Skip to content

Instantly share code, notes, and snippets.

@tommycarstensen

tommycarstensen/verbos.py

Last active April 3, 2025 14:50
Show Gist options
  • Save tommycarstensen/d6ca630431d1472bb2588fe159fa0777 to your computer and use it in GitHub Desktop.
Save tommycarstensen/d6ca630431d1472bb2588fe159fa0777 to your computer and use it in GitHub Desktop.
Download ZIP
Conjugación de verbos en español
Raw
verbos.py
#!/usr/bin/env python
# Copyright (C) 2019, Tommy Carstensen
# https://brittanygervin.com/projects/stem-changing-spanish-verbs-flowchart/
# https://2.bp.blogspot.com/-Y8Y7cyZEpzs/WuLmoDZhvYI/AAAAAAAAPDs/GAAtM_6zA5EwG9aPkh0e06uUQ3vDXVSXQCLcBGAs/s1600/gram%25C3%25A1tica-mind-map.png
# https://www.spanishdict.com/guide/spanish-present-tense-forms
# https://www.spanishdict.com/guide/spanish-irregular-present-tense/
# https://www.spanishdict.com/guide/stem-changing-verbs/
# https://www.spanishdict.com/guide/spelling-changes-in-the-present-tense
import json
from collections import Counter
import re
import random
# Irregular “yo” form with no stem change
# conocer – “to know” – yo conozco, tú conoces
# dar – “to give” – yo doy, tú das
# hacer – “to do, make” – yo hago, tú haces
# poner – “to put” – yo pongo, tú pones
# salir – “to exit” – yo salgo, tú sales
# traer – “to bring” – yo traigo, tú traes
# ver – “to see” – yo veo, tú ves
# oír – “to hear” – yo oigo, tú oyes
# saber – “to know” – yo sé, tú sabes
# ir – “to go” – yo voy, tú vas
# estar – “to be” – yo estoy, tú estás
# caber – “to fit” – yo quepo, tú cabes
# lucir – “to wear” – yo luzco, tú luces
# valer – “to be worth” – yo valgo, tú vales
# Irregular “yo” form with a stem change
# decir – “to say” – yo digo, tú dices
# tener – “to have” – yo tengo, tú tienes
# venir – “to come” – yo vengo, tú vienes
##import pyphen
##dic = pyphen.Pyphen(lang='es')
# wrong for sobreestimar
##print(dic.inserted('sobreestimar'))
# pres1s
# raer rao,raigo,rayo
# mecer mezo - estremecer estremezco
# pres2s
# ofender ofendes - defender defiendes
# adecentar ad/e/cen/tar adecentas - acrecentar ac/cre/cen/tar acrecientas
# anhelar an/he/lar anhelas - helar he/lar hielas
# alcanforar al/can/fo/rar alcanforas - aforar a/fo/rar afueras/aforas - agorar a/go/rar agoras
# aposentar a/po/sen/tar aposentas - asentar a/sen/tar asientas
# asonar a/so/nar asuenas - apisonar a/pi/so/nar apisonas
# atentar a/ten/tar atentas -
# acollar a/co/llar acolas - apercollar apercollas - descollar des/co/llar descuelas
# descolar descolas - encolar encolas - escolar escuelas - trascolar trascuelas
# atronar atruenas - destronar destronas
# empavesar empaviesas - atravesar atraviesas
# aporcar aporcas - emporcar empuercas
# decorar decoras - encorar encueras
# alforzar alforzas - esforzar esfuerzas
# impostar impostas - apostar apuestas
# censar censas - incensar inciensas
# inmolar inmolas - amolar amuelas
# insolar insolas - consolar consuelas
# interpretar interpretas - apretar aprietas
# inventar inventas - aventar avientas
# aprehender aprehendes - hender hiendes
# bregar bregas - regar riegas
# rogar ruegas - derogar derogas
# adecentar adecentas - acrecentar acrecientas
# descompensar descompensas - pensar piensas
# pres2s tilde
# vaciar vacías - viciar vicias
# ahumar ahúmas - inhumar inhumas
# airar aíras - desairar desairas
# cohibir cohíbes - inhibir inhibes
# participio
# entre/a/brir entreabierto, des/a/brir desabrido
# pret3s
# contrahacer contrahízo deshacer deshizo
# hacer, deshacer, satisfacer, rehacer, etc
# poner, componer, descomponer, reponer, etc
# decir, maldecir, bendecir, etc
# verbos terciopersonales:
# llover, tronar, granizar, relampaguear, diluviar, nevar
# Aspecto: Perfecto/Perfectivo (Preterite), Imperfecto/Imperfectivo (Imperfecto)
# Modo: Indicativo o Subjuntivo o Imperativo
# Tiempo: presente, pasado y futuro
# Persona: 1a, singular (se llama numero?)
# https://en.wiktionary.org/wiki/Category:Spanish_prefixes
prefijos = [
'mal', 'ben', 'des', 'pre',
#'con', # not conocer
'ex', 'inter', 're',
# 'sobre', # not so/bren/ten/der? pero sobre-estimar
'sub', 'contra', 'uni', 'equi',
'ante', 'entre', 'hiper', 'hipo',
# 'pos', # not poseer
'super',
'in',
'trans',
'ad', # Contiene prefijo ad- que proviene del latín y significa "proximidad", "hacia" o "añadido". Ejemplos: adyacente, adjunto.
'en',
]
tilde = {'a': 'á', 'e': 'é', 'i': 'í', 'o': 'ó', 'u': 'ú',}
endings_uir4 = (
'buir', 'cuir', 'tuir', 'huir', 'güir', 'luir',
'nuir', # disminuir
)
endings_uir5 = endings_pres2s_ui_to_uy = endings_pret3s_ui_to_yo = [
'fluir', 'truir', 'cluir', 'rruir',
# 'creer',
]
endings_CeCXir = [
'servir',
'rendir',
'seguir',
'vestir',
]
endings_CeCir = (
'cebir',
'decir',
'pedir', 'medir',
'regir', 'legir',
'gemir',
'ferir', 'gerir', 'herir', 'jerir',
'petir',
)
def main():
with open('esp_verbos.json') as f:
l = json.loads(f.read())
# import sys
# if len(sys.argv) > 1:
# l = [{
# 'verbo': sys.argv[-1],
# 'indicativo': {'presente': {'tú': 'xxx'}},
# 'perfecto': {'presente': {'yo': 'xxx'}},
# }]
# print(l)
endings = []
##for d in random.sample(l, len(l)):
w2 = []
w3 = []
w4 = []
w5 = []
w6 = []
# Crear ordenable lista de verbos. Create sortable list of verbs.
verbos = []
reflexivos = set()
for d in l:
verbo = d['verbo']
if d['indicativo']['presente']['yo'].startswith('me '):
reflexivos.add(verbo)
if verbo in (
# pres2s missing - just a dash
'tutear',
):
continue
sílabas = find_syllables(verbo)
try:
sil2 = sílabas[-2]
except IndexError:
sil2 = ''
conj = {
'imp2p': d['imperativo']['afirmativo']['vosotros'].split()[-1],
'gerundio': d['progresivo']['presente']['yo'].split()[-1],
'participio': d['perfecto']['presente']['yo'].split()[-1].split(','),
'pres1s': d['indicativo']['presente']['yo'].split()[-1].split(','),
'pres2s': d['indicativo']['presente']['tú'].split()[-1].split(','),
'pres3s': d['indicativo']['presente']['él/ella/Ud.'].split()[-1].split(','),
'pres1p': d['indicativo']['presente']['nosotros'].split()[-1].split(','),
'pres2p': d['indicativo']['presente']['vosotros'].split()[-1].split(','),
'pres3p': d['indicativo']['presente']['ellos/ellas/Uds.'].split()[-1].split(','),
'pret3s': d['indicativo']['preterito']['él/ella/Ud.'].split()[-1].split(','),
'imp2s': d['imperativo']['afirmativo']['tú'].split()[-1].split(','),
'subj1s': d['subjuntivo']['presente']['yo'].split()[-1].split(','),
'subj3s': d['subjuntivo']['presente']['yo'].split()[-1].split(','),
}
verbos.append((
verbo[::-1],
verbo[-2:], # ar or er/ir
verbo[-3:], # iar, uar or ???
# len(sílabas[[-2]),
sílabas[-1][:-2],
verbo,
conj
))
for k, v in conj.items():
if ',' in v:
print(k, v)
stop
v = list(sorted(verbos))
verbos = v
# for i_verbo, d in enumerate(reversed(l)):
for i_verbo, t in enumerate(sorted(verbos)):
print()
# palabra = verbo = word = verb = d['verbo']
verbo = t[4]
d = t[5]
# participio = d['perfecto']['presente']['yo'].split()[-1]
participio = d['participio']
# pres2s = d['indicativo']['presente']['tú'].split()[-1]
pres1s = d['pres1s']
pres2s = d['pres2s']
pret3s = d['pret3s']
## print(d['indicativo']['presente'])
# pres2s = pres2s.replace('í', 'i') # tmp!!!
# pres2s = pres2s.replace('ú', 'u') # tmp!!!
# participio = participio.replace('ído', 'ido') # tmp!!!
if ',' in pres2s: continue
if ',' in pret3s: continue
if ',' in participio: continue
if verbo in (
'fungus', 'lee', 'poteen', 'UNIDO', 'VI', 'quejarse',
'collar', 'familiar', 'caviar', 'alongar', # no es un verbo...
'tutear', 'solar', # pres2s missing - just a dash
'asolar', # Asolar suele conjugarse usando el modelo de contar, con el cambio de la o por ue en algunas tiempos, pero también se acepta el uso de la conjugación regular, sin dicho cambio.
'repudrir', # incorrectly pres2s repodres in json and not repudres
'colar', # colas/cuelas https://dle.rae.es/?id=9jtl8nd https://dle.rae.es/?id=9jtl8nd
# memorize
# 'haber', 'hacer', 'ser', 'estar', 'poder', 'poner', 'ir', 'decir', 'querer', 'volver',
'holgar', 'hollar', # incorrectly conjugated in the json file
# 'placer', # pret3s plació,plugo
# 'responder', # pret3s respondió,repuso
# 'sobrentender', # sobre-entender
'minar', # participio minarán in JSON file
# 'dar', # super irregular
'manir', # manir participio manirán not manido
'preterir', # pres2s not preteres
'raer', # pres1s raigo,rayo
# 'yacer', # pres1s yazco,yago,yazgo
'roer', 'corroer', # pres1s roo o roigo o royo
):
continue
## syllables = dic.inserted(verbo)
## print(syllables)
sílabas = find_syllables(verbo)
# syllabyle_last = syllables.split('/')[-1]
sílaba_ultima = sílabas[-1]
for i in range(len(verbo)-1):
w2.append(verbo[i:i+2])
for i in range(len(verbo)-2):
w3.append(verbo[i:i+3])
for i in range(len(verbo)-3):
w4.append(verbo[i:i+4])
for i in range(len(verbo)-4):
w5.append(verbo[i:i+5])
for i in range(len(verbo)-5):
w6.append(verbo[i:i+6])
print(
i_verbo, len(verbos),
'\n'+verbo, sílabas,
'\npres',
d['pres1s'], d['pres2s'], d['pres3s'],
d['pres1p'], d['pres2p'], d['pres3p'],
'\npret', pret3s,
'\npart', participio,
)
# Para determinar primera letra.
sílabas_sin_prefijos = sílabas
while sílabas_sin_prefijos[0] in prefijos:
sílabas_sin_prefijos = sílabas_sin_prefijos[1:]
if verbo[-2:] == 'ar':
ar(verbo, d, sílabas, sílabas_sin_prefijos)
#
# er/ir
#
else:
erir(verbo, d, sílabas, sílabas_sin_prefijos)
with open('pass.txt', 'a') as f:
print(verbo, file=f)
## print(d['indicativo']['presente'])
## print(d['indicativo']['preterito'])
## print(d['indicativo']['imperfecto'])
## print(d['indicativo']['futuro'])
## print(d['indicativo']['condicional'])
## print(d['imperativo'])
## print(d['progresivo'])
## print(d['subjuntivo'])
## print(d['perfecto_subjuntivo'])
## print(verb)
## print(m)
## print(m.group(0))
# m = re.search("[aeiou][^aeiou]*[ar|er|ir]$", verb)
# ending = m.group(0)
# try:
# ending = dic.inserted(word).split('-')[-2][-1] + dic.inserted(word).split('-')[-1]
# except IndexError:
# ending = dic.inserted(word).split('-')[-1]
## print(ending, verb)
## stop
## ass.append(verbo[-3:])
endings.append(sílaba_ultima)
## print(verbo[-3:], verbo)
print(Counter(w2).most_common(100))
print(Counter(w3).most_common(100))
print(Counter(w4).most_common(100))
print(Counter(w5).most_common(100))
print(Counter(w6).most_common(100))
for t in Counter(endings).most_common():
print(t[1], t[0], sep=' ')
return
def ar(verbo, d, sílabas, sílabas_sin_prefijos):
# participio ar
assert verbo[:-2] + 'ado' in d['participio']
pres_ar(d, verbo, sílabas, sílabas_sin_prefijos)
pret_ar(d, verbo, sílabas)
return
def erir(verbo, d, sílabas, sílabas_sin_prefijos):
participio_erir(d, verbo, sílabas)
pres_erir(d, verbo, sílabas, sílabas_sin_prefijos)
pret_erir(d, verbo, sílabas)
return
def participio_erir(d, verbo, sílabas):
# participio er/ir
Irreg = [
# eir/ito
['freir', 'frito',],
]
if verbo == 'escribir':
print(verbo, d['participio'], participio)
stoptmp
if False:
pass
elif verbo.endswith('ver') and verbo[:-3] in [''] + prefijos: # ver
participio = verbo[:-2] + 'isto'
# elif verbo == 'leer':
# assert participio == verbo[:-2] + 'ído', participio
elif verbo != 'desabrir' and verbo.endswith('brir'): # abrir, cubrir, escribir
# entre/a/brir, des/a/brir
participio = verbo[:-4] + 'bierto'
elif verbo[-5:] in ('morir',): # morir
participio = verbo[:-4] + 'uerto'
elif verbo.endswith('poner'): # poner, yuxtaponer
participio = verbo[:-4] + 'uesto'
## elif verbo[-3:] == 'ver': # volver
## assert participio == verbo[0] +'uelto', participio
elif verbo[-6:] in ('solver', 'volver'): # disolver, volver, resolver
participio = verbo[:-5] + 'uelto'
elif verbo.endswith('decir'): # decir
participio = verbo[:-4] + 'icho'
elif verbo[-5:] in ('facer', 'hacer'): # hacer, satisfacer
participio = verbo[:-4] + 'echo'
elif verbo.endswith('freir'): # freor
participio = verbo[:-3] + 'ito'
elif verbo != 'corromper' and verbo.endswith('romper'): # romper
participio = verbo[:-5] + 'oto'
elif verbo.endswith('pudrir'): # pudrir
participio = verbo[:-5] + 'odrido'
else:
if sílabas[-1] in ('er', 'ír') and verbo[-3] in 'aeo':
participio = verbo[:-2] + 'ído'
assert verbo in (
'caer', 'decaer', 'recaer',
'raer', 'traer', 'atraer', 'detraer',
'retraer', 'maltraer', 'contraer', 'retrotraer',
'distraer', 'sustraer',
'leer', 'releer', 'creer',
'sobreseer', 'poseer', 'desposeer', 'proveer', 'desproveer',
'roer', 'corroer',
'reír', 'sonreír',
) or verbo.endswith('traer') or verbo.endswith('creer'), verbo
# assert len(sílabas_sin_prefijos) <= 2
else:
participio = verbo[:-2] + 'ido'
assert not verbo.endswith('aer')
assert not verbo.endswith('eer')
assert not verbo.endswith('oer')
assert participio in d['participio'], ('participio', d['participio'])
assert participio in d['participio'], ('participio', participio, d['participio'])
return
def pres_ar(d, verbo, sílabas, sílabas_sin_prefijos):
ie = 'ie'
ue = 'ue'
if False:
pass
# tmp removal...
# elif verbo[:3] == 'vol' and verbo[-3:] not in ('ear', 'zar'): # volcar, volar
# pres2s = verbo[:1] +'uel'+ verbo[3:-2] +'as'
# ## elif verbo[-4:] == 'ezar': (not acezar)
# ## assert d['pres2s'] == verbo[:-4] +'iezas', pres2s
# assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
# dar > doy
elif verbo == 'dar':
pres1s = 'doy'
pres2s = 'das'
assert pres1s in d['pres1s'], (d['pres1s'], pres1s)
# estar > estoy; a > á (ar)
elif sílabas[-2:] == ['es', 'tar']:
pres1s = verbo[:-2] + 'oy'
pres2s = verbo[:-2] + 'ás'
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
# ar, pres2s, o > ue
# elif verbo[-4:] == 'ovar' and sílabas[-2:] != ['o', 'var']: # renovar
# assert d['pres2s'] == verbo[:-4] +'ue'+ verbo[-3] +'as', pres2s
# print('o>ue 9', verbo)
elif verbo in ('rogar', 'renovar',) or ''.join(sílabas[-2:]) in (
'gorar',
'rodar',
'novar', # renovar, not innovar
'forar',
# 'rogar',
) and verbo not in (
'derogar', 'innovar',
'alcanforar', 'perforar',
): # destrocar (not debocar), a/fo/rar, not alcanforar
if verbo.endswith('gorar'):
ue = 'üe'
raiz = verbo[:-4] + ue + verbo[-3]
pres1s = raiz + 'o'
pres2s = raiz + 'as'
print('o>ue 2', verbo)
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
# elif sílabas[-2:] in (['xxlo', 'car'],) and verbo not in ('alocar', 'colocar', 'descolocar'):
# conj = verbo[:-4] + 'ue' + verbo[-3] + 'as'
# assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
elif verbo in (
'escolar', 'trascolar',
'amolar',
) or verbo == 'encorar' or verbo[-5:] in (
'sonar', # asonar (not apisonar)
'volar',
# 'colar', # escolar, trascolar, not descolar
# 'molar', # amolar, not molar
'solar',
# 'corar',
) and verbo not in (
'apisonar', 'artesonar', 'blasonar',
'inmolar',
'insolar', 'acrisolar', 'tornasolar',
'descolar', 'encolar', 'estercolar', 'socolar',
): # tronar (not embolar), trasvolar, trascolar not socolar
raiz = verbo[:-4] + 'ue' + verbo[-3]
pres1s = raiz + 'o'
pres2s = raiz + 'as'
print('o>ue 3', verbo)
afijo = 'o_to_ue'
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
# ar, pres2s, o > ue (CCoCar and CoCCar)
elif verbo == 'esforzar' or verbo == 'descollar' or verbo[-6:] in (
'porcar',
'volcar',
'cordar',
'goldar',
'soldar',
# 'longar', # not prolongar
'colgar',
# 'drogar',
'poblar',
# 'collar', # descollar, not escollar
'sollar',
'cornar',
'contar',
'costar',
'nostar',
'postar',
'tostar',
'soltar',
# 'forzar', # not alforzar
'forzar',
'gonzar',
'morzar',
'probar',
'clocar',
'trocar',
'tronar',
) and verbo not in (
'acollar', 'apercollar', 'destronar', 'aporcar' ,'encornar', 'alforzar', 'impostar',): # contar, encordar (not asordar)
if verbo[-6:-4] == 'go':
ue = 'üe'
if verbo[-5] == 'o':
pres2s = verbo[:-5] + ue + verbo[-4:-2] + 'as'
pres1s = verbo[:-5] + ue + verbo[-4:-2] + 'o'
else:
pres2s = verbo[:-4] + ue + verbo[-3:-2] + 'as'
pres1s = verbo[:-4] + ue + verbo[-3:-2] + 'o'
ue = 'ue'
print('o>ue 8', verbo)
assert pres1s in d['pres1s'], (d['pres1s'], pres1s)
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
elif verbo[-7:] in (
'mostrar', 'contrar',): # demostrar, encontrar
raiz = verbo[:-6] +'ue'+ verbo[-5:-2]
pres1s = raiz + 'o'
pres2s = raiz + 'as'
print('o>ue 5', verbo)
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
elif verbo[-8:] in ('desollar', 'degollar'): # demostrar
if verbo[-6] == 'g':
ue = 'üe'
raiz = verbo[:-5] + ue + verbo[-4:-2]
pres1s = raiz + 'o'
pres2s = raiz + 'as'
ue = 'ue'
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
# elif verbo[-7:] == 'degollar': # degollar (not acogollar)
# assert d['pres2s'] == verbo[:-5] +'üe'+ verbo[-4:-2] +'as', pres2s
# print('o>ue 6', verbo)
# pres, u > ue (jugar)
elif verbo == 'jugar':
pres1s = 'juego'
pres2s = 'juegas'
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
# ar, pres2s, e > ie
elif verbo == 'regar' or verbo[-5:] in (
'helar',
'fesar', # confesar, not profesar
'vesar',
'pezar',
'negar', # denegar, but anegas en DLE, aniegas en WR
'segar',
'cegar',
'nevar',
# 'regar',
) and verbo not in (
'anhelar', 'empavesar', 'bregar', 'anegar', 'profesar',
):
raiz = verbo[:-4] + ie + verbo[-3]
pres1s = raiz + 'o'
pres2s = raiz + 'as'
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
# elif verbo[-5:] in ('eblar',): # temblar tmp!!!
# conj = verbo[:-5] + ie + verbo[-4:-2] + 'as'
# assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
# ar, pres2s, e > ie (CeCCar/CeCCar)
elif verbo in (
'escarmentar',
'apretar',
'desapretar',
'aventar', 'reventar',
'acrecentar', 'apacentar',
'desalentar',
'mentar', 'salpimentar', 'cimentar',
'pensar', 'repensar',
'sentar', 'asentar',
'tentar',
'dentar', 'endentar',
'incensar',
) or ''.join(sílabas[-2:]) in (
# 'yerbar',
'herbar',
'beldar',
'mendar',
'rendar',
'plegar',
'fregar',
'tregar', # restregar
'holgar',
'hollar',
'neblar',
'hollar',
'bernar',
# 'censar', not censar
'pensar', # not compensar
'cerrar',
'herrar',
'pedrar',
'serrar',
'terrar',
'centar', # acrecentar, not adecentar
'certar', # 'acertar', 'concertar', 'desacertar',
'dentar',
'festar', # manifestar, not infestar
# 'mentar', # escarmentar (not alimentar/alimentum/alimento, not argumentar)
'hestar',
'pertar', # despertar
# 'lentar',
# 'pretar',
# 'sentar',
# 'tentar',
'testar', # atestas/atiestas, not contestar, atestar, not testar
# 'ventar',
'menzar',
#) and (
# len(sílabas_sin_prefijos) == 2 or verbo[-7] in 'aeiou'
) and verbo not in (
'aposentar',
'atentar', 'contentar',
'alimentar', 'bastimentar',
'fundamentar', 'ornamentar', 'sacramentar', 'juramentar',
'lamentar', 'reglamentar', 'parlamentar',
'argumentar', 'aumentar',
'atormentar',
# 'censar',
'testar', 'detestar', 'contestar', 'protestar', 'infestar', 'desinfestar',
'interpretar',
'descompensar', 'dispensar', 'expensar', 'recompensar', 'compensar',
'adecentar',
'inventar', 'reinventar', 'solventar',
): # herrar (not aferrar)
# tentar
if verbo[-5] == 'e':
raiz = verbo[:-5] + ie + verbo[-4:-2]
pres2s = raiz + 'as'
pres1s = raiz + 'o'
# pretar
else:
raiz = verbo[:-4] + ie + verbo[-3:-2]
pres2s = raiz + 'as'
pres1s = raiz + 'o'
assert pres1s in d['pres1s'], (d['pres1s'], pres1s)
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
elif verbo[-7:] in (
'temblar', 'sembrar', 'membrar', 'grentar', 'quebrar',
'rrendar',
): # temblar, sembrar (not zozobras)
if verbo[-6] == 'e':
raiz = verbo[:-6] + ie + verbo[-5:-2]
else:
raiz = verbo[:-5] + ie + verbo[-4:-2]
pres1s = raiz + 'o'
pres2s = raiz + 'as'
assert pres1s in d['pres1s'], (d['pres1s'], pres1s)
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
elif verbo[-6:] in ('lentar') and verbo[-7] in 'a': # alentar, sobrecalentar (not violentar)
raiz = verbo[:-5] + ie + verbo[-4:-2]
pres1s = raiz + 'o'
pres2s = raiz + 'as'
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
else: # hablar, acantonar, ventear
# if len(sílabas) > 1:
# if 'a' in sílabas[-2]:
# afijo = 'a'
# elif 'e' in sílabas[-2]:
# afijo = 'e'
# elif 'i' in sílabas[-2]:
# afijo = 'i'
# elif 'o' in sílabas[-2]:
# afijo = 'o'
# elif 'u' in sílabas[-2]:
# afijo = 'u'
# else:
# print(sílabas[-2])
# stop
# else:
# afijo = 'x'
if False:
pass
# elif sílabas[-1] == 'ciar' and len(sílabas) <= 2 and verbo not in ('saciar', 'viciar',):
# conj = verbo[:-3] + tilde.get(verbo[-3], verbo[-3]) + 'as'
# afijo = 'tilde'
# assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
# ar, pres, i > í / u > ú / iar > íar / uar > úar
# tilde
elif verbo in ( # irregulars / palabras graves
# 'espiar', 'expiar',
# 'aliar', 'desliar',
# 'aviar', 'desviar', 'enviar', 'reenviar',
'cariar', 'contrariar', 'inventariar', 'variar', 'desvariar', 'averiar',
# 'hastiar',
# 'ansiar',
# 'confiar',
'vaciar', 'ciar', 'rociar',
'piar', 'pipiar', 'espiar', 'expiar',
# 'criar',
# 'ampliar',
) or (verbo not in ( # regulars / sin tilde
# Pregunta Daniel por qué no hay tilde en pres2s...
# https://www.spanishdict.com/guide/spanish-word-stress/
'espaciar', 'agraciar', 'congraciar', 'desgraciar', 'saciar',
'apreciar', 'depreciar', 'especiar', 'justipreciar', 'despreciar',
'iniciar', 'reiniciar', 'oficiar',
'menospreciar', 'arreciar', 'codiciar', 'desperdiciar', 'beneficiar',
'conciliar', 'domiciliar', 'reconciliar', 'defoliar', 'exfoliar', 'foliar',
'exiliar', 'expoliar', 'tertuliar',
'chipiar', 'principiar', 'limpiar', 'tapiar', 'ripiar', 'columpiar',
'acopiar', 'copiar', 'fotocopiar', 'multicopiar', 'xerocopiar',
'escariar', 'excoriar', 'feriar', 'injuriar', 'asalariar', 'seriar',
'pifiar', 'atrofiar',
'obviar', 'agraviar', 'desagraviar', 'aliviar', 'soliviar', 'noviar', 'diluviar',
'angustiar', 'sitiar',
'soliloquiar', 'obsequiar',
'anestesiar',
# 'feriar',
) and sílabas[-1] in (
'cuar',
'duar', # graduar
'luar', # valuar
'nuar', # atenuar
'ruar',
'suar',
'tuar',
# 'ciar', # ciar, vaciar, not espaciar, not agraciar, not desgraciar, not saciar
'fiar', # desafiar, confiar, not pifiar, not atrofiar
'liar', # aliar, desliar, paliar, not exiliar, not familiar
# 'miar', #
# 'piar', # espiar, expiar, pipiar
# 'riar', # cariar, inventariar, not injuriar, not asalariar
'siar',
'tiar', # hastiar, amnistiar
'viar', # aviar
'criar',
'friar',
'griar',
'pliar', 'rriar',
'triar',
'truar',
'guiar',
'quiar', # esquiar, not soliloquiar
)# and any((
# 'tiar' in verbo, 'fiar' in verbo, 'aliar' in verbo,
# 'riar' in verbo, 'squia' in verbo,
# ))
):
raiz = verbo[:-3] + tilde.get(verbo[-3], verbo[-3])
pres1s = raiz + 'o'
pres2s = raiz + 'as'
afijo = 'tilde'
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
# elif len(sílabas) == 2 and sílabas[-1] in (
# 'riar',
# ):
# conj = verbo[:-3] + tilde.get(verbo[-3], verbo[-3]) + 'as'
# afijo = 'tilde'
elif ''.join(sílabas[-2:]) in (
'baular', 'feinar',
):
raiz = ''.join(sílabas[:-2]) + ''.join(sílabas[-2:])[:-4] + tilde.get(verbo[-4], verbo[-4]) + verbo[-3:-2]
pres1s = raiz + 'o'
pres2s = raiz + 'as'
afijo = 'tilde'
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
# # pres2s i > í (ar)
# elif len(sílabas) == 1 and 'i' in verbo[:-2]:
# conj = verbo[:-3] + tilde[verbo[-3]] + 'as'
# assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
# pres2s i > í (ar)
elif sílabas[0][-1] in 'aeo' and ''.join(sílabas[-2:]) in (
'hijar', # ahijar, prohijar
'hilar', # ahilar, rehilar
'hinar', # amohinar
'hitar', # ahitar
'humar', # ahumar, not inhumar, not trashumar, not exhumar
'husar', # rehusar
'hincar', # ahincar (silent h?)
'huchar', # ahuchar (silent h?)
):
raiz = ''.join(sílabas[:-2]) + sílabas[-2][0] + tilde.get(sílabas[-2][1]) + sílabas[-2][2:] + sílabas[-1][:-2]
pres1s = raiz + 'o'
pres2s = raiz + 'as'
afijo = 'tilde'
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
elif all((
verbo not in ('desairar',),
''.join(sílabas[-2:]) in (
'traillar', 'aullar', 'maullar',
'aunar',
'aislar',
'mau',
'nar', 'rar',
# 'lar', # aislar, not bailar, not hular
'aupar',
'airar', # airar, not desairar
'raizar', # enraizar
'peizar',
),
)):
print(''.join(sílabas[:-1])[:-1])
print(tilde.get(''.join(sílabas[:-1])[-1]))
print(sílabas[-1][:-2])
if sílabas[-2] in ('ais',):
raiz = ''.join(sílabas[:-1])[:-2] + tilde.get(''.join(sílabas[:-1])[-2]) + ''.join(sílabas[:-1])[-1] + sílabas[-1][:-2]
else:
raiz = ''.join(sílabas[:-1])[:-1] + tilde.get(''.join(sílabas[:-1])[-1]) + sílabas[-1][:-2]
pres1s = raiz + 'o'
pres2s = raiz + 'as'
afijo = 'tilde'
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
else:
raiz = verbo[:-2]
pres1s = raiz + 'o'
pres2s = raiz + 'as'
pres3s = raiz + 'a'
pres1p = raiz + 'amos'
pres2p = raiz + 'áis'
pres3p = raiz + 'an'
vocalicos = ('ai', 'au', 'ei', 'eu',)
if any((
verbo[-3:] in ('iar', 'uar',),
any(vocalico in ''.join(sílabas[-2:]) for vocalico in vocalicos),
)):
afijo = 'regular1'
afijo = 'regular2'
assert pres1s in d['pres1s'], (d['pres1s'], 'pres1s not regular!')
assert pres2s in d['pres2s'], (d['pres2s'], 'pres2s not regular!')
assert pres3s in d['pres3s'], (pres3s, d['pres3s'], 'pres3s not regular!')
assert pres1p in d['pres1p'], (d['pres1p'], 'pres1p not regular!')
assert pres2p in d['pres2p'], (d['pres2p'], 'pres2p not regular!')
assert pres3p in d['pres3p'], (d['pres3p'], 'pres3p not regular!')
with open('pres2s.ar.{}.txt'.format(afijo), 'a') as f:
print(verbo, ''.join(sílabas[-2:]), sep='\t', file=f)
## continue # tmp!!!
# pres1s = raiz + 'o'
# pres2s = raiz + 'as'
assert pres1s in d['pres1s'], (d['pres1s'], pres1s)
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
return
def pret_ar(d, verbo, sílabas):
# pret3s ar
if False:
pass
elif verbo == 'dar':
pret3s = 'dio'
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
elif len(verbo) <= 4 and verbo[-3] in ('i',):
# dar, ciar, fiar
pret3s = verbo[:-2] + 'o'
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
# elif verbo in ('andar', 'desandar'):
# conj = verbo[:-3] + verbo[-3] + 'uvo'
# assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
# elif sílabas[-2:] == ['an', 'dar']:
# conj = ''.join(sílabas[:-1]) + sílabas[-1][:-2] + 'uvo'
# assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
# with open('irregular.pret3s.dar.txt', 'a') as f:
# print(verbo, file=f)
elif sílabas[-2:] in (['es', 'tar'], ['an', 'dar'],):
raiz = verbo[:-3] + verbo[-3]
pret3s = raiz + 'uvo'
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
else:
pret3s = verbo[:-2] +'ó'
assert pret3s in d['pret3s'], (d['pret3s'], pret3s, 'pret3s not regular!')
## continue # tmp!!!
assert not verbo.endswith('uir')
with open('regular.pret3s.ar.txt', 'a') as f:
print(verbo, file=f)
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
return
def pret_erir(d, verbo, sílabas):
if False:
pass
elif verbo in ('ser', 'ir'):
pret3s = 'fue'
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
elif verbo == 'ver':
pret3s = 'vio'
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
elif verbo.endswith('tener'):
pret3s = verbo[:-4] + 'uvo' # como andar/anduvo
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
# irregular
elif verbo.endswith('aber'):
if verbo[-5] == 'h':
assert verbo == 'haber'
pret3s = verbo[:-4] + 'ubo'
else:
pret3s = verbo[:-4] + 'upo'
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
# elif verbo.endswith('bucir'):
# conj = verbo[:-4] + 'ijo'
# assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
# i > j, -c
elif verbo[-5:] in ('ducir',):
pret3s = verbo[:-3] + 'jo'
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
# irregular
elif verbo[-5:] == 'poner':
pret3s = verbo[:-4] + 'uso'
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
# e > i
elif verbo.endswith('querer'): # querer, malquerer
pret3s = verbo[:-6] + 'quiso'
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
# pret3s e > i, i > j, -c
elif verbo[-5:] in ('decir',):
pret3s = verbo[:-5] + 'dijo'
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
# pret3s e > i
elif verbo[-6:] in ('querir', 'rretir',): # requerir
pret3s = verbo[:-4] + i + verbo[-3:-2] + 'ió'
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
# pret3s e > i
elif verbo[-6:] in ('hervir',): # hervir
pret3s = verbo[:-5] + i + verbo[-4:-2] + 'ió'
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
# elif verbo[-6:] == 'querir': # requerir
# conj = verbo[:-4] + ie + verbo[-3] + 'es'
# assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
# e > i, -i
elif verbo.endswith('venir'): # venir, avenir
pret3s = verbo[:-5] + 'vino'
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
# pret3s o > u (er/ir)
elif verbo == 'dormir':
pret3s = 'durm' + 'ió'
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
elif verbo == 'morir':
pret3s = 'mur' + 'ió'
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
elif verbo == 'poder':
pret3s = 'pudo'
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
# i > j
elif verbo[-5:] in ('traer',):
pret3s = verbo[:-2] + 'jo'
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
# -e
elif verbo[-4:] == 'reír':
pret3s = verbo[:-3] + 'ió'
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
# -i
elif verbo[-6:] in [
'bullir', 'fallir', 'gullir', 'mullir', 'tullir',
'bruñir', 'gruñir',
]:
pret3s = verbo[:-2] + 'ó'
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
# ui > y (er/ir)
elif verbo[-4:] in endings_uir4:
pret3s = verbo[:-2].replace('ü', 'u') + 'yó'
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
elif verbo[-4:] in (
'caer', 'raer',
'leer', 'seer', 'veer',
'roer',
):
pret3s = verbo[:-2] + 'yó'
afijo = 'aer_eer_oer'
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
elif verbo[-5:] in endings_uir5 + ['creer']:
pret3s = verbo[:-2] + 'yó'
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
# acer > izo (er/ir)
elif verbo[-5:] in ('haber', 'hacer', 'facer'):
# silent h...
if len(verbo) == 5:
pret3s = verbo[:-4] + 'izo'
elif verbo[-6] in 'ae' and verbo[-5] == 'h':
pret3s = verbo[:-4] + 'ízo'
else:
pret3s = verbo[:-4] + 'izo'
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
# pret3s e > i (er/ir)
elif verbo[-5:] in endings_CeCir:
pret3s = verbo[:-4] + 'i' + verbo[-3:-2] + 'ió'
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
elif verbo[-6:] in ('mentir', 'sentir', 'vertir', 'bestir',):
pret3s = verbo[:-5] + 'i' + verbo[-4:-2] + 'ió'
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
elif verbo[-6:] in endings_CeCXir:
pret3s = verbo[:-5] + 'i' + verbo[-4:-2] + 'ió'
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
elif verbo.endswith('henchir'):
pret3s = verbo[:-6] + 'i' + verbo[-5:-2] + 'ió'
assert pret3s in d['pret3s'], (d['pret3s'], pret3s)
else:
assert verbo[-4:] != 'llir'
assert verbo[-3:] != 'uir'
assert verbo[-3:] not in ('aer', 'eer', 'oer')
pret3s = verbo[:-2] + 'ió'
assert pret3s in d['pret3s'], (pret3s, 'pret3s not regular!')
## continue # tmp!!!
with open('regular.pret3s.er_ir.txt', 'a') as f:
print(verbo, file=f)
return
def pres_erir(d, verbo, sílabas, sílabas_sin_prefijos):
ue = 'ue'
ie = 'ie'
raiz = verbo[:-2]
if False:
pass
# irregular
elif verbo == 'ser':
pres1s = 'soy'
pres2s = 'eres' # not ses
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
afijo = 'irregular'
elif ''.join(sílabas_sin_prefijos) == 'ver':
pres1s = ''.join(sílabas[:-1]) + 'veo' # not vo or ve
if verbo == 'ver':
pres2s = ''.join(sílabas[:-1]) + 'ves' # regular
else: # rever
pres2s = ''.join(sílabas[:-1]) + 'vés' # regular
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
afijo = 'irregular'
elif verbo == 'ir':
pres1s = 'voy' # not not vo
pres2s = 'vas' # not ves
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
afijo = 'irregular'
# irregular ber
elif verbo == 'haber':
pres1s = 'he'
pres2s = 'has' # not habes
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
afijo = 'irregular'
elif verbo == 'caber':
pres1s = 'quepo'
pres2s = raiz + 'es' # regular!
afijo = 'irregular1sregular2s'
elif verbo == 'saber':
pres1s = 'sé'
pres2s = raiz + 'es' # regular!
afijo = 'irregular1sregular2s'
elif verbo[-5:] in ('beber', 'deber', 'ceder'):
pres1s = raiz + 'o'
pres2s = raiz + 'es' # regular!
afijo = 'irregular1sregular2s'
elif verbo[-6:] in ('lamber', 'sorber',):
pres1s = raiz + 'o'
pres2s = raiz + 'es' # regular!
afijo = 'irregular1sregular2s'
elif verbo[-4:] == 'caer':
pres1s = raiz + 'igo'
pres2s = raiz + 'es' # regular!
afijo = 'irregular1s'
elif verbo[-5:] == 'traer':
pres1s = raiz + 'igo'
pres2s = raiz + 'es' # regular!
afijo = 'irregular1sregular2s'
# https://www.spanishdict.com/guide/spelling-changes-in-the-present-tense
elif ''.join(sílabas[-2:]) in (
'valer',
'tener',
'poner',
# 'asir',
# 'salir',
# 'oír',
):
sufijo = 'go'
pres1s = verbo[:-2] + sufijo
if verbo.endswith('tener'):
pres2s = verbo[:-4] + ie + verbo[-3] + 'es'
else:
pres2s = verbo[:-2] + 'es'
afijo = 'pres1sGO'
# https://www.spanishdict.com/guide/spelling-changes-in-the-present-tense
elif verbo[-3:] in ('cer', 'cir'):
if verbo[-5:] in (
'hacer', 'facer', 'yacer',
):
sufijo = 'go'
elif verbo[-4] in 'aeiou' and ''.join(sílabas_sin_prefijos) != 'mecer':
sufijo = 'zco' # conocer
else:
sufijo = 'zo'
# er, pres1s, o > ue
if ''.join(sílabas[-2:]) in (
'cocer', # cocer, recocer
'torcer',
# 'nocer', # conocer
):
index = verbo.rindex('o')
prefijo = verbo[:index] + ue + verbo[index + 1:-3]
# prefijo2s = verbo[:index] + ue + verbo[index + 1:-3]
sufijo = 'zo'
afijo = 'pres1scercir_OtoUE2s'
else:
prefijo = verbo[:-3]
assert raiz == prefijo + verbo[-3]
assert 'o' not in sílabas[-2] or verbo in ('conocer', 'reconocer', 'desconocer')
afijo = 'irregular1sregular2s'
pres1s = prefijo + sufijo
pres2s = prefijo + 'ces'
# elif verbo[-6:] in ('placer', 'checer',):
# pres1s = verbo[:-3] + 'zco'
# pres2s = raiz + 'es' # regular!
# afijo = 'irregular1sregular2s'
# elif ''.join(sílabas_sin_prefijos) in (
# 'mecer', 'vencer', 'ejercer',
# ): # mecer, remecer, not estremecer
# pres1s = verbo[:-3] + 'zo'
# pres2s = raiz + 'es' # regular!
# afijo = 'irregular1sregular2s'
elif verbo[-3:] in ('ger', 'gir',):
raiz = verbo[:-3]
pres1s = raiz + 'jo'
pres2s = raiz + 'ges'
afijo = 'pres1sgergir'
# er/ir, pres2s, o > ue
# elif verbo[-6:] in ('volver', 'solver',): # volver, not resolver
# pres2s = verbo[:-5] + 'uelves'
# assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
elif ''.join(sílabas[-2:]) in (
'cocer',
'poder',
'doler', 'moler', 'soler', 'oler',
'mover',
'morir',
'morder',
'dormir',
'volver',
'solver',
):
index = verbo[:-2].rindex('o')
raiz = verbo[:index] + ue + verbo[index + 1:-2]
if verbo == 'oler':
prefijo = 'h'
else:
prefijo = ''
pres1s = prefijo + raiz + 'o'
pres2s = prefijo + raiz + 'es'
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
afijo = 'pres1sOtoUEpres2sOtoUE'
# ui > uy (er/ir)
elif verbo[-4:] in endings_uir4: # atribuir (not delinquir)
if verbo[-4] == 'h' and len(verbo) > 4: # rehuir
assert verbo == 'rehuir'
pres2s = verbo[:-2].replace('u', 'ú') + 'yes'
else:
pres2s = verbo[:-2].replace('ü', 'u') + 'yes'
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
elif verbo[-5:] in endings_uir5:
# atribuir (not delinquir)
pres2s = verbo[:-2] + 'yes'
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
# assert d['pres2s'] == verbo[:-2].replace('ü', 'u') + 'yes', pres2s
# er/ir, pres2s, e > ie
elif verbo[-4:] == 'reír': # reír, sonreír
pres1s = verbo[:-4] + 'rió'
pres2s = verbo[:-4] + 'ríes'
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
# er/ir, pres2s, e > ie
elif verbo[-3:] in (
'rir', 'nir', 'tir',
'der', 'eer', 'jer', 'ler', 'mer', 'ner', 'per', 'rer', 'ser', 'ter', 'ver',
):
# ) or ''.join(sílabas[-2:]) in (
# 'leer', 'creer', 'seer', 'veer',
# 'herir', 'ferir', 'gerir', 'jerir',
# 'venir',
# 'heder',
# 'poder',
# 'tejer',
# 'tener',
# # raiz = verbo[:-4] + ie + verbo[-3:-2]
# # pres1s = raiz + 'o' # heder
# # pres2s = raiz + 'es'
# # assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
# 'cender',
# 'conder', # esconder escondo escondes
# 'fender', # defender defiendo defiendes, ofender ofendo ofendes
# 'hender',
# 'pender',
# 'ponder', # corresponder correspondo correspondes
# 'perder',
# 'tender', # contender
# 'vender', # vender vendo vendes
# 'cerner',
# 'verter',
# 'hendir',
# 'cernir',
# 'mentir',
# 'sentir',
# 'vertir',
# 'hervir',
# 'prender', # desprender
# 'rromper',
# ):
# # pres2s = verbo[:-5] + ie + verbo[-4:-2] + 'es'
# # assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
# no e > ie stem change
if verbo in (
'creer',
'arder',
'ofender', # not defender
'aprehender',
'pretender',
'vender',
'esconder',
'joder',
'temer',
'barrer',
'toser',
'competer',
'precaver',
) or ''.join(sílabas[-2:]) in (
'pender', 'prender',
'vender', # vender, revender
'leer', # leer, releer
'creer', # creer, decreer
'seer', # poseer, sobreseer, desposeer
'veer', # proveer, desproveer
'tejer', # tejer, entretejer
'peler', # repeler, impeler
'lamer', # lamer, relamer
'comer', # comer, carcomer
'ponder', # corresponder, responder
'rromper', # corromper
'romper', # romper
'correr', # correr, acorrer
'coser', # coser, recoser
'meter', # meter, remeter
):
# 'prender', 'aprender', 'desaprender', 'reprender', 'emprender', 'reemprender', 'comprender', 'sorprender',
# ):
raiz = verbo[:-2]
afijo = 'pres1sOending'
# e > ie stem change
else:
assert sílabas[-2] in (
'he', # heder
'cen', # encender
'fen',
'hen',
'ten', # tender
'per', # perder
'cer', # cerner
'que', # querer
'ver', # verter
) and sílabas[-1] in (
'der',
'ner',
'rer', # querer
'ter', # verter
)
if verbo.endswith('prender'):
stop5
index = verbo[:-2].rindex('e')
raiz = verbo[:index] + ie + verbo[index + 1:-2]
afijo = 'EtoIE'
pres1s = raiz + 'o'
pres2s = raiz + 'es'
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
assert pres1s in d['pres1s'], (d['pres1s'], pres1s)
elif verbo[-6:] in ('querir', 'querer',): # requerir
raiz = verbo[:-4] + ie + verbo[-3:-2]
pres2s = raiz + 'es'
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
# elif verbo[-4:] in ('erer'): # querer, zaherir
# conj = verbo[:-4] + ie + verbo[-3:-2] + 'es'
# assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
# elif verbo[-5:] in ('entir', 'ertir',): # mentir, pervertir
# assert d['pres2s'] == verbo[:-5] + ie + verbo[-4:-2] + 'es', pres2s
# elif verbo[-4:] in ('enir', 'ener'): # venir, tener
# assert d['pres2s'] == verbo[:-4] + ie + verbo[-3] + 'es', pres2s
# elif verbo[-4:] == 'rter': # verter (not cometer)
# assert d['pres2s'] == verbo[0] + 'iertes', pres2s
# pres2s e > é
elif verbo.endswith('rever'):
pres2s = verbo[:-2] + 'es'.replace('e', 'é')
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
# pres2s u > ú
elif verbo != 'unir' and verbo.endswith('unir') and verbo[-5] == 'e': # reunir, not desunir
pres2s = verbo[:-4] + 'únes'
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
# pres2s e > i (er/ir)
elif verbo[-6:] in endings_CeCXir + ['bestir']:
pres2s = verbo[:-5] + i + verbo[-4:-2] + 'es'
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
elif verbo[-6:] in (
'rretir',
): # derretir
pres2s = verbo[:-4] + i + verbo[-3:-2] + 'es'
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
elif verbo[-7:] in ('henchir',):
try:
if verbo[-8] == 'e':
vocal = 'e'
else:
vocal = None
except IndexError:
vocal = None
if vocal == 'e':
pres2s = verbo[:-6] + 'í' + verbo[-5:-2] + 'es'
else:
pres2s = verbo[:-6] + 'i' + verbo[-5:-2] + 'es'
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
# pres2s e > i (er/ir) CeCir
elif verbo[-5:] in endings_CeCir: # impedir (not trasgredir)
assert d['pres2s'] == verbo[:-4] + 'i' + verbo[-3] + 'es', pres2s
# elif verbo[-5:] in ('eguir', 'ervir',): # proseguir
# assert d['pres2s'] == verbo[:-5] +'i'+ verbo[-4:-2] +'es', pres2s
## elif verbo[-4:] in ('reír',): # sonreír
## assert d['pres2s'] == verbo[:-3] + ie + 'es', pres2s
# i > ie (adquirir, inquirir, re-adquirir)
elif verbo[-4:] == 'irir': # adquirir
pres2s = verbo[:-4] + ie + verbo[-3] + 'es'
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
# pres2s i > í (er/ir)
elif verbo[-5:] == 'hibir' and verbo[-6] == 'o':
pres2s = verbo[:-5] + 'híbes'
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
# elif verbo[-4:] in ('oler', 'over', 'oder', 'orir'): # moler (not valer), poder (not interceder), mover
# assert d['pres2s'] == verbo[:-4] + ue + verbo[-3] + 'es', pres2s
else: # comer
assert verbo[-3:] != 'uir'
assert verbo[-3:] != 'aer' # caer, traer
assert verbo[-3:] != 'ber' # caber
assert verbo[-3:] != 'cer' # hacer, satisfacer
pres1s = raiz + 'e'
pres2s = raiz + 'es'
pres3s = raiz + 'o'
pres1p = raiz + 'emos'
pres2p = raiz + 'eis'
pres3p = raiz + 'en'
assert pres1s in d['pres1s'], (d['pres1s'], 'pres1s not regular!')
assert pres2s in d['pres2s'], (d['pres2s'], 'pres2s not regular!')
assert pres3s in d['pres3s'], (d['pres3s'], 'pres3s not regular!')
assert pres1p in d['pres1p'], (d['pres1p'], 'pres1p not regular!')
assert pres2p in d['pres2p'], (d['pres2p'], 'pres2p not regular!')
assert pres3p in d['pres3p'], (d['pres3p'], 'pres3p not regular!')
## continue # tmp!!!
with open('regular.pres2s.er_ir.txt', 'a') as f:
print(verbo, file=f)
afijo = 'regular'
# pres1s = raiz + 'e'
assert pres1s in d['pres1s'], (d['pres1s'], pres1s)
assert pres2s in d['pres2s'], (d['pres2s'], pres2s)
with open('pres.er_ir.{afijo}.txt'.format(afijo=afijo), 'a') as f:
print(verbo, file=f)
return
def Any(verb):
S = 0
A = 0
pos = [
'tener','estar','venir','haber','hacer',
'salir','caber','valer','querer','poner','traer','decir',
'poder','saber','abrir','cubrir','escribir','freir',
'morir','resolver','romper','volver',
]
while pos[S] not in verb and S<len(pos)-1:
S += 1
B = len(pos[S])
while verb[A:B] != pos[S] and B<len(verb) and pos[S] in verb:
A += 1
B += 1
if verb[A:B] in pos:
stem = verb[0:A]
return stem
return False
def find_syllables_test():
for palabra in (
'amigo', 'mañana', 'enero', 'dinero',
'leo', 'caer', 'lee',
'cinco',
'calle', 'muchacho', 'cigarro',
'hablar', 'atlas', 'isla', 'perla', 'atlantico', 'encontrar',
'juicio', 'puerta', 'hueso', 'silabación', 'increíble',
'día', 'leído', 'flúido',
'instante', 'constante',
'expresar', 'conseguir', 'desorden', # prefixes
'sobreestimar', # prefixes
'Uruguay', 'Paraguay', # https://en.wikipedia.org/wiki/Triphthong
#'guayaba', # triphtong sin acento
#'cambiáis', 'cambiéis', 'situáis', 'guiáis', 'enviáis', 'estudiéis',
'redargüir',
'comandar',
):
sílabas = '/'.join(find_syllables(palabra))
print(palabra, sílabas)
assert sílabas in (
'a/mi/go', 'ma/ña/na', 'e/ne/ro', 'di/ne/ro',
'le/o', 'ca/er', 'le/e',
'cin/co',
'ca/lle', 'mu/cha/cho', 'ci/ga/rro',
'ha/blar', 'at/las', 'is/la', 'per/la', 'at/lan/ti/co', 'en/con/trar',
'jui/cio', 'puer/ta', 'hue/so', 'si/la/ba/ción', 'in/cre/í/ble',
'dí/a le/í/do', 'flú/i/do',
'cons/tan/te', 'ins/tan/te',
'ex/pre/sar', 'con/se/guir', 'des/or/den',
'dí/a', 'le/í/do', 'flú/i/do',
'cons/tan/te', 'ins/tan/te',
'ex/pre/sar', 'con/se/guir', 'des/or/den', # prefixes
'sobre/es/ti/mar', 'so/bre/es/ti/mar', # prefixes
'U/ru/guay', 'Pa/ra/guay', 'gu/aya/ba', 'cam/biáis', 'cam/biéis', 'si/tuáis', 'gu/iáis', 'en/viáis', 'es/tu/diéis',
're/dar/güir',
'co/man/dar',
), (palabra, sílabas)
return
def find_syllables(word):
## https://www.spanishdict.com/guide/spanish-syllables-and-syllabification-rules
## 1) Consonant Plus Vowel
## Whenever possible, you should break up words so that each syllable contains a consonant followed by a vowel. A consonant between two vowels belongs to the syllable with the second vowel.
## 2) Two Consecutive Consonants
## Two consecutive consonants will generally belong to separate syllables. However, if the second consonant in a consonant pair is r or l, the consonant pair is not separated into different syllables.
## Words that begin with prefixes often violate the above rules. For example the syllabification of enloquecer is en-lo-que-cer.
## 3) Three Consecutive Consonants
## When three consonants appear together, the first one will generally belong to a separate syllable.
## 4) Strong and Weak Vowels
##Spanish has both strong vowels (a, e, o) and weak vowels (i, u). Here are some rules on how the combinations of these vowels are divided into syllables.
##Two weak vowels together form a diphthong and are not separated into different syllables. Example:
##fui
##A weak vowel and a strong vowel together form a diphthong and are not separated into different syllables. Example:
##Juan
##Two strong vowels together form a hiatus and are separated into different syllables. Example:
##Le-o
## A tilde placed over a letter changes the above pronunciation rules, and the accented letter must be separated from any surrounding vowels. Example: mí-o
## https://quizlet.com/12460213/chapter-1-part-4-dividing-syllables-rules-in-spanish-pgs-16-18-flash-cards/
## 1) When dividing words into syllables the fundamental rule is to make each syllable end in a vowel and join a consonant occurring between vowels to the following vowel. a/mi/go ma/ña/na e/ne/ro di/ne/ro
## 2) Separate two strong vowels. le/o ca/er le/e
## 3) Usually, separate two consonants between vowels. cin/co
## 4) Consider ch, ll, and rr to be one letter and never separate them. ca/lle mu/cha/cho ci/ga/rro
## 5) Do not separate a consonant followed by the letter R or L, except r/l, s/l, t/l, n/r, s/r. ha/blar (not sep) at/las (sep) is/la per/la at/lan/ti/co
## 6) Do not separate the vowels of the diphthong or triphthong if accent marks are not used over the vowels. jui/cio puer/ta hue/so si/la/ba/ción (not sep) in/cre/í/ble (sep)
## 7) Divide syllables between vowels when an accent mark is placed over the weak vowel of the diphthong or triphthong or over the first of two weak vowels. dí/a le/í/do flú/i/do
## 8) If more than two consonants occur between vowels, join the final consonant to the next vowel. cons/tan/te ins/tan/te
## 9) A prefix is a separate syllable. ex/pre/sar con/se/guir des/or/den
##traslocar
##tras/lo/car
## si/la/ba/ción (weak strong, rising io diphtong in radio, why not separated?, dipthong over strong!)
## in/cre/í/ble (strong weak, accent mark and thus separated, dipthong over weak!) - in is a prefix?
## why is con not a prefix in cons/tan/te and in not in ins/tan/te? but con in con/se/guir and ex in ex/pre/sar and in in in/cre/í/ble? http://etimologias.dechile.net/?constante
## silabación
## increíble
## instante
## conseguir
## constante
## tripthong guayaba
s = ''
vowel = None
vowels = ''
consonants = ''
print(word)
m = re.match('^' + '|^'.join(prefijos) + '', word)
if m and word != 'enero':
end = m.end()
# cons-tan-te and ads-cri-bir? but not con-se-guir
if word[end] == 's' and word[end + 1] not in 'aeiouü':
breaks = [end + 1]
start = end + 1
else:
breaks = [end]
start = end
else:
breaks = []
start = 0
for i, x in enumerate(word):
## Adjust for existence of prefix.
if i < start:
continue
##for x in 'increíble':
if x in 'aeiouáéíóúAEIOUü':
if not vowel is None:
## Consecutive Vowels
if i - vowel == 1:
if len(vowels) > 2:
print(vowels)
stoptmp
## print(i, x, vowels)
# 6b) Do not separate the vowels of the diphthong or *triphthong* if accent marks are not used over the vowels.
# if word[vowel : vowel+3] in (
# 'uai',
# ):
# vowel = i
# vowels += x
# stop1
# continue
if False:
pass
# 6b) Do not separate the vowels of the diphthong or *triphthong* if accent marks are not used over the vowels.
elif vowels + x in (
'uai',
):
vowel = i
vowels += x
print('c', breaks)
## 1) Separate two strong vowels.
elif vowels + x in (
'aa', 'ae', 'ao',
'ea', 'ee', 'eo',
'oa', 'oe', 'oo',
):
breaks.append(vowel + 1)
print('a', breaks)
# 6a) Do not separate the vowels of the *diphthong* or triphthong if accent marks are not used over the vowels.
elif vowels + x in (
# falling (diptongo decreciente)
'ai', 'ei', 'oy', 'uy',
'au', # pausa
'eu', 'ou', 'ay',
# rising (diptongo creciente)
'ia', 'ie', 'io', 'iu', 'ua', 'ue',
'ui', # fuimos
'üi', # redagüir?
'uo',
):
vowel = i
vowels += x
print('b', breaks)
continue
## 7) Divide syllables between vowels when an accent mark is placed over the weak vowel of the diphthong or triphthong or over the first of two weak vowels.
elif vowels + x in (
'aí', 'eí', 'úi', 'aú', 'eú', 'oú',
'ía', 'íe', 'ío', 'íu', 'úa', 'úe', 'úi', 'úo',
):
breaks.append(vowel + 1)
else:
vowel = i
vowels += x
continue
## Two strong vowels together form a hiatus and are separated into different syllables.
## breaks.append(vowel + 1)
## Consonant Plus Vowel (rule 1)
elif i - vowel == 2:
breaks.append(vowel + 1)
print('d', breaks)
elif i - vowel in (3, 4, 5):
## Two Consecutive Consonants
if i - vowel == 3:
b = 1
## Three Consecutive Consonants.
elif i - vowel == 4:
b = 2
## Four Consecutive Consonants.
elif i - vowel == 5:
b = 3
else:
print(i - vowel, word, i, x, breaks, start)
stop22
## print(consonants)
## Consider ch, ll, and rr to be one letter and never separate them.
if consonants[-2:] in ('ch', 'll', 'rr'):
breaks.append(vowel + b)
## Do not separate a consonant followed by the letter R or L, except r/l, s/l, t/l, n/r, s/r.
# Do not seperate ha/blar
elif consonants[-2:][-1] in ('r', 'l'):
## except r/l, s/l, t/l, n/r, s/r.
if consonants[-2:] in ('rl', 'sl', 'tl', 'nr', 'sr'):
breaks.append(vowel + b + 1)
else:
breaks.append(vowel + b)
else:
breaks.append(vowel + b + 1)
print('e', breaks)
# word was broken left of the vowel
vowel = i
vowels = x
consonants = ''
## elif any((
## (word.startswith(consonants) and consonants + vowels in prefixes),
## (word.startswith(vowels) and vowels + consonants in prefixes),
## )):
## breaks.append(i)
## vowel = None
## vowels = ''
## consonants = ''
## m =
## print(m.start())
#### m = re.match(r'|'.join(prefixes), word)
#### print(m.start())
## stop77
else:
consonants += x
s = word
for pos in reversed(breaks):
s = s[:pos] + '/' + s[pos:]
return s.split('/')
if __name__ == '__main__':
find_syllables_test()
main()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment