lgrz

WORD	ABBREVIATIONS	LANGUAGE CODES
's-Graveland	n.a.	dut
's-Gravenhage	n.a.	dut
's-Gravenmoer	n.a.	dut
's-Heerenberg	n.a.	dut
's-Hertogenbosch	n.a.	dut
-agōgē	-ag.	gre
-aineisto	-ain.	fin
-Alföld	-Alf.	hun
-arvio	n.a.	fin

lgrz

<parameters>
  <stopper>  
  <word>a</word>
  <word>about</word>
  <word>above</word>
  <word>according</word>
  <word>across</word>
  <word>after</word>
  <word>afterwards</word>

lgrz

feature-id,feature-description,stream,comments
1,covered query term number,body,
2,covered query term number,anchor,
3,covered query term number,title,
4,covered query term number,url,
5,covered query term number,whole document,
6,covered query term ratio,body,
7,covered query term ratio,anchor,
8,covered query term ratio,title,
9,covered query term ratio,url,

lgrz

#!/usr/bin/perl

#
# Perl subroutine that generates Indri dependence model queries.
#
# Written by: Don Metzler ([email protected])
# Last updated: 06/27/2005
#
# Feel free to distribute, edit, modify, or mangle this code as you see fit. If you make any interesting
# changes please email me a copy.

lgrz

#!/usr/bin/perl

#
# Perl subroutine that generates Indri dependence model queries.
#
# Written by: Don Metzler ([email protected])
# Last updated: 06/27/2005
#
# Feel free to distribute, edit, modify, or mangle this code as you see fit. If you make any interesting
# changes please email me a copy.

lgrz

\begin{tabular}{r@{$.$}l}
  $3$ &$14$  \\
  $9$ &$80665$
\end{tabular}

lgrz

<parmeters>
    <memory>128G</memory>
	<index>myindex</index>
	<storeDocs>true</storeDocs>
	<stemmer><name>krovetz</name></stemmer>
	<corpus>
        <path>/path/to/corpus</path>
		<class>warc</class>
        <inlink>/path/to/links/sorted</inlink>
	</corpus>

lgrz

# build sdm template file
awk -F\; 'BEGIN {
  print "<parameters>"
}
{
 "./dm.pl \"" $2 "\" sd 1WFI 1WOD 1WUW" | getline qry
 printf "<query><number>%s</number><text>%s</text></query>\n", $1, qry
 }
 END {
print "</parameters>"

lgrz

https://blog.archive.org/developers/

lgrz

:g/^/p| call system(getline('.'))