Avoid global LC_CTYPE dependency in pg_locale_icu.c.

ICU still depends on libc for compatibility with certain historical
behavior for single-byte encodings. Make the dependency explicit by
holding a locale_t object when required.

We should consider a better solution in the future, such as decoding
the text to UTF-32 and using u_tolower(). That would be a behavior
change and require additional infrastructure though; so for now, just
avoid the global LC_CTYPE dependency.

Reviewed-by: Chao Li <[email protected]>
Discussion: https://postgr.es/m/450ceb6260cad30d7afdf155d991a9caafee7c0d[email protected]

diff --git a/src/backend/utils/adt/pg_locale_icu.c b/src/backend/utils/adt/pg_locale_icu.c
index 69f22b47a68c1fb6c5aeb87869c9cd4cf75ab390..43d44fe43bdc408c3d0da66f97384c2a76e78f86 100644 (file)
--- a/src/backend/utils/adt/pg_locale_icu.c
+++ b/src/backend/utils/adt/pg_locale_icu.c
@@ -244,6 +244,29 @@ static const struct ctype_methods ctype_methods_icu = {
    .wc_toupper = toupper_icu,
    .wc_tolower = tolower_icu,
 };
+
+/*
+ * ICU still depends on libc for compatibility with certain historical
+ * behavior for single-byte encodings.  See downcase_ident_icu().
+ *
+ * XXX: consider fixing by decoding the single byte into a code point, and
+ * using u_tolower().
+ */
+static locale_t
+make_libc_ctype_locale(const char *ctype)
+{
+   locale_t    loc;
+
+#ifndef WIN32
+   loc = newlocale(LC_CTYPE_MASK, ctype, NULL);
+#else
+   loc = _create_locale(LC_ALL, ctype);
+#endif
+   if (!loc)
+       report_newlocale_failure(ctype);
+
+   return loc;
+}
 #endif
 
 pg_locale_t
@@ -254,6 +277,7 @@ create_pg_locale_icu(Oid collid, MemoryContext context)
    const char *iculocstr;
    const char *icurules = NULL;
    UCollator  *collator;
+   locale_t    loc = (locale_t) 0;
    pg_locale_t result;
 
    if (collid == DEFAULT_COLLATION_OID)
@@ -276,6 +300,18 @@ create_pg_locale_icu(Oid collid, MemoryContext context)
        if (!isnull)
            icurules = TextDatumGetCString(datum);
 
+       /* libc only needed for default locale and single-byte encoding */
+       if (pg_database_encoding_max_length() == 1)
+       {
+           const char *ctype;
+
+           datum = SysCacheGetAttrNotNull(DATABASEOID, tp,
+                                          Anum_pg_database_datctype);
+           ctype = TextDatumGetCString(datum);
+
+           loc = make_libc_ctype_locale(ctype);
+       }
+
        ReleaseSysCache(tp);
    }
    else
@@ -306,6 +342,7 @@ create_pg_locale_icu(Oid collid, MemoryContext context)
    result = MemoryContextAllocZero(context, sizeof(struct pg_locale_struct));
    result->icu.locale = MemoryContextStrdup(context, iculocstr);
    result->icu.ucol = collator;
+   result->icu.lt = loc;
    result->deterministic = deterministic;
    result->collate_is_c = false;
    result->ctype_is_c = false;
@@ -578,17 +615,19 @@ downcase_ident_icu(char *dst, size_t dstsize, const char *src,
                   ssize_t srclen, pg_locale_t locale)
 {
    int         i;
-   bool        enc_is_single_byte;
+   bool        libc_lower;
+   locale_t    lt = locale->icu.lt;
+
+   libc_lower = lt && (pg_database_encoding_max_length() == 1);
 
-   enc_is_single_byte = pg_database_encoding_max_length() == 1;
    for (i = 0; i < srclen && i < dstsize; i++)
    {
        unsigned char ch = (unsigned char) src[i];
 
        if (ch >= 'A' && ch <= 'Z')
            ch = pg_ascii_tolower(ch);
-       else if (enc_is_single_byte && IS_HIGHBIT_SET(ch) && isupper(ch))
-           ch = tolower(ch);
+       else if (libc_lower && IS_HIGHBIT_SET(ch) && isupper_l(ch, lt))
+           ch = tolower_l(ch, lt);
        dst[i] = (char) ch;
    }
 

diff --git a/src/include/utils/pg_locale.h b/src/include/utils/pg_locale.h
index 1e584819c5e9faad309266a247cf2333318b2dcc..86016b9344e4d981237f66d7c37cbdb2f0f988b4 100644 (file)
--- a/src/include/utils/pg_locale.h
+++ b/src/include/utils/pg_locale.h
@@ -167,6 +167,7 @@ struct pg_locale_struct
        {
            const char *locale;
            UCollator  *ucol;
+           locale_t    lt;
        }           icu;
 #endif
    };