use new load_file_as_signatures function more broadly

doc/api-example.md

@@ -422,24 +422,24 @@ checks.)
 Now, save the tree:
 
 ```
->>> filename = tree.save(tempdir + '/test.sbt.json')
+>>> filename = tree.save(tempdir + '/test.sbt.zip')
 
 ```
 
-### Loading and search SBTs
+### Loading and searching SBTs
 
 How do we load the SBT and search it with a DNA sequence,
 from within Python?
 
-The SBT filename is `test.sbt.json`, as above:
+The SBT filename is `test.sbt.zip`, as above:
 ```
->>> SBT_filename = tempdir + '/test.sbt.json'
+>>> SBT_filename = tempdir + '/test.sbt.zip'
 
 ```
 
 and with it we can load the SBT:
 ```
->>> tree = sourmash.load_sbt_index(SBT_filename)
+>>> tree = sourmash.load_file_as_index(SBT_filename)
 
 ```
 
@@ -465,9 +465,7 @@ and create a scaled signature:
 Now do a search --
 
 ```
->>> threshold = 0.1
-
->>> for found_sig, similarity in sourmash.search_sbt_index(tree, query_sig, threshold):
+>>> for similarity, found_sig, filename in tree.search(query_sig, threshold=0.1):
 ...    print(query_sig.name())
 ...    print(found_sig.name())
 ...    print(similarity)

doc/command-line.md

@@ -86,6 +86,12 @@ Finally, there are a number of utility and information commands:
 * `categorize` is an experimental command to categorize many signatures.
 * `watch` is an experimental command to classify a stream of sequencing data.
 
+Please use the command line option `--help` to get more detailed usage
+information for each command.
+
+Note that as of sourmash v3.4, most commands will load signatures from
+indexed databases (the SBT and LCA formats) as well as from signature files.
+
 ### `sourmash compute`
 
 The `compute` subcommand computes and saves signatures for
@@ -118,7 +124,7 @@ Optional arguments:
 ### `sourmash compare`
 
 
-The `compare` subcommand compares one or more signature files
+The `compare` subcommand compares one or more signatures
 (created with `compute`) using estimated [Jaccard index][3] or
 (if signatures are computed with `--track-abundance`) the [angular
 similarity](https://en.wikipedia.org/wiki/Cosine_similarity#Angular_distance_and_similarity).
@@ -142,6 +148,8 @@ Options:
 --ksize -- do the comparisons at this k-mer size.
 --containment -- compute containment instead of similarity.
         C(i, j) = size(i intersection j) / size(i).
+--from-file -- append the list of files in this text file to the input
+        signatures
 ```
 
 **Note:** compare by default produces a symmetric similarity matrix that can be used as an input to clustering. With `--containment`, however, this matrix is no longer symmetric and cannot formally be used for clustering.
@@ -316,6 +324,11 @@ species level assignments would not be reported.
 (This is the approach that Kraken and other lowest common ancestor
 implementations use, we believe.)
 
+Note: you can specify a list of files to load signatures from in a
+text file passed to `sourmash lca classify` with the
+`--query-from-file` flag; these files will be appended to the `--query`
+input.
+
 ### `sourmash lca summarize`
 
 `sourmash lca summarize` produces a Kraken-style summary of the
@@ -416,6 +429,11 @@ genome is present only once; when weighted by abundance, the Bacterial genome
 is only 41.8% of the metagenome content, while the Archaeal genome is
 58.1% of the metagenome content.
 
+Note: you can specify a list of files to load signatures from in a
+text file passed to `sourmash lca summarize` with the
+`--query-from-file` flag; these files will be appended to the `--query`
+input.
+
 ### `sourmash lca gather`
 
 The `sourmash lca gather` command finds all non-overlapping
@@ -466,6 +484,9 @@ genomes (or building off of NCBI taxonomies more generally), please
 see
 [the NCBI lineage repository](https://github.com/dib-lab/2018-ncbi-lineages).
 
+You can use `--from-file` to pass `lca index` a text file containing a
+list of files to index.
+
 ### `sourmash lca rankinfo`
 
 The `sourmash lca rankinfo` command displays k-mer specificity
@@ -508,6 +529,10 @@ such as `search`, `gather`, and `compare`.
 
 Note, you can use `sourmash sig` as shorthand for all of these commands.
 
+Most commands will load signatures automatically from indexed databases
+(SBT and LCA formats) as well as from signature files, and you can load
+signatures from stdin using `-` on the command line.
+
 ### `sourmash signature cat`
 
 Concatenate signature files.

sourmash/__init__.py

@@ -46,3 +46,5 @@
 from . import sig
 from . import cli
 from . import commands
+from .sourmash_args import load_file_as_index
+from .sourmash_args import load_file_as_signatures

sourmash/cli/compare.py

@@ -6,7 +6,8 @@
 def subparser(subparsers):
     subparser = subparsers.add_parser('compare')
     subparser.add_argument(
-        'signatures', nargs='+', help='list of signatures to compare'
+        'signatures', nargs='*', help='list of signatures to compare',
+        default=[]
     )
     subparser.add_argument(
         '-q', '--quiet', action='store_true', help='suppress non-error output'
@@ -30,6 +31,10 @@ def subparser(subparsers):
         '--traverse-directory', action='store_true',
         help='compare all signatures underneath directories'
     )
+    subparser.add_argument(
+        '--from-file',
+        help='a file containing a list of signatures file to compare'
+    )
     subparser.add_argument(
         '-f', '--force', action='store_true',
         help='continue past errors in file loading'

sourmash/cli/gather.py

@@ -51,6 +51,10 @@ def subparser(subparsers):
         '--ignore-abundance',  action='store_true',
         help='do NOT use k-mer abundances if present'
     )
+    subparser.add_argument(
+        '--md5', default=None,
+        help='select the signature with this md5 as query'
+    )
     add_ksize_arg(subparser, 31)
     add_moltype_args(subparser)
 

sourmash/cli/index.py

@@ -37,6 +37,10 @@ def subparser(subparsers):
         'signatures', nargs='+',
         help='signatures to load into SBT'
     )
+    subparser.add_argument(
+        '--from-file',
+        help='a file containing a list of signatures file to load'
+    )
     subparser.add_argument(
         '-q', '--quiet', action='store_true',
         help='suppress non-error output'

sourmash/cli/lca/classify.py

@@ -3,8 +3,12 @@
 
 def subparser(subparsers):
     subparser = subparsers.add_parser('classify')
-    subparser.add_argument('--db', nargs='+', action='append')
-    subparser.add_argument('--query', nargs='+', action='append')
+    subparser.add_argument('--db', nargs='+', action='append',
+                           help='databases to use to classify')
+    subparser.add_argument('--query', nargs='*', default=[], action='append',
+                           help='query signatures to classify')
+    subparser.add_argument('--query-from-file',
+                           help='file containing list of signature files to query')
     subparser.add_argument('--threshold', metavar='T', type=int, default=5)
     subparser.add_argument(
         '-q', '--quiet', action='store_true',

sourmash/cli/lca/index.py

@@ -11,6 +11,10 @@ def subparser(subparsers):
         'signatures', nargs='+',
         help='one or more sourmash signatures'
     )
+    subparser.add_argument(
+        '--from-file',
+        help='a file containing a list of signatures file to load'
+    )
     subparser.add_argument(
         '--scaled', metavar='S', default=10000, type=float
     )

sourmash/cli/lca/summarize.py

@@ -5,8 +5,10 @@ def subparser(subparsers):
     subparser = subparsers.add_parser('summarize')
     subparser.add_argument('--db', nargs='+', action='append',
                            help='one or more LCA databases to use')
-    subparser.add_argument('--query', nargs='+', action='append',
+    subparser.add_argument('--query', nargs='*', default=[], action='append',
                            help='one or more signature files to use as queries')
+    subparser.add_argument('--query-from-file',
+                           help='file containing list of signature files to query')
     subparser.add_argument('--threshold', metavar='T', type=int, default=5,
                            help='minimum number of hashes to require for a match')
     subparser.add_argument(

sourmash/cli/multigather.py

@@ -6,9 +6,13 @@
 def subparser(subparsers):
     subparser = subparsers.add_parser('multigather')
     subparser.add_argument(
-        '--query', nargs='+', action='append',
+        '--query', nargs='*', default=[], action='append',
         help='query signature'
     )
+    subparser.add_argument(
+        '--query-from-file',
+        help='file containing list of signature files to query'
+    )
     subparser.add_argument(
         '--db', nargs='+', action='append',
         help='signatures/SBTs to search',

sourmash/cli/search.py

@@ -53,6 +53,10 @@ def subparser(subparsers):
         '-o', '--output', metavar='FILE',
         help='output CSV containing matches to this file'
     )
+    subparser.add_argument(
+        '--md5', default=None,
+        help='select the signature with this md5 as query'
+    )
     add_ksize_arg(subparser, 31)
     add_moltype_args(subparser)
 

sourmash/cli/sig/export.py

@@ -16,6 +16,10 @@ def subparser(subparsers):
         '-o', '--output', metavar='FILE',
         help='output signature to this file (default stdout)'
     )
+    subparser.add_argument(
+        '--md5', default=None,
+        help='select the signature with this md5 as query'
+    )
     add_ksize_arg(subparser, 31)
     add_moltype_args(subparser)