[3745] | 1 | /**************************************************************************
|
---|
| 2 | *
|
---|
| 3 | * text.h -- Header file for compression related stuff
|
---|
| 4 | * Copyright (C) 1994 Neil Sharman
|
---|
| 5 | *
|
---|
| 6 | * This program is free software; you can redistribute it and/or modify
|
---|
| 7 | * it under the terms of the GNU General Public License as published by
|
---|
| 8 | * the Free Software Foundation; either version 2 of the License, or
|
---|
| 9 | * (at your option) any later version.
|
---|
| 10 | *
|
---|
| 11 | * This program is distributed in the hope that it will be useful,
|
---|
| 12 | * but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
| 13 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
| 14 | * GNU General Public License for more details.
|
---|
| 15 | *
|
---|
| 16 | * You should have received a copy of the GNU General Public License
|
---|
| 17 | * along with this program; if not, write to the Free Software
|
---|
| 18 | * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
| 19 | *
|
---|
| 20 | * $Id: text.h 16583 2008-07-29 10:20:36Z davidb $
|
---|
| 21 | *
|
---|
| 22 | **************************************************************************/
|
---|
| 23 |
|
---|
| 24 |
|
---|
| 25 |
|
---|
| 26 | #ifndef H_TEXT
|
---|
| 27 | #define H_TEXT
|
---|
| 28 |
|
---|
| 29 | #include "huffman.h"
|
---|
| 30 |
|
---|
| 31 |
|
---|
| 32 |
|
---|
| 33 |
|
---|
| 34 |
|
---|
| 35 | /*****************************************************************************
|
---|
| 36 | *
|
---|
| 37 | * There are several different methods of compressing the text of the
|
---|
| 38 | * database. The following defines list the different methods of text
|
---|
| 39 | * compression
|
---|
| 40 | *
|
---|
| 41 | */
|
---|
| 42 |
|
---|
| 43 |
|
---|
| 44 | /* The dictionary contains all the fragments that occur in the collection
|
---|
| 45 | i.e. escapes are not possible */
|
---|
| 46 | #define MG_COMPLETE_DICTIONARY 0
|
---|
| 47 |
|
---|
| 48 |
|
---|
| 49 | /* Certain words have been deleted from the dictionary. The words deleted
|
---|
| 50 | have been used to create the frequency huffman codes of the characters.
|
---|
| 51 | This dictionary has an escape code and may be used to compress novel
|
---|
| 52 | words. This dictionary may fail if there is a novel character. */
|
---|
| 53 | #define MG_PARTIAL_DICTIONARY 1
|
---|
| 54 |
|
---|
| 55 |
|
---|
| 56 | /* This dictionary has an escape so that novel words and non-words can be
|
---|
| 57 | coded. The method for coding the novel words and non-words is determined
|
---|
| 58 | by a dictionary parameter. */
|
---|
| 59 | #define MG_SEED_DICTIONARY 2
|
---|
| 60 |
|
---|
| 61 |
|
---|
| 62 |
|
---|
| 63 |
|
---|
| 64 |
|
---|
| 65 |
|
---|
| 66 |
|
---|
| 67 |
|
---|
| 68 |
|
---|
| 69 | /*****************************************************************************
|
---|
| 70 | *
|
---|
| 71 | * With a seed dictionary there are several methods for coding the novel
|
---|
| 72 | * words and non-words the following defined values specify the different
|
---|
| 73 | * methods of coding.
|
---|
| 74 | *
|
---|
| 75 | */
|
---|
| 76 |
|
---|
| 77 |
|
---|
| 78 | /* Code novel words and non-words character by character using huffman codes.
|
---|
| 79 | The huffman codes for the word and non-word lengths and characters are
|
---|
| 80 | generated from the distribution of lengths and characters in the
|
---|
| 81 | dictionary. */
|
---|
| 82 | #define MG_NOVEL_HUFFMAN_CHARS 0
|
---|
| 83 |
|
---|
| 84 |
|
---|
| 85 | /* This method codes novel words using binary codes. The novel words are stored
|
---|
| 86 | in a auxillary dictionary which is built by pass two. */
|
---|
| 87 | #define MG_NOVEL_BINARY 1
|
---|
| 88 |
|
---|
| 89 |
|
---|
| 90 | /* This method codes novel words using delta codes. The novel words are stored
|
---|
| 91 | in a auxillary dictionary which is built by pass two. */
|
---|
| 92 | #define MG_NOVEL_DELTA 2
|
---|
| 93 |
|
---|
| 94 |
|
---|
| 95 | /* This method codes novel words using hybrid version of delta. The novel
|
---|
| 96 | words are stored in a auxillary dictionary which is built by pass two. */
|
---|
| 97 | #define MG_NOVEL_HYBRID 3
|
---|
| 98 |
|
---|
| 99 |
|
---|
| 100 | /* This method codes novel words using hybrid version of delta and a MTF
|
---|
| 101 | operation. The novel words are stored in a auxillary dictionary which
|
---|
| 102 | is built by pass two. */
|
---|
| 103 | #define MG_NOVEL_HYBRID_MTF 4
|
---|
| 104 |
|
---|
| 105 |
|
---|
| 106 |
|
---|
| 107 |
|
---|
| 108 |
|
---|
| 109 |
|
---|
| 110 | /* This specified an amount of extra space allocated in the
|
---|
| 111 | compression_dict_header for adding new parameters. As new
|
---|
| 112 | parameters are added this should be decreased. */
|
---|
| 113 | #define TEXT_PARAMS 15
|
---|
| 114 |
|
---|
| 115 |
|
---|
| 116 |
|
---|
| 117 | typedef struct compression_dict_header
|
---|
| 118 | {
|
---|
| 119 | u_long dict_type;
|
---|
| 120 | u_long novel_method;
|
---|
| 121 | u_long params[TEXT_PARAMS];
|
---|
| 122 | u_long num_words[2];
|
---|
| 123 | u_long num_word_chars[2];
|
---|
| 124 | u_long lookback;
|
---|
| 125 | }
|
---|
| 126 | compression_dict_header;
|
---|
| 127 |
|
---|
| 128 |
|
---|
| 129 | typedef struct comp_frags_header
|
---|
| 130 | {
|
---|
| 131 | huff_data hd;
|
---|
| 132 | u_long uncompressed_size;
|
---|
| 133 | u_long huff_words_size[MAX_HUFFCODE_LEN + 1];
|
---|
| 134 | }
|
---|
| 135 | comp_frags_header;
|
---|
| 136 |
|
---|
| 137 |
|
---|
| 138 |
|
---|
| 139 | typedef struct compressed_text_header
|
---|
| 140 | {
|
---|
| 141 | u_long num_of_docs;
|
---|
| 142 | u_long num_of_words; /* number of words in collection */
|
---|
| 143 | double num_of_bytes; /* [RJM 07/97: 4G limit] */
|
---|
| 144 | double ratio;
|
---|
| 145 | u_long length_of_longest_doc; /* (characters) */
|
---|
| 146 | u_long dummy; /* added to make the structure the same on different architectures */
|
---|
| 147 | }
|
---|
| 148 | compressed_text_header;
|
---|
| 149 |
|
---|
| 150 |
|
---|
| 151 | typedef struct compression_stats_header
|
---|
| 152 | {
|
---|
| 153 | u_long num_docs;
|
---|
| 154 | u_long dummy; /* added to make the structure the same on different architectures */
|
---|
| 155 | double num_bytes; /* [RJM 07/97: 4G limit] */
|
---|
| 156 | }
|
---|
| 157 | compression_stats_header;
|
---|
| 158 |
|
---|
| 159 |
|
---|
| 160 | typedef struct frags_stats_header
|
---|
| 161 | {
|
---|
| 162 | u_long num_frags;
|
---|
| 163 | u_long mem_for_frags;
|
---|
| 164 | }
|
---|
| 165 | frags_stats_header;
|
---|
| 166 |
|
---|
| 167 |
|
---|
| 168 | typedef struct aux_frags_header
|
---|
| 169 | {
|
---|
| 170 | u_long num_frags;
|
---|
| 171 | u_long mem_for_frags;
|
---|
| 172 | }
|
---|
| 173 | aux_frags_header;
|
---|
| 174 |
|
---|
| 175 |
|
---|
| 176 | #endif
|
---|