merge revision(s) 78b7646bdb91285873ac26bca060591e06c45afe, b4a62a1ca949d93332ad8bce0fcc273581160cc5: [Backport #21842]

	[PATCH] [Bug #21842] Let `rb_interned_str` return US-ASCII if possible

	[PATCH] [DOC] Update docs for rb_interned_str and related functions (#15897)

	Related to [Bug #21842].

	* rb_interned_str: document what decides whether the returned string is
	  in US-ASCII or BINARY encoding.
	* rb_interned_str_cstr: include the same description as rb_interned_str
	  for the encoding. This one was still missing the update for US-ASCII
	  and erroneously said the returned string was alwasy in BINARY encoding
	* rb_str_to_interned_str: document how the encoding of the result is
	  defined.

	Co-authored-by: Herwin <herwinw@users.noreply.github.com>

3 files changed, 22 insertions, 7 deletions

diff --git a/include/ruby/internal/intern/string.h b/include/ruby/internal/intern/string.h
index 75a28143fb..8bd1ffcfb4 100644
--- a/include/ruby/internal/intern/string.h
+++ b/include/ruby/internal/intern/string.h
@@ -412,8 +412,8 @@ VALUE rb_utf8_str_new_static(const char *ptr, long len);
 
 /**
  * Identical to rb_interned_str(),  except it takes a Ruby's  string instead of
- * C's.  It can also be seen  as a routine identical to rb_str_new_shared(),
- * except it returns an infamous "f"string.
+ * C's and preserves its encoding.  It can also be seen  as a routine identical
+ * to rb_str_new_shared(), except it returns an infamous "f"string.
  *
  * @param[in]  str  An object of ::RString.
  * @return     An instance  of ::rb_cString, either cached  or allocated, which
@@ -444,8 +444,9 @@ VALUE rb_str_to_interned_str(VALUE str);
  *                           terminating NUL character.
  * @exception  rb_eArgError  `len` is negative.
  * @return     A  found or  created instance  of ::rb_cString,  of `len`  bytes
- *             length, of  "binary" encoding,  whose contents are  identical to
- *             that of `ptr`.
+ *             length,  whose  contents  are  identical  to that of `ptr`.  Its
+ *             encoding  will  be US-ASCII if all bytes are lower ASCII, BINARY
+ *             otherwise.
  * @pre        At  least  `len` bytes  of  continuous  memory region  shall  be
  *             accessible via `ptr`.
  */
@@ -461,8 +462,9 @@ RBIMPL_ATTR_NONNULL(())
  *
  * @param[in]  ptr             A C string.
  * @exception  rb_eNoMemError  Failed to allocate memory.
- * @return     An  instance  of  ::rb_cString,   of  "binary"  encoding,  whose
- *             contents are verbatim copy of `ptr`.
+ * @return     An  instance  of  ::rb_cString, whose contents are verbatim copy
+ *             of `ptr`. Its encoding  will  be US-ASCII if all bytes are lower
+ *             ASCII, BINARY otherwise.
  * @pre        `ptr` must not be a null pointer.
  */
 VALUE rb_interned_str_cstr(const char *ptr);
diff --git a/string.c b/string.c
index b70cee020d..516fc81b93 100644
--- a/string.c
+++ b/string.c
@@ -12705,7 +12705,15 @@ VALUE
 rb_interned_str(const char *ptr, long len)
 {
     struct RString fake_str = {RBASIC_INIT};
-    return register_fstring(setup_fake_str(&fake_str, ptr, len, ENCINDEX_US_ASCII), true, false);
+    int encidx = ENCINDEX_US_ASCII;
+    int coderange = ENC_CODERANGE_7BIT;
+    if (len > 0 && search_nonascii(ptr, ptr + len)) {
+        encidx = ENCINDEX_ASCII_8BIT;
+        coderange = ENC_CODERANGE_VALID;
+    }
+    VALUE str = setup_fake_str(&fake_str, ptr, len, encidx);
+    ENC_CODERANGE_SET(str, coderange);
+    return register_fstring(str, true, false);
 }
 
 VALUE
diff --git a/test/-ext-/string/test_interned_str.rb b/test/-ext-/string/test_interned_str.rb
index 340dba41e8..a81cb59aa5 100644
--- a/test/-ext-/string/test_interned_str.rb
+++ b/test/-ext-/string/test_interned_str.rb
@@ -9,4 +9,9 @@ class Test_RbInternedStr < Test::Unit::TestCase
     src << "b" * 20
     assert_equal "a" * 20, interned_str
   end
+
+  def test_interned_str_encoding
+    src = :ascii.name
+    assert_equal Encoding::US_ASCII, Bug::String.rb_interned_str_dup(src).encoding
+  end
 end