[Emacs-diffs] /srv/bzr/emacs/trunk r109251: Fix non-ASCII input in non-GUI frames on MS-Windows. (Bug#12055)

[Eli Zaretskii]

------------------------------------------------------------
revno: 109251
fixes bug: http://debbugs.gnu.org/12055
committer: Eli Zaretskii <address@hidden>
branch nick: trunk
timestamp: Sat 2012-07-28 19:57:57 +0300
message:
  Fix non-ASCII input in non-GUI frames on MS-Windows.  (Bug#12055)
  
   src/w32inevt.c: Include w32inevt.h.
   (w32_read_console_input): New inline function, calls either
   ReadConsoleInputA or ReadConsoleInputW, depending on the value of
   w32_console_unicode_input.
   (fill_queue): Call w32_read_console_input instead of ReadConsoleInput.
   (w32_kbd_patch_key, key_event): Use the codepage returned by
   GetConsoleCP, rather than the ANSI codepage returned by GetLocaleInfo.
   (key_event): use uChar.UnicodeChar only if
   w32_console_unicode_input is non-zero.
   src/w32console.c: Include w32heap.h.
   <w32_console_unicode_input>: New global variable.
   (initialize_w32_display): Set w32_console_unicode_input to 1 on NT
   family of Windows, zero otherwise.
   src/w32inevt.h: Declare w32_console_unicode_input.
   lisp/international/mule-cmds.el (set-locale-environment): In a
   console session on MS-Windows, set up keyboard and terminal
   encoding from the OEM codepage, not the ANSI codepage.
modified:
  lisp/ChangeLog
  lisp/international/mule-cmds.el
  src/ChangeLog
  src/w32console.c
  src/w32inevt.c
  src/w32inevt.h

=== modified file 'lisp/ChangeLog'
--- a/lisp/ChangeLog    2012-07-28 15:12:12 +0000
+++ b/lisp/ChangeLog    2012-07-28 16:57:57 +0000
@@ -1,3 +1,10 @@
+2012-07-28  Eli Zaretskii  <address@hidden>
+
+       * international/mule-cmds.el (set-locale-environment): In a
+       console session on MS-Windows, set up keyboard and terminal
+       encoding from the OEM codepage, not the ANSI codepage.
+       (Bug#12055)
+
 2012-07-28  Chong Yidong  <address@hidden>
 
        * progmodes/gdb-mi.el (gdb-place-breakpoints): Fix the call to

=== modified file 'lisp/international/mule-cmds.el'
--- a/lisp/international/mule-cmds.el   2012-07-25 23:11:23 +0000
+++ b/lisp/international/mule-cmds.el   2012-07-28 16:57:57 +0000
@@ -2655,23 +2655,32 @@
 
     ;; On Windows, override locale-coding-system,
     ;; default-file-name-coding-system, keyboard-coding-system,
-    ;; terminal-coding-system with system codepage.
+    ;; terminal-coding-system with the appropriate codepages.
     (when (boundp 'w32-ansi-code-page)
-      (let ((code-page-coding (intern (format "cp%d" w32-ansi-code-page))))
-       (when (coding-system-p code-page-coding)
-         (unless frame (setq locale-coding-system code-page-coding))
-         (set-keyboard-coding-system code-page-coding frame)
-         (set-terminal-coding-system code-page-coding frame)
-         ;; Set default-file-name-coding-system last, so that Emacs
-         ;; doesn't try to use cpNNNN when it defines keyboard and
-         ;; terminal encoding.  That's because the above two lines
-         ;; will want to load code-pages.el, where cpNNNN are
-         ;; defined; if default-file-name-coding-system were set to
-         ;; cpNNNN while these two lines run, Emacs will want to use
-         ;; it for encoding the file name it wants to load.  And that
-         ;; will fail, since cpNNNN is not yet usable until
-         ;; code-pages.el finishes loading.
-         (setq default-file-name-coding-system code-page-coding))))
+      (let ((ansi-code-page-coding (intern (format "cp%d" w32-ansi-code-page)))
+           (oem-code-page-coding
+            (intern (format "cp%d" (w32-get-console-codepage))))
+           (oem-code-page-output-coding
+            (intern (format "cp%d" (w32-get-console-output-codepage))))
+           ansi-cs-p oem-cs-p oem-o-cs-p)
+       (setq ansi-cs-p (coding-system-p ansi-code-page-coding))
+       (setq oem-cs-p (coding-system-p oem-code-page-coding))
+       (setq oem-o-cs-p (coding-system-p oem-code-page-output-coding))
+       ;; Set the keyboard and display encoding to either the current
+       ;; ANSI codepage of the OEM codepage, depending on whether
+       ;; this is a GUI or a TTY frame.
+       (when ansi-cs-p
+         (unless frame (setq locale-coding-system ansi-code-page-coding))
+         (when (display-graphic-p frame)
+           (set-keyboard-coding-system ansi-code-page-coding frame)
+           (set-terminal-coding-system ansi-code-page-coding frame))
+         (setq default-file-name-coding-system ansi-code-page-coding))
+       (when oem-cs-p
+         (unless (display-graphic-p frame)
+           (set-keyboard-coding-system oem-code-page-coding frame)
+           (set-terminal-coding-system
+            (if oem-o-cs-p oem-code-page-output-coding oem-code-page-coding)
+            frame)))))
 
     (when (eq system-type 'darwin)
       ;; On Darwin, file names are always encoded in utf-8, no matter

=== modified file 'src/ChangeLog'
--- a/src/ChangeLog     2012-07-28 07:59:34 +0000
+++ b/src/ChangeLog     2012-07-28 16:57:57 +0000
@@ -1,5 +1,23 @@
 2012-07-28  Eli Zaretskii  <address@hidden>
 
+       Fix non-ASCII input in non-GUI frames on MS-Windows.  (Bug#12055)
+       * w32inevt.c: Include w32inevt.h.
+       (w32_read_console_input): New inline function, calls either
+       ReadConsoleInputA or ReadConsoleInputW, depending on the value of
+       w32_console_unicode_input.
+       (fill_queue): Call w32_read_console_input instead of ReadConsoleInput.
+       (w32_kbd_patch_key, key_event): Use the codepage returned by
+       GetConsoleCP, rather than the ANSI codepage returned by GetLocaleInfo.
+       (key_event): use uChar.UnicodeChar only if
+       w32_console_unicode_input is non-zero.
+
+       * w32console.c: Include w32heap.h.
+       <w32_console_unicode_input>: New global variable.
+       (initialize_w32_display): Set w32_console_unicode_input to 1 on NT
+       family of Windows, zero otherwise.
+
+       * w32inevt.h: Declare w32_console_unicode_input.
+
        * xdisp.c (init_iterator): Don't reference tip_frame in a build
        --without-x.  (Bug#11742)
 

=== modified file 'src/w32console.c'
--- a/src/w32console.c  2012-06-28 07:50:27 +0000
+++ b/src/w32console.c  2012-07-28 16:57:57 +0000
@@ -37,6 +37,7 @@
 #include "termhooks.h"
 #include "termchar.h"
 #include "dispextern.h"
+#include "w32heap.h"   /* for os_subtype */
 #include "w32inevt.h"
 
 /* from window.c */
@@ -67,6 +68,7 @@
 #endif
 
 HANDLE  keyboard_handle;
+int w32_console_unicode_input;
 
 
 /* Setting this as the ctrl handler prevents emacs from being killed when
@@ -786,6 +788,11 @@
                       info.srWindow.Left);
     }
 
+  if (os_subtype == OS_NT)
+    w32_console_unicode_input = 1;
+  else
+    w32_console_unicode_input = 0;
+
   /* Setup w32_display_info structure for this frame. */
 
   w32_initialize_display_info (build_string ("Console"));

=== modified file 'src/w32inevt.c'
--- a/src/w32inevt.c    2012-05-26 11:58:19 +0000
+++ b/src/w32inevt.c    2012-07-28 16:57:57 +0000
@@ -41,6 +41,7 @@
 #include "termchar.h"
 #include "w32heap.h"
 #include "w32term.h"
+#include "w32inevt.h"
 
 /* stdin, from w32console.c */
 extern HANDLE keyboard_handle;
@@ -61,6 +62,15 @@
 /* Temporarily store lead byte of DBCS input sequences.  */
 static char dbcs_lead = 0;
 
+static inline BOOL
+w32_read_console_input (HANDLE h, INPUT_RECORD *rec, DWORD recsize,
+                       DWORD *waiting)
+{
+  return (w32_console_unicode_input
+         ? ReadConsoleInputW (h, rec, recsize, waiting)
+         : ReadConsoleInputA (h, rec, recsize, waiting));
+}
+
 static int
 fill_queue (BOOL block)
 {
@@ -80,8 +90,8 @@
        return 0;
     }
 
-  rc = ReadConsoleInput (keyboard_handle, event_queue, EVENT_QUEUE_SIZE,
-                        &events_waiting);
+  rc = w32_read_console_input (keyboard_handle, event_queue, EVENT_QUEUE_SIZE,
+                              &events_waiting);
   if (!rc)
     return -1;
   queue_ptr = event_queue;
@@ -224,7 +234,7 @@
 #endif
 
   /* On NT, call ToUnicode instead and then convert to the current
-     locale's default codepage.  */
+     console input codepage.  */
   if (os_subtype == OS_NT)
     {
       WCHAR buf[128];
@@ -233,14 +243,9 @@
                          keystate, buf, 128, 0);
       if (isdead > 0)
        {
-         char cp[20];
-         int cpId;
+         int cpId = GetConsoleCP ();
 
          event->uChar.UnicodeChar = buf[isdead - 1];
-
-         GetLocaleInfo (GetThreadLocale (),
-                        LOCALE_IDEFAULTANSICODEPAGE, cp, 20);
-         cpId = atoi (cp);
          isdead = WideCharToMultiByte (cpId, 0, buf, isdead,
                                        ansi_code, 4, NULL, NULL);
        }
@@ -447,26 +452,34 @@
        }
       else if (event->uChar.AsciiChar > 0)
        {
+         /* Pure ASCII characters < 128.  */
          emacs_ev->kind = ASCII_KEYSTROKE_EVENT;
          emacs_ev->code = event->uChar.AsciiChar;
        }
-      else if (event->uChar.UnicodeChar > 0)
+      else if (event->uChar.UnicodeChar > 0
+              && w32_console_unicode_input)
        {
+         /* Unicode codepoint; only valid if we are using Unicode
+            console input mode.  */
          emacs_ev->kind = MULTIBYTE_CHAR_KEYSTROKE_EVENT;
          emacs_ev->code = event->uChar.UnicodeChar;
        }
       else
        {
-         /* Fallback for non-Unicode versions of Windows.  */
+         /* Fallback handling of non-ASCII characters for non-Unicode
+            versions of Windows, and for non-Unicode input on NT
+            family of Windows.  Only characters in the current
+            console codepage are supported by this fallback.  */
          wchar_t code;
          char dbcs[2];
-          char cp[20];
           int cpId;
 
-         /* Get the codepage to interpret this key with.  */
-          GetLocaleInfo (GetThreadLocale (),
-                        LOCALE_IDEFAULTANSICODEPAGE, cp, 20);
-          cpId = atoi (cp);
+         /* Get the current console input codepage to interpret this
+            key with.  Note that the system defaults for the OEM
+            codepage could have been changed by calling SetConsoleCP
+            or w32-set-console-codepage, so using GetLocaleInfo to
+            get LOCALE_IDEFAULTCODEPAGE is not TRT here.  */
+          cpId = GetConsoleCP ();
 
          dbcs[0] = dbcs_lead;
          dbcs[1] = event->uChar.AsciiChar;
@@ -501,6 +514,7 @@
     }
   else
     {
+      /* Function keys and other non-character keys.  */
       emacs_ev->kind = NON_ASCII_KEYSTROKE_EVENT;
       emacs_ev->code = event->wVirtualKeyCode;
     }

=== modified file 'src/w32inevt.h'
--- a/src/w32inevt.h    2012-01-19 07:21:25 +0000
+++ b/src/w32inevt.h    2012-07-28 16:57:57 +0000
@@ -19,6 +19,8 @@
 #ifndef EMACS_W32INEVT_H
 #define EMACS_W32INEVT_H
 
+extern int w32_console_unicode_input;
+
 extern int w32_console_read_socket (struct terminal *term, int numchars,
                                    struct input_event *hold_quit);
 extern void w32_console_mouse_position (FRAME_PTR *f, int insist,