Sales Trainer v0.1: corporate sales-training simulator (Flask+Vue, 15 personas, chat simulator, judge, analytics)

- Auth/roles (no self-reg), admin user provision, JWT
- Analyze: sales kit + initial pain-fit from form/upload
- Persona generator: 15 personas (5/tier) w/ pain variety, negotiation, init mode, channel, latent/revealable, wrong_text special
- Chat simulator: per-mode initiation, one-shot, hidden signals, judge-LLM debrief+coaching
- Trainee loop: win/lose board, weak-areas, user-generated personas
- Admin analytics; EN+TH Vue SPA served by Flask
- Deploy: Dockerfile, docker-compose, README, eng-log + HANDOFF
- Tests (mock LLM): m0/m1/routes/e2e all pass

backend/app/services/file_parser.py

@@ -0,0 +1,46 @@
+"""File parsing for uploaded documents (pdf / markdown / txt)."""
+from __future__ import annotations
+
+from pathlib import Path
+
+
+class ParseError(Exception):
+    pass
+
+
+def parse_pdf(path: Path) -> str:
+    import fitz  # PyMuPDF
+
+    try:
+        doc = fitz.open(path)
+    except Exception as exc:
+        raise ParseError(f"cannot open PDF: {exc}") from exc
+    parts = []
+    for page in doc:
+        parts.append(page.get_text())
+    doc.close()
+    return "\n".join(parts)
+
+
+def parse_text(path: Path) -> str:
+    import chardet
+
+    raw = path.read_bytes()
+    # Try utf-8 first, else detect encoding
+    try:
+        return raw.decode("utf-8")
+    except UnicodeDecodeError:
+        pass
+    guess = chardet.detect(raw)
+    enc = guess.get("encoding") or "utf-8"
+    try:
+        return raw.decode(enc, errors="replace")
+    except Exception:
+        return raw.decode("utf-8", errors="replace")
+
+
+def parse_document(path: Path) -> str:
+    ext = path.suffix.lower().lstrip(".")
+    if ext == "pdf":
+        return parse_pdf(path)
+    return parse_text(path)