From 2413d436ed98866e9a70fbd4070a5da52dd97cd5 Mon Sep 17 00:00:00 2001 From: John MacFarlane Date: Fri, 8 Jan 2016 12:15:31 -0800 Subject: New format for spec tests, new lua formatter for specs. The format for the spec examples has changed from . markdown . html . to ```````````````````````````````` example markdown . html ```````````````````````````````` One advantage of this is that `spec.txt` becomes a valid Markdown file. `tests/spec_test.py` has been changed to use the new format. The old `tools/makespec.py` has been replaced by a lua program, `tools/make_spec.lua`, which uses the `lcmark` rock (and indirectly libcmark). It can generate html, latex, and commonmark versions of the spec. Pandoc is no longer needed for the latex/PDF version. And, since the new program uses the cmark API and operates directly on the parse tree, we avoid certain bad results we got with the regex replacements done by the python script. --- Makefile | 23 +- README.md | 11 +- spec.txt | 3338 +++++++++++++++++++++++++++------------------ test/spec_tests.py | 38 +- tools/make_spec.lua | 292 ++++ tools/makespec.py | 172 --- tools/specfilter.hs | 39 - tools/template.commonmark | 9 + tools/template.html | 21 +- tools/template.latex | 95 ++ tools/template.tex | 207 --- 11 files changed, 2424 insertions(+), 1821 deletions(-) create mode 100644 tools/make_spec.lua delete mode 100755 tools/makespec.py delete mode 100755 tools/specfilter.hs create mode 100644 tools/template.commonmark create mode 100644 tools/template.latex delete mode 100644 tools/template.tex diff --git a/Makefile b/Makefile index f50996b..af6bb36 100644 --- a/Makefile +++ b/Makefile @@ -2,20 +2,21 @@ SPEC=spec.txt SITE=_site SPECVERSION=$(shell perl -ne 'print $$1 if /^version: *([0-9.]+)/' $(SPEC)) -.PHONY: spec update-site upload-site +.PHONY: spec clean -spec: spec.html # spec.pdf +spec: spec.html # spec.pdf spec.md -spec.md: $(SPEC) - python3 tools/makespec.py markdown > $@ +spec.md: spec.txt tools/template.commonmark + lua tools/make_spec.lua commonmark < $< > $@ spec.html: spec.txt tools/template.html - python3 tools/makespec.py html > $@ + lua tools/make_spec.lua html < $< > $@ -spec.pdf: spec.md tools/template.tex tools/specfilter.hs - pandoc -s $< --template tools/template.tex \ - --filter tools/specfilter.hs -o $@ --latex-engine=xelatex --toc \ - --number-sections --toc-depth=2 --no-highlight \ - -V documentclass=report \ - -V classoption=twosides +spec.tex: spec.txt tools/template.latex + lua tools/make_spec.lua latex < $< > $@ +spec.pdf: spec.tex + xelatex $< + +clean: + -rm spec.tex spec.md spec.html diff --git a/README.md b/README.md index 65ef742..f0ea60e 100644 --- a/README.md +++ b/README.md @@ -46,16 +46,17 @@ The spec The source of [the spec] is `spec.txt`. This is basically a Markdown file, with code examples written in a shorthand form: - . + ```````````````````````````````` example Markdown source . expected HTML output - . + ```````````````````````````````` To build an HTML version of the spec, do `make spec.html`. To build a -PDF version, do `make spec.pdf`. (Creating the HTML version requires -that [cmark](https://github.com/jgm/cmark) and `python3` be installed -and in your path. Creating a PDF also requires [pandoc] and LaTeX.) +PDF version, do `make spec.pdf`. For both versions, you must +have the lua rock `lcmark` installed: after installing lua and +lua rocks, `luarocks install lcmark`. For the PDF you must also +have xelatex installed. The spec is written from the point of view of the human writer, not the computer reader. It is not an algorithm---an English translation of diff --git a/spec.txt b/spec.txt index 85356de..690d975 100644 --- a/spec.txt +++ b/spec.txt @@ -2,7 +2,7 @@ title: CommonMark Spec author: John MacFarlane version: 0.23 -date: 2015-12-29 +date: '2015-12-29' license: '[CC-BY-SA 4.0](http://creativecommons.org/licenses/by-sa/4.0/)' ... @@ -201,91 +201,94 @@ In the examples, the `→` character is used to represent tabs. ## Characters and lines -Any sequence of [character]s is a valid CommonMark +Any sequence of [characters] is a valid CommonMark document. -A [character](@character) is a Unicode code point. Although some +A [character](@) is a Unicode code point. Although some code points (for example, combining accents) do not correspond to characters in an intuitive sense, all code points count as characters for purposes of this spec. This spec does not specify an encoding; it thinks of lines as composed -of [character]s rather than bytes. A conforming parser may be limited +of [characters] rather than bytes. A conforming parser may be limited to a certain encoding. -A [line](@line) is a sequence of zero or more [character]s +A [line](@) is a sequence of zero or more [characters] other than newline (`U+000A`) or carriage return (`U+000D`), followed by a [line ending] or by the end of file. -A [line ending](@line-ending) is a newline (`U+000A`), a carriage return +A [line ending](@) is a newline (`U+000A`), a carriage return (`U+000D`) not followed by a newline, or a carriage return and a following newline. A line containing no characters, or a line containing only spaces -(`U+0020`) or tabs (`U+0009`), is called a [blank line](@blank-line). +(`U+0020`) or tabs (`U+0009`), is called a [blank line](@). The following definitions of character classes will be used in this spec: -A [whitespace character](@whitespace-character) is a space +A [whitespace character](@) is a space (`U+0020`), tab (`U+0009`), newline (`U+000A`), line tabulation (`U+000B`), form feed (`U+000C`), or carriage return (`U+000D`). -[Whitespace](@whitespace) is a sequence of one or more [whitespace -character]s. +[Whitespace](@) is a sequence of one or more [whitespace +characters]. -A [Unicode whitespace character](@unicode-whitespace-character) is +A [Unicode whitespace character](@) is any code point in the Unicode `Zs` class, or a tab (`U+0009`), carriage return (`U+000D`), newline (`U+000A`), or form feed (`U+000C`). -[Unicode whitespace](@unicode-whitespace) is a sequence of one -or more [Unicode whitespace character]s. +[Unicode whitespace](@) is a sequence of one +or more [Unicode whitespace characters]. -A [space](@space) is `U+0020`. +A [space](@) is `U+0020`. -A [non-whitespace character](@non-whitespace-character) is any character +A [non-whitespace character](@) is any character that is not a [whitespace character]. -An [ASCII punctuation character](@ascii-punctuation-character) +An [ASCII punctuation character](@) is `!`, `"`, `#`, `$`, `%`, `&`, `'`, `(`, `)`, `*`, `+`, `,`, `-`, `.`, `/`, `:`, `;`, `<`, `=`, `>`, `?`, `@`, `[`, `\`, `]`, `^`, `_`, `` ` ``, `{`, `|`, `}`, or `~`. -A [punctuation character](@punctuation-character) is an [ASCII +A [punctuation character](@) is an [ASCII punctuation character] or anything in the Unicode classes `Pc`, `Pd`, `Pe`, `Pf`, `Pi`, `Po`, or `Ps`. ## Tabs -Tabs in lines are not expanded to [spaces][space]. However, +Tabs in lines are not expanded to [spaces]. However, in contexts where indentation is significant for the document's structure, tabs behave as if they were replaced by spaces with a tab stop of 4 characters. -. +```````````````````````````````` example →foo→baz→→bim . 
foo→baz→→bim
-. +```````````````````````````````` -. + +```````````````````````````````` example →foo→baz→→bim . 
foo→baz→→bim
-. +```````````````````````````````` -. + +```````````````````````````````` example a→a ὐ→a . 
a→a
 ὐ→a
-. +```````````````````````````````` -. + +```````````````````````````````` example - foo →bar @@ -296,24 +299,27 @@ by spaces with a tab stop of 4 characters.

bar

-. +```````````````````````````````` -. + +```````````````````````````````` example >→foo→bar .

foo→bar

-. +```````````````````````````````` -. + +```````````````````````````````` example foo →bar . 
foo
 bar
-. +```````````````````````````````` + ## Insecure characters @@ -324,10 +330,10 @@ with the REPLACEMENT CHARACTER (`U+FFFD`). # Blocks and inlines We can think of a document as a sequence of -[blocks](@block)---structural elements like paragraphs, block +[blocks](@)---structural elements like paragraphs, block quotations, lists, headings, rules, and code blocks. Some blocks (like block quotes and list items) contain other blocks; others (like -headings and paragraphs) contain [inline](@inline) content---text, +headings and paragraphs) contain [inline](@) content---text, links, emphasized text, images, code, and so on. ## Precedence @@ -336,7 +342,7 @@ Indicators of block structure always take precedence over indicators of inline structure. So, for example, the following is a list with two items, not a list with one item containing a code span: -. +```````````````````````````````` example - `one - two` . @@ -344,7 +350,8 @@ two items, not a list with one item containing a code span:
  • `one
  • two`
    • -. +```````````````````````````````` + This means that parsing can proceed in two steps: first, the block structure of the document can be discerned; second, text lines inside @@ -358,8 +365,8 @@ one block element does not affect the inline parsing of any other. ## Container blocks and leaf blocks We can divide blocks into two types: -[container block](@container-block)s, -which can contain other blocks, and [leaf block](@leaf-block)s, +[container block](@)s, +which can contain other blocks, and [leaf block](@)s, which cannot. # Leaf blocks @@ -372,9 +379,9 @@ Markdown document. A line consisting of 0-3 spaces of indentation, followed by a sequence of three or more matching `-`, `_`, or `*` characters, each followed optionally by any number of spaces, forms a -[thematic break](@thematic-break). +[thematic break](@). -. +```````````````````````````````` example *** --- ___ @@ -382,25 +389,28 @@ ___
    -. +```````````````````````````````` + Wrong characters: -. +```````````````````````````````` example +++ .

    +++

    -. +```````````````````````````````` -. + +```````````````````````````````` example === .

    ===

    -. +```````````````````````````````` + Not enough characters: -. +```````````````````````````````` example -- ** __ @@ -408,11 +418,12 @@ __

    -- ** __

    -. +```````````````````````````````` + One to three spaces indent are allowed: -. +```````````````````````````````` example *** *** *** @@ -420,64 +431,72 @@ One to three spaces indent are allowed:
    -. +```````````````````````````````` + Four spaces is too many: -. +```````````````````````````````` example *** . 
    ***
    -. +```````````````````````````````` -. + +```````````````````````````````` example Foo *** .

    Foo ***

    -. +```````````````````````````````` + More than three characters may be used: -. +```````````````````````````````` example _____________________________________ .
    -. +```````````````````````````````` + Spaces are allowed between the characters: -. +```````````````````````````````` example - - - .
    -. +```````````````````````````````` -. + +```````````````````````````````` example ** * ** * ** * ** .
    -. +```````````````````````````````` -. + +```````````````````````````````` example - - - - .
    -. +```````````````````````````````` + Spaces are allowed at the end: -. +```````````````````````````````` example - - - - .
    -. +```````````````````````````````` + However, no other characters may occur in the line: -. +```````````````````````````````` example _ _ _ _ a a------ @@ -487,20 +506,22 @@ a------

    _ _ _ _ a

    a------

    ---a---

    -. +```````````````````````````````` + -It is required that all of the [non-whitespace character]s be the same. +It is required that all of the [non-whitespace characters] be the same. So, this is not a thematic break: -. +```````````````````````````````` example *-* .

    -

    -. +```````````````````````````````` + Thematic breaks do not need blank lines before or after: -. +```````````````````````````````` example - foo *** - bar @@ -512,11 +533,12 @@ Thematic breaks do not need blank lines before or after: -. +```````````````````````````````` + Thematic breaks can interrupt a paragraph: -. +```````````````````````````````` example Foo *** bar @@ -524,7 +546,8 @@ bar

    Foo

    bar

    -. +```````````````````````````````` + If a line of dashes that meets the above conditions for being a thematic break could also be interpreted as the underline of a [setext @@ -532,19 +555,20 @@ heading], the interpretation as a [setext heading] takes precedence. Thus, for example, this is a setext heading, not a paragraph followed by a thematic break: -. +```````````````````````````````` example Foo --- bar .

    Foo

    bar

    -. +```````````````````````````````` + When both a thematic break and a list item are possible interpretations of a line, the thematic break takes precedence: -. +```````````````````````````````` example * Foo * * * * Bar @@ -556,11 +580,12 @@ interpretations of a line, the thematic break takes precedence: -. +```````````````````````````````` + If you want a thematic break in a list item, use a different bullet: -. +```````````````````````````````` example - Foo - * * * . @@ -570,11 +595,12 @@ If you want a thematic break in a list item, use a different bullet:
    -. +```````````````````````````````` + ## ATX headings -An [ATX heading](@atx-heading) +An [ATX heading](@) consists of a string of characters, parsed as inline content, between an opening sequence of 1--6 unescaped `#` characters and an optional closing sequence of any number of unescaped `#` characters. @@ -588,7 +614,7 @@ characters in the opening sequence. Simple headings: -. +```````````````````````````````` example # foo ## foo ### foo @@ -602,15 +628,17 @@ Simple headings:

    foo

    foo
    foo
    -. +```````````````````````````````` + More than six `#` characters is not a heading: -. +```````````````````````````````` example ####### foo .

    ####### foo

    -. +```````````````````````````````` + At least one space is required between the `#` characters and the heading's contents, unless the heading is empty. Note that many @@ -620,50 +648,55 @@ space was required by the and it helps prevent things like the following from being parsed as headings: -. +```````````````````````````````` example #5 bolt #hashtag .

    #5 bolt

    #hashtag

    -. +```````````````````````````````` + A tab will not work: -. +```````````````````````````````` example #→foo .

    #→foo

    -. +```````````````````````````````` + This is not a heading, because the first `#` is escaped: -. +```````````````````````````````` example \## foo .

    ## foo

    -. +```````````````````````````````` + Contents are parsed as inlines: -. +```````````````````````````````` example # foo *bar* \*baz\* .

    foo bar *baz*

    -. +```````````````````````````````` + Leading and trailing blanks are ignored in parsing inline content: -. +```````````````````````````````` example # foo .

    foo

    -. +```````````````````````````````` + One to three spaces indentation are allowed: -. +```````````````````````````````` example ### foo ## foo # foo @@ -671,75 +704,83 @@ One to three spaces indentation are allowed:

    foo

    foo

    foo

    -. +```````````````````````````````` + Four spaces are too much: -. +```````````````````````````````` example # foo . 
    # foo
    -. +```````````````````````````````` -. + +```````````````````````````````` example foo # bar .

    foo # bar

    -. +```````````````````````````````` + A closing sequence of `#` characters is optional: -. +```````````````````````````````` example ## foo ## ### bar ### .

    foo

    bar

    -. +```````````````````````````````` + It need not be the same length as the opening sequence: -. +```````````````````````````````` example # foo ################################## ##### foo ## .

    foo

    foo
    -. +```````````````````````````````` + Spaces are allowed after the closing sequence: -. +```````````````````````````````` example ### foo ### .

    foo

    -. +```````````````````````````````` -A sequence of `#` characters with anything but [space]s following it + +A sequence of `#` characters with anything but [spaces] following it is not a closing sequence, but counts as part of the contents of the heading: -. +```````````````````````````````` example ### foo ### b .

    foo ### b

    -. +```````````````````````````````` + The closing sequence must be preceded by a space: -. +```````````````````````````````` example # foo# .

    foo#

    -. +```````````````````````````````` + Backslash-escaped `#` characters do not count as part of the closing sequence: -. +```````````````````````````````` example ### foo \### ## foo #\## # foo \# @@ -747,12 +788,13 @@ of the closing sequence:

    foo ###

    foo ###

    foo #

    -. +```````````````````````````````` + ATX headings need not be separated from surrounding content by blank lines, and they can interrupt paragraphs: -. +```````````````````````````````` example **** ## foo **** @@ -760,9 +802,10 @@ lines, and they can interrupt paragraphs:

    foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example Foo bar # baz Bar foo @@ -770,11 +813,12 @@ Bar foo

    Foo bar

    baz

    Bar foo

    -. +```````````````````````````````` + ATX headings can be empty: -. +```````````````````````````````` example ## # ### ### @@ -782,11 +826,12 @@ ATX headings can be empty:

    -. +```````````````````````````````` + ## Setext headings -A [setext heading](@setext-heading) consists of one or more +A [setext heading](@) consists of one or more lines of text, each containing at least one [non-whitespace character], with no more than 3 spaces indentation, followed by a [setext heading underline]. The lines of text must be such @@ -796,7 +841,7 @@ interpretable as a [code fence], [ATX heading][ATX headings], [block quote][block quotes], [thematic break][thematic breaks], [list item][list items], or [HTML block][HTML blocks]. -A [setext heading underline](@setext-heading-underline) is a sequence of +A [setext heading underline](@) is a sequence of `=` characters or a sequence of `-` characters, with no more than 3 spaces indentation and any number of trailing spaces. If a line containing a single `-` can be interpreted as an @@ -816,7 +861,7 @@ them. Simple examples: -. +```````````````````````````````` example Foo *bar* ========= @@ -825,22 +870,24 @@ Foo *bar* .

    Foo bar

    Foo bar

    -. +```````````````````````````````` + The content of the header may span more than one line: -. +```````````````````````````````` example Foo *bar baz* ==== .

    Foo bar baz

    -. +```````````````````````````````` + The underlining can be any length: -. +```````````````````````````````` example Foo ------------------------- @@ -849,12 +896,13 @@ Foo .

    Foo

    Foo

    -. +```````````````````````````````` + The heading content can be indented up to three spaces, and need not line up with the underlining: -. +```````````````````````````````` example Foo --- @@ -867,11 +915,12 @@ not line up with the underlining:

    Foo

    Foo

    Foo

    -. +```````````````````````````````` + Four spaces indent is too much: -. +```````````````````````````````` example Foo --- @@ -884,31 +933,34 @@ Four spaces indent is too much: Foo
    -. +```````````````````````````````` + The setext heading underline can be indented up to three spaces, and may have trailing spaces: -. +```````````````````````````````` example Foo ---- .

    Foo

    -. +```````````````````````````````` + Four spaces is too much: -. +```````````````````````````````` example Foo --- .

    Foo ---

    -. +```````````````````````````````` + The setext heading underline cannot contain internal spaces: -. +```````````````````````````````` example Foo = = @@ -919,30 +971,33 @@ Foo = =

    Foo

    -. +```````````````````````````````` + Trailing spaces in the content line do not cause a line break: -. +```````````````````````````````` example Foo ----- .

    Foo

    -. +```````````````````````````````` + Nor does a backslash at the end: -. +```````````````````````````````` example Foo\ ---- .

    Foo\

    -. +```````````````````````````````` + Since indicators of block structure take precedence over indicators of inline structure, the following are setext headings: -. +```````````````````````````````` example `Foo ---- ` @@ -955,12 +1010,13 @@ of dashes"/>

    `

    <a title="a lot

    of dashes"/>

    -. +```````````````````````````````` + The setext heading underline cannot be a [lazy continuation line] in a list item or block quote: -. +```````````````````````````````` example > Foo --- . @@ -968,9 +1024,10 @@ line] in a list item or block quote:

    Foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example > foo bar === @@ -980,9 +1037,10 @@ bar bar ===

    -. +```````````````````````````````` -. + +```````````````````````````````` example - Foo --- . @@ -990,25 +1048,27 @@ bar
  • Foo
    • -. +```````````````````````````````` + A blank line is needed between a paragraph and a following setext heading, since otherwise the paragraph becomes part of the heading's content: -. +```````````````````````````````` example Foo Bar --- .

    Foo Bar

    -. +```````````````````````````````` + But in general a blank line is not required before or after setext headings: -. +```````````````````````````````` example --- Foo --- @@ -1020,30 +1080,33 @@ Baz

    Foo

    Bar

    Baz

    -. +```````````````````````````````` + Setext headings cannot be empty: -. +```````````````````````````````` example ==== .

    ====

    -. +```````````````````````````````` + Setext heading text lines must not be interpretable as block constructs other than paragraphs. So, the line of dashes in these examples gets interpreted as a thematic break: -. +```````````````````````````````` example --- --- .
    -. +```````````````````````````````` -. + +```````````````````````````````` example - foo ----- . @@ -1051,18 +1114,20 @@ in these examples gets interpreted as a thematic break:
  • foo
    • -. +```````````````````````````````` -. + +```````````````````````````````` example foo --- . 
    foo
    -. +```````````````````````````````` -. + +```````````````````````````````` example > foo ----- . @@ -1070,17 +1135,19 @@ in these examples gets interpreted as a thematic break:

    foo

    -. +```````````````````````````````` + If you want a heading with `> foo` as its literal text, you can use backslash escapes: -. +```````````````````````````````` example \> foo ------ .

    > foo

    -. +```````````````````````````````` + **Compatibility note:** Most existing Markdown implementations do not allow the text of setext headings to span multiple lines. @@ -1105,7 +1172,7 @@ increases the expressive power of CommonMark, by allowing multiline headings. Authors who want interpretation 1 can put a blank line after the first paragraph: -. +```````````````````````````````` example Foo bar @@ -1115,12 +1182,13 @@ baz

    Foo

    bar

    baz

    -. +```````````````````````````````` + Authors who want interpretation 2 can put blank lines around the thematic break, -. +```````````````````````````````` example Foo bar @@ -1132,12 +1200,13 @@ baz bar

    baz

    -. +```````````````````````````````` + or use a thematic break that cannot count as a [setext heading line], such as -. +```````````````````````````````` example Foo bar * * * @@ -1147,11 +1216,12 @@ baz bar

    baz

    -. +```````````````````````````````` + Authors who want interpretation 3 can use backslash escapes: -. +```````````````````````````````` example Foo bar \--- @@ -1161,16 +1231,17 @@ baz bar --- baz

    -. +```````````````````````````````` + ## Indented code blocks -An [indented code block](@indented-code-block) is composed of one or more -[indented chunk]s separated by blank lines. -An [indented chunk](@indented-chunk) is a sequence of non-blank lines, +An [indented code block](@) is composed of one or more +[indented chunks] separated by blank lines. +An [indented chunk](@) is a sequence of non-blank lines, each indented four or more spaces. The contents of the code block are the literal contents of the lines, including trailing -[line ending]s, minus four spaces of indentation. +[line endings], minus four spaces of indentation. An indented code block has no [info string]. An indented code block cannot interrupt a paragraph, so there must be @@ -1178,20 +1249,21 @@ a blank line between a paragraph and a following indented code block. (A blank line is not needed, however, between a code block and a following paragraph.) -. +```````````````````````````````` example a simple indented code block . 
    a simple
   indented code block
    -. +```````````````````````````````` + If there is any ambiguity between an interpretation of indentation as a code block and as indicating that material belongs to a [list item][list items], the list item interpretation takes precedence: -. +```````````````````````````````` example - foo bar @@ -1202,9 +1274,10 @@ item][list items], the list item interpretation takes precedence:

    bar

    -. +```````````````````````````````` -. + +```````````````````````````````` example 1. foo - bar @@ -1217,13 +1290,14 @@ item][list items], the list item interpretation takes precedence: -. +```````````````````````````````` + The contents of a code block are literal text, and do not get parsed as Markdown: -. +```````````````````````````````` example *hi* @@ -1234,11 +1308,12 @@ as Markdown: - one -. +```````````````````````````````` + Here we have three chunks separated by blank lines: -. +```````````````````````````````` example chunk1 chunk2 @@ -1255,12 +1330,13 @@ chunk2 chunk3 -. +```````````````````````````````` + Any initial spaces beyond four will be included in the content, even in interior blank lines: -. +```````````````````````````````` example chunk1 chunk2 @@ -1269,37 +1345,40 @@ in interior blank lines: chunk2 -. +```````````````````````````````` + An indented code block cannot interrupt a paragraph. (This allows hanging indents and the like.) -. +```````````````````````````````` example Foo bar .

    Foo bar

    -. +```````````````````````````````` + However, any non-blank line with fewer than four leading spaces ends the code block immediately. So a paragraph may occur immediately after indented code: -. +```````````````````````````````` example foo bar . 
    foo

    bar

    -. +```````````````````````````````` + And indented code can occur immediately before and after other kinds of blocks: -. +```````````````````````````````` example # Heading foo Heading @@ -1314,23 +1393,25 @@ Heading 
    foo
    -. +```````````````````````````````` + The first line can be indented more than four spaces: -. +```````````````````````````````` example foo bar . 
        foo
 bar
    -. +```````````````````````````````` + Blank lines preceding or following an indented code block are not included in it: -. +```````````````````````````````` example foo @@ -1339,29 +1420,31 @@ are not included in it: . 
    foo
    -. +```````````````````````````````` + Trailing spaces are included in the code block's content: -. +```````````````````````````````` example foo . 
    foo
    -. +```````````````````````````````` + ## Fenced code blocks -A [code fence](@code-fence) is a sequence +A [code fence](@) is a sequence of at least three consecutive backtick characters (`` ` ``) or tildes (`~`). (Tildes and backticks cannot be mixed.) -A [fenced code block](@fenced-code-block) +A [fenced code block](@) begins with a code fence, indented no more than three spaces. The line with the opening code fence may optionally contain some text following the code fence; this is trimmed of leading and trailing -spaces and called the [info string](@info-string). +spaces and called the [info string](@). The [info string] may not contain any backtick characters. (The reason for this restriction is that otherwise some inline code would be incorrectly interpreted as the @@ -1397,7 +1480,7 @@ particular treatment of the [info string]. Here is a simple example with backticks: -. +```````````````````````````````` example ``` < > @@ -1406,11 +1489,12 @@ Here is a simple example with backticks: 
    <
  >
    -. +```````````````````````````````` + With tildes: -. +```````````````````````````````` example ~~~ < > @@ -1419,12 +1503,13 @@ With tildes: 
    <
  >
    -. +```````````````````````````````` + The closing code fence must use the same character as the opening fence: -. +```````````````````````````````` example ``` aaa ~~~ @@ -1433,9 +1518,10 @@ aaa 
    aaa
 ~~~
    -. +```````````````````````````````` -. + +```````````````````````````````` example ~~~ aaa ``` @@ -1444,11 +1530,12 @@ aaa 
    aaa
 ```
    -. +```````````````````````````````` + The closing code fence must be at least as long as the opening fence: -. +```````````````````````````````` example ```` aaa ``` @@ -1457,9 +1544,10 @@ aaa 
    aaa
 ```
    -. +```````````````````````````````` -. + +```````````````````````````````` example ~~~~ aaa ~~~ @@ -1468,18 +1556,20 @@ aaa 
    aaa
 ~~~
    -. +```````````````````````````````` + Unclosed code blocks are closed by the end of the document (or the enclosing [block quote][block quotes] or [list item][list items]): -. +```````````````````````````````` example ``` .
    -. +```````````````````````````````` -. + +```````````````````````````````` example ````` ``` @@ -1489,9 +1579,10 @@ aaa ``` aaa -. +```````````````````````````````` -. + +```````````````````````````````` example > ``` > aaa @@ -1502,11 +1593,12 @@ bbb

    bbb

    -. +```````````````````````````````` + A code block can have all empty lines as its content: -. +```````````````````````````````` example ``` @@ -1515,22 +1607,24 @@ A code block can have all empty lines as its content:
    -. +```````````````````````````````` + A code block can be empty: -. +```````````````````````````````` example ``` ``` .
    -. +```````````````````````````````` + Fences can be indented. If the opening fence is indented, content lines will have equivalent opening indentation removed, if present: -. +```````````````````````````````` example ``` aaa aaa @@ -1539,9 +1633,10 @@ aaa 
    aaa
 aaa
    -. +```````````````````````````````` -. + +```````````````````````````````` example ``` aaa aaa @@ -1552,9 +1647,10 @@ aaa aaa aaa -. +```````````````````````````````` -. + +```````````````````````````````` example ``` aaa aaa @@ -1565,11 +1661,12 @@ aaa aaa aaa -. +```````````````````````````````` + Four spaces indentation produces an indented code block: -. +```````````````````````````````` example ``` aaa ``` @@ -1578,32 +1675,35 @@ Four spaces indentation produces an indented code block: aaa ``` -. +```````````````````````````````` + Closing fences may be indented by 0-3 spaces, and their indentation need not match that of the opening fence: -. +```````````````````````````````` example ``` aaa ``` . 
    aaa
    -. +```````````````````````````````` -. + +```````````````````````````````` example ``` aaa ``` . 
    aaa
    -. +```````````````````````````````` + This is not a closing fence, because it is indented 4 spaces: -. +```````````````````````````````` example ``` aaa ``` @@ -1611,20 +1711,22 @@ aaa 
    aaa
     ```
    -. +```````````````````````````````` + Code fences (opening and closing) cannot contain internal spaces: -. +```````````````````````````````` example ``` ``` aaa .

    aaa

    -. +```````````````````````````````` -. + +```````````````````````````````` example ~~~~~~ aaa ~~~ ~~ @@ -1632,12 +1734,13 @@ aaa 
    aaa
 ~~~ ~~
    -. +```````````````````````````````` + Fenced code blocks can interrupt paragraphs, and can be followed directly by paragraphs, without a blank line between: -. +```````````````````````````````` example foo ``` bar @@ -1648,12 +1751,13 @@ baz 
    bar

    baz

    -. +```````````````````````````````` + Other blocks can also occur before and after fenced code blocks without an intervening blank line: -. +```````````````````````````````` example foo --- ~~~ @@ -1665,14 +1769,15 @@ bar 
    bar

    baz

    -. +```````````````````````````````` + An [info string] can be provided after the opening code fence. Opening and closing spaces will be stripped, and the first word, prefixed with `language-`, is used as the value for the `class` attribute of the `code` element within the enclosing `pre` element. -. +```````````````````````````````` example ```ruby def foo(x) return 3 @@ -1683,9 +1788,10 @@ end return 3 end -. +```````````````````````````````` -. + +```````````````````````````````` example ~~~~ ruby startline=3 $%@#$ def foo(x) return 3 @@ -1696,47 +1802,51 @@ end return 3 end -. +```````````````````````````````` -. + +```````````````````````````````` example ````; ```` .
    -. +```````````````````````````````` -[Info string]s for backtick code blocks cannot contain backticks: -. +[Info strings] for backtick code blocks cannot contain backticks: + +```````````````````````````````` example ``` aa ``` foo .

    aa foo

    -. +```````````````````````````````` -Closing code fences cannot have [info string]s: -. +Closing code fences cannot have [info strings]: + +```````````````````````````````` example ``` ``` aaa ``` . 
    ``` aaa
    -. +```````````````````````````````` + ## HTML blocks -An [HTML block](@html-block) is a group of lines that is treated +An [HTML block](@) is a group of lines that is treated as raw HTML (and will not be escaped in HTML output). There are seven kinds of [HTML block], which can be defined by their start and end conditions. The block begins with a line that -meets a [start condition](@start-condition) (after up to three spaces +meets a [start condition](@) (after up to three spaces optional indentation). It ends with the first subsequent line that -meets a matching [end condition](@end-condition), or the last line of +meets a matching [end condition](@), or the last line of the document, if no line is encountered that meets the [end condition]. If the first line meets both the [start condition] and the [end condition], the block will contain just that line. @@ -1790,7 +1900,7 @@ of long tags inside a wrapped paragraph as starting HTML blocks.) Some simple examples follow. Here are some basic HTML blocks of type 6: -. +```````````````````````````````` example
    @@ -1809,9 +1919,10 @@ okay.

    okay.

    -. +```````````````````````````````` -. + +```````````````````````````````` example
    *hello* @@ -1819,21 +1930,23 @@ okay.
    *hello* -. +```````````````````````````````` + A block can also start with a closing tag: -. +```````````````````````````````` example
    *foo* .
    *foo* -. +```````````````````````````````` + Here we have two HTML blocks with a Markdown paragraph between them: -. +```````````````````````````````` example
    *Markdown* @@ -1843,12 +1956,13 @@ Here we have two HTML blocks with a Markdown paragraph between them:

    Markdown

    -. +```````````````````````````````` + The tag on the first line can be partial, as long as it is split where there would be whitespace: -. +```````````````````````````````` example
    @@ -1856,9 +1970,10 @@ as it is split where there would be whitespace:
    -. +```````````````````````````````` -. + +```````````````````````````````` example
    @@ -1866,10 +1981,11 @@ as it is split where there would be whitespace:
    -. +```````````````````````````````` + An open tag need not be closed: -. +```````````````````````````````` example
    *foo* @@ -1878,49 +1994,54 @@ An open tag need not be closed:
    *foo*

    bar

    -. +```````````````````````````````` + A partial tag need not even be completed (garbage in, garbage out): -. +```````````````````````````````` example     .
    *foo*
    -. +```````````````````````````````` -. + +```````````````````````````````` example
    foo
    @@ -1928,7 +2049,8 @@ foo
    foo
    -. +```````````````````````````````` + Everything until the next blank line or end of document gets included in the HTML block. So, in the following @@ -1936,7 +2058,7 @@ example, what looks like a Markdown code block is actually part of the HTML block, which continues until a blank line or the end of the document is reached: -. +```````````````````````````````` example
    ``` c int x = 33; @@ -1946,13 +2068,14 @@ int x = 33; ``` c int x = 33; ``` -. +```````````````````````````````` + To start an [HTML block] with a tag that is *not* in the list of block-level tags in (6), you must put the tag by itself on the first line (and it must be complete): -. +```````````````````````````````` example *bar* @@ -1960,11 +2083,12 @@ itself on the first line (and it must be complete): *bar* -. +```````````````````````````````` + In type 7 blocks, the [tag name] can be anything: -. +```````````````````````````````` example *bar* @@ -1972,9 +2096,10 @@ In type 7 blocks, the [tag name] can be anything: *bar* -. +```````````````````````````````` -. + +```````````````````````````````` example *bar* @@ -1982,15 +2107,17 @@ In type 7 blocks, the [tag name] can be anything: *bar* -. +```````````````````````````````` -. + +```````````````````````````````` example *bar* . *bar* -. +```````````````````````````````` + These rules are designed to allow us to work with tags that can function as either block-level or inline-level tags. @@ -1998,7 +2125,7 @@ The `` tag is a nice example. We can surround content with `` tags in three different ways. In this case, we get a raw HTML block, because the `` tag is on a line by itself: -. +```````````````````````````````` example *foo* @@ -2006,13 +2133,14 @@ HTML block, because the `` tag is on a line by itself: *foo* -. +```````````````````````````````` + In this case, we get a raw HTML block that just includes the `` tag (because it ends with the following blank line). So the contents get interpreted as CommonMark: -. +```````````````````````````````` example *foo* @@ -2022,18 +2150,20 @@ line). So the contents get interpreted as CommonMark:

    foo

     -. +```````````````````````````````` + Finally, in this case, the `` tags are interpreted as [raw HTML] *inside* the CommonMark paragraph. (Because the tag is not on a line by itself, we get inline HTML rather than an [HTML block].) -. +```````````````````````````````` example *foo* .

    foo

    -. +```````````````````````````````` + HTML tags designed to contain literal content (`script`, `style`, `pre`), comments, processing instructions, @@ -2044,7 +2174,7 @@ As a result, these blocks can contain blank lines: A pre tag (type 1): -. +```````````````````````````````` example 
    
 import Text.HTML.TagSoup
 
@@ -2058,11 +2188,12 @@ import Text.HTML.TagSoup
 main :: IO ()
 main = print $ parseTags tags
    -. +```````````````````````````````` + A script tag (type 1): -. +```````````````````````````````` example -. +```````````````````````````````` + A style tag (type 1): -. +```````````````````````````````` example -. +```````````````````````````````` + If there is no matching end tag, the block will end at the end of the document (or the enclosing [block quote][block quotes] or [list item][list items]): -. +```````````````````````````````` example *foo* .

    foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example *bar* *baz* . *bar*

    baz

    -. +```````````````````````````````` + Note that anything on the last line after the end tag will be included in the [HTML block]: -. +```````````````````````````````` example 1. *bar* @@ -2164,11 +2302,12 @@ foo 1. *bar* -. +```````````````````````````````` + A comment (type 2): -. +```````````````````````````````` example -. +```````````````````````````````` + A processing instruction (type 3): -. +```````````````````````````````` example '; @@ -2195,19 +2335,21 @@ A processing instruction (type 3): echo '>'; ?> -. +```````````````````````````````` + A declaration (type 4): -. +```````````````````````````````` example . -. +```````````````````````````````` + CDATA (type 5): -. +```````````````````````````````` example -. +```````````````````````````````` + The opening tag can be indented 1-3 spaces, but not 4: -. +```````````````````````````````` example @@ -2245,9 +2388,10 @@ The opening tag can be indented 1-3 spaces, but not 4: 
    <!-- foo -->
    -. +```````````````````````````````` -. + +```````````````````````````````` example
    @@ -2255,12 +2399,13 @@ The opening tag can be indented 1-3 spaces, but not 4: 
    <div>
    -. +```````````````````````````````` + An HTML block of types 1--6 can interrupt a paragraph, and need not be preceded by a blank line. -. +```````````````````````````````` example Foo
    bar @@ -2270,12 +2415,13 @@ bar
    bar
    -. +```````````````````````````````` + However, a following blank line is needed, except at the end of a document, and except for blocks of types 1--5, above: -. +```````````````````````````````` example
    bar
    @@ -2285,11 +2431,12 @@ bar bar
    *foo* -. +```````````````````````````````` + HTML blocks of type 7 cannot interrupt a paragraph: -. +```````````````````````````````` example Foo baz @@ -2297,7 +2444,8 @@ baz

    Foo baz

    -. +```````````````````````````````` + This rule differs from John Gruber's original Markdown syntax specification, which says: @@ -2329,7 +2477,7 @@ simply separate the Markdown from the HTML using blank lines: Compare: -. +```````````````````````````````` example
    *Emphasized* text. @@ -2339,9 +2487,10 @@ Compare:

    Emphasized text.

    -. +```````````````````````````````` -. + +```````````````````````````````` example
    *Emphasized* text.
    @@ -2349,7 +2498,8 @@ Compare:
    *Emphasized* text.
    -. +```````````````````````````````` + Some Markdown implementations have adopted a convention of interpreting content inside tags as text if the open tag has @@ -2362,7 +2512,7 @@ blocks into Markdown documents with 100% reliability. However, *in most cases* this will work fine, because the blank lines in HTML are usually followed by HTML block tags. For example: -. +```````````````````````````````` example @@ -2382,13 +2532,14 @@ Hi
    -. +```````````````````````````````` + There are problems, however, if the inner tags are indented *and* separated by spaces, as then they will be interpreted as an indented code block: -. +```````````````````````````````` example @@ -2409,7 +2560,8 @@ an indented code block:
    -. +```````````````````````````````` + Fortunately, blank lines are usually not necessary and can be deleted. The exception is inside `
    ` tags, but as described
@@ -2418,7 +2570,7 @@ lines.
 
 ## Link reference definitions
 
-A [link reference definition](@link-reference-definition)
+A [link reference definition](@)
 consists of a [link label], indented up to three spaces, followed
 by a colon (`:`), optional [whitespace] (including up to one
 [line ending]), a [link destination],
@@ -2426,24 +2578,25 @@ optional [whitespace] (including up to one
 [line ending]), and an optional [link
 title], which if it is present must be separated
 from the [link destination] by [whitespace].
-No further [non-whitespace character]s may occur on the line.
+No further [non-whitespace characters] may occur on the line.
 
 A [link reference definition]
 does not correspond to a structural element of a document.  Instead, it
-defines a label which can be used in [reference link]s
+defines a label which can be used in [reference links]
 and reference-style [images] elsewhere in the document.  [Link
 reference definitions] can come either before or after the links that use
 them.
 
-.
+```````````````````````````````` example
 [foo]: /url "title"
 
 [foo]
 .
 
    foo
    
-.
+````````````````````````````````
 
-.
+
+```````````````````````````````` example
    [foo]: 
       /url  
            'the title'  
@@ -2451,17 +2604,19 @@ them.
 [foo]
 .
 
    foo
    
-.
+````````````````````````````````
 
-.
+
+```````````````````````````````` example
 [Foo*bar\]]:my_(url) 'title (with parens)'
 
 [Foo*bar\]]
 .
 
    Foo*bar]
    
-.
+````````````````````````````````
 
-.
+
+```````````````````````````````` example
 [Foo bar]:
 
 'title'
@@ -2469,11 +2624,12 @@ them.
 [Foo bar]
 .
 
    Foo bar
    
-.
+````````````````````````````````
+
 
 The title may extend over multiple lines:
 
-.
+```````````````````````````````` example
 [foo]: /url '
 title
 line1
@@ -2487,11 +2643,12 @@ title
 line1
 line2
 ">foo
    
-.
+````````````````````````````````
+
 
 However, it may not contain a [blank line]:
 
-.
+```````````````````````````````` example
 [foo]: /url 'title
 
 with blank line'
@@ -2501,123 +2658,135 @@ with blank line'
 
    [foo]: /url 'title
    
 
    with blank line'
    
 
    [foo]
    
-.
+````````````````````````````````
+
 
 The title may be omitted:
 
-.
+```````````````````````````````` example
 [foo]:
 /url
 
 [foo]
 .
 
    foo
    
-.
+````````````````````````````````
+
 
 The link destination may not be omitted:
 
-.
+```````````````````````````````` example
 [foo]:
 
 [foo]
 .
 
    [foo]:
    
 
    [foo]
    
-.
+````````````````````````````````
+
 
 Both title and destination can contain backslash escapes
 and literal backslashes:
 
-.
+```````````````````````````````` example
 [foo]: /url\bar\*baz "foo\"bar\baz"
 
 [foo]
 .
 
    foo
    
-.
+````````````````````````````````
+
 
 A link can come before its corresponding definition:
 
-.
+```````````````````````````````` example
 [foo]
 
 [foo]: url
 .
 
    foo
    
-.
+````````````````````````````````
+
 
 If there are several matching definitions, the first one takes
 precedence:
 
-.
+```````````````````````````````` example
 [foo]
 
 [foo]: first
 [foo]: second
 .
 
    foo
    
-.
+````````````````````````````````
+
 
 As noted in the section on [Links], matching of labels is
 case-insensitive (see [matches]).
 
-.
+```````````````````````````````` example
 [FOO]: /url
 
 [Foo]
 .
 
    Foo
    
-.
+````````````````````````````````
 
-.
+
+```````````````````````````````` example
 [ΑΓΩ]: /φου
 
 [αγω]
 .
 
    αγω
    
-.
+````````````````````````````````
+
 
 Here is a link reference definition with no corresponding link.
 It contributes nothing to the document.
 
-.
+```````````````````````````````` example
 [foo]: /url
 .
-.
+````````````````````````````````
+
 
 Here is another one:
 
-.
+```````````````````````````````` example
 [
 foo
 ]: /url
 bar
 .
 
    bar
    
-.
+````````````````````````````````
+
 
 This is not a link reference definition, because there are
-[non-whitespace character]s after the title:
+[non-whitespace characters] after the title:
 
-.
+```````````````````````````````` example
 [foo]: /url "title" ok
 .
 
    [foo]: /url "title" ok
    
-.
+````````````````````````````````
+
 
 This is a link reference definition, but it has no title:
 
-.
+```````````````````````````````` example
 [foo]: /url
 "title" ok
 .
 
    "title" ok
    
-.
+````````````````````````````````
+
 
 This is not a link reference definition, because it is indented
 four spaces:
 
-.
+```````````````````````````````` example
     [foo]: /url "title"
 
 [foo]
@@ -2625,12 +2794,13 @@ four spaces:
 
    [foo]: /url "title"
 
    
 
    [foo]
    
-.
+````````````````````````````````
+
 
 This is not a link reference definition, because it occurs inside
 a code block:
 
-.
+```````````````````````````````` example
 ```
 [foo]: /url
 ```
@@ -2640,11 +2810,12 @@ a code block:
 
    [foo]: /url
 
    
 
    [foo]
    
-.
+````````````````````````````````
+
 
 A [link reference definition] cannot interrupt a paragraph.
 
-.
+```````````````````````````````` example
 Foo
 [bar]: /baz
 
@@ -2653,12 +2824,13 @@ Foo
 
    Foo
 [bar]: /baz
    
 
    [bar]
    
-.
+````````````````````````````````
+
 
 However, it can directly follow other block elements, such as headings
 and thematic breaks, and it need not be followed by a blank line.
 
-.
+```````````````````````````````` example
 # [Foo]
 [foo]: /url
 > bar
@@ -2667,12 +2839,13 @@ and thematic breaks, and it need not be followed by a blank line.
 
    
 
    bar
    
 
    
-.
+````````````````````````````````
 
-Several [link reference definition]s
+
+Several [link reference definitions]
 can occur one after another, without intervening blank lines.
 
-.
+```````````````````````````````` example
 [foo]: /foo-url "foo"
 [bar]: /bar-url
   "bar"
@@ -2685,14 +2858,15 @@ can occur one after another, without intervening blank lines.
 
    foo,
 bar,
 baz
    
-.
+````````````````````````````````
+
 
-[Link reference definition]s can occur
+[Link reference definitions] can occur
 inside block containers, like lists and block quotations.  They
 affect the entire document, not just the container in which they
 are defined:
 
-.
+```````````````````````````````` example
 [foo]
 
 > [foo]: /url
@@ -2700,13 +2874,14 @@ are defined:
 
    foo
    
 
    
 
    
-.
+````````````````````````````````
+
 
 
 ## Paragraphs
 
 A sequence of non-blank lines that cannot be interpreted as other
-kinds of blocks forms a [paragraph](@paragraph).
+kinds of blocks forms a [paragraph](@).
 The contents of the paragraph are the result of parsing the
 paragraph's raw content as inlines.  The paragraph's raw content
 is formed by concatenating the lines and removing initial and final
@@ -2714,18 +2889,19 @@ is formed by concatenating the lines and removing initial and final
 
 A simple example with two paragraphs:
 
-.
+```````````````````````````````` example
 aaa
 
 bbb
 .
 
    aaa
    
 
    bbb
    
-.
+````````````````````````````````
+
 
 Paragraphs can contain multiple lines, but no blank lines:
 
-.
+```````````````````````````````` example
 aaa
 bbb
 
@@ -2736,11 +2912,12 @@ ddd
 bbb
    
 
    ccc
 ddd
    
-.
+````````````````````````````````
+
 
 Multiple blank lines between paragraph have no effect:
 
-.
+```````````````````````````````` example
 aaa
 
 
@@ -2748,22 +2925,24 @@ bbb
 .
 
    aaa
    
 
    bbb
    
-.
+````````````````````````````````
+
 
 Leading spaces are skipped:
 
-.
+```````````````````````````````` example
   aaa
  bbb
 .
 
    aaa
 bbb
    
-.
+````````````````````````````````
+
 
 Lines after the first may be indented any amount, since indented
 code blocks cannot interrupt paragraphs.
 
-.
+```````````````````````````````` example
 aaa
              bbb
                                        ccc
@@ -2771,49 +2950,53 @@ aaa
 
    aaa
 bbb
 ccc
    
-.
+````````````````````````````````
+
 
 However, the first line may be indented at most three spaces,
 or an indented code block will be triggered:
 
-.
+```````````````````````````````` example
    aaa
 bbb
 .
 
    aaa
 bbb
    
-.
+````````````````````````````````
 
-.
+
+```````````````````````````````` example
     aaa
 bbb
 .
 
    aaa
 
    
 
    bbb
    
-.
+````````````````````````````````
+
 
 Final spaces are stripped before inline parsing, so a paragraph
 that ends with two or more spaces will not end with a [hard line
 break]:
 
-.
+```````````````````````````````` example
 aaa     
 bbb     
 .
 
    aaa
    
 bbb
    
-.
+````````````````````````````````
+
 
 ## Blank lines
 
-[Blank line]s between block-level elements are ignored,
+[Blank lines] between block-level elements are ignored,
 except for the role they play in determining whether a [list]
 is [tight] or [loose].
 
 Blank lines at the beginning and end of the document are also ignored.
 
-.
+```````````````````````````````` example
   
 
 aaa
@@ -2825,7 +3008,8 @@ aaa
 .
 
    aaa
    
 
    aaa
    
-.
+````````````````````````````````
+
 
 
 # Container blocks
@@ -2850,7 +3034,7 @@ these constructions.  (A recipe is provided below in the section entitled
 
 ## Block quotes
 
-A [block quote marker](@block-quote-marker)
+A [block quote marker](@)
 consists of 0-3 spaces of initial indent, plus (a) the character `>` together
 with a following space, or (b) a single character `>` not followed by a space.
 
@@ -2867,7 +3051,7 @@ The following rules define [block quotes]:
     more lines in which the next [non-whitespace character] after the [block
     quote marker] is [paragraph continuation
     text] is a block quote with *Bs* as its content.
-    [Paragraph continuation text](@paragraph-continuation-text) is text
+    [Paragraph continuation text](@) is text
     that will be parsed as part of the content of a paragraph, but does
     not occur at the beginning of the paragraph.
 
@@ -2878,7 +3062,7 @@ Nothing else counts as a [block quote](#block-quotes).
 
 Here is a simple example:
 
-.
+```````````````````````````````` example
 > # Foo
 > bar
 > baz
@@ -2888,11 +3072,12 @@ Here is a simple example:
 
    bar
 baz
    
 
-.
+````````````````````````````````
+
 
 The spaces after the `>` characters can be omitted:
 
-.
+```````````````````````````````` example
 ># Foo
 >bar
 > baz
@@ -2902,11 +3087,12 @@ The spaces after the `>` characters can be omitted:
 
    bar
 baz
    
 
-.
+````````````````````````````````
+
 
 The `>` characters can be indented 1-3 spaces:
 
-.
+```````````````````````````````` example
    > # Foo
    > bar
  > baz
@@ -2916,11 +3102,12 @@ The `>` characters can be indented 1-3 spaces:
 
    bar
 baz
    
 
-.
+````````````````````````````````
+
 
 Four spaces gives us a code block:
 
-.
+```````````````````````````````` example
     > # Foo
     > bar
     > baz
@@ -2929,12 +3116,13 @@ Four spaces gives us a code block:
 > bar
 > baz
    -. +```````````````````````````````` + The Laziness clause allows us to omit the `>` before a paragraph continuation line: -. +```````````````````````````````` example > # Foo > bar baz @@ -2944,12 +3132,13 @@ baz

    bar baz

    -. +```````````````````````````````` + A block quote can contain some lazy and some non-lazy continuation lines: -. +```````````````````````````````` example > bar baz > foo @@ -2959,10 +3148,11 @@ baz baz foo

    -. +```````````````````````````````` + Laziness only applies to lines that would have been continuations of -paragraphs had they been prepended with [block quote marker]s. +paragraphs had they been prepended with [block quote markers]. For example, the `> ` cannot be omitted in the second line of ``` markdown @@ -2972,7 +3162,7 @@ For example, the `> ` cannot be omitted in the second line of without changing the meaning: -. +```````````````````````````````` example > foo --- . @@ -2980,7 +3170,8 @@ without changing the meaning:

    foo

    -. +```````````````````````````````` + Similarly, if we omit the `> ` in the second line of @@ -2991,7 +3182,7 @@ Similarly, if we omit the `> ` in the second line of then the block quote ends after the first line: -. +```````````````````````````````` example > - foo - bar . @@ -3003,12 +3194,13 @@ then the block quote ends after the first line:
    • bar
    -. +```````````````````````````````` + For the same reason, we can't omit the `> ` in front of subsequent lines of an indented or fenced code block: -. +```````````````````````````````` example > foo bar . @@ -3018,9 +3210,10 @@ subsequent lines of an indented or fenced code block: 
    bar
    -. +```````````````````````````````` -. + +```````````````````````````````` example > ``` foo ``` @@ -3030,12 +3223,13 @@ foo

    foo

    -. +```````````````````````````````` + Note that in the following case, we have a paragraph continuation line: -. +```````````````````````````````` example > foo - bar . @@ -3043,7 +3237,8 @@ continuation line:

    foo - bar

    -. +```````````````````````````````` + To see why, note that in @@ -3058,25 +3253,27 @@ interrupt paragraphs, so it is a [paragraph continuation line]. A block quote can be empty: -. +```````````````````````````````` example > .
    -. +```````````````````````````````` -. + +```````````````````````````````` example > > > .
    -. +```````````````````````````````` + A block quote can have initial or final blank lines: -. +```````````````````````````````` example > > foo > @@ -3084,11 +3281,12 @@ A block quote can have initial or final blank lines:

    foo

    -. +```````````````````````````````` + A blank line always separates block quotes: -. +```````````````````````````````` example > foo > bar @@ -3099,7 +3297,8 @@ A blank line always separates block quotes:

    bar

    -. +```````````````````````````````` + (Most current Markdown implementations, including John Gruber's original `Markdown.pl`, will parse this example as a single block quote @@ -3109,7 +3308,7 @@ whether two block quotes or one are wanted.) Consecutiveness means that if we put these block quotes together, we get a single block quote: -. +```````````````````````````````` example > foo > bar . @@ -3117,11 +3316,12 @@ we get a single block quote:

    foo bar

    -. +```````````````````````````````` + To get a block quote with two paragraphs, use: -. +```````````````````````````````` example > foo > > bar @@ -3130,11 +3330,12 @@ To get a block quote with two paragraphs, use:

    foo

    bar

    -. +```````````````````````````````` + Block quotes can interrupt paragraphs: -. +```````````````````````````````` example foo > bar . @@ -3142,12 +3343,13 @@ foo

    bar

    -. +```````````````````````````````` + In general, blank lines are not needed before or after block quotes: -. +```````````````````````````````` example > aaa *** > bbb @@ -3159,12 +3361,13 @@ quotes:

    bbb

    -. +```````````````````````````````` + However, because of laziness, a blank line is needed between a block quote and a following paragraph: -. +```````````````````````````````` example > bar baz . @@ -3172,9 +3375,10 @@ baz

    bar baz

    -. +```````````````````````````````` -. + +```````````````````````````````` example > bar baz @@ -3183,9 +3387,10 @@ baz

    bar

    baz

    -. +```````````````````````````````` -. + +```````````````````````````````` example > bar > baz @@ -3194,13 +3399,14 @@ baz

    bar

    baz

    -. +```````````````````````````````` + It is a consequence of the Laziness rule that any number of initial `>`s may be omitted on a continuation line of a nested block quote: -. +```````````````````````````````` example > > > foo bar . @@ -3212,9 +3418,10 @@ bar

    -. +```````````````````````````````` -. + +```````````````````````````````` example >>> foo > bar >>baz @@ -3228,14 +3435,15 @@ baz

    -. +```````````````````````````````` + When including an indented code block in a block quote, remember that the [block quote marker] includes both the `>` and a following space. So *five spaces* are needed after the `>`: -. +```````````````````````````````` example > code > not code @@ -3247,18 +3455,19 @@ the `>`:

    not code

    -. +```````````````````````````````` + ## List items -A [list marker](@list-marker) is a +A [list marker](@) is a [bullet list marker] or an [ordered list marker]. -A [bullet list marker](@bullet-list-marker) +A [bullet list marker](@) is a `-`, `+`, or `*` character. -An [ordered list marker](@ordered-list-marker) +An [ordered list marker](@) is a sequence of 1--9 arabic digits (`0-9`), followed by either a `.` character or a `)` character. (The reason for the length limit is that with 10 digits we start seeing integer overflows @@ -3279,7 +3488,7 @@ The following rules define [list items]: For example, let *Ls* be the lines -. +```````````````````````````````` example A paragraph with two lines. @@ -3294,13 +3503,14 @@ with two lines.

    A block quote.

    -. +```````````````````````````````` + And let *M* be the marker `1.`, and *N* = 2. Then rule #1 says that the following is an ordered list item with start number 1, and the same contents as *Ls*: -. +```````````````````````````````` example 1. A paragraph with two lines. @@ -3319,7 +3529,8 @@ with two lines.

    -. +```````````````````````````````` + The most important thing to notice is that the position of the text after the list marker determines how much indentation @@ -3332,7 +3543,7 @@ item. Here are some examples showing how far content must be indented to be put under the list item: -. +```````````````````````````````` example - one two @@ -3341,9 +3552,10 @@ put under the list item:
  • one

    • two

    -. +```````````````````````````````` -. + +```````````````````````````````` example - one two @@ -3354,9 +3566,10 @@ put under the list item:

    two

    -. +```````````````````````````````` -. + +```````````````````````````````` example - one two @@ -3366,9 +3579,10 @@ put under the list item: 
     two
    -. +```````````````````````````````` -. + +```````````````````````````````` example - one two @@ -3379,7 +3593,8 @@ put under the list item:

    two

    -. +```````````````````````````````` + It is tempting to think of this in terms of columns: the continuation blocks must be indented at least to the column of the first @@ -3389,7 +3604,7 @@ is needed. Which column this indentation reaches will depend on how the list item is embedded in other constructions, as shown by this example: -. +```````````````````````````````` example > > 1. one >> >> two @@ -3404,7 +3619,8 @@ this example: -. +```````````````````````````````` + Here `two` occurs in the same column as the list marker `1.`, but is actually contained in the list item, because there is @@ -3415,7 +3631,7 @@ occurs far to the right of the initial text of the list item, `one`, but it is not considered part of the list item, because it is not indented far enough past the blockquote marker: -. +```````````````````````````````` example >>- one >> > > two @@ -3428,25 +3644,27 @@ far enough past the blockquote marker:

    two

    -. +```````````````````````````````` + Note that at least one space is needed between the list marker and any following content, so these are not list items: -. +```````````````````````````````` example -one 2.two .

    -one

    2.two

    -. +```````````````````````````````` + A list item may not contain blocks that are separated by more than one blank line. Thus, two blank lines will end a list, unless the two blanks are contained in a [fenced code block]. -. +```````````````````````````````` example - foo bar @@ -3503,11 +3721,12 @@ bar -. +```````````````````````````````` + A list item may contain any kind of block: -. +```````````````````````````````` example 1. foo ``` @@ -3529,14 +3748,15 @@ A list item may contain any kind of block: -. +```````````````````````````````` + A list item that contains an indented code block will preserve empty lines within the code block verbatim, unless there are two or more empty lines in a row (since as described above, two blank lines end the list): -. +```````````````````````````````` example - Foo bar @@ -3552,9 +3772,10 @@ baz -. +```````````````````````````````` -. + +```````````````````````````````` example - Foo bar @@ -3571,49 +3792,55 @@ baz 
      baz
    -. +```````````````````````````````` + Note that ordered list start numbers must be nine digits or less: -. +```````````````````````````````` example 123456789. ok .
    1. ok
    -. +```````````````````````````````` -. + +```````````````````````````````` example 1234567890. not ok .

    1234567890. not ok

    -. +```````````````````````````````` + A start number may begin with 0s: -. +```````````````````````````````` example 0. ok .
    1. ok
    -. +```````````````````````````````` -. + +```````````````````````````````` example 003. ok .
    1. ok
    -. +```````````````````````````````` + A start number may not be negative: -. +```````````````````````````````` example -1. not ok .

    -1. not ok

    -. +```````````````````````````````` + 2. **Item starting with indented code.** If a sequence of lines *Ls* @@ -3632,7 +3859,7 @@ An indented code block will have to be indented four spaces beyond the edge of the region where text will be included in the list item. In the following case that is 6 spaces: -. +```````````````````````````````` example - foo bar @@ -3644,11 +3871,12 @@ In the following case that is 6 spaces: -. +```````````````````````````````` + And in this case it is 11 spaces: -. +```````````````````````````````` example 10. foo bar @@ -3660,13 +3888,14 @@ And in this case it is 11 spaces: -. +```````````````````````````````` + If the *first* block in the list item is an indented code block, then by rule #2, the contents must be indented *one* space after the list marker: -. +```````````````````````````````` example indented code paragraph @@ -3678,9 +3907,10 @@ paragraph

    paragraph

    more code
    -. +```````````````````````````````` -. + +```````````````````````````````` example 1. indented code paragraph @@ -3696,12 +3926,13 @@ paragraph -. +```````````````````````````````` + Note that an additional space indent is interpreted as space inside the code block: -. +```````````````````````````````` example 1. indented code paragraph @@ -3717,7 +3948,8 @@ inside the code block: -. +```````````````````````````````` + Note that rules #1 and #2 only apply to two cases: (a) cases in which the lines to be included in a list item begin with a @@ -3727,16 +3959,17 @@ block. In a case like the following, where the first block begins with a three-space indent, the rules do not allow us to form a list item by indenting the whole thing and prepending a list marker: -. +```````````````````````````````` example foo bar .

    foo

    bar

    -. +```````````````````````````````` -. + +```````````````````````````````` example - foo bar @@ -3745,14 +3978,15 @@ bar
  • foo

    • bar

    -. +```````````````````````````````` + This is not a significant restriction, because when a block begins with 1-3 spaces indent, the indentation can always be removed without a change in interpretation, allowing rule #1 to be applied. So, in the above case: -. +```````````````````````````````` example - foo bar @@ -3763,7 +3997,8 @@ the above case:

    bar

    -. +```````````````````````````````` + 3. **Item starting with a blank line.** If a sequence of lines *Ls* starting with a single [blank line] constitute a (possibly empty) @@ -3779,7 +4014,7 @@ the above case: Here are some list items that start with a blank line but are not empty: -. +```````````````````````````````` example - foo - @@ -3800,13 +4035,14 @@ Here are some list items that start with a blank line but are not empty: -. +```````````````````````````````` + A list item can begin with at most one blank line. In the following example, `foo` is not part of the list item: -. +```````````````````````````````` example - foo @@ -3815,11 +4051,12 @@ item:

  • foo

    -. +```````````````````````````````` + Here is an empty bullet list item: -. +```````````````````````````````` example - foo - - bar @@ -3829,11 +4066,12 @@ Here is an empty bullet list item:
  • bar
    • -. +```````````````````````````````` + It does not matter whether there are spaces following the [list marker]: -. +```````````````````````````````` example - foo - - bar @@ -3843,11 +4081,12 @@ It does not matter whether there are spaces following the [list marker]:
  • bar
    • -. +```````````````````````````````` + Here is an empty ordered list item: -. +```````````````````````````````` example 1. foo 2. 3. bar @@ -3857,17 +4096,19 @@ Here is an empty ordered list item:
  • bar
    • -. +```````````````````````````````` + A list may start or end with an empty list item: -. +```````````````````````````````` example * .
    -. +```````````````````````````````` + 4. **Indentation.** If a sequence of lines *Ls* constitutes a list item @@ -3878,7 +4119,7 @@ A list may start or end with an empty list item: Indented one space: -. +```````````````````````````````` example 1. A paragraph with two lines. @@ -3897,11 +4138,12 @@ with two lines.

    -. +```````````````````````````````` + Indented two spaces: -. +```````````````````````````````` example 1. A paragraph with two lines. @@ -3920,11 +4162,12 @@ with two lines.

    -. +```````````````````````````````` + Indented three spaces: -. +```````````````````````````````` example 1. A paragraph with two lines. @@ -3943,11 +4186,12 @@ with two lines.

    -. +```````````````````````````````` + Four spaces indent gives a code block: -. +```````````````````````````````` example 1. A paragraph with two lines. @@ -3962,7 +4206,8 @@ Four spaces indent gives a code block: > A block quote. -. +```````````````````````````````` + 5. **Laziness.** If a string of lines *Ls* constitute a [list @@ -3972,11 +4217,11 @@ Four spaces indent gives a code block: [paragraph continuation text] is a list item with the same contents and attributes. The unindented lines are called - [lazy continuation line](@lazy-continuation-line)s. + [lazy continuation line](@)s. -Here is an example with [lazy continuation line]s: +Here is an example with [lazy continuation lines]: -. +```````````````````````````````` example 1. A paragraph with two lines. @@ -3995,11 +4240,12 @@ with two lines.

    -. +```````````````````````````````` + Indentation can be partially deleted: -. +```````````````````````````````` example 1. A paragraph with two lines. . @@ -4007,11 +4253,12 @@ Indentation can be partially deleted:
  • A paragraph with two lines.
    • -. +```````````````````````````````` + These examples show how laziness can work in nested structures: -. +```````````````````````````````` example > 1. > Blockquote continued here. . @@ -4025,9 +4272,10 @@ continued here.

    -. +```````````````````````````````` -. + +```````````````````````````````` example > 1. > Blockquote > continued here. . @@ -4041,7 +4289,8 @@ continued here.

    -. +```````````````````````````````` + 6. **That's all.** Nothing that is not counted as a list item by rules @@ -4053,7 +4302,7 @@ in order to be included in the list item. So, in this case we need two spaces indent: -. +```````````````````````````````` example - foo - bar - baz @@ -4069,11 +4318,12 @@ So, in this case we need two spaces indent: -. +```````````````````````````````` + One is not enough: -. +```````````````````````````````` example - foo - bar - baz @@ -4083,11 +4333,12 @@ One is not enough:
  • bar
  • baz
    • -. +```````````````````````````````` + Here we need four, because the list marker is wider: -. +```````````````````````````````` example 10) foo - bar . @@ -4098,11 +4349,12 @@ Here we need four, because the list marker is wider: -. +```````````````````````````````` + Three is not enough: -. +```````````````````````````````` example 10) foo - bar . @@ -4112,11 +4364,12 @@ Three is not enough:
    • bar
    -. +```````````````````````````````` + A list may be the first block in a list item: -. +```````````````````````````````` example - - foo .
      @@ -4126,9 +4379,10 @@ A list may be the first block in a list item:
    -. +```````````````````````````````` -. + +```````````````````````````````` example 1. - 2. foo .
      @@ -4142,11 +4396,12 @@ A list may be the first block in a list item:
    -. +```````````````````````````````` + A list item can contain a heading: -. +```````````````````````````````` example - # Foo - Bar --- @@ -4160,7 +4415,8 @@ A list item can contain a heading:

    Bar

    baz -. +```````````````````````````````` + ### Motivation @@ -4350,39 +4606,39 @@ takes four spaces (a common case), but diverge in other cases. ## Lists -A [list](@list) is a sequence of one or more +A [list](@) is a sequence of one or more list items [of the same type]. The list items may be separated by single [blank lines], but two blank lines end all containing lists. -Two list items are [of the same type](@of-the-same-type) +Two list items are [of the same type](@) if they begin with a [list marker] of the same type. Two list markers are of the same type if (a) they are bullet list markers using the same character (`-`, `+`, or `*`) or (b) they are ordered list numbers with the same delimiter (either `.` or `)`). -A list is an [ordered list](@ordered-list) +A list is an [ordered list](@) if its constituent list items begin with -[ordered list marker]s, and a -[bullet list](@bullet-list) if its constituent list -items begin with [bullet list marker]s. +[ordered list markers], and a +[bullet list](@) if its constituent list +items begin with [bullet list markers]. -The [start number](@start-number) +The [start number](@) of an [ordered list] is determined by the list number of its initial list item. The numbers of subsequent list items are disregarded. -A list is [loose](@loose) if any of its constituent +A list is [loose](@) if any of its constituent list items are separated by blank lines, or if any of its constituent list items directly contain two block-level elements with a blank line -between them. Otherwise a list is [tight](@tight). +between them. Otherwise a list is [tight](@). (The difference in HTML output is that paragraphs in a loose list are wrapped in `

    ` tags, while paragraphs in a tight list are not.) Changing the bullet or ordered list delimiter starts a new list: -. +```````````````````````````````` example - foo - bar + baz @@ -4394,9 +4650,10 @@ Changing the bullet or ordered list delimiter starts a new list:

    • baz
    -. +```````````````````````````````` -. + +```````````````````````````````` example 1. foo 2. bar 3) baz @@ -4408,13 +4665,14 @@ Changing the bullet or ordered list delimiter starts a new list:
    1. baz
    -. +```````````````````````````````` + In CommonMark, a list can interrupt a paragraph. That is, no blank line is needed to separate a paragraph from a following list: -. +```````````````````````````````` example Foo - bar - baz @@ -4424,12 +4682,13 @@ Foo
  • bar
  • baz
    • -. +```````````````````````````````` + `Markdown.pl` does not allow this, through fear of triggering a list via a numeral in a hard-wrapped line: -. +```````````````````````````````` example The number of windows in my house is 14. The number of doors is 6. . @@ -4437,7 +4696,8 @@ The number of windows in my house is
    1. The number of doors is 6.
    -. +```````````````````````````````` + Oddly, `Markdown.pl` *does* allow a blockquote to interrupt a paragraph, even though the same considerations might apply. We think that the two @@ -4454,7 +4714,7 @@ blank lines: Second, we are attracted to a -> [principle of uniformity](@principle-of-uniformity): +> [principle of uniformity](@): > if a chunk of text has a certain > meaning, it will continue to have the same meaning when put into a > container block (such as a list item or blockquote). @@ -4494,7 +4754,7 @@ seems more consistent with established practice with Markdown. There can be blank lines between items, but two blank lines end a list: -. +```````````````````````````````` example - foo - bar @@ -4513,13 +4773,14 @@ a list:
    • baz
    -. +```````````````````````````````` + As illustrated above in the section on [list items], two blank lines between blocks *within* a list item will also end a list: -. +```````````````````````````````` example - foo @@ -4533,11 +4794,12 @@ list:
    • baz
    -. +```````````````````````````````` + Indeed, two blank lines will end *all* containing lists: -. +```````````````````````````````` example - foo - bar - baz @@ -4558,14 +4820,15 @@ Indeed, two blank lines will end *all* containing lists: 
      bim
    -. +```````````````````````````````` + Thus, two blank lines can be used to separate consecutive lists of the same type, or to separate a list from an indented code block that would otherwise be parsed as a subparagraph of the final list item: -. +```````````````````````````````` example - foo - bar @@ -4581,9 +4844,10 @@ item:
  • baz
  • bim
    • -. +```````````````````````````````` -. + +```````````````````````````````` example - foo notcode @@ -4604,14 +4868,15 @@ item: 
    code
    -. +```````````````````````````````` + List items need not be indented to the same level. The following list items will be treated as items at the same list level, since none is indented enough to belong to the previous list item: -. +```````````````````````````````` example - a - b - c @@ -4633,9 +4898,10 @@ item:
  • h
  • i
    • -. +```````````````````````````````` -. + +```````````````````````````````` example 1. a 2. b @@ -4653,12 +4919,13 @@ item:

    c

    -. +```````````````````````````````` + This is a loose list, because there is a blank line between two of the list items: -. +```````````````````````````````` example - a - b @@ -4675,11 +4942,12 @@ two of the list items:

    c

    -. +```````````````````````````````` + So is this, with a empty second item: -. +```````````````````````````````` example * a * @@ -4694,13 +4962,14 @@ So is this, with a empty second item:

    c

    -. +```````````````````````````````` + These are loose lists, even though there is no space between the items, because one of the items directly contains two block-level elements with a blank line between them: -. +```````````````````````````````` example - a - b @@ -4719,9 +4988,10 @@ with a blank line between them:

    d

    -. +```````````````````````````````` -. + +```````````````````````````````` example - a - b @@ -4739,11 +5009,12 @@ with a blank line between them:

    d

    -. +```````````````````````````````` + This is a tight list, because the blank lines are in a code block: -. +```````````````````````````````` example - a - ``` b @@ -4762,13 +5033,14 @@ This is a tight list, because the blank lines are in a code block:
  • c
    • -. +```````````````````````````````` + This is a tight list, because the blank line is between two paragraphs of a sublist. So the sublist is loose while the outer list is tight: -. +```````````````````````````````` example - a - b @@ -4786,12 +5058,13 @@ the outer list is tight:
  • d
    • -. +```````````````````````````````` + This is a tight list, because the blank line is inside the block quote: -. +```````````````````````````````` example * a > b > @@ -4805,12 +5078,13 @@ block quote:
  • c
    • -. +```````````````````````````````` + This list is tight, because the consecutive block elements are not separated by blank lines: -. +```````````````````````````````` example - a > b ``` @@ -4828,19 +5102,21 @@ are not separated by blank lines:
  • d
    • -. +```````````````````````````````` + A single-paragraph list is tight: -. +```````````````````````````````` example - a .
    • a
    -. +```````````````````````````````` -. + +```````````````````````````````` example - a - b . @@ -4851,12 +5127,13 @@ A single-paragraph list is tight: -. +```````````````````````````````` + This list is loose, because of the blank line between the two block elements in the list item: -. +```````````````````````````````` example 1. ``` foo ``` @@ -4870,11 +5147,12 @@ two block elements in the list item:

    bar

    -. +```````````````````````````````` + Here the outer list is loose, the inner list tight: -. +```````````````````````````````` example * foo * bar @@ -4889,9 +5167,10 @@ Here the outer list is loose, the inner list tight:

    baz

    -. +```````````````````````````````` -. + +```````````````````````````````` example - a - b - c @@ -4916,7 +5195,8 @@ Here the outer list is loose, the inner list tight: -. +```````````````````````````````` + # Inlines @@ -4924,11 +5204,12 @@ Inlines are parsed sequentially from the beginning of the character stream to the end (left to right, in left-to-right languages). Thus, for example, in -. +```````````````````````````````` example `hi`lo` .

    hilo`

    -. +```````````````````````````````` + `hi` is parsed as code, leaving the backtick at the end as a literal backtick. @@ -4937,25 +5218,27 @@ backtick. Any ASCII punctuation character may be backslash-escaped: -. +```````````````````````````````` example \!\"\#\$\%\&\'\(\)\*\+\,\-\.\/\:\;\<\=\>\?\@\[\\\]\^\_\`\{\|\}\~ .

    !"#$%&'()*+,-./:;<=>?@[\]^_`{|}~

    -. +```````````````````````````````` + Backslashes before other characters are treated as literal backslashes: -. +```````````````````````````````` example \→\A\a\ \3\φ\« .

    \→\A\a\ \3\φ\«

    -. +```````````````````````````````` + Escaped characters are treated as regular characters and do not have their usual Markdown meanings: -. +```````````````````````````````` example \*not emphasized* \
    not a tag \[not a link](/foo) @@ -4973,88 +5256,99 @@ not have their usual Markdown meanings: * not a list # not a heading [foo]: /url "not a reference"

    -. +```````````````````````````````` + If a backslash is itself escaped, the following character is not: -. +```````````````````````````````` example \\*emphasis* .

    \emphasis

    -. +```````````````````````````````` + A backslash at the end of the line is a [hard line break]: -. +```````````````````````````````` example foo\ bar .

    foo
    bar

    -. +```````````````````````````````` + Backslash escapes do not work in code blocks, code spans, autolinks, or raw HTML: -. +```````````````````````````````` example `` \[\` `` .

    \[\`

    -. +```````````````````````````````` -. + +```````````````````````````````` example \[\] . 
    \[\]
    -. +```````````````````````````````` -. + +```````````````````````````````` example ~~~ \[\] ~~~ . 
    \[\]
    -. +```````````````````````````````` -. + +```````````````````````````````` example .

    http://example.com?find=\*

    -. +```````````````````````````````` -. + +```````````````````````````````` example . -. +```````````````````````````````` + But they work in all other contexts, including URLs and link titles, -link references, and [info string]s in [fenced code block]s: +link references, and [info strings] in [fenced code blocks]: -. +```````````````````````````````` example [foo](/bar\* "ti\*tle") .

    foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example [foo] [foo]: /bar\* "ti\*tle" .

    foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example ``` foo\+bar foo ``` . 
    foo
    -. +```````````````````````````````` + ## Entity and numeric character references @@ -5067,13 +5361,13 @@ need not store information about whether a particular character was represented in the source using a Unicode character or an entity reference. -[Entity references](@entity-references) consist of `&` + any of the valid +[Entity references](@) consist of `&` + any of the valid HTML5 entity names + `;`. The document is used as an authoritative source for the valid entity references and their corresponding code points. -. +```````````````````````````````` example   & © Æ Ď ¾ ℋ ⅆ ∲ ≧̸ @@ -5081,176 +5375,193 @@ references and their corresponding code points.

      & © Æ Ď ¾ ℋ ⅆ ∲ ≧̸

    -. +```````````````````````````````` + [Decimal numeric character -references](@decimal-numeric-character-references) +references](@) consist of `&#` + a string of 1--8 arabic digits + `;`. A numeric character reference is parsed as the corresponding Unicode character. Invalid Unicode code points will be replaced by the REPLACEMENT CHARACTER (`U+FFFD`). For security reasons, the code point `U+0000` will also be replaced by `U+FFFD`. -. +```````````````````````````````` example # Ӓ Ϡ � � .

    # Ӓ Ϡ � �

    -. +```````````````````````````````` + [Hexadecimal numeric character -references](@hexadecimal-numeric-character-references) consist of `&#` + +references](@) consist of `&#` + either `X` or `x` + a string of 1-8 hexadecimal digits + `;`. They too are parsed as the corresponding Unicode character (this time specified with a hexadecimal numeral instead of decimal). -. +```````````````````````````````` example " ആ ಫ .

    " ആ ಫ

    -. +```````````````````````````````` + Here are some nonentities: -. +```````````````````````````````` example   &x; &#; &#x; &ThisIsNotDefined; &hi?; .

    &nbsp &x; &#; &#x; &ThisIsNotDefined; &hi?;

    -. +```````````````````````````````` + Although HTML5 does accept some entity references without a trailing semicolon (such as `©`), these are not recognized here, because it makes the grammar too ambiguous: -. +```````````````````````````````` example © .

    &copy

    -. +```````````````````````````````` + Strings that are not on the list of HTML5 named entities are not recognized as entity references either: -. +```````````````````````````````` example &MadeUpEntity; .

    &MadeUpEntity;

    -. +```````````````````````````````` + Entity and numeric character references are recognized in any context besides code spans or code blocks, including -URLs, [link title]s, and [fenced code block][] [info string]s: +URLs, [link titles], and [fenced code block][] [info strings]: -. +```````````````````````````````` example . -. +```````````````````````````````` -. + +```````````````````````````````` example [foo](/föö "föö") .

    foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example [foo] [foo]: /föö "föö" .

    foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example ``` föö foo ``` . 
    foo
    -. +```````````````````````````````` + Entity and numeric character references are treated as literal text in code spans and code blocks: -. +```````````````````````````````` example `föö` .

    f&ouml;&ouml;

    -. +```````````````````````````````` -. + +```````````````````````````````` example föfö . 
    f&ouml;f&ouml;
    -. +```````````````````````````````` + ## Code spans -A [backtick string](@backtick-string) +A [backtick string](@) is a string of one or more backtick characters (`` ` ``) that is neither preceded nor followed by a backtick. -A [code span](@code-span) begins with a backtick string and ends with +A [code span](@) begins with a backtick string and ends with a backtick string of equal length. The contents of the code span are the characters between the two backtick strings, with leading and -trailing spaces and [line ending]s removed, and +trailing spaces and [line endings] removed, and [whitespace] collapsed to single spaces. This is a simple code span: -. +```````````````````````````````` example `foo` .

    foo

    -. +```````````````````````````````` + Here two backticks are used, because the code contains a backtick. This example also illustrates stripping of leading and trailing spaces: -. +```````````````````````````````` example `` foo ` bar `` .

    foo ` bar

    -. +```````````````````````````````` + This example shows the motivation for stripping leading and trailing spaces: -. +```````````````````````````````` example ` `` ` .

    ``

    -. +```````````````````````````````` -[Line ending]s are treated like spaces: -. +[Line endings] are treated like spaces: + +```````````````````````````````` example `` foo `` .

    foo

    -. +```````````````````````````````` + -Interior spaces and [line ending]s are collapsed into +Interior spaces and [line endings] are collapsed into single spaces, just as they would be by a browser: -. +```````````````````````````````` example `foo bar baz` .

    foo bar baz

    -. +```````````````````````````````` + Q: Why not just leave the spaces, since browsers will collapse them anyway? A: Because we might be targeting a non-HTML format, and we shouldn't rely on HTML-specific rendering assumptions. (Existing implementations differ in their treatment of internal -spaces and [line ending]s. Some, including `Markdown.pl` and +spaces and [line endings]. Some, including `Markdown.pl` and `showdown`, convert an internal [line ending] into a `
    ` tag. But this makes things difficult for those who like to hard-wrap their paragraphs, since a line break in the midst of a code @@ -5258,20 +5569,22 @@ span will cause an unintended line break in the output. Others just leave internal spaces as they are, which is fine if only HTML is being targeted.) -. +```````````````````````````````` example `foo `` bar` .

    foo `` bar

    -. +```````````````````````````````` + Note that backslash escapes do not work in code spans. All backslashes are treated literally: -. +```````````````````````````````` example `foo\`bar` .

    foo\bar`

    -. +```````````````````````````````` + Backslash escapes are never needed, because one can always choose a string of *n* backtick characters as delimiters, where the code does @@ -5282,67 +5595,75 @@ constructs except HTML tags and autolinks. Thus, for example, this is not parsed as emphasized text, since the second `*` is part of a code span: -. +```````````````````````````````` example *foo`*` .

    *foo*

    -. +```````````````````````````````` + And this is not parsed as a link: -. +```````````````````````````````` example [not a `link](/foo`) .

    [not a link](/foo)

    -. +```````````````````````````````` + Code spans, HTML tags, and autolinks have the same precedence. Thus, this is code: -. +```````````````````````````````` example `` .

    <a href="">`

    -. +```````````````````````````````` + But this is an HTML tag: -. +```````````````````````````````` example     ` .

    `

    -. +```````````````````````````````` + And this is code: -. +```````````````````````````````` example `` .

    <http://foo.bar.baz>`

    -. +```````````````````````````````` + But this is an autolink: -. +```````````````````````````````` example ` .

    http://foo.bar.`baz`

    -. +```````````````````````````````` + When a backtick string is not closed by a matching backtick string, we just have literal backticks: -. +```````````````````````````````` example ```foo`` .

    ```foo``

    -. +```````````````````````````````` -. + +```````````````````````````````` example `foo .

    `foo

    -. +```````````````````````````````` + ## Emphasis and strong emphasis @@ -5390,19 +5711,19 @@ no emphasis: foo_bar_baz The rules given below capture all of these patterns, while allowing for efficient parsing strategies that do not backtrack. -First, some definitions. A [delimiter run](@delimiter-run) is either +First, some definitions. A [delimiter run](@) is either a sequence of one or more `*` characters that is not preceded or followed by a `*` character, or a sequence of one or more `_` characters that is not preceded or followed by a `_` character. -A [left-flanking delimiter run](@left-flanking-delimiter-run) is +A [left-flanking delimiter run](@) is a [delimiter run] that is (a) not followed by [Unicode whitespace], and (b) either not followed by a [punctuation character], or preceded by [Unicode whitespace] or a [punctuation character]. For purposes of this definition, the beginning and the end of the line count as Unicode whitespace. -A [right-flanking delimiter run](@right-flanking-delimiter-run) is +A [right-flanking delimiter run](@) is a [delimiter run] that is (a) not preceded by [Unicode whitespace], and (b) either not preceded by a [punctuation character], or followed by [Unicode whitespace] or a [punctuation character]. @@ -5453,7 +5774,7 @@ are a bit more complex than the ones given here.) The following rules define emphasis and strong emphasis: -1. A single `*` character [can open emphasis](@can-open-emphasis) +1. A single `*` character [can open emphasis](@) iff (if and only if) it is part of a [left-flanking delimiter run]. 2. A single `_` character [can open emphasis] iff @@ -5462,7 +5783,7 @@ The following rules define emphasis and strong emphasis: or (b) part of a [right-flanking delimiter run] preceded by punctuation. -3. A single `*` character [can close emphasis](@can-close-emphasis) +3. A single `*` character [can close emphasis](@) iff it is part of a [right-flanking delimiter run]. 4. A single `_` character [can close emphasis] iff @@ -5471,7 +5792,7 @@ The following rules define emphasis and strong emphasis: or (b) part of a [left-flanking delimiter run] followed by punctuation. -5. A double `**` [can open strong emphasis](@can-open-strong-emphasis) +5. A double `**` [can open strong emphasis](@) iff it is part of a [left-flanking delimiter run]. 6. A double `__` [can open strong emphasis] iff @@ -5480,7 +5801,7 @@ The following rules define emphasis and strong emphasis: or (b) part of a [right-flanking delimiter run] preceded by punctuation. -7. A double `**` [can close strong emphasis](@can-close-strong-emphasis) +7. A double `**` [can close strong emphasis](@) iff it is part of a [right-flanking delimiter run]. 8. A double `__` [can close strong emphasis] @@ -5547,141 +5868,157 @@ These rules can be illustrated through a series of examples. Rule 1: -. +```````````````````````````````` example *foo bar* .

    foo bar

    -. +```````````````````````````````` + This is not emphasis, because the opening `*` is followed by whitespace, and hence not part of a [left-flanking delimiter run]: -. +```````````````````````````````` example a * foo bar* .

    a * foo bar*

    -. +```````````````````````````````` + This is not emphasis, because the opening `*` is preceded by an alphanumeric and followed by punctuation, and hence not part of a [left-flanking delimiter run]: -. +```````````````````````````````` example a*"foo"* .

    a*"foo"*

    -. +```````````````````````````````` + Unicode nonbreaking spaces count as whitespace, too: -. +```````````````````````````````` example * a * .

    * a *

    -. +```````````````````````````````` + Intraword emphasis with `*` is permitted: -. +```````````````````````````````` example foo*bar* .

    foobar

    -. +```````````````````````````````` -. + +```````````````````````````````` example 5*6*78 .

    5678

    -. +```````````````````````````````` + Rule 2: -. +```````````````````````````````` example _foo bar_ .

    foo bar

    -. +```````````````````````````````` + This is not emphasis, because the opening `_` is followed by whitespace: -. +```````````````````````````````` example _ foo bar_ .

    _ foo bar_

    -. +```````````````````````````````` + This is not emphasis, because the opening `_` is preceded by an alphanumeric and followed by punctuation: -. +```````````````````````````````` example a_"foo"_ .

    a_"foo"_

    -. +```````````````````````````````` + Emphasis with `_` is not allowed inside words: -. +```````````````````````````````` example foo_bar_ .

    foo_bar_

    -. +```````````````````````````````` -. + +```````````````````````````````` example 5_6_78 .

    5_6_78

    -. +```````````````````````````````` -. + +```````````````````````````````` example пристаням_стремятся_ .

    пристаням_стремятся_

    -. +```````````````````````````````` + Here `_` does not generate emphasis, because the first delimiter run is right-flanking and the second left-flanking: -. +```````````````````````````````` example aa_"bb"_cc .

    aa_"bb"_cc

    -. +```````````````````````````````` + This is emphasis, even though the opening delimiter is both left- and right-flanking, because it is preceded by punctuation: -. +```````````````````````````````` example foo-_(bar)_ .

    foo-(bar)

    -. +```````````````````````````````` + Rule 3: This is not emphasis, because the closing delimiter does not match the opening delimiter: -. +```````````````````````````````` example _foo* .

    _foo*

    -. +```````````````````````````````` + This is not emphasis, because the closing `*` is preceded by whitespace: -. +```````````````````````````````` example *foo bar * .

    *foo bar *

    -. +```````````````````````````````` + A newline also counts as whitespace: -. +```````````````````````````````` example *foo bar * . @@ -5689,34 +6026,38 @@ A newline also counts as whitespace:
    -. +```````````````````````````````` + This is not emphasis, because the second `*` is preceded by punctuation and followed by an alphanumeric (hence it is not part of a [right-flanking delimiter run]: -. +```````````````````````````````` example *(*foo) .

    *(*foo)

    -. +```````````````````````````````` + The point of this restriction is more easily appreciated with this example: -. +```````````````````````````````` example *(*foo*)* .

    (foo)

    -. +```````````````````````````````` + Intraword emphasis with `*` is allowed: -. +```````````````````````````````` example *foo*bar .

    foobar

    -. +```````````````````````````````` + Rule 4: @@ -5724,164 +6065,184 @@ Rule 4: This is not emphasis, because the closing `_` is preceded by whitespace: -. +```````````````````````````````` example _foo bar _ .

    _foo bar _

    -. +```````````````````````````````` + This is not emphasis, because the second `_` is preceded by punctuation and followed by an alphanumeric: -. +```````````````````````````````` example _(_foo) .

    _(_foo)

    -. +```````````````````````````````` + This is emphasis within emphasis: -. +```````````````````````````````` example _(_foo_)_ .

    (foo)

    -. +```````````````````````````````` + Intraword emphasis is disallowed for `_`: -. +```````````````````````````````` example _foo_bar .

    _foo_bar

    -. +```````````````````````````````` -. + +```````````````````````````````` example _пристаням_стремятся .

    _пристаням_стремятся

    -. +```````````````````````````````` -. + +```````````````````````````````` example _foo_bar_baz_ .

    foo_bar_baz

    -. +```````````````````````````````` + This is emphasis, even though the closing delimiter is both left- and right-flanking, because it is followed by punctuation: -. +```````````````````````````````` example _(bar)_. .

    (bar).

    -. +```````````````````````````````` + Rule 5: -. +```````````````````````````````` example **foo bar** .

    foo bar

    -. +```````````````````````````````` + This is not strong emphasis, because the opening delimiter is followed by whitespace: -. +```````````````````````````````` example ** foo bar** .

    ** foo bar**

    -. +```````````````````````````````` + This is not strong emphasis, because the opening `**` is preceded by an alphanumeric and followed by punctuation, and hence not part of a [left-flanking delimiter run]: -. +```````````````````````````````` example a**"foo"** .

    a**"foo"**

    -. +```````````````````````````````` + Intraword strong emphasis with `**` is permitted: -. +```````````````````````````````` example foo**bar** .

    foobar

    -. +```````````````````````````````` + Rule 6: -. +```````````````````````````````` example __foo bar__ .

    foo bar

    -. +```````````````````````````````` + This is not strong emphasis, because the opening delimiter is followed by whitespace: -. +```````````````````````````````` example __ foo bar__ .

    __ foo bar__

    -. +```````````````````````````````` + A newline counts as whitespace: -. +```````````````````````````````` example __ foo bar__ .

    __ foo bar__

    -. +```````````````````````````````` + This is not strong emphasis, because the opening `__` is preceded by an alphanumeric and followed by punctuation: -. +```````````````````````````````` example a__"foo"__ .

    a__"foo"__

    -. +```````````````````````````````` + Intraword strong emphasis is forbidden with `__`: -. +```````````````````````````````` example foo__bar__ .

    foo__bar__

    -. +```````````````````````````````` -. + +```````````````````````````````` example 5__6__78 .

    5__6__78

    -. +```````````````````````````````` -. + +```````````````````````````````` example пристаням__стремятся__ .

    пристаням__стремятся__

    -. +```````````````````````````````` -. + +```````````````````````````````` example __foo, __bar__, baz__ .

    foo, bar, baz

    -. +```````````````````````````````` + This is strong emphasis, even though the opening delimiter is both left- and right-flanking, because it is preceded by punctuation: -. +```````````````````````````````` example foo-__(bar)__ .

    foo-(bar)

    -. +```````````````````````````````` + Rule 7: @@ -5889,11 +6250,12 @@ Rule 7: This is not strong emphasis, because the closing delimiter is preceded by whitespace: -. +```````````````````````````````` example **foo bar ** .

    **foo bar **

    -. +```````````````````````````````` + (Nor can it be interpreted as an emphasized `*foo bar *`, because of Rule 11.) @@ -5901,215 +6263,242 @@ Rule 11.) This is not strong emphasis, because the second `**` is preceded by punctuation and followed by an alphanumeric: -. +```````````````````````````````` example **(**foo) .

    **(**foo)

    -. +```````````````````````````````` + The point of this restriction is more easily appreciated with these examples: -. +```````````````````````````````` example *(**foo**)* .

    (foo)

    -. +```````````````````````````````` -. + +```````````````````````````````` example **Gomphocarpus (*Gomphocarpus physocarpus*, syn. *Asclepias physocarpa*)** .

    Gomphocarpus (Gomphocarpus physocarpus, syn. Asclepias physocarpa)

    -. +```````````````````````````````` -. + +```````````````````````````````` example **foo "*bar*" foo** .

    foo "bar" foo

    -. +```````````````````````````````` + Intraword emphasis: -. +```````````````````````````````` example **foo**bar .

    foobar

    -. +```````````````````````````````` + Rule 8: This is not strong emphasis, because the closing delimiter is preceded by whitespace: -. +```````````````````````````````` example __foo bar __ .

    __foo bar __

    -. +```````````````````````````````` + This is not strong emphasis, because the second `__` is preceded by punctuation and followed by an alphanumeric: -. +```````````````````````````````` example __(__foo) .

    __(__foo)

    -. +```````````````````````````````` + The point of this restriction is more easily appreciated with this example: -. +```````````````````````````````` example _(__foo__)_ .

    (foo)

    -. +```````````````````````````````` + Intraword strong emphasis is forbidden with `__`: -. +```````````````````````````````` example __foo__bar .

    __foo__bar

    -. +```````````````````````````````` -. + +```````````````````````````````` example __пристаням__стремятся .

    __пристаням__стремятся

    -. +```````````````````````````````` -. + +```````````````````````````````` example __foo__bar__baz__ .

    foo__bar__baz

    -. +```````````````````````````````` + This is strong emphasis, even though the closing delimiter is both left- and right-flanking, because it is followed by punctuation: -. +```````````````````````````````` example __(bar)__. .

    (bar).

    -. +```````````````````````````````` + Rule 9: Any nonempty sequence of inline elements can be the contents of an emphasized span. -. +```````````````````````````````` example *foo [bar](/url)* .

    foo bar

    -. +```````````````````````````````` -. + +```````````````````````````````` example *foo bar* .

    foo bar

    -. +```````````````````````````````` + In particular, emphasis and strong emphasis can be nested inside emphasis: -. +```````````````````````````````` example _foo __bar__ baz_ .

    foo bar baz

    -. +```````````````````````````````` -. + +```````````````````````````````` example _foo _bar_ baz_ .

    foo bar baz

    -. +```````````````````````````````` -. + +```````````````````````````````` example __foo_ bar_ .

    foo bar

    -. +```````````````````````````````` -. + +```````````````````````````````` example *foo *bar** .

    foo bar

    -. +```````````````````````````````` -. + +```````````````````````````````` example *foo **bar** baz* .

    foo bar baz

    -. +```````````````````````````````` + But note: -. +```````````````````````````````` example *foo**bar**baz* .

    foobarbaz

    -. +```````````````````````````````` + The difference is that in the preceding case, the internal delimiters [can close emphasis], while in the cases with spaces, they cannot. -. +```````````````````````````````` example ***foo** bar* .

    foo bar

    -. +```````````````````````````````` -. + +```````````````````````````````` example *foo **bar*** .

    foo bar

    -. +```````````````````````````````` + Note, however, that in the following case we get no strong emphasis, because the opening delimiter is closed by the first `*` before `bar`: -. +```````````````````````````````` example *foo**bar*** .

    foobar**

    -. +```````````````````````````````` + Indefinite levels of nesting are possible: -. +```````````````````````````````` example *foo **bar *baz* bim** bop* .

    foo bar baz bim bop

    -. +```````````````````````````````` -. + +```````````````````````````````` example *foo [*bar*](/url)* .

    foo bar

    -. +```````````````````````````````` + There can be no empty emphasis or strong emphasis: -. +```````````````````````````````` example ** is not an empty emphasis .

    ** is not an empty emphasis

    -. +```````````````````````````````` -. + +```````````````````````````````` example **** is not an empty strong emphasis .

    **** is not an empty strong emphasis

    -. +```````````````````````````````` + Rule 10: @@ -6117,431 +6506,492 @@ Rule 10: Any nonempty sequence of inline elements can be the contents of an strongly emphasized span. -. +```````````````````````````````` example **foo [bar](/url)** .

    foo bar

    -. +```````````````````````````````` -. + +```````````````````````````````` example **foo bar** .

    foo bar

    -. +```````````````````````````````` + In particular, emphasis and strong emphasis can be nested inside strong emphasis: -. +```````````````````````````````` example __foo _bar_ baz__ .

    foo bar baz

    -. +```````````````````````````````` -. + +```````````````````````````````` example __foo __bar__ baz__ .

    foo bar baz

    -. +```````````````````````````````` -. + +```````````````````````````````` example ____foo__ bar__ .

    foo bar

    -. +```````````````````````````````` -. + +```````````````````````````````` example **foo **bar**** .

    foo bar

    -. +```````````````````````````````` -. + +```````````````````````````````` example **foo *bar* baz** .

    foo bar baz

    -. +```````````````````````````````` + But note: -. +```````````````````````````````` example **foo*bar*baz** .

    foobarbaz**

    -. +```````````````````````````````` + The difference is that in the preceding case, the internal delimiters [can close emphasis], while in the cases with spaces, they cannot. -. +```````````````````````````````` example ***foo* bar** .

    foo bar

    -. +```````````````````````````````` -. + +```````````````````````````````` example **foo *bar*** .

    foo bar

    -. +```````````````````````````````` + Indefinite levels of nesting are possible: -. +```````````````````````````````` example **foo *bar **baz** bim* bop** .

    foo bar baz bim bop

    -. +```````````````````````````````` -. + +```````````````````````````````` example **foo [*bar*](/url)** .

    foo bar

    -. +```````````````````````````````` + There can be no empty emphasis or strong emphasis: -. +```````````````````````````````` example __ is not an empty emphasis .

    __ is not an empty emphasis

    -. +```````````````````````````````` -. + +```````````````````````````````` example ____ is not an empty strong emphasis .

    ____ is not an empty strong emphasis

    -. +```````````````````````````````` + Rule 11: -. +```````````````````````````````` example foo *** .

    foo ***

    -. +```````````````````````````````` -. + +```````````````````````````````` example foo *\** .

    foo *

    -. +```````````````````````````````` -. + +```````````````````````````````` example foo *_* .

    foo _

    -. +```````````````````````````````` -. + +```````````````````````````````` example foo ***** .

    foo *****

    -. +```````````````````````````````` -. + +```````````````````````````````` example foo **\*** .

    foo *

    -. +```````````````````````````````` -. + +```````````````````````````````` example foo **_** .

    foo _

    -. +```````````````````````````````` + Note that when delimiters do not match evenly, Rule 11 determines that the excess literal `*` characters will appear outside of the emphasis, rather than inside it: -. +```````````````````````````````` example **foo* .

    *foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example *foo** .

    foo*

    -. +```````````````````````````````` -. + +```````````````````````````````` example ***foo** .

    *foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example ****foo* .

    ***foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example **foo*** .

    foo*

    -. +```````````````````````````````` -. + +```````````````````````````````` example *foo**** .

    foo***

    -. +```````````````````````````````` + Rule 12: -. +```````````````````````````````` example foo ___ .

    foo ___

    -. +```````````````````````````````` -. + +```````````````````````````````` example foo _\__ .

    foo _

    -. +```````````````````````````````` -. + +```````````````````````````````` example foo _*_ .

    foo *

    -. +```````````````````````````````` -. + +```````````````````````````````` example foo _____ .

    foo _____

    -. +```````````````````````````````` -. + +```````````````````````````````` example foo __\___ .

    foo _

    -. +```````````````````````````````` -. + +```````````````````````````````` example foo __*__ .

    foo *

    -. +```````````````````````````````` -. + +```````````````````````````````` example __foo_ .

    _foo

    -. +```````````````````````````````` + Note that when delimiters do not match evenly, Rule 12 determines that the excess literal `_` characters will appear outside of the emphasis, rather than inside it: -. +```````````````````````````````` example _foo__ .

    foo_

    -. +```````````````````````````````` -. + +```````````````````````````````` example ___foo__ .

    _foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example ____foo_ .

    ___foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example __foo___ .

    foo_

    -. +```````````````````````````````` -. + +```````````````````````````````` example _foo____ .

    foo___

    -. +```````````````````````````````` + Rule 13 implies that if you want emphasis nested directly inside emphasis, you must use different delimiters: -. +```````````````````````````````` example **foo** .

    foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example *_foo_* .

    foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example __foo__ .

    foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example _*foo*_ .

    foo

    -. +```````````````````````````````` + However, strong emphasis within strong emphasis is possible without switching delimiters: -. +```````````````````````````````` example ****foo**** .

    foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example ____foo____ .

    foo

    -. +```````````````````````````````` + Rule 13 can be applied to arbitrarily long sequences of delimiters: -. +```````````````````````````````` example ******foo****** .

    foo

    -. +```````````````````````````````` + Rule 14: -. +```````````````````````````````` example ***foo*** .

    foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example _____foo_____ .

    foo

    -. +```````````````````````````````` + Rule 15: -. +```````````````````````````````` example *foo _bar* baz_ .

    foo _bar baz_

    -. +```````````````````````````````` -. + +```````````````````````````````` example **foo*bar** .

    foobar*

    -. +```````````````````````````````` -. + +```````````````````````````````` example *foo __bar *baz bim__ bam* .

    foo bar *baz bim bam

    -. +```````````````````````````````` + Rule 16: -. +```````````````````````````````` example **foo **bar baz** .

    **foo bar baz

    -. +```````````````````````````````` -. + +```````````````````````````````` example *foo *bar baz* .

    *foo bar baz

    -. +```````````````````````````````` + Rule 17: -. +```````````````````````````````` example *[bar*](/url) .

    *bar*

    -. +```````````````````````````````` -. + +```````````````````````````````` example _foo [bar_](/url) .

    _foo bar_

    -. +```````````````````````````````` -. + +```````````````````````````````` example * .

    *

    -. +```````````````````````````````` -. + +```````````````````````````````` example ** .

    **

    -. +```````````````````````````````` -. + +```````````````````````````````` example __ .

    __

    -. +```````````````````````````````` -. + +```````````````````````````````` example *a `*`* .

    a *

    -. +```````````````````````````````` -. + +```````````````````````````````` example _a `_`_ .

    a _

    -. +```````````````````````````````` -. + +```````````````````````````````` example **a .

    **ahttp://foo.bar/?q=**

    -. +```````````````````````````````` -. + +```````````````````````````````` example __a .

    __ahttp://foo.bar/?q=__

    -. +```````````````````````````````` + ## Links A link contains [link text] (the visible text), a [link destination] (the URI that is the link destination), and optionally a [link title]. -There are two basic kinds of links in Markdown. In [inline link]s the +There are two basic kinds of links in Markdown. In [inline links] the destination and title are given immediately after the link text. In -[reference link]s the destination and title are defined elsewhere in +[reference links] the destination and title are defined elsewhere in the document. -A [link text](@link-text) consists of a sequence of zero or more +A [link text](@) consists of a sequence of zero or more inline elements enclosed by square brackets (`[` and `]`). The following rules apply: @@ -6554,7 +7004,7 @@ following rules apply: with an open bracket `[`, a sequence of zero or more inlines, and a close bracket `]`. -- Backtick [code span]s, [autolink]s, and raw [HTML tag]s bind more tightly +- Backtick [code spans], [autolinks], and raw [HTML tags] bind more tightly than the brackets in link text. Thus, for example, `` [foo`]` `` could not be a link text, since the second `]` is part of a code span. @@ -6562,7 +7012,7 @@ following rules apply: - The brackets in link text bind more tightly than markers for [emphasis and strong emphasis]. Thus, for example, `*[foo*](url)` is a link. -A [link destination](@link-destination) consists of either +A [link destination](@) consists of either - a sequence of zero or more characters between an opening `<` and a closing `>` that contains no spaces, line breaks, or unescaped @@ -6574,7 +7024,7 @@ A [link destination](@link-destination) consists of either a balanced pair of unescaped parentheses that is not itself inside a balanced pair of unescaped parentheses. -A [link title](@link-title) consists of either +A [link title](@) consists of either - a sequence of zero or more characters between straight double-quote characters (`"`), including a `"` character only if it is @@ -6587,10 +7037,10 @@ A [link title](@link-title) consists of either - a sequence of zero or more characters between matching parentheses (`(...)`), including a `)` character only if it is backslash-escaped. -Although [link title]s may span multiple lines, they may not contain +Although [link titles] may span multiple lines, they may not contain a [blank line]. -An [inline link](@inline-link) consists of a [link text] followed immediately +An [inline link](@) consists of a [link text] followed immediately by a left parenthesis `(`, optional [whitespace], an optional [link destination], an optional [link title] separated from the link destination by [whitespace], optional [whitespace], and a right @@ -6604,106 +7054,119 @@ above. Here is a simple inline link: -. +```````````````````````````````` example [link](/uri "title") .

    link

    -. +```````````````````````````````` + The title may be omitted: -. +```````````````````````````````` example [link](/uri) .

    link

    -. +```````````````````````````````` + Both the title and the destination may be omitted: -. +```````````````````````````````` example [link]() .

    link

    -. +```````````````````````````````` -. + +```````````````````````````````` example [link](<>) .

    link

    -. +```````````````````````````````` + The destination cannot contain spaces or line breaks, even if enclosed in pointy brackets: -. +```````````````````````````````` example [link](/my uri) .

    [link](/my uri)

    -. +```````````````````````````````` -. + +```````````````````````````````` example [link]() .

    [link](</my uri>)

    -. +```````````````````````````````` -. + +```````````````````````````````` example [link](foo bar) .

    [link](foo bar)

    -. +```````````````````````````````` -. + +```````````````````````````````` example [link]() .

    [link]()

    -. +```````````````````````````````` + One level of balanced parentheses is allowed without escaping: -. +```````````````````````````````` example [link]((foo)and(bar)) .

    link

    -. +```````````````````````````````` + However, if you have parentheses within parentheses, you need to escape or use the `<...>` form: -. +```````````````````````````````` example [link](foo(and(bar))) .

    [link](foo(and(bar)))

    -. +```````````````````````````````` -. + +```````````````````````````````` example [link](foo(and\(bar\))) .

    link

    -. +```````````````````````````````` -. + +```````````````````````````````` example [link]() .

    link

    -. +```````````````````````````````` + Parentheses and other symbols can also be escaped, as usual in Markdown: -. +```````````````````````````````` example [link](foo\)\:) .

    link

    -. +```````````````````````````````` + A link can contain fragment identifiers and queries: -. +```````````````````````````````` example [link](#fragment) [link](http://example.com#fragment) @@ -6713,16 +7176,18 @@ A link can contain fragment identifiers and queries:

    link

    link

    link

    -. +```````````````````````````````` + Note that a backslash before a non-escapable character is just a backslash: -. +```````````````````````````````` example [link](foo\bar) .

    link

    -. +```````````````````````````````` + URL-escaping should be left alone inside the destination, as all URL-escaped characters are also valid URL characters. Entity and @@ -6733,25 +7198,27 @@ does not enforce any particular policy for rendering URLs in HTML or other formats. Renderers may make different decisions about how to escape or normalize URLs in the output. -. +```````````````````````````````` example [link](foo%20bä) .

    link

    -. +```````````````````````````````` + Note that, because titles can often be parsed as destinations, if you try to omit the destination and keep the title, you'll get unexpected results: -. +```````````````````````````````` example [link]("title") .

    link

    -. +```````````````````````````````` + Titles may be in single quotes, double quotes, or parentheses: -. +```````````````````````````````` example [link](/url "title") [link](/url 'title') [link](/url (title)) @@ -6759,32 +7226,36 @@ Titles may be in single quotes, double quotes, or parentheses:

    link link link

    -. +```````````````````````````````` + Backslash escapes and entity and numeric character references may be used in titles: -. +```````````````````````````````` example [link](/url "title \""") .

    link

    -. +```````````````````````````````` + Nested balanced quotes are not allowed without escaping: -. +```````````````````````````````` example [link](/url "title "and" title") .

    [link](/url "title "and" title")

    -. +```````````````````````````````` + But it is easy to work around this by using a different quote type: -. +```````````````````````````````` example [link](/url 'title "and" title') .

    link

    -. +```````````````````````````````` + (Note: `Markdown.pl` did allow double quotes inside a double-quoted title, and its test suite included a test demonstrating this. @@ -6803,144 +7274,161 @@ the same way in inline links and link reference definitions.) [Whitespace] is allowed around the destination and title: -. +```````````````````````````````` example [link]( /uri "title" ) .

    link

    -. +```````````````````````````````` + But it is not allowed between the link text and the following parenthesis: -. +```````````````````````````````` example [link] (/uri) .

    [link] (/uri)

    -. +```````````````````````````````` + The link text may contain balanced brackets, but not unbalanced ones, unless they are escaped: -. +```````````````````````````````` example [link [foo [bar]]](/uri) .

    link [foo [bar]]

    -. +```````````````````````````````` -. + +```````````````````````````````` example [link] bar](/uri) .

    [link] bar](/uri)

    -. +```````````````````````````````` -. + +```````````````````````````````` example [link [bar](/uri) .

    [link bar

    -. +```````````````````````````````` -. + +```````````````````````````````` example [link \[bar](/uri) .

    link [bar

    -. +```````````````````````````````` + The link text may contain inline content: -. +```````````````````````````````` example [link *foo **bar** `#`*](/uri) .

    link foo bar #

    -. +```````````````````````````````` -. + +```````````````````````````````` example [![moon](moon.jpg)](/uri) .

    moon

    -. +```````````````````````````````` + However, links may not contain other links, at any level of nesting. -. +```````````````````````````````` example [foo [bar](/uri)](/uri) .

    [foo bar](/uri)

    -. +```````````````````````````````` -. + +```````````````````````````````` example [foo *[bar [baz](/uri)](/uri)*](/uri) .

    [foo [bar baz](/uri)](/uri)

    -. +```````````````````````````````` -. + +```````````````````````````````` example ![[[foo](uri1)](uri2)](uri3) .

    [foo](uri2)

    -. +```````````````````````````````` + These cases illustrate the precedence of link text grouping over emphasis grouping: -. +```````````````````````````````` example *[foo*](/uri) .

    *foo*

    -. +```````````````````````````````` -. + +```````````````````````````````` example [foo *bar](baz*) .

    foo *bar

    -. +```````````````````````````````` + Note that brackets that *aren't* part of links do not take precedence: -. +```````````````````````````````` example *foo [bar* baz] .

    foo [bar baz]

    -. +```````````````````````````````` + These cases illustrate the precedence of HTML tags, code spans, and autolinks over link grouping: -. +```````````````````````````````` example [foo .

    [foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example [foo`](/uri)` .

    [foo](/uri)

    -. +```````````````````````````````` -. + +```````````````````````````````` example [foo .

    [foohttp://example.com/?search=](uri)

    -. +```````````````````````````````` + -There are three kinds of [reference link](@reference-link)s: +There are three kinds of [reference link](@)s: [full](#full-reference-link), [collapsed](#collapsed-reference-link), and [shortcut](#shortcut-reference-link). -A [full reference link](@full-reference-link) +A [full reference link](@) consists of a [link text] immediately followed by a [link label] that [matches] a [link reference definition] elsewhere in the document. -A [link label](@link-label) begins with a left bracket (`[`) and ends +A [link label](@) begins with a left bracket (`[`) and ends with the first right bracket (`]`) that is not backslash-escaped. Between these brackets there must be at least one [non-whitespace character]. Unescaped square bracket characters are not allowed in -[link label]s. A link label can have at most 999 +[link labels]. A link label can have at most 999 characters inside the square brackets. -One label [matches](@matches) +One label [matches](@) another just in case their normalized forms are equal. To normalize a label, perform the *Unicode case fold* and collapse consecutive internal [whitespace] to a single space. If there are multiple @@ -6953,165 +7441,181 @@ matching [link reference definition]. Here is a simple example: -. +```````````````````````````````` example [foo][bar] [bar]: /url "title" .

    foo

    -. +```````````````````````````````` + The rules for the [link text] are the same as with -[inline link]s. Thus: +[inline links]. Thus: The link text may contain balanced brackets, but not unbalanced ones, unless they are escaped: -. +```````````````````````````````` example [link [foo [bar]]][ref] [ref]: /uri .

    link [foo [bar]]

    -. +```````````````````````````````` -. + +```````````````````````````````` example [link \[bar][ref] [ref]: /uri .

    link [bar

    -. +```````````````````````````````` + The link text may contain inline content: -. +```````````````````````````````` example [link *foo **bar** `#`*][ref] [ref]: /uri .

    link foo bar #

    -. +```````````````````````````````` -. + +```````````````````````````````` example [![moon](moon.jpg)][ref] [ref]: /uri .

    moon

    -. +```````````````````````````````` + However, links may not contain other links, at any level of nesting. -. +```````````````````````````````` example [foo [bar](/uri)][ref] [ref]: /uri .

    [foo bar]ref

    -. +```````````````````````````````` -. + +```````````````````````````````` example [foo *bar [baz][ref]*][ref] [ref]: /uri .

    [foo bar baz]ref

    -. +```````````````````````````````` -(In the examples above, we have two [shortcut reference link]s + +(In the examples above, we have two [shortcut reference links] instead of one [full reference link].) The following cases illustrate the precedence of link text grouping over emphasis grouping: -. +```````````````````````````````` example *[foo*][ref] [ref]: /uri .

    *foo*

    -. +```````````````````````````````` -. + +```````````````````````````````` example [foo *bar][ref] [ref]: /uri .

    foo *bar

    -. +```````````````````````````````` + These cases illustrate the precedence of HTML tags, code spans, and autolinks over link grouping: -. +```````````````````````````````` example [foo [ref]: /uri .

    [foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example [foo`][ref]` [ref]: /uri .

    [foo][ref]

    -. +```````````````````````````````` -. + +```````````````````````````````` example [foo [ref]: /uri .

    [foohttp://example.com/?search=][ref]

    -. +```````````````````````````````` + Matching is case-insensitive: -. +```````````````````````````````` example [foo][BaR] [bar]: /url "title" .

    foo

    -. +```````````````````````````````` + Unicode case fold is used: -. +```````````````````````````````` example [Толпой][Толпой] is a Russian word. [ТОЛПОЙ]: /url .

    Толпой is a Russian word.

    -. +```````````````````````````````` + Consecutive internal [whitespace] is treated as one space for purposes of determining matching: -. +```````````````````````````````` example [Foo bar]: /url [Baz][Foo bar] .

    Baz

    -. +```````````````````````````````` + No [whitespace] is allowed between the [link text] and the [link label]: -. +```````````````````````````````` example [foo] [bar] [bar]: /url "title" .

    [foo] bar

    -. +```````````````````````````````` -. + +```````````````````````````````` example [foo] [bar] @@ -7119,15 +7623,16 @@ No [whitespace] is allowed between the [link text] and the .

    [foo] bar

    -. +```````````````````````````````` + This is a departure from John Gruber's original Markdown syntax description, which explicitly allows whitespace between the link text and the link label. It brings reference links in line with -[inline link]s, which (according to both original Markdown and +[inline links], which (according to both original Markdown and this spec) cannot have whitespace after the link text. More importantly, it prevents inadvertent capture of consecutive -[shortcut reference link]s. If whitespace is allowed between the +[shortcut reference links]. If whitespace is allowed between the link text and the link label, then in the following we will have a single reference link, not two shortcut reference links, as intended: @@ -7140,7 +7645,7 @@ intended: [bar]: /url2 ``` -(Note that [shortcut reference link]s were introduced by Gruber +(Note that [shortcut reference links] were introduced by Gruber himself in a beta version of `Markdown.pl`, but never included in the official syntax description. Without shortcut reference links, it is harmless to allow space between the link text and @@ -7148,10 +7653,10 @@ link label; but once shortcut references are introduced, it is too dangerous to allow this, as it frequently leads to unintended results.) -When there are multiple matching [link reference definition]s, +When there are multiple matching [link reference definitions], the first is used: -. +```````````````````````````````` example [foo]: /url1 [foo]: /url2 @@ -7159,80 +7664,88 @@ the first is used: [bar][foo] .

    bar

    -. +```````````````````````````````` + Note that matching is performed on normalized strings, not parsed inline content. So the following does not match, even though the labels define equivalent inline content: -. +```````````````````````````````` example [bar][foo\!] [foo!]: /url .

    [bar][foo!]

    -. +```````````````````````````````` -[Link label]s cannot contain brackets, unless they are + +[Link labels] cannot contain brackets, unless they are backslash-escaped: -. +```````````````````````````````` example [foo][ref[] [ref[]: /uri .

    [foo][ref[]

    [ref[]: /uri

    -. +```````````````````````````````` -. + +```````````````````````````````` example [foo][ref[bar]] [ref[bar]]: /uri .

    [foo][ref[bar]]

    [ref[bar]]: /uri

    -. +```````````````````````````````` -. + +```````````````````````````````` example [[[foo]]] [[[foo]]]: /url .

    [[[foo]]]

    [[[foo]]]: /url

    -. +```````````````````````````````` -. + +```````````````````````````````` example [foo][ref\[] [ref\[]: /uri .

    foo

    -. +```````````````````````````````` + Note that in this example `]` is not backslash-escaped: -. +```````````````````````````````` example [bar\\]: /uri [bar\\] .

    bar\

    -. +```````````````````````````````` + A [link label] must contain at least one [non-whitespace character]: -. +```````````````````````````````` example [] []: /uri .

    []

    []: /uri

    -. +```````````````````````````````` -. + +```````````````````````````````` example [ ] @@ -7243,9 +7756,10 @@ A [link label] must contain at least one [non-whitespace character]: ]

    [ ]: /uri

    -. +```````````````````````````````` + -A [collapsed reference link](@collapsed-reference-link) +A [collapsed reference link](@) consists of a [link label] that [matches] a [link reference definition] elsewhere in the document, followed by the string `[]`. @@ -7254,37 +7768,40 @@ which are used as the link's text. The link's URI and title are provided by the matching reference link definition. Thus, `[foo][]` is equivalent to `[foo][foo]`. -. +```````````````````````````````` example [foo][] [foo]: /url "title" .

    foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example [*foo* bar][] [*foo* bar]: /url "title" .

    foo bar

    -. +```````````````````````````````` + The link labels are case-insensitive: -. +```````````````````````````````` example [Foo][] [foo]: /url "title" .

    Foo

    -. +```````````````````````````````` + As with full reference links, [whitespace] is not allowed between the two sets of brackets: -. +```````````````````````````````` example [foo] [] @@ -7292,9 +7809,10 @@ allowed between the two sets of brackets: .

    foo []

    -. +```````````````````````````````` + -A [shortcut reference link](@shortcut-reference-link) +A [shortcut reference link](@) consists of a [link label] that [matches] a [link reference definition] elsewhere in the document and is not followed by `[]` or a link label. @@ -7303,132 +7821,144 @@ which are used as the link's text. the link's URI and title are provided by the matching link reference definition. Thus, `[foo]` is equivalent to `[foo][]`. -. +```````````````````````````````` example [foo] [foo]: /url "title" .

    foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example [*foo* bar] [*foo* bar]: /url "title" .

    foo bar

    -. +```````````````````````````````` -. + +```````````````````````````````` example [[*foo* bar]] [*foo* bar]: /url "title" .

    [foo bar]

    -. +```````````````````````````````` -. + +```````````````````````````````` example [[bar [foo] [foo]: /url .

    [[bar foo

    -. +```````````````````````````````` + The link labels are case-insensitive: -. +```````````````````````````````` example [Foo] [foo]: /url "title" .

    Foo

    -. +```````````````````````````````` + A space after the link text should be preserved: -. +```````````````````````````````` example [foo] bar [foo]: /url .

    foo bar

    -. +```````````````````````````````` + If you just want bracketed text, you can backslash-escape the opening bracket to avoid links: -. +```````````````````````````````` example \[foo] [foo]: /url "title" .

    [foo]

    -. +```````````````````````````````` + Note that this is a link, because a link label ends with the first following closing bracket: -. +```````````````````````````````` example [foo*]: /url *[foo*] .

    *foo*

    -. +```````````````````````````````` + Full references take precedence over shortcut references: -. +```````````````````````````````` example [foo][bar] [foo]: /url1 [bar]: /url2 .

    foo

    -. +```````````````````````````````` + In the following case `[bar][baz]` is parsed as a reference, `[foo]` as normal text: -. +```````````````````````````````` example [foo][bar][baz] [baz]: /url .

    [foo]bar

    -. +```````````````````````````````` + Here, though, `[foo][bar]` is parsed as a reference, since `[bar]` is defined: -. +```````````````````````````````` example [foo][bar][baz] [baz]: /url1 [bar]: /url2 .

    foobaz

    -. +```````````````````````````````` + Here `[foo]` is not parsed as a shortcut reference, because it is followed by a link label (even though `[bar]` is not defined): -. +```````````````````````````````` example [foo][bar][baz] [baz]: /url1 [foo]: /url2 .

    [foo]bar

    -. +```````````````````````````````` + ## Images Syntax for images is like the syntax for links, with one difference. Instead of [link text], we have an -[image description](@image-description). The rules for this are the +[image description](@). The rules for this are the same as for [link text], except that (a) an image description starts with `![` rather than `[`, and (b) an image description may contain links. @@ -7436,31 +7966,35 @@ An image description has inline elements as its contents. When an image is rendered to HTML, this is standardly used as the image's `alt` attribute. -. +```````````````````````````````` example ![foo](/url "title") .

    foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example ![foo *bar*] [foo *bar*]: train.jpg "train & tracks" .

    foo bar

    -. +```````````````````````````````` -. + +```````````````````````````````` example ![foo ![bar](/url)](/url2) .

    foo bar

    -. +```````````````````````````````` -. + +```````````````````````````````` example ![foo [bar](/url)](/url2) .

    foo bar

    -. +```````````````````````````````` + Though this spec is concerned with parsing, not rendering, it is recommended that in rendering to HTML, only the plain string content @@ -7469,96 +8003,107 @@ the above example, the alt attribute's value is `foo bar`, not `foo [bar](/url)` or `foo bar`. Only the plain string content is rendered, without formatting. -. +```````````````````````````````` example ![foo *bar*][] [foo *bar*]: train.jpg "train & tracks" .

    foo bar

    -. +```````````````````````````````` -. + +```````````````````````````````` example ![foo *bar*][foobar] [FOOBAR]: train.jpg "train & tracks" .

    foo bar

    -. +```````````````````````````````` -. + +```````````````````````````````` example ![foo](train.jpg) .

    foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example My ![foo bar](/path/to/train.jpg "title" ) .

    My foo bar

    -. +```````````````````````````````` -. + +```````````````````````````````` example ![foo]() .

    foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example ![](/url) .

    -. +```````````````````````````````` + Reference-style: -. +```````````````````````````````` example ![foo][bar] [bar]: /url .

    foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example ![foo][bar] [BAR]: /url .

    foo

    -. +```````````````````````````````` + Collapsed: -. +```````````````````````````````` example ![foo][] [foo]: /url "title" .

    foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example ![*foo* bar][] [*foo* bar]: /url "title" .

    foo bar

    -. +```````````````````````````````` + The labels are case-insensitive: -. +```````````````````````````````` example ![Foo][] [foo]: /url "title" .

    Foo

    -. +```````````````````````````````` + As with reference links, [whitespace] is not allowed between the two sets of brackets: -. +```````````````````````````````` example ![foo] [] @@ -7566,170 +8111,187 @@ between the two sets of brackets: .

    foo []

    -. +```````````````````````````````` + Shortcut: -. +```````````````````````````````` example ![foo] [foo]: /url "title" .

    foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example ![*foo* bar] [*foo* bar]: /url "title" .

    foo bar

    -. +```````````````````````````````` + Note that link labels cannot contain unescaped brackets: -. +```````````````````````````````` example ![[foo]] [[foo]]: /url "title" .

    ![[foo]]

    [[foo]]: /url "title"

    -. +```````````````````````````````` + The link labels are case-insensitive: -. +```````````````````````````````` example ![Foo] [foo]: /url "title" .

    Foo

    -. +```````````````````````````````` + If you just want bracketed text, you can backslash-escape the opening `!` and `[`: -. +```````````````````````````````` example \!\[foo] [foo]: /url "title" .

    ![foo]

    -. +```````````````````````````````` + If you want a link after a literal `!`, backslash-escape the `!`: -. +```````````````````````````````` example \![foo] [foo]: /url "title" .

    !foo

    -. +```````````````````````````````` + ## Autolinks -[Autolink](@autolink)s are absolute URIs and email addresses inside +[Autolink](@)s are absolute URIs and email addresses inside `<` and `>`. They are parsed as links, with the URL or email address as the link label. -A [URI autolink](@uri-autolink) consists of `<`, followed by an +A [URI autolink](@) consists of `<`, followed by an [absolute URI] not containing `<`, followed by `>`. It is parsed as a link to the URI, with the URI as the link's label. -An [absolute URI](@absolute-uri), +An [absolute URI](@), for these purposes, consists of a [scheme] followed by a colon (`:`) followed by zero or more characters other than ASCII [whitespace] and control characters, `<`, and `>`. If the URI includes these characters, they must be percent-encoded (e.g. `%20` for a space). -For purposes of this spec, a [scheme](@scheme) is any sequence +For purposes of this spec, a [scheme](@) is any sequence of 2--32 characters beginning with an ASCII letter and followed by any combination of ASCII letters, digits, or the symbols plus ("+"), period ("."), or hyphen ("-"). Here are some valid autolinks: -. +```````````````````````````````` example .

    http://foo.bar.baz

    -. +```````````````````````````````` -. + +```````````````````````````````` example .

    http://foo.bar.baz/test?q=hello&id=22&boolean

    -. +```````````````````````````````` -. + +```````````````````````````````` example .

    irc://foo.bar:2233/baz

    -. +```````````````````````````````` + Uppercase is also fine: -. +```````````````````````````````` example .

    MAILTO:FOO@BAR.BAZ

    -. +```````````````````````````````` + -Note that many strings that count as [absolute URI]s for +Note that many strings that count as [absolute URIs] for purposes of this spec are not valid URIs, because their schemes are not registered or because of other problems with their syntax: -. +```````````````````````````````` example .

    a+b+c:d

    -. +```````````````````````````````` -. + +```````````````````````````````` example .

    made-up-scheme://foo,bar

    -. +```````````````````````````````` -. + +```````````````````````````````` example .

    http://../

    -. +```````````````````````````````` -. + +```````````````````````````````` example .

    localhost:5001/foo

    -. +```````````````````````````````` + Spaces are not allowed in autolinks: -. +```````````````````````````````` example .

    <http://foo.bar/baz bim>

    -. +```````````````````````````````` + Backslash-escapes do not work inside autolinks: -. +```````````````````````````````` example .

    http://example.com/\[\

    -. +```````````````````````````````` + -An [email autolink](@email-autolink) +An [email autolink](@) consists of `<`, followed by an [email address], followed by `>`. The link's label is the email address, and the URL is `mailto:` followed by the email address. -An [email address](@email-address), +An [email address](@), for these purposes, is anything that matches the [non-normative regex from the HTML5 spec](https://html.spec.whatwg.org/multipage/forms.html#e-mail-state-(type=email)): @@ -7739,63 +8301,72 @@ spec](https://html.spec.whatwg.org/multipage/forms.html#e-mail-state-(type=email Examples of email autolinks: -. +```````````````````````````````` example .

    foo@bar.example.com

    -. +```````````````````````````````` -. + +```````````````````````````````` example .

    foo+special@Bar.baz-bar0.com

    -. +```````````````````````````````` + Backslash-escapes do not work inside email autolinks: -. +```````````````````````````````` example .

    <foo+@bar.example.com>

    -. +```````````````````````````````` + These are not autolinks: -. +```````````````````````````````` example <> .

    <>

    -. +```````````````````````````````` -. + +```````````````````````````````` example < http://foo.bar > .

    < http://foo.bar >

    -. +```````````````````````````````` -. + +```````````````````````````````` example .

    <m:abc>

    -. +```````````````````````````````` -. + +```````````````````````````````` example .

    <foo.bar.baz>

    -. +```````````````````````````````` -. + +```````````````````````````````` example http://example.com .

    http://example.com

    -. +```````````````````````````````` -. + +```````````````````````````````` example foo@bar.example.com .

    foo@bar.example.com

    -. +```````````````````````````````` + ## Raw HTML @@ -7806,380 +8377,416 @@ so custom tags (and even, say, DocBook tags) may be used. Here is the grammar for tags: -A [tag name](@tag-name) consists of an ASCII letter +A [tag name](@) consists of an ASCII letter followed by zero or more ASCII letters, digits, or hyphens (`-`). -An [attribute](@attribute) consists of [whitespace], +An [attribute](@) consists of [whitespace], an [attribute name], and an optional [attribute value specification]. -An [attribute name](@attribute-name) +An [attribute name](@) consists of an ASCII letter, `_`, or `:`, followed by zero or more ASCII letters, digits, `_`, `.`, `:`, or `-`. (Note: This is the XML specification restricted to ASCII. HTML5 is laxer.) -An [attribute value specification](@attribute-value-specification) +An [attribute value specification](@) consists of optional [whitespace], a `=` character, optional [whitespace], and an [attribute value]. -An [attribute value](@attribute-value) +An [attribute value](@) consists of an [unquoted attribute value], a [single-quoted attribute value], or a [double-quoted attribute value]. -An [unquoted attribute value](@unquoted-attribute-value) +An [unquoted attribute value](@) is a nonempty string of characters not including spaces, `"`, `'`, `=`, `<`, `>`, or `` ` ``. -A [single-quoted attribute value](@single-quoted-attribute-value) +A [single-quoted attribute value](@) consists of `'`, zero or more characters not including `'`, and a final `'`. -A [double-quoted attribute value](@double-quoted-attribute-value) +A [double-quoted attribute value](@) consists of `"`, zero or more characters not including `"`, and a final `"`. -An [open tag](@open-tag) consists of a `<` character, a [tag name], -zero or more [attribute]s, optional [whitespace], an optional `/` +An [open tag](@) consists of a `<` character, a [tag name], +zero or more [attributes], optional [whitespace], an optional `/` character, and a `>` character. -A [closing tag](@closing-tag) consists of the string ``. -An [HTML comment](@html-comment) consists of ``, +An [HTML comment](@) consists of ``, where *text* does not start with `>` or `->`, does not end with `-`, and does not contain `--`. (See the [HTML5 spec](http://www.w3.org/TR/html5/syntax.html#comments).) -A [processing instruction](@processing-instruction) +A [processing instruction](@) consists of the string ``, and the string `?>`. -A [declaration](@declaration) consists of the +A [declaration](@) consists of the string ``, and the character `>`. -A [CDATA section](@cdata-section) consists of +A [CDATA section](@) consists of the string ``, and the string `]]>`. -An [HTML tag](@html-tag) consists of an [open tag], a [closing tag], +An [HTML tag](@) consists of an [open tag], a [closing tag], an [HTML comment], a [processing instruction], a [declaration], or a [CDATA section]. Here are some simple open tags: -. +```````````````````````````````` example .

    -. +```````````````````````````````` + Empty elements: -. +```````````````````````````````` example .

    -. +```````````````````````````````` + [Whitespace] is allowed: -. +```````````````````````````````` example .

    -. +```````````````````````````````` + With attributes: -. +```````````````````````````````` example .

    -. +```````````````````````````````` + Custom tag names can be used: -. +```````````````````````````````` example Foo .

    Foo

    -. +```````````````````````````````` + Illegal tag names, not parsed as HTML: -. +```````````````````````````````` example <33> <__> .

    <33> <__>

    -. +```````````````````````````````` + Illegal attribute names: -. +```````````````````````````````` example     .

    <a h*#ref="hi">

    -. +```````````````````````````````` + Illegal attribute values: -. +```````````````````````````````` example     .

    </a href="foo">

    -. +```````````````````````````````` + Comments: -. +```````````````````````````````` example foo .

    foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example foo .

    foo <!-- not a comment -- two hyphens -->

    -. +```````````````````````````````` + Not comments: -. +```````````````````````````````` example foo foo --> foo .

    foo <!--> foo -->

    foo <!-- foo--->

    -. +```````````````````````````````` + Processing instructions: -. +```````````````````````````````` example foo .

    foo

    -. +```````````````````````````````` + Declarations: -. +```````````````````````````````` example foo .

    foo

    -. +```````````````````````````````` + CDATA sections: -. +```````````````````````````````` example foo &<]]> .

    foo &<]]>

    -. +```````````````````````````````` + Entity and numeric character references are preserved in HTML attributes: -. +```````````````````````````````` example foo     .

    foo

    -. +```````````````````````````````` + Backslash escapes do not work in HTML attributes: -. +```````````````````````````````` example foo .

    foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example .

    <a href=""">

    -. +```````````````````````````````` + ## Hard line breaks A line break (not in a code span or HTML tag) that is preceded by two or more spaces and does not occur at the end of a block -is parsed as a [hard line break](@hard-line-break) (rendered +is parsed as a [hard line break](@) (rendered in HTML as a `
    ` tag): -. +```````````````````````````````` example foo baz .

    foo
    baz

    -. +```````````````````````````````` + For a more visible alternative, a backslash before the [line ending] may be used instead of two spaces: -. +```````````````````````````````` example foo\ baz .

    foo
    baz

    -. +```````````````````````````````` + More than two spaces can be used: -. +```````````````````````````````` example foo baz .

    foo
    baz

    -. +```````````````````````````````` + Leading spaces at the beginning of the next line are ignored: -. +```````````````````````````````` example foo bar .

    foo
    bar

    -. +```````````````````````````````` -. + +```````````````````````````````` example foo\ bar .

    foo
    bar

    -. +```````````````````````````````` + Line breaks can occur inside emphasis, links, and other constructs that allow inline content: -. +```````````````````````````````` example *foo bar* .

    foo
    bar

    -. +```````````````````````````````` -. + +```````````````````````````````` example *foo\ bar* .

    foo
    bar

    -. +```````````````````````````````` + Line breaks do not occur inside code spans -. +```````````````````````````````` example `code span` .

    code span

    -. +```````````````````````````````` -. + +```````````````````````````````` example `code\ span` .

    code\ span

    -. +```````````````````````````````` + or HTML tags: -. +```````````````````````````````` example     .

    -. +```````````````````````````````` -. + +```````````````````````````````` example .

    -. +```````````````````````````````` + Hard line breaks are for separating inline content within a block. Neither syntax for hard line breaks works at the end of a paragraph or other block element: -. +```````````````````````````````` example foo\ .

    foo\

    -. +```````````````````````````````` -. + +```````````````````````````````` example foo .

    foo

    -. +```````````````````````````````` -. + +```````````````````````````````` example ### foo\ .

    foo\

    -. +```````````````````````````````` -. + +```````````````````````````````` example ### foo .

    foo

    -. +```````````````````````````````` + ## Soft line breaks @@ -8189,24 +8796,26 @@ softbreak. (A softbreak may be rendered in HTML either as a [line ending] or as a space. The result will be the same in browsers. In the examples here, a [line ending] will be used.) -. +```````````````````````````````` example foo baz .

    foo baz

    -. +```````````````````````````````` + Spaces at the end of the line and beginning of the next line are removed: -. +```````````````````````````````` example foo baz .

    foo baz

    -. +```````````````````````````````` + A conforming parser may render a soft line break in HTML either as a line break or as a space. @@ -8219,34 +8828,37 @@ as hard line breaks. Any characters not given an interpretation by the above rules will be parsed as plain textual content. -. +```````````````````````````````` example hello $.;'there .

    hello $.;'there

    -. +```````````````````````````````` -. + +```````````````````````````````` example Foo χρῆν .

    Foo χρῆν

    -. +```````````````````````````````` + Internal spaces are preserved verbatim: -. +```````````````````````````````` example Multiple spaces .

    Multiple spaces

    -. +```````````````````````````````` + -# Appendix: A parsing strategy {-} +# Appendix: A parsing strategy In this appendix we describe some features of the parsing strategy used in the CommonMark reference implementations. -## Overview {-} +## Overview Parsing has two phases: @@ -8284,7 +8896,7 @@ marked by arrows: "aliquando id" ``` -## Phase 1: block structure {-} +## Phase 1: block structure Each line that is processed has an effect on this tree. The line is analyzed and, depending on its contents, the document may be altered @@ -8426,7 +9038,7 @@ We thus obtain the final tree: "aliquando id" ``` -## Phase 2: inline structure {-} +## Phase 2: inline structure Once all of the input has been parsed, all open blocks are closed. @@ -8457,7 +9069,7 @@ Notice how the [line ending] in the first paragraph has been parsed as a `softbreak`, and the asterisks in the first list item have become an `emph`. -### An algorithm for parsing nested emphasis and links {-} +### An algorithm for parsing nested emphasis and links By far the trickiest part of inline parsing is handling emphasis, strong emphasis, links, and images. This is done using the following @@ -8469,7 +9081,7 @@ When we're parsing inlines and we hit either - a `[` or `![` we insert a text node with these symbols as its literal content, and we -add a pointer to this text node to the [delimiter stack](@delimiter-stack). +add a pointer to this text node to the [delimiter stack](@). The [delimiter stack] is a doubly linked list. Each element contains a pointer to a text node, plus information about @@ -8487,7 +9099,7 @@ procedure (see below). When we hit the end of the input, we call the *process emphasis* procedure (see below), with `stack_bottom` = NULL. -#### *look for link or image* {-} +#### *look for link or image* Starting at the top of the delimiter stack, we look backwards through the stack for an opening `[` or `![` delimiter. @@ -8518,7 +9130,7 @@ through the stack for an opening `[` or `![` delimiter. `[` delimiters before the opening delimiter to *inactive*. (This will prevent us from getting links within links.) -#### *process emphasis* {-} +#### *process emphasis* Parameter `stack_bottom` sets a lower bound to how far we descend in the [delimiter stack]. If it is NULL, we can diff --git a/test/spec_tests.py b/test/spec_tests.py index c6950fb..d5b4d05 100755 --- a/test/spec_tests.py +++ b/test/spec_tests.py @@ -90,29 +90,33 @@ def get_tests(specfile): with open(specfile, 'r', encoding='utf-8') as specf: for line in specf: line_number = line_number + 1 - if state == 0 and re.match(header_re, line): - headertext = header_re.sub('', line).strip() - if line.strip() == ".": - state = (state + 1) % 3 - if state == 0: - example_number = example_number + 1 - end_line = line_number - tests.append({ - "markdown":''.join(markdown_lines).replace('→',"\t"), - "html":''.join(html_lines).replace('→',"\t"), - "example": example_number, - "start_line": start_line, - "end_line": end_line, - "section": headertext}) - start_line = 0 - markdown_lines = [] - html_lines = [] + l = line.strip() + if l == "`" * 32 + " example": + state = 1 + elif l == "`" * 32: + state = 0 + example_number = example_number + 1 + end_line = line_number + tests.append({ + "markdown":''.join(markdown_lines).replace('→',"\t"), + "html":''.join(html_lines).replace('→',"\t"), + "example": example_number, + "start_line": start_line, + "end_line": end_line, + "section": headertext}) + start_line = 0 + markdown_lines = [] + html_lines = [] + elif l == ".": + state = 2 elif state == 1: if start_line == 0: start_line = line_number - 1 markdown_lines.append(line) elif state == 2: html_lines.append(line) + elif state == 0 and re.match(header_re, line): + headertext = header_re.sub('', line).strip() return tests if __name__ == "__main__": diff --git a/tools/make_spec.lua b/tools/make_spec.lua new file mode 100644 index 0000000..3425f35 --- /dev/null +++ b/tools/make_spec.lua @@ -0,0 +1,292 @@ +local lcmark = require('lcmark') +local cmark = require('cmark') + +local format = arg[1] or 'html' + +local trim = function(s) + return s:gsub("^%s+",""):gsub("%s+$","") +end + +local warn = function(s) + io.stderr:write('WARNING: ' .. s .. '\n') +end + +local to_identifier = function(s) + return trim(s):lower():gsub('[^%w]+', ' '):gsub('[%s]+', '-') +end + +local render_number = function(tbl) + local buf = {} + for i,x in ipairs(tbl) do + buf[i] = tostring(x) + end + return table.concat(buf, '.') +end + +local extract_references = function(doc) + local cur, entering, node_type + local refs = {} + for cur, entering, node_type in cmark.walk(doc) do + if not entering and + ((node_type == cmark.NODE_LINK and cmark.node_get_url(cur) == '@') or + node_type == cmark.NODE_HEADING) then + local children = cmark.node_first_child(cur) + local label = trim(cmark.render_commonmark(children, OPT_DEFAULT, 0)) + local ident = to_identifier(label) + if refs[label] then + warn("duplicate reference " .. label) + end + refs[label] = ident + if not refs[label .. 's'] then + -- plural too + refs[label .. 's'] = ident + end + end + end + -- check for duplicate IDs + local idents = {} + for _,id in ipairs(refs) do + if idents[id] then + warn("duplicate identifier " .. id) + end + idents[#idents + 1] = id + end + return refs +end + +local make_toc = function(toc) + -- we create a commonmark string, then parse it + local toclines = {} + for _,entry in ipairs(toc) do + if entry.level <= 2 then + local indent = string.rep(' ', entry.level - 1) + toclines[#toclines + 1] = indent .. '* [' .. + (entry.number == '' and '' + or '' .. entry.number .. '') .. + entry.label .. '](#' .. entry.ident .. ')' + end + end + -- now parse our cm list and return the resulting list node: + local doc = cmark.parse_string(table.concat(toclines, '\n'), cmark.OPT_SMART) + return cmark.node_first_child(doc) +end + +local make_html_element = function(block, tagname, attrs) + local div = cmark.node_new(block and cmark.NODE_CUSTOM_BLOCK or + cmark.NODE_CUSTOM_INLINE) + local attribs = {} + for _,attr in ipairs(attrs) do + attribs[#attribs + 1] = ' ' .. attr[1] .. '="' .. attr[2] .. '"' + end + local opentag = '<' .. tagname .. table.concat(attribs, '') .. '>' + local closetag = '' + cmark.node_set_on_enter(div, opentag) + cmark.node_set_on_exit(div, closetag) + return div +end + +local make_html_block = function(tagname, attrs) + return make_html_element(true, tagname, attrs) +end + +local make_html_inline = function(tagname, attrs) + return make_html_element(false, tagname, attrs) +end + +local make_latex = function(spec) + local latex = cmark.node_new(spec.block and cmark.NODE_CUSTOM_BLOCK or + cmark.NODE_CUSTOM_INLINE) + cmark.node_set_on_enter(latex, spec.start) + cmark.node_set_on_exit(latex, spec.stop) + return latex +end + +local make_text = function(s) + local text = cmark.node_new(cmark.NODE_TEXT) + cmark.node_set_literal(text, s) + return text +end + +local create_anchors = function(doc, meta, to) + local cur, entering, node_type + local toc = {} + local number = {0} + local example = 0 + for cur, entering, node_type in cmark.walk(doc) do + if not entering and + ((node_type == cmark.NODE_LINK and cmark.node_get_url(cur) == '@') or + node_type == cmark.NODE_HEADING) then + + local anchor + local children = cmark.node_first_child(cur) + local label = trim(cmark.render_commonmark(children, OPT_DEFAULT, 0)) + local ident = to_identifier(label) + if node_type == cmark.NODE_LINK then + if format == 'latex' then + anchor = make_latex({start="\\hypertarget{" .. ident .. "}{", + stop="\\label{" .. ident .. "}}", + block = true}) + else + anchor = make_html_inline('a', {{'id', ident}, {'href', '#'..ident}, + {'class', 'definition'}}) + end + + else -- NODE_HEADING + + local level = cmark.node_get_heading_level(cur) + local last_level = #toc == 0 and 1 or toc[#toc].level + if #number > 0 then + if level > last_level then -- subhead + number[level] = 1 + else + while last_level > level do + number[last_level] = nil + last_level = last_level - 1 + end + number[level] = number[level] + 1 + end + end + table.insert(toc, { label = label, ident = ident, level = level, number = render_number(number) }) + local num = render_number(number) + local section_cmds = {"\\section", "\\subsection", + "\\subsubsection", "\\chapter"} + if format == 'latex' then + anchor = make_latex({start="\\hypertarget{" .. ident .. "}{" .. + section_cmds[level] .. "{", + stop="}\\label{" .. ident .. "}}", + block = true}) + else + anchor = make_html_block('h' .. tostring(level), + {{'id', ident}, + {'href', '#'..ident}, + {'class', 'definition'}}) + if num ~= '' then + local numspan = make_html_inline('span', {{'class','number'}}) + node_append_child(numspan, make_text(num)) + node_append_child(anchor, numspan) + end + end + end + while children do + node_append_child(anchor, children) + children = cmark.node_next(children) + end + cmark.node_insert_before(cur, anchor) + cmark.node_unlink(cur) + elseif entering and node_type == cmark.NODE_CODE_BLOCK and + cmark.node_get_fence_info(cur) == 'example' then + example = example + 1 + -- split into two code blocks + local code = cmark.node_get_literal(cur) + local sepstart, sepend = code:find("[\n\r]+%.[\n\r]+") + if not sepstart then + warn("Could not find separator in:\n" .. contents) + end + local markdown_code = cmark.node_new(cmark.NODE_CODE_BLOCK) + local html_code = cmark.node_new(cmark.NODE_CODE_BLOCK) + -- note: we replace the ␣ with a special span after rendering + local markdown_code_string = code:sub(1, sepstart):gsub(' ', '␣') + local html_code_string = code:sub(sepend + 1):gsub(' ', '␣') + cmark.node_set_literal(markdown_code, markdown_code_string) + cmark.node_set_fence_info(markdown_code, 'markdown') + cmark.node_set_literal(html_code, html_code_string) + cmark.node_set_fence_info(html_code, 'html') + + local example_div, leftcol_div, rightcol_div + if format == 'latex' then + example_div = make_latex({start = '\\begin{minipage}[t]{\\textwidth}\n{\\scriptsize Example ' .. tostring(example) .. '}\n\n\\vspace{-0.4em}\n', stop = '\\end{minipage}', block = true}) + leftcol_div = make_latex({start = "\\begin{minipage}[t]{0.49\\textwidth}\n\\definecolor{shadecolor}{gray}{0.85}\n\\begin{snugshade}\\small\n", stop = "\\end{snugshade}\n\\end{minipage}\n\\hfill", block = true}) + rightcol_div = make_latex({start = "\\begin{minipage}[t]{0.49\\textwidth}\n\\definecolor{shadecolor}{gray}{0.95}\n\\begin{snugshade}\\small\n", stop = "\\end{snugshade}\n\\end{minipage}\n\\vspace{0.8em}", block = true}) + cmark.node_append_child(leftcol_div, markdown_code) + cmark.node_append_child(rightcol_div, html_code) + cmark.node_append_child(example_div, leftcol_div) + cmark.node_append_child(example_div, rightcol_div) + else + leftcol_div = make_html_block('div', {{'class','column'}}) + rightcol_div = make_html_block('div', {{'class', 'column'}}) + cmark.node_append_child(leftcol_div, markdown_code) + cmark.node_append_child(rightcol_div, html_code) + local examplenum_div = make_html_block('div', {{'class', 'examplenum'}}) + local interact_link = make_html_inline('a', {{'class', 'dingus'}, + {'title', 'open in interactive dingus'}}) + cmark.node_append_child(interact_link, make_text("(interact)")) + local examplenum_link = cmark.node_new(cmark.NODE_LINK) + cmark.node_set_url(examplenum_link, '#example-' .. tostring(example)) + cmark.node_append_child(examplenum_link, + make_text("Example " .. tostring(example))) + cmark.node_append_child(examplenum_div, examplenum_link) + if format == 'html' then + cmark.node_append_child(examplenum_div, interact_link) + end + example_div = make_html_block('div', {{'class', 'example'}, + {'id','example-' .. tostring(example)}}) + cmark.node_append_child(example_div, examplenum_div) + cmark.node_append_child(example_div, leftcol_div) + cmark.node_append_child(example_div, rightcol_div) + end + cmark.node_insert_before(cur, example_div) + cmark.node_unlink(cur) + cmark.node_free(cur) + elseif node_type == cmark.NODE_HTML_BLOCK and + cmark.node_get_literal(cur) == '\n' then + -- change numbering + number = {} + if format ~= 'latex' then + local appendices = make_html_block('div', {{'class','appendices'}}) + cmark.node_insert_after(cur, appendices) + -- put the remaining sections in an appendix + local tmp = cmark.node_next(appendices) + while tmp do + cmark.node_append_child(appendices, tmp) + tmp = cmark.node_next(tmp) + end + end + end + end + meta.toc = make_toc(toc) +end + +local to_ref = function(ref) + return '[' .. ref.label .. ']: #' .. ref.indent .. '\n' +end + +local inp = io.read("*a") +local doc1 = cmark.parse_string(inp, cmark.OPT_DEFAULT) +local refs = extract_references(doc1) +local refblock = '\n' +for lab,ident in pairs(refs) do + refblock = refblock .. '[' .. lab .. ']: #' .. ident .. '\n' + -- refblock = refblock .. '[' .. lab .. 's]: #' .. ident .. '\n' +end +-- append references and parse again +local contents, meta, msg = lcmark.convert(inp .. refblock, format, + { smart = true, + yaml_metadata = true, + safe = false, + filters = { create_anchors } + }) + +if contents then + local f = io.open("tools/template." .. format, 'r') + if not f then + io.stderr:write("Could not find template!") + os.exit(1) + end + local template = f:read("*a") + + if format == 'html' then + contents = contents:gsub('␣', ' ') + end + meta.body = contents + local rendered, msg = lcmark.render_template(template, meta) + if not rendered then + io.stderr:write(msg) + os.exit(1) + end + io.write(rendered) + os.exit(0) +else + io.stderr:write(msg) + os.exit(1) +end + diff --git a/tools/makespec.py b/tools/makespec.py deleted file mode 100755 index 0ef924a..0000000 --- a/tools/makespec.py +++ /dev/null @@ -1,172 +0,0 @@ -#!/usr/bin/env python3 -# -*- coding: utf-8 -*- - -import re -import sys -from subprocess import * -from string import Template - -def out(str): - sys.stdout.buffer.write(str.encode('utf-8')) - -def err(str): - sys.stderr.buffer.write(str.encode('utf-8')) - -if len(sys.argv) == 2: - specformat = sys.argv[1] - if not (specformat in ["html", "markdown"]): - err("Format must be html or markdown\n") - exit(1) -else: - err("Usage: makespec.py [html|markdown]\n") - exit(1) - -def toIdentifier(s): - return re.sub(r'\s+', '-', re.sub(r'\W+', ' ', s.strip().lower())) - -def parseYaml(yaml): - metadata = {} - def parseField(match): - key = match.group(1) - val = match.group(2).strip() - if re.match(r'^\'', val): - val = val[1:len(val) - 1] - metadata[key] = val - fieldre = re.compile('^(\w+):(.*)$', re.MULTILINE) - re.sub(fieldre, parseField, yaml) - return metadata - -def pipe_through_prog(prog, text): - result = check_output(prog.split(), input=text.encode('utf-8')) - return result.decode('utf-8') - -def replaceAnchor(match): - refs.append("[{0}]: #{1}".format(match.group(1), match.group(2))) - if specformat == "html": - return '    {0}'.format(match.group(1), match.group(2)) - else: - return match.group(0) - -stage = 0 -example = 0 -section = "" -sections = [] -mdlines = [] -refs = [] -lastnum = [] -finishedMeta = False -yamllines = [] - -with open('spec.txt', 'r', encoding='utf-8') as spec: - for ln in spec: - if not finishedMeta: - yamllines.append(ln) - if re.match(r'^\.\.\.$', ln): - finishedMeta = True - elif re.match(r'^\.$', ln): - if stage == 0: - example += 1 - mdlines.append("\n
    \n".format(example, section)) - mdlines.append("
    Example {0}".format(example)) - if specformat == "html": - mdlines.append("  (interact)") - mdlines.append("
    \n
    \n\n") - mdlines.append("````````````````````````````````````````````````````````` markdown\n") - stage = 1 - elif stage == 1: - mdlines.append("`````````````````````````````````````````````````````````\n\n") - mdlines.append("\n
    \n\n
    \n\n") - mdlines.append("````````````````````````````````````````````````````````` html\n") - stage = 2 - elif stage == 2: - mdlines.append("`````````````````````````````````````````````````````````\n\n") - mdlines.append("
    \n
    \n") - stage = 0 - else: - sys.stderr.out("Encountered unknown stage {0}\n".format(stage)) - sys.exit(1) - else: - if stage == 0: - match = re.match(r'^(#{1,6}) *(.*)', ln) - if match: - section = match.group(2) - lastlevel = len(lastnum) - level = len(match.group(1)) - if re.search(r'{-}$', section): - section = re.sub(r' *{-} *$', '', section) - if specformat == 'html': - ln = re.sub(r' *{-} *$', '', ln) - number = '' - else: - if lastlevel == level: - lastnum[level - 1] = lastnum[level - 1] + 1 - elif lastlevel < level: - while len(lastnum) < level: - lastnum.append(1) - else: # lastlevel > level - lastnum = lastnum[0:level] - lastnum[level - 1] = lastnum[level - 1] + 1 - number = '.'.join([str(x) for x in lastnum]) - ident = toIdentifier(section) - ln = re.sub(r' ', ' ' + number + ' ', ln, count=1) - sections.append(dict(level=level, - contents=section, - ident=ident, - number=number)) - refs.append("[{0}]: #{1}".format(section, ident)) - ln = re.sub(r'# +', '# '.format(ident), - ln, count=1) - else: - ln = re.sub(r' ', '␣', ln) - mdlines.append(ln) - -mdtext = re.sub(r'\[([^]]*)\]\(@([^)]*)\)', replaceAnchor, - ''.join(mdlines)) + '\n\n' + '\n'.join(refs) + '\n' -yaml = ''.join(yamllines) -metadata = parseYaml(yaml) - -if specformat == "markdown": - out(yaml + '\n\n' + mdtext) -elif specformat == "html": - with open("tools/template.html", "r", encoding="utf-8") as templatefile: - template = Template(templatefile.read()) - toclines = [] - for section in sections: - if section['level'] <= 2: - indent = ' ' * (section['level'] - 1) - toclines.append(indent + '* [' + section['number'] + ' ' + - section['contents'] + '](#' + section['ident'] + ')') - toc = '
    \n\n' + '\n'.join(toclines) + '\n\n
    \n\n' - prog = "cmark --smart" - result = pipe_through_prog(prog, toc + mdtext) - if result == '': - err("Error converting markdown version of spec to HTML.\n") - exit(1) - else: - result = re.sub(r'␣', ' ', result) - result = re.sub(r'<\/a> ', - "", result) - # put plural s inside links for better visuals: - result = re.sub(r'<\/a>s', "s", result) - out(template.substitute(metadata, body=result)) - - # check for errors: - idents = [] - for ident in re.findall(r'id="([^"]*)"', result): - if ident in idents: - err("WARNING: duplicate identifier '" + ident + "'\n") - else: - idents.append(ident) - for href in re.findall(r'href="#([^"]*)"', result): - if not (href in idents): - err("WARNING: internal link with no anchor '" + href + "'\n") - reftexts = [] - for ref in refs: - ref = re.sub('].*',']',ref).upper() - if ref in reftexts: - err("WARNING: duplicate reference link '" + ref + "'\n") - else: - reftexts.append(ref) - - -exit(0) diff --git a/tools/specfilter.hs b/tools/specfilter.hs deleted file mode 100755 index 304e463..0000000 --- a/tools/specfilter.hs +++ /dev/null @@ -1,39 +0,0 @@ -#!/usr/bin/env runhaskell - -import Text.Pandoc.JSON -import Text.Pandoc.Walk -import Text.Pandoc.Generic - -main = toJSONFilter go - where go :: Pandoc -> Pandoc - go = bottomUp exampleDivs . bottomUp (concatMap anchors) - -exampleDivs :: Block -> Block -exampleDivs (Div (ident, ["example"], kvs) - [ d@(Div (_,["examplenum"],_) _), - d1@(Div (_,["column"],_) _), - d2@(Div (_,["column"],_) _) - ]) = Div (ident, ["example"], kvs) - [ rawtex "\\begin{minipage}[t]{\\textwidth}\n{\\scriptsize " - , d - , rawtex "}\\vspace{-0.4em}\n" - , rawtex "\\begin{minipage}[t]{0.49\\textwidth}\n\\definecolor{shadecolor}{gray}{0.85}\n\\begin{snugshade}\\small\n" - , walk addBreaks d1 - , rawtex "\\end{snugshade}\n\\end{minipage}\n\\hfill\n\\begin{minipage}[t]{0.49\\textwidth}\n\\definecolor{shadecolor}{gray}{0.95}\n\\begin{snugshade}\\small\n" - , walk addBreaks d2 - , rawtex "\\end{snugshade}\n\\end{minipage}\n\\end{minipage}" - ] - where rawtex = RawBlock (Format "latex") - addBreaks (CodeBlock attrs code) = CodeBlock attrs $ addBreaks' code - addBreaks x = x - addBreaks' code = - if length code > 49 - then take 49 code ++ ('\n':addBreaks' (drop 49 code)) - else code -exampleDivs x = x - -anchors :: Inline -> [Inline] -anchors (Link text ('@':lab,_)) = - [RawInline (Format "latex") ("\\hyperdef{}{" ++ lab ++ "}{\\label{" ++ lab ++ "}}"), Strong text] -anchors (Span ("",["number"],[]) xs) = [] -- remove sect numbers -anchors x = [x] diff --git a/tools/template.commonmark b/tools/template.commonmark new file mode 100644 index 0000000..b866378 --- /dev/null +++ b/tools/template.commonmark @@ -0,0 +1,9 @@ +--- +title: $title$ +author: $author$ +version: $version$ +date: '$date$' +license: '$license$' +... + +$body$ diff --git a/tools/template.html b/tools/template.html index fd2e56b..ca63146 100644 --- a/tools/template.html +++ b/tools/template.html @@ -2,7 +2,7 @@ -${title} +$title$ - + -

    ${title}

    -
    Version ${version} (${date})
    +

    $title$

    +
    Version $version$ ($date$)
    - ${author} + $author$
    .
    -${body} + +
    +$toc$ +
    + +$body$ + diff --git a/tools/template.latex b/tools/template.latex new file mode 100644 index 0000000..66fb997 --- /dev/null +++ b/tools/template.latex @@ -0,0 +1,95 @@ +\documentclass[10pt,letterpaper,twosides]{report} +\usepackage{lmodern} +\usepackage{amssymb,amsmath} +\usepackage{ifxetex,ifluatex} +\usepackage{fixltx2e} % provides \textsubscript +\usepackage[margin=1in]{geometry} +\ifnum 0\ifxetex 1\fi\ifluatex 1\fi=0 % if pdftex + \usepackage[T1]{fontenc} + \usepackage[utf8]{inputenc} +\else % if luatex or xelatex + \ifxetex + \usepackage{mathspec} + \usepackage{xltxtra,xunicode} + \else + \usepackage{fontspec} + \fi + \defaultfontfeatures{Mapping=tex-text,Scale=MatchLowercase} + \newcommand{\euro}{€} +\fi +% use upquote if available, for straight quotes in verbatim environments +\IfFileExists{upquote.sty}{\usepackage{upquote}}{} +% use microtype if available +\IfFileExists{microtype.sty}{% +\usepackage{microtype} +\UseMicrotypeSet[protrusion]{basicmath} % disable protrusion for tt fonts +}{} +\usepackage{framed} % code examples +\usepackage{color} +$if(geometry)$ +\usepackage[$for(geometry)$$geometry$$sep$,$endfor$]{geometry} +$endif$ +\usepackage{hyperref} +$if(colorlinks)$ +\PassOptionsToPackage{usenames,dvipsnames}{color} % color is loaded by hyperref +$endif$ +\hypersetup{unicode=true, +$if(title-meta)$ + pdftitle={$title-meta$}, +$endif$ +$if(author-meta)$ + pdfauthor={$author-meta$}, +$endif$ +$if(keywords)$ + pdfkeywords={$for(keywords)$$keywords$$sep$; $endfor$}, +$endif$ +$if(colorlinks)$ + colorlinks=true, + linkcolor=$if(linkcolor)$$linkcolor$$else$Maroon$endif$, + citecolor=$if(citecolor)$$citecolor$$else$Blue$endif$, + urlcolor=$if(urlcolor)$$urlcolor$$else$Blue$endif$, +$else$ + pdfborder={0 0 0}, +$endif$ + breaklinks=true} +\urlstyle{same} % don't use monospace font for urls +\usepackage{fancyvrb} +\VerbatimFootnotes % allows verbatim text in footnotes +$if(links-as-notes)$ +% Make links footnotes instead of hotlinks: +\renewcommand{\href}[2]{#2\footnote{\url{#1}}} +$endif$ +$if(indent)$ +$else$ +\IfFileExists{parskip.sty}{% +\usepackage{parskip} +}{% else +\setlength{\parindent}{0pt} +\setlength{\parskip}{6pt plus 2pt minus 1pt} +} +$endif$ +\setlength{\emergencystretch}{3em} % prevent overfull lines +\providecommand{\tightlist}{% + \setlength{\itemsep}{0pt}\setlength{\parskip}{0pt}} +$if(numbersections)$ +\setcounter{secnumdepth}{5} +$else$ +\setcounter{secnumdepth}{0} +$endif$ + +\title{$title$$if(thanks)$\thanks{$thanks$}$endif$} +\author{$for(author)$$author$$sep$ \and $endfor$} +\date{$date$} + +\begin{document} +\maketitle + +{ +\hypersetup{linkcolor=$if(toccolor)$$toccolor$$else$black$endif$} +\setcounter{tocdepth}{2} +\tableofcontents +} + +$body$ + +\end{document} diff --git a/tools/template.tex b/tools/template.tex deleted file mode 100644 index 13d38a3..0000000 --- a/tools/template.tex +++ /dev/null @@ -1,207 +0,0 @@ -\documentclass[$if(fontsize)$$fontsize$,$endif$$if(lang)$$lang$,$endif$$if(papersize)$$papersize$,$endif$$for(classoption)$$classoption$$sep$,$endfor$]{$documentclass$} -$if(fontfamily)$ -\usepackage{$fontfamily$} -$else$ -\usepackage{lmodern} -$endif$ -$if(linestretch)$ -\usepackage{setspace} -\setstretch{$linestretch$} -$endif$ -\usepackage{amssymb,amsmath} -\usepackage{ifxetex,ifluatex} -\usepackage{fixltx2e} % provides \textsubscript -\ifnum 0\ifxetex 1\fi\ifluatex 1\fi=0 % if pdftex - \usepackage[T1]{fontenc} - \usepackage[utf8]{inputenc} -$if(euro)$ - \usepackage{eurosym} -$endif$ -\else % if luatex or xelatex - \ifxetex - \usepackage{mathspec} - \usepackage{xltxtra,xunicode} - \else - \usepackage{fontspec} - \fi - \defaultfontfeatures{Mapping=tex-text,Scale=MatchLowercase} - \newcommand{\euro}{€} -$if(mainfont)$ - \setmainfont{$mainfont$} -$endif$ -$if(sansfont)$ - \setsansfont{$sansfont$} -$endif$ -$if(monofont)$ - \setmonofont[Mapping=tex-ansi]{$monofont$} -$endif$ -$if(mathfont)$ - \setmathfont(Digits,Latin,Greek){$mathfont$} -$endif$ -\fi -% use upquote if available, for straight quotes in verbatim environments -\IfFileExists{upquote.sty}{\usepackage{upquote}}{} -% use microtype if available -\IfFileExists{microtype.sty}{\usepackage{microtype}}{} -\usepackage[margin=1in]{geometry} -\providecommand{\tightlist}{% - \setlength{\itemsep}{0pt}\setlength{\parskip}{0pt}} -$if(natbib)$ -\usepackage{natbib} -\bibliographystyle{$if(biblio-style)$$biblio-style$$else$plainnat$endif$} -$endif$ -$if(biblatex)$ -\usepackage{biblatex} -$if(biblio-files)$ -\bibliography{$biblio-files$} -$endif$ -$endif$ -$if(listings)$ -\usepackage{listings} -$endif$ -$if(lhs)$ -\lstnewenvironment{code}{\lstset{language=Haskell,basicstyle=\small\ttfamily}}{} -$endif$ -\usepackage{fancyvrb} -$if(highlighting-macros)$ -$highlighting-macros$ -$endif$ -\usepackage{color,framed} -$if(verbatim-in-note)$ -\usepackage{fancyvrb} -$endif$ -$if(tables)$ -\usepackage{longtable,booktabs} -$endif$ -$if(graphics)$ -\usepackage{graphicx} -\makeatletter -\def\maxwidth{\ifdim\Gin@nat@width>\linewidth\linewidth\else\Gin@nat@width\fi} -\def\maxheight{\ifdim\Gin@nat@height>\textheight\textheight\else\Gin@nat@height\fi} -\makeatother -% Scale images if necessary, so that they will not overflow the page -% margins by default, and it is still possible to overwrite the defaults -% using explicit options in \includegraphics[width, height, ...]{} -\setkeys{Gin}{width=\maxwidth,height=\maxheight,keepaspectratio} -$endif$ -\ifxetex - \usepackage[setpagesize=false, % page size defined by xetex - unicode=false, % unicode breaks when used with xetex - xetex]{hyperref} -\else - \usepackage[unicode=true]{hyperref} -\fi -\hypersetup{breaklinks=true, - bookmarks=true, - pdfauthor={$author-meta$}, - pdftitle={$title-meta$}, - colorlinks=true, - citecolor=$if(citecolor)$$citecolor$$else$blue$endif$, - urlcolor=$if(urlcolor)$$urlcolor$$else$blue$endif$, - linkcolor=$if(linkcolor)$$linkcolor$$else$magenta$endif$, - pdfborder={0 0 0}} -\urlstyle{same} % don't use monospace font for urls -$if(links-as-notes)$ -% Make links footnotes instead of hotlinks: -\renewcommand{\href}[2]{#2\footnote{\url{#1}}} -$endif$ -$if(strikeout)$ -\usepackage[normalem]{ulem} -% avoid problems with \sout in headers with hyperref: -\pdfstringdefDisableCommands{\renewcommand{\sout}{}} -$endif$ -\setlength{\parindent}{0pt} -\setlength{\parskip}{6pt plus 2pt minus 1pt} -\setlength{\emergencystretch}{3em} % prevent overfull lines -$if(numbersections)$ -\setcounter{secnumdepth}{5} -$else$ -\setcounter{secnumdepth}{0} -$endif$ -$if(verbatim-in-note)$ -\VerbatimFootnotes % allows verbatim text in footnotes -$endif$ -$if(lang)$ -\ifxetex - \usepackage{polyglossia} - \setmainlanguage{$mainlang$} -\else - \usepackage[$lang$]{babel} -\fi -$endif$ - -\usepackage[small]{titlesec} -\titleformat{\chapter} - {\Large\bfseries} % format - {\Large\thechapter} % label - {0pt} % sep - {\Large} % before-code - - -\usepackage{fancyhdr} -\pagestyle{fancy} -\pagenumbering{arabic} -\lhead{\itshape $title$} -\chead{} -\rhead{\itshape{\nouppercase{\rightmark}}} -\lfoot{v$version$ ($date$)} -\cfoot{} -\rfoot{\thepage} - -$if(title)$ -\title{$title$\\ -Version $version$} -$endif$ -$if(author)$ -\author{$for(author)$$author$$sep$ \and $endfor$} -$endif$ -\date{$date$} -$for(header-includes)$ -$header-includes$ -$endfor$ - -\begin{document} -$if(title)$ -\maketitle -$endif$ -$if(abstract)$ -\begin{abstract} -$abstract$ -\end{abstract} -$endif$ - -$for(include-before)$ -$include-before$ - -$endfor$ -$if(toc)$ -{ -\hypersetup{linkcolor=black} -\setcounter{tocdepth}{$toc-depth$} -\tableofcontents -} -$endif$ -$body$ - -$if(natbib)$ -$if(biblio-files)$ -$if(biblio-title)$ -$if(book-class)$ -\renewcommand\bibname{$biblio-title$} -$else$ -\renewcommand\refname{$biblio-title$} -$endif$ -$endif$ -\bibliography{$biblio-files$} - -$endif$ -$endif$ -$if(biblatex)$ -\printbibliography$if(biblio-title)$[title=$biblio-title$]$endif$ - -$endif$ -$for(include-after)$ -$include-after$ - -$endfor$ -\end{document} -- cgit v1.2.3