diff mbox series

[v1,04/12] lib/string_helpers: Introduce ESCAPE_NAP to escape non-ASCII and non-printable

Message ID 20210503204907.34013-5-andriy.shevchenko@linux.intel.com (mailing list archive)
State New, archived
Headers show
Series lib/string_helpers: get rid of ugly *_escape_mem_ascii() API | expand

Commit Message

Andy Shevchenko May 3, 2021, 8:48 p.m. UTC
Some users may want to have an ASCII based filter for printable only characters,
provided by conjunction of isascii() and isprint() functions.

Here is the addition of a such.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 include/linux/string_helpers.h |  1 +
 lib/string_helpers.c           | 20 ++++++++++++++++----
 2 files changed, 17 insertions(+), 4 deletions(-)
diff mbox series

Patch

diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h
index d6cf6fe10f74..811c6a627620 100644
--- a/include/linux/string_helpers.h
+++ b/include/linux/string_helpers.h
@@ -53,6 +53,7 @@  static inline int string_unescape_any_inplace(char *buf)
 #define ESCAPE_ANY_NP		(ESCAPE_ANY | ESCAPE_NP)
 #define ESCAPE_HEX		BIT(5)
 #define ESCAPE_NA		BIT(6)
+#define ESCAPE_NAP		BIT(7)
 
 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 d426163cb446..26e35018684f 100644
--- a/lib/string_helpers.c
+++ b/lib/string_helpers.c
@@ -454,9 +454,11 @@  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 or ASCII class, if asked,
+ *	2. The character is matched to the printable and ASCII classes, 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.
+ *	3. The character is matched to the printable or ASCII class, if asked,
+ *	   and in case of match it passes through to the output.
+ *	4. 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
  *	   %ESCAPE_HEX will be ignored.
@@ -489,11 +491,15 @@  static bool escape_hex(unsigned char c, char **dst, char *end)
  *		'\xHH' - byte with hexadecimal value HH (2 digits)
  *	%ESCAPE_NA:
  *		escape only non-ascii characters, checked by isascii()
+ *	%ESCAPE_NAP:
+ *		escape only non-printable or non-ascii characters
  *
- * 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).
+ * One notable caveat, the %ESCAPE_NAP, %ESCAPE_NP and %ESCAPE_NA have the
+ * higher priority than the rest of the flags (%ESCAPE_NAP is the highest).
  * 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.
+ * %ESCAPE_NAP can utilize %ESCAPE_SPACE or %ESCAPE_SPECIAL in addition to
+ * the above.
  *
  * Return:
  * The total size of the escaped output that would be generated for
@@ -515,6 +521,8 @@  int string_escape_mem(const char *src, size_t isz, char *dst, size_t osz,
 		 * Apply rules in the following sequence:
 		 *	- the @only string is supplied and does not contain a
 		 *	  character under question
+		 *	- the character is printable and ASCII, when @flags has
+		 *	  %ESCAPE_NAP bit set
 		 *	- the character is printable, when @flags has
 		 *	  %ESCAPE_NP bit set
 		 *	- the character is ASCII, when @flags has
@@ -527,6 +535,10 @@  int string_escape_mem(const char *src, size_t isz, char *dst, size_t osz,
 		if (is_dict && !strchr(only, c)) {
 			/* do nothing */
 		} else {
+			if (isascii(c) && isprint(c) &&
+			    flags & ESCAPE_NAP && escape_passthrough(c, &p, end))
+				continue;
+
 			if (isprint(c) &&
 			    flags & ESCAPE_NP && escape_passthrough(c, &p, end))
 				continue;