2utf.config

一个UTF的源代码,可以提供参考

# List of directories with charmap files, one per line.
# Must end in `/'.
	
/usr/local/share/i18n/charmaps/
/usr/share/i18n/charmaps/
/usr/share/i18n/charmap/
	
[charsets]
#       These can  override iconv(3) and charmap  files if any.   Charset description
#       consist of 3 lines, 2) or 3) may be leaved blank:
#
# 1 line) Space separeted names. Case isn't significant, `-' and `_' are
# removed.   If US-ASCII  is subset  of  this charset  or encoding,  put
# [US-ASCII_is_subset] at the  beginning of  the line. This  means that
# US-ASCII message headers can be passed safely through this filter.
#
# 2 line)  Command for translation  to UTF-8, should read  from standard
# input and write to standard output. If this command doesn't buffers
# it's input and output (even no line buffering) put `%' as a first
# character in the line.
#
# 3 line) Command for translation from UTF-8.

# Due to the popen(3)
# bug in Linux libc (glibc) inexistant commands are not detected.
# So please check everything by hand.



## The following is at ftp://ftp.cnd.org/pub/ifcss.org/software/unix/convert/

#utf-7 Unicode-1-1-UTF-7 Unicode-2-0-UTF-7
#u7tou8
#u8tou7

## Some people say `tcs''s Big5 is wrong (is this true?).
#Big5
#b5tou8
#u8tob5



# `tcs' is in most popular software distributions.
[US-ASCII_is_subset] EUC-KR EUC-K
tcs -f euc-k
tcs -t euc-k

[US-ASCII_is_subset] gb GB-2312-80 iso-ir-58
tcs -f gb
tcs -t gb

[US-ASCII_is_subset] Big5
tcs -f big5
tcs -t big5

[US-ASCII_is_subset] jis-kanji ISO_2022-JP
tcs -f jis-kanji
tcs -t jis-kanji

[US-ASCII_is_subset] ujis EUC-JX JIS_0208
tcs -f ujis
tcs -t ujis

[US-ASCII_is_subset] ms-kanji Shift-JiS
tcs -f ms-kanji
tcs -t ms-kanji

[US-ASCII_is_subset] jis
tcs -f jis


[US-ASCII_is_subset] viscii VISCII_1.1
tcs -f viet1
tcs -t viet1

[US-ASCII_is_subset] viet1 VSCII-1
tcs -f viet1
tcs -t viet1

[US-ASCII_is_subset] viet2 VSCII-2
tcs -f viet2
tcs -t viet2

testing
cat
cat