annotate goodreads/UTFUtil.php @ 43:dbc006408d2b

ASSUMES we have SetEnv PHP_VALUE "include_path =.:/var/test/private:/var/test/ywww:/usr/share/php" in apache2/.../test.conf use dl(...) for debug logging, defined in dlog.php use doAmazonRequest in amazonBookSearch use ../private/web.php (q.v., not in mercurial) for Aserver and Aassociates Started by updating from 40:c24ae74bf6d5, i.e. just before the bug on the main line
author Charlie Root
date Sat, 05 Jan 2019 18:00:10 -0500
parents 077b0a0a3e6d
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
6
077b0a0a3e6d remaining originals according to dependency walk
Robert Boland <robert@markup.co.uk>
parents:
diff changeset
1 <?PHP
077b0a0a3e6d remaining originals according to dependency walk
Robert Boland <robert@markup.co.uk>
parents:
diff changeset
2 function convert_utf8($str){
077b0a0a3e6d remaining originals according to dependency walk
Robert Boland <robert@markup.co.uk>
parents:
diff changeset
3 if(!seems_utf8($str))
077b0a0a3e6d remaining originals according to dependency walk
Robert Boland <robert@markup.co.uk>
parents:
diff changeset
4 return mb_convert_encoding($str, 'UTF-8');
077b0a0a3e6d remaining originals according to dependency walk
Robert Boland <robert@markup.co.uk>
parents:
diff changeset
5 return $str;
077b0a0a3e6d remaining originals according to dependency walk
Robert Boland <robert@markup.co.uk>
parents:
diff changeset
6 }
077b0a0a3e6d remaining originals according to dependency walk
Robert Boland <robert@markup.co.uk>
parents:
diff changeset
7
077b0a0a3e6d remaining originals according to dependency walk
Robert Boland <robert@markup.co.uk>
parents:
diff changeset
8 function seems_utf8($Str) {
077b0a0a3e6d remaining originals according to dependency walk
Robert Boland <robert@markup.co.uk>
parents:
diff changeset
9 for ($i=0; $i<strlen($Str); $i++) {
077b0a0a3e6d remaining originals according to dependency walk
Robert Boland <robert@markup.co.uk>
parents:
diff changeset
10 if (ord($Str[$i]) < 0x80) continue; # 0bbbbbbb
077b0a0a3e6d remaining originals according to dependency walk
Robert Boland <robert@markup.co.uk>
parents:
diff changeset
11 elseif ((ord($Str[$i]) & 0xE0) == 0xC0) $n=1; # 110bbbbb
077b0a0a3e6d remaining originals according to dependency walk
Robert Boland <robert@markup.co.uk>
parents:
diff changeset
12 elseif ((ord($Str[$i]) & 0xF0) == 0xE0) $n=2; # 1110bbbb
077b0a0a3e6d remaining originals according to dependency walk
Robert Boland <robert@markup.co.uk>
parents:
diff changeset
13 elseif ((ord($Str[$i]) & 0xF8) == 0xF0) $n=3; # 11110bbb
077b0a0a3e6d remaining originals according to dependency walk
Robert Boland <robert@markup.co.uk>
parents:
diff changeset
14 elseif ((ord($Str[$i]) & 0xFC) == 0xF8) $n=4; # 111110bb
077b0a0a3e6d remaining originals according to dependency walk
Robert Boland <robert@markup.co.uk>
parents:
diff changeset
15 elseif ((ord($Str[$i]) & 0xFE) == 0xFC) $n=5; # 1111110b
077b0a0a3e6d remaining originals according to dependency walk
Robert Boland <robert@markup.co.uk>
parents:
diff changeset
16 else return false; # Does not match any model
077b0a0a3e6d remaining originals according to dependency walk
Robert Boland <robert@markup.co.uk>
parents:
diff changeset
17 for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ?
077b0a0a3e6d remaining originals according to dependency walk
Robert Boland <robert@markup.co.uk>
parents:
diff changeset
18 if ((++$i == strlen($Str)) || ((ord($Str[$i]) & 0xC0) != 0x80))
077b0a0a3e6d remaining originals according to dependency walk
Robert Boland <robert@markup.co.uk>
parents:
diff changeset
19 return false;
077b0a0a3e6d remaining originals according to dependency walk
Robert Boland <robert@markup.co.uk>
parents:
diff changeset
20 }
077b0a0a3e6d remaining originals according to dependency walk
Robert Boland <robert@markup.co.uk>
parents:
diff changeset
21 }
077b0a0a3e6d remaining originals according to dependency walk
Robert Boland <robert@markup.co.uk>
parents:
diff changeset
22 return true;
077b0a0a3e6d remaining originals according to dependency walk
Robert Boland <robert@markup.co.uk>
parents:
diff changeset
23 }
077b0a0a3e6d remaining originals according to dependency walk
Robert Boland <robert@markup.co.uk>
parents:
diff changeset
24 ?>