- or download this
<doc id="some_id_string" title="title string" date="date_string" ...>
<text>
...
</text>
</doc>
...
- or download this
create table content_index (
search_term varchar(50),
...
in_body char(1),
how_many integer
)
- or download this
#!/usr/bin/perl
...
print join( ",", $tkn, $id, "Y,N", $tknhist{ttl}{$tkn} ), "\n"
+;
}
}
- or download this
cut -f1 -d, table-data | sort | uniq -c | sort -nr > word.doc-freqs