52acddf36c
Enhance `string_list_split_in_place()` to accept multiple characters as
delimiters instead of a single character.
Instead of using `strchr(2)` to locate the first occurrence of the given
delimiter character, `string_list_split_in_place_multi()` uses
`strcspn(2)` to move past the initial segment of characters comprised of
any characters in the delimiting set.
When only a single delimiting character is provided, `strpbrk(2)` (which
is implemented with `strcspn(2)`) has equivalent performance to
`strchr(2)`. Modern `strcspn(2)` implementations treat an empty
delimiter or the singleton delimiter as a special case and fall back to
calling strchrnul(). Both glibc[1] and musl[2] implement `strcspn(2)`
this way.
This change is one step to removing `strtok(2)` from the tree. Note that
`string_list_split_in_place()` is not a strict replacement for
`strtok()`, since it will happily turn sequential delimiter characters
into empty entries in the resulting string_list. For example:
string_list_split_in_place(&xs, "foo:;:bar:;:baz", ":;", -1)
would yield a string list of:
["foo", "", "", "bar", "", "", "baz"]
Callers that wish to emulate the behavior of strtok(2) more directly
should call `string_list_remove_empty_items()` after splitting.
To avoid regressions for the new multi-character delimter cases, update
t0063 in this patch as well.
[1]: https://sourceware.org/git/?p=glibc.git;a=blob;f=string/strcspn.c;hb=glibc-2.37#l35
[2]: https://git.musl-libc.org/cgit/musl/tree/src/string/strcspn.c?h=v1.2.3#n11
Signed-off-by: Taylor Blau <me@ttaylorr.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
144 lines
3.1 KiB
Bash
Executable File
144 lines
3.1 KiB
Bash
Executable File
#!/bin/sh
|
|
#
|
|
# Copyright (c) 2012 Michael Haggerty
|
|
#
|
|
|
|
test_description='Test string list functionality'
|
|
|
|
TEST_PASSES_SANITIZE_LEAK=true
|
|
. ./test-lib.sh
|
|
|
|
test_split () {
|
|
cat >expected &&
|
|
test_expect_success "split $1 at $2, max $3" "
|
|
test-tool string-list split '$1' '$2' '$3' >actual &&
|
|
test_cmp expected actual &&
|
|
test-tool string-list split_in_place '$1' '$2' '$3' >actual &&
|
|
test_cmp expected actual
|
|
"
|
|
}
|
|
|
|
test_split_in_place() {
|
|
cat >expected &&
|
|
test_expect_success "split (in place) $1 at $2, max $3" "
|
|
test-tool string-list split_in_place '$1' '$2' '$3' >actual &&
|
|
test_cmp expected actual
|
|
"
|
|
}
|
|
|
|
test_split "foo:bar:baz" ":" "-1" <<EOF
|
|
3
|
|
[0]: "foo"
|
|
[1]: "bar"
|
|
[2]: "baz"
|
|
EOF
|
|
|
|
test_split "foo:bar:baz" ":" "0" <<EOF
|
|
1
|
|
[0]: "foo:bar:baz"
|
|
EOF
|
|
|
|
test_split "foo:bar:baz" ":" "1" <<EOF
|
|
2
|
|
[0]: "foo"
|
|
[1]: "bar:baz"
|
|
EOF
|
|
|
|
test_split "foo:bar:baz" ":" "2" <<EOF
|
|
3
|
|
[0]: "foo"
|
|
[1]: "bar"
|
|
[2]: "baz"
|
|
EOF
|
|
|
|
test_split "foo:bar:" ":" "-1" <<EOF
|
|
3
|
|
[0]: "foo"
|
|
[1]: "bar"
|
|
[2]: ""
|
|
EOF
|
|
|
|
test_split "" ":" "-1" <<EOF
|
|
1
|
|
[0]: ""
|
|
EOF
|
|
|
|
test_split ":" ":" "-1" <<EOF
|
|
2
|
|
[0]: ""
|
|
[1]: ""
|
|
EOF
|
|
|
|
test_split_in_place "foo:;:bar:;:baz:;:" ":;" "-1" <<EOF
|
|
10
|
|
[0]: "foo"
|
|
[1]: ""
|
|
[2]: ""
|
|
[3]: "bar"
|
|
[4]: ""
|
|
[5]: ""
|
|
[6]: "baz"
|
|
[7]: ""
|
|
[8]: ""
|
|
[9]: ""
|
|
EOF
|
|
|
|
test_split_in_place "foo:;:bar:;:baz" ":;" "0" <<EOF
|
|
1
|
|
[0]: "foo:;:bar:;:baz"
|
|
EOF
|
|
|
|
test_split_in_place "foo:;:bar:;:baz" ":;" "1" <<EOF
|
|
2
|
|
[0]: "foo"
|
|
[1]: ";:bar:;:baz"
|
|
EOF
|
|
|
|
test_split_in_place "foo:;:bar:;:baz" ":;" "2" <<EOF
|
|
3
|
|
[0]: "foo"
|
|
[1]: ""
|
|
[2]: ":bar:;:baz"
|
|
EOF
|
|
|
|
test_split_in_place "foo:;:bar:;:" ":;" "-1" <<EOF
|
|
7
|
|
[0]: "foo"
|
|
[1]: ""
|
|
[2]: ""
|
|
[3]: "bar"
|
|
[4]: ""
|
|
[5]: ""
|
|
[6]: ""
|
|
EOF
|
|
|
|
test_expect_success "test filter_string_list" '
|
|
test "x-" = "x$(test-tool string-list filter - y)" &&
|
|
test "x-" = "x$(test-tool string-list filter no y)" &&
|
|
test yes = "$(test-tool string-list filter yes y)" &&
|
|
test yes = "$(test-tool string-list filter no:yes y)" &&
|
|
test yes = "$(test-tool string-list filter yes:no y)" &&
|
|
test y1:y2 = "$(test-tool string-list filter y1:y2 y)" &&
|
|
test y2:y1 = "$(test-tool string-list filter y2:y1 y)" &&
|
|
test "x-" = "x$(test-tool string-list filter x1:x2 y)"
|
|
'
|
|
|
|
test_expect_success "test remove_duplicates" '
|
|
test "x-" = "x$(test-tool string-list remove_duplicates -)" &&
|
|
test "x" = "x$(test-tool string-list remove_duplicates "")" &&
|
|
test a = "$(test-tool string-list remove_duplicates a)" &&
|
|
test a = "$(test-tool string-list remove_duplicates a:a)" &&
|
|
test a = "$(test-tool string-list remove_duplicates a:a:a:a:a)" &&
|
|
test a:b = "$(test-tool string-list remove_duplicates a:b)" &&
|
|
test a:b = "$(test-tool string-list remove_duplicates a:a:b)" &&
|
|
test a:b = "$(test-tool string-list remove_duplicates a:b:b)" &&
|
|
test a:b:c = "$(test-tool string-list remove_duplicates a:b:c)" &&
|
|
test a:b:c = "$(test-tool string-list remove_duplicates a:a:b:c)" &&
|
|
test a:b:c = "$(test-tool string-list remove_duplicates a:b:b:c)" &&
|
|
test a:b:c = "$(test-tool string-list remove_duplicates a:b:c:c)" &&
|
|
test a:b:c = "$(test-tool string-list remove_duplicates a:a:b:b:c:c)" &&
|
|
test a:b:c = "$(test-tool string-list remove_duplicates a:a:a:b:b:b:c:c:c)"
|
|
'
|
|
|
|
test_done
|