Spaces:
Sleeping
Sleeping
fix filename
Browse files
app.py
CHANGED
|
@@ -2,7 +2,6 @@ import streamlit as st
|
|
| 2 |
import pandas as pd
|
| 3 |
import numpy as np
|
| 4 |
import os
|
| 5 |
-
import glob
|
| 6 |
from grobidmonkey import reader
|
| 7 |
from grobid_client.grobid_client import GrobidClient
|
| 8 |
|
|
@@ -23,29 +22,21 @@ if uploaded_file is not None:
|
|
| 23 |
st.write(len(bytes_data), "bytes")
|
| 24 |
saved_file_path = save_uploaded_file(uploaded_file)
|
| 25 |
|
| 26 |
-
os.makedirs("./grobidoutputs", exist_ok=True)
|
| 27 |
client = GrobidClient(config_path="./grobidconfig.json")
|
| 28 |
client.process("processFulltextDocument",
|
| 29 |
"./uploads/",
|
| 30 |
-
output="./grobidoutputs/",
|
| 31 |
n=20)
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
pattern = os.path.splitext(uploaded_file.name)[0] + ".grobid.tei.xml"
|
| 36 |
-
matching_files = glob.glob(f"{directory}/**/{pattern}", recursive=True)
|
| 37 |
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
|
| 41 |
-
|
| 42 |
-
else:
|
| 43 |
-
st.write("No matching file found.")
|
| 44 |
-
|
| 45 |
-
output_file_path = matching_files[0]
|
| 46 |
|
| 47 |
monkeyReader = reader.MonkeyReader('x2d')
|
| 48 |
-
outline = monkeyReader.readOutline(
|
| 49 |
|
| 50 |
for pre, fill, node in outline:
|
| 51 |
st.write("%s%s" % (pre, node.name))
|
|
|
|
| 2 |
import pandas as pd
|
| 3 |
import numpy as np
|
| 4 |
import os
|
|
|
|
| 5 |
from grobidmonkey import reader
|
| 6 |
from grobid_client.grobid_client import GrobidClient
|
| 7 |
|
|
|
|
| 22 |
st.write(len(bytes_data), "bytes")
|
| 23 |
saved_file_path = save_uploaded_file(uploaded_file)
|
| 24 |
|
|
|
|
| 25 |
client = GrobidClient(config_path="./grobidconfig.json")
|
| 26 |
client.process("processFulltextDocument",
|
| 27 |
"./uploads/",
|
|
|
|
| 28 |
n=20)
|
| 29 |
+
|
| 30 |
+
folder_path = '/path/to/uploads'
|
| 31 |
+
files = os.listdir(folder_path)
|
|
|
|
|
|
|
| 32 |
|
| 33 |
+
for file in files:
|
| 34 |
+
if not file.endswith('.pdf'):
|
| 35 |
+
st.write(f"The other file in the 'uploads' folder is: {file}")
|
| 36 |
+
break
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
|
| 38 |
monkeyReader = reader.MonkeyReader('x2d')
|
| 39 |
+
outline = monkeyReader.readOutline(file)
|
| 40 |
|
| 41 |
for pre, fill, node in outline:
|
| 42 |
st.write("%s%s" % (pre, node.name))
|