From a19c1220f1b9ec84fb747efcaac7d8cbf95cb64f Mon Sep 17 00:00:00 2001 From: haohangyan Date: Tue, 4 Mar 2025 12:58:23 -0500 Subject: [PATCH 1/2] Fixed syntax warning for escape string --- indra_db/cli/content.py | 4 ++-- indra_db/reading/read_db.py | 2 +- indra_db/util/aws.py | 2 +- indra_db/util/data_gatherer.py | 2 +- indra_db/util/s3_path.py | 2 +- 5 files changed, 6 insertions(+), 6 deletions(-) diff --git a/indra_db/cli/content.py b/indra_db/cli/content.py index 1138daa24..001a2c566 100644 --- a/indra_db/cli/content.py +++ b/indra_db/cli/content.py @@ -226,7 +226,7 @@ class ContentManager(object): tr_cols: Tuple = NotImplemented tc_cols: Tuple = NotImplemented primary_col: str = NotImplemented - err_patt = re.compile('.*?constraint "(.*?)".*?Key \((.*?)\)=\((.*?)\).*?', + err_patt = re.compile(r'.*?constraint "(.*?)".*?Key \((.*?)\)=\((.*?)\).*?', re.DOTALL) def __init__(self): @@ -1513,7 +1513,7 @@ def get_file_data(self): def get_tarname_from_filename(self, fname): "Get the name of the tar file based on the file name (or a pmcid)." - re_match = re.match('(PMC00\d).*?', fname) + re_match = re.match(r'(PMC00\d).*?', fname) if re_match is not None: tarname = re_match.group(0) + 6*'X' + '.xml.tar.gz' else: diff --git a/indra_db/reading/read_db.py b/indra_db/reading/read_db.py index 0f51ee2f5..3337022b4 100644 --- a/indra_db/reading/read_db.py +++ b/indra_db/reading/read_db.py @@ -193,7 +193,7 @@ def __init__(self, result, reading_id=None, db_info_id=None, class DatabaseStatementData(DatabaseResultData): def __init__(self, *args, **kwargs): super(DatabaseStatementData, self).__init__(*args, **kwargs) - self.__text_patt = re.compile('[\W_]+') + self.__text_patt = re.compile(r'[\W_]+') @staticmethod def get_cols(): diff --git a/indra_db/util/aws.py b/indra_db/util/aws.py index 3d079d69f..8540e908d 100644 --- a/indra_db/util/aws.py +++ b/indra_db/util/aws.py @@ -3,7 +3,7 @@ def uncamel(word): - return re.sub(r'([a-z])([A-Z])', '\g<1>_\g<2>', word).lower() + return re.sub(r'([a-z])([A-Z])', r'\g<1>_\g<2>', word).lower() def get_role_kwargs(role): diff --git a/indra_db/util/data_gatherer.py b/indra_db/util/data_gatherer.py index a2fd43abf..d448f3867 100644 --- a/indra_db/util/data_gatherer.py +++ b/indra_db/util/data_gatherer.py @@ -183,7 +183,7 @@ def digest_s3_files(): bucket = S3_DATA_LOC['bucket'] prefix = S3_DATA_LOC['prefix'] - patt = re.compile(prefix + '([0-9]+)/(\w*?)/?(\w+)_([0-9]+).json') + patt = re.compile(prefix + r'([0-9]+)/(\w*?)/?(\w+)_([0-9]+).json') # Get a list of the prefixes for each day. res = s3.list_objects_v2(Bucket=bucket, Prefix=prefix, Delimiter='/') diff --git a/indra_db/util/s3_path.py b/indra_db/util/s3_path.py index 585d03a5b..0f5a2ed96 100644 --- a/indra_db/util/s3_path.py +++ b/indra_db/util/s3_path.py @@ -86,7 +86,7 @@ def from_key_parts(cls, bucket, *key_elements): @classmethod def from_string(cls, s3_key_str): - patt = re.compile('s3://([a-z0-9\-.]+)/(.*)') + patt = re.compile(r's3://([a-z0-9\-.]+)/(.*)') m = patt.match(s3_key_str) if m is None: raise ValueError("Invalid format for s3 path: %s" % s3_key_str) From bf7bcca411a0d9261316647bcdb02297d0aa78ed Mon Sep 17 00:00:00 2001 From: haohangyan Date: Tue, 4 Mar 2025 16:18:59 -0500 Subject: [PATCH 2/2] Fixed variable passing for n_proc --- indra_db/cli/reading.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/indra_db/cli/reading.py b/indra_db/cli/reading.py index 3a9881a02..001c0bb09 100644 --- a/indra_db/cli/reading.py +++ b/indra_db/cli/reading.py @@ -395,7 +395,7 @@ def run_local(task, buffer, num_procs): readers = ['SPARSER', 'REACH', 'EIDOS', 'TRIPS'] bulk_manager = BulkLocalReadingManager(readers, buffer_days=buffer, - n_procs=num_procs) + n_proc=num_procs) if task == 'all': bulk_manager.read_all(db) elif task == 'new':