diff --git a/html-tokenizer.cabal b/html-tokenizer.cabal
--- a/html-tokenizer.cabal
+++ b/html-tokenizer.cabal
@@ -1,18 +1,11 @@
name:
html-tokenizer
version:
- 0.5
+ 0.5.1
synopsis:
An "attoparsec"-based HTML tokenizer
description:
- This library can be used as a basis for complex HTML parsers,
- or for streaming.
- E.g., by composing it with
-
- you can produce a token stream,
- thus becoming able to implement a highly efficient stream-parser,
- which works in a single pass, constant memory and is capable of early termination.
- is such a parser.
+ This library can be used as a basis for streaming HTML parsers.
category:
Parsing, HTML, XML
homepage:
diff --git a/library/HTMLTokenizer/Parsing.hs b/library/HTMLTokenizer/Parsing.hs
--- a/library/HTMLTokenizer/Parsing.hs
+++ b/library/HTMLTokenizer/Parsing.hs
@@ -20,11 +20,11 @@
token :: Parser Token
token =
labeled "HTML Token" $
+ DoctypeToken <$> doctype <|>
openingTag OpeningTagToken <|>
ClosingTagToken <$> closingTag <|>
TextToken <$> textBetweenTags <|>
CommentToken <$> comment <|>
- DoctypeToken <$> doctype <|>
fail "Invalid token"
{-|
diff --git a/tests/Main.hs b/tests/Main.hs
--- a/tests/Main.hs
+++ b/tests/Main.hs
@@ -60,6 +60,10 @@
(Right (A.ClosingTagToken (A.UnprefixedName "x")))
""
,
+ testTokenParsing "Closing tag"
+ (Right (A.DoctypeToken "html"))
+ ""
+ ,
testTokensParsing "Text between tags, stripped"
(Right
[