| 1 | /**************************************************************************
|
|---|
| 2 | *
|
|---|
| 3 | * build.h -- Global information for the passes of mg_passes
|
|---|
| 4 | * Copyright (C) 1994 Neil Sharman, Alistair Moffat and Lachlan Andrew
|
|---|
| 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: build.h 439 1999-08-10 21:23:37Z sjboddie $
|
|---|
| 21 | *
|
|---|
| 22 | **************************************************************************/
|
|---|
| 23 |
|
|---|
| 24 |
|
|---|
| 25 | #ifndef H_BUILD
|
|---|
| 26 | #define H_BUILD
|
|---|
| 27 |
|
|---|
| 28 |
|
|---|
| 29 | #define TERMPARAGRAPH '\003'
|
|---|
| 30 |
|
|---|
| 31 |
|
|---|
| 32 | int init_special (char *file_name);
|
|---|
| 33 | int init_text_1 (char *file_name);
|
|---|
| 34 | int init_text_2 (char *file_name);
|
|---|
| 35 | int init_invf_1 (char *file_name);
|
|---|
| 36 | int init_invf_2 (char *file_name);
|
|---|
| 37 | int init_ivf_1 (char *file_name);
|
|---|
| 38 | int init_ivf_2 (char *file_name);
|
|---|
| 39 | /*
|
|---|
| 40 | * file_name IN The name of the dictionary file
|
|---|
| 41 | *
|
|---|
| 42 | * returns COMPALLOK for all ok,
|
|---|
| 43 | * COMPERROR for any error. e.g. cannot read file
|
|---|
| 44 | */
|
|---|
| 45 |
|
|---|
| 46 |
|
|---|
| 47 |
|
|---|
| 48 |
|
|---|
| 49 |
|
|---|
| 50 | int process_special (u_char * s_in, int l_in);
|
|---|
| 51 | int process_text_1 (u_char * s_in, int l_in);
|
|---|
| 52 | int process_text_2 (u_char * s_in, int l_in);
|
|---|
| 53 | int process_invf_1 (u_char * s_in, int l_in);
|
|---|
| 54 | int process_invf_2 (u_char * s_in, int l_in);
|
|---|
| 55 | int process_ivf_1 (u_char * s_in, int l_in);
|
|---|
| 56 | int process_ivf_2 (u_char * s_in, int l_in);
|
|---|
| 57 | /*
|
|---|
| 58 | * s_in IN The binary string to be compressed
|
|---|
| 59 | * l_in IN The number of characters in s_in
|
|---|
| 60 | *
|
|---|
| 61 | * returns COMPALLOK for all ok,
|
|---|
| 62 | * COMPERROR for any error. e.g. cannot read file
|
|---|
| 63 | *
|
|---|
| 64 | * The calling routine is responsible for ensuring that s_out is long
|
|---|
| 65 | * enough.
|
|---|
| 66 | */
|
|---|
| 67 |
|
|---|
| 68 |
|
|---|
| 69 |
|
|---|
| 70 |
|
|---|
| 71 |
|
|---|
| 72 | int done_special (char *filename);
|
|---|
| 73 | int done_text_1 (char *filename);
|
|---|
| 74 | int done_text_2 (char *filename);
|
|---|
| 75 | int done_invf_1 (char *filename);
|
|---|
| 76 | int done_invf_2 (char *filename);
|
|---|
| 77 | int done_ivf_1 (char *filename);
|
|---|
| 78 | int done_ivf_2 (char *filename);
|
|---|
| 79 | /*
|
|---|
| 80 | * returns COMPALLOK for all ok,
|
|---|
| 81 | * COMPERROR for any error. e.g. cannot write file
|
|---|
| 82 | */
|
|---|
| 83 |
|
|---|
| 84 |
|
|---|
| 85 |
|
|---|
| 86 |
|
|---|
| 87 |
|
|---|
| 88 |
|
|---|
| 89 |
|
|---|
| 90 |
|
|---|
| 91 |
|
|---|
| 92 |
|
|---|
| 93 |
|
|---|
| 94 |
|
|---|
| 95 |
|
|---|
| 96 |
|
|---|
| 97 | extern char InvfLevel;
|
|---|
| 98 | /*
|
|---|
| 99 | * This will determine the level of the inverted file it can take on the
|
|---|
| 100 | * values 1, 2, or 3.
|
|---|
| 101 | *
|
|---|
| 102 | * Level 1: The inverted file contains only document numbers making it possible
|
|---|
| 103 | * to do only boolean queries.
|
|---|
| 104 | *
|
|---|
| 105 | * Level 2: The inverted file also contains word counts per document making it
|
|---|
| 106 | * possible to do cosine ranked queries.
|
|---|
| 107 | *
|
|---|
| 108 | * Level 3: The inverted file contains word positions.
|
|---|
| 109 | */
|
|---|
| 110 |
|
|---|
| 111 |
|
|---|
| 112 | extern unsigned long buf_size;
|
|---|
| 113 | /*
|
|---|
| 114 | * The size of the document input buffer.
|
|---|
| 115 | */
|
|---|
| 116 |
|
|---|
| 117 | extern unsigned long ChunkLimit;
|
|---|
| 118 | /*
|
|---|
| 119 | * The maximum number of chunks that can be written to disk.
|
|---|
| 120 | */
|
|---|
| 121 |
|
|---|
| 122 | extern unsigned long invf_buffer_size;
|
|---|
| 123 | /*
|
|---|
| 124 | * The amount of memory to allocate to the invertion buffer.
|
|---|
| 125 | */
|
|---|
| 126 |
|
|---|
| 127 | extern char SkipSGML;
|
|---|
| 128 | /*
|
|---|
| 129 | * 1 if SGML tags are to be considered non-words when building the
|
|---|
| 130 | * inverted file.
|
|---|
| 131 | */
|
|---|
| 132 |
|
|---|
| 133 | extern char MakeWeights;
|
|---|
| 134 | /*
|
|---|
| 135 | * 1 if the weights file should be generated.
|
|---|
| 136 | */
|
|---|
| 137 |
|
|---|
| 138 | extern FILE *Comp_Stats;
|
|---|
| 139 | /*
|
|---|
| 140 | * Contains a file pointer to the file where compression stats should be sent
|
|---|
| 141 | */
|
|---|
| 142 |
|
|---|
| 143 | extern int comp_stat_point;
|
|---|
| 144 | /*
|
|---|
| 145 | * Generate a compression stat entry every comp_stat_point bytes
|
|---|
| 146 | */
|
|---|
| 147 |
|
|---|
| 148 | extern double bytes_processed; /* [RJM 07/97: 4G limit] */
|
|---|
| 149 | /*
|
|---|
| 150 | * The number of bytes processed. NOTE: This excludes document separators.
|
|---|
| 151 | */
|
|---|
| 152 |
|
|---|
| 153 | extern double bytes_received; /* [RJM 07/97: 4G limit] */
|
|---|
| 154 | /*
|
|---|
| 155 | * The number of bytes processed. NOTE: This includes document separators.
|
|---|
| 156 | */
|
|---|
| 157 |
|
|---|
| 158 |
|
|---|
| 159 | extern int stemmer_num;
|
|---|
| 160 | /*
|
|---|
| 161 | * The stemmer to use for stemming words for the inverted file.
|
|---|
| 162 | * see stemmer.h
|
|---|
| 163 | */
|
|---|
| 164 |
|
|---|
| 165 | extern int stem_method;
|
|---|
| 166 | /*
|
|---|
| 167 | * The method to use for stemming words for the inverted file.
|
|---|
| 168 | * see stemmer.h
|
|---|
| 169 | */
|
|---|
| 170 | #endif
|
|---|
