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 * $Id: names.h,v 1.25 2004/09/11 19:15:57 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_FORT 2 /* the oldest one */ 47 #define L_MAKE 3 /* Makefiles */ 48 #define L_PLI 4 /* PL/1 */ 49 #define L_MACH 5 /* some kinda assembler */ 50 #define L_ENG 6 /* English */ 51 #define L_PAS 7 /* Pascal */ 52 #define L_MAIL 8 /* Electronic mail */ 53 #define L_NEWS 9 /* Usenet Netnews */ 54 #define L_JAVA 10 /* Java code */ 55 #define L_HTML 11 /* HTML */ 56 #define L_BCPL 12 /* BCPL */ 57 #define L_M4 13 /* M4 */ 58 #define L_PO 14 /* PO */ 59 #define L_JAM 15 /* Jamfiles */ 60 61 static const struct { 62 const char *human; 63 const char *generic_mime; 64 const char *specific_mime; 65 } types[] = { 66 { "C program", "text/x-source-code", "text/x-c", }, 67 { "C++ program", "text/x-source-code", "text/x-c++" }, 68 { "FORTRAN program", "text/x-source-code", "text/x-fortran" }, 69 { "make commands", "text/x-source-code", "text/x-makefile" }, 70 { "PL/1 program", "text/x-source-code", "text/x-pl1" }, 71 { "assembler program", "text/x-source-code", "text/x-asm" }, 72 { "English", "text/plain", NULL }, 73 { "Pascal program", "text/x-source-code", "text/x-pascal" }, 74 { "mail", "text/plain", "text/x-mail" }, 75 { "news", "text/plain", "text/x-news" }, 76 { "Java program", "text/x-source-code", "text/x-java" }, 77 { "HTML document", "text/x-source-code", "text/html", }, 78 { "BCPL program", "text/x-source-code", "text/x-bcpl" }, 79 { "M4 macro language pre-processor", "text/x-source-code", "text/x-m4" }, 80 { "PO (gettext message catalogue)", "text/plain", "text/x-po" }, 81 { "Jamfile", "text/x-source-code", "text/x-jamfile" }, 82 { "cannot happen error on names.h/types", "text/plain", "error/x-error" }, 83 { NULL, NULL, NULL } 84 }; 85 86 /* 87 * XXX - how should we distinguish Java from C++? 88 * The trick used in a Debian snapshot, of having "extends" or "implements" 89 * as tags for Java, doesn't work very well, given that those keywords 90 * are often preceded by "class", which flags it as C++. 91 * 92 * Perhaps we need to be able to say 93 * 94 * If "class" then 95 * 96 * if "extends" or "implements" then 97 * Java 98 * else 99 * C++ 100 * endif 101 * 102 * Or should we use other keywords, such as "package" or "import"? 103 * Unfortunately, Ada95 uses "package", and Modula-3 uses "import", 104 * although I infer from the language spec at 105 * 106 * http://www.research.digital.com/SRC/m3defn/html/m3.html 107 * 108 * that Modula-3 uses "IMPORT" rather than "import", i.e. it must be 109 * in all caps. 110 * 111 * So, for now, we go with "import". We must put it before the C++ 112 * stuff, so that we don't misidentify Java as C++. Not using "package" 113 * means we won't identify stuff that defines a package but imports 114 * nothing; hopefully, very little Java code imports nothing (one of the 115 * reasons for doing OO programming is to import as much as possible 116 * and write only what you need to, right?). 117 * 118 * Unfortunately, "import" may cause us to misidentify English text 119 * as Java, as it comes after "the" and "The". Perhaps we need a fancier 120 * heuristic to identify Java? 121 */ 122 static struct names { 123 const char *name; 124 short type; 125 } names[] = { 126 /* These must be sorted by eye for optimal hit rate */ 127 /* Add to this list only after substantial meditation */ 128 {"msgid", L_PO}, 129 {"dnl", L_M4}, 130 {"import", L_JAVA}, 131 {"\"libhdr\"", L_BCPL}, 132 {"\"LIBHDR\"", L_BCPL}, 133 {"//", L_CC}, 134 {"template", L_CC}, 135 {"virtual", L_CC}, 136 {"class", L_CC}, 137 {"public:", L_CC}, 138 {"private:", L_CC}, 139 {"/*", L_C}, /* must precede "The", "the", etc. */ 140 {"#include", L_C}, 141 {"char", L_C}, 142 {"The", L_ENG}, 143 {"the", L_ENG}, 144 {"double", L_C}, 145 {"extern", L_C}, 146 {"float", L_C}, 147 {"struct", L_C}, 148 {"union", L_C}, 149 {"SubDir", L_JAM}, 150 {"rule", L_JAM}, 151 {"actions", L_JAM}, 152 {"CFLAGS", L_MAKE}, 153 {"LDFLAGS", L_MAKE}, 154 {"all:", L_MAKE}, 155 {".PRECIOUS", L_MAKE}, 156 /* Too many files of text have these words in them. Find another way 157 * to recognize Fortrash. 158 */ 159 #ifdef NOTDEF 160 {"subroutine", L_FORT}, 161 {"function", L_FORT}, 162 {"block", L_FORT}, 163 {"common", L_FORT}, 164 {"dimension", L_FORT}, 165 {"integer", L_FORT}, 166 {"data", L_FORT}, 167 #endif /*NOTDEF*/ 168 {".ascii", L_MACH}, 169 {".asciiz", L_MACH}, 170 {".byte", L_MACH}, 171 {".even", L_MACH}, 172 {".globl", L_MACH}, 173 {".text", L_MACH}, 174 {"clr", L_MACH}, 175 {"(input,", L_PAS}, 176 {"dcl", L_PLI}, 177 {"Received:", L_MAIL}, 178 {">From", L_MAIL}, 179 {"Return-Path:",L_MAIL}, 180 {"Cc:", L_MAIL}, 181 {"Newsgroups:", L_NEWS}, 182 {"Path:", L_NEWS}, 183 {"Organization:",L_NEWS}, 184 {"href=", L_HTML}, 185 {"HREF=", L_HTML}, 186 {"<body", L_HTML}, 187 {"<BODY", L_HTML}, 188 {"<html", L_HTML}, 189 {"<HTML", L_HTML}, 190 {NULL, 0} 191 }; 192 #define NNAMES ((sizeof(names)/sizeof(struct names)) - 1) 193