def content_raw(request, query_string): """Django view that produces a raw display of a content identified by its hash value. The url that points to it is :http:get:`/browse/content/[(algo_hash):](hash)/raw/` """ re_encode = bool(strtobool(request.GET.get("re_encode", "false"))) algo, checksum = query.parse_hash(query_string) checksum = hash_to_hex(checksum) content_data = request_content(query_string, max_size=None, re_encode=re_encode) filename = request.GET.get("filename", None) if not filename: filename = "%s_%s" % (algo, checksum) if (content_data["mimetype"].startswith("text/") or content_data["mimetype"] == "inode/x-empty"): response = HttpResponse(content_data["raw_data"], content_type="text/plain") response["Content-disposition"] = "filename=%s" % filename else: response = HttpResponse(content_data["raw_data"], content_type="application/octet-stream") response["Content-disposition"] = "attachment; filename=%s" % filename return response
def content_raw(request, query_string): """Django view that produces a raw display of a content identified by its hash value. The url that points to it is :http:get:`/browse/content/[(algo_hash):](hash)/raw/` """ # noqa try: reencode = bool(strtobool(request.GET.get('reencode', 'false'))) algo, checksum = query.parse_hash(query_string) checksum = hash_to_hex(checksum) content_data = request_content(query_string, max_size=None, reencode=reencode) except Exception as exc: return handle_view_exception(request, exc) filename = request.GET.get('filename', None) if not filename: filename = '%s_%s' % (algo, checksum) if content_data['mimetype'].startswith('text/') or \ content_data['mimetype'] == 'inode/x-empty': response = HttpResponse(content_data['raw_data'], content_type="text/plain") response['Content-disposition'] = 'filename=%s' % filename else: response = HttpResponse(content_data['raw_data'], content_type='application/octet-stream') response['Content-disposition'] = 'attachment; filename=%s' % filename return response
def lookup_content_raw(q: str) -> Dict[str, Any]: """Lookup the content defined by q. Args: q: query string of the form <hash_algo:hash> Returns: dict with 'sha1' and 'data' keys. data representing its raw data decoded. Raises: NotFoundExc if the requested content is not found or if the content bytes are not available in the storage """ c = lookup_content(q) content_sha1_bytes = hashutil.hash_to_bytes(c["checksums"]["sha1"]) content_data = storage.content_get_data(content_sha1_bytes) if content_data is None: algo, hash_ = query.parse_hash(q) raise NotFoundExc( f"Bytes of content with {algo} checksum equals " f"to {hashutil.hash_to_hex(hash_)} are not available!") return converters.from_content({ "sha1": content_sha1_bytes, "data": content_data })
def search_hash(q): """Checks if the storage contains a given content checksum Args: query string of the form <hash_algo:hash> Returns: Dict with key found to True or False, according to whether the checksum is present or not """ algo, hash = query.parse_hash(q) found = storage.content_find({algo: hash}) return {'found': found is not None}
def lookup_hash(q): """Checks if the storage contains a given content checksum Args: query string of the form <hash_algo:hash> Returns: Dict with key found containing the hash info if the hash is present, None if not. """ algo, hash = query.parse_hash(q) found = storage.content_find({algo: hash}) return {'found': converters.from_content(found), 'algo': algo}
def search_hash(q: str) -> Dict[str, bool]: """Search storage for a given content checksum. Args: q: query string of the form <hash_algo:hash> Returns: Dict with key found to True or False, according to whether the checksum is present or not """ algo, hash_ = query.parse_hash(q) found = _first_element(storage.content_find({algo: hash_})) return {"found": found is not None}
def enrich_content( content: Dict[str, Any], top_url: Optional[bool] = False, query_string: Optional[str] = None, request: Optional[HttpRequest] = None, ) -> Dict[str, str]: """Enrich content with links to: - data_url: its raw data - filetype_url: its filetype information - language_url: its programming language information - license_url: its licensing information Args: content: dict of data associated to a swh content object top_url: whether or not to include the content url in the enriched data query_string: optional query string of type '<algo>:<hash>' used when requesting the content, it acts as a hint for picking the same hash method when computing the url listed above request: Absolute URIs will be generated if provided Returns: An enriched content dict filled with additional urls """ checksums = content if "checksums" in content: checksums = content["checksums"] hash_algo = "sha1" if query_string: hash_algo = parse_hash(query_string)[0] if hash_algo in checksums: q = "%s:%s" % (hash_algo, checksums[hash_algo]) if top_url: content["content_url"] = reverse("api-1-content", url_args={"q": q}) content["data_url"] = reverse( "api-1-content-raw", url_args={"q": q}, request=request ) content["filetype_url"] = reverse( "api-1-content-filetype", url_args={"q": q}, request=request ) content["language_url"] = reverse( "api-1-content-language", url_args={"q": q}, request=request ) content["license_url"] = reverse( "api-1-content-license", url_args={"q": q}, request=request ) return content
def lookup_content(q): """Lookup the content designed by q. Args: q: The release's sha1 as hexadecimal Raises: NotFoundExc if the requested content is not found """ algo, hash = query.parse_hash(q) c = storage.content_find({algo: hash}) if not c: raise NotFoundExc('Content with %s checksum equals to %s not found!' % (algo, hashutil.hash_to_hex(hash))) return converters.from_content(c)
def lookup_content(q: str) -> Dict[str, Any]: """Lookup the content designed by q. Args: q: The release's sha1 as hexadecimal Raises: NotFoundExc if the requested content is not found """ algo, hash_ = query.parse_hash(q) c = _first_element(storage.content_find({algo: hash_})) if not c: hhex = hashutil.hash_to_hex(hash_) raise NotFoundExc( f"Content with {algo} checksum equals to {hhex} not found!") return converters.from_content(c.to_dict())
def _lookup_content_sha1(q): """Given a possible input, query for the content's sha1. Args: q: query string of the form <hash_algo:hash> Returns: binary sha1 if found or None """ algo, hash = query.parse_hash(q) if algo != 'sha1': hashes = storage.content_find({algo: hash}) if not hashes: return None return hashes['sha1'] return hash
def _lookup_content_sha1(q: str) -> Optional[bytes]: """Given a possible input, query for the content's sha1. Args: q: query string of the form <hash_algo:hash> Returns: binary sha1 if found or None """ algo, hash_ = query.parse_hash(q) if algo != "sha1": hashes = _first_element(storage.content_find({algo: hash_})) if not hashes: return None return hashes.sha1 return hash_
def lookup_hash(q: str) -> Dict[str, Any]: """Check if the storage contains a given content checksum and return it if found. Args: q: query string of the form <hash_algo:hash> Returns: Dict with key found containing the hash info if the hash is present, None if not. """ algo, hash_ = query.parse_hash(q) found = _first_element(storage.content_find({algo: hash_})) if found: content = converters.from_content(found.to_dict()) else: content = None return {"found": content, "algo": algo}
def lookup_content_raw(q): """Lookup the content defined by q. Args: q: query string of the form <hash_algo:hash> Returns: dict with 'sha1' and 'data' keys. data representing its raw data decoded. Raises: NotFoundExc if the requested content is not found or if the content bytes are not available in the storage """ c = lookup_content(q) content_sha1_bytes = hashutil.hash_to_bytes(c['checksums']['sha1']) content = _first_element(storage.content_get([content_sha1_bytes])) if not content: algo, hash = query.parse_hash(q) raise NotFoundExc('Bytes of content with %s checksum equals to %s ' 'are not available!' % (algo, hashutil.hash_to_hex(hash))) return converters.from_content(content)
def test_parse_hash_check_sha256(self): h = '084C799CD551DD1D8D5C5F9A5D593B2E931F5E36122ee5c793c1d08a19839cc0' r = query.parse_hash('sha256:' + h) self.assertEqual(r, ('sha256', hashutil.hash_to_bytes(h)))
def test_parse_hash_check_sha1_git(self): h = 'e1d2d2f924e986ac86fdf7b36c94bcdf32beec15' r = query.parse_hash('sha1_git:' + h) self.assertEqual(r, ('sha1_git', hashutil.hash_to_bytes(h)))
def test_parse_hash_guess_algo_malformed_hash(self): with self.assertRaises(BadInputExc): query.parse_hash('1234567890987654')
def test_parse_hash_guess_sha1(self): h = 'f1d2d2f924e986ac86fdf7b36c94bcdf32beec15' r = query.parse_hash(h) self.assertEqual(r, ('sha1', hashutil.hash_to_bytes(h)))
def test_parse_hash_malformed_query_with_more_than_2_parts(self): with self.assertRaises(BadInputExc): query.parse_hash('sha1:1234567890987654:other-stuff')
def test_parse_hash_check_algo_unknown_one(): with pytest.raises(BadInputExc): query.parse_hash("sha2:1234567890987654")
def test_parse_hash_check_algo_malformed_sha256_hash(): with pytest.raises(BadInputExc): query.parse_hash("sha256:1234567890987654")
def test_parse_hash_check_sha256(): h = "084C799CD551DD1D8D5C5F9A5D593B2E931F5E36122ee5c793c1d08a19839cc0" r = query.parse_hash("sha256:" + h) assert r == ("sha256", hashutil.hash_to_bytes(h))
def test_parse_hash_check_sha1_git(): h = "e1d2d2f924e986ac86fdf7b36c94bcdf32beec15" r = query.parse_hash("sha1_git:" + h) assert r == ("sha1_git", hashutil.hash_to_bytes(h))
def test_parse_hash_guess_algo_malformed_hash(): with pytest.raises(BadInputExc): query.parse_hash("1234567890987654")
def test_parse_hash_guess_sha1(): h = "f1d2d2f924e986ac86fdf7b36c94bcdf32beec15" r = query.parse_hash(h) assert r == ("sha1", hashutil.hash_to_bytes(h))
def test_parse_hash_malformed_query_with_more_than_2_parts(): with pytest.raises(BadInputExc): query.parse_hash("sha1:1234567890987654:other-stuff")
def content_display(request, query_string): """Django view that produces an HTML display of a content identified by its hash value. The url that points to it is :http:get:`/browse/content/[(algo_hash):](hash)/` """ algo, checksum = query.parse_hash(query_string) checksum = hash_to_hex(checksum) origin_url = request.GET.get("origin_url") selected_language = request.GET.get("language") if not origin_url: origin_url = request.GET.get("origin") snapshot_id = request.GET.get("snapshot") path = request.GET.get("path") content_data = {} error_info = {"status_code": 200, "description": None} try: content_data = request_content(query_string) except NotFoundExc as e: error_info["status_code"] = 404 error_info["description"] = f"NotFoundExc: {str(e)}" snapshot_context = None if origin_url is not None or snapshot_id is not None: try: snapshot_context = get_snapshot_context( origin_url=origin_url, snapshot_id=snapshot_id, branch_name=request.GET.get("branch"), release_name=request.GET.get("release"), revision_id=request.GET.get("revision"), path=path, browse_context=CONTENT, ) except NotFoundExc as e: if str(e).startswith("Origin"): raw_cnt_url = reverse("browse-content", url_args={"query_string": query_string}) error_message = ( "The Software Heritage archive has a content " "with the hash you provided but the origin " "mentioned in your request appears broken: %s. " "Please check the URL and try again.\n\n" "Nevertheless, you can still browse the content " "without origin information: %s" % (gen_link(origin_url), gen_link(raw_cnt_url))) raise NotFoundExc(error_message) else: raise e content = None language = None mimetype = None if content_data.get("raw_data") is not None: content_display_data = prepare_content_for_display( content_data["raw_data"], content_data["mimetype"], path) content = content_display_data["content_data"] language = content_display_data["language"] mimetype = content_display_data["mimetype"] # Override language with user-selected language if selected_language is not None: language = selected_language available_languages = None if mimetype and "text/" in mimetype: available_languages = highlightjs.get_supported_languages() filename = None path_info = None directory_id = None root_dir = None if snapshot_context: root_dir = snapshot_context.get("root_directory") query_params = snapshot_context["query_params"] if snapshot_context else {} breadcrumbs = [] if path: split_path = path.split("/") root_dir = root_dir or split_path[0] filename = split_path[-1] if root_dir != path: path = path.replace(root_dir + "/", "") path = path[:-len(filename)] path_info = gen_path_info(path) query_params.pop("path", None) dir_url = reverse( "browse-directory", url_args={"sha1_git": root_dir}, query_params=query_params, ) breadcrumbs.append({"name": root_dir[:7], "url": dir_url}) for pi in path_info: query_params["path"] = pi["path"] dir_url = reverse( "browse-directory", url_args={"sha1_git": root_dir}, query_params=query_params, ) breadcrumbs.append({"name": pi["name"], "url": dir_url}) breadcrumbs.append({"name": filename, "url": None}) if path and root_dir != path: dir_info = archive.lookup_directory_with_path(root_dir, path) directory_id = dir_info["target"] elif root_dir != path: directory_id = root_dir else: root_dir = None query_params = {"filename": filename} content_checksums = content_data.get("checksums", {}) content_url = reverse( "browse-content", url_args={"query_string": query_string}, ) content_raw_url = reverse( "browse-content-raw", url_args={"query_string": query_string}, query_params=query_params, ) content_metadata = ContentMetadata( object_type=CONTENT, object_id=content_checksums.get("sha1_git"), sha1=content_checksums.get("sha1"), sha1_git=content_checksums.get("sha1_git"), sha256=content_checksums.get("sha256"), blake2s256=content_checksums.get("blake2s256"), content_url=content_url, mimetype=content_data.get("mimetype"), encoding=content_data.get("encoding"), size=filesizeformat(content_data.get("length", 0)), language=content_data.get("language"), root_directory=root_dir, path=f"/{path}" if path else None, filename=filename or "", directory=directory_id, revision=None, release=None, snapshot=None, origin_url=origin_url, ) swh_objects = [ SWHObjectInfo(object_type=CONTENT, object_id=content_checksums.get("sha1_git")) ] if directory_id: swh_objects.append( SWHObjectInfo(object_type=DIRECTORY, object_id=directory_id)) if snapshot_context: swh_objects.append( SWHObjectInfo(object_type=REVISION, object_id=snapshot_context["revision_id"])) swh_objects.append( SWHObjectInfo(object_type=SNAPSHOT, object_id=snapshot_context["snapshot_id"])) if snapshot_context["release_id"]: swh_objects.append( SWHObjectInfo(object_type=RELEASE, object_id=snapshot_context["release_id"])) swhids_info = get_swhids_info( swh_objects, snapshot_context, extra_context=content_metadata, ) heading = "Content - %s" % content_checksums.get("sha1_git") if breadcrumbs: content_path = "/".join([bc["name"] for bc in breadcrumbs]) heading += " - %s" % content_path return render( request, "browse/content.html", { "heading": heading, "swh_object_id": swhids_info[0]["swhid"], "swh_object_name": "Content", "swh_object_metadata": content_metadata, "content": content, "content_size": content_data.get("length"), "max_content_size": content_display_max_size, "filename": filename, "encoding": content_data.get("encoding"), "mimetype": mimetype, "language": language, "available_languages": available_languages, "breadcrumbs": breadcrumbs, "top_right_link": { "url": content_raw_url, "icon": swh_object_icons["content"], "text": "Raw File", }, "snapshot_context": snapshot_context, "vault_cooking": None, "show_actions": True, "swhids_info": swhids_info, "error_code": error_info["status_code"], "error_message": http_status_code_message.get(error_info["status_code"]), "error_description": error_info["description"], }, status=error_info["status_code"], )
def test_parse_hash_check_algo_malformed_sha256_hash(self): with self.assertRaises(BadInputExc): query.parse_hash('sha256:1234567890987654')
def test_parse_hash_check_algo_unknown_one(self): with self.assertRaises(BadInputExc): query.parse_hash('sha2:1234567890987654')
def content_display(request, query_string): """Django view that produces an HTML display of a content identified by its hash value. The url that points to it is :http:get:`/browse/content/[(algo_hash):](hash)/` """ # noqa try: algo, checksum = query.parse_hash(query_string) checksum = hash_to_hex(checksum) content_data = request_content(query_string, raise_if_unavailable=False) origin_type = request.GET.get('origin_type', None) origin_url = request.GET.get('origin_url', None) if not origin_url: origin_url = request.GET.get('origin', None) snapshot_context = None if origin_url: try: snapshot_context = get_snapshot_context( None, origin_type, origin_url) except Exception: raw_cnt_url = reverse('browse-content', url_args={'query_string': query_string}) error_message = \ ('The Software Heritage archive has a content ' 'with the hash you provided but the origin ' 'mentioned in your request appears broken: %s. ' 'Please check the URL and try again.\n\n' 'Nevertheless, you can still browse the content ' 'without origin information: %s' % (gen_link(origin_url), gen_link(raw_cnt_url))) raise NotFoundExc(error_message) if snapshot_context: snapshot_context['visit_info'] = None except Exception as exc: return handle_view_exception(request, exc) path = request.GET.get('path', None) content = None language = None mimetype = None if content_data['raw_data'] is not None: content_display_data = prepare_content_for_display( content_data['raw_data'], content_data['mimetype'], path) content = content_display_data['content_data'] language = content_display_data['language'] mimetype = content_display_data['mimetype'] root_dir = None filename = None path_info = None query_params = {'origin': origin_url} breadcrumbs = [] if path: split_path = path.split('/') root_dir = split_path[0] filename = split_path[-1] if root_dir != path: path = path.replace(root_dir + '/', '') path = path[:-len(filename)] path_info = gen_path_info(path) dir_url = reverse('browse-directory', url_args={'sha1_git': root_dir}, query_params=query_params) breadcrumbs.append({'name': root_dir[:7], 'url': dir_url}) for pi in path_info: dir_url = reverse('browse-directory', url_args={ 'sha1_git': root_dir, 'path': pi['path'] }, query_params=query_params) breadcrumbs.append({'name': pi['name'], 'url': dir_url}) breadcrumbs.append({'name': filename, 'url': None}) query_params = {'filename': filename} content_raw_url = reverse('browse-content-raw', url_args={'query_string': query_string}, query_params=query_params) content_metadata = { 'sha1 checksum': content_data['checksums']['sha1'], 'sha1_git checksum': content_data['checksums']['sha1_git'], 'sha256 checksum': content_data['checksums']['sha256'], 'blake2s256 checksum': content_data['checksums']['blake2s256'], 'mime type': content_data['mimetype'], 'encoding': content_data['encoding'], 'size': filesizeformat(content_data['length']), 'language': content_data['language'], 'licenses': content_data['licenses'], 'filename': filename } if filename: content_metadata['filename'] = filename sha1_git = content_data['checksums']['sha1_git'] swh_ids = get_swh_persistent_ids([{'type': 'content', 'id': sha1_git}]) heading = 'Content - %s' % sha1_git if breadcrumbs: content_path = '/'.join([bc['name'] for bc in breadcrumbs]) heading += ' - %s' % content_path return render(request, 'browse/content.html', { 'heading': heading, 'swh_object_id': swh_ids[0]['swh_id'], 'swh_object_name': 'Content', 'swh_object_metadata': content_metadata, 'content': content, 'content_size': content_data['length'], 'max_content_size': content_display_max_size, 'mimetype': mimetype, 'language': language, 'breadcrumbs': breadcrumbs, 'top_right_link': { 'url': content_raw_url, 'icon': swh_object_icons['content'], 'text': 'Raw File' }, 'snapshot_context': snapshot_context, 'vault_cooking': None, 'show_actions_menu': True, 'swh_ids': swh_ids, 'error_code': content_data['error_code'], 'error_message': content_data['error_message'], 'error_description': content_data['error_description'] }, status=content_data['error_code'])