string.c: cut down intermediate string

* string.c (rb_external_str_new_with_enc): cut down intermediate
  string for conversion source, by appending with conversion.

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@58709 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

1 files changed, 30 insertions, 3 deletions

diff --git a/string.c b/string.c
index 1d30a153cb..1d357638a5 100644
--- a/string.c
+++ b/string.c
@@ -997,10 +997,37 @@ rb_str_conv_enc(VALUE str, rb_encoding *from, rb_encoding *to)
 VALUE
 rb_external_str_new_with_enc(const char *ptr, long len, rb_encoding *eenc)
 {
+    rb_encoding *ienc;
     VALUE str;
-
-    str = rb_tainted_str_new_with_enc(ptr, len, eenc);
-    return rb_external_str_with_enc(str, eenc);
+    const int eidx = rb_enc_to_index(eenc);
+
+    /* ASCII-8BIT case, no conversion */
+    if ((eidx == rb_ascii8bit_encindex()) ||
+	(eidx == rb_usascii_encindex() && search_nonascii(ptr, ptr + len))) {
+	return rb_tainted_str_new(ptr, len);
+    }
+    /* no default_internal or same encoding, no conversion */
+    ienc = rb_default_internal_encoding();
+    if (!ienc || eenc == ienc) {
+	return rb_tainted_str_new_with_enc(ptr, len, eenc);
+    }
+    /* ASCII compatible, and ASCII only string, no conversion in
+     * default_internal */
+    if ((eidx == rb_ascii8bit_encindex()) ||
+	(eidx == rb_usascii_encindex()) ||
+	(rb_enc_asciicompat(eenc) && !search_nonascii(ptr, ptr + len))) {
+	return rb_tainted_str_new_with_enc(ptr, len, ienc);
+    }
+    /* convert from the given encoding to default_internal */
+    str = rb_tainted_str_new_with_enc(NULL, 0, ienc);
+    /* when the conversion failed for some reason, just ignore the
+     * default_internal and result in the given encoding as-is. */
+    if (NIL_P(rb_str_cat_conv_enc_opts(str, 0, ptr, len, eenc, 0, Qnil))) {
+	STR_SET_LEN(str, 0);
+	rb_enc_associate(str, eenc);
+	rb_str_cat(str, ptr, len);
+    }
+    return str;
 }
 
 VALUE