Cyclic0007/python-markdownify
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

More carefully separate inline text from block content

Browse Source 
There are various cases in which inline text fails to be separated by
(sufficiently many) newlines from adjacent block content.  A paragraph
needs a blank line (two newlines) separating it from prior text, as
does an underlined header; an ATX header needs a single newline
separating it from prior text.  A list needs at least one newline
separating it from prior text, but in general two newlines (for an
ordered list starting other than at 1, which will only be recognized
given a blank line before).

To avoid accumulation of more newlines than necessary, take care when
concatenating the results of converting consecutive tags to remove
redundant newlines (keeping the greater of the number ending the prior
text and the number starting the subsequent text).

This is thus an alternative to #108 that tries to avoid the excess
newline accumulation that was a concern there, as well as fixing more
cases than just paragraphs, and updating tests.

Fixes #92

Fixes #98
This commit is contained in:
Joseph Myers
2024-04-09 16:47:15 +00:00
parent 43dbe20aaf
commit 60d86663d7
4 changed files with 58 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
markdownify/__init__.py
View File

@@ -143,7 +143,13 @@ class MarkdownConverter(object):
elif isinstance(el, NavigableString):
text += self.process_text(el)
else:
text += self.process_tag(el, convert_children_as_inline)
text_strip = text.rstrip('\n')
newlines_left = len(text) - len(text_strip)
next_text = self.process_tag(el, convert_children_as_inline)
next_text_strip = next_text.lstrip('\n')
newlines_right = len(next_text) - len(next_text_strip)
newlines = '\n' * max(newlines_left, newlines_right)
text = text_strip + newlines + next_text_strip
if not children_only:
convert_fn = getattr(self, 'convert_%s' % node.name, None)
@@ -216,7 +222,7 @@ class MarkdownConverter(object):
def underline(self, text, pad_char):
text = (text or '').rstrip()
return '%s\n%s\n\n' % (text, pad_char * len(text)) if text else ''
return '\n\n%s\n%s\n\n' % (text, pad_char * len(text)) if text else ''
def convert_a(self, el, text, convert_as_inline):
prefix, suffix, text = chomp(text)
@@ -277,8 +283,8 @@ class MarkdownConverter(object):
return self.underline(text, line)
hashes = '#' * n
if style == ATX_CLOSED:
return '%s %s %s\n\n' % (hashes, text, hashes)
return '%s %s\n\n' % (hashes, text)
return '\n%s %s %s\n\n' % (hashes, text, hashes)
return '\n%s %s\n\n' % (hashes, text)
def convert_hr(self, el, text, convert_as_inline):
return '\n\n---\n\n'
@@ -313,7 +319,7 @@ class MarkdownConverter(object):
if nested:
# remove trailing newline if nested
return '\n' + self.indent(text, 1).rstrip()
return text + ('\n' if before_paragraph else '')
return '\n\n' + text + ('\n' if before_paragraph else '')
convert_ul = convert_list
convert_ol = convert_list
@@ -344,7 +350,7 @@ class MarkdownConverter(object):
width=self.options['wrap_width'],
break_long_words=False,
break_on_hyphens=False)
return '%s\n\n' % text if text else ''
return '\n\n%s\n\n' % text if text else ''
def convert_pre(self, el, text, convert_as_inline):
if not text: