mammoth-cli 2.2.49__tar.gz → 2.2.50__tar.gz

{mammoth_cli-2.2.49 → mammoth_cli-2.2.50}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mammoth-cli
-Version: 2.2.49
+Version: 2.2.50
 Summary: Command-line interface for the Mammoth Analytics platform
 Project-URL: homepage, https://mammoth.io
 Project-URL: repository, https://github.com/EdgeMetric/mammothsdk

{mammoth_cli-2.2.49 → mammoth_cli-2.2.50}/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__ = "2.2.49"
+__version__ = "2.2.50"
 
 # The versioned machine output envelope contract.
 SCHEMA_VERSION = 1

{mammoth_cli-2.2.49 → mammoth_cli-2.2.50}/mammoth_cli/commands/view.py

@@ -1547,19 +1547,32 @@ def _relabel_and_check(
     rows = data.get(_ROWS_KEY) if isinstance(data, dict) else None
     if not isinstance(rows, list) or not rows:
         data = _relabel_columns(service, dataset_id, view_id, project_id, data, mapping)
-        return _with_column_warnings(data, types or {}, view_id, dataset_id, read_only=True)
+        return _with_column_warnings(
+            data, types or {}, view_id, dataset_id, read_only=True, project_id=project_id
+        )
     if mapping is None or types is None:
         mapping, types = _column_profile(service, dataset_id, view_id, project_id)
     data = _relabel_columns(service, dataset_id, view_id, project_id, data, mapping)
-    data = _with_column_warnings(data, types, view_id, dataset_id, read_only=True)
-    return _with_duplicates_fact(data, view_id, dataset_id, whole_view)
+    data = _with_column_warnings(
+        data, types, view_id, dataset_id, read_only=True, project_id=project_id
+    )
+    return _with_duplicates_fact(data, view_id, dataset_id, whole_view, project_id=project_id)
 
 
-def _with_duplicates_fact(data: Any, view_id: int, dataset_id: int | None, whole_view: bool) -> Any:
+def _with_duplicates_fact(
+    data: Any,
+    view_id: int,
+    dataset_id: int | None,
+    whole_view: bool,
+    *,
+    project_id: int | None = None,
+) -> Any:
     """Add ``duplicates``: the read's own statement about exact duplicate rows."""
     if not isinstance(data, dict) or not isinstance(data.get(_ROWS_KEY), list):
         return data
-    fact = duplicate_rows_fact(data[_ROWS_KEY], view_id, dataset_id, whole_view=whole_view)
+    fact = duplicate_rows_fact(
+        data[_ROWS_KEY], view_id, dataset_id, whole_view=whole_view, project_id=project_id
+    )
     return {**data, "duplicates": fact} if fact is not None else data
 
 
@@ -1580,6 +1593,7 @@ def _with_column_warnings(
     view_id: int,
     dataset_id: int | None = None,
     read_only: bool = False,
+    project_id: int | None = None,
 ) -> Any:
     """Add ``column_checks`` (always) and ``column_warnings`` (when found).
 
@@ -1590,7 +1604,7 @@ def _with_column_warnings(
     if not isinstance(data, dict) or not isinstance(data.get(_ROWS_KEY, []), list):
         return data
     checks, warnings = _check_columns(
-        data.get(_ROWS_KEY) or [], types, view_id, dataset_id, read_only
+        data.get(_ROWS_KEY) or [], types, view_id, dataset_id, read_only, project_id
     )
     out = {**data, "column_checks": checks}
     return {**out, "column_warnings": warnings} if warnings else out
@@ -1602,6 +1616,7 @@ def _check_columns(
     view_id: int,
     dataset_id: int | None,
     read_only: bool = False,
+    project_id: int | None = None,
 ) -> tuple[dict[str, Any], list[dict[str, Any]]]:
     """Run ``column_warnings`` and describe what was checked (never raises)."""
     checks: dict[str, Any] = {
@@ -1613,7 +1628,7 @@ def _check_columns(
     warnings: list[dict[str, Any]] = []
     if rows and types:
         try:
-            warnings = column_warnings(rows, types, view_id, dataset_id, read_only)
+            warnings = column_warnings(rows, types, view_id, dataset_id, read_only, project_id)
         except Exception as exc:  # noqa: BLE001 -- a presentation aid must not fail the read
             checks["checked"] = []
             checks["error"] = f"{type(exc).__name__}: {exc}"
@@ -4789,7 +4804,7 @@ def upload_preview(
         rows = [row for row in rows or [] if isinstance(row, dict)]
     except Exception as exc:  # noqa: BLE001 -- a preview must never fail the upload
         return {"preview_error": f"{type(exc).__name__}: {exc}"}
-    checks, warnings = _check_columns(rows, types, view_id, dataset_id)
+    checks, warnings = _check_columns(rows, types, view_id, dataset_id, project_id=project_id)
     preview: dict[str, Any] = {
         "view_id": view_id,
         "view_name": record.get("name"),

{mammoth_cli-2.2.49 → mammoth_cli-2.2.50}/mammoth_cli/services/data_quality.py

@@ -65,18 +65,31 @@ def _is_date(text: str) -> bool:
     return False
 
 
-def _convert_hint(view_id: int | None, column: str, to: str) -> str:
+def _project_flag(project_id: int | None) -> str:
+    """`` --project N`` for a fix command, or nothing when the project is not known."""
+    return f" --project {project_id}" if project_id is not None else ""
+
+
+def _convert_hint(view_id: int | None, column: str, to: str, project_id: int | None) -> str:
     target = str(view_id) if view_id is not None else "VIEW_ID"
     spec = json.dumps({"conversions": [{"column": column, "to": to}]})
-    return f"mammoth view transform convert-type {target} --input {shlex.quote(spec)}"
+    return (
+        f"mammoth view transform convert-type {target} --input {shlex.quote(spec)}"
+        f"{_project_flag(project_id)}"
+    )
 
 
-def _bulk_replace_hint(view_id: int | None, column: str, mapping: list[dict[str, Any]]) -> str:
+def _bulk_replace_hint(
+    view_id: int | None, column: str, mapping: list[dict[str, Any]], project_id: int | None
+) -> str:
     target = str(view_id) if view_id is not None else "VIEW_ID"
     spec = json.dumps(
         {"columns": [column], "mapping": mapping, "match_case": True, "match_words": True}
     )
-    return f"mammoth view transform bulk-replace {target} --input {shlex.quote(spec)}"
+    return (
+        f"mammoth view transform bulk-replace {target} --input {shlex.quote(spec)}"
+        f"{_project_flag(project_id)}"
+    )
 
 
 def _spelling_key(text: str) -> str:
@@ -149,6 +162,7 @@ def _variant_spellings_warning(
     texts: list[str],
     view_id: int | None,
     checked: int,
+    project_id: int | None,
 ) -> dict[str, Any] | None:
     groups = _variant_spelling_groups(texts)
     if not groups:
@@ -172,7 +186,7 @@ def _variant_spellings_warning(
         "column": column,
         "issue": "variant_spellings",
         "detail": detail,
-        "fix": _bulk_replace_hint(view_id, column, mapping),
+        "fix": _bulk_replace_hint(view_id, column, mapping, project_id),
         "rows_checked": checked,
     }
 
@@ -206,6 +220,7 @@ def _renamed_label_warning(
     column: str,
     date_column: str,
     view_id: int | None,
+    project_id: int | None,
 ) -> dict[str, Any] | None:
     """A label that stops before a longer label starting with its words begins
     reads as one thing renamed ("Riverside" -> "Riverside Mall"): left apart, its
@@ -240,7 +255,7 @@ def _renamed_label_warning(
             "its figures split across two names and a period comparison shows a drop "
             "and a new entry that are the same thing; confirm, then unify them."
         ),
-        "fix": _bulk_replace_hint(view_id, column, mapping),
+        "fix": _bulk_replace_hint(view_id, column, mapping, project_id),
         "rows_checked": len(rows),
     }
 
@@ -273,6 +288,7 @@ def duplicate_rows_fact(
     dataset_id: int | None,
     *,
     whole_view: bool,
+    project_id: int | None = None,
 ) -> dict[str, Any] | None:
     """The read's positive statement about exact duplicate rows (zero included).
 
@@ -308,7 +324,7 @@ def duplicate_rows_fact(
         spec = json.dumps({"dataset_id": dataset_id})
         fact["table_wide_check"] = (
             f"mammoth view transform discard-duplicates {view_id} "
-            f"--input {shlex.quote(spec)} --dry-run"
+            f"--input {shlex.quote(spec)} --dry-run{_project_flag(project_id)}"
         )
     return fact
 
@@ -317,6 +333,7 @@ def _duplicate_rows_warning(
     rows: list[Mapping[str, Any]],
     view_id: int | None,
     dataset_id: int | None,
+    project_id: int | None,
 ) -> dict[str, Any] | None:
     """Return a table-level warning when the page itself holds exact duplicates.
 
@@ -340,6 +357,7 @@ def _duplicate_rows_warning(
         spec = json.dumps({"dataset_id": dataset_id})
         warning["fix"] = (
             f"mammoth view transform discard-duplicates {view_id} --input {shlex.quote(spec)}"
+            f"{_project_flag(project_id)}"
         )
     return warning
 
@@ -389,11 +407,16 @@ def _blank_values_warning(
     }
 
 
-def _remove_blank_rows_hint(view_id: int, dataset_id: int, column: str) -> str:
+def _remove_blank_rows_hint(
+    view_id: int, dataset_id: int, column: str, project_id: int | None
+) -> str:
     spec = json.dumps(
         {"condition": {"column": column, "operator": "IS_NOT_EMPTY"}, "dataset_id": dataset_id}
     )
-    return f"mammoth view transform filter {view_id} --input {shlex.quote(spec)}"
+    return (
+        f"mammoth view transform filter {view_id} --input {shlex.quote(spec)}"
+        f"{_project_flag(project_id)}"
+    )
 
 
 def column_warnings(
@@ -402,6 +425,7 @@ def column_warnings(
     view_id: int | None = None,
     dataset_id: int | None = None,
     read_only: bool = False,
+    project_id: int | None = None,
 ) -> list[dict[str, Any]]:
     """Return warnings for text columns that hold numbers or dates, and for blanks.
 
@@ -413,6 +437,8 @@ def column_warnings(
             command (a mutation, so it needs the exact parent, not discovery).
         read_only: The rows came from a read-only data read; a ``dates_stored_as_text``
             finding then carries no ``fix``, since a read answers from the text as it is.
+        project_id: The project the rows were read from; each fix command names it
+            with ``--project`` (the saved profile project may differ, or be absent).
 
     Returns:
         One record per finding: ``column``, ``issue``
@@ -428,7 +454,7 @@ def column_warnings(
     checked = len(materialised)
     warnings: list[dict[str, Any]] = []
     figures = _varying_numbers(materialised, column_types)
-    duplicate_warning = _duplicate_rows_warning(materialised, view_id, dataset_id)
+    duplicate_warning = _duplicate_rows_warning(materialised, view_id, dataset_id, project_id)
     if duplicate_warning is not None:
         warnings.append(duplicate_warning)
     for column, col_type in column_types.items():
@@ -466,10 +492,12 @@ def column_warnings(
                     detail += "."
                 finding: dict[str, Any] = {"column": column, "issue": issue, "detail": detail}
                 if not (read_only and kind == "dates"):
-                    finding["fix"] = _convert_hint(view_id, column, to)
+                    finding["fix"] = _convert_hint(view_id, column, to, project_id)
                 warnings.append({**finding, "rows_checked": checked})
                 break
-            variant_warning = _variant_spellings_warning(column, texts, view_id, checked)
+            variant_warning = _variant_spellings_warning(
+                column, texts, view_id, checked, project_id
+            )
             if variant_warning is not None:
                 warnings.append(variant_warning)
             date_column = next(
@@ -477,7 +505,7 @@ def column_warnings(
                 None,
             )
             renamed = (
-                _renamed_label_warning(materialised, column, date_column, view_id)
+                _renamed_label_warning(materialised, column, date_column, view_id, project_id)
                 if date_column is not None
                 else None
             )
@@ -486,6 +514,6 @@ def column_warnings(
         if blanks:
             remove_fix = None
             if figures == [column] and view_id is not None and dataset_id is not None:
-                remove_fix = _remove_blank_rows_hint(view_id, dataset_id, column)
+                remove_fix = _remove_blank_rows_hint(view_id, dataset_id, column, project_id)
             warnings.append(_blank_values_warning(column, blanks, len(values), checked, remove_fix))
     return warnings

{mammoth_cli-2.2.49 → mammoth_cli-2.2.50}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "mammoth-cli"
-version = "2.2.49"
+version = "2.2.50"
 description = "Command-line interface for the Mammoth Analytics platform"
 authors = [{name = "Mammoth Analytics", email = "support@mammoth.io"}]
 readme = "README.md"