Add Spaces Revisited
Revisiting the add_nbsps() and add_spaces() function patterns. It gets activated by the show_spaces option in the config as well as in the usersettings.
What it should do and what not. Now we have Unicode and some patterns may be useful only in a certain context, here we can set different patterns for Chinese if we have to.
I build a test action and feed this action with different test data to show what it does on each pattern iteration.
Additional we should define a set of tags to determine in which context the result should differ.
- Latin
- Cyrillic
- Chinese
- Farsi
- Hindi
Example tags:
日本語123
ABCD123
Abcd123
AbCd123
abcd123
123日本語
123ABCD
123Abcd
123AbCd
123abcd
ABCD123
Abcd123
AbCd123
abcd123
123日本語
123ABCD
123Abcd
123AbCd
123abcd
1. Test Action
action/test_addspaces.php
<?php
if (!defined('IN_WACKO'))
{
exit;
}
$info = <<<EOD
Description:
Shows tags with applied show_spaces setting.
Usage:
{{test_addspaces}}
Options:
[set="tag1, tag2, ..."]
a comma-delimited list of tag names
[debug=0|1]
shows result for each processed pattern
EOD;
// set defaults
$help ??= 0;
$set ??= '';
$debug ??= 0;
if ($help)
{
$tpl->help = $this->help($info, 'blog');
return;
}
if ($set)
{
$_tags = explode(',', $set);
$tags = array_map('trim', $_tags);
$tags = array_map($this->sanitize_page_tag, $tags);
}
if (!$tags)
{
$tags = [
'日本語123',
'ABCD123',
'Abcd123',
'AbCd123',
'abcd123',
'123日本語',
'123ABCD',
'123Abcd',
'123AbCd',
'123abcd',
];
}
# Ut::debug_print_r($tags);
$addspaces = function ($text, $debug) use ($tpl)
{
$i = 1;
$patterns =[
['(' . self::PATTERN['ALPHANUM'] . ')(' . self::PATTERN['UPPERNUM'] . ')', '\\1' . NBSP . '\\2'],
['(' . self::PATTERN['UPPERNUM'] . ')(' . self::PATTERN['UPPERNUM'] . ')', '\\1' . NBSP . '\\2'],
['(' . self::PATTERN['ALPHANUM'] . ')\/', '\\1' . NBSP . '/'],
['(' . self::PATTERN['UPPER'] . ')' . NBSP . '(?=' . self::PATTERN['UPPER'] . NBSP . self::PATTERN['UPPERNUM'] . ')', '\\1'],
['(' . self::PATTERN['UPPER'] . ')' . NBSP . '(?=' . self::PATTERN['UPPER'] . NBSP . '\/)', '\\1'],
['\/(' . self::PATTERN['ALPHANUM'] . ')', '/' . NBSP . '\\1'],
['(' . self::PATTERN['UPPERNUM'] . ')' . NBSP . '(' . self::PATTERN['UPPERNUM'] . ')($|\b)', '\\1\\2'],
# ['(\d)(' . self::PATTERN['ALPHA'] . ')', '\\1' . NBSP . '\\2'],
# ['(' . self::PATTERN['ALPHA'] . ')(\d)', '\\1' . NBSP . '\\2'],
# ['(\d)' . NBSP . '(?=\d)', '\\1'],
['(\d)' . NBSP . '(?!' . self::PATTERN['ALPHA'] . ')', '\\1'],
];
$tpl->enter($debug ? 'debug_' : 'result_');
$tpl->text = $text;
$tpl->enter('l_');
foreach ($patterns as $pattern)
{
$text = preg_replace('/' . $pattern[0] . '/u', $pattern[1], $text);
if ($debug)
{
$tpl->n = $i;
$tpl->pattern0 = $pattern[0];
$tpl->pattern1 = $pattern[1];
$tpl->text = $text;
$i++;
}
}
$tpl->leave();
$tpl->result = $text;
$tpl->leave();
};
foreach ($tags as $tag)
{
$this->sanitize_page_tag($tag);
$addspaces($tag, $debug);
}
action/template/test_addspaces.tpl
[ === main === ] [ ' help ' ] <table class="hl-line"> [= debug _ = <tr> <th>Pattern</th> <td></td> <td></td> <td><strong>[ ' text | e ' ]:</strong></td> </tr> [= l _ = <tr> <td>[ ' n ' ]. <code>[ ' pattern0 | e ' ]</code></td> <td>⇨ <code>[ ' pattern1 | e ' ]</code></td> <td> ↳ </td> <td>[ ' text | e ' ]</td> </tr> =] <tr> <td colspan=4><hr><br></td> </tr> =] [= result _ = <tr> <td>[ ' text | e ' ]</td> <td> → </td> <td>[ ' result | e ' ]</td> </tr> =] </table>
2. 4.2
<?php
$text = preg_replace("/(".$this->language["ALPHANUM"].")(".$this->language["UPPERNUM"].")/","\\1 \\2",$text);
$text = preg_replace("/(".$this->language["UPPERNUM"].")(".$this->language["UPPERNUM"].")/","\\1 \\2",$text);
$text = preg_replace("/(".$this->language["ALPHANUM"].")\//","\\1 /",$text);
$text = preg_replace("/(".$this->language["UPPER"].") (?=".$this->language["UPPER"]." ".$this->language["UPPERNUM"].")/","\\1",$text);
$text = preg_replace("/(".$this->language["UPPER"].") (?=".$this->language["UPPER"]." \/)/","\\1",$text);
$text = preg_replace("/\/(".$this->language["ALPHANUM"].")/","/ \\1",$text);
$text = preg_replace("/(".$this->language["UPPERNUM"].") (".$this->language["UPPERNUM"].")($|\b)/","\\1\\2",$text);
$text = preg_replace("/([0-9])(".$this->language["ALPHA"].")/","\\1 \\2",$text);
$text = preg_replace("/(".$this->language["ALPHA"].")([0-9])/","\\1 \\2",$text);
$text = preg_replace("/([0-9]) (?=[0-9])/","\\1",$text);
3. 6.1
<?php
$patterns =[
['(' . self::PATTERN['ALPHANUM'] . ')(' . self::PATTERN['UPPERNUM'] . ')', '\\1' . NBSP . '\\2'],
['(' . self::PATTERN['UPPERNUM'] . ')(' . self::PATTERN['UPPERNUM'] . ')', '\\1' . NBSP . '\\2'],
['(' . self::PATTERN['ALPHANUM'] . ')\/', '\\1' . NBSP . '/'],
['(' . self::PATTERN['UPPER'] . ')' . NBSP . '(?=' . self::PATTERN['UPPER'] . NBSP . self::PATTERN['UPPERNUM'] . ')', '\\1'],
['(' . self::PATTERN['UPPER'] . ')' . NBSP . '(?=' . self::PATTERN['UPPER'] . NBSP . '\/)', '\\1'],
['\/(' . self::PATTERN['ALPHANUM'] . ')', '/' . NBSP . '\\1'],
['(' . self::PATTERN['UPPERNUM'] . ')' . NBSP . '(' . self::PATTERN['UPPERNUM'] . ')($|\b)', '\\1\\2'],
# ['(\d)(' . self::PATTERN['ALPHA'] . ')', '\\1' . NBSP . '\\2'],
# ['(' . self::PATTERN['ALPHA'] . ')(\d)', '\\1' . NBSP . '\\2'],
# ['(\d)' . NBSP . '(?=\d)', '\\1'],
['(\d)' . NBSP . '(?!' . self::PATTERN['ALPHA'] . ')', '\\1'],
];