| 1 | ## compare_shells: dash bash mksh zsh
|
| 2 | ## oils_failures_allowed: 1
|
| 3 |
|
| 4 | # Test the length oeprator, which dash supports. Dash doesn't support most
|
| 5 | # other ops.
|
| 6 |
|
| 7 | #### String length
|
| 8 | v=foo
|
| 9 | echo ${#v}
|
| 10 | ## stdout: 3
|
| 11 |
|
| 12 | #### Unicode string length (UTF-8)
|
| 13 | v=$'_\u03bc_'
|
| 14 | echo ${#v}
|
| 15 | ## stdout: 3
|
| 16 | ## N-I dash stdout: 9
|
| 17 | ## N-I mksh stdout: 4
|
| 18 |
|
| 19 | #### Unicode string length (spec/testdata/utf8-chars.txt)
|
| 20 | v=$(cat $REPO_ROOT/spec/testdata/utf8-chars.txt)
|
| 21 | echo ${#v}
|
| 22 | ## stdout: 7
|
| 23 | ## N-I dash stdout: 13
|
| 24 | ## N-I mksh stdout: 13
|
| 25 |
|
| 26 | #### String length with incomplete utf-8
|
| 27 | for num_bytes in 0 1 2 3 4 5 6 7 8 9 10 11 12 13; do
|
| 28 | s=$(head -c $num_bytes $REPO_ROOT/spec/testdata/utf8-chars.txt)
|
| 29 | echo ${#s}
|
| 30 | done 2> $TMP/err.txt
|
| 31 |
|
| 32 | grep 'warning:' $TMP/err.txt
|
| 33 | true # exit 0
|
| 34 |
|
| 35 | ## STDOUT:
|
| 36 | 0
|
| 37 | 1
|
| 38 | 2
|
| 39 | -1
|
| 40 | 3
|
| 41 | 4
|
| 42 | -1
|
| 43 | -1
|
| 44 | 5
|
| 45 | 6
|
| 46 | -1
|
| 47 | -1
|
| 48 | -1
|
| 49 | 7
|
| 50 | [ stdin ]:3: warning: UTF-8 decode: Truncated bytes at offset 2 in string of 3 bytes
|
| 51 | [ stdin ]:3: warning: UTF-8 decode: Truncated bytes at offset 5 in string of 6 bytes
|
| 52 | [ stdin ]:3: warning: UTF-8 decode: Truncated bytes at offset 5 in string of 7 bytes
|
| 53 | [ stdin ]:3: warning: UTF-8 decode: Truncated bytes at offset 9 in string of 10 bytes
|
| 54 | [ stdin ]:3: warning: UTF-8 decode: Truncated bytes at offset 9 in string of 11 bytes
|
| 55 | [ stdin ]:3: warning: UTF-8 decode: Truncated bytes at offset 9 in string of 12 bytes
|
| 56 | ## END
|
| 57 | # zsh behavior actually matches bash!
|
| 58 | ## BUG bash/zsh stderr-json: ""
|
| 59 | ## BUG bash/zsh STDOUT:
|
| 60 | 0
|
| 61 | 1
|
| 62 | 2
|
| 63 | 3
|
| 64 | 3
|
| 65 | 4
|
| 66 | 5
|
| 67 | 6
|
| 68 | 5
|
| 69 | 6
|
| 70 | 7
|
| 71 | 8
|
| 72 | 9
|
| 73 | 7
|
| 74 | ## END
|
| 75 | ## N-I dash/mksh stderr-json: ""
|
| 76 | ## N-I dash/mksh STDOUT:
|
| 77 | 0
|
| 78 | 1
|
| 79 | 2
|
| 80 | 3
|
| 81 | 4
|
| 82 | 5
|
| 83 | 6
|
| 84 | 7
|
| 85 | 8
|
| 86 | 9
|
| 87 | 10
|
| 88 | 11
|
| 89 | 12
|
| 90 | 13
|
| 91 | ## END
|
| 92 |
|
| 93 | #### String length with invalid utf-8 continuation bytes
|
| 94 | for num_bytes in 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14; do
|
| 95 | s=$(head -c $num_bytes $REPO_ROOT/spec/testdata/utf8-chars.txt)$(echo -e "\xFF")
|
| 96 | echo ${#s}
|
| 97 | done 2> $TMP/err.txt
|
| 98 |
|
| 99 | grep 'warning:' $TMP/err.txt
|
| 100 | true
|
| 101 |
|
| 102 | ## STDOUT:
|
| 103 | -1
|
| 104 | -1
|
| 105 | -1
|
| 106 | -1
|
| 107 | -1
|
| 108 | -1
|
| 109 | -1
|
| 110 | -1
|
| 111 | -1
|
| 112 | -1
|
| 113 | -1
|
| 114 | -1
|
| 115 | -1
|
| 116 | -1
|
| 117 | -1
|
| 118 | [ stdin ]:3: warning: UTF-8 decode: Bad encoding at offset 0 in string of 1 bytes
|
| 119 | [ stdin ]:3: warning: UTF-8 decode: Bad encoding at offset 1 in string of 2 bytes
|
| 120 | [ stdin ]:3: warning: UTF-8 decode: Bad encoding at offset 2 in string of 3 bytes
|
| 121 | [ stdin ]:3: warning: UTF-8 decode: Bad encoding at offset 2 in string of 4 bytes
|
| 122 | [ stdin ]:3: warning: UTF-8 decode: Bad encoding at offset 4 in string of 5 bytes
|
| 123 | [ stdin ]:3: warning: UTF-8 decode: Bad encoding at offset 5 in string of 6 bytes
|
| 124 | [ stdin ]:3: warning: UTF-8 decode: Bad encoding at offset 5 in string of 7 bytes
|
| 125 | [ stdin ]:3: warning: UTF-8 decode: Bad encoding at offset 5 in string of 8 bytes
|
| 126 | [ stdin ]:3: warning: UTF-8 decode: Bad encoding at offset 8 in string of 9 bytes
|
| 127 | [ stdin ]:3: warning: UTF-8 decode: Bad encoding at offset 9 in string of 10 bytes
|
| 128 | [ stdin ]:3: warning: UTF-8 decode: Bad encoding at offset 9 in string of 11 bytes
|
| 129 | [ stdin ]:3: warning: UTF-8 decode: Bad encoding at offset 9 in string of 12 bytes
|
| 130 | [ stdin ]:3: warning: UTF-8 decode: Bad encoding at offset 9 in string of 13 bytes
|
| 131 | [ stdin ]:3: warning: UTF-8 decode: Bad encoding at offset 13 in string of 14 bytes
|
| 132 | [ stdin ]:3: warning: UTF-8 decode: Bad encoding at offset 13 in string of 14 bytes
|
| 133 | ## END
|
| 134 | ## BUG bash/zsh stderr-json: ""
|
| 135 | ## BUG bash/zsh STDOUT:
|
| 136 | 1
|
| 137 | 2
|
| 138 | 3
|
| 139 | 4
|
| 140 | 4
|
| 141 | 5
|
| 142 | 6
|
| 143 | 7
|
| 144 | 6
|
| 145 | 7
|
| 146 | 8
|
| 147 | 9
|
| 148 | 10
|
| 149 | 8
|
| 150 | 8
|
| 151 | ## N-I dash stderr-json: ""
|
| 152 | ## N-I dash STDOUT:
|
| 153 | 7
|
| 154 | 8
|
| 155 | 9
|
| 156 | 10
|
| 157 | 11
|
| 158 | 12
|
| 159 | 13
|
| 160 | 14
|
| 161 | 15
|
| 162 | 16
|
| 163 | 17
|
| 164 | 18
|
| 165 | 19
|
| 166 | 20
|
| 167 | 20
|
| 168 | ## END
|
| 169 | ## N-I mksh stderr-json: ""
|
| 170 | ## N-I mksh STDOUT:
|
| 171 | 1
|
| 172 | 2
|
| 173 | 3
|
| 174 | 4
|
| 175 | 5
|
| 176 | 6
|
| 177 | 7
|
| 178 | 8
|
| 179 | 9
|
| 180 | 10
|
| 181 | 11
|
| 182 | 12
|
| 183 | 13
|
| 184 | 14
|
| 185 | 14
|
| 186 | ## END
|
| 187 |
|
| 188 | #### Length of undefined variable
|
| 189 | echo ${#undef}
|
| 190 | ## stdout: 0
|
| 191 |
|
| 192 | #### Length of undefined variable with nounset
|
| 193 | set -o nounset
|
| 194 | echo ${#undef}
|
| 195 | ## status: 1
|
| 196 | ## OK dash status: 2
|
| 197 |
|
| 198 | #### Length operator can't be followed by test operator
|
| 199 | echo ${#x-default}
|
| 200 |
|
| 201 | x=''
|
| 202 | echo ${#x-default}
|
| 203 |
|
| 204 | x='foo'
|
| 205 | echo ${#x-default}
|
| 206 |
|
| 207 | ## status: 2
|
| 208 | ## OK bash/mksh status: 1
|
| 209 | ## stdout-json: ""
|
| 210 | ## BUG zsh status: 0
|
| 211 | ## BUG zsh STDOUT:
|
| 212 | 7
|
| 213 | 0
|
| 214 | 3
|
| 215 | ## END
|
| 216 | ## BUG dash status: 0
|
| 217 | ## BUG dash STDOUT:
|
| 218 | 0
|
| 219 | 0
|
| 220 | 3
|
| 221 | ## END
|
| 222 |
|
| 223 | #### ${#s} respects LC_ALL - length in bytes or code points
|
| 224 | case $SH in dash) exit ;; esac
|
| 225 |
|
| 226 | # This test case is sorta "infected" because spec-common.sh sets LC_ALL=C.UTF-8
|
| 227 | #
|
| 228 | # For some reason mksh behaves differently
|
| 229 | #
|
| 230 | # See demo/04-unicode.sh
|
| 231 |
|
| 232 | #echo $LC_ALL
|
| 233 | unset LC_ALL
|
| 234 |
|
| 235 | # note: this may depend on the CI machine config
|
| 236 | LANG=en_US.UTF-8
|
| 237 |
|
| 238 | #LC_ALL=en_US.UTF-8
|
| 239 |
|
| 240 | for s in $'\u03bc' $'\U00010000'; do
|
| 241 | LC_ALL=
|
| 242 | echo "len=${#s}"
|
| 243 |
|
| 244 | LC_ALL=C
|
| 245 | echo "len=${#s}"
|
| 246 |
|
| 247 | echo
|
| 248 | done
|
| 249 |
|
| 250 | ## STDOUT:
|
| 251 | len=1
|
| 252 | len=2
|
| 253 |
|
| 254 | len=1
|
| 255 | len=4
|
| 256 |
|
| 257 | ## END
|
| 258 |
|
| 259 | ## N-I dash STDOUT:
|
| 260 | ## END
|
| 261 |
|
| 262 | ## BUG mksh STDOUT:
|
| 263 | len=2
|
| 264 | len=2
|
| 265 |
|
| 266 | len=3
|
| 267 | len=3
|
| 268 |
|
| 269 | ## END
|