update

.gitattributes

@@ -0,0 +1,13 @@
+* text=auto
+*.sh text eol=lf
+*.py text eol=lf
+Dockerfile text eol=lf
+*.ini text eol=lf
+*.cfg text eol=lf
+*.yml text eol=lf
+*.yaml text eol=lf
+*.json text eol=lf
+*.md text eol=lf
+.gitignore text eol=lf
+.dockerignore text eol=lf
+.env text eol=lf

.gitignore

@@ -125,4 +125,6 @@ run_docker.py
 docs
 .claude
 start_docker.txt
-Reconciliation-file-processing-service.postman_collection.json
+Reconciliation-file-processing-service.postman_collection.json
+pytest.ini
+tests/*

Dockerfile

@@ -5,9 +5,10 @@
 
 FROM python:3.12-slim
 
-LABEL maintainer="Reconciliation API"
+LABEL maintainer="Reconciliation File Processing Service API"
 LABEL description="Document-to-Markdown & PDF-to-image API"
 LABEL version="2.2.0"
+LABEL description="Production-ready: consolidated logging, unified app, cleanup loop, self-ping"
 
 # ── System dependencies ──────────────────────────────────────
 RUN apt-get update && apt-get install -y --no-install-recommends \

__init__.py

@@ -1,4 +1,4 @@
-from .core import ConversionError, ConversionResult, DocumentConverter, SUPPORTED_EXTENSIONS
+from core.converter import ConversionError, ConversionResult, DocumentConverter, SUPPORTED_EXTENSIONS
 
 __all__ = [
     "ConversionError",

api/server.py

@@ -20,7 +20,6 @@ PDF-to-image conversion (under /api/v1):
   GET  /api/v1/files/{id}/{fn}
   GET  /api/v1/health
   GET  /api/v1/ready
-  GET  /api/v1/ping
 
 System:
   GET  /              Root info
@@ -34,11 +33,10 @@ from __future__ import annotations
 
 import asyncio
 import concurrent.futures
+import json
 import os
-import threading
 import time
 import uuid
-import urllib.request
 from contextlib import asynccontextmanager
 from datetime import datetime, timezone
 from pathlib import Path
@@ -46,6 +44,7 @@ from typing import Annotated, Any, Dict, List, Optional
 from urllib.parse import urlparse
 
 import httpx
+import structlog
 from fastapi import APIRouter, Depends, FastAPI, File, Form, HTTPException, Request, UploadFile, status
 from fastapi.responses import JSONResponse, PlainTextResponse
 from fastapi.middleware.cors import CORSMiddleware
@@ -62,6 +61,8 @@ from app.core.config import settings
 from app.core.exceptions import AppException
 from app.core.logging import configure_logging
 from app.core.rate_limit import RateLimitMiddleware
+from app.services.ping import start_self_ping
+from app.utils.cleanup import cleanup_loop
 
 configure_logging()
 logger = get_logger(__name__)
@@ -69,43 +70,14 @@ logger = get_logger(__name__)
 _START_TIME = time.time()
 APP_NAME = "reconciliation-file-processing-service"
 
-MAX_UPLOAD_BYTES = 100 * 1024 * 1024
+MAX_UPLOAD_BYTES = int(os.getenv("MAX_UPLOAD_BYTES", str(100 * 1024 * 1024)))
 
 MAX_WORKERS = min(32, (os.cpu_count() or 1) + 4)
 _thread_pool = concurrent.futures.ThreadPoolExecutor(max_workers=MAX_WORKERS)
 
 _converter = DocumentConverter()
 
-logger.info("Thread pool initialised with %d workers", MAX_WORKERS)
-
-
-# ---------------------------------------------------------------------------
-# Self-ping
-# ---------------------------------------------------------------------------
-
-PING_URL = os.environ.get("PING_URL", "https://validops-us-data-extract.hf.space/health")
-PING_INTERVAL_SECONDS = 30 * 60
-
-
-def _ping_once() -> None:
-    ts = datetime.now(timezone.utc).strftime("%Y-%m-%d %H:%M:%S UTC")
-    try:
-        with urllib.request.urlopen(PING_URL, timeout=10) as resp:
-            logger.info("self_ping | status=%d | url=%s | ts=%s", resp.status, PING_URL, ts)
-    except Exception as exc:
-        logger.warning("self_ping | failed | url=%s | error=%s | ts=%s", PING_URL, exc, ts)
-
-
-def _ping_loop() -> None:
-    logger.info("self_ping | scheduler started | interval_minutes=30 | url=%s", PING_URL)
-    while True:
-        time.sleep(PING_INTERVAL_SECONDS)
-        _ping_once()
-
-
-def _start_ping_scheduler() -> None:
-    thread = threading.Thread(target=_ping_loop, name="self-ping", daemon=True)
-    thread.start()
+logger.info("thread_pool_initialised", workers=MAX_WORKERS)
 
 
 # ---------------------------------------------------------------------------
@@ -114,12 +86,14 @@ def _start_ping_scheduler() -> None:
 
 @asynccontextmanager
 async def lifespan(app: FastAPI):
-    logger.info(
-        "MarkItDown & PDF Conversion API starting | version=2.1.0 | host=0.0.0.0:7860",
-    )
-    _start_ping_scheduler()
+    logger.info("api_starting", version="2.2.0", host="0.0.0.0:7860")
+    ping_task = await start_self_ping()
+    cleanup_task = asyncio.create_task(cleanup_loop())
     yield
-    logger.info("MarkItDown & PDF Conversion API shutting down")
+    if ping_task:
+        ping_task.cancel()
+    cleanup_task.cancel()
+    logger.info("api_shutting_down")
 
 
 # ---------------------------------------------------------------------------
@@ -132,7 +106,7 @@ app = FastAPI(
         "Unified API for document-to-Markdown conversion (Microsoft MarkItDown + RapidOCR) "
         "and PDF-to-image conversion with async job support."
     ),
-    version="2.1.0",
+    version="2.2.0",
     docs_url="/docs",
     redoc_url="/redoc",
     lifespan=lifespan,
@@ -154,9 +128,8 @@ async def request_context_middleware(request: Request, call_next):
     request_id = str(uuid.uuid4())
     start = time.perf_counter()
 
-    import structlog as _structlog
-    _structlog.contextvars.clear_contextvars()
-    _structlog.contextvars.bind_contextvars(
+    structlog.contextvars.clear_contextvars()
+    structlog.contextvars.bind_contextvars(
         request_id=request_id,
         method=request.method,
         path=request.url.path,
@@ -165,7 +138,7 @@ async def request_context_middleware(request: Request, call_next):
     response = await call_next(request)
     elapsed = round((time.perf_counter() - start) * 1000, 2)
 
-    logger.info("request_completed | status=%d | duration_ms=%.2f", response.status_code, elapsed)
+    logger.info("request_completed", status=response.status_code, duration_ms=elapsed)
     response.headers["X-Request-ID"] = request_id
     response.headers["X-Response-Time-Ms"] = str(elapsed)
     return response
@@ -174,7 +147,7 @@ async def request_context_middleware(request: Request, call_next):
 # -- Exception handlers --
 @app.exception_handler(AppException)
 async def app_exception_handler(request: Request, exc: AppException):
-    logger.warning("app_exception | detail=%s | status_code=%d", exc.detail, exc.status_code)
+    logger.warning("app_exception", detail=exc.detail, status_code=exc.status_code)
     return JSONResponse(
         status_code=exc.status_code,
         content={"error": exc.detail, "request_id": getattr(request.state, "request_id", "")},
@@ -190,10 +163,10 @@ async def generic_exception_handler(request: Request, exc: Exception):
     )
 
 
-# -- Root-level routes (only / , /ping , /health) --
+# -- Root-level routes (only / , /ping) --
 @app.get("/", tags=["System"], summary="Root", include_in_schema=False)
 async def root():
-    return {"service": APP_NAME, "version": "2.1.0", "status": "running"}
+    return {"service": APP_NAME, "version": "2.2.0", "status": "running"}
 
 
 @app.get("/ping", tags=["System"], summary="Ping", include_in_schema=False)
@@ -427,20 +400,20 @@ async def convert_file(
         except _json.JSONDecodeError:
             raise HTTPException(status_code=400, detail={"success": False, "message": "Invalid JSON in mappings parameter."})
 
-    logger.info("convert_file | filename=%s", file.filename)
+    logger.info("convert_file", filename=file.filename)
     raw = await file.read()
     if len(raw) > MAX_UPLOAD_BYTES:
-        logger.warning("convert_file | file too large | filename=%s | size=%d", file.filename, len(raw))
+        logger.warning("convert_file | file too large", filename=file.filename, size=len(raw))
         raise HTTPException(status_code=413, detail={"success": False, "message": "File exceeds 100 MB limit."})
 
     loop = asyncio.get_running_loop()
     outcome = await loop.run_in_executor(_thread_pool, _converter.convert_stream, raw, file.filename or "upload")
 
     if isinstance(outcome, ConversionError):
-        logger.error("convert_file | conversion failed | filename=%s | error=%s", file.filename, outcome.message)
+        logger.error("convert_file | conversion failed", filename=file.filename, error=outcome.message)
         _raise_for_error(outcome)
 
-    logger.info("convert_file | success | filename=%s | chars=%d | time_ms=%.1f", file.filename, outcome.char_count, outcome.duration_ms)
+    logger.info("convert_file | success", filename=file.filename, chars=outcome.char_count, time_ms=round(outcome.duration_ms, 1))
 
     if plain_text:
         return PlainTextResponse(outcome.markdown)
@@ -455,7 +428,7 @@ async def convert_file(
     summary="Convert a public URL to Markdown",
 )
 async def convert_url(body: UrlRequest):
-    logger.info("convert_url | url=%s", body.url)
+    logger.info("convert_url", url=body.url)
     parsed = urlparse(body.url)
     filename = Path(parsed.path).name or "url_content"
     loop = asyncio.get_running_loop()
@@ -466,7 +439,7 @@ async def convert_url(body: UrlRequest):
                 resp = await client.get(body.url)
                 resp.raise_for_status()
         except httpx.HTTPError as exc:
-            logger.error("convert_url | fetch failed | url=%s | error=%s", body.url, exc)
+            logger.error("convert_url | fetch failed", url=body.url, error=str(exc))
             raise HTTPException(status_code=400, detail={"success": False, "message": f"Failed to fetch URL: {exc}"})
 
         raw_data = resp.content
@@ -475,18 +448,18 @@ async def convert_url(body: UrlRequest):
 
         outcome = await loop.run_in_executor(_thread_pool, _converter.convert_stream, raw_data, filename)
         if isinstance(outcome, ConversionError):
-            logger.error("convert_url | conversion failed | url=%s | error=%s", body.url, outcome.message)
+            logger.error("convert_url | conversion failed", url=body.url, error=outcome.message)
             _raise_for_error(outcome)
 
-        logger.info("convert_url | success | url=%s | chars=%d | time_ms=%.1f", body.url, outcome.char_count, outcome.duration_ms)
+        logger.info("convert_url | success", url=body.url, chars=outcome.char_count, time_ms=round(outcome.duration_ms, 1))
         return await _build_response(outcome, return_json=body.return_json, filename=filename, raw_data=raw_data, mappings=body.mappings)
 
     outcome = await loop.run_in_executor(_thread_pool, _converter.convert_url, body.url)
     if isinstance(outcome, ConversionError):
-        logger.error("convert_url | conversion failed | url=%s | error=%s", body.url, outcome.message)
+        logger.error("convert_url | conversion failed", url=body.url, error=outcome.message)
         _raise_for_error(outcome)
 
-    logger.info("convert_url | success | url=%s | chars=%d | time_ms=%.1f", body.url, outcome.char_count, outcome.duration_ms)
+    logger.info("convert_url | success", url=body.url, chars=outcome.char_count, time_ms=round(outcome.duration_ms, 1))
     return await _build_response(outcome, return_json=body.return_json, filename=filename, mappings=body.mappings)
 
 
@@ -505,7 +478,7 @@ async def batch_files(
         raise HTTPException(status_code=400, detail={"success": False, "message": "Maximum 10 files per batch."})
 
     batch_start = time.perf_counter()
-    logger.info("batch_files | count=%d", len(files))
+    logger.info("batch_files", count=len(files))
 
     async def _process_file(f: UploadFile) -> BatchFileResult:
         if f is None:
@@ -520,7 +493,7 @@ async def batch_files(
     results = await asyncio.gather(*[_process_file(f) for f in files])
     total_ms = round((time.perf_counter() - batch_start) * 1000, 3)
     succeeded = sum(1 for r in results if r.success)
-    logger.info("batch_files | done | succeeded=%d | failed=%d | total_ms=%.1f", succeeded, len(results) - succeeded, total_ms)
+    logger.info("batch_files | done", succeeded=succeeded, failed=len(results) - succeeded, total_ms=round(total_ms, 1))
 
     return BatchResponse(total=len(results), succeeded=succeeded, failed=len(results) - succeeded, total_time_ms=total_ms, results=results)
 
@@ -533,7 +506,7 @@ async def batch_files(
 )
 async def batch_urls(body: BatchUrlRequest):
     batch_start = time.perf_counter()
-    logger.info("batch_urls | count=%d", len(body.urls))
+    logger.info("batch_urls", count=len(body.urls))
 
     async def _process_url(url: str) -> BatchFileResult:
         loop = asyncio.get_running_loop()
@@ -543,7 +516,7 @@ async def batch_urls(body: BatchUrlRequest):
     results = await asyncio.gather(*[_process_url(url) for url in body.urls])
     total_ms = round((time.perf_counter() - batch_start) * 1000, 3)
     succeeded = sum(1 for r in results if r.success)
-    logger.info("batch_urls | done | succeeded=%d | failed=%d | total_ms=%.1f", succeeded, len(results) - succeeded, total_ms)
+    logger.info("batch_urls | done", succeeded=succeeded, failed=len(results) - succeeded, total_ms=round(total_ms, 1))
 
     return BatchResponse(total=len(results), succeeded=succeeded, failed=len(results) - succeeded, total_time_ms=total_ms, results=results)
 

app/banner.py

@@ -1,21 +0,0 @@
-import pyfiglet
-from rich.console import Console
-from rich.rule import Rule
-from rich.text import Text
-
-from app.core.config import get_settings
-
-_console = Console()
-
-
-def print_banner() -> None:
-    settings = get_settings()
-
-    art = pyfiglet.figlet_format("ValidOps", font="slant")
-
-    _console.print(Text(art, style="bold cyan"))
-    _console.print(f"  [bold white]{'Service:':<14}[/bold white]  [cyan]{settings.APP_NAME}[/cyan]")
-    _console.print(f"  [bold white]{'Version:':<14}[/bold white]  [cyan]v{settings.VERSION}[/cyan]")
-    _console.print(f"  [bold white]{'Environment:':<14}[/bold white]  [cyan]{settings.ENV}[/cyan]")
-    _console.print(Rule(style="dim cyan"))
-    _console.print()

app/core/exceptions.py

@@ -54,8 +54,3 @@ class InvalidParameterError(AppException):
 class FileServiceError(AppException):
     def __init__(self, detail: str = "File upload service error"):
         super().__init__(detail, status.HTTP_502_BAD_GATEWAY)
-
-
-class CSVGenerationError(AppException):
-    def __init__(self, detail: str = "CSV generation failed"):
-        super().__init__(detail, status.HTTP_500_INTERNAL_SERVER_ERROR)

app/main.py

@@ -1,95 +0,0 @@
-from __future__ import annotations
-
-import time
-import uuid
-from contextlib import asynccontextmanager
-
-import structlog
-from fastapi import FastAPI, Request
-from fastapi.middleware.cors import CORSMiddleware
-from fastapi.middleware.gzip import GZipMiddleware
-from fastapi.responses import JSONResponse
-from prometheus_client import make_asgi_app
-
-from app.api.routes import router
-from app.core.config import settings
-from app.core.exceptions import AppException
-from app.core.logging import configure_logging
-from app.core.rate_limit import RateLimitMiddleware
-configure_logging()
-logger = structlog.get_logger(__name__)
-
-
-@asynccontextmanager
-async def lifespan(app: FastAPI):
-    logger.info("startup", service=settings.APP_NAME, version=settings.VERSION, env=settings.ENV)
-    yield
-    logger.info("shutdown", service=settings.APP_NAME)
-
-
-app = FastAPI(
-    title=settings.APP_NAME,
-    description="High-performance PDF to Image conversion and CSV report generation API",
-    version=settings.VERSION,
-    docs_url="/docs",
-    redoc_url="/redoc",
-    lifespan=lifespan,
-)
-
-app.add_middleware(RateLimitMiddleware)
-app.add_middleware(GZipMiddleware, minimum_size=1000)
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=settings.ALLOWED_ORIGINS,
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-
-
-@app.middleware("http")
-async def request_context_middleware(request: Request, call_next):
-    request_id = str(uuid.uuid4())
-    start = time.perf_counter()
-    request.state.request_id = request_id
-
-    structlog.contextvars.clear_contextvars()
-    structlog.contextvars.bind_contextvars(
-        request_id=request_id,
-        method=request.method,
-        path=request.url.path,
-    )
-
-    response = await call_next(request)
-    elapsed = round((time.perf_counter() - start) * 1000, 2)
-
-    logger.info("request_completed", status_code=response.status_code, duration_ms=elapsed)
-    response.headers["X-Request-ID"] = request_id
-    response.headers["X-Response-Time-Ms"] = str(elapsed)
-    return response
-
-
-@app.exception_handler(AppException)
-async def app_exception_handler(request: Request, exc: AppException):
-    logger.warning("app_exception", detail=exc.detail, status_code=exc.status_code)
-    return JSONResponse(
-        status_code=exc.status_code,
-        content={"error": exc.detail, "request_id": request.state.request_id},
-    )
-
-
-@app.exception_handler(Exception)
-async def generic_exception_handler(request: Request, exc: Exception):
-    logger.exception("unhandled_exception", exc_info=exc)
-    return JSONResponse(
-        status_code=500,
-        content={"error": "Internal server error", "request_id": request.state.request_id},
-    )
-
-
-@app.get("/")
-async def root():
-    return {"message": f"{settings.APP_NAME} v{settings.VERSION}"}
-
-app.include_router(router, prefix="/api/v1")
-app.mount("/metrics", make_asgi_app())

app/services/ping.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import asyncio
+from typing import Optional
 
 import httpx
 import structlog
@@ -10,11 +11,13 @@ from app.core.config import settings
 logger = structlog.get_logger(__name__)
 
 
-async def start_self_ping() -> None:
+async def start_self_ping() -> Optional[asyncio.Task]:
     if not settings.SELF_PING_ENABLED or not settings.SELF_PING_URL:
         logger.info("self_ping_disabled")
-        return
-    asyncio.create_task(_ping_loop())
+        return None
+    task = asyncio.create_task(_ping_loop())
+    logger.info("self_ping_started", url=settings.SELF_PING_URL, interval=settings.SELF_PING_INTERVAL_SECONDS)
+    return task
 
 
 async def _ping_loop() -> None:

banner.py

@@ -8,7 +8,7 @@ from rich.text import Text
 _console = Console()
 
 SERVICE_NAME = os.getenv("SERVICE_NAME", "reconciliation-file-processing-service")
-API_VERSION  = os.getenv("API_VERSION", "2.1.0")
+API_VERSION  = os.getenv("API_VERSION", "2.2.0")
 ENVIRONMENT  = os.getenv("ENVIRONMENT", "production")
 
 

core/__init__.py

@@ -1,15 +1,8 @@
 from .converter import ConversionError, ConversionResult, DocumentConverter, SUPPORTED_EXTENSIONS
-from .batch import BatchProcessor, BatchReport
-from .output import OutputWriter
-from .ocr_engine import ocr_image
 
 __all__ = [
     "ConversionError",
     "ConversionResult",
     "DocumentConverter",
     "SUPPORTED_EXTENSIONS",
-    "BatchProcessor",
-    "BatchReport",
-    "OutputWriter",
-    "ocr_image",
 ]

core/converter.py

@@ -37,6 +37,13 @@ from logger import get_logger
 
 logger = get_logger(__name__)
 
+# Extensions that route through RapidOCR rather than MarkItDown.
+IMAGE_EXTENSIONS = {
+    ".jpg", ".jpeg", ".png", ".gif", ".bmp", ".webp", ".tiff",
+}
+
+IMAGE_MIME_PREFIXES = {"image/"}
+
 
 # ---------------------------------------------------------------------------
 # Supported formats
@@ -51,14 +58,6 @@ SUPPORTED_EXTENSIONS = {
     ".zip", ".epub",
 }
 
-# Extensions that route through RapidOCR rather than MarkItDown.
-IMAGE_EXTENSIONS = {
-    ".jpg", ".jpeg", ".png", ".gif", ".bmp", ".webp", ".tiff",
-}
-
-IMAGE_MIME_PREFIXES = {"image/"}
-
-
 def _is_image(ext: str, mime: str) -> bool:
     """Return True when the input should be routed through RapidOCR."""
     return ext.lower() in IMAGE_EXTENSIONS or any(

extraction/json_extractor.py

@@ -20,10 +20,11 @@ logger = get_logger(__name__)
 SUPPORTED_EXTENSIONS = {'.csv', '.xls', '.xlsx'}
 
 # Resource limits to prevent abuse
-MAX_FILE_SIZE_BYTES = 100 * 1024 * 1024  # 100 MB
-MAX_CSV_ROWS = 100000  # Limit rows for CSV
-MAX_EXCEL_ROWS = 50000  # Limit rows for Excel
-MAX_MEMORY_ROWS = 100000  # Global memory guard
+from app.core.config import settings as _app_settings
+MAX_FILE_SIZE_BYTES = _app_settings.MAX_FILE_SIZE_BYTES
+MAX_CSV_ROWS = 100000
+MAX_EXCEL_ROWS = 50000
+MAX_MEMORY_ROWS = 100000
 
 
 def _validate_file_size(size: int) -> Optional[str]:

extraction/spacy_extractor.py

@@ -66,10 +66,6 @@ def _get_nlp():
     return _nlp
 
 
-def clean_text(text: str) -> str:
-    return text
-
-
 # ---------------------------------------------------------------------------
 # Normalizer registry
 # ---------------------------------------------------------------------------
@@ -600,7 +596,7 @@ def extract_fields(
     Backward-compatible: callers that pass flat scalar rules unchanged still work.
     """
     nlp     = _get_nlp()
-    cleaned = clean_text(text)
+    cleaned = text
 
     try:
         doc = next(iter(nlp.pipe([cleaned])))
@@ -642,7 +638,7 @@ def extract_schema(
     # → [{"date": "Jan 2024", "amount": "$1,200"}, ...]
     """
     nlp     = _get_nlp()
-    cleaned = clean_text(text)
+    cleaned = text
 
     try:
         doc = next(iter(nlp.pipe([cleaned])))

logger.py

@@ -1,87 +1,20 @@
-"""Production-grade structured JSON logger.
+"""Centralised logging — re-exports structlog.getLogger.
 
-Emits newline-delimited JSON to stdout (12-factor app pattern) for
-seamless ingestion by log aggregators (Datadog, ELK, CloudWatch, etc.).
+All application code should use this module to obtain loggers,
+ensuring consistent structlog configuration throughout the codebase.
 
 Usage
 -----
     from logger import get_logger
 
     logger = get_logger(__name__)
-    logger.info("processed | file=%s | rows=%d", filename, n)
-
-Configuration (environment variables):
-
-    LOG_LEVEL     Minimum level (default: INFO)
+    logger.info("event", key="value", duration_ms=42.0)
 """
 
 from __future__ import annotations
 
-import json
-import logging
-import os
-import sys
-from datetime import datetime, timezone
-from typing import Any
-
-
-__all__ = ["get_logger", "app_logger"]
-
-
-class JSONFormatter(logging.Formatter):
-    """Render log records as JSON lines.
-
-    Each line contains ``timestamp`` (ISO 8601 UTC), ``level``,
-    ``logger``, and ``message``.  Exception tracebacks are included
-    under ``exception`` when ``exc_info`` is set on the record.
-    """
-
-    __slots__ = ()
-
-    def format(self, record: logging.LogRecord) -> str:
-        payload: dict[str, Any] = {
-            "timestamp": datetime.fromtimestamp(
-                record.created, tz=timezone.utc
-            ).isoformat(),
-            "level": record.levelname,
-            "logger": record.name,
-            "message": record.getMessage(),
-        }
-        if record.exc_info and record.exc_info[0] is not None:
-            payload["exception"] = self.formatException(record.exc_info)
-        return json.dumps(payload, default=str, ensure_ascii=False, sort_keys=True)
-
-
-def get_logger(name: str) -> logging.Logger:
-    """Return a named logger.
-
-    All loggers inherit handlers from the root logger, which is
-    configured once at import time with a :class:`JSONFormatter`.
-    """
-    return logging.getLogger(name)
-
-
-_initialised: bool = False
-
-
-def _setup() -> None:
-    """Configure the root logger once from environment defaults."""
-    global _initialised
-    if _initialised:
-        return
-    _initialised = True
-
-    level = os.getenv("LOG_LEVEL", "INFO").upper()
-
-    root = logging.getLogger()
-    root.setLevel(getattr(logging, level, logging.INFO))
-
-    fmt = JSONFormatter()
-
-    console = logging.StreamHandler(sys.stdout)
-    console.setFormatter(fmt)
-    root.addHandler(console)
+import structlog
 
+__all__ = ["get_logger"]
 
-_setup()
-app_logger = get_logger("docx")
+get_logger = structlog.get_logger

self_ping.py

@@ -1,19 +0,0 @@
-#!/usr/bin/env python3
-"""Self-ping script that hits a URL."""
-
-import datetime
-import os
-import urllib.request
-
-PING_URL = os.environ.get("PING_URL", "https://your-url.com/health")  
-
-def main():
-    timestamp = datetime.datetime.now().isoformat()
-    try:
-        urllib.request.urlopen(PING_URL, timeout=10)
-        print(f"[{timestamp}] Pinged {PING_URL} - OK")
-    except Exception as e:
-        print(f"[{timestamp}] Ping failed: {e}")
-
-if __name__ == "__main__":
-    main()