5 Commits

Author SHA1 Message Date
a4d8de7cc6 Changing CSV argument to --csv or -o
All checks were successful
automlst.cli/pipeline/head This commit looks good
automlst.cli/pipeline/tag This commit looks good
2025-02-19 19:57:15 +00:00
5ef5b6ac08 Updated pyproject.toml to use license text and updated repo
All checks were successful
automlst.cli/pipeline/head This commit looks good
2025-02-19 16:26:59 +00:00
3aa2916324 Updated pipeline to not publish to system repo if it's a tagged version
All checks were successful
automlst.cli/pipeline/head This commit looks good
automlst.cli/pipeline/tag This commit looks good
2025-02-19 16:02:31 +00:00
af9c8c70b8 Stop on fail argument now works
All checks were successful
automlst.cli/pipeline/head This commit looks good
2025-02-19 15:50:18 +00:00
319edf36af Added option to output database and schemas lists to CSV 2025-02-19 15:01:57 +00:00
4 changed files with 42 additions and 9 deletions

7
Jenkinsfile vendored
View File

@@ -32,6 +32,11 @@ pipeline {
stage("publish") { stage("publish") {
parallel { parallel {
stage ("git.reslate.systems") { stage ("git.reslate.systems") {
when {
not {
tag '*.*.*'
}
}
environment { environment {
CREDS = credentials('username-password-rs-git') CREDS = credentials('username-password-rs-git')
} }
@@ -41,7 +46,7 @@ pipeline {
} }
stage ("pypi.org") { stage ("pypi.org") {
when { when {
tag '*.*' tag '*.*.*'
} }
environment { environment {
TOKEN = credentials('pypi.org') TOKEN = credentials('pypi.org')

View File

@@ -6,7 +6,7 @@ build-backend = "setuptools.build_meta"
name = "autoBIGS.cli" name = "autoBIGS.cli"
dynamic = ["version"] dynamic = ["version"]
readme = "README.md" readme = "README.md"
license = {file = "LICENSE"} license = {text = "GPL-3.0-or-later"}
dependencies = [ dependencies = [
"autoBIGS-engine==0.12.*" "autoBIGS-engine==0.12.*"
] ]
@@ -14,8 +14,8 @@ requires-python = ">=3.12"
description = "A CLI tool to rapidly fetch fetch MLST profiles given sequences for various diseases." description = "A CLI tool to rapidly fetch fetch MLST profiles given sequences for various diseases."
[project.urls] [project.urls]
Repository = "https://github.com/RealYHD/autoBIGS.cli" Repository = "https://github.com/Syph-and-VPD-Lab/autoBIGS.cli"
Issues = "https://github.com/RealYHD/autoBIGS.cli/issues" Issues = "https://github.com/Syph-and-VPD-Lab/autoBIGS.cli/issues"
[project.scripts] [project.scripts]

View File

@@ -1,5 +1,7 @@
from argparse import ArgumentParser, Namespace from argparse import ArgumentParser, Namespace
import asyncio import asyncio
import csv
from os import path
from autobigs.engine.analysis.bigsdb import BIGSdbIndex from autobigs.engine.analysis.bigsdb import BIGSdbIndex
def setup_parser(parser: ArgumentParser): def setup_parser(parser: ArgumentParser):
@@ -24,24 +26,50 @@ def setup_parser(parser: ArgumentParser):
help="Lists the known schema IDs for a given BIGSdb sequence definition database name. The name, and then the ID of the schema is given." help="Lists the known schema IDs for a given BIGSdb sequence definition database name. The name, and then the ID of the schema is given."
) )
parser.add_argument(
"--csv", "-o",
dest="csv_output",
required=False,
default=None,
help="Output list as CSV at a given path. A suffix is added depending on the action taken."
)
parser.set_defaults(run=run_asynchronously) parser.set_defaults(run=run_asynchronously)
return parser return parser
async def run(args: Namespace): async def run(args: Namespace):
async with BIGSdbIndex() as bigsdb_index: async with BIGSdbIndex() as bigsdb_index:
if args.list_dbs and len(args.list_bigsdb_schemas) > 0:
print("Cannot specify both database listing and schema listing, please choose one!")
exit(1)
if args.list_dbs: if args.list_dbs:
known_seqdef_dbs = await bigsdb_index.get_known_seqdef_dbs(force=False) known_seqdef_dbs = await bigsdb_index.get_known_seqdef_dbs(force=False)
print("The following are all known BIGS database names (sorted alphabetically):") sorted_seqdef_dbs = [(name, source) for name, source in sorted(known_seqdef_dbs.items())]
print("\n".join(sorted(known_seqdef_dbs.keys()))) print("The following are all known BIGS database names, and their source (sorted alphabetically):")
print("\n".join(["{0}: {1}".format(name, source) for name, source in sorted_seqdef_dbs]))
if args.csv_output:
with open(args.csv_output, "w") as csv_out_handle:
writer = csv.writer(csv_out_handle)
writer.writerow(("BIGSdb Names", "Source"))
writer.writerows(sorted_seqdef_dbs)
print("\nDatabase output written to {0}".format(args.csv_output))
for bigsdb_schema_name in args.list_bigsdb_schemas: for bigsdb_schema_name in args.list_bigsdb_schemas:
schemas = await bigsdb_index.get_schemas_for_seqdefdb(bigsdb_schema_name) schemas = await bigsdb_index.get_schemas_for_seqdefdb(bigsdb_schema_name)
sorted_schemas = [(name, id) for name, id in sorted(schemas.items())]
print("The following are the known schemas for \"{0}\", and their associated IDs:".format(bigsdb_schema_name)) print("The following are the known schemas for \"{0}\", and their associated IDs:".format(bigsdb_schema_name))
for schema_desc, schema_id in schemas.items(): print("\n".join(["{0}: {1}".format(name, id) for name, id in sorted_schemas]))
print(f"{schema_desc}: {schema_id}") if args.csv_output:
with open(args.csv_output, "w") as csv_out_handle:
writer = csv.writer(csv_out_handle)
writer.writerow(("Name", "ID"))
writer.writerows(sorted_schemas)
print("\nSchema list output written to {0}".format(args.csv_output))
if not (args.list_dbs or len(args.list_bigsdb_schemas) > 0): if not (args.list_dbs or len(args.list_bigsdb_schemas) > 0):
print("Nothing to do. Try specifying \"-l\" for a list of known databases, or \"-h\" for more information.") print("Nothing to do. Try specifying \"-l\" for a list of known databases, or \"-h\" for more information.")
exit(1)
def run_asynchronously(args: Namespace): def run_asynchronously(args: Namespace):
asyncio.run(run(args)) asyncio.run(run(args))

View File

@@ -50,7 +50,7 @@ async def run(args: Namespace):
async with BIGSdbIndex() as bigsdb_index: async with BIGSdbIndex() as bigsdb_index:
gen_strings = read_multiple_fastas(args.fastas) gen_strings = read_multiple_fastas(args.fastas)
async with await bigsdb_index.build_profiler_from_seqdefdb(False, args.seqdefdb, args.schema) as mlst_profiler: async with await bigsdb_index.build_profiler_from_seqdefdb(False, args.seqdefdb, args.schema) as mlst_profiler:
mlst_profiles = mlst_profiler.profile_multiple_strings(gen_strings) mlst_profiles = mlst_profiler.profile_multiple_strings(gen_strings, args.stop_on_fail)
failed = await write_mlst_profiles_as_csv(mlst_profiles, args.out) failed = await write_mlst_profiles_as_csv(mlst_profiles, args.out)
if len(failed) > 0: if len(failed) > 0:
print(f"A total of {len(failed)} IDs failed (no profile found):\n{"\n".join(failed)}") print(f"A total of {len(failed)} IDs failed (no profile found):\n{"\n".join(failed)}")