User:Darkicebot/eo

#coding: utf-8
"""
This python script, based on pagefromfile.py, is to be used by bots loading batches of words into Wiktionary.
 
*** This version (eo.py), was modified for use with Esperanto verb forms.
"""

__version__='$Id: Exp $'
 
import wikipedia, config
import re, sys, codecs
 
msg={
    'en': u'Mass creating Esperanto verb/noun/adjective forms'
    }
 
starttext = "{{-start-}}"
endtext = "{{-stop-}}"
filename = "eo.txt"
include = False
titlestart = u"<<<"
titleend = u">>>"
search_string = u""
force = False
append = "False"
notitle = True
 
def findpage(t):
    search_string = titlestart + "(.*?)" + titleend
    try:
        location = re.search(starttext+"([^\Z]*?)"+endtext,t)
        if include:
            contents = location.group()
        else:
            contents = location.group(1)
    except AttributeError:
        print 'Start or end marker not found.'
        return
    try:
        title = re.search(search_string, contents).group(1)
    except AttributeError:
        wikipedia.output(u"No title found - skipping a page.")
        return
    else:
        page = wikipedia.Page(mysite, title)
        wikipedia.output(page.title())
        if notitle:
          #Remove title (to allow creation of redirects)
          contents = re.sub(search_string, "", contents)
        #Remove trailing newlines (cause troubles when creating redirects)
        contents = re.sub('^[\r\n]*','',contents)
        if page.exists():
            old_text = page.get()
            if not re.search(r'==\s*Esperanto\s*==', old_text):
                contents = old_text + '\n\n----\n'  + contents + '\n{{rfc-auto}}\n'
                commenttext_add = commenttext + " - appended"
                wikipedia.output(u"Page %s already exists, adding to entry!"%title)
                page.put(contents, comment = commenttext_add, minorEdit = False)
            else:
                wikipedia.output(u"Page %s already exists with Esperanto section, not adding!"%title)
        else:
            page.put(contents, comment = commenttext, minorEdit = True) # was False (see above)
    findpage(t[location.end()+1:])
    return
 
def main():
    text = []
    f = codecs.open(filename,'r', encoding = config.textfile_encoding)
    text = f.read()
    findpage(text)
 
mysite = wikipedia.getSite()
commenttext = wikipedia.translate(mysite,msg)
for arg in sys.argv[1:]:
    arg = wikipedia.argHandler(arg, 'pagefromfile')
    if arg:
        if arg.startswith("-start:"):
            starttext=arg[7:]
        elif arg.startswith("-end:"):
            endtext=arg[5:]
        elif arg.startswith("-file:"):
            filename=arg[6:]
        elif arg=="-include":
            include = True
        #elif arg=="-exclude":
            #exclude = True
        elif arg=="-appendtop":
            append = "Top"
        elif arg=="-appendbottom":
            append = "Bottom"
        elif arg=="-force":
            force=True
        elif arg=="-safe":
            force=False
            append="False"
        elif arg=='-notitle':
            notitle=True
        elif arg.startswith("-titlestart:"):
            titlestart=arg[12:]
        elif arg.startswith("-titleend:"):
            titleend=arg[10:]
        elif arg.startswith("-summary:"):
            commenttext=arg[9:]
        else:
            wikipedia.output(u"Disregarding unknown argument %s."%arg)
 
try:
    main()
except:
    wikipedia.stopme()
    raise
else:
    wikipedia.stopme()