kattyo's blog

標準には無いパッケージ

nkf

$ tar xzf nkf-2.1.5.tar.gz
$ cd nkf-2_1_5/
$ make
cc -g -O2 -Wall -pedantic -c nkf.c
cc -g -O2 -Wall -pedantic -c utf8tbl.c
cc -g -O2 -Wall -pedantic  -o nkf nkf.o utf8tbl.o
$ make install
mkdir /usr/local/bin
mkdir: ディレクトリ `/usr/local/bin' を作成できません: File exists
make: [Makefile:49: install-main] エラー 1 (無視されました)
cp -f nkf /usr/local/bin/
mkdir /usr/local/man
mkdir /usr/local/man/man1
cp -f nkf.1 /usr/local/man/man1/
mkdir /usr/local/man/ja
mkdir /usr/local/man/ja/man1
cp -f nkf.1j /usr/local/man/ja/man1/nkf.1
$ nkf
$ nkf --help
Usage:  nkf -[flags] [--] [in file] .. [out file for -O flag]
 j/s/e/w  Specify output encoding ISO-2022-JP, Shift_JIS, EUC-JP
          UTF options is -w[8[0],{16,32}[{B,L}[0]]]
 J/S/E/W  Specify input encoding ISO-2022-JP, Shift_JIS, EUC-JP
          UTF option is -W[8,[16,32][B,L]]
 m[BQSN0] MIME decode [B:base64,Q:quoted,S:strict,N:nonstrict,0:no decode]
 M[BQ]    MIME encode [B:base64 Q:quoted]
 f/F      Folding: -f60 or -f or -f60-10 (fold margin 10) F preserve nl
 Z[0-4]   Default/0: Convert JISX0208 Alphabet to ASCII
          1: Kankaku to one space  2: to two spaces  3: HTML Entity
          4: JISX0208 Katakana to JISX0201 Katakana
 X,x      Convert Halfwidth Katakana to Fullwidth or preserve it
 O        Output to File (DEFAULT 'nkf.out')
 L[uwm]   Line mode u:LF w:CRLF m:CR (DEFAULT noconversion)
 --ic=<encoding>        Specify the input encoding
 --oc=<encoding>        Specify the output encoding
 --hiragana --katakana  Hiragana/Katakana Conversion
 --katakana-hiragana    Converts each other
 --{cap, url}-input     Convert hex after ':' or '%'
 --numchar-input        Convert Unicode Character Reference
 --fb-{skip, html, xml, perl, java, subchar}
                        Specify unassigned character's replacement
 --in-place[=SUF]       Overwrite original files
 --overwrite[=SUF]      Preserve timestamp of original files
 -g --guess             Guess the input code
 -v --version           Print the version
 --help/-V              Print this help / configuration
Network Kanji Filter Version 2.1.5 (2018-12-15)
Copyright (C) 1987, FUJITSU LTD. (I.Ichikawa).
Copyright (C) 1996-2018, The nkf Project.
$

存在するパッケージ

lv

$ cat file | lv -Os | cat

       coding-system:
              a: auto-select
              c: iso-2022-cn
              j: iso-2022-jp
              k: iso-2022-kr
              ec: euc-china
              ej: euc-japan
              ek: euc-korea
              et: euc-taiwan
              u7: UTF-7
              u8: UTF-8
              l1..9: iso-8859-1..9
              l0: iso-8859-10
              lb,ld,le,lf,lg: iso-8859-11,13,14,15,16
              s: shift-jis
              b: big5
              h: HZ
              r: raw mode

libiconv

$ iconv -l | egrep -i 'jis|2022-?jp|20932' | egrep -vi 'sjis|shift|euc'
ISO-IR-14 ISO646-JP JIS_C6220-1969-RO JP CSISO14JISC6220RO
JIS0201 JISX0201-1976 JISX0201.1976-0 JIS_X0201 X0201 CSHALFWIDTHKATAKANA
ISO-IR-87 JIS0208 JISX0208.1983-0 JISX0208.1990-0 JIS_C6226-1983 JIS_X0208 JIS_X0208-1983 JIS_X0208-1990 X0208 CSISO87JISX0208
ISO-IR-159 JIS0212 JISX0212.1990-0 JIS_X0212 JIS_X0212-1990 JIS_X0212.1990-0 X0212 CSISO159JISX02121990
ISO-2022-JP ISO2022JP CSISO2022JP
ISO-2022-JP-1
ISO-2022-JP-2 CSISO2022JP2
CP50221 ISO-2022-JP-ESC ISO-2022-JP-MS
ISO-2022-JP-2004 ISO-2022-JP-3
$
$ iconv -l | egrep -i 'euc' | egrep -i 'jp|jis'
CP51932 EUC-JP EUCJP EUC_JP EXTENDED_UNIX_CODE_PACKED_FORMAT_FOR_JAPANESE CSEUCPKDFMTJAPANESE
EUC-JIS-2004 EUC-JISX0213
$
$ iconv -l | egrep -i 'sjis|shift|932|31j'  | grep -v 51932
MS_KANJI SHIFT-JIS SHIFT_JIS SJIS CSSHIFTJIS
CP932 WINDOWS-31J
SHIFT_JIS-2004 SHIFT_JISX0213
$

piconv (perL)

$ piconv -l | grep -i jis | egrep -iv 'shift|sjis'
7bit-jis
jis0201-raw
jis0208-raw
jis0212-raw
$
$ piconv -l | egrep -i 'jis|31j|932' | egrep -i 'shift|sjis'
shiftjis
$
$ piconv -l | egrep -i 'euc' | egrep -v -e '[-_](cn|tw|kr)'
euc-jp
$