139 lines
3.5 KiB
Python
139 lines
3.5 KiB
Python
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
|
|
from mysql_red import MYSQL_RED_PAGE
|
|
from red_fam import RED_FAM_PARSER
|
|
|
|
class RED_PAGE:
|
|
"""Class for handling redundance discussion pages and archives"""
|
|
|
|
def __init__( self, page, archive=False ):
|
|
"""
|
|
Generate a new RED_PAGE object based on the given pywikibot page object
|
|
|
|
@param page page
|
|
"""
|
|
|
|
# Safe the pywikibot page object
|
|
self.page = page
|
|
self._archive = archive
|
|
|
|
self.__handle_db( )
|
|
|
|
self.is_page_changed()
|
|
|
|
self.__parsed = None
|
|
if( self.__changed or self.__mysql.data[ 'status' ] == 0 ):
|
|
self.parse()
|
|
|
|
self.__update_db()
|
|
|
|
# else:
|
|
# self.__mysql.add_page()
|
|
|
|
def __handle_db( self ):
|
|
"""
|
|
Handles opening of db connection
|
|
"""
|
|
# We need a connection to our mysqldb
|
|
self.__mysql = MYSQL_RED_PAGE( 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() ):
|
|
return True
|
|
else:
|
|
return False
|
|
|
|
def parse( self ):
|
|
"""
|
|
Handles the parsing process
|
|
"""
|
|
|
|
# Since @param text is a string we need to split it in lines
|
|
text_lines = self.page.text.split( "\n" )
|
|
|
|
# Initialise line counter
|
|
i = 0
|
|
fam_heading = None
|
|
beginning = None
|
|
ending = None
|
|
|
|
# Set line for last detected Redundance-Family to 0
|
|
last_fam = 0
|
|
|
|
# Iterate over the lines of the page
|
|
for line in text_lines:
|
|
|
|
# Check wether we have an "Redundance-Family"-Section heading (Level 3)
|
|
if RED_FAM_PARSER.is_sectionheading( line ):
|
|
|
|
# Before working with next red_fam create the object for the one before (if one)
|
|
if( fam_heading and beginning ):
|
|
#Maybe we can find a ending by feed
|
|
if not ending:
|
|
j = i
|
|
while (j > last_fam) and not ending:
|
|
j -= 1
|
|
ending = RED_FAM_PARSER.is_ending2( text_lines[ j ] )
|
|
|
|
red_fam = RED_FAM_PARSER( fam_heading, self.page._pageid, self.is_archive(), beginning, ending )
|
|
print( red_fam )
|
|
|
|
# Save line number for last detected Redundance-Family
|
|
last_fam = i
|
|
# Save heading
|
|
fam_heading = line
|
|
|
|
# Defined (re)initialisation of dates
|
|
beginning = None
|
|
ending = None
|
|
|
|
# Check wether we are currently in an "Redundance-Family"-Section Body
|
|
if i > last_fam and last_fam > 0:
|
|
|
|
# Check if we have alredy recognized the beginning date of the discussion (in former iteration) or if we have a done-notice
|
|
if not beginning:
|
|
beginning = RED_FAM_PARSER.is_beginning( line )
|
|
elif not ending:
|
|
ending = RED_FAM_PARSER.is_ending( line )
|
|
# Increment line counter
|
|
i += 1
|
|
else:
|
|
# For the last red_fam create the object
|
|
if( fam_heading and beginning ):
|
|
#~ try:
|
|
red_fam = RED_FAM_PARSER( fam_heading, self.page._pageid, self.is_archive(), beginning, ending )
|
|
#~ except:
|
|
#~ pass
|
|
# Set status of red_page to parsed
|
|
self.__parsed = True
|
|
def __update_db( self ):
|
|
"""
|
|
Updates the page meta data in mysql db
|
|
"""
|
|
if( self.__parsed ):
|
|
status = 1
|
|
|
|
if( self.is_archive() ):
|
|
status = 2
|
|
else:
|
|
status = 0
|
|
|
|
self.__mysql.update_page( self.page._revid, self.page.title(), status )
|