informatica-python 1.0.0__py3-none-any.whl

informatica_python/generators/sql_gen.py

@@ -0,0 +1,132 @@
+from informatica_python.models import FolderDef
+from informatica_python.utils.expression_converter import convert_sql_expression, detect_sql_dialect
+
+
+def generate_sql_file(folder: FolderDef) -> str:
+    lines = []
+    lines.append("-- ============================================================")
+    lines.append(f"-- All SQL Queries extracted from folder: {folder.name}")
+    lines.append("-- Auto-generated by informatica-python")
+    lines.append("-- ============================================================")
+    lines.append("")
+
+    sql_count = 0
+
+    for mapping in folder.mappings:
+        mapping_sqls = []
+
+        for tx in mapping.transformations:
+            for attr in tx.attributes:
+                if attr.name == "Sql Query" and attr.value and attr.value.strip():
+                    sql = convert_sql_expression(attr.value)
+                    dialect = detect_sql_dialect(sql)
+                    mapping_sqls.append({
+                        "transformation": tx.name,
+                        "type": tx.type,
+                        "attribute": "Sql Query",
+                        "sql": sql,
+                        "dialect": dialect,
+                    })
+                    sql_count += 1
+
+                elif attr.name == "Lookup Sql Override" and attr.value and attr.value.strip():
+                    sql = convert_sql_expression(attr.value)
+                    dialect = detect_sql_dialect(sql)
+                    mapping_sqls.append({
+                        "transformation": tx.name,
+                        "type": tx.type,
+                        "attribute": "Lookup SQL Override",
+                        "sql": sql,
+                        "dialect": dialect,
+                    })
+                    sql_count += 1
+
+                elif attr.name == "Pre SQL" and attr.value and attr.value.strip():
+                    sql = convert_sql_expression(attr.value)
+                    mapping_sqls.append({
+                        "transformation": tx.name,
+                        "type": tx.type,
+                        "attribute": "Pre-SQL",
+                        "sql": sql,
+                        "dialect": detect_sql_dialect(sql),
+                    })
+                    sql_count += 1
+
+                elif attr.name == "Post SQL" and attr.value and attr.value.strip():
+                    sql = convert_sql_expression(attr.value)
+                    mapping_sqls.append({
+                        "transformation": tx.name,
+                        "type": tx.type,
+                        "attribute": "Post-SQL",
+                        "sql": sql,
+                        "dialect": detect_sql_dialect(sql),
+                    })
+                    sql_count += 1
+
+                elif attr.name == "User Defined Join" and attr.value and attr.value.strip():
+                    sql = convert_sql_expression(attr.value)
+                    mapping_sqls.append({
+                        "transformation": tx.name,
+                        "type": tx.type,
+                        "attribute": "User Defined Join",
+                        "sql": sql,
+                        "dialect": detect_sql_dialect(sql),
+                    })
+                    sql_count += 1
+
+                elif attr.name == "Source Filter" and attr.value and attr.value.strip():
+                    sql = convert_sql_expression(attr.value)
+                    mapping_sqls.append({
+                        "transformation": tx.name,
+                        "type": tx.type,
+                        "attribute": "Source Filter",
+                        "sql": sql,
+                        "dialect": detect_sql_dialect(sql),
+                    })
+                    sql_count += 1
+
+        if mapping_sqls:
+            lines.append(f"-- ============================================================")
+            lines.append(f"-- Mapping: {mapping.name}")
+            lines.append(f"-- ============================================================")
+            lines.append("")
+
+            for sq in mapping_sqls:
+                lines.append(f"-- Transformation: {sq['transformation']} ({sq['type']})")
+                lines.append(f"-- Attribute: {sq['attribute']}")
+                lines.append(f"-- Detected dialect: {sq['dialect']}")
+                lines.append(f"-- ----")
+                lines.append(sq["sql"].rstrip())
+                lines.append("")
+                lines.append("")
+
+    for session in folder.sessions:
+        session_sqls = []
+        for sti in session.transform_instances:
+            for attr in sti.attributes:
+                if "sql" in attr.name.lower() and attr.value and attr.value.strip():
+                    sql = convert_sql_expression(attr.value)
+                    session_sqls.append({
+                        "instance": sti.instance_name,
+                        "attribute": attr.name,
+                        "sql": sql,
+                    })
+                    sql_count += 1
+
+        if session_sqls:
+            lines.append(f"-- ============================================================")
+            lines.append(f"-- Session: {session.name}")
+            lines.append(f"-- ============================================================")
+            lines.append("")
+            for sq in session_sqls:
+                lines.append(f"-- Instance: {sq['instance']}")
+                lines.append(f"-- Attribute: {sq['attribute']}")
+                lines.append(f"-- ----")
+                lines.append(sq["sql"].rstrip())
+                lines.append("")
+                lines.append("")
+
+    lines.append(f"-- Total SQL queries extracted: {sql_count}")
+    lines.append("")
+
+    return "\n".join(lines)

informatica_python/generators/workflow_gen.py

@@ -0,0 +1,234 @@
+from informatica_python.models import FolderDef, WorkflowDef, TaskInstanceDef
+
+
+def generate_workflow_code(folder: FolderDef) -> str:
+    lines = []
+    lines.append('"""')
+    lines.append(f"Workflow orchestration for folder: {folder.name}")
+    lines.append("Auto-generated by informatica-python")
+    lines.append('"""')
+    lines.append("")
+    lines.append("import sys")
+    lines.append("import logging")
+    lines.append("from datetime import datetime")
+    lines.append("from helper_functions import load_config, logger")
+    lines.append("")
+
+    for i, mapping in enumerate(folder.mappings, 1):
+        safe_name = _safe_name(mapping.name)
+        lines.append(f"from mapping_{i} import run_{safe_name}")
+    lines.append("")
+    lines.append("")
+
+    if folder.workflows:
+        for wf in folder.workflows:
+            _generate_workflow_function(lines, wf, folder)
+    else:
+        _generate_default_workflow(lines, folder)
+
+    lines.append("")
+    lines.append("if __name__ == '__main__':")
+    lines.append("    config = load_config()")
+    lines.append("    success = run_workflow(config)")
+    lines.append("    sys.exit(0 if success else 1)")
+    lines.append("")
+
+    return "\n".join(lines)
+
+
+def _generate_workflow_function(lines, wf: WorkflowDef, folder: FolderDef):
+    wf_safe = _safe_name(wf.name)
+    lines.append(f"def run_workflow(config, workflow_name='{wf.name}'):")
+    lines.append(f'    """')
+    lines.append(f"    Execute workflow: {wf.name}")
+    if wf.description:
+        lines.append(f"    Description: {wf.description}")
+    lines.append(f'    """')
+    lines.append(f"    logger.info(f'=== Starting Workflow: {wf.name} ===')")
+    lines.append(f"    wf_start = datetime.now()")
+    lines.append(f"    success = True")
+    lines.append(f"    failed_tasks = []")
+    lines.append("")
+
+    if wf.variables:
+        lines.append("    # Workflow Variables")
+        for var in wf.variables:
+            var_name = _safe_name(var.name.replace("$$", ""))
+            default = var.default_value or "''"
+            lines.append(f"    {var_name} = {default}")
+        lines.append("")
+
+    execution_order = _get_task_execution_order(wf)
+
+    mapping_name_map = {}
+    for i, mapping in enumerate(folder.mappings, 1):
+        mapping_name_map[mapping.name] = f"run_{_safe_name(mapping.name)}"
+
+    session_to_mapping = {}
+    for session in folder.sessions:
+        if session.mapping_name:
+            session_to_mapping[session.name] = session.mapping_name
+
+    for task in execution_order:
+        task_safe = _safe_name(task.name)
+
+        if task.task_type == "Start Task":
+            lines.append(f"    # Start Task: {task.name}")
+            lines.append(f"    logger.info('Workflow started')")
+            lines.append("")
+            continue
+
+        if task.task_type == "Session":
+            mapping_name = session_to_mapping.get(task.task_name or task.name, "")
+            run_func = mapping_name_map.get(mapping_name, None)
+
+            lines.append(f"    # Session: {task.name}")
+            lines.append(f"    try:")
+            lines.append(f"        logger.info('Executing session: {task.name}')")
+            if run_func:
+                lines.append(f"        {run_func}(config)")
+            else:
+                lines.append(f"        # TODO: Map session '{task.name}' to corresponding mapping function")
+                lines.append(f"        logger.warning('Session {task.name} has no mapped function')")
+            lines.append(f"    except Exception as e:")
+            lines.append(f"        logger.error(f'Session {task.name} failed: {{e}}')")
+
+            if task.fail_parent_if_instance_fails == "YES":
+                lines.append(f"        success = False")
+                lines.append(f"        failed_tasks.append('{task.name}')")
+            else:
+                lines.append(f"        logger.warning('Continuing despite failure (fail_parent=NO)')")
+            lines.append("")
+
+        elif task.task_type == "Command":
+            cmd = ""
+            for attr in task.attributes:
+                if attr.name in ("Command", "CmdLine"):
+                    cmd = attr.value
+            lines.append(f"    # Command Task: {task.name}")
+            lines.append(f"    try:")
+            lines.append(f"        import subprocess, shlex")
+            if cmd:
+                lines.append(f"        subprocess.run(shlex.split({repr(cmd)}), check=True)")
+            else:
+                lines.append(f"        # TODO: Configure command for task '{task.name}'")
+                lines.append(f"        pass")
+            lines.append(f"    except Exception as e:")
+            lines.append(f"        logger.error(f'Command task {task.name} failed: {{e}}')")
+            if task.fail_parent_if_instance_fails == "YES":
+                lines.append(f"        success = False")
+                lines.append(f"        failed_tasks.append('{task.name}')")
+            lines.append("")
+
+        elif task.task_type == "Email Task":
+            lines.append(f"    # Email Task: {task.name}")
+            lines.append(f"    # TODO: Implement email notification logic")
+            lines.append(f"    logger.info('Email task: {task.name} - skipped (implement email logic)')")
+            lines.append("")
+
+        elif task.task_type == "Decision":
+            lines.append(f"    # Decision Task: {task.name}")
+            decision_cond = ""
+            for attr in task.attributes:
+                if attr.name == "Decision Condition":
+                    decision_cond = attr.value
+            if decision_cond:
+                lines.append(f"    # Condition: {decision_cond}")
+            lines.append(f"    logger.info('Decision task: {task.name}')")
+            lines.append("")
+
+        elif task.task_type == "Timer":
+            lines.append(f"    # Timer Task: {task.name}")
+            lines.append(f"    import time")
+            lines.append(f"    # TODO: Configure timer delay")
+            lines.append(f"    logger.info('Timer task: {task.name}')")
+            lines.append("")
+
+        elif task.task_type == "Assignment":
+            lines.append(f"    # Assignment Task: {task.name}")
+            for attr in task.attributes:
+                if attr.name and attr.value:
+                    lines.append(f"    # {attr.name} = {attr.value}")
+            lines.append(f"    logger.info('Assignment task: {task.name}')")
+            lines.append("")
+
+        else:
+            lines.append(f"    # Task: {task.name} (Type: {task.task_type})")
+            lines.append(f"    logger.info('Executing task: {task.name} ({task.task_type})')")
+            lines.append(f"    # TODO: Implement task logic")
+            lines.append("")
+
+    lines.append(f"    elapsed = (datetime.now() - wf_start).total_seconds()")
+    lines.append(f"    if success:")
+    lines.append(f"        logger.info(f'=== Workflow {wf.name} completed successfully in {{elapsed:.2f}}s ===')")
+    lines.append(f"    else:")
+    lines.append(f"        logger.error(f'=== Workflow {wf.name} failed in {{elapsed:.2f}}s. Failed tasks: {{failed_tasks}} ===')")
+    lines.append(f"    return success")
+    lines.append("")
+
+
+def _generate_default_workflow(lines, folder):
+    lines.append("def run_workflow(config, workflow_name='default'):")
+    lines.append('    """Execute all mappings in order."""')
+    lines.append(f"    logger.info('=== Starting Default Workflow ===')")
+    lines.append(f"    wf_start = datetime.now()")
+    lines.append(f"    success = True")
+    lines.append("")
+
+    for i, mapping in enumerate(folder.mappings, 1):
+        safe_name = _safe_name(mapping.name)
+        lines.append(f"    try:")
+        lines.append(f"        logger.info('Executing mapping {i}: {mapping.name}')")
+        lines.append(f"        run_{safe_name}(config)")
+        lines.append(f"    except Exception as e:")
+        lines.append(f"        logger.error(f'Mapping {mapping.name} failed: {{e}}')")
+        lines.append(f"        success = False")
+        lines.append("")
+
+    lines.append(f"    elapsed = (datetime.now() - wf_start).total_seconds()")
+    lines.append(f"    logger.info(f'=== Workflow completed in {{elapsed:.2f}}s (success={{success}}) ===')")
+    lines.append(f"    return success")
+    lines.append("")
+
+
+def _get_task_execution_order(wf: WorkflowDef):
+    if not wf.task_instances:
+        return []
+
+    task_map = {t.name: t for t in wf.task_instances}
+    adj = {t.name: [] for t in wf.task_instances}
+    in_degree = {t.name: 0 for t in wf.task_instances}
+
+    for link in wf.links:
+        if link.from_instance in adj and link.to_instance in adj:
+            adj[link.from_instance].append(link.to_instance)
+            in_degree[link.to_instance] += 1
+
+    queue = []
+    for name, deg in in_degree.items():
+        if deg == 0:
+            queue.append(name)
+
+    ordered = []
+    while queue:
+        queue.sort()
+        node = queue.pop(0)
+        ordered.append(task_map[node])
+        for neighbor in adj.get(node, []):
+            in_degree[neighbor] -= 1
+            if in_degree[neighbor] == 0:
+                queue.append(neighbor)
+
+    for t in wf.task_instances:
+        if t not in ordered:
+            ordered.append(t)
+
+    return ordered
+
+
+def _safe_name(name):
+    import re
+    safe = re.sub(r'[^a-zA-Z0-9_]', '_', name)
+    if safe and safe[0].isdigit():
+        safe = '_' + safe
+    return safe.lower()

informatica_python/models.py

@@ -0,0 +1,281 @@
+from dataclasses import dataclass, field
+from typing import List, Dict, Optional
+
+
+@dataclass
+class FieldDef:
+    name: str
+    datatype: str
+    precision: int = 0
+    scale: int = 0
+    nullable: str = "NULL"
+    keytype: str = "NOT A KEY"
+    default_value: str = ""
+    expression: str = ""
+    expression_type: str = ""
+    porttype: str = ""
+    description: str = ""
+    field_number: int = 0
+    hidden: str = "NO"
+    business_name: str = ""
+
+
+@dataclass
+class TableAttribute:
+    name: str
+    value: str
+
+
+@dataclass
+class SourceDef:
+    name: str
+    database_type: str = ""
+    db_name: str = ""
+    owner_name: str = ""
+    description: str = ""
+    business_name: str = ""
+    fields: List[FieldDef] = field(default_factory=list)
+    attributes: List[TableAttribute] = field(default_factory=list)
+
+
+@dataclass
+class TargetDef:
+    name: str
+    database_type: str = ""
+    description: str = ""
+    business_name: str = ""
+    constraint: str = ""
+    table_options: str = ""
+    fields: List[FieldDef] = field(default_factory=list)
+    attributes: List[TableAttribute] = field(default_factory=list)
+
+
+@dataclass
+class TransformationDef:
+    name: str
+    type: str
+    description: str = ""
+    reusable: str = "NO"
+    fields: List[FieldDef] = field(default_factory=list)
+    attributes: List[TableAttribute] = field(default_factory=list)
+    metadata: Dict[str, str] = field(default_factory=dict)
+
+
+@dataclass
+class ConnectorDef:
+    from_field: str
+    from_instance: str
+    from_instance_type: str
+    to_field: str
+    to_instance: str
+    to_instance_type: str
+
+
+@dataclass
+class InstanceDef:
+    name: str
+    type: str
+    transformation_name: str = ""
+    transformation_type: str = ""
+    description: str = ""
+    reusable: str = "NO"
+
+
+@dataclass
+class TargetLoadOrder:
+    order: int = 1
+    target_instance: str = ""
+
+
+@dataclass
+class MappingVariable:
+    name: str
+    datatype: str = "string"
+    default_value: str = ""
+    description: str = ""
+    is_expression_variable: str = "NO"
+    is_persistent: str = "NO"
+    precision: int = 0
+    scale: int = 0
+    usage_type: str = ""
+
+
+@dataclass
+class MappingDef:
+    name: str
+    description: str = ""
+    is_valid: str = "YES"
+    sources: List[SourceDef] = field(default_factory=list)
+    targets: List[TargetDef] = field(default_factory=list)
+    transformations: List[TransformationDef] = field(default_factory=list)
+    connectors: List[ConnectorDef] = field(default_factory=list)
+    instances: List[InstanceDef] = field(default_factory=list)
+    target_load_orders: List[TargetLoadOrder] = field(default_factory=list)
+    variables: List[MappingVariable] = field(default_factory=list)
+    metadata: Dict[str, str] = field(default_factory=dict)
+
+
+@dataclass
+class ConnectionRef:
+    connection_name: str = ""
+    connection_type: str = ""
+    connection_subtype: str = ""
+    component_version: str = ""
+    variable: str = ""
+
+
+@dataclass
+class SessionTransformInst:
+    instance_name: str = ""
+    pipeline: str = ""
+    stage: str = ""
+    transformation_name: str = ""
+    transformation_type: str = ""
+    is_partitionable: str = "NO"
+    attributes: List[TableAttribute] = field(default_factory=list)
+    connections: List[ConnectionRef] = field(default_factory=list)
+
+
+@dataclass
+class SessionDef:
+    name: str
+    mapping_name: str = ""
+    description: str = ""
+    is_valid: str = "YES"
+    reusable: str = "NO"
+    transform_instances: List[SessionTransformInst] = field(default_factory=list)
+    attributes: List[TableAttribute] = field(default_factory=list)
+    config_references: List[Dict[str, str]] = field(default_factory=list)
+    connections: List[ConnectionRef] = field(default_factory=list)
+    components: List[Dict] = field(default_factory=list)
+
+
+@dataclass
+class TaskInstanceDef:
+    name: str
+    task_name: str = ""
+    task_type: str = ""
+    description: str = ""
+    is_valid: str = "YES"
+    reusable: str = "NO"
+    fail_parent_if_instance_fails: str = "YES"
+    fail_parent_if_instance_did_not_run: str = "NO"
+    treat_input_link_as_and: str = "YES"
+    attributes: List[TableAttribute] = field(default_factory=list)
+
+
+@dataclass
+class WorkflowLink:
+    from_instance: str
+    to_instance: str
+    condition: str = ""
+    link_type: str = ""
+
+
+@dataclass
+class WorkflowVariable:
+    name: str
+    datatype: str = "string"
+    default_value: str = ""
+    description: str = ""
+    is_null: str = "NO"
+    is_persistent: str = "NO"
+    is_user_defined: str = "YES"
+    precision: int = 0
+    scale: int = 0
+    usage_type: str = ""
+
+
+@dataclass
+class SchedulerDef:
+    name: str
+    description: str = ""
+    reusable: str = "NO"
+    attributes: List[TableAttribute] = field(default_factory=list)
+
+
+@dataclass
+class WorkflowDef:
+    name: str
+    description: str = ""
+    is_valid: str = "YES"
+    reusable: str = "NO"
+    scheduler_name: str = ""
+    task_instances: List[TaskInstanceDef] = field(default_factory=list)
+    links: List[WorkflowLink] = field(default_factory=list)
+    variables: List[WorkflowVariable] = field(default_factory=list)
+    attributes: List[TableAttribute] = field(default_factory=list)
+    metadata: Dict[str, str] = field(default_factory=dict)
+
+
+@dataclass
+class ConfigDef:
+    name: str
+    description: str = ""
+    is_valid: str = "YES"
+    attributes: List[TableAttribute] = field(default_factory=list)
+
+
+@dataclass
+class MappletDef:
+    name: str
+    description: str = ""
+    is_valid: str = "YES"
+    transformations: List[TransformationDef] = field(default_factory=list)
+    connectors: List[ConnectorDef] = field(default_factory=list)
+    instances: List[InstanceDef] = field(default_factory=list)
+
+
+@dataclass
+class ShortcutDef:
+    name: str
+    shortcut_type: str = ""
+    reference_name: str = ""
+    folder_name: str = ""
+    repository_name: str = ""
+
+
+@dataclass
+class TaskDef:
+    name: str
+    type: str = ""
+    description: str = ""
+    reusable: str = "NO"
+    attributes: List[TableAttribute] = field(default_factory=list)
+
+
+@dataclass
+class FolderDef:
+    name: str
+    owner: str = ""
+    description: str = ""
+    group: str = ""
+    shared: str = "NOTSHARED"
+    permissions: str = ""
+    sources: List[SourceDef] = field(default_factory=list)
+    targets: List[TargetDef] = field(default_factory=list)
+    mappings: List[MappingDef] = field(default_factory=list)
+    mapplets: List[MappletDef] = field(default_factory=list)
+    sessions: List[SessionDef] = field(default_factory=list)
+    workflows: List[WorkflowDef] = field(default_factory=list)
+    tasks: List[TaskDef] = field(default_factory=list)
+    configs: List[ConfigDef] = field(default_factory=list)
+    schedulers: List[SchedulerDef] = field(default_factory=list)
+    shortcuts: List[ShortcutDef] = field(default_factory=list)
+    transformations: List[TransformationDef] = field(default_factory=list)
+
+
+@dataclass
+class RepositoryDef:
+    name: str
+    version: str = ""
+    codepage: str = ""
+    database_type: str = ""
+    folders: List[FolderDef] = field(default_factory=list)
+
+
+@dataclass
+class PowermartDef:
+    creation_date: str = ""
+    repository_version: str = ""
+    repositories: List[RepositoryDef] = field(default_factory=list)