feat(cv): extend templates and extraction

tools/summarizer/app.py

@@ -1045,8 +1045,20 @@ async def purge_cache():
 
 
 def _normalize_text(value: str) -> str:
-    value = value.replace("\x00", " ")
-    return re.sub(r"\s+", " ", value).strip()
+    """Normalize extraction noise without destroying section, bullet, or table boundaries."""
+    value = value.replace("\x00", " ").replace("\r\n", "\n").replace("\r", "\n")
+    lines = []
+    blank = False
+    for raw_line in value.split("\n"):
+        line = re.sub(r"[\t\f\v]+", " ", raw_line).strip()
+        if not line:
+            if lines and not blank:
+                lines.append("")
+            blank = True
+            continue
+        lines.append(line)
+        blank = False
+    return "\n".join(lines).strip()
 
 
 def _ocr_image(image: Image.Image) -> str:
@@ -1063,7 +1075,10 @@ def _extract_pdf_text(data: bytes) -> tuple[str, bool, int]:
         reader = PdfReader(io.BytesIO(data))
         page_count = len(reader.pages)
         for page in reader.pages:
-            extracted_pages.append(page.extract_text() or "")
+            try:
+                extracted_pages.append(page.extract_text(extraction_mode="layout") or "")
+            except TypeError:
+                extracted_pages.append(page.extract_text() or "")
     except Exception:
         extracted_pages = []
 
@@ -1084,7 +1099,20 @@ def _extract_pdf_text(data: bytes) -> tuple[str, bool, int]:
 
 def _extract_docx_text(data: bytes) -> str:
     document = Document(io.BytesIO(data))
-    parts = [p.text.strip() for p in document.paragraphs if p.text and p.text.strip()]
+    parts = []
+    blocks = document.iter_inner_content() if hasattr(document, "iter_inner_content") else document.paragraphs
+    for block in blocks:
+        if hasattr(block, "rows"):
+            for row in block.rows:
+                cells = [cell.text.strip() for cell in row.cells if cell.text and cell.text.strip()]
+                if cells:
+                    parts.append(" | ".join(cells))
+        elif getattr(block, "text", "").strip():
+            text = block.text.strip()
+            style = (getattr(getattr(block, "style", None), "name", "") or "").lower()
+            if "role" in style and parts:
+                parts.append("")
+            parts.append(f"- {text}" if "bullet" in style else text)
     return _normalize_text("\n".join(parts))
 
 

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"