EXP: skipmer sketching

Cargo.toml

@@ -12,14 +12,15 @@ crate-type = ["cdylib"]
 pyo3 = { version = "0.23.2", features = ["extension-module", "anyhow"] }
 rayon = "1.10.0"
 serde = { version = "1.0.216", features = ["derive"] }
-sourmash = { version = "0.17.2", features = ["branchwater"] }
+#sourmash = { version = "0.17.2", features = ["branchwater"] }
+sourmash = {git = "https://github.com/sourmash-bio/sourmash/", branch = "try-skipmers", features = ["branchwater"]}
 serde_json = "1.0.133"
 niffler = "2.4.0"
 log = "0.4.22"
 env_logger = { version = "0.11.5" }
 simple-error = "0.3.1"
 anyhow = "1.0.94"
-zip = { version = "2.0", default-features = false }
+zip = { version = "=2.0", default-features = false }
 tempfile = "3.14"
 needletail = "0.5.1"
 csv = "1.3.1"

src/python/sourmash_plugin_branchwater/__init__.py

@@ -78,8 +78,8 @@ def __init__(self, p):
             "-m",
             "--moltype",
             default="DNA",
-            choices=["DNA", "protein", "dayhoff", "hp"],
-            help="molecule type (DNA, protein, dayhoff, or hp; default DNA)",
+            choices=["DNA", "protein", "dayhoff", "hp", "skipm1n3", "skipm2n3"],
+            help="molecule type: DNA, protein, dayhoff, hp, or skipmer (skipm1n3 or skipm2n3); default DNA",
         )
         p.add_argument(
             "-c",
@@ -180,8 +180,8 @@ def __init__(self, p):
             "-m",
             "--moltype",
             default="DNA",
-            choices=["DNA", "protein", "dayhoff", "hp"],
-            help="molecule type (DNA, protein, dayhoff, or hp; default DNA)",
+            choices=["DNA", "protein", "dayhoff", "hp", "skipm1n3", "skipm2n3"],
+            help="molecule type: DNA, protein, dayhoff, hp, or skipmer (skipm1n3 or skipm2n3); default DNA",
         )
         p.add_argument(
             "-c",
@@ -257,8 +257,8 @@ def __init__(self, p):
             "-m",
             "--moltype",
             default="DNA",
-            choices=["DNA", "protein", "dayhoff", "hp"],
-            help="molecule type (DNA, protein, dayhoff, or hp; default DNA)",
+            choices=["DNA", "protein", "dayhoff", "hp", "skipm1n3", "skipm2n3"],
+            help="molecule type: DNA, protein, dayhoff, hp, or skipmer (skipm1n3 or skipm2n3); default DNA",
         )
         p.add_argument(
             "-c",
@@ -341,8 +341,8 @@ def __init__(self, p):
             "-m",
             "--moltype",
             default="DNA",
-            choices=["DNA", "protein", "dayhoff", "hp"],
-            help="molecule type (DNA, protein, dayhoff, or hp; default DNA)",
+            choices=["DNA", "protein", "dayhoff", "hp", "skipm1n3", "skipm2n3"],
+            help="molecule type: DNA, protein, dayhoff, hp, or skipmer (skipm1n3 or skipm2n3); default DNA",
         )
         p.add_argument(
             "-c",
@@ -443,8 +443,8 @@ def __init__(self, p):
             "-m",
             "--moltype",
             default="DNA",
-            choices=["DNA", "protein", "dayhoff", "hp"],
-            help="molecule type (DNA, protein, dayhoff, or hp; default DNA)",
+            choices=["DNA", "protein", "dayhoff", "hp", "skipm1n3", "skipm2n3"],
+            help="molecule type: DNA, protein, dayhoff, hp, or skipmer (skipm1n3 or skipm2n3); default DNA",
         )
         p.add_argument(
             "-c",
@@ -530,8 +530,8 @@ def __init__(self, p):
             "-m",
             "--moltype",
             default="DNA",
-            choices=["DNA", "protein", "dayhoff", "hp"],
-            help="molecule type (DNA, protein, dayhoff, or hp; default DNA)",
+            choices=["DNA", "protein", "dayhoff", "hp", "skipm1n3", "skipm2n3"],
+            help="molecule type: DNA, protein, dayhoff, hp, or skipmer (skipm1n3 or skipm2n3); default DNA",
         )
         p.add_argument(
             "-c",
@@ -618,7 +618,7 @@ def main(self, args):
             args.param_string = ["k=31,scaled=1000,dna"]
 
         # Check and append 'dna' if no moltype is found in a param string
-        moltypes = ["dna", "protein", "dayhoff", "hp"]
+        moltypes = ["dna", "protein", "dayhoff", "hp", "skipm1n3", "skipm2n3"]
         updated_param_strings = []
 
         for param in args.param_string:

src/python/tests/sourmash_tst_utils.py

@@ -7,8 +7,7 @@
 import collections
 import pprint
 
-import pkg_resources
-from pkg_resources import Requirement, resource_filename, ResolutionError
+import importlib.metadata
 import traceback
 from io import open  # pylint: disable=redefined-builtin
 from io import StringIO
@@ -61,46 +60,18 @@ def index_siglist(
     return db
 
 
-def scriptpath(scriptname="sourmash"):
-    """Return the path to the scripts, in both dev and install situations."""
-    # note - it doesn't matter what the scriptname is here, as long as
-    # it's some script present in this version of sourmash.
-
-    path = os.path.join(os.path.dirname(__file__), "../")
-    if os.path.exists(os.path.join(path, scriptname)):
-        return path
-
-    path = os.path.join(os.path.dirname(__file__), "../../EGG-INFO/")
-    if os.path.exists(os.path.join(path, scriptname)):
-        return path
-
-    for path in os.environ["PATH"].split(":"):
-        if os.path.exists(os.path.join(path, scriptname)):
-            return path
-
-
 def _runscript(scriptname):
     """Find & run a script with exec (i.e. not via os.system or subprocess)."""
     namespace = {"__name__": "__main__"}
     namespace["sys"] = globals()["sys"]
 
-    try:
-        pkg_resources.load_entry_point("sourmash", "console_scripts", scriptname)()
-        return 0
-    except pkg_resources.ResolutionError:
-        pass
-
-    path = scriptpath()
-
-    scriptfile = os.path.join(path, scriptname)
-    if os.path.isfile(scriptfile):
-        if os.path.isfile(scriptfile):
-            exec(  # pylint: disable=exec-used
-                compile(open(scriptfile).read(), scriptfile, "exec"), namespace
-            )
-            return 0
-
-    return -1
+    entry_points = importlib.metadata.entry_points(
+        group="console_scripts", name="sourmash"
+    )
+    assert len(entry_points) == 1
+    smash_cli = tuple(entry_points)[0].load()
+    smash_cli()
+    return 0
 
 
 ScriptResults = collections.namedtuple("ScriptResults", ["status", "out", "err"])