granicus.if.org Git - onig/blob - README.md

   1 Oniguruma
   2 =========
   3
   4 https://github.com/kkos/oniguruma
   5
   6 Oniguruma is a regular expressions library.
   7 The characteristics of this library is that different character encoding
   8 for every regular expression object can be specified.
   9
  10 Supported character encodings:
  11
  12   ASCII, UTF-8, UTF-16BE, UTF-16LE, UTF-32BE, UTF-32LE,
  13   EUC-JP, EUC-TW, EUC-KR, EUC-CN,
  14   Shift_JIS, Big5, GB18030, KOI8-R, CP1251,
  15   ISO-8859-1, ISO-8859-2, ISO-8859-3, ISO-8859-4, ISO-8859-5,
  16   ISO-8859-6, ISO-8859-7, ISO-8859-8, ISO-8859-9, ISO-8859-10,
  17   ISO-8859-11, ISO-8859-13, ISO-8859-14, ISO-8859-15, ISO-8859-16
  18
  19 * GB18030: contributed by KUBO Takehiro
  20 * CP1251:  contributed by Byte
  21
  22
  23 License
  24 -------
  25
  26   BSD license.
  27
  28
  29 Install
  30 -------
  31
  32 ### Case 1: Unix and Cygwin platform
  33
  34    1. ./configure
  35    2. make
  36    3. make install
  37
  38    * uninstall
  39
  40      make uninstall
  41
  42    * test (ASCII/EUC-JP)
  43
  44      make atest
  45
  46    * configuration check
  47
  48      onig-config --cflags
  49      onig-config --libs
  50      onig-config --prefix
  51      onig-config --exec-prefix
  52
  53
  54
  55 ### Case 2: Win32 platform (VC++)
  56
  57    1. copy win32\Makefile Makefile
  58    2. copy win32\config.h config.h
  59    3. nmake
  60
  61       onig_s.lib:  static link library
  62       onig.dll:    dynamic link library
  63
  64    * test (ASCII/Shift_JIS)
  65
  66    4. copy win32\testc.c testc.c
  67    5. nmake ctest
  68
  69
  70
  71 Regular Expressions
  72 -------------------
  73
  74   See [doc/RE](doc/RE) or [doc/RE.ja](doc/RE.ja) for Japanese.
  75
  76
  77 Usage
  78 -----
  79
  80   Include oniguruma.h in your program. (Oniguruma API)
  81   See doc/API for Oniguruma API.
  82
  83   If you want to disable UChar type (== unsigned char) definition
  84   in oniguruma.h, define ONIG_ESCAPE_UCHAR_COLLISION and then
  85   include oniguruma.h.
  86
  87   If you want to disable regex_t type definition in oniguruma.h,
  88   define ONIG_ESCAPE_REGEX_T_COLLISION and then include oniguruma.h.
  89
  90   Example of the compiling/linking command line in Unix or Cygwin,
  91   (prefix == /usr/local case)
  92
  93     cc sample.c -L/usr/local/lib -lonig
  94
  95
  96   If you want to use static link library(onig_s.lib) in Win32,
  97   add option -DONIG_EXTERN=extern to C compiler.
  98
  99
 100
 101 Sample Programs
 102 ---------------
 103
 104 |sample/simple.c    |example of the minimum (Oniguruma API)   |
 105 |sample/names.c     |example of the named group callback.     |
 106 |sample/encode.c    |example of some encodings.               |
 107 |sample/listcap.c   |example of the capture history.          |
 108 |sample/posix.c     |POSIX API sample.                        |
 109 |sample/sql.c       |example of the variable meta characters. |
 110
 111
 112 Test Programs
 113
 114 |sample/syntax.c    |Perl, Java and ASIS syntax test.       |
 115 |sample/crnl.c      |--enable-crnl-as-line-terminator test  |
 116
 117
 118 Source Files
 119 ------------
 120
 121 |oniguruma.h        |Oniguruma API header file (public)                      |
 122 |onig-config.in     |configuration check program template                    |
 123 |regenc.h           |character encodings framework header file               |
 124 |regint.h           |internal definitions                                    |
 125 |regparse.h         |internal definitions for regparse.c and regcomp.c       |
 126 |regcomp.c          |compiling and optimization functions                    |
 127 |regenc.c           |character encodings framework                           |
 128 |regerror.c         |error message function                                  |
 129 |regext.c           |extended API functions (deluxe version API)             |
 130 |regexec.c          |search and match functions                              |
 131 |regparse.c         |parsing functions.                                      |
 132 |regsyntax.c        |pattern syntax functions and built-in syntax definitions|
 133 |regtrav.c          |capture history tree data traverse functions            |
 134 |regversion.c       |version info function                                   |
 135 |st.h               |hash table functions header file                        |
 136 |st.c               |hash table functions                                    |
 137 |oniggnu.h          |GNU regex API header file (public)                      |
 138 |reggnu.c           |GNU regex API functions                                 |
 139 |onigposix.h        |POSIX API header file (public)                          |
 140 |regposerr.c        |POSIX error message function                            |
 141 |regposix.c         |POSIX API functions                                     |
 142 |enc/mktable.c      |character type table generator                          |
 143 |enc/ascii.c        |ASCII encoding                                          |
 144 |enc/euc_jp.c       |EUC-JP encoding                                         |
 145 |enc/euc_tw.c       |EUC-TW encoding                                         |
 146 |enc/euc_kr.c       |EUC-KR, EUC-CN encoding                                 |
 147 |enc/sjis.c         |Shift_JIS encoding                                      |
 148 |enc/big5.c         |Big5      encoding                                      |
 149 |enc/gb18030.c      |GB18030   encoding                                      |
 150 |enc/koi8.c         |KOI8      encoding                                      |
 151 |enc/koi8_r.c       |KOI8-R    encoding                                      |
 152 |enc/cp1251.c       |CP1251    encoding                                      |
 153 |enc/iso8859_1.c    |ISO-8859-1 (Latin-1)                                    |
 154 |enc/iso8859_2.c    |ISO-8859-2 (Latin-2)                                    |
 155 |enc/iso8859_3.c    |ISO-8859-3 (Latin-3)                                    |
 156 |enc/iso8859_4.c    |ISO-8859-4 (Latin-4)                                    |
 157 |enc/iso8859_5.c    |ISO-8859-5 (Cyrillic)                                   |
 158 |enc/iso8859_6.c    |ISO-8859-6 (Arabic)                                     |
 159 |enc/iso8859_7.c    |ISO-8859-7 (Greek)                                      |
 160 |enc/iso8859_8.c    |ISO-8859-8 (Hebrew)                                     |
 161 |enc/iso8859_9.c    |ISO-8859-9 (Latin-5 or Turkish)                         |
 162 |enc/iso8859_10.c   |ISO-8859-10 (Latin-6 or Nordic)                         |
 163 |enc/iso8859_11.c   |ISO-8859-11 (Thai)                                      |
 164 |enc/iso8859_13.c   |ISO-8859-13 (Latin-7 or Baltic Rim)                     |
 165 |enc/iso8859_14.c   |ISO-8859-14 (Latin-8 or Celtic)                         |
 166 |enc/iso8859_15.c   |ISO-8859-15 (Latin-9 or West European with Euro)        |
 167 |enc/iso8859_16.c   |ISO-8859-16 (Latin-10)                                  |
 168 |enc/utf8.c         |UTF-8    encoding                                       |
 169 |enc/utf16_be.c     |UTF-16BE encoding                                       |
 170 |enc/utf16_le.c     |UTF-16LE encoding                                       |
 171 |enc/utf32_be.c     |UTF-32BE encoding                                       |
 172 |enc/utf32_le.c     |UTF-32LE encoding                                       |
 173 |enc/unicode.c      |Unicode information data                                |
 174 |win32/Makefile     |Makefile for Win32 (VC++)                               |
 175 |win32/config.h     |config.h for Win32                                      |