` 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: 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.
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 alt
attribute text for the image;
followed by a set of parentheses, containing the URL or path to
the image, and an optional title attribute 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
foo
bar
foo
]]
markdown_ordered_and_unordered_lists = [[
## 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:
1. First
2. Second
3. Third
and:
1. One
2. Two
3. Three
Loose using tabs:
1. First
2. Second
3. Third
and using spaces:
1. One
2. Two
3. Three
Multiple paragraphs:
1. Item 1, graf one.
Item 2. graf two. The quick brown fox jumped over the lazy dog's
back.
2. Item 2.
3. Item 3.
## Nested
* Tab
* Tab
* Tab
Here's another:
1. First
2. Second:
* Fee
* Fie
* Foe
3. Third
Same thing but with paragraphs:
1. First
2. Second:
* Fee
* Fie
* Foe
3. Third
~
Unordered
Asterisks tight:
asterisk 1
asterisk 2
asterisk 3
Asterisks loose:
asterisk 1
asterisk 2
asterisk 3
Pluses tight:
Pluses loose:
Minuses tight:
Minuses loose:
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
Here's another:
First
Second:
Third
Same thing but with paragraphs:
First
Second:
Third
]]
markdown_strong_and_em_together = [[
***This is strong and em.***
So is ***this*** word.
___This is strong and em.___
So is ___this___ word.
~
This is strong and em.
So is this
This is strong and em.
So is this
]]
markdown_tabs = [[
+ this 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
~
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
A list within a blockquote:
asterisk 1
asterisk 2
asterisk 3
]]
bug_from_paul_chiusano_gmail_com = [[
[context-free grammar][CFG]
[notated][BNF]
[unrestricted grammar][]
[CFG]:
[BNF]:
[unrestricted grammar]:
~
context-free grammar notated unrestricted grammar
]]
setfenv(1, _G)
-- Test running function
local function run_tests()
-- Are s1 and s2 equal except for whitespace issues.
local function nonspace_equal(s1, s2)
s1 = s1:gsub("[ \t\n\r]", "")
s2 = s2:gsub("[ \t\n\r]", "")
return s1 == s2
end
-- Runs a single test
local function run_single_test(name, source, desired)
local result = markdown(source)
local res = nonspace_equal(result, desired)
if not res then
print("********** TEST FAILED **********")
print(name)
print("----- Input:")
print(source)
print("----- Expected output:")
print(desired)
print("----- Actual output:")
print(result)
print("*********************************")
print()
end
return res
end
-- Runs a specified test battery
local function run_test(name, code)
local failed, succeeded = 0,0
local data = split(code, "\n~[ \t]*\n")
for i = 1, #data, 2 do
if run_single_test(name, data[i], data[i+1]) then
succeeded = succeeded + 1
else
failed = failed + 1
end
end
print(string.format("%-20s %15s %5i %15s %5i", name, "Succeeded:", succeeded, "Failed:", failed))
end
for _,k in ipairs(TESTS._indices) do
run_test(k,TESTS[k])
end
end
run_tests() markdown-0.32/markdown.lua 0000644 0001750 0001750 00000120132 11020272623 014627 0 ustar tassi tassi #!/usr/bin/env lua
--[[
# markdown.lua -- version 0.32
**Author:** Niklas Frykholm,
**Date:** 31 May 2008
This is an implementation of the popular text markup language Markdown in pure Lua.
Markdown can convert documents written in a simple and easy to read text format
to well-formatted HTML. For a more thourough description of Markdown and the Markdown
syntax, see .
The original Markdown source is written in Perl and makes heavy use of advanced
regular expression techniques (such as negative look-ahead, etc) which are not available
in Lua's simple regex engine. Therefore this Lua port has been rewritten from the ground
up. It is probably not completely bug free. If you notice any bugs, please report them to
me. A unit test that exposes the error is helpful.
## Usage
require "markdown"
markdown(source)
``markdown.lua`` exposes a single global function named ``markdown(s)`` which applies the
Markdown transformation to the specified string.
``markdown.lua`` can also be used directly from the command line:
lua markdown.lua test.md
Creates a file ``test.html`` with the converted content of ``test.md``. Run:
lua markdown.lua -h
For a description of the command-line options.
``markdown.lua`` uses the same license as Lua, the MIT license.
## License
Copyright © 2008 Niklas Frykholm.
Permission is hereby granted, free of charge, to any person obtaining a copy of this
software and associated documentation files (the "Software"), to deal in the Software
without restriction, including without limitation the rights to use, copy, modify, merge,
publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons
to whom the Software is furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all copies
or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
THE SOFTWARE.
## Version history
- **0.32** -- 31 May 2008
- Fix for links containing brackets
- **0.31** -- 1 Mar 2008
- Fix for link definitions followed by spaces
- **0.30** -- 25 Feb 2008
- Consistent behavior with Markdown when the same link reference is reused
- **0.29** -- 24 Feb 2008
- Fix for blocks with spaces in them
- **0.28** -- 18 Feb 2008
- Fix for link encoding
- **0.27** -- 14 Feb 2008
- Fix for link database links with ()
- **0.26** -- 06 Feb 2008
- Fix for nested italic and bold markers
- **0.25** -- 24 Jan 2008
- Fix for encoding of naked <
- **0.24** -- 21 Jan 2008
- Fix for link behavior.
- **0.23** -- 10 Jan 2008
- Fix for a regression bug in longer expressions in italic or bold.
- **0.22** -- 27 Dec 2007
- Fix for crash when processing blocks with a percent sign in them.
- **0.21** -- 27 Dec 2007
- Fix for combined strong and emphasis tags
- **0.20** -- 13 Oct 2007
- Fix for < as well in image titles, now matches Dingus behavior
- **0.19** -- 28 Sep 2007
- Fix for quotation marks " and ampersands & in link and image titles.
- **0.18** -- 28 Jul 2007
- Does not crash on unmatched tags (behaves like standard markdown)
- **0.17** -- 12 Apr 2007
- Fix for links with %20 in them.
- **0.16** -- 12 Apr 2007
- Do not require arg global to exist.
- **0.15** -- 28 Aug 2006
- Better handling of links with underscores in them.
- **0.14** -- 22 Aug 2006
- Bug for *`foo()`*
- **0.13** -- 12 Aug 2006
- Added -l option for including stylesheet inline in document.
- Fixed bug in -s flag.
- Fixed emphasis bug.
- **0.12** -- 15 May 2006
- Fixed several bugs to comply with MarkdownTest 1.0
- **0.11** -- 12 May 2006
- Fixed bug for escaping `*` and `_` inside code spans.
- Added license terms.
- Changed join() to table.concat().
- **0.10** -- 3 May 2006
- Initial public release.
// Niklas
]]
-- Set up a table for holding local functions to avoid polluting the global namespace
local M = {}
local MT = {__index = _G}
setmetatable(M, MT)
setfenv(1, M)
----------------------------------------------------------------------
-- Utility functions
----------------------------------------------------------------------
-- Locks table t from changes, writes an error if someone attempts to change the table.
-- This is useful for detecting variables that have "accidently" been made global. Something
-- I tend to do all too much.
function lock(t)
function lock_new_index(t, k, v)
error("module has been locked -- " .. k .. " must be declared local", 2)
end
local mt = {__newindex = lock_new_index}
if getmetatable(t) then mt.__index = getmetatable(t).__index end
setmetatable(t, mt)
end
-- Returns the result of mapping the values in table t through the function f
function map(t, f)
local out = {}
for k,v in pairs(t) do out[k] = f(v,k) end
return out
end
-- The identity function, useful as a placeholder.
function identity(text) return text end
-- Functional style if statement. (NOTE: no short circuit evaluation)
function iff(t, a, b) if t then return a else return b end end
-- Splits the text into an array of separate lines.
function split(text, sep)
sep = sep or "\n"
local lines = {}
local pos = 1
while true do
local b,e = text:find(sep, pos)
if not b then table.insert(lines, text:sub(pos)) break end
table.insert(lines, text:sub(pos, b-1))
pos = e + 1
end
return lines
end
-- Converts tabs to spaces
function detab(text)
local tab_width = 4
local function rep(match)
local spaces = -match:len()
while spaces<1 do spaces = spaces + tab_width end
return match .. string.rep(" ", spaces)
end
text = text:gsub("([^\n]-)\t", rep)
return text
end
-- Applies string.find for every pattern in the list and returns the first match
function find_first(s, patterns, index)
local res = {}
for _,p in ipairs(patterns) do
local match = {s:find(p, index)}
if #match>0 and (#res==0 or match[1] < res[1]) then res = match end
end
return unpack(res)
end
-- If a replacement array is specified, the range [start, stop] in the array is replaced
-- with the replacement array and the resulting array is returned. Without a replacement
-- array the section of the array between start and stop is returned.
function splice(array, start, stop, replacement)
if replacement then
local n = stop - start + 1
while n > 0 do
table.remove(array, start)
n = n - 1
end
for i,v in ipairs(replacement) do
table.insert(array, start, v)
end
return array
else
local res = {}
for i = start,stop do
table.insert(res, array[i])
end
return res
end
end
-- Outdents the text one step.
function outdent(text)
text = "\n" .. text
text = text:gsub("\n ? ? ?", "\n")
text = text:sub(2)
return text
end
-- Indents the text one step.
function indent(text)
text = text:gsub("\n", "\n ")
return text
end
-- Does a simple tokenization of html data. Returns the data as a list of tokens.
-- Each token is a table with a type field (which is either "tag" or "text") and
-- a text field (which contains the original token data).
function tokenize_html(html)
local tokens = {}
local pos = 1
while true do
local start = find_first(html, {"", start)
elseif html:match("^<%?", start) then
_,stop = html:find("?>", start)
else
_,stop = html:find("%b<>", start)
end
if not stop then
-- error("Could not match html tag " .. html:sub(start,start+30))
table.insert(tokens, {type="text", text=html:sub(start, start)})
pos = start + 1
else
table.insert(tokens, {type="tag", text=html:sub(start, stop)})
pos = stop + 1
end
end
return tokens
end
----------------------------------------------------------------------
-- Hash
----------------------------------------------------------------------
-- This is used to "hash" data into alphanumeric strings that are unique
-- in the document. (Note that this is not cryptographic hash, the hash
-- function is not one-way.) The hash procedure is used to protect parts
-- of the document from further processing.
local HASH = {
-- Has the hash been inited.
inited = false,
-- The unique string prepended to all hash values. This is to ensure
-- that hash values do not accidently coincide with an actual existing
-- string in the document.
identifier = "",
-- Counter that counts up for each new hash instance.
counter = 0,
-- Hash table.
table = {}
}
-- Inits hashing. Creates a hash_identifier that doesn't occur anywhere
-- in the text.
function init_hash(text)
HASH.inited = true
HASH.identifier = ""
HASH.counter = 0
HASH.table = {}
local s = "HASH"
local counter = 0
local id
while true do
id = s .. counter
if not text:find(id, 1, true) then break end
counter = counter + 1
end
HASH.identifier = id
end
-- Returns the hashed value for s.
function hash(s)
assert(HASH.inited)
if not HASH.table[s] then
HASH.counter = HASH.counter + 1
local id = HASH.identifier .. HASH.counter .. "X"
HASH.table[s] = id
end
return HASH.table[s]
end
----------------------------------------------------------------------
-- Protection
----------------------------------------------------------------------
-- The protection module is used to "protect" parts of a document
-- so that they are not modified by subsequent processing steps.
-- Protected parts are saved in a table for later unprotection
-- Protection data
local PD = {
-- Saved blocks that have been converted
blocks = {},
-- Block level tags that will be protected
tags = {"p", "div", "h1", "h2", "h3", "h4", "h5", "h6", "blockquote",
"pre", "table", "dl", "ol", "ul", "script", "noscript", "form", "fieldset",
"iframe", "math", "ins", "del"}
}
-- Pattern for matching a block tag that begins and ends in the leftmost
-- column and may contain indented subtags, i.e.
--
-- A nested block.
--
-- Nested data.
--
--
]->[ \t]*\n"})
text = protect_matches(text, {"\n[ \t]*\n"})
return text
end
-- Returns true if the string s is a hash resulting from protection
function is_protected(s)
return PD.blocks[s]
end
-- Unprotects the specified text by expanding all the nonces
function unprotect(text)
for k,v in pairs(PD.blocks) do
v = v:gsub("%%", "%%%%")
text = text:gsub(k, v)
end
return text
end
----------------------------------------------------------------------
-- Block transform
----------------------------------------------------------------------
-- The block transform functions transform the text on the block level.
-- They work with the text as an array of lines rather than as individual
-- characters.
-- Returns true if the line is a ruler of (char) characters.
-- The line must contain at least three char characters and contain only spaces and
-- char characters.
function is_ruler_of(line, char)
if not line:match("^[ %" .. char .. "]*$") then return false end
if not line:match("%" .. char .. ".*%" .. char .. ".*%" .. char) then return false end
return true
end
-- Identifies the block level formatting present in the line
function classify(line)
local info = {line = line, text = line}
if line:match("^ ") then
info.type = "indented"
info.outdented = line:sub(5)
return info
end
for _,c in ipairs({'*', '-', '_', '='}) do
if is_ruler_of(line, c) then
info.type = "ruler"
info.ruler_char = c
return info
end
end
if line == "" then
info.type = "blank"
return info
end
if line:match("^(#+)[ \t]*(.-)[ \t]*#*[ \t]*$") then
local m1, m2 = line:match("^(#+)[ \t]*(.-)[ \t]*#*[ \t]*$")
info.type = "header"
info.level = m1:len()
info.text = m2
return info
end
if line:match("^ ? ? ?(%d+)%.[ \t]+(.+)") then
local number, text = line:match("^ ? ? ?(%d+)%.[ \t]+(.+)")
info.type = "list_item"
info.list_type = "numeric"
info.number = 0 + number
info.text = text
return info
end
if line:match("^ ? ? ?([%*%+%-])[ \t]+(.+)") then
local bullet, text = line:match("^ ? ? ?([%*%+%-])[ \t]+(.+)")
info.type = "list_item"
info.list_type = "bullet"
info.bullet = bullet
info.text= text
return info
end
if line:match("^>[ \t]?(.*)") then
info.type = "blockquote"
info.text = line:match("^>[ \t]?(.*)")
return info
end
if is_protected(line) then
info.type = "raw"
info.html = unprotect(line)
return info
end
info.type = "normal"
return info
end
-- Find headers constisting of a normal line followed by a ruler and converts them to
-- header entries.
function headers(array)
local i = 1
while i <= #array - 1 do
if array[i].type == "normal" and array[i+1].type == "ruler" and
(array[i+1].ruler_char == "-" or array[i+1].ruler_char == "=") then
local info = {line = array[i].line}
info.text = info.line
info.type = "header"
info.level = iff(array[i+1].ruler_char == "=", 1, 2)
table.remove(array, i+1)
array[i] = info
end
i = i + 1
end
return array
end
-- Find list blocks and convert them to protected data blocks
function lists(array, sublist)
local function process_list(arr)
local function any_blanks(arr)
for i = 1, #arr do
if arr[i].type == "blank" then return true end
end
return false
end
local function split_list_items(arr)
local acc = {arr[1]}
local res = {}
for i=2,#arr do
if arr[i].type == "list_item" then
table.insert(res, acc)
acc = {arr[i]}
else
table.insert(acc, arr[i])
end
end
table.insert(res, acc)
return res
end
local function process_list_item(lines, block)
while lines[#lines].type == "blank" do
table.remove(lines)
end
local itemtext = lines[1].text
for i=2,#lines do
itemtext = itemtext .. "\n" .. outdent(lines[i].line)
end
if block then
itemtext = block_transform(itemtext, true)
if not itemtext:find("") then itemtext = indent(itemtext) end
return " " .. itemtext .. " "
else
local lines = split(itemtext)
lines = map(lines, classify)
lines = lists(lines, true)
lines = blocks_to_html(lines, true)
itemtext = table.concat(lines, "\n")
if not itemtext:find("") then itemtext = indent(itemtext) end
return " " .. itemtext .. " "
end
end
local block_list = any_blanks(arr)
local items = split_list_items(arr)
local out = ""
for _, item in ipairs(items) do
out = out .. process_list_item(item, block_list) .. "\n"
end
if arr[1].list_type == "numeric" then
return "\n" .. out .. " "
else
return ""
end
end
-- Finds the range of lines composing the first list in the array. A list
-- starts with (^ list_item) or (blank list_item) and ends with
-- (blank* $) or (blank normal).
--
-- A sublist can start with just (list_item) does not need a blank...
local function find_list(array, sublist)
local function find_list_start(array, sublist)
if array[1].type == "list_item" then return 1 end
if sublist then
for i = 1,#array do
if array[i].type == "list_item" then return i end
end
else
for i = 1, #array-1 do
if array[i].type == "blank" and array[i+1].type == "list_item" then
return i+1
end
end
end
return nil
end
local function find_list_end(array, start)
local pos = #array
for i = start, #array-1 do
if array[i].type == "blank" and array[i+1].type ~= "list_item"
and array[i+1].type ~= "indented" and array[i+1].type ~= "blank" then
pos = i-1
break
end
end
while pos > start and array[pos].type == "blank" do
pos = pos - 1
end
return pos
end
local start = find_list_start(array, sublist)
if not start then return nil end
return start, find_list_end(array, start)
end
while true do
local start, stop = find_list(array, sublist)
if not start then break end
local text = process_list(splice(array, start, stop))
local info = {
line = text,
type = "raw",
html = text
}
array = splice(array, start, stop, {info})
end
-- Convert any remaining list items to normal
for _,line in ipairs(array) do
if line.type == "list_item" then line.type = "normal" end
end
return array
end
-- Find and convert blockquote markers.
function blockquotes(lines)
local function find_blockquote(lines)
local start
for i,line in ipairs(lines) do
if line.type == "blockquote" then
start = i
break
end
end
if not start then return nil end
local stop = #lines
for i = start+1, #lines do
if lines[i].type == "blank" or lines[i].type == "blockquote" then
elseif lines[i].type == "normal" then
if lines[i-1].type == "blank" then stop = i-1 break end
else
stop = i-1 break
end
end
while lines[stop].type == "blank" do stop = stop - 1 end
return start, stop
end
local function process_blockquote(lines)
local raw = lines[1].text
for i = 2,#lines do
raw = raw .. "\n" .. lines[i].text
end
local bt = block_transform(raw)
if not bt:find("") then bt = indent(bt) end
return "\n " .. bt ..
"\n "
end
while true do
local start, stop = find_blockquote(lines)
if not start then break end
local text = process_blockquote(splice(lines, start, stop))
local info = {
line = text,
type = "raw",
html = text
}
lines = splice(lines, start, stop, {info})
end
return lines
end
-- Find and convert codeblocks.
function codeblocks(lines)
local function find_codeblock(lines)
local start
for i,line in ipairs(lines) do
if line.type == "indented" then start = i break end
end
if not start then return nil end
local stop = #lines
for i = start+1, #lines do
if lines[i].type ~= "indented" and lines[i].type ~= "blank" then
stop = i-1
break
end
end
while lines[stop].type == "blank" do stop = stop - 1 end
return start, stop
end
local function process_codeblock(lines)
local raw = detab(encode_code(outdent(lines[1].line)))
for i = 2,#lines do
raw = raw .. "\n" .. detab(encode_code(outdent(lines[i].line)))
end
return "" .. raw .. "\n" .. span_transform(s) .. "
")
end
elseif line.type == "header" then
local s = "" .. span_transform(line.text) .. " "
table.insert(out, s)
else
table.insert(out, line.line)
end
i = i + 1
end
return out
end
-- Perform all the block level transforms
function block_transform(text, sublist)
local lines = split(text)
lines = map(lines, classify)
lines = headers(lines)
lines = lists(lines, sublist)
lines = codeblocks(lines)
lines = blockquotes(lines)
lines = blocks_to_html(lines)
local text = table.concat(lines, "\n")
return text
end
-- Debug function for printing a line array to see the result
-- of partial transforms.
function print_lines(lines)
for i, line in ipairs(lines) do
print(i, line.type, line.text or line.line)
end
end
----------------------------------------------------------------------
-- Span transform
----------------------------------------------------------------------
-- Functions for transforming the text at the span level.
-- These characters may need to be escaped because they have a special
-- meaning in markdown.
escape_chars = "'\\`*_{}[]()>#+-.!'"
escape_table = {}
function init_escape_table()
escape_table = {}
for i = 1,#escape_chars do
local c = escape_chars:sub(i,i)
escape_table[c] = hash(c)
end
end
-- Adds a new escape to the escape table.
function add_escape(text)
if not escape_table[text] then
escape_table[text] = hash(text)
end
return escape_table[text]
end
-- Escape characters that should not be disturbed by markdown.
function escape_special_chars(text)
local tokens = tokenize_html(text)
local out = ""
for _, token in ipairs(tokens) do
local t = token.text
if token.type == "tag" then
-- In tags, encode * and _ so they don't conflict with their use in markdown.
t = t:gsub("%*", escape_table["*"])
t = t:gsub("%_", escape_table["_"])
else
t = encode_backslash_escapes(t)
end
out = out .. t
end
return out
end
-- Encode backspace-escaped characters in the markdown source.
function encode_backslash_escapes(t)
for i=1,escape_chars:len() do
local c = escape_chars:sub(i,i)
t = t:gsub("\\%" .. c, escape_table[c])
end
return t
end
-- Unescape characters that have been encoded.
function unescape_special_chars(t)
local tin = t
for k,v in pairs(escape_table) do
k = k:gsub("%%", "%%%%")
t = t:gsub(v,k)
end
if t ~= tin then t = unescape_special_chars(t) end
return t
end
-- Encode/escape certain characters inside Markdown code runs.
-- The point is that in code, these characters are literals,
-- and lose their special Markdown meanings.
function encode_code(s)
s = s:gsub("%&", "&")
s = s:gsub("<", "<")
s = s:gsub(">", ">")
for k,v in pairs(escape_table) do
s = s:gsub("%"..k, v)
end
return s
end
-- Handle backtick blocks.
function code_spans(s)
s = s:gsub("\\\\", escape_table["\\"])
s = s:gsub("\\`", escape_table["`"])
local pos = 1
while true do
local start, stop = s:find("`+", pos)
if not start then return s end
local count = stop - start + 1
-- Find a matching numbert of backticks
local estart, estop = s:find(string.rep("`", count), stop+1)
local brstart = s:find("\n", stop+1)
if estart and (not brstart or estart < brstart) then
local code = s:sub(stop+1, estart-1)
code = code:gsub("^[ \t]+", "")
code = code:gsub("[ \t]+$", "")
code = code:gsub(escape_table["\\"], escape_table["\\"] .. escape_table["\\"])
code = code:gsub(escape_table["`"], escape_table["\\"] .. escape_table["`"])
code = "" .. encode_code(code) .. ""
code = add_escape(code)
s = s:sub(1, start-1) .. code .. s:sub(estop+1)
pos = start + code:len()
else
pos = stop + 1
end
end
return s
end
-- Encode alt text... enodes &, and ".
function encode_alt(s)
if not s then return s end
s = s:gsub('&', '&')
s = s:gsub('"', '"')
s = s:gsub('<', '<')
return s
end
-- Handle image references
function images(text)
local function reference_link(alt, id)
alt = encode_alt(alt:match("%b[]"):sub(2,-2))
id = id:match("%[(.*)%]"):lower()
if id == "" then id = text:lower() end
link_database[id] = link_database[id] or {}
if not link_database[id].url then return nil end
local url = link_database[id].url or id
url = encode_alt(url)
local title = encode_alt(link_database[id].title)
if title then title = " title=\"" .. title .. "\"" else title = "" end
return add_escape ('") .. text .. add_escape(" ")
end
local function inline_link(text, link)
text = text:match("%b[]"):sub(2,-2)
local url, title = link:match("%(?[ \t]*['\"](.+)['\"]")
title = encode_alt(title)
url = url or link:match("%(?%)") or ""
url = encode_alt(url)
if title then
return add_escape("") .. text .. " "
else
return add_escape("") .. text .. add_escape(" ")
end
end
text = text:gsub("(%b[])[ \t]*\n?[ \t]*(%b[])", reference_link)
text = text:gsub("(%b[])(%b())", inline_link)
return text
end
-- Handle auto links, i.e. ") .. s .. " "
end
-- Encode chars as a mix of dec and hex entitites to (perhaps) fool
-- spambots.
local function encode_email_address(s)
-- Use a deterministic encoding to make unit testing possible.
-- Code 45% hex, 45% dec, 10% plain.
local hex = {code = function(c) return "&#x" .. string.format("%x", c:byte()) .. ";" end, count = 1, rate = 0.45}
local dec = {code = function(c) return "&#" .. c:byte() .. ";" end, count = 0, rate = 0.45}
local plain = {code = function(c) return c end, count = 0, rate = 0.1}
local codes = {hex, dec, plain}
local function swap(t,k1,k2) local temp = t[k2] t[k2] = t[k1] t[k1] = temp end
local out = ""
for i = 1,s:len() do
for _,code in ipairs(codes) do code.count = code.count + code.rate end
if codes[1].count < codes[2].count then swap(codes,1,2) end
if codes[2].count < codes[3].count then swap(codes,2,3) end
if codes[1].count < codes[2].count then swap(codes,1,2) end
local code = codes[1]
local c = s:sub(i,i)
-- Force encoding of "@" to make email address more invisible.
if c == "@" and code == plain then code = codes[2] end
out = out .. code.code(c)
code.count = code.count - 1
end
return out
end
local function mail(s)
s = unescape_special_chars(s)
local address = encode_email_address("mailto:" .. s)
local text = encode_email_address(s)
return add_escape("") .. text .. " "
end
-- links
text = text:gsub("<(https?:[^'\">%s]+)>", link)
text = text:gsub("<(ftp:[^'\">%s]+)>", link)
-- mail
text = text:gsub("%s]+)>", mail)
text = text:gsub("<([-.%w]+%@[-.%w]+)>", mail)
return text
end
-- Encode free standing amps (&) and angles (<)... note that this does not
-- encode free >.
function amps_and_angles(s)
-- encode amps not part of &..; expression
local pos = 1
while true do
local amp = s:find("&", pos)
if not amp then break end
local semi = s:find(";", amp+1)
local stop = s:find("[ \t\n&]", amp+1)
if not semi or (stop and stop < semi) or (semi - amp) > 15 then
s = s:sub(1,amp-1) .. "&" .. s:sub(amp+1)
pos = amp+1
else
pos = amp+1
end
end
-- encode naked <'s
s = s:gsub("<([^a-zA-Z/?$!])", "<%1")
s = s:gsub("<$", "<")
-- what about >, nothing done in the original markdown source to handle them
return s
end
-- Handles emphasis markers (* and _) in the text.
function emphasis(text)
for _, s in ipairs {"%*%*", "%_%_"} do
text = text:gsub(s .. "([^%s][%*%_]?)" .. s, "%1 ")
text = text:gsub(s .. "([^%s][^<>]-[^%s][%*%_]?)" .. s, "%1 ")
end
for _, s in ipairs {"%*", "%_"} do
text = text:gsub(s .. "([^%s_])" .. s, "%1 ")
text = text:gsub(s .. "([^%s_] )" .. s, "%1 ")
text = text:gsub(s .. "([^%s_][^<>_]-[^%s_])" .. s, "%1 ")
text = text:gsub(s .. "([^<>_]-[^<>_]- [^<>_]-)" .. s, "%1 ")
end
return text
end
-- Handles line break markers in the text.
function line_breaks(text)
return text:gsub(" +\n", " TITLE
(.-) ") or s:match("(.-) ") or
s:match("(.-) ") or "Untitled"
header = header:gsub("TITLE", title)
if options.inline_style then
local style = ""
local f = io.open(options.stylesheet)
if f then
style = f:read("*a") f:close()
else
error("Could not include style sheet " .. options.stylesheet .. ": File not found")
end
header = header:gsub(' tag).
-s, --style STYLE Specifies style sheet file (default default.css).
-l, --inline-style Include the style sheet file inline in the header.
Generated files:
-a, --append Append .html extension (instead of replacing).
Other options:
-h, --help Print this help text.
-t, --test Run the unit tests.
]]
local run_stdin = true
local op = OptionParser:new()
op:flag("n", "no-wrap", function () options.wrap_header = false end)
op:param("e", "header", function (x) options.header = x end)
op:param("f", "footer", function (x) options.footer = x end)
op:param("c", "charset", function (x) options.charset = x end)
op:param("i", "title", function(x) options.title = x end)
op:param("s", "style", function(x) options.stylesheet = x end)
op:flag("l", "inline-style", function(x) options.inline_style = true end)
op:flag("a", "append", function() options.append = true end)
op:flag("t", "test", function()
local n = arg[0]:gsub("markdown.lua", "markdown-tests.lua")
local f = io.open(n)
if f then
f:close() dofile(n)
else
error("Cannot find markdown-tests.lua")
end
run_stdin = false
end)
op:flag("h", "help", function() print(help) run_stdin = false end)
op:arg(function(path)
local file = io.open(path) or error("Could not open file: " .. path)
local s = file:read("*a")
file:close()
s = run(s, options)
file = io.open(outpath(path, options), "w") or error("Could not open output file: " .. outpath(path, options))
file:write(s)
file:close()
run_stdin = false
end
)
if not op:run(arg) then
print(help)
run_stdin = false
end
if run_stdin then
local s = io.read("*a")
s = run(s, options)
io.write(s)
end
end
-- If we are being run from the command-line, act accordingly
if arg and arg[0]:find("markdown%.lua$") then
run_command_line(arg)
else
return markdown
end