informatica-python 1.9.8__py3-none-any.whl → 1.10.0__py3-none-any.whl

informatica_python/generators/mapping_gen.py

@@ -54,6 +54,8 @@ def _expand_mapplet_recursive(mapplet, mapplet_map, prefix, depth=0, max_depth=1
             to_instance=new_to,
             to_field=conn.to_field,
             to_instance_type=conn.to_instance_type,
+            from_instance_group=conn.from_instance_group,
+            to_instance_group=conn.to_instance_group,
         ))
 
     for inst in getattr(mapplet, 'instances', []):
@@ -138,6 +140,8 @@ def _inline_mapplets(mapping, folder):
                     to_instance=first_tx,
                     to_field=conn.to_field,
                     to_instance_type=conn.to_instance_type,
+                    from_instance_group=conn.from_instance_group,
+                    to_instance_group=conn.to_instance_group,
                 ))
             else:
                 rewired_connectors.append(conn)
@@ -167,6 +171,8 @@ def _inline_mapplets(mapping, folder):
                     to_instance=conn.to_instance,
                     to_field=conn.to_field,
                     to_instance_type=conn.to_instance_type,
+                    from_instance_group=conn.from_instance_group,
+                    to_instance_group=conn.to_instance_group,
                 ))
             else:
                 rewired_connectors.append(conn)
@@ -730,7 +736,11 @@ def _generate_transformation(lines, tx, connector_graph, source_dfs, transform_m
     input_conns = connector_graph.get("to", {}).get(tx.name, [])
     input_sources = set()
     for c in input_conns:
-        input_sources.add(c.from_instance)
+        if c.from_instance_group:
+            group_key = f"{c.from_instance}:{c.from_instance_group}"
+            input_sources.add(group_key)
+        else:
+            input_sources.add(c.from_instance)
 
     input_df = None
     for src in input_sources:
@@ -739,7 +749,14 @@ def _generate_transformation(lines, tx, connector_graph, source_dfs, transform_m
             break
     if not input_df:
         for src in input_sources:
-            input_df = f"df_{_safe_name(src)}"
+            base = src.split(":")[0] if ":" in src else src
+            if base in source_dfs:
+                input_df = source_dfs[base]
+                break
+    if not input_df:
+        for src in input_sources:
+            base = src.split(":")[0] if ":" in src else src
+            input_df = f"df_{_safe_name(base)}"
             break
     if not input_df:
         input_df = "df_input"
@@ -1095,9 +1112,24 @@ def _gen_lookup_transform(lines, tx, tx_safe, input_df, source_dfs, connector_gr
 def _gen_router_transform(lines, tx, tx_safe, input_df, source_dfs):
     lines.append(f"    # Router groups:")
     group_conditions = {}
-    for attr in tx.attributes:
-        if "Group Filter Condition" in attr.name:
-            group_conditions[attr.name] = attr.value
+
+    output_groups = [
+        g for g in tx.groups
+        if g.type.upper() not in ("INPUT", "") and "DEFAULT" not in g.type.upper()
+    ]
+    output_groups.sort(key=lambda g: g.order)
+
+    if output_groups:
+        for g in output_groups:
+            if g.expression and g.expression.strip():
+                group_conditions[g.name] = g.expression
+            else:
+                group_conditions[g.name] = ""
+
+    if not group_conditions:
+        for attr in tx.attributes:
+            if "Group Filter Condition" in attr.name:
+                group_conditions[attr.name] = attr.value
 
     remaining_mask_parts = []
     if group_conditions:
@@ -1108,15 +1140,21 @@ def _gen_router_transform(lines, tx, tx_safe, input_df, source_dfs):
                 expr_py = f"pd.Series(True, index={input_df}.index)"
             mask_var = f"_router_mask_{tx_safe}_{i}"
             lines.append(f"    {mask_var} = {expr_py}  # {gname}")
-            lines.append(f"    df_{tx_safe}_group{i} = {input_df}[{mask_var}].copy()")
-            source_dfs[f"{tx.name}_group{i}"] = f"df_{tx_safe}_group{i}"
+            group_df_name = f"df_{tx_safe}_{_safe_name(gname)}"
+            lines.append(f"    {group_df_name} = {input_df}[{mask_var}].copy()")
+            source_dfs[f"{tx.name}:{gname}"] = group_df_name
             remaining_mask_parts.append(f"~{mask_var}")
+
+    default_groups = [g for g in tx.groups if "DEFAULT" in g.type.upper()]
+    default_name = default_groups[0].name if default_groups else "DEFAULT"
+
     if remaining_mask_parts:
         lines.append(f"    _router_default_mask = {' & '.join(remaining_mask_parts)}")
-        lines.append(f"    df_{tx_safe} = {input_df}[_router_default_mask].copy()  # Default group")
+        lines.append(f"    df_{tx_safe} = {input_df}[_router_default_mask].copy()  # Default group ({default_name})")
     else:
-        lines.append(f"    df_{tx_safe} = {input_df}.copy()  # Default group")
+        lines.append(f"    df_{tx_safe} = {input_df}.copy()  # Default group ({default_name})")
     source_dfs[tx.name] = f"df_{tx_safe}"
+    source_dfs[f"{tx.name}:{default_name}"] = f"df_{tx_safe}"
 
 
 def _gen_union_transform(lines, tx, tx_safe, input_sources, source_dfs, data_lib="pandas"):
@@ -1448,6 +1486,11 @@ def _generate_target_write(lines, tgt_name, tgt_def, connector_graph, source_dfs
     to_conns = connector_graph.get("to", {}).get(tgt_name, [])
     input_df = None
     for c in to_conns:
+        if c.from_instance_group:
+            group_key = f"{c.from_instance}:{c.from_instance_group}"
+            if group_key in source_dfs:
+                input_df = source_dfs[group_key]
+                break
         if c.from_instance in source_dfs:
             input_df = source_dfs[c.from_instance]
             break

informatica_python/models.py

@@ -80,6 +80,7 @@ class GroupDef:
     type: str = ""
     description: str = ""
     order: int = 0
+    expression: str = ""
     fields: List[FieldDef] = field(default_factory=list)
 
 
@@ -274,6 +275,8 @@ class ConnectorDef:
     to_field: str
     to_instance: str
     to_instance_type: str
+    from_instance_group: str = ""
+    to_instance_group: str = ""
 
 
 @dataclass

informatica_python/parser.py

@@ -240,6 +240,7 @@ class InformaticaParser:
             type=self._attr(elem, "TYPE"),
             description=self._attr(elem, "DESCRIPTION"),
             order=self._int_attr(elem, "ORDER"),
+            expression=self._attr(elem, "EXPRESSION"),
         )
         for fld in elem.findall("SOURCEFIELD"):
             grp.fields.append(self._parse_source_field(fld))
@@ -580,6 +581,8 @@ class InformaticaParser:
             to_field=self._attr(elem, "TOFIELD"),
             to_instance=self._attr(elem, "TOINSTANCE"),
             to_instance_type=self._attr(elem, "TOINSTANCETYPE"),
+            from_instance_group=self._attr(elem, "FROMINSTANCEGROUP"),
+            to_instance_group=self._attr(elem, "TOINSTANCEGROUP"),
         )
 
     def _parse_instance(self, elem) -> InstanceDef:

{informatica_python-1.9.8.dist-info → informatica_python-1.10.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: informatica-python
-Version: 1.9.8
+Version: 1.10.0
 Summary: Convert Informatica PowerCenter workflow XML to Python/PySpark code
 Author: Nick
 License: MIT
@@ -124,7 +124,7 @@ The code generator produces real, runnable Python for these transformation types
 - **Expression** — Field-level expressions converted to vectorized pandas operations (`df["COL"]` style) with 40+ vectorized function handlers
 - **Filter** — Row filtering with vectorized converted conditions
 - **Joiner** — `pd.merge()` with join type and condition parsing (inner/left/right/outer)
-- **Lookup** — `pd.merge()` lookups with connection-aware DB reads, multiple match policies, default values, `$$PARAM` substitution
+- **Lookup** — `pd.merge()` lookups with connection-aware DB reads, multiple match policies, default values, `$$PARAM` substitution, SQL override support, table caching via `lookup_func()`
 - **Aggregator** — `groupby().agg()` with SUM/COUNT/AVG/MIN/MAX/FIRST/LAST, computed aggregates
 - **Sorter** — `sort_values()` with multi-key ascending/descending per-field direction from SORTDIRECTION attribute
 - **Router** — Multi-group conditional routing with named groups
@@ -196,7 +196,7 @@ Column-level pandas operations instead of row-level iteration. The expression co
 - `REPLACECHR/REPLACESTR` → `.str.replace()`
 - `REG_EXTRACT/REG_REPLACE` → `.str.extract()/.str.replace(regex=True)`
 - `CHR(code)` → `chr(int(code))`
-- `||` concatenation → `+` with `.astype(str)` on non-literals
+- `||` concatenation → `+` with smart coercion: `.fillna('').astype(str)` for Series, `str()` for scalars
 
 **Date/Time:**
 - `TO_DATE(val, fmt)` → `pd.to_datetime()` with Informatica→Python format conversion
@@ -343,10 +343,12 @@ Target field datatypes are mapped to pandas types and generate proper casting co
 - Decimals/Floats: `pd.to_numeric(errors='coerce')`
 - Booleans: `.astype('boolean')`
 
-### Flat File Handling (v1.3+)
+### Flat File Handling (v1.3+, enhanced v1.9.8)
 
 Parses FLATFILE metadata for delimiter, fixed-width, header lines, skip rows, quote/escape chars. Generates `pd.read_fwf()` for fixed-width or enriched `read_file()` for delimited.
 
+**Fixed-width enhancements (v1.9.8):** `OFFSET`, `PHYSICALLENGTH`, and `PHYSICALOFFSET` are parsed from `SOURCEFIELD` attributes. `physical_length` is preferred over `precision` for accurate column width calculations in `pd.read_fwf()`.
+
 ### Mapplet Inlining (v1.3+)
 
 Expands Mapplet instances into prefixed transforms, rewires connectors, and eliminates duplication.
@@ -371,12 +373,17 @@ The generated `helper_functions.py` provides a complete runtime library:
 ### Database Operations
 | Function | Description |
 |----------|-------------|
-| `get_db_connection(config, conn_name)` | Create DB connection (pyodbc/pymssql/sqlalchemy fallback for MSSQL) |
+| `get_db_connection(config, conn_name)` | SQLAlchemy-first DB connection with engine caching and connection pooling; DBAPI fallback for pyodbc/pymssql |
 | `read_from_db(config, query, conn_name)` | Execute SQL query and return DataFrame |
 | `write_to_db(config, df, table, conn_name)` | Write DataFrame to database table via `.to_sql()` |
-| `execute_sql(config, sql, conn_name)` | Execute DDL/DML statement (INSERT, UPDATE, DELETE) |
+| `execute_sql(config, sql, conn_name)` | Execute DDL/DML statement; auto-detects SQLAlchemy vs DBAPI via `dialect` attribute |
 | `write_with_update_strategy(config, df, table, ...)` | Split rows by `_update_strategy` column into INSERT/UPDATE/DELETE/REJECT operations |
 | `call_stored_procedure(config, proc, params, ...)` | Execute stored procedure with input/output parameter mapping (Oracle/MSSQL/generic) |
+| `lookup_func(table, *args)` | Full lookup implementation with table caching, condition parsing, and default value support |
+| `resolve_env(value)` | Resolve `${VAR}` placeholders from environment variables with config fallback |
+| `resolve_builtin_variable(var_name, ...)` | Resolve `$PMMappingName`, `$PMSessionName`, `$PMFolderName`, etc. |
+| `rename_with_duplicates(df, col_map)` | Safe column rename supporting one-source-to-many-target mapping |
+| `_safe_close(conn)` | Safe connection cleanup handling both SQLAlchemy and raw DBAPI connections |
 
 ### File Operations
 | Function | Description |
@@ -407,7 +414,41 @@ The generated `helper_functions.py` provides a complete runtime library:
 
 ## Changelog
 
-### v1.9.3 (Current)
+### v1.10.0 (Current)
+- **Router multi-group output support**: Router transformations now properly handle `<GROUP>` elements with `EXPRESSION` attributes — generates separate filtered DataFrames for each named output group (e.g., `df_rtr_rest_type_per`, `df_rtr_rest_value_per`), not just the DEFAULT group
+- **Connector group routing**: `FROMINSTANCEGROUP` / `TOINSTANCEGROUP` attributes on `CONNECTOR` elements are now parsed and used to wire downstream transforms/targets to the correct Router output group
+- **GroupDef expression field**: `GroupDef` model now stores the `EXPRESSION` attribute from `<GROUP>` XML elements
+- **Backward-compatible Router fallback**: Existing `TABLEATTRIBUTE`-based Router group conditions (older XML format) continue to work — the code checks `<GROUP>` elements first, then falls back to `TABLEATTRIBUTE` entries
+- **223 tests** passing
+
+### v1.9.8
+- **NOT(expr) function-call form**: `NOT(ISNULL(x))` now correctly converts to `~(df["x"].isna())` — handles both `NOT ` (with space) and `NOT(` (without space) forms
+- **AND/OR/NOT as field names fix**: Logical operators no longer mangled into `df["AND"]` / `df["OR"]` — conversion moved before field substitution in both `_vec_recursive` fallback and `_vectorize_simple`
+- **Condition tokenizer word-boundary fix**: `_split_condition_tokens` no longer splits on `OR` inside field names like `DeletedIndicator` — verifies preceding character is a real word boundary
+- **`$PMMappingName` in expressions**: `$PM*` built-in variables in expression context properly convert to `resolve_builtin_variable("PMMappingName")` instead of being mangled to `$df["PMMappingName"]`
+- **TO_CHAR arithmetic parenthesization**: `TO_CHAR(TO_INTEGER(x) - 1)` now produces `(pd.to_numeric(...) - 1).astype(str)` instead of incorrect `- 1.astype(str)` binding
+- **String literal early-return fix**: Expressions like `'PER_' || X || '_suffix'` no longer short-circuit as a single string literal
+- **Fixed-width file enhancements**: `OFFSET`, `PHYSICALLENGTH`, `PHYSICALOFFSET` parsed from SOURCEFIELD XML; `physical_length` preferred over `precision` for `read_fwf` column widths
+- **Smart concat coercion**: Scalar returns (e.g. `resolve_builtin_variable()`, `get_variable()`) use `str()` wrapping; Series use `.fillna('').astype(str)`
+- **700 tests** passing
+
+### v1.9.5 / v1.9.6
+- **`rename_with_duplicates`** helper for one-source-to-many-target column mapping
+- **`resolve_env()`** for `${VAR}` placeholder resolution (env → config fallback)
+- **`resolve_builtin_variable()`** for `$PMMappingName`, `$PMSessionName`, `$PMFolderName`, etc.
+- **SQLAlchemy-first `get_db_connection`**: Engine caching and connection pooling; DBAPI fallback for pyodbc/pymssql
+- **`_safe_close()`**: Safe connection cleanup handling both SQLAlchemy and raw DBAPI connections
+- **Full `lookup_func()` implementation**: Table caching, condition parsing, default value support
+- **Null-safe `||` concatenation**: `.fillna('').astype(str)` prevents "nan" strings in concatenation
+- **`$PM*` variable substitution in SQL Override queries**
+- **`execute_sql` dialect detection**: Uses `dialect` attribute to choose SQLAlchemy `text()` vs DBAPI `cursor.execute()`
+- **678 tests** passing
+
+### v1.9.4
+- Extended expression function coverage and edge-case fixes
+- Improved mapplet and connector handling
+
+### v1.9.3
 - **Smart target write detection**: Bare targets default to `write_to_db()` instead of `write_file()`; file extension allowlist (`.csv`, `.dat`, `.txt`, `.xml`, `.json`, `.parquet`, `.xlsx`, `.xls`, `.tsv`, `.avro`) for file targets; schema-qualified names (`dbo.TABLE`) correctly route to database
 - **DECODE vectorization**: `DECODE(TRUE, cond1, val1, ..., default)` → nested `np.where()` chains; value-matching DECODE; handles IN() conditions and complex boolean nesting
 - **IS_SPACES vectorization**: `IS_SPACES(field)` → `field.str.strip().eq("")`
@@ -495,7 +536,7 @@ The generated `helper_functions.py` provides a complete runtime library:
 cd informatica_python
 pip install -e ".[dev]"
 
-# Run tests (663 tests)
+# Run tests (700 tests)
 pytest tests/ -v
 ```
 

{informatica_python-1.9.8.dist-info → informatica_python-1.10.0.dist-info}/RECORD

@@ -1,13 +1,13 @@
 informatica_python/__init__.py,sha256=JFO8fVMClSWe0SR-CBseX4RaPyyC3rZBdxxjy47ZT5E,337
 informatica_python/cli.py,sha256=gFwg0O99vKM-OLO0HoHA4emd-6qrgjMNqa9T59e4e_s,2905
 informatica_python/converter.py,sha256=xCuWrYzDji0yN72D3QqOgZCVVM2j3k2_CvlGplCWxLU,22779
-informatica_python/models.py,sha256=sZvVzYrEIRAfzV_HduN-qCeOAt5KZ_z7jzNTmPP3Oxs,17371
-informatica_python/parser.py,sha256=RVxoT1j6QTer2RyeG-PCEyKaoZAQhFepRcrRdsEm6OM,45410
+informatica_python/models.py,sha256=lBlxJBVSyW050KAGj8OyUd11Wyfk-MA2XWBT3qEQSK4,17462
+informatica_python/parser.py,sha256=LpX6Cg5jlqqZyLMr_VRUVvNaLdqls4aB-PdGCLbehZo,45603
 informatica_python/generators/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 informatica_python/generators/config_gen.py,sha256=4tqcNKTB06kyGZIiM4yl0q97q_i3zeCHXTjuE1dNFKY,5726
 informatica_python/generators/error_log_gen.py,sha256=2cc0rEcblydHkb9VAMXlrH7WdSQ-CNqAXcwVk3FYZeM,21319
 informatica_python/generators/helper_gen.py,sha256=lC30hyZn6RIkbo4e_6sbqdrCfmZHWaXdr-p0tmtfILc,82376
-informatica_python/generators/mapping_gen.py,sha256=5wPS9t3OLpbo89gYsHMbVqCg9Jgfzmt13IqK4diOS2g,72781
+informatica_python/generators/mapping_gen.py,sha256=eBYJEGWKUPeRrdnWpJRFl6VL9N7qj5ybmKCgG7rFBDI,74554
 informatica_python/generators/sql_gen.py,sha256=O8Y-aJz9EyFJ0DXeuISRt5yKwC3wlp2K3B0BHrmxrXw,4872
 informatica_python/generators/workflow_gen.py,sha256=_uSlBg31ZRMhMlCYk4hWDRBPaBROrepD8_v3QGEWJxE,18089
 informatica_python/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -15,9 +15,9 @@ informatica_python/utils/datatype_map.py,sha256=iLOYg-iBKT4rMecGbrFkTpJj4yqs5S9H
 informatica_python/utils/expression_converter.py,sha256=ynprsvZGvavML3Y8C485GyjaoqQ-k67OESXHShafeTo,48244
 informatica_python/utils/lib_adapters.py,sha256=1ZtuMbgDg9Ukf-OF_EG1L_BeeR-6JQk8Kx3WwMfvNRU,6516
 informatica_python/utils/sql_dialect.py,sha256=_IHJbfu8a3mT_OvHpybgSfZKqz6mwVy5ItTKDRChqnU,5461
-informatica_python-1.9.8.dist-info/licenses/LICENSE,sha256=77RaRDdXgey1D90YZAjXqEQdBxWfvUQqLQX3pC1qjUE,1061
-informatica_python-1.9.8.dist-info/METADATA,sha256=YErpXHS5T-sSTEUwENMiaCWaYhj6xiQALyyLZACrc2g,26097
-informatica_python-1.9.8.dist-info/WHEEL,sha256=PovZm1ExVWmrRefZoXCfejlbKLnQI5SVIf1SWRV4QQI,97
-informatica_python-1.9.8.dist-info/entry_points.txt,sha256=030jjTrx-1oRRQ16HZz52rdcKS8R8_llnymsTUtn_Xc,67
-informatica_python-1.9.8.dist-info/top_level.txt,sha256=Dngg-WNteYi22XAJU2XKAQS8aZ52yM2LYC0tzxrlbVQ,19
-informatica_python-1.9.8.dist-info/RECORD,,
+informatica_python-1.10.0.dist-info/licenses/LICENSE,sha256=77RaRDdXgey1D90YZAjXqEQdBxWfvUQqLQX3pC1qjUE,1061
+informatica_python-1.10.0.dist-info/METADATA,sha256=eL7mk2t5wXyw9J1g6MjSXuUzByXzyX0BxPtXXX_wTAs,30427
+informatica_python-1.10.0.dist-info/WHEEL,sha256=PovZm1ExVWmrRefZoXCfejlbKLnQI5SVIf1SWRV4QQI,97
+informatica_python-1.10.0.dist-info/entry_points.txt,sha256=030jjTrx-1oRRQ16HZz52rdcKS8R8_llnymsTUtn_Xc,67
+informatica_python-1.10.0.dist-info/top_level.txt,sha256=Dngg-WNteYi22XAJU2XKAQS8aZ52yM2LYC0tzxrlbVQ,19
+informatica_python-1.10.0.dist-info/RECORD,,