Smalot\PdfParser\PDFObject::formatContent()

Complexity

Conditions	19
Paths	386

Size

Total Lines	177
Code Lines	83

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	93
CRAP Score	19

Importance

Changes	2
Bugs	1	Features	0

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

        // Outside of (String) content in PDF document streams, all
        // text should conform to UTF-8. Test for binary content by
        // deleting everything after the first open-parenthesis ( which
        // indicates the beginning of a string. Then test what remains
        // for valid UTF-8. If it's not UTF-8, return an empty string
        // as this $content is most likely binary.
        if (false === mb_check_encoding(preg_replace('/\(.*$/s', '', $content), 'UTF-8')) {
            return '';
        }

        // Find all inline image content and replace them so they aren't
        // affected by the next steps
        $pdfInlineImages = [];
        $offsetBI = 0;
        while (preg_match('/\sBI\s(\/.+?)\sID\s(.+?)\sEI(?=\s|$)/s', $content, $text, \PREG_OFFSET_CAPTURE, $offsetBI)) {
            // Attempt to detemine if this instance of the 'BI' command
            // actually occured within a (string) using the following
            // steps:

            // Remove any escaped parentheses from the alleged image
            // characteristics data
            $para = str_replace(['\\(', '\\)'], '', $text[1][0]);

            // Remove all correctly ordered and balanced parentheses
            // from (strings)
            do {
                $paraTest = $para;
                $para = preg_replace('/\(([^)]*)\)/', '$1', $paraTest);
            } while ($para != $paraTest);

            $paraOpen = strpos($para, '(');
            $paraClose = strpos($para, ')');

            // If the remaining text contains a close parenthesis ')'
            // AND it occurs before any open parenthesis, then we are
            // almost certain to be inside a (string)
            if (0 < $paraClose && (false === $paraOpen || $paraClose < $paraOpen)) {
                // Bump the search offset forward and match again
                $offsetBI = (int) $text[1][1];
                continue;
            }

            // Double check that this is actually inline image data by
            // parsing the alleged image characteristics as a dictionary
            $dict = $this->parseDictionary('<<'.$text[1][0].'>>');

            // Check if an image Width and Height are set in the dict
            if ((isset($dict['W']) || isset($dict['Width']))
                && (isset($dict['H']) || isset($dict['Height']))) {
                $id = uniqid('IMAGE_', true);
                $pdfInlineImages[$id] = [
                    preg_replace(['/\r\n/', '/\r/', '/\n/'], ' ', $text[1][0]),
                    preg_replace(['/\r\n/', '/\r/', '/\n/'], '', $text[2][0]),
                ];
                $content = preg_replace(
                    '/'.preg_quote($text[0][0], '/').'/',
                    '^^^'.$id.'^^^',
                    $content,
                    1
                );
            }
        }

        // 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)/s', $content, $dicttext)) {
            $dictid = uniqid('DICT_', true);
            $dictstore[$dictid] = $dicttext[1];
            $content = preg_replace(
                '/'.preg_quote($dicttext[0], '/').'/',
                ' ###'.$dictid.'###'.$dicttext[2],
                $content,
                1
            );
        }

        // 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);
        }

        // Restore the original content of any inline images
        $pdfInlineImages = array_reverse($pdfInlineImages, true);
        foreach ($pdfInlineImages as $id => $image) {
            $content = str_replace(
                '^^^'.$id.'^^^',
                "\r\nBI\r\n".$image[0]." ID\r\n".$image[1]." EI\r\n",
                $content
            );
        }

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

        return $content;
    }