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 "2006-07-30" "nkf 2.0.7" " "
134 nkf \- Network Kanji Filter
136 .IX Header "SYNOPSIS"
138 \& nkf B<[-butjnesliohrTVvwWJESZxXFfmMBOcdILg]> B<[>I<file ...>B<]>
141 .IX Header "DESCRIPTION"
142 \&\fBNkf\fR is a yet another kanji code converter among networks, hosts and terminals.
143 It converts input kanji code to designated kanji code
144 such as \s-1ISO\-2022\-JP\s0, Shift_JIS, \s-1EUC\-JP\s0, \s-1UTF\-8\s0 or \s-1UTF\-16\s0.
146 One of the most unique faculty of \fBnkf\fR is the guess of the input kanji encodings.
147 It currently recognizes \s-1ISO\-2022\-JP\s0, Shift_JIS, \s-1EUC\-JP\s0, \s-1UTF\-8\s0 and \s-1UTF\-16\s0.
148 So users needn't set the input kanji code explicitly.
150 By default, X0201 kana is converted into X0208 kana.
151 For X0201 kana, \s-1SO/SI\s0, \s-1SSO\s0 and \s-1ESC\-\s0(\-I methods are supported.
152 For automatic code detection, nkf assumes no X0201 kana in Shift_JIS.
153 To accept X0201 in Shift_JIS, use \fB\-X\fR, \fB\-x\fR or \fB\-S\fR.
156 .IP "\fB\-b \-u\fR" 4
158 Output is buffered (\s-1DEFAULT\s0), Output is unbuffered.
159 .IP "\fB\-j \-s \-e \-w \-w16\fR" 4
160 .IX Item "-j -s -e -w -w16"
161 Output code is \s-1ISO\-2022\-JP\s0 (7bit \s-1JIS\s0), Shift_JIS, \s-1EUC\-JP\s0,
162 \&\s-1UTF\-8N\s0, \s-1UTF\-16BE\s0.
163 Without this option and compile option, \s-1ISO\-2022\-JP\s0 is assumed.
164 .IP "\fB\-J \-S \-E \-W \-W16\fR" 4
165 .IX Item "-J -S -E -W -W16"
166 Input assumption is \s-1JIS\s0 7 bit, Shift_JIS, \s-1EUC\-JP\s0,
167 \&\s-1UTF\-8\s0, \s-1UTF\-16LE\s0.
171 Assume \s-1JIS\s0 input. It also accepts \s-1EUC\-JP\s0.
172 This is the default. This flag does not exclude Shift_JIS.
175 Assume Shift_JIS and X0201 kana input. It also accepts \s-1JIS\s0.
176 EUC-JP is recognized as X0201 kana. Without \fB\-x\fR flag,
177 X0201 kana (halfwidth kana) is converted into X0208.
180 Assume EUC-JP input. It also accepts \s-1JIS\s0.
188 .IP "\fB\-i[@B]\fR" 4
190 Specify the Esc Seq for \s-1JIS\s0 X 0208\-1978/83. (\s-1DEFAULT\s0 B)
191 .IP "\fB\-o[\s-1BJH\s0]\fR" 4
193 Specify the Esc Seq for ASCII/Roman. (\s-1DEFAULT\s0 B)
196 {de/en}crypt \s-1ROT13/47\s0
197 .IP "\fB\-h[123] \-\-hiragana \-\-katakana \-\-katakana\-hiragana\fR" 4
198 .IX Item "-h[123] --hiragana --katakana --katakana-hiragana"
201 .IP "\fB\-h1 \-\-hiragana\fR" 4
202 .IX Item "-h1 --hiragana"
204 Katakana to Hiragana conversion.
205 .IP "\fB\-h2 \-\-katakana\fR" 4
206 .IX Item "-h2 --katakana"
207 Hiragana to Katakana conversion.
208 .IP "\fB\-h3 \-\-katakana\-hiragana\fR" 4
209 .IX Item "-h3 --katakana-hiragana"
210 Katakana to Hiragana and Hiragana to Katakana conversion.
216 Text mode output (\s-1MS\-DOS\s0)
219 \&\s-1ISO8859\-1\s0 (Latin\-1) support
220 .IP "\fB\-f[\f(BIm\fB [\- \f(BIn\fB]]\fR" 4
221 .IX Item "-f[m [- n]]"
222 Folding on \fIm\fR length with \fIn\fR margin in a line.
223 Without this option, fold length is 60 and fold margin is 10.
226 New line preserving line folding.
227 .IP "\fB\-Z[0\-3]\fR" 4
229 Convert X0208 alphabet (Fullwidth Alphabets) to \s-1ASCII\s0.
231 .IP "\fB\-Z \-Z0\fR" 4
233 Convert X0208 alphabet to \s-1ASCII\s0.
236 Converts X0208 kankaku to single \s-1ASCII\s0 space.
239 Converts X0208 kankaku to double \s-1ASCII\s0 spaces.
242 Replacing Fullwidth >, <, ", & into '>', '<', '"', '&' as in \s-1HTML\s0.
246 .IP "\fB\-X \-x\fR" 4
248 Assume X0201 kana in MS\-Kanji.
249 With \fB\-X\fR or without this option, X0201 is converted into X0208 Kana.
250 With \fB\-x\fR, try to preserve X0208 kana and do not convert X0201 kana to X0208.
251 In \s-1JIS\s0 output, \s-1ESC\-\s0(\-I is used. In \s-1EUC\s0 output, \s-1SSO\s0 is used.
252 .IP "\fB\-B[0\-2]\fR" 4
254 Assume broken JIS-Kanji input, which lost \s-1ESC\s0.
255 Useful when your site is using old B\-News Nihongo patch.
259 allows any char after \s-1ESC\-\s0( or \s-1ESC\-$\s0.
262 forces \s-1ASCII\s0 after \s-1NL\s0.
268 Replacing non iso\-2022\-jp char into a geta character
269 (substitute character in Japanese).
270 .IP "\fB\-m[\s-1BQN0\s0]\fR" 4
272 \&\s-1MIME\s0 \s-1ISO\-2022\-JP/ISO8859\-1\s0 decode. (\s-1DEFAULT\s0)
273 To see \s-1ISO8859\-1\s0 (Latin\-1) \-l is necessary.
277 Decode \s-1MIME\s0 base64 encoded stream. Remove header or other part before
281 Decode \s-1MIME\s0 quoted stream. '_' in quoted stream is converted to space.
285 It allows line break in the middle of the base64 encoding.
288 No \s-1MIME\s0 decode.
294 \&\s-1MIME\s0 encode. Header style. All \s-1ASCII\s0 code and control characters are intact.
298 \&\s-1MIME\s0 encode Base64 stream.
299 Kanji conversion is performed before encoding, so this cannot be used as a picture encoder.
302 Perfome quoted encoding.
308 Input and output code is \s-1ISO8859\-1\s0 (Latin\-1) and \s-1ISO\-2022\-JP\s0.
309 \&\fB\-s\fR, \fB\-e\fR and \fB\-x\fR are not compatible with this option.
310 .IP "\fB\-L[uwm] \-d \-c\fR" 4
311 .IX Item "-L[uwm] -d -c"
314 .IP "\fB\-Lu \-d\fR" 4
317 .IP "\fB\-Lw \-c\fR" 4
319 windows (\s-1CRLF\s0)
324 Without this option, nkf doesn't convert line breaks.
328 .IP "\fB\-\-fj \-\-unix \-\-mac \-\-msdos \-\-windows\fR" 4
329 .IX Item "--fj --unix --mac --msdos --windows"
330 convert for these system
331 .IP "\fB\-\-jis \-\-euc \-\-sjis \-\-mime \-\-base64\fR" 4
332 .IX Item "--jis --euc --sjis --mime --base64"
333 convert for named code
334 .IP "\fB\-\-jis\-input \-\-euc\-input \-\-sjis\-input \-\-mime\-input \-\-base64\-input\fR" 4
335 .IX Item "--jis-input --euc-input --sjis-input --mime-input --base64-input"
337 .IP "\fB\-\-ic=\f(BIinput codeset\fB \-\-oc=\f(BIoutput codeset\fB\fR" 4
338 .IX Item "--ic=input codeset --oc=output codeset"
339 Set the input or output codeset.
340 \&\s-1NKF\s0 supports following codesets and those codeset name are case insensitive.
342 .IP "\s-1ISO\-2022\-JP\s0" 4
343 .IX Item "ISO-2022-JP"
344 a.k.a. \s-1RFC1468\s0, 7bit \s-1JIS\s0, \s-1JUNET\s0
345 .IP "EUC-JP (eucJP\-nkf)" 4
346 .IX Item "EUC-JP (eucJP-nkf)"
347 a.k.a. \s-1AT&T\s0 \s-1JIS\s0, Japanese \s-1EUC\s0, \s-1UJIS\s0
349 .IX Item "eucJP-ascii"
353 .IP "\s-1CP51932\s0" 4
356 Microsoft Version of \s-1EUC\-JP\s0.
359 a.k.a. \s-1SJIS\s0, MS-Kanji
363 .IP "\s-1UTF\-8\s0" 4
365 same as \s-1UTF\-8N\s0
366 .IP "\s-1UTF\-8N\s0" 4
368 \&\s-1UTF\-8\s0 without \s-1BOM\s0
369 .IP "\s-1UTF\-8\-BOM\s0" 4
371 \&\s-1UTF\-8\s0 with \s-1BOM\s0
372 .IP "\s-1UTF\-16\s0" 4
374 same as \s-1UTF\-16BE\s0
375 .IP "\s-1UTF\-16BE\s0" 4
377 \&\s-1UTF\-16\s0 Big Endian without \s-1BOM\s0
378 .IP "\s-1UTF\-16BE\-BOM\s0" 4
379 .IX Item "UTF-16BE-BOM"
380 \&\s-1UTF\-16\s0 Big Endian with \s-1BOM\s0
381 .IP "\s-1UTF\-16LE\s0" 4
383 \&\s-1UTF\-16\s0 Little Endian without \s-1BOM\s0
384 .IP "\s-1UTF\-16LE\-BOM\s0" 4
385 .IX Item "UTF-16LE-BOM"
386 \&\s-1UTF\-16\s0 Little Endian with \s-1BOM\s0
387 .IP "\s-1UTF8\-MAC\s0 (input only)" 4
388 .IX Item "UTF8-MAC (input only)"
393 .IP "\fB\-\-fb\-{skip, html, xml, perl, java, subchar}\fR" 4
394 .IX Item "--fb-{skip, html, xml, perl, java, subchar}"
396 Specify the way that nkf handles unassigned characters.
397 Without this option, \-\-fb\-skip is assumed.
398 .IP "\fB\-\-prefix=\f(BIescape character\fB\f(BItarget character\fB..\fR" 4
399 .IX Item "--prefix=escape charactertarget character.."
400 When nkf converts to Shift_JIS,
401 nkf adds a specified escape character to specified 2nd byte of Shift_JIS characters.
402 1st byte of argument is the escape character and following bytes are target characters.
403 .IP "\fB\-\-no\-cp932ext\fR" 4
404 .IX Item "--no-cp932ext"
405 Handle the characters extended in \s-1CP932\s0 as unassigned characters.
406 .IP "\fB\-\-no\-best\-fit\-chars\fR" 4
407 .IX Item "--no-best-fit-chars"
408 When Unicode to Encoded byte conversion,
409 don't convert characters which is not round trip safe.
410 When Unicode to Unicode conversion,
411 with this and \-x option, nkf can be used as \s-1UTF\s0 converter.
412 (In other words, without this and \-x option, nkf doesn't save some characters)
414 When nkf convert string which related to path, you should use this opion.
415 .IP "\fB\-\-cap\-input\fR" 4
416 .IX Item "--cap-input"
417 Decode hex encoded characters.
418 .IP "\fB\-\-url\-input\fR" 4
419 .IX Item "--url-input"
420 Unescape percent escaped characters.
421 .IP "\fB\-\-numchar\-input\fR" 4
422 .IX Item "--numchar-input"
423 Decode character reference, such as \*(L"&#....;\*(R".
424 .IP "\fB\-\-in\-place[=\fR\fI\s-1SUFFIX\s0\fR\fB]\fR \fB\-\-overwrite[=\fR\fI\s-1SUFFIX\s0\fR\fB]\fR" 4
425 .IX Item "--in-place[=SUFFIX] --overwrite[=SUFFIX]"
426 Overwrite \fBoriginal\fR listed files by filtered result.
428 \&\fBNote\fR \-\-overwrite preserves timestamp of original files.
429 .IP "\fB\-\-guess\fR" 4
431 Print guessed encoding.
432 .IP "\fB\-\-help\fR" 4
435 .IP "\fB\-\-version\fR" 4
440 Ignore rest of \-option.
443 Copyright (C) 1987, \s-1FUJITSU\s0 \s-1LTD\s0. (I.Ichikawa),2000 S. Kono, \s-1COW\s0
444 Copyright (C) 2002\-2006 Kono, Furukawa, Naruse, mastodon