pdf-anonymizer-cli 0.3.0__py3-none-any.whl

pdf_anonymizer_cli/cli.py

@@ -0,0 +1,201 @@
+import logging
+import os
+import sys
+from pathlib import Path
+from typing import Dict, List, Optional
+
+import typer
+from dotenv import load_dotenv
+from pdf_anonymizer_core.conf import (
+    DEFAULT_CHARACTERS_TO_ANONYMIZE,
+    DEFAULT_MODEL_NAME,
+    DEFAULT_PROMPT_NAME,
+    ModelName,
+    ModelProvider,
+    PromptEnum,
+    get_enum_value,
+)
+from pdf_anonymizer_core.core import anonymize_file
+from pdf_anonymizer_core.prompts import detailed, simple
+from pdf_anonymizer_core.utils import (
+    consolidate_mapping,
+    deanonymize_file,
+    save_results,
+)
+from typing_extensions import Annotated
+
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
+    handlers=[logging.FileHandler("app.log"), logging.StreamHandler()],
+)
+
+app = typer.Typer()
+
+
+def load_environment() -> None:
+    """Load environment variables from .env file if it exists."""
+    env_path = Path(__file__).parent.parent.parent / ".env"
+    if env_path.exists():
+        load_dotenv(env_path)
+
+
+@app.command()
+def run(
+    file_paths: Annotated[
+        List[Path],
+        typer.Argument(
+            help="A list of paths to files to anonymize.",
+            exists=True,
+            file_okay=True,
+            dir_okay=False,
+            writable=False,
+            readable=True,
+            resolve_path=True,
+        ),
+    ],
+    characters_to_anonymize: Annotated[
+        int,
+        typer.Option(help="Number of characters to send for anonymization in one go."),
+    ] = DEFAULT_CHARACTERS_TO_ANONYMIZE,
+    prompt_name: Annotated[
+        PromptEnum,
+        typer.Option(
+            help="The name of the prompt to use for anonymization.",
+            case_sensitive=False,
+        ),
+    ] = get_enum_value(PromptEnum, DEFAULT_PROMPT_NAME),
+    model_name: Annotated[
+        ModelName,
+        typer.Option(
+            help="The name of the model to use for anonymization.",
+            case_sensitive=False,
+        ),
+    ] = get_enum_value(ModelName, DEFAULT_MODEL_NAME),
+    anonymized_entities: Annotated[
+        Optional[Path],
+        typer.Option(
+            "--anonymized-entities",
+            help="A file with a list of entities to anonymize.",
+            exists=True,
+            file_okay=True,
+            dir_okay=False,
+            writable=False,
+            readable=True,
+            resolve_path=True,
+        ),
+    ] = None,
+) -> None:
+    """
+    Anonymize one or more files by replacing PII with anonymized placeholders.
+
+    Args:
+        file_paths: List of paths to files to process.
+        characters_to_anonymize: Number of characters to process in each chunk.
+        prompt_name: The prompt template to use for anonymization.
+        model_name: The language model to use for anonymization.
+        anonymized_entities: A file with a list of entities to anonymize.
+    """
+    load_environment()
+
+    if model_name.provider == ModelProvider.GOOGLE:
+        if "gemini" in model_name.value and not os.getenv("GOOGLE_API_KEY"):
+            logging.error(
+                "Error: GOOGLE_API_KEY not found. Please set it in the .env file."
+            )
+            sys.exit(1)
+
+    logging.info(f"  --file-paths: {file_paths}")
+    logging.info(f"  --characters-to-anonymize: {characters_to_anonymize}")
+    logging.info(f"  --model-name: {model_name.value}")
+
+    # Select the appropriate prompt template
+    prompt_templates: Dict[str, str] = {
+        PromptEnum.simple: simple.prompt_template,
+        PromptEnum.detailed: detailed.prompt_template,
+    }
+    prompt_template: str = prompt_templates[prompt_name]
+    logging.info(f"  --prompt-name: {prompt_name.value}")
+
+    entities_to_anonymize = None
+    if anonymized_entities:
+        with open(anonymized_entities, "r") as f:
+            entities_to_anonymize = [line.strip() for line in f.readlines()]
+        logging.info(f"  --anonymized-entities: {entities_to_anonymize}")
+
+    logging.info(f"Found {len(file_paths)} file(s) to process.")
+
+    for i, file_path in enumerate(file_paths, 1):
+        logging.info("=" * 40)
+        logging.info(f"Processing file {i}/{len(file_paths)}: {file_path}")
+        full_anonymized_text, final_mapping = anonymize_file(
+            str(file_path),
+            characters_to_anonymize,
+            prompt_template,
+            model_name.value,
+            entities_to_anonymize,
+        )
+
+        if full_anonymized_text and final_mapping:
+            # The mapping from anonymize_file is original -> placeholder.
+            # We will standardize on placeholder -> original for subsequent steps.
+            placeholder_to_original = {v: k for k, v in final_mapping.items()}
+
+            logging.info("Consolidating mapping...")
+            full_anonymized_text, consolidated_placeholder_map = consolidate_mapping(
+                full_anonymized_text, placeholder_to_original
+            )
+
+            anonymized_output_file, mapping_file = save_results(
+                full_anonymized_text, consolidated_placeholder_map, str(file_path)
+            )
+            logging.info(f"Anonymization for {file_path} complete!")
+            logging.info(f"Anonymized text saved into '{anonymized_output_file}'")
+            logging.info(f"Mapping vocabulary saved into '{mapping_file}'")
+
+
+@app.command()
+def deanonymize(
+    anonymized_file: Annotated[
+        Path,
+        typer.Argument(
+            help="Path to the anonymized file.",
+            exists=True,
+            file_okay=True,
+            dir_okay=False,
+            writable=False,
+            readable=True,
+            resolve_path=True,
+        ),
+    ],
+    mapping_file: Annotated[
+        Path,
+        typer.Argument(
+            help="Path to the mapping file.",
+            exists=True,
+            file_okay=True,
+            dir_okay=False,
+            writable=False,
+            readable=True,
+            resolve_path=True,
+        ),
+    ],
+) -> None:
+    """
+    Deanonymize a file using a mapping file.
+
+    Args:
+        anonymized_file: Path to the anonymized file.
+        mapping_file: Path to the mapping file.
+    """
+    logging.info(f"Deanonymizing '{anonymized_file}' using '{mapping_file}'")
+    deanonymized_output_file, stats_file = deanonymize_file(
+        str(anonymized_file), str(mapping_file)
+    )
+    logging.info("Deanonymization complete!")
+    logging.info(f"Deanonymized text saved into '{deanonymized_output_file}'")
+    logging.info(f"Deanonymization statistics saved into '{stats_file}'")
+
+
+if __name__ == "__main__":
+    app()

pdf_anonymizer_cli/main.py

@@ -0,0 +1,4 @@
+from pdf_anonymizer_cli.cli import app
+
+if __name__ == "__main__":
+    app()

pdf_anonymizer_cli-0.3.0.dist-info/METADATA

@@ -0,0 +1,100 @@
+Metadata-Version: 2.4
+Name: pdf-anonymizer-cli
+Version: 0.3.0
+Summary: CLI for a tool to anonymize PDF, Markdown, and plain text files using LLMs.
+Author-email: Leonid Ganeline <leo.gan.57@gmail.com>
+License: MIT
+Project-URL: repository, https://github.com/leo-gan/anonymizer
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: typer
+Requires-Dist: rich
+Requires-Dist: pdf-anonymizer-core
+
+# PDF Anonymizer CLI
+
+A command-line interface for anonymizing PDF, Markdown, and plain text files using LLMs.
+
+## Installation
+
+This project uses `uv` and is structured as a monorepo. The dependencies for the CLI and its core library are managed at the root of the project.
+
+1.  **Install `uv`**: Follow the [official installation instructions](https://astral.sh/docs/uv#installation).
+2.  **Install dependencies from the repository root**:
+    ```bash
+    # From the repository root
+    uv sync
+    ```
+    This installs the `pdf-anonymizer` executable.
+
+## Environment Variables
+
+The CLI will automatically load a `.env` file from the current directory or any parent directory. For consistency, it's recommended to place a single `.env` file at the root of the repository.
+
+- `GOOGLE_API_KEY`: Required when using Google's Gemini models.
+- `OLLAMA_HOST`: Optional, defaults to `http://localhost:11434` when using local Ollama models.
+
+Example `.env` file:
+```env
+GOOGLE_API_KEY="YOUR_API_KEY_HERE"
+```
+
+## Usage
+
+### Anonymize
+
+The `run` command anonymizes one or more files.
+
+```bash
+pdf-anonymizer run FILE_PATH [FILE_PATH ...] \
+  [--characters-to-anonymize INTEGER] \
+  [--prompt-name {simple|detailed}] \
+  [--model-name TEXT] \
+  [--anonymized-entities PATH]
+```
+
+**Arguments**:
+- `FILE_PATH`: Path to one or several PDF, Markdown, or text files for anonymization.
+
+**Options**:
+- `--characters-to-anonymize INTEGER`: Number of characters to process in each chunk (default: `100000`).
+- `--prompt-name [simple|detailed]`: The prompt template to use (default: `detailed`).
+- `--model-name TEXT`: The language model to use.
+- `--anonymized-entities PATH`: Path to a file with a list of entities to anonymize.
+
+**Models**:
+- **Google**: `gemini-2.5-pro`, `gemini-2.5-flash` (default), `gemini-2.5-flash-lite`.
+- **Ollama**: `gemma:7b`, `phi4-mini`.
+
+### Examples
+
+**Basic anonymization**:
+```bash
+pdf-anonymizer run document.pdf
+```
+
+**Custom model and prompt**:
+```bash
+pdf-anonymizer run notes.md --model-name phi4-mini --prompt-name simple
+```
+
+### Deanonymize
+
+The `deanonymize` command reverts anonymization using a mapping file.
+
+```bash
+pdf-anonymizer deanonymize ANONYMIZED_FILE MAPPING_FILE
+```
+
+**Arguments**:
+- `ANONYMIZED_FILE`: Path to the anonymized text file.
+- `MAPPING_FILE`: Path to the JSON mapping file.
+
+**Example**:
+```bash
+pdf-anonymizer deanonymize \
+    data/anonymized/document.anonymized.md \
+    data/mappings/document.mapping.json
+```
+
+This will create a deanonymized version of the file at `data/deanonymized/document.deanonymized.md`.

pdf_anonymizer_cli-0.3.0.dist-info/RECORD

@@ -0,0 +1,8 @@
+pdf_anonymizer_cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+pdf_anonymizer_cli/cli.py,sha256=4UGhtVMoJf6eCB3_uX7iLl1yGNJ2bbllx47AP-6uCvA,6520
+pdf_anonymizer_cli/main.py,sha256=Mt7A2eMn_VBHS9Ys0j9Op5sQ3g9qglzBFOIySYYWAWk,77
+pdf_anonymizer_cli-0.3.0.dist-info/METADATA,sha256=vMaZmpDHH3btOxE21OQQ2DsSDdLKU5tjduQE7QOuAeE,2989
+pdf_anonymizer_cli-0.3.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+pdf_anonymizer_cli-0.3.0.dist-info/entry_points.txt,sha256=jy60k1AqhUvt_At4lCoNmyYE1_xPb8rCeXNxPDBqW9E,62
+pdf_anonymizer_cli-0.3.0.dist-info/top_level.txt,sha256=kkJTXhriYdwOxJRultk1V1CfPL-i0AmIBOPUNGm3-Ys,19
+pdf_anonymizer_cli-0.3.0.dist-info/RECORD,,

pdf_anonymizer_cli-0.3.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (80.9.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

pdf_anonymizer_cli-0.3.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+pdf-anonymizer = pdf_anonymizer_cli.cli:app

pdf_anonymizer_cli-0.3.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+pdf_anonymizer_cli