diff --git a/swh/web/browse/utils.py b/swh/web/browse/utils.py index 604d4ea9..7e753153 100644 --- a/swh/web/browse/utils.py +++ b/swh/web/browse/utils.py @@ -1,1173 +1,1178 @@ # Copyright (C) 2017-2018 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 base64 from collections import defaultdict import magic import math import pypandoc import stat import textwrap from django.core.cache import cache from django.utils.safestring import mark_safe from importlib import reload from swh.model.identifiers import persistent_identifier from swh.web.common import highlightjs, service from swh.web.common.exc import NotFoundExc, http_status_code_message from swh.web.common.utils import ( reverse, format_utc_iso_date, parse_timestamp, get_origin_visits, get_swh_persistent_id, swh_object_icons ) from swh.web.config import get_config def get_directory_entries(sha1_git): """Function that retrieves the content of a directory from the archive. The directories entries are first sorted in lexicographical order. Sub-directories and regular files are then extracted. Args: sha1_git: sha1_git identifier of the directory Returns: A tuple whose first member corresponds to the sub-directories list and second member the regular files list Raises: NotFoundExc if the directory is not found """ cache_entry_id = 'directory_entries_%s' % sha1_git cache_entry = cache.get(cache_entry_id) if cache_entry: return cache_entry entries = list(service.lookup_directory(sha1_git)) for e in entries: e['perms'] = stat.filemode(e['perms']) if e['type'] == 'rev': # modify dir entry name to explicitly show it points # to a revision e['name'] = '%s @ %s' % (e['name'], e['target'][:7]) dirs = [e for e in entries if e['type'] in ('dir', 'rev')] files = [e for e in entries if e['type'] == 'file'] dirs = sorted(dirs, key=lambda d: d['name']) files = sorted(files, key=lambda f: f['name']) cache.set(cache_entry_id, (dirs, files)) return dirs, files def get_mimetype_and_encoding_for_content(content): """Function that returns the mime type and the encoding associated to a content buffer using the magic module under the hood. Args: content (bytes): a content buffer Returns: A tuple (mimetype, encoding), for instance ('text/plain', 'us-ascii'), associated to the provided content. """ while True: try: magic_result = magic.detect_from_content(content) mime_type = magic_result.mime_type encoding = magic_result.encoding break except Exception: # workaround an issue with the magic module who can fail # if detect_from_content is called multiple times in # a short amount of time reload(magic) return mime_type, encoding # maximum authorized content size in bytes for HTML display # with code highlighting content_display_max_size = get_config()['content_display_max_size'] snapshot_content_max_size = get_config()['snapshot_content_max_size'] def request_content(query_string, max_size=content_display_max_size, raise_if_unavailable=True, reencode=True): """Function that retrieves a content from the archive. Raw bytes content is first retrieved, then the content mime type. If the mime type is not stored in the archive, it will be computed using Python magic module. Args: query_string: a string of the form "[ALGO_HASH:]HASH" where optional ALGO_HASH can be either ``sha1``, ``sha1_git``, ``sha256``, or ``blake2s256`` (default to ``sha1``) and HASH the hexadecimal representation of the hash value max_size: the maximum size for a content to retrieve (default to 1MB, no size limit if None) Returns: A tuple whose first member corresponds to the content raw bytes and second member the content mime type Raises: NotFoundExc if the content is not found """ content_data = service.lookup_content(query_string) filetype = None language = None license = None # requests to the indexer db may fail so properly handle # those cases in order to avoid content display errors try: filetype = service.lookup_content_filetype(query_string) language = service.lookup_content_language(query_string) license = service.lookup_content_license(query_string) except Exception: pass mimetype = 'unknown' encoding = 'unknown' if filetype: mimetype = filetype['mimetype'] encoding = filetype['encoding'] + # workaround when encountering corrupted data due to implicit + # conversion from bytea to text in the indexer db (see T818) + # TODO: Remove that code when all data have been correctly converted + if mimetype.startswith('\\'): + filetype = None content_data['error_code'] = 200 content_data['error_message'] = '' content_data['error_description'] = '' if not max_size or content_data['length'] < max_size: try: content_raw = service.lookup_content_raw(query_string) except Exception as e: if raise_if_unavailable: raise e else: content_data['raw_data'] = None content_data['error_code'] = 404 content_data['error_description'] = \ 'The bytes of the content are currently not available in the archive.' # noqa content_data['error_message'] = \ http_status_code_message[content_data['error_code']] else: content_data['raw_data'] = content_raw['data'] if not filetype: mimetype, encoding = \ get_mimetype_and_encoding_for_content(content_data['raw_data']) # noqa # encode textual content to utf-8 if needed if reencode and mimetype.startswith('text/'): # probably a malformed UTF-8 content, re-encode it # by replacing invalid chars with a substitution one if encoding == 'unknown-8bit': content_data['raw_data'] = \ content_data['raw_data'].decode('utf-8', 'replace')\ .encode('utf-8') elif 'ascii' not in encoding and encoding not in ['utf-8', 'binary']: # noqa content_data['raw_data'] = \ content_data['raw_data'].decode(encoding, 'replace')\ .encode('utf-8') elif reencode and mimetype.startswith('application/octet-stream'): # file may detect a text content as binary # so try to decode it for display encodings = ['us-ascii'] encodings += ['iso-8859-%s' % i for i in range(1, 17)] for encoding in encodings: try: content_data['raw_data'] = \ content_data['raw_data'].decode(encoding)\ .encode('utf-8') except Exception: pass else: # ensure display in content view mimetype = 'text/plain' break else: content_data['raw_data'] = None content_data['mimetype'] = mimetype content_data['encoding'] = encoding if language: content_data['language'] = language['lang'] else: content_data['language'] = 'not detected' if license: content_data['licenses'] = ', '.join(license['facts'][0]['licenses']) else: content_data['licenses'] = 'not detected' return content_data _browsers_supported_image_mimes = set(['image/gif', 'image/png', 'image/jpeg', 'image/bmp', 'image/webp', 'image/svg', 'image/svg+xml']) def prepare_content_for_display(content_data, mime_type, path): """Function that prepares a content for HTML display. The function tries to associate a programming language to a content in order to perform syntax highlighting client-side using highlightjs. The language is determined using either the content filename or its mime type. If the mime type corresponds to an image format supported by web browsers, the content will be encoded in base64 for displaying the image. Args: content_data (bytes): raw bytes of the content mime_type (string): mime type of the content path (string): path of the content including filename Returns: A dict containing the content bytes (possibly different from the one provided as parameter if it is an image) under the key 'content_data and the corresponding highlightjs language class under the key 'language'. """ language = highlightjs.get_hljs_language_from_filename(path) if not language: language = highlightjs.get_hljs_language_from_mime_type(mime_type) if not language: language = 'nohighlight' elif mime_type.startswith('application/'): mime_type = mime_type.replace('application/', 'text/') if mime_type.startswith('image/'): if mime_type in _browsers_supported_image_mimes: content_data = base64.b64encode(content_data) else: content_data = None if mime_type.startswith('image/svg'): mime_type = 'image/svg+xml' return {'content_data': content_data, 'language': language, 'mimetype': mime_type} def get_origin_visit(origin_info, visit_ts=None, visit_id=None, snapshot_id=None): """Function that returns information about a visit for a given origin. The visit is retrieved from a provided timestamp. The closest visit from that timestamp is selected. Args: origin_info (dict): a dict filled with origin information (id, url, type) visit_ts (int or str): an ISO date string or Unix timestamp to parse Returns: A dict containing the visit info as described below:: {'origin': 2, 'date': '2017-10-08T11:54:25.582463+00:00', 'metadata': {}, 'visit': 25, 'status': 'full'} """ visits = get_origin_visits(origin_info) if not visits: raise NotFoundExc('No visit associated to origin with' ' type %s and url %s!' % (origin_info['type'], origin_info['url'])) if snapshot_id: visit = [v for v in visits if v['snapshot'] == snapshot_id] if len(visit) == 0: raise NotFoundExc( 'Visit for snapshot with id %s for origin with type %s' ' and url %s not found!' % (snapshot_id, origin_info['type'], origin_info['url'])) return visit[0] if visit_id: visit = [v for v in visits if v['visit'] == int(visit_id)] if len(visit) == 0: raise NotFoundExc( 'Visit with id %s for origin with type %s' ' and url %s not found!' % (visit_id, origin_info['type'], origin_info['url'])) return visit[0] if not visit_ts: # returns the latest full visit when no timestamp is provided for v in reversed(visits): if v['status'] == 'full': return v return visits[-1] parsed_visit_ts = math.floor(parse_timestamp(visit_ts).timestamp()) visit_idx = None for i, visit in enumerate(visits): ts = math.floor(parse_timestamp(visit['date']).timestamp()) if i == 0 and parsed_visit_ts <= ts: return visit elif i == len(visits) - 1: if parsed_visit_ts >= ts: return visit else: next_ts = math.floor( parse_timestamp(visits[i+1]['date']).timestamp()) if parsed_visit_ts >= ts and parsed_visit_ts < next_ts: if (parsed_visit_ts - ts) < (next_ts - parsed_visit_ts): visit_idx = i break else: visit_idx = i+1 break if visit_idx is not None: visit = visits[visit_idx] while visit_idx < len(visits) - 1 and \ visit['date'] == visits[visit_idx+1]['date']: visit_idx = visit_idx + 1 visit = visits[visit_idx] return visit else: raise NotFoundExc( 'Visit with timestamp %s for origin with type %s and url %s not found!' % # noqa (visit_ts, origin_info['type'], origin_info['url'])) def process_snapshot_branches(snapshot_branches): """ Process a dictionary describing snapshot branches: extract those targeting revisions and releases, put them in two different lists, then sort those lists in lexicographical order of the branches' names. Args: snapshot_branches (dict): A dict describing the branches of a snapshot as returned for instance by :func:`swh.web.common.service.lookup_snapshot` Returns: tuple: A tuple whose first member is the sorted list of branches targeting revisions and second member the sorted list of branches targeting releases """ # noqa branches = {} releases = {} revision_to_branch = defaultdict(set) revision_to_release = defaultdict(set) release_to_branch = defaultdict(set) for branch_name, target in snapshot_branches.items(): if not target: # FIXME: display branches with an unknown target anyway continue target_id = target['target'] target_type = target['target_type'] if target_type == 'revision': branches[branch_name] = { 'name': branch_name, 'revision': target_id, } revision_to_branch[target_id].add(branch_name) elif target_type == 'release': release_to_branch[target_id].add(branch_name) # FIXME: handle pointers to other object types # FIXME: handle branch aliases releases_info = service.lookup_release_multiple( release_to_branch.keys() ) for release in releases_info: branches_to_update = release_to_branch[release['id']] for branch in branches_to_update: releases[branch] = { 'name': release['name'], 'branch_name': branch, 'date': format_utc_iso_date(release['date']), 'id': release['id'], 'message': release['message'], 'target_type': release['target_type'], 'target': release['target'], } if release['target_type'] == 'revision': revision_to_release[release['target']].update( branches_to_update ) revisions = service.lookup_revision_multiple( set(revision_to_branch.keys()) | set(revision_to_release.keys()) ) for revision in revisions: if not revision: continue revision_data = { 'directory': revision['directory'], 'date': format_utc_iso_date(revision['date']), 'message': revision['message'], } for branch in revision_to_branch[revision['id']]: branches[branch].update(revision_data) for release in revision_to_release[revision['id']]: releases[release]['directory'] = revision['directory'] ret_branches = list(sorted(branches.values(), key=lambda b: b['name'])) ret_releases = list(sorted(releases.values(), key=lambda b: b['name'])) return ret_branches, ret_releases def get_snapshot_content(snapshot_id): """Returns the lists of branches and releases associated to a swh snapshot. That list is put in cache in order to speedup the navigation in the swh-web/browse ui. .. warning:: At most 1000 branches contained in the snapshot will be returned for performance reasons. Args: snapshot_id (str): hexadecimal representation of the snapshot identifier Returns: A tuple with two members. The first one is a list of dict describing the snapshot branches. The second one is a list of dict describing the snapshot releases. Raises: NotFoundExc if the snapshot does not exist """ cache_entry_id = 'swh_snapshot_%s' % snapshot_id cache_entry = cache.get(cache_entry_id) if cache_entry: return cache_entry['branches'], cache_entry['releases'] branches = [] releases = [] if snapshot_id: snapshot = service.lookup_snapshot( snapshot_id, branches_count=snapshot_content_max_size) branches, releases = process_snapshot_branches(snapshot['branches']) cache.set(cache_entry_id, { 'branches': branches, 'releases': releases, }) return branches, releases def get_origin_visit_snapshot(origin_info, visit_ts=None, visit_id=None, snapshot_id=None): """Returns the lists of branches and releases associated to a swh origin for a given visit. The visit is expressed by a timestamp. In the latter case, the closest visit from the provided timestamp will be used. If no visit parameter is provided, it returns the list of branches found for the latest visit. That list is put in cache in order to speedup the navigation in the swh-web/browse ui. .. warning:: At most 1000 branches contained in the snapshot will be returned for performance reasons. Args: origin_info (dict): a dict filled with origin information (id, url, type) visit_ts (int or str): an ISO date string or Unix timestamp to parse visit_id (int): optional visit id for disambiguation in case several visits have the same timestamp Returns: A tuple with two members. The first one is a list of dict describing the origin branches for the given visit. The second one is a list of dict describing the origin releases for the given visit. Raises: NotFoundExc if the origin or its visit are not found """ visit_info = get_origin_visit(origin_info, visit_ts, visit_id, snapshot_id) return get_snapshot_content(visit_info['snapshot']) def gen_link(url, link_text=None, link_attrs={}): """ Utility function for generating an HTML link to insert in Django templates. Args: url (str): an url link_text (str): optional text for the produced link, if not provided the url will be used link_attrs (dict): optional attributes (e.g. class) to add to the link Returns: An HTML link in the form 'link_text' """ attrs = ' ' for k, v in link_attrs.items(): attrs += '%s="%s" ' % (k, v) if not link_text: link_text = url link = '%s' % (attrs, url, link_text) return mark_safe(link) def gen_person_link(person_id, person_name, snapshot_context=None, link_attrs={}): """ Utility function for generating a link to a person HTML view to insert in Django templates. Args: person_id (int): a person id person_name (str): the associated person name link_attrs (dict): optional attributes (e.g. class) to add to the link Returns: An HTML link in the form 'person_name' """ query_params = None if snapshot_context and snapshot_context['origin_info']: origin_info = snapshot_context['origin_info'] query_params = {'origin_type': origin_info['type'], 'origin': origin_info['url']} if 'timestamp' in snapshot_context['url_args']: query_params['timestamp'] = \ snapshot_context['url_args']['timestamp'] if 'visit_id' in snapshot_context['query_params']: query_params['visit_id'] = \ snapshot_context['query_params']['visit_id'] elif snapshot_context: query_params = {'snapshot_id': snapshot_context['snapshot_id']} person_url = reverse('browse-person', url_args={'person_id': person_id}, query_params=query_params) return gen_link(person_url, person_name or 'None', link_attrs) def gen_revision_url(revision_id, snapshot_context=None): """ Utility function for generating an url to a revision. Args: revision_id (str): a revision id snapshot_context (dict): if provided, generate snapshot-dependent browsing url Returns: str: The url to browse the revision """ query_params = None if snapshot_context and snapshot_context['origin_info']: origin_info = snapshot_context['origin_info'] origin_type = snapshot_context['origin_type'] query_params = {'origin_type': origin_type, 'origin': origin_info['url']} if 'timestamp' in snapshot_context['url_args']: query_params['timestamp'] = \ snapshot_context['url_args']['timestamp'] if 'visit_id' in snapshot_context['query_params']: query_params['visit_id'] = \ snapshot_context['query_params']['visit_id'] elif snapshot_context: query_params = {'snapshot_id': snapshot_context['snapshot_id']} return reverse('browse-revision', url_args={'sha1_git': revision_id}, query_params=query_params) def gen_revision_link(revision_id, shorten_id=False, snapshot_context=None, link_text=None, link_attrs={}): """ Utility function for generating a link to a revision HTML view to insert in Django templates. Args: revision_id (str): a revision id shorten_id (boolean): whether to shorten the revision id to 7 characters for the link text snapshot_context (dict): if provided, generate snapshot-dependent browsing link link_attrs (dict): optional attributes (e.g. class) to add to the link Returns: str: An HTML link in the form 'revision_id' """ if not revision_id: return None revision_url = gen_revision_url(revision_id, snapshot_context) if shorten_id: return gen_link(revision_url, revision_id[:7], link_attrs) else: if not link_text: link_text = revision_id return gen_link(revision_url, link_text, link_attrs) def gen_origin_link(origin_info, link_attrs={}): """ Utility function for generating a link to a software origin HTML view to insert in Django templates. Args: origin_info (dict): a dict filled with origin information (id, type, url) link_attrs (dict): optional attributes (e.g. class) to add to the link Returns: An HTML link in the form 'Origin: origin_url' """ # noqa origin_browse_url = reverse('browse-origin', url_args={'origin_type': origin_info['type'], 'origin_url': origin_info['url']}) return gen_link(origin_browse_url, 'Origin: ' + origin_info['url'], link_attrs) def gen_directory_link(sha1_git, link_text=None, link_attrs={}): """ Utility function for generating a link to a directory HTML view to insert in Django templates. Args: sha1_git (str): directory identifier link_text (str): optional text for the generated link (the generated url will be used by default) link_attrs (dict): optional attributes (e.g. class) to add to the link Returns: An HTML link in the form 'link_text' """ if not sha1_git: return None directory_url = reverse('browse-directory', url_args={'sha1_git': sha1_git}) if not link_text: link_text = directory_url return gen_link(directory_url, link_text, link_attrs) def gen_snapshot_link(snapshot_id, link_text=None, link_attrs={}): """ Utility function for generating a link to a snapshot HTML view to insert in Django templates. Args: snapshot_id (str): snapshot identifier link_text (str): optional text for the generated link (the generated url will be used by default) link_attrs (dict): optional attributes (e.g. class) to add to the link Returns: An HTML link in the form 'link_text' """ snapshot_url = reverse('browse-snapshot', url_args={'snapshot_id': snapshot_id}) if not link_text: link_text = snapshot_url return gen_link(snapshot_url, link_text, link_attrs) def gen_snapshot_directory_link(snapshot_context, revision_id=None, link_text=None, link_attrs={}): """ Utility function for generating a link to a directory HTML view in the context of a snapshot to insert in Django templates. Args: snapshot_context (dict): the snapshot information revision_id (str): optional revision identifier in order to use the associated directory link_text (str): optional text to use for the generated link link_attrs (dict): optional attributes (e.g. class) to add to the link Returns: An HTML link in the form 'origin_directory_view_url' """ query_params = {'revision': revision_id} if snapshot_context['origin_info']: origin_info = snapshot_context['origin_info'] url_args = {'origin_url': origin_info['url']} if 'timestamp' in snapshot_context['url_args']: url_args['timestamp'] = \ snapshot_context['url_args']['timestamp'] if 'visit_id' in snapshot_context['query_params']: query_params['visit_id'] = \ snapshot_context['query_params']['visit_id'] directory_url = reverse('browse-origin-directory', url_args=url_args, query_params=query_params) else: url_args = {'snapshot_id': snapshot_context['snapshot_id']} directory_url = reverse('browse-snapshot-directory', url_args=url_args, query_params=query_params) if not link_text: link_text = directory_url return gen_link(directory_url, link_text, link_attrs) def gen_content_link(sha1_git, link_text=None, link_attrs={}): """ Utility function for generating a link to a content HTML view to insert in Django templates. Args: sha1_git (str): content identifier link_text (str): optional text for the generated link (the generated url will be used by default) link_attrs (dict): optional attributes (e.g. class) to add to the link Returns: An HTML link in the form 'link_text' """ if not sha1_git: return None content_url = reverse('browse-content', url_args={'query_string': 'sha1_git:' + sha1_git}) if not link_text: link_text = content_url return gen_link(content_url, link_text, link_attrs) def get_revision_log_url(revision_id, snapshot_context=None): """ Utility function for getting the URL for a revision log HTML view (possibly in the context of an origin). Args: revision_id (str): revision identifier the history heads to snapshot_context (dict): if provided, generate snapshot-dependent browsing link Returns: The revision log view URL """ query_params = {'revision': revision_id} if snapshot_context and snapshot_context['origin_info']: origin_info = snapshot_context['origin_info'] url_args = {'origin_url': origin_info['url']} if 'timestamp' in snapshot_context['url_args']: url_args['timestamp'] = \ snapshot_context['url_args']['timestamp'] if 'visit_id' in snapshot_context['query_params']: query_params['visit_id'] = \ snapshot_context['query_params']['visit_id'] revision_log_url = reverse('browse-origin-log', url_args=url_args, query_params=query_params) elif snapshot_context: url_args = {'snapshot_id': snapshot_context['snapshot_id']} revision_log_url = reverse('browse-snapshot-log', url_args=url_args, query_params=query_params) else: revision_log_url = reverse('browse-revision-log', url_args={'sha1_git': revision_id}) return revision_log_url def gen_revision_log_link(revision_id, snapshot_context=None, link_text=None, link_attrs={}): """ Utility function for generating a link to a revision log HTML view (possibly in the context of an origin) to insert in Django templates. Args: revision_id (str): revision identifier the history heads to snapshot_context (dict): if provided, generate snapshot-dependent browsing link link_text (str): optional text to use for the generated link link_attrs (dict): optional attributes (e.g. class) to add to the link Returns: An HTML link in the form 'link_text' """ if not revision_id: return None revision_log_url = get_revision_log_url(revision_id, snapshot_context) if not link_text: link_text = revision_log_url return gen_link(revision_log_url, link_text, link_attrs) def format_log_entries(revision_log, per_page, snapshot_context=None): """ Utility functions that process raw revision log data for HTML display. Its purpose is to: * add links to relevant browse views * format date in human readable format * truncate the message log Args: revision_log (list): raw revision log as returned by the swh-web api per_page (int): number of log entries per page snapshot_context (dict): if provided, generate snapshot-dependent browsing link """ revision_log_data = [] for i, rev in enumerate(revision_log): if i == per_page: break author_name = 'None' author_fullname = 'None' committer_fullname = 'None' if rev['author']: author_name = rev['author']['name'] or rev['author']['fullname'] author_fullname = rev['author']['fullname'] if rev['committer']: committer_fullname = rev['committer']['fullname'] author_date = format_utc_iso_date(rev['date']) committer_date = format_utc_iso_date(rev['committer_date']) tooltip = 'revision %s\n' % rev['id'] tooltip += 'author: %s\n' % author_fullname tooltip += 'author date: %s\n' % author_date tooltip += 'committer: %s\n' % committer_fullname tooltip += 'committer date: %s\n\n' % committer_date tooltip += textwrap.indent(rev['message'], ' '*4) revision_log_data.append({ 'author': author_name, 'id': rev['id'][:7], 'message': rev['message'], 'date': author_date, 'commit_date': committer_date, 'url': gen_revision_url(rev['id'], snapshot_context), 'tooltip': tooltip }) return revision_log_data # list of origin types that can be found in the swh archive # TODO: retrieve it dynamically in an efficient way instead # of hardcoding it _swh_origin_types = ['git', 'svn', 'deb', 'hg', 'ftp', 'deposit', 'pypi'] def get_origin_info(origin_url, origin_type=None): """ Get info about a software origin. Its main purpose is to automatically find an origin type when it is not provided as parameter. Args: origin_url (str): complete url of a software origin origin_type (str): optional origin type Returns: A dict with the following entries: * type: the origin type * url: the origin url * id: the internal id of the origin """ if origin_type: return service.lookup_origin({'type': origin_type, 'url': origin_url}) else: for origin_type in _swh_origin_types: try: origin_info = service.lookup_origin({'type': origin_type, 'url': origin_url}) return origin_info except Exception: pass raise NotFoundExc('Origin with url %s not found!' % origin_url) def get_snapshot_context(snapshot_id=None, origin_type=None, origin_url=None, timestamp=None, visit_id=None): """ Utility function to compute relevant information when navigating the archive in a snapshot context. The snapshot is either referenced by its id or it will be retrieved from an origin visit. Args: snapshot_id (str): hexadecimal representation of a snapshot identifier, all other parameters will be ignored if it is provided origin_type (str): the origin type (git, svn, deposit, ...) origin_url (str): the origin_url (e.g. https://github.com/(user)/(repo)/) timestamp (str): a datetime string for retrieving the closest visit of the origin visit_id (int): optional visit id for disambiguation in case of several visits with the same timestamp Returns: A dict with the following entries: * origin_info: dict containing origin information * visit_info: dict containing visit information * branches: the list of branches for the origin found during the visit * releases: the list of releases for the origin found during the visit * origin_browse_url: the url to browse the origin * origin_branches_url: the url to browse the origin branches * origin_releases_url': the url to browse the origin releases * origin_visit_url: the url to browse the snapshot of the origin found during the visit * url_args: dict containing url arguments to use when browsing in the context of the origin and its visit Raises: NotFoundExc: if no snapshot is found for the visit of an origin. """ # noqa origin_info = None visit_info = None url_args = None query_params = {} branches = [] releases = [] browse_url = None visit_url = None branches_url = None releases_url = None swh_type = 'snapshot' if origin_url: swh_type = 'origin' origin_info = get_origin_info(origin_url, origin_type) visit_info = get_origin_visit(origin_info, timestamp, visit_id, snapshot_id) fmt_date = format_utc_iso_date(visit_info['date']) visit_info['fmt_date'] = fmt_date snapshot_id = visit_info['snapshot'] if not snapshot_id: raise NotFoundExc('No snapshot associated to the visit of origin ' '%s on %s' % (origin_url, fmt_date)) # provided timestamp is not necessarily equals to the one # of the retrieved visit, so get the exact one in order # use it in the urls generated below if timestamp: timestamp = visit_info['date'] branches, releases = \ get_origin_visit_snapshot(origin_info, timestamp, visit_id, snapshot_id) url_args = {'origin_type': origin_type, 'origin_url': origin_info['url']} query_params = {'visit_id': visit_id} browse_url = reverse('browse-origin-visits', url_args=url_args) if timestamp: url_args['timestamp'] = format_utc_iso_date(timestamp, '%Y-%m-%dT%H:%M:%S') visit_url = reverse('browse-origin-directory', url_args=url_args, query_params=query_params) visit_info['url'] = visit_url branches_url = reverse('browse-origin-branches', url_args=url_args, query_params=query_params) releases_url = reverse('browse-origin-releases', url_args=url_args, query_params=query_params) elif snapshot_id: branches, releases = get_snapshot_content(snapshot_id) url_args = {'snapshot_id': snapshot_id} browse_url = reverse('browse-snapshot', url_args=url_args) branches_url = reverse('browse-snapshot-branches', url_args=url_args) releases_url = reverse('browse-snapshot-releases', url_args=url_args) releases = list(reversed(releases)) snapshot_size = service.lookup_snapshot_size(snapshot_id) is_empty = sum(snapshot_size.values()) == 0 swh_snp_id = persistent_identifier('snapshot', snapshot_id) return { 'swh_type': swh_type, 'swh_object_id': swh_snp_id, 'snapshot_id': snapshot_id, 'snapshot_size': snapshot_size, 'is_empty': is_empty, 'origin_info': origin_info, # keep track if the origin type was provided as url argument 'origin_type': origin_type, 'visit_info': visit_info, 'branches': branches, 'releases': releases, 'branch': None, 'release': None, 'browse_url': browse_url, 'branches_url': branches_url, 'releases_url': releases_url, 'url_args': url_args, 'query_params': query_params } # list of common readme names ordered by preference # (lower indices have higher priority) _common_readme_names = [ "readme.markdown", "readme.md", "readme.rst", "readme.txt", "readme" ] def get_readme_to_display(readmes): """ Process a list of readme files found in a directory in order to find the adequate one to display. Args: readmes: a list of dict where keys are readme file names and values are readme sha1s Returns: A tuple (readme_name, readme_sha1) """ readme_name = None readme_url = None readme_sha1 = None readme_html = None lc_readmes = {k.lower(): {'orig_name': k, 'sha1': v} for k, v in readmes.items()} # look for readme names according to the preference order # defined by the _common_readme_names list for common_readme_name in _common_readme_names: if common_readme_name in lc_readmes: readme_name = lc_readmes[common_readme_name]['orig_name'] readme_sha1 = lc_readmes[common_readme_name]['sha1'] readme_url = reverse('browse-content-raw', url_args={'query_string': readme_sha1}) break # otherwise pick the first readme like file if any if not readme_name and len(readmes.items()) > 0: readme_name = next(iter(readmes)) readme_sha1 = readmes[readme_name] readme_url = reverse('browse-content-raw', url_args={'query_string': readme_sha1}) # convert rst README to html server side as there is # no viable solution to perform that task client side if readme_name and readme_name.endswith('.rst'): cache_entry_id = 'readme_%s' % readme_sha1 cache_entry = cache.get(cache_entry_id) if cache_entry: readme_html = cache_entry else: try: rst_doc = request_content(readme_sha1) readme_html = pypandoc.convert_text(rst_doc['raw_data'], 'html', format='rst') cache.set(cache_entry_id, readme_html) except Exception: readme_html = 'Readme bytes are not available' return readme_name, readme_url, readme_html def get_swh_persistent_ids(swh_objects, snapshot_context=None): """ Returns a list of dict containing info related to persistent identifiers of swh objects. Args: swh_objects (list): a list of dict with the following keys: * type: swh object type (content/directory/release/revision/snapshot) * id: swh object id snapshot_context (dict): optional parameter describing the snapshot in which the object has been found Returns: list: a list of dict with the following keys: * object_type: the swh object type (content/directory/release/revision/snapshot) * object_icon: the swh object icon to use in HTML views * swh_id: the computed swh object persistent identifier * swh_id_url: the url resolving the persistent identifier * show_options: boolean indicating if the persistent id options must be displayed in persistent ids HTML view """ # noqa swh_ids = [] for swh_object in swh_objects: if not swh_object['id']: continue swh_id = get_swh_persistent_id(swh_object['type'], swh_object['id']) show_options = swh_object['type'] == 'content' or \ (snapshot_context and snapshot_context['origin_info'] is not None) object_icon = swh_object_icons[swh_object['type']] swh_ids.append({ 'object_type': swh_object['type'], 'object_icon': object_icon, 'swh_id': swh_id, 'swh_id_url': reverse('browse-swh-id', url_args={'swh_id': swh_id}), 'show_options': show_options }) return swh_ids diff --git a/swh/web/common/converters.py b/swh/web/common/converters.py index 08d53e24..e4aded53 100644 --- a/swh/web/common/converters.py +++ b/swh/web/common/converters.py @@ -1,382 +1,381 @@ # 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 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 fmap(f, data): """Map f to data at each level. This must keep the origin data structure type: - map -> map - dict -> dict - list -> list - None -> None Args: f: function that expects one argument. data: data to traverse to apply the f function. list, map, dict or bare value. Returns: The same data-structure with modified values by the f function. """ if data is None: return data if isinstance(data, map): return map(lambda y: fmap(f, y), (x for x in data)) if isinstance(data, list): return [fmap(f, x) for x in data] if isinstance(data, dict): return {k: fmap(f, v) for (k, v) in data.items()} return f(data) def from_swh(dict_swh, hashess={}, bytess={}, dates={}, blacklist={}, removables_if_empty={}, empty_dict={}, empty_list={}, convert={}, convert_fn=lambda x: x): """Convert from a 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 not v: return v 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] = fmap(convert_hashes_bytes, value) elif key in bytess: try: new_dict[key] = 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] = 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 swh 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 a swh origin to an origin dictionary. """ return from_swh(origin) def from_release(release): """Convert from a 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 a 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'}) return ov def from_snapshot(snapshot): """Convert swh snapshot to serializable snapshot dictionary. """ sv = from_swh(snapshot, hashess={'id', 'target'}, bytess={'next_branch'}) 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'}) + hashess={'id'}) diff --git a/swh/web/tests/common/test_converters.py b/swh/web/tests/common/test_converters.py index 25ad6840..47e061cf 100644 --- a/swh/web/tests/common/test_converters.py +++ b/swh/web/tests/common/test_converters.py @@ -1,785 +1,785 @@ # 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 from swh.model import hashutil from swh.web.common import converters from swh.web.tests.testcase import SWHWebTestCase class ConvertersTestCase(SWHWebTestCase): def test_fmap(self): self.assertEqual([2, 3, None, 4], converters.fmap(lambda x: x+1, [1, 2, None, 3])) self.assertEqual([11, 12, 13], list(converters.fmap(lambda x: x+10, map(lambda x: x, [1, 2, 3])))) self.assertEqual({'a': 2, 'b': 4}, converters.fmap(lambda x: x*2, {'a': 1, 'b': 2})) self.assertEqual(100, converters.fmap(lambda x: x*10, 10)) self.assertEqual({'a': [2, 6], 'b': 4}, converters.fmap(lambda x: x*2, {'a': [1, 3], 'b': 2})) # noqa self.assertIsNone(converters.fmap(lambda x: x, None)) def test_from_swh(self): some_input = { 'a': 'something', 'b': 'someone', 'c': b'sharp-0.3.4.tgz', 'd': hashutil.hash_to_bytes( 'b04caf10e9535160d90e874b45aa426de762f19f'), 'e': b'sharp.html/doc_002dS_005fISREG.html', 'g': [b'utf-8-to-decode', b'another-one'], 'h': 'something filtered', 'i': {'e': b'something'}, 'j': { 'k': { 'l': [b'bytes thing', b'another thingy', b''], 'n': 'dont care either' }, 'm': 'dont care' }, 'o': 'something', 'p': b'foo', 'q': {'extra-headers': [['a', b'intact']]}, 'w': None, 'r': {'p': 'also intact', 'q': 'bar'}, 's': { 'timestamp': 42, 'offset': -420, 'negative_utc': None, }, 's1': { 'timestamp': {'seconds': 42, 'microseconds': 0}, 'offset': -420, 'negative_utc': None, }, 's2': datetime.datetime( 2013, 7, 1, 20, 0, 0, tzinfo=datetime.timezone.utc), 't': None, 'u': None, 'v': None, 'x': None, } expected_output = { 'a': 'something', 'b': 'someone', 'c': 'sharp-0.3.4.tgz', 'd': 'b04caf10e9535160d90e874b45aa426de762f19f', 'e': 'sharp.html/doc_002dS_005fISREG.html', 'g': ['utf-8-to-decode', 'another-one'], 'i': {'e': 'something'}, 'j': { 'k': { 'l': ['bytes thing', 'another thingy', ''] } }, 'p': 'foo', 'q': {'extra-headers': [['a', 'intact']]}, 'w': {}, 'r': {'p': 'also intact', 'q': 'bar'}, 's': '1969-12-31T17:00:42-07:00', 's1': '1969-12-31T17:00:42-07:00', 's2': '2013-07-01T20:00:00+00:00', 'u': {}, 'v': [], 'x': None, } actual_output = converters.from_swh( some_input, hashess={'d', 'o', 'x'}, bytess={'c', 'e', 'g', 'l'}, dates={'s', 's1', 's2'}, blacklist={'h', 'm', 'n', 'o'}, removables_if_empty={'t'}, empty_dict={'u'}, empty_list={'v'}, convert={'p', 'q', 'w'}, convert_fn=converters.convert_revision_metadata) self.assertEqual(expected_output, actual_output) def test_from_swh_edge_cases_do_no_conversion_if_none_or_not_bytes(self): some_input = { 'a': 'something', 'b': None, 'c': 'someone', 'd': None, 'e': None } expected_output = { 'a': 'something', 'b': None, 'c': 'someone', 'd': None, 'e': None } actual_output = converters.from_swh(some_input, hashess={'a', 'b'}, bytess={'c', 'd'}, dates={'e'}) self.assertEqual(expected_output, actual_output) def test_from_swh_edge_cases_convert_invalid_utf8_bytes(self): some_input = { 'a': 'something', 'b': 'someone', 'c': b'a name \xff', 'd': b'an email \xff', } expected_output = { 'a': 'something', 'b': 'someone', 'c': 'a name \\xff', 'd': 'an email \\xff', 'decoding_failures': ['c', 'd'] } actual_output = converters.from_swh(some_input, hashess={'a', 'b'}, bytess={'c', 'd'}) for v in ['a', 'b', 'c', 'd']: self.assertEqual(expected_output[v], actual_output[v]) self.assertEqual(len(expected_output['decoding_failures']), len(actual_output['decoding_failures'])) for v in expected_output['decoding_failures']: self.assertTrue(v in actual_output['decoding_failures']) def test_from_swh_empty(self): # when self.assertEqual({}, converters.from_swh({})) def test_from_swh_none(self): # when self.assertIsNone(converters.from_swh(None)) def test_from_provenance(self): # given input_provenance = { 'origin': 10, 'visit': 1, 'content': hashutil.hash_to_bytes( '321caf10e9535160d90e874b45aa426de762f19f'), 'revision': hashutil.hash_to_bytes( '123caf10e9535160d90e874b45aa426de762f19f'), 'path': b'octave-3.4.0/doc/interpreter/octave/doc_002dS_005fISREG' } expected_provenance = { 'origin': 10, 'visit': 1, 'content': '321caf10e9535160d90e874b45aa426de762f19f', 'revision': '123caf10e9535160d90e874b45aa426de762f19f', 'path': 'octave-3.4.0/doc/interpreter/octave/doc_002dS_005fISREG' } # when actual_provenance = converters.from_provenance(input_provenance) # then self.assertEqual(actual_provenance, expected_provenance) def test_from_origin(self): # given origin_input = { 'id': 9, 'type': 'ftp', 'url': 'rsync://ftp.gnu.org/gnu/octave', } expected_origin = { 'id': 9, 'type': 'ftp', 'url': 'rsync://ftp.gnu.org/gnu/octave', } # when actual_origin = converters.from_origin(origin_input) # then self.assertEqual(actual_origin, expected_origin) def test_from_origin_visit(self): snap_hash = 'b5f0b7f716735ebffe38505c60145c4fd9da6ca3' for snap in [snap_hash, None]: # given visit = { 'date': { 'timestamp': datetime.datetime( 2015, 1, 1, 22, 0, 0, tzinfo=datetime.timezone.utc).timestamp(), 'offset': 0, 'negative_utc': False, }, 'origin': 10, 'visit': 100, 'metadata': None, 'status': 'full', 'snapshot': hashutil.hash_to_bytes(snap) if snap else snap, } expected_visit = { 'date': '2015-01-01T22:00:00+00:00', 'origin': 10, 'visit': 100, 'metadata': {}, 'status': 'full', 'snapshot': snap_hash if snap else snap } # when actual_visit = converters.from_origin_visit(visit) # then self.assertEqual(actual_visit, expected_visit) def test_from_release(self): release_input = { 'id': hashutil.hash_to_bytes( 'aad23fa492a0c5fed0708a6703be875448c86884'), 'target': hashutil.hash_to_bytes( '5e46d564378afc44b31bb89f99d5675195fbdf67'), 'target_type': 'revision', 'date': { 'timestamp': datetime.datetime( 2015, 1, 1, 22, 0, 0, tzinfo=datetime.timezone.utc).timestamp(), 'offset': 0, 'negative_utc': False, }, 'author': { 'name': b'author name', 'fullname': b'Author Name author@email', 'email': b'author@email', }, 'name': b'v0.0.1', 'message': b'some comment on release', 'synthetic': True, } expected_release = { 'id': 'aad23fa492a0c5fed0708a6703be875448c86884', 'target': '5e46d564378afc44b31bb89f99d5675195fbdf67', 'target_type': 'revision', 'date': '2015-01-01T22:00:00+00:00', 'author': { 'name': 'author name', 'fullname': 'Author Name author@email', 'email': 'author@email', }, 'name': 'v0.0.1', 'message': 'some comment on release', 'target_type': 'revision', 'synthetic': True, } # when actual_release = converters.from_release(release_input) # then self.assertEqual(actual_release, expected_release) def test_from_release_no_revision(self): release_input = { 'id': hashutil.hash_to_bytes( 'b2171ee2bdf119cd99a7ec7eff32fa8013ef9a4e'), 'target': None, 'date': { 'timestamp': datetime.datetime( 2016, 3, 2, 10, 0, 0, tzinfo=datetime.timezone.utc).timestamp(), 'offset': 0, 'negative_utc': True, }, 'name': b'v0.1.1', 'message': b'comment on release', 'synthetic': False, 'author': { 'name': b'bob', 'fullname': b'Bob bob@alice.net', 'email': b'bob@alice.net', }, } expected_release = { 'id': 'b2171ee2bdf119cd99a7ec7eff32fa8013ef9a4e', 'target': None, 'date': '2016-03-02T10:00:00-00:00', 'name': 'v0.1.1', 'message': 'comment on release', 'synthetic': False, 'author': { 'name': 'bob', 'fullname': 'Bob bob@alice.net', 'email': 'bob@alice.net', }, } # when actual_release = converters.from_release(release_input) # then self.assertEqual(actual_release, expected_release) def test_from_revision(self): revision_input = { 'id': hashutil.hash_to_bytes( '18d8be353ed3480476f032475e7c233eff7371d5'), 'directory': hashutil.hash_to_bytes( '7834ef7e7c357ce2af928115c6c6a42b7e2a44e6'), 'author': { 'name': b'Software Heritage', 'fullname': b'robot robot@softwareheritage.org', 'email': b'robot@softwareheritage.org', }, 'committer': { 'name': b'Software Heritage', 'fullname': b'robot robot@softwareheritage.org', 'email': b'robot@softwareheritage.org', }, 'message': b'synthetic revision message', 'date': { 'timestamp': datetime.datetime( 2000, 1, 17, 11, 23, 54, tzinfo=datetime.timezone.utc).timestamp(), 'offset': 0, 'negative_utc': False, }, 'committer_date': { 'timestamp': datetime.datetime( 2000, 1, 17, 11, 23, 54, tzinfo=datetime.timezone.utc).timestamp(), 'offset': 0, 'negative_utc': False, }, 'synthetic': True, 'type': 'tar', 'parents': [ hashutil.hash_to_bytes( '29d8be353ed3480476f032475e7c244eff7371d5'), hashutil.hash_to_bytes( '30d8be353ed3480476f032475e7c244eff7371d5') ], 'children': [ hashutil.hash_to_bytes( '123546353ed3480476f032475e7c244eff7371d5'), ], 'metadata': { 'extra_headers': [['gpgsig', b'some-signature']], 'original_artifact': [{ 'archive_type': 'tar', 'name': 'webbase-5.7.0.tar.gz', 'sha1': '147f73f369733d088b7a6fa9c4e0273dcd3c7ccd', 'sha1_git': '6a15ea8b881069adedf11feceec35588f2cfe8f1', 'sha256': '401d0df797110bea805d358b85bcc1ced29549d3d73f' '309d36484e7edf7bb912', }] }, } expected_revision = { 'id': '18d8be353ed3480476f032475e7c233eff7371d5', 'directory': '7834ef7e7c357ce2af928115c6c6a42b7e2a44e6', 'author': { 'name': 'Software Heritage', 'fullname': 'robot robot@softwareheritage.org', 'email': 'robot@softwareheritage.org', }, 'committer': { 'name': 'Software Heritage', 'fullname': 'robot robot@softwareheritage.org', 'email': 'robot@softwareheritage.org', }, 'message': 'synthetic revision message', 'date': "2000-01-17T11:23:54+00:00", 'committer_date': "2000-01-17T11:23:54+00:00", 'children': [ '123546353ed3480476f032475e7c244eff7371d5' ], 'parents': [ '29d8be353ed3480476f032475e7c244eff7371d5', '30d8be353ed3480476f032475e7c244eff7371d5' ], 'type': 'tar', 'synthetic': True, 'metadata': { 'extra_headers': [['gpgsig', 'some-signature']], 'original_artifact': [{ 'archive_type': 'tar', 'name': 'webbase-5.7.0.tar.gz', 'sha1': '147f73f369733d088b7a6fa9c4e0273dcd3c7ccd', 'sha1_git': '6a15ea8b881069adedf11feceec35588f2cfe8f1', 'sha256': '401d0df797110bea805d358b85bcc1ced29549d3d73f' '309d36484e7edf7bb912' }] }, 'merge': True } # when actual_revision = converters.from_revision(revision_input) # then self.assertEqual(actual_revision, expected_revision) def test_from_revision_nomerge(self): revision_input = { 'id': hashutil.hash_to_bytes( '18d8be353ed3480476f032475e7c233eff7371d5'), 'parents': [ hashutil.hash_to_bytes( '29d8be353ed3480476f032475e7c244eff7371d5') ] } expected_revision = { 'id': '18d8be353ed3480476f032475e7c233eff7371d5', 'parents': [ '29d8be353ed3480476f032475e7c244eff7371d5' ], 'merge': False } # when actual_revision = converters.from_revision(revision_input) # then self.assertEqual(actual_revision, expected_revision) def test_from_revision_noparents(self): revision_input = { 'id': hashutil.hash_to_bytes( '18d8be353ed3480476f032475e7c233eff7371d5'), 'directory': hashutil.hash_to_bytes( '7834ef7e7c357ce2af928115c6c6a42b7e2a44e6'), 'author': { 'name': b'Software Heritage', 'fullname': b'robot robot@softwareheritage.org', 'email': b'robot@softwareheritage.org', }, 'committer': { 'name': b'Software Heritage', 'fullname': b'robot robot@softwareheritage.org', 'email': b'robot@softwareheritage.org', }, 'message': b'synthetic revision message', 'date': { 'timestamp': datetime.datetime( 2000, 1, 17, 11, 23, 54, tzinfo=datetime.timezone.utc).timestamp(), 'offset': 0, 'negative_utc': False, }, 'committer_date': { 'timestamp': datetime.datetime( 2000, 1, 17, 11, 23, 54, tzinfo=datetime.timezone.utc).timestamp(), 'offset': 0, 'negative_utc': False, }, 'synthetic': True, 'type': 'tar', 'children': [ hashutil.hash_to_bytes( '123546353ed3480476f032475e7c244eff7371d5'), ], 'metadata': { 'original_artifact': [{ 'archive_type': 'tar', 'name': 'webbase-5.7.0.tar.gz', 'sha1': '147f73f369733d088b7a6fa9c4e0273dcd3c7ccd', 'sha1_git': '6a15ea8b881069adedf11feceec35588f2cfe8f1', 'sha256': '401d0df797110bea805d358b85bcc1ced29549d3d73f' '309d36484e7edf7bb912', }] }, } expected_revision = { 'id': '18d8be353ed3480476f032475e7c233eff7371d5', 'directory': '7834ef7e7c357ce2af928115c6c6a42b7e2a44e6', 'author': { 'name': 'Software Heritage', 'fullname': 'robot robot@softwareheritage.org', 'email': 'robot@softwareheritage.org', }, 'committer': { 'name': 'Software Heritage', 'fullname': 'robot robot@softwareheritage.org', 'email': 'robot@softwareheritage.org', }, 'message': 'synthetic revision message', 'date': "2000-01-17T11:23:54+00:00", 'committer_date': "2000-01-17T11:23:54+00:00", 'children': [ '123546353ed3480476f032475e7c244eff7371d5' ], 'type': 'tar', 'synthetic': True, 'metadata': { 'original_artifact': [{ 'archive_type': 'tar', 'name': 'webbase-5.7.0.tar.gz', 'sha1': '147f73f369733d088b7a6fa9c4e0273dcd3c7ccd', 'sha1_git': '6a15ea8b881069adedf11feceec35588f2cfe8f1', 'sha256': '401d0df797110bea805d358b85bcc1ced29549d3d73f' '309d36484e7edf7bb912' }] } } # when actual_revision = converters.from_revision(revision_input) # then self.assertEqual(actual_revision, expected_revision) def test_from_revision_invalid(self): revision_input = { 'id': hashutil.hash_to_bytes( '18d8be353ed3480476f032475e7c233eff7371d5'), 'directory': hashutil.hash_to_bytes( '7834ef7e7c357ce2af928115c6c6a42b7e2a44e6'), 'author': { 'name': b'Software Heritage', 'fullname': b'robot robot@softwareheritage.org', 'email': b'robot@softwareheritage.org', }, 'committer': { 'name': b'Software Heritage', 'fullname': b'robot robot@softwareheritage.org', 'email': b'robot@softwareheritage.org', }, 'message': b'invalid message \xff', 'date': { 'timestamp': datetime.datetime( 2000, 1, 17, 11, 23, 54, tzinfo=datetime.timezone.utc).timestamp(), 'offset': 0, 'negative_utc': False, }, 'committer_date': { 'timestamp': datetime.datetime( 2000, 1, 17, 11, 23, 54, tzinfo=datetime.timezone.utc).timestamp(), 'offset': 0, 'negative_utc': False, }, 'synthetic': True, 'type': 'tar', 'parents': [ hashutil.hash_to_bytes( '29d8be353ed3480476f032475e7c244eff7371d5'), hashutil.hash_to_bytes( '30d8be353ed3480476f032475e7c244eff7371d5') ], 'children': [ hashutil.hash_to_bytes( '123546353ed3480476f032475e7c244eff7371d5'), ], 'metadata': { 'original_artifact': [{ 'archive_type': 'tar', 'name': 'webbase-5.7.0.tar.gz', 'sha1': '147f73f369733d088b7a6fa9c4e0273dcd3c7ccd', 'sha1_git': '6a15ea8b881069adedf11feceec35588f2cfe8f1', 'sha256': '401d0df797110bea805d358b85bcc1ced29549d3d73f' '309d36484e7edf7bb912', }] }, } expected_revision = { 'id': '18d8be353ed3480476f032475e7c233eff7371d5', 'directory': '7834ef7e7c357ce2af928115c6c6a42b7e2a44e6', 'author': { 'name': 'Software Heritage', 'fullname': 'robot robot@softwareheritage.org', 'email': 'robot@softwareheritage.org', }, 'committer': { 'name': 'Software Heritage', 'fullname': 'robot robot@softwareheritage.org', 'email': 'robot@softwareheritage.org', }, 'message': None, 'message_decoding_failed': True, 'date': "2000-01-17T11:23:54+00:00", 'committer_date': "2000-01-17T11:23:54+00:00", 'children': [ '123546353ed3480476f032475e7c244eff7371d5' ], 'parents': [ '29d8be353ed3480476f032475e7c244eff7371d5', '30d8be353ed3480476f032475e7c244eff7371d5' ], 'type': 'tar', 'synthetic': True, 'metadata': { 'original_artifact': [{ 'archive_type': 'tar', 'name': 'webbase-5.7.0.tar.gz', 'sha1': '147f73f369733d088b7a6fa9c4e0273dcd3c7ccd', 'sha1_git': '6a15ea8b881069adedf11feceec35588f2cfe8f1', 'sha256': '401d0df797110bea805d358b85bcc1ced29549d3d73f' '309d36484e7edf7bb912' }] }, 'merge': True } # when actual_revision = converters.from_revision(revision_input) # then self.assertEqual(actual_revision, expected_revision) def test_from_content_none(self): self.assertIsNone(converters.from_content(None)) def test_from_content(self): content_input = { 'sha1': hashutil.hash_to_bytes( '5c6f0e2750f48fa0bd0c4cf5976ba0b9e02ebda5'), 'sha256': hashutil.hash_to_bytes( '39007420ca5de7cb3cfc15196335507e' 'e76c98930e7e0afa4d2747d3bf96c926'), 'blake2s256': hashutil.hash_to_bytes( '49007420ca5de7cb3cfc15196335507e' 'e76c98930e7e0afa4d2747d3bf96c926'), 'sha1_git': hashutil.hash_to_bytes( '40e71b8614fcd89ccd17ca2b1d9e66c5b00a6d03'), 'ctime': 'something-which-is-filtered-out', 'data': b'data in bytes', 'length': 10, 'status': 'hidden', } # 'status' is filtered expected_content = { 'checksums': { 'sha1': '5c6f0e2750f48fa0bd0c4cf5976ba0b9e02ebda5', 'sha256': '39007420ca5de7cb3cfc15196335507ee76c98' '930e7e0afa4d2747d3bf96c926', 'blake2s256': '49007420ca5de7cb3cfc15196335507ee7' '6c98930e7e0afa4d2747d3bf96c926', 'sha1_git': '40e71b8614fcd89ccd17ca2b1d9e66c5b00a6d03', }, 'data': b'data in bytes', 'length': 10, 'status': 'absent', } # when actual_content = converters.from_content(content_input) # then self.assertEqual(actual_content, expected_content) def test_from_person(self): person_input = { 'id': 10, 'anything': 'else', 'name': b'bob', 'fullname': b'bob bob@alice.net', 'email': b'bob@foo.alice', } expected_person = { 'id': 10, 'anything': 'else', 'name': 'bob', 'fullname': 'bob bob@alice.net', 'email': 'bob@foo.alice', } # when actual_person = converters.from_person(person_input) # then self.assertEqual(actual_person, expected_person) def test_from_directory_entries(self): dir_entries_input = { 'sha1': hashutil.hash_to_bytes( '5c6f0e2750f48fa0bd0c4cf5976ba0b9e02ebda5'), 'sha256': hashutil.hash_to_bytes( '39007420ca5de7cb3cfc15196335507e' 'e76c98930e7e0afa4d2747d3bf96c926'), 'sha1_git': hashutil.hash_to_bytes( '40e71b8614fcd89ccd17ca2b1d9e66c5b00a6d03'), 'blake2s256': hashutil.hash_to_bytes( '685395c5dc57cada459364f0946d3dd45bad5fcbab' 'c1048edb44380f1d31d0aa'), 'target': hashutil.hash_to_bytes( '40e71b8614fcd89ccd17ca2b1d9e66c5b00a6d03'), 'dir_id': hashutil.hash_to_bytes( '40e71b8614fcd89ccd17ca2b1d9e66c5b00a6d03'), 'name': b'bob', 'type': 10, 'status': 'hidden', } expected_dir_entries = { 'checksums': { 'sha1': '5c6f0e2750f48fa0bd0c4cf5976ba0b9e02ebda5', 'sha256': '39007420ca5de7cb3cfc15196335507ee76c98' '930e7e0afa4d2747d3bf96c926', 'sha1_git': '40e71b8614fcd89ccd17ca2b1d9e66c5b00a6d03', 'blake2s256': '685395c5dc57cada459364f0946d3dd45bad5f' 'cbabc1048edb44380f1d31d0aa', }, 'target': '40e71b8614fcd89ccd17ca2b1d9e66c5b00a6d03', 'dir_id': '40e71b8614fcd89ccd17ca2b1d9e66c5b00a6d03', 'name': 'bob', 'type': 10, 'status': 'absent', } # when actual_dir_entries = converters.from_directory_entry(dir_entries_input) # then self.assertEqual(actual_dir_entries, expected_dir_entries) def test_from_filetype(self): content_filetype = { 'id': hashutil.hash_to_bytes( '5c6f0e2750f48fa0bd0c4cf5976ba0b9e02ebda5'), - 'encoding': b'utf-8', - 'mimetype': b'text/plain', + 'encoding': 'utf-8', + 'mimetype': 'text/plain', } expected_content_filetype = { 'id': '5c6f0e2750f48fa0bd0c4cf5976ba0b9e02ebda5', 'encoding': 'utf-8', 'mimetype': 'text/plain', } # when actual_content_filetype = converters.from_filetype(content_filetype) # then self.assertEqual(actual_content_filetype, expected_content_filetype) diff --git a/swh/web/tests/common/test_service.py b/swh/web/tests/common/test_service.py index b7cca942..a9309d07 100644 --- a/swh/web/tests/common/test_service.py +++ b/swh/web/tests/common/test_service.py @@ -1,2011 +1,2011 @@ # 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 from unittest.mock import MagicMock, patch, call from swh.model.hashutil import hash_to_bytes, hash_to_hex from swh.web.common import service from swh.web.common.exc import BadInputExc, NotFoundExc from swh.web.tests.testcase import SWHWebTestCase class ServiceTestCase(SWHWebTestCase): def setUp(self): self.BLAKE2S256_SAMPLE = ('685395c5dc57cada459364f0946d3dd45b' 'ad5fcbabc1048edb44380f1d31d0aa') self.BLAKE2S256_SAMPLE_BIN = hash_to_bytes(self.BLAKE2S256_SAMPLE) self.SHA1_SAMPLE = '40e71b8614fcd89ccd17ca2b1d9e66c5b00a6d03' self.SHA1_SAMPLE_BIN = hash_to_bytes(self.SHA1_SAMPLE) self.SHA256_SAMPLE = ('8abb0aa566452620ecce816eecdef4792d77a' '293ad8ea82a4d5ecb4d36f7e560') self.SHA256_SAMPLE_BIN = hash_to_bytes(self.SHA256_SAMPLE) self.SHA1GIT_SAMPLE = '25d1a2e8f32937b0f498a5ca87f823d8df013c01' self.SHA1GIT_SAMPLE_BIN = hash_to_bytes(self.SHA1GIT_SAMPLE) self.DIRECTORY_ID = '7834ef7e7c357ce2af928115c6c6a42b7e2a44e6' self.DIRECTORY_ID_BIN = hash_to_bytes(self.DIRECTORY_ID) self.AUTHOR_ID_BIN = { 'name': b'author', 'email': b'author@company.org', } self.AUTHOR_ID = { 'name': 'author', 'email': 'author@company.org', } self.COMMITTER_ID_BIN = { 'name': b'committer', 'email': b'committer@corp.org', } self.COMMITTER_ID = { 'name': 'committer', 'email': 'committer@corp.org', } self.SAMPLE_DATE_RAW = { 'timestamp': datetime.datetime( 2000, 1, 17, 11, 23, 54, tzinfo=datetime.timezone.utc, ).timestamp(), 'offset': 0, 'negative_utc': False, } self.SAMPLE_DATE = '2000-01-17T11:23:54+00:00' self.SAMPLE_MESSAGE_BIN = b'elegant fix for bug 31415957' self.SAMPLE_MESSAGE = 'elegant fix for bug 31415957' self.SAMPLE_REVISION = { 'id': self.SHA1_SAMPLE, 'directory': self.DIRECTORY_ID, 'author': self.AUTHOR_ID, 'committer': self.COMMITTER_ID, 'message': self.SAMPLE_MESSAGE, 'date': self.SAMPLE_DATE, 'committer_date': self.SAMPLE_DATE, 'synthetic': False, 'type': 'git', 'parents': [], 'metadata': {}, 'merge': False } self.SAMPLE_REVISION_RAW = { 'id': self.SHA1_SAMPLE_BIN, 'directory': self.DIRECTORY_ID_BIN, 'author': self.AUTHOR_ID_BIN, 'committer': self.COMMITTER_ID_BIN, 'message': self.SAMPLE_MESSAGE_BIN, 'date': self.SAMPLE_DATE_RAW, 'committer_date': self.SAMPLE_DATE_RAW, 'synthetic': False, 'type': 'git', 'parents': [], 'metadata': [], } self.SAMPLE_CONTENT = { 'checksums': { 'blake2s256': self.BLAKE2S256_SAMPLE, 'sha1': self.SHA1_SAMPLE, 'sha256': self.SHA256_SAMPLE, 'sha1_git': self.SHA1GIT_SAMPLE, }, 'length': 190, 'status': 'absent' } self.SAMPLE_CONTENT_RAW = { 'blake2s256': self.BLAKE2S256_SAMPLE_BIN, 'sha1': self.SHA1_SAMPLE_BIN, 'sha256': self.SHA256_SAMPLE_BIN, 'sha1_git': self.SHA1GIT_SAMPLE_BIN, 'length': 190, 'status': 'hidden' } self.date_origin_visit1 = datetime.datetime( 2015, 1, 1, 22, 0, 0, tzinfo=datetime.timezone.utc) self.origin_visit1 = { 'date': self.date_origin_visit1, 'origin': 1, 'visit': 1 } @patch('swh.web.common.service.storage') def test_lookup_multiple_hashes_ball_missing(self, mock_storage): # given mock_storage.content_missing_per_sha1 = MagicMock(return_value=[]) # when actual_lookup = service.lookup_multiple_hashes( [{'filename': 'a', 'sha1': '456caf10e9535160d90e874b45aa426de762f19f'}, {'filename': 'b', 'sha1': '745bab676c8f3cec8016e0c39ea61cf57e518865'}]) # then self.assertEqual(actual_lookup, [ {'filename': 'a', 'sha1': '456caf10e9535160d90e874b45aa426de762f19f', 'found': True}, {'filename': 'b', 'sha1': '745bab676c8f3cec8016e0c39ea61cf57e518865', 'found': True} ]) @patch('swh.web.common.service.storage') def test_lookup_multiple_hashes_some_missing(self, mock_storage): # given mock_storage.content_missing_per_sha1 = MagicMock(return_value=[ hash_to_bytes('456caf10e9535160d90e874b45aa426de762f19f') ]) # when actual_lookup = service.lookup_multiple_hashes( [{'filename': 'a', 'sha1': '456caf10e9535160d90e874b45aa426de762f19f'}, {'filename': 'b', 'sha1': '745bab676c8f3cec8016e0c39ea61cf57e518865'}]) # then self.assertEqual(actual_lookup, [ {'filename': 'a', 'sha1': '456caf10e9535160d90e874b45aa426de762f19f', 'found': False}, {'filename': 'b', 'sha1': '745bab676c8f3cec8016e0c39ea61cf57e518865', 'found': True} ]) @patch('swh.web.common.service.storage') def test_lookup_hash_does_not_exist(self, mock_storage): # given mock_storage.content_find = MagicMock(return_value=None) # when actual_lookup = service.lookup_hash( 'sha1_git:123caf10e9535160d90e874b45aa426de762f19f') # then self.assertEqual({'found': None, 'algo': 'sha1_git'}, actual_lookup) # check the function has been called with parameters mock_storage.content_find.assert_called_with( {'sha1_git': hash_to_bytes('123caf10e9535160d90e874b45aa426de762f19f')}) @patch('swh.web.common.service.storage') def test_lookup_hash_exist(self, mock_storage): # given stub_content = { 'sha1': hash_to_bytes( '456caf10e9535160d90e874b45aa426de762f19f') } mock_storage.content_find = MagicMock(return_value=stub_content) # when actual_lookup = service.lookup_hash( 'sha1:456caf10e9535160d90e874b45aa426de762f19f') # then self.assertEqual({'found': stub_content, 'algo': 'sha1'}, actual_lookup) mock_storage.content_find.assert_called_with( {'sha1': hash_to_bytes('456caf10e9535160d90e874b45aa426de762f19f')} ) @patch('swh.web.common.service.storage') def test_search_hash_does_not_exist(self, mock_storage): # given mock_storage.content_find = MagicMock(return_value=None) # when actual_lookup = service.search_hash( 'sha1_git:123caf10e9535160d90e874b45aa426de762f19f') # then self.assertEqual({'found': False}, actual_lookup) # check the function has been called with parameters mock_storage.content_find.assert_called_with( {'sha1_git': hash_to_bytes('123caf10e9535160d90e874b45aa426de762f19f')}) @patch('swh.web.common.service.storage') def test_search_hash_exist(self, mock_storage): # given stub_content = { 'sha1': hash_to_bytes( '456caf10e9535160d90e874b45aa426de762f19f') } mock_storage.content_find = MagicMock(return_value=stub_content) # when actual_lookup = service.search_hash( 'sha1:456caf10e9535160d90e874b45aa426de762f19f') # then self.assertEqual({'found': True}, actual_lookup) mock_storage.content_find.assert_called_with( {'sha1': hash_to_bytes('456caf10e9535160d90e874b45aa426de762f19f')}, ) @patch('swh.web.common.service.idx_storage') def test_lookup_content_ctags(self, mock_idx_storage): # given mock_idx_storage.content_ctags_get = MagicMock( return_value=[{ 'id': hash_to_bytes( '123caf10e9535160d90e874b45aa426de762f19f'), 'line': 100, 'name': 'hello', 'kind': 'function', 'tool_name': 'ctags', 'tool_version': 'some-version', }]) expected_ctags = [{ 'id': '123caf10e9535160d90e874b45aa426de762f19f', 'line': 100, 'name': 'hello', 'kind': 'function', 'tool_name': 'ctags', 'tool_version': 'some-version', }] # when actual_ctags = list(service.lookup_content_ctags( 'sha1:123caf10e9535160d90e874b45aa426de762f19f')) # then self.assertEqual(actual_ctags, expected_ctags) mock_idx_storage.content_ctags_get.assert_called_with( [hash_to_bytes('123caf10e9535160d90e874b45aa426de762f19f')]) @patch('swh.web.common.service.idx_storage') def test_lookup_content_ctags_no_hash(self, mock_idx_storage): # given mock_idx_storage.content_ctags_get = MagicMock(return_value=[]) # when actual_ctags = list(service.lookup_content_ctags( 'sha1:123caf10e9535160d90e874b45aa426de762f19f')) # then self.assertEqual(actual_ctags, []) @patch('swh.web.common.service.idx_storage') def test_lookup_content_filetype(self, mock_idx_storage): # given mock_idx_storage.content_mimetype_get = MagicMock( return_value=[{ 'id': hash_to_bytes( '123caf10e9535160d90e874b45aa426de762f19f'), - 'mimetype': b'text/x-c++', - 'encoding': b'us-ascii', + 'mimetype': 'text/x-c++', + 'encoding': 'us-ascii', }]) expected_filetype = { 'id': '123caf10e9535160d90e874b45aa426de762f19f', 'mimetype': 'text/x-c++', 'encoding': 'us-ascii', } # when actual_filetype = service.lookup_content_filetype( 'sha1:123caf10e9535160d90e874b45aa426de762f19f') # then self.assertEqual(actual_filetype, expected_filetype) mock_idx_storage.content_mimetype_get.assert_called_with( [hash_to_bytes('123caf10e9535160d90e874b45aa426de762f19f')]) @patch('swh.web.common.service.idx_storage') @patch('swh.web.common.service.storage') def test_lookup_content_filetype_2(self, mock_storage, mock_idx_storage): # given mock_storage.content_find = MagicMock( return_value={ 'sha1': hash_to_bytes( '123caf10e9535160d90e874b45aa426de762f19f') } ) mock_idx_storage.content_mimetype_get = MagicMock( return_value=[{ 'id': hash_to_bytes( '123caf10e9535160d90e874b45aa426de762f19f'), - 'mimetype': b'text/x-python', - 'encoding': b'us-ascii', + 'mimetype': 'text/x-python', + 'encoding': 'us-ascii', }] ) expected_filetype = { 'id': '123caf10e9535160d90e874b45aa426de762f19f', 'mimetype': 'text/x-python', 'encoding': 'us-ascii', } # when actual_filetype = service.lookup_content_filetype( 'sha1_git:456caf10e9535160d90e874b45aa426de762f19f') # then self.assertEqual(actual_filetype, expected_filetype) mock_storage.content_find( 'sha1_git', hash_to_bytes( '456caf10e9535160d90e874b45aa426de762f19f') ) mock_idx_storage.content_mimetype_get.assert_called_with( [hash_to_bytes('123caf10e9535160d90e874b45aa426de762f19f')]) @patch('swh.web.common.service.idx_storage') def test_lookup_content_language(self, mock_idx_storage): # given mock_idx_storage.content_language_get = MagicMock( return_value=[{ 'id': hash_to_bytes( '123caf10e9535160d90e874b45aa426de762f19f'), 'lang': 'python', }]) expected_language = { 'id': '123caf10e9535160d90e874b45aa426de762f19f', 'lang': 'python', } # when actual_language = service.lookup_content_language( 'sha1:123caf10e9535160d90e874b45aa426de762f19f') # then self.assertEqual(actual_language, expected_language) mock_idx_storage.content_language_get.assert_called_with( [hash_to_bytes('123caf10e9535160d90e874b45aa426de762f19f')]) @patch('swh.web.common.service.idx_storage') @patch('swh.web.common.service.storage') def test_lookup_content_language_2(self, mock_storage, mock_idx_storage): # given mock_storage.content_find = MagicMock( return_value={ 'sha1': hash_to_bytes( '123caf10e9535160d90e874b45aa426de762f19f') } ) mock_idx_storage.content_language_get = MagicMock( return_value=[{ 'id': hash_to_bytes( '123caf10e9535160d90e874b45aa426de762f19f'), 'lang': 'haskell', }] ) expected_language = { 'id': '123caf10e9535160d90e874b45aa426de762f19f', 'lang': 'haskell', } # when actual_language = service.lookup_content_language( 'sha1_git:456caf10e9535160d90e874b45aa426de762f19f') # then self.assertEqual(actual_language, expected_language) mock_storage.content_find( 'sha1_git', hash_to_bytes( '456caf10e9535160d90e874b45aa426de762f19f') ) mock_idx_storage.content_language_get.assert_called_with( [hash_to_bytes('123caf10e9535160d90e874b45aa426de762f19f')]) @patch('swh.web.common.service.idx_storage') def test_lookup_expression(self, mock_idx_storage): # given mock_idx_storage.content_ctags_search = MagicMock( return_value=[{ 'id': hash_to_bytes( '123caf10e9535160d90e874b45aa426de762f19f'), 'name': 'foobar', 'kind': 'variable', 'lang': 'C', 'line': 10 }]) expected_ctags = [{ 'sha1': '123caf10e9535160d90e874b45aa426de762f19f', 'name': 'foobar', 'kind': 'variable', 'lang': 'C', 'line': 10 }] # when actual_ctags = list(service.lookup_expression( 'foobar', last_sha1='hash', per_page=10)) # then self.assertEqual(actual_ctags, expected_ctags) mock_idx_storage.content_ctags_search.assert_called_with( 'foobar', last_sha1='hash', limit=10) @patch('swh.web.common.service.idx_storage') def test_lookup_expression_no_result(self, mock_idx_storage): # given mock_idx_storage.content_ctags_search = MagicMock( return_value=[]) expected_ctags = [] # when actual_ctags = list(service.lookup_expression( 'barfoo', last_sha1='hash', per_page=10)) # then self.assertEqual(actual_ctags, expected_ctags) mock_idx_storage.content_ctags_search.assert_called_with( 'barfoo', last_sha1='hash', limit=10) @patch('swh.web.common.service.idx_storage') def test_lookup_content_license(self, mock_idx_storage): # given mock_idx_storage.content_fossology_license_get = MagicMock( return_value=[{ hash_to_bytes('123caf10e9535160d90e874b45aa426de762f19f'): [{ 'licenses': ['GPL-3.0+'], 'tool': {} }] }]) expected_license = { 'id': '123caf10e9535160d90e874b45aa426de762f19f', 'facts': [{ 'licenses': ['GPL-3.0+'], 'tool': {} }] } # when actual_license = service.lookup_content_license( 'sha1:123caf10e9535160d90e874b45aa426de762f19f') # then self.assertEqual(actual_license, expected_license) mock_idx_storage.content_fossology_license_get.assert_called_with( [hash_to_bytes('123caf10e9535160d90e874b45aa426de762f19f')]) @patch('swh.web.common.service.idx_storage') @patch('swh.web.common.service.storage') def test_lookup_content_license_2(self, mock_storage, mock_idx_storage): # given mock_storage.content_find = MagicMock( return_value={ 'sha1': hash_to_bytes( '123caf10e9535160d90e874b45aa426de762f19f') } ) mock_idx_storage.content_fossology_license_get = MagicMock( return_value=[{ hash_to_bytes('123caf10e9535160d90e874b45aa426de762f19f'): [{ 'licenses': ['BSD-2-Clause'], 'tool': {} }] }] ) expected_license = { 'id': '123caf10e9535160d90e874b45aa426de762f19f', 'facts': [{ 'licenses': ['BSD-2-Clause'], 'tool': {} }] } # when actual_license = service.lookup_content_license( 'sha1_git:456caf10e9535160d90e874b45aa426de762f19f') # then self.assertEqual(actual_license, expected_license) mock_storage.content_find( 'sha1_git', hash_to_bytes( '456caf10e9535160d90e874b45aa426de762f19f') ) mock_idx_storage.content_fossology_license_get.assert_called_with( [hash_to_bytes('123caf10e9535160d90e874b45aa426de762f19f')]) @patch('swh.web.common.service.storage') def test_lookup_content_provenance(self, mock_storage): # given mock_storage.content_find_provenance = MagicMock( return_value=(p for p in [{ 'content': hash_to_bytes( '123caf10e9535160d90e874b45aa426de762f19f'), 'revision': hash_to_bytes( '456caf10e9535160d90e874b45aa426de762f19f'), 'origin': 100, 'visit': 1, 'path': b'octavio-3.4.0/octave.html/doc_002dS_005fISREG.html' }])) expected_provenances = [{ 'content': '123caf10e9535160d90e874b45aa426de762f19f', 'revision': '456caf10e9535160d90e874b45aa426de762f19f', 'origin': 100, 'visit': 1, 'path': 'octavio-3.4.0/octave.html/doc_002dS_005fISREG.html' }] # when actual_provenances = service.lookup_content_provenance( 'sha1_git:123caf10e9535160d90e874b45aa426de762f19f') # then self.assertEqual(list(actual_provenances), expected_provenances) mock_storage.content_find_provenance.assert_called_with( {'sha1_git': hash_to_bytes('123caf10e9535160d90e874b45aa426de762f19f')}) @patch('swh.web.common.service.storage') def test_lookup_content_provenance_not_found(self, mock_storage): # given mock_storage.content_find_provenance = MagicMock(return_value=None) # when actual_provenances = service.lookup_content_provenance( 'sha1_git:456caf10e9535160d90e874b45aa426de762f19f') # then self.assertIsNone(actual_provenances) mock_storage.content_find_provenance.assert_called_with( {'sha1_git': hash_to_bytes('456caf10e9535160d90e874b45aa426de762f19f')}) @patch('swh.web.common.service.storage') def test_stat_counters(self, mock_storage): # given input_stats = { "content": 1770830, "directory": 211683, "directory_entry_dir": 209167, "directory_entry_file": 1807094, "directory_entry_rev": 0, "entity": 0, "entity_history": 0, "origin": 1096, "person": 0, "release": 8584, "revision": 7792, "revision_history": 0, "skipped_content": 0 } mock_storage.stat_counters = MagicMock(return_value=input_stats) # when actual_stats = service.stat_counters() # then expected_stats = input_stats self.assertEqual(actual_stats, expected_stats) mock_storage.stat_counters.assert_called_with() @patch('swh.web.common.service._lookup_origin_visits') def test_lookup_origin_visits(self, mock_lookup_visits): # given date_origin_visit2 = datetime.datetime( 2013, 7, 1, 20, 0, 0, tzinfo=datetime.timezone.utc) date_origin_visit3 = datetime.datetime( 2015, 1, 1, 21, 0, 0, tzinfo=datetime.timezone.utc) stub_result = [self.origin_visit1, { 'date': date_origin_visit2, 'origin': 1, 'visit': 2, 'target': hash_to_bytes( '65a55bbdf3629f916219feb3dcc7393ded1bc8db'), 'branch': b'master', 'target_type': 'release', 'metadata': None, }, { 'date': date_origin_visit3, 'origin': 1, 'visit': 3 }] mock_lookup_visits.return_value = stub_result # when expected_origin_visits = [{ 'date': self.origin_visit1['date'].isoformat(), 'origin': self.origin_visit1['origin'], 'visit': self.origin_visit1['visit'] }, { 'date': date_origin_visit2.isoformat(), 'origin': 1, 'visit': 2, 'target': '65a55bbdf3629f916219feb3dcc7393ded1bc8db', 'branch': 'master', 'target_type': 'release', 'metadata': {}, }, { 'date': date_origin_visit3.isoformat(), 'origin': 1, 'visit': 3 }] actual_origin_visits = service.lookup_origin_visits(6) # then self.assertEqual(list(actual_origin_visits), expected_origin_visits) mock_lookup_visits.assert_called_once_with( 6, last_visit=None, limit=10) @patch('swh.web.common.service.storage') def test_lookup_origin_visit(self, mock_storage): # given stub_result = self.origin_visit1 mock_storage.origin_visit_get_by.return_value = stub_result expected_origin_visit = { 'date': self.origin_visit1['date'].isoformat(), 'origin': self.origin_visit1['origin'], 'visit': self.origin_visit1['visit'] } # when actual_origin_visit = service.lookup_origin_visit(1, 1) # then self.assertEqual(actual_origin_visit, expected_origin_visit) mock_storage.origin_visit_get_by.assert_called_once_with(1, 1) @patch('swh.web.common.service.storage') def test_lookup_origin(self, mock_storage): # given mock_storage.origin_get = MagicMock(return_value={ 'id': 'origin-id', 'url': 'ftp://some/url/to/origin', 'type': 'ftp'}) # when actual_origin = service.lookup_origin({'id': 'origin-id'}) # then self.assertEqual(actual_origin, {'id': 'origin-id', 'url': 'ftp://some/url/to/origin', 'type': 'ftp'}) mock_storage.origin_get.assert_called_with({'id': 'origin-id'}) @patch('swh.web.common.service.storage') def test_lookup_release_ko_id_checksum_not_a_sha1(self, mock_storage): # given mock_storage.release_get = MagicMock() with self.assertRaises(BadInputExc) as cm: # when service.lookup_release('not-a-sha1') self.assertIn('invalid checksum', cm.exception.args[0].lower()) mock_storage.release_get.called = False @patch('swh.web.common.service.storage') def test_lookup_release_ko_id_checksum_too_long(self, mock_storage): # given mock_storage.release_get = MagicMock() # when with self.assertRaises(BadInputExc) as cm: service.lookup_release( '13c1d34d138ec13b5ebad226dc2528dc7506c956e4646f62d4daf5' '1aea892abe') self.assertEqual('Only sha1_git is supported.', cm.exception.args[0]) mock_storage.release_get.called = False @patch('swh.web.common.service.storage') def test_lookup_directory_with_path_not_found(self, mock_storage): # given mock_storage.lookup_directory_with_path = MagicMock(return_value=None) sha1_git = '65a55bbdf3629f916219feb3dcc7393ded1bc8db' # when actual_directory = mock_storage.lookup_directory_with_path( sha1_git, 'some/path/here') self.assertIsNone(actual_directory) @patch('swh.web.common.service.storage') def test_lookup_directory_with_path_found(self, mock_storage): # given sha1_git = '65a55bbdf3629f916219feb3dcc7393ded1bc8db' entry = {'id': 'dir-id', 'type': 'dir', 'name': 'some/path/foo'} mock_storage.lookup_directory_with_path = MagicMock(return_value=entry) # when actual_directory = mock_storage.lookup_directory_with_path( sha1_git, 'some/path/here') self.assertEqual(entry, actual_directory) @patch('swh.web.common.service.storage') def test_lookup_release(self, mock_storage): # given mock_storage.release_get = MagicMock(return_value=[{ 'id': hash_to_bytes('65a55bbdf3629f916219feb3dcc7393ded1bc8db'), 'target': None, 'date': { 'timestamp': datetime.datetime( 2015, 1, 1, 22, 0, 0, tzinfo=datetime.timezone.utc).timestamp(), 'offset': 0, 'negative_utc': True, }, 'name': b'v0.0.1', 'message': b'synthetic release', 'synthetic': True, }]) # when actual_release = service.lookup_release( '65a55bbdf3629f916219feb3dcc7393ded1bc8db') # then self.assertEqual(actual_release, { 'id': '65a55bbdf3629f916219feb3dcc7393ded1bc8db', 'target': None, 'date': '2015-01-01T22:00:00-00:00', 'name': 'v0.0.1', 'message': 'synthetic release', 'synthetic': True, }) mock_storage.release_get.assert_called_with( [hash_to_bytes('65a55bbdf3629f916219feb3dcc7393ded1bc8db')]) def test_lookup_revision_with_context_ko_not_a_sha1_1(self): # given sha1_git = '13c1d34d138ec13b5ebad226dc2528dc7506c956e4646f62d4' \ 'daf51aea892abe' sha1_git_root = '65a55bbdf3629f916219feb3dcc7393ded1bc8db' # when with self.assertRaises(BadInputExc) as cm: service.lookup_revision_with_context(sha1_git_root, sha1_git) self.assertIn('Only sha1_git is supported', cm.exception.args[0]) def test_lookup_revision_with_context_ko_not_a_sha1_2(self): # given sha1_git_root = '65a55bbdf3629f916219feb3dcc7393ded1bc8db' sha1_git = '13c1d34d138ec13b5ebad226dc2528dc7506c956e4646f6' \ '2d4daf51aea892abe' # when with self.assertRaises(BadInputExc) as cm: service.lookup_revision_with_context(sha1_git_root, sha1_git) self.assertIn('Only sha1_git is supported', cm.exception.args[0]) @patch('swh.web.common.service.storage') def test_lookup_revision_with_context_ko_sha1_git_does_not_exist( self, mock_storage): # given sha1_git_root = '65a55bbdf3629f916219feb3dcc7393ded1bc8db' sha1_git = '777777bdf3629f916219feb3dcc7393ded1bc8db' sha1_git_bin = hash_to_bytes(sha1_git) mock_storage.revision_get.return_value = None # when with self.assertRaises(NotFoundExc) as cm: service.lookup_revision_with_context(sha1_git_root, sha1_git) self.assertIn('Revision 777777bdf3629f916219feb3dcc7393ded1bc8db' ' not found', cm.exception.args[0]) mock_storage.revision_get.assert_called_once_with( [sha1_git_bin]) @patch('swh.web.common.service.storage') def test_lookup_revision_with_context_ko_root_sha1_git_does_not_exist( self, mock_storage): # given sha1_git_root = '65a55bbdf3629f916219feb3dcc7393ded1bc8db' sha1_git = '777777bdf3629f916219feb3dcc7393ded1bc8db' sha1_git_root_bin = hash_to_bytes(sha1_git_root) sha1_git_bin = hash_to_bytes(sha1_git) mock_storage.revision_get.side_effect = ['foo', None] # when with self.assertRaises(NotFoundExc) as cm: service.lookup_revision_with_context(sha1_git_root, sha1_git) self.assertIn('Revision root 65a55bbdf3629f916219feb3dcc7393ded1bc8db' ' not found', cm.exception.args[0]) mock_storage.revision_get.assert_has_calls([call([sha1_git_bin]), call([sha1_git_root_bin])]) @patch('swh.web.common.service.storage') @patch('swh.web.common.service.query') def test_lookup_revision_with_context(self, mock_query, mock_storage): # given sha1_git_root = '666' sha1_git = '883' sha1_git_root_bin = b'666' sha1_git_bin = b'883' sha1_git_root_dict = { 'id': sha1_git_root_bin, 'parents': [b'999'], } sha1_git_dict = { 'id': sha1_git_bin, 'parents': [], 'directory': b'278', } stub_revisions = [ sha1_git_root_dict, { 'id': b'999', 'parents': [b'777', b'883', b'888'], }, { 'id': b'777', 'parents': [b'883'], }, sha1_git_dict, { 'id': b'888', 'parents': [b'889'], }, { 'id': b'889', 'parents': [], }, ] # inputs ok mock_query.parse_hash_with_algorithms_or_throws.side_effect = [ ('sha1', sha1_git_bin), ('sha1', sha1_git_root_bin) ] # lookup revision first 883, then 666 (both exists) mock_storage.revision_get.return_value = [ sha1_git_dict, sha1_git_root_dict ] mock_storage.revision_log = MagicMock( return_value=stub_revisions) # when actual_revision = service.lookup_revision_with_context( sha1_git_root, sha1_git) # then self.assertEqual(actual_revision, { 'id': hash_to_hex(sha1_git_bin), 'parents': [], 'children': [hash_to_hex(b'999'), hash_to_hex(b'777')], 'directory': hash_to_hex(b'278'), 'merge': False }) mock_query.parse_hash_with_algorithms_or_throws.assert_has_calls( [call(sha1_git, ['sha1'], 'Only sha1_git is supported.'), call(sha1_git_root, ['sha1'], 'Only sha1_git is supported.')]) mock_storage.revision_log.assert_called_with( [sha1_git_root_bin], 100) @patch('swh.web.common.service.storage') @patch('swh.web.common.service.query') def test_lookup_revision_with_context_retrieved_as_dict( self, mock_query, mock_storage): # given sha1_git = '883' sha1_git_root_bin = b'666' sha1_git_bin = b'883' sha1_git_root_dict = { 'id': sha1_git_root_bin, 'parents': [b'999'], } sha1_git_dict = { 'id': sha1_git_bin, 'parents': [], 'directory': b'278', } stub_revisions = [ sha1_git_root_dict, { 'id': b'999', 'parents': [b'777', b'883', b'888'], }, { 'id': b'777', 'parents': [b'883'], }, sha1_git_dict, { 'id': b'888', 'parents': [b'889'], }, { 'id': b'889', 'parents': [], }, ] # inputs ok mock_query.parse_hash_with_algorithms_or_throws.return_value = ( 'sha1', sha1_git_bin) # lookup only on sha1 mock_storage.revision_get.return_value = [sha1_git_dict] mock_storage.revision_log.return_value = stub_revisions # when actual_revision = service.lookup_revision_with_context( {'id': sha1_git_root_bin}, sha1_git) # then self.assertEqual(actual_revision, { 'id': hash_to_hex(sha1_git_bin), 'parents': [], 'children': [hash_to_hex(b'999'), hash_to_hex(b'777')], 'directory': hash_to_hex(b'278'), 'merge': False }) mock_query.parse_hash_with_algorithms_or_throws.assert_called_once_with( # noqa sha1_git, ['sha1'], 'Only sha1_git is supported.') mock_storage.revision_get.assert_called_once_with([sha1_git_bin]) mock_storage.revision_log.assert_called_with( [sha1_git_root_bin], 100) @patch('swh.web.common.service.storage') @patch('swh.web.common.service.query') def test_lookup_directory_with_revision_not_found(self, mock_query, mock_storage): # given mock_query.parse_hash_with_algorithms_or_throws.return_value = ('sha1', b'123') mock_storage.revision_get.return_value = None # when with self.assertRaises(NotFoundExc) as cm: service.lookup_directory_with_revision('123') self.assertIn('Revision 123 not found', cm.exception.args[0]) mock_query.parse_hash_with_algorithms_or_throws.assert_called_once_with ('123', ['sha1'], 'Only sha1_git is supported.') mock_storage.revision_get.assert_called_once_with([b'123']) @patch('swh.web.common.service.storage') @patch('swh.web.common.service.query') def test_lookup_directory_with_revision_ko_revision_with_path_to_nowhere( self, mock_query, mock_storage): # given mock_query.parse_hash_with_algorithms_or_throws.return_value = ('sha1', b'123') dir_id = b'dir-id-as-sha1' mock_storage.revision_get.return_value = [{ 'directory': dir_id, }] mock_storage.directory_entry_get_by_path.return_value = None # when with self.assertRaises(NotFoundExc) as cm: service.lookup_directory_with_revision( '123', 'path/to/something/unknown') exception_text = cm.exception.args[0].lower() self.assertIn('directory or file', exception_text) self.assertIn('path/to/something/unknown', exception_text) self.assertIn('revision 123', exception_text) self.assertIn('not found', exception_text) mock_query.parse_hash_with_algorithms_or_throws.assert_called_once_with ('123', ['sha1'], 'Only sha1_git is supported.') mock_storage.revision_get.assert_called_once_with([b'123']) mock_storage.directory_entry_get_by_path.assert_called_once_with( b'dir-id-as-sha1', [b'path', b'to', b'something', b'unknown']) @patch('swh.web.common.service.storage') @patch('swh.web.common.service.query') def test_lookup_directory_with_revision_ko_type_not_implemented( self, mock_query, mock_storage): # given mock_query.parse_hash_with_algorithms_or_throws.return_value = ('sha1', b'123') dir_id = b'dir-id-as-sha1' mock_storage.revision_get.return_value = [{ 'directory': dir_id, }] mock_storage.directory_entry_get_by_path.return_value = { 'type': 'rev', 'name': b'some/path/to/rev', 'target': b'456' } stub_content = { 'id': b'12', 'type': 'file' } mock_storage.content_get.return_value = stub_content # when with self.assertRaises(NotImplementedError) as cm: service.lookup_directory_with_revision( '123', 'some/path/to/rev') self.assertIn("Entity of type rev not implemented.", cm.exception.args[0]) # then mock_query.parse_hash_with_algorithms_or_throws.assert_called_once_with ('123', ['sha1'], 'Only sha1_git is supported.') mock_storage.revision_get.assert_called_once_with([b'123']) mock_storage.directory_entry_get_by_path.assert_called_once_with( b'dir-id-as-sha1', [b'some', b'path', b'to', b'rev']) @patch('swh.web.common.service.storage') @patch('swh.web.common.service.query') def test_lookup_directory_with_revision_revision_without_path( self, mock_query, mock_storage, ): # given mock_query.parse_hash_with_algorithms_or_throws.return_value = ('sha1', b'123') dir_id = b'dir-id-as-sha1' mock_storage.revision_get.return_value = [{ 'directory': dir_id, }] stub_dir_entries = [{ 'id': b'123', 'type': 'dir' }, { 'id': b'456', 'type': 'file' }] mock_storage.directory_ls.return_value = stub_dir_entries # when actual_directory_entries = service.lookup_directory_with_revision( '123') self.assertEqual(actual_directory_entries['type'], 'dir') self.assertEqual(list(actual_directory_entries['content']), stub_dir_entries) mock_query.parse_hash_with_algorithms_or_throws.assert_called_once_with ('123', ['sha1'], 'Only sha1_git is supported.') mock_storage.revision_get.assert_called_once_with([b'123']) mock_storage.directory_ls.assert_called_once_with(dir_id) @patch('swh.web.common.service.storage') @patch('swh.web.common.service.query') def test_lookup_directory_with_revision_with_path_to_dir(self, mock_query, mock_storage): # given mock_query.parse_hash_with_algorithms_or_throws.return_value = ('sha1', b'123') dir_id = b'dir-id-as-sha1' mock_storage.revision_get.return_value = [{ 'directory': dir_id, }] stub_dir_entries = [{ 'id': b'12', 'type': 'dir' }, { 'id': b'34', 'type': 'file' }] mock_storage.directory_entry_get_by_path.return_value = { 'type': 'dir', 'name': b'some/path', 'target': b'456' } mock_storage.directory_ls.return_value = stub_dir_entries # when actual_directory_entries = service.lookup_directory_with_revision( '123', 'some/path') self.assertEqual(actual_directory_entries['type'], 'dir') self.assertEqual(actual_directory_entries['revision'], '123') self.assertEqual(actual_directory_entries['path'], 'some/path') self.assertEqual(list(actual_directory_entries['content']), stub_dir_entries) mock_query.parse_hash_with_algorithms_or_throws.assert_called_once_with ('123', ['sha1'], 'Only sha1_git is supported.') mock_storage.revision_get.assert_called_once_with([b'123']) mock_storage.directory_entry_get_by_path.assert_called_once_with( dir_id, [b'some', b'path']) mock_storage.directory_ls.assert_called_once_with(b'456') @patch('swh.web.common.service.storage') @patch('swh.web.common.service.query') def test_lookup_directory_with_revision_with_path_to_file_wo_data( self, mock_query, mock_storage): # given mock_query.parse_hash_with_algorithms_or_throws.return_value = ('sha1', b'123') dir_id = b'dir-id-as-sha1' mock_storage.revision_get.return_value = [{ 'directory': dir_id, }] mock_storage.directory_entry_get_by_path.return_value = { 'type': 'file', 'name': b'some/path/to/file', 'target': b'789' } stub_content = { 'status': 'visible', } mock_storage.content_find.return_value = stub_content # when actual_content = service.lookup_directory_with_revision( '123', 'some/path/to/file') # then self.assertEqual(actual_content, {'type': 'file', 'revision': '123', 'path': 'some/path/to/file', 'content': stub_content}) mock_query.parse_hash_with_algorithms_or_throws.assert_called_once_with ('123', ['sha1'], 'Only sha1_git is supported.') mock_storage.revision_get.assert_called_once_with([b'123']) mock_storage.directory_entry_get_by_path.assert_called_once_with( b'dir-id-as-sha1', [b'some', b'path', b'to', b'file']) mock_storage.content_find.assert_called_once_with({'sha1_git': b'789'}) @patch('swh.web.common.service.storage') @patch('swh.web.common.service.query') def test_lookup_directory_with_revision_with_path_to_file_w_data( self, mock_query, mock_storage): # given mock_query.parse_hash_with_algorithms_or_throws.return_value = ('sha1', b'123') dir_id = b'dir-id-as-sha1' mock_storage.revision_get.return_value = [{ 'directory': dir_id, }] mock_storage.directory_entry_get_by_path.return_value = { 'type': 'file', 'name': b'some/path/to/file', 'target': b'789' } stub_content = { 'status': 'visible', 'sha1': b'content-sha1' } mock_storage.content_find.return_value = stub_content mock_storage.content_get.return_value = [{ 'sha1': b'content-sha1', 'data': b'some raw data' }] expected_content = { 'status': 'visible', 'checksums': { 'sha1': hash_to_hex(b'content-sha1'), }, 'data': b'some raw data' } # when actual_content = service.lookup_directory_with_revision( '123', 'some/path/to/file', with_data=True) # then self.assertEqual(actual_content, {'type': 'file', 'revision': '123', 'path': 'some/path/to/file', 'content': expected_content}) mock_query.parse_hash_with_algorithms_or_throws.assert_called_once_with ('123', ['sha1'], 'Only sha1_git is supported.') mock_storage.revision_get.assert_called_once_with([b'123']) mock_storage.directory_entry_get_by_path.assert_called_once_with( b'dir-id-as-sha1', [b'some', b'path', b'to', b'file']) mock_storage.content_find.assert_called_once_with({'sha1_git': b'789'}) mock_storage.content_get.assert_called_once_with([b'content-sha1']) @patch('swh.web.common.service.storage') def test_lookup_revision(self, mock_storage): # given mock_storage.revision_get = MagicMock( return_value=[self.SAMPLE_REVISION_RAW]) # when actual_revision = service.lookup_revision( self.SHA1_SAMPLE) # then self.assertEqual(actual_revision, self.SAMPLE_REVISION) mock_storage.revision_get.assert_called_with( [self.SHA1_SAMPLE_BIN]) @patch('swh.web.common.service.storage') def test_lookup_revision_invalid_msg(self, mock_storage): # given stub_rev = self.SAMPLE_REVISION_RAW stub_rev['message'] = b'elegant fix for bug \xff' expected_revision = self.SAMPLE_REVISION expected_revision['message'] = None expected_revision['message_decoding_failed'] = True mock_storage.revision_get = MagicMock(return_value=[stub_rev]) # when actual_revision = service.lookup_revision( self.SHA1_SAMPLE) # then self.assertEqual(actual_revision, expected_revision) mock_storage.revision_get.assert_called_with( [self.SHA1_SAMPLE_BIN]) @patch('swh.web.common.service.storage') def test_lookup_revision_msg_ok(self, mock_storage): # given mock_storage.revision_get.return_value = [self.SAMPLE_REVISION_RAW] # when rv = service.lookup_revision_message( self.SHA1_SAMPLE) # then self.assertEqual(rv, {'message': self.SAMPLE_MESSAGE_BIN}) mock_storage.revision_get.assert_called_with( [self.SHA1_SAMPLE_BIN]) @patch('swh.web.common.service.storage') def test_lookup_revision_msg_absent(self, mock_storage): # given stub_revision = self.SAMPLE_REVISION_RAW del stub_revision['message'] mock_storage.revision_get.return_value = stub_revision # when with self.assertRaises(NotFoundExc) as cm: service.lookup_revision_message( self.SHA1_SAMPLE) # then mock_storage.revision_get.assert_called_with( [self.SHA1_SAMPLE_BIN]) self.assertEqual( cm.exception.args[0], 'No message for revision with sha1_git %s.' % self.SHA1_SAMPLE, ) @patch('swh.web.common.service.storage') def test_lookup_revision_msg_norev(self, mock_storage): # given mock_storage.revision_get.return_value = None # when with self.assertRaises(NotFoundExc) as cm: service.lookup_revision_message( self.SHA1_SAMPLE) # then mock_storage.revision_get.assert_called_with( [self.SHA1_SAMPLE_BIN]) self.assertEqual( cm.exception.args[0], 'Revision with sha1_git %s not found.' % self.SHA1_SAMPLE, ) @patch('swh.web.common.service.storage') def test_lookup_revision_multiple(self, mock_storage): # given sha1 = self.SHA1_SAMPLE sha1_other = 'adc83b19e793491b1c6ea0fd8b46cd9f32e592fc' stub_revisions = [ self.SAMPLE_REVISION_RAW, { 'id': hash_to_bytes(sha1_other), 'directory': 'abcdbe353ed3480476f032475e7c233eff7371d5', 'author': { 'name': b'name', 'email': b'name@surname.org', }, 'committer': { 'name': b'name', 'email': b'name@surname.org', }, 'message': b'ugly fix for bug 42', 'date': { 'timestamp': datetime.datetime( 2000, 1, 12, 5, 23, 54, tzinfo=datetime.timezone.utc).timestamp(), 'offset': 0, 'negative_utc': False }, 'date_offset': 0, 'committer_date': { 'timestamp': datetime.datetime( 2000, 1, 12, 5, 23, 54, tzinfo=datetime.timezone.utc).timestamp(), 'offset': 0, 'negative_utc': False }, 'committer_date_offset': 0, 'synthetic': False, 'type': 'git', 'parents': [], 'metadata': [], } ] mock_storage.revision_get.return_value = stub_revisions # when actual_revisions = service.lookup_revision_multiple( [sha1, sha1_other]) # then self.assertEqual(list(actual_revisions), [ self.SAMPLE_REVISION, { 'id': sha1_other, 'directory': 'abcdbe353ed3480476f032475e7c233eff7371d5', 'author': { 'name': 'name', 'email': 'name@surname.org', }, 'committer': { 'name': 'name', 'email': 'name@surname.org', }, 'message': 'ugly fix for bug 42', 'date': '2000-01-12T05:23:54+00:00', 'date_offset': 0, 'committer_date': '2000-01-12T05:23:54+00:00', 'committer_date_offset': 0, 'synthetic': False, 'type': 'git', 'parents': [], 'metadata': {}, 'merge': False } ]) self.assertEqual( list(mock_storage.revision_get.call_args[0][0]), [hash_to_bytes(sha1), hash_to_bytes(sha1_other)]) @patch('swh.web.common.service.storage') def test_lookup_revision_multiple_none_found(self, mock_storage): # given sha1_bin = self.SHA1_SAMPLE sha1_other = 'adc83b19e793491b1c6ea0fd8b46cd9f32e592fc' mock_storage.revision_get.return_value = [] # then actual_revisions = service.lookup_revision_multiple( [sha1_bin, sha1_other]) self.assertEqual(list(actual_revisions), []) self.assertEqual( list(mock_storage.revision_get.call_args[0][0]), [hash_to_bytes(self.SHA1_SAMPLE), hash_to_bytes(sha1_other)]) @patch('swh.web.common.service.storage') def test_lookup_revision_log(self, mock_storage): # given stub_revision_log = [self.SAMPLE_REVISION_RAW] mock_storage.revision_log = MagicMock(return_value=stub_revision_log) # when actual_revision = service.lookup_revision_log( 'abcdbe353ed3480476f032475e7c233eff7371d5', limit=25) # then self.assertEqual(list(actual_revision), [self.SAMPLE_REVISION]) mock_storage.revision_log.assert_called_with( [hash_to_bytes('abcdbe353ed3480476f032475e7c233eff7371d5')], 25) @patch('swh.web.common.service.storage') def test_lookup_revision_log_by(self, mock_storage): # given stub_revision_log = [self.SAMPLE_REVISION_RAW] mock_storage.revision_log_by = MagicMock( return_value=stub_revision_log) # when actual_log = service.lookup_revision_log_by( 1, 'refs/heads/master', None, limit=100) # then self.assertEqual(list(actual_log), [self.SAMPLE_REVISION]) mock_storage.revision_log_by.assert_called_with( 1, 'refs/heads/master', None, limit=100) @patch('swh.web.common.service.storage') def test_lookup_revision_log_by_nolog(self, mock_storage): # given mock_storage.revision_log_by = MagicMock(return_value=None) # when res = service.lookup_revision_log_by( 1, 'refs/heads/master', None, limit=100) # then self.assertEqual(res, None) mock_storage.revision_log_by.assert_called_with( 1, 'refs/heads/master', None, limit=100) @patch('swh.web.common.service.storage') def test_lookup_content_raw_not_found(self, mock_storage): # given mock_storage.content_find = MagicMock(return_value=None) # when with self.assertRaises(NotFoundExc) as cm: service.lookup_content_raw('sha1:' + self.SHA1_SAMPLE) self.assertIn(cm.exception.args[0], 'Content with %s checksum equals to %s not found!' % ('sha1', self.SHA1_SAMPLE)) mock_storage.content_find.assert_called_with( {'sha1': hash_to_bytes(self.SHA1_SAMPLE)}) @patch('swh.web.common.service.storage') def test_lookup_content_raw(self, mock_storage): # given mock_storage.content_find = MagicMock(return_value={ 'sha1': self.SHA1_SAMPLE, }) mock_storage.content_get = MagicMock(return_value=[{ 'data': b'binary data'}]) # when actual_content = service.lookup_content_raw( 'sha256:%s' % self.SHA256_SAMPLE) # then self.assertEqual(actual_content, {'data': b'binary data'}) mock_storage.content_find.assert_called_once_with( {'sha256': self.SHA256_SAMPLE_BIN}) mock_storage.content_get.assert_called_once_with( [self.SHA1_SAMPLE]) @patch('swh.web.common.service.storage') def test_lookup_content_not_found(self, mock_storage): # given mock_storage.content_find = MagicMock(return_value=None) # when with self.assertRaises(NotFoundExc) as cm: # then service.lookup_content('sha1:%s' % self.SHA1_SAMPLE) self.assertIn(cm.exception.args[0], 'Content with %s checksum equals to %s not found!' % ('sha1', self.SHA1_SAMPLE)) mock_storage.content_find.assert_called_with( {'sha1': self.SHA1_SAMPLE_BIN}) @patch('swh.web.common.service.storage') def test_lookup_content_with_sha1(self, mock_storage): # given mock_storage.content_find = MagicMock( return_value=self.SAMPLE_CONTENT_RAW) # when actual_content = service.lookup_content( 'sha1:%s' % self.SHA1_SAMPLE) # then self.assertEqual(actual_content, self.SAMPLE_CONTENT) mock_storage.content_find.assert_called_with( {'sha1': hash_to_bytes(self.SHA1_SAMPLE)}) @patch('swh.web.common.service.storage') def test_lookup_content_with_sha256(self, mock_storage): # given stub_content = self.SAMPLE_CONTENT_RAW stub_content['status'] = 'visible' expected_content = self.SAMPLE_CONTENT expected_content['status'] = 'visible' mock_storage.content_find = MagicMock( return_value=stub_content) # when actual_content = service.lookup_content( 'sha256:%s' % self.SHA256_SAMPLE) # then self.assertEqual(actual_content, expected_content) mock_storage.content_find.assert_called_with( {'sha256': self.SHA256_SAMPLE_BIN}) @patch('swh.web.common.service.storage') def test_lookup_person(self, mock_storage): # given mock_storage.person_get = MagicMock(return_value=[{ 'id': 'person_id', 'name': b'some_name', 'email': b'some-email', }]) # when actual_person = service.lookup_person('person_id') # then self.assertEqual(actual_person, { 'id': 'person_id', 'name': 'some_name', 'email': 'some-email', }) mock_storage.person_get.assert_called_with(['person_id']) @patch('swh.web.common.service.storage') def test_lookup_directory_bad_checksum(self, mock_storage): # given mock_storage.directory_ls = MagicMock() # when with self.assertRaises(BadInputExc): service.lookup_directory('directory_id') # then mock_storage.directory_ls.called = False @patch('swh.web.common.service.storage') @patch('swh.web.common.service.query') def test_lookup_directory_not_found(self, mock_query, mock_storage): # given mock_query.parse_hash_with_algorithms_or_throws.return_value = ( 'sha1', 'directory-id-bin') mock_storage.directory_ls.return_value = [] # when with self.assertRaises(NotFoundExc) as cm: service.lookup_directory('directory_id') self.assertIn('Directory with sha1_git directory_id not found', cm.exception.args[0]) # then mock_query.parse_hash_with_algorithms_or_throws.assert_called_with( 'directory_id', ['sha1'], 'Only sha1_git is supported.') mock_storage.directory_ls.assert_called_with('directory-id-bin') @patch('swh.web.common.service.storage') @patch('swh.web.common.service.query') def test_lookup_directory(self, mock_query, mock_storage): mock_query.parse_hash_with_algorithms_or_throws.return_value = ( 'sha1', 'directory-sha1-bin') # given stub_dir_entries = [{ 'sha1': self.SHA1_SAMPLE_BIN, 'sha256': self.SHA256_SAMPLE_BIN, 'sha1_git': self.SHA1GIT_SAMPLE_BIN, 'blake2s256': self.BLAKE2S256_SAMPLE_BIN, 'target': hash_to_bytes( '40e71b8614fcd89ccd17ca2b1d9e66c5b00a6d03'), 'dir_id': self.DIRECTORY_ID_BIN, 'name': b'bob', 'type': 10, }] expected_dir_entries = [{ 'checksums': { 'sha1': self.SHA1_SAMPLE, 'sha256': self.SHA256_SAMPLE, 'sha1_git': self.SHA1GIT_SAMPLE, 'blake2s256': self.BLAKE2S256_SAMPLE }, 'target': '40e71b8614fcd89ccd17ca2b1d9e66c5b00a6d03', 'dir_id': self.DIRECTORY_ID, 'name': 'bob', 'type': 10, }] mock_storage.directory_ls.return_value = stub_dir_entries # when actual_directory_ls = list(service.lookup_directory( 'directory-sha1')) # then self.assertEqual(actual_directory_ls, expected_dir_entries) mock_query.parse_hash_with_algorithms_or_throws.assert_called_with( 'directory-sha1', ['sha1'], 'Only sha1_git is supported.') mock_storage.directory_ls.assert_called_with( 'directory-sha1-bin') @patch('swh.web.common.service.storage') def test_lookup_directory_empty(self, mock_storage): empty_dir_sha1 = '4b825dc642cb6eb9a060e54bf8d69288fbee4904' mock_storage.directory_ls.return_value = [] # when actual_directory_ls = list(service.lookup_directory(empty_dir_sha1)) # then self.assertEqual(actual_directory_ls, []) self.assertFalse(mock_storage.directory_ls.called) @patch('swh.web.common.service.storage') def test_lookup_revision_by_nothing_found(self, mock_storage): # given mock_storage.revision_get_by.return_value = None # when with self.assertRaises(NotFoundExc): service.lookup_revision_by(1) # then mock_storage.revision_get_by.assert_called_with(1, 'refs/heads/master', # noqa limit=1, timestamp=None) @patch('swh.web.common.service.storage') def test_lookup_revision_by(self, mock_storage): # given stub_rev = self.SAMPLE_REVISION_RAW expected_rev = self.SAMPLE_REVISION mock_storage.revision_get_by.return_value = [stub_rev] # when actual_revision = service.lookup_revision_by(10, 'master2', 'some-ts') # then self.assertEqual(actual_revision, expected_rev) mock_storage.revision_get_by.assert_called_with(10, 'master2', limit=1, timestamp='some-ts') @patch('swh.web.common.service.storage') def test_lookup_revision_by_nomerge(self, mock_storage): # given stub_rev = self.SAMPLE_REVISION_RAW stub_rev['parents'] = [ hash_to_bytes('adc83b19e793491b1c6ea0fd8b46cd9f32e592fc')] expected_rev = self.SAMPLE_REVISION expected_rev['parents'] = ['adc83b19e793491b1c6ea0fd8b46cd9f32e592fc'] mock_storage.revision_get_by.return_value = [stub_rev] # when actual_revision = service.lookup_revision_by(10, 'master2', 'some-ts') # then self.assertEqual(actual_revision, expected_rev) mock_storage.revision_get_by.assert_called_with(10, 'master2', limit=1, timestamp='some-ts') @patch('swh.web.common.service.storage') def test_lookup_revision_by_merge(self, mock_storage): # given stub_rev = self.SAMPLE_REVISION_RAW stub_rev['parents'] = [ hash_to_bytes('adc83b19e793491b1c6ea0fd8b46cd9f32e592fc'), hash_to_bytes('ffff3b19e793491b1c6db0fd8b46cd9f32e592fc') ] expected_rev = self.SAMPLE_REVISION expected_rev['parents'] = [ 'adc83b19e793491b1c6ea0fd8b46cd9f32e592fc', 'ffff3b19e793491b1c6db0fd8b46cd9f32e592fc' ] expected_rev['merge'] = True mock_storage.revision_get_by.return_value = [stub_rev] # when actual_revision = service.lookup_revision_by(10, 'master2', 'some-ts') # then self.assertEqual(actual_revision, expected_rev) mock_storage.revision_get_by.assert_called_with(10, 'master2', limit=1, timestamp='some-ts') @patch('swh.web.common.service.storage') def test_lookup_revision_with_context_by_ko(self, mock_storage): # given mock_storage.revision_get_by.return_value = None # when origin_id = 1 branch_name = 'master3' ts = None with self.assertRaises(NotFoundExc) as cm: service.lookup_revision_with_context_by(origin_id, branch_name, ts, 'sha1') # then self.assertIn( 'Revision with (origin_id: %s, branch_name: %s' ', ts: %s) not found.' % (origin_id, branch_name, ts), cm.exception.args[0]) mock_storage.revision_get_by.assert_called_once_with( origin_id, branch_name, limit=1, timestamp=ts) @patch('swh.web.common.service.lookup_revision_with_context') @patch('swh.web.common.service.storage') def test_lookup_revision_with_context_by( self, mock_storage, mock_lookup_revision_with_context, ): # given stub_root_rev = {'id': 'root-rev-id'} mock_storage.revision_get_by.return_value = [{'id': 'root-rev-id'}] stub_rev = {'id': 'rev-found'} mock_lookup_revision_with_context.return_value = stub_rev # when origin_id = 1 branch_name = 'master3' ts = None sha1_git = 'sha1' actual_root_rev, actual_rev = service.lookup_revision_with_context_by( origin_id, branch_name, ts, sha1_git) # then self.assertEqual(actual_root_rev, stub_root_rev) self.assertEqual(actual_rev, stub_rev) mock_storage.revision_get_by.assert_called_once_with( origin_id, branch_name, limit=1, timestamp=ts) mock_lookup_revision_with_context.assert_called_once_with( stub_root_rev, sha1_git, 100) @patch('swh.web.common.service.storage') @patch('swh.web.common.service.query') def test_lookup_entity_by_uuid(self, mock_query, mock_storage): # given uuid_test = 'correct-uuid' mock_query.parse_uuid4.return_value = uuid_test stub_entities = [{'uuid': uuid_test}] mock_storage.entity_get.return_value = stub_entities # when actual_entities = list(service.lookup_entity_by_uuid(uuid_test)) # then self.assertEqual(actual_entities, stub_entities) mock_query.parse_uuid4.assert_called_once_with(uuid_test) mock_storage.entity_get.assert_called_once_with(uuid_test) def test_lookup_revision_through_ko_not_implemented(self): # then with self.assertRaises(NotImplementedError): service.lookup_revision_through({ 'something-unknown': 10, }) @patch('swh.web.common.service.lookup_revision_with_context_by') def test_lookup_revision_through_with_context_by(self, mock_lookup): # given stub_rev = {'id': 'rev'} mock_lookup.return_value = stub_rev # when actual_revision = service.lookup_revision_through({ 'origin_id': 1, 'branch_name': 'master', 'ts': None, 'sha1_git': 'sha1-git' }, limit=1000) # then self.assertEqual(actual_revision, stub_rev) mock_lookup.assert_called_once_with( 1, 'master', None, 'sha1-git', 1000) @patch('swh.web.common.service.lookup_revision_by') def test_lookup_revision_through_with_revision_by(self, mock_lookup): # given stub_rev = {'id': 'rev'} mock_lookup.return_value = stub_rev # when actual_revision = service.lookup_revision_through({ 'origin_id': 2, 'branch_name': 'master2', 'ts': 'some-ts', }, limit=10) # then self.assertEqual(actual_revision, stub_rev) mock_lookup.assert_called_once_with( 2, 'master2', 'some-ts') @patch('swh.web.common.service.lookup_revision_with_context') def test_lookup_revision_through_with_context(self, mock_lookup): # given stub_rev = {'id': 'rev'} mock_lookup.return_value = stub_rev # when actual_revision = service.lookup_revision_through({ 'sha1_git_root': 'some-sha1-root', 'sha1_git': 'some-sha1', }) # then self.assertEqual(actual_revision, stub_rev) mock_lookup.assert_called_once_with( 'some-sha1-root', 'some-sha1', 100) @patch('swh.web.common.service.lookup_revision') def test_lookup_revision_through_with_revision(self, mock_lookup): # given stub_rev = {'id': 'rev'} mock_lookup.return_value = stub_rev # when actual_revision = service.lookup_revision_through({ 'sha1_git': 'some-sha1', }) # then self.assertEqual(actual_revision, stub_rev) mock_lookup.assert_called_once_with( 'some-sha1') @patch('swh.web.common.service.lookup_revision_through') def test_lookup_directory_through_revision_ko_not_found( self, mock_lookup_rev): # given mock_lookup_rev.return_value = None # when with self.assertRaises(NotFoundExc): service.lookup_directory_through_revision( {'id': 'rev'}, 'some/path', 100) mock_lookup_rev.assert_called_once_with({'id': 'rev'}, 100) @patch('swh.web.common.service.lookup_revision_through') @patch('swh.web.common.service.lookup_directory_with_revision') def test_lookup_directory_through_revision_ok_with_data( self, mock_lookup_dir, mock_lookup_rev): # given mock_lookup_rev.return_value = {'id': 'rev-id'} mock_lookup_dir.return_value = {'type': 'dir', 'content': []} # when rev_id, dir_result = service.lookup_directory_through_revision( {'id': 'rev'}, 'some/path', 100) # then self.assertEqual(rev_id, 'rev-id') self.assertEqual(dir_result, {'type': 'dir', 'content': []}) mock_lookup_rev.assert_called_once_with({'id': 'rev'}, 100) mock_lookup_dir.assert_called_once_with('rev-id', 'some/path', False) @patch('swh.web.common.service.lookup_revision_through') @patch('swh.web.common.service.lookup_directory_with_revision') def test_lookup_directory_through_revision_ok_with_content( self, mock_lookup_dir, mock_lookup_rev): # given mock_lookup_rev.return_value = {'id': 'rev-id'} stub_result = {'type': 'file', 'revision': 'rev-id', 'content': {'data': b'blah', 'sha1': 'sha1'}} mock_lookup_dir.return_value = stub_result # when rev_id, dir_result = service.lookup_directory_through_revision( {'id': 'rev'}, 'some/path', 10, with_data=True) # then self.assertEqual(rev_id, 'rev-id') self.assertEqual(dir_result, stub_result) mock_lookup_rev.assert_called_once_with({'id': 'rev'}, 10) mock_lookup_dir.assert_called_once_with('rev-id', 'some/path', True)