inverted_index.php

<?php
// build an inverted index
// https://en.m.wikipedia.org/wiki/Inverted_index

function buildInvertedIndex(array $filenames): array
{
    $invertedIndex = [];
 
    foreach($filenames as $filename) {
        $data = file_get_contents($filename);
 
        if ($data === false) {
            die('Unable to read file: '.$filename);
        }
 
        // collect words in files
        preg_match_all('/(\w+)/', $data, $matches, PREG_SET_ORDER);
 
        foreach($matches as $match) {
            $word = strtolower($match[0]);
 
            // add an entry for a (new) word
            if (!array_key_exists($word, $invertedIndex)) {
                $invertedIndex[$word] = [];
            }
            // add an entry for a (new) filename
            if (!in_array($filename, $invertedIndex[$word], true)) {
                $invertedIndex[$word][] = $filename;
            }
        }
    }
 
    return $invertedIndex;
}
 
// search for a word in the index and returns filenames (array) or false
function lookupWord($invertedIndex, $word)
{
    return array_key_exists($word, $invertedIndex) ? $invertedIndex[$word] : false;
}

test_inverted_index.php

<?php
$invertedIndex = buildInvertedIndex(['file1.txt', 'file2.txt', 'file3.txt']);
 
foreach(['cat', 'dog'] as $word) {
    $matches = lookupWord($invertedIndex, $word);
 
    if ($matches !== false) {
        echo 'Found the word "$word" in files: '.implode(', ', $matches)."\n";
    } else {
        echo 'Unable to find the word "$word" in the index'."\n";
    }
}