diff --git a/docs/uri-scheme-api-origin.rst b/docs/uri-scheme-api-origin.rst index e5f3efbc..f239cd37 100644 --- a/docs/uri-scheme-api-origin.rst +++ b/docs/uri-scheme-api-origin.rst @@ -1,264 +1,276 @@ Origin ------ .. http:get:: /api/1/origin/(origin_id)/ Get information about a software origin from its unique (but otherwise meaningless) identifier. :param int origin_id: a SWH origin identifier :>json number id: the origin unique identifier :>json string origin_visits_url: link to in order to get information about the SWH visits for that origin :>json string type: the type of software origin (*git*, *svn*, *hg*, *deb*, *ftp*, ...) :>json string url: the origin canonical url :reqheader Accept: the requested response content type, either *application/json* (default) or *application/yaml* :resheader Content-Type: this depends on :http:header:`Accept` header of request :statuscode 200: no error :statuscode 404: requested origin can not be found in the SWH archive **Request:** .. parsed-literal:: $ curl -i :swh_web_api:`origin/1/` **Response:** .. sourcecode:: http HTTP/1.1 200 OK Content-Type: application/json { "id": 1, "origin_visits_url": "/api/1/origin/1/visits/", "type": "git", "url": "https://github.com/hylang/hy" } .. http:get:: /api/1/origin/(origin_type)/url/(origin_url)/ Get information about a software origin from its type and canonical url. :param string origin_type: the origin type (*git*, *svn*, *hg*, *deb*, *ftp*, ...) :param string origin_url: the origin url :>json number id: the origin unique identifier :>json string origin_visits_url: link to in order to get information about the SWH visits for that origin :>json string type: the type of software origin (*git*, *svn*, *hg*, *deb*, *ftp*, ...) :>json string url: the origin canonical url :reqheader Accept: the requested response content type, either *application/json* (default) or *application/yaml* :resheader Content-Type: this depends on :http:header:`Accept` header of request **Allowed HTTP Methods:** :http:method:`get`, :http:method:`head`, :http:method:`options` :statuscode 200: no error :statuscode 404: requested origin can not be found in the SWH archive **Request:** .. parsed-literal:: $ curl -i :swh_web_api:`origin/git/url/https://github.com/python/cpython/` **Response:** .. sourcecode:: http HTTP/1.1 200 OK Content-Type: application/json { "id": 13706355, "origin_visits_url": "/api/1/origin/13706355/visits/", "type": "git", "url": "https://github.com/python/cpython" } .. 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. :param string url_pattern: a string pattern or a regular expression :query int offset: the number of found origins to skip before returning results :query int limit: the maximum number of found origins to return :query boolean regexp: if true, consider provided pattern as a regular expression and search origins whose urls match it :>jsonarr number id: the origin unique identifier :>jsonarr string origin_visits_url: link to in order to get information about the SWH visits for that origin :>jsonarr string type: the type of software origin (*git*, *svn*, *hg*, *deb*, *ftp*, ...) :>jsonarr string url: the origin canonical url :reqheader Accept: the requested response content type, either *application/json* (default) or *application/yaml* :resheader Content-Type: this depends on :http:header:`Accept` header of request **Allowed HTTP Methods:** :http:method:`get`, :http:method:`head`, :http:method:`options` :statuscode 200: no error **Request:** .. parsed-literal:: $ curl -i :swh_web_api:`origin/search/python/?limit=2` **Response:** .. sourcecode:: http HTTP/1.1 200 OK Content-Type: application/json [ { "type": "git", "origin_visits_url": "/api/1/origin/220/visits/", "id": 220, "url": "https://github.com/neon670/python.dev" }, { "type": "git", "origin_visits_url": "/api/1/origin/328/visits/", "id": 328, "url": "https://github.com/aur-archive/python-werkzeug" } ] .. http:get:: /api/1/origin/(origin_id)/visits/ Get information about all visits of a software origin. :param int origin_id: a SWH origin identifier :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 :reqheader Accept: the requested response content type, either *application/json* (default) or *application/yaml* :resheader Content-Type: this depends on :http:header:`Accept` header of request :resheader Link: indicates that a subsequent result page is available and contains the url pointing to it :>jsonarr string date: ISO representation of the visit date (in UTC) :>jsonarr number id: the unique identifier of the origin :>jsonarr string origin_visit_url: link to :http:get:`/api/1/origin/(origin_id)/visit/(visit_id)/` in order to get information about the visit + :>jsonarr string snapshot: the snapshot identifier of the visit + :>jsonarr string snapshot_url: link to :http:get:`/api/1/snapshot/(snapshot_id)/` + in order to get information about the snapshot of the visit :>jsonarr string status: status of the visit (either *full*, *partial* or *ongoing*) :>jsonarr number visit: the unique identifier of the visit **Allowed HTTP Methods:** :http:method:`get`, :http:method:`head`, :http:method:`options` :statuscode 200: no error :statuscode 404: requested origin can not be found in the SWH archive **Request:** .. parsed-literal:: $ curl -i :swh_web_api:`origin/1/visits/` **Response:** .. sourcecode:: http HTTP/1.1 200 OK Link: ; rel="next" Content-Type: application/json [ { "date": "2015-08-04T22:26:14.804009+00:00", "origin": 1, "origin_visit_url": "/api/1/origin/1/visit/1/", + "snapshot": "584b2fe3ce6218a96892e73bd76c2966bbc2a797", + "snapshot_url": "/api/1/snapshot/584b2fe3ce6218a96892e73bd76c2966bbc2a797/", "status": "full", "visit": 1 }, { "date": "2016-02-22T16:56:16.725068+00:00", "metadata": {}, "origin": 1, "origin_visit_url": "/api/1/origin/1/visit/2/", + "snapshot": "9d502b5a193c33b59b22be3c75f73472867b0f8e", + "snapshot_url": "/api/1/snapshot/9d502b5a193c33b59b22be3c75f73472867b0f8e/", "status": "full", "visit": 2 }, ] .. http:get:: /api/1/origin/(origin_id)/visit/(visit_id)/ Get information about a specific visit of a software origin. :param int origin_id: a SWH origin identifier :param int visit_id: a visit identifier :reqheader Accept: the requested response content type, either *application/json* (default) or *application/yaml* :resheader Content-Type: this depends on :http:header:`Accept` header of request :>json string date: ISO representation of the visit date (in UTC) :>json object occurrences: object containing all branches associated to the origin found - during the visit, for each of them the associated SWH revision id is given but also - a link to in order to get information about it + during the visit, for each of them the associated SWH target type and id are given + but also a link to get information about that target :>json number origin: the origin unique identifier :>json string origin_url: link to get information about the origin + :>jsonarr string snapshot: the snapshot identifier of the visit + :>jsonarr string snapshot_url: link to :http:get:`/api/1/snapshot/(snapshot_id)/` + in order to get information about the snapshot of the visit :>json string status: status of the visit (either *full*, *partial* or *ongoing*) :>json number visit: the unique identifier of the visit **Allowed HTTP Methods:** :http:method:`get`, :http:method:`head`, :http:method:`options` :statuscode 200: no error :statuscode 404: requested origin or visit can not be found in the SWH archive **Request:** .. parsed-literal:: $ curl -i :swh_web_api:`origin/1500/visit/1/` **Response:** .. sourcecode:: http HTTP/1.1 200 OK Content-Type: application/json { "date": "2015-08-23T17:48:46.800813+00:00", "occurrences": { "refs/heads/master": { "target": "83c20a6a63a7ebc1a549d367bc07a61b926cecf3", "target_type": "revision", "target_url": "/api/1/revision/83c20a6a63a7ebc1a549d367bc07a61b926cecf3/" }, "refs/heads/wiki": { "target": "71f667aeb5d02562f2fa0941ad91df69c474ff3b", "target_type": "revision", "target_url": "/api/1/revision/71f667aeb5d02562f2fa0941ad91df69c474ff3b/" }, "refs/tags/dpkt-1.6": { "target": "7fc0fd582812af36064d1c85fe51e33227920479", "target_type": "revision", "target_url": "/api/1/revision/7fc0fd582812af36064d1c85fe51e33227920479/" }, "refs/tags/dpkt-1.7": { "target": "0c9dbfbc0974ec8ac1d8253aa1092366a03633a8", "target_type": "revision", "target_url": "/api/1/revision/0c9dbfbc0974ec8ac1d8253aa1092366a03633a8/" } }, "origin": 1500, "origin_url": "/api/1/origin/1500/", + "snapshot": "6a3a2cf0b2b90ce7ae1cf0a221ed68035b686f5a", + "snapshot_url": "/api/1/snapshot/6a3a2cf0b2b90ce7ae1cf0a221ed68035b686f5a/", "status": "full", "visit": 1 } diff --git a/docs/uri-scheme-api-snapshot.rst b/docs/uri-scheme-api-snapshot.rst new file mode 100644 index 00000000..ea2e4634 --- /dev/null +++ b/docs/uri-scheme-api-snapshot.rst @@ -0,0 +1,76 @@ +Snapshot +-------- + +.. http:get:: /api/1/snapshot/(snapshot_id)/ + + Get information about a snapshot in the SWH archive. + + A snapshot is a set of named branches, which are pointers to objects at any + level of the Software Heritage DAG. It represents a full picture of an + origin at a given time. + + As well as pointing to other objects in the Software Heritage DAG, branches + can also be aliases, in which case their target is the name of another + branch in the same snapshot, or dangling, in which case the target is + unknown. + + A snapshot identifier is a salted sha1. See :func:`swh.model.identifiers.snapshot_identifier` + in our data model module for details about how they are computed. + + :param sha1 snapshot_id: a SWH snapshot identifier + + :reqheader Accept: the requested response content type, + either *application/json* (default) or *application/yaml* + :resheader Content-Type: this depends on :http:header:`Accept` header of request + + :>json object branches: object containing all branches associated to the snapshot, + for each of them the associated SWH target type and id are given but also + a link to get information about that target + :>json string id: the unique identifier of the snapshot + + **Allowed HTTP Methods:** :http:method:`get`, :http:method:`head`, :http:method:`options` + + :statuscode 200: no error + :statuscode 400: an invalid snapshot identifier has been provided + :statuscode 404: requested snapshot can not be found in the SWH archive + + **Request:** + + .. parsed-literal:: + + $ curl -i :swh_web_api:`snapshot/6a3a2cf0b2b90ce7ae1cf0a221ed68035b686f5a/` + + **Response:** + + .. sourcecode:: http + + HTTP/1.1 200 OK + Content-Type: application/json + + { + "branches": { + "refs/heads/master": { + "target": "83c20a6a63a7ebc1a549d367bc07a61b926cecf3", + "target_type": "revision", + "target_url": "/api/1/revision/83c20a6a63a7ebc1a549d367bc07a61b926cecf3/" + }, + "refs/heads/wiki": { + "target": "71f667aeb5d02562f2fa0941ad91df69c474ff3b", + "target_type": "revision", + "target_url": "/api/1/revision/71f667aeb5d02562f2fa0941ad91df69c474ff3b/" + }, + "refs/tags/dpkt-1.6": { + "target": "7fc0fd582812af36064d1c85fe51e33227920479", + "target_type": "revision", + "target_url": "/api/1/revision/7fc0fd582812af36064d1c85fe51e33227920479/" + }, + "refs/tags/dpkt-1.7": { + "target": "0c9dbfbc0974ec8ac1d8253aa1092366a03633a8", + "target_type": "revision", + "target_url": "/api/1/revision/0c9dbfbc0974ec8ac1d8253aa1092366a03633a8/" + } + }, + "id": "6a3a2cf0b2b90ce7ae1cf0a221ed68035b686f5a" + } + + diff --git a/docs/uri-scheme-api.rst b/docs/uri-scheme-api.rst index 1a03747c..c64375cd 100644 --- a/docs/uri-scheme-api.rst +++ b/docs/uri-scheme-api.rst @@ -1,18 +1,20 @@ .. _swh-web-api-urls: SWH Web API URLs ================ .. include:: uri-scheme-api-content.rst .. include:: uri-scheme-api-directory.rst .. include:: uri-scheme-api-origin.rst .. include:: uri-scheme-api-person.rst .. include:: uri-scheme-api-release.rst .. include:: uri-scheme-api-revision.rst +.. include:: uri-scheme-api-snapshot.rst + .. include:: uri-scheme-api-stat.rst diff --git a/swh/web/api/urls.py b/swh/web/api/urls.py index f24d30a1..03071b5a 100644 --- a/swh/web/api/urls.py +++ b/swh/web/api/urls.py @@ -1,18 +1,19 @@ # Copyright (C) 2017-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import swh.web.api.views.content # noqa import swh.web.api.views.directory # noqa import swh.web.api.views.entity # noqa import swh.web.api.views.origin # noqa import swh.web.api.views.person # noqa import swh.web.api.views.release # noqa import swh.web.api.views.revision # noqa +import swh.web.api.views.snapshot # noqa import swh.web.api.views.stat # noqa import swh.web.api.views.vault # noqa from swh.web.api.apiurls import APIUrls urlpatterns = APIUrls.get_url_patterns() diff --git a/swh/web/api/views/origin.py b/swh/web/api/views/origin.py index f4c6a7c0..b0b9dfd0 100644 --- a/swh/web/api/views/origin.py +++ b/swh/web/api/views/origin.py @@ -1,241 +1,248 @@ # Copyright (C) 2015-2018 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 swh.web.common import service from swh.web.common.utils import reverse from swh.web.api import utils from swh.web.api import apidoc as api_doc from swh.web.api.apiurls import api_route from swh.web.api.views.utils import ( api_lookup, doc_exc_id_not_found, doc_header_link, doc_arg_last_elt, doc_arg_per_page ) def _enrich_origin(origin): if 'id' in origin: o = origin.copy() o['origin_visits_url'] = \ reverse('origin-visits', kwargs={'origin_id': origin['id']}) return o return origin @api_route(r'/origin/(?P[0-9]+)/', 'origin') @api_route(r'/origin/(?P[a-z]+)/url/(?P.+)', 'origin') @api_doc.route('/origin/') @api_doc.arg('origin_id', default=1, argtype=api_doc.argtypes.int, argdoc='origin identifier (when looking up by ID)') @api_doc.arg('origin_type', default='git', argtype=api_doc.argtypes.str, argdoc='origin type (when looking up by type+URL)') @api_doc.arg('origin_url', default='https://github.com/hylang/hy', argtype=api_doc.argtypes.path, argdoc='origin URL (when looking up by type+URL)') @api_doc.raises(exc=api_doc.excs.notfound, doc=doc_exc_id_not_found) @api_doc.returns(rettype=api_doc.rettypes.dict, retdoc="""The metadata of the origin corresponding to the given criteria""") def api_origin(request, origin_id=None, origin_type=None, origin_url=None): """Get information about a software origin. Software origins might be looked up by origin type and canonical URL (e.g., "git" + a "git clone" URL), or by their unique (but otherwise meaningless) identifier. """ ori_dict = { 'id': origin_id, 'type': origin_type, 'url': origin_url } ori_dict = {k: v for k, v in ori_dict.items() if ori_dict[k]} if 'id' in ori_dict: error_msg = 'Origin with id %s not found.' % ori_dict['id'] else: error_msg = 'Origin with type %s and URL %s not found' % ( ori_dict['type'], ori_dict['url']) return api_lookup( service.lookup_origin, ori_dict, notfound_msg=error_msg, enrich_fn=_enrich_origin) @api_route(r'/origin/search/(?P.+)/', 'origin-search') @api_doc.route('/origin/search/') @api_doc.arg('url_pattern', default='python', argtype=api_doc.argtypes.str, argdoc='string pattern to search for in origin urls') @api_doc.header('Link', doc=doc_header_link) @api_doc.param('offset', default=0, argtype=api_doc.argtypes.int, doc='number of found origins to skip before returning results') # noqa @api_doc.param('limit', default=50, argtype=api_doc.argtypes.int, doc='the maximum number of found origins to return') @api_doc.param('regexp', default='false', argtype=api_doc.argtypes.str, doc="""if that query parameter is set to 'true', consider provided pattern as a regular expression and search origins whose urls match it""") @api_doc.returns(rettype=api_doc.rettypes.list, retdoc="""The metadata of the origins whose urls match the provided string pattern""") def api_origin_search(request, url_pattern): """Search for origins whose urls contain a provided string pattern or match a provided regular expression. The search is performed in a case insensitive way. """ result = {} offset = int(request.query_params.get('offset', '0')) limit = int(request.query_params.get('limit', '50')) regexp = request.query_params.get('regexp', 'false') r = api_lookup(service.search_origin, url_pattern, offset, limit, bool(strtobool(regexp)), enrich_fn=_enrich_origin) l = len(r) if l == limit: query_params = {} query_params['offset'] = offset + limit query_params['limit'] = limit query_params['regexp'] = regexp result['headers'] = { 'link-next': reverse('origin-search', kwargs={'url_pattern': url_pattern}, query_params=query_params) } result.update({ 'results': r }) return result @api_route(r'/origin/(?P[0-9]+)/visits/', 'origin-visits') @api_doc.route('/origin/visits/') @api_doc.arg('origin_id', default=1, argtype=api_doc.argtypes.int, argdoc='software origin identifier') @api_doc.header('Link', doc=doc_header_link) @api_doc.param('last_visit', default=None, argtype=api_doc.argtypes.int, doc=doc_arg_last_elt) @api_doc.param('per_page', default=10, argtype=api_doc.argtypes.int, doc=doc_arg_per_page) @api_doc.raises(exc=api_doc.excs.notfound, doc=doc_exc_id_not_found) @api_doc.returns(rettype=api_doc.rettypes.list, retdoc="""a list of dictionaries describing individual visits. For each visit, its identifier, timestamp (as UNIX time), outcome, and visit-specific URL for more information are given.""") def api_origin_visits(request, origin_id): """Get information about all visits of a given software origin. """ result = {} per_page = int(request.query_params.get('per_page', '10')) last_visit = request.query_params.get('last_visit') if last_visit: last_visit = int(last_visit) def _lookup_origin_visits( origin_id, last_visit=last_visit, per_page=per_page): return service.lookup_origin_visits( origin_id, last_visit=last_visit, per_page=per_page) def _enrich_origin_visit(origin_visit): ov = origin_visit.copy() ov['origin_visit_url'] = reverse('origin-visit', kwargs={'origin_id': origin_id, 'visit_id': ov['visit']}) + ov['snapshot_url'] = reverse('snapshot', + kwargs={'snapshot_id': ov['snapshot']}) return ov r = api_lookup( _lookup_origin_visits, origin_id, notfound_msg='No origin {} found'.format(origin_id), enrich_fn=_enrich_origin_visit) if r: l = len(r) if l == per_page: new_last_visit = r[-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('origin-visits', kwargs={'origin_id': origin_id}, query_params=query_params) } result.update({ 'results': r }) return result @api_route(r'/origin/(?P[0-9]+)/visit/(?P[0-9]+)/', 'origin-visit') @api_doc.route('/origin/visit/') @api_doc.arg('origin_id', default=1, argtype=api_doc.argtypes.int, argdoc='software origin identifier') @api_doc.arg('visit_id', default=1, argtype=api_doc.argtypes.int, argdoc="""visit identifier, relative to the origin identified by origin_id""") @api_doc.raises(exc=api_doc.excs.notfound, doc=doc_exc_id_not_found) @api_doc.returns(rettype=api_doc.rettypes.dict, retdoc="""dictionary containing both metadata for the entire visit (e.g., timestamp as UNIX time, visit outcome, etc.) and what was at the software origin during the visit (i.e., a mapping from branches to other archive objects)""") def api_origin_visit(request, origin_id, visit_id): """Get information about a specific visit of a software origin. """ def _enrich_origin_visit(origin_visit): ov = origin_visit.copy() ov['origin_url'] = reverse('origin', kwargs={'origin_id': ov['origin']}) + ov['snapshot_url'] = reverse('snapshot', + kwargs={'snapshot_id': ov['snapshot']}) + + # TODO: remove that piece of code once the snapshot migration + # is totally effective in storage (no more occurrences) if 'occurrences' in ov: ov['occurrences'] = { k: utils.enrich_object(v) for k, v in ov['occurrences'].items() } return ov return api_lookup( service.lookup_origin_visit, origin_id, visit_id, notfound_msg=('No visit {} for origin {} found' .format(visit_id, origin_id)), enrich_fn=_enrich_origin_visit) diff --git a/swh/web/api/views/snapshot.py b/swh/web/api/views/snapshot.py new file mode 100644 index 00000000..94f011e7 --- /dev/null +++ b/swh/web/api/views/snapshot.py @@ -0,0 +1,55 @@ +# Copyright (C) 2018 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 swh.web.common import service +from swh.web.api import apidoc as api_doc +from swh.web.api import utils +from swh.web.api.apiurls import api_route +from swh.web.api.views.utils import ( + api_lookup, doc_exc_id_not_found, doc_exc_bad_id +) + + +@api_route(r'/snapshot/(?P[0-9a-f]+)/', 'snapshot') +@api_doc.route('/snapshot/') +@api_doc.arg('snapshot_id', + default='584b2fe3ce6218a96892e73bd76c2966bbc2a797', + argtype=api_doc.argtypes.sha1, + argdoc='snapshot identifier') +@api_doc.raises(exc=api_doc.excs.badinput, doc=doc_exc_bad_id) +@api_doc.raises(exc=api_doc.excs.notfound, doc=doc_exc_id_not_found) +@api_doc.returns(rettype=api_doc.rettypes.dict, + retdoc='dictionnary referencing the different' + ' named branches the snapshot contains') +def api_snapshot(request, snapshot_id): + """Get information about a snapshot. + + A snapshot is a set of named branches, which are pointers to objects at any + level of the Software Heritage DAG. It represents a full picture of an + origin at a given time. + + As well as pointing to other objects in the Software Heritage DAG, branches + can also be aliases, in which case their target is the name of another + branch in the same snapshot, or dangling, in which case the target is + unknown. + + A snapshot identifier is a salted sha1. See the `documentation + `_ + for details about how they are computed. + """ + + def _enrich_snapshot(snapshot): + s = snapshot.copy() + if 'branches' in s: + s['branches'] = { + k: utils.enrich_object(v) + for k, v in s['branches'].items() + } + return s + + return api_lookup( + service.lookup_snapshot, snapshot_id, + notfound_msg='Snapshot with id {} not found.'.format(snapshot_id), + enrich_fn=_enrich_snapshot) diff --git a/swh/web/common/converters.py b/swh/web/common/converters.py index 2cb76cde..01eeb911 100644 --- a/swh/web/common/converters.py +++ b/swh/web/common/converters.py @@ -1,342 +1,360 @@ # Copyright (C) 2015-2018 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 import datetime import json from swh.model import hashutil from swh.core.utils import decode_with_escape from swh.web.api import utils def _group_checksums(data): """Groups checksums values computed from hash functions used in swh and stored in data dict under a single entry 'checksums' """ if data: checksums = {} for hash in hashutil.ALGORITHMS: if hash in data and data[hash]: checksums[hash] = data[hash] del data[hash] if len(checksums) > 0: data['checksums'] = checksums def from_swh(dict_swh, hashess={}, bytess={}, dates={}, blacklist={}, removables_if_empty={}, empty_dict={}, empty_list={}, convert={}, convert_fn=lambda x: x): """Convert from an swh dictionary to something reasonably json serializable. Args: dict_swh: the origin dictionary needed to be transformed hashess: list/set of keys representing hashes values (sha1, sha256, sha1_git, etc...) as bytes. Those need to be transformed in hexadecimal string bytess: list/set of keys representing bytes values which needs to be decoded blacklist: set of keys to filter out from the conversion convert: set of keys whose associated values need to be converted using convert_fn convert_fn: the conversion function to apply on the value of key in 'convert' The remaining keys are copied as is in the output. Returns: dictionary equivalent as dict_swh only with its keys converted. """ def convert_hashes_bytes(v): """v is supposedly a hash as bytes, returns it converted in hex. """ if isinstance(v, bytes): return hashutil.hash_to_hex(v) return v def convert_bytes(v): """v is supposedly a bytes string, decode as utf-8. FIXME: Improve decoding policy. If not utf-8, break! """ if isinstance(v, bytes): return v.decode('utf-8') return v def convert_date(v): """ Args: v (dict or datatime): either: - a dict with three keys: - timestamp (dict or integer timestamp) - offset - negative_utc - or, a datetime We convert it to a human-readable string """ if isinstance(v, datetime.datetime): return v.isoformat() tz = datetime.timezone(datetime.timedelta(minutes=v['offset'])) swh_timestamp = v['timestamp'] if isinstance(swh_timestamp, dict): date = datetime.datetime.fromtimestamp( swh_timestamp['seconds'], tz=tz) else: date = datetime.datetime.fromtimestamp( swh_timestamp, tz=tz) datestr = date.isoformat() if v['offset'] == 0 and v['negative_utc']: # remove the rightmost + and replace it with a - return '-'.join(datestr.rsplit('+', 1)) return datestr if not dict_swh: return dict_swh new_dict = {} for key, value in dict_swh.items(): if key in blacklist or (key in removables_if_empty and not value): continue if key in dates: new_dict[key] = convert_date(value) elif key in convert: new_dict[key] = convert_fn(value) elif isinstance(value, dict): new_dict[key] = from_swh(value, hashess=hashess, bytess=bytess, dates=dates, blacklist=blacklist, removables_if_empty=removables_if_empty, empty_dict=empty_dict, empty_list=empty_list, convert=convert, convert_fn=convert_fn) elif key in hashess: new_dict[key] = utils.fmap(convert_hashes_bytes, value) elif key in bytess: try: new_dict[key] = utils.fmap(convert_bytes, value) except UnicodeDecodeError: if 'decoding_failures' not in new_dict: new_dict['decoding_failures'] = [key] else: new_dict['decoding_failures'].append(key) new_dict[key] = utils.fmap(decode_with_escape, value) elif key in empty_dict and not value: new_dict[key] = {} elif key in empty_list and not value: new_dict[key] = [] else: new_dict[key] = value _group_checksums(new_dict) return new_dict def from_provenance(provenance): """Convert from a provenance information to a provenance dictionary. Args: provenance (dict): Dictionary with the following keys: - content (sha1_git): the content's identifier - revision (sha1_git): the revision the content was seen - origin (int): the origin the content was seen - visit (int): the visit it occurred - path (bytes): the path the content was seen at """ return from_swh(provenance, hashess={'content', 'revision'}, bytess={'path'}) def from_origin(origin): """Convert from an SWH origin to an origin dictionary. """ return from_swh(origin, removables_if_empty={'lister', 'project'}) def from_release(release): """Convert from an SWH release to a json serializable release dictionary. Args: release (dict): dictionary with keys: - id: identifier of the revision (sha1 in bytes) - revision: identifier of the revision the release points to (sha1 in bytes) comment: release's comment message (bytes) name: release's name (string) author: release's author identifier (swh's id) synthetic: the synthetic property (boolean) Returns: dict: Release dictionary with the following keys: - id: hexadecimal sha1 (string) - revision: hexadecimal sha1 (string) - comment: release's comment message (string) - name: release's name (string) - author: release's author identifier (swh's id) - synthetic: the synthetic property (boolean) """ return from_swh( release, hashess={'id', 'target'}, bytess={'message', 'name', 'fullname', 'email'}, dates={'date'}, ) class SWHMetadataEncoder(json.JSONEncoder): """Special json encoder for metadata field which can contain bytes encoded value. """ def default(self, obj): if isinstance(obj, bytes): return obj.decode('utf-8') # Let the base class default method raise the TypeError return json.JSONEncoder.default(self, obj) def convert_revision_metadata(metadata): """Convert json specific dict to a json serializable one. """ if not metadata: return {} return json.loads(json.dumps(metadata, cls=SWHMetadataEncoder)) def from_revision(revision): """Convert from an SWH revision to a json serializable revision dictionary. Args: revision (dict): dict with keys: - id: identifier of the revision (sha1 in bytes) - directory: identifier of the directory the revision points to (sha1 in bytes) - author_name, author_email: author's revision name and email - committer_name, committer_email: committer's revision name and email - message: revision's message - date, date_offset: revision's author date - committer_date, committer_date_offset: revision's commit date - parents: list of parents for such revision - synthetic: revision's property nature - type: revision's type (git, tar or dsc at the moment) - metadata: if the revision is synthetic, this can reference dynamic properties. Returns: dict: Revision dictionary with the same keys as inputs, except: - sha1s are in hexadecimal strings (id, directory) - bytes are decoded in string (author_name, committer_name, author_email, committer_email) Remaining keys are left as is """ revision = from_swh(revision, hashess={'id', 'directory', 'parents', 'children'}, bytess={'name', 'fullname', 'email'}, convert={'metadata'}, convert_fn=convert_revision_metadata, dates={'date', 'committer_date'}) if revision: if 'parents' in revision: revision['merge'] = len(revision['parents']) > 1 if 'message' in revision: try: revision['message'] = revision['message'].decode('utf-8') except UnicodeDecodeError: revision['message_decoding_failed'] = True revision['message'] = None return revision def from_content(content): """Convert swh content to serializable content dictionary. """ return from_swh(content, hashess={'sha1', 'sha1_git', 'sha256', 'blake2s256'}, blacklist={'ctime'}, convert={'status'}, convert_fn=lambda v: 'absent' if v == 'hidden' else v) def from_person(person): """Convert swh person to serializable person dictionary. """ return from_swh(person, bytess={'name', 'fullname', 'email'}) def from_origin_visit(visit): """Convert swh origin_visit to serializable origin_visit dictionary. """ ov = from_swh(visit, hashess={'target', 'snapshot'}, bytess={'branch'}, dates={'date'}, empty_dict={'metadata'}) + # TODO: remove that piece of code once snapshot migration + # is totally effective in storage (no more occurrences) if ov and 'occurrences' in ov: ov['occurrences'] = { decode_with_escape(k): v for k, v in ov['occurrences'].items() } return ov +def from_snapshot(snapshot): + """Convert swh snapshot to serializable snapshot dictionary. + + """ + sv = from_swh(snapshot, + hashess={'id', 'target'}) + + if sv and 'branches' in sv: + sv['branches'] = { + decode_with_escape(k): v + for k, v in sv['branches'].items() + } + + return sv + + def from_directory_entry(dir_entry): """Convert swh person to serializable person dictionary. """ return from_swh(dir_entry, hashess={'dir_id', 'sha1_git', 'sha1', 'sha256', 'blake2s256', 'target'}, bytess={'name'}, removables_if_empty={ 'sha1', 'sha1_git', 'sha256', 'blake2s256', 'status'}, convert={'status'}, convert_fn=lambda v: 'absent' if v == 'hidden' else v) def from_filetype(content_entry): """Convert swh person to serializable person dictionary. """ return from_swh(content_entry, hashess={'id'}, bytess={'mimetype', 'encoding'}) diff --git a/swh/web/common/service.py b/swh/web/common/service.py index f59fdd05..b4d3bd0e 100644 --- a/swh/web/common/service.py +++ b/swh/web/common/service.py @@ -1,889 +1,904 @@ # Copyright (C) 2015-2018 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 import os from collections import defaultdict from swh.model import hashutil from swh.web.common import converters from swh.web.common import query from swh.web.common.exc import NotFoundExc from swh.web import config storage = config.storage() vault = config.vault() idx_storage = config.indexer_storage() MAX_LIMIT = 50 # Top limit the users can ask for def _first_element(l): """Returns the first element in the provided list or None if it is empty or None""" return next(iter(l 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 Returns: List of 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): """Checks if the storage contains a given content checksum Args: 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 = storage.content_find({algo: hash}) return {'found': found, 'algo': algo} def search_hash(q): """Checks if the storage contains a given content checksum Args: 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 = storage.content_find({algo: hash}) return {'found': found is not None} def lookup_content_provenance(q): """Return provenance information from a specified content. Args: q: query string of the form Yields: provenance information (dict) list if the content is found. """ algo, hash = query.parse_hash(q) provenances = storage.content_find_provenance({algo: hash}) if not provenances: return None return (converters.from_provenance(p) for p in provenances) def _lookup_content_sha1(q): """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 = 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) def lookup_content_language(q): """Return language information from a specified content. Args: q: query string of the form Yields: language information (dict) list if the content is found. """ sha1 = _lookup_content_sha1(q) if not sha1: return None lang = _first_element(list(idx_storage.content_language_get([sha1]))) if not lang: return None return converters.from_swh(lang, hashess={'id'}) 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 lang = _first_element(idx_storage.content_fossology_license_get([sha1])) if not lang: return None return converters.from_swh(lang, hashess={'id'}) def lookup_origin(origin): """Return information about the origin matching dict origin. Args: origin: origin's dict with keys either 'id' or ('type' AND 'url') Returns: origin information as dict. """ origin_info = storage.origin_get(origin) if not origin_info: if 'id' in origin and origin['id']: msg = 'Origin with id %s not found!' % origin['id'] else: msg = 'Origin of type %s and url %s not found!' % \ (origin['type'], origin['url']) raise NotFoundExc(msg) return converters.from_origin(origin_info) def search_origin(url_pattern, offset=0, limit=50, regexp=False): """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 offset: number of found origins to skip before returning results limit: the maximum number of found origins to return Returns: lisf of origin information as dict. """ origins = storage.origin_search(url_pattern, offset, limit, regexp) return map(converters.from_origin, origins) def lookup_person(person_id): """Return information about the person with id person_id. Args: person_id as string Returns: person information as dict. Raises: NotFoundExc if there is no person with the provided id. """ person = _first_element(storage.person_get([person_id])) if not person: raise NotFoundExc('Person with id %s not found' % person_id) return converters.from_person(person) def _to_sha1_bin(sha1_hex): _, sha1_git_bin = query.parse_hash_with_algorithms_or_throws( sha1_hex, ['sha1'], # HACK: sha1_git really 'Only sha1_git is supported.') return sha1_git_bin def lookup_directory(sha1_git): """Return information about the directory with id sha1_git. Args: sha1_git as string Returns: directory information as dict. """ sha1_git_bin = _to_sha1_bin(sha1_git) dir = _first_element(storage.directory_get([sha1_git_bin])) if not dir: raise NotFoundExc('Directory with sha1_git %s not found' % sha1_git) directory_entries = storage.directory_ls(sha1_git_bin) or [] return map(converters.from_directory_entry, directory_entries) def lookup_directory_with_path(directory_sha1_git, path_string): """Return directory information for entry with path path_string w.r.t. root directory pointed by directory_sha1_git Args: - directory_sha1_git: sha1_git corresponding to the directory to which we append paths to (hopefully) find the entry - the relative path to the entry starting from the directory pointed by directory_sha1_git Raises: NotFoundExc if the directory entry is not found """ sha1_git_bin = _to_sha1_bin(directory_sha1_git) paths = path_string.strip(os.path.sep).split(os.path.sep) queried_dir = storage.directory_entry_get_by_path( sha1_git_bin, list(map(lambda p: p.encode('utf-8'), paths))) if not queried_dir: raise NotFoundExc(('Directory entry with path %s from %s not found') % (path_string, directory_sha1_git)) return converters.from_directory_entry(queried_dir) def lookup_release(release_sha1_git): """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('Release with sha1_git %s not found.' % release_sha1_git) return converters.from_release(release) def lookup_release_multiple(sha1_git_list): """Return information about the revisions identified with their sha1_git identifiers. Args: sha1_git_list: A list of revision sha1_git identifiers Returns: Release 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) or [] return (converters.from_release(r) for r in releases) def lookup_revision(rev_sha1_git): """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 = _first_element(storage.revision_get([sha1_git_bin])) if not revision: raise NotFoundExc('Revision with sha1_git %s not found.' % rev_sha1_git) return converters.from_revision(revision) def lookup_revision_multiple(sha1_git_list): """Return information about the revisions identified with their sha1_git identifiers. Args: sha1_git_list: A list of revision sha1_git identifiers Returns: Generator of revisions 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) revisions = storage.revision_get(sha1_bin_list) or [] return (converters.from_revision(r) for r in revisions) def lookup_revision_message(rev_sha1_git): """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 = _first_element(storage.revision_get([sha1_git_bin])) if not revision: raise NotFoundExc('Revision with sha1_git %s not found.' % rev_sha1_git) if 'message' not in revision: raise NotFoundExc('No message for revision with sha1_git %s.' % rev_sha1_git) res = {'message': revision['message']} return res def lookup_revision_by(origin_id, branch_name="refs/heads/master", timestamp=None): """Lookup revisions by origin_id, branch_name and timestamp. If: - branch_name is not provided, lookup using 'refs/heads/master' as default. - ts is not provided, use the most recent Args: - origin_id: origin of the revision. - branch_name: revision's branch. - timestamp: revision's time frame. Yields: The revisions matching the criterions. Raises: NotFoundExc if no revision corresponds to the criterion """ res = _first_element(storage.revision_get_by(origin_id, branch_name, timestamp=timestamp, limit=1)) if not res: raise NotFoundExc('Revision for origin %s and branch %s not found.' % (origin_id, branch_name)) return converters.from_revision(res) def lookup_revision_log(rev_sha1_git, limit): """Return information about the revision with sha1 revision_sha1_git. Args: revision_sha1_git: The revision's sha1 as hexadecimal limit: the maximum number of revisions returned 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_entries = storage.revision_log([sha1_git_bin], limit) if not revision_entries: raise NotFoundExc('Revision with sha1_git %s not found.' % rev_sha1_git) return map(converters.from_revision, revision_entries) def lookup_revision_log_by(origin_id, branch_name, timestamp, limit): """Return information about the revision with sha1 revision_sha1_git. Args: origin_id: origin of the revision branch_name: revision's branch timestamp: revision's time frame limit: the maximum number of revisions returned Returns: Revision information as dict. Raises: NotFoundExc if no revision corresponds to the criterion """ revision_entries = storage.revision_log_by(origin_id, branch_name, timestamp, limit=limit) if not revision_entries: return None return map(converters.from_revision, revision_entries) def lookup_revision_with_context_by(origin_id, branch_name, ts, 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_id, branch_name and ts. In other words, sha1_git is an ancestor of sha1_git_root. Args: - origin_id: 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 = _first_element(storage.revision_get_by(origin_id, branch_name, timestamp=ts, limit=1)) if not rev_root: raise NotFoundExc('Revision with (origin_id: %s, branch_name: %s' ', ts: %s) not found.' % (origin_id, branch_name, ts)) return (converters.from_revision(rev_root), lookup_revision_with_context(rev_root, sha1_git, limit)) def lookup_revision_with_context(sha1_git_root, sha1_git, limit=100): """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 = _first_element(storage.revision_get([sha1_git_bin])) if not revision: raise NotFoundExc('Revision %s not found' % sha1_git) if isinstance(sha1_git_root, str): sha1_git_root_bin = _to_sha1_bin(sha1_git_root) revision_root = _first_element(storage.revision_get([sha1_git_root_bin])) # noqa if not revision_root: raise NotFoundExc('Revision root %s not found' % sha1_git_root) else: sha1_git_root_bin = sha1_git_root['id'] revision_log = storage.revision_log([sha1_git_root_bin], limit) parents = {} 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('Revision %s is not an ancestor of %s' % (sha1_git, sha1_git_root)) revision['children'] = children[revision['id']] return converters.from_revision(revision) 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 = _first_element(storage.revision_get([sha1_git_bin])) if not revision: raise NotFoundExc('Revision %s not found' % sha1_git) 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': map(converters.from_directory_entry, directory_entries)} elif entity['type'] == 'file': # content content = storage.content_find({'sha1_git': entity['target']}) if with_data: c = _first_element(storage.content_get([content['sha1']])) content['data'] = c['data'] return {'type': 'file', 'path': '.' if not dir_path else dir_path, 'revision': sha1_git, 'content': converters.from_content(content)} else: raise NotImplementedError('Entity of type %s not implemented.' % entity['type']) def lookup_content(q): """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 = storage.content_find({algo: hash}) if not c: raise NotFoundExc('Content with %s checksum equals to %s not found!' % (algo, hashutil.hash_to_hex(hash))) return converters.from_content(c) def lookup_content_raw(q): """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 = _first_element(storage.content_get([c['checksums']['sha1']])) if not content: algo, hash = query.parse_hash(q) raise NotFoundExc('Bytes of content with %s checksum equals to %s ' 'not available in SWH storage!' % (algo, hashutil.hash_to_hex(hash))) return converters.from_content(content) def stat_counters(): """Return the stat counters for Software Heritage Returns: A dict mapping textual labels to integer values. """ return storage.stat_counters() def _lookup_origin_visits(origin_id, last_visit=None, limit=10): """Yields the origin origin_ids' visits. Args: origin_id (int): origin to list visits for last_visit (int): last visit to lookup from limit (int): Number of elements max to display Yields: Dictionaries of origin_visit for that origin """ limit = min(limit, MAX_LIMIT) yield from storage.origin_visit_get( origin_id, last_visit=last_visit, limit=limit) def lookup_origin_visits(origin_id, last_visit=None, per_page=10): """Yields the origin origin_ids' visits. Args: origin_id: origin to list visits for Yields: Dictionaries of origin_visit for that origin """ visits = _lookup_origin_visits(origin_id, last_visit=last_visit, limit=per_page) for visit in visits: yield converters.from_origin_visit(visit) def lookup_origin_visit(origin_id, visit_id): """Return information about visit visit_id with origin origin_id. Args: origin_id: origin concerned by the visit visit_id: the visit identifier to lookup Yields: The dict origin_visit concerned """ visit = storage.origin_visit_get_by(origin_id, visit_id) if not visit: raise NotFoundExc('Origin with id %s or its visit ' 'with id %s not found!' % (origin_id, visit_id)) return converters.from_origin_visit(visit) +def lookup_snapshot(snapshot_id): + """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 + + Returns: + A dict filled with the snapshot content. + """ + snapshot_id_bin = _to_sha1_bin(snapshot_id) + snapshot = storage.snapshot_get(snapshot_id_bin) + return converters.from_snapshot(snapshot) + + def lookup_entity_by_uuid(uuid): """Return the entity's hierarchy from its uuid. Args: uuid: entity's identifier. Returns: List of hierarchy entities from the entity with uuid. """ uuid = query.parse_uuid4(uuid) for entity in storage.entity_get(uuid): entity = converters.from_swh(entity, convert={'last_seen', 'uuid'}, convert_fn=lambda x: str(x)) yield entity 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_id, branch_name, ts, sha1_git - origin_id, branch_name, ts - sha1_git_root, sha1_git - sha1_git Returns: None if the revision is not found or the actual revision. """ if 'origin_id' in revision and \ 'branch_name' in revision and \ 'ts' in revision and \ 'sha1_git' in revision: return lookup_revision_with_context_by(revision['origin_id'], revision['branch_name'], revision['ts'], revision['sha1_git'], limit) if 'origin_id' in revision and \ 'branch_name' in revision and \ 'ts' in revision: return lookup_revision_by(revision['origin_id'], 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_cook(obj_type, obj_id, email=None): """Cook a vault bundle. """ return vault.cook(obj_type, obj_id, email=email) def vault_fetch(obj_type, obj_id): """Fetch a vault bundle. """ return vault.fetch(obj_type, obj_id) def vault_progress(obj_type, obj_id): """Get the current progress of a vault bundle. """ return vault.progress(obj_type, obj_id) diff --git a/swh/web/tests/api/views/test_origin.py b/swh/web/tests/api/views/test_origin.py index 36b23721..5190466a 100644 --- a/swh/web/tests/api/views/test_origin.py +++ b/swh/web/tests/api/views/test_origin.py @@ -1,250 +1,259 @@ # Copyright (C) 2015-2018 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 nose.tools import istest from rest_framework.test import APITestCase from unittest.mock import patch from swh.storage.exc import StorageDBError, StorageAPIError from swh.web.tests.testbase import SWHWebTestBase class OriginApiTestCase(SWHWebTestBase, APITestCase): def setUp(self): self.origin_visit1 = { 'date': 1104616800.0, 'origin': 10, 'visit': 100, 'metadata': None, 'status': 'full', } self.origin1 = { 'id': 1234, 'lister': 'uuid-lister-0', 'project': 'uuid-project-0', 'url': 'ftp://some/url/to/origin/0', 'type': 'ftp' } @patch('swh.web.api.views.origin.service') @istest def api_1_lookup_origin_visits_raise_error(self, mock_service): # given mock_service.lookup_origin_visits.side_effect = ValueError( 'voluntary error to check the bad request middleware.') # when rv = self.client.get('/api/1/origin/2/visits/') # then self.assertEquals(rv.status_code, 400) self.assertEquals(rv['Content-Type'], 'application/json') self.assertEquals(rv.data, { 'exception': 'ValueError', 'reason': 'voluntary error to check the bad request middleware.'}) @patch('swh.web.api.views.origin.service') @istest def api_1_lookup_origin_visits_raise_swh_storage_error_db( self, mock_service): # given mock_service.lookup_origin_visits.side_effect = StorageDBError( 'SWH Storage exploded! Will be back online shortly!') # when rv = self.client.get('/api/1/origin/2/visits/') # then self.assertEquals(rv.status_code, 503) self.assertEquals(rv['Content-Type'], 'application/json') self.assertEquals(rv.data, { 'exception': 'StorageDBError', 'reason': 'An unexpected error occurred in the backend: ' 'SWH Storage exploded! Will be back online shortly!'}) @patch('swh.web.api.views.origin.service') @istest def api_1_lookup_origin_visits_raise_swh_storage_error_api( self, mock_service): # given mock_service.lookup_origin_visits.side_effect = StorageAPIError( 'SWH Storage API dropped dead! Will resurrect from its ashes asap!' ) # when rv = self.client.get('/api/1/origin/2/visits/') # then self.assertEquals(rv.status_code, 503) self.assertEquals(rv['Content-Type'], 'application/json') self.assertEquals(rv.data, { 'exception': 'StorageAPIError', 'reason': 'An unexpected error occurred in the api backend: ' 'SWH Storage API dropped dead! Will resurrect from its ashes asap!' }) @patch('swh.web.api.views.origin.service') @istest def api_1_lookup_origin_visits(self, mock_service): # given stub_visits = [ { 'date': 1293919200.0, 'origin': 2, + 'snapshot': '1234', 'visit': 2 }, { 'date': 1420149600.0, 'origin': 2, + 'snapshot': '5678', 'visit': 3 } ] mock_service.lookup_origin_visits.return_value = stub_visits # when rv = self.client.get('/api/1/origin/2/visits/?per_page=2&last_visit=1') self.assertEquals(rv.status_code, 200) self.assertEquals(rv['Content-Type'], 'application/json') self.assertEquals(rv.data, [ { 'date': 1293919200.0, 'origin': 2, + 'snapshot': '1234', 'visit': 2, 'origin_visit_url': '/api/1/origin/2/visit/2/', + 'snapshot_url': '/api/1/snapshot/1234/' }, { 'date': 1420149600.0, 'origin': 2, + 'snapshot': '5678', 'visit': 3, 'origin_visit_url': '/api/1/origin/2/visit/3/', + 'snapshot_url': '/api/1/snapshot/5678/' } ]) mock_service.lookup_origin_visits.assert_called_once_with( '2', last_visit=1, per_page=2) @patch('swh.web.api.views.origin.service') @istest def api_1_lookup_origin_visit(self, mock_service): # given origin_visit = self.origin_visit1.copy() origin_visit.update({ 'occurrences': { 'master': { 'target_type': 'revision', 'target': '98564', } - } + }, + 'snapshot': '57478754' }) mock_service.lookup_origin_visit.return_value = origin_visit expected_origin_visit = self.origin_visit1.copy() expected_origin_visit.update({ 'origin_url': '/api/1/origin/10/', 'occurrences': { 'master': { 'target_type': 'revision', 'target': '98564', 'target_url': '/api/1/revision/98564/' } - } + }, + 'snapshot': '57478754', + 'snapshot_url': '/api/1/snapshot/57478754/' }) # when rv = self.client.get('/api/1/origin/10/visit/100/') self.assertEquals(rv.status_code, 200) self.assertEquals(rv['Content-Type'], 'application/json') self.assertEquals(rv.data, expected_origin_visit) mock_service.lookup_origin_visit.assert_called_once_with('10', '100') @patch('swh.web.api.views.origin.service') @istest def api_1_lookup_origin_visit_not_found(self, mock_service): # given mock_service.lookup_origin_visit.return_value = None # when rv = self.client.get('/api/1/origin/1/visit/1000/') self.assertEquals(rv.status_code, 404) self.assertEquals(rv['Content-Type'], 'application/json') self.assertEquals(rv.data, { 'exception': 'NotFoundExc', 'reason': 'No visit 1000 for origin 1 found' }) mock_service.lookup_origin_visit.assert_called_once_with('1', '1000') @patch('swh.web.api.views.origin.service') @istest def api_origin_by_id(self, mock_service): # given mock_service.lookup_origin.return_value = self.origin1 expected_origin = self.origin1.copy() expected_origin.update({ 'origin_visits_url': '/api/1/origin/1234/visits/' }) # when rv = self.client.get('/api/1/origin/1234/') # then self.assertEquals(rv.status_code, 200) self.assertEquals(rv['Content-Type'], 'application/json') self.assertEquals(rv.data, expected_origin) mock_service.lookup_origin.assert_called_with({'id': '1234'}) @patch('swh.web.api.views.origin.service') @istest def api_origin_by_type_url(self, mock_service): # given stub_origin = self.origin1.copy() stub_origin.update({ 'id': 987 }) mock_service.lookup_origin.return_value = stub_origin expected_origin = stub_origin.copy() expected_origin.update({ 'origin_visits_url': '/api/1/origin/987/visits/' }) # when rv = self.client.get('/api/1/origin/ftp/url' '/ftp://some/url/to/origin/0/') # then self.assertEquals(rv.status_code, 200) self.assertEquals(rv['Content-Type'], 'application/json') self.assertEquals(rv.data, expected_origin) mock_service.lookup_origin.assert_called_with( {'url': 'ftp://some/url/to/origin/0/', 'type': 'ftp'}) @patch('swh.web.api.views.origin.service') @istest def api_origin_not_found(self, mock_service): # given mock_service.lookup_origin.return_value = None # when rv = self.client.get('/api/1/origin/4321/') # then self.assertEquals(rv.status_code, 404) self.assertEquals(rv['Content-Type'], 'application/json') self.assertEquals(rv.data, { 'exception': 'NotFoundExc', 'reason': 'Origin with id 4321 not found.' }) mock_service.lookup_origin.assert_called_with({'id': '4321'})