"""Build paper/references.bib from literature/references_verified.csv (only verified entries)."""
import re, pandas as pd
from src.common import ROOT, get_logger
log = get_logger("bib")

def tex(s): return str(s).replace("&", "&").replace("\\&", "&").replace("&", "\\&") if isinstance(s, str) else ""

def main():
    df = pd.read_csv(ROOT / "literature" / "references_verified.csv"); df = df[df.verified == True]
    out = []
    for _, r in df.iterrows():
        title = tex(r.crossref_title if isinstance(r.crossref_title, str) and r.crossref_title else r.title).replace("‐", "-")
        authors = r.authors if isinstance(r.authors, str) and r.authors else r.author
        authors = " and ".join(a.strip() for a in str(authors).split(";") if a.strip()) if ";" in str(authors) else str(authors)
        yr = int(r.pub_year) if pd.notna(r.pub_year) else int(r.year)
        typ = str(r.type) if isinstance(r.type, str) else "journal-article"
        if typ == "report" or r.key == "competitionbureau2023":
            out.append(f"@techreport{{{r.key},\n  author = {{{authors}}},\n  title = {{{title}}},\n  institution = {{Competition Bureau Canada}},\n  year = {{{yr}}},\n  url = {{https://competition-bureau.canada.ca}}\n}}\n")
            continue
        if typ == "posted-content":   # preprint / working paper (SSRN): cite as unpublished work with DOI
            out.append(f"@unpublished{{{r.key},\n  author = {{{authors}}},\n  title = {{{title}}},\n  note = {{Working paper, SSRN}},\n  year = {{{yr}}},\n  doi = {{{r.doi}}}\n}}\n")
            continue
        if typ in ("book", "monograph"):
            out.append(f"@book{{{r.key},\n  author = {{{authors}}},\n  title = {{{title}}},\n  publisher = {{{tex(r.publisher)}}},\n  year = {{{yr}}}" + (f",\n  doi = {{{r.doi}}}" if isinstance(r.doi, str) else "") + "\n}\n")
            continue
        fields = [f"  author = {{{authors}}}", f"  title = {{{title}}}", f"  journal = {{{tex(r.journal)}}}", f"  year = {{{yr}}}"]
        if pd.notna(r.volume) and str(r.volume) != "nan": fields.append(f"  volume = {{{str(r.volume).replace('.0', '')}}}")
        if pd.notna(r.issue) and str(r.issue) != "nan": fields.append(f"  number = {{{str(r.issue).replace('.0', '')}}}")
        if pd.notna(r.pages) and str(r.pages) != "nan": fields.append(f"  pages = {{{str(r.pages).replace('-', '--')}}}")
        if isinstance(r.doi, str) and r.doi: fields.append(f"  doi = {{{r.doi}}}")
        elif isinstance(r.note, str) and "jstor" in r.note: fields.append(f"  note = {{{re.search(r'https?://[^ ]+', r.note).group(0)}}}")
        out.append(f"@article{{{r.key},\n" + ",\n".join(fields) + "\n}\n")
    (ROOT / "paper" / "references.bib").write_text("% Generated from literature/references_verified.csv — every entry verified via Crossref or a stable URL\n" + "\n".join(out))
    log.info("wrote %d entries", len(out))

if __name__ == "__main__":
    main()