# -*- coding: utf-8 -*-
"""
This bot will make direct text replacements. It will retrieve information on
which pages might need changes either from an XML dump or a text file, or only
change a single page.
These command line parameters can be used to specify which pages to work on:
¶ms;
-xml Retrieve information from a local XML dump (pages-articles
or pages-meta-current, see http://download.wikimedia.org).
Argument can also be given as "-xml:filename".
-page Only edit a specific page.
Argument can also be given as "-page:pagetitle". You can
give this parameter multiple times to edit multiple pages.
Furthermore, the following command line parameters are supported:
-regex Make replacements using regular expressions. If this argument
isn't given, the bot will make simple text replacements.
-nocase Use case insensitive regular expressions.
-dotall Make the dot match any character at all, including a newline.
Without this flag, '.' will match anything except a newline.
-multiline '^' and '$' will now match begin and end of each line.
-xmlstart (Only works with -xml) Skip all articles in the XML dump
before the one specified (may also be given as
-xmlstart:Article).
-addcat:cat_name Adds "cat_name" category to every altered page.
-excepttitle:XYZ Skip pages with titles that contain XYZ. If the -regex
argument is given, XYZ will be regarded as a regular
expression.
-requiretitle:XYZ Only do pages with titles that contain XYZ. If the -regex
argument is given, XYZ will be regarded as a regular
expression.
-excepttext:XYZ Skip pages which contain the text XYZ. If the -regex
argument is given, XYZ will be regarded as a regular
expression.
-exceptinside:XYZ Skip occurences of the to-be-replaced text which lie
within XYZ. If the -regex argument is given, XYZ will be
regarded as a regular expression.
-exceptinsidetag:XYZ Skip occurences of the to-be-replaced text which lie
within an XYZ tag.
-summary:XYZ Set the summary message text for the edit to XYZ, bypassing
the predefined message texts with original and replacements
inserted.
-sleep:123 If you use -fix you can check multiple regex at the same time
in every page. This can lead to a great waste of CPU because
the bot will check every regex without waiting using all the
resources. This will slow it down between a regex and another
in order not to waste too much CPU.
-fix:XYZ Perform one of the predefined replacements tasks, which are
given in the dictionary 'fixes' defined inside the file
fixes.py.
The -regex and -nocase argument and given replacements will
be ignored if you use -fix.
Currently available predefined fixes are:
&fixes-help;
-always Don't prompt you for each replacement
-recursive Recurse replacement as long as possible. Be careful, this
might lead to an infinite loop.
-allowoverlap When occurences of the pattern overlap, replace all of them.
Be careful, this might lead to an infinite loop.
other: First argument is the old text, second argument is the new
text. If the -regex argument is given, the first argument
will be regarded as a regular expression, and the second
argument might contain expressions like \\1 or \g<name>.
Examples:
If you want to change templates from the old syntax, e.g. {{msg:Stub}}, to the
new syntax, e.g. {{Stub}}, download an XML dump file (pages-articles) from
http://download.wikimedia.org, then use this command:
python replace.py -xml -regex "{{msg:(.*?)}}" "{{\\1}}"
If you have a dump called foobar.xml and want to fix typos in articles, e.g.
Errror -> Error, use this:
python replace.py -xml:foobar.xml "Errror" "Error" -namespace:0
If you have a page called 'John Doe' and want to fix the format of ISBNs, use:
python replace.py -page:John_Doe -fix:isbn
This command will change 'referer' to 'referrer', but not in pages which
talk about HTTP, where the typo has become part of the standard:
python replace.py referer referrer -file:typos.txt -excepttext:HTTP
"""
#
# (C) Daniel Herding & the Pywikipediabot Team, 2004-2008
#
# Distributed under the terms of the MIT license.
#
from __future__ import generators
import os, sys, codecs, re, time
import string
import encodings
from string import Template
import wikipedia, pagegenerators, catlib, config
import editarticle
import webbrowser
import metai
import biografijos, ltasmen, politikai, valdovai, sportininkai, dvasininkai, teisininkai, prezidentai
import pedagogai, karininkai, menininkai, mokslininkai
# Imports predefined replacements tasks from fixes.py
import fixes
# This is required for the text that is shown when you run this script
# with the parameter -help.
docuReplacements = {
'¶ms;': pagegenerators.parameterHelp,
'&fixes-help;': fixes.help,
}
__version__='$Id: replace.py 6412 2009-02-22 16:13:01Z nicdumz $'
# Summary messages in different languages
# NOTE: Predefined replacement tasks might use their own dictionary, see 'fixes'
# below.`v
msg = {
'ar': u'%s روبوت : استبدال تلقائي للنص',
'ca': u'Robot: Reemplaçament automàtic de text %s',
'cs': u'Robot automaticky nahradil text: %s',
'de': u'Bot: Automatisierte Textersetzung %s',
'el': u'Ρομπότ: Αυτόματη αντικατάσταση κειμένου %s',
'en': u'Robot: Automated text replacement %s',
'es': u'Robot: Reemplazo automático de texto %s',
'fa': u'ربات: تغییر خودکار متن %s',
'fr': u'Bot : Remplacement de texte automatisé %s',
'he': u'בוט: החלפת טקסט אוטומטית %s',
'hu': u'Robot: Automatikus szövegcsere %s',
'ia': u'Robot: Reimplaciamento automatic de texto %s',
'id': u'Bot: Penggantian teks otomatis %s',
'is': u'Vélmenni: breyti texta %s',
'it': u'Bot: Sostituzione automatica %s',
'ja': u'ロボットによる: 文字置き換え %s',
'ka': u'რობოტი: ტექსტის ავტომატური შეცვლა %s',
'kk': u'Бот: Мәтінді өздікті алмастырды: %s',
'ksh': u'Bot: hät outomatesch Täx jetuusch: %s',
'lt': u'robotas: Automatinis teksto keitimas %s',
'nds': u'Bot: Text automaatsch utwesselt: %s',
'nds-nl': u'Bot: autematisch tekse vervungen %s',
'nl': u'Bot: automatisch tekst vervangen %s',
'nn': u'robot: automatisk teksterstatning: %s',
'no': u'robot: automatisk teksterstatning: %s',
'pl': u'Robot automatycznie zamienia tekst %s',
'pt': u'Bot: Mudança automática %s',
'ru': u'Робот: Автоматизированная замена текста %s',
'sr': u'Бот: Аутоматска замена текста %s',
'sv': u'Bot: Automatisk textersättning: %s',
'zh': u'機器人:執行文字代換作業 %s',
}
class XmlDumpReplacePageGenerator:
"""
Iterator that will yield Pages that might contain text to replace.
These pages will be retrieved from a local XML dump file.
Arguments:
* xmlFilename - The dump's path, either absolute or relative
* xmlStart - Skip all articles in the dump before this one
* replacements - A list of 2-tuples of original text (as a
compiled regular expression) and replacement
text (as a string).
* exceptions - A dictionary which defines when to ignore an
occurence. See docu of the ReplaceRobot
constructor below.
"""
def __init__(self, xmlFilename, xmlStart, replacements, exceptions):
self.xmlFilename = xmlFilename
self.replacements = replacements
self.exceptions = exceptions
self.xmlStart = xmlStart
self.skipping = bool(xmlStart)
self.excsInside = []
if self.exceptions.has_key('inside-tags'):
self.excsInside += self.exceptions['inside-tags']
if self.exceptions.has_key('inside'):
self.excsInside += self.exceptions['inside']
import xmlreader
self.site = wikipedia.getSite()
dump = xmlreader.XmlDump(self.xmlFilename)
self.parser = dump.parse()
def __iter__(self):
try:
for entry in self.parser:
if self.skipping:
if entry.title != self.xmlStart:
continue
self.skipping = False
if not self.isTitleExcepted(entry.title) \
and not self.isTextExcepted(entry.text):
new_text = entry.text
for old, new in self.replacements:
new_text = wikipedia.replaceExcept(new_text, old, new, self.excsInside, self.site)
if new_text != entry.text:
yield wikipedia.Page(self.site, entry.title)
except KeyboardInterrupt:
try:
if not self.skipping:
wikipedia.output(
u'To resume, use "-xmlstart:%s" on the command line.'
% entry.title)
except NameError:
pass
def isTitleExcepted(self, title):
if self.exceptions.has_key('title'):
for exc in self.exceptions['title']:
if exc.search(title):
return True
if self.exceptions.has_key('require-title'):
for req in self.exceptions['require-title']:
if not req.search(title): # if not all requirements are met:
return True
return False
def isTextExcepted(self, text):
if self.exceptions.has_key('text-contains'):
for exc in self.exceptions['text-contains']:
if exc.search(text):
return True
if self.exceptions.has_key('require-text'):
ret = True
for exc in self.exceptions['require-text']:
if exc.search(text):
return False
return ret
return False
def file_exists(filename):
if os.path.exists(filename):
print "'%s' already exists." % filename
return True
return False
class ReplaceRobot:
"""
A bot that can do text replacements.
"""
def __init__(self, generator, replacements, exceptions={},
acceptall=False, allowoverlap=False, recursive=False,
addedCat=None, sleep=None, biogr=None, biogr1=None, zbiogr=None, upe=None):
"""
Arguments:
* generator - A generator that yields Page objects.
* replacements - A list of 2-tuples of original text (as a
compiled regular expression) and replacement
text (as a string).
* exceptions - A dictionary which defines when not to change an
occurence. See below.
* acceptall - If True, the user won't be prompted before changes
are made.
* allowoverlap - If True, when matches overlap, all of them are
replaced.
* addedCat - If set to a value, add this category to every page
touched.
Structure of the exceptions dictionary:
This dictionary can have these keys:
title
A list of regular expressions. All pages with titles that
are matched by one of these regular expressions are skipped.
text-contains
A list of regular expressions. All pages with text that
contains a part which is matched by one of these regular
expressions are skipped.
inside
A list of regular expressions. All occurences are skipped which
lie within a text region which is matched by one of these
regular expressions.
inside-tags
A list of strings. These strings must be keys from the
exceptionRegexes dictionary in wikipedia.replaceExcept().
"""
self.generator = generator
self.replacements = replacements
self.exceptions = exceptions
self.acceptall = acceptall
self.allowoverlap = allowoverlap
self.recursive = recursive
self.biogr = biogr
self.biogr1 = biogr1
self.zbiogr = zbiogr
self.upe = upe
self.page = None
if addedCat:
site = wikipedia.getSite()
cat_ns = site.category_namespaces()[0]
self.addedCat = wikipedia.Page(site,
cat_ns + ':' + addedCat)
self.sleep = sleep
self.ltasmencat = ltasmen.ltasmen()
self.valdovaicat = valdovai.valdovai()
self.politikaicat = politikai.politikai()
self.sportininkaicat = sportininkai.sportininkai()
self.dvasininkaicat = dvasininkai.dvasininkai()
self.teisininkaicat = teisininkai.teisininkai()
self.karininkaicat = karininkai.karininkai()
self.menininkaicat = menininkai.menininkai()
self.mokslininkaicat = mokslininkai.mokslininkai()
self.pedagogaicat = pedagogai.pedagogai()
self.prezidentaicat = prezidentai.prezidentai()
#_fnf = os.path.join('', "biografija.txt")
#if not file_exists(_fnf):
# self.f = codecs.open(_fnf, "w", "utf-8")
def isTitleExcepted(self, title):
"""
Iff one of the exceptions applies for the given title, returns True.
"""
if self.exceptions.has_key('title'):
for exc in self.exceptions['title']:
if exc.search(title):
return True
if self.exceptions.has_key('require-title'):
for req in self.exceptions['require-title']:
if not req.search(title):
return True
return False
def isTextExcepted(self, original_text):
"""
Iff one of the exceptions applies for the given page contents,
returns True.
"""
if self.exceptions.has_key('text-contains'):
for exc in self.exceptions['text-contains']:
if exc.search(original_text):
return True
if self.exceptions.has_key('require-title'):
for req in self.exceptions['require-title']:
if not req.search(title): # if not all requirements are met:
return True
if self.exceptions.has_key('require-text'):
ret = True
for exc in self.exceptions['require-text']:
if exc.search(original_text):
return False
return ret
return False
def doReplacements(self, original_text):
"""
Returns the text which is generated by applying all replacements to
the given text.
"""
new_text = original_text
exceptions = []
if self.exceptions.has_key('inside-tags'):
exceptions += self.exceptions['inside-tags']
if self.exceptions.has_key('inside'):
exceptions += self.exceptions['inside']
#sab = re.compile(u'\{\{(?:(?:I|i)nfolentelė )?(?:U|u)pė(\|(?P<params>[^\{\}\|\=]*?))\|')
for old, new in self.replacements:
if self.sleep != None:
time.sleep(self.sleep)
if self.upe:
if type(old) is str or type(old) is unicode:
old1 = re.compile(old)
else:
old1 = old
index = 0
#match = old1.search(new_text, index)
#wikipedia.output(u'match %s :' %match)
temp = self.page.templatesWithParams()
#wikipedia.output(u'Templates %s :' % temp)
#matchsab = sab.search(new_text, index)
#if match == None:
#if matchsab != None:
# wikipedia.output(u'Templates %s :' % temp)
# choice = wikipedia.inputChoice(
# u'Not Found. Nead customize?',
# ["Quit"],
# ['q'], 'q')
#else:
# return original_text*/
find = False
#if match:
#if matchsab:
tparm = re.compile(u'\ *(?P<name>.*?)\ *\=\ *(?P<value>.*?)\r?\n')
for templname, parms in temp:
if (templname == u'Upė') or (templname == u'upė') or (templname == u'Infolentelupė upė'):
parms2 = []
for parm in parms:
match0 = tparm.search(parm, 0)
parms2.append( match0.group('value'))
name = parms2[0]
pav = parms2[1]
pava = parms2[2]
ilg = parms2[3]
nuol = parms2[4]
#choice = wikipedia.inputChoice(
# u'Found, but not nead customize?',
# ["Quit"],
# ['q'], 'q')
if nuol.strip(' ') == u'-' or nuol.strip(' ') == u'–' or nuol.strip(' ') == u'?':
nuol = ''
deb = parms2[5]
plot = parms2[6]
ist = parms2[7]
ziot = parms2[8]
sal = parms2[9]
if nuol != '':
nuol = ''
else:
return original_text
#to = Template(u'{{Upė|${name}|${pav}|${pava}|${ilg}|${nuol}|${deb}|${plot}|${ist}|${ziot}|${sal}}}\n')
#old1 = to.substitute(name=name,
# pav=pav,
# pava=pava,
# ilg=ilg,
# nuol=nuol,
# deb=deb,
# plot=plot,
# ist=ist,
# ziot=ziot,
# sal=sal,
# )
#
t1 = Template(new)
new = t1.substitute(name=name,
pav=pav,
pava=pava,
ilg=ilg,
nuol=nuol,
deb=deb,
plot=plot,
ist=ist,
ziot=ziot,
sal=sal,
)
#wikipedia.output(u'New %s :' % new)
find = True
break
if not find:
choice = wikipedia.inputChoice(
u'Found, but not nead customize?',
["Quit"],
['q'], 'q')
if self.biogr1:
old1 = re.compile(old, re.VERBOSE)
index = 0
match = old1.search(new_text, index)
if match:
mens = {
'1': u'sausio',
'2': u'vasario',
'3': u'kovo',
'4': u'balandžio',
'5': u'gegužės',
'6': u'birželio',
'7': u'liepos',
'8': u'rugpjūčio',
'9': u'rugsėjo',
'10': u'spalio',
'11': u'lapkričio',
'12': u'gruodžio',
}
mend = {
'1': u'Sausio',
'2': u'Vasario',
'3': u'Kovo',
'4': u'Balandžio',
'5': u'Gegužės',
'6': u'Birželio',
'7': u'Liepos',
'8': u'Rugpjūčio',
'9': u'Rugsėjo',
'10': u'Spalio',
'11': u'Lapkričio',
'12': u'Gruodžio',
}
men = {
u'sausio': '1',
u'vasario': '2',
u'kovo': '3',
u'balandžio': '4',
u'gegužės': '5',
u'birželio': '6',
u'liepos': '7',
u'rugpjūčio': '8',
u'rugsėjo': '9',
u'spalio': '10',
u'lapkričio': '11',
u'gruodžio': '12',
u'Sausio': '1',
u'Vasario': '2',
u'Kovo': '3',
u'Balandžio': '4',
u'Gegužės': '5',
u'Birželio': '6',
u'Liepos': '7',
u'Rugpjūčio': '8',
u'Rugsėjo': '9',
u'Spalio': '10',
u'Lapkričio': '11',
u'Gruodžio': '12',
}
gmet = match.group('gmet')
gmen = match.group('gmen')
gd = match.group('gd')
gv = match.group('gv')
mmet = match.group('mmet')
mmen = match.group('mmen')
md = match.group('md')
mv = match.group('mv')
gmet2 = match.group('gmet2')
gmen2 = match.group('gmen2')
gd2 = match.group('gd2')
gv2 = match.group('gv2')
mmet2 = match.group('mmet2')
mmen2 = match.group('mmen2')
md2 = match.group('md2')
mv2 = match.group('mv2')
pav = match.group('pav')
name2 = match.group('name2')
name3 = match.group('name3')
veikl = match.group('veikl')
text = match.group('text')
gmenn = ''
mmenn = ''
if gmet == None:
if gmet2 != None:
gmet = gmet2
else:
gmet = ''
if gmen == None:
if gmen2 != None:
gmen = gmen2
if gmen != None:
gmenn = men[gmen]
if gd == None:
if gd2 != None:
gd = gd2
else:
gd = ''
if gv == None:
if gv2 != None:
gv = gv2
else:
gv = ''
if mmet == None:
if mmet2 != None:
mmet = mmet2
else:
mmet = ''
if mmen == None:
if mmen2 != None:
mmen = mmen2
if mmen != None:
mmenn = men[mmen]
if md == None:
if md2 != None:
md = md2
else:
md = ''
if mv == None:
if mv2 != None:
mv = mv2
else:
mv = ''
if pav == None:
pav = ''
if veikl == None:
veikl = ''
if name2 == None:
name2 = ''
if name3 == None:
name3 = ''
if text == None:
text = ''
if mmet=='':
text2=\
'* \'\'\'[['+mend[gmenn]+' '+gd+']]\'\'\' d. - [['+self.page.title()+'|'+name2+']], '+veikl+'\n'+\
'* [['+gmet+']] - [['+self.page.title()+'|'+name2+']], '+veikl+'\n'
else:
text2=\
'* \'\'\'[['+mend[gmenn]+' '+gd+']]\'\'\' d. - [['+self.page.title()+'|'+name2+']], '+veikl+' (m. [['+mmet+ur']])\n'+\
'* [['+gmet+']] - [['+self.page.title()+'|'+name2+']], '+veikl+' (m. [['+mmet+ur']])\n'+\
'* \'\'\'[['+mend[mmenn]+' '+md+']]\'\'\' d. - [['+self.page.title()+'|'+name2+']], '+veikl+' (g. [['+gmet+ur']])\n'+\
'* [['+mmet+']] - [['+self.page.title()+'|'+name2+']], '+veikl+' (g. [['+gmet+ur']])\n'
t1 = Template(new)
new = t1.substitute(name=self.page.title(),
gmet=gmet,
gmen=gmenn,
gd=gd,
gv=gv,
mmet=mmet,
mmen=mmenn,
md=md,
mv=mv,
pav=pav,
veikl=veikl,
name2=name2,
name3=name3,
text=text,
text2=text2,
)
if self.biogr:
if type(old) is str or type(old) is unicode:
old1 = re.compile(old)
else:
old1 = old
index = 0
ltOrPs = 'Pasaulyje'
category = wikipedia.getCategoryLinks(original_text,wikipedia.getSite())
ltparm = re.compile(u'^Lietuvos')
for cat in category:
catName = cat.titleWithoutNamespace()
wikipedia.output(u'category : %s' % catName)
matchlt = ltparm.search(catName, 0)
if matchlt:
ltOrPs = 'Lietuvoje'
temp = self.page.templatesWithParams()
find = False
tparm = re.compile(u'\s*(?P<name>.*?)\s*(?P<ly>\=)\s*(?P<reik>.*)\r?\n?$')
parms2 = {'pav':'', 'g-data':'', 'm-data':'', 'g-vieta':'', 'm-vieta':''}
for templname, parms in temp:
if (templname == u'Biografija') or (templname == u'biografija'):
#wikipedia.output(u'Parms : %s' % parms)
for parm in parms:
#wikipedia.output(u'Parm : %s' % parm)
match0 = tparm.search(parm, 0)
#wikipedia.output(u'match0.groups : %s' % match0.groupdict())
#wikipedia.output(u'match0 : %s' % match0.group('reik'))
parms2[match0.group('name')] = match0.group('reik')
for key in parms2:
wikipedia.output(u'Parm key : %s = %s' % (key, parms2[key]))
pav = parms2['pav']
tmpl = re.compile(u'\[\[(((i|I)mage)|((v|V)aizdas))\:(?P<pav>.*?)\|')
match = tmpl.search(pav, 0)
if match:
pav = match.group('pav')
wikipedia.output(u'Pav is : %s' % pav)
gd = metai.Data(data = parms2['g-data'])
#wikipedia.output(u'gdType is : %s, %s, %s' % (type(gd), type(gd._metai), gd._metai.get()))
md = metai.Data(data = parms2['m-data'])
gv = parms2['g-vieta']
mv = parms2['m-vieta']
#self.f.write('Page : %s \n' % self.page.title())
#self.f.write(u'Parm key : %s = %s \n' % (key, parms2[key]))
#wikipedia.output(u'Parm is : %s' % parms2[key])
if gd._metai:
gmet = gd._metai.get()
else:
gmet = None
gadd = gd._papild
gmen = None
if gd._menDien:
gmen = gd._menDien._menuo.get()
gd = gd._menDien._diena.get()
else:
gmen = None
gd = None
#wikipedia.output(u'gmet is : %s' % gmet)
#wikipedia.output(u'gmen is : %s' % gmen)
#wikipedia.output(u'gd is : %s' % gd)
if md._metai:
mmet = md._metai.get()
else:
mmet = None
madd = md._papild
mmen = None
if md._menDien:
mmen = md._menDien._menuo.get()
md = md._menDien._diena.get()
else:
mmen = None
md = None
#return original_text
match = old1.search(new_text, 0)
if match:
name2 = match.group('name2')
veikl = match.group('veikl')
text = match.group('text')
skliaust = match.group('skliaust')
if name2 == None:
name2 = ''
if text == None:
text = ''
tparms = re.compile(u'^(?P<name3>.*?)(\[\[(?P<gmet2>\d*?)\]\](?:\s*(?:m\.\s*)?\[\[(?P<gmen2>.*?)\ (?P<gd2>\d*?)\]\](?:\s*(d\.\s*)?)?)?(?P<gv2>.*?)((((\-\s*(m\.\s*)?)|(–\s*(m\.\s*)?)|(-\s*(m\.\s*)?)|(—\s*(m\.\s*)?)))\[\[(?P<mmet2>\d*?)\]\](?:\s*(?:m\.\s*)?\[\[(?P<mmen2>.*?)\ (?P<md2>\d*?)\]\](?:\s*(d\.\s*)?)?)?(?P<mv2>.*?))?)?$')
matchs = tparms.search(skliaust, 0)
if matchs:
gmet2 = matchs.group('gmet2')
gmen2 = matchs.group('gmen2')
gd2 = matchs.group('gd2')
gv2 = matchs.group('gv2')
mmet2 = matchs.group('mmet2')
mmen2 = matchs.group('mmen2')
md2 = matchs.group('md2')
mv2 = matchs.group('mv2')
name3 = matchs.group('name3')
if name3 == None:
name3 = ''
if gmet == None:
if gmet2 != None:
gmet = gmet2
if gmen == None:
if gmen2 != None:
gmen = gmen2
if gd == None:
if gd2 != None:
gd = gd2
if gv == None:
if gv2 != None:
gv = gv2
if mmet == None:
if mmet2 != None:
mmet = mmet2
if mmen == None:
if mmen2 != None:
mmen = mmen2
if md == None:
if md2 != None:
md = md2
if mv == None:
if mv2 != None:
mv = mv2
if pav == None:
pav = ''
asm = metai.Asmuo(name = self.page.title(), nameShow = name2,\
gData = metai.Data(metai = gmet, menuo = gmen, diena = gd), gVieta = gv,\
mData = metai.Data(metai = mmet, menuo = mmen, diena = md), mVieta = mv,\
what = veikl)
parttype = 'I'
if gmet is not None:
gPageMetai = metai.PageMetai(gmet)
if gmen is None:
gmeni = 'Nedatuoti'
parttype = 'MNI'
nextind = self.page.title()
else:
gmeni = metai.Menuo(gmen).get(vard = True, upper=True)
parttype = 'I'
nextind = int(gd)
ind = [ ltOrPs, 'Gimtadieniai', gmeni, nextind, self.page.title()]
gime = asm.getGimeMetai(full=False)
wikipedia.output(u'Itraukiam %s: \n%s' % (ind, gime))
gPageMetai.add(metai.PageMetaiPart(self.page.title(), parttype, gime, _ind=ind), ind)
gPageMetai.join()
wikipedia.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<"
% gmet)
oldMet = gPageMetai.old
newMet = gPageMetai.new
#wikipedia.setAction('Gimtadienis:'+gime[0:100])
while True:
wikipedia.showDiff(oldMet, newMet)
choice = wikipedia.inputChoice(
u'Do you want to accept these changes?',
['Yes', 'No', 'Edit', "Quit"],
['y', 'N', 'e', 'q'], 'N')
if choice == 'e':
editor = editarticle.TextEditor()
as_edited = editor.edit(newMet)
# if user didn't press Cancel
if as_edited and as_edited != newMet:
newMet = as_edited
if choice == 'q':
break
if choice == 'N':
break
if choice == 'n':
break
if choice == 'y':
gPageMetai.page.put_async(newMet, watchArticle=True, comment='Gimtadienis:'+gime[0:100])
break
if mmet is not None:
mPageMetai = metai.PageMetai(mmet)
if mmen is None:
mmeni = 'Nedatuoti'
parttype = 'MNI'
nextind = self.page.title()
else:
mmeni = metai.Menuo(mmen).get(vard = True, upper=True)
parttype = 'I'
nextind = int(md)
ind = [ ltOrPs, 'Mirtys', mmeni, nextind, self.page.title()]
mire = asm.getMireMetai(full=False)
wikipedia.output(u'Itraukiam %s: \n%s' % (ind, mire))
mPageMetai.add(metai.PageMetaiPart(self.page.title(), parttype, mire, _ind=ind), ind)
mPageMetai.join()
wikipedia.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<"
% mmet)
oldMet = mPageMetai.old
newMet = mPageMetai.new
#wikipedia.setAction('Mirtys:'+mire[0:100])
while True:
wikipedia.showDiff(oldMet, newMet)
choice = wikipedia.inputChoice(
u'Do you want to accept these changes?',
['Yes', 'No', 'Edit', "Quit"],
['y', 'N', 'e', 'q'], 'N')
if choice == 'e':
editor = editarticle.TextEditor()
as_edited = editor.edit(newMet)
# if user didn't press Cancel
if as_edited and as_edited != newMet:
newMet = as_edited
if choice == 'q':
break
if choice == 'N':
break
if choice == 'n':
break
if choice == 'y':
mPageMetai.page.put_async(newMet, watchArticle=True, comment='Mirtys:'+mire[0:100])
break
if mmet is None:
text2= asm.getGimeData()
t1 = Template(new)
new = t1.substitute(name=self.page.title(),
gd=asm.getGime(aslist = True),
gv=asm._gVieta,
gadd = gadd,
md='',
mv='',
madd = madd,
pav=pav,
veikl=asm._what,
name2=asm._nameShow,
name3=name3,
text=text,
text2=text2,
)
else:
text2= asm.getGimeData() + asm.getMireData()
t1 = Template(new)
new = t1.substitute(name=self.page.title(),
gd=asm.getGime(aslist = True),
gv=asm._gVieta,
gadd = gadd,
md=asm.getMire(aslist = True),
mv=asm._mVieta,
madd = madd,
pav=pav,
veikl=asm._what,
name2=asm._nameShow,
name3=name3,
text=text,
text2=text2,
)
else:
raise TypeError('Blogo formato skliaustai: %s' % skliaust)
if self.zbiogr:
fonas = ''
if type(old) is str or type(old) is unicode:
old1 = re.compile(old)
else:
old1 = old
index = 0
ltOrPs = 'Pasaulyje'
category = wikipedia.getCategoryLinks(original_text,wikipedia.getSite())
#ltparm = re.compile(u'^Lietuvos')
for cat in category:
catName = cat.titleWithoutNamespace()
wikipedia.output(u'category : %s' % catName)
#matchlt = ltparm.search(catName, 0)
if catName in self.ltasmencat:
ltOrPs = 'Lietuvoje'
## temp = self.page.templatesWithParams()
## find = False
## tparm = re.compile(u'\s*(?P<name>.*?)\s*(?P<ly>\=)\s*(?P<reik>.*)\r?\n?$')
## parms2 = {'pav':'', 'g-data':'', 'm-data':'', 'g-vieta':'', 'm-vieta':''}
## for templname, parms in temp:
## if (templname == u'Biografija') or (templname == u'biografija'):
## #wikipedia.output(u'Parms : %s' % parms)
## for parm in parms:
## #wikipedia.output(u'Parm : %s' % parm)
## match0 = tparm.search(parm, 0)
## #wikipedia.output(u'match0.groups : %s' % match0.groupdict())
## #wikipedia.output(u'match0 : %s' % match0.group('reik'))
## parms2[match0.group('name')] = match0.group('reik')
##
## for key in parms2:
## wikipedia.output(u'Parm key : %s = %s' % (key, parms2[key]))
## pav = parms2['pav']
## tmpl = re.compile(u'\[\[(((i|I)mage)|((v|V)aizdas))\:(?P<pav>.*?)\|')
## match = tmpl.search(pav, 0)
## if match:
## pav = match.group('pav')
## wikipedia.output(u'Pav is : %s' % pav)
## gd = metai.Data(data = parms2['g-data'])
## #wikipedia.output(u'gdType is : %s, %s, %s' % (type(gd), type(gd._metai), gd._metai.get()))
## md = metai.Data(data = parms2['m-data'])
## gv = parms2['g-vieta']
## mv = parms2['m-vieta']
## #self.f.write('Page : %s \n' % self.page.title())
## #self.f.write(u'Parm key : %s = %s \n' % (key, parms2[key]))
## #wikipedia.output(u'Parm is : %s' % parms2[key])
## if gd._metai:
## gmet = gd._metai.get()
## else:
## gmet = None
## gadd = gd._papild
## gmen = None
## if gd._menDien:
## gmen = gd._menDien._menuo.get()
## gd = gd._menDien._diena.get()
## else:
## gmen = None
## gd = None
## #wikipedia.output(u'gmet is : %s' % gmet)
## #wikipedia.output(u'gmen is : %s' % gmen)
## #wikipedia.output(u'gd is : %s' % gd)
## if md._metai:
## mmet = md._metai.get()
## else:
## mmet = None
## madd = md._papild
## mmen = None
## if md._menDien:
## mmen = md._menDien._menuo.get()
## md = md._menDien._diena.get()
## else:
## mmen = None
## md = None
## #return original_text
break
for cat in category:
catName = cat.titleWithoutNamespace()
wikipedia.output(u'category : %s' % catName)
if catName in self.valdovaicat:
fonas = 'reg'
new = u'{{Valdovas\n' +\
u'| fonas = ${fonas}\n' +\
u'| titulas = \n' +\
u'| kiti titulai = \n' +\
u'| dinastija = \n' +\
u'| vardas = ${names}\n' +\
u'| paveikslėlis = \n' +\
u'| paveikslėlio apibūdinimas = \n' +\
u'| paveikslėlio dydis = \n' +\
u'| gimimo data = ${gd}\n' +\
u'| gimimo vieta = ${gv}\n' +\
u'| mirties data = ${md}\n' +\
u'| mirties vieta = ${mv}\n' +\
u'| tautybė = \n' +\
u'| sutuoktinis = \n' +\
u'| tėvas = \n' +\
u'| motina = \n' +\
u'| vaikai = \n' +\
u'<!-- Veikla -->\n' +\
u'| veikla = ${veikl}\n' +\
u'<!-- Pasikartojanti dalis iki 10 kartu. Pasikartoja, jei nurodytas titulas su atitinkamu numeriu. Nuo 2 yra paslepiami. -->\n' +\
u'| titulas0 = \n' +\
u'| fonas0 = ${fonas}\n' +\
u'| kelintas0 = \n' +\
u'| valdė0 = \n' +\
u'| karūnavimas0 = \n' +\
u'| pirmtakas0 = \n' +\
u'| įpėdinis0 = \n' +\
u'| žinomas = \n' +\
u'| parašas = \n' +\
u'| pastabos = \n' +\
u'}}\n' +\
u'\'\'\'\g<name2>\'\'\' (\g<skliaust>) – \g<veikl>\n${text2}'
break
elif catName in self.prezidentaicat:
fonas = 'off'
new = u'{{Žmogaus biografija\n' +\
u'| fonas = ${fonas}\n' +\
u'| titulas = \n' +\
u'| kiti titulai = \n' +\
u'| vardas = ${names}\n' +\
u'| paveikslėlis = \n' +\
u'| paveikslėlio apibūdinimas = \n' +\
u'| paveikslėlio dydis = \n' +\
u'| gimimo data = ${gd}\n' +\
u'| gimimo vieta = ${gv}\n' +\
u'| mirties data = ${md}\n' +\
u'| mirties vieta = ${mv}\n' +\
u'| tautybė = \n' +\
u'| sutuoktinis = \n' +\
u'| tėvas = \n' +\
u'| motina = \n' +\
u'| vaikai = \n' +\
u'<!-- Veikla -->\n' +\
u'| veikla = ${veikl}\n' +\
u'| sritis = \n' +\
u'| įstaigos = \n' +\
u'| pareigos = \n' +\
u'| partija = \n' +\
u'<!-- Išsilavinimas -->\n' +\
u'| išsilavinimas = \n' +\
u'| alma_mater = \n' +\
u'| doktorantūros_vadovas = \n' +\
u'| studentai = \n' +\
u'| žinomas = \n' +\
u'| apdovanojimai = \n' +\
u'<!-- Pasikartojanti dalis iki 0-10, pasikartoja jei nurodytas titulas su atitinkamu numeriu. Nuo 2 yra paslepiami. -->\n' +\
u'| titulas0 = \n' +\
u'| fonas0 = ${fonas}\n' +\
u'| kelintas0 = \n' +\
u'| nuo0 = \n' +\
u'| iki0 = \n' +\
u'| vadovavo0 = \n' +\
u'| ėjo pareigas0 = \n' +\
u'| ankstesnis0 = \n' +\
u'| vėlesnis0 = \n' +\
u'| parašas = \n' +\
u'| pastabos = \n' +\
u'}}\n' +\
u'\'\'\'\g<name2>\'\'\' (\g<skliaust>) – \g<veikl>\n${text2}'
break
elif catName in self.politikaicat:
fonas = 'off'
new = u'{{Žmogaus biografija\n' +\
u'| fonas = ${fonas}\n' +\
u'| vardas = ${names}\n' +\
u'| paveikslėlis = \n' +\
u'| paveikslėlio apibūdinimas = \n' +\
u'| paveikslėlio dydis = \n' +\
u'| gimimo data = ${gd}\n' +\
u'| gimimo vieta = ${gv}\n' +\
u'| mirties data = ${md}\n' +\
u'| mirties vieta = ${mv}\n' +\
u'| tautybė = \n' +\
u'| sutuoktinis = \n' +\
u'| tėvas = \n' +\
u'| motina = \n' +\
u'| vaikai = \n' +\
u'<!-- Veikla -->\n' +\
u'| veikla = ${veikl}\n' +\
u'| sritis = \n' +\
u'| įstaigos = \n' +\
u'| pareigos = \n' +\
u'| partija = \n' +\
u'| žinomas = \n' +\
u'| apdovanojimai = \n' +\
u'| parašas = \n' +\
u'| pastabos = \n' +\
u'}}\n' +\
u'\'\'\'\g<name2>\'\'\' (\g<skliaust>) – \g<veikl>\n${text2}'
break
elif catName in self.dvasininkaicat:
fonas = 'rel'
new = u'{{Žmogaus biografija\n' +\
u'| fonas = ${fonas}\n' +\
u'| titulas = \n' +\
u'| kiti titulai = \n' +\
u'| vardas = ${names}\n' +\
u'| paveikslėlis = \n' +\
u'| paveikslėlio apibūdinimas = \n' +\
u'| paveikslėlio dydis = \n' +\
u'| gimimo data = ${gd}\n' +\
u'| gimimo vieta = ${gv}\n' +\
u'| mirties data = ${md}\n' +\
u'| mirties vieta = ${mv}\n' +\
u'| tautybė = \n' +\
u'| sutuoktinis = \n' +\
u'| tėvas = \n' +\
u'| motina = \n' +\
u'| vaikai = \n' +\
u'<!-- Veikla -->\n' +\
u'| veikla = ${veikl}\n' +\
u'| sritis = \n' +\
u'| įstaigos = \n' +\
u'| pareigos = \n' +\
u'<!-- Išsilavinimas -->\n' +\
u'| išsilavinimas = \n' +\
u'| alma_mater = \n' +\
u'| doktorantūros_vadovas = \n' +\
u'| studentai = \n' +\
u'| žinomas = \n' +\
u'| apdovanojimai = \n' +\
u'| religija = \n' +\
u'<!-- Šventasis -->\n' +\
u'<!-- | įšventintas = \n' +\
u'| palaimintas = \n' +\
u'| kanonizuotas = \n' +\
u'| kanonizavo = \n' +\
u'| šventė = \n' +\
u'| globėjas = -->\n' +\
u'<!--| popiežiaus tarnystės pradžia = \n' +\
u'| popiežiaus tarnystės pabaiga = -->\n' +\
u'<!-- Pasikartojanti dalis iki 0-10, pasikartoja jei nurodytas titulas su atitinkamu numeriu. Nuo 2 yra paslepiami. -->\n' +\
u'| titulas0 = \n' +\
u'| fonas0 = ${fonas}\n' +\
u'| kelintas0 = \n' +\
u'| ėjo pareigas0 = \n' +\
u'| ankstesnis0 = \n' +\
u'| vėlesnis0 = \n' +\
u'| parašas = \n' +\
u'| pastabos = \n' +\
u'}}\n' +\
u'\'\'\'\g<name2>\'\'\' (\g<skliaust>) – \g<veikl>\n${text2}'
break
elif catName in self.sportininkaicat:
fonas = 'sports'
new = u'{{Žmogaus biografija\n' +\
u'| fonas = ${fonas}\n' +\
u'| vardas = ${names}\n' +\
u'| paveikslėlis = \n' +\
u'| paveikslėlio apibūdinimas = \n' +\
u'| paveikslėlio dydis = \n' +\
u'| gimimo data = ${gd}\n' +\
u'| gimimo vieta = ${gv}\n' +\
u'| mirties data = ${md}\n' +\
u'| mirties vieta = ${mv}\n' +\
u'| tautybė = \n' +\
u'| sutuoktinis = \n' +\
u'| tėvas = \n' +\
u'| motina = \n' +\
u'| vaikai = \n' +\
u'<!-- Veikla -->\n' +\
u'| veikla = ${veikl}\n' +\
u'| sritis = \n' +\
u'| įstaigos = \n' +\
u'| pareigos = \n' +\
u'<!-- Išsilavinimas -->\n' +\
u'| išsilavinimas = \n' +\
u'| alma_mater = \n' +\
u'| doktorantūros_vadovas = \n' +\
u'| studentai = \n' +\
u'| žinomas = \n' +\
u'| apdovanojimai = \n' +\
u'| parašas = \n' +\
u'| pastabos = \n' +\
u'}}\n' +\
u'\'\'\'\g<name2>\'\'\' (\g<skliaust>) – \g<veikl>\n${text2}'
break
elif catName in self.teisininkaicat:
fonas = 'legal'
new = u'{{Žmogaus biografija\n' +\
u'| fonas = ${fonas}\n' +\
u'| vardas = ${names}\n' +\
u'| paveikslėlis = \n' +\
u'| paveikslėlio apibūdinimas = \n' +\
u'| paveikslėlio dydis = \n' +\
u'| gimimo data = ${gd}\n' +\
u'| gimimo vieta = ${gv}\n' +\
u'| mirties data = ${md}\n' +\
u'| mirties vieta = ${mv}\n' +\
u'| tautybė = \n' +\
u'| sutuoktinis = \n' +\
u'| tėvas = \n' +\
u'| motina = \n' +\
u'| vaikai = \n' +\
u'<!-- Veikla -->\n' +\
u'| veikla = ${veikl}\n' +\
u'| sritis = \n' +\
u'| įstaigos = \n' +\
u'| pareigos = \n' +\
u'<!-- Išsilavinimas -->\n' +\
u'| išsilavinimas = \n' +\
u'| alma_mater = \n' +\
u'| doktorantūros_vadovas = \n' +\
u'| studentai = \n' +\
u'| žinomas = \n' +\
u'| apdovanojimai = \n' +\
u'| parašas = \n' +\
u'| pastabos = \n' +\
u'}}\n' +\
u'\'\'\'\g<name2>\'\'\' (\g<skliaust>) – \g<veikl>\n${text2}'
break
elif catName in self.karininkaicat:
fonas = 'mil'
new = u'{{Žmogaus biografija\n' +\
u'| fonas = ${fonas}\n' +\
u'| vardas = ${names}\n' +\
u'| paveikslėlis = \n' +\
u'| paveikslėlio apibūdinimas = \n' +\
u'| paveikslėlio dydis = \n' +\
u'| gimimo data = ${gd}\n' +\
u'| gimimo vieta = ${gv}\n' +\
u'| mirties data = ${md}\n' +\
u'| mirties vieta = ${mv}\n' +\
u'| tautybė = \n' +\
u'| sutuoktinis = \n' +\
u'| tėvas = \n' +\
u'| motina = \n' +\
u'| vaikai = \n' +\
u'<!-- Veikla -->\n' +\
u'| veikla = ${veikl}\n' +\
u'| sritis = \n' +\
u'| įstaigos = \n' +\
u'| pareigos = \n' +\
u'<!-- Išsilavinimas -->\n' +\
u'| išsilavinimas = \n' +\
u'| alma_mater = \n' +\
u'| doktorantūros_vadovas = \n' +\
u'| studentai = \n' +\
u'| žinomas = \n' +\
u'| apdovanojimai = \n' +\
u'| parašas = \n' +\
u'| pastabos = \n' +\
u'}}\n' +\
u'\'\'\'\g<name2>\'\'\' (\g<skliaust>) – \g<veikl>\n${text2}'
break
elif catName in self.menininkaicat:
fonas = 'culture'
new = u'{{Žmogaus biografija\n' +\
u'| fonas = ${fonas}\n' +\
u'| vardas = ${names}\n' +\
u'| paveikslėlis = \n' +\
u'| paveikslėlio apibūdinimas = \n' +\
u'| paveikslėlio dydis = \n' +\
u'| gimimo data = ${gd}\n' +\
u'| gimimo vieta = ${gv}\n' +\
u'| mirties data = ${md}\n' +\
u'| mirties vieta = ${mv}\n' +\
u'| tautybė = \n' +\
u'| sutuoktinis = \n' +\
u'| tėvas = \n' +\
u'| motina = \n' +\
u'| vaikai = \n' +\
u'<!-- Veikla -->\n' +\
u'| veikla = ${veikl}\n' +\
u'| sritis = \n' +\
u'| įstaigos = \n' +\
u'| pareigos = \n' +\
u'<!-- Išsilavinimas -->\n' +\
u'| išsilavinimas = \n' +\
u'| alma_mater = \n' +\
u'| doktorantūros_vadovas = \n' +\
u'| studentai = \n' +\
u'| žinomas = \n' +\
u'| apdovanojimai = \n' +\
u'| parašas = \n' +\
u'| pastabos = \n' +\
u'}}\n' +\
u'\'\'\'\g<name2>\'\'\' (\g<skliaust>) – \g<veikl>\n${text2}'
break
elif catName in self.pedagogaicat:
fonas = 'edu'
new = u'{{Žmogaus biografija\n' +\
u'| fonas = ${fonas}\n' +\
u'| vardas = ${names}\n' +\
u'| paveikslėlis = \n' +\
u'| paveikslėlio apibūdinimas = \n' +\
u'| paveikslėlio dydis = \n' +\
u'| gimimo data = ${gd}\n' +\
u'| gimimo vieta = ${gv}\n' +\
u'| mirties data = ${md}\n' +\
u'| mirties vieta = ${mv}\n' +\
u'| tautybė = \n' +\
u'| sutuoktinis = \n' +\
u'| tėvas = \n' +\
u'| motina = \n' +\
u'| vaikai = \n' +\
u'<!-- Veikla -->\n' +\
u'| veikla = ${veikl}\n' +\
u'| sritis = \n' +\
u'| įstaigos = \n' +\
u'| pareigos = \n' +\
u'<!-- Išsilavinimas -->\n' +\
u'| išsilavinimas = \n' +\
u'| alma_mater = \n' +\
u'| doktorantūros_vadovas = \n' +\
u'| studentai = \n' +\
u'| žinomas = \n' +\
u'| apdovanojimai = \n' +\
u'| parašas = \n' +\
u'| pastabos = \n' +\
u'}}\n' +\
u'\'\'\'\g<name2>\'\'\' (\g<skliaust>) – \g<veikl>\n${text2}'
break
else:
fonas = ''
new = u'{{Žmogaus biografija\n' +\
u'| fonas = ${fonas}\n' +\
u'| vardas = ${names}\n' +\
u'| paveikslėlis = \n' +\
u'| paveikslėlio apibūdinimas = \n' +\
u'| paveikslėlio dydis = \n' +\
u'| gimimo data = ${gd}\n' +\
u'| gimimo vieta = ${gv}\n' +\
u'| mirties data = ${md}\n' +\
u'| mirties vieta = ${mv}\n' +\
u'| tautybė = \n' +\
u'| sutuoktinis = \n' +\
u'| tėvas = \n' +\
u'| motina = \n' +\
u'| vaikai = \n' +\
u'<!-- Veikla -->\n' +\
u'| veikla = ${veikl}\n' +\
u'| sritis = \n' +\
u'| įstaigos = \n' +\
u'| pareigos = \n' +\
u'<!-- Išsilavinimas -->\n' +\
u'| išsilavinimas = \n' +\
u'| alma_mater = \n' +\
u'| doktorantūros_vadovas = \n' +\
u'| studentai = \n' +\
u'| žinomas = \n' +\
u'| apdovanojimai = \n' +\
u'| parašas = \n' +\
u'| pastabos = \n' +\
u'}}\n' +\
u'\'\'\'\g<name2>\'\'\' (\g<skliaust>) – \g<veikl>\n${text2}'
gmet = None
gmen = None
gd = None
gv = None
mmet = None
mmen = None
md = None
mv = None
match = old1.search(new_text, 0)
if match:
name2 = match.group('name2')
veikl = match.group('veikl')
text = match.group('text')
skliaust = match.group('skliaust')
if name2 == None:
name2 = ''
else:
name2 = name2.strip(' \r\n\t')
if text == None:
text = ''
tparms = re.compile(u'^(?P<name3>.*?)(((g\.)|(gimė))\s*)?(\[\[(?P<gmet2>\d*(\ m\.)?(\ pr\.\ m\.\ e\.)?)(\|\d*)?\]\](?:\s*)(?:m\.\s*)?(\[\[(?P<gmen2>[^\ ]*?)\ (?P<gd2>\d*?)\]\](?:\s*(d\.\s*)?)?)?(?P<gv2>.*?)(((((\-\s*)|(–\s*)|(-\s*)|(—\s*)|(−\s*)|(–\s*))(((m\.)|(mirė))\s*)?)|(†\s*))\[\[(?P<mmet2>\d*?(\ m\.)?(\ pr\.\ m\.\ e\.)?)\]\](?:\s*)(?:m\.\s*)?(\[\[(?P<mmen2>[^\ ]*?)\ (?P<md2>\d*?)\]\](?:\s*(d\.\s*)?)?)?(?P<mv2>.*?))?)?$')
matchs = tparms.search(skliaust, 0)
if matchs:
gmet2 = matchs.group('gmet2')
gmen2 = matchs.group('gmen2')
gd2 = matchs.group('gd2')
gv2 = matchs.group('gv2')
mmet2 = matchs.group('mmet2')
mmen2 = matchs.group('mmen2')
md2 = matchs.group('md2')
mv2 = matchs.group('mv2')
name3 = matchs.group('name3')
if name3 == None:
name3 = ''
else:
name3 = name3.strip(' \r\n\t')
if gmet == None:
if gmet2 != None:
gmet = gmet2
if gmen == None:
if gmen2 != None:
gmen = gmen2
if gd == None:
if gd2 != None:
gd = gd2
if gv == None:
if gv2 != None:
gv = gv2
if mmet == None:
if mmet2 != None:
mmet = mmet2
if mmen == None:
if mmen2 != None:
mmen = mmen2
if md == None:
if md2 != None:
md = md2
if mv == None:
if mv2 != None:
mv = mv2
## if pav == None:
## pav = ''
names = self.page.title()
if names != name2:
names += '<br/>' + name2
if name3 not in (u'', u'g.', u'gimė'):
names += '<br/>' + name3
ltcats = []
ltcat = catlib
asm = metai.Asmuo(name = self.page.title(), nameShow = name2,\
gData = metai.Data(metai = gmet, menuo = gmen, diena = gd), gVieta = gv,\
mData = metai.Data(metai = mmet, menuo = mmen, diena = md), mVieta = mv,\
what = veikl)
parttype = 'I'
if gmet is not None:
gPageMetai = metai.PageMetai(gmet)
if gmen is None:
gmeni = 'Nedatuoti'
parttype = 'MNI'
nextind = self.page.title()
else:
gmeni = metai.Menuo(gmen).get(vard = True, upper=True)
parttype = 'I'
nextind = int(gd)
ind = [ ltOrPs, 'Gimtadieniai', gmeni, nextind, self.page.title()]
gime = asm.getGimeMetai(full=False)
wikipedia.output(u'Itraukiam %s: \n%s' % (ind, gime))
gPageMetai.add(metai.PageMetaiPart(self.page.title(), parttype, gime, _ind=ind), ind)
gPageMetai.join()
wikipedia.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<"
% gmet)
oldMet = gPageMetai.old
newMet = gPageMetai.new
#wikipedia.setAction('Gimtadienis:'+gime[0:100])
while True:
wikipedia.showDiff(oldMet, newMet)
choice = wikipedia.inputChoice(
u'Do you want to accept these changes?',
['Yes', 'No', 'Edit', "Quit"],
['y', 'N', 'e', 'q'], 'N')
if choice == 'e':
editor = editarticle.TextEditor()
as_edited = editor.edit(newMet)
# if user didn't press Cancel
if as_edited and as_edited != newMet:
newMet = as_edited
if choice == 'q':
break
if choice == 'N':
break
if choice == 'n':
break
if choice == 'y':
gPageMetai.page.put_async(newMet, watchArticle=True, comment='Gimtadienis:'+gime[0:100])
break
if mmet is not None:
mPageMetai = metai.PageMetai(mmet)
if mmen is None:
mmeni = 'Nedatuoti'
parttype = 'MNI'
nextind = self.page.title()
else:
mmeni = metai.Menuo(mmen).get(vard = True, upper=True)
parttype = 'I'
nextind = int(md)
ind = [ ltOrPs, 'Mirtys', mmeni, nextind, self.page.title()]
mire = asm.getMireMetai(full=False)
wikipedia.output(u'Itraukiam %s: \n%s' % (ind, mire))
mPageMetai.add(metai.PageMetaiPart(self.page.title(), parttype, mire, _ind=ind), ind)
mPageMetai.join()
wikipedia.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<"
% mmet)
oldMet = mPageMetai.old
newMet = mPageMetai.new
#wikipedia.setAction('Mirtys:'+mire[0:100])
while True:
wikipedia.showDiff(oldMet, newMet)
choice = wikipedia.inputChoice(
u'Do you want to accept these changes?',
['Yes', 'No', 'Edit', "Quit"],
['y', 'N', 'e', 'q'], 'N')
if choice == 'e':
editor = editarticle.TextEditor()
as_edited = editor.edit(newMet)
# if user didn't press Cancel
if as_edited and as_edited != newMet:
newMet = as_edited
if choice == 'q':
break
if choice == 'N':
break
if choice == 'n':
break
if choice == 'y':
mPageMetai.page.put_async(newMet, watchArticle=True, comment='Mirtys:'+mire[0:100])
break
if mmet is None:
text2= asm.getGimeData()
if text2 is None:
text2 = ''
t1 = Template(new)
new = t1.substitute(#name=self.page.title(),
gd=asm.getGime(aslist = True),
gv=asm._gVieta,
#gadd = gadd,
md='',
mv='',
#madd = madd,
fonas=fonas,
veikl=asm._what,
names=names,
#name3=name3,
#text=text,
text2=text2,
)
else:
text2= asm.getGimeData() + asm.getMireData()
t1 = Template(new)
new = t1.substitute(#name=self.page.title(),
gd=asm.getGime(aslist = True),
gv=asm._gVieta,
#gadd = gadd,
md=asm.getMire(aslist = True),
mv=asm._mVieta,
#madd = madd,
fonas=fonas,
veikl=asm._what,
names=names,
#name3=name3,
#text=text,
text2=text2,
)
else:
raise TypeError('Blogo formato skliaustai: %s' % skliaust)
## else:
## wikipedia.output(u'Nerasta : %s' % new_text)
## raise TypeError('Nerasta:')
new_text = wikipedia.replaceExcept(new_text, old, new, exceptions,
allowoverlap=self.allowoverlap)
return new_text
def run(self):
"""
Starts the robot.
"""
# Run the generator which will yield Pages which might need to be
# changed.
for self.page in self.generator:
wikipedia.output(u'Page %s begin:' % self.page.title())
if self.isTitleExcepted(self.page.title()):
wikipedia.output(
u'Skipping %s because the title is on the exceptions list.'
% self.page.aslink())
continue
try:
# Load the page's text from the wiki
original_text = self.page.get(get_redirect=True)
if not self.page.canBeEdited():
wikipedia.output(u"You can't edit page %s"
% self.page.aslink())
continue
except wikipedia.NoPage:
wikipedia.output(u'Page %s not found' % self.page.aslink())
continue
new_text = original_text
while True:
if self.isTextExcepted(new_text):
wikipedia.output(
u'Skipping %s because it contains text that is on the exceptions list.'
% self.page.aslink())
break
new_text = self.doReplacements(new_text)
if new_text == original_text:
wikipedia.output('No changes were necessary in %s'
% self.page.aslink())
break
if self.recursive:
newest_text = self.doReplacements(new_text)
while (newest_text!=new_text):
new_text = newest_text
newest_text = self.doReplacements(new_text)
if hasattr(self, "addedCat"):
cats = self.page.categories(nofollow_redirects=True)
if self.addedCat not in cats:
cats.append(self.addedCat)
new_text = wikipedia.replaceCategoryLinks(new_text,
cats)
# Show the title of the page we're working on.
# Highlight the title in purple.
#wikipedia.setAction('{{biografija}} pakeitimas')
while True:
wikipedia.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<"
% self.page.title())
wikipedia.showDiff(original_text, new_text)
if self.acceptall:
break
choice = wikipedia.inputChoice(
u'Do you want to accept these changes?',
['Yes', 'No', 'Edit', 'open in Browser', 'All', "Quit"],
['y', 'N', 'e', 'b', 'a', 'q'], 'N')
if choice == 'e':
editor = editarticle.TextEditor()
as_edited = editor.edit(new_text)
# if user didn't press Cancel
if as_edited and as_edited != new_text:
new_text = as_edited
continue
if choice == 'b':
webbrowser.open("http://%s%s" % (
self.page.site().hostname(),
self.page.site().nice_get_address(self.page.title())
))
wikipedia.input("Press Enter when finished in browser.")
original_text = self.page.get(get_redirect=True, force=True)
new_text = original_text
continue
if choice == 'q':
return
if choice == 'n':
new_text = original_text
break
if choice == 'a':
self.acceptall = True
if choice == 'y':
self.page.put_async(new_text, watchArticle=True, comment='{{biografija}} pakeitimas:'+self.page.title())
new_text = original_text
break
# choice must be 'N'
break
if self.acceptall and new_text != original_text:
try:
self.page.put(new_text, watchArticle=True)
except wikipedia.EditConflict:
wikipedia.output(u'Skipping %s because of edit conflict'
% (self.page.title(),))
except wikipedia.SpamfilterError, e:
wikipedia.output(
u'Cannot change %s because of blacklist entry %s'
% (self.page.title(), e.url))
except wikipedia.PageNotSaved, error:
wikipedia.output(u'Error putting page: %s'
% (error.args,))
except wikipedia.LockedPage:
wikipedia.output(u'Skipping %s (locked page)'
% (self.page.title(),))
def prepareRegexForMySQL(pattern):
pattern = pattern.replace('\s', '[:space:]')
pattern = pattern.replace('\d', '[:digit:]')
pattern = pattern.replace('\w', '[:alnum:]')
pattern = pattern.replace("'", "\\" + "'")
#pattern = pattern.replace('\\', '\\\\')
#for char in ['[', ']', "'"]:
# pattern = pattern.replace(char, '\%s' % char)
return pattern
def main(*args):
add_cat = None
gen = None
# summary message
summary_commandline = None
# Array which will collect commandline parameters.
# First element is original text, second element is replacement text.
commandline_replacements = []
# A list of 2-tuples of original text and replacement text.
replacements = []
# Don't edit pages which contain certain texts.
exceptions = {
'title': [],
'text-contains': [],
'require-text': [],
'inside': [],
'inside-tags': [],
'require-title': [], # using a seperate requirements dict needs some
} # major refactoring of code.
# Should the elements of 'replacements' and 'exceptions' be interpreted
# as regular expressions?
regex = False
# Predefined fixes from dictionary 'fixes' (see above).
fix = None
fixCountryKas = None
fixCountryKa = None
fixCountryKo = None
fixdalis = 'vks'
fixform = '1a-ti-a-e'
fixs1 = u'mir'
fixs2 = u'mir\u0161t'
fixs3 = u'mir'
# the dump's path, either absolute or relative, which will be used
# if -xml flag is present
xmlFilename = None
useSql = False
PageTitles = []
# will become True when the user presses a ('yes to all') or uses the
# -always flag.
acceptall = False
# Will become True if the user inputs the commandline parameter -nocase
caseInsensitive = False
# Will become True if the user inputs the commandline parameter -dotall
dotall = False
# Will become True if the user inputs the commandline parameter -multiline
multiline = False
# Do all hits when they overlap
allowoverlap = False
# Do not recurse replacement
recursive = False
# This factory is responsible for processing command line arguments
# that are also used by other scripts and that determine on which pages
# to work on.
genFactory = pagegenerators.GeneratorFactory()
# Load default summary message.
# BUG WARNING: This is probably incompatible with the -lang parameter.
wikipedia.setAction(wikipedia.translate(wikipedia.getSite(), msg))
# Between a regex and another (using -fix) sleep some time (not to waste
# too much CPU
sleep = None
biogr = None
upe = None
#Set the regular expression flags
flags = re.UNICODE
if caseInsensitive:
flags = flags | re.IGNORECASE
if dotall:
flags = flags | re.DOTALL
if multiline:
flags = flags | re.MULTILINE
# Read commandline parameters.
for arg in wikipedia.handleArgs(*args):
if arg == '-regex':
regex = True
elif arg.startswith('-xmlstart'):
if len(arg) == 9:
xmlStart = wikipedia.input(
u'Please enter the dumped article to start with:')
else:
xmlStart = arg[10:]
elif arg.startswith('-xml'):
if len(arg) == 4:
xmlFilename = wikipedia.input(
u'Please enter the XML dump\'s filename:')
else:
xmlFilename = arg[5:]
elif arg =='-sql':
useSql = True
elif arg.startswith('-page'):
if len(arg) == 5:
PageTitles.append(wikipedia.input(
u'Which page do you want to change?'))
else:
PageTitles.append(arg[6:])
elif arg.startswith('-excepttitle:'):
exceptions['title'].append(arg[13:])
elif arg.startswith('-requiretitle:'):
exceptions['require-title'].append(arg[14:])
elif arg.startswith('-excepttext:'):
exceptions['text-contains'].append(arg[12:])
elif arg.startswith('-exceptinside:'):
exceptions['inside'].append(arg[14:])
elif arg.startswith('-exceptinsidetag:'):
exceptions['inside-tags'].append(arg[17:])
elif arg.startswith('-fix:'):
fix = arg[5:]
elif arg.startswith('-kas:'):
fixCountryKas = arg[5:]
elif arg.startswith('-ka:'):
fixCountryKa = arg[4:]
elif arg.startswith('-ko:'):
fixCountryKo = arg[4:]
elif arg.startswith('-sleep:'):
sleep = float(arg[7:])
elif arg == '-always':
acceptall = True
elif arg == '-recursive':
recursive = True
elif arg == '-nocase':
caseInsensitive = True
elif arg == '-dotall':
dotall = True
elif arg == '-multiline':
multiline = True
elif arg.startswith('-addcat:'):
add_cat = arg[len('addcat:'):]
elif arg.startswith('-summary:'):
wikipedia.setAction(arg[len('-summary:'):])
summary_commandline = True
elif arg.startswith('-allowoverlap'):
allowoverlap = True
else:
if not genFactory.handleArg(arg):
commandline_replacements.append(arg)
if fixCountryKa == 'zaid':
fixCountryKa = u'\u017eaid'
if fixCountryKo == 'CRC':
fixCountryKo = u'Kosta Rikos'
if fixCountryKo == 'TRI':
fixCountryKo = u'Trinidado ir Tobago'
if fixCountryKo == 'KOR':
fixCountryKo = u'Piet\u0173 Kor\u0117jos'
if fixCountryKo == 'KSA':
fixCountryKo = u'Saudo Arabijos'
if fixCountryKo == 'GUI':
fixCountryKo = u'Gvin\u0117jos'
if fixCountryKo == 'CMR':
fixCountryKo = u'Kamer\u016bno'
if fixCountryKo == 'CIV':
fixCountryKo = u'Dramblio Kaulo Kranto'
if fixCountryKo == 'SLO':
fixCountryKo = u'Slov\u0117nijos'
if fixCountryKo == 'SMR':
fixCountryKo = 'San Marino'
if fixCountryKo == 'LIE':
fixCountryKo = u'Lichten\u0161teino'
if fixCountryKo == 'BIH':
fixCountryKo = 'Bosnijos ir Hercegovinos'
if fixCountryKo == 'ARM':
fixCountryKo = u'Arm\u0117nijos'
if fixCountryKo == 'CZE':
fixCountryKo = u'\u010cekijos'
if fixCountryKo == 'FRA':
fixCountryKo = u'Pranc\u016bzijos'
if fixCountryKo == 'AZE':
fixCountryKo = u'Azerbaid\u017eano'
if fixCountryKo == 'RSA':
fixCountryKo = u'Piet\u0173 Afrikos Respublikos'
if fixCountryKo == 'CH':
fixCountryKo = u'\u0160veicarijos'
if fixCountryKo == 'FRO':
fixCountryKo = u'Farer\u0173'
elif fixCountryKo == 'SCO':
fixCountryKo = u'\u0160kotijos'
elif fixCountryKo == 'SWE':
fixCountryKo = u'\u0160vedijos'
elif fixCountryKo == 'NED':
fixCountryKo = u'Nyderland\u0173'
elif fixCountryKo == 'SR':
fixCountryKo = u'Senov\u0117s Romos'
elif fixCountryKo == 'UK':
fixCountryKo = u'Jungtin\u0117s Karalyst\u0117s'
if fix == 'upe':
upe = True
if fix == 'biogr':
biogr = True
if fix == 'stub':
if fixCountryKas != None and fixCountryKa != None and fixCountryKo != None:
fixes.stubCoutry(fixCountryKas,fixCountryKo,fixCountryKa)
fix = fix + '-' + fixCountryKas
elif fix == 'fut':
if fixCountryKas != None and fixCountryKa != None and fixCountryKo != None:
fixes.futCoutry(fixCountryKas,fixCountryKo,fixCountryKa)
fix = fix + '-' + fixCountryKas
elif fix == 'krep':
if fixCountryKas != None and fixCountryKa != None and fixCountryKo != None:
fixes.krepCoutry(fixCountryKas,fixCountryKo,fixCountryKa)
fix = fix + '-' + fixCountryKas
elif fix == 'ledr':
if fixCountryKas != None and fixCountryKa != None and fixCountryKo != None:
fixes.ledrCoutry(fixCountryKas,fixCountryKo,fixCountryKa)
fix = fix + '-' + fixCountryKas
if (len(commandline_replacements) % 2):
raise wikipedia.Error, 'require even number of replacements.'
elif (len(commandline_replacements) == 2 and fix == None):
replacements.append((commandline_replacements[0],
commandline_replacements[1]))
if summary_commandline == None:
wikipedia.setAction(wikipedia.translate(wikipedia.getSite(), msg )
% (' (-' + commandline_replacements[0] + ' +'
+ commandline_replacements[1] + ')'))
elif (len(commandline_replacements) > 1):
if (fix == None):
for i in xrange (0, len(commandline_replacements), 2):
replacements.append((commandline_replacements[i],
commandline_replacements[i + 1]))
if summary_commandline == None:
pairs = [( commandline_replacements[i],
commandline_replacements[i + 1] )
for i in range(0, len(commandline_replacements), 2)]
replacementsDescription = '(%s)' % ', '.join(
[('-' + pair[0] + ' +' + pair[1]) for pair in pairs])
wikipedia.setAction(
wikipedia.translate(wikipedia.getSite(), msg )
% replacementsDescription)
else:
raise wikipedia.Error(
'Specifying -fix with replacements is undefined')
elif fix == None:
old = wikipedia.input(u'Please enter the text that should be replaced:')
new = wikipedia.input(u'Please enter the new text:')
change = '(-' + old + ' +' + new
replacements.append((old, new))
while True:
old = wikipedia.input(
u'Please enter another text that should be replaced, or press Enter to start:')
if old == '':
change = change + ')'
break
new = wikipedia.input(u'Please enter the new text:')
change = change + ' & -' + old + ' +' + new
replacements.append((old, new))
if not summary_commandline == True:
default_summary_message = wikipedia.translate(wikipedia.getSite(), msg) % change
wikipedia.output(u'The summary message will default to: %s'
% default_summary_message)
summary_message = wikipedia.input(
u'Press Enter to use this default message, or enter a description of the\nchanges your bot will make:')
if summary_message == '':
summary_message = default_summary_message
wikipedia.setAction(summary_message)
else:
# Perform one of the predefined actions.
try:
fix = fixes.fixes[fix]
except KeyError:
wikipedia.output(u'Available predefined fixes are: %s'
% fixes.fixes.keys())
return
if fix.has_key('regex'):
regex = fix['regex']
if fix.has_key('msg'):
wikipedia.setAction(
wikipedia.translate(wikipedia.getSite(), fix['msg']))
if fix.has_key('exceptions'):
exceptions = fix['exceptions']
if fix.has_key('nocase'):
caseInsensitive = fix['nocase']
replacements = fix['replacements']
# Pre-compile all regular expressions here to save time later
for i in range(len(replacements)):
old, new = replacements[i]
if not regex:
old = re.escape(old)
oldR = re.compile(old, flags)
replacements[i] = oldR, new
for exceptionCategory in ['title', 'require-title', 'text-contains', 'inside', 'require-text']:
if exceptions.has_key(exceptionCategory):
patterns = exceptions[exceptionCategory]
if not regex:
patterns = [re.escape(pattern) for pattern in patterns]
patterns = [re.compile(pattern, flags) for pattern in patterns]
exceptions[exceptionCategory] = patterns
if xmlFilename:
try:
xmlStart
except NameError:
xmlStart = None
gen = XmlDumpReplacePageGenerator(xmlFilename, xmlStart,
replacements, exceptions)
elif useSql:
whereClause = 'WHERE (%s)' % ' OR '.join(
["old_text RLIKE '%s'" % prepareRegexForMySQL(old.pattern)
for (old, new) in replacements])
if exceptions:
exceptClause = 'AND NOT (%s)' % ' OR '.join(
["old_text RLIKE '%s'" % prepareRegexForMySQL(exc.pattern)
for exc in exceptions])
else:
exceptClause = ''
query = u"""
SELECT page_namespace, page_title
FROM page
JOIN text ON (page_id = old_id)
%s
%s
LIMIT 200""" % (whereClause, exceptClause)
gen = pagegenerators.MySQLPageGenerator(query)
elif PageTitles:
pages = [wikipedia.Page(wikipedia.getSite(), PageTitle)
for PageTitle in PageTitles]
gen = iter(pages)
gen = genFactory.getCombinedGenerator(gen)
if not gen:
# syntax error, show help text from the top of this file
wikipedia.showHelp('replace')
return
if xmlFilename:
# XML parsing can be quite slow, so use smaller batches and
# longer lookahead.
preloadingGen = pagegenerators.PreloadingGenerator(gen,
pageNumber=20, lookahead=100)
else:
preloadingGen = pagegenerators.PreloadingGenerator(gen, pageNumber=60)
bot = ReplaceRobot(preloadingGen, replacements, exceptions, acceptall, allowoverlap, recursive, add_cat, sleep, zbiogr = biogr, upe = upe)
bot.run()
if __name__ == "__main__":
try:
main()
finally:
wikipedia.stopme()