47a1606 · typeable/pandoc

git.iko.soy/typeable/pandoc

Removed --parse-raw and readerParseRaw.

These were confusing. Now we rely on the +raw_tex or +raw_html extension with latex or html input. Thus, instead of --parse-raw -f latex we use -f latex+raw_tex and instead of --parse-raw -f html we use -f html+raw_html

commit47a16065c44eb5028ca9b9e86993fe880ef2a37d authorJohn MacFarlane <jgm@berkeley.edu> dateMon 6 Feb 2017, 23:33 (10 years ago) parentd1c16c4

12 files changed+66−59

compare with master

unifiedsplit

MANUAL.txt−11 src/Text/Pandoc.hs+1 src/Text/Pandoc/App.hs+14−19 src/Text/Pandoc/Options.hs−2 src/Text/Pandoc/Readers/EPUB.hs+2−1 src/Text/Pandoc/Readers/HTML.hs+7−7 src/Text/Pandoc/Readers/LaTeX.hs+12−7 src/Text/Pandoc/Readers/Markdown.hs−4 src/Text/Pandoc/Readers/Org/Inlines.hs+2−1 src/Text/Pandoc/Readers/Textile.hs−6 test/Tests/Old.hs+1−1 test/command/parse-raw.md+27

MANUAL.txt−11

@@ -391,17 +391,6 @@ General options

391391Reader options

392392--------------

393393

394−`-R`, `--parse-raw`

395−

396−: Parse untranslatable HTML codes and LaTeX environments as raw HTML

397− or LaTeX, instead of ignoring them. Affects only HTML and LaTeX

398− input. Raw HTML can be printed in Markdown, reStructuredText, Emacs Org

399− mode, HTML, Slidy, Slideous, DZSlides, reveal.js, and S5 output; raw LaTeX

400− can be printed in Markdown, reStructuredText, Emacs Org mode, LaTeX, and

401− ConTeXt output. The default is for the readers to omit untranslatable

402− HTML codes and LaTeX environments. (The LaTeX reader does pass through

403− untranslatable LaTeX *commands*, even if `-R` is not specified.)

404−

405394`--base-header-level=`*NUMBER*

406395

407396: Specify the base level for headers (defaults to 1).

src/Text/Pandoc.hs+1

@@ -336,6 +336,7 @@ getDefaultExtensions "context" = extensionsFromList

336336getDefaultExtensions "textile" = extensionsFromList

337337 [Ext_old_dashes,

338338 Ext_smart,

339+ Ext_raw_html,

339340 Ext_auto_identifiers]

340341getDefaultExtensions _ = extensionsFromList

341342 [Ext_auto_identifiers]

src/Text/Pandoc/App.hs+14−19

@@ -90,7 +90,7 @@ parseOptions options' defaults = do

9090 let (actions, args, unrecognizedOpts, errors) =

9191 getOpt' Permute options' rawArgs

9292

93− let unknownOptionErrors = foldr handelUnrecognizedOption [] unrecognizedOpts

93+ let unknownOptionErrors = foldr handleUnrecognizedOption [] unrecognizedOpts

9494

9595 unless (null errors && null unknownOptionErrors) $

9696 err 2 $ concat errors ++ unlines unknownOptionErrors ++

@@ -273,7 +273,6 @@ convertWithOpts opts = do

273273 _ -> Nothing

274274

275275 let readerOpts = def{ readerStandalone = standalone

276− , readerParseRaw = optParseRaw opts

277276 , readerColumns = optColumns opts

278277 , readerTabStop = optTabStop opts

279278 , readerIndentedCodeClasses = optIndentedCodeClasses opts

@@ -463,7 +462,6 @@ data Opt = Opt

463462 , optStandalone :: Bool -- ^ Include header, footer

464463 , optReader :: Maybe String -- ^ Reader format

465464 , optWriter :: Maybe String -- ^ Writer format

466− , optParseRaw :: Bool -- ^ Parse unconvertable HTML and TeX

467465 , optTableOfContents :: Bool -- ^ Include table of contents

468466 , optBaseHeaderLevel :: Int -- ^ Base header level

469467 , optTemplate :: Maybe FilePath -- ^ Custom template

@@ -529,7 +527,6 @@ defaultOpts = Opt

529527 , optStandalone = False

530528 , optReader = Nothing

531529 , optWriter = Nothing

532− , optParseRaw = False

533530 , optTableOfContents = False

534531 , optBaseHeaderLevel = 1

535532 , optTemplate = Nothing

@@ -777,11 +774,6 @@ options =

777774 "DIRECTORY") -- "Directory containing pandoc data files."

778775 ""

779776

780− , Option "R" ["parse-raw"]

781− (NoArg

782− (\opt -> return opt { optParseRaw = True }))

783− "" -- "Parse untranslatable HTML codes and LaTeX environments as raw"

784−

785777 , Option "" ["base-header-level"]

786778 (ReqArg

787779 (\arg opt ->

@@ -1403,22 +1395,25 @@ compileInfo =

14031395 "\nCompiled with pandoc-types " ++ VERSION_pandoc_types ++ ", texmath " ++

14041396 VERSION_texmath ++ ", skylighting " ++ VERSION_skylighting

14051397

1406−handelUnrecognizedOption :: String -> [String] -> [String]

1407−handelUnrecognizedOption "--smart" =

1408− (("--smart has been removed. Use +smart or -smart extension instead.\n" ++

1398+handleUnrecognizedOption :: String -> [String] -> [String]

1399+handleUnrecognizedOption "--smart" =

1400+ (("--smart/-S has been removed. Use +smart or -smart extension instead.\n" ++

14091401 "For example: pandoc -f markdown+smart -t markdown-smart.") :)

1410−handelUnrecognizedOption "-S" = handelUnrecognizedOption "--smart"

1411−handelUnrecognizedOption "--old-dashes" =

1402+handleUnrecognizedOption "-S" = handleUnrecognizedOption "--smart"

1403+handleUnrecognizedOption "--old-dashes" =

14121404 ("--old-dashes has been removed. Use +old_dashes extension instead." :)

1413−handelUnrecognizedOption "--no-wrap" =

1405+handleUnrecognizedOption "--no-wrap" =

14141406 ("--no-wrap has been removed. Use --wrap=none instead." :)

1415−handelUnrecognizedOption "--chapters" =

1407+handleUnrecognizedOption "--chapters" =

14161408 ("--chapters has been removed. Use --top-level-division=chapter instead." :)

1417−handelUnrecognizedOption "--reference-docx" =

1409+handleUnrecognizedOption "--reference-docx" =

14181410 ("--reference-docx has been removed. Use --reference-doc instead." :)

1419−handelUnrecognizedOption "--reference-odt" =

1411+handleUnrecognizedOption "--reference-odt" =

14201412 ("--reference-odt has been removed. Use --reference-doc instead." :)

1421−handelUnrecognizedOption x =

1413+handleUnrecognizedOption "--parse-raw" =

1414+ (("--parse-raw/-R has been removed. Use +raw_html or +raw_tex extension.\n") :)

1415+handleUnrecognizedOption "-R" = handleUnrecognizedOption "--parse-raw"

1416+handleUnrecognizedOption x =

14221417 (("Unknown option " ++ x ++ ".") :)

14231418

14241419uppercaseFirstLetter :: String -> String

src/Text/Pandoc/Options.hs−2

@@ -55,7 +55,6 @@ import GHC.Generics (Generic)

5555data ReaderOptions = ReaderOptions{

5656 readerExtensions :: Extensions -- ^ Syntax extensions

5757 , readerStandalone :: Bool -- ^ Standalone document with header

58− , readerParseRaw :: Bool -- ^ Parse raw HTML, LaTeX

5958 , readerColumns :: Int -- ^ Number of columns in terminal

6059 , readerTabStop :: Int -- ^ Tab stop

6160 , readerApplyMacros :: Bool -- ^ Apply macros to TeX math

@@ -69,7 +68,6 @@ instance Default ReaderOptions

6968 where def = ReaderOptions{

7069 readerExtensions = emptyExtensions

7170 , readerStandalone = False

72− , readerParseRaw = False

7371 , readerColumns = 80

7472 , readerTabStop = 4

7573 , readerApplyMacros = True

src/Text/Pandoc/Readers/EPUB.hs+2−1

@@ -13,6 +13,7 @@ import Text.Pandoc.Definition hiding (Attr)

1313import Text.Pandoc.Readers.HTML (readHtml)

1414import Text.Pandoc.Walk (walk, query)

1515import Text.Pandoc.Options ( ReaderOptions(..), Verbosity(..))

16+import Text.Pandoc.Extensions (enableExtension, Extension(Ext_raw_html))

1617import Text.Pandoc.Shared (escapeURI, collapseFilePath, addMetaField)

1718import Network.URI (unEscapeString)

1819import Text.Pandoc.MediaBag (MediaBag, insertMedia)

@@ -66,7 +67,7 @@ archiveToEPUB os archive = do

6667 P.setMediaBag $ fetchImages (M.elems items) root archive ast

6768 return ast

6869 where

69− os' = os {readerParseRaw = True}

70+ os' = os {readerExtensions = enableExtension Ext_raw_html (readerExtensions os)}

7071 parseSpineElem :: PandocMonad m => FilePath -> (FilePath, MimeType) -> m Pandoc

7172 parseSpineElem (normalise -> r) (normalise -> path, mime) = do

7273 report DEBUG ("parseSpineElem called with path " ++ show path)

src/Text/Pandoc/Readers/HTML.hs+7−7

@@ -45,9 +45,9 @@ import qualified Text.Pandoc.Builder as B

4545import Text.Pandoc.Builder (Blocks, Inlines, trimInlines, HasMeta(..))

4646import Text.Pandoc.Shared ( extractSpaces, renderTags', addMetaField

4747 , escapeURI, safeRead )

48−import Text.Pandoc.Options (ReaderOptions(readerParseRaw),

49− Verbosity(..), Extension (Ext_epub_html_exts,

50− Ext_native_divs, Ext_native_spans))

48+import Text.Pandoc.Options (ReaderOptions(readerExtensions), extensionEnabled,

49+ Verbosity(..), Extension (Ext_epub_html_exts,

50+ Ext_raw_html, Ext_native_divs, Ext_native_spans))

5151import Text.Pandoc.Parsing hiding ((<|>))

5252import Text.Pandoc.Walk

5353import qualified Data.Map as M

@@ -367,8 +367,8 @@ pDiv = try $ do

367367pRawHtmlBlock :: PandocMonad m => TagParser m Blocks

368368pRawHtmlBlock = do

369369 raw <- pHtmlBlock "script" <|> pHtmlBlock "style" <|> pRawTag

370− parseRaw <- getOption readerParseRaw

371− if parseRaw && not (null raw)

370+ exts <- getOption readerExtensions

371+ if extensionEnabled Ext_raw_html exts && not (null raw)

372372 then return $ B.rawBlock "html" raw

373373 else return mempty

374374

@@ -690,8 +690,8 @@ pRawHtmlInline = do

690690 <|> if inplain

691691 then pSatisfy (not . isBlockTag)

692692 else pSatisfy isInlineTag

693− parseRaw <- getOption readerParseRaw

694− if parseRaw

693+ exts <- getOption readerExtensions

694+ if extensionEnabled Ext_raw_html exts

695695 then return $ B.rawInline "html" $ renderTags' [result]

696696 else return mempty

697697

src/Text/Pandoc/Readers/LaTeX.hs+12−7

@@ -303,14 +303,18 @@ ignoreInlines name = (name, doraw <|> (mempty <$ optargs))

303303 where optargs = skipopts *> skipMany (try $ optional sp *> braced)

304304 contseq = '\\':name

305305 doraw = (rawInline "latex" . (contseq ++) . snd) <$>

306− (getOption readerParseRaw >>= guard >> withRaw optargs)

306+ (do exts <- getOption readerExtensions

307+ guard $ extensionEnabled Ext_raw_tex exts

308+ withRaw optargs)

307309

308310ignoreBlocks :: PandocMonad m => String -> (String, LP m Blocks)

309311ignoreBlocks name = (name, doraw <|> (mempty <$ optargs))

310312 where optargs = skipopts *> skipMany (try $ optional sp *> braced)

311313 contseq = '\\':name

312314 doraw = (rawBlock "latex" . (contseq ++) . snd) <$>

313− (getOption readerParseRaw >>= guard >> withRaw optargs)

315+ (do exts <- getOption readerExtensions

316+ guard $ extensionEnabled Ext_raw_tex exts

317+ withRaw optargs)

314318

315319blockCommands :: PandocMonad m => M.Map String (LP m Blocks)

316320blockCommands = M.fromList $

@@ -423,7 +427,7 @@ inlineCommand = try $ do

423427 name <- anyControlSeq

424428 guard $ name /= "begin" && name /= "end"

425429 guard $ not $ isBlockCommand name

426− parseRaw <- getOption readerParseRaw

430+ exts <- getOption readerExtensions

427431 star <- option "" (string "*")

428432 let name' = name ++ star

429433 let raw = do

@@ -433,7 +437,7 @@ inlineCommand = try $ do

433437 transformed <- applyMacros' rawcommand

434438 if transformed /= rawcommand

435439 then parseFromString inlines transformed

436− else if parseRaw

440+ else if extensionEnabled Ext_raw_tex exts

437441 then return $ rawInline "latex" rawcommand

438442 else return mempty

439443 (lookupListDefault mzero [name',name] inlineCommands <*

@@ -441,7 +445,8 @@ inlineCommand = try $ do

441445 <|> raw

442446

443447unlessParseRaw :: PandocMonad m => LP m ()

444−unlessParseRaw = getOption readerParseRaw >>= guard . not

448+unlessParseRaw = getOption readerExtensions >>=

449+ guard . not . extensionEnabled Ext_raw_tex

445450

446451isBlockCommand :: String -> Bool

447452isBlockCommand s = s `M.member` (blockCommands :: M.Map String (LP PandocPure Blocks))

@@ -923,10 +928,10 @@ inlineEnvironment = try $ do

923928

924929rawEnv :: PandocMonad m => String -> LP m Blocks

925930rawEnv name = do

926− parseRaw <- getOption readerParseRaw

931+ exts <- getOption readerExtensions

927932 rawOptions <- mconcat <$> many rawopt

928933 let addBegin x = "\\begin{" ++ name ++ "}" ++ rawOptions ++ x

929− if parseRaw

934+ if extensionEnabled Ext_raw_tex exts

930935 then (rawBlock "latex" . addBegin) <$>

931936 (withRaw (env name blocks) >>= applyMacros' . snd)

932937 else env name blocks

src/Text/Pandoc/Readers/Markdown.hs−4

@@ -359,10 +359,6 @@ kvPair allowEmpty = try $ do

359359

360360parseMarkdown :: PandocMonad m => MarkdownParser m Pandoc

361361parseMarkdown = do

362− -- markdown allows raw HTML

363− updateState $ \state -> state { stateOptions =

364− let oldOpts = stateOptions state in

365− oldOpts{ readerParseRaw = True } }

366362 optional titleBlock

367363 blocks <- parseBlocks

368364 st <- getState

src/Text/Pandoc/Readers/Org/Inlines.hs+2−1

@@ -806,7 +806,8 @@ inlineLaTeX = try $ do

806806 where clean = dropWhileEnd (`elem` ("{}" :: String)) . drop 1

807807

808808 state :: ParserState

809− state = def{ stateOptions = def{ readerParseRaw = True }}

809+ state = def{ stateOptions = def{ readerExtensions =

810+ enableExtension Ext_raw_tex (readerExtensions def) } }

810811

811812 texMathToPandoc :: String -> Maybe [Inline]

812813 texMathToPandoc cs = (maybeRight $ readTeX cs) >>= writePandoc DisplayInline

src/Text/Pandoc/Readers/Textile.hs−6

@@ -85,12 +85,6 @@ readTextile opts s = do

8585-- | Generate a Pandoc ADT from a textile document

8686parseTextile :: PandocMonad m => ParserT [Char] ParserState m Pandoc

8787parseTextile = do

88− -- textile allows raw HTML and does smart punctuation by default,

89− -- but we do not enable smart punctuation unless it is explicitly

90− -- asked for, for better conversion to other light markup formats

91− oldOpts <- stateOptions `fmap` getState

92− updateState $ \state -> state{ stateOptions =

93− oldOpts{ readerParseRaw = True } }

9488 many blankline

9589 startPos <- getPosition

9690 -- go through once just to get list of reference keys and notes

test/Tests/Old.hs+1−1

@@ -46,7 +46,7 @@ tests = [ testGroup "markdown"

4646 , testGroup "latex"

4747 [ testGroup "writer" (writerTests "latex" ++ lhsWriterTests "latex")

4848 , testGroup "reader"

49− [ test "basic" ["-r", "latex", "-w", "native", "-s", "-R"]

49+ [ test "basic" ["-r", "latex+raw_tex", "-w", "native", "-s"]

5050 "latex-reader.latex" "latex-reader.native"

5151 , lhsReaderTest "latex+lhs"

5252 ]

test/command/parse-raw.mdnew file+27

@@ -0,0 +1,27 @@

1+```

2+% pandoc -f latex+raw_tex -t markdown

3+\emph{Hi \foo{there}}

4+^D

5+*Hi \foo{there}*

6+```

8+```

9+% pandoc -f latex -t markdown

10+\emph{Hi \foo{there}}

11+^D

12+*Hi*

13+```

14+

15+```

16+% pandoc -f html+raw_html -t markdown

17+<em>Hi <blink>there</blink></em>

18+^D

19+*Hi <blink>there</blink>*

20+```

21+

22+```

23+% pandoc -f html -t markdown

24+<em>Hi <blink>there</blink></em>

25+^D

26+*Hi there*

27+```