html-tokenizer 0.6 → 0.6.1

raw patch · 8 files changed

+146/−21 lines, 8 filesPVP: major bump suggested

API removals or changes: PVP suggests a major version bump

API changes (from Hackage documentation)

Files

• html-tokenizer.cabal +6/−1
• library/HTMLTokenizer/Data.hs +8/−20
• library/HTMLTokenizer/Data/Instances/Eq.hs +10/−0
• library/HTMLTokenizer/Data/Instances/Show.hs +16/−0
• library/HTMLTokenizer/Data/Types.hs +20/−0
• library/HTMLTokenizer/Prelude.hs +14/−0
• library/HTMLTokenizer/Rendering/Text.hs +17/−0
• library/HTMLTokenizer/Rendering/Text/Builder.hs +55/−0

@@ -1,7 +1,7 @@ name:   html-tokenizer version:-  0.6+  0.6.1 synopsis:   An "attoparsec"-based HTML tokenizer description:@@ -43,7 +43,12 @@   exposed-modules:     HTMLTokenizer.Data     HTMLTokenizer.Parsing+    HTMLTokenizer.Rendering.Text+    HTMLTokenizer.Rendering.Text.Builder   other-modules:+    HTMLTokenizer.Data.Types+    HTMLTokenizer.Data.Instances.Show+    HTMLTokenizer.Data.Instances.Eq     HTMLTokenizer.MonadPlus     HTMLTokenizer.Prelude   build-depends:

@@ -1,23 +1,11 @@-{-# OPTIONS_GHC -funbox-strict-fields #-} module HTMLTokenizer.Data+(+  module HTMLTokenizer.Data.Types,+  module HTMLTokenizer.Data.Instances.Show,+  module HTMLTokenizer.Data.Instances.Eq,+) where -import HTMLTokenizer.Prelude---data Token =-  OpeningTagToken !Name !(Vector Attribute) !Bool |-  ClosingTagToken !Name |-  TextToken !Text |-  CommentToken !Text |-  DoctypeToken !Text-  deriving (Show, Eq)--data Name =-  UnprefixedName !Text |-  PrefixedName !Text !Text-  deriving (Show, Eq)--data Attribute =-  Attribute !Name !Text-  deriving (Show, Eq)+import HTMLTokenizer.Data.Types+import HTMLTokenizer.Data.Instances.Show+import HTMLTokenizer.Data.Instances.Eq

@@ -0,0 +1,10 @@+module HTMLTokenizer.Data.Instances.Eq+where++import HTMLTokenizer.Prelude+import HTMLTokenizer.Data.Types+++deriving instance Eq Token+deriving instance Eq Name+deriving instance Eq Attribute

@@ -0,0 +1,16 @@+module HTMLTokenizer.Data.Instances.Show+where++import HTMLTokenizer.Prelude+import HTMLTokenizer.Data.Types+import qualified HTMLTokenizer.Rendering.Text as A+++instance Show Token where+  show = textString . A.token++instance Show Name where+  show = textString . A.name++instance Show Attribute where+  show = textString . A.attribute

@@ -0,0 +1,20 @@+{-# OPTIONS_GHC -funbox-strict-fields #-}+module HTMLTokenizer.Data.Types+where++import HTMLTokenizer.Prelude+++data Token =+  OpeningTagToken !Name !(Vector Attribute) !Bool |+  ClosingTagToken !Name |+  TextToken !Text |+  CommentToken !Text |+  DoctypeToken !Text++data Name =+  UnprefixedName !Text |+  PrefixedName !Text !Text++data Attribute =+  Attribute !Name !Text

@@ -1,6 +1,8 @@ module HTMLTokenizer.Prelude (    module Exports,+  textString,+  showText, ) where @@ -20,3 +22,15 @@ -- vector ------------------------- import Data.Vector as Exports (Vector)++--------------------------------------------------------------------------------++import qualified Data.Text as A++textString :: Text -> String+textString =+  A.unpack++showText :: Show a => a -> Text+showText =+  fromString . show

@@ -0,0 +1,17 @@+module HTMLTokenizer.Rendering.Text+where++import HTMLTokenizer.Prelude+import HTMLTokenizer.Data.Types+import qualified Text.Builder as A+import qualified HTMLTokenizer.Rendering.Text.Builder as B+++token :: Token -> Text+token = A.run . B.token++attribute :: Attribute -> Text+attribute = A.run . B.attribute++name :: Name -> Text+name = A.run . B.name

@@ -0,0 +1,55 @@+module HTMLTokenizer.Rendering.Text.Builder+(+  token,+  attribute,+  name,+)+where++import HTMLTokenizer.Prelude hiding (takeWhile)+import HTMLTokenizer.Data.Types+import Text.Builder+import qualified Data.Text as D+import qualified HTMLEntities.Text as B+++encodedText :: Text -> Builder+encodedText =+  text . B.text++name :: Name -> Builder+name =+  \ case+    UnprefixedName localName ->+      encodedText localName+    PrefixedName space localName ->+      encodedText space <> char ':' <> encodedText localName++attribute :: Attribute -> Builder+attribute (Attribute attributeName content) =+  if D.null content+    then name attributeName+    else name attributeName <> text "=\"" <> encodedText content <> char '"'++token :: Token -> Builder+token =+  \ case+    OpeningTagToken tagName attrVec closed ->+      char '<' <> name tagName <> attrs <> closing+      where+        attrs =+          foldMap (\ x -> char ' ' <> attribute x) attrVec+        closing =+          if closed+            then text "/>"+            else char '>'+    ClosingTagToken tagName ->+      text "</" <> name tagName <> char '>'+    TextToken theText ->+      encodedText theText+    CommentToken commentText ->+      text "<!--" <> encodedText commentText <> text "-->"+    DoctypeToken doctypeText ->+      text "<!doctype" <>+      (if D.null doctypeText then mempty else char ' ' <> encodedText doctypeText) <>+      char '>'