util: make sanitize string available in string util for reuse

No functional changes.

2 files changed, 29 insertions, 0 deletions

diff --git a/util/string-util.c b/util/string-util.c
index a5622d7a..9e2f728f 100644
--- a/util/string-util.c
+++ b/util/string-util.c
@@ -37,6 +37,28 @@ strtok_len (char *s, const char *delim, size_t *len)
     return *len ? s : NULL;
 }
 
+char *
+sanitize_string (const void *ctx, const char *str)
+{
+    char *out, *loop;
+
+    if (! str)
+	return NULL;
+
+    out = talloc_strdup (ctx, str);
+    if (! out)
+	return NULL;
+
+    for (loop = out; *loop; loop++) {
+	if (*loop == '\t' || *loop == '\n')
+	    *loop = ' ';
+	else if ((unsigned char)(*loop) < 32)
+	    *loop = '?';
+    }
+
+    return out;
+}
+
 static int
 is_unquoted_terminator (unsigned char c)
 {
diff --git a/util/string-util.h b/util/string-util.h
index 0194607e..8a3ad19e 100644
--- a/util/string-util.h
+++ b/util/string-util.h
@@ -19,6 +19,13 @@
 
 char *strtok_len (char *s, const char *delim, size_t *len);
 
+/* Return a talloced string with str sanitized.
+ *
+ * Whitespace characters (tabs and newlines) are replaced with spaces,
+ * non-printable characters with question marks.
+ */
+char *sanitize_string (const void *ctx, const char *str);
+
 /* Construct a boolean term query with the specified prefix (e.g.,
  * "id") and search term, quoting term as necessary.  Specifically, if
  * term contains any non-printable ASCII characters, non-ASCII