Merge "Handle missing namespace prefix in XML dumps more gracefully"

[lhc/web/wiklou.git] / includes / parser / Preprocessor_Hash.php

diff --git a/includes/parser/Preprocessor_Hash.php b/includes/parser/Preprocessor_Hash.php
index 8a4637e..b2e9531 100644 (file)
--- a/includes/parser/Preprocessor_Hash.php
+++ b/includes/parser/Preprocessor_Hash.php
@@ -107,7 +107,7 @@ class Preprocessor_Hash extends Preprocessor {
         *                                 included. Default is to assume a direct page view.
         *
         * The generated DOM tree must depend only on the input text and the flags.
-        * The DOM tree must be the same in OT_HTML and OT_WIKI mode, to avoid a regression of bug 4899.
+        * The DOM tree must be the same in OT_HTML and OT_WIKI mode, to avoid a regression of T6899.
         *
         * Any flag added to the $flags parameter here, or any other parameter liable to cause a
         * change in the DOM tree for a given text, must be passed through the section identifier
@@ -117,6 +117,8 @@ class Preprocessor_Hash extends Preprocessor {
         * @return PPNode_Hash_Tree
         */
        public function preprocessToObj( $text, $flags = 0 ) {
+               global $wgDisableLangConversion;
+
                $tree = $this->cacheGetTree( $text, $flags );
                if ( $tree !== false ) {
                        $store = json_decode( $tree );
@@ -152,6 +154,11 @@ class Preprocessor_Hash extends Preprocessor {
                $stack = new PPDStack_Hash;
 
                $searchBase = "[{<\n";
+               if ( !$wgDisableLangConversion ) {
+                       // FIXME: disabled due to T153761
+                       // $searchBase .= '-';
+               }
+
                // For fast reverse searches
                $revText = strrev( $text );
                $lengthText = strlen( $text );
@@ -229,7 +236,10 @@ class Preprocessor_Hash extends Preprocessor {
                                                break;
                                        }
                                } else {
-                                       $curChar = $text[$i];
+                                       $curChar = $curTwoChar = $text[$i];
+                                       if ( ( $i + 1 ) < $lengthText ) {
+                                               $curTwoChar .= $text[$i + 1];
+                                       }
                                        if ( $curChar == '|' ) {
                                                $found = 'pipe';
                                        } elseif ( $curChar == '=' ) {
@@ -242,11 +252,20 @@ class Preprocessor_Hash extends Preprocessor {
                                                } else {
                                                        $found = 'line-start';
                                                }
+                                       } elseif ( $curTwoChar == $currentClosing ) {
+                                               $found = 'close';
+                                               $curChar = $curTwoChar;
                                        } elseif ( $curChar == $currentClosing ) {
                                                $found = 'close';
+                                       } elseif ( isset( $this->rules[$curTwoChar] ) ) {
+                                               $curChar = $curTwoChar;
+                                               $found = 'open';
+                                               $rule = $this->rules[$curChar];
                                        } elseif ( isset( $this->rules[$curChar] ) ) {
                                                $found = 'open';
                                                $rule = $this->rules[$curChar];
+                                       } elseif ( $curChar == '-' ) {
+                                               $found = 'dash';
                                        } else {
                                                # Some versions of PHP have a strcspn which stops on null characters
                                                # Ignore and continue
@@ -538,7 +557,8 @@ class Preprocessor_Hash extends Preprocessor {
                                // input pointer.
                        } elseif ( $found == 'open' ) {
                                # count opening brace characters
-                               $count = strspn( $text, $curChar, $i );
+                               $curLen = strlen( $curChar );
+                               $count = ( $curLen > 1 ) ? 1 : strspn( $text, $curChar, $i );
 
                                # we need to add to stack only if opening brace count is enough for one of the rules
                                if ( $count >= $rule['min'] ) {
@@ -557,12 +577,13 @@ class Preprocessor_Hash extends Preprocessor {
                                        # Add literal brace(s)
                                        self::addLiteral( $accum, str_repeat( $curChar, $count ) );
                                }
-                               $i += $count;
+                               $i += $curLen * $count;
                        } elseif ( $found == 'close' ) {
                                $piece = $stack->top;
                                # lets check if there are enough characters for closing brace
                                $maxCount = $piece->count;
-                               $count = strspn( $text, $curChar, $i, $maxCount );
+                               $curLen = strlen( $curChar );
+                               $count = ( $curLen > 1 ) ? 1 : strspn( $text, $curChar, $i, $maxCount );
 
                                # check for maximum matching characters (if there are 5 closing
                                # characters, we will probably need only 3 - depending on the rules)
@@ -585,7 +606,7 @@ class Preprocessor_Hash extends Preprocessor {
                                        # No matching element found in callback array
                                        # Output a literal closing brace and continue
                                        self::addLiteral( $accum, str_repeat( $curChar, $count ) );
-                                       $i += $count;
+                                       $i += $curLen * $count;
                                        continue;
                                }
                                $name = $rule['names'][$matchingCount];
@@ -627,7 +648,7 @@ class Preprocessor_Hash extends Preprocessor {
                                }
 
                                # Advance input pointer
-                               $i += $matchingCount;
+                               $i += $curLen * $matchingCount;
 
                                # Unwind the stack
                                $stack->pop();
@@ -661,6 +682,9 @@ class Preprocessor_Hash extends Preprocessor {
                                $accum[] = [ 'equals', [ '=' ] ];
                                $stack->getCurrentPart()->eqpos = count( $accum ) - 1;
                                ++$i;
+                       } elseif ( $found == 'dash' ) {
+                               self::addLiteral( $accum, '-' );
+                               ++$i;
                        }
                }