1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
|
import java.lang.Character
try:
# import from jarjar-ed version
from org.python.icu.text import Normalizer
from org.python.icu.lang import UCharacter, UProperty
from org.python.icu.util import VersionInfo
from org.python.icu.lang.UCharacter import EastAsianWidth, DecompositionType
from org.python.icu.lang.UCharacterEnums import ECharacterCategory, ECharacterDirection
except ImportError:
# development version of Jython, so use extlibs
from com.ibm.icu.text import Normalizer
from com.ibm.icu.lang import UCharacter, UProperty
from com.ibm.icu.util import VersionInfo
from com.ibm.icu.lang.UCharacter import EastAsianWidth, DecompositionType
from com.ibm.icu.lang.UCharacterEnums import ECharacterCategory, ECharacterDirection
__all__ = (
"bidirectional", "category", "combining", "decimal", "decomposition", "digit", "east_asian_width",
"lookup", "mirrored", "name", "normalize", "numeric", "unidata_version")
_forms = {
'NFC': Normalizer.NFC,
'NFKC': Normalizer.NFKC,
'NFD': Normalizer.NFD,
'NFKD': Normalizer.NFKD
}
Nonesuch = object() # to distinguish from None, which is a valid return value for some functions
def _validate_unichr(unichr):
if not(isinstance(unichr, unicode)):
raise TypeError("must be unicode, not {}".format(type(unichr).__name__))
if len(unichr) > 1 or len(unichr) == 0:
raise TypeError("need a single Unicode character as parameter")
def _get_codepoint(unichr):
_validate_unichr(unichr)
return ord(unichr)
def name(unichr, default=Nonesuch):
# handle None
n = UCharacter.getName(_get_codepoint(unichr))
if n is None:
if default is not Nonesuch:
return default
else:
raise ValueError("no such name")
return n
def lookup(name):
codepoint = UCharacter.getCharFromName(name)
if codepoint == -1:
raise KeyError("undefined character name '{}".format(name))
return unichr(codepoint)
def digit(unichr, default=Nonesuch):
d = UCharacter.digit(_get_codepoint(unichr))
if d == -1:
if default is not Nonesuch:
return default
else:
raise ValueError("not a digit")
return d
def decimal(unichr, default=Nonesuch):
d = UCharacter.getNumericValue(_get_codepoint(unichr))
if d < 0 or d > 9:
if default is not Nonesuch:
return default
else:
raise ValueError("not a decimal")
return d
def numeric(unichr, default=Nonesuch):
n = UCharacter.getUnicodeNumericValue(_get_codepoint(unichr))
if n == UCharacter.NO_NUMERIC_VALUE:
if default is not Nonesuch:
return default
else:
raise ValueError("not a numeric")
return n
_decomp = {
DecompositionType.CANONICAL: "canonical",
DecompositionType.CIRCLE: "circle",
DecompositionType.COMPAT: "compat",
DecompositionType.FINAL: "final",
DecompositionType.FONT: "font",
DecompositionType.FRACTION: "fraction",
DecompositionType.INITIAL: "initial",
DecompositionType.ISOLATED: "isolated",
DecompositionType.MEDIAL: "medial",
DecompositionType.NARROW: "narrow",
DecompositionType.NOBREAK: "nobreak",
DecompositionType.NONE: None,
DecompositionType.SMALL: "small",
DecompositionType.SQUARE: "square",
DecompositionType.SUB: "sub",
DecompositionType.SUPER: "super",
DecompositionType.VERTICAL: "vertical",
DecompositionType.WIDE: "wide"
}
def _get_decomp_type(unichr):
if unichr == u"\u2044": # FRACTION SLASH
# special case this for CPython compatibility even though this returns as not being combining, eg, see
# http://www.fileformat.info/info/unicode/char/2044/index.htm
return "fraction"
else:
return _decomp[UCharacter.getIntPropertyValue(ord(unichr), UProperty.DECOMPOSITION_TYPE)]
def decomposition(unichr):
_validate_unichr(unichr)
d = Normalizer.decompose(unichr, True)
decomp_type = None
if len(d) == 1:
decomp_type = _get_decomp_type(unichr)
else:
for c in d:
decomp_type = _get_decomp_type(c)
# print "Got a decomp_type %r %r %r" % (c, d, decomp_type)
if decomp_type is not None:
break
hexed = " ".join(("{0:04X}".format(ord(c)) for c in d))
if decomp_type:
return "<{}> {}".format(decomp_type, hexed)
elif len(d) == 1:
return ""
else:
return hexed
# To map from ICU4J enumerations for category, bidirection, and
# east_asian_width to the underlying property values that Python uses
# from UnicodeData.txt required a manual mapping between the following
# two files:
#
# http://icu-project.org/apiref/icu4j/constant-values.html
# http://www.unicode.org/Public/6.3.0/ucd/PropertyValueAliases.txt
_cat = {
ECharacterCategory.COMBINING_SPACING_MARK: "Mc",
ECharacterCategory.CONNECTOR_PUNCTUATION: "Pc",
ECharacterCategory.CONTROL: "Cc",
ECharacterCategory.CURRENCY_SYMBOL: "Sc",
ECharacterCategory.DASH_PUNCTUATION: "Pd",
ECharacterCategory.DECIMAL_DIGIT_NUMBER: "Nd",
ECharacterCategory.ENCLOSING_MARK: "Me",
ECharacterCategory.END_PUNCTUATION: "Pe",
ECharacterCategory.FINAL_PUNCTUATION: "Pf",
ECharacterCategory.FORMAT: "Cf",
# per http://icu-project.org/apiref/icu4j/com/ibm/icu/lang/UCharacterEnums.ECharacterCategory.html#GENERAL_OTHER_TYPES
# - no characters in [UnicodeData.txt] have this property
ECharacterCategory.GENERAL_OTHER_TYPES: "Cn Not Assigned",
ECharacterCategory.INITIAL_PUNCTUATION: "Pi",
ECharacterCategory.LETTER_NUMBER: "Nl",
ECharacterCategory.LINE_SEPARATOR: "Zl",
ECharacterCategory.LOWERCASE_LETTER: "Ll",
ECharacterCategory.MATH_SYMBOL: "Sm",
ECharacterCategory.MODIFIER_LETTER: "Lm",
ECharacterCategory.MODIFIER_SYMBOL: "Sk",
ECharacterCategory.NON_SPACING_MARK: "Mn",
ECharacterCategory.OTHER_LETTER: "Lo",
ECharacterCategory.OTHER_NUMBER: "No",
ECharacterCategory.OTHER_PUNCTUATION: "Po",
ECharacterCategory.OTHER_SYMBOL: "So",
ECharacterCategory.PARAGRAPH_SEPARATOR: "Zp",
ECharacterCategory.PRIVATE_USE: "Co",
ECharacterCategory.SPACE_SEPARATOR: "Zs",
ECharacterCategory.START_PUNCTUATION: "Ps",
ECharacterCategory.SURROGATE: "Cs",
ECharacterCategory.TITLECASE_LETTER: "Lt",
ECharacterCategory.UNASSIGNED: "Cn",
ECharacterCategory.UPPERCASE_LETTER: "Lu",
}
def category(unichr):
return _cat[UCharacter.getType(_get_codepoint(unichr))]
_dir = {
ECharacterDirection.ARABIC_NUMBER: "An",
ECharacterDirection.BLOCK_SEPARATOR: "B",
ECharacterDirection.BOUNDARY_NEUTRAL: "BN",
ECharacterDirection.COMMON_NUMBER_SEPARATOR: "CS",
ECharacterDirection.DIR_NON_SPACING_MARK: "NSM",
ECharacterDirection.EUROPEAN_NUMBER: "EN",
ECharacterDirection.EUROPEAN_NUMBER_SEPARATOR: "ES",
ECharacterDirection.EUROPEAN_NUMBER_TERMINATOR: "ET",
ECharacterDirection.FIRST_STRONG_ISOLATE: "FSI",
ECharacterDirection.LEFT_TO_RIGHT: "L",
ECharacterDirection.LEFT_TO_RIGHT_EMBEDDING: "LRE",
ECharacterDirection.LEFT_TO_RIGHT_ISOLATE: "LRI",
ECharacterDirection.LEFT_TO_RIGHT_OVERRIDE: "LRO",
ECharacterDirection.OTHER_NEUTRAL: "ON",
ECharacterDirection.POP_DIRECTIONAL_FORMAT: "PDF",
ECharacterDirection.POP_DIRECTIONAL_ISOLATE: "PDI",
ECharacterDirection.RIGHT_TO_LEFT: "R",
ECharacterDirection.RIGHT_TO_LEFT_ARABIC: "AL",
ECharacterDirection.RIGHT_TO_LEFT_EMBEDDING: "RLE",
ECharacterDirection.RIGHT_TO_LEFT_ISOLATE: "RLI",
ECharacterDirection.RIGHT_TO_LEFT_OVERRIDE: "RLO",
ECharacterDirection.SEGMENT_SEPARATOR: "S",
ECharacterDirection.WHITE_SPACE_NEUTRAL: "WS"
}
def bidirectional(unichr):
return _dir[UCharacter.getDirection(_get_codepoint(unichr))]
def combining(unichr):
return UCharacter.getCombiningClass(_get_codepoint(unichr))
def mirrored(unichr):
return UCharacter.isMirrored(_get_codepoint(unichr))
_eaw = {
# http://www.unicode.org/reports/tr11/
EastAsianWidth.AMBIGUOUS : "A",
EastAsianWidth.COUNT : "?", # apparently not used, see above TR
EastAsianWidth.FULLWIDTH : "F",
EastAsianWidth.HALFWIDTH : "H",
EastAsianWidth.NARROW : "Na",
EastAsianWidth.NEUTRAL : "N",
EastAsianWidth.WIDE : "W"
}
def east_asian_width(unichr):
return _eaw[UCharacter.getIntPropertyValue(_get_codepoint(unichr), UProperty.EAST_ASIAN_WIDTH)]
def normalize(form, unistr):
"""
Return the normal form 'form' for the Unicode string unistr. Valid
values for form are 'NFC', 'NFKC', 'NFD', and 'NFKD'.
"""
try:
normalizer_form = _forms[form]
except KeyError:
raise ValueError('invalid normalization form')
return Normalizer.normalize(unistr, normalizer_form)
def get_icu_version():
versions = []
for k in VersionInfo.__dict__.iterkeys():
if k.startswith("UNICODE_"):
v = getattr(VersionInfo, k)
versions.append((v.getMajor(), v.getMinor(), v.getMilli()))
return ".".join(str(x) for x in max(versions))
unidata_version = get_icu_version()
|
