lib/string_helpers: introduce ESCAPE_NA for escaping non-ASCII

Some users may want to have an ASCII based filter, provided by isascii()
function.  Here is the addition of a such.

Link: https://lkml.kernel.org/r/20210504180819.73127-5-andriy.shevchenko@linux.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Chuck Lever <chuck.lever@oracle.com>
Cc: "J. Bruce Fields" <bfields@fieldses.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h
index bf01e24edd893d91f267551b7c41c521e754d93b..d6cf6fe10f74770678dade009555d73dfdcb77a2 100644 (file)
--- a/include/linux/string_helpers.h
+++ b/include/linux/string_helpers.h
@@ -52,6 +52,7 @@ static inline int string_unescape_any_inplace(char *buf)
 #define ESCAPE_NP              BIT(4)
 #define ESCAPE_ANY_NP          (ESCAPE_ANY | ESCAPE_NP)
 #define ESCAPE_HEX             BIT(5)
+#define ESCAPE_NA              BIT(6)
 
 int string_escape_mem(const char *src, size_t isz, char *dst, size_t osz,
                unsigned int flags, const char *only);

diff --git a/lib/string_helpers.c b/lib/string_helpers.c
index e3ef9f86cc3417c45d7b2df65a12d2ef4bbf0dcc..a963404b8c16a714cfa3836b1e0bb58ee3d17f5b 100644 (file)
--- a/lib/string_helpers.c
+++ b/lib/string_helpers.c
@@ -454,8 +454,8 @@ static bool escape_hex(unsigned char c, char **dst, char *end)
  *
  *     1. The character is not matched to the one from @only string and thus
  *        must go as-is to the output.
- *     2. The character is matched to the printable class, if asked, and in
- *        case of match it passes through to the output.
+ *     2. The character is matched to the printable or ASCII class, if asked,
+ *        and in case of match it passes through to the output.
  *     3. The character is checked if it falls into the class given by @flags.
  *        %ESCAPE_OCTAL and %ESCAPE_HEX are going last since they cover any
  *        character. Note that they actually can't go together, otherwise
@@ -463,7 +463,7 @@ static bool escape_hex(unsigned char c, char **dst, char *end)
  *
  * Caller must provide valid source and destination pointers. Be aware that
  * destination buffer will not be NULL-terminated, thus caller have to append
- * it if needs.   The supported flags are::
+ * it if needs. The supported flags are::
  *
  *     %ESCAPE_SPACE: (special white space, not space itself)
  *             '\f' - form feed
@@ -482,11 +482,18 @@ static bool escape_hex(unsigned char c, char **dst, char *end)
  *     %ESCAPE_ANY:
  *             all previous together
  *     %ESCAPE_NP:
- *             escape only non-printable characters (checked by isprint)
+ *             escape only non-printable characters, checked by isprint()
  *     %ESCAPE_ANY_NP:
  *             all previous together
  *     %ESCAPE_HEX:
  *             '\xHH' - byte with hexadecimal value HH (2 digits)
+ *     %ESCAPE_NA:
+ *             escape only non-ascii characters, checked by isascii()
+ *
+ * One notable caveat, the %ESCAPE_NP and %ESCAPE_NA have higher priority
+ * than the rest of the flags (%ESCAPE_NP is higher than %ESCAPE_NA).
+ * It doesn't make much sense to use either of them without %ESCAPE_OCTAL
+ * or %ESCAPE_HEX, because they cover most of the other character classes.
  *
  * Return:
  * The total size of the escaped output that would be generated for
@@ -510,6 +517,8 @@ int string_escape_mem(const char *src, size_t isz, char *dst, size_t osz,
                 *        character under question
                 *      - the character is printable, when @flags has
                 *        %ESCAPE_NP bit set
+                *      - the character is ASCII, when @flags has
+                *        %ESCAPE_NA bit set
                 *      - the character doesn't fall into a class of symbols
                 *        defined by given @flags
                 * In these cases we just pass through a character to the
@@ -523,6 +532,10 @@ int string_escape_mem(const char *src, size_t isz, char *dst, size_t osz,
                    flags & ESCAPE_NP && escape_passthrough(c, &p, end))
                        continue;
 
+               if (isascii(c) &&
+                   flags & ESCAPE_NA && escape_passthrough(c, &p, end))
+                       continue;
+
                if (flags & ESCAPE_SPACE && escape_space(c, &p, end))
                        continue;