pages/BulkDigest.py

import streamlit as st
import os, hashlib, re, sys

# ─── Ensure utils/ is importable ──────────────────────────────
sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "..")))

from utils.file_utils import normalize_log_line
from utils.summarizer import summarize_text
from utils.docgen import generate_doc

st.title("📂 AI Bulk Digest")
st.write("Upload multiple files for batch digestion, summarization, and documentation.")

# Init counters
if "uploaded_files" not in st.session_state:
    st.session_state.uploaded_files = []
if "errors" not in st.session_state:
    st.session_state.errors = []
if "bulk_digests" not in st.session_state:
    st.session_state.bulk_digests = []

uploads = st.file_uploader(
    "Upload files (scripts, logs, text, PDFs)", 
    type=["py", "sh", "txt", "log", "pdf"], 
    accept_multiple_files=True
)

if uploads:
    digests = []
    for f in uploads:
        try:
            content = f.read().decode("utf-8", errors="ignore")
            sha1 = hashlib.sha1(content.encode()).hexdigest()

            # Detect type
            is_log = f.name.endswith(".log")
            is_script = f.name.endswith(".py") or f.name.endswith(".sh")

            # Normalize logs
            if is_log:
                normalized = [normalize_log_line(line) for line in content.splitlines()]
                preview = "\n".join(normalized[:30])
            else:
                preview = "\n".join(content.splitlines()[:30])

            # AI summary
            summary = summarize_text(content)

            # Script docs if applicable
            doc = generate_doc(f.name, "uploaded", content) if is_script else None

            result = {
                "name": f.name,
                "sha1": sha1,
                "preview": preview,
                "summary": summary,
                "doc": doc,
            }
            digests.append(result)

            # Track upload
            st.session_state.uploaded_files.append(f.name)

            # Display in UI
            st.subheader(f"📄 {f.name}")
            st.code(preview)
            st.markdown(f"**SHA1:** `{sha1}`")
            st.write("🧠 **Summary:**", summary)
            if doc:
                st.write("📘 **Generated Documentation:**")
                st.markdown(doc)

        except Exception as e:
            st.error(f"⚠️ Error processing {f.name}: {e}")
            st.session_state.errors.append(str(e))

    # Save to session state for Chatbot
    st.session_state.bulk_digests = digests
    st.success(f"✅ Bulk digestion complete for {len(digests)} files.")