PHP _get_wptexturize_split_regex函数代码示例

//.........这里部分代码省略.........
        $dynamic_replacements['apos'] = array_values($dynamic);
        $dynamic = array();
        // Quoted Numbers like "42"
        if ('"' !== $opening_quote && '"' !== $closing_quote) {
            $dynamic['/(?<=\\A|' . $spaces . ')"(\\d[.,\\d]*)"/'] = $open_q_flag . '$1' . $closing_quote;
        }
        // Double quote at start, or preceded by (, {, <, [, -, or spaces, and not followed by spaces.
        if ('"' !== $opening_quote) {
            $dynamic['/(?<=\\A|[([{\\-]|&lt;|' . $spaces . ')"(?!' . $spaces . ')/'] = $open_q_flag;
        }
        $dynamic_characters['quote'] = array_keys($dynamic);
        $dynamic_replacements['quote'] = array_values($dynamic);
        $dynamic = array();
        // Dashes and spaces
        $dynamic['/---/'] = $em_dash;
        $dynamic['/(?<=^|' . $spaces . ')--(?=$|' . $spaces . ')/'] = $em_dash;
        $dynamic['/(?<!xn)--/'] = $en_dash;
        $dynamic['/(?<=^|' . $spaces . ')-(?=$|' . $spaces . ')/'] = $en_dash;
        $dynamic_characters['dash'] = array_keys($dynamic);
        $dynamic_replacements['dash'] = array_values($dynamic);
    }
    // Must do this every time in case plugins use these filters in a context sensitive manner
    /**
     * Filter the list of HTML elements not to texturize.
     *
     * @since 2.8.0
     *
     * @param array $default_no_texturize_tags An array of HTML element names.
     */
    $no_texturize_tags = apply_filters('no_texturize_tags', $default_no_texturize_tags);
    /**
     * Filter the list of shortcodes not to texturize.
     *
     * @since 2.8.0
     *
     * @param array $default_no_texturize_shortcodes An array of shortcode names.
     */
    $no_texturize_shortcodes = apply_filters('no_texturize_shortcodes', $default_no_texturize_shortcodes);
    $no_texturize_tags_stack = array();
    $no_texturize_shortcodes_stack = array();
    // Look for shortcodes and HTML elements.
    preg_match_all('@\\[/?([^<>&/\\[\\]\\x00-\\x20]++)@', $text, $matches);
    $tagnames = array_intersect(array_keys($shortcode_tags), $matches[1]);
    $found_shortcodes = !empty($tagnames);
    $shortcode_regex = $found_shortcodes ? _get_wptexturize_shortcode_regex($tagnames) : '';
    $regex = _get_wptexturize_split_regex($shortcode_regex);
    $textarr = preg_split($regex, $text, -1, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY);
    foreach ($textarr as &$curl) {
        // Only call _wptexturize_pushpop_element if $curl is a delimiter.
        $first = $curl[0];
        if ('<' === $first) {
            if ('<!--' === substr($curl, 0, 4)) {
                // This is an HTML comment delimiter.
                continue;
            } else {
                // This is an HTML element delimiter.
                // Replace each & with &#038; unless it already looks like an entity.
                $curl = preg_replace('/&(?!#(?:\\d+|x[a-f0-9]+);|[a-z1-4]{1,8};)/i', '&#038;', $curl);
                _wptexturize_pushpop_element($curl, $no_texturize_tags_stack, $no_texturize_tags);
            }
        } elseif ('' === trim($curl)) {
            // This is a newline between delimiters.  Performance improves when we check this.
            continue;
        } elseif ('[' === $first && $found_shortcodes && 1 === preg_match('/^' . $shortcode_regex . '$/', $curl)) {
            // This is a shortcode delimiter.
            if ('[[' !== substr($curl, 0, 2) && ']]' !== substr($curl, -2)) {
                // Looks like a normal shortcode.
                _wptexturize_pushpop_element($curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes);
            } else {
                // Looks like an escaped shortcode.
                continue;
            }
        } elseif (empty($no_texturize_shortcodes_stack) && empty($no_texturize_tags_stack)) {
            // This is neither a delimiter, nor is this content inside of no_texturize pairs.  Do texturize.
            $curl = str_replace($static_characters, $static_replacements, $curl);
            if (false !== strpos($curl, "'")) {
                $curl = preg_replace($dynamic_characters['apos'], $dynamic_replacements['apos'], $curl);
                $curl = wptexturize_primes($curl, "'", $prime, $open_sq_flag, $closing_single_quote);
                $curl = str_replace($apos_flag, $apos, $curl);
                $curl = str_replace($open_sq_flag, $opening_single_quote, $curl);
            }
            if (false !== strpos($curl, '"')) {
                $curl = preg_replace($dynamic_characters['quote'], $dynamic_replacements['quote'], $curl);
                $curl = wptexturize_primes($curl, '"', $double_prime, $open_q_flag, $closing_quote);
                $curl = str_replace($open_q_flag, $opening_quote, $curl);
            }
            if (false !== strpos($curl, '-')) {
                $curl = preg_replace($dynamic_characters['dash'], $dynamic_replacements['dash'], $curl);
            }
            // 9x9 (times), but never 0x9999
            if (1 === preg_match('/(?<=\\d)x\\d/', $curl)) {
                // Searching for a digit is 10 times more expensive than for the x, so we avoid doing this one!
                $curl = preg_replace('/\\b(\\d(?(?<=0)[\\d\\.,]+|[\\d\\.,]*))x(\\d[\\d\\.,]*)\\b/', '$1&#215;$2', $curl);
            }
            // Replace each & with &#038; unless it already looks like an entity.
            $curl = preg_replace('/&(?!#(?:\\d+|x[a-f0-9]+);|[a-z1-4]{1,8};)/i', '&#038;', $curl);
        }
    }
    return implode('', $textarr);
}

 /**
  * Automated performance testing of the main regex.
  *
  * @dataProvider data_whole_posts
  */
 function test_pcre_performance($input)
 {
     global $shortcode_tags;
     // With Shortcodes Disabled
     $regex = _get_wptexturize_split_regex();
     $result = benchmark_pcre_backtracking($regex, $input, 'split');
     $this->assertLessThan(200, $result);
     // With Shortcodes Enabled
     $shortcode_regex = _get_wptexturize_shortcode_regex(array_keys($shortcode_tags));
     $regex = _get_wptexturize_split_regex($shortcode_regex);
     $result = benchmark_pcre_backtracking($regex, $input, 'split');
     return $this->assertLessThan(200, $result);
 }