model2data 1.1.0__tar.gz → 1.3.0__tar.gz

{model2data-1.1.0/model2data.egg-info → model2data-1.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: model2data
-Version: 1.1.0
+Version: 1.3.0
 Summary: Generate analytics-ready datasets from DBML models
 Author: JB Analytica
 License-Expression: MIT

{model2data-1.1.0 → model2data-1.3.0}/README.md

@@ -39,7 +39,8 @@ access required.
 - **Privacy-safe.** Nothing but a schema definition goes in; nothing but synthetic data comes out.
 - **Realistic, not random.** Column names are matched against ~35 common patterns — `email`,
   `first_name`, `city`, `phone`, `company`, ... — so a column called `email` gets real-looking
-  emails, not `Lorem ipsum` text.
+  emails, not `Lorem ipsum` text. Type a column with any Faker provider (`billing_country state`,
+  `sku ean13`) to pick its generator outright when the name is wrong for the data.
 - **Relationship-preserving.** Foreign keys resolve to real parent rows; tables are generated in
   dependency order.
 - **Deterministic.** Pass `--seed` and the same schema always produces the same data — safe to
@@ -97,8 +98,9 @@ flowchart LR
 
 1. **Parse.** Reads tables, columns, types, and `Ref` relationships from a DBML file.
 2. **Generate.** Produces synthetic values per column — typed generation for known SQL types
-   (int, date, timestamp, ...), name-aware inference for everything else (`email`, `phone`,
-   `city`, ...), foreign keys resolved against already-generated parent rows.
+   (int, date, timestamp, ...), then a Faker provider named as the type (`sku ean13`), then
+   name-aware inference for everything else (`email`, `phone`, `city`, ...), foreign keys
+   resolved against already-generated parent rows.
 3. **Scaffold.** Writes a complete dbt project around that data: CSV seeds, staging models that
    `ref()` those seeds, `not_null`/`unique`/`relationships` tests, `accepted_values` tests for
    DBML `Enum`-typed columns, singular SQL tests for composite primary/unique keys, table and

model2data-1.3.0/model2data/__init__.py

@@ -0,0 +1,12 @@
+"""Model2Data: Generate analytics-ready datasets from DBML models."""
+
+from importlib.metadata import PackageNotFoundError, version
+
+try:
+    # Read the installed distribution's version rather than repeating it here.
+    # The literal that used to live in this file said 0.1.1 for every release up
+    # to and including 1.2.0: nothing reads `__version__`, so nothing caught it
+    # drifting. Deriving it means it cannot drift again.
+    __version__ = version("model2data")
+except PackageNotFoundError:  # pragma: no cover - running from a source tree
+    __version__ = "0.0.0.dev0"

{model2data-1.1.0 → model2data-1.3.0}/model2data/cli.py

@@ -18,6 +18,7 @@ from model2data.generate.core import (
     get_unresolved_composite_keys,
 )
 from model2data.generate.faker import (
+    DEFAULT_LOCALE,
     get_duplicate_unique_columns,
     get_unmapped_columns,
     reset_stats,
@@ -125,6 +126,15 @@ def main(
             "Using the same seed will always produce identical datasets."
         ),
     ),
+    locale: Optional[str] = typer.Option(
+        None,
+        "--locale",
+        help=(
+            f"Faker locale for generated people and addresses "
+            f"(default: {DEFAULT_LOCALE}).\n"
+            "Examples: en_GB, nl_BE, fr_FR, de_DE."
+        ),
+    ),
     name: Optional[str] = typer.Option(
         None,
         "--name",
@@ -214,6 +224,7 @@ def main(
         base_rows=rows,
         seed=seed,
         row_overrides=row_overrides,
+        locale=locale,
     )
 
     # -------------------------

{model2data-1.1.0 → model2data-1.3.0}/model2data/generate/core.py

@@ -10,7 +10,10 @@ from faker import Faker
 
 from model2data.generate.faker import (
     generate_column_values,
+    release_row_pools,
     reset_duplicate_unique_columns,
+    reset_row_pools,
+    set_locale,
 )
 from model2data.generate.relationships import (
     build_fk_lookup,
@@ -18,8 +21,6 @@ from model2data.generate.relationships import (
 )
 from model2data.parse.dbml import TableDef
 
-fake = Faker()
-
 # Tables the most recent generate_data_from_dbml() call found stuck in an
 # unresolved FK cycle (never reached indegree 0 during the topological
 # sort). Exposed out-of-band, mirroring generate.faker's
@@ -66,6 +67,7 @@ def generate_data_from_dbml(
     base_rows: int = 100,
     seed: Optional[int] = None,
     row_overrides: Optional[Mapping[str, int]] = None,
+    locale: Optional[str] = None,
 ) -> dict[str, pd.DataFrame]:
     """
     Generate synthetic datasets from parsed DBML definitions.
@@ -78,9 +80,19 @@ def generate_data_from_dbml(
     present in `row_overrides` fall back to `base_rows`; unknown names are
     ignored.
 
+    `locale` picks the Faker locale every generated person and address is drawn
+    from -- `"nl_BE"`, `"fr_FR"`, `"en_GB"` -- defaulting to `DEFAULT_LOCALE`.
+    It is a per-run setting rather than a per-column one on purpose: a table
+    holding one Belgian and one American address is the incoherence the row
+    pools exist to remove.
+
     This function is deterministic if a seed is provided.
     It performs no filesystem I/O and returns pandas DataFrames.
     """
+    # Locale first, then the seed: switching locale builds a new Faker, and the
+    # seed has to be the last word on the generator that actually runs.
+    set_locale(locale)
+
     if seed is not None:
         random.seed(seed)
         Faker.seed(seed)
@@ -88,6 +100,7 @@ def generate_data_from_dbml(
     reset_cycle_state()
     reset_dedup_state()
     reset_duplicate_unique_columns()
+    reset_row_pools()
 
     # ---------------------------------------------------------
     # Classify references
@@ -193,6 +206,9 @@ def generate_data_from_dbml(
 
         df = _coerce_integer_dtypes(df, table_def)
         generated[table_name] = df
+        # This table is finished: nothing will read its people or addresses
+        # again, and on a million-row table they are worth tens of megabytes.
+        release_row_pools(table_name)
 
     return generated