From e1a7d10063192beae092649d6b2bf7eae43c58af Mon Sep 17 00:00:00 2001
From: Gabriel Wicke <gwicke@wikimedia.org>
Date: Thu, 28 Jun 2012 16:12:23 +0200
Subject: [PATCH] Fix round-tripping of invalid external links somewhat

* Don't consider them for auto-numbered links
* Don't insert a trailing space if the content is empty

These links are still wrapped in nowiki on round-tripping since the
valid/invalid url determination is done in the LinkHandler and not the
Tokenizer as it is configuration-dependent. Not incorrect for rendering (and
perhaps easier to understand for humans too), but might still introduce a
dirty diff. We'll still need reconciliation / damage tracking in the end ;)

Change-Id: I959ebc1b7f81d110a1141bb38ba5ee97f52ebf96
---
 modules/parser/ext.core.LinkHandler.js | 16 +++++++++++-----
 modules/parser/pegTokenizer.pegjs.txt  |  2 +-
 2 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/modules/parser/ext.core.LinkHandler.js b/modules/parser/ext.core.LinkHandler.js
index 5fbacdd12a..4eca5ba180 100644
--- a/modules/parser/ext.core.LinkHandler.js
+++ b/modules/parser/ext.core.LinkHandler.js
@@ -412,11 +412,11 @@ ExternalLinkHandler.prototype.onExtLink = function ( token, manager, cb ) {
 	//console.warn('extlink href: ' + href );
 	//console.warn( 'content: ' + JSON.stringify( content, null, 2 ) );
 	// validate the href
-	if ( ! content.length ) {
-		content = ['[' + this.linkCount + ']'];
-		this.linkCount++;
-	}
 	if ( this.imageParser.tokenizeURL( href ) ) {
+		if ( ! content.length ) {
+			content = ['[' + this.linkCount + ']'];
+			this.linkCount++;
+		}
 		if ( content.length === 1 && 
 				content[0].constructor === String &&
 				this.imageParser.tokenizeURL( content[0] ) &&
@@ -446,8 +446,14 @@ ExternalLinkHandler.prototype.onExtLink = function ( token, manager, cb ) {
 				].concat( content, [ new EndTagTk( 'a' )])
 		} );
 	} else {
+		var tokens = ['[', href ];
+		if ( content.length ) {
+			tokens = tokens.concat( [' '], content );
+		}
+		tokens.push(']');
+
 		cb( {
-			tokens: ['[', href, ' ' ].concat( content, [']'] )
+			tokens: tokens
 		} );
 	}
 };
diff --git a/modules/parser/pegTokenizer.pegjs.txt b/modules/parser/pegTokenizer.pegjs.txt
index 454c4cc924..8fea5dbf40 100644
--- a/modules/parser/pegTokenizer.pegjs.txt
+++ b/modules/parser/pegTokenizer.pegjs.txt
@@ -1548,7 +1548,7 @@ table_data_tags
     td:table_data_tag
     tagEndPos:({return pos})
     tds:( pipe_pipe tdt:table_data_tag { tdt[0].dataAttribs.stx_v = 'row';  return tdt } )* {
-        td[0].dataAttribs.tsr = [pos0, tagEndPos];
+        td[0].dataAttribs.tsr[0] = pos0;
         return td.concat(tds);
     }