any-file to PDF (Phase 1): converters/ dispatcher, images/text/md/csv/json/xml/svg/pdf-passthrough, 112 tests green

app.py

@@ -34,6 +34,8 @@ from werkzeug.exceptions import HTTPException, RequestEntityTooLarge
 from lxml import etree
 from pypdf import PdfWriter
 
+import converters  # PHASE 1: multi-format dispatch (any common file -> PDF)
+
 BASE_DIR = Path(__file__).resolve().parent
 # DATA_DIR is overridable via env so container deployments (e.g. Coolify)
 # can point uploads/output/work at a persistent volume.
@@ -46,6 +48,12 @@ for _d in (UPLOAD_DIR, OUTPUT_DIR, WORK_DIR):
 
 MAX_UPLOAD_MB = 400
 
+# req 3 (health): supported formats advertised to clients. Additive key — the
+# existing /health contract asserts only status + max_upload_mb.
+SUPPORTED_FORMATS = ["epub", "html", "htm", "md", "markdown", "txt", "log",
+                     "csv", "tsv", "json", "xml", "svg", "png", "jpg",
+                     "jpeg", "webp", "tiff", "bmp", "pdf"]
+
 # ZIP-bomb guard: total uncompressed size must stay within 8x the upload
 # size, with a 2 GiB floor so normal books always fit (finding: zip bomb,
 # app.py extractall).
@@ -127,6 +135,10 @@ body {
     font-size: 10.5pt;
     line-height: 1.65;
     color: #1c1b1a;
+    /* WeasyPrint emits CSS kerning as positive TJ adjustments that
+       pypdf's extract_text misreads as inter-word spaces ("BRA VO");
+       disable it to keep text extraction faithful. */
+    font-kerning: none;
 }
 h1, h2, h3, h4, h5, h6 {
     font-weight: 700; line-height: 1.25; color: #111;
@@ -526,8 +538,9 @@ def _run_job(job_id: str, epub_path: Path) -> None:
         _set_job(job_id, progress=pct, message=msg)
 
     try:
-        filename = convert_epub(epub_path, job_id, progress_cb=_cb,
-                                source_name=JOBS.get(job_id, {}).get("epub"))
+        filename = converters.convert_file(
+            epub_path, job_id, progress_cb=_cb,
+            source_name=JOBS.get(job_id, {}).get("epub"))
         _set_job(job_id, status="done", progress=100.0, message="Done",
                  filename=filename, error=None)
     except Exception as exc:  # noqa: BLE001 - any failure is a job error
@@ -539,7 +552,10 @@ def _run_job(job_id: str, epub_path: Path) -> None:
         except ValueError:
             pass
         try:
-            (UPLOAD_DIR / f"{job_id}.epub").unlink(missing_ok=True)
+            # PHASE 1: uploads keep their real suffix ({job_id}.html, ...);
+            # job_id is 32-hex so the glob cannot match anything else.
+            for _up in UPLOAD_DIR.glob(f"{job_id}.*"):
+                _up.unlink(missing_ok=True)
         except OSError:
             pass
         _sweep_stale_work_dirs()
@@ -571,9 +587,11 @@ def health():
         problems.append("weasyprint not importable")
     if not _cjk_fonts_present():
         problems.append("CJK fonts missing (fc-list found none)")
-    body = {"status": "ok", "max_upload_mb": MAX_UPLOAD_MB}
+    body = {"status": "ok", "max_upload_mb": MAX_UPLOAD_MB,
+            "supported_formats": SUPPORTED_FORMATS}
     if problems:
-        body = {"status": "degraded", "max_upload_mb": MAX_UPLOAD_MB, "problems": problems}
+        body = {"status": "degraded", "max_upload_mb": MAX_UPLOAD_MB,
+                "supported_formats": SUPPORTED_FORMATS, "problems": problems}
         return jsonify(body), 503
     return jsonify(body), 200
 
@@ -583,15 +601,21 @@ def convert_upload():
     up = request.files.get("file")
     if up is None or not up.filename:
         return jsonify(error="No file uploaded"), 400
-    if not up.filename.lower().endswith(".epub"):
-        return jsonify(error="Only .epub files are accepted"), 400
+    if not converters.is_supported(up.filename):
+        # PHASE 1: gate on the full extension matrix; the error lists every
+        # accepted extension (incl. .epub) so the legacy 400 contract holds.
+        ext = Path(up.filename).suffix or "<none>"
+        return jsonify(error=(
+            f"Unsupported file type: '{ext}'. "
+            f"Supported: {', '.join(sorted(converters.SUPPORTED_EXTENSIONS))}"
+        )), 400
     data = up.read()
     if len(data) > MAX_UPLOAD_MB * 1024 * 1024:
         return jsonify(error=f"File too large (max {MAX_UPLOAD_MB} MB)"), 400
     if not WORKER_SLOTS.acquire(blocking=False):
         return jsonify(error="Server busy: all conversion slots in use, retry shortly"), 503
     job_id = _register_job(Path(up.filename).name)
-    dest = UPLOAD_DIR / f"{job_id}.epub"
+    dest = UPLOAD_DIR / f"{job_id}{Path(up.filename).suffix.lower()}"
     try:
         with open(dest, "wb") as out:
             out.write(data)
@@ -621,9 +645,12 @@ def download(name):
         return jsonify(error="unknown file"), 404
     # req 4: explicit PDF mimetype + defensive .pdf on download_name
     download_name = safe if safe.lower().endswith(".pdf") else safe + ".pdf"
-    return send_file(
+    resp = send_file(
         target, as_attachment=True, mimetype="application/pdf", download_name=download_name
     )
+    # contract: quoted filename in Content-Disposition
+    resp.headers["Content-Disposition"] = f'attachment; filename="{download_name}"'
+    return resp
 
 
 # --------------------------------------------------------------------------
@@ -655,7 +682,9 @@ def _run_cli(argv: list[str]) -> int:
         print(f"[{pct:5.1f}%] {message}")
 
     try:
-        filename = convert_epub(src, job_id, progress_cb=_cb, output_dir=out_dir)
+        filename = converters.convert_file(src, job_id, progress_cb=_cb,
+                                           output_dir=out_dir,
+                                           source_name=src.name)
     except Exception as exc:  # noqa: BLE001 - CLI reports any failure as error:
         print(f"error: {exc}")
         return 1