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, 19 insertions, 15 deletions

diff --git a/sql/item_cmpfunc.cc b/sql/item_cmpfunc.cc
index 1da383ce3e9..db4a55bbcd0 100644
--- a/sql/item_cmpfunc.cc
+++ b/sql/item_cmpfunc.cc
@@ -483,7 +483,7 @@ void Item_bool_func2::fix_length_and_dec()
   DTCollation coll;
   if (args[0]->result_type() == STRING_RESULT &&
       args[1]->result_type() == STRING_RESULT &&
-      agg_arg_charsets(coll, args, 2, MY_COLL_CMP_CONV, 1))
+      agg_arg_charsets_for_comparison(coll, args, 2))
     return;
     
   args[0]->cmp_context= args[1]->cmp_context=
@@ -934,6 +934,7 @@ int Arg_comparator::set_cmp_func(Item_result_field *owner_arg,
     func= &Arg_comparator::compare_datetime;
     get_value_a_func= &get_datetime_value;
     get_value_b_func= &get_datetime_value;
+    cmp_collation.set(&my_charset_numeric);
     return 0;
   }
   else if (type == STRING_RESULT && (*a)->field_type() == MYSQL_TYPE_TIME &&
@@ -2173,7 +2174,7 @@ void Item_func_between::fix_length_and_dec()
   if ( agg_cmp_type(&cmp_type, args, 3))
     return;
   if (cmp_type == STRING_RESULT &&
-      agg_arg_charsets(cmp_collation, args, 3, MY_COLL_CMP_CONV, 1))
+      agg_arg_charsets_for_comparison(cmp_collation, args, 3))
    return;
 
   /*
@@ -2374,7 +2375,7 @@ Item_func_ifnull::fix_length_and_dec()
 
   switch (hybrid_type) {
   case STRING_RESULT:
-    agg_arg_charsets(collation, args, arg_count, MY_COLL_CMP_CONV, 1);
+    agg_arg_charsets_for_comparison(collation, args, arg_count);
     break;
   case DECIMAL_RESULT:
   case REAL_RESULT:
@@ -2549,12 +2550,12 @@ Item_func_if::fix_length_and_dec()
     agg_result_type(&cached_result_type, args+1, 2);
     if (cached_result_type == STRING_RESULT)
     {
-      if (agg_arg_charsets(collation, args+1, 2, MY_COLL_ALLOW_CONV, 1))
+      if (agg_arg_charsets_for_string_result(collation, args + 1, 2))
         return;
     }
     else
     {
-      collation.set(&my_charset_bin);	// Number
+      collation.set_numeric(); // Number
     }
     cached_field_type= agg_field_type(args + 1, 2);
   }
@@ -2640,7 +2641,7 @@ Item_func_nullif::fix_length_and_dec()
     unsigned_flag= args[0]->unsigned_flag;
     cached_result_type= args[0]->result_type();
     if (cached_result_type == STRING_RESULT &&
-        agg_arg_charsets(collation, args, arg_count, MY_COLL_CMP_CONV, 1))
+        agg_arg_charsets_for_comparison(collation, args, arg_count))
       return;
   }
 }
@@ -2917,9 +2918,13 @@ void Item_func_case::fix_length_and_dec()
     agg[nagg++]= args[else_expr_num];
   
   agg_result_type(&cached_result_type, agg, nagg);
-  if ((cached_result_type == STRING_RESULT) &&
-      agg_arg_charsets(collation, agg, nagg, MY_COLL_ALLOW_CONV, 1))
-    return;
+  if (cached_result_type == STRING_RESULT)
+  {
+    if (agg_arg_charsets_for_string_result(collation, agg, nagg))
+      return;
+  }
+  else
+    collation.set_numeric();
   
   cached_field_type= agg_field_type(agg, nagg);
   /*
@@ -2944,7 +2949,7 @@ void Item_func_case::fix_length_and_dec()
       {
         DBUG_ASSERT((Item_result)i != ROW_RESULT);
         if ((Item_result)i == STRING_RESULT &&
-            agg_arg_charsets(cmp_collation, agg, nagg, MY_COLL_CMP_CONV, 1))
+            agg_arg_charsets_for_comparison(cmp_collation, agg, nagg))
           return;
         if (!(cmp_items[i]=
             cmp_item::get_comparator((Item_result)i,
@@ -3107,7 +3112,7 @@ void Item_func_coalesce::fix_length_and_dec()
   case STRING_RESULT:
     count_only_length();
     decimals= NOT_FIXED_DEC;
-    agg_arg_charsets(collation, args, arg_count, MY_COLL_ALLOW_CONV, 1);
+    agg_arg_charsets_for_string_result(collation, args, arg_count);
     break;
   case DECIMAL_RESULT:
     count_decimal_length();
@@ -3752,7 +3757,7 @@ void Item_func_in::fix_length_and_dec()
   if (type_cnt == 1)
   {
     if (cmp_type == STRING_RESULT && 
-        agg_arg_charsets(cmp_collation, args, arg_count, MY_COLL_CMP_CONV, 1))
+        agg_arg_charsets_for_comparison(cmp_collation, args, arg_count))
       return;
     arg_types_compatible= TRUE;
   }
@@ -3930,8 +3935,7 @@ void Item_func_in::fix_length_and_dec()
         if (found_types & (1 << i) && !cmp_items[i])
         {
           if ((Item_result)i == STRING_RESULT &&
-              agg_arg_charsets(cmp_collation, args, arg_count,
-                               MY_COLL_CMP_CONV, 1))
+              agg_arg_charsets_for_comparison(cmp_collation, args, arg_count))
             return;
           if (!cmp_items[i] && !(cmp_items[i]=
               cmp_item::get_comparator((Item_result)i,
@@ -4762,7 +4766,7 @@ Item_func_regex::fix_fields(THD *thd, Item **ref)
   max_length= 1;
   decimals= 0;
 
-  if (agg_arg_charsets(cmp_collation, args, 2, MY_COLL_CMP_CONV, 1))
+  if (agg_arg_charsets_for_comparison(cmp_collation, args, 2))
     return TRUE;
 
   regex_lib_flags= (cmp_collation.collation->state &