diff --git a/swh/web/api/views/origin.py b/swh/web/api/views/origin.py index a8610f11..cadef97b 100644 --- a/swh/web/api/views/origin.py +++ b/swh/web/api/views/origin.py @@ -1,500 +1,506 @@ # Copyright (C) 2015-2022 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU Affero General Public License version 3, or any later version # See top-level LICENSE file for more information from distutils.util import strtobool from functools import partial from typing import Dict from rest_framework.request import Request from swh.search.exc import SearchQuerySyntaxError from swh.web.api.apidoc import api_doc, format_docstring from swh.web.api.apiurls import api_route from swh.web.api.utils import ( enrich_origin, enrich_origin_search_result, enrich_origin_visit, ) from swh.web.api.views.utils import api_lookup from swh.web.common import archive from swh.web.common.exc import BadInputExc from swh.web.common.origin_visits import get_origin_visits +from swh.web.common.typing import OriginInfo from swh.web.common.utils import origin_visit_types, reverse DOC_RETURN_ORIGIN = """ :>json string origin_visits_url: link to in order to get information about the visits for that origin :>json string url: the origin canonical url """ DOC_RETURN_ORIGIN_ARRAY = DOC_RETURN_ORIGIN.replace(":>json", ":>jsonarr") DOC_RETURN_ORIGIN_VISIT = """ :>json string date: ISO8601/RFC3339 representation of the visit date (in UTC) :>json str origin: the origin canonical url :>json string origin_url: link to get information about the origin :>jsonarr string snapshot: the snapshot identifier of the visit (may be null if status is not **full**). :>jsonarr string snapshot_url: link to :http:get:`/api/1/snapshot/(snapshot_id)/` in order to get information about the snapshot of the visit (may be null if status is not **full**). :>json string status: status of the visit (either **full**, **partial** or **ongoing**) :>json number visit: the unique identifier of the visit """ DOC_RETURN_ORIGIN_VISIT_ARRAY = DOC_RETURN_ORIGIN_VISIT.replace(":>json", ":>jsonarr") DOC_RETURN_ORIGIN_VISIT_ARRAY += """ :>jsonarr number id: the unique identifier of the origin :>jsonarr string origin_visit_url: link to :http:get:`/api/1/origin/(origin_url)/visit/(visit_id)/` in order to get information about the visit """ @api_route(r"/origins/", "api-1-origins") @api_doc("/origins/", noargs=True) @format_docstring(return_origin_array=DOC_RETURN_ORIGIN_ARRAY) def api_origins(request: Request): """ .. http:get:: /api/1/origins/ Get list of archived software origins. .. warning:: This endpoint used to provide an ``origin_from`` query parameter, and guarantee an order on results. This is no longer true, and only the Link header should be used for paginating through results. :query int origin_count: The maximum number of origins to return (default to 100, can not exceed 10000) {return_origin_array} {common_headers} {resheader_link} :statuscode 200: no error **Example:** .. parsed-literal:: :swh_web_api:`origins?origin_count=500` """ old_param_origin_from = request.query_params.get("origin_from") if old_param_origin_from: raise BadInputExc("Please use the Link header to browse through result") page_token = request.query_params.get("page_token", None) limit = min(int(request.query_params.get("origin_count", "100")), 10000) page_result = archive.lookup_origins(page_token, limit) origins = [enrich_origin(o, request=request) for o in page_result.results] next_page_token = page_result.next_page_token headers: Dict[str, str] = {} if next_page_token is not None: headers["link-next"] = reverse( "api-1-origins", query_params={"page_token": next_page_token, "origin_count": str(limit)}, request=request, ) return {"results": origins, "headers": headers} @api_route(r"/origin/(?P.+)/get/", "api-1-origin") @api_doc("/origin/") @format_docstring(return_origin=DOC_RETURN_ORIGIN) def api_origin(request: Request, origin_url: str): """ .. http:get:: /api/1/origin/(origin_url)/get/ Get information about a software origin. :param string origin_url: the origin url {return_origin} {common_headers} :statuscode 200: no error :statuscode 404: requested origin can not be found in the archive **Example:** .. parsed-literal:: :swh_web_api:`origin/https://github.com/python/cpython/get/` """ ori_dict = {"url": origin_url} error_msg = "Origin with url %s not found." % ori_dict["url"] return api_lookup( archive.lookup_origin, ori_dict, + lookup_similar_urls=False, notfound_msg=error_msg, enrich_fn=enrich_origin, request=request, ) def _visit_types() -> str: docstring = "" # available visit types are queried using swh-search so we do it in a try # block in case of failure (for instance in docker environment when # elasticsearch service is not available) try: visit_types = [f"**{visit_type}**" for visit_type in origin_visit_types()] docstring = ", ".join(visit_types[:-1]) + f", and {visit_types[-1]}" except Exception: docstring = "???" pass return docstring @api_route( r"/origin/search/(?P.*)/", "api-1-origin-search", throttle_scope="swh_api_origin_search", ) @api_doc("/origin/search/") @format_docstring( return_origin_array=DOC_RETURN_ORIGIN_ARRAY, visit_types=_visit_types() ) def api_origin_search(request: Request, url_pattern: str): """ .. http:get:: /api/1/origin/search/(url_pattern)/ Search for software origins whose urls contain a provided string pattern or match a provided regular expression. The search is performed in a case insensitive way. .. warning:: This endpoint used to provide an ``offset`` query parameter, and guarantee an order on results. This is no longer true, and only the Link header should be used for paginating through results. :param string url_pattern: a string pattern :query boolean use_ql: whether to use swh search query language or not :query int limit: the maximum number of found origins to return (bounded to 1000) :query boolean with_visit: if true, only return origins with at least one visit by Software heritage :query string visit_type: if provided, only return origins with that specific visit type (currently the supported types are {visit_types}) {return_origin_array} {common_headers} {resheader_link} :statuscode 200: no error **Example:** .. parsed-literal:: :swh_web_api:`origin/search/python/?limit=2` """ result = {} limit = min(int(request.query_params.get("limit", "70")), 1000) page_token = request.query_params.get("page_token") use_ql = request.query_params.get("use_ql", "false") with_visit = request.query_params.get("with_visit", "false") visit_type = request.query_params.get("visit_type") try: (results, page_token) = api_lookup( archive.search_origin, url_pattern, bool(strtobool(use_ql)), limit, bool(strtobool(with_visit)), [visit_type] if visit_type else None, page_token, enrich_fn=enrich_origin_search_result, request=request, ) except SearchQuerySyntaxError as e: raise BadInputExc(f"Syntax error in search query: {e.args[0]}") if page_token is not None: query_params = {k: v for (k, v) in request.GET.dict().items()} query_params["page_token"] = page_token result["headers"] = { "link-next": reverse( "api-1-origin-search", url_args={"url_pattern": url_pattern}, query_params=query_params, request=request, ) } result.update({"results": results}) return result @api_route(r"/origin/metadata-search/", "api-1-origin-metadata-search") @api_doc("/origin/metadata-search/", noargs=True) @format_docstring(return_origin_array=DOC_RETURN_ORIGIN_ARRAY) def api_origin_metadata_search(request: Request): """ .. http:get:: /api/1/origin/metadata-search/ Search for software origins whose metadata (expressed as a JSON-LD/CodeMeta dictionary) match the provided criteria. For now, only full-text search on this dictionary is supported. :query str fulltext: a string that will be matched against origin metadata; results are ranked and ordered starting with the best ones. :query int limit: the maximum number of found origins to return (bounded to 100) {return_origin_array} {common_headers} :statuscode 200: no error **Example:** .. parsed-literal:: :swh_web_api:`origin/metadata-search/?limit=2&fulltext=Jane%20Doe` """ fulltext = request.query_params.get("fulltext", None) limit = min(int(request.query_params.get("limit", "70")), 100) if not fulltext: content = '"fulltext" must be provided and non-empty.' raise BadInputExc(content) results = api_lookup( archive.search_origin_metadata, fulltext, limit, request=request ) return { "results": results, } @api_route(r"/origin/(?P.+)/visits/", "api-1-origin-visits") @api_doc("/origin/visits/") @format_docstring(return_origin_visit_array=DOC_RETURN_ORIGIN_VISIT_ARRAY) def api_origin_visits(request: Request, origin_url: str): """ .. http:get:: /api/1/origin/(origin_url)/visits/ Get information about all visits of a software origin. Visits are returned sorted in descending order according to their date. :param str origin_url: a software origin URL :query int per_page: specify the number of visits to list, for pagination purposes :query int last_visit: visit to start listing from, for pagination purposes {common_headers} {resheader_link} {return_origin_visit_array} :statuscode 200: no error :statuscode 404: requested origin can not be found in the archive **Example:** .. parsed-literal:: :swh_web_api:`origin/https://github.com/hylang/hy/visits/` """ result = {} - origin_query = {"url": origin_url} + origin_query = OriginInfo(url=origin_url) notfound_msg = "No origin {} found".format(origin_url) url_args_next = {"origin_url": origin_url} per_page = int(request.query_params.get("per_page", "10")) last_visit_str = request.query_params.get("last_visit") last_visit = int(last_visit_str) if last_visit_str else None def _lookup_origin_visits(origin_query, last_visit=last_visit, per_page=per_page): - all_visits = get_origin_visits(origin_query) + all_visits = get_origin_visits(origin_query, lookup_similar_urls=False) all_visits.reverse() visits = [] if not last_visit: visits = all_visits[:per_page] else: for i, v in enumerate(all_visits): if v["visit"] == last_visit: visits = all_visits[i + 1 : i + 1 + per_page] break for v in visits: yield v results = api_lookup( _lookup_origin_visits, origin_query, notfound_msg=notfound_msg, enrich_fn=partial( enrich_origin_visit, with_origin_link=False, with_origin_visit_link=True ), request=request, ) if results: nb_results = len(results) if nb_results == per_page: new_last_visit = results[-1]["visit"] query_params = {} query_params["last_visit"] = new_last_visit if request.query_params.get("per_page"): query_params["per_page"] = per_page result["headers"] = { "link-next": reverse( "api-1-origin-visits", url_args=url_args_next, query_params=query_params, request=request, ) } result.update({"results": results}) return result @api_route( r"/origin/(?P.+)/visit/latest/", "api-1-origin-visit-latest", throttle_scope="swh_api_origin_visit_latest", ) @api_doc("/origin/visit/latest/") @format_docstring(return_origin_visit=DOC_RETURN_ORIGIN_VISIT) def api_origin_visit_latest(request: Request, origin_url: str): """ .. http:get:: /api/1/origin/(origin_url)/visit/latest/ Get information about the latest visit of a software origin. :param str origin_url: a software origin URL :query boolean require_snapshot: if true, only return a visit with a snapshot {common_headers} {return_origin_visit} :statuscode 200: no error :statuscode 404: requested origin or visit can not be found in the archive **Example:** .. parsed-literal:: :swh_web_api:`origin/https://github.com/hylang/hy/visit/latest/` """ + require_snapshot = request.query_params.get("require_snapshot", "false") return api_lookup( archive.lookup_origin_visit_latest, origin_url, bool(strtobool(require_snapshot)), + lookup_similar_urls=False, notfound_msg=("No visit for origin {} found".format(origin_url)), enrich_fn=partial( enrich_origin_visit, with_origin_link=True, with_origin_visit_link=False ), request=request, ) @api_route( r"/origin/(?P.+)/visit/(?P[0-9]+)/", "api-1-origin-visit" ) @api_doc("/origin/visit/") @format_docstring(return_origin_visit=DOC_RETURN_ORIGIN_VISIT) def api_origin_visit(request: Request, visit_id: str, origin_url: str): """ .. http:get:: /api/1/origin/(origin_url)/visit/(visit_id)/ Get information about a specific visit of a software origin. :param str origin_url: a software origin URL :param int visit_id: a visit identifier {common_headers} {return_origin_visit} :statuscode 200: no error :statuscode 404: requested origin or visit can not be found in the archive **Example:** .. parsed-literal:: :swh_web_api:`origin/https://github.com/hylang/hy/visit/1/` """ + return api_lookup( archive.lookup_origin_visit, origin_url, int(visit_id), + lookup_similar_urls=False, notfound_msg=("No visit {} for origin {} found".format(visit_id, origin_url)), enrich_fn=partial( enrich_origin_visit, with_origin_link=True, with_origin_visit_link=False ), request=request, ) @api_route( r"/origin/(?P.+)/intrinsic-metadata/", "api-origin-intrinsic-metadata" ) @api_doc("/origin/intrinsic-metadata/") @format_docstring() def api_origin_intrinsic_metadata(request: Request, origin_url: str): """ .. http:get:: /api/1/origin/(origin_url)/intrinsic-metadata Get intrinsic metadata of a software origin (as a JSON-LD/CodeMeta dictionary). :param string origin_url: the origin url :>json string ???: intrinsic metadata field of the origin {common_headers} :statuscode 200: no error :statuscode 404: requested origin can not be found in the archive **Example:** .. parsed-literal:: :swh_web_api:`origin/https://github.com/python/cpython/intrinsic-metadata` """ return api_lookup( archive.lookup_origin_intrinsic_metadata, origin_url, notfound_msg=f"Origin with url {origin_url} not found", enrich_fn=enrich_origin, request=request, ) diff --git a/swh/web/common/archive.py b/swh/web/common/archive.py index 7aecf4d9..712480ce 100644 --- a/swh/web/common/archive.py +++ b/swh/web/common/archive.py @@ -1,1456 +1,1477 @@ # Copyright (C) 2015-2022 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU Affero 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 os import re from typing import Any, Dict, Iterable, Iterator, List, Optional, Set, Tuple, Union from urllib.parse import urlparse from swh.model import hashutil from swh.model.model import Revision from swh.model.swhids import CoreSWHID, ObjectType from swh.storage.algos import diff, revisions_walker from swh.storage.algos.origin import origin_get_latest_visit_status from swh.storage.algos.snapshot import snapshot_get_latest, snapshot_resolve_alias from swh.storage.interface import OriginVisitWithStatuses from swh.vault.exc import NotFoundExc as VaultNotFoundExc from swh.web import config from swh.web.common import converters, query from swh.web.common.exc import NotFoundExc from swh.web.common.typing import ( OriginInfo, OriginMetadataInfo, OriginVisitInfo, PagedResult, ) search = config.search() storage = config.storage() vault = config.vault() idx_storage = config.indexer_storage() counters = config.counters() MAX_LIMIT = 1000 # Top limit the users can ask for def _first_element(lst): """Returns the first element in the provided list or None if it is empty or None""" return next(iter(lst or []), None) def lookup_multiple_hashes(hashes): """Lookup the passed hashes in a single DB connection, using batch processing. Args: An array of {filename: X, sha1: Y}, string X, hex sha1 string Y. Returns: The same array with elements updated with elem['found'] = true if the hash is present in storage, elem['found'] = false if not. """ hashlist = [hashutil.hash_to_bytes(elem["sha1"]) for elem in hashes] content_missing = storage.content_missing_per_sha1(hashlist) missing = [hashutil.hash_to_hex(x) for x in content_missing] for x in hashes: x.update({"found": True}) for h in hashes: if h["sha1"] in missing: h["found"] = False return hashes def lookup_expression(expression, last_sha1, per_page): """Lookup expression in raw content. Args: expression (str): An expression to lookup through raw indexed content last_sha1 (str): Last sha1 seen per_page (int): Number of results per page Yields: ctags whose content match the expression """ limit = min(per_page, MAX_LIMIT) ctags = idx_storage.content_ctags_search( expression, last_sha1=last_sha1, limit=limit ) for ctag in ctags: ctag = converters.from_swh(ctag, hashess={"id"}) ctag["sha1"] = ctag["id"] ctag.pop("id") yield ctag def lookup_hash(q: str) -> Dict[str, Any]: """Check if the storage contains a given content checksum and return it if found. Args: q: query string of the form Returns: Dict with key found containing the hash info if the hash is present, None if not. """ algo, hash_ = query.parse_hash(q) found = _first_element(storage.content_find({algo: hash_})) if found: content = converters.from_content(found.to_dict()) else: content = None return {"found": content, "algo": algo} def search_hash(q: str) -> Dict[str, bool]: """Search storage for a given content checksum. Args: q: query string of the form Returns: Dict with key found to True or False, according to whether the checksum is present or not """ algo, hash_ = query.parse_hash(q) found = _first_element(storage.content_find({algo: hash_})) return {"found": found is not None} def _lookup_content_sha1(q: str) -> Optional[bytes]: """Given a possible input, query for the content's sha1. Args: q: query string of the form Returns: binary sha1 if found or None """ algo, hash_ = query.parse_hash(q) if algo != "sha1": hashes = _first_element(storage.content_find({algo: hash_})) if not hashes: return None return hashes.sha1 return hash_ def lookup_content_ctags(q): """Return ctags information from a specified content. Args: q: query string of the form Yields: ctags information (dict) list if the content is found. """ sha1 = _lookup_content_sha1(q) if not sha1: return None ctags = list(idx_storage.content_ctags_get([sha1])) if not ctags: return None for ctag in ctags: yield converters.from_swh(ctag, hashess={"id"}) def lookup_content_filetype(q): """Return filetype information from a specified content. Args: q: query string of the form Yields: filetype information (dict) list if the content is found. """ sha1 = _lookup_content_sha1(q) if not sha1: return None filetype = _first_element(list(idx_storage.content_mimetype_get([sha1]))) if not filetype: return None return converters.from_filetype(filetype.to_dict()) def lookup_content_language(q): """Always returns None. This used to return language information from a specified content, but this is currently disabled. Args: q: query string of the form Yields: language information (dict) list if the content is found. """ return None def lookup_content_license(q): """Return license information from a specified content. Args: q: query string of the form Yields: license information (dict) list if the content is found. """ sha1 = _lookup_content_sha1(q) if not sha1: return None licenses = list(idx_storage.content_fossology_license_get([sha1])) if not licenses: return None license_dicts = [license.to_dict() for license in licenses] for license_dict in license_dicts: del license_dict["id"] lic = { "id": sha1, "facts": license_dicts, } return converters.from_swh(lic, hashess={"id"}) -def lookup_origin(origin: OriginInfo) -> OriginInfo: +def lookup_origin(origin: OriginInfo, lookup_similar_urls: bool = True) -> OriginInfo: """Return information about the origin matching dict origin. Args: origin: origin's dict with 'url' key + lookup_similar_urls: if :const:`True`, lookup origin with and + without trailing slash in its URL Returns: origin information as dict. """ origin_urls = [origin["url"]] - if origin["url"]: + if origin["url"] and lookup_similar_urls: # handle case when user provided an origin url with a trailing # slash while the url in storage does not have it (e.g. GitHub) if origin["url"].endswith("/"): origin_urls.append(origin["url"][:-1]) # handle case when user provided an origin url without a trailing # slash while the url in storage have it (e.g. Debian source package) else: origin_urls.append(f"{origin['url']}/") try: # handle case where the "://" character sequence was mangled into ":/" parsed_url = urlparse(origin["url"]) if ( parsed_url.scheme and not parsed_url.netloc and origin["url"].startswith(f"{parsed_url.scheme}:/") and not origin["url"].startswith(f"{parsed_url.scheme}://") ): origin_urls.append( origin["url"].replace( f"{parsed_url.scheme}:/", f"{parsed_url.scheme}://" ) ) except Exception: pass origins = [o for o in storage.origin_get(origin_urls) if o is not None] if not origins: msg = "Origin with url %s not found!" % origin["url"] raise NotFoundExc(msg) return converters.from_origin(origins[0].to_dict()) def lookup_origins( page_token: Optional[str], limit: int = 100 ) -> PagedResult[OriginInfo]: """Get list of archived software origins in a paginated way. Origins are sorted by id before returning them Args: origin_from (int): The minimum id of the origins to return origin_count (int): The maximum number of origins to return Returns: Page of OriginInfo """ page = storage.origin_list(page_token=page_token, limit=limit) return PagedResult( [converters.from_origin(o.to_dict()) for o in page.results], next_page_token=page.next_page_token, ) def lookup_origin_snapshots(origin: OriginInfo) -> List[str]: """Return ids of the snapshots of an origin. Args: origin: origin's dict with 'url' key Returns: List of unique snapshot identifiers in hexadecimal format resulting from the visits of the origin. """ return [ snapshot.hex() for snapshot in storage.origin_snapshot_get_all(origin["url"]) ] def search_origin( url_pattern: str, use_ql: bool = False, limit: int = 50, with_visit: bool = False, visit_types: Optional[List[str]] = None, page_token: Optional[str] = None, ) -> Tuple[List[OriginInfo], Optional[str]]: """Search for origins whose urls contain a provided string pattern or match a provided regular expression. Args: url_pattern: the string pattern to search for in origin urls use_ql: whether to use swh search query language or not limit: the maximum number of found origins to return with_visit: Whether origins with no visit are to be filtered out visit_types: Only origins having any of the provided visit types (e.g. git, svn, pypi) will be returned page_token: opaque string used to get the next results of a search Returns: list of origin information as dict. """ if page_token: assert isinstance(page_token, str) if search: if use_ql: page_result = search.origin_search( query=url_pattern, page_token=page_token, with_visit=with_visit, visit_types=visit_types, limit=limit, ) else: page_result = search.origin_search( url_pattern=url_pattern, page_token=page_token, with_visit=with_visit, visit_types=visit_types, limit=limit, ) origins = [converters.from_origin(ori_dict) for ori_dict in page_result.results] else: # Fallback to swh-storage if swh-search is not configured search_words = [re.escape(word) for word in url_pattern.split()] if len(search_words) >= 7: url_pattern = ".*".join(search_words) else: pattern_parts = [] for permut in itertools.permutations(search_words): pattern_parts.append(".*".join(permut)) url_pattern = "|".join(pattern_parts) page_result = storage.origin_search( url_pattern, page_token=page_token, with_visit=with_visit, limit=limit, visit_types=visit_types, regexp=True, ) origins = [converters.from_origin(ori.to_dict()) for ori in page_result.results] return (origins, page_result.next_page_token) def search_origin_metadata( fulltext: str, limit: int = 50 ) -> Iterable[OriginMetadataInfo]: """Search for origins whose metadata match a provided string pattern. Args: fulltext: the string pattern to search for in origin metadata limit: the maximum number of found origins to return Returns: Iterable of origin metadata information for existing origins """ results = [] if ( search and config.get_config()["search_config"]["metadata_backend"] == "swh-search" ): page_result = search.origin_search( metadata_pattern=fulltext, limit=limit, ) matches = idx_storage.origin_intrinsic_metadata_get( [r["url"] for r in page_result.results] ) else: matches = idx_storage.origin_intrinsic_metadata_search_fulltext( conjunction=[fulltext], limit=limit ) matches = [match.to_dict() for match in matches] origins = storage.origin_get([match["id"] for match in matches]) for origin, match in zip(origins, matches): if not origin: continue for field in ("from_directory", "from_revision"): # from_directory when using swh.indexer >= 2.0.0, from_revision otherwise if field in match: match[field] = hashutil.hash_to_hex(match[field]) del match["id"] results.append(OriginMetadataInfo(url=origin.url, metadata=match)) return results def lookup_origin_intrinsic_metadata(origin_url: str) -> Dict[str, Any]: """Return intrinsic metadata for origin whose origin matches given origin. Args: origin_url: origin url Raises: NotFoundExc when the origin is not found Returns: origin metadata. """ origins = [origin_url] origin_info = storage.origin_get(origins)[0] if not origin_info: raise NotFoundExc(f"Origin with url {origin_url} not found!") match = _first_element(idx_storage.origin_intrinsic_metadata_get(origins)) result = {} if match: result = match.metadata return result def _to_sha1_bin(sha1_hex): _, sha1_git_bin = query.parse_hash_with_algorithms_or_throws( sha1_hex, ["sha1"], "Only sha1_git is supported." # HACK: sha1_git really ) return sha1_git_bin def _check_directory_exists(sha1_git, sha1_git_bin): if len(list(storage.directory_missing([sha1_git_bin]))): raise NotFoundExc("Directory with sha1_git %s not found" % sha1_git) def lookup_directory(sha1_git): """Return information about the directory with id sha1_git. Args: sha1_git as string Returns: directory information as dict. """ empty_dir_sha1 = "4b825dc642cb6eb9a060e54bf8d69288fbee4904" if sha1_git == empty_dir_sha1: return [] sha1_git_bin = _to_sha1_bin(sha1_git) _check_directory_exists(sha1_git, sha1_git_bin) directory_entries = storage.directory_ls(sha1_git_bin) return map(converters.from_directory_entry, directory_entries) def lookup_directory_with_path(sha1_git: str, path: str) -> Dict[str, Any]: """Return directory information for entry with specified path w.r.t. root directory pointed by sha1_git Args: sha1_git: sha1_git corresponding to the directory to which we append paths to (hopefully) find the entry path: the relative path to the entry starting from the root directory pointed by sha1_git Returns: Directory entry information as dict. Raises: NotFoundExc if the directory entry is not found """ sha1_git_bin = _to_sha1_bin(sha1_git) _check_directory_exists(sha1_git, sha1_git_bin) paths = path.strip(os.path.sep).split(os.path.sep) queried_dir = storage.directory_entry_get_by_path( sha1_git_bin, [p.encode("utf-8") for p in paths] ) if not queried_dir: raise NotFoundExc( f"Directory entry with path {path} from root directory {sha1_git} not found" ) return converters.from_directory_entry(queried_dir) def lookup_release(release_sha1_git: str) -> Dict[str, Any]: """Return information about the release with sha1 release_sha1_git. Args: release_sha1_git: The release's sha1 as hexadecimal Returns: Release information as dict. Raises: ValueError if the identifier provided is not of sha1 nature. """ sha1_git_bin = _to_sha1_bin(release_sha1_git) release = _first_element(storage.release_get([sha1_git_bin])) if not release: raise NotFoundExc(f"Release with sha1_git {release_sha1_git} not found.") return converters.from_release(release) def lookup_release_multiple(sha1_git_list) -> Iterator[Optional[Dict[str, Any]]]: """Return information about the releases identified with their sha1_git identifiers. Args: sha1_git_list: A list of release sha1_git identifiers Returns: Iterator of Release metadata information as dict. Raises: ValueError if the identifier provided is not of sha1 nature. """ sha1_bin_list = [_to_sha1_bin(sha1_git) for sha1_git in sha1_git_list] releases = storage.release_get(sha1_bin_list) for r in releases: if r is not None: yield converters.from_release(r) else: yield None def lookup_revision(rev_sha1_git) -> Dict[str, Any]: """Return information about the revision with sha1 revision_sha1_git. Args: revision_sha1_git: The revision's sha1 as hexadecimal Returns: Revision information as dict. Raises: ValueError if the identifier provided is not of sha1 nature. NotFoundExc if there is no revision with the provided sha1_git. """ sha1_git_bin = _to_sha1_bin(rev_sha1_git) revision = storage.revision_get([sha1_git_bin])[0] if not revision: raise NotFoundExc(f"Revision with sha1_git {rev_sha1_git} not found.") return converters.from_revision(revision) def lookup_revision_multiple(sha1_git_list) -> Iterator[Optional[Dict[str, Any]]]: """Return information about the revisions identified with their sha1_git identifiers. Args: sha1_git_list: A list of revision sha1_git identifiers Yields: revision information as dict if the revision exists, None otherwise. Raises: ValueError if the identifier provided is not of sha1 nature. """ sha1_bin_list = [_to_sha1_bin(sha1_git) for sha1_git in sha1_git_list] revisions = storage.revision_get(sha1_bin_list) for revision in revisions: if revision is not None: yield converters.from_revision(revision) else: yield None def lookup_revision_message(rev_sha1_git) -> Dict[str, bytes]: """Return the raw message of the revision with sha1 revision_sha1_git. Args: revision_sha1_git: The revision's sha1 as hexadecimal Returns: Decoded revision message as dict {'message': } Raises: ValueError if the identifier provided is not of sha1 nature. NotFoundExc if the revision is not found, or if it has no message """ sha1_git_bin = _to_sha1_bin(rev_sha1_git) revision = storage.revision_get([sha1_git_bin])[0] if not revision: raise NotFoundExc(f"Revision with sha1_git {rev_sha1_git} not found.") if not revision.message: raise NotFoundExc(f"No message for revision with sha1_git {rev_sha1_git}.") return {"message": revision.message} def _lookup_revision_id_by(origin, branch_name, timestamp): def _get_snapshot_branch(snapshot, branch_name): snapshot = lookup_snapshot( visit["snapshot"], branches_from=branch_name, branches_count=10, branch_name_exclude_prefix=None, ) branch = None if branch_name in snapshot["branches"]: branch = snapshot["branches"][branch_name] return branch if isinstance(origin, int): origin = {"id": origin} elif isinstance(origin, str): origin = {"url": origin} else: raise TypeError('"origin" must be an int or a string.') from swh.web.common.origin_visits import get_origin_visit visit = get_origin_visit(origin, visit_ts=timestamp) branch = _get_snapshot_branch(visit["snapshot"], branch_name) rev_id = None if branch and branch["target_type"] == "revision": rev_id = branch["target"] elif branch and branch["target_type"] == "alias": branch = _get_snapshot_branch(visit["snapshot"], branch["target"]) if branch and branch["target_type"] == "revision": rev_id = branch["target"] if not rev_id: raise NotFoundExc( "Revision for origin %s and branch %s not found." % (origin.get("url"), branch_name) ) return rev_id def lookup_revision_by(origin, branch_name="HEAD", timestamp=None): """Lookup revision by origin, snapshot branch name and visit timestamp. If branch_name is not provided, lookup using 'HEAD' as default. If timestamp is not provided, use the most recent. Args: origin (Union[int,str]): origin of the revision branch_name (str): snapshot branch name timestamp (str/int): origin visit time frame Returns: dict: The revision matching the criterions Raises: NotFoundExc if no revision corresponds to the criterion """ rev_id = _lookup_revision_id_by(origin, branch_name, timestamp) return lookup_revision(rev_id) def lookup_revision_log(rev_sha1_git, limit): """Lookup revision log by revision id. Args: rev_sha1_git (str): The revision's sha1 as hexadecimal limit (int): the maximum number of revisions returned Returns: list: Revision log as list of revision dicts Raises: ValueError: if the identifier provided is not of sha1 nature. swh.web.common.exc.NotFoundExc: if there is no revision with the provided sha1_git. """ lookup_revision(rev_sha1_git) sha1_git_bin = _to_sha1_bin(rev_sha1_git) revision_entries = storage.revision_log([sha1_git_bin], limit=limit) return map(converters.from_revision, revision_entries) def lookup_revision_log_by(origin, branch_name, timestamp, limit): """Lookup revision by origin, snapshot branch name and visit timestamp. Args: origin (Union[int,str]): origin of the revision branch_name (str): snapshot branch timestamp (str/int): origin visit time frame limit (int): the maximum number of revisions returned Returns: list: Revision log as list of revision dicts Raises: swh.web.common.exc.NotFoundExc: if no revision corresponds to the criterion """ rev_id = _lookup_revision_id_by(origin, branch_name, timestamp) return lookup_revision_log(rev_id, limit) def lookup_revision_with_context_by( origin, branch_name, timestamp, sha1_git, limit=100 ): """Return information about revision sha1_git, limited to the sub-graph of all transitive parents of sha1_git_root. sha1_git_root being resolved through the lookup of a revision by origin, branch_name and ts. In other words, sha1_git is an ancestor of sha1_git_root. Args: - origin: origin of the revision. - branch_name: revision's branch. - timestamp: revision's time frame. - sha1_git: one of sha1_git_root's ancestors. - limit: limit the lookup to 100 revisions back. Returns: Pair of (root_revision, revision). Information on sha1_git if it is an ancestor of sha1_git_root including children leading to sha1_git_root Raises: - BadInputExc in case of unknown algo_hash or bad hash. - NotFoundExc if either revision is not found or if sha1_git is not an ancestor of sha1_git_root. """ rev_root_id = _lookup_revision_id_by(origin, branch_name, timestamp) rev_root_id_bin = hashutil.hash_to_bytes(rev_root_id) rev_root = storage.revision_get([rev_root_id_bin])[0] return ( converters.from_revision(rev_root) if rev_root else None, lookup_revision_with_context(rev_root, sha1_git, limit), ) def lookup_revision_with_context( sha1_git_root: Union[str, Dict[str, Any], Revision], sha1_git: str, limit: int = 100 ) -> Dict[str, Any]: """Return information about revision sha1_git, limited to the sub-graph of all transitive parents of sha1_git_root. In other words, sha1_git is an ancestor of sha1_git_root. Args: sha1_git_root: latest revision. The type is either a sha1 (as an hex string) or a non converted dict. sha1_git: one of sha1_git_root's ancestors limit: limit the lookup to 100 revisions back Returns: Information on sha1_git if it is an ancestor of sha1_git_root including children leading to sha1_git_root Raises: BadInputExc in case of unknown algo_hash or bad hash NotFoundExc if either revision is not found or if sha1_git is not an ancestor of sha1_git_root """ sha1_git_bin = _to_sha1_bin(sha1_git) revision = storage.revision_get([sha1_git_bin])[0] if not revision: raise NotFoundExc(f"Revision {sha1_git} not found") if isinstance(sha1_git_root, str): sha1_git_root_bin = _to_sha1_bin(sha1_git_root) revision_root = storage.revision_get([sha1_git_root_bin])[0] if not revision_root: raise NotFoundExc(f"Revision root {sha1_git_root} not found") elif isinstance(sha1_git_root, Revision): sha1_git_root_bin = sha1_git_root.id else: sha1_git_root_bin = sha1_git_root["id"] revision_log = storage.revision_log([sha1_git_root_bin], limit=limit) parents: Dict[str, List[str]] = {} children = defaultdict(list) for rev in revision_log: rev_id = rev["id"] parents[rev_id] = [] for parent_id in rev["parents"]: parents[rev_id].append(parent_id) children[parent_id].append(rev_id) if revision.id not in parents: raise NotFoundExc(f"Revision {sha1_git} is not an ancestor of {sha1_git_root}") revision_d = revision.to_dict() revision_d["children"] = children[revision.id] return converters.from_revision(revision_d) def lookup_directory_with_revision(sha1_git, dir_path=None, with_data=False): """Return information on directory pointed by revision with sha1_git. If dir_path is not provided, display top level directory. Otherwise, display the directory pointed by dir_path (if it exists). Args: sha1_git: revision's hash. dir_path: optional directory pointed to by that revision. with_data: boolean that indicates to retrieve the raw data if the path resolves to a content. Default to False (for the api) Returns: Information on the directory pointed to by that revision. Raises: BadInputExc in case of unknown algo_hash or bad hash. NotFoundExc either if the revision is not found or the path referenced does not exist. NotImplementedError in case of dir_path exists but do not reference a type 'dir' or 'file'. """ sha1_git_bin = _to_sha1_bin(sha1_git) revision = storage.revision_get([sha1_git_bin])[0] if not revision: raise NotFoundExc(f"Revision {sha1_git} not found") dir_sha1_git_bin = revision.directory if dir_path: paths = dir_path.strip(os.path.sep).split(os.path.sep) entity = storage.directory_entry_get_by_path( dir_sha1_git_bin, list(map(lambda p: p.encode("utf-8"), paths)) ) if not entity: raise NotFoundExc( "Directory or File '%s' pointed to by revision %s not found" % (dir_path, sha1_git) ) else: entity = {"type": "dir", "target": dir_sha1_git_bin} if entity["type"] == "dir": directory_entries = storage.directory_ls(entity["target"]) or [] return { "type": "dir", "path": "." if not dir_path else dir_path, "revision": sha1_git, "content": list(map(converters.from_directory_entry, directory_entries)), } elif entity["type"] == "file": # content content = _first_element(storage.content_find({"sha1_git": entity["target"]})) if not content: raise NotFoundExc(f"Content not found for revision {sha1_git}") content_d = content.to_dict() if with_data: data = storage.content_get_data(content.sha1) if data: content_d["data"] = data return { "type": "file", "path": "." if not dir_path else dir_path, "revision": sha1_git, "content": converters.from_content(content_d), } elif entity["type"] == "rev": # revision revision = storage.revision_get([entity["target"]])[0] return { "type": "rev", "path": "." if not dir_path else dir_path, "revision": sha1_git, "content": converters.from_revision(revision) if revision else None, } else: raise NotImplementedError("Entity of type %s not implemented." % entity["type"]) def lookup_content(q: str) -> Dict[str, Any]: """Lookup the content designed by q. Args: q: The release's sha1 as hexadecimal Raises: NotFoundExc if the requested content is not found """ algo, hash_ = query.parse_hash(q) c = _first_element(storage.content_find({algo: hash_})) if not c: hhex = hashutil.hash_to_hex(hash_) raise NotFoundExc(f"Content with {algo} checksum equals to {hhex} not found!") return converters.from_content(c.to_dict()) def lookup_content_raw(q: str) -> Dict[str, Any]: """Lookup the content defined by q. Args: q: query string of the form Returns: dict with 'sha1' and 'data' keys. data representing its raw data decoded. Raises: NotFoundExc if the requested content is not found or if the content bytes are not available in the storage """ c = lookup_content(q) content_sha1_bytes = hashutil.hash_to_bytes(c["checksums"]["sha1"]) content_data = storage.content_get_data(content_sha1_bytes) if content_data is None: algo, hash_ = query.parse_hash(q) raise NotFoundExc( f"Bytes of content with {algo} checksum equals " f"to {hashutil.hash_to_hex(hash_)} are not available!" ) return converters.from_content({"sha1": content_sha1_bytes, "data": content_data}) def stat_counters(): """Return the stat counters for Software Heritage Returns: A dict mapping textual labels to integer values. """ res = {} if counters and config.get_config()["counters_backend"] == "swh-counters": res = counters.get_counts( ["origin", "revision", "content", "directory", "release", "person"] ) else: res = storage.stat_counters() return res def _lookup_origin_visits( origin_url: str, last_visit: Optional[int] = None, limit: int = 10 ) -> Iterator[OriginVisitWithStatuses]: """Yields the origin origins' visits. Args: - origin_url (str): origin to list visits for - last_visit (int): last visit to lookup from - limit (int): Number of elements max to display + origin_url: origin to list visits for + last_visit: last visit to lookup from + limit: Number of elements max to display Yields: OriginVisit for that origin """ limit = min(limit, MAX_LIMIT) page_token: Optional[str] if last_visit is not None: page_token = str(last_visit) else: page_token = None visit_page = storage.origin_visit_get_with_statuses( origin_url, page_token=page_token, limit=limit ) yield from visit_page.results def lookup_origin_visits( origin: str, last_visit: Optional[int] = None, per_page: int = 10 ) -> Iterator[OriginVisitInfo]: """Yields the origin origins' visits. Args: origin: origin to list visits for Yields: Dictionaries of origin_visit for that origin """ for visit in _lookup_origin_visits(origin, last_visit=last_visit, limit=per_page): yield converters.from_origin_visit(visit.statuses[-1].to_dict()) def lookup_origin_visit_latest( origin_url: str, require_snapshot: bool = False, type: Optional[str] = None, allowed_statuses: Optional[List[str]] = None, + lookup_similar_urls: bool = True, ) -> Optional[OriginVisitInfo]: """Return the origin's latest visit Args: origin_url: origin to list visits for type: Optional visit type to filter on (e.g git, tar, dsc, svn, hg, npm, pypi, ...) allowed_statuses: list of visit statuses considered to find the latest visit. For instance, ``allowed_statuses=['full']`` will only consider visits that have successfully run to completion. require_snapshot: filter out origins without a snapshot + lookup_similar_urls: if :const:`True`, lookup origin with and + without trailing slash in its URL Returns: The origin visit info as dict if found """ + # check origin existence in the archive + origin_url = lookup_origin( + OriginInfo(url=origin_url), lookup_similar_urls=lookup_similar_urls + )["url"] + visit_status = origin_get_latest_visit_status( storage, origin_url, type=type, allowed_statuses=allowed_statuses, require_snapshot=require_snapshot, ) return ( converters.from_origin_visit(visit_status.to_dict()) if visit_status else None ) -def lookup_origin_visit(origin_url: str, visit_id: int) -> OriginVisitInfo: +def lookup_origin_visit( + origin_url: str, + visit_id: int, + lookup_similar_urls: bool = True, +) -> OriginVisitInfo: """Return information about visit visit_id with origin origin. Args: origin: origin concerned by the visit visit_id: the visit identifier to lookup + lookup_similar_urls: if :const:`True`, lookup origin with and + without trailing slash in its URL Raises: NotFoundExc if no origin visit matching the criteria is found Returns: The dict origin_visit concerned """ + # check origin existence in the archive + origin_url = lookup_origin( + OriginInfo(url=origin_url), lookup_similar_urls=lookup_similar_urls + )["url"] + visit = storage.origin_visit_get_by(origin_url, visit_id) visit_status = storage.origin_visit_status_get_latest(origin_url, visit_id) if not visit: raise NotFoundExc( f"Origin {origin_url} or its visit with id {visit_id} not found!" ) return converters.from_origin_visit({**visit_status.to_dict(), "type": visit.type}) def origin_visit_find_by_date( origin_url: str, visit_date: datetime.datetime, greater_or_equal: bool = True ) -> Optional[OriginVisitInfo]: """Retrieve origin visit status whose date is most recent than the provided visit_date. Args: origin_url: origin concerned by the visit visit_date: provided visit date greater_or_equal: ensure returned visit has a date greater or equal than the one passed as parameter Returns: The dict origin_visit_status matching the criteria if any. """ visit = storage.origin_visit_find_by_date(origin_url, visit_date) if greater_or_equal and visit and visit.date < visit_date: # when visit is anterior to the provided date, trying to find another one most # recent visits = storage.origin_visit_get( origin_url, page_token=str(visit.visit), limit=1, ).results visit = visits[0] if visits else None if not visit: return None visit_status = storage.origin_visit_status_get_latest(origin_url, visit.visit) return converters.from_origin_visit({**visit_status.to_dict(), "type": visit.type}) def lookup_snapshot_sizes( snapshot_id: str, branch_name_exclude_prefix: Optional[str] = "refs/pull/" ) -> Dict[str, int]: """Count the number of branches in the snapshot with the given id. Args: snapshot_id (str): sha1 identifier of the snapshot Returns: dict: A dict whose keys are the target types of branches and values their corresponding amount """ snapshot_id_bin = _to_sha1_bin(snapshot_id) snapshot_sizes = dict.fromkeys(("alias", "release", "revision"), 0) branch_counts = storage.snapshot_count_branches( snapshot_id_bin, branch_name_exclude_prefix.encode() if branch_name_exclude_prefix else None, ) # remove possible None key returned by snapshot_count_branches # when null branches are present in the snapshot branch_counts.pop(None, None) snapshot_sizes.update(branch_counts) return snapshot_sizes def lookup_snapshot( snapshot_id: str, branches_from: str = "", branches_count: int = 1000, target_types: Optional[List[str]] = None, branch_name_include_substring: Optional[str] = None, branch_name_exclude_prefix: Optional[str] = "refs/pull/", ) -> Dict[str, Any]: """Return information about a snapshot, aka the list of named branches found during a specific visit of an origin. Args: snapshot_id: sha1 identifier of the snapshot branches_from: optional parameter used to skip branches whose name is lesser than it before returning them branches_count: optional parameter used to restrain the amount of returned branches target_types: optional parameter used to filter the target types of branch to return (possible values that can be contained in that list are `'content', 'directory', 'revision', 'release', 'snapshot', 'alias'`) branch_name_include_substring: if provided, only return branches whose name contains given substring branch_name_exclude_prefix: if provided, do not return branches whose name starts with given pattern Raises: NotFoundExc if the given snapshot_id is missing Returns: A dict filled with the snapshot content. """ snapshot_id_bin = _to_sha1_bin(snapshot_id) if storage.snapshot_missing([snapshot_id_bin]): raise NotFoundExc(f"Snapshot with id {snapshot_id} not found!") partial_branches = storage.snapshot_get_branches( snapshot_id_bin, branches_from.encode(), branches_count, target_types, branch_name_include_substring.encode() if branch_name_include_substring else None, branch_name_exclude_prefix.encode() if branch_name_exclude_prefix else None, ) return ( converters.from_partial_branches(partial_branches) if partial_branches else None ) def lookup_latest_origin_snapshot( origin: str, allowed_statuses: List[str] = None ) -> Optional[Dict[str, Any]]: """Return information about the latest snapshot of an origin. .. warning:: At most 1000 branches contained in the snapshot will be returned for performance reasons. Args: origin: URL or integer identifier of the origin allowed_statuses: list of visit statuses considered to find the latest snapshot for the visit. For instance, ``allowed_statuses=['full']`` will only consider visits that have successfully run to completion. Returns: A dict filled with the snapshot content. """ snp = snapshot_get_latest( storage, origin, allowed_statuses=allowed_statuses, branches_count=1000 ) return converters.from_snapshot(snp.to_dict()) if snp is not None else None def lookup_snapshot_alias( snapshot_id: str, alias_name: str ) -> Optional[Dict[str, Any]]: """Try to resolve a branch alias in a snapshot. Args: snapshot_id: hexadecimal representation of a snapshot id alias_name: name of the branch alias to resolve Returns: Target branch information or None if the alias does not exist or target a dangling branch. """ resolved_alias = snapshot_resolve_alias( storage, _to_sha1_bin(snapshot_id), alias_name.encode() ) return ( converters.from_swh(resolved_alias.to_dict(), hashess={"target"}) if resolved_alias is not None else None ) def lookup_revision_through(revision, limit=100): """Retrieve a revision from the criterion stored in revision dictionary. Args: revision: Dictionary of criterion to lookup the revision with. Here are the supported combination of possible values: - origin_url, branch_name, ts, sha1_git - origin_url, branch_name, ts - sha1_git_root, sha1_git - sha1_git Returns: None if the revision is not found or the actual revision. """ if ( "origin_url" in revision and "branch_name" in revision and "ts" in revision and "sha1_git" in revision ): return lookup_revision_with_context_by( revision["origin_url"], revision["branch_name"], revision["ts"], revision["sha1_git"], limit, ) if "origin_url" in revision and "branch_name" in revision and "ts" in revision: return lookup_revision_by( revision["origin_url"], revision["branch_name"], revision["ts"] ) if "sha1_git_root" in revision and "sha1_git" in revision: return lookup_revision_with_context( revision["sha1_git_root"], revision["sha1_git"], limit ) if "sha1_git" in revision: return lookup_revision(revision["sha1_git"]) # this should not happen raise NotImplementedError("Should not happen!") def lookup_directory_through_revision(revision, path=None, limit=100, with_data=False): """Retrieve the directory information from the revision. Args: revision: dictionary of criterion representing a revision to lookup path: directory's path to lookup. limit: optional query parameter to limit the revisions log (default to 100). For now, note that this limit could impede the transitivity conclusion about sha1_git not being an ancestor of. with_data: indicate to retrieve the content's raw data if path resolves to a content. Returns: The directory pointing to by the revision criterions at path. """ rev = lookup_revision_through(revision, limit) if not rev: raise NotFoundExc("Revision with criterion %s not found!" % revision) return (rev["id"], lookup_directory_with_revision(rev["id"], path, with_data)) def _vault_request(vault_fn, bundle_type: str, swhid: CoreSWHID, **kwargs): try: return vault_fn(bundle_type, swhid, **kwargs) except VaultNotFoundExc: return None def vault_cook(bundle_type: str, swhid: CoreSWHID, email=None): """Cook a vault bundle.""" return _vault_request(vault.cook, bundle_type, swhid, email=email) def vault_fetch(bundle_type: str, swhid: CoreSWHID): """Fetch a vault bundle.""" return _vault_request(vault.fetch, bundle_type, swhid) def vault_progress(bundle_type: str, swhid: CoreSWHID): """Get the current progress of a vault bundle.""" return _vault_request(vault.progress, bundle_type, swhid) def diff_revision(rev_id): """Get the list of file changes (insertion / deletion / modification / renaming) for a particular revision. """ rev_sha1_git_bin = _to_sha1_bin(rev_id) changes = diff.diff_revision(storage, rev_sha1_git_bin, track_renaming=True) for change in changes: change["from"] = converters.from_directory_entry(change["from"]) change["to"] = converters.from_directory_entry(change["to"]) if change["from_path"]: change["from_path"] = change["from_path"].decode("utf-8") if change["to_path"]: change["to_path"] = change["to_path"].decode("utf-8") return changes class _RevisionsWalkerProxy(object): """ Proxy class wrapping a revisions walker iterator from swh-storage and performing needed conversions. """ def __init__(self, rev_walker_type, rev_start, *args, **kwargs): rev_start_bin = hashutil.hash_to_bytes(rev_start) self.revisions_walker = revisions_walker.get_revisions_walker( rev_walker_type, storage, rev_start_bin, *args, **kwargs ) def export_state(self): return self.revisions_walker.export_state() def __next__(self): return converters.from_revision(next(self.revisions_walker)) def __iter__(self): return self def get_revisions_walker(rev_walker_type, rev_start, *args, **kwargs): """ Utility function to instantiate a revisions walker of a given type, see :mod:`swh.storage.algos.revisions_walker`. Args: rev_walker_type (str): the type of revisions walker to return, possible values are: ``committer_date``, ``dfs``, ``dfs_post``, ``bfs`` and ``path`` rev_start (str): hexadecimal representation of a revision identifier args (list): position arguments to pass to the revisions walker constructor kwargs (dict): keyword arguments to pass to the revisions walker constructor """ # first check if the provided revision is valid lookup_revision(rev_start) return _RevisionsWalkerProxy(rev_walker_type, rev_start, *args, **kwargs) def lookup_object(object_type: ObjectType, object_id: str) -> Dict[str, Any]: """ Utility function for looking up an object in the archive by its type and id. Args: object_type (str): the type of object to lookup, either *content*, *directory*, *release*, *revision* or *snapshot* object_id (str): the *sha1_git* checksum identifier in hexadecimal form of the object to lookup Returns: Dict[str, Any]: A dictionary describing the object or a list of dictionary for the directory object type. Raises: swh.web.common.exc.NotFoundExc: if the object could not be found in the archive BadInputExc: if the object identifier is invalid """ if object_type == ObjectType.CONTENT: return lookup_content(f"sha1_git:{object_id}") elif object_type == ObjectType.DIRECTORY: return {"id": object_id, "content": list(lookup_directory(object_id))} elif object_type == ObjectType.RELEASE: return lookup_release(object_id) elif object_type == ObjectType.REVISION: return lookup_revision(object_id) elif object_type == ObjectType.SNAPSHOT: return lookup_snapshot(object_id) else: raise ValueError(f"Unexpected object type variant: {object_type}") def lookup_missing_hashes(grouped_swhids: Dict[ObjectType, List[bytes]]) -> Set[str]: """Lookup missing Software Heritage persistent identifier hash, using batch processing. Args: A dictionary with: keys: object types values: object hashes Returns: A set(hexadecimal) of the hashes not found in the storage """ missing_hashes = [] for obj_type, obj_ids in grouped_swhids.items(): if obj_type == ObjectType.CONTENT: missing_hashes.append(storage.content_missing_per_sha1_git(obj_ids)) elif obj_type == ObjectType.DIRECTORY: missing_hashes.append(storage.directory_missing(obj_ids)) elif obj_type == ObjectType.REVISION: missing_hashes.append(storage.revision_missing(obj_ids)) elif obj_type == ObjectType.RELEASE: missing_hashes.append(storage.release_missing(obj_ids)) elif obj_type == ObjectType.SNAPSHOT: missing_hashes.append(storage.snapshot_missing(obj_ids)) missing = set( map(lambda x: hashutil.hash_to_hex(x), itertools.chain(*missing_hashes)) ) return missing def lookup_origins_by_sha1s(sha1s: List[str]) -> Iterator[Optional[OriginInfo]]: """Lookup origins from the sha1 hash values of their URLs. Args: sha1s: list of sha1s hexadecimal representation Yields: origin information as dict """ sha1s_bytes = [hashutil.hash_to_bytes(sha1) for sha1 in sha1s] origins = storage.origin_get_by_sha1(sha1s_bytes) for origin in origins: yield converters.from_origin(origin) diff --git a/swh/web/common/origin_visits.py b/swh/web/common/origin_visits.py index a7412563..1de913ff 100644 --- a/swh/web/common/origin_visits.py +++ b/swh/web/common/origin_visits.py @@ -1,175 +1,178 @@ # Copyright (C) 2018-2022 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU Affero General Public License version 3, or any later version # See top-level LICENSE file for more information from typing import List, Optional from django.core.cache import cache from swh.web.common import archive from swh.web.common.exc import NotFoundExc from swh.web.common.typing import OriginInfo, OriginVisitInfo from swh.web.common.utils import parse_iso8601_date_to_utc -def get_origin_visits(origin_info: OriginInfo) -> List[OriginVisitInfo]: +def get_origin_visits( + origin_info: OriginInfo, lookup_similar_urls: bool = True +) -> List[OriginVisitInfo]: """Function that returns the list of visits for a swh origin. That list is put in cache in order to speedup the navigation in the swh web browse ui. The returned visits are sorted according to their date in ascending order. Args: origin_info: dict describing the origin to fetch visits from + lookup_similar_urls: if :const:`True`, lookup origin with and + without trailing slash in its URL Returns: A list of dict describing the origin visits Raises: swh.web.common.exc.NotFoundExc: if the origin is not found """ from swh.web.common import archive - if "url" in origin_info: - origin_url = origin_info["url"] - else: - origin_url = archive.lookup_origin(origin_info)["url"] + origin_url = archive.lookup_origin( + origin_info, lookup_similar_urls=lookup_similar_urls + )["url"] cache_entry_id = "origin_visits_%s" % origin_url cache_entry = cache.get(cache_entry_id) last_visit = 0 origin_visits = [] new_visits = [] per_page = archive.MAX_LIMIT if cache_entry: origin_visits = cache_entry last_visit = cache_entry[-1]["visit"] new_visits = list( archive.lookup_origin_visits( origin_url, last_visit=last_visit, per_page=per_page ) ) last_visit += len(new_visits) if not new_visits: last_snp = archive.lookup_latest_origin_snapshot(origin_url) if not last_snp or last_snp["id"] == cache_entry[-1]["snapshot"]: return cache_entry # get new visits that we did not retrieve yet while 1: visits = list( archive.lookup_origin_visits( origin_url, last_visit=last_visit, per_page=per_page ) ) new_visits += visits if len(visits) < per_page: break last_visit += per_page def _visit_sort_key(visit): ts = parse_iso8601_date_to_utc(visit["date"]).timestamp() return ts + (float(visit["visit"]) / 10e3) # cache entry is already sorted with oldest visits origin_visits += sorted(new_visits, key=lambda v: _visit_sort_key(v)) cache.set(cache_entry_id, origin_visits) return origin_visits def get_origin_visit( origin_info: OriginInfo, visit_ts: Optional[str] = None, visit_id: Optional[int] = None, snapshot_id: Optional[str] = None, ) -> OriginVisitInfo: """Function that returns information about a visit for a given origin. If a timestamp is provided, the closest visit from that timestamp is returned. If a snapshot identifier is provided, the first visit with that snapshot is returned. If no search hints are provided, return the most recent full visit with a valid snapshot or the most recent partial visit with a valid snapshot otherwise. Args: origin_info: a dict filled with origin information visit_ts: an ISO 8601 datetime string to parse snapshot_id: a snapshot identifier Returns: A dict containing the visit info. Raises: swh.web.common.exc.NotFoundExc: if no visit can be found """ # returns the latest full visit with a valid snapshot visit = archive.lookup_origin_visit_latest( origin_info["url"], allowed_statuses=["full"], require_snapshot=True ) if not visit: # or the latest partial visit with a valid snapshot otherwise visit = archive.lookup_origin_visit_latest( origin_info["url"], allowed_statuses=["partial"], require_snapshot=True ) if not visit_ts and not visit_id and not snapshot_id: if visit: return visit else: raise NotFoundExc( f"No valid visit for origin with url {origin_info['url']} found!" ) # no need to fetch all visits list and search in it if the latest # visit matches some criteria if visit and (visit["snapshot"] == snapshot_id or visit["visit"] == visit_id): return visit if visit_id: return archive.lookup_origin_visit(origin_info["url"], visit_id) if visit_ts: visit = archive.origin_visit_find_by_date( origin_info["url"], parse_iso8601_date_to_utc(visit_ts), greater_or_equal=False, ) if visit is not None: return visit else: raise NotFoundExc( ( "Visit with timestamp %s for origin with " "url %s not found!" % (visit_ts, origin_info["url"]) ) ) visits = get_origin_visits(origin_info) if not visits: raise NotFoundExc( f"No visits associated to origin with url {origin_info['url']}!" ) if snapshot_id: visits = [v for v in visits if v["snapshot"] == snapshot_id] if len(visits) == 0: raise NotFoundExc( ( "Visit for snapshot with id %s for origin with" " url %s not found!" % (snapshot_id, origin_info["url"]) ) ) return visits[0] return visits[-1] diff --git a/swh/web/tests/api/views/test_origin.py b/swh/web/tests/api/views/test_origin.py index cbd52fda..815216fe 100644 --- a/swh/web/tests/api/views/test_origin.py +++ b/swh/web/tests/api/views/test_origin.py @@ -1,839 +1,867 @@ # Copyright (C) 2015-2021 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU Affero General Public License version 3, or any later version # See top-level LICENSE file for more information from datetime import timedelta import json from hypothesis import given import pytest from swh.indexer.storage.model import OriginIntrinsicMetadataRow from swh.model.hashutil import hash_to_bytes from swh.model.model import Origin, OriginVisit, OriginVisitStatus from swh.search.exc import SearchQuerySyntaxError from swh.search.interface import PagedResult from swh.storage.exc import StorageAPIError, StorageDBError from swh.storage.utils import now from swh.web.api.utils import enrich_origin, enrich_origin_visit from swh.web.common.exc import BadInputExc from swh.web.common.origin_visits import get_origin_visits from swh.web.common.utils import reverse from swh.web.tests.api.views.utils import scroll_results from swh.web.tests.data import ( INDEXER_TOOL, ORIGIN_MASTER_DIRECTORY, ORIGIN_MASTER_REVISION, ORIGIN_METADATA_KEY, ORIGIN_METADATA_VALUE, ) from swh.web.tests.strategies import new_origin, new_snapshots, visit_dates from swh.web.tests.utils import check_api_get_responses -def test_api_lookup_origin_visits_raise_error(api_client, mocker): +def test_api_lookup_origin_visits_raise_error(api_client, origin, mocker): mock_get_origin_visits = mocker.patch("swh.web.api.views.origin.get_origin_visits") err_msg = "voluntary error to check the bad request middleware." mock_get_origin_visits.side_effect = BadInputExc(err_msg) - url = reverse("api-1-origin-visits", url_args={"origin_url": "http://foo"}) + url = reverse("api-1-origin-visits", url_args={"origin_url": origin["url"]}) rv = check_api_get_responses(api_client, url, status_code=400) assert rv.data == {"exception": "BadInputExc", "reason": err_msg} -def test_api_lookup_origin_visits_raise_swh_storage_error_db(api_client, mocker): +def test_api_lookup_origin_visits_raise_swh_storage_error_db( + api_client, origin, mocker +): mock_get_origin_visits = mocker.patch("swh.web.api.views.origin.get_origin_visits") err_msg = "Storage exploded! Will be back online shortly!" mock_get_origin_visits.side_effect = StorageDBError(err_msg) - url = reverse("api-1-origin-visits", url_args={"origin_url": "http://foo"}) + url = reverse("api-1-origin-visits", url_args={"origin_url": origin["url"]}) rv = check_api_get_responses(api_client, url, status_code=503) assert rv.data == { "exception": "StorageDBError", "reason": "An unexpected error occurred in the backend: %s" % err_msg, } -def test_api_lookup_origin_visits_raise_swh_storage_error_api(api_client, mocker): +def test_api_lookup_origin_visits_raise_swh_storage_error_api( + api_client, origin, mocker +): mock_get_origin_visits = mocker.patch("swh.web.api.views.origin.get_origin_visits") err_msg = "Storage API dropped dead! Will resurrect asap!" mock_get_origin_visits.side_effect = StorageAPIError(err_msg) - url = reverse("api-1-origin-visits", url_args={"origin_url": "http://foo"}) + url = reverse("api-1-origin-visits", url_args={"origin_url": origin["url"]}) rv = check_api_get_responses(api_client, url, status_code=503) assert rv.data == { "exception": "StorageAPIError", "reason": "An unexpected error occurred in the api backend: %s" % err_msg, } @given(new_origin(), visit_dates(3), new_snapshots(3)) def test_api_lookup_origin_visits( api_client, subtest, new_origin, visit_dates, new_snapshots ): # ensure archive_data fixture will be reset between each hypothesis # example test run @subtest def test_inner(archive_data): archive_data.origin_add([new_origin]) for i, visit_date in enumerate(visit_dates): origin_visit = archive_data.origin_visit_add( [ OriginVisit( origin=new_origin.url, date=visit_date, type="git", ) ] )[0] archive_data.snapshot_add([new_snapshots[i]]) visit_status = OriginVisitStatus( origin=new_origin.url, visit=origin_visit.visit, date=now(), status="full", snapshot=new_snapshots[i].id, ) archive_data.origin_visit_status_add([visit_status]) all_visits = list(reversed(get_origin_visits(new_origin.to_dict()))) for last_visit, expected_visits in ( (None, all_visits[:2]), (all_visits[1]["visit"], all_visits[2:]), ): url = reverse( "api-1-origin-visits", url_args={"origin_url": new_origin.url}, query_params={"per_page": 2, "last_visit": last_visit}, ) rv = check_api_get_responses(api_client, url, status_code=200) for i in range(len(expected_visits)): expected_visits[i] = enrich_origin_visit( expected_visits[i], with_origin_link=False, with_origin_visit_link=True, request=rv.wsgi_request, ) assert rv.data == expected_visits @given(new_origin(), visit_dates(3), new_snapshots(3)) def test_api_lookup_origin_visits_by_id( api_client, subtest, new_origin, visit_dates, new_snapshots ): # ensure archive_data fixture will be reset between each hypothesis # example test run @subtest def test_inner(archive_data): archive_data.origin_add([new_origin]) for i, visit_date in enumerate(visit_dates): origin_visit = archive_data.origin_visit_add( [ OriginVisit( origin=new_origin.url, date=visit_date, type="git", ) ] )[0] archive_data.snapshot_add([new_snapshots[i]]) visit_status = OriginVisitStatus( origin=new_origin.url, visit=origin_visit.visit, date=now(), status="full", snapshot=new_snapshots[i].id, ) archive_data.origin_visit_status_add([visit_status]) all_visits = list(reversed(get_origin_visits(new_origin.to_dict()))) for last_visit, expected_visits in ( (None, all_visits[:2]), (all_visits[1]["visit"], all_visits[2:4]), ): url = reverse( "api-1-origin-visits", url_args={"origin_url": new_origin.url}, query_params={"per_page": 2, "last_visit": last_visit}, ) rv = check_api_get_responses(api_client, url, status_code=200) for i in range(len(expected_visits)): expected_visits[i] = enrich_origin_visit( expected_visits[i], with_origin_link=False, with_origin_visit_link=True, request=rv.wsgi_request, ) assert rv.data == expected_visits @given(new_origin(), visit_dates(3), new_snapshots(3)) def test_api_lookup_origin_visit( api_client, subtest, new_origin, visit_dates, new_snapshots ): # ensure archive_data fixture will be reset between each hypothesis # example test run @subtest def test_inner(archive_data): archive_data.origin_add([new_origin]) for i, visit_date in enumerate(visit_dates): origin_visit = archive_data.origin_visit_add( [ OriginVisit( origin=new_origin.url, date=visit_date, type="git", ) ] )[0] visit_id = origin_visit.visit archive_data.snapshot_add([new_snapshots[i]]) visit_status = OriginVisitStatus( origin=new_origin.url, visit=origin_visit.visit, date=visit_date + timedelta(minutes=5), status="full", snapshot=new_snapshots[i].id, ) archive_data.origin_visit_status_add([visit_status]) url = reverse( "api-1-origin-visit", url_args={"origin_url": new_origin.url, "visit_id": visit_id}, ) rv = check_api_get_responses(api_client, url, status_code=200) expected_visit = archive_data.origin_visit_get_by(new_origin.url, visit_id) expected_visit = enrich_origin_visit( expected_visit, with_origin_link=True, with_origin_visit_link=False, request=rv.wsgi_request, ) assert rv.data == expected_visit @given(new_origin()) def test_api_lookup_origin_visit_latest_no_visit(api_client, archive_data, new_origin): archive_data.origin_add([new_origin]) url = reverse("api-1-origin-visit-latest", url_args={"origin_url": new_origin.url}) rv = check_api_get_responses(api_client, url, status_code=404) assert rv.data == { "exception": "NotFoundExc", "reason": "No visit for origin %s found" % new_origin.url, } @given(new_origin(), visit_dates(2), new_snapshots(1)) def test_api_lookup_origin_visit_latest( api_client, subtest, new_origin, visit_dates, new_snapshots ): # ensure archive_data fixture will be reset between each hypothesis # example test run @subtest def test_inner(archive_data): archive_data.origin_add([new_origin]) visit_dates.sort() visit_ids = [] for i, visit_date in enumerate(visit_dates): origin_visit = archive_data.origin_visit_add( [ OriginVisit( origin=new_origin.url, date=visit_date, type="git", ) ] )[0] visit_ids.append(origin_visit.visit) archive_data.snapshot_add([new_snapshots[0]]) visit_status = OriginVisitStatus( origin=new_origin.url, visit=visit_ids[0], date=now(), status="full", snapshot=new_snapshots[0].id, ) archive_data.origin_visit_status_add([visit_status]) url = reverse( "api-1-origin-visit-latest", url_args={"origin_url": new_origin.url} ) rv = check_api_get_responses(api_client, url, status_code=200) expected_visit = archive_data.origin_visit_status_get_latest( new_origin.url, type="git" ) expected_visit = enrich_origin_visit( expected_visit, with_origin_link=True, with_origin_visit_link=False, request=rv.wsgi_request, ) assert rv.data == expected_visit @given(new_origin(), visit_dates(2), new_snapshots(1)) def test_api_lookup_origin_visit_latest_with_snapshot( api_client, subtest, new_origin, visit_dates, new_snapshots ): # ensure archive_data fixture will be reset between each hypothesis # example test run @subtest def test_inner(archive_data): archive_data.origin_add([new_origin]) visit_dates.sort() visit_ids = [] for i, visit_date in enumerate(visit_dates): origin_visit = archive_data.origin_visit_add( [ OriginVisit( origin=new_origin.url, date=visit_date, type="git", ) ] )[0] visit_ids.append(origin_visit.visit) archive_data.snapshot_add([new_snapshots[0]]) # Add snapshot to the latest visit visit_id = visit_ids[-1] visit_status = OriginVisitStatus( origin=new_origin.url, visit=visit_id, date=now(), status="full", snapshot=new_snapshots[0].id, ) archive_data.origin_visit_status_add([visit_status]) url = reverse( "api-1-origin-visit-latest", url_args={"origin_url": new_origin.url}, query_params={"require_snapshot": True}, ) rv = check_api_get_responses(api_client, url, status_code=200) expected_visit = archive_data.origin_visit_status_get_latest( new_origin.url, type="git", require_snapshot=True ) expected_visit = enrich_origin_visit( expected_visit, with_origin_link=True, with_origin_visit_link=False, request=rv.wsgi_request, ) assert rv.data == expected_visit def test_api_lookup_origin_visit_not_found(api_client, origin): all_visits = list(reversed(get_origin_visits(origin))) max_visit_id = max([v["visit"] for v in all_visits]) url = reverse( "api-1-origin-visit", url_args={"origin_url": origin["url"], "visit_id": max_visit_id + 1}, ) rv = check_api_get_responses(api_client, url, status_code=404) assert rv.data == { "exception": "NotFoundExc", "reason": "Origin %s or its visit with id %s not found!" % (origin["url"], max_visit_id + 1), } def test_api_origins_wrong_input(api_client, archive_data): """Should fail with 400 if the input is deprecated.""" # fail if wrong input url = reverse("api-1-origins", query_params={"origin_from": 1}) rv = check_api_get_responses(api_client, url, status_code=400) assert rv.data == { "exception": "BadInputExc", "reason": "Please use the Link header to browse through result", } def test_api_origins(api_client, archive_data): page_result = archive_data.origin_list(limit=10000) origins = page_result.results origin_urls = {origin.url for origin in origins} # Get only one url = reverse("api-1-origins", query_params={"origin_count": 1}) rv = check_api_get_responses(api_client, url, status_code=200) assert len(rv.data) == 1 assert {origin["url"] for origin in rv.data} <= origin_urls # Get all url = reverse("api-1-origins", query_params={"origin_count": len(origins)}) rv = check_api_get_responses(api_client, url, status_code=200) assert len(rv.data) == len(origins) assert {origin["url"] for origin in rv.data} == origin_urls # Get "all + 10" url = reverse("api-1-origins", query_params={"origin_count": len(origins) + 10}) rv = check_api_get_responses(api_client, url, status_code=200) assert len(rv.data) == len(origins) assert {origin["url"] for origin in rv.data} == origin_urls @pytest.mark.parametrize("origin_count", [1, 2, 10, 100]) def test_api_origins_scroll(api_client, archive_data, origin_count): page_result = archive_data.origin_list(limit=10000) origins = page_result.results origin_urls = {origin.url for origin in origins} url = reverse("api-1-origins", query_params={"origin_count": origin_count}) results = scroll_results(api_client, url) assert len(results) == len(origins) assert {origin["url"] for origin in results} == origin_urls def test_api_origin_by_url(api_client, archive_data, origin): origin_url = origin["url"] url = reverse("api-1-origin", url_args={"origin_url": origin_url}) rv = check_api_get_responses(api_client, url, status_code=200) expected_origin = archive_data.origin_get([origin_url])[0] expected_origin = enrich_origin(expected_origin, rv.wsgi_request) assert rv.data == expected_origin @given(new_origin()) def test_api_origin_not_found(api_client, new_origin): url = reverse("api-1-origin", url_args={"origin_url": new_origin.url}) rv = check_api_get_responses(api_client, url, status_code=404) assert rv.data == { "exception": "NotFoundExc", "reason": "Origin with url %s not found!" % new_origin.url, } @pytest.mark.parametrize("backend", ["swh-search", "swh-storage"]) def test_api_origin_search(api_client, mocker, backend): if backend != "swh-search": # equivalent to not configuring search in the config mocker.patch("swh.web.common.archive.search", None) expected_origins = { "https://github.com/wcoder/highlightjs-line-numbers.js", "https://github.com/memononen/libtess2", } # Search for 'github.com', get only one url = reverse( "api-1-origin-search", url_args={"url_pattern": "github.com"}, query_params={"limit": 1}, ) rv = check_api_get_responses(api_client, url, status_code=200) assert len(rv.data) == 1 assert {origin["url"] for origin in rv.data} <= expected_origins assert rv.data == [ enrich_origin({"url": origin["url"]}, request=rv.wsgi_request) for origin in rv.data ] # Search for 'github.com', get all url = reverse( "api-1-origin-search", url_args={"url_pattern": "github.com"}, query_params={"limit": 2}, ) rv = check_api_get_responses(api_client, url, status_code=200) assert {origin["url"] for origin in rv.data} == expected_origins assert rv.data == [ enrich_origin({"url": origin["url"]}, request=rv.wsgi_request) for origin in rv.data ] # Search for 'github.com', get more than available url = reverse( "api-1-origin-search", url_args={"url_pattern": "github.com"}, query_params={"limit": 10}, ) rv = check_api_get_responses(api_client, url, status_code=200) assert {origin["url"] for origin in rv.data} == expected_origins assert rv.data == [ enrich_origin({"url": origin["url"]}, request=rv.wsgi_request) for origin in rv.data ] @pytest.mark.parametrize("backend", ["swh-search", "swh-storage"]) def test_api_origin_search_words(api_client, mocker, backend): if backend != "swh-search": # equivalent to not configuring search in the config mocker.patch("swh.web.common.archive.search", None) expected_origins = { "https://github.com/wcoder/highlightjs-line-numbers.js", "https://github.com/memononen/libtess2", } url = reverse( "api-1-origin-search", url_args={"url_pattern": "github com"}, query_params={"limit": 2}, ) rv = check_api_get_responses(api_client, url, status_code=200) assert {origin["url"] for origin in rv.data} == expected_origins url = reverse( "api-1-origin-search", url_args={"url_pattern": "com github"}, query_params={"limit": 2}, ) rv = check_api_get_responses(api_client, url, status_code=200) assert {origin["url"] for origin in rv.data} == expected_origins url = reverse( "api-1-origin-search", url_args={"url_pattern": "memononen libtess2"}, query_params={"limit": 2}, ) rv = check_api_get_responses(api_client, url, status_code=200) assert len(rv.data) == 1 assert {origin["url"] for origin in rv.data} == { "https://github.com/memononen/libtess2" } url = reverse( "api-1-origin-search", url_args={"url_pattern": "libtess2 memononen"}, query_params={"limit": 2}, ) rv = check_api_get_responses(api_client, url, status_code=200) assert len(rv.data) == 1 assert {origin["url"] for origin in rv.data} == { "https://github.com/memononen/libtess2" } @pytest.mark.parametrize("backend", ["swh-search", "swh-storage"]) def test_api_origin_search_visit_type(api_client, mocker, backend): if backend != "swh-search": # equivalent to not configuring search in the config mocker.patch("swh.web.common.archive.search", None) expected_origins = { "https://github.com/wcoder/highlightjs-line-numbers.js", "https://github.com/memononen/libtess2", } url = reverse( "api-1-origin-search", url_args={ "url_pattern": "github com", }, query_params={"visit_type": "git"}, ) rv = check_api_get_responses(api_client, url, status_code=200) assert {origin["url"] for origin in rv.data} == expected_origins url = reverse( "api-1-origin-search", url_args={ "url_pattern": "github com", }, query_params={"visit_type": "foo"}, ) rv = check_api_get_responses(api_client, url, status_code=200) assert rv.data == [] def test_api_origin_search_use_ql(api_client, mocker): expected_origins = { "https://github.com/wcoder/highlightjs-line-numbers.js", "https://github.com/memononen/libtess2", } ORIGINS = [{"url": origin} for origin in expected_origins] mock_archive_search = mocker.patch("swh.web.common.archive.search") mock_archive_search.origin_search.return_value = PagedResult( results=ORIGINS, next_page_token=None, ) query = "origin : 'github.com'" url = reverse( "api-1-origin-search", url_args={"url_pattern": query}, query_params={"visit_type": "git", "use_ql": "true"}, ) rv = check_api_get_responses(api_client, url, status_code=200) assert {origin["url"] for origin in rv.data} == expected_origins mock_archive_search.origin_search.assert_called_with( query=query, page_token=None, with_visit=False, visit_types=["git"], limit=70 ) def test_api_origin_search_ql_syntax_error(api_client, mocker): mock_archive_search = mocker.patch("swh.web.common.archive.search") mock_archive_search.origin_search.side_effect = SearchQuerySyntaxError( "Invalid syntax" ) query = "this is not a valid query" url = reverse( "api-1-origin-search", url_args={"url_pattern": query}, query_params={"visit_type": "git", "use_ql": "true"}, ) rv = check_api_get_responses(api_client, url, status_code=400) assert rv.data == { "exception": "BadInputExc", "reason": "Syntax error in search query: Invalid syntax", } mock_archive_search.origin_search.assert_called_with( query=query, page_token=None, with_visit=False, visit_types=["git"], limit=70 ) @pytest.mark.parametrize("backend", ["swh-search", "swh-storage"]) @pytest.mark.parametrize("limit", [1, 2, 3, 10]) def test_api_origin_search_scroll(api_client, archive_data, mocker, limit, backend): if backend != "swh-search": # equivalent to not configuring search in the config mocker.patch("swh.web.common.archive.search", None) expected_origins = { "https://github.com/wcoder/highlightjs-line-numbers.js", "https://github.com/memononen/libtess2", } url = reverse( "api-1-origin-search", url_args={"url_pattern": "github.com"}, query_params={"limit": limit}, ) results = scroll_results(api_client, url) assert {origin["url"] for origin in results} == expected_origins @pytest.mark.parametrize("backend", ["swh-search", "swh-storage"]) def test_api_origin_search_limit(api_client, archive_data, tests_data, mocker, backend): if backend == "swh-search": tests_data["search"].origin_update( [{"url": "http://foobar/{}".format(i)} for i in range(2000)] ) else: # equivalent to not configuring search in the config mocker.patch("swh.web.common.archive.search", None) archive_data.origin_add( [Origin(url="http://foobar/{}".format(i)) for i in range(2000)] ) url = reverse( "api-1-origin-search", url_args={"url_pattern": "foobar"}, query_params={"limit": 1050}, ) rv = check_api_get_responses(api_client, url, status_code=200) assert len(rv.data) == 1000 @pytest.mark.parametrize("backend", ["swh-search", "swh-indexer-storage"]) def test_api_origin_metadata_search(api_client, mocker, backend): mock_config = mocker.patch("swh.web.common.archive.config") mock_config.get_config.return_value = { "search_config": {"metadata_backend": backend} } url = reverse( "api-1-origin-metadata-search", query_params={"fulltext": ORIGIN_METADATA_VALUE} ) rv = check_api_get_responses(api_client, url, status_code=200) rv.data = sorted(rv.data, key=lambda d: d["url"]) expected_data = sorted( [ { "url": origin_url, "metadata": { "from_directory": ORIGIN_MASTER_DIRECTORY[origin_url], "tool": { "name": INDEXER_TOOL["tool_name"], "version": INDEXER_TOOL["tool_version"], "configuration": INDEXER_TOOL["tool_configuration"], "id": INDEXER_TOOL["id"], }, "mappings": [], }, } for origin_url in sorted(ORIGIN_MASTER_REVISION.keys()) ], key=lambda d: d["url"], ) for i in range(len(expected_data)): expected = expected_data[i] response = rv.data[i] metadata = response["metadata"].pop("metadata") assert any( [ORIGIN_METADATA_VALUE in json.dumps(val) for val in metadata.values()] ) assert response == expected def test_api_origin_metadata_search_limit(api_client, mocker): mock_idx_storage = mocker.patch("swh.web.common.archive.idx_storage") oimsft = mock_idx_storage.origin_intrinsic_metadata_search_fulltext oimsft.side_effect = lambda conjunction, limit: [ OriginIntrinsicMetadataRow( id=origin_url, from_directory=hash_to_bytes(directory), indexer_configuration_id=INDEXER_TOOL["id"], metadata={ORIGIN_METADATA_KEY: ORIGIN_METADATA_VALUE}, mappings=[], ) for origin_url, directory in ORIGIN_MASTER_DIRECTORY.items() ] url = reverse( "api-1-origin-metadata-search", query_params={"fulltext": ORIGIN_METADATA_VALUE} ) rv = check_api_get_responses(api_client, url, status_code=200) assert len(rv.data) == len(ORIGIN_MASTER_REVISION) oimsft.assert_called_with(conjunction=[ORIGIN_METADATA_VALUE], limit=70) url = reverse( "api-1-origin-metadata-search", query_params={"fulltext": ORIGIN_METADATA_VALUE, "limit": 10}, ) rv = check_api_get_responses(api_client, url, status_code=200) assert len(rv.data) == len(ORIGIN_MASTER_REVISION) oimsft.assert_called_with(conjunction=[ORIGIN_METADATA_VALUE], limit=10) url = reverse( "api-1-origin-metadata-search", query_params={"fulltext": ORIGIN_METADATA_VALUE, "limit": 987}, ) rv = check_api_get_responses(api_client, url, status_code=200) assert len(rv.data) == len(ORIGIN_MASTER_REVISION) oimsft.assert_called_with(conjunction=[ORIGIN_METADATA_VALUE], limit=100) def test_api_origin_intrinsic_metadata(api_client, origin): url = reverse( "api-origin-intrinsic-metadata", url_args={"origin_url": origin["url"]} ) rv = check_api_get_responses(api_client, url, status_code=200) assert ORIGIN_METADATA_KEY in rv.data assert rv.data[ORIGIN_METADATA_KEY] == ORIGIN_METADATA_VALUE def test_api_origin_metadata_search_invalid(api_client, mocker): mock_idx_storage = mocker.patch("swh.web.common.archive.idx_storage") url = reverse("api-1-origin-metadata-search") check_api_get_responses(api_client, url, status_code=400) mock_idx_storage.assert_not_called() @pytest.mark.parametrize("backend", ["swh-counters", "swh-storage"]) def test_api_stat_counters(api_client, mocker, backend): mock_config = mocker.patch("swh.web.common.archive.config") mock_config.get_config.return_value = {"counters_backend": backend} url = reverse("api-1-stat-counters") rv = check_api_get_responses(api_client, url, status_code=200) counts = json.loads(rv.content) for obj in ["content", "origin", "release", "directory", "revision"]: assert counts.get(obj, 0) > 0 @pytest.fixture def archived_origins(archive_data): page_result = archive_data.origin_list(page_token=None, limit=10000) origins = [origin.to_dict() for origin in page_result.results] for origin in origins: ovs = archive_data.origin_visit_get_with_statuses(origin["url"]).results del origin["id"] origin["type"] = ovs[0].visit.type return origins def test_api_origin_search_empty_pattern(api_client, archived_origins): url = reverse( "api-1-origin-search", url_args={"url_pattern": ""}, query_params={"limit": 10000}, ) rv = check_api_get_responses(api_client, url, status_code=200) assert {o["url"] for o in rv.data} == {o["url"] for o in archived_origins} def test_api_origin_search_empty_pattern_and_visit_type(api_client, archived_origins): visit_types = {o["type"] for o in archived_origins} for visit_type in visit_types: url = reverse( "api-1-origin-search", url_args={"url_pattern": ""}, query_params={"visit_type": visit_type, "limit": 10000}, ) rv = check_api_get_responses(api_client, url, status_code=200) assert {o["url"] for o in rv.data} == { o["url"] for o in archived_origins if o["type"] == visit_type } + + +@pytest.mark.parametrize( + "view_name, extra_args", + [ + ("api-1-origin", {}), + ("api-1-origin-visits", {}), + ("api-1-origin-visit", {"visit_id": 1}), + ("api-1-origin-visit-latest", {}), + ("api-origin-intrinsic-metadata", {}), + ], +) +def test_api_origin_by_url_with_extra_trailing_slash( + api_client, origin, view_name, extra_args +): + origin_url = origin["url"] + assert not origin_url.endswith("/") + origin_url = origin_url + "/" + url = reverse(view_name, url_args={"origin_url": origin_url, **extra_args}) + rv = check_api_get_responses(api_client, url, status_code=404) + assert rv.data == { + "exception": "NotFoundExc", + "reason": f"Origin with url {origin_url} not found!", + }