jenkins-bot has submitted this change. (
https://gerrit.wikimedia.org/r/c/pywikibot/core/+/516527 )
Change subject: [IMPR] use namedtuple as result of textlib.extract_sections
......................................................................
[IMPR] use namedtuple as result of textlib.extract_sections
Modify tests accordingly
Change-Id: Ie3e3e3f1891365178ad0b93fe1dfb2f8b1a0f0f4
---
M pywikibot/textlib.py
M tests/textlib_tests.py
2 files changed, 69 insertions(+), 60 deletions(-)
Approvals:
Hazard-SJ: Looks good to me, but someone else must approve
Xqt: Looks good to me, approved
jenkins-bot: Verified
diff --git a/pywikibot/textlib.py b/pywikibot/textlib.py
index 972c290..e2a177c 100644
--- a/pywikibot/textlib.py
+++ b/pywikibot/textlib.py
@@ -18,7 +18,7 @@
from collections import OrderedDict, namedtuple
from contextlib import suppress
from html.parser import HTMLParser
-from typing import Optional, Union
+from typing import List, NamedTuple, Optional, Tuple, Union
import pywikibot
from pywikibot.exceptions import InvalidTitle, SiteDefinitionError
@@ -834,6 +834,7 @@
# -------------------------------
_Heading = namedtuple('_Heading', ('text', 'start', 'end'))
_Section = namedtuple('_Section', ('title', 'content'))
+_Content = namedtuple('_Content', ('header', 'sections', 'footer'))
def _extract_headings(text: str, site) -> list:
@@ -864,16 +865,21 @@
return []
-def extract_sections(text: str, site=None) -> tuple:
+def extract_sections(
+ text: str, site=None
+) -> NamedTuple('_Content', [('header', str), # noqa: F821
+ ('body', List[Tuple[str, str]]), # noqa: F821
+ ('footer', str)]): # noqa: F821
"""
Return section headings and contents found in text.
- @return: The returned tuple contains the text parsed into three
- parts: The first part is a string containing header part above
- the first heading. The last part is also a string containing
- footer part after the last section. The middle part is a list
- of tuples, each tuple containing a string with section heading
- and a string with section content. Example article::
+ @return: The returned namedtuple contains the text parsed into
+ header, contents and footer parts: The header part is a string
+ containing text part above the first heading. The footer part
+ is also a string containing text part after the last section.
+ The section part is a list of tuples, each tuple containing a
+ string with section heading and a string with section content.
+ Example article::
'''A''' is a thing.
@@ -885,15 +891,14 @@
[[Category:Things starting with A]]
- ...is parsed into the following tuple::
+ ...is parsed into the following namedtuple::
- (header, body, footer)
- header = "'''A''' is a thing."
- body = [('== History of A ==', 'Some history...'),
- ('== Usage of A ==', 'Some usage...')]
- footer = '[[Category:Things starting with A]]'
+ result = extract_sections(text, site)
+ result.header = "'''A''' is a thing."
+ result.body = [('== History of A ==', 'Some history...'),
+ ('== Usage of A ==', 'Some usage...')]
+ result.footer = '[[Category:Things starting with A]]'
- @rtype: tuple of (str, list of tuples, str)
"""
headings = _extract_headings(text, site)
sections = _extract_sections(text, headings)
@@ -912,7 +917,7 @@
sections[-1].title, last_section_content[:-len(footer)])
else:
header = header[:-len(footer)]
- return header, sections, footer
+ return _Content(header, sections, footer)
# -----------------------------------------------
diff --git a/tests/textlib_tests.py b/tests/textlib_tests.py
index b647ab6..d6db787 100644
--- a/tests/textlib_tests.py
+++ b/tests/textlib_tests.py
@@ -1628,71 +1628,77 @@
"""Test the extract_sections function."""
+ def _extract_sections_tests(self, result, header, sections, footer):
+ """Test extract_sections function."""
+ self.assertIsInstance(result, tuple)
+ self.assertIsInstance(result.sections, list)
+ self.assertEqual(result, (header, sections, footer))
+ self.assertEqual(result.header, header)
+ self.assertEqual(result.sections, sections)
+ self.assertEqual(result.footer, footer)
+ if result.sections:
+ for section in sections:
+ self.assertIsInstance(section, tuple)
+ self.assertLength(section, 2)
+
def test_no_sections_no_footer(self):
"""Test for text having no sections or footer."""
- self.assertEqual(
- extract_sections('text', self.site),
- ('text', [], '')
- )
+ text = 'text'
+ result = extract_sections(text, self.site)
+ self._extract_sections_tests(result, text, [], '')
def test_no_sections_with_footer(self):
"""Test for text having footer but no section."""
- self.assertEqual(
- extract_sections('text\n\n[[Category:A]]', self.site),
- ('text\n\n', [], '[[Category:A]]')
- )
+ text = 'text\n\n[[Category:A]]'
+ result = extract_sections(text, self.site)
+ self._extract_sections_tests(result, 'text\n\n', [], '[[Category:A]]')
def test_with_section_no_footer(self):
"""Test for text having sections but no footer."""
- self.assertEqual(
- extract_sections(
- 'text\n\n'
+ text = ('text\n\n'
'==title==\n'
- 'content',
- self.site),
- ('text\n\n', [('==title==', '\ncontent')], '')
- )
+ 'content')
+ result = extract_sections(text, self.site)
+ self._extract_sections_tests(
+ result, 'text\n\n', [('==title==', '\ncontent')], '')
def test_with_section_with_footer(self):
"""Test for text having sections and footer."""
- self.assertEqual(
- extract_sections(
- 'text\n\n'
+ text = ('text\n\n'
'==title==\n'
'content\n'
- '[[Category:A]]\n',
- self.site),
- ('text\n\n', [('==title==', '\ncontent\n')], '[[Category:A]]\n')
- )
+ '[[Category:A]]\n')
+ result = extract_sections(text, self.site)
+ self._extract_sections_tests(
+ result,
+ 'text\n\n', [('==title==', '\ncontent\n')], '[[Category:A]]\n')
def test_with_h1_and_h2_sections(self):
"""Test for text having h1 and h2 sections."""
- self.assertEqual(
- extract_sections(
- 'text\n\n'
+ text = ('text\n\n'
'=first level=\n'
'foo\n'
'==title==\n'
- 'bar',
- self.site),
- ('text\n\n',
- [('=first level=', '\nfoo\n'), ('==title==', '\nbar')],
- '')
- )
+ 'bar')
+ result = extract_sections(text, self.site)
+ self._extract_sections_tests(
+ result,
+ 'text\n\n',
+ [('=first level=', '\nfoo\n'), ('==title==', '\nbar')],
+ '')
def test_with_h4_and_h2_sections(self):
"""Test for text having h4 and h2 sections."""
- self.assertEqual(
- extract_sections(
- 'text\n\n'
+ text = ('text\n\n'
'====title====\n'
'==title 2==\n'
- 'content',
- self.site),
- ('text\n\n',
- [('====title====', '\n'), ('==title 2==', '\ncontent')],
- '')
- )
+ 'content')
+ result = extract_sections(text, self.site)
+ self._extract_sections_tests(
+ result,
+ 'text\n\n',
+ [('====title====', '\n'), ('==title 2==', '\ncontent')],
+ '')
def test_long_comment(self):
r"""Test for text having a long expanse of white space.
@@ -1705,10 +1711,8 @@
https://www.regular-expressions.info/catastrophic.html
"""
text = '<!-- -->'
- self.assertEqual(
- extract_sections(text, self.site),
- (text, [], '')
- )
+ result = extract_sections(text, self.site)
+ self._extract_sections_tests(result, text, [], '')
if __name__ == '__main__': # pragma: no cover
--
To view, visit https://gerrit.wikimedia.org/r/c/pywikibot/core/+/516527
To unsubscribe, or for help writing mail filters, visit
https://gerrit.wikimedia.org/r/settings
Gerrit-Project: pywikibot/core
Gerrit-Branch: master
Gerrit-Change-Id: Ie3e3e3f1891365178ad0b93fe1dfb2f8b1a0f0f4
Gerrit-Change-Number: 516527
Gerrit-PatchSet: 9
Gerrit-Owner: Xqt <[email protected]>
Gerrit-Reviewer: Hazard-SJ <[email protected]>
Gerrit-Reviewer: John Vandenberg <[email protected]>
Gerrit-Reviewer: Matěj Suchánek <[email protected]>
Gerrit-Reviewer: Xqt <[email protected]>
Gerrit-Reviewer: jenkins-bot
Gerrit-MessageType: merged
_______________________________________________
Pywikibot-commits mailing list
[email protected]
https://lists.wikimedia.org/mailman/listinfo/pywikibot-commits
