Subramanya Sastry has uploaded a new change for review.
https://gerrit.wikimedia.org/r/293796
Change subject: Emit url-links where appropriate no matter what rel attribute
says
......................................................................
Emit url-links where appropriate no matter what rel attribute says
* A bunch of parser tests changed for the better including a bug
fix for fragments. [[#foo|#foo]] is correct, not #foo since #foo
will serialize as a list item or plain text, not as a link!
Change-Id: I273a4ea671e4455f2c67fb0c98e120445a5e4470
---
M lib/html2wt/LinkHandler.js
M tests/parserTests-blacklist.js
2 files changed, 69 insertions(+), 56 deletions(-)
git pull ssh://gerrit.wikimedia.org:29418/mediawiki/services/parsoid
refs/changes/96/293796/1
diff --git a/lib/html2wt/LinkHandler.js b/lib/html2wt/LinkHandler.js
index a17f19a..eaf330d 100644
--- a/lib/html2wt/LinkHandler.js
+++ b/lib/html2wt/LinkHandler.js
@@ -402,6 +402,9 @@
linkData.content.string =
Util.decodeURI(Util.decodeEntities(target.value));
}
p = Promise.resolve();
+ } else if (isURLLink(state.env, node, linkData)) {
+ state.emitChunk(new AutoURLLinkText(node.textContent, node),
node);
+ return;
} else {
p = Promise.resolve();
}
@@ -531,12 +534,25 @@
});
});
-var serializeAsExtLink = Promise.method(function(node, state, linkData) {
- var env = state.env;
- var wiki = env.conf.wiki;
+var isURLLink = function(env, node, linkData) {
var target = linkData.target;
var dp = DU.getDataParsoid(node);
+ // Get plain text content, if any
+ var contentStr = node.childNodes.length >= 1 &&
+ DU.allChildrenAreText(node) ? node.textContent : null;
+ // First check if we can serialize as an URL link
+ return (contentStr &&
+ // Can we minimize this?
+ (target.value === contentStr ||
+ getHref(env, node) === contentStr) &&
+ Util.isProtocolValid(contentStr, env) &&
+ // But preserve non-minimal encoding
+ (target.modified || linkData.contentModified || dp.stx
=== 'url'));
+};
+
+var serializeAsExtLink = Promise.method(function(node, state, linkData) {
+ var target = linkData.target;
var urlStr = target.value;
if (target.modified || !target.fromsrc) {
// We expect modified hrefs to be percent-encoded already, so
@@ -547,59 +563,57 @@
// percent-encoded because they are valid in URLs and HTML5
urlStr = escapeExtLinkURL(urlStr);
}
- // Get plain text content, if any
- var contentStr = node.childNodes.length >= 1 &&
- DU.allChildrenAreText(node) ? node.textContent : null;
- // First check if we can serialize as an URL link
- if (contentStr &&
- // Can we minimize this?
- (target.value === contentStr ||
- getHref(env, node) === contentStr) &&
- // But preserve non-minimal encoding
- (target.modified || linkData.contentModified || dp.stx
=== 'url')) {
+
+ if (isURLLink(state.env, node, linkData)) {
// Serialize as URL link
state.emitChunk(new AutoURLLinkText(urlStr, node), node);
return;
- } else {
- // TODO: match vs. interwikis too
- var magicLinkMatch =
wiki.ExtResourceURLPatternMatcher.match(Util.decodeURI(linkData.origHref));
- // Fully serialize the content
- return state.serializeLinkChildrenToString(node,
-
state.serializer.wteHandlers.aHandler).then(function(_contentStr) {
- contentStr = _contentStr;
- // First check for ISBN/RFC/PMID links. We rely on
selser to
- // preserve non-minimal forms.
- if (magicLinkMatch) {
- var serializer =
wiki.ExtResourceSerializer[magicLinkMatch[0]];
- var serialized = serializer(magicLinkMatch,
target.value, contentStr);
- if (serialized[0] === '[') {
- // Serialization as a magic link failed
(perhaps the
- // content string wasn't appropriate).
- state.emitChunk(magicLinkMatch[0] ===
'ISBN' ?
- new WikiLinkText(serialized,
node, wiki, 'mw:WikiLink') :
- new ExtLinkText(serialized,
node, wiki, 'mw:ExtLink'));
- } else {
- state.emitChunk(new
MagicLinkText(serialized, node), node);
- }
- return;
- // There is an interwiki for RFCs, but strangely none
for PMIDs.
- } else {
- // serialize as auto-numbered external link
- // [http://example.com]
- var linktext, Construct;
- // If it's just anchor text, serialize as an
internal link.
- if (/^#/.test(urlStr)) {
- Construct = WikiLinkText;
- linktext = '[[' + urlStr + (contentStr
? '|' + contentStr : '') + ']]';
- } else {
- Construct = ExtLinkText;
- linktext = '[' + urlStr + (contentStr ?
' ' + contentStr : '') + ']';
- }
- state.emitChunk(new Construct(linktext, node,
wiki, linkData.type), node);
- return;
- }
- });
}
+
+ var wiki = state.env.conf.wiki;
+
+ // Get plain text content, if any
+ var contentStr = node.childNodes.length >= 1 &&
+ DU.allChildrenAreText(node) ? node.textContent : null;
+
+ // TODO: match vs. interwikis too
+ var magicLinkMatch =
wiki.ExtResourceURLPatternMatcher.match(Util.decodeURI(linkData.origHref));
+ // Fully serialize the content
+ return state.serializeLinkChildrenToString(node,
+
state.serializer.wteHandlers.aHandler).then(function(_contentStr) {
+ contentStr = _contentStr;
+ // First check for ISBN/RFC/PMID links. We rely on selser to
+ // preserve non-minimal forms.
+ if (magicLinkMatch) {
+ var serializer =
wiki.ExtResourceSerializer[magicLinkMatch[0]];
+ var serialized = serializer(magicLinkMatch,
target.value, contentStr);
+ if (serialized[0] === '[') {
+ // Serialization as a magic link failed
(perhaps the
+ // content string wasn't appropriate).
+ state.emitChunk(magicLinkMatch[0] === 'ISBN' ?
+ new WikiLinkText(serialized, node,
wiki, 'mw:WikiLink') :
+ new ExtLinkText(serialized, node, wiki,
'mw:ExtLink'));
+ } else {
+ state.emitChunk(new MagicLinkText(serialized,
node), node);
+ }
+ return;
+ // There is an interwiki for RFCs, but strangely none for PMIDs.
+ } else {
+ // serialize as auto-numbered external link
+ // [http://example.com]
+ var linktext, Construct;
+ // If it's just anchor text, serialize as an internal
link.
+ if (/^#/.test(urlStr)) {
+ Construct = WikiLinkText;
+ linktext = '[[' + urlStr + (contentStr ? '|' +
contentStr : '') + ']]';
+ } else {
+ Construct = ExtLinkText;
+ linktext = '[' + urlStr + (contentStr ? ' ' +
contentStr : '') + ']';
+ }
+ state.emitChunk(new Construct(linktext, node, wiki,
linkData.type), node);
+ return;
+ }
+ });
});
var linkHandler = Promise.method(function(node) {
diff --git a/tests/parserTests-blacklist.js b/tests/parserTests-blacklist.js
index 9f2973c..f0bc1c5 100644
--- a/tests/parserTests-blacklist.js
+++ b/tests/parserTests-blacklist.js
@@ -396,7 +396,6 @@
// Blacklist for html2html
add("html2html", "Extra newlines followed by heading", "<p
data-parsoid='{\"dsr\":[0,1,0,0]}'>a</p>\n\n<p
data-parsoid='{\"dsr\":[3,3,0,0]}'><br
data-parsoid='{\"dsr\":[3,3,0,0]}'/></p>\n\n<h1
data-parsoid='{\"dsr\":[5,10,1,1]}'> b </h1>\n<p
data-parsoid='{\"dsr\":[11,55,0,0]}'>[/index.php?title=A&action=edit&redlink=1
a]</p>\n\n<p data-parsoid='{\"dsr\":[57,57,0,0]}'><br
data-parsoid='{\"dsr\":[57,57,0,0]}'/></p>\n\n<h1
data-parsoid='{\"dsr\":[59,64,1,1]}'> b </h1>\n");
add("html2html", "Extra newlines between heading and content are swallowed",
"<h1 data-parsoid='{\"dsr\":[0,5,1,1]}'> b </h1>\n<p
data-parsoid='{\"dsr\":[6,50,0,0]}'>[/index.php?title=A&action=edit&redlink=1
a]</p>\n");
-add("html2html", "Parsing an URL", "<p data-parsoid='{\"dsr\":[0,42,0,0]}'><a
rel=\"mw:ExtLink\" href=\"http://fr.wikipedia.org/wiki/🍺\"; title=\"fr:🍺\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"http://fr.wikipedia.org/wiki/🍺\"},\"sa\":{\"href\":\":fr:🍺\"},\"isIW\":true,\"dsr\":[0,42,9,2]}'>http://fr.wikipedia.org/wiki/🍺</a></p>\n");
add("html2html", "Italics and possessives (1)", "<p
data-parsoid='{\"dsr\":[0,115,0,0]}'>obtained by <i
data-parsoid='{\"dsr\":[12,91,2,2]}'>[/index.php?title=Lunar_Prospector&action=edit&redlink=1
Lunar Prospector]'</i>s gamma-ray spectrometer</p>\n");
add("html2html", "Italics and possessives (3)", "<p
data-parsoid='{\"dsr\":[0,421,0,0]}'>The first monolingual dictionary written
in a Romance language was <i data-parsoid='{\"dsr\":[67,93,2,2]}'>Sebastián
Covarrubias'</i> <i data-parsoid='{\"dsr\":[94,139,2,2]}'>Tesoro de la lengua
castellana o española</i>, published in 1611 in Madrid. In 1612 the first
edition of the <i data-parsoid='{\"dsr\":[203,310,2,2]}'>Vocabolario
dell'[/index.php?title=Accademia_della_Crusca&action=edit&redlink=1
Accademia della Crusca]</i>, for Italian, was published. In 1690 in Rotterdam
was published, posthumously, the <i
data-parsoid='{\"dsr\":[394,420,2,2]}'>Dictionnaire Universel</i>.</p>\n");
add("html2html", "Preformatted text", "<pre
data-parsoid='{\"dsr\":[0,96,1,0]}'>This is some\nPreformatted text\nWith <i
data-parsoid='{\"dsr\":[39,49,2,2]}'>italic</i>\nAnd <b
data-parsoid='{\"dsr\":[55,65,3,3]}'>bold</b>\nAnd a <a rel=\"mw:WikiLink\"
href=\"./Wiki/Main_Page\" title=\"Wiki/Main Page\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Wiki/Main_Page\"},\"sa\":{\"href\":\"wiki/Main
Page\"},\"dsr\":[73,96,17,2]}'>link</a></pre>\n");
@@ -519,7 +518,7 @@
add("html2html", "Link inside a section heading", "<h2
data-parsoid='{\"dsr\":[0,50,2,2]}'> Section with a <a rel=\"mw:WikiLink\"
href=\"./Wiki/Main_Page\" title=\"Wiki/Main Page\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Wiki/Main_Page\"},\"sa\":{\"href\":\"wiki/Main
Page\"},\"dsr\":[18,41,17,2]}'>link</a> in it </h2>\n");
add("html2html", "TOC regression (T14077)", "<div id=\"toc\" class=\"toc\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[0,339,26,6]}'><div id=\"toctitle\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[26,67,19,6]}'>\n<h2
data-parsoid='{\"dsr\":[46,60,2,2]}'> Contents </h2>\n</div>\n\n<ul
data-parsoid='{\"dsr\":[69,153,0,0]}'><li
data-parsoid='{\"dsr\":[69,153,1,0]}'> <a rel=\"mw:WikiLink\"
href=\"./Main_Page#title_1\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#title_1\"},\"sa\":{\"href\":\"#title_1\"},\"dsr\":[71,153,11,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[82,114,24,7]}'>1</span> <span
class=\"toctext\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[115,151,22,7]}'>title
1</span></a></li></ul>\n\n<ul data-parsoid='{\"dsr\":[155,331,0,0]}'><li
data-parsoid='{\"dsr\":[155,246,1,0]}'><ul
data-parsoid='{\"dsr\":[156,246,0,0]}'><li
data-parsoid='{\"dsr\":[156,246,1,0]}'> <a rel=\"mw:WikiLink\"
href=\"./Main_Page#title_1.1\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#title_1.1\"},\"sa\":{\"href\":\"#title_1.1\"},\"dsr\":[158,246,13,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[171,205,24,7]}'>1.1</span> <span
class=\"toctext\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[206,244,22,7]}'>title
1.1</span></a></li></ul></li>\n<li data-parsoid='{\"dsr\":[247,331,1,0]}'> <a
rel=\"mw:WikiLink\" href=\"./Main_Page#title_2\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#title_2\"},\"sa\":{\"href\":\"#title_2\"},\"dsr\":[249,331,11,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[260,292,24,7]}'>2</span> <span
class=\"toctext\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[293,329,22,7]}'>title
2</span></a></li></ul>\n\n</div>\n\n<h2 data-parsoid='{\"dsr\":[341,354,2,2]}'>
title 1 </h2>\n\n<h3 data-parsoid='{\"dsr\":[356,373,3,3]}'> title 1.1
</h3>\n\n<h2 data-parsoid='{\"dsr\":[375,388,2,2]}'> title 2 </h2>\n");
add("html2html", "Header with special characters (bug 25462)", "<p
data-parsoid='{\"dsr\":[0,72,0,0]}'>The tooltips shall not show entities to the
user (ie. be double escaped)</p>\n\n<div id=\"toc\" class=\"toc\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[74,625,26,6]}'><div id=\"toctitle\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[100,141,19,6]}'>\n<h2
data-parsoid='{\"dsr\":[120,134,2,2]}'> Contents </h2>\n</div>\n\n<ul
data-parsoid='{\"dsr\":[143,617,0,0]}'><li
data-parsoid='{\"dsr\":[143,237,1,0]}'> <a rel=\"mw:WikiLink\"
href=\"./Main_Page#text_.3E_text\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#text_.3E_text\"},\"sa\":{\"href\":\"#text_.3E_text\"},\"dsr\":[145,237,17,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[162,194,24,7]}'>1</span> <span
class=\"toctext\" data-parsoid='{\"stx\":\"html\",\"dsr\":[195,235,22,7]}'>text
> text</span></a></li>\n<li data-parsoid='{\"dsr\":[238,332,1,0]}'> <a
rel=\"mw:WikiLink\" href=\"./Main_Page#text_.3C_text\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#text_.3C_text\"},\"sa\":{\"href\":\"#text_.3C_text\"},\"dsr\":[240,332,17,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[257,289,24,7]}'>2</span> <span
class=\"toctext\" data-parsoid='{\"stx\":\"html\",\"dsr\":[290,330,22,7]}'>text
< text</span></a></li>\n<li data-parsoid='{\"dsr\":[333,427,1,0]}'> <a
rel=\"mw:WikiLink\" href=\"./Main_Page#text_.26_text\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#text_.26_text\"},\"sa\":{\"href\":\"#text_.26_text\"},\"dsr\":[335,427,17,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[352,384,24,7]}'>3</span> <span
class=\"toctext\" data-parsoid='{\"stx\":\"html\",\"dsr\":[385,425,22,7]}'>text
& text</span></a></li>\n<li data-parsoid='{\"dsr\":[428,522,1,0]}'> <a
rel=\"mw:WikiLink\" href=\"./Main_Page#text_.27_text\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#text_.27_text\"},\"sa\":{\"href\":\"#text_.27_text\"},\"dsr\":[430,522,17,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[447,479,24,7]}'>4</span> <span
class=\"toctext\" data-parsoid='{\"stx\":\"html\",\"dsr\":[480,520,22,7]}'>text
' text</span></a></li>\n<li data-parsoid='{\"dsr\":[523,617,1,0]}'> <a
rel=\"mw:WikiLink\" href=\"./Main_Page#text_.22_text\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#text_.22_text\"},\"sa\":{\"href\":\"#text_.22_text\"},\"dsr\":[525,617,17,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[542,574,24,7]}'>5</span> <span
class=\"toctext\" data-parsoid='{\"stx\":\"html\",\"dsr\":[575,615,22,7]}'>text
\" text</span></a></li></ul>\n\n</div>\n\n<h2
data-parsoid='{\"dsr\":[627,644,2,2]}'> text > text </h2>\n<p
data-parsoid='{\"dsr\":[645,654,0,0]}'>section 1</p>\n\n<h2
data-parsoid='{\"dsr\":[656,673,2,2]}'> text < text </h2>\n<p
data-parsoid='{\"dsr\":[674,683,0,0]}'>section 2</p>\n\n<h2
data-parsoid='{\"dsr\":[685,702,2,2]}'> text & text </h2>\n<p
data-parsoid='{\"dsr\":[703,712,0,0]}'>section 3</p>\n\n<h2
data-parsoid='{\"dsr\":[714,731,2,2]}'> text ' text </h2>\n<p
data-parsoid='{\"dsr\":[732,741,0,0]}'>section 4</p>\n\n<h2
data-parsoid='{\"dsr\":[743,760,2,2]}'> text \" text </h2>\n<p
data-parsoid='{\"dsr\":[761,770,0,0]}'>section 5</p>\n");
-add("html2html", "Header with space, plus and underscore as entity", "<p
data-parsoid='{\"dsr\":[0,34,0,0]}'>Id should not contain + for
spaces</p>\n\n<div id=\"toc\" class=\"toc\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[36,820,26,6]}'><div id=\"toctitle\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[62,103,19,6]}'>\n<h2
data-parsoid='{\"dsr\":[82,96,2,2]}'> Contents </h2>\n</div>\n\n<ul
data-parsoid='{\"dsr\":[105,812,0,0]}'><li
data-parsoid='{\"dsr\":[105,211,1,0]}'> <a rel=\"mw:WikiLink\"
href=\"./Main_Page#Space_between_Text\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#Space_between_Text\"},\"sa\":{\"href\":\"#Space_between_Text\"},\"dsr\":[107,211,22,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[129,161,24,7]}'>1</span> <span
class=\"toctext\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[162,209,22,7]}'>Space between
Text</span></a></li>\n<li data-parsoid='{\"dsr\":[212,332,1,0]}'> <a
rel=\"mw:WikiLink\" href=\"./Main_Page#Space-Entity_between_Text\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#Space-Entity_between_Text\"},\"sa\":{\"href\":\"#Space-Entity_between_Text\"},\"dsr\":[214,332,29,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[243,275,24,7]}'>2</span> <span
class=\"toctext\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[276,330,22,7]}'>Space-Entity between
Text</span></a></li>\n<li data-parsoid='{\"dsr\":[333,441,1,0]}'> <a
rel=\"mw:WikiLink\" href=\"./Main_Page#Plus.2Bbetween.2BText\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#Plus.2Bbetween.2BText\"},\"sa\":{\"href\":\"#Plus.2Bbetween.2BText\"},\"dsr\":[335,441,25,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[360,392,24,7]}'>3</span> <span
class=\"toctext\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[393,439,22,7]}'>Plus+between+Text</span></a></li>\n<li
data-parsoid='{\"dsr\":[442,564,1,0]}'> <a rel=\"mw:WikiLink\"
href=\"./Main_Page#Plus-Entity.2Bbetween.2BText\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#Plus-Entity.2Bbetween.2BText\"},\"sa\":{\"href\":\"#Plus-Entity.2Bbetween.2BText\"},\"dsr\":[444,564,32,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[476,508,24,7]}'>4</span> <span
class=\"toctext\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[509,562,22,7]}'>Plus-Entity+between+Text</span></a></li>\n<li
data-parsoid='{\"dsr\":[565,681,1,0]}'> <a rel=\"mw:WikiLink\"
href=\"./Main_Page#Underscore_between_Text\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#Underscore_between_Text\"},\"sa\":{\"href\":\"#Underscore_between_Text\"},\"dsr\":[567,681,27,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[594,626,24,7]}'>5</span> <span
class=\"toctext\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[627,679,22,7]}'>Underscore_between_Text</span></a></li>\n<li
data-parsoid='{\"dsr\":[682,812,1,0]}'> <a rel=\"mw:WikiLink\"
href=\"./Main_Page#Underscore-Entity_between_Text\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#Underscore-Entity_between_Text\"},\"sa\":{\"href\":\"#Underscore-Entity_between_Text\"},\"dsr\":[684,812,34,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[718,750,24,7]}'>6</span> <span
class=\"toctext\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[751,810,22,7]}'>Underscore-Entity_between_Text</span></a></li></ul>\n\n</div>\n\n<h2
data-parsoid='{\"dsr\":[822,846,2,2]}'> Space between Text </h2>\n<p
data-parsoid='{\"dsr\":[847,856,0,0]}'>section 1</p>\n\n<h2
data-parsoid='{\"dsr\":[858,889,2,2]}'> Space-Entity between Text </h2>\n<p
data-parsoid='{\"dsr\":[890,899,0,0]}'>section 2</p>\n\n<h2
data-parsoid='{\"dsr\":[901,924,2,2]}'> Plus+between+Text </h2>\n<p
data-parsoid='{\"dsr\":[925,934,0,0]}'>section 3</p>\n\n<h2
data-parsoid='{\"dsr\":[936,966,2,2]}'> Plus-Entity+between+Text </h2>\n<p
data-parsoid='{\"dsr\":[967,976,0,0]}'>section 4</p>\n\n<h2
data-parsoid='{\"dsr\":[978,1007,2,2]}'> Underscore_between_Text </h2>\n<p
data-parsoid='{\"dsr\":[1008,1017,0,0]}'>section 5</p>\n\n<h2
data-parsoid='{\"dsr\":[1019,1055,2,2]}'> Underscore-Entity_between_Text
</h2>\n<p data-parsoid='{\"dsr\":[1056,1065,0,0]}'>section 6</p>\n\n<p
data-parsoid='{\"dsr\":[1067,1274,0,0]}'><a rel=\"mw:WikiLink\"
href=\"./Main_Page#Space_between_Text\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#Space_between_Text\"},\"sa\":{\"href\":\"#Space_between_Text\"},\"dsr\":[1067,1110,22,2]}'>#Space
between Text</a>\n<a rel=\"mw:WikiLink\"
href=\"./Main_Page#Space-Entity_between_Text\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#Space-Entity_between_Text\"},\"sa\":{\"href\":\"#Space-Entity_between_Text\"},\"dsr\":[1111,1168,29,2]}'>#Space-Entity
between Text</a>\n<a rel=\"mw:WikiLink\"
href=\"./Main_Page#Plus.2Bbetween.2BText\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#Plus.2Bbetween.2BText\"},\"sa\":{\"href\":\"#Plus.2Bbetween.2BText\"},\"dsr\":[1169,1214,25,2]}'>#Plus+between+Text</a>\n<a
rel=\"mw:WikiLink\" href=\"./Main_Page#Plus-Entity.2Bbetween.2BText\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#Plus-Entity.2Bbetween.2BText\"},\"sa\":{\"href\":\"#Plus-Entity.2Bbetween.2BText\"},\"dsr\":[1215,1274,32,2]}'>#Plus-Entity+between+Text</a></p>\n<ol
data-parsoid='{\"dsr\":[1275,1331,0,0]}'><li
data-parsoid='{\"dsr\":[1275,1299,1,0]}'>Underscore_between_Text</li>\n<li
data-parsoid='{\"dsr\":[1300,1331,1,0]}'>Underscore-Entity_between_Text</li></ol>\n");
+add("html2html", "Header with space, plus and underscore as entity", "<p
data-parsoid='{\"dsr\":[0,34,0,0]}'>Id should not contain + for
spaces</p>\n\n<div id=\"toc\" class=\"toc\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[36,820,26,6]}'><div id=\"toctitle\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[62,103,19,6]}'>\n<h2
data-parsoid='{\"dsr\":[82,96,2,2]}'> Contents </h2>\n</div>\n\n<ul
data-parsoid='{\"dsr\":[105,812,0,0]}'><li
data-parsoid='{\"dsr\":[105,211,1,0]}'> <a rel=\"mw:WikiLink\"
href=\"./Main_Page#Space_between_Text\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#Space_between_Text\"},\"sa\":{\"href\":\"#Space_between_Text\"},\"dsr\":[107,211,22,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[129,161,24,7]}'>1</span> <span
class=\"toctext\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[162,209,22,7]}'>Space between
Text</span></a></li>\n<li data-parsoid='{\"dsr\":[212,332,1,0]}'> <a
rel=\"mw:WikiLink\" href=\"./Main_Page#Space-Entity_between_Text\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#Space-Entity_between_Text\"},\"sa\":{\"href\":\"#Space-Entity_between_Text\"},\"dsr\":[214,332,29,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[243,275,24,7]}'>2</span> <span
class=\"toctext\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[276,330,22,7]}'>Space-Entity between
Text</span></a></li>\n<li data-parsoid='{\"dsr\":[333,441,1,0]}'> <a
rel=\"mw:WikiLink\" href=\"./Main_Page#Plus.2Bbetween.2BText\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#Plus.2Bbetween.2BText\"},\"sa\":{\"href\":\"#Plus.2Bbetween.2BText\"},\"dsr\":[335,441,25,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[360,392,24,7]}'>3</span> <span
class=\"toctext\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[393,439,22,7]}'>Plus+between+Text</span></a></li>\n<li
data-parsoid='{\"dsr\":[442,564,1,0]}'> <a rel=\"mw:WikiLink\"
href=\"./Main_Page#Plus-Entity.2Bbetween.2BText\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#Plus-Entity.2Bbetween.2BText\"},\"sa\":{\"href\":\"#Plus-Entity.2Bbetween.2BText\"},\"dsr\":[444,564,32,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[476,508,24,7]}'>4</span> <span
class=\"toctext\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[509,562,22,7]}'>Plus-Entity+between+Text</span></a></li>\n<li
data-parsoid='{\"dsr\":[565,681,1,0]}'> <a rel=\"mw:WikiLink\"
href=\"./Main_Page#Underscore_between_Text\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#Underscore_between_Text\"},\"sa\":{\"href\":\"#Underscore_between_Text\"},\"dsr\":[567,681,27,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[594,626,24,7]}'>5</span> <span
class=\"toctext\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[627,679,22,7]}'>Underscore_between_Text</span></a></li>\n<li
data-parsoid='{\"dsr\":[682,812,1,0]}'> <a rel=\"mw:WikiLink\"
href=\"./Main_Page#Underscore-Entity_between_Text\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#Underscore-Entity_between_Text\"},\"sa\":{\"href\":\"#Underscore-Entity_between_Text\"},\"dsr\":[684,812,34,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[718,750,24,7]}'>6</span> <span
class=\"toctext\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[751,810,22,7]}'>Underscore-Entity_between_Text</span></a></li></ul>\n\n</div>\n\n<h2
data-parsoid='{\"dsr\":[822,846,2,2]}'> Space between Text </h2>\n<p
data-parsoid='{\"dsr\":[847,856,0,0]}'>section 1</p>\n\n<h2
data-parsoid='{\"dsr\":[858,889,2,2]}'> Space-Entity between Text </h2>\n<p
data-parsoid='{\"dsr\":[890,899,0,0]}'>section 2</p>\n\n<h2
data-parsoid='{\"dsr\":[901,924,2,2]}'> Plus+between+Text </h2>\n<p
data-parsoid='{\"dsr\":[925,934,0,0]}'>section 3</p>\n\n<h2
data-parsoid='{\"dsr\":[936,966,2,2]}'> Plus-Entity+between+Text </h2>\n<p
data-parsoid='{\"dsr\":[967,976,0,0]}'>section 4</p>\n\n<h2
data-parsoid='{\"dsr\":[978,1007,2,2]}'> Underscore_between_Text </h2>\n<p
data-parsoid='{\"dsr\":[1008,1017,0,0]}'>section 5</p>\n\n<h2
data-parsoid='{\"dsr\":[1019,1055,2,2]}'> Underscore-Entity_between_Text
</h2>\n<p data-parsoid='{\"dsr\":[1056,1065,0,0]}'>section 6</p>\n\n<p
data-parsoid='{\"dsr\":[1067,1396,0,0]}'><a rel=\"mw:WikiLink\"
href=\"./Main_Page#Space_between_Text\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#Space_between_Text\"},\"sa\":{\"href\":\"#Space_between_Text\"},\"dsr\":[1067,1110,22,2]}'>#Space
between Text</a>\n<a rel=\"mw:WikiLink\"
href=\"./Main_Page#Space-Entity_between_Text\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#Space-Entity_between_Text\"},\"sa\":{\"href\":\"#Space-Entity_between_Text\"},\"dsr\":[1111,1168,29,2]}'>#Space-Entity
between Text</a>\n<a rel=\"mw:WikiLink\"
href=\"./Main_Page#Plus.2Bbetween.2BText\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#Plus.2Bbetween.2BText\"},\"sa\":{\"href\":\"#Plus.2Bbetween.2BText\"},\"dsr\":[1169,1214,25,2]}'>#Plus+between+Text</a>\n<a
rel=\"mw:WikiLink\" href=\"./Main_Page#Plus-Entity.2Bbetween.2BText\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#Plus-Entity.2Bbetween.2BText\"},\"sa\":{\"href\":\"#Plus-Entity.2Bbetween.2BText\"},\"dsr\":[1215,1274,32,2]}'>#Plus-Entity+between+Text</a>\n<a
rel=\"mw:WikiLink\" href=\"./Main_Page#Underscore_between_Text\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#Underscore_between_Text\"},\"sa\":{\"href\":\"#Underscore_between_Text\"},\"dsr\":[1275,1328,27,2]}'>#Underscore_between_Text</a>\n<a
rel=\"mw:WikiLink\" href=\"./Main_Page#Underscore-Entity_between_Text\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#Underscore-Entity_between_Text\"},\"sa\":{\"href\":\"#Underscore-Entity_between_Text\"},\"dsr\":[1329,1396,34,2]}'>#Underscore-Entity_between_Text</a></p>\n");
add("html2html", "Headers with excess '=' characters\n(Are similar tests
necessary beyond the 1st level?)", "<div id=\"toc\" class=\"toc\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[0,452,26,6]}'><div id=\"toctitle\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[26,67,19,6]}'>\n<h2
data-parsoid='{\"dsr\":[46,60,2,2]}'> Contents </h2>\n</div>\n\n<ul
data-parsoid='{\"dsr\":[69,444,0,0]}'><li
data-parsoid='{\"dsr\":[69,149,1,0]}'> <a rel=\"mw:WikiLink\"
href=\"./Main_Page#foo.3D\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#foo.3D\"},\"sa\":{\"href\":\"#foo.3D\"},\"dsr\":[71,149,10,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[81,113,24,7]}'>1</span> <span
class=\"toctext\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[114,147,22,7]}'>foo=</span></a></li>\n<li
data-parsoid='{\"dsr\":[150,230,1,0]}'> <a rel=\"mw:WikiLink\"
href=\"./Main_Page#.3Dfoo\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#.3Dfoo\"},\"sa\":{\"href\":\"#.3Dfoo\"},\"dsr\":[152,230,10,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[162,194,24,7]}'>2</span> <span
class=\"toctext\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[195,228,22,7]}'>=foo</span></a></li>\n<li
data-parsoid='{\"dsr\":[231,337,1,0]}'> <a rel=\"mw:WikiLink\"
href=\"./Main_Page#italic_heading.3D\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#italic_heading.3D\"},\"sa\":{\"href\":\"#italic_heading.3D\"},\"dsr\":[233,337,21,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[254,286,24,7]}'>3</span> <span
class=\"toctext\" data-parsoid='{\"stx\":\"html\",\"dsr\":[287,335,22,7]}'><i
data-parsoid='{\"dsr\":[309,319,2,2]}'>italic</i> heading=</span></a></li>\n<li
data-parsoid='{\"dsr\":[338,444,1,0]}'> <a rel=\"mw:WikiLink\"
href=\"./Main_Page#.3Ditalic_heading\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#.3Ditalic_heading\"},\"sa\":{\"href\":\"#.3Ditalic_heading\"},\"dsr\":[340,444,21,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[361,393,24,7]}'>4</span> <span
class=\"toctext\" data-parsoid='{\"stx\":\"html\",\"dsr\":[394,442,22,7]}'>=<i
data-parsoid='{\"dsr\":[417,427,2,2]}'>italic</i>
heading</span></a></li></ul>\n\n</div>\n\n<h1
data-parsoid='{\"dsr\":[454,462,1,1]}'> foo= </h1>\n\n<h1
data-parsoid='{\"dsr\":[464,472,1,1]}'> =foo </h1>\n\n<h1
data-parsoid='{\"dsr\":[474,497,1,1]}'> <i
data-parsoid='{\"dsr\":[476,486,2,2]}'>italic</i> heading= </h1>\n\n<h1
data-parsoid='{\"dsr\":[499,522,1,1]}'> =<i
data-parsoid='{\"dsr\":[502,512,2,2]}'>italic</i> heading </h1>\n");
add("html2html", "HTML headers vs TOC (bug 23393)\n(__NOEDITSECTION__ for
clearer output, doesn't matter here)", "<div id=\"toc\" class=\"toc\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[0,628,26,6]}'><div id=\"toctitle\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[26,67,19,6]}'>\n<h2
data-parsoid='{\"dsr\":[46,60,2,2]}'> Contents </h2>\n</div>\n\n<ul
data-parsoid='{\"dsr\":[69,155,0,0]}'><li
data-parsoid='{\"dsr\":[69,155,1,0]}'> <a rel=\"mw:WikiLink\"
href=\"./Main_Page#Header_1\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#Header_1\"},\"sa\":{\"href\":\"#Header_1\"},\"dsr\":[71,155,12,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[83,115,24,7]}'>1</span> <span
class=\"toctext\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[116,153,22,7]}'>Header
1</span></a></li></ul>\n\n<ul data-parsoid='{\"dsr\":[157,431,0,0]}'><li
data-parsoid='{\"dsr\":[157,344,1,0]}'><ul
data-parsoid='{\"dsr\":[158,344,0,0]}'><li
data-parsoid='{\"dsr\":[158,250,1,0]}'> <a rel=\"mw:WikiLink\"
href=\"./Main_Page#Header_1.1\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#Header_1.1\"},\"sa\":{\"href\":\"#Header_1.1\"},\"dsr\":[160,250,14,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[174,208,24,7]}'>1.1</span> <span
class=\"toctext\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[209,248,22,7]}'>Header
1.1</span></a></li>\n<li data-parsoid='{\"dsr\":[251,344,2,0]}'> <a
rel=\"mw:WikiLink\" href=\"./Main_Page#Header_1.2\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#Header_1.2\"},\"sa\":{\"href\":\"#Header_1.2\"},\"dsr\":[254,344,14,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[268,302,24,7]}'>1.2</span> <span
class=\"toctext\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[303,342,22,7]}'>Header
1.2</span></a></li></ul></li>\n<li data-parsoid='{\"dsr\":[345,431,1,0]}'> <a
rel=\"mw:WikiLink\" href=\"./Main_Page#Header_2\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#Header_2\"},\"sa\":{\"href\":\"#Header_2\"},\"dsr\":[347,431,12,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[359,391,24,7]}'>2</span> <span
class=\"toctext\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[392,429,22,7]}'>Header
2</span></a></li></ul>\n\n<ul data-parsoid='{\"dsr\":[433,620,0,0]}'><li
data-parsoid='{\"dsr\":[433,620,1,0]}'><ul
data-parsoid='{\"dsr\":[434,620,0,0]}'><li
data-parsoid='{\"dsr\":[434,526,1,0]}'> <a rel=\"mw:WikiLink\"
href=\"./Main_Page#Header_2.1\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#Header_2.1\"},\"sa\":{\"href\":\"#Header_2.1\"},\"dsr\":[436,526,14,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[450,484,24,7]}'>2.1</span> <span
class=\"toctext\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[485,524,22,7]}'>Header
2.1</span></a></li>\n<li data-parsoid='{\"dsr\":[527,620,2,0]}'> <a
rel=\"mw:WikiLink\" href=\"./Main_Page#Header_2.2\"
data-parsoid='{\"stx\":\"piped\",\"a\":{\"href\":\"./Main_Page#Header_2.2\"},\"sa\":{\"href\":\"#Header_2.2\"},\"dsr\":[530,620,14,2]}'><span
class=\"tocnumber\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[544,578,24,7]}'>2.2</span> <span
class=\"toctext\"
data-parsoid='{\"stx\":\"html\",\"dsr\":[579,618,22,7]}'>Header
2.2</span></a></li></ul></li></ul>\n\n</div>\n\n<h1
data-parsoid='{\"dsr\":[630,642,1,1]}'> Header 1 </h1>\n\n<h2
data-parsoid='{\"dsr\":[644,660,2,2]}'> Header 1.1 </h2>\n\n<h2
data-parsoid='{\"dsr\":[662,678,2,2]}'> Header 1.2 </h2>\n\n<h1
data-parsoid='{\"dsr\":[680,692,1,1]}'> Header 2 </h1>\n\n<h2
data-parsoid='{\"dsr\":[694,710,2,2]}'> Header 2.1 </h2>\n\n<h2
data-parsoid='{\"dsr\":[712,728,2,2]}'> Header 2.2 </h2>\n");
add("html2html", "Media link", "<p data-parsoid='{\"dsr\":[0,60,0,0]}'><a
rel=\"mw:ExtLink\" href=\"http://example.com/images/3/3a/Foobar.jpg\";
data-parsoid='{\"targetOff\":43,\"contentOffsets\":[43,59],\"dsr\":[0,60,43,1]}'>Media:Foobar.jpg</a></p>\n");
@@ -634,7 +633,7 @@
add("html2wt", "Extra newlines: More paragraphs with indented comment",
"a\n\n\nb\n");
add("html2wt", "Extra newlines followed by heading", "a\n\n\n\n= b
=\n[/index.php?title=A&action=edit&redlink=1 a]\n\n\n\n= b =\n");
add("html2wt", "Extra newlines between heading and content are swallowed", "=
b =\n[/index.php?title=A&action=edit&redlink=1 a]\n");
-add("html2wt", "Parsing an URL", "[[:fr:🍺|http://fr.wikipedia.org/wiki/🍺]]\n";);
+add("html2wt", "Parsing an URL", "http://fr.wikipedia.org/wiki/🍺\n";);
add("html2wt", "Italics and possessives (1)", "obtained by
''[/index.php?title=Lunar_Prospector&action=edit&redlink=1 Lunar
Prospector]'''s gamma-ray spectrometer\n");
add("html2wt", "Italics and possessives (3)", "The first monolingual
dictionary written in a Romance language was ''Sebastián Covarrubias'''
''Tesoro de la lengua castellana o española'', published in 1611 in Madrid. In
1612 the first edition of the ''Vocabolario
dell'[/index.php?title=Accademia_della_Crusca&action=edit&redlink=1 Accademia
della Crusca]'', for Italian, was published. In 1690 in Rotterdam was
published, posthumously, the ''Dictionnaire Universel''.\n");
add("html2wt", "<wbr> is valid wikitext (bug 52468)", "<wbr />\n");
@@ -1059,7 +1058,7 @@
add("html2wt", "TOC regression (T14077)", "<div id=\"toc\" class=\"toc\"><div
id=\"toctitle\">\n== Contents ==\n</div>\n\n* [[#title_1|<span
class=\"tocnumber\">1</span> <span class=\"toctext\">title 1</span>]]\n\n**
[[#title_1.1|<span class=\"tocnumber\">1.1</span> <span class=\"toctext\">title
1.1</span>]]\n* [[#title_2|<span class=\"tocnumber\">2</span> <span
class=\"toctext\">title 2</span>]]\n\n</div>\n\n== title 1 ==\n\n=== title 1.1
===\n\n== title 2 ==\n");
add("html2wt", "Short headings with trailing space should match behavior of
Parser::doHeadings (bug 19910)", "= = =\nThe line above must have a trailing
space!\n\n= = =\nBut just in case it doesn't...\n");
add("html2wt", "Header with special characters (bug 25462)", "The tooltips
shall not show entities to the user (ie. be double escaped)\n\n<div id=\"toc\"
class=\"toc\"><div id=\"toctitle\">\n== Contents ==\n</div>\n\n*
[[#text_.3E_text|<span class=\"tocnumber\">1</span> <span
class=\"toctext\">text > text</span>]]\n* [[#text_.3C_text|<span
class=\"tocnumber\">2</span> <span class=\"toctext\">text < text</span>]]\n*
[[#text_.26_text|<span class=\"tocnumber\">3</span> <span
class=\"toctext\">text & text</span>]]\n* [[#text_.27_text|<span
class=\"tocnumber\">4</span> <span class=\"toctext\">text ' text</span>]]\n*
[[#text_.22_text|<span class=\"tocnumber\">5</span> <span
class=\"toctext\">text \" text</span>]]\n\n</div>\n\n== text > text ==\nsection
1\n\n== text < text ==\nsection 2\n\n== text & text ==\nsection 3\n\n== text '
text ==\nsection 4\n\n== text \" text ==\nsection 5\n");
-add("html2wt", "Header with space, plus and underscore as entity", "Id should
not contain + for spaces\n\n<div id=\"toc\" class=\"toc\"><div
id=\"toctitle\">\n== Contents ==\n</div>\n\n* [[#Space_between_Text|<span
class=\"tocnumber\">1</span> <span class=\"toctext\">Space between
Text</span>]]\n* [[#Space-Entity_between_Text|<span
class=\"tocnumber\">2</span> <span class=\"toctext\">Space-Entity between
Text</span>]]\n* [[#Plus.2Bbetween.2BText|<span class=\"tocnumber\">3</span>
<span class=\"toctext\">Plus+between+Text</span>]]\n*
[[#Plus-Entity.2Bbetween.2BText|<span class=\"tocnumber\">4</span> <span
class=\"toctext\">Plus-Entity+between+Text</span>]]\n*
[[#Underscore_between_Text|<span class=\"tocnumber\">5</span> <span
class=\"toctext\">Underscore_between_Text</span>]]\n*
[[#Underscore-Entity_between_Text|<span class=\"tocnumber\">6</span> <span
class=\"toctext\">Underscore-Entity_between_Text</span>]]\n\n</div>\n\n== Space
between Text ==\nsection 1\n\n== Space-Entity between Text ==\nsection 2\n\n==
Plus+between+Text ==\nsection 3\n\n== Plus-Entity+between+Text ==\nsection
4\n\n== Underscore_between_Text ==\nsection 5\n\n==
Underscore-Entity_between_Text ==\nsection 6\n\n[[#Space_between_Text|#Space
between Text]]\n[[#Space-Entity_between_Text|#Space-Entity between
Text]]\n[[#Plus.2Bbetween.2BText|#Plus+between+Text]]\n[[#Plus-Entity.2Bbetween.2BText|#Plus-Entity+between+Text]]\n#Underscore_between_Text\n#Underscore-Entity_between_Text\n");
+add("html2wt", "Header with space, plus and underscore as entity", "Id should
not contain + for spaces\n\n<div id=\"toc\" class=\"toc\"><div
id=\"toctitle\">\n== Contents ==\n</div>\n\n* [[#Space_between_Text|<span
class=\"tocnumber\">1</span> <span class=\"toctext\">Space between
Text</span>]]\n* [[#Space-Entity_between_Text|<span
class=\"tocnumber\">2</span> <span class=\"toctext\">Space-Entity between
Text</span>]]\n* [[#Plus.2Bbetween.2BText|<span class=\"tocnumber\">3</span>
<span class=\"toctext\">Plus+between+Text</span>]]\n*
[[#Plus-Entity.2Bbetween.2BText|<span class=\"tocnumber\">4</span> <span
class=\"toctext\">Plus-Entity+between+Text</span>]]\n*
[[#Underscore_between_Text|<span class=\"tocnumber\">5</span> <span
class=\"toctext\">Underscore_between_Text</span>]]\n*
[[#Underscore-Entity_between_Text|<span class=\"tocnumber\">6</span> <span
class=\"toctext\">Underscore-Entity_between_Text</span>]]\n\n</div>\n\n== Space
between Text ==\nsection 1\n\n== Space-Entity between Text ==\nsection 2\n\n==
Plus+between+Text ==\nsection 3\n\n== Plus-Entity+between+Text ==\nsection
4\n\n== Underscore_between_Text ==\nsection 5\n\n==
Underscore-Entity_between_Text ==\nsection 6\n\n[[#Space_between_Text|#Space
between Text]]\n[[#Space-Entity_between_Text|#Space-Entity between
Text]]\n[[#Plus.2Bbetween.2BText|#Plus+between+Text]]\n[[#Plus-Entity.2Bbetween.2BText|#Plus-Entity+between+Text]]\n[[#Underscore_between_Text|#Underscore_between_Text]]\n[[#Underscore-Entity_between_Text|#Underscore-Entity_between_Text]]\n");
add("html2wt", "Headers with excess '=' characters\n(Are similar tests
necessary beyond the 1st level?)", "<div id=\"toc\" class=\"toc\"><div
id=\"toctitle\">\n== Contents ==\n</div>\n\n* [[#foo.3D|<span
class=\"tocnumber\">1</span> <span class=\"toctext\">foo=</span>]]\n*
[[#.3Dfoo|<span class=\"tocnumber\">2</span> <span
class=\"toctext\">=foo</span>]]\n* [[#italic_heading.3D|<span
class=\"tocnumber\">3</span> <span class=\"toctext\">''italic''
heading=</span>]]\n* [[#.3Ditalic_heading|<span class=\"tocnumber\">4</span>
<span class=\"toctext\">=''italic'' heading</span>]]\n\n</div>\n\n= foo= =\n\n=
=foo =\n\n= ''italic'' heading= =\n\n= =''italic'' heading =\n");
add("html2wt", "HTML headers vs TOC (bug 23393)\n(__NOEDITSECTION__ for
clearer output, doesn't matter here)", "<div id=\"toc\" class=\"toc\"><div
id=\"toctitle\">\n== Contents ==\n</div>\n\n* [[#Header_1|<span
class=\"tocnumber\">1</span> <span class=\"toctext\">Header 1</span>]]\n\n**
[[#Header_1.1|<span class=\"tocnumber\">1.1</span> <span
class=\"toctext\">Header 1.1</span>]]\n** [[#Header_1.2|<span
class=\"tocnumber\">1.2</span> <span class=\"toctext\">Header 1.2</span>]]\n*
[[#Header_2|<span class=\"tocnumber\">2</span> <span class=\"toctext\">Header
2</span>]]\n\n** [[#Header_2.1|<span class=\"tocnumber\">2.1</span> <span
class=\"toctext\">Header 2.1</span>]]\n** [[#Header_2.2|<span
class=\"tocnumber\">2.2</span> <span class=\"toctext\">Header
2.2</span>]]\n\n</div>\n\n= Header 1 =\n\n== Header 1.1 ==\n\n== Header 1.2
==\n\n= Header 2 =\n\n== Header 2.1 ==\n\n== Header 2.2 ==\n");
add("html2wt", "Namespaced link must have a title",
"<nowiki>[[Project:]]</nowiki>\n");
--
To view, visit https://gerrit.wikimedia.org/r/293796
To unsubscribe, visit https://gerrit.wikimedia.org/r/settings
Gerrit-MessageType: newchange
Gerrit-Change-Id: I273a4ea671e4455f2c67fb0c98e120445a5e4470
Gerrit-PatchSet: 1
Gerrit-Project: mediawiki/services/parsoid
Gerrit-Branch: master
Gerrit-Owner: Subramanya Sastry <ssas...@wikimedia.org>
_______________________________________________
MediaWiki-commits mailing list
MediaWiki-commits@lists.wikimedia.org
https://lists.wikimedia.org/mailman/listinfo/mediawiki-commits
![http://example.com/images/3/3a/Foobar.jpg\"](http://example.com/images/3/3a/Foobar.jpg\"){kind=link}