html-conduit 1.3.2.1 → 1.3.2.2

raw patch · 4 files changed

+29/−3 lines, 4 filesPVP ok

version bump matches the API change (PVP)

API changes (from Hackage documentation)

Files

ChangeLog.md +4/−0
html-conduit.cabal +4/−2
src/Text/HTML/DOM.hs +4/−1
test/main.hs +17/−0

ChangeLog.md view

@@ -1,5 +1,9 @@ # ChangeLog for `html-conduit` +## 1.3.2.2++* Fix handling of mixed case void tags [#167](https://github.com/snoyberg/xml/issues/167)+ ## 1.3.2.1  * Allow xml-conduit 1.9

html-conduit.cabal view

@@ -1,5 +1,5 @@ Name:                html-conduit-Version:             1.3.2.1+Version:             1.3.2.2 Synopsis:            Parse HTML documents using xml-conduit datatypes. Description:         This package uses tagstream-conduit for its parser. It automatically balances mismatched tags, so that there shouldn't be any parse failures. It does not handle a full HTML document rendering, such as adding missing html and head tags. Note that, since version 1.3.1, it uses an inlined copy of tagstream-conduit with entity decoding bugfixes applied. Homepage:            https://github.com/snoyberg/xml@@ -10,9 +10,10 @@ Category:            Web, Text, Conduit Build-type:          Simple Extra-source-files:  test/main.hs README.md ChangeLog.md LICENSE-tagstream-conduit-Cabal-version:       >=1.8+Cabal-version:       >=1.10  Library+  default-language:    Haskell2010   Exposed-modules:     Text.HTML.DOM   other-modules:       Text.HTML.TagStream   hs-source-dirs:      src@@ -31,6 +32,7 @@                      , conduit-extra  test-suite test+    default-language:    Haskell2010     type: exitcode-stdio-1.0     main-is: main.hs     hs-source-dirs: test

src/Text/HTML/DOM.hs view

@@ -77,7 +77,10 @@     toName l = XT.Name l Nothing Nothing     closeStack = mapM_ (yield . XT.EventEndElement) -    isVoid = flip Set.member $ Set.fromList+    isVoid name = Set.member (T.toLower name) voidSet++voidSet :: Set.Set T.Text+voidSet = Set.fromList         [ "area"         , "base"         , "br"

test/main.hs view

@@ -97,6 +97,23 @@                         ]                     ]              in H.parseLBS html @?= doc+        it "Mixed case br #167" $+            let html = "<html><head><title>foo</title></head><body><bR><p>Hello World</p><BR>done</body></html>"+                doc = X.Document (X.Prologue [] Nothing []) root []+                root = X.Element "html" Map.empty+                    [ X.NodeElement $ X.Element "head" Map.empty+                        [ X.NodeElement $ X.Element "title" Map.empty+                            [X.NodeContent "foo"]+                        ]+                    , X.NodeElement $ X.Element "body" Map.empty+                        [ X.NodeElement $ X.Element "bR" Map.empty []+                        , X.NodeElement $ X.Element "p" Map.empty+                            [X.NodeContent "Hello World"]+                        , X.NodeElement $ X.Element "BR" Map.empty []+                        , X.NodeContent "done"+                        ]+                    ]+             in H.parseLBS html @?= doc      it "doesn't double unescape" $         let html = "<p>Hello &amp;gt; World</p>"