Tarantool development patches archive
 help / color / mirror / Atom feed
From: Mergen Imeev via Tarantool-patches <tarantool-patches@dev.tarantool.org>
To: Vladislav Shpilevoy <v.shpilevoy@tarantool.org>
Cc: tarantool-patches@dev.tarantool.org
Subject: Re: [Tarantool-patches] [PATCH v1 14/21] sql: refactor UNICODE() function
Date: Mon, 25 Oct 2021 11:40:47 +0300
Message-ID: <20211025084047.GJ36295@tarantool.org> (raw)
In-Reply-To: <77fcefe4-cde9-ed81-4764-c539fe51ea23@tarantool.org>

Thank you for the review! My answer, diff and new patch below. Also, I added
description to the function.

On Fri, Oct 15, 2021 at 12:44:37AM +0200, Vladislav Shpilevoy wrote:
> Thanks for the patch!
> 
> > diff --git a/src/box/sql/func.c b/src/box/sql/func.c
> > index fb7fd772e..5e12ef729 100644
> > --- a/src/box/sql/func.c
> > +++ b/src/box/sql/func.c
> > @@ -1007,6 +1007,19 @@ func_version(struct sql_context *ctx, int argc, struct Mem *argv)
> >  	return mem_set_str0_static(ctx->pOut, (char *)tarantool_version());
> >  }
> >  
> > +/** Implementation of the UNICODE() function. */
> > +static void
> > +func_unicode(struct sql_context *ctx, int argc, struct Mem *argv)
> > +{
> > +	assert(argc == 1);
> > +	(void)argc;
> > +	if (mem_is_null(&argv[0]))
> > +		return;
> > +	assert(mem_is_str(&argv[0]));
> > +	const char *str = tt_cstr(argv[0].z, argv[0].n);
> > +	mem_set_uint(ctx->pOut, sqlUtf8Read((const unsigned char **)&str));
> 
> You can dodge the copying. See utf8_next() in utf8.c:
> 
> 	UChar32 c;
> 	U8_NEXT(str, pos, len, c);
Thanks, fixed.


Diff:

diff --git a/src/box/sql/func.c b/src/box/sql/func.c
index ebc38751e..6d80559d5 100644
--- a/src/box/sql/func.c
+++ b/src/box/sql/func.c
@@ -1016,17 +1016,28 @@ func_version(struct sql_context *ctx, int argc, struct Mem *argv)
 	return mem_set_str0_static(ctx->pOut, (char *)tarantool_version());
 }
 
-/** Implementation of the UNICODE() function. */
+/**
+ * Implementation of the UNICODE() function.
+ *
+ * Return the Unicode code point value for the first character of the input
+ * string.
+ */
 static void
 func_unicode(struct sql_context *ctx, int argc, struct Mem *argv)
 {
 	assert(argc == 1);
 	(void)argc;
-	if (mem_is_null(&argv[0]))
+	struct Mem *arg = &argv[0];
+	if (mem_is_null(arg))
 		return;
-	assert(mem_is_str(&argv[0]));
-	const char *str = tt_cstr(argv[0].z, argv[0].n);
-	mem_set_uint(ctx->pOut, sqlUtf8Read((const unsigned char **)&str));
+	assert(mem_is_str(arg));
+	if (arg->n == 0)
+		return mem_set_uint(ctx->pOut, 0);
+	int pos = 0;
+	UChar32 c;
+	U8_NEXT(arg->z, pos, arg->n, c);
+	(void)pos;
+	mem_set_uint(ctx->pOut, (uint64_t)c);
 }
 
 static const unsigned char *


New patch:

commit 6346c542b8c81814753a1853d7ae347222af0f23
Author: Mergen Imeev <imeevma@gmail.com>
Date:   Thu Oct 7 13:43:38 2021 +0300

    sql: refactor UNICODE() function
    
    Part of #4145

diff --git a/src/box/sql/func.c b/src/box/sql/func.c
index 3afc8ec7f..6d80559d5 100644
--- a/src/box/sql/func.c
+++ b/src/box/sql/func.c
@@ -1016,6 +1016,30 @@ func_version(struct sql_context *ctx, int argc, struct Mem *argv)
 	return mem_set_str0_static(ctx->pOut, (char *)tarantool_version());
 }
 
+/**
+ * Implementation of the UNICODE() function.
+ *
+ * Return the Unicode code point value for the first character of the input
+ * string.
+ */
+static void
+func_unicode(struct sql_context *ctx, int argc, struct Mem *argv)
+{
+	assert(argc == 1);
+	(void)argc;
+	struct Mem *arg = &argv[0];
+	if (mem_is_null(arg))
+		return;
+	assert(mem_is_str(arg));
+	if (arg->n == 0)
+		return mem_set_uint(ctx->pOut, 0);
+	int pos = 0;
+	UChar32 c;
+	U8_NEXT(arg->z, pos, arg->n, c);
+	(void)pos;
+	mem_set_uint(ctx->pOut, (uint64_t)c);
+}
+
 static const unsigned char *
 mem_as_ustr(struct Mem *mem)
 {
@@ -1437,19 +1461,6 @@ quoteFunc(struct sql_context *context, int argc, struct Mem *argv)
 	}
 }
 
-/*
- * The unicode() function.  Return the integer unicode code-point value
- * for the first character of the input string.
- */
-static void
-unicodeFunc(struct sql_context *context, int argc, struct Mem *argv)
-{
-	const unsigned char *z = mem_as_ustr(&argv[0]);
-	(void)argc;
-	if (z && z[0])
-		sql_result_uint(context, sqlUtf8Read(&z));
-}
-
 /*
  * The replace() function.  Three arguments are all strings: call
  * them A, B, and C. The result is also a string which is derived
@@ -1883,7 +1894,7 @@ static struct sql_func_definition definitions[] = {
 	 FIELD_TYPE_VARBINARY, func_trim_bin, NULL},
 
 	{"TYPEOF", 1, {FIELD_TYPE_ANY}, FIELD_TYPE_STRING, func_typeof, NULL},
-	{"UNICODE", 1, {FIELD_TYPE_STRING}, FIELD_TYPE_INTEGER, unicodeFunc,
+	{"UNICODE", 1, {FIELD_TYPE_STRING}, FIELD_TYPE_INTEGER, func_unicode,
 	 NULL},
 	{"UNLIKELY", 1, {FIELD_TYPE_ANY}, FIELD_TYPE_BOOLEAN, sql_builtin_stub,
 	 NULL},

  reply	other threads:[~2021-10-25  8:40 UTC|newest]

Thread overview: 54+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-10-08 17:31 [Tarantool-patches] [PATCH v1 00/21] Refactor non-standard and non-aggragate functions Mergen Imeev via Tarantool-patches
2021-10-08 17:31 ` [Tarantool-patches] [PATCH v1 01/21] sql: refactor CHAR() function Mergen Imeev via Tarantool-patches
2021-10-14 22:42   ` Vladislav Shpilevoy via Tarantool-patches
2021-10-25  8:02     ` Mergen Imeev via Tarantool-patches
2021-10-29 23:42       ` Vladislav Shpilevoy via Tarantool-patches
2021-11-02 11:35         ` Mergen Imeev via Tarantool-patches
2021-10-08 17:31 ` [Tarantool-patches] [PATCH v1 02/21] sql: refactor GREATEST() and LEAST() functions Mergen Imeev via Tarantool-patches
2021-10-14 22:42   ` Vladislav Shpilevoy via Tarantool-patches
2021-10-25  8:17     ` Mergen Imeev via Tarantool-patches
2021-10-08 17:31 ` [Tarantool-patches] [PATCH v1 03/21] sql: refactor HEX() function Mergen Imeev via Tarantool-patches
2021-10-14 22:43   ` Vladislav Shpilevoy via Tarantool-patches
2021-10-25  8:19     ` Mergen Imeev via Tarantool-patches
2021-10-08 17:31 ` [Tarantool-patches] [PATCH v1 04/21] sql: refactor LENGTH() function Mergen Imeev via Tarantool-patches
2021-10-14 22:43   ` Vladislav Shpilevoy via Tarantool-patches
2021-10-25  8:30     ` Mergen Imeev via Tarantool-patches
2021-10-29 23:42       ` Vladislav Shpilevoy via Tarantool-patches
2021-11-02 11:39         ` Mergen Imeev via Tarantool-patches
2021-10-08 17:31 ` [Tarantool-patches] [PATCH v1 05/21] sql: refactor PRINTF() function Mergen Imeev via Tarantool-patches
2021-10-14 22:44   ` Vladislav Shpilevoy via Tarantool-patches
2021-10-25  8:33     ` Mergen Imeev via Tarantool-patches
2021-10-08 17:31 ` [Tarantool-patches] [PATCH v1 06/21] sql: refactor RANDOM() function Mergen Imeev via Tarantool-patches
2021-10-25  8:35   ` Mergen Imeev via Tarantool-patches
2021-10-08 17:31 ` [Tarantool-patches] [PATCH v1 07/21] sql: rework RANDOMBLOB() function Mergen Imeev via Tarantool-patches
2021-10-25  8:36   ` Mergen Imeev via Tarantool-patches
2021-10-08 17:31 ` [Tarantool-patches] [PATCH v1 08/21] sql: refactor ZEROBLOB() function Mergen Imeev via Tarantool-patches
2021-10-25  8:37   ` Mergen Imeev via Tarantool-patches
2021-10-08 17:31 ` [Tarantool-patches] [PATCH v1 09/21] sql: refactor TYPEOF() function Mergen Imeev via Tarantool-patches
2021-10-08 17:31 ` [Tarantool-patches] [PATCH v1 10/21] sql: refactor ROUND() function Mergen Imeev via Tarantool-patches
2021-10-08 17:31 ` [Tarantool-patches] [PATCH v1 11/21] sql: refactor ROW_COUNT() function Mergen Imeev via Tarantool-patches
2021-10-08 17:31 ` [Tarantool-patches] [PATCH v1 12/21] sql: rework UUID() function Mergen Imeev via Tarantool-patches
2021-10-25  8:38   ` Mergen Imeev via Tarantool-patches
2021-10-08 17:31 ` [Tarantool-patches] [PATCH v1 13/21] sql: refactor VERSION() function Mergen Imeev via Tarantool-patches
2021-10-08 17:31 ` [Tarantool-patches] [PATCH v1 14/21] sql: refactor UNICODE() function Mergen Imeev via Tarantool-patches
2021-10-14 22:44   ` Vladislav Shpilevoy via Tarantool-patches
2021-10-25  8:40     ` Mergen Imeev via Tarantool-patches [this message]
2021-11-02 11:42       ` Mergen Imeev via Tarantool-patches
2021-10-08 17:32 ` [Tarantool-patches] [PATCH v1 15/21] sql: refactor of SOUNDEX() function Mergen Imeev via Tarantool-patches
2021-10-08 17:32 ` [Tarantool-patches] [PATCH v1 16/21] sql: refactor REPLACE() function Mergen Imeev via Tarantool-patches
2021-10-14 22:45   ` Vladislav Shpilevoy via Tarantool-patches
2021-10-25  8:45     ` Mergen Imeev via Tarantool-patches
2021-10-08 17:32 ` [Tarantool-patches] [PATCH v1 17/21] sql: refactor QUOTE() function Mergen Imeev via Tarantool-patches
2021-10-08 17:32 ` [Tarantool-patches] [PATCH v1 18/21] sql: remove unused code Mergen Imeev via Tarantool-patches
2021-10-25  8:51   ` Mergen Imeev via Tarantool-patches
2021-10-08 17:32 ` [Tarantool-patches] [PATCH v1 19/21] sql: remove MEM_Dyn flag Mergen Imeev via Tarantool-patches
2021-10-14 22:46   ` Vladislav Shpilevoy via Tarantool-patches
2021-10-25  8:54     ` Mergen Imeev via Tarantool-patches
2021-10-29 23:43       ` Vladislav Shpilevoy via Tarantool-patches
2021-11-02 11:43         ` Mergen Imeev via Tarantool-patches
2021-10-08 17:32 ` [Tarantool-patches] [PATCH v1 20/21] sql: remove MEM_Term flag Mergen Imeev via Tarantool-patches
2021-10-14 22:47   ` Vladislav Shpilevoy via Tarantool-patches
2021-10-25  9:57     ` Mergen Imeev via Tarantool-patches
2021-10-08 17:32 ` [Tarantool-patches] [PATCH v1 21/21] sql: make arguments to be const Mergen Imeev via Tarantool-patches
2021-11-02 22:15 ` [Tarantool-patches] [PATCH v1 00/21] Refactor non-standard and non-aggragate functions Vladislav Shpilevoy via Tarantool-patches
2021-11-11 10:48 Mergen Imeev via Tarantool-patches
2021-11-11 10:49 ` [Tarantool-patches] [PATCH v1 14/21] sql: refactor UNICODE() function Mergen Imeev via Tarantool-patches

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20211025084047.GJ36295@tarantool.org \
    --to=tarantool-patches@dev.tarantool.org \
    --cc=imeevma@tarantool.org \
    --cc=v.shpilevoy@tarantool.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Tarantool development patches archive

This inbox may be cloned and mirrored by anyone:

	git clone --mirror https://lists.tarantool.org/tarantool-patches/0 tarantool-patches/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 tarantool-patches tarantool-patches/ https://lists.tarantool.org/tarantool-patches \
		tarantool-patches@dev.tarantool.org.
	public-inbox-index tarantool-patches

Example config snippet for mirrors.


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git