From 2507e957e07ffd707b45742523e82f5f0c5772ba Mon Sep 17 00:00:00 2001 From: naruse Date: Thu, 23 Feb 2006 23:17:20 +0000 Subject: * ext/nkf/nkf.c ext/nkf/lib/kconv.rb: Add rdoc. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/branches/ruby_1_8@9990 b2dd03c8-39d4-4d8f-98ff-823fe69b080e --- ext/nkf/nkf.c | 378 +++++++++++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 345 insertions(+), 33 deletions(-) (limited to 'ext/nkf/nkf.c') diff --git a/ext/nkf/nkf.c b/ext/nkf/nkf.c index 65442a130c..f03a858c64 100644 --- a/ext/nkf/nkf.c +++ b/ext/nkf/nkf.c @@ -1,9 +1,9 @@ /* - * NKF Module for Ruby base on nkf 2.x + * NKF - Ruby extension for Network Kanji Filter * - * original nkf2.x is maintained at http://sourceforge.jp/projects/nkf/ + * original nkf2.x is maintained at http://sourceforge.jp/projects/nkf/ * - * $Id$ + * $Id$ * */ @@ -78,6 +78,21 @@ rb_nkf_putchar(c) #include "nkf-utf8/utf8tbl.c" #include "nkf-utf8/nkf.c" +/* + * call-seq: + * NKF.nkf(opt, str) -> string + * + * Convert _str_ and return converted result. + * Conversion details are specified by _opt_ as String. + * + * require 'nkf' + * output = NKF.nkf("-s", input) + * + * *Note* + * By default, nkf decodes MIME encoded string. + * If you want not to decode input, use NKF.nkf with -m0 flag. + */ + static VALUE rb_nkf_kconv(obj, opt, src) VALUE obj, opt, src; @@ -118,11 +133,27 @@ rb_nkf_kconv(obj, opt, src) /* - * NKF.guess1 + * call-seq: + * NKF.guess1(str) -> integer + * + * Returns guessed encoding of _str_ as integer. + * + * Algorithm described in: + * Ken Lunde. `Understanding Japanese Information Processing' + * Sebastopol, CA: O'Reilly & Associates. * - * Character code detection - Algorithm described in: - * Ken Lunde. `Understanding Japanese Information Processing' - * Sebastopol, CA: O'Reilly & Associates. + * case NKF.guess1(input) + * when NKF::JIS + * "ISO-2022-JP" + * when NKF::SJIS + * "Shift_JIS" + * when NKF::EUC + * "EUC-JP" + * when NKF::UNKNOWN + * "UNKNOWN(ASCII)" + * when NKF::BINARY + * "BINARY" + * end */ static VALUE @@ -214,9 +245,29 @@ rb_nkf_guess1(obj, src) /* - * NKF.guess2 + * call-seq: + * NKF.guess2(str) -> integer * - * Guess Encoding By NKF2.0 Routine + * Returns guessed encoding of _str_ as integer by nkf routine. + * + * case NKF.guess(input) + * when NKF::ASCII + * "ASCII" + * when NKF::JIS + * "ISO-2022-JP" + * when NKF::SJIS + * "Shift_JIS" + * when NKF::EUC + * "EUC-JP" + * when NKF::UTF8 + * "UTF-8" + * when NKF::UTF16 + * "UTF-16" + * when NKF::UNKNOWN + * "UNKNOWN" + * when NKF::BINARY + * "BINARY" + * end */ static VALUE @@ -261,32 +312,293 @@ rb_nkf_guess2(obj, src) } -/* Initialize NKF Module */ +/* + * NKF - Ruby extension for Network Kanji Filter + * + * == Description + * + * This is a Ruby Extension version of nkf (Netowrk Kanji Filter). + * It converts the first argument and return converted result. Conversion + * details are specified by flags as the first argument. + * + * *Nkf* is a yet another kanji code converter among networks, hosts and terminals. + * It converts input kanji code to designated kanji code + * such as ISO-2022-JP, Shift_JIS, EUC-JP, UTF-8 or UTF-16. + * + * One of the most unique faculty of *nkf* is the guess of the input kanji encodings. + * It currently recognizes ISO-2022-JP, Shift_JIS, EUC-JP, UTF-8 and UTF-16. + * So users needn't set the input kanji code explicitly. + * + * 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 Shift_JIS. + * To accept X0201 in Shift_JIS, use -X, -x or -S. + * + * == Flags + * + * === -b -u + * + * Output is buffered (DEFAULT), Output is unbuffered. + * + * === -j -s -e -w -w16 + * + * Output code is ISO-2022-JP (7bit JIS), Shift_JIS, EUC-JP, + * UTF-8N, UTF-16BE. + * Without this option and compile option, ISO-2022-JP is assumed. + * + * === -J -S -E -W -W16 + * + * Input assumption is JIS 7 bit, Shift_JIS, EUC-JP, + * UTF-8, UTF-16LE. + * + * ==== -J + * + * Assume JIS input. It also accepts EUC-JP. + * This is the default. This flag does not exclude Shift_JIS. + * + * ==== -S + * + * Assume Shift_JIS and X0201 kana input. It also accepts JIS. + * EUC-JP is recognized as X0201 kana. Without -x flag, + * X0201 kana (halfwidth kana) is converted into X0208. + * + * ==== -E + * + * Assume EUC-JP input. It also accepts JIS. + * Same as -J. + * + * === -t + * + * No conversion. + * + * === -i_ + * + * Output sequence to designate JIS-kanji. (DEFAULT B) + * + * === -o_ + * + * Output sequence to designate ASCII. (DEFAULT B) + * + * === -r + * + * {de/en}crypt ROT13/47 + * + * === -h[123] --hiragana --katakana --katakana-hiragana + * + * [-h1 --hiragana] Katakana to Hiragana conversion. + * + * [-h2 --katakana] Hiragana to Katakana conversion. + * + * [-h3 --katakana-hiragana] Katakana to Hiragana and Hiragana to Katakana conversion. + * + * === -T + * + * Text mode output (MS-DOS) + * + * === -l + * + * ISO8859-1 (Latin-1) support + * + * === -f[m [- n]] + * + * Folding on m length with n margin in a line. + * Without this option, fold length is 60 and fold margin is 10. + * + * === -F + * + * New line preserving line folding. + * + * === -Z[0-3] + * + * Convert X0208 alphabet (Fullwidth Alphabets) to ASCII. + * + * [-Z -Z0] Convert X0208 alphabet to ASCII. + * + * [-Z1] Converts X0208 kankaku to single ASCII space. + * + * [-Z2] Converts X0208 kankaku to double ASCII spaces. + * + * [-Z3] Replacing Fullwidth >, <, ", & into '>', '<', '"', '&' as in HTML. + * + * === -X -x + * + * Assume X0201 kana in MS-Kanji. + * With -X or without this option, X0201 is converted into X0208 Kana. + * With -x, try to preserve X0208 kana and do not convert X0201 kana to X0208. + * In JIS output, ESC-(-I is used. In EUC output, SSO is used. + * + * === -B[0-2] + * + * Assume broken JIS-Kanji input, which lost ESC. + * Useful when your site is using old B-News Nihongo patch. + * + * [-B1] allows any char after ESC-( or ESC-$. + * + * [-B2] forces ASCII after NL. + * + * === -I + * + * Replacing non iso-2022-jp char into a geta character + * (substitute character in Japanese). + * + * === -d -c + * + * Delete \r in line feed, Add \r in line feed. + * + * === -m[BQN0] + * + * MIME ISO-2022-JP/ISO8859-1 decode. (DEFAULT) + * To see ISO8859-1 (Latin-1) -l is necessary. + * + * [-mB] Decode MIME base64 encoded stream. Remove header or other part before + * conversion. + * + * [-mQ] Decode MIME quoted stream. '_' in quoted stream is converted to space. + * + * [-mN] Non-strict decoding. + * It allows line break in the middle of the base64 encoding. + * + * [-m0] No MIME decode. + * + * === -M + * + * MIME encode. Header style. All ASCII code and control characters are intact. + * Kanji conversion is performed before encoding, so this cannot be used as a picture encoder. + * + * [-MB] MIME encode Base64 stream. + * + * [-MQ] Perfome quoted encoding. + * + * === -l + * + * Input and output code is ISO8859-1 (Latin-1) and ISO-2022-JP. + * -s, -e and -x are not compatible with this option. + * + * === -L[uwm] + * + * new line mode + * Without this option, nkf doesn't convert line breaks. + * + * [-Lu] unix (LF) + * + * [-Lw] windows (CRLF) + * + * [-Lm] mac (CR) + * + * === --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 + * + * === --ic=input codeset --oc=output codeset + * + * Set the input or output codeset. + * NKF supports following codesets and those codeset name are case insensitive. + * + * [ISO-2022-JP] a.k.a. RFC1468, 7bit JIS, JUNET + * + * [EUC-JP (eucJP-nkf)] a.k.a. AT&T JIS, Japanese EUC, UJIS + * + * [eucJP-ascii] a.k.a. x-eucjp-open-19970715-ascii + * + * [eucJP-ms] a.k.a. x-eucjp-open-19970715-ms + * + * [CP51932] Microsoft Version of EUC-JP. + * + * [Shift_JIS] SJIS, MS-Kanji + * + * [CP932] a.k.a. Windows-31J + * + * [UTF-8] same as UTF-8N + * + * [UTF-8N] UTF-8 without BOM + * + * [UTF-8-BOM] UTF-8 with BOM + * + * [UTF-16] same as UTF-16BE + * + * [UTF-16BE] UTF-16 Big Endian without BOM + * + * [UTF-16BE-BOM] UTF-16 Big Endian with BOM + * + * [UTF-16LE] UTF-16 Little Endian without BOM + * + * [UTF-16LE-BOM] UTF-16 Little Endian with BOM + * + * [UTF8-MAC] NKDed UTF-8, a.k.a. UTF8-NFD (input only) + * + * === --fb-{skip, html, xml, perl, java, subchar} + * + * Specify the way that nkf handles unassigned characters. + * Without this option, --fb-skip is assumed. + * + * === --prefix= escape character target 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. + * + * === --disable-cp932ext + * + * Handle the characters extended in CP932 as unassigned characters. + * + * === --cap-input + * + * Decode hex encoded characters. + * + * === --url-input + * + * Unescape percent escaped characters. + * + * === -- + * + * Ignore rest of -option. + */ void Init_nkf() { - VALUE mKconv = rb_define_module("NKF"); - - rb_define_module_function(mKconv, "nkf", rb_nkf_kconv, 2); - rb_define_module_function(mKconv, "guess", rb_nkf_guess2, 1); - rb_define_module_function(mKconv, "guess1", rb_nkf_guess1, 1); - rb_define_module_function(mKconv, "guess2", rb_nkf_guess2, 1); - - rb_define_const(mKconv, "AUTO", INT2FIX(_AUTO)); - rb_define_const(mKconv, "JIS", INT2FIX(_JIS)); - rb_define_const(mKconv, "EUC", INT2FIX(_EUC)); - rb_define_const(mKconv, "SJIS", INT2FIX(_SJIS)); - rb_define_const(mKconv, "BINARY", INT2FIX(_BINARY)); - rb_define_const(mKconv, "NOCONV", INT2FIX(_NOCONV)); - rb_define_const(mKconv, "ASCII", INT2FIX(_ASCII)); - rb_define_const(mKconv, "UTF8", INT2FIX(_UTF8)); - rb_define_const(mKconv, "UTF16", INT2FIX(_UTF16)); - rb_define_const(mKconv, "UTF32", INT2FIX(_UTF32)); - rb_define_const(mKconv, "UNKNOWN", INT2FIX(_UNKNOWN)); - rb_define_const(mKconv, "VERSION", rb_str_new2(RUBY_NKF_VERSION)); - /* for debug */ - rb_define_const(mKconv, "NKF_VERSION", rb_str_new2(NKF_VERSION)); - rb_define_const(mKconv, "NKF_RELEASE_DATE", rb_str_new2(NKF_RELEASE_DATE)); - rb_define_const(mKconv, "REVISION", rb_str_new2(RUBY_NKF_REVISION)); + VALUE mKconv = rb_define_module("NKF"); + + rb_define_module_function(mKconv, "nkf", rb_nkf_kconv, 2); + rb_define_module_function(mKconv, "guess1", rb_nkf_guess1, 1); + rb_define_module_function(mKconv, "guess2", rb_nkf_guess2, 1); + rb_define_alias(mKconv, "guess", "guess2"); + rb_define_alias(rb_singleton_class(mKconv), "guess", "guess2"); + + /* Auto-Detect */ + rb_define_const(mKconv, "AUTO", INT2FIX(_AUTO)); + /* ISO-2022-JP */ + rb_define_const(mKconv, "JIS", INT2FIX(_JIS)); + /* EUC-JP */ + rb_define_const(mKconv, "EUC", INT2FIX(_EUC)); + /* Shift_JIS */ + rb_define_const(mKconv, "SJIS", INT2FIX(_SJIS)); + /* BINARY */ + rb_define_const(mKconv, "BINARY", INT2FIX(_BINARY)); + /* No conversion */ + rb_define_const(mKconv, "NOCONV", INT2FIX(_NOCONV)); + /* ASCII */ + rb_define_const(mKconv, "ASCII", INT2FIX(_ASCII)); + /* UTF-8 */ + rb_define_const(mKconv, "UTF8", INT2FIX(_UTF8)); + /* UTF-16 */ + rb_define_const(mKconv, "UTF16", INT2FIX(_UTF16)); + /* UTF-32 */ + rb_define_const(mKconv, "UTF32", INT2FIX(_UTF32)); + /* UNKNOWN */ + rb_define_const(mKconv, "UNKNOWN", INT2FIX(_UNKNOWN)); + /* Full version string of nkf */ + rb_define_const(mKconv, "VERSION", rb_str_new2(RUBY_NKF_VERSION)); + /* Version of nkf */ + rb_define_const(mKconv, "NKF_VERSION", rb_str_new2(NKF_VERSION)); + /* Release date of nkf */ + rb_define_const(mKconv, "NKF_RELEASE_DATE", rb_str_new2(NKF_RELEASE_DATE)); } -- cgit v1.2.3