Fetch sample/case names from database

Fetch the sample/case names from the database rather than from a
static file in the repository.

Issue:
https://issues.genenetwork.org/issues/quality-control/read-samples-from-database-by-species

2 files changed, 51 insertions, 59 deletions

diff --git a/scripts/qc.py b/scripts/qc.py
index 7d41d6c..e8573a9 100644
--- a/scripts/qc.py
+++ b/scripts/qc.py
@@ -1,9 +1,9 @@
 """Implements the command-line interface for the qc application"""
 import os
 import sys
-import argparse
 import mimetypes
 from typing import Union, Callable
+from argparse import ArgumentParser
 
 from functional_tools import take
 
@@ -11,17 +11,18 @@ from quality_control.utils import make_progress_calculator
 from quality_control.errors import InvalidValue, DuplicateHeading
 from quality_control.parsing import FileType, strain_names, collect_errors
 
+from qc_app.db_utils import database_connection
+
+from .cli_parser import init_cli_parser
+
 
 def is_file_mime(filepath:str, mimetype:str) -> bool:
     """Check that `filepath` has a mimetype of `mimetype` or `text/plain`"""
     the_type = mimetypes.guess_type(filepath)[0]
     return the_type in ("text/plain", mimetype)
 
-def cli_argument_parser():
-    """Create the parser for the CLI arguments"""
-    parser = argparse.ArgumentParser(
-        prog="qc", description = (
-            "Command-Line Interface program for quality control of data files"))
+def add_file_validation_arguments(parser: ArgumentParser) -> ArgumentParser:
+    """File validation specific CLI arguments."""
     parser.add_argument(
         "filetype",
         help="The type of file to check",
@@ -32,14 +33,6 @@ def cli_argument_parser():
             "The path to the file to be checked."
             "If an absolute path is not provided, then the file will be relative to"
             f"\t'{os.getcwd()}'"))
-    default_strains_file = os.path.join(
-        os.path.dirname(os.path.dirname(__file__)), "etc/strains.csv")
-    parser.add_argument(
-        "-s", "--strainsfile",
-        help=(
-            "Path to the file containing allowable strains/samples. "
-            f"[default '{default_strains_file}']"),
-        default=default_strains_file)
 
     parser.add_argument(
         "-c", "--count", type=int,
@@ -54,6 +47,14 @@ def cli_argument_parser():
         default=False, action="store_true")
     return parser
 
+def cli_argument_parser():
+    """Create the parser for the CLI arguments"""
+    theparser = init_cli_parser(
+        "qc",
+        "Command-Line Interface program for quality control of data files")
+    theparser.add_argument("speciesid", type=int, help="ID of the species.")
+    return add_file_validation_arguments(theparser)
+
 def make_progress_indicator(
         verbose: bool, progress_calc_fn: Callable) -> Union[Callable, None]:
     """Utility to display the progress"""
@@ -106,26 +107,14 @@ def main():
         print(f"The file '{args.filepath}' does not exist.", file=sys.stderr)
         return 1
 
-    if not os.path.exists(args.strainsfile):
-        print(f"The file '{args.strainsfile}' does not exist.", file=sys.stderr)
-        return 2
-
     if not is_file_mime(args.filepath, "text/tab-separated-values"):
         print(
             f"The file '{args.filepath}' MUST be a tab-separated file.",
             file=sys.stderr)
         return 3
 
-    if not is_file_mime(args.strainsfile, "text/csv"):
-        print(
-            f"The file '{args.strainsfile}' MUST be a tab-separated file.",
-            file=sys.stderr)
-        return 4
-
-    if args.verbose:
-        print(f"Parsing the strain names from '{args.strainsfile}'")
-
-    strains = strain_names(os.path.realpath(args.strainsfile))
+    with database_connection(args.databaseuri) as dbconn:
+        strains = strain_names(dbconn, args.speciesid)
 
     filepath = os.path.realpath(args.filepath)
     if args.verbose:
diff --git a/scripts/validate_file.py b/scripts/validate_file.py
index 9f0a561..4b4fc0c 100644
--- a/scripts/validate_file.py
+++ b/scripts/validate_file.py
@@ -11,16 +11,20 @@ from redis.exceptions import ConnectionError # pylint: disable=[redefined-builti
 
 from quality_control.utils import make_progress_calculator
 from quality_control.parsing import FileType, strain_names, collect_errors
-from .qc import cli_argument_parser
 
+from qc_app.db_utils import database_connection
 
-def make_progress_indicator(
-        redis_connection: Redis, job_id: str,
-        progress_calc_fn: Callable) -> Callable:
+from .cli_parser import init_cli_parser
+from .qc import add_file_validation_arguments
+
+
+def make_progress_indicator(redis_connection: Redis,
+                            jobid: str,
+                            progress_calc_fn: Callable) -> Callable:
     """Make function that will compute the progress and update redis"""
     def __indicator__(linenumber, linetext):
         progress = progress_calc_fn(linenumber, linetext)
-        redis_connection.hset(name=job_id, mapping=progress._asdict())
+        redis_connection.hset(name=str(jobid), mapping=progress._asdict())
 
         return progress
 
@@ -32,13 +36,9 @@ def cli_args_valid(args):
         print(f"The file '{args.filepath}' does not exist.", file=sys.stderr)
         return None
 
-    if not os.path.exists(args.strainsfile):
-        print(f"The file '{args.strainsfile}' does not exist.", file=sys.stderr)
-        return None
-
     try:
-        conn = Redis.from_url(args.redisurl) # pylint: disable=[unused-variable]
-    except ConnectionError as conn_err: # pylint: disable=[unused-variable]
+        _conn = Redis.from_url(args.redisuri)
+    except ConnectionError as _conn_err:
         print(traceback.format_exc(), file=sys.stderr)
         return None
 
@@ -46,28 +46,31 @@ def cli_args_valid(args):
 
 def process_cli_arguments():
     """Setup command-line parser"""
-    parser = cli_argument_parser()
-    parser.prog = "worker"
-    parser.add_argument(
-        "redisurl", default="redis:///", help="URL to the redis server")
-    parser.add_argument("job_id", help="The id of the job being processed")
+    parser = init_cli_parser(
+        "validate-file",
+        ("Verify that the file with the expression data conforms to "
+         "expectations."))
+    parser.add_argument("speciesid",
+                        type=int,
+                        help="Species for which the data is to be processed.")
+    parser = add_file_validation_arguments(parser)
 
     return cli_args_valid(parser.parse_args())
 
-def stream_error(redis_conn, job_id, error):
+def stream_error(redis_conn, jobid, error):
     """Update redis with the most current error(s) found"""
     errors = jsonpickle.decode(
-        redis_conn.hget(job_id, key="errors") or jsonpickle.encode(tuple()))
+        redis_conn.hget(str(jobid), key="errors") or jsonpickle.encode(tuple()))
     redis_conn.hset(
-        job_id, key="errors", value=jsonpickle.encode(errors + (error,)))
+        str(jobid), key="errors", value=jsonpickle.encode(errors + (error,)))
 
-def make_user_aborted(redis_conn, job_id):
+def make_user_aborted(redis_conn, jobid):
     """Mkae function that checks whether the user aborted the process"""
     def __aborted__():
         user_aborted = bool(int(
-            redis_conn.hget(name=job_id, key="user_aborted") or "0"))
+            redis_conn.hget(name=str(jobid), key="user_aborted") or "0"))
         if user_aborted:
-            redis_conn.hset(name=job_id, key="status", value="aborted")
+            redis_conn.hset(name=str(jobid), key="status", value="aborted")
 
         return user_aborted
     return __aborted__
@@ -84,36 +87,36 @@ def main():
         print("Quiting due to errors!", file=sys.stderr)
         return 1
 
-    with Redis.from_url(args.redisurl) as redis_conn:
+    with (Redis.from_url(args.redisuri) as redis_conn,
+          database_connection(args.databaseuri) as dbconn):
         progress_calculator = make_progress_calculator(
             get_zipfile_size(args.filepath) if is_zipfile(args.filepath)
             else os.stat(args.filepath).st_size)
         progress_indicator = make_progress_indicator(
-            redis_conn, args.job_id, progress_calculator)
+            redis_conn, args.jobid, progress_calculator)
         count = args.count
         filepath = args.filepath
         filetype = (
             FileType.AVERAGE if args.filetype == "average"
             else FileType.STANDARD_ERROR)
-        strains = strain_names(args.strainsfile)
+        strains = strain_names(dbconn, args.speciesid)
 
+        redis_conn.hset(name=str(args.jobid), key="status", value="Processing")
         redis_conn.hset(
-            name=args.job_id, key="status", value="Processing")
-        redis_conn.hset(
-            name=args.job_id, key="message", value="Collecting errors")
+            name=str(args.jobid), key="message", value="Collecting errors")
 
         error_count = 0
         for error in collect_errors(
                 filepath, filetype, strains, progress_indicator,
-                make_user_aborted(redis_conn, args.job_id)):
-            stream_error(redis_conn, args.job_id, error)
+                make_user_aborted(redis_conn, args.jobid)):
+            stream_error(redis_conn, args.jobid, error)
 
             if count > 0:
                 error_count = error_count + 1
                 if error_count >= count:
                     break
 
-        redis_conn.hset(name=args.job_id, key="status", value="success")
+        redis_conn.hset(name=str(args.jobid), key="status", value="success")
 
     return 0