Changeset 32863 for trunk/src/wp-includes/formatting.php

Timestamp:

06/19/2015 08:05:52 PM (10 years ago)

Author:

wonderboymusic

Message:

wptexturize() improvements:

• Make sure that strings ending with a number and quotation mark get the proper smart quotes
• Introduce wptexturize_primes(), a logic tree to determine whether or not "7'." represents seven feet, then converts the special char into either a prime char or a closing quote char.

Adds unit tests.

Props miqrogroove.
Fixes #29256.

File:

• trunk/src/wp-includes/formatting.php (modified) (5 diffs)

trunk/src/wp-includes/formatting.php

@@ -47 +47 @@
         $default_no_texturize_tags = null,
         $default_no_texturize_shortcodes = null,
-        $run_texturize = true;
+        $run_texturize = true,
+        $apos = null,
+        $prime = null,
+        $double_prime = null,
+        $opening_quote = null,
+        $closing_quote = null,
+        $opening_single_quote = null,
+        $closing_single_quote = null,
+        $open_q_flag = '<!--oq-->',
+        $open_sq_flag = '<!--osq-->',
+        $apos_flag = '<!--apos-->';
 
     // If there's nothing to do, just stop.
@@ -130 +140 @@
         // '99' and '99" are ambiguous among other patterns; assume it's an abbreviated year at the end of a quotation.
         if ( "'" !== $apos || "'" !== $closing_single_quote ) {
-            $dynamic[ '/\'(\d\d)\'(?=\Z|[.,:;!?)}\-\]]|&gt;|' . $spaces . ')/' ] = $apos . '$1' . $closing_single_quote;
+            $dynamic[ '/\'(\d\d)\'(?=\Z|[.,:;!?)}\-\]]|&gt;|' . $spaces . ')/' ] = $apos_flag . '$1' . $closing_single_quote;
         }
         if ( "'" !== $apos || '"' !== $closing_quote ) {
-            $dynamic[ '/\'(\d\d)"(?=\Z|[.,:;!?)}\-\]]|&gt;|' . $spaces . ')/' ] = $apos . '$1' . $closing_quote;
+            $dynamic[ '/\'(\d\d)"(?=\Z|[.,:;!?)}\-\]]|&gt;|' . $spaces . ')/' ] = $apos_flag . '$1' . $closing_quote;
         }
 
         // '99 '99s '99's (apostrophe)  But never '9 or '99% or '999 or '99.0.
         if ( "'" !== $apos ) {
-            $dynamic[ '/\'(?=\d\d(?:\Z|(?![%\d]|[.,]\d)))/' ] = $apos;
+            $dynamic[ '/\'(?=\d\d(?:\Z|(?![%\d]|[.,]\d)))/' ] = $apos_flag;
         }
 
         // Quoted Numbers like '0.42'
         if ( "'" !== $opening_single_quote && "'" !== $closing_single_quote ) {
-            $dynamic[ '/(?<=\A|' . $spaces . ')\'(\d[.,\d]*)\'/' ] = $opening_single_quote . '$1' . $closing_single_quote;
+            $dynamic[ '/(?<=\A|' . $spaces . ')\'(\d[.,\d]*)\'/' ] = $open_sq_flag . '$1' . $closing_single_quote;
         }
 
         // Single quote at start, or preceded by (, {, <, [, ", -, or spaces.
         if ( "'" !== $opening_single_quote ) {
-            $dynamic[ '/(?<=\A|[([{"\-]|&lt;|' . $spaces . ')\'/' ] = $opening_single_quote;
+            $dynamic[ '/(?<=\A|[([{"\-]|&lt;|' . $spaces . ')\'/' ] = $open_sq_flag;
         }
 
         // Apostrophe in a word.  No spaces, double apostrophes, or other punctuation.
         if ( "'" !== $apos ) {
-            $dynamic[ '/(?<!' . $spaces . ')\'(?!\Z|[.,:;!?"\'(){}[\]\-]|&[lg]t;|' . $spaces . ')/' ] = $apos;
-        }
-
-        // 9' (prime)
-        if ( "'" !== $prime ) {
-            $dynamic[ '/(?<=\d)\'/' ] = $prime;
-        }
-
-        // Single quotes followed by spaces or ending punctuation.
-        if ( "'" !== $closing_single_quote ) {
-            $dynamic[ '/\'(?=\Z|[.,:;!?)}\-\]]|&gt;|' . $spaces . ')/' ] = $closing_single_quote;
+            $dynamic[ '/(?<!' . $spaces . ')\'(?!\Z|[.,:;!?"\'(){}[\]\-]|&[lg]t;|' . $spaces . ')/' ] = $apos_flag;
         }
 
@@ -172 +172 @@
         // Quoted Numbers like "42"
         if ( '"' !== $opening_quote && '"' !== $closing_quote ) {
-            $dynamic[ '/(?<=\A|' . $spaces . ')"(\d[.,\d]*)"/' ] = $opening_quote . '$1' . $closing_quote;
-        }
-
-        // 9" (double prime)
-        if ( '"' !== $double_prime ) {
-            $dynamic[ '/(?<=\d)"/' ] = $double_prime;
+            $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 . ')/' ] = $opening_quote;
-        }
-
-        // Any remaining double quotes.
-        if ( '"' !== $closing_quote ) {
-            $dynamic[ '/"/' ] = $closing_quote;
+            $dynamic[ '/(?<=\A|[([{\-]|&lt;|' . $spaces . ')"(?!' . $spaces . ')/' ] = $open_q_flag;
         }
 
@@ -301 +291 @@
             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, '-' ) ) {
@@ -320 +315 @@
     // Replace each & with &#038; unless it already looks like an entity.
     return preg_replace( '/&(?!#(?:\d+|x[a-f0-9]+);|[a-z1-4]{1,8};)/i', '&#038;', $text );
+}
+
+/**
+ * Implements a logic tree to determine whether or not "7'." represents seven feet,
+ * then converts the special char into either a prime char or a closing quote char.
+ *
+ * @since 4.3.0
+ *
+ * @param string $haystack The plain text to be searched.
+ * @param string $needle The character to search for such as ' or ".
+ * @param string $prime The prime char to use for replacement.
+ * @param string $open_quote The opening quote char. Opening quote replacement must be accomplished already.
+ * @param string $close_quote The closing quote char to use for replacement.
+ * @return string The $haystack value after primes and quotes replacements.
+ */
+function wptexturize_primes( $haystack, $needle, $prime, $open_quote, $close_quote ) {
+    $spaces = wp_spaces_regexp();
+    $flag = '<!--wp-prime-or-quote-->';
+    $quote_pattern = "/$needle(?=\\Z|[.,:;!?)}\\-\\]]|&gt;|" . $spaces . ")/";
+    $prime_pattern    = "/(?<=\\d)$needle/";
+    $flag_after_digit = "/(?<=\\d)$flag/";
+    $flag_no_digit    = "/(?<!\\d)$flag/";
+
+    $sentences = explode( $open_quote, $haystack );
+
+    foreach( $sentences as $key => &$sentence ) {
+        if ( false === strpos( $sentence, $needle ) ) {
+            continue;
+        } elseif ( 0 !== $key && 0 === substr_count( $sentence, $close_quote ) ) {
+            $sentence = preg_replace( $quote_pattern, $flag, $sentence, -1, $count );
+            if ( $count > 1 ) {
+                // This sentence appears to have multiple closing quotes.  Attempt Vulcan logic.
+                $sentence = preg_replace( $flag_no_digit, $close_quote, $sentence, -1, $count2 );
+                if ( 0 === $count2 ) {
+                    // Try looking for a quote followed by a period.
+                    $count2 = substr_count( $sentence, "$flag." );
+                    if ( $count2 > 0 ) {
+                        // Assume the rightmost quote-period match is the end of quotation.
+                        $pos = strrpos( $sentence, "$flag." );
+                    } else {
+                        // When all else fails, make the rightmost candidate a closing quote.
+                        // This is most likely to be problematic in the context of bug #18549.
+                        $pos = strrpos( $sentence, $flag );
+                    }
+                    $sentence = substr_replace( $sentence, $close_quote, $pos, strlen( $flag ) );
+                }
+                // Use conventional replacement on any remaining primes and quotes.
+                $sentence = preg_replace( $prime_pattern, $prime, $sentence );
+                $sentence = preg_replace( $flag_after_digit, $prime, $sentence );
+                $sentence = str_replace( $flag, $close_quote, $sentence );
+            } elseif ( 1 == $count ) {
+                // Found only one closing quote candidate, so give it priority over primes.
+                $sentence = str_replace( $flag, $close_quote, $sentence );
+                $sentence = preg_replace( $prime_pattern, $prime, $sentence );
+            } else {
+                // No closing quotes found.  Just run primes pattern.
+                $sentence = preg_replace( $prime_pattern, $prime, $sentence );
+            }
+        } else {
+            $sentence = preg_replace( $prime_pattern, $prime, $sentence );
+            $sentence = preg_replace( $quote_pattern, $close_quote, $sentence );
+        }
+        if ( '"' == $needle && false !== strpos( $sentence, '"' ) ) {
+            $sentence = str_replace( '"', $close_quote, $sentence );
+        }
+    }
+
+    return implode( $open_quote, $sentences );
 }