Make dmetaphone collation-aware

The dmetaphone() SQL function internally upper-cases the argument
string.  It did this using the toupper() function.  That way, it has a
dependency on the global LC_CTYPE locale setting, which we want to get
rid of.

The "double metaphone" algorithm specifically supports the "C with
cedilla" letter, so just using ASCII case conversion wouldn't work.

To fix that, use the passed-in collation and use the str_toupper()
function, which has full awareness of collations and collation
providers.

Note that this does not change the fact that this function only works
correctly with single-byte encodings.  The change to str_toupper()
makes the case conversion multibyte-enabled, but the rest of the
function is still not ready.

Reviewed-by: Jeff Davis <pgsql@j-davis.com>
Discussion: https://www.postgresql.org/message-id/108e07a2-0632-4f00-984d-fe0e0d0ec726%40eisentraut.org

diff --git a/contrib/fuzzystrmatch/dmetaphone.c b/contrib/fuzzystrmatch/dmetaphone.c
index 227d8b11ddca85f0b75d2522c0062b5799e418ca..062667527c2dad82a94b9044782b3d24772c154a 100644 (file)
--- a/contrib/fuzzystrmatch/dmetaphone.c
+++ b/contrib/fuzzystrmatch/dmetaphone.c
@@ -99,6 +99,7 @@ The remaining code is authored by Andrew Dunstan <amdunstan@ncshp.org> and
 #include "postgres.h"
 
 #include "utils/builtins.h"
+#include "utils/formatting.h"
 
 /* turn off assertions for embedded function */
 #define NDEBUG
@@ -117,7 +118,7 @@ The remaining code is authored by Andrew Dunstan <amdunstan@ncshp.org> and
 #include <ctype.h>
 
 /* prototype for the main function we got from the perl module */
-static void DoubleMetaphone(char *str, char **codes);
+static void DoubleMetaphone(const char *str, Oid collid, char **codes);
 
 #ifndef DMETAPHONE_MAIN
 
@@ -142,7 +143,7 @@ dmetaphone(PG_FUNCTION_ARGS)
        arg = PG_GETARG_TEXT_PP(0);
        aptr = text_to_cstring(arg);
 
-       DoubleMetaphone(aptr, codes);
+       DoubleMetaphone(aptr, PG_GET_COLLATION(), codes);
        code = codes[0];
        if (!code)
                code = "";
@@ -171,7 +172,7 @@ dmetaphone_alt(PG_FUNCTION_ARGS)
        arg = PG_GETARG_TEXT_PP(0);
        aptr = text_to_cstring(arg);
 
-       DoubleMetaphone(aptr, codes);
+       DoubleMetaphone(aptr, PG_GET_COLLATION(), codes);
        code = codes[1];
        if (!code)
                code = "";
@@ -278,13 +279,17 @@ IncreaseBuffer(metastring *s, int chars_needed)
 }
 
 
-static void
-MakeUpper(metastring *s)
+static metastring *
+MakeUpper(metastring *s, Oid collid)
 {
-       char       *i;
+       char       *newstr;
+       metastring *newms;
+
+       newstr = str_toupper(s->str, s->length, collid);
+       newms = NewMetaString(newstr);
+       DestroyMetaString(s);
 
-       for (i = s->str; *i; i++)
-               *i = toupper((unsigned char) *i);
+       return newms;
 }
 
 
@@ -392,7 +397,7 @@ MetaphAdd(metastring *s, const char *new_str)
 
 
 static void
-DoubleMetaphone(char *str, char **codes)
+DoubleMetaphone(const char *str, Oid collid, char **codes)
 {
        int                     length;
        metastring *original;
@@ -414,7 +419,7 @@ DoubleMetaphone(char *str, char **codes)
        primary->free_string_on_destroy = 0;
        secondary->free_string_on_destroy = 0;
 
-       MakeUpper(original);
+       original = MakeUpper(original, collid);
 
        /* skip these when at start of word */
        if (StringAt(original, 0, 2, "GN", "KN", "PN", "WR", "PS", ""))
@@ -1430,7 +1435,7 @@ main(int argc, char **argv)
 
        if (argc > 1)
        {
-               DoubleMetaphone(argv[1], codes);
+               DoubleMetaphone(argv[1], DEFAULT_COLLATION_OID, codes);
                printf("%s|%s\n", codes[0], codes[1]);
        }
 }