[tarantool-patches] Re: [PATCH] sql: LIKE & GLOB pattern comparison issue

[Nikita Tatunov <hollow653@gmail.com>]

[-- Attachment #1: Type: text/plain, Size: 7712 bytes --]

ср, 18 июл. 2018 г. в 18:53, Alex Khatskevich <avkhatskevich@tarantool.org>:

> Once you have fixed comments, please apply a new full diff at the end of
> email, to
> continue review process.
> Answer with a full diff to this email please (just paste as a plain text
> output of `git diff` command)
>
> On 18.07.2018 18:24, Nikita Tatunov wrote:
>
>
> Fixed it.
>
> Yeah, you're right. Fixed it.
>
> Isn't actual with the fix.
>
> Yeah, sure.
>
>
>
Sorry. Here it is:

diff --git a/src/box/sql/func.c b/src/box/sql/func.c
index c06e3bd..a7f7c17 100644
--- a/src/box/sql/func.c
+++ b/src/box/sql/func.c
@@ -617,13 +617,15 @@ struct compareInfo {
  u8 noCase; /* true to ignore case differences */
 };

-/*
- * For LIKE and GLOB matching on EBCDIC machines, assume that every
- * character is exactly one byte in size.  Also, provde the Utf8Read()
- * macro for fast reading of the next character in the common case where
- * the next character is ASCII.
+/**
+ * Providing there are symbols in string s this macro returns
+ * UTF-8 code of character and pushes pointer to the next symbol
+ * in the string. Otherwise return code is SQL_END_OF_STRING.
  */
-#define Utf8Read(s, e)    ucnv_getNextUChar(pUtf8conv, &s, e, &status)
+#define Utf8Read(s, e) (s < e ?\
+ ucnv_getNextUChar(pUtf8conv, &s, e, &status) : 0)
+
+#define SQL_END_OF_STRING       0

 static const struct compareInfo globInfo = { '*', '?', '[', 0 };

@@ -698,29 +700,27 @@ patternCompare(const char * pattern, /* The glob
pattern */
  const char * string_end = string + strlen(string);
  UErrorCode status = U_ZERO_ERROR;

- while (pattern < pattern_end){
- c = Utf8Read(pattern, pattern_end);
+ while ((c = Utf8Read(pattern, pattern_end))) {
  if (c == matchAll) { /* Match "*" */
  /* Skip over multiple "*" characters in the pattern.  If there
  * are also "?" characters, skip those as well, but consume a
  * single character of the input string for each "?" skipped
  */
- while (pattern < pattern_end){
- c = Utf8Read(pattern, pattern_end);
+ while ((c = Utf8Read(pattern, pattern_end))) {
  if (c != matchAll && c != matchOne)
  break;
- if (c == matchOne
-     && Utf8Read(string, string_end) == 0) {
+ if (c == matchOne &&
+     Utf8Read(string, string_end) ==
+     SQL_END_OF_STRING)
  return SQLITE_NOWILDCARDMATCH;
- }
  }
  /* "*" at the end of the pattern matches */
- if (pattern == pattern_end)
+ if (c == SQL_END_OF_STRING)
  return SQLITE_MATCH;
  if (c == matchOther) {
  if (pInfo->matchSet == 0) {
  c = Utf8Read(pattern, pattern_end);
- if (c == 0)
+ if (c == SQL_END_OF_STRING)
  return SQLITE_NOWILDCARDMATCH;
  } else {
  /* "[...]" immediately follows the "*".  We have to do a slow
@@ -782,7 +782,7 @@ patternCompare(const char * pattern, /* The glob
pattern */
  if (c == matchOther) {
  if (pInfo->matchSet == 0) {
  c = Utf8Read(pattern, pattern_end);
- if (c == 0)
+ if (c == SQL_END_OF_STRING)
  return SQLITE_NOMATCH;
  zEscaped = pattern;
  } else {
@@ -802,7 +802,7 @@ patternCompare(const char * pattern, /* The glob
pattern */
  seen = 1;
  c2 = Utf8Read(pattern, pattern_end);
  }
- while (c2 && c2 != ']') {
+ while (c2 != SQL_END_OF_STRING && c2 != ']') {
  if (c2 == '-' && pattern[0] != ']'
      && pattern < pattern_end
      && prior_c > 0) {
@@ -839,7 +839,8 @@ patternCompare(const char * pattern, /* The glob
pattern */
      c == u_tolower(c2))
  continue;
  }
- if (c == matchOne && pattern != zEscaped && c2 != 0)
+ if (c == matchOne && pattern != zEscaped &&
+     c2 != SQL_END_OF_STRING)
  continue;
  return SQLITE_NOMATCH;
  }
diff --git a/test/sql-tap/like1.test.lua b/test/sql-tap/like1.test.lua
new file mode 100755
index 0000000..807ee65
--- /dev/null
+++ b/test/sql-tap/like1.test.lua
@@ -0,0 +1,181 @@
+#!/usr/bin/env tarantool
+test = require("sqltester")
+test:plan(16)
+
+test:do_catchsql_test(
+ "like-test-1.1",
+ [[
+ CREATE TABLE t2 (column1 INTEGER,
+      column2 VARCHAR(100),
+      column3 BLOB,
+      column4 FLOAT,
+      PRIMARY KEY (column1, column2));
+ INSERT INTO t2 VALUES (1, 'AB', X'4142', 5.5);
+ INSERT INTO t2 VALUES (1, 'CD', X'2020', 1E4);
+ INSERT INTO t2 VALUES (2, 'AB', X'2020', 12.34567);
+ INSERT INTO t2 VALUES (-1000, '', X'', 0.0);
+ CREATE TABLE t1 (a INT PRIMARY KEY, str VARCHAR(100));
+ INSERT INTO t1 VALUES (1, 'ab');
+ INSERT INTO t1 VALUES (2, 'abCDF');
+ INSERT INTO t1 VALUES (3, 'CDF');
+ CREATE TABLE t (s1 char(2) primary key, s2 char(2));
+ INSERT INTO t VALUES ('AB', 'AB');
+ ]], {
+ -- <like-test-1.1>
+ 0
+ -- <like-test-1.1>
+ })
+
+test:do_execsql_test(
+ "like-test-1.2",
+ [[
+ SELECT column1, column2, column1 * column4 FROM t2 WHERE column2 LIKE
'_B';
+ ]], {
+ -- <like-test-1.2>
+ 1, 'AB', 5.5, 2, 'AB', 24.69134
+ -- <like-test-1.2>
+ })
+
+test:do_execsql_test(
+ "like-test-1.3",
+ [[
+ SELECT column1, column2 FROM t2 WHERE column2 LIKE '%B';
+ ]], {
+             -- <like-test-1.3>
+             1, 'AB', 2, 'AB'
+             -- <like-test-1.3>
+ })
+
+test:do_execsql_test(
+ "like-test-1.4",
+ [[
+ SELECT column1, column2 FROM t2 WHERE column2 LIKE 'A__';
+ ]], {
+             -- <like-test-1.4>
+
+             -- <like-test-1.4>
+ })
+
+test:do_execsql_test(
+ "like-test-1.5",
+ [[
+ SELECT column1, column2 FROM t2 WHERE column2 LIKE 'A_';
+ ]], {
+             -- <like-test-1.5>
+             1, 'AB', 2, 'AB'
+             -- <like-test-1.5>
+ })
+
+test:do_execsql_test(
+ "like-test-1.6",
+ [[
+ SELECT column1, column2 FROM t2 WHERE column2 LIKE 'A';
+ ]], {
+             -- <like-test-1.6>
+
+             -- <like-test-1.6>
+ })
+
+test:do_execsql_test(
+ "like-test-1.7",
+ [[
+ SELECT column1, column2 FROM t2 WHERE column2 LIKE '_';
+ ]], {
+             -- <like-test-1.7>
+
+             -- <like-test-1.7>
+ })
+
+test:do_execsql_test(
+ "like-test-1.8",
+ [[
+ SELECT * FROM t WHERE s1 LIKE '%A';
+ ]], {
+             -- <like-test-1.8>
+
+             -- <like-test-1.8>
+ })
+
+test:do_execsql_test(
+ "like-test-1.9",
+ [[
+ SELECT * FROM t WHERE s1 LIKE '%C';
+ ]], {
+             -- <like-test-1.9>
+
+             -- <like-test-1.9>
+ })
+
+test:do_execsql_test(
+ "like-test-1.10",
+ [[
+ SELECT * FROM t1 WHERE str LIKE '%df';
+ ]], {
+             -- <like-test-1.10>
+             2, 'abCDF', 3, 'CDF'
+             -- <like-test-1.10>
+ })
+
+test:do_execsql_test(
+ "like-test-1.11",
+ [[
+ SELECT * FROM t1 WHERE str LIKE 'a_';
+ ]], {
+             -- <like-test-1.11>
+             1, 'ab'
+             -- <like-test-1.11>
+ })
+
+test:do_execsql_test(
+ "like-test-1.12",
+ [[
+ SELECT column1, column2 FROM t2 WHERE column2 LIKE '__';
+ ]], {
+             -- <like-test-1.12>
+             1, 'AB', 1, 'CD', 2, 'AB'
+             -- <like-test-1.12>
+ })
+
+test:do_execsql_test(
+ "like-test-1.13",
+ [[
+ SELECT str FROM t1 WHERE str LIKE 'ab%';
+ ]], {
+ -- <like-test-1.13>
+ 'ab', 'abCDF'
+ -- <like-test-1.13>
+ })
+
+test:do_execsql_test(
+ "like-test-1.14",
+ [[
+ SELECT str FROM t1 WHERE str LIKE 'abC%';
+ ]], {
+ -- <like-test-1.14>
+ 'abCDF'
+ -- <like-test-1.14>
+ })
+
+test:do_execsql_test(
+ "like-test-1.15",
+ [[
+ SELECT str FROM t1 WHERE str LIKE 'a_%';
+ ]], {
+ -- <like-test-1.15>
+ 'ab', 'abCDF'
+ -- <like-test-1.15>
+ })
+
+test:do_execsql_test(
+ "like-test-1.16",
+ [[
+ DROP TABLE t1;
+ DROP TABLE t2;
+ DROP TABLE t;
+ ]], {
+             -- <like-test-1.16>
+
+             -- <like-test-1.16>
+ })
+
+test:finish_test()

[-- Attachment #2: Type: text/html, Size: 19060 bytes --]