Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,60 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+from docx import Document
+from io import BytesIO
 
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+st.set_page_config(page_title="Doc Cleaner", layout="wide")
+
+st.title("📄 DOCX Heading Cleaner")
+
+uploaded_file = st.file_uploader("Upload a .docx file", type=["docx"])
+
+if uploaded_file:
+    doc = Document(uploaded_file)
+
+    removed_headings = []
+    cleaned_paragraphs = []
+
+    for para in doc.paragraphs:
+        style_name = para.style.name.lower()
+
+        # Detect headings
+        if "heading" in style_name:
+            removed_headings.append(para.text.strip())
+        else:
+            if para.text.strip():
+                cleaned_paragraphs.append(para.text.strip())
+
+    # Join cleaned text as paragraphs
+    cleaned_text = "\n\n".join(cleaned_paragraphs)
+
+    st.subheader("🗑️ Removed Headings")
+    if removed_headings:
+        for i, h in enumerate(removed_headings, 1):
+            st.write(f"{i}. {h}")
+    else:
+        st.info("No headings found")
+
+    st.subheader("📝 Cleaned Text")
+
+    st.text_area(
+        "Paragraph Content",
+        value=cleaned_text,
+        height=400
+    )
+
+    # Optional: Download cleaned text as DOCX
+    if st.button("Download Cleaned DOCX"):
+        new_doc = Document()
+        for para in cleaned_paragraphs:
+            new_doc.add_paragraph(para)
+
+        buffer = BytesIO()
+        new_doc.save(buffer)
+        buffer.seek(0)
+
+        st.download_button(
+            label="Download",
+            data=buffer,
+            file_name="cleaned.docx",
+            mime="application/vnd.openxmlformats-officedocument.wordprocessingml.document"
+        )