Non-matched optional capture group should be null and offset -1

Fixes #3093
jqlang · Jan 26, 2025 · 55ff8b8 · 55ff8b8
1 parent 31dac28
commit 55ff8b8
Show file tree

Hide file tree

Showing 2 changed files with 34 additions and 3 deletions.
diff --git a/src/builtin.c b/src/builtin.c
@@ -1006,8 +1006,13 @@ static jv f_match(jq_state *jq, jv input, jv regex, jv modifiers, jv testmode) {
         jv captures = jv_array();
         for (int i = 1; i < region->num_regs; ++i) {
           jv cap = jv_object();
-          cap = jv_object_set(cap, jv_string("offset"), jv_number(idx));
-          cap = jv_object_set(cap, jv_string("string"), jv_string(""));
+          if (region->beg[i] == -1) {
+            cap = jv_object_set(jv_object(), jv_string("offset"), jv_number(-1));
+            cap = jv_object_set(cap, jv_string("string"), jv_null());
+          } else {
+            cap = jv_object_set(cap, jv_string("offset"), jv_number(idx));
+            cap = jv_object_set(cap, jv_string("string"), jv_string(""));
+          }
           cap = jv_object_set(cap, jv_string("length"), jv_number(0));
           cap = jv_object_set(cap, jv_string("name"), jv_null());
           captures = jv_array_append(captures, cap);

diff --git a/tests/onig.test b/tests/onig.test
@@ -1,7 +1,7 @@
 # match builtin
 [match("( )*"; "g")]
 "abc"
-[{"offset":0,"length":0,"string":"","captures":[{"offset":0,"string":"","length":0,"name":null}]},{"offset":1,"length":0,"string":"","captures":[{"offset":1,"string":"","length":0,"name":null}]},{"offset":2,"length":0,"string":"","captures":[{"offset":2,"string":"","length":0,"name":null}]},{"offset":3,"length":0,"string":"","captures":[{"offset":3,"string":"","length":0,"name":null}]}]
+[{"offset":0,"length":0,"string":"","captures":[{"offset":-1,"string":null,"length":0,"name":null}]},{"offset":1,"length":0,"string":"","captures":[{"offset":-1,"string":null,"length":0,"name":null}]},{"offset":2,"length":0,"string":"","captures":[{"offset":-1,"string":null,"length":0,"name":null}]},{"offset":3,"length":0,"string":"","captures":[{"offset":-1,"string":null,"length":0,"name":null}]}]
 
 [match("( )*"; "gn")]
 "abc"
@@ -37,6 +37,32 @@
 "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"}]}]
 
+# non-matched optional group
+"a","b","c" | capture("(?<x>a)?b?")
+null
+{"x":"a"}
+{"x":null}
+{"x":null}
+
+"a","b","c" | match("(?<x>a)?b?")
+null
+{"offset":0,"length":1,"string":"a","captures":[{"offset":0,"length":1,"string":"a","name":"x"}]}
+{"offset":0,"length":1,"string":"b","captures":[{"offset":-1,"string":null,"length":0,"name":"x"}]}
+{"offset":0,"length":0,"string":"","captures":[{"offset":-1,"string":null,"length":0,"name":"x"}]}
+
+# same as above but allow empty match for group
+"a","b","c" | capture("(?<x>a?)?b?")
+null
+{"x":"a"}
+{"x":""}
+{"x":""}
+
+"a","b","c" | match("(?<x>a?)?b?")
+null
+{"offset":0,"length":1,"string":"a","captures":[{"offset":0,"length":1,"string":"a","name":"x"}]}
+{"offset":0,"length":1,"string":"b","captures":[{"offset":0,"string":"","length":0,"name":"x"}]}
+{"offset":0,"length":0,"string":"","captures":[{"offset":0,"string":"","length":0,"name":"x"}]}
+
 #test builtin
 [test("( )*"; "gn")]
 "abc"