mirror of https://github.com/kiwix/libkiwix.git
+ improved version of removeAccents(9
This commit is contained in:
parent
27ee27bbe9
commit
31dc311f2a
|
@ -123,19 +123,19 @@ namespace kiwix {
|
|||
|
||||
/* Index the title */
|
||||
if (!this->htmlParser.title.empty()) {
|
||||
indexer.index_text_without_positions(removeAccents(this->htmlParser.title.c_str(), this->htmlParser.title.size()),
|
||||
indexer.index_text_without_positions(removeAccents(this->htmlParser.title),
|
||||
((this->htmlParser.dump.size() / 100) + 1) /
|
||||
countWords(this->htmlParser.title) );
|
||||
}
|
||||
|
||||
/* Index the keywords */
|
||||
if (!this->htmlParser.keywords.empty()) {
|
||||
indexer.index_text_without_positions(removeAccents(this->htmlParser.keywords.c_str(), this->htmlParser.keywords.size()), 3);
|
||||
indexer.index_text_without_positions(removeAccents(this->htmlParser.keywords), 3);
|
||||
}
|
||||
|
||||
/* Index the content */
|
||||
if (!this->htmlParser.dump.empty()) {
|
||||
indexer.index_text_without_positions(removeAccents(this->htmlParser.dump.c_str(), this->htmlParser.dump.size()));
|
||||
indexer.index_text_without_positions(removeAccents(this->htmlParser.dump));
|
||||
}
|
||||
|
||||
/* add to the database */
|
||||
|
|
|
@ -36,7 +36,7 @@ namespace kiwix {
|
|||
|
||||
/* Create the query term vector */
|
||||
/* I have the doublequote " because bug ID: 2939690 */
|
||||
std::vector<std::string> queryTerms = split(removeAccents(search.c_str(), search.size()), " #@%$0/\\_-*()[]{},;:\"´`'");
|
||||
std::vector<std::string> queryTerms = split(removeAccents(search), " #@%$0/\\_-*()[]{},;:\"´`'");
|
||||
|
||||
/* Create query object */
|
||||
Xapian::Query query(Xapian::Query::OP_OR, queryTerms.begin(), queryTerms.end());
|
||||
|
|
|
@ -57,23 +57,12 @@ void UnaccentTransliterator::handleTransliterate(Replaceable& text,
|
|||
|
||||
/* Remove accents from a String */
|
||||
UnaccentTransliterator unaccent;
|
||||
char *unaccentedString = NULL;
|
||||
unsigned unaccentedStringSize=0;
|
||||
UnicodeString unicodeAccentedString;
|
||||
|
||||
const char* removeAccents(const char *accentedString, const unsigned size) {
|
||||
|
||||
/* Realloc memory if necessary */
|
||||
if (size > unaccentedStringSize) {
|
||||
unaccentedString = (char*)realloc(unaccentedString, size+1);
|
||||
unaccentedStringSize = size+1;
|
||||
}
|
||||
|
||||
/* Transcode the String */
|
||||
unicodeAccentedString = UnicodeString(accentedString);
|
||||
std::string &removeAccents(std::string &text) {
|
||||
unicodeAccentedString = UnicodeString(text.c_str());
|
||||
unaccent.transliterate(unicodeAccentedString);
|
||||
|
||||
/* Extract and return the result */
|
||||
unicodeAccentedString.extract(0, size, unaccentedString, size, "UTF-8");
|
||||
return unaccentedString;
|
||||
text.clear();
|
||||
unicodeAccentedString.toUTF8String(text);
|
||||
return text;
|
||||
}
|
||||
|
|
|
@ -95,4 +95,4 @@ private:
|
|||
static const char fgClassID;
|
||||
};
|
||||
|
||||
const char* removeAccents(const char *, const unsigned);
|
||||
std::string &removeAccents(std::string &text);
|
||||
|
|
Loading…
Reference in New Issue