Filter OpenCorpora abbreviations & proper nouns from the Russian noun list

OpenCorpora tags indeclinable abbreviations as common nouns (Abbr+Fixd), and
Stage 2 seeded the result with its whole noun lexicon, so non-words leaked into
scrabble.txt: ндс, ст, ср, кпд, чп, гибдд, днк, …

ru_stage2.py now drops Abbr+Fixd nouns from the OpenCorpora seed and lets the
orthographic dictionary decide instead: a lowercase РАН headword whose note is a
noun is kept (the lexicalised сельпо, под, ска, роно, врио, тв, фио, суперэвм),
everything else is dropped. Function words (CONJ/PRCL, e.g. зато) and OpenCorpora
inflected forms (ан = род. мн. от «ана»; proper «Ан») are excluded too.

--trace WORD now prints a detailed per-signal audit (all.txt, OpenCorpora POS /
Abbr / Fixd / CONJ/PRCL, libmorph, РАН note + classify, outcome) for auditing a
word or repeating the analysis; tools/README.md documents the rule and method.

Net: 179 words removed from scrabble.txt (83385 -> 83206) and erudit.txt
(83343 -> 83164); verified to remove exactly those 179 and add none. DAWGs
rebuild clean.

tools/ru_stage2.py

@@ -38,6 +38,8 @@ LIBMORPH_BIN = os.path.join(HERE, "libmorph_check")
 ALPHABET = "абвгдеёжзийклмнопрстуфхцчшщъыьэюя"
 ORDER = {c: i for i, c in enumerate(ALPHABET)}
 PROPER = {"Name", "Surn", "Patr", "Geox", "Orgn", "Trad"}
+ABBR_NOUN = {"Abbr", "Fixd"}      # indeclinable abbreviation marker (НДС, КПД, сельпо, …)
+FUNCTION_POS = {"CONJ", "PRCL"}   # conjunction / particle: a function word, never a Scrabble noun
 LIBMORPH_NOUN_CODES = set(range(7, 22)) | {24}  # 7..21 plus 24 (pluralia tantum)
 ADJ_END = {"ая", "яя", "ое", "ее", "ье", "ья", "ьи"}
 VERB3 = ("ет", "ёт", "ит", "ют", "ут", "ает", "яет", "ует", "уют", "нет", "жет", "чет")
@@ -72,7 +74,10 @@ D = M._dawg_dict
 
 
 def oc_noun_lemmas():
-    """Every common-noun lemma (nom. sing. / pluralia tantum) in OpenCorpora's words.dawg."""
+    """Every common-noun lemma (nom. sing. / pluralia tantum) in OpenCorpora's words.dawg,
+    excluding indeclinable abbreviations (Abbr+Fixd, e.g. НДС, КПД). Such words are admitted
+    only when the orthographic dictionary attests them as nouns (see oc_abbr_fixd_only and the
+    Stage-2 loop); abbreviations carried by OpenCorpora alone (ст, ср, кпд, …) are dropped."""
     gp, pt = D.get_paradigm, D.parse_tag_string
     para0, tagc = {}, {}
 
@@ -104,6 +109,8 @@ def oc_noun_lemmas():
         pre0, suf0, gr0 = g0(pid)
         if (PROPER & gr) or (PROPER & gr0):
             continue
+        if ABBR_NOUN <= gr0:        # indeclinable abbreviation: not seeded; the loop decides via the note
+            continue
         stem = word[len(pre):len(word) - len(suf)] if suf else word[len(pre):]
         out.add(pre0 + stem + suf0)
     return {w for w in out if cyr_ok(w)}
@@ -126,6 +133,43 @@ def oc_status(word):
     return False, True
 
 
+def oc_abbr_fixd_only(word):
+    """True when OpenCorpora's only common-noun reading of word is an indeclinable
+    abbreviation (Abbr+Fixd) — e.g. сельпо, ндс, ан. Such a word is not admitted as a noun on
+    OpenCorpora's say-so; the Stage-2 loop hands it to the orthographic note (and the function-
+    word check) instead, so lexicalised nouns (сельпо, под, ска) survive while bare letter-
+    abbreviations (ндс, кпд) and proper/служебные homographs (ан, зато) do not."""
+    parses = D.get_word_parses(word)
+    if not parses:
+        return False
+    gp, pt = D.get_paradigm, D.parse_tag_string
+    has_noun = has_plain = False
+    for pid, idx in parses:
+        suf, tag, pre = gp(pid, idx)
+        pos, gr = pt(tag)
+        if pos != "NOUN":
+            continue
+        _, tag0, _ = gp(pid, 0)
+        _, gr0 = pt(tag0)
+        if PROPER & gr or PROPER & gr0:
+            continue
+        has_noun = True
+        if not (ABBR_NOUN <= gr0):
+            has_plain = True
+    return has_noun and not has_plain
+
+
+def oc_function_word(word):
+    """True when OpenCorpora reads word as a conjunction or particle — a function word that
+    shares a spelling with an abbreviation/proper noun (ан «ан нет», зато). It is never a
+    Scrabble noun even if the orthographic note looks noun-like (ан → «самолёт Антонова»)."""
+    gp, pt = D.get_paradigm, D.parse_tag_string
+    for pid, idx in (D.get_word_parses(word) or []):
+        if pt(gp(pid, idx)[1])[0] in FUNCTION_POS:
+            return True
+    return False
+
+
 def libmorph_analyze(words):
     """Map each word to (known, noun_lemma, codes) per libmorph; noun_lemma is None when it
     is not a common noun there. Empty result if the helper binary is not built."""
@@ -240,9 +284,27 @@ def build():
     scrabble = set(oc)
     adj, verb, amb = [], [], []
     for w in pdf:
+        if oc_abbr_fixd_only(w):
+            # Indeclinable abbreviation in OpenCorpora: do not trust OC's noun verdict. Drop it
+            # if OC also reads it as a function word (ан, зато — служебное/пропер); otherwise let
+            # the orthographic note decide, keeping lexicalised nouns (сельпо, под, ска) and
+            # dropping the rest (кпд, чп, гор, …).
+            if oc_function_word(w):
+                fate[w] = "отброшено: служебное слово (CONJ/PRCL в OpenCorpora)"
+            elif classify(w, hmap.get(w)) == "noun":
+                s = to_singular(w)
+                scrabble.add(s)
+                fate[w] = "scrabble: несклон. аббрев.-сущ. по помете орфословаря" + ("" if s == w else f" → {s}")
+            else:
+                fate[w] = "отброшено: аббревиатура без подтверждающей пометы орфословаря"
+            continue
         oc_noun, oc_known = oc_status(w)
         if oc_noun:
-            fate[w] = "scrabble: сущ. по OpenCorpora"
+            # A common-noun reading already put w in the seed (scrabble = set(oc)) — unless its
+            # lemma is a different word, i.e. w is an inflected form (ан = род. мн. от «ана»);
+            # such a form is not a headword and stays out.
+            fate[w] = ("scrabble: сущ. по OpenCorpora" if w in scrabble
+                       else "отброшено: словоформа OpenCorpora (лемма — другое слово)")
             continue
         lm_known, lm_lemma, _ = lm.get(w, (False, None, frozenset()))
         if lm_lemma is not None:
@@ -295,21 +357,51 @@ def build():
     return {
         "oc": oc, "scrabble": scrabble, "undefined": undefined,
         "adjectives": adj, "verbs": verb, "singulars": ed_nouns,
-        "fate": fate, "all": set(all_words),
+        "fate": fate, "all": set(all_words), "hmap": hmap,
     }
 
 
 def trace(word, r):
+    """A detailed, per-signal audit of how WORD did or did not reach the dictionary: its
+    Stage-1 (all.txt) membership, every OpenCorpora reading, libmorph, the orthographic note
+    with its classify verdict, and the final outcome. Used by `--trace WORD`."""
     w = destress(word)
-    if w in r["fate"]:
-        return r["fate"][w]
-    if w in r["scrabble"]:
-        return "scrabble: лексикон OpenCorpora" if w in r["oc"] else "scrabble: производная/лемма"
-    if w not in r["all"]:
-        return "нет в russian_all (не извлечено на Stage 1 — нет в .pdf, либо имя собств./дефис/форма)"
-    if not cyr_ok(w):
-        return "отсеяно: длина или символы вне диапазона (2–15 кириллица)"
-    return "не определено"
+    note = r["hmap"].get(w)
+    parses = D.get_word_parses(w) or []
+    gp, pt = D.get_paradigm, D.parse_tag_string
+    pos = sorted({pt(gp(pid, idx)[1])[0] for pid, idx in parses})
+    oc_noun, _ = oc_status(w)
+
+    out = [f"{word}  →  {'В СЛОВАРЕ' if w in r['scrabble'] else 'НЕ в словаре'}"]
+    out.append(f"  Stage-1 / all.txt (строчный заголовок РАН): {'да' if w in r['all'] else 'нет'}")
+    if parses:
+        kind = ("только несклон. аббрев. (Abbr+Fixd)" if oc_abbr_fixd_only(w) else
+                "обычное сущ." if oc_noun else
+                "не существительное")
+        out.append(f"  OpenCorpora: части речи {pos}; как сущ. — {kind}; "
+                   f"служебное (CONJ/PRCL): {'да' if oc_function_word(w) else 'нет'}")
+    else:
+        out.append("  OpenCorpora: нет в словаре")
+    lm = libmorph_analyze([w]).get(w)
+    if lm:
+        known, lemma, _ = lm
+        out.append("  libmorph: " + (f"сущ. → {lemma}" if lemma else ("известно, не сущ." if known else "нет")))
+    else:
+        out.append("  libmorph: helper отсутствует — в анализе не участвует")
+    out.append("  Орфословарь РАН: " + (f"помета «{note}» → classify={classify(w, note)}"
+                                        if note is not None else "нет заголовка"))
+    reason = r["fate"].get(w)
+    if reason is None:
+        if w in r["scrabble"]:
+            reason = "лексикон OpenCorpora (обычное сущ.)"
+        elif oc_abbr_fixd_only(w) and w not in r["all"]:
+            reason = "исключено из посева: несклон. аббрев. (Abbr+Fixd), нет в all.txt"
+        elif not parses and w not in r["all"]:
+            reason = "нет ни в OpenCorpora, ни в all.txt"
+        else:
+            reason = "не прошло ни один путь отбора"
+    out.append(f"  ИТОГ: {reason}")
+    return "\n".join(out)
 
 
 def main():
@@ -320,7 +412,7 @@ def main():
 
     r = build()
     if args.trace:
-        print(f"{args.trace}: {trace(args.trace, r)}")
+        print(trace(args.trace, r))
         return
 
     write(os.path.join(OUT_DIR, "scrabble.txt"), r["scrabble"])