will.anderson
a816b119e7
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.
73 lines
4.8 KiB
EmacsLisp
73 lines
4.8 KiB
EmacsLisp
;;; lang_profile_ca.el — Catalan language profile for ELP.
|
|
;;; Mirrors lang_profile_it / _es / _pt; keys the realizer's construction switches.
|
|
;;; Catalan is the CLOSEST Romance sibling to the shared engine (~85% conceptual
|
|
;;; reuse). The deltas: PRONOMS FEBLES with four position allomorphs, l'-elision,
|
|
;;; del/al/pel contractions, the periphrastic preterite (vaig+INF), and NO
|
|
;;; essere/avere split (perfect aux is always HAVER; ser/estar is only the copula).
|
|
|
|
(lang_profile_ca
|
|
(language "Catalan")
|
|
(iso639 "ca")
|
|
(family "Romance")
|
|
|
|
;; ── core typology flags ────────────────────────────────────────────────
|
|
(pro-drop yes) ; null subjects default; overt pronoun = emphatic
|
|
(obligatory-subject no)
|
|
(grammatical-gender yes) ; m/f; full NP agreement (art + adj + participle)
|
|
(do-support no)
|
|
(subject-aux-inversion no) ; yes/no Q = declarative order + '?'; no inversion
|
|
(article-selection "el/la/l'/els/les ; un/una/uns/unes") ; l'-ELISION:
|
|
; el/la -> l' before vowel or (silent) h, glued to
|
|
; the next word (l'home, l'illa); de -> d' before vowel
|
|
(article-drives-contraction yes) ; article choice feeds prep+article contraction
|
|
(adjective-position "postnominal-default + small prenominal class") ; bo/bon,
|
|
; mal, gran, nou, vell, primer, molt... prenominal
|
|
(question-punct plain) ; ? and ! only (no inverted ¿ ¡)
|
|
|
|
;; ── MANDATORY prep+article contractions ────────────────────────────────
|
|
(contractions ((de el del) (de els dels)
|
|
(a el al) (a els als)
|
|
(per el pel) (per els pels)))
|
|
(contraction-mandatory yes) ; *de el -> del obligatory
|
|
(contraction-blocked-before-elision yes) ; de l'home / a l'home (NO *del home)
|
|
|
|
;; ── clitic system: PRONOMS FEBLES (the headline delta) ──────────────────
|
|
(clitics yes)
|
|
(clitic-allomorphy four-position) ; per pronoun, form varies by position+onset:
|
|
; reinforced (em, et, el) proclitic before a consonant
|
|
; elided (m', t', l', n') proclitic before a vowel/h
|
|
; full (-me, -lo, -li) enclitic after a consonant/-r
|
|
; reduced ('m, 't, 'l, 'ns) enclitic after a vowel
|
|
(clitic-placement ((finite proclitic) ; el veig, no m'ho dóna
|
|
(imperative-affirmative enclitic) ; dóna'm, digues-me
|
|
(imperative-negative present-subjunctive) ; no parlis (delta)
|
|
(infinitive enclitic) ; ajudar-me, veure'l
|
|
(gerund enclitic))) ; fent-ho
|
|
(clitic-combination ((me el "me'l") (te el "te'l") (se el "se'l")
|
|
(me la "me la") (me en "me'n")
|
|
(li el "l'hi") (li en "n'hi"))) ; dative+accusative clusters
|
|
(clitic-particles (hi en ho)) ; locative hi, partitive/genitive en, neuter ho
|
|
|
|
;; ── verb / aspect system ───────────────────────────────────────────────
|
|
(finite-agreement "person+number (6-way)")
|
|
(tenses (present imperfet preterit-simple perifrastic-preterit futur
|
|
condicional subjuntiu-present subjuntiu-imperfet imperatiu))
|
|
(periphrastic-preterite "vaig/vas/va/vam/vau/van + INFINITIVE") ; << hallmark CA
|
|
; (vaig cantar = 'I sang'); coexists w/ synthetic pret.
|
|
(compound-past "pretèrit perfet = haver(present) + participle")
|
|
(perfect-aux "HAVER only") ; << NO essere/avere split (simpler than IT)
|
|
(participle-agreement ((haver preceding-acc-clitic))) ; les he vistes; else invariable
|
|
(progressive-aux "estar + gerundi")
|
|
(copula "ser / estar") ; ser: identity/essential/origin; estar:
|
|
; location + transient state (estic cansat, és a casa)
|
|
(passive-aux "ser (+ per-agent)")
|
|
(future inflectional) ; cantaré, serà
|
|
(comparative "més/menys ADJ que")
|
|
|
|
;; ── SACRED safety bar (shared with es/pt/it/en) ────────────────────────
|
|
(negation-faithful yes) ; polarity never dropped/inverted; unplaceable -> FLAG
|
|
(negation "no (preverbal) + optional 'pas' + concord") ; no...res/
|
|
; ningú/mai/cap/gens/enlloc
|
|
(negative-concord yes) ; preverbal negative subject (ningú) keeps 'no'
|
|
(neg-reinforcer pas)) ; optional (no ho faré pas)
|