diff --git a/swh/storage/converters.py b/swh/storage/converters.py
index 30ff4a09..97b7be5e 100644
--- a/swh/storage/converters.py
+++ b/swh/storage/converters.py
@@ -1,354 +1,391 @@
# 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 swh.core.utils import decode_with_escape, encode_with_unescape
DEFAULT_AUTHOR = {
'fullname': None,
'name': None,
'email': None,
}
DEFAULT_DATE = {
'timestamp': None,
'offset': 0,
'neg_utc_offset': None,
}
def author_to_db(author):
"""Convert a swh-model author to its DB representation.
Args: a swh-model compatible author
Returns:
a dict containing three keys: author, fullname and email
"""
if author is None:
return DEFAULT_AUTHOR
return author
def db_to_author(id, fullname, name, email):
"""Convert the DB representation of an author to a swh-model author.
Args:
id (long): the author's identifier
fullname (bytes): the author's fullname
name (bytes): the author's name
email (bytes): the author's email
Returns:
a dict with four keys: id, fullname, name and email, or None if the id
is None
"""
if id is None:
return None
return {
'id': id,
'fullname': fullname,
'name': name,
'email': email,
}
def git_headers_to_db(git_headers):
"""Convert git headers to their database representation.
We convert the bytes to unicode by decoding them into utf-8 and replacing
invalid utf-8 sequences with backslash escapes.
"""
ret = []
for key, values in git_headers:
if isinstance(values, list):
ret.append([key, [decode_with_escape(value) for value in values]])
else:
ret.append([key, decode_with_escape(values)])
return ret
def db_to_git_headers(db_git_headers):
ret = []
for key, values in db_git_headers:
if isinstance(values, list):
ret.append([key, [encode_with_unescape(value)
for value in values]])
else:
ret.append([key, encode_with_unescape(values)])
return ret
def db_to_date(date, offset, neg_utc_offset):
"""Convert the DB representation of a date to a swh-model compatible date.
Args:
date (datetime.datetime): a date pulled out of the database
offset (int): an integer number of minutes representing an UTC offset
neg_utc_offset (boolean): whether an utc offset is negative
Returns:
a dict with three keys:
timestamp: a timestamp from UTC
offset: the number of minutes since UTC
negative_utc: whether a null UTC offset is negative
"""
if date is None:
return None
return {
'timestamp': date.timestamp(),
'offset': offset,
'negative_utc': neg_utc_offset,
}
def date_to_db(date_offset):
"""Convert a swh-model date_offset to its DB representation.
Args: a swh-model compatible date_offset
Returns:
a dict with three keys:
timestamp: a date in ISO format
offset: the UTC offset in minutes
neg_utc_offset: a boolean indicating whether a null offset is
negative or positive.
"""
if date_offset is None:
return DEFAULT_DATE
if isinstance(date_offset, numbers.Real):
date_offset = datetime.datetime.fromtimestamp(date_offset,
tz=datetime.timezone.utc)
if isinstance(date_offset, datetime.datetime):
timestamp = date_offset
utcoffset = date_offset.utcoffset()
offset = int(utcoffset.total_seconds()) // 60
neg_utc_offset = False if offset == 0 else None
else:
if isinstance(date_offset['timestamp'], numbers.Real):
timestamp = datetime.datetime.fromtimestamp(
date_offset['timestamp'], tz=datetime.timezone.utc)
else:
timestamp = date_offset['timestamp']
offset = date_offset['offset']
neg_utc_offset = date_offset.get('negative_utc', None)
return {
'timestamp': timestamp.isoformat(),
'offset': offset,
'neg_utc_offset': neg_utc_offset,
}
def revision_to_db(revision):
"""Convert a swh-model revision to its database representation.
"""
author = author_to_db(revision['author'])
date = date_to_db(revision['date'])
committer = author_to_db(revision['committer'])
committer_date = date_to_db(revision['committer_date'])
metadata = revision['metadata']
if metadata and 'extra_headers' in metadata:
metadata = metadata.copy()
extra_headers = git_headers_to_db(metadata['extra_headers'])
metadata['extra_headers'] = extra_headers
return {
'id': revision['id'],
'author_fullname': author['fullname'],
'author_name': author['name'],
'author_email': author['email'],
'date': date['timestamp'],
'date_offset': date['offset'],
'date_neg_utc_offset': date['neg_utc_offset'],
'committer_fullname': committer['fullname'],
'committer_name': committer['name'],
'committer_email': committer['email'],
'committer_date': committer_date['timestamp'],
'committer_date_offset': committer_date['offset'],
'committer_date_neg_utc_offset': committer_date['neg_utc_offset'],
'type': revision['type'],
'directory': revision['directory'],
'message': revision['message'],
'metadata': metadata,
'synthetic': revision['synthetic'],
'parents': [
{
'id': revision['id'],
'parent_id': parent,
'parent_rank': i,
} for i, parent in enumerate(revision['parents'])
],
}
def db_to_revision(db_revision):
"""Convert a database representation of a revision to its swh-model
representation."""
author = db_to_author(
db_revision['author_id'],
db_revision['author_fullname'],
db_revision['author_name'],
db_revision['author_email'],
)
date = db_to_date(
db_revision['date'],
db_revision['date_offset'],
db_revision['date_neg_utc_offset'],
)
committer = db_to_author(
db_revision['committer_id'],
db_revision['committer_fullname'],
db_revision['committer_name'],
db_revision['committer_email'],
)
committer_date = db_to_date(
db_revision['committer_date'],
db_revision['committer_date_offset'],
db_revision['committer_date_neg_utc_offset']
)
metadata = db_revision['metadata']
if metadata and 'extra_headers' in metadata:
extra_headers = db_to_git_headers(metadata['extra_headers'])
metadata['extra_headers'] = extra_headers
parents = []
if 'parents' in db_revision:
for parent in db_revision['parents']:
if parent:
parents.append(parent)
ret = {
'id': db_revision['id'],
'author': author,
'date': date,
'committer': committer,
'committer_date': committer_date,
'type': db_revision['type'],
'directory': db_revision['directory'],
'message': db_revision['message'],
'metadata': metadata,
'synthetic': db_revision['synthetic'],
'parents': parents,
}
if 'object_id' in db_revision:
ret['object_id'] = db_revision['object_id']
return ret
def release_to_db(release):
"""Convert a swh-model release to its database representation.
"""
author = author_to_db(release['author'])
date = date_to_db(release['date'])
return {
'id': release['id'],
'author_fullname': author['fullname'],
'author_name': author['name'],
'author_email': author['email'],
'date': date['timestamp'],
'date_offset': date['offset'],
'date_neg_utc_offset': date['neg_utc_offset'],
'name': release['name'],
'target': release['target'],
'target_type': release['target_type'],
'comment': release['message'],
'synthetic': release['synthetic'],
}
def db_to_release(db_release):
"""Convert a database representation of a release to its swh-model
representation.
"""
author = db_to_author(
db_release['author_id'],
db_release['author_fullname'],
db_release['author_name'],
db_release['author_email'],
)
date = db_to_date(
db_release['date'],
db_release['date_offset'],
db_release['date_neg_utc_offset']
)
ret = {
'author': author,
'date': date,
'id': db_release['id'],
'name': db_release['name'],
'message': db_release['comment'],
'synthetic': db_release['synthetic'],
'target': db_release['target'],
'target_type': db_release['target_type'],
}
if 'object_id' in db_release:
ret['object_id'] = db_release['object_id']
return ret
def ctags_to_db(ctags):
"""Convert a ctags entry into a ready ctags entry.
Args:
ctags (dict): ctags entry with the following keys:
- id (bytes): content's identifier
+ - tool_name (str): tool name used to compute ctags
+ - tool_version (str): associated tool's version
- ctags ([dict]): List of dictionary with the following keys:
- name (str): symbol's name
- kind (str): symbol's kind
- line (int): symbol's line in the content
- language (str): language
Returns:
List of ctags ready entry (dict with the following keys):
- id (bytes): content's identifier
- name (str): symbol's name
- kind (str): symbol's kind
- language (str): language for that content
+ - tool_name (str): tool name used to compute ctags
+ - tool_version (str): associated tool's version
"""
res = []
id = ctags['id']
tool_name = ctags['tool_name']
tool_version = ctags['tool_version']
for ctag in ctags['ctags']:
res.append({
'id': id,
'name': ctag['name'],
'kind': ctag['kind'],
'line': ctag['line'],
'lang': ctag['lang'],
'tool_name': tool_name,
'tool_version': tool_version,
})
return res
+
+
+def db_to_ctags(ctag):
+ """Convert a ctags entry into a ready ctags entry.
+
+ Args:
+ ctags (dict): ctags entry with the following keys:
+ - id (bytes): content's identifier
+ - ctags ([dict]): List of dictionary with the following keys:
+ - name (str): symbol's name
+ - kind (str): symbol's kind
+ - line (int): symbol's line in the content
+ - language (str): language
+
+ Returns:
+ List of ctags ready entry (dict with the following keys):
+ - id (bytes): content's identifier
+ - name (str): symbol's name
+ - kind (str): symbol's kind
+ - language (str): language for that content
+
+ """
+ return {
+ 'id': ctag['id'],
+ 'name': ctag['name'],
+ 'kind': ctag['kind'],
+ 'line': ctag['line'],
+ 'lang': ctag['lang'],
+ 'tool': {
+ 'name': ctag['tool_name'],
+ 'version': ctag['tool_version'],
+ }
+ }
diff --git a/swh/storage/storage.py b/swh/storage/storage.py
index 52e84424..46acdc06 100644
--- a/swh/storage/storage.py
+++ b/swh/storage/storage.py
@@ -1,1549 +1,1549 @@
# Copyright (C) 2015-2016 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 datetime
import itertools
import dateutil.parser
import psycopg2
from . import converters
from .common import db_transaction_generator, db_transaction
from .db import Db
from .exc import StorageDBError
from swh.core.hashutil import ALGORITHMS
from swh.objstorage import PathSlicingObjStorage
from swh.objstorage.exc import ObjNotFoundError
# Max block size of contents to return
BULK_BLOCK_CONTENT_LEN_MAX = 10000
class Storage():
"""SWH storage proxy, encompassing DB and object storage
"""
def __init__(self, db_conn, obj_root):
"""
Args:
db_conn: either a libpq connection string, or a psycopg2 connection
obj_root: path to the root of the object storage
"""
try:
if isinstance(db_conn, psycopg2.extensions.connection):
self.db = Db(db_conn)
else:
self.db = Db.connect(db_conn)
except psycopg2.OperationalError as e:
raise StorageDBError(e)
# TODO this needs to be configured
self.objstorage = PathSlicingObjStorage(obj_root,
slicing='0:2/2:4/4:6')
def check_config(self, *, check_write):
"""Check that the storage is configured and ready to go."""
if not self.objstorage.check_config(check_write=check_write):
return False
# Check permissions on one of the tables
with self.db.transaction() as cur:
if check_write:
check = 'INSERT'
else:
check = 'SELECT'
cur.execute(
"select has_table_privilege(current_user, 'content', %s)",
(check,)
)
return cur.fetchone()[0]
return True
def content_add(self, content):
"""Add content blobs to the storage
Note: in case of DB errors, objects might have already been added to
the object storage and will not be removed. Since addition to the
object storage is idempotent, that should not be a problem.
Args:
content: iterable of dictionaries representing individual pieces of
content to add. Each dictionary has the following keys:
- data (bytes): the actual content
- length (int): content length (default: -1)
- one key for each checksum algorithm in
swh.core.hashutil.ALGORITHMS, mapped to the corresponding
checksum
- status (str): one of visible, hidden, absent
- reason (str): if status = absent, the reason why
- origin (int): if status = absent, the origin we saw the
content in
"""
db = self.db
content_by_status = defaultdict(list)
for d in content:
if 'status' not in d:
d['status'] = 'visible'
if 'length' not in d:
d['length'] = -1
content_by_status[d['status']].append(d)
content_with_data = content_by_status['visible']
content_without_data = content_by_status['absent']
missing_content = set(self.content_missing(content_with_data))
missing_skipped = set(
sha1_git for sha1, sha1_git, sha256
in self.skipped_content_missing(content_without_data))
with db.transaction() as cur:
if missing_content:
# create temporary table for metadata injection
db.mktemp('content', cur)
def add_to_objstorage(cont):
self.objstorage.add(cont['data'],
obj_id=cont['sha1'])
content_filtered = (cont for cont in content_with_data
if cont['sha1'] in missing_content)
db.copy_to(content_filtered, 'tmp_content',
['sha1', 'sha1_git', 'sha256', 'length', 'status'],
cur, item_cb=add_to_objstorage)
# move metadata in place
db.content_add_from_temp(cur)
if missing_skipped:
missing_filtered = (cont for cont in content_without_data
if cont['sha1_git'] in missing_skipped)
db.mktemp('skipped_content', cur)
db.copy_to(missing_filtered, 'tmp_skipped_content',
['sha1', 'sha1_git', 'sha256', 'length',
'reason', 'status', 'origin'], cur)
# move metadata in place
db.skipped_content_add_from_temp(cur)
def content_get(self, content):
"""Retrieve in bulk contents and their data.
Args:
content: iterables of sha1
Returns:
Generates streams of contents as dict with their raw data:
- sha1: sha1's content
- data: bytes data of the content
Raises:
ValueError in case of too much contents are required.
cf. BULK_BLOCK_CONTENT_LEN_MAX
"""
# FIXME: Improve on server module to slice the result
if len(content) > BULK_BLOCK_CONTENT_LEN_MAX:
raise ValueError(
"Send at maximum %s contents." % BULK_BLOCK_CONTENT_LEN_MAX)
for obj_id in content:
try:
data = self.objstorage.get(obj_id)
except ObjNotFoundError:
yield None
continue
yield {'sha1': obj_id, 'data': data}
@db_transaction_generator
def content_get_metadata(self, content, cur=None):
"""Retrieve content metadata in bulk
Args:
content: iterable of content identifiers (sha1)
Returns:
an iterable with content metadata corresponding to the given ids
"""
db = self.db
db.store_tmp_bytea(content, cur)
for content_metadata in db.content_get_metadata_from_temp(cur):
yield dict(zip(db.content_get_metadata_keys, content_metadata))
@db_transaction_generator
def content_missing(self, content, key_hash='sha1', cur=None):
"""List content missing from storage
Args:
content: iterable of dictionaries containing one key for each
checksum algorithm in swh.core.hashutil.ALGORITHMS, mapped to
the corresponding checksum, and a length key mapped to the
content length.
key_hash: the name of the hash used as key (default: 'sha1')
Returns:
an iterable of `key_hash`es missing from the storage
Raises:
TODO: an exception when we get a hash collision.
"""
db = self.db
keys = ['sha1', 'sha1_git', 'sha256']
if key_hash not in keys:
raise ValueError("key_hash should be one of %s" % keys)
key_hash_idx = keys.index(key_hash)
# Create temporary table for metadata injection
db.mktemp('content', cur)
db.copy_to(content, 'tmp_content', keys + ['length'], cur)
for obj in db.content_missing_from_temp(cur):
yield obj[key_hash_idx]
@db_transaction_generator
def content_missing_per_sha1(self, contents, cur=None):
"""List content missing from storage based only on sha1.
Args:
contents: Iterable of sha1 to check for absence.
Returns:
an iterable of `sha1`s missing from the storage.
Raises:
TODO: an exception when we get a hash collision.
"""
db = self.db
db.store_tmp_bytea(contents, cur)
for obj in db.content_missing_per_sha1_from_temp(cur):
yield obj[0]
@db_transaction_generator
def skipped_content_missing(self, content, cur=None):
"""List skipped_content missing from storage
Args:
content: iterable of dictionaries containing the data for each
checksum algorithm.
Returns:
an iterable of signatures missing from the storage
"""
keys = ['sha1', 'sha1_git', 'sha256']
db = self.db
db.mktemp('skipped_content', cur)
db.copy_to(content, 'tmp_skipped_content',
keys + ['length', 'reason'], cur)
yield from db.skipped_content_missing_from_temp(cur)
@db_transaction
def content_find(self, content, cur=None):
"""Find a content hash in db.
Args:
content: a dictionary representing one content hash, mapping
checksum algorithm names (see swh.core.hashutil.ALGORITHMS) to
checksum values
Returns:
a triplet (sha1, sha1_git, sha256) if the content exist
or None otherwise.
Raises:
ValueError in case the key of the dictionary is not sha1, sha1_git
nor sha256.
"""
db = self.db
if not set(content).intersection(ALGORITHMS):
raise ValueError('content keys must contain at least one of: '
'sha1, sha1_git, sha256')
c = db.content_find(sha1=content.get('sha1'),
sha1_git=content.get('sha1_git'),
sha256=content.get('sha256'),
cur=cur)
if c:
keys = ['sha1', 'sha1_git', 'sha256', 'length', 'ctime', 'status']
return dict(zip(keys, c))
return None
@db_transaction_generator
def content_find_provenance(self, content, cur=None):
"""Find content's provenance information.
Args:
content: a dictionary entry representing one content hash.
The dictionary key is one of swh.core.hashutil.ALGORITHMS.
The value mapped to the corresponding checksum.
Yields:
The provenance information on content.
"""
db = self.db
c = self.content_find(content)
if not c:
return []
sha1_git = c['sha1_git']
for provenance in db.content_find_provenance(sha1_git, cur=cur):
yield dict(zip(db.provenance_cols, provenance))
def directory_add(self, directories):
"""Add directories to the storage
Args:
directories: iterable of dictionaries representing the individual
directories to add. Each dict has the following keys:
- id (sha1_git): the id of the directory to add
- entries (list): list of dicts for each entry in the
directory. Each dict has the following keys:
- name (bytes)
- type (one of 'file', 'dir', 'rev'):
type of the directory entry (file, directory, revision)
- target (sha1_git): id of the object pointed at by the
directory entry
- perms (int): entry permissions
"""
dirs = set()
dir_entries = {
'file': defaultdict(list),
'dir': defaultdict(list),
'rev': defaultdict(list),
}
for cur_dir in directories:
dir_id = cur_dir['id']
dirs.add(dir_id)
for src_entry in cur_dir['entries']:
entry = src_entry.copy()
entry['dir_id'] = dir_id
dir_entries[entry['type']][dir_id].append(entry)
dirs_missing = set(self.directory_missing(dirs))
if not dirs_missing:
return
db = self.db
with db.transaction() as cur:
# Copy directory ids
dirs_missing_dict = ({'id': dir} for dir in dirs_missing)
db.mktemp('directory', cur)
db.copy_to(dirs_missing_dict, 'tmp_directory', ['id'], cur)
# Copy entries
for entry_type, entry_list in dir_entries.items():
entries = itertools.chain.from_iterable(
entries_for_dir
for dir_id, entries_for_dir
in entry_list.items()
if dir_id in dirs_missing)
db.mktemp_dir_entry(entry_type)
db.copy_to(
entries,
'tmp_directory_entry_%s' % entry_type,
['target', 'name', 'perms', 'dir_id'],
cur,
)
# Do the final copy
db.directory_add_from_temp(cur)
@db_transaction_generator
def directory_missing(self, directories, cur):
"""List directories missing from storage
Args: an iterable of directory ids
Returns: a list of missing directory ids
"""
db = self.db
# Create temporary table for metadata injection
db.mktemp('directory', cur)
directories_dicts = ({'id': dir} for dir in directories)
db.copy_to(directories_dicts, 'tmp_directory', ['id'], cur)
for obj in db.directory_missing_from_temp(cur):
yield obj[0]
@db_transaction_generator
def directory_get(self,
directories,
cur=None):
"""Get information on directories.
Args:
- directories: an iterable of directory ids
Returns:
List of directories as dict with keys and associated values.
"""
db = self.db
keys = ('id', 'dir_entries', 'file_entries', 'rev_entries')
db.mktemp('directory', cur)
db.copy_to(({'id': dir_id} for dir_id in directories),
'tmp_directory', ['id'], cur)
dirs = db.directory_get_from_temp(cur)
for line in dirs:
yield dict(zip(keys, line))
@db_transaction_generator
def directory_ls(self, directory, recursive=False, cur=None):
"""Get entries for one directory.
Args:
- directory: the directory to list entries from.
- recursive: if flag on, this list recursively from this directory.
Returns:
List of entries for such directory.
"""
db = self.db
if recursive:
res_gen = db.directory_walk(directory)
else:
res_gen = db.directory_walk_one(directory)
for line in res_gen:
yield dict(zip(db.directory_ls_cols, line))
@db_transaction
def cache_content_revision_add(self, revisions, cur=None):
"""Cache the current revision's current targeted arborescence directory.
If the revision has already been cached, it just does nothing.
Args:
- revisions: the revisions to cache
Returns:
None
"""
db = self.db
db.store_tmp_bytea(revisions, cur)
db.cache_content_revision_add()
@db_transaction_generator
def cache_content_get_all(self, cur=None):
"""Read the distinct contents in the cache table.
Yields:
contents from cache
"""
for content in self.db.cache_content_get_all(cur):
yield dict(zip(self.db.cache_content_get_cols, content))
@db_transaction
def cache_content_get(self, content, cur=None):
"""Retrieve information on content.
Args:
content (dict): content with checkums
Returns:
Its properties (sha1, sha1_git, sha256, revision_paths)
"""
if 'sha1_git' in content:
sha1_git = content['sha1_git']
else:
c = self.content_find(content)
if not c:
return None
sha1_git = c['sha1_git']
c = self.db.cache_content_get(sha1_git, cur=cur)
if not c:
return None
return dict(zip(self.db.cache_content_get_cols, c))
@db_transaction_generator
def cache_revision_origin_add(self, origin, visit, cur=None):
"""Cache the list of revisions the given visit added to the origin.
Args:
- origin: the id of the origin
- visit: the id of the visit
Returns:
The list of new revisions
"""
for (revision,) in self.db.cache_revision_origin_add(origin, visit):
yield revision
@db_transaction
def directory_entry_get_by_path(self, directory, paths, cur=None):
"""Get the directory entry (either file or dir) from directory with
path.
Args:
- directory: sha1 of the top level directory
- paths: path to lookup from the top level directory. From left
(top) to right (bottom).
Returns:
The corresponding directory entry if found, None otherwise.
"""
db = self.db
keys = ('dir_id', 'type', 'target', 'name', 'perms', 'status',
'sha1', 'sha1_git', 'sha256')
res = db.directory_entry_get_by_path(directory, paths, cur)
if res:
return dict(zip(keys, res))
def revision_add(self, revisions):
"""Add revisions to the storage
Args:
revisions: iterable of dictionaries representing the individual
revisions to add. Each dict has the following keys:
- id (sha1_git): id of the revision to add
- date (datetime.DateTime): date the revision was written
- date_offset (int): offset from UTC in minutes the revision
was written
- date_neg_utc_offset (boolean): whether a null date_offset
represents a negative UTC offset
- committer_date (datetime.DateTime): date the revision got
added to the origin
- committer_date_offset (int): offset from UTC in minutes the
revision was added to the origin
- committer_date_neg_utc_offset (boolean): whether a null
committer_date_offset represents a negative UTC offset
- type (one of 'git', 'tar'): type of the revision added
- directory (sha1_git): the directory the revision points at
- message (bytes): the message associated with the revision
- author_name (bytes): the name of the revision author
- author_email (bytes): the email of the revision author
- committer_name (bytes): the name of the revision committer
- committer_email (bytes): the email of the revision committer
- metadata (jsonb): extra information as dictionary
- synthetic (bool): revision's nature (tarball, directory
creates synthetic revision)
- parents (list of sha1_git): the parents of this revision
"""
db = self.db
revisions_missing = set(self.revision_missing(
set(revision['id'] for revision in revisions)))
if not revisions_missing:
return
with db.transaction() as cur:
db.mktemp_revision(cur)
revisions_filtered = (
converters.revision_to_db(revision) for revision in revisions
if revision['id'] in revisions_missing)
parents_filtered = []
db.copy_to(
revisions_filtered, 'tmp_revision', db.revision_add_cols,
cur,
lambda rev: parents_filtered.extend(rev['parents']))
db.revision_add_from_temp(cur)
db.copy_to(parents_filtered, 'revision_history',
['id', 'parent_id', 'parent_rank'], cur)
@db_transaction_generator
def revision_missing(self, revisions, cur=None):
"""List revisions missing from storage
Args: an iterable of revision ids
Returns: a list of missing revision ids
"""
db = self.db
db.store_tmp_bytea(revisions, cur)
for obj in db.revision_missing_from_temp(cur):
yield obj[0]
@db_transaction_generator
def revision_get(self, revisions, cur):
"""Get all revisions from storage
Args: an iterable of revision ids
Returns: an iterable of revisions as dictionaries
(or None if the revision doesn't exist)
"""
db = self.db
db.store_tmp_bytea(revisions, cur)
for line in self.db.revision_get_from_temp(cur):
data = converters.db_to_revision(
dict(zip(db.revision_get_cols, line))
)
if not data['type']:
yield None
continue
yield data
@db_transaction_generator
def revision_log(self, revisions, limit=None, cur=None):
"""Fetch revision entry from the given root revisions.
Args:
- revisions: array of root revision to lookup
- limit: limitation on the output result. Default to null.
Yields:
List of revision log from such revisions root.
"""
db = self.db
for line in db.revision_log(revisions, limit, cur):
data = converters.db_to_revision(
dict(zip(db.revision_get_cols, line))
)
if not data['type']:
yield None
continue
yield data
@db_transaction_generator
def revision_shortlog(self, revisions, limit=None, cur=None):
"""Fetch the shortlog for the given revisions
Args:
revisions: list of root revisions to lookup
limit: depth limitation for the output
Yields:
a list of (id, parents) tuples.
"""
db = self.db
yield from db.revision_shortlog(revisions, limit, cur)
@db_transaction_generator
def revision_log_by(self, origin_id, branch_name=None, timestamp=None,
limit=None, cur=None):
"""Fetch revision entry from the actual origin_id's latest revision.
Args:
- origin_id: the origin id from which deriving the revision
- branch_name: (optional) occurrence's branch name
- timestamp: (optional) occurrence's time
- limit: (optional) depth limitation for the
output. Default to None.
Yields:
The revision log starting from the revision derived from
the (origin, branch_name, timestamp) combination if any.
Returns the [] if no revision matching this combination is
found.
"""
db = self.db
# Retrieve the revision by criterion
revisions = list(db.revision_get_by(
origin_id, branch_name, timestamp, limit=1))
if not revisions:
return None
revision_id = revisions[0][0]
# otherwise, retrieve the revision log from that revision
yield from self.revision_log([revision_id], limit)
def release_add(self, releases):
"""Add releases to the storage
Args:
releases: iterable of dictionaries representing the individual
releases to add. Each dict has the following keys:
- id (sha1_git): id of the release to add
- revision (sha1_git): id of the revision the release points
to
- date (datetime.DateTime): the date the release was made
- date_offset (int): offset from UTC in minutes the release was
made
- date_neg_utc_offset (boolean): whether a null date_offset
represents a negative UTC offset
- name (bytes): the name of the release
- comment (bytes): the comment associated with the release
- author_name (bytes): the name of the release author
- author_email (bytes): the email of the release author
"""
db = self.db
release_ids = set(release['id'] for release in releases)
releases_missing = set(self.release_missing(release_ids))
if not releases_missing:
return
with db.transaction() as cur:
db.mktemp_release(cur)
releases_filtered = (
converters.release_to_db(release) for release in releases
if release['id'] in releases_missing
)
db.copy_to(releases_filtered, 'tmp_release', db.release_add_cols,
cur)
db.release_add_from_temp(cur)
@db_transaction_generator
def release_missing(self, releases, cur=None):
"""List releases missing from storage
Args: an iterable of release ids
Returns: a list of missing release ids
"""
db = self.db
# Create temporary table for metadata injection
db.store_tmp_bytea(releases, cur)
for obj in db.release_missing_from_temp(cur):
yield obj[0]
@db_transaction_generator
def release_get(self, releases, cur=None):
"""Given a list of sha1, return the releases's information
Args:
releases: list of sha1s
Returns:
Generates the list of releases dict with the following keys:
- id: origin's id
- revision: origin's type
- url: origin's url
- lister: lister's uuid
- project: project's uuid (FIXME, retrieve this information)
Raises:
ValueError if the keys does not match (url and type) nor id.
"""
db = self.db
# Create temporary table for metadata injection
db.store_tmp_bytea(releases, cur)
for release in db.release_get_from_temp(cur):
yield converters.db_to_release(
dict(zip(db.release_get_cols, release))
)
@db_transaction
def occurrence_add(self, occurrences, cur=None):
"""Add occurrences to the storage
Args:
occurrences: iterable of dictionaries representing the individual
occurrences to add. Each dict has the following keys:
- origin (int): id of the origin corresponding to the
occurrence
- branch (str): the reference name of the occurrence
- target (sha1_git): the id of the object pointed to by
the occurrence
- target_type (str): the type of object pointed to by the
occurrence
"""
db = self.db
db.mktemp_occurrence_history(cur)
db.copy_to(occurrences, 'tmp_occurrence_history',
['origin', 'branch', 'target', 'target_type', 'visit'], cur)
db.occurrence_history_add_from_temp(cur)
@db_transaction_generator
def occurrence_get(self, origin_id, cur=None):
"""Retrieve occurrence information per origin_id.
Args:
origin_id: The occurrence's origin.
Yields:
List of occurrences matching criterion.
"""
db = self.db
for line in db.occurrence_get(origin_id, cur):
yield {
'origin': line[0],
'branch': line[1],
'target': line[2],
'target_type': line[3],
}
@db_transaction
def origin_visit_add(self, origin, ts, cur=None):
"""Add an origin_visit for the origin at ts with status 'ongoing'.
Args:
origin: Visited Origin id
ts: timestamp of such visit
Returns:
Dict with keys origin and visit where:
- origin: origin identifier
- visit: the visit identifier for the new visit occurrence
- ts (datetime.DateTime): the visit date
"""
if isinstance(ts, str):
ts = dateutil.parser.parse(ts)
return {
'origin': origin,
'visit': self.db.origin_visit_add(origin, ts, cur)
}
@db_transaction
def origin_visit_update(self, origin, visit_id, status, metadata=None,
cur=None):
"""Update an origin_visit's status.
Args:
origin: Visited Origin id
visit_id: Visit's id
status: Visit's new status
metadata: Data associated to the visit
Returns:
None
"""
return self.db.origin_visit_update(origin, visit_id, status, metadata,
cur)
@db_transaction_generator
def origin_visit_get(self, origin, cur=None):
"""Retrieve all the origin's visit's information.
Args:
origin: The occurrence's origin (identifier).
Yields:
List of visits.
"""
db = self.db
for line in db.origin_visit_get_all(origin, cur):
data = dict(zip(self.db.origin_visit_get_cols, line))
yield data
@db_transaction
def origin_visit_get_by(self, origin, visit, cur=None):
"""Retrieve origin visit's information.
Args:
origin: The occurrence's origin (identifier).
Returns:
The information on that particular (origin, visit)
"""
db = self.db
ori_visit = db.origin_visit_get(origin, visit, cur)
if not ori_visit:
return None
ori_visit = dict(zip(self.db.origin_visit_get_cols, ori_visit))
occs = {}
for occ in db.occurrence_by_origin_visit(origin, visit):
_, branch_name, target, target_type = occ
occs[branch_name] = {
'target': target,
'target_type': target_type
}
ori_visit.update({
'occurrences': occs
})
return ori_visit
@db_transaction_generator
def revision_get_by(self,
origin_id,
branch_name=None,
timestamp=None,
limit=None,
cur=None):
"""Given an origin_id, retrieve occurrences' list per given criterions.
Args:
origin_id: The origin to filter on.
branch_name: (optional) branch name.
timestamp: (optional) time.
limit: (optional) limit
Yields:
List of occurrences matching the criterions or None if nothing is
found.
"""
for line in self.db.revision_get_by(origin_id,
branch_name,
timestamp,
limit=limit,
cur=cur):
data = converters.db_to_revision(
dict(zip(self.db.revision_get_cols, line))
)
if not data['type']:
yield None
continue
yield data
def release_get_by(self, origin_id, limit=None):
"""Given an origin id, return all the tag objects pointing to heads of
origin_id.
Args:
origin_id: the origin to filter on.
limit: None by default
Yields:
List of releases matching the criterions or None if nothing is
found.
"""
for line in self.db.release_get_by(origin_id, limit=limit):
data = converters.db_to_release(
dict(zip(self.db.release_get_cols, line))
)
yield data
@db_transaction
def object_find_by_sha1_git(self, ids, cur=None):
"""Return the objects found with the given ids.
Args:
ids: a generator of sha1_gits
Returns:
a dict mapping the id to the list of objects found. Each object
found is itself a dict with keys:
sha1_git: the input id
type: the type of object found
id: the id of the object found
object_id: the numeric id of the object found.
"""
db = self.db
ret = {id: [] for id in ids}
for retval in db.object_find_by_sha1_git(ids):
if retval[1]:
ret[retval[0]].append(dict(zip(db.object_find_by_sha1_git_cols,
retval)))
return ret
@db_transaction
def origin_get(self, origin, cur=None):
"""Return the origin either identified by its id or its tuple
(type, url).
Args:
origin: dictionary representing the individual
origin to find.
This dict has either the keys type and url:
- type (FIXME: enum TBD): the origin type ('git', 'wget', ...)
- url (bytes): the url the origin points to
either the id:
- id: the origin id
Returns:
the origin dict with the keys:
- id: origin's id
- type: origin's type
- url: origin's url
- lister: lister's uuid
- project: project's uuid (FIXME, retrieve this information)
Raises:
ValueError if the keys does not match (url and type) nor id.
"""
db = self.db
keys = ['id', 'type', 'url', 'lister', 'project']
origin_id = origin.get('id')
if origin_id: # check lookup per id first
ori = db.origin_get(origin_id, cur)
elif 'type' in origin and 'url' in origin: # or lookup per type, url
ori = db.origin_get_with(origin['type'], origin['url'], cur)
else: # unsupported lookup
raise ValueError('Origin must have either id or (type and url).')
if ori:
return dict(zip(keys, ori))
return None
@db_transaction
def _person_add(self, person, cur=None):
"""Add a person in storage.
BEWARE: Internal function for now.
Do not do anything fancy in case a person already exists.
Please adapt code if more checks are needed.
Args:
person dictionary with keys name and email.
Returns:
Id of the new person.
"""
db = self.db
return db.person_add(person)
@db_transaction_generator
def person_get(self, person, cur=None):
"""Return the persons identified by their ids.
Args:
person: array of ids.
Returns:
The array of persons corresponding of the ids.
"""
db = self.db
for person in db.person_get(person):
yield dict(zip(db.person_get_cols, person))
@db_transaction
def origin_add(self, origins, cur=None):
"""Add origins to the storage
Args:
origins: list of dictionaries representing the individual origins,
with the following keys:
type: the origin type ('git', 'svn', 'deb', ...)
url (bytes): the url the origin points to
Returns:
The array of ids corresponding to the given origins
"""
ret = []
for origin in origins:
ret.append(self.origin_add_one(origin, cur=cur))
return ret
@db_transaction
def origin_add_one(self, origin, cur=None):
"""Add origin to the storage
Args:
origin: dictionary representing the individual
origin to add. This dict has the following keys:
- type (FIXME: enum TBD): the origin type ('git', 'wget', ...)
- url (bytes): the url the origin points to
Returns:
the id of the added origin, or of the identical one that already
exists.
"""
db = self.db
data = db.origin_get_with(origin['type'], origin['url'], cur)
if data:
return data[0]
return db.origin_add(origin['type'], origin['url'], cur)
@db_transaction
def fetch_history_start(self, origin_id, cur=None):
"""Add an entry for origin origin_id in fetch_history. Returns the id
of the added fetch_history entry
"""
fetch_history = {
'origin': origin_id,
'date': datetime.datetime.now(tz=datetime.timezone.utc),
}
return self.db.create_fetch_history(fetch_history, cur)
@db_transaction
def fetch_history_end(self, fetch_history_id, data, cur=None):
"""Close the fetch_history entry with id `fetch_history_id`, replacing
its data with `data`.
"""
now = datetime.datetime.now(tz=datetime.timezone.utc)
fetch_history = self.db.get_fetch_history(fetch_history_id, cur)
if not fetch_history:
raise ValueError('No fetch_history with id %d' % fetch_history_id)
fetch_history['duration'] = now - fetch_history['date']
fetch_history.update(data)
self.db.update_fetch_history(fetch_history, cur)
@db_transaction
def fetch_history_get(self, fetch_history_id, cur=None):
"""Get the fetch_history entry with id `fetch_history_id`.
"""
return self.db.get_fetch_history(fetch_history_id, cur)
@db_transaction
def entity_add(self, entities, cur=None):
"""Add the given entitites to the database (in entity_history).
Args:
- entities: iterable of dictionaries containing the following keys:
- uuid (uuid): id of the entity
- parent (uuid): id of the parent entity
- name (str): name of the entity
- type (str): type of entity (one of 'organization',
'group_of_entities', 'hosting', 'group_of_persons',
'person', 'project')
- description (str, optional): description of the entity
- homepage (str): url of the entity's homepage
- active (bool): whether the entity is active
- generated (bool): whether the entity was generated
- lister_metadata (dict): lister-specific entity metadata
- metadata (dict): other metadata for the entity
- validity (datetime.DateTime array): timestamps at which we
listed the entity.
"""
db = self.db
cols = list(db.entity_history_cols)
cols.remove('id')
db.mktemp_entity_history()
db.copy_to(entities, 'tmp_entity_history', cols, cur)
db.entity_history_add_from_temp()
@db_transaction_generator
def entity_get_from_lister_metadata(self, entities, cur=None):
"""Fetch entities from the database, matching with the lister and
associated metadata.
Args:
entities: iterable of dictionaries containing the lister metadata
to look for. Useful keys are 'lister', 'type', 'id', ...
Returns:
A generator of fetched entities with all their attributes. If no
match was found, the returned entity is None.
"""
db = self.db
db.mktemp_entity_lister(cur)
mapped_entities = []
for i, entity in enumerate(entities):
mapped_entity = {
'id': i,
'lister_metadata': entity,
}
mapped_entities.append(mapped_entity)
db.copy_to(mapped_entities, 'tmp_entity_lister',
['id', 'lister_metadata'], cur)
cur.execute('''select id, %s
from swh_entity_from_tmp_entity_lister()
order by id''' %
','.join(db.entity_cols))
for id, *entity_vals in cur:
fetched_entity = dict(zip(db.entity_cols, entity_vals))
if fetched_entity['uuid']:
yield fetched_entity
else:
yield {
'uuid': None,
'lister_metadata': entities[i],
}
@db_transaction_generator
def entity_get(self, uuid, cur=None):
"""Returns the list of entity per its uuid identifier and also its
parent hierarchy.
Args:
uuid: entity's identifier
Returns:
List of entities starting with entity with uuid and the parent
hierarchy from such entity.
"""
db = self.db
for entity in db.entity_get(uuid, cur):
yield dict(zip(db.entity_cols, entity))
@db_transaction
def entity_get_one(self, uuid, cur=None):
"""Returns one entity using its uuid identifier.
Args:
uuid: entity's identifier
Returns:
the object corresponding to the given entity
"""
db = self.db
entity = db.entity_get_one(uuid, cur)
if entity:
return dict(zip(db.entity_cols, entity))
else:
return None
@db_transaction
def stat_counters(self, cur=None):
"""compute statistics about the number of tuples in various tables
Returns:
a dictionary mapping textual labels (e.g., content) to integer
values (e.g., the number of tuples in table content)
"""
return {k: v for (k, v) in self.db.stat_counters()}
@db_transaction_generator
def content_mimetype_missing(self, mimetypes, cur=None):
"""List mimetypes missing from storage.
Args:
mimetypes: iterable of sha1
Returns:
an iterable of missing id
"""
db = self.db
db.store_tmp_bytea(mimetypes, cur)
for obj in db.content_mimetype_missing_from_temp(cur):
yield obj[0]
@db_transaction
def content_mimetype_add(self, mimetypes, conflict_update=False, cur=None):
"""Add mimetypes not present in storage.
Args:
mimetypes: iterable of dictionary with keys:
- id: sha1
- mimetype: bytes
- encoding: bytes
conflict_update: Flag to determine if we want to overwrite (true)
or skip duplicates (false, the default)
"""
db = self.db
db.mktemp('content_mimetype', cur)
db.copy_to(mimetypes, 'tmp_content_mimetype',
['id', 'mimetype', 'encoding'], cur)
db.content_mimetype_add_from_temp(conflict_update, cur)
@db_transaction_generator
def content_mimetype_get(self, ids, cur=None):
db = self.db
db.store_tmp_bytea(ids, cur)
for c in db.content_mimetype_get_from_temp():
yield dict(zip(db.content_mimetype_cols, c))
@db_transaction_generator
def content_language_missing(self, languages, cur=None):
"""List languages missing from storage.
Args:
languages: iterable of sha1
Returns:
an iterable of missing id
"""
db = self.db
db.store_tmp_bytea(languages, cur)
for obj in db.content_language_missing_from_temp(cur):
yield obj[0]
@db_transaction_generator
def content_language_get(self, ids, cur=None):
db = self.db
db.store_tmp_bytea(ids, cur)
for c in db.content_language_get_from_temp():
yield dict(zip(db.content_language_cols, c))
@db_transaction
def content_language_add(self, languages, conflict_update=False, cur=None):
"""Add languages not present in storage.
Args:
languages: iterable of dictionary with keys:
- id: sha1
- lang: bytes
conflict_update: Flag to determine if we want to overwrite (true)
or skip duplicates (false, the default)
"""
db = self.db
db.mktemp('content_language', cur)
# empty language is mapped to 'unknown'
db.copy_to(
({
'id': l['id'],
'lang': 'unknown' if not l['lang'] else l['lang']
} for l in languages),
'tmp_content_language', ['id', 'lang'], cur)
db.content_language_add_from_temp(conflict_update, cur)
@db_transaction_generator
def content_ctags_missing(self, ctags, cur=None):
"""List ctags missing from storage.
Args:
ctags: iterable of dict with keys:
- id (bytes): sha1 identifier
- tool_name (str): tool name used
- tool_version (str): associated version
Returns:
an iterable of missing id
"""
db = self.db
db.mktemp_content_ctags_missing(cur)
db.copy_to(ctags,
tblname='tmp_content_ctags_missing',
columns=['id', 'tool_name', 'tool_version'],
cur=cur)
for obj in db.content_ctags_missing_from_temp(cur):
yield obj[0]
@db_transaction_generator
def content_ctags_get(self, ids, cur=None):
"""Retrieve ctags per id.
Args:
ids ([sha1]): Iterable of sha1
"""
db = self.db
db.store_tmp_bytea(ids, cur)
for c in db.content_ctags_get_from_temp():
- yield dict(zip(db.content_ctags_cols, c))
+ yield converters.db_to_ctags(dict(zip(db.content_ctags_cols, c)))
@db_transaction
def content_ctags_add(self, ctags, conflict_update=False, cur=None):
"""Add ctags not present in storage
Args:
ctags: iterable of dictionaries with keys:
- id (bytes): sha1
- ctags ([dict]): List of dictionary with keys (name,
kind, line, language)
"""
db = self.db
def _convert_ctags(ctags):
"""Convert ctags to list of ctags.
"""
res = []
for ctag in ctags:
res.extend(converters.ctags_to_db(ctag))
return res
db.mktemp_content_ctags(cur)
db.copy_to(_convert_ctags(ctags),
tblname='tmp_content_ctags',
columns=db.content_ctags_cols,
cur=cur)
db.content_ctags_add_from_temp(conflict_update, cur)
@db_transaction_generator
def content_ctags_search(self, expression,
limit=10, last_sha1=None, cur=None):
"""Search through content's raw ctags symbols.
Args:
expression (str): Expression to search for
limit (int): Number of rows to return (default to 10).
last_sha1 (str): Offset from which retrieving data (default to '').
Yields:
rows of ctags including id, name, lang, kind, line, etc...
"""
db = self.db
for obj in db.content_ctags_search(expression, last_sha1, limit,
cur=cur):
- yield dict(zip(db.content_ctags_cols, obj))
+ yield converters.db_to_ctags(dict(zip(db.content_ctags_cols, obj)))
@db_transaction_generator
def content_fossology_license_missing(self, licenses, cur=None):
"""List license missing from storage.
Args:
licenses ([bytes]): iterable of sha1
Returns:
an iterable of missing id
"""
db = self.db
db.store_tmp_bytea(licenses, cur)
for obj in db.content_fossology_license_missing_from_temp(cur):
yield obj[0]
@db_transaction_generator
def content_fossology_license_get(self, ids, cur=None):
"""Retrieve licenses per id.
Args:
ids ([sha1]): Iterable of sha1
Yields:
List of dict with the following keys:
- id (bytes)
- licenses ([str]): associated licenses for that content
"""
db = self.db
db.store_tmp_bytea(ids, cur)
for c in db.content_fossology_license_get_from_temp():
yield dict(zip(db.content_fossology_license_cols, c))
@db_transaction
def content_fossology_license_add(self, licenses,
conflict_update=False, cur=None):
"""Add licenses not present in storage.
Args:
licenses ([dict]): iterable of dict with keys:
- id: sha1
- license ([bytes]): List of licenses associated to sha1
- tool (str): nomossa
conflict_update: Flag to determine if we want to overwrite (true)
or skip duplicates (false, the default)
Returns:
List of content_license entries which failed due to
unknown licenses
"""
db = self.db
# First, we check the licenses are ok
licenses_to_check = set() # set of licenses to check
content_licenses_to_add = {} # content_licenses to add
names_to_content_license = {} # map from names to content licenses
for c in licenses:
id = c['id']
for name in c['licenses']:
licenses_to_check.add(name)
l = names_to_content_license.get(name, [])
l.append(id)
names_to_content_license[name] = l
content_licenses_to_add[id] = c
db.mktemp_content_fossology_license_unknown()
db.copy_to(({'name': name} for name in licenses_to_check),
tblname='tmp_content_fossology_license_unknown',
columns=['name'],
cur=cur)
unknown_licenses = db.content_fossology_license_unknown(cur)
# We filter out wrong content_license (this will be the result)
wrong_content_licenses = []
for name, in unknown_licenses:
for id in names_to_content_license[name]:
# we can remove it multiple times since one content
# can have multiple licenses
content_license = content_licenses_to_add.pop(id, None)
if content_license:
wrong_content_licenses.append(content_license)
if content_licenses_to_add:
# Then, we add the correct ones
db.mktemp_content_fossology_license(cur)
db.copy_to(
({
'id': c['id'],
'tool_name': c['tool_name'],
'tool_version': c['tool_version'],
'license': license,
} for c in content_licenses_to_add.values()
for license in c['licenses']),
tblname='tmp_content_fossology_license',
columns=['id', 'tool_name', 'tool_version', 'license'],
cur=cur)
db.content_fossology_license_add_from_temp(conflict_update, cur)
return wrong_content_licenses
diff --git a/swh/storage/tests/test_converters.py b/swh/storage/tests/test_converters.py
index ab79a7b5..ea3533ad 100644
--- a/swh/storage/tests/test_converters.py
+++ b/swh/storage/tests/test_converters.py
@@ -1,176 +1,205 @@
# 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 unittest
from nose.tools import istest
from nose.plugins.attrib import attr
from swh.storage import converters
@attr('!db')
class TestConverters(unittest.TestCase):
def setUp(self):
self.maxDiff = None
@istest
def db_to_author(self):
# when
actual_author = converters.db_to_author(
1, b'fullname', b'name', b'email')
# then
self.assertEquals(actual_author, {
'id': 1,
'fullname': b'fullname',
'name': b'name',
'email': b'email',
})
@istest
def db_to_revision(self):
# when
actual_revision = converters.db_to_revision({
'id': 'revision-id',
'date': None,
'date_offset': None,
'date_neg_utc_offset': None,
'committer_date': None,
'committer_date_offset': None,
'committer_date_neg_utc_offset': None,
'type': 'rev',
'directory': b'dir-sha1',
'message': b'commit message',
'author_id': 'auth-id',
'author_fullname': b'auth-fullname',
'author_name': b'auth-name',
'author_email': b'auth-email',
'committer_id': 'comm-id',
'committer_fullname': b'comm-fullname',
'committer_name': b'comm-name',
'committer_email': b'comm-email',
'metadata': {},
'synthetic': False,
'parents': [123, 456]
})
# then
self.assertEquals(actual_revision, {
'id': 'revision-id',
'author': {
'id': 'auth-id',
'fullname': b'auth-fullname',
'name': b'auth-name',
'email': b'auth-email',
},
'date': None,
'committer': {
'id': 'comm-id',
'fullname': b'comm-fullname',
'name': b'comm-name',
'email': b'comm-email',
},
'committer_date': None,
'type': 'rev',
'directory': b'dir-sha1',
'message': b'commit message',
'metadata': {},
'synthetic': False,
'parents': [123, 456],
})
@istest
def db_to_release(self):
# when
actual_release = converters.db_to_release({
'id': b'release-id',
'target': b'revision-id',
'target_type': 'revision',
'date': None,
'date_offset': None,
'date_neg_utc_offset': None,
'name': b'release-name',
'comment': b'release comment',
'synthetic': True,
'author_id': 'auth-id',
'author_fullname': b'auth-fullname',
'author_name': b'auth-name',
'author_email': b'auth-email',
})
# then
self.assertEquals(actual_release, {
'author': {
'id': 'auth-id',
'fullname': b'auth-fullname',
'name': b'auth-name',
'email': b'auth-email',
},
'date': None,
'id': b'release-id',
'name': b'release-name',
'message': b'release comment',
'synthetic': True,
'target': b'revision-id',
'target_type': 'revision'
})
@istest
def db_to_git_headers(self):
raw_data = [
['gpgsig', b'garbage\x89a\x43b\x14'],
['extra', [b'fo\\\\\\o', b'bar\\', b'inval\\\\\x99id']],
]
db_data = converters.git_headers_to_db(raw_data)
loop = converters.db_to_git_headers(db_data)
self.assertEquals(raw_data, loop)
@istest
def ctags_to_db(self):
input_ctag = {
'id': b'some-id',
'tool_name': 'some-toolname',
'tool_version': 'some-toolversion',
'ctags': [
{
'name': 'some-name',
'kind': 'some-kind',
'line': 10,
'lang': 'Yaml',
}, {
'name': 'main',
'kind': 'function',
'line': 12,
'lang': 'Yaml',
},
]
}
expected_ctags = [
{
'id': b'some-id',
'name': 'some-name',
'kind': 'some-kind',
'line': 10,
'lang': 'Yaml',
'tool_name': 'some-toolname',
'tool_version': 'some-toolversion',
}, {
'id': b'some-id',
'name': 'main',
'kind': 'function',
'line': 12,
'lang': 'Yaml',
'tool_name': 'some-toolname',
'tool_version': 'some-toolversion',
}]
# when
actual_ctags = converters.ctags_to_db(input_ctag)
# then
self.assertEquals(actual_ctags, expected_ctags)
+
+ @istest
+ def db_to_ctags(self):
+ input_ctags = {
+ 'id': b'some-id',
+ 'tool_name': 'some-toolname',
+ 'tool_version': 'some-toolversion',
+ 'name': 'some-name',
+ 'kind': 'some-kind',
+ 'line': 10,
+ 'lang': 'Yaml',
+ }
+ expected_ctags = {
+ 'id': b'some-id',
+ 'name': 'some-name',
+ 'kind': 'some-kind',
+ 'line': 10,
+ 'lang': 'Yaml',
+ 'tool': {
+ 'name': 'some-toolname',
+ 'version': 'some-toolversion'
+ }
+ }
+
+ # when
+ actual_ctags = converters.db_to_ctags(input_ctags)
+
+ # then
+ self.assertEquals(actual_ctags, expected_ctags)
diff --git a/swh/storage/tests/test_storage.py b/swh/storage/tests/test_storage.py
index a90ff8c9..19b0b68d 100644
--- a/swh/storage/tests/test_storage.py
+++ b/swh/storage/tests/test_storage.py
@@ -1,2827 +1,2851 @@
# Copyright (C) 2015-2016 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
import copy
import datetime
import os
import psycopg2
import shutil
import tempfile
import unittest
from uuid import UUID
from unittest.mock import patch
from nose.tools import istest
from nose.plugins.attrib import attr
from swh.core.tests.db_testing import DbTestFixture
from swh.core.hashutil import hex_to_hash
from swh.storage import Storage
from swh.storage.db import cursor_to_bytes
TEST_DIR = os.path.dirname(os.path.abspath(__file__))
TEST_DATA_DIR = os.path.join(TEST_DIR, '../../../../swh-storage-testdata')
@attr('db')
class AbstractTestStorage(DbTestFixture):
"""Base class for Storage testing.
This class is used as-is to test local storage (see TestStorage
below) and remote storage (see TestRemoteStorage in
test_remote_storage.py.
We need to have the two classes inherit from this base class
separately to avoid nosetests running the tests from the base
class twice.
"""
TEST_DB_DUMP = os.path.join(TEST_DATA_DIR, 'dumps/swh.dump')
def setUp(self):
super().setUp()
self.maxDiff = None
self.objroot = tempfile.mkdtemp()
self.storage = Storage(self.conn, self.objroot)
self.cont = {
'data': b'42\n',
'length': 3,
'sha1': hex_to_hash(
'34973274ccef6ab4dfaaf86599792fa9c3fe4689'),
'sha1_git': hex_to_hash(
'd81cc0710eb6cf9efd5b920a8453e1e07157b6cd'),
'sha256': hex_to_hash(
'673650f936cb3b0a2f93ce09d81be107'
'48b1b203c19e8176b4eefc1964a0cf3a'),
'status': 'visible',
}
self.cont2 = {
'data': b'4242\n',
'length': 5,
'sha1': hex_to_hash(
'61c2b3a30496d329e21af70dd2d7e097046d07b7'),
'sha1_git': hex_to_hash(
'36fade77193cb6d2bd826161a0979d64c28ab4fa'),
'sha256': hex_to_hash(
'859f0b154fdb2d630f45e1ecae4a8629'
'15435e663248bb8461d914696fc047cd'),
'status': 'visible',
}
self.cont3 = {
'data': b'424242\n',
'length': 7,
'sha1': hex_to_hash(
'3e21cc4942a4234c9e5edd8a9cacd1670fe59f13'),
'sha1_git': hex_to_hash(
'c932c7649c6dfa4b82327d121215116909eb3bea'),
'sha256': hex_to_hash(
'92fb72daf8c6818288a35137b72155f5'
'07e5de8d892712ab96277aaed8cf8a36'),
'status': 'visible',
}
self.missing_cont = {
'data': b'missing\n',
'length': 8,
'sha1': hex_to_hash(
'f9c24e2abb82063a3ba2c44efd2d3c797f28ac90'),
'sha1_git': hex_to_hash(
'33e45d56f88993aae6a0198013efa80716fd8919'),
'sha256': hex_to_hash(
'6bbd052ab054ef222c1c87be60cd191a'
'ddedd24cc882d1f5f7f7be61dc61bb3a'),
'status': 'absent',
}
self.skipped_cont = {
'length': 1024 * 1024 * 200,
'sha1_git': hex_to_hash(
'33e45d56f88993aae6a0198013efa80716fd8920'),
'reason': 'Content too long',
'status': 'absent',
}
self.skipped_cont2 = {
'length': 1024 * 1024 * 300,
'sha1_git': hex_to_hash(
'33e45d56f88993aae6a0198013efa80716fd8921'),
'reason': 'Content too long',
'status': 'absent',
}
self.dir = {
'id': b'4\x013\x422\x531\x000\xf51\xe62\xa73\xff7\xc3\xa90',
'entries': [
{
'name': b'foo',
'type': 'file',
'target': self.cont['sha1_git'],
'perms': 0o644,
},
{
'name': b'bar\xc3',
'type': 'dir',
'target': b'12345678901234567890',
'perms': 0o2000,
},
],
}
self.dir2 = {
'id': b'4\x013\x422\x531\x000\xf51\xe62\xa73\xff7\xc3\xa95',
'entries': [
{
'name': b'oof',
'type': 'file',
'target': self.cont2['sha1_git'],
'perms': 0o644,
}
],
}
self.dir3 = {
'id': hex_to_hash('33e45d56f88993aae6a0198013efa80716fd8921'),
'entries': [
{
'name': b'foo',
'type': 'file',
'target': self.cont['sha1_git'],
'perms': 0o644,
},
{
'name': b'bar',
'type': 'dir',
'target': b'12345678901234560000',
'perms': 0o2000,
},
{
'name': b'hello',
'type': 'file',
'target': b'12345678901234567890',
'perms': 0o644,
},
],
}
self.minus_offset = datetime.timezone(datetime.timedelta(minutes=-120))
self.plus_offset = datetime.timezone(datetime.timedelta(minutes=120))
self.revision = {
'id': b'56789012345678901234',
'message': b'hello',
'author': {
'name': b'Nicolas Dandrimont',
'email': b'nicolas@example.com',
'fullname': b'Nicolas Dandrimont <nicolas@example.com> ',
},
'date': {
'timestamp': 1234567890,
'offset': 120,
'negative_utc': None,
},
'committer': {
'name': b'St\xc3fano Zacchiroli',
'email': b'stefano@example.com',
'fullname': b'St\xc3fano Zacchiroli <stefano@example.com>'
},
'committer_date': {
'timestamp': 1123456789,
'offset': 0,
'negative_utc': True,
},
'parents': [b'01234567890123456789', b'23434512345123456789'],
'type': 'git',
'directory': self.dir['id'],
'metadata': {
'checksums': {
'sha1': 'tarball-sha1',
'sha256': 'tarball-sha256',
},
'signed-off-by': 'some-dude',
'extra_headers': [
['gpgsig', b'test123'],
['mergetags', [b'foo\\bar', b'\x22\xaf\x89\x80\x01\x00']],
],
},
'synthetic': True
}
self.revision2 = {
'id': b'87659012345678904321',
'message': b'hello again',
'author': {
'name': b'Roberto Dicosmo',
'email': b'roberto@example.com',
'fullname': b'Roberto Dicosmo <roberto@example.com>',
},
'date': {
'timestamp': 1234567843.22,
'offset': -720,
'negative_utc': None,
},
'committer': {
'name': b'tony',
'email': b'ar@dumont.fr',
'fullname': b'tony <ar@dumont.fr>',
},
'committer_date': {
'timestamp': 1123456789,
'offset': 0,
'negative_utc': False,
},
'parents': [b'01234567890123456789'],
'type': 'git',
'directory': self.dir2['id'],
'metadata': None,
'synthetic': False
}
self.revision3 = {
'id': hex_to_hash('7026b7c1a2af56521e951c01ed20f255fa054238'),
'message': b'a simple revision with no parents this time',
'author': {
'name': b'Roberto Dicosmo',
'email': b'roberto@example.com',
'fullname': b'Roberto Dicosmo <roberto@example.com>',
},
'date': {
'timestamp': 1234567843.22,
'offset': -720,
'negative_utc': None,
},
'committer': {
'name': b'tony',
'email': b'ar@dumont.fr',
'fullname': b'tony <ar@dumont.fr>',
},
'committer_date': {
'timestamp': 1127351742,
'offset': 0,
'negative_utc': False,
},
'parents': [],
'type': 'git',
'directory': self.dir2['id'],
'metadata': None,
'synthetic': True
}
self.revision4 = {
'id': hex_to_hash('368a48fe15b7db2383775f97c6b247011b3f14f4'),
'message': b'parent of self.revision2',
'author': {
'name': b'me',
'email': b'me@soft.heri',
'fullname': b'me <me@soft.heri>',
},
'date': {
'timestamp': 1244567843.22,
'offset': -720,
'negative_utc': None,
},
'committer': {
'name': b'committer-dude',
'email': b'committer@dude.com',
'fullname': b'committer-dude <committer@dude.com>',
},
'committer_date': {
'timestamp': 1244567843.22,
'offset': -720,
'negative_utc': None,
},
'parents': [self.revision3['id']],
'type': 'git',
'directory': self.dir['id'],
'metadata': None,
'synthetic': False
}
self.origin = {
'url': 'file:///dev/null',
'type': 'git',
}
self.origin2 = {
'url': 'file:///dev/zero',
'type': 'git',
}
self.date_visit1 = datetime.datetime(2015, 1, 1, 23, 0, 0,
tzinfo=datetime.timezone.utc)
self.occurrence = {
'branch': b'master',
'target': b'67890123456789012345',
'target_type': 'revision',
}
self.date_visit2 = datetime.datetime(2015, 1, 1, 23, 0, 0,
tzinfo=datetime.timezone.utc)
self.occurrence2 = {
'branch': b'master',
'target': self.revision2['id'],
'target_type': 'revision',
}
self.date_visit3 = datetime.datetime(2015, 1, 1, 23, 0, 0,
tzinfo=datetime.timezone.utc)
# template occurrence to be filled in test (cf. revision_log_by)
self.occurrence3 = {
'branch': b'master',
'target_type': 'revision',
}
self.release = {
'id': b'87659012345678901234',
'name': b'v0.0.1',
'author': {
'name': b'olasd',
'email': b'nic@olasd.fr',
'fullname': b'olasd <nic@olasd.fr>',
},
'date': {
'timestamp': 1234567890,
'offset': 42,
'negative_utc': None,
},
'target': b'43210987654321098765',
'target_type': 'revision',
'message': b'synthetic release',
'synthetic': True,
}
self.release2 = {
'id': b'56789012348765901234',
'name': b'v0.0.2',
'author': {
'name': b'tony',
'email': b'ar@dumont.fr',
'fullname': b'tony <ar@dumont.fr>',
},
'date': {
'timestamp': 1634366813,
'offset': -120,
'negative_utc': None,
},
'target': b'432109\xa9765432\xc309\x00765',
'target_type': 'revision',
'message': b'v0.0.2\nMisc performance improvments + bug fixes',
'synthetic': False
}
self.release3 = {
'id': b'87659012345678904321',
'name': b'v0.0.2',
'author': {
'name': b'tony',
'email': b'tony@ardumont.fr',
'fullname': b'tony <tony@ardumont.fr>',
},
'date': {
'timestamp': 1634336813,
'offset': 0,
'negative_utc': False,
},
'target': self.revision2['id'],
'target_type': 'revision',
'message': b'yet another synthetic release',
'synthetic': True,
}
self.fetch_history_date = datetime.datetime(
2015, 1, 2, 21, 0, 0,
tzinfo=datetime.timezone.utc)
self.fetch_history_end = datetime.datetime(
2015, 1, 2, 23, 0, 0,
tzinfo=datetime.timezone.utc)
self.fetch_history_duration = (self.fetch_history_end -
self.fetch_history_date)
self.fetch_history_data = {
'status': True,
'result': {'foo': 'bar'},
'stdout': 'blabla',
'stderr': 'blablabla',
}
self.entity1 = {
'uuid': UUID('f96a7ec1-0058-4920-90cc-7327e4b5a4bf'),
# GitHub users
'parent': UUID('ad6df473-c1d2-4f40-bc58-2b091d4a750e'),
'name': 'github:user:olasd',
'type': 'person',
'description': 'Nicolas Dandrimont',
'homepage': 'http://example.com',
'active': True,
'generated': True,
'lister_metadata': {
# swh.lister.github
'lister': '34bd6b1b-463f-43e5-a697-785107f598e4',
'id': 12877,
'type': 'user',
'last_activity': '2015-11-03',
},
'metadata': None,
'validity': [
datetime.datetime(2015, 11, 3, 11, 0, 0,
tzinfo=datetime.timezone.utc),
]
}
self.entity1_query = {
'lister': '34bd6b1b-463f-43e5-a697-785107f598e4',
'id': 12877,
'type': 'user',
}
self.entity2 = {
'uuid': UUID('3903d075-32d6-46d4-9e29-0aef3612c4eb'),
# GitHub users
'parent': UUID('ad6df473-c1d2-4f40-bc58-2b091d4a750e'),
'name': 'github:user:zacchiro',
'type': 'person',
'description': 'Stefano Zacchiroli',
'homepage': 'http://example.com',
'active': True,
'generated': True,
'lister_metadata': {
# swh.lister.github
'lister': '34bd6b1b-463f-43e5-a697-785107f598e4',
'id': 216766,
'type': 'user',
'last_activity': '2015-11-03',
},
'metadata': None,
'validity': [
datetime.datetime(2015, 11, 3, 11, 0, 0,
tzinfo=datetime.timezone.utc),
]
}
self.entity3 = {
'uuid': UUID('111df473-c1d2-4f40-bc58-2b091d4a7111'),
# GitHub users
'parent': UUID('222df473-c1d2-4f40-bc58-2b091d4a7222'),
'name': 'github:user:ardumont',
'type': 'person',
'description': 'Antoine R. Dumont a.k.a tony',
'homepage': 'https://ardumont.github.io',
'active': True,
'generated': True,
'lister_metadata': {
'lister': '34bd6b1b-463f-43e5-a697-785107f598e4',
'id': 666,
'type': 'user',
'last_activity': '2016-01-15',
},
'metadata': None,
'validity': [
datetime.datetime(2015, 11, 3, 11, 0, 0,
tzinfo=datetime.timezone.utc),
]
}
self.entity4 = {
'uuid': UUID('222df473-c1d2-4f40-bc58-2b091d4a7222'),
# GitHub users
'parent': None,
'name': 'github:user:ToNyX',
'type': 'person',
'description': 'ToNyX',
'homepage': 'https://ToNyX.github.io',
'active': True,
'generated': True,
'lister_metadata': {
'lister': '34bd6b1b-463f-43e5-a697-785107f598e4',
'id': 999,
'type': 'user',
'last_activity': '2015-12-24',
},
'metadata': None,
'validity': [
datetime.datetime(2015, 11, 3, 11, 0, 0,
tzinfo=datetime.timezone.utc),
]
}
self.entity2_query = {
'lister_metadata': {
'lister': '34bd6b1b-463f-43e5-a697-785107f598e4',
'id': 216766,
'type': 'user',
},
}
def tearDown(self):
shutil.rmtree(self.objroot)
self.cursor.execute("""SELECT table_name FROM information_schema.tables
WHERE table_schema = %s""", ('public',))
tables = set(table for (table,) in self.cursor.fetchall())
tables -= {'dbversion', 'entity', 'entity_history', 'listable_entity',
'fossology_license', 'indexer_configuration'}
for table in tables:
self.cursor.execute('truncate table %s cascade' % table)
self.cursor.execute('delete from entity where generated=true')
self.cursor.execute('delete from entity_history where generated=true')
self.conn.commit()
super().tearDown()
@istest
def check_config(self):
self.assertTrue(self.storage.check_config(check_write=True))
self.assertTrue(self.storage.check_config(check_write=False))
@istest
def content_add(self):
cont = self.cont
self.storage.content_add([cont])
if hasattr(self.storage, 'objstorage'):
self.assertIn(cont['sha1'], self.storage.objstorage)
self.cursor.execute('SELECT sha1, sha1_git, sha256, length, status'
' FROM content WHERE sha1 = %s',
(cont['sha1'],))
datum = self.cursor.fetchone()
self.assertEqual(
(datum[0].tobytes(), datum[1].tobytes(), datum[2].tobytes(),
datum[3], datum[4]),
(cont['sha1'], cont['sha1_git'], cont['sha256'],
cont['length'], 'visible'))
@istest
def content_add_collision(self):
cont1 = self.cont
# create (corrupted) content with same sha1{,_git} but != sha256
cont1b = cont1.copy()
sha256_array = bytearray(cont1b['sha256'])
sha256_array[0] += 1
cont1b['sha256'] = bytes(sha256_array)
with self.assertRaises(psycopg2.IntegrityError):
self.storage.content_add([cont1, cont1b])
@istest
def skipped_content_add(self):
cont = self.skipped_cont
cont2 = self.skipped_cont2
self.storage.content_add([cont])
self.storage.content_add([cont2])
self.cursor.execute('SELECT sha1, sha1_git, sha256, length, status,'
'reason FROM skipped_content ORDER BY sha1_git')
datum = self.cursor.fetchone()
self.assertEqual(
(datum[0], datum[1].tobytes(), datum[2],
datum[3], datum[4], datum[5]),
(None, cont['sha1_git'], None,
cont['length'], 'absent', 'Content too long'))
datum2 = self.cursor.fetchone()
self.assertEqual(
(datum2[0], datum2[1].tobytes(), datum2[2],
datum2[3], datum2[4], datum2[5]),
(None, cont2['sha1_git'], None,
cont2['length'], 'absent', 'Content too long'))
@istest
def content_missing(self):
cont2 = self.cont2
missing_cont = self.missing_cont
self.storage.content_add([cont2])
gen = self.storage.content_missing([cont2, missing_cont])
self.assertEqual(list(gen), [missing_cont['sha1']])
@istest
def content_missing_per_sha1(self):
# given
cont2 = self.cont2
missing_cont = self.missing_cont
self.storage.content_add([cont2])
# when
gen = self.storage.content_missing_per_sha1([cont2['sha1'],
missing_cont['sha1']])
# then
self.assertEqual(list(gen), [missing_cont['sha1']])
@istest
def content_get_metadata(self):
cont1 = self.cont.copy()
cont2 = self.cont2.copy()
self.storage.content_add([cont1, cont2])
gen = self.storage.content_get_metadata([cont1['sha1'], cont2['sha1']])
# we only retrieve the metadata
cont1.pop('data')
cont2.pop('data')
self.assertEqual(list(gen), [cont1, cont2])
@istest
def content_get_metadata_missing_sha1(self):
cont1 = self.cont.copy()
cont2 = self.cont2.copy()
missing_cont = self.missing_cont.copy()
self.storage.content_add([cont1, cont2])
gen = self.storage.content_get_metadata([missing_cont['sha1']])
# All the metadata keys are None
missing_cont.pop('data')
for key in list(missing_cont):
if key != 'sha1':
missing_cont[key] = None
self.assertEqual(list(gen), [missing_cont])
@istest
def directory_get(self):
# given
init_missing = list(self.storage.directory_missing([self.dir['id']]))
self.assertEqual([self.dir['id']], init_missing)
self.storage.directory_add([self.dir])
# when
actual_dirs = list(self.storage.directory_get([self.dir['id']]))
self.assertEqual(len(actual_dirs), 1)
dir0 = actual_dirs[0]
self.assertEqual(dir0['id'], self.dir['id'])
# ids are generated so non deterministic value
self.assertEqual(len(dir0['file_entries']), 1)
self.assertEqual(len(dir0['dir_entries']), 1)
self.assertIsNone(dir0['rev_entries'])
after_missing = list(self.storage.directory_missing([self.dir['id']]))
self.assertEqual([], after_missing)
@istest
def directory_add(self):
init_missing = list(self.storage.directory_missing([self.dir['id']]))
self.assertEqual([self.dir['id']], init_missing)
self.storage.directory_add([self.dir])
stored_data = list(self.storage.directory_ls(self.dir['id']))
data_to_store = [{
'dir_id': self.dir['id'],
'type': ent['type'],
'target': ent['target'],
'name': ent['name'],
'perms': ent['perms'],
'status': None,
'sha1': None,
'sha1_git': None,
'sha256': None,
}
for ent in sorted(self.dir['entries'], key=lambda ent: ent['name'])
]
self.assertEqual(data_to_store, stored_data)
after_missing = list(self.storage.directory_missing([self.dir['id']]))
self.assertEqual([], after_missing)
@istest
def directory_entry_get_by_path(self):
# given
init_missing = list(self.storage.directory_missing([self.dir3['id']]))
self.assertEqual([self.dir3['id']], init_missing)
self.storage.directory_add([self.dir3])
expected_entries = [
{
'dir_id': self.dir3['id'],
'name': b'foo',
'type': 'file',
'target': self.cont['sha1_git'],
'sha1': None,
'sha1_git': None,
'sha256': None,
'status': None,
'perms': 0o644,
},
{
'dir_id': self.dir3['id'],
'name': b'bar',
'type': 'dir',
'target': b'12345678901234560000',
'sha1': None,
'sha1_git': None,
'sha256': None,
'status': None,
'perms': 0o2000,
},
{
'dir_id': self.dir3['id'],
'name': b'hello',
'type': 'file',
'target': b'12345678901234567890',
'sha1': None,
'sha1_git': None,
'sha256': None,
'status': None,
'perms': 0o644,
},
]
# when (all must be found here)
for entry, expected_entry in zip(self.dir3['entries'],
expected_entries):
actual_entry = self.storage.directory_entry_get_by_path(
self.dir3['id'],
[entry['name']])
self.assertEqual(actual_entry, expected_entry)
# when (nothing should be found here since self.dir is not persisted.)
for entry in self.dir['entries']:
actual_entry = self.storage.directory_entry_get_by_path(
self.dir['id'],
[entry['name']])
self.assertIsNone(actual_entry)
@istest
def revision_add(self):
init_missing = self.storage.revision_missing([self.revision['id']])
self.assertEqual([self.revision['id']], list(init_missing))
self.storage.revision_add([self.revision])
end_missing = self.storage.revision_missing([self.revision['id']])
self.assertEqual([], list(end_missing))
def cache_content_revision_objects(self):
self.storage.content_add([self.cont, self.cont2, self.cont3])
directory = {
'id': b'4\x013\x422\x531\x000\xf51\xe62\xa73\xff7\xc3\xa90',
'entries': [
{
'name': b'bar',
'type': 'file',
'target': self.cont2['sha1_git'],
'perms': 0o644,
},
{
'name': b'foo',
'type': 'file',
'target': self.cont['sha1_git'],
'perms': 0o644,
},
{
'name': b'bar\xc3',
'type': 'dir',
'target': b'12345678901234567890',
'perms': 0o2000,
},
],
}
directory2 = copy.deepcopy(directory)
directory2['id'] = (directory2['id'][:-1] +
bytes([(directory2['id'][-1] + 1) % 256]))
directory2['entries'][1] = {
'name': b'foo',
'type': 'file',
'target': self.cont3['sha1_git'],
'perms': 0o644,
}
self.storage.directory_add([directory, directory2])
revision = self.revision.copy()
revision['directory'] = directory['id']
revision2 = copy.deepcopy(revision)
revision2['parents'] = [revision['id']]
revision2['directory'] = directory2['id']
revision2['id'] = (revision2['id'][:-1] +
bytes([(revision2['id'][-1] + 1) % 256]))
self.storage.revision_add([revision, revision2])
return (directory, directory2, revision, revision2)
@istest
def cache_content_revision_add(self):
# Create a real arborescence tree (contents + directory) and a
# revision targeting that directory.
# Assert the cache is empty for that revision
# Then create that revision
# Trigger the cache population for that revision
# Assert the cache now contains information for that revision
# Trigger again the cache population for that revision
# Assert the cache is not modified
# given ()
(directory, directory2,
revision, revision2) = self.cache_content_revision_objects()
# assert nothing in cache yet
count_query = '''select count(*)
from cache_content_revision'''
self.cursor.execute(count_query)
ret = self.cursor.fetchone()
self.assertEqual(ret, (0, ))
# when, triggered the first time, we cache the revision
self.storage.cache_content_revision_add([revision['id']])
# the second time, we do nothing as this is already done
self.storage.cache_content_revision_add([revision['id']])
# then
self.cursor.execute(count_query)
ret = self.cursor.fetchone()
# only 2 contents exists for that revision (the second call to
# revision_cache discards as the revision is already cached)
self.assertEqual(ret, (2, ))
self.cursor.execute('select * from cache_content_revision')
ret = self.cursor.fetchall()
expected_cache_entries = [
(directory['entries'][0]['target'], False,
[[revision['id'], directory['entries'][0]['name']]]),
(directory['entries'][1]['target'], False,
[[revision['id'], directory['entries'][1]['name']]])
]
for i, expected_entry in enumerate(expected_cache_entries):
ret_entry = (ret[i][0].tobytes(), ret[i][1],
[[ret[i][2][0][0].tobytes(),
ret[i][2][0][1].tobytes()]])
self.assertEquals(ret_entry, expected_entry)
@istest
def cache_content_revision_add_twice(self):
# given ()
(directory, directory2,
revision, revision2) = self.cache_content_revision_objects()
# assert nothing in cache yet
count_query = '''select count(*)
from cache_content_revision'''
self.cursor.execute(count_query)
ret = self.cursor.fetchone()
self.assertEqual(ret, (0, ))
# when, triggered the first time, we cache the revision
self.storage.cache_content_revision_add([revision['id']])
# the second time, we do nothing as this is already done
self.storage.cache_content_revision_add([revision2['id']])
# then
self.cursor.execute('select * from cache_content_revision')
cache_entries = {
content.tobytes(): [[rev.tobytes(), path.tobytes()]
for rev, path in rev_paths]
for content, blacklisted, rev_paths in self.cursor.fetchall()
}
self.assertEquals(len(cache_entries), 3)
self.assertEquals(len(cache_entries[self.cont['sha1_git']]), 1)
self.assertEquals(len(cache_entries[self.cont2['sha1_git']]), 2)
self.assertEquals(len(cache_entries[self.cont3['sha1_git']]), 1)
@istest
def cache_content_get_all(self):
# given
(directory, directory2,
revision, revision2) = self.cache_content_revision_objects()
# assert nothing in cache yet
test_query = '''select sha1, sha1_git, sha256, ccr.revision_paths
from cache_content_revision ccr
inner join content c on c.sha1_git=ccr.content'''
self.storage.cache_content_revision_add([revision['id']])
self.cursor.execute(test_query, (revision['id'],))
ret = list(cursor_to_bytes(self.cursor))
self.assertEqual(len(ret), 2)
expected_contents = []
for entry in ret:
expected_contents.append(dict(
zip(['sha1', 'sha1_git', 'sha256', 'revision_paths'], entry)))
# 1. default filters gives everything
actual_cache_contents = list(self.storage.cache_content_get_all())
self.assertEquals(actual_cache_contents, expected_contents)
@istest
def cache_content_get(self):
# given
(directory, directory2,
revision, revision2) = self.cache_content_revision_objects()
# assert nothing in cache yet
test_query = '''select c.sha1, c.sha1_git, c.sha256, ccr.revision_paths
from cache_content_revision ccr
inner join content c on c.sha1_git=ccr.content
where ccr.content=%s'''
self.storage.cache_content_revision_add([revision['id']])
self.cursor.execute(test_query, (self.cont2['sha1_git'],))
ret = list(cursor_to_bytes(self.cursor))[0]
self.assertIsNotNone(ret)
expected_content = dict(
zip(['sha1', 'sha1_git', 'sha256', 'revision_paths'], ret))
# when
actual_cache_content = self.storage.cache_content_get(self.cont2)
# then
self.assertEquals(actual_cache_content, expected_content)
@istest
def revision_log(self):
# given
# self.revision4 -is-child-of-> self.revision3
self.storage.revision_add([self.revision3,
self.revision4])
# when
actual_results = list(self.storage.revision_log(
[self.revision4['id']]))
# hack: ids generated
for actual_result in actual_results:
del actual_result['author']['id']
del actual_result['committer']['id']
self.assertEqual(len(actual_results), 2) # rev4 -child-> rev3
self.assertEquals(actual_results[0], self.revision4)
self.assertEquals(actual_results[1], self.revision3)
@istest
def revision_log_with_limit(self):
# given
# self.revision4 -is-child-of-> self.revision3
self.storage.revision_add([self.revision3,
self.revision4])
actual_results = list(self.storage.revision_log(
[self.revision4['id']], 1))
# hack: ids generated
for actual_result in actual_results:
del actual_result['author']['id']
del actual_result['committer']['id']
self.assertEqual(len(actual_results), 1)
self.assertEquals(actual_results[0], self.revision4)
@istest
def revision_log_by(self):
# given
origin_id = self.storage.origin_add_one(self.origin2)
self.storage.revision_add([self.revision3,
self.revision4])
# occurrence3 targets 'revision4'
# with branch 'master' and origin origin_id
occurrence3 = self.occurrence3.copy()
date_visit1 = self.date_visit3
origin_visit1 = self.storage.origin_visit_add(origin_id,
date_visit1)
occurrence3.update({
'origin': origin_id,
'target': self.revision4['id'],
'visit': origin_visit1['visit'],
})
self.storage.occurrence_add([occurrence3])
# self.revision4 -is-child-of-> self.revision3
# when
actual_results = list(self.storage.revision_log_by(
origin_id,
branch_name=occurrence3['branch'],
timestamp=date_visit1))
# hack: ids generated
for actual_result in actual_results:
del actual_result['author']['id']
del actual_result['committer']['id']
self.assertEqual(len(actual_results), 2)
self.assertEquals(actual_results[0], self.revision4)
self.assertEquals(actual_results[1], self.revision3)
# when - 2
actual_results = list(self.storage.revision_log_by(
origin_id,
branch_name=None,
timestamp=None,
limit=1))
# then
for actual_result in actual_results:
del actual_result['author']['id']
del actual_result['committer']['id']
self.assertEqual(len(actual_results), 1)
self.assertEquals(actual_results[0], self.revision4)
# when - 3 (revision not found)
actual_res = list(self.storage.revision_log_by(
origin_id,
branch_name='inexistant-branch',
timestamp=None))
self.assertEquals(actual_res, [])
@staticmethod
def _short_revision(revision):
return [revision['id'], revision['parents']]
@istest
def revision_shortlog(self):
# given
# self.revision4 -is-child-of-> self.revision3
self.storage.revision_add([self.revision3,
self.revision4])
# when
actual_results = list(self.storage.revision_shortlog(
[self.revision4['id']]))
self.assertEqual(len(actual_results), 2) # rev4 -child-> rev3
self.assertEquals(list(actual_results[0]),
self._short_revision(self.revision4))
self.assertEquals(list(actual_results[1]),
self._short_revision(self.revision3))
@istest
def revision_shortlog_with_limit(self):
# given
# self.revision4 -is-child-of-> self.revision3
self.storage.revision_add([self.revision3,
self.revision4])
actual_results = list(self.storage.revision_shortlog(
[self.revision4['id']], 1))
self.assertEqual(len(actual_results), 1)
self.assertEquals(list(actual_results[0]),
self._short_revision(self.revision4))
@istest
def revision_get(self):
self.storage.revision_add([self.revision])
actual_revisions = list(self.storage.revision_get(
[self.revision['id'], self.revision2['id']]))
# when
del actual_revisions[0]['author']['id'] # hack: ids are generated
del actual_revisions[0]['committer']['id']
self.assertEqual(len(actual_revisions), 2)
self.assertEqual(actual_revisions[0], self.revision)
self.assertIsNone(actual_revisions[1])
@istest
def revision_get_no_parents(self):
self.storage.revision_add([self.revision3])
get = list(self.storage.revision_get([self.revision3['id']]))
self.assertEqual(len(get), 1)
self.assertEqual(get[0]['parents'], []) # no parents on this one
@istest
def revision_get_by(self):
# given
self.storage.content_add([self.cont2])
self.storage.directory_add([self.dir2]) # point to self.cont
self.storage.revision_add([self.revision2]) # points to self.dir
origin_id = self.storage.origin_add_one(self.origin2)
# occurrence2 points to 'revision2' with branch 'master', we
# need to point to the right origin
occurrence2 = self.occurrence2.copy()
date_visit1 = self.date_visit2
origin_visit1 = self.storage.origin_visit_add(origin_id, date_visit1)
occurrence2.update({
'origin': origin_id,
'visit': origin_visit1['visit'],
})
self.storage.occurrence_add([occurrence2])
# we want only revision 2
expected_revisions = list(self.storage.revision_get(
[self.revision2['id']]))
# when
actual_results = list(self.storage.revision_get_by(
origin_id,
occurrence2['branch'],
None))
self.assertEqual(actual_results[0], expected_revisions[0])
# when (with no branch filtering, it's still ok)
actual_results = list(self.storage.revision_get_by(
origin_id,
None,
None))
self.assertEqual(actual_results[0], expected_revisions[0])
@istest
def revision_get_by_multiple_occurrence(self):
# 2 occurrences pointing to 2 different revisions
# each occurence have 1 hour delta
# the api must return the revision whose occurrence is the nearest.
# given
self.storage.content_add([self.cont2])
self.storage.directory_add([self.dir2])
self.storage.revision_add([self.revision2, self.revision3])
origin_id = self.storage.origin_add_one(self.origin2)
# occurrence2 points to 'revision2' with branch 'master', we
# need to point to the right origin
date_visit1 = self.date_visit2
origin_visit1 = self.storage.origin_visit_add(origin_id, date_visit1)
occurrence2 = self.occurrence2.copy()
occurrence2.update({
'origin': origin_id,
'visit': origin_visit1['visit']
})
dt = datetime.timedelta(days=1)
date_visit2 = date_visit1 + dt
origin_visit2 = self.storage.origin_visit_add(origin_id, date_visit2)
occurrence3 = self.occurrence2.copy()
occurrence3.update({
'origin': origin_id,
'visit': origin_visit2['visit'],
'target': self.revision3['id'],
})
# 2 occurrences on same revision with lower validity date with 1h delta
self.storage.occurrence_add([occurrence2])
self.storage.occurrence_add([occurrence3])
# when
actual_results0 = list(self.storage.revision_get_by(
origin_id,
occurrence2['branch'],
date_visit1))
# hack: ids are generated
del actual_results0[0]['author']['id']
del actual_results0[0]['committer']['id']
self.assertEquals(len(actual_results0), 1)
self.assertEqual(actual_results0, [self.revision2])
# when
actual_results1 = list(self.storage.revision_get_by(
origin_id,
occurrence2['branch'],
date_visit1 + dt/3)) # closer to first visit
# hack: ids are generated
del actual_results1[0]['author']['id']
del actual_results1[0]['committer']['id']
self.assertEquals(len(actual_results1), 1)
self.assertEqual(actual_results1, [self.revision2])
# when
actual_results2 = list(self.storage.revision_get_by(
origin_id,
occurrence2['branch'],
date_visit1 + 2*dt/3)) # closer to second visit
del actual_results2[0]['author']['id']
del actual_results2[0]['committer']['id']
self.assertEquals(len(actual_results2), 1)
self.assertEqual(actual_results2, [self.revision3])
# when
actual_results3 = list(self.storage.revision_get_by(
origin_id,
occurrence3['branch'],
date_visit2))
# hack: ids are generated
del actual_results3[0]['author']['id']
del actual_results3[0]['committer']['id']
self.assertEquals(len(actual_results3), 1)
self.assertEqual(actual_results3, [self.revision3])
# when
actual_results4 = list(self.storage.revision_get_by(
origin_id,
None,
None))
for actual_result in actual_results4:
del actual_result['author']['id']
del actual_result['committer']['id']
self.assertEquals(len(actual_results4), 2)
self.assertCountEqual(actual_results4,
[self.revision3, self.revision2])
@istest
def release_add(self):
init_missing = self.storage.release_missing([self.release['id'],
self.release2['id']])
self.assertEqual([self.release['id'], self.release2['id']],
list(init_missing))
self.storage.release_add([self.release, self.release2])
end_missing = self.storage.release_missing([self.release['id'],
self.release2['id']])
self.assertEqual([], list(end_missing))
@istest
def release_get(self):
# given
self.storage.release_add([self.release, self.release2])
# when
actual_releases = list(self.storage.release_get([self.release['id'],
self.release2['id']]))
# then
for actual_release in actual_releases:
del actual_release['author']['id'] # hack: ids are generated
self.assertEquals([self.release, self.release2],
[actual_releases[0], actual_releases[1]])
@istest
def release_get_by(self):
# given
self.storage.revision_add([self.revision2]) # points to self.dir
self.storage.release_add([self.release3])
origin_id = self.storage.origin_add_one(self.origin2)
# occurrence2 points to 'revision2' with branch 'master', we
# need to point to the right origin
origin_visit = self.storage.origin_visit_add(origin_id,
self.date_visit2)
occurrence2 = self.occurrence2.copy()
occurrence2.update({
'origin': origin_id,
'visit': origin_visit['visit'],
})
self.storage.occurrence_add([occurrence2])
# we want only revision 2
expected_releases = list(self.storage.release_get(
[self.release3['id']]))
# when
actual_results = list(self.storage.release_get_by(
occurrence2['origin']))
# then
self.assertEqual(actual_results[0], expected_releases[0])
@istest
def origin_add_one(self):
origin0 = self.storage.origin_get(self.origin)
self.assertIsNone(origin0)
id = self.storage.origin_add_one(self.origin)
actual_origin = self.storage.origin_get({'url': self.origin['url'],
'type': self.origin['type']})
self.assertEqual(actual_origin['id'], id)
id2 = self.storage.origin_add_one(self.origin)
self.assertEqual(id, id2)
@istest
def origin_add(self):
origin0 = self.storage.origin_get(self.origin)
self.assertIsNone(origin0)
id1, id2 = self.storage.origin_add([self.origin, self.origin2])
actual_origin = self.storage.origin_get({
'url': self.origin['url'],
'type': self.origin['type'],
})
self.assertEqual(actual_origin['id'], id1)
actual_origin2 = self.storage.origin_get({
'url': self.origin2['url'],
'type': self.origin2['type'],
})
self.assertEqual(actual_origin2['id'], id2)
@istest
def origin_add_twice(self):
add1 = self.storage.origin_add([self.origin, self.origin2])
add2 = self.storage.origin_add([self.origin, self.origin2])
self.assertEqual(add1, add2)
@istest
def origin_get(self):
self.assertIsNone(self.storage.origin_get(self.origin))
id = self.storage.origin_add_one(self.origin)
# lookup per type and url (returns id)
actual_origin0 = self.storage.origin_get({'url': self.origin['url'],
'type': self.origin['type']})
self.assertEqual(actual_origin0['id'], id)
# lookup per id (returns dict)
actual_origin1 = self.storage.origin_get({'id': id})
self.assertEqual(actual_origin1, {'id': id,
'type': self.origin['type'],
'url': self.origin['url'],
'lister': None,
'project': None})
@istest
def origin_visit_add(self):
# given
self.assertIsNone(self.storage.origin_get(self.origin2))
origin_id = self.storage.origin_add_one(self.origin2)
self.assertIsNotNone(origin_id)
# when
origin_visit1 = self.storage.origin_visit_add(
origin_id,
ts=self.date_visit2)
# then
self.assertEquals(origin_visit1['origin'], origin_id)
self.assertIsNotNone(origin_visit1['visit'])
self.assertTrue(origin_visit1['visit'] > 0)
actual_origin_visits = list(self.storage.origin_visit_get(origin_id))
self.assertEquals(actual_origin_visits,
[{
'origin': origin_id,
'date': self.date_visit2,
'visit': origin_visit1['visit'],
'status': 'ongoing',
'metadata': None,
}])
@istest
def origin_visit_update(self):
# given
origin_id = self.storage.origin_add_one(self.origin2)
origin_id2 = self.storage.origin_add_one(self.origin)
origin_visit1 = self.storage.origin_visit_add(
origin_id,
ts=self.date_visit2)
origin_visit2 = self.storage.origin_visit_add(
origin_id,
ts=self.date_visit3)
origin_visit3 = self.storage.origin_visit_add(
origin_id2,
ts=self.date_visit3)
# when
visit1_metadata = {
'contents': 42,
'directories': 22,
}
self.storage.origin_visit_update(
origin_id, origin_visit1['visit'], status='full',
metadata=visit1_metadata)
self.storage.origin_visit_update(origin_id2, origin_visit3['visit'],
status='partial')
# then
actual_origin_visits = list(self.storage.origin_visit_get(origin_id))
self.assertEquals(actual_origin_visits,
[{
'origin': origin_visit2['origin'],
'date': self.date_visit2,
'visit': origin_visit1['visit'],
'status': 'full',
'metadata': visit1_metadata,
},
{
'origin': origin_visit2['origin'],
'date': self.date_visit3,
'visit': origin_visit2['visit'],
'status': 'ongoing',
'metadata': None,
}])
actual_origin_visits2 = list(self.storage.origin_visit_get(origin_id2))
self.assertEquals(actual_origin_visits2,
[{
'origin': origin_visit3['origin'],
'date': self.date_visit3,
'visit': origin_visit3['visit'],
'status': 'partial',
'metadata': None,
}])
@istest
def origin_visit_get_by(self):
origin_id = self.storage.origin_add_one(self.origin2)
origin_id2 = self.storage.origin_add_one(self.origin)
origin_visit1 = self.storage.origin_visit_add(
origin_id,
ts=self.date_visit2)
occurrence2 = self.occurrence2.copy()
occurrence2.update({
'origin': origin_id,
'visit': origin_visit1['visit'],
})
self.storage.occurrence_add([occurrence2])
# Add some other {origin, visit} entries
self.storage.origin_visit_add(origin_id, ts=self.date_visit3)
self.storage.origin_visit_add(origin_id2, ts=self.date_visit3)
# when
visit1_metadata = {
'contents': 42,
'directories': 22,
}
self.storage.origin_visit_update(
origin_id, origin_visit1['visit'], status='full',
metadata=visit1_metadata)
expected_origin_visit = origin_visit1.copy()
expected_origin_visit.update({
'origin': origin_id,
'visit': origin_visit1['visit'],
'date': self.date_visit2,
'metadata': visit1_metadata,
'status': 'full',
'occurrences': {
occurrence2['branch']: {
'target': occurrence2['target'],
'target_type': occurrence2['target_type'],
}
}
})
# when
actual_origin_visit1 = self.storage.origin_visit_get_by(
origin_visit1['origin'], origin_visit1['visit'])
# then
self.assertEquals(actual_origin_visit1, expected_origin_visit)
@istest
def origin_visit_get_by_no_result(self):
# No result
actual_origin_visit = self.storage.origin_visit_get_by(
10, 999)
self.assertIsNone(actual_origin_visit)
@istest
def occurrence_add(self):
occur = self.occurrence.copy()
origin_id = self.storage.origin_add_one(self.origin2)
date_visit1 = self.date_visit1
origin_visit1 = self.storage.origin_visit_add(origin_id, date_visit1)
revision = self.revision.copy()
revision['id'] = occur['target']
self.storage.revision_add([revision])
occur.update({
'origin': origin_id,
'visit': origin_visit1['visit'],
})
self.storage.occurrence_add([occur])
test_query = '''
with indiv_occurrences as (
select origin, branch, target, target_type, unnest(visits) as visit
from occurrence_history
)
select origin, branch, target, target_type, date
from indiv_occurrences
left join origin_visit using(origin, visit)
order by origin, date'''
self.cursor.execute(test_query)
ret = self.cursor.fetchall()
self.assertEqual(len(ret), 1)
self.assertEqual(
(ret[0][0], ret[0][1].tobytes(), ret[0][2].tobytes(),
ret[0][3], ret[0][4]),
(occur['origin'], occur['branch'], occur['target'],
occur['target_type'], self.date_visit1))
date_visit2 = date_visit1 + datetime.timedelta(hours=10)
origin_visit2 = self.storage.origin_visit_add(origin_id, date_visit2)
occur2 = occur.copy()
occur2.update({
'visit': origin_visit2['visit'],
})
self.storage.occurrence_add([occur2])
self.cursor.execute(test_query)
ret = self.cursor.fetchall()
self.assertEqual(len(ret), 2)
self.assertEqual(
(ret[0][0], ret[0][1].tobytes(), ret[0][2].tobytes(),
ret[0][3], ret[0][4]),
(occur['origin'], occur['branch'], occur['target'],
occur['target_type'], date_visit1))
self.assertEqual(
(ret[1][0], ret[1][1].tobytes(), ret[1][2].tobytes(),
ret[1][3], ret[1][4]),
(occur2['origin'], occur2['branch'], occur2['target'],
occur2['target_type'], date_visit2))
@istest
def occurrence_get(self):
# given
occur = self.occurrence.copy()
origin_id = self.storage.origin_add_one(self.origin2)
origin_visit1 = self.storage.origin_visit_add(origin_id,
self.date_visit1)
revision = self.revision.copy()
revision['id'] = occur['target']
self.storage.revision_add([revision])
occur.update({
'origin': origin_id,
'visit': origin_visit1['visit'],
})
self.storage.occurrence_add([occur])
self.storage.occurrence_add([occur])
# when
actual_occurrence = list(self.storage.occurrence_get(origin_id))
# then
expected_occurrence = self.occurrence.copy()
expected_occurrence.update({
'origin': origin_id
})
self.assertEquals(len(actual_occurrence), 1)
self.assertEquals(actual_occurrence[0], expected_occurrence)
def _trigger_cache_provenance(self, origin_visit):
"""Trigger cache population for cache_content_revision.
"""
ret = list(self.storage.cache_revision_origin_add(
origin_visit['origin'],
origin_visit['visit'],
))
for revision_id in ret:
self.storage.cache_content_revision_add([revision_id])
return ret
@istest
def content_find_provenance_with_present_content(self):
# 1. with something to find
# given
origin_id = self.storage.origin_add_one(self.origin2)
self.storage.content_add([self.cont2])
self.storage.directory_add([self.dir2]) # point to self.cont
self.storage.revision_add([self.revision3]) # points to self.dir
occurrence = self.occurrence3.copy()
occurrence['target'] = self.revision3['id']
origin_visit1 = self.storage.origin_visit_add(origin_id,
self.date_visit2)
occurrence.update({
'origin': origin_id,
'visit': origin_visit1['visit'],
})
self.storage.occurrence_add([occurrence])
# Trigger cache population for cache_content_revision
cached_revisions = self._trigger_cache_provenance(origin_visit1)
self.assertIn(self.revision3['id'], cached_revisions)
# when
occs = list(self.storage.content_find_provenance(
{'sha1': self.cont2['sha1']}))
# then
self.assertEquals(len(occs), 1)
self.assertEquals(occs[0]['origin'], origin_visit1['origin'])
self.assertEquals(occs[0]['visit'], origin_visit1['visit'])
self.assertEquals(occs[0]['revision'], self.revision3['id'])
self.assertEquals(occs[0]['path'], self.dir2['entries'][0]['name'])
occs2 = list(self.storage.content_find_provenance(
{'sha1_git': self.cont2['sha1_git']}))
self.assertEquals(len(occs2), 1)
self.assertEquals(occs2[0]['origin'], origin_visit1['origin'])
self.assertEquals(occs2[0]['visit'], origin_visit1['visit'])
self.assertEquals(occs2[0]['revision'], self.revision3['id'])
self.assertEquals(occs2[0]['path'], self.dir2['entries'][0]['name'])
occs3 = list(self.storage.content_find_provenance(
{'sha256': self.cont2['sha256']}))
self.assertEquals(len(occs3), 1)
self.assertEquals(occs3[0]['origin'], origin_visit1['origin'])
self.assertEquals(occs3[0]['visit'], origin_visit1['visit'])
self.assertEquals(occs3[0]['revision'], self.revision3['id'])
self.assertEquals(occs3[0]['path'], self.dir2['entries'][0]['name'])
@istest
def content_find_provenance_with_non_present_content(self):
# 1. with something that does not exist
missing_cont = self.missing_cont
occ = list(self.storage.content_find_provenance(
{'sha1': missing_cont['sha1']}))
self.assertEquals(occ, [],
"Content does not exist so no occurrence")
# 2. with something that does not exist
occ = list(self.storage.content_find_provenance(
{'sha1_git': missing_cont['sha1_git']}))
self.assertEquals(occ, [],
"Content does not exist so no occurrence")
# 3. with something that does not exist
occ = list(self.storage.content_find_provenance(
{'sha256': missing_cont['sha256']}))
self.assertEquals(occ, [],
"Content does not exist so no occurrence")
@istest
def content_find_occurrence_bad_input(self):
# 1. with bad input
with self.assertRaises(ValueError) as cm:
list(self.storage.content_find_provenance({})) # empty is bad
self.assertIn('content keys', cm.exception.args[0])
# 2. with bad input
with self.assertRaises(ValueError) as cm:
list(self.storage.content_find_provenance(
{'unknown-sha1': 'something'})) # not the right key
self.assertIn('content keys', cm.exception.args[0])
@istest
def entity_get_from_lister_metadata(self):
self.storage.entity_add([self.entity1])
fetched_entities = list(
self.storage.entity_get_from_lister_metadata(
[self.entity1_query, self.entity2_query]))
# Entity 1 should have full metadata, with last_seen/last_id instead
# of validity
entity1 = self.entity1.copy()
entity1['last_seen'] = entity1['validity'][0]
del fetched_entities[0]['last_id']
del entity1['validity']
# Entity 2 should have no metadata
entity2 = {
'uuid': None,
'lister_metadata': self.entity2_query.copy(),
}
self.assertEquals(fetched_entities, [entity1, entity2])
@istest
def entity_get_from_lister_metadata_twice(self):
self.storage.entity_add([self.entity1])
fetched_entities1 = list(
self.storage.entity_get_from_lister_metadata(
[self.entity1_query]))
fetched_entities2 = list(
self.storage.entity_get_from_lister_metadata(
[self.entity1_query]))
self.assertEquals(fetched_entities1, fetched_entities2)
@istest
def entity_get(self):
# given
self.storage.entity_add([self.entity4])
self.storage.entity_add([self.entity3])
# when: entity3 -child-of-> entity4
actual_entity3 = list(self.storage.entity_get(self.entity3['uuid']))
self.assertEquals(len(actual_entity3), 2)
# remove dynamic data (modified by db)
entity3 = self.entity3.copy()
entity4 = self.entity4.copy()
del entity3['validity']
del entity4['validity']
del actual_entity3[0]['last_seen']
del actual_entity3[0]['last_id']
del actual_entity3[1]['last_seen']
del actual_entity3[1]['last_id']
self.assertEquals(actual_entity3, [entity3, entity4])
# when: entity4 only child
actual_entity4 = list(self.storage.entity_get(self.entity4['uuid']))
self.assertEquals(len(actual_entity4), 1)
# remove dynamic data (modified by db)
entity4 = self.entity4.copy()
del entity4['validity']
del actual_entity4[0]['last_id']
del actual_entity4[0]['last_seen']
self.assertEquals(actual_entity4, [entity4])
@istest
def entity_get_one(self):
# given
self.storage.entity_add([self.entity3, self.entity4])
# when: entity3 -child-of-> entity4
actual_entity3 = self.storage.entity_get_one(self.entity3['uuid'])
# remove dynamic data (modified by db)
entity3 = self.entity3.copy()
del entity3['validity']
del actual_entity3['last_seen']
del actual_entity3['last_id']
self.assertEquals(actual_entity3, entity3)
@istest
def stat_counters(self):
expected_keys = ['content', 'directory', 'directory_entry_dir',
'occurrence', 'origin', 'person', 'revision']
counters = self.storage.stat_counters()
self.assertTrue(set(expected_keys) <= set(counters))
self.assertIsInstance(counters[expected_keys[0]], int)
@istest
def content_find_with_present_content(self):
# 1. with something to find
cont = self.cont
self.storage.content_add([cont])
actually_present = self.storage.content_find({'sha1': cont['sha1']})
actually_present.pop('ctime')
self.assertEqual(actually_present, {
'sha1': cont['sha1'],
'sha256': cont['sha256'],
'sha1_git': cont['sha1_git'],
'length': cont['length'],
'status': 'visible'
})
# 2. with something to find
actually_present = self.storage.content_find(
{'sha1_git': cont['sha1_git']})
actually_present.pop('ctime')
self.assertEqual(actually_present, {
'sha1': cont['sha1'],
'sha256': cont['sha256'],
'sha1_git': cont['sha1_git'],
'length': cont['length'],
'status': 'visible'
})
# 3. with something to find
actually_present = self.storage.content_find(
{'sha256': cont['sha256']})
actually_present.pop('ctime')
self.assertEqual(actually_present, {
'sha1': cont['sha1'],
'sha256': cont['sha256'],
'sha1_git': cont['sha1_git'],
'length': cont['length'],
'status': 'visible'
})
# 4. with something to find
actually_present = self.storage.content_find(
{'sha1': cont['sha1'],
'sha1_git': cont['sha1_git'],
'sha256': cont['sha256']})
actually_present.pop('ctime')
self.assertEqual(actually_present, {
'sha1': cont['sha1'],
'sha256': cont['sha256'],
'sha1_git': cont['sha1_git'],
'length': cont['length'],
'status': 'visible'
})
@istest
def content_find_with_non_present_content(self):
# 1. with something that does not exist
missing_cont = self.missing_cont
actually_present = self.storage.content_find(
{'sha1': missing_cont['sha1']})
self.assertIsNone(actually_present)
# 2. with something that does not exist
actually_present = self.storage.content_find(
{'sha1_git': missing_cont['sha1_git']})
self.assertIsNone(actually_present)
# 3. with something that does not exist
actually_present = self.storage.content_find(
{'sha256': missing_cont['sha256']})
self.assertIsNone(actually_present)
@istest
def content_find_bad_input(self):
# 1. with bad input
with self.assertRaises(ValueError):
self.storage.content_find({}) # empty is bad
# 2. with bad input
with self.assertRaises(ValueError):
self.storage.content_find(
{'unknown-sha1': 'something'}) # not the right key
@istest
def object_find_by_sha1_git(self):
sha1_gits = [b'00000000000000000000']
expected = {
b'00000000000000000000': [],
}
self.storage.content_add([self.cont])
sha1_gits.append(self.cont['sha1_git'])
expected[self.cont['sha1_git']] = [{
'sha1_git': self.cont['sha1_git'],
'type': 'content',
'id': self.cont['sha1'],
}]
self.storage.directory_add([self.dir])
sha1_gits.append(self.dir['id'])
expected[self.dir['id']] = [{
'sha1_git': self.dir['id'],
'type': 'directory',
'id': self.dir['id'],
}]
self.storage.revision_add([self.revision])
sha1_gits.append(self.revision['id'])
expected[self.revision['id']] = [{
'sha1_git': self.revision['id'],
'type': 'revision',
'id': self.revision['id'],
}]
self.storage.release_add([self.release])
sha1_gits.append(self.release['id'])
expected[self.release['id']] = [{
'sha1_git': self.release['id'],
'type': 'release',
'id': self.release['id'],
}]
ret = self.storage.object_find_by_sha1_git(sha1_gits)
for val in ret.values():
for obj in val:
del obj['object_id']
self.assertEqual(expected, ret)
@istest
def content_mimetype_missing(self):
# given
cont2 = self.cont2
self.storage.content_add([cont2])
mimetypes = [self.cont2['sha1'], self.missing_cont['sha1']]
# when
actual_missing = self.storage.content_mimetype_missing(mimetypes)
# then
self.assertEqual(list(actual_missing), [
self.cont2['sha1'],
self.missing_cont['sha1']
])
# given
self.storage.content_mimetype_add([{
'id': self.cont2['sha1'],
'mimetype': b'text/plain',
'encoding': b'utf-8'
}])
# when
actual_missing = self.storage.content_mimetype_missing(mimetypes)
# then
self.assertEqual(list(actual_missing), [self.missing_cont['sha1']])
@istest
def content_mimetype_add__drop_duplicate(self):
# given
cont2 = self.cont2
self.storage.content_add([cont2])
mimetype_v1 = {
'id': self.cont2['sha1'],
'mimetype': b'text/plain',
'encoding': b'utf-8'
}
# given
self.storage.content_mimetype_add([mimetype_v1])
# when
actual_mimetypes = list(self.storage.content_mimetype_get(
[self.cont2['sha1']]))
# then
self.assertEqual(actual_mimetypes[0], mimetype_v1)
# given
mimetype_v2 = mimetype_v1.copy()
mimetype_v2.update({
'mimetype': b'text/html',
'encoding': b'us-ascii',
})
self.storage.content_mimetype_add([mimetype_v2])
actual_mimetypes = list(self.storage.content_mimetype_get(
[self.cont2['sha1']]))
# mimetype did not change as the v2 was dropped.
self.assertEqual(actual_mimetypes[0], mimetype_v1)
@istest
def content_mimetype_add__update_in_place_duplicate(self):
# given
cont2 = self.cont2
self.storage.content_add([cont2])
mimetype_v1 = {
'id': self.cont2['sha1'],
'mimetype': b'text/plain',
'encoding': b'utf-8'
}
# given
self.storage.content_mimetype_add([mimetype_v1])
# when
actual_mimetypes = list(self.storage.content_mimetype_get(
[self.cont2['sha1']]))
# then
self.assertEqual(actual_mimetypes[0], mimetype_v1)
# given
mimetype_v2 = mimetype_v1.copy()
mimetype_v2.update({
'mimetype': b'text/html',
'encoding': b'us-ascii',
})
self.storage.content_mimetype_add([mimetype_v2], conflict_update=True)
actual_mimetypes = list(self.storage.content_mimetype_get(
[self.cont2['sha1']]))
# mimetype did change as the v2 was used to overwrite v1
self.assertEqual(actual_mimetypes[0], mimetype_v2)
@istest
def content_mimetype_get(self):
# given
cont2 = self.cont2
self.storage.content_add([cont2])
mimetypes = [self.cont2['sha1'], self.missing_cont['sha1']]
mimetype1 = {
'id': self.cont2['sha1'],
'mimetype': b'text/plain',
'encoding': b'utf-8'
}
# when
self.storage.content_mimetype_add([mimetype1])
# then
actual_mimetypes = self.storage.content_mimetype_get(mimetypes)
# then
self.assertEqual(list(actual_mimetypes), [mimetype1])
@istest
def content_language_missing(self):
# given
cont2 = self.cont2
self.storage.content_add([cont2])
languages = [self.cont2['sha1'], self.missing_cont['sha1']]
# when
actual_missing = self.storage.content_language_missing(languages)
# then
self.assertEqual(list(actual_missing), [
self.cont2['sha1'],
self.missing_cont['sha1']
])
# given
self.storage.content_language_add([{
'id': self.cont2['sha1'],
'lang': 'haskell',
}])
# when
actual_missing = self.storage.content_language_missing(languages)
# then
self.assertEqual(list(actual_missing), [self.missing_cont['sha1']])
@istest
def content_language_get(self):
# given
cont2 = self.cont2
self.storage.content_add([cont2])
languages = [self.cont2['sha1'], self.missing_cont['sha1']]
language1 = {
'id': self.cont2['sha1'],
'lang': 'common-lisp',
}
# when
self.storage.content_language_add([language1])
# then
actual_languages = self.storage.content_language_get(languages)
# then
self.assertEqual(list(actual_languages), [language1])
@istest
def content_language_add__drop_duplicate(self):
# given
cont2 = self.cont2
self.storage.content_add([cont2])
language_v1 = {
'id': self.cont2['sha1'],
'lang': 'emacslisp',
}
# given
self.storage.content_language_add([language_v1])
# when
actual_languages = list(self.storage.content_language_get(
[self.cont2['sha1']]))
# then
self.assertEqual(actual_languages[0], language_v1)
# given
language_v2 = language_v1.copy()
language_v2.update({
'lang': 'common-lisp',
})
self.storage.content_language_add([language_v2])
actual_languages = list(self.storage.content_language_get(
[self.cont2['sha1']]))
# language did not change as the v2 was dropped.
self.assertEqual(actual_languages[0], language_v1)
@istest
def content_language_add__update_in_place_duplicate(self):
# given
cont2 = self.cont2
self.storage.content_add([cont2])
language_v1 = {
'id': self.cont2['sha1'],
'lang': 'common-lisp',
}
# given
self.storage.content_language_add([language_v1])
# when
actual_languages = list(self.storage.content_language_get(
[self.cont2['sha1']]))
# then
self.assertEqual(actual_languages[0], language_v1)
# given
language_v2 = language_v1.copy()
language_v2.update({
'lang': 'emacslisp',
})
self.storage.content_language_add([language_v2], conflict_update=True)
actual_languages = list(self.storage.content_language_get(
[self.cont2['sha1']]))
# language did change as the v2 was used to overwrite v1
self.assertEqual(actual_languages[0], language_v2)
@istest
def content_ctags_missing(self):
# given
cont2 = self.cont2
self.storage.content_add([cont2])
ctags = [
{
'id': self.cont2['sha1'],
'tool_name': 'universal-ctags',
'tool_version': '~git7859817b',
},
{
'id': self.missing_cont['sha1'],
'tool_name': 'universal-ctags',
'tool_version': '~git7859817b',
}
]
# when
actual_missing = self.storage.content_ctags_missing(ctags)
# then
self.assertEqual(list(actual_missing), [
self.cont2['sha1'],
self.missing_cont['sha1']
])
# given
self.storage.content_ctags_add([
{
'id': self.cont2['sha1'],
'tool_name': 'universal-ctags',
'tool_version': '~git7859817b',
'ctags': [{
'name': 'done',
'kind': 'variable',
'line': 119,
'lang': 'OCaml',
}]
},
])
# when
actual_missing = self.storage.content_ctags_missing(ctags)
# then
self.assertEqual(list(actual_missing), [self.missing_cont['sha1']])
@istest
def content_ctags_get(self):
# given
cont2 = self.cont2
self.storage.content_add([cont2])
ctags = [self.cont2['sha1'], self.missing_cont['sha1']]
ctag1 = {
'id': self.cont2['sha1'],
'tool_name': 'universal-ctags',
'tool_version': '~git7859817b',
'ctags': [
{
'name': 'done',
'kind': 'variable',
'line': 100,
'lang': 'Python',
},
{
'name': 'main',
'kind': 'function',
'line': 119,
'lang': 'Python',
}]
}
# when
self.storage.content_ctags_add([ctag1])
# then
actual_ctags = list(self.storage.content_ctags_get(ctags))
# then
expected_ctags = [
{
'id': self.cont2['sha1'],
- 'tool_name': 'universal-ctags',
- 'tool_version': '~git7859817b',
+ 'tool': {
+ 'name': 'universal-ctags',
+ 'version': '~git7859817b',
+ },
'name': 'done',
'kind': 'variable',
'line': 100,
'lang': 'Python',
},
{
'id': self.cont2['sha1'],
- 'tool_name': 'universal-ctags',
- 'tool_version': '~git7859817b',
+ 'tool': {
+ 'name': 'universal-ctags',
+ 'version': '~git7859817b',
+ },
'name': 'main',
'kind': 'function',
'line': 119,
'lang': 'Python',
}
]
self.assertEqual(actual_ctags, expected_ctags)
- @attr('one')
@istest
def content_ctags_search(self):
# 1. given
cont = self.cont
cont2 = self.cont2
self.storage.content_add([cont, cont2])
ctag1 = {
'id': cont['sha1'],
'tool_name': 'universal-ctags',
'tool_version': '~git7859817b',
'ctags': [
{
'name': 'hello',
'kind': 'function',
'line': 133,
'lang': 'Python',
},
{
'name': 'counter',
'kind': 'variable',
'line': 119,
'lang': 'Python',
},
]
}
ctag2 = {
'id': cont2['sha1'],
'tool_name': 'universal-ctags',
'tool_version': '~git7859817b',
'ctags': [
{
'name': 'hello',
'kind': 'variable',
'line': 100,
'lang': 'C',
},
]
}
self.storage.content_ctags_add([ctag1, ctag2])
# 1. when
actual_ctags = list(self.storage.content_ctags_search('hello',
limit=1))
# 1. then
self.assertEqual(actual_ctags, [
{
'id': ctag1['id'],
- 'tool_name': 'universal-ctags',
- 'tool_version': '~git7859817b',
+ 'tool': {
+ 'name': 'universal-ctags',
+ 'version': '~git7859817b',
+ },
'name': 'hello',
'kind': 'function',
'line': 133,
'lang': 'Python',
}
])
# 2. when
actual_ctags = list(self.storage.content_ctags_search(
'hello',
limit=1,
last_sha1=ctag1['id']))
# 2. then
self.assertEqual(actual_ctags, [
{
'id': ctag2['id'],
- 'tool_name': 'universal-ctags',
- 'tool_version': '~git7859817b',
+ 'tool': {
+ 'name': 'universal-ctags',
+ 'version': '~git7859817b',
+ },
'name': 'hello',
'kind': 'variable',
'line': 100,
'lang': 'C',
}
])
# 3. when
actual_ctags = list(self.storage.content_ctags_search('hello'))
# 3. then
self.assertEqual(actual_ctags, [
{
'id': ctag1['id'],
- 'tool_name': 'universal-ctags',
- 'tool_version': '~git7859817b',
+ 'tool': {
+ 'name': 'universal-ctags',
+ 'version': '~git7859817b',
+ },
'name': 'hello',
'kind': 'function',
'line': 133,
'lang': 'Python',
},
{
'id': ctag2['id'],
- 'tool_name': 'universal-ctags',
- 'tool_version': '~git7859817b',
+ 'tool': {
+ 'name': 'universal-ctags',
+ 'version': '~git7859817b',
+ },
'name': 'hello',
'kind': 'variable',
'line': 100,
'lang': 'C',
},
])
# 4. when
actual_ctags = list(self.storage.content_ctags_search('counter'))
# then
self.assertEqual(actual_ctags, [{
'id': ctag1['id'],
- 'tool_name': 'universal-ctags',
- 'tool_version': '~git7859817b',
+ 'tool': {
+ 'name': 'universal-ctags',
+ 'version': '~git7859817b',
+ },
'name': 'counter',
'kind': 'variable',
'line': 119,
'lang': 'Python',
}])
- @attr('one')
@istest
def content_ctags_search_no_result(self):
actual_ctags = list(self.storage.content_ctags_search('counter'))
self.assertEquals(actual_ctags, [])
@istest
def content_ctags_add__add_new_ctags_added(self):
# given
cont2 = self.cont2
self.storage.content_add([cont2])
ctag_v1 = {
'id': self.cont2['sha1'],
'tool_name': 'universal-ctags',
'tool_version': '~git7859817b',
'ctags': [{
'name': 'done',
'kind': 'variable',
'line': 100,
'lang': 'Scheme',
}]
}
# given
self.storage.content_ctags_add([ctag_v1])
self.storage.content_ctags_add([ctag_v1]) # conflict does nothing
# when
actual_ctags = list(self.storage.content_ctags_get(
[self.cont2['sha1']]))
# then
expected_ctags = [{
'id': self.cont2['sha1'],
- 'tool_name': 'universal-ctags',
- 'tool_version': '~git7859817b',
'name': 'done',
'kind': 'variable',
'line': 100,
'lang': 'Scheme',
+ 'tool': {
+ 'name': 'universal-ctags',
+ 'version': '~git7859817b',
+ }
}]
self.assertEqual(actual_ctags, expected_ctags)
# given
ctag_v2 = ctag_v1.copy()
ctag_v2.update({
'ctags': [
{
'name': 'defn',
'kind': 'function',
'line': 120,
'lang': 'Scheme',
}
]
})
self.storage.content_ctags_add([ctag_v2])
expected_ctags = [
{
'id': self.cont2['sha1'],
- 'tool_name': 'universal-ctags',
- 'tool_version': '~git7859817b',
'name': 'done',
'kind': 'variable',
'line': 100,
'lang': 'Scheme',
+ 'tool': {
+ 'name': 'universal-ctags',
+ 'version': '~git7859817b',
+ },
}, {
'id': self.cont2['sha1'],
- 'tool_name': 'universal-ctags',
- 'tool_version': '~git7859817b',
'name': 'defn',
'kind': 'function',
'line': 120,
'lang': 'Scheme',
+ 'tool': {
+ 'name': 'universal-ctags',
+ 'version': '~git7859817b',
+ },
}
]
actual_ctags = list(self.storage.content_ctags_get(
[self.cont2['sha1']]))
self.assertEqual(actual_ctags, expected_ctags)
@istest
def content_ctags_add__update_in_place(self):
# given
cont2 = self.cont2
self.storage.content_add([cont2])
ctag_v1 = {
'id': self.cont2['sha1'],
'tool_name': 'universal-ctags',
'tool_version': '~git7859817b',
'ctags': [{
'name': 'done',
'kind': 'variable',
'line': 100,
'lang': 'Scheme',
}]
}
# given
self.storage.content_ctags_add([ctag_v1])
# when
actual_ctags = list(self.storage.content_ctags_get(
[self.cont2['sha1']]))
# then
expected_ctags = [
{
'id': self.cont2['sha1'],
- 'tool_name': 'universal-ctags',
- 'tool_version': '~git7859817b',
'name': 'done',
'kind': 'variable',
'line': 100,
'lang': 'Scheme',
+ 'tool': {
+ 'name': 'universal-ctags',
+ 'version': '~git7859817b',
+ }
}
]
self.assertEqual(actual_ctags, expected_ctags)
# given
ctag_v2 = ctag_v1.copy()
ctag_v2.update({
'ctags': [
{
'name': 'done',
'kind': 'variable',
'line': 100,
'lang': 'Scheme',
},
{
'name': 'defn',
'kind': 'function',
'line': 120,
'lang': 'Scheme',
}
]
})
self.storage.content_ctags_add([ctag_v2], conflict_update=True)
actual_ctags = list(self.storage.content_ctags_get(
[self.cont2['sha1']]))
# ctag did change as the v2 was used to overwrite v1
expected_ctags = [
{
'id': self.cont2['sha1'],
- 'tool_name': 'universal-ctags',
- 'tool_version': '~git7859817b',
'name': 'done',
'kind': 'variable',
'line': 100,
'lang': 'Scheme',
+ 'tool': {
+ 'name': 'universal-ctags',
+ 'version': '~git7859817b',
+ },
},
{
'id': self.cont2['sha1'],
- 'tool_name': 'universal-ctags',
- 'tool_version': '~git7859817b',
'name': 'defn',
'kind': 'function',
'line': 120,
'lang': 'Scheme',
+ 'tool': {
+ 'name': 'universal-ctags',
+ 'version': '~git7859817b',
+ },
}
]
self.assertEqual(actual_ctags, expected_ctags)
@istest
def content_fossology_license_missing(self):
# given
cont = self.cont
self.storage.content_add([cont])
licenses = [cont['sha1'], self.missing_cont['sha1']]
# when
actual_missing = list(self.storage.content_fossology_license_missing(
licenses))
# then
self.assertEqual(actual_missing, [
cont['sha1'],
self.missing_cont['sha1']
])
# given
r = self.storage.content_fossology_license_add([{
'id': cont['sha1'],
'licenses': ['GPL-2.0', 'GPL-2.0+'],
'tool_name': 'nomos',
'tool_version': '3.1.0rc2-31-ga2cbb8c',
}])
self.assertEqual(r, [])
# when
actual_missing = list(self.storage.content_fossology_license_missing(
licenses))
# then
self.assertEqual(actual_missing, [self.missing_cont['sha1']])
@istest
def content_fossology_license_get(self):
# given
cont = self.cont
self.storage.content_add([cont])
licenses = [cont['sha1'], self.missing_cont['sha1']]
license1 = {
'id': cont['sha1'],
'licenses': ['GPL-2.0+'],
'tool_name': 'nomos',
'tool_version': '3.1.0rc2-31-ga2cbb8c',
}
# when
r = self.storage.content_fossology_license_add([license1])
self.assertEquals(r, [])
# then
actual_licenses = list(self.storage.content_fossology_license_get(
licenses))
# then
self.assertEqual(actual_licenses, [license1])
@istest
def content_fossology_license_add__wrong_license(self):
# given
cont = self.cont
self.storage.content_add([cont])
license_v1 = {
'id': cont['sha1'],
'licenses': ['blackhole'],
'tool_name': 'nomos',
'tool_version': '3.1.0rc2-31-ga2cbb8c',
}
# given
r = self.storage.content_fossology_license_add([license_v1])
# then
self.assertEqual(r, [license_v1])
# when
actual_licenses = list(self.storage.content_fossology_license_get(
[cont['sha1']]))
# then
self.assertEqual(actual_licenses, [])
@istest
def content_fossology_license_add__new_license_added(self):
# given
cont = self.cont
self.storage.content_add([cont])
license_v1 = {
'id': cont['sha1'],
'licenses': ['Apache-2.0'],
'tool_name': 'nomos',
'tool_version': '3.1.0rc2-31-ga2cbb8c',
}
# given
self.storage.content_fossology_license_add([license_v1])
# conflict does nothing
self.storage.content_fossology_license_add([license_v1])
# when
actual_licenses = list(self.storage.content_fossology_license_get(
[cont['sha1']]))
# then
self.assertEqual(actual_licenses[0], license_v1)
# given
license_v2 = license_v1.copy()
license_v2.update({
'licenses': ['BSD-2-Clause'],
})
self.storage.content_fossology_license_add([license_v2])
actual_licenses = list(self.storage.content_fossology_license_get(
[cont['sha1']]))
expected_license = license_v1.copy()
expected_license.update({
'licenses': ['Apache-2.0', 'BSD-2-Clause'],
})
# license did not change as the v2 was dropped.
self.assertEqual(actual_licenses[0], expected_license)
@istest
def content_fossology_license_add__update_in_place_duplicate(self):
# given
cont = self.cont
self.storage.content_add([cont])
license_v1 = {
'id': cont['sha1'],
'licenses': ['CECILL'],
'tool_name': 'nomos',
'tool_version': '3.1.0rc2-31-ga2cbb8c',
}
# given
self.storage.content_fossology_license_add([license_v1])
# conflict does nothing
self.storage.content_fossology_license_add([license_v1])
# when
actual_licenses = list(self.storage.content_fossology_license_get(
[cont['sha1']]))
# then
self.assertEqual(actual_licenses[0], license_v1)
# given
license_v2 = license_v1.copy()
license_v2.update({
'licenses': ['CECILL-2.0']
})
self.storage.content_fossology_license_add([license_v2],
conflict_update=True)
actual_licenses = list(self.storage.content_fossology_license_get(
[cont['sha1']]))
# license did change as the v2 was used to overwrite v1
self.assertEqual(actual_licenses[0], license_v2)
class TestStorage(AbstractTestStorage, unittest.TestCase):
"""Test the local storage"""
# Can only be tested with local storage as you can't mock
# datetimes for the remote server
@istest
def fetch_history(self):
origin = self.storage.origin_add_one(self.origin)
with patch('datetime.datetime'):
datetime.datetime.now.return_value = self.fetch_history_date
fetch_history_id = self.storage.fetch_history_start(origin)
datetime.datetime.now.assert_called_with(tz=datetime.timezone.utc)
with patch('datetime.datetime'):
datetime.datetime.now.return_value = self.fetch_history_end
self.storage.fetch_history_end(fetch_history_id,
self.fetch_history_data)
fetch_history = self.storage.fetch_history_get(fetch_history_id)
expected_fetch_history = self.fetch_history_data.copy()
expected_fetch_history['id'] = fetch_history_id
expected_fetch_history['origin'] = origin
expected_fetch_history['date'] = self.fetch_history_date
expected_fetch_history['duration'] = self.fetch_history_duration
self.assertEqual(expected_fetch_history, fetch_history)
@istest
def person_get(self):
# given
person0 = {
'fullname': b'bob <alice@bob>',
'name': b'bob',
'email': b'alice@bob',
}
id0 = self.storage._person_add(person0)
person1 = {
'fullname': b'tony <tony@bob>',
'name': b'tony',
'email': b'tony@bob',
}
id1 = self.storage._person_add(person1)
# when
actual_persons = self.storage.person_get([id0, id1])
# given (person injection through release for example)
self.assertEqual(
list(actual_persons), [
{
'id': id0,
'fullname': person0['fullname'],
'name': person0['name'],
'email': person0['email'],
},
{
'id': id1,
'fullname': person1['fullname'],
'name': person1['name'],
'email': person1['email'],
},
])