| 1 | #!/usr/bin/env python2
|
| 2 | """
|
| 3 | strings.py
|
| 4 | """
|
| 5 | from __future__ import print_function
|
| 6 |
|
| 7 | import os
|
| 8 | from mycpp import mylib
|
| 9 | from mycpp.mylib import log
|
| 10 |
|
| 11 | from typing import List
|
| 12 |
|
| 13 |
|
| 14 | def banner(s):
|
| 15 | # type: (str) -> None
|
| 16 | print('')
|
| 17 | print('=== %s ===' % s)
|
| 18 | print('')
|
| 19 |
|
| 20 |
|
| 21 | class Foo(object):
|
| 22 |
|
| 23 | def __init__(self):
|
| 24 | # type: () -> None
|
| 25 | self.s = 'mystr'
|
| 26 |
|
| 27 |
|
| 28 | def TestMethods():
|
| 29 | # type: () -> None
|
| 30 |
|
| 31 | s = 'a1bc'
|
| 32 |
|
| 33 | if s.startswith(''):
|
| 34 | print('empty yes')
|
| 35 |
|
| 36 | if s.startswith('a1'):
|
| 37 | print('a1 yes')
|
| 38 |
|
| 39 | if not s.startswith('zz'):
|
| 40 | print('zz no')
|
| 41 |
|
| 42 | if s.endswith(''):
|
| 43 | print('empty yes')
|
| 44 |
|
| 45 | if s.endswith('bc'):
|
| 46 | print('bc yes')
|
| 47 |
|
| 48 | if s.endswith('c'):
|
| 49 | print('bc yes')
|
| 50 |
|
| 51 | if not s.endswith('zzzzzz'):
|
| 52 | print('zzzzzz no')
|
| 53 |
|
| 54 | # This file is out of date! It thinks it happens in Python 3, but we have
|
| 55 | # it in Python 2.7
|
| 56 |
|
| 57 | # /home/andy/wedge/oils-for-unix.org/pkg/mypy/0.780/mypy/typeshed/stdlib/2/__builtin__.pyi:509: note: "startswith" of "str" defined here
|
| 58 |
|
| 59 | # Fixed here - https://github.com/python/typeshed/blob/main/stdlib/builtins.pyi
|
| 60 | #
|
| 61 | # It can be fixed by patching, gah
|
| 62 |
|
| 63 | # start pos
|
| 64 | #if s.startswith('bc', start=2):
|
| 65 | # print('bc YES')
|
| 66 |
|
| 67 | # find(s, start, end) can be used to implement TokenStartsWith() and
|
| 68 | # TokenEndsWith(), TokenEquals(), IsPlusEquals(), TokenContains(), etc.
|
| 69 |
|
| 70 | s = 'aaa-bb-cc'
|
| 71 | substrs = [
|
| 72 | 'aa',
|
| 73 | 'b',
|
| 74 | 'z',
|
| 75 | 'aaaa', # too long
|
| 76 | '',
|
| 77 | ]
|
| 78 | for substr in substrs:
|
| 79 | for start in xrange(0, len(s)):
|
| 80 | pos = s.find(substr, start)
|
| 81 | print('%s find %s start:%d => %d' % (s, substr, start, pos))
|
| 82 |
|
| 83 | print('---')
|
| 84 |
|
| 85 | for substr in substrs:
|
| 86 | for end in xrange(0, len(s)):
|
| 87 | pos = s.find(substr, 0, end)
|
| 88 | print('%s find %s end:%d => %d' % (s, substr, end, pos))
|
| 89 |
|
| 90 | print('---')
|
| 91 |
|
| 92 | # empty string test
|
| 93 | for start in xrange(0, 3):
|
| 94 | for end in xrange(0, 3):
|
| 95 | pos = s.find('', start, end)
|
| 96 | print('%s find empty [%d, %d) => %d' % (s, start, end, pos))
|
| 97 |
|
| 98 |
|
| 99 | def TestFormat():
|
| 100 | # type: () -> None
|
| 101 |
|
| 102 | banner('TestFormat')
|
| 103 |
|
| 104 | print('foo' + 'bar')
|
| 105 | print('foo' * 3)
|
| 106 | obj = Foo()
|
| 107 | print('foo' + obj.s)
|
| 108 |
|
| 109 | s = 'mystr'
|
| 110 | print('[%s]' % s)
|
| 111 |
|
| 112 | s = 'mystr'
|
| 113 | print('[%s, %s]' % (s, 'abc'))
|
| 114 |
|
| 115 | print('%s: 5%%-100%%' % 'abc')
|
| 116 |
|
| 117 | print('<a href="foo.html">%s</a>' % 'anchor')
|
| 118 |
|
| 119 | print("foo? %d" % ('f' in s))
|
| 120 | print("str? %d" % ('s' in s))
|
| 121 |
|
| 122 | print("int 5d %5d" % 35)
|
| 123 |
|
| 124 | print("'single'")
|
| 125 | print('"double"')
|
| 126 |
|
| 127 | # test escape codes
|
| 128 | print("a\tb\nc\td\n")
|
| 129 |
|
| 130 | x = 'x'
|
| 131 | print("%s\tb\n%s\td\n" % (x, x))
|
| 132 |
|
| 133 | fmt = "%dfoo"
|
| 134 | print(fmt % 10)
|
| 135 |
|
| 136 | fmts = ["foo%d"]
|
| 137 | print(fmts[0] % 10)
|
| 138 |
|
| 139 | print(("foo " + "%s") % "bar")
|
| 140 |
|
| 141 | # NUL bytes
|
| 142 | s = "spam\0%s" % "eggs"
|
| 143 |
|
| 144 | # TODO: There's a bug here -- we get len == 4 in C++, but it should be 9.
|
| 145 | # It's either StrFormat() or the bad JSON literals \u0000
|
| 146 | if 0:
|
| 147 | print("len(s) = %d" % len(s))
|
| 148 | print(s)
|
| 149 |
|
| 150 | s = "foo%s" % "\0bar"
|
| 151 | print("len(s) = %d" % len(s))
|
| 152 |
|
| 153 | print("%o" % 12345)
|
| 154 | print("%17o" % 12345)
|
| 155 | print("%017o" % 12345)
|
| 156 |
|
| 157 | print("%%%d%%%%" % 12345)
|
| 158 |
|
| 159 | print("%r" % "tab\tline\nline\r\n")
|
| 160 |
|
| 161 | s = 'a1b2c3d4e5'
|
| 162 | # Disable step support
|
| 163 | # print(s[0:10:2])
|
| 164 | # print(s[1:10:2])
|
| 165 | print(s.upper())
|
| 166 |
|
| 167 |
|
| 168 | def TestByteOperations():
|
| 169 | # type: () -> None
|
| 170 | banner('TestByteOperations')
|
| 171 |
|
| 172 | s = 'foo' * 10
|
| 173 |
|
| 174 | i = 0
|
| 175 | n = len(s)
|
| 176 | total = 0
|
| 177 | total2 = 0
|
| 178 | while i < n:
|
| 179 | byte = ord(s[i])
|
| 180 | byte2 = mylib.ByteAt(s, i)
|
| 181 |
|
| 182 | total += byte
|
| 183 | total2 += byte2
|
| 184 |
|
| 185 | i += 1
|
| 186 |
|
| 187 | if total != total2:
|
| 188 | raise AssertionError()
|
| 189 |
|
| 190 | print('total = %d' % total)
|
| 191 | print('total2 = %d' % total2)
|
| 192 |
|
| 193 |
|
| 194 | def TestBytes2():
|
| 195 | # type: () -> None
|
| 196 |
|
| 197 | banner('TestBytes2')
|
| 198 |
|
| 199 | b = [] # type: List[int]
|
| 200 | ch = [] # type: List[str]
|
| 201 | for i in xrange(256):
|
| 202 | # Shuffle it a bit, make it a better test
|
| 203 | j = 255 - i
|
| 204 | if j == 2:
|
| 205 | j = 0
|
| 206 |
|
| 207 | b.append(j)
|
| 208 | ch.append(chr(j))
|
| 209 |
|
| 210 | print('len(b) = %d' % len(b))
|
| 211 | print('len(ch) = %d' % len(ch))
|
| 212 |
|
| 213 | all_bytes = ''.join(ch)
|
| 214 |
|
| 215 | b2 = mylib.JoinBytes(b)
|
| 216 | if all_bytes == b2:
|
| 217 | print('EQUAL ==')
|
| 218 | else:
|
| 219 | raise AssertionError('should be equal')
|
| 220 |
|
| 221 | n = len(all_bytes)
|
| 222 | print('len(all_bytes) = %d' % n)
|
| 223 | print('')
|
| 224 | #print('[%s]' % all_bytes)
|
| 225 |
|
| 226 | i = 0
|
| 227 | while i < n:
|
| 228 | byte = mylib.ByteAt(all_bytes, i)
|
| 229 | #log('byte = %d', byte)
|
| 230 |
|
| 231 | if mylib.ByteEquals(byte, '['):
|
| 232 | print('LEFT')
|
| 233 | if mylib.ByteEquals(byte, ']'):
|
| 234 | print('RIGHT')
|
| 235 | if mylib.ByteEquals(byte, '\\'):
|
| 236 | print('BACKSLASH')
|
| 237 |
|
| 238 | # TODO: get rid of JSON crap
|
| 239 | #if mylib.ByteEqualsStr(byte, '\xff'):
|
| 240 | # print('0xff')
|
| 241 |
|
| 242 | if mylib.ByteEquals(byte, chr(255)):
|
| 243 | print('0xff')
|
| 244 |
|
| 245 | if mylib.ByteInSet(byte, 'abcXYZ'):
|
| 246 | print('abcXYZ')
|
| 247 |
|
| 248 | i += 1
|
| 249 |
|
| 250 | print('')
|
| 251 |
|
| 252 |
|
| 253 | def run_tests():
|
| 254 | # type: () -> None
|
| 255 |
|
| 256 | TestFormat()
|
| 257 | TestMethods()
|
| 258 | TestByteOperations()
|
| 259 | TestBytes2()
|
| 260 |
|
| 261 |
|
| 262 | def run_benchmarks():
|
| 263 | # type: () -> None
|
| 264 | pass
|
| 265 |
|
| 266 |
|
| 267 | if __name__ == '__main__':
|
| 268 | if os.getenv('BENCHMARK'):
|
| 269 | log('Benchmarking...')
|
| 270 | run_benchmarks()
|
| 271 | else:
|
| 272 | run_tests()
|