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, 45 insertions, 29 deletions

diff --git a/sql/item_strfunc.h b/sql/item_strfunc.h
index 09a7da021c0..c9d62ac1052 100644
--- a/sql/item_strfunc.h
+++ b/sql/item_strfunc.h
@@ -41,28 +41,41 @@ public:
   bool fix_fields(THD *thd, Item **ref);
 };
 
-class Item_func_md5 :public Item_str_func
+
+
+/*
+  Functions that return values with ASCII repertoire
+*/
+class Item_str_ascii_func :public Item_str_func
+{
+  String ascii_buf;
+public:
+  Item_str_ascii_func() :Item_str_func() {}
+  Item_str_ascii_func(Item *a) :Item_str_func(a) {}
+  Item_str_ascii_func(Item *a,Item *b) :Item_str_func(a,b) {}
+  Item_str_ascii_func(Item *a,Item *b,Item *c) :Item_str_func(a,b,c) {}
+  String *val_str_convert_from_ascii(String *str, String *ascii_buf);
+  String *val_str(String *str);
+  virtual String *val_str_ascii(String *)= 0;
+};
+
+
+class Item_func_md5 :public Item_str_ascii_func
 {
   String tmp_value;
 public:
-  Item_func_md5(Item *a) :Item_str_func(a)
-  {
-    collation.set(&my_charset_bin);
-  }
-  String *val_str(String *);
+  Item_func_md5(Item *a) :Item_str_ascii_func(a) {}
+  String *val_str_ascii(String *);
   void fix_length_and_dec();
   const char *func_name() const { return "md5"; }
 };
 
 
-class Item_func_sha :public Item_str_func
+class Item_func_sha :public Item_str_ascii_func
 {
 public:
-  Item_func_sha(Item *a) :Item_str_func(a)
-  {
-    collation.set(&my_charset_bin);
-  }
-  String *val_str(String *);    
+  Item_func_sha(Item *a) :Item_str_ascii_func(a) {}
+  String *val_str_ascii(String *);    
   void fix_length_and_dec();      
   const char *func_name() const { return "sha"; }	
 };
@@ -263,13 +276,16 @@ public:
   authentication procedure works, see comments in password.c.
 */
 
-class Item_func_password :public Item_str_func
+class Item_func_password :public Item_str_ascii_func
 {
   char tmp_value[SCRAMBLED_PASSWORD_CHAR_LENGTH+1]; 
 public:
-  Item_func_password(Item *a) :Item_str_func(a) {}
-  String *val_str(String *str);
-  void fix_length_and_dec() { max_length= SCRAMBLED_PASSWORD_CHAR_LENGTH; }
+  Item_func_password(Item *a) :Item_str_ascii_func(a) {}
+  String *val_str_ascii(String *str);
+  void fix_length_and_dec()
+  {
+    fix_length_and_charset(SCRAMBLED_PASSWORD_CHAR_LENGTH, default_charset());
+  }
   const char *func_name() const { return "password"; }
   static char *alloc(THD *thd, const char *password, size_t pass_len);
 };
@@ -282,13 +298,16 @@ public:
   function.
 */
 
-class Item_func_old_password :public Item_str_func
+class Item_func_old_password :public Item_str_ascii_func
 {
   char tmp_value[SCRAMBLED_PASSWORD_CHAR_LENGTH_323+1];
 public:
-  Item_func_old_password(Item *a) :Item_str_func(a) {}
-  String *val_str(String *str);
-  void fix_length_and_dec() { max_length= SCRAMBLED_PASSWORD_CHAR_LENGTH_323; } 
+  Item_func_old_password(Item *a) :Item_str_ascii_func(a) {}
+  String *val_str_ascii(String *str);
+  void fix_length_and_dec()
+  {
+    fix_length_and_charset(SCRAMBLED_PASSWORD_CHAR_LENGTH_323, default_charset());
+  } 
   const char *func_name() const { return "old_password"; }
   static char *alloc(THD *thd, const char *password, size_t pass_len);
 };
@@ -688,7 +707,7 @@ public:
   void fix_length_and_dec() 
   { 
     decimals= 0; 
-    max_length= 3 * 8 + 7; 
+    fix_length_and_charset(3 * 8 + 7, default_charset()); 
     maybe_null= 1;
   }
 };
@@ -848,14 +867,11 @@ class Item_func_uuid: public Item_str_func
 {
 public:
   Item_func_uuid(): Item_str_func() {}
-  void fix_length_and_dec() {
-    collation.set(system_charset_info);
-    /*
-       NOTE! uuid() should be changed to use 'ascii'
-       charset when hex(), format(), md5(), etc, and implicit
-       number-to-string conversion will use 'ascii'
-    */
-    max_length= UUID_LENGTH * system_charset_info->mbmaxlen;
+  void fix_length_and_dec()
+  {
+    collation.set(system_charset_info,
+                  DERIVATION_COERCIBLE, MY_REPERTOIRE_ASCII);
+    fix_char_length(UUID_LENGTH);
   }
   const char *func_name() const{ return "uuid"; }
   String *val_str(String *);