1
0
Fork 0
mirror of https://github.com/sbrl/Pepperminty-Wiki.git synced 2024-11-25 17:23:00 +00:00

Enhance utf8 support in id index & search system, but there's more work to be done.

This commit is contained in:
Starbeamrainbowlabs 2018-03-18 16:19:13 +00:00
parent 20e7c9f0fb
commit 24efac3c5e
Signed by: sbrl
GPG key ID: 1BE5172E637709C2
5 changed files with 31 additions and 22 deletions

View file

@ -71,8 +71,13 @@ A live demo of the latest stable version can be found over at [my website](//sta
### Requirements
- PHP-enabled webserver (must be PHP 7+)
- PHP session support (for logging in, see [here](https://php.net/manual/en/session.installation.php) for more information)
- The following PHP extensions: mbstring, imagick (for preview generation), fileinfo (for proper mime type checking of uploaded files), and zip (for compress exports)
- Write access to own folder (only for editing)
- The following PHP extensions:
- `mbstring`
- `imagick` (for preview generation)
- `fileinfo` (for proper mime type checking of uploaded files)
- `zip` (for compressing exports)
- `intl` (for Unicode text normalization when searching and in the id index)
- Write access to Pepperminty Wiki's own folder (only for editing)
### Getting your own copy
Setting up your own copy of Pepperminty Wiki is easy. Since Pepperminty Wiki works on a module based system, all you need to do is choose the modules you want installed, and then configure your new installation so that it fits your needs. There are several ways to do this:

View file

@ -1286,7 +1286,7 @@ class ids
foreach ($idindex as $id => $entry)
{
if($entry == $pagename)
if(Normalizer::normalize($entry, Normalizer::FORM_C) == Normalizer::normalize($pagename, Normalizer::FORM_C))
return $id;
}
@ -1318,14 +1318,14 @@ class ids
* that the destination name doesn't already exist.
* @package core
* @param string $oldpagename The old page name to move.
* @param string $newpagename The new pagee name to move the old page name to.
* @param string $newpagename The new page name to move the old page name to.
*/
public static function movepagename($oldpagename, $newpagename)
{
global $idindex, $paths;
$pageid = self::getid($oldpagename);
$idindex->$pageid = $newpagename;
$pageid = self::getid(Normalizer::normalize($oldpagename, Normalizer::FORM_C));
$idindex->$pageid = Normalizer::normalize($newpagename, Normalizer::FORM_C);
file_put_contents($paths->idindex, json_encode($idindex));
}
@ -1380,6 +1380,8 @@ class ids
{
global $idindex, $paths;
$pagename = Normalizer::normalize($pagename, Normalizer::FORM_C);
$nextid = count(array_keys(get_object_vars($idindex)));
// Increment the generated id until it's unique
while(isset($idindex->nextid))
@ -3682,7 +3684,7 @@ register_module([
/**
* @api {get} ?action=idindex-show Show the id index
* @apiDescription Outputs the id index. Useful if you need to verify that it's working as expected.
* @apiDescription Outputs the id index. Useful if you need to verify that it's working as expected. Output is a json object.
* @apiName SearchShowIdIndex
* @apiGroup Search
* @apiPermission Anonymous
@ -4142,7 +4144,7 @@ class search
public static function tokenize($source)
{
$source = strtolower($source);
$source = str_replace([ '[', ']', '|', '{', '}', '/' ], " ", $source);
$source = preg_replace('/[\[\]\|\{\}\/]/u', " ", $source);
return preg_split("/((^\p{P}+)|(\p{P}*\s+\p{P}*)|(\p{P}+$))|\|/u", $source, -1, PREG_SPLIT_NO_EMPTY);
}
@ -4154,7 +4156,7 @@ class search
*/
public static function strip_markup($source)
{
return str_replace([ "[", "]", "\"", "*", "_", " - ", "`" ], "", $source);
return preg_replace('/([\"*_\[\]]| - |`)/u', "", $source);
}
/**
@ -4181,7 +4183,7 @@ class search
{
$page_filename = $env->storage_prefix . $pagedetails->filename;
if(!file_exists($page_filename)) {
echo("data: [" . ($i + 1) . " / $max] Error: Can't find $page_filename");
echo("data: [" . ($i + 1) . " / $max] Error: Can't find $page_filename\n");
flush();
$missing_files++;
continue;
@ -4497,7 +4499,7 @@ class search
return ($a[1] > $b[1]) ? +1 : -1;
});
$sourceLength = strlen($source);
$sourceLength = mb_strlen($source);
$contexts = [];
$basepos = 0;
@ -4569,7 +4571,7 @@ class search
if(in_array($qterm, static::$stop_words))
continue;
// From http://stackoverflow.com/a/2483859/1460422
$context = preg_replace("/" . str_replace("/", "\/", preg_quote($qterm)) . "/i", "<strong class='search-term-highlight'>$0</strong>", $context);
$context = preg_replace("/" . str_replace("/", "\/", preg_quote($qterm)) . "/iu", "<strong class='search-term-highlight'>$0</strong>", $context);
}
return $context;

View file

@ -910,7 +910,7 @@ class ids
foreach ($idindex as $id => $entry)
{
if($entry == $pagename)
if(Normalizer::normalize($entry, Normalizer::FORM_C) == Normalizer::normalize($pagename, Normalizer::FORM_C))
return $id;
}
@ -942,14 +942,14 @@ class ids
* that the destination name doesn't already exist.
* @package core
* @param string $oldpagename The old page name to move.
* @param string $newpagename The new pagee name to move the old page name to.
* @param string $newpagename The new page name to move the old page name to.
*/
public static function movepagename($oldpagename, $newpagename)
{
global $idindex, $paths;
$pageid = self::getid($oldpagename);
$idindex->$pageid = $newpagename;
$pageid = self::getid(Normalizer::normalize($oldpagename, Normalizer::FORM_C));
$idindex->$pageid = Normalizer::normalize($newpagename, Normalizer::FORM_C);
file_put_contents($paths->idindex, json_encode($idindex));
}
@ -1004,6 +1004,8 @@ class ids
{
global $idindex, $paths;
$pagename = Normalizer::normalize($pagename, Normalizer::FORM_C);
$nextid = count(array_keys(get_object_vars($idindex)));
// Increment the generated id until it's unique
while(isset($idindex->nextid))

View file

@ -104,7 +104,7 @@
"author": "Starbeamrainbowlabs",
"description": "Adds proper search functionality to Pepperminty Wiki using an inverted index to provide a full text search engine. If pages don't show up, then you might have hit a stop word. If not, try requesting the `invindex-rebuild` action to rebuild the inverted index from scratch.",
"id": "feature-search",
"lastupdate": 1518649628,
"lastupdate": 1521389882,
"optional": false
},
{

View file

@ -544,7 +544,7 @@ class search
public static function tokenize($source)
{
$source = strtolower($source);
$source = str_replace([ '[', ']', '|', '{', '}', '/' ], " ", $source);
$source = preg_replace('/[\[\]\|\{\}\/]/u', " ", $source);
return preg_split("/((^\p{P}+)|(\p{P}*\s+\p{P}*)|(\p{P}+$))|\|/u", $source, -1, PREG_SPLIT_NO_EMPTY);
}
@ -556,7 +556,7 @@ class search
*/
public static function strip_markup($source)
{
return str_replace([ "[", "]", "\"", "*", "_", " - ", "`" ], "", $source);
return preg_replace('/([\"*_\[\]]| - |`)/u', "", $source);
}
/**
@ -583,7 +583,7 @@ class search
{
$page_filename = $env->storage_prefix . $pagedetails->filename;
if(!file_exists($page_filename)) {
echo("data: [" . ($i + 1) . " / $max] Error: Can't find $page_filename");
echo("data: [" . ($i + 1) . " / $max] Error: Can't find $page_filename\n");
flush();
$missing_files++;
continue;
@ -899,7 +899,7 @@ class search
return ($a[1] > $b[1]) ? +1 : -1;
});
$sourceLength = strlen($source);
$sourceLength = mb_strlen($source);
$contexts = [];
$basepos = 0;
@ -971,7 +971,7 @@ class search
if(in_array($qterm, static::$stop_words))
continue;
// From http://stackoverflow.com/a/2483859/1460422
$context = preg_replace("/" . str_replace("/", "\/", preg_quote($qterm)) . "/i", "<strong class='search-term-highlight'>$0</strong>", $context);
$context = preg_replace("/" . str_replace("/", "\/", preg_quote($qterm)) . "/iu", "<strong class='search-term-highlight'>$0</strong>", $context);
}
return $context;