[MRG] add sum_hashes to sourmash sig describe output.

doc/command-line.md

@@ -989,20 +989,25 @@ Display signature details.
 
 For example,
 ```
-sourmash sig describe tests/test-data/47.fa.sig
+sourmash sig describe tests/test-data/track_abund/47.fa.sig
 ```
 will display:
 
 ```
-signature filename: tests/test-data/47.fa.sig
+signature filename: tests/test-data/track_abund/47.fa.sig
 signature: NC_009665.1 Shewanella baltica OS185, complete genome
-source file: 47.fa
+source file: podar-ref/47.fa
 md5: 09a08691ce52952152f0e866a59f6261
-k=31 molecule=DNA num=0 scaled=1000 seed=42 track_abundance=0
+k=31 molecule=DNA num=0 scaled=1000 seed=42 track_abundance=1
 size: 5177
+sum hashes: 5292
 signature license: CC0
 ```
 
+Here, the `size` is the number of distinct hashes in the sketch, and
+`sum_hashes` is the total number of hashes in the sketch, with abundances.
+When `track_abundance` is 0, `size` is always the same as `sum_hashes`.
+
 ### `sourmash signature fileinfo` - display a summary of the contents of a sourmash collection
 
 Display signature file, database, or collection.

src/sourmash/cli/sig/describe.py

@@ -1,7 +1,7 @@
 """show details of signature"""
 
 from sourmash.cli.utils import (add_moltype_args, add_ksize_arg,
-                                add_picklist_args)
+                                add_picklist_args, add_pattern_args)
 
 
 def subparser(subparsers):
@@ -26,6 +26,7 @@ def subparser(subparsers):
     add_ksize_arg(subparser, 31)
     add_moltype_args(subparser)
     add_picklist_args(subparser)
+    add_pattern_args(subparser)
 
 
 def main(args):

src/sourmash/sig/__main__.py

@@ -205,6 +205,7 @@ def describe(args):
     set_quiet(args.quiet)
     moltype = sourmash_args.calculate_moltype(args)
     picklist = sourmash_args.load_picklist(args)
+    pattern_search = sourmash_args.load_include_exclude_db_patterns(args)
     _extend_signatures_with_from_file(args)
 
     # write CSV?
@@ -214,11 +215,11 @@ def describe(args):
         csv_obj = sourmash_args.FileOutputCSV(args.csv)
         csv_fp = csv_obj.open()
 
-        # CTB: might want to switch to sourmash_args.FileOutputCSV here?
         w = csv.DictWriter(csv_fp,
                            ['signature_file', 'md5', 'ksize', 'moltype',
                             'num', 'scaled', 'n_hashes', 'seed',
-                            'with_abundance', 'name', 'filename', 'license'],
+                            'with_abundance', 'name', 'filename', 'license',
+                            'sum_hashes'],
                            extrasaction='ignore')
         w.writeheader()
 
@@ -230,17 +231,20 @@ def describe(args):
                                                 picklist=picklist,
                                                 progress=progress,
                                                 yield_all_files=args.force,
-                                                force=args.force)
+                                                force=args.force,
+                                                pattern=pattern_search)
 
     for sig, location in loader:
         # extract info, write as appropriate.
+        signature_file = location
         mh = sig.minhash
         ksize = mh.ksize
         moltype = mh.moltype
         scaled = mh.scaled
         num = mh.num
         seed = mh.seed
         n_hashes = len(mh)
+        sum_hashes = sum(mh.hashes.values())
         with_abundance = 0
         if mh.track_abundance:
             with_abundance = 1
@@ -262,6 +266,7 @@ def describe(args):
 md5: {md5}
 k={ksize} molecule={moltype} num={num} scaled={scaled} seed={seed} track_abundance={with_abundance}
 size: {n_hashes}
+sum hashes: {sum_hashes}
 signature license: {license}
 ''', **locals())
 

tests/test_bugs.py

@@ -3,7 +3,7 @@
 @utils.in_tempdir
 def test_bug_803(c):
     # can we do a 'sourmash search' on an LCA database and a query with abundance?
-    query = utils.get_test_data('47.abunds.fa.sig')
+    query = utils.get_test_data('track_abund/47.fa.sig')
     lca_db = utils.get_test_data('lca/47+63.lca.json')
 
     c.run_sourmash('search', query, lca_db, '--ignore-abundance')

tests/test_cmd_signature.py

@@ -2800,7 +2800,7 @@ def test_sig_describe_1_hp(c):
     c.run_sourmash('sig', 'describe', computed_sig)
 
     out = c.last_result.out
-    print(c.last_result)
+    print(c.last_result.out)
 
     # Add final trailing slash for this OS
     testdata_dirname = os.path.dirname(testdata) + os.sep
@@ -2814,6 +2814,7 @@ def test_sig_describe_1_hp(c):
 md5: e45a080101751e044d6df861d3d0f3fd
 k=7 molecule=protein num=500 scaled=0 seed=42 track_abundance=0
 size: 500
+sum hashes: 500
 signature license: CC0
 
 ---
@@ -2823,6 +2824,7 @@ def test_sig_describe_1_hp(c):
 md5: c027e96c3379d38942639219daa24fdc
 k=7 molecule=dayhoff num=500 scaled=0 seed=42 track_abundance=0
 size: 500
+sum hashes: 500
 signature license: CC0
 
 ---
@@ -2841,6 +2843,7 @@ def test_sig_describe_1_hp(c):
 md5: 1136a8a68420bd93683e45cdaf109b80
 k=21 molecule=DNA num=500 scaled=0 seed=42 track_abundance=0
 size: 500
+sum hashes: 500
 signature license: CC0
 
 ---
@@ -2850,6 +2853,7 @@ def test_sig_describe_1_hp(c):
 md5: 4244d1612598af044e799587132f007e
 k=10 molecule=protein num=500 scaled=0 seed=42 track_abundance=0
 size: 500
+sum hashes: 500
 signature license: CC0
 
 ---
@@ -2859,6 +2863,7 @@ def test_sig_describe_1_hp(c):
 md5: 396dcb7c1875f48ca31e0759bec72ee1
 k=10 molecule=dayhoff num=500 scaled=0 seed=42 track_abundance=0
 size: 500
+sum hashes: 500
 signature license: CC0
 
 ---
@@ -2868,6 +2873,7 @@ def test_sig_describe_1_hp(c):
 md5: 4c43878296459783dbd6a4a071ab7e9d
 k=10 molecule=hp num=500 scaled=0 seed=42 track_abundance=0
 size: 500
+sum hashes: 500
 signature license: CC0
 
 ---
@@ -2877,6 +2883,7 @@ def test_sig_describe_1_hp(c):
 md5: 71f7c111c01785e5f38efad45b00a0e1
 k=30 molecule=DNA num=500 scaled=0 seed=42 track_abundance=0
 size: 500
+sum hashes: 500
 signature license: CC0
 
 """.splitlines()
@@ -2982,6 +2989,29 @@ def test_sig_describe_1_zipfile(c):
         assert line.strip() in out
 
 
+def test_sig_describe_1_sig_abund(runtmp):
+    # check output of sig describe on a sketch with abundances
+    c = runtmp
+
+    sigfile = utils.get_test_data('track_abund/47.fa.sig')
+    c.run_sourmash('sig', 'describe', sigfile)
+
+    out = c.last_result.out
+    print(c.last_result.out)
+
+    expected_output = """\
+signature: NC_009665.1 Shewanella baltica OS185, complete genome
+source file: podar-ref/47.fa
+md5: 09a08691ce52952152f0e866a59f6261
+k=31 molecule=DNA num=0 scaled=1000 seed=42 track_abundance=1
+size: 5177
+sum hashes: 5292
+signature license: CC0
+""".splitlines()
+    for line in expected_output:
+        assert line.strip() in out
+
+
 @utils.in_thisdir
 def test_sig_describe_stdin(c):
     sig = utils.get_test_data('prot/protein/GCA_001593925.1_ASM159392v1_protein.faa.gz.sig')
@@ -3045,6 +3075,37 @@ def test_sig_describe_2_csv(runtmp):
         assert n == 2
 
 
+def test_sig_describe_2_csv_abund(runtmp):
+    # output info in CSV spreadsheet, for abund sig
+    c = runtmp
+
+    sig47 = utils.get_test_data('track_abund/47.fa.sig')
+    c.run_sourmash('sig', 'describe', sig47, '--csv', 'out.csv')
+
+    with open(c.output('out.csv'), 'rt') as fp:
+        r = csv.DictReader(fp)
+
+        n = 0
+
+        rows = list(r)
+        assert len(rows) == 1
+        row = rows[0]
+
+        assert row['signature_file'] == sig47
+        assert row['md5'] == "09a08691ce52952152f0e866a59f6261"
+        assert row['ksize'] == "31"
+        assert row['moltype'] == "DNA"
+        assert row['num'] == "0"
+        assert row['scaled'] == "1000"
+        assert row['n_hashes'] == "5177"
+        assert row['seed'] == "42"
+        assert row['with_abundance'] == "1"
+        assert row['name'] == "NC_009665.1 Shewanella baltica OS185, complete genome"
+        assert row['filename'] == "podar-ref/47.fa"
+        assert row['license'] == "CC0"
+        assert row['sum_hashes'] == "5292"
+
+
 def test_sig_describe_2_csv_as_picklist(runtmp):
     # generate an output CSV from describe and then use it as a manifest
     # pickfile
@@ -3074,6 +3135,54 @@ def test_sig_describe_2_csv_as_picklist(runtmp):
         assert line.strip() in out
 
 
+def test_sig_describe_2_include_db_pattern(runtmp):
+    # test sig describe --include-db-pattern
+    c = runtmp
+
+    allzip = utils.get_test_data('prot/all.zip')
+
+    c.run_sourmash('sig', 'describe', allzip,
+                   '--include-db-pattern', 'os185')
+
+    out = c.last_result.out
+    print(c.last_result)
+
+    expected_output = """\
+signature: NC_009665.1 Shewanella baltica OS185, complete genome
+source file: 47.fa
+md5: 09a08691ce52952152f0e866a59f6261
+k=31 molecule=DNA num=0 scaled=1000 seed=42 track_abundance=0
+size: 5177
+signature license: CC0
+""".splitlines()
+    for line in expected_output:
+        assert line.strip() in out
+
+
+def test_sig_describe_2_exclude_db_pattern(runtmp):
+    # test sig describe --exclude-db-pattern
+    c = runtmp
+
+    allzip = utils.get_test_data('prot/all.zip')
+
+    c.run_sourmash('sig', 'describe', allzip, '--dna', '-k', '31',
+                   '--exclude-db-pattern', 'os223')
+
+    out = c.last_result.out
+    print(c.last_result)
+
+    expected_output = """\
+signature: NC_009665.1 Shewanella baltica OS185, complete genome
+source file: 47.fa
+md5: 09a08691ce52952152f0e866a59f6261
+k=31 molecule=DNA num=0 scaled=1000 seed=42 track_abundance=0
+size: 5177
+signature license: CC0
+""".splitlines()
+    for line in expected_output:
+        assert line.strip() in out
+
+
 @utils.in_tempdir
 def test_sig_overlap(c):
     # get overlap details

tests/test_cmd_signature_fileinfo.py

@@ -63,7 +63,7 @@ def test_fileinfo_1_sig_summarize(runtmp):
 
 def test_fileinfo_1_sig_abund(runtmp):
     # get basic info on a signature with abundance
-    sig47 = utils.get_test_data('47.abunds.fa.sig')
+    sig47 = utils.get_test_data('track_abund/47.fa.sig')
 
     shutil.copyfile(sig47, runtmp.output('sig47.sig'))
     runtmp.run_sourmash('sig', 'fileinfo', 'sig47.sig')