Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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 CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@ adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
### Fixed

- Surname particles remain attached after given-name initials: `J. van Gogh` now keeps first name `J.` and surname `van Gogh`, rather than promoting `van` to the first name. This also applies with a salutation, nickname, or trailing credential. See the [parser regression cases](tests/InitialSurnamePrefixTest.php).
- Numeric symmetric nickname delimiters now obey token boundaries when splitting names and shield nickname commas during standalone confidence assessment.

## [1.6.0] - 2026-10-16

Expand Down
1 change: 1 addition & 0 deletions src/Confidence.php
Original file line number Diff line number Diff line change
Expand Up @@ -284,6 +284,7 @@ private static function tokenizeAsciiDelimiters(string $normalized, array $delim

$closerStart = $position - 1;
foreach ($symmetric as $delimiter => $_) {
$delimiter = (string) $delimiter;
if ($closerStart < $tokenStart || $normalized[$closerStart] !== $delimiter) {
continue;
}
Expand Down
1 change: 1 addition & 0 deletions src/StructuralCommaSplitter.php
Original file line number Diff line number Diff line change
Expand Up @@ -115,6 +115,7 @@ private static function splitDelimiters(array $delimiters): array
/** @var array<string, true> $symmetric */
$symmetric = [];
foreach ($delimiters as $open => $close) {
$open = (string) $open;
if ($open === '' || $close === '') {
continue;
}
Expand Down
39 changes: 39 additions & 0 deletions tests/ConfidenceTest.php
Original file line number Diff line number Diff line change
Expand Up @@ -306,6 +306,45 @@ public function testEmptyWhitespacePreservesTabsBeforeConfidenceTokenization():
);
}

/**
* @return array<string, array{string}>
*/
public static function numericNicknameDelimiterProvider(): array
{
$cases = [];
for ($digit = 0; $digit <= 9; ++$digit) {
$cases['digit ' . $digit] = [(string) $digit];
}

return $cases;
}

#[DataProvider('numericNicknameDelimiterProvider')]
public function testNumericNicknameDelimitersShieldCommas(string $delimiter): void
{
$delimiters = [$delimiter => $delimiter];
$input = 'John ' . $delimiter . 'foo,do,bar' . $delimiter . ' Smith';
$name = (new Parser())->setNicknameDelimiters($delimiters)->parse($input);

$this->assertSame('Foo,Do,Bar', $name->getNickname());
$this->assertSame(['ambiguous' => false, 'notes' => []], $name->getConfidence());
$this->assertSame(
$name->getConfidence(),
Confidence::assess($input, nicknameDelimiters: $delimiters),
);

// The comma after the closed nickname must remain structural.
$this->assertTrue(Confidence::assess(
$input . ', do',
nicknameDelimiters: $delimiters,
)['ambiguous']);
// An unmatched opener must not hide the lowercase credential.
$this->assertTrue(Confidence::assess(
'John ' . $delimiter . 'foo,do,bar Smith',
nicknameDelimiters: $delimiters,
)['ambiguous']);
}

public function testManyConfiguredDelimitersStayWithinMemoryBudget(): void
{
$input = 'X ' . str_repeat('a', (1024 * 1024) - 10) . ', Y';
Expand Down
47 changes: 47 additions & 0 deletions tests/NumericNicknameDelimiterTest.php
Original file line number Diff line number Diff line change
@@ -0,0 +1,47 @@
<?php

namespace Tests\Iliaal\NameParser;

use Iliaal\NameParser\Parser;
use Iliaal\NameParser\StructuralCommaSplitter;
use PHPUnit\Framework\Attributes\DataProvider;
use PHPUnit\Framework\TestCase;

class NumericNicknameDelimiterTest extends TestCase
{
/**
* @return array<string, array{string}>
*/
public static function delimiterProvider(): array
{
$cases = [];
foreach (['0', '1', '2', '3', '4', '5', '6', '7', '8', '9', '10', '-1'] as $delimiter) {
$cases['delimiter ' . $delimiter] = [$delimiter];
}

return $cases;
}

#[DataProvider('delimiterProvider')]
public function testSymmetricNumericDelimitersRequireTokenBoundaries(string $delimiter): void
{
$delimiters = [$delimiter => $delimiter];
$input = 'Smith' . $delimiter . ', John' . $delimiter;

$this->assertSame(
['Smith' . $delimiter, ' John' . $delimiter],
StructuralCommaSplitter::split($input, $delimiters),
);
$name = (new Parser())->setNicknameDelimiters($delimiters)->parse($input);
$this->assertSame('John' . $delimiter, $name->getFirstname());
$this->assertSame('Smith' . $delimiter, $name->getLastname());
$this->assertSame('', $name->getNickname());

$this->assertSame(
['John ' . $delimiter . 'foo', 'bar' . $delimiter . 'x Smith'],
StructuralCommaSplitter::split('John ' . $delimiter . 'foo,bar' . $delimiter . 'x Smith', $delimiters),
);
$closed = 'John ' . $delimiter . 'foo,bar' . $delimiter . ' Smith';
$this->assertSame([$closed], StructuralCommaSplitter::split($closed, $delimiters));
}
}
Loading