Modified: trunk/Source/WebKit/gtk/ChangeLog (117670 => 117671)
--- trunk/Source/WebKit/gtk/ChangeLog 2012-05-19 03:29:10 UTC (rev 117670)
+++ trunk/Source/WebKit/gtk/ChangeLog 2012-05-19 04:21:19 UTC (rev 117671)
@@ -1,3 +1,17 @@
+2012-05-18 Sheriff Bot <[email protected]>
+
+ Unreviewed, rolling out r117628.
+ http://trac.webkit.org/changeset/117628
+ https://bugs.webkit.org/show_bug.cgi?id=86936
+
+ triggers 20+ timeouts in the editing test suite (Requested by
+ philn on #webkit).
+
+ * WebCoreSupport/TextCheckerClientGtk.cpp:
+ (WebKit::TextCheckerClientGtk::checkSpellingOfString):
+ * webkit/webkitspellcheckerenchant.cpp:
+ (checkSpellingOfString):
+
2012-05-18 Martin Robinson <[email protected]>
Spell checker doesn't recognize contractions (apostrophes)
Modified: trunk/Source/WebKit/gtk/WebCoreSupport/TextCheckerClientGtk.cpp (117670 => 117671)
--- trunk/Source/WebKit/gtk/WebCoreSupport/TextCheckerClientGtk.cpp 2012-05-19 03:29:10 UTC (rev 117670)
+++ trunk/Source/WebKit/gtk/WebCoreSupport/TextCheckerClientGtk.cpp 2012-05-19 04:21:19 UTC (rev 117671)
@@ -63,27 +63,6 @@
{
GOwnPtr<gchar> utf8Text(g_utf16_to_utf8(const_cast<gunichar2*>(text), length, 0, 0, 0));
webkit_spell_checker_check_spelling_of_string(m_spellChecker.get(), utf8Text.get(), misspellingLocation, misspellingLength);
-
- // We have the offset and length in Unicode characters, but we need to convert them to UTF-16 offsets.
- // Unfortunately there doesn't seem to be a simple way to do this.
- if (!*misspellingLength)
- return;
-
- bool pastStartOfWord = false;
- for (int i = 0; i < length; i++) {
- if (i >= *misspellingLocation + *misspellingLength)
- return;
- if (!pastStartOfWord && i > *misspellingLocation)
- pastStartOfWord = true;
-
- // If this character is part of a surrogate pair, we need to skip the next character (the trail)
- // and to increase our offsets.
- if (!U16_IS_SINGLE(text[i])) {
- i++;
- (*misspellingLength)++;
- *misspellingLocation += pastStartOfWord ? 0 : 1;
- }
- }
}
String TextCheckerClientGtk::getAutoCorrectSuggestionForMisspelledWord(const String& inputWord)
Modified: trunk/Source/WebKit/gtk/webkit/webkitspellcheckerenchant.cpp (117670 => 117671)
--- trunk/Source/WebKit/gtk/webkit/webkitspellcheckerenchant.cpp 2012-05-19 03:29:10 UTC (rev 117670)
+++ trunk/Source/WebKit/gtk/webkit/webkitspellcheckerenchant.cpp 2012-05-19 04:21:19 UTC (rev 117671)
@@ -88,14 +88,6 @@
priv->enchantDicts = 0;
}
-static size_t findByteOffsetToFirstNonGraphableCharacter(const char* utf8String)
-{
- const char* firstNonGraphableCharacter = utf8String;
- while (firstNonGraphableCharacter && g_unichar_isgraph(g_utf8_get_char(firstNonGraphableCharacter)))
- firstNonGraphableCharacter = g_utf8_find_next_char(firstNonGraphableCharacter, 0);
- return firstNonGraphableCharacter - utf8String;
-}
-
static void checkSpellingOfString(WebKitSpellChecker* checker, const char* string, int* misspellingLocation, int* misspellingLength)
{
WebKitSpellCheckerEnchantPrivate* priv = WEBKIT_SPELL_CHECKER_ENCHANT(checker)->priv;
@@ -104,33 +96,50 @@
if (!dicts)
return;
- // At the time this code was written, WebCore only sends us one word at a
- // time during spellchecking, with a chance of having some small amount of
- // leading and trailing whitespace. For this reason we can merely chop off
- // the whitespace and send the word directly to Enchant.
- const char* firstWord = string;
- while (firstWord && !g_unichar_isgraph(g_utf8_get_char(firstWord)))
- firstWord = g_utf8_find_next_char(firstWord, NULL);
+ int length = g_utf8_strlen(string, -1);
- // Either the string only had whitespace characters or no characters at all.
- if (!firstWord)
- return;
+ PangoLanguage* language(pango_language_get_default());
+ GOwnPtr<PangoLogAttr> attrs(g_new(PangoLogAttr, length + 1));
- size_t byteOffsetToEndOfFirstWord = findByteOffsetToFirstNonGraphableCharacter(firstWord);
- for (; dicts; dicts = dicts->next) {
- EnchantDict* dict = static_cast<EnchantDict*>(dicts->data);
- int result = enchant_dict_check(dict, firstWord, byteOffsetToEndOfFirstWord);
+ // pango_get_log_attrs uses an aditional position at the end of the text.
+ pango_get_log_attrs(string, -1, -1, language, attrs.get(), length + 1);
- if (result < 0) // Error during checking.
- continue;
- if (!result) { // Stop checking, as this word is correct for at least one dictionary.
- *misspellingLocation = -1;
- *misspellingLength = 0;
- return;
+ for (int 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)
+ 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(string, start);
+ gint bytes = static_cast<gint>(g_utf8_offset_to_pointer(string, end) - cstart);
+ GOwnPtr<gchar> word(g_new0(gchar, bytes + 1));
+
+ g_utf8_strncpy(word.get(), cstart, wordLength);
+
+ for (; dicts; dicts = dicts->next) {
+ EnchantDict* dict = static_cast<EnchantDict*>(dicts->data);
+ if (enchant_dict_check(dict, word.get(), wordLength)) {
+ *misspellingLocation = start;
+ *misspellingLength = wordLength;
+ } else {
+ // Stop checking, this word is ok in at least one dict.
+ *misspellingLocation = -1;
+ *misspellingLength = 0;
+ break;
+ }
+ }
}
-
- *misspellingLocation = g_utf8_pointer_to_offset(string, firstWord);
- *misspellingLength = g_utf8_pointer_to_offset(string, firstWord + byteOffsetToEndOfFirstWord) - *misspellingLocation;
}
}
