Commit | Line | Data |
---|---|---|
86530b38 AT |
1 | <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN"> |
2 | <html> | |
3 | <head> | |
4 | <link rel="STYLESHEET" href="lib.css" type='text/css' /> | |
5 | <link rel="SHORTCUT ICON" href="../icons/pyfav.png" type="image/png" /> | |
6 | <link rel='start' href='../index.html' title='Python Documentation Index' /> | |
7 | <link rel="first" href="lib.html" title='Python Library Reference' /> | |
8 | <link rel='contents' href='contents.html' title="Contents" /> | |
9 | <link rel='index' href='genindex.html' title='Index' /> | |
10 | <link rel='last' href='about.html' title='About this document...' /> | |
11 | <link rel='help' href='about.html' title='About this document...' /> | |
12 | <link rel="next" href="differ-objects.html" /> | |
13 | <link rel="prev" href="sequence-matcher.html" /> | |
14 | <link rel="parent" href="module-difflib.html" /> | |
15 | <link rel="next" href="differ-objects.html" /> | |
16 | <meta name='aesop' content='information' /> | |
17 | <title>4.4.2 SequenceMatcher Examples </title> | |
18 | </head> | |
19 | <body> | |
20 | <DIV CLASS="navigation"> | |
21 | <div id='top-navigation-panel' xml:id='top-navigation-panel'> | |
22 | <table align="center" width="100%" cellpadding="0" cellspacing="2"> | |
23 | <tr> | |
24 | <td class='online-navigation'><a rel="prev" title="4.4.1 SequenceMatcher Objects" | |
25 | href="sequence-matcher.html"><img src='../icons/previous.png' | |
26 | border='0' height='32' alt='Previous Page' width='32' /></A></td> | |
27 | <td class='online-navigation'><a rel="parent" title="4.4 difflib " | |
28 | href="module-difflib.html"><img src='../icons/up.png' | |
29 | border='0' height='32' alt='Up One Level' width='32' /></A></td> | |
30 | <td class='online-navigation'><a rel="next" title="4.4.3 Differ Objects" | |
31 | href="differ-objects.html"><img src='../icons/next.png' | |
32 | border='0' height='32' alt='Next Page' width='32' /></A></td> | |
33 | <td align="center" width="100%">Python Library Reference</td> | |
34 | <td class='online-navigation'><a rel="contents" title="Table of Contents" | |
35 | href="contents.html"><img src='../icons/contents.png' | |
36 | border='0' height='32' alt='Contents' width='32' /></A></td> | |
37 | <td class='online-navigation'><a href="modindex.html" title="Module Index"><img src='../icons/modules.png' | |
38 | border='0' height='32' alt='Module Index' width='32' /></a></td> | |
39 | <td class='online-navigation'><a rel="index" title="Index" | |
40 | href="genindex.html"><img src='../icons/index.png' | |
41 | border='0' height='32' alt='Index' width='32' /></A></td> | |
42 | </tr></table> | |
43 | <div class='online-navigation'> | |
44 | <b class="navlabel">Previous:</b> | |
45 | <a class="sectref" rel="prev" href="sequence-matcher.html">4.4.1 SequenceMatcher Objects</A> | |
46 | <b class="navlabel">Up:</b> | |
47 | <a class="sectref" rel="parent" href="module-difflib.html">4.4 difflib </A> | |
48 | <b class="navlabel">Next:</b> | |
49 | <a class="sectref" rel="next" href="differ-objects.html">4.4.3 Differ Objects</A> | |
50 | </div> | |
51 | <hr /></div> | |
52 | </DIV> | |
53 | <!--End of Navigation Panel--> | |
54 | ||
55 | <H2><A NAME="SECTION006420000000000000000"></A><A NAME="sequencematcher-examples"></A> | |
56 | <BR> | |
57 | 4.4.2 SequenceMatcher Examples | |
58 | </H2> | |
59 | ||
60 | <P> | |
61 | This example compares two strings, considering blanks to be ``junk:'' | |
62 | ||
63 | <P> | |
64 | <div class="verbatim"><pre> | |
65 | >>> s = SequenceMatcher(lambda x: x == " ", | |
66 | ... "private Thread currentThread;", | |
67 | ... "private volatile Thread currentThread;") | |
68 | </pre></div> | |
69 | ||
70 | <P> | |
71 | <tt class="method">ratio()</tt> returns a float in [0, 1], measuring the similarity | |
72 | of the sequences. As a rule of thumb, a <tt class="method">ratio()</tt> value over | |
73 | 0.6 means the sequences are close matches: | |
74 | ||
75 | <P> | |
76 | <div class="verbatim"><pre> | |
77 | >>> print round(s.ratio(), 3) | |
78 | 0.866 | |
79 | </pre></div> | |
80 | ||
81 | <P> | |
82 | If you're only interested in where the sequences match, | |
83 | <tt class="method">get_matching_blocks()</tt> is handy: | |
84 | ||
85 | <P> | |
86 | <div class="verbatim"><pre> | |
87 | >>> for block in s.get_matching_blocks(): | |
88 | ... print "a[%d] and b[%d] match for %d elements" % block | |
89 | a[0] and b[0] match for 8 elements | |
90 | a[8] and b[17] match for 6 elements | |
91 | a[14] and b[23] match for 15 elements | |
92 | a[29] and b[38] match for 0 elements | |
93 | </pre></div> | |
94 | ||
95 | <P> | |
96 | Note that the last tuple returned by <tt class="method">get_matching_blocks()</tt> is | |
97 | always a dummy, <code>(len(<var>a</var>), len(<var>b</var>), 0)</code>, and this is | |
98 | the only case in which the last tuple element (number of elements | |
99 | matched) is <code>0</code>. | |
100 | ||
101 | <P> | |
102 | If you want to know how to change the first sequence into the second, | |
103 | use <tt class="method">get_opcodes()</tt>: | |
104 | ||
105 | <P> | |
106 | <div class="verbatim"><pre> | |
107 | >>> for opcode in s.get_opcodes(): | |
108 | ... print "%6s a[%d:%d] b[%d:%d]" % opcode | |
109 | equal a[0:8] b[0:8] | |
110 | insert a[8:8] b[8:17] | |
111 | equal a[8:14] b[17:23] | |
112 | equal a[14:29] b[23:38] | |
113 | </pre></div> | |
114 | ||
115 | <P> | |
116 | See also the function <tt class="function">get_close_matches()</tt> in this module, | |
117 | which shows how simple code building on <tt class="class">SequenceMatcher</tt> can be | |
118 | used to do useful work. | |
119 | ||
120 | <P> | |
121 | ||
122 | <DIV CLASS="navigation"> | |
123 | <div class='online-navigation'> | |
124 | <p></p><hr /> | |
125 | <table align="center" width="100%" cellpadding="0" cellspacing="2"> | |
126 | <tr> | |
127 | <td class='online-navigation'><a rel="prev" title="4.4.1 SequenceMatcher Objects" | |
128 | href="sequence-matcher.html"><img src='../icons/previous.png' | |
129 | border='0' height='32' alt='Previous Page' width='32' /></A></td> | |
130 | <td class='online-navigation'><a rel="parent" title="4.4 difflib " | |
131 | href="module-difflib.html"><img src='../icons/up.png' | |
132 | border='0' height='32' alt='Up One Level' width='32' /></A></td> | |
133 | <td class='online-navigation'><a rel="next" title="4.4.3 Differ Objects" | |
134 | href="differ-objects.html"><img src='../icons/next.png' | |
135 | border='0' height='32' alt='Next Page' width='32' /></A></td> | |
136 | <td align="center" width="100%">Python Library Reference</td> | |
137 | <td class='online-navigation'><a rel="contents" title="Table of Contents" | |
138 | href="contents.html"><img src='../icons/contents.png' | |
139 | border='0' height='32' alt='Contents' width='32' /></A></td> | |
140 | <td class='online-navigation'><a href="modindex.html" title="Module Index"><img src='../icons/modules.png' | |
141 | border='0' height='32' alt='Module Index' width='32' /></a></td> | |
142 | <td class='online-navigation'><a rel="index" title="Index" | |
143 | href="genindex.html"><img src='../icons/index.png' | |
144 | border='0' height='32' alt='Index' width='32' /></A></td> | |
145 | </tr></table> | |
146 | <div class='online-navigation'> | |
147 | <b class="navlabel">Previous:</b> | |
148 | <a class="sectref" rel="prev" href="sequence-matcher.html">4.4.1 SequenceMatcher Objects</A> | |
149 | <b class="navlabel">Up:</b> | |
150 | <a class="sectref" rel="parent" href="module-difflib.html">4.4 difflib </A> | |
151 | <b class="navlabel">Next:</b> | |
152 | <a class="sectref" rel="next" href="differ-objects.html">4.4.3 Differ Objects</A> | |
153 | </div> | |
154 | </div> | |
155 | <hr /> | |
156 | <span class="release-info">Release 2.4.2, documentation updated on 28 September 2005.</span> | |
157 | </DIV> | |
158 | <!--End of Navigation Panel--> | |
159 | <ADDRESS> | |
160 | See <i><a href="about.html">About this document...</a></i> for information on suggesting changes. | |
161 | </ADDRESS> | |
162 | </BODY> | |
163 | </HTML> |