Merge branch 'fix_console_encoding' into 'master'

Add and use g_get_console_charset when printing text

Closes #1270

See merge request GNOME/glib!767

docs/reference/glib/glib-sections.txt

@@ -2946,6 +2946,7 @@ GConvertError
 <SUBSECTION>
 g_get_charset
 g_get_codeset
+g_get_console_charset
 
 <SUBSECTION Private>
 g_convert_error_quark

glib/gcharset.c

@@ -36,6 +36,10 @@
 
 #include <string.h>
 #include <stdio.h>
+#ifdef G_OS_WIN32
+#define WIN32_LEAN_AND_MEAN
+#include <windows.h>
+#endif
 
 G_LOCK_DEFINE_STATIC (aliases);
 
@@ -194,7 +198,7 @@ g_get_charset (const char **charset)
   raw = _g_locale_charset_raw ();
   G_UNLOCK (aliases);
 
-  if (!(cache->raw && strcmp (cache->raw, raw) == 0))
+  if (cache->raw == NULL || strcmp (cache->raw, raw) != 0)
     {
       const gchar *new_charset;
 
@@ -229,6 +233,113 @@ g_get_codeset (void)
   return g_strdup (charset);
 }
 
+/**
+ * g_get_console_charset:
+ * @charset: (out) (optional) (transfer none): return location for character set
+ *   name, or %NULL.
+ *
+ * Obtains the character set used by the console attached to the process,
+ * which is suitable for printing output to the terminal.
+ *
+ * Usually this matches the result returned by g_get_charset(), but in
+ * environments where the locale's character set does not match the encoding
+ * of the console this function tries to guess a more suitable value instead.
+ *
+ * On Windows the character set returned by this function is the
+ * output code page used by the console associated with the calling process.
+ * If the codepage can't be determined (for example because there is no
+ * console attached) UTF-8 is assumed.
+ *
+ * The return value is %TRUE if the locale's encoding is UTF-8, in that
+ * case you can perhaps avoid calling g_convert().
+ *
+ * The string returned in @charset is not allocated, and should not be
+ * freed.
+ *
+ * Returns: %TRUE if the returned charset is UTF-8
+ *
+ * Since: 2.62
+ */
+gboolean
+g_get_console_charset (const char **charset)
+{
+#ifdef G_OS_WIN32
+  static GPrivate cache_private = G_PRIVATE_INIT (charset_cache_free);
+  GCharsetCache *cache = g_private_get (&cache_private);
+  const gchar *locale;
+  unsigned int cp;
+  char buf[2 + 20 + 1]; /* "CP" + G_MAXUINT64 (to be safe) in decimal form (20 bytes) + "\0" */
+  const gchar *raw = NULL;
+
+  if (!cache)
+    cache = g_private_set_alloc0 (&cache_private, sizeof (GCharsetCache));
+
+  /* first try to query $LANG (works for Cygwin/MSYS/MSYS2 and others using mintty) */
+  locale = g_getenv ("LANG");
+  if (locale != NULL && locale[0] != '\0')
+    {
+      /* If the locale name contains an encoding after the dot, return it.  */
+      const char *dot = strchr (locale, '.');
+
+      if (dot != NULL)
+        {
+          const char *modifier;
+
+          dot++;
+          /* Look for the possible @... trailer and remove it, if any.  */
+          modifier = strchr (dot, '@');
+          if (modifier == NULL)
+            raw = dot;
+          else if (modifier - dot < sizeof (buf))
+            {
+              memcpy (buf, dot, modifier - dot);
+              buf[modifier - dot] = '\0';
+              raw = buf;
+            }
+        }
+    }
+  /* next try querying console codepage using native win32 API */
+  if (raw == NULL)
+    {
+      cp = GetConsoleOutputCP ();
+      if (cp)
+        {
+          sprintf (buf, "CP%u", cp);
+          raw = buf;
+        }
+      else if (GetLastError () != ERROR_INVALID_HANDLE)
+        {
+          gchar *emsg = g_win32_error_message (GetLastError ());
+          g_warning ("Failed to determine console output code page: %s. "
+                     "Falling back to UTF-8", emsg);
+          g_free (emsg);
+        }
+    }
+  /* fall-back to UTF-8 if the rest failed (it's a sane and universal default) */
+  if (raw == NULL)
+    raw = "UTF-8";
+
+  if (cache->raw == NULL || strcmp (cache->raw, raw) != 0)
+    {
+      const gchar *new_charset;
+
+      g_free (cache->raw);
+      g_free (cache->charset);
+      cache->raw = g_strdup (raw);
+      cache->is_utf8 = g_utf8_get_charset_internal (raw, &new_charset);
+      cache->charset = g_strdup (new_charset);
+    }
+
+  if (charset)
+    *charset = cache->charset;
+
+  return cache->is_utf8;
+#else
+  /* assume the locale settings match the console encoding on non-Windows OSs */
+  return g_get_charset (charset);
+#endif
+}
+
 #ifndef G_OS_WIN32
 
 /* read an alias file for the locales */

glib/gcharset.h

@@ -31,6 +31,8 @@ GLIB_AVAILABLE_IN_ALL
 gboolean              g_get_charset         (const char **charset);
 GLIB_AVAILABLE_IN_ALL
 gchar *               g_get_codeset         (void);
+GLIB_AVAILABLE_IN_2_62
+gboolean              g_get_console_charset (const char **charset);
 
 GLIB_AVAILABLE_IN_ALL
 const gchar * const * g_get_language_names  (void);

glib/gmessages.c

@@ -2291,7 +2291,7 @@ g_log_writer_format_fields (GLogLevelFlags   log_level,
       msg = g_string_new (message);
       escape_string (msg);
 
-      if (g_get_charset (&charset))
+      if (g_get_console_charset (&charset))
         {
           /* charset is UTF-8 already */
           g_string_append (gstring, msg->str);
@@ -3186,7 +3186,7 @@ g_print (const gchar *format,
     {
       const gchar *charset;
 
-      if (g_get_charset (&charset))
+      if (g_get_console_charset (&charset))
         fputs (string, stdout); /* charset is UTF-8 already */
       else
         {
@@ -3265,7 +3265,7 @@ g_printerr (const gchar *format,
     {
       const gchar *charset;
 
-      if (g_get_charset (&charset))
+      if (g_get_console_charset (&charset))
         fputs (string, stderr); /* charset is UTF-8 already */
       else
         {

glib/gstrfuncs.c

@@ -1302,7 +1302,7 @@ g_strerror (gint errnum)
       g_strlcpy (buf, strerror (errnum), sizeof (buf));
       msg = buf;
 #endif
-      if (!g_get_charset (NULL))
+      if (!g_get_console_charset (NULL))
         {
           msg = g_locale_to_utf8 (msg, -1, NULL, NULL, &error);
           if (error)
@@ -1342,7 +1342,7 @@ g_strsignal (gint signum)
 
 #ifdef HAVE_STRSIGNAL
   msg = strsignal (signum);
-  if (!g_get_charset (NULL))
+  if (!g_get_console_charset (NULL))
     msg = tofree = g_locale_to_utf8 (msg, -1, NULL, NULL, NULL);
 #endif
 

glib/tests/utils.c

@@ -29,6 +29,9 @@
 #include <stdlib.h>
 #include <string.h>
 #include <stdarg.h>
+#ifdef G_OS_WIN32
+#include <windows.h>
+#endif
 
 static gboolean
 strv_check (const gchar * const *strv, ...)
@@ -335,6 +338,42 @@ test_codeset2 (void)
   g_test_trap_assert_passed ();
 }
 
+static void
+test_console_charset (void)
+{
+  const gchar *c1;
+  const gchar *c2;
+
+#ifdef G_OS_WIN32
+  /* store current environment and unset $LANG to make sure it does not interfere */
+  const unsigned int initial_cp = GetConsoleOutputCP ();
+  gchar *initial_lang = g_strdup (g_getenv ("LANG"));
+  g_unsetenv ("LANG");
+
+  /* set console output codepage to something specific (ISO-8859-1 aka CP28591) and query it */
+  SetConsoleOutputCP (28591);
+  g_get_console_charset (&c1);
+  g_assert_cmpstr (c1, ==, "ISO-8859-1");
+
+  /* set $LANG to something specific (should override the console output codepage) and query it */
+  g_setenv ("LANG", "de_DE.ISO-8859-15@euro", TRUE);
+  g_get_console_charset (&c2);
+  g_assert_cmpstr (c2, ==, "ISO-8859-15");
+
+  /* reset environment */
+  if (initial_cp)
+    SetConsoleOutputCP (initial_cp);
+  if (initial_lang)
+    g_setenv ("LANG", initial_lang, TRUE);
+  g_free (initial_lang);
+#else
+  g_get_charset (&c1);
+  g_get_console_charset (&c2);
+
+  g_assert_cmpstr (c1, ==, c2);
+#endif
+}
+
 static void
 test_basename (void)
 {
@@ -717,6 +756,7 @@ main (int   argc,
   g_test_add_func ("/utils/debug", test_debug);
   g_test_add_func ("/utils/codeset", test_codeset);
   g_test_add_func ("/utils/codeset2", test_codeset2);
+  g_test_add_func ("/utils/console-charset", test_console_charset);
   g_test_add_func ("/utils/basename", test_basename);
   g_test_add_func ("/utils/gettext", test_gettext);
   g_test_add_func ("/utils/username", test_username);