| 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_perf_hash_build 1 \*(Dt CITRI
|
|---|
| 9 | .SH NAME
|
|---|
| 10 | mgpp_perf_hash_build \- generate an order-preserving hash function for the stemmed dictionary
|
|---|
| 11 | .SH SYNOPSIS
|
|---|
| 12 | .B mgpp_perf_hash_build
|
|---|
| 13 | [
|
|---|
| 14 | .B \-h
|
|---|
| 15 | ]
|
|---|
| 16 | [
|
|---|
| 17 | .BI \-r " rndseed"
|
|---|
| 18 | ]
|
|---|
| 19 | [
|
|---|
| 20 | .BI \-d " directory"
|
|---|
| 21 | ]
|
|---|
| 22 | .if n .ti +9n
|
|---|
| 23 | .BI \-f " name"
|
|---|
| 24 | .SH DESCRIPTION
|
|---|
| 25 | .B mgpp_perf_hash_build
|
|---|
| 26 | generates an order-preserving hashing function from the compressed
|
|---|
| 27 | stemmed dictionary and writes it out to disk.
|
|---|
| 28 | .BR mgpp_passes (1)
|
|---|
| 29 | will make use of the hash function when it builds the inverted file.
|
|---|
| 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 stderr .
|
|---|
| 36 | .TP
|
|---|
| 37 | .BI \-r " rndseed"
|
|---|
| 38 | This specifies the random seed to be used in the generation of the
|
|---|
| 39 | hash function; it must be an integer. If this is not specified, the
|
|---|
| 40 | current time will be used as the random seed.
|
|---|
| 41 | .TP
|
|---|
| 42 | .BI \-d " directory"
|
|---|
| 43 | This specifies the directory where the document collection can be found.
|
|---|
| 44 | .TP
|
|---|
| 45 | .BI \-f " name"
|
|---|
| 46 | This specifies the base name of the document collection.
|
|---|
| 47 | .SH ENVIRONMENT
|
|---|
| 48 | .TP "\w'\fBMGDATA\fP'u+2n"
|
|---|
| 49 | .SB MGDATA
|
|---|
| 50 | If this environment variable exists, then its value is used as the
|
|---|
| 51 | default directory where the mg
|
|---|
| 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 *.invf.dict
|
|---|
| 61 | Stemmed dictionary.
|
|---|
| 62 | .TP
|
|---|
| 63 | .B *.invf.dict.hash
|
|---|
| 64 | Data for a order-preserving perfect hash function.
|
|---|
| 65 | .SH "SEE ALSO"
|
|---|
| 66 | .na
|
|---|
| 67 | .BR mgpp_compression_dict (1),
|
|---|
| 68 | .BR mgpp_fast_comp_dict (1),
|
|---|
| 69 | .BR mgpp_invf_dict (1),
|
|---|
| 70 | .BR mgpp_passes (1),
|
|---|
| 71 | .BR mgpp_stem_idx (1),
|
|---|
| 72 | .BR mgpp_weights_build (1)
|
|---|
