jenkins-bot has submitted this change. (
https://gerrit.wikimedia.org/r/c/pywikibot/core/+/611425 )
Change subject: [4.0] Remove Python 2 related code in pagegenerators.py
......................................................................
[4.0] Remove Python 2 related code in pagegenerators.py
Change-Id: I376d19b712b27db7a7d56601c725f5b8391de4d7
---
M pywikibot/pagegenerators.py
1 file changed, 26 insertions(+), 45 deletions(-)
Approvals:
Zhuyifei1999: Looks good to me, approved
jenkins-bot: Verified
diff --git a/pywikibot/pagegenerators.py b/pywikibot/pagegenerators.py
index 1328bd4..a37e88b 100644
--- a/pywikibot/pagegenerators.py
+++ b/pywikibot/pagegenerators.py
@@ -18,8 +18,6 @@
#
# Distributed under the terms of the MIT license.
#
-from __future__ import absolute_import, division, unicode_literals
-
import calendar
import codecs
import datetime
@@ -30,6 +28,7 @@
from datetime import timedelta
from functools import partial
+from itertools import zip_longest
from requests.exceptions import ReadTimeout
from warnings import warn
@@ -57,12 +56,7 @@
UnknownExtension,
)
from pywikibot.proofreadpage import ProofreadPage
-from pywikibot.tools import PY2, UnicodeType
-if not PY2:
- from itertools import zip_longest
-else:
- from itertools import izip_longest as zip_longest
_logger = 'pagegenerators'
@@ -423,7 +417,7 @@
filter_unique, key=lambda page: '{}:{}:{}'.format(*page._cmpkey()))
-class GeneratorFactory(object):
+class GeneratorFactory:
"""Process command line arguments and return appropriate page generator.
@@ -674,7 +668,7 @@
"""
total = None
start = start or None # because start might be an empty string
- if isinstance(start, UnicodeType) and len(start) == 8:
+ if isinstance(start, str) and len(start) == 8:
start = pywikibot.Timestamp.strptime(start, '%Y%m%d')
elif start is not None:
try:
@@ -1209,11 +1203,7 @@
if value == '':
value = None
- try:
- handler = getattr(self, '_handle_' + arg[1:], None)
- except UnicodeEncodeError:
- # getattr() on py2 does implicit unicode -> str
- return False
+ handler = getattr(self, '_handle_' + arg[1:], None)
if handler:
handler_result = handler(value)
if isinstance(handler_result, bool):
@@ -1545,8 +1535,7 @@
return
return
kwargs['startprefix'] = start
- for a in category.articles(**kwargs):
- yield a
+ yield from category.articles(**kwargs)
@deprecated_args(step=None)
@@ -1633,7 +1622,7 @@
def PagesFromTitlesGenerator(iterable, site=None):
"""
- Generate pages from the titles (unicode strings) yielded by iterable.
+ Generate pages from the titles (strings) yielded by iterable.
@param site: Site for generator results.
@type site: L{pywikibot.site.BaseSite}
@@ -1641,7 +1630,7 @@
if site is None:
site = pywikibot.Site()
for title in iterable:
- if not isinstance(title, UnicodeType):
+ if not isinstance(title, str):
break
yield pywikibot.Page(pywikibot.Link(title, site))
@@ -1783,7 +1772,7 @@
% page)
-class ItemClaimFilter(object):
+class ItemClaimFilter:
"""Item claim filter."""
@@ -1876,7 +1865,7 @@
% page)
-class RegexFilter(object):
+class RegexFilter:
"""Regex filter."""
@@ -1902,7 +1891,7 @@
regex = [regex]
# Test if regex is already compiled.
# We assume that all list components have the same type
- if isinstance(regex[0], UnicodeType):
+ if isinstance(regex[0], str):
regex = [re.compile(r, flag) for r in regex]
return regex
@@ -2093,7 +2082,7 @@
@type show_filtered: bool
"""
if timestamp:
- if isinstance(timestamp, UnicodeType):
+ if isinstance(timestamp, str):
ts = pywikibot.Timestamp.fromtimestampformat(timestamp)
else:
ts = timestamp
@@ -2190,8 +2179,8 @@
else:
break
pywikibot.sleep(sleep_duration)
- for item in list(filtered_generator())[::-1]:
- yield item
+
+ yield from list(filtered_generator())[::-1]
@deprecated_args(pageNumber='groupsize', step='groupsize', lookahead=None)
@@ -2213,12 +2202,11 @@
if len(sites[site]) >= groupsize:
# if this site is at the groupsize, process it
group = sites.pop(site)
- for i in site.preloadpages(group, groupsize):
- yield i
+ yield from site.preloadpages(group, groupsize)
+
for site, pages in sites.items():
# process any leftover sites that never reached the groupsize
- for i in site.preloadpages(pages, groupsize):
- yield i
+ yield from site.preloadpages(pages, groupsize)
@deprecated_args(step='groupsize')
@@ -2232,8 +2220,7 @@
if not page_count:
return
- for page in PreloadingGenerator(generator, page_count):
- yield page
+ yield from PreloadingGenerator(generator, page_count)
@deprecated_args(step='groupsize')
@@ -2256,13 +2243,12 @@
# if this site is at the groupsize, process it
group = sites.pop(site)
repo = site.data_repository()
- for i in repo.preload_entities(group, groupsize):
- yield i
+ yield from repo.preload_entities(group, groupsize)
+
for site, pages in sites.items():
# process any leftover sites that never reached the groupsize
repo = site.data_repository()
- for i in repo.preload_entities(pages, groupsize):
- yield i
+ yield from repo.preload_entities(pages, groupsize)
@deprecated_args(number='total', step=None, repeat=None)
@@ -2667,7 +2653,7 @@
# following classes just ported from version 1 without revision; not tested
-class GoogleSearchPageGenerator(object):
+class GoogleSearchPageGenerator:
"""
Page generator using Google search results.
@@ -2719,8 +2705,7 @@
'To install, please run: pip install google.')
exit(1)
pywikibot.warning('Please read http://www.google.com/accounts/TOS')
- for url in google.search(query):
- yield url
+ yield from google.search(query)
def __iter__(self):
"""Iterate results."""
@@ -2845,10 +2830,7 @@
def __next__(self):
"""Get next Page."""
while True:
- try:
- entry = next(self.parser)
- except StopIteration:
- raise
+ entry = next(self.parser)
if self.skipping:
if entry.title < self.start:
continue
@@ -2867,7 +2849,7 @@
def __next__(self):
"""Get next Page from dump and remove the text."""
- page = super(XMLDumpPageGenerator, self).__next__()
+ page = super().__next__()
del page.text
return page
@@ -3002,7 +2984,7 @@
return (pywikibot.ItemPage(repo, item['id']) for item in data)
-class PetScanPageGenerator(object):
+class PetScanPageGenerator:
"""Queries PetScan (https://petscan.wmflabs.org/) to generate pages."""
def __init__(self, categories, subset_combination=True, namespaces=None,
@@ -3075,8 +3057,7 @@
'received {0} status from {1}'.format(req.status, req.uri))
j = json.loads(req.text)
raw_pages = j['*'][0]['a']['*']
- for raw_page in raw_pages:
- yield raw_page
+ yield from raw_pages
def __iter__(self):
for raw_page in self.query():
--
To view, visit https://gerrit.wikimedia.org/r/c/pywikibot/core/+/611425
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: I376d19b712b27db7a7d56601c725f5b8391de4d7
Gerrit-Change-Number: 611425
Gerrit-PatchSet: 1
Gerrit-Owner: Xqt <[email protected]>
Gerrit-Reviewer: Zhuyifei1999 <[email protected]>
Gerrit-Reviewer: jenkins-bot
Gerrit-MessageType: merged
_______________________________________________
Pywikibot-commits mailing list
[email protected]
https://lists.wikimedia.org/mailman/listinfo/pywikibot-commits
