]> git.madduck.net Git - etc/neomutt.git/blobdiff - .config/neomutt/buildmimetree.py

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:

confvars update to latest version
[etc/neomutt.git] / .config / neomutt / buildmimetree.py
index d1f9eaaf6381a1103230ae24ff80c067c169d389..a27f64c1488bbf1417add4edae91f09a7127e992 100755 (executable)
@@ -11,7 +11,7 @@
 #       <enter-command> source '$my_confdir/buildmimetree.py \
 #       --tempdir $tempdir --extensions $my_mdwn_extensions \
 #       --css-file $my_confdir/htmlmail.css |'<enter>\
-#       <enter-command> sourc e \$my_mdwn_postprocess_cmd_file<enter>\
+#       <enter-command> source \$my_mdwn_postprocess_cmd_file<enter>\
 #     " "Convert message into a modern MIME tree with inline images"
 #
 #     (Yes, we need to call source twice, as mutt only starts to process output
 #   - Pynliner, provides --css-file and thus inline styling of HTML output
 #   - Pygments, then syntax highlighting for fenced code is enabled
 #
+# Running tests:
+#   pytest -x buildmimetree.py
+#
 # Latest version:
 #   https://git.madduck.net/etc/neomutt.git/blob_plain/HEAD:/.config/neomutt/buildmimetree.py
 #
-# Copyright © 2023 martin f. krafft <madduck@madduck.net>
-# Released under the GPL-2+ licence, just like Mutt itself.
+# Copyright © 2023–24 martin f. krafft <madduck@madduck.net>
+# Released under the GPL-2+ licence, just like NeoMutt itself.
 #
 
 import sys
@@ -47,11 +50,16 @@ import bs4
 import xml.etree.ElementTree as etree
 import io
 import enum
+import warnings
 from contextlib import contextmanager
 from collections import namedtuple, OrderedDict
 from markdown.extensions import Extension
 from markdown.blockprocessors import BlockProcessor
-from markdown.inlinepatterns import ImageInlineProcessor, IMAGE_LINK_RE
+from markdown.inlinepatterns import (
+    SimpleTextInlineProcessor,
+    ImageInlineProcessor,
+    IMAGE_LINK_RE,
+)
 from email.utils import make_msgid
 from urllib import request
 
@@ -64,7 +72,7 @@ def parse_cli_args(*args, **kwargs):
         )
     )
     parser.epilog = (
-        "Copyright © 2023 martin f. krafft <madduck@madduck.net>.\n"
+        "Copyright © 2023-24 martin f. krafft <madduck@madduck.net>.\n"
         "Released under the MIT licence"
     )
 
@@ -118,6 +126,11 @@ def parse_cli_args(*args, **kwargs):
         help="Only build, don't send the message",
     )
 
+    parser.add_argument(
+        "--domain",
+        help="Domain to use in content IDs",
+    )
+
     parser.add_argument(
         "--tempdir",
         metavar="DIR",
@@ -173,7 +186,6 @@ def parse_cli_args(*args, **kwargs):
 
 
 class File:
-
     class Op(enum.Enum):
         R = enum.auto()
         W = enum.auto()
@@ -192,10 +204,7 @@ class File:
         if content and not re.search(r"[r+]", mode):
             raise RuntimeError("Cannot specify content without read mode")
 
-        self._cache = {
-            File.Op.R: [content] if content else [],
-            File.Op.W: []
-        }
+        self._cache = {File.Op.R: [content] if content else [], File.Op.W: []}
         self._lastop = None
         self._mode = mode
         self._kwargs = kwargs
@@ -247,7 +256,6 @@ class File:
             return self._file.read()
 
     def write(self, s, *, cache=True):
-
         if self._lastop == File.Op.R:
             try:
                 self._file.seek(0)
@@ -347,12 +355,12 @@ class ImageRegistry:
     def __init__(self):
         self._images = OrderedDict()
 
-    def register(self, path, description=None):
+    def register(self, path, description=None, *, domain=None):
         # path = str(pathlib.Path(path).expanduser())
         path = os.path.expanduser(path)
         if path.startswith("/"):
             path = f"file://{path}"
-        cid = make_msgid()[1:-1]
+        cid = make_msgid(domain=domain)[1:-1]
         self._images[path] = InlineImageInfo(cid, description)
         return cid
 
@@ -444,7 +452,10 @@ def markdown_with_inline_image_support(
 
 
 try:
-    import pynliner
+    with warnings.catch_warnings():
+        # https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=1081037
+        warnings.filterwarnings("ignore", category=SyntaxWarning)
+        import pynliner
 
     _PYNLINER = True
 
@@ -473,11 +484,22 @@ def apply_styling(html, css):
     )
 
 
+# [ FORMAT=FLOWED HANDLING ] ##################################################
+
+
+class FormatFlowedNewlineExtension(Extension):
+    FFNL_RE = r"(?!\S)(\s)\n"
+
+    def extendMarkdown(self, md):
+        ffnl = SimpleTextInlineProcessor(self.FFNL_RE)
+        md.inlinePatterns.register(ffnl, "ffnl", 125)
+
+
 # [ QUOTE HANDLING ] ##########################################################
 
 
 class QuoteToAdmonitionExtension(Extension):
-    class EmailQuoteBlockProcessor(BlockProcessor):
+    class BlockProcessor(BlockProcessor):
         RE = re.compile(r"(?:^|\n)>\s*(.*)")
 
         def __init__(self, parser):
@@ -525,9 +547,7 @@ class QuoteToAdmonitionExtension(Extension):
 
             admonition[0].set("class", "admonition-title")
             with self.disable():
-                self.parser.parseChunk(
-                    admonition, "\n".join(quotelines)
-                )
+                self.parser.parseChunk(admonition, "\n".join(quotelines))
 
         @contextmanager
         def disable(self):
@@ -542,7 +562,7 @@ class QuoteToAdmonitionExtension(Extension):
 
     def extendMarkdown(self, md):
         md.registerExtension(self)
-        email_quote_proc = self.EmailQuoteBlockProcessor(md.parser)
+        email_quote_proc = self.BlockProcessor(md.parser)
         md.parser.blockprocessors.register(email_quote_proc, "emailquote", 25)
 
 
@@ -689,6 +709,7 @@ def convert_markdown_to_html(
     tempdir=None,
     extensions=None,
     extension_configs=None,
+    domain=None,
 ):
     # TODO extension_configs need to be handled differently
     extension_configs = extension_configs or {}
@@ -697,6 +718,7 @@ def convert_markdown_to_html(
     ] = _CODEHILITE_CLASS
 
     extensions = extensions or []
+    extensions.append(FormatFlowedNewlineExtension())
     extensions.append(QuoteToAdmonitionExtension())
 
     draft = draft_f.read()
@@ -722,7 +744,7 @@ def convert_markdown_to_html(
         for img in soup.find_all("img"):
             uri = img.attrs["src"]
             desc = img.attrs.get("title", img.attrs.get("alt"))
-            cid = image_registry.register(uri, desc)
+            cid = image_registry.register(uri, desc, domain=domain)
             img.attrs["src"] = f"cid:{cid}"
 
         htmlsig = str(soup)
@@ -952,6 +974,7 @@ def do_massage(
     only_build=False,
     max_other_attachments=20,
     tempdir=None,
+    domain=None,
     debug_commands=False,
     debug_walk=False,
 ):
@@ -973,6 +996,7 @@ def do_massage(
         related_to_html_only=related_to_html_only,
         tempdir=tempdir,
         extensions=extensions,
+        domain=domain,
     )
 
     mimetree = MIMETreeDFWalker(debug=debug_walk)
@@ -1145,6 +1169,7 @@ if __name__ == "__main__":
                 max_other_attachments=args.max_number_other_attachments,
                 only_build=args.only_build,
                 tempdir=args.tempdir,
+                domain=args.domain,
                 debug_commands=args.debug_commands,
                 debug_walk=args.debug_walk,
             )
@@ -1765,7 +1790,7 @@ try:
                 with (
                     File() as draft_f,
                     File(mode="w") as cmd_f,
-                    File(content=css) as css_f
+                    File(content=css) as css_f,
                 ):
                     do_massage(
                         draft_f=draft_f,
@@ -1856,6 +1881,15 @@ try:
             assert not cid.endswith(">")
             assert const1 in reg
 
+        @pytest.mark.imgproc
+        def test_image_registry_domain(self, const1, const2):
+            reg = ImageRegistry()
+            cid = reg.register(const1, domain=const2)
+            assert f"@{const2}" in cid
+            assert not cid.startswith("<")
+            assert not cid.endswith(">")
+            assert const1 in reg
+
         @pytest.mark.imgproc
         def test_image_registry_file_uri(self, const1):
             reg = ImageRegistry()
@@ -1913,9 +1947,7 @@ try:
                 "This is the plain-text version",
             )
             htmlsig = "HTML Signature from {path} but as a string"
-            html = (
-                f'<div id="signature"><p>{htmlsig.format(path=fakepath2)}</p></div>'
-            )
+            html = f'<div id="signature"><p>{htmlsig.format(path=fakepath2)}</p></div>'
 
             sig_f = fakefilefactory(fakepath2, content=html)
 
@@ -2114,6 +2146,46 @@ try:
                 == mailparts[-2]
             )
 
+        @pytest.mark.converter
+        def test_converter_format_flowed_with_nl2br(
+            self, fakepath, fakefilefactory
+        ):
+            mailparts = (
+                "This is format=flowed text ",
+                "with spaces at the end ",
+                "and there ought be no newlines.",
+                "",
+                "[link](https://example.org) ",
+                "and text.",
+                "",
+                "[link text ",
+                "broken up](https://example.org).",
+                "",
+                "This is on a new line with a hard break  ",
+                "due to the double space",
+            )
+            with fakefilefactory(
+                fakepath, content="\n".join(mailparts)
+            ) as draft_f:
+                convert_markdown_to_html(
+                    draft_f, extensions=["nl2br"], filefactory=fakefilefactory
+                )
+
+            soup = bs4.BeautifulSoup(
+                fakefilefactory[fakepath.with_suffix(".html")].read(),
+                "html.parser",
+            )
+            import ipdb
+
+            p = soup.p.extract().text
+            assert "".join(mailparts[0:3]) == p
+            p = ''.join(map(str, soup.p.extract().contents))
+            assert p == '<a href="https://example.org">link</a> and text.'
+            p = ''.join(map(str, soup.p.extract().contents))
+            assert (
+                p == '<a href="https://example.org">link text broken up</a>.'
+            )
+
         @pytest.mark.fileio
         def test_file_class_contextmanager(self, const1, monkeypatch):
             state = dict(o=False, c=False)