pydpm_xl 0.2.8__py3-none-any.whl → 0.2.10__py3-none-any.whl

py_dpm/__init__.py

@@ -41,7 +41,7 @@ Available packages:
 - pydpm.api: Main APIs for migration, syntax, and semantic analysis
 """
 
-__version__ = "0.2.8"
+__version__ = "0.2.10"
 __author__ = "MeaningfulData S.L."
 __email__ = "info@meaningfuldata.eu"
 __license__ = "GPL-3.0-or-later"

py_dpm/api/__init__.py

@@ -11,10 +11,7 @@ from py_dpm.api.dpm_xl import (
     SemanticAPI,
     ASTGeneratorAPI,
     OperationScopesAPI,
-    generate_complete_ast,
-    generate_enriched_ast,
-    enrich_ast_with_metadata,
-    parse_with_data_fields,
+    generate_validations_script,
 )
 
 # Import from general DPM API
@@ -40,9 +37,6 @@ __all__ = [
     "SemanticAPI",
     "ASTGeneratorAPI",
     "OperationScopesAPI",
-    # Complete AST functions (backwards compatibility)
-    "generate_complete_ast",
-    "generate_enriched_ast",
-    "enrich_ast_with_metadata",
-    "parse_with_data_fields",
+    # Standalone function
+    "generate_validations_script",
 ]

py_dpm/api/dpm_xl/__init__.py

@@ -9,13 +9,7 @@ from py_dpm.api.dpm_xl.semantic import SemanticAPI
 from py_dpm.api.dpm_xl.ast_generator import ASTGeneratorAPI
 from py_dpm.api.dpm_xl.operation_scopes import OperationScopesAPI
 
-# Backwards-compatible standalone functions (delegate to ASTGeneratorAPI)
-from py_dpm.api.dpm_xl.complete_ast import (
-    generate_complete_ast,
-    generate_enriched_ast,
-    enrich_ast_with_metadata,
-    parse_with_data_fields,
-)
+from py_dpm.api.dpm_xl.complete_ast import generate_validations_script
 
 __all__ = [
     # Class-based APIs
@@ -23,9 +17,6 @@ __all__ = [
     "SemanticAPI",
     "ASTGeneratorAPI",
     "OperationScopesAPI",
-    # Standalone functions (backwards compatibility)
-    "generate_complete_ast",
-    "generate_enriched_ast",
-    "enrich_ast_with_metadata",
-    "parse_with_data_fields",
+    # Standalone function
+    "generate_validations_script",
 ]

py_dpm/api/dpm_xl/ast_generator.py

@@ -32,7 +32,7 @@ class ASTGeneratorAPI:
        - Returns: AST with data fields populated (datapoint IDs, operand references)
        - Use for: AST analysis with complete metadata, matching json_scripts/*.json format
 
-    3. **Enriched AST** (generate_enriched_ast):
+    3. **Validations Script** (generate_validations_script):
        - Requires database connection
        - Extends complete AST with framework structure for execution engines
        - Returns: Engine-ready AST with operations, variables, tables, preconditions sections
@@ -90,7 +90,7 @@ class ASTGeneratorAPI:
 
         **What you DON'T get:**
         - Data fields (datapoint IDs, operand references) - use generate_complete_ast()
-        - Framework structure - use generate_enriched_ast()
+        - Framework structure - use generate_validations_script()
 
         Args:
             expression: DPM-XL expression string
@@ -347,7 +347,7 @@ class ASTGeneratorAPI:
             return [(expressions, "default_code", None)]
         return expressions
 
-    def generate_enriched_ast(
+    def generate_validations_script(
         self,
         expressions: Union[str, List[Tuple[str, str, Optional[str]]]],
         release_code: Optional[str] = None,
@@ -360,9 +360,9 @@ class ASTGeneratorAPI:
         module_version_number: Optional[str] = None,
     ) -> Dict[str, Any]:
         """
-        Generate enriched, engine-ready AST with framework structure (Level 3).
+        Generate validations script with engine-ready AST and framework structure.
 
-        This extends generate_complete_ast() by wrapping the complete AST in an engine-ready
+        This method generates the complete validations script by wrapping ASTs in an engine-ready
         framework structure with operations, variables, tables, and preconditions sections.
         This is the format required by business rule execution engines.
 
@@ -370,7 +370,7 @@ class ASTGeneratorAPI:
         expression/operation/precondition tuples for generating scripts with multiple operations.
 
         **What you get:**
-        - Everything from generate_complete_ast() PLUS:
+        - Complete AST with data fields PLUS:
         - Framework structure: operations, variables, tables, preconditions
         - Module metadata: version, release info, dates
         - Dependency information (including cross-module dependencies)
@@ -428,14 +428,14 @@ class ASTGeneratorAPI:
 
         Example:
             >>> generator = ASTGeneratorAPI(database_path="data.db")
-            >>> # Single expression (backward compatible)
-            >>> result = generator.generate_enriched_ast(
+            >>> # Single expression
+            >>> result = generator.generate_validations_script(
             ...     "{tF_01.00, r0010, c0010}",
             ...     release_code="4.2",
             ... )
             >>>
             >>> # Multiple expressions with operations and preconditions
-            >>> result = generator.generate_enriched_ast(
+            >>> result = generator.generate_validations_script(
             ...     [
             ...         ("{tF_01.00, r0010, c0010} = 0", "v1234_m", None),
             ...         ("{tF_01.00, r0020, c0010} > 0", "v1235_m", "{v_F_44_04}"),
@@ -984,6 +984,7 @@ class ASTGeneratorAPI:
         """
         from py_dpm.dpm.utils import get_engine
         from py_dpm.api.dpm import DataDictionaryAPI
+        from py_dpm.api.dpm_xl.operation_scopes import OperationScopesAPI
 
         # Initialize database connection
         engine = get_engine(database_path=self.database_path, connection_url=self.connection_url)
@@ -1017,6 +1018,12 @@ class ASTGeneratorAPI:
             connection_url=self.connection_url
         )
 
+        # Initialize OperationScopesAPI once for all expressions (performance optimization)
+        scopes_api = OperationScopesAPI(
+            database_path=self.database_path,
+            connection_url=self.connection_url
+        )
+
         # Primary module info will be determined from the first expression or module_code
         primary_module_info = None
         namespace = None
@@ -1035,6 +1042,21 @@ class ASTGeneratorAPI:
                 complete_ast = complete_result["ast"]
                 context = complete_result.get("context") or table_context
 
+                # Get tables with modules for this expression FIRST (reuse scopes_api from outer scope)
+                # This is done before _get_primary_module_info to pass precomputed values
+                tables_with_modules = scopes_api.get_tables_with_metadata_from_expression(
+                    expression=expression,
+                    release_id=release_id
+                )
+
+                # Calculate scope_result once (avoid duplicate calls in other methods)
+                scope_result = scopes_api.calculate_scopes_from_expression(
+                    expression=expression,
+                    release_id=release_id,
+                    read_only=True
+                )
+                all_tables_with_modules.extend(tables_with_modules)
+
                 # Get primary module info from first expression (or use module_code)
                 if primary_module_info is None:
                     primary_module_info = self._get_primary_module_info(
@@ -1042,6 +1064,9 @@ class ASTGeneratorAPI:
                         primary_module_vid=primary_module_vid,
                         release_id=release_id,
                         module_code=module_code,
+                        # Performance optimization: pass precomputed values
+                        tables_with_modules=tables_with_modules,
+                        scopes_api=scopes_api,
                     )
                     namespace = primary_module_info.get("module_uri", "default_module")
 
@@ -1066,18 +1091,6 @@ class ASTGeneratorAPI:
                 # Clean extra fields from data entries
                 self._clean_ast_data_entries(ast_with_coords)
 
-                # Get tables with modules for this expression
-                from py_dpm.api.dpm_xl.operation_scopes import OperationScopesAPI
-                scopes_api = OperationScopesAPI(
-                    database_path=self.database_path,
-                    connection_url=self.connection_url
-                )
-                tables_with_modules = scopes_api.get_tables_with_metadata_from_expression(
-                    expression=expression,
-                    release_id=release_id
-                )
-                all_tables_with_modules.extend(tables_with_modules)
-
                 # Build mapping of table_code -> module_vid
                 # Prefer the module VID that matches the detected primary module
                 table_to_module = {}
@@ -1179,6 +1192,10 @@ class ASTGeneratorAPI:
                     operation_code=operation_code,
                     release_id=release_id,
                     preferred_module_dependencies=preferred_module_dependencies,
+                    # Performance optimization: pass precomputed values to avoid redundant work
+                    tables_with_modules=tables_with_modules,
+                    scopes_api=scopes_api,
+                    scope_result=scope_result,
                 )
 
                 # Merge dependency modules (avoid table duplicates)
@@ -1313,6 +1330,8 @@ class ASTGeneratorAPI:
         primary_module_vid: Optional[int],
         release_id: Optional[int],
         module_code: Optional[str] = None,
+        tables_with_modules: Optional[List[Dict[str, Any]]] = None,
+        scopes_api: Optional[Any] = None,
     ) -> Dict[str, Any]:
         """
         Detect and return metadata for the primary module from the expression.
@@ -1323,6 +1342,10 @@ class ASTGeneratorAPI:
             release_id: Optional release ID for filtering
             module_code: Optional module code (e.g., "FINREP9") - takes precedence over
                 primary_module_vid if provided
+            tables_with_modules: Optional precomputed tables with module metadata
+                (performance optimization to avoid redundant database queries)
+            scopes_api: Optional precomputed OperationScopesAPI instance
+                (performance optimization to reuse database connections)
 
         Returns:
             Dict with module_uri, module_code, module_version, framework_code,
@@ -1341,20 +1364,28 @@ class ASTGeneratorAPI:
             "module_vid": None,
         }
 
+        # Track if we created the scopes_api locally (need to close it)
+        local_scopes_api = False
+
         try:
-            scopes_api = OperationScopesAPI(
-                database_path=self.database_path,
-                connection_url=self.connection_url
-            )
+            # Reuse provided scopes_api or create a new one
+            if scopes_api is None:
+                scopes_api = OperationScopesAPI(
+                    database_path=self.database_path,
+                    connection_url=self.connection_url
+                )
+                local_scopes_api = True
 
-            # Get tables with module metadata from expression
-            tables_with_modules = scopes_api.get_tables_with_metadata_from_expression(
-                expression=expression,
-                release_id=release_id
-            )
+            # Reuse provided tables_with_modules or fetch if not available
+            if tables_with_modules is None:
+                tables_with_modules = scopes_api.get_tables_with_metadata_from_expression(
+                    expression=expression,
+                    release_id=release_id
+                )
 
             if not tables_with_modules:
-                scopes_api.close()
+                if local_scopes_api:
+                    scopes_api.close()
                 return default_info
 
             # Determine primary module
@@ -1408,7 +1439,8 @@ class ASTGeneratorAPI:
                         to_date = module.get("to_reference_date", to_date)
                         break
 
-            scopes_api.close()
+            if local_scopes_api:
+                scopes_api.close()
 
             return {
                 "module_uri": module_uri or "default_module",
@@ -1864,6 +1896,9 @@ class ASTGeneratorAPI:
         operation_code: str,
         release_id: Optional[int] = None,
         preferred_module_dependencies: Optional[List[str]] = None,
+        tables_with_modules: Optional[List[Dict[str, Any]]] = None,
+        scopes_api: Optional[Any] = None,
+        scope_result: Optional[Any] = None,
     ) -> tuple:
         """
         Detect cross-module dependencies for a single expression.
@@ -1879,6 +1914,12 @@ class ASTGeneratorAPI:
             release_id: Optional release ID for filtering
             preferred_module_dependencies: Optional list of module codes to prefer when
                 a table belongs to multiple modules
+            tables_with_modules: Optional precomputed tables with module metadata
+                (performance optimization to avoid redundant database queries)
+            scopes_api: Optional precomputed OperationScopesAPI instance
+                (performance optimization to reuse database connections)
+            scope_result: Optional precomputed scope result from calculate_scopes_from_expression
+                (performance optimization to avoid redundant computation)
 
         Returns:
             Tuple of (dependency_modules, cross_instance_dependencies)
@@ -1889,24 +1930,28 @@ class ASTGeneratorAPI:
         from py_dpm.dpm.queries.explorer_queries import ExplorerQuery
         import logging
 
-        scopes_api = OperationScopesAPI(
-            database_path=self.database_path,
-            connection_url=self.connection_url
-        )
+        # Reuse provided scopes_api or create a new one
+        if scopes_api is None:
+            scopes_api = OperationScopesAPI(
+                database_path=self.database_path,
+                connection_url=self.connection_url
+            )
 
         try:
-            # Get tables with module info (includes module_version)
-            tables_with_modules = scopes_api.get_tables_with_metadata_from_expression(
-                expression=expression,
-                release_id=release_id
-            )
+            # Reuse provided tables_with_modules or fetch if not available
+            if tables_with_modules is None:
+                tables_with_modules = scopes_api.get_tables_with_metadata_from_expression(
+                    expression=expression,
+                    release_id=release_id
+                )
 
-            # Check if cross-module
-            scope_result = scopes_api.calculate_scopes_from_expression(
-                expression=expression,
-                release_id=release_id,
-                read_only=True
-            )
+            # Reuse provided scope_result or compute if not available
+            if scope_result is None:
+                scope_result = scopes_api.calculate_scopes_from_expression(
+                    expression=expression,
+                    release_id=release_id,
+                    read_only=True
+                )
 
             if scope_result.has_error or not scope_result.is_cross_module:
                 return {}, []

py_dpm/api/dpm_xl/complete_ast.py

@@ -1,85 +1,21 @@
 #!/usr/bin/env python3
 """
-Complete AST API - Generate ASTs exactly like the JSON examples
+Validations Script API - Generate engine-ready ASTs for validation frameworks.
 
-This module provides backwards-compatible standalone functions that delegate to ASTGeneratorAPI.
-All AST-related functionality is now consolidated in the ASTGeneratorAPI class.
+This module provides a standalone function that delegates to ASTGeneratorAPI.
 
-For new code, prefer using ASTGeneratorAPI directly:
+For direct class usage:
     from py_dpm.api.dpm_xl import ASTGeneratorAPI
 
     generator = ASTGeneratorAPI(database_path="data.db")
-    result = generator.generate_complete_ast(expression)
+    result = generator.generate_validations_script(expressions)
 """
 
 from typing import Dict, Any, Optional, List, Union, Tuple
 from py_dpm.api.dpm_xl.ast_generator import ASTGeneratorAPI
 
 
-def generate_complete_ast(
-    expression: str,
-    database_path: str = None,
-    connection_url: str = None,
-    release_id: Optional[int] = None,
-):
-    """
-    Generate complete AST with all data fields, exactly like json_scripts examples.
-
-    This function delegates to ASTGeneratorAPI for backwards compatibility.
-
-    Args:
-        expression: DPM-XL expression string
-        database_path: Path to SQLite database file (e.g., "./database.db")
-        connection_url: SQLAlchemy connection URL for PostgreSQL (optional)
-        release_id: Optional release ID to filter database lookups by specific release.
-            If None, uses all available data (release-agnostic).
-
-    Returns:
-        dict with keys:
-            success, ast, context, error, data_populated, semantic_result
-    """
-    generator = ASTGeneratorAPI(
-        database_path=database_path,
-        connection_url=connection_url,
-        enable_semantic_validation=True
-    )
-    return generator.generate_complete_ast(expression, release_id=release_id)
-
-
-# Convenience function with cleaner interface
-def parse_with_data_fields(
-    expression: str,
-    database_path: str = None,
-    connection_url: str = None,
-    release_id: Optional[int] = None,
-):
-    """
-    Simple function to parse expression and get AST with data fields.
-
-    This function delegates to ASTGeneratorAPI for backwards compatibility.
-
-    Args:
-        expression: DPM-XL expression string
-        database_path: Path to SQLite database file
-        connection_url: SQLAlchemy connection URL for PostgreSQL (optional)
-        release_id: Optional release ID to filter database lookups by specific release.
-            If None, uses all available data (release-agnostic).
-
-    Returns:
-        dict: AST dictionary with data fields, or None if failed
-    """
-    result = generate_complete_ast(
-        expression, database_path, connection_url, release_id=release_id
-    )
-    return result["ast"] if result["success"] else None
-
-
-# ============================================================================
-# AST Enrichment Functions - Create engine-ready ASTs
-# ============================================================================
-
-
-def generate_enriched_ast(
+def generate_validations_script(
     expressions: Union[str, List[Tuple[str, str, Optional[str]]]],
     database_path: Optional[str] = None,
     connection_url: Optional[str] = None,
@@ -91,15 +27,15 @@ def generate_enriched_ast(
     preferred_module_dependencies: Optional[List[str]] = None,
 ) -> Dict[str, Any]:
     """
-    Generate enriched, engine-ready AST from DPM-XL expression(s).
+    Generate validations script with engine-ready AST from DPM-XL expression(s).
 
-    This function delegates to ASTGeneratorAPI for backwards compatibility.
+    This function delegates to ASTGeneratorAPI.generate_validations_script().
 
-    Supports both single expressions (for backward compatibility) and multiple
-    expression/operation/precondition tuples for generating scripts with multiple operations.
+    Supports both single expressions and multiple expression/operation/precondition
+    tuples for generating scripts with multiple operations.
 
     Args:
-        expressions: Either a single DPM-XL expression string (backward compatible),
+        expressions: Either a single DPM-XL expression string,
             or a list of tuples: [(expression, operation_code, precondition), ...].
             Each tuple contains:
             - expression (str): The DPM-XL expression (required)
@@ -125,15 +61,15 @@ def generate_enriched_ast(
         }
 
     Example:
-        >>> # Single expression (backward compatible)
-        >>> result = generate_enriched_ast(
+        >>> # Single expression
+        >>> result = generate_validations_script(
         ...     "{tF_01.00, r0010, c0010}",
         ...     database_path="data.db",
         ...     release_code="4.2",
         ... )
         >>>
         >>> # Multiple expressions
-        >>> result = generate_enriched_ast(
+        >>> result = generate_validations_script(
         ...     [
         ...         ("{tF_01.00, r0010, c0010} = 0", "v1234_m", None),
         ...         ("{tF_01.00, r0020, c0010} > 0", "v1235_m", "{v_F_44_04}"),
@@ -148,7 +84,7 @@ def generate_enriched_ast(
         connection_url=connection_url,
         enable_semantic_validation=True
     )
-    return generator.generate_enriched_ast(
+    return generator.generate_validations_script(
         expressions=expressions,
         release_code=release_code,
         table_context=table_context,
@@ -157,52 +93,3 @@ def generate_enriched_ast(
         module_code=module_code,
         preferred_module_dependencies=preferred_module_dependencies,
     )
-
-
-def enrich_ast_with_metadata(
-    ast_dict: Dict[str, Any],
-    expression: str,
-    context: Optional[Dict[str, Any]],
-    database_path: Optional[str] = None,
-    connection_url: Optional[str] = None,
-    release_code: Optional[str] = None,
-    operation_code: Optional[str] = None,
-    precondition: Optional[str] = None,
-    release_id: Optional[int] = None,
-    primary_module_vid: Optional[int] = None,
-) -> Dict[str, Any]:
-    """
-    Add framework structure (operations, variables, tables, preconditions) to complete AST.
-
-    This function delegates to ASTGeneratorAPI for backwards compatibility.
-
-    Args:
-        ast_dict: Complete AST dictionary (from generate_complete_ast)
-        expression: Original DPM-XL expression
-        context: Context dict with table, rows, columns, sheets, default, interval
-        database_path: Path to SQLite database
-        connection_url: PostgreSQL connection URL (takes precedence)
-        release_code: DPM release code (e.g., "4.2")
-        operation_code: Operation code (defaults to "default_code")
-        precondition: Precondition variable reference (e.g., {v_F_44_04})
-        release_id: Optional release ID to filter database lookups
-        primary_module_vid: Optional module VID of the module being exported
-
-    Returns:
-        dict: Engine-ready AST with framework structure
-    """
-    generator = ASTGeneratorAPI(
-        database_path=database_path,
-        connection_url=connection_url,
-        enable_semantic_validation=True
-    )
-    return generator._enrich_ast_with_metadata(
-        ast_dict=ast_dict,
-        expression=expression,
-        context=context,
-        release_code=release_code,
-        operation_code=operation_code,
-        precondition=precondition,
-        release_id=release_id,
-        primary_module_vid=primary_module_vid,
-    )

py_dpm/dpm/migration.py

@@ -103,14 +103,16 @@ def _extract_with_pyodbc(access_file):
         import pyodbc
     except ImportError:
         raise Exception("pyodbc not available")
-    
+
+    import decimal
+
     # Try different Access drivers
     drivers_to_try = [
         r'DRIVER={Microsoft Access Driver (*.mdb, *.accdb)};',
         r'DRIVER={Microsoft Access Driver (*.mdb)};',
         r'DRIVER={MDBTools};'
     ]
-    
+
     conn = None
     for driver in drivers_to_try:
         try:
@@ -120,10 +122,10 @@ def _extract_with_pyodbc(access_file):
             break
         except pyodbc.Error:
             continue
-    
+
     if not conn:
         raise Exception("No suitable ODBC driver found for Access database")
-    
+
     try:
         # Get all table names
         cursor = conn.cursor()
@@ -132,63 +134,56 @@ def _extract_with_pyodbc(access_file):
             table_name = table_info.table_name
             if not table_name.startswith('MSys'):  # Skip system tables
                 tables.append(table_name)
-        
+
         data = {}
-        STRING_COLUMNS = ["row", "column", "sheet"]
-        
+
         # Extract each table
         for table_name in tables:
             print(table_name)
             try:
                 cursor.execute(f"SELECT * FROM [{table_name}]")
-                columns = [column[0] for column in cursor.description]
+
+                # Get column metadata from cursor.description
+                # Each entry is: (name, type_code, display_size, internal_size, precision, scale, null_ok)
+                # type_code is a Python type (str, int, float, decimal.Decimal, etc.)
+                column_info = []
+                for col_desc in cursor.description:
+                    col_name = col_desc[0]
+                    col_type = col_desc[1]  # Python type from ODBC metadata
+                    column_info.append((col_name, col_type))
+
+                columns = [info[0] for info in column_info]
                 rows = cursor.fetchall()
-                
+
                 if rows:
                     # Convert to DataFrame
                     df = pd.DataFrame([list(row) for row in rows], columns=columns)
 
-                    # Apply same dtype conversion logic as mdb-tools method
-                    # Start with all strings, but preserve None as actual None (not string 'None')
-                    for col in df.columns:
-                        df[col] = df[col].astype(object)
-                        mask = df[col].notna()
-                        df.loc[mask, col] = df.loc[mask, col].astype(str)
-
-                    numeric_columns = []
-                    for column in df.columns:
-                        if column in STRING_COLUMNS:
-                            continue
-                        try:
-                            # Convert to numeric and check if any values start with '0' (except '0' itself)
-                            # Only check string values for leading zeros
-                            string_mask = df[column].astype(str).str.match(r'^0\d+', na=False)
-                            has_leading_zeros = string_mask.any()
-
-                            # Test numeric conversion
-                            numeric_series = pd.to_numeric(df[column], errors='coerce')
-
-                            if not has_leading_zeros and not numeric_series.isna().all():
-                                numeric_columns.append(column)
-                        except Exception:
-                            continue
-
-                    # Convert only the identified numeric columns
-                    for col in numeric_columns:
-                        try:
-                            df[col] = pd.to_numeric(df[col], errors='coerce')
-                        except (ValueError, TypeError):
-                            # Keep as string if conversion fails
-                            pass
-                    
+                    # Use the actual column types from Access schema metadata
+                    # instead of inferring from data values (fixes Windows vs Linux inconsistency)
+                    numeric_types = (int, float, decimal.Decimal)
+
+                    for col_name, col_type in column_info:
+                        if col_type in numeric_types:
+                            # Column is defined as numeric in Access schema - convert to numeric
+                            try:
+                                df[col_name] = pd.to_numeric(df[col_name], errors='coerce')
+                            except (ValueError, TypeError):
+                                pass
+                        else:
+                            # Column is defined as text/other in Access schema - keep as string
+                            df[col_name] = df[col_name].astype(object)
+                            mask = df[col_name].notna()
+                            df.loc[mask, col_name] = df.loc[mask, col_name].astype(str)
+
                     data[table_name] = df
-                
+
             except Exception as e:
                 print(f"Error processing table {table_name}: {e}", file=sys.stderr)
                 continue
-        
+
         return data
-        
+
     finally:
         conn.close()
 

py_dpm/dpm/models.py

@@ -1,5 +1,5 @@
 from datetime import datetime
-from typing import List
+from typing import Dict, Hashable, List, Tuple
 from sqlalchemy import (
     Boolean,
     Column,
@@ -36,6 +36,11 @@ class SerializationMixin:
 Base = declarative_base(cls=SerializationMixin)
 
 
+def _get_engine_cache_key(session) -> Hashable:
+    bind = session.get_bind()
+    return getattr(bind, "url", repr(bind))
+
+
 def _read_sql_with_connection(sql, session):
     """
     Execute pd.read_sql with proper connection handling to avoid pandas warnings.
@@ -2319,6 +2324,11 @@ class ViewDatapoints(Base):
     context_id = Column(Integer)
     variable_vid = Column(String)
 
+    _TABLE_DATA_CACHE: Dict[
+        Tuple[Hashable, str, Tuple[str, ...] | None, Tuple[str, ...] | None, Tuple[str, ...] | None, int | None],
+        pd.DataFrame,
+    ] = {}
+
     @classmethod
     def _create_base_query_with_aliases(cls, session):
         """
@@ -2552,7 +2562,16 @@ class ViewDatapoints(Base):
     def get_table_data(
         cls, session, table, rows=None, columns=None, sheets=None, release_id=None
     ):
-        # Build query using ORM for database-agnostic compatibility
+        engine_key = _get_engine_cache_key(session)
+        rows_key = tuple(rows) if rows is not None else None
+        columns_key = tuple(columns) if columns is not None else None
+        sheets_key = tuple(sheets) if sheets is not None else None
+        cache_key = (engine_key, table, rows_key, columns_key, sheets_key, release_id)
+
+        cached = cls._TABLE_DATA_CACHE.get(cache_key)
+        if cached is not None:
+            return cached
+
         query, aliases = cls._create_base_query_with_aliases(session)
 
         # Add column selections
@@ -2669,6 +2688,7 @@ class ViewDatapoints(Base):
         data = _check_ranges_values_are_present(data, "column_code", columns)
         data = _check_ranges_values_are_present(data, "sheet_code", sheets)
 
+        cls._TABLE_DATA_CACHE[cache_key] = data
         return data
 
     @classmethod

py_dpm/dpm_xl/ast/operands.py

@@ -2,6 +2,7 @@ from abc import ABC
 
 import pandas as pd
 import warnings
+from typing import Dict, Hashable, Tuple
 
 # Suppress pandas UserWarning about SQLAlchemy connection types
 warnings.filterwarnings("ignore", message=".*pandas only supports SQLAlchemy.*")
@@ -43,6 +44,9 @@ from py_dpm.dpm_xl.utils.data_handlers import filter_all_data
 operand_elements = ["table", "rows", "cols", "sheets", "default", "interval"]
 
 
+_HEADERS_CACHE: Dict[Tuple[Hashable, int, Tuple[str, ...]], pd.DataFrame] = {}
+
+
 def _create_operand_label(node):
     label = generate_new_label()
     node.label = label
@@ -185,42 +189,47 @@ class OperandsChecking(ASTTemplate, ABC):
         if len(table_codes) == 0:
             return
 
-        # Build ORM query
-        query = (
-            self.session.query(
-                TableVersion.code.label("Code"),
-                TableVersion.startreleaseid.label("StartReleaseID"),
-                TableVersion.endreleaseid.label("EndReleaseID"),
-                Header.direction.label("Direction"),
-                Table.hasopenrows.label("HasOpenRows"),
-                Table.hasopencolumns.label("HasOpenColumns"),
-                Table.hasopensheets.label("HasOpenSheets"),
-            )
-            .join(Table, Table.tableid == TableVersion.tableid)
-            .join(
-                TableVersionHeader, TableVersion.tablevid == TableVersionHeader.tablevid
+        engine = self.session.get_bind()
+        engine_key: Hashable = getattr(engine, "url", repr(engine))
+        cache_key = (engine_key, self.release_id, tuple(sorted(table_codes)))
+
+        df_headers = _HEADERS_CACHE.get(cache_key)
+        if df_headers is None:
+            query = (
+                self.session.query(
+                    TableVersion.code.label("Code"),
+                    TableVersion.startreleaseid.label("StartReleaseID"),
+                    TableVersion.endreleaseid.label("EndReleaseID"),
+                    Header.direction.label("Direction"),
+                    Table.hasopenrows.label("HasOpenRows"),
+                    Table.hasopencolumns.label("HasOpenColumns"),
+                    Table.hasopensheets.label("HasOpenSheets"),
+                )
+                .join(Table, Table.tableid == TableVersion.tableid)
+                .join(
+                    TableVersionHeader,
+                    TableVersion.tablevid == TableVersionHeader.tablevid,
+                )
+                .join(Header, Header.headerid == TableVersionHeader.headerid)
+                .filter(TableVersion.code.in_(table_codes))
+                .distinct()
             )
-            .join(Header, Header.headerid == TableVersionHeader.headerid)
-            .filter(TableVersion.code.in_(table_codes))
-            .distinct()
-        )
 
-        # Apply release filter
-        query = filter_by_release(
-            query,
-            start_col=TableVersion.startreleaseid,
-            end_col=TableVersion.endreleaseid,
-            release_id=self.release_id,
-        )
+            query = filter_by_release(
+                query,
+                start_col=TableVersion.startreleaseid,
+                end_col=TableVersion.endreleaseid,
+                release_id=self.release_id,
+            )
 
-        # Execute query and convert to DataFrame
-        from py_dpm.dpm.models import (
-            _compile_query_for_pandas,
-            _read_sql_with_connection,
-        )
+            from py_dpm.dpm.models import (
+                _compile_query_for_pandas,
+                _read_sql_with_connection,
+            )
 
-        compiled_query = _compile_query_for_pandas(query.statement, self.session)
-        df_headers = _read_sql_with_connection(compiled_query, self.session)
+            compiled_query = _compile_query_for_pandas(query.statement, self.session)
+            df_headers = _read_sql_with_connection(compiled_query, self.session)
+            _HEADERS_CACHE[cache_key] = df_headers
 
         for table in table_codes:
             table_headers = df_headers[df_headers["Code"] == table]

py_dpm/dpm_xl/utils/serialization.py

@@ -452,6 +452,21 @@ class ASTToJSONVisitor(NodeVisitor):
             'shift_number': node.shift_number
         }
 
+    def visit_RenameOp(self, node):
+        """Visit RenameOp nodes and serialize as RenameClauseOp."""
+        return {
+            'class_name': 'RenameClauseOp',
+            'operand': self.visit(node.operand),
+            'clauses': [self._serialize_rename_node(rn) for rn in node.rename_nodes]
+        }
+
+    def _serialize_rename_node(self, node):
+        """Serialize a RenameNode as a clause dictionary."""
+        return {
+            'from_component': node.old_name,
+            'to_component': node.new_name
+        }
+
     def visit_PreconditionItem(self, node):
         """Visit PreconditionItem nodes."""
         result = {

{pydpm_xl-0.2.8.dist-info → pydpm_xl-0.2.10.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pydpm_xl
-Version: 0.2.8
+Version: 0.2.10
 Summary: Python library for DPM-XL data processing and analysis
 Author-email: "MeaningfulData S.L." <info@meaningfuldata.eu>
 License: GPL-3.0-or-later
@@ -210,22 +210,21 @@ else:
     print(f"Error: {result.error}")
 ```
 
-#### Complete AST Generation
+#### Validations Script Generation
 
 ```python
-from py_dpm.api import generate_complete_ast, generate_enriched_ast
+from py_dpm.api import generate_validations_script
 
-# Generate complete AST with data fields
-result = generate_complete_ast("{tT_01.00, r0010, c0010}", release_id=123)
-if result.success:
-    print(f"AST: {result.ast}")
-    print(f"Data fields: {result.data_fields}")
+# Generate engine-ready validations script
+result = generate_validations_script(
+    "{tT_01.00, r0010, c0010}",
+    database_path="data.db",
+    release_code="4.2"
+)
+if result["success"]:
+    print(f"Enriched AST: {result['enriched_ast']}")
 else:
-    print(f"Errors: {result.errors}")
-
-# Generate enriched AST (ready for execution engine)
-enriched = generate_enriched_ast("{tT_01.00, r0010, c0010}", release_id=123)
-print(f"Enriched AST: {enriched}")
+    print(f"Error: {result['error']}")
 ```
 
 #### Migration

{pydpm_xl-0.2.8.dist-info → pydpm_xl-0.2.10.dist-info}/RECORD

@@ -1,14 +1,14 @@
-py_dpm/__init__.py,sha256=4k-u3wCmXF8WInrw7MzDeJ0E3F7WlfF1uzzPIe-g7vg,1858
-py_dpm/api/__init__.py,sha256=6ElO0NKEjuqiHNxK7pxkzLNlaUOrYKnY3N0fUDDobik,1021
+py_dpm/__init__.py,sha256=8RZiE-F0XPTFPGEyFhEp9cS-0ahXQN5PMGSlLRrarL8,1859
+py_dpm/api/__init__.py,sha256=bPWo4KWW99GmGkQbq0yQ3_tbTxvidEVVrWmcDXWz-xA,828
 py_dpm/api/dpm/__init__.py,sha256=HQflgiRbs1eDi3KTadNhxS1NoaG6PGQDVMvFnuIEfXo,506
 py_dpm/api/dpm/data_dictionary.py,sha256=q6w_5bFdc6WPd5Z601PpDaCcnIw39CnI4wdby3GJmFU,29893
 py_dpm/api/dpm/explorer.py,sha256=xgrSdh2D83RivypF26WWo20rbQifYBEH7PXvINoi07Y,10861
 py_dpm/api/dpm/hierarchical_queries.py,sha256=X4AbpsWy3iItOTVIdVbtaTmRgOHPf0Y64Ig-_377uns,4054
 py_dpm/api/dpm/instance.py,sha256=v3DWzdaM5gPCecLjwjZ49FGfqZzUR3dPC0U8zGwdttk,3795
 py_dpm/api/dpm/migration.py,sha256=9FT7zzz4QdUIRR6MD01gMODBtfq9HH_RF4hRgZqMcZc,2404
-py_dpm/api/dpm_xl/__init__.py,sha256=cwqeYgmowGH6MK8kQMQkjQaTL9qKEnC8-M5rueqhrPI,850
-py_dpm/api/dpm_xl/ast_generator.py,sha256=7EEUEmXMwck7obL3rnBjHeDnsM0F-LHnpUZNd3rVjHI,94929
-py_dpm/api/dpm_xl/complete_ast.py,sha256=_FSxA0FmNXuW0OLS3c8yzp14yjkmdR0rTebBAs1pg-E,8141
+py_dpm/api/dpm_xl/__init__.py,sha256=SOsCtwxuCkFQIdYoTcU6tVJdK1j96dPF4ZQpr8okLPc,576
+py_dpm/api/dpm_xl/ast_generator.py,sha256=hmfy2qV5t_RFGgmid7YuCXbrkjknv1KuQaJGxbXuHLs,97583
+py_dpm/api/dpm_xl/complete_ast.py,sha256=jjn9tsns4X7EN4RV5mFh5DRxxZfBOuX2b1wic4oB_ls,3967
 py_dpm/api/dpm_xl/operation_scopes.py,sha256=v2t3f2-AiF39hspNtpf_PA94T69JqbymFK9a5hpckRs,48831
 py_dpm/api/dpm_xl/semantic.py,sha256=Ddmh2Wj_iXIpQZ4jCjqOI-6ddFCquaO9RTu6W9i1Rts,13968
 py_dpm/api/dpm_xl/syntax.py,sha256=Ke_kKd9ModoJ6siL3GPT9j9QClmopryCRcdDAT3M5-E,5954
@@ -16,8 +16,8 @@ py_dpm/cli/__init__.py,sha256=UrfGHoQ0sZLjWfA0hoOoI4iTrn-bjr2f9Q8wDWd5nMo,133
 py_dpm/cli/main.py,sha256=LJ7JBk7lyWXe7ZYxnbxmohM1Dbha4sIdQzSTYKd9ZNo,22457
 py_dpm/cli/commands/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 py_dpm/dpm/__init__.py,sha256=moagUo5Gxf24-Tl9FL_3n2wmVoD_oXtpC-YIGktH_rc,212
-py_dpm/dpm/migration.py,sha256=ivO_ObvKzVomTns6qfo-o5FuciWxkXbMd_gJ4_tu7Xc,14110
-py_dpm/dpm/models.py,sha256=Rt1b8zOSayXd9KhwyfkGJVhCai3YxUakmLYgwaiICWA,135660
+py_dpm/dpm/migration.py,sha256=I_OX1xS2eE3L2V1RAPyHOqFn3Z54NWE0ozLAJdQrLcc,13810
+py_dpm/dpm/models.py,sha256=YyOYXzN4tIT2rO6-PP-53C6f7skatgnz7VY_5SnOsLQ,136414
 py_dpm/dpm/utils.py,sha256=3w06_kKiFRPqHvRUfN_0nNQIpppfidFybdDge97qzI0,14918
 py_dpm/dpm/queries/base.py,sha256=EddMeJMwtp63DyyIFO7_XxGvdlCtJQWWpeOVImlKp4I,3648
 py_dpm/dpm/queries/basic_objects.py,sha256=JOXC235lMDfVENrFAhZAl7_nqePJ4RrwJhFF0WDyk0M,955
@@ -35,7 +35,7 @@ py_dpm/dpm_xl/ast/ml_generation.py,sha256=Lw_1Btln2x1ewD9xH-2Ea4NJJP3PIqFoivWASX
 py_dpm/dpm_xl/ast/module_analyzer.py,sha256=ZnldoYn-s41UMiJpcAV6hjIwH6fssZeOpc564epngg8,2872
 py_dpm/dpm_xl/ast/module_dependencies.py,sha256=tbCqoDcE1n1lJOjtbpD3rNPkXrLk-k2rM5zyVwmsNpc,8355
 py_dpm/dpm_xl/ast/nodes.py,sha256=5ob8MsCW0fPZgz9yP_6IgVTH2SGeoTk5VncJuQ2SgrE,25035
-py_dpm/dpm_xl/ast/operands.py,sha256=UN69SQB0S8VG4sjQPz6CNfwjg1uDPEXqKsJtVIgiGGA,21128
+py_dpm/dpm_xl/ast/operands.py,sha256=0Yye5z6l0BBh9nrMlkVVNy3fYgbeUzZYLmP5Jvzr95M,21606
 py_dpm/dpm_xl/ast/template.py,sha256=QhYm7Jh_a-ws3kSmf0hqXFLzB_quO9GgKcmcFe22_fg,3045
 py_dpm/dpm_xl/ast/visitor.py,sha256=yL9UpPMQlq8ToHR8COyFYpuSChnDRjnkQHbCyYX0tsY,509
 py_dpm/dpm_xl/ast/where_clause.py,sha256=g3cslQ8vmlm0doqQ_ghjXzhzItc_xlC_bQ9odn87FGk,328
@@ -69,16 +69,16 @@ py_dpm/dpm_xl/utils/data_handlers.py,sha256=a0E-IaP_-CDKLcj-Gt2ggAziKIOUiwnT2D9I
 py_dpm/dpm_xl/utils/operands_mapping.py,sha256=LG0hPlUuTM2X2uWOtiD6HkmNeDEJkWJ8gV-Fxej_8QM,2241
 py_dpm/dpm_xl/utils/operator_mapping.py,sha256=BFgbVbSCSuutFNHJ4gtgm5VuG38pcl8Kmfi-sefg6JU,1913
 py_dpm/dpm_xl/utils/scopes_calculator.py,sha256=do_emsUqD1TbrjguKlOOqFleaVhxzqm-NnlgdrdIb6I,20906
-py_dpm/dpm_xl/utils/serialization.py,sha256=ouQpkmZWc6_T0hVzjwmxpHRu9yheNyyMBBaOZERe0qM,32558
+py_dpm/dpm_xl/utils/serialization.py,sha256=4ZBHIP-67_19QSxqzkv8GPh3RNJ861if26GKbV9Bxj8,33088
 py_dpm/dpm_xl/utils/tokens.py,sha256=VRIrPDi5ttwgH-on5Qt4-l4ho4bLA755-nfTalponcA,3496
 py_dpm/exceptions/__init__.py,sha256=yDERfUxYW7NUUEiTQChGpuJx6abr7IDe2XUpwVFPtvM,416
 py_dpm/exceptions/exceptions.py,sha256=6S3p-_i5O1oStvSMixt_JQG0xwTeSfBcdzrwL8yBy6Q,2413
 py_dpm/exceptions/messages.py,sha256=UwY6QIK8c-POcDCc9HYbZFGArCIYAanUGNh2LNKPx3U,7534
 py_dpm/instance/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 py_dpm/instance/instance.py,sha256=gRSg2dh1nEa0Srx9yKcN3bxiYidvZyRU_jsTNaKkP5I,10882
-pydpm_xl-0.2.8.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-pydpm_xl-0.2.8.dist-info/METADATA,sha256=lxBecMV5iI2uJ7kYokD9ewnzfV5k6Zprgvb0OdtehF8,9302
-pydpm_xl-0.2.8.dist-info/WHEEL,sha256=qELbo2s1Yzl39ZmrAibXA2jjPLUYfnVhUNTlyF1rq0Y,92
-pydpm_xl-0.2.8.dist-info/entry_points.txt,sha256=6DDmBfw-AjtgvMHgq_I730i_LAAs_7-N3C95HD_bRr4,47
-pydpm_xl-0.2.8.dist-info/top_level.txt,sha256=495PvWZRoKl2NvbQU25W7dqWIBHqY-mFMPt83uxPpcM,7
-pydpm_xl-0.2.8.dist-info/RECORD,,
+pydpm_xl-0.2.10.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+pydpm_xl-0.2.10.dist-info/METADATA,sha256=SPIgOJT90xDaqE4CYrE2VIsWXOAzGmXbLlI8Yl7yv9I,9154
+pydpm_xl-0.2.10.dist-info/WHEEL,sha256=qELbo2s1Yzl39ZmrAibXA2jjPLUYfnVhUNTlyF1rq0Y,92
+pydpm_xl-0.2.10.dist-info/entry_points.txt,sha256=6DDmBfw-AjtgvMHgq_I730i_LAAs_7-N3C95HD_bRr4,47
+pydpm_xl-0.2.10.dist-info/top_level.txt,sha256=495PvWZRoKl2NvbQU25W7dqWIBHqY-mFMPt83uxPpcM,7
+pydpm_xl-0.2.10.dist-info/RECORD,,