Refactor logic to check for ASCII-only characters in string

michaelpq · michaelpq · commit 93e8ff8701a6 · 2020-12-21T09:37:11.000+09:00
The same logic was present for collation commands, SASLprep and pgcrypto, so this removes some code. Author: Michael Paquier Reviewed-by: Stephen Frost, Heikki Linnakangas Discussion: https://postgr.es/m/X9womIn6rne6Gud2@paquier.xyz
diff --git a/contrib/pgcrypto/pgp-pgsql.c b/contrib/pgcrypto/pgp-pgsql.c
@@ -32,6 +32,7 @@
 #include "postgres.h"
 
 #include "catalog/pg_type.h"
+#include "common/string.h"
 #include "funcapi.h"
 #include "lib/stringinfo.h"
 #include "mb/pg_wchar.h"
@@ -92,19 +93,6 @@ convert_to_utf8(text *src)
 	return convert_charset(src, GetDatabaseEncoding(), PG_UTF8);
 }
 
-static bool
-string_is_ascii(const char *str)
-{
-	const char *p;
-
-	for (p = str; *p; p++)
-	{
-		if (IS_HIGHBIT_SET(*p))
-			return false;
-	}
-	return true;
-}
-
 static void
 clear_and_pfree(text *p)
 {
@@ -814,7 +802,7 @@ parse_key_value_arrays(ArrayType *key_array, ArrayType *val_array,
 
 		v = TextDatumGetCString(key_datums[i]);
 
-		if (!string_is_ascii(v))
+		if (!pg_is_ascii(v))
 			ereport(ERROR,
 					(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
 					 errmsg("header key must not contain non-ASCII characters")));
@@ -836,7 +824,7 @@ parse_key_value_arrays(ArrayType *key_array, ArrayType *val_array,
 
 		v = TextDatumGetCString(val_datums[i]);
 
-		if (!string_is_ascii(v))
+		if (!pg_is_ascii(v))
 			ereport(ERROR,
 					(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
 					 errmsg("header value must not contain non-ASCII characters")));
diff --git a/src/backend/commands/collationcmds.c b/src/backend/commands/collationcmds.c
@@ -27,6 +27,7 @@
 #include "commands/comment.h"
 #include "commands/dbcommands.h"
 #include "commands/defrem.h"
+#include "common/string.h"
 #include "mb/pg_wchar.h"
 #include "miscadmin.h"
 #include "utils/acl.h"
@@ -286,23 +287,6 @@ pg_collation_actual_version(PG_FUNCTION_ARGS)
 #define READ_LOCALE_A_OUTPUT
 #endif
 
-#if defined(READ_LOCALE_A_OUTPUT) || defined(USE_ICU)
-/*
- * Check a string to see if it is pure ASCII
- */
-static bool
-is_all_ascii(const char *str)
-{
-	while (*str)
-	{
-		if (IS_HIGHBIT_SET(*str))
-			return false;
-		str++;
-	}
-	return true;
-}
-#endif							/* READ_LOCALE_A_OUTPUT || USE_ICU */
-
 #ifdef READ_LOCALE_A_OUTPUT
 /*
  * "Normalize" a libc locale name, stripping off encoding tags such as
@@ -396,7 +380,7 @@ get_icu_locale_comment(const char *localename)
 	if (U_FAILURE(status))
 		return NULL;			/* no good reason to raise an error */
 
-	/* Check for non-ASCII comment (can't use is_all_ascii for this) */
+	/* Check for non-ASCII comment (can't use pg_is_ascii for this) */
 	for (i = 0; i < len_uchar; i++)
 	{
 		if (displayname[i] > 127)
@@ -477,7 +461,7 @@ pg_import_system_collations(PG_FUNCTION_ARGS)
 			 * interpret the non-ASCII characters. We can't do much with
 			 * those, so we filter them out.
 			 */
-			if (!is_all_ascii(localebuf))
+			if (!pg_is_ascii(localebuf))
 			{
 				elog(DEBUG1, "locale name has non-ASCII characters, skipped: \"%s\"", localebuf);
 				continue;
@@ -623,7 +607,7 @@ pg_import_system_collations(PG_FUNCTION_ARGS)
 			 * Be paranoid about not allowing any non-ASCII strings into
 			 * pg_collation
 			 */
-			if (!is_all_ascii(langtag) || !is_all_ascii(collcollate))
+			if (!pg_is_ascii(langtag) || !pg_is_ascii(collcollate))
 				continue;
 
 			collid = CollationCreate(psprintf("%s-x-icu", langtag),
diff --git a/src/common/saslprep.c b/src/common/saslprep.c
@@ -26,6 +26,7 @@
 #endif
 
 #include "common/saslprep.h"
+#include "common/string.h"
 #include "common/unicode_norm.h"
 #include "mb/pg_wchar.h"
 
@@ -47,7 +48,6 @@
 static int	codepoint_range_cmp(const void *a, const void *b);
 static bool is_code_in_table(pg_wchar code, const pg_wchar *map, int mapsize);
 static int	pg_utf8_string_len(const char *source);
-static bool pg_is_ascii_string(const char *p);
 
 /*
  * Stringprep Mapping Tables.
@@ -1019,21 +1019,6 @@ pg_utf8_string_len(const char *source)
 	return num_chars;
 }
 
-/*
- * Returns true if the input string is pure ASCII.
- */
-static bool
-pg_is_ascii_string(const char *p)
-{
-	while (*p)
-	{
-		if (IS_HIGHBIT_SET(*p))
-			return false;
-		p++;
-	}
-	return true;
-}
-
 
 /*
  * pg_saslprep - Normalize a password with SASLprep.
@@ -1076,7 +1061,7 @@ pg_saslprep(const char *input, char **output)
 	 * Quick check if the input is pure ASCII.  An ASCII string requires no
 	 * further processing.
 	 */
-	if (pg_is_ascii_string(input))
+	if (pg_is_ascii(input))
 	{
 		*output = STRDUP(input);
 		if (!(*output))
diff --git a/src/common/string.c b/src/common/string.c
@@ -92,6 +92,22 @@ pg_clean_ascii(char *str)
 }
 
 
+/*
+ * pg_is_ascii -- Check if string is made only of ASCII characters
+ */
+bool
+pg_is_ascii(const char *str)
+{
+	while (*str)
+	{
+		if (IS_HIGHBIT_SET(*str))
+			return false;
+		str++;
+	}
+	return true;
+}
+
+
 /*
  * pg_strip_crlf -- Remove any trailing newline and carriage return
  *
diff --git a/src/include/common/string.h b/src/include/common/string.h
@@ -18,6 +18,7 @@ extern int	strtoint(const char *pg_restrict str, char **pg_restrict endptr,
 					 int base);
 extern void pg_clean_ascii(char *str);
 extern int	pg_strip_crlf(char *str);
+extern bool pg_is_ascii(const char *str);
 
 /* functions in src/common/pg_get_line.c */
 extern char *pg_get_line(FILE *stream);
