From 532ae22c290b40932c1797b19b9cb4248ec543f6 Mon Sep 17 00:00:00 2001 From: John MacFarlane Date: Fri, 30 Oct 2015 10:50:18 -0700 Subject: [PATCH] Textile reader: don't do smart punctuation unless explicitly asked. Closes #2480. Note that although smart punctuation is part of the textile spec, it's not always wanted when converting from textile to, say, Markdown. So it seems better to make this an option. --- README | 6 ++---- src/Text/Pandoc/Readers/Textile.hs | 7 ++++--- tests/textile-reader.native | 16 ++++++++-------- 3 files changed, 14 insertions(+), 15 deletions(-) diff --git a/README b/README index 9807fbc1c..40fe3aafd 100644 --- a/README +++ b/README @@ -372,10 +372,8 @@ Reader options : Produce typographically correct output, converting straight quotes to curly quotes, `---` to em-dashes, `--` to en-dashes, and `...` to ellipses. Nonbreaking spaces are inserted after certain - abbreviations, such as "Mr." (Note: This option is significant only when - the input format is `markdown`, `markdown_strict`, `textile` or `twiki`. - It is selected automatically when the input format is `textile` or the - output format is `latex` or `context`, unless `--no-tex-ligatures` + abbreviations, such as "Mr." (Note: This option is selected automatically + when the output format is `latex` or `context`, unless `--no-tex-ligatures` is used.) `--old-dashes` diff --git a/src/Text/Pandoc/Readers/Textile.hs b/src/Text/Pandoc/Readers/Textile.hs index 83280aa2e..43aaa3f9a 100644 --- a/src/Text/Pandoc/Readers/Textile.hs +++ b/src/Text/Pandoc/Readers/Textile.hs @@ -79,11 +79,12 @@ readTextile opts s = -- | Generate a Pandoc ADT from a textile document parseTextile :: Parser [Char] ParserState Pandoc parseTextile = do - -- textile allows raw HTML and does smart punctuation by default + -- textile allows raw HTML and does smart punctuation by default, + -- but we do not enable smart punctuation unless it is explicitly + -- asked for, for better conversion to other light markup formats oldOpts <- stateOptions `fmap` getState updateState $ \state -> state{ stateOptions = - oldOpts{ readerSmart = True - , readerParseRaw = True + oldOpts{ readerParseRaw = True , readerOldDashes = True } } many blankline diff --git a/tests/textile-reader.native b/tests/textile-reader.native index de0637f5f..f6a8408c6 100644 --- a/tests/textile-reader.native +++ b/tests/textile-reader.native @@ -1,5 +1,5 @@ Pandoc (Meta {unMeta = fromList []}) -[Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "set",Space,Str "of",Space,Str "tests",Space,Str "for",Space,Str "pandoc",Space,Str "Textile",Space,Str "Reader.",Space,Str "Part",Space,Str "of",Space,Str "it",Space,Str "comes",LineBreak,Str "from",Space,Str "John",Space,Str "Gruber\8217s",Space,Str "markdown",Space,Str "test",Space,Str "suite."] +[Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "set",Space,Str "of",Space,Str "tests",Space,Str "for",Space,Str "pandoc",Space,Str "Textile",Space,Str "Reader.",Space,Str "Part",Space,Str "of",Space,Str "it",Space,Str "comes",LineBreak,Str "from",Space,Str "John",Space,Str "Gruber's",Space,Str "markdown",Space,Str "test",Space,Str "suite."] ,HorizontalRule ,Header 1 ("headers",[],[]) [Str "Headers"] ,Header 2 ("level-2-with-an-embeded-link",[],[]) [Str "Level",Space,Str "2",Space,Str "with",Space,Str "an",Space,Link [Str "embeded",Space,Str "link"] ("http://www.example.com","")] @@ -8,9 +8,9 @@ Pandoc (Meta {unMeta = fromList []}) ,Header 5 ("level-5",[],[]) [Str "Level",Space,Str "5"] ,Header 6 ("level-6",[],[]) [Str "Level",Space,Str "6"] ,Header 1 ("paragraphs",[],[]) [Str "Paragraphs"] -,Para [Str "Here\8217s",Space,Str "a",Space,Str "regular",Space,Str "paragraph."] +,Para [Str "Here's",Space,Str "a",Space,Str "regular",Space,Str "paragraph."] ,Para [Str "Line",Space,Str "breaks",Space,Str "are",Space,Str "preserved",Space,Str "in",Space,Str "textile,",Space,Str "so",Space,Str "you",Space,Str "can",Space,Str "not",Space,Str "wrap",Space,Str "your",Space,Str "very",LineBreak,Str "long",Space,Str "paragraph",Space,Str "with",Space,Str "your",Space,Str "favourite",Space,Str "text",Space,Str "editor",Space,Str "and",Space,Str "have",Space,Str "it",Space,Str "rendered",LineBreak,Str "with",Space,Str "no",Space,Str "break."] -,Para [Str "Here\8217s",Space,Str "one",Space,Str "with",Space,Str "a",Space,Str "bullet."] +,Para [Str "Here's",Space,Str "one",Space,Str "with",Space,Str "a",Space,Str "bullet."] ,BulletList [[Plain [Str "criminey."]]] ,Para [Str "There",Space,Str "should",Space,Str "be",Space,Str "a",Space,Str "paragraph",Space,Str "break",Space,Str "between",Space,Str "here"] @@ -87,9 +87,9 @@ Pandoc (Meta {unMeta = fromList []}) ,Para [Str "This",Space,Str "is",Space,Emph [Str "emphasized"],Str ",",Space,Str "and",Space,Str "so",Space,Emph [Str "is",Space,Str "this"],Str ".",LineBreak,Str "This",Space,Str "is",Space,Strong [Str "strong"],Str ",",Space,Str "and",Space,Str "so",Space,Strong [Str "is",Space,Str "this"],Str ".",LineBreak,Str "Hyphenated-words-are-ok,",Space,Str "as",Space,Str "well",Space,Str "as",Space,Str "strange_underscore_notation.",LineBreak,Str "A",Space,Link [Strong [Str "strong",Space,Str "link"]] ("http://www.foobar.com",""),Str "."] ,Para [Emph [Strong [Str "This",Space,Str "is",Space,Str "strong",Space,Str "and",Space,Str "em."]],LineBreak,Str "So",Space,Str "is",Space,Strong [Emph [Str "this"]],Space,Str "word",Space,Str "and",Space,Emph [Strong [Str "that",Space,Str "one"]],Str ".",LineBreak,Strikeout [Str "This",Space,Str "is",Space,Str "strikeout",Space,Str "and",Space,Strong [Str "strong"]]] ,Para [Str "Superscripts:",Space,Str "a",Superscript [Str "bc"],Str "d",Space,Str "a",Space,Superscript [Strong [Str "hello"]],Space,Str "a",Superscript [Str "hello",Space,Str "there"],Str ".",LineBreak,Str "Subscripts:",Space,Subscript [Str "here"],Space,Str "H",Space,Subscript [Str "2"],Str "O,",Space,Str "H",Space,Subscript [Str "23"],Str "O,",Space,Str "H",Space,Subscript [Str "many",Space,Str "of",Space,Str "them"],Str "O."] -,Para [Str "Dashes",Space,Str ":",Space,Str "How",Space,Str "cool",Space,Str "\8212",Space,Str "automatic",Space,Str "dashes."] -,Para [Str "Elipses",Space,Str ":",Space,Str "He",Space,Str "thought",Space,Str "and",Space,Str "thought",Space,Str "\8230",Space,Str "and",Space,Str "then",Space,Str "thought",Space,Str "some",Space,Str "more."] -,Para [Str "Quotes",Space,Str "and",Space,Str "apostrophes",Space,Str ":",Space,Quoted DoubleQuote [Str "I\8217d",Space,Str "like",Space,Str "to",Space,Str "thank",Space,Str "you"],Space,Str "for",Space,Str "example."] +,Para [Str "Dashes",Space,Str ":",Space,Str "How",Space,Str "cool",Space,Str "--",Space,Str "automatic",Space,Str "dashes."] +,Para [Str "Elipses",Space,Str ":",Space,Str "He",Space,Str "thought",Space,Str "and",Space,Str "thought",Space,Str "...",Space,Str "and",Space,Str "then",Space,Str "thought",Space,Str "some",Space,Str "more."] +,Para [Str "Quotes",Space,Str "and",Space,Str "apostrophes",Space,Str ":",Space,Str "\"I'd",Space,Str "like",Space,Str "to",Space,Str "thank",Space,Str "you\"",Space,Str "for",Space,Str "example."] ,Header 1 ("links",[],[]) [Str "Links"] ,Header 2 ("explicit",[],[]) [Str "Explicit"] ,Para [Str "Just",Space,Str "a",Space,Link [Str "url"] ("http://www.url.com","")] @@ -114,7 +114,7 @@ Pandoc (Meta {unMeta = fromList []}) ,[[Plain [Str "bella"]] ,[Plain [Str "45"]] ,[Plain [Str "f"]]]] -,Para [Str "and",Space,Str "some",Space,Str "text",Space,Str "following",Space,Str "\8230"] +,Para [Str "and",Space,Str "some",Space,Str "text",Space,Str "following",Space,Str "..."] ,Header 2 ("with-headers",[],[]) [Str "With",Space,Str "headers"] ,Table [] [AlignDefault,AlignDefault,AlignDefault] [0.0,0.0,0.0] [[Plain [Str "name"]] @@ -152,7 +152,7 @@ Pandoc (Meta {unMeta = fromList []}) ,RawBlock (Format "html") "" ,Para [Str "Html",Space,Str "blocks",Space,Str "can",Space,Str "be",Space,RawInline (Format "html") "
",Str "inlined",RawInline (Format "html") "
",Space,Str "as",Space,Str "well."] ,BulletList - [[Plain [Str "this",Space,RawInline (Format "html") "
",Space,Str "won\8217t",Space,Str "produce",Space,Str "raw",Space,Str "html",Space,Str "blocks",Space,RawInline (Format "html") "
"]] + [[Plain [Str "this",Space,RawInline (Format "html") "
",Space,Str "won't",Space,Str "produce",Space,Str "raw",Space,Str "html",Space,Str "blocks",Space,RawInline (Format "html") "
"]] ,[Plain [Str "but",Space,Str "this",Space,RawInline (Format "html") "",Space,Str "will",Space,Str "produce",Space,Str "inline",Space,Str "html",Space,RawInline (Format "html") ""]]] ,Para [Str "Can",Space,Str "you",Space,Str "prove",Space,Str "that",Space,Str "2",Space,Str "<",Space,Str "3",Space,Str "?"] ,Header 1 ("acronyms-and-marks",[],[]) [Str "Acronyms",Space,Str "and",Space,Str "marks"]