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 | .\"------------------------------------------------------------
|
---|
8 | .TH mgpp_weights_build 1 \*(Dt CITRI
|
---|
9 | .SH NAME
|
---|
10 | mgpp_weights_build \- builds the approximate weights file
|
---|
11 | .SH SYNOPSIS
|
---|
12 | .B mgpp_weights_build
|
---|
13 | [
|
---|
14 | .B \-h
|
---|
15 | ]
|
---|
16 | [
|
---|
17 | .BI \-b " num-bits"
|
---|
18 | ]
|
---|
19 | .if n .ti +17n
|
---|
20 | [
|
---|
21 | .BI \-d " directory"
|
---|
22 | ]
|
---|
23 | .BI \-f " name"
|
---|
24 | .SH DESCRIPTION
|
---|
25 | .B mgpp_weights_build
|
---|
26 | is the program that generates the exact and approximate weights
|
---|
27 | files. To do this, it uses the inverted file
|
---|
28 | and dictionary.
|
---|
29 | .SH OPTIONS
|
---|
30 | Options may appear in any order.
|
---|
31 | .TP "\w'\fB\-d\fP \fIirectory\fP'u+2n"
|
---|
32 | .B \-h
|
---|
33 | This displays a usage line on
|
---|
34 | .IR stderr .
|
---|
35 | .TP
|
---|
36 | .BI \-b " num-bits"
|
---|
37 | This specifies the number of bits of precision that should be used for
|
---|
38 | the approximate weights. If not specified, it defaults to 8.
|
---|
39 | .TP
|
---|
40 | .BI \-d " directory"
|
---|
41 | This specifies the directory where the document collection is.
|
---|
42 | .TP
|
---|
43 | .BI \-f " name"
|
---|
44 | This specifies the base name of the document collection.
|
---|
45 | .SH ENVIRONMENT
|
---|
46 | .TP "\w'\fBMGDATA\fP'u+2n"
|
---|
47 | .SB MGDATA
|
---|
48 | If this environment variable exists, then its value is used as the
|
---|
49 | default directory where the mgpp
|
---|
50 | collection files are. If this variable does not exist, then the
|
---|
51 | directory \*(lq\fB.\fP\*(rq is used by default. The command line
|
---|
52 | option
|
---|
53 | .BI \-d " directory"
|
---|
54 | overrides the directory in
|
---|
55 | .BR MGDATA .
|
---|
56 | .SH FILES
|
---|
57 | .TP 20
|
---|
58 | .B *.invf
|
---|
59 | Inverted file.
|
---|
60 | .TP
|
---|
61 | .B *.invf.dict
|
---|
62 | Compressed stemmed dictionary.
|
---|
63 | .TP
|
---|
64 | .B *.text.idx
|
---|
65 | Index into the compressed documents.
|
---|
66 | .TP
|
---|
67 | .B *.weight
|
---|
68 | The exact weights file.
|
---|
69 | .TP
|
---|
70 | .B *.weight.approx
|
---|
71 | Approximate document weights.
|
---|
72 | .SH "SEE ALSO"
|
---|
73 | .na
|
---|
74 | .BR mgpp_compression_dict (1),
|
---|
75 | .BR mgpp_fast_comp_dict (1),
|
---|
76 | .BR mgpp_invf_dict (1),
|
---|
77 | .BR mgpp_passes (1),
|
---|
78 | .BR mgpp_perf_hash_build (1),
|
---|
79 | .BR mgpp_stem_idx (1)
|
---|