New --file flag to enable search using a file of rsIDs (#7)

.github/workflows/cibuild.yml

@@ -9,7 +9,7 @@ jobs:
     strategy:
       max-parallel: 4
       matrix:
-        python-version: [3.5, 3.6, 3.7, 3.8]
+        python-version: [3.6, 3.7, 3.8, 3.9]
 
     steps:
     - uses: actions/checkout@v1

CHANGELOG.md

@@ -0,0 +1,35 @@
+# Change Log
+All notable changes to this project will be documented in this file.
+This project adheres to [Semantic Versioning](http://semver.org/).
+
+
+## Unreleased
+
+### Added
+- New `--file` flag to enable search using a file of rsIDs (#7)
+
+
+## [0.2] 2020-04-21
+
+### Added
+- Added support for multiple rsIDs in the VCF ID column
+- Added support for rsIDs appearing in multiple records (forbidden by VCF spec but used in some popularpopulation survey data)
+- Configured continuous integration (CI) with GitHub actions
+
+### Changed
+- Changed `rsidx index` so that it now fails if index already exists; provided a `--force` flag to override
+
+
+## [0.1.1] 2019-05-21
+
+Bugfix release with updated file manifest.
+
+
+## [0.1] 2019-05-21
+
+Initial release!
+
+- Command-line entry point: `rsidx`
+- Command-line operations:
+    - `rsidx index`: index a VCF file
+    - `rsidx search`: query a VCF file by rsID

rsidx/cli.py

@@ -37,6 +37,10 @@ def search_subparser(subparsers):
         '-o', '--out', metavar='FILE', help='write output to specified FILE; '
         'default is terminal (stdout)'
     )
+    cli.add_argument(
+        '--file', action='store_true', help='rsIDs are provided in a text file, one per line, '
+        'rather than as command line arguments'
+    )
     cli.add_argument('vcf', help='sorted and indexed VCF file')
     cli.add_argument('idx', help='rsidx index file')
     cli.add_argument('rsid', nargs='+', help='rsID(s) to search')

rsidx/search.py

@@ -55,9 +55,21 @@ def fmt(row):
         yield line
 
 
+def parse_rsids(rsidlist, fromfile):
+    if fromfile is False:
+        return rsidlist
+    rsids = list()
+    for filename in rsidlist:
+        with open(filename, 'r') as fh:
+            for line in fh:
+                rsids.extend(line.strip().split())
+    return rsids
+
+
 def main(args):
+    rsidlist = parse_rsids(args.rsid, args.file)
     conn = sqlite3.connect(args.idx)
     with rsidx.open(args.out, 'w') as out:
-        for line in search(args.rsid, conn, args.vcf, header=args.header):
+        for line in search(rsidlist, conn, args.vcf, header=args.header):
             print(line, end='', file=out)
     conn.close()

rsidx/tests/data/five-rsids.txt

@@ -0,0 +1,3 @@
+rs1472751972
+rs1287502205 rs897983471	rs1172219431
+rs189123651

rsidx/tests/test_search.py

@@ -145,6 +145,22 @@ def test_search_stdout(capsys):
     assert len(outlines) == 5
 
 
+def test_search_with_file(tmp_path):
+    outfile = str(tmp_path / "out.vcf")
+    arglist = [
+        'search', data_file('chr17-sample.vcf.gz'), data_file('chr17-sample.rsidx'),
+        '--file', data_file('five-rsids.txt'), '--out', outfile
+    ]
+    args = rsidx.cli.get_parser().parse_args(arglist)
+    rsidx.search.main(args)
+    with open(outfile, 'r') as fh:
+        positions = list()
+        for line in fh:
+            pos = line.split()[1]
+            positions.append(pos)
+        assert positions == ['132359', '1313935', '1458046', '1521873', '1895904']
+
+
 @pytest.mark.parametrize('doheader,numlines', [
     (False, 1),
     (True, 57 + 1),