diff --git a/bin/swh-revhash b/bin/swh-revhash index 56b587d..ad76f9e 100755 --- a/bin/swh-revhash +++ b/bin/swh-revhash @@ -1,31 +1,29 @@ #!/usr/bin/env python3 # Use: # swh-revhash 'tree 4b825dc642cb6eb9a060e54bf8d69288fbee4904\nparent 22c0fa5195a53f2e733ec75a9b6e9d1624a8b771\nauthor seanius 1138341044 +0000\ncommitter seanius 1138341044 +0000\n\nmaking dir structure...\n' # noqa # output: 17a631d474f49bbebfdf3d885dcde470d7faafd7 # To compare with git: # git-revhash 'tree 4b825dc642cb6eb9a060e54bf8d69288fbee4904\nparent 22c0fa5195a53f2e733ec75a9b6e9d1624a8b771\nauthor seanius 1138341044 +0000\ncommitter seanius 1138341044 +0000\n\nmaking dir structure...\n' # noqa # output: 17a631d474f49bbebfdf3d885dcde470d7faafd7 import sys from swh.model import hashutil, identifiers def revhash(revision_raw): - """Compute the revision hash. - - """ + """Compute the revision hash.""" # HACK: string have somehow their \n expanded to \\n if b"\\n" in revision_raw: revision_raw = revision_raw.replace(b"\\n", b"\n") h = hashutil.hash_git_data(revision_raw, "commit") return identifiers.identifier_to_str(h) if __name__ == "__main__": revision_raw = sys.argv[1].encode("utf-8") print(revhash(revision_raw)) diff --git a/swh/model/cli.py b/swh/model/cli.py index 583d5c1..6220661 100644 --- a/swh/model/cli.py +++ b/swh/model/cli.py @@ -1,307 +1,310 @@ # 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, Iterable, 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.swhids import CoreSWHID 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.swhids.CoreSWHID` instances """ + :class:`swh.model.swhids.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 object = Content.from_file(path=path) return object.swhid() def swhid_of_file_content(data) -> CoreSWHID: from swh.model.from_disk import Content object = Content.from_bytes(mode=644, data=data) return object.swhid() def model_of_dir(path: bytes, exclude_patterns: Iterable[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 ) return Directory.from_disk(path=path, dir_filter=dir_filter) def swhid_of_dir(path: bytes, exclude_patterns: Iterable[bytes] = None) -> CoreSWHID: obj = model_of_dir(path, exclude_patterns) return obj.swhid() def swhid_of_origin(url): from swh.model.model import Origin return Origin(url).swhid() 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.model import Snapshot 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 Snapshot.from_dict(snapshot).swhid() def identify_object( obj_type: str, follow_symlinks: bool, exclude_patterns: Iterable[bytes], 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, 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", + "-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, recursive, ): """Compute the Software Heritage persistent identifier (SWHID) for the given source code object(s). For more details about SWHIDs see: https://docs.softwareheritage.org/devel/swh-model/persistent-identifiers.html Tip: you can pass "-" to identify the content of standard input. Examples:: $ 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 $ git clone --mirror https://forge.softwareheritage.org/source/helloworld.git $ swh identify --type snapshot helloworld.git/ swh:1:snp:510aa88bdc517345d258c1fc2babcd0e1f905e93 helloworld.git """ from functools import partial import logging if exclude_patterns: exclude_patterns = set(pattern.encode() for pattern in exclude_patterns) if verify and len(objects) != 1: raise click.BadParameter("verification requires a single object") 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(sub_obj.swhid()) 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) 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) if __name__ == "__main__": identify() diff --git a/swh/model/fields/compound.py b/swh/model/fields/compound.py index 90b4685..dcdbfd6 100644 --- a/swh/model/fields/compound.py +++ b/swh/model/fields/compound.py @@ -1,125 +1,128 @@ # Copyright (C) 2015 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 collections import defaultdict import itertools from ..exceptions import NON_FIELD_ERRORS, ValidationError def validate_against_schema(model, schema, value): """Validate a value for the given model against the given schema. Args: model: the name of the model schema: the schema to validate against value: the value to validate Returns: True if the value is correct against the schema Raises: ValidationError if the value does not validate against the schema """ if not isinstance(value, dict): raise ValidationError( "Unexpected type %(type)s for %(model)s, expected dict", - params={"model": model, "type": value.__class__.__name__,}, + params={ + "model": model, + "type": value.__class__.__name__, + }, code="model-unexpected-type", ) errors = defaultdict(list) for key, (mandatory, validators) in itertools.chain( ((k, v) for k, v in schema.items() if k != NON_FIELD_ERRORS), [(NON_FIELD_ERRORS, (False, schema.get(NON_FIELD_ERRORS, [])))], ): if not validators: continue if not isinstance(validators, list): validators = [validators] validated_value = value if key != NON_FIELD_ERRORS: try: validated_value = value[key] except KeyError: if mandatory: errors[key].append( ValidationError( "Field %(field)s is mandatory", params={"field": key}, code="model-field-mandatory", ) ) continue else: if errors: # Don't validate the whole object if some fields are broken continue for validator in validators: try: valid = validator(validated_value) except ValidationError as e: errors[key].append(e) else: if not valid: errdata = { "validator": validator.__name__, } if key == NON_FIELD_ERRORS: errmsg = ( "Validation of model %(model)s failed in " "%(validator)s" ) errdata["model"] = model errcode = "model-validation-failed" else: errmsg = ( "Validation of field %(field)s failed in " "%(validator)s" ) errdata["field"] = key errcode = "field-validation-failed" errors[key].append( ValidationError(errmsg, params=errdata, code=errcode) ) if errors: raise ValidationError(dict(errors)) return True def validate_all_keys(value, keys): """Validate that all the given keys are present in value""" missing_keys = set(keys) - set(value) if missing_keys: missing_fields = ", ".join(sorted(missing_keys)) raise ValidationError( "Missing mandatory fields %(missing_fields)s", params={"missing_fields": missing_fields}, code="missing-mandatory-field", ) return True def validate_any_key(value, keys): """Validate that any of the given keys is present in value""" present_keys = set(keys) & set(value) if not present_keys: missing_fields = ", ".join(sorted(keys)) raise ValidationError( "Must contain one of the alternative fields %(missing_fields)s", params={"missing_fields": missing_fields}, code="missing-alternative-field", ) return True diff --git a/swh/model/fields/hashes.py b/swh/model/fields/hashes.py index 9b5ee4a..46c94ec 100644 --- a/swh/model/fields/hashes.py +++ b/swh/model/fields/hashes.py @@ -1,116 +1,118 @@ # Copyright (C) 2015 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 string from ..exceptions import ValidationError def validate_hash(value, hash_type): """Validate that the given value represents a hash of the given hash_type. Args: value: the value to check hash_type: the type of hash the value is representing Returns: True if the hash validates Raises: ValueError if the hash does not validate """ hash_lengths = { "sha1": 20, "sha1_git": 20, "sha256": 32, } hex_digits = set(string.hexdigits) if hash_type not in hash_lengths: raise ValidationError( "Unexpected hash type %(hash_type)s, expected one of" " %(hash_types)s", params={ "hash_type": hash_type, "hash_types": ", ".join(sorted(hash_lengths)), }, code="unexpected-hash-type", ) if isinstance(value, str): errors = [] extra_chars = set(value) - hex_digits if extra_chars: errors.append( ValidationError( "Unexpected characters `%(unexpected_chars)s' for hash " "type %(hash_type)s", params={ "unexpected_chars": ", ".join(sorted(extra_chars)), "hash_type": hash_type, }, code="unexpected-hash-contents", ) ) length = len(value) expected_length = 2 * hash_lengths[hash_type] if length != expected_length: errors.append( ValidationError( "Unexpected length %(length)d for hash type " "%(hash_type)s, expected %(expected_length)d", params={ "length": length, "expected_length": expected_length, "hash_type": hash_type, }, code="unexpected-hash-length", ) ) if errors: raise ValidationError(errors) return True if isinstance(value, bytes): length = len(value) expected_length = hash_lengths[hash_type] if length != expected_length: raise ValidationError( "Unexpected length %(length)d for hash type " "%(hash_type)s, expected %(expected_length)d", params={ "length": length, "expected_length": expected_length, "hash_type": hash_type, }, code="unexpected-hash-length", ) return True raise ValidationError( "Unexpected type %(type)s for hash, expected str or bytes", - params={"type": value.__class__.__name__,}, + params={ + "type": value.__class__.__name__, + }, code="unexpected-hash-value-type", ) def validate_sha1(sha1): """Validate that sha1 is a valid sha1 hash""" return validate_hash(sha1, "sha1") def validate_sha1_git(sha1_git): """Validate that sha1_git is a valid sha1_git hash""" return validate_hash(sha1_git, "sha1_git") def validate_sha256(sha256): """Validate that sha256 is a valid sha256 hash""" return validate_hash(sha256, "sha256") diff --git a/swh/model/fields/simple.py b/swh/model/fields/simple.py index 98fcc11..71fe1d7 100644 --- a/swh/model/fields/simple.py +++ b/swh/model/fields/simple.py @@ -1,79 +1,82 @@ # Copyright (C) 2015 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 numbers from ..exceptions import ValidationError def validate_type(value, type): """Validate that value is an integer""" if not isinstance(value, type): if isinstance(type, tuple): typestr = "one of %s" % ", ".join(typ.__name__ for typ in type) else: typestr = type.__name__ raise ValidationError( "Unexpected type %(type)s, expected %(expected_type)s", - params={"type": value.__class__.__name__, "expected_type": typestr,}, + params={ + "type": value.__class__.__name__, + "expected_type": typestr, + }, code="unexpected-type", ) return True def validate_int(value): """Validate that the given value is an int""" return validate_type(value, numbers.Integral) def validate_str(value): """Validate that the given value is a string""" return validate_type(value, str) def validate_bytes(value): """Validate that the given value is a bytes object""" return validate_type(value, bytes) def validate_datetime(value): """Validate that the given value is either a datetime, or a numeric number of seconds since the UNIX epoch.""" errors = [] try: validate_type(value, (datetime.datetime, numbers.Real)) except ValidationError as e: errors.append(e) if isinstance(value, datetime.datetime) and value.tzinfo is None: errors.append( ValidationError( "Datetimes must be timezone-aware in swh", code="datetime-without-tzinfo", ) ) if errors: raise ValidationError(errors) return True def validate_enum(value, expected_values): """Validate that value is contained in expected_values""" if value not in expected_values: raise ValidationError( "Unexpected value %(value)s, expected one of %(expected_values)s", params={ "value": value, "expected_values": ", ".join(sorted(expected_values)), }, code="unexpected-value", ) return True diff --git a/swh/model/from_disk.py b/swh/model/from_disk.py index 43a9c71..9ef7afa 100644 --- a/swh/model/from_disk.py +++ b/swh/model/from_disk.py @@ -1,563 +1,561 @@ # 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 """Conversion from filesystem tree to SWH objects. This module allows reading a tree of directories and files from a local filesystem, and convert them to in-memory data structures, which can then be exported to SWH data model objects, as defined in :mod:`swh.model.model`. """ 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 .git_objects import directory_entry_sort_key from .hashutil import MultiHash, hash_to_hex from .merkle import MerkleLeaf, MerkleNode from .swhids import CoreSWHID, ObjectType @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 swhid(self) -> CoreSWHID: - """Return node identifier as a SWHID - """ + """Return node identifier as a SWHID""" return CoreSWHID(object_type=ObjectType.CONTENT, object_id=self.hash) def __repr__(self): return "Content(id=%s)" % hash_to_hex(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. + 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 + Args: + root_path (bytes): path to the root directory + patterns (list of byte): patterns to match - Yields: - an SRE_Pattern object + 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), "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 :func:`swh.model.git_objects.directory_git_object` 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 swhid(self) -> CoreSWHID: - """Return node identifier as a SWHID - """ + """Return node identifier as a SWHID""" return CoreSWHID(object_type=ObjectType.DIRECTORY, object_id=self.hash) def compute_hash(self): return model.Directory.from_dict({"entries": self.entries}).id 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 __contains__(self, key): if b"/" not in key: return super().__contains__(key) else: key1, key2 = key.split(b"/", 1) return super().__contains__(key1) and self[key1].__contains__(key2) def __repr__(self): return "Directory(id=%s, entries=[%s])" % ( hash_to_hex(self.hash), ", ".join(str(entry) for entry in self), ) diff --git a/swh/model/git_objects.py b/swh/model/git_objects.py index 7b36da6..d0f7bf8 100644 --- a/swh/model/git_objects.py +++ b/swh/model/git_objects.py @@ -1,626 +1,638 @@ # 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 """ Converts SWH model objects to git(-like) objects Most of the functions in this module take as argument an object from :mod:`swh.model.model`, and format it like a git object. They are the inverse functions of those in :mod:`swh.loader.git.converters`, but with extensions, as SWH's model is a superset of Git's: * extensions of existing types (eg. revision/commit and release/tag dates can be expressed with precision up to milliseconds, to support formatting Mercurial objects) * new types, for SWH's specific needs (:class:`swh.model.model.RawExtrinsicMetadata` and :class:`swh.model.model.ExtID`) * support for somewhat corrupted git objects that we need to reproduce This is used for two purposes: * Format manifests that can be hashed to produce :ref:`intrinsic identifiers ` * Write git objects to reproduce git repositories that were ingested in the archive. """ from __future__ import annotations import datetime from functools import lru_cache from typing import Dict, Iterable, List, Optional, Tuple, Union, cast import warnings from . import model from .collections import ImmutableDict from .hashutil import git_object_header, hash_to_bytehex def directory_entry_sort_key(entry: model.DirectoryEntry): """The sorting key for tree entries""" if isinstance(entry, dict): # For backward compatibility entry = model.DirectoryEntry.from_dict(entry) 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 canonical 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 format_date(date: model.Timestamp) -> bytes: """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 isinstance(date, dict): # For backward compatibility date = model.Timestamp.from_dict(date) if not date.microseconds: return str(date.seconds).encode() else: float_value = "%d.%06d" % (date.seconds, date.microseconds) return float_value.rstrip("0").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 else: return model.TimestampWithTimezone.from_dict(time_representation).to_dict() def directory_git_object(directory: Union[Dict, model.Directory]) -> bytes: """Formats a directory as a git tree. 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) """ if isinstance(directory, dict): # For backward compatibility warnings.warn( "directory_git_object's argument should be a swh.model.model.Directory " "object.", DeprecationWarning, stacklevel=2, ) directory = model.Directory.from_dict(directory) directory = cast(model.Directory, directory) 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", entry.target,] + [ + _perms_to_bytes(entry.perms), + b"\x20", + entry.name, + b"\x00", + entry.target, + ] ) return format_git_object_from_parts("tree", components) 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: model.Person, date_offset: Optional[model.TimestampWithTimezone] ) -> 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. Returns: the byte string containing the authorship data """ ret = [author.fullname] if date_offset is not None: date_f = format_date(date_offset.timestamp) ret.extend([b" ", date_f, b" ", date_offset.offset_bytes]) return b"".join(ret) def revision_git_object(revision: Union[Dict, model.Revision]) -> bytes: """Formats a revision as a git tree. 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 using the :attr:`Person.fullname` attribute only. 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. """ if isinstance(revision, dict): # For backward compatibility warnings.warn( "revision_git_object's argument should be a swh.model.model.Revision " "object.", DeprecationWarning, stacklevel=2, ) revision = model.Revision.from_dict(revision) revision = cast(model.Revision, revision) headers = [(b"tree", hash_to_bytehex(revision.directory))] for parent in revision.parents: if parent: headers.append((b"parent", hash_to_bytehex(parent))) if revision.author is not None: headers.append((b"author", format_author_data(revision.author, revision.date))) if revision.committer is not None: headers.append( ( b"committer", format_author_data(revision.committer, revision.committer_date), ) ) # Handle extra headers metadata = revision.metadata or ImmutableDict() extra_headers = revision.extra_headers or () 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: model.ObjectType) -> bytes: """Convert a software heritage target type to a git object type""" return { model.ObjectType.CONTENT: b"blob", model.ObjectType.DIRECTORY: b"tree", model.ObjectType.REVISION: b"commit", model.ObjectType.RELEASE: b"tag", model.ObjectType.SNAPSHOT: b"refs", }[target_type] def release_git_object(release: Union[Dict, model.Release]) -> bytes: if isinstance(release, dict): # For backward compatibility warnings.warn( "release_git_object's argument should be a swh.model.model.Directory " "object.", DeprecationWarning, stacklevel=2, ) release = model.Release.from_dict(release) release = cast(model.Release, release) headers = [ (b"object", hash_to_bytehex(release.target)), (b"type", target_type_to_git(release.target_type)), (b"tag", release.name), ] if release.author is not None: headers.append((b"tagger", format_author_data(release.author, release.date))) return format_git_object_from_headers("tag", headers, release.message) def snapshot_git_object(snapshot: Union[Dict, model.Snapshot]) -> bytes: """Formats a snapshot as a git-like object. 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. """ if isinstance(snapshot, dict): # For backward compatibility warnings.warn( "snapshot_git_object's argument should be a swh.model.model.Snapshot " "object.", DeprecationWarning, stacklevel=2, ) snapshot = model.Snapshot.from_dict(snapshot) snapshot = cast(model.Snapshot, snapshot) unresolved = [] lines = [] for name, target in sorted(snapshot.branches.items()): if not target: target_type = b"dangling" target_id = b"" elif target.target_type == model.TargetType.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.value.encode() target_id = target.target lines.extend( [ target_type, b"\x20", name, b"\x00", ("%d:" % len(target_id)).encode(), target_id, ] ) if 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 raw_extrinsic_metadata_git_object( metadata: Union[Dict, model.RawExtrinsicMetadata] ) -> bytes: """Formats RawExtrinsicMetadata as a git-like 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. """ if isinstance(metadata, dict): # For backward compatibility warnings.warn( "raw_extrinsic_metadata_git_object's argument should be a " "swh.model.model.RawExtrinsicMetadata object.", DeprecationWarning, stacklevel=2, ) metadata = model.RawExtrinsicMetadata.from_dict(metadata) metadata = cast(model.RawExtrinsicMetadata, metadata) # 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.value} {metadata.authority.url}".encode(), ), - (b"fetcher", f"{metadata.fetcher.name} {metadata.fetcher.version}".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 getattr(metadata, key, None) is not None: value: bytes if key == "path": value = getattr(metadata, key) else: value = str(getattr(metadata, key)).encode() headers.append((key.encode("ascii"), value)) return format_git_object_from_headers( "raw_extrinsic_metadata", headers, metadata.metadata ) def extid_git_object(extid: model.ExtID) -> bytes: """Formats an extid as a gi-like 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_version $Str] 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. The extid_version line is only generated if the version is non-zero. """ headers = [ (b"extid_type", extid.extid_type.encode("ascii")), ] extid_version = extid.extid_version if extid_version != 0: headers.append((b"extid_version", str(extid_version).encode("ascii"))) headers.extend( - [(b"extid", extid.extid), (b"target", str(extid.target).encode("ascii")),] + [ + (b"extid", extid.extid), + (b"target", str(extid.target).encode("ascii")), + ] ) return format_git_object_from_headers("extid", headers) diff --git a/swh/model/hashutil.py b/swh/model/hashutil.py index 8740787..106e7c0 100644 --- a/swh/model/hashutil.py +++ b/swh/model/hashutil.py @@ -1,353 +1,351 @@ # Copyright (C) 2015-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information """Module in charge of hashing function definitions. This is the base module use to compute swh's hashes. Only a subset of hashing algorithms is supported as defined in the ALGORITHMS set. Any provided algorithms not in that list will result in a ValueError explaining the error. This module defines a MultiHash class to ease the softwareheritage hashing algorithms computation. This allows to compute hashes from file object, path, data using a similar interface as what the standard hashlib module provides. Basic usage examples: - file object: MultiHash.from_file( file_object, hash_names=DEFAULT_ALGORITHMS).digest() - path (filepath): MultiHash.from_path(b'foo').hexdigest() - data (bytes): MultiHash.from_data(b'foo').bytehexdigest() "Complex" usage, defining a swh hashlib instance first: - To compute length, integrate the length to the set of algorithms to compute, for example: .. code-block:: python h = MultiHash(hash_names=set({'length'}).union(DEFAULT_ALGORITHMS)) with open(filepath, 'rb') as f: h.update(f.read(HASH_BLOCK_SIZE)) hashes = h.digest() # returns a dict of {hash_algo_name: hash_in_bytes} - Write alongside computing hashing algorithms (from a stream), example: .. code-block:: python h = MultiHash(length=length) with open(filepath, 'wb') as f: for chunk in r.iter_content(): # r a stream of sort h.update(chunk) f.write(chunk) hashes = h.hexdigest() # returns a dict of {hash_algo_name: hash_in_hex} """ import binascii import functools import hashlib from io import BytesIO import os from typing import Callable, Dict, Optional ALGORITHMS = set(["sha1", "sha256", "sha1_git", "blake2s256", "blake2b512", "md5"]) """Hashing algorithms supported by this module""" DEFAULT_ALGORITHMS = set(["sha1", "sha256", "sha1_git", "blake2s256"]) """Algorithms computed by default when calling the functions from this module. Subset of :const:`ALGORITHMS`. """ HASH_BLOCK_SIZE = 32768 """Block size for streaming hash computations made in this module""" _blake2_hash_cache = {} # type: Dict[str, Callable] class MultiHash: """Hashutil class to support multiple hashes computation. Args: hash_names (set): Set of hash algorithms (+ optionally length) to compute hashes (cf. DEFAULT_ALGORITHMS) length (int): Length of the total sum of chunks to read If the length is provided as algorithm, the length is also computed and returned. """ def __init__(self, hash_names=DEFAULT_ALGORITHMS, length=None): self.state = {} self.track_length = False for name in hash_names: if name == "length": self.state["length"] = 0 self.track_length = True else: self.state[name] = _new_hash(name, length) @classmethod def from_state(cls, state, track_length): ret = cls([]) ret.state = state ret.track_length = track_length @classmethod def from_file(cls, fobj, hash_names=DEFAULT_ALGORITHMS, length=None): ret = cls(length=length, hash_names=hash_names) while True: chunk = fobj.read(HASH_BLOCK_SIZE) if not chunk: break ret.update(chunk) return ret @classmethod def from_path(cls, path, hash_names=DEFAULT_ALGORITHMS): length = os.path.getsize(path) with open(path, "rb") as f: ret = cls.from_file(f, hash_names=hash_names, length=length) return ret @classmethod def from_data(cls, data, hash_names=DEFAULT_ALGORITHMS): length = len(data) fobj = BytesIO(data) return cls.from_file(fobj, hash_names=hash_names, length=length) def update(self, chunk): for name, h in self.state.items(): if name == "length": continue h.update(chunk) if self.track_length: self.state["length"] += len(chunk) def digest(self): return { name: h.digest() if name != "length" else h for name, h in self.state.items() } def hexdigest(self): return { name: h.hexdigest() if name != "length" else h for name, h in self.state.items() } def bytehexdigest(self): return { name: hash_to_bytehex(h.digest()) if name != "length" else h for name, h in self.state.items() } def copy(self): copied_state = { name: h.copy() if name != "length" else h for name, h in self.state.items() } return self.from_state(copied_state, self.track_length) def _new_blake2_hash(algo): - """Return a function that initializes a blake2 hash. - - """ + """Return a function that initializes a blake2 hash.""" if algo in _blake2_hash_cache: return _blake2_hash_cache[algo]() lalgo = algo.lower() if not lalgo.startswith("blake2"): raise ValueError("Algorithm %s is not a blake2 hash" % algo) blake_family = lalgo[:7] digest_size = None if lalgo[7:]: try: digest_size, remainder = divmod(int(lalgo[7:]), 8) except ValueError: raise ValueError("Unknown digest size for algo %s" % algo) from None if remainder: raise ValueError( "Digest size for algorithm %s must be a multiple of 8" % algo ) blake2 = getattr(hashlib, blake_family) _blake2_hash_cache[algo] = lambda: blake2(digest_size=digest_size) return _blake2_hash_cache[algo]() def _new_hashlib_hash(algo): """Initialize a digest object from hashlib. Handle the swh-specific names for the blake2-related algorithms """ if algo.startswith("blake2"): return _new_blake2_hash(algo) else: return hashlib.new(algo) def git_object_header(git_type: str, length: int) -> bytes: """Returns the header for a git object of the given type and length. The header of a git object consists of: - The type of the object (encoded in ASCII) - One ASCII space (\x20) - The length of the object (decimal encoded in ASCII) - One NUL byte Args: base_algo (str from :const:`ALGORITHMS`): a hashlib-supported algorithm git_type: the type of the git object (supposedly one of 'blob', 'commit', 'tag', 'tree') length: the length of the git object you're encoding Returns: a hashutil.hash object """ git_object_types = { "blob", "tree", "commit", "tag", "snapshot", "raw_extrinsic_metadata", "extid", } if git_type not in git_object_types: raise ValueError( "Unexpected git object type %s, expected one of %s" % (git_type, ", ".join(sorted(git_object_types))) ) return ("%s %d\0" % (git_type, length)).encode("ascii") def _new_hash(algo: str, length: Optional[int] = None): """Initialize a digest object (as returned by python's hashlib) for the requested algorithm. See the constant ALGORITHMS for the list of supported algorithms. If a git-specific hashing algorithm is requested (e.g., "sha1_git"), the hashing object will be pre-fed with the needed header; for this to work, length must be given. Args: algo (str): a hashing algorithm (one of ALGORITHMS) length (int): the length of the hashed payload (needed for git-specific algorithms) Returns: a hashutil.hash object Raises: ValueError if algo is unknown, or length is missing for a git-specific hash. """ if algo not in ALGORITHMS: raise ValueError( "Unexpected hashing algorithm %s, expected one of %s" % (algo, ", ".join(sorted(ALGORITHMS))) ) if algo.endswith("_git"): if length is None: raise ValueError("Missing length for git hashing algorithm") base_algo = algo[:-4] h = _new_hashlib_hash(base_algo) h.update(git_object_header("blob", length)) return h return _new_hashlib_hash(algo) def hash_git_data(data, git_type, base_algo="sha1"): """Hash the given data as a git object of type git_type. Args: data: a bytes object git_type: the git object type base_algo: the base hashing algorithm used (default: sha1) Returns: a dict mapping each algorithm to a bytes digest Raises: ValueError if the git_type is unexpected. """ h = _new_hashlib_hash(base_algo) h.update(git_object_header(git_type, len(data))) h.update(data) return h.digest() @functools.lru_cache() def hash_to_hex(hash): """Converts a hash (in hex or bytes form) to its hexadecimal ascii form Args: hash (str or bytes): a :class:`bytes` hash or a :class:`str` containing the hexadecimal form of the hash Returns: str: the hexadecimal form of the hash """ if isinstance(hash, str): return hash return binascii.hexlify(hash).decode("ascii") @functools.lru_cache() def hash_to_bytehex(hash): """Converts a hash to its hexadecimal bytes representation Args: hash (bytes): a :class:`bytes` hash Returns: bytes: the hexadecimal form of the hash, as :class:`bytes` """ return binascii.hexlify(hash) @functools.lru_cache() def hash_to_bytes(hash): """Converts a hash (in hex or bytes form) to its raw bytes form Args: hash (str or bytes): a :class:`bytes` hash or a :class:`str` containing the hexadecimal form of the hash Returns: bytes: the :class:`bytes` form of the hash """ if isinstance(hash, bytes): return hash return bytes.fromhex(hash) @functools.lru_cache() def bytehex_to_hash(hex): """Converts a hexadecimal bytes representation of a hash to that hash Args: hash (bytes): a :class:`bytes` containing the hexadecimal form of the hash encoded in ascii Returns: bytes: the :class:`bytes` form of the hash """ return hash_to_bytes(hex.decode()) diff --git a/swh/model/hypothesis_strategies.py b/swh/model/hypothesis_strategies.py index 54f552c..dabecf9 100644 --- a/swh/model/hypothesis_strategies.py +++ b/swh/model/hypothesis_strategies.py @@ -1,589 +1,590 @@ # 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 import string from typing import Sequence from hypothesis import assume from hypothesis.extra.dateutil import timezones from hypothesis.strategies import ( binary, booleans, builds, characters, composite, datetimes, dictionaries, from_regex, integers, just, lists, none, one_of, sampled_from, sets, text, tuples, ) from .from_disk import DentryPerms from .model import ( BaseContent, Content, Directory, DirectoryEntry, MetadataAuthority, MetadataFetcher, ObjectType, Origin, OriginVisit, OriginVisitStatus, Person, RawExtrinsicMetadata, Release, Revision, RevisionType, SkippedContent, Snapshot, SnapshotBranch, TargetType, Timestamp, TimestampWithTimezone, ) from .swhids import ExtendedObjectType, ExtendedSWHID pgsql_alphabet = characters( blacklist_categories=("Cs",), blacklist_characters=["\u0000"] ) # postgresql does not like these def optional(strategy): return one_of(none(), strategy) def pgsql_text(): return text(alphabet=pgsql_alphabet) def sha1_git(): return binary(min_size=20, max_size=20) def sha1(): return binary(min_size=20, max_size=20) def binaries_without_bytes(blacklist: Sequence[int]): """Like hypothesis.strategies.binary, but takes a sequence of bytes that should not be included.""" return lists(sampled_from([i for i in range(256) if i not in blacklist])).map(bytes) @composite def extended_swhids(draw): object_type = draw(sampled_from(ExtendedObjectType)) object_id = draw(sha1_git()) return ExtendedSWHID(object_type=object_type, object_id=object_id) def aware_datetimes(): # datetimes in Software Heritage are not used for software artifacts # (which may be much older than 2000), but only for objects like scheduler # task runs, and origin visits, which were created by Software Heritage, # so at least in 2015. # We're forbidding old datetimes, because until 1956, many timezones had seconds # in their "UTC offsets" (see # ), which is not # encodable in ISO8601; and we need our datetimes to be ISO8601-encodable in the # RPC protocol min_value = datetime.datetime(2000, 1, 1, 0, 0, 0) return datetimes(min_value=min_value, timezones=timezones()) @composite def iris(draw): protocol = draw(sampled_from(["git", "http", "https", "deb"])) domain = draw(from_regex(r"\A([a-z]([a-z0-9é🏛️-]*)\.){1,3}([a-z0-9é])+\Z")) return "%s://%s" % (protocol, domain) @composite def persons_d(draw): fullname = draw(binary()) email = draw(optional(binary())) name = draw(optional(binary())) assume(not (len(fullname) == 32 and email is None and name is None)) return dict(fullname=fullname, name=name, email=email) def persons(): return persons_d().map(Person.from_dict) def timestamps_d(): max_seconds = datetime.datetime.max.replace( tzinfo=datetime.timezone.utc ).timestamp() min_seconds = datetime.datetime.min.replace( tzinfo=datetime.timezone.utc ).timestamp() return builds( dict, seconds=integers(min_seconds, max_seconds), microseconds=integers(0, 1000000), ) def timestamps(): return timestamps_d().map(Timestamp.from_dict) @composite def timestamps_with_timezone_d( draw, timestamp=timestamps_d(), offset=integers(min_value=-14 * 60, max_value=14 * 60), negative_utc=booleans(), ): timestamp = draw(timestamp) offset = draw(offset) negative_utc = draw(negative_utc) assume(not (negative_utc and offset)) return dict(timestamp=timestamp, offset=offset, negative_utc=negative_utc) timestamps_with_timezone = timestamps_with_timezone_d().map( TimestampWithTimezone.from_dict ) def origins_d(): return builds(dict, url=iris()) def origins(): return origins_d().map(Origin.from_dict) def origin_visits_d(): return builds( dict, visit=integers(1, 1000), origin=iris(), date=aware_datetimes(), type=pgsql_text(), ) def origin_visits(): return origin_visits_d().map(OriginVisit.from_dict) def metadata_dicts(): return dictionaries(pgsql_text(), pgsql_text()) def origin_visit_statuses_d(): return builds( dict, visit=integers(1, 1000), origin=iris(), type=optional(sampled_from(["git", "svn", "pypi", "debian"])), status=sampled_from( ["created", "ongoing", "full", "partial", "not_found", "failed"] ), date=aware_datetimes(), snapshot=optional(sha1_git()), metadata=optional(metadata_dicts()), ) def origin_visit_statuses(): return origin_visit_statuses_d().map(OriginVisitStatus.from_dict) @composite def releases_d(draw): target_type = sampled_from([x.value for x in ObjectType]) name = binary() message = optional(binary()) synthetic = booleans() target = sha1_git() metadata = optional(revision_metadata()) d = draw( one_of( # None author/date: builds( dict, name=name, message=message, synthetic=synthetic, author=none(), date=none(), target=target, target_type=target_type, metadata=metadata, ), # non-None author/date: builds( dict, name=name, message=message, synthetic=synthetic, date=timestamps_with_timezone_d(), author=persons_d(), target=target, target_type=target_type, metadata=metadata, ), # it is also possible for date to be None but not author, but let's not # overwhelm hypothesis with this edge case ) ) raw_manifest = draw(optional(binary())) if raw_manifest: d["raw_manifest"] = raw_manifest return d def releases(): return releases_d().map(Release.from_dict) revision_metadata = metadata_dicts def extra_headers(): return lists( tuples(binary(min_size=0, max_size=50), binary(min_size=0, max_size=500)) ).map(tuple) @composite def revisions_d(draw): d = draw( one_of( # None author/committer/date/committer_date builds( dict, message=optional(binary()), synthetic=booleans(), author=none(), committer=none(), date=none(), committer_date=none(), parents=tuples(sha1_git()), directory=sha1_git(), type=sampled_from([x.value for x in RevisionType]), metadata=optional(revision_metadata()), extra_headers=extra_headers(), ), # non-None author/committer/date/committer_date builds( dict, message=optional(binary()), synthetic=booleans(), author=persons_d(), committer=persons_d(), date=timestamps_with_timezone_d(), committer_date=timestamps_with_timezone_d(), parents=tuples(sha1_git()), directory=sha1_git(), type=sampled_from([x.value for x in RevisionType]), metadata=optional(revision_metadata()), extra_headers=extra_headers(), ), # There are many other combinations, but let's not overwhelm hypothesis # with these edge cases ) ) # TODO: metadata['extra_headers'] can have binary keys and values raw_manifest = draw(optional(binary())) if raw_manifest: d["raw_manifest"] = raw_manifest return d def revisions(): return revisions_d().map(Revision.from_dict) def directory_entries_d(): return one_of( builds( dict, name=binaries_without_bytes(b"/"), target=sha1_git(), type=just("file"), perms=one_of( integers(min_value=0o100000, max_value=0o100777), # regular file integers(min_value=0o120000, max_value=0o120777), # symlink ), ), builds( dict, name=binaries_without_bytes(b"/"), target=sha1_git(), type=just("dir"), perms=integers( min_value=DentryPerms.directory, max_value=DentryPerms.directory + 0o777, ), ), builds( dict, name=binaries_without_bytes(b"/"), target=sha1_git(), type=just("rev"), perms=integers( - min_value=DentryPerms.revision, max_value=DentryPerms.revision + 0o777, + min_value=DentryPerms.revision, + max_value=DentryPerms.revision + 0o777, ), ), ) def directory_entries(): return directory_entries_d().map(DirectoryEntry) @composite def directories_d(draw): d = draw(builds(dict, entries=tuples(directory_entries_d()))) raw_manifest = draw(optional(binary())) if raw_manifest: d["raw_manifest"] = raw_manifest return d def directories(): return directories_d().map(Directory.from_dict) def contents_d(): return one_of(present_contents_d(), skipped_contents_d()) def contents(): return one_of(present_contents(), skipped_contents()) def present_contents_d(): return builds( dict, data=binary(max_size=4096), ctime=optional(aware_datetimes()), status=one_of(just("visible"), just("hidden")), ) def present_contents(): return present_contents_d().map(lambda d: Content.from_data(**d)) @composite def skipped_contents_d(draw): result = BaseContent._hash_data(draw(binary(max_size=4096))) result.pop("data") nullify_attrs = draw( sets(sampled_from(["sha1", "sha1_git", "sha256", "blake2s256"])) ) for k in nullify_attrs: result[k] = None result["reason"] = draw(pgsql_text()) result["status"] = "absent" result["ctime"] = draw(optional(aware_datetimes())) return result def skipped_contents(): return skipped_contents_d().map(SkippedContent.from_dict) def branch_names(): return binary(min_size=1) def branch_targets_object_d(): return builds( dict, target=sha1_git(), target_type=sampled_from( [x.value for x in TargetType if x.value not in ("alias",)] ), ) def branch_targets_alias_d(): return builds( dict, target=sha1_git(), target_type=just("alias") ) # TargetType.ALIAS.value)) def branch_targets_d(*, only_objects=False): if only_objects: return branch_targets_object_d() else: return one_of(branch_targets_alias_d(), branch_targets_object_d()) def branch_targets(*, only_objects=False): return builds(SnapshotBranch.from_dict, branch_targets_d(only_objects=only_objects)) @composite def snapshots_d(draw, *, min_size=0, max_size=100, only_objects=False): branches = draw( dictionaries( keys=branch_names(), values=optional(branch_targets_d(only_objects=only_objects)), min_size=min_size, max_size=max_size, ) ) if not only_objects: # Make sure aliases point to actual branches unresolved_aliases = { branch: target["target"] for branch, target in branches.items() if ( target and target["target_type"] == "alias" and target["target"] not in branches ) } for alias_name, alias_target in unresolved_aliases.items(): # Override alias branch with one pointing to a real object # if max_size constraint is reached alias = alias_target if len(branches) < max_size else alias_name branches[alias] = draw(branch_targets_d(only_objects=True)) # Ensure no cycles between aliases while True: try: snapshot = Snapshot.from_dict( { "branches": { name: branch or None for (name, branch) in branches.items() } } ) except ValueError as e: for (source, target) in e.args[1]: branches[source] = draw(branch_targets_d(only_objects=True)) else: break return snapshot.to_dict() def snapshots(*, min_size=0, max_size=100, only_objects=False): return snapshots_d( min_size=min_size, max_size=max_size, only_objects=only_objects ).map(Snapshot.from_dict) def metadata_authorities(): return builds(MetadataAuthority, url=iris(), metadata=just(None)) def metadata_fetchers(): return builds( MetadataFetcher, name=text(min_size=1, alphabet=string.printable), version=text( min_size=1, alphabet=string.ascii_letters + string.digits + string.punctuation, ), metadata=just(None), ) def raw_extrinsic_metadata(): return builds( RawExtrinsicMetadata, target=extended_swhids(), discovery_date=aware_datetimes(), authority=metadata_authorities(), fetcher=metadata_fetchers(), format=text(min_size=1, alphabet=string.printable), ) def raw_extrinsic_metadata_d(): return raw_extrinsic_metadata().map(RawExtrinsicMetadata.to_dict) def objects(blacklist_types=("origin_visit_status",), split_content=False): """generates a random couple (type, obj) which obj is an instance of the Model class corresponding to obj_type. `blacklist_types` is a list of obj_type to exclude from the strategy. If `split_content` is True, generates Content and SkippedContent under different obj_type, resp. "content" and "skipped_content". """ strategies = [ ("origin", origins), ("origin_visit", origin_visits), ("origin_visit_status", origin_visit_statuses), ("snapshot", snapshots), ("release", releases), ("revision", revisions), ("directory", directories), ("raw_extrinsic_metadata", raw_extrinsic_metadata), ] if split_content: strategies.append(("content", present_contents)) strategies.append(("skipped_content", skipped_contents)) else: strategies.append(("content", contents)) args = [ obj_gen().map(lambda x, obj_type=obj_type: (obj_type, x)) for (obj_type, obj_gen) in strategies if obj_type not in blacklist_types ] return one_of(*args) def object_dicts(blacklist_types=("origin_visit_status",), split_content=False): """generates a random couple (type, dict) which dict is suitable for .from_dict() factory methods. `blacklist_types` is a list of obj_type to exclude from the strategy. If `split_content` is True, generates Content and SkippedContent under different obj_type, resp. "content" and "skipped_content". """ strategies = [ ("origin", origins_d), ("origin_visit", origin_visits_d), ("origin_visit_status", origin_visit_statuses_d), ("snapshot", snapshots_d), ("release", releases_d), ("revision", revisions_d), ("directory", directories_d), ("raw_extrinsic_metadata", raw_extrinsic_metadata_d), ] if split_content: strategies.append(("content", present_contents_d)) strategies.append(("skipped_content", skipped_contents_d)) else: strategies.append(("content", contents_d)) args = [ obj_gen().map(lambda x, obj_type=obj_type: (obj_type, x)) for (obj_type, obj_gen) in strategies if obj_type not in blacklist_types ] return one_of(*args) diff --git a/swh/model/merkle.py b/swh/model/merkle.py index 8934ad1..ab6b8ea 100644 --- a/swh/model/merkle.py +++ b/swh/model/merkle.py @@ -1,315 +1,315 @@ # 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 """Merkle tree data structure""" import abc from collections.abc import Mapping from typing import Dict, Iterator, List, Set def deep_update(left, right): """Recursively update the left mapping with deeply nested values from the right mapping. This function is useful to merge the results of several calls to :func:`MerkleNode.collect`. Arguments: left: a mapping (modified by the update operation) right: a mapping Returns: the left mapping, updated with nested values from the right mapping Example: >>> a = { ... 'key1': { ... 'key2': { ... 'key3': 'value1/2/3', ... }, ... }, ... } >>> deep_update(a, { ... 'key1': { ... 'key2': { ... 'key4': 'value1/2/4', ... }, ... }, ... }) == { ... 'key1': { ... 'key2': { ... 'key3': 'value1/2/3', ... 'key4': 'value1/2/4', ... }, ... }, ... } True >>> deep_update(a, { ... 'key1': { ... 'key2': { ... 'key3': 'newvalue1/2/3', ... }, ... }, ... }) == { ... 'key1': { ... 'key2': { ... 'key3': 'newvalue1/2/3', ... 'key4': 'value1/2/4', ... }, ... }, ... } True """ for key, rvalue in right.items(): if isinstance(rvalue, Mapping): new_lvalue = deep_update(left.get(key, {}), rvalue) left[key] = new_lvalue else: left[key] = rvalue return left class MerkleNode(dict, metaclass=abc.ABCMeta): """Representation of a node in a Merkle Tree. A (generalized) `Merkle Tree`_ is a tree in which every node is labeled with a hash of its own data and the hash of its children. .. _Merkle Tree: https://en.wikipedia.org/wiki/Merkle_tree In pseudocode:: node.hash = hash(node.data + sum(child.hash for child in node.children)) This class efficiently implements the Merkle Tree data structure on top of a Python :class:`dict`, minimizing hash computations and new data collections when updating nodes. Node data is stored in the :attr:`data` attribute, while (named) children are stored as items of the underlying dictionary. Addition, update and removal of objects are instrumented to automatically invalidate the hashes of the current node as well as its registered parents; It also resets the collection status of the objects so the updated objects can be collected. The collection of updated data from the tree is implemented through the :func:`collect` function and associated helpers. """ __slots__ = ["parents", "data", "__hash", "collected"] data: Dict """data associated to the current node""" parents: List """known parents of the current node""" collected: bool """whether the current node has been collected""" def __init__(self, data=None): super().__init__() self.parents = [] self.data = data self.__hash = None self.collected = False def __eq__(self, other): return ( isinstance(other, MerkleNode) and super().__eq__(other) and self.data == other.data ) def __ne__(self, other): return not self.__eq__(other) def invalidate_hash(self): """Invalidate the cached hash of the current node.""" if not self.__hash: return self.__hash = None self.collected = False for parent in self.parents: parent.invalidate_hash() def update_hash(self, *, force=False): """Recursively compute the hash of the current node. Args: force (bool): invalidate the cache and force the computation for this node and all children. """ if self.__hash and not force: return self.__hash if force: self.invalidate_hash() for child in self.values(): child.update_hash(force=force) self.__hash = self.compute_hash() return self.__hash @property def hash(self): """The hash of the current node, as calculated by :func:`compute_hash`. """ return self.update_hash() @abc.abstractmethod def compute_hash(self): """Compute the hash of the current node. The hash should depend on the data of the node, as well as on hashes of the children nodes. """ raise NotImplementedError("Must implement compute_hash method") def __setitem__(self, name, new_child): """Add a child, invalidating the current hash""" self.invalidate_hash() super().__setitem__(name, new_child) new_child.parents.append(self) def __delitem__(self, name): """Remove a child, invalidating the current hash""" if name in self: self.invalidate_hash() self[name].parents.remove(self) super().__delitem__(name) else: raise KeyError(name) def update(self, new_children): """Add several named children from a dictionary""" if not new_children: return self.invalidate_hash() for name, new_child in new_children.items(): new_child.parents.append(self) if name in self: self[name].parents.remove(self) super().update(new_children) def get_data(self, **kwargs): """Retrieve and format the collected data for the current node, for use by :func:`collect`. Can be overridden, for instance when you want the collected data to contain information about the child nodes. Arguments: kwargs: allow subclasses to alter behaviour depending on how :func:`collect` is called. Returns: data formatted for :func:`collect` """ return self.data def collect_node(self, **kwargs): """Collect the data for the current node, for use by :func:`collect`. Arguments: kwargs: passed as-is to :func:`get_data`. Returns: A :class:`dict` compatible with :func:`collect`. """ if not self.collected: self.collected = True return {self.object_type: {self.hash: self.get_data(**kwargs)}} else: return {} def collect(self, **kwargs): """Collect the data for all nodes in the subtree rooted at `self`. The data is deduplicated by type and by hash. Arguments: kwargs: passed as-is to :func:`get_data`. Returns: A :class:`dict` with the following structure:: { 'typeA': { node1.hash: node1.get_data(), node2.hash: node2.get_data(), }, 'typeB': { node3.hash: node3.get_data(), ... }, ... } """ ret = self.collect_node(**kwargs) for child in self.values(): deep_update(ret, child.collect(**kwargs)) return ret def reset_collect(self): """Recursively unmark collected nodes in the subtree rooted at `self`. This lets the caller use :func:`collect` again. """ self.collected = False for child in self.values(): child.reset_collect() def iter_tree(self, dedup=True) -> Iterator["MerkleNode"]: """Yields all children nodes, recursively. Common nodes are deduplicated - by default (deduplication can be turned off setting the given argument - 'dedup' to False). + by default (deduplication can be turned off setting the given argument + 'dedup' to False). """ yield from self._iter_tree(set(), dedup) def _iter_tree(self, seen: Set[bytes], dedup) -> Iterator["MerkleNode"]: if self.hash not in seen: if dedup: seen.add(self.hash) yield self for child in self.values(): yield from child._iter_tree(seen=seen, dedup=dedup) class MerkleLeaf(MerkleNode): """A leaf to a Merkle tree. A Merkle leaf is simply a Merkle node with children disabled. """ __slots__ = [] # type: List[str] def __setitem__(self, name, child): raise ValueError("%s is a leaf" % self.__class__.__name__) def __getitem__(self, name): raise ValueError("%s is a leaf" % self.__class__.__name__) def __delitem__(self, name): raise ValueError("%s is a leaf" % self.__class__.__name__) def update(self, new_children): """Children update operation. Disabled for leaves.""" raise ValueError("%s is a leaf" % self.__class__.__name__) diff --git a/swh/model/model.py b/swh/model/model.py index 3eca674..1438678 100644 --- a/swh/model/model.py +++ b/swh/model/model.py @@ -1,1515 +1,1521 @@ # 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 """ Implementation of Software Heritage's data model See :ref:`data-model` for an overview of the data model. The classes defined in this module are immutable `attrs objects `__ and enums. All classes define a ``from_dict`` class method and a ``to_dict`` method to convert between them and msgpack-serializable objects. """ from abc import ABCMeta, abstractmethod import datetime from enum import Enum import hashlib from typing import Any, Dict, Iterable, Optional, Tuple, TypeVar, Union import attr from attrs_strict import AttributeTypeError import dateutil.parser import iso8601 from typing_extensions import Final from . import git_objects from .collections import ImmutableDict from .hashutil import DEFAULT_ALGORITHMS, MultiHash, hash_to_hex from .swhids import CoreSWHID from .swhids import ExtendedObjectType as SwhidExtendedObjectType from .swhids import ExtendedSWHID from .swhids 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 _OFFSET_CHARS = frozenset(b"+-0123456789") # TODO: Limit this to 20 bytes Sha1Git = bytes Sha1 = bytes KT = TypeVar("KT") VT = TypeVar("VT") def hash_repr(h: bytes) -> str: if h is None: return "None" else: return f"hash_to_bytes('{hash_to_hex(h)}')" 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 def _check_type(type_, value): if type_ is object or type_ is Any: return True if type_ is None: return value is None origin = getattr(type_, "__origin__", None) # Non-generic type, check it directly if origin is None: # This is functionally equivalent to using just this: # return isinstance(value, type) # but using type equality before isinstance allows very quick checks # when the exact class is used (which is the overwhelming majority of cases) # while still allowing subclasses to be used. return type(value) == type_ or isinstance(value, type_) # Check the type of the value itself # # For the same reason as above, this condition is functionally equivalent to: # if origin is not Union and not isinstance(value, origin): if origin is not Union and type(value) != origin and not isinstance(value, origin): return False # Then, if it's a container, check its items. if origin is tuple: args = type_.__args__ if len(args) == 2 and args[1] is Ellipsis: # Infinite tuple return all(_check_type(args[0], item) for item in value) else: # Finite tuple if len(args) != len(value): return False return all( _check_type(item_type, item) for (item_type, item) in zip(args, value) ) elif origin is Union: args = type_.__args__ return any(_check_type(variant, value) for variant in args) elif origin is ImmutableDict: (key_type, value_type) = type_.__args__ return all( _check_type(key_type, key) and _check_type(value_type, value) for (key, value) in value.items() ) else: # No need to check dict or list. because they are converted to ImmutableDict # and tuple respectively. raise NotImplementedError(f"Type-checking {type_}") def type_validator(): """Like attrs_strict.type_validator(), but stricter. It is an attrs validator, which checks attributes have the specified type, using type equality instead of ``isinstance()``, for improved performance """ def validator(instance, attribute, value): if not _check_type(attribute.type, value): raise AttributeTypeError(value, attribute) return validator 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}") def check(self) -> None: """Performs internal consistency checks, and raises an error if one fails.""" attr.validate(self) def _compute_hash_from_manifest(manifest: bytes) -> Sha1Git: return hashlib.new("sha1", manifest).digest() class HashableObject(metaclass=ABCMeta): """Mixin to automatically compute object identifier hash when the associated model is instantiated.""" __slots__ = () id: Sha1Git 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. """ return self._compute_hash_from_attributes() @abstractmethod def _compute_hash_from_attributes(self) -> Sha1Git: raise NotImplementedError(f"_compute_hash_from_attributes for {self}") 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 def check(self) -> None: super().check() # type: ignore if self.id != self.compute_hash(): raise ValueError("'id' does not match recomputed hash.") class HashableObjectWithManifest(HashableObject): """Derived class of HashableObject, for objects that may need to store verbatim git objects as ``raw_manifest`` to preserve original hashes.""" __slots__ = () raw_manifest: Optional[bytes] = None """Stores the original content of git objects when they cannot be faithfully represented using only the other attributes. This should only be used as a last resort, and only set in the Git loader, for objects too corrupt to fit the data model.""" def to_dict(self): d = super().to_dict() if d["raw_manifest"] is None: del d["raw_manifest"] return d 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. """ if self.raw_manifest is None: return super().compute_hash() else: return _compute_hash_from_manifest(self.raw_manifest) def check(self) -> None: super().check() if ( self.raw_manifest is not None and self.id == self._compute_hash_from_attributes() ): raise ValueError( f"{self} has a non-none raw_manifest attribute, but does not need it." ) @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(), eq=False) email = attr.ib(type=Optional[bytes], validator=type_validator(), eq=False) @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,) + 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=hashlib.sha256(self.fullname).digest(), name=None, email=None, + fullname=hashlib.sha256(self.fullname).digest(), + name=None, + email=None, ) @classmethod def from_dict(cls, d): """ If the fullname is missing, 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 "fullname" not in d: parts = [] if d["name"] is not None: parts.append(d["name"]) if d["email"] is not None: parts.append(b"".join([b"<", d["email"], b">"])) fullname = b" ".join(parts) d = {**d, "fullname": fullname} d = {"name": None, "email": None, **d} return super().from_dict(d) @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): + 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): + 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_bytes = attr.ib(type=bytes, validator=type_validator()) """Raw git representation of the timezone, as an offset from UTC. It should follow this format: ``+HHMM`` or ``-HHMM`` (including ``+0000`` and ``-0000``). However, when created from git objects, it must be the exact bytes used in the original objects, so it may differ from this format when they do. """ @classmethod def from_numeric_offset( cls, timestamp: Timestamp, offset: int, negative_utc: bool ) -> "TimestampWithTimezone": """Returns a :class:`TimestampWithTimezone` instance from the old dictionary format (with ``offset`` and ``negative_utc`` instead of ``offset_bytes``). """ negative = offset < 0 or negative_utc (hours, minutes) = divmod(abs(offset), 60) offset_bytes = f"{'-' if negative else '+'}{hours:02}{minutes:02}".encode() tstz = TimestampWithTimezone(timestamp=timestamp, offset_bytes=offset_bytes) assert tstz.offset_minutes() == offset, (tstz.offset_minutes(), offset) return tstz @classmethod def from_dict( cls, time_representation: Union[Dict, datetime.datetime, int] ) -> "TimestampWithTimezone": """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 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( f"TimestampWithTimezone.from_dict received non-integer timestamp " f"member {ts!r}" ) timestamp = Timestamp(seconds=seconds, microseconds=microseconds) if "offset_bytes" in time_representation: return cls( timestamp=timestamp, offset_bytes=time_representation["offset_bytes"], ) else: # old format offset = time_representation["offset"] negative_utc = time_representation.get("negative_utc") or False return cls.from_numeric_offset(timestamp, offset, negative_utc) elif isinstance(time_representation, datetime.datetime): # TODO: warn when using from_dict() on a datetime utcoffset = time_representation.utcoffset() time_representation = time_representation.astimezone(datetime.timezone.utc) microseconds = time_representation.microsecond if microseconds: time_representation = time_representation.replace(microsecond=0) seconds = int(time_representation.timestamp()) if utcoffset is None: raise ValueError( f"TimestampWithTimezone.from_dict received datetime without " f"timezone: {time_representation}" ) # utcoffset is an integer number of minutes seconds_offset = utcoffset.total_seconds() offset = int(seconds_offset) // 60 # TODO: warn if remainder is not zero return cls.from_numeric_offset( Timestamp(seconds=seconds, microseconds=microseconds), offset, False ) elif isinstance(time_representation, int): # TODO: warn when using from_dict() on an int seconds = time_representation timestamp = Timestamp(seconds=time_representation, microseconds=0) return cls(timestamp=timestamp, offset_bytes=b"+0000") else: raise ValueError( f"TimestampWithTimezone.from_dict received non-integer timestamp: " f"{time_representation!r}" ) @classmethod def from_datetime(cls, dt: datetime.datetime) -> "TimestampWithTimezone": 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: ``-0000`` and 'weird' offsets cannot be represented. Also note that it may fail due to type overflow. """ timestamp = datetime.datetime.fromtimestamp( self.timestamp.seconds, datetime.timezone(datetime.timedelta(minutes=self.offset_minutes())), ) timestamp = timestamp.replace(microsecond=self.timestamp.microseconds) return timestamp @classmethod def from_iso8601(cls, s): - """Builds a TimestampWithTimezone from an ISO8601-formatted string. - """ + """Builds a TimestampWithTimezone from an ISO8601-formatted string.""" dt = iso8601.parse_date(s) tstz = cls.from_datetime(dt) if dt.tzname() == "-00:00": assert tstz.offset_bytes == b"+0000" tstz = attr.evolve(tstz, offset_bytes=b"-0000") return tstz @staticmethod def _parse_offset_bytes(offset_bytes: bytes) -> int: """Parses an ``offset_bytes`` value (in Git's ``[+-]HHMM`` format), and returns the corresponding numeric values (in number of minutes). Tries to account for some mistakes in the format, to support incorrect Git implementations. >>> TimestampWithTimezone._parse_offset_bytes(b"+0000") 0 >>> TimestampWithTimezone._parse_offset_bytes(b"-0000") 0 >>> TimestampWithTimezone._parse_offset_bytes(b"+0200") 120 >>> TimestampWithTimezone._parse_offset_bytes(b"-0200") -120 >>> TimestampWithTimezone._parse_offset_bytes(b"+200") 120 >>> TimestampWithTimezone._parse_offset_bytes(b"-200") -120 >>> TimestampWithTimezone._parse_offset_bytes(b"+02") 120 >>> TimestampWithTimezone._parse_offset_bytes(b"-02") -120 >>> TimestampWithTimezone._parse_offset_bytes(b"+0010") 10 >>> TimestampWithTimezone._parse_offset_bytes(b"-0010") -10 >>> TimestampWithTimezone._parse_offset_bytes(b"+200000000000000000") 0 >>> TimestampWithTimezone._parse_offset_bytes(b"+0160") # 60 minutes... 0 """ offset_str = offset_bytes.decode() assert offset_str[0] in "+-" sign = int(offset_str[0] + "1") if len(offset_str) <= 3: hours = int(offset_str[1:]) minutes = 0 else: hours = int(offset_str[1:-2]) minutes = int(offset_str[-2:]) offset = sign * (hours * 60 + minutes) - if (0 <= minutes <= 59) and (-(2 ** 15) <= offset < 2 ** 15): + if (0 <= minutes <= 59) and (-(2**15) <= offset < 2**15): return offset else: # can't parse it to a reasonable value; give up and pretend it's UTC. return 0 def offset_minutes(self): """Returns the offset, as a number of minutes since UTC. >>> TimestampWithTimezone( ... Timestamp(seconds=1642765364, microseconds=0), offset_bytes=b"+0000" ... ).offset_minutes() 0 >>> TimestampWithTimezone( ... Timestamp(seconds=1642765364, microseconds=0), offset_bytes=b"+0200" ... ).offset_minutes() 120 >>> TimestampWithTimezone( ... Timestamp(seconds=1642765364, microseconds=0), offset_bytes=b"-0200" ... ).offset_minutes() -120 >>> TimestampWithTimezone( ... Timestamp(seconds=1642765364, microseconds=0), offset_bytes=b"+0530" ... ).offset_minutes() 330 """ return self._parse_offset_bytes(self.offset_bytes) @attr.s(frozen=True, slots=True) class Origin(HashableObject, BaseModel): """Represents a software source: a VCS and an URL.""" object_type: Final = "origin" url = attr.ib(type=str, validator=type_validator()) id = attr.ib(type=Sha1Git, validator=type_validator(), default=b"") def unique_key(self) -> KeyType: return {"url": self.url} def _compute_hash_from_attributes(self) -> bytes: return _compute_hash_from_manifest(self.url.encode("utf-8")) def swhid(self) -> ExtendedSWHID: """Returns a SWHID representing this origin.""" return ExtendedSWHID( - object_type=SwhidExtendedObjectType.ORIGIN, object_id=self.id, + object_type=SwhidExtendedObjectType.ORIGIN, + object_id=self.id, ) @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. - - """ + """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(), repr=hash_repr ) # 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" def __repr__(self): return f"TargetType.{self.name}" 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" def __repr__(self): return f"ObjectType.{self.name}" @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(), repr=hash_repr) 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"", repr=hash_repr) def _compute_hash_from_attributes(self) -> bytes: return _compute_hash_from_manifest(git_objects.snapshot_git_object(self)) @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(HashableObjectWithManifest, 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(), repr=hash_repr) 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"", repr=hash_repr) raw_manifest = attr.ib(type=Optional[bytes], default=None) def _compute_hash_from_attributes(self) -> bytes: return _compute_hash_from_manifest(git_objects.release_git_object(self)) @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" CVS = "cvs" BAZAAR = "bzr" def __repr__(self): return f"RevisionType.{self.name}" def tuplify_extra_headers(value: Iterable): return tuple((k, v) for k, v in value) @attr.s(frozen=True, slots=True) class Revision(HashableObjectWithManifest, BaseModel): object_type: Final = "revision" message = attr.ib(type=Optional[bytes], validator=type_validator()) author = attr.ib(type=Optional[Person], validator=type_validator()) committer = attr.ib(type=Optional[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(), repr=hash_repr) 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"", repr=hash_repr) extra_headers = attr.ib( type=Tuple[Tuple[bytes, bytes], ...], validator=type_validator(), converter=tuplify_extra_headers, default=(), ) raw_manifest = attr.ib(type=Optional[bytes], default=None) 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), + self, + "extra_headers", + tuplify_extra_headers(extra_headers), ) attr.validate(self) object.__setattr__(self, "metadata", metadata) def _compute_hash_from_attributes(self) -> bytes: return _compute_hash_from_manifest(git_objects.revision_git_object(self)) @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("revision date must be None if author is None.") @committer.validator def check_committer(self, attribute, value): """If the committer is `None`, checks the committer_date is `None` too.""" if self.committer is None and self.committer_date is not None: raise ValueError( "revision committer_date must be None if committer is None." ) @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) author = d.pop("author") if author: author = Person.from_dict(author) committer = d.pop("committer") if committer: committer = Person.from_dict(committer) return cls( author=author, committer=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=None if self.author is None else self.author.anonymize(), committer=None if self.committer is None else 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(), repr=hash_repr) perms = attr.ib(type=int, validator=type_validator(), converter=int, repr=oct) """Usually one of the values of `swh.model.from_disk.DentryPerms`.""" @name.validator def check_name(self, attribute, value): if b"/" in value: raise ValueError(f"{value!r} is not a valid directory entry name.") @attr.s(frozen=True, slots=True) class Directory(HashableObjectWithManifest, BaseModel): object_type: Final = "directory" entries = attr.ib(type=Tuple[DirectoryEntry, ...], validator=type_validator()) id = attr.ib(type=Sha1Git, validator=type_validator(), default=b"", repr=hash_repr) raw_manifest = attr.ib(type=Optional[bytes], default=None) def _compute_hash_from_attributes(self) -> bytes: return _compute_hash_from_manifest(git_objects.directory_git_object(self)) @entries.validator def check_entries(self, attribute, value): seen = set() for entry in value: if entry.name in seen: # Cannot use self.swhid() here, self.id may be None raise ValueError( f"swh:1:dir:{hash_to_hex(self.id)} has duplicated entry name: " f"{entry.name!r}" ) seen.add(entry.name) @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(), repr=hash_repr) sha1_git = attr.ib(type=Sha1Git, validator=type_validator(), repr=hash_repr) sha256 = attr.ib(type=bytes, validator=type_validator(), repr=hash_repr) blake2s256 = attr.ib(type=bytes, validator=type_validator(), repr=hash_repr) 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(), repr=hash_repr) sha1_git = attr.ib( type=Optional[Sha1Git], validator=type_validator(), repr=hash_repr ) sha256 = attr.ib(type=Optional[bytes], validator=type_validator(), repr=hash_repr) blake2s256 = attr.ib( type=Optional[bytes], validator=type_validator(), repr=hash_repr ) 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" def __repr__(self): return f"MetadataAuthorityType.{self.name}" @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"", repr=hash_repr) def _compute_hash_from_attributes(self) -> bytes: return _compute_hash_from_manifest( git_objects.raw_extrinsic_metadata_git_object(self) ) @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()) extid_version = attr.ib(type=int, validator=type_validator(), default=0) id = attr.ib(type=Sha1Git, validator=type_validator(), default=b"", repr=hash_repr) @classmethod def from_dict(cls, d): return cls( extid=d["extid"], extid_type=d["extid_type"], target=CoreSWHID.from_string(d["target"]), extid_version=d.get("extid_version", 0), ) def _compute_hash_from_attributes(self) -> bytes: return _compute_hash_from_manifest(git_objects.extid_git_object(self)) diff --git a/swh/model/tests/fields/test_compound.py b/swh/model/tests/fields/test_compound.py index 352bba9..23b05b2 100644 --- a/swh/model/tests/fields/test_compound.py +++ b/swh/model/tests/fields/test_compound.py @@ -1,238 +1,242 @@ # Copyright (C) 2015 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 unittest from swh.model.exceptions import NON_FIELD_ERRORS, ValidationError from swh.model.fields import compound, simple class ValidateCompound(unittest.TestCase): def setUp(self): def validate_always(model): return True def validate_never(model): return False self.test_model = "test model" self.test_schema = { "int": (True, simple.validate_int), "str": (True, simple.validate_str), "str2": (True, simple.validate_str), "datetime": (False, simple.validate_datetime), NON_FIELD_ERRORS: validate_always, } self.test_schema_shortcut = self.test_schema.copy() self.test_schema_shortcut[NON_FIELD_ERRORS] = validate_never self.test_schema_field_failed = self.test_schema.copy() self.test_schema_field_failed["int"] = ( True, [simple.validate_int, validate_never], ) self.test_value = { "str": "value1", "str2": "value2", "int": 42, "datetime": datetime.datetime( 1990, 1, 1, 12, 0, 0, tzinfo=datetime.timezone.utc ), } self.test_value_missing = { "str": "value1", } self.test_value_str_error = { "str": 1984, "str2": "value2", "int": 42, "datetime": datetime.datetime( 1990, 1, 1, 12, 0, 0, tzinfo=datetime.timezone.utc ), } self.test_value_missing_keys = {"int"} self.test_value_wrong_type = 42 self.present_keys = set(self.test_value) self.missing_keys = {"missingkey1", "missingkey2"} def test_validate_any_key(self): self.assertTrue(compound.validate_any_key(self.test_value, self.present_keys)) self.assertTrue( compound.validate_any_key( self.test_value, self.present_keys | self.missing_keys ) ) def test_validate_any_key_missing(self): with self.assertRaises(ValidationError) as cm: compound.validate_any_key(self.test_value, self.missing_keys) exc = cm.exception self.assertIsInstance(str(exc), str) self.assertEqual(exc.code, "missing-alternative-field") self.assertEqual( exc.params["missing_fields"], ", ".join(sorted(self.missing_keys)) ) def test_validate_all_keys(self): self.assertTrue(compound.validate_all_keys(self.test_value, self.present_keys)) def test_validate_all_keys_missing(self): with self.assertRaises(ValidationError) as cm: compound.validate_all_keys(self.test_value, self.missing_keys) exc = cm.exception self.assertIsInstance(str(exc), str) self.assertEqual(exc.code, "missing-mandatory-field") self.assertEqual( exc.params["missing_fields"], ", ".join(sorted(self.missing_keys)) ) with self.assertRaises(ValidationError) as cm: compound.validate_all_keys( self.test_value, self.present_keys | self.missing_keys ) exc = cm.exception self.assertIsInstance(str(exc), str) self.assertEqual(exc.code, "missing-mandatory-field") self.assertEqual( exc.params["missing_fields"], ", ".join(sorted(self.missing_keys)) ) def test_validate_against_schema(self): self.assertTrue( compound.validate_against_schema( self.test_model, self.test_schema, self.test_value ) ) def test_validate_against_schema_wrong_type(self): with self.assertRaises(ValidationError) as cm: compound.validate_against_schema( self.test_model, self.test_schema, self.test_value_wrong_type ) exc = cm.exception self.assertIsInstance(str(exc), str) self.assertEqual(exc.code, "model-unexpected-type") self.assertEqual(exc.params["model"], self.test_model) self.assertEqual( exc.params["type"], self.test_value_wrong_type.__class__.__name__ ) def test_validate_against_schema_mandatory_keys(self): with self.assertRaises(ValidationError) as cm: compound.validate_against_schema( self.test_model, self.test_schema, self.test_value_missing ) # The exception should be of the form: # ValidationError({ # 'mandatory_key1': [ValidationError('model-field-mandatory')], # 'mandatory_key2': [ValidationError('model-field-mandatory')], # }) exc = cm.exception self.assertIsInstance(str(exc), str) for key in self.test_value_missing_keys: nested_key = exc.error_dict[key] self.assertIsInstance(nested_key, list) self.assertEqual(len(nested_key), 1) nested = nested_key[0] self.assertIsInstance(nested, ValidationError) self.assertEqual(nested.code, "model-field-mandatory") self.assertEqual(nested.params["field"], key) def test_validate_whole_schema_shortcut_previous_error(self): with self.assertRaises(ValidationError) as cm: compound.validate_against_schema( - self.test_model, self.test_schema_shortcut, self.test_value_missing, + self.test_model, + self.test_schema_shortcut, + self.test_value_missing, ) exc = cm.exception self.assertIsInstance(str(exc), str) self.assertNotIn(NON_FIELD_ERRORS, exc.error_dict) def test_validate_whole_schema(self): with self.assertRaises(ValidationError) as cm: compound.validate_against_schema( - self.test_model, self.test_schema_shortcut, self.test_value, + self.test_model, + self.test_schema_shortcut, + self.test_value, ) # The exception should be of the form: # ValidationError({ # NON_FIELD_ERRORS: [ValidationError('model-validation-failed')], # }) exc = cm.exception self.assertIsInstance(str(exc), str) self.assertEqual(set(exc.error_dict.keys()), {NON_FIELD_ERRORS}) non_field_errors = exc.error_dict[NON_FIELD_ERRORS] self.assertIsInstance(non_field_errors, list) self.assertEqual(len(non_field_errors), 1) nested = non_field_errors[0] self.assertIsInstance(nested, ValidationError) self.assertEqual(nested.code, "model-validation-failed") self.assertEqual(nested.params["model"], self.test_model) self.assertEqual(nested.params["validator"], "validate_never") def test_validate_against_schema_field_error(self): with self.assertRaises(ValidationError) as cm: compound.validate_against_schema( self.test_model, self.test_schema, self.test_value_str_error ) # The exception should be of the form: # ValidationError({ # 'str': [ValidationError('unexpected-type')], # }) exc = cm.exception self.assertIsInstance(str(exc), str) self.assertEqual(set(exc.error_dict.keys()), {"str"}) str_errors = exc.error_dict["str"] self.assertIsInstance(str_errors, list) self.assertEqual(len(str_errors), 1) nested = str_errors[0] self.assertIsInstance(nested, ValidationError) self.assertEqual(nested.code, "unexpected-type") def test_validate_against_schema_field_failed(self): with self.assertRaises(ValidationError) as cm: compound.validate_against_schema( self.test_model, self.test_schema_field_failed, self.test_value ) # The exception should be of the form: # ValidationError({ # 'int': [ValidationError('field-validation-failed')], # }) exc = cm.exception self.assertIsInstance(str(exc), str) self.assertEqual(set(exc.error_dict.keys()), {"int"}) int_errors = exc.error_dict["int"] self.assertIsInstance(int_errors, list) self.assertEqual(len(int_errors), 1) nested = int_errors[0] self.assertIsInstance(nested, ValidationError) self.assertEqual(nested.code, "field-validation-failed") self.assertEqual(nested.params["validator"], "validate_never") self.assertEqual(nested.params["field"], "int") diff --git a/swh/model/tests/swh_model_data.py b/swh/model/tests/swh_model_data.py index 03b9ca7..382b643 100644 --- a/swh/model/tests/swh_model_data.py +++ b/swh/model/tests/swh_model_data.py @@ -1,435 +1,475 @@ # 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.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, ) from swh.model.swhids import ExtendedSWHID 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_bytes=b"+0200", + timestamp=Timestamp( + seconds=1234567891, + microseconds=0, + ), + offset_bytes=b"+0200", ), TimestampWithTimezone( - timestamp=Timestamp(seconds=1234567892, microseconds=0,), offset_bytes=b"+0200", + timestamp=Timestamp( + seconds=1234567892, + microseconds=0, + ), + offset_bytes=b"+0200", ), ] 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"),), ), Revision( id=hash_to_bytes("51580d63b8dcc0ec73e74994e66896858542840a"), 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"),), raw_manifest=( b"commit 207\x00" b"tree 0101010101010101010101010101010101010101\n" b"parent 9B918DD063CEC85C2BC63CC7F167E29F5894DCBC" # upper-cased b"nauthor foo 1234567891 +0200\n" b"committer foo 1234567891 +0200" b"\n\nhello" ), ), ] 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(),), + ExtID( + extid_type="git256", + extid=b"\x03" * 32, + target=REVISIONS[0].swhid(), + ), + ExtID( + extid_type="hg", + extid=b"\x04" * 20, + target=REVISIONS[1].swhid(), + ), ExtID( extid_type="hg-nodeid", extid=b"\x05" * 20, target=REVISIONS[1].swhid(), extid_version=1, ), ] RELEASES = [ Release( id=hash_to_bytes("8059dc4e17fcd0e51ca3bcd6b80f4577d281fd08"), name=b"v0.0.1", date=TimestampWithTimezone( - timestamp=Timestamp(seconds=1234567890, microseconds=0,), + timestamp=Timestamp( + seconds=1234567890, + microseconds=0, + ), offset_bytes=b"+0200", ), 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, ), Release( id=hash_to_bytes("1cdd1e87234b6f066d0855a3b5b567638a55d583"), name=b"v0.0.1", date=TimestampWithTimezone( - timestamp=Timestamp(seconds=1234567890, microseconds=0,), + timestamp=Timestamp( + seconds=1234567890, + microseconds=0, + ), offset_bytes=b"+0200", ), author=COMMITTERS[0], target_type=ObjectType.REVISION, target=b"\x04" * 20, message=b"foo", synthetic=False, raw_manifest=( b"tag 102\x00" b"object 0404040404040404040404040404040404040404\n" b"type commit\n" b"tag v0.0.1\n" b"tagger foo 1234567890 +200" # missing leading 0 for timezone b"\n\nfoo" ), ), ] ORIGINS = [ - Origin(url="https://somewhere.org/den/fox",), - Origin(url="https://overtherainbow.org/fox/den",), + 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, + name=b"subprepo1", + perms=0o160000, + type="rev", + target=REVISIONS[1].id, ), ), ), Directory( id=hash_to_bytes("d135a91ac82a754e7f4bdeff8d56ef06d921eb7d"), entries=( DirectoryEntry( - name=b"file1.ext", perms=0o644, type="file", target=b"\x11" * 20, + name=b"file1.ext", + perms=0o644, + type="file", + target=b"\x11" * 20, ), ), raw_manifest=( b"tree 34\x00" + b"00644 file1.ext\x00" # added two leading zeros + b"\x11" * 20 ), ), ] 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, + 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, + 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={}, + type=MetadataAuthorityType.FORGE, + url="http://example.org/", + metadata={}, ), ] METADATA_FETCHERS = [ - MetadataFetcher(name="test-fetcher", version="1.0.0", metadata={},) + 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 eeb5a63..ad42349 100644 --- a/swh/model/tests/test_cli.py +++ b/swh/model/tests/test_cli.py @@ -1,211 +1,213 @@ # 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, + 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_from_disk.py b/swh/model/tests/test_from_disk.py index fa3d8b6..b7674d4 100644 --- a/swh/model/tests/test_from_disk.py +++ b/swh/model/tests/test_from_disk.py @@ -1,996 +1,1001 @@ # 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 from collections import defaultdict import os import tarfile import tempfile from typing import ClassVar, Optional import unittest import pytest from swh.model import from_disk, model from swh.model.from_disk import Content, DentryPerms, Directory, DiskBackedContent from swh.model.hashutil import DEFAULT_ALGORITHMS, hash_to_bytes, hash_to_hex TEST_DATA = os.path.join(os.path.dirname(__file__), "data") class ModeToPerms(unittest.TestCase): def setUp(self): super().setUp() # Generate a full permissions map self.perms_map = {} # Symlinks for i in range(0o120000, 0o127777 + 1): self.perms_map[i] = DentryPerms.symlink # Directories for i in range(0o040000, 0o047777 + 1): self.perms_map[i] = DentryPerms.directory # Other file types: socket, regular file, block device, character # device, fifo all map to regular files for ft in [0o140000, 0o100000, 0o060000, 0o020000, 0o010000]: for i in range(ft, ft + 0o7777 + 1): if i & 0o111: # executable bits are set self.perms_map[i] = DentryPerms.executable_content else: self.perms_map[i] = DentryPerms.content def test_exhaustive_mode_to_perms(self): for fmode, perm in self.perms_map.items(): self.assertEqual(perm, from_disk.mode_to_perms(fmode)) class TestDiskBackedContent(unittest.TestCase): def test_with_data(self): expected_content = model.Content( length=42, status="visible", data=b"foo bar", sha1=b"foo", sha1_git=b"bar", sha256=b"baz", blake2s256=b"qux", ) with tempfile.NamedTemporaryFile(mode="w+b") as fd: content = DiskBackedContent( length=42, status="visible", path=fd.name, sha1=b"foo", sha1_git=b"bar", sha256=b"baz", blake2s256=b"qux", ) fd.write(b"foo bar") fd.seek(0) content_with_data = content.with_data() assert expected_content == content_with_data def test_lazy_data(self): with tempfile.NamedTemporaryFile(mode="w+b") as fd: fd.write(b"foo") fd.seek(0) content = DiskBackedContent( length=42, status="visible", path=fd.name, sha1=b"foo", sha1_git=b"bar", sha256=b"baz", blake2s256=b"qux", ) fd.write(b"bar") fd.seek(0) content_with_data = content.with_data() fd.write(b"baz") fd.seek(0) assert content_with_data.data == b"bar" def test_with_data_cannot_read(self): with tempfile.NamedTemporaryFile(mode="w+b") as fd: content = DiskBackedContent( length=42, status="visible", path=fd.name, sha1=b"foo", sha1_git=b"bar", sha256=b"baz", blake2s256=b"qux", ) with pytest.raises(OSError): content.with_data() def test_missing_path(self): with pytest.raises(TypeError): DiskBackedContent( length=42, status="visible", sha1=b"foo", sha1_git=b"bar", sha256=b"baz", blake2s256=b"qux", ) with pytest.raises(TypeError): DiskBackedContent( length=42, status="visible", path=None, sha1=b"foo", sha1_git=b"bar", sha256=b"baz", blake2s256=b"qux", ) class DataMixin: maxDiff = None # type: ClassVar[Optional[int]] def setUp(self): self.tmpdir = tempfile.TemporaryDirectory(prefix="swh.model.from_disk") self.tmpdir_name = os.fsencode(self.tmpdir.name) self.contents = { b"file": { "data": b"42\n", "sha1": hash_to_bytes("34973274ccef6ab4dfaaf86599792fa9c3fe4689"), "sha256": hash_to_bytes( "084c799cd551dd1d8d5c5f9a5d593b2e" "931f5e36122ee5c793c1d08a19839cc0" ), "sha1_git": hash_to_bytes("d81cc0710eb6cf9efd5b920a8453e1e07157b6cd"), "blake2s256": hash_to_bytes( "d5fe1939576527e42cfd76a9455a2432" "fe7f56669564577dd93c4280e76d661d" ), "length": 3, "mode": 0o100644, }, } self.symlinks = { b"symlink": { "data": b"target", "blake2s256": hash_to_bytes( "595d221b30fdd8e10e2fdf18376e688e" "9f18d56fd9b6d1eb6a822f8c146c6da6" ), "sha1": hash_to_bytes("0e8a3ad980ec179856012b7eecf4327e99cd44cd"), "sha1_git": hash_to_bytes("1de565933b05f74c75ff9a6520af5f9f8a5a2f1d"), "sha256": hash_to_bytes( "34a04005bcaf206eec990bd9637d9fdb" "6725e0a0c0d4aebf003f17f4c956eb5c" ), "length": 6, "perms": DentryPerms.symlink, } } self.specials = { b"fifo": os.mkfifo, } self.empty_content = { "data": b"", "length": 0, "blake2s256": hash_to_bytes( "69217a3079908094e11121d042354a7c" "1f55b6482ca1a51e1b250dfd1ed0eef9" ), "sha1": hash_to_bytes("da39a3ee5e6b4b0d3255bfef95601890afd80709"), "sha1_git": hash_to_bytes("e69de29bb2d1d6434b8b29ae775ad8c2e48c5391"), "sha256": hash_to_bytes( "e3b0c44298fc1c149afbf4c8996fb924" "27ae41e4649b934ca495991b7852b855" ), "perms": DentryPerms.content, } self.empty_directory = { "id": hash_to_bytes("4b825dc642cb6eb9a060e54bf8d69288fbee4904"), "entries": [], } # Generated with generate_testdata_from_disk self.tarball_contents = { b"": { "entries": [ { "name": b"bar", "perms": DentryPerms.directory, "target": hash_to_bytes( "3c1f578394f4623f74a0ba7fe761729f59fc6ec4" ), "type": "dir", }, { "name": b"empty-folder", "perms": DentryPerms.directory, "target": hash_to_bytes( "4b825dc642cb6eb9a060e54bf8d69288fbee4904" ), "type": "dir", }, { "name": b"foo", "perms": DentryPerms.directory, "target": hash_to_bytes( "2b41c40f0d1fbffcba12497db71fba83fcca96e5" ), "type": "dir", }, { "name": b"link-to-another-quote", "perms": DentryPerms.symlink, "target": hash_to_bytes( "7d5c08111e21c8a9f71540939998551683375fad" ), "type": "file", }, { "name": b"link-to-binary", "perms": DentryPerms.symlink, "target": hash_to_bytes( "e86b45e538d9b6888c969c89fbd22a85aa0e0366" ), "type": "file", }, { "name": b"link-to-foo", "perms": DentryPerms.symlink, "target": hash_to_bytes( "19102815663d23f8b75a47e7a01965dcdc96468c" ), "type": "file", }, { "name": b"some-binary", "perms": DentryPerms.executable_content, "target": hash_to_bytes( "68769579c3eaadbe555379b9c3538e6628bae1eb" ), "type": "file", }, ], "id": hash_to_bytes("e8b0f1466af8608c8a3fb9879db172b887e80759"), }, b"bar": { "entries": [ { "name": b"barfoo", "perms": DentryPerms.directory, "target": hash_to_bytes( "c3020f6bf135a38c6df3afeb5fb38232c5e07087" ), "type": "dir", } ], "id": hash_to_bytes("3c1f578394f4623f74a0ba7fe761729f59fc6ec4"), }, b"bar/barfoo": { "entries": [ { "name": b"another-quote.org", "perms": DentryPerms.content, "target": hash_to_bytes( "133693b125bad2b4ac318535b84901ebb1f6b638" ), "type": "file", } ], "id": hash_to_bytes("c3020f6bf135a38c6df3afeb5fb38232c5e07087"), }, b"bar/barfoo/another-quote.org": { "blake2s256": hash_to_bytes( "d26c1cad82d43df0bffa5e7be11a60e3" "4adb85a218b433cbce5278b10b954fe8" ), "length": 72, "perms": DentryPerms.content, "sha1": hash_to_bytes("90a6138ba59915261e179948386aa1cc2aa9220a"), "sha1_git": hash_to_bytes("133693b125bad2b4ac318535b84901ebb1f6b638"), "sha256": hash_to_bytes( "3db5ae168055bcd93a4d08285dc99ffe" "e2883303b23fac5eab850273a8ea5546" ), }, b"empty-folder": { "entries": [], "id": hash_to_bytes("4b825dc642cb6eb9a060e54bf8d69288fbee4904"), }, b"foo": { "entries": [ { "name": b"barfoo", "perms": DentryPerms.symlink, "target": hash_to_bytes( "8185dfb2c0c2c597d16f75a8a0c37668567c3d7e" ), "type": "file", }, { "name": b"quotes.md", "perms": DentryPerms.content, "target": hash_to_bytes( "7c4c57ba9ff496ad179b8f65b1d286edbda34c9a" ), "type": "file", }, { "name": b"rel-link-to-barfoo", "perms": DentryPerms.symlink, "target": hash_to_bytes( "acac326ddd63b0bc70840659d4ac43619484e69f" ), "type": "file", }, ], "id": hash_to_bytes("2b41c40f0d1fbffcba12497db71fba83fcca96e5"), }, b"foo/barfoo": { "blake2s256": hash_to_bytes( "e1252f2caa4a72653c4efd9af871b62b" "f2abb7bb2f1b0e95969204bd8a70d4cd" ), "data": b"bar/barfoo", "length": 10, "perms": DentryPerms.symlink, "sha1": hash_to_bytes("9057ee6d0162506e01c4d9d5459a7add1fedac37"), "sha1_git": hash_to_bytes("8185dfb2c0c2c597d16f75a8a0c37668567c3d7e"), "sha256": hash_to_bytes( "29ad3f5725321b940332c78e403601af" "ff61daea85e9c80b4a7063b6887ead68" ), }, b"foo/quotes.md": { "blake2s256": hash_to_bytes( "bf7ce4fe304378651ee6348d3e9336ed" "5ad603d33e83c83ba4e14b46f9b8a80b" ), "length": 66, "perms": DentryPerms.content, "sha1": hash_to_bytes("1bf0bb721ac92c18a19b13c0eb3d741cbfadebfc"), "sha1_git": hash_to_bytes("7c4c57ba9ff496ad179b8f65b1d286edbda34c9a"), "sha256": hash_to_bytes( "caca942aeda7b308859eb56f909ec96d" "07a499491690c453f73b9800a93b1659" ), }, b"foo/rel-link-to-barfoo": { "blake2s256": hash_to_bytes( "d9c327421588a1cf61f316615005a2e9" "c13ac3a4e96d43a24138d718fa0e30db" ), "data": b"../bar/barfoo", "length": 13, "perms": DentryPerms.symlink, "sha1": hash_to_bytes("dc51221d308f3aeb2754db48391b85687c2869f4"), "sha1_git": hash_to_bytes("acac326ddd63b0bc70840659d4ac43619484e69f"), "sha256": hash_to_bytes( "8007d20db2af40435f42ddef4b8ad76b" "80adbec26b249fdf0473353f8d99df08" ), }, b"link-to-another-quote": { "blake2s256": hash_to_bytes( "2d0e73cea01ba949c1022dc10c8a43e6" "6180639662e5dc2737b843382f7b1910" ), "data": b"bar/barfoo/another-quote.org", "length": 28, "perms": DentryPerms.symlink, "sha1": hash_to_bytes("cbeed15e79599c90de7383f420fed7acb48ea171"), "sha1_git": hash_to_bytes("7d5c08111e21c8a9f71540939998551683375fad"), "sha256": hash_to_bytes( "e6e17d0793aa750a0440eb9ad5b80b25" "8076637ef0fb68f3ac2e59e4b9ac3ba6" ), }, b"link-to-binary": { "blake2s256": hash_to_bytes( "9ce18b1adecb33f891ca36664da676e1" "2c772cc193778aac9a137b8dc5834b9b" ), "data": b"some-binary", "length": 11, "perms": DentryPerms.symlink, "sha1": hash_to_bytes("d0248714948b3a48a25438232a6f99f0318f59f1"), "sha1_git": hash_to_bytes("e86b45e538d9b6888c969c89fbd22a85aa0e0366"), "sha256": hash_to_bytes( "14126e97d83f7d261c5a6889cee73619" "770ff09e40c5498685aba745be882eff" ), }, b"link-to-foo": { "blake2s256": hash_to_bytes( "08d6cad88075de8f192db097573d0e82" "9411cd91eb6ec65e8fc16c017edfdb74" ), "data": b"foo", "length": 3, "perms": DentryPerms.symlink, "sha1": hash_to_bytes("0beec7b5ea3f0fdbc95d0dd47f3c5bc275da8a33"), "sha1_git": hash_to_bytes("19102815663d23f8b75a47e7a01965dcdc96468c"), "sha256": hash_to_bytes( "2c26b46b68ffc68ff99b453c1d304134" "13422d706483bfa0f98a5e886266e7ae" ), }, b"some-binary": { "blake2s256": hash_to_bytes( "922e0f7015035212495b090c27577357" "a740ddd77b0b9e0cd23b5480c07a18c6" ), "length": 5, "perms": DentryPerms.executable_content, "sha1": hash_to_bytes("0bbc12d7f4a2a15b143da84617d95cb223c9b23c"), "sha1_git": hash_to_bytes("68769579c3eaadbe555379b9c3538e6628bae1eb"), "sha256": hash_to_bytes( "bac650d34a7638bb0aeb5342646d24e3" "b9ad6b44c9b383621faa482b990a367d" ), }, } def tearDown(self): self.tmpdir.cleanup() def assertContentEqual(self, left, right, *, check_path=False): # noqa if not isinstance(left, Content): raise ValueError("%s is not a Content" % left) if isinstance(right, Content): right = right.get_data() # Compare dictionaries keys = DEFAULT_ALGORITHMS | { "length", "perms", } if check_path: keys |= {"path"} failed = [] for key in keys: try: lvalue = left.data[key] if key == "perms" and "perms" not in right: rvalue = from_disk.mode_to_perms(right["mode"]) else: rvalue = right[key] except KeyError: failed.append(key) continue if lvalue != rvalue: failed.append(key) if failed: raise self.failureException( "Content mismatched:\n" + "\n".join( "content[%s] = %r != %r" % (key, left.data.get(key), right.get(key)) for key in failed ) ) def assertDirectoryEqual(self, left, right): # NoQA if not isinstance(left, Directory): raise ValueError("%s is not a Directory" % left) if isinstance(right, Directory): right = right.get_data() assert left.entries == right["entries"] assert left.hash == right["id"] assert left.to_model() == model.Directory.from_dict(right) def make_contents(self, directory): for filename, content in self.contents.items(): path = os.path.join(directory, filename) with open(path, "wb") as f: f.write(content["data"]) os.chmod(path, content["mode"]) def make_symlinks(self, directory): for filename, symlink in self.symlinks.items(): path = os.path.join(directory, filename) os.symlink(symlink["data"], path) def make_specials(self, directory): for filename, fn in self.specials.items(): path = os.path.join(directory, filename) fn(path) def make_from_tarball(self, directory): tarball = os.path.join(TEST_DATA, "dir-folders", "sample-folder.tgz") with tarfile.open(tarball, "r:gz") as f: f.extractall(os.fsdecode(directory)) class TestContent(DataMixin, unittest.TestCase): def setUp(self): super().setUp() def test_data_to_content(self): for filename, content in self.contents.items(): conv_content = Content.from_bytes( mode=content["mode"], data=content["data"] ) self.assertContentEqual(conv_content, content) self.assertIn(hash_to_hex(conv_content.hash), repr(conv_content)) def test_content_swhid(self): for _, content in self.contents.items(): content_res = Content.from_bytes(mode=content["mode"], data=content["data"]) content_swhid = "swh:1:cnt:" + hash_to_hex(content["sha1_git"]) assert str(content_res.swhid()) == content_swhid class TestDirectory(DataMixin, unittest.TestCase): def setUp(self): super().setUp() def test_directory_swhid(self): directory_swhid = "swh:1:dir:" + hash_to_hex(self.empty_directory["id"]) directory = Directory.from_disk(path=self.tmpdir_name) assert str(directory.swhid()) == directory_swhid class SymlinkToContent(DataMixin, unittest.TestCase): def setUp(self): super().setUp() self.make_symlinks(self.tmpdir_name) def test_symlink_to_content(self): for filename, symlink in self.symlinks.items(): path = os.path.join(self.tmpdir_name, filename) perms = 0o120000 conv_content = Content.from_symlink(path=path, mode=perms) self.assertContentEqual(conv_content, symlink) def test_symlink_to_base_model(self): for filename, symlink in self.symlinks.items(): path = os.path.join(self.tmpdir_name, filename) perms = 0o120000 model_content = Content.from_symlink(path=path, mode=perms).to_model() right = symlink.copy() for key in ("perms", "path", "mode"): right.pop(key, None) right["status"] = "visible" assert model_content == model.Content.from_dict(right) class FileToContent(DataMixin, unittest.TestCase): def setUp(self): super().setUp() self.make_contents(self.tmpdir_name) self.make_symlinks(self.tmpdir_name) self.make_specials(self.tmpdir_name) def test_symlink_to_content(self): for filename, symlink in self.symlinks.items(): path = os.path.join(self.tmpdir_name, filename) conv_content = Content.from_file(path=path) self.assertContentEqual(conv_content, symlink) def test_file_to_content(self): for filename, content in self.contents.items(): path = os.path.join(self.tmpdir_name, filename) conv_content = Content.from_file(path=path) self.assertContentEqual(conv_content, content) def test_special_to_content(self): for filename in self.specials: path = os.path.join(self.tmpdir_name, filename) conv_content = Content.from_file(path=path) self.assertContentEqual(conv_content, self.empty_content) for path in ["/dev/null", "/dev/zero"]: path = os.path.join(self.tmpdir_name, filename) conv_content = Content.from_file(path=path) self.assertContentEqual(conv_content, self.empty_content) def test_symlink_to_content_model(self): for filename, symlink in self.symlinks.items(): path = os.path.join(self.tmpdir_name, filename) model_content = Content.from_file(path=path).to_model() right = symlink.copy() for key in ("perms", "path", "mode"): right.pop(key, None) right["status"] = "visible" assert model_content == model.Content.from_dict(right) def test_file_to_content_model(self): for filename, content in self.contents.items(): path = os.path.join(self.tmpdir_name, filename) model_content = Content.from_file(path=path).to_model() right = content.copy() for key in ("perms", "mode"): right.pop(key, None) assert model_content.with_data() == model.Content.from_dict(right) right["path"] = path del right["data"] assert model_content == DiskBackedContent.from_dict(right) def test_special_to_content_model(self): for filename in self.specials: path = os.path.join(self.tmpdir_name, filename) model_content = Content.from_file(path=path).to_model() right = self.empty_content.copy() for key in ("perms", "path", "mode"): right.pop(key, None) right["status"] = "visible" assert model_content == model.Content.from_dict(right) for path in ["/dev/null", "/dev/zero"]: model_content = Content.from_file(path=path).to_model() right = self.empty_content.copy() for key in ("perms", "path", "mode"): right.pop(key, None) right["status"] = "visible" assert model_content == model.Content.from_dict(right) def test_symlink_max_length(self): for max_content_length in [4, 10]: for filename, symlink in self.symlinks.items(): path = os.path.join(self.tmpdir_name, filename) content = Content.from_file(path=path) if content.data["length"] > max_content_length: with pytest.raises(Exception, match="too large"): Content.from_file( path=path, max_content_length=max_content_length ) else: limited_content = Content.from_file( path=path, max_content_length=max_content_length ) assert content == limited_content def test_file_max_length(self): for max_content_length in [2, 4]: for filename, content in self.contents.items(): path = os.path.join(self.tmpdir_name, filename) content = Content.from_file(path=path) limited_content = Content.from_file( path=path, max_content_length=max_content_length ) assert content.data["length"] == limited_content.data["length"] assert content.data["status"] == "visible" if content.data["length"] > max_content_length: assert limited_content.data["status"] == "absent" assert limited_content.data["reason"] == "Content too large" else: assert limited_content.data["status"] == "visible" def test_special_file_max_length(self): for max_content_length in [None, 0, 1]: for filename in self.specials: path = os.path.join(self.tmpdir_name, filename) content = Content.from_file(path=path) limited_content = Content.from_file( path=path, max_content_length=max_content_length ) assert limited_content == content def test_file_to_content_with_path(self): for filename, content in self.contents.items(): content_w_path = content.copy() path = os.path.join(self.tmpdir_name, filename) content_w_path["path"] = path conv_content = Content.from_file(path=path) self.assertContentEqual(conv_content, content_w_path, check_path=True) @pytest.mark.fs class DirectoryToObjects(DataMixin, unittest.TestCase): def setUp(self): super().setUp() contents = os.path.join(self.tmpdir_name, b"contents") os.mkdir(contents) self.make_contents(contents) symlinks = os.path.join(self.tmpdir_name, b"symlinks") os.mkdir(symlinks) self.make_symlinks(symlinks) specials = os.path.join(self.tmpdir_name, b"specials") os.mkdir(specials) self.make_specials(specials) empties = os.path.join(self.tmpdir_name, b"empty1", b"empty2") os.makedirs(empties) def test_directory_to_objects(self): directory = Directory.from_disk(path=self.tmpdir_name) for name, value in self.contents.items(): self.assertContentEqual(directory[b"contents/" + name], value) for name, value in self.symlinks.items(): self.assertContentEqual(directory[b"symlinks/" + name], value) for name in self.specials: self.assertContentEqual( - directory[b"specials/" + name], self.empty_content, + directory[b"specials/" + name], + self.empty_content, ) self.assertEqual( - directory[b"empty1/empty2"].get_data(), self.empty_directory, + directory[b"empty1/empty2"].get_data(), + self.empty_directory, ) # Raise on non existent file with self.assertRaisesRegex(KeyError, "b'nonexistent'"): directory[b"empty1/nonexistent"] # Raise on non existent directory with self.assertRaisesRegex(KeyError, "b'nonexistentdir'"): directory[b"nonexistentdir/file"] objs = directory.collect() self.assertCountEqual(["content", "directory"], objs) self.assertEqual(len(objs["directory"]), 6) self.assertEqual( len(objs["content"]), len(self.contents) + len(self.symlinks) + 1 ) def test_directory_to_objects_ignore_empty(self): directory = Directory.from_disk( path=self.tmpdir_name, dir_filter=from_disk.ignore_empty_directories ) for name, value in self.contents.items(): self.assertContentEqual(directory[b"contents/" + name], value) for name, value in self.symlinks.items(): self.assertContentEqual(directory[b"symlinks/" + name], value) for name in self.specials: self.assertContentEqual( - directory[b"specials/" + name], self.empty_content, + directory[b"specials/" + name], + self.empty_content, ) # empty directories have been ignored recursively with self.assertRaisesRegex(KeyError, "b'empty1'"): directory[b"empty1"] with self.assertRaisesRegex(KeyError, "b'empty1'"): directory[b"empty1/empty2"] objs = directory.collect() self.assertCountEqual(["content", "directory"], objs) self.assertEqual(len(objs["directory"]), 4) self.assertEqual( len(objs["content"]), len(self.contents) + len(self.symlinks) + 1 ) def test_directory_to_objects_ignore_name(self): directory = Directory.from_disk( path=self.tmpdir_name, dir_filter=from_disk.ignore_named_directories([b"symlinks"]), ) for name, value in self.contents.items(): self.assertContentEqual(directory[b"contents/" + name], value) for name in self.specials: self.assertContentEqual( - directory[b"specials/" + name], self.empty_content, + directory[b"specials/" + name], + self.empty_content, ) self.assertEqual( - directory[b"empty1/empty2"].get_data(), self.empty_directory, + directory[b"empty1/empty2"].get_data(), + self.empty_directory, ) with self.assertRaisesRegex(KeyError, "b'symlinks'"): directory[b"symlinks"] objs = directory.collect() self.assertCountEqual(["content", "directory"], objs) self.assertEqual(len(objs["directory"]), 5) self.assertEqual(len(objs["content"]), len(self.contents) + 1) def test_directory_to_objects_ignore_name_case(self): directory = Directory.from_disk( path=self.tmpdir_name, dir_filter=from_disk.ignore_named_directories( [b"symLiNks"], case_sensitive=False ), ) for name, value in self.contents.items(): self.assertContentEqual(directory[b"contents/" + name], value) for name in self.specials: self.assertContentEqual( - directory[b"specials/" + name], self.empty_content, + directory[b"specials/" + name], + self.empty_content, ) self.assertEqual( - directory[b"empty1/empty2"].get_data(), self.empty_directory, + directory[b"empty1/empty2"].get_data(), + self.empty_directory, ) with self.assertRaisesRegex(KeyError, "b'symlinks'"): directory[b"symlinks"] objs = directory.collect() self.assertCountEqual(["content", "directory"], objs) self.assertEqual(len(objs["directory"]), 5) self.assertEqual(len(objs["content"]), len(self.contents) + 1) def test_directory_entry_order(self): with tempfile.TemporaryDirectory() as dirname: dirname = os.fsencode(dirname) open(os.path.join(dirname, b"foo."), "a") open(os.path.join(dirname, b"foo0"), "a") os.mkdir(os.path.join(dirname, b"foo")) directory = Directory.from_disk(path=dirname) assert [entry["name"] for entry in directory.entries] == [ b"foo.", b"foo", b"foo0", ] @pytest.mark.fs class TarballTest(DataMixin, unittest.TestCase): def setUp(self): super().setUp() self.make_from_tarball(self.tmpdir_name) def test_contents_match(self): directory = Directory.from_disk( path=os.path.join(self.tmpdir_name, b"sample-folder") ) for name, expected in self.tarball_contents.items(): obj = directory[name] if isinstance(obj, Content): self.assertContentEqual(obj, expected) elif isinstance(obj, Directory): self.assertDirectoryEqual(obj, expected) else: raise self.failureException("Unknown type for %s" % obj) class TarballIterDirectory(DataMixin, unittest.TestCase): def setUp(self): super().setUp() self.make_from_tarball(self.tmpdir_name) def test_iter_directory(self): - """Iter from_disk.directory should yield the full arborescence tree - - """ + """Iter from_disk.directory should yield the full arborescence tree""" directory = Directory.from_disk( path=os.path.join(self.tmpdir_name, b"sample-folder") ) contents, skipped_contents, directories = from_disk.iter_directory(directory) expected_nb = defaultdict(int) for name in self.tarball_contents.keys(): obj = directory[name] expected_nb[obj.object_type] += 1 assert len(contents) == expected_nb["content"] and len(contents) > 0 assert len(skipped_contents) == 0 assert len(directories) == expected_nb["directory"] and len(directories) > 0 class DirectoryManipulation(DataMixin, unittest.TestCase): def test_directory_access_nested(self): d = Directory() d[b"a"] = Directory() d[b"a/b"] = Directory() self.assertEqual(d[b"a/b"].get_data(), self.empty_directory) def test_directory_del_nested(self): d = Directory() d[b"a"] = Directory() d[b"a/b"] = Directory() with self.assertRaisesRegex(KeyError, "b'c'"): del d[b"a/b/c"] with self.assertRaisesRegex(KeyError, "b'level2'"): del d[b"a/level2/c"] del d[b"a/b"] self.assertEqual(d[b"a"].get_data(), self.empty_directory) def test_directory_access_self(self): d = Directory() self.assertIs(d, d[b""]) self.assertIs(d, d[b"/"]) self.assertIs(d, d[b"//"]) def test_directory_access_wrong_type(self): d = Directory() with self.assertRaisesRegex(ValueError, "bytes from Directory"): d["foo"] with self.assertRaisesRegex(ValueError, "bytes from Directory"): d[42] def test_directory_repr(self): entries = [b"a", b"b", b"c"] d = Directory() for entry in entries: d[entry] = Directory() r = repr(d) self.assertIn(hash_to_hex(d.hash), r) for entry in entries: self.assertIn(str(entry), r) def test_directory_set_wrong_type_name(self): d = Directory() with self.assertRaisesRegex(ValueError, "bytes Directory entry"): d["foo"] = Directory() with self.assertRaisesRegex(ValueError, "bytes Directory entry"): d[42] = Directory() def test_directory_set_nul_in_name(self): d = Directory() with self.assertRaisesRegex(ValueError, "nul bytes"): d[b"\x00\x01"] = Directory() def test_directory_set_empty_name(self): d = Directory() with self.assertRaisesRegex(ValueError, "must have a name"): d[b""] = Directory() with self.assertRaisesRegex(ValueError, "must have a name"): d[b"/"] = Directory() def test_directory_set_wrong_type(self): d = Directory() with self.assertRaisesRegex(ValueError, "Content or Directory"): d[b"entry"] = object() def test_directory_del_wrong_type(self): d = Directory() with self.assertRaisesRegex(ValueError, "bytes Directory entry"): del d["foo"] with self.assertRaisesRegex(ValueError, "bytes Directory entry"): del d[42] def test_directory_contains(self): d = Directory() d[b"a"] = Directory() d[b"a/b"] = Directory() d[b"a/b/c"] = Directory() d[b"a/b/c/d"] = Content() self.assertIn(b"a", d) self.assertIn(b"a/b", d) self.assertIn(b"a/b/c", d) self.assertIn(b"a/b/c/d", d) self.assertNotIn(b"b", d) self.assertNotIn(b"b/c", d) self.assertNotIn(b"b/c/d", d) diff --git a/swh/model/tests/test_identifiers.py b/swh/model/tests/test_identifiers.py index 6214584..793e6d5 100644 --- a/swh/model/tests/test_identifiers.py +++ b/swh/model/tests/test_identifiers.py @@ -1,1187 +1,1339 @@ # 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 datetime import hashlib from typing import Dict import unittest import pytest from swh.model import git_objects, hashutil from swh.model.hashutil import hash_to_bytes as _x from swh.model.model import ( Content, Directory, ExtID, Origin, RawExtrinsicMetadata, Release, Revision, Snapshot, TimestampWithTimezone, ) 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 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,}, + b"1448210036": { + "seconds": 1448210036, + "microseconds": 0, + }, + b"1448210036.002342": { + "seconds": 1448210036, + "microseconds": 2342, + }, + b"1448210036.12": { + "seconds": 1448210036, + "microseconds": 120000, + }, } def test_format_date(self): for date_repr, date in self.dates.items(): self.assertEqual(git_objects.format_date(date), date_repr) 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( Content.from_data(content_example["data"]).hashes(), self.content_id ) directory_example = { "id": _x("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"), }, ], } class DirectoryIdentifier(unittest.TestCase): def setUp(self): self.directory = directory_example self.empty_directory = { "id": "4b825dc642cb6eb9a060e54bf8d69288fbee4904", "entries": [], } def test_dir_identifier(self): self.assertEqual(Directory.from_dict(self.directory).id, self.directory["id"]) self.assertEqual( - Directory.from_dict(remove_id(self.directory)).id, self.directory["id"], + Directory.from_dict(remove_id(self.directory)).id, + 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( - Directory.from_dict(remove_id(directory)).id, self.directory["id"], + Directory.from_dict(remove_id(directory)).id, + self.directory["id"], ) def test_dir_identifier_empty_directory(self): self.assertEqual( Directory.from_dict(remove_id(self.empty_directory)).id, _x(self.empty_directory["id"]), ) linus_tz = datetime.timezone(datetime.timedelta(minutes=-420)) revision_example = { "id": _x("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": _x("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", "type": "git", "synthetic": False, "metadata": None, } self.synthetic_revision = { "id": _x("b2a7e1260492e344fab3cbf91bc13c91e05426fd"), "author": { "name": b"Software Heritage", "email": b"robot@softwareheritage.org", }, - "date": {"timestamp": {"seconds": 1437047495}, "offset_bytes": b"+0000",}, + "date": { + "timestamp": {"seconds": 1437047495}, + "offset_bytes": b"+0000", + }, "type": "tar", "committer": { "name": b"Software Heritage", "email": b"robot@softwareheritage.org", }, "committer_date": 1437047495, "synthetic": True, "parents": [], "message": b"synthetic revision message\n", "directory": _x("d11f00a6a0fea6055341d25584b5a96516c0d2b8"), "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": _x("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", "type": "git", "synthetic": False, "extra_headers": ( (b"svn-repo-uuid", b"046f1af7-66c2-d61b-5410-ce57b7db7bff"), (b"svn-revision", b"10"), ), } self.revision_with_gpgsig = { "id": _x("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,}, + "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 """, "type": "git", "synthetic": False, } self.revision_no_message = { "id": _x("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,}, + "date": { + "timestamp": 1428538899, + "offset": 480, + }, + "committer": { + "name": b"Jiang Xin", + "email": b"worldhello.net@gmail.com", + }, + "committer_date": { + "timestamp": 1428538899, + "offset": 480, + }, "message": None, "type": "git", "synthetic": False, } self.revision_empty_message = { "id": _x("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,}, + "date": { + "timestamp": 1428538899, + "offset": 480, + }, + "committer": { + "name": b"Jiang Xin", + "email": b"worldhello.net@gmail.com", + }, + "committer_date": { + "timestamp": 1428538899, + "offset": 480, + }, "message": b"", "type": "git", "synthetic": False, } self.revision_only_fullname = { "id": _x("010d34f384fa99d047cdd5e2f41e56e5c2feee45"), "directory": _x("85a74718d377195e1efd0843ba4f3260bad4fe07"), "parents": [_x("01e2d0627a9a6edb24c37db45db5ecb31e9de808")], - "author": {"fullname": b"Linus Torvalds ",}, + "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", "type": "git", "synthetic": False, "extra_headers": ( (b"svn-repo-uuid", b"046f1af7-66c2-d61b-5410-ce57b7db7bff"), (b"svn-revision", b"10"), ), } def test_revision_identifier(self): self.assertEqual( - Revision.from_dict(self.revision).id, self.revision["id"], + Revision.from_dict(self.revision).id, + self.revision["id"], ) self.assertEqual( - Revision.from_dict(remove_id(self.revision)).id, self.revision["id"], + Revision.from_dict(remove_id(self.revision)).id, + self.revision["id"], ) def test_revision_identifier_none_metadata(self): self.assertEqual( Revision.from_dict(remove_id(self.revision_none_metadata)).id, self.revision_none_metadata["id"], ) def test_revision_identifier_synthetic(self): self.assertEqual( Revision.from_dict(remove_id(self.synthetic_revision)).id, self.synthetic_revision["id"], ) def test_revision_identifier_with_extra_headers(self): self.assertEqual( Revision.from_dict(remove_id(self.revision_with_extra_headers)).id, self.revision_with_extra_headers["id"], ) def test_revision_identifier_with_gpgsig(self): self.assertEqual( Revision.from_dict(remove_id(self.revision_with_gpgsig)).id, self.revision_with_gpgsig["id"], ) def test_revision_identifier_no_message(self): self.assertEqual( Revision.from_dict(remove_id(self.revision_no_message)).id, self.revision_no_message["id"], ) def test_revision_identifier_empty_message(self): self.assertEqual( Revision.from_dict(remove_id(self.revision_empty_message)).id, self.revision_empty_message["id"], ) def test_revision_identifier_only_fullname(self): self.assertEqual( Revision.from_dict(remove_id(self.revision_only_fullname)).id, self.revision_only_fullname["id"], ) release_example = { "id": _x("2b10839e32c4c476e9d94492756bb1a3e1ec4aa8"), "target": _x("741b2252a5e14d6c60a913c77a6099abe73a854a"), "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": _x("26791a8bcf0e6d33f43aef7682bdb555236d56de"), "target": _x("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": _x("b6f4f446715f7d9543ef54e41b62982f0db40045"), "target": _x("9ee1c939d1cb936b1f98e8d81aeffab57bae46ab"), "target_type": "revision", "name": b"v2.6.12", - "author": {"name": b"Linus Torvalds", "email": b"torvalds@g5.osdl.org",}, + "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, "synthetic": False, } self.release_empty_message = { "id": _x("71a0aea72444d396575dc25ac37fec87ee3c6492"), "target": _x("9ee1c939d1cb936b1f98e8d81aeffab57bae46ab"), "target_type": "revision", "name": b"v2.6.12", - "author": {"name": b"Linus Torvalds", "email": b"torvalds@g5.osdl.org",}, + "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"", "synthetic": False, } self.release_negative_utc = { "id": _x("97c8d2573a001f88e72d75f596cf86b12b82fd01"), "name": b"20081029", "target": _x("54e9abca4c77421e2921f5f156c9fe4a9f7441c7"), "target_type": "revision", - "date": {"timestamp": {"seconds": 1225281976}, "offset_bytes": b"-0000",}, - "author": {"name": b"Otavio Salvador", "email": b"otavio@debian.org",}, + "date": { + "timestamp": {"seconds": 1225281976}, + "offset_bytes": b"-0000", + }, + "author": { + "name": b"Otavio Salvador", + "email": b"otavio@debian.org", + }, "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": { "offset_bytes": b"+1000", - "timestamp": {"microseconds": 0, "seconds": 1377480558,}, + "timestamp": { + "microseconds": 0, + "seconds": 1377480558, + }, }, "id": _x("5c98f559d034162de22d3ebeb95433e6f8885231"), "message": b"Release of v0.3.2.", "name": b"0.3.2", "synthetic": False, "target": _x("c06aa3d93b78a2865c4935170030f8c2d7396fd3"), "target_type": "revision", } self.release_snapshot_target = dict(self.release) self.release_snapshot_target["target_type"] = "snapshot" self.release_snapshot_target["id"] = _x( "c29c3ddcc6769a04e54dd69d63a6fdcbc566f850" ) def test_release_identifier(self): self.assertEqual( - Release.from_dict(self.release).id, self.release["id"], + Release.from_dict(self.release).id, + self.release["id"], ) self.assertEqual( - Release.from_dict(remove_id(self.release)).id, self.release["id"], + Release.from_dict(remove_id(self.release)).id, + self.release["id"], ) def test_release_identifier_no_author(self): self.assertEqual( Release.from_dict(remove_id(self.release_no_author)).id, self.release_no_author["id"], ) def test_release_identifier_no_message(self): self.assertEqual( Release.from_dict(remove_id(self.release_no_message)).id, self.release_no_message["id"], ) def test_release_identifier_empty_message(self): self.assertEqual( Release.from_dict(remove_id(self.release_empty_message)).id, self.release_empty_message["id"], ) def test_release_identifier_negative_utc(self): self.assertEqual( Release.from_dict(remove_id(self.release_negative_utc)).id, self.release_negative_utc["id"], ) def test_release_identifier_newline_in_author(self): self.assertEqual( Release.from_dict(remove_id(self.release_newline_in_author)).id, self.release_newline_in_author["id"], ) def test_release_identifier_snapshot_target(self): self.assertEqual( Release.from_dict(self.release_snapshot_target).id, 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"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": _x("1a8893e6a86f444e8be8e7bda6cb34fb1735a00e"), "branches": {}, } self.dangling_branch = { "id": _x("c84502e821eb21ed84e9fd3ec40973abc8b32353"), - "branches": {b"HEAD": None,}, + "branches": { + b"HEAD": None, + }, } self.unresolved = { "id": _x("84b4548ea486e4b0a7933fa541ff1503a0afe1e0"), - "branches": {b"foo": {"target": b"bar", "target_type": "alias",},}, + "branches": { + b"foo": { + "target": b"bar", + "target_type": "alias", + }, + }, } self.all_types = snapshot_example def test_empty_snapshot(self): self.assertEqual( - Snapshot.from_dict(remove_id(self.empty)).id, self.empty["id"], + Snapshot.from_dict(remove_id(self.empty)).id, + self.empty["id"], ) def test_dangling_branch(self): self.assertEqual( Snapshot.from_dict(remove_id(self.dangling_branch)).id, self.dangling_branch["id"], ) def test_unresolved(self): with self.assertRaisesRegex(ValueError, "b'foo' -> b'bar'"): Snapshot.from_dict(remove_id(self.unresolved)) def test_all_types(self): self.assertEqual( - Snapshot.from_dict(remove_id(self.all_types)).id, self.all_types["id"], + Snapshot.from_dict(remove_id(self.all_types)).id, + 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": "swh:1:snp:" + "00" * 20, "release": "swh:1:rel:" + "01" * 20, "revision": "swh:1:rev:" + "02" * 20, "path": b"/abc/def", "directory": "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( git_objects.raw_extrinsic_metadata_git_object( RawExtrinsicMetadata.from_dict(self.minimal) ), git_object, ) self.assertEqual( RawExtrinsicMetadata.from_dict(self.minimal).id, hashlib.sha1(git_object).digest(), ) self.assertEqual( RawExtrinsicMetadata.from_dict(self.minimal).id, _x("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( git_objects.raw_extrinsic_metadata_git_object( RawExtrinsicMetadata.from_dict(self.maximal) ), git_object, ) self.assertEqual( RawExtrinsicMetadata.from_dict(self.maximal).id, hashlib.sha1(git_object).digest(), ) self.assertEqual( RawExtrinsicMetadata.from_dict(self.maximal).id, _x("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( git_objects.raw_extrinsic_metadata_git_object( RawExtrinsicMetadata.from_dict(metadata) ), git_object, ) self.assertEqual( RawExtrinsicMetadata.from_dict(metadata).id, hashlib.sha1(git_object).digest(), ) self.assertEqual( RawExtrinsicMetadata.from_dict(metadata).id, _x("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, + 2021, + 1, + 25, + 12, + 27, + 51, + tzinfo=utc_plus_one, ), } self.assertEqual( git_objects.raw_extrinsic_metadata_git_object( RawExtrinsicMetadata.from_dict(self.minimal) ), git_objects.raw_extrinsic_metadata_git_object( RawExtrinsicMetadata.from_dict(metadata) ), ) self.assertEqual( RawExtrinsicMetadata.from_dict(self.minimal).id, RawExtrinsicMetadata.from_dict(metadata).id, ) self.assertEqual( RawExtrinsicMetadata.from_dict(metadata).id, _x("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, + 2021, + 1, + 25, + 11, + 27, + 51, + 123456, + tzinfo=datetime.timezone.utc, ), } self.assertEqual( git_objects.raw_extrinsic_metadata_git_object( RawExtrinsicMetadata.from_dict(self.minimal) ), git_objects.raw_extrinsic_metadata_git_object( RawExtrinsicMetadata.from_dict(metadata) ), ) self.assertEqual( RawExtrinsicMetadata.from_dict(self.minimal).id, RawExtrinsicMetadata.from_dict(metadata).id, ) self.assertEqual( RawExtrinsicMetadata.from_dict(metadata).id, _x("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, + 2021, + 1, + 25, + 11, + 27, + 50, + 1_000_000 - 42, + tzinfo=tz, ), } self.assertEqual( git_objects.raw_extrinsic_metadata_git_object( RawExtrinsicMetadata.from_dict(self.minimal) ), git_objects.raw_extrinsic_metadata_git_object( RawExtrinsicMetadata.from_dict(metadata) ), ) self.assertEqual( RawExtrinsicMetadata.from_dict(self.minimal).id, RawExtrinsicMetadata.from_dict(metadata).id, ) self.assertEqual( RawExtrinsicMetadata.from_dict(metadata).id, _x("5c13f20ba336e44549baf3d7b9305b027ec9f43d"), ) def test_negative_timestamp(self): metadata = { **self.minimal, "discovery_date": datetime.datetime( - 1960, 1, 25, 11, 27, 51, tzinfo=datetime.timezone.utc, + 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( git_objects.raw_extrinsic_metadata_git_object( RawExtrinsicMetadata.from_dict(metadata) ), git_object, ) self.assertEqual( RawExtrinsicMetadata.from_dict(metadata).id, hashlib.sha1(git_object).digest(), ) self.assertEqual( RawExtrinsicMetadata.from_dict(metadata).id, _x("895d0821a2991dd376ddc303424aceb7c68280f9"), ) def test_epoch(self): metadata = { **self.minimal, "discovery_date": datetime.datetime( - 1970, 1, 1, 0, 0, 0, tzinfo=datetime.timezone.utc, + 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( git_objects.raw_extrinsic_metadata_git_object( RawExtrinsicMetadata.from_dict(metadata) ), git_object, ) self.assertEqual( RawExtrinsicMetadata.from_dict(metadata).id, hashlib.sha1(git_object).digest(), ) self.assertEqual( RawExtrinsicMetadata.from_dict(metadata).id, _x("27a53df54ace35ebd910493cdc70b334d6b7cb88"), ) def test_negative_epoch(self): metadata = { **self.minimal, "discovery_date": datetime.datetime( - 1969, 12, 31, 23, 59, 59, 1, tzinfo=datetime.timezone.utc, + 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( git_objects.raw_extrinsic_metadata_git_object( RawExtrinsicMetadata.from_dict(metadata) ), git_object, ) self.assertEqual( RawExtrinsicMetadata.from_dict(metadata).id, hashlib.sha1(git_object).digest(), ) self.assertEqual( RawExtrinsicMetadata.from_dict(metadata).id, _x("be7154a8fd49d87f81547ea634d1e2152907d089"), ) origin_example = { "url": "https://github.com/torvalds/linux", } class OriginIdentifier(unittest.TestCase): def test_content_identifier(self): self.assertEqual( Origin.from_dict(origin_example).id, _x("b63a575fe3faab7692c9f38fb09d4bb45651bb0f"), ) # Format: [ # ( # input1, # expected_output1, # ), # ( # input2, # expected_output2, # ), # ... # ] TS_DICTS = [ # with current input dict format (offset_bytes) ( {"timestamp": 12345, "offset_bytes": b"+0000"}, - {"timestamp": {"seconds": 12345, "microseconds": 0}, "offset_bytes": b"+0000",}, + { + "timestamp": {"seconds": 12345, "microseconds": 0}, + "offset_bytes": b"+0000", + }, ), ( {"timestamp": 12345, "offset_bytes": b"-0000"}, - {"timestamp": {"seconds": 12345, "microseconds": 0}, "offset_bytes": b"-0000",}, + { + "timestamp": {"seconds": 12345, "microseconds": 0}, + "offset_bytes": b"-0000", + }, ), ( {"timestamp": 12345, "offset_bytes": b"+0200"}, - {"timestamp": {"seconds": 12345, "microseconds": 0}, "offset_bytes": b"+0200",}, + { + "timestamp": {"seconds": 12345, "microseconds": 0}, + "offset_bytes": b"+0200", + }, ), ( {"timestamp": 12345, "offset_bytes": b"-0200"}, - {"timestamp": {"seconds": 12345, "microseconds": 0}, "offset_bytes": b"-0200",}, + { + "timestamp": {"seconds": 12345, "microseconds": 0}, + "offset_bytes": b"-0200", + }, ), ( {"timestamp": 12345, "offset_bytes": b"--700"}, - {"timestamp": {"seconds": 12345, "microseconds": 0}, "offset_bytes": b"--700",}, + { + "timestamp": {"seconds": 12345, "microseconds": 0}, + "offset_bytes": b"--700", + }, ), ( {"timestamp": 12345, "offset_bytes": b"1234567"}, { "timestamp": {"seconds": 12345, "microseconds": 0}, "offset_bytes": b"1234567", }, ), # with old-style input dicts (numeric offset + optional negative_utc): ( {"timestamp": 12345, "offset": 0}, - {"timestamp": {"seconds": 12345, "microseconds": 0}, "offset_bytes": b"+0000",}, + { + "timestamp": {"seconds": 12345, "microseconds": 0}, + "offset_bytes": b"+0000", + }, ), ( {"timestamp": 12345, "offset": 0, "negative_utc": False}, - {"timestamp": {"seconds": 12345, "microseconds": 0}, "offset_bytes": b"+0000",}, + { + "timestamp": {"seconds": 12345, "microseconds": 0}, + "offset_bytes": b"+0000", + }, ), ( {"timestamp": 12345, "offset": 0, "negative_utc": False}, - {"timestamp": {"seconds": 12345, "microseconds": 0}, "offset_bytes": b"+0000",}, + { + "timestamp": {"seconds": 12345, "microseconds": 0}, + "offset_bytes": b"+0000", + }, ), ( {"timestamp": 12345, "offset": 0, "negative_utc": None}, - {"timestamp": {"seconds": 12345, "microseconds": 0}, "offset_bytes": b"+0000",}, + { + "timestamp": {"seconds": 12345, "microseconds": 0}, + "offset_bytes": b"+0000", + }, ), ( {"timestamp": {"seconds": 12345}, "offset": 0, "negative_utc": None}, - {"timestamp": {"seconds": 12345, "microseconds": 0}, "offset_bytes": b"+0000",}, + { + "timestamp": {"seconds": 12345, "microseconds": 0}, + "offset_bytes": b"+0000", + }, ), ( { "timestamp": {"seconds": 12345, "microseconds": 0}, "offset": 0, "negative_utc": None, }, - {"timestamp": {"seconds": 12345, "microseconds": 0}, "offset_bytes": b"+0000",}, + { + "timestamp": {"seconds": 12345, "microseconds": 0}, + "offset_bytes": b"+0000", + }, ), ( { "timestamp": {"seconds": 12345, "microseconds": 100}, "offset": 0, "negative_utc": None, }, { "timestamp": {"seconds": 12345, "microseconds": 100}, "offset_bytes": b"+0000", }, ), ( {"timestamp": 12345, "offset": 0, "negative_utc": True}, - {"timestamp": {"seconds": 12345, "microseconds": 0}, "offset_bytes": b"-0000",}, + { + "timestamp": {"seconds": 12345, "microseconds": 0}, + "offset_bytes": b"-0000", + }, ), ( {"timestamp": 12345, "offset": 0, "negative_utc": None}, - {"timestamp": {"seconds": 12345, "microseconds": 0}, "offset_bytes": b"+0000",}, + { + "timestamp": {"seconds": 12345, "microseconds": 0}, + "offset_bytes": b"+0000", + }, ), ] @pytest.mark.parametrize("dict_input,expected", TS_DICTS) def test_normalize_timestamp_dict(dict_input, expected): assert TimestampWithTimezone.from_dict(dict_input).to_dict() == 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"): TimestampWithTimezone.from_dict(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_TZ_BYTES_EXPECTED = [b"-2359", b"-0100", b"+0000", b"+0100", b"+2359"] 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, offset_bytes", zip(TS_TIMEZONES, TS_TZ_EXPECTED, TS_TZ_BYTES_EXPECTED) ) @pytest.mark.parametrize("microsecond", [0, 1, 10, 100, 1000, 999999]) def test_normalize_timestamp_datetime( date, seconds, tz, offset, offset_bytes, microsecond ): date = date.astimezone(tz).replace(microsecond=microsecond) assert TimestampWithTimezone.from_dict(date).to_dict() == { "timestamp": {"seconds": seconds, "microseconds": microsecond}, "offset_bytes": offset_bytes, } def test_extid_identifier_bwcompat(): extid_dict = { "extid_type": "test-type", "extid": b"extid", "target": "swh:1:dir:" + "00" * 20, } assert ExtID.from_dict(extid_dict).id == _x( "b9295e1931c31e40a7e3e1e967decd1c89426455" ) assert ( ExtID.from_dict({**extid_dict, "extid_version": 0}).id == ExtID.from_dict(extid_dict).id ) assert ( ExtID.from_dict({**extid_dict, "extid_version": 1}).id != ExtID.from_dict(extid_dict).id ) diff --git a/swh/model/tests/test_merkle.py b/swh/model/tests/test_merkle.py index 32de872..52edb2c 100644 --- a/swh/model/tests/test_merkle.py +++ b/swh/model/tests/test_merkle.py @@ -1,255 +1,267 @@ # 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 unittest from swh.model import merkle class MerkleTestNode(merkle.MerkleNode): object_type = "tested_merkle_node_type" def __init__(self, data): super().__init__(data) self.compute_hash_called = 0 def compute_hash(self): self.compute_hash_called += 1 child_data = [child + b"=" + self[child].hash for child in sorted(self)] return b"hash(" + b", ".join([self.data["value"]] + child_data) + b")" class MerkleTestLeaf(merkle.MerkleLeaf): object_type = "tested_merkle_leaf_type" def __init__(self, data): super().__init__(data) self.compute_hash_called = 0 def compute_hash(self): self.compute_hash_called += 1 return b"hash(" + self.data["value"] + b")" class TestMerkleLeaf(unittest.TestCase): def setUp(self): self.data = {"value": b"value"} self.instance = MerkleTestLeaf(self.data) def test_equality(self): leaf1 = MerkleTestLeaf(self.data) leaf2 = MerkleTestLeaf(self.data) leaf3 = MerkleTestLeaf({}) self.assertEqual(leaf1, leaf2) self.assertNotEqual(leaf1, leaf3) def test_hash(self): self.assertEqual(self.instance.compute_hash_called, 0) instance_hash = self.instance.hash self.assertEqual(self.instance.compute_hash_called, 1) instance_hash2 = self.instance.hash self.assertEqual(self.instance.compute_hash_called, 1) self.assertEqual(instance_hash, instance_hash2) def test_data(self): self.assertEqual(self.instance.get_data(), self.data) def test_collect(self): collected = self.instance.collect() self.assertEqual( collected, { self.instance.object_type: { self.instance.hash: self.instance.get_data(), }, }, ) collected2 = self.instance.collect() self.assertEqual(collected2, {}) self.instance.reset_collect() collected3 = self.instance.collect() self.assertEqual(collected, collected3) def test_leaf(self): with self.assertRaisesRegex(ValueError, "is a leaf"): self.instance[b"key1"] = "Test" with self.assertRaisesRegex(ValueError, "is a leaf"): del self.instance[b"key1"] with self.assertRaisesRegex(ValueError, "is a leaf"): self.instance[b"key1"] with self.assertRaisesRegex(ValueError, "is a leaf"): self.instance.update(self.data) class TestMerkleNode(unittest.TestCase): maxDiff = None def setUp(self): self.root = MerkleTestNode({"value": b"root"}) self.nodes = {b"root": self.root} for i in (b"a", b"b", b"c"): value = b"root/" + i - node = MerkleTestNode({"value": value,}) + node = MerkleTestNode( + { + "value": value, + } + ) self.root[i] = node self.nodes[value] = node for j in (b"a", b"b", b"c"): value2 = value + b"/" + j - node2 = MerkleTestNode({"value": value2,}) + node2 = MerkleTestNode( + { + "value": value2, + } + ) node[j] = node2 self.nodes[value2] = node2 for k in (b"a", b"b", b"c"): value3 = value2 + b"/" + j - node3 = MerkleTestNode({"value": value3,}) + node3 = MerkleTestNode( + { + "value": value3, + } + ) node2[j] = node3 self.nodes[value3] = node3 def test_equality(self): node1 = merkle.MerkleNode({"foo": b"bar"}) node2 = merkle.MerkleNode({"foo": b"bar"}) node3 = merkle.MerkleNode({}) self.assertEqual(node1, node2) self.assertNotEqual(node1, node3, node1 == node3) node1["foo"] = node3 self.assertNotEqual(node1, node2) node2["foo"] = node3 self.assertEqual(node1, node2) def test_hash(self): for node in self.nodes.values(): self.assertEqual(node.compute_hash_called, 0) # Root hash will compute hash for all the nodes hash = self.root.hash for node in self.nodes.values(): self.assertEqual(node.compute_hash_called, 1) self.assertIn(node.data["value"], hash) # Should use the cached value hash2 = self.root.hash self.assertEqual(hash, hash2) for node in self.nodes.values(): self.assertEqual(node.compute_hash_called, 1) # Should still use the cached value hash3 = self.root.update_hash(force=False) self.assertEqual(hash, hash3) for node in self.nodes.values(): self.assertEqual(node.compute_hash_called, 1) # Force update of the cached value for a deeply nested node self.root[b"a"][b"b"].update_hash(force=True) for key, node in self.nodes.items(): # update_hash rehashes all children if key.startswith(b"root/a/b"): self.assertEqual(node.compute_hash_called, 2) else: self.assertEqual(node.compute_hash_called, 1) hash4 = self.root.hash self.assertEqual(hash, hash4) for key, node in self.nodes.items(): # update_hash also invalidates all parents if key in (b"root", b"root/a") or key.startswith(b"root/a/b"): self.assertEqual(node.compute_hash_called, 2) else: self.assertEqual(node.compute_hash_called, 1) def test_collect(self): collected = self.root.collect() self.assertEqual(len(collected[self.root.object_type]), len(self.nodes)) for node in self.nodes.values(): self.assertTrue(node.collected) collected2 = self.root.collect() self.assertEqual(collected2, {}) def test_iter_tree_with_deduplication(self): nodes = list(self.root.iter_tree()) self.assertCountEqual(nodes, self.nodes.values()) def test_iter_tree_without_deduplication(self): # duplicate existing hash in merkle tree self.root[b"d"] = MerkleTestNode({"value": b"root/c/c/c"}) nodes_dedup = list(self.root.iter_tree()) nodes = list(self.root.iter_tree(dedup=False)) assert nodes != nodes_dedup assert len(nodes) == len(nodes_dedup) + 1 def test_get(self): for key in (b"a", b"b", b"c"): self.assertEqual(self.root[key], self.nodes[b"root/" + key]) with self.assertRaisesRegex(KeyError, "b'nonexistent'"): self.root[b"nonexistent"] def test_del(self): hash_root = self.root.hash hash_a = self.nodes[b"root/a"].hash del self.root[b"a"][b"c"] hash_root2 = self.root.hash hash_a2 = self.nodes[b"root/a"].hash self.assertNotEqual(hash_root, hash_root2) self.assertNotEqual(hash_a, hash_a2) self.assertEqual(self.nodes[b"root/a/c"].parents, []) with self.assertRaisesRegex(KeyError, "b'nonexistent'"): del self.root[b"nonexistent"] def test_update(self): hash_root = self.root.hash hash_b = self.root[b"b"].hash new_children = { b"c": MerkleTestNode({"value": b"root/b/new_c"}), b"d": MerkleTestNode({"value": b"root/b/d"}), } # collect all nodes self.root.collect() self.root[b"b"].update(new_children) # Ensure everyone got reparented self.assertEqual(new_children[b"c"].parents, [self.root[b"b"]]) self.assertEqual(new_children[b"d"].parents, [self.root[b"b"]]) self.assertEqual(self.nodes[b"root/b/c"].parents, []) hash_root2 = self.root.hash self.assertNotEqual(hash_root, hash_root2) self.assertIn(b"root/b/new_c", hash_root2) self.assertIn(b"root/b/d", hash_root2) hash_b2 = self.root[b"b"].hash self.assertNotEqual(hash_b, hash_b2) for key, node in self.nodes.items(): if key in (b"root", b"root/b"): self.assertEqual(node.compute_hash_called, 2) else: self.assertEqual(node.compute_hash_called, 1) # Ensure we collected root, root/b, and both new children collected_after_update = self.root.collect() self.assertCountEqual( collected_after_update[MerkleTestNode.object_type], [ self.nodes[b"root"].hash, self.nodes[b"root/b"].hash, new_children[b"c"].hash, new_children[b"d"].hash, ], ) # test that noop updates doesn't invalidate anything self.root[b"a"][b"b"].update({}) self.assertEqual(self.root.collect(), {}) diff --git a/swh/model/tests/test_model.py b/swh/model/tests/test_model.py index 2e7fa77..8c058b9 100644 --- a/swh/model/tests/test_model.py +++ b/swh/model/tests/test_model.py @@ -1,1518 +1,1641 @@ # 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 collections import copy import datetime import hashlib from typing import Any, List, Optional, Tuple, Union import attr from attrs_strict import AttributeTypeError import dateutil from hypothesis import given from hypothesis.strategies import binary import pytest from swh.model.collections import ImmutableDict from swh.model.from_disk import DentryPerms import swh.model.git_objects from swh.model.hashutil import MultiHash, hash_to_bytes import swh.model.hypothesis_strategies as strategies import swh.model.model from swh.model.model import ( BaseModel, Content, Directory, DirectoryEntry, MetadataAuthority, MetadataAuthorityType, MetadataFetcher, MissingData, Origin, OriginVisit, OriginVisitStatus, Person, RawExtrinsicMetadata, Release, Revision, SkippedContent, Snapshot, TargetType, Timestamp, TimestampWithTimezone, type_validator, ) import swh.model.swhids from swh.model.swhids import CoreSWHID, ExtendedSWHID, ObjectType from swh.model.tests.swh_model_data import TEST_OBJECTS from swh.model.tests.test_identifiers import ( TS_DATETIMES, TS_TIMEZONES, directory_example, metadata_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() @given(strategies.objects()) def test_repr(objtype_and_obj): """Checks every model object has a working repr(), and that it can be eval()uated (so that printed objects can be copy-pasted to write test cases.)""" (obj_type, obj) = objtype_and_obj r = repr(obj) env = { "tzutc": lambda: datetime.timezone.utc, "tzfile": dateutil.tz.tzfile, "hash_to_bytes": hash_to_bytes, **swh.model.swhids.__dict__, **swh.model.model.__dict__, } assert eval(r, env) == obj @attr.s class Cls1: pass @attr.s class Cls2(Cls1): pass _custom_namedtuple = collections.namedtuple("_custom_namedtuple", "a b") class _custom_tuple(tuple): pass # List of (type, valid_values, invalid_values) _TYPE_VALIDATOR_PARAMETERS: List[Tuple[Any, List[Any], List[Any]]] = [ # base types: ( bool, [True, False], [-1, 0, 1, 42, 1000, None, "123", 0.0, (), ("foo",), ImmutableDict()], ), ( int, [-1, 0, 1, 42, 1000, DentryPerms.directory, True, False], [None, "123", 0.0, (), ImmutableDict()], ), ( float, [-1.0, 0.0, 1.0, float("infinity"), float("NaN")], [True, False, None, 1, "1.2", (), ImmutableDict()], ), ( bytes, [b"", b"123"], [None, bytearray(b"\x12\x34"), "123", 0, 123, (), (1, 2, 3), ImmutableDict()], ), (str, ["", "123"], [None, b"123", b"", 0, (), (1, 2, 3), ImmutableDict()]), (None, [None], [b"", b"123", "", "foo", 0, 123, ImmutableDict(), float("NaN")]), # unions: ( Optional[int], [None, -1, 0, 1, 42, 1000, DentryPerms.directory], ["123", 0.0, (), ImmutableDict()], ), ( Optional[bytes], [None, b"", b"123"], ["123", "", 0, (), (1, 2, 3), ImmutableDict()], ), ( Union[str, bytes], ["", "123", b"123", b""], [None, 0, (), (1, 2, 3), ImmutableDict()], ), ( Union[str, bytes, None], ["", "123", b"123", b"", None], [0, (), (1, 2, 3), ImmutableDict()], ), # tuples ( Tuple[str, str], [("foo", "bar"), ("", ""), _custom_namedtuple("", ""), _custom_tuple(("", ""))], [("foo",), ("foo", "bar", "baz"), ("foo", 42), (42, "foo")], ), ( Tuple[str, ...], [ ("foo",), ("foo", "bar"), ("", ""), ("foo", "bar", "baz"), _custom_namedtuple("", ""), _custom_tuple(("", "")), ], [("foo", 42), (42, "foo")], ), # composite generic: ( Tuple[Union[str, int], Union[str, int]], [("foo", "foo"), ("foo", 42), (42, "foo"), (42, 42)], [("foo", b"bar"), (b"bar", "foo")], ), ( Union[Tuple[str, str], Tuple[int, int]], [("foo", "foo"), (42, 42)], [("foo", b"bar"), (b"bar", "foo"), ("foo", 42), (42, "foo")], ), ( Tuple[Tuple[bytes, bytes], ...], [(), ((b"foo", b"bar"),), ((b"foo", b"bar"), (b"baz", b"qux"))], [((b"foo", "bar"),), ((b"foo", b"bar"), ("baz", b"qux"))], ), # standard types: ( datetime.datetime, [ datetime.datetime(2021, 12, 15, 12, 59, 27), datetime.datetime(2021, 12, 15, 12, 59, 27, tzinfo=datetime.timezone.utc), ], [None, 123], ), # ImmutableDict ( ImmutableDict[str, int], [ ImmutableDict(), ImmutableDict({"foo": 42}), ImmutableDict({"foo": 42, "bar": 123}), ], [ImmutableDict({"foo": "bar"}), ImmutableDict({42: 123})], ), # Any: - (object, [-1, 0, 1, 42, 1000, None, "123", 0.0, (), ImmutableDict()], [],), - (Any, [-1, 0, 1, 42, 1000, None, "123", 0.0, (), ImmutableDict()], [],), + ( + object, + [-1, 0, 1, 42, 1000, None, "123", 0.0, (), ImmutableDict()], + [], + ), + ( + Any, + [-1, 0, 1, 42, 1000, None, "123", 0.0, (), ImmutableDict()], + [], + ), ( ImmutableDict[Any, int], [ ImmutableDict(), ImmutableDict({"foo": 42}), ImmutableDict({"foo": 42, "bar": 123}), ImmutableDict({42: 123}), ], [ImmutableDict({"foo": "bar"})], ), ( ImmutableDict[str, Any], [ ImmutableDict(), ImmutableDict({"foo": 42}), ImmutableDict({"foo": "bar"}), ImmutableDict({"foo": 42, "bar": 123}), ], [ImmutableDict({42: 123})], ), # attr objects: ( Timestamp, - [Timestamp(seconds=123, microseconds=0),], + [ + Timestamp(seconds=123, microseconds=0), + ], [None, "2021-09-28T11:27:59", 123], ), - (Cls1, [Cls1(), Cls2()], [None, b"abcd"],), + ( + Cls1, + [Cls1(), Cls2()], + [None, b"abcd"], + ), # enums: ( TargetType, [TargetType.CONTENT, TargetType.ALIAS], ["content", "alias", 123, None], ), ] @pytest.mark.parametrize( "type_,value", [ pytest.param(type_, value, id=f"type={type_}, value={value}") for (type_, values, _) in _TYPE_VALIDATOR_PARAMETERS for value in values ], ) def test_type_validator_valid(type_, value): type_validator()(None, attr.ib(type=type_), value) @pytest.mark.parametrize( "type_,value", [ pytest.param(type_, value, id=f"type={type_}, value={value}") for (type_, _, values) in _TYPE_VALIDATOR_PARAMETERS for value in values ], ) def test_type_validator_invalid(type_, value): with pytest.raises(AttributeTypeError): type_validator()(None, attr.ib(type=type_), value) @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),} + ).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", + 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)) + attr.validate(Timestamp(seconds=2**63 - 1, microseconds=0)) with pytest.raises(ValueError): - Timestamp(seconds=2 ** 63, microseconds=0) + Timestamp(seconds=2**63, microseconds=0) - attr.validate(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) + 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)) + attr.validate(Timestamp(seconds=0, microseconds=10**6 - 1)) with pytest.raises(ValueError): - Timestamp(seconds=0, microseconds=10 ** 6) + 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}) + Timestamp.from_dict({"seconds": 0, "microseconds": 10**6 - 1}) with pytest.raises(ValueError): - Timestamp.from_dict({"seconds": 0, "microseconds": 10 ** 6}) + Timestamp.from_dict({"seconds": 0, "microseconds": 10**6}) # TimestampWithTimezone def test_timestampwithtimezone(): ts = Timestamp(seconds=0, microseconds=0) tstz = TimestampWithTimezone(timestamp=ts, offset_bytes=b"+0000") attr.validate(tstz) assert tstz.offset_minutes() == 0 assert tstz.offset_bytes == b"+0000" tstz = TimestampWithTimezone(timestamp=ts, offset_bytes=b"+0010") attr.validate(tstz) assert tstz.offset_minutes() == 10 assert tstz.offset_bytes == b"+0010" tstz = TimestampWithTimezone(timestamp=ts, offset_bytes=b"-0010") attr.validate(tstz) assert tstz.offset_minutes() == -10 assert tstz.offset_bytes == b"-0010" tstz = TimestampWithTimezone(timestamp=ts, offset_bytes=b"-0000") attr.validate(tstz) assert tstz.offset_minutes() == 0 assert tstz.offset_bytes == b"-0000" tstz = TimestampWithTimezone(timestamp=ts, offset_bytes=b"-1030") attr.validate(tstz) assert tstz.offset_minutes() == -630 assert tstz.offset_bytes == b"-1030" tstz = TimestampWithTimezone(timestamp=ts, offset_bytes=b"+1320") attr.validate(tstz) assert tstz.offset_minutes() == 800 assert tstz.offset_bytes == b"+1320" tstz = TimestampWithTimezone(timestamp=ts, offset_bytes=b"+200") attr.validate(tstz) assert tstz.offset_minutes() == 120 assert tstz.offset_bytes == b"+200" tstz = TimestampWithTimezone(timestamp=ts, offset_bytes=b"+02") attr.validate(tstz) assert tstz.offset_minutes() == 120 assert tstz.offset_bytes == b"+02" tstz = TimestampWithTimezone(timestamp=ts, offset_bytes=b"+2000000000") attr.validate(tstz) assert tstz.offset_minutes() == 0 assert tstz.offset_bytes == b"+2000000000" with pytest.raises(AttributeTypeError): TimestampWithTimezone(timestamp=datetime.datetime.now(), offset_bytes=b"+0000") with pytest.raises((AttributeTypeError, TypeError)): TimestampWithTimezone(timestamp=ts, offset_bytes=0) def test_timestampwithtimezone_from_datetime(): # Typical case 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_bytes=b"+0100" + timestamp=Timestamp( + seconds=1582810759, + microseconds=0, + ), + offset_bytes=b"+0100", ) # Typical case (close to epoch) tz = datetime.timezone(datetime.timedelta(minutes=+60)) date = datetime.datetime(1970, 1, 1, 1, 0, 5, tzinfo=tz) tstz = TimestampWithTimezone.from_datetime(date) assert tstz == TimestampWithTimezone( - timestamp=Timestamp(seconds=5, microseconds=0,), offset_bytes=b"+0100" + timestamp=Timestamp( + seconds=5, + microseconds=0, + ), + offset_bytes=b"+0100", ) # non-integer number of seconds before UNIX epoch date = datetime.datetime( 1969, 12, 31, 23, 59, 59, 100000, tzinfo=datetime.timezone.utc ) tstz = TimestampWithTimezone.from_datetime(date) assert tstz == TimestampWithTimezone( - timestamp=Timestamp(seconds=-1, microseconds=100000,), offset_bytes=b"+0000" + timestamp=Timestamp( + seconds=-1, + microseconds=100000, + ), + offset_bytes=b"+0000", ) # non-integer number of seconds in both the timestamp and the offset tz = datetime.timezone(datetime.timedelta(microseconds=-600000)) date = datetime.datetime(1969, 12, 31, 23, 59, 59, 600000, tzinfo=tz) tstz = TimestampWithTimezone.from_datetime(date) assert tstz == TimestampWithTimezone( - timestamp=Timestamp(seconds=0, microseconds=200000,), offset_bytes=b"+0000" + timestamp=Timestamp( + seconds=0, + microseconds=200000, + ), + offset_bytes=b"+0000", ) # timezone offset with non-integer number of seconds, for dates before epoch # we round down to the previous second, so it should be the same as # 1969-01-01T23:59:59Z tz = datetime.timezone(datetime.timedelta(microseconds=900000)) date = datetime.datetime(1970, 1, 1, 0, 0, 0, tzinfo=tz) tstz = TimestampWithTimezone.from_datetime(date) assert tstz == TimestampWithTimezone( - timestamp=Timestamp(seconds=-1, microseconds=100000,), offset_bytes=b"+0000" + timestamp=Timestamp( + seconds=-1, + microseconds=100000, + ), + offset_bytes=b"+0000", ) 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,), + timestamp=Timestamp( + seconds=1582810759, + microseconds=123456, + ), offset_bytes=b"+0100", ) 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_bytes=b"-0000" + timestamp=Timestamp( + seconds=1582810759, + microseconds=0, + ), + offset_bytes=b"-0000", ) @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. - - """ + """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", + 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). - - """ + """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,) + 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,) + 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"a ": Person( + name=b"a", + email=b"b@c.com", + fullname=b"a ", + ), b"": Person( - name=None, email=b"foo@bar.com", fullname=b"", + 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 ", + 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"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 ", + name=b"more", + email=b"sp@c.es", + fullname=b" more ", + ), + b" <>": Person( + name=None, + email=None, + fullname=b" <>", ), - b" <>": Person(name=None, email=None, fullname=b" <>",), } for person in sorted(tests): expected_person = tests[person] assert expected_person == Person.from_fullname(person) def test_person_comparison(): - """Check only the fullname attribute is used to compare Person objects - - """ + """Check only the fullname attribute is used to compare Person objects""" person = Person(fullname=b"p1", name=None, email=None) assert attr.evolve(person, name=b"toto") == person assert attr.evolve(person, email=b"toto@example.com") == person person = Person(fullname=b"", name=b"toto", email=b"toto@example.com") assert attr.evolve(person, fullname=b"dude") != 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(), + **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(), + **c.to_dict(), + ctime=datetime.datetime.now(), ) # Directory @given(strategies.directories().filter(lambda d: d.raw_manifest is None)) def test_directory_check(directory): directory.check() directory2 = attr.evolve(directory, id=b"\x00" * 20) with pytest.raises(ValueError, match="does not match recomputed hash"): directory2.check() directory2 = attr.evolve( directory, raw_manifest=swh.model.git_objects.directory_git_object(directory) ) with pytest.raises( ValueError, match="non-none raw_manifest attribute, but does not need it." ): directory2.check() @given(strategies.directories().filter(lambda d: d.raw_manifest is None)) def test_directory_raw_manifest(directory): assert "raw_manifest" not in directory.to_dict() raw_manifest = b"foo" id_ = hashlib.new("sha1", raw_manifest).digest() directory2 = attr.evolve(directory, raw_manifest=raw_manifest) assert directory2.to_dict()["raw_manifest"] == raw_manifest with pytest.raises(ValueError, match="does not match recomputed hash"): directory2.check() directory2 = attr.evolve(directory, raw_manifest=raw_manifest, id=id_) assert directory2.id is not None assert directory2.id == id_ != directory.id assert directory2.to_dict()["raw_manifest"] == raw_manifest directory2.check() def test_directory_entry_name_validation(): with pytest.raises(ValueError, match="valid directory entry name."): DirectoryEntry(name=b"foo/", type="dir", target=b"\x00" * 20, perms=0), def test_directory_duplicate_entry_name(): entries = ( DirectoryEntry(name=b"foo", type="file", target=b"\x00" * 20, perms=0), DirectoryEntry(name=b"foo", type="dir", target=b"\x01" * 20, perms=1), ) with pytest.raises(ValueError, match="duplicated entry name"): Directory(entries=entries) entries = ( DirectoryEntry(name=b"foo", type="file", target=b"\x00" * 20, perms=0), DirectoryEntry(name=b"foo", type="file", target=b"\x00" * 20, perms=0), ) with pytest.raises(ValueError, match="duplicated entry name"): Directory(entries=entries) # Release @given(strategies.releases().filter(lambda rel: rel.raw_manifest is None)) def test_release_check(release): release.check() release2 = attr.evolve(release, id=b"\x00" * 20) with pytest.raises(ValueError, match="does not match recomputed hash"): release2.check() release2 = attr.evolve( release, raw_manifest=swh.model.git_objects.release_git_object(release) ) with pytest.raises( ValueError, match="non-none raw_manifest attribute, but does not need it." ): release2.check() @given(strategies.releases().filter(lambda rev: rev.raw_manifest is None)) def test_release_raw_manifest(release): raw_manifest = b"foo" id_ = hashlib.new("sha1", raw_manifest).digest() release2 = attr.evolve(release, raw_manifest=raw_manifest) assert release2.to_dict()["raw_manifest"] == raw_manifest with pytest.raises(ValueError, match="does not match recomputed hash"): release2.check() release2 = attr.evolve(release, raw_manifest=raw_manifest, id=id_) assert release2.id is not None assert release2.id == id_ != release.id assert release2.to_dict()["raw_manifest"] == raw_manifest release2.check() # Revision @given(strategies.revisions().filter(lambda rev: rev.raw_manifest is None)) def test_revision_check(revision): revision.check() revision2 = attr.evolve(revision, id=b"\x00" * 20) with pytest.raises(ValueError, match="does not match recomputed hash"): revision2.check() revision2 = attr.evolve( revision, raw_manifest=swh.model.git_objects.revision_git_object(revision) ) with pytest.raises( ValueError, match="non-none raw_manifest attribute, but does not need it." ): revision2.check() @given(strategies.revisions().filter(lambda rev: rev.raw_manifest is None)) def test_revision_raw_manifest(revision): raw_manifest = b"foo" id_ = hashlib.new("sha1", raw_manifest).digest() revision2 = attr.evolve(revision, raw_manifest=raw_manifest) assert revision2.to_dict()["raw_manifest"] == raw_manifest with pytest.raises(ValueError, match="does not match recomputed hash"): revision2.check() revision2 = attr.evolve(revision, raw_manifest=raw_manifest, id=id_) assert revision2.id is not None assert revision2.id == id_ != revision.id assert revision2.to_dict()["raw_manifest"] == raw_manifest revision2.check() 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 def test_revision_no_author_or_committer_from_dict(): rev_dict = revision_example.copy() rev_dict["author"] = rev_dict["date"] = None rev_dict["committer"] = rev_dict["committer_date"] = None rev_model = Revision.from_dict(rev_dict) assert rev_model.to_dict() == { **rev_dict, "parents": tuple(rev_dict["parents"]), "extra_headers": (), "metadata": None, } def test_revision_none_author_or_committer(): rev_dict = revision_example.copy() rev_dict["author"] = None with pytest.raises(ValueError, match=".*date must be None if author is None.*"): Revision.from_dict(rev_dict) rev_dict = revision_example.copy() rev_dict["committer"] = None with pytest.raises( ValueError, match=".*committer_date must be None if committer is None.*" ): Revision.from_dict(rev_dict) @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", + type=MetadataAuthorityType.FORGE, + url="https://forge.softwareheritage.org", +) +_metadata_fetcher = MetadataFetcher( + name="test-fetcher", + version="0.0.1", ) -_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, + 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",}, + "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,) + 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,) + 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, + target=_origin_swhid, + origin=_origin_url, + **_common_metadata_fields, ) # but all other types can RawExtrinsicMetadata( - target=_content_swhid, origin=_origin_url, **_common_metadata_fields, + 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, + 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, + 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, + 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, + 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,), + 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,), + 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,), + 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, + 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,), + 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, + target=_origin_swhid, + path=b"/foo/bar", + **_common_metadata_fields, ) # but content can RawExtrinsicMetadata( - target=_content_swhid, path=b"/foo/bar", **_common_metadata_fields, + 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, + 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,), + 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, + 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, + 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, + target=_content_swhid, + discovery_date=date_with_tz, + **fields_copy, ) assert md.discovery_date == truncated_date assert md.discovery_date.tzinfo == datetime.timezone.utc diff --git a/swh/model/tests/test_swh_model_data.py b/swh/model/tests/test_swh_model_data.py index 5e2521d..e9d7374 100644 --- a/swh/model/tests/test_swh_model_data.py +++ b/swh/model/tests/test_swh_model_data.py @@ -1,54 +1,54 @@ # Copyright (C) 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 attr import pytest from swh.model.tests.swh_model_data import TEST_OBJECTS @pytest.mark.parametrize("object_type, objects", TEST_OBJECTS.items()) def test_swh_model_data(object_type, objects): """checks model objects in swh_model_data are in correct shape""" assert objects for obj in objects: assert obj.object_type == object_type attr.validate(obj) @pytest.mark.parametrize( - "object_type", ("directory", "revision", "release", "snapshot"), + "object_type", + ("directory", "revision", "release", "snapshot"), ) def test_swh_model_data_hash(object_type): for obj in TEST_OBJECTS[object_type]: assert ( obj.compute_hash() == obj.id ), f"{obj.compute_hash().hex()} != {obj.id.hex()}" def test_ensure_visit_status_date_consistency(): """ensure origin-visit-status dates are more recent than their visit counterpart 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}... """ visits = TEST_OBJECTS["origin_visit"] visit_statuses = TEST_OBJECTS["origin_visit_status"] for visit, visit_status in zip(visits, visit_statuses): assert visit.origin == visit_status.origin assert visit.visit == visit_status.visit assert visit.date < visit_status.date def test_ensure_visit_status_snapshot_consistency(): - """ensure origin-visit-status snapshots exist in the test dataset - """ + """ensure origin-visit-status snapshots exist in the test dataset""" snapshots = [snp.id for snp in TEST_OBJECTS["snapshot"]] for visit_status in TEST_OBJECTS["origin_visit_status"]: if visit_status.snapshot: assert visit_status.snapshot in snapshots diff --git a/swh/model/tests/test_swhids.py b/swh/model/tests/test_swhids.py index 34a55f6..5c3cab2 100644 --- a/swh/model/tests/test_swhids.py +++ b/swh/model/tests/test_swhids.py @@ -1,638 +1,801 @@ # 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 itertools import attr import pytest from swh.model.exceptions import ValidationError from swh.model.hashutil import hash_to_bytes as _x from swh.model.swhids import ( SWHID_QUALIFIERS, CoreSWHID, ExtendedObjectType, ExtendedSWHID, ObjectType, QualifiedSWHID, ) dummy_qualifiers = {"origin": "https://example.com", "lines": "42"} # 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),), + 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),), + 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),), + 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),), + 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),), + 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),), + 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), + 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": 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": 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"}, + 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"}, + 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,), + ( + 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, + object_type=ObjectType.DIRECTORY, + object_id=object_id, + **dummy_qualifiers, ) ) == hash( QualifiedSWHID( - object_type=ObjectType.DIRECTORY, object_id=object_id, **dummy_qualifiers, + 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, + object_type=ObjectType.DIRECTORY, + object_id=object_id, + **dummy_qualifiers, ) == QualifiedSWHID( - object_type=ObjectType.DIRECTORY, object_id=object_id, **dummy_qualifiers, + object_type=ObjectType.DIRECTORY, + object_id=object_id, + **dummy_qualifiers, ) assert QualifiedSWHID( - object_type=ObjectType.DIRECTORY, object_id=object_id, **dummy_qualifiers, + object_type=ObjectType.DIRECTORY, + object_id=object_id, + **dummy_qualifiers, ) == QualifiedSWHID( - object_type=ObjectType.DIRECTORY, object_id=object_id, **dummy_qualifiers, + 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,), + ( + 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), + 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), + 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,), + ( + 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), + 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,)) + 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,)) + 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,) + 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,) + 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), + 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,) + ExtendedSWHID( + object_type=ExtendedObjectType.DIRECTORY, + object_id=object_id, + ) ) == hash( - ExtendedSWHID(object_type=ExtendedObjectType.DIRECTORY, object_id=object_id,) + 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,) + ExtendedSWHID( + object_type=ExtendedObjectType.DIRECTORY, + object_id=object_id, + ) ) == hash( - ExtendedSWHID(object_type=ExtendedObjectType.DIRECTORY, object_id=object_id,) + 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,) + 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,) + 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