[PATCH v3 1/3] dtc: Refactor character literal parsing code

[Anton Staaf]

Move the parsing of hex, octal and escaped characters from data.c
to util.c where it can be used for character literal parsing within
strings as well as for stand alone C style character literals.

Signed-off-by: Anton Staaf <robotboy at chromium.org>
Cc: Jon Loeliger <jdl at jdl.com>
Cc: David Gibson <david at gibson.dropbear.id.au>
---
 data.c |   85 ++----------------------------------------------------
 util.c |   99 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 util.h |    8 +++++
 3 files changed, 111 insertions(+), 81 deletions(-)

diff --git a/data.c b/data.c
index fe555e8..b5f3066 100644
--- a/data.c
+++ b/data.c
@@ -68,40 +68,6 @@ struct data data_copy_mem(const char *mem, int len)
 	return d;
 }
 
-static char get_oct_char(const char *s, int *i)
-{
-	char x[4];
-	char *endx;
-	long val;
-
-	x[3] = '\0';
-	strncpy(x, s + *i, 3);
-
-	val = strtol(x, &endx, 8);
-
-	assert(endx > x);
-
-	(*i) += endx - x;
-	return val;
-}
-
-static char get_hex_char(const char *s, int *i)
-{
-	char x[3];
-	char *endx;
-	long val;
-
-	x[2] = '\0';
-	strncpy(x, s + *i, 2);
-
-	val = strtol(x, &endx, 16);
-	if (!(endx  > x))
-		die("\\x used with no following hex digits\n");
-
-	(*i) += endx - x;
-	return val;
-}
-
 struct data data_copy_escape_string(const char *s, int len)
 {
 	int i = 0;
@@ -114,53 +80,10 @@ struct data data_copy_escape_string(const char *s, int len)
 	while (i < len) {
 		char c = s[i++];
 
-		if (c != '\\') {
-			q[d.len++] = c;
-			continue;
-		}
-
-		c = s[i++];
-		assert(c);
-		switch (c) {
-		case 'a':
-			q[d.len++] = '\a';
-			break;
-		case 'b':
-			q[d.len++] = '\b';
-			break;
-		case 't':
-			q[d.len++] = '\t';
-			break;
-		case 'n':
-			q[d.len++] = '\n';
-			break;
-		case 'v':
-			q[d.len++] = '\v';
-			break;
-		case 'f':
-			q[d.len++] = '\f';
-			break;
-		case 'r':
-			q[d.len++] = '\r';
-			break;
-		case '0':
-		case '1':
-		case '2':
-		case '3':
-		case '4':
-		case '5':
-		case '6':
-		case '7':
-			i--; /* need to re-read the first digit as
-			      * part of the octal value */
-			q[d.len++] = get_oct_char(s, &i);
-			break;
-		case 'x':
-			q[d.len++] = get_hex_char(s, &i);
-			break;
-		default:
-			q[d.len++] = c;
-		}
+		if (c == '\\')
+			c = get_escape_char(s, &i);
+
+		q[d.len++] = c;
 	}
 
 	q[d.len++] = '\0';
diff --git a/util.c b/util.c
index 994436f..6d07292 100644
--- a/util.c
+++ b/util.c
@@ -25,6 +25,7 @@
 #include <stdlib.h>
 #include <stdarg.h>
 #include <string.h>
+#include <assert.h>
 
 #include "util.h"
 
@@ -85,3 +86,101 @@ int util_is_printable_string(const void *data, int len)
 
 	return 1;
 }
+
+/*
+ * Parse a octal encoded character starting at index i in string s.  The
+ * resulting character will be returned and the index i will be updated to
+ * point at the character directly after the end of the encoding, this may be
+ * the '\0' terminator of the string.
+ */
+static char get_oct_char(const char *s, int *i)
+{
+	char x[4];
+	char *endx;
+	long val;
+
+	x[3] = '\0';
+	strncpy(x, s + *i, 3);
+
+	val = strtol(x, &endx, 8);
+
+	assert(endx > x);
+
+	(*i) += endx - x;
+	return val;
+}
+
+/*
+ * Parse a hexadecimal encoded character starting at index i in string s.  The
+ * resulting character will be returned and the index i will be updated to
+ * point at the character directly after the end of the encoding, this may be
+ * the '\0' terminator of the string.
+ */
+static char get_hex_char(const char *s, int *i)
+{
+	char x[3];
+	char *endx;
+	long val;
+
+	x[2] = '\0';
+	strncpy(x, s + *i, 2);
+
+	val = strtol(x, &endx, 16);
+	if (!(endx  > x))
+		die("\\x used with no following hex digits\n");
+
+	(*i) += endx - x;
+	return val;
+}
+
+char get_escape_char(const char *s, int *i)
+{
+	char	c = s[*i];
+	int	j = *i + 1;
+	char	val;
+
+	assert(c);
+	switch (c) {
+	case 'a':
+		val = '\a';
+		break;
+	case 'b':
+		val = '\b';
+		break;
+	case 't':
+		val = '\t';
+		break;
+	case 'n':
+		val = '\n';
+		break;
+	case 'v':
+		val = '\v';
+		break;
+	case 'f':
+		val = '\f';
+		break;
+	case 'r':
+		val = '\r';
+		break;
+	case '0':
+	case '1':
+	case '2':
+	case '3':
+	case '4':
+	case '5':
+	case '6':
+	case '7':
+		j--; /* need to re-read the first digit as
+		      * part of the octal value */
+		val = get_oct_char(s, &j);
+		break;
+	case 'x':
+		val = get_hex_char(s, &j);
+		break;
+	default:
+		val = c;
+	}
+
+	(*i) = j;
+	return val;
+}
diff --git a/util.h b/util.h
index cc68933..f251480 100644
--- a/util.h
+++ b/util.h
@@ -64,4 +64,12 @@ extern char *join_path(const char *path, const char *name);
  * @return 1 if a valid printable string, 0 if not */
 int util_is_printable_string(const void *data, int len);
 
+/*
+ * Parse an escaped character starting at index i in string s.  The resulting
+ * character will be returned and the index i will be updated to point at the
+ * character directly after the end of the encoding, this may be the '\0'
+ * terminator of the string.
+ */
+char get_escape_char(const char *s, int *i);
+
 #endif /* _UTIL_H */
-- 
1.7.3.1