sql-dag-flow 0.5.2__tar.gz → 0.5.4__tar.gz

{sql_dag_flow-0.5.2/src/sql_dag_flow.egg-info → sql_dag_flow-0.5.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sql-dag-flow
-Version: 0.5.2
+Version: 0.5.4
 Summary: A sophisticated SQL lineage visualization tool for Medallion Architectures.
 Author-email: Flavio Sandoval <dsandovalflavio@gmail.com>
 License: MIT
@@ -65,6 +65,7 @@ Specially optimized for the **Medallion Architecture** (Bronze, Silver, Gold) an
     *   Powered by **ELK (Eclipse Layout Kernel)**.
     *   Minimizes edge crossings and optimizes flow direction.
     *   Intelligent "Port" handling for cleaner connections.
+*   **Startup Configuration Selector**: Instantly resume previous sessions by selecting any `.json` configuration file found in your project directory upon launching the app.
 
 ### 🎮 Interactive Graph
 *   **Smart Context Menu**:
@@ -99,6 +100,7 @@ Specially optimized for the **Medallion Architecture** (Bronze, Silver, Gold) an
 *   **Column-Level Lineage (New in v0.4.9 🆕)**: Traces how each output column derives from source columns. Shows transformation chain (e.g., `order_timestamp ← orders_raw.order_date via CAST(... AS DATETIME)`).
 *   **SQL Syntax Validation (New in v0.4.9 🆕)**: Detects SQL parse errors and displays structured warnings with line/column references. Shows ⚠️ badge on nodes with syntax issues.
 *   **Large DAG Support & Safe Cycle Detection (New in v0.5.1 🚀)**: Optimized cycle detection algorithm prevents backend hanging and "Failed to fetch" browser errors when analyzing massive projects (50+ nodes). Employs quick DAG verifications and bounded iterator loops.
+*   **Performance Optimizations (New in v0.5.2 ⚡)**: Includes backend parsing TTL caching and frontend request deduplication to prevent server overload when refreshing large numbers of un-cached SQL files simultaneously.
 *   **Batch Hide from Toolbar**: Select multiple nodes → click "Hide" in the selection toolbar to hide them all at once.
 *   **Discovery Mode Fix**: Ghost nodes from Discovery Mode are now hidden when their connected source nodes are hidden, preventing orphan ghost nodes.
 
@@ -145,7 +147,7 @@ Install easily via `pip`:
 pip install sql-dag-flow
 ```
 
-To update to the latest version (**v0.5.1**):
+To update to the latest version (**v0.5.3**):
 
 ```bash
 pip install --upgrade sql-dag-flow

{sql_dag_flow-0.5.2 → sql_dag_flow-0.5.4}/README.md

@@ -40,6 +40,7 @@ Specially optimized for the **Medallion Architecture** (Bronze, Silver, Gold) an
     *   Powered by **ELK (Eclipse Layout Kernel)**.
     *   Minimizes edge crossings and optimizes flow direction.
     *   Intelligent "Port" handling for cleaner connections.
+*   **Startup Configuration Selector**: Instantly resume previous sessions by selecting any `.json` configuration file found in your project directory upon launching the app.
 
 ### 🎮 Interactive Graph
 *   **Smart Context Menu**:
@@ -74,6 +75,7 @@ Specially optimized for the **Medallion Architecture** (Bronze, Silver, Gold) an
 *   **Column-Level Lineage (New in v0.4.9 🆕)**: Traces how each output column derives from source columns. Shows transformation chain (e.g., `order_timestamp ← orders_raw.order_date via CAST(... AS DATETIME)`).
 *   **SQL Syntax Validation (New in v0.4.9 🆕)**: Detects SQL parse errors and displays structured warnings with line/column references. Shows ⚠️ badge on nodes with syntax issues.
 *   **Large DAG Support & Safe Cycle Detection (New in v0.5.1 🚀)**: Optimized cycle detection algorithm prevents backend hanging and "Failed to fetch" browser errors when analyzing massive projects (50+ nodes). Employs quick DAG verifications and bounded iterator loops.
+*   **Performance Optimizations (New in v0.5.2 ⚡)**: Includes backend parsing TTL caching and frontend request deduplication to prevent server overload when refreshing large numbers of un-cached SQL files simultaneously.
 *   **Batch Hide from Toolbar**: Select multiple nodes → click "Hide" in the selection toolbar to hide them all at once.
 *   **Discovery Mode Fix**: Ghost nodes from Discovery Mode are now hidden when their connected source nodes are hidden, preventing orphan ghost nodes.
 
@@ -120,7 +122,7 @@ Install easily via `pip`:
 pip install sql-dag-flow
 ```
 
-To update to the latest version (**v0.5.1**):
+To update to the latest version (**v0.5.3**):
 
 ```bash
 pip install --upgrade sql-dag-flow

{sql_dag_flow-0.5.2 → sql_dag_flow-0.5.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "sql-dag-flow"
-version = "0.5.2"
+version = "0.5.4"
 description = "A sophisticated SQL lineage visualization tool for Medallion Architectures."
 readme = "README.md"
 requires-python = ">=3.8"

{sql_dag_flow-0.5.2 → sql_dag_flow-0.5.4}/src/sql_dag_flow/main.py

@@ -36,6 +36,24 @@ STATIC_DIR = os.path.join(BASE_DIR, "static")
 CURRENT_DIRECTORY = os.getcwd() # Default, updated by start()
 DIAGRAM_FILE = "sql_diagram.json"
 
+# Parse cache to avoid re-parsing on concurrent/rapid requests
+_parse_cache = {"key": None, "tables": None, "time": 0}
+PARSE_CACHE_TTL = 5  # seconds
+
+def _cached_parse(directory, subfolders_tuple, dialect):
+    """Parse with simple TTL cache. Prevents re-parsing on concurrent requests."""
+    cache_key = (directory, subfolders_tuple, dialect)
+    now = time.time()
+    if _parse_cache["key"] == cache_key and (now - _parse_cache["time"]) < PARSE_CACHE_TTL:
+        return _parse_cache["tables"]
+    
+    subfolders_list = list(subfolders_tuple) if subfolders_tuple else None
+    tables = parse_sql_files(directory, allowed_subfolders=subfolders_list, dialect=dialect)
+    _parse_cache["key"] = cache_key
+    _parse_cache["tables"] = tables
+    _parse_cache["time"] = now
+    return tables
+
 @app.get("/graph")
 def get_graph(dialect: str = "bigquery", discovery: bool = False, expanded_nodes: str = ""):
     """Parses SQL files in the current directory and returns graph data."""
@@ -44,7 +62,7 @@ def get_graph(dialect: str = "bigquery", discovery: bool = False, expanded_nodes
         
     exp_nodes_list = [n.strip() for n in expanded_nodes.split(",")] if expanded_nodes else []
     try:
-        tables = parse_sql_files(CURRENT_DIRECTORY, dialect=dialect)
+        tables = _cached_parse(CURRENT_DIRECTORY, None, dialect)
         nodes, edges, cycles = build_graph(tables, discovery_mode=discovery, expanded_nodes=exp_nodes_list)
         return {"nodes": nodes, "edges": edges, "cycles": cycles}
     except Exception as e:
@@ -61,8 +79,8 @@ def set_path(path_data: dict = Body(...)):
     if not path or not os.path.exists(path):
         raise HTTPException(status_code=400, detail="Directory does not exist")
     
-    
     CURRENT_DIRECTORY = path
+    _parse_cache["key"] = None  # Invalidate cache on path change
     return {"message": "Path updated", "path": CURRENT_DIRECTORY}
 
 @app.post("/scan/folders")
@@ -105,7 +123,7 @@ def get_filtered_graph(data: dict = Body(...)):
     expanded_nodes = data.get("expanded_nodes", [])
     
     try:
-        tables = parse_sql_files(CURRENT_DIRECTORY, allowed_subfolders=subfolders, dialect=dialect)
+        tables = _cached_parse(CURRENT_DIRECTORY, tuple(subfolders) if subfolders else None, dialect)
         nodes, edges, cycles = build_graph(tables, discovery_mode=discovery, expanded_nodes=expanded_nodes)
         return {"nodes": nodes, "edges": edges, "cycles": cycles}
     except Exception as e:

{sql_dag_flow-0.5.2 → sql_dag_flow-0.5.4}/src/sql_dag_flow/parser.py

@@ -650,7 +650,7 @@ def parse_sql_files(directory, allowed_subfolders=None, dialect="bigquery"):
     # ===== Column-Level Lineage =====
     # For each table, trace how each output column derives from source columns
     # Protected: skip if project is very large (>100 tables) and cap columns per table
-    MAX_LINEAGE_TABLES = 100
+    MAX_LINEAGE_TABLES = 500
     MAX_COLS_PER_TABLE = 30
     LINEAGE_TIME_BUDGET = 1.5  # seconds per table