#! /usr/bin/env python
"""
Module difflib -- helpers for computing deltas between objects.
Function get_close_matches(word, possibilities, n=3, cutoff=0.6):
Use SequenceMatcher to return list of the best "good enough" matches.
Function context_diff(a, b):
For two lists of strings, return a delta in context diff format.
Function mdiff(fromlines, tolines, chgfmt, linefmt, context=None, sep=None,
linejunk=None, charjunk=IS_CHARACTER_JUNK):
Returns generator yielding marked up from/to side by side difference lines.
Function ndiff(a, b):
Return a delta: the difference between `a` and `b` (lists of strings).
Function restore(delta, which):
Return one of the two sequences that generated an ndiff delta.
Function unified_diff(a, b):
For two lists of strings, return a delta in unified diff format.
Class SequenceMatcher:
A flexible class for comparing pairs of sequences of any type.
Class Differ:
For producing human-readable deltas from sequences of lines of text.
Class HtmlDiff:
For producing HTML side by side comparison with change highlights.
"""
__all__ = ['get_close_matches', 'ndiff', 'restore', 'SequenceMatcher',
'Differ','IS_CHARACTER_JUNK', 'IS_LINE_JUNK', 'context_diff',
'unified_diff', 'mdiff', 'HtmlDiff']
import heapq
def _calculate_ratio(matches, length):
if length:
return 2.0 * matches / length
return 1.0
class SequenceMatcher:
"""
SequenceMatcher is a flexible class for comparing pairs of sequences of
any type, so long as the sequence elements are 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 basic idea is to find
the longest contiguous matching subsequence that contains no "junk"
elements (R-O 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.
SequenceMatcher tries to compute a "human-friendly diff" between two
sequences. Unlike e.g. UNIX(tm) diff, the fundamental notion is the
longest *contiguous* & junk-free matching subsequence. That's what
catches peoples' eyes. The Windows(tm) windiff has another interesting
notion, pairing up elements that appear uniquely in each sequence.
That, and the method here, appear to yield more intuitive difference
reports than does diff. This method appears to be the least vulnerable
to synching up on blocks of "junk lines", though (like blank lines in
ordinary text files, or maybe "
" lines in HTML files). That may be
because this is the only method of the 3 that has a *concept* of
"junk" .
Example, comparing two strings, and considering blanks to be "junk":
>>> s = SequenceMatcher(lambda x: x == " ",
... "private Thread currentThread;",
... "private volatile Thread currentThread;")
>>>
.ratio() returns a float in [0, 1], measuring the "similarity" of the
sequences. As a rule of thumb, a .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,
.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 6 elements
a[14] and b[23] match for 15 elements
a[29] and b[38] match for 0 elements
Note that the last tuple returned by .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 .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[8:14] b[17:23]
equal a[14:29] b[23:38]
See the Differ class for a fancy human-friendly file differencer, which
uses SequenceMatcher both to compare sequences of lines, and to compare
sequences of characters within similar (near-matching) lines.
See also function get_close_matches() in this module, which shows how
simple code building on SequenceMatcher can be used to do useful work.
Timing: Basic R-O is cubic time worst case and quadratic time expected
case. 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.
Methods:
__init__(isjunk=None, a='', b='')
Construct a SequenceMatcher.
set_seqs(a, b)
Set the two sequences to be compared.
set_seq1(a)
Set the first sequence to be compared.
set_seq2(b)
Set the second sequence to be compared.
find_longest_match(alo, ahi, blo, bhi)
Find longest matching block in a[alo:ahi] and b[blo:bhi].
get_matching_blocks()
Return list of triples describing matching subsequences.
get_opcodes()
Return list of 5-tuples describing how to turn a into b.
ratio()
Return a measure of the sequences' similarity (float in [0,1]).
quick_ratio()
Return an upper bound on .ratio() relatively quickly.
real_quick_ratio()
Return an upper bound on ratio() very quickly.
"""
def __init__(self, isjunk=None, a='', b=''):
"""Construct a SequenceMatcher.
Optional arg isjunk is None (the default), or a one-argument
function that takes a sequence element and returns true iff the
element is junk. None is equivalent to passing "lambda x: 0", i.e.
no elements are considered to be junk. 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.
Optional arg a is the first of two sequences to be compared. By
default, an empty string. The elements of a must be hashable. See
also .set_seqs() and .set_seq1().
Optional arg b is the second of two sequences to be compared. By
default, an empty string. The elements of b must be hashable. See
also .set_seqs() and .set_seq2().
"""
# Members:
# a
# first sequence
# b
# second sequence; differences are computed as "what do
# we need to do to 'a' to change it into 'b'?"
# b2j
# for x in b, b2j[x] is a list of the indices (into b)
# at which x appears; junk elements do not appear
# fullbcount
# for x in b, fullbcount[x] == the number of times x
# appears in b; only materialized if really needed (used
# only for computing quick_ratio())
# matching_blocks
# a list of (i, j, k) triples, where a[i:i+k] == b[j:j+k];
# ascending & non-overlapping in i and in j; terminated by
# a dummy (len(a), len(b), 0) sentinel
# opcodes
# a list of (tag, i1, i2, j1, j2) tuples, where tag is
# one of
# 'replace' a[i1:i2] should be replaced by b[j1:j2]
# 'delete' a[i1:i2] should be deleted
# 'insert' b[j1:j2] should be inserted
# 'equal' a[i1:i2] == b[j1:j2]
# isjunk
# a user-supplied function taking a sequence element and
# returning true iff the element is "junk" -- this has
# subtle but helpful effects on the algorithm, which I'll
# get around to writing up someday <0.9 wink>.
# DON'T USE! Only __chain_b uses this. Use isbjunk.
# isbjunk
# for x in b, isbjunk(x) == isjunk(x) but much faster;
# it's really the has_key method of a hidden dict.
# DOES NOT WORK for x in a!
# isbpopular
# for x in b, isbpopular(x) is true iff b is reasonably long
# (at least 200 elements) and x accounts for more than 1% of
# its elements. DOES NOT WORK for x in a!
self.isjunk = isjunk
self.a = self.b = None
self.set_seqs(a, b)
def set_seqs(self, a, b):
"""Set the two sequences to be compared.
>>> s = SequenceMatcher()
>>> s.set_seqs("abcd", "bcde")
>>> s.ratio()
0.75
"""
self.set_seq1(a)
self.set_seq2(b)
def set_seq1(self, a):
"""Set the first sequence to be compared.
The second sequence to be compared is not changed.
>>> s = SequenceMatcher(None, "abcd", "bcde")
>>> s.ratio()
0.75
>>> s.set_seq1("bcde")
>>> s.ratio()
1.0
>>>
SequenceMatcher computes and caches detailed information about the
second sequence, so if you want to compare one sequence S against
many sequences, use .set_seq2(S) once and call .set_seq1(x)
repeatedly for each of the other sequences.
See also set_seqs() and set_seq2().
"""
if a is self.a:
return
self.a = a
self.matching_blocks = self.opcodes = None
def set_seq2(self, b):
"""Set the second sequence to be compared.
The first sequence to be compared is not changed.
>>> s = SequenceMatcher(None, "abcd", "bcde")
>>> s.ratio()
0.75
>>> s.set_seq2("abcd")
>>> s.ratio()
1.0
>>>
SequenceMatcher computes and caches detailed information about the
second sequence, so if you want to compare one sequence S against
many sequences, use .set_seq2(S) once and call .set_seq1(x)
repeatedly for each of the other sequences.
See also set_seqs() and set_seq1().
"""
if b is self.b:
return
self.b = b
self.matching_blocks = self.opcodes = None
self.fullbcount = None
self.__chain_b()
# For each element x in b, set b2j[x] to a list of the indices in
# b where x appears; the indices are in increasing order; note that
# the number of times x appears in b is len(b2j[x]) ...
# when self.isjunk is defined, junk elements don't show up in this
# map at all, which stops the central find_longest_match method
# from starting any matching block at a junk element ...
# also creates the fast isbjunk function ...
# b2j also does not contain entries for "popular" elements, meaning
# elements that account for more than 1% of the total elements, and
# when the sequence is reasonably large (>= 200 elements); this can
# be viewed as an adaptive notion of semi-junk, and yields an enormous
# speedup when, e.g., comparing program files with hundreds of
# instances of "return NULL;" ...
# note that this is only called when b changes; so for cross-product
# kinds of matches, it's best to call set_seq2 once, then set_seq1
# repeatedly
def __chain_b(self):
# Because isjunk is a user-defined (not C) function, and we test
# for junk a LOT, it's important to minimize the number of calls.
# Before the tricks described here, __chain_b was by far the most
# time-consuming routine in the whole module! If anyone sees
# Jim Roskind, thank him again for profile.py -- I never would
# have guessed that.
# The first trick is to build b2j ignoring the possibility
# of junk. I.e., we don't call isjunk at all yet. Throwing
# out the junk later is much cheaper than building b2j "right"
# from the start.
b = self.b
n = len(b)
self.b2j = b2j = {}
populardict = {}
for i, elt in enumerate(b):
if elt in b2j:
indices = b2j[elt]
if n >= 200 and len(indices) * 100 > n:
populardict[elt] = 1
del indices[:]
else:
indices.append(i)
else:
b2j[elt] = [i]
# Purge leftover indices for popular elements.
for elt in populardict:
del b2j[elt]
# Now b2j.keys() contains elements uniquely, and especially when
# the sequence is a string, that's usually a good deal smaller
# than len(string). The difference is the number of isjunk calls
# saved.
isjunk = self.isjunk
junkdict = {}
if isjunk:
for d in populardict, b2j:
for elt in d.keys():
if isjunk(elt):
junkdict[elt] = 1
del d[elt]
# Now for x in b, isjunk(x) == x in junkdict, but the
# latter is much faster. Note too that while there may be a
# lot of junk in the sequence, the number of *unique* junk
# elements is probably small. So the memory burden of keeping
# this dict alive is likely trivial compared to the size of b2j.
self.isbjunk = junkdict.has_key
self.isbpopular = populardict.has_key
def find_longest_match(self, alo, ahi, blo, bhi):
"""Find longest matching block in a[alo:ahi] and b[blo:bhi].
If isjunk is not defined:
Return (i,j,k) such that a[i:i+k] is equal to b[j:j+k], where
alo <= i <= i+k <= ahi
blo <= j <= j+k <= bhi
and for all (i',j',k') meeting those conditions,
k >= k'
i <= i'
and if i == i', j <= j'
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)
(0, 4, 5)
If isjunk is defined, 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)
(1, 0, 4)
If no blocks match, return (alo, blo, 0).
>>> s = SequenceMatcher(None, "ab", "c")
>>> s.find_longest_match(0, 2, 0, 1)
(0, 0, 0)
"""
# CAUTION: stripping common prefix or suffix would be incorrect.
# E.g.,
# ab
# acab
# Longest matching block is "ab", but if common prefix is
# stripped, it's "a" (tied with "b"). UNIX(tm) diff does so
# strip, so ends up claiming that ab is changed to acab by
# inserting "ca" in the middle. That's minimal but unintuitive:
# "it's obvious" that someone inserted "ac" at the front.
# Windiff ends up at the same place as diff, but by pairing up
# the unique 'b's and then matching the first two 'a's.
a, b, b2j, isbjunk = self.a, self.b, self.b2j, self.isbjunk
besti, bestj, bestsize = alo, blo, 0
# find longest junk-free match
# during an iteration of the loop, j2len[j] = length of longest
# junk-free match ending with a[i-1] and b[j]
j2len = {}
nothing = []
for i in xrange(alo, ahi):
# look at all instances of a[i] in b; note that because
# b2j has no junk keys, the loop is skipped if a[i] is junk
j2lenget = j2len.get
newj2len = {}
for j in b2j.get(a[i], nothing):
# a[i] matches b[j]
if j < blo:
continue
if j >= bhi:
break
k = newj2len[j] = j2lenget(j-1, 0) + 1
if k > bestsize:
besti, bestj, bestsize = i-k+1, j-k+1, k
j2len = newj2len
# Extend the best by non-junk elements on each end. In particular,
# "popular" non-junk elements aren't in b2j, which greatly speeds
# the inner loop above, but also means "the best" match so far
# doesn't contain any junk *or* popular non-junk elements.
while besti > alo and bestj > blo and \
not isbjunk(b[bestj-1]) and \
a[besti-1] == b[bestj-1]:
besti, bestj, bestsize = besti-1, bestj-1, bestsize+1
while besti+bestsize < ahi and bestj+bestsize < bhi and \
not isbjunk(b[bestj+bestsize]) and \
a[besti+bestsize] == b[bestj+bestsize]:
bestsize += 1
# Now that we have a wholly interesting match (albeit possibly
# empty!), we may as well suck up the matching junk on each
# side of it too. Can't think of a good reason not to, and it
# saves post-processing the (possibly considerable) expense of
# figuring out what to do with it. In the case of an empty
# interesting match, this is clearly the right thing to do,
# because no other kind of match is possible in the regions.
while besti > alo and bestj > blo and \
isbjunk(b[bestj-1]) and \
a[besti-1] == b[bestj-1]:
besti, bestj, bestsize = besti-1, bestj-1, bestsize+1
while besti+bestsize < ahi and bestj+bestsize < bhi and \
isbjunk(b[bestj+bestsize]) and \
a[besti+bestsize] == b[bestj+bestsize]:
bestsize = bestsize + 1
return besti, bestj, bestsize
def get_matching_blocks(self):
"""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 in j.
The last triple is a dummy, (len(a), len(b), 0), and is the only
triple with n==0.
>>> s = SequenceMatcher(None, "abxcd", "abcd")
>>> s.get_matching_blocks()
[(0, 0, 2), (3, 2, 2), (5, 4, 0)]
"""
if self.matching_blocks is not None:
return self.matching_blocks
self.matching_blocks = []
la, lb = len(self.a), len(self.b)
self.__helper(0, la, 0, lb, self.matching_blocks)
self.matching_blocks.append( (la, lb, 0) )
return self.matching_blocks
# builds list of matching blocks covering a[alo:ahi] and
# b[blo:bhi], appending them in increasing order to answer
def __helper(self, alo, ahi, blo, bhi, answer):
i, j, k = x = self.find_longest_match(alo, ahi, blo, bhi)
# a[alo:i] vs b[blo:j] unknown
# a[i:i+k] same as b[j:j+k]
# a[i+k:ahi] vs b[j+k:bhi] unknown
if k:
if alo < i and blo < j:
self.__helper(alo, i, blo, j, answer)
answer.append(x)
if i+k < ahi and j+k < bhi:
self.__helper(i+k, ahi, j+k, bhi, answer)
def get_opcodes(self):
"""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 == the i2 from the
tuple preceding it, and likewise for j1 == the previous j2.
The tags are strings, with these meanings:
'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]
>>> 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)
"""
if self.opcodes is not None:
return self.opcodes
i = j = 0
self.opcodes = answer = []
for ai, bj, size in self.get_matching_blocks():
# invariant: we've pumped out correct diffs to change
# a[:i] into b[:j], and the next matching block is
# a[ai:ai+size] == b[bj:bj+size]. So we need to pump
# out a diff to change a[i:ai] into b[j:bj], pump out
# the matching block, and move (i,j) beyond the match
tag = ''
if i < ai and j < bj:
tag = 'replace'
elif i < ai:
tag = 'delete'
elif j < bj:
tag = 'insert'
if tag:
answer.append( (tag, i, ai, j, bj) )
i, j = ai+size, bj+size
# the list of matching blocks is terminated by a
# sentinel with size 0
if size:
answer.append( ('equal', ai, i, bj, j) )
return answer
def get_grouped_opcodes(self, n=3):
""" Isolate change clusters by eliminating ranges with no changes.
Return a generator of groups with upto n lines of context.
Each group is in the same format as returned by get_opcodes().
>>> from pprint import pprint
>>> a = map(str, range(1,40))
>>> b = a[:]
>>> b[8:8] = ['i'] # Make an insertion
>>> b[20] += 'x' # Make a replacement
>>> b[23:28] = [] # Make a deletion
>>> b[30] += 'y' # Make another replacement
>>> pprint(list(SequenceMatcher(None,a,b).get_grouped_opcodes()))
[[('equal', 5, 8, 5, 8), ('insert', 8, 8, 8, 9), ('equal', 8, 11, 9, 12)],
[('equal', 16, 19, 17, 20),
('replace', 19, 20, 20, 21),
('equal', 20, 22, 21, 23),
('delete', 22, 27, 23, 23),
('equal', 27, 30, 23, 26)],
[('equal', 31, 34, 27, 30),
('replace', 34, 35, 30, 31),
('equal', 35, 38, 31, 34)]]
"""
codes = self.get_opcodes()
if not codes:
codes = [("equal", 0, 1, 0, 1)]
# Fixup leading and trailing groups if they show no changes.
if codes[0][0] == 'equal':
tag, i1, i2, j1, j2 = codes[0]
codes[0] = tag, max(i1, i2-n), i2, max(j1, j2-n), j2
if codes[-1][0] == 'equal':
tag, i1, i2, j1, j2 = codes[-1]
codes[-1] = tag, i1, min(i2, i1+n), j1, min(j2, j1+n)
nn = n + n
group = []
for tag, i1, i2, j1, j2 in codes:
# End the current group and start a new one whenever
# there is a large range with no changes.
if tag == 'equal' and i2-i1 > nn:
group.append((tag, i1, min(i2, i1+n), j1, min(j2, j1+n)))
yield group
group = []
i1, j1 = max(i1, i2-n), max(j1, j2-n)
group.append((tag, i1, i2, j1 ,j2))
if group and not (len(group)==1 and group[0][0] == 'equal'):
yield group
def ratio(self):
"""Return a measure of the sequences' similarity (float in [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 if the sequences are identical, and 0 if
they have nothing in common.
.ratio() is expensive to compute if you haven't already computed
.get_matching_blocks() or .get_opcodes(), in which case you may
want to try .quick_ratio() or .real_quick_ratio() first to get an
upper bound.
>>> s = SequenceMatcher(None, "abcd", "bcde")
>>> s.ratio()
0.75
>>> s.quick_ratio()
0.75
>>> s.real_quick_ratio()
1.0
"""
matches = reduce(lambda sum, triple: sum + triple[-1],
self.get_matching_blocks(), 0)
return _calculate_ratio(matches, len(self.a) + len(self.b))
def quick_ratio(self):
"""Return an upper bound on ratio() relatively quickly.
This isn't defined beyond that it is an upper bound on .ratio(), and
is faster to compute.
"""
# viewing a and b as multisets, set matches to the cardinality
# of their intersection; this counts the number of matches
# without regard to order, so is clearly an upper bound
if self.fullbcount is None:
self.fullbcount = fullbcount = {}
for elt in self.b:
fullbcount[elt] = fullbcount.get(elt, 0) + 1
fullbcount = self.fullbcount
# avail[x] is the number of times x appears in 'b' less the
# number of times we've seen it in 'a' so far ... kinda
avail = {}
availhas, matches = avail.has_key, 0
for elt in self.a:
if availhas(elt):
numb = avail[elt]
else:
numb = fullbcount.get(elt, 0)
avail[elt] = numb - 1
if numb > 0:
matches = matches + 1
return _calculate_ratio(matches, len(self.a) + len(self.b))
def real_quick_ratio(self):
"""Return an upper bound on ratio() very quickly.
This isn't defined beyond that it is an upper bound on .ratio(), and
is faster to compute than either .ratio() or .quick_ratio().
"""
la, lb = len(self.a), len(self.b)
# can't have more matches than the number of elements in the
# shorter sequence
return _calculate_ratio(min(la, lb), la + lb)
def get_close_matches(word, possibilities, n=3, cutoff=0.6):
"""Use SequenceMatcher to return list of the best "good enough" matches.
word is a sequence for which close matches are desired (typically a
string).
possibilities is a list of sequences against which to match word
(typically a list of strings).
Optional arg n (default 3) is the maximum number of close matches to
return. n must be > 0.
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.
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 as _keyword
>>> get_close_matches("wheel", _keyword.kwlist)
['while']
>>> get_close_matches("apple", _keyword.kwlist)
[]
>>> get_close_matches("accept", _keyword.kwlist)
['except']
"""
if not n > 0:
raise ValueError("n must be > 0: %r" % (n,))
if not 0.0 <= cutoff <= 1.0:
raise ValueError("cutoff must be in [0.0, 1.0]: %r" % (cutoff,))
result = []
s = SequenceMatcher()
s.set_seq2(word)
for x in possibilities:
s.set_seq1(x)
if s.real_quick_ratio() >= cutoff and \
s.quick_ratio() >= cutoff and \
s.ratio() >= cutoff:
result.append((s.ratio(), x))
# Move the best scorers to head of list
result = heapq.nlargest(n, result)
# Strip scores for the best n matches
return [x for score, x in result]
def _count_leading(line, ch):
"""
Return number of `ch` characters at the start of `line`.
Example:
>>> _count_leading(' abc', ' ')
3
"""
i, n = 0, len(line)
while i < n and line[i] == ch:
i += 1
return i
class Differ:
r"""
Differ is a class for comparing sequences of lines of text, and
producing human-readable differences or deltas. Differ uses
SequenceMatcher both to compare sequences of lines, and to compare
sequences of characters within similar (near-matching) lines.
Each line of a Differ delta begins with a two-letter code:
'- ' 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.
Note that Differ makes no claim to produce a *minimal* diff. 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.
Example: Comparing 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
`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 Differ object we may pass functions to
filter out line and character 'junk'. See Differ.__init__ 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 as _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:
>>> print ''.join(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.
Methods:
__init__(linejunk=None, charjunk=None)
Construct a text differencer, with optional filters.
compare(a, b)
Compare two sequences of lines; generate the resulting delta.
"""
def __init__(self, linejunk=None, charjunk=None):
"""
Construct a text differencer, with optional filters.
The two optional keyword parameters are for filter functions:
- `linejunk`: A function that should accept a single string argument,
and return true iff the string is junk. The module-level function
`IS_LINE_JUNK` may be used to filter out lines without visible
characters, except for at most one splat ('#'). It is recommended
to leave linejunk None; as of Python 2.3, the underlying
SequenceMatcher class has grown an adaptive notion of "noise" lines
that's better than any static definition the author has ever been
able to craft.
- `charjunk`: A function that should accept a string of length 1. The
module-level function `IS_CHARACTER_JUNK` may be used to filter out
whitespace characters (a blank or tab; **note**: bad idea to include
newline in this!). Use of IS_CHARACTER_JUNK is recommended.
"""
self.linejunk = linejunk
self.charjunk = charjunk
def compare(self, a, b):
r"""
Compare two sequences of lines; generate the resulting delta.
Each sequence must contain individual single-line strings ending with
newlines. Such sequences can be obtained from the `readlines()` method
of file-like objects. The delta generated also consists of newline-
terminated strings, ready to be printed as-is via the writeline()
method of a file-like object.
Example:
>>> print ''.join(Differ().compare('one\ntwo\nthree\n'.splitlines(1),
... 'ore\ntree\nemu\n'.splitlines(1))),
- one
? ^
+ ore
? ^
- two
- three
? -
+ tree
+ emu
"""
cruncher = SequenceMatcher(self.linejunk, a, b)
for tag, alo, ahi, blo, bhi in cruncher.get_opcodes():
if tag == 'replace':
g = self._fancy_replace(a, alo, ahi, b, blo, bhi)
elif tag == 'delete':
g = self._dump('-', a, alo, ahi)
elif tag == 'insert':
g = self._dump('+', b, blo, bhi)
elif tag == 'equal':
g = self._dump(' ', a, alo, ahi)
else:
raise ValueError, 'unknown tag %r' % (tag,)
for line in g:
yield line
def _dump(self, tag, x, lo, hi):
"""Generate comparison results for a same-tagged range."""
for i in xrange(lo, hi):
yield '%s %s' % (tag, x[i])
def _plain_replace(self, a, alo, ahi, b, blo, bhi):
assert alo < ahi and blo < bhi
# dump the shorter block first -- reduces the burden on short-term
# memory if the blocks are of very different sizes
if bhi - blo < ahi - alo:
first = self._dump('+', b, blo, bhi)
second = self._dump('-', a, alo, ahi)
else:
first = self._dump('-', a, alo, ahi)
second = self._dump('+', b, blo, bhi)
for g in first, second:
for line in g:
yield line
def _fancy_replace(self, a, alo, ahi, b, blo, bhi):
r"""
When replacing one block of lines with another, search the blocks
for *similar* lines; the best-matching pair (if any) is used as a
synch point, and intraline difference marking is done on the
similar pair. Lots of work, but often worth it.
Example:
>>> d = Differ()
>>> results = d._fancy_replace(['abcDefghiJkl\n'], 0, 1,
... ['abcdefGhijkl\n'], 0, 1)
>>> print ''.join(results),
- abcDefghiJkl
? ^ ^ ^
+ abcdefGhijkl
? ^ ^ ^
"""
# don't synch up unless the lines have a similarity score of at
# least cutoff; best_ratio tracks the best score seen so far
best_ratio, cutoff = 0.74, 0.75
cruncher = SequenceMatcher(self.charjunk)
eqi, eqj = None, None # 1st indices of equal lines (if any)
# search for the pair that matches best without being identical
# (identical lines must be junk lines, & we don't want to synch up
# on junk -- unless we have to)
for j in xrange(blo, bhi):
bj = b[j]
cruncher.set_seq2(bj)
for i in xrange(alo, ahi):
ai = a[i]
if ai == bj:
if eqi is None:
eqi, eqj = i, j
continue
cruncher.set_seq1(ai)
# computing similarity is expensive, so use the quick
# upper bounds first -- have seen this speed up messy
# compares by a factor of 3.
# note that ratio() is only expensive to compute the first
# time it's called on a sequence pair; the expensive part
# of the computation is cached by cruncher
if cruncher.real_quick_ratio() > best_ratio and \
cruncher.quick_ratio() > best_ratio and \
cruncher.ratio() > best_ratio:
best_ratio, best_i, best_j = cruncher.ratio(), i, j
if best_ratio < cutoff:
# no non-identical "pretty close" pair
if eqi is None:
# no identical pair either -- treat it as a straight replace
for line in self._plain_replace(a, alo, ahi, b, blo, bhi):
yield line
return
# no close pair, but an identical pair -- synch up on that
best_i, best_j, best_ratio = eqi, eqj, 1.0
else:
# there's a close pair, so forget the identical pair (if any)
eqi = None
# a[best_i] very similar to b[best_j]; eqi is None iff they're not
# identical
# pump out diffs from before the synch point
for line in self._fancy_helper(a, alo, best_i, b, blo, best_j):
yield line
# do intraline marking on the synch pair
aelt, belt = a[best_i], b[best_j]
if eqi is None:
# pump out a '-', '?', '+', '?' quad for the synched lines
atags = btags = ""
cruncher.set_seqs(aelt, belt)
for tag, ai1, ai2, bj1, bj2 in cruncher.get_opcodes():
la, lb = ai2 - ai1, bj2 - bj1
if tag == 'replace':
atags += '^' * la
btags += '^' * lb
elif tag == 'delete':
atags += '-' * la
elif tag == 'insert':
btags += '+' * lb
elif tag == 'equal':
atags += ' ' * la
btags += ' ' * lb
else:
raise ValueError, 'unknown tag %r' % (tag,)
for line in self._qformat(aelt, belt, atags, btags):
yield line
else:
# the synch pair is identical
yield ' ' + aelt
# pump out diffs from after the synch point
for line in self._fancy_helper(a, best_i+1, ahi, b, best_j+1, bhi):
yield line
def _fancy_helper(self, a, alo, ahi, b, blo, bhi):
g = []
if alo < ahi:
if blo < bhi:
g = self._fancy_replace(a, alo, ahi, b, blo, bhi)
else:
g = self._dump('-', a, alo, ahi)
elif blo < bhi:
g = self._dump('+', b, blo, bhi)
for line in g:
yield line
def _qformat(self, aline, bline, atags, btags):
r"""
Format "?" output and deal with leading tabs.
Example:
>>> d = Differ()
>>> results = d._qformat('\tabcDefghiJkl\n', '\t\tabcdefGhijkl\n',
... ' ^ ^ ^ ', '+ ^ ^ ^ ')
>>> for line in results: print repr(line)
...
'- \tabcDefghiJkl\n'
'? \t ^ ^ ^\n'
'+ \t\tabcdefGhijkl\n'
'? \t ^ ^ ^\n'
"""
# Can hurt, but will probably help most of the time.
common = min(_count_leading(aline, "\t"),
_count_leading(bline, "\t"))
common = min(common, _count_leading(atags[:common], " "))
atags = atags[common:].rstrip()
btags = btags[common:].rstrip()
yield "- " + aline
if atags:
yield "? %s%s\n" % ("\t" * common, atags)
yield "+ " + bline
if btags:
yield "? %s%s\n" % ("\t" * common, btags)
# With respect to junk, an earlier version of ndiff simply refused to
# *start* a match with a junk element. The result was cases like this:
# before: private Thread currentThread;
# after: private volatile Thread currentThread;
# If you consider whitespace to be junk, the longest contiguous match
# not starting with junk is "e Thread currentThread". So ndiff reported
# that "e volatil" was inserted between the 't' and the 'e' in "private".
# While an accurate view, to people that's absurd. The current version
# looks for matching blocks that are entirely junk-free, then extends the
# longest one of those as far as possible but only with matching junk.
# So now "currentThread" is matched, then extended to suck up the
# preceding blank; then "private" is matched, and extended to suck up the
# following blank; then "Thread" is matched; and finally ndiff reports
# that "volatile " was inserted before "Thread". The only quibble
# remaining is that perhaps it was really the case that " volatile"
# was inserted after "private". I can live with that .
import re
def IS_LINE_JUNK(line, pat=re.compile(r"\s*#?\s*$").match):
r"""
Return 1 for ignorable line: iff `line` is blank or contains a single '#'.
Examples:
>>> IS_LINE_JUNK('\n')
True
>>> IS_LINE_JUNK(' # \n')
True
>>> IS_LINE_JUNK('hello\n')
False
"""
return pat(line) is not None
def IS_CHARACTER_JUNK(ch, ws=" \t"):
r"""
Return 1 for ignorable character: iff `ch` is a space or tab.
Examples:
>>> IS_CHARACTER_JUNK(' ')
True
>>> IS_CHARACTER_JUNK('\t')
True
>>> IS_CHARACTER_JUNK('\n')
False
>>> IS_CHARACTER_JUNK('x')
False
"""
return ch in ws
def unified_diff(a, b, fromfile='', tofile='', fromfiledate='',
tofiledate='', n=3, lineterm='\n'):
r"""
Compare two sequences of lines; generate the delta as a unified diff.
Unified diffs are a compact way of showing line changes and a few
lines of context. 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 file.readlines() result in diffs that are suitable for
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 unidiff 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 time.ctime().
Example:
>>> for line in unified_diff('one two three four'.split(),
... 'zero one tree four'.split(), 'Original', 'Current',
... 'Sat Jan 26 23:30:50 1991', 'Fri Jun 06 10:20:52 2003',
... lineterm=''):
... print line
--- Original Sat Jan 26 23:30:50 1991
+++ Current Fri Jun 06 10:20:52 2003
@@ -1,4 +1,4 @@
+zero
one
-two
-three
+tree
four
"""
started = False
for group in SequenceMatcher(None,a,b).get_grouped_opcodes(n):
if not started:
yield '--- %s %s%s' % (fromfile, fromfiledate, lineterm)
yield '+++ %s %s%s' % (tofile, tofiledate, lineterm)
started = True
i1, i2, j1, j2 = group[0][1], group[-1][2], group[0][3], group[-1][4]
yield "@@ -%d,%d +%d,%d @@%s" % (i1+1, i2-i1, j1+1, j2-j1, lineterm)
for tag, i1, i2, j1, j2 in group:
if tag == 'equal':
for line in a[i1:i2]:
yield ' ' + line
continue
if tag == 'replace' or tag == 'delete':
for line in a[i1:i2]:
yield '-' + line
if tag == 'replace' or tag == 'insert':
for line in b[j1:j2]:
yield '+' + line
# See http://www.unix.org/single_unix_specification/
def context_diff(a, b, fromfile='', tofile='',
fromfiledate='', tofiledate='', n=3, lineterm='\n'):
r"""
Compare two sequences of lines; generate the delta as a context diff.
Context diffs are a compact way of showing line changes and a few
lines of context. 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 file.readlines() result in diffs that are suitable for
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 time.ctime(). If not specified, the strings default to blanks.
Example:
>>> print ''.join(context_diff('one\ntwo\nthree\nfour\n'.splitlines(1),
... 'zero\none\ntree\nfour\n'.splitlines(1), 'Original', 'Current',
... 'Sat Jan 26 23:30:50 1991', 'Fri Jun 06 10:22:46 2003')),
*** Original Sat Jan 26 23:30:50 1991
--- Current Fri Jun 06 10:22:46 2003
***************
*** 1,4 ****
one
! two
! three
four
--- 1,4 ----
+ zero
one
! tree
four
"""
started = False
prefixmap = {'insert':'+ ', 'delete':'- ', 'replace':'! ', 'equal':' '}
for group in SequenceMatcher(None,a,b).get_grouped_opcodes(n):
if not started:
yield '*** %s %s%s' % (fromfile, fromfiledate, lineterm)
yield '--- %s %s%s' % (tofile, tofiledate, lineterm)
started = True
yield '***************%s' % (lineterm,)
if group[-1][2] - group[0][1] >= 2:
yield '*** %d,%d ****%s' % (group[0][1]+1, group[-1][2], lineterm)
else:
yield '*** %d ****%s' % (group[-1][2], lineterm)
visiblechanges = [e for e in group if e[0] in ('replace', 'delete')]
if visiblechanges:
for tag, i1, i2, _, _ in group:
if tag != 'insert':
for line in a[i1:i2]:
yield prefixmap[tag] + line
if group[-1][4] - group[0][3] >= 2:
yield '--- %d,%d ----%s' % (group[0][3]+1, group[-1][4], lineterm)
else:
yield '--- %d ----%s' % (group[-1][4], lineterm)
visiblechanges = [e for e in group if e[0] in ('replace', 'insert')]
if visiblechanges:
for tag, _, _, j1, j2 in group:
if tag != 'delete':
for line in b[j1:j2]:
yield prefixmap[tag] + line
def ndiff(a, b, linejunk=None, charjunk=IS_CHARACTER_JUNK):
r"""
Compare `a` and `b` (lists of strings); return a `Differ`-style delta.
Optional keyword parameters `linejunk` and `charjunk` are for filter
functions (or None):
- linejunk: A function that should accept a single string argument, and
return true iff the string is junk. The default is None, and is
recommended; as of Python 2.3, an adaptive notion of "noise" lines is
used that does a good job on its own.
- charjunk: A function that should accept a string of length 1. The
default is module-level function IS_CHARACTER_JUNK, which filters out
whitespace characters (a blank or tab; note: bad idea to include newline
in this!).
Tools/scripts/ndiff.py is a command-line front-end to this function.
Example:
>>> diff = ndiff('one\ntwo\nthree\n'.splitlines(1),
... 'ore\ntree\nemu\n'.splitlines(1))
>>> print ''.join(diff),
- one
? ^
+ ore
? ^
- two
- three
? -
+ tree
+ emu
"""
return Differ(linejunk, charjunk).compare(a, b)
def mdiff(fromlines, tolines, chgfmt, linefmt, context=None, sep=None,
linejunk=None, charjunk=IS_CHARACTER_JUNK):
"""Returns generator yielding marked up from/to side by side difference lines.
Arguments:
fromlines -- text lines which will be iterated over and compared to tolines
tolines -- text lines which will be iterated over and compared to fromlines
chgfmt -- function to markup add/delete/change differences in text lines
(see example below)
linefmt -- function to format line of text for display (see example below)
context -- number of context lines to display on each side of difference,
if None or less that 1, the all from/to text lines will be
generated.
sep -- separator string to use between context differences.
linejunk -- passed on to ndiff (see ndiff documentation)
charjunk -- passed on to ndiff (see ndiff documentation)
This function returns an interator which returns a tuple of a "from"
line, a corresponding "to" line and a boolean indicating if either the
"from" or "to" line contains a difference.
This function/iterator was originally developed to generate side by side
file difference for making HTML pages. The function requires functions to
be passed in as arguments to allow it to be configurable to generate any
type of markup such as HTML or XHTML. The function supports generating a
full file difference report or just contextual differences.
See HtmlDiff class for an example usage of this function. Note, this
function utilizes the ndiff function to generate the side by side
difference markup. Optional ndiff arguments may be passed to this function
and they in turn will be passed to ndiff.
"""
import re
# adjust number of context lines to include the line with the change
if context:
context += 1
# regular expression for finding intraline change indices
change_re = re.compile('(\++|\-+|\^+)')
# regular expression to find hidden markers
marker_re = re.compile('\0([+-^])(.*?)\1',re.DOTALL)
# create the difference iterator to generate the differences
diff_lines_iterator = ndiff(fromlines,tolines,linejunk,charjunk)
def _make_line(lines, format_key, side, num_lines=[0,0]):
"""Returns line of text with user's change markup and line formatting.
lines -- list of lines from the ndiff generator to produce a line of
text from. When producing the line of text to return, the
lines used are removed from this list.
format_key -- '+' return first line in list with "add" markup around
the entire line.
'-' return first line in list with "delete" markup around
the entire line.
'?' return first line in list with add/delete/change
intraline markup (indices obtained from second line)
None return first line in list with no markup
side -- indice into the num_lines list (0=from,1=to)
num_lines -- from/to current line number. This is NOT intended to be a
passed parameter. It is present as a keyword argument to
maintain memory of the current line numbers between calls
of this function.
Note, this function is purposefully not defined at the module scope so
that data it needs from its parent function (within whose context it
is defined) does not need to be of module scope.
"""
num_lines[side] += 1
# Handle case where no user markup is to be added, just return line of
# text with user's line format to allow for usage of the line number.
if format_key is None:
return linefmt(side,num_lines[side],lines.pop(0)[2:])
# Handle case of intraline changes
if format_key == '?':
text, markers = lines.pop(0), lines.pop(0)
# find intraline changes (store change type and indices in tuples)
sub_info = []
def record_sub_info(match_object,sub_info=sub_info):
sub_info.append([match_object.group(1)[0],match_object.span()])
return match_object.group(1)
change_re.sub(record_sub_info,markers)
# process each tuple inserting our special marks that won't be
# noticed by an xml/html escaper.
for key,(begin,end) in sub_info[::-1]:
text = text[0:begin]+'\0'+key+text[begin:end]+'\1'+text[end:]
text = text[2:]
# Handle case of add/delete entire line
else:
text = lines.pop(0)[2:]
# if line of text is just a newline, insert a space so there is
# something for the user to highlight and see.
if len(text) <= 1:
text = ' '+text
# insert marks that won't be noticed by an xml/html escaper.
text = '\0' + format_key + text + '\1'
# Return line of text, first allow user's line formatter to do it's
# thing (such as adding the line number) then replace the special
# marks with what the user's change markup.
line_num = num_lines[side]
replacer = lambda m : chgfmt(side,line_num,m.group(2),m.group(1))
return marker_re.sub(replacer,linefmt(side,line_num,text))
def _line_iterator():
"""Yields from/to lines of text with a change indication.
This function is an iterator. It itself pulls lines from a
differencing iterator, processes them and yields them. When it can
it yields both a "from" and a "to" line, otherwise it will yield one
or the other. Processing includes formatting the line with the user's
line formatter (for adding line numbering) and formatting differences
using the user's change format function. In addition to yielding the
lines of from/to text, a boolean flag is yielded to indicate if the
text line(s) have differences in them.
Note, this function is purposefully not defined at the module scope so
that data it needs from its parent function (within whose context it
is defined) does not need to be of module scope.
"""
lines = []
num_blanks_pending, num_blanks_to_yield = 0, 0
while True:
# Load up next 4 lines so we can look ahead, create strings which
# are a concatenation of the first character of each of the 4 lines
# so we can do some very readable comparisons.
while len(lines) < 4:
try:
lines.append(diff_lines_iterator.next())
except StopIteration:
lines.append('X')
s = ''.join([line[0] for line in lines])
if s.startswith('X'):
# When no more lines, pump out any remaining blank lines so the
# corresponding add/delete lines get a matching blank line so
# all line pairs get yielded at the next level.
num_blanks_to_yield = num_blanks_pending
elif s.startswith('-?+?'):
# simple intraline change
yield _make_line(lines,'?',0), _make_line(lines,'?',1), True
continue
elif s.startswith('--++'):
# in delete block, add block coming: we do NOT want to get
# caught up on blank lines yet, just process the delete line
num_blanks_pending -= 1
yield _make_line(lines,'-',0), None, True
continue
elif s.startswith('--?+') or s.startswith('--+') or \
s.startswith('- '):
# in delete block and see a intraline change or unchanged line
# coming: yield the delete line and then blanks
from_line,to_line = _make_line(lines,'-',0), None
num_blanks_to_yield,num_blanks_pending = num_blanks_pending-1,0
elif s.startswith('-+?'):
# intraline change
yield _make_line(lines,None,0), _make_line(lines,'?',1), True
continue
elif s.startswith('-?+'):
# intraline change
yield _make_line(lines,'?',0), _make_line(lines,None,1), True
continue
elif s.startswith('-'):
# delete FROM line
num_blanks_pending -= 1
yield _make_line(lines,'-',0), None, True
continue
elif s.startswith('+--'):
# in add block, delete block coming: we do NOT want to get
# caught up on blank lines yet, just process the add line
num_blanks_pending += 1
yield None, _make_line(lines,'+',1), True
continue
elif s.startswith('+ ') or s.startswith('+-'):
# will be leaving an add block: yield blanks then add line
from_line, to_line = None, _make_line(lines,'+',1)
num_blanks_to_yield,num_blanks_pending = num_blanks_pending+1,0
elif s.startswith('+'):
# inside an add block, yield the add line
num_blanks_pending += 1
yield None, _make_line(lines,'+',1), True
continue
elif s.startswith(' '):
# unchanged text, yield it to both sides
yield _make_line(lines[:],None,0),_make_line(lines,None,1),False
continue
# Catch up on the blank lines so when we yield the next from/to
# pair, they are lined up.
while(num_blanks_to_yield < 0):
num_blanks_to_yield += 1
yield None,linefmt(1,None,'\n'),True
while(num_blanks_to_yield > 0):
num_blanks_to_yield -= 1
yield linefmt(0,None,'\n'),None,True
if s.startswith('X'):
raise StopIteration
else:
yield from_line,to_line,True
def _line_pair_iterator():
"""Yields from/to lines of text with a change indication.
This function is an iterator. It itself pulls lines from the line
iterator. It's difference from that iterator is that this function
always yields a pair of from/to text lines (with the change
indication). If necessary it will collect single from/to lines
until it has a matching pair from/to pair to yield.
Note, this function is purposefully not defined at the module scope so
that data it needs from its parent function (within whose context it
is defined) does not need to be of module scope.
"""
line_iterator = _line_iterator()
fromlines,tolines=[],[]
while True:
# Collecting lines of text until we have a from/to pair
while (len(fromlines)==0 or len(tolines)==0):
from_line, to_line, found_diff =line_iterator.next()
if from_line is not None:
fromlines.append((from_line,found_diff))
if to_line is not None:
tolines.append((to_line,found_diff))
# Once we have a pair, remove them from the collection and yield it
from_line, fromDiff = fromlines.pop(0)
to_line, to_diff = tolines.pop(0)
yield (from_line,to_line,fromDiff or to_diff)
# Handle case where user does not want context differencing, just yield
# them up without doing anything else with them.
line_pair_iterator = _line_pair_iterator()
if context is None or context <= 0:
while True:
yield line_pair_iterator.next()
# Handle case where user wants context differencing. We must do some
# storage of lines until we know for sure that they are to be yielded.
else:
lines_to_write = 0
insert_separator = False
while True:
# Store lines up until we find a difference, note use of a
# circular queue because we only need to keep around what
# we need for context.
index, contextLines = 0, [None]*(context)
found_diff = False
while(found_diff is False):
from_line, to_line, found_diff = line_pair_iterator.next()
i = index % context
contextLines[i] = (from_line, to_line, found_diff)
index += 1
# Yield lines that we have collected so far, but first yield
# the user's separator.
if insert_separator:
yield sep, sep, None
else:
insert_separator = True
if index > context:
lines_to_write = context
else:
lines_to_write = index
index = 0
while(lines_to_write):
i = index % context
index += 1
yield contextLines[i]
lines_to_write -= 1
# Now yield the context lines after the change
lines_to_write = context-1
while(lines_to_write):
from_line, to_line, found_diff = line_pair_iterator.next()
# If another change within the context, extend the context
if found_diff:
lines_to_write = context
else:
lines_to_write -= 1
yield from_line, to_line, found_diff
class HtmlDiff(object):
"""For producing HTML side by side comparison with change highlights.
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 comparision
of text with inter-line and intra-line change highlights. The table can
be generated in either full or contextual difference mode. Additional
control of the format of the generated difference table can be controlled
by subclassing and overriding the appropriate template or method.
The following templates and methods are intended for subclass overriding:
file_template -- controls HTML file format
styles -- style specifications for change highlights
table_template -- controls difference table format
linenum_template -- controls format of line number column
legend -- legend table content
format_line -- method to markup each line
format_change -- method to provide change highlight markup
The following methods are provided for HTML generation:
make_table -- generates HTML for a single side by side table
make_file -- generates complete HTML file with a single side by side table
See tools/scripts/diff.py for an example usage of this class.
"""
file_template = """
%(title)s
%(header)s
%(table)s%(legend)s
"""
styles = """
.diff_header {background-color:#e0e0e0}
td.diff_header {text-align:right}
.diff_next {background-color:#c0c0c0}
.diff_add {background-color:#aaffaa}
.diff_chg {background-color:#ffff77}
.diff_sub {background-color:#ffaaaa}"""
linenum_template = "%d"
table_template = """
%(header_row)s%(data_rows)s
"""
legend = """
Legends |
Colors |
Added |
Changed |
Deleted |
|
Links |
(f)irst change |
(n)ext change |
(t)op |
|
"""
def __init__(self,prefix=['from','to'], linejunk=None,
charjunk=IS_CHARACTER_JUNK):
"""HtmlDiff instance initializer
Arguments:
prefix -- from/to line anchors name prefix (useful for hyperlinking to
specific lines in a table when multiple tables exist so that the
correct table can be referenced)
linejunk -- passed on to ndiff (see ndiff documentation)
charjunk -- passed on to ndiff (see ndiff documentation)
"""
self._prefix = prefix
self._linejunk = linejunk
self._charjunk = charjunk
import xml.sax.saxutils
self._escape = xml.sax.saxutils.escape
def make_file(self,fromlines,tolines,fromdesc='',todesc='',context=False,
numlines=5,title='',header='',summary=''):
"""Returns HTML file of side by side comparison with change highlights
Arguments:
fromlines -- list of "from" lines
tolines -- list of "to" lines
fromdesc -- "from" file column header string
todesc -- "to" file column header string
context -- set to True for contextual differences
numlines -- number of context lines (needed for full differences to
place the "next" anchor a few lines ahead of the next change)
title -- window title string
header -- header HTML string to be placed above table
summary -- summary attribute of table string
"""
return self.file_template % dict(
styles = self.styles,
legend = self.legend,
title = title,
header = header,
table = self.make_table(fromlines,tolines,fromdesc,todesc,
context=context,numlines=numlines,
summary=summary))
def make_table(self,fromlines,tolines,fromdesc='',todesc='',context=False,
numlines=5,summary=''):
"""Returns HTML table of side by side comparison with change highlights
Arguments:
fromlines -- list of "from" lines
tolines -- list of "to" lines
fromdesc -- "from" file column header string
todesc -- "to" file column header string
context -- set to True for contextual differences
numlines -- number of context lines (needed for full differences to
place the "next" anchor a few lines ahead of the next change)
summary -- summary attribute of table
"""
if context:
context = numlines
else:
context = 0
prefix = self._prefix[1]
# collect up from/to lines in string, difference flags in a list
from_text, to_text, diff_flags = [],[],[]
diffs = mdiff(fromlines,tolines,self.format_change,self.format_line,
context,None,linejunk=self._linejunk,
charjunk=self._charjunk)
for from_line, to_line, found_diff in diffs:
from_text.append(from_line)
to_text.append(to_line)
diff_flags.append(found_diff)
# process change flags, generating middle column of next anchors/links
next_id = ['']*len(diff_flags)
next_href = ['']*len(diff_flags)
num_chg, in_change = 0, False
last = 0
for i,flag in enumerate(diff_flags):
if flag:
if not in_change:
in_change = True
last = i
# at the beginning of a change, drop an anchor a few lines
# (the context lines) before the change for the previous
# link
i = max([0,i-numlines])
next_id[i] = ' id="difflib_chg_%s_%d"' % (prefix,num_chg)
# at the beginning of a change, drop a link to the next
# change
num_chg += 1
next_href[last] = 'n' % (
prefix,num_chg)
else:
in_change = False
# if not a change on first line, drop a link
if not diff_flags[0]:
next_href[0] = 'f' % prefix
# redo the last link to link to the top
next_href[last] = 't' % (prefix)
import cStringIO
s = cStringIO.StringIO()
for i in range(len(diff_flags)):
if diff_flags[i] is None:
# mdiff yields None on separator lines
s.write('\n')
else:
s.write('%s\n%s | \n%s\n
' %
(from_text[i],next_id[i],next_href[i],to_text[i]))
if fromdesc or todesc:
header_row = '%s%s%s
' % (
'' % fromdesc,
'
| ',
'' % todesc)
else:
header_row = ''
return self.table_template % dict(
summary=summary,
data_rows=s.getvalue(),
header_row=header_row,
prefix=prefix)
def format_line(self,side,linenum,text):
"""Returns marked up "from" or "to" text line
mdiff() will call this function with the following arguments:
side -- 0 or 1 indicating "from" or "to" text
linenum -- line number (used for line number column)
text -- line text to be marked up
"""
try:
linenum = self.linenum_template % linenum
id = ' id="%s%s"' % (self._prefix[side],linenum)
except TypeError:
# handle blank lines where linenum is None
linenum = ''
id = ''
text = self._escape(text)
text = text.replace(' ',' ')
fmt = '%s | '
return fmt % (id,linenum,text)
def format_change(self,side,linenum,text,type):
"""Returns HTML highlighted text
mdiff() will call this function with the following arguments:
side -- 0 or 1 indicating "from" or "to" text
linenum -- line number that contains the text (used for creating
"next" links)
text -- text to be highlighted
type -- +/-/^ indicating type of change
"""
if type == '+':
return '%s' % text
elif type == '-':
return '%s' % text
# must be '^':
return '%s' % text
del re
def restore(delta, which):
r"""
Generate one of the two sequences that generated a delta.
Given a `delta` produced by `Differ.compare()` or `ndiff()`, extract
lines originating from file 1 or 2 (parameter `which`), stripping off line
prefixes.
Examples:
>>> diff = ndiff('one\ntwo\nthree\n'.splitlines(1),
... 'ore\ntree\nemu\n'.splitlines(1))
>>> diff = list(diff)
>>> print ''.join(restore(diff, 1)),
one
two
three
>>> print ''.join(restore(diff, 2)),
ore
tree
emu
"""
try:
tag = {1: "- ", 2: "+ "}[int(which)]
except KeyError:
raise ValueError, ('unknown delta choice (must be 1 or 2): %r'
% which)
prefixes = (" ", tag)
for line in delta:
if line[:2] in prefixes:
yield line[2:]
def _test():
import doctest, difflib
return doctest.testmod(difflib)
if __name__ == "__main__":
_test()