jenkins-bot has submitted this change and it was merged. Change subject: Fix anomalous escape (\) ...................................................................... Fix anomalous escape (\) Also fix checkimages to use given site, and add tests. Change-Id: I8bcea1d5db3b5d0c2c9ada19382ada01f7339044 --- M .travis.yml M pywikibot/__init__.py M pywikibot/botirc.py M pywikibot/i18n.py M pywikibot/page.py M pywikibot/pagegenerators.py M pywikibot/textlib.py M scripts/archivebot.py M scripts/casechecker.py M scripts/category.py M scripts/checkimages.py M scripts/cosmetic_changes.py M scripts/image.py M scripts/imagerecat.py M scripts/interwiki.py M scripts/maintenance/compat2core.py M scripts/reflinks.py M scripts/replace.py M scripts/revertbot.py M scripts/script_wui.py M scripts/selflink.py M scripts/solve_disambiguation.py M scripts/template.py M scripts/weblinkchecker.py A tests/checkimages_tests.py 25 files changed, 140 insertions(+), 99 deletions(-) Approvals: XZise: Looks good to me, approved jenkins-bot: Verified diff --git a/.travis.yml b/.travis.yml index addcc33..f0c970b 100644 --- a/.travis.yml +++ b/.travis.yml @@ -38,6 +38,7 @@ - if [[ -n "$USER_PASSWORD" && -n "$PYWIKIBOT2_USERNAME" ]]; then echo "usernames['wikipedia']['en'] = '$PYWIKIBOT2_USERNAME'" >> ~/.pywikibot/user-config.py; fi - if [[ -n "$USER_PASSWORD" && -n "$PYWIKIBOT2_USERNAME" ]]; then echo "usernames['wikipedia']['test'] = '$PYWIKIBOT2_USERNAME'" >> ~/.pywikibot/user-config.py; fi - if [[ -n "$USER_PASSWORD" && -n "$PYWIKIBOT2_USERNAME" ]]; then echo "usernames['wikidata']['test'] = '$PYWIKIBOT2_USERNAME'" >> ~/.pywikibot/user-config.py; fi + - if [[ -n "$USER_PASSWORD" && -n "$PYWIKIBOT2_USERNAME" ]]; then echo "usernames['commons']['commons'] = '$PYWIKIBOT2_USERNAME'" >> ~/.pywikibot/user-config.py; fi - if [[ -n "$USER_PASSWORD" && -n "$PYWIKIBOT2_USERNAME" ]]; then echo "('$PYWIKIBOT2_USERNAME', '$USER_PASSWORD')" > ~/.pywikibot/passwordfile; fi diff --git a/pywikibot/__init__.py b/pywikibot/__init__.py index b93f53f..b7161d8 100644 --- a/pywikibot/__init__.py +++ b/pywikibot/__init__.py @@ -398,7 +398,7 @@ @classmethod def fromTimestr(cls, datetimestr, precision=14, before=0, after=0, timezone=0, calendarmodel=None, site=None): - match = re.match('([-+]?\d+)-(\d+)-(\d+)T(\d+):(\d+):(\d+)Z', + match = re.match(r'([-+]?\d+)-(\d+)-(\d+)T(\d+):(\d+):(\d+)Z', datetimestr) if not match: raise ValueError(u"Invalid format: '%s'" % datetimestr) diff --git a/pywikibot/botirc.py b/pywikibot/botirc.py index ce5e1d3..e4868a1 100644 --- a/pywikibot/botirc.py +++ b/pywikibot/botirc.py @@ -50,8 +50,9 @@ self.channel = channel self.site = site self.other_ns = re.compile( - u'14\[\[07(' + u'|'.join([item[0] for item in - list(site.namespaces().values()) if item[0]]) + u')') + u'\x0314\\[\\[\x0307(%s)' + % u'|'.join(item.custom_name for item in site.namespaces().values() + if item != 0)) self.api_url = self.site.apipath() self.api_url += '?action=query&meta=siteinfo&siprop=statistics&format=xml' self.api_found = re.compile(r'articles="(.*?)"') diff --git a/pywikibot/i18n.py b/pywikibot/i18n.py index bd9b418..f0bdb23 100644 --- a/pywikibot/i18n.py +++ b/pywikibot/i18n.py @@ -28,7 +28,7 @@ if sys.version_info[0] > 2: basestring = (str, ) -PLURAL_PATTERN = '{{PLURAL:(?:%\()?([^\)]*?)(?:\)d)?\|(.*?)}}' +PLURAL_PATTERN = r'{{PLURAL:(?:%\()?([^\)]*?)(?:\)d)?\|(.*?)}}' # Package name for the translation messages messages_package_name = 'scripts.i18n' diff --git a/pywikibot/page.py b/pywikibot/page.py index ea260c7..4a65bef 100644 --- a/pywikibot/page.py +++ b/pywikibot/page.py @@ -3296,7 +3296,7 @@ # to the namespace case=first-letter. # Validate the title is 'Q' and a positive integer. - if not re.match('^Q[1-9]\d*$', self._link.title): + if not re.match(r'^Q[1-9]\d*$', self._link.title): raise pywikibot.InvalidTitle( u"'%s' is not a valid item page title" % self._link.title) diff --git a/pywikibot/pagegenerators.py b/pywikibot/pagegenerators.py index 1a73e8f..9a66176 100644 --- a/pywikibot/pagegenerators.py +++ b/pywikibot/pagegenerators.py @@ -730,7 +730,7 @@ p = re.compile(r'(?<!\\),') # Match "," only if there no "\" before temp = [] # Array to store split argument for arg in p.split(claim): - temp.append(arg.replace('\,', ',').split('=')) + temp.append(arg.replace(r'\,', ',').split('=')) self.claimfilter_list.append((temp[0][0], temp[0][1], dict(temp[1:]), ifnot)) return True diff --git a/pywikibot/textlib.py b/pywikibot/textlib.py index 145ea5f..aa40e10 100644 --- a/pywikibot/textlib.py +++ b/pywikibot/textlib.py @@ -32,7 +32,8 @@ from pywikibot.tools import OrderedDict TEMP_REGEX = re.compile( - '{{(?:msg:)?(?P<name>[^{\|]+?)(?:\|(?P<params>[^{]+?(?:{[^{]+?}[^{]*?)?))?}}') + r'{{(?:msg:)?(?P<name>[^{\|]+?)(?:\|(?P<params>[^{]+?(?:{[^{]+?}[^{]*?)?))?}}') + NON_LATIN_DIGITS = { 'ckb': u'٠١٢٣٤٥٦٧٨٩', 'fa': u'۰۱۲۳۴۵۶۷۸۹', @@ -174,8 +175,8 @@ marker1 = findmarker(text) marker2 = findmarker(text, u'##', u'#') Rvalue = re.compile('{{{.+?}}}') - Rmarker1 = re.compile('%(mark)s(\d+)%(mark)s' % {'mark': marker1}) - Rmarker2 = re.compile('%(mark)s(\d+)%(mark)s' % {'mark': marker2}) + Rmarker1 = re.compile(r'%(mark)s(\d+)%(mark)s' % {'mark': marker1}) + Rmarker2 = re.compile(r'%(mark)s(\d+)%(mark)s' % {'mark': marker2}) # hide the flat template marker dontTouchRegexes.append(Rmarker1) origin = text @@ -600,9 +601,9 @@ # Do we have a noinclude at the end of the template? parts = s2.split(includeOff) lastpart = parts[-1] - if re.match('\s*%s' % marker, lastpart): + if re.match(r'\s*%s' % marker, lastpart): # Put the langlinks back into the noinclude's - regexp = re.compile('%s\s*%s' % (includeOff, marker)) + regexp = re.compile(r'%s\s*%s' % (includeOff, marker)) newtext = regexp.sub(s + includeOff, s2) else: # Put the langlinks at the end, inside noinclude's @@ -734,7 +735,7 @@ site=site) if marker: # avoid having multiple linefeeds at the end of the text - text = re.sub('\s*%s' % re.escape(marker), config.LS + marker, + text = re.sub(r'\s*%s' % re.escape(marker), config.LS + marker, text.strip()) return text.strip() @@ -920,12 +921,12 @@ # Note: While allowing dots inside URLs, MediaWiki will regard # dots at the end of the URL as not part of that URL. # The same applies to comma, colon and some other characters. - notAtEnd = '\]\s\.:;,<>"\|\)' + notAtEnd = r'\]\s\.:;,<>"\|\)' # So characters inside the URL can be anything except whitespace, # closing squared brackets, quotation marks, greater than and less # than, and the last character also can't be parenthesis or another # character disallowed by MediaWiki. - notInside = '\]\s<>"' + notInside = r'\]\s<>"' # The first half of this regular expression is required because '' is # not allowed inside links. For example, in this wiki text: # ''Please see https://www.example.org.'' @@ -1216,7 +1217,7 @@ """ # match preceding colon for text links - section = re.sub(r'\\\[\\\[(\\:)?', '\[\[\:?', re.escape(section)) + section = re.sub(r'\\\[\\\[(\\:)?', r'\[\[\:?', re.escape(section)) # match underscores and white spaces section = re.sub(r'\\?[ _]', '[ _]', section) m = re.search("=+[ ']*%s[ ']*=+" % section, pagetext) diff --git a/scripts/archivebot.py b/scripts/archivebot.py index 588e3be..993c454 100644 --- a/scripts/archivebot.py +++ b/scripts/archivebot.py @@ -186,7 +186,7 @@ 'B' (bytes) or 'T' (threads). """ - r = re.search('(\d+) *([BkKMT]?)', string) + r = re.search(r'(\d+) *([BkKMT]?)', string) val, unit = (int(r.group(1)), r.group(2)) if unit == 'M': val *= 1024 diff --git a/scripts/casechecker.py b/scripts/casechecker.py index e77e856..4a9a684 100644 --- a/scripts/casechecker.py +++ b/scripts/casechecker.py @@ -117,7 +117,7 @@ latClrFnt = u'<font color=brown>' suffixClr = u'</font>' - wordBreaker = re.compile(u'[ _\-/\|#[\]():]') + wordBreaker = re.compile(r'[ _\-/\|#[\]():]') stripChars = u' \t,' titles = True diff --git a/scripts/category.py b/scripts/category.py index 2236f11..4e2fcc2 100755 --- a/scripts/category.py +++ b/scripts/category.py @@ -303,7 +303,7 @@ site = pagelink.site # regular expression that matches a name followed by a space and # disambiguation brackets. Group 1 is the name without the rest. - bracketsR = re.compile('(.*) \(.+?\)') + bracketsR = re.compile(r'(.*) \(.+?\)') match_object = bracketsR.match(page_name) if match_object: page_name = match_object.group(1) diff --git a/scripts/checkimages.py b/scripts/checkimages.py index 7b94bdb..91cc078 100644 --- a/scripts/checkimages.py +++ b/scripts/checkimages.py @@ -561,6 +561,17 @@ # END OF CONFIGURATION. +SETTINGS_REGEX = re.compile(r""" +<-------\ ------->\n +\*[Nn]ame\ ?=\ ?['"](.*?)['"]\n +\*([Ff]ind|[Ff]indonly)\ ?=\ ?(.*?)\n +\*[Ii]magechanges\ ?=\ ?(.*?)\n +\*[Ss]ummary\ ?=\ ?['"](.*?)['"]\n +\*[Hh]ead\ ?=\ ?['"](.*?)['"]\n +\*[Tt]ext\ ?=\ ?['"](.*?)['"]\n +\*[Mm]ex\ ?=\ ?['"]?([^\n]*?)['"]?\n +""", re.UNICODE | re.DOTALL | re.VERBOSE) + class LogIsFull(pywikibot.Error): @@ -603,7 +614,7 @@ self.comment = i18n.translate(self.site, msg_comm, fallback=True) # Adding the bot's nickname at the notification text if needed. botolist = i18n.translate(self.site, bot_list) - project = pywikibot.Site().family.name + project = site.family.name self.project = project bot = config.usernames[project] try: @@ -1159,19 +1170,9 @@ self.settingsData = list() try: testo = wikiPage.get() - r = re.compile( - r"<------- ------->\n" - "\*[Nn]ame ?= ?['\"](.*?)['\"]\n" - "\*([Ff]ind|[Ff]indonly)=(.*?)\n" - "\*[Ii]magechanges=(.*?)\n" - "\*[Ss]ummary=['\"](.*?)['\"]\n" - "\*[Hh]ead=['\"](.*?)['\"]\n" - "\*[Tt]ext ?= ?['\"](.*?)['\"]\n" - "\*[Mm]ex ?= ?['\"]?([^\n]*?)['\"]?\n", - re.UNICODE | re.DOTALL) number = 1 - for m in r.finditer(testo): + for m in SETTINGS_REGEX.finditer(testo): name = str(m.group(1)) find_tipe = str(m.group(2)) find = str(m.group(3)) @@ -1185,7 +1186,7 @@ self.settingsData += [tupla] number += 1 - if self.settingsData == list(): + if not self.settingsData: pywikibot.output( u"You've set wrongly your settings, please take a " u"look to the relative page. (run without them)") diff --git a/scripts/cosmetic_changes.py b/scripts/cosmetic_changes.py index 3d5f5b2..04a19e6 100755 --- a/scripts/cosmetic_changes.py +++ b/scripts/cosmetic_changes.py @@ -143,10 +143,10 @@ deprecatedTemplates = { 'wikipedia': { 'de': [ - (u'Belege', u'Belege fehlen\g<parameters>'), - (u'Quelle', u'Belege fehlen\g<parameters>'), - (u'Quellen', u'Belege fehlen\g<parameters>'), - (u'Quellen fehlen', u'Belege fehlen\g<parameters>'), + (u'Belege', u'Belege fehlen\\g<parameters>'), + (u'Quelle', u'Belege fehlen\\g<parameters>'), + (u'Quellen', u'Belege fehlen\\g<parameters>'), + (u'Quellen fehlen', u'Belege fehlen\\g<parameters>'), ], } } @@ -337,7 +337,7 @@ # Removing the stars' issue starstext = textlib.removeDisabledParts(text) for star in starsList: - regex = re.compile('(\{\{(?:template:|)%s\|.*?\}\}[\s]*)' + regex = re.compile(r'(\{\{(?:template:|)%s\|.*?\}\}[\s]*)' % star, re.I) found = regex.findall(starstext) if found != []: @@ -431,8 +431,8 @@ text = textlib.replaceExcept( text, r'\[\[(?P<left>.+?:.+?\..+?\|) *(' + '|'.join(aliases) + - ') *(?P<right>(\|.*?)?\]\])', - r'[[\g<left>' + aliases[0] + '\g<right>', exceptions) + r') *(?P<right>(\|.*?)?\]\])', + r'[[\g<left>' + aliases[0] + r'\g<right>', exceptions) return text def cleanUpLinks(self, text): @@ -637,7 +637,7 @@ text = textlib.replaceExcept( text, r'(?m)^(?P<bullet>[:;]*(\*+|#+)[:;\*#]*)(?P<char>[^\s\*#:;].+?)', - '\g<bullet> \g<char>', + r'\g<bullet> \g<char>', exceptions) return text @@ -809,8 +809,8 @@ # do not change inside file links namespaces = list(self.site.namespace(6, all=True)) pattern = re.compile( - u'\[\[(' + '|'.join(namespaces) + - '):.+?\.\w+? *(\|((\[\[.*?\]\])|.)*)?\]\]', + u'\\[\\[(%s):.+?\\.\\w+? *(\\|((\\[\\[.*?\\]\\])|.)*)?\\]\\]' + % u'|'.join(namespaces), re.UNICODE) # not to let bot edits in latin content exceptions.append(re.compile(u"[^%(fa)s] *?\"*? *?, *?[^%(fa)s]" @@ -834,7 +834,7 @@ for i in range(0, 10): text = textlib.replaceExcept(text, old[i], new[i], exceptions) # do not change digits in class, style and table params - pattern = re.compile(u'\w+=(".+?"|\d+)', re.UNICODE) + pattern = re.compile(r'\w+=(".+?"|\d+)', re.UNICODE) exceptions.append(pattern) # do not change digits inside html-tags pattern = re.compile(u'<[/]*?[^</]+?[/]*?>', re.UNICODE) diff --git a/scripts/image.py b/scripts/image.py index 00758e4..fb26ad2 100644 --- a/scripts/image.py +++ b/scripts/image.py @@ -155,7 +155,10 @@ if self.new_image: if not self.getOption('loose'): - replacements.append((image_regex, '[[' + self.site.image_namespace() + ':' + self.new_image + '\g<parameters>]]')) + replacements.append((image_regex, + u'[[%s:%s\\g<parameters>]]' + % (self.site.image_namespace(), + self.new_image))) else: replacements.append((image_regex, self.new_image)) else: diff --git a/scripts/imagerecat.py b/scripts/imagerecat.py index ab8d03f..b911148 100644 --- a/scripts/imagerecat.py +++ b/scripts/imagerecat.py @@ -275,7 +275,7 @@ project = '' article = '' usageRe = re.compile( - '^(?P<lang>([\w-]+))\.(?P<project>([\w]+))\.org:(?P<articles>\s(.*))') + r'^(?P<lang>([\w-]+))\.(?P<project>([\w]+))\.org:(?P<articles>\s(.*))') matches = usageRe.search(use) if matches: if matches.group('lang'): @@ -377,7 +377,7 @@ toFilter = toFilter + "[[Category:" + cat + "]]\n" parameters = urlencode({'source': toFilter.encode('utf-8'), 'bot': '1'}) - filterCategoriesRe = re.compile('\[\[Category:([^\]]*)\]\]') + filterCategoriesRe = re.compile(r'\[\[Category:([^\]]*)\]\]') try: filterCategoriesPage = urlopen( "https://toolserver.org/~multichill/filtercats.php?%s" % parameters) @@ -416,10 +416,11 @@ def removeTemplates(oldtext=u''): """Remove {{Uncategorized}} and {{Check categories}} templates.""" result = re.sub( - u'\{\{\s*([Uu]ncat(egori[sz]ed( image)?)?|[Nn]ocat|[Nn]eedscategory)[^}]*\}\}', u'', oldtext) + r'{{\s*([Uu]ncat(egori[sz]ed( image)?)?|[Nn]ocat|[Nn]eedscategory)[^}]*}}', + u'', oldtext) result = re.sub(u'<!-- Remove this line once you have added categories -->', u'', result) - result = re.sub(u'\{\{\s*[Cc]heck categories[^}]*\}\}', u'', result) + result = re.sub(r'\{\{\s*[Cc]heck categories[^}]*\}\}', u'', result) return result diff --git a/scripts/interwiki.py b/scripts/interwiki.py index 93cb2f8..f17bc0c 100755 --- a/scripts/interwiki.py +++ b/scripts/interwiki.py @@ -1850,7 +1850,7 @@ interwikis = [pywikibot.Page(l) for l in page.iterlanglinks()] # remove interwiki links to ignore - for iw in re.finditer('<!-- *\[\[(.*?:.*?)\]\] *-->', pagetext): + for iw in re.finditer(r'<!-- *\[\[(.*?:.*?)\]\] *-->', pagetext): try: ignorepage = pywikibot.Page(page.site, iw.groups()[0]) if (new[ignorepage.site] == ignorepage) and \ diff --git a/scripts/maintenance/compat2core.py b/scripts/maintenance/compat2core.py index a8b2c58..386d509 100644 --- a/scripts/maintenance/compat2core.py +++ b/scripts/maintenance/compat2core.py @@ -52,32 +52,33 @@ ('import catlib\r?\n', ''), ('import userlib\r?\n', ''), # change wikipedia to pywikibot, exclude URLs - ('(?<!\.)wikipedia\.', u'pywikibot.'), + (r'(?<!\.)wikipedia\.', u'pywikibot.'), # site instance call - ('pywikibot\.getSite\s*\(\s*', 'pywikibot.Site('), + (r'pywikibot\.getSite\s*\(\s*', 'pywikibot.Site('), # lang is different from code. We should use code in core - ('([Ss])ite.lang(?:uage\(\))?', r'\1ite.code'), + (r'([Ss])ite.lang(?:uage\(\))?', r'\1ite.code'), # change compat library classes to pywikibot intrinsic classes - ('catlib\.Category\s*\(\s*', 'pywikibot.Category('), - ('catlib\.change_category\s*\((\s*)(?P<article>.+?),\s*(?P<oldcat>.+?),', + (r'catlib\.Category\s*\(\s*', 'pywikibot.Category('), + (r'catlib\.change_category\s*\((\s*)(?P<article>.+?),\s*(?P<oldcat>.+?),', r'\g<article>.change_category(\1\g<oldcat>,'), - ('userlib\.User\s*\(\s*', 'pywikibot.User('), + (r'userlib\.User\s*\(\s*', 'pywikibot.User('), # change ImagePage to FilePage - ('pywikibot\.ImagePage\s*\(\s*', 'pywikibot.FilePage('), + (r'pywikibot\.ImagePage\s*\(\s*', 'pywikibot.FilePage('), # deprecated title methods - ('\.urlname\s*\(\s*\)', '.title(asUrl=True)'), - ('\.urlname\s*\(\s*(?:withNamespace\s*=\s*)?(True|False)+\s*\)', + (r'\.urlname\s*\(\s*\)', '.title(asUrl=True)'), + (r'\.urlname\s*\(\s*(?:withNamespace\s*=\s*)?(True|False)+\s*\)', r'.title(asUrl=True, withNamespace=\1)'), - ('\.titleWithoutNamespace\s*\(\s*\)', '.title(withNamespace=False)'), - ('\.sectionFreeTitle\s*\(\s*\)', '.title(withSection=False)'), - ('\.aslink\s*\(\s*\)', '.title(asLink=True)'), + (r'\.titleWithoutNamespace\s*\(\s*\)', '.title(withNamespace=False)'), + (r'\.sectionFreeTitle\s*\(\s*\)', '.title(withSection=False)'), + (r'\.aslink\s*\(\s*\)', '.title(asLink=True)'), # other deprecated methods - ('(?<!site)\.encoding\s*\(\s*\)', '.site.encoding()'), - ('\.newimages\s*\(', '.newfiles('), + (r'(?<!site)\.encoding\s*\(\s*\)', '.site.encoding()'), + (r'\.newimages\s*\(', '.newfiles('), # new core methods - ('\.get\s*\(\s*get_redirect\s*=\s*True\s*\)', '.text'), + (r'\.get\s*\(\s*get_redirect\s*=\s*True\s*\)', '.text'), # stopme() is done by the framework itself - ('(\s*)try\:\s*\r?\n\s+main\(\)\s*\r?\n\s*finally\:\s*\r?\n\s+pywikibot\.stopme\(\)', + (r'(\s*)try\:\s*\r?\n\s+main\(\)\s*\r?\n\s*finally\:\s*\r?\n' + r'\s+pywikibot\.stopme\(\)', r'\1main()'), ) diff --git a/scripts/reflinks.py b/scripts/reflinks.py index f50083b..f7badef 100644 --- a/scripts/reflinks.py +++ b/scripts/reflinks.py @@ -122,7 +122,7 @@ # Extracts the domain name domain = re.compile(r'^(\w+)://(?:www.|)([^/]+)') -globalbadtitles = """ +globalbadtitles = r""" # is (test| # starts with @@ -304,11 +304,11 @@ def __init__(self): # Match references self.REFS = re.compile( - u'(?i)<ref(?P<params>[^>/]*)>(?P<content>.*?)</ref>') + r'(?i)<ref(?P<params>[^>/]*)>(?P<content>.*?)</ref>') self.NAMES = re.compile( - u'(?i).*name\s*=\s*(?P<quote>"?)\s*(?P<name>.+)\s*(?P=quote).*') + r'(?i).*name\s*=\s*(?P<quote>"?)\s*(?P<name>.+)\s*(?P=quote).*') self.GROUPS = re.compile( - u'(?i).*group\s*=\s*(?P<quote>"?)\s*(?P<group>.+)\s*(?P=quote).*') + r'(?i).*group\s*=\s*(?P<quote>"?)\s*(?P<group>.+)\s*(?P=quote).*') self.autogen = i18n.twtranslate(pywikibot.Site(), 'reflinks-autogen') def process(self, text): @@ -401,7 +401,7 @@ if v[1]: name = u'"%s"' % name text = re.sub( - u'<ref name\s*=\s*(?P<quote>"?)\s*%s\s*(?P=quote)\s*/>' % k, + u'<ref name\\s*=\\s*(?P<quote>"?)\\s*%s\\s*(?P=quote)\\s*/>' % k, u'<ref name=%s />' % name, text) return text @@ -662,7 +662,7 @@ s = self.CHARSET.search(tag) if s: tmp = s.group('enc').strip("\"' ").lower() - naked = re.sub('[ _\-]', '', tmp) + naked = re.sub(r'[ _\-]', '', tmp) # Convert to python correct encoding names if naked == "gb2312": enc.append("gbk") diff --git a/scripts/replace.py b/scripts/replace.py index 95fe144..cbc9a43 100755 --- a/scripts/replace.py +++ b/scripts/replace.py @@ -627,9 +627,9 @@ def prepareRegexForMySQL(pattern): """Convert regex to MySQL syntax.""" - pattern = pattern.replace('\s', '[:space:]') - pattern = pattern.replace('\d', '[:digit:]') - pattern = pattern.replace('\w', '[:alnum:]') + pattern = pattern.replace(r'\s', '[:space:]') + pattern = pattern.replace(r'\d', '[:digit:]') + pattern = pattern.replace(r'\w', '[:alnum:]') pattern = pattern.replace("'", "\\" + "'") # pattern = pattern.replace('\\', '\\\\') diff --git a/scripts/revertbot.py b/scripts/revertbot.py index 161263e..4f99c73 100644 --- a/scripts/revertbot.py +++ b/scripts/revertbot.py @@ -131,7 +131,7 @@ if 'top' in item: page = pywikibot.Page(self.site, item['title']) text = page.get(get_redirect=True) - pattern = re.compile(u'\[\[.+?:.+?\..+?\]\]', re.UNICODE) + pattern = re.compile(r'\[\[.+?:.+?\..+?\]\]', re.UNICODE) return pattern.search(text) >= 0 return False diff --git a/scripts/script_wui.py b/scripts/script_wui.py index 7250589..fd6e792 100755 --- a/scripts/script_wui.py +++ b/scripts/script_wui.py @@ -280,7 +280,7 @@ # (might be a problem here for TS and SGE, output string has another encoding) if False: buffer = buffer.decode(pywikibot.config.console_encoding) - buffer = re.sub("\03\{(.*?)\}(.*?)\03\{default\}", "\g<2>", buffer) + buffer = re.sub(r'\03\{(.*?)\}(.*?)\03\{default\}', r'\g<2>', buffer) if rev is None: rev = page.latestRevision() link = page.permalink(oldid=rev) diff --git a/scripts/selflink.py b/scripts/selflink.py index 1687c97..734cf39 100644 --- a/scripts/selflink.py +++ b/scripts/selflink.py @@ -53,7 +53,7 @@ self.linkR = re.compile( r'\[\[(?P<title>[^\]\|#]*)' r'(?P<section>#[^\]\|]*)?' - '(\|(?P<label>[^\]]*))?\]\]' + r'(\|(?P<label>[^\]]*))?\]\]' r'(?P<linktrail>' + linktrail + ')') def handleNextLink(self, page, match, context=100): diff --git a/scripts/solve_disambiguation.py b/scripts/solve_disambiguation.py index f25f617..f36b28e 100644 --- a/scripts/solve_disambiguation.py +++ b/scripts/solve_disambiguation.py @@ -202,7 +202,7 @@ 'en': [ u'Wikipedia:Links to disambiguating pages', u'Wikipedia:Disambiguation pages with links', - u'Wikipedia:Multiple-place names \([A-Z]\)', + u'Wikipedia:Multiple-place names \\([A-Z]\\)', u'Wikipedia:Non-unique personal name', u"User:Jerzy/Disambiguation Pages i've Editted", u'User:Gareth Owen/inprogress', @@ -252,7 +252,7 @@ # hu:Wikipédia:Kocsmafal (egyéb)#Hol nem kell egyértelműsíteni? # 2012-02-08 u'Wikipédia:(?!Sportműhely/Eddigi cikkeink).*', - u'.*\(egyértelműsítő lap\)$', + u'.*\\(egyértelműsítő lap\\)$', u'.*[Vv]ita:.*', u'Szerkesztő:[^/]+$', ], @@ -293,7 +293,7 @@ u'Overleg Wikipedia:Logboek.*', u'Wikipedia:Logboek.*', u'Overleg gebruiker:Sybren/test.*', - u'Overleg gebruiker:[0-9][0-9]?[0-9]?\.[0-9][0-9]?[0-9]?\.[0-9][0-9]?[0-9]?\.[0-9][0-9]?[0-9]?', + u'Overleg gebruiker:([0-9][0-9]?[0-9]?\\.){3}[0-9][0-9]?[0-9]?', u'Overleg:Lage Landen (staatkunde)', u'Wikipedia:.*[aA]rchief.*', u'Wikipedia:Doorverwijspagina', @@ -757,7 +757,7 @@ search_text = text[m.end():m.end() + context] # figure out where the link (and sentance) ends, put note # there - end_of_word_match = re.search("\s", search_text) + end_of_word_match = re.search(r'\s', search_text) if end_of_word_match: position_split = end_of_word_match.start(0) else: diff --git a/scripts/template.py b/scripts/template.py index de98b32..25aad55 100755 --- a/scripts/template.py +++ b/scripts/template.py @@ -265,11 +265,11 @@ if self.getOption('subst') and self.getOption('remove'): replacements.append((templateRegex, - '{{subst:%s\g<parameters>}}' % new)) + r'{{subst:%s\g<parameters>}}' % new)) exceptions['inside-tags'] = ['ref', 'gallery'] elif self.getOption('subst'): replacements.append((templateRegex, - '{{subst:%s\g<parameters>}}' % old)) + r'{{subst:%s\g<parameters>}}' % old)) exceptions['inside-tags'] = ['ref', 'gallery'] elif self.getOption('remove'): replacements.append((templateRegex, '')) @@ -281,7 +281,7 @@ default=False, automatic_quit=False): continue replacements.append((templateRegex, - '{{%s\g<parameters>}}' % new)) + r'{{%s\g<parameters>}}' % new)) replaceBot = replace.ReplaceRobot(self.generator, replacements, exceptions, acceptall=self.getOption('always'), diff --git a/scripts/weblinkchecker.py b/scripts/weblinkchecker.py index 4c36069..968d763 100644 --- a/scripts/weblinkchecker.py +++ b/scripts/weblinkchecker.py @@ -128,26 +128,30 @@ # Officially reserved for testing, documentation, etc. in # https://tools.ietf.org/html/rfc2606#page-2 # top-level domains: - re.compile(&#39;.*[\./(a)]test(/.*)?&#39;))?'), - re.compile(&#39;.*[\./(a)]example(/.*)?&#39;))?'), - re.compile(&#39;.*[\./(a)]invalid(/.*)?&#39;))?'), - re.compile(&#39;.*[\./(a)]localhost(/.*)?&#39;))?'), + re.compile(r&#39;.*[\./(a)]test(/.*)?&#39;))?'), + re.compile(r&#39;.*[\./(a)]example(/.*)?&#39;))?'), + re.compile(r&#39;.*[\./(a)]invalid(/.*)?&#39;))?'), + re.compile(r&#39;.*[\./(a)]localhost(/.*)?&#39;))?'), # second-level domains: - re.compile(&#39;.*[\./(a)]example\.com(/.*)?&#39;))?'), - re.compile(&#39;.*[\./(a)]example\.net(/.*)?&#39;))?'), - re.compile(&#39;.*[\./(a)]example\.org(/.*)?&#39;))?'), + re.compile(r&#39;.*[\./(a)]example\.com(/.*)?&#39;))?'), + re.compile(r&#39;.*[\./(a)]example\.net(/.*)?&#39;))?'), + re.compile(r&#39;.*[\./(a)]example\.org(/.*)?&#39;))?'), # Other special cases - re.compile(&#39;.*[\./(a)]gso\.gbv\.de(/.*)?&#39;))?'), # bot somehow can't handle their redirects - re.compile(&#39;.*[\./(a)]berlinonline\.de(/.*)?&#39;))?'), + # bot somehow can't handle their redirects: + re.compile(r&#39;.*[\./(a)]gso\.gbv\.de(/.*)?&#39;))?'), + re.compile(r&#39;.*[\./(a)]berlinonline\.de(/.*)?&#39;))?'), # above entry to be manually fixed per request at [[de:Benutzer:BLueFiSH.as/BZ]] - re.compile(&#39;.*[\./(a)]bodo\.kommune\.no(/.*)?&#39;))?'), # bot can't handle their redirects - re.compile(&#39;.*[\./(a)]jpl\.nasa\.gov(/.*)?&#39;))?'), # bot rejected on the site - re.compile(&#39;.*[\./(a)]itis\.gov(/.*)?&#39;))?'), # bot rejected on the site - re.compile(&#39;.*[\./(a)]cev\.lu(/.*)?&#39;))?'), # bot rejected on the site - re.compile(&#39;.*[\./(a)]science\.ksc\.nasa\.gov(/.*)?&#39;))?'), # very slow response resulting in bot error - re.compile(&#39;.*[\./(a)]britannica\.com(/.*)?&#39;))?'), # HTTP redirect loop - re.compile(&#39;.*[\./(a)]quickfacts\.census\.gov(/.*)?&#39;))?'), # bot rejected on the site + # bot can't handle their redirects: + re.compile(r&#39;.*[\./(a)]bodo\.kommune\.no(/.*)?&#39;))?'), + re.compile(r&#39;.*[\./(a)]jpl\.nasa\.gov(/.*)?&#39;))?'), # bot rejected on the site + re.compile(r&#39;.*[\./(a)]itis\.gov(/.*)?&#39;))?'), # bot rejected on the site + re.compile(r&#39;.*[\./(a)]cev\.lu(/.*)?&#39;))?'), # bot rejected on the site + # very slow response resulting in bot error: + re.compile(r&#39;.*[\./(a)]science\.ksc\.nasa\.gov(/.*)?&#39;))?'), + re.compile(r&#39;.*[\./(a)]britannica\.com(/.*)?&#39;))?'), # HTTP redirect loop + # bot rejected on the site: + re.compile(r&#39;.*[\./(a)]quickfacts\.census\.gov(/.*)?&#39;))?'), ] diff --git a/tests/checkimages_tests.py b/tests/checkimages_tests.py new file mode 100644 index 0000000..4c0b10e --- /dev/null +++ b/tests/checkimages_tests.py @@ -0,0 +1,28 @@ +#!/usr/bin/python +# -*- coding: utf-8 -*- +"""Unit tests for checkimages script.""" + +from scripts import checkimages + +from tests.aspects import unittest, TestCase + + +class TestSettings(TestCase): + + """Test checkimages settings.""" + + family = 'commons' + code = 'commons' + user = True + + def test_load(self): + """Test loading settings.""" + b = checkimages.checkImagesBot(self.get_site()) + rv = b.takesettings() + item1 = rv[0] + self.assertEqual(item1[0], 1) + self.assertEqual(item1[1], 'a deprecated template') + + +if __name__ == "__main__": + unittest.main() -- To view, visit https://gerrit.wikimedia.org/r/189914 To unsubscribe, visit https://gerrit.wikimedia.org/r/settings Gerrit-MessageType: merged Gerrit-Change-Id: I8bcea1d5db3b5d0c2c9ada19382ada01f7339044 Gerrit-PatchSet: 7 Gerrit-Project: pywikibot/core Gerrit-Branch: master Gerrit-Owner: John Vandenberg &lt;jayvdb(a)gmail.com&gt; Gerrit-Reviewer: John Vandenberg &lt;jayvdb(a)gmail.com&gt; Gerrit-Reviewer: Ladsgroup &lt;ladsgroup(a)gmail.com&gt; Gerrit-Reviewer: Merlijn van Deen &lt;valhallasw(a)arctus.nl&gt; Gerrit-Reviewer: Siebrand &lt;siebrand(a)kitano.nl&gt; Gerrit-Reviewer: XZise &lt;CommodoreFabianus(a)gmx.de&gt; Gerrit-Reviewer: jenkins-bot <>