(actualLocale, other.actualLocale, sizeof(actualLocale));
uprv_strncpy(validLocale, other.validLocale, sizeof(validLocale));
uprv_strncpy(requestLocale, other.requestLocale, sizeof(requestLocale));
UErrorCode status = U_ZERO_ERROR;
U_LOCALE_BASED(locBased, *this);
locBased.setLocaleIDs(other.validLocale, other.actualLocale, status);
LocaleBased::setLocaleID(other.requestLocale, requestLocale, status);
U_ASSERT(U_SUCCESS(status));
}
return *this;
}
BreakIterator::~BreakIterator()
{
delete validLocale;
delete actualLocale;
delete requestLocale;
}
// ------------------------------------------
@@ -394,7 +399,7 @@ BreakIterator::createInstance(const Locale& loc, int32_t kind, UErrorCode& statu
// revisit this in ICU 3.0 and clean it up/fix it/remove it.
if (U_SUCCESS(status) && (result != nullptr) && *actualLoc.getName() != 0) {
U_LOCALE_BASED(locBased, *result);
locBased.setLocaleIDs(actualLoc.getName(), actualLoc.getName());
locBased.setLocaleIDs(actualLoc.getName(), actualLoc.getName(), status);
}
return result;
}
@@ -488,6 +493,7 @@ BreakIterator::makeInstance(const Locale& loc, int32_t kind, UErrorCode& status)
}
if (U_FAILURE(status)) {
delete result;
return nullptr;
}
@@ -496,20 +502,25 @@ BreakIterator::makeInstance(const Locale& loc, int32_t kind, UErrorCode& status)
Locale
BreakIterator::getLocale(ULocDataLocaleType type, UErrorCode& status) const {
if (type == ULOC_REQUESTED_LOCALE) {
return {requestLocale};
if (U_FAILURE(status)) {
return Locale::getRoot();
}
U_LOCALE_BASED(locBased, *this);
return locBased.getLocale(type, status);
if (type == ULOC_REQUESTED_LOCALE) {
return requestLocale == nullptr ?
Locale::getRoot() : Locale(requestLocale->data());
}
return LocaleBased::getLocale(validLocale, actualLocale, type, status);
}
const char *
BreakIterator::getLocaleID(ULocDataLocaleType type, UErrorCode& status) const {
if (type == ULOC_REQUESTED_LOCALE) {
return requestLocale;
if (U_FAILURE(status)) {
return nullptr;
}
U_LOCALE_BASED(locBased, *this);
return locBased.getLocaleID(type, status);
if (type == ULOC_REQUESTED_LOCALE) {
return requestLocale == nullptr ? "" : requestLocale->data();
}
return LocaleBased::getLocaleID(validLocale, actualLocale, type, status);
}
@@ -536,8 +547,10 @@ int32_t BreakIterator::getRuleStatusVec(int32_t *fillInVec, int32_t capacity, UE
}
BreakIterator::BreakIterator (const Locale& valid, const Locale& actual) {
UErrorCode status = U_ZERO_ERROR;
U_LOCALE_BASED(locBased, (*this));
locBased.setLocaleIDs(valid, actual);
locBased.setLocaleIDs(valid.getName(), actual.getName(), status);
U_ASSERT(U_SUCCESS(status));
}
U_NAMESPACE_END

11
intl/icu/source/common/charstr.cpp
View File

@@ -70,6 +70,15 @@ CharString &CharString::copyFrom(const CharString &s, UErrorCode &errorCode) {
return *this;
}
CharString &CharString::copyFrom(StringPiece s, UErrorCode &errorCode) {
if (U_FAILURE(errorCode)) {
return *this;
}
len = 0;
append(s, errorCode);
return *this;
}
int32_t CharString::lastIndexOf(char c) const {
for(int32_t i=len; i>0;) {
if(buffer[--i]==c) {
@@ -143,7 +152,7 @@ CharString &CharString::append(const char *s, int32_t sLength, UErrorCode &error
return *this;
}
CharString &CharString::appendNumber(int32_t number, UErrorCode &status) {
CharString &CharString::appendNumber(int64_t number, UErrorCode &status) {
if (number < 0) {
this->append('-', status);
if (U_FAILURE(status)) {

3
intl/icu/source/common/charstr.h
View File

@@ -74,6 +74,7 @@ public:
* use a UErrorCode where memory allocations might be needed.
*/
CharString &copyFrom(const CharString &other, UErrorCode &errorCode);
CharString &copyFrom(StringPiece s, UErrorCode &errorCode);
UBool isEmpty() const { return len==0; }
int32_t length() const { return len; }
@@ -135,7 +136,7 @@ public:
}
CharString &append(const char *s, int32_t sLength, UErrorCode &status);
CharString &appendNumber(int32_t number, UErrorCode &status);
CharString &appendNumber(int64_t number, UErrorCode &status);
/**
* Returns a writable buffer for appending and writes the buffer's capacity to

2311
intl/icu/source/common/localefallback_data.h
View File

File diff suppressed because it is too large Load Diff

70
intl/icu/source/common/locbased.cpp
View File

@@ -12,44 +12,84 @@
*/
#include "locbased.h"
#include "cstring.h"
#include "charstr.h"
U_NAMESPACE_BEGIN
Locale LocaleBased::getLocale(ULocDataLocaleType type, UErrorCode& status) const {
const char* id = getLocaleID(type, status);
Locale LocaleBased::getLocale(const CharString* valid, const CharString* actual,
ULocDataLocaleType type, UErrorCode& status) {
const char* id = getLocaleID(valid, actual, type, status);
return Locale(id != nullptr ? id : "");
}
const char* LocaleBased::getLocaleID(ULocDataLocaleType type, UErrorCode& status) const {
const char* LocaleBased::getLocaleID(const CharString* valid, const CharString* actual,
ULocDataLocaleType type, UErrorCode& status) {
if (U_FAILURE(status)) {
return nullptr;
}
switch(type) {
case ULOC_VALID_LOCALE:
return valid;
return valid == nullptr ? "" : valid->data();
case ULOC_ACTUAL_LOCALE:
return actual;
return actual == nullptr ? "" : actual->data();
default:
status = U_ILLEGAL_ARGUMENT_ERROR;
return nullptr;
}
}
void LocaleBased::setLocaleIDs(const char* validID, const char* actualID) {
if (validID != nullptr) {
uprv_strncpy(valid, validID, ULOC_FULLNAME_CAPACITY);
valid[ULOC_FULLNAME_CAPACITY-1] = 0; // always terminate
void LocaleBased::setLocaleIDs(const CharString* validID, const CharString* actualID, UErrorCode& status) {
setValidLocaleID(validID, status);
setActualLocaleID(actualID,status);
}
void LocaleBased::setLocaleIDs(const char* validID, const char* actualID, UErrorCode& status) {
setValidLocaleID(validID, status);
setActualLocaleID(actualID,status);
}
void LocaleBased::setLocaleID(const char* id, CharString*& dest, UErrorCode& status) {
if (U_FAILURE(status)) { return; }
if (id == nullptr || *id == 0) {
delete dest;
dest = nullptr;
} else {
if (dest == nullptr) {
dest = new CharString(id, status);
if (dest == nullptr) {
status = U_MEMORY_ALLOCATION_ERROR;
return;
}
} else {
dest->copyFrom(id, status);
}
if (actualID != nullptr) {
uprv_strncpy(actual, actualID, ULOC_FULLNAME_CAPACITY);
actual[ULOC_FULLNAME_CAPACITY-1] = 0; // always terminate
}
}
void LocaleBased::setLocaleIDs(const Locale& validID, const Locale& actualID) {
uprv_strcpy(valid, validID.getName());
uprv_strcpy(actual, actualID.getName());
void LocaleBased::setLocaleID(const CharString* id, CharString*& dest, UErrorCode& status) {
if (U_FAILURE(status)) { return; }
if (id == nullptr || id->isEmpty()) {
delete dest;
dest = nullptr;
} else {
if (dest == nullptr) {
dest = new CharString(*id, status);
if (dest == nullptr) {
status = U_MEMORY_ALLOCATION_ERROR;
return;
}
} else {
dest->copyFrom(*id, status);
}
}
}
bool LocaleBased::equalIDs(const CharString* left, const CharString* right) {
// true if both are nullptr
if (left == nullptr && right == nullptr) return true;
// false if only one is nullptr
if (left == nullptr || right == nullptr) return false;
return *left == *right;
}
U_NAMESPACE_END

62
intl/icu/source/common/locbased.h
View File

@@ -19,13 +19,14 @@
/**
* Macro to declare a locale LocaleBased wrapper object for the given
* object, which must have two members named `validLocale' and
* `actualLocale' of size ULOC_FULLNAME_CAPACITY
* `actualLocale' of which are pointers to the internal icu::CharString.
*/
#define U_LOCALE_BASED(varname, objname) \
LocaleBased varname((objname).validLocale, (objname).actualLocale)
U_NAMESPACE_BEGIN
class CharString;
/**
* A utility class that unifies the implementation of getLocale() by
* various ICU services. This class is likely to be removed in the
@@ -41,33 +42,35 @@ class U_COMMON_API LocaleBased : public UMemory {
* Construct a LocaleBased wrapper around the two pointers. These
* will be aliased for the lifetime of this object.
*/
inline LocaleBased(char* validAlias, char* actualAlias);
/**
* Construct a LocaleBased wrapper around the two const pointers.
* These will be aliased for the lifetime of this object.
*/
inline LocaleBased(const char* validAlias, const char* actualAlias);
inline LocaleBased(CharString*& validAlias, CharString*& actualAlias);
/**
* Return locale meta-data for the service object wrapped by this
* object. Either the valid or the actual locale may be
* retrieved.
* @param valid The valid locale.
* @param actual The actual locale.
* @param type either ULOC_VALID_LOCALE or ULOC_ACTUAL_LOCALE
* @param status input-output error code
* @return the indicated locale
*/
Locale getLocale(ULocDataLocaleType type, UErrorCode& status) const;
static Locale getLocale(
const CharString* valid, const CharString* actual,
ULocDataLocaleType type, UErrorCode& status);
/**
* Return the locale ID for the service object wrapped by this
* object. Either the valid or the actual locale may be
* retrieved.
* @param valid The valid locale.
* @param actual The actual locale.
* @param type either ULOC_VALID_LOCALE or ULOC_ACTUAL_LOCALE
* @param status input-output error code
* @return the indicated locale ID
*/
const char* getLocaleID(ULocDataLocaleType type, UErrorCode& status) const;
static const char* getLocaleID(
const CharString* valid, const CharString* actual,
ULocDataLocaleType type, UErrorCode& status);
/**
* Set the locale meta-data for the service object wrapped by this
@@ -75,31 +78,40 @@ class U_COMMON_API LocaleBased : public UMemory {
* @param valid the ID of the valid locale
* @param actual the ID of the actual locale
*/
void setLocaleIDs(const char* valid, const char* actual);
void setLocaleIDs(const char* valid, const char* actual, UErrorCode& status);
void setLocaleIDs(const CharString* valid, const CharString* actual, UErrorCode& status);
/**
* Set the locale meta-data for the service object wrapped by this
* object.
* @param valid the ID of the valid locale
* @param actual the ID of the actual locale
*/
void setLocaleIDs(const Locale& valid, const Locale& actual);
static void setLocaleID(const char* id, CharString*& dest, UErrorCode& status);
static void setLocaleID(const CharString* id, CharString*& dest, UErrorCode& status);
static bool equalIDs(const CharString* left, const CharString* right);
private:
char* valid;
void setValidLocaleID(const CharString* id, UErrorCode& status);
void setActualLocaleID(const CharString* id, UErrorCode& status);
void setValidLocaleID(const char* id, UErrorCode& status);
void setActualLocaleID(const char* id, UErrorCode& status);
char* actual;
CharString*& valid;
CharString*& actual;
};
inline LocaleBased::LocaleBased(char* validAlias, char* actualAlias) :
inline LocaleBased::LocaleBased(CharString*& validAlias, CharString*& actualAlias) :
valid(validAlias), actual(actualAlias) {
}
inline LocaleBased::LocaleBased(const char* validAlias,
const char* actualAlias) :
// ugh: cast away const
valid(const_cast<char*>(validAlias)), actual(const_cast<char*>(actualAlias)) {
inline void LocaleBased::setValidLocaleID(const CharString* id, UErrorCode& status) {
setLocaleID(id, valid, status);
}
inline void LocaleBased::setActualLocaleID(const CharString* id, UErrorCode& status) {
setLocaleID(id, actual, status);
}
inline void LocaleBased::setValidLocaleID(const char* id, UErrorCode& status) {
setLocaleID(id, valid, status);
}
inline void LocaleBased::setActualLocaleID(const char* id, UErrorCode& status) {
setLocaleID(id, actual, status);
}
U_NAMESPACE_END

8
intl/icu/source/common/locdispnames.cpp
View File

@@ -19,6 +19,8 @@
* that then do not depend on resource bundle code and display name data.
*/
#include <string_view>
#include "unicode/utypes.h"
#include "unicode/brkiter.h"
#include "unicode/locid.h"
@@ -359,7 +361,7 @@ _getStringOrCopyKey(const char *path, const char *locale,
return u_terminateUChars(dest, destCapacity, length, &errorCode);
}
using UDisplayNameGetter = icu::CharString(const char*, UErrorCode&);
using UDisplayNameGetter = icu::CharString(std::string_view, UErrorCode&);
int32_t
_getDisplayNameForComponent(const char *locale,
@@ -377,6 +379,10 @@ _getDisplayNameForComponent(const char *locale,
return 0;
}
if (locale == nullptr) {
locale = uloc_getDefault();
}
localStatus = U_ZERO_ERROR;
icu::CharString localeBuffer = (*getter)(locale, localStatus);
if (U_FAILURE(localStatus)) {

43
intl/icu/source/common/locid.cpp
View File

@@ -1828,8 +1828,13 @@ ulocimp_isCanonicalizedLocaleForTest(const char* localeName)
U_NAMESPACE_BEGIN
/*This function initializes a Locale from a C locale ID*/
Locale& Locale::init(const char* localeID, UBool canonicalize)
{
return localeID == nullptr ? *this = getDefault() : init(StringPiece{localeID}, canonicalize);
}
/*This function initializes a Locale from a C locale ID*/
Locale& Locale::init(StringPiece localeID, UBool canonicalize)
{
fIsBogus = false;
/* Free our current storage */
@@ -1854,19 +1859,28 @@ Locale& Locale::init(const char* localeID, UBool canonicalize)
int32_t length;
UErrorCode err;
if(localeID == nullptr) {
// not an error, just set the default locale
return *this = getDefault();
}
/* preset all fields to empty */
language[0] = script[0] = country[0] = 0;
const auto parse = [canonicalize](std::string_view localeID,
char* name,
int32_t nameCapacity,
UErrorCode& status) {
return ByteSinkUtil::viaByteSinkToTerminatedChars(
name, nameCapacity,
[&](ByteSink& sink, UErrorCode& status) {
if (canonicalize) {
ulocimp_canonicalize(localeID, sink, status);
} else {
ulocimp_getName(localeID, sink, status);
}
},
status);
};
// "canonicalize" the locale ID to ICU/Java format
err = U_ZERO_ERROR;
length = canonicalize ?
uloc_canonicalize(localeID, fullName, sizeof(fullNameBuffer), &err) :
uloc_getName(localeID, fullName, sizeof(fullNameBuffer), &err);
length = parse(localeID, fullName, sizeof fullNameBuffer, err);
if (err == U_BUFFER_OVERFLOW_ERROR || length >= static_cast<int32_t>(sizeof(fullNameBuffer))) {
U_ASSERT(baseName == nullptr);
@@ -1877,9 +1891,7 @@ Locale& Locale::init(const char* localeID, UBool canonicalize)
}
fullName = newFullName;
err = U_ZERO_ERROR;
length = canonicalize ?
uloc_canonicalize(localeID, fullName, length+1, &err) :
uloc_getName(localeID, fullName, length+1, &err);
length = parse(localeID, fullName, length + 1, err);
}
if(U_FAILURE(err) || err == U_STRING_NOT_TERMINATED_WARNING) {
/* should never occur */
@@ -2200,6 +2212,13 @@ Locale::createFromName (const char *name)
}
}
Locale U_EXPORT2
Locale::createFromName(StringPiece name) {
Locale loc("");
loc.init(name, false);
return loc;
}
Locale U_EXPORT2
Locale::createCanonical(const char* name) {
Locale loc("");

16
intl/icu/source/common/loclikely.cpp
View File

@@ -300,6 +300,9 @@ ulocimp_addLikelySubtags(const char* localeID,
icu::ByteSink& sink,
UErrorCode& status) {
if (U_FAILURE(status)) { return; }
if (localeID == nullptr) {
localeID = uloc_getDefault();
}
icu::CharString localeBuffer = ulocimp_canonicalize(localeID, status);
_uloc_addLikelySubtags(localeBuffer.data(), sink, status);
}
@@ -334,6 +337,9 @@ ulocimp_minimizeSubtags(const char* localeID,
bool favorScript,
UErrorCode& status) {
if (U_FAILURE(status)) { return; }
if (localeID == nullptr) {
localeID = uloc_getDefault();
}
icu::CharString localeBuffer = ulocimp_canonicalize(localeID, status);
_uloc_minimizeSubtags(localeBuffer.data(), sink, favorScript, status);
}
@@ -349,7 +355,9 @@ uloc_isRightToLeft(const char *locale) {
UErrorCode errorCode = U_ZERO_ERROR;
icu::CharString lang;
icu::CharString script;
ulocimp_getSubtags(locale, &lang, &script, nullptr, nullptr, nullptr, errorCode);
ulocimp_getSubtags(
locale == nullptr ? uloc_getDefault() : locale,
&lang, &script, nullptr, nullptr, nullptr, errorCode);
if (U_FAILURE(errorCode) || script.isEmpty()) {
// Fastpath: We know the likely scripts and their writing direction
// for some common languages.
@@ -369,7 +377,7 @@ uloc_isRightToLeft(const char *locale) {
if (U_FAILURE(errorCode)) {
return false;
}
ulocimp_getSubtags(likely.data(), nullptr, &script, nullptr, nullptr, nullptr, errorCode);
ulocimp_getSubtags(likely.toStringPiece(), nullptr, &script, nullptr, nullptr, nullptr, errorCode);
if (U_FAILURE(errorCode) || script.isEmpty()) {
return false;
}
@@ -430,7 +438,7 @@ ulocimp_getRegionForSupplementalData(const char *localeID, bool inferRegion,
icu::CharString rgBuf = GetRegionFromKey(localeID, "rg", status);
if (U_SUCCESS(status) && rgBuf.isEmpty()) {
// No valid rg keyword value, try for unicode_region_subtag
rgBuf = ulocimp_getRegion(localeID, status);
rgBuf = ulocimp_getRegion(localeID == nullptr ? uloc_getDefault() : localeID, status);
if (U_SUCCESS(status) && rgBuf.isEmpty() && inferRegion) {
// Second check for sd keyword value
rgBuf = GetRegionFromKey(localeID, "sd", status);
@@ -439,7 +447,7 @@ ulocimp_getRegionForSupplementalData(const char *localeID, bool inferRegion,
UErrorCode rgStatus = U_ZERO_ERROR;
icu::CharString locBuf = ulocimp_addLikelySubtags(localeID, rgStatus);
if (U_SUCCESS(rgStatus)) {
rgBuf = ulocimp_getRegion(locBuf.data(), status);
rgBuf = ulocimp_getRegion(locBuf.toStringPiece(), status);
}
}
}

2
intl/icu/source/common/loclikelysubtags.cpp
View File

@@ -527,7 +527,7 @@ LSR LikelySubtags::makeMaximizedLsrFrom(const Locale &locale,
return {};
}
const char *name = locale.getName();
if (uprv_isAtSign(name[0]) && name[1] == 'x' && name[2] == '=') { // name.startsWith("@x=")
if (!returnInputIfUnmatch && uprv_isAtSign(name[0]) && name[1] == 'x' && name[2] == '=') { // name.startsWith("@x=")
// Private use language tag x-subtag-subtag... which CLDR changes to
// und-x-subtag-subtag...
return LSR(name, "", "", LSR::EXPLICIT_LSR);

3
intl/icu/source/common/locresdata.cpp
View File

@@ -161,6 +161,9 @@ _uloc_getOrientationHelper(const char* localeId,
if (U_FAILURE(status)) { return result; }
if (localeId == nullptr) {
localeId = uloc_getDefault();
}
icu::CharString localeBuffer = ulocimp_canonicalize(localeId, status);
if (U_FAILURE(status)) { return result; }

2
intl/icu/source/common/punycode.cpp
View File

@@ -193,7 +193,7 @@ u_strToPunycode(const char16_t *src, int32_t srcLength,
return 0;
}
if(src==nullptr || srcLength<-1 || (dest==nullptr && destCapacity!=0)) {
if(src==nullptr || srcLength<-1 || destCapacity<0 || (dest==nullptr && destCapacity!=0)) {
*pErrorCode=U_ILLEGAL_ARGUMENT_ERROR;
return 0;
}

2
intl/icu/source/common/putil.cpp
View File

@@ -76,7 +76,7 @@
#include <float.h>
#ifndef U_COMMON_IMPLEMENTATION
#error U_COMMON_IMPLEMENTATION not set - must be set for all ICU source files in common/ - see https://unicode-org.github.io/icu/userguide/howtouseicu
#error U_COMMON_IMPLEMENTATION not set - must be set for all ICU source files in common/ - see https://unicode-org.github.io/icu/userguide/icu/howtouseicu.html
#endif

110
intl/icu/source/common/rbbinode.cpp
View File

@@ -47,7 +47,10 @@ static int gLastSerial = 0;
// Constructor. Just set the fields to reasonable default values.
//
//-------------------------------------------------------------------------
RBBINode::RBBINode(NodeType t) : UMemory() {
RBBINode::RBBINode(NodeType t, UErrorCode& status) : UMemory() {
if (U_FAILURE(status)) {
return;
}
#ifdef RBBI_DEBUG
fSerialNum = ++gLastSerial;
#endif
@@ -65,10 +68,13 @@ RBBINode::RBBINode(NodeType t) : UMemory() {
fVal = 0;
fPrecedence = precZero;
UErrorCode status = U_ZERO_ERROR;
fFirstPosSet = new UVector(status); // TODO - get a real status from somewhere
fFirstPosSet = new UVector(status);
fLastPosSet = new UVector(status);
fFollowPos = new UVector(status);
if (U_SUCCESS(status) &&
(fFirstPosSet == nullptr || fLastPosSet == nullptr || fFollowPos == nullptr)) {
status = U_MEMORY_ALLOCATION_ERROR;
}
if (t==opCat) {fPrecedence = precOpCat;}
else if (t==opOr) {fPrecedence = precOpOr;}
else if (t==opStart) {fPrecedence = precStart;}
@@ -77,7 +83,10 @@ RBBINode::RBBINode(NodeType t) : UMemory() {
}
RBBINode::RBBINode(const RBBINode &other) : UMemory(other) {
RBBINode::RBBINode(const RBBINode &other, UErrorCode& status) : UMemory(other) {
if (U_FAILURE(status)) {
return;
}
#ifdef RBBI_DEBUG
fSerialNum = ++gLastSerial;
#endif
@@ -94,10 +103,13 @@ RBBINode::RBBINode(const RBBINode &other) : UMemory(other) {
fVal = other.fVal;
fRuleRoot = false;
fChainIn = other.fChainIn;
UErrorCode status = U_ZERO_ERROR;
fFirstPosSet = new UVector(status); // TODO - get a real status from somewhere
fLastPosSet = new UVector(status);
fFollowPos = new UVector(status);
if (U_SUCCESS(status) &&
(fFirstPosSet == nullptr || fLastPosSet == nullptr || fFollowPos == nullptr)) {
status = U_MEMORY_ALLOCATION_ERROR;
}
}
@@ -193,27 +205,54 @@ void RBBINode::NRDeleteNode(RBBINode *node) {
// references in preparation for generating the DFA tables.
//
//-------------------------------------------------------------------------
RBBINode *RBBINode::cloneTree() {
constexpr int kRecursiveDepthLimit = 3500;
RBBINode *RBBINode::cloneTree(UErrorCode &status, int depth) {
if (U_FAILURE(status)) {
return nullptr;
}
// If the depth of the stack is too deep, we return U_INPUT_TOO_LONG_ERROR
// to avoid stack overflow crash.
if (depth > kRecursiveDepthLimit) {
status = U_INPUT_TOO_LONG_ERROR;
return nullptr;
}
RBBINode *n;
if (fType == RBBINode::varRef) {
// If the current node is a variable reference, skip over it
// and clone the definition of the variable instead.
n = fLeftChild->cloneTree();
n = fLeftChild->cloneTree(status, depth+1);
if (U_FAILURE(status)) {
return nullptr;
}
} else if (fType == RBBINode::uset) {
n = this;
} else {
n = new RBBINode(*this);
n = new RBBINode(*this, status);
if (U_FAILURE(status)) {
delete n;
return nullptr;
}
// Check for null pointer.
if (n != nullptr) {
if (n == nullptr) {
status = U_MEMORY_ALLOCATION_ERROR;
return nullptr;
}
if (fLeftChild != nullptr) {
n->fLeftChild = fLeftChild->cloneTree();
n->fLeftChild = fLeftChild->cloneTree(status, depth+1);
if (U_FAILURE(status)) {
delete n;
return nullptr;
}
n->fLeftChild->fParent = n;
}
if (fRightChild != nullptr) {
n->fRightChild = fRightChild->cloneTree();
n->fRightChild->fParent = n;
n->fRightChild = fRightChild->cloneTree(status, depth+1);
if (U_FAILURE(status)) {
delete n;
return nullptr;
}
n->fRightChild->fParent = n;
}
}
return n;
@@ -239,7 +278,6 @@ RBBINode *RBBINode::cloneTree() {
// nested references are handled by cloneTree(), not here.
//
//-------------------------------------------------------------------------
constexpr int kRecursiveDepthLimit = 3500;
RBBINode *RBBINode::flattenVariables(UErrorCode& status, int depth) {
if (U_FAILURE(status)) {
return this;
@@ -251,21 +289,34 @@ RBBINode *RBBINode::flattenVariables(UErrorCode& status, int depth) {
return this;
}
if (fType == varRef) {
RBBINode *retNode = fLeftChild->cloneTree();
if (retNode != nullptr) {
RBBINode *retNode = fLeftChild->cloneTree(status, depth+1);
if (U_FAILURE(status)) {
return this;
}
retNode->fRuleRoot = this->fRuleRoot;
retNode->fChainIn = this->fChainIn;
}
delete this; // TODO: undefined behavior. Fix.
return retNode;
}
if (fLeftChild != nullptr) {
fLeftChild = fLeftChild->flattenVariables(status, depth+1);
if (fLeftChild == nullptr) {
status = U_MEMORY_ALLOCATION_ERROR;
}
if (U_FAILURE(status)) {
return this;
}
fLeftChild->fParent = this;
}
if (fRightChild != nullptr) {
fRightChild = fRightChild->flattenVariables(status, depth+1);
if (fRightChild == nullptr) {
status = U_MEMORY_ALLOCATION_ERROR;
}
if (U_FAILURE(status)) {
return this;
}
fRightChild->fParent = this;
}
return this;
@@ -280,7 +331,16 @@ RBBINode *RBBINode::flattenVariables(UErrorCode& status, int depth) {
// the left child of the uset node.
//
//-------------------------------------------------------------------------
void RBBINode::flattenSets() {
void RBBINode::flattenSets(UErrorCode &status, int depth) {
if (U_FAILURE(status)) {
return;
}
// If the depth of the stack is too deep, we return U_INPUT_TOO_LONG_ERROR
// to avoid stack overflow crash.
if (depth > kRecursiveDepthLimit) {
status = U_INPUT_TOO_LONG_ERROR;
return;
}
U_ASSERT(fType != setRef);
if (fLeftChild != nullptr) {
@@ -288,11 +348,15 @@ void RBBINode::flattenSets() {
RBBINode *setRefNode = fLeftChild;
RBBINode *usetNode = setRefNode->fLeftChild;
RBBINode *replTree = usetNode->fLeftChild;
fLeftChild = replTree->cloneTree();
fLeftChild = replTree->cloneTree(status, depth+1);
if (U_FAILURE(status)) {
delete setRefNode;
return;
}
fLeftChild->fParent = this;
delete setRefNode;
} else {
fLeftChild->flattenSets();
fLeftChild->flattenSets(status, depth+1);
}
}
@@ -301,11 +365,15 @@ void RBBINode::flattenSets() {
RBBINode *setRefNode = fRightChild;
RBBINode *usetNode = setRefNode->fLeftChild;
RBBINode *replTree = usetNode->fLeftChild;
fRightChild = replTree->cloneTree();
fRightChild = replTree->cloneTree(status, depth+1);
if (U_FAILURE(status)) {
delete setRefNode;
return;
}
fRightChild->fParent = this;
delete setRefNode;
} else {
fRightChild->flattenSets();
fRightChild->flattenSets(status, depth+1);
}
}
}

8
intl/icu/source/common/rbbinode.h
View File

@@ -91,14 +91,14 @@ class RBBINode : public UMemory {
UVector *fFollowPos;
RBBINode(NodeType t);
RBBINode(const RBBINode &other);
RBBINode(NodeType t, UErrorCode& status);
RBBINode(const RBBINode &other, UErrorCode& status);
~RBBINode();
static void NRDeleteNode(RBBINode *node);
RBBINode *cloneTree();
RBBINode *cloneTree(UErrorCode &status, int depth=0);
RBBINode *flattenVariables(UErrorCode &status, int depth=0);
void flattenSets();
void flattenSets(UErrorCode &status, int depth=0);
void findNodes(UVector *dest, RBBINode::NodeType kind, UErrorCode &status);
#ifdef RBBI_DEBUG

15
intl/icu/source/common/rbbiscan.cpp
View File

@@ -767,15 +767,24 @@ void RBBIRuleScanner::findSetFor(const UnicodeString &s, RBBINode *node, Unicode
c = s.char32At(0);
setToAdopt = new UnicodeSet(c, c);
}
if (setToAdopt == nullptr) {
error(U_MEMORY_ALLOCATION_ERROR);
return;
}
}
//
// Make a new uset node to refer to this UnicodeSet
// This new uset node becomes the child of the caller's setReference node.
//
RBBINode *usetNode = new RBBINode(RBBINode::uset);
UErrorCode localStatus = U_ZERO_ERROR;
RBBINode *usetNode = new RBBINode(RBBINode::uset, localStatus);
if (usetNode == nullptr) {
error(U_MEMORY_ALLOCATION_ERROR);
localStatus = U_MEMORY_ALLOCATION_ERROR;
}
if (U_FAILURE(localStatus)) {
delete usetNode;
error(localStatus);
delete setToAdopt;
return;
}
@@ -1191,7 +1200,7 @@ RBBINode *RBBIRuleScanner::pushNewNode(RBBINode::NodeType t) {
return nullptr;
}
fNodeStackPtr++;
fNodeStack[fNodeStackPtr] = new RBBINode(t);
fNodeStack[fNodeStackPtr] = new RBBINode(t, *fRB->fStatus);
if (fNodeStack[fNodeStackPtr] == nullptr) {
*fRB->fStatus = U_MEMORY_ALLOCATION_ERROR;
}

12
intl/icu/source/common/rbbisetb.cpp
View File

@@ -375,7 +375,11 @@ void RBBISetBuilder::addValToSets(UVector *sets, uint32_t val) {
}
void RBBISetBuilder::addValToSet(RBBINode *usetNode, uint32_t val) {
RBBINode *leafNode = new RBBINode(RBBINode::leafChar);
RBBINode *leafNode = new RBBINode(RBBINode::leafChar, *fStatus);
if (U_FAILURE(*fStatus)) {
delete leafNode;
return;
}
if (leafNode == nullptr) {
*fStatus = U_MEMORY_ALLOCATION_ERROR;
return;
@@ -388,9 +392,13 @@ void RBBISetBuilder::addValToSet(RBBINode *usetNode, uint32_t val) {
// There are already input symbols present for this set.
// Set up an OR node, with the previous stuff as the left child
// and the new value as the right child.
RBBINode *orNode = new RBBINode(RBBINode::opOr);
RBBINode *orNode = new RBBINode(RBBINode::opOr, *fStatus);
if (orNode == nullptr) {
*fStatus = U_MEMORY_ALLOCATION_ERROR;
}
if (U_FAILURE(*fStatus)) {
delete orNode;
delete leafNode;
return;
}
orNode->fLeftChild = usetNode->fLeftChild;

28
intl/icu/source/common/rbbitblb.cpp
View File

@@ -99,13 +99,22 @@ void RBBITableBuilder::buildForwardTable() {
// {bof} fake character.
//
if (fRB->fSetBuilder->sawBOF()) {
RBBINode *bofTop = new RBBINode(RBBINode::opCat);
RBBINode *bofLeaf = new RBBINode(RBBINode::leafChar);
// Delete and exit if memory allocation failed.
if (bofTop == nullptr || bofLeaf == nullptr) {
RBBINode *bofTop = new RBBINode(RBBINode::opCat, *fStatus);
if (bofTop == nullptr) {
*fStatus = U_MEMORY_ALLOCATION_ERROR;
}
if (U_FAILURE(*fStatus)) {
delete bofTop;
return;
}
RBBINode *bofLeaf = new RBBINode(RBBINode::leafChar, *fStatus);
// Delete and exit if memory allocation failed.
if (bofLeaf == nullptr) {
*fStatus = U_MEMORY_ALLOCATION_ERROR;
}
if (U_FAILURE(*fStatus)) {
delete bofLeaf;
delete bofTop;
return;
}
bofTop->fLeftChild = bofLeaf;
@@ -120,18 +129,23 @@ void RBBITableBuilder::buildForwardTable() {
// Appears as a cat-node, left child being the original tree,
// right child being the end marker.
//
RBBINode *cn = new RBBINode(RBBINode::opCat);
RBBINode *cn = new RBBINode(RBBINode::opCat, *fStatus);
// Exit if memory allocation failed.
if (cn == nullptr) {
*fStatus = U_MEMORY_ALLOCATION_ERROR;
}
if (U_FAILURE(*fStatus)) {
delete cn;
return;
}
cn->fLeftChild = fTree;
fTree->fParent = cn;
RBBINode *endMarkerNode = cn->fRightChild = new RBBINode(RBBINode::endMark);
RBBINode *endMarkerNode = cn->fRightChild = new RBBINode(RBBINode::endMark, *fStatus);
// Delete and exit if memory allocation failed.
if (cn->fRightChild == nullptr) {
*fStatus = U_MEMORY_ALLOCATION_ERROR;
}
if (U_FAILURE(*fStatus)) {
delete cn;
return;
}
@@ -142,7 +156,7 @@ void RBBITableBuilder::buildForwardTable() {
// Replace all references to UnicodeSets with the tree for the equivalent
// expression.
//
fTree->flattenSets();
fTree->flattenSets(*fStatus, 0);
#ifdef RBBI_DEBUG
if (fRB->fDebugEnv && uprv_strstr(fRB->fDebugEnv, "stree")) {
RBBIDebugPuts("\nParse tree after flattening Unicode Set references.");

2
intl/icu/source/common/resbund.cpp
View File

@@ -388,7 +388,7 @@ const Locale &ResourceBundle::getLocale() const {
return ncThis->fLocale != nullptr ? *ncThis->fLocale : Locale::getDefault();
}
const Locale ResourceBundle::getLocale(ULocDataLocaleType type, UErrorCode &status) const
Locale ResourceBundle::getLocale(ULocDataLocaleType type, UErrorCode &status) const
{
return ures_getLocaleByType(fResource, type, &status);
}

5
intl/icu/source/common/ucnvmbcs.cpp
View File

@@ -3146,11 +3146,8 @@ ucnv_MBCSGetNextUChar(UConverterToUnicodeArgs *pArgs,
if(c<0) {
if(U_SUCCESS(*pErrorCode) && source==sourceLimit && lastSource<source) {
/* incomplete character byte sequence */
uint8_t *bytes=cnv->toUBytes;
cnv->toULength = static_cast<int8_t>(source - lastSource);
do {
*bytes++=*lastSource++;
} while(lastSource<source);
uprv_memcpy(cnv->toUBytes, lastSource, cnv->toULength);
*pErrorCode=U_TRUNCATED_CHAR_FOUND;
} else if(U_FAILURE(*pErrorCode)) {
/* callback(illegal) */

17
intl/icu/source/common/ucurr.cpp
View File

@@ -372,12 +372,8 @@ struct CReg : public icu::UMemory {
CReg(const char16_t* _iso, const char* _id)
: next(nullptr)
{
int32_t len = static_cast<int32_t>(uprv_strlen(_id));
if (len > static_cast<int32_t>(sizeof(id) - 1)) {
len = (sizeof(id)-1);
}
uprv_strncpy(id, _id, len);
id[len] = 0;
uprv_strncpy(id, _id, sizeof(id)-1);
id[sizeof(id)-1] = 0;
u_memcpy(iso, _iso, ISO_CURRENCY_CODE_LENGTH);
iso[ISO_CURRENCY_CODE_LENGTH] = 0;
}
@@ -682,6 +678,9 @@ ucurr_getName(const char16_t* currency,
// this function.
UErrorCode ec2 = U_ZERO_ERROR;
if (locale == nullptr) {
locale = uloc_getDefault();
}
CharString loc = ulocimp_getName(locale, ec2);
if (U_FAILURE(ec2)) {
*ec = U_ILLEGAL_ARGUMENT_ERROR;
@@ -780,6 +779,9 @@ ucurr_getPluralName(const char16_t* currency,
// this function.
UErrorCode ec2 = U_ZERO_ERROR;
if (locale == nullptr) {
locale = uloc_getDefault();
}
CharString loc = ulocimp_getName(locale, ec2);
if (U_FAILURE(ec2)) {
*ec = U_ILLEGAL_ARGUMENT_ERROR;
@@ -973,6 +975,9 @@ collectCurrencyNames(const char* locale,
// Look up the Currencies resource for the given locale.
UErrorCode ec2 = U_ZERO_ERROR;
if (locale == nullptr) {
locale = uloc_getDefault();
}
CharString loc = ulocimp_getName(locale, ec2);
if (U_FAILURE(ec2)) {
ec = U_ILLEGAL_ARGUMENT_ERROR;

527
intl/icu/source/common/uloc.cpp
View File

@@ -482,8 +482,8 @@ constexpr CanonicalizationMap CANONICALIZE_MAP[] = {
/* ### BCP47 Conversion *******************************************/
/* Gets the size of the shortest subtag in the given localeID. */
int32_t getShortestSubtagLength(const char *localeID) {
int32_t localeIDLength = static_cast<int32_t>(uprv_strlen(localeID));
int32_t getShortestSubtagLength(std::string_view localeID) {
int32_t localeIDLength = static_cast<int32_t>(localeID.length());
int32_t length = localeIDLength;
int32_t tmpLength = 0;
int32_t i;
@@ -507,8 +507,8 @@ int32_t getShortestSubtagLength(const char *localeID) {
return length;
}
/* Test if the locale id has BCP47 u extension and does not have '@' */
inline bool _hasBCP47Extension(const char *id) {
return id != nullptr && uprv_strstr(id, "@") == nullptr && getShortestSubtagLength(id) == 1;
inline bool _hasBCP47Extension(std::string_view id) {
return id.find('@') == std::string_view::npos && getShortestSubtagLength(id) == 1;
}
/* ### Keywords **************************************************/
@@ -523,10 +523,9 @@ inline bool UPRV_OK_VALUE_PUNCTUATION(char c) { return c == '_' || c == '-' || c
#define ULOC_MAX_NO_KEYWORDS 25
U_CAPI const char * U_EXPORT2
locale_getKeywordsStart(const char *localeID) {
const char *result = nullptr;
if((result = uprv_strchr(localeID, '@')) != nullptr) {
return result;
locale_getKeywordsStart(std::string_view localeID) {
if (size_t pos = localeID.find('@'); pos != std::string_view::npos) {
return localeID.data() + pos;
}
#if (U_CHARSET_FAMILY == U_EBCDIC_FAMILY)
else {
@@ -536,8 +535,8 @@ locale_getKeywordsStart(const char *localeID) {
static const uint8_t ebcdicSigns[] = { 0x7C, 0x44, 0x66, 0x80, 0xAC, 0xAE, 0xAF, 0xB5, 0xEC, 0xEF, 0x00 };
const uint8_t *charToFind = ebcdicSigns;
while(*charToFind) {
if((result = uprv_strchr(localeID, *charToFind)) != nullptr) {
return result;
if (size_t pos = localeID.find(*charToFind); pos != std::string_view::npos) {
return localeID.data() + pos;
}
charToFind++;
}
@@ -590,7 +589,7 @@ compareKeywordStructs(const void * /*context*/, const void *left, const void *ri
} // namespace
U_EXPORT CharString
ulocimp_getKeywords(const char* localeID,
ulocimp_getKeywords(std::string_view localeID,
char prev,
bool valuesToo,
UErrorCode& status)
@@ -607,7 +606,7 @@ ulocimp_getKeywords(const char* localeID,
}
U_EXPORT void
ulocimp_getKeywords(const char* localeID,
ulocimp_getKeywords(std::string_view localeID,
char prev,
ByteSink& sink,
bool valuesToo,
@@ -619,9 +618,8 @@ ulocimp_getKeywords(const char* localeID,
int32_t maxKeywords = ULOC_MAX_NO_KEYWORDS;
int32_t numKeywords = 0;
const char* pos = localeID;
const char* equalSign = nullptr;
const char* semicolon = nullptr;
size_t equalSign = std::string_view::npos;
size_t semicolon = std::string_view::npos;
int32_t i = 0, j, n;
if(prev == '@') { /* start of keyword definition */
@@ -629,74 +627,72 @@ ulocimp_getKeywords(const char* localeID,
do {
bool duplicate = false;
/* skip leading spaces */
while(*pos == ' ') {
pos++;
while (localeID.front() == ' ') {
localeID.remove_prefix(1);
}
if (!*pos) { /* handle trailing "; " */
if (localeID.empty()) { /* handle trailing "; " */
break;
}
if(numKeywords == maxKeywords) {
status = U_INTERNAL_PROGRAM_ERROR;
return;
}
equalSign = uprv_strchr(pos, '=');
semicolon = uprv_strchr(pos, ';');
equalSign = localeID.find('=');
semicolon = localeID.find(';');
/* lack of '=' [foo@currency] is illegal */
/* ';' before '=' [foo@currency;collation=pinyin] is illegal */
if(!equalSign || (semicolon && semicolon<equalSign)) {
if (equalSign == std::string_view::npos ||
(semicolon != std::string_view::npos && semicolon < equalSign)) {
status = U_INVALID_FORMAT_ERROR;
return;
}
/* zero-length keyword is an error. */
if (equalSign == 0) {
status = U_INVALID_FORMAT_ERROR;
return;
}
/* need to normalize both keyword and keyword name */
if(equalSign - pos >= ULOC_KEYWORD_BUFFER_LEN) {
if (equalSign >= ULOC_KEYWORD_BUFFER_LEN) {
/* keyword name too long for internal buffer */
status = U_INTERNAL_PROGRAM_ERROR;
return;
}
for(i = 0, n = 0; i < equalSign - pos; ++i) {
if (pos[i] != ' ') {
keywordList[numKeywords].keyword[n++] = uprv_tolower(pos[i]);
for (i = 0, n = 0; static_cast<size_t>(i) < equalSign; ++i) {
if (localeID[i] != ' ') {
keywordList[numKeywords].keyword[n++] = uprv_tolower(localeID[i]);
}
}
/* zero-length keyword is an error. */
if (n == 0) {
status = U_INVALID_FORMAT_ERROR;
return;
}
keywordList[numKeywords].keyword[n] = 0;
keywordList[numKeywords].keywordLen = n;
/* now grab the value part. First we skip the '=' */
equalSign++;
/* then we leading spaces */
while(*equalSign == ' ') {
while (equalSign < localeID.length() && localeID[equalSign] == ' ') {
equalSign++;
}
/* Premature end or zero-length value */
if (!*equalSign || equalSign == semicolon) {
if (equalSign == localeID.length() || equalSign == semicolon) {
status = U_INVALID_FORMAT_ERROR;
return;
}
keywordList[numKeywords].valueStart = equalSign;
keywordList[numKeywords].valueStart = localeID.data() + equalSign;
pos = semicolon;
i = 0;
if(pos) {
while(*(pos - i - 1) == ' ') {
i++;
}
keywordList[numKeywords].valueLen = static_cast<int32_t>(pos - equalSign - i);
pos++;
std::string_view value = localeID;
if (semicolon != std::string_view::npos) {
value.remove_suffix(value.length() - semicolon);
localeID.remove_prefix(semicolon + 1);
} else {
i = static_cast<int32_t>(uprv_strlen(equalSign));
while(i && equalSign[i-1] == ' ') {
i--;
localeID = {};
}
keywordList[numKeywords].valueLen = i;
value.remove_prefix(equalSign);
if (size_t last = value.find_last_not_of(' '); last != std::string_view::npos) {
value.remove_suffix(value.length() - last - 1);
}
keywordList[numKeywords].valueLen = static_cast<int32_t>(value.length());
/* If this is a duplicate keyword, then ignore it */
for (j=0; j<numKeywords; ++j) {
if (uprv_strcmp(keywordList[j].keyword, keywordList[numKeywords].keyword) == 0) {
@@ -707,7 +703,7 @@ ulocimp_getKeywords(const char* localeID,
if (!duplicate) {
++numKeywords;
}
} while(pos);
} while (!localeID.empty());
/* now we have a list of keywords */
/* we need to sort it */
@@ -784,7 +780,7 @@ ulocimp_getKeywordValue(const char* localeID,
return;
}
if (_hasBCP47Extension(localeID)) {
if (localeID != nullptr && _hasBCP47Extension(localeID)) {
tempBuffer = ulocimp_forLanguageTag(localeID, -1, nullptr, status);
tmpLocaleID = U_SUCCESS(status) && !tempBuffer.isEmpty() ? tempBuffer.data() : localeID;
} else {
@@ -889,7 +885,8 @@ uloc_setKeywordValue(const char* keywordName,
return 0;
}
char* keywords = const_cast<char*>(locale_getKeywordsStart(buffer));
char* keywords = const_cast<char*>(
locale_getKeywordsStart({buffer, static_cast<std::string_view::size_type>(bufLen)}));
int32_t baseLen = keywords == nullptr ? bufLen : keywords - buffer;
// Remove -1 from the capacity so that this function can guarantee NUL termination.
CheckedArrayByteSink sink(keywords == nullptr ? buffer + bufLen : keywords,
@@ -921,7 +918,7 @@ ulocimp_setKeywordValue(std::string_view keywordName,
{
if (U_FAILURE(status)) { return; }
std::string_view keywords;
if (const char* start = locale_getKeywordsStart(localeID.data()); start != nullptr) {
if (const char* start = locale_getKeywordsStart(localeID.toStringPiece()); start != nullptr) {
// This is safe because CharString::truncate() doesn't actually erase any
// data, but simply sets the position for where new data will be written.
int32_t size = start - localeID.data();
@@ -1138,15 +1135,18 @@ inline bool _isPrefixLetter(char a) { return a == 'x' || a == 'X' || a == 'i' ||
/*returns true if one of the special prefixes is here (s=string)
'x-' or 'i-' */
inline bool _isIDPrefix(const char *s) { return _isPrefixLetter(s[0]) && _isIDSeparator(s[1]); }
inline bool _isIDPrefix(std::string_view s) {
return s.size() >= 2 && _isPrefixLetter(s[0]) && _isIDSeparator(s[1]);
}
/* Dot terminates it because of POSIX form where dot precedes the codepage
* except for variant
*/
inline bool _isTerminator(char a) { return a == 0 || a == '.' || a == '@'; }
inline bool _isTerminator(char a) { return a == '.' || a == '@'; }
inline bool _isBCP47Extension(const char* p) {
return p[0] == '-' &&
inline bool _isBCP47Extension(std::string_view p) {
return p.size() >= 3 &&
p[0] == '-' &&
(p[1] == 't' || p[1] == 'T' ||
p[1] == 'u' || p[1] == 'U' ||
p[1] == 'x' || p[1] == 'X') &&
@@ -1202,49 +1202,44 @@ namespace {
* TODO try to use this in Locale
*/
void
_getLanguage(const char* localeID,
ByteSink* sink,
const char** pEnd,
UErrorCode& status) {
U_ASSERT(pEnd != nullptr);
*pEnd = localeID;
if (uprv_stricmp(localeID, "root") == 0) {
localeID += 4;
} else if (uprv_strnicmp(localeID, "und", 3) == 0 &&
(localeID[3] == '\0' ||
size_t _getLanguage(std::string_view localeID, ByteSink* sink, UErrorCode& status) {
size_t skip = 0;
if (localeID.size() == 4 && uprv_strnicmp(localeID.data(), "root", 4) == 0) {
skip = 4;
localeID.remove_prefix(skip);
} else if (localeID.size() >= 3 && uprv_strnicmp(localeID.data(), "und", 3) == 0 &&
(localeID.size() == 3 ||
localeID[3] == '-' ||
localeID[3] == '_' ||
localeID[3] == '@')) {
localeID += 3;
skip = 3;
localeID.remove_prefix(skip);
}
constexpr int32_t MAXLEN = ULOC_LANG_CAPACITY - 1; // Minus NUL.
/* if it starts with i- or x- then copy that prefix */
int32_t len = _isIDPrefix(localeID) ? 2 : 0;
while (!_isTerminator(localeID[len]) && !_isIDSeparator(localeID[len])) {
size_t len = _isIDPrefix(localeID) ? 2 : 0;
while (len < localeID.size() && !_isTerminator(localeID[len]) && !_isIDSeparator(localeID[len])) {
if (len == MAXLEN) {
status = U_ILLEGAL_ARGUMENT_ERROR;
return;
return 0;
}
len++;
}
*pEnd = localeID + len;
if (sink == nullptr || len == 0) { return; }
if (sink == nullptr || len == 0) { return skip + len; }
int32_t minCapacity = uprv_max(len, 4); // Minimum 3 letters plus NUL.
int32_t minCapacity = uprv_max(static_cast<int32_t>(len), 4); // Minimum 3 letters plus NUL.
char scratch[MAXLEN];
int32_t capacity = 0;
char* buffer = sink->GetAppendBuffer(
minCapacity, minCapacity, scratch, UPRV_LENGTHOF(scratch), &capacity);
for (int32_t i = 0; i < len; ++i) {
for (size_t i = 0; i < len; ++i) {
buffer[i] = uprv_tolower(localeID[i]);
}
if (_isIDSeparator(localeID[1])) {
if (localeID.size() >= 2 && _isIDSeparator(localeID[1])) {
buffer[1] = '-';
}
@@ -1256,32 +1251,26 @@ _getLanguage(const char* localeID,
if (offset.has_value()) {
const char* const alias = LANGUAGES[*offset];
sink->Append(alias, static_cast<int32_t>(uprv_strlen(alias)));
return;
return skip + len;
}
}
sink->Append(buffer, len);
sink->Append(buffer, static_cast<int32_t>(len));
return skip + len;
}
void
_getScript(const char* localeID,
ByteSink* sink,
const char** pEnd) {
U_ASSERT(pEnd != nullptr);
*pEnd = localeID;
size_t _getScript(std::string_view localeID, ByteSink* sink) {
constexpr int32_t LENGTH = 4;
int32_t len = 0;
while (!_isTerminator(localeID[len]) && !_isIDSeparator(localeID[len]) &&
size_t len = 0;
while (len < localeID.size() && !_isTerminator(localeID[len]) && !_isIDSeparator(localeID[len]) &&
uprv_isASCIILetter(localeID[len])) {
if (len == LENGTH) { return; }
if (len == LENGTH) { return 0; }
len++;
}
if (len != LENGTH) { return; }
if (len != LENGTH) { return 0; }
*pEnd = localeID + LENGTH;
if (sink == nullptr) { return; }
if (sink == nullptr) { return len; }
char scratch[LENGTH];
int32_t capacity = 0;
@@ -1294,27 +1283,21 @@ _getScript(const char* localeID,
}
sink->Append(buffer, LENGTH);
return len;
}
void
_getRegion(const char* localeID,
ByteSink* sink,
const char** pEnd) {
U_ASSERT(pEnd != nullptr);
*pEnd = localeID;
size_t _getRegion(std::string_view localeID, ByteSink* sink) {
constexpr int32_t MINLEN = 2;
constexpr int32_t MAXLEN = ULOC_COUNTRY_CAPACITY - 1; // Minus NUL.
int32_t len = 0;
while (!_isTerminator(localeID[len]) && !_isIDSeparator(localeID[len])) {
if (len == MAXLEN) { return; }
size_t len = 0;
while (len < localeID.size() && !_isTerminator(localeID[len]) && !_isIDSeparator(localeID[len])) {
if (len == MAXLEN) { return 0; }
len++;
}
if (len < MINLEN) { return; }
if (len < MINLEN) { return 0; }
*pEnd = localeID + len;
if (sink == nullptr) { return; }
if (sink == nullptr) { return len; }
char scratch[ULOC_COUNTRY_CAPACITY];
int32_t capacity = 0;
@@ -1325,7 +1308,7 @@ _getRegion(const char* localeID,
UPRV_LENGTHOF(scratch),
&capacity);
for (int32_t i = 0; i < len; ++i) {
for (size_t i = 0; i < len; ++i) {
buffer[i] = uprv_toupper(localeID[i]);
}
@@ -1337,26 +1320,25 @@ _getRegion(const char* localeID,
if (offset.has_value()) {
const char* const alias = COUNTRIES[*offset];
sink->Append(alias, static_cast<int32_t>(uprv_strlen(alias)));
return;
return len;
}
}
sink->Append(buffer, len);
sink->Append(buffer, static_cast<int32_t>(len));
return len;
}
/**
* @param needSeparator if true, then add leading '_' if any variants
* are added to 'variant'
*/
void
_getVariant(const char* localeID,
size_t
_getVariant(std::string_view localeID,
char prev,
ByteSink* sink,
const char** pEnd,
bool needSeparator,
UErrorCode& status) {
if (U_FAILURE(status)) return;
if (pEnd != nullptr) { *pEnd = localeID; }
if (U_FAILURE(status) || localeID.empty()) return 0;
// Reasonable upper limit for variants
// There are no strict limitation of the syntax of variant in the legacy
@@ -1369,42 +1351,62 @@ _getVariant(const char* localeID,
constexpr int32_t MAX_VARIANTS_LENGTH = 179;
/* get one or more variant tags and separate them with '_' */
int32_t index = 0;
size_t index = 0;
if (_isIDSeparator(prev)) {
/* get a variant string after a '-' or '_' */
for (index=0; !_isTerminator(localeID[index]); index++) {
if (index >= MAX_VARIANTS_LENGTH) { // same as length > MAX_VARIANTS_LENGTH
for (std::string_view sub = localeID;;) {
size_t next = sub.find_first_of(".@_-");
// For historical reasons, a trailing separator is included in the variant.
bool finished = next == std::string_view::npos || next + 1 == sub.length();
size_t limit = finished ? sub.length() : next;
index += limit;
if (index > MAX_VARIANTS_LENGTH) {
status = U_ILLEGAL_ARGUMENT_ERROR;
return;
}
if (needSeparator) {
if (sink != nullptr) {
sink->Append("_", 1);
}
needSeparator = false;
}
if (sink != nullptr) {
char c = uprv_toupper(localeID[index]);
if (c == '-') c = '_';
sink->Append(&c, 1);
}
}
if (pEnd != nullptr) { *pEnd = localeID+index; }
return 0;
}
/* if there is no variant tag after a '-' or '_' then look for '@' */
if (index == 0) {
if (prev=='@') {
/* keep localeID */
} else if((localeID=locale_getKeywordsStart(localeID))!=nullptr) {
++localeID; /* point after the '@' */
if (sink != nullptr) {
if (needSeparator) {
sink->Append("_", 1);
} else {
return;
needSeparator = true;
}
for(; !_isTerminator(localeID[index]); index++) {
int32_t length = static_cast<int32_t>(limit);
int32_t minCapacity = uprv_min(length, MAX_VARIANTS_LENGTH);
char scratch[MAX_VARIANTS_LENGTH];
int32_t capacity = 0;
char* buffer = sink->GetAppendBuffer(
minCapacity, minCapacity, scratch, UPRV_LENGTHOF(scratch), &capacity);
for (size_t i = 0; i < limit; ++i) {
buffer[i] = uprv_toupper(sub[i]);
}
sink->Append(buffer, length);
}
if (finished) { return index; }
sub.remove_prefix(next);
if (_isTerminator(sub.front()) || _isBCP47Extension(sub)) { return index; }
sub.remove_prefix(1);
index++;
}
}
size_t skip = 0;
/* if there is no variant tag after a '-' or '_' then look for '@' */
if (prev == '@') {
/* keep localeID */
} else if (const char* p = locale_getKeywordsStart(localeID); p != nullptr) {
skip = 1 + p - localeID.data(); /* point after the '@' */
localeID.remove_prefix(skip);
} else {
return 0;
}
for (; index < localeID.size() && !_isTerminator(localeID[index]); index++) {
if (index >= MAX_VARIANTS_LENGTH) { // same as length > MAX_VARIANTS_LENGTH
status = U_ILLEGAL_ARGUMENT_ERROR;
return;
return 0;
}
if (needSeparator) {
if (sink != nullptr) {
@@ -1418,14 +1420,13 @@ _getVariant(const char* localeID,
sink->Append(&c, 1);
}
}
if (pEnd != nullptr) { *pEnd = localeID + index; }
}
return skip + index;
}
} // namespace
U_EXPORT CharString
ulocimp_getLanguage(const char* localeID, UErrorCode& status) {
ulocimp_getLanguage(std::string_view localeID, UErrorCode& status) {
return ByteSinkUtil::viaByteSinkToCharString(
[&](ByteSink& sink, UErrorCode& status) {
ulocimp_getSubtags(
@@ -1441,7 +1442,7 @@ ulocimp_getLanguage(const char* localeID, UErrorCode& status) {
}
U_EXPORT CharString
ulocimp_getScript(const char* localeID, UErrorCode& status) {
ulocimp_getScript(std::string_view localeID, UErrorCode& status) {
return ByteSinkUtil::viaByteSinkToCharString(
[&](ByteSink& sink, UErrorCode& status) {
ulocimp_getSubtags(
@@ -1457,7 +1458,7 @@ ulocimp_getScript(const char* localeID, UErrorCode& status) {
}
U_EXPORT CharString
ulocimp_getRegion(const char* localeID, UErrorCode& status) {
ulocimp_getRegion(std::string_view localeID, UErrorCode& status) {
return ByteSinkUtil::viaByteSinkToCharString(
[&](ByteSink& sink, UErrorCode& status) {
ulocimp_getSubtags(
@@ -1473,7 +1474,7 @@ ulocimp_getRegion(const char* localeID, UErrorCode& status) {
}
U_EXPORT CharString
ulocimp_getVariant(const char* localeID, UErrorCode& status) {
ulocimp_getVariant(std::string_view localeID, UErrorCode& status) {
return ByteSinkUtil::viaByteSinkToCharString(
[&](ByteSink& sink, UErrorCode& status) {
ulocimp_getSubtags(
@@ -1490,7 +1491,7 @@ ulocimp_getVariant(const char* localeID, UErrorCode& status) {
U_EXPORT void
ulocimp_getSubtags(
const char* localeID,
std::string_view localeID,
CharString* language,
CharString* script,
CharString* region,
@@ -1521,7 +1522,7 @@ ulocimp_getSubtags(
U_EXPORT void
ulocimp_getSubtags(
const char* localeID,
std::string_view localeID,
ByteSink* language,
ByteSink* script,
ByteSink* region,
@@ -1531,7 +1532,7 @@ ulocimp_getSubtags(
if (U_FAILURE(status)) { return; }
if (pEnd != nullptr) {
*pEnd = localeID;
*pEnd = localeID.data();
} else if (language == nullptr &&
script == nullptr &&
region == nullptr &&
@@ -1539,62 +1540,94 @@ ulocimp_getSubtags(
return;
}
if (localeID.empty()) { return; }
bool hasRegion = false;
if (localeID == nullptr) {
localeID = uloc_getDefault();
{
size_t len = _getLanguage(localeID, language, status);
if (U_FAILURE(status)) { return; }
if (len > 0) {
localeID.remove_prefix(len);
}
}
_getLanguage(localeID, language, &localeID, status);
if (U_FAILURE(status)) { return; }
U_ASSERT(localeID != nullptr);
if (pEnd != nullptr) {
*pEnd = localeID;
*pEnd = localeID.data();
} else if (script == nullptr &&
region == nullptr &&
variant == nullptr) {
return;
}
if (_isIDSeparator(*localeID)) {
const char* begin = localeID + 1;
const char* end = nullptr;
_getScript(begin, script, &end);
U_ASSERT(end != nullptr);
if (end != begin) {
localeID = end;
if (pEnd != nullptr) { *pEnd = localeID; }
if (localeID.empty()) { return; }
if (_isIDSeparator(localeID.front())) {
std::string_view sub = localeID;
sub.remove_prefix(1);
size_t len = _getScript(sub, script);
if (len > 0) {
localeID.remove_prefix(len + 1);
if (pEnd != nullptr) { *pEnd = localeID.data(); }
}
}
if (region == nullptr && variant == nullptr && pEnd == nullptr) { return; }
if ((region == nullptr && variant == nullptr && pEnd == nullptr) || localeID.empty()) { return; }
if (_isIDSeparator(*localeID)) {
const char* begin = localeID + 1;
const char* end = nullptr;
_getRegion(begin, region, &end);
U_ASSERT(end != nullptr);
if (end != begin) {
if (_isIDSeparator(localeID.front())) {
std::string_view sub = localeID;
sub.remove_prefix(1);
size_t len = _getRegion(sub, region);
if (len > 0) {
hasRegion = true;
localeID = end;
if (pEnd != nullptr) { *pEnd = localeID; }
localeID.remove_prefix(len + 1);
if (pEnd != nullptr) { *pEnd = localeID.data(); }
}
}
if (variant == nullptr && pEnd == nullptr) { return; }
if ((variant == nullptr && pEnd == nullptr) || localeID.empty()) { return; }
if (_isIDSeparator(*localeID) && !_isBCP47Extension(localeID)) {
bool hasVariant = false;
if (_isIDSeparator(localeID.front()) && !_isBCP47Extension(localeID)) {
std::string_view sub = localeID;
/* If there was no country ID, skip a possible extra IDSeparator */
if (!hasRegion && _isIDSeparator(localeID[1])) {
localeID++;
}
const char* begin = localeID + 1;
const char* end = nullptr;
_getVariant(begin, *localeID, variant, &end, false, status);
size_t skip = !hasRegion && localeID.size() > 1 && _isIDSeparator(localeID[1]) ? 2 : 1;
sub.remove_prefix(skip);
size_t len = _getVariant(sub, localeID[0], variant, false, status);
if (U_FAILURE(status)) { return; }
U_ASSERT(end != nullptr);
if (end != begin && pEnd != nullptr) { *pEnd = end; }
if (len > 0) {
hasVariant = true;
localeID.remove_prefix(skip + len);
if (pEnd != nullptr) { *pEnd = localeID.data(); }
}
}
if ((variant == nullptr && pEnd == nullptr) || localeID.empty()) { return; }
if (_isBCP47Extension(localeID)) {
localeID.remove_prefix(2);
constexpr char vaposix[] = "-va-posix";
constexpr size_t length = sizeof vaposix - 1;
for (size_t next;; localeID.remove_prefix(next)) {
next = localeID.find('-', 1);
if (next == std::string_view::npos) { break; }
next = localeID.find('-', next + 1);
bool finished = next == std::string_view::npos;
std::string_view sub = localeID;
if (!finished) { sub.remove_suffix(sub.length() - next); }
if (sub.length() == length && uprv_strnicmp(sub.data(), vaposix, length) == 0) {
if (variant != nullptr) {
if (hasVariant) { variant->Append("_", 1); }
constexpr char posix[] = "POSIX";
variant->Append(posix, sizeof posix - 1);
}
if (pEnd != nullptr) { *pEnd = localeID.data() + length; }
}
if (finished) { break; }
}
}
}
@@ -1700,7 +1733,7 @@ uloc_openKeywords(const char* localeID,
CharString tempBuffer;
const char* tmpLocaleID;
if (_hasBCP47Extension(localeID)) {
if (localeID != nullptr && _hasBCP47Extension(localeID)) {
tempBuffer = ulocimp_forLanguageTag(localeID, -1, nullptr, *status);
tmpLocaleID = U_SUCCESS(*status) && !tempBuffer.isEmpty() ? tempBuffer.data() : localeID;
} else {
@@ -1753,7 +1786,7 @@ constexpr int32_t I_DEFAULT_LENGTH = UPRV_LENGTHOF(i_default);
* This is the code underlying uloc_getName and uloc_canonicalize.
*/
void
_canonicalize(const char* localeID,
_canonicalize(std::string_view localeID,
ByteSink& sink,
uint32_t options,
UErrorCode& err) {
@@ -1764,33 +1797,30 @@ _canonicalize(const char* localeID,
int32_t j, fieldCount=0;
CharString tempBuffer; // if localeID has a BCP47 extension, tmpLocaleID points to this
CharString localeIDWithHyphens; // if localeID has a BPC47 extension and have _, tmpLocaleID points to this
const char* origLocaleID;
const char* tmpLocaleID;
const char* keywordAssign = nullptr;
const char* separatorIndicator = nullptr;
std::string_view origLocaleID;
std::string_view tmpLocaleID;
size_t keywordAssign = std::string_view::npos;
size_t separatorIndicator = std::string_view::npos;
if (_hasBCP47Extension(localeID)) {
const char* localeIDPtr = localeID;
std::string_view localeIDPtr = localeID;
// convert all underbars to hyphens, unless the "BCP47 extension" comes at the beginning of the string
if (uprv_strchr(localeID, '_') != nullptr && localeID[1] != '-' && localeID[1] != '_') {
localeIDWithHyphens.append(localeID, -1, err);
if (localeID.size() >= 2 && localeID.find('_') != std::string_view::npos && localeID[1] != '-' && localeID[1] != '_') {
localeIDWithHyphens.append(localeID, err);
if (U_SUCCESS(err)) {
for (char* p = localeIDWithHyphens.data(); *p != '\0'; ++p) {
if (*p == '_') {
*p = '-';
}
}
localeIDPtr = localeIDWithHyphens.data();
localeIDPtr = localeIDWithHyphens.toStringPiece();
}
}
tempBuffer = ulocimp_forLanguageTag(localeIDPtr, -1, nullptr, err);
tmpLocaleID = U_SUCCESS(err) && !tempBuffer.isEmpty() ? tempBuffer.data() : localeIDPtr;
tempBuffer = ulocimp_forLanguageTag(localeIDPtr.data(), static_cast<int32_t>(localeIDPtr.size()), nullptr, err);
tmpLocaleID = U_SUCCESS(err) && !tempBuffer.isEmpty() ? static_cast<std::string_view>(tempBuffer.toStringPiece()) : localeIDPtr;
} else {
if (localeID==nullptr) {
localeID=uloc_getDefault();
}
tmpLocaleID=localeID;
}
@@ -1801,20 +1831,25 @@ _canonicalize(const char* localeID,
CharString script;
CharString country;
CharString variant;
const char* end = nullptr;
ulocimp_getSubtags(
tmpLocaleID,
&tag,
&script,
&country,
&variant,
&tmpLocaleID,
&end,
err);
if (U_FAILURE(err)) {
return;
}
U_ASSERT(end != nullptr);
if (end > tmpLocaleID.data()) {
tmpLocaleID.remove_prefix(end - tmpLocaleID.data());
}
if (tag.length() == I_DEFAULT_LENGTH &&
uprv_strncmp(origLocaleID, i_default, I_DEFAULT_LENGTH) == 0) {
if (tag.length() == I_DEFAULT_LENGTH && origLocaleID.length() >= I_DEFAULT_LENGTH &&
uprv_strncmp(origLocaleID.data(), i_default, I_DEFAULT_LENGTH) == 0) {
tag.clear();
tag.append(uloc_getDefault(), err);
} else {
@@ -1839,15 +1874,14 @@ _canonicalize(const char* localeID,
}
/* Copy POSIX-style charset specifier, if any [mr.utf8] */
if (!OPTION_SET(options, _ULOC_CANONICALIZE) && *tmpLocaleID == '.') {
if (!OPTION_SET(options, _ULOC_CANONICALIZE) && !tmpLocaleID.empty() && tmpLocaleID.front() == '.') {
tag.append('.', err);
++tmpLocaleID;
const char *atPos = nullptr;
tmpLocaleID.remove_prefix(1);
size_t length;
if((atPos = uprv_strchr(tmpLocaleID, '@')) != nullptr) {
length = atPos - tmpLocaleID;
if (size_t atPos = tmpLocaleID.find('@'); atPos != std::string_view::npos) {
length = atPos;
} else {
length = uprv_strlen(tmpLocaleID);
length = tmpLocaleID.length();
}
// The longest charset name we found in IANA charset registry
// https://www.iana.org/assignments/character-sets/ is
@@ -1859,33 +1893,34 @@ _canonicalize(const char* localeID,
err = U_ILLEGAL_ARGUMENT_ERROR; /* malformed keyword name */
return;
}
tag.append(tmpLocaleID, static_cast<int32_t>(length), err);
tmpLocaleID += length;
if (length > 0) {
tag.append(tmpLocaleID.data(), static_cast<int32_t>(length), err);
tmpLocaleID.remove_prefix(length);
}
}
/* Scan ahead to next '@' and determine if it is followed by '=' and/or ';'
After this, tmpLocaleID either points to '@' or is nullptr */
if ((tmpLocaleID=locale_getKeywordsStart(tmpLocaleID))!=nullptr) {
keywordAssign = uprv_strchr(tmpLocaleID, '=');
separatorIndicator = uprv_strchr(tmpLocaleID, ';');
After this, tmpLocaleID either starts at '@' or is empty. */
if (const char* start = locale_getKeywordsStart(tmpLocaleID); start != nullptr) {
if (start > tmpLocaleID.data()) {
tmpLocaleID.remove_prefix(start - tmpLocaleID.data());
}
keywordAssign = tmpLocaleID.find('=');
separatorIndicator = tmpLocaleID.find(';');
} else {
tmpLocaleID = {};
}
/* Copy POSIX-style variant, if any [mr@FOO] */
if (!OPTION_SET(options, _ULOC_CANONICALIZE) &&
tmpLocaleID != nullptr && keywordAssign == nullptr) {
for (;;) {
char c = *tmpLocaleID;
if (c == 0) {
break;
}
tag.append(c, err);
++tmpLocaleID;
}
!tmpLocaleID.empty() && keywordAssign == std::string_view::npos) {
tag.append(tmpLocaleID, err);
tmpLocaleID = {};
}
if (OPTION_SET(options, _ULOC_CANONICALIZE)) {
/* Handle @FOO variant if @ is present and not followed by = */
if (tmpLocaleID!=nullptr && keywordAssign==nullptr) {
if (!tmpLocaleID.empty() && keywordAssign == std::string_view::npos) {
/* Add missing '_' if needed */
if (fieldCount < 2 || (fieldCount < 3 && !script.isEmpty())) {
do {
@@ -1895,7 +1930,9 @@ _canonicalize(const char* localeID,
}
CharStringByteSink s(&tag);
_getVariant(tmpLocaleID+1, '@', &s, nullptr, !variant.isEmpty(), err);
std::string_view sub = tmpLocaleID;
sub.remove_prefix(1);
_getVariant(sub, '@', &s, !variant.isEmpty(), err);
if (U_FAILURE(err)) { return; }
}
@@ -1903,7 +1940,7 @@ _canonicalize(const char* localeID,
for (j=0; j<UPRV_LENGTHOF(CANONICALIZE_MAP); j++) {
StringPiece id(CANONICALIZE_MAP[j].id);
if (tag == id) {
if (id.empty() && tmpLocaleID != nullptr) {
if (id.empty() && !tmpLocaleID.empty()) {
break; /* Don't remap "" if keywords present */
}
tag.clear();
@@ -1916,11 +1953,12 @@ _canonicalize(const char* localeID,
sink.Append(tag.data(), tag.length());
if (!OPTION_SET(options, _ULOC_STRIP_KEYWORDS)) {
if (tmpLocaleID!=nullptr && keywordAssign!=nullptr &&
(!separatorIndicator || separatorIndicator > keywordAssign)) {
if (!tmpLocaleID.empty() && keywordAssign != std::string_view::npos &&
(separatorIndicator == std::string_view::npos || separatorIndicator > keywordAssign)) {
sink.Append("@", 1);
++fieldCount;
ulocimp_getKeywords(tmpLocaleID+1, '@', sink, true, err);
tmpLocaleID.remove_prefix(1);
ulocimp_getKeywords(tmpLocaleID, '@', sink, true, err);
}
}
}
@@ -1989,6 +2027,10 @@ uloc_getLanguage(const char* localeID,
int32_t languageCapacity,
UErrorCode* err)
{
if (localeID == nullptr) {
localeID = uloc_getDefault();
}
/* uloc_getLanguage will return a 2 character iso-639 code if one exists. *CWB*/
return ByteSinkUtil::viaByteSinkToTerminatedChars(
language, languageCapacity,
@@ -2011,6 +2053,10 @@ uloc_getScript(const char* localeID,
int32_t scriptCapacity,
UErrorCode* err)
{
if (localeID == nullptr) {
localeID = uloc_getDefault();
}
return ByteSinkUtil::viaByteSinkToTerminatedChars(
script, scriptCapacity,
[&](ByteSink& sink, UErrorCode& status) {
@@ -2032,6 +2078,10 @@ uloc_getCountry(const char* localeID,
int32_t countryCapacity,
UErrorCode* err)
{
if (localeID == nullptr) {
localeID = uloc_getDefault();
}
return ByteSinkUtil::viaByteSinkToTerminatedChars(
country, countryCapacity,
[&](ByteSink& sink, UErrorCode& status) {
@@ -2053,6 +2103,10 @@ uloc_getVariant(const char* localeID,
int32_t variantCapacity,
UErrorCode* err)
{
if (localeID == nullptr) {
localeID = uloc_getDefault();
}
return ByteSinkUtil::viaByteSinkToTerminatedChars(
variant, variantCapacity,
[&](ByteSink& sink, UErrorCode& status) {
@@ -2074,6 +2128,9 @@ uloc_getName(const char* localeID,
int32_t nameCapacity,
UErrorCode* err)
{
if (localeID == nullptr) {
localeID = uloc_getDefault();
}
return ByteSinkUtil::viaByteSinkToTerminatedChars(
name, nameCapacity,
[&](ByteSink& sink, UErrorCode& status) {
@@ -2083,7 +2140,7 @@ uloc_getName(const char* localeID,
}
U_EXPORT CharString
ulocimp_getName(const char* localeID,
ulocimp_getName(std::string_view localeID,
UErrorCode& err)
{
return ByteSinkUtil::viaByteSinkToCharString(
@@ -2094,7 +2151,7 @@ ulocimp_getName(const char* localeID,
}
U_EXPORT void
ulocimp_getName(const char* localeID,
ulocimp_getName(std::string_view localeID,
ByteSink& sink,
UErrorCode& err)
{
@@ -2107,6 +2164,9 @@ uloc_getBaseName(const char* localeID,
int32_t nameCapacity,
UErrorCode* err)
{
if (localeID == nullptr) {
localeID = uloc_getDefault();
}
return ByteSinkUtil::viaByteSinkToTerminatedChars(
name, nameCapacity,
[&](ByteSink& sink, UErrorCode& status) {
@@ -2116,7 +2176,7 @@ uloc_getBaseName(const char* localeID,
}
U_EXPORT CharString
ulocimp_getBaseName(const char* localeID,
ulocimp_getBaseName(std::string_view localeID,
UErrorCode& err)
{
return ByteSinkUtil::viaByteSinkToCharString(
@@ -2127,7 +2187,7 @@ ulocimp_getBaseName(const char* localeID,
}
U_EXPORT void
ulocimp_getBaseName(const char* localeID,
ulocimp_getBaseName(std::string_view localeID,
ByteSink& sink,
UErrorCode& err)
{
@@ -2140,6 +2200,9 @@ uloc_canonicalize(const char* localeID,
int32_t nameCapacity,
UErrorCode* err)
{
if (localeID == nullptr) {
localeID = uloc_getDefault();
}
return ByteSinkUtil::viaByteSinkToTerminatedChars(
name, nameCapacity,
[&](ByteSink& sink, UErrorCode& status) {
@@ -2149,7 +2212,7 @@ uloc_canonicalize(const char* localeID,
}
U_EXPORT CharString
ulocimp_canonicalize(const char* localeID,
ulocimp_canonicalize(std::string_view localeID,
UErrorCode& err)
{
return ByteSinkUtil::viaByteSinkToCharString(
@@ -2160,7 +2223,7 @@ ulocimp_canonicalize(const char* localeID,
}
U_EXPORT void
ulocimp_canonicalize(const char* localeID,
ulocimp_canonicalize(std::string_view localeID,
ByteSink& sink,
UErrorCode& err)
{

25
intl/icu/source/common/uloc_tag.cpp
View File

@@ -1043,7 +1043,7 @@ _initializeULanguageTag(ULanguageTag* langtag) {
}
void
_appendLanguageToLanguageTag(const char* localeID, icu::ByteSink& sink, bool strict, UErrorCode& status) {
_appendLanguageToLanguageTag(std::string_view localeID, icu::ByteSink& sink, bool strict, UErrorCode& status) {
UErrorCode tmpStatus = U_ZERO_ERROR;
if (U_FAILURE(status)) {
@@ -1088,7 +1088,7 @@ _appendLanguageToLanguageTag(const char* localeID, icu::ByteSink& sink, bool str
}
void
_appendScriptToLanguageTag(const char* localeID, icu::ByteSink& sink, bool strict, UErrorCode& status) {
_appendScriptToLanguageTag(std::string_view localeID, icu::ByteSink& sink, bool strict, UErrorCode& status) {
UErrorCode tmpStatus = U_ZERO_ERROR;
if (U_FAILURE(status)) {
@@ -1118,7 +1118,7 @@ _appendScriptToLanguageTag(const char* localeID, icu::ByteSink& sink, bool stric
}
void
_appendRegionToLanguageTag(const char* localeID, icu::ByteSink& sink, bool strict, UErrorCode& status) {
_appendRegionToLanguageTag(std::string_view localeID, icu::ByteSink& sink, bool strict, UErrorCode& status) {
UErrorCode tmpStatus = U_ZERO_ERROR;
if (U_FAILURE(status)) {
@@ -1169,7 +1169,7 @@ void _sortVariants(VariantListEntry* first) {
}
void
_appendVariantsToLanguageTag(const char* localeID, icu::ByteSink& sink, bool strict, bool& hadPosix, UErrorCode& status) {
_appendVariantsToLanguageTag(std::string_view localeID, icu::ByteSink& sink, bool strict, bool& hadPosix, UErrorCode& status) {
if (U_FAILURE(status)) { return; }
UErrorCode tmpStatus = U_ZERO_ERROR;
@@ -1872,7 +1872,7 @@ _appendKeywords(ULanguageTag* langtag, icu::ByteSink& sink, UErrorCode& status)
}
void
_appendPrivateuseToLanguageTag(const char* localeID, icu::ByteSink& sink, bool strict, bool /*hadPosix*/, UErrorCode& status) {
_appendPrivateuseToLanguageTag(std::string_view localeID, icu::ByteSink& sink, bool strict, bool /*hadPosix*/, UErrorCode& status) {
if (U_FAILURE(status)) { return; }
UErrorCode tmpStatus = U_ZERO_ERROR;
@@ -2596,6 +2596,9 @@ ulocimp_toLanguageTag(const char* localeID,
bool hadPosix = false;
const char* pKeywordStart;
if (localeID == nullptr) {
localeID = uloc_getDefault();
}
/* Note: uloc_canonicalize returns "en_US_POSIX" for input locale ID "". See #6835 */
icu::CharString canonical = ulocimp_canonicalize(localeID, tmpStatus);
if (U_FAILURE(tmpStatus)) {
@@ -2604,7 +2607,7 @@ ulocimp_toLanguageTag(const char* localeID,
}
/* For handling special case - private use only tag */
pKeywordStart = locale_getKeywordsStart(canonical.data());
pKeywordStart = locale_getKeywordsStart(canonical.toStringPiece());
if (pKeywordStart == canonical.data()) {
int kwdCnt = 0;
bool done = false;
@@ -2642,12 +2645,12 @@ ulocimp_toLanguageTag(const char* localeID,
}
}
_appendLanguageToLanguageTag(canonical.data(), sink, strict, status);
_appendScriptToLanguageTag(canonical.data(), sink, strict, status);
_appendRegionToLanguageTag(canonical.data(), sink, strict, status);
_appendVariantsToLanguageTag(canonical.data(), sink, strict, hadPosix, status);
_appendLanguageToLanguageTag(canonical.toStringPiece(), sink, strict, status);
_appendScriptToLanguageTag(canonical.toStringPiece(), sink, strict, status);
_appendRegionToLanguageTag(canonical.toStringPiece(), sink, strict, status);
_appendVariantsToLanguageTag(canonical.toStringPiece(), sink, strict, hadPosix, status);
_appendKeywordsToLanguageTag(canonical.data(), sink, strict, hadPosix, status);
_appendPrivateuseToLanguageTag(canonical.data(), sink, strict, hadPosix, status);
_appendPrivateuseToLanguageTag(canonical.toStringPiece(), sink, strict, hadPosix, status);
}

5
intl/icu/source/common/ulocale.cpp
View File

@@ -10,7 +10,6 @@
#include "unicode/locid.h"
#include "bytesinkutil.h"
#include "charstr.h"
#include "cmemory.h"
U_NAMESPACE_USE
@@ -24,9 +23,7 @@ ulocale_openForLocaleID(const char* localeID, int32_t length, UErrorCode* err) {
if (length < 0) {
return EXTERNAL(icu::Locale::createFromName(localeID).clone());
}
CharString str(localeID, length, *err); // Make a NUL terminated copy.
if (U_FAILURE(*err)) { return nullptr; }
return EXTERNAL(icu::Locale::createFromName(str.data()).clone());
return EXTERNAL(icu::Locale::createFromName(StringPiece{localeID, length}).clone());
}
ULocale*

32
intl/icu/source/common/ulocimp.h
View File

@@ -68,42 +68,42 @@ U_EXPORT std::optional<std::string_view>
ulocimp_toLegacyTypeWithFallback(std::string_view keyword, std::string_view value);
U_EXPORT icu::CharString
ulocimp_getKeywords(const char* localeID,
ulocimp_getKeywords(std::string_view localeID,
char prev,
bool valuesToo,
UErrorCode& status);
U_EXPORT void
ulocimp_getKeywords(const char* localeID,
ulocimp_getKeywords(std::string_view localeID,
char prev,
icu::ByteSink& sink,
bool valuesToo,
UErrorCode& status);
U_EXPORT icu::CharString
ulocimp_getName(const char* localeID,
ulocimp_getName(std::string_view localeID,
UErrorCode& err);
U_EXPORT void
ulocimp_getName(const char* localeID,
ulocimp_getName(std::string_view localeID,
icu::ByteSink& sink,
UErrorCode& err);
U_EXPORT icu::CharString
ulocimp_getBaseName(const char* localeID,
ulocimp_getBaseName(std::string_view localeID,
UErrorCode& err);
U_EXPORT void
ulocimp_getBaseName(const char* localeID,
ulocimp_getBaseName(std::string_view localeID,
icu::ByteSink& sink,
UErrorCode& err);
U_EXPORT icu::CharString
ulocimp_canonicalize(const char* localeID,
ulocimp_canonicalize(std::string_view localeID,
UErrorCode& err);
U_EXPORT void
ulocimp_canonicalize(const char* localeID,
ulocimp_canonicalize(std::string_view localeID,
icu::ByteSink& sink,
UErrorCode& err);
@@ -119,16 +119,16 @@ ulocimp_getKeywordValue(const char* localeID,
UErrorCode& status);
U_EXPORT icu::CharString
ulocimp_getLanguage(const char* localeID, UErrorCode& status);
ulocimp_getLanguage(std::string_view localeID, UErrorCode& status);
U_EXPORT icu::CharString
ulocimp_getScript(const char* localeID, UErrorCode& status);
ulocimp_getScript(std::string_view localeID, UErrorCode& status);
U_EXPORT icu::CharString
ulocimp_getRegion(const char* localeID, UErrorCode& status);
ulocimp_getRegion(std::string_view localeID, UErrorCode& status);
U_EXPORT icu::CharString
ulocimp_getVariant(const char* localeID, UErrorCode& status);
ulocimp_getVariant(std::string_view localeID, UErrorCode& status);
U_EXPORT void
ulocimp_setKeywordValue(std::string_view keywordName,
@@ -145,7 +145,7 @@ ulocimp_setKeywordValue(std::string_view keywords,
U_EXPORT void
ulocimp_getSubtags(
const char* localeID,
std::string_view localeID,
icu::CharString* language,
icu::CharString* script,
icu::CharString* region,
@@ -155,7 +155,7 @@ ulocimp_getSubtags(
U_EXPORT void
ulocimp_getSubtags(
const char* localeID,
std::string_view localeID,
icu::ByteSink* language,
icu::ByteSink* script,
icu::ByteSink* region,
@@ -165,7 +165,7 @@ ulocimp_getSubtags(
inline void
ulocimp_getSubtags(
const char* localeID,
std::string_view localeID,
std::nullptr_t,
std::nullptr_t,
std::nullptr_t,
@@ -364,7 +364,7 @@ ulocimp_minimizeSubtags(const char* localeID,
UErrorCode& err);
U_CAPI const char * U_EXPORT2
locale_getKeywordsStart(const char *localeID);
locale_getKeywordsStart(std::string_view localeID);
bool
ultag_isExtensionSubtags(const char* s, int32_t len);

7
intl/icu/source/common/umapfile.cpp
View File

@@ -237,8 +237,13 @@ typedef HANDLE MemoryMap;
pData->map = (char *)data + length;
pData->pHeader=(const DataHeader *)data;
pData->mapAddr = data;
#if U_PLATFORM == U_PF_IPHONE
#if U_PLATFORM == U_PF_IPHONE || U_PLATFORM == U_PF_ANDROID
// Apparently supported from Android 23 and higher:
// https://github.com/ggml-org/llama.cpp/pull/3631
// Checking for the flag itself is safer than checking for __ANDROID_API__.
# ifdef POSIX_MADV_RANDOM
posix_madvise(data, length, POSIX_MADV_RANDOM);
# endif
#endif
return true;
}

8
intl/icu/source/common/unicode/brkiter.h
View File

@@ -58,6 +58,8 @@ U_NAMESPACE_END
U_NAMESPACE_BEGIN
class CharString;
/**
* The BreakIterator class implements methods for finding the location
* of boundaries in text. BreakIterator is an abstract base class.
@@ -646,9 +648,9 @@ protected:
private:
/** @internal (private) */
char actualLocale[ULOC_FULLNAME_CAPACITY];
char validLocale[ULOC_FULLNAME_CAPACITY];
char requestLocale[ULOC_FULLNAME_CAPACITY];
CharString* actualLocale = nullptr;
CharString* validLocale = nullptr;
CharString* requestLocale = nullptr;
};
#ifndef U_HIDE_DEPRECATED_API

77
intl/icu/source/common/unicode/char16ptr.h
View File

@@ -9,10 +9,13 @@
#include "unicode/utypes.h"
#if U_SHOW_CPLUSPLUS_API
#if U_SHOW_CPLUSPLUS_API || U_SHOW_CPLUSPLUS_HEADER_API
#include <cstddef>
#include <string_view>
#include <type_traits>
#endif
/**
* \file
@@ -21,8 +24,6 @@
* Also conversion functions from char16_t * to UChar * and OldUChar *.
*/
U_NAMESPACE_BEGIN
/**
* \def U_ALIASING_BARRIER
* Barrier for pointer anti-aliasing optimizations even across function boundaries.
@@ -36,6 +37,11 @@ U_NAMESPACE_BEGIN
# define U_ALIASING_BARRIER(ptr)
#endif
// ICU DLL-exported
#if U_SHOW_CPLUSPLUS_API
U_NAMESPACE_BEGIN
/**
* char16_t * wrapper with implicit conversion from distinct but bit-compatible pointer types.
* @stable ICU 59
@@ -251,6 +257,60 @@ const char16_t *ConstChar16Ptr::get() const { return u_.cp; }
#endif
/// \endcond
U_NAMESPACE_END
#endif // U_SHOW_CPLUSPLUS_API
// Usable in header-only definitions
#if U_SHOW_CPLUSPLUS_API || U_SHOW_CPLUSPLUS_HEADER_API
namespace U_ICU_NAMESPACE_OR_INTERNAL {
#ifndef U_FORCE_HIDE_INTERNAL_API
/** @internal */
template<typename T, typename = std::enable_if_t<std::is_same_v<T, UChar>>>
inline const char16_t *uprv_char16PtrFromUChar(const T *p) {
if constexpr (std::is_same_v<UChar, char16_t>) {
return p;
} else {
#if U_SHOW_CPLUSPLUS_API
return ConstChar16Ptr(p).get();
#else
#ifdef U_ALIASING_BARRIER
U_ALIASING_BARRIER(p);
#endif
return reinterpret_cast<const char16_t *>(p);
#endif
}
}
#if !U_CHAR16_IS_TYPEDEF && (!defined(_LIBCPP_VERSION) || _LIBCPP_VERSION < 180000)
/** @internal */
inline const char16_t *uprv_char16PtrFromUint16(const uint16_t *p) {
#if U_SHOW_CPLUSPLUS_API
return ConstChar16Ptr(p).get();
#else
#ifdef U_ALIASING_BARRIER
U_ALIASING_BARRIER(p);
#endif
return reinterpret_cast<const char16_t *>(p);
#endif
}
#endif
#if U_SIZEOF_WCHAR_T==2
/** @internal */
inline const char16_t *uprv_char16PtrFromWchar(const wchar_t *p) {
#if U_SHOW_CPLUSPLUS_API
return ConstChar16Ptr(p).get();
#else
#ifdef U_ALIASING_BARRIER
U_ALIASING_BARRIER(p);
#endif
return reinterpret_cast<const char16_t *>(p);
#endif
}
#endif
#endif
/**
* Converts from const char16_t * to const UChar *.
* Includes an aliasing barrier if available.
@@ -307,6 +367,15 @@ inline OldUChar *toOldUCharPtr(char16_t *p) {
return reinterpret_cast<OldUChar *>(p);
}
} // U_ICU_NAMESPACE_OR_INTERNAL
#endif // U_SHOW_CPLUSPLUS_API || U_SHOW_CPLUSPLUS_HEADER_API
// ICU DLL-exported
#if U_SHOW_CPLUSPLUS_API
U_NAMESPACE_BEGIN
#ifndef U_FORCE_HIDE_INTERNAL_API
/**
* Is T convertible to a std::u16string_view or some other 16-bit string view?
@@ -379,6 +448,6 @@ inline std::u16string_view toU16StringViewNullable(const T& text) {
U_NAMESPACE_END
#endif /* U_SHOW_CPLUSPLUS_API */
#endif // U_SHOW_CPLUSPLUS_API
#endif // __CHAR16PTR_H__

9
intl/icu/source/common/unicode/locid.h
View File

@@ -449,6 +449,11 @@ public:
*/
static Locale U_EXPORT2 createFromName(const char *name);
#ifndef U_HIDE_INTERNAL_API
/** @internal */
static Locale U_EXPORT2 createFromName(StringPiece name);
#endif /* U_HIDE_INTERNAL_API */
/**
* Creates a locale from the given string after canonicalizing
* the string according to CLDR by calling uloc_canonicalize().
@@ -1133,7 +1138,9 @@ private:
* @param cLocaleID The new locale name.
* @param canonicalize whether to call uloc_canonicalize on cLocaleID
*/
Locale& init(const char* cLocaleID, UBool canonicalize);
Locale& init(const char* localeID, UBool canonicalize);
/** @internal */
Locale& init(StringPiece localeID, UBool canonicalize);
/*
* Internal constructor to allow construction of a locale object with

2
intl/icu/source/common/unicode/resbund.h
View File

@@ -450,7 +450,7 @@ public:
* @return a Locale object
* @stable ICU 2.8
*/
const Locale
Locale
getLocale(ULocDataLocaleType type, UErrorCode &status) const;
#ifndef U_HIDE_INTERNAL_API
/**

48
intl/icu/source/common/unicode/uchar.h
View File

@@ -675,14 +675,14 @@ typedef enum UProperty {
* @stable ICU 63
*/
UCHAR_VERTICAL_ORIENTATION=0x1018,
#ifndef U_HIDE_DRAFT_API
/**
* Enumerated property Identifier_Status.
* Used for UTS #39 General Security Profile for Identifiers
* (https://www.unicode.org/reports/tr39/#General_Security_Profile).
* @draft ICU 75
* @stable ICU 75
*/
UCHAR_IDENTIFIER_STATUS=0x1019,
#ifndef U_HIDE_DRAFT_API
/**
* Enumerated property Indic_Conjunct_Break.
* Used in the grapheme cluster break algorithm in UAX #29.
@@ -796,7 +796,6 @@ typedef enum UProperty {
UCHAR_SCRIPT_EXTENSIONS=0x7000,
/** First constant for Unicode properties with unusual value types. @stable ICU 4.6 */
UCHAR_OTHER_PROPERTY_START=UCHAR_SCRIPT_EXTENSIONS,
#ifndef U_HIDE_DRAFT_API
/**
* Miscellaneous property Identifier_Type.
* Used for UTS #39 General Security Profile for Identifiers
@@ -808,10 +807,9 @@ typedef enum UProperty {
*
* @see u_hasIDType
* @see u_getIDTypes
* @draft ICU 75
* @stable ICU 75
*/
UCHAR_IDENTIFIER_TYPE=0x7001,
#endif // U_HIDE_DRAFT_API
#ifndef U_HIDE_DEPRECATED_API
/**
* One more than the last constant for Unicode properties with unusual value types.
@@ -2791,13 +2789,12 @@ typedef enum UVerticalOrientation {
U_VO_UPRIGHT,
} UVerticalOrientation;
#ifndef U_HIDE_DRAFT_API
/**
* Identifier Status constants.
* See https://www.unicode.org/reports/tr39/#Identifier_Status_and_Type.
*
* @see UCHAR_IDENTIFIER_STATUS
* @draft ICU 75
* @stable ICU 75
*/
typedef enum UIdentifierStatus {
/*
@@ -2806,9 +2803,9 @@ typedef enum UIdentifierStatus {
* U_ID_STATUS_<Unicode Identifier_Status value name>
*/
/** @draft ICU 75 */
/** @stable ICU 75 */
U_ID_STATUS_RESTRICTED,
/** @draft ICU 75 */
/** @stable ICU 75 */
U_ID_STATUS_ALLOWED,
} UIdentifierStatus;
@@ -2817,7 +2814,7 @@ typedef enum UIdentifierStatus {
* See https://www.unicode.org/reports/tr39/#Identifier_Status_and_Type.
*
* @see UCHAR_IDENTIFIER_TYPE
* @draft ICU 75
* @stable ICU 75
*/
typedef enum UIdentifierType {
/*
@@ -2826,32 +2823,31 @@ typedef enum UIdentifierType {
* U_ID_TYPE_<Unicode Identifier_Type value name>
*/
/** @draft ICU 75 */
/** @stable ICU 75 */
U_ID_TYPE_NOT_CHARACTER,
/** @draft ICU 75 */
/** @stable ICU 75 */
U_ID_TYPE_DEPRECATED,
/** @draft ICU 75 */
/** @stable ICU 75 */
U_ID_TYPE_DEFAULT_IGNORABLE,
/** @draft ICU 75 */
/** @stable ICU 75 */
U_ID_TYPE_NOT_NFKC,
/** @draft ICU 75 */
/** @stable ICU 75 */
U_ID_TYPE_NOT_XID,
/** @draft ICU 75 */
/** @stable ICU 75 */
U_ID_TYPE_EXCLUSION,
/** @draft ICU 75 */
/** @stable ICU 75 */
U_ID_TYPE_OBSOLETE,
/** @draft ICU 75 */
/** @stable ICU 75 */
U_ID_TYPE_TECHNICAL,
/** @draft ICU 75 */
/** @stable ICU 75 */
U_ID_TYPE_UNCOMMON_USE,
/** @draft ICU 75 */
/** @stable ICU 75 */
U_ID_TYPE_LIMITED_USE,
/** @draft ICU 75 */
/** @stable ICU 75 */
U_ID_TYPE_INCLUSION,
/** @draft ICU 75 */
/** @stable ICU 75 */
U_ID_TYPE_RECOMMENDED,
} UIdentifierType;
#endif // U_HIDE_DRAFT_API
/**
* Check a binary Unicode property for a code point.
@@ -4057,7 +4053,6 @@ u_isIDStart(UChar32 c);
U_CAPI UBool U_EXPORT2
u_isIDPart(UChar32 c);
#ifndef U_HIDE_DRAFT_API
/**
* Does the set of Identifier_Type values code point c contain the given type?
*
@@ -4069,7 +4064,7 @@ u_isIDPart(UChar32 c);
* @param c code point
* @param type Identifier_Type to check
* @return true if type is in Identifier_Type(c)
* @draft ICU 75
* @stable ICU 75
*/
U_CAPI bool U_EXPORT2
u_hasIDType(UChar32 c, UIdentifierType type);
@@ -4104,11 +4099,10 @@ u_hasIDType(UChar32 c, UIdentifierType type);
* function chaining. (See User Guide for details.)
* @return number of values in c's Identifier_Type,
* written to types unless U_BUFFER_OVERFLOW_ERROR indicates insufficient capacity
* @draft ICU 75
* @stable ICU 75
*/
U_CAPI int32_t U_EXPORT2
u_getIDTypes(UChar32 c, UIdentifierType *types, int32_t capacity, UErrorCode *pErrorCode);
#endif // U_HIDE_DRAFT_API
/**
* Determines if the specified character should be regarded

11
intl/icu/source/common/unicode/uniset.h
View File

@@ -1173,10 +1173,12 @@ public:
inline U_HEADER_NESTED_NAMESPACE::USetStrings strings() const {
return U_HEADER_NESTED_NAMESPACE::USetStrings(toUSet());
}
#endif // U_HIDE_DRAFT_API
#ifndef U_HIDE_DRAFT_API
/**
* Returns a C++ iterator for iterating over all of the elements of this set.
* Convenient all-in one iteration, but creates a UnicodeString for each
* Convenient all-in one iteration, but creates a std::u16string for each
* code point or string.
* (Similar to how Java UnicodeSet *is an* Iterable&lt;String&gt;.)
*
@@ -1185,13 +1187,14 @@ public:
* \code
* UnicodeSet set(u"[abcçカ🚴{}{abc}{de}]", errorCode);
* for (auto el : set) {
* UnicodeString us(el);
* std::string u8;
* printf("set.string length %ld \"%s\"\n", (long)el.length(), el.toUTF8String(u8).c_str());
* printf("set.element length %ld \"%s\"\n", (long)us.length(), us.toUTF8String(u8).c_str());
* }
* \endcode
*
* @return an all-elements iterator.
* @draft ICU 76
* @draft ICU 77
* @see end
* @see codePoints
* @see ranges
@@ -1203,7 +1206,7 @@ public:
/**
* @return an exclusive-end sentinel for iterating over all of the elements of this set.
* @draft ICU 76
* @draft ICU 77
* @see begin
* @see codePoints
* @see ranges

92
intl/icu/source/common/unicode/uset.h
View File

@@ -32,12 +32,13 @@
#include "unicode/utypes.h"
#include "unicode/uchar.h"
#if U_SHOW_CPLUSPLUS_API
#if U_SHOW_CPLUSPLUS_API || U_SHOW_CPLUSPLUS_HEADER_API
#include <string>
#include <string_view>
#include "unicode/char16ptr.h"
#include "unicode/localpointer.h"
#include "unicode/unistr.h"
#endif // U_SHOW_CPLUSPLUS_API
#include "unicode/utf16.h"
#endif
#ifndef USET_DEFINED
@@ -1392,8 +1393,8 @@ public:
private:
friend class USetCodePoints;
USetCodePointIterator(const USet *uset, int32_t rangeIndex, int32_t rangeCount)
: uset(uset), rangeIndex(rangeIndex), rangeCount(rangeCount),
USetCodePointIterator(const USet *pUset, int32_t nRangeIndex, int32_t nRangeCount)
: uset(pUset), rangeIndex(nRangeIndex), rangeCount(nRangeCount),
c(U_SENTINEL), end(U_SENTINEL) {
// Fetch the first range.
operator++();
@@ -1429,7 +1430,7 @@ public:
* Constructs a C++ "range" object over the code points of the USet.
* @draft ICU 76
*/
USetCodePoints(const USet *uset) : uset(uset), rangeCount(uset_getRangeCount(uset)) {}
USetCodePoints(const USet *pUset) : uset(pUset), rangeCount(uset_getRangeCount(pUset)) {}
/** @draft ICU 76 */
USetCodePoints(const USetCodePoints &other) = default;
@@ -1460,7 +1461,7 @@ struct CodePointRange {
/** @draft ICU 76 */
struct iterator {
/** @draft ICU 76 */
iterator(UChar32 c) : c(c) {}
iterator(UChar32 aC) : c(aC) {}
/** @draft ICU 76 */
bool operator==(const iterator &other) const { return c == other.c; }
@@ -1573,8 +1574,8 @@ public:
private:
friend class USetRanges;
USetRangeIterator(const USet *uset, int32_t rangeIndex, int32_t rangeCount)
: uset(uset), rangeIndex(rangeIndex), rangeCount(rangeCount) {}
USetRangeIterator(const USet *pUset, int32_t nRangeIndex, int32_t nRangeCount)
: uset(pUset), rangeIndex(nRangeIndex), rangeCount(nRangeCount) {}
const USet *uset;
int32_t rangeIndex;
@@ -1610,7 +1611,7 @@ public:
* Constructs a C++ "range" object over the code point ranges of the USet.
* @draft ICU 76
*/
USetRanges(const USet *uset) : uset(uset), rangeCount(uset_getRangeCount(uset)) {}
USetRanges(const USet *pUset) : uset(pUset), rangeCount(uset_getRangeCount(pUset)) {}
/** @draft ICU 76 */
USetRanges(const USetRanges &other) = default;
@@ -1657,7 +1658,7 @@ public:
int32_t length;
const UChar *uchars = uset_getString(uset, index, &length);
// assert uchars != nullptr;
return {ConstChar16Ptr(uchars), static_cast<uint32_t>(length)};
return {uprv_char16PtrFromUChar(uchars), static_cast<size_t>(length)};
}
return {};
}
@@ -1684,8 +1685,8 @@ public:
private:
friend class USetStrings;
USetStringIterator(const USet *uset, int32_t index, int32_t count)
: uset(uset), index(index), count(count) {}
USetStringIterator(const USet *pUset, int32_t nIndex, int32_t nCount)
: uset(pUset), index(nIndex), count(nCount) {}
const USet *uset;
int32_t index;
@@ -1699,9 +1700,11 @@ private:
* using U_HEADER_NESTED_NAMESPACE::USetStrings;
* LocalUSetPointer uset(uset_openPattern(u"[abcçカ🚴{}{abc}{de}]", -1, &errorCode));
* for (auto s : USetStrings(uset.getAlias())) {
* UnicodeString us(s);
* std::string u8;
* printf("uset.string length %ld \"%s\"\n", (long)s.length(), us.toUTF8String(u8).c_str());
* int32_t len32 = s.length();
* char utf8[200];
* u_strToUTF8WithSub(utf8, int32_t{sizeof(utf8) - 1}, nullptr,
* s.data(), len32, 0xFFFD, nullptr, errorCode);
* printf("uset.string length %ld \"%s\"\n", long{len32}, utf8);
* }
* \endcode
*
@@ -1718,7 +1721,7 @@ public:
* Constructs a C++ "range" object over the strings of the USet.
* @draft ICU 76
*/
USetStrings(const USet *uset) : uset(uset), count(uset_getStringCount(uset)) {}
USetStrings(const USet *pUset) : uset(pUset), count(uset_getStringCount(pUset)) {}
/** @draft ICU 76 */
USetStrings(const USetStrings &other) = default;
@@ -1737,17 +1740,19 @@ private:
const USet *uset;
int32_t count;
};
#endif // U_HIDE_DRAFT_API
#ifndef U_HIDE_DRAFT_API
/**
* Iterator returned by USetElements.
* @draft ICU 76
* @draft ICU 77
*/
class USetElementIterator {
public:
/** @draft ICU 76 */
/** @draft ICU 77 */
USetElementIterator(const USetElementIterator &other) = default;
/** @draft ICU 76 */
/** @draft ICU 77 */
bool operator==(const USetElementIterator &other) const {
// No need to compare rangeCount & end given private constructor
// and assuming we don't compare iterators across the set being modified.
@@ -1756,26 +1761,28 @@ public:
return uset == other.uset && c == other.c && index == other.index;
}
/** @draft ICU 76 */
/** @draft ICU 77 */
bool operator!=(const USetElementIterator &other) const { return !operator==(other); }
/** @draft ICU 76 */
UnicodeString operator*() const {
/** @draft ICU 77 */
std::u16string operator*() const {
if (c >= 0) {
return UnicodeString(c);
return c <= 0xffff ?
std::u16string({static_cast<char16_t>(c)}) :
std::u16string({U16_LEAD(c), U16_TRAIL(c)});
} else if (index < totalCount) {
int32_t length;
const UChar *uchars = uset_getString(uset, index - rangeCount, &length);
// assert uchars != nullptr;
return UnicodeString(uchars, length);
return {uprv_char16PtrFromUChar(uchars), static_cast<size_t>(length)};
} else {
return UnicodeString();
return {};
}
}
/**
* Pre-increment.
* @draft ICU 76
* @draft ICU 77
*/
USetElementIterator &operator++() {
if (c < end) {
@@ -1800,7 +1807,7 @@ public:
/**
* Post-increment.
* @draft ICU 76
* @draft ICU 77
*/
USetElementIterator operator++(int) {
USetElementIterator result(*this);
@@ -1811,8 +1818,8 @@ public:
private:
friend class USetElements;
USetElementIterator(const USet *uset, int32_t index, int32_t rangeCount, int32_t totalCount)
: uset(uset), index(index), rangeCount(rangeCount), totalCount(totalCount),
USetElementIterator(const USet *pUset, int32_t nIndex, int32_t nRangeCount, int32_t nTotalCount)
: uset(pUset), index(nIndex), rangeCount(nRangeCount), totalCount(nTotalCount),
c(U_SENTINEL), end(U_SENTINEL) {
if (index < rangeCount) {
// Fetch the first range.
@@ -1840,7 +1847,7 @@ private:
/**
* A C++ "range" for iterating over all of the elements of a USet.
* Convenient all-in one iteration, but creates a UnicodeString for each
* Convenient all-in one iteration, but creates a std::u16string for each
* code point or string.
*
* Code points are returned first, then empty and multi-character strings.
@@ -1849,15 +1856,18 @@ private:
* using U_HEADER_NESTED_NAMESPACE::USetElements;
* LocalUSetPointer uset(uset_openPattern(u"[abcçカ🚴{}{abc}{de}]", -1, &errorCode));
* for (auto el : USetElements(uset.getAlias())) {
* std::string u8;
* printf("uset.string length %ld \"%s\"\n", (long)el.length(), el.toUTF8String(u8).c_str());
* int32_t len32 = el.length();
* char utf8[200];
* u_strToUTF8WithSub(utf8, int32_t{sizeof(utf8) - 1}, nullptr,
* el.data(), len32, 0xFFFD, nullptr, errorCode);
* printf("uset.element length %ld \"%s\"\n", long{len32}, utf8);
* }
* \endcode
*
* C++ UnicodeSet has member functions for iteration, including begin() and end().
*
* @return an all-elements iterator.
* @draft ICU 76
* @draft ICU 77
* @see USetCodePoints
* @see USetRanges
* @see USetStrings
@@ -1866,21 +1876,21 @@ class USetElements {
public:
/**
* Constructs a C++ "range" object over all of the elements of the USet.
* @draft ICU 76
* @draft ICU 77
*/
USetElements(const USet *uset)
: uset(uset), rangeCount(uset_getRangeCount(uset)),
stringCount(uset_getStringCount(uset)) {}
USetElements(const USet *pUset)
: uset(pUset), rangeCount(uset_getRangeCount(pUset)),
stringCount(uset_getStringCount(pUset)) {}
/** @draft ICU 76 */
/** @draft ICU 77 */
USetElements(const USetElements &other) = default;
/** @draft ICU 76 */
/** @draft ICU 77 */
USetElementIterator begin() const {
return USetElementIterator(uset, 0, rangeCount, rangeCount + stringCount);
}
/** @draft ICU 76 */
/** @draft ICU 77 */
USetElementIterator end() const {
return USetElementIterator(uset, rangeCount + stringCount, rangeCount, rangeCount + stringCount);
}

4
intl/icu/source/common/unicode/utf8.h
View File

@@ -124,7 +124,7 @@
* @internal
*/
U_CAPI UChar32 U_EXPORT2
utf8_nextCharSafeBody(const uint8_t *s, int32_t *pi, int32_t length, UChar32 c, UBool strict);
utf8_nextCharSafeBody(const uint8_t *s, int32_t *pi, int32_t length, UChar32 c, int8_t strict);
/**
* Function for handling "append code point" with error-checking.
@@ -148,7 +148,7 @@ utf8_appendCharSafeBody(uint8_t *s, int32_t i, int32_t length, UChar32 c, UBool
* @internal
*/
U_CAPI UChar32 U_EXPORT2
utf8_prevCharSafeBody(const uint8_t *s, int32_t start, int32_t *pi, UChar32 c, UBool strict);
utf8_prevCharSafeBody(const uint8_t *s, int32_t start, int32_t *pi, UChar32 c, int8_t strict);
/**
* Function for handling "skip backward one code point" with error-checking.

3
intl/icu/source/common/unicode/utypes.h
View File

@@ -598,12 +598,13 @@ typedef enum UErrorCode {
U_MF_DUPLICATE_DECLARATION_ERROR, /**< The same variable is declared in more than one .local or .input declaration. @internal ICU 75 technology preview @deprecated This API is for technology preview only. */
U_MF_OPERAND_MISMATCH_ERROR, /**< An operand provided to a function does not have the required form for that function @internal ICU 75 technology preview @deprecated This API is for technology preview only. */
U_MF_DUPLICATE_VARIANT_ERROR, /**< A message includes a variant with the same key list as another variant. @internal ICU 76 technology preview @deprecated This API is for technology preview only. */
U_MF_BAD_OPTION, /**< An option value provided to a function does not have the required form for that option. @internal ICU 77 technology preview @deprecated This API is for technology preview only. */
#ifndef U_HIDE_DEPRECATED_API
/**
* One more than the highest normal formatting API error code.
* @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
*/
U_FMT_PARSE_ERROR_LIMIT = 0x10120,
U_FMT_PARSE_ERROR_LIMIT = 0x10121,
#endif // U_HIDE_DEPRECATED_API
/*

10
intl/icu/source/common/unicode/uvernum.h
View File

@@ -53,7 +53,7 @@
* This value will change in the subsequent releases of ICU
* @stable ICU 2.4
*/
#define U_ICU_VERSION_MAJOR_NUM 76
#define U_ICU_VERSION_MAJOR_NUM 77
/** The current ICU minor version as an integer.
* This value will change in the subsequent releases of ICU
@@ -79,7 +79,7 @@
* This value will change in the subsequent releases of ICU
* @stable ICU 2.6
*/
#define U_ICU_VERSION_SUFFIX _76
#define U_ICU_VERSION_SUFFIX _77
/**
* \def U_DEF2_ICU_ENTRY_POINT_RENAME
@@ -132,7 +132,7 @@
* This value will change in the subsequent releases of ICU
* @stable ICU 2.4
*/
#define U_ICU_VERSION "76.1"
#define U_ICU_VERSION "77.1"
/**
* The current ICU library major version number as a string, for library name suffixes.
@@ -145,13 +145,13 @@
*
* @stable ICU 2.6
*/
#define U_ICU_VERSION_SHORT "76"
#define U_ICU_VERSION_SHORT "77"
#ifndef U_HIDE_INTERNAL_API
/** Data version in ICU4C.
* @internal ICU 4.4 Internal Use Only
**/
#define U_ICU_DATA_VERSION "76.1"
#define U_ICU_DATA_VERSION "77.1"
#endif /* U_HIDE_INTERNAL_API */
/*===========================================================================

19
intl/icu/source/common/unicode/uversion.h
View File

@@ -125,7 +125,7 @@ typedef uint8_t UVersionInfo[U_MAX_VERSION_LENGTH];
U_NAMESPACE_USE
# endif
#ifndef U_HIDE_DRAFT_API
#ifndef U_FORCE_HIDE_DRAFT_API
/**
* \def U_HEADER_NESTED_NAMESPACE
* Nested namespace used inside U_ICU_NAMESPACE for header-only APIs.
@@ -150,22 +150,37 @@ typedef uint8_t UVersionInfo[U_MAX_VERSION_LENGTH];
* @draft ICU 76
*/
/**
* \def U_ICU_NAMESPACE_OR_INTERNAL
* Namespace used for header-only APIs that used to be regular C++ APIs.
* Different when used inside ICU to prevent public use of internal instantiations.
* Similar to U_HEADER_ONLY_NAMESPACE, but the public definition is the same as U_ICU_NAMESPACE.
* "U_ICU_NAMESPACE" or "U_ICU_NAMESPACE::internal".
*
* @draft ICU 77
*/
// The first test is the same as for defining U_EXPORT for Windows.
#if defined(_MSC_VER) || (UPRV_HAS_DECLSPEC_ATTRIBUTE(__dllexport__) && \
UPRV_HAS_DECLSPEC_ATTRIBUTE(__dllimport__))
# define U_HEADER_NESTED_NAMESPACE header
# define U_ICU_NAMESPACE_OR_INTERNAL U_ICU_NAMESPACE
#elif defined(U_COMBINED_IMPLEMENTATION) || defined(U_COMMON_IMPLEMENTATION) || \
defined(U_I18N_IMPLEMENTATION) || defined(U_IO_IMPLEMENTATION) || \
defined(U_LAYOUTEX_IMPLEMENTATION) || defined(U_TOOLUTIL_IMPLEMENTATION)
# define U_HEADER_NESTED_NAMESPACE internal
# define U_ICU_NAMESPACE_OR_INTERNAL U_ICU_NAMESPACE::internal
namespace U_ICU_NAMESPACE_OR_INTERNAL {}
using namespace U_ICU_NAMESPACE_OR_INTERNAL;
#else
# define U_HEADER_NESTED_NAMESPACE header
# define U_ICU_NAMESPACE_OR_INTERNAL U_ICU_NAMESPACE
#endif
#define U_HEADER_ONLY_NAMESPACE U_ICU_NAMESPACE::U_HEADER_NESTED_NAMESPACE
namespace U_HEADER_ONLY_NAMESPACE {}
#endif // U_HIDE_DRAFT_API
#endif // U_FORCE_HIDE_DRAFT_API
#endif /* __cplusplus */

7
intl/icu/source/common/unistr.cpp
View File

@@ -1945,6 +1945,13 @@ UnicodeString::cloneArrayIfNeeded(int32_t newCapacity,
growCapacity = newCapacity;
} else if(newCapacity <= US_STACKBUF_SIZE && growCapacity > US_STACKBUF_SIZE) {
growCapacity = US_STACKBUF_SIZE;
} else if(newCapacity > growCapacity) {
setToBogus();
return false; // bad inputs
}
if(growCapacity > kMaxCapacity) {
setToBogus();
return false;
}
// save old values

8
intl/icu/source/common/uresbund.cpp
View File

@@ -2716,6 +2716,9 @@ ures_openWithType(UResourceBundle *r, const char* path, const char* localeID,
UResourceDataEntry *entry;
if(openType != URES_OPEN_DIRECT) {
if (localeID == nullptr) {
localeID = uloc_getDefault();
}
/* first "canonicalize" the locale ID */
CharString canonLocaleID = ulocimp_getBaseName(localeID, *status);
if(U_FAILURE(*status)) {
@@ -3080,6 +3083,9 @@ ures_getFunctionalEquivalent(char *result, int32_t resultCapacity,
kwVal.clear();
}
}
if (locid == nullptr) {
locid = uloc_getDefault();
}
CharString base = ulocimp_getBaseName(locid, subStatus);
#if defined(URES_TREE_DEBUG)
fprintf(stderr, "getFunctionalEquivalent: \"%s\" [%s=%s] in %s - %s\n",
@@ -3244,7 +3250,7 @@ ures_getFunctionalEquivalent(char *result, int32_t resultCapacity,
const char *validLoc = ures_getLocaleByType(res, ULOC_VALID_LOCALE, &subStatus);
if (U_SUCCESS(subStatus) && validLoc != nullptr && validLoc[0] != 0 && uprv_strcmp(validLoc, "root") != 0) {
CharString validLang = ulocimp_getLanguage(validLoc, subStatus);
CharString parentLang = ulocimp_getLanguage(parent.data(), subStatus);
CharString parentLang = ulocimp_getLanguage(parent.toStringPiece(), subStatus);
if (U_SUCCESS(subStatus) && validLang != parentLang) {
// validLoc is not root and has a different language than parent, use it instead
found.clear().append(validLoc, subStatus);

3
intl/icu/source/common/uscript.cpp
View File

@@ -59,6 +59,9 @@ getCodesFromLocale(const char *locale,
if (U_FAILURE(*err)) { return 0; }
icu::CharString lang;
icu::CharString script;
if (locale == nullptr) {
locale = uloc_getDefault();
}
ulocimp_getSubtags(locale, &lang, &script, nullptr, nullptr, nullptr, *err);
if (U_FAILURE(*err)) { return 0; }
// Multi-script languages, equivalent to the LocaleScript data

5
intl/icu/source/common/ushape.cpp
View File

@@ -28,6 +28,7 @@
#include "ubidi_props.h"
#include "uassert.h"
#include <limits>
/*
* This implementation is designed for 16-bit Unicode strings.
* The main assumption is that the Arabic characters and their
@@ -747,6 +748,10 @@ handleGeneratedSpaces(char16_t *dest, int32_t sourceLength,
}
}
if (static_cast<size_t>(sourceLength) + 1 > std::numeric_limits<size_t>::max() / U_SIZEOF_UCHAR) {
*pErrorCode = U_INDEX_OUTOFBOUNDS_ERROR;
return 0;
}
tempbuffer = static_cast<char16_t*>(uprv_malloc((sourceLength + 1) * U_SIZEOF_UCHAR));
/* Test for nullptr */
if(tempbuffer == nullptr) {

2
intl/icu/source/common/usprep.cpp
View File

@@ -126,7 +126,7 @@ compareEntries(const UHashTok p1, const UHashTok p2) {
name2.pointer = b2->name;
path1.pointer = b1->path;
path2.pointer = b2->path;
return uhash_compareChars(name1, name2) & uhash_compareChars(path1, path2);
return uhash_compareChars(name1, name2) && uhash_compareChars(path1, path2);
}
static void

6
intl/icu/source/common/utf_impl.cpp
View File

@@ -124,11 +124,9 @@ errorValue(int32_t count, int8_t strict) {
* >0 Obsolete "strict" behavior of UTF8_NEXT_CHAR_SAFE(..., true):
* Same as the obsolete "safe" behavior, but non-characters are also treated
* like illegal sequences.
*
* Note that a UBool is the same as an int8_t.
*/
U_CAPI UChar32 U_EXPORT2
utf8_nextCharSafeBody(const uint8_t *s, int32_t *pi, int32_t length, UChar32 c, UBool strict) {
utf8_nextCharSafeBody(const uint8_t *s, int32_t *pi, int32_t length, UChar32 c, int8_t strict) {
// *pi is one after byte c.
int32_t i=*pi;
// length can be negative for NUL-terminated strings: Read and validate one byte at a time.
@@ -233,7 +231,7 @@ utf8_appendCharSafeBody(uint8_t *s, int32_t i, int32_t length, UChar32 c, UBool
}
U_CAPI UChar32 U_EXPORT2
utf8_prevCharSafeBody(const uint8_t *s, int32_t start, int32_t *pi, UChar32 c, UBool strict) {
utf8_prevCharSafeBody(const uint8_t *s, int32_t start, int32_t *pi, UChar32 c, int8_t strict) {
// *pi is the index of byte c.
int32_t i=*pi;
if(U8_IS_TRAIL(c) && i>start) {

3
intl/icu/source/common/utypes.cpp
View File

@@ -140,7 +140,8 @@ _uFmtErrorName[U_FMT_PARSE_ERROR_LIMIT - U_FMT_PARSE_ERROR_START] = {
"U_MF_MISSING_SELECTOR_ANNOTATION_ERROR",
"U_MF_DUPLICATE_DECLARATION_ERROR",
"U_MF_OPERAND_MISMATCH_ERROR",
"U_MF_DUPLICATE_VARIANT_ERROR"
"U_MF_DUPLICATE_VARIANT_ERROR",
"U_MF_BAD_OPTION"
};
static const char * const

61
intl/icu/source/configure vendored
View File

@@ -1,6 +1,6 @@
#! /bin/sh
# Guess values for system-dependent variables and create Makefiles.
# Generated by GNU Autoconf 2.72 for ICU 76.1.
# Generated by GNU Autoconf 2.72 for ICU 77.1.
#
# Report bugs to <https://icu.unicode.org/bugs>.
#
@@ -606,8 +606,8 @@ MAKEFLAGS=
# Identity of this package.
PACKAGE_NAME='ICU'
PACKAGE_TARNAME='icu4c'
PACKAGE_VERSION='76.1'
PACKAGE_STRING='ICU 76.1'
PACKAGE_VERSION='77.1'
PACKAGE_STRING='ICU 77.1'
PACKAGE_BUGREPORT='https://icu.unicode.org/bugs'
PACKAGE_URL='https://icu.unicode.org/'
@@ -1387,7 +1387,7 @@ 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 76.1 to adapt to many kinds of systems.
'configure' configures ICU 77.1 to adapt to many kinds of systems.
Usage: $0 [OPTION]... [VAR=VALUE]...
@@ -1453,7 +1453,7 @@ fi
if test -n "$ac_init_help"; then
case $ac_init_help in
short | recursive ) echo "Configuration of ICU 76.1:";;
short | recursive ) echo "Configuration of ICU 77.1:";;
esac
cat <<\_ACEOF
@@ -1461,30 +1461,30 @@ Optional Features:
--disable-option-checking ignore unrecognized --enable/--with options
--disable-FEATURE do not include FEATURE (same as --enable-FEATURE=no)
--enable-FEATURE[=ARG] include FEATURE [ARG=yes]
--enable-icu-config install icu-config
--enable-debug build debug libraries and enable the U_DEBUG define default=no
--enable-release build release libraries default=yes
--enable-strict compile with strict compiler options default=yes
--disable-icu-config do not install icu-config
--enable-debug build debug libraries and enable the U_DEBUG define
--disable-release do not build release libraries
--disable-strict do not compile with strict compiler options
--enable-64bit-libs (deprecated, use --with-library-bits) build 64-bit libraries default= platform default
--enable-shared build shared libraries default=yes
--enable-static build static libraries default=no
--enable-auto-cleanup enable auto cleanup of libraries default=no
--enable-draft enable draft APIs (and internal APIs) default=yes
--enable-renaming add a version suffix to symbols default=yes
--enable-tracing enable function and data tracing default=no
--enable-plugins enable plugins default=no
--disable-dyload disable dynamic loading default=no
--disable-shared do not build shared libraries
--enable-static build static libraries
--enable-auto-cleanup enable auto cleanup of libraries
--disable-draft do not enable draft APIs (and internal APIs)
--disable-renaming do not add a version suffix to symbols
--enable-tracing enable function and data tracing
--enable-plugins enable plugins
--disable-dyload disable dynamic loading
--enable-rpath use rpath when linking default is only if necessary
--enable-weak-threads weakly reference the threading library default=no
--enable-extras build ICU extras default=yes
--enable-icuio build ICU's icuio library default=yes
--enable-layoutex build ICU's Paragraph Layout library default=no.
--enable-weak-threads weakly reference the threading library
--disable-extras do not build ICU extras
--disable-icuio do not build ICU's icuio library
--enable-layoutex build ICU's Paragraph Layout library.
icu-le-hb must be installed via pkg-config. See http://harfbuzz.org
--enable-tools build ICU's tools default=yes
--enable-fuzzer build ICU's fuzzer test targets default=no
--enable-tests build ICU tests default=yes
--enable-samples build ICU samples default=yes
--disable-tools do not build ICU's tools
--enable-fuzzer build ICU's fuzzer test targets
--disable-tests do not build ICU tests
--disable-samples do not build ICU samples
Additionally, the variable FORCE_LIBS may be set before calling configure.
If set, it will REPLACE any automatic list of libraries.
@@ -1592,7 +1592,7 @@ fi
test -n "$ac_init_help" && exit $ac_status
if $ac_init_version; then
cat <<\_ACEOF
ICU configure 76.1
ICU configure 77.1
generated by GNU Autoconf 2.72
Copyright (C) 2023 Free Software Foundation, Inc.
@@ -2184,7 +2184,7 @@ 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 76.1, which was
It was created by ICU $as_me 77.1, which was
generated by GNU Autoconf 2.72. Invocation command line was
$ $0$ac_configure_args_raw
@@ -8487,7 +8487,7 @@ echo "CXXFLAGS=$CXXFLAGS"
# output the Makefiles
ac_config_files="$ac_config_files icudefs.mk Makefile data/pkgdataMakefile config/Makefile.inc config/icu.pc config/pkgdataMakefile data/Makefile stubdata/Makefile common/Makefile i18n/Makefile layoutex/Makefile io/Makefile extra/Makefile extra/uconv/Makefile extra/uconv/pkgdataMakefile extra/scrptrun/Makefile tools/Makefile tools/ctestfw/Makefile tools/toolutil/Makefile tools/makeconv/Makefile tools/genrb/Makefile tools/genccode/Makefile tools/gencmn/Makefile tools/gencnval/Makefile tools/gendict/Makefile tools/gentest/Makefile tools/gennorm2/Makefile tools/genbrk/Makefile tools/gensprep/Makefile tools/icuinfo/Makefile tools/icupkg/Makefile tools/icuswap/Makefile tools/pkgdata/Makefile tools/icuexportdata/Makefile tools/tzcode/Makefile tools/gencfu/Makefile tools/escapesrc/Makefile test/Makefile test/compat/Makefile test/testdata/Makefile test/testdata/pkgdataMakefile test/hdrtst/Makefile test/intltest/Makefile test/cintltst/Makefile test/iotest/Makefile test/letest/Makefile test/perf/Makefile test/perf/collationperf/Makefile test/perf/collperf/Makefile test/perf/collperf2/Makefile test/perf/dicttrieperf/Makefile test/perf/ubrkperf/Makefile test/perf/charperf/Makefile test/perf/convperf/Makefile test/perf/localecanperf/Makefile test/perf/normperf/Makefile test/perf/DateFmtPerf/Makefile test/perf/howExpensiveIs/Makefile test/perf/strsrchperf/Makefile test/perf/unisetperf/Makefile test/perf/usetperf/Makefile test/perf/ustrperf/Makefile test/perf/utfperf/Makefile test/perf/utrie2perf/Makefile test/perf/leperf/Makefile test/fuzzer/Makefile samples/Makefile"
ac_config_files="$ac_config_files icudefs.mk Makefile data/pkgdataMakefile config/Makefile.inc config/icu.pc config/pkgdataMakefile data/Makefile stubdata/Makefile common/Makefile i18n/Makefile layoutex/Makefile io/Makefile extra/Makefile extra/uconv/Makefile extra/uconv/pkgdataMakefile extra/scrptrun/Makefile tools/Makefile tools/ctestfw/Makefile tools/toolutil/Makefile tools/makeconv/Makefile tools/genrb/Makefile tools/genccode/Makefile tools/gencmn/Makefile tools/gencnval/Makefile tools/gendict/Makefile tools/gentest/Makefile tools/gennorm2/Makefile tools/genbrk/Makefile tools/gensprep/Makefile tools/icuinfo/Makefile tools/icupkg/Makefile tools/icuswap/Makefile tools/pkgdata/Makefile tools/icuexportdata/Makefile tools/tzcode/Makefile tools/gencfu/Makefile tools/escapesrc/Makefile test/Makefile test/compat/Makefile test/testdata/Makefile test/testdata/pkgdataMakefile test/hdrtst/Makefile test/intltest/Makefile test/cintltst/Makefile test/iotest/Makefile test/letest/Makefile test/perf/Makefile test/perf/collationperf/Makefile test/perf/collperf/Makefile test/perf/collperf2/Makefile test/perf/dicttrieperf/Makefile test/perf/ubrkperf/Makefile test/perf/charperf/Makefile test/perf/convperf/Makefile test/perf/localecanperf/Makefile test/perf/normperf/Makefile test/perf/DateFmtPerf/Makefile test/perf/howExpensiveIs/Makefile test/perf/strsrchperf/Makefile test/perf/unisetperf/Makefile test/perf/usetperf/Makefile test/perf/ustrperf/Makefile test/perf/utfperf/Makefile test/perf/utrie2perf/Makefile test/fuzzer/Makefile samples/Makefile"
cat >confcache <<\_ACEOF
# This file is a shell script that caches the results of configure
@@ -9025,7 +9025,7 @@ cat >>$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 76.1, which was
This file was extended by ICU $as_me 77.1, which was
generated by GNU Autoconf 2.72. Invocation command line was
CONFIG_FILES = $CONFIG_FILES
@@ -9081,7 +9081,7 @@ ac_cs_config_escaped=`printf "%s\n" "$ac_cs_config" | sed "s/^ //; s/'/'\\\\\\\\
cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
ac_cs_config='$ac_cs_config_escaped'
ac_cs_version="\\
ICU config.status 76.1
ICU config.status 77.1
configured by $0, generated by GNU Autoconf 2.72,
with options \\"\$ac_cs_config\\"
@@ -9256,7 +9256,6 @@ do
"test/perf/ustrperf/Makefile") CONFIG_FILES="$CONFIG_FILES test/perf/ustrperf/Makefile" ;;
"test/perf/utfperf/Makefile") CONFIG_FILES="$CONFIG_FILES test/perf/utfperf/Makefile" ;;
"test/perf/utrie2perf/Makefile") CONFIG_FILES="$CONFIG_FILES test/perf/utrie2perf/Makefile" ;;
"test/perf/leperf/Makefile") CONFIG_FILES="$CONFIG_FILES test/perf/leperf/Makefile" ;;
"test/fuzzer/Makefile") CONFIG_FILES="$CONFIG_FILES test/fuzzer/Makefile" ;;
"samples/Makefile") CONFIG_FILES="$CONFIG_FILES samples/Makefile" ;;

39
intl/icu/source/configure.ac
View File

@@ -89,7 +89,7 @@ UCONFIG_CFLAGS=""
# Check whether to install icu-config
AC_ARG_ENABLE([icu-config],
AS_HELP_STRING([--enable-icu-config], [install icu-config]),
AS_HELP_STRING([--disable-icu-config], [do not install icu-config]),
[case "${enableval}" in
yes) enable_icu_config=true ;;
no) enable_icu_config=false ;;
@@ -102,7 +102,7 @@ AC_MSG_CHECKING([whether to build debug libraries])
enabled=no
ENABLE_DEBUG=0
AC_ARG_ENABLE(debug,
[ --enable-debug build debug libraries and enable the U_DEBUG define [default=no]],
[ --enable-debug build debug libraries and enable the U_DEBUG define],
[ case "${enableval}" in
yes|"") enabled=yes; ENABLE_DEBUG=1; CONFIG_CPPFLAGS="$CONFIG_CPPFLAGS -DU_DEBUG=1" ;;
*) ;;
@@ -116,7 +116,7 @@ AC_MSG_CHECKING([whether to build release libraries])
enabled=yes
ENABLE_RELEASE=1
AC_ARG_ENABLE(release,
[ --enable-release build release libraries [default=yes]],
[ --disable-release do not build release libraries],
[ case "${enableval}" in
no) enabled=no; ENABLE_RELEASE=0 ;;
*) ;;
@@ -270,7 +270,7 @@ AC_SUBST(LIB_M)
AC_MSG_CHECKING([whether to build shared libraries])
enabled=no
AC_ARG_ENABLE(shared,
[ --enable-shared build shared libraries [default=yes]],
[ --disable-shared do not build shared libraries],
[ case "${enableval}" in
yes|"") enabled=yes; ENABLE_SHARED=YES ;;
no);;
@@ -285,7 +285,7 @@ AC_SUBST(ENABLE_SHARED)
AC_MSG_CHECKING([whether to build static libraries])
enabled=no
AC_ARG_ENABLE(static,
[ --enable-static build static libraries [default=no]],
[ --enable-static build static libraries],
[ case "${enableval}" in
yes|"") enabled=yes; ENABLE_STATIC=YES ;;
no) ;;
@@ -332,7 +332,7 @@ AC_MSG_CHECKING([whether to enable auto cleanup of libraries])
enabled=no
UCLN_NO_AUTO_CLEANUP=1
AC_ARG_ENABLE(auto-cleanup,
[ --enable-auto-cleanup enable auto cleanup of libraries [default=no]],
[ --enable-auto-cleanup enable auto cleanup of libraries],
[ case "${enableval}" in
yes) enabled=yes;
CONFIG_CPPFLAGS="$CONFIG_CPPFLAGS -DUCLN_NO_AUTO_CLEANUP=0";
@@ -349,7 +349,7 @@ AC_MSG_CHECKING([whether to enable draft APIs])
enabled=yes
U_DEFAULT_SHOW_DRAFT=1
AC_ARG_ENABLE(draft,
[ --enable-draft enable draft APIs (and internal APIs) [default=yes]],
[ --disable-draft do not enable draft APIs (and internal APIs)],
[ case "${enableval}" in
no) enabled=no; U_DEFAULT_SHOW_DRAFT=0;
CONFIG_CPPFLAGS="$CONFIG_CPPFLAGS -DU_DEFAULT_SHOW_DRAFT=0"
@@ -376,7 +376,7 @@ AC_MSG_CHECKING([whether to enable renaming of symbols])
enabled=yes
U_DISABLE_RENAMING=0
AC_ARG_ENABLE(renaming,
[ --enable-renaming add a version suffix to symbols [default=yes]],
[ --disable-renaming do not add a version suffix to symbols],
[ case "${enableval}" in
yes|"") enabled=yes ;;
no) enabled=no; U_DISABLE_RENAMING=1;
@@ -392,7 +392,7 @@ AC_MSG_CHECKING([whether to enable function and data tracing])
enabled=no
U_ENABLE_TRACING=0
AC_ARG_ENABLE(tracing,
[ --enable-tracing enable function and data tracing [default=no]],
[ --enable-tracing enable function and data tracing],
[ case "${enableval}" in
yes|"") enabled=yes;
CONFIG_CPPFLAGS="$CONFIG_CPPFLAGS -DU_ENABLE_TRACING=1";
@@ -412,7 +412,7 @@ fi
# Enable/disable plugins
AC_ARG_ENABLE(plugins,
[ --enable-plugins enable plugins [default=no]],
[ --enable-plugins enable plugins],
[case "${enableval}" in
yes) plugins=true ;;
no) plugins=false ;;
@@ -430,7 +430,7 @@ U_ENABLE_DYLOAD=1
enable=yes
AC_MSG_CHECKING([whether to enable dynamic loading of plugins. Ignored if plugins disabled.])
AC_ARG_ENABLE(dyload,
[ --disable-dyload disable dynamic loading [default=no]],
[ --disable-dyload disable dynamic loading],
[ case "${enableval}" in
yes|"")
U_ENABLE_DYLOAD=1
@@ -577,7 +577,7 @@ case "${host}" in
esac
AC_ARG_ENABLE(weak-threads,
[ --enable-weak-threads weakly reference the threading library [default=no]],
[ --enable-weak-threads weakly reference the threading library],
[case "${enableval}" in
yes)
LIB_THREAD="${LIBS%${OLD_LIBS}}"
@@ -974,7 +974,7 @@ AC_MSG_RESULT($CHECK_UTF16_STRING_RESULT)
# Enable/disable extras
AC_ARG_ENABLE(extras,
[ --enable-extras build ICU extras [default=yes]],
[ --disable-extras do not build ICU extras],
[case "${enableval}" in
yes) extras=true ;;
no) extras=false ;;
@@ -983,7 +983,7 @@ AC_ARG_ENABLE(extras,
extras=true)
ICU_CONDITIONAL(EXTRAS, test "$extras" = true)
AC_ARG_ENABLE(icuio,
[ --enable-icuio build ICU's icuio library [default=yes]],
[ --disable-icuio do not build ICU's icuio library],
[case "${enableval}" in
yes) icuio=true ;;
no) icuio=false ;;
@@ -994,7 +994,7 @@ ICU_CONDITIONAL(ICUIO, test "$icuio" = true)
# Enable/disable layoutex
AC_ARG_ENABLE(layoutex,
[ --enable-layoutex build ICU's Paragraph Layout library [default=no].
[ --enable-layoutex build ICU's Paragraph Layout library.
icu-le-hb must be installed via pkg-config. See http://harfbuzz.org],
[case "${enableval}" in
yes) layoutex=$have_icu_le_hb ;;
@@ -1016,7 +1016,7 @@ AC_ARG_ENABLE(layout,
# Enable/disable tools
AC_ARG_ENABLE(tools,
[ --enable-tools build ICU's tools [default=yes]],
[ --disable-tools do not build ICU's tools],
[case "${enableval}" in
yes) tools=true ;;
no) tools=false ;;
@@ -1027,7 +1027,7 @@ ICU_CONDITIONAL(TOOLS, test "$tools" = true)
# Enable/disable fuzzer target tests.
AC_ARG_ENABLE(fuzzer,
[ --enable-fuzzer build ICU's fuzzer test targets [default=no]],
[ --enable-fuzzer build ICU's fuzzer test targets],
[case "${enableval}" in
yes) fuzzer=true ;;
no) fuzzer=false ;;
@@ -1144,7 +1144,7 @@ AC_SUBST(ICULIBSUFFIXCNAME)
# Enable/disable tests
AC_ARG_ENABLE(tests,
[ --enable-tests build ICU tests [default=yes]],
[ --disable-tests do not build ICU tests],
[case "${enableval}" in
yes) tests=true ;;
no) tests=false ;;
@@ -1155,7 +1155,7 @@ ICU_CONDITIONAL(TESTS, test "$tests" = true)
# Enable/disable samples
AC_ARG_ENABLE(samples,
[ --enable-samples build ICU samples [default=yes]
[ --disable-samples do not build ICU samples
Additionally, the variable FORCE_LIBS may be set before calling configure.
If set, it will REPLACE any automatic list of libraries.],
@@ -1304,7 +1304,6 @@ AC_CONFIG_FILES([icudefs.mk \
test/perf/ustrperf/Makefile \
test/perf/utfperf/Makefile \
test/perf/utrie2perf/Makefile \
test/perf/leperf/Makefile \
test/fuzzer/Makefile \
samples/Makefile])
AC_OUTPUT

4
intl/icu/source/data/brkitr/LOCALE_DEPS.json
View File

@@ -1,7 +1,7 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
{
"cldrVersion": "46"
"cldrVersion": "47"
}

2
intl/icu/source/data/brkitr/de.txt
View File

@@ -1,6 +1,6 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
de{
exceptions{
SentenceBreak:array{

2
intl/icu/source/data/brkitr/el.txt
View File

@@ -1,6 +1,6 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
el{
boundaries{
sentence:process(dependency){"sent_el.brk"}

2
intl/icu/source/data/brkitr/en.txt
View File

@@ -1,6 +1,6 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
en{
exceptions{
SentenceBreak:array{

2
intl/icu/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
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
en_US{
}

2
intl/icu/source/data/brkitr/en_US_POSIX.txt
View File

@@ -1,6 +1,6 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
en_US_POSIX{
boundaries{
word:process(dependency){"word_POSIX.brk"}

2
intl/icu/source/data/brkitr/es.txt
View File

@@ -1,6 +1,6 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
es{
exceptions{
SentenceBreak:array{

5
intl/icu/source/data/brkitr/fi.txt
View File

@@ -1,8 +1,5 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
fi{
boundaries{
word:process(dependency){"word_fi_sv.brk"}
}
}

2
intl/icu/source/data/brkitr/fr.txt
View File

@@ -1,6 +1,6 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
fr{
exceptions{
SentenceBreak:array{

2
intl/icu/source/data/brkitr/it.txt
View File

@@ -1,6 +1,6 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
it{
exceptions{
SentenceBreak:array{

2
intl/icu/source/data/brkitr/ja.txt
View File

@@ -1,6 +1,6 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
ja{
boundaries{
line:process(dependency){"line_normal.brk"}

2
intl/icu/source/data/brkitr/ko.txt
View File

@@ -1,6 +1,6 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
ko{
boundaries{
line:process(dependency){"line_normal.brk"}

2
intl/icu/source/data/brkitr/pt.txt
View File

@@ -1,6 +1,6 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
pt{
exceptions{
SentenceBreak:array{

4
intl/icu/source/data/brkitr/root.txt
View File

@@ -1,8 +1,8 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
root{
Version{"46"}
Version{"47"}
boundaries{
grapheme:process(dependency){"char.brk"}
line:process(dependency){"line.brk"}

2
intl/icu/source/data/brkitr/ru.txt
View File

@@ -1,6 +1,6 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
ru{
exceptions{
SentenceBreak:array{

14
intl/icu/source/data/brkitr/rules/char.txt
View File

@@ -24,13 +24,9 @@ $Regional_Indicator = [\p{Grapheme_Cluster_Break = Regional_Indicator}];
$Prepend = [\p{Grapheme_Cluster_Break = Prepend}];
$SpacingMark = [\p{Grapheme_Cluster_Break = SpacingMark}];
#
# From cldr/common/properties/segments/
# and issue CLDR-10994
#
$Virama = [\p{Gujr}\p{sc=Telu}\p{sc=Mlym}\p{sc=Orya}\p{sc=Beng}\p{sc=Deva}&\p{Indic_Syllabic_Category=Virama}];
$LinkingConsonant = [\p{Gujr}\p{sc=Telu}\p{sc=Mlym}\p{sc=Orya}\p{sc=Beng}\p{sc=Deva}&\p{Indic_Syllabic_Category=Consonant}];
$ExtCccZwj = [[\p{gcb=Extend}-\p{ccc=0}] \p{gcb=ZWJ}];
$InCBConsonant = [\p{InCB=Consonant}];
$InCBExtend = [\p{InCB=Extend}];
$InCBLinker = [\p{InCB=Linker}];
# Korean Syllable Definitions
#
@@ -64,8 +60,8 @@ $L ($L | $V | $LV | $LVT);
# GB 9b
$Prepend [^$Control $CR $LF];
# GB 9.3, from CLDR-10994
$LinkingConsonant $ExtCccZwj* $Virama $ExtCccZwj* $LinkingConsonant;
# GB 9c
$InCBConsonant [ $InCBExtend $InCBLinker ]* $InCBLinker [ $InCBExtend $InCBLinker ]* $InCBConsonant;
# GB 11 Do not break within emoji modifier sequences or emoji zwj sequences.
$Extended_Pict $Extend* $ZWJ $Extended_Pict;

2
intl/icu/source/data/brkitr/rules/line.txt
View File

@@ -297,7 +297,7 @@ $LB20NonBreaks = [$LB18NonBreaks - $CB];
# and then to default UAX #14 behaviour (UTC-179-C32).
#
^($HY | $HH) $CM* $ALPlus;
$GL ($HY | $HH) $CM* $ALPlus;
$GL $CM* ($HY | $HH) $CM* $ALPlus;
# Non-breaking CB from LB8a:
$CB $CM* $ZWJ ($HY | $HH) $CM* $ALPlus;
# Non-breaking SP from LB14:

2
intl/icu/source/data/brkitr/rules/line_cj.txt
View File

@@ -298,7 +298,7 @@ $LB20NonBreaks = [$LB18NonBreaks - $CB];
# and then to default UAX #14 behaviour (UTC-179-C32).
#
^($HY | $HH) $CM* $ALPlus;
$GL ($HY | $HH) $CM* $ALPlus;
$GL $CM* ($HY | $HH) $CM* $ALPlus;
# Non-breaking CB from LB8a:
$CB $CM* $ZWJ ($HY | $HH) $CM* $ALPlus;
# Non-breaking SP from LB14:

2
intl/icu/source/data/brkitr/rules/line_loose.txt
View File

@@ -306,7 +306,7 @@ $LB20NonBreaks = [$LB18NonBreaks - $CB];
# and then to default UAX #14 behaviour (UTC-179-C32).
#
^($HY | $HH) $CM* $ALPlus;
$GL ($HY | $HH) $CM* $ALPlus;
$GL $CM* ($HY | $HH) $CM* $ALPlus;
# Non-breaking CB from LB8a:
$CB $CM* $ZWJ ($HY | $HH) $CM* $ALPlus;
# Non-breaking SP from LB14:

2
intl/icu/source/data/brkitr/rules/line_loose_cj.txt
View File

@@ -318,7 +318,7 @@ $LB20NonBreaks = [$LB18NonBreaks - $CB];
# and then to default UAX #14 behaviour (UTC-179-C32).
#
^($HY | $HH) $CM* $ALPlus;
$GL ($HY | $HH) $CM* $ALPlus;
$GL $CM* ($HY | $HH) $CM* $ALPlus;
# Non-breaking CB from LB8a:
$CB $CM* $ZWJ ($HY | $HH) $CM* $ALPlus;
# Non-breaking SP from LB14:

2
intl/icu/source/data/brkitr/rules/line_loose_phrase_cj.txt
View File

@@ -331,7 +331,7 @@ $LB20NonBreaks = [$LB18NonBreaks - $CB];
# and then to default UAX #14 behaviour (UTC-179-C32).
#
^($HY | $HH) $CM* $ALPlus;
$GL ($HY | $HH) $CM* $ALPlus;
$GL $CM* ($HY | $HH) $CM* $ALPlus;
# Non-breaking CB from LB8a:
$CB $CM* $ZWJ ($HY | $HH) $CM* $ALPlus;
# Non-breaking SP from LB14:

2
intl/icu/source/data/brkitr/rules/line_normal.txt
View File

@@ -299,7 +299,7 @@ $LB20NonBreaks = [$LB18NonBreaks - $CB];
# and then to default UAX #14 behaviour (UTC-179-C32).
#
^($HY | $HH) $CM* $ALPlus;
$GL ($HY | $HH) $CM* $ALPlus;
$GL $CM* ($HY | $HH) $CM* $ALPlus;
# Non-breaking CB from LB8a:
$CB $CM* $ZWJ ($HY | $HH) $CM* $ALPlus;
# Non-breaking SP from LB14:

2
intl/icu/source/data/brkitr/rules/line_normal_cj.txt
View File

@@ -304,7 +304,7 @@ $LB20NonBreaks = [$LB18NonBreaks - $CB];
# and then to default UAX #14 behaviour (UTC-179-C32).
#
^($HY | $HH) $CM* $ALPlus;
$GL ($HY | $HH) $CM* $ALPlus;
$GL $CM* ($HY | $HH) $CM* $ALPlus;
# Non-breaking CB from LB8a:
$CB $CM* $ZWJ ($HY | $HH) $CM* $ALPlus;
# Non-breaking SP from LB14:

2
intl/icu/source/data/brkitr/rules/line_normal_phrase_cj.txt
View File

@@ -317,7 +317,7 @@ $LB20NonBreaks = [$LB18NonBreaks - $CB];
# and then to default UAX #14 behaviour (UTC-179-C32).
#
^($HY | $HH) $CM* $ALPlus;
$GL ($HY | $HH) $CM* $ALPlus;
$GL $CM* ($HY | $HH) $CM* $ALPlus;
# Non-breaking CB from LB8a:
$CB $CM* $ZWJ ($HY | $HH) $CM* $ALPlus;
# Non-breaking SP from LB14:

2
intl/icu/source/data/brkitr/rules/line_phrase_cj.txt
View File

@@ -310,7 +310,7 @@ $LB20NonBreaks = [$LB18NonBreaks - $CB];
# and then to default UAX #14 behaviour (UTC-179-C32).
#
^($HY | $HH) $CM* $ALPlus;
$GL ($HY | $HH) $CM* $ALPlus;
$GL $CM* ($HY | $HH) $CM* $ALPlus;
# Non-breaking CB from LB8a:
$CB $CM* $ZWJ ($HY | $HH) $CM* $ALPlus;
# Non-breaking SP from LB14:

4
intl/icu/source/data/brkitr/rules/word.txt
View File

@@ -11,7 +11,7 @@
# These rules are based on UAX #29 Revision 34 for Unicode Version 12.0
#
# Note: Updates to word.txt will usually need to be merged into
# word_POSIX.txt and word_fi_sv.txt also.
# word_POSIX.txt also.
##############################################################################
#
@@ -42,7 +42,7 @@ $ALetter = [\p{Word_Break = ALetter}];
$Single_Quote = [\p{Word_Break = Single_Quote}];
$Double_Quote = [\p{Word_Break = Double_Quote}];
$MidNumLet = [\p{Word_Break = MidNumLet}];
$MidLetter = [\p{Word_Break = MidLetter} - [\: \uFE55 \uFF1A]];
$MidLetter = [\p{Word_Break = MidLetter}];
$MidNum = [\p{Word_Break = MidNum}];
$Numeric = [\p{Word_Break = Numeric}];
$ExtendNumLet = [\p{Word_Break = ExtendNumLet}];

2
intl/icu/source/data/brkitr/rules/word_POSIX.txt
View File

@@ -42,7 +42,7 @@ $ALetter = [\p{Word_Break = ALetter}];
$Single_Quote = [\p{Word_Break = Single_Quote}];
$Double_Quote = [\p{Word_Break = Double_Quote}];
$MidNumLet = [\p{Word_Break = MidNumLet} - [.]];
$MidLetter = [\p{Word_Break = MidLetter} - [\: \uFE55 \uFF1A]];
$MidLetter = [\p{Word_Break = MidLetter} - [\:]];
$MidNum = [\p{Word_Break = MidNum} [.]];
$Numeric = [\p{Word_Break = Numeric}];
$ExtendNumLet = [\p{Word_Break = ExtendNumLet}];

172
intl/icu/source/data/brkitr/rules/word_fi_sv.txt
View File

@@ -1,172 +0,0 @@
#
# Copyright (C) 2016 and later: Unicode, Inc. and others.
# License & terms of use: http://www.unicode.org/copyright.html
# Copyright (C) 2002-2016, International Business Machines Corporation
# and others. All Rights Reserved.
#
# file: word_fi_sv.txt
#
# ICU Word Break Rules
# See Unicode Standard Annex #29.
# These rules are based on UAX #29 Revision 34 for Unicode Version 12.0
#
# Note: Updates to word.txt will usually need to be merged into
# word_fi_sv.txt also.
##############################################################################
#
# Character class definitions from TR 29
#
##############################################################################
!!chain;
!!quoted_literals_only;
#
# Character Class Definitions.
#
$Han = [:Han:];
$CR = [\p{Word_Break = CR}];
$LF = [\p{Word_Break = LF}];
$Newline = [\p{Word_Break = Newline}];
$Extend = [\p{Word_Break = Extend}-$Han];
$ZWJ = [\p{Word_Break = ZWJ}];
$Regional_Indicator = [\p{Word_Break = Regional_Indicator}];
$Format = [\p{Word_Break = Format}];
$Katakana = [\p{Word_Break = Katakana}];
$Hebrew_Letter = [\p{Word_Break = Hebrew_Letter}];
$ALetter = [\p{Word_Break = ALetter}];
$Single_Quote = [\p{Word_Break = Single_Quote}];
$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}];
$ExtendNumLet = [\p{Word_Break = ExtendNumLet}];
$WSegSpace = [\p{Word_Break = WSegSpace}];
$Extended_Pict = [\p{Extended_Pictographic}];
$Hiragana = [:Hiragana:];
$Ideographic = [\p{Ideographic}];
# Dictionary character set, for triggering language-based break engines. Currently
# limited to LineBreak=Complex_Context. Note that this set only works in Unicode
# 5.0 or later as the definition of Complex_Context was corrected to include all
# characters requiring dictionary break.
$Control = [\p{Grapheme_Cluster_Break = Control}];
$HangulSyllable = [\uac00-\ud7a3];
$ComplexContext = [:LineBreak = Complex_Context:];
$KanaKanji = [$Han $Hiragana $Katakana];
$dictionaryCJK = [$KanaKanji $HangulSyllable];
$dictionary = [$ComplexContext $dictionaryCJK];
# TODO: check if handling of katakana in dictionary makes rules incorrect/void
# leave CJK scripts out of ALetterPlus
$ALetterPlus = [$ALetter-$dictionaryCJK [$ComplexContext-$Extend-$Control]];
## -------------------------------------------------
# Rule 3 - CR x LF
#
$CR $LF;
# Rule 3c Do not break within emoji zwj sequences.
# ZWJ × \p{Extended_Pictographic}. Precedes WB4, so no intervening Extend chars allowed.
#
$ZWJ $Extended_Pict;
# Rule 3d - Keep horizontal whitespace together.
#
$WSegSpace $WSegSpace;
# Rule 4 - ignore Format and Extend characters, except when they appear at the beginning
# of a region of Text.
$ExFm = [$Extend $Format $ZWJ];
^$ExFm+; # This rule fires only when there are format or extend characters at the
# start of text, or immediately following another boundary. It groups them, in
# the event there are more than one.
[^$CR $LF $Newline $ExFm] $ExFm*; # This rule rule attaches trailing format/extends to words,
# with no special rule status value.
$Numeric $ExFm* {100}; # This group of rules also attach trailing format/extends, but
$ALetterPlus $ExFm* {200}; # with rule status set based on the word's final base character.
$HangulSyllable {200};
$Hebrew_Letter $ExFm* {200};
$Katakana $ExFm* {400}; # note: these status values override those from rule 5
$Hiragana $ExFm* {400}; # by virtue of being numerically larger.
$Ideographic $ExFm* {400}; #
#
# rule 5
# Do not break between most letters.
#
($ALetterPlus | $Hebrew_Letter) $ExFm* ($ALetterPlus | $Hebrew_Letter);
# rule 6 and 7
($ALetterPlus | $Hebrew_Letter) $ExFm* ($MidLetter | $MidNumLet | $Single_Quote) $ExFm* ($ALetterPlus | $Hebrew_Letter) {200};
# rule 7a
$Hebrew_Letter $ExFm* $Single_Quote {200};
# rule 7b and 7c
$Hebrew_Letter $ExFm* $Double_Quote $ExFm* $Hebrew_Letter;
# rule 8
$Numeric $ExFm* $Numeric;
# rule 9
($ALetterPlus | $Hebrew_Letter) $ExFm* $Numeric;
# rule 10
$Numeric $ExFm* ($ALetterPlus | $Hebrew_Letter);
# rule 11 and 12
$Numeric $ExFm* ($MidNum | $MidNumLet | $Single_Quote) $ExFm* $Numeric;
# rule 13
# to be consistent with $KanaKanji $KanaKanhi, changed
# from 300 to 400.
# See also TestRuleStatus in intltest/rbbiapts.cpp
$Katakana $ExFm* $Katakana {400};
# rule 13a/b
$ALetterPlus $ExFm* $ExtendNumLet {200}; # (13a)
$Hebrew_Letter $ExFm* $ExtendNumLet {200}; # (13a)
$Numeric $ExFm* $ExtendNumLet {100}; # (13a)
$Katakana $ExFm* $ExtendNumLet {400}; # (13a)
$ExtendNumLet $ExFm* $ExtendNumLet {200}; # (13a)
$ExtendNumLet $ExFm* $ALetterPlus {200}; # (13b)
$ExtendNumLet $ExFm* $Hebrew_Letter {200}; # (13b)
$ExtendNumLet $ExFm* $Numeric {100}; # (13b)
$ExtendNumLet $ExFm* $Katakana {400}; # (13b)
# rules 15 - 17
# Pairs of Regional Indicators stay together.
# With incoming rule chaining disabled by ^, this rule will match exactly two of them.
# No other rule begins with a Regional_Indicator, so chaining cannot extend the match.
#
^$Regional_Indicator $ExFm* $Regional_Indicator;
# special handling for CJK characters: chain for later dictionary segmentation
$HangulSyllable $HangulSyllable {200};
$KanaKanji $KanaKanji {400}; # different rule status if both kana and kanji found
# Rule 999
# Match a single code point if no other rule applies.
.;

5
intl/icu/source/data/brkitr/sv.txt
View File

@@ -1,8 +1,5 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
sv{
boundaries{
word:process(dependency){"word_fi_sv.brk"}
}
}

2
intl/icu/source/data/brkitr/zh.txt
View File

@@ -1,6 +1,6 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
zh{
boundaries{
line:process(dependency){"line_cj.brk"}

2
intl/icu/source/data/brkitr/zh_Hant.txt
View File

@@ -1,6 +1,6 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
zh_Hant{
boundaries{
line:process(dependency){"line_cj.brk"}

4
intl/icu/source/data/coll/LOCALE_DEPS.json
View File

@@ -1,9 +1,9 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
{
"cldrVersion": "46",
"cldrVersion": "47",
"aliases": {
"ars": "ar_SA",
"in": "id",

4
intl/icu/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
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
af{
collations{
standard{
Sequence{"&N<<<ʼn"}
Version{"46"}
Version{"47"}
}
}
}

4
intl/icu/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
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
am{
collations{
standard{
Sequence{"[reorder Ethi]"}
Version{"46"}
Version{"47"}
}
}
}

6
intl/icu/source/data/coll/ar.txt
View File

@@ -1,6 +1,6 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
ar{
collations{
compat{
@@ -9,7 +9,7 @@ ar{
"&ت<<ة<<<ﺔ<<<ﺓ"
"&ي<<ى<<<ﯨ<<<ﯩ<<<ﻰ<<<ﻯ<<<ﲐ<<<ﱝ"
}
Version{"46"}
Version{"47"}
}
standard{
Sequence{
@@ -397,7 +397,7 @@ ar{
"‎&ۓ‎=ﮰ‎=ﮱ"
"‎&ۀ‎=ﮤ‎=ﮥ"
}
Version{"46"}
Version{"47"}
}
}
}

2
intl/icu/source/data/coll/ar_SA.txt
View File

@@ -1,6 +1,6 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
/**
* generated alias target
*/

2
intl/icu/source/data/coll/ars.txt
View File

@@ -1,6 +1,6 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
ars{
"%%ALIAS"{"ar_SA"}
}

4
intl/icu/source/data/coll/as.txt
View File

@@ -1,6 +1,6 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
as{
collations{
standard{
@@ -11,7 +11,7 @@ as{
"&[before 1]ত<ৎ=ত্\u200D"
"&হ<ক্ষ"
}
Version{"46"}
Version{"47"}
}
}
}

6
intl/icu/source/data/coll/az.txt
View File

@@ -1,6 +1,6 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
az{
collations{
search{
@@ -9,7 +9,7 @@ az{
"[import az-u-co-standard]"
"[reorder others]"
}
Version{"46"}
Version{"47"}
}
standard{
Sequence{
@@ -26,7 +26,7 @@ az{
"&H<x<<<X"
"&Z<w<<<W"
}
Version{"46"}
Version{"47"}
}
}
}

4
intl/icu/source/data/coll/be.txt
View File

@@ -1,6 +1,6 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
be{
collations{
standard{
@@ -9,7 +9,7 @@ be{
"&Е<ё<<<Ё"
"&у<ў<<<Ў"
}
Version{"46"}
Version{"47"}
}
}
}

4
intl/icu/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
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
bg{
collations{
standard{
Sequence{"[reorder Cyrl]"}
Version{"46"}
Version{"47"}
}
}
}

6
intl/icu/source/data/coll/bn.txt
View File

@@ -1,6 +1,6 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
bn{
collations{
standard{
@@ -9,7 +9,7 @@ bn{
"[reorder Beng Deva Guru Gujr Orya Taml Telu Knda Mlym Sinh]"
"&ঔ<ং<ঃ<ঁ"
}
Version{"46"}
Version{"47"}
}
traditional{
Sequence{
@@ -629,7 +629,7 @@ bn{
"&যৌ<<<য়ৌ"
"&য্<<<য়্"
}
Version{"46"}
Version{"47"}
}
}
}

4
intl/icu/source/data/coll/bo.txt
View File

@@ -1,6 +1,6 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
bo{
collations{
standard{
@@ -65,7 +65,7 @@ bo{
"&ྲཱྀ=ཷ"
"&ླཱྀ=ཹ"
}
Version{"46"}
Version{"47"}
}
}
}

4
intl/icu/source/data/coll/br.txt
View File

@@ -1,6 +1,6 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
br{
collations{
standard{
@@ -8,7 +8,7 @@ br{
"&C<ch<<<Ch<<<CH<c''h=c\u02BCh=c\u2019h<<<C''h=C\u02BCh=C\u2019h<<<C'"
"'H=C\u02BCH=C\u2019H"
}
Version{"46"}
Version{"47"}
}
}
}

6
intl/icu/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
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
bs{
collations{
search{
Sequence{"[import hr-u-co-search]"}
Version{"46"}
Version{"47"}
}
standard{
Sequence{"[import hr]"}
Version{"46"}
Version{"47"}
}
}
}

4
intl/icu/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
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
bs_Cyrl{
collations{
standard{
Sequence{"[import sr]"}
Version{"46"}
Version{"47"}
}
}
}

4
intl/icu/source/data/coll/ca.txt
View File

@@ -1,6 +1,6 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
ca{
collations{
search{
@@ -8,7 +8,7 @@ ca{
"[import und-u-co-search]"
"&L<ŀ=l·<<<Ŀ=L·"
}
Version{"46"}
Version{"47"}
}
}
}

4
intl/icu/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
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
// Generated using tools/cldr/cldr-to-icu/
ceb{
collations{
standard{
Sequence{"&N<ñ<<<Ñ<ng<<<Ng<<<NG"}
Version{"46"}
Version{"47"}
}
}
}

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