Skip to content
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

Experiment with similar titles #333

Merged
merged 1 commit into from
Aug 8, 2022
Merged

Experiment with similar titles #333

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
1 change: 1 addition & 0 deletions composer.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,6 +50,7 @@
"twig/cssinliner-extra": "^3.3",
"twig/extra-bundle": "^2.12|^3.0",
"twig/inky-extra": "^3.3",
"twig/intl-extra": "^3.4",
"twig/markdown-extra": "^3.3",
"twig/string-extra": "^3.0",
"twig/twig": "^2.12|^3.0",
Expand Down
71 changes: 70 additions & 1 deletion composer.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

5 changes: 4 additions & 1 deletion src/Controller/TitleController.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -313,14 +313,17 @@ public function importMarcAction(Request $request, EstcMarcImporter $importer, $
* @Template
*
* @return array<string,mixed> */
public function showAction(Title $title, SourceLinker $linker) {
public function showAction(Title $title, SourceLinker $linker, TitleRepository $repo) {
if ( ! $this->getUser() && ! $title->getFinalattempt() && ! $title->getFinalcheck()) {
throw new AccessDeniedHttpException('This title has not been verified and is not available to the public.');
}

$similar = $repo->moreLike($title);

return [
'title' => $title,
'linker' => $linker,
'similar' => $similar,
];
}

Expand Down
39 changes: 39 additions & 0 deletions src/Repository/TitleRepository.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,7 @@
use Doctrine\ORM\Query;
use Doctrine\ORM\QueryBuilder;
use Doctrine\Persistence\ManagerRegistry;
use Symfony\Component\Console\Input\InputOption;

/**
* Title Repository.
Expand Down Expand Up @@ -90,6 +91,44 @@ public function typeaheadQuery($q) {
return $qb->getQuery()->execute();
}

/**
* @param Title $title
*
* @return array
*/
public function moreLike(Title $title) {
$qb = $this->createQueryBuilder('title');
$qb->addSelect('MATCH(title.title) AGAINST (:title BOOLEAN) AS score');
$qb->setParameter('title', $title->getTitle());
$qb->andHaving('score > 5.0');
$qb->orderBy('score', 'desc');
$result = $qb->getQuery()->execute();

// MySQL's full text indexing is good, but not good enough for this. It
// finds a lot of false positives, so filter them out with a quick
// levenshtein().
$similar = [];
// No mb_substr here, as levenshtein() is hard-limited to 255 bytes!
$t1 = substr($title->getTitle(), 0, 255);
foreach($result as $row) {
$t = $row[0];
if($t->getId() === $title->getId()) {
continue;
}
// No mb_substr here, as levenshtein() is hard-limited to 255 bytes!
$t2 = substr($t->getTitle(), 0, 255);
$lev = 1.0 - levenshtein($t1, $t2) / max(mb_strlen($t1), mb_strlen($t2));
if($lev > 0.3) {
$similar[] = [
'title' => $t,
'score' => $row['score'],
'lev' => $lev,
];
}
}
return $similar;
}

/**
* Build a complex search query from form data.
*
Expand Down
70 changes: 70 additions & 0 deletions templates/title/show.html.twig
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -267,6 +267,76 @@
{% endembed %}
</div>

{% if is_granted('ROLE_USER') %}
<div class='similarity'>
<h2>Similar Titles</h2>
{% set count = similar | length %}
{% if count > 0 %}
<p><i>These titles are selected from the database automatically,
based on text analysis. The list may be incomplete or contain
unrelated titles.</i></p>
<table class='table'>
<thead>
<th>ID</th>
<th>Title</th>
<th>Contributors</th>
<th>Firms</th>
<th>Edition</th>
{% if is_granted('ROLE_ADMIN') %}
<th></th>
{% endif %}
</thead>
<tbody>
{% for row in similar %}
{% set title = row.title %}
<tr>
<td>
<a href="{{ path('title_show', { 'id': title.id }) }}">
{{ title.id }}
</a>
</td>
<td>
<a href="{{ path('title_show', { 'id': title.id }) }}">
{{ title.title }}
</a>
</td>
<td>
{% for tr in title.titleRoles|slice(0,title_index_authors) %}
{% set person = tr.person %}
<a href="{{ path('person_show', {'id': person.id}) }}">{{ person.lastName }}
, {{ person.firstName }}</a>
({{ tr.role }})
<br/>
{% endfor %}
{% if title.titleRoles|length > title_index_authors %}and {{ title.titleRoles|length - title_index_authors }} more.{% endif %}
</td>
<td>
{% for tfr in title.titleFirmRoles|slice(0,title_index_authors) %}
{% set firm = tfr.firm %}
<a href="{{ path('firm_show', {'id': firm.id}) }}">{{ firm.name }}</a>
({{ tfr.firmrole }})
<br/>
{% endfor %}
{% if title.titleFirmRoles|length > title_index_authors %}and {{ title.titleFirmRoles|length - title_index_authors }} more.{% endif %}
</td>
<td class="numeric">{{ title.pubdate }}</td>
<td class="numeric">{{ title.editionNumber }}</td>
{% if is_granted('ROLE_ADMIN') %}
<td class='numeric'>
{{ row.score|format_number({fraction_digit: 1}) }}<br>
{{ row.lev|format_number(style='percent') }}
</td>
{% endif %}
</tr>
{% endfor %}
</tbody>
</table>
{% else %}
<p><i>No similar titles found in the database.</i></p>
{% endif %}
</div>
{% endif %}

{% set relations = title.relatedTitles|merge(title.titlesRelated) %}
{% if relations|length > 0 %}
<div>
Expand Down