diff --git a/swh/lister/core/lister_base.py b/swh/lister/core/lister_base.py index 66bfd0e..fe23c5a 100644 --- a/swh/lister/core/lister_base.py +++ b/swh/lister/core/lister_base.py @@ -1,517 +1,525 @@ # Copyright (C) 2015-2018 the Software Heritage developers # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import abc import datetime import gzip import json import logging import os import re import time from sqlalchemy import create_engine, func from sqlalchemy.orm import sessionmaker from swh.core import config from swh.scheduler import get_scheduler, utils from swh.storage import get_storage from .abstractattribute import AbstractAttribute logger = logging.getLogger(__name__) def utcnow(): return datetime.datetime.now(tz=datetime.timezone.utc) class FetchError(RuntimeError): def __init__(self, response): self.response = response def __str__(self): return repr(self.response) class ListerBase(abc.ABC, config.SWHConfig): """Lister core base class. Generally a source code hosting service provides an API endpoint for listing the set of stored repositories. A Lister is the discovery service responsible for finding this list, all at once or sequentially by parts, and queueing local tasks to fetch and ingest the referenced repositories. The core method in this class is ingest_data. Any subclasses should be calling this method one or more times to fetch and ingest data from API endpoints. See swh.lister.core.lister_base.IndexingLister for example usage. This class cannot be instantiated. Any instantiable Lister descending from ListerBase must provide at least the required overrides. (see member docstrings for details): Required Overrides: MODEL def transport_request def transport_response_to_string def transport_response_simplified def transport_quota_check Optional Overrides: def filter_before_inject def is_within_bounds """ MODEL = AbstractAttribute('Subclass type (not instance)' ' of swh.lister.core.models.ModelBase' ' customized for a specific service.') LISTER_NAME = AbstractAttribute("Lister's name") def transport_request(self, identifier): """Given a target endpoint identifier to query, try once to request it. Implementation of this method determines the network request protocol. Args: identifier (string): unique identifier for an endpoint query. e.g. If the service indexes lists of repositories by date and time of creation, this might be that as a formatted string. Or it might be an integer UID. Or it might be nothing. It depends on what the service needs. Returns: the entire request response Raises: Will catch internal transport-dependent connection exceptions and raise swh.lister.core.lister_base.FetchError instead. Other non-connection exceptions should propagate unchanged. """ pass def transport_response_to_string(self, response): """Convert the server response into a formatted string for logging. Implementation of this method depends on the shape of the network response object returned by the transport_request method. Args: response: the server response Returns: a pretty string of the response """ pass def transport_response_simplified(self, response): """Convert the server response into list of a dict for each repo in the response, mapping columns in the lister's MODEL class to repo data. Implementation of this method depends on the server API spec and the shape of the network response object returned by the transport_request method. Args: response: response object from the server. Returns: list of repo MODEL dicts ( eg. [{'uid': r['id'], etc.} for r in response.json()] ) """ pass def transport_quota_check(self, response): """Check server response to see if we're hitting request rate limits. Implementation of this method depends on the server communication protocol and API spec and the shape of the network response object returned by the transport_request method. Args: response (session response): complete API query response Returns: 1) must retry request? True/False 2) seconds to delay if True """ pass def filter_before_inject(self, models_list): """Filter models_list entries prior to injection in the db. This is ran directly after `transport_response_simplified`. Default implementation is to have no filtering. Args: models_list: list of dicts returned by transport_response_simplified. Returns: models_list with entries changed according to custom logic. """ return models_list def do_additional_checks(self, models_list): """Execute some additional checks on the model list (after the filtering). Default implementation is to run no check at all and to return the input as is. Args: models_list: list of dicts returned by transport_response_simplified. Returns: models_list with entries if checks ok, False otherwise """ return models_list def is_within_bounds(self, inner, lower=None, upper=None): """See if a sortable value is inside the range [lower,upper]. MAY BE OVERRIDDEN, for example if the server indexable* key is technically sortable but not automatically so. * - ( see: swh.lister.core.indexing_lister.IndexingLister ) Args: inner (sortable type): the value being checked lower (sortable type): optional lower bound upper (sortable type): optional upper bound Returns: whether inner is confined by the optional lower and upper bounds """ try: if lower is None and upper is None: return True elif lower is None: ret = inner <= upper elif upper is None: ret = inner >= lower else: ret = lower <= inner <= upper self.string_pattern_check(inner, lower, upper) except Exception as e: logger.error(str(e) + ': %s, %s, %s' % (('inner=%s%s' % (type(inner), inner)), ('lower=%s%s' % (type(lower), lower)), ('upper=%s%s' % (type(upper), upper))) ) raise return ret # You probably don't need to override anything below this line. DEFAULT_CONFIG = { 'storage': ('dict', { 'cls': 'remote', 'args': { 'url': 'http://localhost:5002/' }, }), 'scheduler': ('dict', { 'cls': 'remote', 'args': { 'url': 'http://localhost:5008/' }, }), 'lister': ('dict', { 'cls': 'local', 'args': { 'db': 'postgresql:///lister', }, }), } @property def CONFIG_BASE_FILENAME(self): # noqa: N802 return 'lister_%s' % self.LISTER_NAME @property def ADDITIONAL_CONFIG(self): # noqa: N802 return { 'credentials': ('dict', {}), 'cache_responses': ('bool', False), 'cache_dir': ('str', '~/.cache/swh/lister/%s' % self.LISTER_NAME), } INITIAL_BACKOFF = 10 MAX_RETRIES = 7 CONN_SLEEP = 10 def __init__(self, override_config=None): self.backoff = self.INITIAL_BACKOFF logger.debug('Loading config from %s' % self.CONFIG_BASE_FILENAME) self.config = self.parse_config_file( base_filename=self.CONFIG_BASE_FILENAME, additional_configs=[self.ADDITIONAL_CONFIG] ) self.config['cache_dir'] = os.path.expanduser(self.config['cache_dir']) if self.config['cache_responses']: config.prepare_folders(self.config, 'cache_dir') if override_config: self.config.update(override_config) logger.debug('%s CONFIG=%s' % (self, self.config)) self.storage = get_storage(**self.config['storage']) self.scheduler = get_scheduler(**self.config['scheduler']) self.db_engine = create_engine(self.config['lister']['args']['db']) self.mk_session = sessionmaker(bind=self.db_engine) self.db_session = self.mk_session() def reset_backoff(self): """Reset exponential backoff timeout to initial level.""" self.backoff = self.INITIAL_BACKOFF def back_off(self): """Get next exponential backoff timeout.""" ret = self.backoff self.backoff *= 10 return ret def safely_issue_request(self, identifier): """Make network request with retries, rate quotas, and response logs. Protocol is handled by the implementation of the transport_request method. Args: identifier: resource identifier Returns: server response """ retries_left = self.MAX_RETRIES do_cache = self.config['cache_responses'] r = None while retries_left > 0: try: r = self.transport_request(identifier) except FetchError: # network-level connection error, try again logger.warning( 'connection error on %s: sleep for %d seconds' % (identifier, self.CONN_SLEEP)) time.sleep(self.CONN_SLEEP) retries_left -= 1 continue if do_cache: self.save_response(r) # detect throttling must_retry, delay = self.transport_quota_check(r) if must_retry: logger.warning( 'rate limited on %s: sleep for %f seconds' % (identifier, delay)) time.sleep(delay) else: # request ok break retries_left -= 1 if not retries_left: logger.warning( 'giving up on %s: max retries exceeded' % identifier) return r def db_query_equal(self, key, value): """Look in the db for a row with key == value Args: key: column key to look at value: value to look for in that column Returns: sqlalchemy.ext.declarative.declarative_base object with the given key == value """ if isinstance(key, str): key = self.MODEL.__dict__[key] return self.db_session.query(self.MODEL) \ .filter(key == value).first() def winnow_models(self, mlist, key, to_remove): """Given a list of models, remove any with matching some member of a list of values. Args: mlist (list of model rows): the initial list of models key (column): the column to filter on to_remove (list): if anything in mlist has column equal to one of the values in to_remove, it will be removed from the result Returns: A list of model rows starting from mlist minus any matching rows """ if isinstance(key, str): key = self.MODEL.__dict__[key] if to_remove: return mlist.filter(~key.in_(to_remove)).all() else: return mlist.all() def db_num_entries(self): """Return the known number of entries in the lister db""" return self.db_session.query(func.count('*')).select_from(self.MODEL) \ .scalar() def db_inject_repo(self, model_dict): """Add/update a new repo to the db and mark it last_seen now. Args: model_dict: dictionary mapping model keys to values Returns: new or updated sqlalchemy.ext.declarative.declarative_base object associated with the injection """ sql_repo = self.db_query_equal('uid', model_dict['uid']) if not sql_repo: sql_repo = self.MODEL(**model_dict) self.db_session.add(sql_repo) else: for k in model_dict: setattr(sql_repo, k, model_dict[k]) sql_repo.last_seen = utcnow() return sql_repo def task_dict(self, origin_type, origin_url, **kwargs): """Return special dict format for the tasks list Args: origin_type (string) origin_url (string) Returns: the same information in a different form """ _type = 'load-%s' % origin_type - _policy = 'recurring' - return utils.create_task_dict(_type, _policy, origin_url) + _policy = kwargs.get('policy', 'recurring') + priority = kwargs.get('priority') + kw = {'priority': priority} if priority else {} + return utils.create_task_dict(_type, _policy, origin_url, **kw) def string_pattern_check(self, a, b, c=None): """When comparing indexable types in is_within_bounds, complex strings may not be allowed to differ in basic structure. If they do, it could be a sign of not understanding the data well. For instance, an ISO 8601 time string cannot be compared against its urlencoded equivalent, but this is an easy mistake to accidentally make. This method acts as a friendly sanity check. Args: a (string): inner component of the is_within_bounds method b (string): lower component of the is_within_bounds method c (string): upper component of the is_within_bounds method Returns: nothing Raises: TypeError if strings a, b, and c don't conform to the same basic pattern. """ if isinstance(a, str): a_pattern = re.sub('[a-zA-Z0-9]', '[a-zA-Z0-9]', re.escape(a)) if (isinstance(b, str) and (re.match(a_pattern, b) is None) or isinstance(c, str) and (re.match(a_pattern, c) is None)): logger.debug(a_pattern) raise TypeError('incomparable string patterns detected') def inject_repo_data_into_db(self, models_list): """Inject data into the db. Args: models_list: list of dicts mapping keys from the db model for each repo to be injected Returns: dict of uid:sql_repo pairs """ injected_repos = {} for m in models_list: injected_repos[m['uid']] = self.db_inject_repo(m) return injected_repos def schedule_missing_tasks(self, models_list, injected_repos): """Find any newly created db entries that do not have been scheduled yet. Args: models_list ([Model]): List of dicts mapping keys in the db model for each repo injected_repos ([dict]): Dict of uid:sql_repo pairs that have just been created Returns: Nothing. Modifies injected_repos. """ tasks = {} def _task_key(m): return '%s-%s' % ( m['type'], json.dumps(m['arguments'], sort_keys=True) ) for m in models_list: ir = injected_repos[m['uid']] if not ir.task_id: + # Patching the model instance to add the policy/priority task + # scheduling + if 'policy' in self.config: + m['policy'] = self.config['policy'] + if 'priority' in self.config: + m['priority'] = self.config['priority'] task_dict = self.task_dict(**m) tasks[_task_key(task_dict)] = (ir, m, task_dict) new_tasks = self.scheduler.create_tasks( (task_dicts for (_, _, task_dicts) in tasks.values())) for task in new_tasks: ir, m, _ = tasks[_task_key(task)] ir.task_id = task['id'] def ingest_data(self, identifier, checks=False): """The core data fetch sequence. Request server endpoint. Simplify and filter response list of repositories. Inject repo information into local db. Queue loader tasks for linked repositories. Args: identifier: Resource identifier. checks (bool): Additional checks required """ # Request (partial?) list of repositories info response = self.safely_issue_request(identifier) if not response: return response, [] models_list = self.transport_response_simplified(response) models_list = self.filter_before_inject(models_list) if checks: models_list = self.do_additional_checks(models_list) if not models_list: return response, [] # inject into local db injected = self.inject_repo_data_into_db(models_list) # queue workers self.schedule_missing_tasks(models_list, injected) return response, injected def save_response(self, response): """Log the response from a server request to a cache dir. Args: response: full server response cache_dir: system path for cache dir Returns: nothing """ datepath = utcnow().isoformat() fname = os.path.join( self.config['cache_dir'], datepath + '.gz', ) with gzip.open(fname, 'w') as f: f.write(bytes( self.transport_response_to_string(response), 'UTF-8' )) diff --git a/swh/lister/cran/lister.py b/swh/lister/cran/lister.py index 55428b5..cae5f1f 100644 --- a/swh/lister/cran/lister.py +++ b/swh/lister/cran/lister.py @@ -1,121 +1,122 @@ # Copyright (C) 2019 the Software Heritage developers # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import subprocess import json import logging import pkg_resources from collections import defaultdict from swh.lister.cran.models import CRANModel from swh.scheduler.utils import create_task_dict from swh.core import utils from swh.lister.core.simple_lister import SimpleLister class CRANLister(SimpleLister): MODEL = CRANModel LISTER_NAME = 'cran' instance = 'cran' descriptions = defaultdict(dict) def task_dict(self, origin_type, origin_url, **kwargs): """Return task format dict This is overridden from the lister_base as more information is needed for the ingestion task creation. """ return create_task_dict( - 'load-%s' % origin_type, 'recurring', + 'load-%s' % origin_type, + kwargs.get('policy', 'recurring'), kwargs.get('name'), origin_url, kwargs.get('version'), project_metadata=self.descriptions[kwargs.get('name')]) def r_script_request(self): """Runs R script which uses inbuilt API to return a json response containing data about all the R packages Returns: List of dictionaries example [ {'Package': 'A3', 'Version': '1.0.0', 'Title': 'Accurate, Adaptable, and Accessible Error Metrics for Predictive\nModels', 'Description': 'Supplies tools for tabulating and analyzing the results of predictive models. The methods employed are ... ' } {'Package': 'abbyyR', 'Version': '0.5.4', 'Title': 'Access to Abbyy Optical Character Recognition (OCR) API', 'Description': 'Get text from images of text using Abbyy Cloud Optical Character\n ...' } ... ] """ file_path = pkg_resources.resource_filename('swh.lister.cran', 'list_all_packages.R') response = subprocess.run(file_path, stdout=subprocess.PIPE, shell=False) return json.loads(response.stdout) def get_model_from_repo(self, repo): """Transform from repository representation to model """ self.descriptions[repo["Package"]] = repo['Description'] project_url = 'https://cran.r-project.org/src/contrib' \ '/%(Package)s_%(Version)s.tar.gz' % repo return { 'uid': repo["Package"], 'name': repo["Package"], 'full_name': repo["Title"], 'version': repo["Version"], 'html_url': project_url, 'origin_url': project_url, 'origin_type': 'cran', } def transport_response_simplified(self, response): """Transform response to list for model manipulation """ return [self.get_model_from_repo(repo) for repo in response] def ingest_data(self, identifier, checks=False): """Rework the base ingest_data. Request server endpoint which gives all in one go. Simplify and filter response list of repositories. Inject repo information into local db. Queue loader tasks for linked repositories. Args: identifier: Resource identifier (unused) checks (bool): Additional checks required (unused) """ response = self.r_script_request() if not response: return response, [] models_list = self.transport_response_simplified(response) models_list = self.filter_before_inject(models_list) all_injected = [] for models in utils.grouper(models_list, n=10000): models = list(models) logging.debug('models: %s' % len(models)) # inject into local db injected = self.inject_repo_data_into_db(models) # queue workers self.create_missing_origins_and_tasks(models, injected) all_injected.append(injected) # flush self.db_session.commit() self.db_session = self.mk_session() return response, all_injected diff --git a/swh/lister/gnu/lister.py b/swh/lister/gnu/lister.py index 1029de7..48a9e7b 100644 --- a/swh/lister/gnu/lister.py +++ b/swh/lister/gnu/lister.py @@ -1,222 +1,223 @@ # Copyright (C) 2019 the Software Heritage developers # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import random import gzip import json import requests from pathlib import Path from collections import defaultdict from .models import GNUModel from swh.scheduler import utils from swh.lister.core.simple_lister import SimpleLister class GNULister(SimpleLister): MODEL = GNUModel LISTER_NAME = 'gnu' TREE_URL = 'https://ftp.gnu.org/tree.json.gz' BASE_URL = 'https://ftp.gnu.org' instance = 'gnu' tarballs = defaultdict(dict) # Dict of key with project name value the # associated is list of tarballs of package to ingest from the gnu mirror def task_dict(self, origin_type, origin_url, **kwargs): """ Return task format dict This is overridden from the lister_base as more information is needed for the ingestion task creation. """ return utils.create_task_dict( - 'load-%s' % origin_type, 'recurring', kwargs.get('name'), + 'load-%s' % origin_type, kwargs.get('policy', 'recurring'), + kwargs.get('name'), origin_url, tarballs=self.tarballs[kwargs.get('name')]) def get_file(self): ''' Download and unzip tree.json.gz file and returns its content in JSON format Returns File content in dictionary format ''' response = requests.get(self.TREE_URL, allow_redirects=True) uncompressed_content = gzip.decompress(response.content) return json.loads(uncompressed_content.decode('utf-8')) def safely_issue_request(self, identifier): ''' Make network request to download the file which has file structure of the GNU website. Args: identifier: resource identifier Returns: Server response ''' return self.get_file() def list_packages(self, response): """ List the actual gnu origins with their names,url and the list of all the tarball for a package from the response. Args: response : File structure of the website in dictionary format Returns: A list of all the packages with their names, url of their root directory and the tarballs present for the particular package. [ {'name': '3dldf', 'url': 'https://ftp.gnu.org/gnu/3dldf/', 'tarballs': [ {'archive': 'https://ftp.gnu.org/gnu/3dldf/3DLDF-1.1.3.tar.gz', 'date': '1071002600'}, {'archive': 'https://ftp.gnu.org/gnu/3dldf/3DLDF-1.1.4.tar.gz', 'date': '1071078759'}} ] }, {'name': '8sync', 'url': 'https://ftp.gnu.org/gnu/8sync/', 'tarballs': [ {'archive': 'https://ftp.gnu.org/gnu/8sync/8sync-0.1.0.tar.gz', 'date': '1461357336'}, {'archive': 'https://ftp.gnu.org/gnu/8sync/8sync-0.2.0.tar.gz', 'date': '1480991830'} ] ] """ response = filter_directories(response) packages = [] for directory in response: content = directory['contents'] for repo in content: if repo['type'] == 'directory': package_url = '%s/%s/%s/' % (self.BASE_URL, directory['name'], repo['name']) package_tarballs = find_tarballs( repo['contents'], package_url) if package_tarballs != []: repo_details = { 'name': repo['name'], 'url': package_url, 'time_modified': repo['time'], } self.tarballs[repo['name']] = package_tarballs packages.append(repo_details) random.shuffle(packages) return packages def get_model_from_repo(self, repo): """Transform from repository representation to model """ return { 'uid': repo['name'], 'name': repo['name'], 'full_name': repo['name'], 'html_url': repo['url'], 'origin_url': repo['url'], 'time_last_updated': repo['time_modified'], 'origin_type': 'tar', } def transport_response_simplified(self, response): """Transform response to list for model manipulation """ return [self.get_model_from_repo(repo) for repo in response] def find_tarballs(package_file_structure, url): ''' Recursively lists all the tarball present in the folder and subfolders for a particular package url. Args package_file_structure : File structure of the package root directory url : URL of the corresponding package Returns List of all the tarball urls and the last their time of update example- For a package called 3dldf [ {'archive': 'https://ftp.gnu.org/gnu/3dldf/3DLDF-1.1.3.tar.gz', 'date': '1071002600'} {'archive': 'https://ftp.gnu.org/gnu/3dldf/3DLDF-1.1.4.tar.gz', 'date': '1071078759'} {'archive': 'https://ftp.gnu.org/gnu/3dldf/3DLDF-1.1.5.1.tar.gz', 'date': '1074278633'} ... ] ''' tarballs = [] for single_file in package_file_structure: file_type = single_file['type'] file_name = single_file['name'] if file_type == 'file': if file_extension_check(file_name): tarballs .append({ "archive": url + file_name, "date": single_file['time'] }) # It will recursively check for tarballs in all sub-folders elif file_type == 'directory': tarballs_in_dir = find_tarballs( single_file['contents'], url + file_name + '/') tarballs.extend(tarballs_in_dir) return tarballs def filter_directories(response): ''' Keep only gnu and old-gnu folders from JSON ''' final_response = [] file_system = response[0]['contents'] for directory in file_system: if directory['name'] in ('gnu', 'old-gnu'): final_response.append(directory) return final_response def file_extension_check(file_name): ''' Check for the extension of the file, if the file is of zip format of .tar.x format, where x could be anything, then returns true. Args: file_name : name of the file for which the extensions is needs to be checked. Returns: True or False example file_extension_check('abc.zip') will return True file_extension_check('abc.tar.gz') will return True file_extension_check('abc.tar.gz.sig') will return False ''' file_suffixes = Path(file_name).suffixes if len(file_suffixes) == 1 and file_suffixes[-1] == '.zip': return True elif len(file_suffixes) > 1: if file_suffixes[-1] == '.zip' or file_suffixes[-2] == '.tar': return True return False diff --git a/swh/lister/packagist/lister.py b/swh/lister/packagist/lister.py index 29ddbc6..93a9fb8 100644 --- a/swh/lister/packagist/lister.py +++ b/swh/lister/packagist/lister.py @@ -1,84 +1,85 @@ # Copyright (C) 2019 the Software Heritage developers # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import random import json from .models import PackagistModel from swh.scheduler import utils from swh.lister.core.simple_lister import SimpleLister from swh.lister.core.lister_transports import ListerOnePageApiTransport class PackagistLister(ListerOnePageApiTransport, SimpleLister): """List packages available in the Packagist package manger. The lister sends the request to the url present in the class variable `PAGE`, to receive a list of all the package names present in the Packagist package manger. Iterates over all the packages and constructs the metadata url of the package from the name of the package and creates a loading task. Task: Type: load-packagist Policy: recurring Args: Example: Type: load-packagist Policy: recurring Args: 'hypejunction/hypegamemechanics' 'https://repo.packagist.org/p/hypejunction/hypegamemechanics.json' """ MODEL = PackagistModel LISTER_NAME = 'packagist' PAGE = 'https://packagist.org/packages/list.json' instance = 'packagist' def __init__(self, override_config=None): ListerOnePageApiTransport .__init__(self) SimpleLister.__init__(self, override_config=override_config) def task_dict(self, origin_type, origin_url, **kwargs): """Return task format dict This is overridden from the lister_base as more information is needed for the ingestion task creation. """ - return utils.create_task_dict('load-%s' % origin_type, 'recurring', + return utils.create_task_dict('load-%s' % origin_type, + kwargs.get('policy', 'recurring'), kwargs.get('name'), origin_url) def list_packages(self, response): """List the actual packagist origins from the response. """ response = json.loads(response.text) packages = [name for name in response['packageNames']] random.shuffle(packages) return packages def get_model_from_repo(self, repo_name): """Transform from repository representation to model """ url = 'https://repo.packagist.org/p/%s.json' % repo_name return { 'uid': repo_name, 'name': repo_name, 'full_name': repo_name, 'html_url': url, 'origin_url': url, 'origin_type': 'packagist', } def transport_response_simplified(self, response): """Transform response to list for model manipulation """ return [self.get_model_from_repo(repo_name) for repo_name in response] diff --git a/swh/lister/pypi/lister.py b/swh/lister/pypi/lister.py index f45a3a6..c8e0e0d 100644 --- a/swh/lister/pypi/lister.py +++ b/swh/lister/pypi/lister.py @@ -1,76 +1,76 @@ # Copyright (C) 2018-2019 the Software Heritage developers # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import random import xmltodict from .models import PyPIModel from swh.scheduler import utils from swh.lister.core.simple_lister import SimpleLister from swh.lister.core.lister_transports import ListerOnePageApiTransport class PyPILister(ListerOnePageApiTransport, SimpleLister): MODEL = PyPIModel LISTER_NAME = 'pypi' PAGE = 'https://pypi.org/simple/' instance = 'pypi' # As of today only the main pypi.org is used def __init__(self, override_config=None): ListerOnePageApiTransport .__init__(self) SimpleLister.__init__(self, override_config=override_config) def task_dict(self, origin_type, origin_url, **kwargs): """(Override) Return task format dict This is overridden from the lister_base as more information is needed for the ingestion task creation. """ _type = 'load-%s' % origin_type - _policy = 'recurring' + _policy = kwargs.get('policy', 'recurring') project_name = kwargs.get('name') project_metadata_url = kwargs.get('html_url') return utils.create_task_dict( _type, _policy, project_name, origin_url, project_metadata_url=project_metadata_url) def list_packages(self, response): """(Override) List the actual pypi origins from the response. """ result = xmltodict.parse(response.content) _packages = [p['#text'] for p in result['html']['body']['a']] random.shuffle(_packages) return _packages def _compute_urls(self, repo_name): """Returns a tuple (project_url, project_metadata_url) """ return ( 'https://pypi.org/project/%s/' % repo_name, 'https://pypi.org/pypi/%s/json' % repo_name ) def get_model_from_repo(self, repo_name): """(Override) Transform from repository representation to model """ project_url, project_url_meta = self._compute_urls(repo_name) return { 'uid': repo_name, 'name': repo_name, 'full_name': repo_name, 'html_url': project_url_meta, 'origin_url': project_url, 'origin_type': 'pypi', } def transport_response_simplified(self, response): """(Override) Transform response to list for model manipulation """ return [self.get_model_from_repo(repo_name) for repo_name in response]