more fine-grained Unicode support

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>

1 files changed, 51 insertions, 0 deletions

diff --git a/Config.in b/Config.in
index 8e751530c..68444839d 100644
--- a/Config.in
+++ b/Config.in
@@ -141,6 +141,57 @@ config FEATURE_CHECK_UNICODE_IN_ENV
 
           Otherwise, Unicode support will be always enabled and active.
 
+config SUBST_WCHAR
+        int "Character code to substitute unprintable characters with"
+        range 1 4294967295
+        depends on FEATURE_ASSUME_UNICODE
+        default 63
+        help
+          Typical values are 63 for '?' (works with any output device),
+          30 for ASCII substitute control code,
+          65533 (0xfffd) for Unicode replacement character.
+
+config LAST_SUPPORTED_WCHAR
+        int "Range of supported Unicode characters"
+        range 0 4294967295
+        depends on FEATURE_ASSUME_UNICODE
+        default 767
+        help
+          Any character with Unicode value bigger than this is assumed
+          to be non-printable on output device. Many applets replace
+          such chars with substitution character.
+
+          The idea is that many valid printable Unicode chars are
+          nevertheless are not displayed correctly. Think about
+          combining charachers, double-wide hieroglyphs and such.
+          Many terminals, xterms and such will fail to handle them
+          correctly.
+
+          Typical values are:
+          126 - ASCII only
+          767 (0x2ff) - there are no combining chars in [0..767] range
+                        (the range includes Latin 1, Latin Ext. A and B),
+                        code is ~700 bytes smaller for this case.
+          4351 (0x10ff) - there are no double-wide chars in [0..4351] range,
+                        code is ~300 bytes smaller for this case.
+          0 - off, any valid printable Unicode character will be printed.
+
+config UNICODE_COMBINING_WCHARS
+        bool "Allow zero-width Unicode characters on output"
+        default n
+        depends on FEATURE_ASSUME_UNICODE
+        help
+          With this option off, any Unicode char with width of 0
+          is substituted on output.
+
+config UNICODE_WIDE_WCHARS
+        bool "Allow wide Unicode characters on output"
+        default n
+        depends on FEATURE_ASSUME_UNICODE
+        help
+          With this option off, any Unicode char with width > 1
+          is substituted on output.
+
 config LONG_OPTS
         bool "Support for --long-options"
         default y