DocumentManager::get_text_content()

Complexity

Conditions	20
Paths	72

Size

Total Lines	72
Code Lines	52

Duplication

Lines	0
Ratio	0 %

Importance

Changes

0

<?php
    public static function get_text_content($doc_path, $doc_mime)
    {
        // TODO: review w$ compatibility
        // Use usual exec output lines array to store stdout instead of a temp file
        // because we need to store it at RAM anyway before index on ChamiloIndexer object
        $ret_val = null;
        switch ($doc_mime) {
            case 'text/plain':
                $handle = fopen($doc_path, 'r');
                $output = [fread($handle, filesize($doc_path))];
                fclose($handle);
                break;
            case 'application/pdf':
                exec("pdftotext $doc_path -", $output, $ret_val);
                break;
            case 'application/postscript':
                $temp_file = tempnam(sys_get_temp_dir(), 'chamilo');
                exec("ps2pdf $doc_path $temp_file", $output, $ret_val);
                if ($ret_val !== 0) { // shell fail, probably 127 (command not found)
                    return false;
                }
                exec("pdftotext $temp_file -", $output, $ret_val);
                unlink($temp_file);
                break;
            case 'application/msword':
                exec("catdoc $doc_path", $output, $ret_val);
                break;
            case 'text/html':
                exec("html2text $doc_path", $output, $ret_val);
                break;
            case 'text/rtf':
                // Note: correct handling of code pages in unrtf
                // on debian lenny unrtf v0.19.2 can not, but unrtf v0.20.5 can
                exec("unrtf --text $doc_path", $output, $ret_val);
                if ($ret_val == 127) { // command not found
                    return false;
                }
                // Avoid index unrtf comments
                if (is_array($output) && count($output) > 1) {
                    $parsed_output = [];
                    foreach ($output as &$line) {
                        if (!preg_match('/^###/', $line, $matches)) {
                            if (!empty($line)) {
                                $parsed_output[] = $line;
                            }
                        }
                    }
                    $output = $parsed_output;
                }
                break;
            case 'application/vnd.ms-powerpoint':
                exec("catppt $doc_path", $output, $ret_val);
                break;
            case 'application/vnd.ms-excel':
                exec("xls2csv -c\" \" $doc_path", $output, $ret_val);
                break;
        }

        $content = '';
        if (!is_null($ret_val)) {
            if ($ret_val !== 0) { // shell fail, probably 127 (command not found)
                return false;
            }
        }
        if (isset($output)) {
            foreach ($output as &$line) {
                $content .= $line."\n";
            }

            return $content;
        } else {
            return false;
        }