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: mgstat.1 3745 2003-02-20 21:20:24Z mdewsnip $
|
---|
8 | .\"------------------------------------------------------------
|
---|
9 | .TH mgstat 1 \*(Dt CITRI
|
---|
10 | .SH NAME
|
---|
11 | mgstat \- print out statistics about a document collection
|
---|
12 | .SH SYNOPSIS
|
---|
13 | .B mgstat
|
---|
14 | [
|
---|
15 | .B \-h
|
---|
16 | ]
|
---|
17 | [
|
---|
18 | .B \-E
|
---|
19 | ]
|
---|
20 | [
|
---|
21 | .BI \-d " directory"
|
---|
22 | ]
|
---|
23 | .BI \-f " name"
|
---|
24 | .SH DESCRIPTION
|
---|
25 | .B mgstat
|
---|
26 | prints out various statistics about an existing
|
---|
27 | .BR mg (1)
|
---|
28 | document collection. Depending on the size of the collection, sizes
|
---|
29 | will be printed in either kilobytes or megabytes.
|
---|
30 | .SH OPTIONS
|
---|
31 | Options may appear in any order.
|
---|
32 | .TP "\w'\fB\-d\fP \fIdirectory\fP'u+2n"
|
---|
33 | .B \-h
|
---|
34 | This displays a usage line on
|
---|
35 | .IR stdout .
|
---|
36 | .TP
|
---|
37 | .B \-E
|
---|
38 | This option forces sizes to be printed in bytes rather than kilobytes
|
---|
39 | or megabytes.
|
---|
40 | .TP
|
---|
41 | .BI \-d " directory"
|
---|
42 | This specifies the directory where the document collection can be found.
|
---|
43 | .TP
|
---|
44 | .BI \-f " name"
|
---|
45 | This specifies the base name of the document collection.
|
---|
46 | .SH ENVIRONMENT
|
---|
47 | .TP "\w'\fBMGDATA\fP'u+2n"
|
---|
48 | .SB MGDATA
|
---|
49 | If this environment variable exists, then its value is used as the
|
---|
50 | default directory where the
|
---|
51 | .BR mg (1)
|
---|
52 | collection files are. If this variable does not exist, then the
|
---|
53 | directory \*(lq\fB.\fP\*(rq is used by default. The command line
|
---|
54 | option
|
---|
55 | .BI \-d " directory"
|
---|
56 | overrides the directory in
|
---|
57 | .BR MGDATA .
|
---|
58 | .SH FILES
|
---|
59 | .TP 20
|
---|
60 | .B *.text
|
---|
61 | Compressed documents.
|
---|
62 | .TP
|
---|
63 | .B *.invf
|
---|
64 | Inverted file.
|
---|
65 | .TP
|
---|
66 | .B *.text.idx.wgt
|
---|
67 | Interleaved index into the compressed documents and document weights.
|
---|
68 | .TP
|
---|
69 | .B *.weight.approx
|
---|
70 | Approximate document weights.
|
---|
71 | .TP
|
---|
72 | .B *.invf.dict.blocked
|
---|
73 | Compressed stemmed dictionary and index into the inverted file merged
|
---|
74 | into an inverted file.
|
---|
75 | .TP
|
---|
76 | .B *.text.dict.fast
|
---|
77 | Fast loading compression dictionary.
|
---|
78 | .TP
|
---|
79 | .B *.text.dict
|
---|
80 | Compressed compression dictionary.
|
---|
81 | .TP
|
---|
82 | .B *.invf.dict
|
---|
83 | Compressed stemmed dictionary.
|
---|
84 | .TP
|
---|
85 | .B *.invf.idx
|
---|
86 | The index into the inverted file.
|
---|
87 | .TP
|
---|
88 | .B *.text.stats
|
---|
89 | Statistics about the text.
|
---|
90 | .TP
|
---|
91 | .B *.text.dict.aux
|
---|
92 | Auxiliary compression dictionary.
|
---|
93 | .TP
|
---|
94 | .B *.text.idx
|
---|
95 | Index into the compressed documents.
|
---|
96 | .TP
|
---|
97 | .B *.weight
|
---|
98 | The exact weights file.
|
---|
99 | .TP
|
---|
100 | .B *.invf.chunk
|
---|
101 | Maps stemmed terms from occurrence order to lexical order.
|
---|
102 | .TP
|
---|
103 | .B *.invf.chunk.trans
|
---|
104 | Describes where the source text is broken up into chunks for the
|
---|
105 | inversion pass.
|
---|
106 | .TP
|
---|
107 | .B *.invf.dict.hash
|
---|
108 | A perfect hash function for the terms in the stemmed dictionary.
|
---|
109 | .SH "SEE ALSO"
|
---|
110 | .na
|
---|
111 | .BR mg (1),
|
---|
112 | .BR mg_compression_dict (1),
|
---|
113 | .BR mg_fast_comp_dict (1),
|
---|
114 | .BR mg_get (1),
|
---|
115 | .BR mg_invf_dict (1),
|
---|
116 | .BR mg_invf_dump (1),
|
---|
117 | .BR mg_invf_rebuild (1),
|
---|
118 | .BR mg_passes (1),
|
---|
119 | .BR mg_perf_hash_build (1),
|
---|
120 | .BR mg_text_estimate (1),
|
---|
121 | .BR mg_weights_build (1),
|
---|
122 | .BR mgbilevel (1),
|
---|
123 | .BR mgbuild (1),
|
---|
124 | .BR mgdictlist (1),
|
---|
125 | .BR mgfelics (1),
|
---|
126 | .BR mgquery (1),
|
---|
127 | .BR mgtic (1),
|
---|
128 | .BR mgticbuild (1),
|
---|
129 | .BR mgticdump (1),
|
---|
130 | .BR mgticprune (1),
|
---|
131 | .BR mgticstat (1).
|
---|