aboutsummaryrefslogtreecommitdiff
path: root/src/backend/utils/adt/pg_locale_builtin.c
diff options
context:
space:
mode:
authorJeff Davis <jdavis@postgresql.org>2025-07-01 07:42:39 -0700
committerJeff Davis <jdavis@postgresql.org>2025-07-01 07:44:47 -0700
commit5a38104b364234615c780656a8b2424f96ed9efa (patch)
tree3bdd0dc7532db1cfa646d5397b2bf095ef3d9e98 /src/backend/utils/adt/pg_locale_builtin.c
parentd81dcc8d6243054e3bde40c6fb2b2a0be4b19da6 (diff)
downloadpostgresql-5a38104b364234615c780656a8b2424f96ed9efa.tar.gz
postgresql-5a38104b364234615c780656a8b2424f96ed9efa.zip
Control ctype behavior internally with a method table.
Previously, pattern matching and case mapping behavior branched based on the provider. Refactor to use a method table, which is less error-prone. This is also a step toward multiple provider versions, which we may want to support in the future. Reviewed-by: Andreas Karlsson <andreas@proxel.se> Reviewed-by: Peter Eisentraut <peter@eisentraut.org> Discussion: https://postgr.es/m/2830211e1b6e6a2e26d845780b03e125281ea17b.camel%40j-davis.com
Diffstat (limited to 'src/backend/utils/adt/pg_locale_builtin.c')
-rw-r--r--src/backend/utils/adt/pg_locale_builtin.c111
1 files changed, 98 insertions, 13 deletions
diff --git a/src/backend/utils/adt/pg_locale_builtin.c b/src/backend/utils/adt/pg_locale_builtin.c
index ce4914a76a1..0b275d0836b 100644
--- a/src/backend/utils/adt/pg_locale_builtin.c
+++ b/src/backend/utils/adt/pg_locale_builtin.c
@@ -24,15 +24,6 @@
extern pg_locale_t create_pg_locale_builtin(Oid collid,
MemoryContext context);
extern char *get_collation_actual_version_builtin(const char *collcollate);
-extern size_t strlower_builtin(char *dest, size_t destsize, const char *src,
- ssize_t srclen, pg_locale_t locale);
-extern size_t strtitle_builtin(char *dest, size_t destsize, const char *src,
- ssize_t srclen, pg_locale_t locale);
-extern size_t strupper_builtin(char *dest, size_t destsize, const char *src,
- ssize_t srclen, pg_locale_t locale);
-extern size_t strfold_builtin(char *dest, size_t destsize, const char *src,
- ssize_t srclen, pg_locale_t locale);
-
struct WordBoundaryState
{
@@ -76,7 +67,7 @@ initcap_wbnext(void *state)
return wbstate->len;
}
-size_t
+static size_t
strlower_builtin(char *dest, size_t destsize, const char *src, ssize_t srclen,
pg_locale_t locale)
{
@@ -84,7 +75,7 @@ strlower_builtin(char *dest, size_t destsize, const char *src, ssize_t srclen,
locale->info.builtin.casemap_full);
}
-size_t
+static size_t
strtitle_builtin(char *dest, size_t destsize, const char *src, ssize_t srclen,
pg_locale_t locale)
{
@@ -102,7 +93,7 @@ strtitle_builtin(char *dest, size_t destsize, const char *src, ssize_t srclen,
initcap_wbnext, &wbstate);
}
-size_t
+static size_t
strupper_builtin(char *dest, size_t destsize, const char *src, ssize_t srclen,
pg_locale_t locale)
{
@@ -110,7 +101,7 @@ strupper_builtin(char *dest, size_t destsize, const char *src, ssize_t srclen,
locale->info.builtin.casemap_full);
}
-size_t
+static size_t
strfold_builtin(char *dest, size_t destsize, const char *src, ssize_t srclen,
pg_locale_t locale)
{
@@ -118,6 +109,98 @@ strfold_builtin(char *dest, size_t destsize, const char *src, ssize_t srclen,
locale->info.builtin.casemap_full);
}
+static bool
+wc_isdigit_builtin(pg_wchar wc, pg_locale_t locale)
+{
+ return pg_u_isdigit(wc, !locale->info.builtin.casemap_full);
+}
+
+static bool
+wc_isalpha_builtin(pg_wchar wc, pg_locale_t locale)
+{
+ return pg_u_isalpha(wc);
+}
+
+static bool
+wc_isalnum_builtin(pg_wchar wc, pg_locale_t locale)
+{
+ return pg_u_isalnum(wc, !locale->info.builtin.casemap_full);
+}
+
+static bool
+wc_isupper_builtin(pg_wchar wc, pg_locale_t locale)
+{
+ return pg_u_isupper(wc);
+}
+
+static bool
+wc_islower_builtin(pg_wchar wc, pg_locale_t locale)
+{
+ return pg_u_islower(wc);
+}
+
+static bool
+wc_isgraph_builtin(pg_wchar wc, pg_locale_t locale)
+{
+ return pg_u_isgraph(wc);
+}
+
+static bool
+wc_isprint_builtin(pg_wchar wc, pg_locale_t locale)
+{
+ return pg_u_isprint(wc);
+}
+
+static bool
+wc_ispunct_builtin(pg_wchar wc, pg_locale_t locale)
+{
+ return pg_u_ispunct(wc, !locale->info.builtin.casemap_full);
+}
+
+static bool
+wc_isspace_builtin(pg_wchar wc, pg_locale_t locale)
+{
+ return pg_u_isspace(wc);
+}
+
+static bool
+char_is_cased_builtin(char ch, pg_locale_t locale)
+{
+ return IS_HIGHBIT_SET(ch) ||
+ (ch >= 'A' && ch <= 'Z') || (ch >= 'a' && ch <= 'z');
+}
+
+static pg_wchar
+wc_toupper_builtin(pg_wchar wc, pg_locale_t locale)
+{
+ return unicode_uppercase_simple(wc);
+}
+
+static pg_wchar
+wc_tolower_builtin(pg_wchar wc, pg_locale_t locale)
+{
+ return unicode_lowercase_simple(wc);
+}
+
+static const struct ctype_methods ctype_methods_builtin = {
+ .strlower = strlower_builtin,
+ .strtitle = strtitle_builtin,
+ .strupper = strupper_builtin,
+ .strfold = strfold_builtin,
+ .wc_isdigit = wc_isdigit_builtin,
+ .wc_isalpha = wc_isalpha_builtin,
+ .wc_isalnum = wc_isalnum_builtin,
+ .wc_isupper = wc_isupper_builtin,
+ .wc_islower = wc_islower_builtin,
+ .wc_isgraph = wc_isgraph_builtin,
+ .wc_isprint = wc_isprint_builtin,
+ .wc_ispunct = wc_ispunct_builtin,
+ .wc_isspace = wc_isspace_builtin,
+ .char_is_cased = char_is_cased_builtin,
+ .wc_tolower = wc_tolower_builtin,
+ .wc_toupper = wc_toupper_builtin,
+};
+
pg_locale_t
create_pg_locale_builtin(Oid collid, MemoryContext context)
{
@@ -161,6 +244,8 @@ create_pg_locale_builtin(Oid collid, MemoryContext context)
result->deterministic = true;
result->collate_is_c = true;
result->ctype_is_c = (strcmp(locstr, "C") == 0);
+ if (!result->ctype_is_c)
+ result->ctype = &ctype_methods_builtin;
return result;
}