fix(cv): harden document parsing

Upgrade and hash-lock upload-facing parser dependencies, reject resource-heavy or mismatched inputs, remove unsafe backend binary fallbacks, and prevent internal parser failures from leaking to users.

tools/summarizer/tests/test_app.py

@@ -2,9 +2,12 @@ import importlib
 import io
 import json
 import sys
+import zipfile
 from pathlib import Path
 
 from fastapi.testclient import TestClient
+from PIL import Image
+from pypdf import PdfWriter
 
 
 ROOT = Path(__file__).resolve().parents[1]
@@ -523,6 +526,86 @@ def test_extract_text_rejects_oversized_upload_before_parsing(monkeypatch):
     assert "too large" in response.json()["detail"].lower()
 
 
+def test_extract_text_rejects_extension_signature_mismatch(monkeypatch):
+    module = load_app_module(monkeypatch)
+    client = TestClient(module.app)
+
+    response = client.post("/extract-text", files={"file": ("resume.pdf", b"not a pdf", "application/pdf")})
+
+    assert response.status_code == 400
+    assert response.json()["detail"] == "The uploaded file does not match its PDF extension."
+
+
+def test_extract_text_rejects_binary_plain_text(monkeypatch):
+    module = load_app_module(monkeypatch)
+    client = TestClient(module.app)
+
+    response = client.post("/extract-text", files={"file": ("resume.txt", b"Name\x00binary", "text/plain")})
+
+    assert response.status_code == 400
+    assert response.json()["detail"] == "The uploaded text file contains binary data."
+
+
+def test_extract_text_rejects_pdf_over_page_limit(monkeypatch):
+    module = load_app_module(monkeypatch)
+    monkeypatch.setattr(module, "MAX_PDF_PAGES", 1)
+    writer = PdfWriter()
+    writer.add_blank_page(width=100, height=100)
+    writer.add_blank_page(width=100, height=100)
+    payload = io.BytesIO()
+    writer.write(payload)
+    client = TestClient(module.app)
+
+    response = client.post("/extract-text", files={"file": ("resume.pdf", payload.getvalue(), "application/pdf")})
+
+    assert response.status_code == 422
+    assert response.json()["detail"] == "The PDF contains too many pages."
+
+
+def test_extract_text_rejects_image_pixel_limit_before_ocr(monkeypatch):
+    module = load_app_module(monkeypatch)
+    monkeypatch.setattr(module, "MAX_IMAGE_PIXELS", 50)
+    monkeypatch.setattr(module, "_ocr_image", lambda image: (_ for _ in ()).throw(AssertionError("OCR must not run")))
+    payload = io.BytesIO()
+    Image.new("RGB", (10, 10), "white").save(payload, format="PNG")
+    client = TestClient(module.app)
+
+    response = client.post("/extract-text", files={"file": ("resume.png", payload.getvalue(), "image/png")})
+
+    assert response.status_code == 422
+    assert response.json()["detail"] == "The document image contains too many pixels."
+
+
+def test_docx_container_rejects_excessive_entries(monkeypatch):
+    module = load_app_module(monkeypatch)
+    monkeypatch.setattr(module, "MAX_DOCX_ENTRIES", 2)
+    payload = io.BytesIO()
+    with zipfile.ZipFile(payload, "w") as archive:
+        archive.writestr("[Content_Types].xml", "types")
+        archive.writestr("word/document.xml", "document")
+        archive.writestr("word/styles.xml", "styles")
+
+    try:
+        module._validate_docx_container(payload.getvalue())
+    except module.HTTPException as exc:
+        assert exc.status_code == 422
+        assert exc.detail == "The DOCX contains too many files."
+    else:
+        raise AssertionError("Expected the DOCX entry limit to reject the container")
+
+
+def test_extract_text_does_not_leak_parser_exception(monkeypatch):
+    module = load_app_module(monkeypatch)
+    monkeypatch.setattr(module, "_extract_pdf_text", lambda data: (_ for _ in ()).throw(RuntimeError("private path C:/secret")))
+    client = TestClient(module.app)
+
+    response = client.post("/extract-text", files={"file": ("resume.pdf", b"%PDF-invalid", "application/pdf")})
+
+    assert response.status_code == 422
+    assert response.json()["detail"] == "Document extraction failed."
+    assert "secret" not in response.text
+
+
 def test_extraction_normalization_preserves_sections_and_bullets(monkeypatch):
     module = load_app_module(monkeypatch)