diff options
Diffstat (limited to 'README')
-rw-r--r-- | README | 189 |
1 files changed, 189 insertions, 0 deletions
@@ -0,0 +1,189 @@ +README 2007/05/31 + +Oniguruma ---- (C) K.Kosako <sndgk393 AT ybb DOT ne DOT jp> + +http://www.geocities.jp/kosako3/oniguruma/ + +Oniguruma is a regular expressions library. +The characteristics of this library is that different character encoding +for every regular expression object can be specified. + +Supported character encodings: + + ASCII, UTF-8, UTF-16BE, UTF-16LE, UTF-32BE, UTF-32LE, + EUC-JP, EUC-TW, EUC-KR, EUC-CN, + Shift_JIS, Big5, GB18030, KOI8-R, CP1251, + ISO-8859-1, ISO-8859-2, ISO-8859-3, ISO-8859-4, ISO-8859-5, + ISO-8859-6, ISO-8859-7, ISO-8859-8, ISO-8859-9, ISO-8859-10, + ISO-8859-11, ISO-8859-13, ISO-8859-14, ISO-8859-15, ISO-8859-16 + +* GB18030: contributed by KUBO Takehiro +* CP1251: contributed by Byte +------------------------------------------------------------ + +License + + BSD license. + + +Install + + Case 1: Unix and Cygwin platform + + 1. ./configure + 2. make + 3. make install + + * uninstall + + make uninstall + + * test (ASCII/EUC-JP) + + make atest + + * configuration check + + onig-config --cflags + onig-config --libs + onig-config --prefix + onig-config --exec-prefix + + + + Case 2: Win32 platform (VC++) + + 1. copy win32\Makefile Makefile + 2. copy win32\config.h config.h + 3. nmake + + onig_s.lib: static link library + onig.dll: dynamic link library + + * test (ASCII/Shift_JIS) + 4. copy win32\testc.c testc.c + 5. nmake ctest + + + +Regular Expressions + + See doc/RE (or doc/RE.ja for Japanese). + + +Usage + + Include oniguruma.h in your program. (Oniguruma API) + See doc/API for Oniguruma API. + + If you want to disable UChar type (== unsigned char) definition + in oniguruma.h, define ONIG_ESCAPE_UCHAR_COLLISION and then + include oniguruma.h. + + If you want to disable regex_t type definition in oniguruma.h, + define ONIG_ESCAPE_REGEX_T_COLLISION and then include oniguruma.h. + + Example of the compiling/linking command line in Unix or Cygwin, + (prefix == /usr/local case) + + cc sample.c -L/usr/local/lib -lonig + + + If you want to use static link library(onig_s.lib) in Win32, + add option -DONIG_EXTERN=extern to C compiler. + + + +Sample Programs + + sample/simple.c example of the minimum (Oniguruma API) + sample/names.c example of the named group callback. + sample/encode.c example of some encodings. + sample/listcap.c example of the capture history. + sample/posix.c POSIX API sample. + sample/sql.c example of the variable meta characters. + (SQL-like pattern matching) + +Test Programs + sample/syntax.c Perl, Java and ASIS syntax test. + sample/crnl.c --enable-crnl-as-line-terminator test + + +Source Files + + oniguruma.h Oniguruma API header file. (public) + onig-config.in configuration check program template. + + regenc.h character encodings framework header file. + regint.h internal definitions + regparse.h internal definitions for regparse.c and regcomp.c + regcomp.c compiling and optimization functions + regenc.c character encodings framework. + regerror.c error message function + regext.c extended API functions. (deluxe version API) + regexec.c search and match functions + regparse.c parsing functions. + regsyntax.c pattern syntax functions and built-in syntax definitions. + regtrav.c capture history tree data traverse functions. + regversion.c version info function. + st.h hash table functions header file + st.c hash table functions + + oniggnu.h GNU regex API header file. (public) + reggnu.c GNU regex API functions + + onigposix.h POSIX API header file. (public) + regposerr.c POSIX error message function. + regposix.c POSIX API functions. + + enc/mktable.c character type table generator. + enc/ascii.c ASCII encoding. + enc/euc_jp.c EUC-JP encoding. + enc/euc_tw.c EUC-TW encoding. + enc/euc_kr.c EUC-KR, EUC-CN encoding. + enc/sjis.c Shift_JIS encoding. + enc/big5.c Big5 encoding. + enc/gb18030.c GB18030 encoding. + enc/koi8.c KOI8 encoding. + enc/koi8_r.c KOI8-R encoding. + enc/cp1251.c CP1251 encoding. + enc/iso8859_1.c ISO-8859-1 encoding. (Latin-1) + enc/iso8859_2.c ISO-8859-2 encoding. (Latin-2) + enc/iso8859_3.c ISO-8859-3 encoding. (Latin-3) + enc/iso8859_4.c ISO-8859-4 encoding. (Latin-4) + enc/iso8859_5.c ISO-8859-5 encoding. (Cyrillic) + enc/iso8859_6.c ISO-8859-6 encoding. (Arabic) + enc/iso8859_7.c ISO-8859-7 encoding. (Greek) + enc/iso8859_8.c ISO-8859-8 encoding. (Hebrew) + enc/iso8859_9.c ISO-8859-9 encoding. (Latin-5 or Turkish) + enc/iso8859_10.c ISO-8859-10 encoding. (Latin-6 or Nordic) + enc/iso8859_11.c ISO-8859-11 encoding. (Thai) + enc/iso8859_13.c ISO-8859-13 encoding. (Latin-7 or Baltic Rim) + enc/iso8859_14.c ISO-8859-14 encoding. (Latin-8 or Celtic) + enc/iso8859_15.c ISO-8859-15 encoding. (Latin-9 or West European with Euro) + enc/iso8859_16.c ISO-8859-16 encoding. + (Latin-10 or South-Eastern European with Euro) + enc/utf8.c UTF-8 encoding. + enc/utf16_be.c UTF-16BE encoding. + enc/utf16_le.c UTF-16LE encoding. + enc/utf32_be.c UTF-32BE encoding. + enc/utf32_le.c UTF-32LE encoding. + enc/unicode.c Unicode information data. + + win32/Makefile Makefile for Win32 (VC++) + win32/config.h config.h for Win32 + + + +ToDo + + ? case fold flag: Katakana <-> Hiragana. + ? add ONIG_OPTION_NOTBOS/NOTEOS. (\A, \z, \Z) + ?? \X (== \PM\pM*) + ?? implement syntax behavior ONIG_SYN_CONTEXT_INDEP_ANCHORS. + ?? transmission stopper. (return ONIG_STOP from match_at()) + +and I'm thankful to Akinori MUSHA. + + +Mail Address: K.Kosako <sndgk393 AT ybb DOT ne DOT jp> |