Package pyxb :: Package utils :: Module unicode :: Class XML1p0e2
[hide private]
[frames] | no frames]

Class XML1p0e2

source code

object --+
         |
        XML1p0e2

Regular expression support for XML Schema Data Types.

This class holds character classes and regular expressions used to constrain the lexical space of XML Schema datatypes derived from string. They are from XML 1.0 (Second Edition) and Namespaces in XML.

Unlike the regular expressions used for pattern constraints in XML Schema, which are derived from the Unicode 3.1 specification, these are derived from the Unicode 2.0 specification.

The XML Schema definition refers explicitly to the second edition of XML, so we have to use these code point sets and patterns. Be aware that subsequent updates to the XML specification have changed the corresponding patterns for other uses of XML. One significant change is that the original specification, used here, does not allow wide unicode characters.

Instance Methods [hide private]

Inherited from object: __delattr__, __format__, __getattribute__, __hash__, __init__, __new__, __reduce__, __reduce_ex__, __repr__, __setattr__, __sizeof__, __str__, __subclasshook__

Class Variables [hide private]
  Char = CodePointSet(0x0009, 0x000A, 0x000D, (0x0020, 0xD7FF), ...
  BaseChar = CodePointSet((0x0041, 0x005A), (0x0061, 0x007A), (0...
  Ideographic = CodePointSet((0x4E00, 0x9FA5), 0x3007, (0x3021, ...
  Letter = CodePointSet(BaseChar).extend(Ideographic)
  CombiningChar = CodePointSet((0x0300, 0x0345), (0x0360, 0x0361...
  Digit = CodePointSet((0x0030, 0x0039), (0x0660, 0x0669), (0x06...
  Extender = CodePointSet(0x00B7, 0x02D0, 0x02D1, 0x0387, 0x0640...
  NameStartChar = CodePointSet(Letter)
  NCNameStartChar = CodePointSet(Letter)
  NameChar = CodePointSet(Letter)
  NCNameChar = CodePointSet(Letter)
  Name_pat = u'[:A-Z_a-zÀ-ÖØ-öø-ıĴ-ľŁ-ňŊ-žƀ-ǃǍ-ǰǴ-ǵǺ-ȗɐ-ʨʻ-ˁΆΈ-Ί...
  Name_re = re.compile(r'^[:A-Z_a-z\xc0-\xd6\xd8-\xf6\xf8-\u0131...
hash(x)
  NmToken_pat = u'[\--.0-:A-Z_a-z·À-ÖØ-öø-ıĴ-ľŁ-ňŊ-žƀ-ǃǍ-ǰǴ-ǵǺ-ȗ...
  NmToken_re = re.compile(r'^[--\.0-:A-Z_a-z\xb7\xc0-\xd6\xd8-\x...
hash(x)
  NCName_pat = u'[A-Z_a-zÀ-ÖØ-öø-ıĴ-ľŁ-ňŊ-žƀ-ǃǍ-ǰǴ-ǵǺ-ȗɐ-ʨʻ-ˁΆΈ-...
  NCName_re = re.compile(r'^[A-Z_a-z\xc0-\xd6\xd8-\xf6\xf8-\u013...
hash(x)
  QName_pat = u'([A-Z_a-zÀ-ÖØ-öø-ıĴ-ľŁ-ňŊ-žƀ-ǃǍ-ǰǴ-ǵǺ-ȗɐ-ʨʻ-ˁΆΈ-...
  QName_re = re.compile(r'^([A-Z_a-z\xc0-\xd6\xd8-\xf6\xf8-\u013...
Properties [hide private]

Inherited from object: __class__

Class Variable Details [hide private]

Char

Value:
CodePointSet(0x0009, 0x000A, 0x000D, (0x0020, 0xD7FF), (0xE000, 0xFFFD\
))

BaseChar

Value:
CodePointSet((0x0041, 0x005A), (0x0061, 0x007A), (0x00C0, 0x00D6), (0x\
00D8, 0x00F6), (0x00F8, 0x00FF), (0x0100, 0x0131), (0x0134, 0x013E), (\
0x0141, 0x0148), (0x014A, 0x017E), (0x0180, 0x01C3), (0x01CD, 0x01F0),\
 (0x01F4, 0x01F5), (0x01FA, 0x0217), (0x0250, 0x02A8), (0x02BB, 0x02C1\
), 0x0386, (0x0388, 0x038A), 0x038C, (0x038E, 0x03A1), (0x03A3, 0x03CE\
), (0x03D0, 0x03D6), 0x03DA, 0x03DC, 0x03DE, 0x03E0, (0x03E2, 0x03F3),\
 (0x0401, 0x040C), (0x040E, 0x044F), (0x0451, 0x045C), (0x045E, 0x0481\
), (0x0490, 0x04C4), (0x04C7, 0x04C8), (0x04CB, 0x04CC), (0x04D0, 0x04\
...

Ideographic

Value:
CodePointSet((0x4E00, 0x9FA5), 0x3007, (0x3021, 0x3029))

CombiningChar

Value:
CodePointSet((0x0300, 0x0345), (0x0360, 0x0361), (0x0483, 0x0486), (0x\
0591, 0x05A1), (0x05A3, 0x05B9), (0x05BB, 0x05BD), 0x05BF, (0x05C1, 0x\
05C2), 0x05C4, (0x064B, 0x0652), 0x0670, (0x06D6, 0x06DC), (0x06DD, 0x\
06DF), (0x06E0, 0x06E4), (0x06E7, 0x06E8), (0x06EA, 0x06ED), (0x0901, \
0x0903), 0x093C, (0x093E, 0x094C), 0x094D, (0x0951, 0x0954), (0x0962, \
0x0963), (0x0981, 0x0983), 0x09BC, 0x09BE, 0x09BF, (0x09C0, 0x09C4), (\
0x09C7, 0x09C8), (0x09CB, 0x09CD), 0x09D7, (0x09E2, 0x09E3), 0x0A02, 0\
x0A3C, 0x0A3E, 0x0A3F, (0x0A40, 0x0A42), (0x0A47, 0x0A48), (0x0A4B, 0x\
...

Digit

Value:
CodePointSet((0x0030, 0x0039), (0x0660, 0x0669), (0x06F0, 0x06F9), (0x\
0966, 0x096F), (0x09E6, 0x09EF), (0x0A66, 0x0A6F), (0x0AE6, 0x0AEF), (\
0x0B66, 0x0B6F), (0x0BE7, 0x0BEF), (0x0C66, 0x0C6F), (0x0CE6, 0x0CEF),\
 (0x0D66, 0x0D6F), (0x0E50, 0x0E59), (0x0ED0, 0x0ED9), (0x0F20, 0x0F29\
))

Extender

Value:
CodePointSet(0x00B7, 0x02D0, 0x02D1, 0x0387, 0x0640, 0x0E46, 0x0EC6, 0\
x3005, (0x3031, 0x3035), (0x309D, 0x309E), (0x30FC, 0x30FE))

Name_pat

Value:
u'[:A-Z_a-zÀ-ÖØ-öø-ıĴ-ľŁ-ňŊ-žƀ-ǃǍ-ǰǴ-ǵǺ-ȗɐ-ʨʻ-ˁΆΈ-ΊΌΎ-ΡΣ-ώϐ-ϖϚϜϞϠϢ-ϳЁ-\
ЌЎ-яё-ќў-ҁҐ-ӄӇ-ӈӋ-ӌӐ-ӫӮ-ӵӸ-ӹԱ-Ֆՙա-ֆא-תװ-ײء-غف-يٱ-ڷں-ھۀ-ێې-ۓەۥ-ۦअ-हऽक़-ॡ\
অ-ঌএ-ঐও-নপ-রলশ-হড়-ঢ়য়-ৡৰ-ৱਅ-ਊਏ-ਐਓ-ਨਪ-ਰਲ-ਲ਼ਵ-ਸ਼ਸ-ਹਖ਼-ੜਫ਼ੲ-ੴઅ-ઋઍએ-ઑઓ-નપ-રલ-ળવ\
-હઽૠଅ-ଌଏ-ଐଓ-ନପ-ରଲ-ଳଶ-ହଽଡ଼-ଢ଼ୟ-ୡஅ-ஊஎ-ஐஒ-கங-சஜஞ-டண-தந-பம-வஷ-ஹఅ-ఌఎ-ఐఒ-నప-ళవ\
-హౠ-ౡಅ-ಌಎ-ಐಒ-ನಪ-ಳವ-ಹೞೠ-ೡഅ-ഌഎ-ഐഒ-നപ-ഹൠ-ൡก-ฮะา-ำเ-ๅກ-ຂຄງ-ຈຊຍດ-ທນ-ຟມ-ຣລວສ\
-ຫອ-ຮະາ-ຳຽເ-ໄཀ-ཇཉ-ཀྵႠ-Ⴥა-ჶᄀᄂ-ᄃᄅ-ᄇᄉᄋ-ᄌᄎ-ᄒᄼᄾᅀᅌᅎᅐᅔ-ᅕᅙᅟ-ᅡᅣᅥᅧᅩᅭ-ᅮᅲ-ᅳᅵᆞᆨᆫᆮ-ᆯᆷ\
-ᆸᆺᆼ-ᇂᇫᇰᇹḀ-ẛẠ-ỹἀ-ἕἘ-Ἕἠ-ὅὈ-Ὅὐ-ὗὙὛὝὟ-ώᾀ-ᾴᾶ-ᾼιῂ-ῄῆ-ῌῐ-ΐῖ-Ίῠ-Ῥῲ-ῴῶ-ῼΩK-Å℮ↀ\
-ↂ〇〡-〩ぁ-ゔァ-ヺㄅ-ㄬ一-龥가-힣][\--.0-:A-Z_a-z·À-ÖØ-öø-ıĴ-ľŁ-ňŊ-žƀ-ǃǍ-ǰǴ-ǵǺ-ȗɐ-\
...

Name_re

hash(x)

Value:
re.compile(r'^[:A-Z_a-z\xc0-\xd6\xd8-\xf6\xf8-\u0131\u0134-\u013e\u014\
1-\u0148\u014a-\u017e\u0180-\u01c3\u01cd-\u01f0\u01f4-\u01f5\u01fa-\u0\
217\u0250-\u02a8\u02bb-\u02c1\u0386\u0388-\u038a\u038c\u038e-\u03a1\u0\
3a3-\u03ce\u03d0-\u03d6\u03da\u03dc\u03de\u03e0\u03e2-\u03f3\u0401-\u0\
40c\u040e-\u044f\u0451-\u045c\u045e-\u0481\u0490-\u04c4\u04c7-\u04c8\u\
04cb-\u04cc\u04d0-\u04eb\u04ee-\u04f5\u04f8-\u04f9\u0531-\u0556\u0559\\
u0561-\u0586\u05d0-\u05ea\u05f0-\u05f2\u0621-\u063a\u0641-\u064a\u0671\
-\u06b7\u06ba-\u06be\u06c0-\u06ce\u06d0-\u06d3\u06d5\u06e5-\u06e6\u090\
...

NmToken_pat

Value:
u'[\--.0-:A-Z_a-z·À-ÖØ-öø-ıĴ-ľŁ-ňŊ-žƀ-ǃǍ-ǰǴ-ǵǺ-ȗɐ-ʨʻ-ˁː-ˑ̀-͠ͅ-͡Ά-ΊΌΎ-Ρ\
Σ-ώϐ-ϖϚϜϞϠϢ-ϳЁ-ЌЎ-яё-ќў-ҁ҃-҆Ґ-ӄӇ-ӈӋ-ӌӐ-ӫӮ-ӵӸ-ӹԱ-Ֆՙա-ֆ֑-֣֡-ֹֻ-ֽֿׁ-ׂׄא-ת\
װ-ײء-غـ-ْ٠-٩ٰ-ڷں-ھۀ-ێې-ۓە-۪ۨ-ۭ۰-۹ँ-ःअ-ह़-्॑-॔क़-ॣ०-९ঁ-ঃঅ-ঌএ-ঐও-নপ-রলশ-হ\
়া-ৄে-ৈো-্ৗড়-ঢ়য়-ৣ০-ৱਂਅ-ਊਏ-ਐਓ-ਨਪ-ਰਲ-ਲ਼ਵ-ਸ਼ਸ-ਹ਼ਾ-ੂੇ-ੈੋ-੍ਖ਼-ੜਫ਼੦-ੴઁ-ઃઅ-ઋઍએ-ઑઓ\
-નપ-રલ-ળવ-હ઼-ૅે-ૉો-્ૠ૦-૯ଁ-ଃଅ-ଌଏ-ଐଓ-ନପ-ରଲ-ଳଶ-ହ଼-ୃେ-ୈୋ-୍ୖ-ୗଡ଼-ଢ଼ୟ-ୡ୦-୯ஂ-ஃஅ\
-ஊஎ-ஐஒ-கங-சஜஞ-டண-தந-பம-வஷ-ஹா-ூெ-ைொ-்ௗ௧-௯ఁ-ఃఅ-ఌఎ-ఐఒ-నప-ళవ-హా-ౄె-ైొ-్ౕ-ౖ\
ౠ-ౡ౦-౯ಂ-ಃಅ-ಌಎ-ಐಒ-ನಪ-ಳವ-ಹಾ-ೄೆ-ೈೊ-್ೕ-ೖೞೠ-ೡ೦-೯ം-ഃഅ-ഌഎ-ഐഒ-നപ-ഹാ-ൃെ-ൈൊ-്ൗൠ-\
ൡ൦-൯ก-ฮะ-ฺเ-๎๐-๙ກ-ຂຄງ-ຈຊຍດ-ທນ-ຟມ-ຣລວສ-ຫອ-ຮະ-ູົ-ຽເ-ໄໆ່-ໍ໐-໙༘-༙༠-༩༹༵༷༾-ཇ\
...

NmToken_re

hash(x)

Value:
re.compile(r'^[--\.0-:A-Z_a-z\xb7\xc0-\xd6\xd8-\xf6\xf8-\u0131\u0134-\\
u013e\u0141-\u0148\u014a-\u017e\u0180-\u01c3\u01cd-\u01f0\u01f4-\u01f5\
\u01fa-\u0217\u0250-\u02a8\u02bb-\u02c1\u02d0-\u02d1\u0300-\u0345\u036\
0-\u0361\u0386-\u038a\u038c\u038e-\u03a1\u03a3-\u03ce\u03d0-\u03d6\u03\
da\u03dc\u03de\u03e0\u03e2-\u03f3\u0401-\u040c\u040e-\u044f\u0451-\u04\
5c\u045e-\u0481\u0483-\u0486\u0490-\u04c4\u04c7-\u04c8\u04cb-\u04cc\u0\
4d0-\u04eb\u04ee-\u04f5\u04f8-\u04f9\u0531-\u0556\u0559\u0561-\u0586\u\
0591-\u05a1\u05a3-\u05b9\u05bb-\u05bd\u05bf\u05c1-\u05c2\u05c4\u05d0-\\
...

NCName_pat

Value:
u'[A-Z_a-zÀ-ÖØ-öø-ıĴ-ľŁ-ňŊ-žƀ-ǃǍ-ǰǴ-ǵǺ-ȗɐ-ʨʻ-ˁΆΈ-ΊΌΎ-ΡΣ-ώϐ-ϖϚϜϞϠϢ-ϳЁ-Ќ\
Ў-яё-ќў-ҁҐ-ӄӇ-ӈӋ-ӌӐ-ӫӮ-ӵӸ-ӹԱ-Ֆՙա-ֆא-תװ-ײء-غف-يٱ-ڷں-ھۀ-ێې-ۓەۥ-ۦअ-हऽक़-ॡঅ\
-ঌএ-ঐও-নপ-রলশ-হড়-ঢ়য়-ৡৰ-ৱਅ-ਊਏ-ਐਓ-ਨਪ-ਰਲ-ਲ਼ਵ-ਸ਼ਸ-ਹਖ਼-ੜਫ਼ੲ-ੴઅ-ઋઍએ-ઑઓ-નપ-રલ-ળવ-\
હઽૠଅ-ଌଏ-ଐଓ-ନପ-ରଲ-ଳଶ-ହଽଡ଼-ଢ଼ୟ-ୡஅ-ஊஎ-ஐஒ-கங-சஜஞ-டண-தந-பம-வஷ-ஹఅ-ఌఎ-ఐఒ-నప-ళవ-\
హౠ-ౡಅ-ಌಎ-ಐಒ-ನಪ-ಳವ-ಹೞೠ-ೡഅ-ഌഎ-ഐഒ-നപ-ഹൠ-ൡก-ฮะา-ำเ-ๅກ-ຂຄງ-ຈຊຍດ-ທນ-ຟມ-ຣລວສ-\
ຫອ-ຮະາ-ຳຽເ-ໄཀ-ཇཉ-ཀྵႠ-Ⴥა-ჶᄀᄂ-ᄃᄅ-ᄇᄉᄋ-ᄌᄎ-ᄒᄼᄾᅀᅌᅎᅐᅔ-ᅕᅙᅟ-ᅡᅣᅥᅧᅩᅭ-ᅮᅲ-ᅳᅵᆞᆨᆫᆮ-ᆯᆷ-\
ᆸᆺᆼ-ᇂᇫᇰᇹḀ-ẛẠ-ỹἀ-ἕἘ-Ἕἠ-ὅὈ-Ὅὐ-ὗὙὛὝὟ-ώᾀ-ᾴᾶ-ᾼιῂ-ῄῆ-ῌῐ-ΐῖ-Ίῠ-Ῥῲ-ῴῶ-ῼΩK-Å℮ↀ-\
ↂ〇〡-〩ぁ-ゔァ-ヺㄅ-ㄬ一-龥가-힣][\--.0-9A-Z_a-z·À-ÖØ-öø-ıĴ-ľŁ-ňŊ-žƀ-ǃǍ-ǰǴ-ǵǺ-ȗɐ-ʨ\
...

NCName_re

hash(x)

Value:
re.compile(r'^[A-Z_a-z\xc0-\xd6\xd8-\xf6\xf8-\u0131\u0134-\u013e\u0141\
-\u0148\u014a-\u017e\u0180-\u01c3\u01cd-\u01f0\u01f4-\u01f5\u01fa-\u02\
17\u0250-\u02a8\u02bb-\u02c1\u0386\u0388-\u038a\u038c\u038e-\u03a1\u03\
a3-\u03ce\u03d0-\u03d6\u03da\u03dc\u03de\u03e0\u03e2-\u03f3\u0401-\u04\
0c\u040e-\u044f\u0451-\u045c\u045e-\u0481\u0490-\u04c4\u04c7-\u04c8\u0\
4cb-\u04cc\u04d0-\u04eb\u04ee-\u04f5\u04f8-\u04f9\u0531-\u0556\u0559\u\
0561-\u0586\u05d0-\u05ea\u05f0-\u05f2\u0621-\u063a\u0641-\u064a\u0671-\
\u06b7\u06ba-\u06be\u06c0-\u06ce\u06d0-\u06d3\u06d5\u06e5-\u06e6\u0905\
...

QName_pat

Value:
u'([A-Z_a-zÀ-ÖØ-öø-ıĴ-ľŁ-ňŊ-žƀ-ǃǍ-ǰǴ-ǵǺ-ȗɐ-ʨʻ-ˁΆΈ-ΊΌΎ-ΡΣ-ώϐ-ϖϚϜϞϠϢ-ϳЁ-\
ЌЎ-яё-ќў-ҁҐ-ӄӇ-ӈӋ-ӌӐ-ӫӮ-ӵӸ-ӹԱ-Ֆՙա-ֆא-תװ-ײء-غف-يٱ-ڷں-ھۀ-ێې-ۓەۥ-ۦअ-हऽक़-ॡ\
অ-ঌএ-ঐও-নপ-রলশ-হড়-ঢ়য়-ৡৰ-ৱਅ-ਊਏ-ਐਓ-ਨਪ-ਰਲ-ਲ਼ਵ-ਸ਼ਸ-ਹਖ਼-ੜਫ਼ੲ-ੴઅ-ઋઍએ-ઑઓ-નપ-રલ-ળવ\
-હઽૠଅ-ଌଏ-ଐଓ-ନପ-ରଲ-ଳଶ-ହଽଡ଼-ଢ଼ୟ-ୡஅ-ஊஎ-ஐஒ-கங-சஜஞ-டண-தந-பம-வஷ-ஹఅ-ఌఎ-ఐఒ-నప-ళవ\
-హౠ-ౡಅ-ಌಎ-ಐಒ-ನಪ-ಳವ-ಹೞೠ-ೡഅ-ഌഎ-ഐഒ-നപ-ഹൠ-ൡก-ฮะา-ำเ-ๅກ-ຂຄງ-ຈຊຍດ-ທນ-ຟມ-ຣລວສ\
-ຫອ-ຮະາ-ຳຽເ-ໄཀ-ཇཉ-ཀྵႠ-Ⴥა-ჶᄀᄂ-ᄃᄅ-ᄇᄉᄋ-ᄌᄎ-ᄒᄼᄾᅀᅌᅎᅐᅔ-ᅕᅙᅟ-ᅡᅣᅥᅧᅩᅭ-ᅮᅲ-ᅳᅵᆞᆨᆫᆮ-ᆯᆷ\
-ᆸᆺᆼ-ᇂᇫᇰᇹḀ-ẛẠ-ỹἀ-ἕἘ-Ἕἠ-ὅὈ-Ὅὐ-ὗὙὛὝὟ-ώᾀ-ᾴᾶ-ᾼιῂ-ῄῆ-ῌῐ-ΐῖ-Ίῠ-Ῥῲ-ῴῶ-ῼΩK-Å℮ↀ\
-ↂ〇〡-〩ぁ-ゔァ-ヺㄅ-ㄬ一-龥가-힣][\--.0-9A-Z_a-z·À-ÖØ-öø-ıĴ-ľŁ-ňŊ-žƀ-ǃǍ-ǰǴ-ǵǺ-ȗɐ-\
...

QName_re

Value:
re.compile(r'^([A-Z_a-z\xc0-\xd6\xd8-\xf6\xf8-\u0131\u0134-\u013e\u014\
1-\u0148\u014a-\u017e\u0180-\u01c3\u01cd-\u01f0\u01f4-\u01f5\u01fa-\u0\
217\u0250-\u02a8\u02bb-\u02c1\u0386\u0388-\u038a\u038c\u038e-\u03a1\u0\
3a3-\u03ce\u03d0-\u03d6\u03da\u03dc\u03de\u03e0\u03e2-\u03f3\u0401-\u0\
40c\u040e-\u044f\u0451-\u045c\u045e-\u0481\u0490-\u04c4\u04c7-\u04c8\u\
04cb-\u04cc\u04d0-\u04eb\u04ee-\u04f5\u04f8-\u04f9\u0531-\u0556\u0559\\
u0561-\u0586\u05d0-\u05ea\u05f0-\u05f2\u0621-\u063a\u0641-\u064a\u0671\
-\u06b7\u06ba-\u06be\u06c0-\u06ce\u06d0-\u06d3\u06d5\u06e5-\u06e6\u090\
...