database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-07-27 12:41:57 +03:00
Code Activity

The fti.pl supplied with the fulltextindex module generate ALL possible

Browse Source 
substrings of two characters or greater, and is case-sensitive.

This patch makes it work correctly.  It generates only the suffixes of each
word, plus lowercases them - as specified by the README file.

This brings it into line with the fti.c function, makes it case-insensitive
properly, removes the problem with duplicate rows being returned from an fti
search and greatly reduces the size of the generated index table.

It was written by my co-worker, Brett Toolin.

Christopher Kings-Lynne
This commit is contained in:
Bruce Momjian
2001-08-01 18:40:12 +00:00
parent 8c6761acc7
commit 938236a297
1 changed files with 13 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
contrib/fulltextindex/fti.pl
View File

@ -1,6 +1,6 @@
#!/usr/bin/perl #!/usr/bin/perl
# #
# This script substracts all substrings out of a specific column in a table # This script substracts all suffixes of all words in a specific column in a table
# and generates output that can be loaded into a new table with the # and generates output that can be loaded into a new table with the
# psql '\copy' command. The new table should have the following structure: # psql '\copy' command. The new table should have the following structure:
# #
@ -52,27 +52,28 @@ $PGRES_BAD_RESPONSE = 5 ;
$PGRES_NONFATAL_ERROR = 6 ; $PGRES_NONFATAL_ERROR = 6 ;
$PGRES_FATAL_ERROR = 7 ; $PGRES_FATAL_ERROR = 7 ;
# the minimum length of word to include in the full text index
$MIN_WORD_LENGTH = 2;
# the minimum length of the substrings in the full text index
$MIN_SUBSTRING_LENGTH = 2;
$[ = 0; # make sure string offsets start at 0 $[ = 0; # make sure string offsets start at 0
sub break_up { sub break_up {
my $string = pop @_; my $string = pop @_;
# convert strings to lower case
$string = lc($string);
@strings = split(/\W+/, $string); @strings = split(/\W+/, $string);
@subs = (); @subs = ();
foreach $s (@strings) { foreach $s (@strings) {
$len = length($s); $len = length($s);
next if ($len < 4); next if ($len <= $MIN_WORD_LENGTH);
for ($i = 0; $i <= $len - $MIN_SUBSTRING_LENGTH; $i++) {
$lpos = $len-1; $tmp = substr($s, $i);
while ($lpos >= 3) { push(@subs, $tmp);
$fpos = $lpos - 3;
while ($fpos >= 0) {
$sub = substr($s, $fpos, $lpos - $fpos + 1);
push(@subs, $sub);
$fpos = $fpos - 1;
}
$lpos = $lpos - 1;
} }
} }