swh.storage.in_memory module

class swh.storage.in_memory.Table(row_class: Type[swh.storage.in_memory.TRow])

Bases: Generic[swh.storage.in_memory.TRow]

partition_key(row: Union[swh.storage.in_memory.TRow, Dict[str, Any]]) → Tuple

Returns the partition key of a row (ie. the cells which get hashed into the token.

clustering_key(row: Union[swh.storage.in_memory.TRow, Dict[str, Any]]) → Tuple

Returns the clustering key of a row (ie. the cells which are used for sorting rows within a partition.

primary_key(row)

primary_key_from_dict(d: Dict[str, Any]) → Tuple

Returns the primary key (ie. concatenation of partition key and clustering key) of the given dictionary interpreted as a row.

token(key: Tuple)

Returns the token of a row (ie. the hash of its partition key).

get_partition(token: int) → Dict[Tuple, swh.storage.in_memory.TRow]

Returns the partition that contains this token.

insert(row: swh.storage.in_memory.TRow)

split_primary_key(key: Tuple) → Tuple[Tuple, Tuple]

Returns (partition_key, clustering_key) from a partition key

get_from_partition_key(partition_key: Tuple) → Iterable[swh.storage.in_memory.TRow]

Returns at most one row, from its partition key.

get_from_primary_key(primary_key: Tuple) → Optional[swh.storage.in_memory.TRow]

Returns at most one row, from its primary key.

get_from_token(token: int) → Iterable[swh.storage.in_memory.TRow]

Returns all rows whose token (ie. non-cryptographic hash of the partition key) is the one passed as argument.

iter_all() → Iterator[Tuple[Tuple, swh.storage.in_memory.TRow]]

get_random() → Optional[swh.storage.in_memory.TRow]

class swh.storage.in_memory.InMemoryCqlRunner

Bases: object

increment_counter(object_type: str, nb: int)

stat_counters() → Iterable[swh.storage.cassandra.model.ObjectCountRow]

content_add_prepare(content: swh.storage.cassandra.model.ContentRow)

content_get_from_pk(content_hashes: Dict[str, bytes]) → Optional[swh.storage.cassandra.model.ContentRow]

content_get_from_tokens(tokens: List[int]) → Iterable[swh.storage.cassandra.model.ContentRow]

content_get_random() → Optional[swh.storage.cassandra.model.ContentRow]

content_get_token_range(start: int, end: int, limit: int) → Iterable[Tuple[int, swh.storage.cassandra.model.ContentRow]]

content_missing_from_hashes(contents_hashes: List[Dict[str, bytes]]) → Iterator[Dict[str, bytes]]

content_missing_by_sha1_git(ids: List[bytes]) → List[bytes]

content_index_add_one(algo: str, content: swh.model.model.Content, token: int) → None

content_get_tokens_from_single_algo(algo: str, hashes: List[bytes]) → Iterable[int]

skipped_content_add_prepare(content: swh.storage.cassandra.model.SkippedContentRow)

skipped_content_get_from_pk(content_hashes: Dict[str, bytes]) → Optional[swh.storage.cassandra.model.SkippedContentRow]

skipped_content_get_from_token(token: int) → Iterable[swh.storage.cassandra.model.SkippedContentRow]

skipped_content_index_add_one(algo: str, content: swh.model.model.SkippedContent, token: int) → None

skipped_content_get_tokens_from_single_hash(algo: str, hash_: bytes) → Iterable[int]

directory_missing(ids: List[bytes]) → List[bytes]

directory_add_one(directory: swh.storage.cassandra.model.DirectoryRow) → None

directory_get_random() → Optional[swh.storage.cassandra.model.DirectoryRow]

directory_entry_add_one(entry: swh.storage.cassandra.model.DirectoryEntryRow) → None

directory_entry_get(directory_ids: List[bytes]) → Iterable[swh.storage.cassandra.model.DirectoryEntryRow]

directory_entry_get_from_name(directory_id: bytes, from_: bytes, limit: int) → Iterable[swh.storage.cassandra.model.DirectoryEntryRow]

revision_missing(ids: List[bytes]) → Iterable[bytes]

revision_add_one(revision: swh.storage.cassandra.model.RevisionRow) → None

revision_get_ids(revision_ids) → Iterable[int]

revision_get(revision_ids: List[bytes]) → Iterable[swh.storage.cassandra.model.RevisionRow]

revision_get_random() → Optional[swh.storage.cassandra.model.RevisionRow]

revision_parent_add_one(revision_parent: swh.storage.cassandra.model.RevisionParentRow) → None

revision_parent_get(revision_id: bytes) → Iterable[bytes]

release_missing(ids: List[bytes]) → List[bytes]

release_add_one(release: swh.storage.cassandra.model.ReleaseRow) → None

release_get(release_ids: List[str]) → Iterable[swh.storage.cassandra.model.ReleaseRow]

release_get_random() → Optional[swh.storage.cassandra.model.ReleaseRow]

snapshot_missing(ids: List[bytes]) → List[bytes]

snapshot_add_one(snapshot: swh.storage.cassandra.model.SnapshotRow) → None

snapshot_get_random() → Optional[swh.storage.cassandra.model.SnapshotRow]

snapshot_branch_add_one(branch: swh.storage.cassandra.model.SnapshotBranchRow) → None

snapshot_count_branches(snapshot_id: bytes, branch_name_exclude_prefix: Optional[bytes] = None) → Dict[Optional[str], int]

Returns a dictionary from type names to the number of branches of that type.

snapshot_branch_get(snapshot_id: bytes, from_: bytes, limit: int, branch_name_exclude_prefix: Optional[bytes] = None) → Iterable[swh.storage.cassandra.model.SnapshotBranchRow]

origin_add_one(origin: swh.storage.cassandra.model.OriginRow) → None

origin_get_by_sha1(sha1: bytes) → Iterable[swh.storage.cassandra.model.OriginRow]

origin_get_by_url(url: str) → Iterable[swh.storage.cassandra.model.OriginRow]

origin_list(start_token: int, limit: int) → Iterable[Tuple[int, swh.storage.cassandra.model.OriginRow]]

Returns an iterable of (token, origin)

origin_iter_all() → Iterable[swh.storage.cassandra.model.OriginRow]

origin_bump_next_visit_id(origin_url: str, visit_id: int) → None

origin_generate_unique_visit_id(origin_url: str) → int

origin_visit_get(origin_url: str, last_visit: Optional[int], limit: int, order: swh.storage.interface.ListOrder) → Iterable[swh.storage.cassandra.model.OriginVisitRow]

origin_visit_add_one(visit: swh.storage.cassandra.model.OriginVisitRow) → None

origin_visit_get_one(origin_url: str, visit_id: int) → Optional[swh.storage.cassandra.model.OriginVisitRow]

origin_visit_get_all(origin_url: str) → Iterable[swh.storage.cassandra.model.OriginVisitRow]

origin_visit_iter(start_token: int) → Iterator[swh.storage.cassandra.model.OriginVisitRow]

Returns all origin visits in order from this token, and wraps around the token space.

origin_visit_status_get_range(origin: str, visit: int, date_from: Optional[datetime.datetime], limit: int, order: swh.storage.interface.ListOrder) → Iterable[swh.storage.cassandra.model.OriginVisitStatusRow]

origin_visit_status_add_one(visit_update: swh.storage.cassandra.model.OriginVisitStatusRow) → None

origin_visit_status_get_latest(origin: str, visit: int) → Optional[swh.storage.cassandra.model.OriginVisitStatusRow]

Given an origin visit id, return its latest origin_visit_status

origin_visit_status_get(origin: str, visit: int) → Iterator[swh.storage.cassandra.model.OriginVisitStatusRow]

Return all origin visit statuses for a given visit

origin_snapshot_get_all(origin: str) → Iterator[bytes]

Return all snapshots for a given origin

metadata_authority_add(authority: swh.storage.cassandra.model.MetadataAuthorityRow)

metadata_authority_get(type, url) → Optional[swh.storage.cassandra.model.MetadataAuthorityRow]

metadata_fetcher_add(fetcher: swh.storage.cassandra.model.MetadataFetcherRow)

metadata_fetcher_get(name, version) → Optional[swh.storage.cassandra.model.MetadataAuthorityRow]

raw_extrinsic_metadata_by_id_add(row: swh.storage.cassandra.model.RawExtrinsicMetadataByIdRow) → None

raw_extrinsic_metadata_get_by_ids(ids) → List[swh.storage.cassandra.model.RawExtrinsicMetadataByIdRow]

raw_extrinsic_metadata_add(raw_extrinsic_metadata)

raw_extrinsic_metadata_get_after_date(target: str, authority_type: str, authority_url: str, after: datetime.datetime) → Iterable[swh.storage.cassandra.model.RawExtrinsicMetadataRow]

raw_extrinsic_metadata_get_after_date_and_id(target: str, authority_type: str, authority_url: str, after_date: datetime.datetime, after_id: bytes) → Iterable[swh.storage.cassandra.model.RawExtrinsicMetadataRow]

raw_extrinsic_metadata_get(target: str, authority_type: str, authority_url: str) → Iterable[swh.storage.cassandra.model.RawExtrinsicMetadataRow]

raw_extrinsic_metadata_get_authorities(target: str) → Iterable[Tuple[str, str]]

extid_add_prepare(extid: swh.storage.cassandra.model.ExtIDRow)

extid_index_add_one(row: swh.storage.cassandra.model.ExtIDByTargetRow) → None

extid_get_from_pk(extid_type: str, extid: bytes, extid_version: int, target: swh.model.swhids.ExtendedSWHID) → Optional[swh.storage.cassandra.model.ExtIDRow]

extid_get_from_extid(extid_type: str, extid: bytes) → Iterable[swh.storage.cassandra.model.ExtIDRow]

extid_get_from_extid_and_version(extid_type: str, extid: bytes, extid_version: int) → Iterable[swh.storage.cassandra.model.ExtIDRow]

extid_get_from_target(target_type: str, target: bytes, extid_type: Optional[str] = None, extid_version: Optional[int] = None) → Iterable[swh.storage.cassandra.model.ExtIDRow]

class swh.storage.in_memory.InMemoryStorage(journal_writer=None)

Bases: swh.storage.cassandra.storage.CassandraStorage

A backend of swh-storage backed by Cassandra

Parameters

• hosts – Seed Cassandra nodes, to start connecting to the cluster

• keyspace – Name of the Cassandra database to use

• objstorage – Passed as argument to ObjStorage

• port – Cassandra port

• journal_writer – Passed as argument to JournalWriter

• allow_overwrite – Whether *_add functions will check if an object already exists in the database before sending it in an INSERT. False is the default as it is more efficient when there is a moderately high probability the object is already known, but True can be useful to overwrite existing objects (eg. when applying a schema update), or when the database is known to be mostly empty. Note that a False value does not guarantee there won’t be any overwrite.

• consistency_level – The default read/write consistency to use

• directory_entries_insert_algo – Must be one of: * one-by-one: naive, one INSERT per directory entry, serialized * concurrent: one INSERT per directory entry, concurrent * batch: using UNLOGGED BATCH to insert many entries in a few statements

reset()

check_config(*, check_write: bool) → bool