From 424584b4984bde7c831f42e9fb47f1ad583a1c46 Mon Sep 17 00:00:00 2001 From: jshin Date: Fri, 21 Oct 2016 01:15:50 -0700 Subject: [PATCH] Update aspirational_scripts per Unicode 9 This is a preparation to update ICU to 58.1. Without this change, ICU update CL cannot be tested on trybots because a compile will fail due to '#error' checking if ICU version is less than 58. BUG=637001 TEST=None TBR=pkasting@chromium.org Review-Url: https://chromiumcodereview.appspot.com/2436113003 Cr-Commit-Position: refs/heads/master@{#426749} --- components/url_formatter/url_formatter.cc | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/components/url_formatter/url_formatter.cc b/components/url_formatter/url_formatter.cc index 4455db3..2b82c0c 100644 --- a/components/url_formatter/url_formatter.cc +++ b/components/url_formatter/url_formatter.cc @@ -428,9 +428,9 @@ void IDNSpoofChecker::SetAllowedUnicodeSet(UErrorCode* status) { // section at // http://www.unicode.org/Public/security/latest/xidmodifications.txt) are // are added to the allowed set. The list has to be updated when a new - // version of Unicode is released. The current version is 8.0.0 and ICU 58 - // will have Unicode 9.0 data. -#if U_ICU_VERSION_MAJOR_NUM < 58 + // version of Unicode is released. The current version is 9.0.0 and ICU 60 + // will have Unicode 10.0 data. +#if U_ICU_VERSION_MAJOR_NUM < 60 const icu::UnicodeSet aspirational_scripts( icu::UnicodeString( // Unified Canadian Syllabics @@ -444,13 +444,13 @@ void IDNSpoofChecker::SetAllowedUnicodeSet(UErrorCode* status) { // Yi "\\uA000-\\uA48C" // Miao - "\\U00016F00-\\U00016F44\\U00016F50-\\U00016F7F" + "\\U00016F00-\\U00016F44\\U00016F50-\\U00016F7E" "\\U00016F8F-\\U00016F9F]", -1, US_INV), *status); allowed_set.addAll(aspirational_scripts); #else -#error "Update aspirational_scripts per Unicode 9.0" +#error "Update aspirational_scripts per Unicode 10.0" #endif // U+0338 is included in the recommended set, while U+05F4 and U+2027 are in -- 2.10.2 From e60b571faa3f14dd9119a6792dccf12f8bf80192 Mon Sep 17 00:00:00 2001 From: jshin Date: Fri, 21 Oct 2016 12:20:05 -0700 Subject: [PATCH] Prepare to upgrade ICU to 58 part 2 U_LB_COUNT is assumed to be 40 in Blink line breaking code, but it's 43 in ICU 58/Unicode 9. Three new classes (Emoji Base, Emoji Modifier, and ZWJ) should behave identically whether or not 'word-break: break-all' is in effect. BUG=637001 TEST=TextBreakIterator.cpp is compiled without an error with ICU 58. R=kojii@chromium.org CQ_INCLUDE_TRYBOTS=master.tryserver.blink:linux_precise_blink_rel Review-Url: https://chromiumcodereview.appspot.com/2440923002 Cr-Commit-Position: refs/heads/master@{#426860} --- .../WebKit/Source/platform/text/TextBreakIterator.cpp | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/third_party/WebKit/Source/platform/text/TextBreakIterator.cpp b/third_party/WebKit/Source/platform/text/TextBreakIterator.cpp index 568dc0a..36121eb 100644 --- a/third_party/WebKit/Source/platform/text/TextBreakIterator.cpp +++ b/third_party/WebKit/Source/platform/text/TextBreakIterator.cpp @@ -28,6 +28,9 @@ #include "wtf/StdLibExtras.h" #include "wtf/text/CharacterNames.h" +#include +#include + namespace blink { unsigned numGraphemeClusters(const String& string) { @@ -129,6 +132,11 @@ static const unsigned char asciiLineBreakTable[][(asciiLineBreakTableLastChar - }; // clang-format on +#if U_ICU_VERSION_MAJOR_NUM >= 58 +#define BA_LB_COUNT (U_LB_COUNT - 3) +#else +#define BA_LB_COUNT U_LB_COUNT +#endif // Line breaking table for CSS word-break: break-all. This table differs from // asciiLineBreakTable in: // - Indices are Line Breaking Classes defined in UAX#14 Unicode Line Breaking @@ -136,7 +144,7 @@ static const unsigned char asciiLineBreakTable[][(asciiLineBreakTableLastChar - // - 1 indicates additional break opportunities. 0 indicates to fallback to // normal line break, not "prohibit break." // clang-format off -static const unsigned char breakAllLineBreakClassTable[][U_LB_COUNT / 8 + 1] = { +static const unsigned char breakAllLineBreakClassTable[][BA_LB_COUNT / 8 + 1] = { // XX AI AL B2 BA BB BK CB CL CM CR EX GL HY ID IN IS LF NS NU OP PO PR QU SA SG SP SY ZW NL WJ H2 H3 JL JT JV CP CJ HL RI { B(0, 0, 0, 0, 0, 0, 0, 0), B(0, 0, 0, 0, 0, 0, 0, 0), B(0, 0, 0, 0, 0, 0, 0, 0), B(0, 0, 0, 0, 0, 0, 0, 0), B(0, 0, 0, 0, 0, 0, 0, 0) }, // XX { B(0, 1, 1, 0, 1, 0, 0, 0), B(0, 0, 0, 0, 0, 1, 0, 0), B(0, 0, 0, 1, 1, 0, 1, 0), B(1, 0, 0, 0, 0, 0, 0, 0), B(0, 0, 0, 0, 0, 0, 1, 0) }, // AI @@ -190,7 +198,7 @@ static_assert(WTF_ARRAY_LENGTH(asciiLineBreakTable) == asciiLineBreakTableLastChar - asciiLineBreakTableFirstChar + 1, "asciiLineBreakTable should be consistent"); -static_assert(WTF_ARRAY_LENGTH(breakAllLineBreakClassTable) == U_LB_COUNT, +static_assert(WTF_ARRAY_LENGTH(breakAllLineBreakClassTable) == BA_LB_COUNT, "breakAllLineBreakClassTable should be consistent"); static inline bool shouldBreakAfter(UChar lastCh, UChar ch, UChar nextCh) { @@ -226,8 +234,8 @@ static inline ULineBreak lineBreakPropertyValue(UChar lastCh, UChar ch) { static inline bool shouldBreakAfterBreakAll(ULineBreak lastLineBreak, ULineBreak lineBreak) { - if (lineBreak >= 0 && lineBreak < U_LB_COUNT && lastLineBreak >= 0 && - lastLineBreak < U_LB_COUNT) { + if (lineBreak >= 0 && lineBreak < BA_LB_COUNT && lastLineBreak >= 0 && + lastLineBreak < BA_LB_COUNT) { const unsigned char* tableRow = breakAllLineBreakClassTable[lastLineBreak]; return tableRow[lineBreak / 8] & (1 << (lineBreak % 8)); } -- 2.10.2