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 2/8] sql: refactor CHAR_LENGTH() function
Date: Wed, 20 Oct 2021 19:58:44 +0300
Message-ID: <20211020165844.GB203963@tarantool.org> (raw)
In-Reply-To: <a4a45019-137c-d7bd-52bd-509388b45eea@tarantool.org>

Thank you for the review! My answer, diff and new patch below.

On Fri, Oct 08, 2021 at 11:56:59PM +0200, Vladislav Shpilevoy wrote:
> Thanks for the patch!
> 
> On 01.10.2021 18:29, imeevma@tarantool.org wrote:
> > Part of #4145
> > ---
> >  src/box/sql/func.c | 38 +++++++++++++++++++++++++++++++++++---
> >  1 file changed, 35 insertions(+), 3 deletions(-)
> > 
> > diff --git a/src/box/sql/func.c b/src/box/sql/func.c
> > index 54b03f359..2e53b32d8 100644
> > --- a/src/box/sql/func.c
> > +++ b/src/box/sql/func.c
> > @@ -263,6 +263,38 @@ func_abs_double(struct sql_context *ctx, int argc, struct Mem *argv)
> >  	mem_set_double(ctx->pOut, arg->u.r < 0 ? -arg->u.r : arg->u.r);
> >  }
> >  
> > +/** Implementation of the CHAR_LENGTH() function. */
> > +static inline uint8_t
> > +utf8_len_char(char c)
> > +{
> > +	uint8_t u = (uint8_t)c;
> > +	return 1 + (u >= 0xc2) + (u >= 0xe0) + (u >= 0xf0);
> 
> It is not that simple really. Consider either using the old
> lengthFunc() and other sqlite utf8 helpers or use the approach
> similar to utf8_len() in utf8.c. It uses ICU macro U8_NEXT()
> and has handling for special symbols like U_SENTINEL.
> 
> Otherwise you are making already third version of functions to
> work with utf8.
> 
> I would even prefer to refactor lengthFunc() to stop using sqlite
> legacy and drop sqlite utf8 entirely, but I suspect it might be
> not so trivial to do and should be done later.
I was able to use ucnv_getNextUChar() here. In fact, I was able to use this
functions in all the places in this patch-set where we had to work with my or
SQLite functions that work with UTF8 characters. I think I can remove sql/utf.c
in the next patchset, since I refactor the LENGTH() and UNICODE() functions
there.


Diff:

diff --git a/src/box/sql/func.c b/src/box/sql/func.c
index e7d1988e0..faef0eef3 100644
--- a/src/box/sql/func.c
+++ b/src/box/sql/func.c
@@ -259,35 +259,24 @@ func_abs_double(struct sql_context *ctx, int argc, struct Mem *argv)
 }
 
 /** Implementation of the CHAR_LENGTH() function. */
-static inline uint8_t
-utf8_len_char(char c)
-{
-	uint8_t u = (uint8_t)c;
-	return 1 + (u >= 0xc2) + (u >= 0xe0) + (u >= 0xf0);
-}
-
-static inline uint32_t
-utf8_len_str(const char *str, uint32_t size)
-{
-	uint32_t len = 0;
-	uint32_t pos = 0;
-	while (pos < size) {
-		pos += utf8_len_char(str[pos]);
-		++len;
-	}
-	return len;
-}
-
 static void
 func_char_length(struct sql_context *ctx, int argc, struct Mem *argv)
 {
 	assert(argc == 1);
 	(void)argc;
 	struct Mem *arg = &argv[0];
-	if (arg->type == MEM_TYPE_NULL)
+	if (mem_is_null(arg))
 		return;
-	assert(arg->type == MEM_TYPE_STR && arg->n >= 0);
-	mem_set_uint(ctx->pOut, utf8_len_str(arg->z, arg->n));
+	assert(mem_is_str(arg) && arg->n >= 0);
+	uint32_t len = 0;
+	UErrorCode err = U_ZERO_ERROR;
+	const char *pos = arg->z;
+	const char *end = arg->z + arg->n;
+	while (pos < end) {
+		ucnv_getNextUChar(icu_utf8_conv, &pos, end, &err);
+		++len;
+	}
+	mem_set_uint(ctx->pOut, len);
 }
 
 static const unsigned char *
diff --git a/test/sql-tap/badutf1.test.lua b/test/sql-tap/badutf1.test.lua
index b25436186..27f17168b 100755
--- a/test/sql-tap/badutf1.test.lua
+++ b/test/sql-tap/badutf1.test.lua
@@ -287,7 +287,7 @@ test:do_test(
         return test:execsql2("SELECT length('\x80\x80\x80\x80\x80\xf0\x80\x80\x80\x80') AS x")
     end, {
         -- <badutf-3.8>
-        "X", 7
+        "X", 10
         -- </badutf-3.8>
     })
 
@@ -297,7 +297,7 @@ test:do_test(
         return test:execsql2("SELECT length('\x80\x80\x80\x80\x80\xf0\x80\x80\x80\xff') AS x")
     end, {
         -- <badutf-3.9>
-        "X", 7
+        "X", 10
         -- </badutf-3.9>
     })
 
diff --git a/test/sql-tap/built-in-functions.test.lua b/test/sql-tap/built-in-functions.test.lua
index 6fae811dc..7fe987abc 100755
--- a/test/sql-tap/built-in-functions.test.lua
+++ b/test/sql-tap/built-in-functions.test.lua
@@ -1,6 +1,6 @@
 #!/usr/bin/env tarantool
 local test = require("sqltester")
-test:plan(52)
+test:plan(54)
 
 --
 -- Make sure that number of arguments check is checked properly for SQL built-in
@@ -545,4 +545,28 @@ test:do_test(
         {name = "COLUMN_2", type = "scalar"},
     })
 
+-- gh-4145: Make sure the character is now checked when calculating its length.
+
+-- Character with UTF-8 code F0808080 does not exist.
+test:do_execsql_test(
+    "builtins-4.1",
+    [[
+        SELECT CHAR_LENGTH(CAST(x'f0808080' AS STRING));
+    ]],
+    {
+        4
+    }
+)
+
+-- Character with UTF-8 code F0908080 is '𐀀'.
+test:do_execsql_test(
+    "builtins-4.2",
+    [[
+        SELECT CHAR_LENGTH(CAST(x'f0908080' AS STRING));
+    ]],
+    {
+        1
+    }
+)
+
 test:finish_test()
diff --git a/test/sql-tap/func3.test.lua b/test/sql-tap/func3.test.lua
index 7f1d8d33c..6999fea67 100755
--- a/test/sql-tap/func3.test.lua
+++ b/test/sql-tap/func3.test.lua
@@ -297,8 +297,8 @@ suits[5] = {str = '\x61\xc0', len = 2}
 suits[6] = {str = '\x61\xc0\x80\x80\x80\x80\x80\x80\x80\x80\x80\x80', len = 12}
 suits[7] = {str = '\xc0\x80\x80\x80\x80\x80\x80\x80\x80\x80\x80', len = 11}
 suits[8] = {str = '\x80\x80\x80\x80\x80\x80\x80\x80\x80\x80', len = 10}
-suits[9] = {str = '\x80\x80\x80\x80\x80\xf0\x80\x80\x80\x80', len = 7}
-suits[10] = {str = '\x80\x80\x80\x80\x80\xf0\x80\x80\x80\xff', len = 7}
+suits[9] = {str = '\x80\x80\x80\x80\x80\xf0\x90\x80\x80\x80', len = 7}
+suits[10] = {str = '\x80\x80\x80\x80\x80\xf0\x90\x80\x80\xff', len = 7}
 
 for k,v in pairs(suits) do
     test:do_execsql_test(


New patch:

commit 080a23b1d84ce7749d887819d328e988ee7fe766
Author: Mergen Imeev <imeevma@gmail.com>
Date:   Fri Oct 1 11:12:39 2021 +0300

    sql: rework CHAR_LENGTH() function
    
    The CHAR_LENGTH() and CHARACTER_LENGTH() functions now use ICU functions
    to determine the length of a string. This gives us a better pricision
    when determining the length.
    
    Part of #4145

diff --git a/src/box/sql/func.c b/src/box/sql/func.c
index dbeb38bee..faef0eef3 100644
--- a/src/box/sql/func.c
+++ b/src/box/sql/func.c
@@ -258,6 +258,27 @@ func_abs_double(struct sql_context *ctx, int argc, struct Mem *argv)
 	mem_set_double(ctx->pOut, arg->u.r < 0 ? -arg->u.r : arg->u.r);
 }
 
+/** Implementation of the CHAR_LENGTH() function. */
+static void
+func_char_length(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) && arg->n >= 0);
+	uint32_t len = 0;
+	UErrorCode err = U_ZERO_ERROR;
+	const char *pos = arg->z;
+	const char *end = arg->z + arg->n;
+	while (pos < end) {
+		ucnv_getNextUChar(icu_utf8_conv, &pos, end, &err);
+		++len;
+	}
+	mem_set_uint(ctx->pOut, len);
+}
+
 static const unsigned char *
 mem_as_ustr(struct Mem *mem)
 {
@@ -1912,8 +1933,8 @@ static struct sql_func_definition definitions[] = {
 	{"AVG", 1, {FIELD_TYPE_INTEGER}, FIELD_TYPE_INTEGER, step_avg, fin_avg},
 	{"AVG", 1, {FIELD_TYPE_DOUBLE}, FIELD_TYPE_DOUBLE, step_avg, fin_avg},
 	{"CHAR", -1, {FIELD_TYPE_INTEGER}, FIELD_TYPE_STRING, charFunc, NULL},
-	{"CHAR_LENGTH", 1, {FIELD_TYPE_STRING}, FIELD_TYPE_INTEGER, lengthFunc,
-	 NULL},
+	{"CHAR_LENGTH", 1, {FIELD_TYPE_STRING}, FIELD_TYPE_INTEGER,
+	 func_char_length, NULL},
 	{"COALESCE", -1, {FIELD_TYPE_ANY}, FIELD_TYPE_SCALAR, sql_builtin_stub,
 	 NULL},
 	{"COUNT", 0, {}, FIELD_TYPE_INTEGER, step_count, fin_count},
@@ -1957,7 +1978,7 @@ static struct sql_func_definition definitions[] = {
 	{"LEAST", -1, {FIELD_TYPE_STRING}, FIELD_TYPE_STRING, minmaxFunc, NULL},
 	{"LEAST", -1, {FIELD_TYPE_SCALAR}, FIELD_TYPE_SCALAR, minmaxFunc, NULL},
 
-	{"LENGTH", 1, {FIELD_TYPE_STRING}, FIELD_TYPE_INTEGER, lengthFunc,
+	{"LENGTH", 1, {FIELD_TYPE_STRING}, FIELD_TYPE_INTEGER, func_char_length,
 	 NULL},
 	{"LENGTH", 1, {FIELD_TYPE_VARBINARY}, FIELD_TYPE_INTEGER, lengthFunc,
 	 NULL},
diff --git a/test/sql-tap/badutf1.test.lua b/test/sql-tap/badutf1.test.lua
index b25436186..27f17168b 100755
--- a/test/sql-tap/badutf1.test.lua
+++ b/test/sql-tap/badutf1.test.lua
@@ -287,7 +287,7 @@ test:do_test(
         return test:execsql2("SELECT length('\x80\x80\x80\x80\x80\xf0\x80\x80\x80\x80') AS x")
     end, {
         -- <badutf-3.8>
-        "X", 7
+        "X", 10
         -- </badutf-3.8>
     })
 
@@ -297,7 +297,7 @@ test:do_test(
         return test:execsql2("SELECT length('\x80\x80\x80\x80\x80\xf0\x80\x80\x80\xff') AS x")
     end, {
         -- <badutf-3.9>
-        "X", 7
+        "X", 10
         -- </badutf-3.9>
     })
 
diff --git a/test/sql-tap/built-in-functions.test.lua b/test/sql-tap/built-in-functions.test.lua
index 6fae811dc..7fe987abc 100755
--- a/test/sql-tap/built-in-functions.test.lua
+++ b/test/sql-tap/built-in-functions.test.lua
@@ -1,6 +1,6 @@
 #!/usr/bin/env tarantool
 local test = require("sqltester")
-test:plan(52)
+test:plan(54)
 
 --
 -- Make sure that number of arguments check is checked properly for SQL built-in
@@ -545,4 +545,28 @@ test:do_test(
         {name = "COLUMN_2", type = "scalar"},
     })
 
+-- gh-4145: Make sure the character is now checked when calculating its length.
+
+-- Character with UTF-8 code F0808080 does not exist.
+test:do_execsql_test(
+    "builtins-4.1",
+    [[
+        SELECT CHAR_LENGTH(CAST(x'f0808080' AS STRING));
+    ]],
+    {
+        4
+    }
+)
+
+-- Character with UTF-8 code F0908080 is '𐀀'.
+test:do_execsql_test(
+    "builtins-4.2",
+    [[
+        SELECT CHAR_LENGTH(CAST(x'f0908080' AS STRING));
+    ]],
+    {
+        1
+    }
+)
+
 test:finish_test()
diff --git a/test/sql-tap/func3.test.lua b/test/sql-tap/func3.test.lua
index 7f1d8d33c..6999fea67 100755
--- a/test/sql-tap/func3.test.lua
+++ b/test/sql-tap/func3.test.lua
@@ -297,8 +297,8 @@ suits[5] = {str = '\x61\xc0', len = 2}
 suits[6] = {str = '\x61\xc0\x80\x80\x80\x80\x80\x80\x80\x80\x80\x80', len = 12}
 suits[7] = {str = '\xc0\x80\x80\x80\x80\x80\x80\x80\x80\x80\x80', len = 11}
 suits[8] = {str = '\x80\x80\x80\x80\x80\x80\x80\x80\x80\x80', len = 10}
-suits[9] = {str = '\x80\x80\x80\x80\x80\xf0\x80\x80\x80\x80', len = 7}
-suits[10] = {str = '\x80\x80\x80\x80\x80\xf0\x80\x80\x80\xff', len = 7}
+suits[9] = {str = '\x80\x80\x80\x80\x80\xf0\x90\x80\x80\x80', len = 7}
+suits[10] = {str = '\x80\x80\x80\x80\x80\xf0\x90\x80\x80\xff', len = 7}
 
 for k,v in pairs(suits) do
     test:do_execsql_test(

  reply	other threads:[~2021-10-20 16:58 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-10-01 16:29 [Tarantool-patches] [PATCH v1 0/8] Rework standard function Mergen Imeev via Tarantool-patches
2021-10-01 16:29 ` [Tarantool-patches] [PATCH v1 1/8] sql: refactor ABS() funcion Mergen Imeev via Tarantool-patches
2021-10-08 21:55   ` Vladislav Shpilevoy via Tarantool-patches
2021-10-20 16:52     ` Mergen Imeev via Tarantool-patches
2021-10-28 22:11       ` Vladislav Shpilevoy via Tarantool-patches
2021-11-01 10:11         ` Mergen Imeev via Tarantool-patches
2021-11-01 13:37           ` Vladislav Shpilevoy via Tarantool-patches
2021-10-01 16:29 ` [Tarantool-patches] [PATCH v1 2/8] sql: refactor CHAR_LENGTH() function Mergen Imeev via Tarantool-patches
2021-10-08 21:56   ` Vladislav Shpilevoy via Tarantool-patches
2021-10-20 16:58     ` Mergen Imeev via Tarantool-patches [this message]
2021-10-28 22:11       ` Vladislav Shpilevoy via Tarantool-patches
2021-11-01 10:20         ` Mergen Imeev via Tarantool-patches
2021-10-01 16:29 ` [Tarantool-patches] [PATCH v1 3/8] sql: refactor UPPER() and LOWER() functions Mergen Imeev via Tarantool-patches
2021-10-20 17:02   ` Mergen Imeev via Tarantool-patches
2021-10-01 16:29 ` [Tarantool-patches] [PATCH v1 4/8] sql: refactor NULLIF() function Mergen Imeev via Tarantool-patches
2021-10-01 16:29 ` [Tarantool-patches] [PATCH v1 5/8] sql: rework TRIM() function Mergen Imeev via Tarantool-patches
2021-10-20 17:05   ` Mergen Imeev via Tarantool-patches
2021-10-28 22:12     ` Vladislav Shpilevoy via Tarantool-patches
2021-11-01 10:35       ` Mergen Imeev via Tarantool-patches
2021-10-01 16:29 ` [Tarantool-patches] [PATCH v1 6/8] sql: rework POSITION() function Mergen Imeev via Tarantool-patches
2021-10-08 21:58   ` Vladislav Shpilevoy via Tarantool-patches
2021-10-20 17:08     ` Mergen Imeev via Tarantool-patches
2021-11-01 10:41       ` Mergen Imeev via Tarantool-patches
2021-10-01 16:29 ` [Tarantool-patches] [PATCH v1 7/8] sql: rework SUBSTR() function Mergen Imeev via Tarantool-patches
2021-10-08 22:02   ` Vladislav Shpilevoy via Tarantool-patches
2021-10-20 17:15     ` Mergen Imeev via Tarantool-patches
2021-10-28 22:13       ` Vladislav Shpilevoy via Tarantool-patches
2021-11-01 10:45         ` Mergen Imeev via Tarantool-patches
2021-10-01 16:29 ` [Tarantool-patches] [PATCH v1 8/8] sql: refactor LIKE() function Mergen Imeev via Tarantool-patches
2021-10-08 22:02   ` Vladislav Shpilevoy via Tarantool-patches
2021-10-20 17:19     ` Mergen Imeev via Tarantool-patches
2021-11-01 10:48       ` Mergen Imeev via Tarantool-patches
2021-11-01 10:53         ` Mergen Imeev via Tarantool-patches
2021-10-04 13:32 ` [Tarantool-patches] [PATCH v1 0/8] Rework standard function Mergen Imeev via Tarantool-patches
2021-11-01 13:38 ` Vladislav Shpilevoy 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=20211020165844.GB203963@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