Skip to content

[6.x] Fix Antlers line and column numbers after multibyte text or whitespace #15373

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
JohnathonKoster wants to merge 1 commit into
base: 6.x
Choose a base branch
from
+42 −14
Open

[6.x] Fix Antlers line and column numbers after multibyte text or whitespace #15373

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
23 changes: 9 additions & 14 deletions src/View/Antlers/Language/Parser/DocumentParser.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -328,24 +328,19 @@ private function processInputText($input)
$this->inputLen = mb_strlen($this->content);

// The document content was normalized, so we can search for "\n".
preg_match_all('/\n/', $this->content, $documentNewLines, PREG_OFFSET_CAPTURE);
$newLineCountLen = count($documentNewLines[0]);

$currentLine = $this->seedStartLine;
$lastOffset = null;
for ($i = 0; $i < $newLineCountLen; $i++) {
$thisNewLine = $documentNewLines[0][$i];
$thisIndex = $thisNewLine[1];
$indexChar = $thisIndex;

if ($lastOffset != null) {
$indexChar = $thisIndex - $lastOffset;
} else {
$indexChar = $indexChar + 1;
$lastOffset = -1;
$thisIndex = -1;

foreach (explode("\n", $this->content) as $line) {
$thisIndex += mb_strlen($line) + 1;

if ($thisIndex >= $this->inputLen) {
break;
}

$this->documentOffsets[$thisIndex] = [
self::K_CHAR => $indexChar,
self::K_CHAR => $thisIndex - $lastOffset,
self::K_LINE => $currentLine,
];

Expand Down
33 changes: 33 additions & 0 deletions tests/Antlers/Parser/BasicNodeTest.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,39 @@ public function test_it_returns_nodes()
$this->assertInstanceOf(LiteralNode::class, $nodes[3]);
}

public function test_multibyte_literals_keep_character_based_region_boundaries_and_lines()
{
$nodes = $this->parseNodes("caf\u{00E9}\n\u{65E5}\u{672C} {{ first }}\n\u{1F389} {{ second }} tail");

$this->assertSame("caf\u{00E9}\n\u{65E5}\u{672C} ", $nodes[0]->content);
$this->assertSame(' first ', $nodes[1]->content);
$this->assertSame("\n\u{1F389} ", $nodes[2]->content);
$this->assertSame(' second ', $nodes[3]->content);
$this->assertSame(' tail', $nodes[4]->content);

$this->assertSame(8, $nodes[1]->startPosition->offset);
$this->assertSame(2, $nodes[1]->startPosition->line);
$this->assertSame(4, $nodes[1]->startPosition->char);
$this->assertSame(22, $nodes[3]->startPosition->offset);
$this->assertSame(3, $nodes[3]->startPosition->line);
$this->assertSame(3, $nodes[3]->startPosition->char);
}

public function test_columns_are_correct_after_a_document_initial_newline()
{
foreach (["\n", "\r", "\r\n"] as $newline) {
$nodes = $this->parseNodes($newline."\u{65E5}\u{672C}{{ first }}".$newline.'ab{{ second }}');

$this->assertSame(3, $nodes[1]->startPosition->offset);
$this->assertSame(2, $nodes[1]->startPosition->line);
$this->assertSame(3, $nodes[1]->startPosition->char);

$this->assertSame(17, $nodes[3]->startPosition->offset);
$this->assertSame(3, $nodes[3]->startPosition->line);
$this->assertSame(3, $nodes[3]->startPosition->char);
}
}

public function test_it_doesnt_trim_off_content_start()
{
$nodes = $this->parseNodes('{{ meta_title ?? title ?? "No Title Set" }}');
Expand Down
Loading