mammoth-cli 2.2.33__tar.gz → 2.2.35__tar.gz

{mammoth_cli-2.2.33 → mammoth_cli-2.2.35}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mammoth-cli
-Version: 2.2.33
+Version: 2.2.35
 Summary: Command-line interface for the Mammoth Analytics platform
 Project-URL: homepage, https://mammoth.io
 Project-URL: repository, https://github.com/EdgeMetric/mammothsdk
@@ -17,7 +17,7 @@ Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: <3.15,>=3.12
 Requires-Dist: jsonschema>=4.20
 Requires-Dist: keyring<26,>=25.7
-Requires-Dist: mammoth-io<0.9,>=0.8.17
+Requires-Dist: mammoth-io<0.9,>=0.8.18
 Requires-Dist: platformdirs<5,>=4.10
 Requires-Dist: pydantic<3,>=2.12.5
 Requires-Dist: pyyaml<7,>=6

{mammoth_cli-2.2.33 → mammoth_cli-2.2.35}/mammoth_cli/__init__.py

@@ -6,7 +6,7 @@ not implement a second HTTP client and does not call private SDK members.
 
 from __future__ import annotations
 
-__version__ = "2.2.33"
+__version__ = "2.2.35"
 
 # The versioned machine output envelope contract.
 SCHEMA_VERSION = 1

{mammoth_cli-2.2.33 → mammoth_cli-2.2.35}/mammoth_cli/commands/dataset.py

@@ -998,15 +998,20 @@ def dataset_create_from_pdf(invocation: Invocation) -> HandlerResult:
 
 
 def dataset_rename(invocation: Invocation) -> HandlerResult:
-    """Rename a dataset. Dataset id is positional; new name comes from ``--input``."""
+    """Rename a dataset. Dataset id is positional; new name comes from ``--input``.
+
+    ``{"unique": true}`` makes the server pick a free name when the requested one is
+    taken; the result's ``name`` is the name applied.
+    """
     project_id = require_project(invocation)
     dataset_id = _require_int_positional(invocation, "dataset id")
     document = invocation.load_input()
     name = _require_field(document, "name")
+    kwargs: dict[str, Any] = {"dataset_id": dataset_id, "name": name, "project_id": project_id}
+    if document.get("unique") is True:
+        kwargs["unique"] = True
     with open_service(invocation) as (service, auth):
-        data = service.call(
-            _symbol(invocation), dataset_id=dataset_id, name=name, project_id=project_id
-        )
+        data = service.call(_symbol(invocation), **kwargs)
     return data, _meta(invocation, auth.workspace_id, project_id)
 
 

{mammoth_cli-2.2.33 → mammoth_cli-2.2.35}/mammoth_cli/services/data_quality.py

@@ -108,6 +108,33 @@ def _variant_spelling_groups(texts: list[str]) -> list[tuple[str, list[str]]]:
     return sorted(groups, key=lambda item: item[0])
 
 
+def _squashed(text: str) -> str:
+    return _WHITESPACE.sub("", _PUNCTUATION.sub("", text))
+
+
+def _spelling_differences(value: str, canonical: str) -> list[str]:
+    """How ``value`` differs from ``canonical``: the part a chat view of it would hide."""
+    if value == canonical:
+        return []
+    found = []
+    if len(value) - len(value.lstrip()) != len(canonical) - len(canonical.lstrip()):
+        found.append("leading space")
+    if len(value) - len(value.rstrip()) != len(canonical) - len(canonical.rstrip()):
+        found.append("trailing space")
+    core, ref = value.strip(), canonical.strip()
+    if _squashed(core) != _squashed(ref):
+        found.append("case differs")
+    if core.lower() != ref.lower():
+        punctuation = _PUNCTUATION.findall(core) != _PUNCTUATION.findall(ref)
+        found.append("punctuation differs" if punctuation else "inner spacing differs")
+    return found
+
+
+def _spelling_label(value: str, canonical: str) -> str:
+    notes = _spelling_differences(value, canonical)
+    return repr(value) + (f" ({', '.join(notes)})" if notes else "")
+
+
 def _most_used_spelling(values: list[str], counts: Counter[str]) -> str:
     """The group's most frequent real spelling (first seen on a tie), trimmed.
 
@@ -131,7 +158,8 @@ def _variant_spellings_warning(
     canonical = {key: _most_used_spelling(values, counts) for key, values in shown}
     mapping = [{"search": sorted(values), "replace": canonical[key]} for key, values in shown]
     examples = "; ".join(
-        "{" + ", ".join(repr(v) for v in sorted(values)) + "}" + f" -> {canonical[key]!r}"
+        "{" + ", ".join(_spelling_label(v, canonical[key]) for v in sorted(values)) + "}"
+        f" -> {canonical[key]!r}"
         for key, values in shown
     )
     detail = (

{mammoth_cli-2.2.33 → mammoth_cli-2.2.35}/pyproject.toml

@@ -1,13 +1,13 @@
 [project]
 name = "mammoth-cli"
-version = "2.2.33"
+version = "2.2.35"
 description = "Command-line interface for the Mammoth Analytics platform"
 authors = [{name = "Mammoth Analytics", email = "support@mammoth.io"}]
 readme = "README.md"
 license = "LicenseRef-Proprietary"
 requires-python = ">=3.12,<3.15"
 dependencies = [
-    "mammoth-io (>=0.8.17,<0.9)",
+    "mammoth-io (>=0.8.18,<0.9)",
     "typer (>=0.27,<0.28)",
     "rich (>=15,<16)",
     "platformdirs (>=4.10,<5)",

{mammoth_cli-2.2.33 → mammoth_cli-2.2.35}/spec/manifests/sdk-methods.yaml

@@ -3811,7 +3811,7 @@ methods:
   reviewed_by: primary
 - sdk_symbol: mammoth.api.datasets.DatasetsAPI.rename
   implementation_origin: mammoth.api.datasets.DatasetsAPI.rename
-  signature: 'rename(self, dataset_id: ''int'', name: ''str'', workspace_id: ''int | None'' = None, project_id: ''int | None'' = None) -> ''dict[str, Any]'''
+  signature: 'rename(self, dataset_id: ''int'', name: ''str'', workspace_id: ''int | None'' = None, project_id: ''int | None'' = None, unique: ''bool'' = False) -> ''dict[str, Any]'''
   openapi_operation_ids: []
   canonical_command: dataset.rename
   alias_of: null