Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
|
@@ -5,7 +5,6 @@ import urllib.parse
|
|
| 5 |
from datetime import datetime
|
| 6 |
import pytz
|
| 7 |
import pandas as pd
|
| 8 |
-
import json
|
| 9 |
|
| 10 |
# --- Constants ---
|
| 11 |
MELBOURNE_TIMEZONE = 'Australia/Melbourne'
|
|
@@ -29,21 +28,6 @@ def load_css():
|
|
| 29 |
font-family: 'Courier New', monospace;
|
| 30 |
}
|
| 31 |
|
| 32 |
-
.copy-button {
|
| 33 |
-
background: #e0e0e0;
|
| 34 |
-
color: black;
|
| 35 |
-
border: none;
|
| 36 |
-
padding: 0.5rem 1rem;
|
| 37 |
-
border-radius: 4px;
|
| 38 |
-
cursor: pointer;
|
| 39 |
-
font-size: 0.9rem;
|
| 40 |
-
margin-top: 0.5rem;
|
| 41 |
-
}
|
| 42 |
-
|
| 43 |
-
.copy-button:hover {
|
| 44 |
-
background: #d0d0d0;
|
| 45 |
-
}
|
| 46 |
-
|
| 47 |
.warning-box {
|
| 48 |
background: #f8f8f8;
|
| 49 |
border: 1px solid #e0e0e0;
|
|
@@ -122,45 +106,15 @@ def format_citation_html(url, fragment_text, author, year, scc_hash):
|
|
| 122 |
full_url = f"{url}#:~:text={encoded_fragment}"
|
| 123 |
return f'<a href="{full_url}" data-hash="{scc_hash}">{author} ({year})</a>'
|
| 124 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 125 |
def check_for_fragment(url):
|
| 126 |
return '#:~:text=' in url
|
| 127 |
|
| 128 |
-
def copy_to_clipboard_js(text, button_id):
|
| 129 |
-
"""Generate JavaScript for copying text to clipboard with proper escaping."""
|
| 130 |
-
# Escape special characters for JavaScript string
|
| 131 |
-
escaped_text = json.dumps(text).strip('"').replace('</', '<\\/') # Properly escape for JS
|
| 132 |
-
return f"""
|
| 133 |
-
<script>
|
| 134 |
-
function copyToClipboard_{button_id}() {{
|
| 135 |
-
const textToCopy = `{escaped_text}`;
|
| 136 |
-
if (navigator.clipboard) {{
|
| 137 |
-
navigator.clipboard.writeText(textToCopy).then(function() {{
|
| 138 |
-
const statusElement = document.getElementById('copy_status_{button_id}');
|
| 139 |
-
if (statusElement) {{
|
| 140 |
-
statusElement.innerHTML = 'Copied!';
|
| 141 |
-
setTimeout(function() {{
|
| 142 |
-
statusElement.innerHTML = '';
|
| 143 |
-
}}, 2000);
|
| 144 |
-
}}
|
| 145 |
-
}}, function(err) {{
|
| 146 |
-
const statusElement = document.getElementById('copy_status_{button_id}');
|
| 147 |
-
if (statusElement) {{
|
| 148 |
-
statusElement.innerHTML = 'Copy failed';
|
| 149 |
-
}}
|
| 150 |
-
console.error('Could not copy text: ', err);
|
| 151 |
-
}});
|
| 152 |
-
}} else {{
|
| 153 |
-
const statusElement = document.getElementById('copy_status_{button_id}');
|
| 154 |
-
if (statusElement) {{
|
| 155 |
-
statusElement.innerHTML = 'Clipboard API not supported';
|
| 156 |
-
}}
|
| 157 |
-
}}
|
| 158 |
-
}}
|
| 159 |
-
</script>
|
| 160 |
-
<button onclick="copyToClipboard_{button_id}()" class="copy-button">Copy to Clipboard</button>
|
| 161 |
-
<span id="copy_status_{button_id}" style="margin-left: 10px; font-weight: bold;"></span>
|
| 162 |
-
"""
|
| 163 |
-
|
| 164 |
# --- Live Clock JavaScript ---
|
| 165 |
def live_clock():
|
| 166 |
return """
|
|
@@ -299,8 +253,9 @@ with tabs[0]:
|
|
| 299 |
""", unsafe_allow_html=True)
|
| 300 |
else:
|
| 301 |
scc_hash = generate_citation_hash(author_name, publication_year, source_url, annotated_text, annotated_text, username, task_name, current_date, current_time)
|
| 302 |
-
citation_link_start =
|
| 303 |
citation_link_end = f'<a href="{source_url}#:~:text={urllib.parse.quote(annotated_text)}" data-hash="{scc_hash}">({author_name}, {publication_year})</a>'
|
|
|
|
| 304 |
|
| 305 |
st.markdown("## Generated Citations")
|
| 306 |
col_html1, col_html2 = st.columns(2)
|
|
@@ -308,40 +263,21 @@ with tabs[0]:
|
|
| 308 |
# HTML Citation - Start of Text
|
| 309 |
with col_html1:
|
| 310 |
st.markdown("### Citation (Start of Text)")
|
| 311 |
-
html_citation_start = citation_link_start
|
| 312 |
-
|
| 313 |
st.markdown('<div class="rendered-citation">', unsafe_allow_html=True)
|
| 314 |
-
st.markdown(
|
| 315 |
-
st.markdown(copy_to_clipboard_js(html_citation_start.replace('`', '\\`'), "html_start"), unsafe_allow_html=True)
|
| 316 |
st.markdown('</div>', unsafe_allow_html=True)
|
| 317 |
|
| 318 |
# HTML Citation - End of Text
|
| 319 |
with col_html2:
|
| 320 |
st.markdown("### Citation (End of Text)")
|
| 321 |
-
html_citation_end = citation_link_end
|
| 322 |
-
|
| 323 |
st.markdown('<div class="rendered-citation">', unsafe_allow_html=True)
|
| 324 |
-
st.markdown(
|
| 325 |
-
st.markdown(copy_to_clipboard_js(html_citation_end.replace('`', '\\`'), "html_end"), unsafe_allow_html=True)
|
| 326 |
st.markdown('</div>', unsafe_allow_html=True)
|
| 327 |
|
| 328 |
-
#
|
| 329 |
-
st.markdown("###
|
| 330 |
-
hash_details = {
|
| 331 |
-
"author": author_name,
|
| 332 |
-
"year": publication_year,
|
| 333 |
-
"url": source_url,
|
| 334 |
-
"fragment_text": annotated_text,
|
| 335 |
-
"cited_text": annotated_text,
|
| 336 |
-
"username": username,
|
| 337 |
-
"task_name": task_name,
|
| 338 |
-
"date": current_date,
|
| 339 |
-
"time": current_time,
|
| 340 |
-
"hash": scc_hash
|
| 341 |
-
}
|
| 342 |
-
|
| 343 |
st.markdown('<div class="hash-display">', unsafe_allow_html=True)
|
| 344 |
-
st.
|
| 345 |
st.markdown('</div>', unsafe_allow_html=True)
|
| 346 |
|
| 347 |
# Guidance on Verifying Citations
|
|
@@ -423,7 +359,7 @@ with tabs[1]:
|
|
| 423 |
"Year": verify_publication_year,
|
| 424 |
"URL": verify_source_url,
|
| 425 |
"Fragment text": verify_annotated_text,
|
| 426 |
-
"
|
| 427 |
"Username": verify_username,
|
| 428 |
"Task name": verify_task_name,
|
| 429 |
"Date": verify_date,
|
|
|
|
| 5 |
from datetime import datetime
|
| 6 |
import pytz
|
| 7 |
import pandas as pd
|
|
|
|
| 8 |
|
| 9 |
# --- Constants ---
|
| 10 |
MELBOURNE_TIMEZONE = 'Australia/Melbourne'
|
|
|
|
| 28 |
font-family: 'Courier New', monospace;
|
| 29 |
}
|
| 30 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
.warning-box {
|
| 32 |
background: #f8f8f8;
|
| 33 |
border: 1px solid #e0e0e0;
|
|
|
|
| 106 |
full_url = f"{url}#:~:text={encoded_fragment}"
|
| 107 |
return f'<a href="{full_url}" data-hash="{scc_hash}">{author} ({year})</a>'
|
| 108 |
|
| 109 |
+
def format_metadata_html(url, author, year, scc_hash, username, task_name, current_date, current_time):
|
| 110 |
+
metadata = f"{username}—{task_name}—{current_date}—{current_time}"
|
| 111 |
+
encoded_metadata = urllib.parse.quote(metadata)
|
| 112 |
+
full_url = f"{url}#:~:text={encoded_metadata}"
|
| 113 |
+
return f'<a href="{full_url}" data-hash="{scc_hash}">{author} ({year}). {scc_hash}</a>'
|
| 114 |
+
|
| 115 |
def check_for_fragment(url):
|
| 116 |
return '#:~:text=' in url
|
| 117 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 118 |
# --- Live Clock JavaScript ---
|
| 119 |
def live_clock():
|
| 120 |
return """
|
|
|
|
| 253 |
""", unsafe_allow_html=True)
|
| 254 |
else:
|
| 255 |
scc_hash = generate_citation_hash(author_name, publication_year, source_url, annotated_text, annotated_text, username, task_name, current_date, current_time)
|
| 256 |
+
citation_link_start = format_citation_html(source_url, annotated_text, author_name, publication_year, scc_hash)
|
| 257 |
citation_link_end = f'<a href="{source_url}#:~:text={urllib.parse.quote(annotated_text)}" data-hash="{scc_hash}">({author_name}, {publication_year})</a>'
|
| 258 |
+
metadata_link = format_metadata_html(source_url, author_name, publication_year, scc_hash, username, task_name, current_date, current_time)
|
| 259 |
|
| 260 |
st.markdown("## Generated Citations")
|
| 261 |
col_html1, col_html2 = st.columns(2)
|
|
|
|
| 263 |
# HTML Citation - Start of Text
|
| 264 |
with col_html1:
|
| 265 |
st.markdown("### Citation (Start of Text)")
|
|
|
|
|
|
|
| 266 |
st.markdown('<div class="rendered-citation">', unsafe_allow_html=True)
|
| 267 |
+
st.markdown(citation_link_start, unsafe_allow_html=True)
|
|
|
|
| 268 |
st.markdown('</div>', unsafe_allow_html=True)
|
| 269 |
|
| 270 |
# HTML Citation - End of Text
|
| 271 |
with col_html2:
|
| 272 |
st.markdown("### Citation (End of Text)")
|
|
|
|
|
|
|
| 273 |
st.markdown('<div class="rendered-citation">', unsafe_allow_html=True)
|
| 274 |
+
st.markdown(citation_link_end, unsafe_allow_html=True)
|
|
|
|
| 275 |
st.markdown('</div>', unsafe_allow_html=True)
|
| 276 |
|
| 277 |
+
# SCC Ledger
|
| 278 |
+
st.markdown("### SCC Ledger")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 279 |
st.markdown('<div class="hash-display">', unsafe_allow_html=True)
|
| 280 |
+
st.markdown(metadata_link, unsafe_allow_html=True)
|
| 281 |
st.markdown('</div>', unsafe_allow_html=True)
|
| 282 |
|
| 283 |
# Guidance on Verifying Citations
|
|
|
|
| 359 |
"Year": verify_publication_year,
|
| 360 |
"URL": verify_source_url,
|
| 361 |
"Fragment text": verify_annotated_text,
|
| 362 |
+
"Cited text": verify_annotated_text,
|
| 363 |
"Username": verify_username,
|
| 364 |
"Task name": verify_task_name,
|
| 365 |
"Date": verify_date,
|