This module Difflib provides classes and functions for comparing sequences. It can be used for example, for comparing files, and can produce difference information in various formats, including HTML and context and unified diffs. For comparing directories and files, see also, the filecmp module.

class difflib.SequenceMatcher The idea is to find the longest contiguous matching subsequence that contains no “junk” elements (the Ratcliff and Obershelp algorithm doesn’t address junk). The most basic functions:

• find_longest_match
• get_matching_blocks

The function get_opcodes using above these functions for parsing
Create SequenceMatcher with input are two strings or two lists

• Calculate match ratio of two strings:

  import difflib
   
  a = ' abcd'
  b = 'abcd abcd'
   
  seq = difflib.SequenceMatcher(None, a, b)
  rate = seq.ratio() * 100
   
  print rate

  ⇒ output:

  71.4285714286

• Find substring with longest match ratio:
  • Syntax:

    find_longest_match(alo, ahi, blo, bhi)

    Find longest matching block in a[alo:ahi] and b[blo:bhi].(lo: low, hi: high). Returns (i, j, k) such that a[i:i+k] is equal to b[j:j+k] with longest match ratio

  • Simple Example

    import difflib
     
    a = ' abcd'
    b = 'abcd abcd'
     
    seq = difflib.SequenceMatcher(None, a, b)
    rate = seq.ratio() * 100
     
    print rate
    print seq.find_longest_match(0, 5, 0, 9)
    a = 'm abcd'
    seq.set_seq1(a)
    print seq.find_longest_match(0, 6, 0, 9)

    ⇒ output:

    71.4285714286
    Match(a=0, b=4, size=5)
    Match(a=1, b=4, size=5)

  • Example find_longest_match with isjunk option:

    import difflib
     
    a = ' abcd'
    b = 'abcd abcd'
     
    seq = difflib.SequenceMatcher(None, a, b)
    seq2 = difflib.SequenceMatcher(lambda x: x==" ", a, b)
    seq3 = difflib.SequenceMatcher(difflib.IS_LINE_JUNK, a, b)
     
    print seq.find_longest_match(0, 5, 0, 9)
    print seq2.find_longest_match(0, 5, 0, 9)
    print seq3.find_longest_match(0, 5, 0, 9)

    output:

    Match(a=0, b=4, size=5)
    Match(a=1, b=0, size=4)
    Match(a=1, b=0, size=4)

• Get matching blocks:

  import difflib
   
  a = ' abcd'
  b = 'abcd abcd'
   
  seq = difflib.SequenceMatcher(None, a, b)
  rate = seq.ratio() * 100
   
  print 'matching1:'
  for block in seq.get_matching_blocks():
      print "a[%d] and b[%d] match for %d elements" % block
  a = 'abced abc'
  seq.set_seq1(a)
  print 'matching2:'
  for block in seq.get_matching_blocks():
      print "a[%d] and b[%d] match for %d elements" % block

  ⇒ output:

  matching1:
  a[0] and b[4] match for 5 elements
  a[5] and b[9] match for 0 elements
  matching2:
  a[0] and b[0] match for 3 elements
  a[4] and b[3] match for 5 elements
  a[9] and b[9] match for 0 elements

  a[0] and b[4] match for 5 elements: 5 elements from a[0] are ' abcd' and 5 elements from b[9] are ' abcd'

import difflib
import sys
 
a = """ abcd 
abc pq
ef abc
mn
"""
b = """abcd abcd
ef
mn
"""
 
seq = difflib.SequenceMatcher(None, a, b)
rate = seq.ratio() * 100
print '*************************'
print 'rate1: ',rate
print 'longest_match1: ', seq.find_longest_match(0, 20, 0, 9)
print 'matching blocks1:'
for block in seq.get_matching_blocks():
    print "a[%d] and b[%d] match for %d elements" % block
    print '>>>>', a[block[0]:(block[0] + block[2])]
    print '<<<<', b[block[1]:(block[1] + block[2])]
 
a = a.splitlines(1)
b = b.splitlines(1)
seq2 = difflib.SequenceMatcher(None, a, b)
rate = seq.ratio() * 100
print '*************************'
print 'rate2: ',rate
print 'longest_match2: ', seq2.find_longest_match(0, 4, 0, 3)
print 'matching blocks2:'
for block in seq2.get_matching_blocks():
    print "a[%d] and b[%d] match for %d elements" % block
    print '>>>>', a[block[0]:(block[0] + block[2])]
    print '<<<<', b[block[1]:(block[1] + block[2])]
 
 
d = difflib.Differ()
result = list(d.compare(a, b))
print 'normal diff:'
sys.stdout.writelines(result)

output:

*************************
*************************
rate1:  60.0
longest_match1:  Match(a=0, b=4, size=5)
matching blocks1:
a[0] and b[4] match for 5 elements
>>>>  abcd
<<<<  abcd
a[13] and b[9] match for 3 elements
>>>>
ef
<<<<
ef
a[20] and b[12] match for 4 elements
>>>>
mn

<<<<
mn

a[24] and b[16] match for 0 elements
>>>>
<<<<
*************************
rate2:  60.0
longest_match2:  Match(a=3, b=2, size=1)
matching blocks2:
a[3] and b[2] match for 1 elements
>>>> ['mn\n']
<<<< ['mn\n']
a[4] and b[3] match for 0 elements
>>>> []
<<<< []
normal diff:
+ abcd abcd
+ ef
-  abcd
- abc pq
- ef abc
  mn

import difflib
from os import path 
 
INPUT_DIR = 'opencart_47066'
htmlfile1 = path.join(INPUT_DIR, 'index.html')
htmlfile2 = path.join(INPUT_DIR, 'index.php@route=account%2Flogin.html')
with open(htmlfile1, 'r') as f:
    doc1 = f.read()
with open(htmlfile2, 'r') as f:
    doc2 = f.read()    
seq = difflib.SequenceMatcher(None, doc1, doc2)
rate = seq.ratio() * 100
print rate
for block in seq.get_matching_blocks():
    print "a[%d] and b[%d] match for %d elements" % block
    print '>>>>', doc1[block[0]:(block[0] + block[2])]
    print '<<<<', doc2[block[1]:(block[1] + block[2])]

Differ object using APIs of SequenceMatcher for comparing:

• SequenceMatcher.get_opcodes
• And SequenceMatcher.get_grouped_opcodes

Understand some basic function:

• Differ.compare:

  d = difflib.Differ()
  result = d.compare(a, b)

• ndiff default will ignore characters IS_CHARACTER_JUNK(' \t') when comparing :

  def ndiff(a, b, linejunk=None, charjunk=IS_CHARACTER_JUNK):
      return Differ(linejunk, charjunk).compare(a, b)

import difflib
from os import path
from pprint import pprint
import sys 
 
a = """ abcd 
abc pq
ef abc
 mpq
""".splitlines(1)
b = """abcd abcd
abc pq
ef
mpq
""".splitlines(1)
 
d = difflib.Differ()
result = list(d.compare(a, b))
print 'normal diff:'
sys.stdout.writelines(result)
 
print 'diff with charjunk = difflib.IS_CHARACTER_JUNK:'
result = difflib.ndiff(a, b)
sys.stdout.writelines(result)

output:

-  abcd
+ abcd abcd
  abc pq
- ef abc
+ ef

• compare 2 files normal:

  import difflib
  from os import path
  from pprint import pprint
  import sys 
   
  INPUT_DIR = 'opencart_47066'
  htmlfile1 = path.join(INPUT_DIR, 'index.html')
  htmlfile2 = path.join(INPUT_DIR, 'index.php@route=account%2Flogin.html')
  with open(htmlfile1, 'r') as f:
      doc1 = f.read().splitlines(1)
  with open(htmlfile2, 'r') as f:
      doc2 = f.read().splitlines(1)
   
  d = difflib.Differ()
  result = d.compare(doc1, doc2)
  with open('compare.html', 'wb') as f:
      for line in result:
          f.writelines(line)

• compare ignore characters IS_CHARACTER_JUNK(' \t') when comparing

  import difflib
  from os import path
  from pprint import pprint
  import sys 
   
  INPUT_DIR = 'opencart_47066'
  htmlfile1 = path.join(INPUT_DIR, 'index.html')
  htmlfile2 = path.join(INPUT_DIR, 'index.php@route=account%2Flogin.html')
  with open(htmlfile1, 'r') as f:
      doc1 = f.read().splitlines(1)
  with open(htmlfile2, 'r') as f:
      doc2 = f.read().splitlines(1)
   
  result = difflib.ndiff(doc1, doc2)
  with open('compare.html', 'wb') as f:
      for line in result:
          f.writelines(line)

• Compare 2 html files:

  import difflib
  from os import path
  from pprint import pprint
  import sys, re 
   
  INPUT_DIR = 'opencart_47066'
  htmlfile1 = path.join(INPUT_DIR, 'index.html')
  htmlfile2 = path.join(INPUT_DIR, 'index.php@route=account%2Flogin.html')
  with open(htmlfile1, 'r') as f:
      content = f.read()
      content = re.sub('[\s\t]+/>', '/>', content)
      content = re.sub('[\s\t]+>', '>', content)
      content = re.sub('>[\s\t]+<', '>\n<', content)
      content = re.sub('[\s\t]*\n[\s\t]*', '\n', content)
      doc1 = content.splitlines(1)
  with open(htmlfile2, 'r') as f:
      content = f.read()
      content = re.sub('[\s\t]+/>', '/>', content)
      content = re.sub('[\s\t]+>', '>', content)
      content = re.sub('>[\s\t]+<', '>\n<', content)
      content = re.sub('[\s\t]*\n[\s\t]*', '\n', content)
      doc2 = content.splitlines(1)
   
  result = difflib.ndiff(doc1, doc2)
  with open('compare.html', 'wb') as f:
      for line in result:
          f.writelines(line)

xml.html.diff using 2 basic libraries:

• difflib for comparing 2 files
• etree for parsing HTML

Examples for lxml.html.diff:

• Simple diff HTML:

  from os import path
  import sys, re
  from lxml.html import diff
  import codecs
   
  INPUT_DIR = 'opencart_47066'
  htmlfile1 = path.join(INPUT_DIR, 'index.html')
  htmlfile2 = path.join(INPUT_DIR, 'index.php@route=account%2Flogin.html')
  with open(htmlfile1, 'r') as f:
      content = f.read()
      doc1 = content
  with open(htmlfile2, 'r') as f:
      content = f.read()
      doc2 = content
  diffcontent = diff.htmldiff(doc1, doc2)
  diffcontent = codecs.encode(diffcontent, 'utf-8')
  print diffcontent