Linguifex

Module:languages/data/3/p: Difference between revisions

← Older edit
m 1 revision imported
m 1 revision imported
 
(One intermediate revision by one other user not shown)
Line 53: Line 53:
"phi",
"phi",
"Latn, Tglg",
"Latn, Tglg",
entry_name = {
strip_diacritics = {
Latn = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer},
Latn = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer},
},
},
Line 87: Line 87:
Phli = "Phli-translit",
Phli = "Phli-translit",
["pal-Avst"] = "Avst-translit",
["pal-Avst"] = "Avst-translit",
Mani = "Mani-translit",
-- Mani translit in [[Module:scripts/data]]
},
},
ancestors = "peo",
ancestors = "peo",
Line 97: Line 97:
"phi",
"phi",
"Latn, Kulit",
"Latn, Kulit",
entry_name = {
strip_diacritics = {
Latn = {remove_diacritics = c.grave .. c.acute .. c.circ}
Latn = {remove_diacritics = c.grave .. c.acute .. c.circ}
},
},
standardChars = {
standard_chars = {
Latn = "AaBbDdEeGgHhIiKkLlMmNnOoPpRrSsTtUuWwYy",
Latn = "AaBbDdEeGgHhIiKkLlMmNnOoPpRrSsTtUuWwYy",
c.punc
c.punc
Line 141: Line 141:
"Papasena",
"Papasena",
7132508,
7132508,
"paa-lkp",
"paa-clp",
"Latn",
"Latn",
}
}
Line 167: Line 167:
"cdd",
"cdd",
"Latn",
"Latn",
entry_name = {remove_diacritics = c.acute},
strip_diacritics = {remove_diacritics = c.acute},
}
}


Line 297: Line 297:


m["pby"] = {
m["pby"] = {
"Pyu",
"Pyu (New Guinea)",
2567925,
2567925,
"paa-asa",
"qfa-dis", -- Papuan; isolate per Glottolog, in a putative Arai-Samaia family in Usher (2020)
"Latn",
"Latn",
}
}
Line 391: Line 391:
"Latn",
"Latn",
ancestors = "en",
ancestors = "en",
entry_name = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.caron .. c.macronbelow},
strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.caron .. c.macronbelow},
sort_key = {
sort_key = {
remove_diacritics = c.tilde,
remove_diacritics = c.tilde,
Line 423: Line 423:
"Anam",
"Anam",
3501930,
3501930,
"ngf-mad",
"ngf-pom",
"Latn",
"Latn",
}
}
Line 489: Line 489:
"Mala (New Guinea)",
"Mala (New Guinea)",
11732569,
11732569,
"ngf-mad",
"ngf-kau",
"Latn",
"Latn",
}
}
Line 568: Line 568:
"Kunja",
"Kunja",
6444807,
6444807,
nil,
"paa-ton",
"Latn",
"Latn",
}
}
Line 579: Line 579:
}
}


-- "pes" IS TREATED AS "fa" (or as etymology-only), SEE WT:LT
-- "pes" is treated as "fa" (or as etymology-only), see [[WT:LT]]


m["pev"] = {
m["pev"] = {
Line 652: Line 652:
"Pagi",
"Pagi",
7124354,
7124354,
"paa-brd",
"paa-bew",
"Latn",
"Latn",
}
}
Line 667: Line 667:
3320030,
3320030,
"cel-gae",
"cel-gae",
"Ogam",
"Ogam, Latn",
translit = "pgl-translit",
translit = "pgl-translit",
}
}
Line 676: Line 676:
"itc-sbl",
"itc-sbl",
"Ital, Latn",
"Ital, Latn",
translit = {
-- Ital translit in [[Module:scripts/data]]
Ital = "Ital-translit",
},
display_text = {
display_text = {
Latn = s["itc-Latn-displaytext"]
Latn = s["itc-Latn-displaytext"]
},
},
entry_name = {
strip_diacritics = {
Latn = s["itc-Latn-entryname"]
Latn = s["itc-Latn-stripdiacritics"]
},
},
sort_key = {
sort_key = {
Line 700: Line 698:
"Pagu",
"Pagu",
7124462,
7124462,
"paa-nha",
"paa-gto",
"Latn",
"Latn",
}
}
Line 739: Line 737:
"Mymr",
"Mymr",
translit = "aio-phk-translit",
translit = "aio-phk-translit",
entry_name = {remove_diacritics = c.VS01},
display_text = s["phk-displaytext"],
strip_diacritics = s["phk-stripdiacritics"],
}
}


m["phl"] = {
m["phl"] = {
"Phalura",
"Palula",
2449549,
2449549,
"inc-shn",
"inc-dng",
"Latn, ur-Arab",
"Latn, ur-Arab",
entry_name = {
strip_diacritics = {
-- character "ۂ" code U+06C2 to "ه" and "هٔ"‎ (U+0647 + U+0654) to "ه"; hamzatu l-waṣli to a regular alif
-- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه"; hamzatu l-waṣli to a regular alif
from = {"هٔ", "ۂ", "ٱ"},
from = {"هٔ", "ۂ", "ٱ"},
to = {"ہ", "ہ", "ا"},
to = {"ہ", "ہ", "ا"},
Line 767: Line 766:
"sem-can",
"sem-can",
"Phnx",
"Phnx",
translit = "Phnx-translit",
-- Phnx translit in [[Module:scripts/data]]
}
}


Line 787: Line 786:
"inc-pan",
"inc-pan",
"pa-Arab, Guru",
"pa-Arab, Guru",
ancestors = "lah",
translit = {
translit = {
Guru = "Guru-translit",
Guru = "Guru-translit",
["pa-Arab"] = "pa-Arab-translit",
["pa-Arab"] = "pa-Arab-translit",
},
},
entry_name = {
strip_diacritics = {
["pa-Arab"] = {
["pa-Arab"] = {
remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna,
remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna,
Line 805: Line 803:
3626597,
3626597,
"tai-swe",
"tai-swe",
"Thai",
}
}


Line 827: Line 826:
"Pima Bajo",
"Pima Bajo",
3388544,
3388544,
"azc",
"azc-pim",
"Latn",
"Latn",
}
}
Line 907: Line 906:
"Piame",
"Piame",
7190042,
7190042,
"paa-sep",
"Latn",
}
}


Line 1,021: Line 1,022:
954916,
954916,
"aus-pmn",
"aus-pmn",
"Latn",
}
}


Line 1,041: Line 1,043:
16835180,
16835180,
"dra-imd",
"dra-imd",
"Mlym",
-- Mlym translit in [[Module:scripts/data]] (NOTE: not present before, presumably an accidental omission)
}
}


Line 1,058: Line 1,062:
"Paku",
"Paku",
2932604,
2932604,
"poz-bre",
"Latn",
}
}


Line 1,063: Line 1,069:
"Miani",
"Miani",
12952844,
12952844,
nil,
"ngf-kau",
"Latn",
"Latn",
}
}
Line 1,110: Line 1,116:
12953882,
12953882,
"inc-shn",
"inc-shn",
"ur-Arab",
"ur-Arab, Latn",
}
}


Line 1,143: Line 1,149:


m["plr"] = {
m["plr"] = {
"Palaka Senoufo",
"Palaka",
36346,
36346,
"alv-snf",
"alv-snf",
Line 1,250: Line 1,256:
"crp",
"crp",
"Latn",
"Latn",
ancestors = "lij, pro, vec",
ancestors = "lij-old, pro, vec-old",
}
}


Line 1,281: Line 1,287:


m["pmr"] = {
m["pmr"] = {
"Paynamar",
"Manat",
3450824,
3450824,
"ngf-sog",
"Latn",
}
}


Line 1,289: Line 1,297:
15085,
15085,
"roa-git",
"roa-git",
ancestors = "pms-old",
"Latn",
"Latn",
}
}
Line 1,307: Line 1,316:
"Plains Miwok",
"Plains Miwok",
3391031,
3391031,
"nai-you",
"nai-utn",
"Latn",
"Latn",
}
}
Line 1,335: Line 1,344:
"Punan Bah-Biau",
"Punan Bah-Biau",
4842201,
4842201,
"poz-bnn",
"Latn",
}
}


Line 1,372: Line 1,383:
4778608,
4778608,
"poz",
"poz",
"Latn",
}
}


Line 1,401: Line 1,413:
"Pinai-Hagahai",
"Pinai-Hagahai",
5638511,
5638511,
"paa-pia",
"Latn",
}
}


Line 1,425: Line 1,439:
"Panim",
"Panim",
11732562,
11732562,
"ngf-mad",
"ngf-gum",
"Latn",
}
}


Line 1,432: Line 1,447:
7227956,
7227956,
"phi",
"phi",
"Latn",
}
}


Line 1,443: Line 1,459:
Grek = "el-translit"
Grek = "el-translit"
},
},
display_text = {
-- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
Grek = s["Grek-displaytext"]
},
entry_name = {
Grek = s["Grek-entryname"]
},
sort_key = {
Grek = s["Grek-sortkey"]
},
}
}


Line 1,648: Line 1,656:
"azc-nah",
"azc-nah",
"Latn",
"Latn",
entry_name = {remove_diacritics = c.acute .. c.macron},
strip_diacritics = {remove_diacritics = c.acute .. c.macron},
}
}


Line 1,668: Line 1,676:
"Folopa",
"Folopa",
5464843,
5464843,
"paa",
"paa-teb",
"Latn",
"Latn",
}
}
Line 1,675: Line 1,683:
"Pei",
"Pei",
7160903,
7160903,
"paa-wal",
"Latn",
}
}


Line 1,687: Line 1,697:
"Pa",
"Pa",
3504757,
3504757,
"ngf",
"paa-kae",
"Latn",
"Latn",
}
}
Line 1,718: Line 1,728:
ancestors = "inc-ash",
ancestors = "inc-ash",
translit = {
translit = {
Brah = "Brah-translit",
-- Brah translit in [[Module:scripts/data]]
Deva = "pra-Deva-translit",
Deva = "pra-Deva-translit",
Gujr = "sa-Gujr-translit",
Gujr = "sa-Gujr-translit",
Knda = "pra-Knda-translit",
Knda = "pra-Knda-translit",
},
},
entry_name = {
strip_diacritics = {
-- FIXME: separate by script
from = {"ऎ", "ऒ", u(0x0946), u(0x094A), "य़", "ಯ಼", u(0x11071), u(0x11072), u(0x11073), u(0x11074)},
from = {"ऎ", "ऒ", u(0x0946), u(0x094A), "य़", "ಯ಼", u(0x11071), u(0x11072), u(0x11073), u(0x11074)},
to = {"ए", "ओ", u(0x0947), u(0x094B), "य", "ಯ", "𑀏", "𑀑", u(0x11042), u(0x11044)}
to = {"ए", "ओ", u(0x0947), u(0x094B), "य", "ಯ", "𑀏", "𑀑", u(0x11042), u(0x11044)}
Line 1,733: Line 1,744:
2640637,
2640637,
"ira-orp",
"ira-orp",
"Arab",
}
}


-- "prd" IS NOT INCLUDED, SEE WT:LT
-- "prd" is not included, see [[WT:LT]]


m["pre"] = {
m["pre"] = {
Line 1,762: Line 1,774:
6583710,
6583710,
"phi",
"phi",
"Latn",
}
}


Line 1,775: Line 1,788:
3363719,
3363719,
"mkh-pal",
"mkh-pal",
"Latn",
}
}


Line 1,786: Line 1,800:
"Kibiri",
"Kibiri",
56745,
56745,
"paa",
"qfa-iso", -- Papuan; isolate in Glottolog and Wurm; suggested grouping with Kiwaian languages by Ross based only on 1sg and 2sg pronouns
"Latn",
}
}


Line 1,803: Line 1,818:
}
}


-- "prp" IS NOT INCLUDED, SEE WT:LT
-- "prp" is not included, see [[WT:LT]]


m["prq"] = {
m["prq"] = {
"Ashéninka Perené",
"Perené Ashéninka",
3450601,
3450601,
"awd",
"awd",
Line 1,817: Line 1,832:
}
}


-- "prs" IS TREATED AS "fa" (or as etymology-only), SEE WT:LT
-- "prs" is treated as "fa" (or as etymology-only), see [[WT:LT]]


m["prt"] = {
m["prt"] = {
Line 1,829: Line 1,844:
7260800,
7260800,
"ngf-sbh",
"ngf-sbh",
"Latn",
}
}


Line 1,834: Line 1,850:
"Parawen",
"Parawen",
7136291,
7136291,
"ngf-mad",
"ngf-num",
"Latn",
}
}


Line 1,852: Line 1,869:
"Asue Awyu",
"Asue Awyu",
11266334,
11266334,
"ngf-awy",
"Latn",
}
}


Line 1,867: Line 1,886:


m["pse"] = {
m["pse"] = {
"Central Malay",
"Central Malay", -- This does not mean the central of Malaysia. It is spoken in Indonesia.
3367751,
3367751,
"poz-mly",
"poz-mly",
Line 1,927: Line 1,946:
"Pasi",
"Pasi",
7142091,
7142091,
"paa-sep",
"Latn",
}
}


Line 1,970: Line 1,991:
10632026,
10632026,
"aus-pam",
"aus-pam",
"Latn",
}
}


Line 2,009: Line 2,031:
"Enrekang",
"Enrekang",
12953520,
12953520,
nil,
"Latn",
}
}


Line 2,015: Line 2,039:
4853321,
4853321,
"poz-ssw",
"poz-ssw",
"Latn",
}
}


Line 2,055: Line 2,080:
"Punan Merap",
"Punan Merap",
7259895,
7259895,
"poz",
"Latn",
}
}


Line 2,060: Line 2,087:
"Punan Aput",
"Punan Aput",
4782333,
4782333,
"poz-swa",
"Latn",
}
}


Line 2,070: Line 2,099:
"Punan Merah",
"Punan Merah",
7259894,
7259894,
"poz-swa",
"Latn",
}
}


Line 2,081: Line 2,112:
"Puinave",
"Puinave",
3027918,
3027918,
nil,
"Latn",
}
}


Line 2,087: Line 2,120:
7259896,
7259896,
"poz-swa",
"poz-swa",
"Latn",
}
}


Line 2,099: Line 2,133:
6440803,
6440803,
"mkh",
"mkh",
"Latn",
}
}


Line 2,104: Line 2,139:
"Pulabu",
"Pulabu",
7259163,
7259163,
"ngf-mad",
"ngf-rai",
"Latn",
}
}


Line 2,142: Line 2,178:
"Puare",
"Puare",
3507983,
3507983,
"paa-shi",
"Latn",
}
}


Line 2,154: Line 2,192:
"Pawaia",
"Pawaia",
7156099,
7156099,
"paa",
"qfa-dis", -- Papuan; isolate in Glottolog; unclassified in Pawley and Hammarström (2018); sister to the Teberan
  -- languages by Usher (2020); tentatively TNG by Ross (2005)
"Latn",
"Latn",
}
}
Line 2,255: Line 2,294:


m["pyx"] = {
m["pyx"] = {
"Tircul",
"Pyu (Myanmar)",
36259,
36259,
"sit",
"sit",
Retrieved from "https://linguifex.com/wiki/Module:languages/data/3/p"