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.

449 lines
15 KiB

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
#
# redfam.py
#
# Copyright 2015 GOLDERWEB – 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 classes for working with RedFams
"""
import hashlib
import locale
import re
from datetime import datetime
import pywikibot
import jogobot
from .mysqlred import MysqlRedFam
class RedFam:
"""
Basic class for RedFams, containing the basic data structure
"""
def __init__( self, articlesList, beginning, ending=None, red_page_id=None,
status=0, fam_hash=None, heading=None ):
"""
Generates a new RedFam object
@param articlesList list List of articles
@param beginning datetime Beginning date
@param ending datetime Ending date
@param red_page_id int MW pageid of containing RedPage
@param status int Status of RedFam
@param fam_hash str SHA1 hash of articlesList
@param heading str Original heading of RedFam (Link)
"""
# Initial attribute values
self._articlesList = articlesList
self._beginning = beginning
self._ending = ending
self._red_page_id = red_page_id
self._status = status
self._fam_hash = fam_hash
self._heading = heading
# Calculates the sha1 hash over self._articlesList to
# rediscover known redundance families
self.calc_fam_hash()
def __repr__( self ):
"""
Returns repression str of RedFam object
@returns str repr() string
"""
__repr = "RedFam( " + \
"articlesList=" + repr( self._articlesList ) + \
", heading=" + repr( self._heading ) + \
", beginning=" + repr( self._beginning ) + \
", ending=" + repr( self._ending ) + \
", red_page_id=" + repr( self._red_page_id ) + \
", status=" + repr( self._status ) + \
", fam_hash=" + repr( self._fam_hash ) + \
" )"
return __repr
def calc_fam_hash( self ):
"""
Calculates the SHA-1 hash for the articlesList of redundance family.
Since we don't need security SHA-1 is just fine.
@returns str String with the hexadecimal hash digest
"""
h = hashlib.sha1()
h.update( str( self._articlesList[:8] ).encode('utf-8') )
if self._fam_hash and h.hexdigest() != self._fam_hash:
raise RedFamHashError( self._fam_hash, h.hexdigest() )
elif self._fam_hash:
return
else:
self._fam_hash = h.hexdigest()
@classmethod
def flush_db_cache( cls ):
"""
Calls flush method of Mysql Interface class
"""
MysqlRedFam.flush()
class RedFamParser( RedFam ):
"""
Provides an interface to RedFam for adding/updating redundance families
while parsig redundance pages
"""
# Define the timestamp format
__timestamp_format = jogobot.timestamp_format
# Define section heading re.pattern
__sectionhead_pat = re.compile( r"^(=+)(.*\[\[.+\]\].*\[\[.+\]\].*)\1" )
# Define timestamp re.pattern
__timestamp_pat = re.compile( jogobot.timestamp_regex )
# Textpattern for recognisation of done-notices
__done_notice = ":<small>Archivierung dieses Abschnittes \
wurde gewünscht von:"
__done_notice2 = "{{Erledigt|"
def __init__( self, heading, red_page_id, red_page_archive,
beginning, ending=None ):
"""
Creates a RedFam object based on data collected while parsing red_pages
combined with possibly former known data from db
@param red_fam_heading str Wikitext heading of section
@param red_page_id int MediaWiki page_id
@param red_page_archive bool Is red_page an archive
@param beginning datetime Timestamp of beginning
str as strptime parseable string
@param ending datetime Timestamp of ending
str strptime parseable string
"""
# Set object attributes:
self._red_page_id = red_page_id
self._red_page_archive = red_page_archive
self._fam_hash = None
# Method self.add_beginning sets self._beginning directly
self.add_beginning( beginning )
# Method self.add_ending sets self._ending directly
if( ending ):
self.add_ending( ending )
else:
# If no ending was provided set to None
self._ending = None
self._status = None
# Parse the provided heading of redundance section
# to set self._articlesList
self.heading_parser( heading )
# Calculates the sha1 hash over self._articlesList to
# rediscover known redundance families
self.calc_fam_hash()
# Open database connection, ask for data if existing,
# otherwise create entry
self.__handle_db()
# Check status changes
self.status()
# Triggers db update if anything changed
self.changed()
def __handle_db( self ):
"""
Handles opening of db connection
"""
# We need a connection to our mysqldb
self.__mysql = MysqlRedFam( self._fam_hash )
if not self.__mysql.data:
self.__mysql.add_fam( self._articlesList, self._heading,
self._red_page_id, self._beginning,
self._ending )
def heading_parser( self, heading ):
"""
Parses given red_fam_heading string and saves articles list
"""
# Predefine a pattern for wikilinks' destination
wikilink_pat = re.compile( r"\[\[([^\[\]\|]+)(?:\]\]|\|)" )
# Parse content of heading for generating section links later
match = type( self ).__sectionhead_pat.search( heading )
if match:
self._heading = match.group(2).lstrip()
else:
raise RedFamHeadingError( heading )
# We get the pages in first [0] element iterating over
# wikilink_pat.findall( line )
self._articlesList = [ link[0] for link
in wikilink_pat.findall( self._heading ) ]
# Catch sections with more then 8 articles, print error
if len( self._articlesList ) > 8:
# For repression in output we need to know the fam hash
self.calc_fam_hash()
pywikibot.output( "\
{datetime}\03{{lightred}}[WARNING] – \
Maximum number of articles in red_fam exceeded, maximum number is 8, \
{number:d} were given \n {repress}".format(
datetime=datetime.now().strftime( "%Y-%m-%d %H:%M:%S" ),
number=len( self._articlesList ), repress=repr( self ) ) )
self._articlesList = self._articlesList[:8]
def add_beginning( self, beginning ):
"""
Adds the beginning date of a redundance diskussion to the object
@param datetime datetime Beginning date
"""
self._beginning = self.__datetime( beginning )
def add_ending( self, ending ):
"""
Adds the ending date of a redundance diskussion to the object.
@param datetime datetime Ending date
"""
self._ending = self.__datetime( ending )
def __datetime( self, timestamp ):
"""
Decides wether given timestamp is a parseable string or a
datetime object and returns a datetime object in both cases
@param datetime timestamp Datetime object
str timestamp Parseable string with timestamp
@returns datetime Datetime object
"""
# Make sure locale is set to 'de_DE.UTF-8' to prevent problems
# with wrong month abreviations in strptime
locale.setlocale(locale.LC_ALL, 'de_DE.UTF-8')
if( isinstance( timestamp, datetime ) ):
return timestamp
else:
result = datetime.strptime( timestamp,
type( self ).__timestamp_format )
return result
def status( self ):
"""
Handles detection of correct status
There are three possible stati:
- 0 Discussion running --> no ending, page is not an archive
- 1 Discussion over --> ending present, page is not an archive
- 2 Discussion archived --> ending (normaly) present, page is archive
- 3 and greater status was set by worker script, do not change it
"""
# Do not change stati set by worker script etc.
if not self.__mysql.data['status'] > 2:
# No ending, discussion is running:
# Sometimes archived discussions also have no detectable ending
if not self._ending and not self._red_page_archive:
self._status = 0
else:
if not self._red_page_archive:
self._status = 1
else:
self._status = 2
else:
self._status = self.__mysql.data[ 'status' ]
def changed( self ):
"""
Checks wether anything has changed and maybe triggers db update
"""
# On archived red_fams do not delete possibly existing ending
if( not self._ending and self._status > 1
and self.__mysql.data[ 'ending' ] ):
self._ending = self.__mysql.data[ 'ending' ]
# Since status change means something has changed, update database
if( self._status != self.__mysql.data[ 'status' ] or
self._beginning != self.__mysql.data[ 'beginning' ] or
self._ending != self.__mysql.data[ 'ending' ] or
self._red_page_id != self.__mysql.data[ 'red_page_id' ] or
self._heading != self.__mysql.data[ 'heading' ]):
self.__mysql.update_fam( self._red_page_id, self._heading,
self._beginning, self._ending,
self._status )
@classmethod
def is_sectionheading( cls, line ):
"""
Checks wether given line is a red_fam section heading
@param str line String to check
@returns bool Returns True if it is a section heading
"""
if cls.__sectionhead_pat.search( line ):
return True
else:
return False
@classmethod
def is_beginning( cls, line ):
"""
Returns the first timestamp found in line, otherwise None
@param str line String to search in
@returns str Timestamp, otherwise None
"""
match = cls.__timestamp_pat.search( line )
if match:
# Since some timestamps are broken we need to reconstruct them
# by regex match groups
result = match.group(1) + ", " + match.group(2) + ". " +\
match.group(3) + ". " + match.group(4)
return result
else:
return None
@classmethod
def is_ending( cls, line ):
"""
Returns the timestamp of done notice ( if one ), otherwise None
@param str line String to search in
@returns str Timestamp, otherwise None
"""
if ( cls.__done_notice in line ) or ( cls.__done_notice2 in line ):
match = cls.__timestamp_pat.search( line )
if match:
# Since some timestamps are broken we need to reconstruct them
# by regex match groups
result = match.group(1) + ", " + match.group(2) + ". " +\
match.group(3) + ". " + match.group(4)
return result
return None
@classmethod
def is_ending2( cls, line ):
"""
Returns the last timestamp found in line, otherwise None
@param str line String to search in
@returns str Timestamp, otherwise None
"""
matches = cls.__timestamp_pat.findall( line )
if matches:
# Since some timestamps are broken we need to reconstruct them
# by regex match groups
result = matches[-1][0] + ", " + matches[-1][1] + ". " +\
matches[-1][2] + ". " + matches[-1][3]
return result
else:
return None
class RedFamWorker( RedFam ):
"""
Handles working with redundance families stored in database
where discussion is finished
"""
pass
class RedFamError( Exception ):
"""
Base class for all Errors of RedFam-Module
"""
def __init__( self, message=None ):
"""
Handles Instantiation of RedFamError's
"""
if not message:
self.message = "An Error occured while executing a RedFam action"
else:
self.message = message
def __str__( self ):
"""
Output of error message
"""
return self.message
class RedFamHashError( RedFamError ):
"""
Raised when given RedFamHash does not match with calculated
"""
def __init__( self, givenHash, calculatedHash ):
message = "Error: Given fam_hash ('{given}') does not match with \
calculated ('{calc}'".format( given=givenHash,
calc=calculatedHash )
super().__init__( message )
class RedFamHeadingError ( RedFamError ):
"""
Raised when given RedFamHeading does not match __sectionhead_pat Regex
"""
def __init__( self, heading ):
message = "Error while trying to parse section heading. Given heading \
'{heading}' does not match RegEx".format(
heading=heading )
super().__init__( message )