import sys, re, datetime
from docx import Document
from docx.shared import Pt
from docx.enum.text import WD_ALIGN_PARAGRAPH
path = sys.argv[1]; doc = Document(path)
paras = doc.paragraphs
norm = lambda p: re.sub(r"\s+", " ", p.text.replace(" ", " ")).strip()
title = "Does the Language of Artificial Intelligence Move Markets?"
# --- title page: everything before the Abstract block is centred
i_abs = next(i for i, p in enumerate(paras) if norm(p) == "Abstract")
for p in paras[:i_abs - 1]:
    p.alignment = WD_ALIGN_PARAGRAPH.CENTER
    if norm(p) == title:
        for r in p.runs: r.font.size = Pt(18); r.font.bold = True
    elif norm(p).startswith("A Semantic Analysis"):
        for r in p.runs: r.font.size = Pt(13)
# --- move References (pandoc appends it at the end) before the appendix, as in the PDF
h1 = [p for p in paras if p.style.name == "Heading 1"]
refs = next(p for p in h1 if norm(p) == "References")
appA = next(p for p in h1 if re.match(r"^A [A-Z]", norm(p)))
body = doc.element.body; kids = list(body)
i_refs, i_app = kids.index(refs._p), kids.index(appA._p)
moved = [k for k in kids[i_refs:] if k.tag.endswith("}sectPr") is False]
for k in moved: appA._p.addprevious(k)
# --- page breaks where the LaTeX source has \newpage
breaks = 0
paras[i_abs - 1].paragraph_format.page_break_before = True; breaks += 1
for p in h1:
    t = norm(p)
    if t.startswith("1 Introduction") or t == "References" or p is appA:
        p.paragraph_format.page_break_before = True; breaks += 1
# --- document properties
cp = doc.core_properties
cp.title = title
cp.subject = "A Semantic Analysis of S&P 500 SEC Filings and the Cross-Section of Stock Returns, 2010–2026"
cp.author = "Manel Kammoun; Djerrycharli Tandjambianda; Simon-Pierre Boucher"
cp.keywords = "textual analysis, sentence embeddings, artificial intelligence, disclosure, cross-section of returns"
cp.comments = "UQO Working Paper No. 17, Version 1.1, October 26, 2026"
cp.created = cp.modified = datetime.datetime(2026, 10, 26, 12, 0)
doc.save(path)
print(f"post-processed: {i_abs-1} title-page paragraphs centred, {len(moved)} reference paragraphs moved before appendix, {breaks} page breaks, properties set")