User:PotatoBot/Code/7

#!/usr/bin/python # -*- coding: utf-8 -*- import pywikibot as w import scripts.noreferences, re, mysave from datetime import date # PotatoBot Task 7: Adds Gl 

#!/usr/bin/python
# -*- coding: utf-8  -*-

import pywikibot as w
import scripts.noreferences, re, mysave
from datetime import date

# PotatoBot Task 7: Adds Glottolog codes to language infoboxes

def main():
	datapage = 'Wikipedia:WikiProject Languages/Glottolog 2.2 language names'
	errNobox, errIsSection, errMultiISO, errWrongGlotto, errMultiISOGlotto, errWrongISO, errNoISO = [], [], [], [], [], [], []
	errIO, refAdded = '', ''
	refbot = scripts.noreferences.NoReferencesBot(None, True)
	for glottoline in w.Page(w.getSite(), datapage).get().splitlines():
		# glottoline == ' aari1239 [[ISO 639:aiw|[aiw]]] [[Aari language|Aari]]'
		i = glottoline.find('[[ISO 639:')
		if i > 1:
			w.output('')
			if '|' in glottoline[i+24:]:
				pipe = glottoline.find('|', i+24)
				langpage = mysave.resolveredir(w.Page(w.getSite(), glottoline[i+24 : pipe]))
				glottoname = glottoline[pipe+1 : glottoline.find(']', pipe)]
			else:
				glottoname = glottoline[i+24 : glottoline.find(']', i+24)]
				langpage = mysave.resolveredir(w.Page(w.getSite(), glottoname))
			glottocode = glottoline[1 : glottoline.find(' ', 1)]
			isocode = glottoline[i+10 : i+13]
			w.output(langpage.title() + ' (' + isocode + '/' + glottocode + '):')
			langbox = False
			paramISO3, paramLC, paramLD, paramGlotto, paramGlottoref = '', [], [], [], ''
			if langpage.exists() and '#' not in langpage.title():
				for template in langpage.templatesWithParams():
					if template[0].title() == 'Template:Infobox language' or template[0].title() == 'Template:Infobox Language':
						langbox = True
						for param in template[1]:
							pp = param.partition('=')
							pname = pp[0].strip()
							pval = pp[2].strip()
							if pname == 'iso3':
								paramISO3 = pval
								paramLC.append(pval)
							elif pname[:2] == 'lc' and pname[2:].isdigit():
								paramLC.append(pval)
							elif pname[:2] == 'ld' and pname[2:].isdigit():
								paramLD.append('"' + pval + '"')
							elif pname[:6] == 'glotto' and (len(pname) == 6 or pname[6:].isdigit()):
								paramGlotto.append(pval)
							elif pname == 'glottorefname':
								paramGlottoref = pval
			if len(paramLD) > 0:
				if len(paramLD) == 1: paramLC += paramLD
				else: paramLC.append('several dialect names')
			entry = '#[[' + langpage.title() + ']] (' + isocode + '/' + glottocode + ')'
			
			if not langbox:
				if '#' in langpage.title():
					w.output('  \03{yellow}redirect to section\03{default}')
					errIsSection.append(entry)
				else:
					w.output('  \03{yellow}no language infobox\03{default}')
					errNobox.append(entry)
			elif len(paramLC) > 1:
				if len(paramGlotto) == 0:
					w.output('  \03{yellow}multiple ISO codes, but no glottocode\03{default}')
					errMultiISO.append(entry + ': ' + ', '.join(paramLC))
				else:
					w.output('  \03{yellow}multiple ISO codes and glottocode(s)\03{default}')
					errMultiISOGlotto.append(entry + ': ' + ', '.join(paramLC) + ' / ' + ', '.join(paramGlotto))
			else:
				if len(paramGlotto) == 0:
					langtext = langpage.get()
					isoparam = re.search(r'\|\s*iso3\s*=[^\|\}]*', langtext)
					if isoparam and paramISO3 != '':
						if paramISO3 != isocode:
							w.output('  \03{yellow}mismatching ISO code\03{default}')
							errWrongISO.append(entry + ': ' + paramISO3)
						else:
							langtext = langtext[:isoparam.end()] + '|glotto=' + glottocode + '\n' +\
								('|glottorefname=' + glottoname + '\n') * (paramGlottoref == '') + langtext[isoparam.end():]
							summary = 'Add [[Glottolog]] code ' + glottocode
							w.output('  NoReferencesBot says: ', newline = False)
							if refbot.lacksReferences(langtext + '</ref>'):
								langtext = refbot.addReferences(langtext)
								summary += ' and &lt;references /&gt;'
								refAdded += entry + '\n'
							errIO += mysave.savepage(langpage, langtext, '7', summary)
					else:
						w.output('  \03{yellow}no ISO code\03{default}')
						errNoISO.append(entry)
				elif len(paramGlotto) > 1 or paramGlotto[0] != glottocode:
					w.output('  \03{yellow}mismatching glottocode(s)\03{default}')
					errWrongGlotto.append(entry + ': ' + ', '.join(paramGlotto))
	errNobox.sort()
	errIsSection.sort()
	errWrongGlotto.sort()
	errMultiISO.sort()
	errMultiISOGlotto.sort()
	errWrongISO.sort()
	errNoISO.sort()
	mysave.savepage(w.Page(w.getSite(), 'User:PotatoBot/Lists/Glottolog log'), 
		'Log for the addition of [[Glottolog]] codes to language infoboxes ([[WP:Bots/Requests for approval/PotatoBot 7|Task 7]]). Date: ' +\
		mysave.fmtdate(date.today()) + '.\n\n' + "''Syntax'':" + '\n' + '#[[Some language]] ([[ISO 639-3]] code/glottocode, from [[' +\
		datapage + '|database]]): ISO codes and dialect names / glottocodes, from {{tl|Infobox language}} (if applicable)\n\n{{TOC right}}\n' +\
		'=== No language infobox ===\n' + '\n'.join(errNobox) + '\n\n' +\
		'=== Redirect to section ===\n' + '\n'.join(errIsSection) + '\n\n' +\
		'=== One ISO code and mismatching glottocode(s) ===\n' + '\n'.join(errWrongGlotto) + '\n\n' +\
		'=== Multiple ISO codes, but no glottocode ===\n' + '\n'.join(errMultiISO) + '\n\n' +\
		'=== Multiple ISO codes and mismatching, missing or surplus glottocode(s) ===\n' + '\n'.join(errMultiISOGlotto) + '\n\n' +\
		'=== Mismatching ISO code ===\n' + '\n'.join(errWrongISO) + '\n\n' +\
		'=== No ISO code ===\n' + '\n'.join(errNoISO) + '\n\n' +\
		'=== &lt;references /&gt; added ===\n' + refAdded +\
		'=== I/O error ===\n' + errIO, '7', 'Creating [[Glottolog]] log')

if __name__ == "__main__":
	try:
		main()
	finally:
		w.stopme()

mysave.py

#!/usr/bin/python
# -*- coding: utf-8  -*-

import pywikibot as w
import re

# Code for saving redirects and other pages

def savepage(page, text, BRFANo, summary = '', minor = False):
	"""Save text to a page and log exceptions."""
	if summary != '':
		w.setAction(summary + '. See [[Wikipedia:Bots/Requests for approval/PotatoBot ' + BRFANo + '|approval]]. Report errors and suggestions at [[User talk:PotatoBot]].')
	try:
		if not '#' in page.title():
			page.put(text, minorEdit = minor)
			w.output('  \03{green}saving %s -> \03{gray}%s\03{default}' % (page.title(), text))
			return ''
		else:
			w.output('  \03{red}cannot save %s because it is a section\03{default}' % page.title())
			return '# %s: this is a secion title' % page.title(aslink=True)
	except w.LockedPage:
		w.output('  \03{red}cannot save %s because it is locked\03{default}' % page.title())
		return '# %s: page was locked\n' % page.title(aslink=True)
	except w.EditConflict:
		w.output('  \03{red}cannot save %s because of edit conflict\03{default}' % page.title())
		return '# %s: edit conflict occurred\n' % page.title(aslink=True)
	except w.SpamfilterError, error:
		w.output('  \03{red}cannot save %s because of spam blacklist entry %s\03{default}' % (page.title(), error.url))
		return '# %s: spam blacklist entry\n' % page.title(aslink=True)
	except:
		w.output('  \03{red}unknown error on saving %s\03{default}' % page.title())
		return '# %s: unknown error occurred\n' % page.title(aslink=True)

def resolveredir(page):
	"""Return target if input is a redirect, else return input."""
	try:
		if page.isRedirectPage():
			try:
				w.output('  \03{gray}resolving redir %s to %s\03{default}'\
					% (page.title(), page.getRedirectTarget().title()))
				return page.getRedirectTarget()
			except:
				w.output('  \03{yellow}target %s is a broken redir\03{default}' % page.title())
				return w.Page(w.getSite(), page.title() + ' (broken redirect)')
		else:
			return page
	except:
		w.output('  \03{yellow}target %s is a bad link\03{default}' % page.title())
		return w.Page(w.getSite(), page.title() + ' (bad link)') # workaround for wikipedia.py breaking wikiasite: links

def makeredir(redirpage, page, BRFANo, templates = ''):
	"""Create a redirect and log existing page that isn't a redirect to the desired article."""
	page = resolveredir(page)
	if redirpage.exists():
		comment = ''
		if redirpage.isDisambig():
			comment = ' (disambiguation)'
			dab = redirpage
		if redirpage.isRedirectPage():
			try:
				if redirpage.getRedirectTarget().title() == page.title() or \
						redirpage.getRedirectTarget().sectionFreeTitle() == page.title():
					# Already a redir to the desired article
					return ''
				elif redirpage.getRedirectTarget().isDisambig():
					comment = ' (redirect to disambiguation)'
					dab = redirpage.getRedirectTarget()
				else:
					comment = ' (redirect)'
			except:
				comment = ' (broken redir)'
		if 'disambiguation' in comment and page in [resolveredir(p) for p in dab.linkedPages()]:
			w.output('  link to %s already on dab page %s' % (page.title(), redirpage.title()))
			return ''
		elif redirpage.title() != page.title():
			w.output('  \03{yellow}redir to %s failed, page %s already exists\03{default}' % (page.title(), redirpage.title()))
			return '# %s: redirecting to %s failed, page already exists%s\n' % (redirpage.title(aslink=True), page.title(aslink=True), comment)
		else:
			return ''
	# Else create redirect, or write page name to list if an error occurs
	else:
		return savepage(redirpage, '#REDIRECT %s %s' % (page.title(aslink=True), templates), BRFANo, 'Redirect to ' + page.title(aslink=True))

def findATCs(page, includeVet = True):
	"""Look for ATC codes in infoboxes."""
	ATCvet, prefix, suffix, supp = False, '', '', ''
	ATCvetpos, prefixpos, suffixpos, supppos = -1, -1, -1, -1
	templatenames = ('Drugbox', 'Chembox Identifiers')
	templates = page.templatesWithParams()
	for tuple in templates:
		if tuple[0] in templatenames:
			idx = templatenames.index(tuple[0])
			templatepos = templates.index(tuple)
			for param in tuple[1]:
				value = param.partition('=')
				if value[0].strip() == 'ATCvet':
					ATCvet = value[2].strip() == 'yes' and includeVet
					ATCvetpos = tuple[1].index(param)
				elif value[0].strip() == ('ATC_prefix', 'ATCCode_prefix')[idx] and value[2].strip().lower != 'none':
					prefix = value[2].strip()
					prefixpos = tuple[1].index(param)
				elif value[0].strip() == ('ATC_suffix', 'ATCCode_suffix')[idx]:
					suffix = value[2].strip()
					suffixpos = tuple[1].index(param)
				elif value[0].strip() == ('ATC_supplemental', 'ATC_Supplemental')[idx]:
					supp = value[2].strip()
					supppos = tuple[1].index(param)
	codes = (prefix != '') * [(ATCvet*'Q' + prefix + suffix)]
	for tupleSupp in page.templatesWithParams(supp):
		if tupleSupp[0] in ['ATC', 'ATCvet']:
			codes.append((tupleSupp[0] == 'ATCvet')*'Q' + tupleSupp[1][0] + tupleSupp[1][1])
	return (codes, ATCvetpos, prefixpos, suffixpos, supppos)

def addTemplateParam(page, newtemplates, BRFANo, summary = 'Updating template', minor = False):
	text = page.get()
	oldtemplates = page.templatesWithParams()
	pointer = 0
	for i in range(len(oldtemplates)):
		search1 = re.compile(r'\{\{\s*(%s|%s)%s\s*\|' % (oldtemplates[i][0][0].upper(), oldtemplates[i][0][0].lower(),\
			oldtemplates[i][0].replace(' ', '( |_)'))).search(text, pointer)
		if search1:
			pointer = end() - 1
		if newtemplates[i] != oldtemplates[i]:
			if newtemplates[i][0].strip() == oldtemplates[i][0].strip():
				for j in range(len(oldtemplates[i][1])):
					oldparam = oldtemplates[i][1][j].partition('=')
					newparam = newtemplates[i][1][j].partition('=')
					# Todo: unnamed params #
					if newparam[0] == oldparam[0]:
						span = re.compile(r'\|\s*%s\s*=\s*([^|}\s]*)\s*(}|\|)' % oldparam[0]).\
							search(text, pointer).span(1)
						pointer = span(1)
						if newparam[2].strip() != oldparam[2].strip():
							text = text[:span(0)] + newparam[2] + text[span(1):]
					else:
						text = text[:] + newtemplates[i][1][j] + text[:]
						pointer = len(text[:] + newtemplates[i][1][j])
			else:
				w.output('\03{yellow}template list does not match page %s: %s vs. %s\03{default}' % \
					(page.title(), newtemplates[i][0].strip(), oldtemplates[i][0].strip()))
				return '# %s: template list did not match templates on page' % page.title(aslink=True)
	if text != page.get():
		return savepage(page, text, BRFANo, summary, minor)
	else:
		return ''

def fmtdate(date):
	"""Format date in English w style."""
	return '%d %s %d' % (date.day, ('', 'January', 'February', 'March', 'April', 'May', 'June', 'July', 'August',\
		'September', 'October', 'November', 'December')[date.month], date.year)

Content Disclaimer

Informasi ini disarikan dari Wikipedia dan disajikan kembali untuk tujuan edukasi. Konten tersedia di bawah lisensi CC BY-SA 3.0. Kami tidak bertanggung jawab atas ketidakakuratan data yang bersumber dari kontribusi publik tersebut.

  1. The information displayed on this website is sourced in part or in whole from Wikipedia and has been adapted for the purpose of restating it. We strive to provide accurate and relevant information, however:
  2. There is no guarantee of absolute accuracy. Wikipedia is an open, collaborative project that can be edited by anyone, so information is subject to change.
  3. It is not intended to constitute professional advice. The content displayed is for informational and educational purposes only. For important decisions (e.g., medical, legal, or financial), please consult a professional.
  4. Content copyright. Wikipedia is licensed under the Creative Commons Attribution-ShareAlike License (CC BY-SA). This means that content may be reused with appropriate attribution and shared under a similar license.
  5. Responsible use. Any risk arising from the use of information from this website is entirely the responsibility of the user.