diff --git a/MANIFEST.in b/MANIFEST.in index 4c357df7..6605f276 100644 --- a/MANIFEST.in +++ b/MANIFEST.in @@ -1,18 +1,16 @@ include Makefile include pytest.ini include README.md include requirements.txt include requirements-swh.txt include requirements-test.txt include tox.ini include version.txt recursive-include swh/web/assets * recursive-include swh/web/static * recursive-include swh/web/templates * -include swh/web/tests/browse/views/data/swh-logo.png -include swh/web/tests/browse/views/data/iso-8859-1_encoded_content recursive-include swh/web/tests/resources * include package-lock.json include package.json include yarn.lock diff --git a/swh/web/browse/utils.py b/swh/web/browse/utils.py index 82201c39..50b753dc 100644 --- a/swh/web/browse/utils.py +++ b/swh/web/browse/utils.py @@ -1,1123 +1,1129 @@ -# Copyright (C) 2017-2018 The Software Heritage developers +# Copyright (C) 2017-2019 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 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.origin_visits import get_origin_visit from swh.web.common.utils import ( reverse, format_utc_iso_date, 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 _reencode_content(mimetype, encoding, content_data): + # encode textual content to utf-8 if needed + if 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 = content_data.decode('utf-8', 'replace')\ + .encode('utf-8') + elif 'ascii' not in encoding and encoding not in ['utf-8', 'binary']: + content_data = content_data.decode(encoding, 'replace')\ + .encode('utf-8') + elif 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 = content_data.decode(encoding)\ + .encode('utf-8') + except Exception: + pass + else: + # ensure display in content view + mimetype = 'text/plain' + break + return mimetype, content_data + + 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 + if reencode: + mimetype, raw_data = _reencode_content( + mimetype, encoding, content_data['raw_data']) + content_data['raw_data'] = raw_data + 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 process_snapshot_branches(snapshot): """ 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 snapshot_branches = snapshot['branches'] branches = {} branch_aliases = {} 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) elif target_type == 'alias': branch_aliases[branch_name] = target_id # FIXME: handle pointers to other object types def _enrich_release_branch(branch, release): 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'], } def _enrich_revision_branch(branch, revision): branches[branch].update({ 'revision': revision['id'], 'directory': revision['directory'], 'date': format_utc_iso_date(revision['date']), 'message': revision['message'] }) 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: _enrich_release_branch(branch, release) 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 for branch in revision_to_branch[revision['id']]: _enrich_revision_branch(branch, revision) for release in revision_to_release[revision['id']]: releases[release]['directory'] = revision['directory'] for branch_alias, branch_target in branch_aliases.items(): if branch_target in branches: branches[branch_alias] = dict(branches[branch_target]) else: snp = service.lookup_snapshot(snapshot['id'], branches_from=branch_target, branches_count=1) if snp and branch_target in snp['branches']: target_type = snp['branches'][branch_target]['target_type'] target = snp['branches'][branch_target]['target'] if target_type == 'revision': branches[branch_alias] = snp['branches'][branch_target] revision = service.lookup_revision(target) _enrich_revision_branch(branch_alias, revision) elif target_type == 'release': release = service.lookup_release(target) _enrich_release_branch(branch_alias, release) if branch_alias in branches: branches[branch_alias]['name'] = branch_alias 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) 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 if rev['message']: 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}, query_params={'reencode': 'true'}) 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}, query_params={'reencode': 'true'}) # 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/tests/browse/views/data/content_test_data.py b/swh/web/tests/browse/views/data/content_test_data.py index 3250a594..75a6fc75 100644 --- a/swh/web/tests/browse/views/data/content_test_data.py +++ b/swh/web/tests/browse/views/data/content_test_data.py @@ -1,232 +1,83 @@ -# Copyright (C) 2017-2018 The Software Heritage developers +# Copyright (C) 2017-2019 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 # flake8: noqa import os stub_content_root_dir = '08e8329257dad3a3ef7adea48aa6e576cd82de5b' stub_content_text_file = \ """ /* This file is part of the KDE project * * This library is free software; you can redistribute it and/or * modify it under the terms of the GNU Library General Public * License as published by the Free Software Foundation; either * version 2 of the License, or (at your option) any later version. * * This library is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * Library General Public License for more details. * * You should have received a copy of the GNU Library General Public License * along with this library; see the file COPYING.LIB. If not, write to * the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, * Boston, MA 02110-1301, USA. */ #ifndef KATE_SESSION_TEST_H #define KATE_SESSION_TEST_H #include class KateSessionTest : public QObject { Q_OBJECT private Q_SLOTS: void init(); void cleanup(); void initTestCase(); void cleanupTestCase(); void create(); void createAnonymous(); void createAnonymousFrom(); void createFrom(); void documents(); void setFile(); void setName(); void timestamp(); private: class QTemporaryFile *m_tmpfile; }; #endif """ -stub_content_text_file_no_highlight = \ -""" - GNU GENERAL PUBLIC LICENSE - Version 3, 29 June 2007 - - Copyright (C) 2007 Free Software Foundation, Inc. - Everyone is permitted to copy and distribute verbatim copies - of this license document, but changing it is not allowed. - - Preamble - - The GNU General Public License is a free, copyleft license for -software and other kinds of works. - - The licenses for most software and other practical works are designed -to take away your freedom to share and change the works. By contrast, -the GNU General Public License is intended to guarantee your freedom to -share and change all versions of a program--to make sure it remains free -software for all its users. We, the Free Software Foundation, use the -GNU General Public License for most of our software; it applies also to -any other work released this way by its authors. You can apply it to -your programs, too. - - When we speak of free software, we are referring to freedom, not -price. Our General Public Licenses are designed to make sure that you -have the freedom to distribute copies of free software (and charge for -them if you wish), that you receive source code or can get it if you -want it, that you can change the software or use pieces of it in new -free programs, and that you know you can do these things. - - To protect your rights, we need to prevent others from denying you -these rights or asking you to surrender the rights. Therefore, you have -certain responsibilities if you distribute copies of the software, or if -you modify it: responsibilities to respect the freedom of others. - - For example, if you distribute copies of such a program, whether -gratis or for a fee, you must pass on to the recipients the same -freedoms that you received. You must make sure that they, too, receive -or can get the source code. And you must show them these terms so they -know their rights. - - Developers that use the GNU GPL protect your rights with two steps: -(1) assert copyright on the software, and (2) offer you this License -giving you legal permission to copy, distribute and/or modify it. - - For the developers' and authors' protection, the GPL clearly explains -that there is no warranty for this free software. For both users' and -authors' sake, the GPL requires that modified versions be marked as -changed, so that their problems will not be attributed erroneously to -authors of previous versions. - - Some devices are designed to deny users access to install or run -modified versions of the software inside them, although the manufacturer -can do so. This is fundamentally incompatible with the aim of -protecting users' freedom to change the software. The systematic -pattern of such abuse occurs in the area of products for individuals to -use, which is precisely where it is most unacceptable. Therefore, we -have designed this version of the GPL to prohibit the practice for those -products. If such problems arise substantially in other domains, we -stand ready to extend this provision to those domains in future versions -of the GPL, as needed to protect the freedom of users. - - Finally, every program is threatened constantly by software patents. -States should not allow patents to restrict development and use of -software on general-purpose computers, but in those that do, we wish to -avoid the special danger that patents applied to a free program could -make it effectively proprietary. To prevent this, the GPL assures that -patents cannot be used to render the program non-free. -""" - stub_content_text_data = { 'checksums': { 'sha1': '5ecd9f37b7a2d2e9980d201acd6286116f2ba1f1', 'sha1_git': '537b47f68469c1c916c1bfbc072599133bfcbb21', 'sha256': 'b3057544f04e5821ab0e2a007e2ceabd7de2dfb1d42a764f1de8d0d2eff80006', 'blake2s256': '25117fa9f124d5b771a0a7dfca9c7a57247d81f8343334b4b41c782c7f7ed64d' }, 'length': 1317, 'raw_data': str.encode(stub_content_text_file), 'mimetype': 'text/x-c++', 'encoding': 'us-ascii', 'language': 'c++', 'licenses': 'GPL', 'error_code': 200, 'error_message': '', 'error_description': '' } -stub_content_text_no_highlight_data = { - 'checksums': { - 'sha1': '8624bcdae55baeef00cd11d5dfcfa60f68710a02', - 'sha1_git': '94a9ed024d3859793618152ea559a168bbcbb5e2', - 'sha256': '8ceb4b9ee5adedde47b31e975c1d90c73ad27b6b165a1dcd80c7c545eb65b903', - 'blake2s256': '38702b7168c7785bfe748b51b45d9856070ba90f9dc6d90f2ea75d4356411ffe' - }, - 'length': 35147, - 'raw_data': str.encode(stub_content_text_file_no_highlight), - 'mimetype': 'text/plain', - 'encoding': 'us-ascii', - 'language': 'not detected', - 'licenses': 'GPL', - 'error_code': 200, - 'error_message': '', - 'error_description': '' -} - stub_content_text_path = 'kate/autotests/session_test.h' -stub_content_text_path_with_root_dir = stub_content_root_dir + '/' + stub_content_text_path - -stub_content_bin_filename = 'swh-logo.png' - -png_file_path = os.path.dirname(__file__) + '/' + stub_content_bin_filename -with open(png_file_path, 'rb') as png_file: - stub_content_bin_data = { - 'checksums': { - 'sha1': 'd0cec0fc2d795f0077c18d51578cdb228eaf6a99', - 'sha1_git': '02328b91cfad800e1d2808cfb379511b79679ebc', - 'sha256': 'e290592e2cfa9767497011bda4b7e273b4cf29e7695d72ecacbd723008a29144', - 'blake2s256': '7177cad95407952e362ee326a800a9d215ccd619fdbdb735bb51039be81ab9ce' - }, - 'length': 18063, - 'raw_data': png_file.read(), - 'mimetype': 'image/png', - 'encoding': 'binary', - 'language': 'not detected', - 'licenses': 'not detected', - 'error_code': 200, - 'error_message': '', - 'error_description': '' - } - -_non_utf8_encoding_file_path = os.path.dirname(__file__) + '/iso-8859-1_encoded_content' - -non_utf8_encoded_content_data = { - 'checksums': { - 'sha1': '62cb71aa3534a03c12572157d20fa893753b03b6', - 'sha1_git': '2f7470d0b26108130e71087e42a53c032473499c', - 'sha256': 'aaf364ccd3acb546829ccc0e8e5e293e924c8a2e55a67cb739d249016e0034ed', - 'blake2s256': 'b7564932460a7c2697c53bd55bd855272490da511d64b20c5a04f636dc9ac467' - }, - 'length': 111000, - 'error_code': 200, - 'error_message': '', - 'error_description': '' -} - -non_utf8_encoding = 'iso-8859-1' - -with open(_non_utf8_encoding_file_path, 'rb') as iso88591_file: - non_utf8_encoded_content = iso88591_file.read() - -stub_content_too_large_data = { - 'checksums': { - 'sha1': '8624bcdae55baeef00cd11d5dfcfa60f68710a02', - 'sha1_git': '94a9ed024d3859793618152ea559a168bbcbb5e2', - 'sha256': '8ceb4b9ee5adedde47b31e975c1d90c73ad27b6b165a1dcd80c7c545eb65b903', - 'blake2s256': '38702b7168c7785bfe748b51b45d9856070ba90f9dc6d90f2ea75d4356411ffe' - }, - 'length': 3000000, - 'raw_data': None, - 'mimetype': 'text/plain', - 'encoding': 'us-ascii', - 'language': 'not detected', - 'licenses': 'GPL', - 'error_code': 200, - 'error_message': '', - 'error_description': '' -} \ No newline at end of file diff --git a/swh/web/tests/browse/views/data/iso-8859-1_encoded_content b/swh/web/tests/browse/views/data/iso-8859-1_encoded_content deleted file mode 100644 index 2f7470d0..00000000 --- a/swh/web/tests/browse/views/data/iso-8859-1_encoded_content +++ /dev/null @@ -1,279 +0,0 @@ - 4) - {header("Location: login.php?mess=".$mess_inc_non_autorise); exit();} - -*/ - -if (isset($_POST['f_deconnect'])) { - //log - require "../utiles/config.inc"; - require "../utiles/fonctions.inc"; - if ($conf_log) {ajout_to_log("LOGOUT");} - session_destroy(); header("Location: login.php?mess=".urlencode("Vous êtes déconnecté")); exit(); - } - - -// Load TemTab class et messages.inc -require "../classes/class.TemTab.php"; -require "../classes/class.ReqSql.php"; -require "../utiles/config.inc"; -require "../utiles/c.inc"; -require "../utiles/fonctions.inc"; - -require "../utiles/secure-session.inc"; - -// Accès ok pour niveaux 1 à 2 -niveau_ok(1,2); - -// compute starting time with microseconds precision -if ($conf_aff_req_sql) { - $mtime = explode(" ",microtime()); - $starttime = $mtime[1] + $mtime[0]; - } - -// Soyons prudent et portable, désactivons magic_quote pour ce script. merci nexen ;) if (get_magic_quotes_gpc()) { - function stripslashes_deep($value) - { - $value = is_array($value) ? - array_map('stripslashes_deep', $value) : - stripslashes($value); - - return $value; - } - - $_POST = array_map('stripslashes_deep', $_POST); - $_GET = array_map('stripslashes_deep', $_GET); - $_COOKIE = array_map('stripslashes_deep', $_COOKIE); -} - -/**************************/ -/* Crée les objets TemTab */ -/**************************/ - - // top - $template_file = "../html/meta.html"; - $template_meta = new TemTab($template_file); - - if ($_SESSION["S_niveau"] == 1) {$template_file = "../html/tete-admin-statistiques.html";} - if ($_SESSION["S_niveau"] == 2) {$template_file = "../html/tete-statistiques.html";} - $template_tete = new TemTab($template_file); - - // corps - $template_file = "../html/statistiques.html"; - $template = new TemTab($template_file); - - // pied $template_file = "../html/pied.html"; - $template_pied = new TemTab($template_file); - -// Some initializations -$sel="";$from="";$whe="";$col_val="";$affmess=""; - - -/************************/ -/* Traitement du script */ -/************************/ - - // Préparation de l'info alias / destination générique - $info_alias_dest_gen = ""; $client_auth_gen = false; - $client_auth_gen = ($conf_alias_dest_gen or $_SESSION["S_niveau"] == 1); - if (!$client_auth_gen) { - $info_alias_dest_gen = "Vous n\'avez pas le droit de modifier des alias ou destinations génériques, du type "@domain.tld " ! Vous devez demander cette modification à l\'administrateur du système."; - } - else { - $info_alias_dest_gen = "Vous avez le droit de modifier des alias ou destinations génériques, du type "@domain.tld "."; - } - - $domaines = str_replace(" ", "", $_SESSION["S_domaines"]); - - // construction de la clause where en fonction des domaines autorisés par le login - $whe_dom = ""; - $whe_dom = $conf_champ_alias." like \"%".$domaines; - $whe_dom = str_replace(",", "\" or ".$conf_champ_alias." like \"%", $whe_dom); - $whe_dom = $whe_dom."\""; - - // recherche des alias et destinations génériques - $alias_dest_gen = new ReqSql($hm_, $um_, $pm_, $nm_); - $sel = $conf_champ_alias.", ".$conf_champ_destination; - $from = $conf_table_alias; - $order = $conf_champ_alias." ASC"; - $alias_dest_gen->RS_select($sel, $from, $whe_dom, $order); - mysql_free_result($alias_dest_gen->RS_res); - - $alias_dest_gen_array = array(); - foreach($alias_dest_gen->RS_ligne as $val1) { - foreach($val1 as $key2 => $val2) { - if (($key2 == "0" or $key2 == "1") and (substr($val2, 0, 1) == "@")) { - array_push($alias_dest_gen_array, "".$val1["0"]." => ".$val1["1"]); - } // if (($key2 == "0" or $key2 == "1") and .. - } // foreach($val1 as $key2 => $val2) - } // foreach($alias_dest_gen->RS_ligne as $val1) - - $alias_dest_gen_array = array_unique($alias_dest_gen_array); - - - // Recherche des domaines ayant un alias - $dom_login = new ReqSql($hm_, $um_, $pm_, $nm_); -// Pas mal, le select et le group by, là ;-) - $sel = "SUBSTRING(".$conf_champ_alias.", LOCATE('@', ".$conf_champ_alias.") + 1, LENGTH(".$conf_champ_alias.")) as nom_domaine, count( SUBSTRING(".$conf_champ_alias.", LOCATE('@', ".$conf_champ_alias.") + 1, LENGTH(".$conf_champ_alias."))) as nb_domaine"; - $from = $conf_table_alias; - $group = "SUBSTRING(".$conf_champ_alias.", LOCATE('@', ".$conf_champ_alias.") + 1, LENGTH(".$conf_champ_alias."))"; - $dom_login->RS_select_group($sel, $from, $whe_dom, $group); - mysql_free_result($dom_login->RS_res); - - // Ajout des domaines du fichier de config n'ayant pas d'alias, puis tri - $domaine_array = array();$dom_array_compare = array();$dom_array_all = array(); - // dédoublonner le tableau de la requete + preparer un tableau simple de comparaison - foreach($dom_login->RS_ligne as $val) { - array_push($domaine_array, array_unique($val)); - array_push($dom_array_compare, $val["0"]); - } - - // Tableau simple de tous les domaines autorisé - $dom_array_all = explode(",", $domaines); - - // ajout des domaines du fichier de config n'ayant pas d'alias a ceux qui en ont - foreach($dom_array_all as $val) { - if (!in_array($val, $dom_array_compare)) {array_push($domaine_array, array($val, 0));} - } - - // Tri (voir bas de page : http://www.nexen.net/docs/php/annotee/function.array-multisort.php ) - foreach ($domaine_array as $key => $row) { - $ligne0[$key] = $row['0']; - $ligne1[$key] = $row['1']; - } - array_multisort($ligne0, SORT_ASC, $ligne1, SORT_DESC, $domaine_array); - - // Correspondance login / domaines et liste des domaines de la table transport - $f_base_login = "";$f_base_domaines = ""; - if ($_SESSION["S_niveau"] == 1) { - $liste_login = new ReqSql($hl_, $ul_, $pl_, $nl_); - $sel = $conf_champ_login.",".$conf_champ_domaines; - $from = $conf_table_login; - $liste_login->RS_select($sel, $from, "", $conf_champ_login); - mysql_free_result($liste_login->RS_res); - $f_base_login = "Login => domaines gérés
(".$liste_login->RS_nb_ligne." login trouvé(s) dans dans la table ".$conf_table_login." de la base de données ".$conf_base_login.". All = tous les domaines [super admin] )"; - - $liste_dom = new ReqSql($hm_, $um_, $pm_, $nm_); - $sel = $conf_champ_domaine.",".$conf_champ_transport; - $from = $conf_table_transport; - $liste_dom->RS_select($sel, $from, "", $conf_champ_domaine); - mysql_free_result($liste_dom->RS_res); - $f_base_domaines = "Domaines [transport]
(".$liste_dom->RS_nb_ligne." domaine(s) trouvé(s) dans la table ".$conf_table_transport." de la base de données ".$conf_base_mail."."; - - } // if ($_SESSION["S_niveau"] == 1) - - -/***********************************/ -/* traitement des variables TemTab */ -/***********************************/ - - // Affichage des balises meta - $template_meta->replace_var("t_meta_charset", $conf_meta_charset); - $template_meta->replace_var("t_meta_general_keywords", $conf_meta_general_keywords); - $template_meta->replace_var("t_meta_particulier_keywords", $meta_particulier_keywords); - $template_meta->replace_var("t_meta_copyright", $conf_meta_copyright); - $template_meta->replace_var("t_meta_author", $conf_meta_author); - $template_meta->replace_var("t_meta_generator", $conf_meta_generator); - $template_meta->replace_var("t_meta_description", $conf_meta_description); - - - // Affichage des titres - $template_meta->replace_var("t_nom_site", $conf_nom_site); - - // Affichage de l(identifiant du site - $template_tete->replace_var("t_conf_name_log", $conf_name_log); - - // formulaire déconnexion - $template_tete->replace_var("t_script_name", $conf_script_name); - - // Affichage des alias et destination génériques - $template->replace_loop_vars_one("loop_gen", $alias_dest_gen_array); - - // Affichage des statistiques des alias - $template->replace_loop_vars("loop_stats", $domaine_array); - - // Affichage des statistiques des comptes - $template->replace_loop_vars("loop_stats_comptes", 0); - - // Affichage des correspondances login / domaines - $template->replace_var("t_base_login_domaines", $f_base_login); - if ($_SESSION["S_niveau"] == 1) {$template->replace_loop_vars("loop_liste_login_domaines", $liste_login->RS_ligne);} - else {@$template->replace_loop_vars("loop_liste_login_domaines", $login_domaines_array);} // tableau vide si niveau 2 - - // Affichage des domaines de la table transport - $template->replace_var("t_base_domaines", $f_base_domaines); - if ($_SESSION["S_niveau"] == 1) {$template->replace_loop_vars("loop_liste_domaines", $liste_dom->RS_ligne);} - else {@$template->replace_loop_vars("loop_liste_domaines", $login_domaines_array);} // tableau vide si niveau 2 - - // Affichage de l'info alias / destination générique - $template->replace_var("t_info_alias_dest_gen", $info_alias_dest_gen); - - // affichage du login - $f_login = $_SESSION["S_login"]; - $template->replace_var("t_login", $f_login); - - -// prépare un message éventuellement passé par GET (déconnexion, en l'occurence) -if (isset($_GET["mess"])) {$affmess = stripslashes($_GET["mess"]);} -if (!isset($affmess)) {$affmess = "";} -if (isset($_GET["mess"]) or $affmess != "") { - $template->replace_var("t_mess_accueil", "
".$affmess."
 
"); - } - - -/*****************************************/ -/* Termine la construction des templates */ -/*****************************************/ - - // get rid of unused variables - $template_meta->remove_all_vars(); - $template_tete->remove_all_vars(); - $template->remove_all_vars(); - $template_pied->remove_all_vars(); - - // and finally get the outputs - print ($template_meta->get_output()); - print ($template_tete->get_output()); - print ($template->get_output()); - print ($template_pied->get_output()); - - -// compute elapsed time with microseconds precision -if ($conf_aff_req_sql) { - $mtime = explode(" ",microtime()); - $endtime = $mtime[1] + $mtime[0] - $starttime; - print "\n"; - print "
Durée du traitement: ".$endtime." microsecondes
\n
"; - } - - - -?> - diff --git a/swh/web/tests/browse/views/data/swh-logo.png b/swh/web/tests/browse/views/data/swh-logo.png deleted file mode 100644 index 3cbb7196..00000000 Binary files a/swh/web/tests/browse/views/data/swh-logo.png and /dev/null differ diff --git a/swh/web/tests/browse/views/test_content.py b/swh/web/tests/browse/views/test_content.py index 1a45cf6f..f88bf07a 100644 --- a/swh/web/tests/browse/views/test_content.py +++ b/swh/web/tests/browse/views/test_content.py @@ -1,326 +1,350 @@ -# Copyright (C) 2017-2018 The Software Heritage developers +# Copyright (C) 2017-2019 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 unittest.mock import patch from django.utils.html import escape -from django.utils.encoding import DjangoUnicodeDecodeError -from swh.web.browse.utils import get_mimetype_and_encoding_for_content +from hypothesis import given + +from swh.web.browse.utils import ( + get_mimetype_and_encoding_for_content, prepare_content_for_display, + _reencode_content +) from swh.web.common.exc import NotFoundExc from swh.web.common.utils import reverse, get_swh_persistent_id from swh.web.common.utils import gen_path_info -from swh.web.tests.testcase import WebTestCase - -from .data.content_test_data import ( - stub_content_text_data, - stub_content_text_path_with_root_dir, - stub_content_bin_data, - stub_content_bin_filename, - stub_content_text_no_highlight_data, - non_utf8_encoded_content_data, - non_utf8_encoded_content, - non_utf8_encoding, - stub_content_too_large_data +from swh.web.tests.strategies import ( + content, content_text_non_utf8, content_text_no_highlight, + content_image_type, content_text, invalid_sha1, unknown_content ) +from swh.web.tests.testcase import WebTestCase class SwhBrowseContentTest(WebTestCase): - @patch('swh.web.browse.views.content.request_content') - def test_content_view_text(self, mock_request_content): - mock_request_content.return_value = stub_content_text_data + @given(content()) + def test_content_view_text(self, content): - sha1_git = stub_content_text_data['checksums']['sha1_git'] + sha1_git = content['sha1_git'] url = reverse('browse-content', - url_args={'query_string': stub_content_text_data['checksums']['sha1']}) # noqa + url_args={'query_string': content['sha1']}, + query_params={'path': content['path']}) url_raw = reverse('browse-content-raw', - url_args={'query_string': stub_content_text_data['checksums']['sha1']}) # noqa + url_args={'query_string': content['sha1']}) resp = self.client.get(url) + content_display = self._process_content_for_display(content) + mimetype = content_display['mimetype'] + self.assertEqual(resp.status_code, 200) self.assertTemplateUsed('browse/content.html') - self.assertContains(resp, '') - self.assertContains(resp, escape(stub_content_text_data['raw_data'])) + if mimetype.startswith('text/'): + self.assertContains(resp, '' % + content_display['language']) + self.assertContains(resp, escape(content_display['content_data'])) self.assertContains(resp, url_raw) swh_cnt_id = get_swh_persistent_id('content', sha1_git) swh_cnt_id_url = reverse('browse-swh-id', url_args={'swh_id': swh_cnt_id}) self.assertContains(resp, swh_cnt_id) self.assertContains(resp, swh_cnt_id_url) - @patch('swh.web.browse.views.content.request_content') - def test_content_view_text_no_highlight(self, mock_request_content): - mock_request_content.return_value = stub_content_text_no_highlight_data + @given(content_text_no_highlight()) + def test_content_view_text_no_highlight(self, content): - sha1_git = stub_content_text_no_highlight_data['checksums']['sha1_git'] + sha1_git = content['sha1_git'] url = reverse('browse-content', - url_args={'query_string': stub_content_text_no_highlight_data['checksums']['sha1']}) # noqa + url_args={'query_string': content['sha1']}) url_raw = reverse('browse-content-raw', - url_args={'query_string': stub_content_text_no_highlight_data['checksums']['sha1']}) # noqa + url_args={'query_string': content['sha1']}) resp = self.client.get(url) + content_display = self._process_content_for_display(content) + self.assertEqual(resp.status_code, 200) self.assertTemplateUsed('browse/content.html') self.assertContains(resp, '') - self.assertContains(resp, escape(stub_content_text_no_highlight_data['raw_data'])) # noqa + self.assertContains(resp, escape(content_display['content_data'])) # noqa self.assertContains(resp, url_raw) swh_cnt_id = get_swh_persistent_id('content', sha1_git) swh_cnt_id_url = reverse('browse-swh-id', url_args={'swh_id': swh_cnt_id}) self.assertContains(resp, swh_cnt_id) self.assertContains(resp, swh_cnt_id_url) - @patch('swh.web.browse.utils.service') - def test_content_view_no_utf8_text(self, mock_service): - mock_service.lookup_content.return_value = \ - non_utf8_encoded_content_data + @given(content_text_non_utf8()) + def test_content_view_no_utf8_text(self, content): - mock_service.lookup_content_raw.return_value = \ - {'data': non_utf8_encoded_content} + sha1_git = content['sha1_git'] - mock_service.lookup_content_filetype.return_value = None - mock_service.lookup_content_language.return_value = None - mock_service.lookup_content_license.return_value = None + url = reverse('browse-content', + url_args={'query_string': content['sha1']}) - sha1_git = non_utf8_encoded_content_data['checksums']['sha1_git'] + resp = self.client.get(url) - url = reverse('browse-content', - url_args={'query_string': non_utf8_encoded_content_data['checksums']['sha1']}) # noqa - - try: - resp = self.client.get(url) - self.assertEqual(resp.status_code, 200) - self.assertTemplateUsed('browse/content.html') - swh_cnt_id = get_swh_persistent_id('content', sha1_git) - swh_cnt_id_url = reverse('browse-swh-id', - url_args={'swh_id': swh_cnt_id}) - self.assertContains(resp, swh_cnt_id_url) - self.assertContains(resp, escape(non_utf8_encoded_content.decode(non_utf8_encoding).encode('utf-8'))) # noqa - except DjangoUnicodeDecodeError: - self.fail('Textual content is not encoded in utf-8') + content_display = self._process_content_for_display(content) - @patch('swh.web.browse.views.content.request_content') - def test_content_view_image(self, mock_request_content): + self.assertEqual(resp.status_code, 200) + self.assertTemplateUsed('browse/content.html') + swh_cnt_id = get_swh_persistent_id('content', sha1_git) + swh_cnt_id_url = reverse('browse-swh-id', + url_args={'swh_id': swh_cnt_id}) + self.assertContains(resp, swh_cnt_id_url) + self.assertContains(resp, escape(content_display['content_data'])) - mime_type = 'image/png' - mock_request_content.return_value = stub_content_bin_data + @given(content_image_type()) + def test_content_view_image(self, content): url = reverse('browse-content', - url_args={'query_string': stub_content_bin_data['checksums']['sha1']}) # noqa + url_args={'query_string': content['sha1']}) url_raw = reverse('browse-content-raw', - url_args={'query_string': stub_content_bin_data['checksums']['sha1']}) # noqa + url_args={'query_string': content['sha1']}) resp = self.client.get(url) + content_display = self._process_content_for_display(content) + mimetype = content_display['mimetype'] + content_data = content_display['content_data'] + self.assertEqual(resp.status_code, 200) self.assertTemplateUsed('browse/content.html') - png_encoded = base64.b64encode(stub_content_bin_data['raw_data']) \ - .decode('utf-8') - self.assertContains(resp, '' - % (mime_type, png_encoded)) + % (mimetype, content_data.decode('utf-8'))) self.assertContains(resp, url_raw) - @patch('swh.web.browse.views.content.request_content') - def test_content_view_with_path(self, mock_request_content): - mock_request_content.return_value = stub_content_text_data + @given(content()) + def test_content_view_with_path(self, content): + + path = content['path'] url = reverse('browse-content', - url_args={'query_string': stub_content_text_data['checksums']['sha1']}, # noqa - query_params={'path': stub_content_text_path_with_root_dir}) # noqa + url_args={'query_string': content['sha1']}, + query_params={'path': path}) resp = self.client.get(url) self.assertEqual(resp.status_code, 200) self.assertTemplateUsed('browse/content.html') self.assertContains(resp, '