Update mistune

md2cf/confluence_renderer.py

@@ -49,8 +49,10 @@ def append(self, child):
         self.children.append(child)
 
 
-class ConfluenceRenderer(mistune.Renderer):
-    def __init__(self, strip_header=False, remove_text_newlines=False, **kwargs):
+class ConfluenceRenderer(mistune.HTMLRenderer):
+    def __init__(self, strip_header=False,
+                 remove_text_newlines=False,
+                 **kwargs):
         super().__init__(**kwargs)
         self.strip_header = strip_header
         self.remove_text_newlines = remove_text_newlines
@@ -61,14 +63,14 @@ def reinit(self):
         self.attachments = list()
         self.title = None
 
-    def header(self, text, level, raw=None):
+    def heading(self, text, level, raw=None):
         if self.title is None and level == 1:
             self.title = text
             # Don't duplicate page title as a header
             if self.strip_header:
                 return ""
 
-        return super(ConfluenceRenderer, self).header(text, level, raw=raw)
+        return super(ConfluenceRenderer, self).heading(text, level, raw=raw)
 
     def structured_macro(self, name):
         return ConfluenceTag("structured-macro", attrib={"name": name})
@@ -87,7 +89,7 @@ def text(self, text):
         if self.remove_text_newlines:
             text = text.replace("\n", " ")
 
-        return super().text(text)
+        return text
 
     def block_code(self, code, lang=None):
         root_element = self.structured_macro("code")

md2cf/document.py

@@ -180,7 +180,9 @@ def get_pages_from_directory(
 
 
 def get_page_data_from_file_path(
-    file_path: Path, strip_header: bool = False, remove_text_newlines: bool = False
+    file_path: Path,
+    strip_header: bool = False,
+    remove_text_newlines: bool = False,
 ) -> Page:
     if not isinstance(file_path, Path):
         file_path = Path(file_path)
@@ -234,17 +236,22 @@ def parse_page(
     markdown_lines: List[str],
     strip_header: bool = False,
     remove_text_newlines: bool = False,
+    escape: bool = False,
+    allow_harmful_protocols: bool = False
 ) -> Page:
     renderer = ConfluenceRenderer(
-        use_xhtml=True,
         strip_header=strip_header,
         remove_text_newlines=remove_text_newlines,
+        escape=escape,
+        allow_harmful_protocols=allow_harmful_protocols
     )
     confluence_mistune = mistune.Markdown(renderer=renderer)
     confluence_content = confluence_mistune("".join(markdown_lines))
 
     page = Page(
-        title=renderer.title, body=confluence_content, attachments=renderer.attachments
+        title=renderer.title,
+        body=confluence_content,
+        attachments=renderer.attachments
     )
 
     return page

setup.py

@@ -21,10 +21,10 @@
     ],
     keywords="markdown confluence",
     install_requires=[
-        "mistune==0.8.4",
+        "mistune==3.0.1",
         "tortilla==0.5.0",
-        "PyYAML==6.0",
-        "gitignore_parser==0.0.8",
+        "PyYAML==6.0.1",
+        "gitignore_parser==0.1.6",
     ],
     python_requires=">=3.6",
     entry_points={"console_scripts": ["md2cf=md2cf.__main__:main"]},

tests/functional/result.xml

@@ -1,27 +1,27 @@
 <h1>Markdown: Syntax</h1>
 <ul>
+<li><a href="#markdown-syntax">Markdown: Syntax</a><ul>
 <li><a href="#overview">Overview</a><ul>
 <li><a href="#philosophy">Philosophy</a></li>
-<li><a href="#html">Inline HTML</a></li>
-<li><a href="#autoescape">Automatic Escaping for Special Characters</a></li>
 </ul>
 </li>
-<li><a href="#block">Block Elements</a><ul>
-<li><a href="#p">Paragraphs and Line Breaks</a></li>
-<li><a href="#header">Headers</a></li>
-<li><a href="#blockquote">Blockquotes</a></li>
-<li><a href="#list">Lists</a></li>
-<li><a href="#precode">Code Blocks</a></li>
-<li><a href="#hr">Horizontal Rules</a></li>
+<li><a href="#block-elements">Block Elements</a><ul>
+<li><a href="#paragraphs-and-line-breaks">Paragraphs and Line Breaks</a></li>
+<li><a href="#headers">Headers</a></li>
+<li><a href="#blockquotes">Blockquotes</a></li>
+<li><a href="#lists">Lists</a></li>
+<li><a href="#code-blocks">Code Blocks</a></li>
 </ul>
 </li>
-<li><a href="#span">Span Elements</a><ul>
-<li><a href="#link">Links</a></li>
-<li><a href="#em">Emphasis</a></li>
+<li><a href="#span-elements">Span Elements</a><ul>
+<li><a href="#links">Links</a></li>
+<li><a href="#emphasis">Emphasis</a></li>
 <li><a href="#code">Code</a></li>
 </ul>
 </li>
 </ul>
+</li>
+</ul>
 <p><strong>Note:</strong> This document is itself written using Markdown; you
 can <a href="/projects/markdown/syntax.text">see the source for it by adding '.text' to the URL</a>.</p>
 <hr />
@@ -60,30 +60,37 @@ determines the header level.)</p>
 familiar with quoting passages of text in an email message, then you
 know how to create a blockquote in Markdown. It looks best if you hard
 wrap the text and put a <code>&gt;</code> before every line:</p>
-<blockquote><p>This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet,
+<blockquote>
+<p>This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet,
 consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus.
 Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus.</p>
 <p>Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse
 id sem consectetuer libero luctus adipiscing.</p>
 </blockquote>
 <p>Markdown allows you to be lazy and only put the <code>&gt;</code> before the first
 line of a hard-wrapped paragraph:</p>
-<blockquote><p>This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet,
+<blockquote>
+<p>This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet,
 consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus.
 Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus.</p>
+</blockquote>
+<blockquote>
 <p>Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse
 id sem consectetuer libero luctus adipiscing.</p>
 </blockquote>
 <p>Blockquotes can be nested (i.e. a blockquote-in-a-blockquote) by
 adding additional levels of <code>&gt;</code>:</p>
-<blockquote><p>This is the first level of quoting.</p>
-<blockquote><p>This is nested blockquote.</p>
+<blockquote>
+<p>This is the first level of quoting.</p>
+<blockquote>
+<p>This is nested blockquote.</p>
 </blockquote>
 <p>Back to the first level.</p>
 </blockquote>
 <p>Blockquotes can contain other Markdown elements, including headers, lists,
 and code blocks:</p>
-<blockquote><h2>This is a header.</h2>
+<blockquote>
+<h2>This is a header.</h2>
 <ol>
 <li>This is the first list item.</li>
 <li>This is the second list item.</li>
@@ -132,16 +139,6 @@ Markdown produces from the above list is:</p>
 <li>McHale</li>
 <li>Parish</li>
 </ol>
-<p>or even:</p>
-<ol>
-<li>Bird</li>
-<li>McHale</li>
-<li>Parish</li>
-</ol>
-<p>you'd get the exact same HTML output. The point is, if you want to,
-you can use ordinal numbers in your ordered Markdown lists, so that
-the numbers in your source match the numbers in your published HTML.
-But if you want to be lazy, you don't have to.</p>
 <p>To make lists look nice, you can wrap items with hanging indents:</p>
 <ul>
 <li>Lorem ipsum dolor sit amet, consectetuer adipiscing elit.
@@ -188,7 +185,8 @@ sit amet, consectetuer adipiscing elit.</p>
 delimiters need to be indented:</p>
 <ul>
 <li><p>A list item with a blockquote:</p>
-<blockquote><p>This is a blockquote
+<blockquote>
+<p>This is a blockquote
 inside a list item.</p>
 </blockquote>
 </li>
@@ -211,17 +209,13 @@ in both <code>&lt;pre&gt;</code> and <code>&lt;code&gt;</code> tags.</p>
 block by at least 4 spaces or 1 tab.</p>
 <p>This is a normal paragraph:</p>
 <ac:structured-macro ac:name="code"><ac:parameter ac:name="linenumbers">true</ac:parameter>
-<ac:plain-text-body><![CDATA[This is a code block.
-
-]]></ac:plain-text-body>
+<ac:plain-text-body><![CDATA[This is a code block.]]></ac:plain-text-body>
 </ac:structured-macro>
 <p>Here is an example of AppleScript:</p>
 <ac:structured-macro ac:name="code"><ac:parameter ac:name="linenumbers">true</ac:parameter>
 <ac:plain-text-body><![CDATA[tell application "Foo"
     beep
-end tell
-
-]]></ac:plain-text-body>
+end tell]]></ac:plain-text-body>
 </ac:structured-macro>
 <p>A code block continues until it reaches a line that is not indented
 (or the end of the article).</p>
@@ -233,17 +227,16 @@ ampersands and angle brackets. For example, this:</p>
 <ac:structured-macro ac:name="code"><ac:parameter ac:name="linenumbers">true</ac:parameter>
 <ac:plain-text-body><![CDATA[<div class="footer">
     &copy; 2004 Foo Corporation
-</div>
-
-]]></ac:plain-text-body>
+</div>]]></ac:plain-text-body>
 </ac:structured-macro>
 <p>Regular Markdown syntax is not processed within code blocks. E.g.,
 asterisks are just literal asterisks within a code block. This means
 it's also easy to use Markdown to write about Markdown's own syntax.</p>
 <ac:structured-macro ac:name="code"><ac:parameter ac:name="linenumbers">true</ac:parameter>
 <ac:plain-text-body><![CDATA[tell application "Foo"
     beep
-end tell]]></ac:plain-text-body>
+end tell
+]]></ac:plain-text-body>
 </ac:structured-macro>
 <h2>Span Elements</h2>
 <h3>Links</h3>

tests/functional/test.md

@@ -1,20 +1,18 @@
 # Markdown: Syntax
 
-*   [Overview](#overview)
-    *   [Philosophy](#philosophy)
-    *   [Inline HTML](#html)
-    *   [Automatic Escaping for Special Characters](#autoescape)
-*   [Block Elements](#block)
-    *   [Paragraphs and Line Breaks](#p)
-    *   [Headers](#header)
-    *   [Blockquotes](#blockquote)
-    *   [Lists](#list)
-    *   [Code Blocks](#precode)
-    *   [Horizontal Rules](#hr)
-*   [Span Elements](#span)
-    *   [Links](#link)
-    *   [Emphasis](#em)
-    *   [Code](#code)
+- [Markdown: Syntax](#markdown-syntax)
+  - [Overview](#overview)
+    - [Philosophy](#philosophy)
+  - [Block Elements](#block-elements)
+    - [Paragraphs and Line Breaks](#paragraphs-and-line-breaks)
+    - [Headers](#headers)
+    - [Blockquotes](#blockquotes)
+    - [Lists](#lists)
+    - [Code Blocks](#code-blocks)
+  - [Span Elements](#span-elements)
+    - [Links](#links)
+    - [Emphasis](#emphasis)
+    - [Code](#code)
 
 
 **Note:** This document is itself written using Markdown; you
@@ -154,17 +152,6 @@ If you instead wrote the list in Markdown like this:
 1.  McHale
 1.  Parish
 
-or even:
-
-3. Bird
-1. McHale
-8. Parish
-
-you'd get the exact same HTML output. The point is, if you want to,
-you can use ordinal numbers in your ordered Markdown lists, so that
-the numbers in your source match the numbers in your published HTML.
-But if you want to be lazy, you don't have to.
-
 To make lists look nice, you can wrap items with hanging indents:
 
 *   Lorem ipsum dolor sit amet, consectetuer adipiscing elit.

tests/unit/test_renderer.py

@@ -99,7 +99,7 @@ def test_tag_render_with_child_and_text():
 
 def test_renderer_reinit():
     renderer = ConfluenceRenderer()
-    renderer.header("this is a title", 1)
+    renderer.heading("this is a title", 1)
     assert renderer.title is not None
 
     renderer.reinit()
@@ -138,7 +138,7 @@ def test_renderer_header_sets_title():
     test_header = "this is a header"
     renderer = ConfluenceRenderer()
 
-    renderer.header(test_header, 1)
+    renderer.heading(test_header, 1)
 
     assert renderer.title == test_header
 
@@ -147,7 +147,7 @@ def test_renderer_strips_header():
     test_header = "this is a header"
     renderer = ConfluenceRenderer(strip_header=True)
 
-    result = renderer.header(test_header, 1)
+    result = renderer.heading(test_header, 1)
 
     assert result == ""
 
@@ -156,7 +156,7 @@ def test_renderer_header_lower_level_does_not_set_title():
     test_header = "this is a header"
     renderer = ConfluenceRenderer()
 
-    renderer.header(test_header, 2)
+    renderer.heading(test_header, 2)
 
     assert renderer.title is None
 
@@ -166,8 +166,8 @@ def test_renderer_header_later_level_sets_title():
     test_header = "this is a header"
     renderer = ConfluenceRenderer()
 
-    renderer.header(test_lower_header, 2)
-    renderer.header(test_header, 1)
+    renderer.heading(test_lower_header, 2)
+    renderer.heading(test_header, 1)
 
     assert renderer.title is test_header
 
@@ -177,8 +177,8 @@ def test_renderer_header_only_sets_first_title():
     test_second_header = "this is another header"
     renderer = ConfluenceRenderer()
 
-    renderer.header(test_header, 1)
-    renderer.header(test_second_header, 1)
+    renderer.heading(test_header, 1)
+    renderer.heading(test_second_header, 1)
 
     assert renderer.title is test_header