You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 

143 lines
4.0 KiB

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
#
# redpage.py
#
# Copyright 2017 Jonathan Golder <jonathan@golderweb.de>
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
# MA 02110-1301, USA.
#
#
"""
Provides a class for handling redundance discussion pages and archives
"""
import pywikibot # noqa
import mwparserfromhell as mwparser
import jogobot # noqa
from lib.mysqlred import (
MysqlRedPage, relationship, attribute_mapped_collection )
from lib.redfam import RedFamParser
class RedPage( MysqlRedPage ):
"""
Class for handling redundance discussion pages and archives
"""
def __init__( self, page=None, pageid=None, archive=False ):
"""
Generate a new RedPage object based on the given pywikibot page object
@param page Pywikibot/MediaWiki page object for page
@type page pywikibot.Page
@param pageid MW-Pageid for related page
@type pageid int
"""
# Safe the pywikibot page object
if page:
self._page = page
super().__init__(
pageid=self._page.pageid,
revid=self._page._revid,
pagetitle=self._page.title(),
status=None
)
self.is_archive()
self.session.add(self)
def update( self, page ):
self._page = page
self.revid = page._revid
self.pagetitle = page.title()
self.is_archive()
@property
def page(self):
if not hasattr(self, "_page"):
self._page = pywikibot.Page( pywikibot.Site(), self.pagetitle )
return self._page
@property
def archive(self):
self.is_archive()
return self.status.has("archive")
def is_archive( self ):
"""
Detects wether current page is an archive of discussions
"""
if( ( u"/Archiv" in self.page.title() ) or
( "{{Archiv}}" in self.page.text ) or
( "{{Archiv|" in self.page.text ) ):
self.status.add("archive")
else:
self.status.discard("archive")
def is_parsing_needed( self ):
"""
Decides wether current RedPage needs to be parsed or not
"""
return self.changedp() or not self.status.has("parsed")
def parse( self ):
"""
Handles the parsing process
"""
# Generate Wikicode object
self.wikicode = mwparser.parse( self.page.text )
# Select RedFam-sections
# matches=Regexp or
# function( gets heading content as wikicode as param 1)
# include_lead = if true include first section (intro)
# include_heading = if true include heading
fams = self.wikicode.get_sections(
matches=RedFamParser.is_section_redfam_cb,
include_lead=False, include_headings=True )
# Iterate over RedFam
for fam in fams:
yield fam
else:
self.status.add("parsed")
self._parsed = True
@classmethod
def flush_db_cache( cls ):
"""
Calls flush method of Mysql Interface class
"""
cls.session.commit()
class RedPageParser( RedPage ):
"""
Wrapper class to change the type of redfams collection elements in parser
"""
redfams = relationship(
"RedFamParser", enable_typechecks=False, back_populates="redpage",
collection_class=attribute_mapped_collection("famhash") )