informatica-python 1.0.0__py3-none-any.whl

informatica_python/generators/helper_gen.py

@@ -0,0 +1,693 @@
+from informatica_python.models import FolderDef
+
+
+def generate_helper_functions(folder: FolderDef, data_lib: str = "pandas") -> str:
+    lines = []
+    lines.append('"""')
+    lines.append(f"Helper functions and core logic for folder: {folder.name}")
+    lines.append(f"Data manipulation library: {data_lib}")
+    lines.append('Auto-generated by informatica-python')
+    lines.append('"""')
+    lines.append("")
+
+    lines.append("import os")
+    lines.append("import sys")
+    lines.append("import logging")
+    lines.append("import yaml")
+    lines.append("from datetime import datetime")
+    lines.append("")
+
+    if data_lib == "pandas":
+        lines.append("import pandas as pd")
+    elif data_lib == "dask":
+        lines.append("import dask.dataframe as dd")
+        lines.append("import pandas as pd")
+    elif data_lib == "polars":
+        lines.append("import polars as pl")
+    elif data_lib == "vaex":
+        lines.append("import vaex")
+    elif data_lib == "modin":
+        lines.append("import modin.pandas as pd")
+    else:
+        lines.append("import pandas as pd")
+
+    lines.append("")
+    lines.append("")
+    lines.append("logging.basicConfig(")
+    lines.append('    level=logging.INFO,')
+    lines.append('    format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",')
+    lines.append('    handlers=[')
+    lines.append('        logging.StreamHandler(sys.stdout),')
+    lines.append('        logging.FileHandler("error_log.txt", mode="a"),')
+    lines.append('    ]')
+    lines.append(")")
+    lines.append('logger = logging.getLogger("informatica_converter")')
+    lines.append("")
+    lines.append("")
+    lines.append("def load_config(config_path='config.yml'):")
+    lines.append('    """Load configuration from YAML file."""')
+    lines.append("    with open(config_path, 'r') as f:")
+    lines.append("        return yaml.safe_load(f)")
+    lines.append("")
+    lines.append("")
+
+    _add_db_functions(lines, data_lib)
+    _add_file_functions(lines, data_lib)
+    _add_expression_helpers(lines)
+    _add_utility_functions(lines)
+
+    return "\n".join(lines)
+
+
+def _add_db_functions(lines, data_lib):
+    lines.append("# ============================================================")
+    lines.append("# Database Operations")
+    lines.append("# ============================================================")
+    lines.append("")
+    lines.append("")
+    lines.append("def get_db_connection(config, connection_name='default'):")
+    lines.append('    """Create database connection from config."""')
+    lines.append("    conn_config = config.get('connections', {}).get(connection_name, {})")
+    lines.append("    db_type = conn_config.get('type', 'mssql')")
+    lines.append("    host = conn_config.get('host', 'localhost')")
+    lines.append("    port = conn_config.get('port', 1433)")
+    lines.append("    database = conn_config.get('database', '')")
+    lines.append("    username = conn_config.get('username', '')")
+    lines.append("    password = conn_config.get('password', '')")
+    lines.append("    schema = conn_config.get('schema', 'dbo')")
+    lines.append("")
+    lines.append("    if db_type == 'mssql':")
+    lines.append("        try:")
+    lines.append("            import pyodbc")
+    lines.append("            conn_str = (")
+    lines.append("                f'DRIVER={{ODBC Driver 17 for SQL Server}};'")
+    lines.append("                f'SERVER={host},{port};'")
+    lines.append("                f'DATABASE={database};'")
+    lines.append("                f'UID={username};'")
+    lines.append("                f'PWD={password}'")
+    lines.append("            )")
+    lines.append("            return pyodbc.connect(conn_str)")
+    lines.append("        except ImportError:")
+    lines.append("            pass")
+    lines.append("")
+    lines.append("    if db_type == 'postgresql':")
+    lines.append("        try:")
+    lines.append("            import psycopg2")
+    lines.append("            return psycopg2.connect(")
+    lines.append("                host=host, port=port, dbname=database,")
+    lines.append("                user=username, password=password")
+    lines.append("            )")
+    lines.append("        except ImportError:")
+    lines.append("            pass")
+    lines.append("")
+    lines.append("    if db_type == 'oracle':")
+    lines.append("        try:")
+    lines.append("            import cx_Oracle")
+    lines.append("            dsn = cx_Oracle.makedsn(host, port, service_name=database)")
+    lines.append("            return cx_Oracle.connect(username, password, dsn)")
+    lines.append("        except ImportError:")
+    lines.append("            pass")
+    lines.append("")
+    lines.append("    jdbc_url = conn_config.get('jdbc_url', '')")
+    lines.append("    if jdbc_url:")
+    lines.append("        try:")
+    lines.append("            import jaydebeapi")
+    lines.append("            driver = conn_config.get('jdbc_driver', '')")
+    lines.append("            return jaydebeapi.connect(driver, jdbc_url, [username, password])")
+    lines.append("        except ImportError:")
+    lines.append("            pass")
+    lines.append("")
+    lines.append("    raise ConnectionError(f'Cannot create connection for type: {db_type}')")
+    lines.append("")
+    lines.append("")
+
+    if data_lib in ("pandas", "modin"):
+        read_func = "pd.read_sql"
+    elif data_lib == "dask":
+        read_func = "dd.read_sql_table"
+    elif data_lib == "polars":
+        read_func = "pl.read_database"
+    else:
+        read_func = "pd.read_sql"
+
+    lines.append("def read_from_db(config, query, connection_name='default'):")
+    lines.append('    """Read data from database using SQL query."""')
+    lines.append("    conn = get_db_connection(config, connection_name)")
+    lines.append("    try:")
+    lines.append(f"        logger.info(f'Executing query on {{connection_name}}')")
+    if data_lib == "polars":
+        lines.append("        df = pl.read_database(query, conn)")
+    elif data_lib == "dask":
+        lines.append("        df = dd.read_sql_query(query, conn)")
+    else:
+        lines.append(f"        df = {read_func}(query, conn)")
+    lines.append("        logger.info(f'Read {{len(df)}} rows from {{connection_name}}')")
+    lines.append("        return df")
+    lines.append("    except Exception as e:")
+    lines.append("        logger.error(f'DB read error on {{connection_name}}: {{e}}')")
+    lines.append("        raise")
+    lines.append("    finally:")
+    lines.append("        conn.close()")
+    lines.append("")
+    lines.append("")
+    lines.append("def write_to_db(config, df, table_name, connection_name='default', if_exists='append', schema=None):")
+    lines.append('    """Write dataframe to database table."""')
+    lines.append("    conn = get_db_connection(config, connection_name)")
+    lines.append("    conn_config = config.get('connections', {}).get(connection_name, {})")
+    lines.append("    if schema is None:")
+    lines.append("        schema = conn_config.get('schema', 'dbo')")
+    lines.append("    try:")
+    lines.append("        logger.info(f'Writing {{len(df)}} rows to {{schema}}.{{table_name}}')")
+    if data_lib == "polars":
+        lines.append("        df.to_pandas().to_sql(table_name, conn, schema=schema, if_exists=if_exists, index=False)")
+    elif data_lib == "dask":
+        lines.append("        df.compute().to_sql(table_name, conn, schema=schema, if_exists=if_exists, index=False)")
+    else:
+        lines.append("        df.to_sql(table_name, conn, schema=schema, if_exists=if_exists, index=False)")
+    lines.append("        logger.info(f'Successfully wrote to {{schema}}.{{table_name}}')")
+    lines.append("    except Exception as e:")
+    lines.append("        logger.error(f'DB write error to {{schema}}.{{table_name}}: {{e}}')")
+    lines.append("        raise")
+    lines.append("    finally:")
+    lines.append("        conn.close()")
+    lines.append("")
+    lines.append("")
+    lines.append("def execute_sql(config, sql, connection_name='default'):")
+    lines.append('    """Execute a SQL statement (INSERT, UPDATE, DELETE, DDL)."""')
+    lines.append("    conn = get_db_connection(config, connection_name)")
+    lines.append("    try:")
+    lines.append("        cursor = conn.cursor()")
+    lines.append("        cursor.execute(sql)")
+    lines.append("        conn.commit()")
+    lines.append("        logger.info(f'Executed SQL on {{connection_name}}')")
+    lines.append("    except Exception as e:")
+    lines.append("        logger.error(f'SQL execution error: {{e}}')")
+    lines.append("        conn.rollback()")
+    lines.append("        raise")
+    lines.append("    finally:")
+    lines.append("        conn.close()")
+    lines.append("")
+    lines.append("")
+
+
+def _add_file_functions(lines, data_lib):
+    lines.append("# ============================================================")
+    lines.append("# File Operations")
+    lines.append("# ============================================================")
+    lines.append("")
+    lines.append("")
+    lines.append("def read_file(file_path, file_config=None):")
+    lines.append('    """')
+    lines.append('    Read data from file based on extension and configuration.')
+    lines.append('    Supports: .csv, .dat, .txt, .xml, .xlsx, .xls, .json, .parquet, and files with no extension.')
+    lines.append('    """')
+    lines.append("    if file_config is None:")
+    lines.append("        file_config = {}")
+    lines.append("")
+    lines.append("    ext = os.path.splitext(file_path)[1].lower()")
+    lines.append("    delimiter = file_config.get('delimiter', ',')")
+    lines.append("    header = file_config.get('header', True)")
+    lines.append("    encoding = file_config.get('encoding', 'utf-8')")
+    lines.append("    header_row = 0 if header else None")
+    lines.append("")
+    lines.append("    logger.info(f'Reading file: {file_path} (ext={ext})')")
+    lines.append("")
+    lines.append("    try:")
+
+    if data_lib == "polars":
+        lines.append("        if ext in ('.csv', '.dat', '.txt', ''):")
+        lines.append("            return pl.read_csv(file_path, separator=delimiter, has_header=header, encoding=encoding)")
+        lines.append("        elif ext in ('.xlsx', '.xls'):")
+        lines.append("            return pl.read_excel(file_path)")
+        lines.append("        elif ext == '.xml':")
+        lines.append("            import xml.etree.ElementTree as ET")
+        lines.append("            tree = ET.parse(file_path)")
+        lines.append("            root = tree.getroot()")
+        lines.append("            return _xml_to_polars(root, file_config)")
+        lines.append("        elif ext == '.json':")
+        lines.append("            return pl.read_json(file_path)")
+        lines.append("        elif ext == '.parquet':")
+        lines.append("            return pl.read_parquet(file_path)")
+        lines.append("        else:")
+        lines.append("            return pl.read_csv(file_path, separator=delimiter, has_header=header)")
+    elif data_lib == "dask":
+        lines.append("        if ext in ('.csv', '.dat', '.txt', ''):")
+        lines.append("            return dd.read_csv(file_path, sep=delimiter, header=header_row, encoding=encoding)")
+        lines.append("        elif ext in ('.xlsx', '.xls'):")
+        lines.append("            return dd.from_pandas(pd.read_excel(file_path, header=header_row), npartitions=1)")
+        lines.append("        elif ext == '.xml':")
+        lines.append("            return dd.from_pandas(_read_xml_to_pandas(file_path, file_config), npartitions=1)")
+        lines.append("        elif ext == '.json':")
+        lines.append("            return dd.read_json(file_path)")
+        lines.append("        elif ext == '.parquet':")
+        lines.append("            return dd.read_parquet(file_path)")
+        lines.append("        else:")
+        lines.append("            return dd.read_csv(file_path, sep=delimiter, header=header_row)")
+    else:
+        lines.append("        if ext in ('.csv', '.dat', '.txt', ''):")
+        lines.append("            return pd.read_csv(file_path, sep=delimiter, header=header_row, encoding=encoding)")
+        lines.append("        elif ext in ('.xlsx', '.xls'):")
+        lines.append("            return pd.read_excel(file_path, header=header_row)")
+        lines.append("        elif ext == '.xml':")
+        lines.append("            return _read_xml_to_pandas(file_path, file_config)")
+        lines.append("        elif ext == '.json':")
+        lines.append("            return pd.read_json(file_path)")
+        lines.append("        elif ext == '.parquet':")
+        lines.append("            return pd.read_parquet(file_path)")
+        lines.append("        else:")
+        lines.append("            return pd.read_csv(file_path, sep=delimiter, header=header_row)")
+
+    lines.append("    except Exception as e:")
+    lines.append("        logger.error(f'File read error for {file_path}: {e}')")
+    lines.append("        raise")
+    lines.append("")
+    lines.append("")
+    lines.append("def write_file(df, file_path, file_config=None):")
+    lines.append('    """Write dataframe to file based on extension."""')
+    lines.append("    if file_config is None:")
+    lines.append("        file_config = {}")
+    lines.append("")
+    lines.append("    ext = os.path.splitext(file_path)[1].lower()")
+    lines.append("    delimiter = file_config.get('delimiter', ',')")
+    lines.append("    header = file_config.get('header', True)")
+    lines.append("    encoding = file_config.get('encoding', 'utf-8')")
+    lines.append("")
+    lines.append("    os.makedirs(os.path.dirname(file_path) or '.', exist_ok=True)")
+    lines.append("    logger.info(f'Writing file: {file_path}')")
+    lines.append("")
+    lines.append("    try:")
+
+    if data_lib == "polars":
+        lines.append("        if ext in ('.csv', '.dat', '.txt', ''):")
+        lines.append("            df.write_csv(file_path, separator=delimiter, has_header=header)")
+        lines.append("        elif ext in ('.xlsx', '.xls'):")
+        lines.append("            df.write_excel(file_path)")
+        lines.append("        elif ext == '.json':")
+        lines.append("            df.write_json(file_path)")
+        lines.append("        elif ext == '.parquet':")
+        lines.append("            df.write_parquet(file_path)")
+        lines.append("        else:")
+        lines.append("            df.write_csv(file_path, separator=delimiter, has_header=header)")
+    elif data_lib == "dask":
+        lines.append("        if ext in ('.csv', '.dat', '.txt', ''):")
+        lines.append("            df.compute().to_csv(file_path, sep=delimiter, header=header, index=False, encoding=encoding)")
+        lines.append("        elif ext in ('.xlsx', '.xls'):")
+        lines.append("            df.compute().to_excel(file_path, header=header, index=False)")
+        lines.append("        elif ext == '.json':")
+        lines.append("            df.compute().to_json(file_path)")
+        lines.append("        elif ext == '.parquet':")
+        lines.append("            df.to_parquet(file_path)")
+        lines.append("        else:")
+        lines.append("            df.compute().to_csv(file_path, sep=delimiter, header=header, index=False)")
+    else:
+        lines.append("        if ext in ('.csv', '.dat', '.txt', ''):")
+        lines.append("            df.to_csv(file_path, sep=delimiter, header=header, index=False, encoding=encoding)")
+        lines.append("        elif ext in ('.xlsx', '.xls'):")
+        lines.append("            df.to_excel(file_path, header=header, index=False)")
+        lines.append("        elif ext == '.json':")
+        lines.append("            df.to_json(file_path)")
+        lines.append("        elif ext == '.parquet':")
+        lines.append("            df.to_parquet(file_path, index=False)")
+        lines.append("        else:")
+        lines.append("            df.to_csv(file_path, sep=delimiter, header=header, index=False)")
+
+    lines.append("    except Exception as e:")
+    lines.append("        logger.error(f'File write error for {file_path}: {e}')")
+    lines.append("        raise")
+    lines.append("")
+    lines.append("")
+
+    if data_lib != "polars":
+        lines.append("def _read_xml_to_pandas(file_path, file_config):")
+        lines.append('    """Parse XML file into a pandas DataFrame."""')
+        lines.append("    import xml.etree.ElementTree as ET")
+        lines.append("    nested = file_config.get('nested', False)")
+        lines.append("    row_tag = file_config.get('row_tag', None)")
+        lines.append("    tree = ET.parse(file_path)")
+        lines.append("    root = tree.getroot()")
+        lines.append("    if row_tag:")
+        lines.append("        rows = root.findall(f'.//{row_tag}')")
+        lines.append("    else:")
+        lines.append("        rows = list(root)")
+        lines.append("    records = []")
+        lines.append("    for row in rows:")
+        lines.append("        record = dict(row.attrib)")
+        lines.append("        for child in row:")
+        lines.append("            tag = child.tag.split('}')[-1] if '}' in child.tag else child.tag")
+        lines.append("            if nested and len(child) > 0:")
+        lines.append("                record[tag] = ET.tostring(child, encoding='unicode')")
+        lines.append("            else:")
+        lines.append("                record[tag] = child.text")
+        lines.append("        records.append(record)")
+        lines.append("    return pd.DataFrame(records)")
+        lines.append("")
+        lines.append("")
+    else:
+        lines.append("def _xml_to_polars(root, file_config):")
+        lines.append('    """Parse XML element tree into a Polars DataFrame."""')
+        lines.append("    import xml.etree.ElementTree as ET")
+        lines.append("    row_tag = file_config.get('row_tag', None)")
+        lines.append("    if row_tag:")
+        lines.append("        rows = root.findall(f'.//{row_tag}')")
+        lines.append("    else:")
+        lines.append("        rows = list(root)")
+        lines.append("    records = []")
+        lines.append("    for row in rows:")
+        lines.append("        record = dict(row.attrib)")
+        lines.append("        for child in row:")
+        lines.append("            tag = child.tag.split('}')[-1] if '}' in child.tag else child.tag")
+        lines.append("            record[tag] = child.text")
+        lines.append("        records.append(record)")
+        lines.append("    return pl.DataFrame(records)")
+        lines.append("")
+        lines.append("")
+
+
+def _add_expression_helpers(lines):
+    lines.append("# ============================================================")
+    lines.append("# Informatica Expression Helper Functions")
+    lines.append("# ============================================================")
+    lines.append("")
+    lines.append("")
+    lines.append("def iif_expr(condition, true_val, false_val=None):")
+    lines.append('    """Informatica IIF equivalent."""')
+    lines.append("    return true_val if condition else false_val")
+    lines.append("")
+    lines.append("")
+    lines.append("def decode_expr(value, *args):")
+    lines.append('    """Informatica DECODE equivalent."""')
+    lines.append("    pairs = list(args)")
+    lines.append("    default = pairs.pop() if len(pairs) % 2 != 0 else None")
+    lines.append("    for i in range(0, len(pairs), 2):")
+    lines.append("        if value == pairs[i]:")
+    lines.append("            return pairs[i + 1]")
+    lines.append("    return default")
+    lines.append("")
+    lines.append("")
+    lines.append("def nvl(value, default):")
+    lines.append('    """Informatica NVL equivalent."""')
+    lines.append("    return default if value is None else value")
+    lines.append("")
+    lines.append("")
+    lines.append("def nvl2(value, not_null_val, null_val):")
+    lines.append('    """Informatica NVL2 equivalent."""')
+    lines.append("    return not_null_val if value is not None else null_val")
+    lines.append("")
+    lines.append("")
+    lines.append("def isnull(value):")
+    lines.append('    """Informatica ISNULL equivalent."""')
+    lines.append("    return value is None")
+    lines.append("")
+    lines.append("")
+    lines.append("def ltrim(value, trim_str=None):")
+    lines.append('    """Informatica LTRIM equivalent."""')
+    lines.append("    if value is None:")
+    lines.append("        return None")
+    lines.append("    return str(value).lstrip(trim_str)")
+    lines.append("")
+    lines.append("")
+    lines.append("def rtrim(value, trim_str=None):")
+    lines.append('    """Informatica RTRIM equivalent."""')
+    lines.append("    if value is None:")
+    lines.append("        return None")
+    lines.append("    return str(value).rstrip(trim_str)")
+    lines.append("")
+    lines.append("")
+    lines.append("def substr(value, start, length=None):")
+    lines.append('    """Informatica SUBSTR equivalent (1-based index)."""')
+    lines.append("    if value is None:")
+    lines.append("        return None")
+    lines.append("    s = str(value)")
+    lines.append("    start_idx = max(start - 1, 0)")
+    lines.append("    if length is not None:")
+    lines.append("        return s[start_idx:start_idx + length]")
+    lines.append("    return s[start_idx:]")
+    lines.append("")
+    lines.append("")
+    lines.append("def to_char(value, fmt=None):")
+    lines.append('    """Informatica TO_CHAR equivalent."""')
+    lines.append("    if value is None:")
+    lines.append("        return None")
+    lines.append("    if fmt and hasattr(value, 'strftime'):")
+    lines.append("        py_fmt = fmt.replace('YYYY', '%Y').replace('MM', '%m').replace('DD', '%d')")
+    lines.append("        py_fmt = py_fmt.replace('HH24', '%H').replace('MI', '%M').replace('SS', '%S')")
+    lines.append("        return value.strftime(py_fmt)")
+    lines.append("    return str(value)")
+    lines.append("")
+    lines.append("")
+    lines.append("def to_date(value, fmt=None):")
+    lines.append('    """Informatica TO_DATE equivalent."""')
+    lines.append("    if value is None:")
+    lines.append("        return None")
+    lines.append("    if fmt:")
+    lines.append("        py_fmt = fmt.replace('YYYY', '%Y').replace('MM', '%m').replace('DD', '%d')")
+    lines.append("        py_fmt = py_fmt.replace('HH24', '%H').replace('MI', '%M').replace('SS', '%S')")
+    lines.append("        return datetime.strptime(str(value), py_fmt)")
+    lines.append("    return datetime.fromisoformat(str(value))")
+    lines.append("")
+    lines.append("")
+    lines.append("def to_integer(value):")
+    lines.append('    """Informatica TO_INTEGER equivalent."""')
+    lines.append("    if value is None:")
+    lines.append("        return None")
+    lines.append("    return int(float(str(value)))")
+    lines.append("")
+    lines.append("")
+    lines.append("def to_bigint(value):")
+    lines.append('    """Informatica TO_BIGINT equivalent."""')
+    lines.append("    return to_integer(value)")
+    lines.append("")
+    lines.append("")
+    lines.append("def to_float(value):")
+    lines.append('    """Informatica TO_FLOAT equivalent."""')
+    lines.append("    if value is None:")
+    lines.append("        return None")
+    lines.append("    return float(str(value))")
+    lines.append("")
+    lines.append("")
+    lines.append("def to_decimal(value, scale=0):")
+    lines.append('    """Informatica TO_DECIMAL equivalent."""')
+    lines.append("    if value is None:")
+    lines.append("        return None")
+    lines.append("    return round(float(str(value)), scale)")
+    lines.append("")
+    lines.append("")
+    lines.append("def replacechr(search_type, source, search_chars, replace_char):")
+    lines.append('    """Informatica REPLACECHR equivalent."""')
+    lines.append("    if source is None:")
+    lines.append("        return None")
+    lines.append("    result = str(source)")
+    lines.append("    for ch in str(search_chars):")
+    lines.append("        result = result.replace(ch, str(replace_char) if replace_char else '')")
+    lines.append("    return result")
+    lines.append("")
+    lines.append("")
+    lines.append("def replacestr(search_type, source, search_str, replace_str):")
+    lines.append('    """Informatica REPLACESTR equivalent."""')
+    lines.append("    if source is None:")
+    lines.append("        return None")
+    lines.append("    return str(source).replace(str(search_str), str(replace_str) if replace_str else '')")
+    lines.append("")
+    lines.append("")
+    lines.append("def instr(value, search, start=1, occurrence=1):")
+    lines.append('    """Informatica INSTR equivalent (1-based)."""')
+    lines.append("    if value is None or search is None:")
+    lines.append("        return 0")
+    lines.append("    s = str(value)")
+    lines.append("    needle = str(search)")
+    lines.append("    idx = max(start - 1, 0)")
+    lines.append("    for _ in range(occurrence):")
+    lines.append("        found = s.find(needle, idx)")
+    lines.append("        if found == -1:")
+    lines.append("            return 0")
+    lines.append("        idx = found + 1")
+    lines.append("    return idx")
+    lines.append("")
+    lines.append("")
+    lines.append("def lpad(value, length, pad_char=' '):")
+    lines.append('    """Informatica LPAD equivalent."""')
+    lines.append("    if value is None:")
+    lines.append("        return None")
+    lines.append("    return str(value).rjust(length, str(pad_char)[0] if pad_char else ' ')")
+    lines.append("")
+    lines.append("")
+    lines.append("def rpad(value, length, pad_char=' '):")
+    lines.append('    """Informatica RPAD equivalent."""')
+    lines.append("    if value is None:")
+    lines.append("        return None")
+    lines.append("    return str(value).ljust(length, str(pad_char)[0] if pad_char else ' ')")
+    lines.append("")
+    lines.append("")
+    lines.append("def length(value):")
+    lines.append('    """Informatica LENGTH equivalent."""')
+    lines.append("    if value is None:")
+    lines.append("        return 0")
+    lines.append("    return len(str(value))")
+    lines.append("")
+    lines.append("")
+    lines.append("def upper(value):")
+    lines.append('    """Informatica UPPER equivalent."""')
+    lines.append("    return str(value).upper() if value is not None else None")
+    lines.append("")
+    lines.append("")
+    lines.append("def lower(value):")
+    lines.append('    """Informatica LOWER equivalent."""')
+    lines.append("    return str(value).lower() if value is not None else None")
+    lines.append("")
+    lines.append("")
+    lines.append("def concat(*args):")
+    lines.append('    """Informatica CONCAT equivalent."""')
+    lines.append("    return ''.join(str(a) if a is not None else '' for a in args)")
+    lines.append("")
+    lines.append("")
+    lines.append("def is_date(value, fmt=None):")
+    lines.append('    """Informatica IS_DATE equivalent."""')
+    lines.append("    try:")
+    lines.append("        if fmt:")
+    lines.append("            py_fmt = fmt.replace('YYYY', '%Y').replace('MM', '%m').replace('DD', '%d')")
+    lines.append("            datetime.strptime(str(value), py_fmt)")
+    lines.append("        else:")
+    lines.append("            datetime.fromisoformat(str(value))")
+    lines.append("        return True")
+    lines.append("    except (ValueError, TypeError):")
+    lines.append("        return False")
+    lines.append("")
+    lines.append("")
+    lines.append("def is_number(value):")
+    lines.append('    """Informatica IS_NUMBER equivalent."""')
+    lines.append("    try:")
+    lines.append("        float(str(value))")
+    lines.append("        return True")
+    lines.append("    except (ValueError, TypeError):")
+    lines.append("        return False")
+    lines.append("")
+    lines.append("")
+    lines.append("def is_spaces(value):")
+    lines.append('    """Informatica IS_SPACES equivalent."""')
+    lines.append("    return value is None or str(value).strip() == ''")
+    lines.append("")
+    lines.append("")
+    lines.append("def reg_extract(value, pattern, group_num=0):")
+    lines.append('    """Informatica REG_EXTRACT equivalent."""')
+    lines.append("    import re")
+    lines.append("    if value is None:")
+    lines.append("        return None")
+    lines.append("    match = re.search(pattern, str(value))")
+    lines.append("    if match:")
+    lines.append("        return match.group(group_num)")
+    lines.append("    return None")
+    lines.append("")
+    lines.append("")
+    lines.append("def reg_match(value, pattern):")
+    lines.append('    """Informatica REG_MATCH equivalent."""')
+    lines.append("    import re")
+    lines.append("    if value is None:")
+    lines.append("        return False")
+    lines.append("    return bool(re.search(pattern, str(value)))")
+    lines.append("")
+    lines.append("")
+    lines.append("def reg_replace(value, pattern, replacement):")
+    lines.append('    """Informatica REG_REPLACE equivalent."""')
+    lines.append("    import re")
+    lines.append("    if value is None:")
+    lines.append("        return None")
+    lines.append("    return re.sub(pattern, replacement, str(value))")
+    lines.append("")
+    lines.append("")
+    lines.append("def get_date_part(part, date_val):")
+    lines.append('    """Informatica GET_DATE_PART equivalent."""')
+    lines.append("    if date_val is None:")
+    lines.append("        return None")
+    lines.append("    if isinstance(date_val, str):")
+    lines.append("        date_val = datetime.fromisoformat(date_val)")
+    lines.append("    part_map = {'YYYY': date_val.year, 'YY': date_val.year % 100,")
+    lines.append("                'MM': date_val.month, 'DD': date_val.day,")
+    lines.append("                'HH': date_val.hour, 'MI': date_val.minute, 'SS': date_val.second}")
+    lines.append("    return part_map.get(part.upper(), None)")
+    lines.append("")
+    lines.append("")
+    lines.append("def add_to_date(date_val, amount, part='DD'):")
+    lines.append('    """Informatica ADD_TO_DATE equivalent."""')
+    lines.append("    from datetime import timedelta")
+    lines.append("    if date_val is None:")
+    lines.append("        return None")
+    lines.append("    if isinstance(date_val, str):")
+    lines.append("        date_val = datetime.fromisoformat(date_val)")
+    lines.append("    if part.upper() in ('DD', 'D', 'DAY', 'DDD'):")
+    lines.append("        return date_val + timedelta(days=amount)")
+    lines.append("    elif part.upper() in ('HH', 'HH24', 'HOUR'):")
+    lines.append("        return date_val + timedelta(hours=amount)")
+    lines.append("    elif part.upper() in ('MI', 'MIN', 'MINUTE'):")
+    lines.append("        return date_val + timedelta(minutes=amount)")
+    lines.append("    elif part.upper() in ('SS', 'SEC', 'SECOND'):")
+    lines.append("        return date_val + timedelta(seconds=amount)")
+    lines.append("    elif part.upper() in ('MM', 'MON', 'MONTH'):")
+    lines.append("        month = date_val.month + amount")
+    lines.append("        year = date_val.year + (month - 1) // 12")
+    lines.append("        month = (month - 1) % 12 + 1")
+    lines.append("        return date_val.replace(year=year, month=month)")
+    lines.append("    elif part.upper() in ('YYYY', 'YY', 'YEAR'):")
+    lines.append("        return date_val.replace(year=date_val.year + amount)")
+    lines.append("    return date_val")
+    lines.append("")
+    lines.append("")
+    lines.append("def raise_error(message):")
+    lines.append('    """Informatica ERROR function equivalent."""')
+    lines.append("    logger.error(f'INFORMATICA ERROR: {message}')")
+    lines.append("    raise RuntimeError(message)")
+    lines.append("")
+    lines.append("")
+    lines.append("def abort_func(message):")
+    lines.append('    """Informatica ABORT function equivalent."""')
+    lines.append("    logger.critical(f'INFORMATICA ABORT: {message}')")
+    lines.append("    raise SystemExit(message)")
+    lines.append("")
+    lines.append("")
+    lines.append("def lookup_func(table, condition, *fields):")
+    lines.append('    """Placeholder for Informatica LOOKUP function."""')
+    lines.append("    logger.warning(f'LOOKUP called for table {table} - implement in mapping-specific code')")
+    lines.append("    return None")
+    lines.append("")
+    lines.append("")
+    lines.append("def get_variable(var_name):")
+    lines.append('    """Get workflow/mapping variable value."""')
+    lines.append("    return os.environ.get(f'INFA_VAR_{var_name}', '')")
+    lines.append("")
+    lines.append("")
+    lines.append("def set_variable(var_name, value):")
+    lines.append('    """Set workflow/mapping variable value."""')
+    lines.append("    os.environ[f'INFA_VAR_{var_name}'] = str(value)")
+    lines.append("    return value")
+    lines.append("")
+    lines.append("")
+    lines.append("current_timestamp = datetime.now")
+    lines.append("session_start_time = datetime.now")
+    lines.append("")
+    lines.append("")
+
+
+def _add_utility_functions(lines):
+    lines.append("# ============================================================")
+    lines.append("# Utility Functions")
+    lines.append("# ============================================================")
+    lines.append("")
+    lines.append("")
+    lines.append("def log_mapping_start(mapping_name):")
+    lines.append('    """Log the start of a mapping execution."""')
+    lines.append("    logger.info(f'=== Starting mapping: {mapping_name} ===')")
+    lines.append("    return datetime.now()")
+    lines.append("")
+    lines.append("")
+    lines.append("def log_mapping_end(mapping_name, start_time, row_count=0):")
+    lines.append('    """Log the end of a mapping execution."""')
+    lines.append("    elapsed = (datetime.now() - start_time).total_seconds()")
+    lines.append("    logger.info(f'=== Completed mapping: {mapping_name} in {elapsed:.2f}s ({row_count} rows) ===')")
+    lines.append("")
+    lines.append("")
+    lines.append("def validate_row_count(df, mapping_name, min_rows=0):")
+    lines.append('    """Validate row count after transformation."""')
+    lines.append("    count = len(df) if hasattr(df, '__len__') else 0")
+    lines.append("    if count < min_rows:")
+    lines.append("        logger.warning(f'{mapping_name}: Expected at least {min_rows} rows, got {count}')")
+    lines.append("    return count")
+    lines.append("")