#!/usr/bin/env python3
"""WP44 — generate manuscript/tables/numbers.tex: every number quoted in the prose is a LaTeX macro produced here from
result files (never typed by hand). Macro names use letters only (no digits: `\\nCoreEligible`, not `\\n2026`).
Sources: data/metadata/prisma_counts.json, linkage_report.json, results/bibliometrics/*.csv, results/econometrics/*.json,
taxonomy/validation/metrics.json, results/emerging/metrics_h12.json (each optional: missing → macro undefined → compile error,
which is intended: the prose cannot cite a number that does not exist)."""
import json, os, sys, csv, re
R = sys.argv[1] if len(sys.argv) > 1 else os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
out = []
WORDS = {"0": "Zero", "1": "One", "2": "Two", "3": "Three", "4": "Four", "5": "Five", "6": "Six", "7": "Seven", "8": "Eight", "9": "Nine"}
def name(s):
    s = re.sub(r"[^A-Za-z0-9]+", " ", s).title().replace(" ", "")
    return "".join(WORDS[ch] if ch.isdigit() else ch for ch in s)
def fmt(v):
    if isinstance(v, bool): return str(v)
    if isinstance(v, int): return f"{v:,}".replace(",", "{,}")
    if isinstance(v, float):
        return f"{v:,.3f}".replace(",", "{,}") if abs(v) < 100 else f"{v:,.1f}".replace(",", "{,}")
    return str(v).replace("%", "\\%").replace("_", "\\_")
def emit(k, v):
    out.append(f"\\newcommand{{\\{name(k)}}}{{{fmt(v)}}}")
def walk(prefix, obj):
    if isinstance(obj, dict):
        for k, v in obj.items(): walk(f"{prefix} {k}", v)
    elif isinstance(obj, (int, float, str, bool)) and obj is not None:
        emit(prefix, obj)
p = os.path.join(R, "data/metadata/prisma_counts.json")
if os.path.exists(p): walk("prisma", json.load(open(p)))
p = os.path.join(R, "data/metadata/linkage_report.json")
if os.path.exists(p): walk("link", json.load(open(p)))
for f in ["volume_yearly", "citation_windows_yearly", "international_collab_yearly", "industry_share_yearly", "venue_hhi_yearly"]:
    p = os.path.join(R, "results/bibliometrics", f + ".csv")
    if os.path.exists(p):
        for row in csv.DictReader(open(p)):
            y = row.get("year") or row.get("publication_year")
            for k, v in row.items():
                if k in ("year", "publication_year") or v in ("", None): continue
                try: v = int(v) if re.fullmatch(r"-?\d+", v) else float(v)
                except ValueError: pass
                emit(f"{f} {y} {k}", v)
for f, key in [("results/econometrics/its_results.json", "its"), ("taxonomy/validation/metrics.json", "val"), ("results/emerging/metrics_h12.json", "emerg"), ("results/emerging/metrics_h24.json", "emergTwoFour")]:
    p = os.path.join(R, f)
    if os.path.exists(p):
        d = json.load(open(p))
        walk(key, {k: v for k, v in d.items() if not isinstance(v, (list,))})
for f, key in [("data/metadata/dblp_parse_report.json", "dblp"), ("data/metadata/acl_parse_report.json", "acl"), ("data/metadata/api_increment_ledger.json", "increment"), ("data/metadata/increment_report.json", "incrementIngest")]:
    p = os.path.join(R, f)
    if os.path.exists(p):
        d = json.load(open(p))
        if key == "increment":
            sl = d.get("slices", {}); emit("increment api calls", d.get("calls", 0)); emit("increment records retrieved", sum(v.get("records", 0) for v in sl.values()))
            emit("increment truncated slices", sum(1 for v in sl.values() if v.get("truncated"))); emit("increment slices done", sum(1 for v in sl.values() if v.get("done"))); emit("increment cost usd", round(d.get("cost_usd_total", 0), 4))
        elif key == "incrementIngest":
            emit("increment new works", d.get("new_works", 0)); emit("increment already in snapshot", d.get("already_in_snapshot", 0))
        elif key == "dblp":
            emit("dblp parsed records", d.get("rows_written", 0)); [emit(f"dblp type {k}", v) for k, v in d.get("counts_by_type", {}).items()]
        elif key == "acl":
            emit("acl parsed entries", d.get("entries", 0))
for f, key in [("reports/classification_report.json", "classification"), ("literature_synthesis/landmarks/selection_report.json", "selection"), ("data/metadata/linkage_sample_summary.json", "linkagesample")]:
    p = os.path.join(R, f)
    if os.path.exists(p): walk(key, json.load(open(p)))
p = os.path.join(R, "results/emerging/known_set_lead_times.csv")
if os.path.exists(p):
    for row in csv.DictReader(open(p)):
        for k in ("total_works", "detection_month", "peak_growth_month", "lead_months"):
            v = row.get(k)
            if v in ("", None): continue
            try: v = int(float(v)) if re.fullmatch(r"-?\d+(\.0)?", v) else v
            except ValueError: pass
            emit(f"known {row['concept']} {k}", v)
    leads = [int(float(r["lead_months"])) for r in csv.DictReader(open(p)) if r.get("lead_months") not in ("", None)]
    if leads:
        import statistics; emit("known set median lead months", int(statistics.median(leads))); emit("known set n detected", len(leads)); emit("known set n positive lead", sum(1 for l in leads if l > 0))
open(os.path.join(R, "manuscript/tables/numbers.tex"), "w").write("% machine-generated by tables/make_numbers.py — do not edit\n" + "\n".join(out) + "\n")
print(len(out), "macros")