stage(elp): consolidate scattered lang work — full-lexicon vocabulary + profiles

Backfill ELP vocabulary from FULL lexicons (UniMorph + kaikki.org Wiktionary, real gender/inflections) for 8 languages, 812,894 entries total, in the proven seed-fn format matching the 18 ancient vocabularies: es 72,032 | fr 130,517 | de 144,692 | la 22,590 | it 193,675 | pt 115,772 | ro 86,504 | ca 47,112 4 of these (es fr de la) backfill ELP languages that had morphology but no vocabulary; it/pt/ro/ca are new Romance (need morphology-*.el ports next). Adds lang_profile_* for all 8 + reproducible generators under tests/lang-gen. Vocab is runtime seed data (not in build manifest, like the 18 ancients); seed-fn format validated to compile to C via elc.
2026-08-13 11:56:03 -05:00
parent ba6e36c3f7
commit a816b119e7
28 changed files with 819286 additions and 0 deletions
@@ -0,0 +1,45 @@
+;;; lang_profile_es.el — Spanish language profile for ELP.
+;;; Keys the realizer's construction switches. Mirrors lang_profile_en / _pt.
+
+(lang_profile_es
+  (language        "Spanish")
+  (iso639          "es")
+  (family          "Romance")
+
+  ;; -- core typology flags -------------------------------------------------
+  (pro-drop            yes)    ; subjects routinely dropped; agreement carries person
+  (obligatory-subject  no)
+  (grammatical-gender  yes)    ; m/f on every noun; article+adjective AGREE
+  (gender-source       lexicon); REAL per-noun gender from UniMorph — NOT a heuristic
+  (do-support          no)
+  (subject-aux-inversion no)   ; questions by intonation/punctuation, not inversion
+  (question-strategy   intonation)
+  (article-selection   "el/la/los/las un/una/unos/unas")
+  (stressed-a-rule     yes)    ; fem sg noun in stressed a-/ha- takes el/un (el agua)
+  (adjective-position  postnominal) ; default post; a few prenominal + apocope
+  (adjective-agreement "gender+number")
+  (question-punct      inverted)    ; opening ¿ ¡ required
+
+  ;; -- MANDATORY CONTRACTIONS (coordinator quality bar) --------------------
+  (contractions        ((de el "del") (a el "al")))
+  (contraction-mandatory yes)  ; 'de el'/'a el' MUST surface as del/al
+
+  ;; -- verb / aspect system ------------------------------------------------
+  (verb-classes        (ar er ir))
+  (tenses              (present preterite imperfect future conditional))
+  (moods               (ind sbjv imp))
+  (finite-agreement    "person+number (6 slots)")
+  (perfect-aux         "haber")  ; haber + past participle (invariant -o)
+  (progressive-aux     "estar")  ; estar + gerund
+  (passive-aux         "ser")    ; ser + participle (agrees) + por-agent
+  (copula-split        "ser/estar")  ; permanent vs stage-level
+  (future              "infinitive + é/ás/á/emos/éis/án")
+
+  ;; -- clitics / government ------------------------------------------------
+  (object-clitics      yes)      ; me te lo la le nos os los las; proclisis/enclisis
+  (clitic-order        "se II I III (le+lo -> se lo)")
+  (enclisis            "imperative/infinitive/gerund + accent repair (dá+me+lo->dámelo)")
+  (verb-prep-government yes)     ; verbs select prep (protestar+contra, escapar+de)
+
+  ;; -- SACRED safety bar (shared with en/pt) -------------------------------
+  (negation-faithful   yes))     ; polarity never dropped/inverted; unplaceable -> FLAG