names.h revision 133359
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 * 3. All advertising materials mentioning features or use of this software 16 * must display the following acknowledgement: 17 * This product includes software developed by Ian F. Darwin and others. 18 * 4. The name of the author may not be used to endorse or promote products 19 * derived from this software without specific prior written permission. 20 * 21 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND 22 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 23 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 24 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE FOR 25 * ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 26 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 27 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 28 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 29 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 30 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 31 * SUCH DAMAGE. 32 */ 33/* 34 * Names.h - names and types used by ascmagic in file(1). 35 * These tokens are here because they can appear anywhere in 36 * the first HOWMANY bytes, while tokens in MAGIC must 37 * appear at fixed offsets into the file. Don't make HOWMANY 38 * too high unless you have a very fast CPU. 39 * 40 * $Id: names.h,v 1.24 2004/03/22 19:09:12 christos Exp $ 41 */ 42 43/* 44 modified by Chris Lowth - 9 April 2000 45 to add mime type strings to the types table. 46*/ 47 48/* these types are used to index the table 'types': keep em in sync! */ 49#define L_C 0 /* first and foremost on UNIX */ 50#define L_CC 1 /* Bjarne's postincrement */ 51#define L_FORT 2 /* the oldest one */ 52#define L_MAKE 3 /* Makefiles */ 53#define L_PLI 4 /* PL/1 */ 54#define L_MACH 5 /* some kinda assembler */ 55#define L_ENG 6 /* English */ 56#define L_PAS 7 /* Pascal */ 57#define L_MAIL 8 /* Electronic mail */ 58#define L_NEWS 9 /* Usenet Netnews */ 59#define L_JAVA 10 /* Java code */ 60#define L_HTML 11 /* HTML */ 61#define L_BCPL 12 /* BCPL */ 62#define L_M4 13 /* M4 */ 63#define L_PO 14 /* PO */ 64 65static const struct { 66 const char *human; 67 const char *mime; 68} types[] = { 69 { "C program", "text/x-c", }, 70 { "C++ program", "text/x-c++" }, 71 { "FORTRAN program", "text/x-fortran" }, 72 { "make commands", "text/x-makefile" }, 73 { "PL/1 program", "text/x-pl1" }, 74 { "assembler program", "text/x-asm" }, 75 { "English", "text/plain" }, 76 { "Pascal program", "text/x-pascal" }, 77 { "mail", "text/x-mail" }, 78 { "news", "text/x-news" }, 79 { "Java program", "text/x-java" }, 80 { "HTML document", "text/html", }, 81 { "BCPL program", "text/x-bcpl" }, 82 { "M4 macro language pre-processor", "text/x-m4" }, 83 { "PO (gettext message catalogue)", "text/x-po" }, 84 { "cannot happen error on names.h/types", "error/x-error" }, 85 { 0, 0} 86}; 87 88/* 89 * XXX - how should we distinguish Java from C++? 90 * The trick used in a Debian snapshot, of having "extends" or "implements" 91 * as tags for Java, doesn't work very well, given that those keywords 92 * are often preceded by "class", which flags it as C++. 93 * 94 * Perhaps we need to be able to say 95 * 96 * If "class" then 97 * 98 * if "extends" or "implements" then 99 * Java 100 * else 101 * C++ 102 * endif 103 * 104 * Or should we use other keywords, such as "package" or "import"? 105 * Unfortunately, Ada95 uses "package", and Modula-3 uses "import", 106 * although I infer from the language spec at 107 * 108 * http://www.research.digital.com/SRC/m3defn/html/m3.html 109 * 110 * that Modula-3 uses "IMPORT" rather than "import", i.e. it must be 111 * in all caps. 112 * 113 * So, for now, we go with "import". We must put it before the C++ 114 * stuff, so that we don't misidentify Java as C++. Not using "package" 115 * means we won't identify stuff that defines a package but imports 116 * nothing; hopefully, very little Java code imports nothing (one of the 117 * reasons for doing OO programming is to import as much as possible 118 * and write only what you need to, right?). 119 * 120 * Unfortunately, "import" may cause us to misidentify English text 121 * as Java, as it comes after "the" and "The". Perhaps we need a fancier 122 * heuristic to identify Java? 123 */ 124static struct names { 125 const char *name; 126 short type; 127} names[] = { 128 /* These must be sorted by eye for optimal hit rate */ 129 /* Add to this list only after substantial meditation */ 130 {"msgid", L_PO}, 131 {"dnl", L_M4}, 132 {"import", L_JAVA}, 133 {"\"libhdr\"", L_BCPL}, 134 {"\"LIBHDR\"", L_BCPL}, 135 {"//", L_CC}, 136 {"template", L_CC}, 137 {"virtual", L_CC}, 138 {"class", L_CC}, 139 {"public:", L_CC}, 140 {"private:", L_CC}, 141 {"/*", L_C}, /* must precede "The", "the", etc. */ 142 {"#include", L_C}, 143 {"char", L_C}, 144 {"The", L_ENG}, 145 {"the", L_ENG}, 146 {"double", L_C}, 147 {"extern", L_C}, 148 {"float", L_C}, 149 {"struct", L_C}, 150 {"union", L_C}, 151 {"CFLAGS", L_MAKE}, 152 {"LDFLAGS", L_MAKE}, 153 {"all:", L_MAKE}, 154 {".PRECIOUS", L_MAKE}, 155/* Too many files of text have these words in them. Find another way 156 * to recognize Fortrash. 157 */ 158#ifdef NOTDEF 159 {"subroutine", L_FORT}, 160 {"function", L_FORT}, 161 {"block", L_FORT}, 162 {"common", L_FORT}, 163 {"dimension", L_FORT}, 164 {"integer", L_FORT}, 165 {"data", L_FORT}, 166#endif /*NOTDEF*/ 167 {".ascii", L_MACH}, 168 {".asciiz", L_MACH}, 169 {".byte", L_MACH}, 170 {".even", L_MACH}, 171 {".globl", L_MACH}, 172 {".text", L_MACH}, 173 {"clr", L_MACH}, 174 {"(input,", L_PAS}, 175 {"dcl", L_PLI}, 176 {"Received:", L_MAIL}, 177 {">From", L_MAIL}, 178 {"Return-Path:",L_MAIL}, 179 {"Cc:", L_MAIL}, 180 {"Newsgroups:", L_NEWS}, 181 {"Path:", L_NEWS}, 182 {"Organization:",L_NEWS}, 183 {"href=", L_HTML}, 184 {"HREF=", L_HTML}, 185 {"<body", L_HTML}, 186 {"<BODY", L_HTML}, 187 {"<html", L_HTML}, 188 {"<HTML", L_HTML}, 189 {NULL, 0} 190}; 191#define NNAMES ((sizeof(names)/sizeof(struct names)) - 1) 192