Module:User:Vitalik/inflection-new/data/ru-noun
Jump to navigation
Jump to search
- This module lacks a documentation subpage. You may create it.
- Useful links: root page • root page’s subpages • links • transclusions • testcases • user page • user talk page • userspace
This is a private module sandbox of Vitalik, for their own experimentation. Items in this module may be added and removed at Vitalik's discretion; do not rely on this module's stability.
return {
template = 'ru-decl-noun-table',
affixes = {
-- masculine singular
m_hard_nom_sg = '',
m_soft_nom_sg = 'ь',
m_hard_gen_sg = 'а',
m_soft_gen_sg = 'я',
m_hard_dat_sg = 'у',
m_soft_dat_sg = 'ю',
m_hard_ins_sg = 'ом',
m_soft_ins_sg_stressed = 'ём',
m_soft_ins_sg_unstressed = 'ем',
-- neuter singular
n_hard_nom_sg = 'о',
n_soft_nom_sg_stressed = 'ё',
n_soft_nom_sg_unstressed = 'е',
n_hard_gen_sg = 'а',
n_soft_gen_sg = 'я',
n_hard_dat_sg = 'у',
n_soft_dat_sg = 'ю',
n_hard_ins_sg = 'ом',
n_soft_ins_sg_stressed = 'ём',
n_soft_ins_sg_unstressed = 'ем',
-- feminine singular
f_hard_nom_sg = 'а',
f_soft_nom_sg = 'я',
f_hard_gen_sg = 'ы',
f_soft_gen_sg = 'и',
f_hard_dat_sg = 'е',
f_soft_dat_sg_stressed = 'е',
f_soft_dat_sg_unstressed = 'е',
f_hard_acc_sg = 'у',
f_soft_acc_sg = 'ю',
f_hard_ins_sg = 'ой',
f_soft_ins_sg_stressed = 'ёй',
f_soft_ins_sg_unstressed = 'ей',
-- common singular
c_prp_sg_stressed = 'е',
c_prp_sg_unstressed = 'е',
-- masculine plural
m_hard_nom_pl = 'ы',
m_soft_nom_pl = 'и',
m_hard_gen_pl = 'ов',
m_soft_gen_pl_stressed = 'ей',
m_soft_gen_pl_unstressed = 'ей',
-- neuter plural
n_hard_nom_pl = 'а',
n_soft_nom_pl = 'я',
n_hard_gen_pl_stressed = '',
n_hard_gen_pl_unstressed = '',
n_soft_gen_pl_stressed = 'ей',
n_soft_gen_pl_unstressed = 'ь',
-- feminine plural
f_hard_nom_pl = 'ы',
f_soft_nom_pl = 'и',
f_hard_gen_pl_stressed = '',
f_hard_gen_pl_unstressed = '',
f_soft_gen_pl_stressed = 'ей',
f_soft_gen_pl_unstressed = 'ь',
-- common plural
c_hard_dat_pl = 'ам',
c_soft_dat_pl = 'ям',
c_hard_ins_pl = 'ами',
c_soft_ins_pl = 'ями',
c_hard_prp_pl = 'ах',
c_soft_prp_pl = 'ях',
},
conditions = {
{
class = 'common',
{},
},
{
comment = 'Remove ending (-а, -е, -ё, -о, -я, -й, -ь) to get stem',
stem = {'replace', 'base', '[аеёояйь]$', ''},
stem_stressed = {'arg_replace', 'base_stressed', '[аеёояйь]́?$', ''}, -- it was also removed last stress here
},
{
comment = "Add stress to stem_stressed if there is only one syllable and stress is absent",
_if = {
stem_stressed__not_match = '́',
stem_stressed__match_once = '{vowel}',
},
stem_stressed = {'var_replace', 'stem_stressed', '({vowel})', '%1́'},
},
{
comment = 'Parse "gender_class" argument and get values for "gender" and "animate"',
gender = {'match_arg', 'gender_class', '([mnf])%-[ia]n'},
animate = {'match_arg', 'gender_class', '[mnf]%-([ia]n)'},
},
{SECTION = 'Determination of stem type'},
{
stem_type = '',
},
{
_if = {stem__endswith = '{velar}'},
stem_type = 'velar',
},
{
_if = {stem__endswith = '{sibilant}'},
stem_type = 'sibilant',
},
{
_if = {stem__endswith = 'ц'},
stem_type = 'letter-ц',
},
{
_if = {stem__endswith = {'[йь]', '[аеёоуыюя]'}},
stem_type = 'vowel',
},
{
_if = {stem__endswith = 'и'},
stem_type = 'letter-и',
},
{
_if = {stem__not_endswith = {'{velar}', '{sibilant}', 'ц', '[йь]', '[аеёоуыюя]', 'и'}},
_then = {
{
_if = {gender = 'm'},
_then = {
{
_if = {stem = '<base>'},
stem_type = 'hard',
},
{
_if = {base__endswith = 'ь', base__not_endswith = 'путь'},
stem_type = 'soft',
},
{
_if = {base__endswith = 'путь'},
stem_type = 'm-3rd',
},
},
},
{
_if = {gender = 'f'},
_then = {
{
_if = {base__endswith = 'а'},
stem_type = 'hard',
},
{
_if = {base__endswith = 'я'},
stem_type = 'soft',
},
{
_if = {base__endswith = 'ь'},
stem_type = 'f-3rd',
},
},
},
{
_if = {gender = 'n'},
_then = {
{
_if = {base__endswith = 'о'},
stem_type = 'hard',
},
{
_if = {base__endswith = 'е'},
stem_type = 'soft',
},
{
_if = {base__endswith = 'мя'},
stem_type = 'n-3rd',
},
},
},
},
},
{
_if = {
gender = 'f',
stem_type = 'sibilant',
base__endswith = 'ь',
},
stem_type = 'f-3rd-sibilant',
},
{
_if = {stem_type = ''},
stem_type = 'hard',
},
{SECTION = 'Special changes for velar, sibilant, vowel etc. stem types'},
{
_if = {stem_type = {'velar', 'sibilant'}},
f_hard_gen_sg = 'и',
m_hard_nom_pl = 'и',
f_hard_nom_pl = 'и',
},
{
_if = {
stem_type = {'sibilant', 'letter-ц'},
stress = {'a', 'c', 'e'},
},
m_hard_ins_sg = 'ем',
n_hard_ins_sg = 'ем',
f_hard_ins_sg = 'ей',
m_hard_gen_pl = 'ев',
},
{
_if = {stem_type = {'sibilant'}},
m_hard_gen_pl = 'ей',
n_hard_gen_pl_stressed = 'ей',
n_hard_gen_pl_unstressed = '',
f_hard_gen_pl_stressed = 'ей',
f_hard_gen_pl_unstressed = '',
},
{
_if = {stem_type = {'vowel', 'letter-и'}},
m_soft_nom_sg = 'й',
n_soft_gen_pl_unstressed = 'й',
f_soft_gen_pl_unstressed = 'й',
},
{
_if = {stem_type = {'vowel', 'letter-и'}},
m_soft_gen_pl_stressed = 'ёв',
m_soft_gen_pl_unstressed = 'ев',
n_soft_gen_pl_stressed = 'й',
n_soft_gen_pl_unstressed = 'й',
f_soft_gen_pl_stressed = 'й',
f_soft_gen_pl_unstressed = 'й',
},
{
_if = {stem_type = {'letter-и'}},
f_soft_dat_sg_unstressed = 'и',
c_prp_sg_unstressed = 'и',
},
{
_if = {stem_type = {'m-3rd'}},
m_soft_gen_sg = 'и',
m_soft_dat_sg = 'и',
c_prp_sg_stressed = 'и',
c_prp_sg_unstressed = 'и',
},
{
_if = {stem_type = {'f-3rd', 'f-3rd-sibilant'}},
f_soft_nom_sg = 'ь',
f_soft_dat_sg_stressed = 'и',
f_soft_dat_sg_unstressed = 'и',
f_soft_acc_sg = 'ь',
f_soft_ins_sg_stressed = 'ью',
f_soft_ins_sg_unstressed = 'ью',
c_prp_sg_stressed = 'и',
c_prp_sg_unstressed = 'и',
f_soft_gen_pl_stressed = 'ей',
f_soft_gen_pl_unstressed = 'ей',
},
{
_if = {stem_type = {'f-3rd-sibilant'}},
c_soft_dat_pl = 'ам',
c_soft_ins_pl = 'ами',
c_soft_prp_pl = 'ах',
},
{SECTION = 'Resolve stressed/unstressed cases of endings'},
{
_if = {stress = {'a', 'c', 'e'}},
f_soft_dat_sg = '<f_soft_dat_sg_unstressed>',
m_soft_ins_sg = '<m_soft_ins_sg_unstressed>',
n_soft_ins_sg = '<n_soft_ins_sg_unstressed>',
f_soft_ins_sg = '<f_soft_ins_sg_unstressed>',
r_prp_sg = '<c_prp_sg_unstressed>',
},
{
_if = {stress = {'b', 'd', "d'", 'f', "f'"}},
f_soft_dat_sg = '<f_soft_dat_sg_stressed>',
m_soft_ins_sg = '<m_soft_ins_sg_stressed>',
n_soft_ins_sg = '<n_soft_ins_sg_stressed>',
f_soft_ins_sg = '<f_soft_ins_sg_stressed>',
r_prp_sg = '<c_prp_sg_stressed>',
},
{
_if = {stress = {'a', 'd', "d'"}},
m_soft_gen_pl = '<m_soft_gen_pl_unstressed>',
n_hard_gen_pl = '<n_hard_gen_pl_unstressed>',
n_soft_gen_pl = '<n_soft_gen_pl_unstressed>',
f_hard_gen_pl = '<f_hard_gen_pl_unstressed>',
f_soft_gen_pl = '<f_soft_gen_pl_unstressed>',
},
{
_if = {stress = {'b', 'c', 'e', 'f', "f'"}},
m_soft_gen_pl = '<m_soft_gen_pl_stressed>',
n_hard_gen_pl = '<n_hard_gen_pl_stressed>',
n_soft_gen_pl = '<n_soft_gen_pl_stressed>',
f_hard_gen_pl = '<f_hard_gen_pl_stressed>',
f_soft_gen_pl = '<f_soft_gen_pl_stressed>',
},
{SECTION = 'Determination of ending (depending on gender and stem type)'},
{
_if = {stem_type = {'hard', 'velar', 'sibilant', 'letter-ц', }},
_then = {
r_dat_pl = '<c_hard_dat_pl>',
r_ins_pl = '<c_hard_ins_pl>',
r_prp_pl = '<c_hard_prp_pl>',
{
_if = {gender = 'm'},
r_nom_sg = '<m_hard_nom_sg>',
r_gen_sg = '<m_hard_gen_sg>',
r_dat_sg = '<m_hard_dat_sg>',
r_ins_sg = '<m_hard_ins_sg>',
r_nom_pl = '<m_hard_nom_pl>',
r_gen_pl = '<m_hard_gen_pl>',
},
{
_if = {gender = 'n'},
r_nom_sg = '<n_hard_nom_sg>',
r_gen_sg = '<n_hard_gen_sg>',
r_dat_sg = '<n_hard_dat_sg>',
r_ins_sg = '<n_hard_ins_sg>',
r_nom_pl = '<n_hard_nom_pl>',
r_gen_pl = '<n_hard_gen_pl>',
},
{
_if = {gender = 'f'},
r_nom_sg = '<f_hard_nom_sg>',
r_gen_sg = '<f_hard_gen_sg>',
r_dat_sg = '<f_hard_dat_sg>',
r_acc_sg = '<f_hard_acc_sg>',
r_ins_sg = '<f_hard_ins_sg>',
r_nom_pl = '<f_hard_nom_pl>',
r_gen_pl = '<f_hard_gen_pl>',
},
},
},
{
_if = {stem_type = {'soft', 'vowel', 'letter-и', 'm-3rd', 'f-3rd', 'f-3rd-sibilant'}},
_then = {
r_dat_pl = '<c_soft_dat_pl>',
r_ins_pl = '<c_soft_ins_pl>',
r_prp_pl = '<c_soft_prp_pl>',
{
_if = {gender = 'm'},
r_nom_sg = '<m_soft_nom_sg>',
r_gen_sg = '<m_soft_gen_sg>',
r_dat_sg = '<m_soft_dat_sg>',
r_ins_sg = '<m_soft_ins_sg>',
r_nom_pl = '<m_soft_nom_pl>',
r_gen_pl = '<m_soft_gen_pl>',
},
{
_if = {gender = 'n'},
r_nom_sg = '<n_soft_nom_sg>',
r_gen_sg = '<n_soft_gen_sg>',
r_dat_sg = '<n_soft_dat_sg>',
r_ins_sg = '<n_soft_ins_sg>',
r_nom_pl = '<n_soft_nom_pl>',
r_gen_pl = '<n_soft_gen_pl>',
},
{
_if = {gender = 'f'},
r_nom_sg = '<f_soft_nom_sg>',
r_gen_sg = '<f_soft_gen_sg>',
r_dat_sg = '<f_soft_dat_sg>',
r_acc_sg = '<f_soft_acc_sg>',
r_ins_sg = '<f_soft_ins_sg>',
r_nom_pl = '<f_soft_nom_pl>',
r_gen_pl = '<f_soft_gen_pl>',
},
},
},
{SECTION = 'Apply stress type'},
{
_if = {stress = {'a', 'c', 'e'}},
stem_sg = '<stem_stressed>',
},
{
_if = {stress = {'b', 'd', "d'", 'f', "f'"}},
stem_sg = '<stem>',
r_nom_sg = {'replace', 'r_nom_sg', '^([аеиоуыюя])', '%1́'}, -- it was added stress here
r_gen_sg = {'replace', 'r_gen_sg', '^([аеиоуыюя])', '%1́'}, -- it was added stress here
r_dat_sg = {'replace', 'r_dat_sg', '^([аеиоуыюя])', '%1́'}, -- it was added stress here
r_ins_sg = {'replace', 'r_ins_sg', '^([аеиоуыюя])', '%1́'}, -- it was added stress here
r_prp_sg = {'replace', 'r_prp_sg', '^([аеиоуыюя])', '%1́'}, -- it was added stress here
},
{
_if = {
gender = 'f',
stress = {'b', 'd', 'f'},
},
r_acc_sg = {'replace', 'r_acc_sg', '^([аеиоуыюя])', '%1́'}, -- it was added stress here
},
{
_if = {stress = {'a', 'd', "d'", 'e', 'f', "f'"}},
stem_nom_pl = '<stem_stressed>',
},
{
_if = {stress = {'b', 'c'}},
stem_nom_pl = '<stem>',
r_nom_pl = {'replace', 'r_nom_pl', '^([аеиоуыюя])', '%1́'}, -- it was added stress here
},
{
_if = {stress = {'a', 'd', "d'"}},
stem_pl = '<stem_stressed>',
},
{
_if = {stress = {'b', 'c', 'e', 'f', "f'"}},
stem_pl = '<stem>',
r_gen_pl = {'replace', 'r_gen_pl', '^([аеиоуыюя])', '%1́'}, -- it was added stress here
r_dat_pl = {'replace', 'r_dat_pl', '^([аеиоуыюя])', '%1́'}, -- it was added stress here
r_ins_pl = {'replace', 'r_ins_pl', '^([аеиоуыюя])', '%1́'}, -- it was added stress here
r_prp_pl = {'replace', 'r_prp_pl', '^([аеиоуыюя])', '%1́'}, -- it was added stress here
},
{SECTION = 'Generate forms'},
{
form_nom_sg = '<stem_sg><r_nom_sg>',
form_gen_sg = '<stem_sg><r_gen_sg>',
form_dat_sg = '<stem_sg><r_dat_sg>',
form_ins_sg = '<stem_sg><r_ins_sg>',
form_prp_sg = '<stem_sg><r_prp_sg>',
form_nom_pl = '<stem_nom_pl><r_nom_pl>',
form_gen_pl = '<stem_pl><r_gen_pl>',
form_dat_pl = '<stem_pl><r_dat_pl>',
form_ins_pl = '<stem_pl><r_ins_pl>',
form_prp_pl = '<stem_pl><r_prp_pl>',
},
{
_if = {gender = 'f'},
form_acc_sg = '<stem_sg><r_acc_sg>',
},
{ -- TODO: refactoring
_if = {
gender = 'f',
stress = {"d'", "f'"},
},
form_acc_sg = '<stem_stressed><r_acc_sg>',
},
-- NEW IDEAS HERE !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
functions = {
add_stress = {
comment = '...',
_if = {
arg1__match_several = '@vowel',
arg1__not_match = '[́ё]',
},
arg1 = {'var_replace', 'arg1', '(@vowel)(@consonant*)$', '%1́%2'},
}
},
{SECTION = "Add stress if there is no one"},
{
_if = {
form_nom_sg__match_several = '@vowel',
form_nom_sg__not_match = '[́ё]',
},
form_nom_sg = {'var_replace', 'form_nom_sg', '(@vowel)(@consonant*)$', '%1́%2'},
},
{
_if = {
form_gen_pl__match_several = '{vowel}',
{equals = {'<тип>', '<base>'}},
{equals = {'<тип2>', '<base2>'}},
form_gen_pl__not_match = '[́ё]',
_or = {
stem = '',
stem_stressed = '',
}
},
form_gen_pl = {'var_replace', 'form_gen_pl', '({vowel})({consonant}*)$', '%1́%2'},
},
{SECTION = "Remove stress if there is only one syllable"},
{
_if = {form_nom_sg__match_once = '{vowel+ё}'},
form_nom_sg = {'var_replace', 'form_nom_sg', '́', ''},
},
{
_if = {form_gen_pl__match_once = '{vowel+ё}'},
form_gen_pl = {'var_replace', 'form_gen_pl', '́', ''},
},
{SECTION = 'Choose accusative forms'},
{
_if = {gender = 'n'},
form_acc_sg = '<form_nom_sg>',
},
{
_if = {gender = 'm'},
_then = {
{
_if = {animate = 'in'},
form_acc_sg = '<form_nom_sg>',
},
{
_if = {animate = 'an'},
form_acc_sg = '<form_gen_sg>',
},
},
},
{
_if = {animate = 'in'},
form_acc_pl = '<form_nom_pl>',
},
{
_if = {animate = 'an'},
form_acc_pl = '<form_gen_pl>',
},
{SECTION = 'If there are no plural forms'},
{
comment = 'This rule should be the last one. Otherwise — removing of plural form can be overriden by other classes',
_if = {st = '1'}, -- if we've received argument "st" equals to "1"
class = 'singularia_tantum',
},
},
classes = {
common = {
nom_sg = '<form_nom_sg>',
gen_sg = '<form_gen_sg>',
dat_sg = '<form_dat_sg>',
acc_sg = '<form_acc_sg>',
ins_sg = '<form_ins_sg>',
prp_sg = '<form_prp_sg>',
nom_pl = '<form_nom_pl>',
gen_pl = '<form_gen_pl>',
dat_pl = '<form_dat_pl>',
acc_pl = '<form_acc_pl>',
ins_pl = '<form_ins_pl>',
prp_pl = '<form_prp_pl>',
stem_type = '<stem_type>', -- just for testcases
},
singularia_tantum = {
nom_pl = '—',
gen_pl = '—',
dat_pl = '—',
acc_pl = '—',
ins_pl = '—',
prp_pl = '—',
},
},
}