1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153
|
{-# LANGUAGE BangPatterns, DeriveDataTypeable, FlexibleInstances,
ForeignFunctionInterface, FunctionalDependencies, MultiParamTypeClasses #-}
-- |
-- Module : Data.Text.ICU.Char
-- Copyright : (c) 2010 Bryan O'Sullivan
--
-- License : BSD-style
-- Maintainer : bos@serpentine.com
-- Stability : experimental
-- Portability : GHC
--
-- Access to the Unicode Character Database, implemented as bindings
-- to the International Components for Unicode (ICU) libraries.
--
-- Unicode assigns each code point (not just assigned character) values for
-- many properties. Most are simple boolean flags, or constants from a
-- small enumerated list. For some, values are relatively more complex
-- types.
--
-- For more information see \"About the Unicode Character Database\"
-- <http://www.unicode.org/ucd/> and the ICU User Guide chapter on
-- Properties <http://icu-project.org/userguide/properties.html>.
module Data.Text.ICU.Char
(
-- * Working with character properties
-- $properties
Property
-- * Property identifier types
, BidiClass_(..)
, Block_(..)
, Bool_(..)
, Decomposition_(..)
, EastAsianWidth_(..)
, GeneralCategory_(..)
, HangulSyllableType_(..)
, JoiningGroup_(..)
, JoiningType_(..)
, NumericType_(..)
-- ** Combining class
, CanonicalCombiningClass_(..)
, LeadCanonicalCombiningClass_(..)
, TrailingCanonicalCombiningClass_(..)
-- ** Normalization checking
, NFCQuickCheck_(..)
, NFDQuickCheck_(..)
, NFKCQuickCheck_(..)
, NFKDQuickCheck_(..)
-- ** Text boundaries
, GraphemeClusterBreak_(..)
, LineBreak_(..)
, SentenceBreak_(..)
, WordBreak_(..)
-- * Property value types
, BlockCode(..)
, Direction(..)
, Decomposition(..)
, EastAsianWidth(..)
, GeneralCategory(..)
, HangulSyllableType(..)
, JoiningGroup(..)
, JoiningType(..)
, NumericType(..)
-- ** Text boundaries
, GraphemeClusterBreak(..)
, LineBreak(..)
, SentenceBreak(..)
, WordBreak(..)
-- * Functions
, blockCode
, charFullName
, charName
, charFromFullName
, charFromName
, combiningClass
, direction
, property
, isMirrored
, mirror
-- ** Conversion to numbers
, digitToInt
, numericValue
) where
#include <unicode/uchar.h>
import Control.DeepSeq (NFData(..))
import Data.Char (chr, ord)
import Data.Int (Int32)
import Data.Text.ICU.Error (u_INVALID_CHAR_FOUND)
import Data.Text.ICU.Error.Internal (UErrorCode, handleOverflowError, withError)
import Data.Text.ICU.Internal (UBool, UChar32, asBool)
import Data.Text.ICU.Normalize.Internal (toNCR)
import Data.Typeable (Typeable)
import Data.Word (Word8)
import Foreign.C.String (CString, peekCStringLen, withCString)
import Foreign.C.Types (CInt(..))
import Foreign.Ptr (Ptr)
import System.IO.Unsafe (unsafePerformIO)
-- $properties
--
-- The 'property' function provides the main view onto the Unicode Character
-- Database. Because Unicode character properties have a variety of types,
-- the 'property' function is polymorphic. The type of its first argument
-- dictates the type of its result, by use of the 'Property' typeclass.
--
-- For instance, @'property' 'Alphabetic'@ returns a 'Bool', while @'property'
-- 'NFCQuickCheck'@ returns a @'Maybe' 'Bool'@.
-- | The language directional property of a character set.
data Direction =
LeftToRight
| RightToLeft
| EuropeanNumber
| EuropeanNumberSeparator
| EuropeanNumberTerminator
| ArabicNumber
| CommonNumberSeparator
| BlockSeparator
| SegmentSeparator
| WhiteSpaceNeutral
| OtherNeutral
| LeftToRightEmbedding
| LeftToRightOverride
| RightToLeftArabic
| RightToLeftEmbedding
| RightToLeftOverride
| PopDirectionalFormat
| DirNonSpacingMark
| BoundaryNeutral
deriving (Eq, Enum, Show, Typeable)
instance NFData Direction where
rnf !_ = ()
-- | Descriptions of Unicode blocks.
data BlockCode =
NoBlock
| BasicLatin
| Latin1Supplement
| LatinExtendedA
| LatinExtendedB
| IPAExtensions
| SpacingModifierLetters
| CombiningDiacriticalMarks
| GreekAndCoptic
| Cyrillic
| Armenian
| Hebrew
| Arabic
| Syriac
| Thaana
| Devanagari
| Bengali
| Gurmukhi
| Gujarati
| Oriya
| Tamil
| Telugu
| Kannada
| Malayalam
| Sinhala
| Thai
| Lao
| Tibetan
| Myanmar
| Georgian
| HangulJamo
| Ethiopic
| Cherokee
| UnifiedCanadianAboriginalSyllabics
| Ogham
| Runic
| Khmer
| Mongolian
| LatinExtendedAdditional
| GreekExtended
| GeneralPunctuation
| SuperscriptsAndSubscripts
| CurrencySymbols
| CombiningDiacriticalMarksForSymbols
| LetterlikeSymbols
| NumberForms
| Arrows
| MathematicalOperators
| MiscellaneousTechnical
| ControlPictures
| OpticalCharacterRecognition
| EnclosedAlphanumerics
| BoxDrawing
| BlockElements
| GeometricShapes
| MiscellaneousSymbols
| Dingbats
| BraillePatterns
| CJKRadicalsSupplement
| KangxiRadicals
| IdeographicDescriptionCharacters
| CJKSymbolsAndPunctuation
| Hiragana
| Katakana
| Bopomofo
| HangulCompatibilityJamo
| Kanbun
| BopomofoExtended
| EnclosedCJKLettersAndMonths
| CJKCompatibility
| CJKUnifiedIdeographsExtensionA
| CJKUnifiedIdeographs
| YiSyllables
| YiRadicals
| HangulSyllables
| HighSurrogates
| HighPrivateUseSurrogates
| LowSurrogates
| PrivateUseArea
| CJKCompatibilityIdeographs
| AlphabeticPresentationForms
| ArabicPresentationFormsA
| CombiningHalfMarks
| CJKCompatibilityForms
| SmallFormVariants
| ArabicPresentationFormsB
| Specials
| HalfwidthAndFullwidthForms
| OldItalic
| Gothic
| Deseret
| ByzantineMusicalSymbols
| MusicalSymbols
| MathematicalAlphanumericSymbols
| CJKUnifiedIdeographsExtensionB
| CJKCompatibilityIdeographsSupplement
| Tags
| CyrillicSupplement
| Tagalog
| Hanunoo
| Buhid
| Tagbanwa
| MiscellaneousMathematicalSymbolsA
| SupplementalArrowsA
| SupplementalArrowsB
| MiscellaneousMathematicalSymbolsB
| SupplementalMathematicalOperators
| KatakanaPhoneticExtensions
| VariationSelectors
| SupplementaryPrivateUseAreaA
| SupplementaryPrivateUseAreaB
| Limbu
| TaiLe
| KhmerSymbols
| PhoneticExtensions
| MiscellaneousSymbolsAndArrows
| YijingHexagramSymbols
| LinearBSyllabary
| LinearBIdeograms
| AegeanNumbers
| Ugaritic
| Shavian
| Osmanya
| CypriotSyllabary
| TaiXuanJingSymbols
| VariationSelectorsSupplement
| AncientGreekMusicalNotation
| AncientGreekNumbers
| ArabicSupplement
| Buginese
| CJKStrokes
| CombiningDiacriticalMarksSupplement
| Coptic
| EthiopicExtended
| EthiopicSupplement
| GeorgianSupplement
| Glagolitic
| Kharoshthi
| ModifierToneLetters
| NewTaiLue
| OldPersian
| PhoneticExtensionsSupplement
| SupplementalPunctuation
| SylotiNagri
| Tifinagh
| VerticalForms
| N'Ko
| Balinese
| LatinExtendedC
| LatinExtendedD
| PhagsPa
| Phoenician
| Cuneiform
| CuneiformNumbersAndPunctuation
| CountingRodNumerals
| Sundanese
| Lepcha
| OlChiki
| CyrillicExtendedA
| Vai
| CyrillicExtendedB
| Saurashtra
| KayahLi
| Rejang
| Cham
| AncientSymbols
| PhaistosDisc
| Lycian
| Carian
| Lydian
| MahjongTiles
| DominoTiles
| Samaritan
| UnifiedCanadianAboriginalSyllabicsExtended
| TaiTham
| VedicExtensions
| Lisu
| Bamum
| CommonIndicNumberForms
| DevanagariExtended
| HangulJamoExtendedA
| Javanese
| MyanmarExtendedA
| TaiViet
| MeeteiMayek
| HangulJamoExtendedB
| ImperialAramaic
| OldSouthArabian
| Avestan
| InscriptionalParthian
| InscriptionalPahlavi
| OldTurkic
| RumiNumeralSymbols
| Kaithi
| EgyptianHieroglyphs
| EnclosedAlphanumericSupplement
| EnclosedIdeographicSupplement
| CJKUnifiedIdeographsExtensionC
| Mandaic
| Batak
| EthiopicExtendedA
| Brahmi
| BamumSupplement
| KanaSupplement
| PlayingCards
| MiscellaneousSymbolsAndPictographs
| Emoticons
| TransportAndMapSymbols
| AlchemicalSymbols
| CJKUnifiedIdeographsExtensionD
| ArabicExtendedA
| ArabicMathematicalAlphabeticSymbols
| Chakma
| MeeteiMayekExtensions
| MeroiticCursive
| MeroiticHieroglyphs
| Miao
| Sharada
| SoraSompeng
| SundaneseSupplement
| Takri
| BassaVah
| CaucasianAlbanian
| CopticEpactNumbers
| CombiningDiacriticalMarksExtended
| Duployan
| Elbasan
| GeometricShapesExtended
| Grantha
| Khojki
| Khudawadi
| LatinExtendedE
| LinearA
| Mahajani
| Manichaean
| MendeKikakui
| Modi
| Mro
| MyanmarExtendedB
| Nabataean
| OldNorthArabian
| OldPermic
| OrnamentalDingbats
| PahawhHmong
| Palmyrene
| PauCinHau
| PsalterPahlavi
| ShorthandFormatControls
| Siddham
| SinhalaArchaicNumbers
| SupplementalArrowsC
| Tirhuta
| WarangCiti
| Ahom
| AnatolianHieroglyphs
| CherokeeSupplement
| CJKUnifiedIdeographsExtensionE
| EarlyDynasticCuneiform
| Hatran
| Multani
| OldHungarian
| SupplementalSymbolsAndPictographs
| SuttonSignwriting
| Adlam
| Bhaiksuki
| CyrillicExtendedC
| GlagoliticSupplement
| IdeographicSymbolsAndPunctuation
| Marchen
| MongolianSupplement
| Newa
| Osage
| Tangut
| TangutComponents
| CJKUnifiedIdeographsExtensionF
| KanaExtendedA
| MasaramGondi
| Nushu
| Soyombo
| SyriacSupplement
| ZanzabarSquare
deriving (Eq, Enum, Bounded, Show, Typeable)
instance NFData BlockCode where
rnf !_ = ()
data Bool_ =
Alphabetic
| ASCIIHexDigit
-- ^ 0-9, A-F, a-f
| BidiControl
-- ^ Format controls which have specific functions in the Bidi Algorithm.
| BidiMirrored
-- ^ Characters that may change display in RTL text.
| Dash
-- ^ Variations of dashes.
| DefaultIgnorable
-- ^ Ignorable in most processing.
| Deprecated
-- ^ The usage of deprecated characters is strongly discouraged.
| Diacritic
-- ^ Characters that linguistically modify the meaning of another
-- character to which they apply.
| Extender
-- ^ Extend the value or shape of a preceding alphabetic character,
-- e.g. length and iteration marks.
| FullCompositionExclusion
| GraphemeBase
-- ^ For programmatic determination of grapheme cluster boundaries.
| GraphemeExtend
-- ^ For programmatic determination of grapheme cluster boundaries.
| GraphemeLink
-- ^ For programmatic determination of grapheme cluster boundaries.
| HexDigit
-- ^ Characters commonly used for hexadecimal numbers.
| Hyphen
-- ^ Dashes used to mark connections between pieces of words, plus the
-- Katakana middle dot.
| IDContinue
-- ^ Characters that can continue an identifier.
| IDStart
-- ^ Characters that can start an identifier.
| Ideographic
-- ^ CJKV ideographs.
| IDSBinaryOperator
-- ^ For programmatic determination of Ideographic Description Sequences.
| IDSTrinaryOperator
| JoinControl
-- ^ Format controls for cursive joining and ligation.
| LogicalOrderException
-- ^ Characters that do not use logical order and require special handling
-- in most processing.
| Lowercase
| Math
| NonCharacter
-- ^ Code points that are explicitly defined as illegal for the encoding
-- of characters.
| QuotationMark
| Radical
-- ^ For programmatic determination of Ideographic Description Sequences.
| SoftDotted
-- ^ Characters with a "soft dot", like i or j. An accent placed on these
-- characters causes the dot to disappear.
| TerminalPunctuation
-- ^ Punctuation characters that generally mark the end of textual units.
| UnifiedIdeograph
-- ^ For programmatic determination of Ideographic Description Sequences.
| Uppercase
| WhiteSpace
| XidContinue
-- ^ 'IDContinue' modified to allow closure under normalization forms
-- NFKC and NFKD.
| XidStart
-- ^ 'IDStart' modified to allow closure under normalization forms NFKC
-- and NFKD.
| CaseSensitive
-- ^ Either the source of a case mapping or /in/ the target of a case
-- mapping. Not the same as the general category @Cased_Letter@.
| STerm
-- ^ Sentence Terminal. Used in UAX #29: Text Boundaries
-- <http://www.unicode.org/reports/tr29/>.
| VariationSelector
-- ^ Indicates all those characters that qualify as Variation
-- Selectors. For details on the behavior of these characters, see
-- <http://unicode.org/Public/UNIDATA/StandardizedVariants.html> and 15.6
-- Variation Selectors.
| NFDInert
-- ^ ICU-specific property for characters that are inert under NFD, i.e.
-- they do not interact with adjacent characters. Used for example in
-- normalizing transforms in incremental mode to find the boundary of
-- safely normalizable text despite possible text additions.
| NFKDInert
-- ^ ICU-specific property for characters that are inert under NFKD, i.e.
-- they do not interact with adjacent characters.
| NFCInert
-- ^ ICU-specific property for characters that are inert under NFC,
-- i.e. they do not interact with adjacent characters.
| NFKCInert
-- ^ ICU-specific property for characters that are inert under NFKC,
-- i.e. they do not interact with adjacent characters.
| SegmentStarter
-- ^ ICU-specific property for characters that are starters in terms of
-- Unicode normalization and combining character sequences.
| PatternSyntax
-- ^ See UAX #31 Identifier and Pattern Syntax
-- <http://www.unicode.org/reports/tr31/>.
| PatternWhiteSpace
-- ^ See UAX #31 Identifier and Pattern Syntax
-- <http://www.unicode.org/reports/tr31/>.
| POSIXAlNum
-- ^ Alphanumeric character class.
| POSIXBlank
-- ^ Blank character class.
| POSIXGraph
-- ^ Graph character class.
| POSIXPrint
-- ^ Printable character class.
| POSIXXDigit
-- ^ Hex digit character class.
deriving (Eq, Enum, Show, Typeable)
instance NFData Bool_ where
rnf !_ = ()
class Property p v | p -> v where
fromNative :: p -> Int32 -> v
toUProperty :: p -> UProperty
data BidiClass_ = BidiClass deriving (Show, Typeable)
instance NFData BidiClass_ where
rnf !_ = ()
instance Property BidiClass_ Direction where
fromNative _ = toEnum . fromIntegral
toUProperty _ = (#const UCHAR_BIDI_CLASS)
data Block_ = Block
instance NFData Block_ where
rnf !_ = ()
instance Property Block_ BlockCode where
fromNative _ = toEnum . fromIntegral
toUProperty _ = (#const UCHAR_BLOCK)
data CanonicalCombiningClass_ = CanonicalCombiningClass deriving (Show,Typeable)
instance NFData CanonicalCombiningClass_ where
rnf !_ = ()
instance Property CanonicalCombiningClass_ Int where
fromNative _ = fromIntegral
toUProperty _ = (#const UCHAR_CANONICAL_COMBINING_CLASS)
data Decomposition_ = Decomposition deriving (Show, Typeable)
instance NFData Decomposition_ where
rnf !_ = ()
data Decomposition =
Canonical
| Compat
| Circle
| Final
| Font
| Fraction
| Initial
| Isolated
| Medial
| Narrow
| NoBreak
| Small
| Square
| Sub
| Super
| Vertical
| Wide
| Count
deriving (Eq, Enum, Show, Typeable)
instance NFData Decomposition where
rnf !_ = ()
instance Property Decomposition_ (Maybe Decomposition) where
fromNative _ = maybeEnum
toUProperty _ = (#const UCHAR_DECOMPOSITION_TYPE)
data EastAsianWidth_ = EastAsianWidth deriving (Show, Typeable)
instance NFData EastAsianWidth_ where
rnf !_ = ()
data EastAsianWidth = EANeutral
| EAAmbiguous
| EAHalf
| EAFull
| EANarrow
| EAWide
| EACount
deriving (Eq, Enum, Show, Typeable)
instance NFData EastAsianWidth where
rnf !_ = ()
instance Property EastAsianWidth_ EastAsianWidth where
fromNative _ = toEnum . fromIntegral
toUProperty _ = (#const UCHAR_EAST_ASIAN_WIDTH)
instance Property Bool_ Bool where
fromNative _ = (/=0)
toUProperty = fromIntegral . fromEnum
data GeneralCategory_ = GeneralCategory deriving (Show, Typeable)
instance NFData GeneralCategory_ where
rnf !_ = ()
data GeneralCategory =
GeneralOtherType
| UppercaseLetter
| LowercaseLetter
| TitlecaseLetter
| ModifierLetter
| OtherLetter
| NonSpacingMark
| EnclosingMark
| CombiningSpacingMark
| DecimalDigitNumber
| LetterNumber
| OtherNumber
| SpaceSeparator
| LineSeparator
| ParagraphSeparator
| ControlChar
| FormatChar
| PrivateUseChar
| Surrogate
| DashPunctuation
| StartPunctuation
| EndPunctuation
| ConnectorPunctuation
| OtherPunctuation
| MathSymbol
| CurrencySymbol
| ModifierSymbol
| OtherSymbol
| InitialPunctuation
| FinalPunctuation
deriving (Eq, Enum, Show, Typeable)
instance NFData GeneralCategory where
rnf !_ = ()
instance Property GeneralCategory_ GeneralCategory where
fromNative _ = toEnum . fromIntegral
toUProperty _ = (#const UCHAR_GENERAL_CATEGORY)
data JoiningGroup_ = JoiningGroup deriving (Show, Typeable)
instance NFData JoiningGroup_ where
rnf !_ = ()
maybeEnum :: Enum a => Int32 -> Maybe a
maybeEnum 0 = Nothing
maybeEnum n = Just $! toEnum (fromIntegral n-1)
data JoiningGroup =
Ain
| Alaph
| Alef
| Beh
| Beth
| Dal
| DalathRish
| E
| Feh
| FinalSemkath
| Gaf
| Gamal
| Hah
| HamzaOnHehGoal
| He
| Heh
| HehGoal
| Heth
| Kaf
| Kaph
| KnottedHeh
| Lam
| Lamadh
| Meem
| Mim
| Noon
| Nun
| Pe
| Qaf
| Qaph
| Reh
| ReversedPe
| Sad
| Sadhe
| Seen
| Semkath
| Shin
| SwashKaf
| SyriacWaw
| Tah
| Taw
| TehMarbuta
| Teth
| Waw
| Yeh
| YehBarree
| YehWithTail
| Yudh
| YudhHe
| Zain
| Fe
| Khaph
| Zhain
| BurushaskiYehBarree
deriving (Eq, Enum, Show, Typeable)
instance NFData JoiningGroup where
rnf !_ = ()
instance Property JoiningGroup_ (Maybe JoiningGroup) where
fromNative _ = maybeEnum
toUProperty _ = (#const UCHAR_JOINING_GROUP)
data JoiningType_ = JoiningType deriving (Show, Typeable)
instance NFData JoiningType_ where
rnf !_ = ()
data JoiningType =
JoinCausing
| DualJoining
| LeftJoining
| RightJoining
| Transparent
deriving (Eq, Enum, Show, Typeable)
instance NFData JoiningType where
rnf !_ = ()
instance Property JoiningType_ (Maybe JoiningType) where
fromNative _ = maybeEnum
toUProperty _ = (#const UCHAR_JOINING_TYPE)
data LineBreak_ = LineBreak deriving (Show, Typeable)
instance NFData LineBreak_ where
rnf !_ = ()
data LineBreak =
Ambiguous
| LBAlphabetic
| BreakBoth
| BreakAfter
| BreakBefore
| MandatoryBreak
| ContingentBreak
| ClosePunctuation
| CombiningMark
| CarriageReturn
| Exclamation
| Glue
| LBHyphen
| LBIdeographic
| Inseparable
| InfixNumeric
| LineFeed
| Nonstarter
| Numeric
| OpenPunctuation
| PostfixNumeric
| PrefixNumeric
| Quotation
| ComplexContext
| LBSurrogate
| Space
| BreakSymbols
| Zwspace
| NextLine
| WordJoiner
| H2
| H3
| JL
| JT
| JV
deriving (Eq, Enum, Show, Typeable)
instance NFData LineBreak where
rnf !_ = ()
instance Property LineBreak_ (Maybe LineBreak) where
fromNative _ = maybeEnum
toUProperty _ = (#const UCHAR_LINE_BREAK)
data NumericType_ = NumericType deriving (Show, Typeable)
instance NFData NumericType_ where
rnf !_ = ()
data NumericType = NTDecimal | NTDigit | NTNumeric
deriving (Eq, Enum, Show, Typeable)
instance NFData NumericType where
rnf !_ = ()
instance Property NumericType_ (Maybe NumericType) where
fromNative _ = maybeEnum
toUProperty _ = (#const UCHAR_NUMERIC_TYPE)
data HangulSyllableType_ = HangulSyllableType deriving (Show, Typeable)
instance NFData HangulSyllableType_ where
rnf !_ = ()
data HangulSyllableType =
LeadingJamo
| VowelJamo
| TrailingJamo
| LVSyllable
| LVTSyllable
deriving (Eq, Enum, Show, Typeable)
instance NFData HangulSyllableType where
rnf !_ = ()
instance Property HangulSyllableType_ (Maybe HangulSyllableType) where
fromNative _ = maybeEnum
toUProperty _ = (#const UCHAR_HANGUL_SYLLABLE_TYPE)
data NFCQuickCheck_ = NFCQuickCheck deriving (Show, Typeable)
data NFDQuickCheck_ = NFDQuickCheck deriving (Show, Typeable)
data NFKCQuickCheck_ = NFKCQuickCheck deriving (Show, Typeable)
data NFKDQuickCheck_ = NFKDQuickCheck deriving (Show, Typeable)
instance NFData NFCQuickCheck_ where
rnf !_ = ()
instance NFData NFDQuickCheck_ where
rnf !_ = ()
instance NFData NFKCQuickCheck_ where
rnf !_ = ()
instance NFData NFKDQuickCheck_ where
rnf !_ = ()
instance Property NFCQuickCheck_ (Maybe Bool) where
fromNative _ = toNCR . fromIntegral
toUProperty _ = (#const UCHAR_NFC_QUICK_CHECK)
instance Property NFDQuickCheck_ (Maybe Bool) where
fromNative _ = toNCR . fromIntegral
toUProperty _ = (#const UCHAR_NFD_QUICK_CHECK)
instance Property NFKCQuickCheck_ (Maybe Bool) where
fromNative _ = toNCR . fromIntegral
toUProperty _ = (#const UCHAR_NFKC_QUICK_CHECK)
instance Property NFKDQuickCheck_ (Maybe Bool) where
fromNative _ = toNCR . fromIntegral
toUProperty _ = (#const UCHAR_NFKD_QUICK_CHECK)
data LeadCanonicalCombiningClass_ = LeadCanonicalCombiningClass
deriving (Show, Typeable)
instance NFData LeadCanonicalCombiningClass_ where
rnf !_ = ()
instance Property LeadCanonicalCombiningClass_ Int where
fromNative _ = fromIntegral
toUProperty _ = (#const UCHAR_LEAD_CANONICAL_COMBINING_CLASS)
data TrailingCanonicalCombiningClass_ = TrailingCanonicalCombiningClass
deriving (Show, Typeable)
instance NFData TrailingCanonicalCombiningClass_ where
rnf !_ = ()
instance Property TrailingCanonicalCombiningClass_ Int where
fromNative _ = fromIntegral
toUProperty _ = (#const UCHAR_TRAIL_CANONICAL_COMBINING_CLASS)
data GraphemeClusterBreak_ = GraphemeClusterBreak deriving (Show, Typeable)
instance NFData GraphemeClusterBreak_ where
rnf !_ = ()
data GraphemeClusterBreak =
Control
| CR
| Extend
| L
| LF
| LV
| LVT
| T
| V
| SpacingMark
| Prepend
deriving (Eq, Enum, Show, Typeable)
instance NFData GraphemeClusterBreak where
rnf !_ = ()
instance Property GraphemeClusterBreak_ (Maybe GraphemeClusterBreak) where
fromNative _ = maybeEnum
toUProperty _ = (#const UCHAR_GRAPHEME_CLUSTER_BREAK)
data SentenceBreak_ = SentenceBreak deriving (Show, Typeable)
instance NFData SentenceBreak_ where
rnf !_ = ()
data SentenceBreak =
SBATerm
| SBClose
| SBFormat
| SBLower
| SBNumeric
| SBOLetter
| SBSep
| SBSP
| SBSTerm
| SBUpper
| SBCR
| SBExtend
| SBLF
| SBSContinue
deriving (Eq, Enum, Show, Typeable)
instance NFData SentenceBreak where
rnf !_ = ()
instance Property SentenceBreak_ (Maybe SentenceBreak) where
fromNative _ = maybeEnum
toUProperty _ = (#const UCHAR_SENTENCE_BREAK)
data WordBreak_ = WordBreak deriving (Show, Typeable)
instance NFData WordBreak_ where
rnf !_ = ()
data WordBreak =
WBALetter
| WBFormat
| WBKatakana
| WBMidLetter
| WBMidNum
| WBNumeric
| WBExtendNumLet
| WBCR
| WBExtend
| WBLF
| WBMidNumLet
| WBNewline
deriving (Eq, Enum, Show, Typeable)
instance NFData WordBreak where
rnf !_ = ()
instance Property WordBreak_ (Maybe WordBreak) where
fromNative _ = maybeEnum
toUProperty _ = (#const UCHAR_WORD_BREAK)
property :: Property p v => p -> Char -> v
property p c = fromNative p . u_getIntPropertyValue (fromIntegral (ord c)) .
toUProperty $ p
{-# INLINE property #-}
-- | Return the Unicode allocation block that contains the given
-- character.
blockCode :: Char -> BlockCode
blockCode = toEnum . fromIntegral . ublock_getCode . fromIntegral . ord
{-# INLINE blockCode #-}
-- | Return the bidirectional category value for the code point,
-- which is used in the Unicode bidirectional algorithm (UAX #9
-- <http://www.unicode.org/reports/tr9/>).
direction :: Char -> Direction
direction = toEnum . fromIntegral . u_charDirection . fromIntegral . ord
{-# INLINE direction #-}
-- | Determine whether the code point has the 'BidiMirrored' property. This
-- property is set for characters that are commonly used in Right-To-Left
-- contexts and need to be displayed with a "mirrored" glyph.
isMirrored :: Char -> Bool
isMirrored = asBool . u_isMirrored . fromIntegral . ord
{-# INLINE isMirrored #-}
-- Map the specified character to a "mirror-image" character.
--
-- For characters with the 'BidiMirrored' property, implementations
-- sometimes need a "poor man's" mapping to another Unicode (code point)
-- such that the default glyph may serve as the mirror image of the default
-- glyph of the specified character. This is useful for text conversion to
-- and from codepages with visual order, and for displays without glyph
-- selection capabilities.
--
-- The return value is another Unicode code point that may serve as a
-- mirror-image substitute, or the original character itself if there
-- is no such mapping or the character lacks the 'BidiMirrored'
-- property.
mirror :: Char -> Char
mirror = chr . fromIntegral . u_charMirror . fromIntegral . ord
{-# INLINE mirror #-}
combiningClass :: Char -> Int
combiningClass = fromIntegral . u_getCombiningClass . fromIntegral . ord
{-# INLINE combiningClass #-}
-- | Return the decimal digit value of a decimal digit character.
-- Such characters have the general category @Nd@ (decimal digit
-- numbers) and a 'NumericType' of 'NTDecimal'.
--
-- No digit values are returned for any Han characters, because Han
-- number characters are often used with a special Chinese-style
-- number format (with characters for powers of 10 in between) instead
-- of in decimal-positional notation. Unicode 4 explicitly assigns
-- Han number characters a 'NumericType' of 'NTNumeric' instead of
-- 'NTDecimal'.
digitToInt :: Char -> Maybe Int
digitToInt c
| i == -1 = Nothing
| otherwise = Just $! fromIntegral i
where i = u_charDigitValue . fromIntegral . ord $ c
-- | Return the numeric value for a Unicode code point as defined in the
-- Unicode Character Database.
--
-- A 'Double' return type is necessary because some numeric values are
-- fractions, negative, or too large to fit in a fixed-width integral type.
numericValue :: Char -> Maybe Double
numericValue c
| v == (#const U_NO_NUMERIC_VALUE) = Nothing
| otherwise = Just v
where v = u_getNumericValue . fromIntegral . ord $ c
-- | Return the name of a Unicode character.
--
-- The names of all unassigned characters are empty.
--
-- The name contains only "invariant" characters like A-Z, 0-9, space,
-- and \'-\'.
charName :: Char -> String
charName = charName' (#const U_UNICODE_CHAR_NAME)
-- | Return the full name of a Unicode character.
--
-- Compared to 'charName', this function gives each Unicode code point
-- a unique extended name. Extended names are lowercase followed by an
-- uppercase hexadecimal number, within angle brackets.
charFullName :: Char -> String
charFullName = charName' (#const U_EXTENDED_CHAR_NAME)
-- | Find a Unicode character by its full name, and return its code
-- point value.
--
-- The name is matched exactly and completely.
--
-- A Unicode 1.0 name is matched only if it differs from the modern
-- name. Unicode names are all uppercase.
charFromName :: String -> Maybe Char
charFromName = charFromName' (#const U_UNICODE_CHAR_NAME)
-- | Find a Unicode character by its full or extended name, and return
-- its code point value.
--
-- The name is matched exactly and completely.
--
-- A Unicode 1.0 name is matched only if it differs from the modern
-- name.
--
-- Compared to 'charFromName', this function gives each Unicode code
-- point a unique extended name. Extended names are lowercase followed
-- by an uppercase hexadecimal number, within angle brackets.
charFromFullName :: String -> Maybe Char
charFromFullName = charFromName' (#const U_EXTENDED_CHAR_NAME)
charFromName' :: UCharNameChoice -> String -> Maybe Char
charFromName' choice name = unsafePerformIO . withCString name $ \ptr -> do
(err,r) <- withError $ u_charFromName choice ptr
return $! if err == u_INVALID_CHAR_FOUND || r == 0xffff
then Nothing
else Just $! chr (fromIntegral r)
charName' :: UCharNameChoice -> Char -> String
charName' choice c = fillString $ u_charName (fromIntegral (ord c)) choice
fillString :: (CString -> Int32 -> Ptr UErrorCode -> IO Int32) -> String
fillString act = unsafePerformIO $
handleOverflowError 83 act (curry peekCStringLen)
type UBlockCode = CInt
type UCharDirection = CInt
type UCharNameChoice = CInt
type UProperty = CInt
foreign import ccall unsafe "hs_text_icu.h __hs_ublock_getCode" ublock_getCode
:: UChar32 -> UBlockCode
foreign import ccall unsafe "hs_text_icu.h __hs_u_charDirection" u_charDirection
:: UChar32 -> UCharDirection
foreign import ccall unsafe "hs_text_icu.h __hs_u_isMirrored" u_isMirrored
:: UChar32 -> UBool
foreign import ccall unsafe "hs_text_icu.h __hs_u_charMirror" u_charMirror
:: UChar32 -> UChar32
foreign import ccall unsafe "hs_text_icu.h __hs_u_getCombiningClass" u_getCombiningClass
:: UChar32 -> Word8
foreign import ccall unsafe "hs_text_icu.h __hs_u_charDigitValue" u_charDigitValue
:: UChar32 -> Int32
foreign import ccall unsafe "hs_text_icu.h __hs_u_charName" u_charName
:: UChar32 -> UCharNameChoice -> CString -> Int32 -> Ptr UErrorCode
-> IO Int32
foreign import ccall unsafe "hs_text_icu.h __hs_u_charFromName" u_charFromName
:: UCharNameChoice -> CString -> Ptr UErrorCode
-> IO UChar32
foreign import ccall unsafe "hs_text_icu.h __hs_u_getIntPropertyValue" u_getIntPropertyValue
:: UChar32 -> UProperty -> Int32
foreign import ccall unsafe "hs_text_icu.h __hs_u_getNumericValue" u_getNumericValue
:: UChar32 -> Double
|