From 800f04c6a521c007e9837813b3564ae6b491e31c Mon Sep 17 00:00:00 2001
From: naruse <naruse@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>
Date: Sun, 8 Jan 2012 20:42:45 +0000
Subject: * numeric.c (rb_enc_uint_char): raise RangeError when added codepoint
   is invalid. [Feature #5855] [Bug #5863] [Bug #5864]

* string.c (rb_str_concat): ditto.

* string.c (rb_str_concat): set encoding as ASCII-8BIT when the string
  is US-ASCII and the argument is an integer greater than 127.

* regenc.c (onigenc_mb2_code_to_mbclen): rearrange error code.

* enc/euc_jp.c (code_to_mbclen): ditto.

* enc/shift_jis.c (code_to_mbclen): ditto.

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@34236 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
---
 string.c | 43 ++++++++++++++++++++++++++++++++++---------
 1 file changed, 34 insertions(+), 9 deletions(-)

(limited to 'string.c')

diff --git a/string.c b/string.c
index 606fef7a42..55691d017c 100644
--- a/string.c
+++ b/string.c
@@ -2074,10 +2074,11 @@ rb_str_append(VALUE str, VALUE str2)
 VALUE
 rb_str_concat(VALUE str1, VALUE str2)
 {
-    unsigned int lc;
+    unsigned int code;
+    rb_encoding *enc = STR_ENC_GET(str1);
 
     if (FIXNUM_P(str2) || RB_TYPE_P(str2, T_BIGNUM)) {
-	if (rb_num_to_uint(str2, &lc) == 0) {
+	if (rb_num_to_uint(str2, &code) == 0) {
 	}
 	else if (FIXNUM_P(str2)) {
 	    rb_raise(rb_eRangeError, "%ld out of char range", FIX2LONG(str2));
@@ -2089,22 +2090,46 @@ rb_str_concat(VALUE str1, VALUE str2)
     else {
 	return rb_str_append(str1, str2);
     }
-    {
-	rb_encoding *enc = STR_ENC_GET(str1);
+
+    if (enc == rb_usascii_encoding()) {
+	/* US-ASCII automatically extended to ASCII-8BIT */
+	char buf[1] = {(char)code};
+	if (code > 0xFF) {
+	    rb_raise(rb_eRangeError, "%u out of char range", code);
+	}
+	rb_str_cat(str1, buf, 1);
+	if (code > 127) {
+	    rb_enc_associate(str1, rb_ascii8bit_encoding());
+	    ENC_CODERANGE_SET(str1, ENC_CODERANGE_VALID);
+	}
+    }
+    else {
 	long pos = RSTRING_LEN(str1);
 	int cr = ENC_CODERANGE(str1);
 	int len;
+	char *buf;
 
-	if ((len = rb_enc_codelen(lc, enc)) <= 0) {
-	    rb_raise(rb_eRangeError, "%u invalid char", lc);
+	switch (len = rb_enc_codelen(code, enc)) {
+	  case ONIGERR_INVALID_CODE_POINT_VALUE:
+	    rb_raise(rb_eRangeError, "invalid codepoint 0x%X in %s", code, rb_enc_name(enc));
+	    break;
+	  case ONIGERR_TOO_BIG_WIDE_CHAR_VALUE:
+	  case 0:
+	    rb_raise(rb_eRangeError, "%u out of char range", code);
+	    break;
+	}
+	buf = ALLOCA_N(char, len + 1);
+	rb_enc_mbcput(code, buf, enc);
+	if (rb_enc_precise_mbclen(buf, buf + len + 1, enc) != len) {
+	    rb_raise(rb_eRangeError, "invalid codepoint 0x%X in %s", code, rb_enc_name(enc));
 	}
 	rb_str_resize(str1, pos+len);
-	rb_enc_mbcput(lc, RSTRING_PTR(str1)+pos, enc);
-	if (cr == ENC_CODERANGE_7BIT && lc > 127)
+	strncpy(RSTRING_PTR(str1) + pos, buf, len);
+	if (cr == ENC_CODERANGE_7BIT && code > 127)
 	    cr = ENC_CODERANGE_VALID;
 	ENC_CODERANGE_SET(str1, cr);
-	return str1;
     }
+    return str1;
 }
 
 /*
-- 
cgit v1.2.3