interscript-maps 2.5.1 → 3.0.0

data/maps/bgnpcgn-tha-Thai-Latn-2002.isc

@@ -0,0 +1,595 @@
+system "BGN/PCGN:tha-Thai:Latn:2002" {
+
+metadata {
+  authority_id bgnpcgn
+  id 2002
+  language iso-639-2:tha
+  source_script Thai
+  destination_script Latn
+  name BGN/PCGN 2002 agreement — Romanization of Thai (Royal Institute of Thailand system)
+  url https://www.gov.uk/government/publications/romanization-systems
+  creation_date 2000
+  adoption_date 2002
+  description
+
+  notes {
+    "BGN/PCGN 2002 agreement; developed by the Royal Institute of Thailand (2000), endorsed by Thailand and approved for UN use in 2002. Vowel length and tone are not romanized.
+
+    Source: ROMANIZATION OF THAI.pdf (interscript-references/bgn-pcgn, checked November 2017). That PDF's text layer drops Thai combining marks; the vowel-sign inventory was reconstructed from the rendered table and cross-checked against the embedded examples.
+
+    Note 1 of the source: correct romanization requires word identification and pronunciation knowledge -- syllable-internal final consonants are not orthographically decidable. This encoding is the deterministic layer: initial consonants by default, final consonants at word end, the vowel table, numerals, and mark stripping. Pronunciation-dependent cases (silent r in สามารถ, ทร by pronunciation, glottal อ) resolve through the pronunciation-lexicon layer.
+
+    Leading vowel glyphs (เ แ โ ไ ใ) precede their consonant in Thai script but romanize after it, per note 1 ("Consonant and vowel characters written in misleading order should be romanized as pronounced") and vowel-table rows 6, 7, 8, 11, 13 and 19 (ไ◌ ใ◌ -> C+ai, โ◌ -> C+o, เ◌ -> C+e, แ◌ -> C+ae, เ◌า -> C+ao). Encoded as one digraph row per consonant, the same mechanism as the corpus's alalc-tha-Thai-Latn-2011 encoding.
+
+    Silent ห as tone mark (ห นำ) is not romanized before the low-class consonants ง ญ ณ น ม ย ร ล (note 4: "ห at the beginning of a syllable and serving as a tone mark should not be romanized"; note 13: พรหม -> Phrom, "ห is silent"). ห + ว is pronunciation-dependent (note 4: หวอ -> wo but หวย -> huai) and stays in the lexicon layer.
+
+    Carrier-interleaved compound vowels (เ-C-า khao) are encoded through the digraph rows above; adjacent-sign compounds (ก-ล-ั-ว klua, ม-ื-อ mue, เ-า ao) are encoded as adjacent-sign rows."
+  }
+}
+
+tests {
+   "ภาษาไทย" ->  "phasathai"
+   "ไทย" ->  "thai"
+   "ใหม่" ->  "mai"
+   "ที่" ->  "thi"
+   "เป็น" ->  "pen"
+   "ใน" ->  "nai"
+   "การ" ->  "kan"
+   "มี" ->  "mi"
+   "๑๒๓" ->  "123"
+   "เขา" ->  "khao"
+   "กลัว" ->  "klua"
+   "มือ" ->  "mue"
+}
+
+
+stage main {
+
+  # MARKS (tone marks are not romanized; the vowel shortening mark ็
+  # has no RTGS effect; the silencing mark ์ removes the consonant it
+  # follows)
+  parallel {
+    sub "่" ""
+    sub "้" ""
+    sub "๊" ""
+    sub "๋" ""
+    sub "็" ""
+    sub "ก์" ""
+    sub "ข์" ""
+    sub "ค์" ""
+    sub "ง์" ""
+    sub "จ์" ""
+    sub "ช์" ""
+    sub "ญ์" ""
+    sub "ด์" ""
+    sub "ต์" ""
+    sub "ถ์" ""
+    sub "ท์" ""
+    sub "น์" ""
+    sub "บ์" ""
+    sub "ป์" ""
+    sub "ผ์" ""
+    sub "ฝ์" ""
+    sub "ฟ์" ""
+    sub "ม์" ""
+    sub "ย์" ""
+    sub "ร์" ""
+    sub "ล์" ""
+    sub "ว์" ""
+    sub "ส์" ""
+    sub "ห์" ""
+    sub "อ์" ""
+  }
+
+  # SILENT ห AS TONE MARK (ห นำ). Note 4: "ห at the beginning of a
+  # syllable and serving as a tone mark should not be romanized"
+  # (หวอ → wo, หลูบ → luep), with note 13's พรหม → Phrom ("ห is
+  # silent"). ห directly preceding a low-class consonant is always the
+  # tone-mark class, and ห is never syllable-final, so this is
+  # orthographically deterministic for ง ญ ณ น ม ย ร ล. ห + ว is
+  # pronunciation-dependent (note 4: หวอ → wo but หวย → huai) and is
+  # left to the pronunciation-lexicon layer.
+  parallel {
+    sub { from "ห" to "" after any("งญณนมยรล") }
+  }
+
+  # LEADING SILENT เ (the e-glyph prefixes a carrier consonant in the
+  # compound rows: เ-ป-ี-ย pia, เ-ก-อ-ย koeai...). Thai-glyph context,
+  # so this runs before the consonant pass. Carrier-interleaved
+  # compounds (เ-C-า class) need capture support (WO80).
+  parallel {
+    sub { from "เ" to "" before any("ก".."ฮ") + "ีย" }
+    sub { from "เ" to "" before any("ก".."ฮ") + "ือ" }
+    sub { from "เ" to "" before any("ก".."ฮ") + "อย" }
+  }
+
+  # LEADING VOWEL GLYPHS, PHONETIC REORDERING. The vowel table writes
+  # the leading vowels as เ◌ (row 6), แ◌ (row 7), โ◌ (row 8), ใ◌ ไ◌
+  # (row 11), โ◌ย (row 13) and เ◌า (row 19): the glyph precedes the
+  # consonant in Thai script while the romanization places the vowel
+  # after the consonant (ไท → thai). Note 1: "Consonant and vowel
+  # characters written in misleading order should be romanized as
+  # pronounced" (แขนง → khanaeng, เขื่อยา → khayao). One enumerated
+  # digraph row per consonant, as in the corpus's ALA-LC Thai 2011
+  # encoding; rows sit before the consonant and vowel passes.
+  parallel {
+    sub "ไกย" "kai"
+    sub "ไขย" "khai"
+    sub "ไฆย" "khai"
+    sub "ไคย" "khai"
+    sub "ไฅย" "khai"
+    sub "ไฃย" "khai"
+    sub "ไงย" "ngai"
+    sub "ไจย" "chai"
+    sub "ไฉย" "chai"
+    sub "ไชย" "chai"
+    sub "ไฌย" "chai"
+    sub "ไญย" "yai"
+    sub "ไฎย" "dai"
+    sub "ไฏย" "tai"
+    sub "ไฑย" "thai"
+    sub "ไฒย" "thai"
+    sub "ไดย" "dai"
+    sub "ไตย" "tai"
+    sub "ไฐย" "thai"
+    sub "ไถย" "thai"
+    sub "ไทย" "thai"
+    sub "ไธย" "thai"
+    sub "ไณย" "nai"
+    sub "ไนย" "nai"
+    sub "ไบย" "bai"
+    sub "ไปย" "pai"
+    sub "ไผย" "phai"
+    sub "ไพย" "phai"
+    sub "ไภย" "phai"
+    sub "ไฝย" "fai"
+    sub "ไฟย" "fai"
+    sub "ไมย" "mai"
+    sub "ไยย" "yai"
+    sub "ไรย" "rai"
+    sub "ไลย" "lai"
+    sub "ไฬย" "lai"
+    sub "ไวย" "wai"
+    sub "ไซย" "sai"
+    sub "ไศย" "sai"
+    sub "ไษย" "sai"
+    sub "ไสย" "sai"
+    sub "ไหย" "hai"
+    sub "ไฮย" "hai"
+    sub "โกย" "koi"
+    sub "โขย" "khoi"
+    sub "โฆย" "khoi"
+    sub "โคย" "khoi"
+    sub "โฅย" "khoi"
+    sub "โฃย" "khoi"
+    sub "โงย" "ngoi"
+    sub "โจย" "choi"
+    sub "โฉย" "choi"
+    sub "โชย" "choi"
+    sub "โฌย" "choi"
+    sub "โญย" "yoi"
+    sub "โฎย" "doi"
+    sub "โฏย" "toi"
+    sub "โฑย" "thoi"
+    sub "โฒย" "thoi"
+    sub "โดย" "doi"
+    sub "โตย" "toi"
+    sub "โฐย" "thoi"
+    sub "โถย" "thoi"
+    sub "โทย" "thoi"
+    sub "โธย" "thoi"
+    sub "โณย" "noi"
+    sub "โนย" "noi"
+    sub "โบย" "boi"
+    sub "โปย" "poi"
+    sub "โผย" "phoi"
+    sub "โพย" "phoi"
+    sub "โภย" "phoi"
+    sub "โฝย" "foi"
+    sub "โฟย" "foi"
+    sub "โมย" "moi"
+    sub "โยย" "yoi"
+    sub "โรย" "roi"
+    sub "โลย" "loi"
+    sub "โฬย" "loi"
+    sub "โวย" "woi"
+    sub "โซย" "soi"
+    sub "โศย" "soi"
+    sub "โษย" "soi"
+    sub "โสย" "soi"
+    sub "โหย" "hoi"
+    sub "โฮย" "hoi"
+    sub "เกา" "kao"
+    sub "เขา" "khao"
+    sub "เฆา" "khao"
+    sub "เคา" "khao"
+    sub "เฅา" "khao"
+    sub "เฃา" "khao"
+    sub "เงา" "ngao"
+    sub "เจา" "chao"
+    sub "เฉา" "chao"
+    sub "เชา" "chao"
+    sub "เฌา" "chao"
+    sub "เญา" "yao"
+    sub "เฎา" "dao"
+    sub "เฏา" "tao"
+    sub "เฑา" "thao"
+    sub "เฒา" "thao"
+    sub "เดา" "dao"
+    sub "เตา" "tao"
+    sub "เฐา" "thao"
+    sub "เถา" "thao"
+    sub "เทา" "thao"
+    sub "เธา" "thao"
+    sub "เณา" "nao"
+    sub "เนา" "nao"
+    sub "เบา" "bao"
+    sub "เปา" "pao"
+    sub "เผา" "phao"
+    sub "เพา" "phao"
+    sub "เภา" "phao"
+    sub "เฝา" "fao"
+    sub "เฟา" "fao"
+    sub "เมา" "mao"
+    sub "เยา" "yao"
+    sub "เรา" "rao"
+    sub "เลา" "lao"
+    sub "เฬา" "lao"
+    sub "เวา" "wao"
+    sub "เซา" "sao"
+    sub "เศา" "sao"
+    sub "เษา" "sao"
+    sub "เสา" "sao"
+    sub "เหา" "hao"
+    sub "เฮา" "hao"
+    sub "ไก" "kai"
+    sub "ไข" "khai"
+    sub "ไฆ" "khai"
+    sub "ไค" "khai"
+    sub "ไฅ" "khai"
+    sub "ไฃ" "khai"
+    sub "ไง" "ngai"
+    sub "ไจ" "chai"
+    sub "ไฉ" "chai"
+    sub "ไช" "chai"
+    sub "ไฌ" "chai"
+    sub "ไญ" "yai"
+    sub "ไฎ" "dai"
+    sub "ไฏ" "tai"
+    sub "ไฑ" "thai"
+    sub "ไฒ" "thai"
+    sub "ได" "dai"
+    sub "ไต" "tai"
+    sub "ไฐ" "thai"
+    sub "ไถ" "thai"
+    sub "ไท" "thai"
+    sub "ไธ" "thai"
+    sub "ไณ" "nai"
+    sub "ไน" "nai"
+    sub "ไบ" "bai"
+    sub "ไป" "pai"
+    sub "ไผ" "phai"
+    sub "ไพ" "phai"
+    sub "ไภ" "phai"
+    sub "ไฝ" "fai"
+    sub "ไฟ" "fai"
+    sub "ไม" "mai"
+    sub "ไย" "yai"
+    sub "ไร" "rai"
+    sub "ไล" "lai"
+    sub "ไฬ" "lai"
+    sub "ไว" "wai"
+    sub "ไซ" "sai"
+    sub "ไศ" "sai"
+    sub "ไษ" "sai"
+    sub "ไส" "sai"
+    sub "ไห" "hai"
+    sub "ไฮ" "hai"
+    sub "ใก" "kai"
+    sub "ใข" "khai"
+    sub "ใฆ" "khai"
+    sub "ใค" "khai"
+    sub "ใฅ" "khai"
+    sub "ใฃ" "khai"
+    sub "ใง" "ngai"
+    sub "ใจ" "chai"
+    sub "ใฉ" "chai"
+    sub "ใช" "chai"
+    sub "ใฌ" "chai"
+    sub "ใญ" "yai"
+    sub "ใฎ" "dai"
+    sub "ใฏ" "tai"
+    sub "ใฑ" "thai"
+    sub "ใฒ" "thai"
+    sub "ใด" "dai"
+    sub "ใต" "tai"
+    sub "ใฐ" "thai"
+    sub "ใถ" "thai"
+    sub "ใท" "thai"
+    sub "ใธ" "thai"
+    sub "ใณ" "nai"
+    sub "ใน" "nai"
+    sub "ใบ" "bai"
+    sub "ใป" "pai"
+    sub "ใผ" "phai"
+    sub "ใพ" "phai"
+    sub "ใภ" "phai"
+    sub "ใฝ" "fai"
+    sub "ใฟ" "fai"
+    sub "ใม" "mai"
+    sub "ใย" "yai"
+    sub "ใร" "rai"
+    sub "ใล" "lai"
+    sub "ใฬ" "lai"
+    sub "ใว" "wai"
+    sub "ใซ" "sai"
+    sub "ใศ" "sai"
+    sub "ใษ" "sai"
+    sub "ใส" "sai"
+    sub "ให" "hai"
+    sub "ใฮ" "hai"
+    sub "โก" "ko"
+    sub "โข" "kho"
+    sub "โฆ" "kho"
+    sub "โค" "kho"
+    sub "โฅ" "kho"
+    sub "โฃ" "kho"
+    sub "โง" "ngo"
+    sub "โจ" "cho"
+    sub "โฉ" "cho"
+    sub "โช" "cho"
+    sub "โฌ" "cho"
+    sub "โญ" "yo"
+    sub "โฎ" "do"
+    sub "โฏ" "to"
+    sub "โฑ" "tho"
+    sub "โฒ" "tho"
+    sub "โด" "do"
+    sub "โต" "to"
+    sub "โฐ" "tho"
+    sub "โถ" "tho"
+    sub "โท" "tho"
+    sub "โธ" "tho"
+    sub "โณ" "no"
+    sub "โน" "no"
+    sub "โบ" "bo"
+    sub "โป" "po"
+    sub "โผ" "pho"
+    sub "โพ" "pho"
+    sub "โภ" "pho"
+    sub "โฝ" "fo"
+    sub "โฟ" "fo"
+    sub "โม" "mo"
+    sub "โย" "yo"
+    sub "โร" "ro"
+    sub "โล" "lo"
+    sub "โฬ" "lo"
+    sub "โว" "wo"
+    sub "โซ" "so"
+    sub "โศ" "so"
+    sub "โษ" "so"
+    sub "โส" "so"
+    sub "โห" "ho"
+    sub "โฮ" "ho"
+    sub "เก" "ke"
+    sub "เข" "khe"
+    sub "เฆ" "khe"
+    sub "เค" "khe"
+    sub "เฅ" "khe"
+    sub "เฃ" "khe"
+    sub "เง" "nge"
+    sub "เจ" "che"
+    sub "เฉ" "che"
+    sub "เช" "che"
+    sub "เฌ" "che"
+    sub "เญ" "ye"
+    sub "เฎ" "de"
+    sub "เฏ" "te"
+    sub "เฑ" "the"
+    sub "เฒ" "the"
+    sub "เด" "de"
+    sub "เต" "te"
+    sub "เฐ" "the"
+    sub "เถ" "the"
+    sub "เท" "the"
+    sub "เธ" "the"
+    sub "เณ" "ne"
+    sub "เน" "ne"
+    sub "เบ" "be"
+    sub "เป" "pe"
+    sub "เผ" "phe"
+    sub "เพ" "phe"
+    sub "เภ" "phe"
+    sub "เฝ" "fe"
+    sub "เฟ" "fe"
+    sub "เม" "me"
+    sub "เย" "ye"
+    sub "เร" "re"
+    sub "เล" "le"
+    sub "เฬ" "le"
+    sub "เว" "we"
+    sub "เซ" "se"
+    sub "เศ" "se"
+    sub "เษ" "se"
+    sub "เส" "se"
+    sub "เห" "he"
+    sub "เฮ" "he"
+    sub "แก" "kae"
+    sub "แข" "khae"
+    sub "แฆ" "khae"
+    sub "แค" "khae"
+    sub "แฅ" "khae"
+    sub "แฃ" "khae"
+    sub "แง" "ngae"
+    sub "แจ" "chae"
+    sub "แฉ" "chae"
+    sub "แช" "chae"
+    sub "แฌ" "chae"
+    sub "แญ" "yae"
+    sub "แฎ" "dae"
+    sub "แฏ" "tae"
+    sub "แฑ" "thae"
+    sub "แฒ" "thae"
+    sub "แด" "dae"
+    sub "แต" "tae"
+    sub "แฐ" "thae"
+    sub "แถ" "thae"
+    sub "แท" "thae"
+    sub "แธ" "thae"
+    sub "แณ" "nae"
+    sub "แน" "nae"
+    sub "แบ" "bae"
+    sub "แป" "pae"
+    sub "แผ" "phae"
+    sub "แพ" "phae"
+    sub "แภ" "phae"
+    sub "แฝ" "fae"
+    sub "แฟ" "fae"
+    sub "แม" "mae"
+    sub "แย" "yae"
+    sub "แร" "rae"
+    sub "แล" "lae"
+    sub "แฬ" "lae"
+    sub "แว" "wae"
+    sub "แซ" "sae"
+    sub "แศ" "sae"
+    sub "แษ" "sae"
+    sub "แส" "sae"
+    sub "แห" "hae"
+    sub "แฮ" "hae"
+  }
+
+  # COMPOUND VOWEL SIGNS (adjacent-sign forms; source rows 10-19)
+  parallel {
+    sub "ีย" "ia"
+    sub "ึย" "ui"
+    sub "อย" "oi"
+    sub "ไย" "ai"
+    sub "าย" "ai"
+    sub "ัวะ" "ua"
+    sub "ัว" "ua"
+    sub "ือะ" "ue"
+    sub "ือ" "ue"
+    sub "เา" "ao"
+  }
+
+  # CONSONANTS — final form at word end
+  # (source table, rows 1-21: the second romanization column)
+  parallel {
+    sub { from "ข" to "k" after boundary }
+    sub { from "ฆ" to "k" after boundary }
+    sub { from "ค" to "k" after boundary }
+    sub { from "ฅ" to "k" after boundary }
+    sub { from "ฃ" to "k" after boundary }
+    sub { from "จ" to "t" after boundary }
+    sub { from "ฉ" to "t" after boundary }
+    sub { from "ช" to "t" after boundary }
+    sub { from "ฌ" to "t" after boundary }
+    sub { from "ญ" to "n" after boundary }
+    sub { from "ฎ" to "t" after boundary }
+    sub { from "ฑ" to "t" after boundary }
+    sub { from "ด" to "t" after boundary }
+    sub { from "ฐ" to "t" after boundary }
+    sub { from "ฒ" to "t" after boundary }
+    sub { from "ถ" to "t" after boundary }
+    sub { from "ท" to "t" after boundary }
+    sub { from "ธ" to "t" after boundary }
+    sub { from "บ" to "p" after boundary }
+    sub { from "ผ" to "p" after boundary }
+    sub { from "พ" to "p" after boundary }
+    sub { from "ภ" to "p" after boundary }
+    sub { from "ฝ" to "p" after boundary }
+    sub { from "ฟ" to "p" after boundary }
+    sub { from "ซ" to "t" after boundary }
+    sub { from "ศ" to "t" after boundary }
+    sub { from "ษ" to "t" after boundary }
+    sub { from "ส" to "t" after boundary }
+    sub { from "ร" to "n" after boundary }
+  }
+
+  # CONSONANTS — initial defaults (source table, rows 1-21, first
+  # romanization column); the standalone carrier อ is silent and
+  # vanishes
+  parallel {
+    sub "ก" "k"
+    sub "ข" "kh"
+    sub "ฆ" "kh"
+    sub "ค" "kh"
+    sub "ฅ" "kh"
+    sub "ฃ" "kh"
+    sub "ง" "ng"
+    sub "จ" "ch"
+    sub "ฉ" "ch"
+    sub "ช" "ch"
+    sub "ฌ" "ch"
+    sub "ญ" "y"
+    sub "ฎ" "d"
+    sub "ฏ" "t"
+    sub "ฑ" "th"
+    sub "ฒ" "th"
+    sub "ด" "d"
+    sub "ต" "t"
+    sub "ฐ" "th"
+    sub "ถ" "th"
+    sub "ท" "th"
+    sub "ธ" "th"
+    sub "ณ" "n"
+    sub "น" "n"
+    sub "บ" "b"
+    sub "ป" "p"
+    sub "ผ" "ph"
+    sub "พ" "ph"
+    sub "ภ" "ph"
+    sub "ฝ" "f"
+    sub "ฟ" "f"
+    sub "ม" "m"
+    sub "ย" "y"
+    sub "ร" "r"
+    sub "ล" "l"
+    sub "ฬ" "l"
+    sub "ว" "w"
+    sub "ซ" "s"
+    sub "ศ" "s"
+    sub "ษ" "s"
+    sub "ส" "s"
+    sub "ห" "h"
+    sub "ฮ" "h"
+    sub "อ" ""
+  }
+
+  # SIMPLE VOWELS (source vowel table, rows 1-9 and 11: single signs;
+  # length is not distinguished)
+  parallel {
+    sub "ะ" "a"
+    sub "ั" "a"
+    sub "า" "a"
+    sub "ๅ" "a"
+    sub "ิ" "i"
+    sub "ี" "i"
+    sub "ึ" "ue"
+    sub "ื" "ue"
+    sub "ุ" "u"
+    sub "ู" "u"
+    sub "เ" "e"
+    sub "แ" "ae"
+    sub "โ" "o"
+    sub "ใ" "ai"
+    sub "ไ" "ai"
+    sub "็" ""
+  }
+
+  # NUMERALS
+  parallel {
+    sub "๐" "0"
+    sub "๑" "1"
+    sub "๒" "2"
+    sub "๓" "3"
+    sub "๔" "4"
+    sub "๕" "5"
+    sub "๖" "6"
+    sub "๗" "7"
+    sub "๘" "8"
+    sub "๙" "9"
+  }
+}
+}