commit a4036327707bc4a69d35eeb3f929b32d89cb62da
parent 52056fb53025e7334d6184c52501a61f222e763f
Author: Drew DeVault <sir@cmpwn.com>
Date: Sun, 21 Mar 2021 13:07:42 -0400
unicode: initial module riggings
This defines constants for all of the Unicode properties found in the
UCD. I'll write a script later which converts the UCD XML representation
into a file which Hare can use to read these properties. This module
will also later be expanded with implementations of various algorithms
defined by Unicode.
Diffstat:
4 files changed, 1200 insertions(+), 1 deletion(-)
diff --git a/scripts/gen-stdlib b/scripts/gen-stdlib
@@ -499,6 +499,14 @@ types() {
gen_ssa types
}
+unicode() {
+ printf '# unicode\n'
+ gen_srcs unicode \
+ properties.ha \
+ unicode.ha
+ gen_ssa unicode
+}
+
printf '# This file is generated by the gen-stdlib script, do not edit it by hand\n\n'
modules="ascii
@@ -536,7 +544,8 @@ strings
strio
temp
time
-types"
+types
+unicode"
stdlib() {
rt
for module in $modules; do
diff --git a/stdlib.mk b/stdlib.mk
@@ -176,6 +176,9 @@ hare_stdlib_deps+=$(stdlib_time)
stdlib_types=$(HARECACHE)/types/types.o
hare_stdlib_deps+=$(stdlib_types)
+stdlib_unicode=$(HARECACHE)/unicode/unicode.o
+hare_stdlib_deps+=$(stdlib_unicode)
+
# ascii
stdlib_ascii_srcs= \
$(STDLIB)/ascii/ctype.ha \
@@ -604,6 +607,17 @@ $(HARECACHE)/types/types.ssa: $(stdlib_types_srcs) $(stdlib_rt)
@HARECACHE=$(HARECACHE) $(HAREC) $(HAREFLAGS) -o $@ -Ntypes \
-t$(HARECACHE)/types/types.td $(stdlib_types_srcs)
+# unicode
+stdlib_unicode_srcs= \
+ $(STDLIB)/unicode/properties.ha \
+ $(STDLIB)/unicode/unicode.ha
+
+$(HARECACHE)/unicode/unicode.ssa: $(stdlib_unicode_srcs) $(stdlib_rt)
+ @printf 'HAREC \t$@\n'
+ @mkdir -p $(HARECACHE)/unicode
+ @HARECACHE=$(HARECACHE) $(HAREC) $(HAREFLAGS) -o $@ -Nunicode \
+ -t$(HARECACHE)/unicode/unicode.td $(stdlib_unicode_srcs)
+
# rt
testlib_rt_srcs= \
$(STDLIB)/rt/$(PLATFORM)/env.ha \
@@ -782,6 +796,9 @@ hare_testlib_deps+=$(testlib_time)
testlib_types=$(TESTCACHE)/types/types.o
hare_testlib_deps+=$(testlib_types)
+testlib_unicode=$(TESTCACHE)/unicode/unicode.o
+hare_testlib_deps+=$(testlib_unicode)
+
# ascii
testlib_ascii_srcs= \
$(STDLIB)/ascii/ctype.ha \
@@ -1221,3 +1238,14 @@ $(TESTCACHE)/types/types.ssa: $(testlib_types_srcs) $(testlib_rt)
@HARECACHE=$(TESTCACHE) $(HAREC) $(TESTHAREFLAGS) -o $@ -Ntypes \
-t$(TESTCACHE)/types/types.td $(testlib_types_srcs)
+# unicode
+testlib_unicode_srcs= \
+ $(STDLIB)/unicode/properties.ha \
+ $(STDLIB)/unicode/unicode.ha
+
+$(TESTCACHE)/unicode/unicode.ssa: $(testlib_unicode_srcs) $(testlib_rt)
+ @printf 'HAREC \t$@\n'
+ @mkdir -p $(TESTCACHE)/unicode
+ @HARECACHE=$(TESTCACHE) $(HAREC) $(TESTHAREFLAGS) -o $@ -Nunicode \
+ -t$(TESTCACHE)/unicode/unicode.td $(testlib_unicode_srcs)
+
diff --git a/unicode/properties.ha b/unicode/properties.ha
@@ -0,0 +1,1130 @@
+// Unicode character blocks. See Blocks.txt in the UCD.
+export type blk = enum {
+ ADLAM,
+ AEGEAN_NUMBERS,
+ AHOM,
+ ALCHEMICAL,
+ ALPHABETIC_PF,
+ ANATOLIAN_HIEROGLYPHS,
+ ANCIENT_GREEK_MUSIC,
+ ANCIENT_GREEK_NUMBERS,
+ ANCIENT_SYMBOLS,
+ ARABIC,
+ ARABIC_EXT_A,
+ ARABIC_MATH,
+ ARABIC_PF_A,
+ ARABIC_PF_B,
+ ARABIC_SUP,
+ ARMENIAN,
+ ARROWS,
+ ASCII,
+ AVESTAN,
+ BALINESE,
+ BAMUM,
+ BAMUM_SUP,
+ BASSA_VAH,
+ BATAK,
+ BENGALI,
+ BHAIKSUKI,
+ BLOCK_ELEMENTS,
+ BOPOMOFO,
+ BOPOMOFO_EXT,
+ BOX_DRAWING,
+ BRAHMI,
+ BRAILLE,
+ BUGINESE,
+ BUHID,
+ BYZANTINE_MUSIC,
+ CARIAN,
+ CAUCASIAN_ALBANIAN,
+ CHAKMA,
+ CHAM,
+ CHEROKEE,
+ CHEROKEE_SUP,
+ CHESS_SYMBOLS,
+ CHORASMIAN,
+ CJK,
+ CJK_COMPAT,
+ CJK_COMPAT_FORMS,
+ CJK_COMPAT_IDEOGRAPHS,
+ CJK_COMPAT_IDEOGRAPHS_SUP,
+ CJK_EXT_A,
+ CJK_EXT_B,
+ CJK_EXT_C,
+ CJK_EXT_D,
+ CJK_EXT_E,
+ CJK_EXT_F,
+ CJK_EXT_G,
+ CJK_RADICALS_SUP,
+ CJK_STROKES,
+ CJK_SYMBOLS,
+ COMPAT_JAMO,
+ CONTROL_PICTURES,
+ COPTIC,
+ COPTIC_EPACT_NUMBERS,
+ COUNTING_ROD,
+ CUNEIFORM,
+ CUNEIFORM_NUMBERS,
+ CURRENCY_SYMBOLS,
+ CYPRIOT_SYLLABARY,
+ CYRILLIC,
+ CYRILLIC_EXT_A,
+ CYRILLIC_EXT_B,
+ CYRILLIC_EXT_C,
+ CYRILLIC_SUP,
+ DESERET,
+ DEVANAGARI,
+ DEVANAGARI_EXT,
+ DIACRITICALS,
+ DIACRITICALS_FOR_SYMBOLS,
+ DIACRITICALS_SUP,
+ DIACRITICALS_EXT,
+ DINGBATS,
+ DIVES_AKURU,
+ DOGRA,
+ DOMINO,
+ DUPLOYAN,
+ EARLY_DYNASTIC_CUNEIFORM,
+ EGYPTIAN_HIEROGLYPHS,
+ EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS,
+ ELBASAN,
+ ELYMAIC,
+ EMOTICONS,
+ ENCLOSED_ALPHANUM,
+ ENCLOSED_ALPHANUM_SUP,
+ ENCLOSED_CJK,
+ ENCLOSED_IDEOGRAPHIC_SUP,
+ ETHIOPIC,
+ ETHIOPIC_EXT,
+ ETHIOPIC_EXT_A,
+ ETHIOPIC_SUP,
+ GEOMETRIC_SHAPES,
+ GEOMETRIC_SHAPES_EXT,
+ GEORGIAN,
+ GEORGIAN_EXT,
+ GEORGIAN_SUP,
+ GLAGOLITIC,
+ GLAGOLITIC_SUP,
+ GOTHIC,
+ GRANTHA,
+ GREEK,
+ GREEK_EXT,
+ GUJARATI,
+ GUNJALA_GONDI,
+ GURMUKHI,
+ HALF_AND_FULL_FORMS,
+ HALF_MARKS,
+ HANGUL,
+ HANIFI_ROHINGYA,
+ HANUNOO,
+ HATRAN,
+ HEBREW,
+ HIGH_PU_SURROGATES,
+ HIGH_SURROGATES,
+ HIRAGANA,
+ IDC,
+ IDEOGRAPHIC_SYMBOLS,
+ IMPERIAL_ARAMAIC,
+ INDIC_NUMBER_FORMS,
+ INDIC_SIYAQ_NUMBERS,
+ INSCRIPTIONAL_PAHLAVI,
+ INSCRIPTIONAL_PARTHIAN,
+ IPA_EXT,
+ JAMO,
+ JAMO_EXT_A,
+ JAMO_EXT_B,
+ JAVANESE,
+ KAITHI,
+ KANA_EXT_A,
+ KANA_SUP,
+ KANBUN,
+ KANGXI,
+ KANNADA,
+ KATAKANA,
+ KATAKANA_EXT,
+ KAYAH_LI,
+ KHAROSHTHI,
+ KHITAN_SMALL_SCRIPT,
+ KHMER,
+ KHMER_SYMBOLS,
+ KHOJKI,
+ KHUDAWADI,
+ LAO,
+ LATIN_1_SUP,
+ LATIN_EXT_A,
+ LATIN_EXT_ADDITIONAL,
+ LATIN_EXT_B,
+ LATIN_EXT_C,
+ LATIN_EXT_D,
+ LATIN_EXT_E,
+ LEPCHA,
+ LETTERLIKE_SYMBOLS,
+ LIMBU,
+ LINEAR_A,
+ LINEAR_B_IDEOGRAMS,
+ LINEAR_B_SYLLABARY,
+ LISU,
+ LISU_SUP,
+ LOW_SURROGATES,
+ LYCIAN,
+ LYDIAN,
+ MAHAJANI,
+ MAHJONG,
+ MAKASAR,
+ MALAYALAM,
+ MANDAIC,
+ MANICHAEAN,
+ MARCHEN,
+ MASARAM_GONDI,
+ MATH_ALPHANUM,
+ MATH_OPERATORS,
+ MAYAN_NUMERALS,
+ MEDEFAIDRIN,
+ MEETEI_MAYEK,
+ MEETEI_MAYEK_EXT,
+ MENDE_KIKAKUI,
+ MEROITIC_CURSIVE,
+ MEROITIC_HIEROGLYPHS,
+ MIAO,
+ MISC_ARROWS,
+ MISC_MATH_SYMBOLS_A,
+ MISC_MATH_SYMBOLS_B,
+ MISC_PICTOGRAPHS,
+ MISC_SYMBOLS,
+ MISC_TECHNICAL,
+ MODI,
+ MODIFIER_LETTERS,
+ MODIFIER_TONE_LETTERS,
+ MONGOLIAN,
+ MONGOLIAN_SUP,
+ MRO,
+ MUSIC,
+ MULTANI,
+ MYANMAR,
+ MYANMAR_EXT_A,
+ MYANMAR_EXT_B,
+ NABATAEAN,
+ NANDINAGARI,
+ NB,
+ NEW_TAI_LUE,
+ NEWA,
+ NKO,
+ NUMBER_FORMS,
+ NUSHU,
+ NYIAKENG_PUACHUE_HMONG,
+ OCR,
+ OGHAM,
+ OL_CHIKI,
+ OLD_HUNGARIAN,
+ OLD_ITALIC,
+ OLD_NORTH_ARABIAN,
+ OLD_PERMIC,
+ OLD_PERSIAN,
+ OLD_SOGDIAN,
+ OLD_SOUTH_ARABIAN,
+ OLD_TURKIC,
+ ORIYA,
+ ORNAMENTAL_DINGBATS,
+ OSAGE,
+ OSMANYA,
+ OTTOMAN_SIYAQ_NUMBERS,
+ PAHAWH_HMONG,
+ PALMYRENE,
+ PAU_CIN_HAU,
+ PHAGS_PA,
+ PHAISTOS,
+ PHOENICIAN,
+ PHONETIC_EXT,
+ PHONETIC_EXT_SUP,
+ PLAYING_CARDS,
+ PSALTER_PAHLAVI,
+ PUA,
+ PUNCTUATION,
+ REJANG,
+ RUMI,
+ RUNIC,
+ SAMARITAN,
+ SAURASHTRA,
+ SHARADA,
+ SHAVIAN,
+ SHORTHAND_FORMAT_CONTROLS,
+ SIDDHAM,
+ SINHALA,
+ SINHALA_ARCHAIC_NUMBERS,
+ SMALL_FORMS,
+ SMALL_KANA_EXT,
+ SOGDIAN,
+ SORA_SOMPENG,
+ SOYOMBO,
+ SPECIALS,
+ SUNDANESE,
+ SUNDANESE_SUP,
+ SUP_ARROWS_A,
+ SUP_ARROWS_B,
+ SUP_ARROWS_C,
+ SUP_MATH_OPERATORS,
+ SUP_PUA_A,
+ SUP_PUA_B,
+ SUP_PUNCTUATION,
+ SUP_SYMBOLS_AND_PICTOGRAPHS,
+ SUPER_AND_SUB,
+ SUTTON_SIGNWRITING,
+ SYLOTI_NAGRI,
+ SYMBOLS_AND_PICTOGRAPHS_EXT_A,
+ SYMBOLS_FOR_LEGACY_COMPUTING,
+ SYRIAC,
+ SYRIAC_SUP,
+ TAGALOG,
+ TAGBANWA,
+ TAGS,
+ TAI_LE,
+ TAI_THAM,
+ TAI_VIET,
+ TAI_XUAN_JING,
+ TAKRI,
+ TAMIL,
+ TAMIL_SUP,
+ TANGUT,
+ TANGUT_COMPONENTS,
+ TANGUT_SUP,
+ TELUGU,
+ THAANA,
+ THAI,
+ TIBETAN,
+ TIFINAGH,
+ TIRHUTA,
+ TRANSPORT_AND_MAP,
+ UCAS,
+ UCAS_EXT,
+ UGARITIC,
+ VAI,
+ VEDIC_EXT,
+ VERTICAL_FORMS,
+ VS,
+ VS_SUP,
+ WANCHO,
+ WARANG_CITI,
+ YEZIDI,
+ YI_RADICALS,
+ YI_SYLLABLES,
+ YIJING,
+ ZANABAZAR_SQUARE,
+};
+
+// Unicode general character categories. See Unicode section 4.5.
+export type gc = enum {
+ // Letter, uppercase
+ LU,
+ // Letter, lowercase
+ LL,
+ // Letter, titlecase
+ LT,
+ // Letter, modifier
+ LM,
+ // Letter, other
+ LO,
+ // Mark, nonspacing
+ MN,
+ // Mark, spacing combining
+ MC,
+ // Mark, enclosing
+ ME,
+ // Number, decimal digit
+ ND,
+ // Number, letter
+ NL,
+ // Number, other
+ NO,
+ // Punctuation, connector
+ PC,
+ // Punctuation, dash
+ PD,
+ // Punctuation, open
+ PS,
+ // Punctuation, close
+ PE,
+ // Punctuation, initial quote
+ PI,
+ // Punctuation, final quote
+ PF,
+ // Punctuation, other
+ PO,
+ // Symbol, math
+ SM,
+ // Symbol, currency
+ SC,
+ // Symbol, modifier
+ SK,
+ // Symbol, other
+ SO,
+ // Separator, space
+ ZS,
+ // Separator, line
+ ZL,
+ // Separator, paragraph
+ ZP,
+ // Other, control
+ CC,
+ // Other, format
+ CF,
+ // Other, surrogate
+ CS,
+ // Other, private use
+ CO,
+ // Other, not assigned (including noncharacters)
+ CN,
+};
+
+// Bidirectional class. See UAX #9.
+export type bc = enum {
+ // Right-to-left (Arabic)
+ AL,
+ // Arabic number
+ AN,
+ // Paragraph separator
+ B,
+ // Boundary neutral
+ BN,
+ // Common number separator
+ CS,
+ // European number
+ EN,
+ // European number separator
+ ES,
+ // Euromean number terminator
+ ET,
+ // First strong isolate
+ FSI,
+ // Left-to-right
+ L,
+ // Left-to-right embedding
+ LRE,
+ // Right-to-left isolate
+ LRI,
+ // Left-to-right override
+ LRO,
+ // Nonspacing mark
+ NSM,
+ // Other neutrals
+ ON,
+ // Pop directional format
+ PDF,
+ // Pop directional isolate
+ PDI,
+ // Right-to-left
+ R,
+ // Right-to-left embedding
+ RLE,
+ // Right-to-left isolate
+ RLI,
+ // Right-to-left override
+ RLO,
+ // Segment separator
+ S,
+ // Whitespace
+ WS,
+};
+
+// Bidi paired bracket type. See BidiBrackets.txt in the UCD.
+export type bpt = enum {
+ // Open
+ O,
+ // Closed
+ C,
+ // None
+ N,
+};
+
+// Decomposition type. See UAX #44, section 5.7.3.
+export type dt = enum {
+ // Canonical mapping
+ CAN,
+ // Otherwise unspecified compatibility character
+ COM,
+ // Encircled form
+ ENC,
+ // Final presentation form (Arabic)
+ FIN,
+ // Font variant (for example, a blackletter form)
+ FONT,
+ // Vulgar fraction form
+ FRA,
+ // Initial presentation form (Arabic)
+ INIT,
+ // Isolated presentation form (Arabic)
+ ISO,
+ // Medial presentation form (Arabic)
+ MED,
+ // Narrow (or hankaku) compatibility character
+ NAR,
+ // No-break version of a space or hyphen
+ NB,
+ // Small variant form (CNS compatibility)
+ SML,
+ // CJK squared font variant
+ SQR,
+ // Subscript form
+ SUB,
+ // Superscript form
+ SUP,
+ // Vertical layout presentation form
+ VERT,
+ // Wide (or zenkaku) compatibility character
+ WIDE,
+ // None
+ NONE,
+};
+
+// Normalization quick-check properties. See UAX #44, section 5.7.5.
+export type quickcheck = enum uint {
+ NO = 0b00,
+ MAYBE = 0b01,
+ YES = 0b11,
+};
+
+// Numeric type. See Unicode section 4.6.
+export type nt = enum {
+ // Non-numeric
+ NONE,
+ // Decimal
+ DE,
+ // Digit
+ DI,
+ // Numeric
+ NU,
+};
+
+// Character joining class. See Unicode section 9.2.
+export type jt = enum {
+ // Non-joining
+ U,
+ // Join causing
+ C,
+ // Transparent
+ T,
+ // Dual joining
+ D,
+ // Left joining
+ L,
+ // Right joining
+ R,
+};
+
+// Character joining group. See Unicode section 9.2.
+export type jg = enum {
+ AFRICAN_FEH,
+ AFRICAN_NOON,
+ AFRICAN_QAF,
+ AIN,
+ ALAPH,
+ ALEF,
+ ALEF_MAQSURAH,
+ BEH,
+ BETH,
+ BURUSHASKI_YEH_BARREE,
+ DAL,
+ DALATH_RISH,
+ E,
+ FARSI_YEH,
+ FE,
+ FEH,
+ FINAL_SEMKATH,
+ GAF,
+ GAMAL,
+ HAH,
+ HAMZA_ON_HEH_GOAL,
+ HE,
+ HEH,
+ HEH_GOAL,
+ HETH,
+ HANIFI_ROHINGYA_KINNA_YA,
+ HANIFI_ROHINGYA_PA,
+ KAF,
+ KAPH,
+ KHAPH,
+ KNOTTED_HEH,
+ LAM,
+ LAMADH,
+ MALAYALAM_NGA,
+ MALAYALAM_JA,
+ MALAYALAM_NYA,
+ MALAYALAM_TTA,
+ MALAYALAM_NNA,
+ MALAYALAM_NNNA,
+ MALAYALAM_BHA,
+ MALAYALAM_RA,
+ MALAYALAM_LLA,
+ MALAYALAM_LLLA,
+ MALAYALAM_SSA,
+ MANICHAEAN_ALEPH,
+ MANICHAEAN_AYIN,
+ MANICHAEAN_BETH,
+ MANICHAEAN_DALETH,
+ MANICHAEAN_DHAMEDH,
+ MANICHAEAN_FIVE,
+ MANICHAEAN_GIMEL,
+ MANICHAEAN_HETH,
+ MANICHAEAN_HUNDRED,
+ MANICHAEAN_KAPH,
+ MANICHAEAN_LAMEDH,
+ MANICHAEAN_MEM,
+ MANICHAEAN_NUN,
+ MANICHAEAN_ONE,
+ MANICHAEAN_PE,
+ MANICHAEAN_QOPH,
+ MANICHAEAN_RESH,
+ MANICHAEAN_SADHE,
+ MANICHAEAN_SAMEKH,
+ MANICHAEAN_TAW,
+ MANICHAEAN_TEN,
+ MANICHAEAN_TETH,
+ MANICHAEAN_THAMEDH,
+ MANICHAEAN_TWENTY,
+ MANICHAEAN_WAW,
+ MANICHAEAN_YODH,
+ MANICHAEAN_ZAYIN,
+ MEEM,
+ MIM,
+ NO_JOINING_GROUP,
+ NOON,
+ NUN,
+ NYA,
+ PE,
+ QAF,
+ QAPH,
+ REH,
+ REVERSED_PE,
+ ROHINGYA_YEH,
+ SAD,
+ SADHE,
+ SEEN,
+ SEMKATH,
+ SHIN,
+ STRAIGHT_WAW,
+ SWASH_KAF,
+ SYRIAC_WAW,
+ TAH,
+ TAW,
+ TEH_MARBUTA,
+ TEH_MARBUTA_GOAL,
+ TETH,
+ WAW,
+ YEH,
+ YEH_BARREE,
+ YEH_WITH_TAIL,
+ YUDH,
+ YUDH_HE,
+ ZAIN,
+ ZHAIN,
+};
+
+// Line breaking properties. See UAX #14.
+export type lb = enum {
+ // Ambiguous
+ AI,
+ // Alphabetic
+ AL,
+ // Break opportunity before and after
+ B2,
+ // Break after
+ BA,
+ // Break before
+ BB,
+ // Mandatory break
+ BK,
+ // Contingent break opportunity
+ CB,
+ // Conditional Japanese starter
+ CJ,
+ // Close punctuation
+ CL,
+ // Combining mark
+ CM,
+ // Close parenthesis
+ CP,
+ // Carriage return
+ CR,
+ // Emoji base
+ EB,
+ // Emoji modifier
+ EM,
+ // Exclamation/interrogation
+ EX,
+ // Non-breaking ("glue")
+ GL,
+ // Hangul LV syllable
+ H2,
+ // Hangul LVT syllable
+ H3,
+ // Hebrew letter
+ HL,
+ // Hyphen
+ HY,
+ // Ideographic
+ ID,
+ // Inseparable
+ IN,
+ // Infix numeric separator
+ IS,
+ // Hangul L Jamo
+ JL,
+ // Hangul T Jamo
+ JT,
+ // Hangul V Jamo
+ JV,
+ // Line feed
+ LF,
+ // Next line
+ NL,
+ // Nonstarter
+ NS,
+ // Numeric
+ NU,
+ // Open punctuation
+ OP,
+ // Postfix numeric
+ PO,
+ // Prefix numeric
+ PR,
+ // Quotation
+ QU,
+ // Regional indicator
+ RI,
+ // Complex context dependent (South East Asian)
+ SA,
+ // Surrogate
+ SG,
+ // Space
+ SP,
+ // Symbols allowing break after
+ SY,
+ // Word joiner
+ WJ,
+ // Unknown
+ XX,
+ // Zero width space
+ ZW,
+ // Zero width joiner
+ ZWJ,
+};
+
+// East-asian width. See UAX #11.
+export type ea = enum {
+ // Ambiguous
+ A,
+ // Fullwidth
+ F,
+ // Halfwidth
+ H,
+ // Neutral
+ N,
+ // Narrow
+ NA,
+ // Wide
+ W,
+};
+
+// Case property. See Unicode section 4.2.
+export type case = enum uint {
+ UPPER = 1 << 0,
+ LOWER = 1 << 1,
+ OTHER_UPPER = 1 << 2,
+ OTHER_LOWER = 1 << 3,
+};
+
+// Casing attributes. See Unicode section 4.2.
+export type case_attrs = enum uint {
+ // Case ignorable
+ CI = 1 << 0,
+ // Cased
+ CASED = 1 << 1,
+ // Changes when casefolded
+ CWCF = 1 << 2,
+ // Changes when casemapped
+ CWCM = 1 << 3,
+ // Changes when lowercased
+ CWL = 1 << 4,
+ // Changes when NFKC casefolded
+ CWKCF = 1 << 5,
+ // Changes when titlecased
+ CWT = 1 << 6,
+ // Changes when uppercased
+ CWU = 1 << 7,
+ // NFKC casefold
+ NFKC_CF = 1 << 8,
+};
+
+// Script property. See UAX #24.
+export type script = enum {
+ ADLM,
+ AGHB,
+ AHOM,
+ ARAB,
+ ARMI,
+ ARMN,
+ AVST,
+ BALI,
+ BAMU,
+ BASS,
+ BATK,
+ BENG,
+ BHKS,
+ BOPO,
+ BRAH,
+ BRAI,
+ BUGI,
+ BUHD,
+ CAKM,
+ CANS,
+ CARI,
+ CHAM,
+ CHER,
+ CHRS,
+ COPT,
+ CPRT,
+ CYRL,
+ DEVA,
+ DIAK,
+ DOGR,
+ DSRT,
+ DUPL,
+ ELBA,
+ ELYM,
+ EGYP,
+ ETHI,
+ GEOR,
+ GLAG,
+ GONG,
+ GONM,
+ GOTH,
+ GRAN,
+ GREK,
+ GUJR,
+ GURU,
+ HANG,
+ HANI,
+ HANO,
+ HATR,
+ HEBR,
+ HIRA,
+ HLUW,
+ HMNG,
+ HMNP,
+ HRKT,
+ HUNG,
+ ITAL,
+ JAVA,
+ KALI,
+ KANA,
+ KHAR,
+ KHMR,
+ KHOJ,
+ KITS,
+ KNDA,
+ KTHI,
+ LANA,
+ LAOO,
+ LATN,
+ LEPC,
+ LIMB,
+ LINA,
+ LINB,
+ LISU,
+ LYCI,
+ LYDI,
+ MAHJ,
+ MAKA,
+ MAND,
+ MANI,
+ MARC,
+ MEDF,
+ MEND,
+ MERC,
+ MERO,
+ MLYM,
+ MODI,
+ MONG,
+ MROO,
+ MTEI,
+ MULT,
+ MYMR,
+ NAND,
+ NARB,
+ NBAT,
+ NEWA,
+ NKOO,
+ NSHU,
+ OGAM,
+ OLCK,
+ ORKH,
+ ORYA,
+ OSGE,
+ OSMA,
+ PALM,
+ PAUC,
+ PERM,
+ PHAG,
+ PHLI,
+ PHLP,
+ PHNX,
+ PLRD,
+ PRTI,
+ QAAI,
+ ROHG,
+ RJNG,
+ RUNR,
+ SAMR,
+ SARB,
+ SAUR,
+ SGNW,
+ SHAW,
+ SHRD,
+ SIDD,
+ SIND,
+ SINH,
+ SOGD,
+ SOGO,
+ SORA,
+ SOYO,
+ SUND,
+ SYLO,
+ SYRC,
+ TAGB,
+ TAKR,
+ TALE,
+ TALU,
+ TAML,
+ TANG,
+ TAVT,
+ TELU,
+ TFNG,
+ TGLG,
+ THAA,
+ THAI,
+ TIBT,
+ TIRH,
+ UGAR,
+ VAII,
+ WARA,
+ WCHO,
+ XPEO,
+ XSUX,
+ YEZI,
+ YIII,
+ ZANB,
+ ZINH,
+ ZYYY,
+ ZZZZ,
+};
+
+// Hangul syllable type. See Unicode section 3.12 and 18.6.
+export type hst = enum {
+ // Leading consonant
+ L,
+ // LV syllable
+ LV,
+ // LVT syllable
+ LVT,
+ // Trailing consonant
+ T,
+ // Vowel
+ V,
+ // Non-applicable
+ NA,
+};
+
+// Indic syllabic category. See IndicSyllabicCategory.txt in the UCD.
+export type insc = enum {
+ AVAGRAHA,
+ BINDU,
+ BRAHMI_JOINING_NUMBER,
+ CANTILLATION_MARK,
+ CONSONANT,
+ CONSONANT_DEAD,
+ CONSONANT_FINAL,
+ CONSONANT_HEAD_LETTER,
+ CONSONANT_INITIAL_POSTFIXED,
+ CONSONANT_KILLER,
+ CONSONANT_MEDIAL,
+ CONSONANT_PLACEHOLDER,
+ CONSONANT_PRECEDING_REPHA,
+ CONSONANT_PREFIXED,
+ CONSONANT_REPHA,
+ CONSONANT_SUBJOINED,
+ CONSONANT_SUCCEEDING_REPHA,
+ CONSONANT_WITH_STACKER,
+ GEMINATION_MARK,
+ INVISIBLE_STACKER,
+ JOINER,
+ MODIFYING_LETTER,
+ NON_JOINER,
+ NUKTA,
+ NUMBER,
+ NUMBER_JOINER,
+ OTHER,
+ PURE_KILLER,
+ REGISTER_SHIFTER,
+ SYLLABLE_MODIFIER,
+ TONE_LETTER,
+ TONE_MARK,
+ VIRAMA,
+ VISARGA,
+ VOWEL,
+ VOWEL_DEPENDENT,
+ VOWEL_INDEPENDENT,
+};
+
+// Indic positional category. See IndicPositionalCategory.txt in the UCD.
+export type inpc = enum {
+ BOTTOM,
+ BOTTOM_AND_LEFT,
+ BOTTOM_AND_RIGHT,
+ LEFT,
+ LEFT_AND_RIGHT,
+ NA,
+ OVERSTRUCK,
+ RIGHT,
+ TOP,
+ TOP_AND_BOTTOM,
+ TOP_AND_BOTTOM_AND_LEFT,
+ TOP_AND_BOTTOM_AND_RIGHT,
+ TOP_AND_LEFT,
+ TOP_AND_LEFT_AND_RIGHT,
+ TOP_AND_RIGHT,
+ VISUAL_ORDER_LEFT,
+};
+
+// Identifier and pattern properties. See UAX #31.
+export type id = enum uint {
+ IDS = 1 << 0,
+ IDC = 1 << 1,
+ OIDS = 1 << 2,
+ OIDC = 1 << 2,
+ XIDS = 1 << 3,
+ XIDC = 1 << 4,
+ SYN = 1 << 5,
+ WS = 1 << 6,
+};
+
+// Properties related to function and graphics characteristics. This is a
+// synethetic type based on mulitple Unicode properties listed in UAX #42
+// section 4.4.10.
+export type fgc = enum uint {
+ DASH = 1 << 0,
+ HYPHEN = 1 << 1,
+ QUOTATION_MARK = 1 << 2,
+ TERMINAL_PUNCTUATION = 1 << 3,
+ SENTENCE_TERMINAL = 1 << 4,
+ DIACRITIC = 1 << 5,
+ EXTENDER = 1 << 6,
+ SOFT_DOTTED = 1 << 7,
+ ALPHABETIC = 1 << 8,
+ OTHER_ALPHABETIC = 1 << 9,
+ MATH = 1 << 10,
+ OTHER_MATH = 1 << 11,
+ HEX_DIGIT = 1 << 12,
+ ASCII_HEX_DIGIT = 1 << 13,
+ DEFAULT_IGNORABLE_CODE_POINT = 1 << 14,
+ OTHER_DEFAULT_IGNORABLE_CODE_POINT = 1 << 15,
+ LOGICAL_ORDER_EXCEPTION = 1 << 16,
+ PREPENDED_CONCATENATION_MARK = 1 << 17,
+ WHITE_SPACE = 1 << 18,
+ VERTICAL_ORIENTATION = 1 << 19,
+ REGIONAL_INDICATOR = 1 << 20,
+};
+
+// Properties related to boundaries. This is a synethetic type based on mulitple
+// Unicode properties listed in UAX #42 section 4.4.20.
+export type gr = enum uint {
+ GR_BASE = 1 << 0,
+ GR_EXT = 1 << 1,
+};
+
+// Grapheme cluster break. See UAX #29.
+export type gcb = enum {
+ XX,
+ CN,
+ CR,
+ EX,
+ L,
+ LF,
+ LV,
+ LVT,
+ PP,
+ RI,
+ SM,
+ T,
+ V,
+ ZWJ,
+};
+
+// Word break. See UAX #29.
+export type wb = enum {
+ XX,
+ CR,
+ DQ,
+ EX,
+ EXTEND,
+ FO,
+ HL,
+ KA,
+ LE,
+ LF,
+ MB,
+ ML,
+ MN,
+ NL,
+ NU,
+ RI,
+ SQ,
+ WSEGSPACE,
+ ZWJ,
+};
+
+// Sentence break. See UAX #29.
+export type sb = enum {
+ XX,
+ AT,
+ CL,
+ CR,
+ EX,
+ FO,
+ LE,
+ LF,
+ LO,
+ NU,
+ SC,
+ SE,
+ SP,
+ ST,
+ UP,
+};
+
+// Properties related to ideographs. This is a synethetic type based on mulitple
+// Unicode properties listed in UAX #42 section 4.4.21.
+export type ideo = enum uint {
+ IDEO = 1 << 1,
+ UIDEO = 1 << 2,
+ IDSB = 1 << 3,
+ IDST = 1 << 4,
+ RADICAL = 1 << 5,
+};
+
+// Miscellaneous properties. This is a synethetic type based on mulitple Unicode
+// properties listed in UAX #42 section 4.4.22.
+export type misc = enum uint {
+ DEP = 1 << 0,
+ VS = 1 << 1,
+ NCHAR = 1 << 2,
+};
+
+// Properties related to Emoji. This is a synethetic type based on mulitple
+// Unicode properties listed in UAX #42 section 4.4.26.
+export type emoji = enum uint {
+ EMOJI = 1 << 0,
+ EPRES = 1 << 1,
+ EMOD = 1 << 2,
+ EBASE = 1 << 3,
+ ECOMP = 1 << 4,
+ EXTPICT = 1 << 5,
+};
diff --git a/unicode/unicode.ha b/unicode/unicode.ha
@@ -0,0 +1,32 @@
+// This module provides Unicode support for Hare programs.
+//
+// Programs which deal with basic text manipulation are likely to be served
+// sufficiently by the [encoding::utf8], [strings], [ascii], and so on. For
+// example, the question of "is this character uppercase?" is often sufficiently
+// answered with [ascii::isupper], and matters such as Unicode string
+// equivalence are often fraught with error potential - for example, a
+// vulnerability was once found in a web login form which used a Unicode
+// equivalence comparison on usernames, allowing a malicious actor to register a
+// username which was bytewise distinct but uniwise equal to a victim, and then
+// use it to log into their account. This module also contains a copy of the
+// Unicode Character Database, which is rather large, and linking to it will
+// increase the size of your binaries.
+//
+// The purpose of this module is not to handle every day string manipulation,
+// but instead to provide support code for software which is explicitly aware of
+// internationalization concerns and seeking out functions which specifically
+// address those concerns.
+//
+// This module makes little attempt to be useful without a broader understanding
+// of Unicode. The module is close to a 1:1 implementation of the Unicode
+// standard, and it is recommended that any reading of this module's API or
+// source code is accompanied by a reading of the Unicode standard. The
+// documentation for each type and function makes an effort to direct the reader
+// to the appropriate part of the Unicode standard.
+//
+// See the [i18n] module for a high-level internationalization API.
+//
+// The present implementation of this module conforms to Unicode 13.0.0, which
+// was released on March 11th, 2020.
+
+def x: int = 0; // TEMP
