feat(cv): extend templates and extraction

tools/summarizer/tests/test_app.py

@@ -1,4 +1,5 @@
 import importlib
+import io
 import json
 import sys
 from pathlib import Path
@@ -522,6 +523,33 @@ def test_extract_text_rejects_oversized_upload_before_parsing(monkeypatch):
     assert "too large" in response.json()["detail"].lower()
 
 
+def test_extraction_normalization_preserves_sections_and_bullets(monkeypatch):
+    module = load_app_module(monkeypatch)
+
+    normalized = module._normalize_text("PROFILE\n\nEngineer\n• Built APIs\n• Shipped services")
+
+    assert normalized.splitlines() == ["PROFILE", "", "Engineer", "• Built APIs", "• Shipped services"]
+
+
+def test_docx_extraction_preserves_paragraph_and_table_boundaries(monkeypatch):
+    module = load_app_module(monkeypatch)
+    document = module.Document()
+    document.add_heading("Technical Skills", level=1)
+    table = document.add_table(rows=2, cols=2)
+    table.cell(0, 0).text = "Backend"
+    table.cell(0, 1).text = "C#, .NET"
+    table.cell(1, 0).text = "DevOps"
+    table.cell(1, 1).text = "Docker, Linux"
+    payload = io.BytesIO()
+    document.save(payload)
+
+    extracted = module._extract_docx_text(payload.getvalue())
+
+    assert "Technical Skills" in extracted
+    assert "Backend | C#, .NET" in extracted
+    assert "DevOps | Docker, Linux" in extracted
+
+
 def test_cache_purge_requires_service_token_and_clears_content(monkeypatch):
     module = load_app_module(monkeypatch, service_token="s3cret")
     module.cache["synthetic-key"] = "synthetic-summary"