From d247e9f72e9c9a86cb0053cffc607b5f84f8b3a4 Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Sun, 22 Sep 2019 10:57:48 -0700
Subject: [PATCH] Make `plain` output plainer.
Previously we used the following Project Gutenberg conventions
for plain output:
- extra space before and after level 1 and 2 headings
- all-caps for strong emphasis `LIKE THIS`
- underscores surrounding regular emphasis `_like this_`
This commit makes `plain` output plainer. Strong and Emph
inlines are rendered without special formatting. Headings
are also rendered without special formatting, and with only
one blank line following.
To restore the former behavior, use `-t plain+gutenberg`.
API change: Add `Ext_gutenberg` constructor to `Extension`.
See #5741.
---
MANUAL.txt | 8 ++
src/Text/Pandoc/Extensions.hs | 1 +
src/Text/Pandoc/Writers/Markdown.hs | 21 +++--
test/Tests/Writers/Plain.hs | 4 +-
test/command/4529.md | 2 +-
test/writer.plain | 124 ++++++++--------------------
6 files changed, 64 insertions(+), 96 deletions(-)
diff --git a/MANUAL.txt b/MANUAL.txt
index 7e01a5002..c9ff7bea5 100644
--- a/MANUAL.txt
+++ b/MANUAL.txt
@@ -4544,6 +4544,14 @@ in several respects:
we must either disallow lazy wrapping or require a blank line between
list items.
+#### Extension: `gutenberg` ####
+
+Use [Project Gutenberg] conventions for `plain` output:
+all-caps for strong emphasis, surround by underscores
+for regular emphasis, add extra blank space around headings.
+
+ [Project Gutenberg]: https://www.gutenberg.org
+
Markdown variants
-----------------
diff --git a/src/Text/Pandoc/Extensions.hs b/src/Text/Pandoc/Extensions.hs
index 6cb87eef6..121b60e7b 100644
--- a/src/Text/Pandoc/Extensions.hs
+++ b/src/Text/Pandoc/Extensions.hs
@@ -155,6 +155,7 @@ data Extension =
| Ext_tex_math_double_backslash -- ^ TeX math btw \\(..\\) \\[..\\]
| Ext_tex_math_single_backslash -- ^ TeX math btw \(..\) \[..\]
| Ext_yaml_metadata_block -- ^ YAML metadata block
+ | Ext_gutenberg -- ^ Use Project Gutenberg conventions for plain
deriving (Show, Read, Enum, Eq, Ord, Bounded, Data, Typeable, Generic)
-- | Extensions to be used with pandoc-flavored markdown.
diff --git a/src/Text/Pandoc/Writers/Markdown.hs b/src/Text/Pandoc/Writers/Markdown.hs
index e298fafe9..fc25cde44 100644
--- a/src/Text/Pandoc/Writers/Markdown.hs
+++ b/src/Text/Pandoc/Writers/Markdown.hs
@@ -523,16 +523,22 @@ blockToMarkdown' opts (Header level attr inlines) = do
contents <- inlineListToMarkdown opts $
-- ensure no newlines; see #3736
walk lineBreakToSpace $
- if level == 1 && plain
+ if level == 1 && plain && isEnabled Ext_gutenberg opts
then capitalize inlines
else inlines
let setext = writerSetextHeaders opts
hdr = nowrap $ case level of
- 1 | plain -> blanklines 3 <> contents <> blanklines 2
+ 1 | plain ->
+ if isEnabled Ext_gutenberg opts
+ then blanklines 3 <> contents <> blanklines 2
+ else contents <> blankline
| setext ->
contents <> attr' <> cr <> text (replicate (offset contents) '=') <>
blankline
- 2 | plain -> blanklines 2 <> contents <> blankline
+ 2 | plain ->
+ if isEnabled Ext_gutenberg opts
+ then blanklines 2 <> contents <> blankline
+ else contents <> blankline
| setext ->
contents <> attr' <> cr <> text (replicate (offset contents) '-') <>
blankline
@@ -1036,13 +1042,18 @@ inlineToMarkdown opts (Emph lst) = do
plain <- asks envPlain
contents <- inlineListToMarkdown opts lst
return $ if plain
- then "_" <> contents <> "_"
+ then if isEnabled Ext_gutenberg opts
+ then "_" <> contents <> "_"
+ else contents
else "*" <> contents <> "*"
inlineToMarkdown _ (Strong []) = return empty
inlineToMarkdown opts (Strong lst) = do
plain <- asks envPlain
if plain
- then inlineListToMarkdown opts $ capitalize lst
+ then inlineListToMarkdown opts $
+ if isEnabled Ext_gutenberg opts
+ then capitalize lst
+ else lst
else do
contents <- inlineListToMarkdown opts lst
return $ "**" <> contents <> "**"
diff --git a/test/Tests/Writers/Plain.hs b/test/Tests/Writers/Plain.hs
index 2a2eb4226..b8d1f6693 100644
--- a/test/Tests/Writers/Plain.hs
+++ b/test/Tests/Writers/Plain.hs
@@ -13,7 +13,9 @@ import Text.Pandoc.Builder
infix 4 =:
(=:) :: (ToString a, ToPandoc a)
=> String -> (a, String) -> TestTree
-(=:) = test (purely (writePlain def) . toPandoc)
+(=:) = test (purely (writePlain def{ writerExtensions =
+ enableExtension Ext_gutenberg plainExtensions }) .
+ toPandoc)
tests :: [TestTree]
diff --git a/test/command/4529.md b/test/command/4529.md
index 4a2125b9c..4242a65c2 100644
--- a/test/command/4529.md
+++ b/test/command/4529.md
@@ -1,5 +1,5 @@
```
-% pandoc -f latex -t plain
+% pandoc -f latex -t plain+gutenberg
\chapter{First chapter}\label{sec:chp1}
The next chapter is Chapter~\ref{sec:chp2}.
\section{First section}\label{sec:chp1sec1}
diff --git a/test/writer.plain b/test/writer.plain
index 79921fa27..b8767957f 100644
--- a/test/writer.plain
+++ b/test/writer.plain
@@ -7,41 +7,31 @@ markdown test suite.
------------------------------------------------------------------------------
-
-
-HEADERS
-
+Headers
Level 2 with an embedded link
-Level 3 with _emphasis_
+Level 3 with emphasis
Level 4
Level 5
+Level 1
-
-LEVEL 1
-
-
-Level 2 with _emphasis_
+Level 2 with emphasis
Level 3
with no blank line
-
Level 2
with no blank line
------------------------------------------------------------------------------
-
-
-PARAGRAPHS
-
+Paragraphs
Here’s a regular paragraph.
@@ -56,10 +46,7 @@ here.
------------------------------------------------------------------------------
-
-
-BLOCK QUOTES
-
+Block Quotes
E-mail style:
@@ -88,10 +75,7 @@ And a following paragraph.
------------------------------------------------------------------------------
-
-
-CODE BLOCKS
-
+Code Blocks
Code:
@@ -111,10 +95,7 @@ And:
------------------------------------------------------------------------------
-
-
-LISTS
-
+Lists
Unordered
@@ -160,7 +141,6 @@ Minuses loose:
- Minus 3
-
Ordered
Tight:
@@ -201,7 +181,6 @@ Multiple paragraphs:
3. Item 3.
-
Nested
- Tab
@@ -229,7 +208,6 @@ Same thing but with paragraphs:
3. Third
-
Tabs and spaces
- this is a list item indented with tabs
@@ -240,7 +218,6 @@ Tabs and spaces
- this is an example list item indented with spaces
-
Fancy list markers
(2) begins with 2
@@ -275,10 +252,7 @@ B. Williams
------------------------------------------------------------------------------
-
-
-DEFINITION LISTS
-
+Definition Lists
Tight using spaces:
@@ -318,13 +292,13 @@ banana
Multiple blocks with italics:
-_apple_
+apple
red fruit
contains seeds, crisp, pleasant to taste
-_orange_
+orange
orange fruit
@@ -371,10 +345,7 @@ orange
1. sublist
2. sublist
-
-
-HTML BLOCKS
-
+HTML Blocks
Simple block on one line:
@@ -388,8 +359,8 @@ bar
Interpreted markdown in a table:
-This is _emphasized_
-And this is STRONG
+This is emphasized
+And this is strong
Here’s a simple block:
foo
@@ -426,30 +397,27 @@ Hr’s:
------------------------------------------------------------------------------
+Inline Markup
+This is emphasized, and so is this.
-INLINE MARKUP
+This is strong, and so is this.
+An emphasized link.
-This is _emphasized_, and so _is this_.
+This is strong and em.
-This is STRONG, and so IS THIS.
+So is this word.
-An _emphasized link_.
+This is strong and em.
-_THIS IS STRONG AND EM._
-
-So is _THIS_ word.
-
-_THIS IS STRONG AND EM._
-
-So is _THIS_ word.
+So is this word.
This is code: >, $, \, \$, <html>.
-~~This is _strikeout_.~~
+~~This is strikeout.~~
-Superscripts: a^(bc)d a^(_hello_) a^(hello there).
+Superscripts: a^(bc)d a^(hello) a^(hello there).
Subscripts: H₂O, H₂₃O, H_(many of them)O.
@@ -458,10 +426,7 @@ spaces: a^b c^d, a~b c~d.
------------------------------------------------------------------------------
-
-
-SMART QUOTES, ELLIPSES, DASHES
-
+Smart quotes, ellipses, dashes
“Hello,” said the spider. “‘Shelob’ is my name.”
@@ -481,10 +446,7 @@ Ellipses…and…and….
------------------------------------------------------------------------------
-
-
-LATEX
-
+LaTeX
-
- 2 + 2 = 4
@@ -499,19 +461,16 @@ LATEX
These shouldn’t be math:
- To get the famous equation, write $e = mc^2$.
-- $22,000 is a _lot_ of money. So is $34,000. (It worked if “lot” is
+- $22,000 is a lot of money. So is $34,000. (It worked if “lot” is
emphasized.)
- Shoes ($20) and socks ($5).
-- Escaped $: $73 _this should be emphasized_ 23$.
+- Escaped $: $73 this should be emphasized 23$.
Here’s a LaTeX table:
------------------------------------------------------------------------------
-
-
-SPECIAL CHARACTERS
-
+Special Characters
Here is some unicode:
@@ -565,10 +524,7 @@ Minus: -
------------------------------------------------------------------------------
-
-
-LINKS
-
+Links
Explicit
@@ -590,7 +546,6 @@ Email link
Empty.
-
Reference
Foo bar.
@@ -613,7 +568,6 @@ Foo bar.
Foo biz.
-
With ampersands
Here’s a link with an ampersand in the URL.
@@ -624,7 +578,6 @@ Here’s an inline link.
Here’s an inline link in pointy braces.
-
Autolinks
With an ampersand: http://example.com/?foo=1&bar=2
@@ -643,10 +596,7 @@ Auto-links should not occur here: <http://example.com/>
------------------------------------------------------------------------------
-
-
-IMAGES
-
+Images
From “Voyage dans la Lune” by Georges Melies (1902):
@@ -656,14 +606,10 @@ Here is a movie [movie] icon.
------------------------------------------------------------------------------
+Footnotes
-
-FOOTNOTES
-
-
-Here is a footnote reference,[1] and another.[2] This should _not_ be a
-footnote reference, because it contains a space.[^my note] Here is an inline
-note.[3]
+Here is a footnote reference,[1] and another.[2] This should not be a footnote
+reference, because it contains a space.[^my note] Here is an inline note.[3]
Notes can go in quotes.[4]
@@ -684,7 +630,7 @@ with list items).
If you want, you can indent every line, but you can also be lazy and just
indent the first line of each block.
-[3] This is _easier_ to type. Inline notes may contain links and ] verbatim
+[3] This is easier to type. Inline notes may contain links and ] verbatim
characters, as well as [bracketed text].
[4] In quote.