fix(workflows): raise catalog error, not raw ValueError, on a malformed catalog URL

src/specify_cli/workflows/catalog.py

@@ -157,16 +157,28 @@ def _validate_catalog_url(self, url: str) -> None:
         """Validate that a catalog URL uses HTTPS (localhost HTTP allowed)."""
         from urllib.parse import urlparse
 
-        parsed = urlparse(url)
-        is_localhost = parsed.hostname in ("localhost", "127.0.0.1", "::1")
+        # A malformed authority (e.g. an unterminated IPv6 bracket
+        # "https://[::1") makes urlparse / hostname access raise ValueError.
+        # This validator's contract is to raise WorkflowValidationError for a
+        # bad URL, so surface that rather than leaking a raw ValueError past the
+        # command handler (which only catches WorkflowValidationError). Mirrors
+        # specify_cli.catalogs (#3435).
+        try:
+            parsed = urlparse(url)
+            hostname = parsed.hostname
+        except ValueError:
+            raise WorkflowValidationError(
+                f"Catalog URL is malformed: {url}"
+            ) from None
+        is_localhost = hostname in ("localhost", "127.0.0.1", "::1")
         if parsed.scheme != "https" and not (
             parsed.scheme == "http" and is_localhost
         ):
             raise WorkflowValidationError(
                 f"Catalog URL must use HTTPS (got {parsed.scheme}://). "
                 "HTTP is only allowed for localhost."
             )
-        if not parsed.hostname:
+        if not hostname:
             raise WorkflowValidationError(
                 "Catalog URL must be a valid URL with a host."
             )
@@ -332,15 +344,26 @@ def _fetch_single_catalog(
         from specify_cli.authentication.http import open_url as _open_url
 
         def _validate_catalog_url(url: str) -> None:
-            parsed = urlparse(url)
-            is_localhost = parsed.hostname in ("localhost", "127.0.0.1", "::1")
+            # A malformed authority (e.g. "https://[::1") makes urlparse /
+            # hostname access raise ValueError; treat it as a refused fetch
+            # rather than leaking a raw ValueError (this also validates the
+            # post-redirect resp.geturl(), so a hostile redirect target cannot
+            # crash the fetch either).
+            try:
+                parsed = urlparse(url)
+                hostname = parsed.hostname
+            except ValueError:
+                raise WorkflowCatalogError(
+                    f"Refusing to fetch catalog from malformed URL: {url}"
+                ) from None
+            is_localhost = hostname in ("localhost", "127.0.0.1", "::1")
             if parsed.scheme != "https" and not (
                 parsed.scheme == "http" and is_localhost
             ):
                 raise WorkflowCatalogError(
                     f"Refusing to fetch catalog from non-HTTPS URL: {url}"
                 )
-            if not parsed.hostname:
+            if not hostname:
                 raise WorkflowCatalogError(
                     f"Refusing to fetch catalog from URL with no hostname: {url}"
                 )
@@ -774,16 +797,28 @@ def _validate_catalog_url(self, url: str) -> None:
         """Validate that a catalog URL uses HTTPS (localhost HTTP allowed)."""
         from urllib.parse import urlparse
 
-        parsed = urlparse(url)
-        is_localhost = parsed.hostname in ("localhost", "127.0.0.1", "::1")
+        # A malformed authority (e.g. an unterminated IPv6 bracket
+        # "https://[::1") makes urlparse / hostname access raise ValueError.
+        # This validator's contract is to raise StepValidationError for a bad
+        # URL, so surface that rather than leaking a raw ValueError past the
+        # command handler (which only catches StepValidationError). Mirrors
+        # specify_cli.catalogs (#3435).
+        try:
+            parsed = urlparse(url)
+            hostname = parsed.hostname
+        except ValueError:
+            raise StepValidationError(
+                f"Catalog URL is malformed: {url}"
+            ) from None
+        is_localhost = hostname in ("localhost", "127.0.0.1", "::1")
         if parsed.scheme != "https" and not (
             parsed.scheme == "http" and is_localhost
         ):
             raise StepValidationError(
                 f"Catalog URL must use HTTPS (got {parsed.scheme}://). "
                 "HTTP is only allowed for localhost."
             )
-        if not parsed.hostname:
+        if not hostname:
             raise StepValidationError(
                 "Catalog URL must be a valid URL with a host."
             )
@@ -949,15 +984,26 @@ def _fetch_single_catalog(
         from specify_cli.authentication.http import open_url as _open_url
 
         def _validate_url(url: str) -> None:
-            parsed = urlparse(url)
-            is_localhost = parsed.hostname in ("localhost", "127.0.0.1", "::1")
+            # A malformed authority (e.g. "https://[::1") makes urlparse /
+            # hostname access raise ValueError; treat it as a refused fetch
+            # rather than leaking a raw ValueError (this also validates the
+            # post-redirect resp.geturl(), so a hostile redirect target cannot
+            # crash the fetch either).
+            try:
+                parsed = urlparse(url)
+                hostname = parsed.hostname
+            except ValueError:
+                raise StepCatalogError(
+                    f"Refusing to fetch catalog from malformed URL: {url}"
+                ) from None
+            is_localhost = hostname in ("localhost", "127.0.0.1", "::1")
             if parsed.scheme != "https" and not (
                 parsed.scheme == "http" and is_localhost
             ):
                 raise StepCatalogError(
                     f"Refusing to fetch catalog from non-HTTPS URL: {url}"
                 )
-            if not parsed.hostname:
+            if not hostname:
                 raise StepCatalogError(
                     f"Refusing to fetch catalog from URL with no hostname: {url}"
                 )

tests/test_workflows.py

@@ -4805,6 +4805,31 @@ def test_validate_url_localhost_http_allowed(self, project_dir):
         # Should not raise
         catalog._validate_catalog_url("http://localhost:8080/catalog.json")
 
+    @pytest.mark.parametrize(
+        "url",
+        [
+            "https://[::1",              # unterminated IPv6 bracket
+            "https://[not-an-ip]/x",     # bracketed non-IP host
+        ],
+    )
+    def test_validate_url_malformed_raises_validation_error(self, project_dir, url):
+        """A malformed authority must raise WorkflowValidationError, not leak a
+        raw ValueError.
+
+        ``urlparse``/``.hostname`` raise ValueError on a malformed IPv6
+        authority. The command handler only catches WorkflowValidationError,
+        so a raw ValueError would surface as an uncaught traceback instead of a
+        clean 'Error:' message + exit 1. Mirrors specify_cli.catalogs (#3435).
+        """
+        from specify_cli.workflows.catalog import (
+            WorkflowCatalog,
+            WorkflowValidationError,
+        )
+
+        catalog = WorkflowCatalog(project_dir)
+        with pytest.raises(WorkflowValidationError, match="malformed"):
+            catalog._validate_catalog_url(url)
+
     def test_add_catalog(self, project_dir):
         from specify_cli.workflows.catalog import WorkflowCatalog
 
@@ -5251,6 +5276,24 @@ def test_validate_url_localhost_http_allowed(self, project_dir):
         # Should not raise
         catalog._validate_catalog_url("http://localhost:8080/step-catalog.json")
 
+    @pytest.mark.parametrize(
+        "url",
+        [
+            "https://[::1",              # unterminated IPv6 bracket
+            "https://[not-an-ip]/x",     # bracketed non-IP host
+        ],
+    )
+    def test_validate_url_malformed_raises_validation_error(self, project_dir, url):
+        """A malformed authority must raise StepValidationError, not leak a raw
+        ValueError past the command handler (which only catches
+        StepValidationError). Mirrors specify_cli.catalogs (#3435).
+        """
+        from specify_cli.workflows.catalog import StepCatalog, StepValidationError
+
+        catalog = StepCatalog(project_dir)
+        with pytest.raises(StepValidationError, match="malformed"):
+            catalog._validate_catalog_url(url)
+
     def test_add_catalog(self, project_dir):
         from specify_cli.workflows.catalog import StepCatalog