1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
|
/*
* Copyright (C) 2012 Igalia S.L.
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This library 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
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include "config.h"
#include "TextCheckerEnchant.h"
#if ENABLE(SPELLCHECK)
#include <pango/pango.h>
#include <wtf/gobject/GOwnPtr.h>
#include <wtf/text/CString.h>
using namespace WebCore;
static const size_t maximumNumberOfSuggestions = 10;
static void getAvailableDictionariesCallback(const char* const languageTag, const char* const, const char* const, const char* const, void* data)
{
Vector<CString>* dictionaries = static_cast<Vector<CString>*>(data);
dictionaries->append(languageTag);
}
static bool wordEndIsAContractionApostrophe(const char* string, long offset)
{
if (g_utf8_get_char(g_utf8_offset_to_pointer(string, offset)) != g_utf8_get_char("'"))
return false;
// If this is the last character in the string, it cannot be the apostrophe part of a contraction.
if (offset == g_utf8_strlen(string, -1))
return false;
return g_unichar_isalpha(g_utf8_get_char(g_utf8_offset_to_pointer(string, offset + 1)));
}
TextCheckerEnchant::TextCheckerEnchant()
: m_broker(enchant_broker_init())
, m_enchantDictionaries(0)
{
}
TextCheckerEnchant::~TextCheckerEnchant()
{
if (!m_broker)
return;
freeEnchantBrokerDictionaries();
enchant_broker_free(m_broker);
}
void TextCheckerEnchant::ignoreWord(const String& word)
{
for (Vector<EnchantDict*>::const_iterator iter = m_enchantDictionaries.begin(); iter != m_enchantDictionaries.end(); ++iter)
enchant_dict_add_to_session(*iter, word.utf8().data(), -1);
}
void TextCheckerEnchant::learnWord(const String& word)
{
for (Vector<EnchantDict*>::const_iterator iter = m_enchantDictionaries.begin(); iter != m_enchantDictionaries.end(); ++iter)
enchant_dict_add_to_personal(*iter, word.utf8().data(), -1);
}
void TextCheckerEnchant::checkSpellingOfString(const String& string, int& misspellingLocation, int& misspellingLength)
{
if (m_enchantDictionaries.isEmpty())
return;
Vector<EnchantDict*>::const_iterator dictIter = m_enchantDictionaries.begin();
GOwnPtr<gchar> cString(g_strdup(string.utf8().data()));
size_t length = string.utf8().length();
PangoLanguage* language(pango_language_get_default());
GOwnPtr<PangoLogAttr> attrs(g_new(PangoLogAttr, length + 1));
// pango_get_log_attrs uses an aditional position at the end of the text.
pango_get_log_attrs(cString.get(), -1, -1, language, attrs.get(), length + 1);
for (size_t i = 0; i < length + 1; i++) {
// We go through each character until we find an is_word_start,
// then we get into an inner loop to find the is_word_end corresponding
// to it.
if (attrs.get()[i].is_word_start) {
int start = i;
int end = i;
int wordLength;
while (attrs.get()[end].is_word_end < 1 || wordEndIsAContractionApostrophe(cString.get(), end))
end++;
wordLength = end - start;
// Set the iterator to be at the current word end, so we don't
// check characters twice.
i = end;
gchar* cstart = g_utf8_offset_to_pointer(cString.get(), start);
gint bytes = static_cast<gint>(g_utf8_offset_to_pointer(cString.get(), end) - cstart);
GOwnPtr<gchar> word(g_new0(gchar, bytes + 1));
g_utf8_strncpy(word.get(), cstart, wordLength);
for (; dictIter != m_enchantDictionaries.end(); ++dictIter) {
if (enchant_dict_check(*dictIter, word.get(), wordLength)) {
misspellingLocation = start;
misspellingLength = wordLength;
} else {
// Stop checking, this word is ok in at least one dict.
misspellingLocation = -1;
misspellingLength = 0;
break;
}
}
}
}
}
Vector<String> TextCheckerEnchant::getGuessesForWord(const String& word)
{
Vector<String> guesses;
if (m_enchantDictionaries.isEmpty())
return guesses;
for (Vector<EnchantDict*>::const_iterator iter = m_enchantDictionaries.begin(); iter != m_enchantDictionaries.end(); ++iter) {
size_t numberOfSuggestions;
size_t i;
gchar** suggestions = enchant_dict_suggest(*iter, word.utf8().data(), -1, &numberOfSuggestions);
if (numberOfSuggestions <= 0)
continue;
if (numberOfSuggestions > maximumNumberOfSuggestions)
numberOfSuggestions = maximumNumberOfSuggestions;
for (i = 0; i < numberOfSuggestions; i++)
guesses.append(String(suggestions[i]));
enchant_dict_free_suggestions(*iter, suggestions);
}
return guesses;
}
void TextCheckerEnchant::updateSpellCheckingLanguages(const String& languages)
{
Vector<EnchantDict*> spellDictionaries;
if (!languages.isEmpty()) {
Vector<String> languagesVector;
languages.split(static_cast<UChar>(','), languagesVector);
for (Vector<String>::const_iterator iter = languagesVector.begin(); iter != languagesVector.end(); ++iter) {
GOwnPtr<gchar> currentLanguage(g_strdup(iter->utf8().data()));
if (enchant_broker_dict_exists(m_broker, currentLanguage.get())) {
EnchantDict* dict = enchant_broker_request_dict(m_broker, currentLanguage.get());
spellDictionaries.append(dict);
}
}
} else {
const char* language = pango_language_to_string(pango_language_get_default());
if (enchant_broker_dict_exists(m_broker, language)) {
EnchantDict* dict = enchant_broker_request_dict(m_broker, language);
spellDictionaries.append(dict);
} else {
// No dictionaries selected, we get one from the list.
Vector<CString> allDictionaries;
enchant_broker_list_dicts(m_broker, getAvailableDictionariesCallback, &allDictionaries);
if (!allDictionaries.isEmpty()) {
EnchantDict* dict = enchant_broker_request_dict(m_broker, allDictionaries[0].data());
spellDictionaries.append(dict);
}
}
}
freeEnchantBrokerDictionaries();
m_enchantDictionaries = spellDictionaries;
}
void TextCheckerEnchant::freeEnchantBrokerDictionaries()
{
for (Vector<EnchantDict*>::const_iterator iter = m_enchantDictionaries.begin(); iter != m_enchantDictionaries.end(); ++iter)
enchant_broker_free_dict(m_broker, *iter);
}
#endif // ENABLE(SPELLCHECK)
|
