diff --git a/CindyScriptPygments.py b/CindyScriptPygments.py
index 82219c6..aae3943 100644
--- a/CindyScriptPygments.py
+++ b/CindyScriptPygments.py
@@ -13,20 +13,20 @@
u = str
uchr = chr
else:
- u = unicode
- uchr = unichr
+ u = str
+ uchr = chr
def decompressUnicodeRanges(d, s, h):
- utf16 = len(u"\U00012345") > 1
+ utf16 = len("\U00012345") > 1
j = 0
- res = u"(?:[" if utf16 else u"["
+ res = "(?:[" if utf16 else "["
n = len(s)
i = 0
while i < n:
c = ord(s[i])
if (c >= 0xe800):
if utf16:
- res += u"]|" + uchr(c - 0x1000) + u"["
+ res += "]|" + uchr(c - 0x1000) + "["
j = 0xdc00
else:
j = ((c - 0xe800) << 10) + 0x10000
@@ -37,12 +37,12 @@ def decompressUnicodeRanges(d, s, h):
j += d[ord(s[i]) - 32]
if j != fst:
if j != fst + 1:
- res += u"-"
+ res += "-"
res += uchr(j)
i += 1
if utf16:
- h = u''.join(c if c == '-' else uchr(ord(c) - 0x1000) for c in h)
- res += u"]|[" + h + eval(r'u"][\udc00-\udfff])"')
+ h = ''.join(c if c == '-' else uchr(ord(c) - 0x1000) for c in h)
+ res += "]|[" + h + eval(r'u"][\udc00-\udfff])"')
else:
n = len(h)
i = 0
@@ -50,13 +50,13 @@ def decompressUnicodeRanges(d, s, h):
c = ord(h[i])
j = (c - 0xe800) << 10
res += uchr(j + 0x10000)
- if i + 1 < n and h[i + 1] == u"-":
+ if i + 1 < n and h[i + 1] == "-":
i += 2
c = ord(h[i])
j = (c - 0xe800) << 10
- res += u"-" + uchr(j + 0x103ff)
+ res += "-" + uchr(j + 0x103ff)
i += 1
- res += u"]"
+ res += "]"
return res
# Regular expression matching letters (Unicode 8.0.0 category L)
@@ -71,27 +71,27 @@ def decompressUnicodeRanges(d, s, h):
107, 108, 116, 122, 130, 132, 134, 138, 160, 165, 185, 195, 196, 255, 268,
277, 310, 332, 339, 362, 365, 390, 449, 457, 470, 512, 513, 541, 568, 582,
619, 673, 726, 768, 820, 921, 991, 1164, 2684, 6581, 8453, 11171, 20949
-], (u"T4(4I!)!'!&/ 0 \x96')2$+! !\x83$ %## !(! ! ; u \x86.\x88 =#!+YoA& 87C"
- u"% } !5%+%) #!*! <0a,!4B1%'!&-'!1!$!33`HsG$!;!+.52'(#%#- & !$#$!*!9% 2%"
- u"H''%#- & % % %B# !H *+ - & % $$!;!5%3!,(#%#- & % $$!X% 5!:! '$ #$% "
- u"! %$%$ $)W!G( / 2$!> &%C( / . $$!L! %5%;( D#!*!* 4'&*$W + !#&]F %"
- u"6&]% !#% !#!(# & ! !#% # %1!#$ !/#L!S( @?$\x817-!*''#$!$%+ ',6!:= !&!"
- u"#7 \x90 ##& ! ##D ##B ##& ! ##9 K ##^Y2*V#'$\x9d#5 4&p((+, #2*2*2, 5OC"
- u"!'!Uy.D !&_)0J<#$,E'4Q/1Pv!|8:&K<9%)E>@7 )@\x80# #$%1gT\x8e#'#=#'#( ! !"
- u" ! 0#P & !$ &$##'',& &d!9!*,b!'!#. !$$(! ! ! # 1##&$'!G%\xa58 8 \x84("
- u"#$%6= !&!#Q+!*/1& & & & & & & &t!\x97%E$&%'V( z #&D${:Aj2\x99\xa6q\xa9"
- u"E\xa4UZ#\x8d$2)%-8*0#_J+#b#M#(S1 # /0O2[R'$! !6>)/A?+8?G)-):9*\ue803!`KJ9J\ue804#PriL3>@7M$!6F2#/! !C* 3V& ! # "
- u"9 .+8N(#%#- & % $$!;!6$\ue805eF-% !\x8987#=F-!k7x4\ue806\x87RB!\x95K"
- u"\ue808!\xa2\ue809e\x8a\ue80d!8\ue811!\x9c\ue81a!\x9b+0c<;F*#BH&:\ue81b"
- u"\xa0U,!l,\ue82c!%\ue82f!\"&,$++.\ue835!w m %#!#%## ) ! & S ##( & > # $ "
- u"!$& \x91#3 3 0 3 0 3 0 3 0 3 (\ue83a!\x8b\ue83b\x98# A % !#! . # ! !(!'"
- u"! ! ! % !#! ! ! ! ! % !## & # # ! . 5& $ 5\ue869!\x9f7\x8c\ue86d!"
- u"\xa1,g\ue86e!<#\xa3\ue873!\x9e\ue87e!\x9a"
-), u"\ue80c\ue840-\ue868\ue86a-\ue86c\ue86f-\ue872")
+], ("T4(4I!)!'!&/ 0 \x96')2$+! !\x83$ %## !(! ! ; u \x86.\x88 =#!+YoA& 87C"
+ "% } !5%+%) #!*! <0a,!4B1%'!&-'!1!$!33`HsG$!;!+.52'(#%#- & !$#$!*!9% 2%"
+ "H''%#- & % % %B# !H *+ - & % $$!;!5%3!,(#%#- & % $$!X% 5!:! '$ #$% "
+ "! %$%$ $)W!G( / 2$!> &%C( / . $$!L! %5%;( D#!*!* 4'&*$W + !#&]F %"
+ "6&]% !#% !#!(# & ! !#% # %1!#$ !/#L!S( @?$\x817-!*''#$!$%+ ',6!:= !&!"
+ "#7 \x90 ##& ! ##D ##B ##& ! ##9 K ##^Y2*V#'$\x9d#5 4&p((+, #2*2*2, 5OC"
+ "!'!Uy.D !&_)0J<#$,E'4Q/1Pv!|8:&K<9%)E>@7 )@\x80# #$%1gT\x8e#'#=#'#( ! !"
+ " ! 0#P & !$ &$##'',& &d!9!*,b!'!#. !$$(! ! ! # 1##&$'!G%\xa58 8 \x84("
+ "#$%6= !&!#Q+!*/1& & & & & & & &t!\x97%E$&%'V( z #&D${:Aj2\x99\xa6q\xa9"
+ "E\xa4UZ#\x8d$2)%-8*0#_J+#b#M#(S1 # /0O2[R'$! !6>)/A?+8?G)-):9*\ue803!`KJ9J\ue804#PriL3>@7M$!6F2#/! !C* 3V& ! # "
+ "9 .+8N(#%#- & % $$!;!6$\ue805eF-% !\x8987#=F-!k7x4\ue806\x87RB!\x95K"
+ "\ue808!\xa2\ue809e\x8a\ue80d!8\ue811!\x9c\ue81a!\x9b+0c<;F*#BH&:\ue81b"
+ "\xa0U,!l,\ue82c!%\ue82f!\"&,$++.\ue835!w m %#!#%## ) ! & S ##( & > # $ "
+ "!$& \x91#3 3 0 3 0 3 0 3 0 3 (\ue83a!\x8b\ue83b\x98# A % !#! . # ! !(!'"
+ "! ! ! % !#! ! ! ! ! % !## & # # ! . 5& $ 5\ue869!\x9f7\x8c\ue86d!"
+ "\xa1,g\ue86e!<#\xa3\ue873!\x9e\ue87e!\x9a"
+), "\ue80c\ue840-\ue868\ue86a-\ue86c\ue86f-\ue872")
reName = (u(r"(?:#(?:[ \t]*[1-9])?|(?:'|L)(?:[ \t]*(?:[0-9']|L))*)")
.replace(u("L"), unicodeLetters))
@@ -100,77 +100,77 @@ def decompressUnicodeRanges(d, s, h):
# These must be sorted by decreasing string length, for longest match first
operators = [
- u"~!=",
- u"~<=",
- u"~>=",
- u":=_",
- u"::=",
- u"!=",
- u"++",
- u"--",
- u"->",
- u"..",
- u":=",
- u":>",
- u"<:",
- u"<=",
- u"<>",
- u"==",
- u">=",
- u"~<",
- u"~=",
- u"~>",
- u"~~",
- u"!",
- u"%",
- u"&",
- u"*",
- u"+",
- u"-",
- u".",
- u"/",
- u":",
- u";",
- u"<",
- u"=",
- u">",
- u"^",
- u"_",
- u"|",
- u"\u00ac", # ¬
- u"\u00b0", # °
- u"\u00b7", # ·
- u"\u00d7", # ×
- u"\u00f7", # ÷
- u"\u2062", # invisible times
- u"\u2192", # →
- u"\u2208", # ∈
- u"\u2209", # ∉
- u"\u2212", # −
- u"\u2215", # ∕
- u"\u2216", # ∖
- u"\u221a", # √
- u"\u2227", # ∧
- u"\u2228", # ∨
- u"\u2229", # ∩
- u"\u222a", # ∪
- u"\u2236", # ∶
- u"\u2248", # ≈
- u"\u2249", # ≉
- u"\u225f", # ≟
- u"\u2260", # ≠
- u"\u2264", # ≤
- u"\u2265", # ≥
- u"\u2266", # ≦
- u"\u2267", # ≧
- u"\u22c5", # ⋅
- u"\u2a85", # ⪅
- u"\u2a86", # ⪆
- u"\u2a89", # ⪉
- u"\u2a8a", # ⪊
+ "~!=",
+ "~<=",
+ "~>=",
+ ":=_",
+ "::=",
+ "!=",
+ "++",
+ "--",
+ "->",
+ "..",
+ ":=",
+ ":>",
+ "<:",
+ "<=",
+ "<>",
+ "==",
+ ">=",
+ "~<",
+ "~=",
+ "~>",
+ "~~",
+ "!",
+ "%",
+ "&",
+ "*",
+ "+",
+ "-",
+ ".",
+ "/",
+ ":",
+ ";",
+ "<",
+ "=",
+ ">",
+ "^",
+ "_",
+ "|",
+ "\u00ac", # ¬
+ "\u00b0", # °
+ "\u00b7", # ·
+ "\u00d7", # ×
+ "\u00f7", # ÷
+ "\u2062", # invisible times
+ "\u2192", # →
+ "\u2208", # ∈
+ "\u2209", # ∉
+ "\u2212", # −
+ "\u2215", # ∕
+ "\u2216", # ∖
+ "\u221a", # √
+ "\u2227", # ∧
+ "\u2228", # ∨
+ "\u2229", # ∩
+ "\u222a", # ∪
+ "\u2236", # ∶
+ "\u2248", # ≈
+ "\u2249", # ≉
+ "\u225f", # ≟
+ "\u2260", # ≠
+ "\u2264", # ≤
+ "\u2265", # ≥
+ "\u2266", # ≦
+ "\u2267", # ≧
+ "\u22c5", # ⋅
+ "\u2a85", # ⪅
+ "\u2a86", # ⪆
+ "\u2a89", # ⪉
+ "\u2a8a", # ⪊
]
-reOps = u"|".join(map(re.escape, operators))
+reOps = "|".join(map(re.escape, operators))
class CindyScriptLexer(RegexLexer):
name = "CindyScript"
@@ -179,22 +179,22 @@ class CindyScriptLexer(RegexLexer):
mimetypes = ["text/x-cindyscript"]
tokens = {
'root': [
- (u'[ \t\n]+', Token.Text.Whitespace),
- (u'//.*', Token.Comment.Single),
- (u'/\\*', Token.Comment.Multiline, 'mlc'),
+ ('[ \t\n]+', Token.Text.Whitespace),
+ ('//.*', Token.Comment.Single),
+ ('/\\*', Token.Comment.Multiline, 'mlc'),
(reNumber, Token.Number),
(reOps, Token.Operator),
(u(r'\,|\[|\]|\(|\)|\{|\}'), Token.Punctuation),
- (u'(?:[₊₋][ \t]*)?[₀₁₂₃₄₅₆₇₈₉](?:[ \t]*[₀₁₂₃₄₅₆₇₈₉])*', Token.Number),
- (u'(?:[⁺⁻][ \t]*)?[⁰¹²³⁴⁵⁶⁷⁸⁹](?:[ \t]*[⁰¹²³⁴⁵⁶⁷⁸⁹])*', Token.Number),
- (reName + u'(?=\s*\()', Token.Name.Function),
+ ('(?:[₊₋][ \t]*)?[₀₁₂₃₄₅₆₇₈₉](?:[ \t]*[₀₁₂₃₄₅₆₇₈₉])*', Token.Number),
+ ('(?:[⁺⁻][ \t]*)?[⁰¹²³⁴⁵⁶⁷⁸⁹](?:[ \t]*[⁰¹²³⁴⁵⁶⁷⁸⁹])*', Token.Number),
+ (reName + '(?=\s*\()', Token.Name.Function),
(reName, Token.Name.Variable),
- (u'"[^"]*"', Token.String.Double),
+ ('"[^"]*"', Token.String.Double),
],
'mlc': [
- (u'/\\*', Token.Comment.Multiline, '#push'),
- (u'\\*/', Token.Comment.Multiline, '#pop'),
- (u'(?:[^*/]|\\*(?!/)|/(?!\\*))+', Token.Comment.Multiline),
+ ('/\\*', Token.Comment.Multiline, '#push'),
+ ('\\*/', Token.Comment.Multiline, '#pop'),
+ ('(?:[^*/]|\\*(?!/)|/(?!\\*))+', Token.Comment.Multiline),
],
}
@@ -209,14 +209,14 @@ class CindyJsHtmlLexer(RegexLexer):
flags = re.DOTALL
tokens = {
'root': [
- (u'(.*<\\s*script[^>]*\\s'
- u'type\\s*=\\s*["\']text/x-cindyscript[^a-z][^>]*>)'
- u'(.*?)'
- u'(<\\s*/\\s*script\\s*>)',
+ ('(.*<\\s*script[^>]*\\s'
+ 'type\\s*=\\s*["\']text/x-cindyscript[^a-z][^>]*>)'
+ '(.*?)'
+ '(<\\s*/\\s*script\\s*>)',
bygroups(using(HtmlLexer),
using(CindyScriptLexer),
using(HtmlLexer))
),
- (u'.+', using(HtmlLexer))
+ ('.+', using(HtmlLexer))
]
}
diff --git a/tests/LexerBase.py b/tests/LexerBase.py
index aa09eca..e31dfdf 100644
--- a/tests/LexerBase.py
+++ b/tests/LexerBase.py
@@ -4,7 +4,7 @@
if sys.version_info[0] >= 3:
u = str
else:
- u = unicode
+ u = str
class LexerBase(unittest.TestCase):
@@ -14,7 +14,7 @@ def lex(self, string, expected = None):
if expected is not None:
if len(expected) != len(toks):
print()
- print(' | '.join(v for t, v in toks))
+ print((' | '.join(v for t, v in toks)))
for exp, act in zip(expected, toks):
if act is None:
pass
diff --git a/tests/TestHtml.py b/tests/TestHtml.py
index 56764db..1104109 100644
--- a/tests/TestHtml.py
+++ b/tests/TestHtml.py
@@ -9,41 +9,41 @@ class TestCindyJsHtmlLexer(LexerBase):
lexerClass = C.CindyJsHtmlLexer
def test_JSandCS(self):
- self.lex(u'''
+ self.lex('''
''',
[
- u'<', u'html', u'>',
- u'<', u'body', u' ', u'data-foo', u'=', u' ', u'"bar"', u'>',
- u'<', (T.Name.Tag, u'script'), u' ', u'type', u'=',
- (T.String, u'"text/javascript"'), u'>', u'', u'\n',
- (T.Keyword, u'if'),
- (T.Punctuation, u'('),
- (T.Keyword, u'false'),
- (T.Punctuation, u')'),
- (T.Name, u'foo'),
- (T.Punctuation, u'('),
- (T.Punctuation, u')'),
- (T.Punctuation, u';'),
- (T.Text, u'\n'),
- u'<', u'/', (T.Name.Tag, u'script'), u'>',
- u'<', u'script', u' ', u'id', u'=', u'"xy"',
- u' ', (T.Name.Attribute, u'type'), u'=',
- (T.String, u'"text/x-cindyscript"'), u'>', u'\n',
- (T.Name.Function, u'if'),
- (T.Punctuation, u'('),
- (T.Name.Variable, u'false'),
- (T.Punctuation, u','),
- (T.Name.Function, u'foo'),
- (T.Punctuation, u'('),
- (T.Punctuation, u')'),
- (T.Punctuation, u')'),
- (T.Text, u'\n'),
- u'<', u'/', (T.Name.Tag, u'script'), u'>',
- u'<', u'/', u'body', u'>',
- u'<', u'/', (T.Name.Tag, u'html'), u'>',
- u'\n',
+ '<', 'html', '>',
+ '<', 'body', ' ', 'data-foo', '=', ' ', '"bar"', '>',
+ '<', (T.Name.Tag, 'script'), ' ', 'type', '=',
+ (T.String, '"text/javascript"'), '>', '', '\n',
+ (T.Keyword, 'if'),
+ (T.Punctuation, '('),
+ (T.Keyword, 'false'),
+ (T.Punctuation, ')'),
+ (T.Name, 'foo'),
+ (T.Punctuation, '('),
+ (T.Punctuation, ')'),
+ (T.Punctuation, ';'),
+ (T.Text, '\n'),
+ '<', '/', (T.Name.Tag, 'script'), '>',
+ '<', 'script', ' ', 'id', '=', '"xy"',
+ ' ', (T.Name.Attribute, 'type'), '=',
+ (T.String, '"text/x-cindyscript"'), '>', '\n',
+ (T.Name.Function, 'if'),
+ (T.Punctuation, '('),
+ (T.Name.Variable, 'false'),
+ (T.Punctuation, ','),
+ (T.Name.Function, 'foo'),
+ (T.Punctuation, '('),
+ (T.Punctuation, ')'),
+ (T.Punctuation, ')'),
+ (T.Text, '\n'),
+ '<', '/', (T.Name.Tag, 'script'), '>',
+ '<', '/', 'body', '>',
+ '<', '/', (T.Name.Tag, 'html'), '>',
+ '\n',
])
diff --git a/tests/TestLexer.py b/tests/TestLexer.py
index fd7f80e..a5f2669 100644
--- a/tests/TestLexer.py
+++ b/tests/TestLexer.py
@@ -9,55 +9,55 @@ class TestCindyScriptLexer(LexerBase):
lexerClass = C.CindyScriptLexer
def test_string(self):
- self.lex(u'some+"f//o/*o\\"+bar', [
- u'some', u'+',
+ self.lex('some+"f//o/*o\\"+bar', [
+ 'some', '+',
(T.String.Double, '"f//o/*o\\"'),
- u'+', u'bar', u'\n'
+ '+', 'bar', '\n'
])
def test_multiLineComment(self):
- self.lex(u'f/*(x)//y+\ng*/(z)', [
- u'f',
- (T.Comment.Multiline, u'/*'),
- (T.Comment.Multiline, u'(x)//y+\ng'),
- (T.Comment.Multiline, u'*/'),
- u'(', u'z', u')', u'\n'
+ self.lex('f/*(x)//y+\ng*/(z)', [
+ 'f',
+ (T.Comment.Multiline, '/*'),
+ (T.Comment.Multiline, '(x)//y+\ng'),
+ (T.Comment.Multiline, '*/'),
+ '(', 'z', ')', '\n'
])
def test_nestedMultiLineComment(self):
- self.lex(u'a/*b/*c///*d*//e/**//*/ */*/***/f', [
- u'a',
- (T.Comment.Multiline, u'/*'),
- (T.Comment.Multiline, u'b'),
- (T.Comment.Multiline, u'/*'),
- (T.Comment.Multiline, u'c//'),
- (T.Comment.Multiline, u'/*'),
- (T.Comment.Multiline, u'd'),
- (T.Comment.Multiline, u'*/'),
- (T.Comment.Multiline, u'/e'),
- (T.Comment.Multiline, u'/*'),
- (T.Comment.Multiline, u'*/'),
- (T.Comment.Multiline, u'/*'),
- (T.Comment.Multiline, u'/ '),
- (T.Comment.Multiline, u'*/'),
- (T.Comment.Multiline, u'*/'),
- (T.Comment.Multiline, u'**'),
- (T.Comment.Multiline, u'*/'),
- u'f', u'\n'
+ self.lex('a/*b/*c///*d*//e/**//*/ */*/***/f', [
+ 'a',
+ (T.Comment.Multiline, '/*'),
+ (T.Comment.Multiline, 'b'),
+ (T.Comment.Multiline, '/*'),
+ (T.Comment.Multiline, 'c//'),
+ (T.Comment.Multiline, '/*'),
+ (T.Comment.Multiline, 'd'),
+ (T.Comment.Multiline, '*/'),
+ (T.Comment.Multiline, '/e'),
+ (T.Comment.Multiline, '/*'),
+ (T.Comment.Multiline, '*/'),
+ (T.Comment.Multiline, '/*'),
+ (T.Comment.Multiline, '/ '),
+ (T.Comment.Multiline, '*/'),
+ (T.Comment.Multiline, '*/'),
+ (T.Comment.Multiline, '**'),
+ (T.Comment.Multiline, '*/'),
+ 'f', '\n'
])
def test_singleDot(self):
- self.lex(u'1.*2', [
- (T.Number, u'1.'),
- (T.Operator, u'*'),
- (T.Number, u'2'),
- u'\n'
+ self.lex('1.*2', [
+ (T.Number, '1.'),
+ (T.Operator, '*'),
+ (T.Number, '2'),
+ '\n'
])
def test_doubleDot(self):
- self.lex(u'1..2', [
- (T.Number, u'1'),
- (T.Operator, u'..'),
- (T.Number, u'2'),
- u'\n'
+ self.lex('1..2', [
+ (T.Number, '1'),
+ (T.Operator, '..'),
+ (T.Number, '2'),
+ '\n'
])
diff --git a/tests/TestRegex.py b/tests/TestRegex.py
index b26f546..d30f8cc 100644
--- a/tests/TestRegex.py
+++ b/tests/TestRegex.py
@@ -7,7 +7,7 @@
if sys.version_info[0] >= 3:
u = str
else:
- u = unicode
+ u = str
class TestRegex(unittest.TestCase):
@@ -27,52 +27,52 @@ def shouldNotMatch(self, string):
def test_reOps(self):
self.re = re.compile(C.reOps)
- self.shouldNotMatch(u'')
- self.shouldMatch(u'+')
- self.shouldNotMatch(u'(')
- self.shouldMatch(u'|')
- self.shouldMatch(u';')
- self.shouldMatch(u'\u2260')
- self.shouldMatch(u'~>=')
+ self.shouldNotMatch('')
+ self.shouldMatch('+')
+ self.shouldNotMatch('(')
+ self.shouldMatch('|')
+ self.shouldMatch(';')
+ self.shouldMatch('\u2260')
+ self.shouldMatch('~>=')
def test_reNumber(self):
self.re = re.compile(C.reNumber)
- self.shouldMatch(u'1.2')
- self.shouldMatch(u'1..2', 1)
- self.shouldMatch(u'1 . . 2', 1)
- self.shouldMatch(u'1 . * 2', 4)
- self.shouldMatch(u'1 . 2')
- self.shouldMatch(u'. 3')
- self.shouldMatch(u'. 1 e + 2')
- self.shouldMatch(u'3 . e 4')
+ self.shouldMatch('1.2')
+ self.shouldMatch('1..2', 1)
+ self.shouldMatch('1 . . 2', 1)
+ self.shouldMatch('1 . * 2', 4)
+ self.shouldMatch('1 . 2')
+ self.shouldMatch('. 3')
+ self.shouldMatch('. 1 e + 2')
+ self.shouldMatch('3 . e 4')
def test_unicodeLetters(self):
self.re = re.compile(C.unicodeLetters)
- self.shouldMatch(u'a')
- self.shouldNotMatch(u'1')
- self.shouldNotMatch(u'.')
- self.shouldMatch(u'\u00F6')
- self.shouldNotMatch(u'\u00F7')
- self.shouldMatch(u'\u00F8')
- self.shouldMatch(u'\u02E4')
- self.shouldNotMatch(u'\u02E5')
- self.shouldMatch(u'\uFFDC')
- self.shouldNotMatch(u'\uFFDE')
- self.shouldMatch(u'\U00010000')
- self.shouldNotMatch(u'\U0001000C')
- self.shouldMatch(u'\U0002CEA0')
- self.shouldMatch(u'\U0002CEA1')
- self.shouldNotMatch(u'\U0002CEA2')
- self.shouldMatch(u'\U00013210')
- self.shouldNotMatch(u'\U00013579')
+ self.shouldMatch('a')
+ self.shouldNotMatch('1')
+ self.shouldNotMatch('.')
+ self.shouldMatch('\u00F6')
+ self.shouldNotMatch('\u00F7')
+ self.shouldMatch('\u00F8')
+ self.shouldMatch('\u02E4')
+ self.shouldNotMatch('\u02E5')
+ self.shouldMatch('\uFFDC')
+ self.shouldNotMatch('\uFFDE')
+ self.shouldMatch('\U00010000')
+ self.shouldNotMatch('\U0001000C')
+ self.shouldMatch('\U0002CEA0')
+ self.shouldMatch('\U0002CEA1')
+ self.shouldNotMatch('\U0002CEA2')
+ self.shouldMatch('\U00013210')
+ self.shouldNotMatch('\U00013579')
def test_unicodeDecompression(self):
# We could have pasted the fully decompressed regexp into the
# source, but we prefer to keep the source small and have the
# expanded version just in the unit tests.
- bmp = u'A-Za-z\xAA\xB5\xBA\xC0-\xD6\xD8-\xF6\xF8-\u02C1\u02C6-\u02D1\u02E0-\u02E4\u02EC\u02EE\u0370-\u0374\u0376\u0377\u037A-\u037D\u037F\u0386\u0388-\u038A\u038C\u038E-\u03A1\u03A3-\u03F5\u03F7-\u0481\u048A-\u052F\u0531-\u0556\u0559\u0561-\u0587\u05D0-\u05EA\u05F0-\u05F2\u0620-\u064A\u066E\u066F\u0671-\u06D3\u06D5\u06E5\u06E6\u06EE\u06EF\u06FA-\u06FC\u06FF\u0710\u0712-\u072F\u074D-\u07A5\u07B1\u07CA-\u07EA\u07F4\u07F5\u07FA\u0800-\u0815\u081A\u0824\u0828\u0840-\u0858\u08A0-\u08B4\u0904-\u0939\u093D\u0950\u0958-\u0961\u0971-\u0980\u0985-\u098C\u098F\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BD\u09CE\u09DC\u09DD\u09DF-\u09E1\u09F0\u09F1\u0A05-\u0A0A\u0A0F\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32\u0A33\u0A35\u0A36\u0A38\u0A39\u0A59-\u0A5C\u0A5E\u0A72-\u0A74\u0A85-\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2\u0AB3\u0AB5-\u0AB9\u0ABD\u0AD0\u0AE0\u0AE1\u0AF9\u0B05-\u0B0C\u0B0F\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32\u0B33\u0B35-\u0B39\u0B3D\u0B5C\u0B5D\u0B5F-\u0B61\u0B71\u0B83\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99\u0B9A\u0B9C\u0B9E\u0B9F\u0BA3\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB9\u0BD0\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C39\u0C3D\u0C58-\u0C5A\u0C60\u0C61\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBD\u0CDE\u0CE0\u0CE1\u0CF1\u0CF2\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D3A\u0D3D\u0D4E\u0D5F-\u0D61\u0D7A-\u0D7F\u0D85-\u0D96\u0D9A-\u0DB1\u0DB3-\u0DBB\u0DBD\u0DC0-\u0DC6\u0E01-\u0E30\u0E32\u0E33\u0E40-\u0E46\u0E81\u0E82\u0E84\u0E87\u0E88\u0E8A\u0E8D\u0E94-\u0E97\u0E99-\u0E9F\u0EA1-\u0EA3\u0EA5\u0EA7\u0EAA\u0EAB\u0EAD-\u0EB0\u0EB2\u0EB3\u0EBD\u0EC0-\u0EC4\u0EC6\u0EDC-\u0EDF\u0F00\u0F40-\u0F47\u0F49-\u0F6C\u0F88-\u0F8C\u1000-\u102A\u103F\u1050-\u1055\u105A-\u105D\u1061\u1065\u1066\u106E-\u1070\u1075-\u1081\u108E\u10A0-\u10C5\u10C7\u10CD\u10D0-\u10FA\u10FC-\u1248\u124A-\u124D\u1250-\u1256\u1258\u125A-\u125D\u1260-\u1288\u128A-\u128D\u1290-\u12B0\u12B2-\u12B5\u12B8-\u12BE\u12C0\u12C2-\u12C5\u12C8-\u12D6\u12D8-\u1310\u1312-\u1315\u1318-\u135A\u1380-\u138F\u13A0-\u13F5\u13F8-\u13FD\u1401-\u166C\u166F-\u167F\u1681-\u169A\u16A0-\u16EA\u16F1-\u16F8\u1700-\u170C\u170E-\u1711\u1720-\u1731\u1740-\u1751\u1760-\u176C\u176E-\u1770\u1780-\u17B3\u17D7\u17DC\u1820-\u1877\u1880-\u18A8\u18AA\u18B0-\u18F5\u1900-\u191E\u1950-\u196D\u1970-\u1974\u1980-\u19AB\u19B0-\u19C9\u1A00-\u1A16\u1A20-\u1A54\u1AA7\u1B05-\u1B33\u1B45-\u1B4B\u1B83-\u1BA0\u1BAE\u1BAF\u1BBA-\u1BE5\u1C00-\u1C23\u1C4D-\u1C4F\u1C5A-\u1C7D\u1CE9-\u1CEC\u1CEE-\u1CF1\u1CF5\u1CF6\u1D00-\u1DBF\u1E00-\u1F15\u1F18-\u1F1D\u1F20-\u1F45\u1F48-\u1F4D\u1F50-\u1F57\u1F59\u1F5B\u1F5D\u1F5F-\u1F7D\u1F80-\u1FB4\u1FB6-\u1FBC\u1FBE\u1FC2-\u1FC4\u1FC6-\u1FCC\u1FD0-\u1FD3\u1FD6-\u1FDB\u1FE0-\u1FEC\u1FF2-\u1FF4\u1FF6-\u1FFC\u2071\u207F\u2090-\u209C\u2102\u2107\u210A-\u2113\u2115\u2119-\u211D\u2124\u2126\u2128\u212A-\u212D\u212F-\u2139\u213C-\u213F\u2145-\u2149\u214E\u2183\u2184\u2C00-\u2C2E\u2C30-\u2C5E\u2C60-\u2CE4\u2CEB-\u2CEE\u2CF2\u2CF3\u2D00-\u2D25\u2D27\u2D2D\u2D30-\u2D67\u2D6F\u2D80-\u2D96\u2DA0-\u2DA6\u2DA8-\u2DAE\u2DB0-\u2DB6\u2DB8-\u2DBE\u2DC0-\u2DC6\u2DC8-\u2DCE\u2DD0-\u2DD6\u2DD8-\u2DDE\u2E2F\u3005\u3006\u3031-\u3035\u303B\u303C\u3041-\u3096\u309D-\u309F\u30A1-\u30FA\u30FC-\u30FF\u3105-\u312D\u3131-\u318E\u31A0-\u31BA\u31F0-\u31FF\u3400-\u4DB5\u4E00-\u9FD5\uA000-\uA48C\uA4D0-\uA4FD\uA500-\uA60C\uA610-\uA61F\uA62A\uA62B\uA640-\uA66E\uA67F-\uA69D\uA6A0-\uA6E5\uA717-\uA71F\uA722-\uA788\uA78B-\uA7AD\uA7B0-\uA7B7\uA7F7-\uA801\uA803-\uA805\uA807-\uA80A\uA80C-\uA822\uA840-\uA873\uA882-\uA8B3\uA8F2-\uA8F7\uA8FB\uA8FD\uA90A-\uA925\uA930-\uA946\uA960-\uA97C\uA984-\uA9B2\uA9CF\uA9E0-\uA9E4\uA9E6-\uA9EF\uA9FA-\uA9FE\uAA00-\uAA28\uAA40-\uAA42\uAA44-\uAA4B\uAA60-\uAA76\uAA7A\uAA7E-\uAAAF\uAAB1\uAAB5\uAAB6\uAAB9-\uAABD\uAAC0\uAAC2\uAADB-\uAADD\uAAE0-\uAAEA\uAAF2-\uAAF4\uAB01-\uAB06\uAB09-\uAB0E\uAB11-\uAB16\uAB20-\uAB26\uAB28-\uAB2E\uAB30-\uAB5A\uAB5C-\uAB65\uAB70-\uABE2\uAC00-\uD7A3\uD7B0-\uD7C6\uD7CB-\uD7FB\uF900-\uFA6D\uFA70-\uFAD9\uFB00-\uFB06\uFB13-\uFB17\uFB1D\uFB1F-\uFB28\uFB2A-\uFB36\uFB38-\uFB3C\uFB3E\uFB40\uFB41\uFB43\uFB44\uFB46-\uFBB1\uFBD3-\uFD3D\uFD50-\uFD8F\uFD92-\uFDC7\uFDF0-\uFDFB\uFE70-\uFE74\uFE76-\uFEFC\uFF21-\uFF3A\uFF41-\uFF5A\uFF66-\uFFBE\uFFC2-\uFFC7\uFFCA-\uFFCF\uFFD2-\uFFD7\uFFDA-\uFFDC'
- if len(u'\U00012345') > 1:
- expected = u'(?:[' + bmp + ']' + eval("""(
+ bmp = 'A-Za-z\xAA\xB5\xBA\xC0-\xD6\xD8-\xF6\xF8-\u02C1\u02C6-\u02D1\u02E0-\u02E4\u02EC\u02EE\u0370-\u0374\u0376\u0377\u037A-\u037D\u037F\u0386\u0388-\u038A\u038C\u038E-\u03A1\u03A3-\u03F5\u03F7-\u0481\u048A-\u052F\u0531-\u0556\u0559\u0561-\u0587\u05D0-\u05EA\u05F0-\u05F2\u0620-\u064A\u066E\u066F\u0671-\u06D3\u06D5\u06E5\u06E6\u06EE\u06EF\u06FA-\u06FC\u06FF\u0710\u0712-\u072F\u074D-\u07A5\u07B1\u07CA-\u07EA\u07F4\u07F5\u07FA\u0800-\u0815\u081A\u0824\u0828\u0840-\u0858\u08A0-\u08B4\u0904-\u0939\u093D\u0950\u0958-\u0961\u0971-\u0980\u0985-\u098C\u098F\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BD\u09CE\u09DC\u09DD\u09DF-\u09E1\u09F0\u09F1\u0A05-\u0A0A\u0A0F\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32\u0A33\u0A35\u0A36\u0A38\u0A39\u0A59-\u0A5C\u0A5E\u0A72-\u0A74\u0A85-\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2\u0AB3\u0AB5-\u0AB9\u0ABD\u0AD0\u0AE0\u0AE1\u0AF9\u0B05-\u0B0C\u0B0F\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32\u0B33\u0B35-\u0B39\u0B3D\u0B5C\u0B5D\u0B5F-\u0B61\u0B71\u0B83\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99\u0B9A\u0B9C\u0B9E\u0B9F\u0BA3\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB9\u0BD0\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C39\u0C3D\u0C58-\u0C5A\u0C60\u0C61\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBD\u0CDE\u0CE0\u0CE1\u0CF1\u0CF2\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D3A\u0D3D\u0D4E\u0D5F-\u0D61\u0D7A-\u0D7F\u0D85-\u0D96\u0D9A-\u0DB1\u0DB3-\u0DBB\u0DBD\u0DC0-\u0DC6\u0E01-\u0E30\u0E32\u0E33\u0E40-\u0E46\u0E81\u0E82\u0E84\u0E87\u0E88\u0E8A\u0E8D\u0E94-\u0E97\u0E99-\u0E9F\u0EA1-\u0EA3\u0EA5\u0EA7\u0EAA\u0EAB\u0EAD-\u0EB0\u0EB2\u0EB3\u0EBD\u0EC0-\u0EC4\u0EC6\u0EDC-\u0EDF\u0F00\u0F40-\u0F47\u0F49-\u0F6C\u0F88-\u0F8C\u1000-\u102A\u103F\u1050-\u1055\u105A-\u105D\u1061\u1065\u1066\u106E-\u1070\u1075-\u1081\u108E\u10A0-\u10C5\u10C7\u10CD\u10D0-\u10FA\u10FC-\u1248\u124A-\u124D\u1250-\u1256\u1258\u125A-\u125D\u1260-\u1288\u128A-\u128D\u1290-\u12B0\u12B2-\u12B5\u12B8-\u12BE\u12C0\u12C2-\u12C5\u12C8-\u12D6\u12D8-\u1310\u1312-\u1315\u1318-\u135A\u1380-\u138F\u13A0-\u13F5\u13F8-\u13FD\u1401-\u166C\u166F-\u167F\u1681-\u169A\u16A0-\u16EA\u16F1-\u16F8\u1700-\u170C\u170E-\u1711\u1720-\u1731\u1740-\u1751\u1760-\u176C\u176E-\u1770\u1780-\u17B3\u17D7\u17DC\u1820-\u1877\u1880-\u18A8\u18AA\u18B0-\u18F5\u1900-\u191E\u1950-\u196D\u1970-\u1974\u1980-\u19AB\u19B0-\u19C9\u1A00-\u1A16\u1A20-\u1A54\u1AA7\u1B05-\u1B33\u1B45-\u1B4B\u1B83-\u1BA0\u1BAE\u1BAF\u1BBA-\u1BE5\u1C00-\u1C23\u1C4D-\u1C4F\u1C5A-\u1C7D\u1CE9-\u1CEC\u1CEE-\u1CF1\u1CF5\u1CF6\u1D00-\u1DBF\u1E00-\u1F15\u1F18-\u1F1D\u1F20-\u1F45\u1F48-\u1F4D\u1F50-\u1F57\u1F59\u1F5B\u1F5D\u1F5F-\u1F7D\u1F80-\u1FB4\u1FB6-\u1FBC\u1FBE\u1FC2-\u1FC4\u1FC6-\u1FCC\u1FD0-\u1FD3\u1FD6-\u1FDB\u1FE0-\u1FEC\u1FF2-\u1FF4\u1FF6-\u1FFC\u2071\u207F\u2090-\u209C\u2102\u2107\u210A-\u2113\u2115\u2119-\u211D\u2124\u2126\u2128\u212A-\u212D\u212F-\u2139\u213C-\u213F\u2145-\u2149\u214E\u2183\u2184\u2C00-\u2C2E\u2C30-\u2C5E\u2C60-\u2CE4\u2CEB-\u2CEE\u2CF2\u2CF3\u2D00-\u2D25\u2D27\u2D2D\u2D30-\u2D67\u2D6F\u2D80-\u2D96\u2DA0-\u2DA6\u2DA8-\u2DAE\u2DB0-\u2DB6\u2DB8-\u2DBE\u2DC0-\u2DC6\u2DC8-\u2DCE\u2DD0-\u2DD6\u2DD8-\u2DDE\u2E2F\u3005\u3006\u3031-\u3035\u303B\u303C\u3041-\u3096\u309D-\u309F\u30A1-\u30FA\u30FC-\u30FF\u3105-\u312D\u3131-\u318E\u31A0-\u31BA\u31F0-\u31FF\u3400-\u4DB5\u4E00-\u9FD5\uA000-\uA48C\uA4D0-\uA4FD\uA500-\uA60C\uA610-\uA61F\uA62A\uA62B\uA640-\uA66E\uA67F-\uA69D\uA6A0-\uA6E5\uA717-\uA71F\uA722-\uA788\uA78B-\uA7AD\uA7B0-\uA7B7\uA7F7-\uA801\uA803-\uA805\uA807-\uA80A\uA80C-\uA822\uA840-\uA873\uA882-\uA8B3\uA8F2-\uA8F7\uA8FB\uA8FD\uA90A-\uA925\uA930-\uA946\uA960-\uA97C\uA984-\uA9B2\uA9CF\uA9E0-\uA9E4\uA9E6-\uA9EF\uA9FA-\uA9FE\uAA00-\uAA28\uAA40-\uAA42\uAA44-\uAA4B\uAA60-\uAA76\uAA7A\uAA7E-\uAAAF\uAAB1\uAAB5\uAAB6\uAAB9-\uAABD\uAAC0\uAAC2\uAADB-\uAADD\uAAE0-\uAAEA\uAAF2-\uAAF4\uAB01-\uAB06\uAB09-\uAB0E\uAB11-\uAB16\uAB20-\uAB26\uAB28-\uAB2E\uAB30-\uAB5A\uAB5C-\uAB65\uAB70-\uABE2\uAC00-\uD7A3\uD7B0-\uD7C6\uD7CB-\uD7FB\uF900-\uFA6D\uFA70-\uFAD9\uFB00-\uFB06\uFB13-\uFB17\uFB1D\uFB1F-\uFB28\uFB2A-\uFB36\uFB38-\uFB3C\uFB3E\uFB40\uFB41\uFB43\uFB44\uFB46-\uFBB1\uFBD3-\uFD3D\uFD50-\uFD8F\uFD92-\uFDC7\uFDF0-\uFDFB\uFE70-\uFE74\uFE76-\uFEFC\uFF21-\uFF3A\uFF41-\uFF5A\uFF66-\uFFBE\uFFC2-\uFFC7\uFFCA-\uFFCF\uFFD2-\uFFD7\uFFDA-\uFFDC'
+ if len('\U00012345') > 1:
+ expected = '(?:[' + bmp + ']' + eval("""(
u'|\uD800[\uDC00-\uDC0B\uDC0D-\uDC26\uDC28-\uDC3A\uDC3C\uDC3D\uDC3F-\uDC4D\uDC50-\uDC5D\uDC80-\uDCFA\uDE80-\uDE9C\uDEA0-\uDED0\uDF00-\uDF1F\uDF30-\uDF40\uDF42-\uDF49\uDF50-\uDF75\uDF80-\uDF9D\uDFA0-\uDFC3\uDFC8-\uDFCF]'
u'|\uD801[\uDC00-\uDC9D\uDD00-\uDD27\uDD30-\uDD63\uDE00-\uDF36\uDF40-\uDF55\uDF60-\uDF67]'
u'|\uD802[\uDC00-\uDC05\uDC08\uDC0A-\uDC35\uDC37\uDC38\uDC3C\uDC3F-\uDC55\uDC60-\uDC76\uDC80-\uDC9E\uDCE0-\uDCF2\uDCF4\uDCF5\uDD00-\uDD15\uDD20-\uDD39\uDD80-\uDDB7\uDDBE\uDDBF\uDE00\uDE10-\uDE13\uDE15-\uDE17\uDE19-\uDE33\uDE60-\uDE7C\uDE80-\uDE9C\uDEC0-\uDEC7\uDEC9-\uDEE4\uDF00-\uDF35\uDF40-\uDF55\uDF60-\uDF72\uDF80-\uDF91]'
@@ -101,32 +101,32 @@ def test_unicodeDecompression(self):
)""")
else:
expected = (
- u'[' + bmp +
- u'\U00010000-\U0001000B\U0001000D-\U00010026\U00010028-\U0001003A\U0001003C\U0001003D\U0001003F-\U0001004D\U00010050-\U0001005D\U00010080-\U000100FA\U00010280-\U0001029C\U000102A0-\U000102D0\U00010300-\U0001031F\U00010330-\U00010340\U00010342-\U00010349\U00010350-\U00010375\U00010380-\U0001039D\U000103A0-\U000103C3\U000103C8-\U000103CF'
- u'\U00010400-\U0001049D\U00010500-\U00010527\U00010530-\U00010563\U00010600-\U00010736\U00010740-\U00010755\U00010760-\U00010767'
- u'\U00010800-\U00010805\U00010808\U0001080A-\U00010835\U00010837\U00010838\U0001083C\U0001083F-\U00010855\U00010860-\U00010876\U00010880-\U0001089E\U000108E0-\U000108F2\U000108F4\U000108F5\U00010900-\U00010915\U00010920-\U00010939\U00010980-\U000109B7\U000109BE\U000109BF\U00010A00\U00010A10-\U00010A13\U00010A15-\U00010A17\U00010A19-\U00010A33\U00010A60-\U00010A7C\U00010A80-\U00010A9C\U00010AC0-\U00010AC7\U00010AC9-\U00010AE4\U00010B00-\U00010B35\U00010B40-\U00010B55\U00010B60-\U00010B72\U00010B80-\U00010B91'
- u'\U00010C00-\U00010C48\U00010C80-\U00010CB2\U00010CC0-\U00010CF2'
- u'\U00011003-\U00011037\U00011083-\U000110AF\U000110D0-\U000110E8\U00011103-\U00011126\U00011150-\U00011172\U00011176\U00011183-\U000111B2\U000111C1-\U000111C4\U000111DA\U000111DC\U00011200-\U00011211\U00011213-\U0001122B\U00011280-\U00011286\U00011288\U0001128A-\U0001128D\U0001128F-\U0001129D\U0001129F-\U000112A8\U000112B0-\U000112DE\U00011305-\U0001130C\U0001130F\U00011310\U00011313-\U00011328\U0001132A-\U00011330\U00011332\U00011333\U00011335-\U00011339\U0001133D\U00011350\U0001135D-\U00011361'
- u'\U00011480-\U000114AF\U000114C4\U000114C5\U000114C7\U00011580-\U000115AE\U000115D8-\U000115DB\U00011600-\U0001162F\U00011644\U00011680-\U000116AA\U00011700-\U00011719'
- u'\U000118A0-\U000118DF\U000118FF\U00011AC0-\U00011AF8'
- u'\U00012000-\U00012399'
- u'\U00012480-\U00012543'
- u'\U00013400-\U0001342E'
- u'\U00014400-\U00014646'
- u'\U00016800-\U00016A38\U00016A40-\U00016A5E\U00016AD0-\U00016AED\U00016B00-\U00016B2F\U00016B40-\U00016B43\U00016B63-\U00016B77\U00016B7D-\U00016B8F'
- u'\U00016F00-\U00016F44\U00016F50\U00016F93-\U00016F9F'
- u'\U0001B000\U0001B001'
- u'\U0001BC00-\U0001BC6A\U0001BC70-\U0001BC7C\U0001BC80-\U0001BC88\U0001BC90-\U0001BC99'
- u'\U0001D400-\U0001D454\U0001D456-\U0001D49C\U0001D49E\U0001D49F\U0001D4A2\U0001D4A5\U0001D4A6\U0001D4A9-\U0001D4AC\U0001D4AE-\U0001D4B9\U0001D4BB\U0001D4BD-\U0001D4C3\U0001D4C5-\U0001D505\U0001D507-\U0001D50A\U0001D50D-\U0001D514\U0001D516-\U0001D51C\U0001D51E-\U0001D539\U0001D53B-\U0001D53E\U0001D540-\U0001D544\U0001D546\U0001D54A-\U0001D550\U0001D552-\U0001D6A5\U0001D6A8-\U0001D6C0\U0001D6C2-\U0001D6DA\U0001D6DC-\U0001D6FA\U0001D6FC-\U0001D714\U0001D716-\U0001D734\U0001D736-\U0001D74E\U0001D750-\U0001D76E\U0001D770-\U0001D788\U0001D78A-\U0001D7A8\U0001D7AA-\U0001D7C2\U0001D7C4-\U0001D7CB'
- u'\U0001E800-\U0001E8C4'
- u'\U0001EE00-\U0001EE03\U0001EE05-\U0001EE1F\U0001EE21\U0001EE22\U0001EE24\U0001EE27\U0001EE29-\U0001EE32\U0001EE34-\U0001EE37\U0001EE39\U0001EE3B\U0001EE42\U0001EE47\U0001EE49\U0001EE4B\U0001EE4D-\U0001EE4F\U0001EE51\U0001EE52\U0001EE54\U0001EE57\U0001EE59\U0001EE5B\U0001EE5D\U0001EE5F\U0001EE61\U0001EE62\U0001EE64\U0001EE67-\U0001EE6A\U0001EE6C-\U0001EE72\U0001EE74-\U0001EE77\U0001EE79-\U0001EE7C\U0001EE7E\U0001EE80-\U0001EE89\U0001EE8B-\U0001EE9B\U0001EEA1-\U0001EEA3\U0001EEA5-\U0001EEA9\U0001EEAB-\U0001EEBB'
- u'\U0002A400-\U0002A6D6\U0002A700-\U0002A7FF'
- u'\U0002B400-\U0002B734\U0002B740-\U0002B7FF'
- u'\U0002B800-\U0002B81D\U0002B820-\U0002BBFF'
- u'\U0002CC00-\U0002CEA1'
- u'\U0002F800-\U0002FA1D'
- u'\U00013000-\U000133FF\U00020000-\U0002A3FF\U0002A800-\U0002B3FF\U0002BC00-\U0002CBFF'
- u']')
+ '[' + bmp +
+ '\U00010000-\U0001000B\U0001000D-\U00010026\U00010028-\U0001003A\U0001003C\U0001003D\U0001003F-\U0001004D\U00010050-\U0001005D\U00010080-\U000100FA\U00010280-\U0001029C\U000102A0-\U000102D0\U00010300-\U0001031F\U00010330-\U00010340\U00010342-\U00010349\U00010350-\U00010375\U00010380-\U0001039D\U000103A0-\U000103C3\U000103C8-\U000103CF'
+ '\U00010400-\U0001049D\U00010500-\U00010527\U00010530-\U00010563\U00010600-\U00010736\U00010740-\U00010755\U00010760-\U00010767'
+ '\U00010800-\U00010805\U00010808\U0001080A-\U00010835\U00010837\U00010838\U0001083C\U0001083F-\U00010855\U00010860-\U00010876\U00010880-\U0001089E\U000108E0-\U000108F2\U000108F4\U000108F5\U00010900-\U00010915\U00010920-\U00010939\U00010980-\U000109B7\U000109BE\U000109BF\U00010A00\U00010A10-\U00010A13\U00010A15-\U00010A17\U00010A19-\U00010A33\U00010A60-\U00010A7C\U00010A80-\U00010A9C\U00010AC0-\U00010AC7\U00010AC9-\U00010AE4\U00010B00-\U00010B35\U00010B40-\U00010B55\U00010B60-\U00010B72\U00010B80-\U00010B91'
+ '\U00010C00-\U00010C48\U00010C80-\U00010CB2\U00010CC0-\U00010CF2'
+ '\U00011003-\U00011037\U00011083-\U000110AF\U000110D0-\U000110E8\U00011103-\U00011126\U00011150-\U00011172\U00011176\U00011183-\U000111B2\U000111C1-\U000111C4\U000111DA\U000111DC\U00011200-\U00011211\U00011213-\U0001122B\U00011280-\U00011286\U00011288\U0001128A-\U0001128D\U0001128F-\U0001129D\U0001129F-\U000112A8\U000112B0-\U000112DE\U00011305-\U0001130C\U0001130F\U00011310\U00011313-\U00011328\U0001132A-\U00011330\U00011332\U00011333\U00011335-\U00011339\U0001133D\U00011350\U0001135D-\U00011361'
+ '\U00011480-\U000114AF\U000114C4\U000114C5\U000114C7\U00011580-\U000115AE\U000115D8-\U000115DB\U00011600-\U0001162F\U00011644\U00011680-\U000116AA\U00011700-\U00011719'
+ '\U000118A0-\U000118DF\U000118FF\U00011AC0-\U00011AF8'
+ '\U00012000-\U00012399'
+ '\U00012480-\U00012543'
+ '\U00013400-\U0001342E'
+ '\U00014400-\U00014646'
+ '\U00016800-\U00016A38\U00016A40-\U00016A5E\U00016AD0-\U00016AED\U00016B00-\U00016B2F\U00016B40-\U00016B43\U00016B63-\U00016B77\U00016B7D-\U00016B8F'
+ '\U00016F00-\U00016F44\U00016F50\U00016F93-\U00016F9F'
+ '\U0001B000\U0001B001'
+ '\U0001BC00-\U0001BC6A\U0001BC70-\U0001BC7C\U0001BC80-\U0001BC88\U0001BC90-\U0001BC99'
+ '\U0001D400-\U0001D454\U0001D456-\U0001D49C\U0001D49E\U0001D49F\U0001D4A2\U0001D4A5\U0001D4A6\U0001D4A9-\U0001D4AC\U0001D4AE-\U0001D4B9\U0001D4BB\U0001D4BD-\U0001D4C3\U0001D4C5-\U0001D505\U0001D507-\U0001D50A\U0001D50D-\U0001D514\U0001D516-\U0001D51C\U0001D51E-\U0001D539\U0001D53B-\U0001D53E\U0001D540-\U0001D544\U0001D546\U0001D54A-\U0001D550\U0001D552-\U0001D6A5\U0001D6A8-\U0001D6C0\U0001D6C2-\U0001D6DA\U0001D6DC-\U0001D6FA\U0001D6FC-\U0001D714\U0001D716-\U0001D734\U0001D736-\U0001D74E\U0001D750-\U0001D76E\U0001D770-\U0001D788\U0001D78A-\U0001D7A8\U0001D7AA-\U0001D7C2\U0001D7C4-\U0001D7CB'
+ '\U0001E800-\U0001E8C4'
+ '\U0001EE00-\U0001EE03\U0001EE05-\U0001EE1F\U0001EE21\U0001EE22\U0001EE24\U0001EE27\U0001EE29-\U0001EE32\U0001EE34-\U0001EE37\U0001EE39\U0001EE3B\U0001EE42\U0001EE47\U0001EE49\U0001EE4B\U0001EE4D-\U0001EE4F\U0001EE51\U0001EE52\U0001EE54\U0001EE57\U0001EE59\U0001EE5B\U0001EE5D\U0001EE5F\U0001EE61\U0001EE62\U0001EE64\U0001EE67-\U0001EE6A\U0001EE6C-\U0001EE72\U0001EE74-\U0001EE77\U0001EE79-\U0001EE7C\U0001EE7E\U0001EE80-\U0001EE89\U0001EE8B-\U0001EE9B\U0001EEA1-\U0001EEA3\U0001EEA5-\U0001EEA9\U0001EEAB-\U0001EEBB'
+ '\U0002A400-\U0002A6D6\U0002A700-\U0002A7FF'
+ '\U0002B400-\U0002B734\U0002B740-\U0002B7FF'
+ '\U0002B800-\U0002B81D\U0002B820-\U0002BBFF'
+ '\U0002CC00-\U0002CEA1'
+ '\U0002F800-\U0002FA1D'
+ '\U00013000-\U000133FF\U00020000-\U0002A3FF\U0002A800-\U0002B3FF\U0002BC00-\U0002CBFF'
+ ']')
actual = C.unicodeLetters
if expected == actual:
return None
@@ -137,10 +137,10 @@ def test_unicodeDecompression(self):
i += 1
e = expected[i - 10 : i + 10]
a = actual[i - 10 : i + 10]
- self.assertEqual(e, a, u"'{0}{1}{2}' != '{0}{3}{4}'".format(
- u'' if i - 10 <= 0 else u'...',
- e, u'' if i + 10 >= len(expected) else u'...',
- a, u'' if i + 10 >= len(actual) else u'...',
+ self.assertEqual(e, a, "'{0}{1}{2}' != '{0}{3}{4}'".format(
+ '' if i - 10 <= 0 else '...',
+ e, '' if i + 10 >= len(expected) else '...',
+ a, '' if i + 10 >= len(actual) else '...',
))