contrib/file-4/src/names.h

   1 /*
   2  * Copyright (c) Ian F. Darwin 1986-1995.
   3  * Software written by Ian F. Darwin and others;
   4  * maintained 1995-present by Christos Zoulas and others.
   5  *
   6  * Redistribution and use in source and binary forms, with or without
   7  * modification, are permitted provided that the following conditions
   8  * are met:
   9  * 1. Redistributions of source code must retain the above copyright
  10  *    notice immediately at the beginning of the file, without modification,
  11  *    this list of conditions, and the following disclaimer.
  12  * 2. Redistributions in binary form must reproduce the above copyright
  13  *    notice, this list of conditions and the following disclaimer in the
  14  *    documentation and/or other materials provided with the distribution.
  15  *
  16  * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
  17  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  18  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  19  * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE FOR
  20  * ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  21  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  22  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  23  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  24  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  25  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  26  * SUCH DAMAGE.
  27  */
  28 /*
  29  * Names.h - names and types used by ascmagic in file(1).
  30  * These tokens are here because they can appear anywhere in
  31  * the first HOWMANY bytes, while tokens in MAGIC must
  32  * appear at fixed offsets into the file. Don't make HOWMANY
  33  * too high unless you have a very fast CPU.
  34  *
  35  * $File: names.h,v 1.29 2007/12/27 20:30:35 christos Exp $
  36  */
  37
  38 /*
  39         modified by Chris Lowth - 9 April 2000
  40         to add mime type strings to the types table.
  41 */
  42
  43 /* these types are used to index the table 'types': keep em in sync! */
  44 #define L_C     0               /* first and foremost on UNIX */
  45 #define L_CC    1               /* Bjarne's postincrement */
  46 #define L_MAKE  2               /* Makefiles */
  47 #define L_PLI   3               /* PL/1 */
  48 #define L_MACH  4               /* some kinda assembler */
  49 #define L_ENG   5               /* English */
  50 #define L_PAS   6               /* Pascal */
  51 #define L_MAIL  7               /* Electronic mail */
  52 #define L_NEWS  8               /* Usenet Netnews */
  53 #define L_JAVA  9               /* Java code */
  54 #define L_HTML  10              /* HTML */
  55 #define L_BCPL  11              /* BCPL */
  56 #define L_M4    12              /* M4 */
  57 #define L_PO    13              /* PO */
  58
  59 static const struct {
  60         const char *human;
  61         const char *mime;
  62 } types[] = {
  63         { "C program",                                  "text/x-c", },
  64         { "C++ program",                                "text/x-c++" },
  65         { "make commands",                              "text/x-makefile" },
  66         { "PL/1 program",                               "text/x-pl1" },
  67         { "assembler program",                          "text/x-asm" },
  68         { "English",                                    "text/plain" },
  69         { "Pascal program",                             "text/x-pascal" },
  70         { "mail",                                       "text/x-mail" },
  71         { "news",                                       "text/x-news" },
  72         { "Java program",                               "text/x-java" },
  73         { "HTML document",                              "text/html", },
  74         { "BCPL program",                               "text/x-bcpl" },
  75         { "M4 macro language pre-processor",            "text/x-m4" },
  76         { "PO (gettext message catalogue)",             "text/x-po" },
  77         { "cannot happen error on names.h/types",       "error/x-error" },
  78         { 0, 0}
  79 };
  80
  81 /*
  82  * XXX - how should we distinguish Java from C++?
  83  * The trick used in a Debian snapshot, of having "extends" or "implements"
  84  * as tags for Java, doesn't work very well, given that those keywords
  85  * are often preceded by "class", which flags it as C++.
  86  *
  87  * Perhaps we need to be able to say
  88  *
  89  *      If "class" then
  90  *
  91  *              if "extends" or "implements" then
  92  *                      Java
  93  *              else
  94  *                      C++
  95  *      endif
  96  *
  97  * Or should we use other keywords, such as "package" or "import"?
  98  * Unfortunately, Ada95 uses "package", and Modula-3 uses "import",
  99  * although I infer from the language spec at
 100  *
 101  *      http://www.research.digital.com/SRC/m3defn/html/m3.html
 102  *
 103  * that Modula-3 uses "IMPORT" rather than "import", i.e. it must be
 104  * in all caps.
 105  *
 106  * So, for now, we go with "import".  We must put it before the C++
 107  * stuff, so that we don't misidentify Java as C++.  Not using "package"
 108  * means we won't identify stuff that defines a package but imports
 109  * nothing; hopefully, very little Java code imports nothing (one of the
 110  * reasons for doing OO programming is to import as much as possible
 111  * and write only what you need to, right?).
 112  *
 113  * Unfortunately, "import" may cause us to misidentify English text
 114  * as Java, as it comes after "the" and "The".  Perhaps we need a fancier
 115  * heuristic to identify Java?
 116  */
 117 static struct names {
 118         const char *name;
 119         short type;
 120 } names[] = {
 121         /* These must be sorted by eye for optimal hit rate */
 122         /* Add to this list only after substantial meditation */
 123         {"msgid",       L_PO},
 124         {"dnl",         L_M4},
 125         {"import",      L_JAVA},
 126         {"\"libhdr\"",  L_BCPL},
 127         {"\"LIBHDR\"",  L_BCPL},
 128         {"//",          L_CC},
 129         {"template",    L_CC},
 130         {"virtual",     L_CC},
 131         {"class",       L_CC},
 132         {"public:",     L_CC},
 133         {"private:",    L_CC},
 134         {"/*",          L_C},   /* must precede "The", "the", etc. */
 135         {"#include",    L_C},
 136         {"char",        L_C},
 137         {"The",         L_ENG},
 138         {"the",         L_ENG},
 139         {"double",      L_C},
 140         {"extern",      L_C},
 141         {"float",       L_C},
 142         {"struct",      L_C},
 143         {"union",       L_C},
 144         {"CFLAGS",      L_MAKE},
 145         {"LDFLAGS",     L_MAKE},
 146         {"all:",        L_MAKE},
 147         {".PRECIOUS",   L_MAKE},
 148 /* Too many files of text have these words in them.  Find another way
 149  * to recognize Fortrash.
 150  */
 151 #ifdef  NOTDEF
 152         {"subroutine",  L_FORT},
 153         {"function",    L_FORT},
 154         {"block",       L_FORT},
 155         {"common",      L_FORT},
 156         {"dimension",   L_FORT},
 157         {"integer",     L_FORT},
 158         {"data",        L_FORT},
 159 #endif  /*NOTDEF*/
 160         {".ascii",      L_MACH},
 161         {".asciiz",     L_MACH},
 162         {".byte",       L_MACH},
 163         {".even",       L_MACH},
 164         {".globl",      L_MACH},
 165         {".text",       L_MACH},
 166         {"clr",         L_MACH},
 167         {"(input,",     L_PAS},
 168         {"program",     L_PAS},
 169         {"record",      L_PAS},
 170         {"dcl",         L_PLI},
 171         {"Received:",   L_MAIL},
 172         {">From",       L_MAIL},
 173         {"Return-Path:",L_MAIL},
 174         {"Cc:",         L_MAIL},
 175         {"Newsgroups:", L_NEWS},
 176         {"Path:",       L_NEWS},
 177         {"Organization:",L_NEWS},
 178         {"href=",       L_HTML},
 179         {"HREF=",       L_HTML},
 180         {"<body",       L_HTML},
 181         {"<BODY",       L_HTML},
 182         {"<html",       L_HTML},
 183         {"<HTML",       L_HTML},
 184         {NULL,          0}
 185 };
 186 #define NNAMES ((sizeof(names)/sizeof(struct names)) - 1)