dualfroz
8a9a70d15e
str_length and str_slice used UTF-8 byte offsets, so any input with
multi-byte characters produced wrong results: str_length("cafe") with
an accented final character returned 5 instead of 4, and str_slice(0,
4, ...) on the same string returned an empty string because the byte
index fell inside the encoding of the last character. This also broke
the higher-level helpers built on top of them (str_find, str_contains,
str_replace).
Count characters with chars().count() and index str_slice by character.
Out-of-range slices still return an empty string, so behavior for ASCII
input is unchanged.
37 lines
1.1 KiB
Plaintext
37 lines
1.1 KiB
Plaintext
assert_eq(str_length(""), 0)
|
|
assert_eq(str_length("foo"), 3)
|
|
|
|
# Length and slicing operate on Unicode code points, not on UTF-8 bytes
|
|
assert_eq(str_length("café"), 4)
|
|
assert_eq(str_length("❤"), 1)
|
|
|
|
assert_eq(str_slice(0, 5, "hello world"), "hello")
|
|
assert_eq(str_slice(6, 11, "hello world"), "world")
|
|
assert_eq(str_slice(0, 0, "hello world"), "")
|
|
assert_eq(str_slice(0, 100, "hello world"), "")
|
|
|
|
assert_eq(str_slice(0, 4, "café"), "café")
|
|
assert_eq(str_slice(3, 4, "café"), "é")
|
|
assert_eq(str_slice(0, 3, "café"), "caf")
|
|
|
|
assert_eq(chr(65), "A")
|
|
assert_eq(chr(97), "a")
|
|
assert_eq(chr(0x2764), "❤")
|
|
|
|
assert_eq(ord("A"), 65)
|
|
assert_eq(ord("a"), 97)
|
|
assert_eq(ord("❤"), 0x2764)
|
|
|
|
assert_eq(str_append("foo", "bar"), "foobar")
|
|
assert_eq(str_prepend("bar", "foo"), "foobar")
|
|
|
|
assert(str_contains("hello", "hello world"))
|
|
assert(str_contains("world", "hello world"))
|
|
assert_eq(str_contains("HELLO", "hello world"), false)
|
|
|
|
assert_eq(str_replace("hello", "HEY", "hello world"), "HEY world")
|
|
assert_eq(str_replace("x", "yY", "xxx"), "yYyYyY")
|
|
assert_eq(str_replace(" ", " ", "a b"), "a b")
|
|
|
|
assert_eq(str_repeat(3, "xy"), "xyxyxy")
|