encoding.c: refill terminator at associating encoding

* encoding.c (rb_enc_associate_index): refill the terminator if it
  becomes longer than before.  [ruby-dev:47500] [Bug #8624]
* string.c (str_null_char, str_fill_term): get rid of out of bound
  access.
* string.c (rb_str_fill_terminator): add a parameter for the length of
  new terminator.

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@41930 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

ChangeLog

@@ -1,3 +1,14 @@
+Fri Jul 12 16:28:37 2013  Nobuyoshi Nakada  <nobu@ruby-lang.org>
+
+	* encoding.c (rb_enc_associate_index): refill the terminator if it
+	  becomes longer than before.  [ruby-dev:47500] [Bug #8624]
+
+	* string.c (str_null_char, str_fill_term): get rid of out of bound
+	  access.
+
+	* string.c (rb_str_fill_terminator): add a parameter for the length of
+	  new terminator.
+
 Fri Jul 12 11:26:25 2013  Masaki Matsushita  <glass.saga@gmail.com>
 
 	* hash.c (rb_hash_reject_bang): do not call rb_hash_foreach() if RHash

encoding.c

@@ -777,10 +777,12 @@ VALUE
 rb_enc_associate_index(VALUE obj, int idx)
 {
     rb_encoding *enc;
+    int oldidx, oldtermlen, termlen;
 
 /*    enc_check_capable(obj);*/
     rb_check_frozen(obj);
-    if (rb_enc_get_index(obj) == idx)
+    oldidx = rb_enc_get_index(obj);
+    if (oldidx == idx)
 	return obj;
     if (SPECIAL_CONST_P(obj)) {
 	rb_raise(rb_eArgError, "cannot set encoding");
@@ -790,6 +792,11 @@ rb_enc_associate_index(VALUE obj, int idx)
 	!rb_enc_asciicompat(enc)) {
 	ENC_CODERANGE_CLEAR(obj);
     }
+    termlen = rb_enc_mbminlen(enc);
+    oldtermlen = rb_enc_mbminlen(rb_enc_from_index(oldidx));
+    if (oldtermlen < termlen && RB_TYPE_P(obj, T_STRING)) {
+	rb_str_fill_terminator(obj, oldtermlen);
+    }
     enc_set_index(obj, idx);
     return obj;
 }

internal.h

@@ -441,7 +441,7 @@ VALUE rb_str_quote_unprintable(VALUE);
 VALUE rb_id_quote_unprintable(ID);
 #define QUOTE(str) rb_str_quote_unprintable(str)
 #define QUOTE_ID(id) rb_id_quote_unprintable(id)
-void rb_str_fill_terminator(VALUE str);
+void rb_str_fill_terminator(VALUE str, const int termlen);
 
 /* struct.c */
 VALUE rb_struct_init_copy(VALUE copy, VALUE s);

string.c

@@ -1483,12 +1483,12 @@ rb_string_value_ptr(volatile VALUE *ptr)
 }
 
 static const char *
-str_null_char(const char *s, long len, rb_encoding *enc)
+str_null_char(const char *s, long len, const int minlen, rb_encoding *enc)
 {
     int n;
     const char *e = s + len;
 
-    for (; s < e; s += n) {
+    for (; s + minlen <= e; s += n) {
 	if (!rb_enc_codepoint_len(s, e, &n, enc)) return s;
     }
     return 0;
@@ -1497,7 +1497,8 @@ str_null_char(const char *s, long len, rb_encoding *enc)
 static char *
 str_fill_term(VALUE str, char *s, long len, int termlen, rb_encoding *enc)
 {
-    long capa = rb_str_capacity(str) + 1;
+    int oldtermlen = rb_enc_mbminlen(enc);
+    long capa = rb_str_capacity(str) + oldtermlen;
     int n;
 
     if (capa < len + termlen) {
@@ -1505,8 +1506,13 @@ str_fill_term(VALUE str, char *s, long len, int termlen, rb_encoding *enc)
     }
     else {
 	const char *e = s + len;
-	if (!rb_enc_ascget(e, e + termlen, &n, enc)) return s;
+	int diff = 0;
-	rb_str_modify(str);
+	if (termlen > oldtermlen) diff = termlen - oldtermlen;
+	if (!diff && str_independent(str) &&
+	    !rb_enc_ascget(e, e + oldtermlen, &n, enc)) {
+	    return s;
+	}
+	str_make_independent_expand(str, diff);
     }
     s = RSTRING_PTR(str);
     TERM_FILL(s + len, termlen);
@@ -1523,7 +1529,7 @@ rb_string_value_cstr(volatile VALUE *ptr)
     const int minlen = rb_enc_mbminlen(enc);
 
     if (minlen > 1) {
-	if (str_null_char(s, len, enc)) {
+	if (str_null_char(s, len, minlen, enc)) {
 	    rb_raise(rb_eArgError, "string contains null char");
 	}
 	return str_fill_term(str, s, len, minlen, enc);
@@ -1540,13 +1546,12 @@ rb_string_value_cstr(volatile VALUE *ptr)
 }
 
 void
-rb_str_fill_terminator(VALUE str)
+rb_str_fill_terminator(VALUE str, const int newminlen)
 {
     char *s = RSTRING_PTR(str);
     long len = RSTRING_LEN(str);
     rb_encoding *enc = rb_enc_get(str);
-    const int minlen = rb_enc_mbminlen(enc);
+    str_fill_term(str, s, len, newminlen, enc);
-    str_fill_term(str, s, len, minlen, enc);
 }
 
 VALUE

transcode.c

@@ -2760,7 +2760,6 @@ str_encode_associate(VALUE str, int encidx)
     int cr = 0;
 
     rb_enc_associate_index(str, encidx);
-    rb_str_fill_terminator(str);
 
     /* transcoded string never be broken. */
     if (rb_enc_asciicompat(rb_enc_from_index(encidx))) {