Smalot\PdfParser\Font::loadTranslateTable()

Complexity

Conditions	19
Paths	14

Size

Total Lines	114
Code Lines	60

Duplication

Lines	0
Ratio	0 %

Importance

Changes	3
Bugs	0	Features	0

<?php
    public function loadTranslateTable(): array
    {
        if (null !== $this->table) {
            return $this->table;
        }

        $this->table = [];
        $this->tableSizes = [
            'from' => 1,
            'to' => 1,
        ];

        if ($this->has('ToUnicode')) {
            $content = $this->get('ToUnicode')->getContent();
            $matches = [];

            // Support for multiple spacerange sections
            if (preg_match_all('/begincodespacerange(?P<sections>.*?)endcodespacerange/s', $content, $matches)) {
                foreach ($matches['sections'] as $section) {
                    $regexp = '/<(?P<from>[0-9A-F]+)> *<(?P<to>[0-9A-F]+)>[ \r\n]+/is';

                    preg_match_all($regexp, $section, $matches);

                    $this->tableSizes = [
                        'from' => max(1, \strlen(current($matches['from'])) / 2),
                        'to' => max(1, \strlen(current($matches['to'])) / 2),
                    ];

                    break;
                }
            }

            // Support for multiple bfchar sections
            if (preg_match_all('/beginbfchar(?P<sections>.*?)endbfchar/s', $content, $matches)) {
                foreach ($matches['sections'] as $section) {
                    $regexp = '/<(?P<from>[0-9A-F]+)> *<(?P<to>[0-9A-F]+)>[ \r\n]+/is';

                    preg_match_all($regexp, $section, $matches);

                    $this->tableSizes['from'] = max(1, \strlen(current($matches['from'])) / 2);

                    foreach ($matches['from'] as $key => $from) {
                        $parts = preg_split(
                            '/([0-9A-F]{4})/i',
                            $matches['to'][$key],
                            0,
                            \PREG_SPLIT_NO_EMPTY | \PREG_SPLIT_DELIM_CAPTURE
                        );
                        $text = '';
                        foreach ($parts as $part) {
                            $text .= self::uchr(hexdec($part));
                        }
                        $this->table[hexdec($from)] = $text;
                    }
                }
            }

            // Support for multiple bfrange sections
            if (preg_match_all('/beginbfrange(?P<sections>.*?)endbfrange/s', $content, $matches)) {
                foreach ($matches['sections'] as $section) {
                    /**
                     * Regexp to capture <from>, <to>, and either <offset> or [...] items.
                     * - (?P<from>...) Source range's start
                     * - (?P<to>...)   Source range's end
                     * - (?P<dest>...) Destination range's offset or each char code
                     *                 Some PDF file has 2-byte Unicode values on new lines > added \r\n
                     */
                    $regexp = '/<(?P<from>[0-9A-F]+)> *<(?P<to>[0-9A-F]+)> *(?P<dest><[0-9A-F]+>|\[[\r\n<>0-9A-F ]+\])[ \r\n]+/is';

                    preg_match_all($regexp, $section, $matches);

                    foreach ($matches['from'] as $key => $from) {
                        $char_from = hexdec($from);
                        $char_to = hexdec($matches['to'][$key]);
                        $dest = $matches['dest'][$key];

                        if (1 === preg_match('/^<(?P<offset>[0-9A-F]+)>$/i', $dest, $offset_matches)) {
                            // Support for : <srcCode1> <srcCode2> <dstString>
                            $offset = hexdec($offset_matches['offset']);

                            for ($char = $char_from; $char <= $char_to; ++$char) {
                                $this->table[$char] = self::uchr($char - $char_from + $offset);
                            }
                        } else {
                            // Support for : <srcCode1> <srcCodeN> [<dstString1> <dstString2> ... <dstStringN>]
                            $strings = [];
                            $matched = preg_match_all('/<(?P<string>[0-9A-F]+)> */is', $dest, $strings);
                            if (false === $matched || 0 === $matched) {
                                continue;
                            }

                            foreach ($strings['string'] as $position => $string) {
                                $parts = preg_split(
                                    '/([0-9A-F]{4})/i',
                                    $string,
                                    0,
                                    \PREG_SPLIT_NO_EMPTY | \PREG_SPLIT_DELIM_CAPTURE
                                );
                                if (false === $parts) {
                                    continue;
                                }
                                $text = '';
                                foreach ($parts as $part) {
                                    $text .= self::uchr(hexdec($part));
                                }
                                $this->table[$char_from + $position] = $text;
                            }
                        }
                    }
                }
            }
        }

        return $this->table;
    }