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 = "From Corporate Disclosures to a Russell 3000 Strategic Project Database"
# --- 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("Identification, Measurement"):
        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 = "Identification, Measurement, Validation, and Research Applications"
cp.author = "Manel Kammoun; Djerrycharli Tandjambianda; Simon-Pierre Boucher"
cp.keywords = "SEC filings, text as data, corporate investment, strategic projects, information extraction, large language models, entity resolution, Russell 3000"
cp.comments = "UQO Working Paper No. 0001 (FIRC-funded), Version 1.0, October 28, 2026 (working draft under validation)"
cp.created = cp.modified = datetime.datetime(2026, 10, 28, 12, 0)
# --- base fonts closer to the PDF (Times)
from docx.oxml.ns import qn
for st in doc.styles:
    try:
        if st.type == 1 and st.font is not None and (st.name == "Normal" or st.name.startswith("Heading") or st.name in ("Title", "Body Text", "First Paragraph", "Compact", "Caption", "Bibliography", "Block Text")):
            st.font.name = "Times New Roman"
            rpr = st.element.get_or_add_rPr(); rf = rpr.find(qn("w:rFonts"))
            if rf is None:
                rf = rpr.makeelement(qn("w:rFonts"), {}); rpr.append(rf)
            for a in ("w:ascii", "w:hAnsi", "w:eastAsia", "w:cs"): rf.set(qn(a), "Times New Roman")
            if st.name in ("Normal", "Body Text", "First Paragraph", "Compact"): st.font.size = Pt(12)
    except Exception:
        pass
# --- wide tables: smaller font and tight cell padding so that 8-10 column tables fit the page width
from docx.shared import Inches
from docx.oxml import OxmlElement
for sec in doc.sections:
    sec.left_margin = sec.right_margin = Inches(0.85)
for tbl in doc.tables:
    ncol = max(len(r.cells) for r in tbl.rows)
    if ncol >= 7:
        size = Pt(7) if ncol >= 9 else Pt(8)
        tbl.autofit = True
        for row in tbl.rows:
            for cell in row.cells:
                for para in cell.paragraphs:
                    para.paragraph_format.space_after = Pt(0); para.paragraph_format.space_before = Pt(0)
                    for run in para.runs: run.font.size = size
                tcPr = cell._tc.get_or_add_tcPr(); mar = OxmlElement("w:tcMar")
                for side in ("left", "right"):
                    el = OxmlElement(f"w:{side}"); el.set(qn("w:w"), "30"); el.set(qn("w:type"), "dxa"); mar.append(el)
                tcPr.append(mar)
# --- proportional column widths for wide tables (pandoc emits equal 0.55-inch grid columns)
TOTAL = 9792  # twips: 8.5in - 2 x 0.85in margins
for tbl in doc.tables:
    ncol = max(len(r.cells) for r in tbl.rows)
    if ncol < 7: continue
    lens = [1] * ncol
    for row in tbl.rows:
        for j, cell in enumerate(row.cells[:ncol]):
            lens[j] = max(lens[j], min(28, max((len(w) for w in cell.text.split()), default=1)))
    weights = [max(l, 4) for l in lens]; tot = sum(weights); widths = [int(TOTAL * wgt / tot) for wgt in weights]
    grid = tbl._tbl.find(qn("w:tblGrid"))
    if grid is not None:
        for g, wd in zip(grid.findall(qn("w:gridCol")), widths): g.set(qn("w:w"), str(wd))
    tblPr = tbl._tbl.tblPr
    for e in tblPr.findall(qn("w:tblW")): e.set(qn("w:type"), "dxa"); e.set(qn("w:w"), str(TOTAL))
    for e in tblPr.findall(qn("w:tblLayout")): e.set(qn("w:type"), "fixed")
    for row in tbl.rows:
        for j, cell in enumerate(row.cells[:ncol]):
            tcPr = cell._tc.get_or_add_tcPr(); tcW = tcPr.find(qn("w:tcW"))
            if tcW is None: tcW = OxmlElement("w:tcW"); tcPr.insert(0, tcW)
            tcW.set(qn("w:type"), "dxa"); tcW.set(qn("w:w"), str(widths[j]))
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")