1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217
|
{-# LANGUAGE CPP #-}
{-
Copyright (C) 2006-2014 John MacFarlane <jgm@berkeley.edu>
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
-}
{- |
Module : Main
Copyright : Copyright (C) 2006-2014 John MacFarlane
License : GNU GPL, version 2 or above
Maintainer : John MacFarlane <jgm@berkeley@edu>
Stability : alpha
Portability : portable
Parses command-line options and calls the appropriate readers and
writers.
-}
module Main where
import Text.Pandoc
import Text.Pandoc.Builder (setMeta)
import Text.Pandoc.PDF (makePDF)
import Text.Pandoc.Readers.LaTeX (handleIncludes)
import Text.Pandoc.Shared ( tabFilter, readDataFileUTF8, readDataFile,
safeRead, headerShift, normalize, err, warn,
openURL )
import Text.Pandoc.XML ( toEntities )
import Text.Pandoc.SelfContained ( makeSelfContained )
import Text.Pandoc.Process (pipeProcess)
import Text.Highlighting.Kate ( languages, Style, tango, pygments,
espresso, zenburn, kate, haddock, monochrome )
import System.Environment ( getArgs, getProgName )
import System.Exit ( exitWith, ExitCode (..) )
import System.FilePath
import System.Console.GetOpt
import Data.Char ( toLower )
import Data.List ( intercalate, isPrefixOf, isSuffixOf, sort )
import System.Directory ( getAppUserDataDirectory, findExecutable,
doesFileExist )
import System.IO ( stdout, stderr )
import System.IO.Error ( isDoesNotExistError )
import qualified Control.Exception as E
import Control.Exception.Extensible ( throwIO )
import qualified Text.Pandoc.UTF8 as UTF8
import Control.Monad (when, unless, liftM)
import Data.Foldable (foldrM)
import Network.URI (parseURI, isURI, URI(..))
import qualified Data.ByteString.Lazy as B
import qualified Data.ByteString as BS
import Data.Aeson (eitherDecode', encode)
import qualified Data.Map as M
import System.IO.Error(ioeGetErrorType)
import GHC.IO.Exception (IOErrorType(ResourceVanished))
import Data.Yaml (decode)
import qualified Data.Yaml as Yaml
import qualified Data.Text as T
copyrightMessage :: String
copyrightMessage = "\nCopyright (C) 2006-2014 John MacFarlane\n" ++
"Web: http://johnmacfarlane.net/pandoc\n" ++
"This is free software; see the source for copying conditions. There is no\n" ++
"warranty, not even for merchantability or fitness for a particular purpose."
compileInfo :: String
compileInfo =
"\nCompiled with texmath " ++
VERSION_texmath ++ ", highlighting-kate " ++ VERSION_highlighting_kate ++
".\nSyntax highlighting is supported for the following languages:\n " ++
wrapWords 4 78
[map toLower l | l <- languages, l /= "Alert" && l /= "Alert_indent"]
-- | Converts a list of strings into a single string with the items printed as
-- comma separated words in lines with a maximum line length.
wrapWords :: Int -> Int -> [String] -> String
wrapWords indent c = wrap' (c - indent) (c - indent)
where wrap' _ _ [] = ""
wrap' cols remaining (x:xs) = if remaining == cols
then x ++ wrap' cols (remaining - length x) xs
else if (length x + 1) > remaining
then ",\n" ++ replicate indent ' ' ++ x ++ wrap' cols (cols - length x) xs
else ", " ++ x ++ wrap' cols (remaining - (length x + 2)) xs
isTextFormat :: String -> Bool
isTextFormat s = takeWhile (`notElem` "+-") s `notElem` ["odt","docx","epub","epub3"]
externalFilter :: FilePath -> [String] -> Pandoc -> IO Pandoc
externalFilter f args' d = do
mbexe <- findExecutable f
(f', args'') <- case mbexe of
Just x -> return (x, args')
Nothing -> do
exists <- doesFileExist f
if exists
then return $
case map toLower $ takeExtension f of
".py" -> ("python", f:args')
".hs" -> ("runhaskell", f:args')
".pl" -> ("perl", f:args')
".rb" -> ("ruby", f:args')
".php" -> ("php", f:args')
_ -> (f, args')
else err 85 $ "Filter " ++ f ++ " not found"
(exitcode, outbs, errbs) <- E.handle filterException $
pipeProcess Nothing f' args'' $ encode d
when (not $ B.null errbs) $ B.hPutStr stderr errbs
case exitcode of
ExitSuccess -> return $ either error id $ eitherDecode' outbs
ExitFailure _ -> err 83 $ "Error running filter " ++ f
where filterException :: E.SomeException -> IO a
filterException e = err 83 $ "Error running filter " ++ f ++ "\n" ++
if ioeGetErrorType `fmap` E.fromException e ==
Just ResourceVanished
then f ++ " not found in path"
else show e
-- | Data structure for command line options.
data Opt = Opt
{ optTabStop :: Int -- ^ Number of spaces per tab
, optPreserveTabs :: Bool -- ^ Preserve tabs instead of converting to spaces
, optStandalone :: Bool -- ^ Include header, footer
, optReader :: String -- ^ Reader format
, optWriter :: String -- ^ Writer format
, optParseRaw :: Bool -- ^ Parse unconvertable HTML and TeX
, optTableOfContents :: Bool -- ^ Include table of contents
, optTransforms :: [Pandoc -> Pandoc] -- ^ Doc transforms to apply
, optTemplate :: Maybe FilePath -- ^ Custom template
, optVariables :: [(String,String)] -- ^ Template variables to set
, optMetadata :: M.Map String MetaValue -- ^ Metadata fields to set
, optOutputFile :: String -- ^ Name of output file
, optNumberSections :: Bool -- ^ Number sections in LaTeX
, optNumberOffset :: [Int] -- ^ Starting number for sections
, optSectionDivs :: Bool -- ^ Put sections in div tags in HTML
, optIncremental :: Bool -- ^ Use incremental lists in Slidy/Slideous/S5
, optSelfContained :: Bool -- ^ Make HTML accessible offline
, optSmart :: Bool -- ^ Use smart typography
, optOldDashes :: Bool -- ^ Parse dashes like pandoc <=1.8.2.1
, optHtml5 :: Bool -- ^ Produce HTML5 in HTML
, optHtmlQTags :: Bool -- ^ Use <q> tags in HTML
, optHighlight :: Bool -- ^ Highlight source code
, optHighlightStyle :: Style -- ^ Style to use for highlighted code
, optChapters :: Bool -- ^ Use chapter for top-level sects
, optHTMLMathMethod :: HTMLMathMethod -- ^ Method to print HTML math
, optReferenceODT :: Maybe FilePath -- ^ Path of reference.odt
, optReferenceDocx :: Maybe FilePath -- ^ Path of reference.docx
, optEpubStylesheet :: Maybe String -- ^ EPUB stylesheet
, optEpubMetadata :: String -- ^ EPUB metadata
, optEpubFonts :: [FilePath] -- ^ EPUB fonts to embed
, optEpubChapterLevel :: Int -- ^ Header level at which to split chapters
, optTOCDepth :: Int -- ^ Number of levels to include in TOC
, optDumpArgs :: Bool -- ^ Output command-line arguments
, optIgnoreArgs :: Bool -- ^ Ignore command-line arguments
, optReferenceLinks :: Bool -- ^ Use reference links in writing markdown, rst
, optWrapText :: Bool -- ^ Wrap text
, optColumns :: Int -- ^ Line length in characters
, optFilters :: [FilePath] -- ^ Filters to apply
, optEmailObfuscation :: ObfuscationMethod
, optIdentifierPrefix :: String
, optIndentedCodeClasses :: [String] -- ^ Default classes for indented code blocks
, optDataDir :: Maybe FilePath
, optCiteMethod :: CiteMethod -- ^ Method to output cites
, optListings :: Bool -- ^ Use listings package for code blocks
, optLaTeXEngine :: String -- ^ Program to use for latex -> pdf
, optSlideLevel :: Maybe Int -- ^ Header level that creates slides
, optSetextHeaders :: Bool -- ^ Use atx headers for markdown level 1-2
, optAscii :: Bool -- ^ Use ascii characters only in html
, optTeXLigatures :: Bool -- ^ Use TeX ligatures for quotes/dashes
, optDefaultImageExtension :: String -- ^ Default image extension
, optTrace :: Bool -- ^ Print debug information
}
-- | Defaults for command-line options.
defaultOpts :: Opt
defaultOpts = Opt
{ optTabStop = 4
, optPreserveTabs = False
, optStandalone = False
, optReader = "" -- null for default reader
, optWriter = "" -- null for default writer
, optParseRaw = False
, optTableOfContents = False
, optTransforms = []
, optTemplate = Nothing
, optVariables = []
, optMetadata = M.empty
, optOutputFile = "-" -- "-" means stdout
, optNumberSections = False
, optNumberOffset = [0,0,0,0,0,0]
, optSectionDivs = False
, optIncremental = False
, optSelfContained = False
, optSmart = False
, optOldDashes = False
, optHtml5 = False
, optHtmlQTags = False
, optHighlight = True
, optHighlightStyle = pygments
, optChapters = False
, optHTMLMathMethod = PlainMath
, optReferenceODT = Nothing
, optReferenceDocx = Nothing
, optEpubStylesheet = Nothing
, optEpubMetadata = ""
, optEpubFonts = []
, optEpubChapterLevel = 1
, optTOCDepth = 3
, optDumpArgs = False
, optIgnoreArgs = False
, optReferenceLinks = False
, optWrapText = True
, optColumns = 72
, optFilters = []
, optEmailObfuscation = JavascriptObfuscation
, optIdentifierPrefix = ""
, optIndentedCodeClasses = []
, optDataDir = Nothing
, optCiteMethod = Citeproc
, optListings = False
, optLaTeXEngine = "pdflatex"
, optSlideLevel = Nothing
, optSetextHeaders = True
, optAscii = False
, optTeXLigatures = True
, optDefaultImageExtension = ""
, optTrace = False
}
-- | A list of functions, each transforming the options data structure
-- in response to a command-line option.
options :: [OptDescr (Opt -> IO Opt)]
options =
[ Option "fr" ["from","read"]
(ReqArg
(\arg opt -> return opt { optReader = arg })
"FORMAT")
""
, Option "tw" ["to","write"]
(ReqArg
(\arg opt -> return opt { optWriter = arg })
"FORMAT")
""
, Option "o" ["output"]
(ReqArg
(\arg opt -> return opt { optOutputFile = arg })
"FILENAME")
"" -- "Name of output file"
, Option "" ["data-dir"]
(ReqArg
(\arg opt -> return opt { optDataDir = Just arg })
"DIRECTORY") -- "Directory containing pandoc data files."
""
, Option "" ["strict"]
(NoArg
(\opt -> do
err 59 $ "The --strict option has been removed.\n" ++
"Use `markdown_strict' input or output format instead."
return opt ))
"" -- "Disable markdown syntax extensions"
, Option "R" ["parse-raw"]
(NoArg
(\opt -> return opt { optParseRaw = True }))
"" -- "Parse untranslatable HTML codes and LaTeX environments as raw"
, Option "S" ["smart"]
(NoArg
(\opt -> return opt { optSmart = True }))
"" -- "Use smart quotes, dashes, and ellipses"
, Option "" ["old-dashes"]
(NoArg
(\opt -> return opt { optSmart = True
, optOldDashes = True }))
"" -- "Use smart quotes, dashes, and ellipses"
, Option "" ["base-header-level"]
(ReqArg
(\arg opt ->
case safeRead arg of
Just t | t > 0 -> do
let oldTransforms = optTransforms opt
let shift = t - 1
return opt{ optTransforms =
headerShift shift : oldTransforms }
_ -> err 19
"base-header-level must be a number > 0")
"NUMBER")
"" -- "Headers base level"
, Option "" ["indented-code-classes"]
(ReqArg
(\arg opt -> return opt { optIndentedCodeClasses = words $
map (\c -> if c == ',' then ' ' else c) arg })
"STRING")
"" -- "Classes (whitespace- or comma-separated) to use for indented code-blocks"
, Option "F" ["filter"]
(ReqArg
(\arg opt -> return opt { optFilters = arg : optFilters opt })
"PROGRAM")
"" -- "External JSON filter"
, Option "" ["normalize"]
(NoArg
(\opt -> return opt { optTransforms =
normalize : optTransforms opt } ))
"" -- "Normalize the Pandoc AST"
, Option "p" ["preserve-tabs"]
(NoArg
(\opt -> return opt { optPreserveTabs = True }))
"" -- "Preserve tabs instead of converting to spaces"
, Option "" ["tab-stop"]
(ReqArg
(\arg opt ->
case safeRead arg of
Just t | t > 0 -> return opt { optTabStop = t }
_ -> err 31
"tab-stop must be a number greater than 0")
"NUMBER")
"" -- "Tab stop (default 4)"
, Option "s" ["standalone"]
(NoArg
(\opt -> return opt { optStandalone = True }))
"" -- "Include needed header and footer on output"
, Option "" ["template"]
(ReqArg
(\arg opt -> do
return opt{ optTemplate = Just arg,
optStandalone = True })
"FILENAME")
"" -- "Use custom template"
, Option "M" ["metadata"]
(ReqArg
(\arg opt -> do
let (key,val) = case break (`elem` ":=") arg of
(k,_:v) -> (k, readMetaValue v)
(k,_) -> (k, MetaBool True)
return opt{ optMetadata = addMetadata key val
$ optMetadata opt })
"KEY[:VALUE]")
""
, Option "V" ["variable"]
(ReqArg
(\arg opt -> do
let (key,val) = case break (`elem` ":=") arg of
(k,_:v) -> (k,v)
(k,_) -> (k,"true")
return opt{ optVariables = (key,val) : optVariables opt })
"KEY[:VALUE]")
""
, Option "D" ["print-default-template"]
(ReqArg
(\arg _ -> do
templ <- getDefaultTemplate Nothing arg
case templ of
Right t -> UTF8.hPutStr stdout t
Left e -> error $ show e
exitWith ExitSuccess)
"FORMAT")
"" -- "Print default template for FORMAT"
, Option "" ["print-default-data-file"]
(ReqArg
(\arg _ -> do
readDataFile Nothing arg >>= BS.hPutStr stdout
exitWith ExitSuccess)
"FILE")
"" -- "Print default data file"
, Option "" ["no-wrap"]
(NoArg
(\opt -> return opt { optWrapText = False }))
"" -- "Do not wrap text in output"
, Option "" ["columns"]
(ReqArg
(\arg opt ->
case safeRead arg of
Just t | t > 0 -> return opt { optColumns = t }
_ -> err 33 $
"columns must be a number greater than 0")
"NUMBER")
"" -- "Length of line in characters"
, Option "" ["toc", "table-of-contents"]
(NoArg
(\opt -> return opt { optTableOfContents = True }))
"" -- "Include table of contents"
, Option "" ["toc-depth"]
(ReqArg
(\arg opt -> do
case safeRead arg of
Just t | t >= 1 && t <= 6 ->
return opt { optTOCDepth = t }
_ -> err 57 $
"TOC level must be a number between 1 and 6")
"NUMBER")
"" -- "Number of levels to include in TOC"
, Option "" ["no-highlight"]
(NoArg
(\opt -> return opt { optHighlight = False }))
"" -- "Don't highlight source code"
, Option "" ["highlight-style"]
(ReqArg
(\arg opt -> do
newStyle <- case map toLower arg of
"pygments" -> return pygments
"tango" -> return tango
"espresso" -> return espresso
"zenburn" -> return zenburn
"kate" -> return kate
"monochrome" -> return monochrome
"haddock" -> return haddock
_ -> err 39 $
"Unknown style :" ++ arg
return opt{ optHighlightStyle = newStyle })
"STYLE")
"" -- "Style for highlighted code"
, Option "H" ["include-in-header"]
(ReqArg
(\arg opt -> do
text <- UTF8.readFile arg
-- add new ones to end, so they're included in order specified
let newvars = optVariables opt ++ [("header-includes",text)]
return opt { optVariables = newvars,
optStandalone = True })
"FILENAME")
"" -- "File to include at end of header (implies -s)"
, Option "B" ["include-before-body"]
(ReqArg
(\arg opt -> do
text <- UTF8.readFile arg
-- add new ones to end, so they're included in order specified
let newvars = optVariables opt ++ [("include-before",text)]
return opt { optVariables = newvars,
optStandalone = True })
"FILENAME")
"" -- "File to include before document body"
, Option "A" ["include-after-body"]
(ReqArg
(\arg opt -> do
text <- UTF8.readFile arg
-- add new ones to end, so they're included in order specified
let newvars = optVariables opt ++ [("include-after",text)]
return opt { optVariables = newvars,
optStandalone = True })
"FILENAME")
"" -- "File to include after document body"
, Option "" ["self-contained"]
(NoArg
(\opt -> return opt { optSelfContained = True,
optStandalone = True }))
"" -- "Make slide shows include all the needed js and css"
, Option "" ["offline"]
(NoArg
(\opt -> do warn $ "--offline is deprecated. Use --self-contained instead."
return opt { optSelfContained = True,
optStandalone = True }))
"" -- "Make slide shows include all the needed js and css"
-- deprecated synonym for --self-contained
, Option "5" ["html5"]
(NoArg
(\opt -> do
warn $ "--html5 is deprecated. "
++ "Use the html5 output format instead."
return opt { optHtml5 = True }))
"" -- "Produce HTML5 in HTML output"
, Option "" ["html-q-tags"]
(NoArg
(\opt -> do
return opt { optHtmlQTags = True }))
"" -- "Use <q> tags for quotes in HTML"
, Option "" ["ascii"]
(NoArg
(\opt -> return opt { optAscii = True }))
"" -- "Use ascii characters only in HTML output"
, Option "" ["reference-links"]
(NoArg
(\opt -> return opt { optReferenceLinks = True } ))
"" -- "Use reference links in parsing HTML"
, Option "" ["atx-headers"]
(NoArg
(\opt -> return opt { optSetextHeaders = False } ))
"" -- "Use atx-style headers for markdown"
, Option "" ["chapters"]
(NoArg
(\opt -> return opt { optChapters = True }))
"" -- "Use chapter for top-level sections in LaTeX, DocBook"
, Option "N" ["number-sections"]
(NoArg
(\opt -> return opt { optNumberSections = True }))
"" -- "Number sections in LaTeX"
, Option "" ["number-offset"]
(ReqArg
(\arg opt ->
case safeRead ('[':arg ++ "]") of
Just ns -> return opt { optNumberOffset = ns,
optNumberSections = True }
_ -> err 57 "could not parse number-offset")
"NUMBERS")
"" -- "Starting number for sections, subsections, etc."
, Option "" ["no-tex-ligatures"]
(NoArg
(\opt -> return opt { optTeXLigatures = False }))
"" -- "Don't use tex ligatures for quotes, dashes"
, Option "" ["listings"]
(NoArg
(\opt -> return opt { optListings = True }))
"" -- "Use listings package for LaTeX code blocks"
, Option "i" ["incremental"]
(NoArg
(\opt -> return opt { optIncremental = True }))
"" -- "Make list items display incrementally in Slidy/Slideous/S5"
, Option "" ["slide-level"]
(ReqArg
(\arg opt -> do
case safeRead arg of
Just t | t >= 1 && t <= 6 ->
return opt { optSlideLevel = Just t }
_ -> err 39 $
"slide level must be a number between 1 and 6")
"NUMBER")
"" -- "Force header level for slides"
, Option "" ["section-divs"]
(NoArg
(\opt -> return opt { optSectionDivs = True }))
"" -- "Put sections in div tags in HTML"
, Option "" ["default-image-extension"]
(ReqArg
(\arg opt -> return opt { optDefaultImageExtension = arg })
"extension")
"" -- "Default extension for extensionless images"
, Option "" ["email-obfuscation"]
(ReqArg
(\arg opt -> do
method <- case arg of
"references" -> return ReferenceObfuscation
"javascript" -> return JavascriptObfuscation
"none" -> return NoObfuscation
_ -> err 6
("Unknown obfuscation method: " ++ arg)
return opt { optEmailObfuscation = method })
"none|javascript|references")
"" -- "Method for obfuscating email in HTML"
, Option "" ["id-prefix"]
(ReqArg
(\arg opt -> return opt { optIdentifierPrefix = arg })
"STRING")
"" -- "Prefix to add to automatically generated HTML identifiers"
, Option "T" ["title-prefix"]
(ReqArg
(\arg opt -> do
let newvars = ("title-prefix", arg) : optVariables opt
return opt { optVariables = newvars,
optStandalone = True })
"STRING")
"" -- "String to prefix to HTML window title"
, Option "c" ["css"]
(ReqArg
(\arg opt -> do
-- add new link to end, so it is included in proper order
let newvars = optVariables opt ++ [("css",arg)]
return opt { optVariables = newvars,
optStandalone = True })
"URL")
"" -- "Link to CSS style sheet"
, Option "" ["reference-odt"]
(ReqArg
(\arg opt -> do
return opt { optReferenceODT = Just arg })
"FILENAME")
"" -- "Path of custom reference.odt"
, Option "" ["reference-docx"]
(ReqArg
(\arg opt -> do
return opt { optReferenceDocx = Just arg })
"FILENAME")
"" -- "Path of custom reference.docx"
, Option "" ["epub-stylesheet"]
(ReqArg
(\arg opt -> do
text <- UTF8.readFile arg
return opt { optEpubStylesheet = Just text })
"FILENAME")
"" -- "Path of epub.css"
, Option "" ["epub-cover-image"]
(ReqArg
(\arg opt ->
return opt { optVariables =
("epub-cover-image", arg) : optVariables opt })
"FILENAME")
"" -- "Path of epub cover image"
, Option "" ["epub-metadata"]
(ReqArg
(\arg opt -> do
text <- UTF8.readFile arg
return opt { optEpubMetadata = text })
"FILENAME")
"" -- "Path of epub metadata file"
, Option "" ["epub-embed-font"]
(ReqArg
(\arg opt -> do
return opt{ optEpubFonts = arg : optEpubFonts opt })
"FILE")
"" -- "Directory of fonts to embed"
, Option "" ["epub-chapter-level"]
(ReqArg
(\arg opt -> do
case safeRead arg of
Just t | t >= 1 && t <= 6 ->
return opt { optEpubChapterLevel = t }
_ -> err 59 $
"chapter level must be a number between 1 and 6")
"NUMBER")
"" -- "Header level at which to split chapters in EPUB"
, Option "" ["latex-engine"]
(ReqArg
(\arg opt -> do
let b = takeBaseName arg
if b `elem` ["pdflatex", "lualatex", "xelatex"]
then return opt { optLaTeXEngine = arg }
else err 45 "latex-engine must be pdflatex, lualatex, or xelatex.")
"PROGRAM")
"" -- "Name of latex program to use in generating PDF"
, Option "" ["bibliography"]
(ReqArg
(\arg opt -> return opt{ optMetadata = addMetadata
"bibliography" (readMetaValue arg)
$ optMetadata opt
, optVariables =
("biblio-files", dropExtension arg) :
optVariables opt
})
"FILE")
""
, Option "" ["csl"]
(ReqArg
(\arg opt ->
return opt{ optMetadata = addMetadata "csl"
(readMetaValue arg)
$ optMetadata opt })
"FILE")
""
, Option "" ["citation-abbreviations"]
(ReqArg
(\arg opt ->
return opt{ optMetadata = addMetadata
"citation-abbreviations"
(readMetaValue arg)
$ optMetadata opt })
"FILE")
""
, Option "" ["natbib"]
(NoArg
(\opt -> return opt { optCiteMethod = Natbib }))
"" -- "Use natbib cite commands in LaTeX output"
, Option "" ["biblatex"]
(NoArg
(\opt -> return opt { optCiteMethod = Biblatex }))
"" -- "Use biblatex cite commands in LaTeX output"
, Option "m" ["latexmathml", "asciimathml"]
(OptArg
(\arg opt -> do
let url' = case arg of
Just u -> u
Nothing -> "http://math.etsu.edu/LaTeXMathML/LaTeXMathML.js"
return opt { optHTMLMathMethod = LaTeXMathML url'})
"URL")
"" -- "Use LaTeXMathML script in html output"
, Option "" ["mathml"]
(OptArg
(\arg opt ->
return opt { optHTMLMathMethod = MathML arg })
"URL")
"" -- "Use mathml for HTML math"
, Option "" ["mimetex"]
(OptArg
(\arg opt -> do
let url' = case arg of
Just u -> u ++ "?"
Nothing -> "/cgi-bin/mimetex.cgi?"
return opt { optHTMLMathMethod = WebTeX url' })
"URL")
"" -- "Use mimetex for HTML math"
, Option "" ["webtex"]
(OptArg
(\arg opt -> do
let url' = case arg of
Just u -> u
Nothing -> "http://chart.apis.google.com/chart?cht=tx&chl="
return opt { optHTMLMathMethod = WebTeX url' })
"URL")
"" -- "Use web service for HTML math"
, Option "" ["jsmath"]
(OptArg
(\arg opt -> return opt { optHTMLMathMethod = JsMath arg})
"URL")
"" -- "Use jsMath for HTML math"
, Option "" ["mathjax"]
(OptArg
(\arg opt -> do
let url' = case arg of
Just u -> u
Nothing -> "http://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML"
return opt { optHTMLMathMethod = MathJax url'})
"URL")
"" -- "Use MathJax for HTML math"
, Option "" ["gladtex"]
(NoArg
(\opt -> return opt { optHTMLMathMethod = GladTeX }))
"" -- "Use gladtex for HTML math"
, Option "" ["trace"]
(NoArg
(\opt -> return opt { optTrace = True }))
"" -- "Turn on diagnostic tracing in readers."
, Option "" ["dump-args"]
(NoArg
(\opt -> return opt { optDumpArgs = True }))
"" -- "Print output filename and arguments to stdout."
, Option "" ["ignore-args"]
(NoArg
(\opt -> return opt { optIgnoreArgs = True }))
"" -- "Ignore command-line arguments."
, Option "v" ["version"]
(NoArg
(\_ -> do
prg <- getProgName
defaultDatadir <- getAppUserDataDirectory "pandoc"
UTF8.hPutStrLn stdout (prg ++ " " ++ pandocVersion ++
compileInfo ++ "\nDefault user data directory: " ++
defaultDatadir ++ copyrightMessage)
exitWith ExitSuccess ))
"" -- "Print version"
, Option "h" ["help"]
(NoArg
(\_ -> do
prg <- getProgName
UTF8.hPutStr stdout (usageMessage prg options)
exitWith ExitSuccess ))
"" -- "Show help"
]
addMetadata :: String -> MetaValue -> M.Map String MetaValue
-> M.Map String MetaValue
addMetadata k v m = case M.lookup k m of
Nothing -> M.insert k v m
Just (MetaList xs) -> M.insert k
(MetaList (xs ++ [v])) m
Just x -> M.insert k (MetaList [v, x]) m
readMetaValue :: String -> MetaValue
readMetaValue s = case decode (UTF8.fromString s) of
Just (Yaml.String t) -> MetaString $ T.unpack t
Just (Yaml.Bool b) -> MetaBool b
_ -> MetaString s
-- Returns usage message
usageMessage :: String -> [OptDescr (Opt -> IO Opt)] -> String
usageMessage programName = usageInfo
(programName ++ " [OPTIONS] [FILES]" ++ "\nInput formats: " ++
(wrapWords 16 78 $ readers'names) ++ "\nOutput formats: " ++
(wrapWords 16 78 $ writers'names) ++
'\n' : replicate 16 ' ' ++
"[*for pdf output, use latex or beamer and -o FILENAME.pdf]\nOptions:")
where
writers'names = sort $ "pdf*" : map fst writers
readers'names = sort $ map fst readers
-- Determine default reader based on source file extensions
defaultReaderName :: String -> [FilePath] -> String
defaultReaderName fallback [] = fallback
defaultReaderName fallback (x:xs) =
case takeExtension (map toLower x) of
".xhtml" -> "html"
".html" -> "html"
".htm" -> "html"
".tex" -> "latex"
".latex" -> "latex"
".ltx" -> "latex"
".rst" -> "rst"
".org" -> "org"
".lhs" -> "markdown+lhs"
".db" -> "docbook"
".opml" -> "opml"
".wiki" -> "mediawiki"
".textile" -> "textile"
".native" -> "native"
".json" -> "json"
_ -> defaultReaderName fallback xs
-- Returns True if extension of first source is .lhs
lhsExtension :: [FilePath] -> Bool
lhsExtension (x:_) = takeExtension x == ".lhs"
lhsExtension _ = False
-- Determine default writer based on output file extension
defaultWriterName :: FilePath -> String
defaultWriterName "-" = "html" -- no output file
defaultWriterName x =
case takeExtension (map toLower x) of
"" -> "markdown" -- empty extension
".tex" -> "latex"
".latex" -> "latex"
".ltx" -> "latex"
".context" -> "context"
".ctx" -> "context"
".rtf" -> "rtf"
".rst" -> "rst"
".s5" -> "s5"
".native" -> "native"
".json" -> "json"
".txt" -> "markdown"
".text" -> "markdown"
".md" -> "markdown"
".markdown" -> "markdown"
".textile" -> "textile"
".lhs" -> "markdown+lhs"
".texi" -> "texinfo"
".texinfo" -> "texinfo"
".db" -> "docbook"
".odt" -> "odt"
".docx" -> "docx"
".epub" -> "epub"
".org" -> "org"
".asciidoc" -> "asciidoc"
".pdf" -> "latex"
".fb2" -> "fb2"
".opml" -> "opml"
['.',y] | y `elem` ['1'..'9'] -> "man"
_ -> "html"
main :: IO ()
main = do
rawArgs <- liftM (map UTF8.decodeArg) getArgs
prg <- getProgName
let compatMode = (prg == "hsmarkdown")
let (actions, args, errors) = if compatMode
then ([], rawArgs, [])
else getOpt Permute options rawArgs
unless (null errors) $
err 2 $ concat $ errors ++
["Try " ++ prg ++ " --help for more information."]
let defaultOpts' = if compatMode
then defaultOpts { optReader = "markdown_strict"
, optWriter = "html"
, optEmailObfuscation =
ReferenceObfuscation }
else defaultOpts
-- thread option data structure through all supplied option actions
opts <- foldl (>>=) (return defaultOpts') actions
let Opt { optTabStop = tabStop
, optPreserveTabs = preserveTabs
, optStandalone = standalone
, optReader = readerName
, optWriter = writerName
, optParseRaw = parseRaw
, optVariables = variables
, optMetadata = metadata
, optTableOfContents = toc
, optTransforms = transforms
, optTemplate = templatePath
, optOutputFile = outputFile
, optNumberSections = numberSections
, optNumberOffset = numberFrom
, optSectionDivs = sectionDivs
, optIncremental = incremental
, optSelfContained = selfContained
, optSmart = smart
, optOldDashes = oldDashes
, optHtml5 = html5
, optHtmlQTags = htmlQTags
, optHighlight = highlight
, optHighlightStyle = highlightStyle
, optChapters = chapters
, optHTMLMathMethod = mathMethod
, optReferenceODT = referenceODT
, optReferenceDocx = referenceDocx
, optEpubStylesheet = epubStylesheet
, optEpubMetadata = epubMetadata
, optEpubFonts = epubFonts
, optEpubChapterLevel = epubChapterLevel
, optTOCDepth = epubTOCDepth
, optDumpArgs = dumpArgs
, optIgnoreArgs = ignoreArgs
, optReferenceLinks = referenceLinks
, optWrapText = wrap
, optColumns = columns
, optFilters = filters
, optEmailObfuscation = obfuscationMethod
, optIdentifierPrefix = idPrefix
, optIndentedCodeClasses = codeBlockClasses
, optDataDir = mbDataDir
, optCiteMethod = citeMethod
, optListings = listings
, optLaTeXEngine = latexEngine
, optSlideLevel = slideLevel
, optSetextHeaders = setextHeaders
, optAscii = ascii
, optTeXLigatures = texLigatures
, optDefaultImageExtension = defaultImageExtension
, optTrace = trace
} = opts
when dumpArgs $
do UTF8.hPutStrLn stdout outputFile
mapM_ (\arg -> UTF8.hPutStrLn stdout arg) args
exitWith ExitSuccess
-- --bibliography implies -F pandoc-citeproc for backwards compatibility:
let filters' = case M.lookup "bibliography" metadata of
Just _ | optCiteMethod opts /= Natbib &&
optCiteMethod opts /= Biblatex &&
all (\f -> takeBaseName f /= "pandoc-citeproc")
filters -> "pandoc-citeproc" : filters
_ -> filters
let plugins = map externalFilter filters'
let sources = if ignoreArgs then [] else args
datadir <- case mbDataDir of
Nothing -> E.catch
(liftM Just $ getAppUserDataDirectory "pandoc")
(\e -> let _ = (e :: E.SomeException)
in return Nothing)
Just _ -> return mbDataDir
-- assign reader and writer based on options and filenames
let readerName' = case map toLower readerName of
[] -> defaultReaderName
(if any isURI sources
then "html"
else "markdown") sources
"html4" -> "html"
x -> x
let writerName' = case map toLower writerName of
[] -> defaultWriterName outputFile
"epub2" -> "epub"
"html4" -> "html"
x -> x
let pdfOutput = map toLower (takeExtension outputFile) == ".pdf"
let laTeXOutput = "latex" `isPrefixOf` writerName' ||
"beamer" `isPrefixOf` writerName'
writer <- if ".lua" `isSuffixOf` writerName'
-- note: use non-lowercased version writerName
then return $ IOStringWriter $ writeCustom writerName
else case getWriter writerName' of
Left e -> err 9 $
if writerName' == "pdf"
then e ++ "\nTo create a pdf with pandoc, use " ++
"the latex or beamer writer and specify\n" ++
"an output file with .pdf extension " ++
"(pandoc -t latex -o filename.pdf)."
else e
Right w -> return w
reader <- case getReader readerName' of
Right r -> return r
Left e -> err 7 e
let standalone' = standalone || not (isTextFormat writerName') || pdfOutput
templ <- case templatePath of
_ | not standalone' -> return ""
Nothing -> do
deftemp <- getDefaultTemplate datadir writerName'
case deftemp of
Left e -> throwIO e
Right t -> return t
Just tp -> do
-- strip off extensions
let format = takeWhile (`notElem` "+-") writerName'
let tp' = case takeExtension tp of
"" -> tp <.> format
_ -> tp
E.catch (UTF8.readFile tp')
(\e -> if isDoesNotExistError e
then E.catch
(readDataFileUTF8 datadir
("templates" </> tp'))
(\e' -> let _ = (e' :: E.SomeException)
in throwIO e')
else throwIO e)
variables' <- case mathMethod of
MathML Nothing -> do
s <- readDataFileUTF8 datadir "MathMLinHTML.js"
return $ ("mathml-script", s) : variables
_ -> return variables
variables'' <- if "dzslides" `isPrefixOf` writerName'
then do
dztempl <- readDataFileUTF8 datadir
("dzslides" </> "template.html")
let dzcore = unlines $ dropWhile (not . isPrefixOf "<!-- {{{{ dzslides core")
$ lines dztempl
return $ ("dzslides-core", dzcore) : variables'
else return variables'
let sourceURL = case sources of
[] -> Nothing
(x:_) -> case parseURI x of
Just u
| uriScheme u `elem` ["http:","https:"] ->
Just $ show u{ uriPath = "",
uriQuery = "",
uriFragment = "" }
_ -> Nothing
let readerOpts = def{ readerSmart = smart || (texLigatures &&
(laTeXOutput || "context" `isPrefixOf` writerName'))
, readerStandalone = standalone'
, readerParseRaw = parseRaw
, readerColumns = columns
, readerTabStop = tabStop
, readerOldDashes = oldDashes
, readerIndentedCodeClasses = codeBlockClasses
, readerApplyMacros = not laTeXOutput
, readerDefaultImageExtension = defaultImageExtension
, readerTrace = trace
}
let writerOptions = def { writerStandalone = standalone',
writerTemplate = templ,
writerVariables = variables'',
writerTabStop = tabStop,
writerTableOfContents = toc,
writerHTMLMathMethod = mathMethod,
writerIncremental = incremental,
writerCiteMethod = citeMethod,
writerIgnoreNotes = False,
writerNumberSections = numberSections,
writerNumberOffset = numberFrom,
writerSectionDivs = sectionDivs,
writerReferenceLinks = referenceLinks,
writerWrapText = wrap,
writerColumns = columns,
writerEmailObfuscation = obfuscationMethod,
writerIdentifierPrefix = idPrefix,
writerSourceURL = sourceURL,
writerUserDataDir = datadir,
writerHtml5 = html5,
writerHtmlQTags = htmlQTags,
writerChapters = chapters,
writerListings = listings,
writerBeamer = False,
writerSlideLevel = slideLevel,
writerHighlight = highlight,
writerHighlightStyle = highlightStyle,
writerSetextHeaders = setextHeaders,
writerTeXLigatures = texLigatures,
writerEpubMetadata = epubMetadata,
writerEpubStylesheet = epubStylesheet,
writerEpubFonts = epubFonts,
writerEpubChapterLevel = epubChapterLevel,
writerTOCDepth = epubTOCDepth,
writerReferenceODT = referenceODT,
writerReferenceDocx = referenceDocx
}
when (not (isTextFormat writerName') && outputFile == "-") $
err 5 $ "Cannot write " ++ writerName' ++ " output to stdout.\n" ++
"Specify an output file using the -o option."
let readSources [] = mapM readSource ["-"]
readSources srcs = mapM readSource srcs
readSource "-" = UTF8.getContents
readSource src = case parseURI src of
Just u | uriScheme u `elem` ["http:","https:"] ->
readURI src
_ -> UTF8.readFile src
readURI src = do
res <- openURL src
case res of
Left e -> throwIO e
Right (bs,_) -> return $ UTF8.toString bs
let convertTabs = tabFilter (if preserveTabs then 0 else tabStop)
let handleIncludes' = if readerName' == "latex" || readerName' == "latex+lhs"
then handleIncludes
else return
doc <- readSources sources >>=
handleIncludes' . convertTabs . intercalate "\n" >>=
reader readerOpts
let doc0 = M.foldWithKey setMeta doc metadata
let doc1 = foldr ($) doc0 transforms
doc2 <- foldrM ($) doc1 $ map ($ [writerName']) plugins
let writeBinary :: B.ByteString -> IO ()
writeBinary = B.writeFile (UTF8.encodePath outputFile)
let writerFn :: FilePath -> String -> IO ()
writerFn "-" = UTF8.putStr
writerFn f = UTF8.writeFile f
case writer of
IOStringWriter f -> f writerOptions doc2 >>= writerFn outputFile
IOByteStringWriter f -> f writerOptions doc2 >>= writeBinary
PureStringWriter f
| pdfOutput -> do
-- make sure writer is latex or beamer
unless laTeXOutput $
err 47 $ "cannot produce pdf output with " ++ writerName' ++
" writer"
-- check for latex program
mbLatex <- findExecutable latexEngine
when (mbLatex == Nothing) $
err 41 $ latexEngine ++ " not found. " ++
latexEngine ++ " is needed for pdf output."
res <- makePDF latexEngine f writerOptions doc2
case res of
Right pdf -> writeBinary pdf
Left err' -> do
B.hPutStr stderr $ err'
B.hPut stderr $ B.pack [10]
err 43 "Error producing PDF from TeX source"
| otherwise -> selfcontain (f writerOptions doc2 ++
['\n' | not standalone'])
>>= writerFn outputFile . handleEntities
where htmlFormat = writerName' `elem`
["html","html+lhs","html5","html5+lhs",
"s5","slidy","slideous","dzslides","revealjs"]
selfcontain = if selfContained && htmlFormat
then makeSelfContained datadir
else return
handleEntities = if htmlFormat && ascii
then toEntities
else id
|