Exemplo n.º 1
0
function del_secchars($file)
{
    global $cn_seg, $jp_seg, $del_secchars, $del_seccharin;
    if ($jp_seg == '1' || $cn_seg == '1' && $del_secchars == 1 || $del_seccharin == 1) {
        //      Delete additional characters (as word separator) like dots, question marks, colons etc. (characters 1-49 in original Chinese dictionary)
        $file = preg_replace('/。|,|〿|;|:|?|_|…|—|·|ˉ|ˇ|¨|‘|’|“|‿|々|~|‖|∶|"|'|`|||〃|〔|〕|〈|〉|《|》|「|〿|『|〿|.|〖|〗|〿|】|(|)|[|]|{|ソ/', " ", $file);
        $file = preg_replace('/ï¼›|¡£|£¬|¡¢|£»|£º|£¿|£¡|¡­|¡ª|¡¤|¡¥|¡¦|¡§|¡®|¡¯|¡°|¡±|¡©|¡«|¡¬|¡Ã|£¢|£§|£à|£ü|¡¨|¡²|¡³|¡´|¡µ|¡¶|¡·|¡¸|¡¹|¡º|¡»|£®|¡¼|¡½|¡¾|¡¿|£¨|£©|£Û|£ÿ|£û|£ý|°¢/', " ", $file);
        $file = preg_replace('/_|&|,|<|:|;|・|\\(|\\)/', " ", $file);
    }
    if ($del_secchars == '1') {
        //    kill  special characters at the end of words
        $file = preg_replace('/— |\\]. |\\%\\? |\\"\\. |, |.\'|\\. |\\.\\. |\\.\\.\\. |! |\\? |" |: |\\) |\\), |\\)\\. |】 |) |?,|? |! |!|。,|。 |„ |“ |” |”|”&nbsp;|» |\\.»|;»|:»|,»|\\.»|·»|«|« |», |»\\. |\\.” |,”|;” |”\\. |”, |‿|、|)|·|;|\\] |\\} |_, |_ |”\\)\\. |.\\"> |\\"> |> |\\)|&lt; |\\%, |\\%. |\\%.\\" |\\% |\\+\\+ |\\+ |\\* |\\# |\\~ /', " ", $file);
        //    kill special characters in front of words
        $file = preg_replace('/ —| \\(\\"| \\(\\$| \\(\\@| \\@| \\[| "| \\(| „|„| “|(| «| 【| ‿| (| \\(“|“| ©| ®| ™| –| <| \\/|\\/| \\"| \\.| \\^| &gt;| \\$| \\£| \\"\\(| \\+| \\*| \\.| \\#| \\%| \\~| \\{/', " ", $file);
    }
    if ($del_seccharin == '1') {
        $file = del_secintern($file);
    }
    return $file;
}
Exemplo n.º 2
0
 $id3_string = @iconv($charSet, "UTF-8//IGNORE", $id3_string);
 $title_orig = $title;
 $title_trans = $title;
 $id3_trans = $id3_string;
 $title .= $delim;
 $id3_string .= $delim;
 //  kill all secondary characters from title tag and EXIF info
 if ($del_seccharin) {
     $title_rem = $title_trans;
     $id3_rem = $id3_trans;
     $title_trans = del_secintern($title_trans);
     if ($title_trans != $title_rem) {
         $title .= " " . $title_trans . "";
         //  add new words to title
     }
     $id3_trans = del_secintern($id3_trans);
     if ($id3_trans != $id3_rem) {
         $id3_string .= " " . $id3_trans . "";
         //  add new words to EXIF info
     }
 }
 //   convert to lower case
 if ($case_sensitive == '0') {
     $title_rem = $title_trans;
     $id3_rem = $id3_trans;
     $title_trans = lower_case(lower_ent($title_trans));
     if ($title_trans != $title_rem) {
         $title .= " " . $title_trans . "";
         //  add new words to title
     }
     $id3_trans = lower_case(lower_ent($id3_trans));