libretube/content/pages/buscar.php.md

196 lines
8.0 KiB
Markdown

Author: Jorge Maldonado Ventura
Date: 2017-04-22 20:38
Modified: 2020-06-11 11:38
Save_as: buscar.php
Status: hidden
Title: Resultados
<main class="row main-videos">
<?php
$STOP_WORDS = ['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n',
'ñ', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z',
'un', 'una', 'unas', 'unos', 'uno', 'sobre', 'todo',
'también', 'tras', 'otro', 'algun', 'alguno', 'alguna', 'algunos',
'algunas', 'ser', 'es', 'soy', 'eres', 'somos', 'sois', 'estoy', 'esta',
'estamos', 'estais', 'estan', 'como', 'en', 'para', 'atras', 'porque',
'por', 'que', 'estado', 'estaba', 'ante', 'antes', 'siendo', 'ambos',
'pero', 'por', 'poder', 'puede', 'puedo', 'podemos', 'podeis', 'pueden',
'fui', 'fue', 'fuimos', 'fueron', 'hacer', 'hago', 'hace', 'hacemos',
'haceis', 'hacen', 'cada', 'fin', 'incluso', 'primero', 'desde',
'conseguir', 'consigo', 'consigue', 'consigues', 'conseguimos',
'consiguen', 'ir', 'voy', 'va', 'vamos', 'vais', 'van', 'vaya', 'gueno',
'ha', 'tener', 'tengo', 'tiene', 'tenemos', 'teneis', 'tienen', 'el', 'la',
'lo', 'las', 'los', 'su', 'aqui', 'mio', 'tuyo', 'ellos', 'ellas', 'nos',
'nosotros', 'vosotros', 'vosotras', 'si', 'dentro', 'solo', 'solamente',
'saber', 'sabes', 'sabe', 'sabemos', 'sabeis', 'saben', 'ultimo', 'largo',
'bastante', 'haces', 'muchos', 'aquellos', 'aquellas', 'sus', 'entonces',
'tiempo', 'verdad', 'verdadero', 'verdadera', 'cierto', 'ciertos',
'cierta', 'ciertas', 'intentar', 'intento', 'intenta', 'intentas',
'intentamos', 'intentais', 'intentan', 'dos', 'bajo', 'arriba', 'encima',
'usar', 'uso', 'usas', 'usa', 'usamos', 'usais', 'usan', 'emplear',
'empleo', 'empleas', 'emplean', 'ampleamos', 'empleais', 'valor', 'muy',
'era', 'eras', 'eramos', 'eran', 'modo', 'bien', 'cual', 'cuando', 'donde',
'mientras', 'quien', 'con', 'entre', 'sin', 'trabajo', 'trabajar',
'trabajas', 'trabaja', 'trabajamos', 'trabajais', 'trabajan', 'podria',
'podrias', 'podriamos', 'podrian', 'podriais', 'yo', 'aquel'];
$web_content = json_decode(file_get_contents('tipuesearch_content.json'), true);
$stop_words_ignored = false;
if (isset($_GET['q']) && !empty($_GET['q'])) {
$search_str = trim($_REQUEST['q']);
$keywords = explode(' ', $search_str);
$keywords_temp = NULL;
foreach ($keywords as $keyword) {
$is_stop_word = false;
foreach ($STOP_WORDS as $stop_word) {
if ($keyword == $stop_word) {
$is_stop_word = true;
$stop_words_ignored = true;
break;
}
}
if (! $is_stop_word) {
$keywords_temp .= "{$keyword} ";
}
}
$keywords = trim($keywords_temp);
$keywords = explode(' ', $keywords);
$found_results = [];
foreach ($web_content["videos"] as $page) {
$score = 0;
$page['description'] = htmlentities($page['description']);
// convert keyworks_tags to strings
$tags = implode(", ", $page['keywords']);
foreach ($keywords as $word) {
if (preg_match("/$word/i", $page['url'])) {
$score += 35;
}
if (preg_match("/$word/i", $page['title'])) {
$score += 35;
}
if (preg_match("/$word/i", $tags)) {
$score += 35;
}
if (preg_match("/$word/i", $page['category'])) {
$score += 30;
}
// It replaces uppercase matches with lowercase matches, but it's fine for now.
if ($stop_words_ignored == 1) {
$page['description'] = preg_replace("/$word/i", $word, $page['description'], -1, $match_count);
} else {
$page['description'] = preg_replace("/$word/i", $word, $page['description'], -1, $match_count);
}
if ($match_count > 0) {
$score += 10 * $match_count;
}
}
if ($score != 0) {
$found_results[] = [
'score' => $score,
'title' => $page['title'],
'time' => $page['time'],
'videoThumbnail' => $page['videoThumbnail'],
'url' => $page['url'],
'published' => $page['published'],
'publishedText' => $page['publishedText'],
'author' => $page['author'],
'authorUrl' => $page['authorUrl'],
];
}
}
/**
* Compare results score.
*/
function comp_result_score($a, $b) {
if ($a['score'] == $b['score']) {
return 0;
}
return ($a['score'] > $b['score']) ? -1 : 1;
};
if ($stop_words_ignored) {
printf('
<div class="col-md-12 text-justify">
<h6 class="tab">%s</h6>
<hr>
</div>', 'Algunas palabras «comunes» fueron ignoradas');
}
$found_results_count = count($found_results);
if ($found_results_count > 0) {
usort($found_results, 'comp_result_score');
if ($found_results_count == 1) {
$found_results_count_str = NULL;
}
} else if ($found_results_count == 0) {
$found_results_count_str = NULL;
printf('<div id="tipue_search_warning">%s</div>', 'No se ha encontrado nada');
}
// Init head
printf('
<div class="col-md-12">
<div class="row">');
foreach ($found_results as $found_result) {
printf('
<article class="col-md-3 video" itemscope itemtype="https://schema.org/Movie">
<a href="%s">
<div class="area">
<div class="mask">
<div class="vertical-align">
<i class="soumaicon play"><svg><use href="/theme/images/svg/master.svg#play"></use></svg></i>
</div>
</div>
<img itemprop="image" src="%s" alt="%s" class="img-fluid">
<span class="duration">%s</span>
</div>
</a>
<h2 itemprop="name">
<a href="%s" rel="bookmark" title="Ver %s">%s</a>
</h2>
<!-- post footer -->
<footer class="card-content-footer mb-4">
<span class="soumaicon text-info">
<svg>
<use href="/theme/images/svg/master.svg#calendar"></use>
</svg>
</span>
<time class="entry-date published" datetime="%s" itemprop="datePublished">
<small>%s</small>
</time>
<span class="soumaicon text-info">
<svg>
<use href="/theme/images/svg/master.svg#user"></use>
</svg>
</span>
<small itemprop="director" itemscope itemtype="https://schema.org/Person">
<a href="%s" title="Autor del artículo" itemprop="name">%s</a>
</small>
</footer>
<!-- end of post footer -->
</article>',
$found_result['url'], $found_result['videoThumbnail'], $found_result['title'],
$found_result['time'], $found_result['url'], $found_result['title'],
$found_result['title'], $found_result['published'], $found_result['publishedText'],
$found_result['authorUrl'], $found_result['author']);
}
} else {
printf('<div id="tipue_search_warning">%s</div>', 'Aún no has buscado');
}
// End head
printf('</div>
</div>');
?>
</main>