From 904050fa36715e18522d80432a2666fcbaacd105 Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Wed, 22 Dec 2010 20:25:15 -0800
Subject: New HTML reader using tagsoup as a lexer.

* The new reader is faster and more accurate.

* API changes for Text.Pandoc.Readers.HTML:
   - removed rawHtmlBlock, anyHtmlBlockTag, anyHtmlInlineTag,
     anyHtmlTag, anyHtmlEndTag, htmlEndTag, extractTagType,
     htmlBlockElement, htmlComment
   - added htmlTag, htmlInBalanced, isInlineTag, isBlockTag, isTextTag

* tagsoup is a new dependency.

* Text.Pandoc.Parsing: Generalized type on readWith.

* Benchmark.hs: Added length calculation to force full evaluation.

* Updated HTML reader tests.

* Updated markdown and textile readers to use the functions from
  the HTML reader.

* Note: The markdown reader now correctly handles some cases it did not
  before. For example:

    <hr/>

  is reproduced without adding a space.

    <script>
      a = '<b>';
    </script>

  is parsed correctly.
---
 tests/html-reader.native | 8 ++++----
 tests/testsuite.txt      | 8 ++++----
 2 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'tests')

diff --git a/tests/html-reader.native b/tests/html-reader.native
index 5bf6c1b5c..5b7749712 100644
--- a/tests/html-reader.native
+++ b/tests/html-reader.native
@@ -269,8 +269,8 @@ Pandoc (Meta {docTitle = [Str "Pandoc",Space,Str "Test",Space,Str "Suite"], docA
   , [ Plain [Str "section:",Space,Str "\167"] ]
   , [ Plain [Str "set",Space,Str "membership:",Space,Str "\8712"] ]
   , [ Plain [Str "copyright:",Space,Str "\169"] ] ]
-, Para [Str "AT",Str "&",Str "T",Space,Str "has",Space,Str "an",Space,Str "ampersand",Space,Str "in",Space,Str "their",Space,Str "name",Str "."]
-, Para [Str "AT",Str "&",Str "T",Space,Str "is",Space,Str "another",Space,Str "way",Space,Str "to",Space,Str "write",Space,Str "it",Str "."]
+, Para [Str "AT&T",Space,Str "has",Space,Str "an",Space,Str "ampersand",Space,Str "in",Space,Str "their",Space,Str "name",Str "."]
+, Para [Str "AT&T",Space,Str "is",Space,Str "another",Space,Str "way",Space,Str "to",Space,Str "write",Space,Str "it",Str "."]
 , Para [Str "This",Space,Str "&",Space,Str "that",Str "."]
 , Para [Str "4",Space,Str "<",Space,Str "5",Str "."]
 , Para [Str "6",Space,Str ">",Space,Str "5",Str "."]
@@ -316,11 +316,11 @@ Pandoc (Meta {docTitle = [Str "Pandoc",Space,Str "Test",Space,Str "Suite"], docA
 , Para [Str "Foo",Space,Link [Str "biz"] ("/url/","Title with \"quote\" inside"),Str "."]
 , Header 2 [Str "With",Space,Str "ampersands"]
 , Para [Str "Here",Str "'",Str "s",Space,Str "a",Space,Link [Str "link",Space,Str "with",Space,Str "an",Space,Str "ampersand",Space,Str "in",Space,Str "the",Space,Str "URL"] ("http://example.com/?foo=1&bar=2",""),Str "."]
-, Para [Str "Here",Str "'",Str "s",Space,Str "a",Space,Str "link",Space,Str "with",Space,Str "an",Space,Str "amersand",Space,Str "in",Space,Str "the",Space,Str "link",Space,Str "text:",Space,Link [Str "AT",Str "&",Str "T"] ("http://att.com/","AT&T"),Str "."]
+, Para [Str "Here",Str "'",Str "s",Space,Str "a",Space,Str "link",Space,Str "with",Space,Str "an",Space,Str "amersand",Space,Str "in",Space,Str "the",Space,Str "link",Space,Str "text:",Space,Link [Str "AT&T"] ("http://att.com/","AT&T"),Str "."]
 , Para [Str "Here",Str "'",Str "s",Space,Str "an",Space,Link [Str "inline",Space,Str "link"] ("/script?foo=1&bar=2",""),Str "."]
 , Para [Str "Here",Str "'",Str "s",Space,Str "an",Space,Link [Str "inline",Space,Str "link",Space,Str "in",Space,Str "pointy",Space,Str "braces"] ("/script?foo=1&bar=2",""),Str "."]
 , Header 2 [Str "Autolinks"]
-, Para [Str "With",Space,Str "an",Space,Str "ampersand:",Space,Link [Str "http://example",Str ".",Str "com/?foo=1",Str "&",Str "bar=2"] ("http://example.com/?foo=1&bar=2","")]
+, Para [Str "With",Space,Str "an",Space,Str "ampersand:",Space,Link [Str "http://example",Str ".",Str "com/?foo=1&bar=2"] ("http://example.com/?foo=1&bar=2","")]
 , BulletList
   [ [ Plain [Str "In",Space,Str "a",Space,Str "list?"] ]
   , [ Plain [Link [Str "http://example",Str ".",Str "com/"] ("http://example.com/","")] ]
diff --git a/tests/testsuite.txt b/tests/testsuite.txt
index 91074efad..ccee0764a 100644
--- a/tests/testsuite.txt
+++ b/tests/testsuite.txt
@@ -431,21 +431,21 @@ Hr's:
 
 <hr>
 
-<hr/>
+<hr />
 
 <hr />
 
 <hr>   
 
-<hr/>  
+<hr />  
 
 <hr /> 
 
 <hr class="foo" id="bar" />
 
-<hr class="foo" id="bar"/>
+<hr class="foo" id="bar" />
 
-<hr class="foo" id="bar" >
+<hr class="foo" id="bar">
 
 -----
 
-- 
cgit v1.2.3