codeanalyzer-python 0.1.2__tar.gz → 0.1.4__tar.gz

{codeanalyzer_python-0.1.2 → codeanalyzer_python-0.1.4}/.gitignore

@@ -175,4 +175,7 @@ cython_debug/
 
 # Project-specific files
 .codeanalyzer
-.vscode/
+.vscode/
+
+# UV
+uv.lock

{codeanalyzer_python-0.1.2 → codeanalyzer_python-0.1.4}/PKG-INFO

@@ -1,42 +1,38 @@
 Metadata-Version: 2.4
 Name: codeanalyzer-python
-Version: 0.1.2
+Version: 0.1.4
 Summary: Static Analysis on Python source code using Jedi, CodeQL and Treesitter.
 Author-email: Rahul Krishna <i.m.ralk@gmail.com>
 License-File: LICENSE
 License-File: NOTICE
 Requires-Python: >=3.12
-Requires-Dist: asteroid>=0.7.0
 Requires-Dist: astor>=0.8.1
 Requires-Dist: jedi>=0.19.2
 Requires-Dist: loguru>=0.7.3
+Requires-Dist: msgpack>=1.1.1
 Requires-Dist: networkx>=3.5
-Requires-Dist: pandas>=2.3.0
+Requires-Dist: pandas>=2.3.1
 Requires-Dist: pydantic>=2.11.7
 Requires-Dist: requests>=2.32.4
 Requires-Dist: rich>=14.0.0
-Requires-Dist: ruff>=0.12.2
-Requires-Dist: toml>=0.10.2
 Requires-Dist: typer>=0.16.0
 Description-Content-Type: text/markdown
 
-![logo](./docs/assets/logo.png)
+![logo](https://github.com/codellm-devkit/codeanalyzer-python/blob/main/docs/assets/logo.png?raw=true)
 
-Python Static Analysis Backend for CLDK
+# A Python Static Analysis Toolkit (and Library)
 
 A comprehensive static analysis tool for Python source code that provides symbol table generation, call graph analysis, and semantic analysis using Jedi, CodeQL, and Tree-sitter.
 
 ## Installation
 
-This project uses [uv](https://docs.astral.sh/uv/) for dependency management.
+```bash
+pip install codeanalyzer-python
+```
 
 ### Prerequisites
 
-- [uv](https://docs.astral.sh/uv/getting-started/installation/) installed
-- Python 3.12 or higher. You can use `uv` to install Python if it's not already installed:
-  ```bash
-  uv python install 3.12
-  ```
+- Python 3.12 or higher
 
 #### System Package Requirements
 
@@ -78,20 +74,6 @@ pyenv global 3.12.0   # or pyenv local 3.12.0 for project-specific
 
 > **Note:** These packages are required as the tool uses Python's built-in `venv` module to create isolated environments for analysis.
 
-### Setup
-
-1. Clone the repository:
-   ```bash
-   git clone https://github.com/codellm-devkit/codeanalyzer-python
-   cd codeanalyzer-python
-   ```
-
-2. Install dependencies using uv:
-   ```bash
-   uv sync --all-groups
-   ```
-   This will install all dependencies including development and test dependencies.
-
 ## Usage
 
 The codeanalyzer provides a command-line interface for performing static analysis on Python projects.
@@ -99,15 +81,15 @@ The codeanalyzer provides a command-line interface for performing static analysi
 ### Basic Usage
 
 ```bash
-uv run codeanalyzer --input /path/to/python/project
+codeanalyzer --input /path/to/python/project
 ```
 
 ### Command Line Options
 
-To view the available options and commands, run `uv run codeanalyzer --help`. You should see output similar to the following:
+To view the available options and commands, run `codeanalyzer --help`. You should see output similar to the following:
 
 ```bash
-❯ uv run codeanalyzer --help
+❯ codeanalyzer --help
 
  Usage: codeanalyzer [OPTIONS] COMMAND [ARGS]...
 
@@ -131,38 +113,38 @@ To view the available options and commands, run `uv run codeanalyzer --help`. Yo
 
 1. **Basic analysis with symbol table:**
    ```bash
-   uv run codeanalyzer --input ./my-python-project
+   codeanalyzer --input ./my-python-project
    ```
 
    This will print the symbol table to stdout in JSON format to the standard output. If you want to save the output, you can use the `--output` option.
 
    ```bash
-   uv run codeanalyzer --input ./my-python-project --output /path/to/analysis-results
+   codeanalyzer --input ./my-python-project --output /path/to/analysis-results
    ```
 
    Now, you can find the analysis results in `analysis.json` in the specified directory.
 
 2. **Toggle analysis levels with `--analysis-level`:**
    ```bash
-   uv run codeanalyzer --input ./my-python-project --analysis-level 1 # Symbol table only
+   codeanalyzer --input ./my-python-project --analysis-level 1 # Symbol table only
    ```
    Call graph analysis can be enabled by setting the level to `2`:
    ```bash
-   uv run codeanalyzer --input ./my-python-project --analysis-level 2 # Symbol table + Call graph
+   codeanalyzer --input ./my-python-project --analysis-level 2 # Symbol table + Call graph
    ```
    ***Note: The `--analysis-level=2` is not yet implemented in this version.***
 
 3. **Analysis with CodeQL enabled:**
    ```bash
-   uv run codeanalyzer --input ./my-python-project --codeql
+   codeanalyzer --input ./my-python-project --codeql
    ```
-    This will perform CodeQL-based analysis in addition to the standard symbol table generation. 
-    
+    This will perform CodeQL-based analysis in addition to the standard symbol table generation.
+
     ***Note: Not yet fully implemented. Please refrain from using this option until further notice.***
 
 4. **Eager analysis with custom cache directory:**
    ```bash
-   uv run codeanalyzer --input ./my-python-project --eager --cache-dir /path/to/custom-cache
+   codeanalyzer --input ./my-python-project --eager --cache-dir /path/to/custom-cache
    ```
     This will rebuild the analysis cache at every run and store it in `/path/to/custom-cache/.codeanalyzer`. The cache will be cleared by default after analysis unless you specify `--keep-cache`.
 
@@ -170,7 +152,7 @@ To view the available options and commands, run `uv run codeanalyzer --help`. Yo
 
 5. **Quiet mode (minimal output):**
    ```bash
-   uv run codeanalyzer --input /path/to/my-python-project --quiet
+   codeanalyzer --input /path/to/my-python-project --quiet
    ```
 
 ### Output
@@ -179,10 +161,36 @@ By default, analysis results are printed to stdout in JSON format. When using th
 
 ## Development
 
+This project uses [uv](https://docs.astral.sh/uv/) for dependency management during development.
+
+### Development Setup
+
+1. Install [uv](https://docs.astral.sh/uv/getting-started/installation/)
+
+2. Clone the repository:
+   ```bash
+   git clone https://github.com/codellm-devkit/codeanalyzer-python
+   cd codeanalyzer-python
+   ```
+
+3. Install dependencies using uv:
+   ```bash
+   uv sync --all-groups
+   ```
+   This will install all dependencies including development and test dependencies.
+
+### Running from Source
+
+When developing, you can run the tool directly from source:
+
+```bash
+uv run codeanalyzer --input /path/to/python/project
+```
+
 ### Running Tests
 
 ```bash
-uv run pytest --pspec -s 
+uv run pytest --pspec -s
 ```
 
 ### Development Dependencies

{codeanalyzer_python-0.1.2 → codeanalyzer_python-0.1.4}/README.md

@@ -1,20 +1,18 @@
-![logo](./docs/assets/logo.png)
+![logo](https://github.com/codellm-devkit/codeanalyzer-python/blob/main/docs/assets/logo.png?raw=true)
 
-Python Static Analysis Backend for CLDK
+# A Python Static Analysis Toolkit (and Library)
 
 A comprehensive static analysis tool for Python source code that provides symbol table generation, call graph analysis, and semantic analysis using Jedi, CodeQL, and Tree-sitter.
 
 ## Installation
 
-This project uses [uv](https://docs.astral.sh/uv/) for dependency management.
+```bash
+pip install codeanalyzer-python
+```
 
 ### Prerequisites
 
-- [uv](https://docs.astral.sh/uv/getting-started/installation/) installed
-- Python 3.12 or higher. You can use `uv` to install Python if it's not already installed:
-  ```bash
-  uv python install 3.12
-  ```
+- Python 3.12 or higher
 
 #### System Package Requirements
 
@@ -56,20 +54,6 @@ pyenv global 3.12.0   # or pyenv local 3.12.0 for project-specific
 
 > **Note:** These packages are required as the tool uses Python's built-in `venv` module to create isolated environments for analysis.
 
-### Setup
-
-1. Clone the repository:
-   ```bash
-   git clone https://github.com/codellm-devkit/codeanalyzer-python
-   cd codeanalyzer-python
-   ```
-
-2. Install dependencies using uv:
-   ```bash
-   uv sync --all-groups
-   ```
-   This will install all dependencies including development and test dependencies.
-
 ## Usage
 
 The codeanalyzer provides a command-line interface for performing static analysis on Python projects.
@@ -77,15 +61,15 @@ The codeanalyzer provides a command-line interface for performing static analysi
 ### Basic Usage
 
 ```bash
-uv run codeanalyzer --input /path/to/python/project
+codeanalyzer --input /path/to/python/project
 ```
 
 ### Command Line Options
 
-To view the available options and commands, run `uv run codeanalyzer --help`. You should see output similar to the following:
+To view the available options and commands, run `codeanalyzer --help`. You should see output similar to the following:
 
 ```bash
-❯ uv run codeanalyzer --help
+❯ codeanalyzer --help
 
  Usage: codeanalyzer [OPTIONS] COMMAND [ARGS]...
 
@@ -109,38 +93,38 @@ To view the available options and commands, run `uv run codeanalyzer --help`. Yo
 
 1. **Basic analysis with symbol table:**
    ```bash
-   uv run codeanalyzer --input ./my-python-project
+   codeanalyzer --input ./my-python-project
    ```
 
    This will print the symbol table to stdout in JSON format to the standard output. If you want to save the output, you can use the `--output` option.
 
    ```bash
-   uv run codeanalyzer --input ./my-python-project --output /path/to/analysis-results
+   codeanalyzer --input ./my-python-project --output /path/to/analysis-results
    ```
 
    Now, you can find the analysis results in `analysis.json` in the specified directory.
 
 2. **Toggle analysis levels with `--analysis-level`:**
    ```bash
-   uv run codeanalyzer --input ./my-python-project --analysis-level 1 # Symbol table only
+   codeanalyzer --input ./my-python-project --analysis-level 1 # Symbol table only
    ```
    Call graph analysis can be enabled by setting the level to `2`:
    ```bash
-   uv run codeanalyzer --input ./my-python-project --analysis-level 2 # Symbol table + Call graph
+   codeanalyzer --input ./my-python-project --analysis-level 2 # Symbol table + Call graph
    ```
    ***Note: The `--analysis-level=2` is not yet implemented in this version.***
 
 3. **Analysis with CodeQL enabled:**
    ```bash
-   uv run codeanalyzer --input ./my-python-project --codeql
+   codeanalyzer --input ./my-python-project --codeql
    ```
-    This will perform CodeQL-based analysis in addition to the standard symbol table generation. 
-    
+    This will perform CodeQL-based analysis in addition to the standard symbol table generation.
+
     ***Note: Not yet fully implemented. Please refrain from using this option until further notice.***
 
 4. **Eager analysis with custom cache directory:**
    ```bash
-   uv run codeanalyzer --input ./my-python-project --eager --cache-dir /path/to/custom-cache
+   codeanalyzer --input ./my-python-project --eager --cache-dir /path/to/custom-cache
    ```
     This will rebuild the analysis cache at every run and store it in `/path/to/custom-cache/.codeanalyzer`. The cache will be cleared by default after analysis unless you specify `--keep-cache`.
 
@@ -148,7 +132,7 @@ To view the available options and commands, run `uv run codeanalyzer --help`. Yo
 
 5. **Quiet mode (minimal output):**
    ```bash
-   uv run codeanalyzer --input /path/to/my-python-project --quiet
+   codeanalyzer --input /path/to/my-python-project --quiet
    ```
 
 ### Output
@@ -157,10 +141,36 @@ By default, analysis results are printed to stdout in JSON format. When using th
 
 ## Development
 
+This project uses [uv](https://docs.astral.sh/uv/) for dependency management during development.
+
+### Development Setup
+
+1. Install [uv](https://docs.astral.sh/uv/getting-started/installation/)
+
+2. Clone the repository:
+   ```bash
+   git clone https://github.com/codellm-devkit/codeanalyzer-python
+   cd codeanalyzer-python
+   ```
+
+3. Install dependencies using uv:
+   ```bash
+   uv sync --all-groups
+   ```
+   This will install all dependencies including development and test dependencies.
+
+### Running from Source
+
+When developing, you can run the tool directly from source:
+
+```bash
+uv run codeanalyzer --input /path/to/python/project
+```
+
 ### Running Tests
 
 ```bash
-uv run pytest --pspec -s 
+uv run pytest --pspec -s
 ```
 
 ### Development Dependencies

{codeanalyzer_python-0.1.2 → codeanalyzer_python-0.1.4}/codeanalyzer/__main__.py

@@ -1,11 +1,16 @@
-from contextlib import nullcontext
-import sys
-import typer
-from typing import Optional, Annotated
 from pathlib import Path
-from codeanalyzer.utils import _set_log_level
-from codeanalyzer.utils import logger
+from typing import Annotated, Optional
+from enum import Enum
+
+import typer
+
 from codeanalyzer.core import AnalyzerCore
+from codeanalyzer.utils import _set_log_level, logger
+
+
+class OutputFormat(str, Enum):
+    JSON = "json"
+    MSGPACK = "msgpack"
 
 
 def main(
@@ -16,6 +21,15 @@ def main(
         Optional[Path],
         typer.Option("-o", "--output", help="Output directory for artifacts."),
     ] = None,
+    format: Annotated[
+        OutputFormat,
+        typer.Option(
+            "-f",
+            "--format",
+            help="Output format: json or msgpack.",
+            case_sensitive=False,
+        ),
+    ] = OutputFormat.JSON,
     analysis_level: Annotated[
         int,
         typer.Option("-a", "--analysis-level", help="1: symbol table, 2: call graph."),
@@ -57,16 +71,40 @@ def main(
         input, analysis_level, using_codeql, rebuild_analysis, cache_dir, clear_cache
     ) as analyzer:
         artifacts = analyzer.analyze()
-        print_stream = sys.stdout
-        stream_context = nullcontext(print_stream)
 
-        if output is not None:
+        # Handle output based on format
+        if output is None:
+            # Output to stdout (only for JSON)
+            if format == OutputFormat.JSON:
+                print(artifacts.model_dump_json(separators=(",", ":")))
+            else:
+                logger.error(
+                    f"Format '{format.value}' requires an output directory (use -o/--output)"
+                )
+                raise typer.Exit(code=1)
+        else:
+            # Output to file
             output.mkdir(parents=True, exist_ok=True)
-            output_file = output / "analysis.json"
-            stream_context = output_file.open("w")
+            _write_output(artifacts, output, format)
+
+
+def _write_output(artifacts, output_dir: Path, format: OutputFormat):
+    """Write artifacts to file in the specified format."""
+    if format == OutputFormat.JSON:
+        output_file = output_dir / "analysis.json"
+        with output_file.open("w") as f:
+            f.write(artifacts.model_dump_json(separators=(",", ":")))
+        logger.info(f"Analysis saved to {output_file}")
 
-        with stream_context as f:
-            print(artifacts.model_dump_json(indent=4), file=f)
+    elif format == OutputFormat.MSGPACK:
+        output_file = output_dir / "analysis.msgpack"
+        msgpack_data = artifacts.to_msgpack_bytes()
+        with output_file.open("wb") as f:
+            f.write(msgpack_data)
+        logger.info(f"Analysis saved to {output_file}")
+        logger.info(
+            f"Compression ratio: {artifacts.get_compression_ratio():.1%} of JSON size"
+        )
 
 
 app = typer.Typer(

{codeanalyzer_python-0.1.2 → codeanalyzer_python-0.1.4}/codeanalyzer/core.py

@@ -1,19 +1,16 @@
 import hashlib
 import os
-from pdb import set_trace
 import shutil
 import subprocess
-from pathlib import Path
 import sys
-from typing import Any, Dict, Union, Optional
-from codeanalyzer.utils import logger
+from pathlib import Path
+from typing import Any, Dict, Optional, Union
 
 from codeanalyzer.schema.py_schema import PyApplication, PyModule
 from codeanalyzer.semantic_analysis.codeql import CodeQLLoader
-from codeanalyzer.semantic_analysis.codeql.codeql_exceptions import (
-    CodeQLExceptions,
-)
+from codeanalyzer.semantic_analysis.codeql.codeql_exceptions import CodeQLExceptions
 from codeanalyzer.syntactic_analysis.symbol_table_builder import SymbolTableBuilder
+from codeanalyzer.utils import logger
 
 
 class AnalyzerCore:
@@ -290,11 +287,7 @@ class AnalyzerCore:
 
     def analyze(self) -> PyApplication:
         """Return the path to the CodeQL database."""
-        return (
-            PyApplication.builder()
-            .with_symbol_table(self._build_symbol_table())
-            .build()
-        )
+        return PyApplication.builder().symbol_table(self._build_symbol_table()).build()
 
     def _compute_checksum(self, root: Path) -> str:
         """Compute SHA256 checksum of all Python source files in a project directory. If somethings changes, the

{codeanalyzer_python-0.1.2 → codeanalyzer_python-0.1.4}/codeanalyzer/schema/__init__.py

@@ -1,13 +1,13 @@
 from .py_schema import (
     PyApplication,
-    PyImport,
+    PyCallable,
+    PyCallableParameter,
+    PyClass,
+    PyClassAttribute,
     PyComment,
+    PyImport,
     PyModule,
-    PyClass,
     PyVariableDeclaration,
-    PyCallable,
-    PyClassAttribute,
-    PyCallableParameter
 )
 
 __all__ = [
@@ -19,5 +19,5 @@ __all__ = [
     "PyVariableDeclaration",
     "PyCallable",
     "PyClassAttribute",
-    "PyCallableParameter"
+    "PyCallableParameter",
 ]