1 | .\"------------------------------------------------------------
|
---|
2 | .\" Id - set Rv,revision, and Dt, Date using rcs-Id tag.
|
---|
3 | .de Id
|
---|
4 | .ds Rv \\$3
|
---|
5 | .ds Dt \\$4
|
---|
6 | ..
|
---|
7 | .Id $Id: mg_text_estimate.1 3745 2003-02-20 21:20:24Z mdewsnip $
|
---|
8 | .\"------------------------------------------------------------
|
---|
9 | .TH mg_text_estimate 1 \*(Dt CITRI
|
---|
10 | .SH NAME
|
---|
11 | mg_text_estimate \- Estimate the size of the compressed text based on the text statistics and a compression dictionary.
|
---|
12 | .SH SYNOPSIS
|
---|
13 | .B mg_text_estimate
|
---|
14 | [
|
---|
15 | .B \-h
|
---|
16 | ]
|
---|
17 | [
|
---|
18 | .BR \-H " |"
|
---|
19 | .BR \-B " |"
|
---|
20 | .BR \-D " |"
|
---|
21 | .BR \-Y " |"
|
---|
22 | .B \-M
|
---|
23 | ]
|
---|
24 | .if n .ti +9n
|
---|
25 | .I stats-dict
|
---|
26 | .I compression-dict
|
---|
27 | .SH DESCRIPTION
|
---|
28 | This program estimates the size of the compressed text that would be
|
---|
29 | generated if text with certain statistics were compressed with a
|
---|
30 | particular dictionary. This program has no real use in the
|
---|
31 | .BR mg (1)
|
---|
32 | system, except for experimenting with the
|
---|
33 | .BR mg_compression_dict (1)
|
---|
34 | program.
|
---|
35 | .SH OPTIONS
|
---|
36 | Options may appear in any order.
|
---|
37 | .TP "\w'\fB\-m\fP'u+2n"
|
---|
38 | .B \-h
|
---|
39 | This displays a usage line on
|
---|
40 | .IR stderr .
|
---|
41 | .TP
|
---|
42 | .B \-H
|
---|
43 | This specifies that novel words will be coded character by character
|
---|
44 | using Huffman codes.
|
---|
45 | .TP
|
---|
46 | .B \-B
|
---|
47 | This specifies that the size of an auxiliary dictionary will be
|
---|
48 | estimated. Each novel word found will be placed at the end of the
|
---|
49 | auxiliary dictionary. Novel words will be coded in the compressed text
|
---|
50 | using binary codes. The binary code represents their occurrence
|
---|
51 | position in the auxiliary dictionary.
|
---|
52 | .TP
|
---|
53 | .B \-D
|
---|
54 | This specifies that the size of an auxiliary dictionary will be
|
---|
55 | estimated. Each novel word found will be placed at the end of the
|
---|
56 | auxiliary dictionary. Novel words will be coded in the compressed text
|
---|
57 | using delta codes. The delta code represents their occurrence position
|
---|
58 | in the auxiliary dictionary.
|
---|
59 | .TP
|
---|
60 | .B \-Y
|
---|
61 | This specifies that the size of an auxiliary dictionary will be
|
---|
62 | estimated. Each novel word found will be placed at the end of the
|
---|
63 | auxiliary dictionary. Novel words will be coded in the compressed text
|
---|
64 | using a combination of gamma and binary codes. The code represents
|
---|
65 | their occurrence position in the auxiliary dictionary. This generally
|
---|
66 | produces better compression than
|
---|
67 | .B \-B
|
---|
68 | or
|
---|
69 | .BR \-D .
|
---|
70 | .TP
|
---|
71 | .B \-M
|
---|
72 | This specifies that the size of an auxiliary dictionary will be
|
---|
73 | estimated. Each novel word found will be placed at the end of the
|
---|
74 | auxiliary dictionary. Novel words will be coded in the compressed text
|
---|
75 | using a combination of gamma and binary codes. The code represents
|
---|
76 | their occurrence position in the auxiliary dictionary. This method is
|
---|
77 | adaptive within documents, and generally produces better compression
|
---|
78 | than
|
---|
79 | .BR \-B ,
|
---|
80 | .B \-D
|
---|
81 | or
|
---|
82 | .BR \-Y .
|
---|
83 | .SH FILES
|
---|
84 | .TP 20
|
---|
85 | .B *.text.stats
|
---|
86 | Statistics about the text.
|
---|
87 | .TP
|
---|
88 | .B *.text.dict
|
---|
89 | Compressed compression dictionary.
|
---|
90 | .SH "SEE ALSO"
|
---|
91 | .na
|
---|
92 | .BR mg (1),
|
---|
93 | .BR mg_compression_dict (1),
|
---|
94 | .BR mg_fast_comp_dict (1),
|
---|
95 | .BR mg_get (1),
|
---|
96 | .BR mg_invf_dict (1),
|
---|
97 | .BR mg_invf_dump (1),
|
---|
98 | .BR mg_invf_rebuild (1),
|
---|
99 | .BR mg_passes (1),
|
---|
100 | .BR mg_perf_hash_build (1),
|
---|
101 | .BR mg_weights_build (1),
|
---|
102 | .BR mgbilevel (1),
|
---|
103 | .BR mgbuild (1),
|
---|
104 | .BR mgdictlist (1),
|
---|
105 | .BR mgfelics (1),
|
---|
106 | .BR mgquery (1),
|
---|
107 | .BR mgstat (1),
|
---|
108 | .BR mgtic (1),
|
---|
109 | .BR mgticbuild (1),
|
---|
110 | .BR mgticdump (1),
|
---|
111 | .BR mgticprune (1),
|
---|
112 | .BR mgticstat (1).
|
---|