def __init__(self, basetext, atext, btext, base=None, a=None, b=None):
self.basetext = basetext
self.atext = atext
self.btext = btext
if base is None:
base = mdiff.splitnewlines(basetext)
if a is None:
a = mdiff.splitnewlines(atext)
if b is None:
b = mdiff.splitnewlines(btext)
self.base = base
self.a = a
self.b = b
def __init__(self, basetext, atext, btext, base=None, a=None, b=None):
self.basetext = basetext
self.atext = atext
self.btext = btext
if base is None:
base = mdiff.splitnewlines(basetext)
if a is None:
a = mdiff.splitnewlines(atext)
if b is None:
b = mdiff.splitnewlines(btext)
self.base = base
self.a = a
self.b = b
def findrenames(repo, added=None, removed=None, threshold=0.5):
'''find renamed files -- yields (before, after, score) tuples'''
if added is None or removed is None:
added, removed = repo.status()[1:3]
ctx = repo.changectx()
for a in added:
aa = repo.wread(a)
bestname, bestscore = None, threshold
for r in removed:
rr = ctx.filectx(r).data()
# bdiff.blocks() returns blocks of matching lines
# count the number of bytes in each
equal = 0
alines = mdiff.splitnewlines(aa)
matches = bdiff.blocks(aa, rr)
for x1, x2, y1, y2 in matches:
for line in alines[x1:x2]:
equal += len(line)
lengths = len(aa) + len(rr)
if lengths:
myscore = equal * 2.0 / lengths
if myscore >= bestscore:
bestname, bestscore = r, myscore
if bestname:
yield bestname, a, bestscore
def findrenames(repo, added=None, removed=None, threshold=0.5):
'''find renamed files -- yields (before, after, score) tuples'''
if added is None or removed is None:
added, removed = repo.status()[1:3]
ctx = repo.changectx()
for a in added:
aa = repo.wread(a)
bestname, bestscore = None, threshold
for r in removed:
rr = ctx.filectx(r).data()
# bdiff.blocks() returns blocks of matching lines
# count the number of bytes in each
equal = 0
alines = mdiff.splitnewlines(aa)
matches = bdiff.blocks(aa, rr)
for x1,x2,y1,y2 in matches:
for line in alines[x1:x2]:
equal += len(line)
lengths = len(aa) + len(rr)
if lengths:
myscore = equal*2.0 / lengths
if myscore >= bestscore:
bestname, bestscore = r, myscore
if bestname:
yield bestname, a, bestscore
def score(text):
if not len(text):
return 0.0
if not fctx.cmp(text):
return 1.0
if threshold == 1.0:
return 0.0
orig = fctx.data()
# bdiff.blocks() returns blocks of matching lines
# count the number of bytes in each
equal = 0
alines = mdiff.splitnewlines(text)
matches = bdiff.blocks(text, orig)
for x1, x2, y1, y2 in matches:
for line in alines[x1:x2]:
equal += len(line)
lengths = len(text) + len(orig)
return equal * 2.0 / lengths
def score(text):
if not len(text):
return 0.0
if not fctx.cmp(text):
return 1.0
if threshold == 1.0:
return 0.0
orig = fctx.data()
# bdiff.blocks() returns blocks of matching lines
# count the number of bytes in each
equal = 0
alines = mdiff.splitnewlines(text)
matches = bdiff.blocks(text, orig)
for x1, x2, y1, y2 in matches:
for line in alines[x1:x2]:
equal += len(line)
lengths = len(text) + len(orig)
return equal * 2.0 / lengths
def data():
orig = r.data()
return orig, mdiff.splitnewlines(orig)
def data():
orig = r.data()
return orig, mdiff.splitnewlines(orig)
