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_invf_dict.1 16583 2008-07-29 10:20:36Z davidb $
|
---|
8 | .\"------------------------------------------------------------
|
---|
9 | .TH mg_invf_dict 1 \*(Dt CITRI
|
---|
10 | .SH NAME
|
---|
11 | mg_invf_dict \- build an `on-disk' stemmed dictionary
|
---|
12 | .SH SYNOPSIS
|
---|
13 | .B mg_invf_dict
|
---|
14 | [
|
---|
15 | .B \-h
|
---|
16 | ]
|
---|
17 | [
|
---|
18 | .B \-F
|
---|
19 | ]
|
---|
20 | [
|
---|
21 | .BI \-b " num"
|
---|
22 | ]
|
---|
23 | [
|
---|
24 | .BI \-d " directory"
|
---|
25 | ]
|
---|
26 | .if n .ti +9n
|
---|
27 | .BI \-f " name"
|
---|
28 | .SH DESCRIPTION
|
---|
29 | .B mg_invf_dict
|
---|
30 | builds an `on-disk' stemmed dictionary from the
|
---|
31 | compressed stemmed dictionary that the
|
---|
32 | .BR mgquery (1)
|
---|
33 | program can access. Each entry in the dictionary contains the disk
|
---|
34 | pointer to the associated inverted file entry, and various other pieces
|
---|
35 | of information about the stemmed word.
|
---|
36 | .SH OPTIONS
|
---|
37 | Options may appear in any order.
|
---|
38 | .TP "\w'\fB\-d\fP \fIdirectory\fP'u+2n"
|
---|
39 | .B \-h
|
---|
40 | This displays a usage line on
|
---|
41 | .IR stderr .
|
---|
42 | .TP
|
---|
43 | .BI \-b " num"
|
---|
44 | The dictionary is stored in blocks on disk; this option is used to set
|
---|
45 | the block size. The default is 4-KB blocks.
|
---|
46 | .TP
|
---|
47 | .B \-F
|
---|
48 | This option causes the disk blocks to be aligned on the appropriate
|
---|
49 | boundaries. For example, if 4-KB blocks are used, they will be aligned
|
---|
50 | in the file on 4-KB boundaries.
|
---|
51 | .TP
|
---|
52 | .BI \-d " directory"
|
---|
53 | This specifies the directory where the document collection can be found.
|
---|
54 | .TP
|
---|
55 | .BI \-f " name"
|
---|
56 | This specifies the base name of the document collection.
|
---|
57 | .SH ENVIRONMENT
|
---|
58 | .TP "\w'\fBMGDATA\fP'u+2n"
|
---|
59 | .SB MGDATA
|
---|
60 | If this environment variable exists, then its value is used as the
|
---|
61 | default directory where the
|
---|
62 | .BR mg (1)
|
---|
63 | collection files are. If this variable does not exist, then the
|
---|
64 | directory \*(lq\fB.\fP\*(rq is used by default. The command line
|
---|
65 | option
|
---|
66 | .BI \-d " directory"
|
---|
67 | overrides the directory in
|
---|
68 | .BR MGDATA .
|
---|
69 | .SH FILES
|
---|
70 | .TP 20
|
---|
71 | .B *.invf
|
---|
72 | Inverted file.
|
---|
73 | .TP
|
---|
74 | .B *.invf.dict.build
|
---|
75 | Compressed stemmed dictionary.
|
---|
76 | .TP
|
---|
77 | .B *.invf.dict
|
---|
78 | The `on-disk' stemmed dictionary.
|
---|
79 | .TP
|
---|
80 | .B *.invf.idx
|
---|
81 | The index into the inverted file.
|
---|
82 | .SH "SEE ALSO"
|
---|
83 | .na
|
---|
84 | .BR mg (1),
|
---|
85 | .BR mg_compression_dict (1),
|
---|
86 | .BR mg_fast_comp_dict (1),
|
---|
87 | .BR mg_get (1),
|
---|
88 | .BR mg_invf_dump (1),
|
---|
89 | .BR mg_invf_rebuild (1),
|
---|
90 | .BR mg_passes (1),
|
---|
91 | .BR mg_perf_hash_build (1),
|
---|
92 | .BR mg_text_estimate (1),
|
---|
93 | .BR mg_weights_build (1),
|
---|
94 | .BR mgbilevel (1),
|
---|
95 | .BR mgbuild (1),
|
---|
96 | .BR mgdictlist (1),
|
---|
97 | .BR mgfelics (1),
|
---|
98 | .BR mgquery (1),
|
---|
99 | .BR mgstat (1),
|
---|
100 | .BR mgtic (1),
|
---|
101 | .BR mgticbuild (1),
|
---|
102 | .BR mgticdump (1),
|
---|
103 | .BR mgticprune (1),
|
---|
104 | .BR mgticstat (1).
|
---|