@@ -34,6 +34,8 @@ var_dump(mb_levenshtein('111', '121', 2, 3, 2));
3434echo '--- Very expensive replacement --- ' . \PHP_EOL ;
3535var_dump (mb_levenshtein ('111 ' , '121 ' , 2 , 9 , 2 ));
3636
37+ echo '--- 128 codepoints --- ' . \PHP_EOL ;
38+ var_dump (mb_levenshtein (str_repeat ("a " , 128 ), str_repeat ("a " , 125 ) . "abc " ));
3739echo '--- 128 codepoints over --- ' . \PHP_EOL ;
3840var_dump (mb_levenshtein (str_repeat ("a " , 128 ) . "abc " , str_repeat ("a " , 128 ) . "aaa " ));
3941echo '--- 128 codepoints over only $string1 --- ' . \PHP_EOL ;
@@ -48,6 +50,10 @@ $hiragana_a = mb_convert_encoding("あ", "SJIS", "UTF-8");
4850$ hiragana_aiu = mb_convert_encoding ("あいう " , "SJIS " , "UTF-8 " );
4951var_dump (mb_levenshtein (str_repeat ($ hiragana_a , 128 + 3 ), str_repeat ($ hiragana_a , 128 ) . $ hiragana_aiu , encoding: "SJIS " ));
5052
53+ echo '--- café in ISO-8859-1 --- ' . \PHP_EOL ;
54+ $ cafe = mb_convert_encoding ("café " , "ISO-8859-1 " , "UTF-8 " );
55+ var_dump (mb_levenshtein ("cafe " , $ cafe , encoding: "ISO-8859-1 " ));
56+
5157echo '--- Usecase of userland code --- ' . \PHP_EOL ;
5258/* from: https://qiita.com/mpyw/items/2b636827730e06c71e3d */
5359$ query = 'ほあようごぁいまーしゅ ' ;
@@ -113,6 +119,8 @@ int(10)
113119int(3)
114120--- Very expensive replacement ---
115121int(4)
122+ --- 128 codepoints ---
123+ int(2)
116124--- 128 codepoints over ---
117125int(2)
118126--- 128 codepoints over only $string1 ---
@@ -123,6 +131,8 @@ int(130)
123131int(2)
124132--- 128 codepoints over Hiragana in Shift_JIS ---
125133int(2)
134+ --- café in ISO-8859-1 ---
135+ int(1)
126136--- Usecase of userland code ---
127137string(30) "おはようございまーす"
128138int(4)
0 commit comments