pdf-anonymizer-cli 0.3.2__tar.gz → 0.3.3__tar.gz

{pdf_anonymizer_cli-0.3.2 → pdf_anonymizer_cli-0.3.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pdf-anonymizer-cli
-Version: 0.3.2
+Version: 0.3.3
 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
@@ -131,3 +131,14 @@ pdf-anonymizer deanonymize \
 ```
 
 This will create a deanonymized version of the file at `data/deanonymized/document.deanonymized.md`.
+
+---
+
+## See Also
+
+- **[Main Documentation](https://leo-gan.github.io/anonymizer/)** — Full guides including the 101 course.
+- **[Core Package README](../pdf-anonymizer-core/README.md)** — Details on the underlying library.
+- **[Recipes & Common Workflows](https://leo-gan.github.io/anonymizer/project/recipes/)** — Practical CLI usage examples (profiles, batching, external workflows, etc.).
+- **[CLI Reference (full)](https://leo-gan.github.io/anonymizer/project/cli-usage/)** — Complete command reference on the docs site.
+- **[Troubleshooting](https://leo-gan.github.io/anonymizer/project/troubleshooting/)** — Help with common CLI problems.
+- **[Architecture](https://leo-gan.github.io/anonymizer/project/architecture/)** — How the CLI and core work together.

{pdf_anonymizer_cli-0.3.2 → pdf_anonymizer_cli-0.3.3}/README.md

@@ -117,4 +117,15 @@ pdf-anonymizer deanonymize \
     data/mappings/document.mapping.json
 ```
 
-This will create a deanonymized version of the file at `data/deanonymized/document.deanonymized.md`.
+This will create a deanonymized version of the file at `data/deanonymized/document.deanonymized.md`.
+
+---
+
+## See Also
+
+- **[Main Documentation](https://leo-gan.github.io/anonymizer/)** — Full guides including the 101 course.
+- **[Core Package README](../pdf-anonymizer-core/README.md)** — Details on the underlying library.
+- **[Recipes & Common Workflows](https://leo-gan.github.io/anonymizer/project/recipes/)** — Practical CLI usage examples (profiles, batching, external workflows, etc.).
+- **[CLI Reference (full)](https://leo-gan.github.io/anonymizer/project/cli-usage/)** — Complete command reference on the docs site.
+- **[Troubleshooting](https://leo-gan.github.io/anonymizer/project/troubleshooting/)** — Help with common CLI problems.
+- **[Architecture](https://leo-gan.github.io/anonymizer/project/architecture/)** — How the CLI and core work together.

{pdf_anonymizer_cli-0.3.2 → pdf_anonymizer_cli-0.3.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "pdf-anonymizer-cli"
-version = "0.3.2"
+version = "0.3.3"
 description = "CLI for a tool to anonymize PDF, Markdown, and plain text files using LLMs."
 authors = [{ name = "Leonid Ganeline", email = "leo.gan.57@gmail.com" }]
 license = { text = "MIT" }

{pdf_anonymizer_cli-0.3.2 → pdf_anonymizer_cli-0.3.3}/src/pdf_anonymizer_cli/cli.py

@@ -7,14 +7,14 @@ 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,
+    DEFAULT_LOG_FILE,
+    ConfigProfile,
     PromptEnum,
-    get_enum_value,
+    get_config_for_profile,
     get_provider_and_model_name,
 )
 from pdf_anonymizer_core.core import anonymize_file
+from pdf_anonymizer_core.llm_provider import configure_cache
 from pdf_anonymizer_core.prompts import detailed, simple
 from pdf_anonymizer_core.utils import (
     consolidate_mapping,
@@ -23,10 +23,11 @@ from pdf_anonymizer_core.utils import (
 )
 from typing_extensions import Annotated
 
+# Setup logging using log file configured in conf.py
 logging.basicConfig(
     level=logging.INFO,
     format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
-    handlers=[logging.FileHandler("app.log"), logging.StreamHandler()],
+    handlers=[logging.FileHandler(DEFAULT_LOG_FILE), logging.StreamHandler()],
 )
 
 app = typer.Typer()
@@ -53,23 +54,34 @@ def run(
             resolve_path=True,
         ),
     ],
+    config_profile: Annotated[
+        ConfigProfile,
+        typer.Option(
+            "--config-profile",
+            "-p",
+            help="The configuration profile to use (best-quality, best-speed, best-cost).",
+            case_sensitive=False,
+        ),
+    ] = ConfigProfile.BEST_SPEED,
     characters_to_anonymize: Annotated[
-        int,
-        typer.Option(help="Number of characters to send for anonymization in one go."),
-    ] = DEFAULT_CHARACTERS_TO_ANONYMIZE,
+        Optional[int],
+        typer.Option(
+            help="Override number of characters to send for anonymization in one go (chunk size)."
+        ),
+    ] = None,
     prompt_name: Annotated[
-        PromptEnum,
+        Optional[PromptEnum],
         typer.Option(
-            help="The name of the prompt to use for anonymization.",
+            help="Override prompt template to use for anonymization.",
             case_sensitive=False,
         ),
-    ] = get_enum_value(PromptEnum, DEFAULT_PROMPT_NAME),
+    ] = None,
     model_name: Annotated[
-        str,
+        Optional[str],
         typer.Option(
-            help="The name of the model to use for anonymization (supports enum values or 'provider/model').",
+            help="Override the language model to use for anonymization.",
         ),
-    ] = DEFAULT_MODEL_NAME,
+    ] = None,
     anonymized_entities: Annotated[
         Optional[Path],
         typer.Option(
@@ -86,35 +98,45 @@ def run(
 ) -> 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()
 
-    provider_name, _ = get_provider_and_model_name(model_name)
+    # Get configuration based on profile and optional user overrides
+    config = get_config_for_profile(
+        profile=config_profile,
+        model_name=model_name,
+        prompt_name=prompt_name,
+        chunk_size=characters_to_anonymize,
+    )
+
+    # Configure LLM caching with values from configuration
+    configure_cache(
+        enabled=config.enable_cache,
+        cache_dir=config.cache_dir,
+        cache_file=config.cache_file,
+    )
+
+    provider_name, _ = get_provider_and_model_name(config.model_name)
     if provider_name == "google":
-        if "gemini" in model_name and not os.getenv("GOOGLE_API_KEY"):
+        if "gemini" in config.model_name 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"Using configuration profile: {config_profile.value}")
     logging.info(f"  --file-paths: {file_paths}")
-    logging.info(f"  --characters-to-anonymize: {characters_to_anonymize}")
-    logging.info(f"  --model-name: {model_name}")
+    logging.info(f"  --chunk-size: {config.chunk_size}")
+    logging.info(f"  --chunk-overlap: {config.chunk_overlap}")
+    logging.info(f"  --model-name: {config.model_name}")
 
     # Select the appropriate prompt template
     prompt_templates: Dict[str, str] = {
-        PromptEnum.simple: simple.prompt_template,
-        PromptEnum.detailed: detailed.prompt_template,
+        PromptEnum.simple.value: simple.prompt_template,
+        PromptEnum.detailed.value: detailed.prompt_template,
     }
-    prompt_template: str = prompt_templates[prompt_name]
-    logging.info(f"  --prompt-name: {prompt_name.value}")
+    prompt_template: str = prompt_templates[config.prompt_name]
+    logging.info(f"  --prompt-name: {config.prompt_name}")
 
     entities_to_anonymize = None
     if anonymized_entities:
@@ -128,11 +150,16 @@ def run(
         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,
-            entities_to_anonymize,
+            file_path=str(file_path),
+            characters_to_anonymize=config.chunk_size,
+            prompt_template=prompt_template,
+            model_name=config.model_name,
+            anonymized_entities=entities_to_anonymize,
+            chunk_overlap=config.chunk_overlap,
+            regex_patterns=config.regex_patterns,
+            max_retries=config.max_retries,
+            base_retry_delay=config.base_retry_delay,
+            max_retry_delay=config.max_retry_delay,
         )
 
         if full_anonymized_text and final_mapping:
@@ -182,10 +209,6 @@ def deanonymize(
 ) -> 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(

{pdf_anonymizer_cli-0.3.2 → pdf_anonymizer_cli-0.3.3}/src/pdf_anonymizer_cli.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pdf-anonymizer-cli
-Version: 0.3.2
+Version: 0.3.3
 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
@@ -131,3 +131,14 @@ pdf-anonymizer deanonymize \
 ```
 
 This will create a deanonymized version of the file at `data/deanonymized/document.deanonymized.md`.
+
+---
+
+## See Also
+
+- **[Main Documentation](https://leo-gan.github.io/anonymizer/)** — Full guides including the 101 course.
+- **[Core Package README](../pdf-anonymizer-core/README.md)** — Details on the underlying library.
+- **[Recipes & Common Workflows](https://leo-gan.github.io/anonymizer/project/recipes/)** — Practical CLI usage examples (profiles, batching, external workflows, etc.).
+- **[CLI Reference (full)](https://leo-gan.github.io/anonymizer/project/cli-usage/)** — Complete command reference on the docs site.
+- **[Troubleshooting](https://leo-gan.github.io/anonymizer/project/troubleshooting/)** — Help with common CLI problems.
+- **[Architecture](https://leo-gan.github.io/anonymizer/project/architecture/)** — How the CLI and core work together.