sbrl-github/Pepperminty-Wiki
sbrl-github
/
Pepperminty-Wiki
mirror of https://github.com/sbrl/Pepperminty-Wiki.git
1
0
Fork 0
Code

begin playing around with indexing

This commit is contained in:
Starbeamrainbowlabs 2015-10-27 21:10:05 +00:00
parent 6e2faf6250
commit db7bf0f7ec
3 changed files with 144 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

68
build/index.php
View File

@ -1249,6 +1249,74 @@ register_module([
register_module([
"name" => "Search",
"version" => "0.1",
"author" => "Starbeamrainbowlabs",
"description" => "Adds proper search functionality to Pepperminty Wiki. Note that this module, at the moment, just contains test code while I figure out how best to write a search engine.",
"id" => "feature-search",
"code" => function() {
add_action("index", function() {
global $settings, $env;
$breakable_chars = "\r\n\t .,\\/!\"£$%^&*[]()+`_~#";
header("content-type: text/plain");
$source = file_get_contents("$env->page.md");
$source_length = strlen($source);
$index = [];
var_dump($env->page);
var_dump($source);
echo("source length: $source_length\n");
$basepos = 0;
$scanpos = $basepos;
while($basepos < $source_length)
{
$word = "";
do {
// Break if we reach the end of the source text
if($scanpos >= $source_length) break;
$word .= $source[$scanpos];
$scanpos++;
} while(strpos($breakable_chars, $source[$scanpos]) === false);
// Move the base position up to the scan position (plus one to
// skip over the breakable character), saving the old base
// position for later
$word_start_pos = $basepos;
$basepos = $scanpos + 1;
// Continue if the word is empty
if(strlen($word) === 0) continue;
// Normalise the word to be lowercase
$word = strtolower($word);
var_dump($word);
// Initialise the entry in the index if it doesn't exist
if(!isset($index[$word]))
{
$index[$word] = [
"freq" => 0,
"offsets" => []
];
}
// Update the index entry
$index[$word]["freq"]++;
$index[$word]["offsets"][] = $word_start_pos;
}
var_dump($index);
});
}
]);
register_module([
"name" => "Uploader",
"version" => "0.1",

9
module_index.json
View File

@ -44,6 +44,15 @@
"lastupdate": 1445170746,
"optional": false
},
{
"name": "Search",
"version": "0.1",
"author": "Starbeamrainbowlabs",
"description": "Adds proper search functionality to Pepperminty Wiki. Note that this module, at the moment, just contains test code while I figure out how best to write a search engine.",
"id": "feature-search",
"lastupdate": 1445980152,
"optional": false
},
{
"name": "Uploader",
"version": "0.1",

67
modules/feature-search.php Normal file
View File

@ -0,0 +1,67 @@
<?php
register_module([
"name" => "Search",
"version" => "0.1",
"author" => "Starbeamrainbowlabs",
"description" => "Adds proper search functionality to Pepperminty Wiki. Note that this module, at the moment, just contains test code while I figure out how best to write a search engine.",
"id" => "feature-search",
"code" => function() {
add_action("index", function() {
global $settings, $env;
$breakable_chars = "\r\n\t .,\\/!\"£$%^&*[]()+`_~#";
header("content-type: text/plain");
$source = file_get_contents("$env->page.md");
$source_length = strlen($source);
$index = [];
var_dump($env->page);
var_dump($source);
echo("source length: $source_length\n");
$basepos = 0;
$scanpos = $basepos;
while($basepos < $source_length)
{
$word = "";
do {
// Break if we reach the end of the source text
if($scanpos >= $source_length) break;
$word .= $source[$scanpos];
$scanpos++;
} while(strpos($breakable_chars, $source[$scanpos]) === false);
// Move the base position up to the scan position (plus one to
// skip over the breakable character), saving the old base
// position for later
$word_start_pos = $basepos;
$basepos = $scanpos + 1;
// Continue if the word is empty
if(strlen($word) === 0) continue;
// Normalise the word to be lowercase
$word = strtolower($word);
var_dump($word);
// Initialise the entry in the index if it doesn't exist
if(!isset($index[$word]))
{
$index[$word] = [
"freq" => 0,
"offsets" => []
];
}
// Update the index entry
$index[$word]["freq"]++;
$index[$word]["offsets"][] = $word_start_pos;
}
var_dump($index);
});
}
]);
?>