#!/usr/bin/env python3
"""Export RESEARCH.org to HTML with Zotero PDF links"""
import argparse
import json
import re
import subprocess
import sys
from socket import setdefaulttimeout
from urllib.request import urlopen, Request
from urllib.error import URLError
BBT_API = "http://localhost:23119/better-bibtex/json-rpc"
TIMEOUT = 5 # seconds
def call_bbt(method, params=None):
"""Call BBT JSON-RPC API with timeout"""
payload = {
"jsonrpc": "2.0",
"method": method,
"id": 1
}
if params is not None:
payload["params"] = params
setdefaulttimeout(TIMEOUT)
req = Request(BBT_API, data=json.dumps(payload).encode('utf-8'),
headers={'Content-Type': 'application/json'})
try:
with urlopen(req) as response:
result = json.loads(response.read().decode('utf-8'))
if 'error' in result:
print(f"BBT API error: {result['error']}", file=sys.stderr)
return None
return result.get('result')
except URLError as e:
print(f"Connection error to BBT API: {e}", file=sys.stderr)
print("Is Zotero with Better BibTeX running?", file=sys.stderr)
return None
except TimeoutError:
print(f"Timeout connecting to BBT API ({TIMEOUT}s)", file=sys.stderr)
return None
except Exception as e:
print(f"Unexpected error calling BBT API: {e}", file=sys.stderr)
return None
def format_author_label(authors, year):
"""Format author label: 'Chow, 1978', 'Arts & Thompson, 2010', 'Kalaji et al., 2011'"""
if not authors:
return "Unknown, Year"
if len(authors) == 1:
return f"{authors[0]['family']}, {year}"
elif len(authors) == 2:
return f"{authors[0]['family']} & {authors[1]['family']}, {year}"
else:
return f"{authors[0]['family']} et al., {year}"
def get_zotero_link(citekey):
"""Get (url, label) tuple for a cite key"""
# First, try to get PDF attachments
attachments = call_bbt("item.attachments", [citekey])
if attachments and len(attachments) > 0:
label = "PDF" # Default, will be refined below
url = attachments[0]['open']
# Try to get proper label from item info
item_info = call_bbt("item.search", [citekey])
if item_info and len(item_info) > 0:
item = item_info[0]
authors = item.get('author', [])
year = item.get('issued', {}).get('date-parts', [['?']])[0][0]
label = format_author_label(authors, year)
return url, label
# Fallback: get item info and construct select link
item_info = call_bbt("item.search", [citekey])
if item_info and len(item_info) > 0:
item = item_info[0]
item_id = item['id']
# Extract item key from URL like "http://zotero.org/users/.../items/ABC12345"
match = re.search(r'/items/([A-Z0-9]+)$', item_id)
if match:
item_key = match.group(1)
label = format_author_label(item.get('author', []),
item.get('issued', {}).get('date-parts', [['?']])[0][0])
return f"zotero://select/library/items/{item_key}", label
return None, None
def main():
parser = argparse.ArgumentParser(description='Export RESEARCH.org to HTML with Zotero links')
parser.add_argument('--input', default='RESEARCH.org', help='Input Org file')
parser.add_argument('--output', default='research.html', help='Output HTML file')
args = parser.parse_args()
# Check BBT API is ready
api_status = call_bbt("api.ready")
if not api_status:
print("Error: BBT API not available. Is Zotero with Better BibTeX running?",
file=sys.stderr)
sys.exit(1)
print(f"BBT API ready: {api_status.get('betterbibtex', 'unknown')}")
# Read Org file
try:
with open(args.input, 'r', encoding='utf-8') as f:
content = f.read()
except FileNotFoundError:
print(f"Error: Input file '{args.input}' not found", file=sys.stderr)
sys.exit(1)
# Extract all cite keys
cite_pattern = r'\[cite:@([a-zA-Z0-9_-]+)\]'
cite_keys = re.findall(cite_pattern, content)
unique_keys = sorted(set(cite_keys))
print(f"Found {len(unique_keys)} unique citations")
# Build citation mapping
citation_map = {}
warnings_count = 0
for citekey in unique_keys:
url, label = get_zotero_link(citekey)
if url:
citation_map[citekey] = (url, label)
print(f" Mapped {citekey} → {label}")
else:
warnings_count += 1
citation_map[citekey] = (None, citekey)
print(f" Warning: Could not map {citekey}", file=sys.stderr)
if warnings_count > 0:
print(f"Completed with {warnings_count} warnings", file=sys.stderr)
# Replace citations with Org links
def replace_citation(match):
citekey = match.group(1)
url, label = citation_map.get(citekey, (None, citekey))
if url:
return f"[[{url}][{label}]]"
return f"[❓cite:@{citekey}]" # Fallback with emoji
processed_content = re.sub(cite_pattern, replace_citation, content)
# CSS and JS to inject
css_to_inject = """
"""
# Run Pandoc to get HTML first, then post-process to inject CSS
cmd = ['pandoc', '--from', 'org', '--to', 'html',
'--standalone', '-']
try:
proc = subprocess.Popen(cmd, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
stdout, stderr = proc.communicate(processed_content.encode('utf-8'))
except FileNotFoundError:
print("Error: pandoc not found on PATH", file=sys.stderr)
sys.exit(1)
if proc.returncode != 0:
print(f"Pandoc error: {stderr.decode('utf-8')}", file=sys.stderr)
sys.exit(1)
# Post-process HTML to inject CSS into
html = stdout.decode('utf-8')
head_match = re.search(r'(.*?)', html, re.DOTALL)
if head_match:
head_content = head_match.group(1)
# Insert CSS into head (before )
new_head = head_content.replace('', css_to_inject + '\n ')
html = html.replace(head_content, new_head, 1)
else:
# No tag found (unexpected), prepend CSS
html = css_to_inject + '\n' + html
# Write final HTML
with open(args.output, 'w', encoding='utf-8') as f:
f.write(html)
print(f"Successfully exported to {args.output}")
if __name__ == "__main__":
main()