# HG changeset patch
# User RussellBallestrini
# Date 1398350380 14400
#      Thu Apr 24 10:39:40 2014 -0400
# Node ID 70436261056967ad963b049495487eb546d3f65c
# Parent  4ff37fbcd4e829ed3f57edd241f2d9f681707154
Save scores or ratios in difflib get_close_matches

The current implementation of difflib's get_close_matches()
function computes computationally complex scores (ratios)
but then tosses them out without giving the end-user the
chance to have at them.

This patch adds an optional "scores" boolean argument that
may be passed to alter the return output from a list of
words, to a list of (score, word) tuples.



changed Lib/difflib.py

diff -r 4ff37fbcd4e8 -r 704362610569 Lib/difflib.py
--- a/Lib/difflib.py	Wed Apr 23 15:37:37 2014 -0500
+++ b/Lib/difflib.py	Thu Apr 24 10:39:40 2014 -0400
@@ -1,7 +1,7 @@
 """
 Module difflib -- helpers for computing deltas between objects.
 
-Function get_close_matches(word, possibilities, n=3, cutoff=0.6):
+Function get_close_matches(word, possibilities, n=3, cutoff=0.6, scores=False):
     Use SequenceMatcher to return list of the best "good enough" matches.
 
 Function context_diff(a, b):
@@ -685,7 +685,7 @@
         # shorter sequence
         return _calculate_ratio(min(la, lb), la + lb)
 
-def get_close_matches(word, possibilities, n=3, cutoff=0.6):
+def get_close_matches(word, possibilities, n=3, cutoff=0.6, scores=False):
     """Use SequenceMatcher to return list of the best "good enough" matches.
 
     word is a sequence for which close matches are desired (typically a
@@ -700,6 +700,10 @@
     Optional arg cutoff (default 0.6) is a float in [0, 1].  Possibilities
     that don't score at least that similar to word are ignored.
 
+    Optional arg scores (default False) is a boolean.  If False a list of
+    words will be returned. If True a list of (score,word) tuples will be
+    returned.
+
     The best (no more than n) matches among the possibilities are returned
     in a list, sorted by similarity score, most similar first.
 
@@ -708,6 +712,8 @@
     >>> import keyword as _keyword
     >>> get_close_matches("wheel", _keyword.kwlist)
     ['while']
+    >>> get_close_matches("wheel", _keyword.kwlist, scores=True)
+    [(1.0, 'while')]
     >>> get_close_matches("Apple", _keyword.kwlist)
     []
     >>> get_close_matches("accept", _keyword.kwlist)
@@ -730,6 +736,10 @@
 
     # Move the best scorers to head of list
     result = heapq.nlargest(n, result)
+
+    if scores:
+        return result
+
     # Strip scores for the best n matches
     return [x for score, x in result]