def test_commit_serialization(self):
assert_commit_serialization(self.gitrwrepo, self.gitrwrepo.head, True)
rwrepo = self.gitrwrepo
make_object = rwrepo.odb.store
# direct serialization - deserialization can be tested afterwards
# serialization is probably limited on IO
hc = rwrepo.commit(rwrepo.head)
nc = 5000
st = time()
for i in xrange(nc):
cm = Commit(rwrepo, Commit.NULL_BIN_SHA, hc.tree,
hc.author, hc.authored_date, hc.author_tz_offset,
hc.committer, hc.committed_date, hc.committer_tz_offset,
str(i), parents=hc.parents, encoding=hc.encoding)
stream = BytesIO()
cm._serialize(stream)
slen = stream.tell()
stream.seek(0)
cm.binsha = make_object(IStream(Commit.type, slen, stream)).binsha
# END commit creation
elapsed = time() - st
print("Serialized %i commits to loose objects in %f s ( %f commits / s )"
% (nc, elapsed, nc / elapsed), file=sys.stderr)
def entry_at(cls, filepath, index):
""":return: RefLogEntry at the given index
:param filepath: full path to the index file from which to read the entry
:param index: python list compatible index, i.e. it may be negative to
specify an entry counted from the end of the list
:raise IndexError: If the entry didn't exist
.. note:: This method is faster as it only parses the entry at index, skipping
all other lines. Nonetheless, the whole file has to be read if
the index is negative
"""
fp = open(filepath, 'rb')
if index < 0:
return RefLogEntry.from_line(fp.readlines()[index].strip())
else:
# read until index is reached
for i in xrange(index + 1):
line = fp.readline()
if not line:
break
# END abort on eof
# END handle runup
if i != index or not line:
raise IndexError
# END handle exception
return RefLogEntry.from_line(line.strip())
def tree_to_stream(entries, write):
"""Write the give list of entries into a stream using its write method
:param entries: **sorted** list of tuples with (binsha, mode, name)
:param write: write method which takes a data string"""
ord_zero = ord('0')
bit_mask = 7 # 3 bits set
for binsha, mode, name in entries:
mode_str = b''
for i in xrange(6):
mode_str = bchr(((mode >> (i * 3)) & bit_mask) + ord_zero) + mode_str
# END for each 8 octal value
# git slices away the first octal if its zero
if byte_ord(mode_str[0]) == ord_zero:
mode_str = mode_str[1:]
# END save a byte
# here it comes: if the name is actually unicode, the replacement below
# will not work as the binsha is not part of the ascii unicode encoding -
# hence we must convert to an utf8 string for it to work properly.
# According to my tests, this is exactly what git does, that is it just
# takes the input literally, which appears to be utf8 on linux.
if isinstance(name, text_type):
name = name.encode(defenc)
write(b''.join((mode_str, b' ', name, b'\0', binsha)))
def tree_to_stream(entries, write):
"""Write the give list of entries into a stream using its write method
:param entries: **sorted** list of tuples with (binsha, mode, name)
:param write: write method which takes a data string"""
ord_zero = ord('0')
bit_mask = 7 # 3 bits set
for binsha, mode, name in entries:
mode_str = b''
for i in xrange(6):
mode_str = bchr((
(mode >> (i * 3)) & bit_mask) + ord_zero) + mode_str
# END for each 8 octal value
# git slices away the first octal if its zero
if byte_ord(mode_str[0]) == ord_zero:
mode_str = mode_str[1:]
# END save a byte
# here it comes: if the name is actually unicode, the replacement below
# will not work as the binsha is not part of the ascii unicode encoding -
# hence we must convert to an utf8 string for it to work properly.
# According to my tests, this is exactly what git does, that is it just
# takes the input literally, which appears to be utf8 on linux.
if isinstance(name, text_type):
name = name.encode(defenc)
write(b''.join((mode_str, b' ', name, b'\0', binsha)))
def test_commit_serialization(self):
assert_commit_serialization(self.gitrwrepo, '58c78e6', True)
rwrepo = self.gitrwrepo
make_object = rwrepo.odb.store
# direct serialization - deserialization can be tested afterwards
# serialization is probably limited on IO
hc = rwrepo.commit(rwrepo.head)
nc = 5000
st = time()
for i in xrange(nc):
cm = Commit(rwrepo,
Commit.NULL_BIN_SHA,
hc.tree,
hc.author,
hc.authored_date,
hc.author_tz_offset,
hc.committer,
hc.committed_date,
hc.committer_tz_offset,
str(i),
parents=hc.parents,
encoding=hc.encoding)
stream = BytesIO()
cm._serialize(stream)
slen = stream.tell()
stream.seek(0)
cm.binsha = make_object(IStream(Commit.type, slen, stream)).binsha
# END commit creation
elapsed = time() - st
print(
"Serialized %i commits to loose objects in %f s ( %f commits / s )"
% (nc, elapsed, nc / elapsed),
file=sys.stderr)
def rev_parse(repo, rev):
"""
:return: Object at the given revision, either Commit, Tag, Tree or Blob
:param rev: git-rev-parse compatible revision specification as string, please see
http://www.kernel.org/pub/software/scm/git/docs/git-rev-parse.html
for details
:raise BadObject: if the given revision could not be found
:raise ValueError: If rev couldn't be parsed
:raise IndexError: If invalid reflog index is specified"""
# colon search mode ?
if rev.startswith(':/'):
# colon search mode
raise NotImplementedError("commit by message search ( regex )")
# END handle search
obj = None
ref = None
output_type = "commit"
start = 0
parsed_to = 0
lr = len(rev)
while start < lr:
if rev[start] not in "^~:@":
start += 1
continue
# END handle start
token = rev[start]
if obj is None:
# token is a rev name
if start == 0:
ref = repo.head.ref
else:
if token == '@':
ref = name_to_object(repo, rev[:start], return_ref=True)
else:
obj = name_to_object(repo, rev[:start])
# END handle token
# END handle refname
if ref is not None:
obj = ref.commit
# END handle ref
# END initialize obj on first token
start += 1
# try to parse {type}
if start < lr and rev[start] == '{':
end = rev.find('}', start)
if end == -1:
raise ValueError("Missing closing brace to define type in %s" %
rev)
output_type = rev[start + 1:end] # exclude brace
# handle type
if output_type == 'commit':
pass # default
elif output_type == 'tree':
try:
obj = to_commit(obj).tree
except (AttributeError, ValueError):
pass # error raised later
# END exception handling
elif output_type in ('', 'blob'):
if obj.type == 'tag':
obj = deref_tag(obj)
else:
# cannot do anything for non-tags
pass
# END handle tag
elif token == '@':
# try single int
assert ref is not None, "Requre Reference to access reflog"
revlog_index = None
try:
# transform reversed index into the format of our revlog
revlog_index = -(int(output_type) + 1)
except ValueError:
# TODO: Try to parse the other date options, using parse_date
# maybe
raise NotImplementedError(
"Support for additional @{...} modes not implemented")
# END handle revlog index
try:
entry = ref.log_entry(revlog_index)
except IndexError:
raise IndexError("Invalid revlog index: %i" % revlog_index)
# END handle index out of bound
obj = Object.new_from_sha(repo, hex_to_bin(entry.newhexsha))
# make it pass the following checks
output_type = None
else:
raise ValueError("Invalid output type: %s ( in %s )" %
(output_type, rev))
# END handle output type
# empty output types don't require any specific type, its just about dereferencing tags
if output_type and obj.type != output_type:
raise ValueError(
"Could not accommodate requested object type %r, got %s" %
(output_type, obj.type))
# END verify output type
start = end + 1 # skip brace
parsed_to = start
continue
# END parse type
# try to parse a number
num = 0
if token != ":":
found_digit = False
while start < lr:
if rev[start] in digits:
num = num * 10 + int(rev[start])
start += 1
found_digit = True
else:
break
# END handle number
# END number parse loop
# no explicit number given, 1 is the default
# It could be 0 though
if not found_digit:
num = 1
# END set default num
# END number parsing only if non-blob mode
parsed_to = start
# handle hierarchy walk
try:
if token == "~":
obj = to_commit(obj)
for _ in xrange(num):
obj = obj.parents[0]
# END for each history item to walk
elif token == "^":
obj = to_commit(obj)
# must be n'th parent
if num:
obj = obj.parents[num - 1]
elif token == ":":
if obj.type != "tree":
obj = obj.tree
# END get tree type
obj = obj[rev[start:]]
parsed_to = lr
else:
raise ValueError("Invalid token: %r" % token)
# END end handle tag
except (IndexError, AttributeError):
raise BadName(
"Invalid revision spec '%s' - not enough parent commits to reach '%s%i'"
% (rev, token, num))
# END exception handling
# END parse loop
# still no obj ? Its probably a simple name
if obj is None:
obj = name_to_object(repo, rev)
parsed_to = lr
# END handle simple name
if obj is None:
raise ValueError("Revision specifier could not be parsed: %s" % rev)
if parsed_to != lr:
raise ValueError(
"Didn't consume complete rev spec %s, consumed part: %s" %
(rev, rev[:parsed_to]))
return obj
def move(self, items, skip_errors=False, **kwargs):
"""Rename/move the items, whereas the last item is considered the destination of
the move operation. If the destination is a file, the first item ( of two )
must be a file as well. If the destination is a directory, it may be preceeded
by one or more directories or files.
The working tree will be affected in non-bare repositories.
:parma items:
Multiple types of items are supported, please see the 'remove' method
for reference.
:param skip_errors:
If True, errors such as ones resulting from missing source files will
be skpped.
:param kwargs:
Additional arguments you would like to pass to git-mv, such as dry_run
or force.
:return:List(tuple(source_path_string, destination_path_string), ...)
A list of pairs, containing the source file moved as well as its
actual destination. Relative to the repository root.
:raise ValueErorr: If only one item was given
GitCommandError: If git could not handle your request"""
args = list()
if skip_errors:
args.append('-k')
paths = self._items_to_rela_paths(items)
if len(paths) < 2:
raise ValueError(
"Please provide at least one source and one destination of the move operation"
)
was_dry_run = kwargs.pop('dry_run', kwargs.pop('n', None))
kwargs['dry_run'] = True
# first execute rename in dryrun so the command tells us what it actually does
# ( for later output )
out = list()
mvlines = self.repo.git.mv(args, paths, **kwargs).splitlines()
# parse result - first 0:n/2 lines are 'checking ', the remaining ones
# are the 'renaming' ones which we parse
for ln in xrange(int(len(mvlines) / 2), len(mvlines)):
tokens = mvlines[ln].split(' to ')
assert len(tokens) == 2, "Too many tokens in %s" % mvlines[ln]
# [0] = Renaming x
# [1] = y
out.append((tokens[0][9:], tokens[1]))
# END for each line to parse
# either prepare for the real run, or output the dry-run result
if was_dry_run:
return out
# END handle dryrun
# now apply the actual operation
kwargs.pop('dry_run')
self.repo.git.mv(args, paths, **kwargs)
return out
def move(self, items, skip_errors=False, **kwargs):
"""Rename/move the items, whereas the last item is considered the destination of
the move operation. If the destination is a file, the first item ( of two )
must be a file as well. If the destination is a directory, it may be preceeded
by one or more directories or files.
The working tree will be affected in non-bare repositories.
:parma items:
Multiple types of items are supported, please see the 'remove' method
for reference.
:param skip_errors:
If True, errors such as ones resulting from missing source files will
be skpped.
:param kwargs:
Additional arguments you would like to pass to git-mv, such as dry_run
or force.
:return:List(tuple(source_path_string, destination_path_string), ...)
A list of pairs, containing the source file moved as well as its
actual destination. Relative to the repository root.
:raise ValueErorr: If only one item was given
GitCommandError: If git could not handle your request"""
args = list()
if skip_errors:
args.append('-k')
paths = self._items_to_rela_paths(items)
if len(paths) < 2:
raise ValueError("Please provide at least one source and one destination of the move operation")
was_dry_run = kwargs.pop('dry_run', kwargs.pop('n', None))
kwargs['dry_run'] = True
# first execute rename in dryrun so the command tells us what it actually does
# ( for later output )
out = list()
mvlines = self.repo.git.mv(args, paths, **kwargs).splitlines()
# parse result - first 0:n/2 lines are 'checking ', the remaining ones
# are the 'renaming' ones which we parse
for ln in xrange(int(len(mvlines) / 2), len(mvlines)):
tokens = mvlines[ln].split(' to ')
assert len(tokens) == 2, "Too many tokens in %s" % mvlines[ln]
# [0] = Renaming x
# [1] = y
out.append((tokens[0][9:], tokens[1]))
# END for each line to parse
# either prepare for the real run, or output the dry-run result
if was_dry_run:
return out
# END handle dryrun
# now apply the actual operation
kwargs.pop('dry_run')
self.repo.git.mv(args, paths, **kwargs)
return out
def rev_parse(repo, rev):
"""
:return: Object at the given revision, either Commit, Tag, Tree or Blob
:param rev: git-rev-parse compatible revision specification as string, please see
http://www.kernel.org/pub/software/scm/git/docs/git-rev-parse.html
for details
:raise BadObject: if the given revision could not be found
:raise ValueError: If rev couldn't be parsed
:raise IndexError: If invalid reflog index is specified"""
# colon search mode ?
if rev.startswith(':/'):
# colon search mode
raise NotImplementedError("commit by message search ( regex )")
# END handle search
obj = None
ref = None
output_type = "commit"
start = 0
parsed_to = 0
lr = len(rev)
while start < lr:
if rev[start] not in "^~:@":
start += 1
continue
# END handle start
token = rev[start]
if obj is None:
# token is a rev name
if start == 0:
ref = repo.head.ref
else:
if token == '@':
ref = name_to_object(repo, rev[:start], return_ref=True)
else:
obj = name_to_object(repo, rev[:start])
# END handle token
# END handle refname
if ref is not None:
obj = ref.commit
# END handle ref
# END initialize obj on first token
start += 1
# try to parse {type}
if start < lr and rev[start] == '{':
end = rev.find('}', start)
if end == -1:
raise ValueError("Missing closing brace to define type in %s" % rev)
output_type = rev[start + 1:end] # exclude brace
# handle type
if output_type == 'commit':
pass # default
elif output_type == 'tree':
try:
obj = to_commit(obj).tree
except (AttributeError, ValueError):
pass # error raised later
# END exception handling
elif output_type in ('', 'blob'):
if obj.type == 'tag':
obj = deref_tag(obj)
else:
# cannot do anything for non-tags
pass
# END handle tag
elif token == '@':
# try single int
assert ref is not None, "Requre Reference to access reflog"
revlog_index = None
try:
# transform reversed index into the format of our revlog
revlog_index = -(int(output_type) + 1)
except ValueError:
# TODO: Try to parse the other date options, using parse_date
# maybe
raise NotImplementedError("Support for additional @{...} modes not implemented")
# END handle revlog index
try:
entry = ref.log_entry(revlog_index)
except IndexError:
raise IndexError("Invalid revlog index: %i" % revlog_index)
# END handle index out of bound
obj = Object.new_from_sha(repo, hex_to_bin(entry.newhexsha))
# make it pass the following checks
output_type = None
else:
raise ValueError("Invalid output type: %s ( in %s )" % (output_type, rev))
# END handle output type
# empty output types don't require any specific type, its just about dereferencing tags
if output_type and obj.type != output_type:
raise ValueError("Could not accomodate requested object type %r, got %s" % (output_type, obj.type))
# END verify ouput type
start = end + 1 # skip brace
parsed_to = start
continue
# END parse type
# try to parse a number
num = 0
if token != ":":
found_digit = False
while start < lr:
if rev[start] in digits:
num = num * 10 + int(rev[start])
start += 1
found_digit = True
else:
break
# END handle number
# END number parse loop
# no explicit number given, 1 is the default
# It could be 0 though
if not found_digit:
num = 1
# END set default num
# END number parsing only if non-blob mode
parsed_to = start
# handle hiererarchy walk
try:
if token == "~":
obj = to_commit(obj)
for item in xrange(num):
obj = obj.parents[0]
# END for each history item to walk
elif token == "^":
obj = to_commit(obj)
# must be n'th parent
if num:
obj = obj.parents[num - 1]
elif token == ":":
if obj.type != "tree":
obj = obj.tree
# END get tree type
obj = obj[rev[start:]]
parsed_to = lr
else:
raise ValueError("Invalid token: %r" % token)
# END end handle tag
except (IndexError, AttributeError):
raise BadName("Invalid revision spec '%s' - not enough parent commits to reach '%s%i'" % (rev, token, num))
# END exception handling
# END parse loop
# still no obj ? Its probably a simple name
if obj is None:
obj = name_to_object(repo, rev)
parsed_to = lr
# END handle simple name
if obj is None:
raise ValueError("Revision specifier could not be parsed: %s" % rev)
if parsed_to != lr:
raise ValueError("Didn't consume complete rev spec %s, consumed part: %s" % (rev, rev[:parsed_to]))
return obj