使用正则表达式进行Python代码优化

Question

I'm building a web app with the purpose to register all the calls made by users. A call can have a service, number called and a cost. The code provided below is currently working (with the numbers turned into regexes), but it's somewhat of a mess and I would like to optimize it. Since this code requires to be exactly in this order to work, when I used a dictionary to store the regex expressions and services, it didn't work. Here is my current code with the regex used:

  if (service=='R'):
        return "ROAMING"
    elif (service=='V  O') or ((service=='S') and (float(cost)==0.0)):
        return "ONNET"
    elif (service=="") and (nr_called==""):
        return "INTERNET"
    elif (service=='I')or (service=='ROAMING - MMS'):          
        return "OTHERSERV"        
    elif (service=='Internet') or (service=='WAP') or service==('BLACKBERRY.NET') or (service=='ROAMING - INTERNET')or (service=='ROAMING - BLACKBERRY'):
        return "INTERNET"
    elif ((nr_called[:6]=="003516" or nr_called[:6]=="003514" or nr_called[:6]=="003511" or nr_called[:6]=="003517" or nr_called[:6]=="003518") or (nr_called[0]=="6"  or nr_called[0]=="4" or nr_called[0]=="1" or nr_called[0]=="7" or nr_called[0]=="8"))  and (service!="V  O"):
        return "OTHERSERV"    
    elif (service=='Vi F') or (service=='Si'):
        return "INTERNATIONAL"
    elif  (nr_called[0]=="9" or nr_called[:6]=="003519") and (service=="Vp F") and (float(cost)>0) :           
        return "INS"   
    elif (nr_called[:9]=="003519220" or  nr_called[:8]=="00351924" or nr_called[:8]=="00351925" or nr_called[:8]=="00351926" or nr_called[:8]=="00351927" or nr_called[:4]=="9220" or nr_called[:3]=="924" or nr_called[:3]=="925" or nr_called[:3]=="926" or nr_called[:3]=="927") :          
        return "INS"
    elif ((len(nr_called)==9) and nr_called[:2]=="96") or (nr_called[:7]=="0035196"):
        return "INS"
    elif (nr_called[:3]=="921" or  nr_called[:8]=="00351921"):
        return "91"
    elif (nr_called[:3]=="929" or  nr_called[:8]=="00351929"):
        return "93"
    elif (nr_called[:3]=="922" or  nr_called[:8]=="00351922"):
        return "OTHERSERV"
    elif (service!="Vp F") and ((nr_called[:2]=="96" ) or(nr_called[:7]=="0035196")):            
        return "INS"
    elif (len(nr_called)==7) or (service=='V O'):           
        return "ONNET"
    elif ((len(nr_called)==9) and nr_called[:2]=="91") or (nr_called[:7]=="0035191"):
        return "91"
    elif ((len(nr_called)==9) and nr_called[:2]=="93") or (nr_called[:7]=="0035193"):
        return "93"
    elif ((len(nr_called)==9) and nr_called[:1]=="2") or (nr_called[:5]=="00352"):
        return "PT"
    elif float(cost)>0:
        return "OTHERSERV"
    else:
        return "OTHERSERV"

Number regexes:

 OTHERSERV: ['(\+*0*351)?922','(\+*0*351)?[146-8]']
 96:        ['(\+*0*351)?92([4-7|20])','(\+*0*351)?96']
 93:        ['(\+*0*351)?929','(\+*0*351)?93']
 91:        ['(\+*0*351)?921','(\+*0*351)?91']
 PT:        ['(\+*0*351)?2']

I have been dwelling with the optimization for quite a while and can't figure out how can I structure this in an optimized and maintainable way, so any help is very appreciated.

Answer 1

I'm not sure I understand what you're referring to about the regexes, but one option to clean up the if/elif list would be to use a list of result/check tuples:

actions = [
  ('ROAMING'  , lambda service,nr_called,cost: service=='R'),
  ('ONNET'    , lambda service,nr_called,cost: service in ('V  O','S') and float(cost)==0.0),
  ('INTERNET' , lambda service,nr_called,cost: service=='' and nr_called==''),
  ('OTHERSERV', lambda service,nr_called,cost: service in ('I','ROAMING - MMS'))

  # fallthrough
  ('OTHERSERV', lambda service_nr_called,cost: True)
]

for value,check in actions:
  if check(service,nr_called,cost):
    return value

# fallthrough
return 'OTHERSERV'

One or the other items labeled "fallthrough" would be needed.

Answer 2

I was thinking of a solution which is more completely data/table-driven than @ryachza suggestion, for example:

import re

def oldcategorize( service, nr_called, cost):
    if (service=='R'):
        return "ROAMING"
    elif (service=='V  O') or ((service=='S') and (float(cost)==0.0)):
        return "ONNET"
    elif (service=="") and (nr_called==""):
        return "INTERNET"
    elif (service=='I')or (service=='ROAMING - MMS'):          
        return "OTHERSERV"        
    elif (service=='Internet') or (service=='WAP') or service==('BLACKBERRY.NET') or (service=='ROAMING - INTERNET')or (service=='ROAMING - BLACKBERRY'):
        return "INTERNET"
    elif ((nr_called[:6]=="003516" or nr_called[:6]=="003514" or nr_called[:6]=="003511" or nr_called[:6]=="003517" or nr_called[:6]=="003518") or (nr_called[0]=="6"  or nr_called[0]=="4" or nr_called[0]=="1" or nr_called[0]=="7" or nr_called[0]=="8"))  and (service!="V  O"):
        return "OTHERSERV"    
    elif (service=='Vi F') or (service=='Si'):
        return "INTERNATIONAL"
    elif  (nr_called[0]=="9" or nr_called[:6]=="003519") and (service=="Vp F") and (float(cost)>0) :           
        return "INS"   
    elif (nr_called[:9]=="003519220" or  nr_called[:8]=="00351924" or nr_called[:8]=="00351925" or nr_called[:8]=="00351926" or nr_called[:8]=="00351927" or nr_called[:4]=="9220" or nr_called[:3]=="924" or nr_called[:3]=="925" or nr_called[:3]=="926" or nr_called[:3]=="927") :          
        return "INS"
    elif ((len(nr_called)==9) and nr_called[:2]=="96") or (nr_called[:7]=="0035196"):
        return "INS"
    elif (nr_called[:3]=="921" or  nr_called[:8]=="00351921"):
        return "91"
    elif (nr_called[:3]=="929" or  nr_called[:8]=="00351929"):
        return "93"
    elif (nr_called[:3]=="922" or  nr_called[:8]=="00351922"):
        return "OTHERSERV"
    elif (service!="Vp F") and ((nr_called[:2]=="96" ) or(nr_called[:7]=="0035196")):            
        return "INS"
    elif (len(nr_called)==7) or (service=='V O'):           
        return "ONNET"
    elif ((len(nr_called)==9) and nr_called[:2]=="91") or (nr_called[:7]=="0035191"):
        return "91"
    elif ((len(nr_called)==9) and nr_called[:2]=="93") or (nr_called[:7]=="0035193"):
        return "93"
    elif ((len(nr_called)==9) and nr_called[:1]=="2") or (nr_called[:5]=="00352"):
        return "PT"
    elif float(cost)>0:
        return "OTHERSERV"
    else:
        return "OTHERSERV"
    return "FAILED"

# table of categories with regex criteria
# special treatment of first character of a pattern "-" means NOT matching
# note cost is coverted to standardized format using str() for matching
#      service                 number       cost   category
categories = [
    #    if (service=='R'):
    #        return "ROAMING"
     ["^R$"                       ,""         ,""         ,"ROAMING"]
    #    elif (service=='V  O') or ((service=='S') and (float(cost)==0.0)):
    #        return "ONNET"
    ,["^V  O$"                    ,""         ,""         ,"ONNET"]
    ,["^S$"                       ,""         ,"^0.0$"    ,"ONNET"]
    # elif (service=="") and (nr_called==""):
    #   return "INTERNET"
    ,["^$"                      ,"^$"       ,""         ,"INTERNET"]
    #    elif (service=='I')or (service=='ROAMING - MMS'):          
    #        return "OTHERSERV"        
    ,["^I$"                       ,""         ,""         ,"OTHERSERV"]
    ,["^ROAMING - MMS$"           ,""         ,""         ,"OTHERSERV"]
    #   elif (service=='Internet') or (service=='WAP') or service==('BLACKBERRY.NET') or (service=='ROAMING - INTERNET')or (service=='ROAMING - BLACKBERRY'):
    #       return "INTERNET"
    ,["^Internet"                ,""         ,""         ,"INTERNET"]
    ,["^WAP"                     ,""         ,""         ,"INTERNET"]
    ,["^BLACKBERRY.NET"          ,""         ,""         ,"INTERNET"]
    ,["^ROAMING - INTERNET"      ,""         ,""         ,"INTERNET"]
    ,["^ROAMING - INTERNET"      ,""         ,""         ,"INTERNET"]
    ,["^ROAMING - INTERNET"      ,""         ,""         ,"INTERNET"]
    ,["^ROAMING - BLACKBERRY"    ,""         ,""         ,"INTERNET"]
    #   elif ((nr_called[:6]=="003516" or nr_called[:6]=="003514" or nr_called[:6]=="003511" or nr_called[:6]=="003517" or nr_called[:6]=="003518") or (nr_called[0]=="6"  or nr_called[0]=="4" or nr_called[0]=="1" or nr_called[0]=="7" or nr_called[0]=="8"))  and (service!="V  O"):
    #       return "OTHERSERV"
    ,["-^V  O"                   ,"^00351[14678]"    ,""         ,"OTHERSERV"]
    ,["-^V  O"                   ,"^[15678]"         ,""         ,"OTHERSERV"]
    #    elif (len(nr_called)==7) or (service=='V O'):           
    #        return "ONNET"
    ,[""                        ,"^.......$"    ,""         ,"ONNET"]
    ,["^V O$"                     ,""             ,""         ,"ONNET"]
    #   ((len(nr_called)==9) and nr_called[:2]=="91") or (nr_called[:7]=="0035191"):
    #       return "91"
    ,[""                        ,"^91.......$"  ,""         ,"91"]
    ,[""                        ,"^0035191"     ,""         ,"91"]
]

def newcategorize(service, nr_called, cost ):
    for servpat,numpat,costpat,res in categories:
        print servpat,numpat,costpat,res
        if (servpat[0]=="-" and not re.match(servpat[1:],service)) or re.match(servpat,service):
            if (numpat[0]=="-" and not re.match(numpat[1:],nr_called)) or re.match(numpat,nr_called):
                if (costpat[0]=="-" and not re.match(costpat[1:],str(cost))) or re.match(costpat,str(cost)):
                    return res
    result = "FAILED to find %s %s %s"%(service,nr_called, cost)
    # print result
    return result

testdata = [
    ["x","012345",0.0]
    ,["S","123",0.0]
    ,["NOT V  O","003517",0.0]
]

for s,n,c in testdata:
    oc = oldcategorize(s,n,c)
    nc = oldcategorize(s,n,c)
    if oc != nc:
        print "ERROR",s,n,c,oc,nc
    print "match",s,n,c,oc,nc

So the table contains all the data needed to drive the logic, but the logic itself is coded in the newcategorize() function, using the power of regex to do most of the hard work, with only the addition that a leading - in a pattern makes the logic look for the pattern NOT matching. Using this approach the table is more concise, whereas with @ryachza solution the table could get quite difficult to read and probably debug for the more complex lambda expressions. With my approach you just add print statements.

HTH Barny