Dear Python's Gurus
I have this nice over-my-head scripts
1. It loads two files (daifmaster.txt and sahihmaster.txt)
HELP ONE
Please I NEED to print these unified two sorted files as one = call it
dsmaster.txt
2. It load file (Kanzmaster.txt) and sort it
HELP TWO
Please I need to print this sorted kanzmaster.txt and call it
KSmaster.txt
3. Please Explain to me the lines
def addCommand(self,command,callback,flags):
self.callbacks[command]={'callback':callback,'command':command,'flags':f
lags}
def findCallback(self,command):
#!/usr/bin/python
# -*- coding: UTF-8 -*-
import sys
import codecs
import re
TYPE_MULTILINE=0x1
class ReaderBase:
def __init__(self):
self.callbacks={}
def addCommand(self,command,callback,flags):
self.callbacks[command]={'callback':callback,'command':command,'flags':f
lags}
def findCallback(self,command):
try:
return self.callbacks[command[0]]
except KeyError:
return None
def processFile(self,path):
#f=open(path, 'r')
f = codecs.open(path, encoding='CP1256', mode='r')
val=''
citem=None
for line in f.readlines():
parts=line.split('|')
if citem!=None:
if citem['flags']&TYPE_MULTILINE:
val+=parts[0]
for part in parts[1:]:
if citem!=None:
citem['callback'](citem['command'],val.strip())
lineparts=part.split(' ',1)
cmd=lineparts[0]
if(len(lineparts)>1):
val=lineparts[1]
else:
val=''
if len(cmd)>0:
citem=self.findCallback(cmd)
else:
citem=None
if citem!=None:
citem['callback'](citem['command'],val.strip())
f.close()
entryCount=0
class HadithEntry:
def __init__(self):
self.keys=[]
self.values=[]
def addValue(self,key,val):
for i in range(len(self.keys)):
if self.keys[i]==key:
self.values[i]=val
return
self.keys.append(key)
self.values.append(val)
def write(self,f=sys.stdout):
global entryCount
entryCount=entryCount+1
for i in range(len(self.keys)):
if not self.keys[i].endswith('-tmp'):
f.write(('|'+self.keys[i]+str(entryCount)+'
'+self.values[i]+'\n').encode('utf-8'))
def getValue(self,key):
for i in range(len(self.keys)):
if self.keys[i]==key:
return self.values[i]
return ''
hadithItems=[]
sortByH_regex_punct = re.compile(u"[ ,،.:\\\\(\\\\)?{}\n.]")
def sortByH(a,b):
a=a.getValue('H-tmp')
b=b.getValue('H-tmp')
#remove punctuation before comparison
#a=re.sub(sortByH_regex_punct,'',a)
#b=re.sub(sortByH_regex_punct,'',b)
if(a==b):
return 0
if(a>b):
return 1
return -1
currentEntry=None
#reads the 40k hadith entries
def fill1stHadithEntries(cmd,val):
global hadithItems
global currentEntry
#the last tag in a record is H
if cmd=='H':
currentEntry=HadithEntry()
hadithItems.append(currentEntry)
a=val
a=re.sub(sortByH_regex_punct,'',a)
currentEntry.addValue('H-tmp',a)
if currentEntry!=None:
currentEntry.addValue(cmd,val)
hadith2Items=[]
#reads the 15K files format
def fill2stHadithEntries(cmd,val):
global hadith2Items
global currentEntry
if cmd=='R':
currentEntry=HadithEntry()
if currentEntry!=None:
currentEntry.addValue(cmd,val)
#The last tag in a record if F
if cmd=='F':
a=currentEntry.getValue('H')
a=re.sub(sortByH_regex_punct,'',a)
currentEntry.addValue('H-tmp',a)
hadith2Items.append(currentEntry)
tempEntry=None
tempEntryPos=0
successMerges=0
#both lists must be sorted, otherwise it will fail.
def mergeHadithEntries(val):
global hadithItems
global tempEntry
global tempEntryPos
global successMerges
while tempEntryPos<len(hadithItems) and
sortByH(val,hadithItems[tempEntryPos])>0:
tempEntryPos=tempEntryPos+1
if tempEntryPos>=len(hadithItems):
return
if sortByH(val,hadithItems[tempEntryPos])==0:
hadithItems[tempEntryPos].addValue('R',val.getValue('R'))
#print 'found entry'
successMerges=successMerges+1
return
#print 'entry not found', val.getValue('H')
reader=ReaderBase()
reader.addCommand('H',fill1stHadithEntries,TYPE_MULTILINE)
reader.addCommand('R',fill1stHadithEntries,0)
reader.addCommand('F',fill1stHadithEntries,0)
#reader.processFile('test.txt')
print "Processing KanzMaster ...."
reader.processFile('../../src/cd2/KanzMaster.txt')
print "loaded ",len(hadithItems),"."
print "Sorting..."
hadithItems.sort(sortByH)
currentEntry=None
reader=ReaderBase()
reader.addCommand('H',fill2stHadithEntries,TYPE_MULTILINE)
reader.addCommand('R',fill2stHadithEntries,0)
reader.addCommand('F',fill2stHadithEntries,0)
print "Processing sahihMaster ...."
reader.processFile('../../src/cd2/sahihMaster.txt')
currentEntry=None
print "Processing daifMaster ...."
reader.processFile('../../src/cd2/daifMaster.txt')
#sort before merging to speed up the merge process
hadith2Items.sort(sortByH)
print "loaded ",len(hadith2Items),"."
#Now both maps are sorted
print "Merging ...."
map(mergeHadithEntries,hadith2Items)
#write the merged items
print "writing ",len(hadithItems),"..."
map(HadithEntry.write,hadithItems)
print "successMerges=",successMerges
Regards
Alan Darwish
"Knowledgeable enemy is better than an ignorant friend"
---
Outgoing mail is certified Virus Free.
Checked by AVG anti-virus system (http://www.grisoft.com).
Version: 6.0.778 / Virus Database: 525 - Release Date: 10/15/2004
_______________________________________________
Tutor maillist - Tutor@python.org
http://mail.python.org/mailman/listinfo/tutor
