unify string replacement

2 files changed, 92 insertions, 16 deletions

diff --git a/udev/lib/libudev-private.h b/udev/lib/libudev-private.h
index 2f8b8259b5..5e09188f08 100644
--- a/udev/lib/libudev-private.h
+++ b/udev/lib/libudev-private.h
@@ -159,9 +159,10 @@ extern int udev_queue_export_device_finished(struct udev_queue *udev_queue, stru
 extern int udev_queue_export_device_failed(struct udev_queue *udev_queue, struct udev_device *udev_device);
 
 /* libudev-utils */
-#define UTIL_PATH_SIZE		1024
-#define UTIL_LINE_SIZE		2048
-#define UTIL_NAME_SIZE		512
+#define UTIL_PATH_SIZE				1024
+#define UTIL_LINE_SIZE				2048
+#define UTIL_NAME_SIZE				512
+#define UDEV_ALLOWED_CHARS_INPUT		"/ $%?,"
 extern ssize_t util_get_sys_subsystem(struct udev *udev, const char *syspath, char *subsystem, size_t size);
 extern ssize_t util_get_sys_driver(struct udev *udev, const char *syspath, char *driver, size_t size);
 extern int util_resolve_sys_link(struct udev *udev, char *syspath, size_t size);
@@ -171,5 +172,7 @@ extern size_t util_path_decode(char *s);
 extern void util_remove_trailing_chars(char *path, char c);
 extern size_t util_strlcpy(char *dst, const char *src, size_t size);
 extern size_t util_strlcat(char *dst, const char *src, size_t size);
-extern int util_replace_chars(char *str, const char *white);
+extern int udev_util_replace_whitespace(const char *str, char *to, size_t len);
+extern int udev_util_replace_chars(char *str, const char *white);
+extern int udev_util_encode_string(const char *str, char *str_enc, size_t len);
 #endif
diff --git a/udev/lib/libudev-util.c b/udev/lib/libudev-util.c
index 9353e8eda7..f4e78850f9 100644
--- a/udev/lib/libudev-util.c
+++ b/udev/lib/libudev-util.c
@@ -331,8 +331,47 @@ static int utf8_encoded_valid_unichar(const char *str)
 	return len;
 }
 
+int udev_util_replace_whitespace(const char *str, char *to, size_t len)
+{
+	size_t i, j;
+
+	/* strip trailing whitespace */
+	len = strnlen(str, len);
+	while (len && isspace(str[len-1]))
+		len--;
+
+	/* strip leading whitespace */
+	i = 0;
+	while (isspace(str[i]) && (i < len))
+		i++;
+
+	j = 0;
+	while (i < len) {
+		/* substitute multiple whitespace with a single '_' */
+		if (isspace(str[i])) {
+			while (isspace(str[i]))
+				i++;
+			to[j++] = '_';
+		}
+		to[j++] = str[i++];
+	}
+	to[j] = '\0';
+	return 0;
+}
+
+static int is_whitelisted(char c, const char *white)
+{
+	if ((c >= '0' && c <= '9') ||
+	    (c >= 'A' && c <= 'Z') ||
+	    (c >= 'a' && c <= 'z') ||
+	    strchr("#+-.:=@_", c) != NULL ||
+	    (white != NULL && strchr(white, c) != NULL))
+		return 1;
+	return 0;
+}
+
 /* allow chars in whitelist, plain ascii, hex-escaping and valid utf8 */
-int util_replace_chars(char *str, const char *white)
+int udev_util_replace_chars(char *str, const char *white)
 {
 	size_t i = 0;
 	int replaced = 0;
@@ -340,16 +379,7 @@ int util_replace_chars(char *str, const char *white)
 	while (str[i] != '\0') {
 		int len;
 
-		/* accept whitelist */
-		if (white != NULL && strchr(white, str[i]) != NULL) {
-			i++;
-			continue;
-		}
-
-		/* accept plain ascii char */
-		if ((str[i] >= '0' && str[i] <= '9') ||
-		    (str[i] >= 'A' && str[i] <= 'Z') ||
-		    (str[i] >= 'a' && str[i] <= 'z')) {
+		if (is_whitelisted(str[i], white)) {
 			i++;
 			continue;
 		}
@@ -380,6 +410,49 @@ int util_replace_chars(char *str, const char *white)
 		i++;
 		replaced++;
 	}
-
 	return replaced;
 }
+
+/**
+ * util_encode_string:
+ * @str: input string to be encoded
+ * @str_enc: output string to store the encoded input string
+ * @len: maximum size of the output string, which may be
+ *       four times as long as the input string
+ *
+ * Encode all potentially unsafe characters of a string to the
+ * corresponding hex value prefixed by '\x'.
+ *
+ * Returns: 0 if the entire string was copied, non-zero otherwise.
+ **/
+int udev_util_encode_string(const char *str, char *str_enc, size_t len)
+{
+	size_t i, j;
+
+	if (str == NULL || str_enc == NULL || len == 0)
+		return -1;
+
+	str_enc[0] = '\0';
+	for (i = 0, j = 0; str[i] != '\0'; i++) {
+		int seqlen;
+
+		seqlen = utf8_encoded_valid_unichar(&str[i]);
+		if (seqlen > 1) {
+			memcpy(&str_enc[j], &str[i], seqlen);
+			j += seqlen;
+			i += (seqlen-1);
+		} else if (str[i] == '\\' || !is_whitelisted(str[i], NULL)) {
+			sprintf(&str_enc[j], "\\x%02x", (unsigned char) str[i]);
+			j += 4;
+		} else {
+			str_enc[j] = str[i];
+			j++;
+		}
+		if (j+3 >= len)
+			goto err;
+	}
+	str_enc[j] = '\0';
+	return 0;
+err:
+	return -1;
+}