Magic-Mirror/gecko-dev
1
0
Fork 0
mirror of https://github.com/mozilla/gecko-dev.git synced 2024-11-24 13:21:05 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Bug 1299615 - Part 3: Update in-tree ICU to release 58.1. rs=Waldo

Browse Source
This commit is contained in:
André Bargull 2016-11-03 05:27:28 -07:00
parent fb59f826a3
commit a934a3b70d
3038 changed files with 153518 additions and 72249 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
config/external/icu/common/sources.mozbuild vendored
View File

@ -12,6 +12,7 @@ SOURCES += [
'/intl/icu/source/common/chariter.cpp',
'/intl/icu/source/common/charstr.cpp',
'/intl/icu/source/common/cmemory.c',
'/intl/icu/source/common/cstr.cpp',
'/intl/icu/source/common/cstring.c',
'/intl/icu/source/common/cwchar.c',
'/intl/icu/source/common/dictbe.cpp',
@ -27,6 +28,7 @@ SOURCES += [
'/intl/icu/source/common/locavailable.cpp',
'/intl/icu/source/common/locbased.cpp',
'/intl/icu/source/common/locdispnames.cpp',
'/intl/icu/source/common/locdspnm.cpp',
'/intl/icu/source/common/locid.cpp',
'/intl/icu/source/common/loclikely.cpp',
'/intl/icu/source/common/locmap.c',
@ -53,6 +55,7 @@ SOURCES += [
'/intl/icu/source/common/rbbitblb.cpp',
'/intl/icu/source/common/resbund.cpp',
'/intl/icu/source/common/resbund_cnv.cpp',
'/intl/icu/source/common/resource.cpp',
'/intl/icu/source/common/ruleiter.cpp',
'/intl/icu/source/common/schriter.cpp',
'/intl/icu/source/common/serv.cpp',
@ -63,13 +66,14 @@ SOURCES += [
'/intl/icu/source/common/servrbf.cpp',
'/intl/icu/source/common/servslkf.cpp',
'/intl/icu/source/common/sharedobject.cpp',
'/intl/icu/source/common/simplepatternformatter.cpp',
'/intl/icu/source/common/simpleformatter.cpp',
'/intl/icu/source/common/stringpiece.cpp',
'/intl/icu/source/common/stringtriebuilder.cpp',
'/intl/icu/source/common/uarrsort.c',
'/intl/icu/source/common/ubidi.c',
'/intl/icu/source/common/ubidi_props.c',
'/intl/icu/source/common/ubidiln.c',
'/intl/icu/source/common/ubiditransform.c',
'/intl/icu/source/common/ubidiwrt.c',
'/intl/icu/source/common/ubrk.cpp',
'/intl/icu/source/common/ucase.cpp',
@ -107,6 +111,7 @@ SOURCES += [
'/intl/icu/source/common/ucnvscsu.c',
'/intl/icu/source/common/ucnvsel.cpp',
'/intl/icu/source/common/ucol_swp.cpp',
'/intl/icu/source/common/ucurr.cpp',
'/intl/icu/source/common/udata.cpp',
'/intl/icu/source/common/udatamem.c',
'/intl/icu/source/common/udataswp.c',
@ -145,7 +150,7 @@ SOURCES += [
'/intl/icu/source/common/uprops.cpp',
'/intl/icu/source/common/ures_cnv.c',
'/intl/icu/source/common/uresbund.cpp',
'/intl/icu/source/common/uresdata.c',
'/intl/icu/source/common/uresdata.cpp',
'/intl/icu/source/common/usc_impl.c',
'/intl/icu/source/common/uscript.c',
'/intl/icu/source/common/uscript_props.cpp',
@ -199,6 +204,7 @@ EXPORTS.unicode += [
'/intl/icu/source/common/unicode/idna.h',
'/intl/icu/source/common/unicode/listformatter.h',
'/intl/icu/source/common/unicode/localpointer.h',
'/intl/icu/source/common/unicode/locdspnm.h',
'/intl/icu/source/common/unicode/locid.h',
'/intl/icu/source/common/unicode/messagepattern.h',
'/intl/icu/source/common/unicode/normalizer2.h',
@ -212,12 +218,14 @@ EXPORTS.unicode += [
'/intl/icu/source/common/unicode/rep.h',
'/intl/icu/source/common/unicode/resbund.h',
'/intl/icu/source/common/unicode/schriter.h',
'/intl/icu/source/common/unicode/simpleformatter.h',
'/intl/icu/source/common/unicode/std_string.h',
'/intl/icu/source/common/unicode/strenum.h',
'/intl/icu/source/common/unicode/stringpiece.h',
'/intl/icu/source/common/unicode/stringtriebuilder.h',
'/intl/icu/source/common/unicode/symtable.h',
'/intl/icu/source/common/unicode/ubidi.h',
'/intl/icu/source/common/unicode/ubiditransform.h',
'/intl/icu/source/common/unicode/ubrk.h',
'/intl/icu/source/common/unicode/ucasemap.h',
'/intl/icu/source/common/unicode/ucat.h',
@ -231,10 +239,13 @@ EXPORTS.unicode += [
'/intl/icu/source/common/unicode/ucnv_err.h',
'/intl/icu/source/common/unicode/ucnvsel.h',
'/intl/icu/source/common/unicode/uconfig.h',
'/intl/icu/source/common/unicode/ucurr.h',
'/intl/icu/source/common/unicode/udata.h',
'/intl/icu/source/common/unicode/udisplaycontext.h',
'/intl/icu/source/common/unicode/uenum.h',
'/intl/icu/source/common/unicode/uidna.h',
'/intl/icu/source/common/unicode/uiter.h',
'/intl/icu/source/common/unicode/uldnames.h',
'/intl/icu/source/common/unicode/ulistformatter.h',
'/intl/icu/source/common/unicode/uloc.h',
'/intl/icu/source/common/unicode/umachine.h',

BIN
config/external/icu/data/icudt56l.dat → config/external/icu/data/icudt58l.dat vendored
View File

Binary file not shown.

11
config/external/icu/i18n/sources.mozbuild vendored
View File

@ -51,6 +51,7 @@ SOURCES += [
'/intl/icu/source/i18n/currunit.cpp',
'/intl/icu/source/i18n/dangical.cpp',
'/intl/icu/source/i18n/datefmt.cpp',
'/intl/icu/source/i18n/dayperiodrules.cpp',
'/intl/icu/source/i18n/dcfmtsym.cpp',
'/intl/icu/source/i18n/decContext.c',
'/intl/icu/source/i18n/decfmtst.cpp',
@ -81,12 +82,10 @@ SOURCES += [
'/intl/icu/source/i18n/gregocal.cpp',
'/intl/icu/source/i18n/gregoimp.cpp',
'/intl/icu/source/i18n/hebrwcal.cpp',
'/intl/icu/source/i18n/identifier_info.cpp',
'/intl/icu/source/i18n/indiancal.cpp',
'/intl/icu/source/i18n/inputext.cpp',
'/intl/icu/source/i18n/islamcal.cpp',
'/intl/icu/source/i18n/japancal.cpp',
'/intl/icu/source/i18n/locdspnm.cpp',
'/intl/icu/source/i18n/measfmt.cpp',
'/intl/icu/source/i18n/measunit.cpp',
'/intl/icu/source/i18n/measure.cpp',
@ -135,6 +134,7 @@ SOURCES += [
'/intl/icu/source/i18n/smpdtfmt.cpp',
'/intl/icu/source/i18n/smpdtfst.cpp',
'/intl/icu/source/i18n/sortkey.cpp',
'/intl/icu/source/i18n/standardplural.cpp',
'/intl/icu/source/i18n/strmatch.cpp',
'/intl/icu/source/i18n/strrepl.cpp',
'/intl/icu/source/i18n/stsearch.cpp',
@ -162,7 +162,6 @@ SOURCES += [
'/intl/icu/source/i18n/ucol_sit.cpp',
'/intl/icu/source/i18n/ucoleitr.cpp',
'/intl/icu/source/i18n/ucsdet.cpp',
'/intl/icu/source/i18n/ucurr.cpp',
'/intl/icu/source/i18n/udat.cpp',
'/intl/icu/source/i18n/udateintervalformat.cpp',
'/intl/icu/source/i18n/udatpg.cpp',
@ -183,7 +182,6 @@ SOURCES += [
'/intl/icu/source/i18n/uspoof_build.cpp',
'/intl/icu/source/i18n/uspoof_conf.cpp',
'/intl/icu/source/i18n/uspoof_impl.cpp',
'/intl/icu/source/i18n/uspoof_wsconf.cpp',
'/intl/icu/source/i18n/utf16collationiterator.cpp',
'/intl/icu/source/i18n/utf8collationiterator.cpp',
'/intl/icu/source/i18n/utmscale.c',
@ -225,7 +223,6 @@ EXPORTS.unicode += [
'/intl/icu/source/i18n/unicode/fpositer.h',
'/intl/icu/source/i18n/unicode/gender.h',
'/intl/icu/source/i18n/unicode/gregocal.h',
'/intl/icu/source/i18n/unicode/locdspnm.h',
'/intl/icu/source/i18n/unicode/measfmt.h',
'/intl/icu/source/i18n/unicode/measunit.h',
'/intl/icu/source/i18n/unicode/measure.h',
@ -260,15 +257,12 @@ EXPORTS.unicode += [
'/intl/icu/source/i18n/unicode/ucol.h',
'/intl/icu/source/i18n/unicode/ucoleitr.h',
'/intl/icu/source/i18n/unicode/ucsdet.h',
'/intl/icu/source/i18n/unicode/ucurr.h',
'/intl/icu/source/i18n/unicode/udat.h',
'/intl/icu/source/i18n/unicode/udateintervalformat.h',
'/intl/icu/source/i18n/unicode/udatpg.h',
'/intl/icu/source/i18n/unicode/udisplaycontext.h',
'/intl/icu/source/i18n/unicode/ufieldpositer.h',
'/intl/icu/source/i18n/unicode/uformattable.h',
'/intl/icu/source/i18n/unicode/ugender.h',
'/intl/icu/source/i18n/unicode/uldnames.h',
'/intl/icu/source/i18n/unicode/ulocdata.h',
'/intl/icu/source/i18n/unicode/umsg.h',
'/intl/icu/source/i18n/unicode/unirepl.h',
@ -277,6 +271,7 @@ EXPORTS.unicode += [
'/intl/icu/source/i18n/unicode/upluralrules.h',
'/intl/icu/source/i18n/unicode/uregex.h',
'/intl/icu/source/i18n/unicode/uregion.h',
'/intl/icu/source/i18n/unicode/ureldatefmt.h',
'/intl/icu/source/i18n/unicode/usearch.h',
'/intl/icu/source/i18n/unicode/uspoof.h',
'/intl/icu/source/i18n/unicode/utmscale.h',

13
intl/icu/SVN-INFO
View File

@ -1,9 +1,10 @@
Path: release-56-1
URL: http://source.icu-project.org/repos/icu/icu/tags/release-56-1
Repository Root: http://source.icu-project.org/repos/icu
Path: release-58-1
URL: https://ssl.icu-project.org/repos/icu/icu/tags/release-58-1
Relative URL: ^/icu/tags/release-58-1
Repository Root: https://ssl.icu-project.org/repos/icu
Repository UUID: 251d0590-4201-4cf1-90de-194747b24ca1
Node Kind: directory
Last Changed Author: mow
Last Changed Rev: 38044
Last Changed Date: 2015-10-07 22:20:20 +0000 (Wed, 07 Oct 2015)
Last Changed Author: srl
Last Changed Rev: 39472
Last Changed Date: 2016-10-19 20:35:30 +0000 (Wed, 19 Oct 2016)

2
intl/icu/source/Doxyfile.in
View File

@ -1,4 +1,6 @@
# Doxyfile 1.3.7
# Copyright (C) 2016 and later: Unicode, Inc. and others.
# License & terms of use: http://www.unicode.org/copyright.html
# ********************************************************************
# * COPYRIGHT:
# * Copyright (c) 2004-2015, International Business Machines Corporation

22
intl/icu/source/Makefile.in
View File

@ -1,6 +1,8 @@
# Copyright (C) 2016 and later: Unicode, Inc. and others.
# License & terms of use: http://www.unicode.org/copyright.html
#******************************************************************************
#
# Copyright (C) 1998-2015, International Business Machines
# Copyright (C) 1998-2016, International Business Machines
# Corporation and others. All Rights Reserved.
#
#******************************************************************************
@ -29,7 +31,6 @@ subdir = .
#AUTOCONF = @AUTOCONF@
## Optional directory setup
@LAYOUT_TRUE@LAYOUT = layout
@LAYOUTEX_TRUE@LAYOUTEX = layoutex
@ICUIO_TRUE@ICUIO = io
@EXTRAS_TRUE@EXTRA = extra
@ -39,7 +40,6 @@ subdir = .
## pkgconfig setup. Always have uc and i18n. Others are optional.
ALL_PKGCONFIG_SUFFIX=uc i18n
@LAYOUT_TRUE@ALL_PKGCONFIG_SUFFIX+= le
@LAYOUTEX_TRUE@ALL_PKGCONFIG_SUFFIX+= lx
@ICUIO_TRUE@ALL_PKGCONFIG_SUFFIX+= io
@ -58,7 +58,7 @@ INSTALLED_BUILT_FILES = $(top_builddir)/config/Makefile.inc $(top_builddir)/conf
LOCAL_BUILT_FILES = icudefs.mk config/icucross.mk config/icucross.inc
DOCDIRS = common i18n
SUBDIRS = stubdata common i18n $(LAYOUT) $(LAYOUTEX) $(ICUIO) $(TOOLS) data $(EXTRA) $(SAMPLE) $(TEST)
SUBDIRS = stubdata common i18n $(LAYOUTEX) $(ICUIO) $(TOOLS) data $(EXTRA) $(SAMPLE) $(TEST)
SECTION = 1
@ -113,13 +113,13 @@ doc doc-searchengine:
else
doc: doc/html/index.html
doc-searchengine: Doxyfile $(wildcard ./common/unicode/platform.h $(srcdir)/common/unicode/*.h $(srcdir)/i18n/unicode/*.h $(srcdir)/layout/unicode/*.h $(srcdir)/io/unicode/*.h)
doc-searchengine: Doxyfile $(wildcard ./common/unicode/platform.h $(srcdir)/common/unicode/*.h $(srcdir)/i18n/unicode/*.h $(srcdir)/io/unicode/*.h)
sed < Doxyfile -e 's%[^#]*SEARCHENGINE.*%SEARCHENGINE=YES%' | $(DOXYGEN) -
@echo adding links from non-namespaced class files
find doc/html -name 'classicu_1_1*' -print | sed -e 's%^\(.*class\)icu_1_1\(.*\)$$%ln & \1\2%' | sh
@echo Docs created - WARNING, probably contains non-GPL .js files
doc/html/index.html: Doxyfile $(wildcard ./common/unicode/platform.h $(srcdir)/common/unicode/*.h $(srcdir)/i18n/unicode/*.h $(srcdir)/layout/unicode/*.h $(srcdir)/io/unicode/*.h)
doc/html/index.html: Doxyfile $(wildcard ./common/unicode/platform.h $(srcdir)/common/unicode/*.h $(srcdir)/i18n/unicode/*.h $(srcdir)/io/unicode/*.h)
$(DOXYGEN)
@echo adding links from non-namespaced class files
find doc/html -name 'classicu_1_1*' -print | sed -e 's%^\(.*class\)icu_1_1\(.*\)$$%ln & \1\2%' | sh
@ -184,7 +184,7 @@ install-icu: $(INSTALLED_BUILT_FILES)
$(INSTALL_SCRIPT) $(top_srcdir)/install-sh $(DESTDIR)$(pkgdatadir)/install-sh
@$(MKINSTALLDIRS) $(DESTDIR)$(libdir)/pkgconfig
$(INSTALL_DATA) $(ALL_PKGCONFIG_FILES) $(DESTDIR)$(libdir)/pkgconfig/
$(INSTALL_DATA) $(top_srcdir)/../license.html $(DESTDIR)$(pkgdatadir)/license.html
$(INSTALL_DATA) $(top_srcdir)/../LICENSE $(DESTDIR)$(pkgdatadir)/LICENSE
$(INSTALL_SCRIPT) $(top_builddir)/config/icu-config $(DESTDIR)$(bindir)/icu-config
$(INSTALL_DATA) $(top_builddir)/config/Makefile.inc $(DESTDIR)$(pkglibdir)/Makefile.inc
$(INSTALL_DATA) $(top_builddir)/config/pkgdata.inc $(DESTDIR)$(pkglibdir)/pkgdata.inc
@ -287,14 +287,6 @@ config/icu-io.pc: config/icu.pc Makefile icudefs.mk
@echo "Libs:" "${ICULIBS_IO}" >> $@
@echo $@ updated.
config/icu-le.pc: config/icu.pc Makefile icudefs.mk
@cat config/icu.pc > $@
@echo "Description: $(PACKAGE_ICU_DESCRIPTION): Layout library" >> $@
@echo "Name: $(PACKAGE)-le" >> $@
@echo "Requires: icu-uc" >> $@
@echo "Libs:" "${ICULIBS_LE}" >> $@
@echo $@ updated.
ICULEHB_LIBS=@ICULEHB_LIBS@
USING_HB=
ifneq ($(ICULEHB_LIBS),)

7
intl/icu/source/acinclude.m4
View File

@ -1,4 +1,6 @@
# Copyright (c) 1999-2015, International Business Machines Corporation and
# Copyright (C) 2016 and later: Unicode, Inc. and others.
# License & terms of use: http://www.unicode.org/copyright.html
# Copyright (c) 1999-2016, International Business Machines Corporation and
# others. All Rights Reserved.
# acinclude.m4 for ICU
# Don't edit aclocal.m4, do edit acinclude.m4
@ -461,6 +463,9 @@ AC_DEFUN([AC_CHECK_STRICT_COMPILE],
if test "$GCC" = yes
then
case "${host}" in
*-*-solaris*)
# Don't use -std=c99 on Solaris because of timezone check fails
;;
*)
# Do not use -ansi. It limits us to C90, and it breaks some platforms.
# We use -std=c99 to disable the gnu99 defaults and its associated warnings

209
intl/icu/source/aclocal.m4 vendored
View File

@ -12,32 +12,63 @@
# PARTICULAR PURPOSE.
m4_ifndef([AC_CONFIG_MACRO_DIRS], [m4_defun([_AM_CONFIG_MACRO_DIRS], [])m4_defun([AC_CONFIG_MACRO_DIRS], [_AM_CONFIG_MACRO_DIRS($@)])])
# pkg.m4 - Macros to locate and utilise pkg-config. -*- Autoconf -*-
# serial 1 (pkg-config-0.24)
#
# Copyright © 2004 Scott James Remnant <scott@netsplit.com>.
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful, but
# WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
# General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
#
# As a special exception to the GNU General Public License, if you
# distribute this file as part of a program that contains a
# configuration script generated by Autoconf, you may include it under
# the same distribution terms that you use for the rest of that program.
dnl pkg.m4 - Macros to locate and utilise pkg-config. -*- Autoconf -*-
dnl serial 11 (pkg-config-0.29.1)
dnl
dnl Copyright © 2004 Scott James Remnant <scott@netsplit.com>.
dnl Copyright © 2012-2015 Dan Nicholson <dbn.lists@gmail.com>
dnl
dnl This program is free software; you can redistribute it and/or modify
dnl it under the terms of the GNU General Public License as published by
dnl the Free Software Foundation; either version 2 of the License, or
dnl (at your option) any later version.
dnl
dnl This program is distributed in the hope that it will be useful, but
dnl WITHOUT ANY WARRANTY; without even the implied warranty of
dnl MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
dnl General Public License for more details.
dnl
dnl You should have received a copy of the GNU General Public License
dnl along with this program; if not, write to the Free Software
dnl Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
dnl 02111-1307, USA.
dnl
dnl As a special exception to the GNU General Public License, if you
dnl distribute this file as part of a program that contains a
dnl configuration script generated by Autoconf, you may include it under
dnl the same distribution terms that you use for the rest of that
dnl program.
# PKG_PROG_PKG_CONFIG([MIN-VERSION])
# ----------------------------------
dnl PKG_PREREQ(MIN-VERSION)
dnl -----------------------
dnl Since: 0.29
dnl
dnl Verify that the version of the pkg-config macros are at least
dnl MIN-VERSION. Unlike PKG_PROG_PKG_CONFIG, which checks the user's
dnl installed version of pkg-config, this checks the developer's version
dnl of pkg.m4 when generating configure.
dnl
dnl To ensure that this macro is defined, also add:
dnl m4_ifndef([PKG_PREREQ],
dnl [m4_fatal([must install pkg-config 0.29 or later before running autoconf/autogen])])
dnl
dnl See the "Since" comment for each macro you use to see what version
dnl of the macros you require.
m4_defun([PKG_PREREQ],
[m4_define([PKG_MACROS_VERSION], [0.29.1])
m4_if(m4_version_compare(PKG_MACROS_VERSION, [$1]), -1,
[m4_fatal([pkg.m4 version $1 or higher is required but ]PKG_MACROS_VERSION[ found])])
])dnl PKG_PREREQ
dnl PKG_PROG_PKG_CONFIG([MIN-VERSION])
dnl ----------------------------------
dnl Since: 0.16
dnl
dnl Search for the pkg-config tool and set the PKG_CONFIG variable to
dnl first found in the path. Checks that the version of pkg-config found
dnl is at least MIN-VERSION. If MIN-VERSION is not specified, 0.9.0 is
dnl used since that's the first version where most current features of
dnl pkg-config existed.
AC_DEFUN([PKG_PROG_PKG_CONFIG],
[m4_pattern_forbid([^_?PKG_[A-Z_]+$])
m4_pattern_allow([^PKG_CONFIG(_(PATH|LIBDIR|SYSROOT_DIR|ALLOW_SYSTEM_(CFLAGS|LIBS)))?$])
@ -59,18 +90,19 @@ if test -n "$PKG_CONFIG"; then
PKG_CONFIG=""
fi
fi[]dnl
])# PKG_PROG_PKG_CONFIG
])dnl PKG_PROG_PKG_CONFIG
# PKG_CHECK_EXISTS(MODULES, [ACTION-IF-FOUND], [ACTION-IF-NOT-FOUND])
#
# Check to see whether a particular set of modules exists. Similar
# to PKG_CHECK_MODULES(), but does not set variables or print errors.
#
# Please remember that m4 expands AC_REQUIRE([PKG_PROG_PKG_CONFIG])
# only at the first occurence in configure.ac, so if the first place
# it's called might be skipped (such as if it is within an "if", you
# have to call PKG_CHECK_EXISTS manually
# --------------------------------------------------------------
dnl PKG_CHECK_EXISTS(MODULES, [ACTION-IF-FOUND], [ACTION-IF-NOT-FOUND])
dnl -------------------------------------------------------------------
dnl Since: 0.18
dnl
dnl Check to see whether a particular set of modules exists. Similar to
dnl PKG_CHECK_MODULES(), but does not set variables or print errors.
dnl
dnl Please remember that m4 expands AC_REQUIRE([PKG_PROG_PKG_CONFIG])
dnl only at the first occurence in configure.ac, so if the first place
dnl it's called might be skipped (such as if it is within an "if", you
dnl have to call PKG_CHECK_EXISTS manually
AC_DEFUN([PKG_CHECK_EXISTS],
[AC_REQUIRE([PKG_PROG_PKG_CONFIG])dnl
if test -n "$PKG_CONFIG" && \
@ -80,8 +112,10 @@ m4_ifvaln([$3], [else
$3])dnl
fi])
# _PKG_CONFIG([VARIABLE], [COMMAND], [MODULES])
# ---------------------------------------------
dnl _PKG_CONFIG([VARIABLE], [COMMAND], [MODULES])
dnl ---------------------------------------------
dnl Internal wrapper calling pkg-config via PKG_CONFIG and setting
dnl pkg_failed based on the result.
m4_define([_PKG_CONFIG],
[if test -n "$$1"; then
pkg_cv_[]$1="$$1"
@ -93,10 +127,11 @@ m4_define([_PKG_CONFIG],
else
pkg_failed=untried
fi[]dnl
])# _PKG_CONFIG
])dnl _PKG_CONFIG
# _PKG_SHORT_ERRORS_SUPPORTED
# -----------------------------
dnl _PKG_SHORT_ERRORS_SUPPORTED
dnl ---------------------------
dnl Internal check to see if pkg-config supports short errors.
AC_DEFUN([_PKG_SHORT_ERRORS_SUPPORTED],
[AC_REQUIRE([PKG_PROG_PKG_CONFIG])
if $PKG_CONFIG --atleast-pkgconfig-version 0.20; then
@ -104,19 +139,17 @@ if $PKG_CONFIG --atleast-pkgconfig-version 0.20; then
else
_pkg_short_errors_supported=no
fi[]dnl
])# _PKG_SHORT_ERRORS_SUPPORTED
])dnl _PKG_SHORT_ERRORS_SUPPORTED
# PKG_CHECK_MODULES(VARIABLE-PREFIX, MODULES, [ACTION-IF-FOUND],
# [ACTION-IF-NOT-FOUND])
#
#
# Note that if there is a possibility the first call to
# PKG_CHECK_MODULES might not happen, you should be sure to include an
# explicit call to PKG_PROG_PKG_CONFIG in your configure.ac
#
#
# --------------------------------------------------------------
dnl PKG_CHECK_MODULES(VARIABLE-PREFIX, MODULES, [ACTION-IF-FOUND],
dnl [ACTION-IF-NOT-FOUND])
dnl --------------------------------------------------------------
dnl Since: 0.4.0
dnl
dnl Note that if there is a possibility the first call to
dnl PKG_CHECK_MODULES might not happen, you should be sure to include an
dnl explicit call to PKG_PROG_PKG_CONFIG in your configure.ac
AC_DEFUN([PKG_CHECK_MODULES],
[AC_REQUIRE([PKG_PROG_PKG_CONFIG])dnl
AC_ARG_VAR([$1][_CFLAGS], [C compiler flags for $1, overriding pkg-config])dnl
@ -170,16 +203,40 @@ else
AC_MSG_RESULT([yes])
$3
fi[]dnl
])# PKG_CHECK_MODULES
])dnl PKG_CHECK_MODULES
# PKG_INSTALLDIR(DIRECTORY)
# -------------------------
# Substitutes the variable pkgconfigdir as the location where a module
# should install pkg-config .pc files. By default the directory is
# $libdir/pkgconfig, but the default can be changed by passing
# DIRECTORY. The user can override through the --with-pkgconfigdir
# parameter.
dnl PKG_CHECK_MODULES_STATIC(VARIABLE-PREFIX, MODULES, [ACTION-IF-FOUND],
dnl [ACTION-IF-NOT-FOUND])
dnl ---------------------------------------------------------------------
dnl Since: 0.29
dnl
dnl Checks for existence of MODULES and gathers its build flags with
dnl static libraries enabled. Sets VARIABLE-PREFIX_CFLAGS from --cflags
dnl and VARIABLE-PREFIX_LIBS from --libs.
dnl
dnl Note that if there is a possibility the first call to
dnl PKG_CHECK_MODULES_STATIC might not happen, you should be sure to
dnl include an explicit call to PKG_PROG_PKG_CONFIG in your
dnl configure.ac.
AC_DEFUN([PKG_CHECK_MODULES_STATIC],
[AC_REQUIRE([PKG_PROG_PKG_CONFIG])dnl
_save_PKG_CONFIG=$PKG_CONFIG
PKG_CONFIG="$PKG_CONFIG --static"
PKG_CHECK_MODULES($@)
PKG_CONFIG=$_save_PKG_CONFIG[]dnl
])dnl PKG_CHECK_MODULES_STATIC
dnl PKG_INSTALLDIR([DIRECTORY])
dnl -------------------------
dnl Since: 0.27
dnl
dnl Substitutes the variable pkgconfigdir as the location where a module
dnl should install pkg-config .pc files. By default the directory is
dnl $libdir/pkgconfig, but the default can be changed by passing
dnl DIRECTORY. The user can override through the --with-pkgconfigdir
dnl parameter.
AC_DEFUN([PKG_INSTALLDIR],
[m4_pushdef([pkg_default], [m4_default([$1], ['${libdir}/pkgconfig'])])
m4_pushdef([pkg_description],
@ -190,16 +247,18 @@ AC_ARG_WITH([pkgconfigdir],
AC_SUBST([pkgconfigdir], [$with_pkgconfigdir])
m4_popdef([pkg_default])
m4_popdef([pkg_description])
]) dnl PKG_INSTALLDIR
])dnl PKG_INSTALLDIR
# PKG_NOARCH_INSTALLDIR(DIRECTORY)
# -------------------------
# Substitutes the variable noarch_pkgconfigdir as the location where a
# module should install arch-independent pkg-config .pc files. By
# default the directory is $datadir/pkgconfig, but the default can be
# changed by passing DIRECTORY. The user can override through the
# --with-noarch-pkgconfigdir parameter.
dnl PKG_NOARCH_INSTALLDIR([DIRECTORY])
dnl --------------------------------
dnl Since: 0.27
dnl
dnl Substitutes the variable noarch_pkgconfigdir as the location where a
dnl module should install arch-independent pkg-config .pc files. By
dnl default the directory is $datadir/pkgconfig, but the default can be
dnl changed by passing DIRECTORY. The user can override through the
dnl --with-noarch-pkgconfigdir parameter.
AC_DEFUN([PKG_NOARCH_INSTALLDIR],
[m4_pushdef([pkg_default], [m4_default([$1], ['${datadir}/pkgconfig'])])
m4_pushdef([pkg_description],
@ -210,13 +269,15 @@ AC_ARG_WITH([noarch-pkgconfigdir],
AC_SUBST([noarch_pkgconfigdir], [$with_noarch_pkgconfigdir])
m4_popdef([pkg_default])
m4_popdef([pkg_description])
]) dnl PKG_NOARCH_INSTALLDIR
])dnl PKG_NOARCH_INSTALLDIR
# PKG_CHECK_VAR(VARIABLE, MODULE, CONFIG-VARIABLE,
# [ACTION-IF-FOUND], [ACTION-IF-NOT-FOUND])
# -------------------------------------------
# Retrieves the value of the pkg-config variable for the given module.
dnl PKG_CHECK_VAR(VARIABLE, MODULE, CONFIG-VARIABLE,
dnl [ACTION-IF-FOUND], [ACTION-IF-NOT-FOUND])
dnl -------------------------------------------
dnl Since: 0.28
dnl
dnl Retrieves the value of the pkg-config variable for the given module.
AC_DEFUN([PKG_CHECK_VAR],
[AC_REQUIRE([PKG_PROG_PKG_CONFIG])dnl
AC_ARG_VAR([$1], [value of $3 for $2, overriding pkg-config])dnl
@ -225,7 +286,7 @@ _PKG_CONFIG([$1], [variable="][$3]["], [$2])
AS_VAR_COPY([$1], [pkg_cv_][$1])
AS_VAR_IF([$1], [""], [$5], [$4])dnl
])# PKG_CHECK_VAR
])dnl PKG_CHECK_VAR
m4_include([config/m4/icu-conditional.m4])
m4_include([acinclude.m4])

14
intl/icu/source/allinone/allinone.sln
View File

@ -31,10 +31,6 @@ Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "i18n", "..\i18n\i18n.vcxpro
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "intltest", "..\test\intltest\intltest.vcxproj", "{73632960-B3A6-464D-83A3-4B43365F19B8}"
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "layout", "..\layout\layout.vcxproj", "{C920062A-0647-4553-A3B2-37C58065664B}"
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "layoutex", "..\layoutex\layoutex.vcxproj", "{37FC2C7F-1904-4811-8955-2F478830EAD1}"
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "makeconv", "..\tools\makeconv\makeconv.vcxproj", "{F5AD9738-1A3D-4906-B9C4-A7D9CE33DC2C}"
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "makedata", "..\data\makedata.vcxproj", "{D9DF7F2F-93B7-4810-B5CD-96F4F33C079B}"
@ -57,8 +53,6 @@ Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "icupkg", "..\tools\icupkg\i
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "gendict", "..\tools\gendict\gendict.vcxproj", "{9D4211F7-2C77-439C-82F0-30A4E43BA569}"
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "letest", "..\test\letest\letest.vcxproj", "{67351485-4D18-4245-BE39-A7EF0675ACD2}"
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "gencfu", "..\tools\gencfu\gencfu.vcxproj", "{691EE0C0-DC57-4A48-8AEE-8ED75EB3A057}"
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "gennorm2", "..\tools\gennorm2\gennorm2.vcxproj", "{C7891A65-80AB-4245-912E-5F1E17B0E6C4}"
@ -295,14 +289,6 @@ Global
{9D4211F7-2C77-439C-82F0-30A4E43BA569}.Release|Win32.Build.0 = Release|Win32
{9D4211F7-2C77-439C-82F0-30A4E43BA569}.Release|x64.ActiveCfg = Release|x64
{9D4211F7-2C77-439C-82F0-30A4E43BA569}.Release|x64.Build.0 = Release|x64
{67351485-4D18-4245-BE39-A7EF0675ACD2}.Debug|Win32.ActiveCfg = Debug|Win32
{67351485-4D18-4245-BE39-A7EF0675ACD2}.Debug|Win32.Build.0 = Debug|Win32
{67351485-4D18-4245-BE39-A7EF0675ACD2}.Debug|x64.ActiveCfg = Debug|x64
{67351485-4D18-4245-BE39-A7EF0675ACD2}.Debug|x64.Build.0 = Debug|x64
{67351485-4D18-4245-BE39-A7EF0675ACD2}.Release|Win32.ActiveCfg = Release|Win32
{67351485-4D18-4245-BE39-A7EF0675ACD2}.Release|Win32.Build.0 = Release|Win32
{67351485-4D18-4245-BE39-A7EF0675ACD2}.Release|x64.ActiveCfg = Release|x64
{67351485-4D18-4245-BE39-A7EF0675ACD2}.Release|x64.Build.0 = Release|x64
{691EE0C0-DC57-4A48-8AEE-8ED75EB3A057}.Debug|Win32.ActiveCfg = Debug|Win32
{691EE0C0-DC57-4A48-8AEE-8ED75EB3A057}.Debug|Win32.Build.0 = Debug|Win32
{691EE0C0-DC57-4A48-8AEE-8ED75EB3A057}.Debug|x64.ActiveCfg = Debug|x64

6
intl/icu/source/allinone/icucheck.bat
View File

@ -1,4 +1,6 @@
@echo off
REM Copyright (C) 2016 and later: Unicode, Inc. and others.
REM License & terms of use: http://www.unicode.org/copyright.html
REM ********************************************************************
REM * COPYRIGHT:
REM * Copyright (c) 2010-2014, International Business Machines Corporation
@ -89,7 +91,7 @@ set ICUFAILCNT=0
:OK_cintltst
@set ICURUN=%ICURUN% %THT%
@REM (Layout is deprecated)
@REM (Layout is deprecated - this would require HarfBuzz)
@REM @set THT=letest
@REM @echo ==== %THT% =========================================================================
@REM @cd %ICU_ICUDIR%\source\test\letest
@ -126,4 +128,4 @@ echo Failing Tests: %ICUFAILED%
echo -
echo FAILED!
exit /b 1
exit /b 1

14
intl/icu/source/common/Makefile.in
View File

@ -1,6 +1,8 @@
# Copyright (C) 2016 and later: Unicode, Inc. and others.
# License & terms of use: http://www.unicode.org/copyright.html
#******************************************************************************
#
# Copyright (C) 1999-2015, International Business Machines
# Copyright (C) 1999-2016, International Business Machines
# Corporation and others. All Rights Reserved.
#
#******************************************************************************
@ -78,14 +80,15 @@ endif
LIBS = $(LIBICUDT) $(DEFAULT_LIBS)
OBJECTS = errorcode.o putil.o umath.o utypes.o uinvchar.o umutex.o ucln_cmn.o \
uinit.o uobject.o cmemory.o charstr.o \
uinit.o uobject.o cmemory.o charstr.o cstr.o \
udata.o ucmndata.o udatamem.o umapfile.o udataswp.o ucol_swp.o utrace.o \
uhash.o uhash_us.o uenum.o ustrenum.o uvector.o ustack.o uvectr32.o uvectr64.o \
ucnv.o ucnv_bld.o ucnv_cnv.o ucnv_io.o ucnv_cb.o ucnv_err.o ucnvlat1.o \
ucnv_u7.o ucnv_u8.o ucnv_u16.o ucnv_u32.o ucnvscsu.o ucnvbocu.o \
ucnv_ext.o ucnvmbcs.o ucnv2022.o ucnvhz.o ucnv_lmb.o ucnvisci.o ucnvdisp.o ucnv_set.o ucnv_ct.o \
uresbund.o ures_cnv.o uresdata.o resbund.o resbund_cnv.o \
messagepattern.o ucat.o locmap.o uloc.o locid.o locutil.o locavailable.o locdispnames.o loclikely.o locresdata.o \
resource.o uresbund.o ures_cnv.o uresdata.o resbund.o resbund_cnv.o \
ucurr.o \
messagepattern.o ucat.o locmap.o uloc.o locid.o locutil.o locavailable.o locdispnames.o locdspnm.o loclikely.o locresdata.o \
bytestream.o stringpiece.o \
stringtriebuilder.o bytestriebuilder.o \
bytestrie.o bytestrieiterator.o \
@ -105,7 +108,8 @@ serv.o servnotf.o servls.o servlk.o servlkf.o servrbf.o servslkf.o \
uidna.o usprep.o uts46.o punycode.o \
util.o util_props.o parsepos.o locbased.o cwchar.o wintz.o dtintrv.o ucnvsel.o propsvec.o \
ulist.o uloc_tag.o icudataver.o icuplug.o listformatter.o ulistformatter.o \
sharedobject.o simplepatternformatter.o unifiedcache.o uloc_keytype.o \
sharedobject.o simpleformatter.o unifiedcache.o uloc_keytype.o \
ubiditransform.o \
pluralmap.o
## Header files to install

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

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
* Copyright (C) 2011-2012, International Business Machines

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

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
*

2
intl/icu/source/common/bmpset.h
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
*

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

@ -1,6 +1,8 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
************************************************************************************
* Copyright (C) 2006-2015, International Business Machines Corporation
* Copyright (C) 2006-2016, International Business Machines Corporation
* and others. All Rights Reserved.
************************************************************************************
*/
@ -10,6 +12,7 @@
#if !UCONFIG_NO_BREAK_ITERATION
#include "brkeng.h"
#include "cmemory.h"
#include "dictbe.h"
#include "unicode/uchar.h"
#include "unicode/uniset.h"
@ -56,13 +59,13 @@ LanguageBreakFactory::~LanguageBreakFactory() {
*/
UnhandledEngine::UnhandledEngine(UErrorCode &/*status*/) {
for (int32_t i = 0; i < (int32_t)(sizeof(fHandled)/sizeof(fHandled[0])); ++i) {
for (int32_t i = 0; i < UPRV_LENGTHOF(fHandled); ++i) {
fHandled[i] = 0;
}
}
UnhandledEngine::~UnhandledEngine() {
for (int32_t i = 0; i < (int32_t)(sizeof(fHandled)/sizeof(fHandled[0])); ++i) {
for (int32_t i = 0; i < UPRV_LENGTHOF(fHandled); ++i) {
if (fHandled[i] != 0) {
delete fHandled[i];
}
@ -71,7 +74,7 @@ UnhandledEngine::~UnhandledEngine() {
UBool
UnhandledEngine::handles(UChar32 c, int32_t breakType) const {
return (breakType >= 0 && breakType < (int32_t)(sizeof(fHandled)/sizeof(fHandled[0]))
return (breakType >= 0 && breakType < UPRV_LENGTHOF(fHandled)
&& fHandled[breakType] != 0 && fHandled[breakType]->contains(c));
}
@ -82,7 +85,7 @@ UnhandledEngine::findBreaks( UText *text,
UBool reverse,
int32_t breakType,
UStack &/*foundBreaks*/ ) const {
if (breakType >= 0 && breakType < (int32_t)(sizeof(fHandled)/sizeof(fHandled[0]))) {
if (breakType >= 0 && breakType < UPRV_LENGTHOF(fHandled)) {
UChar32 c = utext_current32(text);
if (reverse) {
while((int32_t)utext_getNativeIndex(text) > startPos && fHandled[breakType]->contains(c)) {
@ -101,7 +104,7 @@ UnhandledEngine::findBreaks( UText *text,
void
UnhandledEngine::handleCharacter(UChar32 c, int32_t breakType) {
if (breakType >= 0 && breakType < (int32_t)(sizeof(fHandled)/sizeof(fHandled[0]))) {
if (breakType >= 0 && breakType < UPRV_LENGTHOF(fHandled)) {
if (fHandled[breakType] == 0) {
fHandled[breakType] = new UnicodeSet();
if (fHandled[breakType] == 0) {

2
intl/icu/source/common/brkeng.h
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/**
************************************************************************************
* Copyright (C) 2006-2012, International Business Machines Corporation and others. *

4
intl/icu/source/common/brkiter.cpp
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
* Copyright (C) 1997-2015, International Business Machines Corporation and
@ -418,6 +420,7 @@ BreakIterator::makeInstance(const Locale& loc, int32_t kind, UErrorCode& status)
break;
case UBRK_SENTENCE:
result = BreakIterator::buildInstance(loc, "sentence", kind, status);
#if !UCONFIG_NO_FILTERED_BREAK_ITERATION
{
char ssKeyValue[kKeyValueLenMax] = {0};
UErrorCode kvStatus = U_ZERO_ERROR;
@ -430,6 +433,7 @@ BreakIterator::makeInstance(const Locale& loc, int32_t kind, UErrorCode& status)
}
}
}
#endif
break;
case UBRK_TITLE:
result = BreakIterator::buildInstance(loc, "title", kind, status);

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

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Copyright (C) 2009-2011, International Business Machines
// Corporation and others. All Rights Reserved.
//

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

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
* Copyright (C) 2010-2011, International Business Machines

10
intl/icu/source/common/bytestriebuilder.cpp
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
* Copyright (C) 2010-2012, International Business Machines
@ -35,7 +37,7 @@ class BytesTrieElement : public UMemory {
public:
// Use compiler's default constructor, initializes nothing.
void setTo(const StringPiece &s, int32_t val, CharString &strings, UErrorCode &errorCode);
void setTo(StringPiece s, int32_t val, CharString &strings, UErrorCode &errorCode);
StringPiece getString(const CharString &strings) const {
int32_t offset=stringOffset;
@ -86,7 +88,7 @@ private:
};
void
BytesTrieElement::setTo(const StringPiece &s, int32_t val,
BytesTrieElement::setTo(StringPiece s, int32_t val,
CharString &strings, UErrorCode &errorCode) {
if(U_FAILURE(errorCode)) {
return;
@ -143,7 +145,7 @@ BytesTrieBuilder::~BytesTrieBuilder() {
}
BytesTrieBuilder &
BytesTrieBuilder::add(const StringPiece &s, int32_t value, UErrorCode &errorCode) {
BytesTrieBuilder::add(StringPiece s, int32_t value, UErrorCode &errorCode) {
if(U_FAILURE(errorCode)) {
return *this;
}
@ -165,7 +167,7 @@ BytesTrieBuilder::add(const StringPiece &s, int32_t value, UErrorCode &errorCode
return *this; // error instead of dereferencing null
}
if(elementsLength>0) {
uprv_memcpy(newElements, elements, elementsLength*sizeof(BytesTrieElement));
uprv_memcpy(newElements, elements, (size_t)elementsLength*sizeof(BytesTrieElement));
}
delete[] elements;
elements=newElements;

10
intl/icu/source/common/bytestrieiterator.cpp
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
* Copyright (C) 2010-2012, International Business Machines
@ -139,7 +141,6 @@ BytesTrie::Iterator::next(UErrorCode &errorCode) {
} else {
pos_=skipValue(pos, node);
}
sp_.set(str_->data(), str_->length());
return TRUE;
}
if(maxLength_>0 && str_->length()==maxLength_) {
@ -167,10 +168,14 @@ BytesTrie::Iterator::next(UErrorCode &errorCode) {
}
}
StringPiece
BytesTrie::Iterator::getString() const {
return str_ == NULL ? StringPiece() : str_->toStringPiece();
}
UBool
BytesTrie::Iterator::truncateAndStop() {
pos_=NULL;
sp_.set(str_->data(), str_->length());
value_=-1; // no real value for str
return TRUE;
}
@ -199,7 +204,6 @@ BytesTrie::Iterator::branchNext(const uint8_t *pos, int32_t length, UErrorCode &
str_->append((char)trieByte, errorCode);
if(isFinal) {
pos_=NULL;
sp_.set(str_->data(), str_->length());
value_=value;
return NULL;
} else {

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

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*****************************************************************************
* Copyright (C) 1996-2015, International Business Machines Corporation and

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

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
* Copyright (C) 1999-2011, International Business Machines

4
intl/icu/source/common/charstr.cpp
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
* Copyright (C) 2010-2015, International Business Machines
@ -144,7 +146,7 @@ UBool CharString::ensureCapacity(int32_t capacity,
return TRUE;
}
CharString &CharString::appendPathPart(const StringPiece &s, UErrorCode &errorCode) {
CharString &CharString::appendPathPart(StringPiece s, UErrorCode &errorCode) {
if(U_FAILURE(errorCode)) {
return *this;
}

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

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
* Copyright (c) 2001-2015, International Business Machines
@ -39,7 +41,7 @@ template class U_COMMON_API MaybeStackArray<char, 40>;
class U_COMMON_API CharString : public UMemory {
public:
CharString() : len(0) { buffer[0]=0; }
CharString(const StringPiece &s, UErrorCode &errorCode) : len(0) {
CharString(StringPiece s, UErrorCode &errorCode) : len(0) {
buffer[0]=0;
append(s, errorCode);
}
@ -76,7 +78,7 @@ public:
CharString &truncate(int32_t newLength);
CharString &append(char c, UErrorCode &errorCode);
CharString &append(const StringPiece &s, UErrorCode &errorCode) {
CharString &append(StringPiece s, UErrorCode &errorCode) {
return append(s.data(), s.length(), errorCode);
}
CharString &append(const CharString &s, UErrorCode &errorCode) {
@ -115,7 +117,7 @@ public:
* First appends a U_FILE_SEP_CHAR if necessary.
* Does nothing if s is empty.
*/
CharString &appendPathPart(const StringPiece &s, UErrorCode &errorCode);
CharString &appendPathPart(StringPiece s, UErrorCode &errorCode);
/**
* Appends a U_FILE_SEP_CHAR if this string is not empty

2
intl/icu/source/common/cmemory.c
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
*

16
intl/icu/source/common/cmemory.h
View File

@ -1,7 +1,9 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
*
* Copyright (C) 1997-2015, International Business Machines
* Copyright (C) 1997-2016, International Business Machines
* Corporation and others. All Rights Reserved.
*
******************************************************************************
@ -153,6 +155,8 @@ U_NAMESPACE_BEGIN
template<typename T>
class LocalMemory : public LocalPointerBase<T> {
public:
using LocalPointerBase<T>::operator*;
using LocalPointerBase<T>::operator->;
/**
* Constructor takes ownership.
* @param p simple pointer to an array of T items that is adopted
@ -279,7 +283,7 @@ inline T *LocalMemory<T>::allocateInsteadAndCopy(int32_t newCapacity, int32_t le
if(length>newCapacity) {
length=newCapacity;
}
uprv_memcpy(p, LocalPointerBase<T>::ptr, length*sizeof(T));
uprv_memcpy(p, LocalPointerBase<T>::ptr, (size_t)length*sizeof(T));
}
uprv_free(LocalPointerBase<T>::ptr);
LocalPointerBase<T>::ptr=p;
@ -426,7 +430,7 @@ inline T *MaybeStackArray<T, stackCapacity>::resize(int32_t newCapacity, int32_t
if(length>newCapacity) {
length=newCapacity;
}
uprv_memcpy(p, ptr, length*sizeof(T));
uprv_memcpy(p, ptr, (size_t)length*sizeof(T));
}
releaseArray();
ptr=p;
@ -457,7 +461,7 @@ inline T *MaybeStackArray<T, stackCapacity>::orphanOrClone(int32_t length, int32
if(p==NULL) {
return NULL;
}
uprv_memcpy(p, ptr, length*sizeof(T));
uprv_memcpy(p, ptr, (size_t)length*sizeof(T));
}
resultCapacity=length;
ptr=stackArray;
@ -605,7 +609,7 @@ inline H *MaybeStackHeaderAndArray<H, T, stackCapacity>::resize(int32_t newCapac
length=newCapacity;
}
}
uprv_memcpy(p, ptr, sizeof(H)+length*sizeof(T));
uprv_memcpy(p, ptr, sizeof(H)+(size_t)length*sizeof(T));
releaseMemory();
ptr=p;
capacity=newCapacity;
@ -636,7 +640,7 @@ inline H *MaybeStackHeaderAndArray<H, T, stackCapacity>::orphanOrClone(int32_t l
if(p==NULL) {
return NULL;
}
uprv_memcpy(p, ptr, sizeof(H)+length*sizeof(T));
uprv_memcpy(p, ptr, sizeof(H)+(size_t)length*sizeof(T));
}
resultCapacity=length;
ptr=&stackHeader;

2
intl/icu/source/common/common.rc
View File

@ -1,6 +1,8 @@
// Do not edit with Microsoft Developer Studio Resource Editor.
// It will permanently substitute version numbers that are intended to be
// picked up by the pre-processor during each build.
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Copyright (c) 2001-2010 International Business Machines
// Corporation and others. All Rights Reserved.
//

100
intl/icu/source/common/common.vcxproj
View File

@ -1,5 +1,5 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<Project DefaultTargets="Build" ToolsVersion="14.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|Win32">
<Configuration>Debug</Configuration>
@ -26,21 +26,25 @@
<ConfigurationType>DynamicLibrary</ConfigurationType>
<UseOfMfc>false</UseOfMfc>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v140</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="Configuration">
<ConfigurationType>DynamicLibrary</ConfigurationType>
<UseOfMfc>false</UseOfMfc>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v140</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'" Label="Configuration">
<ConfigurationType>DynamicLibrary</ConfigurationType>
<UseOfMfc>false</UseOfMfc>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v140</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'" Label="Configuration">
<ConfigurationType>DynamicLibrary</ConfigurationType>
<UseOfMfc>false</UseOfMfc>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v140</PlatformToolset>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
@ -104,7 +108,7 @@
<Culture>0x0409</Culture>
</ResourceCompile>
<Link>
<OutputFile>..\..\bin\icuuc56.dll</OutputFile>
<OutputFile>..\..\bin\icuuc58.dll</OutputFile>
<SuppressStartupBanner>true</SuppressStartupBanner>
<ProgramDatabaseFile>.\..\..\lib\icuuc.pdb</ProgramDatabaseFile>
<EnableCOMDATFolding>true</EnableCOMDATFolding>
@ -145,7 +149,7 @@
<Culture>0x0409</Culture>
</ResourceCompile>
<Link>
<OutputFile>..\..\bin\icuuc56d.dll</OutputFile>
<OutputFile>..\..\bin\icuuc58d.dll</OutputFile>
<SuppressStartupBanner>true</SuppressStartupBanner>
<GenerateDebugInformation>true</GenerateDebugInformation>
<ProgramDatabaseFile>.\..\..\lib\icuucd.pdb</ProgramDatabaseFile>
@ -183,7 +187,7 @@
<Culture>0x0409</Culture>
</ResourceCompile>
<Link>
<OutputFile>..\..\bin64\icuuc56.dll</OutputFile>
<OutputFile>..\..\bin64\icuuc58.dll</OutputFile>
<SuppressStartupBanner>true</SuppressStartupBanner>
<ProgramDatabaseFile>.\..\..\lib64\icuuc.pdb</ProgramDatabaseFile>
<EnableCOMDATFolding>true</EnableCOMDATFolding>
@ -222,7 +226,7 @@
<Culture>0x0409</Culture>
</ResourceCompile>
<Link>
<OutputFile>..\..\bin64\icuuc56d.dll</OutputFile>
<OutputFile>..\..\bin64\icuuc58d.dll</OutputFile>
<SuppressStartupBanner>true</SuppressStartupBanner>
<GenerateDebugInformation>true</GenerateDebugInformation>
<ProgramDatabaseFile>.\..\..\lib64\icuucd.pdb</ProgramDatabaseFile>
@ -234,6 +238,7 @@
<ItemGroup>
<ClCompile Include="filteredbrk.cpp" />
<ClCompile Include="ubidi.c" />
<ClCompile Include="ubiditransform.c" />
<ClCompile Include="ubidi_props.c" />
<ClCompile Include="ubidiln.c" />
<ClCompile Include="ubidiwrt.c" />
@ -365,6 +370,7 @@
</ClCompile>
<ClCompile Include="locbased.cpp" />
<ClCompile Include="locdispnames.cpp" />
<ClCompile Include="locdspnm.cpp" />
<ClCompile Include="locid.cpp">
</ClCompile>
<ClCompile Include="loclikely.cpp" />
@ -379,7 +385,9 @@
<ClCompile Include="uloc_tag.c" />
<ClCompile Include="ures_cnv.c" />
<ClCompile Include="uresbund.cpp" />
<ClCompile Include="uresdata.c" />
<ClCompile Include="uresdata.cpp" />
<ClCompile Include="resource.cpp" />
<ClCompile Include="ucurr.cpp" />
<ClCompile Include="caniter.cpp">
</ClCompile>
<ClCompile Include="filterednormalizer2.cpp" />
@ -439,12 +447,13 @@
<ClCompile Include="chariter.cpp" />
<ClCompile Include="charstr.cpp" />
<ClCompile Include="cstring.c" />
<ClCompile Include="cstr.cpp" />
<ClCompile Include="cwchar.c" />
<ClCompile Include="messagepattern.cpp" />
<ClCompile Include="schriter.cpp" />
<ClCompile Include="stringpiece.cpp" />
<ClCompile Include="stringtriebuilder.cpp" />
<ClCompile Include="simplepatternformatter.cpp" />
<ClCompile Include="simpleformatter.cpp" />
<ClCompile Include="ucasemap.cpp" />
<ClCompile Include="ucasemap_titlecase_brkiter.cpp" />
<ClCompile Include="ucharstrie.cpp" />
@ -578,6 +587,7 @@
<ClInclude Include="uchar_props_data.h" />
<ClInclude Include="ucol_data.h" />
<ClInclude Include="ucol_swp.h" />
<ClInclude Include="unicode\ubiditransform.h" />
<ClInclude Include="unistrappender.h" />
<ClInclude Include="hash.h" />
<ClInclude Include="propsvec.h" />
@ -1087,7 +1097,34 @@
</CustomBuild>
<ClInclude Include="sharedobject.h" />
<ClCompile Include="sharedobject.cpp" />
<ClInclude Include="simplepatternformatter.h" />
<CustomBuild Include="unicode\locdspnm.h">
<Command Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">copy "%(FullPath)" ..\..\include\unicode
</Command>
<Outputs Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">..\..\include\unicode\%(Filename)%(Extension);%(Outputs)</Outputs>
<Command Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">copy "%(FullPath)" ..\..\include\unicode
</Command>
<Outputs Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">..\..\include\unicode\%(Filename)%(Extension);%(Outputs)</Outputs>
<Command Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">copy "%(FullPath)" ..\..\include\unicode
</Command>
<Outputs Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">..\..\include\unicode\%(Filename)%(Extension);%(Outputs)</Outputs>
<Command Condition="'$(Configuration)|$(Platform)'=='Release|x64'">copy "%(FullPath)" ..\..\include\unicode
</Command>
<Outputs Condition="'$(Configuration)|$(Platform)'=='Release|x64'">..\..\include\unicode\%(Filename)%(Extension);%(Outputs)</Outputs>
</CustomBuild>
<CustomBuild Include="unicode\simpleformatter.h">
<Command Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">copy "%(FullPath)" ..\..\include\unicode
</Command>
<Outputs Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">..\..\include\unicode\%(Filename)%(Extension);%(Outputs)</Outputs>
<Command Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">copy "%(FullPath)" ..\..\include\unicode
</Command>
<Outputs Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">..\..\include\unicode\%(Filename)%(Extension);%(Outputs)</Outputs>
<Command Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">copy "%(FullPath)" ..\..\include\unicode
</Command>
<Outputs Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">..\..\include\unicode\%(Filename)%(Extension);%(Outputs)</Outputs>
<Command Condition="'$(Configuration)|$(Platform)'=='Release|x64'">copy "%(FullPath)" ..\..\include\unicode
</Command>
<Outputs Condition="'$(Configuration)|$(Platform)'=='Release|x64'">..\..\include\unicode\%(Filename)%(Extension);%(Outputs)</Outputs>
</CustomBuild>
<CustomBuild Include="unicode\ucat.h">
<Command Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">copy "%(FullPath)" ..\..\include\unicode
</Command>
@ -1099,6 +1136,34 @@
</Command>
<Outputs Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">..\..\include\unicode\%(Filename)%(Extension);%(Outputs)</Outputs>
<Command Condition="'$(Configuration)|$(Platform)'=='Release|x64'">copy "%(FullPath)" ..\..\include\unicode
</Command>
<Outputs Condition="'$(Configuration)|$(Platform)'=='Release|x64'">..\..\include\unicode\%(Filename)%(Extension);%(Outputs)</Outputs>
</CustomBuild>
<CustomBuild Include="unicode\udisplaycontext.h">
<Command Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">copy "%(FullPath)" ..\..\include\unicode
</Command>
<Outputs Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">..\..\include\unicode\%(Filename)%(Extension);%(Outputs)</Outputs>
<Command Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">copy "%(FullPath)" ..\..\include\unicode
</Command>
<Outputs Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">..\..\include\unicode\%(Filename)%(Extension);%(Outputs)</Outputs>
<Command Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">copy "%(FullPath)" ..\..\include\unicode
</Command>
<Outputs Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">..\..\include\unicode\%(Filename)%(Extension);%(Outputs)</Outputs>
<Command Condition="'$(Configuration)|$(Platform)'=='Release|x64'">copy "%(FullPath)" ..\..\include\unicode
</Command>
<Outputs Condition="'$(Configuration)|$(Platform)'=='Release|x64'">..\..\include\unicode\%(Filename)%(Extension);%(Outputs)</Outputs>
</CustomBuild>
<CustomBuild Include="unicode\uldnames.h">
<Command Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">copy "%(FullPath)" ..\..\include\unicode
</Command>
<Outputs Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">..\..\include\unicode\%(Filename)%(Extension);%(Outputs)</Outputs>
<Command Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">copy "%(FullPath)" ..\..\include\unicode
</Command>
<Outputs Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">..\..\include\unicode\%(Filename)%(Extension);%(Outputs)</Outputs>
<Command Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">copy "%(FullPath)" ..\..\include\unicode
</Command>
<Outputs Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">..\..\include\unicode\%(Filename)%(Extension);%(Outputs)</Outputs>
<Command Condition="'$(Configuration)|$(Platform)'=='Release|x64'">copy "%(FullPath)" ..\..\include\unicode
</Command>
<Outputs Condition="'$(Configuration)|$(Platform)'=='Release|x64'">..\..\include\unicode\%(Filename)%(Extension);%(Outputs)</Outputs>
</CustomBuild>
@ -1135,6 +1200,22 @@
<ClInclude Include="uresdata.h" />
<ClInclude Include="uresimp.h" />
<ClInclude Include="ureslocs.h" />
<ClInclude Include="resource.h" />
<CustomBuild Include="unicode\ucurr.h">
<Command Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">copy "%(FullPath)" ..\..\include\unicode
</Command>
<Outputs Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">..\..\include\unicode\%(Filename)%(Extension);%(Outputs)</Outputs>
<Command Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">copy "%(FullPath)" ..\..\include\unicode
</Command>
<Outputs Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">..\..\include\unicode\%(Filename)%(Extension);%(Outputs)</Outputs>
<Command Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">copy "%(FullPath)" ..\..\include\unicode
</Command>
<Outputs Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">..\..\include\unicode\%(Filename)%(Extension);%(Outputs)</Outputs>
<Command Condition="'$(Configuration)|$(Platform)'=='Release|x64'">copy "%(FullPath)" ..\..\include\unicode
</Command>
<Outputs Condition="'$(Configuration)|$(Platform)'=='Release|x64'">..\..\include\unicode\%(Filename)%(Extension);%(Outputs)</Outputs>
</CustomBuild>
<ClInclude Include="ucurrimp.h" />
<CustomBuild Include="unicode\caniter.h">
<Command Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">copy "%(FullPath)" ..\..\include\unicode
</Command>
@ -1449,6 +1530,7 @@
</CustomBuild>
<ClInclude Include="charstr.h" />
<ClInclude Include="cstring.h" />
<ClInclude Include="cstr.h" />
<ClInclude Include="cwchar.h" />
<CustomBuild Include="unicode\messagepattern.h">
<Command Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">copy "%(FullPath)" ..\..\include\unicode
@ -1774,4 +1856,4 @@
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
</ImportGroup>
</Project>
</Project>

53
intl/icu/source/common/common.vcxproj.filters
View File

@ -277,10 +277,16 @@
<ClCompile Include="dtintrv.cpp">
<Filter>formatting</Filter>
</ClCompile>
<ClCompile Include="locdspnm.cpp">
<Filter>formatting</Filter>
</ClCompile>
<ClCompile Include="parsepos.cpp">
<Filter>formatting</Filter>
</ClCompile>
<ClCompile Include="simplepatternformatter.cpp">
<ClCompile Include="simpleformatter.cpp">
<Filter>formatting</Filter>
</ClCompile>
<ClCompile Include="ucurr.cpp">
<Filter>formatting</Filter>
</ClCompile>
<ClCompile Include="ustrfmt.c">
@ -343,7 +349,10 @@
<ClCompile Include="uresbund.cpp">
<Filter>locales &amp; resources</Filter>
</ClCompile>
<ClCompile Include="uresdata.c">
<ClCompile Include="uresdata.cpp">
<Filter>locales &amp; resources</Filter>
</ClCompile>
<ClCompile Include="resource.cpp">
<Filter>locales &amp; resources</Filter>
</ClCompile>
<ClCompile Include="caniter.cpp">
@ -463,6 +472,9 @@
<ClCompile Include="cstring.c">
<Filter>strings</Filter>
</ClCompile>
<ClCompile Include="cstr.cpp">
<Filter>strings</Filter>
</ClCompile>
<ClCompile Include="cwchar.c">
<Filter>strings</Filter>
</ClCompile>
@ -574,13 +586,18 @@
<ClCompile Include="stringtriebuilder.cpp">
<Filter>collections</Filter>
</ClCompile>
<ClCompile Include="icuplug.cpp" />
<ClCompile Include="uloc_keytype.cpp">
<Filter>locales &amp; resources</Filter>
</ClCompile>
<ClCompile Include="filteredbrk.cpp">
<Filter>break iteration</Filter>
</ClCompile>
<ClCompile Include="icuplug.cpp">
<Filter>registration</Filter>
</ClCompile>
<ClCompile Include="ubiditransform.c">
<Filter>bidi</Filter>
</ClCompile>
</ItemGroup>
<ItemGroup>
<ClInclude Include="ubidi_props.h">
@ -745,15 +762,30 @@
<ClInclude Include="umapfile.h">
<Filter>data &amp; memory</Filter>
</ClInclude>
<ClInclude Include="simplepatternformatter.h">
<CustomBuild Include="unicode\locdspnm.h">
<Filter>formatting</Filter>
</ClInclude>
</CustomBuild>
<CustomBuild Include="unicode\simpleformatter.h">
<Filter>formatting</Filter>
</CustomBuild>
<ClInclude Include="ustrfmt.h">
<Filter>formatting</Filter>
</ClInclude>
<ClInclude Include="util.h">
<Filter>formatting</Filter>
</ClInclude>
<CustomBuild Include="unicode\ucurr.h">
<Filter>formatting</Filter>
</CustomBuild>
<ClInclude Include="ucurrimp.h">
<Filter>formatting</Filter>
</ClInclude>
<CustomBuild Include="unicode\udisplaycontext.h">
<Filter>formatting</Filter>
</CustomBuild>
<CustomBuild Include="unicode\uldnames.h">
<Filter>formatting</Filter>
</CustomBuild>
<ClInclude Include="punycode.h">
<Filter>idna</Filter>
</ClInclude>
@ -769,6 +801,9 @@
<ClInclude Include="uresdata.h">
<Filter>locales &amp; resources</Filter>
</ClInclude>
<ClInclude Include="resource.h">
<Filter>locales &amp; resources</Filter>
</ClInclude>
<ClInclude Include="uresimp.h">
<Filter>locales &amp; resources</Filter>
</ClInclude>
@ -829,6 +864,9 @@
<ClInclude Include="cstring.h">
<Filter>strings</Filter>
</ClInclude>
<ClInclude Include="cstr.h">
<Filter>strings</Filter>
</ClInclude>
<ClInclude Include="cwchar.h">
<Filter>strings</Filter>
</ClInclude>
@ -877,6 +915,9 @@
<ClInclude Include="unicode\filteredbrk.h">
<Filter>break iteration</Filter>
</ClInclude>
<ClInclude Include="unicode\ubiditransform.h">
<Filter>bidi</Filter>
</ClInclude>
</ItemGroup>
<ItemGroup>
<ResourceCompile Include="common.rc">
@ -1140,4 +1181,4 @@
<Filter>collections</Filter>
</CustomBuild>
</ItemGroup>
</Project>
</Project>

20
intl/icu/source/common/cpputils.h
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
*
@ -24,45 +26,45 @@
static
inline void uprv_arrayCopy(const double* src, double* dst, int32_t count)
{ uprv_memcpy(dst, src, (size_t)(count * sizeof(*src))); }
{ uprv_memcpy(dst, src, (size_t)count * sizeof(*src)); }
static
inline void uprv_arrayCopy(const double* src, int32_t srcStart,
double* dst, int32_t dstStart, int32_t count)
{ uprv_memcpy(dst+dstStart, src+srcStart, (size_t)(count * sizeof(*src))); }
{ uprv_memcpy(dst+dstStart, src+srcStart, (size_t)count * sizeof(*src)); }
static
inline void uprv_arrayCopy(const int8_t* src, int8_t* dst, int32_t count)
{ uprv_memcpy(dst, src, (size_t)(count * sizeof(*src))); }
{ uprv_memcpy(dst, src, (size_t)count * sizeof(*src)); }
static
inline void uprv_arrayCopy(const int8_t* src, int32_t srcStart,
int8_t* dst, int32_t dstStart, int32_t count)
{ uprv_memcpy(dst+dstStart, src+srcStart, (size_t)(count * sizeof(*src))); }
{ uprv_memcpy(dst+dstStart, src+srcStart, (size_t)count * sizeof(*src)); }
static
inline void uprv_arrayCopy(const int16_t* src, int16_t* dst, int32_t count)
{ uprv_memcpy(dst, src, (size_t)(count * sizeof(*src))); }
{ uprv_memcpy(dst, src, (size_t)count * sizeof(*src)); }
static
inline void uprv_arrayCopy(const int16_t* src, int32_t srcStart,
int16_t* dst, int32_t dstStart, int32_t count)
{ uprv_memcpy(dst+dstStart, src+srcStart, (size_t)(count * sizeof(*src))); }
{ uprv_memcpy(dst+dstStart, src+srcStart, (size_t)count * sizeof(*src)); }
static
inline void uprv_arrayCopy(const int32_t* src, int32_t* dst, int32_t count)
{ uprv_memcpy(dst, src, (size_t)(count * sizeof(*src))); }
{ uprv_memcpy(dst, src, (size_t)count * sizeof(*src)); }
static
inline void uprv_arrayCopy(const int32_t* src, int32_t srcStart,
int32_t* dst, int32_t dstStart, int32_t count)
{ uprv_memcpy(dst+dstStart, src+srcStart, (size_t)(count * sizeof(*src))); }
{ uprv_memcpy(dst+dstStart, src+srcStart, (size_t)count * sizeof(*src)); }
static
inline void
uprv_arrayCopy(const UChar *src, int32_t srcStart,
UChar *dst, int32_t dstStart, int32_t count)
{ uprv_memcpy(dst+dstStart, src+srcStart, (size_t)(count * sizeof(*src))); }
{ uprv_memcpy(dst+dstStart, src+srcStart, (size_t)count * sizeof(*src)); }
/**
* Copy an array of UnicodeString OBJECTS (not pointers).

54
intl/icu/source/common/cstr.cpp Normal file
View File

@ -0,0 +1,54 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
* Copyright (C) 2015-2016, International Business Machines
* Corporation and others. All Rights Reserved.
*******************************************************************************
* file name: charstr.cpp
*/
#include "unicode/utypes.h"
#include "unicode/putil.h"
#include "unicode/unistr.h"
#include "cstr.h"
#include "charstr.h"
#include "uinvchar.h"
U_NAMESPACE_BEGIN
CStr::CStr(const UnicodeString &in) {
UErrorCode status = U_ZERO_ERROR;
#if !UCONFIG_NO_CONVERSION || U_CHARSET_IS_UTF8
int32_t length = in.extract(0, in.length(), static_cast<char *>(NULL), static_cast<uint32_t>(0));
int32_t resultCapacity = 0;
char *buf = s.getAppendBuffer(length, length, resultCapacity, status);
if (U_SUCCESS(status)) {
in.extract(0, in.length(), buf, resultCapacity);
s.append(buf, length, status);
}
#else
// No conversion available. Convert any invariant characters; substitute '?' for the rest.
// Note: can't just call u_UCharsToChars() or CharString.appendInvariantChars() on the
// whole string because they require that the entire input be invariant.
char buf[2];
for (int i=0; i<in.length(); i = in.moveIndex32(i, 1)) {
if (uprv_isInvariantUString(in.getBuffer()+i, 1)) {
u_UCharsToChars(in.getBuffer()+i, buf, 1);
} else {
buf[0] = '?';
}
s.append(buf, 1, status);
}
#endif
}
CStr::~CStr() {
}
const char * CStr::operator ()() const {
return s.data();
}
U_NAMESPACE_END

60
intl/icu/source/common/cstr.h Normal file
View File

@ -0,0 +1,60 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
*
* Copyright (C) 2016, International Business Machines
* Corporation and others. All Rights Reserved.
*
******************************************************************************
*
* File: cstr.h
*/
#ifndef CSTR_H
#define CSTR_H
#include "unicode/unistr.h"
#include "unicode/uobject.h"
#include "unicode/utypes.h"
#include "charstr.h"
/**
* ICU-internal class CStr, a small helper class to facilitate passing UnicodeStrings
* to functions needing (const char *) strings, such as printf().
*
* It is intended primarily for use in debugging or in tests. Uses platform
* default code page conversion, which will do the best job possible,
* but may be lossy, depending on the platform.
*
* If no other conversion is available, use invariant conversion and substitue
* '?' for non-invariant characters.
*
* Example Usage:
* UnicodeString s = whatever;
* printf("%s", CStr(s)());
*
* The explicit call to the CStr() constructor creates a temporary object.
* Operator () on the temporary object returns a (const char *) pointer.
* The lifetime of the (const char *) data is that of the temporary object,
* which works well when passing it as a parameter to another function, such as printf.
*/
U_NAMESPACE_BEGIN
class U_COMMON_API CStr : public UMemory {
public:
CStr(const UnicodeString &in);
~CStr();
const char * operator ()() const;
private:
CharString s;
CStr(const CStr &other); // Forbid copying of this class.
CStr &operator =(const CStr &other); // Forbid assignment.
};
U_NAMESPACE_END
#endif

2
intl/icu/source/common/cstring.c
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
*

2
intl/icu/source/common/cstring.h
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
*

2
intl/icu/source/common/cwchar.c
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
*

2
intl/icu/source/common/cwchar.h
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
*

40
intl/icu/source/common/dictbe.cpp
View File

@ -1,6 +1,8 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/**
*******************************************************************************
* Copyright (C) 2006-2015, International Business Machines Corporation
* Copyright (C) 2006-2016, International Business Machines Corporation
* and others. All Rights Reserved.
*******************************************************************************
*/
@ -70,13 +72,13 @@ DictionaryBreakEngine::findBreaks( UText *text,
rangeStart = current;
if (!isDict) {
utext_next32(text);
rangeStart = utext_getNativeIndex(text);
rangeStart = (int32_t)utext_getNativeIndex(text);
}
}
// rangeEnd = start + 1;
utext_setNativeIndex(text, start);
utext_next32(text);
rangeEnd = utext_getNativeIndex(text);
rangeEnd = (int32_t)utext_getNativeIndex(text);
}
else {
while((current = (int32_t)utext_getNativeIndex(text)) < endPos && fSet.contains(c)) {
@ -335,9 +337,9 @@ foundBest:
UChar32 pc;
int32_t chars = 0;
for (;;) {
int32_t pcIndex = utext_getNativeIndex(text);
int32_t pcIndex = (int32_t)utext_getNativeIndex(text);
pc = utext_next32(text);
int32_t pcSize = utext_getNativeIndex(text) - pcIndex;
int32_t pcSize = (int32_t)utext_getNativeIndex(text) - pcIndex;
chars += pcSize;
remaining -= pcSize;
if (remaining <= 0) {
@ -390,9 +392,9 @@ foundBest:
if (!fSuffixSet.contains(utext_previous32(text))) {
// Skip over previous end and PAIYANNOI
utext_next32(text);
int32_t paiyannoiIndex = utext_getNativeIndex(text);
int32_t paiyannoiIndex = (int32_t)utext_getNativeIndex(text);
utext_next32(text);
cuWordLength += utext_getNativeIndex(text) - paiyannoiIndex; // Add PAIYANNOI to word
cuWordLength += (int32_t)utext_getNativeIndex(text) - paiyannoiIndex; // Add PAIYANNOI to word
uc = utext_current32(text); // Fetch next character
}
else {
@ -404,9 +406,9 @@ foundBest:
if (utext_previous32(text) != THAI_MAIYAMOK) {
// Skip over previous end and MAIYAMOK
utext_next32(text);
int32_t maiyamokIndex = utext_getNativeIndex(text);
int32_t maiyamokIndex = (int32_t)utext_getNativeIndex(text);
utext_next32(text);
cuWordLength += utext_getNativeIndex(text) - maiyamokIndex; // Add MAIYAMOK to word
cuWordLength += (int32_t)utext_getNativeIndex(text) - maiyamokIndex; // Add MAIYAMOK to word
}
else {
// Restore prior position
@ -568,9 +570,9 @@ foundBest:
UChar32 uc;
int32_t chars = 0;
for (;;) {
int32_t pcIndex = utext_getNativeIndex(text);
int32_t pcIndex = (int32_t)utext_getNativeIndex(text);
pc = utext_next32(text);
int32_t pcSize = utext_getNativeIndex(text) - pcIndex;
int32_t pcSize = (int32_t)utext_getNativeIndex(text) - pcIndex;
chars += pcSize;
remaining -= pcSize;
if (remaining <= 0) {
@ -761,9 +763,9 @@ foundBest:
UChar32 uc;
int32_t chars = 0;
for (;;) {
int32_t pcIndex = utext_getNativeIndex(text);
int32_t pcIndex = (int32_t)utext_getNativeIndex(text);
pc = utext_next32(text);
int32_t pcSize = utext_getNativeIndex(text) - pcIndex;
int32_t pcSize = (int32_t)utext_getNativeIndex(text) - pcIndex;
chars += pcSize;
remaining -= pcSize;
if (remaining <= 0) {
@ -967,9 +969,9 @@ foundBest:
UChar32 uc;
int32_t chars = 0;
for (;;) {
int32_t pcIndex = utext_getNativeIndex(text);
int32_t pcIndex = (int32_t)utext_getNativeIndex(text);
pc = utext_next32(text);
int32_t pcSize = utext_getNativeIndex(text) - pcIndex;
int32_t pcSize = (int32_t)utext_getNativeIndex(text) - pcIndex;
chars += pcSize;
remaining -= pcSize;
if (remaining <= 0) {
@ -1166,14 +1168,14 @@ CjkBreakEngine::divideUpDictionaryRange( UText *inText,
int32_t limit = rangeEnd;
U_ASSERT(limit <= utext_nativeLength(inText));
if (limit > utext_nativeLength(inText)) {
limit = utext_nativeLength(inText);
limit = (int32_t)utext_nativeLength(inText);
}
inputMap.adoptInsteadAndCheckErrorCode(new UVector32(status), status);
if (U_FAILURE(status)) {
return 0;
}
while (utext_getNativeIndex(inText) < limit) {
int32_t nativePosition = utext_getNativeIndex(inText);
int32_t nativePosition = (int32_t)utext_getNativeIndex(inText);
UChar32 c = utext_next32(inText);
U_ASSERT(c != U_SENTINEL);
inString.append(c);
@ -1293,6 +1295,7 @@ CjkBreakEngine::divideUpDictionaryRange( UText *inText,
// ix is the corresponding string (code unit) index.
// They differ when the string contains supplementary characters.
int32_t ix = 0;
bool is_prev_katakana = false;
for (int32_t i = 0; i < numCodePts; ++i, ix = inString.moveIndex32(ix, 1)) {
if ((uint32_t)bestSnlp.elementAti(i) == kuint32max) {
continue;
@ -1306,7 +1309,7 @@ CjkBreakEngine::divideUpDictionaryRange( UText *inText,
// The NULL parameter is the ignored code unit lengths.
// if there are no single character matches found in the dictionary
// starting with this charcter, treat character as a 1-character word
// starting with this character, treat character as a 1-character word
// with the highest value possible, i.e. the least likely to occur.
// Exclude Korean characters from this treatment, as they should be left
// together by default.
@ -1331,7 +1334,6 @@ CjkBreakEngine::divideUpDictionaryRange( UText *inText,
// characters is considered a candidate word with a default cost
// specified in the katakanaCost table according to its length.
bool is_prev_katakana = false;
bool is_katakana = isKatakana(inString.char32At(ix));
int32_t katakanaRunLength = 1;
if (!is_prev_katakana && is_katakana) {

2
intl/icu/source/common/dictbe.h
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/**
*******************************************************************************
* Copyright (C) 2006-2014, International Business Machines Corporation *

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

@ -1,6 +1,8 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
* Copyright (C) 2014, International Business Machines
* Copyright (C) 2014-2016, International Business Machines
* Corporation and others. All Rights Reserved.
*******************************************************************************
* dictionarydata.h
@ -45,13 +47,13 @@ int32_t UCharsDictionaryMatcher::matches(UText *text, int32_t maxLength, int32_t
int32_t *prefix) const {
UCharsTrie uct(characters);
int32_t startingTextIndex = utext_getNativeIndex(text);
int32_t startingTextIndex = (int32_t)utext_getNativeIndex(text);
int32_t wordCount = 0;
int32_t codePointsMatched = 0;
for (UChar32 c = utext_next32(text); c >= 0; c=utext_next32(text)) {
UStringTrieResult result = (codePointsMatched == 0) ? uct.first(c) : uct.next(c);
int32_t lengthMatched = utext_getNativeIndex(text) - startingTextIndex;
int32_t lengthMatched = (int32_t)utext_getNativeIndex(text) - startingTextIndex;
codePointsMatched += 1;
if (USTRINGTRIE_HAS_VALUE(result)) {
if (wordCount < limit) {
@ -112,13 +114,13 @@ int32_t BytesDictionaryMatcher::matches(UText *text, int32_t maxLength, int32_t
int32_t *lengths, int32_t *cpLengths, int32_t *values,
int32_t *prefix) const {
BytesTrie bt(characters);
int32_t startingTextIndex = utext_getNativeIndex(text);
int32_t startingTextIndex = (int32_t)utext_getNativeIndex(text);
int32_t wordCount = 0;
int32_t codePointsMatched = 0;
for (UChar32 c = utext_next32(text); c >= 0; c=utext_next32(text)) {
UStringTrieResult result = (codePointsMatched == 0) ? bt.first(transform(c)) : bt.next(transform(c));
int32_t lengthMatched = utext_getNativeIndex(text) - startingTextIndex;
int32_t lengthMatched = (int32_t)utext_getNativeIndex(text) - startingTextIndex;
codePointsMatched += 1;
if (USTRINGTRIE_HAS_VALUE(result)) {
if (wordCount < limit) {

2
intl/icu/source/common/dictionarydata.h
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
* Copyright (C) 2014, International Business Machines

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

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*******************************************************************************
* Copyright (C) 2008, International Business Machines Corporation and
* others. All Rights Reserved.

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

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*

48
intl/icu/source/common/filteredbrk.cpp
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
* Copyright (C) 2014-2015, International Business Machines Corporation and
@ -401,7 +403,8 @@ SimpleFilteredSentenceBreakIterator::next() {
int32_t
SimpleFilteredSentenceBreakIterator::first(void) {
return internalNext(fDelegate->first());
// Don't suppress a break opportunity at the beginning of text.
return fDelegate->first();
}
int32_t
@ -415,7 +418,9 @@ SimpleFilteredSentenceBreakIterator::previous(void) {
}
UBool SimpleFilteredSentenceBreakIterator::isBoundary(int32_t offset) {
if(!fDelegate->isBoundary(offset)) return false; // no break to suppress
if (!fDelegate->isBoundary(offset)) return false; // no break to suppress
if (fData->fBackwardsTrie.isNull()) return true; // no data = no suppressions
UErrorCode status = U_ZERO_ERROR;
resetState(status);
@ -476,13 +481,42 @@ SimpleFilteredBreakIteratorBuilder::SimpleFilteredBreakIteratorBuilder(const Loc
: fSet(status)
{
if(U_SUCCESS(status)) {
LocalUResourceBundlePointer b(ures_open(U_ICUDATA_BRKITR, fromLocale.getBaseName(), &status));
LocalUResourceBundlePointer exceptions(ures_getByKeyWithFallback(b.getAlias(), "exceptions", NULL, &status));
LocalUResourceBundlePointer breaks(ures_getByKeyWithFallback(exceptions.getAlias(), "SentenceBreak", NULL, &status));
if(U_FAILURE(status)) return; // leaves the builder empty, if you try to use it.
UErrorCode subStatus = U_ZERO_ERROR;
LocalUResourceBundlePointer b(ures_open(U_ICUDATA_BRKITR, fromLocale.getBaseName(), &subStatus));
if (U_FAILURE(subStatus) || (subStatus == U_USING_DEFAULT_WARNING) ) {
status = subStatus; // copy the failing status
#if FB_DEBUG
fprintf(stderr, "open BUNDLE %s : %s, %s\n", fromLocale.getBaseName(), "[exit]", u_errorName(status));
#endif
return; // leaves the builder empty, if you try to use it.
}
LocalUResourceBundlePointer exceptions(ures_getByKeyWithFallback(b.getAlias(), "exceptions", NULL, &subStatus));
if (U_FAILURE(subStatus) || (subStatus == U_USING_DEFAULT_WARNING) ) {
status = subStatus; // copy the failing status
#if FB_DEBUG
fprintf(stderr, "open EXCEPTIONS %s : %s, %s\n", fromLocale.getBaseName(), "[exit]", u_errorName(status));
#endif
return; // leaves the builder empty, if you try to use it.
}
LocalUResourceBundlePointer breaks(ures_getByKeyWithFallback(exceptions.getAlias(), "SentenceBreak", NULL, &subStatus));
#if FB_DEBUG
{
UErrorCode subsub = subStatus;
fprintf(stderr, "open SentenceBreak %s => %s, %s\n", fromLocale.getBaseName(), ures_getLocale(breaks.getAlias(), &subsub), u_errorName(subStatus));
}
#endif
if (U_FAILURE(subStatus) || (subStatus == U_USING_DEFAULT_WARNING) ) {
status = subStatus; // copy the failing status
#if FB_DEBUG
fprintf(stderr, "open %s : %s, %s\n", fromLocale.getBaseName(), "[exit]", u_errorName(status));
#endif
return; // leaves the builder empty, if you try to use it.
}
LocalUResourceBundlePointer strs;
UErrorCode subStatus = status;
subStatus = status; // Pick up inherited warning status now
do {
strs.adoptInstead(ures_getNextResource(breaks.getAlias(), strs.orphan(), &subStatus));
if(strs.isValid() && U_SUCCESS(subStatus)) {

2
intl/icu/source/common/filterednormalizer2.cpp
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*

2
intl/icu/source/common/hash.h
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
* Copyright (C) 1997-2014, International Business Machines

2
intl/icu/source/common/icudataver.c
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
*

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

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
*

2
intl/icu/source/common/icuplugimp.h
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
*

47
intl/icu/source/common/listformatter.cpp
View File

@ -1,7 +1,9 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*
* Copyright (C) 2013-2014, International Business Machines
* Copyright (C) 2013-2016, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
@ -15,7 +17,7 @@
*/
#include "unicode/listformatter.h"
#include "simplepatternformatter.h"
#include "unicode/simpleformatter.h"
#include "mutex.h"
#include "hash.h"
#include "cstring.h"
@ -27,26 +29,27 @@
U_NAMESPACE_BEGIN
struct ListFormatInternal : public UMemory {
SimplePatternFormatter twoPattern;
SimplePatternFormatter startPattern;
SimplePatternFormatter middlePattern;
SimplePatternFormatter endPattern;
SimpleFormatter twoPattern;
SimpleFormatter startPattern;
SimpleFormatter middlePattern;
SimpleFormatter endPattern;
ListFormatInternal(
const UnicodeString& two,
const UnicodeString& start,
const UnicodeString& middle,
const UnicodeString& end) :
twoPattern(two),
startPattern(start),
middlePattern(middle),
endPattern(end) {}
const UnicodeString& end,
UErrorCode &errorCode) :
twoPattern(two, 2, 2, errorCode),
startPattern(start, 2, 2, errorCode),
middlePattern(middle, 2, 2, errorCode),
endPattern(end, 2, 2, errorCode) {}
ListFormatInternal(const ListFormatData &data) :
twoPattern(data.twoPattern),
startPattern(data.startPattern),
middlePattern(data.middlePattern),
endPattern(data.endPattern) { }
ListFormatInternal(const ListFormatData &data, UErrorCode &errorCode) :
twoPattern(data.twoPattern, errorCode),
startPattern(data.startPattern, errorCode),
middlePattern(data.middlePattern, errorCode),
endPattern(data.endPattern, errorCode) { }
ListFormatInternal(const ListFormatInternal &other) :
twoPattern(other.twoPattern),
@ -191,11 +194,15 @@ static ListFormatInternal* loadListFormatInternal(
if (U_FAILURE(errorCode)) {
return NULL;
}
ListFormatInternal* result = new ListFormatInternal(two, start, middle, end);
ListFormatInternal* result = new ListFormatInternal(two, start, middle, end, errorCode);
if (result == NULL) {
errorCode = U_MEMORY_ALLOCATION_ERROR;
return NULL;
}
if (U_FAILURE(errorCode)) {
delete result;
return NULL;
}
return result;
}
@ -231,8 +238,8 @@ ListFormatter* ListFormatter::createInstance(const Locale& locale, const char *s
return p;
}
ListFormatter::ListFormatter(const ListFormatData& listFormatData) {
owned = new ListFormatInternal(listFormatData);
ListFormatter::ListFormatter(const ListFormatData& listFormatData, UErrorCode &errorCode) {
owned = new ListFormatInternal(listFormatData, errorCode);
data = owned;
}
@ -252,7 +259,7 @@ ListFormatter::~ListFormatter() {
* according to pat. Any previous value of result gets replaced.
*/
static void joinStringsAndReplace(
const SimplePatternFormatter& pat,
const SimpleFormatter& pat,
const UnicodeString& first,
const UnicodeString& second,
UnicodeString &result,

2
intl/icu/source/common/loadednormalizer2impl.cpp
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
* Copyright (C) 2014, International Business Machines

2
intl/icu/source/common/localsvc.h
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
***************************************************************************
* Copyright (C) 2006 International Business Machines Corporation *

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

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*

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

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
* Copyright (c) 2004-2014, International Business Machines

2
intl/icu/source/common/locbased.h
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
* Copyright (c) 2004-2014, International Business Machines

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

@ -1,7 +1,9 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*
* Copyright (C) 1997-2013, International Business Machines
* Copyright (C) 1997-2016, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
@ -638,7 +640,7 @@ uloc_getDisplayName(const char *locale,
break;
case 3:
kenum = uloc_openKeywords(locale, pErrorCode);
/* fall through */
U_FALLTHROUGH;
default: {
const char* kw=uenum_next(kenum, &len, pErrorCode);
if (kw == NULL) {
@ -852,7 +854,7 @@ uloc_getDisplayKeywordValue( const char* locale,
/* now copy the dispName over if not NULL */
if(dispName != NULL){
if(dispNameLen <= destCapacity){
uprv_memcpy(dest, dispName, dispNameLen * U_SIZEOF_UCHAR);
u_memcpy(dest, dispName, dispNameLen);
return u_terminateUChars(dest, destCapacity, dispNameLen, status);
}else{
*status = U_BUFFER_OVERFLOW_ERROR;

290
intl/icu/source/i18n/locdspnm.cpp → intl/icu/source/common/locdspnm.cpp
View File

@ -1,6 +1,8 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
* Copyright (C) 2010-2014, International Business Machines Corporation and
* Copyright (C) 2010-2016, International Business Machines Corporation and
* others. All Rights Reserved.
*******************************************************************************
*/
@ -10,11 +12,11 @@
#if !UCONFIG_NO_FORMATTING
#include "unicode/locdspnm.h"
#include "unicode/msgfmt.h"
#include "unicode/simpleformatter.h"
#include "unicode/ures.h"
#include "unicode/udisplaycontext.h"
#include "unicode/udisplaycontext.h"
#include "unicode/brkiter.h"
#include "unicode/ucurr.h"
#include "cmemory.h"
#include "cstring.h"
#include "mutex.h"
@ -274,11 +276,15 @@ class LocaleDisplayNamesImpl : public LocaleDisplayNames {
UDialectHandling dialectHandling;
ICUDataTable langData;
ICUDataTable regionData;
MessageFormat *separatorFormat;
MessageFormat *format;
MessageFormat *keyTypeFormat;
SimpleFormatter separatorFormat;
SimpleFormatter format;
SimpleFormatter keyTypeFormat;
UDisplayContext capitalizationContext;
BreakIterator* capitalizationBrkIter;
#if !UCONFIG_NO_BREAK_ITERATION
BreakIterator* capitalizationBrkIter;
#else
UObject* capitalizationBrkIter;
#endif
static UMutex capitalizationBrkIterLock;
UnicodeString formatOpenParen;
UnicodeString formatReplaceOpenParen;
@ -334,7 +340,15 @@ private:
UnicodeString& result) const;
UnicodeString& appendWithSep(UnicodeString& buffer, const UnicodeString& src) const;
UnicodeString& adjustForUsageAndContext(CapContextUsage usage, UnicodeString& result) const;
UnicodeString& scriptDisplayName(const char* script, UnicodeString& result, UBool skipAdjust) const;
UnicodeString& regionDisplayName(const char* region, UnicodeString& result, UBool skipAdjust) const;
UnicodeString& variantDisplayName(const char* variant, UnicodeString& result, UBool skipAdjust) const;
UnicodeString& keyDisplayName(const char* key, UnicodeString& result, UBool skipAdjust) const;
UnicodeString& keyValueDisplayName(const char* key, const char* value,
UnicodeString& result, UBool skipAdjust) const;
void initialize(void);
struct CapitalizationContextSink;
};
UMutex LocaleDisplayNamesImpl::capitalizationBrkIterLock = U_MUTEX_INITIALIZER;
@ -344,9 +358,6 @@ LocaleDisplayNamesImpl::LocaleDisplayNamesImpl(const Locale& locale,
: dialectHandling(dialectHandling)
, langData(U_ICUDATA_LANG, locale)
, regionData(U_ICUDATA_REGION, locale)
, separatorFormat(NULL)
, format(NULL)
, keyTypeFormat(NULL)
, capitalizationContext(UDISPCTX_CAPITALIZATION_NONE)
, capitalizationBrkIter(NULL)
, nameLength(UDISPCTX_LENGTH_FULL)
@ -359,9 +370,6 @@ LocaleDisplayNamesImpl::LocaleDisplayNamesImpl(const Locale& locale,
: dialectHandling(ULDN_STANDARD_NAMES)
, langData(U_ICUDATA_LANG, locale)
, regionData(U_ICUDATA_REGION, locale)
, separatorFormat(NULL)
, format(NULL)
, keyTypeFormat(NULL)
, capitalizationContext(UDISPCTX_CAPITALIZATION_NONE)
, capitalizationBrkIter(NULL)
, nameLength(UDISPCTX_LENGTH_FULL)
@ -386,6 +394,54 @@ LocaleDisplayNamesImpl::LocaleDisplayNamesImpl(const Locale& locale,
initialize();
}
struct LocaleDisplayNamesImpl::CapitalizationContextSink : public ResourceSink {
UBool hasCapitalizationUsage;
LocaleDisplayNamesImpl& parent;
CapitalizationContextSink(LocaleDisplayNamesImpl& _parent)
: hasCapitalizationUsage(FALSE), parent(_parent) {}
virtual ~CapitalizationContextSink();
virtual void put(const char *key, ResourceValue &value, UBool /*noFallback*/,
UErrorCode &errorCode) {
ResourceTable contexts = value.getTable(errorCode);
if (U_FAILURE(errorCode)) { return; }
for (int i = 0; contexts.getKeyAndValue(i, key, value); ++i) {
CapContextUsage usageEnum;
if (uprv_strcmp(key, "key") == 0) {
usageEnum = kCapContextUsageKey;
} else if (uprv_strcmp(key, "keyValue") == 0) {
usageEnum = kCapContextUsageKeyValue;
} else if (uprv_strcmp(key, "languages") == 0) {
usageEnum = kCapContextUsageLanguage;
} else if (uprv_strcmp(key, "script") == 0) {
usageEnum = kCapContextUsageScript;
} else if (uprv_strcmp(key, "territory") == 0) {
usageEnum = kCapContextUsageTerritory;
} else if (uprv_strcmp(key, "variant") == 0) {
usageEnum = kCapContextUsageVariant;
} else {
continue;
}
int32_t len = 0;
const int32_t* intVector = value.getIntVector(len, errorCode);
if (U_FAILURE(errorCode)) { return; }
if (len < 2) { continue; }
int32_t titlecaseInt = (parent.capitalizationContext == UDISPCTX_CAPITALIZATION_FOR_UI_LIST_OR_MENU) ? intVector[0] : intVector[1];
if (titlecaseInt == 0) { continue; }
parent.fCapitalization[usageEnum] = TRUE;
hasCapitalizationUsage = TRUE;
}
}
};
// Virtual destructors must be defined out of line.
LocaleDisplayNamesImpl::CapitalizationContextSink::~CapitalizationContextSink() {}
void
LocaleDisplayNamesImpl::initialize(void) {
LocaleDisplayNamesImpl *nonConstThis = (LocaleDisplayNamesImpl *)this;
@ -399,14 +455,14 @@ LocaleDisplayNamesImpl::initialize(void) {
sep = UnicodeString("{0}, {1}", -1, US_INV);
}
UErrorCode status = U_ZERO_ERROR;
separatorFormat = new MessageFormat(sep, status);
separatorFormat.applyPatternMinMaxArguments(sep, 2, 2, status);
UnicodeString pattern;
langData.getNoFallback("localeDisplayPattern", "pattern", pattern);
if (pattern.isBogus()) {
pattern = UnicodeString("{0} ({1})", -1, US_INV);
}
format = new MessageFormat(pattern, status);
format.applyPatternMinMaxArguments(pattern, 2, 2, status);
if (pattern.indexOf((UChar)0xFF08) >= 0) {
formatOpenParen.setTo((UChar)0xFF08); // fullwidth (
formatReplaceOpenParen.setTo((UChar)0xFF3B); // fullwidth [
@ -424,62 +480,25 @@ LocaleDisplayNamesImpl::initialize(void) {
if (ktPattern.isBogus()) {
ktPattern = UnicodeString("{0}={1}", -1, US_INV);
}
keyTypeFormat = new MessageFormat(ktPattern, status);
keyTypeFormat.applyPatternMinMaxArguments(ktPattern, 2, 2, status);
uprv_memset(fCapitalization, 0, sizeof(fCapitalization));
#if !UCONFIG_NO_BREAK_ITERATION
// The following is basically copied from DateFormatSymbols::initializeData
typedef struct {
const char * usageName;
LocaleDisplayNamesImpl::CapContextUsage usageEnum;
} ContextUsageNameToEnum;
const ContextUsageNameToEnum contextUsageTypeMap[] = {
// Entries must be sorted by usageTypeName; entry with NULL name terminates list.
{ "key", kCapContextUsageKey },
{ "keyValue", kCapContextUsageKeyValue },
{ "languages", kCapContextUsageLanguage },
{ "script", kCapContextUsageScript },
{ "territory", kCapContextUsageTerritory },
{ "variant", kCapContextUsageVariant },
{ NULL, (CapContextUsage)0 },
};
// Only get the context data if we need it! This is a const object so we know now...
// Also check whether we will need a break iterator (depends on the data)
UBool needBrkIter = FALSE;
if (capitalizationContext == UDISPCTX_CAPITALIZATION_FOR_UI_LIST_OR_MENU || capitalizationContext == UDISPCTX_CAPITALIZATION_FOR_STANDALONE) {
int32_t len = 0;
UResourceBundle *localeBundle = ures_open(NULL, locale.getName(), &status);
if (U_SUCCESS(status)) {
UResourceBundle *contextTransforms = ures_getByKeyWithFallback(localeBundle, "contextTransforms", NULL, &status);
if (U_SUCCESS(status)) {
UResourceBundle *contextTransformUsage;
while ( (contextTransformUsage = ures_getNextResource(contextTransforms, NULL, &status)) != NULL ) {
const int32_t * intVector = ures_getIntVector(contextTransformUsage, &len, &status);
if (U_SUCCESS(status) && intVector != NULL && len >= 2) {
const char* usageKey = ures_getKey(contextTransformUsage);
if (usageKey != NULL) {
const ContextUsageNameToEnum * typeMapPtr = contextUsageTypeMap;
int32_t compResult = 0;
// linear search; list is short and we cannot be sure that bsearch is available
while ( typeMapPtr->usageName != NULL && (compResult = uprv_strcmp(usageKey, typeMapPtr->usageName)) > 0 ) {
++typeMapPtr;
}
if (typeMapPtr->usageName != NULL && compResult == 0) {
int32_t titlecaseInt = (capitalizationContext == UDISPCTX_CAPITALIZATION_FOR_UI_LIST_OR_MENU)? intVector[0]: intVector[1];
if (titlecaseInt != 0) {
fCapitalization[typeMapPtr->usageEnum] = TRUE;;
needBrkIter = TRUE;
}
}
}
}
status = U_ZERO_ERROR;
ures_close(contextTransformUsage);
}
ures_close(contextTransforms);
}
ures_close(localeBundle);
LocalUResourceBundlePointer resource(ures_open(NULL, locale.getName(), &status));
if (U_FAILURE(status)) { return; }
CapitalizationContextSink sink(*this);
ures_getAllItemsWithFallback(resource.getAlias(), "contextTransforms", sink, status);
if (status == U_MISSING_RESOURCE_ERROR) {
// Silently ignore. Not every locale has contextTransforms.
status = U_ZERO_ERROR;
} else if (U_FAILURE(status)) {
return;
}
needBrkIter = sink.hasCapitalizationUsage;
}
// Get a sentence break iterator if we will need it
if (needBrkIter || capitalizationContext == UDISPCTX_CAPITALIZATION_FOR_BEGINNING_OF_SENTENCE) {
@ -494,11 +513,10 @@ LocaleDisplayNamesImpl::initialize(void) {
}
LocaleDisplayNamesImpl::~LocaleDisplayNamesImpl() {
delete separatorFormat;
delete format;
delete keyTypeFormat;
#if !UCONFIG_NO_BREAK_ITERATION
delete capitalizationBrkIter;
}
#endif
}
const Locale&
LocaleDisplayNamesImpl::getLocale() const {
@ -543,6 +561,10 @@ LocaleDisplayNamesImpl::adjustForUsageAndContext(CapContextUsage usage,
UnicodeString&
LocaleDisplayNamesImpl::localeDisplayName(const Locale& locale,
UnicodeString& result) const {
if (locale.isBogus()) {
result.setToBogus();
return result;
}
UnicodeString resultName;
const char* lang = locale.getLanguage();
@ -593,45 +615,41 @@ LocaleDisplayNamesImpl::localeDisplayName(const Locale& locale,
UnicodeString resultRemainder;
UnicodeString temp;
StringEnumeration *e = NULL;
UErrorCode status = U_ZERO_ERROR;
if (hasScript) {
resultRemainder.append(scriptDisplayName(script, temp));
resultRemainder.append(scriptDisplayName(script, temp, TRUE));
}
if (hasCountry) {
appendWithSep(resultRemainder, regionDisplayName(country, temp));
appendWithSep(resultRemainder, regionDisplayName(country, temp, TRUE));
}
if (hasVariant) {
appendWithSep(resultRemainder, variantDisplayName(variant, temp));
appendWithSep(resultRemainder, variantDisplayName(variant, temp, TRUE));
}
resultRemainder.findAndReplace(formatOpenParen, formatReplaceOpenParen);
resultRemainder.findAndReplace(formatCloseParen, formatReplaceCloseParen);
e = locale.createKeywords(status);
if (e && U_SUCCESS(status)) {
LocalPointer<StringEnumeration> e(locale.createKeywords(status));
if (e.isValid() && U_SUCCESS(status)) {
UnicodeString temp2;
char value[ULOC_KEYWORD_AND_VALUES_CAPACITY]; // sigh, no ULOC_VALUE_CAPACITY
const char* key;
while ((key = e->next((int32_t *)0, status)) != NULL) {
locale.getKeywordValue(key, value, ULOC_KEYWORD_AND_VALUES_CAPACITY, status);
keyDisplayName(key, temp);
if (U_FAILURE(status)) {
return result;
}
keyDisplayName(key, temp, TRUE);
temp.findAndReplace(formatOpenParen, formatReplaceOpenParen);
temp.findAndReplace(formatCloseParen, formatReplaceCloseParen);
keyValueDisplayName(key, value, temp2);
keyValueDisplayName(key, value, temp2, TRUE);
temp2.findAndReplace(formatOpenParen, formatReplaceOpenParen);
temp2.findAndReplace(formatCloseParen, formatReplaceCloseParen);
if (temp2 != UnicodeString(value, -1, US_INV)) {
appendWithSep(resultRemainder, temp2);
} else if (temp != UnicodeString(key, -1, US_INV)) {
UnicodeString temp3;
Formattable data[] = {
temp,
temp2
};
FieldPosition fpos;
status = U_ZERO_ERROR;
keyTypeFormat->format(data, 2, temp3, fpos, status);
keyTypeFormat.format(temp, temp2, temp3, status);
appendWithSep(resultRemainder, temp3);
} else {
appendWithSep(resultRemainder, temp)
@ -639,17 +657,10 @@ LocaleDisplayNamesImpl::localeDisplayName(const Locale& locale,
.append(temp2);
}
}
delete e;
}
if (!resultRemainder.isEmpty()) {
Formattable data[] = {
resultName,
resultRemainder
};
FieldPosition fpos;
status = U_ZERO_ERROR;
format->format(data, 2, result, fpos, status);
format.format(resultName, resultRemainder, result.remove(), status);
return adjustForUsageAndContext(kCapContextUsageLanguage, result);
}
@ -662,17 +673,9 @@ LocaleDisplayNamesImpl::appendWithSep(UnicodeString& buffer, const UnicodeString
if (buffer.isEmpty()) {
buffer.setTo(src);
} else {
UnicodeString combined;
Formattable data[] = {
buffer,
src
};
FieldPosition fpos;
const UnicodeString *values[2] = { &buffer, &src };
UErrorCode status = U_ZERO_ERROR;
separatorFormat->format(data, 2, combined, fpos, status);
if (U_SUCCESS(status)) {
buffer.setTo(combined);
}
separatorFormat.formatAndReplace(values, 2, buffer, NULL, 0, status);
}
return buffer;
}
@ -714,56 +717,86 @@ LocaleDisplayNamesImpl::languageDisplayName(const char* lang,
UnicodeString&
LocaleDisplayNamesImpl::scriptDisplayName(const char* script,
UnicodeString& result) const {
UnicodeString& result,
UBool skipAdjust) const {
if (nameLength == UDISPCTX_LENGTH_SHORT) {
langData.get("Scripts%short", script, result);
if (!result.isBogus()) {
return adjustForUsageAndContext(kCapContextUsageScript, result);
return skipAdjust? result: adjustForUsageAndContext(kCapContextUsageScript, result);
}
}
langData.get("Scripts", script, result);
return adjustForUsageAndContext(kCapContextUsageScript, result);
return skipAdjust? result: adjustForUsageAndContext(kCapContextUsageScript, result);
}
UnicodeString&
LocaleDisplayNamesImpl::scriptDisplayName(const char* script,
UnicodeString& result) const {
return scriptDisplayName(script, result, FALSE);
}
UnicodeString&
LocaleDisplayNamesImpl::scriptDisplayName(UScriptCode scriptCode,
UnicodeString& result) const {
return scriptDisplayName(uscript_getName(scriptCode), result);
return scriptDisplayName(uscript_getName(scriptCode), result, FALSE);
}
UnicodeString&
LocaleDisplayNamesImpl::regionDisplayName(const char* region,
UnicodeString& result,
UBool skipAdjust) const {
if (nameLength == UDISPCTX_LENGTH_SHORT) {
regionData.get("Countries%short", region, result);
if (!result.isBogus()) {
return skipAdjust? result: adjustForUsageAndContext(kCapContextUsageTerritory, result);
}
}
regionData.get("Countries", region, result);
return skipAdjust? result: adjustForUsageAndContext(kCapContextUsageTerritory, result);
}
UnicodeString&
LocaleDisplayNamesImpl::regionDisplayName(const char* region,
UnicodeString& result) const {
if (nameLength == UDISPCTX_LENGTH_SHORT) {
regionData.get("Countries%short", region, result);
if (!result.isBogus()) {
return adjustForUsageAndContext(kCapContextUsageTerritory, result);
}
}
regionData.get("Countries", region, result);
return adjustForUsageAndContext(kCapContextUsageTerritory, result);
return regionDisplayName(region, result, FALSE);
}
UnicodeString&
LocaleDisplayNamesImpl::variantDisplayName(const char* variant,
UnicodeString& result,
UBool skipAdjust) const {
// don't have a resource for short variant names
langData.get("Variants", variant, result);
return skipAdjust? result: adjustForUsageAndContext(kCapContextUsageVariant, result);
}
UnicodeString&
LocaleDisplayNamesImpl::variantDisplayName(const char* variant,
UnicodeString& result) const {
// don't have a resource for short variant names
langData.get("Variants", variant, result);
return adjustForUsageAndContext(kCapContextUsageVariant, result);
return variantDisplayName(variant, result, FALSE);
}
UnicodeString&
LocaleDisplayNamesImpl::keyDisplayName(const char* key,
UnicodeString& result,
UBool skipAdjust) const {
// don't have a resource for short key names
langData.get("Keys", key, result);
return skipAdjust? result: adjustForUsageAndContext(kCapContextUsageKey, result);
}
UnicodeString&
LocaleDisplayNamesImpl::keyDisplayName(const char* key,
UnicodeString& result) const {
// don't have a resource for short key names
langData.get("Keys", key, result);
return adjustForUsageAndContext(kCapContextUsageKey, result);
return keyDisplayName(key, result, FALSE);
}
UnicodeString&
LocaleDisplayNamesImpl::keyValueDisplayName(const char* key,
const char* value,
UnicodeString& result) const {
UnicodeString& result,
UBool skipAdjust) const {
if (uprv_strcmp(key, "currency") == 0) {
// ICU4C does not have ICU4J CurrencyDisplayInfo equivalent for now.
UErrorCode sts = U_ZERO_ERROR;
@ -778,17 +811,24 @@ LocaleDisplayNamesImpl::keyValueDisplayName(const char* key,
return result;
}
result.setTo(currencyName, len);
return adjustForUsageAndContext(kCapContextUsageKeyValue, result);
return skipAdjust? result: adjustForUsageAndContext(kCapContextUsageKeyValue, result);
}
if (nameLength == UDISPCTX_LENGTH_SHORT) {
langData.get("Types%short", key, value, result);
if (!result.isBogus()) {
return adjustForUsageAndContext(kCapContextUsageKeyValue, result);
return skipAdjust? result: adjustForUsageAndContext(kCapContextUsageKeyValue, result);
}
}
langData.get("Types", key, value, result);
return adjustForUsageAndContext(kCapContextUsageKeyValue, result);
return skipAdjust? result: adjustForUsageAndContext(kCapContextUsageKeyValue, result);
}
UnicodeString&
LocaleDisplayNamesImpl::keyValueDisplayName(const char* key,
const char* value,
UnicodeString& result) const {
return keyValueDisplayName(key, value, result, FALSE);
}
////////////////////////////////////////////////////////////////////////////////////////////////////
@ -887,6 +927,10 @@ uldn_localeDisplayName(const ULocaleDisplayNames *ldn,
}
UnicodeString temp(result, 0, maxResultSize);
((const LocaleDisplayNames *)ldn)->localeDisplayName(locale, temp);
if (temp.isBogus()) {
*pErrorCode = U_ILLEGAL_ARGUMENT_ERROR;
return 0;
}
return temp.extract(result, maxResultSize, *pErrorCode);
}

85
intl/icu/source/common/locid.cpp
View File

@ -1,6 +1,8 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
* Copyright (C) 1997-2015, International Business Machines
* Copyright (C) 1997-2016, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
*
@ -42,6 +44,7 @@
#include "uhash.h"
#include "ucln_cmn.h"
#include "ustr_imp.h"
#include "charstr.h"
U_CDECL_BEGIN
static UBool U_CALLCONV locale_cleanup(void);
@ -57,6 +60,12 @@ static UMutex gDefaultLocaleMutex = U_MUTEX_INITIALIZER;
static UHashtable *gDefaultLocalesHashT = NULL;
static Locale *gDefaultLocale = NULL;
/**
* \def ULOC_STRING_LIMIT
* strings beyond this value crash in CharString
*/
#define ULOC_STRING_LIMIT 357913941
U_NAMESPACE_END
typedef enum ELocalePos {
@ -283,13 +292,12 @@ Locale::Locale( const char * newLanguage,
}
else
{
MaybeStackArray<char, ULOC_FULLNAME_CAPACITY> togo;
UErrorCode status = U_ZERO_ERROR;
int32_t size = 0;
int32_t lsize = 0;
int32_t csize = 0;
int32_t vsize = 0;
int32_t ksize = 0;
char *p;
// Calculate the size of the resulting string.
@ -297,13 +305,23 @@ Locale::Locale( const char * newLanguage,
if ( newLanguage != NULL )
{
lsize = (int32_t)uprv_strlen(newLanguage);
if ( lsize < 0 || lsize > ULOC_STRING_LIMIT ) { // int32 wrap
setToBogus();
return;
}
size = lsize;
}
CharString togo(newLanguage, lsize, status); // start with newLanguage
// _Country
if ( newCountry != NULL )
{
csize = (int32_t)uprv_strlen(newCountry);
if ( csize < 0 || csize > ULOC_STRING_LIMIT ) { // int32 wrap
setToBogus();
return;
}
size += csize;
}
@ -318,6 +336,10 @@ Locale::Locale( const char * newLanguage,
// remove trailing _'s
vsize = (int32_t)uprv_strlen(newVariant);
if ( vsize < 0 || vsize > ULOC_STRING_LIMIT ) { // int32 wrap
setToBogus();
return;
}
while( (vsize>1) && (newVariant[vsize-1] == SEP_CHAR) )
{
vsize--;
@ -342,70 +364,56 @@ Locale::Locale( const char * newLanguage,
if ( newKeywords != NULL)
{
ksize = (int32_t)uprv_strlen(newKeywords);
if ( ksize < 0 || ksize > ULOC_STRING_LIMIT ) {
setToBogus();
return;
}
size += ksize + 1;
}
// NOW we have the full locale string..
/*if the whole string is longer than our internal limit, we need
to go to the heap for temporary buffers*/
if (size >= togo.getCapacity())
{
// If togo_heap could not be created, initialize with default settings.
if (togo.resize(size+1) == NULL) {
init(NULL, FALSE);
}
}
togo[0] = 0;
// Now, copy it back.
p = togo.getAlias();
if ( lsize != 0 )
{
uprv_strcpy(p, newLanguage);
p += lsize;
}
// newLanguage is already copied
if ( ( vsize != 0 ) || (csize != 0) ) // at least: __v
{ // ^
*p++ = SEP_CHAR;
togo.append(SEP_CHAR, status);
}
if ( csize != 0 )
{
uprv_strcpy(p, newCountry);
p += csize;
togo.append(newCountry, status);
}
if ( vsize != 0)
{
*p++ = SEP_CHAR; // at least: __v
uprv_strncpy(p, newVariant, vsize); // Must use strncpy because
p += vsize; // of trimming (above).
*p = 0; // terminate
togo.append(SEP_CHAR, status)
.append(newVariant, vsize, status);
}
if ( ksize != 0)
{
if (uprv_strchr(newKeywords, '=')) {
*p++ = '@'; /* keyword parsing */
togo.append('@', status); /* keyword parsing */
}
else {
*p++ = '_'; /* Variant parsing with a script */
togo.append('_', status); /* Variant parsing with a script */
if ( vsize == 0) {
*p++ = '_'; /* No country found */
togo.append('_', status); /* No country found */
}
}
uprv_strcpy(p, newKeywords);
p += ksize;
togo.append(newKeywords, status);
}
if (U_FAILURE(status)) {
// Something went wrong with appending, etc.
setToBogus();
return;
}
// Parse it, because for example 'language' might really be a complete
// string.
init(togo.getAlias(), FALSE);
init(togo.data(), FALSE);
}
}
@ -536,7 +544,7 @@ Locale& Locale::init(const char* localeID, UBool canonicalize)
/* after uloc_getName/canonicalize() we know that only '_' are separators */
separator = field[0] = fullName;
fieldIdx = 1;
while ((separator = uprv_strchr(field[fieldIdx-1], SEP_CHAR)) && fieldIdx < (int32_t)(sizeof(field)/sizeof(field[0]))-1) {
while ((separator = uprv_strchr(field[fieldIdx-1], SEP_CHAR)) && fieldIdx < UPRV_LENGTHOF(field)-1) {
field[fieldIdx] = separator + 1;
fieldLen[fieldIdx-1] = (int32_t)(separator - field[fieldIdx-1]);
fieldIdx++;
@ -662,6 +670,7 @@ Locale::setToBogus() {
*script = 0;
*country = 0;
fIsBogus = TRUE;
variantBegin = 0;
}
const Locale& U_EXPORT2

54
intl/icu/source/common/loclikely.cpp
View File

@ -1,7 +1,9 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*
* Copyright (C) 1997-2014, International Business Machines
* Copyright (C) 1997-2016, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
@ -1331,3 +1333,53 @@ Locale::isRightToLeft() const {
}
U_NAMESPACE_END
// The following must at least allow for rg key value (6) plus terminator (1).
#define ULOC_RG_BUFLEN 8
U_CAPI int32_t U_EXPORT2
ulocimp_getRegionForSupplementalData(const char *localeID, UBool inferRegion,
char *region, int32_t regionCapacity, UErrorCode* status) {
if (U_FAILURE(*status)) {
return 0;
}
char rgBuf[ULOC_RG_BUFLEN];
UErrorCode rgStatus = U_ZERO_ERROR;
// First check for rg keyword value
int32_t rgLen = uloc_getKeywordValue(localeID, "rg", rgBuf, ULOC_RG_BUFLEN, &rgStatus);
if (U_FAILURE(rgStatus) || rgLen != 6) {
rgLen = 0;
} else {
// rgBuf guaranteed to be zero terminated here, with text len 6
char *rgPtr = rgBuf;
for (; *rgPtr!= 0; rgPtr++) {
*rgPtr = uprv_toupper(*rgPtr);
}
rgLen = (uprv_strcmp(rgBuf+2, "ZZZZ") == 0)? 2: 0;
}
if (rgLen == 0) {
// No valid rg keyword value, try for unicode_region_subtag
rgLen = uloc_getCountry(localeID, rgBuf, ULOC_RG_BUFLEN, status);
if (U_FAILURE(*status)) {
rgLen = 0;
} else if (rgLen == 0 && inferRegion) {
// no unicode_region_subtag but inferRegion TRUE, try likely subtags
char locBuf[ULOC_FULLNAME_CAPACITY];
rgStatus = U_ZERO_ERROR;
(void)uloc_addLikelySubtags(localeID, locBuf, ULOC_FULLNAME_CAPACITY, &rgStatus);
if (U_SUCCESS(rgStatus)) {
rgLen = uloc_getCountry(locBuf, rgBuf, ULOC_RG_BUFLEN, status);
if (U_FAILURE(*status)) {
rgLen = 0;
}
}
}
}
rgBuf[rgLen] = 0;
uprv_strncpy(region, rgBuf, regionCapacity);
return u_terminateChars(region, regionCapacity, rgLen, status);
}

108
intl/icu/source/common/locmap.c
View File

@ -1,6 +1,8 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
* Copyright (C) 1996-2014, International Business Machines
* Copyright (C) 1996-2016, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
*
@ -113,7 +115,7 @@ static const ILcidPosixElement locmap_ ## id [] =
* @param _posixID the full POSIX ID for this entry.
*/
#define ILCID_POSIX_MAP(_posixID) \
{sizeof(locmap_ ## _posixID)/sizeof(ILcidPosixElement), locmap_ ## _posixID}
{UPRV_LENGTHOF(locmap_ ## _posixID), locmap_ ## _posixID}
/*
////////////////////////////////////////////
@ -196,7 +198,8 @@ ILCID_POSIX_SUBTABLE(bn) {
ILCID_POSIX_SUBTABLE(bo) {
{0x51, "bo"},
{0x0851, "bo_BT"},
{0x0451, "bo_CN"}
{0x0451, "bo_CN"},
{0x0c51, "dz_BT"}
};
ILCID_POSIX_ELEMENT_ARRAY(0x047e, br, br_FR)
@ -212,11 +215,8 @@ ILCID_POSIX_ELEMENT_ARRAY(0x045c, chr,chr_US)
ILCID_POSIX_SUBTABLE(ckb) {
{0x92, "ckb"},
{0x92, "ku"},
{0x7c92, "ckb_Arab"},
{0x7c92, "ku_Arab"},
{0x0492, "ckb_Arab_IQ"},
{0x0492, "ku_Arab_IQ"}
{0x0492, "ckb_Arab_IQ"}
};
/* Declared as cs_CZ to get around compiler errors on z/OS, which defines cs as a function */
@ -279,6 +279,7 @@ ILCID_POSIX_SUBTABLE(es) {
{0x340a, "es_CL"},
{0x240a, "es_CO"},
{0x140a, "es_CR"},
{0x5c0a, "es_CU"},
{0x1c0a, "es_DO"},
{0x300a, "es_EC"},
{0x0c0a, "es_ES"}, /*Modern sort.*/
@ -318,7 +319,8 @@ ILCID_POSIX_SUBTABLE(fa_AF) {
ILCID_POSIX_SUBTABLE(ff) {
{0x67, "ff"},
{0x7c67, "ff_Latn"},
{0x0867, "ff_Latn_SN"}
{0x0867, "ff_Latn_SN"},
{0x0467, "ff_NG"}
};
ILCID_POSIX_ELEMENT_ARRAY(0x040b, fi, fi_FI)
@ -552,7 +554,35 @@ ILCID_POSIX_SUBTABLE(qu) {
{0x0C6b, "quz_PE"}
};
ILCID_POSIX_ELEMENT_ARRAY(0x0486, qut, qut_GT) /* qut is an ISO-639-3 code */
ILCID_POSIX_SUBTABLE(quc) {
{0x93, "quc"},
{0x0493, "quc_CO"},
/*
"quc_Latn_GT" is an exceptional case. Language ID of "quc"
is 0x93, but LCID of "quc_Latn_GT" is 0x486, which should be
under the group of "qut". "qut" is a retired ISO 639-3 language
code for West Central Quiche, and merged to "quc".
It looks Windows previously reserved "qut" for K'iche', but,
decided to use "quc" when adding a locale for K'iche' (Guatemala).
This data structure used here assumes language ID bits in
LCID is unique for alphabetic language code. But this is not true
for "quc_Latn_GT". If we don't have the data below, LCID look up
by alphabetic locale ID (POSIX) will fail. The same entry is found
under "qut" below, which is required for reverse look up.
*/
{0x0486, "quc_Latn_GT"}
};
ILCID_POSIX_SUBTABLE(qut) {
{0x86, "qut"},
{0x0486, "qut_GT"},
/*
See the note in "quc" above.
*/
{0x0486, "quc_Latn_GT"}
};
ILCID_POSIX_ELEMENT_ARRAY(0x0417, rm, rm_CH)
ILCID_POSIX_SUBTABLE(ro) {
@ -578,6 +608,7 @@ ILCID_POSIX_ELEMENT_ARRAY(0x0485, sah,sah_RU)
ILCID_POSIX_SUBTABLE(sd) {
{0x59, "sd"},
{0x0459, "sd_IN"},
{0x0459, "sd_Deva_IN"},
{0x0859, "sd_PK"}
};
@ -660,6 +691,7 @@ ILCID_POSIX_SUBTABLE(tzm) {
{0x7c5f, "tzm_Latn"},
{0x085f, "tzm_Latn_DZ"},
{0x105f, "tzm_Tfng_MA"},
{0x045f, "tzm_Arab_MA"},
{0x045f, "tmz"}
};
@ -828,6 +860,7 @@ static const ILcidPosixMap gPosixIDmap[] = {
ILCID_POSIX_MAP(ps), /* ps Pashto 0x63 */
ILCID_POSIX_MAP(pt), /* pt Portuguese 0x16 */
ILCID_POSIX_MAP(qu), /* qu Quechua 0x6B */
ILCID_POSIX_MAP(quc), /* quc K'iche 0x93 */
ILCID_POSIX_MAP(qut), /* qut K'iche 0x86 */
ILCID_POSIX_MAP(rm), /* rm Raeto-Romance/Romansh 0x17 */
ILCID_POSIX_MAP(ro), /* ro Romanian 0x18 */
@ -874,7 +907,7 @@ static const ILcidPosixMap gPosixIDmap[] = {
ILCID_POSIX_MAP(zu), /* zu Zulu 0x35 */
};
static const uint32_t gLocaleCount = sizeof(gPosixIDmap)/sizeof(ILcidPosixMap);
static const uint32_t gLocaleCount = UPRV_LENGTHOF(gPosixIDmap);
/**
* Do not call this function. It is called by hostID.
@ -985,33 +1018,40 @@ uprv_convertToPosix(uint32_t hostid, char *posixID, int32_t posixIDCapacity, UEr
const char *pPosixID = NULL;
#ifdef USE_WINDOWS_LOCALE_API
int32_t tmpLen = 0;
char locName[157]; /* ULOC_FULLNAME_CAPACITY */
// Note: Windows primary lang ID 0x92 in LCID is used for Central Kurdish and
// GetLocaleInfo() maps such LCID to "ku". However, CLDR uses "ku" for
// Northern Kurdish and "ckb" for Central Kurdish. For this reason, we cannot
// use the Windows API to resolve locale ID for this specific case.
if (hostid & 0x3FF != 0x92) {
int32_t tmpLen = 0;
char locName[157]; /* ULOC_FULLNAME_CAPACITY */
tmpLen = GetLocaleInfoA(hostid, LOCALE_SNAME, (LPSTR)locName, sizeof(locName)/sizeof(locName[0]));
if (tmpLen > 1) {
/* Windows locale name may contain sorting variant, such as "es-ES_tradnl".
In such case, we need special mapping data found in the hardcoded table
in this source file. */
char *p = uprv_strchr(locName, '_');
if (p) {
/* Keep the base locale, without variant */
*p = 0;
tmpLen = uprv_strlen(locName);
} else {
/* No hardcoded table lookup necessary */
bLookup = FALSE;
}
/* Change the tag separator from '-' to '_' */
p = locName;
while (*p) {
if (*p == '-') {
*p = '_';
tmpLen = GetLocaleInfoA(hostid, LOCALE_SNAME, (LPSTR)locName, UPRV_LENGTHOF(locName));
if (tmpLen > 1) {
/* Windows locale name may contain sorting variant, such as "es-ES_tradnl".
In such case, we need special mapping data found in the hardcoded table
in this source file. */
char *p = uprv_strchr(locName, '_');
if (p) {
/* Keep the base locale, without variant */
*p = 0;
tmpLen = uprv_strlen(locName);
}
p++;
else {
/* No hardcoded table lookup necessary */
bLookup = FALSE;
}
/* Change the tag separator from '-' to '_' */
p = locName;
while (*p) {
if (*p == '-') {
*p = '_';
}
p++;
}
FIX_LANGUAGE_ID_TAG(locName, tmpLen);
pPosixID = locName;
}
FIX_LANGUAGE_ID_TAG(locName, tmpLen);
pPosixID = locName;
}
#endif
if (bLookup) {

2
intl/icu/source/common/locmap.h
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
*

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

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*

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

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
* Copyright (C) 2002-2014, International Business Machines Corporation and

2
intl/icu/source/common/locutil.h
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/**
*******************************************************************************
* Copyright (C) 2002-2005, International Business Machines Corporation and *

2
intl/icu/source/common/messageimpl.h
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
* Copyright (C) 2011, International Business Machines

4
intl/icu/source/common/messagepattern.cpp
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
* Copyright (C) 2011-2012, International Business Machines
@ -114,7 +116,7 @@ MessagePatternList<T, stackCapacity>::copyFrom(
errorCode=U_MEMORY_ALLOCATION_ERROR;
return;
}
uprv_memcpy(a.getAlias(), other.a.getAlias(), length*sizeof(T));
uprv_memcpy(a.getAlias(), other.a.getAlias(), (size_t)length*sizeof(T));
}
}

2
intl/icu/source/common/msvcres.h
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
//{{NO_DEPENDENCIES}}
// Copyright (c) 2003-2010 International Business Machines
// Corporation and others. All Rights Reserved.

2
intl/icu/source/common/mutex.h
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
*

1084
intl/icu/source/common/norm2_nfc_data.h
View File

File diff suppressed because it is too large Load Diff

2
intl/icu/source/common/norm2allmodes.h
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
* Copyright (C) 2014, International Business Machines

5
intl/icu/source/common/normalizer2.cpp
View File

@ -1,7 +1,9 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*
* Copyright (C) 2009-2014, International Business Machines
* Copyright (C) 2009-2016, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
@ -31,6 +33,7 @@
using icu::Normalizer2Impl;
// NFC/NFD data machine-generated by gennorm2 --csource
#define INCLUDED_FROM_NORMALIZER2_CPP
#include "norm2_nfc_data.h"
U_NAMESPACE_BEGIN

2
intl/icu/source/common/normalizer2impl.cpp
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*

2
intl/icu/source/common/normalizer2impl.h
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*

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

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*************************************************************************
* COPYRIGHT:

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

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
* Copyright (C) 2003-2003, International Business Machines

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

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
* Copyright (C) 2011, International Business Machines

2
intl/icu/source/common/patternprops.h
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
* Copyright (C) 2011, International Business Machines

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

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
* Copyright (C) 2015, International Business Machines Corporation and
* others. All Rights Reserved.

2
intl/icu/source/common/pluralmap.h
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
* Copyright (C) 2015, International Business Machines Corporation and

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

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
* Copyright (c) 2002-2014, International Business Machines

2
intl/icu/source/common/propname.h
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
* Copyright (c) 2002-2011, International Business Machines

1798
intl/icu/source/common/propname_data.h
View File

File diff suppressed because it is too large Load Diff

12
intl/icu/source/common/propsvec.c
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*
@ -218,7 +220,7 @@ upvec_setValue(UPropsVectors *pv,
*pErrorCode=U_MEMORY_ALLOCATION_ERROR;
return;
}
uprv_memcpy(newVectors, pv->v, rows*columns*4);
uprv_memcpy(newVectors, pv->v, (size_t)rows*columns*4);
firstRow=newVectors+(firstRow-pv->v);
lastRow=newVectors+(lastRow-pv->v);
uprv_free(pv->v);
@ -240,7 +242,7 @@ upvec_setValue(UPropsVectors *pv,
if(splitFirstRow) {
/* copy all affected rows up one and move the lastRow pointer */
count = (int32_t)((lastRow-firstRow)+columns);
uprv_memmove(firstRow+columns, firstRow, count*4);
uprv_memmove(firstRow+columns, firstRow, (size_t)count*4);
lastRow+=columns;
/* split the range and move the firstRow pointer */
@ -251,7 +253,7 @@ upvec_setValue(UPropsVectors *pv,
/* split the last row */
if(splitLastRow) {
/* copy the last row data */
uprv_memcpy(lastRow+columns, lastRow, columns*4);
uprv_memcpy(lastRow+columns, lastRow, (size_t)columns*4);
/* split the range and move the firstRow pointer */
lastRow[1]=lastRow[columns]=(uint32_t)limit;
@ -415,7 +417,7 @@ upvec_compact(UPropsVectors *pv, UPVecCompactHandler *handler, void *context, UE
/* add a new values vector if it is different from the current one */
if(count<0 || 0!=uprv_memcmp(row+2, pv->v+count, valueColumns*4)) {
count+=valueColumns;
uprv_memmove(pv->v+count, row+2, valueColumns*4);
uprv_memmove(pv->v+count, row+2, (size_t)valueColumns*4);
}
if(start<UPVEC_FIRST_SPECIAL_CP) {
@ -477,7 +479,7 @@ upvec_cloneArray(const UPropsVectors *pv,
U_CAPI UTrie2 * U_EXPORT2
upvec_compactToUTrie2WithRowIndexes(UPropsVectors *pv, UErrorCode *pErrorCode) {
UPVecToUTrie2Context toUTrie2={ NULL };
UPVecToUTrie2Context toUTrie2={ NULL, 0, 0, 0 };
upvec_compact(pv, upvec_compactToUTrie2Handler, &toUTrie2, pErrorCode);
utrie2_freeze(toUTrie2.trie, UTRIE2_16_VALUE_BITS, pErrorCode);
if(U_FAILURE(*pErrorCode)) {

2
intl/icu/source/common/propsvec.h
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*

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

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*

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

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*

96
intl/icu/source/common/putil.cpp
View File

@ -1,7 +1,9 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
*
* Copyright (C) 1997-2014, International Business Machines
* Copyright (C) 1997-2016, International Business Machines
* Corporation and others. All Rights Reserved.
*
******************************************************************************
@ -832,7 +834,6 @@ static const char* remapShortTimeZone(const char *stdID, const char *dstID, int3
#endif
#ifdef SEARCH_TZFILE
#define MAX_PATH_SIZE PATH_MAX /* Set the limit for the size of the path. */
#define MAX_READ_SIZE 512
typedef struct DefaultTZInfo {
@ -908,15 +909,19 @@ static UBool compareBinaryFiles(const char* defaultTZFileName, const char* TZFil
return result;
}
/*
* This method recursively traverses the directory given for a matching TZ file and returns the first match.
*/
/* dirent also lists two entries: "." and ".." that we can safely ignore. */
#define SKIP1 "."
#define SKIP2 ".."
static char SEARCH_TZFILE_RESULT[MAX_PATH_SIZE] = "";
static UBool U_CALLCONV putil_cleanup(void);
static CharString *gSearchTZFileResult = NULL;
/*
* This method recursively traverses the directory given for a matching TZ file and returns the first match.
* This function is not thread safe - it uses a global, gSearchTZFileResult, to hold its results.
*/
static char* searchForTZFile(const char* path, DefaultTZInfo* tzInfo) {
char curpath[MAX_PATH_SIZE];
DIR* dirp = opendir(path);
DIR* subDirp = NULL;
struct dirent* dirEntry = NULL;
@ -926,24 +931,40 @@ static char* searchForTZFile(const char* path, DefaultTZInfo* tzInfo) {
return result;
}
if (gSearchTZFileResult == NULL) {
gSearchTZFileResult = new CharString;
if (gSearchTZFileResult == NULL) {
return NULL;
}
ucln_common_registerCleanup(UCLN_COMMON_PUTIL, putil_cleanup);
}
/* Save the current path */
uprv_memset(curpath, 0, MAX_PATH_SIZE);
uprv_strcpy(curpath, path);
UErrorCode status = U_ZERO_ERROR;
CharString curpath(path, -1, status);
if (U_FAILURE(status)) {
return NULL;
}
/* Check each entry in the directory. */
while((dirEntry = readdir(dirp)) != NULL) {
const char* dirName = dirEntry->d_name;
if (uprv_strcmp(dirName, SKIP1) != 0 && uprv_strcmp(dirName, SKIP2) != 0) {
/* Create a newpath with the new entry to test each entry in the directory. */
char newpath[MAX_PATH_SIZE];
uprv_strcpy(newpath, curpath);
uprv_strcat(newpath, dirName);
CharString newpath(curpath, status);
newpath.append(dirName, -1, status);
if (U_FAILURE(status)) {
return NULL;
}
if ((subDirp = opendir(newpath)) != NULL) {
if ((subDirp = opendir(newpath.data())) != NULL) {
/* If this new path is a directory, make a recursive call with the newpath. */
closedir(subDirp);
uprv_strcat(newpath, "/");
result = searchForTZFile(newpath, tzInfo);
newpath.append('/', status);
if (U_FAILURE(status)) {
return NULL;
}
result = searchForTZFile(newpath.data(), tzInfo);
/*
Have to get out here. Otherwise, we'd keep looking
and return the first match in the top-level directory
@ -955,11 +976,19 @@ static char* searchForTZFile(const char* path, DefaultTZInfo* tzInfo) {
if (result != NULL)
break;
} else if (uprv_strcmp(TZFILE_SKIP, dirName) != 0 && uprv_strcmp(TZFILE_SKIP2, dirName) != 0) {
if(compareBinaryFiles(TZDEFAULT, newpath, tzInfo)) {
const char* zoneid = newpath + (sizeof(TZZONEINFO)) - 1;
if(compareBinaryFiles(TZDEFAULT, newpath.data(), tzInfo)) {
int32_t amountToSkip = sizeof(TZZONEINFO) - 1;
if (amountToSkip > newpath.length()) {
amountToSkip = newpath.length();
}
const char* zoneid = newpath.data() + amountToSkip;
skipZoneIDPrefix(&zoneid);
uprv_strcpy(SEARCH_TZFILE_RESULT, zoneid);
result = SEARCH_TZFILE_RESULT;
gSearchTZFileResult->clear();
gSearchTZFileResult->append(zoneid, -1, status);
if (U_FAILURE(status)) {
return NULL;
}
result = gSearchTZFileResult->data();
/* Get out after the first one found. */
break;
}
@ -1009,6 +1038,10 @@ uprv_tzname(int n)
&& uprv_strcmp(tzid, TZ_ENV_CHECK) != 0
#endif
) {
/* The colon forces tzset() to treat the remainder as zoneinfo path */
if (tzid[0] == ':') {
tzid++;
}
/* This might be a good Olson ID. */
skipZoneIDPrefix(&tzid);
return tzid;
@ -1024,7 +1057,7 @@ uprv_tzname(int n)
because the tzfile contents is underspecified.
This isn't guaranteed to work because it may not be a symlink.
*/
int32_t ret = (int32_t)readlink(TZDEFAULT, gTimeZoneBuffer, sizeof(gTimeZoneBuffer));
int32_t ret = (int32_t)readlink(TZDEFAULT, gTimeZoneBuffer, sizeof(gTimeZoneBuffer)-1);
if (0 < ret) {
int32_t tzZoneInfoLen = uprv_strlen(TZZONEINFO);
gTimeZoneBuffer[ret] = 0;
@ -1144,6 +1177,11 @@ static UBool U_CALLCONV putil_cleanup(void)
gTimeZoneFilesDirectory = NULL;
gTimeZoneFilesInitOnce.reset();
#ifdef SEARCH_TZFILE
delete gSearchTZFileResult;
gSearchTZFileResult = NULL;
#endif
#if U_POSIX_LOCALE || U_PLATFORM_USES_ONLY_WIN32_API
if (gCorrectedPOSIXLocale) {
uprv_free(gCorrectedPOSIXLocale);
@ -1392,9 +1430,18 @@ static const char *uprv_getPOSIXIDForCategory(int category)
{
/* Maybe we got some garbage. Try something more reasonable */
posixID = getenv("LC_ALL");
/* Solaris speaks POSIX - See IEEE Std 1003.1-2008
* This is needed to properly handle empty env. variables
*/
#if U_PLATFORM == U_PF_SOLARIS
if ((posixID == 0) || (posixID[0] == '\0')) {
posixID = getenv(category == LC_MESSAGES ? "LC_MESSAGES" : "LC_CTYPE");
if ((posixID == 0) || (posixID[0] == '\0')) {
#else
if (posixID == 0) {
posixID = getenv(category == LC_MESSAGES ? "LC_MESSAGES" : "LC_CTYPE");
if (posixID == 0) {
#endif
posixID = getenv("LANG");
}
}
@ -1886,7 +1933,10 @@ int_getDefaultCodepage()
localeName = uprv_getPOSIXIDForDefaultCodepage();
uprv_memset(codesetName, 0, sizeof(codesetName));
#if U_HAVE_NL_LANGINFO_CODESET
/* On Solaris nl_langinfo returns C locale values unless setlocale
* was called earlier.
*/
#if (U_HAVE_NL_LANGINFO_CODESET && U_PLATFORM != U_PF_SOLARIS)
/* When available, check nl_langinfo first because it usually gives more
useful names. It depends on LC_CTYPE.
nl_langinfo may use the same buffer as setlocale. */
@ -2197,6 +2247,7 @@ uprv_dlsym_func(void *lib, const char* sym, UErrorCode *status) {
U_INTERNAL void * U_EXPORT2
uprv_dl_open(const char *libName, UErrorCode *status) {
(void)libName;
if(U_FAILURE(*status)) return NULL;
*status = U_UNSUPPORTED_ERROR;
return NULL;
@ -2204,6 +2255,7 @@ uprv_dl_open(const char *libName, UErrorCode *status) {
U_INTERNAL void U_EXPORT2
uprv_dl_close(void *lib, UErrorCode *status) {
(void)lib;
if(U_FAILURE(*status)) return;
*status = U_UNSUPPORTED_ERROR;
return;
@ -2212,6 +2264,8 @@ uprv_dl_close(void *lib, UErrorCode *status) {
U_INTERNAL UVoidFunction* U_EXPORT2
uprv_dlsym_func(void *lib, const char* sym, UErrorCode *status) {
(void)lib;
(void)sym;
if(U_SUCCESS(*status)) {
*status = U_UNSUPPORTED_ERROR;
}

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

@ -1,7 +1,9 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
*
* Copyright (C) 1997-2015, International Business Machines
* Copyright (C) 1997-2016, International Business Machines
* Corporation and others. All Rights Reserved.
*
******************************************************************************
@ -148,7 +150,7 @@ typedef size_t uintptr_t;
#ifdef U_HAVE_MMAP
/* Use the predefined value. */
#elif U_PLATFORM_HAS_WIN32_API
#elif U_PLATFORM_USES_ONLY_WIN32_API
# define U_HAVE_MMAP 0
#else
# define U_HAVE_MMAP 1
@ -171,7 +173,7 @@ typedef size_t uintptr_t;
*/
#ifdef U_HAVE_DIRENT_H
/* Use the predefined value. */
#elif U_PLATFORM_HAS_WIN32_API
#elif U_PLATFORM_USES_ONLY_WIN32_API
# define U_HAVE_DIRENT_H 0
#else
# define U_HAVE_DIRENT_H 1

187
intl/icu/source/common/rbbi.cpp
View File

@ -1,6 +1,8 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
***************************************************************************
* Copyright (C) 1999-2014 International Business Machines Corporation
* Copyright (C) 1999-2016 International Business Machines Corporation
* and others. All rights reserved.
***************************************************************************
*/
@ -72,21 +74,6 @@ RuleBasedBreakIterator::RuleBasedBreakIterator(RBBIDataHeader* data, UErrorCode
}
}
/**
* Same as above but does not adopt memory
*/
RuleBasedBreakIterator::RuleBasedBreakIterator(const RBBIDataHeader* data, enum EDontAdopt, UErrorCode &status)
{
init();
fData = new RBBIDataWrapper(data, RBBIDataWrapper::kDontAdopt, status); // status checked in constructor
if (U_FAILURE(status)) {return;}
if(fData == 0) {
status = U_MEMORY_ALLOCATION_ERROR;
return;
}
}
//
// Construct from precompiled binary rules (tables). This constructor is public API,
// taking the rules as a (const uint8_t *) to match the type produced by getBinaryRules().
@ -715,7 +702,7 @@ int32_t RuleBasedBreakIterator::following(int32_t offset) {
// Move requested offset to a code point start. It might be on a trail surrogate,
// or on a trail byte if the input is UTF-8.
utext_setNativeIndex(fText, offset);
offset = utext_getNativeIndex(fText);
offset = (int32_t)utext_getNativeIndex(fText);
// if we have cached break positions and offset is in the range
// covered by them, use them
@ -826,7 +813,7 @@ int32_t RuleBasedBreakIterator::preceding(int32_t offset) {
// Move requested offset to a code point start. It might be on a trail surrogate,
// or on a trail byte if the input is UTF-8.
utext_setNativeIndex(fText, offset);
offset = utext_getNativeIndex(fText);
offset = (int32_t)utext_getNativeIndex(fText);
// if we have cached break positions and offset is in the range
// covered by them, use them
@ -983,6 +970,54 @@ enum RBBIRunMode {
};
// Map from look-ahead break states (corresponds to rules) to boundary positions.
// Allows multiple lookahead break rules to be in flight at the same time.
//
// This is a temporary approach for ICU 57. A better fix is to make the look-ahead numbers
// in the state table be sequential, then we can just index an array. And the
// table could also tell us in advance how big that array needs to be.
//
// Before ICU 57 there was just a single simple variable for a look-ahead match that
// was in progress. Two rules at once did not work.
static const int32_t kMaxLookaheads = 8;
struct LookAheadResults {
int32_t fUsedSlotLimit;
int32_t fPositions[8];
int16_t fKeys[8];
LookAheadResults() : fUsedSlotLimit(0), fPositions(), fKeys() {};
int32_t getPosition(int16_t key) {
for (int32_t i=0; i<fUsedSlotLimit; ++i) {
if (fKeys[i] == key) {
return fPositions[i];
}
}
U_ASSERT(FALSE);
return -1;
}
void setPosition(int16_t key, int32_t position) {
int32_t i;
for (i=0; i<fUsedSlotLimit; ++i) {
if (fKeys[i] == key) {
fPositions[i] = position;
return;
}
}
if (i >= kMaxLookaheads) {
U_ASSERT(FALSE);
i = kMaxLookaheads - 1;
}
fKeys[i] = key;
fPositions[i] = position;
U_ASSERT(fUsedSlotLimit == i);
fUsedSlotLimit = i + 1;
}
};
//-----------------------------------------------------------------------------------
//
// handleNext(stateTable)
@ -1000,14 +1035,11 @@ int32_t RuleBasedBreakIterator::handleNext(const RBBIStateTable *statetable) {
RBBIStateTableRow *row;
UChar32 c;
int32_t lookaheadStatus = 0;
int32_t lookaheadTagIdx = 0;
int32_t result = 0;
int32_t initialPosition = 0;
int32_t lookaheadResult = 0;
UBool lookAheadHardBreak = (statetable->fFlags & RBBI_LOOKAHEAD_HARD_BREAK) != 0;
const char *tableData = statetable->fTableData;
uint32_t tableRowLen = statetable->fRowLen;
LookAheadResults lookAheadMatches;
int32_t result = 0;
int32_t initialPosition = 0;
const char *tableData = statetable->fTableData;
uint32_t tableRowLen = statetable->fRowLen;
#ifdef RBBI_DEBUG
if (fTrace) {
@ -1050,14 +1082,6 @@ int32_t RuleBasedBreakIterator::handleNext(const RBBIStateTable *statetable) {
// We have already run the loop one last time with the
// character set to the psueudo {eof} value. Now it is time
// to unconditionally bail out.
if (lookaheadResult > result) {
// We ran off the end of the string with a pending look-ahead match.
// Treat this as if the look-ahead condition had been met, and return
// the match at the / position from the look-ahead rule.
result = lookaheadResult;
fLastRuleStatusIndex = lookaheadTagIdx;
lookaheadStatus = 0;
}
break;
}
// Run the loop one last time with the fake end-of-input character category.
@ -1123,38 +1147,23 @@ int32_t RuleBasedBreakIterator::handleNext(const RBBIStateTable *statetable) {
fLastRuleStatusIndex = row->fTagIdx; // Remember the break status (tag) values.
}
if (row->fLookAhead != 0) {
if (lookaheadStatus != 0
&& row->fAccepting == lookaheadStatus) {
// Lookahead match is completed.
result = lookaheadResult;
fLastRuleStatusIndex = lookaheadTagIdx;
lookaheadStatus = 0;
// TODO: make a standalone hard break in a rule work.
if (lookAheadHardBreak) {
UTEXT_SETNATIVEINDEX(fText, result);
return result;
}
// Look-ahead completed, but other rules may match further. Continue on
// TODO: junk this feature? I don't think it's used anywhwere.
goto continueOn;
int16_t completedRule = row->fAccepting;
if (completedRule > 0) {
// Lookahead match is completed.
int32_t lookaheadResult = lookAheadMatches.getPosition(completedRule);
if (lookaheadResult >= 0) {
fLastRuleStatusIndex = row->fTagIdx;
UTEXT_SETNATIVEINDEX(fText, lookaheadResult);
return lookaheadResult;
}
int32_t r = (int32_t)UTEXT_GETNATIVEINDEX(fText);
lookaheadResult = r;
lookaheadStatus = row->fLookAhead;
lookaheadTagIdx = row->fTagIdx;
goto continueOn;
}
int16_t rule = row->fLookAhead;
if (rule != 0) {
// At the position of a '/' in a look-ahead match. Record it.
int32_t pos = (int32_t)UTEXT_GETNATIVEINDEX(fText);
lookAheadMatches.setPosition(rule, pos);
}
if (row->fAccepting != 0) {
// Because this is an accepting state, any in-progress look-ahead match
// is no longer relavant. Clear out the pending lookahead status.
lookaheadStatus = 0; // clear out any pending look-ahead match.
}
continueOn:
if (state == STOP_STATE) {
// This is the normal exit from the lookup state machine.
// We have advanced through the string until it is certain that no
@ -1216,11 +1225,9 @@ int32_t RuleBasedBreakIterator::handlePrevious(const RBBIStateTable *statetable)
RBBIRunMode mode;
RBBIStateTableRow *row;
UChar32 c;
int32_t lookaheadStatus = 0;
LookAheadResults lookAheadMatches;
int32_t result = 0;
int32_t initialPosition = 0;
int32_t lookaheadResult = 0;
UBool lookAheadHardBreak = (statetable->fFlags & RBBI_LOOKAHEAD_HARD_BREAK) != 0;
#ifdef RBBI_DEBUG
if (fTrace) {
@ -1266,13 +1273,7 @@ int32_t RuleBasedBreakIterator::handlePrevious(const RBBIStateTable *statetable)
// We have already run the loop one last time with the
// character set to the psueudo {eof} value. Now it is time
// to unconditionally bail out.
if (lookaheadResult < result) {
// We ran off the end of the string with a pending look-ahead match.
// Treat this as if the look-ahead condition had been met, and return
// the match at the / position from the look-ahead rule.
result = lookaheadResult;
lookaheadStatus = 0;
} else if (result == initialPosition) {
if (result == initialPosition) {
// Ran off start, no match found.
// move one index one (towards the start, since we are doing a previous())
UTEXT_SETNATIVEINDEX(fText, initialPosition);
@ -1338,36 +1339,22 @@ int32_t RuleBasedBreakIterator::handlePrevious(const RBBIStateTable *statetable)
result = (int32_t)UTEXT_GETNATIVEINDEX(fText);
}
if (row->fLookAhead != 0) {
if (lookaheadStatus != 0
&& row->fAccepting == lookaheadStatus) {
// Lookahead match is completed.
result = lookaheadResult;
lookaheadStatus = 0;
// TODO: make a standalone hard break in a rule work.
if (lookAheadHardBreak) {
UTEXT_SETNATIVEINDEX(fText, result);
return result;
}
// Look-ahead completed, but other rules may match further. Continue on
// TODO: junk this feature? I don't think it's used anywhwere.
goto continueOn;
int16_t completedRule = row->fAccepting;
if (completedRule > 0) {
// Lookahead match is completed.
int32_t lookaheadResult = lookAheadMatches.getPosition(completedRule);
if (lookaheadResult >= 0) {
UTEXT_SETNATIVEINDEX(fText, lookaheadResult);
return lookaheadResult;
}
int32_t r = (int32_t)UTEXT_GETNATIVEINDEX(fText);
lookaheadResult = r;
lookaheadStatus = row->fLookAhead;
goto continueOn;
}
int16_t rule = row->fLookAhead;
if (rule != 0) {
// At the position of a '/' in a look-ahead match. Record it.
int32_t pos = (int32_t)UTEXT_GETNATIVEINDEX(fText);
lookAheadMatches.setPosition(rule, pos);
}
if (row->fAccepting != 0) {
// Because this is an accepting state, any in-progress look-ahead match
// is no longer relavant. Clear out the pending lookahead status.
lookaheadStatus = 0;
}
continueOn:
if (state == STOP_STATE) {
// This is the normal exit from the lookup state machine.
// We have advanced through the string until it is certain that no

10
intl/icu/source/common/rbbicst.pl
View File

@ -1,6 +1,10 @@
#**************************************************************************
# Copyright (C) 2002-2005 International Business Machines Corporation *
# and others. All rights reserved. *
# Copyright (C) 2016 and later: Unicode, Inc. and others.
# License & terms of use: http://www.unicode.org/copyright.html#License
#**************************************************************************
#**************************************************************************
# Copyright (C) 2002-2016 International Business Machines Corporation
# and others. All rights reserved.
#**************************************************************************
#
# rbbicst Compile the RBBI rule paser state table data into initialized C data.
@ -348,6 +352,8 @@ else
print "#ifndef RBBIRPT_H\n";
print "#define RBBIRPT_H\n";
print "\n";
print "#include \"unicode/utypes.h\"\n";
print "\n";
print "U_NAMESPACE_BEGIN\n";
#

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

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
***************************************************************************
* Copyright (C) 1999-2014 International Business Machines Corporation *

2
intl/icu/source/common/rbbidata.h
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*

78
intl/icu/source/common/rbbinode.cpp
View File

@ -1,6 +1,8 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
***************************************************************************
* Copyright (C) 2002-2008 International Business Machines Corporation *
* Copyright (C) 2002-2016 International Business Machines Corporation *
* and others. All rights reserved. *
***************************************************************************
*/
@ -23,6 +25,8 @@
#include "unicode/uniset.h"
#include "unicode/uchar.h"
#include "unicode/parsepos.h"
#include "cstr.h"
#include "uvector.h"
#include "rbbirb.h"
@ -56,6 +60,8 @@ RBBINode::RBBINode(NodeType t) : UMemory() {
fLastPos = 0;
fNullable = FALSE;
fLookAheadEnd = FALSE;
fRuleRoot = FALSE;
fChainIn = FALSE;
fVal = 0;
fPrecedence = precZero;
@ -86,6 +92,8 @@ RBBINode::RBBINode(const RBBINode &other) : UMemory(other) {
fLastPos = other.fLastPos;
fNullable = other.fNullable;
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);
@ -186,8 +194,12 @@ RBBINode *RBBINode::cloneTree() {
//-------------------------------------------------------------------------
RBBINode *RBBINode::flattenVariables() {
if (fType == varRef) {
RBBINode *retNode = fLeftChild->cloneTree();
delete this;
RBBINode *retNode = fLeftChild->cloneTree();
if (retNode != NULL) {
retNode->fRuleRoot = this->fRuleRoot;
retNode->fChainIn = this->fChainIn;
}
delete this; // TODO: undefined behavior. Fix.
return retNode;
}
@ -272,7 +284,13 @@ void RBBINode::findNodes(UVector *dest, RBBINode::NodeType kind, UErrorCode &s
//
//-------------------------------------------------------------------------
#ifdef RBBI_DEBUG
void RBBINode::printNode() {
static int32_t serial(const RBBINode *node) {
return (node == NULL? -1 : node->fSerialNum);
}
void RBBINode::printNode(const RBBINode *node) {
static const char * const nodeTypeNames[] = {
"setRef",
"uset",
@ -292,14 +310,16 @@ void RBBINode::printNode() {
"opLParen"
};
if (this==NULL) {
RBBIDebugPrintf("%10p", (void *)this);
if (node==NULL) {
RBBIDebugPrintf("%10p", (void *)node);
} else {
RBBIDebugPrintf("%10p %12s %10p %10p %10p %4d %6d %d ",
(void *)this, nodeTypeNames[fType], (void *)fParent, (void *)fLeftChild, (void *)fRightChild,
fSerialNum, fFirstPos, fVal);
if (fType == varRef) {
RBBI_DEBUG_printUnicodeString(fText);
RBBIDebugPrintf("%10p %5d %12s %c%c %5d %5d %5d %6d %d ",
(void *)node, node->fSerialNum, nodeTypeNames[node->fType],
node->fRuleRoot?'R':' ', node->fChainIn?'C':' ',
serial(node->fLeftChild), serial(node->fRightChild), serial(node->fParent),
node->fFirstPos, node->fVal);
if (node->fType == varRef) {
RBBI_DEBUG_printUnicodeString(node->fText);
}
}
RBBIDebugPrintf("\n");
@ -308,16 +328,8 @@ void RBBINode::printNode() {
#ifdef RBBI_DEBUG
U_CFUNC void RBBI_DEBUG_printUnicodeString(const UnicodeString &s, int minWidth)
{
int i;
for (i=0; i<s.length(); i++) {
RBBIDebugPrintf("%c", s.charAt(i));
// putc(s.charAt(i), stdout);
}
for (i=s.length(); i<minWidth; i++) {
RBBIDebugPrintf(" ");
}
U_CFUNC void RBBI_DEBUG_printUnicodeString(const UnicodeString &s, int minWidth) {
RBBIDebugPrintf("%*s", minWidth, CStr(s)());
}
#endif
@ -328,23 +340,25 @@ U_CFUNC void RBBI_DEBUG_printUnicodeString(const UnicodeString &s, int minWidth)
//
//-------------------------------------------------------------------------
#ifdef RBBI_DEBUG
void RBBINode::printTree(UBool printHeading) {
void RBBINode::printNodeHeader() {
RBBIDebugPrintf(" Address serial type LeftChild RightChild Parent position value\n");
}
void RBBINode::printTree(const RBBINode *node, UBool printHeading) {
if (printHeading) {
RBBIDebugPrintf( "-------------------------------------------------------------------\n"
" Address type Parent LeftChild RightChild serial position value\n"
);
printNodeHeader();
}
this->printNode();
if (this != NULL) {
printNode(node);
if (node != NULL) {
// Only dump the definition under a variable reference if asked to.
// Unconditinally dump children of all other node types.
if (fType != varRef) {
if (fLeftChild != NULL) {
fLeftChild->printTree(FALSE);
if (node->fType != varRef) {
if (node->fLeftChild != NULL) {
printTree(node->fLeftChild, FALSE);
}
if (fRightChild != NULL) {
fRightChild->printTree(FALSE);
if (node->fRightChild != NULL) {
printTree(node->fRightChild, FALSE);
}
}
}

15
intl/icu/source/common/rbbinode.h
View File

@ -1,6 +1,8 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/********************************************************************
* COPYRIGHT:
* Copyright (c) 2001-2006, International Business Machines Corporation and
* Copyright (c) 2001-2016, International Business Machines Corporation and
* others. All Rights Reserved.
********************************************************************/
@ -8,6 +10,7 @@
#define RBBINODE_H
#include "unicode/utypes.h"
#include "unicode/unistr.h"
#include "unicode/uobject.h"
//
@ -79,6 +82,10 @@ class RBBINode : public UMemory {
UBool fLookAheadEnd; // For endMark nodes, set TRUE if
// marking the end of a look-ahead rule.
UBool fRuleRoot; // True if this node is the root of a rule.
UBool fChainIn; // True if chaining into this rule is allowed
// (no '^' present).
UVector *fFirstPosSet;
UVector *fLastPosSet; // TODO: rename fFirstPos & fLastPos to avoid confusion.
UVector *fFollowPos;
@ -94,8 +101,9 @@ class RBBINode : public UMemory {
void findNodes(UVector *dest, RBBINode::NodeType kind, UErrorCode &status);
#ifdef RBBI_DEBUG
void printNode();
void printTree(UBool withHeading);
static void printNodeHeader();
static void printNode(const RBBINode *n);
static void printTree(const RBBINode *n, UBool withHeading);
#endif
private:
@ -103,6 +111,7 @@ class RBBINode : public UMemory {
UBool operator == (const RBBINode &other); // Private, so these functions won't accidently be used.
#ifdef RBBI_DEBUG
public:
int fSerialNum; // Debugging aids.
#endif
};

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

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
//
// file: rbbirb.cpp
//

2
intl/icu/source/common/rbbirb.h
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
//
// rbbirb.h
//

211
intl/icu/source/common/rbbirpt.h
View File

@ -1,3 +1,5 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
//---------------------------------------------------------------------------------
//
// Generated Header File. Do not edit by hand.
@ -6,13 +8,15 @@
// It is generated by the Perl script "rbbicst.pl" from
// the rule parser state definitions file "rbbirpt.txt".
//
// Copyright (C) 2002-2005 International Business Machines Corporation
// Copyright (C) 2002-2016 International Business Machines Corporation
// and others. All rights reserved.
//
//---------------------------------------------------------------------------------
#ifndef RBBIRPT_H
#define RBBIRPT_H
#include "unicode/utypes.h"
U_NAMESPACE_BEGIN
//
// Character classes for RBBI rule scanning.
@ -38,6 +42,7 @@ enum RBBI_RuleParseAction {
doExprStart,
doLParen,
doNOP,
doNoChain,
doOptionEnd,
doOptionStart,
doReverseDir,
@ -75,101 +80,109 @@ struct RBBIRuleTableEl {
static const struct RBBIRuleTableEl gRuleParseStateTable[] = {
{doNOP, 0, 0, 0, TRUE}
, {doExprStart, 254, 21, 8, FALSE} // 1 start
, {doExprStart, 254, 29, 9, FALSE} // 1 start
, {doNOP, 132, 1,0, TRUE} // 2
, {doExprStart, 36 /* $ */, 80, 90, FALSE} // 3
, {doNOP, 33 /* ! */, 11,0, TRUE} // 4
, {doNOP, 59 /* ; */, 1,0, TRUE} // 5
, {doNOP, 252, 0,0, FALSE} // 6
, {doExprStart, 255, 21, 8, FALSE} // 7
, {doEndOfRule, 59 /* ; */, 1,0, TRUE} // 8 break-rule-end
, {doNOP, 132, 8,0, TRUE} // 9
, {doRuleError, 255, 95,0, FALSE} // 10
, {doNOP, 33 /* ! */, 13,0, TRUE} // 11 rev-option
, {doReverseDir, 255, 20, 8, FALSE} // 12
, {doOptionStart, 130, 15,0, TRUE} // 13 option-scan1
, {doRuleError, 255, 95,0, FALSE} // 14
, {doNOP, 129, 15,0, TRUE} // 15 option-scan2
, {doOptionEnd, 255, 17,0, FALSE} // 16
, {doNOP, 59 /* ; */, 1,0, TRUE} // 17 option-scan3
, {doNOP, 132, 17,0, TRUE} // 18
, {doRuleError, 255, 95,0, FALSE} // 19
, {doExprStart, 255, 21, 8, FALSE} // 20 reverse-rule
, {doRuleChar, 254, 30,0, TRUE} // 21 term
, {doNOP, 132, 21,0, TRUE} // 22
, {doRuleChar, 131, 30,0, TRUE} // 23
, {doNOP, 91 /* [ */, 86, 30, FALSE} // 24
, {doLParen, 40 /* ( */, 21, 30, TRUE} // 25
, {doNOP, 36 /* $ */, 80, 29, FALSE} // 26
, {doDotAny, 46 /* . */, 30,0, TRUE} // 27
, {doRuleError, 255, 95,0, FALSE} // 28
, {doCheckVarDef, 255, 30,0, FALSE} // 29 term-var-ref
, {doNOP, 132, 30,0, TRUE} // 30 expr-mod
, {doUnaryOpStar, 42 /* * */, 35,0, TRUE} // 31
, {doUnaryOpPlus, 43 /* + */, 35,0, TRUE} // 32
, {doUnaryOpQuestion, 63 /* ? */, 35,0, TRUE} // 33
, {doNOP, 255, 35,0, FALSE} // 34
, {doExprCatOperator, 254, 21,0, FALSE} // 35 expr-cont
, {doNOP, 132, 35,0, TRUE} // 36
, {doExprCatOperator, 131, 21,0, FALSE} // 37
, {doExprCatOperator, 91 /* [ */, 21,0, FALSE} // 38
, {doExprCatOperator, 40 /* ( */, 21,0, FALSE} // 39
, {doExprCatOperator, 36 /* $ */, 21,0, FALSE} // 40
, {doExprCatOperator, 46 /* . */, 21,0, FALSE} // 41
, {doExprCatOperator, 47 /* / */, 47,0, FALSE} // 42
, {doExprCatOperator, 123 /* { */, 59,0, TRUE} // 43
, {doExprOrOperator, 124 /* | */, 21,0, TRUE} // 44
, {doExprRParen, 41 /* ) */, 255,0, TRUE} // 45
, {doExprFinished, 255, 255,0, FALSE} // 46
, {doSlash, 47 /* / */, 49,0, TRUE} // 47 look-ahead
, {doNOP, 255, 95,0, FALSE} // 48
, {doExprCatOperator, 254, 21,0, FALSE} // 49 expr-cont-no-slash
, {doNOP, 132, 35,0, TRUE} // 50
, {doExprCatOperator, 131, 21,0, FALSE} // 51
, {doExprCatOperator, 91 /* [ */, 21,0, FALSE} // 52
, {doExprCatOperator, 40 /* ( */, 21,0, FALSE} // 53
, {doExprCatOperator, 36 /* $ */, 21,0, FALSE} // 54
, {doExprCatOperator, 46 /* . */, 21,0, FALSE} // 55
, {doExprOrOperator, 124 /* | */, 21,0, TRUE} // 56
, {doExprRParen, 41 /* ) */, 255,0, TRUE} // 57
, {doExprFinished, 255, 255,0, FALSE} // 58
, {doNOP, 132, 59,0, TRUE} // 59 tag-open
, {doStartTagValue, 128, 62,0, FALSE} // 60
, {doTagExpectedError, 255, 95,0, FALSE} // 61
, {doNOP, 132, 66,0, TRUE} // 62 tag-value
, {doNOP, 125 /* } */, 66,0, FALSE} // 63
, {doTagDigit, 128, 62,0, TRUE} // 64
, {doTagExpectedError, 255, 95,0, FALSE} // 65
, {doNOP, 132, 66,0, TRUE} // 66 tag-close
, {doTagValue, 125 /* } */, 69,0, TRUE} // 67
, {doTagExpectedError, 255, 95,0, FALSE} // 68
, {doExprCatOperator, 254, 21,0, FALSE} // 69 expr-cont-no-tag
, {doNOP, 132, 69,0, TRUE} // 70
, {doExprCatOperator, 131, 21,0, FALSE} // 71
, {doExprCatOperator, 91 /* [ */, 21,0, FALSE} // 72
, {doExprCatOperator, 40 /* ( */, 21,0, FALSE} // 73
, {doExprCatOperator, 36 /* $ */, 21,0, FALSE} // 74
, {doExprCatOperator, 46 /* . */, 21,0, FALSE} // 75
, {doExprCatOperator, 47 /* / */, 47,0, FALSE} // 76
, {doExprOrOperator, 124 /* | */, 21,0, TRUE} // 77
, {doExprRParen, 41 /* ) */, 255,0, TRUE} // 78
, {doExprFinished, 255, 255,0, FALSE} // 79
, {doStartVariableName, 36 /* $ */, 82,0, TRUE} // 80 scan-var-name
, {doNOP, 255, 95,0, FALSE} // 81
, {doNOP, 130, 84,0, TRUE} // 82 scan-var-start
, {doVariableNameExpectedErr, 255, 95,0, FALSE} // 83
, {doNOP, 129, 84,0, TRUE} // 84 scan-var-body
, {doEndVariableName, 255, 255,0, FALSE} // 85
, {doScanUnicodeSet, 91 /* [ */, 255,0, TRUE} // 86 scan-unicode-set
, {doScanUnicodeSet, 112 /* p */, 255,0, TRUE} // 87
, {doScanUnicodeSet, 80 /* P */, 255,0, TRUE} // 88
, {doNOP, 255, 95,0, FALSE} // 89
, {doNOP, 132, 90,0, TRUE} // 90 assign-or-rule
, {doStartAssign, 61 /* = */, 21, 93, TRUE} // 91
, {doNOP, 255, 29, 8, FALSE} // 92
, {doEndAssign, 59 /* ; */, 1,0, TRUE} // 93 assign-end
, {doRuleErrorAssignExpr, 255, 95,0, FALSE} // 94
, {doExit, 255, 95,0, TRUE} // 95 errorDeath
, {doNoChain, 94 /* ^ */, 12, 9, TRUE} // 3
, {doExprStart, 36 /* $ */, 88, 98, FALSE} // 4
, {doNOP, 33 /* ! */, 19,0, TRUE} // 5
, {doNOP, 59 /* ; */, 1,0, TRUE} // 6
, {doNOP, 252, 0,0, FALSE} // 7
, {doExprStart, 255, 29, 9, FALSE} // 8
, {doEndOfRule, 59 /* ; */, 1,0, TRUE} // 9 break-rule-end
, {doNOP, 132, 9,0, TRUE} // 10
, {doRuleError, 255, 103,0, FALSE} // 11
, {doExprStart, 254, 29,0, FALSE} // 12 start-after-caret
, {doNOP, 132, 12,0, TRUE} // 13
, {doRuleError, 94 /* ^ */, 103,0, FALSE} // 14
, {doExprStart, 36 /* $ */, 88, 37, FALSE} // 15
, {doRuleError, 59 /* ; */, 103,0, FALSE} // 16
, {doRuleError, 252, 103,0, FALSE} // 17
, {doExprStart, 255, 29,0, FALSE} // 18
, {doNOP, 33 /* ! */, 21,0, TRUE} // 19 rev-option
, {doReverseDir, 255, 28, 9, FALSE} // 20
, {doOptionStart, 130, 23,0, TRUE} // 21 option-scan1
, {doRuleError, 255, 103,0, FALSE} // 22
, {doNOP, 129, 23,0, TRUE} // 23 option-scan2
, {doOptionEnd, 255, 25,0, FALSE} // 24
, {doNOP, 59 /* ; */, 1,0, TRUE} // 25 option-scan3
, {doNOP, 132, 25,0, TRUE} // 26
, {doRuleError, 255, 103,0, FALSE} // 27
, {doExprStart, 255, 29, 9, FALSE} // 28 reverse-rule
, {doRuleChar, 254, 38,0, TRUE} // 29 term
, {doNOP, 132, 29,0, TRUE} // 30
, {doRuleChar, 131, 38,0, TRUE} // 31
, {doNOP, 91 /* [ */, 94, 38, FALSE} // 32
, {doLParen, 40 /* ( */, 29, 38, TRUE} // 33
, {doNOP, 36 /* $ */, 88, 37, FALSE} // 34
, {doDotAny, 46 /* . */, 38,0, TRUE} // 35
, {doRuleError, 255, 103,0, FALSE} // 36
, {doCheckVarDef, 255, 38,0, FALSE} // 37 term-var-ref
, {doNOP, 132, 38,0, TRUE} // 38 expr-mod
, {doUnaryOpStar, 42 /* * */, 43,0, TRUE} // 39
, {doUnaryOpPlus, 43 /* + */, 43,0, TRUE} // 40
, {doUnaryOpQuestion, 63 /* ? */, 43,0, TRUE} // 41
, {doNOP, 255, 43,0, FALSE} // 42
, {doExprCatOperator, 254, 29,0, FALSE} // 43 expr-cont
, {doNOP, 132, 43,0, TRUE} // 44
, {doExprCatOperator, 131, 29,0, FALSE} // 45
, {doExprCatOperator, 91 /* [ */, 29,0, FALSE} // 46
, {doExprCatOperator, 40 /* ( */, 29,0, FALSE} // 47
, {doExprCatOperator, 36 /* $ */, 29,0, FALSE} // 48
, {doExprCatOperator, 46 /* . */, 29,0, FALSE} // 49
, {doExprCatOperator, 47 /* / */, 55,0, FALSE} // 50
, {doExprCatOperator, 123 /* { */, 67,0, TRUE} // 51
, {doExprOrOperator, 124 /* | */, 29,0, TRUE} // 52
, {doExprRParen, 41 /* ) */, 255,0, TRUE} // 53
, {doExprFinished, 255, 255,0, FALSE} // 54
, {doSlash, 47 /* / */, 57,0, TRUE} // 55 look-ahead
, {doNOP, 255, 103,0, FALSE} // 56
, {doExprCatOperator, 254, 29,0, FALSE} // 57 expr-cont-no-slash
, {doNOP, 132, 43,0, TRUE} // 58
, {doExprCatOperator, 131, 29,0, FALSE} // 59
, {doExprCatOperator, 91 /* [ */, 29,0, FALSE} // 60
, {doExprCatOperator, 40 /* ( */, 29,0, FALSE} // 61
, {doExprCatOperator, 36 /* $ */, 29,0, FALSE} // 62
, {doExprCatOperator, 46 /* . */, 29,0, FALSE} // 63
, {doExprOrOperator, 124 /* | */, 29,0, TRUE} // 64
, {doExprRParen, 41 /* ) */, 255,0, TRUE} // 65
, {doExprFinished, 255, 255,0, FALSE} // 66
, {doNOP, 132, 67,0, TRUE} // 67 tag-open
, {doStartTagValue, 128, 70,0, FALSE} // 68
, {doTagExpectedError, 255, 103,0, FALSE} // 69
, {doNOP, 132, 74,0, TRUE} // 70 tag-value
, {doNOP, 125 /* } */, 74,0, FALSE} // 71
, {doTagDigit, 128, 70,0, TRUE} // 72
, {doTagExpectedError, 255, 103,0, FALSE} // 73
, {doNOP, 132, 74,0, TRUE} // 74 tag-close
, {doTagValue, 125 /* } */, 77,0, TRUE} // 75
, {doTagExpectedError, 255, 103,0, FALSE} // 76
, {doExprCatOperator, 254, 29,0, FALSE} // 77 expr-cont-no-tag
, {doNOP, 132, 77,0, TRUE} // 78
, {doExprCatOperator, 131, 29,0, FALSE} // 79
, {doExprCatOperator, 91 /* [ */, 29,0, FALSE} // 80
, {doExprCatOperator, 40 /* ( */, 29,0, FALSE} // 81
, {doExprCatOperator, 36 /* $ */, 29,0, FALSE} // 82
, {doExprCatOperator, 46 /* . */, 29,0, FALSE} // 83
, {doExprCatOperator, 47 /* / */, 55,0, FALSE} // 84
, {doExprOrOperator, 124 /* | */, 29,0, TRUE} // 85
, {doExprRParen, 41 /* ) */, 255,0, TRUE} // 86
, {doExprFinished, 255, 255,0, FALSE} // 87
, {doStartVariableName, 36 /* $ */, 90,0, TRUE} // 88 scan-var-name
, {doNOP, 255, 103,0, FALSE} // 89
, {doNOP, 130, 92,0, TRUE} // 90 scan-var-start
, {doVariableNameExpectedErr, 255, 103,0, FALSE} // 91
, {doNOP, 129, 92,0, TRUE} // 92 scan-var-body
, {doEndVariableName, 255, 255,0, FALSE} // 93
, {doScanUnicodeSet, 91 /* [ */, 255,0, TRUE} // 94 scan-unicode-set
, {doScanUnicodeSet, 112 /* p */, 255,0, TRUE} // 95
, {doScanUnicodeSet, 80 /* P */, 255,0, TRUE} // 96
, {doNOP, 255, 103,0, FALSE} // 97
, {doNOP, 132, 98,0, TRUE} // 98 assign-or-rule
, {doStartAssign, 61 /* = */, 29, 101, TRUE} // 99
, {doNOP, 255, 37, 9, FALSE} // 100
, {doEndAssign, 59 /* ; */, 1,0, TRUE} // 101 assign-end
, {doRuleErrorAssignExpr, 255, 103,0, FALSE} // 102
, {doExit, 255, 103,0, TRUE} // 103 errorDeath
};
#ifdef RBBI_DEBUG
static const char * const RBBIRuleStateNames[] = { 0,
@ -179,9 +192,17 @@ static const char * const RBBIRuleStateNames[] = { 0,
0,
0,
0,
0,
0,
"break-rule-end",
0,
0,
"start-after-caret",
0,
0,
0,
0,
0,
0,
"rev-option",
0,

26
intl/icu/source/common/rbbirpt.txt
View File

@ -1,7 +1,13 @@
#*****************************************************************************
#
# Copyright (C) 2002-2003, International Business Machines Corporation and others.
# Copyright (C) 2016 and later: Unicode, Inc. and others.
# License & terms of use: http://www.unicode.org/copyright.html#License
#
#*****************************************************************************
#*****************************************************************************
#
# Copyright (C) 2002-2016, International Business Machines Corporation and others.
# All Rights Reserved.
#
#*****************************************************************************
@ -19,6 +25,7 @@
# This file is processed by a perl script "rbbicst.pl" to produce initialized C arrays
# that are then built with the rule parser.
#
# perl rbbicst.pl < rbbirpt.txt > rbbirpt.h
#
# Here is the syntax of the state definitions in this file:
@ -57,6 +64,7 @@
start:
escaped term ^break-rule-end doExprStart
white_space n start
'^' n start-after-caret ^break-rule-end doNoChain
'$' scan-var-name ^assign-or-rule doExprStart
'!' n rev-option
';' n start # ignore empty rules.
@ -71,7 +79,21 @@ break-rule-end:
white_space n break-rule-end
default errorDeath doRuleError
#
# start of a rule, after having seen a '^' (inhibits rule chain in).
# Similar to the main 'start' state in most respects, except
# - empty rule is an error.
# - A second '^' is an error.
#
start-after-caret:
escaped term doExprStart
white_space n start-after-caret
'^' errorDeath doRuleError # two '^'s
'$' scan-var-name ^term-var-ref doExprStart
';' errorDeath doRuleError # ^ ;
eof errorDeath doRuleError
default term doExprStart
#
# ! We've just scanned a '!', indicating either a !!key word flag or a
# !Reverse rule.

82
intl/icu/source/common/rbbiscan.cpp
View File

@ -1,7 +1,9 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
//
// file: rbbiscan.cpp
//
// Copyright (C) 2002-2015, International Business Machines Corporation and others.
// Copyright (C) 2002-2016, International Business Machines Corporation and others.
// All Rights Reserved.
//
// This file contains the Rule Based Break Iterator Rule Builder functions for
@ -87,24 +89,27 @@ U_NAMESPACE_BEGIN
RBBIRuleScanner::RBBIRuleScanner(RBBIRuleBuilder *rb)
{
fRB = rb;
fScanIndex = 0;
fNextIndex = 0;
fQuoteMode = FALSE;
fLineNum = 1;
fCharNum = 0;
fLastChar = 0;
fStateTable = NULL;
fStack[0] = 0;
fStackPtr = 0;
fStack[fStackPtr] = 0;
fNodeStackPtr = 0;
fRuleNum = 0;
fNodeStack[0] = NULL;
fSymbolTable = NULL;
fSetTable = NULL;
fScanIndex = 0;
fNextIndex = 0;
fNodeStackPtr = 0;
fReverseRule = FALSE;
fLookAheadRule = FALSE;
fNoChainInRule = FALSE;
fLineNum = 1;
fCharNum = 0;
fQuoteMode = FALSE;
fSymbolTable = NULL;
fSetTable = NULL;
fRuleNum = 0;
fOptionStart = 0;
// Do not check status until after all critical fields are sufficiently initialized
// that the destructor can run cleanly.
@ -205,6 +210,12 @@ UBool RBBIRuleScanner::doParseActions(int32_t action)
break;
case doNoChain:
// Scanned a '^' while on the rule start state.
fNoChainInRule = TRUE;
break;
case doExprOrOperator:
{
fixOpStack(RBBINode::precOpCat);
@ -318,11 +329,11 @@ UBool RBBIRuleScanner::doParseActions(int32_t action)
if (fRB->fDebugEnv && uprv_strstr(fRB->fDebugEnv, "rtree")) {printNodeStack("end of rule");}
#endif
U_ASSERT(fNodeStackPtr == 1);
RBBINode *thisRule = fNodeStack[fNodeStackPtr];
// If this rule includes a look-ahead '/', add a endMark node to the
// expression tree.
if (fLookAheadRule) {
RBBINode *thisRule = fNodeStack[fNodeStackPtr];
RBBINode *endNode = pushNewNode(RBBINode::endMark);
RBBINode *catNode = pushNewNode(RBBINode::opCat);
if (U_FAILURE(*fRB->fStatus)) {
@ -334,8 +345,24 @@ UBool RBBIRuleScanner::doParseActions(int32_t action)
fNodeStack[fNodeStackPtr] = catNode;
endNode->fVal = fRuleNum;
endNode->fLookAheadEnd = TRUE;
thisRule = catNode;
// TODO: Disable chaining out of look-ahead (hard break) rules.
// The break on rule match is forced, so there is no point in building up
// the state table to chain into another rule for a longer match.
}
// Mark this node as being the root of a rule.
thisRule->fRuleRoot = TRUE;
// Flag if chaining into this rule is wanted.
//
if (fRB->fChainRules && // If rule chaining is enabled globally via !!chain
!fNoChainInRule) { // and no '^' chain-in inhibit was on this rule
thisRule->fChainIn = TRUE;
}
// All rule expressions are ORed together.
// The ';' that terminates an expression really just functions as a '|' with
// a low operator prededence.
@ -372,6 +399,7 @@ UBool RBBIRuleScanner::doParseActions(int32_t action)
}
fReverseRule = FALSE; // in preparation for the next rule.
fLookAheadRule = FALSE;
fNoChainInRule = FALSE;
fNodeStackPtr = 0;
}
break;
@ -994,7 +1022,7 @@ void RBBIRuleScanner::parse() {
for (;;) {
#ifdef RBBI_DEBUG
if (fRB->fDebugEnv && uprv_strstr(fRB->fDebugEnv, "scan")) { RBBIDebugPrintf(".");}
if (fRB->fDebugEnv && uprv_strstr(fRB->fDebugEnv, "scan")) { RBBIDebugPrintf("."); fflush(stdout);}
#endif
if (tableEl->fCharClass < 127 && fC.fEscaped == FALSE && tableEl->fCharClass == fC.fChar) {
// Table row specified an individual character, not a set, and
@ -1077,6 +1105,17 @@ void RBBIRuleScanner::parse() {
}
if (U_FAILURE(*fRB->fStatus)) {
return;
}
// If there are no forward rules set an error.
//
if (fRB->fForwardTree == NULL) {
error(U_BRK_RULE_SYNTAX);
return;
}
//
// If there were NO user specified reverse rules, set up the equivalent of ".*;"
//
@ -1100,16 +1139,15 @@ void RBBIRuleScanner::parse() {
//
#ifdef RBBI_DEBUG
if (fRB->fDebugEnv && uprv_strstr(fRB->fDebugEnv, "symbols")) {fSymbolTable->rbbiSymtablePrint();}
if (fRB->fDebugEnv && uprv_strstr(fRB->fDebugEnv, "ptree"))
{
if (fRB->fDebugEnv && uprv_strstr(fRB->fDebugEnv, "ptree")) {
RBBIDebugPrintf("Completed Forward Rules Parse Tree...\n");
fRB->fForwardTree->printTree(TRUE);
RBBINode::printTree(fRB->fForwardTree, TRUE);
RBBIDebugPrintf("\nCompleted Reverse Rules Parse Tree...\n");
fRB->fReverseTree->printTree(TRUE);
RBBINode::printTree(fRB->fReverseTree, TRUE);
RBBIDebugPrintf("\nCompleted Safe Point Forward Rules Parse Tree...\n");
fRB->fSafeFwdTree->printTree(TRUE);
RBBINode::printTree(fRB->fSafeFwdTree, TRUE);
RBBIDebugPrintf("\nCompleted Safe Point Reverse Rules Parse Tree...\n");
fRB->fSafeRevTree->printTree(TRUE);
RBBINode::printTree(fRB->fSafeRevTree, TRUE);
}
#endif
}
@ -1124,7 +1162,7 @@ void RBBIRuleScanner::parse() {
void RBBIRuleScanner::printNodeStack(const char *title) {
int i;
RBBIDebugPrintf("%s. Dumping node stack...\n", title);
for (i=fNodeStackPtr; i>0; i--) {fNodeStack[i]->printTree(TRUE);}
for (i=fNodeStackPtr; i>0; i--) {RBBINode::printTree(fNodeStack[i], TRUE);}
}
#endif

11
intl/icu/source/common/rbbiscan.h
View File

@ -1,7 +1,9 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
//
// rbbiscan.h
//
// Copyright (C) 2002-2008, International Business Machines Corporation and others.
// Copyright (C) 2002-2016, International Business Machines Corporation and others.
// All Rights Reserved.
//
// This file contains declarations for class RBBIRuleScanner
@ -21,9 +23,7 @@
#include "unicode/symtable.h"// For UnicodeSet parsing, is the interface that
// looks up references to $variables within a set.
#include "rbbinode.h"
//#include "rbbitblb.h"
#include "rbbirpt.h"
U_NAMESPACE_BEGIN
@ -54,6 +54,7 @@ public:
struct RBBIRuleChar {
UChar32 fChar;
UBool fEscaped;
RBBIRuleChar() : fChar(0), fEscaped(FALSE) {};
};
RBBIRuleScanner(RBBIRuleBuilder *rb);
@ -129,6 +130,8 @@ private:
UBool fLookAheadRule; // True if the rule includes a '/'
// somewhere within it.
UBool fNoChainInRule; // True if the current rule starts with a '^'.
RBBISymbolTable *fSymbolTable; // symbol table, holds definitions of
// $variable symbols.

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