From: C. Scott Ananian Date: Tue, 6 Aug 2013 19:22:18 +0000 (-0400) Subject: Make line breaks in
behave like
(bug 6200). X-Git-Tag: 1.31.0-rc.0~18772^2 X-Git-Url: http://git.cyclocoop.org/?a=commitdiff_plain;h=336d7465239431106c4a0222e8671585733b7842;p=lhc%2Fweb%2Fwiklou.git Make line breaks in
behave like
(bug 6200). This is an old, old bug: the earliest filed dup is bug 1857, on 2005-04-10. See bug 51086 for a modern discussion, and bug 52763 for some non-obvious consequences: indented text inside a blockquote must not trigger creation of a 
 block (unlike 
).

This patch should bring the PHP parser and Parsoid closer together.

This also fixes (or works around) bug 15491, which is really a bug in tidy.
But because 
 content is typically wrapped with 
 tags now,
we don't trigger the tidy bug (see
https://bugzilla.wikimedia.org/show_bug.cgi?id=15491#c7 for details).

Credit to Aryeh Gregor (https://bugzilla.wikimedia.org/show_bug.cgi?id=6200#c8)
and Vitaliy Filippov (https://bugzilla.wikimedia.org/show_bug.cgi?id=6200#c37)
for almost-correct patches for this bug, which saved me a bunch of effort.
Thanks to Subramanya Sastry for pointing out bug 52763 and preventing a
bunch of broken articles on enwiki.

Bug: 6200
Bug: 15491
Bug: 52763
Change-Id: I3696d4ab7b8ad6ebccf8483d6da1722353c1697d
---

diff --git a/RELEASE-NOTES-1.22 b/RELEASE-NOTES-1.22
index e503e30195..295a95fd8b 100644
--- a/RELEASE-NOTES-1.22
+++ b/RELEASE-NOTES-1.22
@@ -291,6 +291,7 @@ production.
 * (bug 51742) Add data-sort-value for better sorting of hitcounts Special:Tags
 * (bug 26811) On DB error pages, server hostnames are now hidden when both
   $wgShowHostnames and $wgShowSQLErrors are false.
+* (bug 6200) line breaks in 
 are handled like they are in 

 
 === API changes in 1.22 ===
 * (bug 25553) The JSON output formatter now leaves forward slashes unescaped
diff --git a/includes/parser/Parser.php b/includes/parser/Parser.php
index fd69bfc3dc..3376734a8d 100644
--- a/includes/parser/Parser.php
+++ b/includes/parser/Parser.php
@@ -2362,6 +2362,7 @@ class Parser {
 		$this->mDTopen = $inBlockElem = false;
 		$prefixLength = 0;
 		$paragraphStack = false;
+		$inBlockquote = false;
 
 		foreach ( $textLines as $oLine ) {
 			# Fix up $linestart
@@ -2455,10 +2456,10 @@ class Parser {
 				wfProfileIn( __METHOD__ . "-paragraph" );
 				# No prefix (not in list)--go to paragraph mode
 				# XXX: use a stack for nestable elements like span, table and div
-				$openmatch = preg_match( '/(?:mUniqPrefix . '-pre|<\\/li|<\\/ul|<\\/ol|<\\/dl|<\\/?center)/iS', $t );
+					'/(?:<\\/table|<\\/h1|<\\/h2|<\\/h3|<\\/h4|<\\/h5|<\\/h6|' .
+					'mUniqPrefix . '-pre|<\\/li|<\\/ul|<\\/ol|<\\/dl|<\\/?center)/iS', $t );
 				if ( $openmatch or $closematch ) {
 					$paragraphStack = false;
 					# TODO bug 5718: paragraph closed
@@ -2466,9 +2467,14 @@ class Parser {
 					if ( $preOpenMatch and !$preCloseMatch ) {
 						$this->mInPre = true;
 					}
+					$bqOffset = 0;
+					while ( preg_match( '/<(\\/?)blockquote[\s>]/i', $t, $bqMatch, PREG_OFFSET_CAPTURE, $bqOffset ) ) {
+						$inBlockquote = !$bqMatch[1][0]; // is this a close tag?
+						$bqOffset = $bqMatch[0][1] + strlen( $bqMatch[0][0] );
+					}
 					$inBlockElem = !$closematch;
 				} elseif ( !$inBlockElem && !$this->mInPre ) {
-					if ( ' ' == substr( $t, 0, 1 ) and ( $this->mLastSection === 'pre' || trim( $t ) != '' ) ) {
+					if ( ' ' == substr( $t, 0, 1 ) and ( $this->mLastSection === 'pre' || trim( $t ) != '' ) and !$inBlockquote ) {
 						# pre
 						if ( $this->mLastSection !== 'pre' ) {
 							$paragraphStack = false;
diff --git a/tests/parser/parserTests.txt b/tests/parser/parserTests.txt
index 146f86718e..f841afb6f8 100644
--- a/tests/parser/parserTests.txt
+++ b/tests/parser/parserTests.txt
@@ -1239,8 +1239,9 @@ b
 
b
 

 !! end
+
 !! test
-Block tag on one line
+Block tag on one line (
)
 !! input
 a 
foo

 
@@ -1252,7 +1253,19 @@ a 
foo

 !! end
 
 !! test
-Block tag on both lines
+Block tag on one line (
)
+!! input
+a 
foo

+
+b
+!! result
+a 
foo

+
b
+

+!! end
+
+!! test
+Block tag on both lines (
)
 !! input
 a 
foo

 
@@ -1263,6 +1276,18 @@ b 
foo

 
 !! end
 
+!! test
+Block tag on both lines (
)
+!! input
+a 
foo

+
+b 
foo

+!! result
+a 
foo

+b 
foo

+
+!! end
+
 !! test
 Multiple lines without block tags
 !! input
@@ -1389,17 +1414,61 @@ Regression with preformatted in 

 
 !! end
 
-# Expected output in the following test is not really expected (there should be
-# 
 in the output) -- it's only testing for well-formedness.
 !! test
-Bug 6200: Preformatted in 

+Bug 52763: Preformatted in 

 !! input
 

  Blah
 

 !! result
 

- Blah
+
 Blah
+

+

+
+!! end
+
+!! test
+Bug 51086: Double newlines in blockquotes should be turned into paragraphs
+!! input
+

+Foo
+
+Bar
+

+!! result
+

+
Foo
+
Bar
+

+

+
+!! end
+
+!! test
+Bug 15491: / in blockquote
+!! input
+

+Foo bar baz quux
+

+!! result
+

+
Foo bar baz quux
+

+

+
+!! end
+
+# Note that the p-wrapping is newline sensitive, which could be
+# considered a bug: tidy will wrap only the 'Foo' in the example
+# below in a 
 tag. (see comment 23-25 of bug #6200)
+!! test
+Bug 15491: / in blockquote (2)
+!! input
+
Foo bar baz quux
+

+!! result
+
Foo bar baz quux
 

 
 !! end
@@ -1882,10 +1951,12 @@ c
 !!input
  
 foo 

  
 foo 

+ 
 foo 

   foo 
 !!result
  
 foo 

  
 foo 

+ 
 foo 

 
 foo 
 

 !!end
@@ -1909,6 +1980,12 @@ c
  foo
 

 
+

+
+foo
+

+

+
 

  foo
 

@@ -1930,7 +2007,13 @@ c
 

 

 

- foo
+
 foo
+

+

+

+
+foo
+

 

 

 
foo
@@ -7288,8 +7371,10 @@ Templates: 1. Simple use
 Templates: 2. Inside a block tag
 !!input
 
{{echo|Foo}}

+
{{echo|Foo}}

 !!result
 
Foo

+
Foo

 
 !!end
 
@@ -13610,9 +13695,6 @@ __NOEDITSECTION__
 

 !! end
 
-# Expected output in the following test is not necessarily expected (there
-# should probably be 
 tags inside the 
 in the output) -- it's
-# only testing for well-formedness.
 !! test
 Bug 6200: blockquotes and paragraph formatting
 !! input
@@ -13625,7 +13707,8 @@ bar
  baz
 !! result
 

-foo
+
foo
+

 

 
bar
 

@@ -14305,8 +14388,6 @@ B
 # Bug 6200: 
 should behave like 
 with respect to line breaks
 !! test
 Bug 6200: paragraphs inside blockquotes (no extra line breaks)
-!! options
-disabled
 !! input
 
Line one
 
@@ -14319,8 +14400,6 @@ Line two

 
 !! test
 Bug 6200: paragraphs inside blockquotes (extra line break on open)
-!! options
-disabled
 !! input
 

 Line one
@@ -14336,8 +14415,6 @@ Line two

 
 !! test
 Bug 6200: paragraphs inside blockquotes (extra line break on close)
-!! options
-disabled
 !! input
 
Line one
 
@@ -14353,8 +14430,6 @@ Line two
 
 !! test
 Bug 6200: paragraphs inside blockquotes (extra line break on open and close)
-!! options
-disabled
 !! input
 

 Line one