| 1 | /* |
| 2 | * Copyright (C) 2006, 2007 Apple Inc. All rights reserved. |
| 3 | * Copyright (C) 2009 Dominik Röttsches <dominik.roettsches@access-company.com> |
| 4 | * |
| 5 | * Redistribution and use in source and binary forms, with or without |
| 6 | * modification, are permitted provided that the following conditions |
| 7 | * are met: |
| 8 | * 1. Redistributions of source code must retain the above copyright |
| 9 | * notice, this list of conditions and the following disclaimer. |
| 10 | * 2. Redistributions in binary form must reproduce the above copyright |
| 11 | * notice, this list of conditions and the following disclaimer in the |
| 12 | * documentation and/or other materials provided with the distribution. |
| 13 | * |
| 14 | * THIS SOFTWARE IS PROVIDED BY APPLE INC. ``AS IS'' AND ANY |
| 15 | * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE |
| 16 | * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR |
| 17 | * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL APPLE INC. OR |
| 18 | * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, |
| 19 | * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, |
| 20 | * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR |
| 21 | * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY |
| 22 | * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT |
| 23 | * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE |
| 24 | * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
| 25 | */ |
| 26 | |
| 27 | #include "config.h" |
| 28 | #include "TextBoundaries.h" |
| 29 | |
| 30 | #include <unicode/ubrk.h> |
| 31 | #include <wtf/text/StringImpl.h> |
| 32 | #include <wtf/text/TextBreakIterator.h> |
| 33 | |
| 34 | namespace WebCore { |
| 35 | |
| 36 | unsigned endOfFirstWordBoundaryContext(StringView text) |
| 37 | { |
| 38 | unsigned length = text.length(); |
| 39 | for (unsigned i = 0; i < length; ) { |
| 40 | unsigned first = i; |
| 41 | UChar32 ch; |
| 42 | U16_NEXT(text, i, length, ch); |
| 43 | if (!requiresContextForWordBoundary(ch)) |
| 44 | return first; |
| 45 | } |
| 46 | return length; |
| 47 | } |
| 48 | |
| 49 | unsigned startOfLastWordBoundaryContext(StringView text) |
| 50 | { |
| 51 | unsigned length = text.length(); |
| 52 | for (unsigned i = length; i > 0; ) { |
| 53 | unsigned last = i; |
| 54 | UChar32 ch; |
| 55 | U16_PREV(text, 0, i, ch); |
| 56 | if (!requiresContextForWordBoundary(ch)) |
| 57 | return last; |
| 58 | } |
| 59 | return 0; |
| 60 | } |
| 61 | |
| 62 | #if !PLATFORM(COCOA) |
| 63 | |
| 64 | int findNextWordFromIndex(StringView text, int position, bool forward) |
| 65 | { |
| 66 | UBreakIterator* it = wordBreakIterator(text); |
| 67 | |
| 68 | if (forward) { |
| 69 | position = ubrk_following(it, position); |
| 70 | while (position != UBRK_DONE) { |
| 71 | // We stop searching when the character preceeding the break is alphanumeric. |
| 72 | if (static_cast<unsigned>(position) < text.length() && u_isalnum(text[position - 1])) |
| 73 | return position; |
| 74 | |
| 75 | position = ubrk_following(it, position); |
| 76 | } |
| 77 | |
| 78 | return text.length(); |
| 79 | } else { |
| 80 | position = ubrk_preceding(it, position); |
| 81 | while (position != UBRK_DONE) { |
| 82 | // We stop searching when the character following the break is alphanumeric. |
| 83 | if (position && u_isalnum(text[position])) |
| 84 | return position; |
| 85 | |
| 86 | position = ubrk_preceding(it, position); |
| 87 | } |
| 88 | |
| 89 | return 0; |
| 90 | } |
| 91 | } |
| 92 | |
| 93 | void findWordBoundary(StringView text, int position, int* start, int* end) |
| 94 | { |
| 95 | UBreakIterator* it = wordBreakIterator(text); |
| 96 | *end = ubrk_following(it, position); |
| 97 | if (*end < 0) |
| 98 | *end = ubrk_last(it); |
| 99 | *start = ubrk_previous(it); |
| 100 | } |
| 101 | |
| 102 | void findEndWordBoundary(StringView text, int position, int* end) |
| 103 | { |
| 104 | UBreakIterator* it = wordBreakIterator(text); |
| 105 | *end = ubrk_following(it, position); |
| 106 | if (*end < 0) |
| 107 | *end = ubrk_last(it); |
| 108 | } |
| 109 | |
| 110 | #endif // !PLATFORM(COCOA) |
| 111 | |
| 112 | } // namespace WebCore |
| 113 | |