b1ee747 · typeable/pandoc

git.iko.soy/typeable/pandoc

Added `--strip-comments` option, `readerStripComments` in `ReaderOptions`.

* Options: Added readerStripComments to ReaderOptions. * Added `--strip-comments` command-line option. * Made `htmlTag` from the HTML reader sensitive to this feature. This affects Markdown and Textile input. Closes #2552.

commitb1ee747a249e0c1b1840222ef77607218157f099 authorJohn MacFarlane <jgm@berkeley.edu> dateSun 17 Sep 2017, 12:49 (9 years ago) parentce05814

6 files changed+46−8

compare with master

unifiedsplit

MANUAL.txt+8 src/Text/Pandoc/App.hs+8 src/Text/Pandoc/Options.hs+3−1 src/Text/Pandoc/Readers/HTML.hs+10−6 src/Text/Pandoc/Readers/Markdown.hs+3−1 test/command/2552.md+14

MANUAL.txt+8

@@ -655,6 +655,14 @@ General writer options

655655 of contents. The default is 3 (which means that level 1, 2, and 3

656656 headers will be listed in the contents).

657657

658+`--strip-comments`

659+

660+: Strip out HTML comments in the Markdown or Textile source,

661+ rather than passing them on to Markdown, Textile or HTML

662+ output as raw HTML. This does not apply to HTML comments

663+ inside raw HTML blocks when the `markdown_in_html_blocks`

664+ extension is not set.

665+

658666`--no-highlight`

659667

660668: Disables syntax highlighting for code blocks and inlines, even when

src/Text/Pandoc/App.hs+8

@@ -483,6 +483,7 @@ convertWithOpts opts = do

483483 , readerTrackChanges = optTrackChanges opts

484484 , readerAbbreviations = abbrevs

485485 , readerExtensions = readerExts

486+ , readerStripComments = optStripComments opts

486487 }

487488

488489 let transforms = (case optBaseHeaderLevel opts of

@@ -666,6 +667,7 @@ data Opt = Opt

666667 , optIncludeInHeader :: [FilePath] -- ^ Files to include in header

667668 , optResourcePath :: [FilePath] -- ^ Path to search for images etc

668669 , optEol :: LineEnding -- ^ Style of line-endings to use

670+ , optStripComments :: Bool -- ^ Skip HTML comments

669671 } deriving (Generic, Show)

670672

671673instance ToJSON Opt where

@@ -742,6 +744,7 @@ defaultOpts = Opt

742744 , optIncludeInHeader = []

743745 , optResourcePath = ["."]

744746 , optEol = Native

747+ , optStripComments = False

745748 }

746749

747750addMetadata :: (String, String) -> Pandoc -> Pandoc

@@ -1114,6 +1117,11 @@ options =

11141117 "NUMBER")

11151118 "" -- "Length of line in characters"

11161119

1120+ , Option "" ["strip-comments"]

1121+ (NoArg

1122+ (\opt -> return opt { optStripComments = True }))

1123+ "" -- "Strip HTML comments"

1124+

11171125 , Option "" ["toc", "table-of-contents"]

11181126 (NoArg

11191127 (\opt -> return opt { optTableOfContents = True }))

src/Text/Pandoc/Options.hs+3−1

@@ -65,7 +65,8 @@ data ReaderOptions = ReaderOptions{

6565 -- indented code blocks

6666 , readerAbbreviations :: Set.Set String -- ^ Strings to treat as abbreviations

6767 , readerDefaultImageExtension :: String -- ^ Default extension for images

68− , readerTrackChanges :: TrackChanges

68+ , readerTrackChanges :: TrackChanges -- ^ Track changes setting for docx

69+ , readerStripComments :: Bool -- ^ Strip HTML comments instead of parsing as raw HTML

6970} deriving (Show, Read, Data, Typeable, Generic)

7071

7172instance ToJSON ReaderOptions where

@@ -82,6 +83,7 @@ instance Default ReaderOptions

8283 , readerAbbreviations = defaultAbbrevs

8384 , readerDefaultImageExtension = ""

8485 , readerTrackChanges = AcceptChanges

86+ , readerStripComments = False

8587 }

8688

8789defaultAbbrevs :: Set.Set String

src/Text/Pandoc/Readers/HTML.hs+10−6

@@ -46,9 +46,10 @@ import qualified Text.Pandoc.Builder as B

4646import Text.Pandoc.Builder (Blocks, Inlines, trimInlines, HasMeta(..))

4747import Text.Pandoc.Shared ( extractSpaces, addMetaField

4848 , escapeURI, safeRead, crFilter )

49−import Text.Pandoc.Options (ReaderOptions(readerExtensions), extensionEnabled,

50− Extension (Ext_epub_html_exts,

51− Ext_raw_html, Ext_native_divs, Ext_native_spans))

49+import Text.Pandoc.Options (

50+ ReaderOptions(readerExtensions,readerStripComments), extensionEnabled,

51+ Extension (Ext_epub_html_exts,

52+ Ext_raw_html, Ext_native_divs, Ext_native_spans))

5253import Text.Pandoc.Logging

5354import Text.Pandoc.Parsing hiding ((<|>))

5455import Text.Pandoc.Walk

@@ -1070,7 +1071,7 @@ _ `closes` _ = False

10701071--- parsers for use in markdown, textile readers

10711072

10721073-- | Matches a stretch of HTML in balanced tags.

1073−htmlInBalanced :: (Monad m)

1074+htmlInBalanced :: (HasReaderOptions st, Monad m)

10741075 => (Tag String -> Bool)

10751076 -> ParserT String st m String

10761077htmlInBalanced f = try $ do

@@ -1118,7 +1119,7 @@ hasTagWarning (TagWarning _:_) = True

11181119hasTagWarning _ = False

11191120

11201121-- | Matches a tag meeting a certain condition.

1121−htmlTag :: Monad m

1122+htmlTag :: (HasReaderOptions st, Monad m)

11221123 => (Tag String -> Bool)

11231124 -> ParserT [Char] st m (Tag String, String)

11241125htmlTag f = try $ do

@@ -1153,7 +1154,10 @@ htmlTag f = try $ do

11531154 count (length s + 4) anyChar

11541155 skipMany (satisfy (/='>'))

11551156 char '>'

1156− return (next, "")

1157+ stripComments <- getOption readerStripComments

1158+ if stripComments

1159+ then return (next, "")

1160+ else return (next, "")

11571161 | otherwise -> fail "bogus comment mode, HTML5 parse error"

11581162 TagOpen tagname attr -> do

11591163 guard $ all (isName . fst) attr

src/Text/Pandoc/Readers/Markdown.hs+3−1

@@ -1079,7 +1079,9 @@ htmlBlock' = try $ do

10791079 first <- htmlElement

10801080 skipMany spaceChar

10811081 optional blanklines

1082− return $ return $ B.rawBlock "html" first

1082+ return $ if null first

1083+ then mempty

1084+ else return $ B.rawBlock "html" first

10831085

10841086strictHtmlBlock :: PandocMonad m => MarkdownParser m String

10851087strictHtmlBlock = htmlInBalanced (not . isInlineTag)

test/command/2552.mdnew file+14

@@ -0,0 +1,14 @@

1+```

2+% pandoc --strip-comments

3+Foo

5+bar

7+

9+bazboop

10+^D

11+Foo

12+bar

13+bazboop

14+```