codegraph-cli-ai 0.1.6__tar.gz → 0.1.8__tar.gz

codegraph_cli_ai-0.1.8/MANIFEST.in

@@ -0,0 +1 @@
+include README.md

codegraph_cli_ai-0.1.8/PKG-INFO

@@ -0,0 +1,225 @@
+Metadata-Version: 2.4
+Name: codegraph-cli-ai
+Version: 0.1.8
+Summary: CLI tool to analyze codebases and visualize knowledge graphs using AST
+Author: Aditya Jogdand
+License: MIT
+Project-URL: Homepage, https://github.com/AdityaJogdand/codegraph-ai
+Keywords: code-analysis,ast,graph,cli,developer-tools
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: typer>=0.9.0
+Requires-Dist: networkx>=3.0
+Requires-Dist: pyvis>=0.3.2
+
+# CodeGraph AI
+
+**CodeGraph AI** is a CLI tool that analyzes your Python codebase and visualizes it as an interactive knowledge graph.
+
+It helps developers understand:
+
+* Code structure
+* Function call relationships
+* File dependencies
+* Overall architecture
+
+---
+
+## Features
+
+* AST-based parsing of Python code
+* Function call graph generation
+* Dependency graph (imports)
+* Interactive visualization in browser
+* Focus on specific files
+* Hide external libraries (stdlib & third-party)
+* Fast CLI-based workflow
+
+---
+
+## Installation
+
+```bash
+pip install codegraph-ai
+```
+
+---
+
+## Quick Start
+
+```bash
+codegraph index
+codegraph plot
+```
+
+---
+
+## Commands
+
+### 1. Index your codebase
+
+Scan and build the graph:
+
+```bash
+codegraph index
+```
+
+Index a specific folder:
+
+```bash
+codegraph index path/to/your/project
+```
+
+---
+
+### 2. Visualize the graph
+
+```bash
+codegraph plot
+```
+
+This opens an interactive graph in your browser.
+
+---
+
+## Advanced Usage
+
+### Hide external libraries
+
+Removes standard library and third-party dependencies from the graph:
+
+```bash
+codegraph plot --hide-external
+```
+
+---
+
+### Focus on a specific file
+
+Shows only a file and its direct relationships:
+
+```bash
+codegraph plot --focus cli.py
+```
+
+---
+
+### Filter by node type
+
+Show only certain types of nodes:
+
+```bash
+codegraph plot --level file
+codegraph plot --level function
+codegraph plot --level class
+```
+
+---
+
+### Filter by edge type
+
+Show only specific relationships:
+
+```bash
+codegraph plot --edge-type calls
+codegraph plot --edge-type imports
+codegraph plot --edge-type contains
+codegraph plot --edge-type all
+```
+
+---
+
+### Combine filters
+
+```bash
+codegraph plot --focus cli.py --hide-external --edge-type calls
+```
+
+---
+
+## How It Works
+
+1. Parses Python files using AST
+2. Extracts:
+
+   * Functions
+   * Classes
+   * Imports
+   * Function calls
+3. Builds a directed knowledge graph
+4. Renders it as an interactive visualization
+
+---
+
+## Graph Semantics
+
+### Node Types
+
+| Type     | Description         |
+| -------- | ------------------- |
+| File     | Python file         |
+| Function | Function or method  |
+| Class    | Class definition    |
+| Module   | External dependency |
+
+---
+
+### Edge Types
+
+| Relation   | Meaning                         |
+| ---------- | ------------------------------- |
+| contains   | File/Class contains function    |
+| calls      | Function calls another function |
+| imports    | File imports module             |
+| defined_in | Function belongs to file        |
+
+---
+
+## Output Files
+
+After indexing:
+
+```
+.codegraph/graph.json
+```
+
+After visualization:
+
+```
+graph.html
+```
+
+---
+
+## Example Workflow
+
+```bash
+codegraph index
+codegraph plot --hide-external
+```
+
+---
+
+## Use Cases
+
+* Understand large codebases quickly
+* Visualize architecture
+* Debug dependencies
+* Explore function interactions
+* Prepare for refactoring
+
+---
+
+## Author
+
+Aditya Jogdand
+
+---
+
+## License
+
+MIT License

codegraph_cli_ai-0.1.8/README.md

@@ -0,0 +1,207 @@
+# CodeGraph AI
+
+**CodeGraph AI** is a CLI tool that analyzes your Python codebase and visualizes it as an interactive knowledge graph.
+
+It helps developers understand:
+
+* Code structure
+* Function call relationships
+* File dependencies
+* Overall architecture
+
+---
+
+## Features
+
+* AST-based parsing of Python code
+* Function call graph generation
+* Dependency graph (imports)
+* Interactive visualization in browser
+* Focus on specific files
+* Hide external libraries (stdlib & third-party)
+* Fast CLI-based workflow
+
+---
+
+## Installation
+
+```bash
+pip install codegraph-ai
+```
+
+---
+
+## Quick Start
+
+```bash
+codegraph index
+codegraph plot
+```
+
+---
+
+## Commands
+
+### 1. Index your codebase
+
+Scan and build the graph:
+
+```bash
+codegraph index
+```
+
+Index a specific folder:
+
+```bash
+codegraph index path/to/your/project
+```
+
+---
+
+### 2. Visualize the graph
+
+```bash
+codegraph plot
+```
+
+This opens an interactive graph in your browser.
+
+---
+
+## Advanced Usage
+
+### Hide external libraries
+
+Removes standard library and third-party dependencies from the graph:
+
+```bash
+codegraph plot --hide-external
+```
+
+---
+
+### Focus on a specific file
+
+Shows only a file and its direct relationships:
+
+```bash
+codegraph plot --focus cli.py
+```
+
+---
+
+### Filter by node type
+
+Show only certain types of nodes:
+
+```bash
+codegraph plot --level file
+codegraph plot --level function
+codegraph plot --level class
+```
+
+---
+
+### Filter by edge type
+
+Show only specific relationships:
+
+```bash
+codegraph plot --edge-type calls
+codegraph plot --edge-type imports
+codegraph plot --edge-type contains
+codegraph plot --edge-type all
+```
+
+---
+
+### Combine filters
+
+```bash
+codegraph plot --focus cli.py --hide-external --edge-type calls
+```
+
+---
+
+## How It Works
+
+1. Parses Python files using AST
+2. Extracts:
+
+   * Functions
+   * Classes
+   * Imports
+   * Function calls
+3. Builds a directed knowledge graph
+4. Renders it as an interactive visualization
+
+---
+
+## Graph Semantics
+
+### Node Types
+
+| Type     | Description         |
+| -------- | ------------------- |
+| File     | Python file         |
+| Function | Function or method  |
+| Class    | Class definition    |
+| Module   | External dependency |
+
+---
+
+### Edge Types
+
+| Relation   | Meaning                         |
+| ---------- | ------------------------------- |
+| contains   | File/Class contains function    |
+| calls      | Function calls another function |
+| imports    | File imports module             |
+| defined_in | Function belongs to file        |
+
+---
+
+## Output Files
+
+After indexing:
+
+```
+.codegraph/graph.json
+```
+
+After visualization:
+
+```
+graph.html
+```
+
+---
+
+## Example Workflow
+
+```bash
+codegraph index
+codegraph plot --hide-external
+```
+
+---
+
+## Use Cases
+
+* Understand large codebases quickly
+* Visualize architecture
+* Debug dependencies
+* Explore function interactions
+* Prepare for refactoring
+
+---
+
+## Author
+
+Aditya Jogdand
+
+---
+
+## License
+
+MIT License

{codegraph_cli_ai-0.1.6 → codegraph_cli_ai-0.1.8}/codegraph/cli.py

@@ -9,6 +9,7 @@ import networkx as nx
 from pathlib import Path
 from typing import Optional
 from codegraph.parsers.python_parser import PythonParser
+from codegraph.parsers.multimodal_parser import MultiModalParser
 from codegraph.graph.builder import GraphBuilder
 
 app = typer.Typer()
@@ -20,6 +21,23 @@ def main():
     pass
 
 
+IGNORE_DIRS = {
+    "venv", ".venv", "env", "bin", "Scripts",
+    ".git", "__pycache__", "node_modules", ".codegraph"
+}
+IGNORE_FILES = {"graph.json", ".DS_Store"}
+IGNORE_EXTENSIONS = {".pyc", ".log", ".pyo", ".pyd"}
+
+
+def is_virtualenv(path: Path) -> bool:
+    """Detect if a directory is a virtual environment based on its structure."""
+    return (
+        (path / "pyvenv.cfg").exists()
+        or (path / "bin" / "python").exists()
+        or (path / "Scripts" / "python.exe").exists()
+    )
+
+
 @app.command()
 def index(
     path: str = typer.Argument(".", help="Path to the repo or folder to index")
@@ -32,31 +50,81 @@ def index(
         raise typer.Exit(code=1)
 
     typer.echo(f"Indexing: {root}\n")
-    py_files = list(root.rglob("*.py"))
+    
+    # Phase A: Identify top-level custom virtualenvs
+    venv_dirs = set()
+    for item in root.iterdir():
+        if item.is_dir() and is_virtualenv(item):
+            venv_dirs.add(item)
+
+    # Phase B: Filtered Scan
+    all_files = []
+    for p in root.rglob("*"):
+        if not p.is_file():
+            continue
+            
+        # 1. Skip if any parent directory is in IGNORE_DIRS
+        if any(part in IGNORE_DIRS for part in p.parts):
+            continue
+            
+        # 2. Skip if inside a detected custom venv
+        if any(v_dir in p.parents for v_dir in venv_dirs):
+            continue
+            
+        # 3. Skip if filename is ignored
+        if p.name in IGNORE_FILES:
+            continue
+            
+        # 4. Skip if extension is ignored
+        if p.suffix.lower() in IGNORE_EXTENSIONS:
+            continue
+            
+        all_files.append(p)
+
+    py_files = [f for f in all_files if f.suffix == ".py"]
+    asset_exts = {
+        ".csv", ".json", ".db", ".sqlite",
+        ".pdf",
+        ".png", ".jpg", ".jpeg"
+    }
+    asset_files = [f for f in all_files if f.suffix.lower() in asset_exts]
 
-    if not py_files:
-        typer.echo("No Python files found.")
+    if not py_files and not asset_files:
+        typer.echo("No supported files found (everything might be ignored).")
         raise typer.Exit()
 
-    typer.echo(f"Found {len(py_files)} Python file(s)\n")
+    typer.echo(f"Found {len(py_files)} Python file(s) and {len(asset_files)} asset(s)\n")
 
     # Step 1 — Parse
-    parser = PythonParser()
+    py_parser = PythonParser()
+    mm_parser = MultiModalParser()
+    
     parsed_files = []
+    parsed_assets = []
     failed_files = []
 
+    # Parse Python files
     for filepath in py_files:
-        result = parser.parse_file(str(filepath))
+        result = py_parser.parse_file(str(filepath))
         if result.errors:
             failed_files.append((str(filepath), result.errors))
         else:
-            typer.echo(f"  ✔  {filepath.relative_to(root)}")
+            typer.echo(f"  ✔ [code]  {filepath.relative_to(root)}")
             parsed_files.append(result)
 
+    # Parse assets
+    for filepath in asset_files:
+        try:
+            asset = mm_parser.parse(str(filepath))
+            typer.echo(f"  ✔ [asset] {filepath.relative_to(root)}")
+            parsed_assets.append(asset)
+        except Exception as e:
+            failed_files.append((str(filepath), [str(e)]))
+
     # Step 2 — Build graph
     typer.echo("\nBuilding graph...")
     builder = GraphBuilder()
-    builder.build(parsed_files)
+    builder.build(parsed_files, parsed_assets)
     summary = builder.summary()
 
     # Step 3 — Save to .codegraph/graph.json
@@ -163,9 +231,13 @@ def _build_premium_html(G: nx.DiGraph) -> str:
     STYLES = {
         "file":     {"color": "#4A90E2", "shape": "diamond", "size": 28, "font_color": "#ffffff"},
         "class":    {"color": "#F5A623", "shape": "hexagon", "size": 24, "font_color": "#ffffff"},
-        "function": {"color": "#50C878", "shape": "dot", "size": 16, "font_color": "#ffffff"},
-        "method":   {"color": "#7ED6A8", "shape": "dot", "size": 14, "font_color": "#ffffff"},
+        "function": {"color": "#50C878", "shape": "dot",     "size": 16, "font_color": "#ffffff"},
+        "method":   {"color": "#7ED6A8", "shape": "dot",     "size": 14, "font_color": "#ffffff"},
         "module":   {"color": "#B0BEC5", "shape": "box",     "size": 14, "font_color": "#ffffff"},
+        "dataset":  {"color": "#FFD700", "shape": "diamond", "size": 22, "font_color": "#ffffff"},
+        "database": {"color": "#FF69B4", "shape": "database", "size": 24, "font_color": "#ffffff"},
+        "document": {"color": "#9B59B6", "shape": "diamond", "size": 24, "font_color": "#ffffff"},
+        "image":    {"color": "#5DADE2", "shape": "diamond", "size": 24, "font_color": "#ffffff"},
     }
 
     EDGE_COLORS = {
@@ -173,6 +245,8 @@ def _build_premium_html(G: nx.DiGraph) -> str:
         "calls":      "#50C878",
         "imports":    "#B0BEC5",
         "defined_in": "#E8E8E8",
+        "uses":       "#FFD700",
+        "references": "#9B59B6",
     }
 
     nodes_js = []
@@ -188,10 +262,41 @@ def _build_premium_html(G: nx.DiGraph) -> str:
 
         # Tooltip
         tooltip_parts = [f"<b>{label}</b>", f"Kind: {kind}"]
-        if attrs.get("file"):
+        if attrs.get("filename"):
+            tooltip_parts.append(f"File: {attrs['filename']}")
+        elif attrs.get("file"):
             tooltip_parts.append(f"File: {attrs['file'].replace('file:', '')}")
         if attrs.get("cls"):
             tooltip_parts.append(f"Class: {attrs['cls']}")
+        
+        # MultiModal Metadata for tooltips
+        metadata = attrs.get("metadata", {})
+        if kind == "dataset":
+            if "columns" in metadata: tooltip_parts.append(f"Columns: {', '.join(metadata['columns'])}")
+            if "keys" in metadata: tooltip_parts.append(f"Keys: {', '.join(metadata['keys'])}")
+        elif kind == "database":
+            if "tables" in metadata: tooltip_parts.append(f"Tables: {', '.join(metadata['tables'])}")
+        elif kind == "document":
+            if "num_pages" in metadata: tooltip_parts.append(f"Pages: {metadata['num_pages']}")
+            if "text_preview" in metadata: tooltip_parts.append(f"<br>Preview: <i>{metadata['text_preview']}</i>")
+        elif kind == "image":
+            if "text" in metadata and metadata["text"]: tooltip_parts.append(f"<br>OCR Text: <i>{metadata['text']}</i>")
+        
+        # Add metadata for datasets/databases
+        metadata = attrs.get("metadata", {})
+        if metadata:
+            if "columns" in metadata:
+                cols = ", ".join(metadata["columns"][:5])
+                if len(metadata["columns"]) > 5: cols += "..."
+                tooltip_parts.append(f"Columns: {cols}")
+            if "tables" in metadata:
+                tbls = ", ".join(metadata["tables"])
+                tooltip_parts.append(f"Tables: {tbls}")
+            if "keys" in metadata:
+                keys = ", ".join(metadata["keys"][:5])
+                if len(metadata["keys"]) > 5: keys += "..."
+                tooltip_parts.append(f"Keys: {keys}")
+
         if external:
             tooltip_parts.append("<i>external</i>")
         tooltip = "<br>".join(tooltip_parts)
@@ -337,10 +442,15 @@ def _build_premium_html(G: nx.DiGraph) -> str:
   <div class="legend-item"><div class="legend-dot" style="background:#50C878"></div>Function</div>
   <div class="legend-item"><div class="legend-dot" style="background:#7ED6A8"></div>Method</div>
   <div class="legend-item"><div class="legend-dot" style="background:#B0BEC5;border-radius:2px"></div>Module</div>
+  <div class="legend-item"><div class="legend-dot" style="background:#FFD700;clip-path:polygon(50% 0%, 100% 50%, 50% 100%, 0% 50%)"></div>Dataset</div>
+  <div class="legend-item"><div class="legend-dot" style="background:#FF69B4;border-radius:2px"></div>Database</div>
+  <div class="legend-item"><div class="legend-dot" style="background:#9B59B6;clip-path:polygon(50% 0%, 100% 50%, 50% 100%, 0% 50%)"></div>Document</div>
+  <div class="legend-item"><div class="legend-dot" style="background:#5DADE2;clip-path:polygon(50% 0%, 100% 50%, 50% 100%, 0% 50%)"></div>Image</div>
   <span style="font-size:11px; color:#546E7A; font-weight: 700; margin-left:12px; margin-right:4px; letter-spacing: 0.05em;">EDGES</span>
   <div class="legend-item"><div style="width:20px;height:2px;background:#4A90E2;opacity:0.6"></div>contains</div>
   <div class="legend-item"><div style="width:20px;height:2px;background:#50C878;opacity:0.6"></div>calls</div>
   <div class="legend-item"><div style="width:20px;height:1px;background:#B0BEC5;border-top:1px dashed #B0BEC5"></div>imports</div>
+  <div class="legend-item"><div style="width:20px;height:2px;background:#FFD700;opacity:0.6"></div>uses</div>
 </div>
 
 <div id="graph-container">