LDML refactoring for "MDEV-9711 NO PAD collations"

- Moving detection of the MY_CS_CSSORT, MY_CS_PUREASCII, MY_CS_NONASCII
  flags of loadable collations from add_collation() in mysys.c
  to my_cset_init_8bit() and my_coll_init_simple() in ctype-simple.c.

- Adding tests that these flags are set properly for loadable collations

- Moving LDML test related *.xml files from mysql-test/std_data/
  to mysql-test/std_data/ldml/, as there will be more *.xml test files

4 files changed, 82 insertions, 53 deletions

diff --git a/strings/conf_to_src.c b/strings/conf_to_src.c
index 5b9793f388d..31093fe4230 100644
--- a/strings/conf_to_src.c
+++ b/strings/conf_to_src.c
@@ -193,25 +193,19 @@ static int my_read_charset_file(const char *filename)
   return FALSE;
 }
 
-static int
-is_case_sensitive(CHARSET_INFO *cs)
-{
- return (cs->sort_order &&
-         cs->sort_order['A'] < cs->sort_order['a'] &&
-         cs->sort_order['a'] < cs->sort_order['B']) ? 1 : 0;
-}
-
 
 void dispcset(FILE *f,CHARSET_INFO *cs)
 {
+  uint flags= my_8bit_charset_flags_from_data(cs) |
+              my_8bit_collation_flags_from_data(cs);
   fprintf(f,"{\n");
   fprintf(f,"  %d,%d,%d,\n",cs->number,0,0);
   fprintf(f,"  MY_CS_COMPILED%s%s%s%s%s,\n",
           cs->state & MY_CS_BINSORT         ? "|MY_CS_BINSORT"   : "",
           cs->state & MY_CS_PRIMARY         ? "|MY_CS_PRIMARY"   : "",
-          is_case_sensitive(cs)             ? "|MY_CS_CSSORT"    : "",
-          my_charset_is_8bit_pure_ascii(cs) ? "|MY_CS_PUREASCII" : "",
-          !my_charset_is_ascii_compatible(cs) ? "|MY_CS_NONASCII": "");
+          flags & MY_CS_CSSORT              ? "|MY_CS_CSSORT"    : "",
+          flags & MY_CS_PUREASCII           ? "|MY_CS_PUREASCII" : "",
+          flags & MY_CS_NONASCII            ? "|MY_CS_NONASCII"  : "");
   
   if (cs->name)
   {
diff --git a/strings/ctype-simple.c b/strings/ctype-simple.c
index f405c4f327b..e6cea06b17b 100644
--- a/strings/ctype-simple.c
+++ b/strings/ctype-simple.c
@@ -1340,9 +1340,80 @@ create_fromuni(struct charset_info_st *cs,
   return FALSE;
 }
 
+
+/*
+  Detect if a character set is 8bit,
+  and it is pure ascii, i.e. doesn't have
+  characters outside U+0000..U+007F
+  This functions is shared between "conf_to_src"
+  and dynamic charsets loader in "mysqld".
+*/
+static my_bool
+my_charset_is_8bit_pure_ascii(CHARSET_INFO *cs)
+{
+  size_t code;
+  if (!cs->tab_to_uni)
+    return 0;
+  for (code= 0; code < 256; code++)
+  {
+    if (cs->tab_to_uni[code] > 0x7F)
+      return 0;
+  }
+  return 1;
+}
+
+
+/*
+  Shared function between conf_to_src and mysys.
+  Check if a 8bit character set is compatible with
+  ascii on the range 0x00..0x7F.
+*/
+static my_bool
+my_charset_is_ascii_compatible(CHARSET_INFO *cs)
+{
+  uint i;
+  if (!cs->tab_to_uni)
+    return 1;
+  for (i= 0; i < 128; i++)
+  {
+    if (cs->tab_to_uni[i] != i)
+      return 0;
+  }
+  return 1;
+}
+
+
+uint my_8bit_charset_flags_from_data(CHARSET_INFO *cs)
+{
+  uint flags= 0;
+  if (my_charset_is_8bit_pure_ascii(cs))
+    flags|= MY_CS_PUREASCII;
+  if (!my_charset_is_ascii_compatible(cs))
+    flags|= MY_CS_NONASCII;
+  return flags;
+}
+
+
+/*
+  Check if case sensitive sort order: A < a < B.
+  We need MY_CS_FLAG for regex library, and for
+  case sensitivity flag for 5.0 client protocol,
+  to support isCaseSensitive() method in JDBC driver
+*/
+uint my_8bit_collation_flags_from_data(CHARSET_INFO *cs)
+{
+  uint flags= 0;
+  if (cs->sort_order && cs->sort_order['A'] < cs->sort_order['a'] &&
+                        cs->sort_order['a'] < cs->sort_order['B'])
+    flags|= MY_CS_CSSORT;
+  return flags;
+}
+
+
 static my_bool
 my_cset_init_8bit(struct charset_info_st *cs, MY_CHARSET_LOADER *loader)
 {
+  cs->state|= my_8bit_charset_flags_from_data(cs);
   cs->caseup_multiply= 1;
   cs->casedn_multiply= 1;
   cs->pad_char= ' ';
@@ -1371,6 +1442,7 @@ static void set_max_sort_char(struct charset_info_st *cs)
 static my_bool my_coll_init_simple(struct charset_info_st *cs,
                                    MY_CHARSET_LOADER *loader __attribute__((unused)))
 {
+  cs->state|= my_8bit_collation_flags_from_data(cs);
   set_max_sort_char(cs);
   return FALSE;
 }
diff --git a/strings/ctype.c b/strings/ctype.c
index 620c7e13503..be8a8cb506e 100644
--- a/strings/ctype.c
+++ b/strings/ctype.c
@@ -974,48 +974,6 @@ my_charset_is_ascii_based(CHARSET_INFO *cs)
 
 
 /*
-  Detect if a character set is 8bit,
-  and it is pure ascii, i.e. doesn't have
-  characters outside U+0000..U+007F
-  This functions is shared between "conf_to_src"
-  and dynamic charsets loader in "mysqld".
-*/
-my_bool
-my_charset_is_8bit_pure_ascii(CHARSET_INFO *cs)
-{
-  size_t code;
-  if (!cs->tab_to_uni)
-    return 0;
-  for (code= 0; code < 256; code++)
-  {
-    if (cs->tab_to_uni[code] > 0x7F)
-      return 0;
-  }
-  return 1;
-}
-
-
-/*
-  Shared function between conf_to_src and mysys.
-  Check if a 8bit character set is compatible with
-  ascii on the range 0x00..0x7F.
-*/
-my_bool
-my_charset_is_ascii_compatible(CHARSET_INFO *cs)
-{
-  uint i;
-  if (!cs->tab_to_uni)
-    return 1;
-  for (i= 0; i < 128; i++)
-  {
-    if (cs->tab_to_uni[i] != i)
-      return 0;
-  }
-  return 1;
-}
-
-
-/*
   Convert a string between two character sets.
   'to' must be large enough to store (form_length * to_cs->mbmaxlen) bytes.
 
diff --git a/strings/strings_def.h b/strings/strings_def.h
index fb280b6bb6b..36d3d2b2fe9 100644
--- a/strings/strings_def.h
+++ b/strings/strings_def.h
@@ -101,6 +101,11 @@ static inline const uchar *skip_trailing_space(const uchar *ptr,size_t len)
   return (end);
 }
 
+
+uint my_8bit_charset_flags_from_data(CHARSET_INFO *cs);
+uint my_8bit_collation_flags_from_data(CHARSET_INFO *cs);
+
+
 /* Macros for hashing characters */
 
 #define MY_HASH_ADD(A, B, value) \