Update app.py

app.py

@@ -1,88 +1,4 @@
-import os, io, re, json
 import streamlit as st
-from PIL import Image
-
-import pdfplumber                 # text layer for PDFs
-from pdf2image import convert_from_bytes  # render image-only PDFs
-import pytesseract                # OCR
-
-st.set_page_config(page_title="Flyer → Where & When", page_icon="📰", layout="centered")
-st.title("📰 Flyer → Where & When")
-st.caption("Upload a flyer (PDF/JPG/PNG). I’ll read it and pull out the date, time, and location.")
-
-DATE_PAT = r"(\b\w{3,9}\b\s+\d{1,2}(?:,\s*\d{4})?)|\b\d{1,2}/\d{1,2}/\d{2,4}\b"
-TIME_PAT = r"\b(\d{1,2}:\d{2}\s*[AP]M|\d{1,2}\s*[AP]M)\b"
-LOC_HINTS = r"(Location|Where|Address|Venue|At)[:\-\s]+(.+)"
-
-def pdf_bytes_to_text(pdf_bytes: bytes) -> str:
-    # Try selectable text first (more accurate)
-    parts = []
-    try:
-        with pdfplumber.open(io.BytesIO(pdf_bytes)) as pdf:
-            for page in pdf.pages:
-                t = page.extract_text() or ""
-                if t.strip():
-                    parts.append(t)
-    except Exception:
-        pass
-    if parts:
-        return "\n\n".join(parts)
-    # Fallback to OCR (image-only PDF)
-    txts = []
-    for img in convert_from_bytes(pdf_bytes, fmt="png", dpi=200):
-        txts.append(pytesseract.image_to_string(img))
-    return "\n".join(txts)
-
-def image_bytes_to_text(img_bytes: bytes) -> str:
-    img = Image.open(io.BytesIO(img_bytes)).convert("RGB")
-    return pytesseract.image_to_string(img)
-
-def extract_where_when(text: str):
-    # Dates (flatten alternation tuples)
-    dates_raw = re.findall(DATE_PAT, text, flags=re.I)
-    dates = []
-    for tup in dates_raw:
-        s = [t for t in tup if t]
-        if s: dates.append(s[0])
-    times = re.findall(TIME_PAT, text, flags=re.I)
-    m = re.search(LOC_HINTS, text, flags=re.I)
-    location = m.group(2).strip() if m else ""
-    return {"dates_found": dates, "times_found": times, "location": location}
-
-uploaded = st.file_uploader("Upload flyer", type=["pdf", "png", "jpg", "jpeg"])
-manual_text = st.text_area("Or paste text manually (optional)", height=140)
-
-if st.button("Read flyer"):
-    if not uploaded and not manual_text.strip():
-        st.warning("Please upload a file or paste some text.")
-        st.stop()
-
-    raw = ""
-    if uploaded:
-        if uploaded.type == "application/pdf":
-            raw = pdf_bytes_to_text(uploaded.read())
-        else:
-            raw = image_bytes_to_text(uploaded.read())
-
-    combined_text = manual_text.strip() or raw
-    if not combined_text.strip():
-        st.error("I couldn’t read any text. Try exporting your Canva flyer as Standard PDF or a larger PNG.")
-        st.stop()
-
-    results = extract_where_when(combined_text)
-    st.success("Done! Here’s what I found:")
-    c1, c2 = st.columns(2)
-    with c1:
-        st.markdown("**Date(s):**")
-        st.write(",  ".join(results["dates_found"]) if results["dates_found"] else "—")
-        st.markdown("**Time(s):**")
-        st.write(",  ".join(results["times_found"]) if results["times_found"] else "—")
-    with c2:
-        st.markdown("**Location:**")
-        st.write(results["location"] or "—")
-
-    st.markdown("---")
-    st.markdown("**All extracted text (for reference):**")
-    st.code(combined_text[:3000])
-    st.download_button("Download JSON", data=json.dumps(results, indent=2),
-                       file_name="where_when.json", mime="application/json")
+st.set_page_config(page_title="OK", page_icon="✅")
+st.title("✅ Streamlit + Docker is running")
+st.write("If you can see this page, your Docker Space is healthy.")