WL#2649 Number-to-string conversions

added:
  include/ctype_numconv.inc
  mysql-test/include/ctype_numconv.inc
  mysql-test/r/ctype_binary.result
  mysql-test/t/ctype_binary.test
  Adding tests

modified:

  mysql-test/r/bigint.result
  mysql-test/r/case.result
  mysql-test/r/create.result
  mysql-test/r/ctype_cp1251.result
  mysql-test/r/ctype_latin1.result
  mysql-test/r/ctype_ucs.result
  mysql-test/r/func_gconcat.result
  mysql-test/r/func_str.result
  mysql-test/r/metadata.result
  mysql-test/r/ps_1general.result
  mysql-test/r/ps_2myisam.result
  mysql-test/r/ps_3innodb.result
  mysql-test/r/ps_4heap.result
  mysql-test/r/ps_5merge.result
  mysql-test/r/show_check.result
  mysql-test/r/type_datetime.result
  mysql-test/r/type_ranges.result
  mysql-test/r/union.result
  mysql-test/suite/ndb/r/ps_7ndb.result
  mysql-test/t/ctype_cp1251.test
  mysql-test/t/ctype_latin1.test
  mysql-test/t/ctype_ucs.test
  mysql-test/t/func_str.test
    Fixing tests


  @ sql/field.cc
     - Return str result using my_charset_numeric.
     - Using real multi-byte aware str_to_XXX functions
       to handle tricky charset values propely (e.g. UCS2)
  @ sql/field.h
     - Changing derivation of non-string field types to DERIVATION_NUMERIC.
     - Changing binary() for numeric/datetime fields to always
     return TRUE even if charset is not my_charset_bin. We need
     this to keep ha_base_keytype() return HA_KEYTYPE_BINARY.
     - Adding BINARY_FLAG into some fields, because it's not
     being set automatically anymore with
     "my_charset_bin to my_charset_numeric" change.
    - Changing derivation for numeric/datetime datatypes to a weaker
      value, to make "SELECT concat('string', field)" use character
      set of the string literal for the result of the function.
  @ sql/item.cc
     - Implementing generic val_str_ascii().
     - Using max_char_length() instead of direct read of max_length
       to make "tricky" charsets like UCS2 work.
       NOTE: in the future we'll possibly remove all direct reads of max_length
     - Fixing Item_num::safe_charset_converter().
       Previously it alligned binary string to
       character string (for example by adding leading 0x00
       when doing binary->UCS2 conversion). Now it just
       converts from my_charset_numbner to "tocs".
     - Using val_str_ascii() in Item::get_time() to make UCS2 arguments work.
     - Other misc changes
  @ sql/item.h
     - Changing MY_COLL_CMP_CONV and MY_COLL_ALLOW_CONV to
       bit operations instead of hard-coded bit masks.
     - Addding new method DTCollation.set_numeric().
     - Adding new methods to Item.
     - Adding helper functions to make code look nicer:
       agg_item_charsets_for_string_result()
       agg_item_charsets_for_comparison()
     - Changing charset for Item_num-derived items
       from my_charset_bin to my_charset_numeric
       (which is an alias for latin1).
  @ sql/item_cmpfunc.cc
     - Using new helper functions
     - Other misc changes
  @ sql/item_cmpfunc.h
     - Fixing strcmp() to return max_length=2.
       Previously it returned 1, which was wrong,
       because it did not fit '-1'.
  @ sql/item_func.cc
     - Using new helper functions
     - Other minor changes
  @ sql/item_func.h
     - Removing unused functions
     - Adding helper functions
       agg_arg_charsets_for_string_result()
       agg_arg_charsets_for_comparison()
     - Adding set_numeric() into constructors of numeric items.
     - Using fix_length_and_charset() and fix_char_length()
       instead of direct write to max_length.
  @ sql/item_geofunc.cc
     - Changing class for Item_func_geometry_type and
       Item_func_as_wkt from Item_str_func to
       Item_str_ascii_func, to make them return UCS2 result
       properly (when character_set_connection=ucs2).
  @ sql/item_geofunc.h
     - Changing class for Item_func_geometry_type and
       Item_func_as_wkt from Item_str_func to
       Item_str_ascii_func, to make them return UCS2 result
       properly (when @@character_set_connection=ucs2).
  @ sql/item_strfunc.cc
     - Implementing Item_str_func::val_str().
     - Renaming val_str to val_str_ascii for some items,
       to make them work with UCS2 properly.
     - Using new helper functions
     - All single-argument functions that expect string
       result now call this method:
       agg_arg_charsets_for_string_result(collation, args, 1);
       This enables character set conversion to @@character_set_connection
       in case of pure numeric input.
  @ sql/item_strfunc.h
     - Introducing Item_str_ascii_func - for functions
       which return pure ASCII data, for performance purposes,
       as well as for the cases when the old implementation
       of val_str() was heavily 8-bit oriented and implementing
       a UCS2-aware version is tricky.
  @ sql/item_sum.cc
     - Using new helper functions.
  @ sql/item_timefunc.cc
     - Using my_charset_numeric instead of my_charset_bin.
     - Using fix_char_length(), fix_length_and_charset()
       and fix_length_and_charset_datetime()
       instead of direct write to max_length.
     - Using tricky-charset aware function str_to_time_with_warn()
  @ sql/item_timefunc.h
     - Using new helper functions for charset and length initialization.
     - Changing base class for Item_func_get_format() to make
       it return UCS2 properly (when character_set_connection=ucs2).
  @ sql/item_xmlfunc.cc
     - Using new helper function
  @ sql/my_decimal.cc
     - Adding a new DECIMAL to CHAR converter
       with real multibyte support (e.g. UCS2)

  @ sql/mysql_priv.h
     - Introducing a new derivation level for numeric/datetime data types.
     - Adding macros for my_charset_numeric and MY_REPERTOIRE_NUMERIC.
     - Adding prototypes for str_set_decimal()
     - Adding prototypes for character-set aware str_to_xxx() functions.
  @ sql/protocol.cc
     - Changing charsetnr to "binary" client-side metadata for
       numeric/datetime data types.
  @ sql/time.cc
     - Adding to_ascii() helper function, to convert a string
       in any character set to ascii representation. In the
       future can be extended to understand digits written
       in various non-Latin word scripts.
     - Adding real multy-byte character set aware versions for str_to_XXXX,
       to make these these type of queries work correct:
         INSERT INTO t1 SET datetime_column=ucs2_expression;
   @  strings/ctype-ucs2.c
     - endptr was not calculated correctly. INSERTing of UCS2
       values into numeric columns returned warnings about
       truncated wrong data.

1 files changed, 33 insertions, 40 deletions

diff --git a/sql/item_timefunc.h b/sql/item_timefunc.h
index 860bd983184..20e4d6488d6 100644
--- a/sql/item_timefunc.h
+++ b/sql/item_timefunc.h
@@ -122,23 +122,22 @@ public:
 class Item_func_month :public Item_func
 {
 public:
-  Item_func_month(Item *a) :Item_func(a) {}
+  Item_func_month(Item *a) :Item_func(a) { collation.set_numeric(); }
   longlong val_int();
   double val_real()
   { DBUG_ASSERT(fixed == 1); return (double) Item_func_month::val_int(); }
   String *val_str(String *str) 
   {
-    str->set(val_int(), &my_charset_bin);
+    str->set(val_int(), collation.collation);
     return null_value ? 0 : str;
   }
   const char *func_name() const { return "month"; }
   enum Item_result result_type () const { return INT_RESULT; }
   void fix_length_and_dec() 
   { 
-    collation.set(&my_charset_bin);
-    decimals=0;
-    max_length=2*MY_CHARSET_BIN_MB_MAXLEN;
-    maybe_null=1; 
+    decimals= 0;
+    fix_char_length(2);
+    maybe_null= 1;
   }
   bool check_partition_func_processor(uchar *int_arg) {return FALSE;}
 };
@@ -165,9 +164,9 @@ public:
   const char *func_name() const { return "dayofyear"; }
   void fix_length_and_dec() 
   { 
-    decimals=0;
-    max_length=3*MY_CHARSET_BIN_MB_MAXLEN;
-    maybe_null=1; 
+    decimals= 0;
+    fix_char_length(3);
+    maybe_null= 1;
   }
   bool check_partition_func_processor(uchar *int_arg) {return FALSE;}
 };
@@ -290,7 +289,7 @@ class Item_func_weekday :public Item_func
   bool odbc_type;
 public:
   Item_func_weekday(Item *a,bool type_arg)
-    :Item_func(a), odbc_type(type_arg) {}
+    :Item_func(a), odbc_type(type_arg) { collation.set_numeric(); }
   longlong val_int();
   double val_real() { DBUG_ASSERT(fixed == 1); return (double) val_int(); }
   String *val_str(String *str)
@@ -306,10 +305,9 @@ public:
   enum Item_result result_type () const { return INT_RESULT; }
   void fix_length_and_dec()
   {
-    collation.set(&my_charset_bin);
-    decimals=0;
-    max_length=1*MY_CHARSET_BIN_MB_MAXLEN;
-    maybe_null=1;
+    decimals= 0;
+    fix_char_length(1);
+    maybe_null= 1;
   }
   bool check_partition_func_processor(uchar *int_arg) {return FALSE;}
 };
@@ -379,15 +377,15 @@ public:
   Item_date(Item *a) :Item_func(a) {}
   enum Item_result result_type () const { return STRING_RESULT; }
   enum_field_types field_type() const { return MYSQL_TYPE_DATE; }
+  CHARSET_INFO *charset_for_protocol(void) const { return &my_charset_bin; }
   String *val_str(String *str);
   longlong val_int();
   double val_real() { return val_real_from_decimal(); }
   const char *func_name() const { return "date"; }
   void fix_length_and_dec()
   { 
-    collation.set(&my_charset_bin);
-    decimals=0;
-    max_length=MAX_DATE_WIDTH*MY_CHARSET_BIN_MB_MAXLEN;
+    decimals= 0;
+    fix_length_and_charset_datetime(MAX_DATE_WIDTH);
   }
   Field *tmp_table_field(TABLE *table)
   {
@@ -414,6 +412,7 @@ public:
   Item_date_func(Item *a,Item *b) :Item_str_func(a,b) {}
   Item_date_func(Item *a,Item *b, Item *c) :Item_str_func(a,b,c) {}
   enum_field_types field_type() const { return MYSQL_TYPE_DATETIME; }
+  CHARSET_INFO *charset_for_protocol(void) const { return &my_charset_bin; }
   Field *tmp_table_field(TABLE *table)
   {
     return tmp_table_field_from_field_type(table, 0);
@@ -440,10 +439,11 @@ public:
   Item_str_timefunc(Item *a,Item *b) :Item_str_func(a,b) {}
   Item_str_timefunc(Item *a, Item *b, Item *c) :Item_str_func(a, b ,c) {}
   enum_field_types field_type() const { return MYSQL_TYPE_TIME; }
+  CHARSET_INFO *charset_for_protocol(void) const { return &my_charset_bin; }
   void fix_length_and_dec()
   {
     decimals= DATETIME_DEC;
-    max_length=MAX_TIME_WIDTH*MY_CHARSET_BIN_MB_MAXLEN;
+    fix_length_and_charset_datetime(MAX_TIME_WIDTH);
   }
   Field *tmp_table_field(TABLE *table)
   {
@@ -701,7 +701,6 @@ public:
   void fix_length_and_dec()
   { 
     Item_str_timefunc::fix_length_and_dec();
-    collation.set(&my_charset_bin);
     maybe_null=1;
   }
   const char *func_name() const { return "sec_to_time"; }
@@ -774,13 +773,7 @@ public:
 class Item_typecast_maybe_null :public Item_typecast
 {
 public:
-  Item_typecast_maybe_null(Item *a) :Item_typecast(a) {}
-  void fix_length_and_dec()
-  {
-    collation.set(&my_charset_bin);
-    max_length=args[0]->max_length;
-    maybe_null= 1;
-  }
+  Item_typecast_maybe_null(Item *a) :Item_typecast(a) { maybe_null= 1; }
 };
 
 
@@ -813,16 +806,12 @@ public:
   bool get_time(MYSQL_TIME *ltime);
   const char *cast_type() const { return "date"; }
   enum_field_types field_type() const { return MYSQL_TYPE_DATE; }
+  CHARSET_INFO *charset_for_protocol(void) const { return &my_charset_bin; }
   Field *tmp_table_field(TABLE *table)
   {
     return tmp_table_field_from_field_type(table, 0);
-  }  
-  void fix_length_and_dec()
-  {
-    collation.set(&my_charset_bin);
-    max_length= 10;
-    maybe_null= 1;
   }
+  void fix_length_and_dec() { fix_length_and_charset_datetime(10); }
   bool result_as_longlong() { return TRUE; }
   longlong val_int();
   double val_real() { return (double) val_int(); }
@@ -847,6 +836,7 @@ public:
   bool get_time(MYSQL_TIME *ltime);
   const char *cast_type() const { return "time"; }
   enum_field_types field_type() const { return MYSQL_TYPE_TIME; }
+  CHARSET_INFO *charset_for_protocol(void) const { return &my_charset_bin; }
   Field *tmp_table_field(TABLE *table)
   {
     return tmp_table_field_from_field_type(table, 0);
@@ -863,6 +853,8 @@ public:
   {
     return save_time_in_field(field);
   }
+  void fix_length_and_dec()
+  { fix_length_and_charset_datetime(args[0]->max_char_length()); }
 };
 
 
@@ -874,15 +866,14 @@ public:
   String *val_str(String *str);
   const char *cast_type() const { return "datetime"; }
   enum_field_types field_type() const { return MYSQL_TYPE_DATETIME; }
+  CHARSET_INFO *charset_for_protocol(void) const { return &my_charset_bin; }
   Field *tmp_table_field(TABLE *table)
   {
     return tmp_table_field_from_field_type(table, 0);
   }
   void fix_length_and_dec()
   {
-    collation.set(&my_charset_bin);
-    maybe_null= 1;
-    max_length= MAX_DATETIME_FULL_WIDTH * MY_CHARSET_BIN_MB_MAXLEN;
+    fix_length_and_charset_datetime(MAX_DATETIME_FULL_WIDTH);
     decimals= DATETIME_DEC;
   }
   bool result_as_longlong() { return TRUE; }
@@ -907,10 +898,11 @@ public:
   String *val_str(String *str);
   const char *func_name() const { return "makedate"; }
   enum_field_types field_type() const { return MYSQL_TYPE_DATE; }
+  CHARSET_INFO *charset_for_protocol(void) const { return &my_charset_bin; }
   void fix_length_and_dec()
   { 
     decimals=0;
-    max_length=MAX_DATE_WIDTH*MY_CHARSET_BIN_MB_MAXLEN;
+    fix_length_and_charset_datetime(MAX_DATE_WIDTH);
     maybe_null= 1;
   }
   longlong val_int();
@@ -929,6 +921,7 @@ public:
   String *val_str(String *str);
   enum_field_types field_type() const { return cached_field_type; }
   void fix_length_and_dec();
+  CHARSET_INFO *charset_for_protocol(void) const { return &my_charset_bin; }
 
   Field *tmp_table_field(TABLE *table)
   {
@@ -1019,20 +1012,20 @@ enum date_time_format
   USA_FORMAT, JIS_FORMAT, ISO_FORMAT, EUR_FORMAT, INTERNAL_FORMAT
 };
 
-class Item_func_get_format :public Item_str_func
+class Item_func_get_format :public Item_str_ascii_func
 {
 public:
   const timestamp_type type; // keep it public
   Item_func_get_format(timestamp_type type_arg, Item *a)
-    :Item_str_func(a), type(type_arg)
+    :Item_str_ascii_func(a), type(type_arg)
   {}
-  String *val_str(String *str);
+  String *val_str_ascii(String *str);
   const char *func_name() const { return "get_format"; }
   void fix_length_and_dec()
   {
     maybe_null= 1;
     decimals=0;
-    max_length=17*MY_CHARSET_BIN_MB_MAXLEN;
+    fix_length_and_charset(17, default_charset());
   }
   virtual void print(String *str, enum_query_type query_type);
 };