d20152e · typeable/pandoc

git.iko.soy/typeable/pandoc

Markdown writer: improved escaping.

`<` should not be escaped as `\<`, for compatibility with original Markdown. We now escape `<` and `>` with entities. Also, we now backslash-escape square brackets. Closes #2086.

commitd20152e01135a27decfd08dbda097fd1fda75354 authorJohn MacFarlane <jgm@berkeley.edu> dateSat 18 Apr 2015, 10:45 (12 years ago) parent0b80073

4 files changed+20−19

compare with master

unifiedsplit

src/Text/Pandoc/Writers/Markdown.hs+3−2 tests/Tests/Writers/Markdown.hs+2−2 tests/writer.markdown+11−11 tests/writer.opml+4−4

src/Text/Pandoc/Writers/Markdown.hs+3−2

@@ -246,7 +246,8 @@ noteToMarkdown opts num blocks = do

246246-- | Escape special characters for Markdown.

247247escapeString :: WriterOptions -> String -> String

248248escapeString opts = escapeStringUsing markdownEscapes

249− where markdownEscapes = backslashEscapes specialChars

249+ where markdownEscapes = ('<', "<") : ('>', ">") :

250+ backslashEscapes specialChars

250251 specialChars =

251252 (if isEnabled Ext_superscript opts

252253 then ('^':)

@@ -257,7 +258,7 @@ escapeString opts = escapeStringUsing markdownEscapes

257258 (if isEnabled Ext_tex_math_dollars opts

258259 then ('$':)

259260 else id) $

260− "\\`*_<>#"

261+ "\\`*_[]#"

261262

262263-- | Construct table of contents from list of header blocks.

263264tableOfContents :: WriterOptions -> [Block] -> Doc

tests/Tests/Writers/Markdown.hs+2−2

@@ -84,13 +84,13 @@ shortcutLinkRefsTests =

8484 ]

8585 , "Reference link is followed by text in brackets"

8686 =: (para ((link "/url" "" "link") <> "[text in brackets]"))

87− =?> unlines [ "[link][][text in brackets]"

87+ =?> unlines [ "[link][]\\[text in brackets\\]"

8888 , ""

8989 , " [link]: /url"

9090 ]

9191 , "Reference link is followed by space and text in brackets"

9292 =: (para ((link "/url" "" "link") <> " [text in brackets]"))

93− =?> unlines [ "[link][] [text in brackets]"

93+ =?> unlines [ "[link][] \\[text in brackets\\]"

9494 , ""

9595 , " [link]: /url"

9696 ]

tests/writer.markdown+11−11

@@ -80,7 +80,7 @@ E-mail style:

8080>

8181> > nested

8282

83−This should not be a block quote: 2 \> 1.

83+This should not be a block quote: 2 > 1.

8484

8585And a following paragraph.

8686

@@ -581,9 +581,9 @@ AT&T is another way to write it.

581581

582582This & that.

583583

584−4 \< 5.

584+4 < 5.

585585

586−6 \> 5.

586+6 > 5.

587587

588588Backslash: \\

589589

@@ -597,15 +597,15 @@ Left brace: {

597597

598598Right brace: }

599599

600−Left bracket: [

600+Left bracket: \[

601601

602−Right bracket: ]

602+Right bracket: \]

603603

604604Left paren: (

605605

606606Right paren: )

607607

608−Greater-than: \>

608+Greater-than: >

609609

610610Hash: \#

611611

@@ -652,7 +652,7 @@ Foo [bar](/url/).

652652

653653Foo [bar](/url/).

654654

655−With [embedded [brackets]](/url/).

655+With [embedded \[brackets\]](/url/).

656656

657657[b](/url/) by itself should be a link.

658658

@@ -662,7 +662,7 @@ Indented [twice](/url).

662662

663663Indented [thrice](/url).

664664

665−This should [not][] be a link.

665+This should \[not\]\[\] be a link.

666666

667667 [not]: /url

668668

@@ -716,8 +716,8 @@ Footnotes

716716=========

717717

718718Here is a footnote reference,[^1] and another.[^2] This should *not* be a

719−footnote reference, because it contains a space.[\^my note] Here is an inline

720−note.[^3]

719+footnote reference, because it contains a space.\[\^my note\] Here is an

720+inline note.[^3]

721721

722722> Notes can go in quotes.[^4]

723723

@@ -740,7 +740,7 @@ This paragraph should not be part of the note, as it is not indented.

740740

741741[^3]: This is *easier* to type. Inline notes may contain

742742 [links](http://google.com) and `]` verbatim characters, as well as

743− [bracketed text].

743+ \[bracketed text\].

744744

745745[^4]: In quote.

746746

tests/writer.opml+4−4

@@ -26,7 +26,7 @@

2626</outline>

2727<outline text="Paragraphs" _note="Here’s a regular paragraph.

In Markdown 1.0.0 and earlier. Version 8. This line turns into a list
item. Because a hard-wrapped line in the middle of a paragraph looked
like a list item.

Here’s one with a bullet. \* criminey.

There should be a hard line break\
here.

------------------------------------------------------------------------">

2828</outline>

29−<outline text="Block Quotes" _note="E-mail style:

> This is a block quote. It is pretty short.

> Code in a block quote:
>
> sub status {
> print "working";
> }
>
> A list:
>
> 1. item one
> 2. item two
>
> Nested block quotes:
>
> > nested
>
> > nested

This should not be a block quote: 2 \> 1.

And a following paragraph.

------------------------------------------------------------------------">

29+<outline text="Block Quotes" _note="E-mail style:

> This is a block quote. It is pretty short.

> Code in a block quote:
>
> sub status {
> print "working";
> }
>
> A list:
>
> 1. item one
> 2. item two
>
> Nested block quotes:
>
> > nested
>
> > nested

This should not be a block quote: 2 &gt; 1.

And a following paragraph.

------------------------------------------------------------------------">

3030</outline>

3131<outline text="Code Blocks" _note="Code:

 ---- (should be four hyphens)

 sub status {
 print "working";
 }

 this code block is indented by one tab

And:

 this code block is indented by two tabs

 These should not be escaped: \$ \\ \> \[ \{

------------------------------------------------------------------------">

3232</outline>

@@ -52,12 +52,12 @@

5252</outline>

5353<outline text="LaTeX" _note="- \cite[22-23]{smith.1899}
- $2+2=4$
- $x \in y$
- $\alpha \wedge \omega$
- $223$
- $p$-Tree
- Here’s some display math:
 $$\frac{d}{dx}f(x)=\lim_{h\to 0}\frac{f(x+h)-f(x)}{h}$$
- Here’s one that has a line break in it:
 $\alpha + \omega \times x^2$.

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 emphasized.)
- Shoes (\$20) and socks (\$5).
- Escaped `$`: \$73 *this should be emphasized* 23\$.

Here’s a LaTeX table:

\begin{tabular}{|l|l|}\hline
Animal & Number \\ \hline
Dog & 2 \\
Cat & 1 \\ \hline
\end{tabular}

------------------------------------------------------------------------">

5454</outline>

55−<outline text="Special Characters" _note="Here is some unicode:

- I hat: Î
- o umlaut: ö
- section: §
- set membership: ∈
- copyright: ©

AT&T has an ampersand in their name.

AT&T is another way to write it.

This & that.

4 \< 5.

6 \> 5.

Backslash: \\

Backtick: \`

Asterisk: \*

Underscore: \_

Left brace: {

Right brace: }

Left bracket: [

Right bracket: ]

Left paren: (

Right paren: )

Greater-than: \>

Hash: \#

Period: .

Bang: !

Plus: +

Minus: -

------------------------------------------------------------------------">

55+<outline text="Special Characters" _note="Here is some unicode:

- I hat: Î
- o umlaut: ö
- section: §
- set membership: ∈
- copyright: ©

AT&T has an ampersand in their name.

AT&T is another way to write it.

This & that.

4 &lt; 5.

6 &gt; 5.

Backslash: \\

Backtick: \`

Asterisk: \*

Underscore: \_

Left brace: {

Right brace: }

Left bracket: \[

Right bracket: \]

Left paren: (

Right paren: )

Greater-than: &gt;

Hash: \#

Period: .

Bang: !

Plus: +

Minus: -

------------------------------------------------------------------------">

5656</outline>

5757<outline text="Links">

5858 <outline text="Explicit" _note="Just a [URL](/url/).

[URL and title](/url/ "title").

[URL and title](/url/ "title preceded by two spaces").

[URL and title](/url/ "title preceded by a tab").

[URL and title](/url/ "title with "quotes" in it")

[URL and title](/url/ "title with single quotes")

[with\_underscore](/url/with_underscore)

[Email link](mailto:nobody@nowhere.net)

[Empty]().">

5959 </outline>

60− <outline text="Reference" _note="Foo [bar](/url/).

Foo [bar](/url/).

Foo [bar](/url/).

With [embedded [brackets]](/url/).

[b](/url/) by itself should be a link.

Indented [once](/url).

Indented [twice](/url).

Indented [thrice](/url).

This should [not][] be a link.

 [not]: /url

Foo [bar](/url/ "Title with "quotes" inside").

Foo [biz](/url/ "Title with "quote" inside").">

60+ <outline text="Reference" _note="Foo [bar](/url/).

Foo [bar](/url/).

Foo [bar](/url/).

With [embedded \[brackets\]](/url/).

[b](/url/) by itself should be a link.

Indented [once](/url).

Indented [twice](/url).

Indented [thrice](/url).

This should \[not\]\[\] be a link.

 [not]: /url

Foo [bar](/url/ "Title with "quotes" inside").

Foo [biz](/url/ "Title with "quote" inside").">

6161 </outline>

6262 <outline text="With ampersands" _note="Here’s a [link with an ampersand in the
URL](http://example.com/?foo=1&bar=2).

Here’s a link with an amersand in the link text:
[AT&T](http://att.com/ "AT&T").

Here’s an [inline link](/script?foo=1&bar=2).

Here’s an [inline link in pointy braces](/script?foo=1&bar=2).">

6363 </outline>

@@ -66,7 +66,7 @@

6666</outline>

6767<outline text="Images" _note="From “Voyage dans la Lune” by Georges Melies (1902):

![lalune](lalune.jpg "Voyage dans la Lune")

Here is a movie ![movie](movie.jpg) icon.

------------------------------------------------------------------------">

6868</outline>

69−<outline text="Footnotes" _note="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]

1. And in list items.[^5]

This paragraph should not be part of the note, as it is not indented.

[^1]: Here is the footnote. It can go anywhere after the footnote
 reference. It need not be placed at the end of the document.

[^2]: Here’s the long note. This one contains multiple blocks.

 Subsequent blocks are indented to show that they belong to the
 footnote (as with list items).

 { <code> }

 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](http://google.com) and `]` verbatim characters, as well as
 [bracketed text].

[^4]: In quote.

[^5]: In list.">

69+<outline text="Footnotes" _note="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]

1. And in list items.[^5]

This paragraph should not be part of the note, as it is not indented.

[^1]: Here is the footnote. It can go anywhere after the footnote
 reference. It need not be placed at the end of the document.

[^2]: Here’s the long note. This one contains multiple blocks.

 Subsequent blocks are indented to show that they belong to the
 footnote (as with list items).

 { <code> }

 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](http://google.com) and `]` verbatim characters, as well as
 \[bracketed text\].

[^4]: In quote.

[^5]: In list.">

7070</outline>

7171 </body>

7272</opml>