Spaces:
Sleeping
Sleeping
File size: 1,780 Bytes
ea5c59c 8d4620d 28c51ee 9ec3b13 395fe09 ea5c59c 8d4620d 28c51ee 8d4620d ea5c59c 8d4620d ea5c59c 1ed0b9b ea5c59c 8d4620d 395fe09 5113d80 e5ef7f9 395fe09 28c51ee 619f943 395fe09 5113d80 675fdb7 0726521 28c51ee d7b55a9 cfcf528 5e43e62 2e65567 fda22ce |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 |
import streamlit as st
import pandas as pd
import numpy as np
import os
import glob
from grobidmonkey import reader
from grobid_client.grobid_client import GrobidClient
def save_uploaded_file(uploaded_file):
file_path = os.path.join("./uploads", uploaded_file.name)
os.makedirs("./uploads", exist_ok=True) # Create 'uploads' directory if it doesn't exist
with open(file_path, "wb") as f:
f.write(uploaded_file.getbuffer())
return file_path # Return the file path as a string
st.title('Paper2Slides')
st.subheader('Upload paper in pdf format')
uploaded_file = st.file_uploader("Choose a file")
if uploaded_file is not None:
st.write(uploaded_file.name)
bytes_data = uploaded_file.getvalue()
st.write(len(bytes_data), "bytes")
saved_file_path = save_uploaded_file(uploaded_file)
os.makedirs("./grobidoutputs", exist_ok=True)
client = GrobidClient(config_path="./grobidconfig.json")
client.process("processFulltextDocument",
"./uploads/",
output="./grobidoutputs/",
n=20)
directory = "$HOME/app"
pattern = os.path.splitext(file_name)[0] + "grobid.tei.xml"
matching_files = glob.glob(f"{directory}/**/{pattern}", recursive=True)
if matching_files:
st.write("Found matching file(s):")
for file in matching_files:
st.write(file)
else:
st.write("No matching file found.")
output_file_path = matching_files[0]
monkeyReader = reader.MonkeyReader('x2d')
outline = monkeyReader.readOutline(output_file_path)
for pre, fill, node in outline:
st.write("%s%s" % (pre, node.name))
# read paper content
essay = monkeyReader.readEssay(saved_file_path)
|