mirror of
https://github.com/Mercury-Language/mercury.git
synced 2026-04-15 17:33:38 +00:00
7350e7f0b6
library/string.m:
Define how string.codepoint_offset counts code units in ill-formed
sequences.
Delete C and C# foreign implementations in favour of the Mercury
implementation that has the intended behaviour.
(The Java implementation uses String.offsetByCodePoints which
also matches our intended behaviour.)
tests/hard_coded/Mmakefile:
tests/hard_coded/string_codepoint_offset_ilseq.exp2:
tests/hard_coded/string_codepoint_offset_ilseq.m:
Add test case.
23 lines
843 B
Plaintext
23 lines
843 B
Plaintext
start counting from offset 0
|
|
string.codepoint_offset(S, 0, 0, 0); Char = a
|
|
string.codepoint_offset(S, 0, 1, 1); Char = 😀
|
|
string.codepoint_offset(S, 0, 2, 3); Char = b
|
|
string.codepoint_offset(S, 0, 3, 4); Char = 0xd83d
|
|
string.codepoint_offset(S, 0, 4, 5); Char = z
|
|
string.codepoint_offset(S, 0, 5, _) failed
|
|
|
|
start counting from offset 1
|
|
string.codepoint_offset(S, 1, 0, 1); Char = 😀
|
|
string.codepoint_offset(S, 1, 1, 3); Char = b
|
|
string.codepoint_offset(S, 1, 2, 4); Char = 0xd83d
|
|
string.codepoint_offset(S, 1, 3, 5); Char = z
|
|
string.codepoint_offset(S, 1, 4, _) failed
|
|
|
|
start counting from offset 2
|
|
string.codepoint_offset(S, 2, 0, 2); Char = 0xde00
|
|
string.codepoint_offset(S, 2, 1, 3); Char = b
|
|
string.codepoint_offset(S, 2, 2, 4); Char = 0xd83d
|
|
string.codepoint_offset(S, 2, 3, 5); Char = z
|
|
string.codepoint_offset(S, 2, 4, _) failed
|
|
|