pathogens: Define workflows in top level key of nextstrain-pathogen.yaml

CHANGES.md

@@ -27,9 +27,10 @@ supported Python version is always bundled with `nextstrain`.
 ## Improvements
 
 * `nextstrain setup <pathogen>` and `nextstrain version --pathogens` now list
-  the available workflows for a pathogen if the pathogen lists the workflows
-  in the top-level `nextstrain-pathogen.yaml` file.
-  ([#461](https://github.com/nextstrain/cli/pull/461))
+  the available workflows (e.g. `ingest`, `phylogenetic`) for a pathogen if the
+  workflows are registered as compatible with `nextstrain run` in the
+  pathogen's `nextstrain-pathogen.yaml` file.
+  ([#461](https://github.com/nextstrain/cli/pull/461), [#472](https://github.com/nextstrain/cli/pull/472))
 
 * Snakemake's storage support downloaded files (stored in `.snakemake/storage/`)
   are now downloaded from AWS Batch builds by default.

doc/changes.md

@@ -31,9 +31,10 @@ supported Python version is always bundled with `nextstrain`.
 ### Improvements
 
 * `nextstrain setup <pathogen>` and `nextstrain version --pathogens` now list
-  the available workflows for a pathogen if the pathogen lists the workflows
-  in the top-level `nextstrain-pathogen.yaml` file.
-  ([#461](https://github.com/nextstrain/cli/pull/461))
+  the available workflows (e.g. `ingest`, `phylogenetic`) for a pathogen if the
+  workflows are registered as compatible with `nextstrain run` in the
+  pathogen's `nextstrain-pathogen.yaml` file.
+  ([#461](https://github.com/nextstrain/cli/pull/461), [#472](https://github.com/nextstrain/cli/pull/472))
 
 * Snakemake's storage support downloaded files (stored in `.snakemake/storage/`)
   are now downloaded from AWS Batch builds by default.

nextstrain/cli/command/run.py

@@ -33,7 +33,7 @@
 from ..errors import UserError
 from ..pathogens import PathogenVersion, UnmanagedPathogen
 from ..runner import aws_batch, docker, singularity
-from ..util import byte_quantity, split_image_name
+from ..util import byte_quantity, split_image_name, warn
 from ..volume import NamedVolume
 from . import build
 
@@ -241,7 +241,21 @@ def run(opts):
         debug(f"Treating {opts.pathogen!r} as unmanaged pathogen directory")
 
     if opts.workflow not in pathogen.registered_workflows():
-        print(f"The {opts.workflow!r} workflow is not registered as a compatible workflow, but trying to run anyways.")
+        warn(cleandoc(f"""
+            The {opts.workflow!r} workflow is not registered by pathogen {opts.pathogen!r}!
+
+            Trying to run it anyways (but it likely won't work)…
+            """))
+        warn()
+
+    elif opts.workflow not in pathogen.compatible_workflows("nextstrain run"):
+        warn(cleandoc(f"""
+            The {opts.workflow!r} workflow is registered by pathogen {opts.pathogen!r}
+            but not marked as compatible with `nextstrain run`!
+
+            Trying to run it anyways (but it likely won't work)…
+            """))
+        warn()
 
     workflow_directory = pathogen.workflow_path(opts.workflow)
 

nextstrain/cli/command/version.py

@@ -68,15 +68,11 @@ def run(opts):
                 print("  " + name)
                 for version in versions.values():
                     is_default = version == defaults.get(name)
-                    print("    " + str(version) + (f"={version.url or ''}" if opts.verbose else ""), "(default)" if is_default else "")
+                    compatible_workflows = version.compatible_workflows("nextstrain run")
+                    print("    " + str(version) + (f"={version.url or ''}" if opts.verbose else "")
+                          + (" (default)" if is_default else "")
+                          + (f" {{{', '.join(compatible_workflows)}}}" if compatible_workflows else ""))
                     if opts.verbose:
                         print("      " + str(version.path))
-
-                    if registered_workflows := version.registered_workflows():
-                        print("      " + "Available workflows:")
-                        for workflow in registered_workflows:
-                            print("        " + workflow)
-                    else:
-                        print("      " + "No workflows listed, please refer to pathogen docs.")
         else:
             print("  (none)")

nextstrain/cli/pathogens.py

@@ -308,21 +308,33 @@ def __init__(self, name_version_url: str, new_setup: bool = False):
 
     def registered_workflows(self) -> Dict[str, Dict]:
         """
-        Parses :attr:`.registration` to return a dict of registered
-        compatible workflows, where the keys are workflow names.
+        Parses :attr:`.registration` to return a dict of registered workflows,
+        where the keys are workflow names.
         """
         if self.registration is None:
             debug("pathogen does not have a registration")
             return {}
 
-        workflows = self.registration.get("compatibility", {}).get("nextstrain run")
+        workflows = self.registration.get("workflows")
         if not isinstance(workflows, dict):
-            debug(f"pathogen registration.compatibility['nextstrain runs'] is not a dict (got a {type(workflows).__name__})")
+            debug(f"pathogen registration.workflows is not a dict (got a {type(workflows).__name__})")
             return {}
 
         return workflows
 
 
+    def compatible_workflows(self, feature: str) -> Dict[str, Dict]:
+        """
+        Filters registered workflows to return a subset of workflows that are
+        compatible with the provided *feature*.
+        """
+        return {
+            name: info
+            for name, info in self.registered_workflows().items()
+            if isinstance(info, dict) and info.get("compatibility", {}).get(feature)
+        }
+
+
     def workflow_path(self, workflow: str) -> Path:
         return self.path / workflow
 
@@ -498,20 +510,13 @@ def test_compatibility() -> SetupTestResult:
             if self.registration is None:
                 return msg + "\n(couldn't read registration)", False
 
-            try:
-                compatibility = self.registration["compatibility"]["nextstrain run"]
-            except (KeyError, IndexError, TypeError):
-                if DEBUGGING:
-                    traceback.print_exc()
-                return msg + "\n(couldn't find 'compatibility: nextstrain run: …' field)", False
-
-            if compatibility:
-                if workflows := self.registered_workflows():
-                    msg += f"\nAvailable workflows: {list(workflows.keys())}"
-                else:
-                    msg += f"\nNo workflows listed, please refer to pathogen docs."
+            if not self.registered_workflows():
+                return msg + "\n(no workflows registered)", False
 
-            return msg, bool(compatibility)
+            if not self.compatible_workflows("nextstrain run"):
+                return msg + "\n(no workflows registered as compatible)", False
+
+            return msg, True
 
         return [
             ('downloaded',
@@ -521,6 +526,9 @@ def test_compatibility() -> SetupTestResult:
                 self.registration_path.is_file()),
 
             test_compatibility(),
+
+            *((f'`nextstrain run` workflow {name!r} exists', self.workflow_path(name).is_dir())
+                for name in self.compatible_workflows("nextstrain run")),
         ]
 
 
@@ -690,6 +698,7 @@ def __init__(self, path: str):
             self.registration = read_pathogen_registration(self.registration_path)
 
     registered_workflows = PathogenVersion.registered_workflows
+    compatible_workflows = PathogenVersion.compatible_workflows
     workflow_path = PathogenVersion.workflow_path
 
     def __str__(self) -> str: