1 .\" Automatically generated by Pod::Man v1.37, Pod::Parser v1.32
4 .\" ========================================================================
5 .de Sh \" Subsection heading
13 .de Sp \" Vertical space (when we can't use .PP)
17 .de Vb \" Begin verbatim text
22 .de Ve \" End verbatim text
26 .\" Set up some character translations and predefined strings. \*(-- will
27 .\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left
28 .\" double quote, and \*(R" will give a right double quote. | will give a
29 .\" real vertical bar. \*(C+ will give a nicer C++. Capital omega is used to
30 .\" do unbreakable dashes and therefore won't be available. \*(C` and \*(C'
31 .\" expand to `' in nroff, nothing in troff, for use with C<>.
33 .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p'
37 . if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch
38 . if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\" diablo 12 pitch
51 .\" If the F register is turned on, we'll generate index entries on stderr for
52 .\" titles (.TH), headers (.SH), subsections (.Sh), items (.Ip), and index
53 .\" entries marked with X<> in POD. Of course, you'll have to process the
54 .\" output yourself in some meaningful fashion.
57 . tm Index:\\$1\t\\n%\t"\\$2"
63 .\" For nroff, turn off justification. Always turn off hyphenation; it makes
64 .\" way too many mistakes in technical documents.
68 .\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2).
69 .\" Fear. Run. Save yourself. No user-serviceable parts.
70 . \" fudge factors for nroff and troff
79 . ds #H ((1u-(\\\\n(.fu%2u))*.13m)
85 . \" simple accents for nroff and troff
95 . ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u"
96 . ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u'
97 . ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u'
98 . ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u'
99 . ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u'
100 . ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u'
102 . \" troff and (daisy-wheel) nroff accents
103 .ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V'
104 .ds 8 \h'\*(#H'\(*b\h'-\*(#H'
105 .ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#]
106 .ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H'
107 .ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u'
108 .ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#]
109 .ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#]
110 .ds ae a\h'-(\w'a'u*4/10)'e
111 .ds Ae A\h'-(\w'A'u*4/10)'E
112 . \" corrections for vroff
113 .if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u'
114 .if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u'
115 . \" for low resolution devices (crt and lpr)
116 .if \n(.H>23 .if \n(.V>19 \
129 .\" ========================================================================
132 .TH nkf 1 "2006-08-22" "nkf 2.0.8" " "
134 nkf \- Network Kanji Filter
136 .IX Header "SYNOPSIS"
137 nkf \fB[\-butjnesliohrTVvwWJESZxXFfmMBOcdILg]\fR \fB[\fR\fIfile ...\fR\fB]\fR
139 .IX Header "DESCRIPTION"
140 \&\fBNkf\fR is a yet another kanji code converter among networks, hosts and terminals.
141 It converts input kanji code to designated kanji code
142 such as \s-1ISO\-2022\-JP\s0, Shift_JIS, \s-1EUC\-JP\s0, \s-1UTF\-8\s0 or \s-1UTF\-16\s0.
144 One of the most unique faculty of \fBnkf\fR is the guess of the input kanji encodings.
145 It currently recognizes \s-1ISO\-2022\-JP\s0, Shift_JIS, \s-1EUC\-JP\s0, \s-1UTF\-8\s0 and \s-1UTF\-16\s0.
146 So users needn't set the input kanji code explicitly.
148 By default, X0201 kana is converted into X0208 kana.
149 For X0201 kana, \s-1SO/SI\s0, \s-1SSO\s0 and \s-1ESC\-\s0(\-I methods are supported.
150 For automatic code detection, nkf assumes no X0201 kana in Shift_JIS.
151 To accept X0201 in Shift_JIS, use \fB\-X\fR, \fB\-x\fR or \fB\-S\fR.
154 .IP "\fB\-b \-u\fR" 4
156 Output is buffered (\s-1DEFAULT\s0), Output is unbuffered.
157 .IP "\fB\-j \-s \-e \-w \-w16\fR" 4
158 .IX Item "-j -s -e -w -w16"
159 Output code is \s-1ISO\-2022\-JP\s0 (7bit \s-1JIS\s0), Shift_JIS, \s-1EUC\-JP\s0,
160 \&\s-1UTF\-8N\s0, \s-1UTF\-16BE\s0.
161 Without this option and compile option, \s-1ISO\-2022\-JP\s0 is assumed.
162 .IP "\fB\-J \-S \-E \-W \-W16\fR" 4
163 .IX Item "-J -S -E -W -W16"
164 Input assumption is \s-1JIS\s0 7 bit, Shift_JIS, \s-1EUC\-JP\s0,
165 \&\s-1UTF\-8\s0, \s-1UTF\-16LE\s0.
169 Assume \s-1JIS\s0 input. It also accepts \s-1EUC\-JP\s0.
170 This is the default. This flag does not exclude Shift_JIS.
173 Assume Shift_JIS and X0201 kana input. It also accepts \s-1JIS\s0.
174 EUC-JP is recognized as X0201 kana. Without \fB\-x\fR flag,
175 X0201 kana (halfwidth kana) is converted into X0208.
178 Assume EUC-JP input. It also accepts \s-1JIS\s0.
186 .IP "\fB\-i[@B]\fR" 4
188 Specify the Esc Seq for \s-1JIS\s0 X 0208\-1978/83. (\s-1DEFAULT\s0 B)
189 .IP "\fB\-o[\s-1BJH\s0]\fR" 4
191 Specify the Esc Seq for ASCII/Roman. (\s-1DEFAULT\s0 B)
194 {de/en}crypt \s-1ROT13/47\s0
195 .IP "\fB\-h[123] \-\-hiragana \-\-katakana \-\-katakana\-hiragana\fR" 4
196 .IX Item "-h[123] --hiragana --katakana --katakana-hiragana"
199 .IP "\fB\-h1 \-\-hiragana\fR" 4
200 .IX Item "-h1 --hiragana"
202 Katakana to Hiragana conversion.
203 .IP "\fB\-h2 \-\-katakana\fR" 4
204 .IX Item "-h2 --katakana"
205 Hiragana to Katakana conversion.
206 .IP "\fB\-h3 \-\-katakana\-hiragana\fR" 4
207 .IX Item "-h3 --katakana-hiragana"
208 Katakana to Hiragana and Hiragana to Katakana conversion.
214 Text mode output (\s-1MS\-DOS\s0)
217 \&\s-1ISO8859\-1\s0 (Latin\-1) support
218 .IP "\fB\-f[\f(BIm\fB [\- \f(BIn\fB]]\fR" 4
219 .IX Item "-f[m [- n]]"
220 Folding on \fIm\fR length with \fIn\fR margin in a line.
221 Without this option, fold length is 60 and fold margin is 10.
224 New line preserving line folding.
225 .IP "\fB\-Z[0\-3]\fR" 4
227 Convert X0208 alphabet (Fullwidth Alphabets) to \s-1ASCII\s0.
229 .IP "\fB\-Z \-Z0\fR" 4
231 Convert X0208 alphabet to \s-1ASCII\s0.
234 Converts X0208 kankaku to single \s-1ASCII\s0 space.
237 Converts X0208 kankaku to double \s-1ASCII\s0 spaces.
240 Replacing Fullwidth >, <, ", & into '>', '<', '"', '&' as in \s-1HTML\s0.
244 .IP "\fB\-X \-x\fR" 4
246 Assume X0201 kana in MS\-Kanji.
247 With \fB\-X\fR or without this option, X0201 is converted into X0208 Kana.
248 With \fB\-x\fR, try to preserve X0208 kana and do not convert X0201 kana to X0208.
249 In \s-1JIS\s0 output, \s-1ESC\-\s0(\-I is used. In \s-1EUC\s0 output, \s-1SSO\s0 is used.
250 .IP "\fB\-B[0\-2]\fR" 4
252 Assume broken JIS-Kanji input, which lost \s-1ESC\s0.
253 Useful when your site is using old B\-News Nihongo patch.
257 allows any char after \s-1ESC\-\s0( or \s-1ESC\-$\s0.
260 forces \s-1ASCII\s0 after \s-1NL\s0.
266 Replacing non iso\-2022\-jp char into a geta character
267 (substitute character in Japanese).
268 .IP "\fB\-m[\s-1BQN0\s0]\fR" 4
270 \&\s-1MIME\s0 \s-1ISO\-2022\-JP/ISO8859\-1\s0 decode. (\s-1DEFAULT\s0)
271 To see \s-1ISO8859\-1\s0 (Latin\-1) \-l is necessary.
275 Decode \s-1MIME\s0 base64 encoded stream. Remove header or other part before
279 Decode \s-1MIME\s0 quoted stream. '_' in quoted stream is converted to space.
283 It allows line break in the middle of the base64 encoding.
286 No \s-1MIME\s0 decode.
292 \&\s-1MIME\s0 encode. Header style. All \s-1ASCII\s0 code and control characters are intact.
296 \&\s-1MIME\s0 encode Base64 stream.
297 Kanji conversion is performed before encoding, so this cannot be used as a picture encoder.
300 Perfome quoted encoding.
306 Input and output code is \s-1ISO8859\-1\s0 (Latin\-1) and \s-1ISO\-2022\-JP\s0.
307 \&\fB\-s\fR, \fB\-e\fR and \fB\-x\fR are not compatible with this option.
308 .IP "\fB\-L[uwm] \-d \-c\fR" 4
309 .IX Item "-L[uwm] -d -c"
312 .IP "\fB\-Lu \-d\fR" 4
315 .IP "\fB\-Lw \-c\fR" 4
317 windows (\s-1CRLF\s0)
322 Without this option, nkf doesn't convert line breaks.
326 .IP "\fB\-\-fj \-\-unix \-\-mac \-\-msdos \-\-windows\fR" 4
327 .IX Item "--fj --unix --mac --msdos --windows"
328 convert for these system
329 .IP "\fB\-\-jis \-\-euc \-\-sjis \-\-mime \-\-base64\fR" 4
330 .IX Item "--jis --euc --sjis --mime --base64"
331 convert for named code
332 .IP "\fB\-\-jis\-input \-\-euc\-input \-\-sjis\-input \-\-mime\-input \-\-base64\-input\fR" 4
333 .IX Item "--jis-input --euc-input --sjis-input --mime-input --base64-input"
335 .IP "\fB\-\-ic=\f(BIinput codeset\fB \-\-oc=\f(BIoutput codeset\fB\fR" 4
336 .IX Item "--ic=input codeset --oc=output codeset"
337 Set the input or output codeset.
338 \&\s-1NKF\s0 supports following codesets and those codeset name are case insensitive.
340 .IP "\s-1ISO\-2022\-JP\s0" 4
341 .IX Item "ISO-2022-JP"
342 a.k.a. \s-1RFC1468\s0, 7bit \s-1JIS\s0, \s-1JUNET\s0
343 .IP "EUC-JP (eucJP\-nkf)" 4
344 .IX Item "EUC-JP (eucJP-nkf)"
345 a.k.a. \s-1AT&T\s0 \s-1JIS\s0, Japanese \s-1EUC\s0, \s-1UJIS\s0
347 .IX Item "eucJP-ascii"
351 .IP "\s-1CP51932\s0" 4
354 Microsoft Version of \s-1EUC\-JP\s0.
357 a.k.a. \s-1SJIS\s0, MS-Kanji
361 .IP "\s-1UTF\-8\s0" 4
363 same as \s-1UTF\-8N\s0
364 .IP "\s-1UTF\-8N\s0" 4
366 \&\s-1UTF\-8\s0 without \s-1BOM\s0
367 .IP "\s-1UTF\-8\-BOM\s0" 4
369 \&\s-1UTF\-8\s0 with \s-1BOM\s0
370 .IP "\s-1UTF8\-MAC\s0 (input only)" 4
371 .IX Item "UTF8-MAC (input only)"
372 decomposed \s-1UTF\-8\s0
373 .IP "\s-1UTF\-16\s0" 4
375 same as \s-1UTF\-16BE\s0
376 .IP "\s-1UTF\-16BE\s0" 4
378 \&\s-1UTF\-16\s0 Big Endian without \s-1BOM\s0
379 .IP "\s-1UTF\-16BE\-BOM\s0" 4
380 .IX Item "UTF-16BE-BOM"
381 \&\s-1UTF\-16\s0 Big Endian with \s-1BOM\s0
382 .IP "\s-1UTF\-16LE\s0" 4
384 \&\s-1UTF\-16\s0 Little Endian without \s-1BOM\s0
385 .IP "\s-1UTF\-16LE\-BOM\s0" 4
386 .IX Item "UTF-16LE-BOM"
387 \&\s-1UTF\-16\s0 Little Endian with \s-1BOM\s0
391 .IP "\fB\-\-fb\-{skip, html, xml, perl, java, subchar}\fR" 4
392 .IX Item "--fb-{skip, html, xml, perl, java, subchar}"
393 Specify the way that nkf handles unassigned characters.
394 Without this option, \-\-fb\-skip is assumed.
395 .IP "\fB\-\-prefix=\f(BIescape character\fB\f(BItarget character\fB..\fR" 4
396 .IX Item "--prefix=escape charactertarget character.."
397 When nkf converts to Shift_JIS,
398 nkf adds a specified escape character to specified 2nd byte of Shift_JIS characters.
399 1st byte of argument is the escape character and following bytes are target characters.
400 .IP "\fB\-\-no\-cp932ext\fR" 4
401 .IX Item "--no-cp932ext"
402 Handle the characters extended in \s-1CP932\s0 as unassigned characters.
403 .IP "\fB\-\-no\-best\-fit\-chars\fR" 4
404 .IX Item "--no-best-fit-chars"
405 When Unicode to Encoded byte conversion,
406 don't convert characters which is not round trip safe.
407 When Unicode to Unicode conversion,
408 with this and \-x option, nkf can be used as \s-1UTF\s0 converter.
409 (In other words, without this and \-x option, nkf doesn't save some characters)
411 When nkf convert string which related to path, you should use this opion.
412 .IP "\fB\-\-cap\-input\fR" 4
413 .IX Item "--cap-input"
414 Decode hex encoded characters.
415 .IP "\fB\-\-url\-input\fR" 4
416 .IX Item "--url-input"
417 Unescape percent escaped characters.
418 .IP "\fB\-\-numchar\-input\fR" 4
419 .IX Item "--numchar-input"
420 Decode character reference, such as \*(L"&#....;\*(R".
421 .IP "\fB\-\-in\-place[=\fR\fI\s-1SUFFIX\s0\fR\fB]\fR \fB\-\-overwrite[=\fR\fI\s-1SUFFIX\s0\fR\fB]\fR" 4
422 .IX Item "--in-place[=SUFFIX] --overwrite[=SUFFIX]"
423 Overwrite \fBoriginal\fR listed files by filtered result.
425 \&\fBNote\fR \-\-overwrite preserves timestamp of original files.
426 .IP "\fB\-\-guess\fR" 4
428 Print guessed encoding.
429 .IP "\fB\-\-help\fR" 4
432 .IP "\fB\-\-version\fR" 4
437 Ignore rest of \-option.
440 Copyright (C) 1987, \s-1FUJITSU\s0 \s-1LTD\s0. (I.Ichikawa),2000 S. Kono, \s-1COW\s0
441 Copyright (C) 2002\-2006 Kono, Furukawa, Naruse, mastodon