Re: [tarantool-patches] Re: [PATCH v3 2/7] lib: introduce a new json_path_multikey_offset helper

[Kirill Shcherbatov <kshcherbatov@tarantool.org>]

> IMO returning path_len if no multikey token is found would be more
> common (think of STL methods, which return end() iterator if not found).
> Doesn't really matter though.
> 
> Other than that looks good to me.

I don't mind. Updated version is on the branch.

==================================================

Introduced a new procedure json_path_multikey_offset. This helper
scans the JSON path string and returns the offset of the first character
[*] (the array index placeholder).

We need this function in the scope of the multikey index patchset to
extract the number of keys to be inserted into the index
using JSON subpath that has json_path_multikey_offset() length.

Needed for #1257
---
 src/lib/json/json.c   | 18 ++++++++++++++++++
 src/lib/json/json.h   | 10 ++++++++++
 test/unit/json.c      | 32 +++++++++++++++++++++++++++++++-
 test/unit/json.result | 12 +++++++++++-
 4 files changed, 70 insertions(+), 2 deletions(-)

diff --git a/src/lib/json/json.c b/src/lib/json/json.c
index 854158f63..7ef511d4e 100644
--- a/src/lib/json/json.c
+++ b/src/lib/json/json.c
@@ -321,6 +321,24 @@ json_path_validate(const char *path, int path_len, int index_base)
 	return rc;
 }
 
+int
+json_path_multikey_offset(const char *path, int path_len, int index_base)
+{
+	struct json_lexer lexer;
+	json_lexer_create(&lexer, path, path_len, index_base);
+	struct json_token token;
+	int rc, last_lexer_offset = 0;
+	while ((rc = json_lexer_next_token(&lexer, &token)) == 0) {
+		if (token.type == JSON_TOKEN_ANY)
+			return last_lexer_offset;
+		else if (token.type == JSON_TOKEN_END)
+			break;
+		last_lexer_offset = lexer.offset;
+	}
+	assert(rc == 0);
+	return path_len;
+}
+
 /**
  * An snprint-style helper to print an individual token key.
  */
diff --git a/src/lib/json/json.h b/src/lib/json/json.h
index c1de3e579..d66a9c7a4 100644
--- a/src/lib/json/json.h
+++ b/src/lib/json/json.h
@@ -259,6 +259,16 @@ json_path_cmp(const char *a, int a_len, const char *b, int b_len,
 int
 json_path_validate(const char *path, int path_len, int index_base);
 
+/**
+ * Scan the JSON path string and return the offset of the first
+ * character [*] (the array index placeholder).
+ * - if [*] is not found, path_len is returned.
+ * - specified JSON path must be valid
+ *   (may be tested with json_path_validate).
+ */
+int
+json_path_multikey_offset(const char *path, int path_len, int index_base);
+
 /**
  * Test if a given JSON token is a JSON tree leaf, i.e.
  * has no child nodes.
diff --git a/test/unit/json.c b/test/unit/json.c
index fd320c9eb..2b7236ea8 100644
--- a/test/unit/json.c
+++ b/test/unit/json.c
@@ -555,17 +555,47 @@ test_path_snprint()
 	footer();
 }
 
+void
+test_path_multikey()
+{
+	static struct {
+		const char *str;
+		int rc;
+	} test_cases[] = {
+		{"", 0},
+		{"[1]Data[1]extra[1]", 18},
+		{"[*]Data[1]extra[1]", 0},
+		{"[*]Data[*]extra[1]", 0},
+		{"[1]Data[*]extra[1]", 7},
+		{"[1]Data[1]extra[*]", 15},
+	};
+
+	header();
+	plan(lengthof(test_cases));
+	for (unsigned i = 0; i < lengthof(test_cases); i++) {
+		int rc = json_path_multikey_offset(test_cases[i].str,
+						   strlen(test_cases[i].str),
+						   INDEX_BASE);
+		is(rc, test_cases[i].rc, "Test json_path_multikey_offset with "
+		   "%s: have %d expected %d", test_cases[i].str, rc,
+		   test_cases[i].rc);
+	}
+	check_plan();
+	footer();
+}
+
 int
 main()
 {
 	header();
-	plan(5);
+	plan(6);
 
 	test_basic();
 	test_errors();
 	test_tree();
 	test_path_cmp();
 	test_path_snprint();
+	test_path_multikey();
 
 	int rc = check_plan();
 	footer();
diff --git a/test/unit/json.result b/test/unit/json.result
index 3a15e84bb..1c3e7f7d2 100644
--- a/test/unit/json.result
+++ b/test/unit/json.result
@@ -1,5 +1,5 @@
 	*** main ***
-1..5
+1..6
 	*** test_basic ***
     1..71
     ok 1 - parse <[1]>
@@ -194,4 +194,14 @@ ok 4 - subtests
     ok 9 - 0-byte buffer - retval
 ok 5 - subtests
 	*** test_path_snprint: done ***
+	*** test_path_multikey ***
+    1..6
+    ok 1 - Test json_path_multikey_offset with : have 0 expected 0
+    ok 2 - Test json_path_multikey_offset with [1]Data[1]extra[1]: have 18 expected 18
+    ok 3 - Test json_path_multikey_offset with [*]Data[1]extra[1]: have 0 expected 0
+    ok 4 - Test json_path_multikey_offset with [*]Data[*]extra[1]: have 0 expected 0
+    ok 5 - Test json_path_multikey_offset with [1]Data[*]extra[1]: have 7 expected 7
+    ok 6 - Test json_path_multikey_offset with [1]Data[1]extra[*]: have 15 expected 15
+ok 6 - subtests
+	*** test_path_multikey: done ***
 	*** main: done ***
-- 
2.21.0