In perl.git, the branch blead has been updated <https://perl5.git.perl.org/perl.git/commitdiff/c64356a259d7e7fe57a4e90f9501c9d861be4ce1?hp=b37d10f658c300104241001e3f5de1f31d62b22f>
- Log ----------------------------------------------------------------- commit c64356a259d7e7fe57a4e90f9501c9d861be4ce1 Author: Karl Williamson <[email protected]> Date: Thu Mar 7 11:40:25 2019 -0700 regexec.c: Rule out match sooner If this function is passed a regnode that won't match a non-UTF-8 string, we can fail immediately if the string isn't UTF-8. commit f38bda849c4f399d092c8dd2852b5dfe73551370 Author: Karl Williamson <[email protected]> Date: Thu Mar 7 11:39:49 2019 -0700 regexec.c: Improve comments for a function commit 70ecb4be2ac4243cbdb6586f87a091a7f8055d91 Author: Karl Williamson <[email protected]> Date: Thu Mar 7 11:37:21 2019 -0700 PATCH: [perl #133899] panic in s/// Thanks for finding this bug, and the others you've been finding. A new regnode was added, but this function was not updated to account for that. I've now checked all the other new regnodes in 5.29 and this was the only missing one. commit 21c34e9717de1e37a5e25d2e7d748da66c781488 Author: Karl Williamson <[email protected]> Date: Wed Mar 6 17:50:23 2019 -0700 Add hook for Unicode private use override I am starting to write a Unicode::Private_Use module which will allow one to specify the Unicode properties of private use code points, thus making them actually useful. This commit adds a hook to regcomp.c to accommodate this module. The changes are pretty minimal. This way we don't have to wait another release cycle to get it out there. I don't want to document this interface, until it's proven. ----------------------------------------------------------------------- Summary of changes: MANIFEST | 1 + charclass_invlists.h | 2 +- embedvar.h | 2 + lib/unicore/uni_keywords.pl | 1266 +++++++++++++++++++++++++++++++++++++++++++ lib/warnings.pm | 17 +- perlapi.h | 2 + perlvars.h | 1 + pod/perldiag.pod | 5 + regcomp.c | 58 +- regen/mk_invlists.pl | 36 ++ regen/warnings.pl | 4 +- regexec.c | 15 +- t/re/subst.t | 7 +- uni_keywords.h | 2 +- warnings.h | 4 + 15 files changed, 1407 insertions(+), 15 deletions(-) create mode 100644 lib/unicore/uni_keywords.pl diff --git a/MANIFEST b/MANIFEST index 1bc8bc54f6..4466caf308 100644 --- a/MANIFEST +++ b/MANIFEST @@ -4771,6 +4771,7 @@ lib/unicore/ScriptExtensions.txt Unicode character database lib/unicore/Scripts.txt Unicode character database lib/unicore/SpecialCasing.txt Unicode character database lib/unicore/StandardizedVariants.txt Unicode character database +lib/unicore/uni_keywords.pl Indices into array in charclass_invlists.h lib/unicore/UnicodeData.txt Unicode character database lib/unicore/version The version of the Unicode lib/unicore/VerticalOrientation.txt Unicode character database diff --git a/charclass_invlists.h b/charclass_invlists.h index 5da5c7c8a6..557f021a5b 100644 --- a/charclass_invlists.h +++ b/charclass_invlists.h @@ -390181,5 +390181,5 @@ static const U8 WB_table[23][23] = { * 93cc868487ef3345596041bcb90c302b1b056733bb95233101bc10dc2dbe36b4 lib/unicore/version * 2680b9254eb236c5c090f11b149605043e8c8433661b96efc4a42fb4709342a5 regen/charset_translations.pl * 03e51b0f07beebd5da62ab943899aa4934eee1f792fa27c1fb638c33bf4ac6ea regen/mk_PL_charclass.pl - * 2fb19108265d37fc38920cd3f775c5c9fc25ae8b95be3bf197f47da1dc4989f4 regen/mk_invlists.pl + * d62728e4cfcba3e6550ff12ad924f4811ca2077ebec705b9fecabed716764414 regen/mk_invlists.pl * ex: set ro: */ diff --git a/embedvar.h b/embedvar.h index 420664d68c..35cf8f2191 100644 --- a/embedvar.h +++ b/embedvar.h @@ -371,6 +371,8 @@ #define PL_GNonFinalFold (my_vars->GNonFinalFold) #define PL_Posix_ptrs (my_vars->GPosix_ptrs) #define PL_GPosix_ptrs (my_vars->GPosix_ptrs) +#define PL_Private_Use (my_vars->GPrivate_Use) +#define PL_GPrivate_Use (my_vars->GPrivate_Use) #define PL_SB_invlist (my_vars->GSB_invlist) #define PL_GSB_invlist (my_vars->GSB_invlist) #define PL_SCX_invlist (my_vars->GSCX_invlist) diff --git a/lib/unicore/uni_keywords.pl b/lib/unicore/uni_keywords.pl new file mode 100644 index 0000000000..43dea59e02 --- /dev/null +++ b/lib/unicore/uni_keywords.pl @@ -0,0 +1,1266 @@ +# -*- buffer-read-only: t -*- +# !!!!!!! DO NOT EDIT THIS FILE !!!!!!! +# This file is built by regen/mk_invlists.pl from Unicode::UCD. +# Any changes made here will be lost! + +%utf8::uni_prop_ptrs_indices = ( + '_perl_any_folds' => 1151, + '_perl_charname_begin' => 1152, + '_perl_charname_continue' => 1153, + '_perl_folds_to_multi_char' => 1154, + '_perl_idcont' => 1155, + '_perl_idstart' => 1156, + '_perl_is_in_multi_char_fold' => 1157, + '_perl_nchar' => 1158, + '_perl_non_final_folds' => 1159, + '_perl_patws' => 1160, + '_perl_problematic_locale_foldeds_start' => 1161, + '_perl_problematic_locale_folds' => 1162, + '_perl_quotemeta' => 1163, + '_perl_surrogate' => 1164, + 'adlm' => 1, + 'aegeannumbers' => 2, + 'age=10' => 3, + 'age=11' => 4, + 'age=12' => 5, + 'age=2' => 6, + 'age=2.1' => 7, + 'age=3' => 8, + 'age=3.1' => 9, + 'age=3.2' => 10, + 'age=4' => 11, + 'age=4.1' => 12, + 'age=5' => 13, + 'age=5.1' => 14, + 'age=5.2' => 15, + 'age=6' => 16, + 'age=6.1' => 17, + 'age=6.2' => 18, + 'age=6.3' => 19, + 'age=7' => 20, + 'age=8' => 21, + 'age=9' => 22, + 'age=na' => 23, + 'aghb' => 24, + 'ahex' => 938, + 'ahom' => 25, + 'alchemical' => 26, + 'all' => 27, + 'alnum' => 1126, + 'alpha' => 1127, + 'alphabetic' => 1127, + 'alphabeticpf' => 28, + 'ancientgreekmusic' => 29, + 'ancientgreeknumbers' => 30, + 'ancientsymbols' => 31, + 'any' => 32, + 'arab' => 33, + 'arabicexta' => 34, + 'arabicmath' => 35, + 'arabicpfa' => 36, + 'arabicpfb' => 37, + 'arabicsup' => 38, + 'armi' => 39, + 'armn' => 40, + 'arrows' => 41, + 'ascii' => 42, + 'asciihexdigit' => 938, + 'assigned' => 43, + 'avst' => 44, + 'bali' => 45, + 'bamu' => 46, + 'bamumsup' => 47, + 'basiclatin' => 42, + 'bass' => 48, + 'batk' => 49, + 'bc=al' => 50, + 'bc=an' => 51, + 'bc=b' => 52, + 'bc=bn' => 53, + 'bc=cs' => 54, + 'bc=en' => 55, + 'bc=es' => 56, + 'bc=et' => 57, + 'bc=fsi' => 58, + 'bc=l' => 59, + 'bc=lre' => 60, + 'bc=lri' => 61, + 'bc=lro' => 62, + 'bc=nsm' => 63, + 'bc=on' => 64, + 'bc=pdf' => 65, + 'bc=pdi' => 66, + 'bc=r' => 67, + 'bc=rle' => 68, + 'bc=rli' => 69, + 'bc=rlo' => 70, + 'bc=s' => 71, + 'bc=ws' => 72, + 'beng' => 73, + 'bhks' => 74, + 'bidic' => 75, + 'bidim' => 76, + 'blank' => 1128, + 'blockelements' => 77, + 'bopo' => 78, + 'bopomofoext' => 79, + 'boxdrawing' => 80, + 'bpt=c' => 81, + 'bpt=n' => 82, + 'bpt=o' => 83, + 'brah' => 84, + 'brai' => 85, + 'bugi' => 86, + 'buhd' => 87, + 'byzantinemusic' => 88, + 'c' => 89, + 'cakm' => 90, + 'cans' => 91, + 'cari' => 92, + 'cased' => 93, + 'casedletter' => 94, + 'cc' => 1129, + 'ccc=0' => 95, + 'ccc=1' => 96, + 'ccc=10' => 97, + 'ccc=103' => 98, + 'ccc=107' => 99, + 'ccc=11' => 100, + 'ccc=118' => 101, + 'ccc=12' => 102, + 'ccc=122' => 103, + 'ccc=129' => 104, + 'ccc=13' => 105, + 'ccc=130' => 106, + 'ccc=132' => 107, + 'ccc=14' => 108, + 'ccc=15' => 109, + 'ccc=16' => 110, + 'ccc=17' => 111, + 'ccc=18' => 112, + 'ccc=19' => 113, + 'ccc=20' => 114, + 'ccc=202' => 115, + 'ccc=21' => 116, + 'ccc=214' => 117, + 'ccc=216' => 118, + 'ccc=22' => 119, + 'ccc=23' => 120, + 'ccc=24' => 121, + 'ccc=25' => 122, + 'ccc=26' => 123, + 'ccc=27' => 124, + 'ccc=28' => 125, + 'ccc=29' => 126, + 'ccc=30' => 127, + 'ccc=31' => 128, + 'ccc=32' => 129, + 'ccc=33' => 130, + 'ccc=34' => 131, + 'ccc=35' => 132, + 'ccc=36' => 133, + 'ccc=7' => 134, + 'ccc=8' => 135, + 'ccc=84' => 136, + 'ccc=9' => 137, + 'ccc=91' => 138, + 'ccc=a' => 139, + 'ccc=al' => 140, + 'ccc=ar' => 141, + 'ccc=b' => 142, + 'ccc=bl' => 143, + 'ccc=br' => 144, + 'ccc=da' => 145, + 'ccc=db' => 146, + 'ccc=is' => 147, + 'ccc=l' => 148, + 'ccc=r' => 149, + 'ce' => 150, + 'cf' => 151, + 'cham' => 152, + 'cher' => 153, + 'cherokeesup' => 154, + 'chesssymbols' => 155, + 'ci' => 156, + 'cjk' => 157, + 'cjkcompat' => 158, + 'cjkcompatforms' => 159, + 'cjkcompatideographs' => 160, + 'cjkcompatideographssup' => 161, + 'cjkexta' => 162, + 'cjkextb' => 163, + 'cjkextc' => 164, + 'cjkextd' => 165, + 'cjkexte' => 166, + 'cjkextf' => 167, + 'cjkradicalssup' => 168, + 'cjkstrokes' => 169, + 'cjksymbols' => 170, + 'cn' => 171, + 'cntrl' => 1129, + 'co' => 172, + 'compatjamo' => 173, + 'compex' => 174, + 'control' => 1129, + 'controlpictures' => 175, + 'copt' => 176, + 'copticepactnumbers' => 177, + 'countingrod' => 178, + 'cprt' => 179, + 'cuneiformnumbers' => 180, + 'currencysymbols' => 181, + 'cwcf' => 182, + 'cwcm' => 183, + 'cwkcf' => 184, + 'cwl' => 185, + 'cwt' => 186, + 'cwu' => 187, + 'cypriotsyllabary' => 188, + 'cyrillicexta' => 189, + 'cyrillicextb' => 190, + 'cyrillicextc' => 191, + 'cyrillicsup' => 192, + 'cyrl' => 193, + 'dash' => 194, + 'decimalnumber' => 1130, + 'dep' => 195, + 'deva' => 196, + 'devanagariext' => 197, + 'di' => 198, + 'dia' => 199, + 'diacriticals' => 200, + 'diacriticalsext' => 201, + 'diacriticalsforsymbols' => 202, + 'diacriticalssup' => 203, + 'digit' => 1130, + 'dingbats' => 204, + 'dogr' => 205, + 'domino' => 206, + 'dsrt' => 207, + 'dt=can' => 208, + 'dt=com' => 209, + 'dt=enc' => 210, + 'dt=fin' => 211, + 'dt=font' => 212, + 'dt=fra' => 213, + 'dt=init' => 214, + 'dt=iso' => 215, + 'dt=med' => 216, + 'dt=nar' => 217, + 'dt=nb' => 218, + 'dt=noncanon' => 219, + 'dt=none' => 220, + 'dt=sml' => 221, + 'dt=sqr' => 222, + 'dt=sub' => 223, + 'dt=sup' => 224, + 'dt=vert' => 225, + 'dupl' => 226, + 'ea=a' => 228, + 'ea=f' => 229, + 'ea=h' => 230, + 'ea=n' => 231, + 'ea=na' => 232, + 'ea=w' => 233, + 'earlydynasticcuneiform' => 227, + 'egyp' => 234, + 'egyptianhieroglyphformatcontrols' => 235, + 'elba' => 236, + 'elym' => 237, + 'emoticons' => 238, + 'enclosedalphanum' => 239, + 'enclosedalphanumsup' => 240, + 'enclosedcjk' => 241, + 'enclosedideographicsup' => 242, + 'ethi' => 243, + 'ethiopicext' => 244, + 'ethiopicexta' => 245, + 'ethiopicsup' => 246, + 'ext' => 247, + 'gcb=cn' => 248, + 'gcb=ex' => 249, + 'gcb=l' => 250, + 'gcb=pp' => 251, + 'gcb=sm' => 252, + 'gcb=t' => 253, + 'gcb=v' => 254, + 'gcb=xx' => 255, + 'geometricshapes' => 256, + 'geometricshapesext' => 257, + 'geor' => 258, + 'georgianext' => 259, + 'georgiansup' => 260, + 'glag' => 261, + 'glagoliticsup' => 262, + 'gong' => 263, + 'gonm' => 264, + 'goth' => 265, + 'gran' => 266, + 'graph' => 1131, + 'grbase' => 267, + 'greekext' => 268, + 'grek' => 269, + 'grext' => 270, + 'gujr' => 271, + 'guru' => 272, + 'halfandfullforms' => 273, + 'halfmarks' => 274, + 'han' => 275, + 'hang' => 276, + 'hano' => 277, + 'hatr' => 278, + 'hebr' => 279, + 'hex' => 1138, + 'hexdigit' => 1138, + 'highpusurrogates' => 280, + 'highsurrogates' => 281, + 'hira' => 282, + 'hluw' => 283, + 'hmng' => 284, + 'hmnp' => 285, + 'horizspace' => 1128, + 'hst=na' => 286, + 'hung' => 287, + 'hyphen_perl_aux' => 288, + 'idc' => 289, + 'ideo' => 290, + 'ideographicsymbols' => 291, + 'ids' => 292, + 'idsb' => 293, + 'idst' => 294, + 'in=1.1' => 485, + 'in=10' => 482, + 'in=11' => 483, + 'in=12' => 484, + 'in=2' => 486, + 'in=2.1' => 487, + 'in=3' => 488, + 'in=3.1' => 489, + 'in=3.2' => 490, + 'in=4' => 491, + 'in=4.1' => 492, + 'in=5' => 493, + 'in=5.1' => 494, + 'in=5.2' => 495, + 'in=6' => 496, + 'in=6.1' => 497, + 'in=6.2' => 498, + 'in=6.3' => 499, + 'in=7' => 500, + 'in=8' => 501, + 'in=9' => 502, + 'inadlam' => 295, + 'inahom' => 296, + 'inanatolianhieroglyphs' => 297, + 'inarabic' => 298, + 'inarmenian' => 299, + 'inavestan' => 300, + 'inbalinese' => 301, + 'inbamum' => 302, + 'inbassavah' => 303, + 'inbatak' => 304, + 'inbengali' => 305, + 'inbhaiksuki' => 306, + 'inbopomofo' => 307, + 'inbrahmi' => 308, + 'inbuginese' => 309, + 'inbuhid' => 310, + 'incarian' => 311, + 'incaucasianalbanian' => 312, + 'inchakma' => 313, + 'incham' => 314, + 'incherokee' => 315, + 'incoptic' => 316, + 'incuneiform' => 317, + 'incyrillic' => 318, + 'indevanagari' => 319, + 'indicnumberforms' => 320, + 'indicsiyaqnumbers' => 321, + 'indogra' => 322, + 'induployan' => 323, + 'inegyptianhieroglyphs' => 324, + 'inelbasan' => 325, + 'inelymaic' => 326, + 'inethiopic' => 327, + 'ingeorgian' => 328, + 'inglagolitic' => 329, + 'ingothic' => 330, + 'ingrantha' => 331, + 'ingreek' => 332, + 'ingujarati' => 333, + 'ingunjalagondi' => 334, + 'ingurmukhi' => 335, + 'inhangul' => 336, + 'inhanifirohingya' => 337, + 'inhanunoo' => 338, + 'inhatran' => 339, + 'inhebrew' => 340, + 'inhiragana' => 341, + 'inidc' => 342, + 'inimperialaramaic' => 343, + 'ininscriptionalpahlavi' => 344, + 'ininscriptionalparthian' => 345, + 'injavanese' => 346, + 'inkaithi' => 347, + 'inkannada' => 348, + 'inkatakana' => 349, + 'inkharoshthi' => 350, + 'inkhmer' => 351, + 'inkhojki' => 352, + 'inkhudawadi' => 353, + 'inlao' => 354, + 'inlepcha' => 355, + 'inlimbu' => 356, + 'inlineara' => 357, + 'inlycian' => 358, + 'inlydian' => 359, + 'inmahajani' => 360, + 'inmakasar' => 361, + 'inmalayalam' => 362, + 'inmandaic' => 363, + 'inmanichaean' => 364, + 'inmarchen' => 365, + 'inmasaramgondi' => 366, + 'inmedefaidrin' => 367, + 'inmeeteimayek' => 368, + 'inmendekikakui' => 369, + 'inmeroiticcursive' => 370, + 'inmiao' => 371, + 'inmodi' => 372, + 'inmongolian' => 373, + 'inmro' => 374, + 'inmultani' => 375, + 'inmyanmar' => 376, + 'innabataean' => 377, + 'innandinagari' => 378, + 'innewa' => 379, + 'innewtailue' => 380, + 'innko' => 381, + 'innushu' => 382, + 'innyiakengpuachuehmong' => 383, + 'inogham' => 384, + 'inoldhungarian' => 385, + 'inolditalic' => 386, + 'inoldpermic' => 387, + 'inoldpersian' => 388, + 'inoldsogdian' => 389, + 'inoldturkic' => 390, + 'inoriya' => 391, + 'inosage' => 392, + 'inosmanya' => 393, + 'inpahawhhmong' => 394, + 'inpaucinhau' => 395, + 'inpc=bottom' => 396, + 'inpc=bottomandleft' => 397, + 'inpc=bottomandright' => 398, + 'inpc=left' => 399, + 'inpc=leftandright' => 400, + 'inpc=na' => 401, + 'inpc=overstruck' => 402, + 'inpc=right' => 403, + 'inpc=top' => 404, + 'inpc=topandbottom' => 405, + 'inpc=topandbottomandright' => 406, + 'inpc=topandleft' => 407, + 'inpc=topandleftandright' => 408, + 'inpc=topandright' => 409, + 'inphagspa' => 410, + 'inphoenician' => 411, + 'inpsalterpahlavi' => 412, + 'inpunctuation' => 413, + 'inrejang' => 414, + 'inrunic' => 415, + 'insamaritan' => 416, + 'insaurashtra' => 417, + 'insc=avagraha' => 418, + 'insc=bindu' => 419, + 'insc=brahmijoiningnumber' => 420, + 'insc=cantillationmark' => 421, + 'insc=consonant' => 422, + 'insc=consonantdead' => 423, + 'insc=consonantfinal' => 424, + 'insc=consonantheadletter' => 425, + 'insc=consonantinitialpostfixed' => 426, + 'insc=consonantkiller' => 427, + 'insc=consonantmedial' => 428, + 'insc=consonantplaceholder' => 429, + 'insc=consonantprecedingrepha' => 430, + 'insc=consonantprefixed' => 431, + 'insc=consonantsubjoined' => 432, + 'insc=consonantsucceedingrepha' => 433, + 'insc=consonantwithstacker' => 434, + 'insc=geminationmark' => 435, + 'insc=invisiblestacker' => 436, + 'insc=modifyingletter' => 437, + 'insc=nonjoiner' => 438, + 'insc=nukta' => 439, + 'insc=number' => 440, + 'insc=numberjoiner' => 441, + 'insc=other' => 442, + 'insc=purekiller' => 443, + 'insc=registershifter' => 444, + 'insc=syllablemodifier' => 445, + 'insc=toneletter' => 446, + 'insc=tonemark' => 447, + 'insc=virama' => 448, + 'insc=visarga' => 449, + 'insc=vowel' => 450, + 'insc=voweldependent' => 451, + 'insc=vowelindependent' => 452, + 'insharada' => 453, + 'insiddham' => 454, + 'insinhala' => 455, + 'insogdian' => 456, + 'insorasompeng' => 457, + 'insoyombo' => 458, + 'insundanese' => 459, + 'insylotinagri' => 460, + 'insyriac' => 461, + 'intagalog' => 462, + 'intagbanwa' => 463, + 'intaile' => 464, + 'intaitham' => 465, + 'intaiviet' => 466, + 'intakri' => 467, + 'intamil' => 468, + 'intangut' => 469, + 'intelugu' => 470, + 'inthaana' => 471, + 'inthai' => 472, + 'intibetan' => 473, + 'intifinagh' => 474, + 'intirhuta' => 475, + 'inugaritic' => 476, + 'invai' => 477, + 'invs' => 478, + 'inwancho' => 479, + 'inwarangciti' => 480, + 'inzanabazarsquare' => 481, + 'ipaext' => 503, + 'ital' => 504, + 'jamo' => 505, + 'jamoexta' => 506, + 'jamoextb' => 507, + 'java' => 508, + 'jg=africanfeh' => 509, + 'jg=africannoon' => 510, + 'jg=africanqaf' => 511, + 'jg=ain' => 512, + 'jg=alaph' => 513, + 'jg=alef' => 514, + 'jg=beh' => 515, + 'jg=beth' => 516, + 'jg=burushaskiyehbarree' => 517, + 'jg=dal' => 518, + 'jg=dalathrish' => 519, + 'jg=e' => 520, + 'jg=farsiyeh' => 521, + 'jg=fe' => 522, + 'jg=feh' => 523, + 'jg=finalsemkath' => 524, + 'jg=gaf' => 525, + 'jg=gamal' => 526, + 'jg=hah' => 527, + 'jg=hamzaonhehgoal' => 528, + 'jg=hanifirohingyakinnaya' => 529, + 'jg=hanifirohingyapa' => 530, + 'jg=he' => 531, + 'jg=heh' => 532, + 'jg=hehgoal' => 533, + 'jg=heth' => 534, + 'jg=kaf' => 535, + 'jg=kaph' => 536, + 'jg=khaph' => 537, + 'jg=knottedheh' => 538, + 'jg=lam' => 539, + 'jg=lamadh' => 540, + 'jg=malayalambha' => 541, + 'jg=malayalamja' => 542, + 'jg=malayalamlla' => 543, + 'jg=malayalamllla' => 544, + 'jg=malayalamnga' => 545, + 'jg=malayalamnna' => 546, + 'jg=malayalamnnna' => 547, + 'jg=malayalamnya' => 548, + 'jg=malayalamra' => 549, + 'jg=malayalamssa' => 550, + 'jg=malayalamtta' => 551, + 'jg=manichaeanaleph' => 552, + 'jg=manichaeanayin' => 553, + 'jg=manichaeanbeth' => 554, + 'jg=manichaeandaleth' => 555, + 'jg=manichaeandhamedh' => 556, + 'jg=manichaeanfive' => 557, + 'jg=manichaeangimel' => 558, + 'jg=manichaeanheth' => 559, + 'jg=manichaeanhundred' => 560, + 'jg=manichaeankaph' => 561, + 'jg=manichaeanlamedh' => 562, + 'jg=manichaeanmem' => 563, + 'jg=manichaeannun' => 564, + 'jg=manichaeanone' => 565, + 'jg=manichaeanpe' => 566, + 'jg=manichaeanqoph' => 567, + 'jg=manichaeanresh' => 568, + 'jg=manichaeansadhe' => 569, + 'jg=manichaeansamekh' => 570, + 'jg=manichaeantaw' => 571, + 'jg=manichaeanten' => 572, + 'jg=manichaeanteth' => 573, + 'jg=manichaeanthamedh' => 574, + 'jg=manichaeantwenty' => 575, + 'jg=manichaeanwaw' => 576, + 'jg=manichaeanyodh' => 577, + 'jg=manichaeanzayin' => 578, + 'jg=meem' => 579, + 'jg=mim' => 580, + 'jg=nojoininggroup' => 581, + 'jg=noon' => 582, + 'jg=nun' => 583, + 'jg=nya' => 584, + 'jg=pe' => 585, + 'jg=qaf' => 586, + 'jg=qaph' => 587, + 'jg=reh' => 588, + 'jg=reversedpe' => 589, + 'jg=rohingyayeh' => 590, + 'jg=sad' => 591, + 'jg=sadhe' => 592, + 'jg=seen' => 593, + 'jg=semkath' => 594, + 'jg=shin' => 595, + 'jg=straightwaw' => 596, + 'jg=swashkaf' => 597, + 'jg=syriacwaw' => 598, + 'jg=tah' => 599, + 'jg=taw' => 600, + 'jg=tehmarbuta' => 601, + 'jg=teth' => 602, + 'jg=waw' => 603, + 'jg=yeh' => 604, + 'jg=yehbarree' => 605, + 'jg=yehwithtail' => 606, + 'jg=yudh' => 607, + 'jg=yudhhe' => 608, + 'jg=zain' => 609, + 'jg=zhain' => 610, + 'joinc' => 611, + 'jt=c' => 612, + 'jt=d' => 613, + 'jt=l' => 614, + 'jt=r' => 615, + 'jt=t' => 616, + 'jt=u' => 617, + 'kali' => 618, + 'kana' => 619, + 'kanaexta' => 620, + 'kanasup' => 621, + 'kanbun' => 622, + 'kangxi' => 623, + 'katakanaext' => 624, + 'khar' => 625, + 'khmersymbols' => 626, + 'khmr' => 627, + 'khoj' => 628, + 'knda' => 629, + 'kthi' => 630, + 'l' => 631, + 'l_' => 94, + 'l_amp_' => 94, + 'lana' => 632, + 'lao' => 633, + 'latin1' => 634, + 'latinexta' => 635, + 'latinextadditional' => 636, + 'latinextb' => 637, + 'latinextc' => 638, + 'latinextd' => 639, + 'latinexte' => 640, + 'latn' => 641, + 'lb=ai' => 642, + 'lb=al' => 643, + 'lb=b2' => 644, + 'lb=ba' => 645, + 'lb=bb' => 646, + 'lb=bk' => 647, + 'lb=cb' => 648, + 'lb=cj' => 649, + 'lb=cl' => 650, + 'lb=cm' => 651, + 'lb=cp' => 652, + 'lb=cr' => 653, + 'lb=eb' => 654, + 'lb=em' => 655, + 'lb=ex' => 656, + 'lb=gl' => 657, + 'lb=h2' => 658, + 'lb=h3' => 659, + 'lb=hl' => 660, + 'lb=hy' => 661, + 'lb=id' => 662, + 'lb=in' => 663, + 'lb=is' => 664, + 'lb=lf' => 665, + 'lb=nl' => 666, + 'lb=ns' => 667, + 'lb=nu' => 668, + 'lb=op' => 669, + 'lb=po' => 670, + 'lb=pr' => 671, + 'lb=qu' => 672, + 'lb=sa' => 673, + 'lb=sg_perl_aux' => 674, + 'lb=sp' => 675, + 'lb=sy' => 676, + 'lb=wj' => 677, + 'lb=xx' => 678, + 'lb=zw' => 679, + 'lb=zwj' => 680, + 'lc' => 94, + 'lepc' => 681, + 'letterlikesymbols' => 682, + 'limb' => 683, + 'lina' => 684, + 'linb' => 685, + 'linearbideograms' => 686, + 'linearbsyllabary' => 687, + 'lisu' => 688, + 'll' => 692, + 'lm' => 689, + 'lo' => 690, + 'loe' => 691, + 'lower' => 1132, + 'lowercase' => 1132, + 'lowercaseletter' => 692, + 'lowsurrogates' => 693, + 'lt' => 1089, + 'lu' => 1095, + 'lyci' => 694, + 'lydi' => 695, + 'm' => 696, + 'mahj' => 697, + 'mahjong' => 698, + 'maka' => 699, + 'mand' => 700, + 'mani' => 701, + 'marc' => 702, + 'math' => 703, + 'mathalphanum' => 704, + 'mathoperators' => 705, + 'mayannumerals' => 706, + 'mc' => 707, + 'me' => 708, + 'medf' => 709, + 'meeteimayekext' => 710, + 'mend' => 711, + 'merc' => 712, + 'mero' => 713, + 'miao' => 714, + 'miscarrows' => 715, + 'miscmathsymbolsa' => 716, + 'miscmathsymbolsb' => 717, + 'miscpictographs' => 718, + 'miscsymbols' => 719, + 'misctechnical' => 720, + 'mlym' => 721, + 'mn' => 722, + 'modi' => 723, + 'modifierletters' => 724, + 'modifiertoneletters' => 725, + 'mong' => 726, + 'mongoliansup' => 727, + 'mro' => 728, + 'mtei' => 729, + 'mult' => 730, + 'music' => 731, + 'myanmarexta' => 732, + 'myanmarextb' => 733, + 'mymr' => 734, + 'n' => 735, + 'nand' => 736, + 'narb' => 737, + 'nb' => 738, + 'nbat' => 739, + 'nd' => 1130, + 'newa' => 740, + 'nfcqc=m' => 741, + 'nfcqc=y' => 742, + 'nfdqc=y' => 743, + 'nfkcqc=n' => 744, + 'nfkcqc=y' => 745, + 'nfkdqc=n' => 746, + 'nko' => 747, + 'nl' => 748, + 'no' => 749, + 'nshu' => 750, + 'nt=di' => 751, + 'nt=nu' => 752, + 'numberforms' => 753, + 'nv=0' => 754, + 'nv=1' => 755, + 'nv=1/10' => 780, + 'nv=1/12' => 781, + 'nv=1/16' => 782, + 'nv=1/160' => 783, + 'nv=1/2' => 784, + 'nv=1/20' => 785, + 'nv=1/3' => 786, + 'nv=1/32' => 787, + 'nv=1/320' => 788, + 'nv=1/4' => 789, + 'nv=1/40' => 790, + 'nv=1/5' => 791, + 'nv=1/6' => 792, + 'nv=1/64' => 793, + 'nv=1/7' => 794, + 'nv=1/8' => 795, + 'nv=1/80' => 796, + 'nv=1/9' => 797, + 'nv=10' => 756, + 'nv=100' => 757, + 'nv=1000' => 758, + 'nv=10000' => 759, + 'nv=100000' => 760, + 'nv=1000000' => 761, + 'nv=10000000' => 762, + 'nv=100000000' => 763, + 'nv=10000000000' => 764, + 'nv=1000000000000' => 765, + 'nv=11' => 766, + 'nv=11/12' => 767, + 'nv=11/2' => 768, + 'nv=12' => 769, + 'nv=13' => 770, + 'nv=13/2' => 771, + 'nv=14' => 772, + 'nv=15' => 773, + 'nv=15/2' => 774, + 'nv=16' => 775, + 'nv=17' => 776, + 'nv=17/2' => 777, + 'nv=18' => 778, + 'nv=19' => 779, + 'nv=2' => 798, + 'nv=2/3' => 815, + 'nv=2/5' => 816, + 'nv=20' => 799, + 'nv=200' => 800, + 'nv=2000' => 801, + 'nv=20000' => 802, + 'nv=200000' => 803, + 'nv=20000000' => 804, + 'nv=21' => 805, + 'nv=216000' => 806, + 'nv=22' => 807, + 'nv=23' => 808, + 'nv=24' => 809, + 'nv=25' => 810, + 'nv=26' => 811, + 'nv=27' => 812, + 'nv=28' => 813, + 'nv=29' => 814, + 'nv=3' => 817, + 'nv=3/16' => 832, + 'nv=3/2' => 833, + 'nv=3/20' => 834, + 'nv=3/4' => 835, + 'nv=3/5' => 836, + 'nv=3/64' => 837, + 'nv=3/8' => 838, + 'nv=3/80' => 839, + 'nv=30' => 818, + 'nv=300' => 819, + 'nv=3000' => 820, + 'nv=30000' => 821, + 'nv=300000' => 822, + 'nv=31' => 823, + 'nv=32' => 824, + 'nv=33' => 825, + 'nv=34' => 826, + 'nv=35' => 827, + 'nv=36' => 828, + 'nv=37' => 829, + 'nv=38' => 830, + 'nv=39' => 831, + 'nv=4' => 840, + 'nv=4/5' => 856, + 'nv=40' => 841, + 'nv=400' => 842, + 'nv=4000' => 843, + 'nv=40000' => 844, + 'nv=400000' => 845, + 'nv=41' => 846, + 'nv=42' => 847, + 'nv=43' => 848, + 'nv=432000' => 849, + 'nv=44' => 850, + 'nv=45' => 851, + 'nv=46' => 852, + 'nv=47' => 853, + 'nv=48' => 854, + 'nv=49' => 855, + 'nv=5' => 857, + 'nv=5/12' => 863, + 'nv=5/2' => 864, + 'nv=5/6' => 865, + 'nv=5/8' => 866, + 'nv=50' => 858, + 'nv=500' => 859, + 'nv=5000' => 860, + 'nv=50000' => 861, + 'nv=500000' => 862, + 'nv=6' => 867, + 'nv=60' => 868, + 'nv=600' => 869, + 'nv=6000' => 870, + 'nv=60000' => 871, + 'nv=600000' => 872, + 'nv=7' => 873, + 'nv=7/12' => 879, + 'nv=7/2' => 880, + 'nv=7/8' => 881, + 'nv=70' => 874, + 'nv=700' => 875, + 'nv=7000' => 876, + 'nv=70000' => 877, + 'nv=700000' => 878, + 'nv=8' => 882, + 'nv=80' => 883, + 'nv=800' => 884, + 'nv=8000' => 885, + 'nv=80000' => 886, + 'nv=800000' => 887, + 'nv=9' => 888, + 'nv=9/2' => 894, + 'nv=90' => 889, + 'nv=900' => 890, + 'nv=9000' => 891, + 'nv=90000' => 892, + 'nv=900000' => 893, + 'nv=_minus_1/2' => 896, + 'nv=nan' => 895, + 'ocr' => 897, + 'ogam' => 898, + 'olck' => 899, + 'orkh' => 900, + 'ornamentaldingbats' => 901, + 'orya' => 902, + 'osge' => 903, + 'osma' => 904, + 'ottomansiyaqnumbers' => 905, + 'p' => 906, + 'palm' => 907, + 'patsyn' => 908, + 'pauc' => 909, + 'pc' => 910, + 'pcm' => 911, + 'pd' => 912, + 'pe' => 913, + 'perlspace' => 935, + 'perlword' => 937, + 'perm' => 914, + 'pf' => 915, + 'phag' => 916, + 'phaistos' => 917, + 'phli' => 918, + 'phlp' => 919, + 'phnx' => 920, + 'phoneticext' => 921, + 'phoneticextsup' => 922, + 'pi' => 923, + 'playingcards' => 924, + 'po' => 925, + 'posixalnum' => 926, + 'posixalpha' => 927, + 'posixblank' => 928, + 'posixcntrl' => 929, + 'posixdigit' => 930, + 'posixgraph' => 931, + 'posixlower' => 932, + 'posixprint' => 933, + 'posixpunct' => 934, + 'posixspace' => 935, + 'posixupper' => 936, + 'posixword' => 937, + 'posixxdigit' => 938, + 'print' => 1133, + 'prti' => 939, + 'ps' => 940, + 'pua' => 941, + 'qaai' => 942, + 'qmark' => 943, + 'radical' => 944, + 'ri' => 945, + 'rjng' => 946, + 'rohg' => 947, + 'rumi' => 948, + 'runr' => 949, + 's' => 950, + 'samr' => 951, + 'sarb' => 952, + 'saur' => 953, + 'sb=at' => 954, + 'sb=cl' => 955, + 'sb=ex' => 956, + 'sb=fo' => 957, + 'sb=le' => 958, + 'sb=lo' => 959, + 'sb=sc' => 960, + 'sb=se' => 961, + 'sb=sp' => 962, + 'sb=st' => 963, + 'sb=up' => 964, + 'sb=xx' => 965, + 'sc' => 966, + 'sc=adlm' => 967, + 'sc=arab' => 968, + 'sc=armn' => 969, + 'sc=beng' => 970, + 'sc=bopo' => 971, + 'sc=bugi' => 972, + 'sc=buhd' => 973, + 'sc=cakm' => 974, + 'sc=copt' => 975, + 'sc=cprt' => 976, + 'sc=cyrl' => 977, + 'sc=deva' => 978, + 'sc=dogr' => 979, + 'sc=dupl' => 980, + 'sc=geor' => 981, + 'sc=glag' => 982, + 'sc=gong' => 983, + 'sc=gonm' => 984, + 'sc=gran' => 985, + 'sc=grek' => 986, + 'sc=gujr' => 987, + 'sc=guru' => 988, + 'sc=han' => 989, + 'sc=hang' => 990, + 'sc=hano' => 991, + 'sc=hira' => 992, + 'sc=java' => 993, + 'sc=kali' => 994, + 'sc=kana' => 995, + 'sc=khoj' => 996, + 'sc=knda' => 997, + 'sc=kthi' => 998, + 'sc=latn' => 999, + 'sc=limb' => 1000, + 'sc=lina' => 1001, + 'sc=linb' => 1002, + 'sc=mahj' => 1003, + 'sc=mand' => 1004, + 'sc=mani' => 1005, + 'sc=mlym' => 1006, + 'sc=modi' => 1007, + 'sc=mong' => 1008, + 'sc=mult' => 1009, + 'sc=mymr' => 1010, + 'sc=nand' => 1011, + 'sc=orya' => 1012, + 'sc=perm' => 1013, + 'sc=phag' => 1014, + 'sc=phlp' => 1015, + 'sc=qaai' => 1016, + 'sc=rohg' => 1017, + 'sc=shrd' => 1018, + 'sc=sind' => 1019, + 'sc=sinh' => 1020, + 'sc=sogd' => 1021, + 'sc=sylo' => 1022, + 'sc=syrc' => 1023, + 'sc=tagb' => 1024, + 'sc=takr' => 1025, + 'sc=tale' => 1026, + 'sc=taml' => 1027, + 'sc=telu' => 1028, + 'sc=tglg' => 1029, + 'sc=thaa' => 1030, + 'sc=tirh' => 1031, + 'sc=yi' => 1032, + 'sc=zyyy' => 1033, + 'sd' => 1034, + 'sgnw' => 1035, + 'shaw' => 1036, + 'shorthandformatcontrols' => 1037, + 'shrd' => 1038, + 'sidd' => 1039, + 'sind' => 1040, + 'sinh' => 1041, + 'sinhalaarchaicnumbers' => 1042, + 'sk' => 1043, + 'sm' => 1044, + 'smallforms' => 1045, + 'smallkanaext' => 1046, + 'so' => 1047, + 'sogd' => 1048, + 'sogo' => 1049, + 'sora' => 1050, + 'soyo' => 1051, + 'space' => 1135, + 'spaceperl' => 1135, + 'specials' => 1052, + 'sterm' => 1053, + 'sund' => 1054, + 'sundanesesup' => 1055, + 'suparrowsa' => 1056, + 'suparrowsb' => 1057, + 'suparrowsc' => 1058, + 'superandsub' => 1059, + 'supmathoperators' => 1060, + 'suppuaa' => 1061, + 'suppuab' => 1062, + 'suppunctuation' => 1063, + 'supsymbolsandpictographs' => 1064, + 'suttonsignwriting' => 1065, + 'sylo' => 1066, + 'symbolsandpictographsexta' => 1067, + 'syrc' => 1068, + 'syriacsup' => 1069, + 'tagb' => 1070, + 'tags' => 1071, + 'taixuanjing' => 1072, + 'takr' => 1073, + 'tale' => 1074, + 'talu' => 1075, + 'tamilsup' => 1076, + 'taml' => 1077, + 'tang' => 1078, + 'tangutcomponents' => 1079, + 'tavt' => 1080, + 'telu' => 1081, + 'term' => 1082, + 'tfng' => 1083, + 'tglg' => 1084, + 'thaa' => 1085, + 'thai' => 1086, + 'tibt' => 1087, + 'tirh' => 1088, + 'title' => 1089, + 'titlecase' => 1089, + 'titlecaseletter' => 1089, + 'transportandmap' => 1090, + 'ucas' => 1091, + 'ucasext' => 1092, + 'ugar' => 1093, + 'uideo' => 1094, + 'upper' => 1136, + 'uppercase' => 1136, + 'uppercaseletter' => 1095, + 'vai' => 1096, + 'vedicext' => 1097, + 'verticalforms' => 1098, + 'vertspace' => 1099, + 'vo=r' => 1100, + 'vo=tr' => 1101, + 'vo=tu' => 1102, + 'vo=u' => 1103, + 'vs' => 1104, + 'vssup' => 1105, + 'wara' => 1106, + 'wb=dq' => 1107, + 'wb=eb' => 1108, + 'wb=ex' => 1109, + 'wb=extend' => 1110, + 'wb=fo' => 1111, + 'wb=ka' => 1112, + 'wb=le' => 1113, + 'wb=mb' => 1114, + 'wb=ml' => 1115, + 'wb=mn' => 1116, + 'wb=nl' => 1117, + 'wb=nu' => 1118, + 'wb=sq' => 1119, + 'wb=wsegspace' => 1120, + 'wb=xx' => 1121, + 'wcho' => 1122, + 'whitespace' => 1135, + 'word' => 1137, + 'wspace' => 1135, + 'xdigit' => 1138, + 'xidc' => 1123, + 'xids' => 1124, + 'xpeo' => 1125, + 'xperlspace' => 1135, + 'xposixalnum' => 1126, + 'xposixalpha' => 1127, + 'xposixblank' => 1128, + 'xposixcntrl' => 1129, + 'xposixdigit' => 1130, + 'xposixgraph' => 1131, + 'xposixlower' => 1132, + 'xposixprint' => 1133, + 'xposixpunct' => 1134, + 'xposixspace' => 1135, + 'xposixupper' => 1136, + 'xposixword' => 1137, + 'xposixxdigit' => 1138, + 'xsux' => 1139, + 'yi' => 1140, + 'yijing' => 1141, + 'yiradicals' => 1142, + 'yisyllables' => 1143, + 'z' => 1144, + 'zanb' => 1145, + 'zl' => 1146, + 'zp' => 1147, + 'zs' => 1148, + 'zyyy' => 1149, + 'zzzz' => 1150, +); + +1; + +# Generated from: +# d34c77b7e7a94986cc82056919f4ffc1503b73091561e16bd8ef145ac0fd04c5 lib/Unicode/UCD.pm +# fdc543859433c4578ec7991d8c3238a3638d59962eb0db446d0228cccb7a48da lib/unicore/ArabicShaping.txt +# 530831b8bdbb2a8a6bc1f2eef88224991513c7371c16537d0a7e09386a2cd326 lib/unicore/BidiBrackets.txt +# f07f44839398bc33792d988f14fcbcaf382abc3b79119e7e0bb083104260b890 lib/unicore/BidiMirroring.txt +# a1a3ca4381eb91f7b65afe7cb7df615cdcf67993fef4b486585f66b349993a10 lib/unicore/Blocks.txt +# d6caa458afc9a76d86bc2ef26a5423f4e663981904de450c97dd53ee0ab5c125 lib/unicore/CaseFolding.txt +# 08a52bd7f893f5c9a34a6d4cc3a0b2d7a44293ee45fb15d581e729b9f8584dfa lib/unicore/CompositionExclusions.txt +# 269ff9d35cbe3cb05dfadb262a6d9d89d7ad43ac6ecd7ec71f47ec036e174912 lib/unicore/DAge.txt +# b559c5ac28549ec48b9f6f14d189b503d35e33158db6b5f63e6103f51aded2cd lib/unicore/DCoreProperties.txt +# 8b4210273920c013e736332434222b73786e6c468a360710f6799eeace9b3d38 lib/unicore/DNormalizationProps.txt +# f7e61d7cd168d4496c6019148579af3adfd6e0dac8fa7cd98d8617bcd8732b28 lib/unicore/EastAsianWidth.txt +# cb048696ab01434bac59c30e5cb1f682d95022c972d8d1ebd5ea79b3841ba66c lib/unicore/EmojiData.txt +# af2928fa86e77dc2d91ed268270ca13895ede2bf29e9f0f7533f1873c0aeb4b5 lib/unicore/EquivalentUnifiedIdeograph.txt +# 2791813c07488ad72b3943bbcb2eb85bb03222271829c13bf25f79edfb214330 lib/unicore/HangulSyllableType.txt +# 1df3666ef987e492b4323a9cd907738e41656e6428752f4b1f6fd95f9bfc8adb lib/unicore/IndicPositionalCategory.txt +# b3932cf25d7ea43e1bf6be6d45094d4552f753f6b651a7a869464028f1aa88a1 lib/unicore/IndicSyllabicCategory.txt +# 035d78d5e1fb60c3b44fb7049a96c660a6d045be27ac8f4425abfbc3733724de lib/unicore/Jamo.txt +# 5afea13d57e5b11c761a9b2553806b12a5fe4e96b729398d9bf0dd94b7e6d7eb lib/unicore/LineBreak.txt +# 46cce9be0639999e6a903bfa9f1313def3c361c7ae68f411cef244132ee8097b lib/unicore/NameAliases.txt +# 0911bfd49367059219a74c69fb2c1440d256869e713619a2a231afd24357ec6e lib/unicore/NamedSequences.txt +# adf1323156ef56014549698eab7b482a3682c8e02c251a7c19f68e427b391189 lib/unicore/PropList.txt +# 648e1cb9942f02b9358edc52d523803efa491ff576aa7063d4b9aebdef7d7217 lib/unicore/PropValueAliases.txt +# 402e075e4b9d56bf46d32c950d693e5bb52c1a324a652f732401dbf5a9a4d269 lib/unicore/PropertyAliases.txt +# b77739d4b7c35069c10f8e156b71c88c5955800240c22e3a32b2ed3ea9620e5f lib/unicore/ScriptExtensions.txt +# bd327cbb8bffd2e4b40b1e9842c9a7d641d1c4e91c34a41020cf174f3a1c86a1 lib/unicore/Scripts.txt +# 22b1bff498f08633f72468d46eebb65e30dc325fbb6822dde319cb605af014c2 lib/unicore/SpecialCasing.txt +# 57913fdb1c1271fa9fd51dea08d49370f33d5bfda6bbaba348f44d90029ea11d lib/unicore/UnicodeData.txt +# 36900e28ff01fa810d8a7e0848e1075289975188525f2c1d14487d561bbf595a lib/unicore/VerticalOrientation.txt +# 238635e1dfcc190345ffbcab734f7017dea05d2a66f2291745c11067893689a7 lib/unicore/auxiliary/GCBTest.txt +# b49f36b98cdd4c996fc7971b8b4d25e3c13b45f0a71f4ad0c5e70a9cebe0b956 lib/unicore/auxiliary/GraphemeBreakProperty.txt +# d7ae54c2704f27b3a8f40ae934c2f6f3ee87bec20a865e0f9689bc1cd3f92335 lib/unicore/auxiliary/LBTest.txt +# a9fafe0badc760379957a282bbe3d82d5a6ba113911b89501781fd6b6ad66377 lib/unicore/auxiliary/SBTest.txt +# 5bf7faf5898403b6adad2d94f1a9ddf26de650cc7a8f2ee00590f05bbea9bd03 lib/unicore/auxiliary/SentenceBreakProperty.txt +# 12e02e6158929ae29c9b47f76ab95d68194b1d0c295d7b4f6df31487590222a5 lib/unicore/auxiliary/WBTest.txt +# 9be679d9772dc4842697a3a5b6e1845022f876c1f230ecea38f1be5d6d5673d8 lib/unicore/auxiliary/WordBreakProperty.txt +# 9e6955b173a13a8a91e3c1b468c9d7e122c588aa288f707bfcef35790a828f8a lib/unicore/extracted/DBidiClass.txt +# 80e94d5bb24639c9f322bd3b4b8159a8e9a7c33ac45076eff9cd3ecb0b9b812e lib/unicore/extracted/DBinaryProperties.txt +# 6dc031734cd287af8b33c99435d41f6c836e8e08a7a6cb6cb07e8453cbebdb3b lib/unicore/extracted/DCombiningClass.txt +# b143bb87f041dcb69335806cb0a1a6b2328eb25cdfa04fe6fcd4c77c6a06fe82 lib/unicore/extracted/DDecompositionType.txt +# f63f08d36d01eb45f34ff8d2b36681252211f92db690fa1258a399a9a86df3bb lib/unicore/extracted/DEastAsianWidth.txt +# 6fa015f11f19a9407d590827276f9884c1ee4c71fbc826a09008f7d9d7c1b255 lib/unicore/extracted/DGeneralCategory.txt +# 1b24a2d586a8b91c0768d4da8919634463bdf126b7479a8e76b85d007cbef8a0 lib/unicore/extracted/DJoinGroup.txt +# 8095565a527d3d0918a17e30a7bcc0c7864ac3ad748defc21027b3e1ad436368 lib/unicore/extracted/DJoinType.txt +# 5f98a68d5aa76b06052fe16312d2fdf17547fd69c4e648532845e11beaf2002b lib/unicore/extracted/DLineBreak.txt +# 8011b1733f6d2cc17576b2a1e20067eca51205e8e0b740d00ebd52afbec2ea39 lib/unicore/extracted/DNumType.txt +# 8b677a4cf17a4c6949632146fa8a99aaa65689a41b9dd231f81783e81600ff36 lib/unicore/extracted/DNumValues.txt +# bdc891efa8fc8425685f8c773bbfba47247c2d3612c9926b096fc7f794a5ffc2 lib/unicore/mktables +# 93cc868487ef3345596041bcb90c302b1b056733bb95233101bc10dc2dbe36b4 lib/unicore/version +# 4bb677187a1a64e39d48f2e341b5ecb6c99857e49d7a79cf503bd8a3c709999b regen/charset_translations.pl +# 03e51b0f07beebd5da62ab943899aa4934eee1f792fa27c1fb638c33bf4ac6ea regen/mk_PL_charclass.pl +# d62728e4cfcba3e6550ff12ad924f4811ca2077ebec705b9fecabed716764414 regen/mk_invlists.pl +# ex: set ro: diff --git a/lib/warnings.pm b/lib/warnings.pm index 8b0137c7de..ca008d241f 100644 --- a/lib/warnings.pm +++ b/lib/warnings.pm @@ -5,7 +5,7 @@ package warnings; -our $VERSION = "1.43"; +our $VERSION = "1.44"; # Verify that we're called correctly so that warnings will work. # Can't use Carp, since Carp uses us! @@ -101,6 +101,9 @@ our %Offsets = ( 'experimental::alpha_assertions' => 134, 'experimental::script_run' => 136, 'shadow' => 138, + + # Warnings Categories added in Perl 5.029 + 'experimental::private_use' => 140, ); our %Bits = ( @@ -114,13 +117,14 @@ our %Bits = ( 'digit' => "\x00\x00\x00\x00\x00\x00\x00\x40\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [31] 'exec' => "\x00\x40\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [7] 'exiting' => "\x40\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [3] - 'experimental' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x40\x55\x51\x15\x50\x01", # [51..56,58..62,66..68] + 'experimental' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x40\x55\x51\x15\x50\x11", # [51..56,58..62,66..68,70] 'experimental::alpha_assertions' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x40\x00", # [67] 'experimental::bitwise' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x10\x00\x00\x00", # [58] 'experimental::const_attr' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x40\x00\x00\x00", # [59] 'experimental::declared_refs' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x10\x00", # [66] 'experimental::lexical_subs' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00", # [52] 'experimental::postderef' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x40\x00\x00\x00\x00", # [55] + 'experimental::private_use' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x10", # [70] 'experimental::re_strict' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00", # [60] 'experimental::refaliasing' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x04\x00\x00", # [61] 'experimental::regex_sets' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x04\x00\x00\x00\x00", # [53] @@ -187,13 +191,14 @@ our %DeadBits = ( 'digit' => "\x00\x00\x00\x00\x00\x00\x00\x80\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [31] 'exec' => "\x00\x80\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [7] 'exiting' => "\x80\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [3] - 'experimental' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\xaa\xa2\x2a\xa0\x02", # [51..56,58..62,66..68] + 'experimental' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\xaa\xa2\x2a\xa0\x22", # [51..56,58..62,66..68,70] 'experimental::alpha_assertions' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\x00", # [67] 'experimental::bitwise' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x20\x00\x00\x00", # [58] 'experimental::const_attr' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\x00\x00\x00", # [59] 'experimental::declared_refs' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x20\x00", # [66] 'experimental::lexical_subs' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x02\x00\x00\x00\x00", # [52] 'experimental::postderef' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\x00\x00\x00\x00", # [55] + 'experimental::private_use' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x20", # [70] 'experimental::re_strict' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x02\x00\x00", # [60] 'experimental::refaliasing' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x08\x00\x00", # [61] 'experimental::regex_sets' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x08\x00\x00\x00\x00", # [53] @@ -251,8 +256,8 @@ our %DeadBits = ( # These are used by various things, including our own tests our $NONE = "\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"; -our $DEFAULT = "\x10\x01\x00\x00\x00\x50\x04\x00\x00\x00\x00\x00\x00\x55\x51\x55\x50\x01", # [2,4,22,23,25,52..56,58..63,66..68] -our $LAST_BIT = 140 ; +our $DEFAULT = "\x10\x01\x00\x00\x00\x50\x04\x00\x00\x00\x00\x00\x00\x55\x51\x55\x50\x11", # [2,4,22,23,25,52..56,58..63,66..68,70] +our $LAST_BIT = 142 ; our $BYTES = 18 ; sub Croaker @@ -806,6 +811,8 @@ The current hierarchy is: | | | +- experimental::postderef | | + | +- experimental::private_use + | | | +- experimental::re_strict | | | +- experimental::refaliasing diff --git a/perlapi.h b/perlapi.h index 66f5ac5f73..4cfbafecdf 100644 --- a/perlapi.h +++ b/perlapi.h @@ -123,6 +123,8 @@ END_EXTERN_C #define PL_NonFinalFold (*Perl_GNonFinalFold_ptr(NULL)) #undef PL_Posix_ptrs #define PL_Posix_ptrs (*Perl_GPosix_ptrs_ptr(NULL)) +#undef PL_Private_Use +#define PL_Private_Use (*Perl_GPrivate_Use_ptr(NULL)) #undef PL_SB_invlist #define PL_SB_invlist (*Perl_GSB_invlist_ptr(NULL)) #undef PL_SCX_invlist diff --git a/perlvars.h b/perlvars.h index edc96c46a5..466c515ebb 100644 --- a/perlvars.h +++ b/perlvars.h @@ -304,6 +304,7 @@ PERLVAR(G, utf8_charname_continue, SV *) PERLVAR(G, utf8_mark, SV *) PERLVARI(G, InBitmap, SV *, NULL) PERLVAR(G, CCC_non0_non230, SV *) +PERLVAR(G, Private_Use, SV *) /* Definitions of user-defined \p{} properties, as the subs that define them * are only called once */ diff --git a/pod/perldiag.pod b/pod/perldiag.pod index 82d3e4e768..f254e96d8b 100644 --- a/pod/perldiag.pod +++ b/pod/perldiag.pod @@ -6130,6 +6130,11 @@ the feature: (F) The function indicated isn't implemented on this architecture, according to the probings of Configure. +=item The private_use feature is experimental + +(S experimental::private_use) This feature is actually a hook for future +use. + =item The regex_sets feature is experimental (S experimental::regex_sets) This warning is emitted if you diff --git a/regcomp.c b/regcomp.c index 5cb8c6a56c..12e2454b69 100644 --- a/regcomp.c +++ b/regcomp.c @@ -21775,6 +21775,7 @@ Perl_init_uniprops(pTHX) PL_utf8_foldclosures = _new_invlist_C_array(_Perl_IVCF_invlist); PL_utf8_mark = _new_invlist_C_array(uni_prop_ptrs[UNI_M]); PL_CCC_non0_non230 = _new_invlist_C_array(_Perl_CCC_non0_non230_invlist); + PL_Private_Use = _new_invlist_C_array(uni_prop_ptrs[UNI_CO]); #ifdef UNI_XIDC /* The below are used only by deprecated functions. They could be removed */ @@ -23036,10 +23037,65 @@ Perl_parse_uniprop_string(pTHX_ /* Create and return the inversion list */ prop_definition =_new_invlist_C_array(uni_prop_ptrs[table_index]); + sv_2mortal(prop_definition); + + + /* See if there is a private use override to add to this definition */ + { + COPHH * hinthash = (IN_PERL_COMPILETIME) + ? CopHINTHASH_get(&PL_compiling) + : CopHINTHASH_get(PL_curcop); + SV * pu_overrides = cophh_fetch_pv(hinthash, "private_use", 0, 0); + + if (UNLIKELY(pu_overrides && SvPOK(pu_overrides))) { + + /* See if there is an element in the hints hash for this table */ + SV * pu_lookup = Perl_newSVpvf(aTHX_ "%d=", table_index); + const char * pos = strstr(SvPVX(pu_overrides), SvPVX(pu_lookup)); + + if (pos) { + bool dummy; + SV * pu_definition; + SV * pu_invlist; + SV * expanded_prop_definition = + sv_2mortal(invlist_clone(prop_definition, NULL)); + + /* If so, it's definition is the string from here to the next + * \a character. And its format is the same as a user-defined + * property */ + pos += SvCUR(pu_lookup); + pu_definition = newSVpvn(pos, strchr(pos, '\a') - pos); + pu_invlist = handle_user_defined_property(lookup_name, + lookup_len, + 0, /* Not UTF-8 */ + 0, /* Not folded */ + runtime, + pu_definition, + &dummy, + msg, + level); + if (TAINT_get) { + if (SvCUR(msg) > 0) sv_catpvs(msg, "; "); + sv_catpvs(msg, "Insecure private-use override"); + goto append_name_to_msg; + } + + /* For now, as a safety measure, make sure that it doesn't + * override non-private use code points */ + _invlist_intersection(pu_invlist, PL_Private_Use, &pu_invlist); + + /* Add it to the list to be returned */ + _invlist_union(prop_definition, pu_invlist, + &expanded_prop_definition); + prop_definition = expanded_prop_definition; + Perl_ck_warner_d(aTHX_ packWARN(WARN_EXPERIMENTAL__PRIVATE_USE), "The private_use feature is experimental"); + } + } + } + if (invert_return) { _invlist_invert(prop_definition); } - sv_2mortal(prop_definition); return prop_definition; diff --git a/regen/mk_invlists.pl b/regen/mk_invlists.pl index 61148282b5..f6515ef567 100644 --- a/regen/mk_invlists.pl +++ b/regen/mk_invlists.pl @@ -3012,6 +3012,42 @@ my @sources = qw(regen/mk_invlists.pl read_only_bottom_close_and_rename($out_fh, \@sources); +use Data::Dumper; +my %name_to_index; +for my $i (0 .. @enums - 1) { + my $loose_name = $enums[$i] =~ s/^$table_name_prefix//r; + $loose_name = lc $loose_name; + $loose_name =~ s/__/=/; + $loose_name =~ s/_dot_/./; + $loose_name =~ s/_slash_/\//g; + $name_to_index{$loose_name} = $i + 1; +} +# unsanitize, exclude &, maybe add these before sanitize +for my $i (0 .. @perl_prop_synonyms - 1) { + my $loose_name_pair = $perl_prop_synonyms[$i] =~ s/#\s*define\s*//r; + $loose_name_pair =~ s/\b$table_name_prefix//g; + $loose_name_pair = lc $loose_name_pair; + $loose_name_pair =~ s/__/=/g; + $loose_name_pair =~ s/_dot_/./g; + $loose_name_pair =~ s/_slash_/\//g; + my ($synonym, $primary) = split / +/, $loose_name_pair; + $name_to_index{$synonym} = $name_to_index{$primary}; +} + +my $uni_pl = open_new('lib/unicore/uni_keywords.pl', '>', + {style => '*', by => 'regen/mk_invlists.pl', + from => "Unicode::UCD"}); +{ + print $uni_pl "\%utf8::uni_prop_ptrs_indices = (\n"; + for my $name (sort keys %name_to_index) { + print STDERR __LINE__, $name, "\n" unless defined $name_to_index{$name}; + print $uni_pl " '$name' => $name_to_index{$name},\n"; + } + print $uni_pl ");\n\n1;\n"; +} + +read_only_bottom_close_and_rename($uni_pl, \@sources); + require './regen/mph.pl'; sub token_name diff --git a/regen/warnings.pl b/regen/warnings.pl index 504d86288e..ff08a2f0ce 100644 --- a/regen/warnings.pl +++ b/regen/warnings.pl @@ -16,7 +16,7 @@ # # This script is normally invoked from regen.pl. -$VERSION = '1.43'; +$VERSION = '1.44'; BEGIN { require './regen/regen_lib.pl'; @@ -111,6 +111,8 @@ my $tree = { [ 5.027, DEFAULT_ON ], 'experimental::alpha_assertions' => [ 5.027, DEFAULT_ON ], + 'experimental::private_use' => + [ 5.029, DEFAULT_ON ], }], 'missing' => [ 5.021, DEFAULT_OFF], diff --git a/regexec.c b/regexec.c index bb3a630e87..e50145d449 100644 --- a/regexec.c +++ b/regexec.c @@ -4290,14 +4290,14 @@ S_reg_check_named_buff_matched(const regexp *rex, const regnode *scan) return 0; } - static bool S_setup_EXACTISH_ST_c1_c2(pTHX_ const regnode * const text_node, int *c1p, U8* c1_utf8, int *c2p, U8* c2_utf8, regmatch_info *reginfo) { - /* This function determines if there are one or two characters that match - * the first character of the passed-in EXACTish node <text_node>, and if - * so, returns them in the passed-in pointers. + /* This function determines if there are zero, one, two, or more characters + * that match the first character of the passed-in EXACTish node + * <text_node>, and if there are one or two, it returns them in the + * passed-in pointers. * * If it determines that no possible character in the target string can * match, it returns FALSE; otherwise TRUE. (The FALSE situation occurs if @@ -4371,6 +4371,7 @@ S_setup_EXACTISH_ST_c1_c2(pTHX_ const regnode * const text_node, int *c1p, * copy the input to the output, avoiding finding the code point of * that character */ if (!is_utf8_pat) { + assert(OP(text_node) != EXACT_ONLY8); c2 = c1 = *pat; } else if (utf8_target) { @@ -4378,6 +4379,9 @@ S_setup_EXACTISH_ST_c1_c2(pTHX_ const regnode * const text_node, int *c1p, Copy(pat, c2_utf8, UTF8SKIP(pat), U8); utf8_has_been_setup = TRUE; } + else if (OP(text_node) == EXACT_ONLY8) { + return FALSE; /* Can only match UTF-8 target */ + } else { c2 = c1 = valid_utf8_to_uvchr(pat, NULL); } @@ -4548,6 +4552,9 @@ S_setup_EXACTISH_ST_c1_c2(pTHX_ const regnode * const text_node, int *c1p, case EXACTFU: c2 = PL_fold_latin1[c1]; break; + case EXACTFU_ONLY8: + return FALSE; + NOT_REACHED; /* NOTREACHED */ default: Perl_croak(aTHX_ "panic: Unexpected op %u", OP(text_node)); diff --git a/t/re/subst.t b/t/re/subst.t index dd62e95ee6..32076921f5 100644 --- a/t/re/subst.t +++ b/t/re/subst.t @@ -11,7 +11,7 @@ BEGIN { require './loc_tools.pl'; } -plan(tests => 276); +plan(tests => 277); $_ = 'david'; $a = s/david/rules/r; @@ -1174,5 +1174,8 @@ __EOF__ is $lines, 4, "RT #131930"; } +{ # [perl $133899], would panic - + fresh_perl_is('my $a = "ha"; $a =~ s!|0?h\x{300}(?{})!!gi', "", {}, + "[perl #133899] s!|0?h\\x{300}(?{})!!gi panics"); +} diff --git a/uni_keywords.h b/uni_keywords.h index 4660ddf44c..a242c551b4 100644 --- a/uni_keywords.h +++ b/uni_keywords.h @@ -7129,6 +7129,6 @@ MPH_VALt match_uniprop( const unsigned char * const key, const U16 key_len ) { * 93cc868487ef3345596041bcb90c302b1b056733bb95233101bc10dc2dbe36b4 lib/unicore/version * 2680b9254eb236c5c090f11b149605043e8c8433661b96efc4a42fb4709342a5 regen/charset_translations.pl * 03e51b0f07beebd5da62ab943899aa4934eee1f792fa27c1fb638c33bf4ac6ea regen/mk_PL_charclass.pl - * 2fb19108265d37fc38920cd3f775c5c9fc25ae8b95be3bf197f47da1dc4989f4 regen/mk_invlists.pl + * d62728e4cfcba3e6550ff12ad924f4811ca2077ebec705b9fecabed716764414 regen/mk_invlists.pl * c56b78df81e0f96632246052d71580b212546ca02ba4075158965e11d892f21e regen/mph.pl * ex: set ro: */ diff --git a/warnings.h b/warnings.h index d076e7acc1..ba15ba94da 100644 --- a/warnings.h +++ b/warnings.h @@ -121,6 +121,10 @@ #define WARN_EXPERIMENTAL__SCRIPT_RUN 68 #define WARN_SHADOW 69 +/* Warnings Categories added in Perl 5.029 */ + +#define WARN_EXPERIMENTAL__PRIVATE_USE 70 + #define WARNsize 18 #define WARN_ALLstring "\125\125\125\125\125\125\125\125\125\125\125\125\125\125\125\125\125\125" #define WARN_NONEstring "\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0" -- Perl5 Master Repository
