https://github.com/python/cpython/commit/d397a4979cfc80a8cd6c73838aa10e9c8cf5ef72 commit: d397a4979cfc80a8cd6c73838aa10e9c8cf5ef72 branch: 3.10 author: Petr Viktorin <[email protected]> committer: pablogsal <[email protected]> date: 2026-10-01T01:29:35+01:00 summary:
[3.10] gh-155292: Don't consider Unicode codepoint attributes outside RFC 3454 (GH-155293) (GH-156020) (#156932) * [3.10] gh-155292: Don't consider Unicode codepoint attributes outside RFC 3454 (GH-155293) (GH-156020) Due to a bug, some Unicode codepoint attributes were considered for characters not yet defined in Unicode 3.2.0 or attributes which changed in later Unicode versions. RFC 3454 (StringPrep) requires using Unicode 3.2.0 strictly. (cherry picked from commit 7e109d084d55e7eb25837a5f3b47ef9beee547bc) The cherry-pick needed reworking as GH-144815 wasn't backported to 3.14 and below, so unassigned characters don't have bidi values. (cherry picked from commit 1e54caa096678a38afcabecabb1ff72400dd6bae) Co-authored-by: Petr Viktorin <[email protected]> Co-authored-by: Seth Larson <[email protected]> Co-authored-by: Stan Ulbrych <[email protected]> Co-authored-by: Petr Viktorin <[email protected]> * Add Unicode_3_2_0_FunctionsTest * Regenerate Unicode data --------- Co-authored-by: Seth Larson <[email protected]> Co-authored-by: Stan Ulbrych <[email protected]> files: A Misc/NEWS.d/next/Security/2026-08-06-11-43-20.gh-issue-155292.j4pHBO.rst M Lib/stringprep.py M Lib/test/test_codecs.py M Lib/test/test_unicodedata.py M Tools/unicode/makeunicodedata.py M Tools/unicode/mkstringprep.py diff --git a/Lib/stringprep.py b/Lib/stringprep.py index 44ecdb266ce8b95..aec1d5a999b5da0 100644 --- a/Lib/stringprep.py +++ b/Lib/stringprep.py @@ -5,12 +5,18 @@ and mappings, for which a mapping function is provided. """ -from unicodedata import ucd_3_2_0 as unicodedata +# This check asserts that mkstringprep.py has been run +# when unicodedata is modified to ensure conformant behavior. +import unicodedata -assert unicodedata.unidata_version == '3.2.0' +assert unicodedata.unidata_version == '13.0.0' + +from unicodedata import ucd_3_2_0 as unicodedata_320 + +assert unicodedata_320.unidata_version == '3.2.0' def in_table_a1(code): - if unicodedata.category(code) != 'Cn': return False + if unicodedata_320.category(code) != 'Cn': return False c = ord(code) if 0xFDD0 <= c < 0xFDF0: return False return (c & 0xFFFF) not in (0xFFFE, 0xFFFF) @@ -22,14 +28,69 @@ def in_table_b1(code): b3_exceptions = { -0xb5:'\u03bc', 0xdf:'ss', 0x130:'i\u0307', 0x149:'\u02bcn', -0x17f:'s', 0x1f0:'j\u030c', 0x345:'\u03b9', 0x37a:' \u03b9', -0x390:'\u03b9\u0308\u0301', 0x3b0:'\u03c5\u0308\u0301', 0x3c2:'\u03c3', 0x3d0:'\u03b2', -0x3d1:'\u03b8', 0x3d2:'\u03c5', 0x3d3:'\u03cd', 0x3d4:'\u03cb', -0x3d5:'\u03c6', 0x3d6:'\u03c0', 0x3f0:'\u03ba', 0x3f1:'\u03c1', -0x3f2:'\u03c3', 0x3f5:'\u03b5', 0x587:'\u0565\u0582', 0x1e96:'h\u0331', +0xb5:'\u03bc', 0xdf:'ss', 0x149:'\u02bcn', 0x17f:'s', +0x1f0:'j\u030c', 0x23a:'\u023a', 0x23b:'\u023b', 0x23d:'\u023d', +0x23e:'\u023e', 0x241:'\u0241', 0x243:'\u0243', 0x244:'\u0244', +0x245:'\u0245', 0x246:'\u0246', 0x248:'\u0248', 0x24a:'\u024a', +0x24c:'\u024c', 0x24e:'\u024e', 0x345:'\u03b9', 0x370:'\u0370', +0x372:'\u0372', 0x376:'\u0376', 0x37a:' \u03b9', 0x37f:'\u037f', +0x390:'\u03b9\u0308\u0301', 0x3b0:'\u03c5\u0308\u0301', 0x3c2:'\u03c3', 0x3cf:'\u03cf', +0x3d0:'\u03b2', 0x3d1:'\u03b8', 0x3d2:'\u03c5', 0x3d3:'\u03cd', +0x3d4:'\u03cb', 0x3d5:'\u03c6', 0x3d6:'\u03c0', 0x3f0:'\u03ba', +0x3f1:'\u03c1', 0x3f2:'\u03c3', 0x3f5:'\u03b5', 0x3f7:'\u03f7', +0x3f9:'\u03f9', 0x3fa:'\u03fa', 0x3fd:'\u03fd', 0x3fe:'\u03fe', +0x3ff:'\u03ff', 0x4c0:'\u04c0', 0x4f6:'\u04f6', 0x4fa:'\u04fa', +0x4fc:'\u04fc', 0x4fe:'\u04fe', 0x510:'\u0510', 0x512:'\u0512', +0x514:'\u0514', 0x516:'\u0516', 0x518:'\u0518', 0x51a:'\u051a', +0x51c:'\u051c', 0x51e:'\u051e', 0x520:'\u0520', 0x522:'\u0522', +0x524:'\u0524', 0x526:'\u0526', 0x528:'\u0528', 0x52a:'\u052a', +0x52c:'\u052c', 0x52e:'\u052e', 0x587:'\u0565\u0582', 0x10a0:'\u10a0', +0x10a1:'\u10a1', 0x10a2:'\u10a2', 0x10a3:'\u10a3', 0x10a4:'\u10a4', +0x10a5:'\u10a5', 0x10a6:'\u10a6', 0x10a7:'\u10a7', 0x10a8:'\u10a8', +0x10a9:'\u10a9', 0x10aa:'\u10aa', 0x10ab:'\u10ab', 0x10ac:'\u10ac', +0x10ad:'\u10ad', 0x10ae:'\u10ae', 0x10af:'\u10af', 0x10b0:'\u10b0', +0x10b1:'\u10b1', 0x10b2:'\u10b2', 0x10b3:'\u10b3', 0x10b4:'\u10b4', +0x10b5:'\u10b5', 0x10b6:'\u10b6', 0x10b7:'\u10b7', 0x10b8:'\u10b8', +0x10b9:'\u10b9', 0x10ba:'\u10ba', 0x10bb:'\u10bb', 0x10bc:'\u10bc', +0x10bd:'\u10bd', 0x10be:'\u10be', 0x10bf:'\u10bf', 0x10c0:'\u10c0', +0x10c1:'\u10c1', 0x10c2:'\u10c2', 0x10c3:'\u10c3', 0x10c4:'\u10c4', +0x10c5:'\u10c5', 0x10c7:'\u10c7', 0x10cd:'\u10cd', 0x13a0:'\u13a0', +0x13a1:'\u13a1', 0x13a2:'\u13a2', 0x13a3:'\u13a3', 0x13a4:'\u13a4', +0x13a5:'\u13a5', 0x13a6:'\u13a6', 0x13a7:'\u13a7', 0x13a8:'\u13a8', +0x13a9:'\u13a9', 0x13aa:'\u13aa', 0x13ab:'\u13ab', 0x13ac:'\u13ac', +0x13ad:'\u13ad', 0x13ae:'\u13ae', 0x13af:'\u13af', 0x13b0:'\u13b0', +0x13b1:'\u13b1', 0x13b2:'\u13b2', 0x13b3:'\u13b3', 0x13b4:'\u13b4', +0x13b5:'\u13b5', 0x13b6:'\u13b6', 0x13b7:'\u13b7', 0x13b8:'\u13b8', +0x13b9:'\u13b9', 0x13ba:'\u13ba', 0x13bb:'\u13bb', 0x13bc:'\u13bc', +0x13bd:'\u13bd', 0x13be:'\u13be', 0x13bf:'\u13bf', 0x13c0:'\u13c0', +0x13c1:'\u13c1', 0x13c2:'\u13c2', 0x13c3:'\u13c3', 0x13c4:'\u13c4', +0x13c5:'\u13c5', 0x13c6:'\u13c6', 0x13c7:'\u13c7', 0x13c8:'\u13c8', +0x13c9:'\u13c9', 0x13ca:'\u13ca', 0x13cb:'\u13cb', 0x13cc:'\u13cc', +0x13cd:'\u13cd', 0x13ce:'\u13ce', 0x13cf:'\u13cf', 0x13d0:'\u13d0', +0x13d1:'\u13d1', 0x13d2:'\u13d2', 0x13d3:'\u13d3', 0x13d4:'\u13d4', +0x13d5:'\u13d5', 0x13d6:'\u13d6', 0x13d7:'\u13d7', 0x13d8:'\u13d8', +0x13d9:'\u13d9', 0x13da:'\u13da', 0x13db:'\u13db', 0x13dc:'\u13dc', +0x13dd:'\u13dd', 0x13de:'\u13de', 0x13df:'\u13df', 0x13e0:'\u13e0', +0x13e1:'\u13e1', 0x13e2:'\u13e2', 0x13e3:'\u13e3', 0x13e4:'\u13e4', +0x13e5:'\u13e5', 0x13e6:'\u13e6', 0x13e7:'\u13e7', 0x13e8:'\u13e8', +0x13e9:'\u13e9', 0x13ea:'\u13ea', 0x13eb:'\u13eb', 0x13ec:'\u13ec', +0x13ed:'\u13ed', 0x13ee:'\u13ee', 0x13ef:'\u13ef', 0x13f0:'\u13f0', +0x13f1:'\u13f1', 0x13f2:'\u13f2', 0x13f3:'\u13f3', 0x13f4:'\u13f4', +0x13f5:'\u13f5', 0x1c90:'\u1c90', 0x1c91:'\u1c91', 0x1c92:'\u1c92', +0x1c93:'\u1c93', 0x1c94:'\u1c94', 0x1c95:'\u1c95', 0x1c96:'\u1c96', +0x1c97:'\u1c97', 0x1c98:'\u1c98', 0x1c99:'\u1c99', 0x1c9a:'\u1c9a', +0x1c9b:'\u1c9b', 0x1c9c:'\u1c9c', 0x1c9d:'\u1c9d', 0x1c9e:'\u1c9e', +0x1c9f:'\u1c9f', 0x1ca0:'\u1ca0', 0x1ca1:'\u1ca1', 0x1ca2:'\u1ca2', +0x1ca3:'\u1ca3', 0x1ca4:'\u1ca4', 0x1ca5:'\u1ca5', 0x1ca6:'\u1ca6', +0x1ca7:'\u1ca7', 0x1ca8:'\u1ca8', 0x1ca9:'\u1ca9', 0x1caa:'\u1caa', +0x1cab:'\u1cab', 0x1cac:'\u1cac', 0x1cad:'\u1cad', 0x1cae:'\u1cae', +0x1caf:'\u1caf', 0x1cb0:'\u1cb0', 0x1cb1:'\u1cb1', 0x1cb2:'\u1cb2', +0x1cb3:'\u1cb3', 0x1cb4:'\u1cb4', 0x1cb5:'\u1cb5', 0x1cb6:'\u1cb6', +0x1cb7:'\u1cb7', 0x1cb8:'\u1cb8', 0x1cb9:'\u1cb9', 0x1cba:'\u1cba', +0x1cbd:'\u1cbd', 0x1cbe:'\u1cbe', 0x1cbf:'\u1cbf', 0x1e96:'h\u0331', 0x1e97:'t\u0308', 0x1e98:'w\u030a', 0x1e99:'y\u030a', 0x1e9a:'a\u02be', -0x1e9b:'\u1e61', 0x1f50:'\u03c5\u0313', 0x1f52:'\u03c5\u0313\u0300', 0x1f54:'\u03c5\u0313\u0301', +0x1e9b:'\u1e61', 0x1e9e:'\u1e9e', 0x1efa:'\u1efa', 0x1efc:'\u1efc', +0x1efe:'\u1efe', 0x1f50:'\u03c5\u0313', 0x1f52:'\u03c5\u0313\u0300', 0x1f54:'\u03c5\u0313\u0301', 0x1f56:'\u03c5\u0313\u0342', 0x1f80:'\u1f00\u03b9', 0x1f81:'\u1f01\u03b9', 0x1f82:'\u1f02\u03b9', 0x1f83:'\u1f03\u03b9', 0x1f84:'\u1f04\u03b9', 0x1f85:'\u1f05\u03b9', 0x1f86:'\u1f06\u03b9', 0x1f87:'\u1f07\u03b9', 0x1f88:'\u1f00\u03b9', 0x1f89:'\u1f01\u03b9', 0x1f8a:'\u1f02\u03b9', @@ -56,135 +117,241 @@ def in_table_b1(code): 0x211b:'r', 0x211c:'r', 0x211d:'r', 0x2120:'sm', 0x2121:'tel', 0x2122:'tm', 0x2124:'z', 0x2128:'z', 0x212c:'b', 0x212d:'c', 0x2130:'e', 0x2131:'f', -0x2133:'m', 0x213e:'\u03b3', 0x213f:'\u03c0', 0x2145:'d', -0x3371:'hpa', 0x3373:'au', 0x3375:'ov', 0x3380:'pa', -0x3381:'na', 0x3382:'\u03bca', 0x3383:'ma', 0x3384:'ka', -0x3385:'kb', 0x3386:'mb', 0x3387:'gb', 0x338a:'pf', -0x338b:'nf', 0x338c:'\u03bcf', 0x3390:'hz', 0x3391:'khz', -0x3392:'mhz', 0x3393:'ghz', 0x3394:'thz', 0x33a9:'pa', -0x33aa:'kpa', 0x33ab:'mpa', 0x33ac:'gpa', 0x33b4:'pv', -0x33b5:'nv', 0x33b6:'\u03bcv', 0x33b7:'mv', 0x33b8:'kv', -0x33b9:'mv', 0x33ba:'pw', 0x33bb:'nw', 0x33bc:'\u03bcw', -0x33bd:'mw', 0x33be:'kw', 0x33bf:'mw', 0x33c0:'k\u03c9', -0x33c1:'m\u03c9', 0x33c3:'bq', 0x33c6:'c\u2215kg', 0x33c7:'co.', -0x33c8:'db', 0x33c9:'gy', 0x33cb:'hp', 0x33cd:'kk', -0x33ce:'km', 0x33d7:'ph', 0x33d9:'ppm', 0x33da:'pr', -0x33dc:'sv', 0x33dd:'wb', 0xfb00:'ff', 0xfb01:'fi', +0x2132:'\u2132', 0x2133:'m', 0x213e:'\u03b3', 0x213f:'\u03c0', +0x2145:'d', 0x2183:'\u2183', 0x2c00:'\u2c00', 0x2c01:'\u2c01', +0x2c02:'\u2c02', 0x2c03:'\u2c03', 0x2c04:'\u2c04', 0x2c05:'\u2c05', +0x2c06:'\u2c06', 0x2c07:'\u2c07', 0x2c08:'\u2c08', 0x2c09:'\u2c09', +0x2c0a:'\u2c0a', 0x2c0b:'\u2c0b', 0x2c0c:'\u2c0c', 0x2c0d:'\u2c0d', +0x2c0e:'\u2c0e', 0x2c0f:'\u2c0f', 0x2c10:'\u2c10', 0x2c11:'\u2c11', +0x2c12:'\u2c12', 0x2c13:'\u2c13', 0x2c14:'\u2c14', 0x2c15:'\u2c15', +0x2c16:'\u2c16', 0x2c17:'\u2c17', 0x2c18:'\u2c18', 0x2c19:'\u2c19', +0x2c1a:'\u2c1a', 0x2c1b:'\u2c1b', 0x2c1c:'\u2c1c', 0x2c1d:'\u2c1d', +0x2c1e:'\u2c1e', 0x2c1f:'\u2c1f', 0x2c20:'\u2c20', 0x2c21:'\u2c21', +0x2c22:'\u2c22', 0x2c23:'\u2c23', 0x2c24:'\u2c24', 0x2c25:'\u2c25', +0x2c26:'\u2c26', 0x2c27:'\u2c27', 0x2c28:'\u2c28', 0x2c29:'\u2c29', +0x2c2a:'\u2c2a', 0x2c2b:'\u2c2b', 0x2c2c:'\u2c2c', 0x2c2d:'\u2c2d', +0x2c2e:'\u2c2e', 0x2c60:'\u2c60', 0x2c62:'\u2c62', 0x2c63:'\u2c63', +0x2c64:'\u2c64', 0x2c67:'\u2c67', 0x2c69:'\u2c69', 0x2c6b:'\u2c6b', +0x2c6d:'\u2c6d', 0x2c6e:'\u2c6e', 0x2c6f:'\u2c6f', 0x2c70:'\u2c70', +0x2c72:'\u2c72', 0x2c75:'\u2c75', 0x2c7e:'\u2c7e', 0x2c7f:'\u2c7f', +0x2c80:'\u2c80', 0x2c82:'\u2c82', 0x2c84:'\u2c84', 0x2c86:'\u2c86', +0x2c88:'\u2c88', 0x2c8a:'\u2c8a', 0x2c8c:'\u2c8c', 0x2c8e:'\u2c8e', +0x2c90:'\u2c90', 0x2c92:'\u2c92', 0x2c94:'\u2c94', 0x2c96:'\u2c96', +0x2c98:'\u2c98', 0x2c9a:'\u2c9a', 0x2c9c:'\u2c9c', 0x2c9e:'\u2c9e', +0x2ca0:'\u2ca0', 0x2ca2:'\u2ca2', 0x2ca4:'\u2ca4', 0x2ca6:'\u2ca6', +0x2ca8:'\u2ca8', 0x2caa:'\u2caa', 0x2cac:'\u2cac', 0x2cae:'\u2cae', +0x2cb0:'\u2cb0', 0x2cb2:'\u2cb2', 0x2cb4:'\u2cb4', 0x2cb6:'\u2cb6', +0x2cb8:'\u2cb8', 0x2cba:'\u2cba', 0x2cbc:'\u2cbc', 0x2cbe:'\u2cbe', +0x2cc0:'\u2cc0', 0x2cc2:'\u2cc2', 0x2cc4:'\u2cc4', 0x2cc6:'\u2cc6', +0x2cc8:'\u2cc8', 0x2cca:'\u2cca', 0x2ccc:'\u2ccc', 0x2cce:'\u2cce', +0x2cd0:'\u2cd0', 0x2cd2:'\u2cd2', 0x2cd4:'\u2cd4', 0x2cd6:'\u2cd6', +0x2cd8:'\u2cd8', 0x2cda:'\u2cda', 0x2cdc:'\u2cdc', 0x2cde:'\u2cde', +0x2ce0:'\u2ce0', 0x2ce2:'\u2ce2', 0x2ceb:'\u2ceb', 0x2ced:'\u2ced', +0x2cf2:'\u2cf2', 0x3371:'hpa', 0x3373:'au', 0x3375:'ov', +0x3380:'pa', 0x3381:'na', 0x3382:'\u03bca', 0x3383:'ma', +0x3384:'ka', 0x3385:'kb', 0x3386:'mb', 0x3387:'gb', +0x338a:'pf', 0x338b:'nf', 0x338c:'\u03bcf', 0x3390:'hz', +0x3391:'khz', 0x3392:'mhz', 0x3393:'ghz', 0x3394:'thz', +0x33a9:'pa', 0x33aa:'kpa', 0x33ab:'mpa', 0x33ac:'gpa', +0x33b4:'pv', 0x33b5:'nv', 0x33b6:'\u03bcv', 0x33b7:'mv', +0x33b8:'kv', 0x33b9:'mv', 0x33ba:'pw', 0x33bb:'nw', +0x33bc:'\u03bcw', 0x33bd:'mw', 0x33be:'kw', 0x33bf:'mw', +0x33c0:'k\u03c9', 0x33c1:'m\u03c9', 0x33c3:'bq', 0x33c6:'c\u2215kg', +0x33c7:'co.', 0x33c8:'db', 0x33c9:'gy', 0x33cb:'hp', +0x33cd:'kk', 0x33ce:'km', 0x33d7:'ph', 0x33d9:'ppm', +0x33da:'pr', 0x33dc:'sv', 0x33dd:'wb', 0xa640:'\ua640', +0xa642:'\ua642', 0xa644:'\ua644', 0xa646:'\ua646', 0xa648:'\ua648', +0xa64a:'\ua64a', 0xa64c:'\ua64c', 0xa64e:'\ua64e', 0xa650:'\ua650', +0xa652:'\ua652', 0xa654:'\ua654', 0xa656:'\ua656', 0xa658:'\ua658', +0xa65a:'\ua65a', 0xa65c:'\ua65c', 0xa65e:'\ua65e', 0xa660:'\ua660', +0xa662:'\ua662', 0xa664:'\ua664', 0xa666:'\ua666', 0xa668:'\ua668', +0xa66a:'\ua66a', 0xa66c:'\ua66c', 0xa680:'\ua680', 0xa682:'\ua682', +0xa684:'\ua684', 0xa686:'\ua686', 0xa688:'\ua688', 0xa68a:'\ua68a', +0xa68c:'\ua68c', 0xa68e:'\ua68e', 0xa690:'\ua690', 0xa692:'\ua692', +0xa694:'\ua694', 0xa696:'\ua696', 0xa698:'\ua698', 0xa69a:'\ua69a', +0xa722:'\ua722', 0xa724:'\ua724', 0xa726:'\ua726', 0xa728:'\ua728', +0xa72a:'\ua72a', 0xa72c:'\ua72c', 0xa72e:'\ua72e', 0xa732:'\ua732', +0xa734:'\ua734', 0xa736:'\ua736', 0xa738:'\ua738', 0xa73a:'\ua73a', +0xa73c:'\ua73c', 0xa73e:'\ua73e', 0xa740:'\ua740', 0xa742:'\ua742', +0xa744:'\ua744', 0xa746:'\ua746', 0xa748:'\ua748', 0xa74a:'\ua74a', +0xa74c:'\ua74c', 0xa74e:'\ua74e', 0xa750:'\ua750', 0xa752:'\ua752', +0xa754:'\ua754', 0xa756:'\ua756', 0xa758:'\ua758', 0xa75a:'\ua75a', +0xa75c:'\ua75c', 0xa75e:'\ua75e', 0xa760:'\ua760', 0xa762:'\ua762', +0xa764:'\ua764', 0xa766:'\ua766', 0xa768:'\ua768', 0xa76a:'\ua76a', +0xa76c:'\ua76c', 0xa76e:'\ua76e', 0xa779:'\ua779', 0xa77b:'\ua77b', +0xa77d:'\ua77d', 0xa77e:'\ua77e', 0xa780:'\ua780', 0xa782:'\ua782', +0xa784:'\ua784', 0xa786:'\ua786', 0xa78b:'\ua78b', 0xa78d:'\ua78d', +0xa790:'\ua790', 0xa792:'\ua792', 0xa796:'\ua796', 0xa798:'\ua798', +0xa79a:'\ua79a', 0xa79c:'\ua79c', 0xa79e:'\ua79e', 0xa7a0:'\ua7a0', +0xa7a2:'\ua7a2', 0xa7a4:'\ua7a4', 0xa7a6:'\ua7a6', 0xa7a8:'\ua7a8', +0xa7aa:'\ua7aa', 0xa7ab:'\ua7ab', 0xa7ac:'\ua7ac', 0xa7ad:'\ua7ad', +0xa7ae:'\ua7ae', 0xa7b0:'\ua7b0', 0xa7b1:'\ua7b1', 0xa7b2:'\ua7b2', +0xa7b3:'\ua7b3', 0xa7b4:'\ua7b4', 0xa7b6:'\ua7b6', 0xa7b8:'\ua7b8', +0xa7ba:'\ua7ba', 0xa7bc:'\ua7bc', 0xa7be:'\ua7be', 0xa7c2:'\ua7c2', +0xa7c4:'\ua7c4', 0xa7c5:'\ua7c5', 0xa7c6:'\ua7c6', 0xa7c7:'\ua7c7', +0xa7c9:'\ua7c9', 0xa7f5:'\ua7f5', 0xfb00:'ff', 0xfb01:'fi', 0xfb02:'fl', 0xfb03:'ffi', 0xfb04:'ffl', 0xfb05:'st', 0xfb06:'st', 0xfb13:'\u0574\u0576', 0xfb14:'\u0574\u0565', 0xfb15:'\u0574\u056b', -0xfb16:'\u057e\u0576', 0xfb17:'\u0574\u056d', 0x1d400:'a', 0x1d401:'b', -0x1d402:'c', 0x1d403:'d', 0x1d404:'e', 0x1d405:'f', -0x1d406:'g', 0x1d407:'h', 0x1d408:'i', 0x1d409:'j', -0x1d40a:'k', 0x1d40b:'l', 0x1d40c:'m', 0x1d40d:'n', -0x1d40e:'o', 0x1d40f:'p', 0x1d410:'q', 0x1d411:'r', -0x1d412:'s', 0x1d413:'t', 0x1d414:'u', 0x1d415:'v', -0x1d416:'w', 0x1d417:'x', 0x1d418:'y', 0x1d419:'z', -0x1d434:'a', 0x1d435:'b', 0x1d436:'c', 0x1d437:'d', -0x1d438:'e', 0x1d439:'f', 0x1d43a:'g', 0x1d43b:'h', -0x1d43c:'i', 0x1d43d:'j', 0x1d43e:'k', 0x1d43f:'l', -0x1d440:'m', 0x1d441:'n', 0x1d442:'o', 0x1d443:'p', -0x1d444:'q', 0x1d445:'r', 0x1d446:'s', 0x1d447:'t', -0x1d448:'u', 0x1d449:'v', 0x1d44a:'w', 0x1d44b:'x', -0x1d44c:'y', 0x1d44d:'z', 0x1d468:'a', 0x1d469:'b', -0x1d46a:'c', 0x1d46b:'d', 0x1d46c:'e', 0x1d46d:'f', -0x1d46e:'g', 0x1d46f:'h', 0x1d470:'i', 0x1d471:'j', -0x1d472:'k', 0x1d473:'l', 0x1d474:'m', 0x1d475:'n', -0x1d476:'o', 0x1d477:'p', 0x1d478:'q', 0x1d479:'r', -0x1d47a:'s', 0x1d47b:'t', 0x1d47c:'u', 0x1d47d:'v', -0x1d47e:'w', 0x1d47f:'x', 0x1d480:'y', 0x1d481:'z', -0x1d49c:'a', 0x1d49e:'c', 0x1d49f:'d', 0x1d4a2:'g', -0x1d4a5:'j', 0x1d4a6:'k', 0x1d4a9:'n', 0x1d4aa:'o', -0x1d4ab:'p', 0x1d4ac:'q', 0x1d4ae:'s', 0x1d4af:'t', -0x1d4b0:'u', 0x1d4b1:'v', 0x1d4b2:'w', 0x1d4b3:'x', -0x1d4b4:'y', 0x1d4b5:'z', 0x1d4d0:'a', 0x1d4d1:'b', -0x1d4d2:'c', 0x1d4d3:'d', 0x1d4d4:'e', 0x1d4d5:'f', -0x1d4d6:'g', 0x1d4d7:'h', 0x1d4d8:'i', 0x1d4d9:'j', -0x1d4da:'k', 0x1d4db:'l', 0x1d4dc:'m', 0x1d4dd:'n', -0x1d4de:'o', 0x1d4df:'p', 0x1d4e0:'q', 0x1d4e1:'r', -0x1d4e2:'s', 0x1d4e3:'t', 0x1d4e4:'u', 0x1d4e5:'v', -0x1d4e6:'w', 0x1d4e7:'x', 0x1d4e8:'y', 0x1d4e9:'z', -0x1d504:'a', 0x1d505:'b', 0x1d507:'d', 0x1d508:'e', -0x1d509:'f', 0x1d50a:'g', 0x1d50d:'j', 0x1d50e:'k', -0x1d50f:'l', 0x1d510:'m', 0x1d511:'n', 0x1d512:'o', -0x1d513:'p', 0x1d514:'q', 0x1d516:'s', 0x1d517:'t', -0x1d518:'u', 0x1d519:'v', 0x1d51a:'w', 0x1d51b:'x', -0x1d51c:'y', 0x1d538:'a', 0x1d539:'b', 0x1d53b:'d', -0x1d53c:'e', 0x1d53d:'f', 0x1d53e:'g', 0x1d540:'i', -0x1d541:'j', 0x1d542:'k', 0x1d543:'l', 0x1d544:'m', -0x1d546:'o', 0x1d54a:'s', 0x1d54b:'t', 0x1d54c:'u', -0x1d54d:'v', 0x1d54e:'w', 0x1d54f:'x', 0x1d550:'y', -0x1d56c:'a', 0x1d56d:'b', 0x1d56e:'c', 0x1d56f:'d', -0x1d570:'e', 0x1d571:'f', 0x1d572:'g', 0x1d573:'h', -0x1d574:'i', 0x1d575:'j', 0x1d576:'k', 0x1d577:'l', -0x1d578:'m', 0x1d579:'n', 0x1d57a:'o', 0x1d57b:'p', -0x1d57c:'q', 0x1d57d:'r', 0x1d57e:'s', 0x1d57f:'t', -0x1d580:'u', 0x1d581:'v', 0x1d582:'w', 0x1d583:'x', -0x1d584:'y', 0x1d585:'z', 0x1d5a0:'a', 0x1d5a1:'b', -0x1d5a2:'c', 0x1d5a3:'d', 0x1d5a4:'e', 0x1d5a5:'f', -0x1d5a6:'g', 0x1d5a7:'h', 0x1d5a8:'i', 0x1d5a9:'j', -0x1d5aa:'k', 0x1d5ab:'l', 0x1d5ac:'m', 0x1d5ad:'n', -0x1d5ae:'o', 0x1d5af:'p', 0x1d5b0:'q', 0x1d5b1:'r', -0x1d5b2:'s', 0x1d5b3:'t', 0x1d5b4:'u', 0x1d5b5:'v', -0x1d5b6:'w', 0x1d5b7:'x', 0x1d5b8:'y', 0x1d5b9:'z', -0x1d5d4:'a', 0x1d5d5:'b', 0x1d5d6:'c', 0x1d5d7:'d', -0x1d5d8:'e', 0x1d5d9:'f', 0x1d5da:'g', 0x1d5db:'h', -0x1d5dc:'i', 0x1d5dd:'j', 0x1d5de:'k', 0x1d5df:'l', -0x1d5e0:'m', 0x1d5e1:'n', 0x1d5e2:'o', 0x1d5e3:'p', -0x1d5e4:'q', 0x1d5e5:'r', 0x1d5e6:'s', 0x1d5e7:'t', -0x1d5e8:'u', 0x1d5e9:'v', 0x1d5ea:'w', 0x1d5eb:'x', -0x1d5ec:'y', 0x1d5ed:'z', 0x1d608:'a', 0x1d609:'b', -0x1d60a:'c', 0x1d60b:'d', 0x1d60c:'e', 0x1d60d:'f', -0x1d60e:'g', 0x1d60f:'h', 0x1d610:'i', 0x1d611:'j', -0x1d612:'k', 0x1d613:'l', 0x1d614:'m', 0x1d615:'n', -0x1d616:'o', 0x1d617:'p', 0x1d618:'q', 0x1d619:'r', -0x1d61a:'s', 0x1d61b:'t', 0x1d61c:'u', 0x1d61d:'v', -0x1d61e:'w', 0x1d61f:'x', 0x1d620:'y', 0x1d621:'z', -0x1d63c:'a', 0x1d63d:'b', 0x1d63e:'c', 0x1d63f:'d', -0x1d640:'e', 0x1d641:'f', 0x1d642:'g', 0x1d643:'h', -0x1d644:'i', 0x1d645:'j', 0x1d646:'k', 0x1d647:'l', -0x1d648:'m', 0x1d649:'n', 0x1d64a:'o', 0x1d64b:'p', -0x1d64c:'q', 0x1d64d:'r', 0x1d64e:'s', 0x1d64f:'t', -0x1d650:'u', 0x1d651:'v', 0x1d652:'w', 0x1d653:'x', -0x1d654:'y', 0x1d655:'z', 0x1d670:'a', 0x1d671:'b', -0x1d672:'c', 0x1d673:'d', 0x1d674:'e', 0x1d675:'f', -0x1d676:'g', 0x1d677:'h', 0x1d678:'i', 0x1d679:'j', -0x1d67a:'k', 0x1d67b:'l', 0x1d67c:'m', 0x1d67d:'n', -0x1d67e:'o', 0x1d67f:'p', 0x1d680:'q', 0x1d681:'r', -0x1d682:'s', 0x1d683:'t', 0x1d684:'u', 0x1d685:'v', -0x1d686:'w', 0x1d687:'x', 0x1d688:'y', 0x1d689:'z', -0x1d6a8:'\u03b1', 0x1d6a9:'\u03b2', 0x1d6aa:'\u03b3', 0x1d6ab:'\u03b4', -0x1d6ac:'\u03b5', 0x1d6ad:'\u03b6', 0x1d6ae:'\u03b7', 0x1d6af:'\u03b8', -0x1d6b0:'\u03b9', 0x1d6b1:'\u03ba', 0x1d6b2:'\u03bb', 0x1d6b3:'\u03bc', -0x1d6b4:'\u03bd', 0x1d6b5:'\u03be', 0x1d6b6:'\u03bf', 0x1d6b7:'\u03c0', -0x1d6b8:'\u03c1', 0x1d6b9:'\u03b8', 0x1d6ba:'\u03c3', 0x1d6bb:'\u03c4', -0x1d6bc:'\u03c5', 0x1d6bd:'\u03c6', 0x1d6be:'\u03c7', 0x1d6bf:'\u03c8', -0x1d6c0:'\u03c9', 0x1d6d3:'\u03c3', 0x1d6e2:'\u03b1', 0x1d6e3:'\u03b2', -0x1d6e4:'\u03b3', 0x1d6e5:'\u03b4', 0x1d6e6:'\u03b5', 0x1d6e7:'\u03b6', -0x1d6e8:'\u03b7', 0x1d6e9:'\u03b8', 0x1d6ea:'\u03b9', 0x1d6eb:'\u03ba', -0x1d6ec:'\u03bb', 0x1d6ed:'\u03bc', 0x1d6ee:'\u03bd', 0x1d6ef:'\u03be', -0x1d6f0:'\u03bf', 0x1d6f1:'\u03c0', 0x1d6f2:'\u03c1', 0x1d6f3:'\u03b8', -0x1d6f4:'\u03c3', 0x1d6f5:'\u03c4', 0x1d6f6:'\u03c5', 0x1d6f7:'\u03c6', -0x1d6f8:'\u03c7', 0x1d6f9:'\u03c8', 0x1d6fa:'\u03c9', 0x1d70d:'\u03c3', -0x1d71c:'\u03b1', 0x1d71d:'\u03b2', 0x1d71e:'\u03b3', 0x1d71f:'\u03b4', -0x1d720:'\u03b5', 0x1d721:'\u03b6', 0x1d722:'\u03b7', 0x1d723:'\u03b8', -0x1d724:'\u03b9', 0x1d725:'\u03ba', 0x1d726:'\u03bb', 0x1d727:'\u03bc', -0x1d728:'\u03bd', 0x1d729:'\u03be', 0x1d72a:'\u03bf', 0x1d72b:'\u03c0', -0x1d72c:'\u03c1', 0x1d72d:'\u03b8', 0x1d72e:'\u03c3', 0x1d72f:'\u03c4', -0x1d730:'\u03c5', 0x1d731:'\u03c6', 0x1d732:'\u03c7', 0x1d733:'\u03c8', -0x1d734:'\u03c9', 0x1d747:'\u03c3', 0x1d756:'\u03b1', 0x1d757:'\u03b2', -0x1d758:'\u03b3', 0x1d759:'\u03b4', 0x1d75a:'\u03b5', 0x1d75b:'\u03b6', -0x1d75c:'\u03b7', 0x1d75d:'\u03b8', 0x1d75e:'\u03b9', 0x1d75f:'\u03ba', -0x1d760:'\u03bb', 0x1d761:'\u03bc', 0x1d762:'\u03bd', 0x1d763:'\u03be', -0x1d764:'\u03bf', 0x1d765:'\u03c0', 0x1d766:'\u03c1', 0x1d767:'\u03b8', -0x1d768:'\u03c3', 0x1d769:'\u03c4', 0x1d76a:'\u03c5', 0x1d76b:'\u03c6', -0x1d76c:'\u03c7', 0x1d76d:'\u03c8', 0x1d76e:'\u03c9', 0x1d781:'\u03c3', -0x1d790:'\u03b1', 0x1d791:'\u03b2', 0x1d792:'\u03b3', 0x1d793:'\u03b4', -0x1d794:'\u03b5', 0x1d795:'\u03b6', 0x1d796:'\u03b7', 0x1d797:'\u03b8', -0x1d798:'\u03b9', 0x1d799:'\u03ba', 0x1d79a:'\u03bb', 0x1d79b:'\u03bc', -0x1d79c:'\u03bd', 0x1d79d:'\u03be', 0x1d79e:'\u03bf', 0x1d79f:'\u03c0', -0x1d7a0:'\u03c1', 0x1d7a1:'\u03b8', 0x1d7a2:'\u03c3', 0x1d7a3:'\u03c4', -0x1d7a4:'\u03c5', 0x1d7a5:'\u03c6', 0x1d7a6:'\u03c7', 0x1d7a7:'\u03c8', -0x1d7a8:'\u03c9', 0x1d7bb:'\u03c3', } +0xfb16:'\u057e\u0576', 0xfb17:'\u0574\u056d', 0x10426:'\U00010426', 0x10427:'\U00010427', +0x104b0:'\U000104b0', 0x104b1:'\U000104b1', 0x104b2:'\U000104b2', 0x104b3:'\U000104b3', +0x104b4:'\U000104b4', 0x104b5:'\U000104b5', 0x104b6:'\U000104b6', 0x104b7:'\U000104b7', +0x104b8:'\U000104b8', 0x104b9:'\U000104b9', 0x104ba:'\U000104ba', 0x104bb:'\U000104bb', +0x104bc:'\U000104bc', 0x104bd:'\U000104bd', 0x104be:'\U000104be', 0x104bf:'\U000104bf', +0x104c0:'\U000104c0', 0x104c1:'\U000104c1', 0x104c2:'\U000104c2', 0x104c3:'\U000104c3', +0x104c4:'\U000104c4', 0x104c5:'\U000104c5', 0x104c6:'\U000104c6', 0x104c7:'\U000104c7', +0x104c8:'\U000104c8', 0x104c9:'\U000104c9', 0x104ca:'\U000104ca', 0x104cb:'\U000104cb', +0x104cc:'\U000104cc', 0x104cd:'\U000104cd', 0x104ce:'\U000104ce', 0x104cf:'\U000104cf', +0x104d0:'\U000104d0', 0x104d1:'\U000104d1', 0x104d2:'\U000104d2', 0x104d3:'\U000104d3', +0x10c80:'\U00010c80', 0x10c81:'\U00010c81', 0x10c82:'\U00010c82', 0x10c83:'\U00010c83', +0x10c84:'\U00010c84', 0x10c85:'\U00010c85', 0x10c86:'\U00010c86', 0x10c87:'\U00010c87', +0x10c88:'\U00010c88', 0x10c89:'\U00010c89', 0x10c8a:'\U00010c8a', 0x10c8b:'\U00010c8b', +0x10c8c:'\U00010c8c', 0x10c8d:'\U00010c8d', 0x10c8e:'\U00010c8e', 0x10c8f:'\U00010c8f', +0x10c90:'\U00010c90', 0x10c91:'\U00010c91', 0x10c92:'\U00010c92', 0x10c93:'\U00010c93', +0x10c94:'\U00010c94', 0x10c95:'\U00010c95', 0x10c96:'\U00010c96', 0x10c97:'\U00010c97', +0x10c98:'\U00010c98', 0x10c99:'\U00010c99', 0x10c9a:'\U00010c9a', 0x10c9b:'\U00010c9b', +0x10c9c:'\U00010c9c', 0x10c9d:'\U00010c9d', 0x10c9e:'\U00010c9e', 0x10c9f:'\U00010c9f', +0x10ca0:'\U00010ca0', 0x10ca1:'\U00010ca1', 0x10ca2:'\U00010ca2', 0x10ca3:'\U00010ca3', +0x10ca4:'\U00010ca4', 0x10ca5:'\U00010ca5', 0x10ca6:'\U00010ca6', 0x10ca7:'\U00010ca7', +0x10ca8:'\U00010ca8', 0x10ca9:'\U00010ca9', 0x10caa:'\U00010caa', 0x10cab:'\U00010cab', +0x10cac:'\U00010cac', 0x10cad:'\U00010cad', 0x10cae:'\U00010cae', 0x10caf:'\U00010caf', +0x10cb0:'\U00010cb0', 0x10cb1:'\U00010cb1', 0x10cb2:'\U00010cb2', 0x118a0:'\U000118a0', +0x118a1:'\U000118a1', 0x118a2:'\U000118a2', 0x118a3:'\U000118a3', 0x118a4:'\U000118a4', +0x118a5:'\U000118a5', 0x118a6:'\U000118a6', 0x118a7:'\U000118a7', 0x118a8:'\U000118a8', +0x118a9:'\U000118a9', 0x118aa:'\U000118aa', 0x118ab:'\U000118ab', 0x118ac:'\U000118ac', +0x118ad:'\U000118ad', 0x118ae:'\U000118ae', 0x118af:'\U000118af', 0x118b0:'\U000118b0', +0x118b1:'\U000118b1', 0x118b2:'\U000118b2', 0x118b3:'\U000118b3', 0x118b4:'\U000118b4', +0x118b5:'\U000118b5', 0x118b6:'\U000118b6', 0x118b7:'\U000118b7', 0x118b8:'\U000118b8', +0x118b9:'\U000118b9', 0x118ba:'\U000118ba', 0x118bb:'\U000118bb', 0x118bc:'\U000118bc', +0x118bd:'\U000118bd', 0x118be:'\U000118be', 0x118bf:'\U000118bf', 0x16e40:'\U00016e40', +0x16e41:'\U00016e41', 0x16e42:'\U00016e42', 0x16e43:'\U00016e43', 0x16e44:'\U00016e44', +0x16e45:'\U00016e45', 0x16e46:'\U00016e46', 0x16e47:'\U00016e47', 0x16e48:'\U00016e48', +0x16e49:'\U00016e49', 0x16e4a:'\U00016e4a', 0x16e4b:'\U00016e4b', 0x16e4c:'\U00016e4c', +0x16e4d:'\U00016e4d', 0x16e4e:'\U00016e4e', 0x16e4f:'\U00016e4f', 0x16e50:'\U00016e50', +0x16e51:'\U00016e51', 0x16e52:'\U00016e52', 0x16e53:'\U00016e53', 0x16e54:'\U00016e54', +0x16e55:'\U00016e55', 0x16e56:'\U00016e56', 0x16e57:'\U00016e57', 0x16e58:'\U00016e58', +0x16e59:'\U00016e59', 0x16e5a:'\U00016e5a', 0x16e5b:'\U00016e5b', 0x16e5c:'\U00016e5c', +0x16e5d:'\U00016e5d', 0x16e5e:'\U00016e5e', 0x16e5f:'\U00016e5f', 0x1d400:'a', +0x1d401:'b', 0x1d402:'c', 0x1d403:'d', 0x1d404:'e', +0x1d405:'f', 0x1d406:'g', 0x1d407:'h', 0x1d408:'i', +0x1d409:'j', 0x1d40a:'k', 0x1d40b:'l', 0x1d40c:'m', +0x1d40d:'n', 0x1d40e:'o', 0x1d40f:'p', 0x1d410:'q', +0x1d411:'r', 0x1d412:'s', 0x1d413:'t', 0x1d414:'u', +0x1d415:'v', 0x1d416:'w', 0x1d417:'x', 0x1d418:'y', +0x1d419:'z', 0x1d434:'a', 0x1d435:'b', 0x1d436:'c', +0x1d437:'d', 0x1d438:'e', 0x1d439:'f', 0x1d43a:'g', +0x1d43b:'h', 0x1d43c:'i', 0x1d43d:'j', 0x1d43e:'k', +0x1d43f:'l', 0x1d440:'m', 0x1d441:'n', 0x1d442:'o', +0x1d443:'p', 0x1d444:'q', 0x1d445:'r', 0x1d446:'s', +0x1d447:'t', 0x1d448:'u', 0x1d449:'v', 0x1d44a:'w', +0x1d44b:'x', 0x1d44c:'y', 0x1d44d:'z', 0x1d468:'a', +0x1d469:'b', 0x1d46a:'c', 0x1d46b:'d', 0x1d46c:'e', +0x1d46d:'f', 0x1d46e:'g', 0x1d46f:'h', 0x1d470:'i', +0x1d471:'j', 0x1d472:'k', 0x1d473:'l', 0x1d474:'m', +0x1d475:'n', 0x1d476:'o', 0x1d477:'p', 0x1d478:'q', +0x1d479:'r', 0x1d47a:'s', 0x1d47b:'t', 0x1d47c:'u', +0x1d47d:'v', 0x1d47e:'w', 0x1d47f:'x', 0x1d480:'y', +0x1d481:'z', 0x1d49c:'a', 0x1d49e:'c', 0x1d49f:'d', +0x1d4a2:'g', 0x1d4a5:'j', 0x1d4a6:'k', 0x1d4a9:'n', +0x1d4aa:'o', 0x1d4ab:'p', 0x1d4ac:'q', 0x1d4ae:'s', +0x1d4af:'t', 0x1d4b0:'u', 0x1d4b1:'v', 0x1d4b2:'w', +0x1d4b3:'x', 0x1d4b4:'y', 0x1d4b5:'z', 0x1d4d0:'a', +0x1d4d1:'b', 0x1d4d2:'c', 0x1d4d3:'d', 0x1d4d4:'e', +0x1d4d5:'f', 0x1d4d6:'g', 0x1d4d7:'h', 0x1d4d8:'i', +0x1d4d9:'j', 0x1d4da:'k', 0x1d4db:'l', 0x1d4dc:'m', +0x1d4dd:'n', 0x1d4de:'o', 0x1d4df:'p', 0x1d4e0:'q', +0x1d4e1:'r', 0x1d4e2:'s', 0x1d4e3:'t', 0x1d4e4:'u', +0x1d4e5:'v', 0x1d4e6:'w', 0x1d4e7:'x', 0x1d4e8:'y', +0x1d4e9:'z', 0x1d504:'a', 0x1d505:'b', 0x1d507:'d', +0x1d508:'e', 0x1d509:'f', 0x1d50a:'g', 0x1d50d:'j', +0x1d50e:'k', 0x1d50f:'l', 0x1d510:'m', 0x1d511:'n', +0x1d512:'o', 0x1d513:'p', 0x1d514:'q', 0x1d516:'s', +0x1d517:'t', 0x1d518:'u', 0x1d519:'v', 0x1d51a:'w', +0x1d51b:'x', 0x1d51c:'y', 0x1d538:'a', 0x1d539:'b', +0x1d53b:'d', 0x1d53c:'e', 0x1d53d:'f', 0x1d53e:'g', +0x1d540:'i', 0x1d541:'j', 0x1d542:'k', 0x1d543:'l', +0x1d544:'m', 0x1d546:'o', 0x1d54a:'s', 0x1d54b:'t', +0x1d54c:'u', 0x1d54d:'v', 0x1d54e:'w', 0x1d54f:'x', +0x1d550:'y', 0x1d56c:'a', 0x1d56d:'b', 0x1d56e:'c', +0x1d56f:'d', 0x1d570:'e', 0x1d571:'f', 0x1d572:'g', +0x1d573:'h', 0x1d574:'i', 0x1d575:'j', 0x1d576:'k', +0x1d577:'l', 0x1d578:'m', 0x1d579:'n', 0x1d57a:'o', +0x1d57b:'p', 0x1d57c:'q', 0x1d57d:'r', 0x1d57e:'s', +0x1d57f:'t', 0x1d580:'u', 0x1d581:'v', 0x1d582:'w', +0x1d583:'x', 0x1d584:'y', 0x1d585:'z', 0x1d5a0:'a', +0x1d5a1:'b', 0x1d5a2:'c', 0x1d5a3:'d', 0x1d5a4:'e', +0x1d5a5:'f', 0x1d5a6:'g', 0x1d5a7:'h', 0x1d5a8:'i', +0x1d5a9:'j', 0x1d5aa:'k', 0x1d5ab:'l', 0x1d5ac:'m', +0x1d5ad:'n', 0x1d5ae:'o', 0x1d5af:'p', 0x1d5b0:'q', +0x1d5b1:'r', 0x1d5b2:'s', 0x1d5b3:'t', 0x1d5b4:'u', +0x1d5b5:'v', 0x1d5b6:'w', 0x1d5b7:'x', 0x1d5b8:'y', +0x1d5b9:'z', 0x1d5d4:'a', 0x1d5d5:'b', 0x1d5d6:'c', +0x1d5d7:'d', 0x1d5d8:'e', 0x1d5d9:'f', 0x1d5da:'g', +0x1d5db:'h', 0x1d5dc:'i', 0x1d5dd:'j', 0x1d5de:'k', +0x1d5df:'l', 0x1d5e0:'m', 0x1d5e1:'n', 0x1d5e2:'o', +0x1d5e3:'p', 0x1d5e4:'q', 0x1d5e5:'r', 0x1d5e6:'s', +0x1d5e7:'t', 0x1d5e8:'u', 0x1d5e9:'v', 0x1d5ea:'w', +0x1d5eb:'x', 0x1d5ec:'y', 0x1d5ed:'z', 0x1d608:'a', +0x1d609:'b', 0x1d60a:'c', 0x1d60b:'d', 0x1d60c:'e', +0x1d60d:'f', 0x1d60e:'g', 0x1d60f:'h', 0x1d610:'i', +0x1d611:'j', 0x1d612:'k', 0x1d613:'l', 0x1d614:'m', +0x1d615:'n', 0x1d616:'o', 0x1d617:'p', 0x1d618:'q', +0x1d619:'r', 0x1d61a:'s', 0x1d61b:'t', 0x1d61c:'u', +0x1d61d:'v', 0x1d61e:'w', 0x1d61f:'x', 0x1d620:'y', +0x1d621:'z', 0x1d63c:'a', 0x1d63d:'b', 0x1d63e:'c', +0x1d63f:'d', 0x1d640:'e', 0x1d641:'f', 0x1d642:'g', +0x1d643:'h', 0x1d644:'i', 0x1d645:'j', 0x1d646:'k', +0x1d647:'l', 0x1d648:'m', 0x1d649:'n', 0x1d64a:'o', +0x1d64b:'p', 0x1d64c:'q', 0x1d64d:'r', 0x1d64e:'s', +0x1d64f:'t', 0x1d650:'u', 0x1d651:'v', 0x1d652:'w', +0x1d653:'x', 0x1d654:'y', 0x1d655:'z', 0x1d670:'a', +0x1d671:'b', 0x1d672:'c', 0x1d673:'d', 0x1d674:'e', +0x1d675:'f', 0x1d676:'g', 0x1d677:'h', 0x1d678:'i', +0x1d679:'j', 0x1d67a:'k', 0x1d67b:'l', 0x1d67c:'m', +0x1d67d:'n', 0x1d67e:'o', 0x1d67f:'p', 0x1d680:'q', +0x1d681:'r', 0x1d682:'s', 0x1d683:'t', 0x1d684:'u', +0x1d685:'v', 0x1d686:'w', 0x1d687:'x', 0x1d688:'y', +0x1d689:'z', 0x1d6a8:'\u03b1', 0x1d6a9:'\u03b2', 0x1d6aa:'\u03b3', +0x1d6ab:'\u03b4', 0x1d6ac:'\u03b5', 0x1d6ad:'\u03b6', 0x1d6ae:'\u03b7', +0x1d6af:'\u03b8', 0x1d6b0:'\u03b9', 0x1d6b1:'\u03ba', 0x1d6b2:'\u03bb', +0x1d6b3:'\u03bc', 0x1d6b4:'\u03bd', 0x1d6b5:'\u03be', 0x1d6b6:'\u03bf', +0x1d6b7:'\u03c0', 0x1d6b8:'\u03c1', 0x1d6b9:'\u03b8', 0x1d6ba:'\u03c3', +0x1d6bb:'\u03c4', 0x1d6bc:'\u03c5', 0x1d6bd:'\u03c6', 0x1d6be:'\u03c7', +0x1d6bf:'\u03c8', 0x1d6c0:'\u03c9', 0x1d6d3:'\u03c3', 0x1d6e2:'\u03b1', +0x1d6e3:'\u03b2', 0x1d6e4:'\u03b3', 0x1d6e5:'\u03b4', 0x1d6e6:'\u03b5', +0x1d6e7:'\u03b6', 0x1d6e8:'\u03b7', 0x1d6e9:'\u03b8', 0x1d6ea:'\u03b9', +0x1d6eb:'\u03ba', 0x1d6ec:'\u03bb', 0x1d6ed:'\u03bc', 0x1d6ee:'\u03bd', +0x1d6ef:'\u03be', 0x1d6f0:'\u03bf', 0x1d6f1:'\u03c0', 0x1d6f2:'\u03c1', +0x1d6f3:'\u03b8', 0x1d6f4:'\u03c3', 0x1d6f5:'\u03c4', 0x1d6f6:'\u03c5', +0x1d6f7:'\u03c6', 0x1d6f8:'\u03c7', 0x1d6f9:'\u03c8', 0x1d6fa:'\u03c9', +0x1d70d:'\u03c3', 0x1d71c:'\u03b1', 0x1d71d:'\u03b2', 0x1d71e:'\u03b3', +0x1d71f:'\u03b4', 0x1d720:'\u03b5', 0x1d721:'\u03b6', 0x1d722:'\u03b7', +0x1d723:'\u03b8', 0x1d724:'\u03b9', 0x1d725:'\u03ba', 0x1d726:'\u03bb', +0x1d727:'\u03bc', 0x1d728:'\u03bd', 0x1d729:'\u03be', 0x1d72a:'\u03bf', +0x1d72b:'\u03c0', 0x1d72c:'\u03c1', 0x1d72d:'\u03b8', 0x1d72e:'\u03c3', +0x1d72f:'\u03c4', 0x1d730:'\u03c5', 0x1d731:'\u03c6', 0x1d732:'\u03c7', +0x1d733:'\u03c8', 0x1d734:'\u03c9', 0x1d747:'\u03c3', 0x1d756:'\u03b1', +0x1d757:'\u03b2', 0x1d758:'\u03b3', 0x1d759:'\u03b4', 0x1d75a:'\u03b5', +0x1d75b:'\u03b6', 0x1d75c:'\u03b7', 0x1d75d:'\u03b8', 0x1d75e:'\u03b9', +0x1d75f:'\u03ba', 0x1d760:'\u03bb', 0x1d761:'\u03bc', 0x1d762:'\u03bd', +0x1d763:'\u03be', 0x1d764:'\u03bf', 0x1d765:'\u03c0', 0x1d766:'\u03c1', +0x1d767:'\u03b8', 0x1d768:'\u03c3', 0x1d769:'\u03c4', 0x1d76a:'\u03c5', +0x1d76b:'\u03c6', 0x1d76c:'\u03c7', 0x1d76d:'\u03c8', 0x1d76e:'\u03c9', +0x1d781:'\u03c3', 0x1d790:'\u03b1', 0x1d791:'\u03b2', 0x1d792:'\u03b3', +0x1d793:'\u03b4', 0x1d794:'\u03b5', 0x1d795:'\u03b6', 0x1d796:'\u03b7', +0x1d797:'\u03b8', 0x1d798:'\u03b9', 0x1d799:'\u03ba', 0x1d79a:'\u03bb', +0x1d79b:'\u03bc', 0x1d79c:'\u03bd', 0x1d79d:'\u03be', 0x1d79e:'\u03bf', +0x1d79f:'\u03c0', 0x1d7a0:'\u03c1', 0x1d7a1:'\u03b8', 0x1d7a2:'\u03c3', +0x1d7a3:'\u03c4', 0x1d7a4:'\u03c5', 0x1d7a5:'\u03c6', 0x1d7a6:'\u03c7', +0x1d7a7:'\u03c8', 0x1d7a8:'\u03c9', 0x1d7bb:'\u03c3', 0x1e900:'\U0001e900', +0x1e901:'\U0001e901', 0x1e902:'\U0001e902', 0x1e903:'\U0001e903', 0x1e904:'\U0001e904', +0x1e905:'\U0001e905', 0x1e906:'\U0001e906', 0x1e907:'\U0001e907', 0x1e908:'\U0001e908', +0x1e909:'\U0001e909', 0x1e90a:'\U0001e90a', 0x1e90b:'\U0001e90b', 0x1e90c:'\U0001e90c', +0x1e90d:'\U0001e90d', 0x1e90e:'\U0001e90e', 0x1e90f:'\U0001e90f', 0x1e910:'\U0001e910', +0x1e911:'\U0001e911', 0x1e912:'\U0001e912', 0x1e913:'\U0001e913', 0x1e914:'\U0001e914', +0x1e915:'\U0001e915', 0x1e916:'\U0001e916', 0x1e917:'\U0001e917', 0x1e918:'\U0001e918', +0x1e919:'\U0001e919', 0x1e91a:'\U0001e91a', 0x1e91b:'\U0001e91b', 0x1e91c:'\U0001e91c', +0x1e91d:'\U0001e91d', 0x1e91e:'\U0001e91e', 0x1e91f:'\U0001e91f', 0x1e920:'\U0001e920', +0x1e921:'\U0001e921', } def map_table_b3(code): r = b3_exceptions.get(ord(code)) @@ -194,9 +361,9 @@ def map_table_b3(code): def map_table_b2(a): al = map_table_b3(a) - b = unicodedata.normalize("NFKC", al) + b = unicodedata_320.normalize("NFKC", al) bl = "".join([map_table_b3(ch) for ch in b]) - c = unicodedata.normalize("NFKC", bl) + c = unicodedata_320.normalize("NFKC", bl) if b != c: return c else: @@ -208,29 +375,29 @@ def in_table_c11(code): def in_table_c12(code): - return unicodedata.category(code) == "Zs" and code != " " + return unicodedata_320.category(code) == "Zs" and code != " " def in_table_c11_c12(code): - return unicodedata.category(code) == "Zs" + return unicodedata_320.category(code) == "Zs" def in_table_c21(code): - return ord(code) < 128 and unicodedata.category(code) == "Cc" + return ord(code) < 128 and unicodedata_320.category(code) == "Cc" c22_specials = set([1757, 1807, 6158, 8204, 8205, 8232, 8233, 65279] + list(range(8288,8292)) + list(range(8298,8304)) + list(range(65529,65533)) + list(range(119155,119163))) def in_table_c22(code): c = ord(code) if c < 128: return False - if unicodedata.category(code) == "Cc": return True + if unicodedata_320.category(code) == "Cc": return True return c in c22_specials def in_table_c21_c22(code): - return unicodedata.category(code) == "Cc" or \ + return unicodedata_320.category(code) == "Cc" or \ ord(code) in c22_specials def in_table_c3(code): - return unicodedata.category(code) == "Co" + return unicodedata_320.category(code) == "Co" def in_table_c4(code): @@ -241,7 +408,7 @@ def in_table_c4(code): def in_table_c5(code): - return unicodedata.category(code) == "Cs" + return unicodedata_320.category(code) == "Cs" c6_set = set(range(65529,65534)) @@ -265,8 +432,8 @@ def in_table_c9(code): def in_table_d1(code): - return unicodedata.bidirectional(code) in ("R","AL") + return unicodedata_320.bidirectional(code) in ("R","AL") def in_table_d2(code): - return unicodedata.bidirectional(code) == "L" + return unicodedata_320.bidirectional(code) == "L" diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py index efe5858547a05a5..25f9aa3b23f4ddd 100644 --- a/Lib/test/test_codecs.py +++ b/Lib/test/test_codecs.py @@ -1547,6 +1547,15 @@ def test_builtin_encode(self): self.assertEqual("pyth\xf6n.org".encode("idna"), b"xn--pythn-mua.org") self.assertEqual("pyth\xf6n.org.".encode("idna"), b"xn--pythn-mua.org.") + @support.subTests(['unicode', 'encoded'], [ + ('\N{CHEROKEE LETTER A}\N{CHEROKEE LETTER A}', b"xn--58da"), + ('\N{GEORGIAN CAPITAL LETTER AN}.', b"xn--7md."), + ('\N{CYRILLIC LETTER PALOCHKA}.example', b"xn--d5a.example"), + ('\N{ROMAN NUMERAL REVERSED ONE HUNDRED}.example.', b"xn--q5g.example."), + ]) + def test_new_unicode_case_folding(self, unicode, encoded): + self.assertEqual(unicode.encode("idna"), encoded) + def test_builtin_decode_length_limit(self): with self.assertRaisesRegex(UnicodeError, "too long"): (b"xn--016c"+b"a"*1100).decode("idna") diff --git a/Lib/test/test_unicodedata.py b/Lib/test/test_unicodedata.py index 8f901a079192243..f46cd75ce6e289c 100644 --- a/Lib/test/test_unicodedata.py +++ b/Lib/test/test_unicodedata.py @@ -69,6 +69,7 @@ class UnicodeDatabaseTest(unittest.TestCase): db = unicodedata class UnicodeFunctionsTest(UnicodeDatabaseTest): + old = False # Update this if the database changes. Make sure to do a full rebuild # (e.g. 'make distclean && make') to get the correct checksum. @@ -94,7 +95,8 @@ def test_function_checksum(self): ] h.update(''.join(data).encode("ascii")) result = h.hexdigest() - self.assertEqual(result, self.expectedchecksum) + if not self.old: + self.assertEqual(result, self.expectedchecksum) @requires_resource('cpu') def test_name_inverse_lookup(self): @@ -120,9 +122,13 @@ def test_numeric(self): self.assertEqual(self.db.numeric('9'), 9) self.assertEqual(self.db.numeric('\u215b'), 0.125) self.assertEqual(self.db.numeric('\u2468'), 9.0) - self.assertEqual(self.db.numeric('\ua627'), 7.0) + # New in 5.1.0 + self.assertEqual(self.db.numeric('\ua627', None), + None if self.old else 7.0) self.assertEqual(self.db.numeric('\U00020000', None), None) - self.assertEqual(self.db.numeric('\U0001012A'), 9000) + # New in 4.1.0 + self.assertEqual(self.db.numeric('\U0001012A', None), + None if self.old else 9000) self.assertRaises(TypeError, self.db.numeric) self.assertRaises(TypeError, self.db.numeric, 'xx') @@ -145,7 +151,8 @@ def test_category(self): self.assertEqual(self.db.category('a'), 'Ll') self.assertEqual(self.db.category('A'), 'Lu') self.assertEqual(self.db.category('\U00020000'), 'Lo') - self.assertEqual(self.db.category('\U0001012A'), 'No') + self.assertEqual(self.db.category('\U0001012A'), + 'Cn' if self.old else 'No') self.assertRaises(TypeError, self.db.category) self.assertRaises(TypeError, self.db.category, 'xx') @@ -159,6 +166,15 @@ def test_bidirectional(self): self.assertRaises(TypeError, self.db.bidirectional) self.assertRaises(TypeError, self.db.bidirectional, 'xx') + def test_bidirectional_unassigned(self): + self.assertEqual(self.db.bidirectional('\u0378'), '') + self.assertEqual(self.db.bidirectional('\u077F'), '' if self.old else 'AL') + self.assertEqual(self.db.bidirectional('\u20CF'), '') + self.assertEqual(self.db.bidirectional('\u0590'), '') + self.assertEqual(self.db.bidirectional('\uFFFF'), '') + self.assertEqual(self.db.bidirectional('\U0001FFFE'), '') + self.assertEqual(self.db.bidirectional('\U00010D01'), '' if self.old else 'AL') + def test_decomposition(self): self.assertEqual(self.db.decomposition('\uFFFE'),'') self.assertEqual(self.db.decomposition('\u00bc'), '<fraction> 0031 2044 0034') @@ -257,8 +273,14 @@ def test_east_asian_width(self): self.assertEqual(eaw('\U00020000'), 'W') def test_east_asian_width_9_0_changes(self): - self.assertEqual(self.db.ucd_3_2_0.east_asian_width('\u231a'), 'N') - self.assertEqual(self.db.east_asian_width('\u231a'), 'W') + self.assertEqual(self.db.east_asian_width('\u231a'), + 'N' if self.old else 'W') + + +class Unicode_3_2_0_FunctionsTest(UnicodeFunctionsTest): + db = unicodedata.ucd_3_2_0 + old = True + class UnicodeMiscTest(UnicodeDatabaseTest): diff --git a/Misc/NEWS.d/next/Security/2026-08-06-11-43-20.gh-issue-155292.j4pHBO.rst b/Misc/NEWS.d/next/Security/2026-08-06-11-43-20.gh-issue-155292.j4pHBO.rst new file mode 100644 index 000000000000000..7a81a8ba1eef1cd --- /dev/null +++ b/Misc/NEWS.d/next/Security/2026-08-06-11-43-20.gh-issue-155292.j4pHBO.rst @@ -0,0 +1,2 @@ +Change the :mod:`stringprep` module and :mod:`encodings.idna` codec to not +consider Unicode codepoint attributes beyond those defined in :rfc:`3454`. diff --git a/Tools/unicode/makeunicodedata.py b/Tools/unicode/makeunicodedata.py index 810b285de2c91e3..797541ac0d08fd4 100644 --- a/Tools/unicode/makeunicodedata.py +++ b/Tools/unicode/makeunicodedata.py @@ -28,6 +28,7 @@ import dataclasses import os +import subprocess import sys import zipfile @@ -35,7 +36,7 @@ from textwrap import dedent from typing import Iterator, List, Optional, Set, Tuple -SCRIPT = sys.argv[0] +SCRIPT = os.path.normpath(sys.argv[0]) VERSION = "3.3" # The Unicode Database @@ -128,6 +129,7 @@ def maketables(trace=0): makeunicodename(unicode, trace) makeunicodedata(unicode, trace) makeunicodetype(unicode, trace) + makestringprep() # -------------------------------------------------------------------- @@ -792,6 +794,19 @@ def word_key(a): fprint('};') + +def makestringprep(): + FILE = "Lib/stringprep.py" + + print("--- Preparing", FILE, "...") + + MKSTRINGPREP = "Tools/unicode/mkstringprep.py" + + with open(FILE, "w") as f: + f.truncate() + subprocess.check_call([sys.executable, MKSTRINGPREP], stdout=f) + + def merge_old_version(version, new, old): # Changes to exclusion file not implemented yet if old.exclusions != new.exclusions: diff --git a/Tools/unicode/mkstringprep.py b/Tools/unicode/mkstringprep.py index 427188389a3b87c..9740338fef9d3d4 100644 --- a/Tools/unicode/mkstringprep.py +++ b/Tools/unicode/mkstringprep.py @@ -1,15 +1,20 @@ import re -from unicodedata import ucd_3_2_0 as unicodedata +import os +import unicodedata as unicodedata_current +from unicodedata import ucd_3_2_0 as unicodedata_320 + +FILENAME = "Tools/unicode/data/rfc3454.txt" +URL = "https://www.rfc-editor.org/rfc/rfc3454.txt"; def gen_category(cats): for i in range(0, 0x110000): - if unicodedata.category(chr(i)) in cats: - yield(i) + if unicodedata_320.category(chr(i)) in cats: + yield i def gen_bidirectional(cats): for i in range(0, 0x110000): - if unicodedata.bidirectional(chr(i)) in cats: - yield(i) + if unicodedata_320.bidirectional(chr(i)) in cats: + yield i def compact_set(l): single = [] @@ -47,8 +52,16 @@ def compact_set(l): ############## Read the tables in the RFC ####################### -with open("rfc3454.txt") as f: - data = f.readlines() +try: + data_file = open(FILENAME, encoding='utf-8') +except FileNotFoundError: + import urllib.request + os.makedirs(os.path.dirname(FILENAME), exist_ok=True) + urllib.request.urlretrieve(URL, filename=FILENAME) + data_file = open(FILENAME, encoding='utf-8') + +with data_file: + data = data_file.readlines() tables = [] curname = None @@ -116,10 +129,18 @@ def compact_set(l): and mappings, for which a mapping function is provided. \"\"\" -from unicodedata import ucd_3_2_0 as unicodedata +# This check asserts that mkstringprep.py has been run +# when unicodedata is modified to ensure conformant behavior. +import unicodedata +""") + +print("assert unicodedata.unidata_version == %r" % (unicodedata_current.unidata_version,)) + +print(""" +from unicodedata import ucd_3_2_0 as unicodedata_320 """) -print("assert unicodedata.unidata_version == %r" % (unicodedata.unidata_version,)) +print("assert unicodedata_320.unidata_version == %r" % (unicodedata_320.unidata_version,)) # A.1 is the table of unassigned characters # XXX Plane 15 PUA is listed as unassigned in Python. @@ -139,7 +160,7 @@ def compact_set(l): print(""" def in_table_a1(code): - if unicodedata.category(code) != 'Cn': return False + if unicodedata_320.category(code) != 'Cn': return False c = ord(code) if 0xFDD0 <= c < 0xFDF0: return False return (c & 0xFFFF) not in (0xFFFE, 0xFFFF) @@ -172,21 +193,33 @@ def in_table_b1(code): # B.3 is mostly Python's .lower, except for a number # of special cases, e.g. considering canonical forms. +# To enforce Unicode 3.2.0 behavior of .lower instead of +# whatever Unicode version is included with Python we +# add unassigned or newly case-folding codepoints to +# the exception map, too. b3_exceptions = {} for k,v in table_b2.items(): if list(map(ord, chr(k).lower())) != v: b3_exceptions[k] = "".join(map(chr,v)) +for cp in range(0x110000): + ch = chr(cp) + # Assigned in current Unicode version + # and supports case folding, but not + # explicitly in B.2 or B.3 tables. + if (unicodedata_current.category(ch) != "Cn" + and ch.lower() != ch + and cp not in table_b2 + and cp not in table_b3): + b3_exceptions[cp] = ch # Identity. b3 = sorted(b3_exceptions.items()) print(""" b3_exceptions = {""") for i, kv in enumerate(b3): - print("0x%x:%a," % kv, end=' ') - if i % 4 == 3: - print() + print("0x%x:%a," % kv, end='\n' if i % 4 == 3 else ' ') print("}") print(""" @@ -207,9 +240,9 @@ def map_table_b3(code): def map_table_b2(a): al = map_table_b3(a) - b = unicodedata.normalize("NFKC", al) + b = unicodedata_320.normalize("NFKC", al) bl = "".join([map_table_b3(ch) for ch in b]) - c = unicodedata.normalize("NFKC", bl) + c = unicodedata_320.normalize("NFKC", bl) if b != c: return c else: @@ -226,9 +259,9 @@ def map_table_b2(a): print(""" def map_table_b2(a): al = map_table_b3(a) - b = unicodedata.normalize("NFKC", al) + b = unicodedata_320.normalize("NFKC", al) bl = "".join([map_table_b3(ch) for ch in b]) - c = unicodedata.normalize("NFKC", bl) + c = unicodedata_320.normalize("NFKC", bl) if b != c: return c else: @@ -251,16 +284,16 @@ def in_table_c11(code): del tables[0] assert name == "C.1.2" -# table = set(table.keys()) -# Zs = set(gen_category(["Zs"])) - {0x20} -# assert Zs == table +table = set(table.keys()) +Zs = set(gen_category(["Zs"])) - {0x20} +assert Zs == table print(""" def in_table_c12(code): - return unicodedata.category(code) == "Zs" and code != " " + return unicodedata_320.category(code) == "Zs" and code != " " def in_table_c11_c12(code): - return unicodedata.category(code) == "Zs" + return unicodedata_320.category(code) == "Zs" """) # C.2.1 ASCII control characters @@ -275,7 +308,7 @@ def in_table_c11_c12(code): print(""" def in_table_c21(code): - return ord(code) < 128 and unicodedata.category(code) == "Cc" + return ord(code) < 128 and unicodedata_320.category(code) == "Cc" """) # C.2.2 Non-ASCII control characters. It also includes @@ -295,11 +328,11 @@ def in_table_c21(code): def in_table_c22(code): c = ord(code) if c < 128: return False - if unicodedata.category(code) == "Cc": return True + if unicodedata_320.category(code) == "Cc": return True return c in c22_specials def in_table_c21_c22(code): - return unicodedata.category(code) == "Cc" or \\ + return unicodedata_320.category(code) == "Cc" or \\ ord(code) in c22_specials """) @@ -313,7 +346,7 @@ def in_table_c21_c22(code): print(""" def in_table_c3(code): - return unicodedata.category(code) == "Co" + return unicodedata_320.category(code) == "Co" """) # C.4 Non-character code points, xFFFE, xFFFF @@ -346,7 +379,7 @@ def in_table_c4(code): print(""" def in_table_c5(code): - return unicodedata.category(code) == "Cs" + return unicodedata_320.category(code) == "Cs" """) # C.6 Inappropriate for plain text @@ -411,7 +444,7 @@ def in_table_c9(code): print(""" def in_table_d1(code): - return unicodedata.bidirectional(code) in ("R","AL") + return unicodedata_320.bidirectional(code) in ("R","AL") """) # D.2 Characters with bidirectional property "L" @@ -424,5 +457,5 @@ def in_table_d1(code): print(""" def in_table_d2(code): - return unicodedata.bidirectional(code) == "L" -""") + return unicodedata_320.bidirectional(code) == "L" +""", end="") _______________________________________________ Python-checkins mailing list -- [email protected] To unsubscribe send an email to [email protected] https://mail.python.org/mailman3//lists/python-checkins.python.org Member address: [email protected]
