Skip to content

Optimize computeScore #132

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
jvandreae wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Optimize computeScore #132

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
31 changes: 19 additions & 12 deletions src/Search/Bitap/computeScore.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,16 +2,23 @@

namespace Fuse\Search\Bitap;

use function Fuse\Core\config;

function computeScore(string $pattern, array $options = [])
{
$errors = $options['errors'] ?? 0;
$currentLocation = $options['currentLocation'] ?? 0;
$expectedLocation = $options['expectedLocation'] ?? 0;
$distance = $options['distance'] ?? config('distance');
$ignoreLocation = $options['ignoreLocation'] ?? config('ignoreLocation');

/**
* @param string $pattern
* @param int $errors
* @param int $currentLocation
* @param int $expectedLocation
* @param int $distance
* @param bool $ignoreLocation
* @return float
*/
function computeScore(
$pattern,
$errors,
$currentLocation,
$expectedLocation,
$distance,
$ignoreLocation
) {
$accuracy = $errors / mb_strlen($pattern);

if ($ignoreLocation) {
Expand All @@ -20,9 +27,9 @@ function computeScore(string $pattern, array $options = [])

$proximity = abs($expectedLocation - $currentLocation);

if (!$distance) {
if ($distance === 0) {
// Dodge divide by zero error.
return $proximity ? 1.0 : $accuracy;
return $proximity === 0 ? 1.0 : $accuracy;
}

return $accuracy + $proximity / $distance;
Expand Down
31 changes: 4 additions & 27 deletions src/Search/Bitap/search.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,12 +49,7 @@ function search(string $text, string $pattern, array $patternAlphabet, array $op

// Get all exact matches, here for speed up
while (($index = mb_strpos($text, $pattern, $bestLocation)) !== false) {
$score = computeScore($pattern, [
'currentLocation' => $index,
'expectedLocation' => $expectedLocation,
'distance' => $distance,
'ignoreLocation' => $ignoreLocation,
]);
$score = computeScore($pattern, 0, $index, $expectedLocation, $distance, $ignoreLocation);

$currentThreshold = min($score, $currentThreshold);
$bestLocation = $index + $patternLen;
Expand Down Expand Up @@ -85,13 +80,7 @@ function search(string $text, string $pattern, array $patternAlphabet, array $op
$binMid = $binMax;

while ($binMin < $binMid) {
$score = computeScore($pattern, [
'errors' => $i,
'currentLocation' => $expectedLocation + $binMid,
'expectedLocation' => $expectedLocation,
'distance' => $distance,
'ignoreLocation' => $ignoreLocation,
]);
$score = computeScore($pattern, $i, $expectedLocation + $binMid, $expectedLocation, $distance, $ignoreLocation);

if ($score <= $currentThreshold) {
$binMin = $binMid;
Expand Down Expand Up @@ -136,13 +125,7 @@ function search(string $text, string $pattern, array $patternAlphabet, array $op
}

if ($bitArr[$j] & $mask) {
$finalScore = computeScore($pattern, [
'errors' => $i,
'currentLocation' => $currentLocation,
'expectedLocation' => $expectedLocation,
'distance' => $distance,
'ignoreLocation' => $ignoreLocation,
]);
$finalScore = computeScore($pattern, $i, $currentLocation, $expectedLocation, $distance, $ignoreLocation);

// This match will almost certainly be better than any existing match.
// But check anyway.
Expand All @@ -163,13 +146,7 @@ function search(string $text, string $pattern, array $patternAlphabet, array $op
}

// No hope for a (better) match at greater error levels.
$score = computeScore($pattern, [
'errors' => $i + 1,
'currentLocation' => $expectedLocation,
'expectedLocation' => $expectedLocation,
'distance' => $distance,
'ignoreLocation' => $ignoreLocation,
]);
$score = computeScore($pattern, $i + 1, $expectedLocation, $expectedLocation, $distance, $ignoreLocation);

if ($score > $currentThreshold) {
break;
Expand Down