external/bsd/file/dist/src/names.h

   1 /*      $NetBSD: names.h,v 1.1.1.2 2011/05/12 20:46:54 christos Exp $   */
   2
   3 /*
   4  * Copyright (c) Ian F. Darwin 1986-1995.
   5  * Software written by Ian F. Darwin and others;
   6  * maintained 1995-present by Christos Zoulas and others.
   7  *
   8  * Redistribution and use in source and binary forms, with or without
   9  * modification, are permitted provided that the following conditions
  10  * are met:
  11  * 1. Redistributions of source code must retain the above copyright
  12  *    notice immediately at the beginning of the file, without modification,
  13  *    this list of conditions, and the following disclaimer.
  14  * 2. Redistributions in binary form must reproduce the above copyright
  15  *    notice, this list of conditions and the following disclaimer in the
  16  *    documentation and/or other materials provided with the distribution.
  17  *
  18  * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
  19  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  20  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  21  * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE FOR
  22  * ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  23  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  24  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  25  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  26  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  27  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  28  * SUCH DAMAGE.
  29  */
  30 /*
  31  * Names.h - names and types used by ascmagic in file(1).
  32  * These tokens are here because they can appear anywhere in
  33  * the first HOWMANY bytes, while tokens in MAGIC must
  34  * appear at fixed offsets into the file. Don't make HOWMANY
  35  * too high unless you have a very fast CPU.
  36  *
  37  * $File: names.h,v 1.33 2010/10/08 21:58:44 christos Exp $
  38  */
  39
  40 /*
  41         modified by Chris Lowth - 9 April 2000
  42         to add mime type strings to the types table.
  43 */
  44
  45 /* these types are used to index the table 'types': keep em in sync! */
  46 #define L_C     0               /* first and foremost on UNIX */
  47 #define L_CC    1               /* Bjarne's postincrement */
  48 #define L_MAKE  2               /* Makefiles */
  49 #define L_PLI   3               /* PL/1 */
  50 #define L_MACH  4               /* some kinda assembler */
  51 #define L_ENG   5               /* English */
  52 #define L_PAS   6               /* Pascal */
  53 #define L_MAIL  7               /* Electronic mail */
  54 #define L_NEWS  8               /* Usenet Netnews */
  55 #define L_JAVA  9               /* Java code */
  56 #define L_HTML  10              /* HTML */
  57 #define L_BCPL  11              /* BCPL */
  58 #define L_M4    12              /* M4 */
  59 #define L_PO    13              /* PO */
  60
  61 static const struct {
  62         char human[48];
  63         char mime[16];
  64 } types[] = {
  65         { "C program",                                  "text/x-c", },
  66         { "C++ program",                                "text/x-c++" },
  67         { "make commands",                              "text/x-makefile" },
  68         { "PL/1 program",                               "text/x-pl1" },
  69         { "assembler program",                          "text/x-asm" },
  70         { "English",                                    "text/plain" },
  71         { "Pascal program",                             "text/x-pascal" },
  72         { "mail",                                       "text/x-mail" },
  73         { "news",                                       "text/x-news" },
  74         { "Java program",                               "text/x-java" },
  75         { "HTML document",                              "text/html", },
  76         { "BCPL program",                               "text/x-bcpl" },
  77         { "M4 macro language pre-processor",            "text/x-m4" },
  78         { "PO (gettext message catalogue)",             "text/x-po" },
  79         { "cannot happen error on names.h/types",       "error/x-error" }
  80 };
  81
  82 /*
  83  * XXX - how should we distinguish Java from C++?
  84  * The trick used in a Debian snapshot, of having "extends" or "implements"
  85  * as tags for Java, doesn't work very well, given that those keywords
  86  * are often preceded by "class", which flags it as C++.
  87  *
  88  * Perhaps we need to be able to say
  89  *
  90  *      If "class" then
  91  *
  92  *              if "extends" or "implements" then
  93  *                      Java
  94  *              else
  95  *                      C++
  96  *      endif
  97  *
  98  * Or should we use other keywords, such as "package" or "import"?
  99  * Unfortunately, Ada95 uses "package", and Modula-3 uses "import",
 100  * although I infer from the language spec at
 101  *
 102  *      http://www.research.digital.com/SRC/m3defn/html/m3.html
 103  *
 104  * that Modula-3 uses "IMPORT" rather than "import", i.e. it must be
 105  * in all caps.
 106  *
 107  * So, for now, we go with "import".  We must put it before the C++
 108  * stuff, so that we don't misidentify Java as C++.  Not using "package"
 109  * means we won't identify stuff that defines a package but imports
 110  * nothing; hopefully, very little Java code imports nothing (one of the
 111  * reasons for doing OO programming is to import as much as possible
 112  * and write only what you need to, right?).
 113  *
 114  * Unfortunately, "import" may cause us to misidentify English text
 115  * as Java, as it comes after "the" and "The".  Perhaps we need a fancier
 116  * heuristic to identify Java?
 117  */
 118 static const struct names {
 119         char name[14];
 120         unsigned char type;
 121         unsigned char score;
 122
 123 } names[] = {
 124         /* These must be sorted by eye for optimal hit rate */
 125         /* Add to this list only after substantial meditation */
 126         {"msgid",       L_PO, 1 },
 127         {"dnl",         L_M4, 2 },
 128         {"import",      L_JAVA, 2 },
 129         {"\"libhdr\"",  L_BCPL, 2 },
 130         {"\"LIBHDR\"",  L_BCPL, 2 },
 131         {"//",          L_CC, 2 },
 132         {"template",    L_CC, 1 },
 133         {"virtual",     L_CC, 1 },
 134         {"class",       L_CC, 2 },
 135         {"public:",     L_CC, 2 },
 136         {"private:",    L_CC, 2 },
 137         {"/*",          L_C, 2 },       /* must precede "The", "the", etc. */
 138         {"#include",    L_C, 2 },
 139         {"char",        L_C, 2 },
 140         {"The",         L_ENG, 2 },
 141         {"the",         L_ENG, 2 },
 142         {"double",      L_C, 1 },
 143         {"extern",      L_C, 2 },
 144         {"float",       L_C, 1 },
 145         {"struct",      L_C, 1 },
 146         {"union",       L_C, 1 },
 147         {"main(",       L_C, 2 },
 148         {"CFLAGS",      L_MAKE, 2 },
 149         {"LDFLAGS",     L_MAKE, 2 },
 150         {"all:",        L_MAKE, 2 },
 151         {".PRECIOUS",   L_MAKE, 2 },
 152         {".ascii",      L_MACH, 2 },
 153         {".asciiz",     L_MACH, 2 },
 154         {".byte",       L_MACH, 2 },
 155         {".even",       L_MACH, 2 },
 156         {".globl",      L_MACH, 2 },
 157         {".text",       L_MACH, 2 },
 158         {"clr",         L_MACH, 2 },
 159         {"(input,",     L_PAS, 2 },
 160         {"program",     L_PAS, 1 },
 161         {"record",      L_PAS, 1 },
 162         {"dcl",         L_PLI, 2 },
 163         {"Received:",   L_MAIL, 2 },
 164         {">From",       L_MAIL, 2 },
 165         {"Return-Path:",L_MAIL, 2 },
 166         {"Cc:",         L_MAIL, 2 },
 167         {"Newsgroups:", L_NEWS, 2 },
 168         {"Path:",       L_NEWS, 2 },
 169         {"Organization:",L_NEWS, 2 },
 170         {"href=",       L_HTML, 2 },
 171         {"HREF=",       L_HTML, 2 },
 172         {"<body",       L_HTML, 2 },
 173         {"<BODY",       L_HTML, 2 },
 174         {"<html",       L_HTML, 2 },
 175         {"<HTML",       L_HTML, 2 },
 176         {"<!--",        L_HTML, 2 },
 177 };
 178 #define NNAMES (sizeof(names)/sizeof(struct names))