diff --git a/PKG-INFO b/PKG-INFO index 10d4946..28abb44 100644 --- a/PKG-INFO +++ b/PKG-INFO @@ -1,42 +1,46 @@ Metadata-Version: 2.1 Name: swh.model -Version: 2.5.1 +Version: 2.6.0 Summary: Software Heritage data model Home-page: https://forge.softwareheritage.org/diffusion/DMOD/ Author: Software Heritage developers Author-email: swh-devel@inria.fr License: UNKNOWN Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest Project-URL: Funding, https://www.softwareheritage.org/donate Project-URL: Source, https://forge.softwareheritage.org/source/swh-model Project-URL: Documentation, https://docs.softwareheritage.org/devel/swh-model/ -Description: swh-model - ========= - - Implementation of the Data model of the Software Heritage project, used to - archive source code artifacts. - - This module defines the notion of SoftWare Heritage persistent IDentifiers - (SWHIDs) and provides tools to compute them: - - ```sh - $ swh-identify fork.c kmod.c sched/deadline.c - swh:1:cnt:2e391c754ae730bd2d8520c2ab497c403220c6e3 fork.c - swh:1:cnt:0277d1216f80ae1adeed84a686ed34c9b2931fc2 kmod.c - swh:1:cnt:57b939c81bce5d06fa587df8915f05affbe22b82 sched/deadline.c - - $ swh-identify --no-filename /usr/src/linux/kernel/ - swh:1:dir:f9f858a48d663b3809c9e2f336412717496202ab - ``` - Platform: UNKNOWN Classifier: Programming Language :: Python :: 3 Classifier: Intended Audience :: Developers Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3) Classifier: Operating System :: OS Independent Classifier: Development Status :: 5 - Production/Stable Requires-Python: >=3.7 Description-Content-Type: text/markdown Provides-Extra: cli Provides-Extra: testing-minimal Provides-Extra: testing +License-File: LICENSE +License-File: AUTHORS + +swh-model +========= + +Implementation of the Data model of the Software Heritage project, used to +archive source code artifacts. + +This module defines the notion of SoftWare Heritage persistent IDentifiers +(SWHIDs) and provides tools to compute them: + +```sh + $ swh-identify fork.c kmod.c sched/deadline.c + swh:1:cnt:2e391c754ae730bd2d8520c2ab497c403220c6e3 fork.c + swh:1:cnt:0277d1216f80ae1adeed84a686ed34c9b2931fc2 kmod.c + swh:1:cnt:57b939c81bce5d06fa587df8915f05affbe22b82 sched/deadline.c + + $ swh-identify --no-filename /usr/src/linux/kernel/ + swh:1:dir:f9f858a48d663b3809c9e2f336412717496202ab +``` + + diff --git a/requirements-test.txt b/requirements-test.txt index 984743d..2a54238 100644 --- a/requirements-test.txt +++ b/requirements-test.txt @@ -1,3 +1,5 @@ -Click +click pytest pytz +types-python-dateutil +types-pytz diff --git a/swh.model.egg-info/PKG-INFO b/swh.model.egg-info/PKG-INFO index 10d4946..28abb44 100644 --- a/swh.model.egg-info/PKG-INFO +++ b/swh.model.egg-info/PKG-INFO @@ -1,42 +1,46 @@ Metadata-Version: 2.1 Name: swh.model -Version: 2.5.1 +Version: 2.6.0 Summary: Software Heritage data model Home-page: https://forge.softwareheritage.org/diffusion/DMOD/ Author: Software Heritage developers Author-email: swh-devel@inria.fr License: UNKNOWN Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest Project-URL: Funding, https://www.softwareheritage.org/donate Project-URL: Source, https://forge.softwareheritage.org/source/swh-model Project-URL: Documentation, https://docs.softwareheritage.org/devel/swh-model/ -Description: swh-model - ========= - - Implementation of the Data model of the Software Heritage project, used to - archive source code artifacts. - - This module defines the notion of SoftWare Heritage persistent IDentifiers - (SWHIDs) and provides tools to compute them: - - ```sh - $ swh-identify fork.c kmod.c sched/deadline.c - swh:1:cnt:2e391c754ae730bd2d8520c2ab497c403220c6e3 fork.c - swh:1:cnt:0277d1216f80ae1adeed84a686ed34c9b2931fc2 kmod.c - swh:1:cnt:57b939c81bce5d06fa587df8915f05affbe22b82 sched/deadline.c - - $ swh-identify --no-filename /usr/src/linux/kernel/ - swh:1:dir:f9f858a48d663b3809c9e2f336412717496202ab - ``` - Platform: UNKNOWN Classifier: Programming Language :: Python :: 3 Classifier: Intended Audience :: Developers Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3) Classifier: Operating System :: OS Independent Classifier: Development Status :: 5 - Production/Stable Requires-Python: >=3.7 Description-Content-Type: text/markdown Provides-Extra: cli Provides-Extra: testing-minimal Provides-Extra: testing +License-File: LICENSE +License-File: AUTHORS + +swh-model +========= + +Implementation of the Data model of the Software Heritage project, used to +archive source code artifacts. + +This module defines the notion of SoftWare Heritage persistent IDentifiers +(SWHIDs) and provides tools to compute them: + +```sh + $ swh-identify fork.c kmod.c sched/deadline.c + swh:1:cnt:2e391c754ae730bd2d8520c2ab497c403220c6e3 fork.c + swh:1:cnt:0277d1216f80ae1adeed84a686ed34c9b2931fc2 kmod.c + swh:1:cnt:57b939c81bce5d06fa587df8915f05affbe22b82 sched/deadline.c + + $ swh-identify --no-filename /usr/src/linux/kernel/ + swh:1:dir:f9f858a48d663b3809c9e2f336412717496202ab +``` + + diff --git a/swh.model.egg-info/requires.txt b/swh.model.egg-info/requires.txt index 3b049f0..ccc9276 100644 --- a/swh.model.egg-info/requires.txt +++ b/swh.model.egg-info/requires.txt @@ -1,28 +1,32 @@ attrs!=21.1.0 attrs_strict>=0.0.7 deprecated hypothesis iso8601 python-dateutil typing_extensions [:python_version < "3.6"] pyblake2 [cli] swh.core>=0.3 Click dulwich [testing] -Click +click pytest pytz +types-python-dateutil +types-pytz swh.core>=0.3 Click dulwich [testing-minimal] -Click +click pytest pytz +types-python-dateutil +types-pytz diff --git a/swh/__init__.py b/swh/__init__.py index f14e196..8d9f151 100644 --- a/swh/__init__.py +++ b/swh/__init__.py @@ -1,4 +1,4 @@ from pkgutil import extend_path -from typing import Iterable +from typing import List -__path__ = extend_path(__path__, __name__) # type: Iterable[str] +__path__: List[str] = extend_path(__path__, __name__) diff --git a/swh/model/cli.py b/swh/model/cli.py index 091f8ab..52f98aa 100644 --- a/swh/model/cli.py +++ b/swh/model/cli.py @@ -1,293 +1,335 @@ # Copyright (C) 2018-2020 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 os import sys from typing import Dict, List, Optional # WARNING: do not import unnecessary things here to keep cli startup time under # control try: import click except ImportError: print( "Cannot run swh-identify; the Click package is not installed." "Please install 'swh.model[cli]' for full functionality.", file=sys.stderr, ) exit(1) try: from swh.core.cli import swh as swh_cli_group except ImportError: # stub so that swh-identify can be used when swh-core isn't installed swh_cli_group = click # type: ignore +from swh.model.from_disk import Directory from swh.model.identifiers import CoreSWHID, ObjectType CONTEXT_SETTINGS = dict(help_option_names=["-h", "--help"]) # Mapping between dulwich types and Software Heritage ones. Used by snapshot ID # computation. _DULWICH_TYPES = { b"blob": "content", b"tree": "directory", b"commit": "revision", b"tag": "release", } class CoreSWHIDParamType(click.ParamType): """Click argument that accepts a core SWHID and returns them as :class:`swh.model.identifiers.CoreSWHID` instances """ name = "SWHID" def convert(self, value, param, ctx) -> CoreSWHID: from swh.model.exceptions import ValidationError try: return CoreSWHID.from_string(value) except ValidationError as e: self.fail(f'"{value}" is not a valid core SWHID: {e}', param, ctx) def swhid_of_file(path) -> CoreSWHID: from swh.model.from_disk import Content from swh.model.hashutil import hash_to_bytes object = Content.from_file(path=path).get_data() return CoreSWHID( object_type=ObjectType.CONTENT, object_id=hash_to_bytes(object["sha1_git"]) ) def swhid_of_file_content(data) -> CoreSWHID: from swh.model.from_disk import Content from swh.model.hashutil import hash_to_bytes object = Content.from_bytes(mode=644, data=data).get_data() return CoreSWHID( object_type=ObjectType.CONTENT, object_id=hash_to_bytes(object["sha1_git"]) ) -def swhid_of_dir(path: bytes, exclude_patterns: List[bytes] = None) -> CoreSWHID: - from swh.model.from_disk import ( - Directory, - accept_all_directories, - ignore_directories_patterns, - ) - from swh.model.hashutil import hash_to_bytes +def model_of_dir(path: bytes, exclude_patterns: List[bytes] = None) -> Directory: + from swh.model.from_disk import accept_all_directories, ignore_directories_patterns dir_filter = ( ignore_directories_patterns(path, exclude_patterns) if exclude_patterns else accept_all_directories ) - object = Directory.from_disk(path=path, dir_filter=dir_filter).get_data() + return Directory.from_disk(path=path, dir_filter=dir_filter) + + +def swhid_of_dir(path: bytes, exclude_patterns: List[bytes] = None) -> CoreSWHID: + from swh.model.hashutil import hash_to_bytes + + obj = model_of_dir(path, exclude_patterns) + return CoreSWHID( - object_type=ObjectType.DIRECTORY, object_id=hash_to_bytes(object["id"]) + object_type=ObjectType.DIRECTORY, object_id=hash_to_bytes(obj.get_data()["id"]) ) def swhid_of_origin(url): from swh.model.hashutil import hash_to_bytes from swh.model.identifiers import ( ExtendedObjectType, ExtendedSWHID, origin_identifier, ) return ExtendedSWHID( object_type=ExtendedObjectType.ORIGIN, object_id=hash_to_bytes(origin_identifier({"url": url})), ) def swhid_of_git_repo(path) -> CoreSWHID: try: import dulwich.repo except ImportError: raise click.ClickException( "Cannot compute snapshot identifier; the Dulwich package is not installed. " "Please install 'swh.model[cli]' for full functionality.", ) from swh.model import hashutil from swh.model.identifiers import snapshot_identifier repo = dulwich.repo.Repo(path) branches: Dict[bytes, Optional[Dict]] = {} for ref, target in repo.refs.as_dict().items(): obj = repo[target] if obj: branches[ref] = { "target": hashutil.bytehex_to_hash(target), "target_type": _DULWICH_TYPES[obj.type_name], } else: branches[ref] = None for ref, target in repo.refs.get_symrefs().items(): branches[ref] = { "target": target, "target_type": "alias", } snapshot = {"branches": branches} return CoreSWHID( object_type=ObjectType.SNAPSHOT, object_id=hashutil.hash_to_bytes(snapshot_identifier(snapshot)), ) def identify_object(obj_type, follow_symlinks, exclude_patterns, obj) -> str: from urllib.parse import urlparse if obj_type == "auto": if obj == "-" or os.path.isfile(obj): obj_type = "content" elif os.path.isdir(obj): obj_type = "directory" else: try: # URL parsing if urlparse(obj).scheme: obj_type = "origin" else: raise ValueError except ValueError: raise click.BadParameter("cannot detect object type for %s" % obj) if obj == "-": content = sys.stdin.buffer.read() swhid = str(swhid_of_file_content(content)) elif obj_type in ["content", "directory"]: path = obj.encode(sys.getfilesystemencoding()) if follow_symlinks and os.path.islink(obj): path = os.path.realpath(obj) if obj_type == "content": swhid = str(swhid_of_file(path)) elif obj_type == "directory": swhid = str( swhid_of_dir(path, [pattern.encode() for pattern in exclude_patterns]) ) elif obj_type == "origin": swhid = str(swhid_of_origin(obj)) elif obj_type == "snapshot": swhid = str(swhid_of_git_repo(obj)) else: # shouldn't happen, due to option validation raise click.BadParameter("invalid object type: " + obj_type) # note: we return original obj instead of path here, to preserve user-given # file name in output return swhid @swh_cli_group.command(context_settings=CONTEXT_SETTINGS) @click.option( "--dereference/--no-dereference", "follow_symlinks", default=True, help="follow (or not) symlinks for OBJECTS passed as arguments " + "(default: follow)", ) @click.option( "--filename/--no-filename", "show_filename", default=True, help="show/hide file name (default: show)", ) @click.option( "--type", "-t", "obj_type", default="auto", type=click.Choice(["auto", "content", "directory", "origin", "snapshot"]), help="type of object to identify (default: auto)", ) @click.option( "--exclude", "-x", "exclude_patterns", metavar="PATTERN", multiple=True, help="Exclude directories using glob patterns \ (e.g., ``*.git`` to exclude all .git directories)", ) @click.option( "--verify", "-v", metavar="SWHID", type=CoreSWHIDParamType(), help="reference identifier to be compared with computed one", ) +@click.option( + "-r", "--recursive", is_flag=True, help="compute SWHID recursively", +) @click.argument("objects", nargs=-1, required=True) def identify( - obj_type, verify, show_filename, follow_symlinks, objects, exclude_patterns, + obj_type, + verify, + show_filename, + follow_symlinks, + objects, + exclude_patterns, + recursive, ): """Compute the Software Heritage persistent identifier (SWHID) for the given source code object(s). For more details about SWHIDs see: \b https://docs.softwareheritage.org/devel/swh-model/persistent-identifiers.html Tip: you can pass "-" to identify the content of standard input. \b Examples:: \b $ swh identify fork.c kmod.c sched/deadline.c swh:1:cnt:2e391c754ae730bd2d8520c2ab497c403220c6e3 fork.c swh:1:cnt:0277d1216f80ae1adeed84a686ed34c9b2931fc2 kmod.c swh:1:cnt:57b939c81bce5d06fa587df8915f05affbe22b82 sched/deadline.c \b $ swh identify --no-filename /usr/src/linux/kernel/ swh:1:dir:f9f858a48d663b3809c9e2f336412717496202ab \b $ git clone --mirror https://forge.softwareheritage.org/source/helloworld.git $ swh identify --type snapshot helloworld.git/ swh:1:snp:510aa88bdc517345d258c1fc2babcd0e1f905e93 helloworld.git """ # NoQA # overlong lines in shell examples are fine from functools import partial + import logging if verify and len(objects) != 1: raise click.BadParameter("verification requires a single object") - results = zip( - objects, - map( - partial(identify_object, obj_type, follow_symlinks, exclude_patterns), + if recursive and not os.path.isdir(objects[0]): + recursive = False + logging.warn("recursive option disabled, input is not a directory object") + + if recursive: + if verify: + raise click.BadParameter( + "verification of recursive object identification is not supported" + ) + + if not obj_type == ("auto" or "directory"): + raise click.BadParameter( + "recursive identification is supported only for directories" + ) + + path = os.fsencode(objects[0]) + dir_obj = model_of_dir(path, exclude_patterns) + for sub_obj in dir_obj.iter_tree(): + path_name = "path" if "path" in sub_obj.data.keys() else "data" + path = os.fsdecode(sub_obj.data[path_name]) + swhid = str( + CoreSWHID( + object_type=ObjectType[sub_obj.object_type.upper()], + object_id=sub_obj.hash, + ) + ) + msg = f"{swhid}\t{path}" if show_filename else f"{swhid}" + click.echo(msg) + else: + results = zip( objects, - ), - ) + map( + partial(identify_object, obj_type, follow_symlinks, exclude_patterns), + objects, + ), + ) - if verify: - swhid = next(results)[1] - if str(verify) == swhid: - click.echo("SWHID match: %s" % swhid) - sys.exit(0) + if verify: + swhid = next(results)[1] + if str(verify) == swhid: + click.echo("SWHID match: %s" % swhid) + sys.exit(0) + else: + click.echo("SWHID mismatch: %s != %s" % (verify, swhid)) + sys.exit(1) else: - click.echo("SWHID mismatch: %s != %s" % (verify, swhid)) - sys.exit(1) - else: - for (obj, swhid) in results: - msg = swhid - if show_filename: - msg = "%s\t%s" % (swhid, os.fsdecode(obj)) - click.echo(msg) + for (obj, swhid) in results: + msg = swhid + if show_filename: + msg = "%s\t%s" % (swhid, os.fsdecode(obj)) + click.echo(msg) if __name__ == "__main__": identify() diff --git a/swh/model/from_disk.py b/swh/model/from_disk.py index ce17079..78dc174 100644 --- a/swh/model/from_disk.py +++ b/swh/model/from_disk.py @@ -1,540 +1,540 @@ # Copyright (C) 2017-2020 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 datetime import enum import fnmatch import glob import os import re import stat from typing import Any, Iterable, Iterator, List, Optional, Pattern, Tuple import attr from attrs_strict import type_validator from typing_extensions import Final from . import model from .exceptions import InvalidDirectoryPath from .hashutil import MultiHash from .identifiers import directory_entry_sort_key, directory_identifier from .identifiers import identifier_to_bytes as id_to_bytes from .identifiers import identifier_to_str as id_to_str from .merkle import MerkleLeaf, MerkleNode @attr.s(frozen=True, slots=True) class DiskBackedContent(model.BaseContent): """Content-like class, which allows lazy-loading data from the disk.""" object_type: Final = "content_file" sha1 = attr.ib(type=bytes, validator=type_validator()) sha1_git = attr.ib(type=model.Sha1Git, validator=type_validator()) sha256 = attr.ib(type=bytes, validator=type_validator()) blake2s256 = attr.ib(type=bytes, validator=type_validator()) length = attr.ib(type=int, validator=type_validator()) status = attr.ib( type=str, validator=attr.validators.in_(["visible", "hidden"]), default="visible", ) ctime = attr.ib( type=Optional[datetime.datetime], validator=type_validator(), default=None, eq=False, ) path = attr.ib(type=Optional[bytes], default=None) @classmethod def from_dict(cls, d): return cls(**d) def __attrs_post_init__(self): if self.path is None: raise TypeError("path must not be None.") def with_data(self) -> model.Content: args = self.to_dict() del args["path"] assert self.path is not None with open(self.path, "rb") as fd: return model.Content.from_dict({**args, "data": fd.read()}) class DentryPerms(enum.IntEnum): """Admissible permissions for directory entries.""" content = 0o100644 """Content""" executable_content = 0o100755 """Executable content (e.g. executable script)""" symlink = 0o120000 """Symbolic link""" directory = 0o040000 """Directory""" revision = 0o160000 """Revision (e.g. submodule)""" def mode_to_perms(mode): """Convert a file mode to a permission compatible with Software Heritage directory entries Args: mode (int): a file mode as returned by :func:`os.stat` in :attr:`os.stat_result.st_mode` Returns: DentryPerms: one of the following values: :const:`DentryPerms.content`: plain file :const:`DentryPerms.executable_content`: executable file :const:`DentryPerms.symlink`: symbolic link :const:`DentryPerms.directory`: directory """ if stat.S_ISLNK(mode): return DentryPerms.symlink if stat.S_ISDIR(mode): return DentryPerms.directory else: # file is executable in any way if mode & (0o111): return DentryPerms.executable_content else: return DentryPerms.content class Content(MerkleLeaf): """Representation of a Software Heritage content as a node in a Merkle tree. The current Merkle hash for the Content nodes is the `sha1_git`, which makes it consistent with what :class:`Directory` uses for its own hash computation. """ __slots__ = [] # type: List[str] object_type: Final = "content" @classmethod def from_bytes(cls, *, mode, data): """Convert data (raw :class:`bytes`) to a Software Heritage content entry Args: mode (int): a file mode (passed to :func:`mode_to_perms`) data (bytes): raw contents of the file """ ret = MultiHash.from_data(data).digest() ret["length"] = len(data) ret["perms"] = mode_to_perms(mode) ret["data"] = data ret["status"] = "visible" return cls(ret) @classmethod def from_symlink(cls, *, path, mode): """Convert a symbolic link to a Software Heritage content entry""" return cls.from_bytes(mode=mode, data=os.readlink(path)) @classmethod def from_file(cls, *, path, max_content_length=None): """Compute the Software Heritage content entry corresponding to an on-disk file. The returned dictionary contains keys useful for both: - loading the content in the archive (hashes, `length`) - using the content as a directory entry in a directory Args: save_path (bool): add the file path to the entry max_content_length (Optional[int]): if given, all contents larger than this will be skipped. """ file_stat = os.lstat(path) mode = file_stat.st_mode length = file_stat.st_size too_large = max_content_length is not None and length > max_content_length if stat.S_ISLNK(mode): # Symbolic link: return a file whose contents are the link target if too_large: # Unlike large contents, we can't stream symlinks to # MultiHash, and we don't want to fit them in memory if # they exceed max_content_length either. # Thankfully, this should not happen for reasonable values of # max_content_length because of OS/filesystem limitations, # so let's just raise an error. raise Exception(f"Symlink too large ({length} bytes)") return cls.from_symlink(path=path, mode=mode) elif not stat.S_ISREG(mode): # not a regular file: return the empty file instead return cls.from_bytes(mode=mode, data=b"") if too_large: skip_reason = "Content too large" else: skip_reason = None hashes = MultiHash.from_path(path).digest() if skip_reason: ret = { **hashes, "status": "absent", "reason": skip_reason, } else: ret = { **hashes, "status": "visible", } ret["path"] = path ret["perms"] = mode_to_perms(mode) ret["length"] = length obj = cls(ret) return obj def __repr__(self): return "Content(id=%s)" % id_to_str(self.hash) def compute_hash(self): return self.data["sha1_git"] def to_model(self) -> model.BaseContent: """Builds a `model.BaseContent` object based on this leaf.""" data = self.get_data().copy() data.pop("perms", None) if data["status"] == "absent": data.pop("path", None) return model.SkippedContent.from_dict(data) elif "data" in data: return model.Content.from_dict(data) else: return DiskBackedContent.from_dict(data) def accept_all_directories(dirpath: str, dirname: str, entries: Iterable[Any]) -> bool: """Default filter for :func:`Directory.from_disk` accepting all directories Args: dirname (bytes): directory name entries (list): directory entries """ return True def ignore_empty_directories( dirpath: str, dirname: str, entries: Iterable[Any] ) -> bool: """Filter for :func:`directory_to_objects` ignoring empty directories Args: dirname (bytes): directory name entries (list): directory entries Returns: True if the directory is not empty, false if the directory is empty """ return bool(entries) def ignore_named_directories(names, *, case_sensitive=True): """Filter for :func:`directory_to_objects` to ignore directories named one of names. Args: names (list of bytes): names to ignore case_sensitive (bool): whether to do the filtering in a case sensitive way Returns: a directory filter for :func:`directory_to_objects` """ if not case_sensitive: names = [name.lower() for name in names] def named_filter( dirpath: str, dirname: str, entries: Iterable[Any], names: Iterable[Any] = names, case_sensitive: bool = case_sensitive, ): if case_sensitive: return dirname not in names else: return dirname.lower() not in names return named_filter # TODO: `extract_regex_objs` has been copied and adapted from `swh.scanner`. # In the future `swh.scanner` should use the `swh.model` version and remove its own. def extract_regex_objs( root_path: bytes, patterns: Iterable[bytes] ) -> Iterator[Pattern[bytes]]: """Generates a regex object for each pattern given in input and checks if the path is a subdirectory or relative to the root path. Args: root_path (bytes): path to the root directory patterns (list of byte): patterns to match Yields: an SRE_Pattern object """ absolute_root_path = os.path.abspath(root_path) for pattern in patterns: for path in glob.glob(pattern): absolute_path = os.path.abspath(path) if not absolute_path.startswith(absolute_root_path): error_msg = ( b'The path "' + path + b'" is not a subdirectory or relative ' b'to the root directory path: "' + root_path + b'"' ) raise InvalidDirectoryPath(error_msg) regex = fnmatch.translate((pattern.decode())) yield re.compile(regex.encode()) def ignore_directories_patterns(root_path: bytes, patterns: Iterable[bytes]): """Filter for :func:`directory_to_objects` to ignore directories matching certain patterns. Args: root_path (bytes): path of the root directory patterns (list of byte): patterns to ignore Returns: a directory filter for :func:`directory_to_objects` """ sre_patterns = set(extract_regex_objs(root_path, patterns)) def pattern_filter( dirpath: bytes, dirname: bytes, entries: Iterable[Any], patterns: Iterable[Any] = sre_patterns, root_path: bytes = os.path.abspath(root_path), ): full_path = os.path.abspath(dirpath) relative_path = os.path.relpath(full_path, root_path) return not any([pattern.match(relative_path) for pattern in patterns]) return pattern_filter def iter_directory( directory, ) -> Tuple[List[model.Content], List[model.SkippedContent], List[model.Directory]]: """Return the directory listing from a disk-memory directory instance. Raises: TypeError in case an unexpected object type is listed. Returns: Tuple of respectively iterable of content, skipped content and directories. """ contents: List[model.Content] = [] skipped_contents: List[model.SkippedContent] = [] directories: List[model.Directory] = [] for obj in directory.iter_tree(): obj = obj.to_model() obj_type = obj.object_type if obj_type in (model.Content.object_type, DiskBackedContent.object_type): # FIXME: read the data from disk later (when the # storage buffer is flushed). obj = obj.with_data() contents.append(obj) elif obj_type == model.SkippedContent.object_type: skipped_contents.append(obj) elif obj_type == model.Directory.object_type: directories.append(obj) else: raise TypeError(f"Unexpected object type from disk: {obj}") return contents, skipped_contents, directories class Directory(MerkleNode): """Representation of a Software Heritage directory as a node in a Merkle Tree. This class can be used to generate, from an on-disk directory, all the objects that need to be sent to the Software Heritage archive. The :func:`from_disk` constructor allows you to generate the data structure from a directory on disk. The resulting :class:`Directory` can then be manipulated as a dictionary, using the path as key. The :func:`collect` method is used to retrieve all the objects that need to be added to the Software Heritage archive since the last collection, by class (contents and directories). When using the dict-like methods to update the contents of the directory, the affected levels of hierarchy are reset and can be collected again using the same method. This enables the efficient collection of updated nodes, for instance when the client is applying diffs. """ __slots__ = ["__entries"] object_type: Final = "directory" @classmethod def from_disk( cls, *, path, dir_filter=accept_all_directories, max_content_length=None ): """Compute the Software Heritage objects for a given directory tree Args: path (bytes): the directory to traverse data (bool): whether to add the data to the content objects save_path (bool): whether to add the path to the content objects dir_filter (function): a filter to ignore some directories by name or contents. Takes two arguments: dirname and entries, and returns True if the directory should be added, False if the directory should be ignored. max_content_length (Optional[int]): if given, all contents larger than this will be skipped. """ top_path = path dirs = {} for root, dentries, fentries in os.walk(top_path, topdown=False): entries = {} # Join fentries and dentries in the same processing, as symbolic # links to directories appear in dentries... for name in fentries + dentries: path = os.path.join(root, name) if not os.path.isdir(path) or os.path.islink(path): content = Content.from_file( path=path, max_content_length=max_content_length ) entries[name] = content else: if dir_filter(path, name, dirs[path].entries): entries[name] = dirs[path] - dirs[root] = cls({"name": os.path.basename(root)}) + dirs[root] = cls({"name": os.path.basename(root), "path": root}) dirs[root].update(entries) return dirs[top_path] def __init__(self, data=None): super().__init__(data=data) self.__entries = None def invalidate_hash(self): self.__entries = None super().invalidate_hash() @staticmethod def child_to_directory_entry(name, child): if child.object_type == "directory": return { "type": "dir", "perms": DentryPerms.directory, "target": child.hash, "name": name, } elif child.object_type == "content": return { "type": "file", "perms": child.data["perms"], "target": child.hash, "name": name, } else: raise ValueError(f"unknown child {child}") def get_data(self, **kwargs): return { "id": self.hash, "entries": self.entries, } @property def entries(self): """Child nodes, sorted by name in the same way `directory_identifier` does.""" if self.__entries is None: self.__entries = sorted( ( self.child_to_directory_entry(name, child) for name, child in self.items() ), key=directory_entry_sort_key, ) return self.__entries def compute_hash(self): return id_to_bytes(directory_identifier({"entries": self.entries})) def to_model(self) -> model.Directory: """Builds a `model.Directory` object based on this node; ignoring its children.""" return model.Directory.from_dict(self.get_data()) def __getitem__(self, key): if not isinstance(key, bytes): raise ValueError("Can only get a bytes from Directory") # Convenience shortcut if key == b"": return self if b"/" not in key: return super().__getitem__(key) else: key1, key2 = key.split(b"/", 1) return self.__getitem__(key1)[key2] def __setitem__(self, key, value): if not isinstance(key, bytes): raise ValueError("Can only set a bytes Directory entry") if not isinstance(value, (Content, Directory)): raise ValueError( "Can only set a Directory entry to a Content or " "Directory" ) if key == b"": raise ValueError("Directory entry must have a name") if b"\x00" in key: raise ValueError("Directory entry name must not contain nul bytes") if b"/" not in key: return super().__setitem__(key, value) else: key1, key2 = key.rsplit(b"/", 1) self[key1].__setitem__(key2, value) def __delitem__(self, key): if not isinstance(key, bytes): raise ValueError("Can only delete a bytes Directory entry") if b"/" not in key: super().__delitem__(key) else: key1, key2 = key.rsplit(b"/", 1) del self[key1][key2] def __repr__(self): return "Directory(id=%s, entries=[%s])" % ( id_to_str(self.hash), ", ".join(str(entry) for entry in self), ) diff --git a/swh/model/identifiers.py b/swh/model/identifiers.py index d542178..04bd407 100644 --- a/swh/model/identifiers.py +++ b/swh/model/identifiers.py @@ -1,1266 +1,1268 @@ # Copyright (C) 2015-2021 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 __future__ import annotations import binascii import datetime import enum from functools import lru_cache import hashlib import re from typing import ( Any, Dict, Generic, Iterable, List, Optional, Tuple, Type, TypeVar, Union, ) import urllib.parse import attr from attrs_strict import type_validator from .exceptions import ValidationError from .hashutil import MultiHash, git_object_header, hash_to_bytes, hash_to_hex class ObjectType(enum.Enum): """Possible object types of a QualifiedSWHID or CoreSWHID. The values of each variant is what is used in the SWHID's string representation.""" SNAPSHOT = "snp" REVISION = "rev" RELEASE = "rel" DIRECTORY = "dir" CONTENT = "cnt" class ExtendedObjectType(enum.Enum): """Possible object types of an ExtendedSWHID. The variants are a superset of :class:`ObjectType`'s""" SNAPSHOT = "snp" REVISION = "rev" RELEASE = "rel" DIRECTORY = "dir" CONTENT = "cnt" ORIGIN = "ori" RAW_EXTRINSIC_METADATA = "emd" # The following are deprecated aliases of the variants defined in ObjectType # while transitioning from SWHID to QualifiedSWHID ORIGIN = "origin" SNAPSHOT = "snapshot" REVISION = "revision" RELEASE = "release" DIRECTORY = "directory" CONTENT = "content" RAW_EXTRINSIC_METADATA = "raw_extrinsic_metadata" SWHID_NAMESPACE = "swh" SWHID_VERSION = 1 SWHID_TYPES = ["snp", "rel", "rev", "dir", "cnt"] EXTENDED_SWHID_TYPES = SWHID_TYPES + ["ori", "emd"] SWHID_SEP = ":" SWHID_CTXT_SEP = ";" SWHID_QUALIFIERS = {"origin", "anchor", "visit", "path", "lines"} SWHID_RE_RAW = ( f"(?P{SWHID_NAMESPACE})" f"{SWHID_SEP}(?P{SWHID_VERSION})" f"{SWHID_SEP}(?P{'|'.join(EXTENDED_SWHID_TYPES)})" f"{SWHID_SEP}(?P[0-9a-f]{{40}})" f"({SWHID_CTXT_SEP}(?P\\S+))?" ) SWHID_RE = re.compile(SWHID_RE_RAW) @lru_cache() def identifier_to_bytes(identifier): """Convert a text identifier to bytes. Args: identifier: an identifier, either a 40-char hexadecimal string or a bytes object of length 20 Returns: The length 20 bytestring corresponding to the given identifier Raises: ValueError: if the identifier is of an unexpected type or length. """ if isinstance(identifier, bytes): if len(identifier) != 20: raise ValueError( "Wrong length for bytes identifier %s, expected 20" % len(identifier) ) return identifier if isinstance(identifier, str): if len(identifier) != 40: raise ValueError( "Wrong length for str identifier %s, expected 40" % len(identifier) ) return bytes.fromhex(identifier) raise ValueError( "Wrong type for identifier %s, expected bytes or str" % identifier.__class__.__name__ ) @lru_cache() def identifier_to_str(identifier): """Convert an identifier to an hexadecimal string. Args: identifier: an identifier, either a 40-char hexadecimal string or a bytes object of length 20 Returns: The length 40 string corresponding to the given identifier, hex encoded Raises: ValueError: if the identifier is of an unexpected type or length. """ if isinstance(identifier, str): if len(identifier) != 40: raise ValueError( "Wrong length for str identifier %s, expected 40" % len(identifier) ) return identifier if isinstance(identifier, bytes): if len(identifier) != 20: raise ValueError( "Wrong length for bytes identifier %s, expected 20" % len(identifier) ) return binascii.hexlify(identifier).decode() raise ValueError( "Wrong type for identifier %s, expected bytes or str" % identifier.__class__.__name__ ) def content_identifier(content: Dict[str, Any]) -> Dict[str, bytes]: """Return the intrinsic identifier for a content. A content's identifier is the sha1, sha1_git and sha256 checksums of its data. Args: content: a content conforming to the Software Heritage schema Returns: A dictionary with all the hashes for the data Raises: KeyError: if the content doesn't have a data member. """ return MultiHash.from_data(content["data"]).digest() def directory_entry_sort_key(entry): """The sorting key for tree entries""" if entry["type"] == "dir": return entry["name"] + b"/" else: return entry["name"] @lru_cache() def _perms_to_bytes(perms): """Convert the perms value to its bytes representation""" oc = oct(perms)[2:] return oc.encode("ascii") def escape_newlines(snippet): """Escape the newlines present in snippet according to git rules. New lines in git manifests are escaped by indenting the next line by one space. """ if b"\n" in snippet: return b"\n ".join(snippet.split(b"\n")) else: return snippet def directory_identifier(directory: Dict[str, Any]) -> str: """Return the intrinsic identifier for a directory. A directory's identifier is the tree sha1 à la git of a directory listing, using the following algorithm, which is equivalent to the git algorithm for trees: 1. Entries of the directory are sorted using the name (or the name with '/' appended for directory entries) as key, in bytes order. 2. For each entry of the directory, the following bytes are output: - the octal representation of the permissions for the entry (stored in the 'perms' member), which is a representation of the entry type: - b'100644' (int 33188) for files - b'100755' (int 33261) for executable files - b'120000' (int 40960) for symbolic links - b'40000' (int 16384) for directories - b'160000' (int 57344) for references to revisions - an ascii space (b'\x20') - the entry's name (as raw bytes), stored in the 'name' member - a null byte (b'\x00') - the 20 byte long identifier of the object pointed at by the entry, stored in the 'target' member: - for files or executable files: their blob sha1_git - for symbolic links: the blob sha1_git of a file containing the link destination - for directories: their intrinsic identifier - for revisions: their intrinsic identifier (Note that there is no separator between entries) """ git_object = directory_git_object(directory) return hashlib.new("sha1", git_object).hexdigest() def directory_git_object(directory: Dict[str, Any]) -> bytes: components = [] for entry in sorted(directory["entries"], key=directory_entry_sort_key): components.extend( [ _perms_to_bytes(entry["perms"]), b"\x20", entry["name"], b"\x00", identifier_to_bytes(entry["target"]), ] ) return format_git_object_from_parts("tree", components) def format_date(date): """Convert a date object into an UTC timestamp encoded as ascii bytes. Git stores timestamps as an integer number of seconds since the UNIX epoch. However, Software Heritage stores timestamps as an integer number of microseconds (postgres type "datetime with timezone"). Therefore, we print timestamps with no microseconds as integers, and timestamps with microseconds as floating point values. We elide the trailing zeroes from microsecond values, to "future-proof" our representation if we ever need more precision in timestamps. """ if not isinstance(date, dict): raise ValueError("format_date only supports dicts, %r received" % date) seconds = date.get("seconds", 0) microseconds = date.get("microseconds", 0) if not microseconds: return str(seconds).encode() else: float_value = "%d.%06d" % (seconds, microseconds) return float_value.rstrip("0").encode() @lru_cache() def format_offset(offset, negative_utc=None): """Convert an integer number of minutes into an offset representation. The offset representation is [+-]hhmm where: - hh is the number of hours; - mm is the number of minutes. A null offset is represented as +0000. """ if offset < 0 or offset == 0 and negative_utc: sign = "-" else: sign = "+" hours = abs(offset) // 60 minutes = abs(offset) % 60 t = "%s%02d%02d" % (sign, hours, minutes) return t.encode() def normalize_timestamp(time_representation): """Normalize a time representation for processing by Software Heritage This function supports a numeric timestamp (representing a number of seconds since the UNIX epoch, 1970-01-01 at 00:00 UTC), a :obj:`datetime.datetime` object (with timezone information), or a normalized Software Heritage time representation (idempotency). Args: time_representation: the representation of a timestamp Returns: dict: a normalized dictionary with three keys: - timestamp: a dict with two optional keys: - seconds: the integral number of seconds since the UNIX epoch - microseconds: the integral number of microseconds - offset: the timezone offset as a number of minutes relative to UTC - negative_utc: a boolean representing whether the offset is -0000 when offset = 0. """ if time_representation is None: return None negative_utc = False if isinstance(time_representation, dict): ts = time_representation["timestamp"] if isinstance(ts, dict): seconds = ts.get("seconds", 0) microseconds = ts.get("microseconds", 0) elif isinstance(ts, int): seconds = ts microseconds = 0 else: raise ValueError( "normalize_timestamp received non-integer timestamp member:" " %r" % ts ) offset = time_representation["offset"] if "negative_utc" in time_representation: negative_utc = time_representation["negative_utc"] if negative_utc is None: negative_utc = False elif isinstance(time_representation, datetime.datetime): - seconds = int(time_representation.timestamp()) microseconds = time_representation.microsecond + if microseconds: + time_representation = time_representation.replace(microsecond=0) + seconds = int(time_representation.timestamp()) utcoffset = time_representation.utcoffset() if utcoffset is None: raise ValueError( "normalize_timestamp received datetime without timezone: %s" % time_representation ) # utcoffset is an integer number of minutes seconds_offset = utcoffset.total_seconds() offset = int(seconds_offset) // 60 elif isinstance(time_representation, int): seconds = time_representation microseconds = 0 offset = 0 else: raise ValueError( "normalize_timestamp received non-integer timestamp:" " %r" % time_representation ) return { "timestamp": {"seconds": seconds, "microseconds": microseconds,}, "offset": offset, "negative_utc": negative_utc, } def format_author(author): """Format the specification of an author. An author is either a byte string (passed unchanged), or a dict with three keys, fullname, name and email. If the fullname exists, return it; if it doesn't, we construct a fullname using the following heuristics: if the name value is None, we return the email in angle brackets, else, we return the name, a space, and the email in angle brackets. """ if isinstance(author, bytes) or author is None: return author if "fullname" in author: return author["fullname"] ret = [] if author["name"] is not None: ret.append(author["name"]) if author["email"] is not None: ret.append(b"".join([b"<", author["email"], b">"])) return b" ".join(ret) def format_git_object_from_headers( git_type: str, headers: Iterable[Tuple[bytes, bytes]], message: Optional[bytes] = None, ) -> bytes: """Format a git_object comprised of a git header and a manifest, which is itself a sequence of `headers`, and an optional `message`. The git_object format, compatible with the git format for tag and commit objects, is as follows: - for each `key`, `value` in `headers`, emit: - the `key`, literally - an ascii space (``\\x20``) - the `value`, with newlines escaped using :func:`escape_newlines`, - an ascii newline (``\\x0a``) - if the `message` is not None, emit: - an ascii newline (``\\x0a``) - the `message`, literally Args: headers: a sequence of key/value headers stored in the manifest; message: an optional message used to trail the manifest. Returns: the formatted git_object as bytes """ entries: List[bytes] = [] for key, value in headers: entries.extend((key, b" ", escape_newlines(value), b"\n")) if message is not None: entries.extend((b"\n", message)) concatenated_entries = b"".join(entries) header = git_object_header(git_type, len(concatenated_entries)) return header + concatenated_entries def format_git_object_from_parts(git_type: str, parts: Iterable[bytes]) -> bytes: """Similar to :func:`format_git_object_from_headers`, but for manifests made of a flat list of entries, instead of key-value + message, ie. trees and snapshots.""" concatenated_parts = b"".join(parts) header = git_object_header(git_type, len(concatenated_parts)) return header + concatenated_parts def format_author_data(author, date_offset) -> bytes: """Format authorship data according to git standards. Git authorship data has two components: - an author specification, usually a name and email, but in practice an arbitrary bytestring - optionally, a timestamp with a UTC offset specification The authorship data is formatted thus:: `name and email`[ `timestamp` `utc_offset`] The timestamp is encoded as a (decimal) number of seconds since the UNIX epoch (1970-01-01 at 00:00 UTC). As an extension to the git format, we support fractional timestamps, using a dot as the separator for the decimal part. The utc offset is a number of minutes encoded as '[+-]HHMM'. Note that some tools can pass a negative offset corresponding to the UTC timezone ('-0000'), which is valid and is encoded as such. Args: author: an author specification (dict with two bytes values: name and email, or byte value) date_offset: a normalized date/time representation as returned by :func:`normalize_timestamp`. Returns: the byte string containing the authorship data """ ret = [format_author(author)] date_offset = normalize_timestamp(date_offset) if date_offset is not None: date_f = format_date(date_offset["timestamp"]) offset_f = format_offset(date_offset["offset"], date_offset["negative_utc"]) ret.extend([b" ", date_f, b" ", offset_f]) return b"".join(ret) def revision_identifier(revision: Dict[str, Any]) -> str: """Return the intrinsic identifier for a revision. The fields used for the revision identifier computation are: - directory - parents - author - author_date - committer - committer_date - extra_headers or metadata -> extra_headers - message A revision's identifier is the 'git'-checksum of a commit manifest constructed as follows (newlines are a single ASCII newline character):: tree [for each parent in parents] parent [end for each parents] author committer [for each key, value in extra_headers] [end for each extra_headers] The directory identifier is the ascii representation of its hexadecimal encoding. Author and committer are formatted with the :func:`format_author` function. Dates are formatted with the :func:`format_offset` function. Extra headers are an ordered list of [key, value] pairs. Keys are strings and get encoded to utf-8 for identifier computation. Values are either byte strings, unicode strings (that get encoded to utf-8), or integers (that get encoded to their utf-8 decimal representation). Multiline extra header values are escaped by indenting the continuation lines with one ascii space. If the message is None, the manifest ends with the last header. Else, the message is appended to the headers after an empty line. The checksum of the full manifest is computed using the 'commit' git object type. """ git_object = revision_git_object(revision) return hashlib.new("sha1", git_object).hexdigest() def revision_git_object(revision: Dict[str, Any]) -> bytes: """Formats the git_object of a revision. See :func:`revision_identifier` for details on the format.""" headers = [(b"tree", identifier_to_str(revision["directory"]).encode())] for parent in revision["parents"]: if parent: headers.append((b"parent", identifier_to_str(parent).encode())) headers.append( (b"author", format_author_data(revision["author"], revision["date"])) ) headers.append( ( b"committer", format_author_data(revision["committer"], revision["committer_date"]), ) ) # Handle extra headers metadata = revision.get("metadata") or {} extra_headers = revision.get("extra_headers", ()) if not extra_headers and "extra_headers" in metadata: extra_headers = metadata["extra_headers"] headers.extend(extra_headers) return format_git_object_from_headers("commit", headers, revision["message"]) def target_type_to_git(target_type: str) -> bytes: """Convert a software heritage target type to a git object type""" return { "content": b"blob", "directory": b"tree", "revision": b"commit", "release": b"tag", "snapshot": b"refs", }[target_type] def release_identifier(release: Dict[str, Any]) -> str: """Return the intrinsic identifier for a release.""" git_object = release_git_object(release) return hashlib.new("sha1", git_object).hexdigest() def release_git_object(release: Dict[str, Any]) -> bytes: headers = [ (b"object", identifier_to_str(release["target"]).encode()), (b"type", target_type_to_git(release["target_type"])), (b"tag", release["name"]), ] if "author" in release and release["author"]: headers.append( (b"tagger", format_author_data(release["author"], release["date"])) ) return format_git_object_from_headers("tag", headers, release["message"]) def snapshot_identifier( snapshot: Dict[str, Any], *, ignore_unresolved: bool = False ) -> str: """Return the intrinsic identifier for a snapshot. Snapshots are a set of named branches, which are pointers to objects at any level of the Software Heritage DAG. As well as pointing to other objects in the Software Heritage DAG, branches can also be *alias*es, in which case their target is the name of another branch in the same snapshot, or *dangling*, in which case the target is unknown (and represented by the ``None`` value). A snapshot identifier is a salted sha1 (using the git hashing algorithm with the ``snapshot`` object type) of a manifest following the algorithm: 1. Branches are sorted using the name as key, in bytes order. 2. For each branch, the following bytes are output: - the type of the branch target: - ``content``, ``directory``, ``revision``, ``release`` or ``snapshot`` for the corresponding entries in the DAG; - ``alias`` for branches referencing another branch; - ``dangling`` for dangling branches - an ascii space (``\\x20``) - the branch name (as raw bytes) - a null byte (``\\x00``) - the length of the target identifier, as an ascii-encoded decimal number (``20`` for current intrinsic identifiers, ``0`` for dangling branches, the length of the target branch name for branch aliases) - a colon (``:``) - the identifier of the target object pointed at by the branch, stored in the 'target' member: - for contents: their *sha1_git* - for directories, revisions, releases or snapshots: their intrinsic identifier - for branch aliases, the name of the target branch (as raw bytes) - for dangling branches, the empty string Note that, akin to directory manifests, there is no separator between entries. Because of symbolic branches, identifiers are of arbitrary length but are length-encoded to avoid ambiguity. Args: snapshot (dict): the snapshot of which to compute the identifier. A single entry is needed, ``'branches'``, which is itself a :class:`dict` mapping each branch to its target ignore_unresolved (bool): if `True`, ignore unresolved branch aliases. Returns: str: the intrinsic identifier for `snapshot` """ git_object = snapshot_git_object(snapshot, ignore_unresolved=ignore_unresolved) return hashlib.new("sha1", git_object).hexdigest() def snapshot_git_object( snapshot: Dict[str, Any], *, ignore_unresolved: bool = False ) -> bytes: """Formats the git_object of a revision. See :func:`snapshot_identifier` for details on the format.""" unresolved = [] lines = [] for name, target in sorted(snapshot["branches"].items()): if not target: target_type = b"dangling" target_id = b"" elif target["target_type"] == "alias": target_type = b"alias" target_id = target["target"] if target_id not in snapshot["branches"] or target_id == name: unresolved.append((name, target_id)) else: target_type = target["target_type"].encode() target_id = identifier_to_bytes(target["target"]) lines.extend( [ target_type, b"\x20", name, b"\x00", ("%d:" % len(target_id)).encode(), target_id, ] ) if unresolved and not ignore_unresolved: raise ValueError( "Branch aliases unresolved: %s" % ", ".join("%r -> %r" % x for x in unresolved), unresolved, ) return format_git_object_from_parts("snapshot", lines) def origin_identifier(origin): """Return the intrinsic identifier for an origin. An origin's identifier is the sha1 checksum of the entire origin URL """ return hashlib.sha1(origin["url"].encode("utf-8")).hexdigest() def raw_extrinsic_metadata_identifier(metadata: Dict[str, Any]) -> str: """Return the intrinsic identifier for a RawExtrinsicMetadata object. A raw_extrinsic_metadata identifier is a salted sha1 (using the git hashing algorithm with the ``raw_extrinsic_metadata`` object type) of a manifest following the format:: target $ExtendedSwhid discovery_date $Timestamp authority $StrWithoutSpaces $IRI fetcher $Str $Version format $StrWithoutSpaces origin $IRI <- optional visit $IntInDecimal <- optional snapshot $CoreSwhid <- optional release $CoreSwhid <- optional revision $CoreSwhid <- optional path $Bytes <- optional directory $CoreSwhid <- optional $MetadataBytes $IRI must be RFC 3987 IRIs (so they may contain newlines, that are escaped as described below) $StrWithoutSpaces and $Version are ASCII strings, and may not contain spaces. $Str is an UTF-8 string. $CoreSwhid are core SWHIDs, as defined in :ref:`persistent-identifiers`. $ExtendedSwhid is a core SWHID, with extra types allowed ('ori' for origins and 'emd' for raw extrinsic metadata) $Timestamp is a decimal representation of the rounded-down integer number of seconds since the UNIX epoch (1970-01-01 00:00:00 UTC), with no leading '0' (unless the timestamp value is zero) and no timezone. It may be negative by prefixing it with a '-', which must not be followed by a '0'. Newlines in $Bytes, $Str, and $Iri are escaped as with other git fields, ie. by adding a space after them. Returns: str: the intrinsic identifier for ``metadata`` """ git_object = raw_extrinsic_metadata_git_object(metadata) return hashlib.new("sha1", git_object).hexdigest() def raw_extrinsic_metadata_git_object(metadata: Dict[str, Any]) -> bytes: """Formats the git_object of a raw_extrinsic_metadata object. See :func:`raw_extrinsic_metadata_identifier` for details on the format.""" # equivalent to using math.floor(dt.timestamp()) to round down, # as int(dt.timestamp()) rounds toward zero, # which would map two seconds on the 0 timestamp. # # This should never be an issue in practice as Software Heritage didn't # start collecting metadata before 2015. timestamp = ( metadata["discovery_date"] .astimezone(datetime.timezone.utc) .replace(microsecond=0) .timestamp() ) assert timestamp.is_integer() headers = [ (b"target", str(metadata["target"]).encode()), (b"discovery_date", str(int(timestamp)).encode("ascii")), ( b"authority", f"{metadata['authority']['type']} {metadata['authority']['url']}".encode(), ), ( b"fetcher", f"{metadata['fetcher']['name']} {metadata['fetcher']['version']}".encode(), ), (b"format", metadata["format"].encode()), ] for key in ( "origin", "visit", "snapshot", "release", "revision", "path", "directory", ): if metadata.get(key) is not None: value: bytes if key == "path": value = metadata[key] else: value = str(metadata[key]).encode() headers.append((key.encode("ascii"), value)) return format_git_object_from_headers( "raw_extrinsic_metadata", headers, metadata["metadata"] ) def extid_identifier(extid: Dict[str, Any]) -> str: """Return the intrinsic identifier for an ExtID object. An ExtID identifier is a salted sha1 (using the git hashing algorithm with the ``extid`` object type) of a manifest following the format: ``` extid_type $StrWithoutSpaces extid $Bytes target $CoreSwhid ``` $StrWithoutSpaces is an ASCII string, and may not contain spaces. Newlines in $Bytes are escaped as with other git fields, ie. by adding a space after them. Returns: str: the intrinsic identifier for `extid` """ headers = [ (b"extid_type", extid["extid_type"].encode("ascii")), (b"extid", extid["extid"]), (b"target", str(extid["target"]).encode("ascii")), ] git_object = format_git_object_from_headers("extid", headers) return hashlib.new("sha1", git_object).hexdigest() # type of the "object_type" attribute of the SWHID class; either # ObjectType or ExtendedObjectType _TObjectType = TypeVar("_TObjectType", ObjectType, ExtendedObjectType) # the SWHID class itself (this is used so that X.from_string() can return X # for all X subclass of _BaseSWHID) _TSWHID = TypeVar("_TSWHID", bound="_BaseSWHID") @attr.s(frozen=True, kw_only=True) class _BaseSWHID(Generic[_TObjectType]): """Common base class for CoreSWHID, QualifiedSWHID, and ExtendedSWHID. This is an "abstract" class and should not be instantiated directly; it only exists to deduplicate code between these three SWHID classes.""" namespace = attr.ib(type=str, default=SWHID_NAMESPACE) """the namespace of the identifier, defaults to ``swh``""" scheme_version = attr.ib(type=int, default=SWHID_VERSION) """the scheme version of the identifier, defaults to 1""" # overridden by subclasses object_type: _TObjectType """the type of object the identifier points to""" object_id = attr.ib(type=bytes, validator=type_validator()) """object's identifier""" @namespace.validator def check_namespace(self, attribute, value): if value != SWHID_NAMESPACE: raise ValidationError( "Invalid SWHID: invalid namespace: %(namespace)s", params={"namespace": value}, ) @scheme_version.validator def check_scheme_version(self, attribute, value): if value != SWHID_VERSION: raise ValidationError( "Invalid SWHID: invalid version: %(version)s", params={"version": value} ) @object_id.validator def check_object_id(self, attribute, value): if len(value) != 20: raise ValidationError( "Invalid SWHID: invalid checksum: %(object_id)s", params={"object_id": hash_to_hex(value)}, ) def __str__(self) -> str: return SWHID_SEP.join( [ self.namespace, str(self.scheme_version), self.object_type.value, hash_to_hex(self.object_id), ] ) @classmethod def from_string(cls: Type[_TSWHID], s: str) -> _TSWHID: parts = _parse_swhid(s) if parts.pop("qualifiers"): raise ValidationError(f"{cls.__name__} does not support qualifiers.") try: return cls(**parts) except ValueError as e: raise ValidationError( "ValueError: %(args)s", params={"args": e.args} ) from None @attr.s(frozen=True, kw_only=True) class CoreSWHID(_BaseSWHID[ObjectType]): """ Dataclass holding the relevant info associated to a SoftWare Heritage persistent IDentifier (SWHID). Unlike `QualifiedSWHID`, it is restricted to core SWHIDs, ie. SWHIDs with no qualifiers. Raises: swh.model.exceptions.ValidationError: In case of invalid object type or id To get the raw SWHID string from an instance of this class, use the :func:`str` function: >>> swhid = CoreSWHID( ... object_type=ObjectType.CONTENT, ... object_id=bytes.fromhex('8ff44f081d43176474b267de5451f2c2e88089d0'), ... ) >>> str(swhid) 'swh:1:cnt:8ff44f081d43176474b267de5451f2c2e88089d0' And vice-versa with :meth:`CoreSWHID.from_string`: >>> swhid == CoreSWHID.from_string( ... "swh:1:cnt:8ff44f081d43176474b267de5451f2c2e88089d0" ... ) True """ object_type = attr.ib( type=ObjectType, validator=type_validator(), converter=ObjectType ) """the type of object the identifier points to""" def to_extended(self) -> ExtendedSWHID: """Converts this CoreSWHID into an ExtendedSWHID. As ExtendedSWHID is a superset of CoreSWHID, this is lossless.""" return ExtendedSWHID( namespace=self.namespace, scheme_version=self.scheme_version, object_type=ExtendedObjectType(self.object_type.value), object_id=self.object_id, ) def _parse_core_swhid(swhid: Union[str, CoreSWHID, None]) -> Optional[CoreSWHID]: if swhid is None or isinstance(swhid, CoreSWHID): return swhid else: return CoreSWHID.from_string(swhid) def _parse_lines_qualifier( lines: Union[str, Tuple[int, Optional[int]], None] ) -> Optional[Tuple[int, Optional[int]]]: try: if lines is None or isinstance(lines, tuple): return lines elif "-" in lines: (from_, to) = lines.split("-", 2) return (int(from_), int(to)) else: return (int(lines), None) except ValueError: raise ValidationError( "Invalid format for the lines qualifier: %(lines)s", params={"lines": lines} ) def _parse_path_qualifier(path: Union[str, bytes, None]) -> Optional[bytes]: if path is None or isinstance(path, bytes): return path else: return urllib.parse.unquote_to_bytes(path) @attr.s(frozen=True, kw_only=True) class QualifiedSWHID(_BaseSWHID[ObjectType]): """ Dataclass holding the relevant info associated to a SoftWare Heritage persistent IDentifier (SWHID) Raises: swh.model.exceptions.ValidationError: In case of invalid object type or id To get the raw SWHID string from an instance of this class, use the :func:`str` function: >>> swhid = QualifiedSWHID( ... object_type=ObjectType.CONTENT, ... object_id=bytes.fromhex('8ff44f081d43176474b267de5451f2c2e88089d0'), ... lines=(5, 10), ... ) >>> str(swhid) 'swh:1:cnt:8ff44f081d43176474b267de5451f2c2e88089d0;lines=5-10' And vice-versa with :meth:`QualifiedSWHID.from_string`: >>> swhid == QualifiedSWHID.from_string( ... "swh:1:cnt:8ff44f081d43176474b267de5451f2c2e88089d0;lines=5-10" ... ) True """ object_type = attr.ib( type=ObjectType, validator=type_validator(), converter=ObjectType ) """the type of object the identifier points to""" # qualifiers: origin = attr.ib(type=Optional[str], default=None, validator=type_validator()) """the software origin where an object has been found or observed in the wild, as an URI""" visit = attr.ib(type=Optional[CoreSWHID], default=None, converter=_parse_core_swhid) """the core identifier of a snapshot corresponding to a specific visit of a repository containing the designated object""" anchor = attr.ib( type=Optional[CoreSWHID], default=None, validator=type_validator(), converter=_parse_core_swhid, ) """a designated node in the Merkle DAG relative to which a path to the object is specified, as the core identifier of a directory, a revision, a release, or a snapshot""" path = attr.ib( type=Optional[bytes], default=None, validator=type_validator(), converter=_parse_path_qualifier, ) """the absolute file path, from the root directory associated to the anchor node, to the object; when the anchor denotes a directory or a revision, and almost always when it’s a release, the root directory is uniquely determined; when the anchor denotes a snapshot, the root directory is the one pointed to by HEAD (possibly indirectly), and undefined if such a reference is missing""" lines = attr.ib( type=Optional[Tuple[int, Optional[int]]], default=None, validator=type_validator(), converter=_parse_lines_qualifier, ) """lines: line number(s) of interest, usually within a content object""" @visit.validator def check_visit(self, attribute, value): if value and value.object_type != ObjectType.SNAPSHOT: raise ValidationError( "The 'visit' qualifier must be a 'snp' SWHID, not '%(type)s'", params={"type": value.object_type.value}, ) @anchor.validator def check_anchor(self, attribute, value): if value and value.object_type not in ( ObjectType.DIRECTORY, ObjectType.REVISION, ObjectType.RELEASE, ObjectType.SNAPSHOT, ): raise ValidationError( "The 'visit' qualifier must be a 'dir', 'rev', 'rel', or 'snp' SWHID, " "not '%s(type)s'", params={"type": value.object_type.value}, ) def qualifiers(self) -> Dict[str, str]: origin = self.origin if origin: unescaped_origin = origin origin = origin.replace(";", "%3B") assert urllib.parse.unquote_to_bytes( origin ) == urllib.parse.unquote_to_bytes( unescaped_origin ), "Escaping ';' in the origin qualifier corrupted the origin URL." d: Dict[str, Optional[str]] = { "origin": origin, "visit": str(self.visit) if self.visit else None, "anchor": str(self.anchor) if self.anchor else None, "path": ( urllib.parse.quote_from_bytes(self.path) if self.path is not None else None ), "lines": ( "-".join(str(line) for line in self.lines if line is not None) if self.lines else None ), } return {k: v for (k, v) in d.items() if v is not None} def __str__(self) -> str: swhid = SWHID_SEP.join( [ self.namespace, str(self.scheme_version), self.object_type.value, hash_to_hex(self.object_id), ] ) qualifiers = self.qualifiers() if qualifiers: for k, v in qualifiers.items(): swhid += "%s%s=%s" % (SWHID_CTXT_SEP, k, v) return swhid @classmethod def from_string(cls, s: str) -> QualifiedSWHID: parts = _parse_swhid(s) qualifiers = parts.pop("qualifiers") invalid_qualifiers = set(qualifiers) - SWHID_QUALIFIERS if invalid_qualifiers: raise ValidationError( "Invalid qualifier(s): %(qualifiers)s", params={"qualifiers": ", ".join(invalid_qualifiers)}, ) try: return QualifiedSWHID(**parts, **qualifiers) except ValueError as e: raise ValidationError( "ValueError: %(args)s", params={"args": e.args} ) from None @attr.s(frozen=True, kw_only=True) class ExtendedSWHID(_BaseSWHID[ExtendedObjectType]): """ Dataclass holding the relevant info associated to a SoftWare Heritage persistent IDentifier (SWHID). It extends `CoreSWHID`, by allowing non-standard object types; and should only be used internally to Software Heritage. Raises: swh.model.exceptions.ValidationError: In case of invalid object type or id To get the raw SWHID string from an instance of this class, use the :func:`str` function: >>> swhid = ExtendedSWHID( ... object_type=ExtendedObjectType.CONTENT, ... object_id=bytes.fromhex('8ff44f081d43176474b267de5451f2c2e88089d0'), ... ) >>> str(swhid) 'swh:1:cnt:8ff44f081d43176474b267de5451f2c2e88089d0' And vice-versa with :meth:`CoreSWHID.from_string`: >>> swhid == ExtendedSWHID.from_string( ... "swh:1:cnt:8ff44f081d43176474b267de5451f2c2e88089d0" ... ) True """ object_type = attr.ib( type=ExtendedObjectType, validator=type_validator(), converter=ExtendedObjectType, ) """the type of object the identifier points to""" def _parse_swhid(swhid: str) -> Dict[str, Any]: """Parse a Software Heritage identifier (SWHID) from string (see: :ref:`persistent-identifiers`.) This is for internal use; use :meth:`CoreSWHID.from_string`, :meth:`QualifiedSWHID.from_string`, or :meth:`ExtendedSWHID.from_string` instead, as they perform validation and build a dataclass. Args: swhid (str): A persistent identifier Raises: swh.model.exceptions.ValidationError: if passed string is not a valid SWHID """ m = SWHID_RE.fullmatch(swhid) if not m: raise ValidationError( "Invalid SWHID: invalid syntax: %(swhid)s", params={"swhid": swhid} ) parts: Dict[str, Any] = m.groupdict() qualifiers_raw = parts["qualifiers"] parts["qualifiers"] = {} if qualifiers_raw: for qualifier in qualifiers_raw.split(SWHID_CTXT_SEP): try: k, v = qualifier.split("=", maxsplit=1) parts["qualifiers"][k] = v except ValueError: raise ValidationError( "Invalid SWHID: invalid qualifier: %(qualifier)s", params={"qualifier": qualifier}, ) parts["scheme_version"] = int(parts["scheme_version"]) parts["object_id"] = hash_to_bytes(parts["object_id"]) return parts diff --git a/swh/model/model.py b/swh/model/model.py index 1781a36..1d1c1ce 100644 --- a/swh/model/model.py +++ b/swh/model/model.py @@ -1,1133 +1,1148 @@ # Copyright (C) 2018-2020 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 abc import ABCMeta, abstractmethod import datetime from enum import Enum from hashlib import sha256 from typing import Any, Dict, Iterable, Optional, Tuple, TypeVar, Union import attr from attrs_strict import type_validator import dateutil.parser import iso8601 from typing_extensions import Final from .collections import ImmutableDict from .hashutil import DEFAULT_ALGORITHMS, MultiHash, hash_to_bytes from .identifiers import ( directory_identifier, extid_identifier, normalize_timestamp, origin_identifier, raw_extrinsic_metadata_identifier, release_identifier, revision_identifier, snapshot_identifier, ) from .identifiers import CoreSWHID from .identifiers import ExtendedObjectType as SwhidExtendedObjectType from .identifiers import ExtendedSWHID from .identifiers import ObjectType as SwhidObjectType class MissingData(Exception): """Raised by `Content.with_data` when it has no way of fetching the data (but not when fetching the data fails).""" pass KeyType = Union[Dict[str, str], Dict[str, bytes], bytes] """The type returned by BaseModel.unique_key().""" SHA1_SIZE = 20 # TODO: Limit this to 20 bytes Sha1Git = bytes Sha1 = bytes KT = TypeVar("KT") VT = TypeVar("VT") def freeze_optional_dict( d: Union[None, Dict[KT, VT], ImmutableDict[KT, VT]] # type: ignore ) -> Optional[ImmutableDict[KT, VT]]: if isinstance(d, dict): return ImmutableDict(d) else: return d def dictify(value): "Helper function used by BaseModel.to_dict()" if isinstance(value, BaseModel): return value.to_dict() elif isinstance(value, (CoreSWHID, ExtendedSWHID)): return str(value) elif isinstance(value, Enum): return value.value elif isinstance(value, (dict, ImmutableDict)): return {k: dictify(v) for k, v in value.items()} elif isinstance(value, tuple): return tuple(dictify(v) for v in value) else: return value ModelType = TypeVar("ModelType", bound="BaseModel") class BaseModel: """Base class for SWH model classes. Provides serialization/deserialization to/from Python dictionaries, that are suitable for JSON/msgpack-like formats.""" __slots__ = () def to_dict(self): """Wrapper of `attr.asdict` that can be overridden by subclasses that have special handling of some of the fields.""" return dictify(attr.asdict(self, recurse=False)) @classmethod def from_dict(cls, d): """Takes a dictionary representing a tree of SWH objects, and recursively builds the corresponding objects.""" return cls(**d) def anonymize(self: ModelType) -> Optional[ModelType]: """Returns an anonymized version of the object, if needed. If the object model does not need/support anonymization, returns None. """ return None def unique_key(self) -> KeyType: """Returns a unique key for this object, that can be used for deduplication.""" raise NotImplementedError(f"unique_key for {self}") class HashableObject(metaclass=ABCMeta): """Mixin to automatically compute object identifier hash when the associated model is instantiated.""" __slots__ = () @abstractmethod def compute_hash(self) -> bytes: """Derived model classes must implement this to compute the object hash. This method is called by the object initialization if the `id` attribute is set to an empty value. """ pass def __attrs_post_init__(self): if not self.id: obj_id = self.compute_hash() object.__setattr__(self, "id", obj_id) def unique_key(self) -> KeyType: return self.id # type: ignore @attr.s(frozen=True, slots=True) class Person(BaseModel): """Represents the author/committer of a revision or release.""" object_type: Final = "person" fullname = attr.ib(type=bytes, validator=type_validator()) name = attr.ib(type=Optional[bytes], validator=type_validator()) email = attr.ib(type=Optional[bytes], validator=type_validator()) @classmethod def from_fullname(cls, fullname: bytes): """Returns a Person object, by guessing the name and email from the fullname, in the `name ` format. The fullname is left unchanged.""" if fullname is None: raise TypeError("fullname is None.") name: Optional[bytes] email: Optional[bytes] try: open_bracket = fullname.index(b"<") except ValueError: name = fullname email = None else: raw_name = fullname[:open_bracket] raw_email = fullname[open_bracket + 1 :] if not raw_name: name = None else: name = raw_name.strip() try: close_bracket = raw_email.rindex(b">") except ValueError: email = raw_email else: email = raw_email[:close_bracket] return Person(name=name or None, email=email or None, fullname=fullname,) def anonymize(self) -> "Person": """Returns an anonymized version of the Person object. Anonymization is simply a Person which fullname is the hashed, with unset name or email. """ return Person(fullname=sha256(self.fullname).digest(), name=None, email=None,) @attr.s(frozen=True, slots=True) class Timestamp(BaseModel): """Represents a naive timestamp from a VCS.""" object_type: Final = "timestamp" seconds = attr.ib(type=int, validator=type_validator()) microseconds = attr.ib(type=int, validator=type_validator()) @seconds.validator def check_seconds(self, attribute, value): """Check that seconds fit in a 64-bits signed integer.""" if not (-(2 ** 63) <= value < 2 ** 63): raise ValueError("Seconds must be a signed 64-bits integer.") @microseconds.validator def check_microseconds(self, attribute, value): """Checks that microseconds are positive and < 1000000.""" if not (0 <= value < 10 ** 6): raise ValueError("Microseconds must be in [0, 1000000[.") @attr.s(frozen=True, slots=True) class TimestampWithTimezone(BaseModel): """Represents a TZ-aware timestamp from a VCS.""" object_type: Final = "timestamp_with_timezone" timestamp = attr.ib(type=Timestamp, validator=type_validator()) offset = attr.ib(type=int, validator=type_validator()) negative_utc = attr.ib(type=bool, validator=type_validator()) @offset.validator def check_offset(self, attribute, value): """Checks the offset is a 16-bits signed integer (in theory, it should always be between -14 and +14 hours).""" if not (-(2 ** 15) <= value < 2 ** 15): # max 14 hours offset in theory, but you never know what # you'll find in the wild... raise ValueError("offset too large: %d minutes" % value) @negative_utc.validator def check_negative_utc(self, attribute, value): if self.offset and value: raise ValueError("negative_utc can only be True is offset=0") @classmethod def from_dict(cls, obj: Union[Dict, datetime.datetime, int]): """Builds a TimestampWithTimezone from any of the formats accepted by :func:`swh.model.normalize_timestamp`.""" # TODO: this accept way more types than just dicts; find a better # name d = normalize_timestamp(obj) return cls( timestamp=Timestamp.from_dict(d["timestamp"]), offset=d["offset"], negative_utc=d["negative_utc"], ) @classmethod def from_datetime(cls, dt: datetime.datetime): return cls.from_dict(dt) + def to_datetime(self) -> datetime.datetime: + """Convert to a datetime (with a timezone set to the recorded fixed UTC offset) + + Beware that this conversion can be lossy: the negative_utc flag is not + taken into consideration (since it cannot be represented in a + datetime). Also note that it may fail due to type overflow. + + """ + timestamp = datetime.datetime.fromtimestamp( + self.timestamp.seconds, + datetime.timezone(datetime.timedelta(minutes=self.offset)), + ) + timestamp = timestamp.replace(microsecond=self.timestamp.microseconds) + return timestamp + @classmethod def from_iso8601(cls, s): """Builds a TimestampWithTimezone from an ISO8601-formatted string. """ dt = iso8601.parse_date(s) tstz = cls.from_datetime(dt) if dt.tzname() == "-00:00": tstz = attr.evolve(tstz, negative_utc=True) return tstz @attr.s(frozen=True, slots=True) class Origin(BaseModel): """Represents a software source: a VCS and an URL.""" object_type: Final = "origin" url = attr.ib(type=str, validator=type_validator()) def unique_key(self) -> KeyType: return {"url": self.url} def swhid(self) -> ExtendedSWHID: """Returns a SWHID representing this origin.""" return ExtendedSWHID( object_type=SwhidExtendedObjectType.ORIGIN, object_id=hash_to_bytes(origin_identifier(self.unique_key())), ) @attr.s(frozen=True, slots=True) class OriginVisit(BaseModel): """Represents an origin visit with a given type at a given point in time, by a SWH loader.""" object_type: Final = "origin_visit" origin = attr.ib(type=str, validator=type_validator()) date = attr.ib(type=datetime.datetime, validator=type_validator()) type = attr.ib(type=str, validator=type_validator()) """Should not be set before calling 'origin_visit_add()'.""" visit = attr.ib(type=Optional[int], validator=type_validator(), default=None) @date.validator def check_date(self, attribute, value): """Checks the date has a timezone.""" if value is not None and value.tzinfo is None: raise ValueError("date must be a timezone-aware datetime.") def to_dict(self): """Serializes the date as a string and omits the visit id if it is `None`.""" ov = super().to_dict() if ov["visit"] is None: del ov["visit"] return ov def unique_key(self) -> KeyType: return {"origin": self.origin, "date": str(self.date)} @attr.s(frozen=True, slots=True) class OriginVisitStatus(BaseModel): """Represents a visit update of an origin at a given point in time. """ object_type: Final = "origin_visit_status" origin = attr.ib(type=str, validator=type_validator()) visit = attr.ib(type=int, validator=type_validator()) date = attr.ib(type=datetime.datetime, validator=type_validator()) status = attr.ib( type=str, validator=attr.validators.in_( ["created", "ongoing", "full", "partial", "not_found", "failed"] ), ) snapshot = attr.ib(type=Optional[Sha1Git], validator=type_validator()) # Type is optional be to able to use it before adding it to the database model type = attr.ib(type=Optional[str], validator=type_validator(), default=None) metadata = attr.ib( type=Optional[ImmutableDict[str, object]], validator=type_validator(), converter=freeze_optional_dict, default=None, ) @date.validator def check_date(self, attribute, value): """Checks the date has a timezone.""" if value is not None and value.tzinfo is None: raise ValueError("date must be a timezone-aware datetime.") def unique_key(self) -> KeyType: return {"origin": self.origin, "visit": str(self.visit), "date": str(self.date)} class TargetType(Enum): """The type of content pointed to by a snapshot branch. Usually a revision or an alias.""" CONTENT = "content" DIRECTORY = "directory" REVISION = "revision" RELEASE = "release" SNAPSHOT = "snapshot" ALIAS = "alias" class ObjectType(Enum): """The type of content pointed to by a release. Usually a revision""" CONTENT = "content" DIRECTORY = "directory" REVISION = "revision" RELEASE = "release" SNAPSHOT = "snapshot" @attr.s(frozen=True, slots=True) class SnapshotBranch(BaseModel): """Represents one of the branches of a snapshot.""" object_type: Final = "snapshot_branch" target = attr.ib(type=bytes, validator=type_validator()) target_type = attr.ib(type=TargetType, validator=type_validator()) @target.validator def check_target(self, attribute, value): """Checks the target type is not an alias, checks the target is a valid sha1_git.""" if self.target_type != TargetType.ALIAS and self.target is not None: if len(value) != 20: raise ValueError("Wrong length for bytes identifier: %d" % len(value)) @classmethod def from_dict(cls, d): return cls(target=d["target"], target_type=TargetType(d["target_type"])) @attr.s(frozen=True, slots=True) class Snapshot(HashableObject, BaseModel): """Represents the full state of an origin at a given point in time.""" object_type: Final = "snapshot" branches = attr.ib( type=ImmutableDict[bytes, Optional[SnapshotBranch]], validator=type_validator(), converter=freeze_optional_dict, ) id = attr.ib(type=Sha1Git, validator=type_validator(), default=b"") def compute_hash(self) -> bytes: return hash_to_bytes(snapshot_identifier(self.to_dict())) @classmethod def from_dict(cls, d): d = d.copy() return cls( branches=ImmutableDict( (name, SnapshotBranch.from_dict(branch) if branch else None) for (name, branch) in d.pop("branches").items() ), **d, ) def swhid(self) -> CoreSWHID: """Returns a SWHID representing this object.""" return CoreSWHID(object_type=SwhidObjectType.SNAPSHOT, object_id=self.id) @attr.s(frozen=True, slots=True) class Release(HashableObject, BaseModel): object_type: Final = "release" name = attr.ib(type=bytes, validator=type_validator()) message = attr.ib(type=Optional[bytes], validator=type_validator()) target = attr.ib(type=Optional[Sha1Git], validator=type_validator()) target_type = attr.ib(type=ObjectType, validator=type_validator()) synthetic = attr.ib(type=bool, validator=type_validator()) author = attr.ib(type=Optional[Person], validator=type_validator(), default=None) date = attr.ib( type=Optional[TimestampWithTimezone], validator=type_validator(), default=None ) metadata = attr.ib( type=Optional[ImmutableDict[str, object]], validator=type_validator(), converter=freeze_optional_dict, default=None, ) id = attr.ib(type=Sha1Git, validator=type_validator(), default=b"") def compute_hash(self) -> bytes: return hash_to_bytes(release_identifier(self.to_dict())) @author.validator def check_author(self, attribute, value): """If the author is `None`, checks the date is `None` too.""" if self.author is None and self.date is not None: raise ValueError("release date must be None if author is None.") def to_dict(self): rel = super().to_dict() if rel["metadata"] is None: del rel["metadata"] return rel @classmethod def from_dict(cls, d): d = d.copy() if d.get("author"): d["author"] = Person.from_dict(d["author"]) if d.get("date"): d["date"] = TimestampWithTimezone.from_dict(d["date"]) return cls(target_type=ObjectType(d.pop("target_type")), **d) def swhid(self) -> CoreSWHID: """Returns a SWHID representing this object.""" return CoreSWHID(object_type=SwhidObjectType.RELEASE, object_id=self.id) def anonymize(self) -> "Release": """Returns an anonymized version of the Release object. Anonymization consists in replacing the author with an anonymized Person object. """ author = self.author and self.author.anonymize() return attr.evolve(self, author=author) class RevisionType(Enum): GIT = "git" TAR = "tar" DSC = "dsc" SUBVERSION = "svn" MERCURIAL = "hg" def tuplify_extra_headers(value: Iterable): return tuple((k, v) for k, v in value) @attr.s(frozen=True, slots=True) class Revision(HashableObject, BaseModel): object_type: Final = "revision" message = attr.ib(type=Optional[bytes], validator=type_validator()) author = attr.ib(type=Person, validator=type_validator()) committer = attr.ib(type=Person, validator=type_validator()) date = attr.ib(type=Optional[TimestampWithTimezone], validator=type_validator()) committer_date = attr.ib( type=Optional[TimestampWithTimezone], validator=type_validator() ) type = attr.ib(type=RevisionType, validator=type_validator()) directory = attr.ib(type=Sha1Git, validator=type_validator()) synthetic = attr.ib(type=bool, validator=type_validator()) metadata = attr.ib( type=Optional[ImmutableDict[str, object]], validator=type_validator(), converter=freeze_optional_dict, default=None, ) parents = attr.ib(type=Tuple[Sha1Git, ...], validator=type_validator(), default=()) id = attr.ib(type=Sha1Git, validator=type_validator(), default=b"") extra_headers = attr.ib( type=Tuple[Tuple[bytes, bytes], ...], validator=type_validator(), converter=tuplify_extra_headers, default=(), ) def __attrs_post_init__(self): super().__attrs_post_init__() # ensure metadata is a deep copy of whatever was given, and if needed # extract extra_headers from there if self.metadata: metadata = self.metadata if not self.extra_headers and "extra_headers" in metadata: (extra_headers, metadata) = metadata.copy_pop("extra_headers") object.__setattr__( self, "extra_headers", tuplify_extra_headers(extra_headers), ) attr.validate(self) object.__setattr__(self, "metadata", metadata) def compute_hash(self) -> bytes: return hash_to_bytes(revision_identifier(self.to_dict())) @classmethod def from_dict(cls, d): d = d.copy() date = d.pop("date") if date: date = TimestampWithTimezone.from_dict(date) committer_date = d.pop("committer_date") if committer_date: committer_date = TimestampWithTimezone.from_dict(committer_date) return cls( author=Person.from_dict(d.pop("author")), committer=Person.from_dict(d.pop("committer")), date=date, committer_date=committer_date, type=RevisionType(d.pop("type")), parents=tuple(d.pop("parents")), # for BW compat **d, ) def swhid(self) -> CoreSWHID: """Returns a SWHID representing this object.""" return CoreSWHID(object_type=SwhidObjectType.REVISION, object_id=self.id) def anonymize(self) -> "Revision": """Returns an anonymized version of the Revision object. Anonymization consists in replacing the author and committer with an anonymized Person object. """ return attr.evolve( self, author=self.author.anonymize(), committer=self.committer.anonymize() ) @attr.s(frozen=True, slots=True) class DirectoryEntry(BaseModel): object_type: Final = "directory_entry" name = attr.ib(type=bytes, validator=type_validator()) type = attr.ib(type=str, validator=attr.validators.in_(["file", "dir", "rev"])) target = attr.ib(type=Sha1Git, validator=type_validator()) perms = attr.ib(type=int, validator=type_validator()) """Usually one of the values of `swh.model.from_disk.DentryPerms`.""" @attr.s(frozen=True, slots=True) class Directory(HashableObject, BaseModel): object_type: Final = "directory" entries = attr.ib(type=Tuple[DirectoryEntry, ...], validator=type_validator()) id = attr.ib(type=Sha1Git, validator=type_validator(), default=b"") def compute_hash(self) -> bytes: return hash_to_bytes(directory_identifier(self.to_dict())) @classmethod def from_dict(cls, d): d = d.copy() return cls( entries=tuple( DirectoryEntry.from_dict(entry) for entry in d.pop("entries") ), **d, ) def swhid(self) -> CoreSWHID: """Returns a SWHID representing this object.""" return CoreSWHID(object_type=SwhidObjectType.DIRECTORY, object_id=self.id) @attr.s(frozen=True, slots=True) class BaseContent(BaseModel): status = attr.ib( type=str, validator=attr.validators.in_(["visible", "hidden", "absent"]) ) @staticmethod def _hash_data(data: bytes): """Hash some data, returning most of the fields of a content object""" d = MultiHash.from_data(data).digest() d["data"] = data d["length"] = len(data) return d @classmethod def from_dict(cls, d, use_subclass=True): if use_subclass: # Chooses a subclass to instantiate instead. if d["status"] == "absent": return SkippedContent.from_dict(d) else: return Content.from_dict(d) else: return super().from_dict(d) def get_hash(self, hash_name): if hash_name not in DEFAULT_ALGORITHMS: raise ValueError("{} is not a valid hash name.".format(hash_name)) return getattr(self, hash_name) def hashes(self) -> Dict[str, bytes]: """Returns a dictionary {hash_name: hash_value}""" return {algo: getattr(self, algo) for algo in DEFAULT_ALGORITHMS} @attr.s(frozen=True, slots=True) class Content(BaseContent): object_type: Final = "content" sha1 = attr.ib(type=bytes, validator=type_validator()) sha1_git = attr.ib(type=Sha1Git, validator=type_validator()) sha256 = attr.ib(type=bytes, validator=type_validator()) blake2s256 = attr.ib(type=bytes, validator=type_validator()) length = attr.ib(type=int, validator=type_validator()) status = attr.ib( type=str, validator=attr.validators.in_(["visible", "hidden"]), default="visible", ) data = attr.ib(type=Optional[bytes], validator=type_validator(), default=None) ctime = attr.ib( type=Optional[datetime.datetime], validator=type_validator(), default=None, eq=False, ) @length.validator def check_length(self, attribute, value): """Checks the length is positive.""" if value < 0: raise ValueError("Length must be positive.") @ctime.validator def check_ctime(self, attribute, value): """Checks the ctime has a timezone.""" if value is not None and value.tzinfo is None: raise ValueError("ctime must be a timezone-aware datetime.") def to_dict(self): content = super().to_dict() if content["data"] is None: del content["data"] if content["ctime"] is None: del content["ctime"] return content @classmethod def from_data(cls, data, status="visible", ctime=None) -> "Content": """Generate a Content from a given `data` byte string. This populates the Content with the hashes and length for the data passed as argument, as well as the data itself. """ d = cls._hash_data(data) d["status"] = status d["ctime"] = ctime return cls(**d) @classmethod def from_dict(cls, d): if isinstance(d.get("ctime"), str): d = d.copy() d["ctime"] = dateutil.parser.parse(d["ctime"]) return super().from_dict(d, use_subclass=False) def with_data(self) -> "Content": """Loads the `data` attribute; meaning that it is guaranteed not to be None after this call. This call is almost a no-op, but subclasses may overload this method to lazy-load data (eg. from disk or objstorage).""" if self.data is None: raise MissingData("Content data is None.") return self def unique_key(self) -> KeyType: return self.sha1 # TODO: use a dict of hashes def swhid(self) -> CoreSWHID: """Returns a SWHID representing this object.""" return CoreSWHID(object_type=SwhidObjectType.CONTENT, object_id=self.sha1_git) @attr.s(frozen=True, slots=True) class SkippedContent(BaseContent): object_type: Final = "skipped_content" sha1 = attr.ib(type=Optional[bytes], validator=type_validator()) sha1_git = attr.ib(type=Optional[Sha1Git], validator=type_validator()) sha256 = attr.ib(type=Optional[bytes], validator=type_validator()) blake2s256 = attr.ib(type=Optional[bytes], validator=type_validator()) length = attr.ib(type=Optional[int], validator=type_validator()) status = attr.ib(type=str, validator=attr.validators.in_(["absent"])) reason = attr.ib(type=Optional[str], validator=type_validator(), default=None) origin = attr.ib(type=Optional[str], validator=type_validator(), default=None) ctime = attr.ib( type=Optional[datetime.datetime], validator=type_validator(), default=None, eq=False, ) @reason.validator def check_reason(self, attribute, value): """Checks the reason is full if status != absent.""" assert self.reason == value if value is None: raise ValueError("Must provide a reason if content is absent.") @length.validator def check_length(self, attribute, value): """Checks the length is positive or -1.""" if value < -1: raise ValueError("Length must be positive or -1.") @ctime.validator def check_ctime(self, attribute, value): """Checks the ctime has a timezone.""" if value is not None and value.tzinfo is None: raise ValueError("ctime must be a timezone-aware datetime.") def to_dict(self): content = super().to_dict() if content["origin"] is None: del content["origin"] if content["ctime"] is None: del content["ctime"] return content @classmethod def from_data( cls, data: bytes, reason: str, ctime: Optional[datetime.datetime] = None ) -> "SkippedContent": """Generate a SkippedContent from a given `data` byte string. This populates the SkippedContent with the hashes and length for the data passed as argument. You can use `attr.evolve` on such a generated content to nullify some of its attributes, e.g. for tests. """ d = cls._hash_data(data) del d["data"] d["status"] = "absent" d["reason"] = reason d["ctime"] = ctime return cls(**d) @classmethod def from_dict(cls, d): d2 = d.copy() if d2.pop("data", None) is not None: raise ValueError('SkippedContent has no "data" attribute %r' % d) return super().from_dict(d2, use_subclass=False) def unique_key(self) -> KeyType: return self.hashes() class MetadataAuthorityType(Enum): DEPOSIT_CLIENT = "deposit_client" FORGE = "forge" REGISTRY = "registry" @attr.s(frozen=True, slots=True) class MetadataAuthority(BaseModel): """Represents an entity that provides metadata about an origin or software artifact.""" object_type: Final = "metadata_authority" type = attr.ib(type=MetadataAuthorityType, validator=type_validator()) url = attr.ib(type=str, validator=type_validator()) metadata = attr.ib( type=Optional[ImmutableDict[str, Any]], default=None, validator=type_validator(), converter=freeze_optional_dict, ) def to_dict(self): d = super().to_dict() if d["metadata"] is None: del d["metadata"] return d @classmethod def from_dict(cls, d): d = { **d, "type": MetadataAuthorityType(d["type"]), } return super().from_dict(d) def unique_key(self) -> KeyType: return {"type": self.type.value, "url": self.url} @attr.s(frozen=True, slots=True) class MetadataFetcher(BaseModel): """Represents a software component used to fetch metadata from a metadata authority, and ingest them into the Software Heritage archive.""" object_type: Final = "metadata_fetcher" name = attr.ib(type=str, validator=type_validator()) version = attr.ib(type=str, validator=type_validator()) metadata = attr.ib( type=Optional[ImmutableDict[str, Any]], default=None, validator=type_validator(), converter=freeze_optional_dict, ) def to_dict(self): d = super().to_dict() if d["metadata"] is None: del d["metadata"] return d def unique_key(self) -> KeyType: return {"name": self.name, "version": self.version} def normalize_discovery_date(value: Any) -> datetime.datetime: if not isinstance(value, datetime.datetime): raise TypeError("discovery_date must be a timezone-aware datetime.") if value.tzinfo is None: raise ValueError("discovery_date must be a timezone-aware datetime.") # Normalize timezone to utc, and truncate microseconds to 0 return value.astimezone(datetime.timezone.utc).replace(microsecond=0) @attr.s(frozen=True, slots=True) class RawExtrinsicMetadata(HashableObject, BaseModel): object_type: Final = "raw_extrinsic_metadata" # target object target = attr.ib(type=ExtendedSWHID, validator=type_validator()) # source discovery_date = attr.ib(type=datetime.datetime, converter=normalize_discovery_date) authority = attr.ib(type=MetadataAuthority, validator=type_validator()) fetcher = attr.ib(type=MetadataFetcher, validator=type_validator()) # the metadata itself format = attr.ib(type=str, validator=type_validator()) metadata = attr.ib(type=bytes, validator=type_validator()) # context origin = attr.ib(type=Optional[str], default=None, validator=type_validator()) visit = attr.ib(type=Optional[int], default=None, validator=type_validator()) snapshot = attr.ib( type=Optional[CoreSWHID], default=None, validator=type_validator() ) release = attr.ib( type=Optional[CoreSWHID], default=None, validator=type_validator() ) revision = attr.ib( type=Optional[CoreSWHID], default=None, validator=type_validator() ) path = attr.ib(type=Optional[bytes], default=None, validator=type_validator()) directory = attr.ib( type=Optional[CoreSWHID], default=None, validator=type_validator() ) id = attr.ib(type=Sha1Git, validator=type_validator(), default=b"") def compute_hash(self) -> bytes: return hash_to_bytes(raw_extrinsic_metadata_identifier(self.to_dict())) @origin.validator def check_origin(self, attribute, value): if value is None: return if self.target.object_type not in ( SwhidExtendedObjectType.SNAPSHOT, SwhidExtendedObjectType.RELEASE, SwhidExtendedObjectType.REVISION, SwhidExtendedObjectType.DIRECTORY, SwhidExtendedObjectType.CONTENT, ): raise ValueError( f"Unexpected 'origin' context for " f"{self.target.object_type.name.lower()} object: {value}" ) if value.startswith("swh:"): # Technically this is valid; but: # 1. SWHIDs are URIs, not URLs # 2. if a SWHID gets here, it's very likely to be a mistake # (and we can remove this check if it turns out there is a # legitimate use for it). raise ValueError(f"SWHID used as context origin URL: {value}") @visit.validator def check_visit(self, attribute, value): if value is None: return if self.target.object_type not in ( SwhidExtendedObjectType.SNAPSHOT, SwhidExtendedObjectType.RELEASE, SwhidExtendedObjectType.REVISION, SwhidExtendedObjectType.DIRECTORY, SwhidExtendedObjectType.CONTENT, ): raise ValueError( f"Unexpected 'visit' context for " f"{self.target.object_type.name.lower()} object: {value}" ) if self.origin is None: raise ValueError("'origin' context must be set if 'visit' is.") if value <= 0: raise ValueError("Nonpositive visit id") @snapshot.validator def check_snapshot(self, attribute, value): if value is None: return if self.target.object_type not in ( SwhidExtendedObjectType.RELEASE, SwhidExtendedObjectType.REVISION, SwhidExtendedObjectType.DIRECTORY, SwhidExtendedObjectType.CONTENT, ): raise ValueError( f"Unexpected 'snapshot' context for " f"{self.target.object_type.name.lower()} object: {value}" ) self._check_swhid(SwhidObjectType.SNAPSHOT, value) @release.validator def check_release(self, attribute, value): if value is None: return if self.target.object_type not in ( SwhidExtendedObjectType.REVISION, SwhidExtendedObjectType.DIRECTORY, SwhidExtendedObjectType.CONTENT, ): raise ValueError( f"Unexpected 'release' context for " f"{self.target.object_type.name.lower()} object: {value}" ) self._check_swhid(SwhidObjectType.RELEASE, value) @revision.validator def check_revision(self, attribute, value): if value is None: return if self.target.object_type not in ( SwhidExtendedObjectType.DIRECTORY, SwhidExtendedObjectType.CONTENT, ): raise ValueError( f"Unexpected 'revision' context for " f"{self.target.object_type.name.lower()} object: {value}" ) self._check_swhid(SwhidObjectType.REVISION, value) @path.validator def check_path(self, attribute, value): if value is None: return if self.target.object_type not in ( SwhidExtendedObjectType.DIRECTORY, SwhidExtendedObjectType.CONTENT, ): raise ValueError( f"Unexpected 'path' context for " f"{self.target.object_type.name.lower()} object: {value}" ) @directory.validator def check_directory(self, attribute, value): if value is None: return if self.target.object_type not in (SwhidExtendedObjectType.CONTENT,): raise ValueError( f"Unexpected 'directory' context for " f"{self.target.object_type.name.lower()} object: {value}" ) self._check_swhid(SwhidObjectType.DIRECTORY, value) def _check_swhid(self, expected_object_type, swhid): if isinstance(swhid, str): raise ValueError(f"Expected SWHID, got a string: {swhid}") if swhid.object_type != expected_object_type: raise ValueError( f"Expected SWHID type '{expected_object_type.name.lower()}', " f"got '{swhid.object_type.name.lower()}' in {swhid}" ) def to_dict(self): d = super().to_dict() context_keys = ( "origin", "visit", "snapshot", "release", "revision", "directory", "path", ) for context_key in context_keys: if d[context_key] is None: del d[context_key] return d @classmethod def from_dict(cls, d): d = { **d, "target": ExtendedSWHID.from_string(d["target"]), "authority": MetadataAuthority.from_dict(d["authority"]), "fetcher": MetadataFetcher.from_dict(d["fetcher"]), } swhid_keys = ("snapshot", "release", "revision", "directory") for swhid_key in swhid_keys: if d.get(swhid_key): d[swhid_key] = CoreSWHID.from_string(d[swhid_key]) return super().from_dict(d) def swhid(self) -> ExtendedSWHID: """Returns a SWHID representing this RawExtrinsicMetadata object.""" return ExtendedSWHID( object_type=SwhidExtendedObjectType.RAW_EXTRINSIC_METADATA, object_id=self.id, ) @attr.s(frozen=True, slots=True) class ExtID(HashableObject, BaseModel): object_type: Final = "extid" extid_type = attr.ib(type=str, validator=type_validator()) extid = attr.ib(type=bytes, validator=type_validator()) target = attr.ib(type=CoreSWHID, validator=type_validator()) id = attr.ib(type=Sha1Git, validator=type_validator(), default=b"") @classmethod def from_dict(cls, d): return cls( extid=d["extid"], extid_type=d["extid_type"], target=CoreSWHID.from_string(d["target"]), ) def compute_hash(self) -> bytes: return hash_to_bytes(extid_identifier(self.to_dict())) diff --git a/swh/model/tests/swh_model_data.py b/swh/model/tests/swh_model_data.py index 732cff5..8db2a28 100644 --- a/swh/model/tests/swh_model_data.py +++ b/swh/model/tests/swh_model_data.py @@ -1,363 +1,379 @@ # Copyright (C) 2019-2021 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 datetime from typing import Dict, Sequence import attr from swh.model.hashutil import MultiHash, hash_to_bytes from swh.model.identifiers import ExtendedSWHID from swh.model.model import ( BaseModel, Content, Directory, DirectoryEntry, ExtID, MetadataAuthority, MetadataAuthorityType, MetadataFetcher, ObjectType, Origin, OriginVisit, OriginVisitStatus, Person, RawExtrinsicMetadata, Release, Revision, RevisionType, SkippedContent, Snapshot, SnapshotBranch, TargetType, Timestamp, TimestampWithTimezone, ) UTC = datetime.timezone.utc CONTENTS = [ Content( length=4, data=f"foo{i}".encode(), status="visible", **MultiHash.from_data(f"foo{i}".encode()).digest(), ) for i in range(10) ] + [ Content( length=14, data=f"forbidden foo{i}".encode(), status="hidden", **MultiHash.from_data(f"forbidden foo{i}".encode()).digest(), ) for i in range(10) ] SKIPPED_CONTENTS = [ SkippedContent( length=4, status="absent", reason=f"because chr({i}) != '*'", **MultiHash.from_data(f"bar{i}".encode()).digest(), ) for i in range(2) ] duplicate_content1 = Content( length=4, sha1=hash_to_bytes("44973274ccef6ab4dfaaf86599792fa9c3fe4689"), sha1_git=b"another-foo", blake2s256=b"another-bar", sha256=b"another-baz", status="visible", ) # Craft a sha1 collision sha1_array = bytearray(duplicate_content1.sha1_git) sha1_array[0] += 1 duplicate_content2 = attr.evolve(duplicate_content1, sha1_git=bytes(sha1_array)) DUPLICATE_CONTENTS = [duplicate_content1, duplicate_content2] COMMITTERS = [ Person(fullname=b"foo", name=b"foo", email=b""), Person(fullname=b"bar", name=b"bar", email=b""), ] DATES = [ TimestampWithTimezone( timestamp=Timestamp(seconds=1234567891, microseconds=0,), offset=120, negative_utc=False, ), TimestampWithTimezone( timestamp=Timestamp(seconds=1234567892, microseconds=0,), offset=120, negative_utc=False, ), ] REVISIONS = [ Revision( id=hash_to_bytes("66c7c1cd9673275037140f2abff7b7b11fc9439c"), message=b"hello", date=DATES[0], committer=COMMITTERS[0], author=COMMITTERS[0], committer_date=DATES[0], type=RevisionType.GIT, directory=b"\x01" * 20, synthetic=False, metadata=None, parents=( hash_to_bytes("9b918dd063cec85c2bc63cc7f167e29f5894dcbc"), hash_to_bytes("757f38bdcd8473aaa12df55357f5e2f1a318e672"), ), ), Revision( id=hash_to_bytes("c7f96242d73c267adc77c2908e64e0c1cb6a4431"), message=b"hello again", date=DATES[1], committer=COMMITTERS[1], author=COMMITTERS[1], committer_date=DATES[1], type=RevisionType.MERCURIAL, directory=b"\x02" * 20, synthetic=False, metadata=None, parents=(), extra_headers=((b"foo", b"bar"),), ), ] EXTIDS = [ ExtID(extid_type="git256", extid=b"\x03" * 32, target=REVISIONS[0].swhid(),), ExtID(extid_type="hg", extid=b"\x04" * 20, target=REVISIONS[1].swhid(),), ] RELEASES = [ Release( id=hash_to_bytes("8059dc4e17fcd0e51ca3bcd6b80f4577d281fd08"), name=b"v0.0.1", date=TimestampWithTimezone( timestamp=Timestamp(seconds=1234567890, microseconds=0,), offset=120, negative_utc=False, ), author=COMMITTERS[0], target_type=ObjectType.REVISION, target=b"\x04" * 20, message=b"foo", synthetic=False, ), Release( id=hash_to_bytes("ee4d20e80af850cc0f417d25dc5073792c5010d2"), name=b"this-is-a/tag/1.0", date=None, author=None, target_type=ObjectType.DIRECTORY, target=b"\x05" * 20, message=b"bar", synthetic=False, ), ] ORIGINS = [ Origin(url="https://somewhere.org/den/fox",), Origin(url="https://overtherainbow.org/fox/den",), ] ORIGIN_VISITS = [ OriginVisit( origin=ORIGINS[0].url, date=datetime.datetime(2013, 5, 7, 4, 20, 39, 369271, tzinfo=UTC), visit=1, type="git", ), OriginVisit( origin=ORIGINS[1].url, date=datetime.datetime(2014, 11, 27, 17, 20, 39, tzinfo=UTC), visit=1, type="hg", ), OriginVisit( origin=ORIGINS[0].url, date=datetime.datetime(2018, 11, 27, 17, 20, 39, tzinfo=UTC), visit=2, type="git", ), OriginVisit( origin=ORIGINS[0].url, date=datetime.datetime(2018, 11, 27, 17, 20, 39, tzinfo=UTC), visit=3, type="git", ), OriginVisit( origin=ORIGINS[1].url, date=datetime.datetime(2015, 11, 27, 17, 20, 39, tzinfo=UTC), visit=2, type="hg", ), ] # The origin-visit-status dates needs to be shifted slightly in the future from their # visit dates counterpart. Otherwise, we are hitting storage-wise the "on conflict" # ignore policy (because origin-visit-add creates an origin-visit-status with the same # parameters from the origin-visit {origin, visit, date}... ORIGIN_VISIT_STATUSES = [ OriginVisitStatus( origin=ORIGINS[0].url, date=datetime.datetime(2013, 5, 7, 4, 20, 39, 432222, tzinfo=UTC), visit=1, type="git", status="ongoing", snapshot=None, metadata=None, ), OriginVisitStatus( origin=ORIGINS[1].url, date=datetime.datetime(2014, 11, 27, 17, 21, 12, tzinfo=UTC), visit=1, type="hg", status="ongoing", snapshot=None, metadata=None, ), OriginVisitStatus( origin=ORIGINS[0].url, date=datetime.datetime(2018, 11, 27, 17, 20, 59, tzinfo=UTC), visit=2, type="git", status="ongoing", snapshot=None, metadata=None, ), OriginVisitStatus( origin=ORIGINS[0].url, date=datetime.datetime(2018, 11, 27, 17, 20, 49, tzinfo=UTC), visit=3, type="git", status="full", snapshot=hash_to_bytes("9e78d7105c5e0f886487511e2a92377b4ee4c32a"), metadata=None, ), OriginVisitStatus( origin=ORIGINS[1].url, date=datetime.datetime(2015, 11, 27, 17, 22, 18, tzinfo=UTC), visit=2, type="hg", status="partial", snapshot=hash_to_bytes("0e7f84ede9a254f2cd55649ad5240783f557e65f"), metadata=None, ), ] DIRECTORIES = [ Directory(id=hash_to_bytes("4b825dc642cb6eb9a060e54bf8d69288fbee4904"), entries=()), Directory( id=hash_to_bytes("87b339104f7dc2a8163dec988445e3987995545f"), entries=( DirectoryEntry( name=b"file1.ext", perms=0o644, type="file", target=CONTENTS[0].sha1_git, ), DirectoryEntry( name=b"dir1", perms=0o755, type="dir", target=hash_to_bytes("4b825dc642cb6eb9a060e54bf8d69288fbee4904"), ), DirectoryEntry( name=b"subprepo1", perms=0o160000, type="rev", target=REVISIONS[1].id, ), ), ), ] SNAPSHOTS = [ Snapshot( id=hash_to_bytes("9e78d7105c5e0f886487511e2a92377b4ee4c32a"), branches={ b"master": SnapshotBranch( target_type=TargetType.REVISION, target=REVISIONS[0].id ) }, ), Snapshot( id=hash_to_bytes("0e7f84ede9a254f2cd55649ad5240783f557e65f"), branches={ b"target/revision": SnapshotBranch( target_type=TargetType.REVISION, target=REVISIONS[0].id, ), b"target/alias": SnapshotBranch( target_type=TargetType.ALIAS, target=b"target/revision" ), b"target/directory": SnapshotBranch( target_type=TargetType.DIRECTORY, target=DIRECTORIES[0].id, ), b"target/release": SnapshotBranch( target_type=TargetType.RELEASE, target=RELEASES[0].id ), b"target/snapshot": SnapshotBranch( target_type=TargetType.SNAPSHOT, target=hash_to_bytes("9e78d7105c5e0f886487511e2a92377b4ee4c32a"), ), }, ), ] METADATA_AUTHORITIES = [ MetadataAuthority( type=MetadataAuthorityType.FORGE, url="http://example.org/", metadata={}, ), ] METADATA_FETCHERS = [ MetadataFetcher(name="test-fetcher", version="1.0.0", metadata={},) ] RAW_EXTRINSIC_METADATA = [ RawExtrinsicMetadata( target=Origin("http://example.org/foo.git").swhid(), discovery_date=datetime.datetime(2020, 7, 30, 17, 8, 20, tzinfo=UTC), authority=attr.evolve(METADATA_AUTHORITIES[0], metadata=None), fetcher=attr.evolve(METADATA_FETCHERS[0], metadata=None), format="json", metadata=b'{"foo": "bar"}', ), RawExtrinsicMetadata( target=ExtendedSWHID.from_string(str(CONTENTS[0].swhid())), discovery_date=datetime.datetime(2020, 7, 30, 17, 8, 20, tzinfo=UTC), authority=attr.evolve(METADATA_AUTHORITIES[0], metadata=None), fetcher=attr.evolve(METADATA_FETCHERS[0], metadata=None), format="json", metadata=b'{"foo": "bar"}', ), ] TEST_OBJECTS: Dict[str, Sequence[BaseModel]] = { "content": CONTENTS, "directory": DIRECTORIES, "extid": EXTIDS, "metadata_authority": METADATA_AUTHORITIES, "metadata_fetcher": METADATA_FETCHERS, "origin": ORIGINS, "origin_visit": ORIGIN_VISITS, "origin_visit_status": ORIGIN_VISIT_STATUSES, "raw_extrinsic_metadata": RAW_EXTRINSIC_METADATA, "release": RELEASES, "revision": REVISIONS, "snapshot": SNAPSHOTS, "skipped_content": SKIPPED_CONTENTS, } + +SAMPLE_FOLDER_SWHIDS = [ + "swh:1:dir:e8b0f1466af8608c8a3fb9879db172b887e80759", + "swh:1:cnt:7d5c08111e21c8a9f71540939998551683375fad", + "swh:1:cnt:68769579c3eaadbe555379b9c3538e6628bae1eb", + "swh:1:cnt:e86b45e538d9b6888c969c89fbd22a85aa0e0366", + "swh:1:dir:3c1f578394f4623f74a0ba7fe761729f59fc6ec4", + "swh:1:dir:c3020f6bf135a38c6df3afeb5fb38232c5e07087", + "swh:1:cnt:133693b125bad2b4ac318535b84901ebb1f6b638", + "swh:1:dir:4b825dc642cb6eb9a060e54bf8d69288fbee4904", + "swh:1:cnt:19102815663d23f8b75a47e7a01965dcdc96468c", + "swh:1:dir:2b41c40f0d1fbffcba12497db71fba83fcca96e5", + "swh:1:cnt:8185dfb2c0c2c597d16f75a8a0c37668567c3d7e", + "swh:1:cnt:7c4c57ba9ff496ad179b8f65b1d286edbda34c9a", + "swh:1:cnt:acac326ddd63b0bc70840659d4ac43619484e69f", +] diff --git a/swh/model/tests/test_cli.py b/swh/model/tests/test_cli.py index de0de48..eeb5a63 100644 --- a/swh/model/tests/test_cli.py +++ b/swh/model/tests/test_cli.py @@ -1,179 +1,211 @@ # Copyright (C) 2018-2019 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 os import sys import tarfile import tempfile import unittest import unittest.mock from click.testing import CliRunner import pytest from swh.model import cli from swh.model.hashutil import hash_to_hex +from swh.model.tests.swh_model_data import SAMPLE_FOLDER_SWHIDS from swh.model.tests.test_from_disk import DataMixin @pytest.mark.fs class TestIdentify(DataMixin, unittest.TestCase): def setUp(self): super().setUp() self.runner = CliRunner() def assertSWHID(self, result, swhid): self.assertEqual(result.exit_code, 0, result.output) self.assertEqual(result.output.split()[0], swhid) def test_no_args(self): result = self.runner.invoke(cli.identify) self.assertNotEqual(result.exit_code, 0) def test_content_id(self): """identify file content""" self.make_contents(self.tmpdir_name) for filename, content in self.contents.items(): path = os.path.join(self.tmpdir_name, filename) result = self.runner.invoke(cli.identify, ["--type", "content", path]) self.assertSWHID(result, "swh:1:cnt:" + hash_to_hex(content["sha1_git"])) def test_content_id_from_stdin(self): """identify file content""" self.make_contents(self.tmpdir_name) for _, content in self.contents.items(): result = self.runner.invoke(cli.identify, ["-"], input=content["data"]) self.assertSWHID(result, "swh:1:cnt:" + hash_to_hex(content["sha1_git"])) def test_directory_id(self): """identify an entire directory""" self.make_from_tarball(self.tmpdir_name) path = os.path.join(self.tmpdir_name, b"sample-folder") result = self.runner.invoke(cli.identify, ["--type", "directory", path]) self.assertSWHID(result, "swh:1:dir:e8b0f1466af8608c8a3fb9879db172b887e80759") @pytest.mark.requires_optional_deps def test_snapshot_id(self): """identify a snapshot""" tarball = os.path.join( os.path.dirname(__file__), "data", "repos", "sample-repo.tgz" ) with tempfile.TemporaryDirectory(prefix="swh.model.cli") as d: with tarfile.open(tarball, "r:gz") as t: t.extractall(d) repo_dir = os.path.join(d, "sample-repo") result = self.runner.invoke( cli.identify, ["--type", "snapshot", repo_dir] ) self.assertSWHID( result, "swh:1:snp:abc888898124270905a0ef3c67e872ce08e7e0c1" ) def test_snapshot_without_dulwich(self): """checks swh-identify returns a 'nice' message instead of a traceback when dulwich is not installed""" with unittest.mock.patch.dict(sys.modules, {"dulwich": None}): with tempfile.TemporaryDirectory(prefix="swh.model.cli") as d: result = self.runner.invoke( cli.identify, ["--type", "snapshot", d], catch_exceptions=False, ) assert result.exit_code == 1 assert "'swh.model[cli]'" in result.output def test_origin_id(self): """identify an origin URL""" url = "https://github.com/torvalds/linux" result = self.runner.invoke(cli.identify, ["--type", "origin", url]) self.assertSWHID(result, "swh:1:ori:b63a575fe3faab7692c9f38fb09d4bb45651bb0f") def test_symlink(self): """identify symlink --- both itself and target""" regular = os.path.join(self.tmpdir_name, b"foo.txt") link = os.path.join(self.tmpdir_name, b"bar.txt") open(regular, "w").write("foo\n") os.symlink(os.path.basename(regular), link) result = self.runner.invoke(cli.identify, [link]) self.assertSWHID(result, "swh:1:cnt:257cc5642cb1a054f08cc83f2d943e56fd3ebe99") result = self.runner.invoke(cli.identify, ["--no-dereference", link]) self.assertSWHID(result, "swh:1:cnt:996f1789ff67c0e3f69ef5933a55d54c5d0e9954") def test_show_filename(self): """filename is shown by default""" self.make_contents(self.tmpdir_name) for filename, content in self.contents.items(): path = os.path.join(self.tmpdir_name, filename) result = self.runner.invoke(cli.identify, ["--type", "content", path]) self.assertEqual(result.exit_code, 0) self.assertEqual( result.output.rstrip(), "swh:1:cnt:%s\t%s" % (hash_to_hex(content["sha1_git"]), path.decode()), ) def test_hide_filename(self): """filename is hidden upon request""" self.make_contents(self.tmpdir_name) for filename, content in self.contents.items(): path = os.path.join(self.tmpdir_name, filename) result = self.runner.invoke( cli.identify, ["--type", "content", "--no-filename", path] ) self.assertSWHID(result, "swh:1:cnt:" + hash_to_hex(content["sha1_git"])) def test_auto_content(self): """automatic object type detection: content""" with tempfile.NamedTemporaryFile(prefix="swh.model.cli") as f: result = self.runner.invoke(cli.identify, [f.name]) self.assertEqual(result.exit_code, 0) self.assertRegex(result.output, r"^swh:\d+:cnt:") def test_auto_directory(self): """automatic object type detection: directory""" with tempfile.TemporaryDirectory(prefix="swh.model.cli") as dirname: result = self.runner.invoke(cli.identify, [dirname]) self.assertEqual(result.exit_code, 0) self.assertRegex(result.output, r"^swh:\d+:dir:") def test_auto_origin(self): """automatic object type detection: origin""" result = self.runner.invoke(cli.identify, ["https://github.com/torvalds/linux"]) self.assertEqual(result.exit_code, 0, result.output) self.assertRegex(result.output, r"^swh:\d+:ori:") def test_verify_content(self): """identifier verification""" self.make_contents(self.tmpdir_name) for filename, content in self.contents.items(): expected_id = "swh:1:cnt:" + hash_to_hex(content["sha1_git"]) # match path = os.path.join(self.tmpdir_name, filename) result = self.runner.invoke(cli.identify, ["--verify", expected_id, path]) self.assertEqual(result.exit_code, 0, result.output) # mismatch with open(path, "a") as f: f.write("trailing garbage to make verification fail") result = self.runner.invoke(cli.identify, ["--verify", expected_id, path]) self.assertEqual(result.exit_code, 1) def test_exclude(self): """exclude patterns""" self.make_from_tarball(self.tmpdir_name) path = os.path.join(self.tmpdir_name, b"sample-folder") excluded_dir = os.path.join(path, b"excluded_dir\x96") os.mkdir(excluded_dir) with open(os.path.join(excluded_dir, b"some_file"), "w") as f: f.write("content") result = self.runner.invoke( cli.identify, ["--type", "directory", "--exclude", "excluded_*", path] ) self.assertSWHID(result, "swh:1:dir:e8b0f1466af8608c8a3fb9879db172b887e80759") + + def test_recursive_directory(self): + self.make_from_tarball(self.tmpdir_name) + path = os.path.join(self.tmpdir_name, b"sample-folder") + result = self.runner.invoke(cli.identify, ["--recursive", path]) + self.assertEqual(result.exit_code, 0, result.output) + + result = result.output.split() + result_swhids = [] + # get all SWHID from the result + for i in range(0, len(result)): + if i % 2 == 0: + result_swhids.append(result[i]) + + assert len(result_swhids) == len(SAMPLE_FOLDER_SWHIDS) + for swhid in SAMPLE_FOLDER_SWHIDS: + assert swhid in result_swhids + + def test_recursive_directory_no_filename(self): + self.make_from_tarball(self.tmpdir_name) + path = os.path.join(self.tmpdir_name, b"sample-folder") + result = self.runner.invoke( + cli.identify, ["--recursive", "--no-filename", path] + ) + self.assertEqual(result.exit_code, 0, result.output) + + result_swhids = result.output.split() + + assert len(result_swhids) == len(SAMPLE_FOLDER_SWHIDS) + for swhid in SAMPLE_FOLDER_SWHIDS: + assert swhid in result_swhids diff --git a/swh/model/tests/test_identifiers.py b/swh/model/tests/test_identifiers.py index 682a3ef..7a236ac 100644 --- a/swh/model/tests/test_identifiers.py +++ b/swh/model/tests/test_identifiers.py @@ -1,1788 +1,1817 @@ # Copyright (C) 2015-2021 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 binascii import datetime import hashlib import itertools from typing import Dict import unittest import attr import pytest from swh.model import hashutil, identifiers from swh.model.exceptions import ValidationError from swh.model.hashutil import hash_to_bytes as _x from swh.model.identifiers import ( SWHID_QUALIFIERS, CoreSWHID, ExtendedObjectType, ExtendedSWHID, ObjectType, QualifiedSWHID, normalize_timestamp, ) def remove_id(d: Dict) -> Dict: """Returns a (shallow) copy of a dict with the 'id' key removed.""" d = d.copy() if "id" in d: del d["id"] return d class UtilityFunctionsIdentifier(unittest.TestCase): def setUp(self): self.str_id = "c2e41aae41ac17bd4a650770d6ee77f62e52235b" self.bytes_id = binascii.unhexlify(self.str_id) self.bad_type_id = object() def test_identifier_to_bytes(self): for id in [self.str_id, self.bytes_id]: self.assertEqual(identifiers.identifier_to_bytes(id), self.bytes_id) # wrong length with self.assertRaises(ValueError) as cm: identifiers.identifier_to_bytes(id[:-2]) self.assertIn("length", str(cm.exception)) with self.assertRaises(ValueError) as cm: identifiers.identifier_to_bytes(self.bad_type_id) self.assertIn("type", str(cm.exception)) def test_identifier_to_str(self): for id in [self.str_id, self.bytes_id]: self.assertEqual(identifiers.identifier_to_str(id), self.str_id) # wrong length with self.assertRaises(ValueError) as cm: identifiers.identifier_to_str(id[:-2]) self.assertIn("length", str(cm.exception)) with self.assertRaises(ValueError) as cm: identifiers.identifier_to_str(self.bad_type_id) self.assertIn("type", str(cm.exception)) class UtilityFunctionsDateOffset(unittest.TestCase): def setUp(self): self.dates = { b"1448210036": {"seconds": 1448210036, "microseconds": 0,}, b"1448210036.002342": {"seconds": 1448210036, "microseconds": 2342,}, b"1448210036.12": {"seconds": 1448210036, "microseconds": 120000,}, } self.broken_dates = [ 1448210036.12, ] self.offsets = { 0: b"+0000", -630: b"-1030", 800: b"+1320", } def test_format_date(self): for date_repr, date in self.dates.items(): self.assertEqual(identifiers.format_date(date), date_repr) def test_format_date_fail(self): for date in self.broken_dates: with self.assertRaises(ValueError): identifiers.format_date(date) def test_format_offset(self): for offset, res in self.offsets.items(): self.assertEqual(identifiers.format_offset(offset), res) content_example = { "status": "visible", "length": 5, "data": b"1984\n", "ctime": datetime.datetime(2015, 11, 22, 16, 33, 56, tzinfo=datetime.timezone.utc), } class ContentIdentifier(unittest.TestCase): def setUp(self): self.content_id = hashutil.MultiHash.from_data(content_example["data"]).digest() def test_content_identifier(self): self.assertEqual( identifiers.content_identifier(content_example), self.content_id ) directory_example = { "id": "d7ed3d2c31d608823be58b1cbe57605310615231", "entries": [ { "type": "file", "perms": 33188, "name": b"README", "target": _x("37ec8ea2110c0b7a32fbb0e872f6e7debbf95e21"), }, { "type": "file", "perms": 33188, "name": b"Rakefile", "target": _x("3bb0e8592a41ae3185ee32266c860714980dbed7"), }, { "type": "dir", "perms": 16384, "name": b"app", "target": _x("61e6e867f5d7ba3b40540869bc050b0c4fed9e95"), }, { "type": "file", "perms": 33188, "name": b"1.megabyte", "target": _x("7c2b2fbdd57d6765cdc9d84c2d7d333f11be7fb3"), }, { "type": "dir", "perms": 16384, "name": b"config", "target": _x("591dfe784a2e9ccc63aaba1cb68a765734310d98"), }, { "type": "dir", "perms": 16384, "name": b"public", "target": _x("9588bf4522c2b4648bfd1c61d175d1f88c1ad4a5"), }, { "type": "file", "perms": 33188, "name": b"development.sqlite3", "target": _x("e69de29bb2d1d6434b8b29ae775ad8c2e48c5391"), }, { "type": "dir", "perms": 16384, "name": b"doc", "target": _x("154705c6aa1c8ead8c99c7915373e3c44012057f"), }, { "type": "dir", "perms": 16384, "name": b"db", "target": _x("85f157bdc39356b7bc7de9d0099b4ced8b3b382c"), }, { "type": "dir", "perms": 16384, "name": b"log", "target": _x("5e3d3941c51cce73352dff89c805a304ba96fffe"), }, { "type": "dir", "perms": 16384, "name": b"script", "target": _x("1b278423caf176da3f3533592012502aa10f566c"), }, { "type": "dir", "perms": 16384, "name": b"test", "target": _x("035f0437c080bfd8711670b3e8677e686c69c763"), }, { "type": "dir", "perms": 16384, "name": b"vendor", "target": _x("7c0dc9ad978c1af3f9a4ce061e50f5918bd27138"), }, { "type": "rev", "perms": 57344, "name": b"will_paginate", "target": _x("3d531e169db92a16a9a8974f0ae6edf52e52659e"), }, # in git order, the dir named "order" should be between the files # named "order." and "order0" { "type": "dir", "perms": 16384, "name": b"order", "target": _x("62cdb7020ff920e5aa642c3d4066950dd1f01f4d"), }, { "type": "file", "perms": 16384, "name": b"order.", "target": _x("0beec7b5ea3f0fdbc95d0dd47f3c5bc275da8a33"), }, { "type": "file", "perms": 16384, "name": b"order0", "target": _x("bbe960a25ea311d21d40669e93df2003ba9b90a2"), }, ], } dummy_qualifiers = {"origin": "https://example.com", "lines": "42"} class DirectoryIdentifier(unittest.TestCase): def setUp(self): self.directory = directory_example self.empty_directory = { "id": "4b825dc642cb6eb9a060e54bf8d69288fbee4904", "entries": [], } def test_dir_identifier(self): self.assertEqual( identifiers.directory_identifier(self.directory), self.directory["id"] ) self.assertEqual( identifiers.directory_identifier(remove_id(self.directory)), self.directory["id"], ) def test_dir_identifier_entry_order(self): # Reverse order of entries, check the id is still the same. directory = {"entries": reversed(self.directory["entries"])} self.assertEqual( identifiers.directory_identifier(remove_id(directory)), self.directory["id"] ) def test_dir_identifier_empty_directory(self): self.assertEqual( identifiers.directory_identifier(remove_id(self.empty_directory)), self.empty_directory["id"], ) linus_tz = datetime.timezone(datetime.timedelta(minutes=-420)) revision_example = { "id": "bc0195aad0daa2ad5b0d76cce22b167bc3435590", "directory": _x("85a74718d377195e1efd0843ba4f3260bad4fe07"), "parents": [_x("01e2d0627a9a6edb24c37db45db5ecb31e9de808")], "author": { "name": b"Linus Torvalds", "email": b"torvalds@linux-foundation.org", "fullname": b"Linus Torvalds ", }, "date": datetime.datetime(2015, 7, 12, 15, 10, 30, tzinfo=linus_tz), "committer": { "name": b"Linus Torvalds", "email": b"torvalds@linux-foundation.org", "fullname": b"Linus Torvalds ", }, "committer_date": datetime.datetime(2015, 7, 12, 15, 10, 30, tzinfo=linus_tz), "message": b"Linux 4.2-rc2\n", "type": "git", "synthetic": False, } class RevisionIdentifier(unittest.TestCase): def setUp(self): gpgsig = b"""\ -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.13 (Darwin) iQIcBAABAgAGBQJVJcYsAAoJEBiY3kIkQRNJVAUQAJ8/XQIfMqqC5oYeEFfHOPYZ L7qy46bXHVBa9Qd8zAJ2Dou3IbI2ZoF6/Et89K/UggOycMlt5FKV/9toWyuZv4Po L682wonoxX99qvVTHo6+wtnmYO7+G0f82h+qHMErxjP+I6gzRNBvRr+SfY7VlGdK wikMKOMWC5smrScSHITnOq1Ews5pe3N7qDYMzK0XVZmgDoaem4RSWMJs4My/qVLN e0CqYWq2A22GX7sXl6pjneJYQvcAXUX+CAzp24QnPSb+Q22Guj91TcxLFcHCTDdn qgqMsEyMiisoglwrCbO+D+1xq9mjN9tNFWP66SQ48mrrHYTBV5sz9eJyDfroJaLP CWgbDTgq6GzRMehHT3hXfYS5NNatjnhkNISXR7pnVP/obIi/vpWh5ll6Gd8q26z+ a/O41UzOaLTeNI365MWT4/cnXohVLRG7iVJbAbCxoQmEgsYMRc/pBAzWJtLfcB2G jdTswYL6+MUdL8sB9pZ82D+BP/YAdHe69CyTu1lk9RT2pYtI/kkfjHubXBCYEJSG +VGllBbYG6idQJpyrOYNRJyrDi9yvDJ2W+S0iQrlZrxzGBVGTB/y65S8C+2WTBcE lf1Qb5GDsQrZWgD+jtWTywOYHtCBwyCKSAXxSARMbNPeak9WPlcW/Jmu+fUcMe2x dg1KdHOa34shrKDaOVzW =od6m -----END PGP SIGNATURE-----""" self.revision = revision_example self.revision_none_metadata = { "id": "bc0195aad0daa2ad5b0d76cce22b167bc3435590", "directory": _x("85a74718d377195e1efd0843ba4f3260bad4fe07"), "parents": [_x("01e2d0627a9a6edb24c37db45db5ecb31e9de808")], "author": { "name": b"Linus Torvalds", "email": b"torvalds@linux-foundation.org", }, "date": datetime.datetime(2015, 7, 12, 15, 10, 30, tzinfo=linus_tz), "committer": { "name": b"Linus Torvalds", "email": b"torvalds@linux-foundation.org", }, "committer_date": datetime.datetime( 2015, 7, 12, 15, 10, 30, tzinfo=linus_tz ), "message": b"Linux 4.2-rc2\n", "metadata": None, } self.synthetic_revision = { "id": b"\xb2\xa7\xe1&\x04\x92\xe3D\xfa\xb3\xcb\xf9\x1b\xc1<\x91" b"\xe0T&\xfd", "author": { "name": b"Software Heritage", "email": b"robot@softwareheritage.org", }, "date": { "timestamp": {"seconds": 1437047495}, "offset": 0, "negative_utc": False, }, "type": "tar", "committer": { "name": b"Software Heritage", "email": b"robot@softwareheritage.org", }, "committer_date": 1437047495, "synthetic": True, "parents": [None], "message": b"synthetic revision message\n", "directory": b"\xd1\x1f\x00\xa6\xa0\xfe\xa6\x05SA\xd2U\x84\xb5\xa9" b"e\x16\xc0\xd2\xb8", "metadata": { "original_artifact": [ { "archive_type": "tar", "name": "gcc-5.2.0.tar.bz2", "sha1_git": "39d281aff934d44b439730057e55b055e206a586", "sha1": "fe3f5390949d47054b613edc36c557eb1d51c18e", "sha256": "5f835b04b5f7dd4f4d2dc96190ec1621b8d89f" "2dc6f638f9f8bc1b1014ba8cad", } ] }, } # cat commit.txt | git hash-object -t commit --stdin self.revision_with_extra_headers = { "id": "010d34f384fa99d047cdd5e2f41e56e5c2feee45", "directory": _x("85a74718d377195e1efd0843ba4f3260bad4fe07"), "parents": [_x("01e2d0627a9a6edb24c37db45db5ecb31e9de808")], "author": { "name": b"Linus Torvalds", "email": b"torvalds@linux-foundation.org", "fullname": b"Linus Torvalds ", }, "date": datetime.datetime(2015, 7, 12, 15, 10, 30, tzinfo=linus_tz), "committer": { "name": b"Linus Torvalds", "email": b"torvalds@linux-foundation.org", "fullname": b"Linus Torvalds ", }, "committer_date": datetime.datetime( 2015, 7, 12, 15, 10, 30, tzinfo=linus_tz ), "message": b"Linux 4.2-rc2\n", "extra_headers": ( (b"svn-repo-uuid", b"046f1af7-66c2-d61b-5410-ce57b7db7bff"), (b"svn-revision", b"10"), ), } self.revision_with_gpgsig = { "id": "44cc742a8ca17b9c279be4cc195a93a6ef7a320e", "directory": _x("b134f9b7dc434f593c0bab696345548b37de0558"), "parents": [ _x("689664ae944b4692724f13b709a4e4de28b54e57"), _x("c888305e1efbaa252d01b4e5e6b778f865a97514"), ], "author": { "name": b"Jiang Xin", "email": b"worldhello.net@gmail.com", "fullname": b"Jiang Xin ", }, "date": {"timestamp": 1428538899, "offset": 480,}, "committer": {"name": b"Jiang Xin", "email": b"worldhello.net@gmail.com",}, "committer_date": {"timestamp": 1428538899, "offset": 480,}, "extra_headers": ((b"gpgsig", gpgsig),), "message": b"""Merge branch 'master' of git://github.com/alexhenrie/git-po * 'master' of git://github.com/alexhenrie/git-po: l10n: ca.po: update translation """, } self.revision_no_message = { "id": "4cfc623c9238fa92c832beed000ce2d003fd8333", "directory": _x("b134f9b7dc434f593c0bab696345548b37de0558"), "parents": [ _x("689664ae944b4692724f13b709a4e4de28b54e57"), _x("c888305e1efbaa252d01b4e5e6b778f865a97514"), ], "author": { "name": b"Jiang Xin", "email": b"worldhello.net@gmail.com", "fullname": b"Jiang Xin ", }, "date": {"timestamp": 1428538899, "offset": 480,}, "committer": {"name": b"Jiang Xin", "email": b"worldhello.net@gmail.com",}, "committer_date": {"timestamp": 1428538899, "offset": 480,}, "message": None, } self.revision_empty_message = { "id": "7442cd78bd3b4966921d6a7f7447417b7acb15eb", "directory": _x("b134f9b7dc434f593c0bab696345548b37de0558"), "parents": [ _x("689664ae944b4692724f13b709a4e4de28b54e57"), _x("c888305e1efbaa252d01b4e5e6b778f865a97514"), ], "author": { "name": b"Jiang Xin", "email": b"worldhello.net@gmail.com", "fullname": b"Jiang Xin ", }, "date": {"timestamp": 1428538899, "offset": 480,}, "committer": {"name": b"Jiang Xin", "email": b"worldhello.net@gmail.com",}, "committer_date": {"timestamp": 1428538899, "offset": 480,}, "message": b"", } self.revision_only_fullname = { "id": "010d34f384fa99d047cdd5e2f41e56e5c2feee45", "directory": _x("85a74718d377195e1efd0843ba4f3260bad4fe07"), "parents": [_x("01e2d0627a9a6edb24c37db45db5ecb31e9de808")], "author": {"fullname": b"Linus Torvalds ",}, "date": datetime.datetime(2015, 7, 12, 15, 10, 30, tzinfo=linus_tz), "committer": { "fullname": b"Linus Torvalds ", }, "committer_date": datetime.datetime( 2015, 7, 12, 15, 10, 30, tzinfo=linus_tz ), "message": b"Linux 4.2-rc2\n", "extra_headers": ( (b"svn-repo-uuid", b"046f1af7-66c2-d61b-5410-ce57b7db7bff"), (b"svn-revision", b"10"), ), } def test_revision_identifier(self): self.assertEqual( identifiers.revision_identifier(self.revision), identifiers.identifier_to_str(self.revision["id"]), ) self.assertEqual( identifiers.revision_identifier(remove_id(self.revision)), identifiers.identifier_to_str(self.revision["id"]), ) def test_revision_identifier_none_metadata(self): self.assertEqual( identifiers.revision_identifier(remove_id(self.revision_none_metadata)), identifiers.identifier_to_str(self.revision_none_metadata["id"]), ) def test_revision_identifier_synthetic(self): self.assertEqual( identifiers.revision_identifier(remove_id(self.synthetic_revision)), identifiers.identifier_to_str(self.synthetic_revision["id"]), ) def test_revision_identifier_with_extra_headers(self): self.assertEqual( identifiers.revision_identifier( remove_id(self.revision_with_extra_headers) ), identifiers.identifier_to_str(self.revision_with_extra_headers["id"]), ) def test_revision_identifier_with_gpgsig(self): self.assertEqual( identifiers.revision_identifier(remove_id(self.revision_with_gpgsig)), identifiers.identifier_to_str(self.revision_with_gpgsig["id"]), ) def test_revision_identifier_no_message(self): self.assertEqual( identifiers.revision_identifier(remove_id(self.revision_no_message)), identifiers.identifier_to_str(self.revision_no_message["id"]), ) def test_revision_identifier_empty_message(self): self.assertEqual( identifiers.revision_identifier(remove_id(self.revision_empty_message)), identifiers.identifier_to_str(self.revision_empty_message["id"]), ) def test_revision_identifier_only_fullname(self): self.assertEqual( identifiers.revision_identifier(remove_id(self.revision_only_fullname)), identifiers.identifier_to_str(self.revision_only_fullname["id"]), ) release_example = { "id": "2b10839e32c4c476e9d94492756bb1a3e1ec4aa8", "target": b't\x1b"R\xa5\xe1Ml`\xa9\x13\xc7z`\x99\xab\xe7:\x85J', "target_type": "revision", "name": b"v2.6.14", "author": { "name": b"Linus Torvalds", "email": b"torvalds@g5.osdl.org", "fullname": b"Linus Torvalds ", }, "date": datetime.datetime(2005, 10, 27, 17, 2, 33, tzinfo=linus_tz), "message": b"""\ Linux 2.6.14 release -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.1 (GNU/Linux) iD8DBQBDYWq6F3YsRnbiHLsRAmaeAJ9RCez0y8rOBbhSv344h86l/VVcugCeIhO1 wdLOnvj91G4wxYqrvThthbE= =7VeT -----END PGP SIGNATURE----- """, "synthetic": False, } class ReleaseIdentifier(unittest.TestCase): def setUp(self): linus_tz = datetime.timezone(datetime.timedelta(minutes=-420)) self.release = release_example self.release_no_author = { "id": b"&y\x1a\x8b\xcf\x0em3\xf4:\xefv\x82\xbd\xb5U#mV\xde", "target": "9ee1c939d1cb936b1f98e8d81aeffab57bae46ab", "target_type": "revision", "name": b"v2.6.12", "message": b"""\ This is the final 2.6.12 release -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.2.4 (GNU/Linux) iD8DBQBCsykyF3YsRnbiHLsRAvPNAJ482tCZwuxp/bJRz7Q98MHlN83TpACdHr37 o6X/3T+vm8K3bf3driRr34c= =sBHn -----END PGP SIGNATURE----- """, "synthetic": False, } self.release_no_message = { "id": "b6f4f446715f7d9543ef54e41b62982f0db40045", "target": "9ee1c939d1cb936b1f98e8d81aeffab57bae46ab", "target_type": "revision", "name": b"v2.6.12", "author": {"name": b"Linus Torvalds", "email": b"torvalds@g5.osdl.org",}, "date": datetime.datetime(2005, 10, 27, 17, 2, 33, tzinfo=linus_tz), "message": None, } self.release_empty_message = { "id": "71a0aea72444d396575dc25ac37fec87ee3c6492", "target": "9ee1c939d1cb936b1f98e8d81aeffab57bae46ab", "target_type": "revision", "name": b"v2.6.12", "author": {"name": b"Linus Torvalds", "email": b"torvalds@g5.osdl.org",}, "date": datetime.datetime(2005, 10, 27, 17, 2, 33, tzinfo=linus_tz), "message": b"", } self.release_negative_utc = { "id": "97c8d2573a001f88e72d75f596cf86b12b82fd01", "name": b"20081029", "target": "54e9abca4c77421e2921f5f156c9fe4a9f7441c7", "target_type": "revision", "date": { "timestamp": {"seconds": 1225281976}, "offset": 0, "negative_utc": True, }, "author": { "name": b"Otavio Salvador", "email": b"otavio@debian.org", "id": 17640, }, "synthetic": False, "message": b"tagging version 20081029\n\nr56558\n", } self.release_newline_in_author = { "author": { "email": b"esycat@gmail.com", "fullname": b"Eugene Janusov\n", "name": b"Eugene Janusov\n", }, "date": { "negative_utc": None, "offset": 600, "timestamp": {"microseconds": 0, "seconds": 1377480558,}, }, "id": b"\\\x98\xf5Y\xd04\x16-\xe2->\xbe\xb9T3\xe6\xf8\x88R1", "message": b"Release of v0.3.2.", "name": b"0.3.2", "synthetic": False, "target": (b"\xc0j\xa3\xd9;x\xa2\x86\\I5\x17" b"\x000\xf8\xc2\xd79o\xd3"), "target_type": "revision", } self.release_snapshot_target = dict(self.release) self.release_snapshot_target["target_type"] = "snapshot" self.release_snapshot_target["id"] = "c29c3ddcc6769a04e54dd69d63a6fdcbc566f850" def test_release_identifier(self): self.assertEqual( identifiers.release_identifier(self.release), identifiers.identifier_to_str(self.release["id"]), ) self.assertEqual( identifiers.release_identifier(remove_id(self.release)), identifiers.identifier_to_str(self.release["id"]), ) def test_release_identifier_no_author(self): self.assertEqual( identifiers.release_identifier(remove_id(self.release_no_author)), identifiers.identifier_to_str(self.release_no_author["id"]), ) def test_release_identifier_no_message(self): self.assertEqual( identifiers.release_identifier(remove_id(self.release_no_message)), identifiers.identifier_to_str(self.release_no_message["id"]), ) def test_release_identifier_empty_message(self): self.assertEqual( identifiers.release_identifier(remove_id(self.release_empty_message)), identifiers.identifier_to_str(self.release_empty_message["id"]), ) def test_release_identifier_negative_utc(self): self.assertEqual( identifiers.release_identifier(remove_id(self.release_negative_utc)), identifiers.identifier_to_str(self.release_negative_utc["id"]), ) def test_release_identifier_newline_in_author(self): self.assertEqual( identifiers.release_identifier(remove_id(self.release_newline_in_author)), identifiers.identifier_to_str(self.release_newline_in_author["id"]), ) def test_release_identifier_snapshot_target(self): self.assertEqual( identifiers.release_identifier(self.release_snapshot_target), identifiers.identifier_to_str(self.release_snapshot_target["id"]), ) snapshot_example = { "id": _x("6e65b86363953b780d92b0a928f3e8fcdd10db36"), "branches": { b"directory": { "target": _x("1bd0e65f7d2ff14ae994de17a1e7fe65111dcad8"), "target_type": "directory", }, b"content": { "target": _x("fe95a46679d128ff167b7c55df5d02356c5a1ae1"), "target_type": "content", }, b"alias": {"target": b"revision", "target_type": "alias",}, b"revision": { "target": _x("aafb16d69fd30ff58afdd69036a26047f3aebdc6"), "target_type": "revision", }, b"release": { "target": _x("7045404f3d1c54e6473c71bbb716529fbad4be24"), "target_type": "release", }, b"snapshot": { "target": _x("1a8893e6a86f444e8be8e7bda6cb34fb1735a00e"), "target_type": "snapshot", }, b"dangling": None, }, } class SnapshotIdentifier(unittest.TestCase): def setUp(self): super().setUp() self.empty = { "id": "1a8893e6a86f444e8be8e7bda6cb34fb1735a00e", "branches": {}, } self.dangling_branch = { "id": "c84502e821eb21ed84e9fd3ec40973abc8b32353", "branches": {b"HEAD": None,}, } self.unresolved = { "id": "84b4548ea486e4b0a7933fa541ff1503a0afe1e0", "branches": {b"foo": {"target": b"bar", "target_type": "alias",},}, } self.all_types = snapshot_example def test_empty_snapshot(self): self.assertEqual( identifiers.snapshot_identifier(remove_id(self.empty)), identifiers.identifier_to_str(self.empty["id"]), ) def test_dangling_branch(self): self.assertEqual( identifiers.snapshot_identifier(remove_id(self.dangling_branch)), identifiers.identifier_to_str(self.dangling_branch["id"]), ) def test_unresolved(self): with self.assertRaisesRegex(ValueError, "b'foo' -> b'bar'"): identifiers.snapshot_identifier(remove_id(self.unresolved)) def test_unresolved_force(self): self.assertEqual( identifiers.snapshot_identifier( remove_id(self.unresolved), ignore_unresolved=True, ), identifiers.identifier_to_str(self.unresolved["id"]), ) def test_all_types(self): self.assertEqual( identifiers.snapshot_identifier(remove_id(self.all_types)), identifiers.identifier_to_str(self.all_types["id"]), ) authority_example = { "type": "forge", "url": "https://forge.softwareheritage.org/", } fetcher_example = { "name": "swh-phabricator-metadata-fetcher", "version": "0.0.1", } metadata_example = { "target": "swh:1:cnt:568aaf43d83b2c3df8067f3bedbb97d83260be6d", "discovery_date": datetime.datetime( 2021, 1, 25, 11, 27, 51, tzinfo=datetime.timezone.utc ), "authority": authority_example, "fetcher": fetcher_example, "format": "json", "metadata": b'{"foo": "bar"}', } class RawExtrinsicMetadataIdentifier(unittest.TestCase): def setUp(self): super().setUp() self.minimal = metadata_example self.maximal = { **self.minimal, "origin": "https://forge.softwareheritage.org/source/swh-model/", "visit": 42, "snapshot": CoreSWHID.from_string("swh:1:snp:" + "00" * 20), "release": CoreSWHID.from_string("swh:1:rel:" + "01" * 20), "revision": CoreSWHID.from_string("swh:1:rev:" + "02" * 20), "path": b"/abc/def", "directory": CoreSWHID.from_string("swh:1:dir:" + "03" * 20), } def test_minimal(self): git_object = ( b"raw_extrinsic_metadata 210\0" b"target swh:1:cnt:568aaf43d83b2c3df8067f3bedbb97d83260be6d\n" b"discovery_date 1611574071\n" b"authority forge https://forge.softwareheritage.org/\n" b"fetcher swh-phabricator-metadata-fetcher 0.0.1\n" b"format json\n" b"\n" b'{"foo": "bar"}' ) self.assertEqual( identifiers.raw_extrinsic_metadata_git_object(self.minimal), git_object, ) self.assertEqual( identifiers.raw_extrinsic_metadata_identifier(self.minimal), hashlib.sha1(git_object).hexdigest(), ) self.assertEqual( identifiers.raw_extrinsic_metadata_identifier(self.minimal), "5c13f20ba336e44549baf3d7b9305b027ec9f43d", ) def test_maximal(self): git_object = ( b"raw_extrinsic_metadata 533\0" b"target swh:1:cnt:568aaf43d83b2c3df8067f3bedbb97d83260be6d\n" b"discovery_date 1611574071\n" b"authority forge https://forge.softwareheritage.org/\n" b"fetcher swh-phabricator-metadata-fetcher 0.0.1\n" b"format json\n" b"origin https://forge.softwareheritage.org/source/swh-model/\n" b"visit 42\n" b"snapshot swh:1:snp:0000000000000000000000000000000000000000\n" b"release swh:1:rel:0101010101010101010101010101010101010101\n" b"revision swh:1:rev:0202020202020202020202020202020202020202\n" b"path /abc/def\n" b"directory swh:1:dir:0303030303030303030303030303030303030303\n" b"\n" b'{"foo": "bar"}' ) self.assertEqual( identifiers.raw_extrinsic_metadata_git_object(self.maximal), git_object, ) self.assertEqual( identifiers.raw_extrinsic_metadata_identifier(self.maximal), hashlib.sha1(git_object).hexdigest(), ) self.assertEqual( identifiers.raw_extrinsic_metadata_identifier(self.maximal), "f96966e1093d15236a31fde07e47d5b1c9428049", ) def test_nonascii_path(self): metadata = { **self.minimal, "path": b"/ab\nc/d\xf0\x9f\xa4\xb7e\x00f", } git_object = ( b"raw_extrinsic_metadata 231\0" b"target swh:1:cnt:568aaf43d83b2c3df8067f3bedbb97d83260be6d\n" b"discovery_date 1611574071\n" b"authority forge https://forge.softwareheritage.org/\n" b"fetcher swh-phabricator-metadata-fetcher 0.0.1\n" b"format json\n" b"path /ab\n" b" c/d\xf0\x9f\xa4\xb7e\x00f\n" b"\n" b'{"foo": "bar"}' ) self.assertEqual( identifiers.raw_extrinsic_metadata_git_object(metadata), git_object, ) self.assertEqual( identifiers.raw_extrinsic_metadata_identifier(metadata), hashlib.sha1(git_object).hexdigest(), ) self.assertEqual( identifiers.raw_extrinsic_metadata_identifier(metadata), "7cc83fd1912176510c083f5df43f01b09af4b333", ) def test_timezone_insensitive(self): """Checks the timezone of the datetime.datetime does not affect the hashed git_object.""" utc_plus_one = datetime.timezone(datetime.timedelta(hours=1)) metadata = { **self.minimal, "discovery_date": datetime.datetime( 2021, 1, 25, 12, 27, 51, tzinfo=utc_plus_one, ), } self.assertEqual( identifiers.raw_extrinsic_metadata_git_object(self.minimal), identifiers.raw_extrinsic_metadata_git_object(metadata), ) self.assertEqual( identifiers.raw_extrinsic_metadata_identifier(self.minimal), identifiers.raw_extrinsic_metadata_identifier(metadata), ) self.assertEqual( identifiers.raw_extrinsic_metadata_identifier(metadata), "5c13f20ba336e44549baf3d7b9305b027ec9f43d", ) def test_microsecond_insensitive(self): """Checks the microseconds of the datetime.datetime does not affect the hashed manifest.""" metadata = { **self.minimal, "discovery_date": datetime.datetime( 2021, 1, 25, 11, 27, 51, 123456, tzinfo=datetime.timezone.utc, ), } self.assertEqual( identifiers.raw_extrinsic_metadata_git_object(self.minimal), identifiers.raw_extrinsic_metadata_git_object(metadata), ) self.assertEqual( identifiers.raw_extrinsic_metadata_identifier(self.minimal), identifiers.raw_extrinsic_metadata_identifier(metadata), ) self.assertEqual( identifiers.raw_extrinsic_metadata_identifier(metadata), "5c13f20ba336e44549baf3d7b9305b027ec9f43d", ) def test_noninteger_timezone(self): """Checks the discovery_date is translated to UTC before truncating microseconds""" tz = datetime.timezone(datetime.timedelta(microseconds=-42)) metadata = { **self.minimal, "discovery_date": datetime.datetime( 2021, 1, 25, 11, 27, 50, 1_000_000 - 42, tzinfo=tz, ), } self.assertEqual( identifiers.raw_extrinsic_metadata_git_object(self.minimal), identifiers.raw_extrinsic_metadata_git_object(metadata), ) self.assertEqual( identifiers.raw_extrinsic_metadata_identifier(self.minimal), identifiers.raw_extrinsic_metadata_identifier(metadata), ) self.assertEqual( identifiers.raw_extrinsic_metadata_identifier(metadata), "5c13f20ba336e44549baf3d7b9305b027ec9f43d", ) def test_negative_timestamp(self): metadata = { **self.minimal, "discovery_date": datetime.datetime( 1960, 1, 25, 11, 27, 51, tzinfo=datetime.timezone.utc, ), } git_object = ( b"raw_extrinsic_metadata 210\0" b"target swh:1:cnt:568aaf43d83b2c3df8067f3bedbb97d83260be6d\n" b"discovery_date -313504329\n" b"authority forge https://forge.softwareheritage.org/\n" b"fetcher swh-phabricator-metadata-fetcher 0.0.1\n" b"format json\n" b"\n" b'{"foo": "bar"}' ) self.assertEqual( identifiers.raw_extrinsic_metadata_git_object(metadata), git_object, ) self.assertEqual( identifiers.raw_extrinsic_metadata_identifier(metadata), hashlib.sha1(git_object).hexdigest(), ) self.assertEqual( identifiers.raw_extrinsic_metadata_identifier(metadata), "895d0821a2991dd376ddc303424aceb7c68280f9", ) def test_epoch(self): metadata = { **self.minimal, "discovery_date": datetime.datetime( 1970, 1, 1, 0, 0, 0, tzinfo=datetime.timezone.utc, ), } git_object = ( b"raw_extrinsic_metadata 201\0" b"target swh:1:cnt:568aaf43d83b2c3df8067f3bedbb97d83260be6d\n" b"discovery_date 0\n" b"authority forge https://forge.softwareheritage.org/\n" b"fetcher swh-phabricator-metadata-fetcher 0.0.1\n" b"format json\n" b"\n" b'{"foo": "bar"}' ) self.assertEqual( identifiers.raw_extrinsic_metadata_git_object(metadata), git_object, ) self.assertEqual( identifiers.raw_extrinsic_metadata_identifier(metadata), hashlib.sha1(git_object).hexdigest(), ) self.assertEqual( identifiers.raw_extrinsic_metadata_identifier(metadata), "27a53df54ace35ebd910493cdc70b334d6b7cb88", ) def test_negative_epoch(self): metadata = { **self.minimal, "discovery_date": datetime.datetime( 1969, 12, 31, 23, 59, 59, 1, tzinfo=datetime.timezone.utc, ), } git_object = ( b"raw_extrinsic_metadata 202\0" b"target swh:1:cnt:568aaf43d83b2c3df8067f3bedbb97d83260be6d\n" b"discovery_date -1\n" b"authority forge https://forge.softwareheritage.org/\n" b"fetcher swh-phabricator-metadata-fetcher 0.0.1\n" b"format json\n" b"\n" b'{"foo": "bar"}' ) self.assertEqual( identifiers.raw_extrinsic_metadata_git_object(metadata), git_object, ) self.assertEqual( identifiers.raw_extrinsic_metadata_identifier(metadata), hashlib.sha1(git_object).hexdigest(), ) self.assertEqual( identifiers.raw_extrinsic_metadata_identifier(metadata), "be7154a8fd49d87f81547ea634d1e2152907d089", ) origin_example = { "url": "https://github.com/torvalds/linux", } class OriginIdentifier(unittest.TestCase): def test_content_identifier(self): self.assertEqual( identifiers.origin_identifier(origin_example), "b63a575fe3faab7692c9f38fb09d4bb45651bb0f", ) TS_DICTS = [ ( {"timestamp": 12345, "offset": 0}, { "timestamp": {"seconds": 12345, "microseconds": 0}, "offset": 0, "negative_utc": False, }, ), ( {"timestamp": 12345, "offset": 0, "negative_utc": False}, { "timestamp": {"seconds": 12345, "microseconds": 0}, "offset": 0, "negative_utc": False, }, ), ( {"timestamp": 12345, "offset": 0, "negative_utc": False}, { "timestamp": {"seconds": 12345, "microseconds": 0}, "offset": 0, "negative_utc": False, }, ), ( {"timestamp": 12345, "offset": 0, "negative_utc": None}, { "timestamp": {"seconds": 12345, "microseconds": 0}, "offset": 0, "negative_utc": False, }, ), ( {"timestamp": {"seconds": 12345}, "offset": 0, "negative_utc": None}, { "timestamp": {"seconds": 12345, "microseconds": 0}, "offset": 0, "negative_utc": False, }, ), ( { "timestamp": {"seconds": 12345, "microseconds": 0}, "offset": 0, "negative_utc": None, }, { "timestamp": {"seconds": 12345, "microseconds": 0}, "offset": 0, "negative_utc": False, }, ), ( { "timestamp": {"seconds": 12345, "microseconds": 100}, "offset": 0, "negative_utc": None, }, { "timestamp": {"seconds": 12345, "microseconds": 100}, "offset": 0, "negative_utc": False, }, ), ( {"timestamp": 12345, "offset": 0, "negative_utc": True}, { "timestamp": {"seconds": 12345, "microseconds": 0}, "offset": 0, "negative_utc": True, }, ), ( {"timestamp": 12345, "offset": 0, "negative_utc": None}, { "timestamp": {"seconds": 12345, "microseconds": 0}, "offset": 0, "negative_utc": False, }, ), ] @pytest.mark.parametrize("dict_input,expected", TS_DICTS) def test_normalize_timestamp_dict(dict_input, expected): assert normalize_timestamp(dict_input) == expected TS_DICTS_INVALID_TIMESTAMP = [ {"timestamp": 1.2, "offset": 0}, {"timestamp": "1", "offset": 0}, # these below should really also trigger a ValueError... # {"timestamp": {"seconds": "1"}, "offset": 0}, # {"timestamp": {"seconds": 1.2}, "offset": 0}, # {"timestamp": {"seconds": 1.2}, "offset": 0}, ] @pytest.mark.parametrize("dict_input", TS_DICTS_INVALID_TIMESTAMP) def test_normalize_timestamp_dict_invalid_timestamp(dict_input): with pytest.raises(ValueError, match="non-integer timestamp"): normalize_timestamp(dict_input) +UTC = datetime.timezone.utc +TS_TIMEZONES = [ + datetime.timezone.min, + datetime.timezone(datetime.timedelta(hours=-1)), + UTC, + datetime.timezone(datetime.timedelta(minutes=+60)), + datetime.timezone.max, +] +TS_TZ_EXPECTED = [-1439, -60, 0, 60, 1439] +TS_DATETIMES = [ + datetime.datetime(2020, 2, 27, 14, 39, 19, tzinfo=UTC), + datetime.datetime(2120, 12, 31, 23, 59, 59, tzinfo=UTC), + datetime.datetime(1610, 5, 14, 15, 43, 0, tzinfo=UTC), +] +TS_DT_EXPECTED = [1582814359, 4765132799, -11348929020] + + +@pytest.mark.parametrize("date, seconds", zip(TS_DATETIMES, TS_DT_EXPECTED)) +@pytest.mark.parametrize("tz, offset", zip(TS_TIMEZONES, TS_TZ_EXPECTED)) +@pytest.mark.parametrize("microsecond", [0, 1, 10, 100, 1000, 999999]) +def test_normalize_timestamp_datetime(date, seconds, tz, offset, microsecond): + date = date.astimezone(tz).replace(microsecond=microsecond) + assert normalize_timestamp(date) == { + "timestamp": {"seconds": seconds, "microseconds": microsecond}, + "offset": offset, + "negative_utc": False, + } + + # SWHIDs that are outright invalid, no matter the context INVALID_SWHIDS = [ "swh:1:cnt", "swh:1:", "swh:", "swh:1:cnt:", "foo:1:cnt:abc8bc9d7a6bcf6db04f476d29314f157507d505", "swh:2:dir:def8bc9d7a6bcf6db04f476d29314f157507d505", "swh:1:foo:fed8bc9d7a6bcf6db04f476d29314f157507d505", "swh:1:dir:0b6959356d30f1a4e9b7f6bca59b9a336464c03d;invalid;malformed", "swh:1:snp:gh6959356d30f1a4e9b7f6bca59b9a336464c03d", "swh:1:snp:foo", # wrong qualifier: ori should be origin "swh:1:dir:0b6959356d30f1a4e9b7f6bca59b9a336464c03d;ori=something;anchor=1;visit=1;path=/", # noqa # wrong qualifier: anc should be anchor "swh:1:dir:0b6959356d30f1a4e9b7f6bca59b9a336464c03d;origin=something;anc=1;visit=1;path=/", # noqa # wrong qualifier: vis should be visit "swh:1:dir:0b6959356d30f1a4e9b7f6bca59b9a336464c03d;origin=something;anchor=1;vis=1;path=/", # noqa # wrong qualifier: pa should be path "swh:1:dir:0b6959356d30f1a4e9b7f6bca59b9a336464c03d;origin=something;anchor=1;visit=1;pa=/", # noqa # wrong qualifier: line should be lines "swh:1:dir:0b6959356d30f1a4e9b7f6bca59b9a336464c03d;line=10;origin=something;anchor=1;visit=1;path=/", # noqa # wrong qualifier value: it contains space before of after "swh:1:dir:0b6959356d30f1a4e9b7f6bca59b9a336464c03d;origin= https://some-url", # noqa "swh:1:dir:0b6959356d30f1a4e9b7f6bca59b9a336464c03d;origin=something;anchor=some-anchor ", # noqa "swh:1:dir:0b6959356d30f1a4e9b7f6bca59b9a336464c03d;origin=something;anchor=some-anchor ;visit=1", # noqa # invalid swhid: whitespaces "swh :1:dir:0b6959356d30f1a4e9b7f6bca59b9a336464c03d;ori=something;anchor=1;visit=1;path=/", # noqa "swh: 1:dir:0b6959356d30f1a4e9b7f6bca59b9a336464c03d;ori=something;anchor=1;visit=1;path=/", # noqa "swh: 1: dir:0b6959356d30f1a4e9b7f6bca59b9a336464c03d;ori=something;anchor=1;visit=1;path=/", # noqa "swh:1: dir: 0b6959356d30f1a4e9b7f6bca59b9a336464c03d", "swh:1: dir: 0b6959356d30f1a4e9b7f6bca59b9a336464c03d; origin=blah", "swh:1: dir: 0b6959356d30f1a4e9b7f6bca59b9a336464c03d;lines=12", # other whitespaces "swh\t:1:dir:0b6959356d30f1a4e9b7f6bca59b9a336464c03d;lines=12", "swh:1\n:dir:0b6959356d30f1a4e9b7f6bca59b9a336464c03d;lines=12", "swh:1:\rdir:0b6959356d30f1a4e9b7f6bca59b9a336464c03d;lines=12", "swh:1:dir:0b6959356d30f1a4e9b7f6bca59b9a336464c03d\f;lines=12", "swh:1:dir:0b6959356d30f1a4e9b7f6bca59b9a336464c03d;lines=12\v", ] SWHID_CLASSES = [CoreSWHID, QualifiedSWHID, ExtendedSWHID] @pytest.mark.parametrize( "invalid_swhid,swhid_class", itertools.product(INVALID_SWHIDS, SWHID_CLASSES) ) def test_swhid_parsing_error(invalid_swhid, swhid_class): """Tests SWHID strings that are invalid for all SWHID classes do raise a ValidationError""" with pytest.raises(ValidationError): swhid_class.from_string(invalid_swhid) # string SWHIDs, and how they should be parsed by each of the classes, # or None if the class does not support it HASH = "94a9ed024d3859793618152ea559a168bbcbb5e2" VALID_SWHIDS = [ ( f"swh:1:cnt:{HASH}", CoreSWHID(object_type=ObjectType.CONTENT, object_id=_x(HASH),), QualifiedSWHID(object_type=ObjectType.CONTENT, object_id=_x(HASH),), ExtendedSWHID(object_type=ExtendedObjectType.CONTENT, object_id=_x(HASH),), ), ( f"swh:1:dir:{HASH}", CoreSWHID(object_type=ObjectType.DIRECTORY, object_id=_x(HASH),), QualifiedSWHID(object_type=ObjectType.DIRECTORY, object_id=_x(HASH),), ExtendedSWHID(object_type=ExtendedObjectType.DIRECTORY, object_id=_x(HASH),), ), ( f"swh:1:rev:{HASH}", CoreSWHID(object_type=ObjectType.REVISION, object_id=_x(HASH),), QualifiedSWHID(object_type=ObjectType.REVISION, object_id=_x(HASH),), ExtendedSWHID(object_type=ExtendedObjectType.REVISION, object_id=_x(HASH),), ), ( f"swh:1:rel:{HASH}", CoreSWHID(object_type=ObjectType.RELEASE, object_id=_x(HASH),), QualifiedSWHID(object_type=ObjectType.RELEASE, object_id=_x(HASH),), ExtendedSWHID(object_type=ExtendedObjectType.RELEASE, object_id=_x(HASH),), ), ( f"swh:1:snp:{HASH}", CoreSWHID(object_type=ObjectType.SNAPSHOT, object_id=_x(HASH),), QualifiedSWHID(object_type=ObjectType.SNAPSHOT, object_id=_x(HASH),), ExtendedSWHID(object_type=ExtendedObjectType.SNAPSHOT, object_id=_x(HASH),), ), ( f"swh:1:cnt:{HASH};origin=https://github.com/python/cpython;lines=1-18", None, # CoreSWHID does not allow qualifiers QualifiedSWHID( object_type=ObjectType.CONTENT, object_id=_x(HASH), origin="https://github.com/python/cpython", lines=(1, 18), ), None, # Neither does ExtendedSWHID ), ( f"swh:1:cnt:{HASH};origin=https://github.com/python/cpython;lines=1-18/", None, # likewise None, None, # likewise ), ( f"swh:1:cnt:{HASH};origin=https://github.com/python/cpython;lines=18", None, # likewise QualifiedSWHID( object_type=ObjectType.CONTENT, object_id=_x(HASH), origin="https://github.com/python/cpython", lines=(18, None), ), None, # likewise ), ( f"swh:1:dir:{HASH};origin=deb://Debian/packages/linuxdoc-tools", None, # likewise QualifiedSWHID( object_type=ObjectType.DIRECTORY, object_id=_x(HASH), origin="deb://Debian/packages/linuxdoc-tools", ), None, # likewise ), ( f"swh:1:ori:{HASH}", None, # CoreSWHID does not allow origin pseudo-SWHIDs None, # Neither does QualifiedSWHID ExtendedSWHID(object_type=ExtendedObjectType.ORIGIN, object_id=_x(HASH),), ), ( f"swh:1:emd:{HASH}", None, # likewise for metadata pseudo-SWHIDs None, # Neither does QualifiedSWHID ExtendedSWHID( object_type=ExtendedObjectType.RAW_EXTRINSIC_METADATA, object_id=_x(HASH), ), ), ( f"swh:1:emd:{HASH};origin=https://github.com/python/cpython", None, # CoreSWHID does not allow metadata pseudo-SWHIDs or qualifiers None, # QualifiedSWHID does not allow metadata pseudo-SWHIDs None, # ExtendedSWHID does not allow qualifiers ), ] @pytest.mark.parametrize( "string,core,qualified,extended", [ pytest.param(string, core, qualified, extended, id=string) for (string, core, qualified, extended) in VALID_SWHIDS ], ) def test_parse_unparse_swhids(string, core, qualified, extended): """Tests parsing and serializing valid SWHIDs with the various SWHID classes.""" classes = [CoreSWHID, QualifiedSWHID, ExtendedSWHID] for (cls, parsed_swhid) in zip(classes, [core, qualified, extended]): if parsed_swhid is None: # This class should not accept this SWHID with pytest.raises(ValidationError) as excinfo: cls.from_string(string) # Check string serialization for exception assert str(excinfo.value) is not None else: # This class should assert cls.from_string(string) == parsed_swhid # Also check serialization assert string == str(parsed_swhid) @pytest.mark.parametrize( "core,extended", [ pytest.param(core, extended, id=string) for (string, core, qualified, extended) in VALID_SWHIDS if core is not None ], ) def test_core_to_extended(core, extended): assert core.to_extended() == extended @pytest.mark.parametrize( "ns,version,type,id,qualifiers", [ ("foo", 1, ObjectType.CONTENT, "abc8bc9d7a6bcf6db04f476d29314f157507d505", {}), ("swh", 2, ObjectType.CONTENT, "def8bc9d7a6bcf6db04f476d29314f157507d505", {}), ("swh", 1, ObjectType.DIRECTORY, "aaaa", {}), ], ) def test_QualifiedSWHID_validation_error(ns, version, type, id, qualifiers): with pytest.raises(ValidationError): QualifiedSWHID( namespace=ns, scheme_version=version, object_type=type, object_id=_x(id), **qualifiers, ) @pytest.mark.parametrize( "object_type,qualifiers,expected", [ # No qualifier: (ObjectType.CONTENT, {}, f"swh:1:cnt:{HASH}"), # origin: (ObjectType.CONTENT, {"origin": None}, f"swh:1:cnt:{HASH}"), (ObjectType.CONTENT, {"origin": 42}, ValueError), # visit: ( ObjectType.CONTENT, {"visit": f"swh:1:snp:{HASH}"}, f"swh:1:cnt:{HASH};visit=swh:1:snp:{HASH}", ), ( ObjectType.CONTENT, {"visit": CoreSWHID(object_type=ObjectType.SNAPSHOT, object_id=_x(HASH))}, f"swh:1:cnt:{HASH};visit=swh:1:snp:{HASH}", ), (ObjectType.CONTENT, {"visit": 42}, TypeError), (ObjectType.CONTENT, {"visit": f"swh:1:rel:{HASH}"}, ValidationError,), ( ObjectType.CONTENT, {"visit": CoreSWHID(object_type=ObjectType.RELEASE, object_id=_x(HASH))}, ValidationError, ), # anchor: ( ObjectType.CONTENT, {"anchor": f"swh:1:snp:{HASH}"}, f"swh:1:cnt:{HASH};anchor=swh:1:snp:{HASH}", ), ( ObjectType.CONTENT, {"anchor": CoreSWHID(object_type=ObjectType.SNAPSHOT, object_id=_x(HASH))}, f"swh:1:cnt:{HASH};anchor=swh:1:snp:{HASH}", ), ( ObjectType.CONTENT, {"anchor": f"swh:1:dir:{HASH}"}, f"swh:1:cnt:{HASH};anchor=swh:1:dir:{HASH}", ), ( ObjectType.CONTENT, {"anchor": CoreSWHID(object_type=ObjectType.DIRECTORY, object_id=_x(HASH))}, f"swh:1:cnt:{HASH};anchor=swh:1:dir:{HASH}", ), (ObjectType.CONTENT, {"anchor": 42}, TypeError), (ObjectType.CONTENT, {"anchor": f"swh:1:cnt:{HASH}"}, ValidationError,), ( ObjectType.CONTENT, {"anchor": CoreSWHID(object_type=ObjectType.CONTENT, object_id=_x(HASH))}, ValidationError, ), # path: (ObjectType.CONTENT, {"path": b"/foo"}, f"swh:1:cnt:{HASH};path=/foo",), ( ObjectType.CONTENT, {"path": b"/foo;bar"}, f"swh:1:cnt:{HASH};path=/foo%3Bbar", ), (ObjectType.CONTENT, {"path": "/foo"}, f"swh:1:cnt:{HASH};path=/foo",), ( ObjectType.CONTENT, {"path": "/foo;bar"}, f"swh:1:cnt:{HASH};path=/foo%3Bbar", ), (ObjectType.CONTENT, {"path": 42}, Exception), # lines: (ObjectType.CONTENT, {"lines": (42, None)}, f"swh:1:cnt:{HASH};lines=42",), (ObjectType.CONTENT, {"lines": (21, 42)}, f"swh:1:cnt:{HASH};lines=21-42",), (ObjectType.CONTENT, {"lines": 42}, TypeError,), (ObjectType.CONTENT, {"lines": (None, 42)}, ValueError,), (ObjectType.CONTENT, {"lines": ("42", None)}, ValueError,), ], ) def test_QualifiedSWHID_init(object_type, qualifiers, expected): """Tests validation and converters of qualifiers""" if isinstance(expected, type): assert issubclass(expected, Exception) with pytest.raises(expected): QualifiedSWHID(object_type=object_type, object_id=_x(HASH), **qualifiers) else: assert isinstance(expected, str) swhid = QualifiedSWHID( object_type=object_type, object_id=_x(HASH), **qualifiers ) # Check the build object has the right serialization assert expected == str(swhid) # Check the internal state of the object is the same as if parsed from a string assert QualifiedSWHID.from_string(expected) == swhid def test_QualifiedSWHID_hash(): object_id = _x("94a9ed024d3859793618152ea559a168bbcbb5e2") assert hash( QualifiedSWHID(object_type=ObjectType.DIRECTORY, object_id=object_id) ) == hash(QualifiedSWHID(object_type=ObjectType.DIRECTORY, object_id=object_id)) assert hash( QualifiedSWHID( object_type=ObjectType.DIRECTORY, object_id=object_id, **dummy_qualifiers, ) ) == hash( QualifiedSWHID( object_type=ObjectType.DIRECTORY, object_id=object_id, **dummy_qualifiers, ) ) # Different order of the dictionary, so the underlying order of the tuple in # ImmutableDict is different. assert hash( QualifiedSWHID( object_type=ObjectType.DIRECTORY, object_id=object_id, origin="https://example.com", lines=(42, None), ) ) == hash( QualifiedSWHID( object_type=ObjectType.DIRECTORY, object_id=object_id, lines=(42, None), origin="https://example.com", ) ) def test_QualifiedSWHID_eq(): object_id = _x("94a9ed024d3859793618152ea559a168bbcbb5e2") assert QualifiedSWHID( object_type=ObjectType.DIRECTORY, object_id=object_id ) == QualifiedSWHID(object_type=ObjectType.DIRECTORY, object_id=object_id) assert QualifiedSWHID( object_type=ObjectType.DIRECTORY, object_id=object_id, **dummy_qualifiers, ) == QualifiedSWHID( object_type=ObjectType.DIRECTORY, object_id=object_id, **dummy_qualifiers, ) assert QualifiedSWHID( object_type=ObjectType.DIRECTORY, object_id=object_id, **dummy_qualifiers, ) == QualifiedSWHID( object_type=ObjectType.DIRECTORY, object_id=object_id, **dummy_qualifiers, ) QUALIFIED_SWHIDS = [ # origin: ( f"swh:1:cnt:{HASH};origin=https://github.com/python/cpython", QualifiedSWHID( object_type=ObjectType.CONTENT, object_id=_x(HASH), origin="https://github.com/python/cpython", ), ), ( f"swh:1:cnt:{HASH};origin=https://example.org/foo%3Bbar%25baz", QualifiedSWHID( object_type=ObjectType.CONTENT, object_id=_x(HASH), origin="https://example.org/foo%3Bbar%25baz", ), ), ( f"swh:1:cnt:{HASH};origin=https://example.org?project=test", QualifiedSWHID( object_type=ObjectType.CONTENT, object_id=_x(HASH), origin="https://example.org?project=test", ), ), # visit: ( f"swh:1:cnt:{HASH};visit=swh:1:snp:{HASH}", QualifiedSWHID( object_type=ObjectType.CONTENT, object_id=_x(HASH), visit=CoreSWHID(object_type=ObjectType.SNAPSHOT, object_id=_x(HASH)), ), ), (f"swh:1:cnt:{HASH};visit=swh:1:rel:{HASH}", None,), # anchor: ( f"swh:1:cnt:{HASH};anchor=swh:1:dir:{HASH}", QualifiedSWHID( object_type=ObjectType.CONTENT, object_id=_x(HASH), anchor=CoreSWHID(object_type=ObjectType.DIRECTORY, object_id=_x(HASH)), ), ), ( f"swh:1:cnt:{HASH};anchor=swh:1:rev:{HASH}", QualifiedSWHID( object_type=ObjectType.CONTENT, object_id=_x(HASH), anchor=CoreSWHID(object_type=ObjectType.REVISION, object_id=_x(HASH)), ), ), ( f"swh:1:cnt:{HASH};anchor=swh:1:cnt:{HASH}", None, # 'cnt' is not valid in anchor ), ( f"swh:1:cnt:{HASH};anchor=swh:1:ori:{HASH}", None, # 'ori' is not valid in a CoreSWHID ), # path: ( f"swh:1:cnt:{HASH};path=/foo", QualifiedSWHID( object_type=ObjectType.CONTENT, object_id=_x(HASH), path=b"/foo" ), ), ( f"swh:1:cnt:{HASH};path=/foo%3Bbar", QualifiedSWHID( object_type=ObjectType.CONTENT, object_id=_x(HASH), path=b"/foo;bar" ), ), ( f"swh:1:cnt:{HASH};path=/foo%25bar", QualifiedSWHID( object_type=ObjectType.CONTENT, object_id=_x(HASH), path=b"/foo%bar" ), ), ( f"swh:1:cnt:{HASH};path=/foo/bar%3Dbaz", QualifiedSWHID( object_type=ObjectType.CONTENT, object_id=_x(HASH), path=b"/foo/bar=baz" ), ), # lines ( f"swh:1:cnt:{HASH};lines=1-18", QualifiedSWHID( object_type=ObjectType.CONTENT, object_id=_x(HASH), lines=(1, 18), ), ), ( f"swh:1:cnt:{HASH};lines=18", QualifiedSWHID( object_type=ObjectType.CONTENT, object_id=_x(HASH), lines=(18, None), ), ), (f"swh:1:cnt:{HASH};lines=", None,), (f"swh:1:cnt:{HASH};lines=aa", None,), (f"swh:1:cnt:{HASH};lines=18-aa", None,), ] @pytest.mark.parametrize("string,parsed", QUALIFIED_SWHIDS) def test_QualifiedSWHID_parse_serialize_qualifiers(string, parsed): """Tests parsing and serializing valid SWHIDs with the various SWHID classes.""" if parsed is None: with pytest.raises(ValidationError): print(repr(QualifiedSWHID.from_string(string))) else: assert QualifiedSWHID.from_string(string) == parsed assert str(parsed) == string def test_QualifiedSWHID_serialize_origin(): """Checks that semicolon in origins are escaped.""" string = f"swh:1:cnt:{HASH};origin=https://example.org/foo%3Bbar%25baz" swhid = QualifiedSWHID( object_type=ObjectType.CONTENT, object_id=_x(HASH), origin="https://example.org/foo;bar%25baz", ) assert str(swhid) == string def test_QualifiedSWHID_attributes(): """Checks the set of QualifiedSWHID attributes match the SWHID_QUALIFIERS constant.""" assert set(attr.fields_dict(QualifiedSWHID)) == { "namespace", "scheme_version", "object_type", "object_id", *SWHID_QUALIFIERS, } @pytest.mark.parametrize( "ns,version,type,id", [ ("foo", 1, ObjectType.CONTENT, "abc8bc9d7a6bcf6db04f476d29314f157507d505"), ("swh", 2, ObjectType.CONTENT, "def8bc9d7a6bcf6db04f476d29314f157507d505"), ("swh", 1, ObjectType.DIRECTORY, "aaaa"), ], ) def test_CoreSWHID_validation_error(ns, version, type, id): with pytest.raises(ValidationError): CoreSWHID( namespace=ns, scheme_version=version, object_type=type, object_id=_x(id), ) def test_CoreSWHID_hash(): object_id = _x("94a9ed024d3859793618152ea559a168bbcbb5e2") assert hash( CoreSWHID(object_type=ObjectType.DIRECTORY, object_id=object_id) ) == hash(CoreSWHID(object_type=ObjectType.DIRECTORY, object_id=object_id)) assert hash( CoreSWHID(object_type=ObjectType.DIRECTORY, object_id=object_id,) ) == hash(CoreSWHID(object_type=ObjectType.DIRECTORY, object_id=object_id,)) # Different order of the dictionary, so the underlying order of the tuple in # ImmutableDict is different. assert hash( CoreSWHID(object_type=ObjectType.DIRECTORY, object_id=object_id,) ) == hash(CoreSWHID(object_type=ObjectType.DIRECTORY, object_id=object_id,)) def test_CoreSWHID_eq(): object_id = _x("94a9ed024d3859793618152ea559a168bbcbb5e2") assert CoreSWHID( object_type=ObjectType.DIRECTORY, object_id=object_id ) == CoreSWHID(object_type=ObjectType.DIRECTORY, object_id=object_id) assert CoreSWHID( object_type=ObjectType.DIRECTORY, object_id=object_id, ) == CoreSWHID(object_type=ObjectType.DIRECTORY, object_id=object_id,) assert CoreSWHID( object_type=ObjectType.DIRECTORY, object_id=object_id, ) == CoreSWHID(object_type=ObjectType.DIRECTORY, object_id=object_id,) @pytest.mark.parametrize( "ns,version,type,id", [ ( "foo", 1, ExtendedObjectType.CONTENT, "abc8bc9d7a6bcf6db04f476d29314f157507d505", ), ( "swh", 2, ExtendedObjectType.CONTENT, "def8bc9d7a6bcf6db04f476d29314f157507d505", ), ("swh", 1, ExtendedObjectType.DIRECTORY, "aaaa"), ], ) def test_ExtendedSWHID_validation_error(ns, version, type, id): with pytest.raises(ValidationError): ExtendedSWHID( namespace=ns, scheme_version=version, object_type=type, object_id=_x(id), ) def test_ExtendedSWHID_hash(): object_id = _x("94a9ed024d3859793618152ea559a168bbcbb5e2") assert hash( ExtendedSWHID(object_type=ExtendedObjectType.DIRECTORY, object_id=object_id) ) == hash( ExtendedSWHID(object_type=ExtendedObjectType.DIRECTORY, object_id=object_id) ) assert hash( ExtendedSWHID(object_type=ExtendedObjectType.DIRECTORY, object_id=object_id,) ) == hash( ExtendedSWHID(object_type=ExtendedObjectType.DIRECTORY, object_id=object_id,) ) # Different order of the dictionary, so the underlying order of the tuple in # ImmutableDict is different. assert hash( ExtendedSWHID(object_type=ExtendedObjectType.DIRECTORY, object_id=object_id,) ) == hash( ExtendedSWHID(object_type=ExtendedObjectType.DIRECTORY, object_id=object_id,) ) def test_ExtendedSWHID_eq(): object_id = _x("94a9ed024d3859793618152ea559a168bbcbb5e2") assert ExtendedSWHID( object_type=ExtendedObjectType.DIRECTORY, object_id=object_id ) == ExtendedSWHID(object_type=ExtendedObjectType.DIRECTORY, object_id=object_id) assert ExtendedSWHID( object_type=ExtendedObjectType.DIRECTORY, object_id=object_id, ) == ExtendedSWHID(object_type=ExtendedObjectType.DIRECTORY, object_id=object_id,) assert ExtendedSWHID( object_type=ExtendedObjectType.DIRECTORY, object_id=object_id, ) == ExtendedSWHID(object_type=ExtendedObjectType.DIRECTORY, object_id=object_id,) def test_object_types(): """Checks ExtendedObjectType is a superset of ObjectType""" for member in ObjectType: assert getattr(ExtendedObjectType, member.name).value == member.value diff --git a/swh/model/tests/test_model.py b/swh/model/tests/test_model.py index 5ea401c..caad5e2 100644 --- a/swh/model/tests/test_model.py +++ b/swh/model/tests/test_model.py @@ -1,1178 +1,1191 @@ # Copyright (C) 2019-2020 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 copy import datetime import attr from attrs_strict import AttributeTypeError from hypothesis import given from hypothesis.strategies import binary import pytest from swh.model.hashutil import MultiHash, hash_to_bytes, hash_to_hex import swh.model.hypothesis_strategies as strategies from swh.model.identifiers import ( CoreSWHID, ExtendedSWHID, ObjectType, content_identifier, directory_identifier, origin_identifier, raw_extrinsic_metadata_identifier, release_identifier, revision_identifier, snapshot_identifier, ) from swh.model.model import ( BaseModel, Content, Directory, MetadataAuthority, MetadataAuthorityType, MetadataFetcher, MissingData, Origin, OriginVisit, OriginVisitStatus, Person, RawExtrinsicMetadata, Release, Revision, SkippedContent, Snapshot, Timestamp, TimestampWithTimezone, ) from swh.model.tests.swh_model_data import TEST_OBJECTS from swh.model.tests.test_identifiers import ( + TS_DATETIMES, + TS_TIMEZONES, content_example, directory_example, metadata_example, origin_example, release_example, revision_example, snapshot_example, ) EXAMPLE_HASH = hash_to_bytes("94a9ed024d3859793618152ea559a168bbcbb5e2") @given(strategies.objects()) def test_todict_inverse_fromdict(objtype_and_obj): (obj_type, obj) = objtype_and_obj if obj_type in ("origin", "origin_visit"): return obj_as_dict = obj.to_dict() obj_as_dict_copy = copy.deepcopy(obj_as_dict) # Check the composition of to_dict and from_dict is the identity assert obj == type(obj).from_dict(obj_as_dict) # Check from_dict() does not change the input dict assert obj_as_dict == obj_as_dict_copy # Check the composition of from_dict and to_dict is the identity assert obj_as_dict == type(obj).from_dict(obj_as_dict).to_dict() @pytest.mark.parametrize("object_type, objects", TEST_OBJECTS.items()) def test_swh_model_todict_fromdict(object_type, objects): """checks model objects in swh_model_data are in correct shape""" assert objects for obj in objects: # Check the composition of from_dict and to_dict is the identity obj_as_dict = obj.to_dict() assert obj == type(obj).from_dict(obj_as_dict) assert obj_as_dict == type(obj).from_dict(obj_as_dict).to_dict() def test_unique_key(): url = "http://example.org/" date = datetime.datetime.now(tz=datetime.timezone.utc) id_ = b"42" * 10 assert Origin(url=url).unique_key() == {"url": url} assert OriginVisit(origin=url, date=date, type="git").unique_key() == { "origin": url, "date": str(date), } assert OriginVisitStatus( origin=url, visit=42, date=date, status="created", snapshot=None ).unique_key() == {"origin": url, "visit": "42", "date": str(date),} assert Snapshot.from_dict({**snapshot_example, "id": id_}).unique_key() == id_ assert Release.from_dict({**release_example, "id": id_}).unique_key() == id_ assert Revision.from_dict({**revision_example, "id": id_}).unique_key() == id_ assert Directory.from_dict({**directory_example, "id": id_}).unique_key() == id_ assert ( RawExtrinsicMetadata.from_dict({**metadata_example, "id": id_}).unique_key() == id_ ) cont = Content.from_data(b"foo") assert cont.unique_key().hex() == "0beec7b5ea3f0fdbc95d0dd47f3c5bc275da8a33" kwargs = { **cont.to_dict(), "reason": "foo", "status": "absent", } del kwargs["data"] assert SkippedContent(**kwargs).unique_key() == cont.hashes() # Anonymization @given(strategies.objects()) def test_anonymization(objtype_and_obj): (obj_type, obj) = objtype_and_obj def check_person(p): if p is not None: assert p.name is None assert p.email is None assert len(p.fullname) == 32 anon_obj = obj.anonymize() if obj_type == "person": assert anon_obj is not None check_person(anon_obj) elif obj_type == "release": assert anon_obj is not None check_person(anon_obj.author) elif obj_type == "revision": assert anon_obj is not None check_person(anon_obj.author) check_person(anon_obj.committer) else: assert anon_obj is None # Origin, OriginVisit, OriginVisitStatus @given(strategies.origins()) def test_todict_origins(origin): obj = origin.to_dict() assert "type" not in obj assert type(origin)(url=origin.url) == type(origin).from_dict(obj) @given(strategies.origin_visits()) def test_todict_origin_visits(origin_visit): obj = origin_visit.to_dict() assert origin_visit == type(origin_visit).from_dict(obj) def test_origin_visit_naive_datetime(): with pytest.raises(ValueError, match="must be a timezone-aware datetime"): OriginVisit( origin="http://foo/", date=datetime.datetime.now(), type="git", ) @given(strategies.origin_visit_statuses()) def test_todict_origin_visit_statuses(origin_visit_status): obj = origin_visit_status.to_dict() assert origin_visit_status == type(origin_visit_status).from_dict(obj) def test_origin_visit_status_naive_datetime(): with pytest.raises(ValueError, match="must be a timezone-aware datetime"): OriginVisitStatus( origin="http://foo/", visit=42, date=datetime.datetime.now(), status="ongoing", snapshot=None, ) # Timestamp @given(strategies.timestamps()) def test_timestamps_strategy(timestamp): attr.validate(timestamp) def test_timestamp_seconds(): attr.validate(Timestamp(seconds=0, microseconds=0)) with pytest.raises(AttributeTypeError): Timestamp(seconds="0", microseconds=0) attr.validate(Timestamp(seconds=2 ** 63 - 1, microseconds=0)) with pytest.raises(ValueError): Timestamp(seconds=2 ** 63, microseconds=0) attr.validate(Timestamp(seconds=-(2 ** 63), microseconds=0)) with pytest.raises(ValueError): Timestamp(seconds=-(2 ** 63) - 1, microseconds=0) def test_timestamp_microseconds(): attr.validate(Timestamp(seconds=0, microseconds=0)) with pytest.raises(AttributeTypeError): Timestamp(seconds=0, microseconds="0") attr.validate(Timestamp(seconds=0, microseconds=10 ** 6 - 1)) with pytest.raises(ValueError): Timestamp(seconds=0, microseconds=10 ** 6) with pytest.raises(ValueError): Timestamp(seconds=0, microseconds=-1) def test_timestamp_from_dict(): assert Timestamp.from_dict({"seconds": 10, "microseconds": 5}) with pytest.raises(AttributeTypeError): Timestamp.from_dict({"seconds": "10", "microseconds": 5}) with pytest.raises(AttributeTypeError): Timestamp.from_dict({"seconds": 10, "microseconds": "5"}) with pytest.raises(ValueError): Timestamp.from_dict({"seconds": 0, "microseconds": -1}) Timestamp.from_dict({"seconds": 0, "microseconds": 10 ** 6 - 1}) with pytest.raises(ValueError): Timestamp.from_dict({"seconds": 0, "microseconds": 10 ** 6}) # TimestampWithTimezone def test_timestampwithtimezone(): ts = Timestamp(seconds=0, microseconds=0) tstz = TimestampWithTimezone(timestamp=ts, offset=0, negative_utc=False) attr.validate(tstz) assert tstz.negative_utc is False attr.validate(TimestampWithTimezone(timestamp=ts, offset=10, negative_utc=False)) attr.validate(TimestampWithTimezone(timestamp=ts, offset=-10, negative_utc=False)) tstz = TimestampWithTimezone(timestamp=ts, offset=0, negative_utc=True) attr.validate(tstz) assert tstz.negative_utc is True with pytest.raises(AttributeTypeError): TimestampWithTimezone( timestamp=datetime.datetime.now(), offset=0, negative_utc=False ) with pytest.raises(AttributeTypeError): TimestampWithTimezone(timestamp=ts, offset="0", negative_utc=False) with pytest.raises(AttributeTypeError): TimestampWithTimezone(timestamp=ts, offset=1.0, negative_utc=False) with pytest.raises(AttributeTypeError): TimestampWithTimezone(timestamp=ts, offset=1, negative_utc=0) with pytest.raises(ValueError): TimestampWithTimezone(timestamp=ts, offset=1, negative_utc=True) with pytest.raises(ValueError): TimestampWithTimezone(timestamp=ts, offset=-1, negative_utc=True) def test_timestampwithtimezone_from_datetime(): tz = datetime.timezone(datetime.timedelta(minutes=+60)) date = datetime.datetime(2020, 2, 27, 14, 39, 19, tzinfo=tz) tstz = TimestampWithTimezone.from_datetime(date) assert tstz == TimestampWithTimezone( timestamp=Timestamp(seconds=1582810759, microseconds=0,), offset=60, negative_utc=False, ) def test_timestampwithtimezone_from_naive_datetime(): date = datetime.datetime(2020, 2, 27, 14, 39, 19) with pytest.raises(ValueError, match="datetime without timezone"): TimestampWithTimezone.from_datetime(date) def test_timestampwithtimezone_from_iso8601(): date = "2020-02-27 14:39:19.123456+0100" tstz = TimestampWithTimezone.from_iso8601(date) assert tstz == TimestampWithTimezone( timestamp=Timestamp(seconds=1582810759, microseconds=123456,), offset=60, negative_utc=False, ) def test_timestampwithtimezone_from_iso8601_negative_utc(): date = "2020-02-27 13:39:19-0000" tstz = TimestampWithTimezone.from_iso8601(date) assert tstz == TimestampWithTimezone( timestamp=Timestamp(seconds=1582810759, microseconds=0,), offset=0, negative_utc=True, ) +@pytest.mark.parametrize("date", TS_DATETIMES) +@pytest.mark.parametrize("tz", TS_TIMEZONES) +@pytest.mark.parametrize("microsecond", [0, 1, 10, 100, 1000, 999999]) +def test_timestampwithtimezone_to_datetime(date, tz, microsecond): + date = date.replace(tzinfo=tz, microsecond=microsecond) + tstz = TimestampWithTimezone.from_datetime(date) + + assert tstz.to_datetime() == date + assert tstz.to_datetime().utcoffset() == date.utcoffset() + + def test_person_from_fullname(): """The author should have name, email and fullname filled. """ actual_person = Person.from_fullname(b"tony ") assert actual_person == Person( fullname=b"tony ", name=b"tony", email=b"ynot@dagobah", ) def test_person_from_fullname_no_email(): """The author and fullname should be the same as the input (author). """ actual_person = Person.from_fullname(b"tony") assert actual_person == Person(fullname=b"tony", name=b"tony", email=None,) def test_person_from_fullname_empty_person(): """Empty person has only its fullname filled with the empty byte-string. """ actual_person = Person.from_fullname(b"") assert actual_person == Person(fullname=b"", name=None, email=None,) def test_git_author_line_to_author(): # edge case out of the way with pytest.raises(TypeError): Person.from_fullname(None) tests = { b"a ": Person(name=b"a", email=b"b@c.com", fullname=b"a ",), b"": Person( name=None, email=b"foo@bar.com", fullname=b"", ), b"malformed ': Person( name=b"malformed", email=b'"', ), b"trailing ": Person( name=b"trailing", email=b"sp@c.e", fullname=b"trailing ", ), b"no": Person(name=b"no", email=b"sp@c.e", fullname=b"no",), b" more ": Person( name=b"more", email=b"sp@c.es", fullname=b" more ", ), b" <>": Person(name=None, email=None, fullname=b" <>",), } for person in sorted(tests): expected_person = tests[person] assert expected_person == Person.from_fullname(person) # Content def test_content_get_hash(): hashes = dict(sha1=b"foo", sha1_git=b"bar", sha256=b"baz", blake2s256=b"qux") c = Content(length=42, status="visible", **hashes) for (hash_name, hash_) in hashes.items(): assert c.get_hash(hash_name) == hash_ def test_content_hashes(): hashes = dict(sha1=b"foo", sha1_git=b"bar", sha256=b"baz", blake2s256=b"qux") c = Content(length=42, status="visible", **hashes) assert c.hashes() == hashes def test_content_data(): c = Content( length=42, status="visible", data=b"foo", sha1=b"foo", sha1_git=b"bar", sha256=b"baz", blake2s256=b"qux", ) assert c.with_data() == c def test_content_data_missing(): c = Content( length=42, status="visible", sha1=b"foo", sha1_git=b"bar", sha256=b"baz", blake2s256=b"qux", ) with pytest.raises(MissingData): c.with_data() @given(strategies.present_contents_d()) def test_content_from_dict(content_d): c = Content.from_data(**content_d) assert c assert c.ctime == content_d["ctime"] content_d2 = c.to_dict() c2 = Content.from_dict(content_d2) assert c2.ctime == c.ctime def test_content_from_dict_str_ctime(): # test with ctime as a string n = datetime.datetime(2020, 5, 6, 12, 34, tzinfo=datetime.timezone.utc) content_d = { "ctime": n.isoformat(), "data": b"", "length": 0, "sha1": b"\x00", "sha256": b"\x00", "sha1_git": b"\x00", "blake2s256": b"\x00", } c = Content.from_dict(content_d) assert c.ctime == n def test_content_from_dict_str_naive_ctime(): # test with ctime as a string n = datetime.datetime(2020, 5, 6, 12, 34) content_d = { "ctime": n.isoformat(), "data": b"", "length": 0, "sha1": b"\x00", "sha256": b"\x00", "sha1_git": b"\x00", "blake2s256": b"\x00", } with pytest.raises(ValueError, match="must be a timezone-aware datetime."): Content.from_dict(content_d) @given(binary(max_size=4096)) def test_content_from_data(data): c = Content.from_data(data) assert c.data == data assert c.length == len(data) assert c.status == "visible" for key, value in MultiHash.from_data(data).digest().items(): assert getattr(c, key) == value @given(binary(max_size=4096)) def test_hidden_content_from_data(data): c = Content.from_data(data, status="hidden") assert c.data == data assert c.length == len(data) assert c.status == "hidden" for key, value in MultiHash.from_data(data).digest().items(): assert getattr(c, key) == value def test_content_naive_datetime(): c = Content.from_data(b"foo") with pytest.raises(ValueError, match="must be a timezone-aware datetime"): Content( **c.to_dict(), ctime=datetime.datetime.now(), ) # SkippedContent @given(binary(max_size=4096)) def test_skipped_content_from_data(data): c = SkippedContent.from_data(data, reason="reason") assert c.reason == "reason" assert c.length == len(data) assert c.status == "absent" for key, value in MultiHash.from_data(data).digest().items(): assert getattr(c, key) == value @given(strategies.skipped_contents_d()) def test_skipped_content_origin_is_str(skipped_content_d): assert SkippedContent.from_dict(skipped_content_d) skipped_content_d["origin"] = "http://path/to/origin" assert SkippedContent.from_dict(skipped_content_d) skipped_content_d["origin"] = Origin(url="http://path/to/origin") with pytest.raises(ValueError, match="origin"): SkippedContent.from_dict(skipped_content_d) def test_skipped_content_naive_datetime(): c = SkippedContent.from_data(b"foo", reason="reason") with pytest.raises(ValueError, match="must be a timezone-aware datetime"): SkippedContent( **c.to_dict(), ctime=datetime.datetime.now(), ) # Revision def test_revision_extra_headers_no_headers(): rev_dict = revision_example.copy() rev_dict.pop("id") rev = Revision.from_dict(rev_dict) rev_dict = attr.asdict(rev, recurse=False) rev_model = Revision(**rev_dict) assert rev_model.metadata is None assert rev_model.extra_headers == () rev_dict["metadata"] = { "something": "somewhere", "some other thing": "stranger", } rev_model = Revision(**rev_dict) assert rev_model.metadata == rev_dict["metadata"] assert rev_model.extra_headers == () def test_revision_extra_headers_with_headers(): rev_dict = revision_example.copy() rev_dict.pop("id") rev = Revision.from_dict(rev_dict) rev_dict = attr.asdict(rev, recurse=False) rev_dict["metadata"] = { "something": "somewhere", "some other thing": "stranger", } extra_headers = ( (b"header1", b"value1"), (b"header2", b"42"), (b"header3", b"should I?\x00"), (b"header1", b"again"), ) rev_dict["extra_headers"] = extra_headers rev_model = Revision(**rev_dict) assert "extra_headers" not in rev_model.metadata assert rev_model.extra_headers == extra_headers def test_revision_extra_headers_in_metadata(): rev_dict = revision_example.copy() rev_dict.pop("id") rev = Revision.from_dict(rev_dict) rev_dict = attr.asdict(rev, recurse=False) rev_dict["metadata"] = { "something": "somewhere", "some other thing": "stranger", } extra_headers = ( (b"header1", b"value1"), (b"header2", b"42"), (b"header3", b"should I?\x00"), (b"header1", b"again"), ) # check the bw-compat init hook does the job # ie. extra_headers are given in the metadata field rev_dict["metadata"]["extra_headers"] = extra_headers rev_model = Revision(**rev_dict) assert "extra_headers" not in rev_model.metadata assert rev_model.extra_headers == extra_headers def test_revision_extra_headers_as_lists(): rev_dict = revision_example.copy() rev_dict.pop("id") rev = Revision.from_dict(rev_dict) rev_dict = attr.asdict(rev, recurse=False) rev_dict["metadata"] = {} extra_headers = ( (b"header1", b"value1"), (b"header2", b"42"), (b"header3", b"should I?\x00"), (b"header1", b"again"), ) # check Revision.extra_headers tuplify does the job rev_dict["extra_headers"] = [list(x) for x in extra_headers] rev_model = Revision(**rev_dict) assert "extra_headers" not in rev_model.metadata assert rev_model.extra_headers == extra_headers def test_revision_extra_headers_type_error(): rev_dict = revision_example.copy() rev_dict.pop("id") rev = Revision.from_dict(rev_dict) orig_rev_dict = attr.asdict(rev, recurse=False) orig_rev_dict["metadata"] = { "something": "somewhere", "some other thing": "stranger", } extra_headers = ( ("header1", b"value1"), (b"header2", 42), ("header1", "again"), ) # check headers one at a time # if given as extra_header for extra_header in extra_headers: rev_dict = copy.deepcopy(orig_rev_dict) rev_dict["extra_headers"] = (extra_header,) with pytest.raises(AttributeTypeError): Revision(**rev_dict) # if given as metadata for extra_header in extra_headers: rev_dict = copy.deepcopy(orig_rev_dict) rev_dict["metadata"]["extra_headers"] = (extra_header,) with pytest.raises(AttributeTypeError): Revision(**rev_dict) def test_revision_extra_headers_from_dict(): rev_dict = revision_example.copy() rev_dict.pop("id") rev_model = Revision.from_dict(rev_dict) assert rev_model.metadata is None assert rev_model.extra_headers == () rev_dict["metadata"] = { "something": "somewhere", "some other thing": "stranger", } rev_model = Revision.from_dict(rev_dict) assert rev_model.metadata == rev_dict["metadata"] assert rev_model.extra_headers == () extra_headers = ( (b"header1", b"value1"), (b"header2", b"42"), (b"header3", b"should I?\nmaybe\x00\xff"), (b"header1", b"again"), ) rev_dict["extra_headers"] = extra_headers rev_model = Revision.from_dict(rev_dict) assert "extra_headers" not in rev_model.metadata assert rev_model.extra_headers == extra_headers def test_revision_extra_headers_in_metadata_from_dict(): rev_dict = revision_example.copy() rev_dict.pop("id") rev_dict["metadata"] = { "something": "somewhere", "some other thing": "stranger", } extra_headers = ( (b"header1", b"value1"), (b"header2", b"42"), (b"header3", b"should I?\nmaybe\x00\xff"), (b"header1", b"again"), ) # check the bw-compat init hook does the job rev_dict["metadata"]["extra_headers"] = extra_headers rev_model = Revision.from_dict(rev_dict) assert "extra_headers" not in rev_model.metadata assert rev_model.extra_headers == extra_headers def test_revision_extra_headers_as_lists_from_dict(): rev_dict = revision_example.copy() rev_dict.pop("id") rev_model = Revision.from_dict(rev_dict) rev_dict["metadata"] = { "something": "somewhere", "some other thing": "stranger", } extra_headers = ( (b"header1", b"value1"), (b"header2", b"42"), (b"header3", b"should I?\nmaybe\x00\xff"), (b"header1", b"again"), ) # check Revision.extra_headers converter does the job rev_dict["extra_headers"] = [list(x) for x in extra_headers] rev_model = Revision.from_dict(rev_dict) assert "extra_headers" not in rev_model.metadata assert rev_model.extra_headers == extra_headers # ID computation def test_content_model_id_computation(): cnt_dict = content_example.copy() cnt_id_str = hash_to_hex(content_identifier(cnt_dict)["sha1_git"]) cnt_model = Content.from_data(cnt_dict["data"]) assert str(cnt_model.swhid()) == "swh:1:cnt:" + cnt_id_str def test_directory_model_id_computation(): dir_dict = directory_example.copy() del dir_dict["id"] dir_id_str = directory_identifier(dir_dict) dir_id = hash_to_bytes(dir_id_str) dir_model = Directory.from_dict(dir_dict) assert dir_model.id == dir_id assert str(dir_model.swhid()) == "swh:1:dir:" + dir_id_str def test_revision_model_id_computation(): rev_dict = revision_example.copy() del rev_dict["id"] rev_id_str = revision_identifier(rev_dict) rev_id = hash_to_bytes(rev_id_str) rev_model = Revision.from_dict(rev_dict) assert rev_model.id == rev_id assert str(rev_model.swhid()) == "swh:1:rev:" + rev_id_str def test_revision_model_id_computation_with_no_date(): """We can have revision with date to None """ rev_dict = revision_example.copy() rev_dict["date"] = None rev_dict["committer_date"] = None del rev_dict["id"] rev_id = hash_to_bytes(revision_identifier(rev_dict)) rev_model = Revision.from_dict(rev_dict) assert rev_model.date is None assert rev_model.committer_date is None assert rev_model.id == rev_id def test_release_model_id_computation(): rel_dict = release_example.copy() del rel_dict["id"] rel_id_str = release_identifier(rel_dict) rel_id = hash_to_bytes(rel_id_str) rel_model = Release.from_dict(rel_dict) assert isinstance(rel_model.date, TimestampWithTimezone) assert rel_model.id == hash_to_bytes(rel_id) assert str(rel_model.swhid()) == "swh:1:rel:" + rel_id_str def test_snapshot_model_id_computation(): snp_dict = snapshot_example.copy() del snp_dict["id"] snp_id_str = snapshot_identifier(snp_dict) snp_id = hash_to_bytes(snp_id_str) snp_model = Snapshot.from_dict(snp_dict) assert snp_model.id == snp_id assert str(snp_model.swhid()) == "swh:1:snp:" + snp_id_str def test_origin_model_id_computation(): ori_dict = origin_example.copy() ori_id_str = origin_identifier(ori_dict) ori_model = Origin.from_dict(ori_dict) assert str(ori_model.swhid()) == "swh:1:ori:" + ori_id_str def test_raw_extrinsic_metadata_model_id_computation(): emd_dict = metadata_example.copy() emd_id_str = raw_extrinsic_metadata_identifier(emd_dict) emd_model = RawExtrinsicMetadata.from_dict(emd_dict) assert str(emd_model.swhid()) == "swh:1:emd:" + emd_id_str @given(strategies.objects(split_content=True)) def test_object_type(objtype_and_obj): obj_type, obj = objtype_and_obj assert obj_type == obj.object_type def test_object_type_is_final(): object_types = set() def check_final(cls): if hasattr(cls, "object_type"): assert cls.object_type not in object_types object_types.add(cls.object_type) if cls.__subclasses__(): assert not hasattr(cls, "object_type") for subcls in cls.__subclasses__(): check_final(subcls) check_final(BaseModel) _metadata_authority = MetadataAuthority( type=MetadataAuthorityType.FORGE, url="https://forge.softwareheritage.org", ) _metadata_fetcher = MetadataFetcher(name="test-fetcher", version="0.0.1",) _content_swhid = ExtendedSWHID.from_string( "swh:1:cnt:94a9ed024d3859793618152ea559a168bbcbb5e2" ) _origin_url = "https://forge.softwareheritage.org/source/swh-model.git" _origin_swhid = ExtendedSWHID.from_string( "swh:1:ori:94a9ed024d3859793618152ea559a168bbcbb5e2" ) _dummy_qualifiers = {"origin": "https://example.com", "lines": "42"} _common_metadata_fields = dict( discovery_date=datetime.datetime( 2021, 1, 29, 13, 57, 9, tzinfo=datetime.timezone.utc ), authority=_metadata_authority, fetcher=_metadata_fetcher, format="json", metadata=b'{"origin": "https://example.com", "lines": "42"}', ) def test_metadata_valid(): """Checks valid RawExtrinsicMetadata objects don't raise an error.""" # Simplest case RawExtrinsicMetadata(target=_origin_swhid, **_common_metadata_fields) # Object with an SWHID RawExtrinsicMetadata( target=_content_swhid, **_common_metadata_fields, ) def test_metadata_to_dict(): """Checks valid RawExtrinsicMetadata objects don't raise an error.""" common_fields = { "authority": {"type": "forge", "url": "https://forge.softwareheritage.org"}, "fetcher": {"name": "test-fetcher", "version": "0.0.1",}, "discovery_date": _common_metadata_fields["discovery_date"], "format": "json", "metadata": b'{"origin": "https://example.com", "lines": "42"}', } m = RawExtrinsicMetadata(target=_origin_swhid, **_common_metadata_fields,) assert m.to_dict() == { "target": str(_origin_swhid), "id": b"@j\xc9\x01\xbc\x1e#p*\xf3q9\xa7u\x97\x00\x14\x02xa", **common_fields, } assert RawExtrinsicMetadata.from_dict(m.to_dict()) == m m = RawExtrinsicMetadata(target=_content_swhid, **_common_metadata_fields,) assert m.to_dict() == { "target": "swh:1:cnt:94a9ed024d3859793618152ea559a168bbcbb5e2", "id": b"\xbc\xa3U\xddf\x19U\xc5\xd2\xd7\xdfK\xd7c\x1f\xa8\xfeh\x992", **common_fields, } assert RawExtrinsicMetadata.from_dict(m.to_dict()) == m hash_hex = "6162" * 10 hash_bin = b"ab" * 10 m = RawExtrinsicMetadata( target=_content_swhid, **_common_metadata_fields, origin="https://example.org/", snapshot=CoreSWHID(object_type=ObjectType.SNAPSHOT, object_id=hash_bin), release=CoreSWHID(object_type=ObjectType.RELEASE, object_id=hash_bin), revision=CoreSWHID(object_type=ObjectType.REVISION, object_id=hash_bin), path=b"/foo/bar", directory=CoreSWHID(object_type=ObjectType.DIRECTORY, object_id=hash_bin), ) assert m.to_dict() == { "target": "swh:1:cnt:94a9ed024d3859793618152ea559a168bbcbb5e2", "id": b"\x14l\xb0\x1f\xb9\xc0{)\xc7\x0f\xbd\xc0*,YZ\xf5C\xab\xfc", **common_fields, "origin": "https://example.org/", "snapshot": f"swh:1:snp:{hash_hex}", "release": f"swh:1:rel:{hash_hex}", "revision": f"swh:1:rev:{hash_hex}", "path": b"/foo/bar", "directory": f"swh:1:dir:{hash_hex}", } assert RawExtrinsicMetadata.from_dict(m.to_dict()) == m def test_metadata_invalid_target(): """Checks various invalid values for the 'target' field.""" # SWHID passed as string instead of SWHID with pytest.raises(ValueError, match="target must be.*ExtendedSWHID"): RawExtrinsicMetadata( target="swh:1:cnt:94a9ed024d3859793618152ea559a168bbcbb5e2", **_common_metadata_fields, ) def test_metadata_naive_datetime(): with pytest.raises(ValueError, match="must be a timezone-aware datetime"): RawExtrinsicMetadata( target=_origin_swhid, **{**_common_metadata_fields, "discovery_date": datetime.datetime.now()}, ) def test_metadata_validate_context_origin(): """Checks validation of RawExtrinsicMetadata.origin.""" # Origins can't have an 'origin' context with pytest.raises( ValueError, match="Unexpected 'origin' context for origin object" ): RawExtrinsicMetadata( target=_origin_swhid, origin=_origin_url, **_common_metadata_fields, ) # but all other types can RawExtrinsicMetadata( target=_content_swhid, origin=_origin_url, **_common_metadata_fields, ) # SWHIDs aren't valid origin URLs with pytest.raises(ValueError, match="SWHID used as context origin URL"): RawExtrinsicMetadata( target=_content_swhid, origin="swh:1:cnt:94a9ed024d3859793618152ea559a168bbcbb5e2", **_common_metadata_fields, ) def test_metadata_validate_context_visit(): """Checks validation of RawExtrinsicMetadata.visit.""" # Origins can't have a 'visit' context with pytest.raises( ValueError, match="Unexpected 'visit' context for origin object" ): RawExtrinsicMetadata( target=_origin_swhid, visit=42, **_common_metadata_fields, ) # but all other types can RawExtrinsicMetadata( target=_content_swhid, origin=_origin_url, visit=42, **_common_metadata_fields, ) # Missing 'origin' with pytest.raises(ValueError, match="'origin' context must be set if 'visit' is"): RawExtrinsicMetadata( target=_content_swhid, visit=42, **_common_metadata_fields, ) # visit id must be positive with pytest.raises(ValueError, match="Nonpositive visit id"): RawExtrinsicMetadata( target=_content_swhid, origin=_origin_url, visit=-42, **_common_metadata_fields, ) def test_metadata_validate_context_snapshot(): """Checks validation of RawExtrinsicMetadata.snapshot.""" # Origins can't have a 'snapshot' context with pytest.raises( ValueError, match="Unexpected 'snapshot' context for origin object" ): RawExtrinsicMetadata( target=_origin_swhid, snapshot=CoreSWHID( object_type=ObjectType.SNAPSHOT, object_id=EXAMPLE_HASH, ), **_common_metadata_fields, ) # but content can RawExtrinsicMetadata( target=_content_swhid, snapshot=CoreSWHID(object_type=ObjectType.SNAPSHOT, object_id=EXAMPLE_HASH), **_common_metadata_fields, ) # SWHID type doesn't match the expected type of this context key with pytest.raises( ValueError, match="Expected SWHID type 'snapshot', got 'content'" ): RawExtrinsicMetadata( target=_content_swhid, snapshot=CoreSWHID(object_type=ObjectType.CONTENT, object_id=EXAMPLE_HASH,), **_common_metadata_fields, ) def test_metadata_validate_context_release(): """Checks validation of RawExtrinsicMetadata.release.""" # Origins can't have a 'release' context with pytest.raises( ValueError, match="Unexpected 'release' context for origin object" ): RawExtrinsicMetadata( target=_origin_swhid, release=CoreSWHID(object_type=ObjectType.RELEASE, object_id=EXAMPLE_HASH,), **_common_metadata_fields, ) # but content can RawExtrinsicMetadata( target=_content_swhid, release=CoreSWHID(object_type=ObjectType.RELEASE, object_id=EXAMPLE_HASH), **_common_metadata_fields, ) # SWHID type doesn't match the expected type of this context key with pytest.raises( ValueError, match="Expected SWHID type 'release', got 'content'" ): RawExtrinsicMetadata( target=_content_swhid, release=CoreSWHID(object_type=ObjectType.CONTENT, object_id=EXAMPLE_HASH,), **_common_metadata_fields, ) def test_metadata_validate_context_revision(): """Checks validation of RawExtrinsicMetadata.revision.""" # Origins can't have a 'revision' context with pytest.raises( ValueError, match="Unexpected 'revision' context for origin object" ): RawExtrinsicMetadata( target=_origin_swhid, revision=CoreSWHID( object_type=ObjectType.REVISION, object_id=EXAMPLE_HASH, ), **_common_metadata_fields, ) # but content can RawExtrinsicMetadata( target=_content_swhid, revision=CoreSWHID(object_type=ObjectType.REVISION, object_id=EXAMPLE_HASH), **_common_metadata_fields, ) # SWHID type doesn't match the expected type of this context key with pytest.raises( ValueError, match="Expected SWHID type 'revision', got 'content'" ): RawExtrinsicMetadata( target=_content_swhid, revision=CoreSWHID(object_type=ObjectType.CONTENT, object_id=EXAMPLE_HASH,), **_common_metadata_fields, ) def test_metadata_validate_context_path(): """Checks validation of RawExtrinsicMetadata.path.""" # Origins can't have a 'path' context with pytest.raises(ValueError, match="Unexpected 'path' context for origin object"): RawExtrinsicMetadata( target=_origin_swhid, path=b"/foo/bar", **_common_metadata_fields, ) # but content can RawExtrinsicMetadata( target=_content_swhid, path=b"/foo/bar", **_common_metadata_fields, ) def test_metadata_validate_context_directory(): """Checks validation of RawExtrinsicMetadata.directory.""" # Origins can't have a 'directory' context with pytest.raises( ValueError, match="Unexpected 'directory' context for origin object" ): RawExtrinsicMetadata( target=_origin_swhid, directory=CoreSWHID( object_type=ObjectType.DIRECTORY, object_id=EXAMPLE_HASH, ), **_common_metadata_fields, ) # but content can RawExtrinsicMetadata( target=_content_swhid, directory=CoreSWHID(object_type=ObjectType.DIRECTORY, object_id=EXAMPLE_HASH,), **_common_metadata_fields, ) # SWHID type doesn't match the expected type of this context key with pytest.raises( ValueError, match="Expected SWHID type 'directory', got 'content'" ): RawExtrinsicMetadata( target=_content_swhid, directory=CoreSWHID( object_type=ObjectType.CONTENT, object_id=EXAMPLE_HASH, ), **_common_metadata_fields, ) def test_metadata_normalize_discovery_date(): fields_copy = {**_common_metadata_fields} truncated_date = fields_copy.pop("discovery_date") assert truncated_date.microsecond == 0 # Check for TypeError on disabled object type: we removed attrs_strict's # type_validator with pytest.raises(TypeError): RawExtrinsicMetadata( target=_content_swhid, discovery_date="not a datetime", **fields_copy ) # Check for truncation to integral second date_with_us = truncated_date.replace(microsecond=42) md = RawExtrinsicMetadata( target=_content_swhid, discovery_date=date_with_us, **fields_copy, ) assert md.discovery_date == truncated_date assert md.discovery_date.tzinfo == datetime.timezone.utc # Check that the timezone gets normalized. Timezones can be offset by a # non-integral number of seconds, so we need to handle that. timezone = datetime.timezone(offset=datetime.timedelta(hours=2)) date_with_tz = truncated_date.astimezone(timezone) assert date_with_tz.tzinfo != datetime.timezone.utc md = RawExtrinsicMetadata( target=_content_swhid, discovery_date=date_with_tz, **fields_copy, ) assert md.discovery_date == truncated_date assert md.discovery_date.tzinfo == datetime.timezone.utc