Introduce new directory structure

To clarify which is a bot and which are helper scripts

Related Task: [https://fs.golderweb.de/index.php?do=details&task_id=74 FS#74]
This commit is contained in:
2016-08-24 22:41:41 +02:00
parent af48888535
commit e28acf88d1
4 changed files with 5 additions and 5 deletions

326
lib/mysqlred.py Normal file
View File

@@ -0,0 +1,326 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
#
# mysqlred.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 interface classes for communication of redundances bot with mysql-db
"""
# Prefere using oursql then MySQLdb
try:
import oursql as mysqldb
except ImportError:
import MySQLdb as mysqldb
import atexit
from pywikibot import config
import jogobot
class MysqlRed:
"""
Basic interface class, containing opening of connection
Specific querys should be defined in descendant classes per data type
"""
# Save mysqldb-connection as class attribute to use only one
# in descendant classes
connection = False
db_hostname = config.db_hostname
db_port = config.db_port
db_username = config.db_username
db_password = config.db_password
db_name = config.db_username + jogobot.config['db_suffix']
# Class variables for storing cached querys
_cached_update_data = []
_update_query = ''
_cached_insert_data = {}
_insert_query = ''
def __init__( self ):
"""
Opens a connection to MySQL-DB
@returns mysql-stream MySQL Connection
"""
# Connect to mysqldb only once
if not type( self ).connection:
type( self ).connection = mysqldb.connect(
host=type( self ).db_hostname,
port=type( self ).db_port,
user=type( self ).db_username,
passwd=type( self ).db_password,
db=type( self ).db_name )
# Register callback for warnig if exit with cached db write querys
atexit.register( type(self).warn_if_not_flushed )
def __del__( self ):
"""
Before deleting class, close connection to MySQL-DB
"""
type( self ).connection.close()
@classmethod
def flush( cls ):
"""
Run cached querys
"""
if not cls.connection:
raise MysqlRedConnectionError( "No connection exists!" )
cursor = cls.connection.cursor()
# Execute insert query
if cls._cached_insert_data:
# Since cls._cached_insert_data is a dict, we need to have a custom
# Generator to iterate over it
cursor.executemany( cls._insert_query,
( cls._cached_insert_data[ key ]
for key in cls._cached_insert_data ) )
# Reset after writing
cls._cached_insert_data = {}
# Execute update query
# Use executemany since update could not be reduced to one query
if cls._cached_update_data:
cursor.executemany( cls._update_query, cls._cached_update_data )
# Reset after writing
cls._cached_update_data = []
# Commit db changes
if cls._cached_insert_data or cls._cached_update_data:
cls.connection.commit()
@classmethod
def warn_if_not_flushed(cls):
"""
Outputs a warning if there are db write querys cached and not flushed
before exiting programm!
"""
if cls._cached_update_data or cls._cached_insert_data:
jogobot.output( "Cached Database write querys not flushed!!! " +
"Data loss is possible!", "WARNING" )
class MysqlRedPage( MysqlRed ):
"""
MySQL-db Interface for handling querys for RedPages
"""
# Class variables for storing cached querys
_cached_update_data = []
_update_query = 'UPDATE `red_pages` \
SET `page_title` = ?, `rev_id` = ?, `status`= ? WHERE `page_id` = ?;'
_cached_insert_data = {}
_insert_query = 'INSERT INTO `red_pages` \
( page_id, page_title, rev_id, status ) VALUES ( ?, ?, ?, ? );'
def __init__( self, page_id ):
"""
Creates a new instance, runs __init__ of parent class
"""
super().__init__( )
self.__page_id = int( page_id )
self.data = self.get_page()
def __del__( self ):
pass
def get_page( self ):
"""
Retrieves a red page row from MySQL-Database for given page_id
@param int page_id MediaWiki page_id for page to retrieve
@returns tuple Tuple with data for given page_id
bool FALSE if none found
"""
cursor = type( self ).connection.cursor(mysqldb.DictCursor)
cursor.execute( 'SELECT * FROM `red_pages` WHERE `page_id` = ?;',
( self.__page_id, ) )
res = cursor.fetchone()
if res:
return res
else:
return False
def add_page( self, page_title, rev_id, status=0 ):
"""
Inserts a red page row in MySQL-Database for given page_id
@param int rev_id MediaWiki current rev_id
@param str page_title MediaWiki new page_title
@param int status Page parsing status
"""
insert_data = { self.__page_id: ( self.__page_id, page_title,
rev_id, status ) }
type( self )._cached_insert_data.update( insert_data )
# Manualy construct self.data dict
self.data = { 'page_id': self.__page_id, 'rev_id': rev_id,
'page_title': page_title, 'status': status }
def update_page( self, rev_id=None, page_title=None, status=0 ):
"""
Updates the red page row in MySQL-Database for given page_id
@param int rev_id MediaWiki current rev_id
@param str page_title MediaWiki new page_title
@param int status Page parsing status
"""
if not page_title:
page_title = self.data[ 'page_title' ]
if not rev_id:
rev_id = self.data[ 'rev_id' ]
type( self )._cached_update_data.append( ( page_title, rev_id,
status, self.__page_id ) )
class MysqlRedFam( MysqlRed ):
"""
MySQL-db Interface for handling querys for RedFams
"""
# Class variables for storing cached querys
_cached_update_data = []
_update_query = 'UPDATE `red_families` \
SET `red_page_id` = ?, `heading` = ?, `beginning` = ?, `ending` = ?, \
`status`= ? WHERE `fam_hash` = ?;'
_cached_insert_data = {}
_insert_query = 'INSERT INTO `red_families` \
( fam_hash, red_page_id, beginning, ending, status, heading, \
article0, article1, article2, article3, article4, article5, article6, \
article7 ) VALUES ( ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ? );'
def __init__( self ):
"""
Creates a new instance, runs __init__ of parent class
"""
super().__init__( )
def __del__( self ):
pass
def get_fam( self, fam_hash ):
"""
Retrieves a red family row from MySQL-Database for given fam_hash
@returns dict Dictionairy with data for given fam hash
False if none found
"""
self.__fam_hash = fam_hash
cursor = type( self ).connection.cursor( mysqldb.DictCursor )
cursor.execute( 'SELECT * FROM `red_families` WHERE `fam_hash` = ?;',
( fam_hash, ) )
self.data = cursor.fetchone()
def add_fam( self, articlesList, heading, red_page_id,
beginning, ending=None, status=0 ):
data = [ self.__fam_hash, red_page_id, beginning, ending,
status, heading ]
for article in articlesList:
data.append( str( article ) )
while len( data ) < 14:
data.append( None )
data = tuple( data )
insert_data = { self.__fam_hash: data }
type( self )._cached_insert_data.update( insert_data )
# Manualy construct self.data dict
data_keys = ( 'fam_hash', 'red_page_id', 'beginning', 'ending',
'status', 'heading', 'article0', 'article1', 'article2',
'article3', 'article4', 'article5', 'article6',
'article7' )
self.data = dict( zip( data_keys, data ) )
def update_fam( self, red_page_id, heading, beginning, ending, status ):
"""
Updates the red fam row in MySQL-Database for given fam_hash
@param int red_page_id MediaWiki page_id
@param datetime beginning Timestamp of beginning
qparam datetime ending Timestamp of ending of
@param int status red_fam status
"""
type( self )._cached_update_data.append( ( red_page_id, heading,
beginning, ending, status,
self.__fam_hash ) )
def get_by_status( self, status ):
"""
Generator witch fetches redFams with given status from DB
"""
cursor = type( self ).connection.cursor( mysqldb.DictCursor )
cursor.execute( 'SELECT * FROM `red_families` WHERE `status` = ?;',
( status, ) )
while True:
res = cursor.fetchmany( 1000 )
if not res:
break
for row in res:
yield row
class MysqlRedError(Exception):
"""
Basic Exception class for this module
"""
pass
class MysqlRedConnectionError(MysqlRedError):
"""
Raised if there are Errors with Mysql-Connections
"""
pass

559
lib/redfam.py Normal file
View File

@@ -0,0 +1,559 @@
#!/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 mwparserfromhell as mwparser # noqa
import pywikibot # noqa
from pywikibot.tools import deprecated # noqa
import jogobot
from lib.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.config['redundances']['timestamp_format']
# Define section heading re.pattern
__sectionhead_pat = re.compile( r"^(.*\[\[.+\]\].*\[\[.+\]\].*)" )
# Define timestamp re.pattern
__timestamp_pat = re.compile( jogobot.config['redundances']
['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, 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 page Pywikibot.page object
@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._pageid
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.__mysql.get_fam( 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
@param heading Heading of RedFam-Section
@type heading wikicode or mwparser-parseable
"""
# Save heading as string
self._heading = str( heading )
# Parse string heading with mwparse again everytime
# In some cases the given wikicode is broken due to syntax errors
# (Task FS#77)
heading = mwparser.parse( self._heading )
# Save destinations of wikilinks in headings
self._articlesList = [ str( link.title ) for link
in heading.ifilter_wikilinks() ]
# 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()
jogobot.output(
( "\03{{lightred}}" +
"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 ) ),
"WARNING" )
# Only save the first 8 articles
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
@deprecated
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( str(line) ):
return True
else:
return False
@classmethod
def is_section_redfam_cb( cls, heading ):
"""
Used as callback for wikicode.get_sections in redpage.parse to
select sections which are redfams
"""
# Because of strange behavior in some cases, parse heading again
# (Task FS#77)
heading = mwparser.parse( str( heading ) )
# Make sure we have min. two wikilinks in heading to assume a redfam
if len( heading.filter_wikilinks() ) >= 2:
return True
else:
return False
@classmethod
def parser( cls, text, page, isarchive=False ):
"""
Handles parsing of redfam section
@param text Text of RedFam-Section
@type text wikicode or mwparser-parseable
"""
# Parse heading with mwparse if needed
if not isinstance( text, mwparser.wikicode.Wikicode ):
text = mwparser.parse( text )
# Extract heading text
heading = next( text.ifilter_headings() ).title
# Extract beginnig and maybe ending
(beginning, ending) = RedFamParser.extract_dates( text, isarchive )
# Missing beginning (Task: FS#76)
# Use first day of month of reddisc
if not beginning:
match = re.search(
jogobot.config["redundances"]["reddiscs_onlyinclude_re"],
page.title() )
if match:
beginning = datetime.strptime(
"01. {month} {year}".format(
month=match.group(1), year=match.group(2)),
"%d. %B %Y" )
# Create the RedFam object
RedFamParser( heading, page, isarchive, beginning, ending )
@classmethod
def extract_dates( cls, text, isarchive=False ):
"""
Returns tuple of the first and maybe last timestamp of a section.
Last timestamp is only returned if there is a done notice or param
*isarchiv* is set to 'True'
@param text Text to search in
@type line Any Type castable to str
@param isarchive If true skip searching done notice (on archivepages)
@type isarchive bool
@returns Timestamps, otherwise None
@returntype tuple of strs
"""
# Match all timestamps
matches = cls.__timestamp_pat.findall( str( text ) )
if matches:
# First one is beginning
# Since some timestamps are broken we need to reconstruct them
# by regex match groups
beginning = ( matches[0][0] + ", " + matches[0][1] + ". " +
matches[0][2] + ". " + matches[0][3] )
# Last one maybe is ending
# Done notice format 1
# Done notice format 2
# Or on archivepages
if ( cls.__done_notice in text or
cls.__done_notice2 in text or
isarchive ):
ending = ( matches[-1][0] + ", " + matches[-1][1] + ". " +
matches[-1][2] + ". " + matches[-1][3] )
else:
ending = None
# Missing dates (Task: FS#76)
else:
beginning = None
ending = None
return (beginning, ending)
@classmethod
@deprecated( 'extract_dates' )
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
"""
return cls.extract_dates( line )[0]
@classmethod
@deprecated( 'extract_dates' )
def is_ending( cls, line, isarchive=False ):
"""
Returns the timestamp of done notice ( if one ), otherwise None
@param line String to search in
@type line str
@param isarchive If true skip searching done notice (on archivepages)
@type isarchive bool
@returns Timestamp, otherwise None
@returntype str
"""
return cls.extract_dates( line )[1]
@classmethod
@deprecated( 'extract_dates' )
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
"""
return cls.extract_dates( line, True )[1]
class RedFamWorker( RedFam ):
"""
Handles working with redundance families stored in database
where discussion is finished
"""
def __init__( self, mysql_data ):
articlesList = []
for key in sorted( mysql_data.keys() ):
if 'article' in key and mysql_data[ key ]:
articlesList.append( mysql_data[ key ] )
super().__init__( articlesList, mysql_data[ 'beginning' ],
mysql_data[ 'ending' ], mysql_data[ 'red_page_id' ],
mysql_data[ 'status' ], mysql_data[ 'fam_hash' ],
mysql_data[ 'heading' ] )
@classmethod
def list_by_status( cls, status ):
"""
Lists red_fams stored in db by given status
"""
mysql = MysqlRedFam()
for fam in mysql.get_by_status( status ):
try:
print( cls( fam ) )
except RedFamHashError:
print(fam)
raise
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 = "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 )

151
lib/redpage.py Normal file
View File

@@ -0,0 +1,151 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
#
# redpage.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 a class for handling redundance discussion pages and archives
"""
import pywikibot # noqa
import mwparserfromhell as mwparser
import jogobot # noqa
from lib.mysqlred import MysqlRedPage
from lib.redfam import RedFamParser
class RedPage:
"""
Class for handling redundance discussion pages and archives
"""
def __init__( self, page, archive=False ):
"""
Generate a new RedPage object based on the given pywikibot page object
@param page page Pywikibot/MediaWiki page object for page
"""
# Safe the pywikibot page object
self.page = page
self._archive = archive
self.__handle_db( )
self.is_page_changed()
self._parsed = None
def __handle_db( self ):
"""
Handles opening of db connection
"""
# We need a connection to our mysqldb
self.__mysql = MysqlRedPage( self.page._pageid )
if not self.__mysql.data:
self.__mysql.add_page( self.page.title(), self.page._revid )
def is_page_changed( self ):
"""
Check wether the page was changed since last run
"""
if( self.__mysql.data != { 'page_id': self.page._pageid,
'rev_id': self.page._revid,
'page_title': self.page.title(),
'status': self.__mysql.data[ 'status' ] } ):
self._changed = True
else:
self._changed = False
def is_archive( self ):
"""
Detects wether current page is an archive of discussions
"""
if( self._archive or ( u"/Archiv" in self.page.title() ) or
( "{{Archiv}}" in self.page.text ) or
( "{{Archiv|" in self.page.text ) ):
return True
else:
return False
def is_parsing_needed( self ):
"""
Decides wether current RedPage needs to be parsed or not
"""
if( self._changed or self.__mysql.data[ 'status' ] == 0 ):
return True
else:
return False
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._parsed = True
self.__update_db()
def __update_db( self ):
"""
Updates the page meta data in mysql db
"""
if( self._parsed or not self._changed ):
status = 1
if( self.is_archive() ):
status = 2
else:
status = 0
self.__mysql.update_page( self.page._revid, self.page.title(), status )
@classmethod
def flush_db_cache( cls ):
"""
Calls flush method of Mysql Interface class
"""
MysqlRedPage.flush()