X-Git-Url: https://git.distorted.org.uk/~mdw/stgit/blobdiff_plain/7a6a45b5f1379466bd23b33a7feed47d0b8331b7..1de97e5f5e62a46d69515052a860138e417f149b:/stgit/lib/git.py diff --git a/stgit/lib/git.py b/stgit/lib/git.py index 6ccdfa7..9c530c7 100644 --- a/stgit/lib/git.py +++ b/stgit/lib/git.py @@ -139,6 +139,7 @@ class Person(Immutable, Repr): assert isinstance(self.__date, Date) or self.__date in [None, NoValue] name = property(lambda self: self.__name) email = property(lambda self: self.__email) + name_email = property(lambda self: '%s <%s>' % (self.name, self.email)) date = property(lambda self: self.__date) def set_name(self, name): return type(self)(name = name, defaults = self) @@ -147,7 +148,7 @@ class Person(Immutable, Repr): def set_date(self, date): return type(self)(date = date, defaults = self) def __str__(self): - return '%s <%s> %s' % (self.name, self.email, self.date) + return '%s %s' % (self.name_email, self.date) @classmethod def parse(cls, s): m = re.match(r'^([^<]*)<([^>]*)>\s+(\d+\s+[+-]\d{4})$', s) @@ -182,16 +183,142 @@ class Person(Immutable, Repr): defaults = cls.user()) return cls.__committer -class Tree(Immutable, Repr): - """Represents a git tree object.""" - def __init__(self, sha1): +class GitObject(Immutable, Repr): + """Base class for all git objects. One git object is represented by at + most one C{GitObject}, which makes it possible to compare them + using normal Python object comparison; it also ensures we don't + waste more memory than necessary.""" + +class BlobData(Immutable, Repr): + """Represents the data contents of a git blob object.""" + def __init__(self, string): + self.__string = str(string) + str = property(lambda self: self.__string) + def commit(self, repository): + """Commit the blob. + @return: The committed blob + @rtype: L{Blob}""" + sha1 = repository.run(['git', 'hash-object', '-w', '--stdin'] + ).raw_input(self.str).output_one_line() + return repository.get_blob(sha1) + +class Blob(GitObject): + """Represents a git blob object. All the actual data contents of the + blob object is stored in the L{data} member, which is a + L{BlobData} object.""" + typename = 'blob' + default_perm = '100644' + def __init__(self, repository, sha1): + self.__repository = repository self.__sha1 = sha1 sha1 = property(lambda self: self.__sha1) def __str__(self): - return 'Tree<%s>' % self.sha1 + return 'Blob<%s>' % self.sha1 + @property + def data(self): + return BlobData(self.__repository.cat_object(self.sha1)) + +class ImmutableDict(dict): + """A dictionary that cannot be modified once it's been created.""" + def error(*args, **kwargs): + raise TypeError('Cannot modify immutable dict') + __delitem__ = error + __setitem__ = error + clear = error + pop = error + popitem = error + setdefault = error + update = error + +class TreeData(Immutable, Repr): + """Represents the data contents of a git tree object.""" + @staticmethod + def __x(po): + if isinstance(po, GitObject): + perm, object = po.default_perm, po + else: + perm, object = po + return perm, object + def __init__(self, entries): + """Create a new L{TreeData} object from the given mapping from names + (strings) to either (I{permission}, I{object}) tuples or just + objects.""" + self.__entries = ImmutableDict((name, self.__x(po)) + for (name, po) in entries.iteritems()) + entries = property(lambda self: self.__entries) + """Map from name to (I{permission}, I{object}) tuple.""" + def set_entry(self, name, po): + """Create a new L{TreeData} object identical to this one, except that + it maps C{name} to C{po}. + + @param name: Name of the changed mapping + @type name: C{str} + @param po: Value of the changed mapping + @type po: L{Blob} or L{Tree} or (C{str}, L{Blob} or L{Tree}) + @return: The new L{TreeData} object + @rtype: L{TreeData}""" + e = dict(self.entries) + e[name] = self.__x(po) + return type(self)(e) + def del_entry(self, name): + """Create a new L{TreeData} object identical to this one, except that + it doesn't map C{name} to anything. + + @param name: Name of the deleted mapping + @type name: C{str} + @return: The new L{TreeData} object + @rtype: L{TreeData}""" + e = dict(self.entries) + del e[name] + return type(self)(e) + def commit(self, repository): + """Commit the tree. + @return: The committed tree + @rtype: L{Tree}""" + listing = ''.join( + '%s %s %s\t%s\0' % (mode, obj.typename, obj.sha1, name) + for (name, (mode, obj)) in self.entries.iteritems()) + sha1 = repository.run(['git', 'mktree', '-z'] + ).raw_input(listing).output_one_line() + return repository.get_tree(sha1) + @classmethod + def parse(cls, repository, s): + """Parse a raw git tree description. + + @return: A new L{TreeData} object + @rtype: L{TreeData}""" + entries = {} + for line in s.split('\0')[:-1]: + m = re.match(r'^([0-7]{6}) ([a-z]+) ([0-9a-f]{40})\t(.*)$', line) + assert m + perm, type, sha1, name = m.groups() + entries[name] = (perm, repository.get_object(type, sha1)) + return cls(entries) + +class Tree(GitObject): + """Represents a git tree object. All the actual data contents of the + tree object is stored in the L{data} member, which is a + L{TreeData} object.""" + typename = 'tree' + default_perm = '040000' + def __init__(self, repository, sha1): + self.__sha1 = sha1 + self.__repository = repository + self.__data = None + sha1 = property(lambda self: self.__sha1) + @property + def data(self): + if self.__data == None: + self.__data = TreeData.parse( + self.__repository, + self.__repository.run(['git', 'ls-tree', '-z', self.sha1] + ).raw_output()) + return self.__data + def __str__(self): + return 'Tree' % self.sha1 class CommitData(Immutable, Repr): - """Represents the actual data contents of a git commit object.""" + """Represents the data contents of a git commit object.""" def __init__(self, tree = NoValue, parents = NoValue, author = NoValue, committer = NoValue, message = NoValue, defaults = NoValue): d = make_defaults(defaults) @@ -238,8 +365,30 @@ class CommitData(Immutable, Repr): return ('CommitData' ) % (tree, parents, self.author, self.committer, self.message) + def commit(self, repository): + """Commit the commit. + @return: The committed commit + @rtype: L{Commit}""" + c = ['git', 'commit-tree', self.tree.sha1] + for p in self.parents: + c.append('-p') + c.append(p.sha1) + env = {} + for p, v1 in ((self.author, 'AUTHOR'), + (self.committer, 'COMMITTER')): + if p != None: + for attr, v2 in (('name', 'NAME'), ('email', 'EMAIL'), + ('date', 'DATE')): + if getattr(p, attr) != None: + env['GIT_%s_%s' % (v1, v2)] = str(getattr(p, attr)) + sha1 = repository.run(c, env = env).raw_input(self.message + ).output_one_line() + return repository.get_commit(sha1) @classmethod def parse(cls, repository, s): + """Parse a raw git commit description. + @return: A new L{CommitData} object + @rtype: L{CommitData}""" cd = cls(parents = []) lines = list(s.splitlines(True)) for i in xrange(len(lines)): @@ -259,10 +408,11 @@ class CommitData(Immutable, Repr): assert False assert False -class Commit(Immutable, Repr): +class Commit(GitObject): """Represents a git commit object. All the actual data contents of the commit object is stored in the L{data} member, which is a L{CommitData} object.""" + typename = 'commit' def __init__(self, repository, sha1): self.__sha1 = sha1 self.__repository = repository @@ -361,13 +511,22 @@ class RunWithEnvCwd(RunWithEnv): @type env: dict @param env: Extra environment""" return RunWithEnv.run(self, args, env).cwd(self.cwd) + def run_in_cwd(self, args): + """Run the given command with an environment given by self.env and + self.env_in_cwd, without changing the current working + directory. + + @type args: list of strings + @param args: Command and argument vector""" + return RunWithEnv.run(self, args, self.env_in_cwd) class Repository(RunWithEnv): """Represents a git repository.""" def __init__(self, directory): self.__git_dir = directory self.__refs = Refs(self) - self.__trees = ObjectCache(lambda sha1: Tree(sha1)) + self.__blobs = ObjectCache(lambda sha1: Blob(self, sha1)) + self.__trees = ObjectCache(lambda sha1: Tree(self, sha1)) self.__commits = ObjectCache(lambda sha1: Commit(self, sha1)) self.__default_index = None self.__default_worktree = None @@ -384,7 +543,7 @@ class Repository(RunWithEnv): @property def current_branch_name(self): """Return the name of the current branch.""" - return utils.strip_leading('refs/heads/', self.head_ref) + return utils.strip_prefix('refs/heads/', self.head_ref) @property def default_index(self): """An L{Index} object representing the default index file for the @@ -422,33 +581,25 @@ class Repository(RunWithEnv): refs = property(lambda self: self.__refs) def cat_object(self, sha1): return self.run(['git', 'cat-file', '-p', sha1]).raw_output() - def rev_parse(self, rev): + def rev_parse(self, rev, discard_stderr = False): try: return self.get_commit(self.run( ['git', 'rev-parse', '%s^{commit}' % rev] - ).output_one_line()) + ).discard_stderr(discard_stderr).output_one_line()) except run.RunException: raise RepositoryException('%s: No such revision' % rev) + def get_blob(self, sha1): + return self.__blobs[sha1] def get_tree(self, sha1): return self.__trees[sha1] def get_commit(self, sha1): return self.__commits[sha1] - def commit(self, commitdata): - c = ['git', 'commit-tree', commitdata.tree.sha1] - for p in commitdata.parents: - c.append('-p') - c.append(p.sha1) - env = {} - for p, v1 in ((commitdata.author, 'AUTHOR'), - (commitdata.committer, 'COMMITTER')): - if p != None: - for attr, v2 in (('name', 'NAME'), ('email', 'EMAIL'), - ('date', 'DATE')): - if getattr(p, attr) != None: - env['GIT_%s_%s' % (v1, v2)] = str(getattr(p, attr)) - sha1 = self.run(c, env = env).raw_input(commitdata.message - ).output_one_line() - return self.get_commit(sha1) + def get_object(self, type, sha1): + return { Blob.typename: self.get_blob, + Tree.typename: self.get_tree, + Commit.typename: self.get_commit }[type](sha1) + def commit(self, objectdata): + return objectdata.commit(self) @property def head_ref(self): try: @@ -459,31 +610,13 @@ class Repository(RunWithEnv): def set_head_ref(self, ref, msg): self.run(['git', 'symbolic-ref', '-m', msg, 'HEAD', ref]).no_output() def simple_merge(self, base, ours, theirs): - """Given three L{Tree}s, tries to do an in-index merge with a - temporary index. Returns the result L{Tree}, or None if the - merge failed (due to conflicts).""" - assert isinstance(base, Tree) - assert isinstance(ours, Tree) - assert isinstance(theirs, Tree) - - # Take care of the really trivial cases. - if base == ours: - return theirs - if base == theirs: - return ours - if ours == theirs: - return ours - index = self.temp_index() try: - index.merge(base, ours, theirs) - try: - return index.write_tree() - except MergeException: - return None + result, index_tree = index.merge(base, ours, theirs) finally: index.delete() - def apply(self, tree, patch_text): + return result + def apply(self, tree, patch_text, quiet): """Given a L{Tree} and a patch, will either return the new L{Tree} that results when the patch is applied, or None if the patch couldn't be applied.""" @@ -494,7 +627,7 @@ class Repository(RunWithEnv): try: index.read_tree(tree) try: - index.apply(patch_text) + index.apply(patch_text, quiet) return index.write_tree() except MergeException: return None @@ -512,12 +645,41 @@ class Repository(RunWithEnv): assert isinstance(t2, Tree) return self.run(['git', 'diff-tree', '-p'] + list(diff_opts) + [t1.sha1, t2.sha1]).raw_output() + def diff_tree_files(self, t1, t2): + """Given two L{Tree}s C{t1} and C{t2}, iterate over all files for + which they differ. For each file, yield a tuple with the old + file mode, the new file mode, the old blob, the new blob, the + status, the old filename, and the new filename. Except in case + of a copy or a rename, the old and new filenames are + identical.""" + assert isinstance(t1, Tree) + assert isinstance(t2, Tree) + i = iter(self.run(['git', 'diff-tree', '-r', '-z'] + [t1.sha1, t2.sha1] + ).raw_output().split('\0')) + try: + while True: + x = i.next() + if not x: + continue + omode, nmode, osha1, nsha1, status = x[1:].split(' ') + fn1 = i.next() + if status[0] in ['C', 'R']: + fn2 = i.next() + else: + fn2 = fn1 + yield (omode, nmode, self.get_blob(osha1), + self.get_blob(nsha1), status, fn1, fn2) + except StopIteration: + pass class MergeException(exception.StgException): """Exception raised when a merge fails for some reason.""" class MergeConflictException(MergeException): """Exception raised when a merge fails due to conflicts.""" + def __init__(self, conflicts): + MergeException.__init__(self) + self.conflicts = conflicts class Index(RunWithEnv): """Represents a git index file.""" @@ -535,30 +697,81 @@ class Index(RunWithEnv): def read_tree(self, tree): self.run(['git', 'read-tree', tree.sha1]).no_output() def write_tree(self): + """Write the index contents to the repository. + @return: The resulting L{Tree} + @rtype: L{Tree}""" try: return self.__repository.get_tree( self.run(['git', 'write-tree']).discard_stderr( ).output_one_line()) except run.RunException: raise MergeException('Conflicting merge') - def is_clean(self): + def is_clean(self, tree): + """Check whether the index is clean relative to the given treeish.""" try: - self.run(['git', 'update-index', '--refresh']).discard_output() + self.run(['git', 'diff-index', '--quiet', '--cached', tree.sha1] + ).discard_output() except run.RunException: return False else: return True - def merge(self, base, ours, theirs): - """In-index merge, no worktree involved.""" - self.run(['git', 'read-tree', '-m', '-i', '--aggressive', - base.sha1, ours.sha1, theirs.sha1]).no_output() - def apply(self, patch_text): + def apply(self, patch_text, quiet): """In-index patch application, no worktree involved.""" try: - self.run(['git', 'apply', '--cached'] - ).raw_input(patch_text).no_output() + r = self.run(['git', 'apply', '--cached']).raw_input(patch_text) + if quiet: + r = r.discard_stderr() + r.no_output() except run.RunException: raise MergeException('Patch does not apply cleanly') + def apply_treediff(self, tree1, tree2, quiet): + """Apply the diff from C{tree1} to C{tree2} to the index.""" + # Passing --full-index here is necessary to support binary + # files. It is also sufficient, since the repository already + # contains all involved objects; in other words, we don't have + # to use --binary. + self.apply(self.__repository.diff_tree(tree1, tree2, ['--full-index']), + quiet) + def merge(self, base, ours, theirs, current = None): + """Use the index (and only the index) to do a 3-way merge of the + L{Tree}s C{base}, C{ours} and C{theirs}. The merge will either + succeed (in which case the first half of the return value is + the resulting tree) or fail cleanly (in which case the first + half of the return value is C{None}). + + If C{current} is given (and not C{None}), it is assumed to be + the L{Tree} currently stored in the index; this information is + used to avoid having to read the right tree (either of C{ours} + and C{theirs}) into the index if it's already there. The + second half of the return value is the tree now stored in the + index, or C{None} if unknown. If the merge succeeded, this is + often the merge result.""" + assert isinstance(base, Tree) + assert isinstance(ours, Tree) + assert isinstance(theirs, Tree) + assert current == None or isinstance(current, Tree) + + # Take care of the really trivial cases. + if base == ours: + return (theirs, current) + if base == theirs: + return (ours, current) + if ours == theirs: + return (ours, current) + + if current == theirs: + # Swap the trees. It doesn't matter since merging is + # symmetric, and will allow us to avoid the read_tree() + # call below. + ours, theirs = theirs, ours + if current != ours: + self.read_tree(ours) + try: + self.apply_treediff(base, theirs, quiet = True) + result = self.write_tree() + return (result, result) + except MergeException: + return (None, ours) def delete(self): if os.path.isfile(self.__filename): os.remove(self.__filename) @@ -576,6 +789,7 @@ class Worktree(object): def __init__(self, directory): self.__directory = directory env = property(lambda self: { 'GIT_WORK_TREE': '.' }) + env_in_cwd = property(lambda self: { 'GIT_WORK_TREE': self.directory }) directory = property(lambda self: self.__directory) class CheckoutException(exception.StgException): @@ -592,7 +806,12 @@ class IndexAndWorktree(RunWithEnvCwd): index = property(lambda self: self.__index) env = property(lambda self: utils.add_dict(self.__index.env, self.__worktree.env)) + env_in_cwd = property(lambda self: self.__worktree.env_in_cwd) cwd = property(lambda self: self.__worktree.directory) + def checkout_hard(self, tree): + assert isinstance(tree, Tree) + self.run(['git', 'read-tree', '--reset', '-u', tree.sha1] + ).discard_output() def checkout(self, old_tree, new_tree): # TODO: Optionally do a 3-way instead of doing nothing when we # have a problem. Or maybe we should stash changes in a patch? @@ -605,7 +824,7 @@ class IndexAndWorktree(RunWithEnvCwd): ).discard_output() except run.RunException: raise CheckoutException('Index/workdir dirty') - def merge(self, base, ours, theirs): + def merge(self, base, ours, theirs, interactive = False): assert isinstance(base, Tree) assert isinstance(ours, Tree) assert isinstance(theirs, Tree) @@ -615,17 +834,53 @@ class IndexAndWorktree(RunWithEnvCwd): env = { 'GITHEAD_%s' % base.sha1: 'ancestor', 'GITHEAD_%s' % ours.sha1: 'current', 'GITHEAD_%s' % theirs.sha1: 'patched'}) - r.discard_output() + r.returns([0, 1]) + output = r.output_lines() + if r.exitcode: + # There were conflicts + if interactive: + self.mergetool() + else: + conflicts = [l for l in output if l.startswith('CONFLICT')] + raise MergeConflictException(conflicts) except run.RunException, e: - if r.exitcode == 1: - raise MergeConflictException() - else: - raise MergeException('Index/worktree dirty') - def changed_files(self): - return self.run(['git', 'diff-files', '--name-only']).output_lines() - def update_index(self, files): - self.run(['git', 'update-index', '--remove', '-z', '--stdin'] - ).input_nulterm(files).discard_output() + raise MergeException('Index/worktree dirty') + def mergetool(self, files = ()): + """Invoke 'git mergetool' on the current IndexAndWorktree to resolve + any outstanding conflicts. If 'not files', all the files in an + unmerged state will be processed.""" + self.run(['git', 'mergetool'] + list(files)).returns([0, 1]).run() + # check for unmerged entries (prepend 'CONFLICT ' for consistency with + # merge()) + conflicts = ['CONFLICT ' + f for f in self.index.conflicts()] + if conflicts: + raise MergeConflictException(conflicts) + def changed_files(self, tree, pathlimits = []): + """Return the set of files in the worktree that have changed with + respect to C{tree}. The listing is optionally restricted to + those files that match any of the path limiters given. + + The path limiters are relative to the current working + directory; the returned file names are relative to the + repository root.""" + assert isinstance(tree, Tree) + return set(self.run_in_cwd( + ['git', 'diff-index', tree.sha1, '--name-only', '-z', '--'] + + list(pathlimits)).raw_output().split('\0')[:-1]) + def update_index(self, paths): + """Update the index with files from the worktree. C{paths} is an + iterable of paths relative to the root of the repository.""" + cmd = ['git', 'update-index', '--remove'] + self.run(cmd + ['-z', '--stdin'] + ).input_nulterm(paths).discard_output() + def worktree_clean(self): + """Check whether the worktree is clean relative to index.""" + try: + self.run(['git', 'update-index', '--refresh']).discard_output() + except run.RunException: + return False + else: + return True class Branch(object): """Represents a Git branch.""" @@ -673,3 +928,8 @@ class Branch(object): repository.run(['git', 'branch', create_at.sha1]).discard_output() return cls(repository, name) + +def diffstat(diff): + """Return the diffstat of the supplied diff.""" + return run.Run('git', 'apply', '--stat', '--summary' + ).raw_input(diff).raw_output()