(utf-8-sig, utf-8-auto): New coding systems.

3 files changed, 54 insertions, 1 deletions

diff --git a/lisp/ChangeLog b/lisp/ChangeLog
index 8339022aac4..b18b186f6de 100644
--- a/lisp/ChangeLog
+++ b/lisp/ChangeLog
@@ -1,3 +1,11 @@
+2008-05-29  Kenichi Handa  <handa@m17n.org>
+
+        * international/mule-conf.el (utf-8-sig, utf-8-auto): New coding
+        systems.
+
+        * international/mule.el (define-coding-system): Accept :bom for
+        utf-8.
+
 2008-05-29  Espen Wiborg  <espen.wiborg@telio.no>  (tiny change)
 
         * international/utf-7.el (utf-7-encode): Use the right escape char
diff --git a/lisp/international/mule-conf.el b/lisp/international/mule-conf.el
index 6fe69aa6630..43fbf2ba800 100644
--- a/lisp/international/mule-conf.el
+++ b/lisp/international/mule-conf.el
@@ -1253,12 +1253,26 @@ is treated as a character."
  :mnemonic ?M)
 
 (define-coding-system 'utf-8
-  "UTF-8."
+  "UTF-8 (no signature (BOM))"
   :coding-type 'utf-8
   :mnemonic ?U
   :charset-list '(unicode)
   :mime-charset 'utf-8)
 
+(define-coding-system 'utf-8-sig
+  "UTF-8 (with signature (BOM))"
+  :coding-type 'utf-8
+  :mnemonic ?U
+  :charset-list '(unicode)
+  :bom t)
+
+(define-coding-system 'utf-8-auto
+  "UTF-8 (auto-detect signature (BOM))"
+  :coding-type 'utf-8
+  :mnemonic ?U
+  :charset-list '(unicode)
+  :bom '(utf-8-sig . utf-8))
+
 (define-coding-system-alias 'mule-utf-8 'utf-8)
 
 (define-coding-system 'utf-8-emacs
diff --git a/src/ChangeLog b/src/ChangeLog
index f61e8c3c595..d79125ca7ee 100644
--- a/src/ChangeLog
+++ b/src/ChangeLog
@@ -1,3 +1,34 @@
+2008-05-29  Kenichi Handa  <handa@m17n.org>
+
+        * coding.h (enum define_coding_utf8_arg_index): New enum.
+        (enum coding_attr_index): Change coding_attr_utf_16_bom to
+        coding_attr_utf_bom.
+        (enum utf_bom_type): Renamed from utf_16_bom_type.
+        (struct utf_16_spec): Adjusted for the above change.
+        (struct coding_system): Add utf_8_bom in `spec' union.
+
+        * coding.c (CODING_UTF_8_BOM): New macro.
+        (enum coding_category): Delete coding_category_utf_8, add
+        coding_category_utf_8_auto, coding_category_utf_8_nosig, and
+        coding_category_utf_8_sig.
+        (CATEGORY_MASK_UTF_8): Delete it.
+        (CATEGORY_MASK_UTF_8_AUTO, CATEGORY_MASK_UTF_8_NOSIG)
+        (CATEGORY_MASK_UTF_8_SIG): New macros.
+        (CATEGORY_MASK_ANY): Delete CATEGORY_MASK_UTF_8, add
+        CATEGORY_MASK_UTF_8_AUTO, CATEGORY_MASK_UTF_8_NOSIG, and
+        CATEGORY_MASK_UTF_8_SIG.
+        (CATEGORY_MASK_UTF_8): New macro.
+        (UTF_BOM, UTF_8_BOM_1, UTF_8_BOM_2, UTF_8_BOM_3): New macros.
+        (detect_coding_utf_8): Check BOM.
+        (decode_coding_utf_8, encode_coding_utf_8): Handle BOM.
+        (decode_coding_utf_16): Adjusted for the change of enum
+        utf_bom_type.
+        (encode_coding_utf_16): Likewise.
+        (setup_coding_system): Likewise.  Set CODING_UTF_8_BOM (coding).
+        (detect_coding, detect_coding_system): Handle utf-8-auto.
+        (Fdefine_coding_system_internal): Handle `bom' property for utf-8.
+        (syms_of_coding): Fix setting up of Vcoding_category_table.
+
 2008-05-29  Stefan Monnier  <monnier@iro.umontreal.ca>
 
         * process.c (Faccept_process_output): If `millisec' is non-nil,