pdf-anonymizer-api 0.29.0__tar.gz

pdf_anonymizer_api-0.29.0/PKG-INFO

@@ -0,0 +1,29 @@
+Metadata-Version: 2.4
+Name: pdf-anonymizer-api
+Version: 0.29.0
+Summary: Local HTTP service for pdf-anonymizer-core. No authentication.
+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: pdf-anonymizer-core>=0.29.0
+Requires-Dist: fastapi>=0.115
+Requires-Dist: uvicorn[standard]>=0.30
+
+# PDF Anonymizer HTTP service
+
+A thin FastAPI wrapper around `pdf-anonymizer-core`. It does **not** depend on the CLI. There is no authentication.
+
+```bash
+pip install pdf-anonymizer-api
+pdf-anonymizer-api --host 127.0.0.1 --port 8000
+```
+
+Docker files live in this package. From the repository root:
+
+```bash
+docker compose -f packages/pdf-anonymizer-api/docker-compose.yml up --build
+```
+
+Docs: [HTTP service and Docker](https://leo-gan.github.io/anonymizer/project/http-service/).

pdf_anonymizer_api-0.29.0/README.md

@@ -0,0 +1,16 @@
+# PDF Anonymizer HTTP service
+
+A thin FastAPI wrapper around `pdf-anonymizer-core`. It does **not** depend on the CLI. There is no authentication.
+
+```bash
+pip install pdf-anonymizer-api
+pdf-anonymizer-api --host 127.0.0.1 --port 8000
+```
+
+Docker files live in this package. From the repository root:
+
+```bash
+docker compose -f packages/pdf-anonymizer-api/docker-compose.yml up --build
+```
+
+Docs: [HTTP service and Docker](https://leo-gan.github.io/anonymizer/project/http-service/).

pdf_anonymizer_api-0.29.0/pyproject.toml

@@ -0,0 +1,29 @@
+[project]
+name = "pdf-anonymizer-api"
+version = "0.29.0"
+description = "Local HTTP service for pdf-anonymizer-core. No authentication."
+authors = [{ name = "Leonid Ganeline", email = "leo.gan.57@gmail.com" }]
+license = { text = "MIT" }
+readme = "README.md"
+requires-python = ">=3.10"
+dependencies = [
+    "pdf-anonymizer-core>=0.29.0",
+    "fastapi>=0.115",
+    "uvicorn[standard]>=0.30",
+]
+
+[project.urls]
+repository = "https://github.com/leo-gan/anonymizer"
+
+[project.scripts]
+pdf-anonymizer-api = "pdf_anonymizer_api.server:main"
+
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools]
+package-dir = {"" = "src"}
+
+[tool.uv.sources]
+pdf-anonymizer-core = { workspace = true }

pdf_anonymizer_api-0.29.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

pdf_anonymizer_api-0.29.0/src/pdf_anonymizer_api/__init__.py

@@ -0,0 +1,5 @@
+"""Local HTTP service for pdf-anonymizer-core."""
+
+from pdf_anonymizer_api.app import create_app
+
+__all__ = ["create_app"]

pdf_anonymizer_api-0.29.0/src/pdf_anonymizer_api/__main__.py

@@ -0,0 +1,4 @@
+from pdf_anonymizer_api.server import main
+
+if __name__ == "__main__":
+    main()

pdf_anonymizer_api-0.29.0/src/pdf_anonymizer_api/app.py

@@ -0,0 +1,239 @@
+"""Thin HTTP service: anonymize, deanonymize, verify, report.
+
+Install ``pdf-anonymizer-api``. Auth is out of scope. Bind to localhost
+or a compose network. This package calls ``pdf-anonymizer-core`` only.
+"""
+
+from __future__ import annotations
+
+from typing import Any, Dict, List, Optional
+
+from pydantic import BaseModel, Field
+
+from pdf_anonymizer_core.conf import filter_regex_patterns
+from pdf_anonymizer_core.core import (
+    build_mapping,
+    collect_entities_from_chunks,
+    finalize_entities,
+)
+from pdf_anonymizer_core.prompts import detailed, hipaa, simple
+from pdf_anonymizer_core.risk import assess_linkage_risk
+from pdf_anonymizer_core.spans import replace_entities
+from pdf_anonymizer_core.operators import restore_encrypt_tokens
+from pdf_anonymizer_core.utils import (
+    mapping_to_placeholder_original,
+    restore_placeholders_in_text,
+)
+from pdf_anonymizer_core.verify import verify_anonymized_text
+
+API_INSTALL_MESSAGE = "HTTP service requires: pip install pdf-anonymizer-api"
+MAX_TEXT_CHARS = 5_000_000
+_PROMPTS = {
+    "simple": simple.prompt_template,
+    "detailed": detailed.prompt_template,
+    "hipaa": hipaa.prompt_template,
+}
+
+
+class AnonymizeBody(BaseModel):
+    text: str
+    use_llm: bool = False
+    use_ner: bool = False
+    min_confidence: float = Field(default=0.0, ge=0.0, le=1.0)
+    keep_list: Optional[List[str]] = None
+    deny_list: Optional[List[str]] = None
+    operators: Optional[Dict[str, str]] = None
+    seed_mapping: Optional[Dict[str, str]] = None
+    fake_secret: Optional[str] = None
+    encrypt_secret: Optional[str] = None
+    model_name: Optional[str] = None
+    prompt_name: str = "simple"
+    anonymized_entities: Optional[List[str]] = None
+    countries: Optional[List[str]] = None
+    opt_in: Optional[List[str]] = None
+
+
+class DeanonymizeBody(BaseModel):
+    text: str
+    mapping: Dict[str, str]
+    encrypt_secret: Optional[str] = None
+
+
+class TextBody(BaseModel):
+    text: str
+    countries: Optional[List[str]] = None
+    opt_in: Optional[List[str]] = None
+    use_llm: bool = False
+    model_name: Optional[str] = None
+
+
+def _public_entity(entity: Dict[str, Any]) -> Dict[str, Any]:
+    return {
+        "text": entity.get("text", ""),
+        "type": str(entity.get("type", "")).upper(),
+        "base_form": entity.get("base_form") or entity.get("text", ""),
+        "score": float(entity.get("score", 1.0)),
+        "source": entity.get("source") or "regex",
+    }
+
+
+def anonymize_text_request(
+    text: str,
+    *,
+    use_llm: bool = False,
+    use_ner: bool = False,
+    min_confidence: float = 0.0,
+    keep_list: Optional[List[str]] = None,
+    deny_list: Optional[List[str]] = None,
+    operators: Optional[Dict[str, str]] = None,
+    seed_mapping: Optional[Dict[str, str]] = None,
+    fake_secret: Optional[str] = None,
+    encrypt_secret: Optional[str] = None,
+    model_name: Optional[str] = None,
+    prompt_name: str = "simple",
+    anonymized_entities: Optional[List[str]] = None,
+    countries: Optional[List[str]] = None,
+    opt_in: Optional[List[str]] = None,
+) -> Dict[str, Any]:
+    """Run the same engine as the CLI on an in-memory string."""
+    if len(text) > MAX_TEXT_CHARS:
+        raise ValueError(
+            f"text is {len(text):,} characters; the HTTP limit is {MAX_TEXT_CHARS:,}."
+        )
+    template = _PROMPTS.get(prompt_name)
+    if template is None:
+        raise ValueError(
+            f"Unknown prompt_name {prompt_name!r}. Use simple, detailed, or hipaa."
+        )
+    if not 0.0 <= min_confidence <= 1.0:
+        raise ValueError("min_confidence must be between 0 and 1.")
+
+    collected = collect_entities_from_chunks(
+        [text],
+        prompt_template=template,
+        model_name=model_name or "gemini-2.5-flash",
+        regex_patterns=filter_regex_patterns(countries, opt_in=opt_in),
+        max_retries=3,
+        base_retry_delay=1.0,
+        max_retry_delay=10.0,
+        use_llm=use_llm,
+        use_ner=use_ner,
+    )
+    entities = finalize_entities(
+        collected,
+        text,
+        anonymized_entities=anonymized_entities,
+        keep_list=keep_list,
+        deny_list=deny_list,
+        min_confidence=min_confidence,
+        seed_mapping=seed_mapping,
+    )
+    mapping = build_mapping(
+        entities,
+        seed_mapping=seed_mapping,
+        operators=operators,
+        fake_secret=fake_secret,
+        encrypt_secret=encrypt_secret,
+    )
+    anonymized = text
+    if entities:
+        anonymized = replace_entities(
+            text, (entity["text"] for entity in entities), mapping
+        )
+    return {
+        "anonymized_text": anonymized,
+        "mapping": mapping,
+        "entities": [_public_entity(entity) for entity in entities],
+    }
+
+
+def deanonymize_text_request(
+    text: str,
+    mapping: Dict[str, str],
+    *,
+    encrypt_secret: Optional[str] = None,
+) -> Dict[str, Any]:
+    if len(text) > MAX_TEXT_CHARS:
+        raise ValueError(
+            f"text is {len(text):,} characters; the HTTP limit is {MAX_TEXT_CHARS:,}."
+        )
+    placeholder_to_original = mapping_to_placeholder_original(mapping)
+    restored, used = restore_placeholders_in_text(text, placeholder_to_original)
+    if encrypt_secret:
+        restored = restore_encrypt_tokens(restored, encrypt_secret)
+    return {
+        "text": restored,
+        "restored_count": len(used),
+    }
+
+
+def create_app():
+    """Build the FastAPI app."""
+    from fastapi import FastAPI, HTTPException
+
+    application = FastAPI(
+        title="PDF Anonymizer",
+        description=(
+            "Local HTTP wrapper around pdf-anonymizer-core. "
+            "No authentication. Bind to localhost or a compose network."
+        ),
+        version="0.26.0",
+    )
+
+    @application.get("/health")
+    def health() -> Dict[str, str]:
+        return {"status": "ok", "version": "0.26.0"}
+
+    @application.post("/anonymize")
+    def anonymize(body: AnonymizeBody) -> Dict[str, Any]:
+        try:
+            return anonymize_text_request(
+                body.text,
+                use_llm=body.use_llm,
+                use_ner=body.use_ner,
+                min_confidence=body.min_confidence,
+                keep_list=body.keep_list,
+                deny_list=body.deny_list,
+                operators=body.operators,
+                seed_mapping=body.seed_mapping,
+                fake_secret=body.fake_secret,
+                encrypt_secret=body.encrypt_secret,
+                model_name=body.model_name,
+                prompt_name=body.prompt_name,
+                anonymized_entities=body.anonymized_entities,
+                countries=body.countries,
+                opt_in=body.opt_in,
+            )
+        except ValueError as exc:
+            raise HTTPException(status_code=400, detail=str(exc)) from exc
+
+    @application.post("/deanonymize")
+    def deanonymize(body: DeanonymizeBody) -> Dict[str, Any]:
+        try:
+            return deanonymize_text_request(
+                body.text,
+                body.mapping,
+                encrypt_secret=body.encrypt_secret,
+            )
+        except ValueError as exc:
+            raise HTTPException(status_code=400, detail=str(exc)) from exc
+
+    @application.post("/verify")
+    def verify(body: TextBody) -> Dict[str, Any]:
+        try:
+            return verify_anonymized_text(
+                body.text,
+                regex_patterns=filter_regex_patterns(
+                    body.countries, opt_in=body.opt_in
+                ),
+                use_llm=body.use_llm,
+                model_name=body.model_name,
+            )
+        except ValueError as exc:
+            raise HTTPException(status_code=400, detail=str(exc)) from exc
+
+    @application.post("/report")
+    def report(body: TextBody) -> Dict[str, Any]:
+        return assess_linkage_risk(body.text)
+
+    return application

pdf_anonymizer_api-0.29.0/src/pdf_anonymizer_api/server.py

@@ -0,0 +1,31 @@
+"""Process entry point. Does not import the CLI."""
+
+from __future__ import annotations
+
+import argparse
+
+from pdf_anonymizer_api.app import create_app
+
+
+def main(argv: list[str] | None = None) -> None:
+    parser = argparse.ArgumentParser(
+        description=(
+            "Local HTTP service for pdf-anonymizer-core. "
+            "No authentication. Default bind is this machine only."
+        )
+    )
+    parser.add_argument(
+        "--host",
+        default="127.0.0.1",
+        help="Bind address (default 127.0.0.1).",
+    )
+    parser.add_argument(
+        "--port",
+        type=int,
+        default=8000,
+        help="TCP port (default 8000).",
+    )
+    args = parser.parse_args(argv)
+    import uvicorn
+
+    uvicorn.run(create_app(), host=args.host, port=args.port)

pdf_anonymizer_api-0.29.0/src/pdf_anonymizer_api.egg-info/PKG-INFO

@@ -0,0 +1,29 @@
+Metadata-Version: 2.4
+Name: pdf-anonymizer-api
+Version: 0.29.0
+Summary: Local HTTP service for pdf-anonymizer-core. No authentication.
+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: pdf-anonymizer-core>=0.29.0
+Requires-Dist: fastapi>=0.115
+Requires-Dist: uvicorn[standard]>=0.30
+
+# PDF Anonymizer HTTP service
+
+A thin FastAPI wrapper around `pdf-anonymizer-core`. It does **not** depend on the CLI. There is no authentication.
+
+```bash
+pip install pdf-anonymizer-api
+pdf-anonymizer-api --host 127.0.0.1 --port 8000
+```
+
+Docker files live in this package. From the repository root:
+
+```bash
+docker compose -f packages/pdf-anonymizer-api/docker-compose.yml up --build
+```
+
+Docs: [HTTP service and Docker](https://leo-gan.github.io/anonymizer/project/http-service/).

pdf_anonymizer_api-0.29.0/src/pdf_anonymizer_api.egg-info/SOURCES.txt

@@ -0,0 +1,12 @@
+README.md
+pyproject.toml
+src/pdf_anonymizer_api/__init__.py
+src/pdf_anonymizer_api/__main__.py
+src/pdf_anonymizer_api/app.py
+src/pdf_anonymizer_api/server.py
+src/pdf_anonymizer_api.egg-info/PKG-INFO
+src/pdf_anonymizer_api.egg-info/SOURCES.txt
+src/pdf_anonymizer_api.egg-info/dependency_links.txt
+src/pdf_anonymizer_api.egg-info/entry_points.txt
+src/pdf_anonymizer_api.egg-info/requires.txt
+src/pdf_anonymizer_api.egg-info/top_level.txt

pdf_anonymizer_api-0.29.0/src/pdf_anonymizer_api.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

pdf_anonymizer_api-0.29.0/src/pdf_anonymizer_api.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+pdf-anonymizer-api = pdf_anonymizer_api.server:main

pdf_anonymizer_api-0.29.0/src/pdf_anonymizer_api.egg-info/requires.txt

@@ -0,0 +1,3 @@
+pdf-anonymizer-core>=0.29.0
+fastapi>=0.115
+uvicorn[standard]>=0.30

pdf_anonymizer_api-0.29.0/src/pdf_anonymizer_api.egg-info/top_level.txt

@@ -0,0 +1 @@
+pdf_anonymizer_api