Patch from Jean Wolter:

it looks like the introduced support for character classes and
equivalence classes is not correct. The attached patch tries to fix
some symptoms and tries to make tr behave like gnu tr for the added
test cases. The patch

 - removes if clauses with side effects
 - fixes handling of buffer pointer (strcat added characters to the
   buffer without increasing the buffer pointer)
 - re-arranges character classes to match ASCII order

regards,
Jean

2 files changed, 38 insertions, 18 deletions

diff --git a/coreutils/tr.c b/coreutils/tr.c
index 15a9d17b0..752b13bf8 100644
--- a/coreutils/tr.c
+++ b/coreutils/tr.c
@@ -116,7 +116,8 @@ static unsigned int expand(const char *arg, register unsigned char *buffer)
 			arg += 3; /* Skip the assumed a-z */
 		} else if (*arg == '[') {
 			arg++;
-			if (ENABLE_FEATURE_TR_CLASSES && *arg++ == ':') {
+			i = *arg++;
+			if (ENABLE_FEATURE_TR_CLASSES && i == ':') {
 				if (strncmp(arg, "alpha", 5) == 0) {
 					for (i = 'A'; i <= 'Z'; i++)
 						*buffer++ = i;
@@ -124,12 +125,12 @@ static unsigned int expand(const char *arg, register unsigned char *buffer)
 						*buffer++ = i;
 				}
 				else if (strncmp(arg, "alnum", 5) == 0) {
+					for (i = '0'; i <= '9'; i++)
+						*buffer++ = i;
 					for (i = 'A'; i <= 'Z'; i++)
 						*buffer++ = i;
 					for (i = 'a'; i <= 'z'; i++)
 						*buffer++ = i;
-					for (i = '0'; i <= '9'; i++)
-						*buffer++ = i;
 				}
 				else if (strncmp(arg, "digit", 5) == 0)
 					for (i = '0'; i <= '9'; i++)
@@ -140,10 +141,15 @@ static unsigned int expand(const char *arg, register unsigned char *buffer)
 				else if (strncmp(arg, "upper", 5) == 0)
 					for (i = 'A'; i <= 'Z'; i++)
 						*buffer++ = i;
-				else if (strncmp(arg, "space", 5) == 0)
-					strcat((char*)buffer, " \f\n\r\t\v");
-				else if (strncmp(arg, "blank", 5) == 0)
-					strcat((char*)buffer, " \t");
+				else if (strncmp(arg, "space", 5) == 0) {
+				    const char s[] = "\t\n\v\f\r ";
+					strcat((char*)buffer, s);
+					buffer += sizeof(s) - 1;
+				}
+				else if (strncmp(arg, "blank", 5) == 0) {
+					*buffer++ = '\t';
+					*buffer++ = ' ';
+				}
 				/* gcc gives a warning if braces aren't used here */
 				else if (strncmp(arg, "punct", 5) == 0) {
 					for (i = 0; i <= ASCII; i++)
@@ -156,13 +162,13 @@ static unsigned int expand(const char *arg, register unsigned char *buffer)
 							*buffer++ = i;
 				}
 				else {
-					strcat((char*)buffer, "[:");
-					arg++;
+					*buffer++ = '[';
+					*buffer++ = ':';
 					continue;
 				}
 				break;
 			}
-			if (ENABLE_FEATURE_TR_EQUIV && *arg++ == '=') {
+			if (ENABLE_FEATURE_TR_EQUIV && i == '=') {
 				*buffer++ = *arg;
 				/* skip the closing =] */
 				arg += 3;
@@ -173,7 +179,6 @@ static unsigned int expand(const char *arg, register unsigned char *buffer)
 				arg -= 2;
 				continue;
 			}
-			i = *arg++;
 			ac = *arg++;
 			while (i <= ac)
 				*buffer++ = i++;
diff --git a/testsuite/tr/tr-works b/testsuite/tr/tr-works
index 8753a3f28..b7a6e8df7 100644
--- a/testsuite/tr/tr-works
+++ b/testsuite/tr/tr-works
@@ -1,9 +1,24 @@
-echo "cbaab" | tr abc zyx > logfile.gnu
-echo "TESTING A B C" | tr [A-Z] [a-z] >> logfile.gnu
-echo abc[] | tr a[b AXB >> logfile.gnu
-
-echo "cbaab" | busybox tr abc zyx > logfile.bb
-echo "TESTING A B C" | busybox tr [A-Z] [a-z] >> logfile.bb
-echo abc[] | busybox tr a[b AXB >> logfile.bb
+run_tr ()
+{
+	echo -n "echo '$1' | tr '$2' '$3': "
+	echo "$1" | $bb tr "$2" "$3"
+	echo
+}
+tr_test ()
+{
+	run_tr "cbaab"		abc 		zyx
+	run_tr "TESTING A B C" 	'[A-Z]' 	'[a-z]' 
+	run_tr "abc[]" 		"a[b" 		AXB
+	run_tr abc		'[:alpha:]' 	A-ZA-Z
+	run_tr abc56		'[:alnum:]' 	A-ZA-Zxxxxxxxxxx
+	run_tr 012		'[:digit:]' 	abcdefghi
+	run_tr abc56		'[:lower:]' 	'[:upper:]'
+	run_tr " 	"	'[:space:]' 	12345
+	run_tr " 	"	'[:blank:]' 	12
+	run_tr 'a b'		'[= =]' 	X
+	run_tr "[:"		'[:' 		ab
+}
 
+bb=        tr_test > logfile.gnu
+bb=busybox tr_test > logfile.bb
 cmp logfile.gnu logfile.bb