Prepare to upgrade ICU to 58 part 2

third_party/WebKit/Source/platform/text/TextBreakIterator.cpp

 /*
  * (C) 1999 Lars Knoll (knoll@kde.org)
  * Copyright (C) 2004, 2005, 2006, 2007, 2008, 2010 Apple Inc. All rights
  * reserved.
  * Copyright (C) 2007-2009 Torch Mobile, Inc.
  * Copyright (C) 2011 Google Inc. All rights reserved.
  *
  * This library is free software; you can redistribute it and/or
  * modify it under the terms of the GNU Library General Public
  * License as published by the Free Software Foundation; either
@@ skipping 10 matching lines @@
  * Boston, MA 02110-1301, USA.
  */
 
 #include "platform/text/TextBreakIterator.h"
 
 #include "platform/text/Character.h"
 #include "wtf/ASCIICType.h"
 #include "wtf/StdLibExtras.h"
 #include "wtf/text/CharacterNames.h"
 
+#include <unicode/uchar.h>
+#include <unicode/uvernum.h>
+
 namespace blink {
 
 unsigned numGraphemeClusters(const String& string) {
   unsigned stringLength = string.length();
 
   if (!stringLength)
     return 0;
 
   // The only Latin-1 Extended Grapheme Cluster is CR LF
   if (string.is8Bit() && !string.contains('\r'))
@@ skipping 81 matching lines @@
     { B(0, 0, 0, 0, 0, 0, 0, 0), B(0, 0, 0, 0, 0, 0, 0, 0), 0, B(0, 0, 0, 0, 0, 0, 0, 0), 0, 0, 0, B(0, 0, 0, 0, 0, 0, 0, 0), 0, 0, 0, B(0, 0, 0, 0, 0, 0, 0, 0) }, // `
     AL,  AL,  AL,  AL,  AL,  AL,  AL,  AL,  AL,  AL,  AL,  AL,  AL,  AL,  AL,  AL,  AL,  AL,  AL,  AL,  AL,  AL,  AL,  AL,  AL,  AL, // a-z
     { B(0, 0, 0, 0, 0, 0, 0, 0), B(0, 0, 0, 0, 0, 0, 0, 0), 0, B(0, 0, 0, 0, 0, 0, 0, 0), 0, 0, 0, B(0, 0, 0, 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, 1), B(0, 0, 0, 0, 0, 0, 0, 0), 0, B(0, 0, 0, 1, 0, 0, 0, 0), 0, 0, 0, B(0, 0, 1, 0, 0, 0, 0, 0), 0, 0, 0, B(0, 0, 1, 0, 0, 0, 0, 0) }, // |
     { B(0, 0, 0, 0, 0, 0, 0, 1), B(0, 0, 0, 0, 0, 0, 0, 0), 0, B(0, 0, 0, 1, 0, 0, 0, 0), 0, 0, 0, B(0, 0, 1, 0, 0, 0, 0, 0), 0, 0, 0, B(0, 0, 1, 0, 0, 0, 0, 0) }, // }
     { B(0, 0, 0, 0, 0, 0, 0, 1), B(0, 0, 0, 0, 0, 0, 0, 0), 0, B(0, 0, 0, 1, 0, 0, 0, 0), 0, 0, 0, B(0, 0, 1, 0, 0, 0, 0, 0), 0, 0, 0, B(0, 0, 1, 0, 0, 0, 0, 0) }, // ~
     { B(0, 0, 0, 0, 0, 0, 0, 0), B(0, 0, 0, 0, 0, 0, 0, 0), 0, B(0, 0, 0, 0, 0, 0, 0, 0), 0, 0, 0, B(0, 0, 0, 0, 0, 0, 0, 0), 0, 0, 0, B(0, 0, 0, 0, 0, 0, 0, 0) }, // DEL
 };
 // 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
 //   Algorithm: http://unicode.org/reports/tr14/#DescriptionOfProperties
 // - 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
     { 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) }, // AL
     { 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) }, // B2
     { 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) }, // BA
     { 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) }, // BB
     { 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) }, // BK
     { 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) }, // CB
     { B(0, 1, 1, 0, 1, 0, 0, 0), B(0, 0, 0, 0, 0, 1, 0, 0), B(0, 0, 0, 1, 0, 0, 1, 0), B(0, 0, 0, 0, 0, 0, 0, 0), B(0, 0, 0, 0, 0, 0, 1, 0) }, // CL
@@ skipping 33 matching lines @@
 
 #undef B
 #undef F
 #undef DI
 #undef AL
 
 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) {
   // Don't allow line breaking between '-' and a digit if the '-' may mean a
   // minus sign in the context, while allow breaking in 'ABCD-1234' and
   // '1234-5678' which may be in long URLs.
   if (ch == '-' && isASCIIDigit(nextCh))
     return isASCIIAlphanumeric(lastCh);
 
   // If both ch and nextCh are ASCII characters, use a lookup table for enhanced
@@ skipping 15 matching lines @@
   if (ch == '+')  // IE tailors '+' to AL-like class when break-all is enabled.
     return U_LB_ALPHABETIC;
   UChar32 ch32 = U16_IS_LEAD(lastCh) && U16_IS_TRAIL(ch)
                      ? U16_GET_SUPPLEMENTARY(lastCh, ch)
                      : ch;
   return static_cast<ULineBreak>(u_getIntPropertyValue(ch32, UCHAR_LINE_BREAK));
 }
 
 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));
   }
   return false;
 }
 
 inline bool needsLineBreakIterator(UChar ch) {
   return ch > asciiLineBreakTableLastChar && ch != noBreakSpaceCharacter;
 }
 
@@ skipping 186 matching lines @@
 
 int LazyLineBreakIterator::nextBreakablePositionKeepAll(int pos) {
   if (m_string.is8Bit())
     return nextBreakablePosition<LChar, LineBreakType::Normal>(
         *this, m_string.characters8(), m_string.length(), pos);
   return nextBreakablePositionKeepAllInternal(*this, m_string.characters16(),
                                               m_string.length(), pos);
 }
 
 }  // namespace blink