doc: Remove obsolete reference to the lack of Unicode support.

* doc/ref/api-data.texi (Bytevectors as Strings): Remove obsolete
  footnote on the lack of Unicode support.

* test-suite/tests/bytevectors.test ("2.9 Operations on
  Strings")["string->utf8 [latin-1]", "utf8->string [latin-1]"]: Remove
  use of `with-latin1-locale'.
  ["string->utf32 [Greek]"]: New tests.

diff --git a/doc/ref/api-data.texi b/doc/ref/api-data.texi
index d413567..8153a5d 100755 (executable)
--- a/doc/ref/api-data.texi
+++ b/doc/ref/api-data.texi
@@ -4406,12 +4406,7 @@ the host's native endianness.
 @cindex Unicode string encoding
 
 Bytevector contents can also be interpreted as Unicode strings encoded
-in one of the most commonly available encoding formats@footnote{Guile
-1.8 does @emph{not} support Unicode strings.  Therefore, the procedures
-described here assume that Guile strings are internally encoded
-according to the current locale.  For instance, if @code{$LC_CTYPE} is
-@code{fr_FR.ISO-8859-1}, then @code{string->utf-8} @i{et al.} will
-assume that Guile strings are Latin-1-encoded.}.
+in one of the most commonly available encoding formats.
 
 @lisp
 (utf8->string (u8-list->bytevector '(99 97 102 101)))

diff --git a/test-suite/tests/bytevectors.test b/test-suite/tests/bytevectors.test
index 3f68c81..3a7cc2d 100644 (file)
--- a/test-suite/tests/bytevectors.test
+++ b/test-suite/tests/bytevectors.test
@@ -1,7 +1,7 @@
-;;;; bytevectors.test --- R6RS bytevectors. -*- mode: scheme; coding: iso-8859-1; -*-
+;;;; bytevectors.test --- R6RS bytevectors. -*- mode: scheme; coding: utf-8; -*-
 ;;;;
 ;;;; Copyright (C) 2009, 2010 Free Software Foundation, Inc.
-;;;; Ludovic Courtès
+;;;; Ludovic Courtès
 ;;;;
 ;;;; This library is free software; you can redistribute it and/or
 ;;;; modify it under the terms of the GNU Lesser General Public
@@ -394,12 +394,11 @@
                    (map integer->char (bytevector->u8-list utf8))))))
 
   (pass-if "string->utf8 [latin-1]"
-    (with-latin1-locale
-      (let* ((str  "hé, ça va bien ?")
-             (utf8 (string->utf8 str)))
-        (and (bytevector? utf8)
-             (= (bytevector-length utf8)
-                (+ 2 (string-length str)))))))
+    (let* ((str  "hé, ça va bien ?")
+           (utf8 (string->utf8 str)))
+      (and (bytevector? utf8)
+           (= (bytevector-length utf8)
+              (+ 2 (string-length str))))))
 
   (pass-if "string->utf16"
     (let* ((str   "hello, world")
@@ -435,6 +434,13 @@
                         (bytevector->uint-list utf32
                                                (endianness big) 4))))))
 
+  (pass-if "string->utf32 [Greek]"
+    (let* ((str   "Ἄνεμοι")
+           (utf32 (string->utf32 str)))
+      (and (bytevector? utf32)
+           (equal? (bytevector->uint-list utf32 (endianness big) 4)
+                   '(#x1f0c #x3bd #x3b5 #x3bc #x3bf #x3b9)))))
+
   (pass-if "string->utf32 [little]"
     (let* ((str   "hello, world")
            (utf32 (string->utf32 str (endianness little))))
@@ -457,12 +463,11 @@
                    (map integer->char (bytevector->u8-list utf8))))))
 
   (pass-if "utf8->string [latin-1]"
-    (with-latin1-locale
-      (let* ((utf8  (string->utf8 "hé, ça va bien ?"))
-             (str   (utf8->string utf8)))
-        (and (string? str)
-             (= (string-length str)
-                (- (bytevector-length utf8) 2))))))
+    (let* ((utf8  (string->utf8 "hé, ça va bien ?"))
+           (str   (utf8->string utf8)))
+      (and (string? str)
+           (= (string-length str)
+              (- (bytevector-length utf8) 2)))))
 
   (pass-if "utf16->string"
     (let* ((utf16  (uint-list->bytevector (map char->integer