Home | History | Annotate | Download | only in common 
      1 # Copyright (c) 2011 Google Inc. All rights reserved.
      2 #
      3 # Redistribution and use in source and binary forms, with or without
      4 # modification, are permitted provided that the following conditions are
      5 # met:
      6 #
      7 #     * Redistributions of source code must retain the above copyright
      8 # notice, this list of conditions and the following disclaimer.
      9 #     * Redistributions in binary form must reproduce the above
     10 # copyright notice, this list of conditions and the following disclaimer
     11 # in the documentation and/or other materials provided with the
     12 # distribution.
     13 #     * Neither the name of Google Inc. nor the names of its
     14 # contributors may be used to endorse or promote products derived from
     15 # this software without specific prior written permission.
     16 #
     17 # THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
     18 # "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
     19 # LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
     20 # A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
     21 # OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
     22 # SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
     23 # LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
     24 # DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
     25 # THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
     26 # (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
     27 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
     28 
     29 from array import array
     30 
     31 
     32 def edit_distance(str1, str2):
     33     unsignedShort = 'h'
     34     distances = [array(unsignedShort, (0,) * (len(str2) + 1)) for i in range(0, len(str1) + 1)]
     35     # distances[0][0] = 0 since distance between str1[:0] and str2[:0] is 0
     36     for i in range(1, len(str1) + 1):
     37         distances[i][0] = i  # Distance between str1[:i] and str2[:0] is i
     38 
     39     for j in range(1, len(str2) + 1):
     40         distances[0][j] = j  # Distance between str1[:0] and str2[:j] is j
     41 
     42     for i in range(0, len(str1)):
     43         for j in range(0, len(str2)):
     44             diff = 0 if str1[i] == str2[j] else 1
     45             # Deletion, Insertion, Identical / Replacement
     46             distances[i + 1][j + 1] = min(distances[i + 1][j] + 1, distances[i][j + 1] + 1, distances[i][j] + diff)
     47     return distances[len(str1)][len(str2)]
     48