Модуль:Ru-pron
Перейти к навигации
Перейти к поиску
Модуль для генерации транскрипции русских слов. Используется в шаблоне {{transcription-ru}}.
local ut = require("Module:utils")
local com = require("Module:ru-common")
local m_ru_translit = require("Module:ru-translit")
local strutils = require("Module:string utilities")
local export = {}
local u = mw.ustring.char
local rfind = mw.ustring.find
local rsubn = mw.ustring.gsub
local rmatch = mw.ustring.match
local rsplit = mw.text.split
local ulower = mw.ustring.lower
local uupper = mw.ustring.upper
local usub = mw.ustring.sub
local ulen = mw.ustring.len
-- version of rsubn() that discards all but the first return value
local function rsub(term, foo, bar)
local retval = rsubn(term, foo, bar)
return retval
end
-- apply rsub() repeatedly until no change
local function rsub_repeatedly(term, foo, bar)
while true do
local new_term = rsub(term, foo, bar)
if new_term == term then
return term
end
term = new_term
end
end
-- If enabled, compare this module with new version of module to make
-- sure all pronunciations are the same. Eventually consider removing this;
-- but useful as new code is created.
local test_new_ru_pron_module = false
-- If enabled, do new code for final -е; else, the old way
local new_final_e_code = false
local AC = u(0x0301) -- acute = ́
local GR = u(0x0300) -- grave = ̀
local CFLEX = u(0x0302) -- circumflex = ̂
local DUBGR = u(0x030F) -- double grave = ̏
local DOTABOVE = u(0x0307) -- dot above = ̇
local DOTBELOW = u(0x0323) -- dot below = ̣
local vow = 'aeiouyɛəäạëöü'
local ipa_vow = vow .. 'ɐɪʊɨæɵʉ'
local vowels, vowels_c = '[' .. vow .. ']', '([' .. vow .. '])'
-- No need to include DUBGR here because we rewrite it to CFLEX very early
local acc = AC .. GR .. CFLEX .. DOTABOVE .. DOTBELOW
local accents = '[' .. acc .. ']'
local perm_syl_onset = ut.list_to_set({
'bd', 'bz', 'bl', 'br', 'vd', 'vz', 'vzv', 'vl', 'vm', 'vr', 'gl', 'gn', 'gr', 'dž', 'dn', 'dv', 'dl', 'dr', 'žd', 'zb', 'zd', 'zm', 'zn', 'zv', 'zr', 'kl', 'kr', 'kt', 'ml', 'mn', 'nr', 'pl', 'pr', 'ps', 'pt', 'pš', 'stv', 'str', 'sp', 'st', 'sk', 'skl', 'skr', 'sl', 'sf', 'sx', 'sc', 'sm', 'sn', 'sv','sʺ', 'sʹj', 'spr', 'sr', 'tk', 'tv', 'tl', 'tr', 'fk', 'fl', 'fr', 'fs', 'ft', 'fš', 'xl', 'xm', 'xr', 'šk', 'šl', 'št', 'šč',
})
-- FIXME: Consider changing ӂ internally to ʑ to match ɕ (it is used externally
-- in e.g. дроӂӂи (pronunciation spelling of дрожжи)
local translit_conv = {
['c'] = 't͡s', ['č'] = 't͡ɕ', ['ĉ'] = 't͡ʂ',
['g'] = 'ɡ', ['ĝ'] = 'd͡ʐ',
['ĵ'] = 'd͡z', ['ǰ'] = 'd͡ʑ', ['ӂ'] = 'ʑ',
['š'] = 'ʂ', ['ž'] = 'ʐ'
}
local translit_conv_j = {
['cʲ'] = 'tʲ͡sʲ',
['ĵʲ'] = 'dʲ͡zʲ'
}
local allophones = {
['a'] = { 'a', 'ɐ', 'ə' },
['e'] = { 'e', 'ɪ', 'ɪ' },
['i'] = { 'i', 'ɪ', 'ɪ' },
['o'] = { 'o', 'ɐ', 'ə' },
['u'] = { 'u', 'ʊ', 'ʊ' },
['y'] = { 'ɨ', 'ɨ', 'ɨ' },
['ɛ'] = { 'ɛ', 'ɛ', 'ɛ' },
['ä'] = { 'a', 'ɪ', 'ɪ' },
['ạ'] = { 'a', 'ɐ', 'ə' },
['ë'] = { 'e', 'ɪ', 'ɪ' },
['ö'] = { 'ɵ', 'ɪ', 'ɪ' },
['ü'] = { 'u', 'ʊ', 'ʊ' },
['ə'] = { 'ə', 'ə', 'ə' },
}
local devoicing = {
['b'] = 'p', ['d'] = 't', ['g'] = 'k',
['z'] = 's', ['v'] = 'f',
['ž'] = 'š', ['ɣ'] = 'x',
['ĵ'] = 'c', ['ǰ'] = 'č', ['ĝ'] = 'ĉ',
['ӂ'] = 'ɕ',
}
local voicing = {
['p'] = 'b', ['t'] = 'd', ['k'] = 'g',
['s'] = 'z', ['f'] = 'v',
['š'] = 'ž', ['c'] = 'ĵ', ['č'] = 'ǰ', ['ĉ'] = 'ĝ',
['x'] = 'ɣ', ['ɕ'] = 'ӂ'
}
local iotating = {
['a'] = 'ä',
['e'] = 'ë',
['o'] = 'ö',
['u'] = 'ü'
}
local retracting = {
['e'] = 'ɛ',
['i'] = 'y',
}
local fronting = {
['a'] = 'æ',
['u'] = 'ʉ',
['ʊ'] = 'ʉ',
}
-- Prefixes that we recognize specially when they end in a geminated
-- consonant. The first element is the result after applying voicing/devoicing,
-- gemination and other changes. The second element is the original spelling,
-- so that we don't overmatch and get cases like Поттер. We check for these
-- prefixes at the beginning of words and also preceded by ne-, po- and nepo-.
local geminate_pref = {
--'abː', --'adː',
{'be[szšž]ː', 'be[sz]'},
--'braomː',
{'[vf]ː', 'v'},
{'vo[szšž]ː', 'vo[sz]'},
{'i[szšž]ː', 'i[sz]'},
--'^inː',
{'kontrː', 'kontr'},
{'superː', 'super'},
{'tran[szšž]ː', 'trans'},
{'na[tdcč]ː', 'nad'},
{'ni[szšž]ː', 'ni[sz]'},
{'o[tdcč]ː', 'ot'}, --'^omː',
{'o[bp]ː', 'ob'},
{'obe[szšž]ː', 'obe[sz]'},
{'po[tdcč]ː', 'pod'},
{'pre[tdcč]ː', 'pred'}, --'^paszː', '^pozː',
{'ra[szšž]ː', 'ra[sz]'},
{'[szšž]ː', '[szšž]'}, -- ž on right for жжёт etc., ш on left for США
{'me[žš]ː', 'mež'},
{'če?re[szšž]ː', 'če?re[sz]'},
-- certain double prefixes involving ra[zs]-
{'predra[szšž]ː', 'predra[sz]'},
{'bezra[szšž]ː', 'bezra[sz]'},
{'nara[szšž]ː', 'nara[sz]'},
{'vra[szšž]ː', 'vra[sz]'},
{'dora[szšž]ː', 'dora[sz]'},
-- '^sverxː', '^subː', '^tröxː', '^četyröxː',
}
local sztab = { s='cs', z='ĵz' }
local function ot_pod_sz(pre, sz)
return pre .. sztab[sz]
end
local phon_respellings = {
{'h', 'ɣ'},
{'šč', 'ɕː'}, -- conversion of šč to geminate
-- the following group is ordered before changes that affect ts
-- FIXME!!! Should these also pay attention to grave accents?
{'́tʹ?sja⁀', '́cca⁀'},
{'([^́])tʹ?sja⁀', '%1ca⁀'},
{'n[dt]sk', 'n(t)sk'},
{'s[dt]sk', 'sck'},
-- Add / before цз, чж sequences (Chinese words) and assimilate чж
{'cz', '/cz'},
{'čž', '/ĝž'},
-- main changes for affricate assimilation of [dt] + sibilant, including ts;
-- we either convert to "short" variants t͡s, d͡z, etc. or to "long" variants
-- t͡ss, d͡zz, etc.
-- 1. т с, д з across word boundary, also т/с, д/з with explicitly written
-- slash, use long variants.
{'[dt](ʹ?[ ‿⁀/]+)s', 'c%1s'},
{'[dt](ʹ?[ ‿⁀/]+)z', 'ĵ%1z'},
-- 2. тс, дз + vowel use long variants.
{'[dt](ʹ?)s(j?' .. vowels .. ')', 'c%1s%2'},
{'[dt](ʹ?)z(j?' .. vowels .. ')', 'ĵ%1z%2'},
-- 3. тьс, дьз use long variants.
{'[dt]ʹs', 'cʹs'},
{'[dt]ʹz', 'ĵʹz'},
-- 4. word-initial от[сз]-, под[сз]- use long variants because there is
-- a morpheme boundary.
{'(⁀o' .. accents .. '?)t([sz])', ot_pod_sz},
{'(⁀po' .. accents .. '?)d([sz])', ot_pod_sz},
-- 5. other тс, дз use short variants.
{'[dt]s', 'c'},
{'[dt]z', 'ĵ'},
-- 6. тш, дж always use long variants (FIXME, may change)
{'[dt](ʹ?[ %-‿⁀/]*)š', 'ĉ%1š'},
{'[dt](ʹ?[ %-‿⁀/]*)ž', 'ĝ%1ž'},
-- 7. soften palatalized hard hushing affricates resulting from the previous
{'ĉʹ', 'č'},
{'ĝʹ', 'ǰ'},
-- changes that generate ɕː and ɕč through assimilation:
-- зч and жч become ɕː, as does сч at the beginning of a word and in the
-- sequence счёт when not following [цдт] (подсчёт); else сч becomes ɕč
-- (отсчи́тываться), as щч always does (рассчитáть written ращчита́ть)
{'[cdt]sč', 'čɕː'},
{'ɕːč', 'ɕč'},
{'[zž]č', 'ɕː'},
{'[szšž]ɕː?', 'ɕː'},
{'⁀sč', '⁀ɕː'},
{'sčjo(' .. accents .. '?)t', 'ɕːjo%1t'},
{'sč', 'ɕč'},
-- misc. changes for assimilation of [dtsz] + sibilants and affricates
{'[sz][dt]c', 'sc'},
{'([rn])[dt]([cč])', '%1%2'},
{'[dt]([cč])', '%1%1'},
-- the following is ordered before the next one, which applies assimilation
-- of [тд] to щ (including across word boundaries)
{'n[dt]ɕ', 'nɕ'},
-- [сз] and [сз]ь before soft affricates [щч], including across word
-- boundaries; note that the common sequence сч has already been handled
{'[zs]ʹ?([ ‿⁀/]*[ɕč])', 'ɕ%1'},
-- reduction of too many ɕ's, which can happen from the previous
{'ɕɕː', 'ɕː'},
-- assimilation before [тдц] and [тдц]ь before щ
{'[cdt]ʹ?([ ‿⁀/]*)ɕ', 'č%1ɕ'},
-- assimilation of [сз] and [сз]ь before [шж]
{'[zs]([ ‿⁀/]*)š', 'š%1š'},
{'[zs]([ ‿⁀/]*)ž', 'ž%1ž'},
{'[zs]ʹ([ ‿⁀/]*)š', 'ɕ%1š'},
{'[zs]ʹ([ ‿⁀/]*)ž', 'ӂ%1ž'},
{'sverxi', 'sverxy'},
{'stʹd', 'zd'},
{'tʹd', 'dd'},
-- loss of consonants in certain clusters
{'([ns])[dt]g', '%1g'},
{'zdn', 'zn'},
{'lnc', 'nc'},
{'[sz]t([ln])', 's%1'},
-- backing of /i/ after hard consonants in close juncture
{'([mnpbtdkgfvszxɣrlšžcĵĉĝ])⁀‿⁀i', '%1⁀‿⁀y'},
}
local cons_assim_palatal = {
-- assimilation of tn, dn, nč, nɕ is handled specially
compulsory = ut.list_to_set({'stʲ', 'zdʲ', 'ntʲ', 'ndʲ', 'xkʲ',
'csʲ', 'ĵzʲ', 'ncʲ', 'nĵʲ'}),
optional = ut.list_to_set({'slʲ', 'zlʲ', 'snʲ', 'znʲ', 'nsʲ', 'nzʲ',
'mpʲ', 'mbʲ', 'mfʲ', 'fmʲ'})
}
-- words which will be treated as accentless (i.e. their vowels will be
-- reduced), and which will liaise with a preceding or following word;
-- this will not happen if the words have an accent mark, cf.
-- по́ небу vs. по не́бу, etc.
local accentless = {
-- class 'pre': particles that join with a following word
pre = ut.list_to_set({'bez', 'bliz', 'v', 'vo', 'do',
'iz-pod', 'iz-za', 'za', 'iz', 'izo',
'k', 'ko', 'mež', 'na', 'nad', 'nado', 'ob', 'obo', 'ot',
'po', 'pod', 'podo', 'pred', 'predo', 'pri', 'pro', 'pered', 'peredo',
'čerez', 's', 'so', 'u', 'ne'}),
-- class 'prespace': particles that join with a following word, but only
-- if a space (not a hyphen) separates them; hyphens are used here
-- to spell out letters, e.g. а-эн-бэ́ for АНБ (NSA = National Security
-- Agency) or о-а-э́ for ОАЭ (UAE = United Arab Emirates)
prespace = ut.list_to_set({'a', 'o'}),
-- class 'post': particles that join with a preceding word
post = ut.list_to_set({'libo', 'nibudʹ', 'by', 'b', 'že', 'ž',
'ka', 'tka', 'li'}),
-- class 'posthyphen': particles that join with a preceding word, but only
-- if a hyphen (not a space) separates them
posthyphen = ut.list_to_set({'to'}),
}
-- Pronunciation of final unstressed -е, depending on the part of speech and
-- exact ending.
--
-- Endings:
-- oe = -ое
-- ve = any other vowel plus -е (FIXME, may have to split out -ее)
-- je = -ье
-- softpaired = soft paired consonant + -е
-- hardsib = hard sibilant (ц, ш, ж) + -е
-- softsib = soft sibilant (ч, щ) + -е
--
-- Parts of speech:
-- def = default used in absence of pos
-- n/noun = neuter noun in the nominative/accusative singular (but not ending
-- in adjectival -ое or -ее; those should be considered as adjectives)
-- pre = prepositional case singular
-- dat = dative case singular (treated same as prepositional case singular)
-- voc = vocative case (currently treated as 'mid')
-- nnp = noun nominative plural in -е (гра́ждане, боя́ре, армя́не); not
-- adjectival plurals in -ие or -ые, including adjectival nouns
-- (да́нные, а́вторские)
-- inv = invariable noun or other word (currently treated as 'mid')
-- a/adj = adjective or adjectival noun (typically either neuter in -ое or
-- -ее, or plural in -ие, -ые, or -ье, or short neuter in unpaired
-- sibilant + -е)
-- c/com = comparative (typically either in -ее or sibilant + -е)
-- adv = adverb
-- p = preposition (treated same as adverb)
-- v/vb/verb = finite verbal form (usually 2nd-plural in -те); not
-- participle forms, which should be treated as adjectives
-- pro = pronoun (кое-, какие-, ваше, сколькие)
-- num = number (двое, трое, обе, четыре; currently treated as 'mid')
-- pref = prefix (treated as 'high' because integral part of word)
-- hi/high = force high values ([ɪ] or [ɨ])
-- mid = force mid values ([e] or [ɨ])
-- lo/low/schwa = force low, really schwa, values ([ə])
--
-- Possible values:
-- 1. ə [ə], e [e], i [ɪ] after a vowel or soft consonant
-- 2. ə [ə] or y [ɨ] after a hard sibilant
--
-- If a part of speech doesn't have an entry for a given type of ending,
-- it receives the default value. If a part of speech's entry is a string,
-- it's an alias for another way of specifying the same part of speech
-- (e.g. n=noun).
local final_e = {
def={oe='ə', ve='e', je='e', softpaired='e', hardsib='y', softsib='e'},
noun={oe='ə', ve='e', je='e', softpaired='e', hardsib='ə', softsib='e'},
n='noun',
pre={oe='e', ve='e', softpaired='e', hardsib='y', softsib='e'},
dat='pre',
voc='mid',
nnp={softpaired='e'}, -- FIXME, not sure about this
inv='mid', --FIXME, not sure about this (e.g. вице-, кофе)
adj={oe='ə', ve='e', je='ə'}, -- FIXME: Not sure about -ее, e.g. neut adj си́нее; FIXME, not sure about short neuter adj, e.g. похо́же from похо́жий, дорогосто́яще from дорогосто́ящий, should this be treated as neuter noun?
a='adj',
com={ve='e', hardsib='y', softsib='e'},
c='com',
adv={softpaired='e', hardsib='y', softsib='e'},
p='adv', --FIXME, not sure about prepositions
verb={softpaired='e'},
v='verb',
vb='verb',
pro={oe='i', ve='i'}, --FIXME, not sure about ваше, сколькие, какие-, кое-
num='mid', --FIXME, not sure about обе
pref='high',
-- forced values
high={oe='i', ve='i', je='i', softpaired='i', hardsib='y', softsib='i'},
hi='high',
mid={oe='e', ve='e', je='e', softpaired='e', hardsib='y', softsib='e'},
low={oe='ə', ve='ə', je='ə', softpaired='ə', hardsib='ə', softsib='ə'},
lo='low',
schwa='low'
}
local function ine(x)
return x ~= "" and x or nil
end
local function track(page)
local m_debug = require("Module:debug")
m_debug.track("ru-pron/" .. page)
return true
end
-- For use with {{ru-IPA|phon=...}}; remove accents that we don't want
-- to appear in the phonetic respelling
function export.phon_respelling(text)
if type(text) == 'table' then
text = ine(text.args[1])
end
text = rsub(text, '[' .. CFLEX .. DUBGR .. DOTABOVE .. DOTBELOW .. ']', '')
return text
end
function export.ipa(text, adj, gem, bracket, pos)
local new_module_result
-- Test code to compare existing module to new one.
if test_new_ru_pron_module then
local m_new_ru_pron = require("Module:User:Benwing2/ru-pron")
new_module_result = m_new_ru_pron.ipa(text, adj, gem, bracket, pos)
end
if type(text) == 'table' then
text, adj, gem, bracket, pos = (ine(text.args.phon) or ine(text.args[1])), ine(text.args.adj), ine(text.args.gem), ine(text.args.bracket), ine(text.args.pos)
if not text then
text = mw.title.getCurrentTitle().text
end
end
gem = usub(gem or '', 1, 1)
bracket = ine(usub(bracket or '', 1, 1))
if bracket == 'n' then
bracket = nil
end
pos = pos or "def"
-- If a multipart part of speech, split into components, and convert
-- each blank component to the default.
if rfind(pos, "/") then
pos = rsplit(pos, "/")
for i=1,#pos do
if pos[i] == "" then
pos[i] = "def"
end
end
end
-- Verify that pos (or each part of multipart pos) is recognized
for _, p in ipairs(type(pos) == "table" and pos or {pos}) do
if not final_e[pos] then
error("Unrecognized part of speech '" .. pos .. "': Should be n/noun/neut, a/adj, c/com, pre, dat, adv, inv, voc, v/verb, pro, hi/high, mid, lo/low/schwa or omitted")
end
end
text = ulower(text)
if gem ~= '' then
track("gem")
track("gem/" .. gem)
end
if adj then
track("adj")
end
if rfind(text, "[a-zščžáéíóúýàèìòùỳ]") then
track("latin-text")
end
if rfind(text, "[сз]ч") then
track("sch")
end
if rfind(text, "[шж]ч") then
track("shch")
end
if rfind(text, CFLEX) then
track("cflex")
end
if rfind(text, DUBGR) then
track("dubgr")
end
text = rsub(text, "``", DUBGR)
text = rsub(text, "`", GR)
text = rsub(text, "@", DOTABOVE)
text = rsub(text, "%^", CFLEX)
text = rsub(text, DUBGR, CFLEX)
-- translit doesn't always convert э to ɛ (depends on whether a consonant
-- precedes), so do it ourselves before translit
text = rsub(text, 'э', 'ɛ')
-- vowel + йе should have double jj, but the translit module will translit
-- it the same as vowel + е, so do it ourselves before translit
text = rsub(text, '([' .. com.vowel .. ']' .. com.opt_accent .. ')й([еѐ])',
'%1йй%2')
-- transliterate and decompose Latin vowels with accents, recomposing
-- certain key combinations
text = com.translit(text)
-- handle old ě (e.g. сѣдло́), and ě̈ from сѣ̈дла
text = rsub(text, 'ě̈', 'jo' .. AC)
text = rsub(text, 'ě', 'e')
-- handle sequences of accents (esp from ё with secondary/tertiary stress)
text = rsub(text, accents .. '+(' .. accents .. ')', '%1')
-- canonicalize multiple spaces
text = rsub(text, '%s+', ' ')
-- Add primary stress to single-syllable words preceded or followed by
-- unstressed particle or preposition. Add "tertiary" stress to remaining
-- single-syllable words that aren't a particle, preposition, prefix or
-- suffix and don't already bear an accent (including force-reduction
-- accents, i.e. dot-above/dot-below); "tertiary stress" means a vowel is
-- treated as stressed for the purposes of vowel reduction but isn't
-- marked with a primary or secondary stress marker; we repurpose a
-- circumflex for this purpose. We need to preserve the distinction
-- between spaces and hyphens because (1) we only recognize certain
-- post-accentless particles following a hyphen (to distinguish e.g.
-- 'то' from '-то'); (2) we only recognize certain pre-accentless
-- particles preceding a space (to distinguish particles 'о' and 'а' from
-- spelled letters о and а, which should not be reduced); and (3) we
-- recognize hyphens for the purpose of marking unstressed prefixes and
-- suffixes.
local word = strutils.capturing_split(text, "([ %-]+)")
for i = 1, #word do
-- check for single-syllable words that need a stress; they must meet
-- the following conditions:
-- 1. must not be an accentless word, which is any of the following:
-- 1a. in the "pre" class, or
if not (accentless['pre'][word[i]] or
-- 1b. in the "prespace" class if followed by space and another word, or
i < #word - 1 and accentless['prespace'][word[i]] and word[i+1] == " " or
-- 1c. in the "post" class if preceded by another word, or
i > 2 and accentless['post'][word[i]] or
-- 1d. in the "posthyphen" class preceded by a hyphen and another word;
i > 2 and accentless['posthyphen'][word[i]] and word[i-1] == "-") and
-- 2. must be one syllable;
ulen(rsub(word[i], '[^' .. vow .. ']', '')) == 1 and
-- 3. must not have any accents (including dot-above, forcing reduction);
not rfind(word[i], accents) and
-- 4. must not be a prefix or suffix, identified by a preceding or trailing hyphen, i.e. one of the following:
-- 4a. utterance-initial preceded by a hyphen, or
not (i == 3 and word[2] == "-" and word[1] == "" or
-- 4b. non-utterance-initial preceded by a hyphen, or
i >= 3 and word[i-1] == " -" or
-- 4c. utterance-final followed by a hyphen, or
i == #word - 2 and word[i+1] == "-" and word[i+2] == "" or
-- 4d. non-utterance-final followed by a hyphen;
i <= #word - 2 and word[i+1] == "- ") then
-- OK, we have a stressable single-syllable word; either add primary
-- or tertiary stress:
-- 1. add primary stress if preceded or followed by an accentless word,
if (i > 2 and accentless['pre'][word[i-2]] or
i > 2 and word[i-1] == " " and accentless['prespace'][word[i-2]] or
i < #word - 1 and accentless['post'][word[i+2]] or
i < #word - 1 and word[i+1] == "-" and accentless['posthyphen'][word[i+2]]) then
word[i] = rsub(word[i], vowels_c, '%1' .. AC)
-- 2. else add tertiary stress
else
word[i] = rsub(word[i], vowels_c, '%1' .. CFLEX)
end
end
end
-- make unaccented prepositions and particles liaise with the following or
-- preceding word
for i = 1, #word do
if i < #word - 1 and (accentless['pre'][word[i]] or accentless['prespace'][word[i]] and word[i+1] == " ") then
word[i+1] = '‿'
elseif i > 2 and (accentless['post'][word[i]] or accentless['posthyphen'][word[i]] and word[i-1] == "-") then
word[i-1] = '‿'
end
end
-- rejoin words, convert hyphens to spaces and eliminate stray spaces
-- resulting from this
text = table.concat(word, "")
text = rsub(text, '[%-%s]+', ' ')
text = rsub(text, '^ ', '')
text = rsub(text, ' $', '')
-- convert commas and en/en dashes to IPA foot boundaries
text = rsub(text, '%s*[,–—]%s*', ' | ')
-- add a ⁀ at the beginning and end of every word and at close juncture
-- boundaries; we will remove this later but it makes it easier to do
-- word-beginning and word-end rsubs
text = rsub(text, ' ', '⁀ ⁀')
text = '⁀' .. text .. '⁀'
text = rsub(text, '‿', '⁀‿⁀')
-- save original word spelling before respellings, (de)voicing changes,
-- geminate changes, etc. for implementation of geminate_pref
local orig_word = rsplit(text, " ", true)
-- insert or remove /j/ before [aou] so that palatal versions of these
-- vowels are always preceded by /j/ and non-palatal versions never are
-- (do this before the change below adding tertiary stress to final
-- palatal о):
-- (1) Non-palatal [ou] after always-hard шж (e.g. in брошю́ра, жю́ри)
-- despite the spelling (FIXME, should this also affect [a]?)
text = rsub(text, '([šž])j([ou])', '%2%3')
-- (2) Palatal [aou] after always-soft щчӂ and voiced variant ǰ (NOTE:
-- this happens before the change šč -> ɕː in phon_respellings)
text = rsub(text, '([čǰӂ])([aou])', '%1j%2')
-- (3) ьо is pronounced as ьйо, i.e. like (possibly unstressed) ьё, e.g.
-- in Асунсьо́н
text = rsub(text, 'ʹo', 'ʹjo')
-- add tertiary stress to some final -о (this needs to be done before
-- eliminating dot-above, after adding ⁀, after adding /j/ before palatal о):
-- (1) after vowels, e.g. То́кио
text = rsub(text, '(' .. vowels .. accents .. '?o)⁀', '%1' .. CFLEX .. '⁀')
-- (2) when palatal, e.g. ра́нчо, га́учо, ма́чо, Ога́йо
text = rsub(text, 'jo⁀', 'jo' .. CFLEX .. '⁀')
-- eliminate dot-above, which has served its purpose of preventing any
-- sort of stress
text = rsub(text, DOTABOVE, '')
-- eliminate dot-below
text = rsub(text, 'ja' .. DOTBELOW, 'jạ')
if rfind(text, DOTBELOW) then
error("Dot-below accent can only be placed on я or palatal а")
end
text = adj and rsub(text, '(.[aoe]́?)go(' .. AC .. '?)⁀', '%1vo%2⁀') or text
text = adj and rsub(text, '(.[aoe]́?)go(' .. AC .. '?)⁀', '%1vo%2sja⁀') or text
--phonetic respellings
for _, respell in ipairs(phon_respellings) do
text = rsub(text, respell[1], respell[2])
end
--voicing, devoicing
--NOTE: v before an obstruent assimilates in voicing and triggers voicing
--assimilation of a preceding consonant; neither happens before a sonorant
--1. absolutely final devoicing
text = rsub(text, '([bdgvɣzžĝĵǰӂ])(ʹ?⁀)$', function(a, b)
return devoicing[a] .. b end)
--2. word-final devoicing before another word
text = rsub(text, '([bdgvɣzžĝĵǰӂ])(ʹ?⁀ ⁀[^bdgɣzžĝĵǰӂ])', function(a, b)
return devoicing[a] .. b end)
--3. voicing/devoicing assimilation; repeat to handle recursive assimilation
while true do
local new_text = rsub(text, '([bdgvɣzžĝĵǰӂ])([ ‿⁀ʹː()/]*[ptkfxsščɕcĉ])', function(a, b)
return devoicing[a] .. b end)
new_text = rsub(new_text, '([ptkfxsščɕcĉ])([ ‿⁀ʹː()/]*v?[ ‿⁀ʹː()/]*[bdgɣzžĝĵǰӂ])', function(a, b)
return voicing[a] .. b end)
if new_text == text then
break
end
text = new_text
end
--re-notate orthographic geminate consonants
text = rsub(text, '([^' .. vow .. '.%-_])' .. '%1', '%1ː')
text = rsub(text, '([^' .. vow .. '.%-_])' .. '%(%1%)', '%1(ː)')
--rewrite iotated vowels
text = rsub(text, '(j[%(ː%)]*)([aeou])', function(a, b)
return a .. iotating[b] end)
-- eliminate j after consonant and before iotated vowel (including
-- semi-reduced ạ)
text = rsub(text, '([^' .. vow .. acc .. 'ʹʺ‿⁀ ]/?)j([äạëöü])', '%1%2')
--split by word and process each word
word = rsplit(text, " ", true)
if type(pos) == "table" and #pos ~= #word then
error("Number of parts of speech (" .. #pos .. ") should match number of combined words (" .. #word .. ")")
end
for i = 1, #word do
local pron = word[i]
-- Check for gemination at prefix boundaries; if so, convert the
-- regular gemination symbol ː to a special symbol ˑ that indicates
-- we always preserve the gemination unless gem=n. We look for
-- certain sequences at the beginning of a word, but make sure that
-- the original spelling is appropriate as well (see comment above
-- for geminate_pref).
if rfind(pron, 'ː') then
local orig_pron = orig_word[i]
local deac = rsub(pron, accents, '')
local orig_deac = rsub(orig_pron, accents, '')
for _, gempref in ipairs(geminate_pref) do
local newspell = gempref[1]
local oldspell = gempref[2]
-- FIXME! The rsub below will be incorrect if there is
-- gemination in a joined preposition or particle
if rfind(orig_deac, '⁀' .. oldspell) and rfind(deac, '⁀' .. newspell) or
rfind(orig_deac, '⁀ne' .. oldspell) and rfind(deac, '⁀ne' .. newspell) then
pron = rsub(pron, '(⁀[^‿⁀ː]*)ː', '%1ˑ')
end
end
end
--degemination, optional gemination
if gem == 'y' then
-- leave geminates alone, convert ˑ to regular gemination; ˑ is a
-- special gemination symbol used at prefix boundaries that we
-- remove only when gem=n, else we convert it to regular gemination
pron = rsub(pron, 'ˑ', 'ː')
elseif gem == 'o' then
-- make geminates optional, except for ɕӂ, also ignore left paren
-- in (ː) sequence
pron = rsub(pron, '([^ɕӂ%(%)])[ːˑ]', '%1(ː)')
elseif gem == 'n' then
-- remove gemination, except for ɕӂ
pron = rsub(pron, '([^ɕӂ%(%)])[ːˑ]', '%1')
else
-- degeminate l's
pron = rsub(pron, '(l)ː', '%1')
-- preserve gemination between vowels immediately after the stress,
-- special gemination symbol ˑ also remains, ɕӂ remain geminated,
-- žn remain geminated between vowels even not immediately after
-- the stress, n becomes optionally geminated when after but not
-- immediately after the stress, ssk and zsk remain geminated
-- immediately after the stress, else degeminate; we signal that
-- gemination should remain by converting to special symbol ˑ,
-- then removing remaining ː not after ɕӂ and left paren; do
-- various subs repeatedly in case of multiple geminations in a word
-- 1. immediately after the stress
pron = rsub_repeatedly(pron, '(' .. vowels .. accents .. '[^ɕӂ%(%)])ː(' .. vowels .. ')', '%1ˑ%2')
-- 2. remaining geminate n after the stress between vowels
pron = rsub_repeatedly(pron, '(' .. AC .. '.-' .. vowels .. accents .. '?n)ː(' .. vowels .. ')', '%1(ː)%2')
-- 3. remaining ž and n between vowels
pron = rsub_repeatedly(pron, '(' .. vowels .. accents .. '?[žn])ː(' .. vowels .. ')', '%1ˑ%2')
-- 4. ssk (and zsk, already normalized) immediately after the stress
pron = rsub(pron, '(' .. vowels .. accents .. '[^' .. vow .. ']*s)ː(k)', '%1ˑ%2')
-- 5. eliminate remaining gemination
pron = rsub(pron, '([^ɕӂ%(%)])ː', '%1')
-- 6. convert special gemination symbol ˑ to regular gemination
pron = rsub(pron, 'ˑ', 'ː')
end
-- handle soft and hard signs, assimilative palatalization
-- 1. insert j before i when required
pron = rsub(pron, 'ʹi', 'ʹji')
-- 2. insert glottal stop after hard sign if required
pron = rsub(pron, 'ʺ([aɛiouy])', 'ʔ%1')
-- 3. assimilative palatalization of consonants when followed by
-- front vowels or soft sign
pron = rsub(pron, '([mnpbtdkgfvszxɣrl])([ː()]*[eiäạëöüʹ])', '%1ʲ%2')
pron = rsub(pron, '([cĵ])([ː()]*[äạöüʹ])', '%1ʲ%2')
-- 4. remove hard and soft signs
pron = rsub(pron, "[ʹʺ]", "")
-- reduction of unstressed word-final -я, -е; but special-case
-- unstressed не, же. Final -я always becomes [ə]; final -е may
-- become [ə], [e], [ɪ] or [ɨ] depending on the part of speech and
-- the preceding consonants/vowels.
pron = rsub(pron, '[äạ]⁀', 'ə⁀')
pron = rsub(pron, '⁀nʲe⁀', '⁀nʲi⁀')
pron = rsub(pron, '⁀že⁀', '⁀žy⁀')
-- function to fetch the appropriate value for ending and part of
-- speech, handling aliases and defaults and converting 'e' to 'ê'
-- so that the unstressed [e] sound is preserved
function fetch_e_sub(ending)
local thispos = type(pos) == "table" and pos[i] or pos
local chart = final_e[thispos]
while type(chart) == "string" do -- handle aliases
chart = final_e[chart]
end
assert(type(chart) == "table")
local sub = chart[ending] or final_e['def'][ending]
assert(sub)
if sub == 'e' then
-- add CFLEX to preserve the unstressed [e] sound, which
-- will otherwise be converted to [ɪ]; NOTE: DO NOT use ê
-- here directly because it's a single composed char, when
-- we need the e and accent to be separate
return 'e' .. CFLEX
else
return sub
end
end
if new_final_e_code then
-- handle substitutions in two parts, one for vowel+j+e sequences
-- and the other for cons+e sequences
pron = rsub(pron, vowels_c .. '(' .. accents .. '?j)ë⁀', function(v, ac)
local ty = v == 'o' and 'oe' or 've'
return v .. ac .. fetch_e_sub(ty)
end)
-- consonant may palatalized, geminated or optional-geminated
pron = rsub(pron, '(.)(ʲ?[ː()]*)[eë]⁀', function(ch, mod)
local ty = ch == 'j' and 'je' or
rfind(ch, '[cĵšžĉĝ]') and 'hardsib' or
rfind(ch, '[čǰɕӂ]') and 'softsib' or
'softpaired'
return ch ..mod .. fetch_e_sub(ty)
end)
else
-- Do the old way, which mostly converts final -е to schwa, but
-- has highly broken retraction code for vowel + [шжц] + е (but
-- not with accent on vowel!) before it that causes final -е in
-- this circumstance to become [ɨ], and a special hack for кое-.
pron = rsub(pron, vowels_c .. '([cĵšžĉĝ][ː()]*)[eë]', '%1%2ɛ')
pron = rsub(pron, '⁀ko(' .. accents .. ')jë⁀', '⁀ko%1ji⁀')
pron = rsub(pron, '[eë]⁀', 'ə⁀')
end
-- retraction of е and и after цшж
pron = rsub(pron, '([cĵšžĉĝ][ː()]*)([ei])', function(a, b)
return a .. retracting[b] end)
--syllabify, inserting @ at syllable boundaries
--1. insert @ after each vowel
pron = rsub(pron, '(' .. vowels .. accents .. '?)', '%1@')
--2. eliminate word-final @
pron = rsub(pron, '@+⁀$', '⁀')
--3. move @ forward directly before any ‿⁀, as long as at least
-- one consonant follows that; we will move it across ‿⁀ later
pron = rsub(pron, '@([^@' .. vow .. acc .. ']*)([‿⁀]+[^‿⁀@' .. vow .. acc .. '])', '%1@%2')
--4. in a consonant cluster, move @ forward so it's before the
-- last consonant
pron = rsub(pron, '@([^‿⁀@' .. vow .. acc .. ']*)([^‿⁀@' .. vow .. acc .. 'ːˑ()ʲ]ʲ?[ːˑ()]*‿?[' .. vow .. acc .. '])', '%1@%2')
--5. move @ backward if in the middle of a "permanent onset" cluster,
-- e.g. sk, str, that comes before a vowel, putting the @ before
-- the permanent onset cluster
pron = rsub(pron, '([^‿⁀@' .. vow .. acc .. ']?)([^‿⁀@' .. vow .. acc .. '])@([^‿⁀@' .. vow .. acc .. 'ːˑ()ʲ])(ʲ?[ːˑ()]*[‿⁀]*[' .. vow .. acc .. '])', function(a, b, c, d)
if perm_syl_onset[a .. b .. c] or c == 'j' and rfind(b, '[čǰɕӂʲ]') then
return '@' .. a .. b .. c .. d
elseif perm_syl_onset[b .. c] then
return a .. '@' .. b .. c .. d
end end)
--6. if / is present (explicit syllable boundary), remove any @
-- (automatic boundary) and convert / to @
if rfind(pron, '/') then
pron = rsub(pron, '[^' .. vow .. acc .. ']+', function(x)
if rfind(x, '/') then
x = rsub(x, '@', '')
x = rsub(x, '/', '@')
end
return x
end)
end
--7. remove @ followed by a final consonant cluster
pron = rsub(pron, '@([^‿⁀@' .. vow .. ']+⁀)$', '%1')
--8. remove @ preceded by an initial consonant cluster (should only
-- happen when / is inserted by user or in цз, чж sequences)
pron = rsub(pron, '^(⁀[^‿⁀@' .. vow .. ']+)@', '%1')
--9. make sure @ isn't directly before linking ‿⁀
pron = rsub(pron, '@([‿⁀]+)', '%1@')
-- handle word-initial unstressed o and a; note, vowels always
-- followed by at least one char because of word-final ⁀
-- do after syllabification because syllabification doesn't know
-- about ɐ as a vowel
pron = rsub(pron, '^⁀[ao]([^' .. acc .. '])', '⁀ɐ%1')
--split by syllable
local syllable = rsplit(pron, '@', true)
--create set of 1-based syllable indexes of stressed syllables
--(acute, grave, circumflex)
local stress = {}
for j = 1, #syllable do
if rfind(syllable[j], accents) then
stress[j] = true
end
end
-- iterate syllable by syllable to handle stress marks, vowel allophony
local syl_conv = {}
for j = 1, #syllable do
local syl = syllable[j]
local alnum
--vowel allophony
if stress[j] then
-- convert acute/grave/circumflex accent to appropriate
-- IPA marker of primary/secondary/unmarked stress
alnum = 1
syl = rsub(syl, '(.*)́', 'ˈ%1')
syl = rsub(syl, '(.*)̀', 'ˌ%1')
syl = rsub(syl, CFLEX, '')
elseif stress[j+1] then
alnum = 2
else
alnum = 3
end
syl = rsub(syl, vowels_c, function(a)
if a ~= '' then
return allophones[a][alnum]
end end)
syl_conv[j] = syl
end
pron = table.concat(syl_conv, "")
-- Optional (j) before ɪ, which is always unstressed
pron = rsub(pron, "⁀jɪ", "⁀(j)ɪ")
pron = rsub(pron, '([' .. ipa_vow .. '])jɪ', "%1(j)ɪ")
--consonant assimilative palatalization of tn/dn, depending on
--whether [rl] precedes
pron = rsub(pron, '([rl]?)([ˈˌ]?[dt])([ˈˌ]?nʲ)', function(a, b, c)
if a == '' then
return a .. b .. 'ʲ' .. c
else
return a .. b .. '⁽ʲ⁾' .. c
end end)
--general consonant assimilative palatalization
pron = rsub_repeatedly(pron, '([szntdpbmfcĵx])([ˈˌ]?)([szntdpbmfcĵlk]ʲ)', function(a, b, c)
if cons_assim_palatal['compulsory'][a..c] then
return a .. 'ʲ' .. b .. c
elseif cons_assim_palatal['optional'][a..c] then
return a .. '⁽ʲ⁾' .. b .. c
else
return a .. b .. c
end end)
-- further assimilation before alveolopalatals
pron = rsub(pron, 'n([ˈˌ]?)([čǰɕӂ])', 'nʲ%1%2')
-- optional palatal assimilation of вп, вб only word-initially
pron = rsub(pron, '⁀([ˈˌ]?[fv])([ˈˌ]?[pb]ʲ)', '⁀%1⁽ʲ⁾%2')
-- optional palatal assimilation of бв but not in обв-
pron = rsub(pron, 'b([ˈˌ]?vʲ)', 'b⁽ʲ⁾%1')
if rfind(word[i], '⁀o' .. accents .. '?bv') then
-- ə in case of a word with a preceding preposition
pron = rsub(pron, '⁀([ˈˌ]?[ɐəo][ˈˌ]?)b⁽ʲ⁾([ˈˌ]?vʲ)', '⁀%1b%2')
end
if rfind(word[i], 's[äạ]⁀') then
pron = rsub(pron, 'sʲə⁀', 's⁽ʲ⁾ə⁀')
end
word[i] = pron
end
text = table.concat(word, " ")
if bracket then
text = '[' .. text .. ']'
end
-- Front a and u between soft consonants. If between a soft and
-- optionally soft consonant (should only occur in that order, shouldn't
-- ever have a or u preceded by optionally soft consonant),
-- split the result into two. We only split into two even if there
-- happen to be multiple optionally fronted a's and u's to avoid
-- excessive numbers of possibilities (and it simplifies the code).
-- 1. First, temporarily add soft symbol to inherently soft consonants.
text = rsub(text, '([čǰɕӂj])', '%1ʲ')
-- 2. Handle case of [au] between two soft consonants
text = rsub(text, '(ʲ[ː()]*)([auʊ])([ˈˌ]?.ʲ)', function(a, b, c)
return a .. fronting[b] .. c end)
-- 3. Handle [au] between soft consonant and optional j, which is still fronted
text = rsub(text, '(ʲ[ː()]*)([auʊ])([ˈˌ]?%(jʲ%))', function(a, b, c)
return a .. fronting[b] .. c end)
-- 4. Handle case of [au] between soft and optionally soft consonant
if rfind(text, 'ʲ[ː()]*[auʊ][ˈˌ]?.⁽ʲ⁾') then
local opt_hard = rsub(text, '(ʲ[ː()]*)([auʊ])([ˈˌ]?.)⁽ʲ⁾', '%1%2%3')
local opt_soft = rsub(text, '(ʲ[ː()]*)([auʊ])([ˈˌ]?.)⁽ʲ⁾', function(a, b, c)
return a .. fronting[b] .. c .. 'ʲ' end)
text = opt_hard .. ', ' .. opt_soft
end
-- 5. Undo addition of soft symbol to inherently soft consonants.
text = rsub(text, '([čǰɕӂj])ʲ', '%1')
-- convert special symbols to IPA
text = rsub(text, '[cĵ]ʲ', translit_conv_j)
text = rsub(text, '[cčgĉĝĵǰšžɕӂ]', translit_conv)
-- Assimilation involving hiatus of ɐ and ə
text = rsub(text, 'ə([‿⁀]*)[ɐə]', 'ɐ%1ɐ')
-- eliminate ⁀ symbol at word boundaries
-- eliminate _ symbol that prevents assimilations
text = rsub(text, '[⁀_]', '')
text = rsub(text, 'ʐ(ː?)ɛ([^ˈˌ]*)([ˈˌ])', 'ʐ%1ɨ%2%3')
text = rsub(text, 'ʂ(ː?)ɛ([^ˈˌ]*)([ˈˌ])', 'ʂ%1ɨ%2%3')
text = rsub(text, 't͡s(ː?)ɛ([^ˈˌ]*)([ˈˌ])', 't͡s%1ɨ%2%3')
text = rsub(text, 't͡sɛ$', 't͡sə')
if test_new_ru_pron_module then
if new_module_result ~= text then
--error(text .. " || " .. new_module_result)
track("different-pron")
end
end
return text
end
return export
-- For Vim, so we get 4-space tabs
-- vim: set ts=4 sw=4 noet: