2012-04-10 23:18:20 +02:00
|
|
|
<?php
|
|
|
|
|
|
|
|
final class PhabricatorSlug {
|
|
|
|
|
|
|
|
public static function normalize($slug) {
|
|
|
|
$slug = preg_replace('@/+@', '/', $slug);
|
|
|
|
$slug = trim($slug, '/');
|
Allow slugs to contain most utf8 characters
Summary:
Ref T2632. Fixes T1466.
Currently, we normalize slugs (and thus Phriction URIs and canonical project names) to a small number of latin characters. Instead, blacklist a few characters and permit everything else (including utf8 characters).
When generating Phriction URIs, encode any utf8 characters. This means we render URIs encoded, but browsers handle this fine and display them readably in the URI and address bar, etc.
The blacklisted characters are mostly for practical reasons: \x00-\x19 are control characters, `#%?` are meaningful in URIs, `+` is sometimes configured to be interprted as space by apache, etc., `<>\\` are just silly, `&= ` are largely cosmetic.
This allows some silly stuff, like generating URIs with zero-width spaces and RTL markers in them. Possibly we should go blacklist those characters at some point.
Depends on: D5191
Test Plan: {F34402}
Reviewers: AnhNhan, chad, vrana
Reviewed By: chad
CC: aran
Maniphest Tasks: T1466, T2632
Differential Revision: https://secure.phabricator.com/D5192
2013-03-03 19:56:33 +01:00
|
|
|
$slug = phutil_utf8_strtolower($slug);
|
|
|
|
$slug = preg_replace("@[\\x00-\\x19#%&+=\\\\?<> ]+@", '_', $slug);
|
|
|
|
$slug = preg_replace('@_+@', '_', $slug);
|
2012-04-10 23:18:20 +02:00
|
|
|
$slug = trim($slug, '_');
|
|
|
|
|
|
|
|
return $slug.'/';
|
|
|
|
}
|
|
|
|
|
|
|
|
public static function getDefaultTitle($slug) {
|
|
|
|
$parts = explode('/', trim($slug, '/'));
|
|
|
|
$default_title = end($parts);
|
|
|
|
$default_title = str_replace('_', ' ', $default_title);
|
Allow slugs to contain most utf8 characters
Summary:
Ref T2632. Fixes T1466.
Currently, we normalize slugs (and thus Phriction URIs and canonical project names) to a small number of latin characters. Instead, blacklist a few characters and permit everything else (including utf8 characters).
When generating Phriction URIs, encode any utf8 characters. This means we render URIs encoded, but browsers handle this fine and display them readably in the URI and address bar, etc.
The blacklisted characters are mostly for practical reasons: \x00-\x19 are control characters, `#%?` are meaningful in URIs, `+` is sometimes configured to be interprted as space by apache, etc., `<>\\` are just silly, `&= ` are largely cosmetic.
This allows some silly stuff, like generating URIs with zero-width spaces and RTL markers in them. Possibly we should go blacklist those characters at some point.
Depends on: D5191
Test Plan: {F34402}
Reviewers: AnhNhan, chad, vrana
Reviewed By: chad
CC: aran
Maniphest Tasks: T1466, T2632
Differential Revision: https://secure.phabricator.com/D5192
2013-03-03 19:56:33 +01:00
|
|
|
$default_title = phutil_utf8_ucwords($default_title);
|
|
|
|
$default_title = nonempty($default_title, pht('Untitled Document'));
|
2012-04-10 23:18:20 +02:00
|
|
|
return $default_title;
|
|
|
|
}
|
|
|
|
|
|
|
|
public static function getAncestry($slug) {
|
|
|
|
$slug = self::normalize($slug);
|
|
|
|
|
|
|
|
if ($slug == '/') {
|
|
|
|
return array();
|
|
|
|
}
|
|
|
|
|
|
|
|
$ancestors = array(
|
|
|
|
'/',
|
|
|
|
);
|
|
|
|
|
|
|
|
$slug = explode('/', $slug);
|
|
|
|
array_pop($slug);
|
|
|
|
array_pop($slug);
|
|
|
|
|
|
|
|
$accumulate = '';
|
|
|
|
foreach ($slug as $part) {
|
|
|
|
$accumulate .= $part.'/';
|
|
|
|
$ancestors[] = $accumulate;
|
|
|
|
}
|
|
|
|
|
|
|
|
return $ancestors;
|
|
|
|
}
|
|
|
|
|
|
|
|
public static function getDepth($slug) {
|
|
|
|
$slug = self::normalize($slug);
|
|
|
|
if ($slug == '/') {
|
|
|
|
return 0;
|
|
|
|
} else {
|
|
|
|
return substr_count($slug, '/');
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
}
|