diff --git a/swh/loader/svn/ra.py b/swh/loader/svn/ra.py index f126082..94d468c 100644 --- a/swh/loader/svn/ra.py +++ b/swh/loader/svn/ra.py @@ -1,489 +1,489 @@ # Copyright (C) 2016-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information """Remote Access client to svn server. """ import click import os import shutil import tempfile from subvertpy import delta, properties from subvertpy.ra import RemoteAccess, Auth, get_username_provider from swh.model import hashutil from swh.model.from_disk import Content, Directory _eol_style = { 'native': b'\n', 'CRLF': b'\r\n', 'LF': b'\n', 'CR': b'\r' } def _normalize_line_endings(lines, eol_style='native'): """Normalize line endings to unix (\n), windows (\r\n) or mac (\r). Args: lines (bytes): The lines to normalize line_ending (str): The line ending format as defined for svn:eol-style property. Acceptable values are 'native', 'CRLF', 'LF' and 'CR' Returns bytes: lines with endings normalized """ lines = lines.replace(_eol_style['CRLF'], _eol_style['LF'])\ .replace(_eol_style['CR'], _eol_style['LF']) if _eol_style[eol_style] != _eol_style['LF']: lines = lines.replace(_eol_style['LF'], _eol_style[eol_style]) return lines def apply_txdelta_handler(sbuf, target_stream): """Return a function that can be called repeatedly with txdelta windows. When done, closes the target_stream. Adapted from subvertpy.delta.apply_txdelta_handler to close the stream when done. Args: sbuf: Source buffer target_stream: Target stream to write to. Returns: Function to be called to apply txdelta windows """ def apply_window(window, sbuf=sbuf, target_stream=target_stream): if window is None: target_stream.close() return # Last call patch = delta.apply_txdelta_window(sbuf, window) target_stream.write(patch) return apply_window def read_svn_link(data): """Read the svn link's content. Args: data (bytes): svn link's raw content Returns: The tuple of (filetype, destination path) """ split_byte = b' ' filetype, *src = data.split(split_byte) src = split_byte.join(src) return filetype, src def is_file_an_svnlink_p(fullpath): """Determine if a filepath is an svnlink or something else. Args: fullpath (str/bytes): Full path to the potential symlink to check Return: boolean value to determine if it's indeed a symlink (as per svn) or not. """ with open(fullpath, 'rb') as f: filetype, src = read_svn_link(f.read()) return filetype == b'link', src DEFAULT_FLAG = 0 EXEC_FLAG = 1 NOEXEC_FLAG = 2 SVN_PROPERTY_EOL = 'svn:eol-style' # EOL state check mess EOL_STYLE = {} -class SWHFileEditor: +class FileEditor: """File Editor in charge of updating file on disk and memory objects. """ __slots__ = ['directory', 'path', 'fullpath', 'executable', 'link'] def __init__(self, directory, rootpath, path): self.directory = directory self.path = path # default value: 0, 1: set the flag, 2: remove the exec flag self.executable = DEFAULT_FLAG self.link = None self.fullpath = os.path.join(rootpath, path) def change_prop(self, key, value): if key == properties.PROP_EXECUTABLE: if value is None: # bit flip off self.executable = NOEXEC_FLAG else: self.executable = EXEC_FLAG elif key == properties.PROP_SPECIAL: # Possibly a symbolic link. We cannot check further at # that moment though, patch(s) not being applied yet self.link = True elif key == SVN_PROPERTY_EOL: # backup end of line style for file EOL_STYLE[self.fullpath] = value def __make_symlink(self, src): """Convert the svnlink to a symlink on disk. This function expects self.fullpath to be a svn link. Args: src (bytes): Path to the link's source Return: tuple: The svnlink's data tuple: - type (should be only 'link') - """ os.remove(self.fullpath) os.symlink(src=src, dst=self.fullpath) def __make_svnlink(self): """Convert the symlink to a svnlink on disk. Return: The symlink's svnlink data (``b'type '``) """ # we replace the symlink by a svnlink # to be able to patch the file on future commits src = os.readlink(self.fullpath) os.remove(self.fullpath) sbuf = b'link ' + src with open(self.fullpath, 'wb') as f: f.write(sbuf) return sbuf def apply_textdelta(self, base_checksum): if os.path.lexists(self.fullpath): if os.path.islink(self.fullpath): # svn does not deal with symlink so we transform into # real svn symlink for potential patching in later # commits sbuf = self.__make_svnlink() self.link = True else: with open(self.fullpath, 'rb') as f: sbuf = f.read() else: sbuf = b'' t = open(self.fullpath, 'wb') return apply_txdelta_handler(sbuf, target_stream=t) def close(self): """When done with the file, this is called. So the file exists and is updated, we can: - adapt accordingly its execution flag if any - compute the objects' checksums - replace the svnlink with a real symlink (for disk computation purposes) """ is_link = None if self.link: # can only check now that the link is a real one # since patch has been applied is_link, src = is_file_an_svnlink_p(self.fullpath) if is_link: self.__make_symlink(src) else: # not a real link... self.link = False if not is_link: # if a link, do nothing regarding flag if self.executable == EXEC_FLAG: os.chmod(self.fullpath, 0o755) elif self.executable == NOEXEC_FLAG: os.chmod(self.fullpath, 0o644) # And now compute file's checksums eol_style = EOL_STYLE.get(self.fullpath, None) if eol_style: # ensure to normalize line endings as defined by svn:eol-style # property to get the same file checksum as after an export # or checkout operation with subversion with open(self.fullpath, 'rb') as f: data = f.read() data = _normalize_line_endings(data, eol_style) mode = os.lstat(self.fullpath).st_mode self.directory[self.path] = Content.from_bytes(mode=mode, data=data) else: self.directory[self.path] = Content.from_file(path=self.fullpath, data=True) -class BaseDirSWHEditor: +class BaseDirEditor: """Base class implementation of dir editor. - see :class:`SWHDirEditor` for an implementation that hashes every + see :class:`DirEditor` for an implementation that hashes every directory encountered. Instantiate a new class inheriting from this class and define the following functions:: def update_checksum(self): # Compute the checksums at current state def open_directory(self, *args): # Update an existing folder. def add_directory(self, *args): # Add a new one. """ __slots__ = ['directory', 'rootpath'] def __init__(self, directory, rootpath): self.directory = directory self.rootpath = rootpath # build directory on init os.makedirs(rootpath, exist_ok=True) def remove_child(self, path): """Remove a path from the current objects. The path can be resolved as link, file or directory. This function takes also care of removing the link between the child and the parent. Args: path: to remove from the current objects. """ try: entry_removed = self.directory[path] except KeyError: entry_removed = None else: del self.directory[path] fpath = os.path.join(self.rootpath, path) if isinstance(entry_removed, Directory): shutil.rmtree(fpath) else: os.remove(fpath) if path in EOL_STYLE: del EOL_STYLE[path] def update_checksum(self): raise NotImplementedError('This should be implemented.') def open_directory(self, *args): raise NotImplementedError('This should be implemented.') def add_directory(self, *args): raise NotImplementedError('This should be implemented.') def open_file(self, *args): """Updating existing file. """ path = os.fsencode(args[0]) self.directory[path] = Content() - return SWHFileEditor(self.directory, rootpath=self.rootpath, path=path) + return FileEditor(self.directory, rootpath=self.rootpath, path=path) def add_file(self, path, copyfrom_path=None, copyfrom_rev=-1): """Creating a new file. """ path = os.fsencode(path) self.directory[path] = Content() - return SWHFileEditor(self.directory, self.rootpath, path) + return FileEditor(self.directory, self.rootpath, path) def change_prop(self, key, value): """Change property callback on directory. """ if key == properties.PROP_EXTERNALS: raise ValueError( "Property '%s' detected. Not implemented yet." % key) def delete_entry(self, path, revision): """Remove a path. """ self.remove_child(path.encode('utf-8')) def close(self): """Function called when we finish walking a repository. """ self.update_checksum() -class SWHDirEditor(BaseDirSWHEditor): +class DirEditor(BaseDirEditor): """Directory Editor in charge of updating directory hashes computation. This implementation includes empty folder in the hash computation. """ def update_checksum(self): """Update the root path self.path's checksums according to the children's objects. This function is expected to be called when the folder has been completely 'walked'. """ pass def open_directory(self, *args): """Updating existing directory. """ return self def add_directory(self, path, copyfrom_path=None, copyfrom_rev=-1): """Adding a new directory. """ path = os.fsencode(path) os.makedirs(os.path.join(self.rootpath, path), exist_ok=True) self.directory[path] = Directory() return self -class SWHEditor: - """SWH Editor in charge of replaying svn events and computing objects - along. +class Editor: + """Editor in charge of replaying svn events and computing objects + along. - This implementation accounts for empty folder during hash - computations. + This implementation accounts for empty folder during hash + computations. """ def __init__(self, rootpath, directory): self.rootpath = rootpath self.directory = directory def set_target_revision(self, revnum): pass def abort(self): pass def close(self): pass def open_root(self, base_revnum): - return SWHDirEditor(self.directory, rootpath=self.rootpath) + return DirEditor(self.directory, rootpath=self.rootpath) -class SWHReplay: +class Replay: """Replay class. """ def __init__(self, conn, rootpath, directory=None): self.conn = conn self.rootpath = rootpath if directory is None: directory = Directory() self.directory = directory - self.editor = SWHEditor(rootpath=rootpath, directory=directory) + self.editor = Editor(rootpath=rootpath, directory=directory) def replay(self, rev): """Replay svn actions between rev and rev+1. This method updates in place the self.editor.directory, as well as the filesystem. Returns: The updated root directory """ self.conn.replay(rev, rev+1, self.editor) return self.editor.directory def compute_hashes(self, rev): """Compute hashes at revisions rev. Expects the state to be at previous revision's objects. Args: rev: The revision to start the replay from. Returns: The updated objects between rev and rev+1. Beware that this mutates the filesystem at rootpath accordingly. """ self.replay(rev) return self.directory.collect() @click.command() @click.option('--local-url', default='/tmp', help="local svn working copy") @click.option('--svn-url', default='file:///home/storage/svn/repos/pkg-fox', help="svn repository's url.") @click.option('--revision-start', default=1, type=click.INT, help="svn repository's starting revision.") @click.option('--revision-end', default=-1, type=click.INT, help="svn repository's ending revision.") @click.option('--debug/--nodebug', default=True, help="Indicates if the server should run in debug mode.") @click.option('--cleanup/--nocleanup', default=True, help="Indicates whether to cleanup disk when done or not.") def main(local_url, svn_url, revision_start, revision_end, debug, cleanup): - """Script to present how to use SWHReplay class. + """Script to present how to use Replay class. """ conn = RemoteAccess(svn_url.encode('utf-8'), auth=Auth([get_username_provider()])) os.makedirs(local_url, exist_ok=True) rootpath = tempfile.mkdtemp(prefix=local_url, suffix='-'+os.path.basename(svn_url)) rootpath = os.fsencode(rootpath) # Do not go beyond the repository's latest revision revision_end_max = conn.get_latest_revnum() if revision_end == -1: revision_end = revision_end_max revision_end = min(revision_end, revision_end_max) try: - replay = SWHReplay(conn, rootpath) + replay = Replay(conn, rootpath) for rev in range(revision_start, revision_end+1): objects = replay.compute_hashes(rev) print("r%s %s (%s new contents, %s new directories)" % ( rev, hashutil.hash_to_hex(replay.directory.hash), len(objects.get('content', {})), len(objects.get('directory', {})), )) if debug: print('%s' % rootpath.decode('utf-8')) finally: if cleanup: if os.path.exists(rootpath): shutil.rmtree(rootpath) if __name__ == '__main__': main() diff --git a/swh/loader/svn/svn.py b/swh/loader/svn/svn.py index 00b832d..35808ea 100644 --- a/swh/loader/svn/svn.py +++ b/swh/loader/svn/svn.py @@ -1,268 +1,268 @@ # Copyright (C) 2015-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information """SVN client in charge of iterating over svn logs and yield commit representations including the hash tree/content computations per svn commit. """ import logging import os import tempfile import shutil from subvertpy.ra import RemoteAccess, Auth, get_username_provider from subvertpy import client, properties from swh.model.from_disk import Directory from . import ra, converters # When log message contains empty data DEFAULT_AUTHOR_MESSAGE = '' class SvnRepo: - """SWH's svn repository representation. + """Svn repository representation. Args: remote_url (str): origin_id (int): Associated origin identifier storage (Storage): Storage to use to execute storage statements local_dirname (str): Path to write intermediary svn action results """ def __init__(self, remote_url, origin_id, storage, local_dirname): self.remote_url = remote_url.rstrip('/') self.storage = storage self.origin_id = origin_id auth = Auth([get_username_provider()]) # one connection for log iteration self.conn_log = RemoteAccess(self.remote_url, auth=auth) # another for replay self.conn = RemoteAccess(self.remote_url, auth=auth) # one client for update operation self.client = client.Client(auth=auth) self.local_dirname = local_dirname local_name = os.path.basename(self.remote_url) self.local_url = os.path.join(self.local_dirname, local_name).encode( 'utf-8') self.uuid = self.conn.get_uuid().encode('utf-8') - self.swhreplay = ra.SWHReplay(conn=self.conn, rootpath=self.local_url) + self.swhreplay = ra.Replay(conn=self.conn, rootpath=self.local_url) def __str__(self): return str({ 'swh-origin': self.origin_id, 'remote_url': self.remote_url, 'local_url': self.local_url, 'uuid': self.uuid, }) def head_revision(self): """Retrieve current head revision. """ return self.conn.get_latest_revnum() def initial_revision(self): """Retrieve the initial revision from which the remote url appeared. """ return 1 def convert_commit_message(self, msg): """Simply encode the commit message. Args: msg (str): the commit message to convert. Returns: The transformed message as bytes. """ if isinstance(msg, bytes): return msg return msg.encode('utf-8') def convert_commit_date(self, date): """Convert the message commit date into a timestamp in swh format. The precision is kept. Args: date (str): the commit date to convert. Returns: The transformed date. """ return converters.svn_date_to_swh_date(date) def convert_commit_author(self, author): """Convert the commit author into an swh person. The user becomes a dictionary of the form:: { name: author, email: '', fullname: author } Args: author (str): the commit author to convert. Returns: The transformed author as dict. """ return converters.svn_author_to_swh_person(author) def __to_entry(self, log_entry): changed_paths, rev, revprops, has_children = log_entry author_date = self.convert_commit_date( revprops.get(properties.PROP_REVISION_DATE)) author = self.convert_commit_author( revprops.get(properties.PROP_REVISION_AUTHOR)) message = self.convert_commit_message( revprops.get(properties.PROP_REVISION_LOG, DEFAULT_AUTHOR_MESSAGE)) return { 'rev': rev, 'author_date': author_date, 'author_name': author, 'message': message, } def logs(self, revision_start, revision_end): """Stream svn logs between revision_start and revision_end by chunks of block_size logs. Yields revision and associated revision information between the revision start and revision_end. Args: revision_start: the svn revision starting bound revision_end: the svn revision ending bound Yields: tuple: tuple of revisions and logs: - revisions: list of revisions in order - logs: Dictionary with key revision number and value the log entry. The log entry is a dictionary with the following keys: - author_date: date of the commit - author_name: name of the author - message: commit message """ for log_entry in self.conn_log.iter_log(paths=None, start=revision_start, end=revision_end, discover_changed_paths=False): yield self.__to_entry(log_entry) def export(self, revision): """Export the repository to a given version. """ self.client.export(self.remote_url, to=self.local_url.decode('utf-8'), rev=revision, ignore_keywords=True) def export_temporary(self, revision): """Export the repository to a given revision in a temporary location. This is up to the caller of this function to clean up the temporary location when done (cf. self.clean_fs method) Args: revision: Revision to export at Returns: The tuple local_dirname the temporary location root folder, local_url where the repository was exported. """ local_dirname = tempfile.mkdtemp( prefix='check-revision-%s.' % revision, dir=self.local_dirname) local_name = os.path.basename(self.remote_url) local_url = os.path.join(local_dirname, local_name) self.client.export( self.remote_url, to=local_url, rev=revision, ignore_keywords=True) return local_dirname, os.fsencode(local_url) def swh_hash_data_per_revision(self, start_revision, end_revision): """Compute swh hash data per each revision between start_revision and end_revision. Args: start_revision: starting revision end_revision: ending revision Yields: tuple (rev, nextrev, commit, objects_per_path) - rev: current revision - nextrev: next revision - commit: commit data (author, date, message) for such revision - objects_per_path: dictionary of path, swh hash data with type """ for commit in self.logs(start_revision, end_revision): rev = commit['rev'] objects = self.swhreplay.compute_hashes(rev) if rev == end_revision: nextrev = None else: nextrev = rev + 1 yield rev, nextrev, commit, objects, self.swhreplay.directory def swh_hash_data_at_revision(self, revision): """Compute the hash data at revision. Expected to be used for update only. """ # Update the disk at revision self.export(revision) # Compute the current hashes on disk directory = Directory.from_disk(path=os.fsencode(self.local_url), save_path=True) # Update the replay collaborator with the right state - self.swhreplay = ra.SWHReplay( + self.swhreplay = ra.Replay( conn=self.conn, rootpath=self.local_url, directory=directory) # Retrieve the commit information for revision commit = list(self.logs(revision, revision))[0] yield revision, revision + 1, commit, {}, directory def clean_fs(self, local_dirname=None): """Clean up the local working copy. Args: local_dirname (str): Path to remove recursively if provided. Otherwise, remove the temporary upper root tree used for svn repository loading. """ dirname = local_dirname if local_dirname else self.local_dirname if os.path.exists(dirname): logging.debug('cleanup %s' % dirname) shutil.rmtree(dirname) diff --git a/swh/loader/svn/tasks.py b/swh/loader/svn/tasks.py index 59b6241..c2eb705 100644 --- a/swh/loader/svn/tasks.py +++ b/swh/loader/svn/tasks.py @@ -1,65 +1,65 @@ # Copyright (C) 2015-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from swh.scheduler.task import Task from .loader import SvnLoader, SvnLoaderFromDumpArchive class LoadSvnRepository(Task): """Import one svn repository to Software Heritage. """ task_queue = 'swh_loader_svn' def run_task(self, *, svn_url, destination_path=None, swh_revision=None, origin_url=None, visit_date=None, start_from_scratch=None): """Import a svn repository with swh policy. Args: args: ordered arguments (expected None) kwargs: Dictionary with the following expected keys: - svn_url (str): (mandatory) svn's repository url - destination_path (str): (mandatory) root directory to locally retrieve svn's data - origin_url (str): Optional original url override - - swh_revision (dict): (optional) extra SWH revision hex to + - swh_revision (dict): (optional) extra revision hex to start from. see swh.loader.svn.SvnLoader.process docstring """ loader = SvnLoader() loader.log = self.log return loader.load( svn_url=svn_url, destination_path=destination_path, origin_url=origin_url, swh_revision=swh_revision, visit_date=visit_date, start_from_scratch=start_from_scratch) class MountAndLoadSvnRepository(Task): task_queue = 'swh_loader_svn_mount_and_load' def run_task(self, *, archive_path, origin_url=None, visit_date=None, start_from_scratch=False): """1. Mount an svn dump from archive as a local svn repository. 2. Load it through the svn loader. 3. Clean up mounted svn repository archive. """ loader = SvnLoaderFromDumpArchive(archive_path) loader.log = self.log return loader.load(svn_url='file://%s' % loader.repo_path, origin_url=origin_url, visit_date=visit_date, archive_path=archive_path, start_from_scratch=start_from_scratch) diff --git a/swh/loader/svn/tests/test_converters.py b/swh/loader/svn/tests/test_converters.py index fba7ae7..f5805f5 100644 --- a/swh/loader/svn/tests/test_converters.py +++ b/swh/loader/svn/tests/test_converters.py @@ -1,294 +1,294 @@ # Copyright (C) 2015-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import unittest from nose.tools import istest from swh.loader.svn import converters class TestAuthorGitSvnConverters(unittest.TestCase): @istest def svn_author_to_gitsvn_person(self): """The author should have name, email and fullname filled. """ actual_person = converters.svn_author_to_gitsvn_person( 'tony ', repo_uuid=None) self.assertEquals(actual_person, { 'fullname': b'tony ', 'name': b'tony', 'email': b'ynot@dagobah', }) @istest def svn_author_to_gitsvn_person_no_email(self): """The author should see his/her email filled with author@. """ actual_person = converters.svn_author_to_gitsvn_person( 'tony', repo_uuid=b'some-uuid') self.assertEquals(actual_person, { 'fullname': b'tony ', 'name': b'tony', 'email': b'tony@some-uuid', }) @istest def svn_author_to_gitsvn_person_empty_person(self): """The empty person should see name, fullname and email filled. """ actual_person = converters.svn_author_to_gitsvn_person( '', repo_uuid=b'some-uuid') self.assertEqual(actual_person, { 'fullname': b'(no author) <(no author)@some-uuid>', 'name': b'(no author)', 'email': b'(no author)@some-uuid' }) -class TestAuthorSWHConverters(unittest.TestCase): +class TestAuthorConverters(unittest.TestCase): @istest def svn_author_to_swh_person(self): """The author should have name, email and fullname filled. """ actual_person = converters.svn_author_to_swh_person( 'tony ') self.assertEquals(actual_person, { 'fullname': b'tony ', 'name': b'tony', 'email': b'ynot@dagobah', }) @istest def svn_author_to_swh_person_no_email(self): """The author and fullname should be the same as the input (author). """ actual_person = converters.svn_author_to_swh_person('tony') self.assertEquals(actual_person, { 'fullname': b'tony', 'name': b'tony', 'email': None, }) @istest def svn_author_to_swh_person_empty_person(self): """Empty person has only its fullname filled with the empty byte-string. """ actual_person = converters.svn_author_to_swh_person('') self.assertEqual(actual_person, { 'fullname': b'', 'name': None, 'email': None, }) -class TestSWHRevisionConverters(unittest.TestCase): +class TestRevisionConverters(unittest.TestCase): @istest def build_swh_revision_default(self): """This should build the swh revision with the swh revision's extra headers about the repository. """ actual_swh_revision = converters.build_swh_revision( repo_uuid=b'uuid', dir_id='dir-id', commit={ 'author_name': { 'name': b'theo', 'email': b'theo@uuid', 'fullname': b'theo ' }, 'message': b'commit message', 'author_date': { 'timestamp': { 'seconds': 1088108379, 'microseconds': 0, }, 'offset': 0 } }, rev=10, parents=['123']) date = { 'timestamp': { 'seconds': 1088108379, 'microseconds': 0, }, 'offset': 0, } self.assertEquals(actual_swh_revision, { 'date': date, 'committer_date': date, 'type': 'svn', 'directory': 'dir-id', 'message': b'commit message', 'author': { 'name': b'theo', 'email': b'theo@uuid', 'fullname': b'theo ' }, 'committer': { 'name': b'theo', 'email': b'theo@uuid', 'fullname': b'theo ' }, 'synthetic': True, 'metadata': { 'extra_headers': [ ['svn_repo_uuid', b'uuid'], ['svn_revision', b'10'], ] }, 'parents': ['123'], }) class TestGitSvnRevisionConverters(unittest.TestCase): @istest def build_gitsvn_swh_revision_default(self): """This should build the swh revision without the swh revision's extra headers about the repository. """ actual_swh_revision = converters.build_gitsvn_swh_revision( dir_id='dir-id', commit={ 'author_name': { 'name': b'theo', 'email': b'theo@uuid', 'fullname': b'theo ' }, 'message': b'commit message', 'author_date': { 'timestamp': { 'seconds': 1088108379, 'microseconds': 0, }, 'offset': 0 } }, rev=10, parents=['123']) date = { 'timestamp': { 'seconds': 1088108379, 'microseconds': 0, }, 'offset': 0, } self.assertEquals(actual_swh_revision, { 'date': date, 'committer_date': date, 'type': 'svn', 'directory': 'dir-id', 'message': b'commit message', 'author': { 'name': b'theo', 'email': b'theo@uuid', 'fullname': b'theo ' }, 'committer': { 'name': b'theo', 'email': b'theo@uuid', 'fullname': b'theo ' }, 'synthetic': True, 'metadata': None, 'parents': ['123'], }) -class ConvertSWHDate(unittest.TestCase): +class ConvertDate(unittest.TestCase): @istest def svn_date_to_swh_date(self): """The timestamp should not be tampered with and include the decimals. """ self.assertEquals( converters.svn_date_to_swh_date('2011-05-31T06:04:39.500900Z'), { 'timestamp': { 'seconds': 1306821879, 'microseconds': 500900, }, 'offset': 0 }) self.assertEquals( converters.svn_date_to_swh_date('2011-05-31T06:04:39.800722Z'), { 'timestamp': { 'seconds': 1306821879, 'microseconds': 800722, }, 'offset': 0 }) @istest def svn_date_to_swh_date_epoch(self): """Empty date should be EPOCH (timestamp and offset at 0).""" # It should return 0, epoch self.assertEquals({ 'timestamp': { 'seconds': 0, 'microseconds': 0, }, 'offset': 0, }, converters.svn_date_to_swh_date('')) self.assertEquals({ 'timestamp': { 'seconds': 0, 'microseconds': 0, }, 'offset': 0, }, converters.svn_date_to_swh_date(None)) class ConvertGitSvnDate(unittest.TestCase): @istest def svn_date_to_gitsvn_date(self): """The timestamp should be truncated to be an integer.""" actual_ts = converters.svn_date_to_gitsvn_date( '2011-05-31T06:04:39.800722Z') self.assertEquals(actual_ts, { 'timestamp': { 'seconds': 1306821879, 'microseconds': 0, }, 'offset': 0, }) @istest def svn_date_to_gitsvn_date_epoch(self): """Empty date should be EPOCH (timestamp and offset at 0).""" # It should return 0, epoch self.assertEquals({ 'timestamp': { 'seconds': 0, 'microseconds': 0, }, 'offset': 0, }, converters.svn_date_to_gitsvn_date('')) self.assertEquals({ 'timestamp': { 'seconds': 0, 'microseconds': 0, }, 'offset': 0, }, converters.svn_date_to_gitsvn_date(None)) diff --git a/swh/loader/svn/tests/test_loader.py b/swh/loader/svn/tests/test_loader.py index 71a00ec..5b7bbfc 100644 --- a/swh/loader/svn/tests/test_loader.py +++ b/swh/loader/svn/tests/test_loader.py @@ -1,905 +1,905 @@ # Copyright (C) 2016-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from nose.tools import istest from test_base import BaseTestSvnLoader from unittest import TestCase from swh.model import hashutil from swh.loader.svn.loader import build_swh_snapshot, DEFAULT_BRANCH from swh.loader.svn.loader import SvnLoader from swh.loader.svn.exception import SvnLoaderEventful, SvnLoaderUneventful from swh.loader.svn.exception import SvnLoaderHistoryAltered -class TestSWHSnapshot(TestCase): +class TestSnapshot(TestCase): @istest def build_swh_snapshot(self): actual_snap = build_swh_snapshot('revision-id') self.assertEquals(actual_snap, { 'id': None, 'branches': { DEFAULT_BRANCH: { 'target': 'revision-id', 'target_type': 'revision', } } }) # Define loaders with no storage # They'll just accumulate the data in place # Only for testing purposes. class TestSvnLoader: """Mixin class to inhibit the persistence and keep in memory the data sent for storage. cf. SvnLoaderNoStorage """ def __init__(self): super().__init__() self.all_contents = [] self.all_directories = [] self.all_revisions = [] self.all_releases = [] self.all_snapshots = [] # Check at each svn revision that the hash tree computation # does not diverge self.check_revision = 10 # typed data self.objects = { 'content': self.all_contents, 'directory': self.all_directories, 'revision': self.all_revisions, 'release': self.all_releases, 'snapshot': self.all_snapshots, } def _add(self, type, l): """Add without duplicates and keeping the insertion order. Args: type (str): Type of objects concerned by the action l ([object]): List of 'type' object """ col = self.objects[type] for o in l: if o in col: continue col.extend([o]) def maybe_load_contents(self, all_contents): self._add('content', all_contents) def maybe_load_directories(self, all_directories): self._add('directory', all_directories) def maybe_load_revisions(self, all_revisions): self._add('revision', all_revisions) def maybe_load_releases(self, releases): raise ValueError('If called, the test must break.') def maybe_load_snapshot(self, snapshot): self._add('snapshot', [snapshot]) def send_origin(self, origin): return 1 # Override to do nothing at the end def close_failure(self): pass def close_success(self): pass def pre_cleanup(self): pass class SvnLoaderNoStorage(TestSvnLoader, SvnLoader): - """An SWHSVNLoader with no persistence. + """An SVNLoader with no persistence. Context: Load a new svn repository using the swh policy (so no update). """ def swh_latest_snapshot_revision(self, origin_id, prev_swh_revision=None): """We do not know this repository so no revision. """ return {} class SvnLoaderUpdateNoStorage(TestSvnLoader, SvnLoader): - """An SWHSVNLoader with no persistence. + """An SVNLoader with no persistence. Context: Load a known svn repository using the swh policy. We can either: - do nothing since it does not contain any new commit (so no change) - either check its history is not altered and update in consequence by loading the new revision """ def swh_latest_snapshot_revision(self, origin_id, prev_swh_revision=None): """Avoid the storage persistence call and return the expected previous revision for that repository. Check the following for explanation about the hashes: - test_loader.org for (swh policy). - cf. SvnLoaderITTest """ return { 'snapshot': 'something', # need a snapshot of sort 'revision': { 'id': hashutil.hash_to_bytes( '4876cb10aec6f708f7466dddf547567b65f6c39c'), 'parents': [hashutil.hash_to_bytes( 'a3a577948fdbda9d1061913b77a1588695eadb41')], 'directory': hashutil.hash_to_bytes( '0deab3023ac59398ae467fc4bff5583008af1ee2'), 'target_type': 'revision', 'metadata': { 'extra_headers': [ ['svn_repo_uuid', '3187e211-bb14-4c82-9596-0b59d67cd7f4'], ['svn_revision', '6'] ] } } } class SvnLoaderUpdateHistoryAlteredNoStorage(TestSvnLoader, SvnLoader): - """An SWHSVNLoader with no persistence. + """An SVNLoader with no persistence. Context: Load a known svn repository using the swh policy with its history altered so we do not update it. """ def swh_latest_snapshot_revision(self, origin_id, prev_swh_revision=None): """Avoid the storage persistence call and return the expected previous revision for that repository. Check the following for explanation about the hashes: - test_loader.org for (swh policy). - cf. SvnLoaderITTest """ return { 'snapshot': None, 'revision': { # Changed the revision id's hash to simulate history altered 'id': hashutil.hash_to_bytes( 'badbadbadbadf708f7466dddf547567b65f6c39d'), 'parents': [hashutil.hash_to_bytes( 'a3a577948fdbda9d1061913b77a1588695eadb41')], 'directory': hashutil.hash_to_bytes( '0deab3023ac59398ae467fc4bff5583008af1ee2'), 'target_type': 'revision', 'metadata': { 'extra_headers': [ ['svn_repo_uuid', '3187e211-bb14-4c82-9596-0b59d67cd7f4'], ['svn_revision', b'6'] ] } } } class SvnLoaderITest1(BaseTestSvnLoader): """Load an unknown svn repository results in new data. """ def setUp(self): super().setUp() self.loader = SvnLoaderNoStorage() @istest def load(self): """Load a new repository results in new swh object and snapshot """ # when self.loader.load( svn_url=self.svn_mirror_url, destination_path=self.destination_path) # then self.assertEquals(len(self.loader.all_revisions), 6) self.assertEquals(len(self.loader.all_releases), 0) last_revision = '4876cb10aec6f708f7466dddf547567b65f6c39c' # cf. test_loader.org for explaining from where those hashes # come from expected_revisions = { # revision hash | directory hash '0d7dd5f751cef8fe17e8024f7d6b0e3aac2cfd71': '669a71cce6c424a81ba42b7dc5d560d32252f0ca', # noqa '95edacc8848369d6fb1608e887d6d2474fd5224f': '008ac97a1118560797c50e3392fa1443acdaa349', # noqa 'fef26ea45a520071711ba2b9d16a2985ee837021': '3780effbe846a26751a95a8c95c511fb72be15b4', # noqa '3f51abf3b3d466571be0855dfa67e094f9ceff1b': 'ffcca9b09c5827a6b8137322d4339c8055c3ee1e', # noqa 'a3a577948fdbda9d1061913b77a1588695eadb41': '7dc52cc04c3b8bd7c085900d60c159f7b846f866', # noqa last_revision: '0deab3023ac59398ae467fc4bff5583008af1ee2', # noqa } self.assertRevisionsOk(expected_revisions) self.assertEquals(len(self.loader.all_snapshots), 1) # FIXME: Check the snapshot's state # self.assertEquals(self.loader.all_snapshots[0], {}) self.assertEqual(self.loader.load_status(), {'status': 'eventful'}) self.assertEqual(self.loader.visit_status(), 'full') class SvnLoaderITest2(BaseTestSvnLoader): """Load a visited repository with no new change results in no data change. """ def setUp(self): super().setUp() self.loader = SvnLoaderUpdateNoStorage() @istest def load(self): """Load a repository without new changes results in same snapshot """ # when self.loader.load( svn_url=self.svn_mirror_url, destination_path=self.destination_path) # then self.assertEquals(len(self.loader.all_contents), 0) self.assertEquals(len(self.loader.all_directories), 0) self.assertEquals(len(self.loader.all_revisions), 0) self.assertEquals(len(self.loader.all_releases), 0) self.assertEquals(len(self.loader.all_snapshots), 1) # FIXME: Check the snapshot's state # self.assertEquals(self.loader.all_snapshots[0], {}) self.assertEqual(self.loader.load_status(), {'status': 'uneventful'}) self.assertEqual(self.loader.visit_status(), 'full') class SvnLoaderITest3(BaseTestSvnLoader): """In this scenario, the dump has been tampered with to modify the commit log. This results in a hash divergence which is detected at startup. In effect, that stops the loading and do nothing. """ def setUp(self): # the svn repository pkg-gourmet has been updated with changes super().setUp(archive_name='pkg-gourmet-with-updates.tgz') self.loader = SvnLoaderUpdateHistoryAlteredNoStorage() @istest def load(self): """Load known repository with history altered should do nothing """ # when self.loader.load(svn_url=self.svn_mirror_url, destination_path=self.destination_path) # then # we got the previous run's last revision (rev 6) # so 2 news + 1 old self.assertEquals(len(self.loader.all_contents), 0) self.assertEquals(len(self.loader.all_directories), 0) self.assertEquals(len(self.loader.all_revisions), 0) self.assertEquals(len(self.loader.all_releases), 0) self.assertEquals(len(self.loader.all_snapshots), 0) # FIXME: Check the snapshot's state # self.assertEquals(self.loader.all_snapshots[0], {}) self.assertEqual(self.loader.load_status(), {'status': 'uneventful'}) self.assertEqual(self.loader.visit_status(), 'partial') class SvnLoaderITest4(BaseTestSvnLoader): """In this scenario, the repository has been updated with new changes. The loading visit should result in new objects stored and 1 new snapshot. """ def setUp(self): # the svn repository pkg-gourmet has been updated with changes super().setUp(archive_name='pkg-gourmet-with-updates.tgz') self.loader = SvnLoaderUpdateNoStorage() @istest def process_repository(self): """Process updated repository should yield new objects """ # when self.loader.load(svn_url=self.svn_mirror_url, destination_path=self.destination_path) # then # we got the previous run's last revision (rev 6) # so 2 new self.assertEquals(len(self.loader.all_revisions), 5) self.assertEquals(len(self.loader.all_releases), 0) last_revision = '171dc35522bfd17dda4e90a542a0377fb2fc707a' # cf. test_loader.org for explaining from where those hashes # come from expected_revisions = { # revision hash | directory hash '7f5bc909c29d4e93d8ccfdda516e51ed44930ee1': '752c52134dcbf2fff13c7be1ce4e9e5dbf428a59', # noqa '38d81702cb28db4f1a6821e64321e5825d1f7fd6': '39c813fb4717a4864bacefbd90b51a3241ae4140', # noqa '99c27ebbd43feca179ac0e895af131d8314cafe1': '3397ca7f709639cbd36b18a0d1b70bce80018c45', # noqa '902f29b4323a9b9de3af6d28e72dd581e76d9397': 'c4e12483f0a13e6851459295a4ae735eb4e4b5c4', # noqa last_revision: 'fd24a76c87a3207428e06612b49860fc78e9f6dc' # noqa } self.assertRevisionsOk(expected_revisions) self.assertEquals(len(self.loader.all_snapshots), 1) # FIXME: Check the snapshot's state # self.assertEquals(self.loader.all_snapshots[0], {}) self.assertEqual(self.loader.load_status(), {'status': 'eventful'}) self.assertEqual(self.loader.visit_status(), 'full') class SvnLoaderITTest5(BaseTestSvnLoader): """Context: - Repository already injected with successfull data - New visit from scratch done with successfull load """ def setUp(self): # the svn repository pkg-gourmet has been updated with changes super().setUp(archive_name='pkg-gourmet-with-updates.tgz') self.loader = SvnLoaderUpdateNoStorage() @istest def load(self): """Load an existing repository from scratch yields same swh objects """ # when self.loader.load(svn_url=self.svn_mirror_url, destination_path=self.destination_path, start_from_scratch=True) # then # we got the previous run's last revision (rev 6) # but we do not inspect that as we start from from scratch so # we should have all revisions so 11 self.assertEquals(len(self.loader.all_revisions), 11) self.assertEquals(len(self.loader.all_releases), 0) expected_revisions = { '0d7dd5f751cef8fe17e8024f7d6b0e3aac2cfd71': '669a71cce6c424a81ba42b7dc5d560d32252f0ca', # noqa '95edacc8848369d6fb1608e887d6d2474fd5224f': '008ac97a1118560797c50e3392fa1443acdaa349', # noqa 'fef26ea45a520071711ba2b9d16a2985ee837021': '3780effbe846a26751a95a8c95c511fb72be15b4', # noqa '3f51abf3b3d466571be0855dfa67e094f9ceff1b': 'ffcca9b09c5827a6b8137322d4339c8055c3ee1e', # noqa 'a3a577948fdbda9d1061913b77a1588695eadb41': '7dc52cc04c3b8bd7c085900d60c159f7b846f866', # noqa '4876cb10aec6f708f7466dddf547567b65f6c39c': '0deab3023ac59398ae467fc4bff5583008af1ee2', # noqa '7f5bc909c29d4e93d8ccfdda516e51ed44930ee1': '752c52134dcbf2fff13c7be1ce4e9e5dbf428a59', # noqa '38d81702cb28db4f1a6821e64321e5825d1f7fd6': '39c813fb4717a4864bacefbd90b51a3241ae4140', # noqa '99c27ebbd43feca179ac0e895af131d8314cafe1': '3397ca7f709639cbd36b18a0d1b70bce80018c45', # noqa '902f29b4323a9b9de3af6d28e72dd581e76d9397': 'c4e12483f0a13e6851459295a4ae735eb4e4b5c4', # noqa '171dc35522bfd17dda4e90a542a0377fb2fc707a': 'fd24a76c87a3207428e06612b49860fc78e9f6dc', # noqa } self.assertRevisionsOk(expected_revisions) self.assertEquals(len(self.loader.all_snapshots), 1) # FIXME: Check the snapshot's state # self.assertEquals(self.loader.all_snapshots[0], {}) self.assertEqual(self.loader.load_status(), {'status': 'eventful'}) self.assertEqual(self.loader.visit_status(), 'full') class SvnLoaderWithPreviousRevisionNoStorage(TestSvnLoader, SvnLoader): - """An SWHSVNLoader with no persistence. + """An SVNLoader with no persistence. Context: Load a known svn repository using the swh policy with its history altered so we do not update it. """ def swh_latest_snapshot_revision(self, origin_id, prev_swh_revision=None): """Avoid the storage persistence call and return the expected previous revision for that repository. Check the following for explanation about the hashes: - test_loader.org for (swh policy). - cf. SvnLoaderITTest """ return { 'snapshot': None, 'revision': { 'id': hashutil.hash_to_bytes( '4876cb10aec6f708f7466dddf547567b65f6c39c'), 'parents': [hashutil.hash_to_bytes( 'a3a577948fdbda9d1061913b77a1588695eadb41')], 'directory': hashutil.hash_to_bytes( '0deab3023ac59398ae467fc4bff5583008af1ee2'), 'target_type': 'revision', 'metadata': { 'extra_headers': [ ['svn_repo_uuid', '3187e211-bb14-4c82-9596-0b59d67cd7f4'], # noqa ['svn_revision', '6'] ] } } } class SvnLoaderITTest6(BaseTestSvnLoader): """Context: - repository already visited with load successfull - Changes on existing repository - New Visit done with successful new data """ def setUp(self): super().setUp(archive_name='pkg-gourmet-with-updates.tgz') self.loader = SvnLoaderWithPreviousRevisionNoStorage() @istest def load(self): """Load from partial previous visit result in new changes """ # when self.loader.load( svn_url=self.svn_mirror_url, destination_path=self.destination_path) # then # we got the previous run's last revision (rev 6) # so 2 new self.assertEquals(len(self.loader.all_revisions), 5) self.assertEquals(len(self.loader.all_releases), 0) last_revision = '171dc35522bfd17dda4e90a542a0377fb2fc707a' # cf. test_loader.org for explaining from where those hashes # come from expected_revisions = { # revision hash | directory hash '7f5bc909c29d4e93d8ccfdda516e51ed44930ee1': '752c52134dcbf2fff13c7be1ce4e9e5dbf428a59', # noqa '38d81702cb28db4f1a6821e64321e5825d1f7fd6': '39c813fb4717a4864bacefbd90b51a3241ae4140', # noqa '99c27ebbd43feca179ac0e895af131d8314cafe1': '3397ca7f709639cbd36b18a0d1b70bce80018c45', # noqa '902f29b4323a9b9de3af6d28e72dd581e76d9397': 'c4e12483f0a13e6851459295a4ae735eb4e4b5c4', # noqa last_revision: 'fd24a76c87a3207428e06612b49860fc78e9f6dc' # noqa } self.assertRevisionsOk(expected_revisions) self.assertEquals(len(self.loader.all_snapshots), 1) # FIXME: Check the snapshot's state # self.assertEquals(self.loader.all_snapshots[0], {}) self.assertEqual(self.loader.load_status(), {'status': 'eventful'}) self.assertEqual(self.loader.visit_status(), 'full') class SvnLoaderITest7(BaseTestSvnLoader): """Context: - repository already visited with load successfull - Changes on existing repository - New Visit done with successful new data """ def setUp(self): super().setUp(archive_name='pkg-gourmet-with-updates.tgz') self.loader = SvnLoaderUpdateNoStorage() @istest def load(self): """Load known and partial repository should start from last visit """ previous_unfinished_revision = { 'id': hashutil.hash_to_bytes( 'a3a577948fdbda9d1061913b77a1588695eadb41'), 'parents': [hashutil.hash_to_bytes( '3f51abf3b3d466571be0855dfa67e094f9ceff1b')], 'directory': hashutil.hash_to_bytes( '7dc52cc04c3b8bd7c085900d60c159f7b846f866'), 'target_type': 'revision', 'metadata': { 'extra_headers': [ ['svn_repo_uuid', '3187e211-bb14-4c82-9596-0b59d67cd7f4'], ['svn_revision', '5'] ] } } # when self.loader.load( svn_url=self.svn_mirror_url, destination_path=self.destination_path, swh_revision=previous_unfinished_revision) # then # we got the previous run's last revision (rev 6) # so 2 new self.assertEquals(len(self.loader.all_revisions), 5) self.assertEquals(len(self.loader.all_releases), 0) last_revision = '171dc35522bfd17dda4e90a542a0377fb2fc707a' # cf. test_loader.org for explaining from where those hashes # come from expected_revisions = { # revision hash | directory hash '7f5bc909c29d4e93d8ccfdda516e51ed44930ee1': '752c52134dcbf2fff13c7be1ce4e9e5dbf428a59', # noqa '38d81702cb28db4f1a6821e64321e5825d1f7fd6': '39c813fb4717a4864bacefbd90b51a3241ae4140', # noqa '99c27ebbd43feca179ac0e895af131d8314cafe1': '3397ca7f709639cbd36b18a0d1b70bce80018c45', # noqa '902f29b4323a9b9de3af6d28e72dd581e76d9397': 'c4e12483f0a13e6851459295a4ae735eb4e4b5c4', # noqa last_revision: 'fd24a76c87a3207428e06612b49860fc78e9f6dc' # noqa } self.assertRevisionsOk(expected_revisions) self.assertEquals(len(self.loader.all_snapshots), 1) # FIXME: Check the snapshot's state # self.assertEquals(self.loader.all_snapshots[0], {}) self.assertEqual(self.loader.load_status(), {'status': 'eventful'}) self.assertEqual(self.loader.visit_status(), 'full') class SvnLoaderUpdateLessRecentNoStorage(TestSvnLoader, SvnLoader): """Context: Load a known svn repository. The last visit seen is less recent than a previous unfinished crawl. """ def swh_latest_snapshot_revision(self, origin_id, prev_swh_revision=None): """Avoid the storage persistence call and return the expected previous revision for that repository. Check the following for explanation about the hashes: - test_loader.org for (swh policy). - cf. SvnLoaderITTest """ return { 'snapshot': None, 'revision': { 'id': hashutil.hash_to_bytes( 'a3a577948fdbda9d1061913b77a1588695eadb41'), 'parents': [hashutil.hash_to_bytes( '3f51abf3b3d466571be0855dfa67e094f9ceff1b')], 'directory': hashutil.hash_to_bytes( '7dc52cc04c3b8bd7c085900d60c159f7b846f866'), 'target_type': 'revision', 'metadata': { 'extra_headers': [ ['svn_repo_uuid', '3187e211-bb14-4c82-9596-0b59d67cd7f4'], ['svn_revision', '5'] ] } } } class SvnLoaderITest8(BaseTestSvnLoader): """Context: - Previous visit on existing repository done - Starting the loading from the last unfinished visit - New objects are created (1 new snapshot) """ def setUp(self): super().setUp(archive_name='pkg-gourmet-with-updates.tgz') self.loader = SvnLoaderUpdateLessRecentNoStorage() @istest def load(self): """Load repository should yield revisions starting from last visit """ previous_unfinished_revision = { 'id': hashutil.hash_to_bytes( '4876cb10aec6f708f7466dddf547567b65f6c39c'), 'parents': [hashutil.hash_to_bytes( 'a3a577948fdbda9d1061913b77a1588695eadb41')], 'directory': hashutil.hash_to_bytes( '0deab3023ac59398ae467fc4bff5583008af1ee2'), 'target_type': 'revision', 'metadata': { 'extra_headers': [ ['svn_repo_uuid', '3187e211-bb14-4c82-9596-0b59d67cd7f4'], ['svn_revision', '6'] ] } } # when self.loader.load( svn_url=self.svn_mirror_url, destination_path=self.destination_path, swh_revision=previous_unfinished_revision) # then # we got the previous run's last revision (rev 6) # so 2 new self.assertEquals(len(self.loader.all_revisions), 5) self.assertEquals(len(self.loader.all_releases), 0) last_revision = '171dc35522bfd17dda4e90a542a0377fb2fc707a' # cf. test_loader.org for explaining from where those hashes # come from expected_revisions = { # revision hash | directory hash '7f5bc909c29d4e93d8ccfdda516e51ed44930ee1': '752c52134dcbf2fff13c7be1ce4e9e5dbf428a59', # noqa '38d81702cb28db4f1a6821e64321e5825d1f7fd6': '39c813fb4717a4864bacefbd90b51a3241ae4140', # noqa '99c27ebbd43feca179ac0e895af131d8314cafe1': '3397ca7f709639cbd36b18a0d1b70bce80018c45', # noqa '902f29b4323a9b9de3af6d28e72dd581e76d9397': 'c4e12483f0a13e6851459295a4ae735eb4e4b5c4', # noqa last_revision: 'fd24a76c87a3207428e06612b49860fc78e9f6dc' # noqa } self.assertRevisionsOk(expected_revisions) self.assertEquals(len(self.loader.all_snapshots), 1) # FIXME: Check the snapshot's state # self.assertEquals(self.loader.all_snapshots[0], {}) self.assertEqual(self.loader.load_status(), {'status': 'eventful'}) self.assertEqual(self.loader.visit_status(), 'full') class SvnLoaderTTest9(BaseTestSvnLoader): """Check that a svn repo containing a versioned file with CRLF line endings with svn:eol-style property set to 'native' (this is a violation of svn specification as the file should have been stored with LF line endings) can be loaded anyway. """ def setUp(self): super().setUp(archive_name='mediawiki-repo-r407-eol-native-crlf.tgz', filename='mediawiki-repo-r407-eol-native-crlf') self.loader = SvnLoaderNoStorage() @istest def process_repository(self): """Load repository with CRLF endings (svn:eol-style: native) is ok """ # noqa # when self.loader.load(svn_url=self.svn_mirror_url, destination_path=self.destination_path) expected_revisions = { '7da4975c363101b819756d33459f30a866d01b1b': 'f63637223ee0f7d4951ffd2d4d9547a4882c5d8b' # noqa } self.assertRevisionsOk(expected_revisions) self.assertEquals(len(self.loader.all_snapshots), 1) # FIXME: Check the snapshot's state # self.assertEquals(self.loader.all_snapshots[0], {}) self.assertEqual(self.loader.load_status(), {'status': 'eventful'}) self.assertEqual(self.loader.visit_status(), 'full') class SvnLoaderITest10(BaseTestSvnLoader): # noqa """Check that a svn repo containing a versioned file with mixed CRLF/LF line endings with svn:eol-style property set to 'native' (this is a violation of svn specification as mixed line endings for textual content should not be stored when the svn:eol-style property is set) can be loaded anyway. """ def setUp(self): super().setUp( archive_name='pyang-repo-r343-eol-native-mixed-lf-crlf.tgz', filename='pyang-repo-r343-eol-native-mixed-lf-crlf') self.loader = SvnLoaderNoStorage() @istest def load(self): """Load repo with mixed CRLF/LF endings (svn:eol-style:native) is ok """ self.loader.load(svn_url=self.svn_mirror_url, destination_path=self.destination_path) expected_revisions = { '9c6962eeb9164a636c374be700672355e34a98a7': '16aa6b6271f3456d4643999d234cf39fe3d0cc5a' # noqa } self.assertRevisionsOk(expected_revisions) self.assertEquals(len(self.loader.all_snapshots), 1) # FIXME: Check the snapshot's state # self.assertEquals(self.loader.all_snapshots[0], {}) self.assertEqual(self.loader.load_status(), {'status': 'eventful'}) self.assertEqual(self.loader.visit_status(), 'full') class SvnLoaderITest11(BaseTestSvnLoader): """Context: - Repository with svn:external (which is not deal with for now) - Visit is partial with as much data loaded as possible """ def setUp(self): super().setUp(archive_name='pkg-gourmet-with-external-id.tgz') self.loader = SvnLoaderNoStorage() @istest def load(self): """Repository with svn:externals property, will stop raising an error """ previous_unfinished_revision = None # when self.loader.load( svn_url=self.svn_mirror_url, destination_path=self.destination_path, swh_revision=previous_unfinished_revision) # then repositories holds 21 revisions, but the last commit # one holds an 'svn:externals' property which will make the # loader-svn stops at the last revision prior to the bad one self.assertEquals(len(self.loader.all_revisions), 20) self.assertEquals(len(self.loader.all_releases), 0) last_revision = '82a7a4a09f9549223429143ba36ad77375e33c5c' expected_revisions = { # revision hash | directory hash '0d7dd5f751cef8fe17e8024f7d6b0e3aac2cfd71': '669a71cce6c424a81ba42b7dc5d560d32252f0ca', # noqa '95edacc8848369d6fb1608e887d6d2474fd5224f': '008ac97a1118560797c50e3392fa1443acdaa349', # noqa 'fef26ea45a520071711ba2b9d16a2985ee837021': '3780effbe846a26751a95a8c95c511fb72be15b4', # noqa '3f51abf3b3d466571be0855dfa67e094f9ceff1b': 'ffcca9b09c5827a6b8137322d4339c8055c3ee1e', # noqa 'a3a577948fdbda9d1061913b77a1588695eadb41': '7dc52cc04c3b8bd7c085900d60c159f7b846f866', # noqa '4876cb10aec6f708f7466dddf547567b65f6c39c': '0deab3023ac59398ae467fc4bff5583008af1ee2', # noqa '7f5bc909c29d4e93d8ccfdda516e51ed44930ee1': '752c52134dcbf2fff13c7be1ce4e9e5dbf428a59', # noqa '38d81702cb28db4f1a6821e64321e5825d1f7fd6': '39c813fb4717a4864bacefbd90b51a3241ae4140', # noqa '99c27ebbd43feca179ac0e895af131d8314cafe1': '3397ca7f709639cbd36b18a0d1b70bce80018c45', # noqa '902f29b4323a9b9de3af6d28e72dd581e76d9397': 'c4e12483f0a13e6851459295a4ae735eb4e4b5c4', # noqa '171dc35522bfd17dda4e90a542a0377fb2fc707a': 'fd24a76c87a3207428e06612b49860fc78e9f6dc', # noqa '027e8769f4786597436ab94a91f85527d04a6cbb': '2d9ca72c6afec6284fb01e459588cbb007017c8c', # noqa '4474d96018877742d9697d5c76666c9693353bfc': 'ab111577e0ab39e4a157c476072af48f2641d93f', # noqa '97ad21eab92961e2a22ca0285f09c6d1e9a7ffbc': 'ab111577e0ab39e4a157c476072af48f2641d93f', # noqa 'd04ea8afcee6205cc8384c091bfc578931c169fd': 'b0a648b02e55a4dce356ac35187a058f89694ec7', # noqa 'ded78810401fd354ffe894aa4a1e5c7d30a645d1': 'b0a648b02e55a4dce356ac35187a058f89694ec7', # noqa '4ee95e39358712f53c4fc720da3fafee9249ed19': 'c3c98df624733fef4e592bef983f93e2ed02b179', # noqa 'ffa901b69ca0f46a2261f42948838d19709cb9f8': 'c3c98df624733fef4e592bef983f93e2ed02b179', # noqa '0148ae3eaa520b73a50802c59f3f416b7a36cf8c': '844d4646d6c2b4f3a3b2b22ab0ee38c7df07bab2', # noqa last_revision: '0de6e75d2b79ec90d00a3a7611aa3861b2e4aa5e', # noqa } # The last revision being the one used later to start back from self.assertRevisionsOk(expected_revisions) self.assertEquals(len(self.loader.all_snapshots), 1) # FIXME: Check the snapshot's state self.assertEqual(self.loader.load_status(), {'status': 'eventful'}) self.assertEqual(self.loader.visit_status(), 'partial') class SvnLoaderITest12(BaseTestSvnLoader): """Edge cases: - first create a file and commit it. Remove it, then add folder holding the same name, commit. - do the same scenario with symbolic link (instead of file) """ def setUp(self): super().setUp( archive_name='pkg-gourmet-with-edge-case-links-and-files.tgz') self.loader = SvnLoaderNoStorage() @istest def load(self): """File/Link removed prior to folder with same name creation is ok """ previous_unfinished_revision = None # when self.loader.load( svn_url=self.svn_mirror_url, destination_path=self.destination_path, swh_revision=previous_unfinished_revision) # then repositories holds 14 revisions, but the last commit self.assertEquals(len(self.loader.all_revisions), 19) self.assertEquals(len(self.loader.all_releases), 0) last_revision = '3f43af2578fccf18b0d4198e48563da7929dc608' expected_revisions = { # revision hash | directory hash '0d7dd5f751cef8fe17e8024f7d6b0e3aac2cfd71': '669a71cce6c424a81ba42b7dc5d560d32252f0ca', # noqa '95edacc8848369d6fb1608e887d6d2474fd5224f': '008ac97a1118560797c50e3392fa1443acdaa349', # noqa 'fef26ea45a520071711ba2b9d16a2985ee837021': '3780effbe846a26751a95a8c95c511fb72be15b4', # noqa '3f51abf3b3d466571be0855dfa67e094f9ceff1b': 'ffcca9b09c5827a6b8137322d4339c8055c3ee1e', # noqa 'a3a577948fdbda9d1061913b77a1588695eadb41': '7dc52cc04c3b8bd7c085900d60c159f7b846f866', # noqa '4876cb10aec6f708f7466dddf547567b65f6c39c': '0deab3023ac59398ae467fc4bff5583008af1ee2', # noqa '7f5bc909c29d4e93d8ccfdda516e51ed44930ee1': '752c52134dcbf2fff13c7be1ce4e9e5dbf428a59', # noqa '38d81702cb28db4f1a6821e64321e5825d1f7fd6': '39c813fb4717a4864bacefbd90b51a3241ae4140', # noqa '99c27ebbd43feca179ac0e895af131d8314cafe1': '3397ca7f709639cbd36b18a0d1b70bce80018c45', # noqa '902f29b4323a9b9de3af6d28e72dd581e76d9397': 'c4e12483f0a13e6851459295a4ae735eb4e4b5c4', # noqa '171dc35522bfd17dda4e90a542a0377fb2fc707a': 'fd24a76c87a3207428e06612b49860fc78e9f6dc', # noqa '9231f9a98a9051a0cd34231cddd4e11773f8348e': '6c07f4f4ac780eaf99a247fbfd0897533598dd36', # noqa 'c309bd3b57796696d6655ab3ab0b438fdd2d8201': 'fd24a76c87a3207428e06612b49860fc78e9f6dc', # noqa 'bb78300cc1ac9119eb6fffa9e9fa04a7f9340b11': 'ee995a0d85f6917c75bcee3aa448bea7726b265d', # noqa 'f2e01111329f84580dc3febb1fd45515692c5886': 'e2baec7b6a5543758e9c73695bc847db0a4f7941', # noqa '1a0f70c34e211f073e1be3435ecf6f0dd7700267': 'e7536e721fa806c19971b749c091c144b2f2b88e', # noqa '0c612a23d293cc3100496a54ae4ad13d750efe4c': '2123d12749294bbfb54e73f9d73fac658aabb266', # noqa '69a53d972e2f863acbbbda546d9da96287af6a88': '13896cb96ec004140ce5be8852fee8c29830d9c7', # noqa last_revision: '6b1e0243768ff9ac060064b2eeade77e764ffc82', # noqa } self.assertRevisionsOk(expected_revisions) self.assertEquals(len(self.loader.all_snapshots), 1) # FIXME: Check the snapshot's state self.assertEqual(self.loader.load_status(), {'status': 'eventful'}) self.assertEqual(self.loader.visit_status(), 'full') class SvnLoaderITTest13(BaseTestSvnLoader): """Edge cases: - wrong symbolic link - wrong symbolic link with empty space names """ def setUp(self): super().setUp( archive_name='pkg-gourmet-with-wrong-link-cases.tgz') self.loader = SvnLoaderNoStorage() @istest def load(self): """Wrong link or empty space-named link should be ok """ # when self.loader.load( svn_url=self.svn_mirror_url, destination_path=self.destination_path) # then repositories holds 14 revisions, but the last commit self.assertEquals(len(self.loader.all_revisions), 21) self.assertEquals(len(self.loader.all_releases), 0) last_revision = 'cf30d3bb9d5967d0a2bbeacc405f10a5dd9b138a' expected_revisions = { # revision hash | directory hash '0d7dd5f751cef8fe17e8024f7d6b0e3aac2cfd71': '669a71cce6c424a81ba42b7dc5d560d32252f0ca', # noqa '95edacc8848369d6fb1608e887d6d2474fd5224f': '008ac97a1118560797c50e3392fa1443acdaa349', # noqa 'fef26ea45a520071711ba2b9d16a2985ee837021': '3780effbe846a26751a95a8c95c511fb72be15b4', # noqa '3f51abf3b3d466571be0855dfa67e094f9ceff1b': 'ffcca9b09c5827a6b8137322d4339c8055c3ee1e', # noqa 'a3a577948fdbda9d1061913b77a1588695eadb41': '7dc52cc04c3b8bd7c085900d60c159f7b846f866', # noqa '4876cb10aec6f708f7466dddf547567b65f6c39c': '0deab3023ac59398ae467fc4bff5583008af1ee2', # noqa '7f5bc909c29d4e93d8ccfdda516e51ed44930ee1': '752c52134dcbf2fff13c7be1ce4e9e5dbf428a59', # noqa '38d81702cb28db4f1a6821e64321e5825d1f7fd6': '39c813fb4717a4864bacefbd90b51a3241ae4140', # noqa '99c27ebbd43feca179ac0e895af131d8314cafe1': '3397ca7f709639cbd36b18a0d1b70bce80018c45', # noqa '902f29b4323a9b9de3af6d28e72dd581e76d9397': 'c4e12483f0a13e6851459295a4ae735eb4e4b5c4', # noqa '171dc35522bfd17dda4e90a542a0377fb2fc707a': 'fd24a76c87a3207428e06612b49860fc78e9f6dc', # noqa '9231f9a98a9051a0cd34231cddd4e11773f8348e': '6c07f4f4ac780eaf99a247fbfd0897533598dd36', # noqa 'c309bd3b57796696d6655ab3ab0b438fdd2d8201': 'fd24a76c87a3207428e06612b49860fc78e9f6dc', # noqa 'bb78300cc1ac9119eb6fffa9e9fa04a7f9340b11': 'ee995a0d85f6917c75bcee3aa448bea7726b265d', # noqa 'f2e01111329f84580dc3febb1fd45515692c5886': 'e2baec7b6a5543758e9c73695bc847db0a4f7941', # noqa '1a0f70c34e211f073e1be3435ecf6f0dd7700267': 'e7536e721fa806c19971b749c091c144b2f2b88e', # noqa '0c612a23d293cc3100496a54ae4ad13d750efe4c': '2123d12749294bbfb54e73f9d73fac658aabb266', # noqa '69a53d972e2f863acbbbda546d9da96287af6a88': '13896cb96ec004140ce5be8852fee8c29830d9c7', # noqa '3f43af2578fccf18b0d4198e48563da7929dc608': '6b1e0243768ff9ac060064b2eeade77e764ffc82', # noqa '4ab5fc264732cd474d2e695c5ac66e4933bdad74': '9a1f5e3961db89422250ce6c1441476f40d65205', # noqa last_revision: 'd853d9628f6f0008d324fed27dadad00ce48bc62', # noqa } self.assertRevisionsOk(expected_revisions) self.assertEquals(len(self.loader.all_snapshots), 1) # FIXME: Check the snapshot's state self.assertEqual(self.loader.load_status(), {'status': 'eventful'}) self.assertEqual(self.loader.visit_status(), 'full')