-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathgen-casemap-txt.py
executable file
·240 lines (211 loc) · 9.01 KB
/
gen-casemap-txt.py
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
#!/usr/bin/env python3
# Copyright (C) 1998, 1999 Tom Tromey
# Copyright (C) 2001 Red Hat Software
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2, or (at your option)
# any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, see <http://www.gnu.org/licenses/>.
"""
gen-casemap-txt.py - Generate test cases for case mapping from Unicode data.
See http://www.unicode.org/Public/UNIDATA/UnicodeCharacterDatabase.html
Usage:
I consider the output of this program to be unrestricted.
Use it as you will.
"""
import sys
import argparse
# Disable line length warnings as wrapping the test templates would be hard
# flake8: noqa: E501
def main(argv):
parser = argparse.ArgumentParser(
description="Generate test cases for case mapping from Unicode data"
)
parser.add_argument("UNICODE-VERSION")
parser.add_argument("UnicodeData.txt")
parser.add_argument("SpecialCasing.txt")
args = parser.parse_args(argv[1:])
version = getattr(args, "UNICODE-VERSION")
filename_udata = getattr(args, "UnicodeData.txt")
filename_casing = getattr(args, "SpecialCasing.txt")
# Names of fields in Unicode data table.
(
CODE,
NAME,
CATEGORY,
COMBINING_CLASSES,
BIDI_CATEGORY,
DECOMPOSITION,
DECIMAL_VALUE,
DIGIT_VALUE,
NUMERIC_VALUE,
MIRRORED,
OLD_NAME,
COMMENT,
UPPER,
LOWER,
TITLE,
) = range(15)
# Names of fields in the SpecialCasing table
CASE_CODE, CASE_LOWER, CASE_TITLE, CASE_UPPER, CASE_CONDITION = range(5)
upper = {}
title = {}
lower = {}
def make_hex(codes):
"""Converts a string of white space separated code points encoded as
hex values to a Unicode string. Any extra white space is ignored.
"""
return "".join([chr(int(c, 16)) for c in codes.split()])
def process_one(code, fields):
type_ = fields[CATEGORY]
if type_ == "Ll":
upper[code] = make_hex(fields[UPPER])
lower[code] = chr(code)
title[code] = make_hex(fields[TITLE])
elif type_ == "Lu":
lower[code] = make_hex(fields[LOWER])
upper[code] = chr(code)
title[code] = make_hex(fields[TITLE])
elif type_ == "Lt":
upper[code] = make_hex(fields[UPPER])
lower[code] = make_hex(fields[LOWER])
title[code] = make_hex(fields[LOWER])
with open(filename_udata, encoding="utf-8") as fileobj:
last_code = -1
for line in fileobj:
line = line.strip()
fields = [f.strip() for f in line.split(";")]
if len(fields) != 15:
raise SystemExit(
"Entry for %s has wrong number of fields (%d)"
% (fields[CODE], len(fields))
)
code = int(fields[CODE], 16)
if code > last_code + 1:
# Found a gap
if fields[NAME].endswith("Last>"):
# Fill the gap with the last character read,
# since this was a range specified in the char database
gfields = fields
else:
# The gap represents undefined characters. Only the type
# matters.
gfields = [
"",
"",
"Cn",
"0",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
]
last_code += 1
while last_code < code:
gfields[CODE] = "%04x" % last_code
process_one(last_code, gfields)
last_code += 1
process_one(code, fields)
last_code = code
with open(filename_casing, encoding="utf-8") as fileobj:
last_code = -1
for line in fileobj:
# strip comments and skip empty lines
line = line.split("#", 1)[0].strip()
if not line:
continue
# all lines end with ";" so just remove it
line = line.rstrip(";").rstrip()
fields = [f.strip() for f in line.split(";")]
if len(fields) not in (4, 5):
raise SystemExit(
"Entry for %s has wrong number of fields (%d)"
% (fields[CASE_CODE], len(fields))
)
if len(fields) == 5:
# Ignore conditional special cases - we'll handle them manually
continue
code = int(fields[CASE_CODE], 16)
upper[code] = make_hex(fields[CASE_UPPER])
lower[code] = make_hex(fields[CASE_LOWER])
title[code] = make_hex(fields[CASE_TITLE])
print_tests(version, upper, title, lower)
def print_tests(version, upper, title, lower):
print(
"""\
# Test cases generated from Unicode {} data
# by gen-casemap-txt.py. Do not edit.
#
# Some special hand crafted tests
#
tr_TR\ti\ti\t\u0130\t\u0130\t# i => LATIN CAPITAL LETTER I WITH DOT ABOVE
tr_TR\tI\t\u0131\tI\tI\t# I => LATIN SMALL LETTER DOTLESS I
tr_TR\tI\u0307\ti\tI\u0307\tI\u0307\t# I => LATIN SMALL LETTER DOTLESS I
tr_TR.UTF-8\ti\ti\t\u0130\t\u0130\t# i => LATIN CAPITAL LETTER I WITH DOT ABOVE
tr_TR.UTF-8\tI\t\u0131\tI\tI\t# I => LATIN SMALL LETTER DOTLESS I
tr_TR.UTF-8\tI\u0307\ti\tI\u0307\tI\u0307\t# I => LATIN SMALL LETTER DOTLESS I
# Test reordering of YPOGEGRAMMENI across other accents
\t\u03b1\u0345\u0314\t\u03b1\u0345\u0314\t\u0391\u0345\u0314\t\u0391\u0314\u0399\t
\t\u03b1\u0314\u0345\t\u03b1\u0314\u0345\t\u0391\u0314\u0345\t\u0391\u0314\u0399\t
# Handling of final and nonfinal sigma
\tΜΆΙΟΣ μάιος Μάιος ΜΆΙΟΣ \t
\tΜΆΙΟΣ μάιος Μάιος ΜΆΙΟΣ\t
\tΣΙΓΜΑ σιγμα Σιγμα ΣΙΓΜΑ\t
# Lithuanian rule of i followed by letter with dot. Not at all sure
# about the titlecase part here
lt_LT\ti\u0117\ti\u0117\tIe\tIE\t
lt_LT\tie\u0307\tie\u0307\tIe\tIE\t
lt_LT\t\u00cc\ti\u0307\u0300\t\u00cc\t\u00cc\t # LATIN CAPITAL LETTER I WITH GRAVE
lt_LT\t\u00CD\ti\u0307\u0301\t\u00CD\t\u00CD\t # LATIN CAPITAL LETTER I WITH ACUTE
lt_LT\t\u0128\ti\u0307\u0303\t\u0128\t\u0128\t # LATIN CAPITAL LETTER I WITH TILDE
lt_LT\tI\u0301\ti\u0307\u0301\tI\u0301\tI\u0301\t # LATIN CAPITAL LETTER I (with acute accent)
lt_LT\tI\u0300\ti\u0307\u0300\tI\u0300\tI\u0300\t # LATIN CAPITAL LETTER I (with grave accent)
lt_LT\tI\u0303\ti\u0307\u0303\tI\u0303\tI\u0303\t # LATIN CAPITAL LETTER I (with tilde above)
lt_LT\tI\u0328\u0301\ti\u0307\u0328\u0301\tI\u0328\u0301\tI\u0328\u0301\t # LATIN CAPITAL LETTER I (with ogonek and acute accent)
lt_LT\tJ\u0301\tj\u0307\u0301\tJ\u0301\tJ\u0301\t # LATIN CAPITAL LETTER J (with acute accent)
lt_LT\t\u012e\u0301\t\u012f\u0307\u0301\t\u012e\u0301\t\u012e\u0301\t # LATIN CAPITAL LETTER I WITH OGONEK (with acute accent)
lt_LT.UTF-8\ti\u0117\ti\u0117\tIe\tIE\t
lt_LT.UTF-8\tie\u0307\tie\u0307\tIe\tIE\t
lt_LT.UTF-8\t\u00cc\ti\u0307\u0300\t\u00cc\t\u00cc\t # LATIN CAPITAL LETTER I WITH GRAVE
lt_LT.UTF-8\t\u00CD\ti\u0307\u0301\t\u00CD\t\u00CD\t # LATIN CAPITAL LETTER I WITH ACUTE
lt_LT.UTF-8\t\u0128\ti\u0307\u0303\t\u0128\t\u0128\t # LATIN CAPITAL LETTER I WITH TILDE
lt_LT.UTF-8\tI\u0301\ti\u0307\u0301\tI\u0301\tI\u0301\t # LATIN CAPITAL LETTER I (with acute accent)
lt_LT.UTF-8\tI\u0300\ti\u0307\u0300\tI\u0300\tI\u0300\t # LATIN CAPITAL LETTER I (with grave accent)
lt_LT.UTF-8\tI\u0303\ti\u0307\u0303\tI\u0303\tI\u0303\t # LATIN CAPITAL LETTER I (with tilde above)
lt_LT.UTF-8\tI\u0328\u0301\ti\u0307\u0328\u0301\tI\u0328\u0301\tI\u0328\u0301\t # LATIN CAPITAL LETTER I (with ogonek and acute accent)
lt_LT.UTF-8\tJ\u0301\tj\u0307\u0301\tJ\u0301\tJ\u0301\t # LATIN CAPITAL LETTER J (with acute accent)
lt_LT.UTF-8\t\u012e\u0301\t\u012f\u0307\u0301\t\u012e\u0301\t\u012e\u0301\t # LATIN CAPITAL LETTER I WITH OGONEK (with acute accent)
# Special case not at initial position
\ta\ufb04\ta\ufb04\tAffl\tAFFL\t# FB04
#
# Now the automatic tests
#""".format(
version
)
)
for i in range(0x10FFFF):
if i == 0x3A3:
# Greek sigma needs special tests
continue
up = upper.get(i, "")
lo = lower.get(i, "")
ti = title.get(i, "")
if any([up, lo, ti]):
print("\t%s\t%s\t%s\t%s\t# %4X" % (chr(i), lo, ti, up, i))
if __name__ == "__main__":
sys.exit(main(sys.argv))