el/elp/tests/lang-gen/gen_elp_seed_full.py

# -*- coding: utf-8 -*-
"""gen_elp_seed_full.py — emit a FULL-lexicon vocabulary-{lang}.el in the
established ELP seed-fn format (same as vocabulary-non.el / the 18 classical
languages), iterating the ENTIRE morphology_{lang}_full lexicon (every verb,
noun, adjective lemma) — NOT a curated demo core.

Schema per row: [lemma, pos, form0, form1, form2, en_translation, semantic_hint]
  Verbs: form0=pres-ind-3sg  form1=preterite-3sg  form2=past-participle
  Nouns: form0=singular      form1=plural         form2=REAL gender (lexicon)
  Adjs : form0=masc-sg       form1=fem-sg         form2=masc-pl

Output structure (chunked to stay within the proven ~5k-append/function scale):
  fn vocab_{lang}_seed_pN(v) -> [[String]] { ... appends ... return v }
  fn vocab_{lang}_seed()     -> [[String]] { chains all chunks; return v }
  fn vocab_{lang}_lookup(w)  -> [String]   { linear scan }

Usage: python3 gen_elp_seed_full.py <lang> <out.el>
"""
import sys, importlib

CHUNK = 5000

def esc(s):
    return str(s).replace("\\", "\\\\").replace('"', '\\"')

def row(fields):
    return "    let v = native_list_append(v, [" + ", ".join(f'"{esc(f)}"' for f in fields) + "])"

def build_rows(lang, M):
    rows = []
    stats = {"verbs":0,"nouns":0,"adjs":0}
    has = lambda n: hasattr(M, n)

    # --- verbs ---
    if has("_VERBS") and has("conjugate"):
        verbs = sorted({k[0] for k in M._VERBS})
        for lem in verbs:
            if not lem: continue
            try:
                f0, s0 = M.conjugate(lem, "ind", "present", "third", "singular")
                f1, _  = M.conjugate(lem, "ind", "preterite", "third", "singular")
                pp, _  = (M.participle(lem) if has("participle") else ("",""))
            except Exception:
                continue
            vclass = lem[-2:] if lem[-2:] in ("ar","er","ir","re") else lem[-2:]
            rows.append([lem, "verb", f0 or "", f1 or "", pp or "", "", "class:"+vclass+" src:"+str(s0)])
            stats["verbs"] += 1

    # --- nouns ---
    if has("_NOUNS") and has("inflect_noun"):
        for lem in sorted(M._NOUNS):
            if not lem: continue
            try:
                sg, _ = M.inflect_noun(lem, "singular")
                pl, _ = M.inflect_noun(lem, "plural")
                g = M.noun_gender(lem) if has("noun_gender") else ""
            except Exception:
                continue
            src = "lexicon" if (isinstance(M._NOUNS.get(lem), dict) and M._NOUNS[lem].get("g")) else "heuristic"
            rows.append([lem, "noun", sg or lem, pl or "", g or "", "", "gender:"+src])
            stats["nouns"] += 1

    # --- adjectives ---
    if has("_ADJS") and has("inflect_adj"):
        for lem in sorted(M._ADJS):
            if not lem: continue
            try:
                m_sg, _ = M.inflect_adj(lem, "m", "singular")
                f_sg, _ = M.inflect_adj(lem, "f", "singular")
                m_pl, _ = M.inflect_adj(lem, "m", "plural")
            except Exception:
                continue
            rows.append([lem, "adj", m_sg or lem, f_sg or "", m_pl or "", "", "src:lexicon"])
            stats["adjs"] += 1

    return rows, stats

def write_seed(lang, rows, stats, out_path):
    """Write vocabulary-{lang}.el in the chunked seed-fn format from prebuilt rows.
    Each row is a 7-field list [lemma,pos,f0,f1,f2,gloss,hint]."""
    total = len(rows)
    chunks = [rows[i:i+CHUNK] for i in range(0, total, CHUNK)] or [[]]
    L = []
    L.append(f"// vocabulary-{lang}.el — FULL {lang} lexicon for ELP surface realization.")
    L.append(f"// Generated by gen_elp_seed_full.py from morphology_{lang}_full")
    L.append(f"// (real UniMorph + kaikki.org Wiktionary forms; gender from lexicon, not heuristic).")
    L.append(f"// Entries: {total}  (verbs={stats['verbs']} nouns={stats['nouns']} adjs={stats['adjs']})")
    L.append(f"// Schema: [lemma, pos, form0, form1, form2, en_translation, semantic_hint]")
    L.append(f"//   verbs: form0=pres-3sg form1=pret-3sg form2=past-participle")
    L.append(f"//   nouns: form0=sg form1=pl form2=REAL gender   adjs: form0=m-sg form1=f-sg form2=m-pl")
    L.append("")
    for ci, ch in enumerate(chunks):
        L.append(f"fn vocab_{lang}_seed_p{ci}(v: [[String]]) -> [[String]] {{")
        for r in ch:
            L.append(row(r))
        L.append("    return v")
        L.append("}")
        L.append("")
    L.append(f"fn vocab_{lang}_seed() -> [[String]] {{")
    L.append("    let v: [[String]] = native_list_empty()")
    for ci in range(len(chunks)):
        L.append(f"    let v = vocab_{lang}_seed_p{ci}(v)")
    L.append("    return v")
    L.append("}")
    L.append("")
    L.append(f"fn vocab_{lang}_lookup(word: String) -> [String] {{")
    L.append(f"    let vocab: [[String]] = vocab_{lang}_seed()")
    L.append("    let n: Int = native_list_len(vocab)")
    L.append("    let i: Int = 0")
    L.append("    while i < n {")
    L.append("        let entry: [String] = native_list_get(vocab, i)")
    L.append('        if str_eq(native_list_get(entry, 0), word) { return entry }')
    L.append("        let i = i + 1")
    L.append("    }")
    L.append("    return native_list_empty()")
    L.append("}")
    with open(out_path, "w", encoding="utf-8") as fh:
        fh.write("\n".join(L) + "\n")
    return total, stats

def emit(lang, out_path):
    M = importlib.import_module(f"morphology_{lang}_full")
    rows, stats = build_rows(lang, M)
    return write_seed(lang, rows, stats, out_path)

if __name__ == "__main__":
    lang, out = sys.argv[1], sys.argv[2]
    total, stats = emit(lang, out)
    print(f"{lang}: wrote {out}  total={total} verbs={stats['verbs']} nouns={stats['nouns']} adjs={stats['adjs']}")