pg_query 2.0.3 → 5.1.0

data/ext/pg_query/src_backend_utils_fmgr_fmgr.c

@@ -1,6 +1,6 @@
 /*--------------------------------------------------------------------
  * Symbols referenced in this file:
- * - FunctionCall5Coll
+ * - FunctionCall6Coll
  *--------------------------------------------------------------------
  */
 
@@ -9,7 +9,7 @@
  * fmgr.c
  *	  The Postgres function manager.
  *
- * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  *
@@ -29,6 +29,7 @@
 #include "lib/stringinfo.h"
 #include "miscadmin.h"
 #include "nodes/makefuncs.h"
+#include "nodes/miscnodes.h"
 #include "nodes/nodeFuncs.h"
 #include "pgstat.h"
 #include "utils/acl.h"
@@ -124,7 +125,7 @@ extern Datum fmgr_security_definer(PG_FUNCTION_ARGS);
  * If *mod == NULL and *fn != NULL, the function is implemented by a symbol in
  * the main binary.
  *
- * If *mod != NULL and *fn !=NULL the function is implemented in an extension
+ * If *mod != NULL and *fn != NULL the function is implemented in an extension
  * shared object.
  *
  * The returned module and function names are pstrdup'ed into the current
@@ -180,14 +181,6 @@ extern Datum fmgr_security_definer(PG_FUNCTION_ARGS);
  */
 
 
-/*
- * clear_external_function_hash: remove entries for a library being closed
- *
- * Presently we just zap the entire hash table, but later it might be worth
- * the effort to remove only the entries associated with the given handle.
- */
-
-
 
 /*
  * Copy an FmgrInfo struct
@@ -291,14 +284,17 @@ struct fmgr_security_definer_cache
 
 
 
+
+
 Datum
-FunctionCall5Coll(FmgrInfo *flinfo, Oid collation, Datum arg1, Datum arg2,
-				  Datum arg3, Datum arg4, Datum arg5)
+FunctionCall6Coll(FmgrInfo *flinfo, Oid collation, Datum arg1, Datum arg2,
+				  Datum arg3, Datum arg4, Datum arg5,
+				  Datum arg6)
 {
-	LOCAL_FCINFO(fcinfo, 5);
+	LOCAL_FCINFO(fcinfo, 6);
 	Datum		result;
 
-	InitFunctionCallInfoData(*fcinfo, flinfo, 5, collation, NULL, NULL);
+	InitFunctionCallInfoData(*fcinfo, flinfo, 6, collation, NULL, NULL);
 
 	fcinfo->args[0].value = arg1;
 	fcinfo->args[0].isnull = false;
@@ -310,6 +306,8 @@ FunctionCall5Coll(FmgrInfo *flinfo, Oid collation, Datum arg1, Datum arg2,
 	fcinfo->args[3].isnull = false;
 	fcinfo->args[4].value = arg5;
 	fcinfo->args[4].isnull = false;
+	fcinfo->args[5].value = arg6;
+	fcinfo->args[5].isnull = false;
 
 	result = FunctionCallInvoke(fcinfo);
 
@@ -327,8 +325,6 @@ FunctionCall5Coll(FmgrInfo *flinfo, Oid collation, Datum arg1, Datum arg2,
 
 
 
-
-
 /*
  * These are for invocation of a function identified by OID with a
  * directly-computed parameter list.  Note that neither arguments nor result
@@ -371,6 +367,37 @@ FunctionCall5Coll(FmgrInfo *flinfo, Oid collation, Datum arg1, Datum arg2,
  */
 
 
+/*
+ * Call a previously-looked-up datatype input function, with non-exception
+ * handling of "soft" errors.
+ *
+ * This is basically like InputFunctionCall, but the converted Datum is
+ * returned into *result while the function result is true for success or
+ * false for failure.  Also, the caller may pass an ErrorSaveContext node.
+ * (We declare that as "fmNodePtr" to avoid including nodes.h in fmgr.h.)
+ *
+ * If escontext points to an ErrorSaveContext, any "soft" errors detected by
+ * the input function will be reported by filling the escontext struct and
+ * returning false.  (The caller can choose to test SOFT_ERROR_OCCURRED(),
+ * but checking the function result instead is usually cheaper.)
+ *
+ * If escontext does not point to an ErrorSaveContext, errors are reported
+ * via ereport(ERROR), so that there is no functional difference from
+ * InputFunctionCall; the result will always be true if control returns.
+ */
+
+
+/*
+ * Call a directly-named datatype input function, with non-exception
+ * handling of "soft" errors.
+ *
+ * This is like InputFunctionCallSafe, except that it is given a direct
+ * pointer to the C function to call.  We assume that that function is
+ * strict.  Also, the function cannot be one that needs to
+ * look at FmgrInfo, since there won't be any.
+ */
+
+
 /*
  * Call a previously-looked-up datatype output function.
  *

data/ext/pg_query/src_backend_utils_init_globals.c

@@ -4,7 +4,6 @@
  * - ExitOnAnyError
  * - InterruptHoldoffCount
  * - QueryCancelHoldoffCount
- * - IsPostmasterEnvironment
  * - InterruptPending
  *--------------------------------------------------------------------
  */
@@ -14,7 +13,7 @@
  * globals.c
  *	  global variable declarations
  *
- * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  *
@@ -45,6 +44,10 @@ __thread volatile sig_atomic_t InterruptPending = false;
 
 
 
+
+
+
+
 __thread volatile uint32 InterruptHoldoffCount = 0;
 
 __thread volatile uint32 QueryCancelHoldoffCount = 0;
@@ -88,7 +91,7 @@ __thread volatile uint32 CritSectionCount = 0;
  /* full path to lib directory */
 
 #ifdef EXEC_BACKEND
-char		postgres_exec_path[MAXPGPATH];	/* full path to backend */
+	/* full path to backend */
 
 /* note: currently this is not valid in backend processes */
 #endif
@@ -120,7 +123,6 @@ char		postgres_exec_path[MAXPGPATH];	/* full path to backend */
  *
  * These are initialized for the bootstrap/standalone case.
  */
-__thread bool		IsPostmasterEnvironment = false;
 
 
 
@@ -152,7 +154,8 @@ __thread bool		ExitOnAnyError = false;
 
 
 
-	/* GUC parameters for vacuum */
+/* GUC parameters for vacuum */
+
 
 
 
@@ -162,7 +165,7 @@ __thread bool		ExitOnAnyError = false;
 
 
 
-	/* working state for vacuum */
 
 
+	/* working state for vacuum */
 

data/ext/pg_query/src_backend_utils_mb_mbutils.c

@@ -5,7 +5,7 @@
  * - cliplen
  * - DatabaseEncoding
  * - pg_verifymbstr
- * - pg_verify_mbstr_len
+ * - pg_verify_mbstr
  * - report_invalid_encoding
  * - GetDatabaseEncoding
  * - pg_get_client_encoding
@@ -17,6 +17,8 @@
  * - pg_mbstrlen_with_len
  * - pg_mblen
  * - SetDatabaseEncoding
+ * - GetMessageEncoding
+ * - MessageEncoding
  *--------------------------------------------------------------------
  */
 
@@ -45,7 +47,7 @@
  * the result is validly encoded according to the destination encoding.
  *
  *
- * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  *
@@ -62,6 +64,7 @@
 #include "utils/builtins.h"
 #include "utils/memutils.h"
 #include "utils/syscache.h"
+#include "varatt.h"
 
 /*
  * We maintain a simple linked list caching the fmgr lookup info for the
@@ -104,6 +107,7 @@ static __thread const pg_enc2name *ClientEncoding = &pg_enc2name_tbl[PG_SQL_ASCI
 
 static __thread const pg_enc2name *DatabaseEncoding = &pg_enc2name_tbl[PG_SQL_ASCII];
 
+static __thread const pg_enc2name *MessageEncoding = &pg_enc2name_tbl[PG_SQL_ASCII];
 
 
 /*
@@ -168,6 +172,37 @@ pg_get_client_encoding(void)
  */
 
 
+/*
+ * Convert src string to another encoding.
+ *
+ * This function has a different API than the other conversion functions.
+ * The caller should've looked up the conversion function using
+ * FindDefaultConversionProc().  Unlike the other functions, the converted
+ * result is not palloc'd.  It is written to the caller-supplied buffer
+ * instead.
+ *
+ * src_encoding   - encoding to convert from
+ * dest_encoding  - encoding to convert to
+ * src, srclen    - input buffer and its length in bytes
+ * dest, destlen  - destination buffer and its size in bytes
+ *
+ * The output is null-terminated.
+ *
+ * If destlen < srclen * MAX_CONVERSION_INPUT_LENGTH + 1, the converted output
+ * wouldn't necessarily fit in the output buffer, and the function will not
+ * convert the whole input.
+ *
+ * TODO: The conversion function interface is not great.  Firstly, it
+ * would be nice to pass through the destination buffer size to the
+ * conversion function, so that if you pass a shorter destination buffer, it
+ * could still continue to fill up the whole buffer.  Currently, we have to
+ * assume worst case expansion and stop the conversion short, even if there
+ * is in fact space left in the destination buffer.  Secondly, it would be
+ * nice to return the number of bytes written to the caller, to avoid a call
+ * to strlen().
+ */
+
+
 /*
  * Convert string to encoding encoding_name. The source
  * encoding is the DB encoding.
@@ -305,14 +340,23 @@ pg_unicode_to_server(pg_wchar c, unsigned char *s)
 	c_as_utf8[c_as_utf8_len] = '\0';
 
 	/* Convert, or throw error if we can't */
-	FunctionCall5(Utf8ToServerConvProc,
+	FunctionCall6(Utf8ToServerConvProc,
 				  Int32GetDatum(PG_UTF8),
 				  Int32GetDatum(server_encoding),
-				  CStringGetDatum(c_as_utf8),
-				  CStringGetDatum(s),
-				  Int32GetDatum(c_as_utf8_len));
+				  CStringGetDatum((char *) c_as_utf8),
+				  CStringGetDatum((char *) s),
+				  Int32GetDatum(c_as_utf8_len),
+				  BoolGetDatum(false));
 }
 
+/*
+ * Convert a single Unicode code point into a string in the server encoding.
+ *
+ * Same as pg_unicode_to_server(), except that we don't throw errors,
+ * but simply return false on conversion failure.
+ */
+
+
 
 /* convert a multibyte string to a wchar */
 
@@ -554,7 +598,11 @@ GetDatabaseEncodingName(void)
  * not attached to a database, and under a database encoding lacking iconv
  * support (MULE_INTERNAL).
  */
-
+int
+GetMessageEncoding(void)
+{
+	return MessageEncoding->encoding;
+}
 
 
 /*
@@ -629,15 +677,29 @@ pg_database_encoding_max_length(void)
 bool
 pg_verifymbstr(const char *mbstr, int len, bool noError)
 {
-	return
-		pg_verify_mbstr_len(GetDatabaseEncoding(), mbstr, len, noError) >= 0;
+	return pg_verify_mbstr(GetDatabaseEncoding(), mbstr, len, noError);
 }
 
 /*
  * Verify mbstr to make sure that it is validly encoded in the specified
  * encoding.
  */
+bool
+pg_verify_mbstr(int encoding, const char *mbstr, int len, bool noError)
+{
+	int			oklen;
 
+	Assert(PG_VALID_ENCODING(encoding));
+
+	oklen = pg_wchar_table[encoding].mbverifystr((const unsigned char *) mbstr, len);
+	if (oklen != len)
+	{
+		if (noError)
+			return false;
+		report_invalid_encoding(encoding, mbstr + oklen, len - oklen);
+	}
+	return true;
+}
 
 /*
  * Verify mbstr to make sure that it is validly encoded in the specified
@@ -649,68 +711,11 @@ pg_verifymbstr(const char *mbstr, int len, bool noError)
  * If OK, return length of string in the encoding.
  * If a problem is found, return -1 when noError is
  * true; when noError is false, ereport() a descriptive message.
+ *
+ * Note: We cannot use the faster encoding-specific mbverifystr() function
+ * here, because we need to count the number of characters in the string.
  */
-int
-pg_verify_mbstr_len(int encoding, const char *mbstr, int len, bool noError)
-{
-	mbverifier	mbverify;
-	int			mb_len;
 
-	Assert(PG_VALID_ENCODING(encoding));
-
-	/*
-	 * In single-byte encodings, we need only reject nulls (\0).
-	 */
-	if (pg_encoding_max_length(encoding) <= 1)
-	{
-		const char *nullpos = memchr(mbstr, 0, len);
-
-		if (nullpos == NULL)
-			return len;
-		if (noError)
-			return -1;
-		report_invalid_encoding(encoding, nullpos, 1);
-	}
-
-	/* fetch function pointer just once */
-	mbverify = pg_wchar_table[encoding].mbverify;
-
-	mb_len = 0;
-
-	while (len > 0)
-	{
-		int			l;
-
-		/* fast path for ASCII-subset characters */
-		if (!IS_HIGHBIT_SET(*mbstr))
-		{
-			if (*mbstr != '\0')
-			{
-				mb_len++;
-				mbstr++;
-				len--;
-				continue;
-			}
-			if (noError)
-				return -1;
-			report_invalid_encoding(encoding, mbstr, len);
-		}
-
-		l = (*mbverify) ((const unsigned char *) mbstr, len);
-
-		if (l < 0)
-		{
-			if (noError)
-				return -1;
-			report_invalid_encoding(encoding, mbstr, len);
-		}
-
-		mbstr += l;
-		len -= l;
-		mb_len++;
-	}
-	return mb_len;
-}
 
 /*
  * check_encoding_conversion_args: check arguments of a conversion function
@@ -772,68 +777,6 @@ report_invalid_encoding(int encoding, const char *mbstr, int len)
  * null. Returns NULL iff failed. Before MessageEncoding initialization, "str"
  * should be ASCII-only; this will function as though MessageEncoding is UTF8.
  */
-WCHAR *
-pgwin32_message_to_UTF16(const char *str, int len, int *utf16len)
-{
-	int			msgenc = GetMessageEncoding();
-	WCHAR	   *utf16;
-	int			dstlen;
-	UINT		codepage;
 
-	if (msgenc == PG_SQL_ASCII)
-		/* No conversion is possible, and SQL_ASCII is never utf16. */
-		return NULL;
-
-	codepage = pg_enc2name_tbl[msgenc].codepage;
-
-	/*
-	 * Use MultiByteToWideChar directly if there is a corresponding codepage,
-	 * or double conversion through UTF8 if not.  Double conversion is needed,
-	 * for example, in an ENCODING=LATIN8, LC_CTYPE=C database.
-	 */
-	if (codepage != 0)
-	{
-		utf16 = (WCHAR *) palloc(sizeof(WCHAR) * (len + 1));
-		dstlen = MultiByteToWideChar(codepage, 0, str, len, utf16, len);
-		utf16[dstlen] = (WCHAR) 0;
-	}
-	else
-	{
-		char	   *utf8;
-
-		/*
-		 * XXX pg_do_encoding_conversion() requires a transaction.  In the
-		 * absence of one, hope for the input to be valid UTF8.
-		 */
-		if (IsTransactionState())
-		{
-			utf8 = (char *) pg_do_encoding_conversion((unsigned char *) str,
-													  len,
-													  msgenc,
-													  PG_UTF8);
-			if (utf8 != str)
-				len = strlen(utf8);
-		}
-		else
-			utf8 = (char *) str;
-
-		utf16 = (WCHAR *) palloc(sizeof(WCHAR) * (len + 1));
-		dstlen = MultiByteToWideChar(CP_UTF8, 0, utf8, len, utf16, len);
-		utf16[dstlen] = (WCHAR) 0;
-
-		if (utf8 != str)
-			pfree(utf8);
-	}
-
-	if (dstlen == 0 && len > 0)
-	{
-		pfree(utf16);
-		return NULL;			/* error */
-	}
-
-	if (utf16len)
-		*utf16len = dstlen;
-	return utf16;
-}
 
 #endif							/* WIN32 */