add: pdf parser

requirements.txt

@@ -1,3 +1,6 @@
 altair
 pandas
-streamlit
+PyMuPDF
+streamlit
+streamlit-cropper
+watchdog

src/streamlit_app.py

@@ -1,40 +1,36 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
-
-"""
-# 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])),
-    ))
+import fitz
+from PIL import Image
+import io
+
+st.header("Line Art Data Annotation")
+uploaded_pdf = st.sidebar.file_uploader("Upload a PDF", type=["pdf"])
+
+if uploaded_pdf:
+    data = uploaded_pdf.read()
+    doc = fitz.open(stream=data, filetype="pdf")
+    
+    # Initialize page index in session state
+    if "page_idx" not in st.session_state:
+        st.session_state.page_idx = 0
+
+    total_pages = doc.page_count
+    page_idx = st.session_state.page_idx % total_pages
+    # Navigation buttons (placed above the image)
+    col_prev, col_caption, col_next = st.columns([1, 8, 1])
+    with col_prev:
+        if st.button("<"):
+            st.session_state.page_idx = (page_idx - 1) % total_pages
+            st.rerun()
+    with col_caption:
+        st.markdown(f"<center>Page {page_idx}/{total_pages - 1}</center>", unsafe_allow_html=True)
+    with col_next:
+        if st.button("\>"):
+            st.session_state.page_idx = (page_idx + 1) % total_pages
+            st.rerun()
+
+    # Render image after controls
+    page = doc.load_page(page_idx)
+    pix = page.get_pixmap(dpi=200)
+    img = Image.open(io.BytesIO(pix.tobytes("png")))
+    st.image(img)