summaryrefslogtreecommitdiff
path: root/src/backend/utils
diff options
context:
space:
mode:
Diffstat (limited to 'src/backend/utils')
-rw-r--r--src/backend/utils/adt/jsonpath_scan.l45
-rw-r--r--src/backend/utils/adt/xml.c24
-rw-r--r--src/backend/utils/mb/mbutils.c105
3 files changed, 117 insertions, 57 deletions
diff --git a/src/backend/utils/adt/jsonpath_scan.l b/src/backend/utils/adt/jsonpath_scan.l
index 70681b789d..be0a2cfa2f 100644
--- a/src/backend/utils/adt/jsonpath_scan.l
+++ b/src/backend/utils/adt/jsonpath_scan.l
@@ -486,13 +486,6 @@ hexval(char c)
static void
addUnicodeChar(int ch)
{
- /*
- * For UTF8, replace the escape sequence by the actual
- * utf8 character in lex->strval. Do this also for other
- * encodings if the escape designates an ASCII character,
- * otherwise raise an error.
- */
-
if (ch == 0)
{
/* We can't allow this, since our TEXT type doesn't */
@@ -501,40 +494,20 @@ addUnicodeChar(int ch)
errmsg("unsupported Unicode escape sequence"),
errdetail("\\u0000 cannot be converted to text.")));
}
- else if (GetDatabaseEncoding() == PG_UTF8)
- {
- char utf8str[5];
- int utf8len;
-
- unicode_to_utf8(ch, (unsigned char *) utf8str);
- utf8len = pg_utf_mblen((unsigned char *) utf8str);
- addstring(false, utf8str, utf8len);
- }
- else if (ch <= 0x007f)
- {
- /*
- * This is the only way to designate things like a
- * form feed character in JSON, so it's useful in all
- * encodings.
- */
- addchar(false, (char) ch);
- }
else
{
- ereport(ERROR,
- (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
- errmsg("invalid input syntax for type %s", "jsonpath"),
- errdetail("Unicode escape values cannot be used for code "
- "point values above 007F when the server encoding "
- "is not UTF8.")));
+ char cbuf[MAX_UNICODE_EQUIVALENT_STRING + 1];
+
+ pg_unicode_to_server(ch, (unsigned char *) cbuf);
+ addstring(false, cbuf, strlen(cbuf));
}
}
-/* Add unicode character and process its hi surrogate */
+/* Add unicode character, processing any surrogate pairs */
static void
addUnicode(int ch, int *hi_surrogate)
{
- if (ch >= 0xd800 && ch <= 0xdbff)
+ if (is_utf16_surrogate_first(ch))
{
if (*hi_surrogate != -1)
ereport(ERROR,
@@ -542,10 +515,10 @@ addUnicode(int ch, int *hi_surrogate)
errmsg("invalid input syntax for type %s", "jsonpath"),
errdetail("Unicode high surrogate must not follow "
"a high surrogate.")));
- *hi_surrogate = (ch & 0x3ff) << 10;
+ *hi_surrogate = ch;
return;
}
- else if (ch >= 0xdc00 && ch <= 0xdfff)
+ else if (is_utf16_surrogate_second(ch))
{
if (*hi_surrogate == -1)
ereport(ERROR,
@@ -553,7 +526,7 @@ addUnicode(int ch, int *hi_surrogate)
errmsg("invalid input syntax for type %s", "jsonpath"),
errdetail("Unicode low surrogate must follow a high "
"surrogate.")));
- ch = 0x10000 + *hi_surrogate + (ch & 0x3ff);
+ ch = surrogate_pair_to_codepoint(*hi_surrogate, ch);
*hi_surrogate = -1;
}
else if (*hi_surrogate != -1)
diff --git a/src/backend/utils/adt/xml.c b/src/backend/utils/adt/xml.c
index c7ae1eded8..4c299057a6 100644
--- a/src/backend/utils/adt/xml.c
+++ b/src/backend/utils/adt/xml.c
@@ -2086,26 +2086,6 @@ map_sql_identifier_to_xml_name(const char *ident, bool fully_escaped,
/*
- * Map a Unicode codepoint into the current server encoding.
- */
-static char *
-unicode_to_sqlchar(pg_wchar c)
-{
- char utf8string[8]; /* need room for trailing zero */
- char *result;
-
- memset(utf8string, 0, sizeof(utf8string));
- unicode_to_utf8(c, (unsigned char *) utf8string);
-
- result = pg_any_to_server(utf8string, strlen(utf8string), PG_UTF8);
- /* if pg_any_to_server didn't strdup, we must */
- if (result == utf8string)
- result = pstrdup(result);
- return result;
-}
-
-
-/*
* Map XML name to SQL identifier; see SQL/XML:2008 section 9.3.
*/
char *
@@ -2125,10 +2105,12 @@ map_xml_name_to_sql_identifier(const char *name)
&& isxdigit((unsigned char) *(p + 5))
&& *(p + 6) == '_')
{
+ char cbuf[MAX_UNICODE_EQUIVALENT_STRING + 1];
unsigned int u;
sscanf(p + 2, "%X", &u);
- appendStringInfoString(&buf, unicode_to_sqlchar(u));
+ pg_unicode_to_server(u, (unsigned char *) cbuf);
+ appendStringInfoString(&buf, cbuf);
p += 6;
}
else
diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c
index 86787bcb31..a8e13cacfd 100644
--- a/src/backend/utils/mb/mbutils.c
+++ b/src/backend/utils/mb/mbutils.c
@@ -68,6 +68,13 @@ static FmgrInfo *ToServerConvProc = NULL;
static FmgrInfo *ToClientConvProc = NULL;
/*
+ * This variable stores the conversion function to convert from UTF-8
+ * to the server encoding. It's NULL if the server encoding *is* UTF-8,
+ * or if we lack a conversion function for this.
+ */
+static FmgrInfo *Utf8ToServerConvProc = NULL;
+
+/*
* These variables track the currently-selected encodings.
*/
static const pg_enc2name *ClientEncoding = &pg_enc2name_tbl[PG_SQL_ASCII];
@@ -273,6 +280,8 @@ SetClientEncoding(int encoding)
void
InitializeClientEncoding(void)
{
+ int current_server_encoding;
+
Assert(!backend_startup_complete);
backend_startup_complete = true;
@@ -289,6 +298,35 @@ InitializeClientEncoding(void)
pg_enc2name_tbl[pending_client_encoding].name,
GetDatabaseEncodingName())));
}
+
+ /*
+ * Also look up the UTF8-to-server conversion function if needed. Since
+ * the server encoding is fixed within any one backend process, we don't
+ * have to do this more than once.
+ */
+ current_server_encoding = GetDatabaseEncoding();
+ if (current_server_encoding != PG_UTF8 &&
+ current_server_encoding != PG_SQL_ASCII)
+ {
+ Oid utf8_to_server_proc;
+
+ Assert(IsTransactionState());
+ utf8_to_server_proc =
+ FindDefaultConversionProc(PG_UTF8,
+ current_server_encoding);
+ /* If there's no such conversion, just leave the pointer as NULL */
+ if (OidIsValid(utf8_to_server_proc))
+ {
+ FmgrInfo *finfo;
+
+ finfo = (FmgrInfo *) MemoryContextAlloc(TopMemoryContext,
+ sizeof(FmgrInfo));
+ fmgr_info_cxt(utf8_to_server_proc, finfo,
+ TopMemoryContext);
+ /* Set Utf8ToServerConvProc only after data is fully valid */
+ Utf8ToServerConvProc = finfo;
+ }
+ }
}
/*
@@ -752,6 +790,73 @@ perform_default_encoding_conversion(const char *src, int len,
return result;
}
+/*
+ * Convert a single Unicode code point into a string in the server encoding.
+ *
+ * The code point given by "c" is converted and stored at *s, which must
+ * have at least MAX_UNICODE_EQUIVALENT_STRING+1 bytes available.
+ * The output will have a trailing '\0'. Throws error if the conversion
+ * cannot be performed.
+ *
+ * Note that this relies on having previously looked up any required
+ * conversion function. That's partly for speed but mostly because the parser
+ * may call this outside any transaction, or in an aborted transaction.
+ */
+void
+pg_unicode_to_server(pg_wchar c, unsigned char *s)
+{
+ unsigned char c_as_utf8[MAX_MULTIBYTE_CHAR_LEN + 1];
+ int c_as_utf8_len;
+ int server_encoding;
+
+ /*
+ * Complain if invalid Unicode code point. The choice of errcode here is
+ * debatable, but really our caller should have checked this anyway.
+ */
+ if (!is_valid_unicode_codepoint(c))
+ ereport(ERROR,
+ (errcode(ERRCODE_SYNTAX_ERROR),
+ errmsg("invalid Unicode code point")));
+
+ /* Otherwise, if it's in ASCII range, conversion is trivial */
+ if (c <= 0x7F)
+ {
+ s[0] = (unsigned char) c;
+ s[1] = '\0';
+ return;
+ }
+
+ /* If the server encoding is UTF-8, we just need to reformat the code */
+ server_encoding = GetDatabaseEncoding();
+ if (server_encoding == PG_UTF8)
+ {
+ unicode_to_utf8(c, s);
+ s[pg_utf_mblen(s)] = '\0';
+ return;
+ }
+
+ /* For all other cases, we must have a conversion function available */
+ if (Utf8ToServerConvProc == NULL)
+ ereport(ERROR,
+ (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+ errmsg("conversion between %s and %s is not supported",
+ pg_enc2name_tbl[PG_UTF8].name,
+ GetDatabaseEncodingName())));
+
+ /* Construct UTF-8 source string */
+ unicode_to_utf8(c, c_as_utf8);
+ c_as_utf8_len = pg_utf_mblen(c_as_utf8);
+ c_as_utf8[c_as_utf8_len] = '\0';
+
+ /* Convert, or throw error if we can't */
+ FunctionCall5(Utf8ToServerConvProc,
+ Int32GetDatum(PG_UTF8),
+ Int32GetDatum(server_encoding),
+ CStringGetDatum(c_as_utf8),
+ CStringGetDatum(s),
+ Int32GetDatum(c_as_utf8_len));
+}
+
/* convert a multibyte string to a wchar */
int
View Lorry Controller Status