Skip to content

Do cleanup on insert/delete/sdt tags #30

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
jlward merged 4 commits into from
May 23, 2013
Merged

Do cleanup on insert/delete/sdt tags #30

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
d584137
refs #30: Updated the tests for expected behaviour
May 21, 2013
c9c76fb
refs #30: no longer adding invalid attributes to insert and delete tags
May 21, 2013
70fc06f
refs #30: stopped break separating tags that were inline like (insert…
May 21, 2013
0bd3e36
Merge branch 'master' into issue_30
May 22, 2013
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 11 additions & 1 deletion pydocx/DocxParser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -576,12 +576,22 @@ def parse_p(self, el, text):
def _should_append_break_tag(self, next_el):
paragraph_like_tags = [
'p',
'sdt',
]
inline_like_tags = [
'smartTag',
'ins',
'delText',
]
if next_el.is_list_item:
return False
if next_el.previous is None:
return False
tag_is_inline_like = any(
next_el.has_descendant_with_tag(tag) for
tag in inline_like_tags
)
if tag_is_inline_like:
return False
if next_el.previous.is_last_list_item_in_root:
return False
if next_el.previous.tag not in paragraph_like_tags:
Expand Down
6 changes: 2 additions & 4 deletions pydocx/parsers/Docx2Html.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,8 +54,7 @@ def heading(self, text, heading_value):

def insertion(self, text, author, date):
return (
"<span class='pydocx-insert' author='%(author)s' "
"date='%(date)s'>%(text)s</span>"
"<span class='pydocx-insert'>%(text)s</span>"
) % {
'author': author,
'date': date,
Expand Down Expand Up @@ -88,8 +87,7 @@ def image(self, path, x, y):

def deletion(self, text, author, date):
return (
"<span class='pydocx-delete' author='%(author)s' "
"date='%(date)s'>%(text)s</span>"
"<span class='pydocx-delete'>%(text)s</span>"
) % {
'author': author,
'date': date,
Expand Down
15 changes: 6 additions & 9 deletions pydocx/tests/test_xml.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -641,7 +641,7 @@ def test_performance(self):

class NonStandardTextTagsTestCase(_TranslationTestCase):
expected_output = '''
<p><span class='pydocx-insert' author='' date=''>insert </span>
<p><span class='pydocx-insert'>insert </span>
smarttag</p>
'''

Expand Down Expand Up @@ -674,8 +674,8 @@ def get_xml(self):
class DeleteTagInList(_TranslationTestCase):
expected_output = '''
<ol list-style-type="decimal">
<li>AAA<br />
<span class='pydocx-delete' author='' date=''>BBB</span>
<li>AAA
<span class='pydocx-delete'>BBB</span>
</li>
<li>CCC</li>
</ol>
Expand All @@ -696,8 +696,7 @@ def get_xml(self):
class InsertTagInList(_TranslationTestCase):
expected_output = '''
<ol list-style-type="decimal">
<li>AAA<br />
<span class='pydocx-insert' author='' date=''>BBB</span>
<li>AAA<span class='pydocx-insert'>BBB</span>
</li>
<li>CCC</li>
</ol>
Expand All @@ -719,8 +718,7 @@ def get_xml(self):
class SmartTagInList(_TranslationTestCase):
expected_output = '''
<ol list-style-type="decimal">
<li>AAA<br />
BBB
<li>AAABBB
</li>
<li>CCC</li>
</ol>
Expand Down Expand Up @@ -875,8 +873,7 @@ def get_xml(self):
class SDTTestCase(_TranslationTestCase):
expected_output = '''
<ol list-style-type="decimal">
<li>AAA<br />
BBB
<li>AAABBB
</li>
<li>CCC</li>
</ol>
Expand Down