diff --git a/unicodetools/data/ucd/dev/IndicPositionalCategory.txt b/unicodetools/data/ucd/dev/IndicPositionalCategory.txt index 9904abd1f..bad2697b9 100644 --- a/unicodetools/data/ucd/dev/IndicPositionalCategory.txt +++ b/unicodetools/data/ucd/dev/IndicPositionalCategory.txt @@ -1,5 +1,5 @@ # IndicPositionalCategory-16.0.0.txt -# Date: 2023-11-02, 22:55:33 GMT +# Date: 2023-11-09, 18:48:36 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -69,7 +69,7 @@ # Ahom, Balinese, Batak, Bengali, Bhaiksuki, Brahmi, Buginese, Buhid, # Chakma, Cham, Devanagari, Dives Akuru, Dogra, Grantha, Gujarati, # Gunjala Gondi, Gurmukhi, Hanunoo, Javanese, Kaithi, Kannada, Kawi, -# Kayah Li, Kharoshthi, Khmer, Khojki, Khudawadi, Lao, Lepcha, Limbu, +# Kayah Li, Kharoshthi, Khmer, Khojki, Khudawadi, Kirat Rai, Lao, Lepcha, Limbu, # Makasar, Malayalam, Marchen, Masaram Gondi, Meetei Mayek, Modi, # Myanmar, Nandinagari, Newa, New Tai Lue, Oriya, Rejang, Saurashtra, # Sharada, Siddham, Sinhala, Soyombo, Sundanese, Syloti Nagri, @@ -83,7 +83,7 @@ # list of Indic scripts, including those which do not have # positional characters. Currently, those additional # Indic scripts without positional characters are -# Kirat Rai, Multani, Phags-pa, and Tai Le. +# Multani, Phags-pa, and Tai Le. # # Notes: # @@ -299,6 +299,9 @@ ABEC ; Right # Mc MEETEI MAYEK LUM IYEK 11F03 ; Right # Mc KAWI SIGN VISARGA 11F34..11F35 ; Right # Mc [2] KAWI VOWEL SIGN AA..KAWI VOWEL SIGN ALTERNATE AA 11F41 ; Right # Mc KAWI SIGN KILLER +16D40..16D42 ; Right # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA +16D63..16D6A ; Right # Lo [8] KIRAT RAI VOWEL SIGN AA..KIRAT RAI VOWEL SIGN AU +16D6B..16D6C ; Right # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT # Indic_Positional_Category=Left diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/MakeUnicodeFiles.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/MakeUnicodeFiles.txt index 2854b13ba..04e0c1339 100644 --- a/unicodetools/src/main/resources/org/unicode/text/UCD/MakeUnicodeFiles.txt +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/MakeUnicodeFiles.txt @@ -972,7 +972,7 @@ File: IndicPositionalCategory # Ahom, Balinese, Batak, Bengali, Bhaiksuki, Brahmi, Buginese, Buhid, # Chakma, Cham, Devanagari, Dives Akuru, Dogra, Grantha, Gujarati, # Gunjala Gondi, Gurmukhi, Hanunoo, Javanese, Kaithi, Kannada, Kawi, -# Kayah Li, Kharoshthi, Khmer, Khojki, Khudawadi, Lao, Lepcha, Limbu, +# Kayah Li, Kharoshthi, Khmer, Khojki, Khudawadi, Kirat Rai, Lao, Lepcha, Limbu, # Makasar, Malayalam, Marchen, Masaram Gondi, Meetei Mayek, Modi, # Myanmar, Nandinagari, Newa, New Tai Lue, Oriya, Rejang, Saurashtra, # Sharada, Siddham, Sinhala, Soyombo, Sundanese, Syloti Nagri, @@ -986,7 +986,7 @@ File: IndicPositionalCategory # list of Indic scripts, including those which do not have # positional characters. Currently, those additional # Indic scripts without positional characters are -# Kirat Rai, Multani, Phags-pa, and Tai Le. +# Multani, Phags-pa, and Tai Le. # # Notes: # diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt index 4f3e7316b..3c077270c 100644 --- a/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt @@ -896,7 +896,7 @@ Let $ideohack = [〆 〇 〡-〩] # InPC-InSC-gc invariants # See https://www.unicode.org/L2/L2023/23200-category-invariants.pdf. -\p{InPC=/(Left|Right)/} ⊆ [\p{gc=Mc}\p{gc=Lo}] +\p{InPC=/(Left|Right)/} ⊆ [\p{gc=Mc}\p{gc=Lo}\p{gc=Lm}] [\P{InPC=NA}&\p{gc=Mc}] ⊆ \p{InPC=/(Left|Right)/} [\P{InPC=NA}&\P{InPC=/(Left|Right)/}] ⊆ [\p{gc=Mn}\p{gc=Lo}] \p{gc=Mn} ⊆ \P{InPC=/(Left|Right)/}