mirror of
https://github.com/python/cpython.git
synced 2025-07-23 11:15:24 +00:00

svn+ssh://pythondev@svn.python.org/python/trunk ................ r61724 | martin.v.loewis | 2008-03-22 01:01:12 +0100 (Sat, 22 Mar 2008) | 49 lines Merged revisions 61602-61723 via svnmerge from svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3 ........ r61626 | david.wolever | 2008-03-19 17:19:16 +0100 (Mi, 19 M?\195?\164r 2008) | 1 line Added fixer for implicit local imports. See #2414. ........ r61628 | david.wolever | 2008-03-19 17:57:43 +0100 (Mi, 19 M?\195?\164r 2008) | 1 line Added a class for tests which should not run if a particular import is found. ........ r61629 | collin.winter | 2008-03-19 17:58:19 +0100 (Mi, 19 M?\195?\164r 2008) | 1 line Two more relative import fixes in pgen2. ........ r61635 | david.wolever | 2008-03-19 20:16:03 +0100 (Mi, 19 M?\195?\164r 2008) | 1 line Fixed print fixer so it will do the Right Thing when it encounters __future__.print_function. 2to3 gets upset, though, so the tests have been commented out. ........ r61637 | david.wolever | 2008-03-19 21:37:17 +0100 (Mi, 19 M?\195?\164r 2008) | 3 lines Added a fixer for itertools imports (from itertools import imap, ifilterfalse --> from itertools import filterfalse) ........ r61645 | david.wolever | 2008-03-19 23:22:35 +0100 (Mi, 19 M?\195?\164r 2008) | 1 line SVN is happier when you add the files you create... -_-' ........ r61654 | david.wolever | 2008-03-20 01:09:56 +0100 (Do, 20 M?\195?\164r 2008) | 1 line Added an explicit sort order to fixers -- fixes problems like #2427 ........ r61664 | david.wolever | 2008-03-20 04:32:40 +0100 (Do, 20 M?\195?\164r 2008) | 3 lines Fixes #2428 -- comments are no longer eatten by __future__ fixer. ........ r61673 | david.wolever | 2008-03-20 17:22:40 +0100 (Do, 20 M?\195?\164r 2008) | 1 line Added 2to3 node pretty-printer ........ r61679 | david.wolever | 2008-03-20 20:50:42 +0100 (Do, 20 M?\195?\164r 2008) | 1 line Made node printing a little bit prettier ........ r61723 | martin.v.loewis | 2008-03-22 00:59:27 +0100 (Sa, 22 M?\195?\164r 2008) | 2 lines Fix whitespace. ........ ................ r61725 | martin.v.loewis | 2008-03-22 01:02:41 +0100 (Sat, 22 Mar 2008) | 2 lines Install lib2to3. ................ r61731 | facundo.batista | 2008-03-22 03:45:37 +0100 (Sat, 22 Mar 2008) | 4 lines Small fix that complicated the test actually when that test failed. ................ r61732 | alexandre.vassalotti | 2008-03-22 05:08:44 +0100 (Sat, 22 Mar 2008) | 2 lines Added warning for the removal of 'hotshot' in Py3k. ................ r61733 | georg.brandl | 2008-03-22 11:07:29 +0100 (Sat, 22 Mar 2008) | 4 lines #1918: document that weak references *to* an object are cleared before the object's __del__ is called, to ensure that the weak reference callback (if any) finds the object healthy. ................ r61734 | georg.brandl | 2008-03-22 11:56:23 +0100 (Sat, 22 Mar 2008) | 2 lines Activate the Sphinx doctest extension and convert howto/functional to use it. ................ r61735 | georg.brandl | 2008-03-22 11:58:38 +0100 (Sat, 22 Mar 2008) | 2 lines Allow giving source names on the cmdline. ................ r61737 | georg.brandl | 2008-03-22 12:00:48 +0100 (Sat, 22 Mar 2008) | 2 lines Fixup this HOWTO's doctest blocks so that they can be run with sphinx' doctest builder. ................ r61739 | georg.brandl | 2008-03-22 12:47:10 +0100 (Sat, 22 Mar 2008) | 2 lines Test decimal.rst doctests as far as possible with sphinx doctest. ................ r61741 | georg.brandl | 2008-03-22 13:04:26 +0100 (Sat, 22 Mar 2008) | 2 lines Make doctests in re docs usable with sphinx' doctest. ................ r61743 | georg.brandl | 2008-03-22 13:59:37 +0100 (Sat, 22 Mar 2008) | 2 lines Make more doctests in pprint docs testable. ................ r61744 | georg.brandl | 2008-03-22 14:07:06 +0100 (Sat, 22 Mar 2008) | 2 lines No need to specify explicit "doctest_block" anymore. ................ r61753 | georg.brandl | 2008-03-22 21:08:43 +0100 (Sat, 22 Mar 2008) | 2 lines Fix-up syntax problems. ................ r61761 | georg.brandl | 2008-03-22 22:06:20 +0100 (Sat, 22 Mar 2008) | 4 lines Make collections' doctests executable. (The <BLANKLINE>s will be stripped from presentation output.) ................ r61765 | georg.brandl | 2008-03-22 22:21:57 +0100 (Sat, 22 Mar 2008) | 2 lines Test doctests in datetime docs. ................ r61766 | georg.brandl | 2008-03-22 22:26:44 +0100 (Sat, 22 Mar 2008) | 2 lines Test doctests in operator docs. ................ r61767 | georg.brandl | 2008-03-22 22:38:33 +0100 (Sat, 22 Mar 2008) | 2 lines Enable doctests in functions.rst. Already found two errors :) ................ r61769 | georg.brandl | 2008-03-22 23:04:10 +0100 (Sat, 22 Mar 2008) | 3 lines Enable doctest running for several other documents. We have now over 640 doctests that are run with "make doctest". ................ r61773 | raymond.hettinger | 2008-03-23 01:55:46 +0100 (Sun, 23 Mar 2008) | 1 line Simplify demo code. ................ r61776 | neal.norwitz | 2008-03-23 04:43:33 +0100 (Sun, 23 Mar 2008) | 7 lines Try to make this test a little more robust and not fail with: timeout (10.0025) is more than 2 seconds more than expected (0.001) I'm assuming this problem is caused by DNS lookup. This change does a DNS lookup of the hostname before trying to connect, so the time is not included. ................ r61777 | neal.norwitz | 2008-03-23 05:08:30 +0100 (Sun, 23 Mar 2008) | 1 line Speed up the test by avoiding socket timeouts. ................ r61778 | neal.norwitz | 2008-03-23 05:43:09 +0100 (Sun, 23 Mar 2008) | 1 line Skip the epoll test if epoll() does not work ................ r61780 | neal.norwitz | 2008-03-23 06:47:20 +0100 (Sun, 23 Mar 2008) | 1 line Suppress failure (to avoid a flaky test) if we cannot connect to svn.python.org ................ r61781 | neal.norwitz | 2008-03-23 07:13:25 +0100 (Sun, 23 Mar 2008) | 4 lines Move itertools before future_builtins since the latter depends on the former. From a clean build importing future_builtins would fail since itertools wasn't built yet. ................ r61782 | neal.norwitz | 2008-03-23 07:16:04 +0100 (Sun, 23 Mar 2008) | 1 line Try to prevent the alarm going off early in tearDown ................ r61783 | neal.norwitz | 2008-03-23 07:19:57 +0100 (Sun, 23 Mar 2008) | 4 lines Remove compiler warnings (on Alpha at least) about using chars as array subscripts. Using chars are dangerous b/c they are signed on some platforms and unsigned on others. ................ r61788 | georg.brandl | 2008-03-23 09:05:30 +0100 (Sun, 23 Mar 2008) | 2 lines Make the doctests presentation-friendlier. ................ r61793 | amaury.forgeotdarc | 2008-03-23 10:55:29 +0100 (Sun, 23 Mar 2008) | 4 lines #1477: ur'\U0010FFFF' raised in narrow unicode builds. Corrected the raw-unicode-escape codec to use UTF-16 surrogates in this case, just like the unicode-escape codec. ................ r61796 | raymond.hettinger | 2008-03-23 14:32:32 +0100 (Sun, 23 Mar 2008) | 1 line Issue 1681432: Add triangular distribution the random module. ................ r61807 | raymond.hettinger | 2008-03-23 20:37:53 +0100 (Sun, 23 Mar 2008) | 4 lines Adopt Nick's suggestion for useful default arguments. Clean-up floating point issues by adding true division and float constants. ................ r61813 | gregory.p.smith | 2008-03-23 22:04:43 +0100 (Sun, 23 Mar 2008) | 6 lines Fix gzip to deal with CRC's being signed values in Python 2.x properly and to read 32bit values as unsigned to start with rather than applying signedness fixups allover the place afterwards. This hopefully fixes the test_tarfile failure on the alpha/tru64 buildbot. ................
743 lines
29 KiB
ReStructuredText
743 lines
29 KiB
ReStructuredText
:mod:`difflib` --- Helpers for computing deltas
|
|
===============================================
|
|
|
|
.. module:: difflib
|
|
:synopsis: Helpers for computing differences between objects.
|
|
.. moduleauthor:: Tim Peters <tim_one@users.sourceforge.net>
|
|
.. sectionauthor:: Tim Peters <tim_one@users.sourceforge.net>
|
|
.. Markup by Fred L. Drake, Jr. <fdrake@acm.org>
|
|
|
|
.. testsetup::
|
|
|
|
import sys
|
|
from difflib import *
|
|
|
|
This module 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 :mod:`filecmp` module.
|
|
|
|
.. class:: SequenceMatcher
|
|
|
|
This is a flexible class for comparing pairs of sequences of any type, so long
|
|
as the sequence elements are :term:`hashable`. The basic algorithm predates, and is a
|
|
little fancier than, an algorithm published in the late 1980's by Ratcliff and
|
|
Obershelp under the hyperbolic name "gestalt pattern matching." 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 same
|
|
idea is then applied recursively to the pieces of the sequences to the left and
|
|
to the right of the matching subsequence. This does not yield minimal edit
|
|
sequences, but does tend to yield matches that "look right" to people.
|
|
|
|
**Timing:** The basic Ratcliff-Obershelp algorithm is cubic time in the worst
|
|
case and quadratic time in the expected case. :class:`SequenceMatcher` is
|
|
quadratic time for the worst case and has expected-case behavior dependent in a
|
|
complicated way on how many elements the sequences have in common; best case
|
|
time is linear.
|
|
|
|
|
|
.. class:: Differ
|
|
|
|
This is a class for comparing sequences of lines of text, and producing
|
|
human-readable differences or deltas. Differ uses :class:`SequenceMatcher`
|
|
both to compare sequences of lines, and to compare sequences of characters
|
|
within similar (near-matching) lines.
|
|
|
|
Each line of a :class:`Differ` delta begins with a two-letter code:
|
|
|
|
+----------+-------------------------------------------+
|
|
| Code | Meaning |
|
|
+==========+===========================================+
|
|
| ``'- '`` | line unique to sequence 1 |
|
|
+----------+-------------------------------------------+
|
|
| ``'+ '`` | line unique to sequence 2 |
|
|
+----------+-------------------------------------------+
|
|
| ``' '`` | line common to both sequences |
|
|
+----------+-------------------------------------------+
|
|
| ``'? '`` | line not present in either input sequence |
|
|
+----------+-------------------------------------------+
|
|
|
|
Lines beginning with '``?``' attempt to guide the eye to intraline differences,
|
|
and were not present in either input sequence. These lines can be confusing if
|
|
the sequences contain tab characters.
|
|
|
|
|
|
.. class:: HtmlDiff
|
|
|
|
This class can be used to create an HTML table (or a complete HTML file
|
|
containing the table) showing a side by side, line by line comparison of text
|
|
with inter-line and intra-line change highlights. The table can be generated in
|
|
either full or contextual difference mode.
|
|
|
|
The constructor for this class is:
|
|
|
|
|
|
.. function:: __init__([tabsize][, wrapcolumn][, linejunk][, charjunk])
|
|
|
|
Initializes instance of :class:`HtmlDiff`.
|
|
|
|
*tabsize* is an optional keyword argument to specify tab stop spacing and
|
|
defaults to ``8``.
|
|
|
|
*wrapcolumn* is an optional keyword to specify column number where lines are
|
|
broken and wrapped, defaults to ``None`` where lines are not wrapped.
|
|
|
|
*linejunk* and *charjunk* are optional keyword arguments passed into ``ndiff()``
|
|
(used by :class:`HtmlDiff` to generate the side by side HTML differences). See
|
|
``ndiff()`` documentation for argument default values and descriptions.
|
|
|
|
The following methods are public:
|
|
|
|
|
|
.. function:: make_file(fromlines, tolines [, fromdesc][, todesc][, context][, numlines])
|
|
|
|
Compares *fromlines* and *tolines* (lists of strings) and returns a string which
|
|
is a complete HTML file containing a table showing line by line differences with
|
|
inter-line and intra-line changes highlighted.
|
|
|
|
*fromdesc* and *todesc* are optional keyword arguments to specify from/to file
|
|
column header strings (both default to an empty string).
|
|
|
|
*context* and *numlines* are both optional keyword arguments. Set *context* to
|
|
``True`` when contextual differences are to be shown, else the default is
|
|
``False`` to show the full files. *numlines* defaults to ``5``. When *context*
|
|
is ``True`` *numlines* controls the number of context lines which surround the
|
|
difference highlights. When *context* is ``False`` *numlines* controls the
|
|
number of lines which are shown before a difference highlight when using the
|
|
"next" hyperlinks (setting to zero would cause the "next" hyperlinks to place
|
|
the next difference highlight at the top of the browser without any leading
|
|
context).
|
|
|
|
|
|
.. function:: make_table(fromlines, tolines [, fromdesc][, todesc][, context][, numlines])
|
|
|
|
Compares *fromlines* and *tolines* (lists of strings) and returns a string which
|
|
is a complete HTML table showing line by line differences with inter-line and
|
|
intra-line changes highlighted.
|
|
|
|
The arguments for this method are the same as those for the :meth:`make_file`
|
|
method.
|
|
|
|
:file:`Tools/scripts/diff.py` is a command-line front-end to this class and
|
|
contains a good example of its use.
|
|
|
|
|
|
.. function:: context_diff(a, b[, fromfile][, tofile][, fromfiledate][, tofiledate][, n][, lineterm])
|
|
|
|
Compare *a* and *b* (lists of strings); return a delta (a :term:`generator`
|
|
generating the delta lines) in context diff format.
|
|
|
|
Context diffs are a compact way of showing just the lines that have changed plus
|
|
a few lines of context. The changes are shown in a before/after style. The
|
|
number of context lines is set by *n* which defaults to three.
|
|
|
|
By default, the diff control lines (those with ``***`` or ``---``) are created
|
|
with a trailing newline. This is helpful so that inputs created from
|
|
:func:`file.readlines` result in diffs that are suitable for use with
|
|
:func:`file.writelines` since both the inputs and outputs have trailing
|
|
newlines.
|
|
|
|
For inputs that do not have trailing newlines, set the *lineterm* argument to
|
|
``""`` so that the output will be uniformly newline free.
|
|
|
|
The context diff format normally has a header for filenames and modification
|
|
times. Any or all of these may be specified using strings for *fromfile*,
|
|
*tofile*, *fromfiledate*, and *tofiledate*. The modification times are normally
|
|
expressed in the format returned by :func:`time.ctime`. If not specified, the
|
|
strings default to blanks.
|
|
|
|
>>> s1 = ['bacon\n', 'eggs\n', 'ham\n', 'guido\n']
|
|
>>> s2 = ['python\n', 'eggy\n', 'hamster\n', 'guido\n']
|
|
>>> for line in context_diff(s1, s2, fromfile='before.py', tofile='after.py'):
|
|
... sys.stdout.write(line) # doctest: +NORMALIZE_WHITESPACE
|
|
*** before.py
|
|
--- after.py
|
|
***************
|
|
*** 1,4 ****
|
|
! bacon
|
|
! eggs
|
|
! ham
|
|
guido
|
|
--- 1,4 ----
|
|
! python
|
|
! eggy
|
|
! hamster
|
|
guido
|
|
|
|
See :ref:`difflib-interface` for a more detailed example.
|
|
|
|
|
|
.. function:: get_close_matches(word, possibilities[, n][, cutoff])
|
|
|
|
Return a list of the best "good enough" matches. *word* is a sequence for which
|
|
close matches are desired (typically a string), and *possibilities* is a list of
|
|
sequences against which to match *word* (typically a list of strings).
|
|
|
|
Optional argument *n* (default ``3``) is the maximum number of close matches to
|
|
return; *n* must be greater than ``0``.
|
|
|
|
Optional argument *cutoff* (default ``0.6``) is a float in the range [0, 1].
|
|
Possibilities that don't score at least that similar to *word* are ignored.
|
|
|
|
The best (no more than *n*) matches among the possibilities are returned in a
|
|
list, sorted by similarity score, most similar first.
|
|
|
|
>>> get_close_matches('appel', ['ape', 'apple', 'peach', 'puppy'])
|
|
['apple', 'ape']
|
|
>>> import keyword
|
|
>>> get_close_matches('wheel', keyword.kwlist)
|
|
['while']
|
|
>>> get_close_matches('apple', keyword.kwlist)
|
|
[]
|
|
>>> get_close_matches('accept', keyword.kwlist)
|
|
['except']
|
|
|
|
|
|
.. function:: ndiff(a, b[, linejunk][, charjunk])
|
|
|
|
Compare *a* and *b* (lists of strings); return a :class:`Differ`\ -style
|
|
delta (a :term:`generator` generating the delta lines).
|
|
|
|
Optional keyword parameters *linejunk* and *charjunk* are for filter functions
|
|
(or ``None``):
|
|
|
|
*linejunk*: A function that accepts a single string argument, and returns true
|
|
if the string is junk, or false if not. The default is (``None``), starting with
|
|
Python 2.3. Before then, the default was the module-level function
|
|
:func:`IS_LINE_JUNK`, which filters out lines without visible characters, except
|
|
for at most one pound character (``'#'``). As of Python 2.3, the underlying
|
|
:class:`SequenceMatcher` class does a dynamic analysis of which lines are so
|
|
frequent as to constitute noise, and this usually works better than the pre-2.3
|
|
default.
|
|
|
|
*charjunk*: A function that accepts a character (a string of length 1), and
|
|
returns if the character is junk, or false if not. The default is module-level
|
|
function :func:`IS_CHARACTER_JUNK`, which filters out whitespace characters (a
|
|
blank or tab; note: bad idea to include newline in this!).
|
|
|
|
:file:`Tools/scripts/ndiff.py` is a command-line front-end to this function.
|
|
|
|
>>> diff = ndiff('one\ntwo\nthree\n'.splitlines(1),
|
|
... 'ore\ntree\nemu\n'.splitlines(1))
|
|
>>> print(''.join(diff), end="")
|
|
- one
|
|
? ^
|
|
+ ore
|
|
? ^
|
|
- two
|
|
- three
|
|
? -
|
|
+ tree
|
|
+ emu
|
|
|
|
|
|
.. function:: restore(sequence, which)
|
|
|
|
Return one of the two sequences that generated a delta.
|
|
|
|
Given a *sequence* produced by :meth:`Differ.compare` or :func:`ndiff`, extract
|
|
lines originating from file 1 or 2 (parameter *which*), stripping off line
|
|
prefixes.
|
|
|
|
Example:
|
|
|
|
>>> diff = ndiff('one\ntwo\nthree\n'.splitlines(1),
|
|
... 'ore\ntree\nemu\n'.splitlines(1))
|
|
>>> diff = list(diff) # materialize the generated delta into a list
|
|
>>> print(''.join(restore(diff, 1)), end="")
|
|
one
|
|
two
|
|
three
|
|
>>> print(''.join(restore(diff, 2)), end="")
|
|
ore
|
|
tree
|
|
emu
|
|
|
|
|
|
.. function:: unified_diff(a, b[, fromfile][, tofile][, fromfiledate][, tofiledate][, n][, lineterm])
|
|
|
|
Compare *a* and *b* (lists of strings); return a delta (a :term:`generator`
|
|
generating the delta lines) in unified diff format.
|
|
|
|
Unified diffs are a compact way of showing just the lines that have changed plus
|
|
a few lines of context. The changes are shown in a inline style (instead of
|
|
separate before/after blocks). The number of context lines is set by *n* which
|
|
defaults to three.
|
|
|
|
By default, the diff control lines (those with ``---``, ``+++``, or ``@@``) are
|
|
created with a trailing newline. This is helpful so that inputs created from
|
|
:func:`file.readlines` result in diffs that are suitable for use with
|
|
:func:`file.writelines` since both the inputs and outputs have trailing
|
|
newlines.
|
|
|
|
For inputs that do not have trailing newlines, set the *lineterm* argument to
|
|
``""`` so that the output will be uniformly newline free.
|
|
|
|
The context diff format normally has a header for filenames and modification
|
|
times. Any or all of these may be specified using strings for *fromfile*,
|
|
*tofile*, *fromfiledate*, and *tofiledate*. The modification times are normally
|
|
expressed in the format returned by :func:`time.ctime`. If not specified, the
|
|
strings default to blanks.
|
|
|
|
|
|
>>> s1 = ['bacon\n', 'eggs\n', 'ham\n', 'guido\n']
|
|
>>> s2 = ['python\n', 'eggy\n', 'hamster\n', 'guido\n']
|
|
>>> for line in unified_diff(s1, s2, fromfile='before.py', tofile='after.py'):
|
|
... sys.stdout.write(line) # doctest: +NORMALIZE_WHITESPACE
|
|
--- before.py
|
|
+++ after.py
|
|
@@ -1,4 +1,4 @@
|
|
-bacon
|
|
-eggs
|
|
-ham
|
|
+python
|
|
+eggy
|
|
+hamster
|
|
guido
|
|
|
|
See :ref:`difflib-interface` for a more detailed example.
|
|
|
|
|
|
.. function:: IS_LINE_JUNK(line)
|
|
|
|
Return true for ignorable lines. The line *line* is ignorable if *line* is
|
|
blank or contains a single ``'#'``, otherwise it is not ignorable. Used as a
|
|
default for parameter *linejunk* in :func:`ndiff` before Python 2.3.
|
|
|
|
|
|
.. function:: IS_CHARACTER_JUNK(ch)
|
|
|
|
Return true for ignorable characters. The character *ch* is ignorable if *ch*
|
|
is a space or tab, otherwise it is not ignorable. Used as a default for
|
|
parameter *charjunk* in :func:`ndiff`.
|
|
|
|
|
|
.. seealso::
|
|
|
|
`Pattern Matching: The Gestalt Approach <http://www.ddj.com/184407970?pgno=5>`_
|
|
Discussion of a similar algorithm by John W. Ratcliff and D. E. Metzener. This
|
|
was published in `Dr. Dobb's Journal <http://www.ddj.com/>`_ in July, 1988.
|
|
|
|
|
|
.. _sequence-matcher:
|
|
|
|
SequenceMatcher Objects
|
|
-----------------------
|
|
|
|
The :class:`SequenceMatcher` class has this constructor:
|
|
|
|
|
|
.. class:: SequenceMatcher([isjunk[, a[, b]]])
|
|
|
|
Optional argument *isjunk* must be ``None`` (the default) or a one-argument
|
|
function that takes a sequence element and returns true if and only if the
|
|
element is "junk" and should be ignored. Passing ``None`` for *isjunk* is
|
|
equivalent to passing ``lambda x: 0``; in other words, no elements are ignored.
|
|
For example, pass::
|
|
|
|
lambda x: x in " \t"
|
|
|
|
if you're comparing lines as sequences of characters, and don't want to synch up
|
|
on blanks or hard tabs.
|
|
|
|
The optional arguments *a* and *b* are sequences to be compared; both default to
|
|
empty strings. The elements of both sequences must be :term:`hashable`.
|
|
|
|
:class:`SequenceMatcher` objects have the following methods:
|
|
|
|
|
|
.. method:: SequenceMatcher.set_seqs(a, b)
|
|
|
|
Set the two sequences to be compared.
|
|
|
|
:class:`SequenceMatcher` computes and caches detailed information about the
|
|
second sequence, so if you want to compare one sequence against many sequences,
|
|
use :meth:`set_seq2` to set the commonly used sequence once and call
|
|
:meth:`set_seq1` repeatedly, once for each of the other sequences.
|
|
|
|
|
|
.. method:: SequenceMatcher.set_seq1(a)
|
|
|
|
Set the first sequence to be compared. The second sequence to be compared is
|
|
not changed.
|
|
|
|
|
|
.. method:: SequenceMatcher.set_seq2(b)
|
|
|
|
Set the second sequence to be compared. The first sequence to be compared is
|
|
not changed.
|
|
|
|
|
|
.. method:: SequenceMatcher.find_longest_match(alo, ahi, blo, bhi)
|
|
|
|
Find longest matching block in ``a[alo:ahi]`` and ``b[blo:bhi]``.
|
|
|
|
If *isjunk* was omitted or ``None``, :meth:`find_longest_match` returns ``(i, j,
|
|
k)`` such that ``a[i:i+k]`` is equal to ``b[j:j+k]``, where ``alo <= i <= i+k <=
|
|
ahi`` and ``blo <= j <= j+k <= bhi``. For all ``(i', j', k')`` meeting those
|
|
conditions, the additional conditions ``k >= k'``, ``i <= i'``, and if ``i ==
|
|
i'``, ``j <= j'`` are also met. In other words, of all maximal matching blocks,
|
|
return one that starts earliest in *a*, and of all those maximal matching blocks
|
|
that start earliest in *a*, return the one that starts earliest in *b*.
|
|
|
|
>>> s = SequenceMatcher(None, " abcd", "abcd abcd")
|
|
>>> s.find_longest_match(0, 5, 0, 9)
|
|
Match(a=0, b=4, size=5)
|
|
|
|
If *isjunk* was provided, first the longest matching block is determined as
|
|
above, but with the additional restriction that no junk element appears in the
|
|
block. Then that block is extended as far as possible by matching (only) junk
|
|
elements on both sides. So the resulting block never matches on junk except as
|
|
identical junk happens to be adjacent to an interesting match.
|
|
|
|
Here's the same example as before, but considering blanks to be junk. That
|
|
prevents ``' abcd'`` from matching the ``' abcd'`` at the tail end of the second
|
|
sequence directly. Instead only the ``'abcd'`` can match, and matches the
|
|
leftmost ``'abcd'`` in the second sequence:
|
|
|
|
>>> s = SequenceMatcher(lambda x: x==" ", " abcd", "abcd abcd")
|
|
>>> s.find_longest_match(0, 5, 0, 9)
|
|
Match(a=1, b=0, size=4)
|
|
|
|
If no blocks match, this returns ``(alo, blo, 0)``.
|
|
|
|
.. versionchanged:: 2.6
|
|
This method returns a :term:`named tuple` ``Match(a, b, size)``.
|
|
|
|
|
|
.. method:: SequenceMatcher.get_matching_blocks()
|
|
|
|
Return list of triples describing matching subsequences. Each triple is of the
|
|
form ``(i, j, n)``, and means that ``a[i:i+n] == b[j:j+n]``. The triples are
|
|
monotonically increasing in *i* and *j*.
|
|
|
|
The last triple is a dummy, and has the value ``(len(a), len(b), 0)``. It is
|
|
the only triple with ``n == 0``. If ``(i, j, n)`` and ``(i', j', n')`` are
|
|
adjacent triples in the list, and the second is not the last triple in the list,
|
|
then ``i+n != i'`` or ``j+n != j'``; in other words, adjacent triples always
|
|
describe non-adjacent equal blocks.
|
|
|
|
.. XXX Explain why a dummy is used!
|
|
|
|
.. doctest::
|
|
|
|
>>> s = SequenceMatcher(None, "abxcd", "abcd")
|
|
>>> s.get_matching_blocks()
|
|
[Match(a=0, b=0, size=2), Match(a=3, b=2, size=2), Match(a=5, b=4, size=0)]
|
|
|
|
|
|
.. method:: SequenceMatcher.get_opcodes()
|
|
|
|
Return list of 5-tuples describing how to turn *a* into *b*. Each tuple is of
|
|
the form ``(tag, i1, i2, j1, j2)``. The first tuple has ``i1 == j1 == 0``, and
|
|
remaining tuples have *i1* equal to the *i2* from the preceding tuple, and,
|
|
likewise, *j1* equal to the previous *j2*.
|
|
|
|
The *tag* values are strings, with these meanings:
|
|
|
|
+---------------+---------------------------------------------+
|
|
| Value | Meaning |
|
|
+===============+=============================================+
|
|
| ``'replace'`` | ``a[i1:i2]`` should be replaced by |
|
|
| | ``b[j1:j2]``. |
|
|
+---------------+---------------------------------------------+
|
|
| ``'delete'`` | ``a[i1:i2]`` should be deleted. Note that |
|
|
| | ``j1 == j2`` in this case. |
|
|
+---------------+---------------------------------------------+
|
|
| ``'insert'`` | ``b[j1:j2]`` should be inserted at |
|
|
| | ``a[i1:i1]``. Note that ``i1 == i2`` in |
|
|
| | this case. |
|
|
+---------------+---------------------------------------------+
|
|
| ``'equal'`` | ``a[i1:i2] == b[j1:j2]`` (the sub-sequences |
|
|
| | are equal). |
|
|
+---------------+---------------------------------------------+
|
|
|
|
For example:
|
|
|
|
>>> a = "qabxcd"
|
|
>>> b = "abycdf"
|
|
>>> s = SequenceMatcher(None, a, b)
|
|
>>> for tag, i1, i2, j1, j2 in s.get_opcodes():
|
|
... print(("%7s a[%d:%d] (%s) b[%d:%d] (%s)" %
|
|
... (tag, i1, i2, a[i1:i2], j1, j2, b[j1:j2])))
|
|
delete a[0:1] (q) b[0:0] ()
|
|
equal a[1:3] (ab) b[0:2] (ab)
|
|
replace a[3:4] (x) b[2:3] (y)
|
|
equal a[4:6] (cd) b[3:5] (cd)
|
|
insert a[6:6] () b[5:6] (f)
|
|
|
|
|
|
.. method:: SequenceMatcher.get_grouped_opcodes([n])
|
|
|
|
Return a :term:`generator` of groups with up to *n* lines of context.
|
|
|
|
Starting with the groups returned by :meth:`get_opcodes`, this method splits out
|
|
smaller change clusters and eliminates intervening ranges which have no changes.
|
|
|
|
The groups are returned in the same format as :meth:`get_opcodes`.
|
|
|
|
|
|
.. method:: SequenceMatcher.ratio()
|
|
|
|
Return a measure of the sequences' similarity as a float in the range [0, 1].
|
|
|
|
Where T is the total number of elements in both sequences, and M is the number
|
|
of matches, this is 2.0\*M / T. Note that this is ``1.0`` if the sequences are
|
|
identical, and ``0.0`` if they have nothing in common.
|
|
|
|
This is expensive to compute if :meth:`get_matching_blocks` or
|
|
:meth:`get_opcodes` hasn't already been called, in which case you may want to
|
|
try :meth:`quick_ratio` or :meth:`real_quick_ratio` first to get an upper bound.
|
|
|
|
|
|
.. method:: SequenceMatcher.quick_ratio()
|
|
|
|
Return an upper bound on :meth:`ratio` relatively quickly.
|
|
|
|
This isn't defined beyond that it is an upper bound on :meth:`ratio`, and is
|
|
faster to compute.
|
|
|
|
|
|
.. method:: SequenceMatcher.real_quick_ratio()
|
|
|
|
Return an upper bound on :meth:`ratio` very quickly.
|
|
|
|
This isn't defined beyond that it is an upper bound on :meth:`ratio`, and is
|
|
faster to compute than either :meth:`ratio` or :meth:`quick_ratio`.
|
|
|
|
The three methods that return the ratio of matching to total characters can give
|
|
different results due to differing levels of approximation, although
|
|
:meth:`quick_ratio` and :meth:`real_quick_ratio` are always at least as large as
|
|
:meth:`ratio`:
|
|
|
|
>>> s = SequenceMatcher(None, "abcd", "bcde")
|
|
>>> s.ratio()
|
|
0.75
|
|
>>> s.quick_ratio()
|
|
0.75
|
|
>>> s.real_quick_ratio()
|
|
1.0
|
|
|
|
|
|
.. _sequencematcher-examples:
|
|
|
|
SequenceMatcher Examples
|
|
------------------------
|
|
|
|
This example compares two strings, considering blanks to be "junk:"
|
|
|
|
>>> s = SequenceMatcher(lambda x: x == " ",
|
|
... "private Thread currentThread;",
|
|
... "private volatile Thread currentThread;")
|
|
|
|
:meth:`ratio` returns a float in [0, 1], measuring the similarity of the
|
|
sequences. As a rule of thumb, a :meth:`ratio` value over 0.6 means the
|
|
sequences are close matches:
|
|
|
|
>>> print(round(s.ratio(), 3))
|
|
0.866
|
|
|
|
If you're only interested in where the sequences match,
|
|
:meth:`get_matching_blocks` is handy:
|
|
|
|
>>> for block in s.get_matching_blocks():
|
|
... print("a[%d] and b[%d] match for %d elements" % block)
|
|
a[0] and b[0] match for 8 elements
|
|
a[8] and b[17] match for 21 elements
|
|
a[29] and b[38] match for 0 elements
|
|
|
|
Note that the last tuple returned by :meth:`get_matching_blocks` is always a
|
|
dummy, ``(len(a), len(b), 0)``, and this is the only case in which the last
|
|
tuple element (number of elements matched) is ``0``.
|
|
|
|
If you want to know how to change the first sequence into the second, use
|
|
:meth:`get_opcodes`:
|
|
|
|
>>> for opcode in s.get_opcodes():
|
|
... print("%6s a[%d:%d] b[%d:%d]" % opcode)
|
|
equal a[0:8] b[0:8]
|
|
insert a[8:8] b[8:17]
|
|
equal a[8:29] b[17:38]
|
|
|
|
See also the function :func:`get_close_matches` in this module, which shows how
|
|
simple code building on :class:`SequenceMatcher` can be used to do useful work.
|
|
|
|
|
|
.. _differ-objects:
|
|
|
|
Differ Objects
|
|
--------------
|
|
|
|
Note that :class:`Differ`\ -generated deltas make no claim to be **minimal**
|
|
diffs. To the contrary, minimal diffs are often counter-intuitive, because they
|
|
synch up anywhere possible, sometimes accidental matches 100 pages apart.
|
|
Restricting synch points to contiguous matches preserves some notion of
|
|
locality, at the occasional cost of producing a longer diff.
|
|
|
|
The :class:`Differ` class has this constructor:
|
|
|
|
|
|
.. class:: Differ([linejunk[, charjunk]])
|
|
|
|
Optional keyword parameters *linejunk* and *charjunk* are for filter functions
|
|
(or ``None``):
|
|
|
|
*linejunk*: A function that accepts a single string argument, and returns true
|
|
if the string is junk. The default is ``None``, meaning that no line is
|
|
considered junk.
|
|
|
|
*charjunk*: A function that accepts a single character argument (a string of
|
|
length 1), and returns true if the character is junk. The default is ``None``,
|
|
meaning that no character is considered junk.
|
|
|
|
:class:`Differ` objects are used (deltas generated) via a single method:
|
|
|
|
|
|
.. method:: Differ.compare(a, b)
|
|
|
|
Compare two sequences of lines, and generate the delta (a sequence of lines).
|
|
|
|
Each sequence must contain individual single-line strings ending with newlines.
|
|
Such sequences can be obtained from the :meth:`readlines` method of file-like
|
|
objects. The delta generated also consists of newline-terminated strings, ready
|
|
to be printed as-is via the :meth:`writelines` method of a file-like object.
|
|
|
|
|
|
.. _differ-examples:
|
|
|
|
Differ Example
|
|
--------------
|
|
|
|
This example compares two texts. First we set up the texts, sequences of
|
|
individual single-line strings ending with newlines (such sequences can also be
|
|
obtained from the :meth:`readlines` method of file-like objects):
|
|
|
|
>>> text1 = ''' 1. Beautiful is better than ugly.
|
|
... 2. Explicit is better than implicit.
|
|
... 3. Simple is better than complex.
|
|
... 4. Complex is better than complicated.
|
|
... '''.splitlines(1)
|
|
>>> len(text1)
|
|
4
|
|
>>> text1[0][-1]
|
|
'\n'
|
|
>>> text2 = ''' 1. Beautiful is better than ugly.
|
|
... 3. Simple is better than complex.
|
|
... 4. Complicated is better than complex.
|
|
... 5. Flat is better than nested.
|
|
... '''.splitlines(1)
|
|
|
|
Next we instantiate a Differ object:
|
|
|
|
>>> d = Differ()
|
|
|
|
Note that when instantiating a :class:`Differ` object we may pass functions to
|
|
filter out line and character "junk." See the :meth:`Differ` constructor for
|
|
details.
|
|
|
|
Finally, we compare the two:
|
|
|
|
>>> result = list(d.compare(text1, text2))
|
|
|
|
``result`` is a list of strings, so let's pretty-print it:
|
|
|
|
>>> from pprint import pprint
|
|
>>> pprint(result)
|
|
[' 1. Beautiful is better than ugly.\n',
|
|
'- 2. Explicit is better than implicit.\n',
|
|
'- 3. Simple is better than complex.\n',
|
|
'+ 3. Simple is better than complex.\n',
|
|
'? ++\n',
|
|
'- 4. Complex is better than complicated.\n',
|
|
'? ^ ---- ^\n',
|
|
'+ 4. Complicated is better than complex.\n',
|
|
'? ++++ ^ ^\n',
|
|
'+ 5. Flat is better than nested.\n']
|
|
|
|
As a single multi-line string it looks like this:
|
|
|
|
>>> import sys
|
|
>>> sys.stdout.writelines(result)
|
|
1. Beautiful is better than ugly.
|
|
- 2. Explicit is better than implicit.
|
|
- 3. Simple is better than complex.
|
|
+ 3. Simple is better than complex.
|
|
? ++
|
|
- 4. Complex is better than complicated.
|
|
? ^ ---- ^
|
|
+ 4. Complicated is better than complex.
|
|
? ++++ ^ ^
|
|
+ 5. Flat is better than nested.
|
|
|
|
|
|
.. _difflib-interface:
|
|
|
|
A command-line interface to difflib
|
|
-----------------------------------
|
|
|
|
This example shows how to use difflib to create a ``diff``-like utility.
|
|
It is also contained in the Python source distribution, as
|
|
:file:`Tools/scripts/diff.py`.
|
|
|
|
.. testcode::
|
|
|
|
""" Command line interface to difflib.py providing diffs in four formats:
|
|
|
|
* ndiff: lists every line and highlights interline changes.
|
|
* context: highlights clusters of changes in a before/after format.
|
|
* unified: highlights clusters of changes in an inline format.
|
|
* html: generates side by side comparison with change highlights.
|
|
|
|
"""
|
|
|
|
import sys, os, time, difflib, optparse
|
|
|
|
def main():
|
|
# Configure the option parser
|
|
usage = "usage: %prog [options] fromfile tofile"
|
|
parser = optparse.OptionParser(usage)
|
|
parser.add_option("-c", action="store_true", default=False,
|
|
help='Produce a context format diff (default)')
|
|
parser.add_option("-u", action="store_true", default=False,
|
|
help='Produce a unified format diff')
|
|
hlp = 'Produce HTML side by side diff (can use -c and -l in conjunction)'
|
|
parser.add_option("-m", action="store_true", default=False, help=hlp)
|
|
parser.add_option("-n", action="store_true", default=False,
|
|
help='Produce a ndiff format diff')
|
|
parser.add_option("-l", "--lines", type="int", default=3,
|
|
help='Set number of context lines (default 3)')
|
|
(options, args) = parser.parse_args()
|
|
|
|
if len(args) == 0:
|
|
parser.print_help()
|
|
sys.exit(1)
|
|
if len(args) != 2:
|
|
parser.error("need to specify both a fromfile and tofile")
|
|
|
|
n = options.lines
|
|
fromfile, tofile = args # as specified in the usage string
|
|
|
|
# we're passing these as arguments to the diff function
|
|
fromdate = time.ctime(os.stat(fromfile).st_mtime)
|
|
todate = time.ctime(os.stat(tofile).st_mtime)
|
|
fromlines = open(fromfile, 'U').readlines()
|
|
tolines = open(tofile, 'U').readlines()
|
|
|
|
if options.u:
|
|
diff = difflib.unified_diff(fromlines, tolines, fromfile, tofile,
|
|
fromdate, todate, n=n)
|
|
elif options.n:
|
|
diff = difflib.ndiff(fromlines, tolines)
|
|
elif options.m:
|
|
diff = difflib.HtmlDiff().make_file(fromlines, tolines, fromfile,
|
|
tofile, context=options.c,
|
|
numlines=n)
|
|
else:
|
|
diff = difflib.context_diff(fromlines, tolines, fromfile, tofile,
|
|
fromdate, todate, n=n)
|
|
|
|
# we're using writelines because diff is a generator
|
|
sys.stdout.writelines(diff)
|
|
|
|
if __name__ == '__main__':
|
|
main()
|