Skip to content

fix: corpus test repairs, batch B - tha, din-fas, khm, lao, mya #255

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ronaldtse merged 5 commits into from
Nov 4, 2026
Merged

fix: corpus test repairs, batch B - tha, din-fas, khm, lao, mya #255

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
f41360d
fix(bgnpcgn-tha): romanize leading vowel glyphs in phonetic order
ronaldtse Nov 4, 2026
6703fb1
fix(din-fas): hamza renders apostrophe; he word-final rule per Tabell…
ronaldtse Nov 4, 2026
cd28e2e
fix(alalc-khm): bantac frame per 2013 notes; correct u-vowel codepoin…
ronaldtse Nov 4, 2026
bded5a4
fix(alalc-lao): o-ang ayn word-initially per Note 6; test input to No…
ronaldtse Nov 4, 2026
2924b7f
fix(alalc-mya): wa romanizes v per 2011 table; bare-medial rows; test…
ronaldtse Nov 4, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
126 changes: 89 additions & 37 deletions maps/alalc-khm-Khmr-Latn-2013.isc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,8 +41,8 @@ tests {
"\u1780\u17b6\u1780\u17cb" -> "kâk"
"\u179f\u17b6\u1780\u17cb" -> "sâk"
"\u1798\u17bb\u1793" -> "mun"
"\u1794\u17bc\u17b8" -> "p˝ī"
"\u179f\u17bc\u17b8" -> "sʹī"
"\u1794\u17bb\u17b8" -> "p˝ī"
"\u179f\u17bb\u17b8" -> "sʹī"
}

stage main {
Expand Down Expand Up @@ -3328,42 +3328,94 @@ stage main {
sub "អៅ" "‛au"
}

# BANTAC FRAME, FIRST CONSONANT (page 4 notes): "◌់ is a Khmer
# diacritic called Banták that shortens the preceding vowel" and
# "◌◌់ is a combined form of consonant sound and Banták as in កក់
# (kák); សក់ (sák)". In the two-consonant frame C1+C2+់ the bantac
# shortens the INHERENT vowel of the first consonant, so the vowel
# slot renders á and the second consonant is syllable-final: the
# first consonant carries no inherent vowel of its own. Khmer-glyph
# context, so this runs before the inherent-vowel pass; the
# vowel+bantac compounds (◌ា◌់ -> â, rows above) are already
# consumed.
parallel {
sub "ក់" "ká"
sub "ខ់" "khá"
sub "គ់" "gá"
sub "ឃ់" "ghá"
sub "ង់" "ngá"
sub "ច់" "cá"
sub "ឆ់" "chá"
sub "ជ់" "já"
sub "ឈ់" "jhá"
sub "ញ់" "ñá"
sub "ដ់" "ṭá"
sub "ឋ់" "ṭhá"
sub "ឌ់" "ḍá"
sub "ឍ់" "ḍhá"
sub "ណ់" "ṇá"
sub "ត់" "tá"
sub "ថ់" "thá"
sub "ទ់" "dá"
sub "ធ់" "dhá"
sub "ន់" "ná"
sub "ប់" "pá"
sub "ផ់" "phá"
sub "ព់" "bá"
sub "ភ់" "bhá"
sub "ម់" "má"
sub "យ់" "yá"
sub "រ់" "rá"
sub "ល់" "lá"
sub "វ់" "vá"
sub "ឝ់" "śá"
sub "ឞ់" "ṣá"
sub "ស់" "sá"
sub "ហ់" "há"
sub "ឡ់" "ḷá"
sub "អ់" "‛á"
sub { from "ក" to "k" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ខ" to "kh" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "គ" to "g" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ឃ" to "gh" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ង" to "ng" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ច" to "c" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ឆ" to "ch" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ជ" to "j" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ឈ" to "jh" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ញ" to "ñ" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ដ" to "ṭ" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ឋ" to "ṭh" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ឌ" to "ḍ" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ឍ" to "ḍh" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ណ" to "ṇ" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ត" to "t" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ថ" to "th" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ទ" to "d" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ធ" to "dh" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ន" to "n" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ប" to "p" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ផ" to "ph" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ព" to "b" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ភ" to "bh" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ម" to "m" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "យ" to "y" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "រ" to "r" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ល" to "l" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "វ" to "v" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ឝ" to "ś" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ឞ" to "ṣ" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ស" to "s" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ហ" to "h" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "ឡ" to "ḷ" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
sub { from "អ" to "‛" after any("កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឝឞសហឡអ") + "់" }
}

# BANTAC, SECOND CONSONANT: the shortened inherent vowel á plus the
# syllable-final consonant (vowel table row ◌◌់ -> á combining acute
# accent; page 4 examples kák, sák). A bantac with no preceding
# consonant frame is unattested in the source.
parallel {
sub "ក់" "ák"
sub "ខ់" "ákh"
sub "គ់" "ág"
sub "ឃ់" "ágh"
sub "ង់" "áng"
sub "ច់" "ác"
sub "ឆ់" "ách"
sub "ជ់" "áj"
sub "ឈ់" "ájh"
sub "ញ់" "áñ"
sub "ដ់" "áṭ"
sub "ឋ់" "áṭh"
sub "ឌ់" "áḍ"
sub "ឍ់" "áḍh"
sub "ណ់" "áṇ"
sub "ត់" "át"
sub "ថ់" "áth"
sub "ទ់" "ád"
sub "ធ់" "ádh"
sub "ន់" "án"
sub "ប់" "áp"
sub "ផ់" "áph"
sub "ព់" "áb"
sub "ភ់" "ábh"
sub "ម់" "ám"
sub "យ់" "áy"
sub "រ់" "ár"
sub "ល់" "ál"
sub "វ់" "áv"
sub "ឝ់" "áś"
sub "ឞ់" "áṣ"
sub "ស់" "ás"
sub "ហ់" "áh"
sub "ឡ់" "áḷ"
sub "អ់" "‛ák"
}

parallel {
Expand Down
12 changes: 11 additions & 1 deletion maps/alalc-lao-Laoo-Latn-2012.isc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,7 @@ tests {
"\u0e9a\u0eb8\u0ea7\u0e81" -> "būak"
"\u0e99\u0eb2\u0ea7" -> "nāo"
"\u0ec1\u0e81\u0ec9\u0ea7" -> "kǣo"
"\u0eab\u0ecd\u0e8d\u0eb2" -> "nyā"
"\u0eab\u0e8d\u0ec9\u0eb2" -> "nyā"
"\u0eab\u0ebc\u0eb2\u0e8d" -> "lāi"
"\u0ead\u0eb5\u0e81" -> "ʻīk"
"\u0e84\u0eb4\u0e94\u0eaa\u0eb0\u0e95\u0ebd\u0e99" -> "khitsatīan"
Expand Down Expand Up @@ -1880,6 +1880,16 @@ stage main {
sub { from "ລ" to "n" after any("ກຂຄງຈສຊດຕຖທນບປຜຝພຟມຢຣລຮ") }
}

# O ANG word-initially carries a vowel-initial syllable and
# romanizes as the ayn (Note 6: "ອ is used in initial position for
# syllables beginning with a vowel, thus: ອີກ (ʻīk)"); this runs
# before the consonant+vowel pair rows so the vowel-syllable carriers
# ອັ ອາ ອິ ອີ ... render ʻ plus the vowel. Elsewhere ອ is the vowel
# ǭ (default row below).
parallel {
sub { from "ອ" to "ʻ" before boundary }
}

parallel {
sub "ກັ" "ka"
sub "ຂັ" "kha"
Expand Down
Loading
Loading