initial crack at a block-level figure parser

I didn't like the other figure + figcaption parsers, they either assumed
a lot about usage (e.g. images only), or they were inline parsers that
either wrapped the figure in a paragraph tag (which is incorrect syntax)
or did span trickery (annoying)

so, this handles images and maybe other things, and does things properly
with figures as their own blocks. incomplete but it works with my
images, and should allow for looping (for multi-line content) in the
future?

incorporealcms/config.py

@@ -32,7 +32,7 @@ class Config(object):
         },
     }
 
-    MARKDOWN_EXTENSIONS = ['extra', 'sane_lists', 'smarty', 'toc']
+    MARKDOWN_EXTENSIONS = ['extra', 'incorporealcms.mdx.figures', 'sane_lists', 'smarty', 'toc']
     MARKDOWN_EXTENSION_CONFIGS = {
         'extra': {
             'footnotes': {

incorporealcms/mdx/figures.py

@@ -0,0 +1,60 @@
+"""Create generic figures with captions."""
+import re
+from xml.etree.ElementTree import SubElement
+
+import markdown
+
+
+class FigureExtension(markdown.Extension):
+    """Wrap the markdown prepcoressor."""
+
+    def extendMarkdown(self, md):
+        """Add FigureBlockProcessor to the Markdown instance."""
+        md.parser.blockprocessors.register(FigureBlockProcessor(md.parser), 'figure', 100)
+
+
+class FigureBlockProcessor(markdown.blockprocessors.BlockProcessor):
+    """Process figures."""
+
+    # |> thing to put in the figure
+    # |: optional caption for the figure
+    # optional whatever else, like maybe an attr_list
+    figure_regex = re.compile(r'^[ ]{0,3}\|>[ ]{0,3}(?P<content>[^\n]*)')
+    caption_regex = re.compile(r'^[ ]{0,3}\|:[ ]{0,3}(?P<caption>[^\n]*)')
+
+    def test(self, parent, block):
+        """Determine if we should process this block."""
+        lines = block.split('\n')
+        return bool(self.figure_regex.search(lines[0]))
+
+    def run(self, parent, blocks):
+        """Replace the top block with HTML."""
+        block = blocks.pop(0)
+        lines = block.split('\n')
+
+        # consume line and create a figure
+        figure_match = self.figure_regex.search(lines[0])
+        lines.pop(0)
+        content = figure_match.group('content')
+        figure = SubElement(parent, 'figure')
+        figure.text = content
+        if lines:
+            if caption_match := self.caption_regex.search(lines[0]):
+                # consume line and add the caption as a child of the figure
+                lines.pop(0)
+                caption = caption_match.group('caption')
+                figcaption = SubElement(figure, 'figcaption')
+                figcaption.text = caption
+        if lines:
+            # other lines are mysteries, might be attr_list, so re-append
+            # make sure there's a child to hang the rest (which is maybe an attr_list?) off of
+            # this is probably a bad hack
+            if not len(list(figure)):
+                SubElement(figure, 'span')
+            rest = '\n'.join(lines)
+            figure[-1].tail = f'\n{rest}'
+
+
+def makeExtension(*args, **kwargs):
+    """Provide the extension to the markdown extension loader."""
+    return FigureExtension(*args, **kwargs)

tests/functional_markdown_tests.py

@@ -37,3 +37,16 @@ def test_invalid_graphviz_is_not_rendered():
     response = client.get('/test-invalid-graphviz')
     assert response.status_code == 500
     assert b'INTERNAL SERVER ERROR' in response.data
+
+
+def test_figures_are_rendered(client):
+    """Test that a page with my figure syntax renders as expected."""
+    response = client.get('/figures')
+    assert response.status_code == 200
+    assert (b'<figure class="right"><img alt="fancy captioned logo" src="bss-square-no-bg.png" />'
+            b'<figcaption>this is my cool logo!</figcaption></figure>') in response.data
+    assert (b'<figure><img alt="vanilla captioned logo" src="bss-square-no-bg.png" />'
+            b'<figcaption>this is my cool logo without an attr!</figcaption>\n</figure>') in response.data
+    assert (b'<figure class="left"><img alt="fancy logo" src="bss-square-no-bg.png" />'
+            b'<span></span></figure>') in response.data
+    assert b'<figure><img alt="just a logo" src="bss-square-no-bg.png" /></figure>' in response.data

tests/instance/pages/figures.md

@@ -0,0 +1,13 @@
+# test of figures
+
+|> ![fancy captioned logo](bss-square-no-bg.png)
+|: this is my cool logo!
+{: .right }
+
+|> ![vanilla captioned logo](bss-square-no-bg.png)
+|: this is my cool logo without an attr!
+
+|> ![fancy logo](bss-square-no-bg.png)
+{: .left }
+
+|> ![just a logo](bss-square-no-bg.png)