skylighting 0.3.1 → 0.3.2

raw patch · 4 files changed

+15/−16 lines, 4 files

Files

• changelog.md +9/−0
• skylighting.cabal +1/−1
• src/Skylighting/Parser.hs +2/−1
• src/Skylighting/Tokenizer.hs +3/−14

@@ -1,5 +1,14 @@ # Revision history for skylighting +## 0.3.2 -- 2017-04-01++  * Parse xml definitions without resolving entities from+    language.dtd.  This allows xml definitions to be used even+    when language.dtd isn't available.  Existing definitions+    don't rely on the two or three entities definied in+    language.dtd, so this is harmless.+  * Small optimizations.+ ## 0.3.1 -- 2017-02-28    * Use handwritten parser for Float instead of regex.  Fixes

@@ -1,5 +1,5 @@ name:                skylighting-version:             0.3.1+version:             0.3.2 synopsis:            syntax highlighting library description:         Skylighting is a syntax highlighting library with                      support for over one hundred languages.  It derives

@@ -67,7 +67,8 @@  application :: String -> IOSArrow b Syntax application fp-    = readDocument [withValidate no, withInputEncoding utf8] fp+    = readDocument [withValidate no, withSubstDTDEntities no,+                    withInputEncoding utf8] fp       >>>       multi (hasName "language")       >>>

@@ -221,8 +221,7 @@                 HlCStringChar -> withAttr attr $ parseCStringChar inp                 HlCChar -> withAttr attr $ parseCChar inp                 Float -> withAttr attr $ parseFloat inp-                Keyword kwattr kws ->-                  withAttr attr $ keyword kwattr kws inp+                Keyword kwattr kws -> withAttr attr $ keyword kwattr kws inp                 StringDetect s -> withAttr attr $                                     stringDetect (rCaseSensitive rule) s inp                 WordDetect s -> withAttr attr $@@ -269,15 +268,6 @@      then return Nothing      else return $ Just (tt, res) -{---- Try a tokenizer and return to original state if it fails.--- This is used when one tokenizer calls another.-try :: TokenizerM a -> TokenizerM a-try tokenizer' = do-  origstate <- get-  tokenizer' <|> (put origstate >> mzero)--}- wordDetect :: Bool -> Text -> ByteString -> TokenizerM Text wordDetect caseSensitive s inp = do   wordBoundary inp@@ -426,6 +416,7 @@   reStr <- if dynamic               then subDynamic (reString re)               else return (reString re)+  when (BS.take 2 reStr == "\\b") $ wordBoundary inp   regex <- if dynamic               then return $ compileRegex (reCaseSensitive re) reStr               else do@@ -437,12 +428,10 @@                              Map.insert re cre (compiledRegexes st) }                        return cre                      Just cre -> return cre-  when (BS.take 2 reStr == "\\b") $ wordBoundary inp   case matchRegex regex inp of        Just (match:capts) -> do-         match' <- decodeBS match          modify $ \st -> st{ captures = capts }-         takeChars (Text.length match')+         takeChars (UTF8.length match)        _ -> mzero  wordBoundary :: ByteString -> TokenizerM ()