Skip to content

Make this reppo uptodate/runnable #5

Make this reppo uptodate/runnable

Make this reppo uptodate/runnable #5

Triggered via pull request April 3, 2024 14:54
@SkitionekSkitionek
synchronize #2
Status Success
Total duration 18s
Artifacts

labeler.yml

on: pull_request_target
Fit to window
Zoom out
Zoom in

Annotations

36 errors and 1 warning
.github/workflows/browserstack.yml#L1
There are issues with this file's formatting, please run Prettier to fix the errors
.github/workflows/codeql-analysis.yml#L1
There are issues with this file's formatting, please run Prettier to fix the errors
docker/README.md#L1
There are issues with this file's formatting, please run Prettier to fix the errors
graph-db/extractor/docs/biocyc/spec.md#L1
There are issues with this file's formatting, please run Prettier to fix the errors
graph-db/extractor/docs/kegg/kegg_spec.md#L1
There are issues with this file's formatting, please run Prettier to fix the errors
graph-db/extractor/docs/literature/literature_spec.md#L1
There are issues with this file's formatting, please run Prettier to fix the errors
/work/graph-db/extractor/src/common/liquibase_utils.py#L29
class ChangeLog: def __init__(self, author: str, change_id_prefix: str): if not change_id_prefix: - raise ValueError('The argument change_id_prefix must not be null or empty string') + raise ValueError( + 'The argument change_id_prefix must not be null or empty string' + ) try: int(change_id_prefix.split('-')[1]) except Exception: - raise ValueError('The argument change_id_prefix must be the JIRA card number; e.g LL-1234') + raise ValueError( + 'The argument change_id_prefix must be the JIRA card number; e.g LL-1234' + ) self.author = author self.id_prefix = change_id_prefix self.file_prefix = f'jira-{change_id_prefix}-' self.logger = logging.getLogger(__name__)
graph-db/extractor/docs/mesh/mesh_rdf_data_model.md#L1
There are issues with this file's formatting, please run Prettier to fix the errors
/work/graph-db/extractor/src/common/liquibase_utils.py#L70
def create_changelog_str(self): template = get_template(sql_template) # liquibase doesn't like the `<` character self.cypher = self.cypher.replace('<', '&lt;') - return template.render(change_id=self.id, author=self.author, change_comment=self.comment, cypher_query=self.cypher) + return template.render( + change_id=self.id, + author=self.author, + change_comment=self.comment, + cypher_query=self.cypher, + ) class CustomChangeSet(ChangeSet): - def __init__(self, id, author, comment, cypher, - filename:str, - handler="edu.ucsd.sbrg.FileQueryHandler", - filetype='TSV', - startrow=1): + def __init__( + self, + id, + author, + comment, + cypher, + filename: str, + handler="edu.ucsd.sbrg.FileQueryHandler", + filetype='TSV', + startrow=1, + ): ChangeSet.__init__(self, id, author, comment, cypher) self.handler = handler self.filename = filename.replace('.tsv', '.zip') self.filetype = filetype self.start_at = startrow def create_changelog_str(self): template = get_template(custom_template) - return template.render(change_id=self.id, change_comment=self.comment, author=self.author, - handler_class=self.handler, cypher_query=self.cypher, data_file=self.filename, - start_at=self.start_at, file_type=self.filetype, params=CUSTOM_PARAMS) + return template.render( + change_id=self.id, + change_comment=self.comment, + author=self.author, + handler_class=self.handler, + cypher_query=self.cypher, + data_file=self.filename, + start_at=self.start_at, + file_type=self.filetype, + params=CUSTOM_PARAMS, + ) def generate_sql_changelog_file(id, author, comment, cypher, outfile): changeset = ChangeSet(id, author, comment, cypher) temp = get_changelog_template()
graph-db/extractor/docs/ncbi/taxonomy_spec.md#L1
There are issues with this file's formatting, please run Prettier to fix the errors
/work/graph-db/extractor/src/common/liquibase_utils.py#L102
if __name__ == '__main__': cypher = 'match(n:Gene)-[r]-(:Gene) where r.score < 0.4 delete r;' comment = 'Remove ecocyc-plus string relationships with 0.4 threshold. After the update, create ecocyc-plus-10012021.dump file' - outfile = os.path.join('../../../migration/liquibase/ecocyc-plus/ecocyc-plus changelog-0010.xml') - generate_sql_changelog_file('LL-3702 cut string rels with threshold', 'robin cai', - comment, - cypher, outfile) + outfile = os.path.join( + '../../../migration/liquibase/ecocyc-plus/ecocyc-plus changelog-0010.xml' + ) + generate_sql_changelog_file( + 'LL-3702 cut string rels with threshold', 'robin cai', comment, cypher, outfile + )
graph-db/extractor/docs/other/scripts for LMDB annotation file.md#L1
There are issues with this file's formatting, please run Prettier to fix the errors
/work/graph-db/extractor/src/biocyc/base_data_file_parser.py#L14
class BaseDataFileParser(BaseParser): """ Base parser for Biocyc .dat files. """ - def __init__(self, base_data_dir: str, biocyc_dbname, tar_file, datafile_name, entity_name, attr_names:dict, rel_names:dict, - db_link_sources: dict=None): + + def __init__( + self, + base_data_dir: str, + biocyc_dbname, + tar_file, + datafile_name, + entity_name, + attr_names: dict, + rel_names: dict, + db_link_sources: dict = None, + ): """ :param base_data_dir: the data file base directory, that is the parent folder for 'download' :param biocyc_dbname: biocyc database name, eg. DB_ECOCYC, DB_HUMANCYC :param tar_file: tar file downloaded from biocyc website :param datafile_name: the data file name to process (in tar_file), e.g. genes.dat
graph-db/extractor/src/biocyc/data_sources.json#L1
There are issues with this file's formatting, please run Prettier to fix the errors
/work/graph-db/extractor/src/biocyc/base_data_file_parser.py#L30
""" BaseParser.__init__(self, DB_BIOCYC.lower(), base_data_dir) self.input_zip = os.path.join(self.download_dir, tar_file) self.db_output_dir = os.path.join(self.output_dir, biocyc_dbname.lower()) self.datafile = datafile_name - self.node_labels = [NODE_BIOCYC, 'db_' + biocyc_dbname, entity_name] + self.node_labels = [NODE_BIOCYC, 'db_' + biocyc_dbname, entity_name] self.entity_name = entity_name self.attr_name_map = attr_names self.rel_name_map = rel_names self.db_link_sources = db_link_sources self.attrs = [] self.version = '' self.logger = logging.getLogger(__name__) - def create_synonym_rels(self)->bool: + def create_synonym_rels(self) -> bool: return False - def get_db_version(self, tar:TarFile): + def get_db_version(self, tar: TarFile): """ find the latest version of data in the tar file. Sometimes a tar file has multiple version data. :param tar: :return: """
graph-db/migrator/README.md#L1
There are issues with this file's formatting, please run Prettier to fix the errors
/work/graph-db/extractor/src/biocyc/base_data_file_parser.py#L63
with tarfile.open(self.input_zip, mode='r:gz') as tar: if not self.version: self.version = self.get_db_version(tar) self.logger.info(f'Database file version: "{self.version}"') for tarinfo in tar: - if tarinfo.name.endswith('/'+ self.datafile) and self.version in tarinfo.name: + if ( + tarinfo.name.endswith('/' + self.datafile) + and self.version in tarinfo.name + ): self.logger.info('Parse ' + tarinfo.name) utf8reader = codecs.getreader('ISO-8859-1') f = utf8reader(tar.extractfile(tarinfo.name)) nodes = [] node = None prev_line_is_comment = False for line in f: line = biocyc_utils.cleanhtml(line) - node, prev_line_is_comment = self.parse_line(line, node, nodes, prev_line_is_comment) + node, prev_line_is_comment = self.parse_line( + line, node, nodes, prev_line_is_comment + ) return nodes def parse_line(self, line, node, nodes, prev_line_is_comment): try: if line.startswith(UNIQUE_ID): node = NodeData(self.node_labels.copy(), PROP_BIOCYC_ID) nodes.append(node) # add data source property node.add_attribute(PROP_DATA_SOURCE, DB_BIOCYC, "str") - if node and PROP_COMMENT in self.attr_name_map and prev_line_is_comment and line.startswith('/'): + if ( + node + and PROP_COMMENT in self.attr_name_map + and prev_line_is_comment + and line.startswith('/') + ): line = line[1:].strip() node.add_attribute(PROP_COMMENT, line, 'str') elif node: attr, val = biocyc_utils.get_attr_val_from_line(line) if attr:
helm/lifelike/examples/external-db.yaml#L1
There are issues with this file's formatting, please run Prettier to fix the errors
/work/graph-db/extractor/src/biocyc/base_data_file_parser.py#L95
# reset comment prev_line_is_comment = False else: prev_line_is_comment = True if attr in self.attr_name_map: - prop_name, data_type = biocyc_utils.get_property_name_type(attr, self.attr_name_map) + prop_name, data_type = biocyc_utils.get_property_name_type( + attr, self.attr_name_map + ) node.add_attribute(prop_name, val, data_type) if attr == UNIQUE_ID: node.add_attribute(PROP_ID, val, data_type) if attr in self.rel_name_map: # some rel could also be an attribute, e.g. types
helm/lifelike/README.md#L1
There are issues with this file's formatting, please run Prettier to fix the errors
/work/graph-db/extractor/src/biocyc/base_data_file_parser.py#L107
tokens = val.split(' ') if len(tokens) > 1: db_name = tokens[0].lstrip('(') reference_id = tokens[1].strip(')').strip('"') add_prefix = tokens[1] - self.add_dblink(node, db_name, reference_id, ) + self.add_dblink( + node, + db_name, + reference_id, + ) else: rel_type = self.rel_name_map.get(attr) node.add_edge_type(rel_type, val) except Exception as ex: self.logger.error('line:', line) return node, prev_line_is_comment - def add_dblink(self, node:NodeData, db_name, reference_id): + def add_dblink(self, node: NodeData, db_name, reference_id): link_node = NodeData(NODE_DBLINK, PROP_REF_ID) if reference_id.startswith(db_name): - reference_id = reference_id[len(db_name)+1:] # remove db prefix + reference_id = reference_id[len(db_name) + 1 :] # remove db prefix link_node.update_attribute(PROP_REF_ID, reference_id) link_node.update_attribute(PROP_DB_NAME, db_name) node.add_edge(node, link_node, REL_DBLINKS) def create_indexes(self, database: Database): - database.create_index(self.entity_name, PROP_ID, f"index_{self.entity_name.lower}_id") - database.create_index(self.entity_name, PROP_BIOCYC_ID, f"index_{self.entity_name.lower}_biocycid") - database.create_index(self.entity_name, PROP_NAME, f"index_{self.entity_name.lower}_name") - - def update_nodes_in_graphdb(self, nodes:[], database:Database, etl_load_id: str): + database.create_index( + self.entity_name, PROP_ID, f"index_{self.entity_name.lower}_id" + ) + database.create_index( + self.entity_name, PROP_BIOCYC_ID, f"index_{self.entity_name.lower}_biocycid" + ) + database.create_index( + self.entity_name, PROP_NAME, f"index_{self.entity_name.lower}_name" + ) + + def update_nodes_in_graphdb(self, nodes: [], database: Database, etl_load_id: str): """ Load or update nodes in KG. This can also be called for initial loading. :param nodes: list of nodes :param database: neo4j Database :param etl_load: Id that (virtually) links a node to an EtlLoad node.
helm/lifelike/values.schema.json#L1
There are issues with this file's formatting, please run Prettier to fix the errors
/work/graph-db/extractor/src/biocyc/base_data_file_parser.py#L143
self.logger.info('Update nodes: ' + ':'.join(self.node_labels)) rows = [] for node in nodes: rows.append(node.to_dict()) attrs = self.attrs + [PROP_ID, PROP_DATA_SOURCE] - query = get_update_nodes_query(NODE_BIOCYC, PROP_BIOCYC_ID, attrs, self.node_labels, etl_load_id=etl_load_id, return_node_count=True) + query = get_update_nodes_query( + NODE_BIOCYC, + PROP_BIOCYC_ID, + attrs, + self.node_labels, + etl_load_id=etl_load_id, + return_node_count=True, + ) return database.load_data_from_rows(query, rows, return_node_count=True) - def add_edges_to_graphdb(self, nodes:[], database:Database, etl_load_id): + def add_edges_to_graphdb(self, nodes: [], database: Database, etl_load_id): no_of_created_nodes = 0 no_of_updated_nodes = 0 no_of_created_relations = 0 no_of_updated_relations = 0 entity_rel_dict = dict()
helm/lifelike/values.yaml#L1
There are issues with this file's formatting, please run Prettier to fix the errors
/work/graph-db/extractor/src/biocyc/base_data_file_parser.py#L159
for node in nodes: if self.create_synonym_rels(): id = node.get_attribute(PROP_BIOCYC_ID) synonyms = node.get_synonym_set() for syn in synonyms: - synonym_list.append({PROP_BIOCYC_ID:id, PROP_NAME: syn}) + synonym_list.append({PROP_BIOCYC_ID: id, PROP_NAME: syn}) for edge in node.edges: from_id = edge.source.get_attribute(edge.source.id_attr) to_id = edge.dest.get_attribute(edge.dest.id_attr) rel = edge.label if rel == REL_DBLINKS:
README.md#L1
There are issues with this file's formatting, please run Prettier to fix the errors
/work/graph-db/extractor/src/biocyc/base_data_file_parser.py#L171
continue db_name = edge.dest.get_attribute(PROP_DB_NAME) if db_name in self.db_link_sources: if db_name not in db_link_dict: db_link_dict[db_name] = [] - db_link_dict[db_name].append({'from_id': from_id, 'to_id': to_id}) + db_link_dict[db_name].append( + {'from_id': from_id, 'to_id': to_id} + ) else: if rel not in entity_rel_dict: entity_rel_dict[rel] = [] entity_rel_dict[rel].append({'from_id': from_id, 'to_id': to_id}) if synonym_list: self.logger.info('Add synonyms') - query = get_create_synonym_relationships_query(NODE_BIOCYC, PROP_BIOCYC_ID, PROP_BIOCYC_ID, PROP_NAME, [], etl_load_id=etl_load_id, return_node_count=True) + query = get_create_synonym_relationships_query( + NODE_BIOCYC, + PROP_BIOCYC_ID, + PROP_BIOCYC_ID, + PROP_NAME, + [], + etl_load_id=etl_load_id, + return_node_count=True, + ) self.logger.debug(query) - node_count, result_counters = database.load_data_from_rows(query, synonym_list, return_node_count=True) + node_count, result_counters = database.load_data_from_rows( + query, synonym_list, return_node_count=True + ) no_of_created_nodes += result_counters.nodes_created - no_of_updated_nodes += (node_count - result_counters.nodes_created) + no_of_updated_nodes += node_count - result_counters.nodes_created for rel in entity_rel_dict.keys(): self.logger.info('Add relationship ' + rel) - query = get_create_relationships_query(NODE_BIOCYC, PROP_BIOCYC_ID, 'from_id', - NODE_BIOCYC, PROP_BIOCYC_ID, 'to_id', rel, etl_load_id=etl_load_id, return_node_count=True) + query = get_create_relationships_query( + NODE_BIOCYC, + PROP_BIOCYC_ID, + 'from_id', + NODE_BIOCYC, + PROP_BIOCYC_ID, + 'to_id', + rel, + etl_load_id=etl_load_id, + return_node_count=True, + ) self.logger.debug(query) - node_count, result_counters = database.load_data_from_rows(query, entity_rel_dict[rel], return_node_count=True) + node_count, result_counters = database.load_data_from_rows( + query, entity_rel_dict[rel], return_node_count=True + ) no_of_created_relations += result_counters.relationships_created - no_of_updated_relations += (node_count - result_counters.relationships_created) - - _no_of_created_relations, _no_of_updated_relations = self.add_dblinks_to_graphdb(db_link_dict, database, etl_load_id) + no_of_updated_relations += ( + node_count - result_counters.relationships_created + ) + + ( + _no_of_created_relations, + _no_of_updated_relations, + ) = self.add_dblinks_to_graphdb(db_link_dict, database, etl_load_id) no_of_created_relations += _no_of_created_relations no_of_updated_relations += _no_of_updated_relations - return no_of_created_nodes, no_of_updated_nodes, no_of_created_relations, no_of_updated_relations - - def add_dblinks_to_graphdb(self, db_link_dict:dict, database:Database, etl_load_id): + return ( + no_of_created_nodes, + no_of_updated_nodes, + no_of_created_relations, + no_of_updated_relations, + ) + + def add_dblinks_to_graphdb( + self, db_link_dict: dict, database: Database, etl_load_id + ): no_of_created_relations = 0 no_of_updated_relations = 0 for db_name in db_link_dict.keys(): - self.logger.info('Add DB Link relationship to ' + db_name ) + self.logger.info('Add DB Link relationship to ' + db_name) dest_label = 'db_' + db_name rel = db_name.upper() + '_LINK' - query = get_create_relationships_query(NODE_BIOCYC, PROP_BIOCYC_ID, 'from_id', - dest_label, PROP_ID, 'to_id', rel, etl_load_id=etl_load_id, return_node_count=True) + query = get_create_relationships_query( + NODE_BIOCYC, + PROP_BIOCYC_ID, + 'from_id', + dest_label, + PROP_ID, + 'to_id', + rel, + etl_load_id=etl_load_id, + return_node_count=True, + ) self.logger.debug(query) - node_count, result_counters = database.load_data_from_rows(query, db_link_dict[db_name], return_node_count=True) + node_count, result_counters = database.load_data_from_rows( + query, db_link_dict[db_name], return_node_count=True + ) no_of_created_relations += result_counters.relationships_created - no_of_updated_relations += (node_count - result_counters.relationships_created) + no_of_updated_relations += ( + node_count - result_counters.relationships_created + ) return no_of_created_relations, no_of_updated_relations - def write_entity_data_files(self, nodes:[]): + def write_entity_data_files(self, nodes: []): os.makedirs(self.db_output_dir, 0o777, True) self.logger.info(f'Writing {self.entity_name} files') - with open(os.path.join(self.db_output_dir, self.entity_name.lower() + '.tsv'), 'w') as f: + with open( + os.path.join(self.db_output_dir, self.entity_name.lower() + '.tsv'), 'w' + ) as f: attrs = [PROP_ID] + [PROP_DATA_SOURCE] + self.attrs f.write('\t'.join(attrs) + '\n') f.writelines(NodeData.get_entity_data_rows(nodes, attrs)) -
tests/cypress/browserstack.json#L1
There are issues with this file's formatting, please run Prettier to fix the errors
/work/graph-db/extractor/src/ncbi/ncbi_taxonomy_liquibase.py#L6
from common.query_builder import * from ncbi.ncbi_taxonomy_parser import * # reference to this directory directory = os.path.realpath(os.path.dirname(__file__)) + class NcbiTaxonomyChangeLog(ChangeLog): def __init__(self, author: str, change_id_prefix: str): super().__init__(author, change_id_prefix) self.date_tag = datetime.today().strftime('%m%d%Y')
tests/cypress/cypress/integration/projects.spec.js#L1
There are issues with this file's formatting, please run Prettier to fix the errors
/work/graph-db/extractor/src/ncbi/ncbi_taxonomy_liquibase.py#L26
def load_ncbi_taxonomy_nodes(self): id = f'NCBI taxonomy data on date {self.date_tag}' if self.id_prefix: id = f'{self.id_prefix} {id}' comment = 'Load NCBI taxonomy nodes' - query = get_create_update_nodes_query(NODE_TAXONOMY, PROP_ID, NODE_ATTRS, [NODE_NCBI], datasource='NCBI Taxonomy') - changeset = CustomChangeSet(id, self.author, comment, query, f'{self.file_prefix}{NCBI_TAXONOMY_FILE}') + query = get_create_update_nodes_query( + NODE_TAXONOMY, PROP_ID, NODE_ATTRS, [NODE_NCBI], datasource='NCBI Taxonomy' + ) + changeset = CustomChangeSet( + id, self.author, comment, query, f'{self.file_prefix}{NCBI_TAXONOMY_FILE}' + ) self.change_sets.append(changeset) def load_ncbi_taxonomy_synonym_rels(self): id = f'load NCBI taxonomy synonym relationship on date {self.date_tag}' if self.id_prefix: id = f'{self.id_prefix} {id}' comment = 'Load NCBI gene taxonomy relationship' - query = get_create_synonym_relationships_query(NODE_TAXONOMY, PROP_ID, PROP_ID, PROP_NAME, [PROP_TYPE]) - changeset = CustomChangeSet(id, self.author, comment, query, f'{self.file_prefix}{NCBI_TAXONOMY_SYNONYM_FILE}') + query = get_create_synonym_relationships_query( + NODE_TAXONOMY, PROP_ID, PROP_ID, PROP_NAME, [PROP_TYPE] + ) + changeset = CustomChangeSet( + id, + self.author, + comment, + query, + f'{self.file_prefix}{NCBI_TAXONOMY_SYNONYM_FILE}', + ) self.change_sets.append(changeset) def load_ncbi_taxonomy_parent_rels(self): id = f'create relationship between taxonomy and parent nodes on date {self.date_tag}' if self.id_prefix:
tests/cypress/cypress/integration/tabs.spec.js#L1
There are issues with this file's formatting, please run Prettier to fix the errors
/work/graph-db/extractor/src/ncbi/ncbi_taxonomy_liquibase.py#L48
comment = 'Taxonomy relationship with parent' query = """ CALL apoc.periodic.iterate( 'MATCH (n:Taxonomy), (m:Taxonomy) WHERE m.prop = n.parent_id RETURN n, m', 'MERGE (n)-[:HAS_PARENT]->(m)', {batchSize:5000}) - """.replace('prop', PROP_ID) + """.replace( + 'prop', PROP_ID + ) changeset = ChangeSet(id, self.author, comment, query) self.change_sets.append(changeset) def set_species_id(self): id = f'set species_id for taxonomy nodes on date {self.date_tag}'
tests/cypress/cypress/support/commands.js#L1
There are issues with this file's formatting, please run Prettier to fix the errors
/work/graph-db/extractor/src/ncbi/ncbi_taxonomy_liquibase.py#L63
changeset = ChangeSet(id, self.author, comment, query) self.change_sets.append(changeset) def create_indexes(self): queries = [] - queries.append(get_create_constraint_query(NODE_TAXONOMY, PROP_ID, 'constraint_taxonomy_id') + ';') - queries.append(get_create_constraint_query(NODE_SYNONYM, PROP_NAME, 'constraint_synonym_name') + ';') - queries.append(get_create_index_query(NODE_TAXONOMY, PROP_NAME, 'index_taxonomy_name') + ';') - queries.append(get_create_index_query(NODE_TAXONOMY, 'species_id', 'index_taxonomy_speciesid') + ';') + queries.append( + get_create_constraint_query( + NODE_TAXONOMY, PROP_ID, 'constraint_taxonomy_id' + ) + + ';' + ) + queries.append( + get_create_constraint_query( + NODE_SYNONYM, PROP_NAME, 'constraint_synonym_name' + ) + + ';' + ) + queries.append( + get_create_index_query(NODE_TAXONOMY, PROP_NAME, 'index_taxonomy_name') + + ';' + ) + queries.append( + get_create_index_query( + NODE_TAXONOMY, 'species_id', 'index_taxonomy_speciesid' + ) + + ';' + ) return queries def add_index_change_set(self): id = f'create NCBI taxonomy constraints on date {self.date_tag}' if self.id_prefix:
tests/cypress/cypress/support/index.js#L1
There are issues with this file's formatting, please run Prettier to fix the errors
triage
Node.js 16 actions are deprecated. Please update the following actions to use Node.js 20: actions/labeler@v4. For more information see: https://github.blog/changelog/2023-09-22-github-actions-transitioning-from-node-16-to-node-20/.