Utilisateur:Kipmaster/tradinter

tradinter.py

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

"""
This bot goes over multiple pages of the home wiki, and edits them without
changing. This is for example used to get category links in templates
working.

Don't forget to set the ftout to your current list of words,
see below for a line that looks like:
ftout =open('/home/cmillet/wikitruks/wiktio/all/2005-12-14.txt', 'r')

This script understands various command-line arguments:

    -start:        used as -start:page_name, specifies that the robot should
                   go alphabetically through all pages on the home wiki,
                   starting at the named page.

    -file:         used as -file:file_name, read a list of pages to treat
                   from the named textfile. Page titles should be enclosed
                   in [[double-squared brackets]].

    -ref:          used as -start:page_name, specifies that the robot should
                   touch all pages referring to the named page.

    -cat:          used as -cat:category_name, specifies that the robot should
                   touch all pages in the named category.

All other parameters will be regarded as a page title; in this case, the bot
will only touch a single page.
"""
import wikipedia, wiktionary, pagegenerators, catlib
import sys
import re

tradmsg = "{{-trad-}}"
'''
listelng = ['fr','als','an','am','ar','as','ast','ay','az','bm','de','dog','el','en','eo','es','et','gu','hi','io','ja','it','ko','ln','nl','oc','vi','pt','ru','sv','tr','ia','kn','pl','ta','la','ur','fi','bn','ga','grc','hu','pa','fa','sl','bo','uk','af','sq','hy','br','bg','ca','chr','da','gl','ka','he','ku','lv','li','mn','ro','sa','sr','scn','tt','cs','th','te','yi','or','ml','zh','zu']
# retrait de dog : pas de wiktionnaire dans cette langue
nowiktiolng = ['dog','fil','grc']

'''

# Wiktionaries that makes the distinction between this and This :
# (the list http://meta.wikimedia.org/wiki/Help:Page_name is not really uptodate)
nocaplng = ['af','bg','cs','de','en','eo','es','fa','fi','fo','fr','gu','hi','hr','hu','is','it','ja','ka','kn','ku','ml','nl','sa','scn','sq','sv','sw','tr','vi']

#Wiktionary I checked that still capitalize there entries:
# ln -- pt

# ftout MUST BE SET correctly
ftout =open('/home/cmillet/wikitruks/wiktio/all/2005-12-14.txt', 'r')
lst_mots = ftout.readlines()
ftout.close()

wikipedia.setAction(u'interwikification des traductions (modèle trad)')

                            # si c'est {{-... ou [[... alors on entre dans une autre section, ou fin de liste
                            # if ( re.compile("^(\{\{-|\[\[)",re.M).match(newtext,curidx) ):


class TouchBot:
  def __init__(self, generator, acceptall = False):
    self.generator = generator
    self.acceptall = acceptall
    
  def run(self):
    for page in self.generator:
      try:
        wikipedia.output('page: %s' % page.title())
        lapage = page.get()
	lapagenew = page.get() # comme newtext, mais avec les commentaires
        #enlevement des <!-- -->
	p = re.compile( u"\<\!\-\-(.*?)\-\-\>", re.DOTALL | re.MULTILINE)
	oldtext = p.sub(u"", lapage)
	# wikipedia.output( oldtext )
        # il faut agir ici...
        newtext = oldtext
        curidx = 0
        while ( newtext.find(tradmsg, curidx) != -1 ):
          curidx = newtext.find(tradmsg,curidx) + len(tradmsg)
          sectiontrad=1
          while (sectiontrad == 1):
            # return original_text[hit:hit + len(exception)]
            # (eventuellement un ":") un *, un espace, un {{code de langue}}, puis des liens, puis retour a la ligne
            # print "sectrad : %d"%sectiontrad
            result = re.compile("(^:?\* *\{\{(\w*?)\}\}(.*?\n))",re.MULTILINE).search(oldtext,curidx)
            if not result:
              # ne matche plus
              sectiontrad = 0
            else:
              ligneTotale = result.group(1)
              lang = result.group(2)

              # print "curidx %d lastidx %d"%(curidx,result.end(2))
              resteAnalyse = result.group(3)
              newLine = ligneTotale
              # wikipedia.output(u'reste : %s'%ligneAnalyse)

              listeT = re.findall("\{\{trad\|\w*?\|(.*?)\}\}" , resteAnalyse )
              # print listeT
              for eltT in listeT :
                # on ne sait pas traiter si il y a un #
                if '#' in eltT:
                  continue
                wikipedia.output(u'recherche de "%s:%s"'%(lang,eltT) )
                #chercher ce mot sur le wiktionnaire lang
                #page_otre = wiktionary.WiktionaryPage(lang,eltT)
#                  site_otre = wikipedia.getSite(code = lang, fam = 'wiktionary')
#                  page_otre = wikipedia.Page(site_otre, eltT)
		if  ( lang not in nocaplng ) :
		  wikipedia.output(u'--------avantcap %s'%eltT)
		  eltTsearch = eltT[0].upper() + eltT[1:]
		  wikipedia.output(u'--------aprescap %s'%eltTsearch)
		else:
		  eltTsearch = eltT
                tosearch = u'%s:%s\n'%(lang,eltTsearch)
                tosearch = tosearch.encode('utf-8')
                if not ( tosearch in lst_mots ):
#                  position = lst_mots.index( tosearch )
#                  if not page_otre.exists():
#                  if not ( position < 0 ):
                  print "DEWIKIFICATION"
                  new = u'[[%s]]'%eltT
                  old = u'{{trad|%s|%s}}'%(lang,eltT)
                  newLine = newLine.replace(old , new)
                    #newtext = newtext.replace(old,new)
                
              listeT = re.findall("\[\[(.*?)\]\]" , resteAnalyse )
              for eltT in listeT :
                if '#' in eltT:
                  continue
                if eltT[0] == ':' :
                  # lien du type [[:lang:mot]] à supprimer                    
                  old = u'[[%s]]'%eltT
                  new = u''
                  newLine = newLine.replace(old , new)
                else:
                  wikipedia.output(u'recherche de "%s:%s"'%(lang,eltT) )
                    #chercher ce mot sur le wiktionnaire lang
                    #page_otre = wiktionary.WiktionaryPage(lang,eltT)
#                    site_otre = wikipedia.getSite(code = lang, fam = 'wiktionary')
#                    page_otre = wikipedia.Page(site_otre, eltT)
  		  if  ( lang not in nocaplng ) :
		    wikipedia.output(u'--------avantcap %s'%eltT)
		    eltTcap = eltT[0].upper() + eltT[1:]
		    wikipedia.output(u'--------aprescap %s'%eltTcap)
                  else:
		    eltTcap = eltT
                  tosearch = u'%s:%s\n'%(lang,eltT)
                  tosearch = tosearch.encode('utf-8')
                  if ( tosearch in lst_mots ):
#  		    position = lst_mots.index( '%s:%s'%(lang,eltT) )
#                  if not page_otre.exists():
#                    if not ( position < 0 ):
                    print "INTERWIKIFICATION"
                    old = u'[[%s]]'%eltT
                    new = u'{{trad|%s|%s}}'%(lang,eltT)
                    newLine = newLine.replace(old , new)
                      # wikipedia.output('old : %s , new : %s , newline : %s'%(old , new , newLine))
                      #newtext = newtext.replace(old,new)
                
                # find de l'analyse de la ligne : on avance d'un pas
              newtext = newtext.replace(ligneTotale, newLine)
              lapagenew = lapagenew.replace(ligneTotale, newLine)
              curidx = result.end(3)
              #fin du if langue pas valide
            #fin du if not result
          #fin du while qu'on est dans la section de traduction
        # fin du while {{-trad-}}
        
        # on uploade le texte
        if newtext == oldtext:
          wikipedia.output('No changes were necessary in %s' % page.title())
        else:
          wikipedia.output(u'>>> %s <<<' % page.title())
          wikipedia.showDiff(lapage, lapagenew)
          if not self.acceptall:
              choice = wikipedia.inputChoice(u'Do you want to accept these changes?',  ['Yes', 'No', 'All'], ['y', 'N', 'a'], 'N')
              if choice in ['a', 'A']:
                  self.acceptall = True
          if self.acceptall or choice in ['y', 'Y']:
              print "put"
              page.put(lapagenew)
      
      except wikipedia.NoPage:
          print "Page %s does not exist?!?!"%page.aslink()
      except wikipedia.IsRedirectPage:
          pass
      except wikipedia.LockedPage:
          pass

def main():
    #page generator
    gen = None
    pageTitle = []
    for arg in sys.argv[1:]:
        arg = wikipedia.argHandler(arg, 'touch')
        if arg:
            if arg.startswith('-start:'):
                gen = pagegenerators.AllpagesPageGenerator(arg[7:])
            elif arg.startswith('-ref:'):
                referredPage = wikipedia.Page(wikipedia.getSite(), arg[5:])
                gen = pagegenerators.ReferringPageGenerator(referredPage)
            elif arg.startswith('-links:'):
                linkingPage = wikipedia.Page(wikipedia.getSite(), arg[7:])
                gen = pagegenerators.LinkedPageGenerator(linkingPage)
            elif arg.startswith('-file:'):
                gen = pagegenerators.TextfilePageGenerator(arg[6:])
            elif arg.startswith('-cat:'):
                cat = catlib.Category(wikipedia.getSite(), arg[5:])
                gen = pagegenerators.CategorizedPageGenerator(cat)
            else:
                pageTitle.append(arg)

    if pageTitle:
        page = wikipedia.Page(wikipedia.getSite(), ' '.join(pageTitle))
        gen = iter([page])
    if not gen:
        wikipedia.showHelp('touch')
    else:
        preloadingGen = pagegenerators.PreloadingGenerator(gen)
        bot = TouchBot(preloadingGen)
        bot.run()

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