]> git.madduck.net Git - etc/mutt.git/blobdiff - .mutt/markdown2html

madduck's git repository

Every one of the projects in this repository is available at the canonical URL git://git.madduck.net/madduck/pub/<projectpath> — see each project's metadata for the exact URL.

All patches and comments are welcome. Please squash your changes to logical commits before using git-format-patch and git-send-email to patches@git.madduck.net. If you'd read over the Git project's submission guidelines and adhered to them, I'd be especially grateful.

SSH access, as well as push access can be individually arranged.

If you use my repositories frequently, consider adding the following snippet to ~/.gitconfig and using the third clone URL listed for each project:

[url "git://git.madduck.net/madduck/"]
  insteadOf = madduck:

Render self-contained HTML with Pandoc
[etc/mutt.git] / .mutt / markdown2html
index 72d0830dcf02149917169280e43a8ccb0a9f519f..2ffe54faeb64a8fffffc2dd78dc72c6af025af71 100755 (executable)
@@ -102,20 +102,16 @@ STYLESHEET = os.path.join(os.path.expanduser('~/.mutt'),
 if os.path.exists(STYLESHEET):
     DEFAULT_CSS += open(STYLESHEET).read()
 
-HTML_DOCUMENT = '''<!DOCTYPE html>
-<html><head>
-<meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>
-<meta charset="utf-8"/>
-<meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes"/>
-</head><body class="email">
-{htmlbody}
-</body></html>'''
-
-
 SIGNATURE_HTML = \
         '<div class="signature"><span class="leader">-- </span>{sig}</div>'
 
 
+def _preprocess_signature(sig):
+    '''
+    Preprocess the signature before markdown processing.
+    '''
+    return sig
+
 def _preprocess_markdown(mdwn):
     '''
     Preprocess Markdown for handling by the converter.
@@ -133,6 +129,13 @@ def _preprocess_markdown(mdwn):
     # text-mode HTML2text converters, and so it's left commented for now.
     #ret = re.sub(r'\n>', r'  \n>[>]{.quotechar}', ret, flags=re.MULTILINE)
 
+    # With the autolink_bare_uris extension, we do not need to put links into
+    # angle brackets to have them converted, so let's conserve the brackets
+    # when used around email addresses. Note that this needs a postprocessing
+    # hack because the pandoc autolink converted includes the ambersand
+    # (https://github.com/jgm/pandoc/issues/7398).
+    ret = re.sub(r'<([^@]+@.+\.[^>]+)>', r'&lt;\g<1> -PANDOC_BUG_7398-&gt;', ret)
+
     return ret
 
 
@@ -214,7 +217,7 @@ def _reformat_quotes(html):
 
 def _convert_with_pandoc(mdwn, inputfmt='markdown', outputfmt='html5',
                          ext_enabled=None, ext_disabled=None,
-                         standalone=True, title="HTML E-Mail"):
+                         standalone=True, selfcontained=True, title=None):
     '''
     Invoke pandoc to do the actual conversion of Markdown to HTML5.
     '''
@@ -257,6 +260,8 @@ def _convert_with_pandoc(mdwn, inputfmt='markdown', outputfmt='html5',
     args = []
     if standalone:
         args.append('--standalone')
+    if selfcontained:
+        args.append('--self-contained')
     if title:
         args.append(f'--metadata=pagetitle:"{title}"')
 
@@ -275,6 +280,10 @@ def _postprocess_html(html):
     '''
     Postprocess the generated and styled HTML.
     '''
+
+    # Preprocessing leaves a sentinel to work around
+    # https://github.com/jgm/pandoc/issues/7398, and so we need to remove it:
+    html = html.replace('</a> -PANDOC_BUG_7398-&gt;', '</a>&gt;')
     return html
 
 
@@ -294,14 +303,19 @@ def convert_markdown_to_html(mdwn):
     if body:
         body = _preprocess_markdown(body)
         body = _identify_quotes_for_later(body)
-        html = _convert_with_pandoc(body, standalone=False)
+        html = _convert_with_pandoc(body, standalone=True, selfcontained=True,
+                                    title=None)
+        html = html.replace('<title>Untitled</title>\n','')
         html = _reformat_quotes(html)
 
     if sig:
+        sig = _preprocess_signature(sig)
         sig = _preprocess_markdown(sig)
-        html += SIGNATURE_HTML.format(sig='<br/>'.join(sig.splitlines()))
+        sig = _convert_with_pandoc(sig, standalone=False, selfcontained=False)
+        sig = SIGNATURE_HTML.format(sig='<br/>'.join(sig.splitlines()))
+        eob = html.find('</body>')
+        html = f'{html[:eob]}{sig}\n{html[eob:]}'
 
-    html = HTML_DOCUMENT.format(htmlbody=html)
     html = _apply_styling(html)
     html = _postprocess_html(html)