2 * Copyright (C) 2014 Google Inc. All rights reserved.
4 * Redistribution and use in source and binary forms, with or without
5 * modification, are permitted provided that the following conditions are
8 * * Redistributions of source code must retain the above copyright
9 * notice, this list of conditions and the following disclaimer.
10 * * Redistributions in binary form must reproduce the above
11 * copyright notice, this list of conditions and the following disclaimer
12 * in the documentation and/or other materials provided with the
14 * * Neither the name of Google Inc. nor the names of its
15 * contributors may be used to endorse or promote products derived from
16 * this software without specific prior written permission.
18 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
19 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
20 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
21 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
22 * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
23 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
24 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
25 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
26 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
27 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
28 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
32 #include "platform/fonts/Character.h"
34 #include "platform/fonts/FontPlatformFeatures.h"
35 #include "wtf/StdLibExtras.h"
36 #include "wtf/text/StringBuilder.h"
39 using namespace Unicode;
43 static const UChar32 cjkIsolatedSymbolsArray[] = {
44 // 0x2C7 Caron, Mandarin Chinese 3rd Tone
46 // 0x2CA Modifier Letter Acute Accent, Mandarin Chinese 2nd Tone
48 // 0x2CB Modifier Letter Grave Access, Mandarin Chinese 4th Tone
50 // 0x2D9 Dot Above, Mandarin Chinese 5th Tone
52 0x2020, 0x2021, 0x2030, 0x203B, 0x203C, 0x2042, 0x2047, 0x2048, 0x2049, 0x2051,
53 0x20DD, 0x20DE, 0x2100, 0x2103, 0x2105, 0x2109, 0x210A, 0x2113, 0x2116, 0x2121,
54 0x212B, 0x213B, 0x2150, 0x2151, 0x2152, 0x217F, 0x2189, 0x2307, 0x2312, 0x23CE,
55 0x2423, 0x25A0, 0x25A1, 0x25A2, 0x25AA, 0x25AB, 0x25B1, 0x25B2, 0x25B3, 0x25B6,
56 0x25B7, 0x25BC, 0x25BD, 0x25C0, 0x25C1, 0x25C6, 0x25C7, 0x25C9, 0x25CB, 0x25CC,
57 0x25EF, 0x2605, 0x2606, 0x260E, 0x2616, 0x2617, 0x2640, 0x2642, 0x26A0, 0x26BD,
58 0x26BE, 0x2713, 0x271A, 0x273F, 0x2740, 0x2756, 0x2B1A, 0xFE10, 0xFE11, 0xFE12,
64 // Takes a flattened list of closed intervals
65 template <class T, size_t size>
66 bool valueInIntervalList(const T (&intervalList)[size], const T& value)
68 const T* bound = std::upper_bound(&intervalList[0], &intervalList[size], value);
69 if ((bound - intervalList) % 2 == 1)
71 return bound > intervalList && *(bound - 1) == value;
74 CodePath Character::characterRangeCodePath(const UChar* characters, unsigned len)
76 static const UChar complexCodePathRanges[] = {
77 // U+02E5 through U+02E9 (Modifier Letters : Tone letters)
79 // U+0300 through U+036F Combining diacritical marks
81 // U+0591 through U+05CF excluding U+05BE Hebrew combining marks, ...
83 // ... Hebrew punctuation Paseq, Sof Pasuq and Nun Hafukha
85 // U+0600 through U+109F Arabic, Syriac, Thaana, NKo, Samaritan, Mandaic,
86 // Devanagari, Bengali, Gurmukhi, Gujarati, Oriya, Tamil, Telugu, Kannada,
87 // Malayalam, Sinhala, Thai, Lao, Tibetan, Myanmar
89 // U+1100 through U+11FF Hangul Jamo (only Ancient Korean should be left
90 // here if you precompose; Modern Korean will be precomposed as a result of step A)
92 // U+135D through U+135F Ethiopic combining marks
94 // U+1780 through U+18AF Tagalog, Hanunoo, Buhid, Taghanwa,Khmer, Mongolian
96 // U+1900 through U+194F Limbu (Unicode 4.0)
98 // U+1980 through U+19DF New Tai Lue
100 // U+1A00 through U+1CFF Buginese, Tai Tham, Balinese, Batak, Lepcha, Vedic
102 // U+1DC0 through U+1DFF Comining diacritical mark supplement
104 // U+20D0 through U+20FF Combining marks for symbols
106 // U+2CEF through U+2CF1 Combining marks for Coptic
108 // U+302A through U+302F Ideographic and Hangul Tone marks
110 // U+A67C through U+A67D Combining marks for old Cyrillic
112 // U+A6F0 through U+A6F1 Combining mark for Bamum
114 // U+A800 through U+ABFF Nagri, Phags-pa, Saurashtra, Devanagari Extended,
115 // Hangul Jamo Ext. A, Javanese, Myanmar Extended A, Tai Viet, Meetei Mayek
117 // U+D7B0 through U+D7FF Hangul Jamo Ext. B
119 // U+FE00 through U+FE0F Unicode variation selectors
121 // U+FE20 through U+FE2F Combining half marks
125 CodePath result = SimplePath;
126 for (unsigned i = 0; i < len; i++) {
127 const UChar c = characters[i];
129 // Shortcut for common case
133 // U+1E00 through U+2000 characters with diacritics and stacked diacritics
134 if (c >= 0x1E00 && c <= 0x2000) {
135 result = SimpleWithGlyphOverflowPath;
140 if (c > 0xD7FF && c <= 0xDBFF) {
144 UChar next = characters[++i];
145 if (!U16_IS_TRAIL(next))
148 UChar32 supplementaryCharacter = U16_GET_SUPPLEMENTARY(c, next);
150 if (supplementaryCharacter < 0x1F1E6) // U+1F1E6 through U+1F1FF Regional Indicator Symbols
152 if (supplementaryCharacter <= 0x1F1FF)
155 if (supplementaryCharacter < 0xE0100) // U+E0100 through U+E01EF Unicode variation selectors.
157 if (supplementaryCharacter <= 0xE01EF)
160 // FIXME: Check for Brahmi (U+11000 block), Kaithi (U+11080 block) and other complex scripts
161 // in plane 1 or higher.
166 // Search for other Complex cases
167 if (valueInIntervalList(complexCodePathRanges, c))
174 bool Character::isCJKIdeograph(UChar32 c)
176 static const UChar32 cjkIdeographRanges[] = {
177 // CJK Radicals Supplement and Kangxi Radicals.
181 // CJK Unified Ideographs Extension A.
183 // The basic CJK Unified Ideographs block.
185 // CJK Compatibility Ideographs.
187 // CJK Unified Ideographs Extension B.
189 // CJK Unified Ideographs Extension C.
190 // CJK Unified Ideographs Extension D.
192 // CJK Compatibility Ideographs Supplement.
195 static size_t cjkIdeographRangesCount = WTF_ARRAY_LENGTH(cjkIdeographRanges);
198 if (c < cjkIdeographRanges[0] || c > cjkIdeographRanges[cjkIdeographRangesCount - 1])
201 return valueInIntervalList(cjkIdeographRanges, c);
204 bool Character::isCJKIdeographOrSymbol(UChar32 c)
206 // Likely common case
210 // Hash lookup for isolated symbols (those not part of a contiguous range)
211 static HashSet<UChar32>* cjkIsolatedSymbols = 0;
212 if (!cjkIsolatedSymbols) {
213 cjkIsolatedSymbols = new HashSet<UChar32>();
214 for (size_t i = 0; i < WTF_ARRAY_LENGTH(cjkIsolatedSymbolsArray); ++i)
215 cjkIsolatedSymbols->add(cjkIsolatedSymbolsArray[i]);
217 if (cjkIsolatedSymbols->contains(c))
220 if (isCJKIdeograph(c))
223 static const UChar32 cjkSymbolRanges[] = {
236 // Ideographic Description Characters, with CJK Symbols and Punctuation, excluding 0x3030.
237 // Then Hiragana 0x3040 .. 0x309F, Katakana 0x30A0 .. 0x30FF, Bopomofo 0x3100 .. 0x312F
240 // More Bopomofo and Bopomofo Extended 0x31A0 .. 0x31BF
242 // Enclosed CJK Letters and Months (0x3200 .. 0x32FF).
243 // CJK Compatibility (0x3300 .. 0x33FF).
246 // CJK Compatibility Forms.
248 // Halfwidth and Fullwidth Forms
249 // Usually only used in CJK
261 return valueInIntervalList(cjkSymbolRanges, c);
264 unsigned Character::expansionOpportunityCount(const LChar* characters, size_t length, TextDirection direction, bool& isAfterExpansion)
267 if (direction == LTR) {
268 for (size_t i = 0; i < length; ++i) {
269 if (treatAsSpace(characters[i])) {
271 isAfterExpansion = true;
273 isAfterExpansion = false;
277 for (size_t i = length; i > 0; --i) {
278 if (treatAsSpace(characters[i - 1])) {
280 isAfterExpansion = true;
282 isAfterExpansion = false;
289 unsigned Character::expansionOpportunityCount(const UChar* characters, size_t length, TextDirection direction, bool& isAfterExpansion)
291 static bool expandAroundIdeographs = FontPlatformFeatures::canExpandAroundIdeographsInComplexText();
293 if (direction == LTR) {
294 for (size_t i = 0; i < length; ++i) {
295 UChar32 character = characters[i];
296 if (treatAsSpace(character)) {
298 isAfterExpansion = true;
301 if (U16_IS_LEAD(character) && i + 1 < length && U16_IS_TRAIL(characters[i + 1])) {
302 character = U16_GET_SUPPLEMENTARY(character, characters[i + 1]);
305 if (expandAroundIdeographs && isCJKIdeographOrSymbol(character)) {
306 if (!isAfterExpansion)
309 isAfterExpansion = true;
312 isAfterExpansion = false;
315 for (size_t i = length; i > 0; --i) {
316 UChar32 character = characters[i - 1];
317 if (treatAsSpace(character)) {
319 isAfterExpansion = true;
322 if (U16_IS_TRAIL(character) && i > 1 && U16_IS_LEAD(characters[i - 2])) {
323 character = U16_GET_SUPPLEMENTARY(characters[i - 2], character);
326 if (expandAroundIdeographs && isCJKIdeographOrSymbol(character)) {
327 if (!isAfterExpansion)
330 isAfterExpansion = true;
333 isAfterExpansion = false;
339 bool Character::canReceiveTextEmphasis(UChar32 c)
341 CharCategory category = Unicode::category(c);
342 if (category & (Separator_Space | Separator_Line | Separator_Paragraph | Other_NotAssigned | Other_Control | Other_Format))
345 // Additional word-separator characters listed in CSS Text Level 3 Editor's Draft 3 November 2010.
346 if (c == ethiopicWordspace || c == aegeanWordSeparatorLine || c == aegeanWordSeparatorDot
347 || c == ugariticWordDivider || c == tibetanMarkIntersyllabicTsheg || c == tibetanMarkDelimiterTshegBstar)
353 template <typename CharacterType>
354 static inline String normalizeSpacesInternal(const CharacterType* characters, unsigned length)
356 StringBuilder normalized;
357 normalized.reserveCapacity(length);
359 for (unsigned i = 0; i < length; ++i)
360 normalized.append(Character::normalizeSpaces(characters[i]));
362 return normalized.toString();
365 String Character::normalizeSpaces(const LChar* characters, unsigned length)
367 return normalizeSpacesInternal(characters, length);
370 String Character::normalizeSpaces(const UChar* characters, unsigned length)
372 return normalizeSpacesInternal(characters, length);