sqlalchemy working for parser
Needs some testing, presumably contains some bugs
This commit is contained in:
@@ -33,8 +33,8 @@ from pywikibot.bot import ExistingPageBot, NoRedirectPageBot
|
||||
|
||||
import jogobot
|
||||
|
||||
from lib import redpage
|
||||
from lib import redfam
|
||||
from lib.redpage import RedPage
|
||||
from lib.redfam import RedFamParser
|
||||
|
||||
|
||||
class DiscussionParserBot(
|
||||
@@ -127,7 +127,7 @@ class DiscussionParserBot(
|
||||
else:
|
||||
|
||||
# If successfully parsed all pages in cat, flush db write cache
|
||||
redpage.RedPage.flush_db_cache()
|
||||
RedPage.flush_db_cache()
|
||||
|
||||
def treat_page( self ):
|
||||
"""
|
||||
@@ -146,20 +146,23 @@ class DiscussionParserBot(
|
||||
return
|
||||
|
||||
# Initiate RedPage object
|
||||
red_page = redpage.RedPage( self.current_page )
|
||||
redpage = RedPage.session.query(RedPage).filter(RedPage.pageid == self.current_page.pageid ).one_or_none()
|
||||
|
||||
# Check whether parsing is needed
|
||||
if red_page.is_parsing_needed():
|
||||
if redpage:
|
||||
redpage.update( self.current_page )
|
||||
else:
|
||||
redpage = RedPage( self.current_page )
|
||||
|
||||
#~ # Check whether parsing is needed
|
||||
if redpage.is_parsing_needed():
|
||||
# Count families for failure analysis
|
||||
fam_counter = 0
|
||||
|
||||
# Iterate over returned generator with redfam sections
|
||||
for fam in red_page.parse():
|
||||
|
||||
for fam in redpage.parse():
|
||||
# Run RedFamParser on section text
|
||||
redfam.RedFamParser.parser( fam, red_page.page,
|
||||
red_page.is_archive() )
|
||||
RedFamParser.parser( fam, redpage,
|
||||
redpage.is_archive() )
|
||||
|
||||
fam_counter += 1
|
||||
|
||||
@@ -167,12 +170,13 @@ class DiscussionParserBot(
|
||||
# If successfully parsed whole page, flush
|
||||
# db write cache
|
||||
if( fam_counter ):
|
||||
redfam.RedFamParser.flush_db_cache()
|
||||
|
||||
RedFamParser.flush_db_cache()
|
||||
jogobot.output( "Page [[{reddisc}]] parsed".format(
|
||||
reddisc=red_page.page.title() ) )
|
||||
reddisc=redpage.page.title() ) )
|
||||
else:
|
||||
jogobot.output(
|
||||
"\03{red}" + "Page [[{reddisc}]], ".format(
|
||||
reddisc=red_page.page.title() ) +
|
||||
reddisc=redpage.page.title() ) +
|
||||
"containing no redfam, parsed!",
|
||||
"WARNING" )
|
||||
|
||||
795
lib/mysqlred.py
795
lib/mysqlred.py
@@ -39,336 +39,553 @@ from pywikibot import config
|
||||
import jogobot
|
||||
|
||||
|
||||
class MysqlRed:
|
||||
"""
|
||||
Basic interface class, containing opening of connection
|
||||
from sqlalchemy import create_engine
|
||||
from sqlalchemy.engine.url import URL
|
||||
url = URL( "mysql+oursql",
|
||||
username=config.db_username,
|
||||
password=config.db_password,
|
||||
host=config.db_hostname,
|
||||
port=config.db_port,
|
||||
database=config.db_username + jogobot.config['db_suffix'] )
|
||||
engine = create_engine(url, echo=True)
|
||||
|
||||
Specific querys should be defined in descendant classes per data type
|
||||
|
||||
from sqlalchemy.ext.declarative import (
|
||||
declarative_base, declared_attr, has_inherited_table )
|
||||
Base = declarative_base()
|
||||
|
||||
from sqlalchemy import Column, Integer, String, Text, DateTime, ForeignKey
|
||||
|
||||
from sqlalchemy.orm import sessionmaker, relationship, composite
|
||||
from sqlalchemy.ext.mutable import MutableComposite, MutableSet
|
||||
from sqlalchemy.orm.collections import attribute_mapped_collection
|
||||
import sqlalchemy.types as types
|
||||
|
||||
|
||||
Session = sessionmaker(bind=engine)
|
||||
session = Session()
|
||||
|
||||
family = "dewpbeta"
|
||||
|
||||
class Mysql(object):
|
||||
session = session
|
||||
@declared_attr
|
||||
def _tableprefix(cls):
|
||||
return family + "_"
|
||||
@declared_attr
|
||||
def _tablesuffix(cls):
|
||||
return "s"
|
||||
@declared_attr
|
||||
def __tablename__(cls):
|
||||
if has_inherited_table(cls):
|
||||
return None
|
||||
prefix = family + "_"
|
||||
name = cls.__name__[len("Mysql"):].lower()
|
||||
suffix = "s"
|
||||
return cls._tableprefix + name + cls._tablesuffix
|
||||
def changedp(self):
|
||||
return self in self.session.dirty
|
||||
|
||||
class ColumnList( list, MutableComposite ):
|
||||
"""
|
||||
Combines multiple Colums into a list like object
|
||||
"""
|
||||
|
||||
# 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']
|
||||
db_table_prefix = False
|
||||
|
||||
# Class variables for storing cached querys
|
||||
_cached_update_data = []
|
||||
_update_query = ''
|
||||
_cached_insert_data = {}
|
||||
_insert_query = ''
|
||||
|
||||
def __init__( self ):
|
||||
def __init__( self, *columns ):
|
||||
"""
|
||||
Opens a connection to MySQL-DB
|
||||
|
||||
@returns mysql-stream MySQL Connection
|
||||
Wrapper to the list constructor deciding whether we have initialization
|
||||
with individual params per article or with an iterable.
|
||||
"""
|
||||
|
||||
# Needs to be generated after Parsing of Args (not at import time)
|
||||
if not type(self).db_table_prefix:
|
||||
type(self).db_table_prefix = \
|
||||
pywikibot.Site().family.dbName(pywikibot.Site().code)
|
||||
|
||||
# Now we can setup prepared queries
|
||||
self._prepare_queries()
|
||||
|
||||
# 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()
|
||||
|
||||
def _prepare_queries( self ):
|
||||
"""
|
||||
Used to replace placeholders in prepared queries
|
||||
"""
|
||||
type(self)._update_query = type(self)._update_query.format(
|
||||
prefix=type(self).db_table_prefix)
|
||||
type(self)._insert_query = type(self)._insert_query.format(
|
||||
prefix=type(self).db_table_prefix)
|
||||
|
||||
@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
|
||||
# '{prefix}' will be replaced during super().__init__()
|
||||
_cached_update_data = []
|
||||
_update_query = 'UPDATE `{prefix}_redpages` \
|
||||
SET `pagetitle` = ?, `revid` = ?, `status`= ? WHERE `pageid` = ?;'
|
||||
|
||||
_cached_insert_data = {}
|
||||
_insert_query = 'INSERT INTO `{prefix}_redpages` \
|
||||
( pageid, pagetitle, revid, status ) VALUES ( ?, ?, ?, ? );'
|
||||
|
||||
def __init__( self, pageid ):
|
||||
"""
|
||||
Creates a new instance, runs __init__ of parent class
|
||||
"""
|
||||
|
||||
super().__init__( )
|
||||
|
||||
self.__pageid = int( pageid )
|
||||
|
||||
self.data = self.get_page()
|
||||
|
||||
def __del__( self ):
|
||||
"""
|
||||
Needed to prevent descendant classes of MYSQL_RED from deleting
|
||||
connection to db
|
||||
"""
|
||||
pass
|
||||
|
||||
def get_page( self ):
|
||||
"""
|
||||
Retrieves a red page row from MySQL-Database for given page_id
|
||||
|
||||
@param int pageid 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 `{prefix}_redpages` WHERE `pageid` = ?;'.format(
|
||||
prefix=type(self).db_table_prefix), ( self.__pageid, ) )
|
||||
|
||||
res = cursor.fetchone()
|
||||
|
||||
if res:
|
||||
return res
|
||||
# Individual params per article (from db), first one is a str
|
||||
if isinstance( columns[0], str ) or \
|
||||
isinstance( columns[0], MutableSet ) or columns[0] is None:
|
||||
super().__init__( columns )
|
||||
# Iterable articles list
|
||||
else:
|
||||
return False
|
||||
super().__init__( columns[0] )
|
||||
|
||||
def add_page( self, pagetitle, revid, status=0 ):
|
||||
def __setitem__(self, key, value):
|
||||
"""
|
||||
Inserts a red page row in MySQL-Database for given pageid
|
||||
|
||||
@param int revid MediaWiki current revid
|
||||
@param str pagetitle MediaWiki new pagetitle
|
||||
@param int status Page parsing status
|
||||
The MutableComposite class needs to be noticed about changes in our
|
||||
component. So we tweak the setitem process.
|
||||
"""
|
||||
|
||||
insert_data = { self.__pageid: ( self.__pageid, pagetitle,
|
||||
revid, status ) }
|
||||
# set the item
|
||||
super().__setitem__( key, value)
|
||||
|
||||
type( self )._cached_insert_data.update( insert_data )
|
||||
# alert all parents to the change
|
||||
self.changed()
|
||||
|
||||
# Manualy construct self.data dict
|
||||
self.data = { 'pageid': self.__pageid, 'revid': revid,
|
||||
'pagetitle': pagetitle, 'status': status }
|
||||
|
||||
def update_page( self, revid=None, pagetitle=None, status=0 ):
|
||||
def __composite_values__(self):
|
||||
"""
|
||||
Updates the red page row in MySQL-Database for given page_id
|
||||
|
||||
@param int revid MediaWiki current rev_id
|
||||
@param str pagetitle MediaWiki new page_title
|
||||
@param int status Page parsing status
|
||||
The Composite method needs to have this method to get the items for db.
|
||||
"""
|
||||
return self
|
||||
|
||||
if not pagetitle:
|
||||
pagetitle = self.data[ 'pagetitle' ]
|
||||
if not revid:
|
||||
revid = self.data[ 'revid' ]
|
||||
class Status( types.TypeDecorator ):
|
||||
|
||||
type( self )._cached_update_data.append( ( pagetitle, revid,
|
||||
status, self.__pageid ) )
|
||||
impl = types.String
|
||||
|
||||
|
||||
class MysqlRedFam( MysqlRed ):
|
||||
"""
|
||||
MySQL-db Interface for handling querys for RedFams
|
||||
"""
|
||||
|
||||
# Class variables for storing cached querys
|
||||
_cached_update_data = []
|
||||
_update_query = 'UPDATE `{prefix}_redfams` \
|
||||
SET `redpageid` = ?, `heading` = ?, `beginning` = ?, `ending` = ?, \
|
||||
`status`= ? WHERE `famhash` = ?;'
|
||||
|
||||
_cached_insert_data = {}
|
||||
_insert_query = 'INSERT INTO `{prefix}_redfams` \
|
||||
( famhash, redpageid, beginning, ending, status, heading, \
|
||||
article0, article1, article2, article3, article4, article5, article6, \
|
||||
article7 ) VALUES ( ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ? );'
|
||||
|
||||
def __init__( self, famhash=None ):
|
||||
def process_bind_param(self, value, dialect):
|
||||
"""
|
||||
Creates a new instance, runs __init__ of parent class
|
||||
Returns status as commaseparated string (to save in DB)
|
||||
|
||||
@returns Raw status string
|
||||
@rtype str
|
||||
"""
|
||||
if isinstance(value, MutableSet):
|
||||
return ",".join( value )
|
||||
elif isinstance(value, String ) or value is None:
|
||||
return value
|
||||
else:
|
||||
raise ProgrammingError
|
||||
|
||||
self.__famhash = famhash
|
||||
|
||||
super().__init__( )
|
||||
|
||||
def __del__( self ):
|
||||
def process_result_value(self, value, dialect):
|
||||
"""
|
||||
Needed to prevent descendant classes of MYSQL_RED from deleting
|
||||
connection to db
|
||||
Sets status based on comma separated list
|
||||
|
||||
@param raw_status Commaseparated string of stati (from DB)
|
||||
@type raw_status str
|
||||
"""
|
||||
pass
|
||||
if value:
|
||||
return MutableSet( value.strip().split(","))
|
||||
else:
|
||||
return MutableSet([])
|
||||
|
||||
def get_fam( self, famhash ):
|
||||
def copy(self, **kw):
|
||||
return Status(self.impl.length)
|
||||
|
||||
|
||||
|
||||
class MysqlRedFam( Mysql, Base ):
|
||||
|
||||
famhash = Column( String(64), primary_key=True, unique=True )
|
||||
|
||||
__article0 = Column('article0', String(255), nullable=False )
|
||||
__article1 = Column('article1', String(255), nullable=False )
|
||||
__article2 = Column('article2', String(255), nullable=True )
|
||||
__article3 = Column('article3', String(255), nullable=True )
|
||||
__article4 = Column('article4', String(255), nullable=True )
|
||||
__article5 = Column('article5', String(255), nullable=True )
|
||||
__article6 = Column('article6', String(255), nullable=True )
|
||||
__article7 = Column('article7', String(255), nullable=True )
|
||||
__articlesList = composite(
|
||||
ColumnList, __article0, __article1, __article2, __article3,
|
||||
__article4, __article5, __article6, __article7 )
|
||||
|
||||
heading = Column( Text, nullable=False )
|
||||
redpageid = Column(
|
||||
Integer, ForeignKey( "dewpbeta_redpages.pageid" ), nullable=False )
|
||||
beginning = Column( DateTime, nullable=False )
|
||||
ending = Column( DateTime, nullable=True )
|
||||
__status = Column( 'status', MutableSet.as_mutable(Status(255)), nullable=True )
|
||||
|
||||
__article0_status = Column(
|
||||
'article0_status', MutableSet.as_mutable(Status(64)), nullable=True )
|
||||
__article1_status = Column(
|
||||
'article1_status', MutableSet.as_mutable(Status(64)), nullable=True )
|
||||
__article2_status = Column(
|
||||
'article2_status', MutableSet.as_mutable(Status(64)), nullable=True )
|
||||
__article3_status = Column(
|
||||
'article3_status', MutableSet.as_mutable(Status(64)), nullable=True )
|
||||
__article4_status = Column(
|
||||
'article4_status', MutableSet.as_mutable(Status(64)), nullable=True )
|
||||
__article5_status = Column(
|
||||
'article5_status', MutableSet.as_mutable(Status(64)), nullable=True )
|
||||
__article6_status = Column(
|
||||
'article6_status', MutableSet.as_mutable(Status(64)), nullable=True )
|
||||
__article7_status = Column(
|
||||
'article7_status', MutableSet.as_mutable(Status(64)), nullable=True )
|
||||
__articlesStatus = composite(
|
||||
ColumnList, __article0_status, __article1_status, __article2_status,
|
||||
__article3_status, __article4_status, __article5_status,
|
||||
__article6_status, __article7_status )
|
||||
|
||||
redpage = relationship( "RedPage", back_populates="redfams" )
|
||||
|
||||
@property
|
||||
def articlesList(self):
|
||||
"""
|
||||
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
|
||||
List of articles belonging to the redfam
|
||||
"""
|
||||
self.__famhash = famhash
|
||||
return self.__articlesList
|
||||
|
||||
cursor = type( self ).connection.cursor( mysqldb.DictCursor )
|
||||
@articlesList.setter
|
||||
def articlesList(self, articlesList):
|
||||
# Make sure to always have full length for complete overwrites
|
||||
while( len(articlesList) < 8 ):
|
||||
articlesList.append(None)
|
||||
self.__articlesList = ColumnList(articlesList)
|
||||
|
||||
cursor.execute(
|
||||
'SELECT * FROM `{prefix}_redfams` WHERE `famhash` = ?;'.
|
||||
format( prefix=type(self).db_table_prefix), ( famhash, ) )
|
||||
|
||||
self.data = cursor.fetchone()
|
||||
|
||||
def add_fam( self, articlesList, heading, redpageid,
|
||||
beginning, ending=None, status=0 ):
|
||||
|
||||
data = [ self.__famhash, redpageid, 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.__famhash: data }
|
||||
type( self )._cached_insert_data.update( insert_data )
|
||||
|
||||
# Manualy construct self.data dict
|
||||
data_keys = ( 'famhash', 'redpageid', 'beginning', 'ending',
|
||||
'status', 'heading', 'article0', 'article1', 'article2',
|
||||
'article3', 'article4', 'article5', 'article6',
|
||||
'article7' )
|
||||
self.data = dict( zip( data_keys, data ) )
|
||||
|
||||
def update_fam( self, redpageid, heading, beginning, ending, status ):
|
||||
@property
|
||||
def status( self ):
|
||||
"""
|
||||
Updates the red fam row in MySQL-Database for given fam_hash
|
||||
|
||||
@param int redpageid MediaWiki page_id
|
||||
@param datetime beginning Timestamp of beginning
|
||||
qparam datetime ending Timestamp of ending of
|
||||
@param int status red_fam status
|
||||
Current fam status
|
||||
"""
|
||||
return self.__status
|
||||
|
||||
type( self )._cached_update_data.append( ( redpageid, heading,
|
||||
beginning, ending, status,
|
||||
self.__famhash ) )
|
||||
@status.setter
|
||||
def status( self, status ):
|
||||
if status:
|
||||
self.__status = MutableSet( status )
|
||||
else:
|
||||
self.__status = MutableSet()
|
||||
|
||||
def get_by_status( self, status ):
|
||||
@property
|
||||
def articlesStatus(self):
|
||||
"""
|
||||
Generator witch fetches redFams with given status from DB
|
||||
List of status strings/sets for the articles of the redfam
|
||||
"""
|
||||
return self.__articlesStatus
|
||||
|
||||
cursor = type( self ).connection.cursor( mysqldb.DictCursor )
|
||||
@articlesStatus.setter
|
||||
def articlesStatus(self, articlesStatus):
|
||||
self.__articlesStatus = ColumnList(articlesStatus)
|
||||
|
||||
cursor.execute(
|
||||
'SELECT * FROM `{prefix}_redfams` WHERE `status` = LIKE %?%;'.
|
||||
format( prefix=type( self ).db_table_prefix), ( status, ) )
|
||||
class MysqlRedPage( Mysql, Base ):
|
||||
pageid = Column( Integer, unique=True, primary_key=True )
|
||||
revid = Column( Integer, unique=True, nullable=False )
|
||||
pagetitle = Column( String(255), nullable=False )
|
||||
status = Column( MutableSet.as_mutable(Status(255)), nullable=True )
|
||||
|
||||
while True:
|
||||
res = cursor.fetchmany( 1000 )
|
||||
if not res:
|
||||
break
|
||||
for row in res:
|
||||
yield row
|
||||
redfams = relationship(
|
||||
"MysqlRedFam", order_by=MysqlRedFam.famhash, back_populates="redpage",
|
||||
collection_class=attribute_mapped_collection("famhash"))
|
||||
|
||||
def get_by_status_and_ending( self, status, ending ):
|
||||
"""
|
||||
Generator witch fetches redFams with given status from DB
|
||||
"""
|
||||
|
||||
cursor = type( self ).connection.cursor( mysqldb.DictCursor )
|
||||
Base.metadata.create_all(engine)
|
||||
|
||||
cursor.execute( (
|
||||
'SELECT * ' +
|
||||
'FROM `{prefix}_redfams` `F` ' +
|
||||
'INNER JOIN `{prefix}_redpages` `P` ' +
|
||||
'ON `F`.`status` = ? ' +
|
||||
'AND `F`.`ending` >= ? ' +
|
||||
'AND `F`.`redpageid` = `P`.`pageid`;').format(
|
||||
prefix=type( self ).db_table_prefix),
|
||||
( status, ending ) )
|
||||
#~ class MysqlRed:
|
||||
#~ """
|
||||
#~ Basic interface class, containing opening of connection
|
||||
|
||||
while True:
|
||||
res = cursor.fetchmany( 1000 )
|
||||
if not res:
|
||||
break
|
||||
for row in res:
|
||||
yield row
|
||||
#~ 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']
|
||||
#~ db_table_prefix = False
|
||||
|
||||
#~ # 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
|
||||
#~ """
|
||||
|
||||
#~ # Needs to be generated after Parsing of Args (not at import time)
|
||||
#~ if not type(self).db_table_prefix:
|
||||
#~ type(self).db_table_prefix = \
|
||||
#~ pywikibot.Site().family.dbName(pywikibot.Site().code)
|
||||
|
||||
#~ # Now we can setup prepared queries
|
||||
#~ self._prepare_queries()
|
||||
|
||||
#~ # 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()
|
||||
|
||||
#~ def _prepare_queries( self ):
|
||||
#~ """
|
||||
#~ Used to replace placeholders in prepared queries
|
||||
#~ """
|
||||
#~ type(self)._update_query = type(self)._update_query.format(
|
||||
#~ prefix=type(self).db_table_prefix)
|
||||
#~ type(self)._insert_query = type(self)._insert_query.format(
|
||||
#~ prefix=type(self).db_table_prefix)
|
||||
|
||||
#~ @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
|
||||
#~ # '{prefix}' will be replaced during super().__init__()
|
||||
#~ _cached_update_data = []
|
||||
#~ _update_query = 'UPDATE `{prefix}_redpages` \
|
||||
#~ SET `pagetitle` = ?, `revid` = ?, `status`= ? WHERE `pageid` = ?;'
|
||||
|
||||
#~ _cached_insert_data = {}
|
||||
#~ _insert_query = 'INSERT INTO `{prefix}_redpages` \
|
||||
#~ ( pageid, pagetitle, revid, status ) VALUES ( ?, ?, ?, ? );'
|
||||
|
||||
#~ def __init__( self, pageid ):
|
||||
#~ """
|
||||
#~ Creates a new instance, runs __init__ of parent class
|
||||
#~ """
|
||||
|
||||
#~ super().__init__( )
|
||||
|
||||
#~ self.__pageid = int( pageid )
|
||||
|
||||
#~ self.data = self.get_page()
|
||||
|
||||
#~ def __del__( self ):
|
||||
#~ """
|
||||
#~ Needed to prevent descendant classes of MYSQL_RED from deleting
|
||||
#~ connection to db
|
||||
#~ """
|
||||
#~ pass
|
||||
|
||||
#~ def get_page( self ):
|
||||
#~ """
|
||||
#~ Retrieves a red page row from MySQL-Database for given page_id
|
||||
|
||||
#~ @param int pageid 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 `{prefix}_redpages` WHERE `pageid` = ?;'.format(
|
||||
#~ prefix=type(self).db_table_prefix), ( self.__pageid, ) )
|
||||
|
||||
#~ res = cursor.fetchone()
|
||||
|
||||
#~ if res:
|
||||
#~ return res
|
||||
#~ else:
|
||||
#~ return False
|
||||
|
||||
#~ def add_page( self, pagetitle, revid, status=0 ):
|
||||
#~ """
|
||||
#~ Inserts a red page row in MySQL-Database for given pageid
|
||||
|
||||
#~ @param int revid MediaWiki current revid
|
||||
#~ @param str pagetitle MediaWiki new pagetitle
|
||||
#~ @param int status Page parsing status
|
||||
#~ """
|
||||
|
||||
#~ insert_data = { self.__pageid: ( self.__pageid, pagetitle,
|
||||
#~ revid, status ) }
|
||||
|
||||
#~ type( self )._cached_insert_data.update( insert_data )
|
||||
|
||||
#~ # Manualy construct self.data dict
|
||||
#~ self.data = { 'pageid': self.__pageid, 'revid': revid,
|
||||
#~ 'pagetitle': pagetitle, 'status': status }
|
||||
|
||||
#~ def update_page( self, revid=None, pagetitle=None, status=0 ):
|
||||
#~ """
|
||||
#~ Updates the red page row in MySQL-Database for given page_id
|
||||
|
||||
#~ @param int revid MediaWiki current rev_id
|
||||
#~ @param str pagetitle MediaWiki new page_title
|
||||
#~ @param int status Page parsing status
|
||||
#~ """
|
||||
|
||||
#~ if not pagetitle:
|
||||
#~ pagetitle = self.data[ 'pagetitle' ]
|
||||
#~ if not revid:
|
||||
#~ revid = self.data[ 'revid' ]
|
||||
|
||||
#~ type( self )._cached_update_data.append( ( pagetitle, revid,
|
||||
#~ status, self.__pageid ) )
|
||||
|
||||
|
||||
#~ class MysqlRedFam( MysqlRed ):
|
||||
#~ """
|
||||
#~ MySQL-db Interface for handling querys for RedFams
|
||||
#~ """
|
||||
|
||||
#~ # Class variables for storing cached querys
|
||||
#~ _cached_update_data = []
|
||||
#~ _update_query = 'UPDATE `{prefix}_redfams` \
|
||||
#~ SET `redpageid` = ?, `heading` = ?, `beginning` = ?, `ending` = ?, \
|
||||
#~ `status`= ? WHERE `famhash` = ?;'
|
||||
|
||||
#~ _cached_insert_data = {}
|
||||
#~ _insert_query = 'INSERT INTO `{prefix}_redfams` \
|
||||
#~ ( famhash, redpageid, beginning, ending, status, heading, \
|
||||
#~ article0, article1, article2, article3, article4, article5, article6, \
|
||||
#~ article7 ) VALUES ( ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ? );'
|
||||
|
||||
#~ def __init__( self, famhash=None ):
|
||||
#~ """
|
||||
#~ Creates a new instance, runs __init__ of parent class
|
||||
#~ """
|
||||
|
||||
#~ self.__famhash = famhash
|
||||
|
||||
#~ super().__init__( )
|
||||
|
||||
#~ def __del__( self ):
|
||||
#~ """
|
||||
#~ Needed to prevent descendant classes of MYSQL_RED from deleting
|
||||
#~ connection to db
|
||||
#~ """
|
||||
#~ pass
|
||||
|
||||
#~ def get_fam( self, famhash ):
|
||||
#~ """
|
||||
#~ 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.__famhash = famhash
|
||||
|
||||
#~ cursor = type( self ).connection.cursor( mysqldb.DictCursor )
|
||||
|
||||
#~ cursor.execute(
|
||||
#~ 'SELECT * FROM `{prefix}_redfams` WHERE `famhash` = ?;'.
|
||||
#~ format( prefix=type(self).db_table_prefix), ( famhash, ) )
|
||||
|
||||
#~ self.data = cursor.fetchone()
|
||||
|
||||
#~ def add_fam( self, articlesList, heading, redpageid,
|
||||
#~ beginning, ending=None, status=0 ):
|
||||
|
||||
#~ data = [ self.__famhash, redpageid, 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.__famhash: data }
|
||||
#~ type( self )._cached_insert_data.update( insert_data )
|
||||
|
||||
#~ # Manualy construct self.data dict
|
||||
#~ data_keys = ( 'famhash', 'redpageid', 'beginning', 'ending',
|
||||
#~ 'status', 'heading', 'article0', 'article1', 'article2',
|
||||
#~ 'article3', 'article4', 'article5', 'article6',
|
||||
#~ 'article7' )
|
||||
#~ self.data = dict( zip( data_keys, data ) )
|
||||
|
||||
#~ def update_fam( self, redpageid, heading, beginning, ending, status ):
|
||||
#~ """
|
||||
#~ Updates the red fam row in MySQL-Database for given fam_hash
|
||||
|
||||
#~ @param int redpageid 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( ( redpageid, heading,
|
||||
#~ beginning, ending, status,
|
||||
#~ self.__famhash ) )
|
||||
|
||||
#~ 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 `{prefix}_redfams` WHERE `status` = LIKE %?%;'.
|
||||
#~ format( prefix=type( self ).db_table_prefix), ( status, ) )
|
||||
|
||||
#~ while True:
|
||||
#~ res = cursor.fetchmany( 1000 )
|
||||
#~ if not res:
|
||||
#~ break
|
||||
#~ for row in res:
|
||||
#~ yield row
|
||||
|
||||
#~ def get_by_status_and_ending( self, status, ending ):
|
||||
#~ """
|
||||
#~ Generator witch fetches redFams with given status from DB
|
||||
#~ """
|
||||
|
||||
#~ cursor = type( self ).connection.cursor( mysqldb.DictCursor )
|
||||
|
||||
#~ cursor.execute( (
|
||||
#~ 'SELECT * ' +
|
||||
#~ 'FROM `{prefix}_redfams` `F` ' +
|
||||
#~ 'INNER JOIN `{prefix}_redpages` `P` ' +
|
||||
#~ 'ON `F`.`status` = ? ' +
|
||||
#~ 'AND `F`.`ending` >= ? ' +
|
||||
#~ 'AND `F`.`redpageid` = `P`.`pageid`;').format(
|
||||
#~ prefix=type( self ).db_table_prefix),
|
||||
#~ ( status, ending ) )
|
||||
|
||||
#~ while True:
|
||||
#~ res = cursor.fetchmany( 1000 )
|
||||
#~ if not res:
|
||||
#~ break
|
||||
#~ for row in res:
|
||||
#~ yield row
|
||||
|
||||
|
||||
class MysqlRedError(Exception):
|
||||
|
||||
360
lib/redfam.py
360
lib/redfam.py
@@ -3,7 +3,7 @@
|
||||
#
|
||||
# redfam.py
|
||||
#
|
||||
# Copyright 2015 GOLDERWEB – Jonathan Golder <jonathan@golderweb.de>
|
||||
# Copyright 2017 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
|
||||
@@ -35,16 +35,17 @@ import pywikibot # noqa
|
||||
from pywikibot.tools import deprecated # noqa
|
||||
|
||||
import jogobot
|
||||
from lib.mysqlred import MysqlRedFam
|
||||
#~ from lib.mysqlred import Column, Integer, String, Text, DateTime, ForeignKey, ColumnList, Status
|
||||
from lib.mysqlred import MysqlRedFam, MutableSet, ColumnList #, Mysql, Base, relationship, composite,
|
||||
|
||||
|
||||
class RedFam:
|
||||
class RedFam( MysqlRedFam ):
|
||||
"""
|
||||
Basic class for RedFams, containing the basic data structure
|
||||
"""
|
||||
|
||||
def __init__( self, articlesList, beginning, ending=None, redpageid=None,
|
||||
status=None, famhash=None, heading=None ):
|
||||
status=MutableSet(), famhash=None, heading=None ):
|
||||
"""
|
||||
Generates a new RedFam object
|
||||
|
||||
@@ -61,21 +62,32 @@ class RedFam:
|
||||
self.site = pywikibot.Site()
|
||||
|
||||
# Database interface
|
||||
self._mysql = MysqlRedFam( famhash )
|
||||
#self._mysql = MysqlRedFam( famhash )
|
||||
|
||||
# Initial attribute values
|
||||
self._articlesList = articlesList
|
||||
self._beginning = beginning
|
||||
self._ending = ending
|
||||
self._redpageid = redpageid
|
||||
self._status = set()
|
||||
self._status = self._parse_status(status)
|
||||
self._famhash = famhash
|
||||
self._heading = heading
|
||||
#~ self.articlesList = articlesList
|
||||
#~ self.beginning = beginning
|
||||
#~ self.ending = ending
|
||||
#~ self.redpageid = redpageid
|
||||
#~ # self._status = set()
|
||||
#~ # self._status = self._parse_status(status)
|
||||
#~ self.famhash = famhash
|
||||
#~ self.heading = heading
|
||||
#self.status = status
|
||||
|
||||
# Calculates the sha1 hash over self._articlesList to
|
||||
# rediscover known redundance families
|
||||
self.calc_famhash()
|
||||
#articlesStatus = ColumnList([ MutableSet() for x in range(0,8) ])
|
||||
|
||||
#~ # Calculates the sha1 hash over self._articlesList to
|
||||
#~ # rediscover known redundance families
|
||||
#~ self.calc_famhash()
|
||||
|
||||
#~ if not status:
|
||||
#~ status = MutableSet()
|
||||
|
||||
super().__init__( articlesList=articlesList, beginning=beginning, ending=ending, redpageid=redpageid,
|
||||
famhash=famhash, heading=heading, status=status, articlesStatus=None )
|
||||
|
||||
#super().__init__()
|
||||
|
||||
def __repr__( self ):
|
||||
"""
|
||||
@@ -85,64 +97,75 @@ class RedFam:
|
||||
"""
|
||||
|
||||
__repr = "RedFam( " + \
|
||||
"articlesList=" + repr( self._articlesList ) + \
|
||||
", heading=" + repr( self._heading ) + \
|
||||
", beginning=" + repr( self._beginning ) + \
|
||||
", ending=" + repr( self._ending ) + \
|
||||
", red_page_id=" + repr( self._redpageid ) + \
|
||||
", status=" + repr( self._status ) + \
|
||||
", fam_hash=" + repr( self._famhash ) + \
|
||||
"articlesList=" + repr( self.articlesList ) + \
|
||||
", heading=" + repr( self.heading ) + \
|
||||
", beginning=" + repr( self.beginning ) + \
|
||||
", ending=" + repr( self.ending ) + \
|
||||
", red_page_id=" + repr( self.redpageid ) + \
|
||||
", status=" + repr( self.status ) + \
|
||||
", fam_hash=" + repr( self.famhash ) + \
|
||||
" )"
|
||||
|
||||
return __repr
|
||||
|
||||
def calc_famhash( self ):
|
||||
@classmethod
|
||||
def calc_famhash(cls, articlesList ):
|
||||
|
||||
h = hashlib.sha1()
|
||||
# Since articlesList attr of RedFam will have always 8 Members we
|
||||
# need to fill up smaller lists (longers will be cropped below).
|
||||
while len( articlesList) < 8:
|
||||
articlesList.append(None)
|
||||
|
||||
h.update( str( articlesList[:8] ).encode('utf-8') )
|
||||
|
||||
return h.hexdigest()
|
||||
|
||||
def c_famhash( 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
|
||||
"""
|
||||
print( type( self ) )
|
||||
|
||||
h = hashlib.sha1()
|
||||
h.update( str( self._articlesList[:8] ).encode('utf-8') )
|
||||
|
||||
if self._famhash and h.hexdigest() != self._famhash:
|
||||
raise RedFamHashError( self._famhash, h.hexdigest() )
|
||||
|
||||
elif self._famhash:
|
||||
if self.famhash and type(self).calc_famhash(self.articlesList) != self.famhash:
|
||||
raise RedFamHashError( self.famhash, h.hexdigest() )
|
||||
elif self.famhash:
|
||||
return
|
||||
else:
|
||||
self._famhash = h.hexdigest()
|
||||
self.famhash = type(self).calc_famhash(self.articlesList)
|
||||
|
||||
def changed( self ):
|
||||
"""
|
||||
Checks wether anything has changed and maybe triggers db update
|
||||
"""
|
||||
#~ def changed( self ):
|
||||
#~ """
|
||||
#~ Checks wether anything has changed and maybe triggers db update
|
||||
#~ """
|
||||
|
||||
# On archived redfams do not delete possibly existing ending
|
||||
if( not self._ending and "archived" in self._status and
|
||||
self._mysql.data[ 'ending' ] ):
|
||||
#~ # On archived redfams do not delete possibly existing ending
|
||||
#~ if( not self.ending and "archived" in self._status and
|
||||
#~ self._mysql.data[ 'ending' ] ):
|
||||
|
||||
self._ending = self._mysql.data[ 'ending' ]
|
||||
#~ self._ending = self._mysql.data[ 'ending' ]
|
||||
|
||||
# Since status change means something has changed, update database
|
||||
if( self._raw_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[ 'redpageid' ] or
|
||||
self._heading != self._mysql.data[ 'heading' ]):
|
||||
#~ # Since status change means something has changed, update database
|
||||
#~ if( self._raw_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[ 'redpageid' ] or
|
||||
#~ self._heading != self._mysql.data[ 'heading' ]):
|
||||
|
||||
self._mysql.update_fam( self._redpageid, self._heading,
|
||||
self._beginning, self._ending,
|
||||
self._raw_status() )
|
||||
#~ self._mysql.update_fam( self._redpageid, self._heading,
|
||||
#~ self._beginning, self._ending,
|
||||
#~ self._raw_status() )
|
||||
|
||||
@classmethod
|
||||
def flush_db_cache( cls ):
|
||||
"""
|
||||
Calls flush method of Mysql Interface class
|
||||
"""
|
||||
MysqlRedFam.flush()
|
||||
cls.session.commit()
|
||||
#~ MysqlRedFam.flush()
|
||||
|
||||
def add_status(self, status):
|
||||
"""
|
||||
@@ -151,7 +174,7 @@ class RedFam:
|
||||
@param status Statusstring to add
|
||||
@type status str
|
||||
"""
|
||||
self._status.add(status)
|
||||
self.status.add(status)
|
||||
|
||||
def remove_status(self, status, weak=True):
|
||||
"""
|
||||
@@ -164,9 +187,9 @@ class RedFam:
|
||||
@type bool
|
||||
"""
|
||||
if weak:
|
||||
self._status.discard(status)
|
||||
self.status.discard(status)
|
||||
else:
|
||||
self._status.remove(status)
|
||||
self.status.remove(status)
|
||||
|
||||
def has_status(self, status):
|
||||
"""
|
||||
@@ -176,28 +199,28 @@ class RedFam:
|
||||
@type status str
|
||||
@returns True if status is present else False
|
||||
"""
|
||||
if status in self._status:
|
||||
if status in self.status:
|
||||
return True
|
||||
else:
|
||||
return False
|
||||
|
||||
def _parse_status(self, raw_status ):
|
||||
"""
|
||||
Sets status based on comma separated list
|
||||
#~ def _parse_status(self, raw_status ):
|
||||
#~ """
|
||||
#~ Sets status based on comma separated list
|
||||
|
||||
@param raw_status Commaseparated string of stati (from DB)
|
||||
@type raw_status str
|
||||
"""
|
||||
self._status = set( raw_status.strip().split(","))
|
||||
#~ @param raw_status Commaseparated string of stati (from DB)
|
||||
#~ @type raw_status str
|
||||
#~ """
|
||||
#~ self._status = set( raw_status.strip().split(","))
|
||||
|
||||
def _raw_status( self ):
|
||||
"""
|
||||
Returns status as commaseparated string (to save in DB)
|
||||
#~ def _raw_status( self ):
|
||||
#~ """
|
||||
#~ Returns status as commaseparated string (to save in DB)
|
||||
|
||||
@returns Raw status string
|
||||
@rtype str
|
||||
"""
|
||||
return ",".join( self._status )
|
||||
#~ @returns Raw status string
|
||||
#~ @rtype str
|
||||
#~ """
|
||||
#~ return ",".join( self._status )
|
||||
|
||||
def article_add_status(self, status, index=None, title=None ):
|
||||
"""
|
||||
@@ -331,7 +354,7 @@ class RedFamParser( RedFam ):
|
||||
wurde gewünscht von:"
|
||||
__done_notice2 = "{{Erledigt|"
|
||||
|
||||
def __init__( self, heading, redpage, redpagearchive,
|
||||
def __init__( self, articlesList, heading, redpage, redpagearchive,
|
||||
beginning, ending=None ):
|
||||
"""
|
||||
Creates a RedFam object based on data collected while parsing red_pages
|
||||
@@ -346,57 +369,111 @@ class RedFamParser( RedFam ):
|
||||
str strptime parseable string
|
||||
"""
|
||||
|
||||
# Set object attributes:
|
||||
self._redpageid = redpage._pageid
|
||||
self._redpagearchive = redpagearchive
|
||||
self._famhash = 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 = set()
|
||||
|
||||
# Parse the provided heading of redundance section
|
||||
# to set self._articlesList
|
||||
self.heading_parser( heading )
|
||||
#~ self.heading = str(heading)
|
||||
#~ self.articlesList = articlesList
|
||||
|
||||
#~ # 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_famhash()
|
||||
|
||||
#~ 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]
|
||||
|
||||
# Calculates the sha1 hash over self._articlesList to
|
||||
# rediscover known redundance families
|
||||
famhash = type(self).calc_famhash(articlesList)
|
||||
|
||||
self.calc_famhash()
|
||||
#~ obj = self.session.query(RedFamParser).filter(RedFamParser.famhash == self.famhash ).one_or_none()
|
||||
#~ if obj:
|
||||
#~ self = obj
|
||||
|
||||
# Open database connection, ask for data if existing,
|
||||
# otherwise create entry
|
||||
self.__handle_db()
|
||||
|
||||
# Set object attributes:
|
||||
#~ self.redpageid = redpage._pageid
|
||||
self._redpagearchive = redpagearchive
|
||||
# self.famhash = 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 = MutableSet()
|
||||
|
||||
beginning = self.__datetime(beginning)
|
||||
if ending:
|
||||
ending = self.__datetime(ending)
|
||||
|
||||
|
||||
super().__init__( articlesList, beginning, ending=ending, redpageid=redpage._pageid,
|
||||
famhash=famhash, heading=heading )
|
||||
|
||||
# Check status changes
|
||||
self.status()
|
||||
self.check_status()
|
||||
|
||||
self.session.add(self)
|
||||
# Open database connection, ask for data if existing,
|
||||
# otherwise create entry
|
||||
# self.__handle_db()
|
||||
|
||||
|
||||
|
||||
# Triggers db update if anything changed
|
||||
self.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._famhash )
|
||||
|
||||
if not self._mysql.data:
|
||||
self._mysql.add_fam( self._articlesList, self._heading,
|
||||
self._redpageid, self._beginning,
|
||||
self._ending )
|
||||
#~ def __handle_db( self ):
|
||||
#~ """
|
||||
#~ Handles opening of db connection
|
||||
#~ """
|
||||
|
||||
def heading_parser( self, heading ):
|
||||
#~ # We need a connection to our mysqldb
|
||||
#~ self._mysql = MysqlRedFam( )
|
||||
#~ self._mysql.get_fam( self._famhash )
|
||||
|
||||
#~ if not self._mysql.data:
|
||||
#~ self._mysql.add_fam( self._articlesList, self._heading,
|
||||
#~ self._redpageid, self._beginning,
|
||||
#~ self._ending )
|
||||
|
||||
def update( self, articlesList, heading, redpage, redpagearchive,
|
||||
beginning, ending=None):
|
||||
|
||||
self.articlesList = articlesList;
|
||||
self.heading = heading;
|
||||
self.redpage = redpage;
|
||||
self.redpageid = redpage.pageid;
|
||||
|
||||
self.add_beginning( beginning )
|
||||
|
||||
if( ending ):
|
||||
self.add_ending( ending )
|
||||
|
||||
self._redpagearchive = redpagearchive
|
||||
|
||||
# Check status changes
|
||||
self.check_status()
|
||||
|
||||
@classmethod
|
||||
def heading_parser( cls, heading ):
|
||||
"""
|
||||
Parses given red_fam_heading string and saves articles list
|
||||
|
||||
@@ -404,34 +481,16 @@ class RedFamParser( RedFam ):
|
||||
@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 )
|
||||
heading = mwparser.parse( str( heading ) )
|
||||
|
||||
# Save destinations of wikilinks in headings
|
||||
self._articlesList = [ str( link.title ) for link
|
||||
return [ 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_famhash()
|
||||
|
||||
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 ):
|
||||
"""
|
||||
@@ -440,7 +499,7 @@ class RedFamParser( RedFam ):
|
||||
@param datetime datetime Beginning date
|
||||
"""
|
||||
|
||||
self._beginning = self.__datetime( beginning )
|
||||
self.beginning = self.__datetime( beginning )
|
||||
|
||||
def add_ending( self, ending ):
|
||||
"""
|
||||
@@ -449,7 +508,7 @@ class RedFamParser( RedFam ):
|
||||
@param datetime datetime Ending date
|
||||
"""
|
||||
|
||||
self._ending = self.__datetime( ending )
|
||||
self.ending = self.__datetime( ending )
|
||||
|
||||
def __datetime( self, timestamp ):
|
||||
"""
|
||||
@@ -473,7 +532,7 @@ class RedFamParser( RedFam ):
|
||||
type( self ).__timestamp_format )
|
||||
return result
|
||||
|
||||
def status( self ):
|
||||
def check_status( self ):
|
||||
"""
|
||||
Handles detection of correct status
|
||||
There are three possible stati:
|
||||
@@ -485,7 +544,7 @@ class RedFamParser( RedFam ):
|
||||
|
||||
# No ending, discussion is running:
|
||||
# Sometimes archived discussions also have no detectable ending
|
||||
if not self._ending and not self._redpagearchive:
|
||||
if not self.ending and not self._redpagearchive:
|
||||
self.add_status("open")
|
||||
else:
|
||||
self.remove_status("open")
|
||||
@@ -513,7 +572,7 @@ class RedFamParser( RedFam ):
|
||||
return False
|
||||
|
||||
@classmethod
|
||||
def parser( cls, text, page, isarchive=False ):
|
||||
def parser( cls, text, redpage, isarchive=False ):
|
||||
"""
|
||||
Handles parsing of redfam section
|
||||
|
||||
@@ -536,16 +595,33 @@ class RedFamParser( RedFam ):
|
||||
if not beginning:
|
||||
match = re.search(
|
||||
jogobot.config["redundances"]["reddiscs_onlyinclude_re"],
|
||||
page.title() )
|
||||
redpage.page.title() )
|
||||
|
||||
if match:
|
||||
beginning = datetime.strptime(
|
||||
"01. {month} {year}".format(
|
||||
month=match.group(1), year=match.group(2)),
|
||||
"%d. %B %Y" )
|
||||
articlesList = RedFamParser.heading_parser( heading )
|
||||
famhash = RedFamParser.calc_famhash( articlesList )
|
||||
|
||||
# Create the RedFam object
|
||||
RedFamParser( heading, page, isarchive, beginning, ending )
|
||||
# Check for existing objects in DB first in current redpage
|
||||
redfam = redpage.redfams.get(famhash)
|
||||
|
||||
with RedFamParser.session.no_autoflush:
|
||||
if not redfam:
|
||||
# Otherwise in db table
|
||||
redfam = RedFamParser.session.query(RedFamParser).filter(
|
||||
RedFamParser.famhash == famhash ).one_or_none()
|
||||
|
||||
if redfam:
|
||||
# Existing redfams need to be updated
|
||||
redfam.update( articlesList, str(heading), redpage, isarchive, beginning, ending )
|
||||
|
||||
else:
|
||||
# Create the RedFam object
|
||||
redfam = RedFamParser( articlesList, str(heading).strip(), redpage.page, isarchive, beginning, ending )
|
||||
return redfam
|
||||
|
||||
@classmethod
|
||||
def extract_dates( cls, text, isarchive=False ):
|
||||
@@ -615,16 +691,16 @@ class RedFamWorker( RedFam ):
|
||||
mysql_data[ 'status' ], mysql_data[ 'famhash' ],
|
||||
mysql_data[ 'heading' ] )
|
||||
|
||||
self._mysql.data = mysql_data
|
||||
# #~ self._mysql.data = mysql_data
|
||||
|
||||
# Set up article status
|
||||
index = 0
|
||||
for article in self._articlesList:
|
||||
raw_status = mysql_data[ "article" + str(index) + "_status" ]
|
||||
if not raw_status:
|
||||
raw_status = str()
|
||||
self._article_parse_status( raw_status, index )
|
||||
index += 1
|
||||
#~ # Set up article status
|
||||
#~ index = 0
|
||||
#~ for article in self.articlesList:
|
||||
#~ raw_status = mysql_data[ "article" + str(index) + "_status" ]
|
||||
#~ if not raw_status:
|
||||
#~ raw_status = str()
|
||||
#~ self._article_parse_status( raw_status, index )
|
||||
#~ index += 1
|
||||
|
||||
# Get related RedPage-Information
|
||||
self.redpageid = mysql_data[ 'pageid' ]
|
||||
|
||||
188
lib/redpage.py
188
lib/redpage.py
@@ -30,15 +30,23 @@ import mwparserfromhell as mwparser
|
||||
|
||||
import jogobot # noqa
|
||||
|
||||
from lib.mysqlred import MysqlRedPage
|
||||
from lib.redfam import RedFamParser
|
||||
#~ from lib.mysqlred import Column, Integer, String, Text, DateTime, ForeignKey, ColumnList, Status
|
||||
from lib.mysqlred import MysqlRedPage, relationship, MutableSet #MysqlRedFam, Base, composite,
|
||||
from lib.redfam import RedFam, RedFamParser
|
||||
from sqlalchemy.orm.collections import attribute_mapped_collection
|
||||
|
||||
|
||||
class RedPage:
|
||||
class RedPage( MysqlRedPage ):
|
||||
"""
|
||||
Class for handling redundance discussion pages and archives
|
||||
"""
|
||||
|
||||
#TODO POLYMORPHISM? of BASEClass
|
||||
redfams = relationship(
|
||||
"RedFamParser", order_by=RedFamParser.famhash,
|
||||
back_populates="redpage",
|
||||
collection_class=attribute_mapped_collection( "famhash" ) )
|
||||
|
||||
def __init__( self, page=None, pageid=None, archive=False ):
|
||||
"""
|
||||
Generate a new RedPage object based on the given pywikibot page object
|
||||
@@ -49,57 +57,91 @@ class RedPage:
|
||||
@type pageid int
|
||||
"""
|
||||
|
||||
self._status = set()
|
||||
|
||||
# Safe the pywikibot page object
|
||||
self.page = page
|
||||
self.pageid = pageid
|
||||
self._archive = archive
|
||||
if page:
|
||||
self._page = page
|
||||
pageid = self._page.pageid
|
||||
|
||||
self.__handle_db( )
|
||||
self.is_page_changed()
|
||||
super().__init__(
|
||||
pageid=pageid,
|
||||
revid=self.page._revid,
|
||||
pagetitle=self.page.title(),
|
||||
status=MutableSet() ) #TODO EMPTY MutableSet() necessary?
|
||||
#~ self._status = set()
|
||||
|
||||
self._parsed = None
|
||||
if archive:
|
||||
self.status.add("archived")
|
||||
|
||||
def __handle_db( self ):
|
||||
"""
|
||||
Handles opening of db connection
|
||||
"""
|
||||
#~ self._archive = archive
|
||||
|
||||
# We need a connection to our mysqldb
|
||||
if self.page:
|
||||
self.__mysql = MysqlRedPage( self.page._pageid )
|
||||
self.pageid = self.page._pageid
|
||||
elif self.pageid:
|
||||
self.__mysql = MysqlRedPage( self.pageid )
|
||||
self.page = pywikibot.Page( pywikibot.Site(),
|
||||
self.__mysql.data['pagetitle'] )
|
||||
self.page.exists()
|
||||
else:
|
||||
raise ValueError( "Page NOR pagid provided!" )
|
||||
#~ self.pageid = pageid
|
||||
#~ self.revid = self.page._revid
|
||||
#~ self.p
|
||||
#~ self.status = MutableSet()
|
||||
|
||||
if not self.__mysql.data:
|
||||
self.__mysql.add_page( self.page.title(), self.page._revid )
|
||||
# self.__handle_db( )
|
||||
#~ self.is_page_changed()
|
||||
|
||||
#~ self._parsed = None
|
||||
|
||||
self.session.add(self)
|
||||
|
||||
#~ def __handle_db( self ):
|
||||
#~ """
|
||||
#~ Handles opening of db connection
|
||||
#~ """
|
||||
|
||||
#~ # We need a connection to our mysqldb
|
||||
#~ if self.page:
|
||||
#~ self.__mysql = MysqlRedPage( self.page._pageid )
|
||||
#~ self.pageid = self.page._pageid
|
||||
#~ elif self.pageid:
|
||||
#~ self.__mysql = MysqlRedPage( self.pageid )
|
||||
#~ self.page = pywikibot.Page( pywikibot.Site(),
|
||||
#~ self.pagetitle )
|
||||
#~ self.page.exists()
|
||||
#~ else:
|
||||
#~ raise ValueError( "Page NOR pagid provided!" )
|
||||
|
||||
#~ if not self.__mysql.data:
|
||||
#~ self.__mysql.add_page( self.page.title(), self.page._revid )
|
||||
|
||||
def update( self, page ):
|
||||
|
||||
self._page = page
|
||||
self.revid = page._revid
|
||||
self.pagetitle = page.title()
|
||||
|
||||
@property
|
||||
def page(self):
|
||||
if not hasattr(self,"_page"):
|
||||
self._page = pywikibot.Page( pywikibot.Site(), self.pagetitle )
|
||||
|
||||
return self._page
|
||||
|
||||
@property
|
||||
def archive(self):
|
||||
return self.has_status("archived")
|
||||
|
||||
def is_page_changed( self ):
|
||||
"""
|
||||
Check wether the page was changed since last run
|
||||
"""
|
||||
|
||||
if( self.__mysql.data != { 'pageid': self.page._pageid,
|
||||
'revid': self.page._revid,
|
||||
'pagetitle': self.page.title(),
|
||||
'status': self.__mysql.data[ 'status' ] } ):
|
||||
self._changed = True
|
||||
else:
|
||||
self._changed = False
|
||||
self._changed = self.changedp()
|
||||
#~ if( self.__mysql.data != { 'pageid': self.page._pageid,
|
||||
#~ 'revid': self.page._revid,
|
||||
#~ 'pagetitle': 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
|
||||
if( self.archive or ( u"/Archiv" in self.page.title() ) or
|
||||
( "{{Archiv}}" in self.page.text ) or
|
||||
( "{{Archiv|" in self.page.text ) ):
|
||||
|
||||
@@ -111,8 +153,7 @@ class RedPage:
|
||||
"""
|
||||
Decides wether current RedPage needs to be parsed or not
|
||||
"""
|
||||
|
||||
if( self._changed or self.__mysql.data[ 'status' ] == "" ):
|
||||
if( self.changedp() or not self.has_status("parsed") ):
|
||||
return True
|
||||
else:
|
||||
return False
|
||||
@@ -140,31 +181,34 @@ class RedPage:
|
||||
yield fam
|
||||
|
||||
else:
|
||||
self.status.add("parsed")
|
||||
self._parsed = True
|
||||
self.__update_db()
|
||||
#~ self.__update_db()
|
||||
|
||||
def __update_db( self ):
|
||||
"""
|
||||
Updates the page meta data in mysql db
|
||||
"""
|
||||
if( self._parsed or not self._changed ):
|
||||
self.add_status( "open" )
|
||||
#~ def __update_db( self ):
|
||||
#~ """
|
||||
#~ Updates the page meta data in mysql db
|
||||
#~ """
|
||||
#~ if( self._parsed or not self._changed ):
|
||||
#~ self.add_status( "open" )
|
||||
|
||||
if( self.is_archive() ):
|
||||
self.remove_status( "open" )
|
||||
self.add_status( "archived" )
|
||||
else:
|
||||
self._status = set()
|
||||
#~ if( self.is_archive() ):
|
||||
#~ self.remove_status( "open" )
|
||||
#~ self.add_status( "archived" )
|
||||
#~ else:
|
||||
#~ pass
|
||||
#~ self._status = set()
|
||||
|
||||
self.__mysql.update_page( self.page._revid, self.page.title(),
|
||||
self._raw_status() )
|
||||
#~ self.__mysql.update_page( self.page._revid, self.page.title(),
|
||||
#~ self._raw_status() )
|
||||
|
||||
@classmethod
|
||||
def flush_db_cache( cls ):
|
||||
"""
|
||||
Calls flush method of Mysql Interface class
|
||||
"""
|
||||
MysqlRedPage.flush()
|
||||
cls.session.commit()
|
||||
#~ MysqlRedPage.flush()
|
||||
|
||||
def add_status(self, status):
|
||||
"""
|
||||
@@ -173,7 +217,7 @@ class RedPage:
|
||||
@param status Statusstring to add
|
||||
@type status str
|
||||
"""
|
||||
self._status.add(status)
|
||||
self.status.add(status)
|
||||
|
||||
def remove_status(self, status, weak=True):
|
||||
"""
|
||||
@@ -186,9 +230,9 @@ class RedPage:
|
||||
@type bool
|
||||
"""
|
||||
if weak:
|
||||
self._status.discard(status)
|
||||
self.status.discard(status)
|
||||
else:
|
||||
self._status.remove(status)
|
||||
self.status.remove(status)
|
||||
|
||||
def has_status(self, status):
|
||||
"""
|
||||
@@ -198,25 +242,25 @@ class RedPage:
|
||||
@type status str
|
||||
@returns True if status is present else False
|
||||
"""
|
||||
if status in self._status:
|
||||
if status in self.status:
|
||||
return True
|
||||
else:
|
||||
return False
|
||||
|
||||
def _parse_status(self, raw_status ):
|
||||
"""
|
||||
Sets status based on comma separated list
|
||||
#~ def _parse_status(self, raw_status ):
|
||||
#~ """
|
||||
#~ Sets status based on comma separated list
|
||||
|
||||
@param raw_status Commaseparated string of stati (from DB)
|
||||
@type raw_status str
|
||||
"""
|
||||
self._status = set( raw_status.strip().split(","))
|
||||
#~ @param raw_status Commaseparated string of stati (from DB)
|
||||
#~ @type raw_status str
|
||||
#~ """
|
||||
#~ self._status = set( raw_status.strip().split(","))
|
||||
|
||||
def _raw_status( self ):
|
||||
"""
|
||||
Returns status as commaseparated string (to save in DB)
|
||||
#~ def _raw_status( self ):
|
||||
#~ """
|
||||
#~ Returns status as commaseparated string (to save in DB)
|
||||
|
||||
@returns Raw status string
|
||||
@rtype str
|
||||
"""
|
||||
return ",".join( self._status )
|
||||
#~ @returns Raw status string
|
||||
#~ @rtype str
|
||||
#~ """
|
||||
#~ return ",".join( self._status )
|
||||
|
||||
Reference in New Issue
Block a user