paragraph
foo bar baz
foo\n bar\nbaz*foo_barbaz\\`bin
" "\\*foo\\_bar_baz_\\\\\\`bin" describe "bullets" $ do it "simple" $ check "- foo
- bar
- baz
- foo
- bar
- baz
foo
bar
baz
" "# foo\n\n## bar\n\n###baz" it "trailing hashes" $ check "foo
" "# foo ####" it "underline" $ check "foo
bar
" "foo\n=============\n\nbar\n----------------\n" describe "headings with ID" $ do let withHeadingId = def { msAddHeadingId = True } it "without spaces" $ checkSet withHeadingId "foo
bar
baz
" "# foo\n\n## bar\n\n###baz" it "with spaces" $ checkSet withHeadingId "Executive summary
" "# Executive summary" it "with special characters" $ checkSet withHeadingId "Executive summary .!@#$%^*()-_=:
" "# Executive summary .!@#$%^*()-_=:" describe "blockquotes" $ do it "simple" $ check "" "> foo\n>\n> bar" describe "links" $ do it "simple" $ check "" "[bar](foo)" it "title" $ check "" "[bar](foo \"baz\")" it "escaped href" $ check "" "[bar](foo\\) \"baz\")" it "escaped title" $ check "" "[bar](foo\\) \"baz\\\"\")" it "inside a paragraph" $ check "foo
bar
Hello bar World
" "Hello [bar](foo) World" it "not a link" $ check "Not a [ link
" "Not a [ link" it "new tab" $ checkSet def { msLinkNewTab = True } "" "[bar](foo)" {- describe "github links" $ do it "simple" $ check "" "[[bar|foo]]" it "no link text" $ check "" "[[foo]]" it "escaping" $ check "" "[[bar|foo/baz bin]]" it "inside a list" $ check "" "* [[foo]]" -} describe "images" $ do it "simple" $ check "![\"foo\"](\"http://link.to/image.jpg\")
Hello World
Not an ![ image
" "Not an ![ image" describe "rules" $ do let options = concatMap (\t -> [t, snoc t '\n']) [ "* * *" , "***" , "*****" , "- - -" , "---------------------------------------" , "----------------------------------" ] forM_ options $ \o -> it (unpack o) $ check "" o describe "html" $ do it "inline" $ check "
foo
bar
bar" it "inline xss" $ check "
foo
bar
bar" it "block" $ check "
1 < 2
" "1 < 2" it "standalone" $ checkSet def { msStandaloneHtml = Set.fromList ["foo\nbarfoo
bar
[1]hello
" "{1}hello" it "references" $ check "[1]hello
" "{^1}hello" describe "examples" $ sequence_ examples describe "John Gruber's test suite" $ sequence_ gruber it "comments without spaces #22" $ check "" "" describe "no follow" $ do it "external 1" $ checkSet (setNoFollowExternal def) "" "[example](http://example.com)" it "external 2" $ checkSet (setNoFollowExternal def) "" "[example](//example.com)" it "internal" $ checkSet (setNoFollowExternal def) "" "[example](/foo)" getExamples :: IO [Spec] getExamples = do files <- getDirectoryContents dir mapM go $ filter (".md" `isSuffixOf`) files where dir = "test/examples" go basename = do let fp = dir basename input <- TIO.readFile fp output <- TIO.readFile $ replaceExtension fp "html" let (checker, stripper) | "-spec" `isInfixOf` fp = (check', dropFinalLF) | otherwise = (check, T.strip) return $ it basename $ checker (fromStrict $ stripper output) (fromStrict input) dropFinalLF t = fromMaybe t $ T.stripSuffix "\n" t getGruber :: IO [Spec] getGruber = do files <- getDirectoryContents dir mapM go $ filter (".text" `isSuffixOf`) files where dir = "test/Tests" go basename = do let fp = dir basename input <- TIO.readFile fp output <- TIO.readFile $ replaceExtension fp "html" return $ it basename $ checkNoNL (fromStrict $ T.strip output) (fromStrict input) markdown-0.1.16/test/examples/ 0000755 0000000 0000000 00000000000 13014511122 014372 5 ustar 00 0000000 0000000 markdown-0.1.16/test/examples/closing-tags.html 0000644 0000000 0000000 00000000035 13014511122 017650 0 ustar 00 0000000 0000000foo
foo
markdown-0.1.16/test/examples/double-backtick.html 0000644 0000000 0000000 00000000246 13014511122 020305 0 ustar 00 0000000 0000000This is a paragraph with double `backtick` inside with space.
This is a paragraph with double `backtick` inside without space.
1 < 2 & 2 > 1, also 1 < 2 & 2 > 1 ý &#xP; …
markdown-0.1.16/test/examples/entities.md 0000644 0000000 0000000 00000000111 13014511122 016531 0 ustar 00 0000000 0000000 1 < 2 & 2 > 1, also 1 < 2 & 2 > 1 ý &#xP; … markdown-0.1.16/test/examples/fence-whitespace.html 0000644 0000000 0000000 00000000046 13014511122 020472 0 ustar 00 0000000 0000000foo
bar| hi |
okay.
markdown-0.1.16/test/examples/html-blocks-spec1.md 0000644 0000000 0000000 00000000110 13014511122 020134 0 ustar 00 0000000 0000000| hi |
Markdown
<!-- foo -->Foo
this is lazy
- This is a list
- Another item
some random code
and other codeThis is a paragraph.
Another paragraph.
Non-paragraph.
Item.
- Sublist item.
- Item 1
- Item 2
- hello world
hello
data Foo
This is a multiline paragraph.
Multiline paragraph in a list.
The purpose of classy prelude is not to encourage writing polymorphic code based on the typeclasses provided. Though it's certainly possible to write code such as:
- No encounters
- Encounters
- First kind
- Second kind
foo
bar
bazAT&T has an ampersand in their name.
AT&T is another way to write it.
This & that.
4 < 5.
6 > 5.
Here's a link with an ampersand in the URL.
Here's a link with an amersand in the link text: AT&T.
Here's an inline link.
Here's an inline link.
markdown-0.1.16/test/Tests/Amps and angle encoding.text 0000644 0000000 0000000 00000000576 13014511122 021035 0 ustar 00 0000000 0000000 AT&T has an ampersand in their name. AT&T is another way to write it. This & that. 4 < 5. 6 > 5. Here's a [link] [1] with an ampersand in the URL. Here's a link with an amersand in the link text: [AT&T] [2]. Here's an inline [link](/script?foo=1&bar=2). Here's an inline [link](). [1]: http://example.com/?foo=1&bar=2 [2]: http://att.com/ "AT&T" markdown-0.1.16/test/Tests/Auto links.html 0000644 0000000 0000000 00000001040 13014511122 016550 0 ustar 00 0000000 0000000Link: http://example.com/.
With an ampersand: http://example.com/?foo=1&bar=2
- In a list?
- http://example.com/
- It should.
Blockquoted: http://example.com/
Auto-links should not occur here: <http://example.com/>
or here: <http://example.com/>
These should all get escaped:
Backslash: \
Backtick: `
Asterisk: *
Underscore: _
Left brace: {
Right brace: }
Left bracket: [
Right bracket: ]
Left paren: (
Right paren: )
Greater-than: >
Hash: #
Period: .
Bang: !
Plus: +
Minus: -
These should not, because they occur within a code block:
Backslash: \\
Backtick: \`
Asterisk: \*
Underscore: \_
Left brace: \{
Right brace: \}
Left bracket: \[
Right bracket: \]
Left paren: \(
Right paren: \)
Greater-than: \>
Hash: \#
Period: \.
Bang: \!
Plus: \+
Minus: \-
Nor should these, which occur in code spans:
Backslash: \\
Backtick: \`
Asterisk: \*
Underscore: \_
Left brace: \{
Right brace: \}
Left bracket: \[
Right bracket: \]
Left paren: \(
Right paren: \)
Greater-than: \>
Hash: \#
Period: \.
Bang: \!
Plus: \+
Minus: \-
These should get escaped, even though they're matching pairs for other Markdown constructs:
*asterisks*
_underscores_
`backticks`
This is a code span with a literal backslash-backtick sequence: \`
This is a tag with unescaped backticks bar.
This is a tag with backslashes bar.
markdown-0.1.16/test/Tests/Backslash escapes.text 0000644 0000000 0000000 00000002342 13014511122 020064 0 ustar 00 0000000 0000000 These should all get escaped: Backslash: \\ Backtick: \` Asterisk: \* Underscore: \_ Left brace: \{ Right brace: \} Left bracket: \[ Right bracket: \] Left paren: \( Right paren: \) Greater-than: \> Hash: \# Period: \. Bang: \! Plus: \+ Minus: \- These should not, because they occur within a code block: Backslash: \\ Backtick: \` Asterisk: \* Underscore: \_ Left brace: \{ Right brace: \} Left bracket: \[ Right bracket: \] Left paren: \( Right paren: \) Greater-than: \> Hash: \# Period: \. Bang: \! Plus: \+ Minus: \- Nor should these, which occur in code spans: Backslash: `\\` Backtick: `` \` `` Asterisk: `\*` Underscore: `\_` Left brace: `\{` Right brace: `\}` Left bracket: `\[` Right bracket: `\]` Left paren: `\(` Right paren: `\)` Greater-than: `\>` Hash: `\#` Period: `\.` Bang: `\!` Plus: `\+` Minus: `\-` These should get escaped, even though they're matching pairs for other Markdown constructs: \*asterisks\* \_underscores\_ \`backticks\` This is a code span with a literal backslash-backtick sequence: `` \` `` This is a tag with unescaped backticks bar. This is a tag with backslashes bar. markdown-0.1.16/test/Tests/Blockquotes with code blocks.html 0000644 0000000 0000000 00000000310 13014511122 022116 0 ustar 00 0000000 0000000markdown-0.1.16/test/Tests/Blockquotes with code blocks.text 0000644 0000000 0000000 00000000207 13014511122 022143 0 ustar 00 0000000 0000000 > Example: > > sub status { > print "working"; > } > > Or: > > sub status { > return "working"; > } markdown-0.1.16/test/Tests/Code Blocks.html 0000644 0000000 0000000 00000000470 13014511122 016615 0 ustar 00 0000000 0000000Example:
sub status { print "working"; }Or:
sub status { return "working"; }
code block on the first line
Regular text.
code block indented by spaces
Regular text.
the lines in this block
all contain trailing spaces
Regular Text.
code block on the last line
<test a=" content of attribute ">
Fix for backticks within HTML tag: like this
Here's how you put `backticks` in a code span.
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.
markdown-0.1.16/test/Tests/Hard-wrapped paragraphs with list-like lines.text 0000644 0000000 0000000 00000000305 13014511122 025116 0 ustar 00 0000000 0000000 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. markdown-0.1.16/test/Tests/Horizontal rules.html 0000644 0000000 0000000 00000000601 13014511122 020005 0 ustar 00 0000000 0000000Dashes:
---
- - -
Asterisks:
***
* * *
Underscores:
___
_ _ _
Inline within a paragraph: alt text.
.
.jpg)
Simple block on one line:
And nested without indentation:
And with attributes:
This was broken in 1.0.2b7:
Here's a simple block:
This should be a code block, though:
<div>
foo
</div>
As should this:
<div>foo</div>
Now, nested:
This should just be an HTML comment:
Multiline:
Code block:
<!-- Comment -->
Just plain comment, with trailing spaces on the line:
Code:
<hr />
Hr's:
markdown-0.1.16/test/Tests/Inline HTML (Simple).text 0000644 0000000 0000000 00000001051 13014511122 020057 0 ustar 00 0000000 0000000 Here's a simple block:
Hr's:
markdown-0.1.16/test/Tests/Inline HTML comments.html 0000644 0000000 0000000 00000000274 13014511122 020320 0 ustar 00 0000000 0000000
Paragraph one.
Paragraph two.
The end.
markdown-0.1.16/test/Tests/Inline HTML comments.text 0000644 0000000 0000000 00000000244 13014511122 020335 0 ustar 00 0000000 0000000 Paragraph one. Paragraph two. The end. markdown-0.1.16/test/Tests/Links, inline style.html 0000644 0000000 0000000 00000001500 13014511122 020254 0 ustar 00 0000000 0000000Just a URL.
URL wrapped in angle brackets.
URL w/ angle brackets + title.
(With outer parens and parens in url)
(With outer parens and parens in url)
markdown-0.1.16/test/Tests/Links, inline style.text 0000644 0000000 0000000 00000001102 13014511122 020272 0 ustar 00 0000000 0000000 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 has spaces afterward" ). [URL wrapped in angle brackets](). [URL w/ angle brackets + title]( "Here's the title"). [Empty](). [With parens in the URL](http://en.wikipedia.org/wiki/WIMP_(computing)) (With outer parens and [parens in url](/foo(bar))) [With parens in the URL](/foo(bar) "and a title") (With outer parens and [parens in url](/foo(bar) "and a title")) markdown-0.1.16/test/Tests/Links, reference style.html 0000644 0000000 0000000 00000002151 13014511122 020737 0 ustar 00 0000000 0000000Foo bar.
Foo bar.
Foo bar.
With embedded [brackets].
Indented once.
Indented twice.
Indented thrice.
Indented [four][] times.
[four]: /url
this should work
So should this.
And this.
And this.
And this.
But not [that] [].
Nor [that][].
Nor [that].
[Something in brackets like this should work]
[Same with this.]
In this case, this points to something else.
Backslashing should suppress [this] and [this].
Here's one where the link breaks across lines.
Here's another where the link breaks across lines, but with a line-ending space.
markdown-0.1.16/test/Tests/Links, reference style.text 0000644 0000000 0000000 00000001427 13014511122 020764 0 ustar 00 0000000 0000000 Foo [bar] [1]. Foo [bar][1]. Foo [bar] [1]. [1]: /url/ "Title" With [embedded [brackets]] [b]. Indented [once][]. Indented [twice][]. Indented [thrice][]. Indented [four][] times. [once]: /url [twice]: /url [thrice]: /url [four]: /url [b]: /url/ * * * [this] [this] should work So should [this][this]. And [this] []. And [this][]. And [this]. But not [that] []. Nor [that][]. Nor [that]. [Something in brackets like [this][] should work] [Same with [this].] In this case, [this](/somethingelse/) points to something else. Backslashing should suppress \[this] and [this\]. [this]: foo * * * Here's one where the [link breaks] across lines. Here's another where the [link breaks] across lines, but with a line-ending space. [link breaks]: /url/ markdown-0.1.16/test/Tests/Links, shortcut references.html 0000755 0000000 0000000 00000000400 13014511122 021633 0 ustar 00 0000000 0000000This is the simple case.
This one has a line break.
This one has a line break with a line-ending space.
markdown-0.1.16/test/Tests/Links, shortcut references.text 0000755 0000000 0000000 00000000354 13014511122 021663 0 ustar 00 0000000 0000000 This is the [simple case]. [simple case]: /simple This one has a [line break]. This one has a [line break] with a line-ending space. [line break]: /foo [this] [that] and the [other] [this]: /this [that]: /that [other]: /other markdown-0.1.16/test/Tests/Literal quotes in titles.html 0000644 0000000 0000000 00000000243 13014511122 021314 0 ustar 00 0000000 0000000Foo bar.
Foo bar.
markdown-0.1.16/test/Tests/Literal quotes in titles.text 0000644 0000000 0000000 00000000154 13014511122 021335 0 ustar 00 0000000 0000000 Foo [bar][]. Foo [bar](/url/ "Title with "quotes" inside"). [bar]: /url/ "Title with "quotes" inside" markdown-0.1.16/test/Tests/Markdown Documentation - Basics.html 0000644 0000000 0000000 00000022250 13014511122 022423 0 ustar 00 0000000 0000000Markdown: Basics
Getting the Gist of Markdown's Formatting Syntax
This page offers a brief overview of what it's like to use Markdown. The syntax page provides complete, detailed documentation for every feature, but Markdown should be very easy to pick up simply by looking at a few examples of it in action. The examples on this page are written in a before/after style, showing example syntax and the HTML output produced by Markdown.
It's also helpful to simply try Markdown out; the Dingus is a web application that allows you type your own Markdown-formatted text and translate it to XHTML.
Note: This document is itself written using Markdown; you can see the source for it by adding '.text' to the URL.
Paragraphs, Headers, Blockquotes
A paragraph is simply one or more consecutive lines of text, separated by one or more blank lines. (A blank line is any line that looks like a blank line -- a line containing nothing spaces or tabs is considered blank.) Normal paragraphs should not be intended with spaces or tabs.
Markdown offers two styles of headers: Setext and atx.
Setext-style headers for <h1> and <h2> are created by
"underlining" with equal signs (=) and hyphens (-), respectively.
To create an atx-style header, you put 1-6 hash marks (#) at the
beginning of the line -- the number of hashes equals the resulting
HTML header level.
Blockquotes are indicated using email-style '>' angle brackets.
Markdown:
A First Level Header
====================
A Second Level Header
---------------------
Now is the time for all good men to come to
the aid of their country. This is just a
regular paragraph.
The quick brown fox jumped over the lazy
dog's back.
### Header 3
> This is a blockquote.
>
> This is the second paragraph in the blockquote.
>
> ## This is an H2 in a blockquote
Output:
<h1>A First Level Header</h1>
<h2>A Second Level Header</h2>
<p>Now is the time for all good men to come to
the aid of their country. This is just a
regular paragraph.</p>
<p>The quick brown fox jumped over the lazy
dog's back.</p>
<h3>Header 3</h3>
<blockquote>
<p>This is a blockquote.</p>
<p>This is the second paragraph in the blockquote.</p>
<h2>This is an H2 in a blockquote</h2>
</blockquote>
Phrase Emphasis
Markdown uses asterisks and underscores to indicate spans of emphasis.
Markdown:
Some of these words *are emphasized*.
Some of these words _are emphasized also_.
Use two asterisks for **strong emphasis**.
Or, if you prefer, __use two underscores instead__.
Output:
<p>Some of these words <em>are emphasized</em>.
Some of these words <em>are emphasized also</em>.</p>
<p>Use two asterisks for <strong>strong emphasis</strong>.
Or, if you prefer, <strong>use two underscores instead</strong>.</p>
Lists
Unordered (bulleted) lists use asterisks, pluses, and hyphens (*,
+, and -) as list markers. These three markers are
interchangable; this:
* Candy.
* Gum.
* Booze.
this:
+ Candy.
+ Gum.
+ Booze.
and this:
- Candy.
- Gum.
- Booze.
all produce the same output:
<ul>
<li>Candy.</li>
<li>Gum.</li>
<li>Booze.</li>
</ul>
Ordered (numbered) lists use regular numbers, followed by periods, as list markers:
1. Red
2. Green
3. Blue
Output:
<ol>
<li>Red</li>
<li>Green</li>
<li>Blue</li>
</ol>
If you put blank lines between items, you'll get <p> tags for the
list item text. You can create multi-paragraph list items by indenting
the paragraphs by 4 spaces or 1 tab:
* A list item.
With multiple paragraphs.
* Another item in the list.
Output:
<ul>
<li><p>A list item.</p>
<p>With multiple paragraphs.</p></li>
<li><p>Another item in the list.</p></li>
</ul>
Links
Markdown supports two styles for creating links: inline and reference. With both styles, you use square brackets to delimit the text you want to turn into a link.
Inline-style links use parentheses immediately after the link text. For example:
This is an [example link](http://example.com/).
Output:
<p>This is an <a href="http://example.com/">
example link</a>.</p>
Optionally, you may include a title attribute in the parentheses:
This is an [example link](http://example.com/ "With a Title").
Output:
<p>This is an <a href="http://example.com/" title="With a Title">
example link</a>.</p>
Reference-style links allow you to refer to your links by names, which you define elsewhere in your document:
I get 10 times more traffic from [Google][1] than from
[Yahoo][2] or [MSN][3].
[1]: http://google.com/ "Google"
[2]: http://search.yahoo.com/ "Yahoo Search"
[3]: http://search.msn.com/ "MSN Search"
Output:
<p>I get 10 times more traffic from <a href="http://google.com/"
title="Google">Google</a> than from <a href="http://search.yahoo.com/"
title="Yahoo Search">Yahoo</a> or <a href="http://search.msn.com/"
title="MSN Search">MSN</a>.</p>
The title attribute is optional. Link names may contain letters, numbers and spaces, but are not case sensitive:
I start my morning with a cup of coffee and
[The New York Times][NY Times].
[ny times]: http://www.nytimes.com/
Output:
<p>I start my morning with a cup of coffee and
<a href="http://www.nytimes.com/">The New York Times</a>.</p>
Images
Image syntax is very much like link syntax.
Inline (titles are optional):
Reference-style:
![alt text][id]
[id]: /path/to/img.jpg "Title"
Both of the above examples produce the same output:
<img src="/path/to/img.jpg" alt="alt text" title="Title" />
Code
In a regular paragraph, you can create code span by wrapping text in
backtick quotes. Any ampersands (&) and angle brackets (< or
>) will automatically be translated into HTML entities. This makes
it easy to use Markdown to write about HTML example code:
I strongly recommend against using any `<blink>` tags.
I wish SmartyPants used named entities like `—`
instead of decimal-encoded entites like `—`.
Output:
<p>I strongly recommend against using any
<code><blink></code> tags.</p>
<p>I wish SmartyPants used named entities like
<code>&mdash;</code> instead of decimal-encoded
entites like <code>&#8212;</code>.</p>
To specify an entire block of pre-formatted code, indent every line of
the block by 4 spaces or 1 tab. Just like with code spans, &, <,
and > characters will be escaped automatically.
Markdown:
If you want your page to validate under XHTML 1.0 Strict,
you've got to put paragraph tags in your blockquotes:
<blockquote>
<p>For example.</p>
</blockquote>
Output:
<p>If you want your page to validate under XHTML 1.0 Strict,
you've got to put paragraph tags in your blockquotes:</p>
<pre><code><blockquote>
<p>For example.</p>
</blockquote>
</code></pre>
Markdown: Syntax
Note: This document is itself written using Markdown; you can see the source for it by adding '.text' to the URL.
Overview
Philosophy
Markdown is intended to be as easy-to-read and easy-to-write as is feasible.
Readability, however, is emphasized above all else. A Markdown-formatted document should be publishable as-is, as plain text, without looking like it's been marked up with tags or formatting instructions. While Markdown's syntax has been influenced by several existing text-to-HTML filters -- including Setext, atx, Textile, reStructuredText, Grutatext, and EtText -- the single biggest source of inspiration for Markdown's syntax is the format of plain text email.
To this end, Markdown's syntax is comprised entirely of punctuation characters, which punctuation characters have been carefully chosen so as to look like what they mean. E.g., asterisks around a word actually look like *emphasis*. Markdown lists look like, well, lists. Even blockquotes look like quoted passages of text, assuming you've ever used email.
Inline HTML
Markdown's syntax is intended for one purpose: to be used as a format for writing for the web.
Markdown is not a replacement for HTML, or even close to it. Its syntax is very small, corresponding only to a very small subset of HTML tags. The idea is not to create a syntax that makes it easier to insert HTML tags. In my opinion, HTML tags are already easy to insert. The idea for Markdown is to make it easy to read, write, and edit prose. HTML is a publishing format; Markdown is a writing format. Thus, Markdown's formatting syntax only addresses issues that can be conveyed in plain text.
For any markup that is not covered by Markdown's syntax, you simply use HTML itself. There's no need to preface it or delimit it to indicate that you're switching from Markdown to HTML; you just use the tags.
The only restrictions are that block-level HTML elements -- e.g. <div>,
<table>, <pre>, <p>, etc. -- must be separated from surrounding
content by blank lines, and the start and end tags of the block should
not be indented with tabs or spaces. Markdown is smart enough not
to add extra (unwanted) <p> tags around HTML block-level tags.
For example, to add an HTML table to a Markdown article:
This is a regular paragraph.
<table>
<tr>
<td>Foo</td>
</tr>
</table>
This is another regular paragraph.
Note that Markdown formatting syntax is not processed within block-level
HTML tags. E.g., you can't use Markdown-style *emphasis* inside an
HTML block.
Span-level HTML tags -- e.g. <span>, <cite>, or <del> -- can be
used anywhere in a Markdown paragraph, list item, or header. If you
want, you can even use HTML tags instead of Markdown formatting; e.g. if
you'd prefer to use HTML <a> or <img> tags instead of Markdown's
link or image syntax, go right ahead.
Unlike block-level HTML tags, Markdown syntax is processed within span-level tags.
Automatic Escaping for Special Characters
In HTML, there are two characters that demand special treatment: <
and &. Left angle brackets are used to start tags; ampersands are
used to denote HTML entities. If you want to use them as literal
characters, you must escape them as entities, e.g. <, and
&.
Ampersands in particular are bedeviling for web writers. If you want to
write about 'AT&T', you need to write 'AT&T'. You even need to
escape ampersands within URLs. Thus, if you want to link to:
http://images.google.com/images?num=30&q=larry+bird
you need to encode the URL as:
http://images.google.com/images?num=30&q=larry+bird
in your anchor tag href attribute. Needless to say, this is easy to
forget, and is probably the single most common source of HTML validation
errors in otherwise well-marked-up web sites.
Markdown allows you to use these characters naturally, taking care of
all the necessary escaping for you. If you use an ampersand as part of
an HTML entity, it remains unchanged; otherwise it will be translated
into &.
So, if you want to include a copyright symbol in your article, you can write:
©
and Markdown will leave it alone. But if you write:
AT&T
Markdown will translate it to:
AT&T
Similarly, because Markdown supports inline HTML, if you use angle brackets as delimiters for HTML tags, Markdown will treat them as such. But if you write:
4 < 5
Markdown will translate it to:
4 < 5
However, inside Markdown code spans and blocks, angle brackets and
ampersands are always encoded automatically. This makes it easy to use
Markdown to write about HTML code. (As opposed to raw HTML, which is a
terrible format for writing about HTML syntax, because every single <
and & in your example code needs to be escaped.)
Block Elements
Paragraphs and Line Breaks
A paragraph is simply one or more consecutive lines of text, separated by one or more blank lines. (A blank line is any line that looks like a blank line -- a line containing nothing but spaces or tabs is considered blank.) Normal paragraphs should not be intended with spaces or tabs.
The implication of the "one or more consecutive lines of text" rule is
that Markdown supports "hard-wrapped" text paragraphs. This differs
significantly from most other text-to-HTML formatters (including Movable
Type's "Convert Line Breaks" option) which translate every line break
character in a paragraph into a <br /> tag.
When you do want to insert a <br /> break tag using Markdown, you
end a line with two or more spaces, then type return.
Yes, this takes a tad more effort to create a <br />, but a simplistic
"every line break is a <br />" rule wouldn't work for Markdown.
Markdown's email-style blockquoting and multi-paragraph list items
work best -- and look better -- when you format them with hard breaks.
Headers
Markdown supports two styles of headers, Setext and atx.
Setext-style headers are "underlined" using equal signs (for first-level headers) and dashes (for second-level headers). For example:
This is an H1
=============
This is an H2
-------------
Any number of underlining ='s or -'s will work.
Atx-style headers use 1-6 hash characters at the start of the line, corresponding to header levels 1-6. For example:
# This is an H1
## This is an H2
###### This is an H6
Optionally, you may "close" atx-style headers. This is purely cosmetic -- you can use this if you think it looks better. The closing hashes don't even need to match the number of hashes used to open the header. (The number of opening hashes determines the header level.) :
# This is an H1 #
## This is an H2 ##
### This is an H3 ######
Blockquotes
Markdown uses email-style > characters for blockquoting. If you're
familiar with quoting passages of text in an email message, then you
know how to create a blockquote in Markdown. It looks best if you hard
wrap the text and put a > before every line:
> This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet,
> consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus.
> Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus.
>
> Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse
> id sem consectetuer libero luctus adipiscing.
Markdown allows you to be lazy and only put the > before the first
line of a hard-wrapped paragraph:
> This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet,
consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus.
Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus.
> Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse
id sem consectetuer libero luctus adipiscing.
Blockquotes can be nested (i.e. a blockquote-in-a-blockquote) by
adding additional levels of >:
> This is the first level of quoting.
>
> > This is nested blockquote.
>
> Back to the first level.
Blockquotes can contain other Markdown elements, including headers, lists, and code blocks:
> ## This is a header.
>
> 1. This is the first list item.
> 2. This is the second list item.
>
> Here's some example code:
>
> return shell_exec("echo $input | $markdown_script");
Any decent text editor should make email-style quoting easy. For example, with BBEdit, you can make a selection and choose Increase Quote Level from the Text menu.
Lists
Markdown supports ordered (numbered) and unordered (bulleted) lists.
Unordered lists use asterisks, pluses, and hyphens -- interchangably -- as list markers:
* Red
* Green
* Blue
is equivalent to:
+ Red
+ Green
+ Blue
and:
- Red
- Green
- Blue
Ordered lists use numbers followed by periods:
1. Bird
2. McHale
3. Parish
It's important to note that the actual numbers you use to mark the list have no effect on the HTML output Markdown produces. The HTML Markdown produces from the above list is:
<ol>
<li>Bird</li>
<li>McHale</li>
<li>Parish</li>
</ol>
If you instead wrote the list in Markdown like this:
1. Bird
1. McHale
1. Parish
or even:
3. Bird
1. McHale
8. Parish
you'd get the exact same HTML output. The point is, if you want to, you can use ordinal numbers in your ordered Markdown lists, so that the numbers in your source match the numbers in your published HTML. But if you want to be lazy, you don't have to.
If you do use lazy list numbering, however, you should still start the list with the number 1. At some point in the future, Markdown may support starting ordered lists at an arbitrary number.
List markers typically start at the left margin, but may be indented by up to three spaces. List markers must be followed by one or more spaces or a tab.
To make lists look nice, you can wrap items with hanging indents:
* Lorem ipsum dolor sit amet, consectetuer adipiscing elit.
Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi,
viverra nec, fringilla in, laoreet vitae, risus.
* Donec sit amet nisl. Aliquam semper ipsum sit amet velit.
Suspendisse id sem consectetuer libero luctus adipiscing.
But if you want to be lazy, you don't have to:
* Lorem ipsum dolor sit amet, consectetuer adipiscing elit.
Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi,
viverra nec, fringilla in, laoreet vitae, risus.
* Donec sit amet nisl. Aliquam semper ipsum sit amet velit.
Suspendisse id sem consectetuer libero luctus adipiscing.
If list items are separated by blank lines, Markdown will wrap the
items in <p> tags in the HTML output. For example, this input:
* Bird
* Magic
will turn into:
<ul>
<li>Bird</li>
<li>Magic</li>
</ul>
But this:
* Bird
* Magic
will turn into:
<ul>
<li><p>Bird</p></li>
<li><p>Magic</p></li>
</ul>
List items may consist of multiple paragraphs. Each subsequent paragraph in a list item must be intended by either 4 spaces or one tab:
1. This is a list item with two paragraphs. Lorem ipsum dolor
sit amet, consectetuer adipiscing elit. Aliquam hendrerit
mi posuere lectus.
Vestibulum enim wisi, viverra nec, fringilla in, laoreet
vitae, risus. Donec sit amet nisl. Aliquam semper ipsum
sit amet velit.
2. Suspendisse id sem consectetuer libero luctus adipiscing.
It looks nice if you indent every line of the subsequent paragraphs, but here again, Markdown will allow you to be lazy:
* This is a list item with two paragraphs.
This is the second paragraph in the list item. You're
only required to indent the first line. Lorem ipsum dolor
sit amet, consectetuer adipiscing elit.
* Another item in the same list.
To put a blockquote within a list item, the blockquote's >
delimiters need to be indented:
* A list item with a blockquote:
> This is a blockquote
> inside a list item.
To put a code block within a list item, the code block needs to be indented twice -- 8 spaces or two tabs:
* A list item with a code block:
<code goes here>
It's worth noting that it's possible to trigger an ordered list by accident, by writing something like this:
1986. What a great season.
In other words, a number-period-space sequence at the beginning of a line. To avoid this, you can backslash-escape the period:
1986\. What a great season.
Code Blocks
Pre-formatted code blocks are used for writing about programming or
markup source code. Rather than forming normal paragraphs, the lines
of a code block are interpreted literally. Markdown wraps a code block
in both <pre> and <code> tags.
To produce a code block in Markdown, simply indent every line of the block by at least 4 spaces or 1 tab. For example, given this input:
This is a normal paragraph:
This is a code block.
Markdown will generate:
<p>This is a normal paragraph:</p>
<pre><code>This is a code block.
</code></pre>
One level of indentation -- 4 spaces or 1 tab -- is removed from each line of the code block. For example, this:
Here is an example of AppleScript:
tell application "Foo"
beep
end tell
will turn into:
<p>Here is an example of AppleScript:</p>
<pre><code>tell application "Foo"
beep
end tell
</code></pre>
A code block continues until it reaches a line that is not indented (or the end of the article).
Within a code block, ampersands (&) and angle brackets (< and >)
are automatically converted into HTML entities. This makes it very
easy to include example HTML source code using Markdown -- just paste
it and indent it, and Markdown will handle the hassle of encoding the
ampersands and angle brackets. For example, this:
<div class="footer">
© 2004 Foo Corporation
</div>
will turn into:
<pre><code><div class="footer">
&copy; 2004 Foo Corporation
</div>
</code></pre>
Regular Markdown syntax is not processed within code blocks. E.g., asterisks are just literal asterisks within a code block. This means it's also easy to use Markdown to write about Markdown's own syntax.
Horizontal Rules
You can produce a horizontal rule tag (<hr />) by placing three or
more hyphens, asterisks, or underscores on a line by themselves. If you
wish, you may use spaces between the hyphens or asterisks. Each of the
following lines will produce a horizontal rule:
* * *
***
*****
- - -
---------------------------------------
_ _ _
Span Elements
Links
Markdown supports two style of links: inline and reference.
In both styles, the link text is delimited by [square brackets].
To create an inline link, use a set of regular parentheses immediately after the link text's closing square bracket. Inside the parentheses, put the URL where you want the link to point, along with an optional title for the link, surrounded in quotes. For example:
This is [an example](http://example.com/ "Title") inline link.
[This link](http://example.net/) has no title attribute.
Will produce:
<p>This is <a href="http://example.com/" title="Title">
an example</a> inline link.</p>
<p><a href="http://example.net/">This link</a> has no
title attribute.</p>
If you're referring to a local resource on the same server, you can use relative paths:
See my [About](/about/) page for details.
Reference-style links use a second set of square brackets, inside which you place a label of your choosing to identify the link:
This is [an example][id] reference-style link.
You can optionally use a space to separate the sets of brackets:
This is [an example] [id] reference-style link.
Then, anywhere in the document, you define your link label like this, on a line by itself:
[id]: http://example.com/ "Optional Title Here"
That is:
- Square brackets containing the link identifier (optionally indented from the left margin using up to three spaces);
- followed by a colon;
- followed by one or more spaces (or tabs);
- followed by the URL for the link;
- optionally followed by a title attribute for the link, enclosed in double or single quotes.
The link URL may, optionally, be surrounded by angle brackets:
[id]: <http://example.com/> "Optional Title Here"
You can put the title attribute on the next line and use extra spaces or tabs for padding, which tends to look better with longer URLs:
[id]: http://example.com/longish/path/to/resource/here
"Optional Title Here"
Link definitions are only used for creating links during Markdown processing, and are stripped from your document in the HTML output.
Link definition names may constist of letters, numbers, spaces, and punctuation -- but they are not case sensitive. E.g. these two links:
[link text][a]
[link text][A]
are equivalent.
The implicit link name shortcut allows you to omit the name of the link, in which case the link text itself is used as the name. Just use an empty set of square brackets -- e.g., to link the word "Google" to the google.com web site, you could simply write:
[Google][]
And then define the link:
[Google]: http://google.com/
Because link names may contain spaces, this shortcut even works for multiple words in the link text:
Visit [Daring Fireball][] for more information.
And then define the link:
[Daring Fireball]: http://daringfireball.net/
Link definitions can be placed anywhere in your Markdown document. I tend to put them immediately after each paragraph in which they're used, but if you want, you can put them all at the end of your document, sort of like footnotes.
Here's an example of reference links in action:
I get 10 times more traffic from [Google] [1] than from
[Yahoo] [2] or [MSN] [3].
[1]: http://google.com/ "Google"
[2]: http://search.yahoo.com/ "Yahoo Search"
[3]: http://search.msn.com/ "MSN Search"
Using the implicit link name shortcut, you could instead write:
I get 10 times more traffic from [Google][] than from
[Yahoo][] or [MSN][].
[google]: http://google.com/ "Google"
[yahoo]: http://search.yahoo.com/ "Yahoo Search"
[msn]: http://search.msn.com/ "MSN Search"
Both of the above examples will produce the following HTML output:
<p>I get 10 times more traffic from <a href="http://google.com/"
title="Google">Google</a> than from
<a href="http://search.yahoo.com/" title="Yahoo Search">Yahoo</a>
or <a href="http://search.msn.com/" title="MSN Search">MSN</a>.</p>
For comparison, here is the same paragraph written using Markdown's inline link style:
I get 10 times more traffic from [Google](http://google.com/ "Google")
than from [Yahoo](http://search.yahoo.com/ "Yahoo Search") or
[MSN](http://search.msn.com/ "MSN Search").
The point of reference-style links is not that they're easier to write. The point is that with reference-style links, your document source is vastly more readable. Compare the above examples: using reference-style links, the paragraph itself is only 81 characters long; with inline-style links, it's 176 characters; and as raw HTML, it's 234 characters. In the raw HTML, there's more markup than there is text.
With Markdown's reference-style links, a source document much more closely resembles the final output, as rendered in a browser. By allowing you to move the markup-related metadata out of the paragraph, you can add links without interrupting the narrative flow of your prose.
Emphasis
Markdown treats asterisks (*) and underscores (_) as indicators of
emphasis. Text wrapped with one * or _ will be wrapped with an
HTML <em> tag; double *'s or _'s will be wrapped with an HTML
<strong> tag. E.g., this input:
*single asterisks*
_single underscores_
**double asterisks**
__double underscores__
will produce:
<em>single asterisks</em>
<em>single underscores</em>
<strong>double asterisks</strong>
<strong>double underscores</strong>
You can use whichever style you prefer; the lone restriction is that the same character must be used to open and close an emphasis span.
Emphasis can be used in the middle of a word:
un*fucking*believable
But if you surround an * or _ with spaces, it'll be treated as a
literal asterisk or underscore.
To produce a literal asterisk or underscore at a position where it would otherwise be used as an emphasis delimiter, you can backslash escape it:
\*this text is surrounded by literal asterisks\*
Code
To indicate a span of code, wrap it with backtick quotes (`).
Unlike a pre-formatted code block, a code span indicates code within a
normal paragraph. For example:
Use the `printf()` function.
will produce:
<p>Use the <code>printf()</code> function.</p>
To include a literal backtick character within a code span, you can use multiple backticks as the opening and closing delimiters:
``There is a literal backtick (`) here.``
which will produce this:
<p><code>There is a literal backtick (`) here.</code></p>
The backtick delimiters surrounding a code span may include spaces -- one after the opening, one before the closing. This allows you to place literal backtick characters at the beginning or end of a code span:
A single backtick in a code span: `` ` ``
A backtick-delimited string in a code span: `` `foo` ``
will produce:
<p>A single backtick in a code span: <code>`</code></p>
<p>A backtick-delimited string in a code span: <code>`foo`</code></p>
With a code span, ampersands and angle brackets are encoded as HTML entities automatically, which makes it easy to include example HTML tags. Markdown will turn this:
Please don't use any `<blink>` tags.
into:
<p>Please don't use any <code><blink></code> tags.</p>
You can write this:
`—` is the decimal-encoded equivalent of `—`.
to produce:
<p><code>&#8212;</code> is the decimal-encoded
equivalent of <code>&mdash;</code>.</p>
Images
Admittedly, it's fairly difficult to devise a "natural" syntax for placing images into a plain text document format.
Markdown uses an image syntax that is intended to resemble the syntax for links, allowing for two styles: inline and reference.
Inline image syntax looks like this:
That is:
- An exclamation mark:
!; - followed by a set of square brackets, containing the
altattribute text for the image; - followed by a set of parentheses, containing the URL or path to
the image, and an optional
titleattribute enclosed in double or single quotes.
Reference-style image syntax looks like this:
![Alt text][id]
Where "id" is the name of a defined image reference. Image references are defined using syntax identical to link references:
[id]: url/to/image "Optional title attribute"
As of this writing, Markdown has no syntax for specifying the
dimensions of an image; if this is important to you, you can simply
use regular HTML <img> tags.
Miscellaneous
Automatic Links
Markdown supports a shortcut style for creating "automatic" links for URLs and email addresses: simply surround the URL or email address with angle brackets. What this means is that if you want to show the actual text of a URL or email address, and also have it be a clickable link, you can do this:
<http://example.com/>
Markdown will turn this into:
<a href="http://example.com/">http://example.com/</a>
Automatic links for email addresses work similarly, except that Markdown will also perform a bit of randomized decimal and hex entity-encoding to help obscure your address from address-harvesting spambots. For example, Markdown will turn this:
<address@example.com>
into something like this:
<a href="mailto:addre
ss@example.co
m">address@exa
mple.com</a>
which will render in a browser as a clickable link to "address@example.com".
(This sort of entity-encoding trick will indeed fool many, if not most, address-harvesting bots, but it definitely won't fool all of them. It's better than nothing, but an address published in this way will probably eventually start receiving spam.)
Backslash Escapes
Markdown allows you to use backslash escapes to generate literal
characters which would otherwise have special meaning in Markdown's
formatting syntax. For example, if you wanted to surround a word with
literal asterisks (instead of an HTML <em> tag), you can backslashes
before the asterisks, like this:
\*literal asterisks\*
Markdown provides backslash escapes for the following characters:
\ backslash
` backtick
* asterisk
_ underscore
{} curly braces
[] square brackets
() parentheses
# hash mark
+ plus sign
- minus sign (hyphen)
. dot
! exclamation mark
markdown-0.1.16/test/Tests/Nested blockquotes.text 0000644 0000000 0000000 00000000030 13014511122 020313 0 ustar 00 0000000 0000000 > foo > > > bar > > foo markdown-0.1.16/test/Tests/Ordered and unordered lists.html 0000644 0000000 0000000 00000003267 13014511122 021752 0 ustar 00 0000000 0000000foo
bar
foo
Unordered
Asterisks tight:
- asterisk 1
- asterisk 2
- asterisk 3
Asterisks loose:
asterisk 1
asterisk 2
asterisk 3
Pluses tight:
- Plus 1
- Plus 2
- Plus 3
Pluses loose:
Plus 1
Plus 2
Plus 3
Minuses tight:
- Minus 1
- Minus 2
- Minus 3
Minuses loose:
Minus 1
Minus 2
Minus 3
Ordered
Tight:
- First
- Second
- Third
and:
- One
- Two
- Three
Loose using tabs:
First
Second
Third
and using spaces:
One
Two
Three
Multiple paragraphs:
Item 1, graf one.
Item 2. graf two. The quick brown fox jumped over the lazy dog's back.
Item 2.
Item 3.
Nested
Tab
Tab
- Tab
Here's another:
- First
- Second:
- Fee
- Fie
- Foe
- Third
Same thing but with paragraphs:
First
Second:
- Fee
- Fie
- Foe
Third
This was an error in Markdown 1.0.1:
this
- sub
that
This is strong and em.
So is this word.
This is strong and em.
So is this word.
markdown-0.1.16/test/Tests/Strong and em together.text 0000644 0000000 0000000 00000000153 13014511122 020746 0 ustar 00 0000000 0000000 ***This is strong and em.*** So is ***this*** word. ___This is strong and em.___ So is ___this___ word. markdown-0.1.16/test/Tests/Tabs.html 0000644 0000000 0000000 00000000667 13014511122 015446 0 ustar 00 0000000 0000000this is a list item indented with tabs
this is a list item indented with spaces
Code:
this code block is indented by one tab
And:
this code block is indented by two tabs
And:
+ this is an example list item
indented with tabs
+ this is an example list item
indented with spaces
markdown-0.1.16/test/Tests/Tidyness.text 0000644 0000000 0000000 00000000116 13014511122 016364 0 ustar 00 0000000 0000000 > A list within a blockquote: > > * asterisk 1 > * asterisk 2 > * asterisk 3 markdown-0.1.16/Text/ 0000755 0000000 0000000 00000000000 13014511122 012521 5 ustar 00 0000000 0000000 markdown-0.1.16/Text/Markdown.hs 0000644 0000000 0000000 00000015227 13014511122 014646 0 ustar 00 0000000 0000000 {-# LANGUAGE OverloadedStrings #-} {-# LANGUAGE GeneralizedNewtypeDeriving #-} {-# LANGUAGE RankNTypes #-} module Text.Markdown ( -- * Functions markdown -- * Settings , MarkdownSettings , defaultMarkdownSettings , msXssProtect , msStandaloneHtml , msFencedHandlers , msBlockCodeRenderer , msLinkNewTab , msBlankBeforeBlockquote , msBlockFilter , msAddHeadingId , setNoFollowExternal -- * Newtype , Markdown (..) -- * Fenced handlers , FencedHandler (..) , codeFencedHandler , htmlFencedHandler -- * Convenience re-exports , def ) where import Control.Arrow ((&&&)) import Text.Markdown.Inline import Text.Markdown.Block import Text.Markdown.Types import Prelude hiding (sequence, takeWhile) import Data.Char (isAlphaNum) import Data.Default (Default (..)) import Data.List (intercalate, isInfixOf) import Data.Maybe (isJust) import Data.Text (Text) import qualified Data.Text as T import qualified Data.Text.Lazy as TL import Text.Blaze (toValue) import Text.Blaze.Html (ToMarkup (..), Html) import Text.Blaze.Html.Renderer.Text (renderHtml) import Data.Conduit import qualified Data.Conduit.List as CL import Data.Monoid (Monoid (mappend, mempty, mconcat)) import Data.Functor.Identity (runIdentity) import qualified Text.Blaze.Html5 as H import qualified Text.Blaze.Html5.Attributes as HA import Text.HTML.SanitizeXSS (sanitizeBalance) import qualified Data.Map as Map import Data.String (IsString) -- | A newtype wrapper providing a @ToHtml@ instance. newtype Markdown = Markdown TL.Text deriving(Eq, Ord, Monoid, IsString, Show) instance ToMarkup Markdown where toMarkup (Markdown t) = markdown def t -- | Convert the given textual markdown content to HTML. -- -- >>> :set -XOverloadedStrings -- >>> import Text.Blaze.Html.Renderer.Text -- >>> renderHtml $ markdown def "# Hello World!" -- "A list within a blockquote:
- asterisk 1
- asterisk 2
- asterisk 3
Hello World!
" -- -- >>> renderHtml $ markdown def { msXssProtect = False } "" -- "" markdown :: MarkdownSettings -> TL.Text -> Html markdown ms tl = sanitize $ runIdentity $ CL.sourceList blocksH $= toHtmlB ms $$ CL.fold mappend mempty where sanitize | msXssProtect ms = preEscapedToMarkup . sanitizeBalance . TL.toStrict . renderHtml | otherwise = id blocksH :: [Block Html] blocksH = processBlocks blocks blocks :: [Block Text] blocks = runIdentity $ CL.sourceList (TL.toChunks tl) $$ toBlocks ms =$ CL.consume processBlocks :: [Block Text] -> [Block Html] processBlocks = map (fmap $ toHtmlI ms) . msBlockFilter ms . map (fmap $ intercalate [InlineHtml ""]) . map (fmap $ map $ toInline refs) . map toBlockLines refs = Map.unions $ map toRef blocks where toRef (BlockReference x y) = Map.singleton x y toRef _ = Map.empty data MState = NoState | InList ListType toHtmlB :: Monad m => MarkdownSettings -> Conduit (Block Html) m Html toHtmlB ms = loop NoState where loop state = await >>= maybe (closeState state) (\x -> do state' <- getState state x yield $ go x loop state') closeState NoState = return () closeState (InList Unordered) = yield $ escape "" closeState (InList Ordered) = yield $ escape "" getState NoState (BlockList ltype _) = do yield $ escape $ case ltype of Unordered -> "
- "
Ordered -> "
- "
return $ InList ltype
getState NoState _ = return NoState
getState state@(InList lt1) b@(BlockList lt2 _)
| lt1 == lt2 = return state
| otherwise = closeState state >> getState NoState b
getState state@(InList _) _ = closeState state >> return NoState
go (BlockPara h) = H.p h
go (BlockPlainText h) = h
go (BlockList _ (Left h)) = H.li h
go (BlockList _ (Right bs)) = H.li $ blocksToHtml bs
go (BlockHtml t) = escape t
go (BlockCode a b) = msBlockCodeRenderer ms a (id &&& toMarkup $ b)
go (BlockQuote bs) = H.blockquote $ blocksToHtml bs
go BlockRule = H.hr
go (BlockHeading level h)
| msAddHeadingId ms = wrap level H.! HA.id (clean h) $ h
| otherwise = wrap level h
where
wrap 1 = H.h1
wrap 2 = H.h2
wrap 3 = H.h3
wrap 4 = H.h4
wrap 5 = H.h5
wrap _ = H.h6
isValidChar c = isAlphaNum c || isInfixOf [c] "-_:."
clean = toValue . TL.filter isValidChar . (TL.replace " " "-") . TL.toLower . renderHtml
go BlockReference{} = return ()
blocksToHtml bs = runIdentity $ mapM_ yield bs $$ toHtmlB ms =$ CL.fold mappend mempty
escape :: Text -> Html
escape = preEscapedToMarkup
toHtmlI :: MarkdownSettings -> [Inline] -> Html
toHtmlI ms is0
| msXssProtect ms = escape $ sanitizeBalance $ TL.toStrict $ renderHtml final
| otherwise = final
where
final = gos is0
gos = mconcat . map go
go (InlineText t) = toMarkup t
go (InlineItalic is) = H.i $ gos is
go (InlineBold is) = H.b $ gos is
go (InlineCode t) = H.code $ toMarkup t
go (InlineLink url mtitle content) =
H.a
H.! HA.href (H.toValue url)
H.!? (msLinkNewTab ms, HA.target "_blank")
H.!? (msNoFollowExternal ms && isExternalLink url, HA.rel "nofollow")
H.!? (isJust mtitle, HA.title $ maybe (error "impossible") H.toValue mtitle)
$ gos content
go (InlineImage url Nothing content) = H.img H.! HA.src (H.toValue url) H.! HA.alt (H.toValue content)
go (InlineImage url (Just title) content) = H.img H.! HA.src (H.toValue url) H.! HA.alt (H.toValue content) H.! HA.title (H.toValue title)
go (InlineHtml t) = escape t
go (InlineFootnoteRef x) = let ishown = TL.pack (show x)
(<>) = mappend
in H.a H.! HA.href (H.toValue $ "#footnote-" <> ishown)
H.! HA.id (H.toValue $ "ref-" <> ishown) $ H.toHtml $ "[" <> ishown <> "]"
go (InlineFootnote x) = let ishown = TL.pack (show x)
(<>) = mappend
in H.a H.! HA.href (H.toValue $ "#ref-" <> ishown)
H.! HA.id (H.toValue $ "footnote-" <> ishown) $ H.toHtml $ "[" <> ishown <> "]"
-- | For external links, add the rel="nofollow" attribute
--
-- @since 0.1.16
setNoFollowExternal :: MarkdownSettings -> MarkdownSettings
setNoFollowExternal ms = ms { msNoFollowExternal = True }
-- | Is the given URL an external link?
isExternalLink :: Text -> Bool
isExternalLink = T.isInfixOf "//"
markdown-0.1.16/Text/Markdown/ 0000755 0000000 0000000 00000000000 13014511122 014303 5 ustar 00 0000000 0000000 markdown-0.1.16/Text/Markdown/Block.hs 0000644 0000000 0000000 00000030546 13014511122 015701 0 ustar 00 0000000 0000000 {-# LANGUAGE OverloadedStrings #-}
{-# LANGUAGE PatternGuards #-}
{-# LANGUAGE NoImplicitPrelude #-}
{-# LANGUAGE RankNTypes #-}
{-# LANGUAGE CPP #-}
{-# OPTIONS_HADDOCK hide #-}
module Text.Markdown.Block
( Block (..)
, ListType (..)
, toBlocks
, toBlockLines
) where
import Prelude
import Control.Monad (msum)
#if MIN_VERSION_conduit(1, 0, 0)
import Data.Conduit
#else
import Data.Conduit hiding ((=$=))
import Data.Conduit.Internal (pipeL)
#endif
import qualified Data.Conduit.Text as CT
import qualified Data.Conduit.List as CL
import Data.Text (Text)
import qualified Data.Text as T
import Data.Functor.Identity (runIdentity)
import Data.Char (isDigit)
import Text.Markdown.Types
import qualified Data.Set as Set
import qualified Data.Map as Map
#if !MIN_VERSION_conduit(1, 0, 0)
(=$=) :: Monad m => Pipe a a b x m y -> Pipe b b c y m z -> Pipe a a c x m z
(=$=) = pipeL
#endif
toBlockLines :: Block Text -> Block [Text]
toBlockLines = fmap $ map T.stripEnd
. concatMap (T.splitOn " \r\n")
. T.splitOn " \n"
toBlocks :: Monad m => MarkdownSettings -> Conduit Text m (Block Text)
toBlocks ms =
mapOutput fixWS CT.lines =$= toBlocksLines ms
where
fixWS = T.pack . go 0 . T.unpack
go _ [] = []
go i ('\r':cs) = go i cs
go i ('\t':cs) =
(replicate j ' ') ++ go (i + j) cs
where
j = 4 - (i `mod` 4)
go i (c:cs) = c : go (i + 1) cs
toBlocksLines :: Monad m => MarkdownSettings -> Conduit Text m (Block Text)
toBlocksLines ms = awaitForever (start ms) =$= tightenLists
tightenLists :: Monad m => Conduit (Either Blank (Block Text)) m (Block Text)
tightenLists =
go Nothing
where
go mTightList =
await >>= maybe (return ()) go'
where
go' (Left Blank) = go mTightList
go' (Right (BlockList ltNew contents)) =
case mTightList of
Just (ltOld, isTight) | ltOld == ltNew -> do
yield $ BlockList ltNew $ (if isTight then tighten else untighten) contents
go mTightList
_ -> do
isTight <- checkTight ltNew False
yield $ BlockList ltNew $ (if isTight then tighten else untighten) contents
go $ Just (ltNew, isTight)
go' (Right b) = yield b >> go Nothing
tighten (Right [BlockPara t]) = Left t
tighten (Right []) = Left T.empty
tighten x = x
untighten (Left t) = Right [BlockPara t]
untighten x = x
checkTight lt sawBlank = do
await >>= maybe (return $ not sawBlank) go'
where
go' (Left Blank) = checkTight lt True
go' b@(Right (BlockList ltNext _)) | ltNext == lt = do
leftover b
return $ not sawBlank
go' b = leftover b >> return False
data Blank = Blank
data LineType = LineList ListType Text
| LineCode Text
| LineFenced Text FencedHandler -- ^ terminator, language
| LineBlockQuote Text
| LineHeading Int Text
| LineBlank
| LineText Text
| LineRule
| LineHtml Text
| LineReference Text Text -- ^ name, destination
lineType :: MarkdownSettings -> Text -> LineType
lineType ms t
| T.null $ T.strip t = LineBlank
| Just (term, fh) <- getFenced (Map.toList $ msFencedHandlers ms) t = LineFenced term fh
| Just t' <- T.stripPrefix "> " t = LineBlockQuote t'
| Just (level, t') <- stripHeading t = LineHeading level t'
| Just t' <- T.stripPrefix " " t = LineCode t'
| isRule t = LineRule
| isHtmlStart t = LineHtml t
| Just (ltype, t') <- listStart t = LineList ltype t'
| Just (name, dest) <- getReference t = LineReference name dest
| otherwise = LineText t
where
getFenced [] _ = Nothing
getFenced ((x, fh):xs) t'
| Just rest <- T.stripPrefix x t' = Just (x, fh $ T.strip rest)
| otherwise = getFenced xs t'
isRule :: Text -> Bool
isRule =
go . T.strip
where
go "* * *" = True
go "***" = True
go "*****" = True
go "- - -" = True
go "---" = True
go "___" = True
go "_ _ _" = True
go t' = T.length (T.takeWhile (== '-') t') >= 5
stripHeading :: Text -> Maybe (Int, Text)
stripHeading t'
| T.null x = Nothing
| otherwise = Just (T.length x, T.strip $ T.dropWhileEnd (== '#') y)
where
(x, y) = T.span (== '#') t'
getReference :: Text -> Maybe (Text, Text)
getReference a = do
b <- T.stripPrefix "[" $ T.dropWhile (== ' ') a
let (name, c) = T.break (== ']') b
d <- T.stripPrefix "]:" c
Just (name, T.strip d)
start :: Monad m => MarkdownSettings -> Text -> Conduit Text m (Either Blank (Block Text))
start ms t =
go $ lineType ms t
where
go LineBlank = yield $ Left Blank
go (LineFenced term fh) = do
(finished, ls) <- takeTillConsume (== term)
case finished of
Just _ -> do
let block =
case fh of
FHRaw fh' -> fh' $ T.intercalate "\n" ls
FHParsed fh' -> fh' $ runIdentity $ mapM_ yield ls $$ toBlocksLines ms =$ CL.consume
mapM_ (yield . Right) block
Nothing -> mapM_ leftover (reverse $ T.cons ' ' t : ls)
go (LineBlockQuote t') = do
ls <- takeQuotes =$= CL.consume
let blocks = runIdentity $ mapM_ yield (t' : ls) $$ toBlocksLines ms =$ CL.consume
yield $ Right $ BlockQuote blocks
go (LineHeading level t') = yield $ Right $ BlockHeading level t'
go (LineCode t') = do
ls <- getIndented 4 =$= CL.consume
yield $ Right $ BlockCode Nothing $ T.intercalate "\n" $ t' : ls
go LineRule = yield $ Right BlockRule
go (LineHtml t') = do
if t' `Set.member` msStandaloneHtml ms
then yield $ Right $ BlockHtml t'
else do
ls <- takeTill (T.null . T.strip) =$= CL.consume
yield $ Right $ BlockHtml $ T.intercalate "\n" $ t' : ls
go (LineList ltype t') = do
t2 <- CL.peek
case fmap (lineType ms) t2 of
-- If the next line is a non-indented text line, then we have a
-- lazy list.
Just (LineText t2') | T.null (T.takeWhile (== ' ') t2') -> do
CL.drop 1
-- Get all of the non-indented lines.
let loop front = do
x <- await
case x of
Nothing -> return $ front []
Just y ->
case lineType ms y of
LineText z -> loop (front . (z:))
_ -> leftover y >> return (front [])
ls <- loop (\rest -> T.dropWhile (== ' ') t' : t2' : rest)
yield $ Right $ BlockList ltype $ Right [BlockPara $ T.intercalate "\n" ls]
-- If the next line is an indented list, then we have a sublist. I
-- disagree with this interpretation of Markdown, but it's the way
-- that Github implements things, so we will too.
_ | Just t2' <- t2
, Just t2'' <- T.stripPrefix " " t2'
, LineList _ltype' _t2''' <- lineType ms t2'' -> do
ls <- getIndented 4 =$= CL.consume
let blocks = runIdentity $ mapM_ yield ls $$ toBlocksLines ms =$ CL.consume
let addPlainText
| T.null $ T.strip t' = id
| otherwise = (BlockPlainText (T.strip t'):)
yield $ Right $ BlockList ltype $ Right $ addPlainText blocks
_ -> do
let t'' = T.dropWhile (== ' ') t'
let leader = T.length t - T.length t''
ls <- getIndented leader =$= CL.consume
let blocks = runIdentity $ mapM_ yield (t'' : ls) $$ toBlocksLines ms =$ CL.consume
yield $ Right $ BlockList ltype $ Right blocks
go (LineReference x y) = yield $ Right $ BlockReference x y
go (LineText t') = do
-- Check for underline headings
let getUnderline :: Text -> Maybe Int
getUnderline s
| T.length s < 2 = Nothing
| T.all (== '=') s = Just 1
| T.all (== '-') s = Just 2
| otherwise = Nothing
t2 <- CL.peek
case t2 >>= getUnderline of
Just level -> do
CL.drop 1
yield $ Right $ BlockHeading level t'
Nothing -> do
let listStartIndent x =
case listStart x of
Just (_, y) -> T.take 2 y == " "
Nothing -> False
isNonPara LineBlank = True
isNonPara LineFenced{} = True
isNonPara LineBlockQuote{} = not $ msBlankBeforeBlockquote ms
isNonPara LineHtml{} = True -- See example 95 in Common Markdown spec
isNonPara _ = False
(mfinal, ls) <- takeTillConsume (\x -> isNonPara (lineType ms x) || listStartIndent x)
maybe (return ()) leftover mfinal
yield $ Right $ BlockPara $ T.intercalate "\n" $ t' : ls
isHtmlStart :: T.Text -> Bool
-- Allow for up to three spaces before the opening tag.
isHtmlStart t | " " `T.isPrefixOf` t = False
isHtmlStart t =
case T.stripPrefix "<" $ T.dropWhile (== ' ') t of
Nothing -> False
Just t' ->
let (name, rest)
| Just _ <- T.stripPrefix "!--" t' = ("--", t')
| otherwise = T.break (\c -> c == ' ' || c == '>') t'
in (T.all isValidTagName name &&
not (T.null name) &&
(not ("/" `T.isPrefixOf` rest) || ("/>" `T.isPrefixOf` rest)))
|| isPI t' || isCommentCData t'
where
isValidTagName :: Char -> Bool
isValidTagName c =
('A' <= c && c <= 'Z') ||
('a' <= c && c <= 'z') ||
('0' <= c && c <= '9') ||
(c == '-') ||
(c == '_') ||
(c == '/') ||
(c == '!')
isPI = ("?" `T.isPrefixOf`)
isCommentCData = ("!" `T.isPrefixOf`)
takeTill :: Monad m => (i -> Bool) -> Conduit i m i
takeTill f =
loop
where
loop = await >>= maybe (return ()) (\x -> if f x then return () else yield x >> loop)
--takeTillConsume :: Monad m => (i -> Bool) -> Consumer i m (Maybe i, [i])
takeTillConsume f =
loop id
where
loop front = await >>= maybe
(return (Nothing, front []))
(\x ->
if f x
then return (Just x, front [])
else loop (front . (x:))
)
listStart :: Text -> Maybe (ListType, Text)
listStart t0
| Just t' <- stripUnorderedListSeparator t = Just (Unordered, t')
| Just t' <- stripNumber t, Just t'' <- stripOrderedListSeparator t' = Just (Ordered, t'')
| otherwise = Nothing
where
t = T.stripStart t0
stripNumber :: Text -> Maybe Text
stripNumber x
| T.null y = Nothing
| otherwise = Just z
where
(y, z) = T.span isDigit x
stripUnorderedListSeparator :: Text -> Maybe Text
stripUnorderedListSeparator =
stripPrefixChoice ["* ", "*\t", "+ ", "+\t", "- ", "-\t"]
stripOrderedListSeparator :: Text -> Maybe Text
stripOrderedListSeparator =
stripPrefixChoice [". ", ".\t", ") ", ")\t"]
-- | Attempt to strip each of the prefixes in @xs@ from the start of @x@. As
-- soon as one matches, return the remainder of @x@. Prefixes are tried in
-- order. If none match, return @Nothing@.
stripPrefixChoice :: [Text] -> Text -> Maybe Text
stripPrefixChoice xs x = msum $ map (flip T.stripPrefix x) xs
getIndented :: Monad m => Int -> Conduit Text m Text
getIndented leader =
go []
where
go blanks = await >>= maybe (mapM_ leftover blanks) (go' blanks)
go' blanks t
| T.null $ T.strip t = go (T.drop leader t : blanks)
| T.length x == leader && T.null (T.strip x) = do
mapM_ yield $ reverse blanks
yield y
go []
| otherwise = mapM_ leftover (t:blanks)
where
(x, y) = T.splitAt leader t
takeQuotes :: Monad m => Conduit Text m Text
takeQuotes =
await >>= maybe (return ()) go
where
go "" = return ()
go ">" = yield "" >> takeQuotes
go t
| Just t' <- T.stripPrefix "> " t = yield t' >> takeQuotes
| otherwise = yield t >> takeQuotes
markdown-0.1.16/Text/Markdown/Inline.hs 0000644 0000000 0000000 00000017150 13014511122 016061 0 ustar 00 0000000 0000000 {-# LANGUAGE OverloadedStrings #-}
{-# OPTIONS_HADDOCK hide #-}
module Text.Markdown.Inline
( Inline (..)
, inlineParser
, toInline
) where
import Prelude hiding (takeWhile)
import Data.Text (Text)
import qualified Data.Text as T
import Data.Attoparsec.Text
import Control.Applicative
import Data.Monoid (Monoid, mappend)
import qualified Data.Map as Map
import Text.Markdown.Types (Inline(..))
import Data.XML.Types (Content (..))
import Text.XML.Stream.Parse (decodeHtmlEntities)
type RefMap = Map.Map Text Text
toInline :: RefMap -> Text -> [Inline]
toInline refmap t =
case parseOnly (inlineParser refmap) t of
Left s -> [InlineText $ T.pack s]
Right is -> is
(<>) :: Monoid m => m -> m -> m
(<>) = mappend
inlineParser :: RefMap -> Parser [Inline]
inlineParser = fmap combine . many . inlineAny
combine :: [Inline] -> [Inline]
combine [] = []
combine (InlineText x:InlineText y:rest) = combine (InlineText (x <> y):rest)
combine (InlineText x:rest) = InlineText x : combine rest
combine (InlineItalic x:InlineItalic y:rest) = combine (InlineItalic (x <> y):rest)
combine (InlineItalic x:rest) = InlineItalic (combine x) : combine rest
combine (InlineBold x:InlineBold y:rest) = combine (InlineBold (x <> y):rest)
combine (InlineBold x:rest) = InlineBold (combine x) : combine rest
combine (InlineCode x:InlineCode y:rest) = combine (InlineCode (x <> y):rest)
combine (InlineCode x:rest) = InlineCode x : combine rest
combine (InlineLink u t c:rest) = InlineLink u t (combine c) : combine rest
combine (InlineImage u t c:rest) = InlineImage u t c : combine rest
combine (InlineHtml t:rest) = InlineHtml t : combine rest
combine (InlineFootnote x:rest) = InlineFootnote x : combine rest
combine (InlineFootnoteRef x:rest) = InlineFootnoteRef x : combine rest
specials :: [Char]
specials = "*_`\\[]!<&{}"
inlineAny :: RefMap -> Parser Inline
inlineAny refs =
inline refs <|> special
where
special = InlineText . T.singleton <$> satisfy (`elem` specials)
inline :: RefMap -> Parser Inline
inline refs =
text
<|> escape
<|> footnote
<|> footnoteRef
<|> paired "**" InlineBold <|> paired "__" InlineBold
<|> paired "*" InlineItalic <|> paired "_" InlineItalic
<|> doubleCodeSpace <|> doubleCode <|> code
<|> link
<|> image
<|> autoLink
<|> html
<|> entity
where
inlinesTill :: Text -> Parser [Inline]
inlinesTill end =
go id
where
go front =
(string end *> pure (front []))
<|> (do
x <- inlineAny refs
go $ front . (x:))
text = InlineText <$> takeWhile1 (`notElem` specials)
paired t wrap = wrap <$> do
_ <- string t
is <- inlinesTill t
if null is then fail "wrapped around something missing" else return is
doubleCodeSpace = InlineCode . T.pack <$> (string "`` " *> manyTill anyChar (string " ``"))
doubleCode = InlineCode . T.pack <$> (string "``" *> manyTill anyChar (string "``"))
code = InlineCode <$> (char '`' *> takeWhile1 (/= '`') <* char '`')
footnoteRef = InlineFootnoteRef <$> (char '{' *> decimal <* char '}')
footnote = InlineFootnote <$> (string "{^" *> decimal <* char '}')
escape = InlineText . T.singleton <$>
(char '\\' *> satisfy (`elem` ("\\`*_{}[]()#+-.!>" :: String)))
takeBalancedBrackets =
T.pack <$> go (0 :: Int)
where
go i = do
c <- anyChar
case c of
'[' -> (c:) <$> go (i + 1)
']'
| i == 0 -> return []
| otherwise -> (c:) <$> go (i - 1)
_ -> (c:) <$> go i
parseUrl = fixUrl . T.pack <$> parseUrl' (0 :: Int)
parseUrl' level
| level > 0 = do
c <- anyChar
let level'
| c == ')' = level - 1
| otherwise = level
c' <-
if c == '\\'
then anyChar
else return c
cs <- parseUrl' level'
return $ c' : cs
| otherwise = (do
c <- hrefChar
if c == '('
then (c:) <$> parseUrl' 1
else (c:) <$> parseUrl' 0) <|> return []
parseUrlTitle defRef = parseUrlTitleInline <|> parseUrlTitleRef defRef
parseUrlTitleInside endTitle = do
url <- parseUrl
mtitle <- (Just <$> title) <|> (skipSpace >> endTitle >> pure Nothing)
return (url, mtitle)
where
title = do
_ <- space
skipSpace
_ <- char '"'
t <- T.stripEnd . T.pack <$> go
return $
if not (T.null t) && T.last t == '"'
then T.init t
else t
where
go = (char '\\' *> anyChar >>= \c -> (c:) <$> go)
<|> (endTitle *> return [])
<|> (anyChar >>= \c -> (c:) <$> go)
parseUrlTitleInline = char '(' *> parseUrlTitleInside (char ')')
parseUrlTitleRef defRef = do
ref' <- (skipSpace *> char '[' *> takeWhile (/= ']') <* char ']') <|> return ""
let ref = if T.null ref' then defRef else ref'
case Map.lookup (T.unwords $ T.words ref) refs of
Nothing -> fail "ref not found"
Just t -> either fail return $ parseOnly (parseUrlTitleInside endOfInput) t
link = do
_ <- char '['
rawContent <- takeBalancedBrackets
content <- either fail return $ parseOnly (inlineParser refs) rawContent
(url, mtitle) <- parseUrlTitle rawContent
return $ InlineLink url mtitle content
image = do
_ <- string "!["
content <- takeBalancedBrackets
(url, mtitle) <- parseUrlTitle content
return $ InlineImage url mtitle content
fixUrl t
| T.length t > 2 && T.head t == '<' && T.last t == '>' = T.init $ T.tail t
| otherwise = t
autoLink = do
_ <- char '<'
a <- string "http:" <|> string "https:"
b <- takeWhile1 (/= '>')
_ <- char '>'
let url = a `T.append` b
return $ InlineLink url Nothing [InlineText url]
html = do
c <- char '<'
t <- takeWhile1 (\x -> ('A' <= x && x <= 'Z') || ('a' <= x && x <= 'z') || x == '/')
if T.null t
then fail "invalid tag"
else do
t2 <- takeWhile (/= '>')
c2 <- char '>'
return $ InlineHtml $ T.concat
[ T.singleton c
, t
, t2
, T.singleton c2
]
entity =
rawent "<"
<|> rawent ">"
<|> rawent "&"
<|> rawent """
<|> rawent "'"
<|> decEnt
<|> hexEnt
<|> namedEnt
rawent t = InlineHtml <$> string t
decEnt = do
s <- string "&#"
t <- takeWhile1 $ \x -> ('0' <= x && x <= '9')
c <- char ';'
return $ InlineHtml $ T.concat
[ s
, t
, T.singleton c
]
hexEnt = do
s <- string "&#x" <|> string "&#X"
t <- takeWhile1 $ \x -> ('0' <= x && x <= '9') || ('A' <= x && x <= 'F') || ('a' <= x && x <= 'f')
c <- char ';'
return $ InlineHtml $ T.concat
[ s
, t
, T.singleton c
]
namedEnt = do
_s <- char '&'
t <- takeWhile1 (/= ';')
_c <- char ';'
case decodeHtmlEntities t of
ContentText t' -> return $ InlineHtml t'
ContentEntity _ -> fail "Unknown named entity"
hrefChar :: Parser Char
hrefChar = (char '\\' *> anyChar) <|> satisfy (notInClass " )")
markdown-0.1.16/Text/Markdown/Types.hs 0000644 0000000 0000000 00000016605 13014511122 015753 0 ustar 00 0000000 0000000 {-# LANGUAGE OverloadedStrings #-}
module Text.Markdown.Types where
import Data.Text (Text)
import qualified Data.Text as T
import Data.Default (Default (def))
import Data.Set (Set, empty)
import Data.Map (Map, singleton)
import Data.Monoid (mappend)
import Text.Blaze.Html (Html)
import qualified Text.Blaze.Html5 as H
import qualified Text.Blaze.Html5.Attributes as HA
-- | A settings type providing various configuration options.
--
-- See
main = putStrLn "Hello world!"