mirror of
https://github.com/stedolan/jq.git
synced 2024-05-11 05:55:39 +00:00
83f375cc83
The primary purpose of this commit is to rectify most problems with `gsub` (and also `sub` with the `g` option), in particular fix #1425 ('\b'), fix #2354 (lookahead), and fix #2532 (regex == `"^(?!cd ).*$|^cd "`). This commit also partly resolves #2148 and resolves #1206 in that `gsub` no longer loops infinitely; however, because the new `gsub` depends critically on `match/2`, the behavior when regex == `""` is sometimes non-standard. The documentation has been updated to reflect the fact that `sub` and `gsub` are intended to be regular in the second argument. Also, `_nwise/1` has been tweaked to take advantage of TCO.
164 lines
3.4 KiB
Plaintext
164 lines
3.4 KiB
Plaintext
# match builtin
|
||
[match("( )*"; "g")]
|
||
"abc"
|
||
[{"offset":0, "length":0, "string":"", "captures":[]},{"offset":1, "length":0, "string":"", "captures":[]},{"offset":2, "length":0, "string":"", "captures":[]}]
|
||
|
||
[match("( )*"; "gn")]
|
||
"abc"
|
||
[]
|
||
|
||
[match("a"; "gi")]
|
||
"āáàä"
|
||
[]
|
||
|
||
[match(["(bar)"])]
|
||
"foo bar"
|
||
[{"offset": 4, "length": 3, "string": "bar", "captures":[{"offset": 4, "length": 3, "string": "bar", "name": null}]}]
|
||
|
||
# offsets account for combining codepoints and multi-byte UTF-8
|
||
[match("bar")]
|
||
"ā bar with a combining codepoint U+0304"
|
||
[{"offset": 3, "length": 3, "string": "bar", "captures":[]}]
|
||
|
||
# matches with combining codepoints still count them in their length
|
||
[match("bār")]
|
||
"a bār"
|
||
[{"offset": 2, "length": 4, "string": "bār", "captures":[]}]
|
||
|
||
[match(".+?\\b")]
|
||
"ā two-codepoint grapheme"
|
||
[{"offset": 0, "length": 2, "string": "ā", "captures":[]}]
|
||
|
||
[match(["foo (?<bar123>bar)? foo", "ig"])]
|
||
"foo bar foo foo foo"
|
||
[{"offset": 0, "length": 11, "string": "foo bar foo", "captures":[{"offset": 4, "length": 3, "string": "bar", "name": "bar123"}]},{"offset":12, "length": 8, "string": "foo foo", "captures":[{"offset": -1, "length": 0, "string": null, "name": "bar123"}]}]
|
||
|
||
#test builtin
|
||
[test("( )*"; "gn")]
|
||
"abc"
|
||
[false]
|
||
|
||
[test("ā")]
|
||
"ā"
|
||
[true]
|
||
|
||
capture("(?<a>[a-z]+)-(?<n>[0-9]+)")
|
||
"xyzzy-14"
|
||
{"a":"xyzzy","n":"14"}
|
||
|
||
|
||
# jq-coded utilities built on match:
|
||
#
|
||
# The second element in these tests' inputs tests the case where the
|
||
# fromstring matches both the head and tail of the string
|
||
[.[] | sub(", "; ":")]
|
||
["a,b, c, d, e,f", ", a,b, c, d, e,f, "]
|
||
["a,b:c, d, e,f",":a,b, c, d, e,f, "]
|
||
|
||
sub("^(?<head>.)"; "Head=\(.head) Tail=")
|
||
"abcdef"
|
||
"Head=a Tail=bcdef"
|
||
|
||
[.[] | gsub(", "; ":")]
|
||
["a,b, c, d, e,f",", a,b, c, d, e,f, "]
|
||
["a,b:c:d:e,f",":a,b:c:d:e,f:"]
|
||
|
||
gsub("(?<d>\\d)"; ":\(.d);")
|
||
"a1b2"
|
||
"a:1;b:2;"
|
||
|
||
gsub("a";"b")
|
||
"aaaaa"
|
||
"bbbbb"
|
||
|
||
gsub( "(.*)"; ""; "x")
|
||
""
|
||
""
|
||
|
||
gsub( ""; "a"; "g")
|
||
""
|
||
"a"
|
||
|
||
gsub( "^"; ""; "g")
|
||
"a"
|
||
"a"
|
||
|
||
|
||
# The following is a regression test and should not be construed as a requirement other than that execution should terminate:
|
||
gsub( ""; "a"; "g")
|
||
"a"
|
||
"aa"
|
||
|
||
gsub( "$"; "a"; "g")
|
||
"a"
|
||
"aa"
|
||
|
||
gsub( "^"; "a")
|
||
""
|
||
"a"
|
||
|
||
gsub("(?=u)"; "u")
|
||
"qux"
|
||
"quux"
|
||
|
||
gsub("^.*a"; "b")
|
||
"aaa"
|
||
"b"
|
||
|
||
gsub("^.*?a"; "b")
|
||
"aaa"
|
||
"baa"
|
||
|
||
# The following is for regression testing and should not be construed as a requirement:
|
||
[gsub("a"; "b", "c")]
|
||
"a"
|
||
["b","c"]
|
||
|
||
[.[] | scan(", ")]
|
||
["a,b, c, d, e,f",", a,b, c, d, e,f, "]
|
||
[", ",", ",", ",", ",", ",", ",", ",", "]
|
||
|
||
[.[]|[[sub(", *";":")], [gsub(", *";":")], [scan(", *")]]]
|
||
["a,b, c, d, e,f",", a,b, c, d, e,f, "]
|
||
[[["a:b, c, d, e,f"],["a:b:c:d:e:f"],[",",", ",", ",", ",","]],[[":a,b, c, d, e,f, "],[":a:b:c:d:e:f:"],[", ",",",", ",", ",", ",",",", "]]]
|
||
|
||
[.[]|[[sub(", +";":")], [gsub(", +";":")], [scan(", +")]]]
|
||
["a,b, c, d, e,f",", a,b, c, d, e,f, "]
|
||
[[["a,b:c, d, e,f"],["a,b:c:d:e,f"],[", ",", ",", "]],[[":a,b, c, d, e,f, "],[":a,b:c:d:e,f:"],[", ",", ",", ",", ",", "]]]
|
||
|
||
# reference to named captures
|
||
gsub("(?<x>.)[^a]*"; "+\(.x)-")
|
||
"Abcabc"
|
||
"+A-+a-"
|
||
|
||
gsub("(?<x>.)(?<y>[0-9])"; "\(.x|ascii_downcase)\(.y)")
|
||
"A1 B2 CD"
|
||
"a1 b2 CD"
|
||
|
||
gsub("\\b(?<x>.)"; "\(.x|ascii_downcase)")
|
||
"ABC DEF"
|
||
"aBC dEF"
|
||
|
||
# utf-8
|
||
sub("(?<x>.)"; "\(.x)!")
|
||
"’"
|
||
"’!"
|
||
|
||
[sub("a"; "b", "c")]
|
||
"a"
|
||
["b","c"]
|
||
|
||
[sub("(?<a>.)"; "\(.a|ascii_upcase)", "\(.a|ascii_downcase)", "c")]
|
||
"aB"
|
||
["AB","aB","cB"]
|
||
|
||
[gsub("(?<a>.)"; "\(.a|ascii_upcase)", "\(.a|ascii_downcase)", "c")]
|
||
"aB"
|
||
["AB","ab","cc"]
|
||
|
||
# splits and _nwise
|
||
[splits("")]
|
||
"ab"
|
||
["","a","b"]
|
||
|