| 1 |
// SPDX-License-Identifier: MPL-2.0 |
| 2 |
// (c) Hare authors <https://harelang.org> |
| 3 |
|
| 4 |
use bytes; |
| 5 |
|
| 6 |
const whitespace: [_]u8 = [' ', '\n', '\t', '\r']; |
| 7 |
|
| 8 |
// Returns a string (borrowed from given input string) after trimming off of |
| 9 |
// the start of the input string the characters in the given list of runes. If |
| 10 |
// no runes are given, returns the string with leading whitespace stripped off. |
| 11 |
export fn ltrim(input: str, trim: rune...) str = { |
| 12 |
if (len(trim) == 0) { |
| 13 |
let input = toutf8(input); |
| 14 |
return fromutf8_unsafe(bytes::ltrim(input, whitespace...)); |
| 15 |
}; |
| 16 |
let it = iter(input); |
| 17 |
for :outer (let r => next(&it)) { |
| 18 |
for (let tr .. trim) { |
| 19 |
if (r == tr) { |
| 20 |
continue :outer; |
| 21 |
}; |
| 22 |
}; |
| 23 |
prev(&it); |
| 24 |
break; |
| 25 |
}; |
| 26 |
return fromutf8_unsafe(it.dec.src[it.dec.offs..]); |
| 27 |
}; |
| 28 |
|
| 29 |
// Returns a string (borrowed from given input string) after trimming off of |
| 30 |
// the end of the input string the characters in the given list of runes. If no |
| 31 |
// runes are given, returns the string with trailing whitespace stripped off. |
| 32 |
export fn rtrim(input: str, trim: rune...) str = { |
| 33 |
if (len(trim) == 0) { |
| 34 |
let input = toutf8(input); |
| 35 |
return fromutf8_unsafe(bytes::rtrim(input, whitespace...)); |
| 36 |
}; |
| 37 |
let it = riter(input); |
| 38 |
for :outer (let r => next(&it)) { |
| 39 |
for (let tr .. trim) { |
| 40 |
if (r == tr) { |
| 41 |
continue :outer; |
| 42 |
}; |
| 43 |
}; |
| 44 |
prev(&it); |
| 45 |
break; |
| 46 |
}; |
| 47 |
return fromutf8_unsafe(it.dec.src[..it.dec.offs]); |
| 48 |
}; |
| 49 |
|
| 50 |
// Returns a string (borrowed from given input string) after trimming off of |
| 51 |
// the both ends of the input string the characters in the given list of runes. |
| 52 |
// If no runes are given, returns the string with both leading and trailing |
| 53 |
// whitespace stripped off. |
| 54 |
export fn trim(input: str, exclude: rune...) str = |
| 55 |
ltrim(rtrim(input, exclude...), exclude...); |
| 56 |
|
| 57 |
// Returns a string (borrowed from given input string) after trimming off the |
| 58 |
// given prefix. If the input string doesn't have the given prefix, it is |
| 59 |
// returned unmodified. |
| 60 |
export fn trimprefix(input: str, trim: str) str = { |
| 61 |
if (!hasprefix(input, trim)) return input; |
| 62 |
const slice = toutf8(input); |
| 63 |
return fromutf8_unsafe(slice[len(trim)..]); |
| 64 |
}; |
| 65 |
|
| 66 |
// Returns a string (borrowed from given input string) after trimming off the |
| 67 |
// given suffix. If the input string doesn't have the given suffix, it is |
| 68 |
// returned unmodified. |
| 69 |
export fn trimsuffix(input: str, trim: str) str = { |
| 70 |
if (!hassuffix(input, trim)) return input; |
| 71 |
const slice = toutf8(input); |
| 72 |
return fromutf8_unsafe(slice[..len(input) - len(trim)]); |
| 73 |
}; |
| 74 |
|
| 75 |
@test fn trim() void = { |
| 76 |
assert(ltrim("") == ""); |
| 77 |
assert(ltrim(" hi") == "hi"); |
| 78 |
assert(ltrim("\t\r\n hello") == "hello"); |
| 79 |
assert(ltrim("((()(())))())", '(', ')') == ""); |
| 80 |
assert(ltrim("abacadabra", 'a', 'b', 'c', 'd') == "ra"); |
| 81 |
assert(ltrim("𝚊𝚋𝚊𝚌𝚊𝚍𝚊𝚋𝚛𝚊", '𝚊', '𝚋', '𝚌', '𝚍') == "𝚛𝚊"); // '𝚊' = U+1D68A |
| 82 |
|
| 83 |
assert(rtrim("") == ""); |
| 84 |
assert(rtrim("hello ") == "hello"); |
| 85 |
assert(rtrim("hello, world\r\n\r\n") == "hello, world"); |
| 86 |
assert(rtrim("Sentimentalized sensationalism sensationalized sentimentalisms", |
| 87 |
' ', 's', 'i', 'l', 'z', 't', 'm', 'n', 'o', 'e', 'a', 'd') == "S"); |
| 88 |
assert(rtrim("\\/\\/\\\\//\\//\\////\\/\\", '/', '\\') == ""); |
| 89 |
assert(rtrim("yellowwooddoor", 'w', 'd', 'o', 'r') == "yell"); |
| 90 |
|
| 91 |
assert(trim("") == ""); |
| 92 |
assert(trim(" ") == ""); |
| 93 |
assert(trim("mississippi", 'm', 'i', 'p', 's') == ""); |
| 94 |
assert(trim("[[][[[]]][][].[[]][]]][]]]", '[', ']') == "."); |
| 95 |
assert(trim("AAAΑА𝖠AAAA", 'A') == "ΑА𝖠"); |
| 96 |
assert(trim(" চিত্ত যেথা ভয়শূন্য, উচ্চ যেথা শির ") == "চিত্ত যেথা ভয়শূন্য, উচ্চ যেথা শির"); |
| 97 |
assert(trim("𝖺𝖻𝖺𝖼𝖺𝖽𝖺𝖻𝗋𝖺𝖼𝖺𝖽𝖺𝖻𝖼𝖺", '𝖺', '𝖻', '𝖼', '𝖽') == "𝗋"); |
| 98 |
|
| 99 |
assert(trimprefix("", "") == ""); |
| 100 |
assert(trimprefix("", "blablabla") == ""); |
| 101 |
assert(trimprefix("hello, world", "hello") == ", world"); |
| 102 |
assert(trimprefix("blablabla", "bla") == "blabla"); |
| 103 |
|
| 104 |
assert(trimsuffix("", "") == ""); |
| 105 |
assert(trimsuffix("", "blablabla") == ""); |
| 106 |
assert(trimsuffix("hello, world", "world") == "hello, "); |
| 107 |
assert(trimsuffix("blablabla", "bla") == "blabla"); |
| 108 |
}; |