def test_disallowed_raw_html_extension_653():
"""
Test case 653: All other HTML tags are left untouched.
"""
# Arrange
source_markdown = """<strong> <title> <style> <em>
<blockquote>
<xmp> is disallowed. <XMP> is also disallowed.
</blockquote>"""
expected_tokens = [
"[para:]",
"[raw-html:a]",
"[raw-html:bab]",
"[raw-html:c2c]",
"[end-para]",
]
expected_gfm = """
"""
# Act & Assert
act_and_assert(source_markdown, expected_gfm, expected_tokens)
def test_fenced_code_blocks_112():
"""
Test case 112: (part a) An info string can be provided after the opening code fence.
"""
# Arrange
source_markdown = """```ruby
def foo(x)
return 3
end
```"""
expected_tokens = [
"[fcode-block(1,1):`:3:ruby:::::]",
"[text(2,1):def foo(x)\n return 3\nend:]",
"[end-fcode-block::3:False]",
]
expected_gfm = """<pre><code class="language-ruby">def foo(x)
return 3
end
</code></pre>"""
# Act & Assert
act_and_assert(source_markdown, expected_gfm, expected_tokens)
def test_emphasis_428():
"""
Test case 428: (part 2) When the lengths of the interior closing and opening delimiter runs are both multiples of 3, though, they can match to create emphasis:
"""
# Arrange
source_markdown = """*foo [*bar*](/url)*"""
expected_tokens = [
"[para(1,1):]",
"[emphasis(1,1):1:*]",
"[text(1,2):foo :]",
"[link(1,6):inline:/url:::::*bar*:False::::]",
"[emphasis(1,7):1:*]",
"[text(1,8):bar:]",
"[end-emphasis(1,11)::]",
"[end-link::]",
"[end-emphasis(1,19)::]",
"[end-para:::True]",
]
expected_gfm = """<p><em>foo <a href="/url"><em>bar</em></a></em></p>"""
# Act & Assert
act_and_assert(source_markdown, expected_gfm, expected_tokens)
def test_raw_html_646():
"""
Test case 646: Not comments:
"""
# Arrange
source_markdown = """foo <!--> foo -->
foo <!-- foo--->"""
expected_tokens = [
"[para(1,1):]",
"[text(1,1):foo \a<\a<\a!--\a>\a>\a foo --\a>\a>\a:]",
"[end-para:::True]",
"[BLANK(2,1):]",
"[para(3,1):]",
"[text(3,1):foo \a<\a<\a!-- foo---\a>\a>\a:]",
"[end-para:::True]",
]
expected_gfm = """<p>foo <!--> foo --></p>
<p>foo <!-- foo---></p>"""
# Act & Assert
act_and_assert(source_markdown, expected_gfm, expected_tokens)
def test_front_matter_03():
"""
Everything between the start and end is parsed, but not as part of HTML output.
"""
# Arrange
source_markdown = """---
Title: my document
---
---
"""
expected_tokens = [
"[front-matter(1,1):---:---:['Title: my document']:{'title': 'my document'}]",
"[tbreak(4,1):-::---]",
"[BLANK(5,1):]",
]
expected_gfm = """<hr />"""
# Act & Assert
act_and_assert(source_markdown,
expected_gfm,
expected_tokens,
config_map=config_map)
def test_image_link_600():
"""
Test case 600: If you just want a literal ! followed by bracketed text, you can backslash-escape the opening [:
"""
# Arrange
source_markdown = """!\\[foo]
[foo]: /url "title"
"""
expected_tokens = [
"[para(1,1):]",
"[text(1,1):!\\\b[foo:]",
"[text(1,7):]:]",
"[end-para:::True]",
"[BLANK(2,1):]",
'[link-ref-def(3,1):True::foo:: :/url:: :title:"title":]',
"[BLANK(4,1):]",
]
expected_gfm = """<p>![foo]</p>"""
# Act & Assert
act_and_assert(source_markdown, expected_gfm, expected_tokens)
def test_image_link_592b():
"""
Test case 592a: variation of 592 with extra space and text after
"""
# Arrange
source_markdown = """![foo][]\atext
[foo]: /url "title"
""".replace("\a", " ")
expected_tokens = [
"[para(1,1):]",
"[image(1,1):collapsed:/url:title:foo::::foo:False::::]",
"[text(1,9): text:]",
"[end-para:::True]",
"[BLANK(2,1):]",
'[link-ref-def(3,1):True::foo:: :/url:: :title:"title":]',
"[BLANK(4,1):]",
]
expected_gfm = """<p><img src="/url" alt="foo" title="title" /> text</p>"""
# Act & Assert
act_and_assert(source_markdown, expected_gfm, expected_tokens)
def test_indented_code_blocks_085():
"""
Test case 085: And indented code can occur immediately before and after other kinds of blocks:
"""
# Arrange
source_markdown = """# Heading
foo
Heading
------
foo
----"""
expected_tokens = [
"[atx(1,1):1:0:]",
"[text(1,3):Heading: ]",
"[end-atx::]",
"[icode-block(2,5): :]",
"[text(2,5):foo:]",
"[end-icode-block:::False]",
"[setext(4,1):-:6::(3,1)]",
"[text(3,1):Heading:]",
"[end-setext::]",
"[icode-block(5,5): :]",
"[text(5,5):foo:]",
"[end-icode-block:::False]",
"[tbreak(6,1):-::----]",
]
expected_gfm = """<h1>Heading</h1>
<pre><code>foo
</code></pre>
<h2>Heading</h2>
<pre><code>foo
</code></pre>
<hr />"""
# Act & Assert
act_and_assert(source_markdown, expected_gfm, expected_tokens)
def test_fenced_code_blocks_extra_08b():
"""
Test case extra 08: variation of 8 with close fence and extra tex
"""
# Arrange
source_markdown = """```
abc
```
abc
def
```"""
expected_tokens = [
"[fcode-block(1,1):`:3::::::]",
"[text(2,1):abc:]",
"[end-fcode-block::3:False]",
"[BLANK(4,1):]",
"[para(5,1):]",
"[text(5,1):abc:]",
"[end-para:::True]",
"[BLANK(6,1):]",
"[para(7,1):]",
"[text(7,1):def:]",
"[end-para:::False]",
"[fcode-block(8,1):`:3::::::]",
"[end-fcode-block:::True]",
]
expected_gfm = """<pre><code>abc
</code></pre>
<p>abc</p>
<p>def</p>
<pre><code></code></pre>"""
# Act & Assert
act_and_assert(source_markdown, expected_gfm, expected_tokens)
def test_fenced_code_blocks_extra_03x():
"""
Test case extra 03: variation of 1 where list already opened but no new list item
NOTE: Small change to output to remove newline at pre/code at end.
"""
# Arrange
source_markdown = """- ```
some text
some other text
```
"""
expected_tokens = [
"[ulist(1,1):-::2:: ]",
"[fcode-block(1,3):`:3::::::]",
"[text(2,3):some text:]",
"[end-fcode-block:::True]",
"[end-ulist:::True]",
"[para(3,1):]",
"[text(3,1):some other text:]",
"[end-para:::False]",
"[fcode-block(4,1):`:3::::::]",
"[text(5,1)::]",
"[end-fcode-block:::True]",
]
expected_gfm = """<ul>
<li>
<pre><code>some text
</code></pre>
</li>
</ul>
<p>some other text</p>
<pre><code></code></pre>"""
# Act & Assert
act_and_assert(source_markdown, expected_gfm, expected_tokens)
def test_paragraph_series_m_hb_ol_nl_i3_ol_nl_i2_hb():
"""
Test case: Ordered list newline indent of 3 ordered list newline indent of 2 html block
"""
# Arrange
source_markdown = """1.
1.
<script>
foo
</script>
"""
expected_tokens = [
"[olist(1,1):.:1:3:]",
"[BLANK(1,3):]",
"[olist(2,4):.:1:6: ]",
"[BLANK(2,6):]",
"[end-olist:::True]",
"[end-olist:::True]",
"[html-block(3,1)]",
"[text(3,3):<script>\nfoo\n</script>: ]",
"[end-html-block:::False]",
"[BLANK(6,1):]",
]
expected_gfm = """<ol>
<li>
<ol>
<li></li>
</ol>
</li>
</ol>
<script>
foo
</script>"""
# Act & Assert
act_and_assert(source_markdown, expected_gfm, expected_tokens)
def test_paragraph_series_m_hb_ol_t_nl_i4_hb():
"""
Test case: Ordered list text newline indent of 4 html block
was: test_list_blocks_256kab
"""
# Arrange
source_markdown = """1. abc
<script>
foo
</script>
"""
expected_tokens = [
"[olist(1,1):.:1:4:: ]",
"[para(1,5):]",
"[text(1,5):abc:]",
"[end-para:::False]",
"[html-block(2,5)]",
"[text(2,5):<script>:]",
"[end-html-block:::True]",
"[end-olist:::True]",
"[para(3,1):\n]",
"[text(3,1):foo\n::\n]",
"[raw-html(4,1):/script]",
"[end-para:::True]",
"[BLANK(5,1):]",
]
expected_gfm = """<ol>
<li>abc
<script>
</li>
</ol>
<p>foo
</script></p>"""
# Act & Assert
act_and_assert(source_markdown, expected_gfm, expected_tokens)
def test_paragraph_series_m_ha_ol_t_nl_ol_t_nl_i3_ha_t():
"""
Test case: Ordered list text newline ordered list text new line indent of 3 atx heading text
"""
# Arrange
source_markdown = """1. abc
1. abc
# foo
"""
expected_tokens = [
"[olist(1,1):.:1:3:: \n]",
"[para(1,4):]",
"[text(1,4):abc:]",
"[end-para:::True]",
"[olist(2,4):.:1:6: ]",
"[para(2,7):]",
"[text(2,7):abc:]",
"[end-para:::True]",
"[end-olist:::True]",
"[atx(3,4):1:0:]",
"[text(3,6):foo: ]",
"[end-atx::]",
"[BLANK(4,1):]",
"[end-olist:::True]",
]
expected_gfm = """<ol>
<li>abc
<ol>
<li>abc</li>
</ol>
<h1>foo</h1>
</li>
</ol>"""
# Act & Assert
act_and_assert(source_markdown, expected_gfm, expected_tokens)
def test_paragraph_series_m_fb_ol_ol_t_nl_all_i6_fb():
"""
Test case: Ordered list x2 text newline fenced block
"""
# Arrange
source_markdown = """1. 1. abc
```
foo
```
"""
expected_tokens = [
"[olist(1,1):.:1:3:]",
"[olist(1,4):.:1:6: : \n \n \n]",
"[para(1,7):]",
"[text(1,7):abc:]",
"[end-para:::False]",
"[fcode-block(2,7):`:3::::::]",
"[text(3,7):foo:]",
"[end-fcode-block::3:False]",
"[BLANK(5,1):]",
"[end-olist:::True]",
"[end-olist:::True]",
]
expected_gfm = """<ol>
<li>
<ol>
<li>abc
<pre><code>foo
</code></pre>
</li>
</ol>
</li>
</ol>"""
# Act & Assert
act_and_assert(source_markdown, expected_gfm, expected_tokens)
def test_thematic_breaks_025():
"""
Test case 025: However, no other characters may occur in the line:
"""
# Arrange
source_markdown = """_ _ _ _ a
a------
---a---"""
expected_tokens = [
"[para(1,1):]",
"[text(1,1):_:]",
"[text(1,2): :]",
"[text(1,3):_:]",
"[text(1,4): :]",
"[text(1,5):_:]",
"[text(1,6): :]",
"[text(1,7):_:]",
"[text(1,8): a:]",
"[end-para:::True]",
"[BLANK(2,1):]",
"[para(3,1):]",
"[text(3,1):a------:]",
"[end-para:::True]",
"[BLANK(4,1):]",
"[para(5,1):]",
"[text(5,1):---a---:]",
"[end-para:::True]",
]
expected_gfm = """<p>_ _ _ _ a</p>
<p>a------</p>
<p>---a---</p>"""
# Act & Assert
act_and_assert(source_markdown, expected_gfm, expected_tokens)
def test_setext_headings_062():
"""
Test case 062: (part a) The setext heading underline cannot be a lazy continuation
line in a list item or block quote:
"""
# Arrange
source_markdown = """> Foo
---"""
expected_tokens = [
"[block-quote(1,1)::> ]",
"[para(1,3):]",
"[text(1,3):Foo:]",
"[end-para:::True]",
"[end-block-quote:::True]",
"[tbreak(2,1):-::---]",
]
expected_gfm = """<blockquote>
<p>Foo</p>
</blockquote>
<hr />"""
# Act & Assert
act_and_assert(source_markdown, expected_gfm, expected_tokens)
def test_setext_headings_061():
"""
Test case 061: Since indicators of block structure take precedence over indicators
of inline structure, the following are setext headings:
"""
# Arrange
source_markdown = """`Foo
----
`
<a title="a lot
---
of dashes"/>"""
expected_tokens = [
"[setext(2,1):-:4::(1,1)]",
"[text(1,1):`Foo:]",
"[end-setext::]",
"[para(3,1):]",
"[text(3,1):`:]",
"[end-para:::True]",
"[BLANK(4,1):]",
"[setext(6,1):-:3::(5,1)]",
'[text(5,1):\a<\a<\aa title=\a"\a"\aa lot:]',
"[end-setext::]",
"[para(7,1):]",
'[text(7,1):of dashes\a"\a"\a/\a>\a>\a:]',
"[end-para:::True]",
]
expected_gfm = """<h2>`Foo</h2>
<p>`</p>
<h2><a title="a lot</h2>
<p>of dashes"/></p>"""
# Act & Assert
act_and_assert(source_markdown, expected_gfm, expected_tokens)
def test_paragraph_series_m_fb_ol_nl_i3_ol_nl_i2_fb():
"""
Test case: Ordered list newline indent of 3 ordered list newline indent of 2 fenced block
"""
# Arrange
source_markdown = """1.
1.
```
foo
```
"""
expected_tokens = [
"[olist(1,1):.:1:3:]",
"[BLANK(1,3):]",
"[olist(2,4):.:1:6: ]",
"[BLANK(2,6):]",
"[end-olist:::True]",
"[end-olist:::True]",
"[fcode-block(3,3):`:3::::: :]",
"[text(4,1):foo:]",
"[end-fcode-block::3:False]",
"[BLANK(6,1):]",
]
expected_gfm = """<ol>
<li>
<ol>
<li></li>
</ol>
</li>
</ol>
<pre><code>foo
</code></pre>"""
# Act & Assert
act_and_assert(source_markdown, expected_gfm, expected_tokens)
def test_emphasis_479():
"""
Test case 479: (part 2) Rule 15
"""
# Arrange
source_markdown = """*foo __bar *baz bim__ bam*"""
expected_tokens = [
"[para(1,1):]",
"[emphasis(1,1):1:*]",
"[text(1,2):foo :]",
"[emphasis(1,6):2:_]",
"[text(1,8):bar :]",
"[text(1,12):*:]",
"[text(1,13):baz bim:]",
"[end-emphasis(1,20)::]",
"[text(1,22): bam:]",
"[end-emphasis(1,26)::]",
"[end-para:::True]",
]
expected_gfm = """<p><em>foo <strong>bar *baz bim</strong> bam</em></p>"""
# Act & Assert
act_and_assert(source_markdown, expected_gfm, expected_tokens)
def test_paragraph_series_j_l_t_em_s():
"""
Test case: Inline link containing text in label with split emphasis after
was: test_paragraph_extra_d3, added title, removed split raw html in label
"""
# Arrange
source_markdown = """a[link](/url)*a\nb*"""
expected_tokens = [
"[para(1,1):\n]",
"[text(1,1):a:]",
"[link(1,2):inline:/url:::::link:False::::]",
"[text(1,3):link:]",
"[end-link::]",
"[emphasis(1,14):1:*]",
"[text(1,15):a\nb::\n]",
"[end-emphasis(2,2)::]",
"[end-para:::True]",
]
expected_gfm = """<p>a<a href="/url">link</a><em>a
b</em></p>"""
# Act & Assert
act_and_assert(source_markdown, expected_gfm, expected_tokens)
def test_paragraph_series_j_l_sh_s_t():
"""
Test case: Inline image containing space hard line break in label, followed by text
was: test_paragraph_extra_h8b
"""
# Arrange
source_markdown = """a[foo \ncom](/uri "title")a"""
expected_tokens = [
"[para(1,1):\n]",
"[text(1,1):a:]",
'[link(1,2):inline:/uri:title::::foo \ncom:False:":: :]',
"[text(1,3):foo:]",
"[hard-break(1,6): :\n]",
"[text(2,1):com:]",
"[end-link::]",
"[text(2,19):a:]",
"[end-para:::True]",
]
expected_gfm = """<p>a<a href="/uri" title="title">foo<br />
com</a>a</p>"""
# Act & Assert
act_and_assert(source_markdown, expected_gfm, expected_tokens)
def test_paragraph_series_j_l_rh_s_t():
"""
Test case: Inline link containing split raw html in label
was: test_paragraph_extra_c7, changed split text at end to text
"""
# Arrange
source_markdown = """a[li<de\nfg>nk](/url)a"""
expected_tokens = [
"[para(1,1):\n]",
"[text(1,1):a:]",
"[link(1,2):inline:/url:::::li<de\nfg>nk:False::::]",
"[text(1,3):li:]",
"[raw-html(1,5):de\nfg]",
"[text(2,4):nk:]",
"[end-link::]",
"[text(2,13):a:]",
"[end-para:::True]",
]
expected_gfm = """<p>a<a href="/url">li<de
fg>nk</a>a</p>"""
# Act & Assert
act_and_assert(source_markdown, expected_gfm, expected_tokens)
def test_thematic_breaks_028():
"""
Test case 028: Thematic breaks can interrupt a paragraph:
"""
# Arrange
source_markdown = """Foo
***
bar"""
expected_tokens = [
"[para(1,1):]",
"[text(1,1):Foo:]",
"[end-para:::False]",
"[tbreak(2,1):*::***]",
"[para(3,1):]",
"[text(3,1):bar:]",
"[end-para:::True]",
]
expected_gfm = """<p>Foo</p>
<hr />
<p>bar</p>"""
# Act & Assert
act_and_assert(source_markdown, expected_gfm, expected_tokens)
def test_html_blocks_extrax_03():
"""
Test case 03: Pragma at the start and end of the document.
"""
# Arrange
source_markdown = """<!-- pyml -->
This is a paragraph
still a paragraph
and still going.
<!-- pyml -->"""
expected_tokens = [
"[para(2,1):\n\n]",
"[text(2,1):This is a paragraph\nstill a paragraph\nand still going.::\n\n]",
"[end-para:::True]",
"[pragma:1:<!-- pyml -->;5:<!-- pyml -->]",
]
expected_gfm = """<p>This is a paragraph\nstill a paragraph\nand still going.</p>"""
# Act & Assert
act_and_assert(source_markdown,
expected_gfm,
expected_tokens,
disable_consistency_checks=True)
def test_html_blocks_extrax_05():
"""
Test case 05: Single line paragraph with double pragmas to start and end document.
"""
# Arrange
source_markdown = """<!-- pyml -->
<!-- pyml -->
this is a paragraph
<!-- pyml -->
<!-- pyml -->"""
expected_tokens = [
"[para(3,1):]",
"[text(3,1):this is a paragraph:]",
"[end-para:::True]",
"[pragma:1:<!-- pyml -->;2:<!-- pyml -->;4:<!-- pyml -->;5:<!-- pyml -->]",
]
expected_gfm = "<p>this is a paragraph</p>"
# Act & Assert
act_and_assert(source_markdown,
expected_gfm,
expected_tokens,
disable_consistency_checks=True)
def test_inline_links_497a():
"""
Test case 497a: variation of 497 with no inline close and
defined reference
"""
# Arrange
source_markdown = """[link](
[link]: /url 'title'"""
expected_tokens = [
"[para(1,1):]",
"[link(1,1):shortcut:/url:title::::link:False::::]",
"[text(1,2):link:]",
"[end-link::]",
"[text(1,7):(:]",
"[end-para:::True]",
"[BLANK(2,1): ]",
"[link-ref-def(3,1):True::link:: :/url:: :title:'title':]",
]
expected_gfm = """<p><a href="/url" title="title">link</a>(</p>"""
# Act & Assert
act_and_assert(source_markdown, expected_gfm, expected_tokens)
def test_setext_headings_064():
"""
Test case 064: (part c) The setext heading underline cannot be a lazy continuation
line in a list item or block quote:
"""
# Arrange
source_markdown = """- Foo
---"""
expected_tokens = [
"[ulist(1,1):-::2:]",
"[para(1,3):]",
"[text(1,3):Foo:]",
"[end-para:::True]",
"[end-ulist:::True]",
"[tbreak(2,1):-::---]",
]
expected_gfm = """<ul>
<li>Foo</li>
</ul>
<hr />"""
# Act & Assert
act_and_assert(source_markdown, expected_gfm, expected_tokens)
def test_inline_links_509():
"""
Test case 509: A link can contain fragment identifiers and queries:
"""
# Arrange
source_markdown = """[link](#fragment)
[link](http://example.com#fragment)
[link](http://example.com?foo=3#frag)"""
expected_tokens = [
"[para(1,1):]",
"[link(1,1):inline:#fragment:::::link:False::::]",
"[text(1,2):link:]",
"[end-link::]",
"[end-para:::True]",
"[BLANK(2,1):]",
"[para(3,1):]",
"[link(3,1):inline:http://example.com#fragment:::::link:False::::]",
"[text(3,2):link:]",
"[end-link::]",
"[end-para:::True]",
"[BLANK(4,1):]",
"[para(5,1):]",
"[link(5,1):inline:http://example.com?foo=3#frag:::::link:False::::]",
"[text(5,2):link:]",
"[end-link::]",
"[end-para:::True]",
]
expected_gfm = """<p><a href="#fragment">link</a></p>
<p><a href="http://example.com#fragment">link</a></p>
<p><a href="http://example.com?foo=3#frag">link</a></p>"""
# Act & Assert
act_and_assert(source_markdown, expected_gfm, expected_tokens)
def test_setext_headings_064c():
"""
Test case 064a: variation of 64 other underline
"""
# Arrange
source_markdown = """- Foo
==="""
expected_tokens = [
"[ulist(1,1):-::2:: ]",
"[setext(2,3):=:3::(1,3)]",
"[text(1,3):Foo:]",
"[end-setext::]",
"[end-ulist:::True]",
]
expected_gfm = """<ul>
<li>
<h1>Foo</h1>
</li>
</ul>"""
# Act & Assert
act_and_assert(source_markdown, expected_gfm, expected_tokens)
def test_paragraph_series_m_hs_ol_nl_i3_ol_t_nl_i2_t_nl_i2_hs():
"""
Test case: Ordered list newline indent of 3 ordered list text new line indent
of 2 text newline indent of 2 setext heading
"""
# Arrange
source_markdown = """1.
1. def
foo
---
"""
expected_tokens = [
"[olist(1,1):.:1:3:]",
"[BLANK(1,3):]",
"[olist(2,4):.:1:6: :]",
"[para(2,7):\n ]",
"[text(2,7):def\nfoo::\n]",
"[end-para:::True]",
"[end-olist:::True]",
"[end-olist:::True]",
"[tbreak(4,3):-: :---]",
"[BLANK(5,1):]",
]
expected_gfm = """<ol>
<li>
<ol>
<li>def
foo</li>
</ol>
</li>
</ol>
<hr />"""
# Act & Assert
act_and_assert(source_markdown, expected_gfm, expected_tokens)
