Question

Lets say i have a regular expression:

match = re.search(pattern, content)
if not match:
    raise Exception, 'regex traceback' # i want to throw here the regex matching process.

If regular expression fails to match then i want to throw in exception Its working and where it fails to match the regular expression pattern, at what stage etc. Is it possible even to achieve the desired functionality?

Answer 1

I have something that helps me to debug complex regex patterns among my codes.
Does this help you ? :

import re

li = ('ksjdhfqsd\n'
      '5 12478 abdefgcd ocean__12      ty--\t\t ghtr789\n'
      'qfgqrgqrg',

      '6 48788 bcfgdebc atlantic__7899 %fg#\t\t ghtu12340\n',

      '2 47890 bbcedefg arctic__124    **juyf\t\t ghtr89877',

      '9 54879 bbdecddf antarctic__13  18:13pomodoro\t\t ghtr6798',


      'ksjdhfqsd\n'
      '5 12478 abdefgcd ocean__1247101247887 ty--\t\t ghtr789\n'
      'qfgqrgqrg',

      '6 48788 bcfgdebc atlantic__7899 %fg#\t\t ghtu12940\n',

      '25 47890 bbcedefg arctic__124    **juyf\t\t ghtr89877',

      '9 54879 bbdeYddf antarctic__13  18:13pomodoro\t\t ghtr6798')


tupleRE = ('^\d',
           ' ',
           '\d{5}',
           ' ',
           '[abcdefghi]+',
           ' ',
           '(?=[a-z\d_ ]{14} [^ ]+\t\t ght)',
           '[a-z]+',
           '__',
           '[\d]+',
           ' +',
           '[^\t]+',
           '\t\t',
           ' ',
           'ght',
           '(r[5-9]+|u[0-4]+)',
           '$')  



def REtest(ch, tuplRE, flags = re.MULTILINE):
    for n in xrange(len(tupleRE)):
        regx = re.compile(''.join(tupleRE[:n+1]), flags)
        testmatch = regx.search(ch)
        if not testmatch:
            print '\n  -*- tupleRE :\n'
            print '\n'.join(str(i).zfill(2)+' '+repr(u)
                            for i,u in enumerate(tupleRE[:n]))
            print '   --------------------------------'
            # tupleRE doesn't works because of element n
            print str(n).zfill(2)+' '+repr(tupleRE[n])\
                  +"   doesn't match anymore from this ligne "\
                  +str(n)+' of tupleRE'
            print '\n'.join(str(n+1+j).zfill(2)+' '+repr(u)
                            for j,u in enumerate(tupleRE[n+1:
                                                         min(n+2,len(tupleRE))]))

            for i in xrange(n):
                match = re.search(''.join(tupleRE[:n-i]),ch, flags)
                if match:
                    break

            matching_portion = match.group()
            matching_li = '\n'.join(map(repr,
                                        matching_portion.splitlines(True)[-5:]))
            fin_matching_portion = match.end()
            print ('\n\n  -*- Part of the tested string which is concerned :\n\n'
                   '######### matching_portion ########\n'+matching_li + '\n'
                   '##### end of matching_portion #####\n'
                   '-----------------------------------\n'
                   '######## unmatching_portion #######')
            print '\n'.join(map(repr,
                                ch[fin_matching_portion:
                                   fin_matching_portion+300].splitlines(True)) )
            break
    else:
        print '\n  SUCCES . The regex integrally matches.'



for x in li:
    print '  -*- Analyzed string :\n%r' % x
    REtest(x,tupleRE)
    print '\nmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwm'

result

  -*- Analyzed string :
'ksjdhfqsd\n5 12478 abdefgcd ocean__12      ty--\t\t ghtr789\nqfgqrgqrg'

  SUCCESS . The regex integrally matches.

mwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwm
  -*- Analyzed string :
'6 48788 bcfgdebc atlantic__7899 %fg#\t\t ghtu12340\n'

  SUCCESS . The regex integrally matches.

mwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwm
  -*- Analyzed string :
'2 47890 bbcedefg arctic__124    **juyf\t\t ghtr89877'

  SUCCESS . The regex integrally matches.

mwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwm
  -*- Analyzed string :
'9 54879 bbdecddf antarctic__13  18:13pomodoro\t\t ghtr6798'

  SUCCESS . The regex integrally matches.

mwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwm
  -*- Analyzed string :
'ksjdhfqsd\n5 12478 abdefgcd ocean__1247101247887 ty--\t\t ghtr789\nqfgqrgqrg'

  -*- tupleRE :

00 '^\\d'
01 ' '
02 '\\d{5}'
03 ' '
04 '[abcdefghi]+'
05 ' '
   --------------------------------
06 '(?=[a-z\\d_ ]{14} [^ ]+\t\t ght)'   doesn't match anymore from this ligne 6 of tupleRE
07 '[a-z]+'


  -*- Part of the tested string which is concerned :

######### matching_portion ########
'5 12478 abdefgcd '
##### end of matching_portion #####
-----------------------------------
######## unmatching_portion #######
'ocean__1247101247887 ty--\t\t ghtr789\n'
'qfgqrgqrg'

mwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwm
  -*- Analyzed string :
'6 48788 bcfgdebc atlantic__7899 %fg#\t\t ghtu12940\n'

  -*- tupleRE :

00 '^\\d'
01 ' '
02 '\\d{5}'
03 ' '
04 '[abcdefghi]+'
05 ' '
06 '(?=[a-z\\d_ ]{14} [^ ]+\t\t ght)'
07 '[a-z]+'
08 '__'
09 '[\\d]+'
10 ' +'
11 '[^\t]+'
12 '\t\t'
13 ' '
14 'ght'
15 '(r[5-9]+|u[0-4]+)'
   --------------------------------
16 '$'   doesn't match anymore from this ligne 16 of tupleRE



  -*- Part of the tested string which is concerned :

######### matching_portion ########
'6 48788 bcfgdebc atlantic__7899 %fg#\t\t ghtu12'
##### end of matching_portion #####
-----------------------------------
######## unmatching_portion #######
'940\n'

mwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwm
  -*- Analyzed string :
'25 47890 bbcedefg arctic__124    **juyf\t\t ghtr89877'

  -*- tupleRE :

00 '^\\d'
   --------------------------------
01 ' '   doesn't match anymore from this ligne 1 of tupleRE
02 '\\d{5}'


  -*- Part of the tested string which is concerned :

######### matching_portion ########
'2'
##### end of matching_portion #####
-----------------------------------
######## unmatching_portion #######
'5 47890 bbcedefg arctic__124    **juyf\t\t ghtr89877'

mwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwm
  -*- Analyzed string :
'9 54879 bbdeYddf antarctic__13  18:13pomodoro\t\t ghtr6798'

  -*- tupleRE :

00 '^\\d'
01 ' '
02 '\\d{5}'
03 ' '
04 '[abcdefghi]+'
   --------------------------------
05 ' '   doesn't match anymore from this ligne 5 of tupleRE
06 '(?=[a-z\\d_ ]{14} [^ ]+\t\t ght)'


  -*- Part of the tested string which is concerned :

######### matching_portion ########
'9 54879 bbde'
##### end of matching_portion #####
-----------------------------------
######## unmatching_portion #######
'Yddf antarctic__13  18:13pomodoro\t\t ghtr6798'

mwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwmwm