bk commit into 4.1 tree (gshchepa:1.2671) BUG#29294

[<gshchepa]

Below is the list of changes that have just been committed into a local
4.1 repository of uchum. When uchum does a push these changes will
be propagated to the main repository and, within 24 hours after the
push, to the public repository.
For information on how to access the public repository
see http://dev.mysql.com/doc/mysql/en/installing-source-tree.html

ChangeSet@stripped, 2007-06-29 16:40:46+05:00, gshchepa@stripped +4 -0
  Fixed bug #29294.
  The `SELECT 'r' INTO OUTFILE ... FIELDS ENCLOSED BY 'r' ' statement
  encoded the 'r' string to a 4 byte string of value x'725c7272'
  (sequence of 4 characters: r\rr).
  The LOAD DATA statement decoded this string to a 1 byte string of
  value x'0d' (ASCII Carriage Return character) instead of the original
  'r' character.
  The same error also happened with the FIELDS ENCLOSED BY clause
  followed by special characters: 'n', 't', 'r', 'b', '0', 'Z' and 'N'.
  
  NOTE 1: This is a result of the undocumented feature: the LOAD DATA INFILE
  recognises 2-byte input sequences like \n, \t, \r and \Z in addition
  to documented 2-byte sequences: \0 and \N. This feature should be
  documented (here backspace character is a default ESCAPED BY character,
  in the real-life example it may be any ESCAPED BY character).
  
  NOTE 2, changed behaviour:
  Now the `SELECT INTO OUTFILE' statement with the `FIELDS ENCLOSED BY'
  clause followed by one of: 'n', 't', 'r', 'b', '0', 'Z' or 'N' characters
  encodes this special character itself by doubling it ('r' --> 'rr'),
  not by prepending it with an escape character.

  mysql-test/r/loaddata.result@stripped, 2007-06-29 16:38:46+05:00, gshchepa@stripped +64 -1
    Update test case for bug #29294.

  mysql-test/t/loaddata.test@stripped, 2007-06-29 16:38:42+05:00, gshchepa@stripped +37 -1
    Update test case for bug #29294.

  sql/sql_class.cc@stripped, 2007-06-29 16:37:16+05:00, gshchepa@stripped +5 -1
    Fixed bug #29294.
    The select_export::send_data method has been modified to
    encode special values of the field_sep field by
    doubling of those values instead of prepending them with a
    value of the escape_char field.
    Example: The SELECT 'r' INTO OUTFILE FIELDS ENCLOSED BY 'r'
    now produces the 'rr' output string instead of x'5c72'
    (i.e. instead of sequence of 2 bytes: \ and r).

  sql/sql_class.h@stripped, 2007-06-29 16:34:41+05:00, gshchepa@stripped +9 -0
    Fixed bug #29294.
    The ESCAPE_CHARS macro constant is defined to enumerate
    symbolic names of espace-sequences like  '\n', '\t' etc.
    The select_export::is_ambiguous_field_sep field has been added
    to distinguish special values of the field_sep field from
    another values (see ESCAPE_CHARS).

diff -Nrup a/mysql-test/r/loaddata.result b/mysql-test/r/loaddata.result
--- a/mysql-test/r/loaddata.result	2005-10-22 07:54:29 +05:00
+++ b/mysql-test/r/loaddata.result	2007-06-29 16:38:46 +05:00
@@ -1,4 +1,4 @@
-drop table if exists t1;
+drop table if exists t1,t2;
 create table t1 (a date, b date, c date not null, d date);
 load data infile '../../std_data/loaddata1.dat' into table t1 fields terminated by ',';
 Warnings:
@@ -85,3 +85,66 @@ field1	field2
 a"b	cd"ef
 a"b	c"d"e
 drop table t1;
+CREATE TABLE t1 (
+id INT AUTO_INCREMENT PRIMARY KEY,
+c1 VARCHAR(255)
+);
+CREATE TABLE t2 (
+id INT,
+c2 VARCHAR(255)
+);
+INSERT INTO t1 (c1) VALUES
+('r'),   ('rr'),   ('rrr'),   ('rrrr'),
+('.r'),  ('.rr'),  ('.rrr'),  ('.rrrr'),
+('r.'),  ('rr.'),  ('rrr.'),  ('rrrr.'),
+('.r.'), ('.rr.'), ('.rrr.'), ('.rrrr.'),
+('\r'),  ('\\rr'), ('\\\rr'), ('\\\\rr');
+SELECT * FROM t1;
+id	c1
+1	r
+2	rr
+3	rrr
+4	rrrr
+5	.r
+6	.rr
+7	.rrr
+8	.rrrr
+9	r.
+10	rr.
+11	rrr.
+12	rrrr.
+13	.r.
+14	.rr.
+15	.rrr.
+16	.rrrr.
+17	
+18	\rr
+19	\
r
+20	\\rr
+SELECT * INTO OUTFILE 'MYSQL_TEST_DIR/var/tmp/t1' FIELDS ENCLOSED BY 'r' FROM t1;
+r1r	rrrr
+r2r	rrrrrr
+r3r	rrrrrrrr
+r4r	rrrrrrrrrr
+r5r	r.rrr
+r6r	r.rrrrr
+r7r	r.rrrrrrr
+r8r	r.rrrrrrrrr
+r9r	rrr.r
+r10r	rrrrr.r
+r11r	rrrrrrr.r
+r12r	rrrrrrrrr.r
+r13r	r.rr.r
+r14r	r.rrrr.r
+r15r	r.rrrrrr.r
+r16r	r.rrrrrrrr.r
+r17r	r
r
+r18r	r\\rrrrr
+r19r	r\\
rrr
+r20r	r\\\\rrrrr
+LOAD DATA INFILE 'MYSQL_TEST_DIR/var/tmp/t1' INTO TABLE t2 FIELDS ENCLOSED BY 'r';
+SELECT t1.id, c1, c2 FROM t1 LEFT  JOIN t2 ON t1.id=t2.id WHERE c1 != c2;
+id	c1	c2
+SELECT t1.id, c1, c2 FROM t1 RIGHT JOIN t2 ON t1.id=t2.id WHERE c1 != c2;
+id	c1	c2
+DROP TABLE t1,t2;
diff -Nrup a/mysql-test/t/loaddata.test b/mysql-test/t/loaddata.test
--- a/mysql-test/t/loaddata.test	2005-10-22 07:54:29 +05:00
+++ b/mysql-test/t/loaddata.test	2007-06-29 16:38:42 +05:00
@@ -3,7 +3,7 @@
 #
 
 --disable_warnings
-drop table if exists t1;
+drop table if exists t1,t2;
 --enable_warnings
 
 create table t1 (a date, b date, c date not null, d date);
@@ -66,5 +66,41 @@ create table t1 (a varchar(20), b varcha
 load data infile '../../std_data/loaddata5.dat' into table t1 fields terminated by ','
enclosed by '"' escaped by '"' (a,b);
 select * from t1;
 drop table t1;
+
+#
+# Bug #29294 SELECT INTO OUTFILE/LOAD DATA INFILE with special
+# characters in the FIELDS ENCLOSED BY clause
+#
+
+CREATE TABLE t1 (
+  id INT AUTO_INCREMENT PRIMARY KEY,
+  c1 VARCHAR(255)
+);
+
+CREATE TABLE t2 (
+  id INT,
+  c2 VARCHAR(255)
+);
+
+INSERT INTO t1 (c1) VALUES
+  ('r'),   ('rr'),   ('rrr'),   ('rrrr'),
+  ('.r'),  ('.rr'),  ('.rrr'),  ('.rrrr'),
+  ('r.'),  ('rr.'),  ('rrr.'),  ('rrrr.'),
+  ('.r.'), ('.rr.'), ('.rrr.'), ('.rrrr.'),
+  ('\r'),  ('\\rr'), ('\\\rr'), ('\\\\rr');
+SELECT * FROM t1;
+
+--exec rm -f $MYSQL_TEST_DIR/var/tmp/t1
+--replace_result $MYSQL_TEST_DIR MYSQL_TEST_DIR
+eval SELECT * INTO OUTFILE '$MYSQL_TEST_DIR/var/tmp/t1' FIELDS ENCLOSED BY 'r' FROM t1;
+--exec cat $MYSQL_TEST_DIR/var/tmp/t1
+
+--replace_result $MYSQL_TEST_DIR MYSQL_TEST_DIR
+eval LOAD DATA INFILE '$MYSQL_TEST_DIR/var/tmp/t1' INTO TABLE t2 FIELDS ENCLOSED BY 'r';
+SELECT t1.id, c1, c2 FROM t1 LEFT  JOIN t2 ON t1.id=t2.id WHERE c1 != c2;
+SELECT t1.id, c1, c2 FROM t1 RIGHT JOIN t2 ON t1.id=t2.id WHERE c1 != c2;
+
+--exec rm $MYSQL_TEST_DIR/var/tmp/t1
+DROP TABLE t1,t2;
 
 # End of 4.1 tests
diff -Nrup a/sql/sql_class.cc b/sql/sql_class.cc
--- a/sql/sql_class.cc	2007-03-20 21:59:23 +04:00
+++ b/sql/sql_class.cc	2007-06-29 16:37:16 +05:00
@@ -1020,6 +1020,7 @@ select_export::prepare(List<Item> &list,
   field_sep_char= (exchange->enclosed->length() ? (*exchange->enclosed)[0] :
 		   field_term_length ? (*exchange->field_term)[0] : INT_MAX);
   escape_char=	(exchange->escaped->length() ? (*exchange->escaped)[0] : -1);
+  is_ambiguous_field_sep= strchr(ESCAPE_CHARS, field_sep_char);
   line_sep_char= (exchange->line_term->length() ?
 		  (*exchange->line_term)[0] : INT_MAX);
   if (!field_term_length)
@@ -1113,7 +1114,10 @@ bool select_export::send_data(List<Item>
 	      (int) *pos == line_sep_char || !*pos)
 	  {
 	    char tmp_buff[2];
-	    tmp_buff[0]= escape_char;
+            if ((int) *pos == field_sep_char && is_ambiguous_field_sep)
+              tmp_buff[0]= field_sep_char;
+            else
+              tmp_buff[0]= escape_char;
 	    tmp_buff[1]= *pos ? *pos : '0';
 	    if (my_b_write(&cache,(byte*) start,(uint) (pos-start)) ||
 		my_b_write(&cache,(byte*) tmp_buff,2))
diff -Nrup a/sql/sql_class.h b/sql/sql_class.h
--- a/sql/sql_class.h	2007-01-15 13:58:02 +04:00
+++ b/sql/sql_class.h	2007-06-29 16:34:41 +05:00
@@ -1224,9 +1224,18 @@ public:
 };
 
 
+#define ESCAPE_CHARS "ntrb0ZN" // keep synchronous with READ_INFO::unescaped
+
+
 class select_export :public select_to_file {
   uint field_term_length;
   int field_sep_char,escape_char,line_sep_char;
+  /*
+    The is_ambiguous_field_sep field is true if a value of the field_sep_char
+    field is one of the 'n', 't', 'r' etc characters
+    (see the READ_INFO::unescape method and the ESCAPE_CHARS constant value).
+  */
+  bool is_ambiguous_field_sep;
   bool fixed_row_size;
 public:
   select_export(sql_exchange *ex) :select_to_file(ex) {}