Smalot\PdfParser\PDFObject::cleanContent()

Complexity

Conditions	9
Paths	55

Size

Total Lines	116
Code Lines	54

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	56
CRAP Score	9.0033

Importance

Changes

0

<?php
    public function cleanContent(?string $content): string
    {
        if (null == $content) {
            return '';
        }

        // Find all strings () and replace them so they aren't affected
        // by the next steps
        $pdfstrings = [];
        $attempt = '(';
        while (preg_match('/'.preg_quote($attempt, '/').'.*?(?<![^\\\\]\\\\)\)/s', $content, $text)) {
            // PDF strings can contain unescaped parentheses as long as
            // they're balanced, so check for balanced parentheses
            $left = preg_match_all('/(?<![^\\\\]\\\\)\(/', $text[0]);
            $right = preg_match_all('/(?<![^\\\\]\\\\)\)/', $text[0]);

            if ($left == $right) {
                // Replace the string with a unique placeholder
                $id = uniqid('STRING_', true);
                $pdfstrings[$id] = $text[0];
                $content = preg_replace(
                    '/'.preg_quote($text[0], '/').'/',
                    '@@@'.$id.'@@@',
                    $content,
                    1
                );

                // Reset to search for the next string
                $attempt = '(';
            } else {
                // We had unbalanced parentheses, so use the current
                // match as a base to find a longer string
                $attempt = $text[0];
            }
        }

        // Remove all carriage returns and line-feeds from the document stream
        $content = str_replace(["\r", "\n"], ' ', trim($content));

        // Find all dictionary << >> commands and replace them so they
        // aren't affected by the next steps
        $dictstore = [];
        while (preg_match('/(<<.*?>> *)(BDC|BMC|DP|MP)/', $content, $dicttext)) {
            $dictid = uniqid('DICT_', true);
            $dictstore[$dictid] = $dicttext[1];
            $content = preg_replace(
                '/'.preg_quote($dicttext[0], '/').'/',
                ' ###'.$dictid.'###'.$dicttext[2],
                $content,
                1
            );
        }

        // Now that all strings and dictionaries are hidden, the only
        // PDF commands left should all be plain text.
        // Detect MIME-type of the current string and prevent reading
        // content streams that are images, etc. This prevents PHP
        // error messages when JPEG content is sent to this function
        // by the sample file '12249.pdf' from:
        // https://github.com/smalot/pdfparser/issues/458
        $finfo = new \finfo(\FILEINFO_MIME);
        if (false === strpos($finfo->buffer($content), 'text/plain')) {
            return '';
        }

        // Normalize white-space in the document stream
        $content = preg_replace('/\s{2,}/', ' ', $content);

        // Find all valid PDF operators and add \r\n after each; this
        // ensures there is just one command on every line
        // Source: https://ia801001.us.archive.org/1/items/pdf1.7/pdf_reference_1-7.pdf - Appendix A
        // Source: https://archive.org/download/pdf320002008/PDF32000_2008.pdf - Annex A
        // Note: PDF Reference 1.7 lists 'I' and 'rI' as valid commands, while
        //       PDF 32000:2008 lists them as 'i' and 'ri' respectively. Both versions
        //       appear here in the list for completeness.
        $operators = [
          'b*', 'b', 'BDC', 'BMC', 'B*', 'BI', 'BT', 'BX', 'B', 'cm', 'cs', 'c', 'CS',
          'd0', 'd1', 'd', 'Do', 'DP', 'EMC', 'EI', 'ET', 'EX', 'f*', 'f', 'F', 'gs',
          'g', 'G',  'h', 'i', 'ID', 'I', 'j', 'J', 'k', 'K', 'l', 'm', 'MP', 'M', 'n',
          'q', 'Q', 're', 'rg', 'ri', 'rI', 'RG', 'scn', 'sc', 'sh', 's', 'SCN', 'SC',
          'S', 'T*', 'Tc', 'Td', 'TD', 'Tf', 'TJ', 'Tj', 'TL', 'Tm', 'Tr', 'Ts', 'Tw',
          'Tz', 'v', 'w', 'W*', 'W', 'y', '\'', '"',
        ];
        foreach ($operators as $operator) {
            $content = preg_replace(
                '/(?<!\w|\/)'.preg_quote($operator, '/').'(?![\w10\*])/',
                $operator."\r\n",
                $content
            );
        }

        // Restore the original content of the dictionary << >> commands
        $dictstore = array_reverse($dictstore, true);
        foreach ($dictstore as $id => $dict) {
            $content = str_replace('###'.$id.'###', $dict, $content);
        }

        // Restore the original string content
        $pdfstrings = array_reverse($pdfstrings, true);
        foreach ($pdfstrings as $id => $text) {
            // Strings may contain escaped newlines, or literal newlines
            // and we should clean these up before replacing the string
            // back into the content stream; this ensures no strings are
            // split between two lines (every command must be on one line)
            $text = str_replace(
                ["\\\r\n", "\\\r", "\\\n", "\r", "\n"],
                ['', '', '', '\r', '\n'],
                $text
            );

            $content = str_replace('@@@'.$id.'@@@', $text, $content);
        }

        $content = trim(preg_replace(['/(\r\n){2,}/', '/\r\n +/'], "\r\n", $content));

        return $content;
    }