* time.c (time_strftime): format should be ascii compatible.

* parse.y (rb_intern3): non ASCII compatible symbols.

* re.c (rb_reg_regsub): add encoding check.

* string.c (rb_str_chomp_bang): ditto.

* test/ruby/test_utf16.rb (TestUTF16::test_chomp): raises exception.

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@15640 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

6 files changed, 47 insertions, 5 deletions

diff --git a/ChangeLog b/ChangeLog
index 306c4bc295..3415de734d 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,15 @@
+Fri Feb 29 18:08:43 2008  Yukihiro Matsumoto  <matz@ruby-lang.org>
+
+	* time.c (time_strftime): format should be ascii compatible.
+
+	* parse.y (rb_intern3): non ASCII compatible symbols.
+
+	* re.c (rb_reg_regsub): add encoding check.
+
+	* string.c (rb_str_chomp_bang): ditto.
+
+	* test/ruby/test_utf16.rb (TestUTF16::test_chomp): raises exception.
+
 Fri Feb 29 15:16:31 2008  Yukihiro Matsumoto  <matz@ruby-lang.org>
 
 	* string.c (rb_str_rpartition): calculation was done in byte indexing.
diff --git a/parse.y b/parse.y
index bf0cd7388f..88e72de4bf 100644
--- a/parse.y
+++ b/parse.y
@@ -9008,6 +9008,10 @@ rb_intern3(const char *name, long len, rb_encoding *enc)
     if (st_lookup(global_symbols.sym_id, str, (st_data_t *)&id))
 	return id;
 
+    if (rb_cString && !rb_enc_asciicompat(enc)) {
+	id = ID_JUNK;
+	goto new_id;
+    }
     last = len-1;
     id = 0;
     switch (*m) {
diff --git a/re.c b/re.c
index 49424eb632..61f6990d04 100644
--- a/re.c
+++ b/re.c
@@ -2960,6 +2960,7 @@ rb_reg_regsub(VALUE str, VALUE src, struct re_registers *regs, VALUE regexp)
     rb_encoding *str_enc = rb_enc_get(str);
     rb_encoding *src_enc = rb_enc_get(src);
 
+    rb_enc_check(str, src);
     p = s = RSTRING_PTR(str);
     e = s + RSTRING_LEN(str);
 
diff --git a/string.c b/string.c
index ffae4518e9..1b88ded7b1 100644
--- a/string.c
+++ b/string.c
@@ -5273,6 +5273,7 @@ rb_str_chomp_bang(int argc, VALUE *argv, VALUE str)
 	rs = rb_rs;
 	if (rs == rb_default_rs) {
 	  smart_chomp:
+	    rb_enc_check(str, rs);
 	    rb_str_modify(str);
 	    if (RSTRING_PTR(str)[len-1] == '\n') {
 		STR_DEC_LEN(str);
@@ -5648,6 +5649,11 @@ rb_str_scan(VALUE str, VALUE pat)
 static VALUE
 rb_str_hex(VALUE str)
 {
+    rb_encoding *enc = rb_enc_get(str);
+
+    if (!rb_enc_asciicompat(enc)) {
+	rb_raise(rb_eArgError, "ASCII incompatible encoding: %s", rb_enc_name(enc));
+    }
     return rb_str_to_inum(str, 16, Qfalse);
 }
 
@@ -5669,6 +5675,11 @@ rb_str_hex(VALUE str)
 static VALUE
 rb_str_oct(VALUE str)
 {
+    rb_encoding *enc = rb_enc_get(str);
+
+    if (!rb_enc_asciicompat(enc)) {
+	rb_raise(rb_eArgError, "ASCII incompatible encoding: %s", rb_enc_name(enc));
+    }
     return rb_str_to_inum(str, -8, Qfalse);
 }
 
diff --git a/test/ruby/test_utf16.rb b/test/ruby/test_utf16.rb
index bd56377734..1647563f84 100644
--- a/test/ruby/test_utf16.rb
+++ b/test/ruby/test_utf16.rb
@@ -132,13 +132,21 @@ EOT
   end
 
   def test_hex
-    s1 = "f\0f\0".force_encoding("utf-16le")
-    assert_equal(255, s1.hex, "#{encdump s1}.hex")
+    assert_raise(ArgumentError) {
+      "ff".encode("utf-16le").hex
+    }
+    assert_raise(ArgumentError) {
+      "ff".encode("utf-16be").hex
+    }
   end
 
   def test_oct
-    assert_equal(077, "77".encode("utf-16le").oct)
-    assert_equal(077, "77".encode("utf-16be").oct)
+    assert_raise(ArgumentError) {
+      "77".encode("utf-16le").oct
+    }
+    assert_raise(ArgumentError) {
+      "77".encode("utf-16be").oct
+    }
   end
 
   def test_count
@@ -224,7 +232,9 @@ EOT
 
   def test_chomp
     s = "\1\n".force_encoding("utf-16be")
-    assert_str_equal(s, s.chomp, "#{encdump s}.chomp")
+    assert_raise(ArgumentError, "#{encdump s}.chomp") {
+      s.chomp
+    }
   end
 
   def test_succ
diff --git a/time.c b/time.c
index 8b3ac6c501..455f15bc1f 100644
--- a/time.c
+++ b/time.c
@@ -12,6 +12,7 @@
 #include "ruby/ruby.h"
 #include <sys/types.h>
 #include <time.h>
+#include "ruby/encoding.h"
 
 #ifdef HAVE_UNISTD_H
 #include <unistd.h>
@@ -2077,6 +2078,9 @@ time_strftime(VALUE time, VALUE format)
 	time_get_tm(time, tobj->gmt);
     }
     StringValue(format);
+    if (!rb_enc_str_asciicompat_p(format)) {
+	rb_raise(rb_eArgError, "format should have ASCII compatible encoding");
+    }
     format = rb_str_new4(format);
     fmt = RSTRING_PTR(format);
     len = RSTRING_LEN(format);