Skip to content

fix error with empty index by including raw information in diff #229

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

Merged
lyrixx merged 3 commits into from
Jan 29, 2025
+140 −6
Merged

fix error with empty index by including raw information in diff #229

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
a9a0135
fix error with empty index by including raw information in diff
Patrick-Beuks Jan 7, 2025
e7a6ac1
fix style error
Patrick-Beuks Jan 7, 2025
a640c6e
Merge branch 'main' into fix-empty-index
Patrick-Beuks Jan 29, 2025
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
2 changes: 1 addition & 1 deletion src/Gitonomy/Git/Commit.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,7 +62,7 @@ public function setData(array $data)
*/
public function getDiff()
{
$args = ['-r', '-p', '-m', '-M', '--no-commit-id', '--full-index', $this->revision];
$args = ['-r', '-p', '--raw', '-m', '-M', '--no-commit-id', '--full-index', $this->revision];

$diff = Diff::parse($this->repository->run('diff-tree', $args));
$diff->setRepository($this->repository);
Expand Down
8 changes: 8 additions & 0 deletions src/Gitonomy/Git/Diff/File.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -278,6 +278,10 @@ public function getOldBlob()
throw new \LogicException('Can\'t return old Blob on a creation');
}

if ($this->oldIndex === '') {
throw new \RuntimeException('Index is missing to return Blob object.');
}

return $this->repository->getBlob($this->oldIndex);
}

Expand All @@ -291,6 +295,10 @@ public function getNewBlob()
throw new \LogicException('Can\'t return new Blob on a deletion');
}

if ($this->newIndex === '') {
throw new \RuntimeException('Index is missing to return Blob object.');
}

return $this->repository->getBlob($this->newIndex);
}
}
21 changes: 19 additions & 2 deletions src/Gitonomy/Git/Parser/DiffParser.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,14 +22,31 @@ class DiffParser extends ParserBase
protected function doParse()
{
$this->files = [];
$indexes = [];
// Diff contains raw information
if (str_starts_with($this->content, ':')) {
while ($this->expects(':')) {
$this->consumeRegexp('/\d{6} \d{6} /');
$oldIndex = $this->consumeShortHash();
$this->consume(' ');
$newIndex = $this->consumeShortHash();
$this->consumeTo("\n");
$this->consumeNewLine();
$indexes[] = [$oldIndex, $newIndex];
}
$this->consumeNewLine();
} elseif (!$this->isFinished()) {
trigger_error('Using Diff::parse without raw information is deprecated. See https://github.com/gitonomy/gitlib/issues/227.', E_USER_DEPRECATED);
Copy link

@veewee veewee Dec 5, 2025 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hello there @Patrick-Beuks @lyrixx,

I'm just wondering:

Would this actually have to result in a deprecation warning?
For other tools using the DiffParser (like grumphp), we don't really care much about the raw index data.

See phpro/grumphp#1199

Copy link
Contributor Author

@Patrick-Beuks Patrick-Beuks Dec 5, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

There are edge cases for parsing the diff that would result in an incorrect parse, not finding changed files, see issue #227.
I will check the use case as you described in your ticket to see if you would have hit the same edge cases tomorrow.

Copy link
Contributor Author

@Patrick-Beuks Patrick-Beuks Dec 7, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Oke, I have checked out your code.

You have a public interface on the diff in src/Git/GitRepository.php that returns the Gitonomy diff back.
Without the --raw this contains incorrect data and to protect consumers of this function from false information, I still think this deprecation is needed.

For example this this code for the spec/Git/GitRepositorySpec.php

    public function it_can_not_get_index_without_raw_without_changes(Repository $repository): void
    {
        $rawDiff = 'diff --git a/testfile b/testfile
old mode 100644
new mode 100755
';

        $diff = @$this->createRawDiff($rawDiff);
        $diff->shouldBeAnInstanceOf(Diff::class);
        /** @var File $file */
        $file = $diff->getFiles()[0];
        $file->getNewIndex()->shouldBe('');
        $file->getOldIndex()->shouldBe('');
    }

    public function it_can_get_index_with_raw(Repository $repository): void
    {
        $rawDiff = ':100644 100755 e69de29 e69de29 M        testfile

diff --git a/testfile b/testfile
old mode 100644
new mode 100755
';
        $diff = $this->createRawDiff($rawDiff);
        $diff->shouldBeAnInstanceOf(Diff::class);
        /** @var File $file */
        $file = $diff->getFiles()[0];
        $file->getNewIndex()->shouldBe('e69de29');
        $file->getOldIndex()->shouldBe('e69de29');

    }

    public function it_can_get_index_with_changes(Repository $repository): void
    {
        $rawDiff = 'diff --git a/testfile b/testfile
index e69de29..9daeafb 100755
--- a/testfile
+++ b/testfile
@@ -0,0 +1 @@
+test
';
        $diff = $this->createRawDiff($rawDiff);
        $diff->shouldBeAnInstanceOf(Diff::class);
        /** @var File $file */
        $file = $diff->getFiles()[0];
        $file->getNewIndex()->shouldBe('e69de29');
        $file->getOldIndex()->shouldBe('9daeafb');

    }

As you can see here without raw or changes the object is in an undesirable state.

(BTW thank you for letting me take another look at this, as I have found a bug with multiple files as fileIndex never increases)

Copy link

@veewee veewee Dec 8, 2025 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for looking into it.
Sorry for my questions here, I'm just trying to understand :)

I'm trying to understand what is problematic about this, but can't really seem to find out why this should have negative impact on our application:
We don't use the new / old index anywhere. We only try to find the files from the git diff.

The way I see it:

  • A diff can have different formats. When no --raw flag is passed, it will be missing some information indeed.
  • A diff parser is responsible for parsing diffs in most common formats, but if some information is not available it just doesn't provide this information to the result of the parse.
  • It's up to the piece of code consuming the diff to figure out it has all the information it needs.

An implementation could for example check if the indexes are set from the diff to check it is a file mode change or a difference in file content as well, without parsing the raw headers.

GrumPHP uses a diff as STDIN for the run command, so we don't always have control about the exact command the diff is created with. (we do have some presets of git hooks in which we have control, but users have the ability to overwrite those.

Copy link
Contributor Author

@Patrick-Beuks Patrick-Beuks Dec 8, 2025 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Without raw Diff contains most of the times the index information. This library even expects index information always to be available on the Diff object.

If you do not use the index information I would suggest to suppress the deprecation warning and wrap the Diff object in your own object and remove the index information to make is clear to users of your library that it is not accessible.

On the otherhand, if users can write their own diff, then it might be an idea to let the deprecation stand so that they can add the raw flag

Sidenote: this function does more then just get changed files, if you just need that there might even be faster option as this does parse the entire diff

(BTW I am just defending my justification for the deprecation as an end user of the library, in the end it is up to @lyrixx if this is a valid use case)

}

$fileIndex = 0;
while (!$this->isFinished()) {
// 1. title
$vars = $this->consumeRegexp("/diff --git \"?(a\/.*?)\"? \"?(b\/.*?)\"?\n/");
$oldName = $vars[1];
$newName = $vars[2];
$oldIndex = null;
$newIndex = null;
$oldIndex = isset($indexes[$fileIndex]) ? $indexes[$fileIndex][0] : null;
$newIndex = isset($indexes[$fileIndex]) ? $indexes[$fileIndex][1] : null;
$oldMode = null;
$newMode = null;

Expand Down
2 changes: 1 addition & 1 deletion src/Gitonomy/Git/Repository.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -416,7 +416,7 @@ public function getDiff($revisions)
$revisions = new RevisionList($this, $revisions);
}

$args = array_merge(['-r', '-p', '-m', '-M', '--no-commit-id', '--full-index'], $revisions->getAsTextArray());
$args = array_merge(['-r', '-p', '--raw', '-m', '-M', '--no-commit-id', '--full-index'], $revisions->getAsTextArray());

$diff = Diff::parse($this->run('diff', $args));
$diff->setRepository($this);
Expand Down
4 changes: 2 additions & 2 deletions src/Gitonomy/Git/WorkingCopy.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,15 +50,15 @@ public function getUntrackedFiles()

public function getDiffPending()
{
$diff = Diff::parse($this->run('diff', ['-r', '-p', '-m', '-M', '--full-index']));
$diff = Diff::parse($this->run('diff', ['-r', '-p', '--raw', '-m', '-M', '--full-index']));
$diff->setRepository($this->repository);

return $diff;
}

public function getDiffStaged()
{
$diff = Diff::parse($this->run('diff', ['-r', '-p', '-m', '-M', '--full-index', '--staged']));
$diff = Diff::parse($this->run('diff', ['-r', '-p', '--raw', '-m', '-M', '--full-index', '--staged']));
$diff->setRepository($this->repository);

return $diff;
Expand Down
109 changes: 109 additions & 0 deletions tests/Gitonomy/Git/Tests/DiffTest.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,8 @@
namespace Gitonomy\Git\Tests;

use Gitonomy\Git\Diff\Diff;
use Gitonomy\Git\Diff\File;
use Gitonomy\Git\Repository;

class DiffTest extends AbstractTest
{
Expand Down Expand Up @@ -151,6 +153,113 @@ public function testWorksWithUmlauts($repository)
$this->assertSame('file_with_umlauts_\303\244\303\266\303\274', $files[0]->getNewName());
}

public function testDeleteFileWithoutRaw()
{
$deprecationCalled = false;
$self = $this;
set_error_handler(function (int $errno, string $errstr) use ($self, &$deprecationCalled): void {
$deprecationCalled = true;
$self->assertSame('Using Diff::parse without raw information is deprecated. See https://github.com/gitonomy/gitlib/issues/227.', $errstr);
}, E_USER_DEPRECATED);

$diff = Diff::parse(<<<'DIFF'
diff --git a/test b/test
deleted file mode 100644
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000

DIFF);
$firstFile = $diff->getFiles()[0];

restore_exception_handler();

$this->assertTrue($deprecationCalled);
$this->assertFalse($firstFile->isCreation());
// TODO: Enable after #226 is merged
//$this->assertTrue($firstFile->isDeletion());
//$this->assertFalse($firstFile->isChangeMode());
$this->assertSame('e69de29bb2d1d6434b8b29ae775ad8c2e48c5391', $firstFile->getOldIndex());
$this->assertNull($firstFile->getNewIndex());
}

public function testModeChangeFileWithoutRaw()
{
$deprecationCalled = false;
$self = $this;
set_error_handler(function (int $errno, string $errstr) use ($self, &$deprecationCalled): void {
$deprecationCalled = true;
$self->assertSame('Using Diff::parse without raw information is deprecated. See https://github.com/gitonomy/gitlib/issues/227.', $errstr);
}, E_USER_DEPRECATED);

$diff = Diff::parse(<<<'DIFF'
diff --git a/a.out b/a.out
old mode 100755
new mode 100644

DIFF);
$firstFile = $diff->getFiles()[0];

restore_exception_handler();

$this->assertTrue($deprecationCalled);
$this->assertFalse($firstFile->isCreation());
$this->assertFalse($firstFile->isDeletion());
$this->assertTrue($firstFile->isChangeMode());
$this->assertSame('', $firstFile->getOldIndex());
$this->assertSame('', $firstFile->getNewIndex());
}

public function testModeChangeFileWithRaw()
{
$deprecationCalled = false;
set_error_handler(function (int $errno, string $errstr) use (&$deprecationCalled): void {
$deprecationCalled = true;
}, E_USER_DEPRECATED);

$diff = Diff::parse(<<<'DIFF'
:100755 100644 d1af4b23d0cc9313e5b2d3ef2fb9696c94afaa81 d1af4b23d0cc9313e5b2d3ef2fb9696c94afaa81 M a.out

diff --git a/a.out b/a.out
old mode 100755
new mode 100644

DIFF);
$firstFile = $diff->getFiles()[0];

restore_exception_handler();

$this->assertFalse($deprecationCalled);
$this->assertFalse($firstFile->isCreation());
$this->assertFalse($firstFile->isDeletion());
$this->assertTrue($firstFile->isChangeMode());
$this->assertSame('d1af4b23d0cc9313e5b2d3ef2fb9696c94afaa81', $firstFile->getOldIndex());
$this->assertSame('d1af4b23d0cc9313e5b2d3ef2fb9696c94afaa81', $firstFile->getNewIndex());
}

public function testThrowErrorOnBlobGetWithoutIndex()
{
$repository = $this->getMockBuilder(Repository::class)->disableOriginalConstructor()->getMock();
$file = new File('oldName', 'newName', '100755', '100644', '', '', false);
$file->setRepository($repository);

try {
$file->getOldBlob();
} catch(\RuntimeException $exception) {
$this->assertSame('Index is missing to return Blob object.', $exception->getMessage());
}

try {
$file->getNewBlob();
} catch(\RuntimeException $exception) {
$this->assertSame('Index is missing to return Blob object.', $exception->getMessage());
}

$this->assertFalse($file->isCreation());
$this->assertFalse($file->isDeletion());
$this->assertTrue($file->isChangeMode());
$this->assertSame('', $file->getOldIndex());
$this->assertSame('', $file->getNewIndex());
}

public function testEmptyNewFile()
{
$diff = Diff::parse("diff --git a/test b/test\nnew file mode 100644\nindex 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391\n");
Expand Down