This is an archive of the discontinued Mercurial Phabricator instance.

Differential D8685

patch: refactor content diffing part in separate fn so extensions can wrap
ClosedPublic

Authored by pulkit on Jul 7 2020, 5:27 AM.

Details

Reviewers
None
Group Reviewers
hg-reviewers
Commits
rHG20a65e397943: patch: refactor content diffing part in separate fn so extensions can wrap
Summary

Right now extdiff uses it's own logic using archival to diff two versions of
file using external diff tools. This makes the extdiff functionality
non-extensible.

This series is an attempt to refactor core patch and diff functionality so that
extdiff can wrap and reuse it. This will help us in using external diffing tools
at more places and not just extdiff command only then.

Diff Detail

Repository
rHG Mercurial
Branch
default
Lint
No Linters Available
Unit
No Unit Test Coverage

Event Timeline

pulkit created this revision.Jul 7 2020, 5:27 AM
pulkit added a commit: rHG20a65e397943: patch: refactor content diffing part in separate fn so extensions can wrap.Jul 15 2020, 8:57 AM
This revision was not accepted when it landed; it landed in state Needs Review.
Closed by commit rHG20a65e397943: patch: refactor content diffing part in separate fn so extensions can wrap (authored by pulkit). · Explain Why
This revision was automatically updated to reflect the committed changes.

Revision Contents
Changeset List

PathPackages
Mmercurial/patch.py (118 lines)

Diff 21778

mercurial/patch.py

f in copyto f in copyto
and copyto[f] in addedset and copyto[f] in addedset
and copy[copyto[f]] == f and copy[copyto[f]] == f
): ):
continue continue
yield f1, f2, copyop yield f1, f2, copyop
def _gitindex(text):
if not text:
text = b""
l = len(text)
s = hashutil.sha1(b'blob %d\0' % l)
s.update(text)
return hex(s.digest())
_gitmode = {b'l': b'120000', b'x': b'100755', b'': b'100644'}
def trydiff( def trydiff(
repo, repo,
revs, revs,
ctx1, ctx1,
ctx2, ctx2,
modified, modified,
added, added,
removed, removed,
copy, copy,
getfilectx, getfilectx,
opts, opts,
losedatafn, losedatafn,
pathfn, pathfn,
): ):
'''given input data, generate a diff and yield it in blocks '''given input data, generate a diff and yield it in blocks
If generating a diff would lose data like flags or binary data and If generating a diff would lose data like flags or binary data and
losedatafn is not None, it will be called. losedatafn is not None, it will be called.
pathfn is applied to every path in the diff output. pathfn is applied to every path in the diff output.
''' '''
def gitindex(text):
if not text:
text = b""
l = len(text)
s = hashutil.sha1(b'blob %d\0' % l)
s.update(text)
return hex(s.digest())
if opts.noprefix: if opts.noprefix:
aprefix = bprefix = b'' aprefix = bprefix = b''
else: else:
aprefix = b'a/' aprefix = b'a/'
bprefix = b'b/' bprefix = b'b/'
def diffline(f, revs): def diffline(f, revs):
revinfo = b' '.join([b"-r %s" % rev for rev in revs]) revinfo = b' '.join([b"-r %s" % rev for rev in revs])
return b'diff %s %s' % (revinfo, f) return b'diff %s %s' % (revinfo, f)
def isempty(fctx): def isempty(fctx):
return fctx is None or fctx.size() == 0 return fctx is None or fctx.size() == 0
date1 = dateutil.datestr(ctx1.date()) date1 = dateutil.datestr(ctx1.date())
date2 = dateutil.datestr(ctx2.date()) date2 = dateutil.datestr(ctx2.date())
gitmode = {b'l': b'120000', b'x': b'100755', b'': b'100644'}
if not pathfn: if not pathfn:
pathfn = lambda f: f pathfn = lambda f: f
for f1, f2, copyop in _filepairs(modified, added, removed, copy, opts): for f1, f2, copyop in _filepairs(modified, added, removed, copy, opts):
content1 = None content1 = None
content2 = None content2 = None
fctx1 = None fctx1 = None
fctx2 = None fctx2 = None
or or
# create with flags # create with flags
(not f1 and flag2) (not f1 and flag2)
or or
# change flags # change flags
(f1 and f2 and flag1 != flag2) (f1 and f2 and flag1 != flag2)
): ):
losedatafn(f2 or f1) losedatafn(f2 or f1)
path1 = pathfn(f1 or f2) path1 = pathfn(f1 or f2)
path2 = pathfn(f2 or f1) path2 = pathfn(f2 or f1)
header = [] header = []
if opts.git: if opts.git:
header.append( header.append(
b'diff --git %s%s %s%s' % (aprefix, path1, bprefix, path2) b'diff --git %s%s %s%s' % (aprefix, path1, bprefix, path2)
) )
if not f1: # added if not f1: # added
header.append(b'new file mode %s' % gitmode[flag2]) header.append(b'new file mode %s' % _gitmode[flag2])
elif not f2: # removed elif not f2: # removed
header.append(b'deleted file mode %s' % gitmode[flag1]) header.append(b'deleted file mode %s' % _gitmode[flag1])
else: # modified/copied/renamed else: # modified/copied/renamed
mode1, mode2 = gitmode[flag1], gitmode[flag2] mode1, mode2 = _gitmode[flag1], _gitmode[flag2]
if mode1 != mode2: if mode1 != mode2:
header.append(b'old mode %s' % mode1) header.append(b'old mode %s' % mode1)
header.append(b'new mode %s' % mode2) header.append(b'new mode %s' % mode2)
if copyop is not None: if copyop is not None:
if opts.showsimilarity: if opts.showsimilarity:
sim = similar.score(ctx1[path1], ctx2[path2]) * 100 sim = similar.score(ctx1[path1], ctx2[path2]) * 100
header.append(b'similarity index %d%%' % sim) header.append(b'similarity index %d%%' % sim)
header.append(b'%s from %s' % (copyop, path1)) header.append(b'%s from %s' % (copyop, path1))
content2 = b'\0\0' content2 = b'\0\0'
else: else:
# normal path: load contents # normal path: load contents
if fctx1 is not None: if fctx1 is not None:
content1 = fctx1.data() content1 = fctx1.data()
if fctx2 is not None: if fctx2 is not None:
content2 = fctx2.data() content2 = fctx2.data()
data1 = (ctx1, fctx1, path1, flag1, content1, date1)
data2 = (ctx2, fctx2, path2, flag2, content2, date2)
yield diffcontent(data1, data2, header, binary, opts)
def diffcontent(data1, data2, header, binary, opts):
""" diffs two versions of a file.
data1 and data2 are tuples containg:
* ctx: changeset for the file
* fctx: file context for that file
* path1: name of the file
* flag: flags of the file
* content: full content of the file (can be null in case of binary)
* date: date of the changeset
header: the patch header
binary: whether the any of the version of file is binary or not
opts: user passed options
It exists as a separate function so that extensions like extdiff can wrap
it and use the file content directly.
"""
ctx1, fctx1, path1, flag1, content1, date1 = data1
ctx2, fctx2, path2, flag2, content2, date2 = data2
if binary and opts.git and not opts.nobinary: if binary and opts.git and not opts.nobinary:
text = mdiff.b85diff(content1, content2) text = mdiff.b85diff(content1, content2)
if text: if text:
header.append( header.append(
b'index %s..%s' % (gitindex(content1), gitindex(content2)) b'index %s..%s' % (_gitindex(content1), _gitindex(content2))
) )
hunks = ((None, [text]),) hunks = ((None, [text]),)
else: else:
if opts.git and opts.index > 0: if opts.git and opts.index > 0:
flag = flag1 flag = flag1
if flag is None: if flag is None:
flag = flag2 flag = flag2
header.append( header.append(
b'index %s..%s %s' b'index %s..%s %s'
% ( % (
gitindex(content1)[0 : opts.index], _gitindex(content1)[0 : opts.index],
gitindex(content2)[0 : opts.index], _gitindex(content2)[0 : opts.index],
gitmode[flag], _gitmode[flag],
) )
) )
uheaders, hunks = mdiff.unidiff( uheaders, hunks = mdiff.unidiff(
content1, content1,
date1, date1,
content2, content2,
date2, date2,
path1, path1,
path2, path2,
binary=binary, binary=binary,
opts=opts, opts=opts,
) )
header.extend(uheaders) header.extend(uheaders)
yield fctx1, fctx2, header, hunks return fctx1, fctx2, header, hunks
def diffstatsum(stats): def diffstatsum(stats):
maxfile, maxtotal, addtotal, removetotal, binary = 0, 0, 0, 0, False maxfile, maxtotal, addtotal, removetotal, binary = 0, 0, 0, 0, False
for f, a, r, b in stats: for f, a, r, b in stats:
maxfile = max(maxfile, encoding.colwidth(f)) maxfile = max(maxfile, encoding.colwidth(f))
maxtotal = max(maxtotal, a + r) maxtotal = max(maxtotal, a + r)
addtotal += a addtotal += a