X-Git-Url: http://git.sourceforge.jp/view?p=nkf%2Fnkf.git;a=blobdiff_plain;f=nkf.1;h=a8f5faa791561368defd4a1db2c7310cba20953f;hp=bed2cc549e2a347e4c0152e462658a6f1e033bc7;hb=7fc0312e737af31ee7380c1af9c07e2f5afed43a;hpb=b920d1af62e6739ceb7fb1906adda6480d330d13 diff --git a/nkf.1 b/nkf.1 index bed2cc5..a8f5faa 100644 --- a/nkf.1 +++ b/nkf.1 @@ -1,254 +1,441 @@ -.TH NKF 1L 24/Feb/2000 -.SH NAME -nkf \- Network Kanji code conversion Filter v2.0 -.SH SYNOPSIS -.B nkf -[ -.B options -] [ -.B file -] -.SH DESCRIPTION +.\" Automatically generated by Pod::Man v1.37, Pod::Parser v1.32 +.\" +.\" Standard preamble: +.\" ======================================================================== +.de Sh \" Subsection heading +.br +.if t .Sp +.ne 5 .PP -.B Nkf -is a yet another kanji code converter among networks, hosts and terminals. +\fB\\$1\fR +.PP +.. +.de Sp \" Vertical space (when we can't use .PP) +.if t .sp .5v +.if n .sp +.. +.de Vb \" Begin verbatim text +.ft CW +.nf +.ne \\$1 +.. +.de Ve \" End verbatim text +.ft R +.fi +.. +.\" Set up some character translations and predefined strings. \*(-- will +.\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left +.\" double quote, and \*(R" will give a right double quote. | will give a +.\" real vertical bar. \*(C+ will give a nicer C++. Capital omega is used to +.\" do unbreakable dashes and therefore won't be available. \*(C` and \*(C' +.\" expand to `' in nroff, nothing in troff, for use with C<>. +.tr \(*W-|\(bv\*(Tr +.ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p' +.ie n \{\ +. ds -- \(*W- +. ds PI pi +. if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch +. if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\" diablo 12 pitch +. ds L" "" +. ds R" "" +. ds C` "" +. ds C' "" +'br\} +.el\{\ +. ds -- \|\(em\| +. ds PI \(*p +. ds L" `` +. ds R" '' +'br\} +.\" +.\" If the F register is turned on, we'll generate index entries on stderr for +.\" titles (.TH), headers (.SH), subsections (.Sh), items (.Ip), and index +.\" entries marked with X<> in POD. Of course, you'll have to process the +.\" output yourself in some meaningful fashion. +.if \nF \{\ +. de IX +. tm Index:\\$1\t\\n%\t"\\$2" +.. +. nr % 0 +. rr F +.\} +.\" +.\" For nroff, turn off justification. Always turn off hyphenation; it makes +.\" way too many mistakes in technical documents. +.hy 0 +.if n .na +.\" +.\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2). +.\" Fear. Run. Save yourself. No user-serviceable parts. +. \" fudge factors for nroff and troff +.if n \{\ +. ds #H 0 +. ds #V .8m +. ds #F .3m +. ds #[ \f1 +. ds #] \fP +.\} +.if t \{\ +. ds #H ((1u-(\\\\n(.fu%2u))*.13m) +. ds #V .6m +. ds #F 0 +. ds #[ \& +. ds #] \& +.\} +. \" simple accents for nroff and troff +.if n \{\ +. ds ' \& +. ds ` \& +. ds ^ \& +. ds , \& +. ds ~ ~ +. ds / +.\} +.if t \{\ +. ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u" +. ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u' +. ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u' +. ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u' +. ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u' +. ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u' +.\} +. \" troff and (daisy-wheel) nroff accents +.ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V' +.ds 8 \h'\*(#H'\(*b\h'-\*(#H' +.ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#] +.ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H' +.ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u' +.ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#] +.ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#] +.ds ae a\h'-(\w'a'u*4/10)'e +.ds Ae A\h'-(\w'A'u*4/10)'E +. \" corrections for vroff +.if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u' +.if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u' +. \" for low resolution devices (crt and lpr) +.if \n(.H>23 .if \n(.V>19 \ +\{\ +. ds : e +. ds 8 ss +. ds o a +. ds d- d\h'-1'\(ga +. ds D- D\h'-1'\(hy +. ds th \o'bp' +. ds Th \o'LP' +. ds ae ae +. ds Ae AE +.\} +.rm #[ #] #H #V #F C +.\" ======================================================================== +.\" +.IX Title "nkf 1" +.TH nkf 1 "2006-08-22" "nkf 2.0.8" " " +.SH "NAME" +nkf \- Network Kanji Filter +.SH "SYNOPSIS" +.IX Header "SYNOPSIS" +nkf \fB[\-butjnesliohrTVvwWJESZxXFfmMBOcdILg]\fR \fB[\fR\fIfile ...\fR\fB]\fR +.SH "DESCRIPTION" +.IX Header "DESCRIPTION" +\&\fBNkf\fR is a yet another kanji code converter among networks, hosts and terminals. It converts input kanji code to designated kanji code -such as 7-bit JIS, MS-kanji (shifted-JIS), utf-8 or EUC. +such as \s-1ISO\-2022\-JP\s0, Shift_JIS, \s-1EUC\-JP\s0, \s-1UTF\-8\s0 or \s-1UTF\-16\s0. .PP -One of the most unique facicility of -.B nkf -is the guess of the input kanji code. -It currently recognizes 7-bit JIS, MS-kanji (shifted-JIS),utf-8 and EUC. -So users needn't the input kanji code specification. - -By default X0201 kana is converted into X0208 kana. For -X0201 kana, SO/SI, SSO and -ESC-(-I methods are supported. For automatic code detection, nkf assumes -no X0201 kana in MS-Kanji. To accept X0201 in MS-Kanji, use \-X, \-x or -\-S. +One of the most unique faculty of \fBnkf\fR is the guess of the input kanji encodings. +It currently recognizes \s-1ISO\-2022\-JP\s0, Shift_JIS, \s-1EUC\-JP\s0, \s-1UTF\-8\s0 and \s-1UTF\-16\s0. +So users needn't set the input kanji code explicitly. .PP -Options are bellow: -.TP -.B \-j -output 7-bit JIS code. -This is a default. -.TP -.B \-s -output MS-kanji (shifted-JIS) code. -.TP -.B \-e -output EUC (AT&T) code. -.TP -.B \-w -output UTF-8 (Unicode 8bit form). -.TP -.B \-S -Assume MS-Kanji and X0201 kana input. It also accpet JIS. -AT&T EUC is recognized as X0201 kana. Without \-x flag, -X0201 kana is converted into X0208. -.TP -.B \-J -Assume JIS input. It also accepts Japanese EUC. -This is the default. This flag does not excludde MS-Kanji. -.TP -.B \-E -Assume AT&T EUC input. It also accpet JIS. +By default, X0201 kana is converted into X0208 kana. +For X0201 kana, \s-1SO/SI\s0, \s-1SSO\s0 and \s-1ESC\-\s0(\-I methods are supported. +For automatic code detection, nkf assumes no X0201 kana in Shift_JIS. +To accept X0201 in Shift_JIS, use \fB\-X\fR, \fB\-x\fR or \fB\-S\fR. +.SH "OPTIONS" +.IX Header "OPTIONS" +.IP "\fB\-b \-u\fR" 4 +.IX Item "-b -u" +Output is buffered (\s-1DEFAULT\s0), Output is unbuffered. +.IP "\fB\-j \-s \-e \-w \-w16\fR" 4 +.IX Item "-j -s -e -w -w16" +Output code is \s-1ISO\-2022\-JP\s0 (7bit \s-1JIS\s0), Shift_JIS, \s-1EUC\-JP\s0, +\&\s-1UTF\-8N\s0, \s-1UTF\-16BE\s0. +Without this option and compile option, \s-1ISO\-2022\-JP\s0 is assumed. +.IP "\fB\-J \-S \-E \-W \-W16\fR" 4 +.IX Item "-J -S -E -W -W16" +Input assumption is \s-1JIS\s0 7 bit, Shift_JIS, \s-1EUC\-JP\s0, +\&\s-1UTF\-8\s0, \s-1UTF\-16LE\s0. +.RS 4 +.IP "\fB\-J\fR" 4 +.IX Item "-J" +Assume \s-1JIS\s0 input. It also accepts \s-1EUC\-JP\s0. +This is the default. This flag does not exclude Shift_JIS. +.IP "\fB\-S\fR" 4 +.IX Item "-S" +Assume Shift_JIS and X0201 kana input. It also accepts \s-1JIS\s0. +EUC-JP is recognized as X0201 kana. Without \fB\-x\fR flag, +X0201 kana (halfwidth kana) is converted into X0208. +.IP "\fB\-E\fR" 4 +.IX Item "-E" +Assume EUC-JP input. It also accepts \s-1JIS\s0. Same as \-J. -.TP -.B \-B -Assume broken JIS-Kanji, which lost ESC. Usefull when your site is -using old B-News Nihongo patch. \-B1 allows any char after ESC-( or -ESC-$. \-B2 forces ASCII after NL. -.TP -.B \-W -Assume UTF-8 input. -.TP -.B \-m -MIME ISO-2022-JP/ISO8859-1 decode. (default) To see ISO8859-1 (Latin-1) -\-l is necessary. \-mN does loose encoding. It allows line break in the -middle of the basr64 encoding. -.TP -.B \-mB -Decode MIME base64 encoded stream. Remove header or other part before -conversion. -.TP -.B \-mQ -Decode MIME quoted stream. '_' in quoted is converted to space. -.TP -.B \-m0 -No MIME decode. -.TP -.B \-M -MIME encode. Header style. All ASCII code and control characters are -intact. -.TP -.B \-MB -MIME encode. Base64 stream. Kanji conversion is performed before encoding, -so this cannot be used as a picture encoder. \MQ perfome quoted encoding. -.TP -.B \-l -Input and output code is ISO8859-1 (Latin-1) and ISO-2022-JP. -\-s, \-e and \-x are not compatible with this option. -.TP -.BI \-f n -Folding on -.BI n -length in a line. Default 60. \-f40-0 forces 0 margin folding. -.TP -.B \-X -Allow X0201 kana in MS-Kanji. -X0201 is converted into X0208 by default. -This is default in MSDOS. -.TP -.B \-x -Try to preseve X0208 kana. -Assume X0201 kana in MS-Kanji. And -do not convert X0201 kana to X0208. -In JIS output, ESC-(-I is used. In EUC output, SSO is used. -.TP -.B \-Z -Convert X0208 alphabet to ASCII. \-Z1 converts X0208 kankaku to one -ASCII space. \-Z2 converts X0208 kankaku to two ASCII spaces. -.TP -.B \-Z3 -Replacing "><&" into '>', '<', '"', '&' as in HTML. -.TP -.B \-I -Replacing Non iso-2022-jp char into the strage geta character. -.TP -.B \-b -bufferd output. -This is a default. -.TP -.B \-u -unbufferd output. -.TP -.B \-t -no operations. -.TP -.B \-O -Output result to file. The first name in arguments becomes output. -Please be careful. If there are no file arguments, nkf.out is chosen. -\--overwrite does rewriting. Original listed files are replaced by filtered -result. -.TP -.BI \-i c -output -.BI ESC\-$\- c -as sequence to designate JIS-kanji -(Default is -.BR B .) -.TP -.BI \-o c -output -.BI ESC\-(\- c -as sequence to designate single-byte roman characters -(Default is -.BR B .) -.TP -.B \-r -{de/en}crypt ROT13/47 -.TP -.B \-v -display Version -.TP -.B \-T -Text mode output (MS-DOS) -.TP -.B \-c -add CR after NL. -.TP -.B \-d -delete CR after NL. -.TP -.B -L[wmu] new line mode -.nf - -Lu unix (LF) - -Lw windows (CRLF) - -Lm mac (CR) -default no conversion -.fl -.PP -.B \-F +.RE +.RS 4 +.RE +.IP "\fB\-t\fR" 4 +.IX Item "-t" +No conversion. +.IP "\fB\-i[@B]\fR" 4 +.IX Item "-i[@B]" +Specify the Esc Seq for \s-1JIS\s0 X 0208\-1978/83. (\s-1DEFAULT\s0 B) +.IP "\fB\-o[\s-1BJH\s0]\fR" 4 +.IX Item "-o[BJH]" +Specify the Esc Seq for ASCII/Roman. (\s-1DEFAULT\s0 B) +.IP "\fB\-r\fR" 4 +.IX Item "-r" +{de/en}crypt \s-1ROT13/47\s0 +.IP "\fB\-h[123] \-\-hiragana \-\-katakana \-\-katakana\-hiragana\fR" 4 +.IX Item "-h[123] --hiragana --katakana --katakana-hiragana" +.RS 4 +.PD 0 +.IP "\fB\-h1 \-\-hiragana\fR" 4 +.IX Item "-h1 --hiragana" +.PD +Katakana to Hiragana conversion. +.IP "\fB\-h2 \-\-katakana\fR" 4 +.IX Item "-h2 --katakana" +Hiragana to Katakana conversion. +.IP "\fB\-h3 \-\-katakana\-hiragana\fR" 4 +.IX Item "-h3 --katakana-hiragana" +Katakana to Hiragana and Hiragana to Katakana conversion. +.RE +.RS 4 +.RE +.IP "\fB\-T\fR" 4 +.IX Item "-T" +Text mode output (\s-1MS\-DOS\s0) +.IP "\fB\-l\fR" 4 +.IX Item "-l" +\&\s-1ISO8859\-1\s0 (Latin\-1) support +.IP "\fB\-f[\f(BIm\fB [\- \f(BIn\fB]]\fR" 4 +.IX Item "-f[m [- n]]" +Folding on \fIm\fR length with \fIn\fR margin in a line. +Without this option, fold length is 60 and fold margin is 10. +.IP "\fB\-F\fR" 4 +.IX Item "-F" New line preserving line folding. - -.PP -hiragana/katakana translation - \-h1 \--katakana - \-h2 \--hirakana - \-h3 \--hirakana-katakana - -.TP -.B -- -long options -.nf - --fj,--unix,--mac,--msdos, --windows - convert for these system - - --jis,--euc,--sjis,--mime,--base64 - convert for named code - --jis-input,--euc-input,--sjis-input,--mime-input,--base64-input - assume input system - - -- ignore rest of -option - - --help - --version -.fl - -.SH "FILES" -nkf - binary -.SH AUTHOR -Itaru Ichikawa , -(was ichikawa@fujitsu.JUNET) -.SH EDITOR -a_kuroe@hoffman.cc.sophia.ac.jp (Akihiko Kuroe), -kono@ie.u-ryukyu.ac.jp (Shinji KONO), -furukawa@tcp-ip.or.jp ( Rei FURUKAWA )` -.SH BUGS -.B Nkf -cannot handle some input that contains mixed kanji codes. -Automatic code detection -becomes very weak with \-x, \-X and \-S. -MIME encoding is very loose. - -.fl - -.SH ACKNOWLEDGE - -Thanks for those people. - -nkf 1.7,1.9,2.0 - -Akio Furukawa, -OHARA Shigeki, -Hiroaki Sengoku, -Ikuhiro MORITA, -Junn Ohta, -KAWAMURA Masao, -Kazuhiko Mori, -Keitaro Isokawa, -Ken-ichi Hirose, -Ki-ichiro SATO, -Kiwamu Aoyama, -Koichi Hirayama, -Mitsuru Hase, -OHARA Shigeki, -Rei FURUKAWA, -Satoru Takabayashi, -Shigeyuki Takagi, -Shin MICHIMUKO, -Tsutomu Sakai, -YAMASHITA Junji, -Yasuyuki Sato, -Yoshiaki Yanagihara, -Yoshiaki Yanagihara, -hat@so-net, -SHIOZAKI Takehiko, -Koji Arai, -Eiichiro Itani, -Masayuki Hatta, -and many others. - -URL: - www.ie.u-ryukyu.ac.jp/~kono/nkf/ +.IP "\fB\-Z[0\-3]\fR" 4 +.IX Item "-Z[0-3]" +Convert X0208 alphabet (Fullwidth Alphabets) to \s-1ASCII\s0. +.RS 4 +.IP "\fB\-Z \-Z0\fR" 4 +.IX Item "-Z -Z0" +Convert X0208 alphabet to \s-1ASCII\s0. +.IP "\fB\-Z1\fR" 4 +.IX Item "-Z1" +Converts X0208 kankaku to single \s-1ASCII\s0 space. +.IP "\fB\-Z2\fR" 4 +.IX Item "-Z2" +Converts X0208 kankaku to double \s-1ASCII\s0 spaces. +.IP "\fB\-Z3\fR" 4 +.IX Item "-Z3" +Replacing Fullwidth >, <, ", & into '>', '<', '"', '&' as in \s-1HTML\s0. +.RE +.RS 4 +.RE +.IP "\fB\-X \-x\fR" 4 +.IX Item "-X -x" +Assume X0201 kana in MS\-Kanji. +With \fB\-X\fR or without this option, X0201 is converted into X0208 Kana. +With \fB\-x\fR, try to preserve X0208 kana and do not convert X0201 kana to X0208. +In \s-1JIS\s0 output, \s-1ESC\-\s0(\-I is used. In \s-1EUC\s0 output, \s-1SSO\s0 is used. +.IP "\fB\-B[0\-2]\fR" 4 +.IX Item "-B[0-2]" +Assume broken JIS-Kanji input, which lost \s-1ESC\s0. +Useful when your site is using old B\-News Nihongo patch. +.RS 4 +.IP "\fB\-B1\fR" 4 +.IX Item "-B1" +allows any char after \s-1ESC\-\s0( or \s-1ESC\-$\s0. +.IP "\fB\-B2\fR" 4 +.IX Item "-B2" +forces \s-1ASCII\s0 after \s-1NL\s0. +.RE +.RS 4 +.RE +.IP "\fB\-I\fR" 4 +.IX Item "-I" +Replacing non iso\-2022\-jp char into a geta character +(substitute character in Japanese). +.IP "\fB\-m[\s-1BQN0\s0]\fR" 4 +.IX Item "-m[BQN0]" +\&\s-1MIME\s0 \s-1ISO\-2022\-JP/ISO8859\-1\s0 decode. (\s-1DEFAULT\s0) +To see \s-1ISO8859\-1\s0 (Latin\-1) \-l is necessary. +.RS 4 +.IP "\fB\-mB\fR" 4 +.IX Item "-mB" +Decode \s-1MIME\s0 base64 encoded stream. Remove header or other part before +conversion. +.IP "\fB\-mQ\fR" 4 +.IX Item "-mQ" +Decode \s-1MIME\s0 quoted stream. '_' in quoted stream is converted to space. +.IP "\fB\-mN\fR" 4 +.IX Item "-mN" +Non-strict decoding. +It allows line break in the middle of the base64 encoding. +.IP "\fB\-m0\fR" 4 +.IX Item "-m0" +No \s-1MIME\s0 decode. +.RE +.RS 4 +.RE +.IP "\fB\-M\fR" 4 +.IX Item "-M" +\&\s-1MIME\s0 encode. Header style. All \s-1ASCII\s0 code and control characters are intact. +.RS 4 +.IP "\fB\-MB\fR" 4 +.IX Item "-MB" +\&\s-1MIME\s0 encode Base64 stream. +Kanji conversion is performed before encoding, so this cannot be used as a picture encoder. +.IP "\fB\-MQ\fR" 4 +.IX Item "-MQ" +Perfome quoted encoding. +.RE +.RS 4 +.RE +.IP "\fB\-l\fR" 4 +.IX Item "-l" +Input and output code is \s-1ISO8859\-1\s0 (Latin\-1) and \s-1ISO\-2022\-JP\s0. +\&\fB\-s\fR, \fB\-e\fR and \fB\-x\fR are not compatible with this option. +.IP "\fB\-L[uwm] \-d \-c\fR" 4 +.IX Item "-L[uwm] -d -c" +Convert line breaks. +.RS 4 +.IP "\fB\-Lu \-d\fR" 4 +.IX Item "-Lu -d" +unix (\s-1LF\s0) +.IP "\fB\-Lw \-c\fR" 4 +.IX Item "-Lw -c" +windows (\s-1CRLF\s0) +.IP "\fB\-Lm\fR" 4 +.IX Item "-Lm" +mac (\s-1CR\s0) +.Sp +Without this option, nkf doesn't convert line breaks. +.RE +.RS 4 +.RE +.IP "\fB\-\-fj \-\-unix \-\-mac \-\-msdos \-\-windows\fR" 4 +.IX Item "--fj --unix --mac --msdos --windows" +convert for these system +.IP "\fB\-\-jis \-\-euc \-\-sjis \-\-mime \-\-base64\fR" 4 +.IX Item "--jis --euc --sjis --mime --base64" +convert for named code +.IP "\fB\-\-jis\-input \-\-euc\-input \-\-sjis\-input \-\-mime\-input \-\-base64\-input\fR" 4 +.IX Item "--jis-input --euc-input --sjis-input --mime-input --base64-input" +assume input system +.IP "\fB\-\-ic=\f(BIinput codeset\fB \-\-oc=\f(BIoutput codeset\fB\fR" 4 +.IX Item "--ic=input codeset --oc=output codeset" +Set the input or output codeset. +\&\s-1NKF\s0 supports following codesets and those codeset name are case insensitive. +.RS 4 +.IP "\s-1ISO\-2022\-JP\s0" 4 +.IX Item "ISO-2022-JP" +a.k.a. \s-1RFC1468\s0, 7bit \s-1JIS\s0, \s-1JUNET\s0 +.IP "EUC-JP (eucJP\-nkf)" 4 +.IX Item "EUC-JP (eucJP-nkf)" +a.k.a. \s-1AT&T\s0 \s-1JIS\s0, Japanese \s-1EUC\s0, \s-1UJIS\s0 +.IP "eucJP-ascii" 4 +.IX Item "eucJP-ascii" +.PD 0 +.IP "eucJP-ms" 4 +.IX Item "eucJP-ms" +.IP "\s-1CP51932\s0" 4 +.IX Item "CP51932" +.PD +Microsoft Version of \s-1EUC\-JP\s0. +.IP "Shift_JIS" 4 +.IX Item "Shift_JIS" +a.k.a. \s-1SJIS\s0, MS-Kanji +.IP "\s-1CP932\s0" 4 +.IX Item "CP932" +a.k.a. Windows\-31J +.IP "\s-1UTF\-8\s0" 4 +.IX Item "UTF-8" +same as \s-1UTF\-8N\s0 +.IP "\s-1UTF\-8N\s0" 4 +.IX Item "UTF-8N" +\&\s-1UTF\-8\s0 without \s-1BOM\s0 +.IP "\s-1UTF\-8\-BOM\s0" 4 +.IX Item "UTF-8-BOM" +\&\s-1UTF\-8\s0 with \s-1BOM\s0 +.IP "\s-1UTF8\-MAC\s0 (input only)" 4 +.IX Item "UTF8-MAC (input only)" +decomposed \s-1UTF\-8\s0 +.IP "\s-1UTF\-16\s0" 4 +.IX Item "UTF-16" +same as \s-1UTF\-16BE\s0 +.IP "\s-1UTF\-16BE\s0" 4 +.IX Item "UTF-16BE" +\&\s-1UTF\-16\s0 Big Endian without \s-1BOM\s0 +.IP "\s-1UTF\-16BE\-BOM\s0" 4 +.IX Item "UTF-16BE-BOM" +\&\s-1UTF\-16\s0 Big Endian with \s-1BOM\s0 +.IP "\s-1UTF\-16LE\s0" 4 +.IX Item "UTF-16LE" +\&\s-1UTF\-16\s0 Little Endian without \s-1BOM\s0 +.IP "\s-1UTF\-16LE\-BOM\s0" 4 +.IX Item "UTF-16LE-BOM" +\&\s-1UTF\-16\s0 Little Endian with \s-1BOM\s0 +.RE +.RS 4 +.RE +.IP "\fB\-\-fb\-{skip, html, xml, perl, java, subchar}\fR" 4 +.IX Item "--fb-{skip, html, xml, perl, java, subchar}" +Specify the way that nkf handles unassigned characters. +Without this option, \-\-fb\-skip is assumed. +.IP "\fB\-\-prefix=\f(BIescape character\fB\f(BItarget character\fB..\fR" 4 +.IX Item "--prefix=escape charactertarget character.." +When nkf converts to Shift_JIS, +nkf adds a specified escape character to specified 2nd byte of Shift_JIS characters. +1st byte of argument is the escape character and following bytes are target characters. +.IP "\fB\-\-no\-cp932ext\fR" 4 +.IX Item "--no-cp932ext" +Handle the characters extended in \s-1CP932\s0 as unassigned characters. +.IP "\fB\-\-no\-best\-fit\-chars\fR" 4 +.IX Item "--no-best-fit-chars" +When Unicode to Encoded byte conversion, +don't convert characters which is not round trip safe. +When Unicode to Unicode conversion, +with this and \-x option, nkf can be used as \s-1UTF\s0 converter. +(In other words, without this and \-x option, nkf doesn't save some characters) +.Sp +When nkf convert string which related to path, you should use this opion. +.IP "\fB\-\-cap\-input\fR" 4 +.IX Item "--cap-input" +Decode hex encoded characters. +.IP "\fB\-\-url\-input\fR" 4 +.IX Item "--url-input" +Unescape percent escaped characters. +.IP "\fB\-\-numchar\-input\fR" 4 +.IX Item "--numchar-input" +Decode character reference, such as \*(L"&#....;\*(R". +.IP "\fB\-\-in\-place[=\fR\fI\s-1SUFFIX\s0\fR\fB]\fR \fB\-\-overwrite[=\fR\fI\s-1SUFFIX\s0\fR\fB]\fR" 4 +.IX Item "--in-place[=SUFFIX] --overwrite[=SUFFIX]" +Overwrite \fBoriginal\fR listed files by filtered result. +.Sp +\&\fBNote\fR \-\-overwrite preserves timestamp of original files. +.IP "\fB\-\-guess\fR" 4 +.IX Item "--guess" +Print guessed encoding. +.IP "\fB\-\-help\fR" 4 +.IX Item "--help" +Print nkf's help. +.IP "\fB\-\-version\fR" 4 +.IX Item "--version" +Print nkf's version. +.IP "\fB\-\-\fR" 4 +.IX Item "--" +Ignore rest of \-option. +.SH "AUTHOR" +.IX Header "AUTHOR" +Copyright (C) 1987, \s-1FUJITSU\s0 \s-1LTD\s0. (I.Ichikawa),2000 S. Kono, \s-1COW\s0 +Copyright (C) 2002\-2006 Kono, Furukawa, Naruse, mastodon