import pandas as pd
import streamlit as st
from utils import nav_to, df_to_html, render_svg, combine_json_files, render_metadata
data = combine_json_files('./languages')
@st.cache_data
def render_home_table():
"""Renders home table."""
# Compute number of unique domains/urls
for key in data.keys():
data[key]['Number of Sites'] = len(data[key].get('Sites', []))
data[key]["Number of Links"] = sum(len(url_data["Links"]) for url_data in data[key].get('Sites', []))
# Convert dict to df
df_data = pd.DataFrame(data).transpose()
df_data['ISO Code'] = df_data.index
# Sort by ISO Code
df_data = df_data.sort_values(by='ISO Code')
df_data['Number of Sites'] = df_data['Number of Sites'].astype(str) # Convert to string
df_data['ISO Code'] = df_data['ISO Code'].astype(str) # Convert to string
df_data['Number of Sites'] = df_data.apply(lambda row: '{}'.format(row['ISO Code'], row['Number of Sites']), axis=1)
df_data['Number of Links'] = df_data.apply(lambda row: '{}'.format(row['ISO Code'], row['Number of Links']), axis=1)
# Display the table
df_data = df_data[['ISO Code', 'Language Name', 'Family', 'Subgrouping', 'Number of Sites', 'Number of Links', 'Number of Speakers', 'Supported by allenai/MADLAD-400 or facebook/flores']]
st.write(df_to_html(df_data), unsafe_allow_html=True)
@st.cache_data
def render_site_table(isocode):
# back
back_text = 'Back'
st.markdown(back_text, unsafe_allow_html=True)
st.write({'Language Name': data[isocode]['Language Name'], 'ISO Code': isocode})
# site
urls = data[isocode].get('Sites', [])
df_urls = pd.DataFrame(urls)
df_urls['Number of Links'] = df_urls['Links'].apply(len)
df_urls = df_urls.sort_values(by='Number of Links', ascending=False)
df_urls = df_urls.reset_index(drop=True)
df_urls['Number of Links'] = df_urls.apply(lambda row: '{}'.format(isocode, row['Site URL'], row['Number of Links']) if row['Number of Links'] else row['Number of Links'], axis=1)
# Display the table
df_urls = df_urls[['Site Name', 'Site URL', 'Category', 'Number of Links', 'Possible Parallel Languages', 'Confidence', 'Info']]
st.write(df_to_html(df_urls), unsafe_allow_html=True)
@st.cache_data
def render_siteurl_table(isocode, url):
# back
back_text = 'Back'.format(isocode)
st.markdown(back_text, unsafe_allow_html=True)
# Find selected domain
urls = data[isocode].get('Sites', [])
selected_domain = next((d for d in urls if 'Site URL' in d and d['Site URL'] == url), None)
if selected_domain:
st.write({'Language Name': data[isocode]['Language Name'], 'ISO Code': isocode, 'Site URL': url, 'Links': selected_domain['Links']})
@st.cache_data
def render_links_table(isocode):
# back
back_text = 'Back'
st.markdown(back_text, unsafe_allow_html=True)
# output
urls = data[isocode].get('Sites', [])
lang_name = data[isocode]['Language Name']
all_urls = [{'Site URL': du['Site URL'], 'Links': du['Links']} for du in urls]
st.write({'Language Name': lang_name, 'ISO Code': isocode, 'URLs': all_urls})
# show logo
render_svg(open("assets/glotweb_logo.svg").read())
render_metadata()
st.markdown("**GlotWeb** is an indexing service for low-resource languages. It indexes sites or links written in each language. This list can be used to create raw text or parallel corpora and to study low-resource languages on the web.")
st.text("")
def main():
params = st.query_params
if 'isocode' in params:
if 'siteurl' in params:
render_siteurl_table(params['isocode'], params['siteurl'])
if 'site' in params:
render_site_table(params['isocode'])
if 'links' in params:
render_links_table(params['isocode'])
elif 'home' not in params:
# redirect to .space
nav_to('https://cis-lmu-glotweb.hf.space/?home=True')
else:
# show home
render_home_table()
main()