cldr-transforms 46.0.0-BETA2

package/transforms/Telugu-ur.txt

@@ -0,0 +1,7 @@
+
+::[ఁ-ఃఅ-ఌఎ-ఐఒ-నప-ళవ-హా-ౄె-ైొ-్ౕ-ౖౠ-ౡ౦-౯];
+::NFD;
+::Telugu-InterIndic;
+::InterIndic-ur;
+::NFC;
+

package/transforms/Thaana-Latin.json

@@ -0,0 +1,11 @@
+{
+  "_backwardAlias": "Thaana-Latin",
+  "_visibility": "external",
+  "_backwardAliasBcp47": "und-Latn-t-und-thaa",
+  "_alias": "Latin-Thaana",
+  "_aliasBcp47": "und-Thaa-t-und-latn",
+  "_source": "Latn",
+  "_direction": "both",
+  "_target": "Thaa",
+  "_rulesFile": "Thaana-Latin.txt"
+}

package/transforms/Thaana-Latin.txt

@@ -0,0 +1,433 @@
+
+tta ↔ ޘަ ;
+ḥa ↔ ޙަ ;
+kha ↔ ޚަ ;
+dha ↔ ޛަ ;
+ša ← ޝަ ;
+ṣa ↔ ޞަ ;
+ḏa ↔ ޟަ ;
+t̤a ↔ ޠަ ;
+ʿa ↔ ޢަ ;
+ǧa ↔ ޣަ ;
+qa ↔ ޤަ ;
+ha ↔ ހަ ;
+ša ↔ ށަ ;
+na ↔ ނަ ;
+ra ↔ ރަ ;
+ba ↔ ބަ ;
+ḷa ↔ ޅަ ;
+ka ↔ ކަ ;
+‘a ↔ އަ ;
+va ↔ ވަ ;
+ma ↔ މަ ;
+fa ↔ ފަ ;
+da ↔ ދަ ;
+ta ↔ ތަ ;
+la ↔ ލަ ;
+ga ↔ ގަ ;
+ña ↔ ޏަ ;
+sa ↔ ސަ ;
+ḍa ↔ ޑަ ;
+ja ↔ ޖަ ;
+ča ↔ ޗަ ;
+za ↔ ޒަ ;
+ṭa ↔ ޓަ ;
+pa ↔ ޕަ ;
+ya ↔ ޔަ ;
+ttā ↔ ޘާ ;
+ḥā ↔ ޙާ ;
+khā ↔ ޚާ ;
+dhā ↔ ޛާ ;
+šā ← ޝާ ;
+ṣā ↔ ޞާ ;
+ḏā ↔ ޟާ ;
+t̤ā ↔ ޠާ ;
+ʿā ↔ ޢާ ;
+ǧā ↔ ޣާ ;
+qā ↔ ޤާ ;
+hā ↔ ހާ ;
+šā ↔ ށާ ;
+nā ↔ ނާ ;
+rā ↔ ރާ ;
+bā ↔ ބާ ;
+ḷā ↔ ޅާ ;
+kā ↔ ކާ ;
+‘ā ↔ އާ ;
+vā ↔ ވާ ;
+mā ↔ މާ ;
+fā ↔ ފާ ;
+dā ↔ ދާ ;
+tā ↔ ތާ ;
+lā ↔ ލާ ;
+gā ↔ ގާ ;
+ñā ↔ ޏާ ;
+sā ↔ ސާ ;
+ḍā ↔ ޑާ ;
+jā ↔ ޖާ ;
+čā ↔ ޗާ ;
+zā ↔ ޒާ ;
+ṭā ↔ ޓާ ;
+pā ↔ ޕާ ;
+yā ↔ ޔާ ;
+tti ↔ ޘި ;
+ḥi ↔ ޙި ;
+khi ↔ ޚި ;
+dhi ↔ ޛި ;
+ši ← ޝި ;
+ṣi ↔ ޞި ;
+ḏi ↔ ޟި ;
+t̤i ↔ ޠި ;
+ʿi ↔ ޢި ;
+ǧi ↔ ޣި ;
+qi ↔ ޤި ;
+hi ↔ ހި ;
+ši ↔ ށި ;
+ni ↔ ނި ;
+ri ↔ ރި ;
+bi ↔ ބި ;
+ḷi ↔ ޅި ;
+ki ↔ ކި ;
+‘i ↔ އި ;
+vi ↔ ވި ;
+mi ↔ މި ;
+fi ↔ ފި ;
+di ↔ ދި ;
+ti ↔ ތި ;
+li ↔ ލި ;
+gi ↔ ގި ;
+ñi ↔ ޏި ;
+si ↔ ސި ;
+ḍi ↔ ޑި ;
+ji ↔ ޖި ;
+či ↔ ޗި ;
+zi ↔ ޒި ;
+ṭi ↔ ޓި ;
+pi ↔ ޕި ;
+yi ↔ ޔި ;
+ttī ↔ ޘީ ;
+ḥī ↔ ޙީ ;
+khī ↔ ޚީ ;
+dhī ↔ ޛީ ;
+šī ← ޝީ ;
+ṣī ↔ ޞީ ;
+ḏī ↔ ޟީ ;
+t̤ī ↔ ޠީ ;
+ʿī ↔ ޢީ ;
+ǧī ↔ ޣީ ;
+qī ↔ ޤީ ;
+hī ↔ ހީ ;
+šī ↔ ށީ ;
+nī ↔ ނީ ;
+rī ↔ ރީ ;
+bī ↔ ބީ ;
+ḷī ↔ ޅީ ;
+kī ↔ ކީ ;
+‘ī ↔ އީ ;
+vī ↔ ވީ ;
+mī ↔ މީ ;
+fī ↔ ފީ ;
+dī ↔ ދީ ;
+tī ↔ ތީ ;
+lī ↔ ލީ ;
+gī ↔ ގީ ;
+ñī ↔ ޏީ ;
+sī ↔ ސީ ;
+ḍī ↔ ޑީ ;
+jī ↔ ޖީ ;
+čī ↔ ޗީ ;
+zī ↔ ޒީ ;
+ṭī ↔ ޓީ ;
+pī ↔ ޕީ ;
+yī ↔ ޔީ ;
+ttu ↔ ޘު ;
+ḥu ↔ ޙު ;
+khu ↔ ޚު ;
+dhu ↔ ޛު ;
+šu ← ޝު ;
+ṣu ↔ ޞު ;
+ḏu ↔ ޟު ;
+t̤u ↔ ޠު ;
+ʿu ↔ ޢު ;
+ǧu ↔ ޣު ;
+qu ↔ ޤު ;
+hu ↔ ހު ;
+šu ↔ ށު ;
+nu ↔ ނު ;
+ru ↔ ރު ;
+bu ↔ ބު ;
+ḷu ↔ ޅު ;
+ku ↔ ކު ;
+‘u ↔ އު ;
+vu ↔ ވު ;
+mu ↔ މު ;
+fu ↔ ފު ;
+du ↔ ދު ;
+tu ↔ ތު ;
+lu ↔ ލު ;
+gu ↔ ގު ;
+ñu ↔ ޏު ;
+su ↔ ސު ;
+ḍu ↔ ޑު ;
+ju ↔ ޖު ;
+ču ↔ ޗު ;
+zu ↔ ޒު ;
+ṭu ↔ ޓު ;
+pu ↔ ޕު ;
+yu ↔ ޔު ;
+ttū ↔ ޘޫ ;
+ḥū ↔ ޙޫ ;
+khū ↔ ޚޫ ;
+dhū ↔ ޛޫ ;
+šū ← ޝޫ ;
+ṣū ↔ ޞޫ ;
+ḏū ↔ ޟޫ ;
+t̤ū ↔ ޠޫ ;
+ʿū ↔ ޢޫ ;
+ǧū ↔ ޣޫ ;
+qū ↔ ޤޫ ;
+hū ↔ ހޫ ;
+šū ↔ ށޫ ;
+nū ↔ ނޫ ;
+rū ↔ ރޫ ;
+bū ↔ ބޫ ;
+ḷū ↔ ޅޫ ;
+kū ↔ ކޫ ;
+‘ū ↔ އޫ ;
+vū ↔ ވޫ ;
+mū ↔ މޫ ;
+fū ↔ ފޫ ;
+dū ↔ ދޫ ;
+tū ↔ ތޫ ;
+lū ↔ ލޫ ;
+gū ↔ ގޫ ;
+ñū ↔ ޏޫ ;
+sū ↔ ސޫ ;
+ḍū ↔ ޑޫ ;
+jū ↔ ޖޫ ;
+čū ↔ ޗޫ ;
+zū ↔ ޒޫ ;
+ṭū ↔ ޓޫ ;
+pū ↔ ޕޫ ;
+yū ↔ ޔޫ ;
+tte ↔ ޘެ ;
+ḥe ↔ ޙެ ;
+khe ↔ ޚެ ;
+dhe ↔ ޛެ ;
+še ← ޝެ ;
+ṣe ↔ ޞެ ;
+ḏe ↔ ޟެ ;
+t̤e ↔ ޠެ ;
+ʿe ↔ ޢެ ;
+ǧe ↔ ޣެ ;
+qe ↔ ޤެ ;
+he ↔ ހެ ;
+še ↔ ށެ ;
+ne ↔ ނެ ;
+re ↔ ރެ ;
+be ↔ ބެ ;
+ḷe ↔ ޅެ ;
+ke ↔ ކެ ;
+‘e ↔ އެ ;
+ve ↔ ވެ ;
+me ↔ މެ ;
+fe ↔ ފެ ;
+de ↔ ދެ ;
+te ↔ ތެ ;
+le ↔ ލެ ;
+ge ↔ ގެ ;
+ñe ↔ ޏެ ;
+se ↔ ސެ ;
+ḍe ↔ ޑެ ;
+je ↔ ޖެ ;
+če ↔ ޗެ ;
+ze ↔ ޒެ ;
+ṭe ↔ ޓެ ;
+pe ↔ ޕެ ;
+ye ↔ ޔެ ;
+ttē ↔ ޘޭ ;
+ḥē ↔ ޙޭ ;
+khē ↔ ޚޭ ;
+dhē ↔ ޛޭ ;
+šē ← ޝޭ ;
+ṣē ↔ ޞޭ ;
+ḏē ↔ ޟޭ ;
+t̤ē ↔ ޠޭ ;
+ʿē ↔ ޢޭ ;
+ǧē ↔ ޣޭ ;
+qē ↔ ޤޭ ;
+hē ↔ ހޭ ;
+šē ↔ ށޭ ;
+nē ↔ ނޭ ;
+rē ↔ ރޭ ;
+bē ↔ ބޭ ;
+ḷē ↔ ޅޭ ;
+kē ↔ ކޭ ;
+‘ē ↔ އޭ ;
+vē ↔ ވޭ ;
+mē ↔ މޭ ;
+fē ↔ ފޭ ;
+dē ↔ ދޭ ;
+tē ↔ ތޭ ;
+lē ↔ ލޭ ;
+gē ↔ ގޭ ;
+ñē ↔ ޏޭ ;
+sē ↔ ސޭ ;
+ḍē ↔ ޑޭ ;
+jē ↔ ޖޭ ;
+čē ↔ ޗޭ ;
+zē ↔ ޒޭ ;
+ṭē ↔ ޓޭ ;
+pē ↔ ޕޭ ;
+yē ↔ ޔޭ ;
+tto ↔ ޘޮ ;
+ḥo ↔ ޙޮ ;
+kho ↔ ޚޮ ;
+dho ↔ ޛޮ ;
+šo ← ޝޮ ;
+ṣo ↔ ޞޮ ;
+ḏo ↔ ޟޮ ;
+t̤o ↔ ޠޮ ;
+ʿo ↔ ޢޮ ;
+ǧo ↔ ޣޮ ;
+qo ↔ ޤޮ ;
+ho ↔ ހޮ ;
+šo ↔ ށޮ ;
+no ↔ ނޮ ;
+ro ↔ ރޮ ;
+bo ↔ ބޮ ;
+ḷo ↔ ޅޮ ;
+ko ↔ ކޮ ;
+‘o ↔ އޮ ;
+vo ↔ ވޮ ;
+mo ↔ މޮ ;
+fo ↔ ފޮ ;
+do ↔ ދޮ ;
+to ↔ ތޮ ;
+lo ↔ ލޮ ;
+go ↔ ގޮ ;
+ño ↔ ޏޮ ;
+so ↔ ސޮ ;
+ḍo ↔ ޑޮ ;
+jo ↔ ޖޮ ;
+čo ↔ ޗޮ ;
+zo ↔ ޒޮ ;
+ṭo ↔ ޓޮ ;
+po ↔ ޕޮ ;
+yo ↔ ޔޮ ;
+ttō ↔ ޘޯ ;
+ḥō ↔ ޙޯ ;
+khō ↔ ޚޯ ;
+dhō ↔ ޛޯ ;
+šō ← ޝޯ ;
+ṣō ↔ ޞޯ ;
+ḏō ↔ ޟޯ ;
+t̤ō ↔ ޠޯ ;
+ʿō ↔ ޢޯ ;
+ǧō ↔ ޣޯ ;
+qō ↔ ޤޯ ;
+hō ↔ ހޯ ;
+šō ↔ ށޯ ;
+nō ↔ ނޯ ;
+rō ↔ ރޯ ;
+bō ↔ ބޯ ;
+ḷō ↔ ޅޯ ;
+kō ↔ ކޯ ;
+‘ō ↔ އޯ ;
+vō ↔ ވޯ ;
+mō ↔ މޯ ;
+fō ↔ ފޯ ;
+dō ↔ ދޯ ;
+tō ↔ ތޯ ;
+lō ↔ ލޯ ;
+gō ↔ ގޯ ;
+ñō ↔ ޏޯ ;
+sō ↔ ސޯ ;
+ḍō ↔ ޑޯ ;
+jō ↔ ޖޯ ;
+čō ↔ ޗޯ ;
+zō ↔ ޒޯ ;
+ṭō ↔ ޓޯ ;
+pō ↔ ޕޯ ;
+yō ↔ ޔޯ ;
+tt ↔ ޘް ;
+ḥ ↔ ޙް ;
+kh ↔ ޚް ;
+dh ↔ ޛް ;
+š ← ޝް ;
+ṣ ↔ ޞް ;
+ḏ ↔ ޟް ;
+t̤ ↔ ޠް ;
+ʿ ↔ ޢް ;
+ǧ ↔ ޣް ;
+q ↔ ޤް ;
+h ↔ ހް ;
+š ↔ ށް ;
+n ↔ ން ;
+r ↔ ރް ;
+b ↔ ބް ;
+ḷ ↔ ޅް ;
+k ↔ ކް ;
+‘ ↔ އް ;
+v ↔ ވް ;
+m ↔ މް ;
+f ↔ ފް ;
+d ↔ ދް ;
+t ↔ ތް ;
+l ↔ ލް ;
+g ↔ ގް ;
+ñ ↔ ޏް ;
+s ↔ ސް ;
+ḍ ↔ ޑް ;
+j ↔ ޖް ;
+č ↔ ޗް ;
+z ↔ ޒް ;
+ṭ ↔ ޓް ;
+p ↔ ޕް ;
+y ↔ ޔް ;
+h ← ހ ;
+š ← ށ ;
+n ← ނ ;
+r ← ރ ;
+b ← ބ ;
+ḷ ← ޅ ;
+k ← ކ ;
+‘ ← އ ;
+v ← ވ ;
+m ← މ ;
+f ← ފ ;
+d ← ދ ;
+t ← ތ ;
+l ← ލ ;
+g ← ގ ;
+ñ ← ޏ ;
+s ← ސ ;
+ḍ ← ޑ ;
+j ← ޖ ;
+č ← ޗ ;
+z ← ޒ ;
+ṭ ← ޓ ;
+p ← ޕ ;
+y ← ޔ ;
+tt ← ޘ ;
+ḥ ← ޙ ;
+kh ← ޚ ;
+dh ← ޛ ;
+š ← ޝ ;
+ṣ ← ޞ ;
+ḏ ← ޟ ;
+t̤ ← ޠ ;
+ʿ ← ޢ ;
+ǧ ← ޣ ;
+q ← ޤ ;
+a ↔ ަ ;
+ā ↔ ާ ;
+i ↔ ި ;
+ī ↔ ީ ;
+u ↔ ު ;
+ū ↔ ޫ ;
+e ↔ ެ ;
+ē ↔ ޭ ;
+o ↔ ޮ ;
+ō ↔ ޯ ;
+← ް ;
+

package/transforms/Thai-Latin.json

@@ -0,0 +1,9 @@
+{
+  "_visibility": "external",
+  "_alias": "Thai-Latin",
+  "_aliasBcp47": "und-Latn-t-und-thai",
+  "_source": "Thai",
+  "_direction": "forward",
+  "_target": "Latn",
+  "_rulesFile": "Thai-Latin.txt"
+}

package/transforms/Thai-Latin.txt

@@ -0,0 +1,9 @@
+
+::[[:thai:] ก-ฺเ-๛];
+::NFD;
+::Thai-ThaiSemi;
+::Any-BreakInternal;
+::Thai-ThaiLogical;
+::ThaiLogical-Latin;
+::NFC;
+

package/transforms/Thai-ThaiLogical.json

@@ -0,0 +1,7 @@
+{
+  "_visibility": "internal",
+  "_source": "Thai",
+  "_direction": "both",
+  "_target": "ThaiLogical",
+  "_rulesFile": "Thai-ThaiLogical.txt"
+}

package/transforms/Thai-ThaiLogical.txt

@@ -0,0 +1,16 @@
+
+# This reverses the Thai LogicalOrderException vowels, and does (part of) spaces
+# The rules that convert space into semicolon are in another file;
+# since they have to come BEFORE the break iterator
+$thai = [[:thai:] ก-ฺเ-๛] ;
+# First convert the semicolon back
+' '  ← $thai { '; '  } $thai;
+# Remove any other spaces between thai letters
+← $thai { ' ' } $thai;
+# Now vowels
+$thai_reversing = [[:Logical_Order_Exception:] & $thai];
+$thai_non_reversing = [$thai - $thai_reversing ];
+( $thai_reversing ) ( $thai_non_reversing ) → $2 $1;
+# other direction
+$2 $1 ← ( $thai_non_reversing ) ( $thai_reversing ) ;
+

package/transforms/Thai-ThaiSemi.json

@@ -0,0 +1,7 @@
+{
+  "_visibility": "internal",
+  "_source": "Thai",
+  "_direction": "both",
+  "_target": "ThaiSemi",
+  "_rulesFile": "Thai-ThaiSemi.txt"
+}

package/transforms/Thai-ThaiSemi.txt

@@ -0,0 +1,6 @@
+
+# The rules that convert space into semicolon are in this file;
+# since they have to come BEFORE the break iterator.
+$thai = [[:thai:] ก-ฺเ-๛] ;
+$thai { ' ' } $thai → '; ' ;
+

package/transforms/ThaiLogical-Latin.json

@@ -0,0 +1,7 @@
+{
+  "_visibility": "internal",
+  "_source": "ThaiLogical",
+  "_direction": "both",
+  "_target": "Latin",
+  "_rulesFile": "ThaiLogical-Latin.txt"
+}

package/transforms/ThaiLogical-Latin.txt

@@ -0,0 +1,147 @@
+
+# Thai-Latin
+# This set of rules follows ISO 11940
+#     see http://homepage.mac.com/sirbinks/pdf/Thai.r2.pdf
+# except that that does not mention an implicit vowel, so we use ọ
+#
+# The transcription is fairly ugly, so we ought to also do the UNGEGN version
+#     see: http://www.eki.ee/wgrs/rom1_th.pdf
+# and probably make that the main variant.
+#
+# Note: this is an internal file. The NFD/NFC is handled externally, in the index
+# The insertion of spaces between words, the reversal of the vowels
+# and the conversion of space to semicolon are done *outside* of these rules.
+# So as far as these rules are concerned, the vowels are in logical order!
+# insert implicit vowel (and remove it going the other way)
+# COMMENTED out: the implicit vowel positions cannot be predicted algorithmically
+#$consonant = [ก-ฮ];
+#$vowel = [ะ-ฺเ-ไ็];
+#{ ( $consonant ) } [^$vowel \uE000] → | $1 \uE000 ;
+#\uE000 → ọ ;
+# ← ọ ;
+$notAbove = [^\p{ccc=0}\p{ccc=above}] ;
+$notBelow = [^\p{ccc=0}\p{ccc=below}] ;
+# Consonants
+# Warning: the 'h's need to be handled carefully!
+# What we really want to say is the following, but we can't
+# $notHAccent = !($notAbove*   ̄ | $notBelow*   ̣) ;
+# Since the only accents we care about that could cause problems are free-standing accents below, we use instead:
+$freeStandingBelow = [̥  ];
+$hAccent =  [   ̄     ̣];
+$notHAccent0 = [^$freeStandingBelow$hAccent];
+$notHAccent1 = $freeStandingBelow [^$hAccent];
+ห → h̄ ; # THAI CHARACTER HO HIP
+ห | $1 ← h ($notAbove*)    ̄; # backward case, account for reordering
+ฮ ↔ ḥ ; # THAI CHARACTER HO NOKHUK
+ข ↔ k̄h ; # THAI CHARACTER KHO KHAI
+ฃ ↔ ḳ̄h ; # THAI CHARACTER KHO KHUAT
+ฅ ↔ kʹh ; # THAI CHARACTER KHO KHON
+ฆ ↔ ḳh ; # THAI CHARACTER KHO RAKHANG
+ค ← kh } $notHAccent1 ; # THAI CHARACTER KHO KHWAI
+ค ↔ kh } $notHAccent0 ; # THAI CHARACTER KHO KHWAI
+ก ↔ k ; # THAI CHARACTER KO KAI
+ภ ↔ p̣h ; # THAI CHARACTER PHO SAMPHAO
+ผ ↔ p̄h ; # THAI CHARACTER PHO PHUNG
+พ ← ph } $notHAccent1 ; # THAI CHARACTER PHO PHAN
+พ ↔ ph } $notHAccent0 ; # THAI CHARACTER PHO PHAN
+ป ↔ p ; # THAI CHARACTER PO PLA
+ฉ ↔ c̄h ; # THAI CHARACTER CHO CHING
+ฌ ↔ c̣h ; # THAI CHARACTER CHO CHOE
+ช ← ch } $notHAccent1 ; # THAI CHARACTER CHO CHANG
+ช ↔ ch } $notHAccent0 ; # THAI CHARACTER CHO CHANG
+จ ↔ c ; # THAI CHARACTER CHO CHAN
+ฐ ↔ ṭ̄h ; # THAI CHARACTER THO THAN
+ฑ ↔ ṯh ; # THAI CHARACTER THO NANGMONTHO
+ฒ ↔ tʹh ; # THAI CHARACTER THO PHUTHAO
+ถ ↔ t̄h ; # THAI CHARACTER THO THUNG
+ธ ↔ ṭh ; # THAI CHARACTER THO THONG
+ท ← th } $notHAccent1 ; # THAI CHARACTER THO THAHAN
+ท ↔ th } $notHAccent0 ; # THAI CHARACTER THO THAHAN
+#Note: TO PATAK deviates from ISO since t-dotunder + h would be ambigous. So it uses vertical tick.
+ฏ ↔ t̩ ; # THAI CHARACTER TO PATAK
+ต ↔ t ; # THAI CHARACTER TO TAO
+# since there is no singleton g (generated), don't worry about that.
+ง ↔ ng ; # THAI CHARACTER NGO NGU
+ณ ↔ ṇ ; # THAI CHARACTER NO NEN
+น ↔ n ; # THAI CHARACTER NO NU
+ญ ↔ ỵ  ; # THAI CHARACTER YO YING
+ฎ ↔ ḍ ; # THAI CHARACTER DO CHADA
+ด ↔ d ; # THAI CHARACTER DO DEK
+บ ↔ b ; # THAI CHARACTER BO BAIMAI
+ฝ ↔ f̄ ; # THAI CHARACTER FO FA
+ฝ | $1 ← f ($notAbove*)    ̄; # backward case, account for reordering
+ม ↔ m ; # THAI CHARACTER MO MA
+ย ↔ y ; # THAI CHARACTER YO YAK
+ร ↔ r ; # THAI CHARACTER RO RUA
+ฤ ↔ v ; # THAI CHARACTER RU
+ฦ ↔ ł ; # THAI CHARACTER LU
+ว ↔ w ; # THAI CHARACTER WO WAEN
+ศ ↔ ṣ̄ ; # THAI CHARACTER SO SALA***
+ศ | $1 ← s    ̣ ($notAbove*)    ̄; # backward case, account for reordering
+ษ ↔ s̄ʹ ; # THAI CHARACTER SO RUSI
+ส → s̄ ; # THAI CHARACTER SO SUA***
+ส | $1 ← s ($notAbove*)    ̄; # backward case, account for reordering
+ฬ ↔ ḷ ; # THAI CHARACTER LO CHULA
+ล ↔ l ; # THAI CHARACTER LO LING
+ฟ ↔ f ; # THAI CHARACTER FO FAN
+อ ↔ x ; # THAI CHARACTER O ANG
+ซ ↔ s ; # THAI CHARACTER SO SO
+# vowels
+ั ↔ ạ ; # THAI CHARACTER MAI HAN-AKAT
+า → ā ; # THAI CHARACTER SARA AA
+า | $1 ← a ($notAbove*)    ̄; # backward case, account for reordering
+# We deviate from ISO for SARA AM for disambiguation
+ำ → a  ̉; # THAI CHARACTER SARA AM
+ำ | $1 ← a ($notAbove*)  ̉ ; # backward case, account for reordering
+ะ ↔ a ; # THAI CHARACTER SARA A
+ี ↔ ī ; # THAI CHARACTER SARA II
+ี | $1 ← i ($notAbove*)    ̄  ; # backward case, account for reordering
+ื ↔ ụ̄ ; # THAI CHARACTER SARA UEE
+ื | $1 ← u   ̣ ($notAbove*)    ̄  ; # backward case, account for reordering
+ึ ↔ ụ ; # THAI CHARACTER SARA UE
+ู ↔ ū ; # THAI CHARACTER SARA UU
+ู | $1 ← u  ($notAbove*)    ̄  ; # backward case, account for reordering
+ุ ↔ u ; # THAI CHARACTER SARA U
+ฯ ↔ ‡ ; # THAI CHARACTER PAIYANNOI
+# ฿ ↔ XXX ; # THAI CURRENCY SYMBOL BAHT
+เ ↔ e ; # THAI CHARACTER SARA E
+แ ↔ æ ; # THAI CHARACTER SARA AE
+โ ↔ o ; # THAI CHARACTER SARA O
+ใ ↔ ı ; # THAI CHARACTER SARA AI MAIMUAN
+ไ ↔ ị ; # THAI CHARACTER SARA AI MAIMALAI
+ๅ ↔ ɨ ; # THAI CHARACTER LAKKHANGYAO
+็ ↔ ̆ ; # THAI CHARACTER MAITAIKHU
+่ ↔ ̀ ; # THAI CHARACTER MAI EK
+้ ↔ ̂ ; # THAI CHARACTER MAI THO
+๊ ↔ ́ ; # THAI CHARACTER MAI TRI
+๋ ↔ ̌ ; # THAI CHARACTER MAI CHATTAWA
+์ ↔ ̒ ; # THAI CHARACTER THANTHAKHAT
+๎ ↔ '~' ; # THAI CHARACTER YAMAKKAN
+# We deviate from ISO for disambiguation
+ํ ↔  ̊ ; # THAI CHARACTER NIKHAHIT
+๏ ↔ '§' ; # THAI CHARACTER FONGMAN
+๐ ↔ 0 ; # THAI DIGIT ZERO
+๑ ↔ 1 ; # THAI DIGIT ONE
+๒ ↔ 2 ; # THAI DIGIT TWO
+๓ ↔ 3 ; # THAI DIGIT THREE
+๔ ↔ 4 ; # THAI DIGIT FOUR
+๕ ↔ 5 ; # THAI DIGIT FIVE
+๖ ↔ 6 ; # THAI DIGIT SIX
+๗ ↔ 7 ; # THAI DIGIT SEVEN
+๘ ↔ 8 ; # THAI DIGIT EIGHT
+๙ ↔ 9 ; # THAI DIGIT NINE
+๚ ↔ '||' ; # THAI CHARACTER ANGKHANKHU
+๛ ↔ » ; # THAI CHARACTER KHOMUT
+ๆ ↔ « ; # THAI CHARACTER MAIYAMOK
+# moved down to make shorter first
+#Note: PHINTHU deviates from ISO since underring causes canonical problems. So it uses spacing tick below.
+ฺ ↔ ˌ ; # THAI CHARACTER PHINTHU
+ิ ↔ i ; # THAI CHARACTER SARA I
+# fallbacks
+| k ← g ;
+| k ← h ;
+| c ← j ;
+| k ← q ;
+| s ← z ;
+:: (lower);
+

package/transforms/Turkmen-Latin-BGN.json

@@ -0,0 +1,9 @@
+{
+  "_visibility": "external",
+  "_alias": "Turkmen-Latin/BGN",
+  "_aliasBcp47": "tk-t-tk-cyrl-m0-bgn",
+  "_source": "tk_Cyrl",
+  "_direction": "forward",
+  "_target": "tk",
+  "_rulesFile": "Turkmen-Latin-BGN.txt"
+}