2015-11-14 17:46:55 -08:00
|
|
|
{-# LANGUAGE DeriveDataTypeable, DeriveGeneric #-}
|
2012-07-25 10:18:57 -07:00
|
|
|
{-
|
2016-03-22 17:20:39 -07:00
|
|
|
Copyright (C) 2012-2016 John MacFarlane <jgm@berkeley.edu>
|
2012-07-25 10:18:57 -07:00
|
|
|
|
|
|
|
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 : Text.Pandoc.Options
|
2016-03-22 17:20:39 -07:00
|
|
|
Copyright : Copyright (C) 2012-2016 John MacFarlane
|
2012-07-25 10:18:57 -07:00
|
|
|
License : GNU GPL, version 2 or above
|
|
|
|
|
|
|
|
Maintainer : John MacFarlane <jgm@berkeley.edu>
|
|
|
|
Stability : alpha
|
|
|
|
Portability : portable
|
|
|
|
|
|
|
|
Data structures and functions for representing parser and writer
|
|
|
|
options.
|
|
|
|
-}
|
2017-01-14 10:29:12 +01:00
|
|
|
module Text.Pandoc.Options ( module Text.Pandoc.Extensions
|
2012-07-25 11:08:06 -07:00
|
|
|
, ReaderOptions(..)
|
2012-07-26 22:59:56 -07:00
|
|
|
, HTMLMathMethod (..)
|
|
|
|
, CiteMethod (..)
|
|
|
|
, ObfuscationMethod (..)
|
|
|
|
, HTMLSlideVariant (..)
|
2013-01-05 13:00:12 -08:00
|
|
|
, EPUBVersion (..)
|
2015-12-11 15:58:11 -08:00
|
|
|
, WrapOption (..)
|
2016-11-27 20:31:04 +01:00
|
|
|
, TopLevelDivision (..)
|
2012-07-26 22:59:56 -07:00
|
|
|
, WriterOptions (..)
|
2014-06-25 14:05:21 -04:00
|
|
|
, TrackChanges (..)
|
2016-10-11 13:10:59 -04:00
|
|
|
, ReferenceLocation (..)
|
2012-07-25 22:35:41 -07:00
|
|
|
, def
|
2012-08-08 23:18:19 -07:00
|
|
|
, isEnabled
|
2012-07-25 10:18:57 -07:00
|
|
|
) where
|
2017-01-14 10:29:12 +01:00
|
|
|
import Text.Pandoc.Extensions
|
2012-07-25 10:45:45 -07:00
|
|
|
import Data.Default
|
2012-07-26 22:59:56 -07:00
|
|
|
import Text.Pandoc.Highlighting (Style, pygments)
|
2014-07-31 12:00:21 -07:00
|
|
|
import Text.Pandoc.MediaBag (MediaBag)
|
2015-03-19 17:07:18 +01:00
|
|
|
import Data.Data (Data)
|
|
|
|
import Data.Typeable (Typeable)
|
2015-11-14 17:46:55 -08:00
|
|
|
import GHC.Generics (Generic)
|
2012-07-25 10:18:57 -07:00
|
|
|
|
2012-07-25 11:08:06 -07:00
|
|
|
data ReaderOptions = ReaderOptions{
|
2017-01-14 13:06:27 +01:00
|
|
|
readerExtensions :: Extensions -- ^ Syntax extensions
|
2012-07-25 22:04:23 -07:00
|
|
|
, readerStandalone :: Bool -- ^ Standalone document with header
|
2012-07-25 20:20:03 -07:00
|
|
|
, readerParseRaw :: Bool -- ^ Parse raw HTML, LaTeX
|
|
|
|
, readerColumns :: Int -- ^ Number of columns in terminal
|
|
|
|
, readerTabStop :: Int -- ^ Tab stop
|
2012-07-25 20:42:15 -07:00
|
|
|
, readerApplyMacros :: Bool -- ^ Apply macros to TeX math
|
|
|
|
, readerIndentedCodeClasses :: [String] -- ^ Default classes for
|
|
|
|
-- indented code blocks
|
2013-02-05 20:08:00 -08:00
|
|
|
, readerDefaultImageExtension :: String -- ^ Default extension for images
|
2014-02-25 22:43:58 -08:00
|
|
|
, readerTrace :: Bool -- ^ Print debugging info
|
2014-06-25 13:57:56 -04:00
|
|
|
, readerTrackChanges :: TrackChanges
|
Introduce file-scope parsing (parse-before-combine)
Traditionally pandoc operates on multiple files by first concetenating
them (around extra line breaks) and then processing the joined file. So
it only parses a multi-file document at the document scope. This has the
benefit that footnotes and links can be in different files, but it also
introduces a couple of difficulties:
- it is difficult to join files with footnotes without some sort of
preprocessing, which makes it difficult to write academic documents
in small pieces.
- it makes it impossible to process multiple binary input files, which
can't be catted.
- it makes it impossible to process files from different input
formats.
This commit introduces alternative method. Instead of catting the files
first, it parses the files first, and then combines the parsed
output. This makes it impossible to have links across multiple files,
and auto-identified headers won't work correctly if headers in multiple
files have the same name. On the other hand, footnotes across multiple
files will work correctly and will allow more freedom for input formats.
Since ByteStringReaders can currently only read one binary file, and
will ignore subsequent files, we also changes the behavior to
automatically parse before combining if using the ByteStringReader. If
we use one file, it will work as normal. If there is more than one file
it will combine them after parsing (assuming that the format is the
same).
Note that this is intended to be an optional method, defaulting to
off. Turn it on with `--file-scope`.
2016-02-20 21:27:08 -05:00
|
|
|
, readerFileScope :: Bool -- ^ Parse before combining
|
2015-11-14 17:46:55 -08:00
|
|
|
} deriving (Show, Read, Data, Typeable, Generic)
|
2012-07-25 10:18:57 -07:00
|
|
|
|
2012-07-25 11:08:06 -07:00
|
|
|
instance Default ReaderOptions
|
|
|
|
where def = ReaderOptions{
|
2013-02-05 20:08:00 -08:00
|
|
|
readerExtensions = pandocExtensions
|
|
|
|
, readerStandalone = False
|
|
|
|
, readerParseRaw = False
|
|
|
|
, readerColumns = 80
|
|
|
|
, readerTabStop = 4
|
|
|
|
, readerApplyMacros = True
|
|
|
|
, readerIndentedCodeClasses = []
|
|
|
|
, readerDefaultImageExtension = ""
|
2014-02-25 22:43:58 -08:00
|
|
|
, readerTrace = False
|
2014-06-25 13:57:56 -04:00
|
|
|
, readerTrackChanges = AcceptChanges
|
Introduce file-scope parsing (parse-before-combine)
Traditionally pandoc operates on multiple files by first concetenating
them (around extra line breaks) and then processing the joined file. So
it only parses a multi-file document at the document scope. This has the
benefit that footnotes and links can be in different files, but it also
introduces a couple of difficulties:
- it is difficult to join files with footnotes without some sort of
preprocessing, which makes it difficult to write academic documents
in small pieces.
- it makes it impossible to process multiple binary input files, which
can't be catted.
- it makes it impossible to process files from different input
formats.
This commit introduces alternative method. Instead of catting the files
first, it parses the files first, and then combines the parsed
output. This makes it impossible to have links across multiple files,
and auto-identified headers won't work correctly if headers in multiple
files have the same name. On the other hand, footnotes across multiple
files will work correctly and will allow more freedom for input formats.
Since ByteStringReaders can currently only read one binary file, and
will ignore subsequent files, we also changes the behavior to
automatically parse before combining if using the ByteStringReader. If
we use one file, it will work as normal. If there is more than one file
it will combine them after parsing (assuming that the format is the
same).
Note that this is intended to be an optional method, defaulting to
off. Turn it on with `--file-scope`.
2016-02-20 21:27:08 -05:00
|
|
|
, readerFileScope = False
|
2012-07-25 10:45:45 -07:00
|
|
|
}
|
2012-07-26 22:59:56 -07:00
|
|
|
|
|
|
|
--
|
|
|
|
-- Writer options
|
|
|
|
--
|
|
|
|
|
2015-11-14 17:46:55 -08:00
|
|
|
data EPUBVersion = EPUB2 | EPUB3 deriving (Eq, Show, Read, Data, Typeable, Generic)
|
2013-01-05 13:00:12 -08:00
|
|
|
|
2012-07-26 22:59:56 -07:00
|
|
|
data HTMLMathMethod = PlainMath
|
|
|
|
| LaTeXMathML (Maybe String) -- url of LaTeXMathML.js
|
|
|
|
| JsMath (Maybe String) -- url of jsMath load script
|
|
|
|
| GladTeX
|
|
|
|
| WebTeX String -- url of TeX->image script.
|
|
|
|
| MathML (Maybe String) -- url of MathMLinHTML.js
|
|
|
|
| MathJax String -- url of MathJax.js
|
2014-09-25 18:23:28 +01:00
|
|
|
| KaTeX String String -- url of stylesheet and katex.js
|
2015-11-14 17:46:55 -08:00
|
|
|
deriving (Show, Read, Eq, Data, Typeable, Generic)
|
2012-07-26 22:59:56 -07:00
|
|
|
|
|
|
|
data CiteMethod = Citeproc -- use citeproc to render them
|
|
|
|
| Natbib -- output natbib cite commands
|
|
|
|
| Biblatex -- output biblatex cite commands
|
2015-11-14 17:46:55 -08:00
|
|
|
deriving (Show, Read, Eq, Data, Typeable, Generic)
|
2012-07-26 22:59:56 -07:00
|
|
|
|
|
|
|
-- | Methods for obfuscating email addresses in HTML.
|
|
|
|
data ObfuscationMethod = NoObfuscation
|
|
|
|
| ReferenceObfuscation
|
|
|
|
| JavascriptObfuscation
|
2015-11-14 17:46:55 -08:00
|
|
|
deriving (Show, Read, Eq, Data, Typeable, Generic)
|
2012-07-26 22:59:56 -07:00
|
|
|
|
|
|
|
-- | Varieties of HTML slide shows.
|
|
|
|
data HTMLSlideVariant = S5Slides
|
|
|
|
| SlidySlides
|
|
|
|
| SlideousSlides
|
|
|
|
| DZSlides
|
2013-03-20 16:59:47 -04:00
|
|
|
| RevealJsSlides
|
2012-07-26 22:59:56 -07:00
|
|
|
| NoSlides
|
2015-11-14 17:46:55 -08:00
|
|
|
deriving (Show, Read, Eq, Data, Typeable, Generic)
|
2012-07-26 22:59:56 -07:00
|
|
|
|
2014-06-25 13:50:08 -04:00
|
|
|
-- | Options for accepting or rejecting MS Word track-changes.
|
|
|
|
data TrackChanges = AcceptChanges
|
|
|
|
| RejectChanges
|
|
|
|
| AllChanges
|
2015-11-14 17:46:55 -08:00
|
|
|
deriving (Show, Read, Eq, Data, Typeable, Generic)
|
2014-06-25 13:50:08 -04:00
|
|
|
|
2015-12-11 15:58:11 -08:00
|
|
|
-- | Options for wrapping text in the output.
|
|
|
|
data WrapOption = WrapAuto -- ^ Automatically wrap to width
|
|
|
|
| WrapNone -- ^ No non-semantic newlines
|
|
|
|
| WrapPreserve -- ^ Preserve wrapping of input source
|
|
|
|
deriving (Show, Read, Eq, Data, Typeable, Generic)
|
|
|
|
|
2016-10-19 13:12:57 +02:00
|
|
|
-- | Options defining the type of top-level headers.
|
2016-11-27 20:31:04 +01:00
|
|
|
data TopLevelDivision = TopLevelPart -- ^ Top-level headers become parts
|
|
|
|
| TopLevelChapter -- ^ Top-level headers become chapters
|
|
|
|
| TopLevelSection -- ^ Top-level headers become sections
|
|
|
|
| TopLevelDefault -- ^ Top-level type is determined via
|
|
|
|
-- heuristics
|
|
|
|
deriving (Show, Read, Eq, Data, Typeable, Generic)
|
2016-10-19 13:12:57 +02:00
|
|
|
|
2016-10-11 13:10:59 -04:00
|
|
|
-- | Locations for footnotes and references in markdown output
|
|
|
|
data ReferenceLocation = EndOfBlock -- ^ End of block
|
|
|
|
| EndOfSection -- ^ prior to next section header (or end of document)
|
|
|
|
| EndOfDocument -- ^ at end of document
|
|
|
|
deriving (Show, Read, Eq, Data, Typeable, Generic)
|
|
|
|
|
2012-07-26 22:59:56 -07:00
|
|
|
-- | Options for writers
|
|
|
|
data WriterOptions = WriterOptions
|
2016-11-30 15:34:58 +01:00
|
|
|
{ writerTemplate :: Maybe String -- ^ Template to use
|
2012-07-26 22:59:56 -07:00
|
|
|
, writerVariables :: [(String, String)] -- ^ Variables to set in template
|
|
|
|
, writerTabStop :: Int -- ^ Tabstop for conversion btw spaces and tabs
|
|
|
|
, writerTableOfContents :: Bool -- ^ Include table of contents
|
|
|
|
, writerSlideVariant :: HTMLSlideVariant -- ^ Are we writing S5, Slidy or Slideous?
|
|
|
|
, writerIncremental :: Bool -- ^ True if lists should be incremental
|
|
|
|
, writerHTMLMathMethod :: HTMLMathMethod -- ^ How to print math in HTML
|
|
|
|
, writerIgnoreNotes :: Bool -- ^ Ignore footnotes (used in making toc)
|
|
|
|
, writerNumberSections :: Bool -- ^ Number sections in LaTeX
|
2013-02-23 18:11:05 -08:00
|
|
|
, writerNumberOffset :: [Int] -- ^ Starting number for section, subsection, ...
|
2012-07-26 22:59:56 -07:00
|
|
|
, writerSectionDivs :: Bool -- ^ Put sections in div tags in HTML
|
2017-01-14 13:06:27 +01:00
|
|
|
, writerExtensions :: Extensions -- ^ Markdown extensions that can be used
|
2012-07-26 22:59:56 -07:00
|
|
|
, writerReferenceLinks :: Bool -- ^ Use reference links in writing markdown, rst
|
2015-04-01 15:52:32 -07:00
|
|
|
, writerDpi :: Int -- ^ Dpi for pixel to/from inch/cm conversions
|
2015-12-11 15:58:11 -08:00
|
|
|
, writerWrapText :: WrapOption -- ^ Option for wrapping text
|
2012-07-26 22:59:56 -07:00
|
|
|
, writerColumns :: Int -- ^ Characters in a line (for text wrapping)
|
|
|
|
, writerEmailObfuscation :: ObfuscationMethod -- ^ How to obfuscate emails
|
|
|
|
, writerIdentifierPrefix :: String -- ^ Prefix for section & note ids in HTML
|
2012-09-25 20:26:38 -07:00
|
|
|
-- and for footnote marks in markdown
|
Options: Changed `writerSourceDir` to `writerSourceURL` (now a Maybe).
Previously we used to store the directory of the first input file,
even if it was local, and used this as a base directory for
finding images in ODT, EPUB, Docx, and PDF.
This has been confusing to many users. It seems better to look for
images relative to the current working directory, even if the first
file argument is in another directory.
writerSourceURL is set to 'Just url' when the first command-line
argument is an absolute URL. (So, relative links will be resolved
in relation to the first page.) Otherwise, 'Nothing'.
The ODT, EPUB, Docx, and PDF writers have been modified accordingly.
Note that this change may break some existing workflows. If you
have been assuming that relative links will be interpreted relative
to the directory of the first file argument, you'll need to
make that the current directory before running pandoc.
Closes #942.
2013-08-11 15:58:09 -07:00
|
|
|
, writerSourceURL :: Maybe String -- ^ Absolute URL + directory of 1st source file
|
2012-07-26 22:59:56 -07:00
|
|
|
, writerUserDataDir :: Maybe FilePath -- ^ Path of user data directory
|
|
|
|
, writerCiteMethod :: CiteMethod -- ^ How to print cites
|
2016-04-29 15:43:15 -07:00
|
|
|
, writerDocbook5 :: Bool -- ^ Produce DocBook5
|
2012-07-26 22:59:56 -07:00
|
|
|
, writerHtml5 :: Bool -- ^ Produce HTML5
|
2013-01-15 18:50:36 -08:00
|
|
|
, writerHtmlQTags :: Bool -- ^ Use @<q>@ tags for quotes in HTML
|
2012-07-26 22:59:56 -07:00
|
|
|
, writerBeamer :: Bool -- ^ Produce beamer LaTeX slide show
|
|
|
|
, writerSlideLevel :: Maybe Int -- ^ Force header level of slides
|
2016-11-27 20:31:04 +01:00
|
|
|
, writerTopLevelDivision :: TopLevelDivision -- ^ Type of top-level divisions
|
2012-07-26 22:59:56 -07:00
|
|
|
, writerListings :: Bool -- ^ Use listings package for code
|
|
|
|
, writerHighlight :: Bool -- ^ Highlight source code
|
|
|
|
, writerHighlightStyle :: Style -- ^ Style to use for highlighting
|
|
|
|
, writerSetextHeaders :: Bool -- ^ Use setext headers for levels 1-2 in markdown
|
|
|
|
, writerTeXLigatures :: Bool -- ^ Use tex ligatures quotes, dashes in latex
|
2013-01-05 13:00:12 -08:00
|
|
|
, writerEpubVersion :: Maybe EPUBVersion -- ^ Nothing or EPUB version
|
2013-01-04 22:41:09 -08:00
|
|
|
, writerEpubMetadata :: String -- ^ Metadata to include in EPUB
|
2012-07-26 22:59:56 -07:00
|
|
|
, writerEpubStylesheet :: Maybe String -- ^ EPUB stylesheet specified at command line
|
|
|
|
, writerEpubFonts :: [FilePath] -- ^ Paths to fonts to embed
|
2013-01-04 22:29:41 -08:00
|
|
|
, writerEpubChapterLevel :: Int -- ^ Header level for chapters (separate files)
|
2013-01-05 12:03:05 -08:00
|
|
|
, writerTOCDepth :: Int -- ^ Number of levels to include in TOC
|
2016-12-10 10:39:44 +01:00
|
|
|
, writerReferenceDoc :: Maybe FilePath -- ^ Path to reference document if specified
|
2014-07-30 13:09:55 -07:00
|
|
|
, writerMediaBag :: MediaBag -- ^ Media collected by docx or epub reader
|
2014-12-26 11:19:55 -07:00
|
|
|
, writerVerbose :: Bool -- ^ Verbose debugging output
|
2015-03-04 15:25:56 +05:30
|
|
|
, writerLaTeXArgs :: [String] -- ^ Flags to pass to latex-engine
|
2016-10-11 13:10:59 -04:00
|
|
|
, writerReferenceLocation :: ReferenceLocation -- ^ Location of footnotes and references for writing markdown
|
2015-11-14 17:46:55 -08:00
|
|
|
} deriving (Show, Data, Typeable, Generic)
|
2012-07-26 22:59:56 -07:00
|
|
|
|
|
|
|
instance Default WriterOptions where
|
2016-11-30 15:34:58 +01:00
|
|
|
def = WriterOptions { writerTemplate = Nothing
|
2012-07-26 22:59:56 -07:00
|
|
|
, writerVariables = []
|
|
|
|
, writerTabStop = 4
|
|
|
|
, writerTableOfContents = False
|
|
|
|
, writerSlideVariant = NoSlides
|
|
|
|
, writerIncremental = False
|
|
|
|
, writerHTMLMathMethod = PlainMath
|
|
|
|
, writerIgnoreNotes = False
|
|
|
|
, writerNumberSections = False
|
2013-02-23 18:11:05 -08:00
|
|
|
, writerNumberOffset = [0,0,0,0,0,0]
|
2012-07-26 22:59:56 -07:00
|
|
|
, writerSectionDivs = False
|
2012-08-07 13:17:30 -07:00
|
|
|
, writerExtensions = pandocExtensions
|
2012-07-26 22:59:56 -07:00
|
|
|
, writerReferenceLinks = False
|
2015-04-01 15:52:32 -07:00
|
|
|
, writerDpi = 96
|
2015-12-11 15:58:11 -08:00
|
|
|
, writerWrapText = WrapAuto
|
2012-07-26 22:59:56 -07:00
|
|
|
, writerColumns = 72
|
2016-06-20 10:35:14 -07:00
|
|
|
, writerEmailObfuscation = NoObfuscation
|
2012-07-26 22:59:56 -07:00
|
|
|
, writerIdentifierPrefix = ""
|
Options: Changed `writerSourceDir` to `writerSourceURL` (now a Maybe).
Previously we used to store the directory of the first input file,
even if it was local, and used this as a base directory for
finding images in ODT, EPUB, Docx, and PDF.
This has been confusing to many users. It seems better to look for
images relative to the current working directory, even if the first
file argument is in another directory.
writerSourceURL is set to 'Just url' when the first command-line
argument is an absolute URL. (So, relative links will be resolved
in relation to the first page.) Otherwise, 'Nothing'.
The ODT, EPUB, Docx, and PDF writers have been modified accordingly.
Note that this change may break some existing workflows. If you
have been assuming that relative links will be interpreted relative
to the directory of the first file argument, you'll need to
make that the current directory before running pandoc.
Closes #942.
2013-08-11 15:58:09 -07:00
|
|
|
, writerSourceURL = Nothing
|
2012-07-26 22:59:56 -07:00
|
|
|
, writerUserDataDir = Nothing
|
|
|
|
, writerCiteMethod = Citeproc
|
2016-04-29 15:43:15 -07:00
|
|
|
, writerDocbook5 = False
|
2012-07-26 22:59:56 -07:00
|
|
|
, writerHtml5 = False
|
2013-01-15 18:50:36 -08:00
|
|
|
, writerHtmlQTags = False
|
2012-07-26 22:59:56 -07:00
|
|
|
, writerBeamer = False
|
|
|
|
, writerSlideLevel = Nothing
|
2016-11-27 20:31:04 +01:00
|
|
|
, writerTopLevelDivision = TopLevelDefault
|
2012-07-26 22:59:56 -07:00
|
|
|
, writerListings = False
|
|
|
|
, writerHighlight = False
|
|
|
|
, writerHighlightStyle = pygments
|
|
|
|
, writerSetextHeaders = True
|
|
|
|
, writerTeXLigatures = True
|
2013-01-05 13:00:12 -08:00
|
|
|
, writerEpubVersion = Nothing
|
2013-01-04 22:41:09 -08:00
|
|
|
, writerEpubMetadata = ""
|
2012-07-26 22:59:56 -07:00
|
|
|
, writerEpubStylesheet = Nothing
|
|
|
|
, writerEpubFonts = []
|
2013-01-04 22:29:41 -08:00
|
|
|
, writerEpubChapterLevel = 1
|
2013-01-05 12:03:05 -08:00
|
|
|
, writerTOCDepth = 3
|
2016-12-10 10:39:44 +01:00
|
|
|
, writerReferenceDoc = Nothing
|
2014-07-31 12:00:21 -07:00
|
|
|
, writerMediaBag = mempty
|
2014-12-26 11:19:55 -07:00
|
|
|
, writerVerbose = False
|
2015-03-04 15:25:56 +05:30
|
|
|
, writerLaTeXArgs = []
|
2016-10-11 13:10:59 -04:00
|
|
|
, writerReferenceLocation = EndOfDocument
|
2012-07-26 22:59:56 -07:00
|
|
|
}
|
|
|
|
|
2012-08-08 23:18:19 -07:00
|
|
|
-- | Returns True if the given extension is enabled.
|
|
|
|
isEnabled :: Extension -> WriterOptions -> Bool
|
2017-01-14 13:06:27 +01:00
|
|
|
isEnabled ext opts = ext `extensionEnabled` (writerExtensions opts)
|