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

Avoid stripping nonbreaking spaces (#188)

Browse Source
This commit is contained in:
Joseph Myers
2025-02-19 12:40:53 +00:00
committed by GitHub
parent 5655f27208
commit 3311f4d896
2 changed files with 7 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
markdownify/__init__.py
View File

@@ -313,7 +313,7 @@ class MarkdownConverter(object):
if (should_remove_whitespace_outside(el.previous_sibling)
or (should_remove_whitespace_inside(el.parent)
and not el.previous_sibling)):
text = text.lstrip()
text = text.lstrip(' \t\r\n')
if (should_remove_whitespace_outside(el.next_sibling)
or (should_remove_whitespace_inside(el.parent)
and not el.next_sibling)):
@@ -399,7 +399,7 @@ class MarkdownConverter(object):
def convert_blockquote(self, el, text, parent_tags):
# handle some early-exit scenarios
text = (text or '').strip()
text = (text or '').strip(' \t\r\n')
if '_inline' in parent_tags:
return ' ' + text + ' '
if not text:
@@ -567,8 +567,8 @@ class MarkdownConverter(object):
def convert_p(self, el, text, parent_tags):
if '_inline' in parent_tags:
return ' ' + text.strip() + ' '
text = text.strip()
return ' ' + text.strip(' \t\r\n') + ' '
text = text.strip(' \t\r\n')
if self.options['wrap']:
# Preserve newlines (and preceding whitespace) resulting
# from <br> tags. Newlines in the input have already been
@@ -577,7 +577,7 @@ class MarkdownConverter(object):
lines = text.split('\n')
new_lines = []
for line in lines:
line = line.lstrip()
line = line.lstrip(' \t\r\n')
line_no_trailing = line.rstrip()
trailing = line[len(line_no_trailing):]
line = fill(line,

2
tests/test_conversions.py
View File

@@ -59,6 +59,7 @@ def test_b_spaces():
def test_blockquote():
assert md('<blockquote>Hello</blockquote>') == '\n> Hello\n\n'
assert md('<blockquote>\nHello\n</blockquote>') == '\n> Hello\n\n'
assert md('<blockquote>&nbsp;Hello</blockquote>') == '\n> \u00a0Hello\n\n'
def test_blockquote_with_nested_paragraph():
@@ -266,6 +267,7 @@ def test_p():
assert md('<p>1234 5678 9012<br />67890</p>', wrap=True, wrap_width=10, newline_style=BACKSLASH) == '\n\n1234 5678\n9012\\\n67890\n\n'
assert md('<p>1234 5678 9012<br />67890</p>', wrap=True, wrap_width=10, newline_style=SPACES) == '\n\n1234 5678\n9012 \n67890\n\n'
assert md('First<p>Second</p><p>Third</p>Fourth') == 'First\n\nSecond\n\nThird\n\nFourth'
assert md('<p>&nbsp;x y</p>', wrap=True, wrap_width=80) == '\n\n\u00a0x y\n\n'
def test_pre():