Added restricted_int

New argparse type parameter to enforce positive integers from user input

docs/api/truvari.rst

@@ -190,6 +190,10 @@ restricted_float
 ^^^^^^^^^^^^^^^^
 .. autofunction:: restricted_float
 
+restricted_int
+^^^^^^^^^^^^^^^^
+.. autofunction:: restricted_int
+
 setup_logging
 ^^^^^^^^^^^^^
 .. autofunction:: setup_logging

truvari/__init__.py

@@ -116,6 +116,7 @@
     make_temp_filename,
     ref_ranges,
     restricted_float,
+    restricted_int,
     setup_logging,
     setup_progressbar,
     vcf_ranges,

truvari/annos/bpovl.py

@@ -26,21 +26,21 @@ def parse_args(args):
                         help="Tab-delimited annotation file")
     parser.add_argument("-o", "--output", type=str, required=True,
                         help="Output joblib DataFrame")
-    parser.add_argument("--sizemin", type=int, default=50,
+    parser.add_argument("--sizemin", type=truvari.restricted_int, default=truvari.restricted_int,
                         help="Minimum size of variant to annotate (%(default)s)")
-    parser.add_argument("--spanmax", type=int, default=50000,
+    parser.add_argument("--spanmax", type=truvari.restricted_int, default=50000,
                         help="Maximum span of SVs to annotate (%(default)s)")
     annosg = parser.add_argument_group("Annotation File Arguments")
     annosg.add_argument("-p", "--preset", choices=PRESET_FMTS.keys(), default=None,
                         help=("Annotation format. This option overwrites "
                               "-s, -b, -e, -c and -1 (%(default)s)"))
     annosg.add_argument("-c", "--comment", type=str, default="#",
                         help="Skip lines started with character. (%(default)s)")
-    annosg.add_argument("-s", "--sequence", type=int, default=0,
+    annosg.add_argument("-s", "--sequence", type=truvari.restricted_int, default=0,
                         help="Column of sequence/chromosome name. (%(default)s)")
-    annosg.add_argument("-b", "--begin", type=int, default=1,
+    annosg.add_argument("-b", "--begin", type=truvari.restricted_int, default=1,
                         help="Column of start chromosomal position. (%(default)s)")
-    annosg.add_argument("-e", "--end", type=int, default=2,
+    annosg.add_argument("-e", "--end", type=truvari.restricted_int, default=2,
                         help="Column of end chromosomal position. (%(default)s)")
     # The end column can be the same as the start column. [2]
     annosg.add_argument("-1", "--one-based", action='store_true',

truvari/annos/density.py

@@ -25,7 +25,7 @@ def parse_args(args):
                         help="Output joblib DataFrame")
     parser.add_argument("-m", "--mask", type=str,
                         help="Mask bed file")
-    parser.add_argument("-w", "--windowsize", type=int, default=10000,
+    parser.add_argument("-w", "--windowsize", type=truvari.restricted_int, default=10000,
                         help="Window size (%(default)s)")
     parser.add_argument("-t", "--threshold", type=float, default=3,
                         help="std for identifying 'dense' regions (%(default)s)")

truvari/annos/grm.py

@@ -167,11 +167,11 @@ def parse_args(args):
                         help="Bed file of regions to parse (None)")
     parser.add_argument("-o", "--output", default="results.jl",
                         help="Output dataframe (%(default)s)")
-    parser.add_argument("-k", "--kmersize", default=50, type=int,
+    parser.add_argument("-k", "--kmersize", default=50, type=truvari.restricted_int,
                         help="Size of kmer to map (%(default)s)")
-    parser.add_argument("-m", "--min-size", default=25, type=int,
+    parser.add_argument("-m", "--min-size", default=25, type=truvari.restricted_int,
                         help="Minimum size of variants to map (%(default)s)")
-    parser.add_argument("-t", "--threads", default=os.cpu_count(), type=int,
+    parser.add_argument("-t", "--threads", default=os.cpu_count(), type=truvari.restricted_int,
                         help="Number of threads (%(default)s)")
     parser.add_argument("--debug", action="store_true",
                         help="Verbose logging")

truvari/annos/hompct.py

@@ -19,11 +19,11 @@ def parse_args(args):
                         help="Compressed, indexed VCF to annotate ")
     parser.add_argument("-o", "--output", type=str, default="/dev/stdout",
                         help="Output filename (stdout)")
-    parser.add_argument("-b", "--buffer", type=int, default=5000,
+    parser.add_argument("-b", "--buffer", type=truvari.restricted_int, default=5000,
                         help="Number of base-pairs up/dn-stream to query (%(default)s)")
-    parser.add_argument("-m", "--minanno", type=int, default=50,
+    parser.add_argument("-m", "--minanno", type=truvari.restricted_int, default=50,
                         help="Minimum size of event to annotate (%(default)s)")
-    parser.add_argument("-M", "--maxgt", type=int, default=1,
+    parser.add_argument("-M", "--maxgt", type=truvari.restricted_int, default=1,
                         help="Largest event size to count for genotyping (%(default)s)")
     parser.add_argument("--debug", action="store_true",
                         help="Verbose logging")

truvari/annos/numneigh.py

@@ -29,9 +29,9 @@ def parse_args(args):
                         help="VCF to annotate")
     parser.add_argument("-o", "--output", type=str, default="/dev/stdout",
                         help="Output vcf (stdout)")
-    parser.add_argument("-r", "--refdist", type=int, default=1000,
+    parser.add_argument("-r", "--refdist", type=truvari.restricted_int, default=1000,
                         help="Max reference location distance (%(default)s)")
-    parser.add_argument("-s", "--sizemin", type=int, default=50,
+    parser.add_argument("-s", "--sizemin", type=truvari.restricted_int, default=50,
                         help="Minimum variant size to consider for annotation (%(default)s)")
     parser.add_argument("--passonly", action="store_true", default=False,
                         help="Only count calls with FILTER == PASS")

truvari/annos/remap.py

@@ -150,14 +150,14 @@ def parse_args(args):
                         help="BWA indexed reference")
     parser.add_argument("-o", "--output", default="/dev/stdout",
                         help="Output VCF (%(default)s)")
-    parser.add_argument("-m", "--minlength", default=50, type=int,
+    parser.add_argument("-m", "--minlength", default=50, type=truvari.restricted_int,
                         help="Smallest length of allele to remap (%(default)s)")
     parser.add_argument("-t", "--threshold", type=truvari.restricted_float, default=.8,
                         help="Threshold for pct of allele covered to consider hit (%(default)s)")
-    parser.add_argument("-d", "--dist", type=int, default=10,
+    parser.add_argument("-d", "--dist", type=truvari.restricted_int, default=10,
                         help=("Minimum distance an alignment must be from a DEL's "
                               "position to be considered (%(default)s))"))
-    parser.add_argument("-H", "--hits", type=int, default=0,
+    parser.add_argument("-H", "--hits", type=truvari.restricted_int, default=0,
                         help="Report top hits as chr:start-end.pct (max %(default)s)")
     parser.add_argument("--debug", action="store_true",
                         help="Verbose logging")

truvari/annos/repmask.py

@@ -182,15 +182,15 @@ def parse_args(args):
                         help="Output filename (%(default)s)")
     parser.add_argument("-e", "--executable", type=str, default="RepeatMasker",
                         help="Path to RepeatMasker (%(default)s)")
-    parser.add_argument("-m", "--min-length", type=int, default=50,
+    parser.add_argument("-m", "--min-length", type=truvari.restricted_int, default=50,
                         help="Minimum size of entry to annotate (%(default)s)")
-    parser.add_argument("-M", "--max-length", type=int, default=50000,
+    parser.add_argument("-M", "--max-length", type=truvari.restricted_int, default=50000,
                         help="Maximum size of entry to annotate (%(default)s)")
     parser.add_argument("-t", "--threshold", type=truvari.restricted_float, default=.8,
                         help="Threshold for pct of allele covered (%(default)s)")
     parser.add_argument("-p", "--params", type=str, default=DEFAULTPARAMS,
                         help="Default parameter string to send to RepeatMasker (%(default)s)")
-    parser.add_argument("-T", "--threads", type=int, default=os.cpu_count(),
+    parser.add_argument("-T", "--threads", type=truvari.restricted_int, default=os.cpu_count(),
                         help="Number of threads to use (%(default)s)")
     parser.add_argument("--debug", action="store_true",
                         help="Verbose logging")

truvari/annos/svinfo.py

@@ -18,7 +18,7 @@ def parse_args(args):
                         help="VCF to annotate (stdin)")
     parser.add_argument("-o", "--output", type=str, default="/dev/stdout",
                         help="Output filename (stdout)")
-    parser.add_argument("-m", "--minsize", type=int, default=50,
+    parser.add_argument("-m", "--minsize", type=truvari.restricted_int, default=50,
                         help="Minimum size of entry to annotate (%(default)s)")
     truvari.setup_logging()
     return parser.parse_args(args)

truvari/annos/trf.py

@@ -102,13 +102,13 @@ def parse_args(args):
                         help="Simple repeats bed")
     parser.add_argument("-f", "--reference", type=str, required=True,
                         help="Reference fasta file")
-    parser.add_argument("-m", "--min-length", type=int, default=50,
+    parser.add_argument("-m", "--min-length", type=truvari.restricted_int, default=50,
                         help="Minimum size of entry to annotate (%(default)s)")
-    parser.add_argument("-M", "--max-length", type=int, default=10000,
+    parser.add_argument("-M", "--max-length", type=truvari.restricted_int, default=10000,
                         help="Maximum size of sequence to run through trf (%(default)s)")
-    parser.add_argument("-t", "--threads", type=int, default=multiprocessing.cpu_count(),
+    parser.add_argument("-t", "--threads", type=truvari.restricted_int, default=multiprocessing.cpu_count(),
                         help="Number of threads to use (%(default)s)")
-    parser.add_argument("-C", "--chunk-size", type=int, default=1,
+    parser.add_argument("-C", "--chunk-size", type=truvari.restricted_int, default=1,
                         help="Size (in mbs) of reference chunks for parallelization (%(default)s)")
     parser.add_argument("--debug", action="store_true",
                         help="Verbose logging")

truvari/bench.py

@@ -67,6 +67,9 @@ def __eq__(self, other):
     def __str__(self):
         return f'{self.state} {self.score} ->\n {self.base} {self.comp}'
 
+    def __repr__(self):
+        return f'<truvari.bench.MatchResult ({self.state} {self.score})>'
+
 
 class Matcher():
     """
@@ -80,7 +83,7 @@ class Matcher():
         >>> v = pysam.VariantFile('repo_utils/test_files/input1.vcf.gz')
         >>> one = next(v); two = next(v)
         >>> mat.build_match(one, two)
-        <0 False chr20:66235->chr20:68303>
+        <truvari.bench.MatchResult (False 0.0)>
     """
 
     def __init__(self, params=None, args=None):
@@ -603,11 +606,11 @@ def parse_args(args):
                         help="Turn on progress monitoring")
 
     thresg = parser.add_argument_group("Comparison Threshold Arguments")
-    thresg.add_argument("-r", "--refdist", type=int, default=defaults.refdist,
+    thresg.add_argument("-r", "--refdist", type=truvari.restricted_int, default=defaults.refdist,
                         help="Max reference location distance (%(default)s)")
     thresg.add_argument("-p", "--pctsim", type=truvari.restricted_float, default=defaults.pctsim,
                         help="Min percent allele sequence similarity. Set to 0 to ignore. (%(default)s)")
-    thresg.add_argument("-B", "--minhaplen", type=int, default=defaults.minhaplen,
+    thresg.add_argument("-B", "--minhaplen", type=truvari.restricted_int, default=defaults.minhaplen,
                         help="Minimum haplotype sequence length to create (%(default)s)")
     thresg.add_argument("-P", "--pctsize", type=truvari.restricted_float, default=defaults.pctsize,
                         help="Min pct allele size similarity (minvarsize/maxvarsize) (%(default)s)")
@@ -617,7 +620,7 @@ def parse_args(args):
                         help="Variant types don't need to match to compare (%(default)s)")
     thresg.add_argument("--use-lev", action="store_true",
                         help="Use the Levenshtein distance ratio instead of edlib editDistance ratio (%(default)s)")
-    thresg.add_argument("-C", "--chunksize", type=int, default=defaults.chunksize,
+    thresg.add_argument("-C", "--chunksize", type=truvari.restricted_int, default=defaults.chunksize,
                         help="Max reference distance to compare calls (%(default)s)")
 
     genoty = parser.add_argument_group("Genotype Comparison Arguments")
@@ -629,19 +632,19 @@ def parse_args(args):
                         help="Comparison calls sample to use (first)")
 
     filteg = parser.add_argument_group("Filtering Arguments")
-    filteg.add_argument("-s", "--sizemin", type=int, default=defaults.sizemin,
+    filteg.add_argument("-s", "--sizemin", type=truvari.restricted_int, default=defaults.sizemin,
                         help="Minimum variant size to consider for comparison (%(default)s)")
-    filteg.add_argument("-S", "--sizefilt", type=int, default=defaults.sizefilt,
+    filteg.add_argument("-S", "--sizefilt", type=truvari.restricted_int, default=defaults.sizefilt,
                         help="Minimum variant size to load into IntervalTree (%(default)s)")
-    filteg.add_argument("--sizemax", type=int, default=defaults.sizemax,
+    filteg.add_argument("--sizemax", type=truvari.restricted_int, default=defaults.sizemax,
                         help="Maximum variant size to consider for comparison (%(default)s)")
     filteg.add_argument("--passonly", action="store_true", default=defaults.passonly,
                         help="Only consider calls with FILTER == PASS")
     filteg.add_argument("--no-ref", default=defaults.no_ref, choices=['a', 'b', 'c'],
                         help="Don't include 0/0 or ./. GT calls from all (a), base (b), or comp (c) vcfs (%(default)s)")
     filteg.add_argument("--includebed", type=str, default=None,
                         help="Bed file of regions in the genome to include only calls overlapping")
-    thresg.add_argument("--extend", type=int, default=0,
+    thresg.add_argument("--extend", type=truvari.restricted_int, default=0,
                         help="Distance to allow comp entries outside of includebed regions (%(default)s)")
     filteg.add_argument("--multimatch", action="store_true", default=defaults.multimatch,
                         help=("Allow base calls to match multiple comparison calls, and vice versa. "
@@ -652,7 +655,7 @@ def parse_args(args):
         parser.error("--reference is required when --pctsim is set")
     if args.chunksize < args.refdist:
         parser.error("--chunksize must be >= --refdist")
-    if args.extend > 0 and args.includebed is None:
+    if args.extend and args.includebed is None:
         parser.error("--extend can only be used when --includebed is set")
     return args
 
@@ -797,7 +800,7 @@ def bench_main(cmdargs):
     for call in itertools.chain.from_iterable(map(compare_chunk, chunks)):
         # setting non-matched call variants that are not fully contained in the original regions to None
         # These don't count as FP or TP and don't appear in the output vcf files
-        if args.extend > 0 and call.comp is not None and not call.state and not regions.include(call.comp):
+        if args.extend and call.comp is not None and not call.state and not regions.include(call.comp):
             call.comp = None
         output_writer(call, outputs, args.sizemin)
 

truvari/collapse.py

@@ -247,11 +247,11 @@ def parse_args(args):
 
     # trubench.add_comparison_args(parser)
     thresg = parser.add_argument_group("Comparison Threshold Arguments")
-    thresg.add_argument("-r", "--refdist", type=int, default=500,
+    thresg.add_argument("-r", "--refdist", type=truvari.restricted_int, default=500,
                         help="Max reference location distance (%(default)s)")
     thresg.add_argument("-p", "--pctsim", type=truvari.restricted_float, default=0.95,
                         help="Min percent allele sequence similarity. Set to 0 to ignore. (%(default)s)")
-    thresg.add_argument("-B", "--minhaplen", type=truvari.restricted_float, default=50,
+    thresg.add_argument("-B", "--minhaplen", type=truvari.restricted_int, default=50,
                         help="Minimum haplotype sequence length to create (%(default)s)")
     thresg.add_argument("-P", "--pctsize", type=truvari.restricted_float, default=0.95,
                         help="Min pct allele size similarity (minvarsize/maxvarsize) (%(default)s)")
@@ -270,9 +270,9 @@ def parse_args(args):
                         help=("Comma separated list of FORMAT fields to consolidate into the kept "
                               "entry by taking the first non-null from all neighbors (%(default)s)"))
     filteg = parser.add_argument_group("Filtering Arguments")
-    filteg.add_argument("-s", "--sizemin", type=int, default=50,
+    filteg.add_argument("-s", "--sizemin", type=truvari.restricted_int, default=50,
                         help="Minimum variant size to consider for comparison (%(default)s)")
-    filteg.add_argument("-S", "--sizemax", type=int, default=50000,
+    filteg.add_argument("-S", "--sizemax", type=truvari.restricted_int, default=50000,
                         help="Maximum variant size to consider for comparison (%(default)s)")
     filteg.add_argument("--passonly", action="store_true", default=False,
                         help="Only consider calls with FILTER == PASS")

truvari/divide.py

@@ -22,9 +22,9 @@ def parse_args(args):
                         help="VCF to split")
     parser.add_argument("output", metavar="DIR",
                         help="Output directory to save parts")
-    parser.add_argument("-b", "--buffer", type=int, default=1000,
+    parser.add_argument("-b", "--buffer", type=truvari.restricted_int, default=1000,
                         help="Buffer to make mini-clusters (%(default)s)")
-    parser.add_argument("-m", "--min", type=int, default=100,
+    parser.add_argument("-m", "--min", type=truvari.restricted_int, default=100,
                         help="Minimum number of entries per-vcf (%(default)s)")
     parser.add_argument("--no-compress", action="store_false",
                         help="Don't attempt to compress/index sub-VCFs")

truvari/utils.py

@@ -46,6 +46,29 @@ def restricted_float(x):
             f"{x} not in range (0, 1)")
     return x
 
+def restricted_int(x):
+    """
+    Restrict int to positive. Raises argparse.ArgumentTypeError if int is negative
+    Used with :class:`argparse.ArgumentParser.add_argument` type parameter
+
+    :param `x`: number to check
+    :type `x`: int
+
+    :return: input number
+    :rtype: float
+
+    Example
+        >>> import truvari
+        >>> truvari.restricted_int(5)
+        5
+        >>> truvari.restricted_int(-2)
+        Traceback (most recent call last):
+        argparse.ArgumentTypeError: -2 is < 0
+    """
+    x = int(x)
+    if x < 0:
+        raise argparse.ArgumentTypeError(f"{x} is < 0")
+    return x
 
 def setup_progressbar(size):
     """