revi-archive/phorge-phorge
1
0
Fork 0
mirror of https://we.phorge.it/source/phorge.git synced 2024-12-23 05:50:55 +01:00
Code Issues Releases Wiki Activity

Fix an issue where prose diffing may fail after hitting the PCRE backtracking limit

Browse source 
Summary:
Fixes T13554. For certain prose diff inputs and PCRE backtracking limits, this regular expression may back track too often and fail.

A characteristic input is "x x x x ...", i.e. many sequences where `(.*?)\s*\z` looks like it may be able to match but actually can not.

I think writing an expression which has all the behavior we'd like without this backtracking issue isn't trivial (at least, I don't think I know how to do it offhand); just use a strategy based on "trim()" insetad, which avoids any PCRE complexities here.

Test Plan: Locally, this passes the "x x x ..." test which the previous code failed. I'm not including that test because it won't reproduce across values of "pcre.backtrac_limit", PCRE versions, etc.

Maniphest Tasks: T13554

Differential Revision: https://secure.phabricator.com/D21422
This commit is contained in:
epriestley 2020-07-23 07:35:57 -07:00
parent 8f9ba48528
commit fcb75d0503
2 changed files with 68 additions and 16 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

51
src/infrastructure/diff/prose/PhutilProseDifferenceEngine.php
View file

@ -142,22 +142,9 @@ final class PhutilProseDifferenceEngine extends Phobject {
}
if ($level < 2) {
// Split pieces into separate text and whitespace sections: make one
// piece out of all the whitespace at the beginning, one piece out of
// all the actual text in the middle, and one piece out of all the
// whitespace at the end.
$matches = null;
preg_match('/^(\s*)(.*?)(\s*)\z/s', $result, $matches);
if (strlen($matches[1])) {
$results[] = $matches[1];
}
if (strlen($matches[2])) {
$results[] = $matches[2];
}
if (strlen($matches[3])) {
$results[] = $matches[3];
$trimmed_pieces = $this->trimApart($result);
foreach ($trimmed_pieces as $trimmed_piece) {
$results[] = $trimmed_piece;
}
} else {
$results[] = $result;
@ -272,4 +259,36 @@ final class PhutilProseDifferenceEngine extends Phobject {
return $blocks;
}
public static function trimApart($input) {
// Split pieces into separate text and whitespace sections: make one
// piece out of all the whitespace at the beginning, one piece out of
// all the actual text in the middle, and one piece out of all the
// whitespace at the end.
$parts = array();
$length = strlen($input);
$corpus = ltrim($input);
$l_length = strlen($corpus);
if ($l_length !== $length) {
$parts[] = substr($input, 0, $length - $l_length);
}
$corpus = rtrim($corpus);
$lr_length = strlen($corpus);
if ($lr_length) {
$parts[] = $corpus;
}
if ($lr_length !== $l_length) {
// NOTE: This will be a negative value; we're slicing from the end of
// the input string.
$parts[] = substr($input, $lr_length - $l_length);
}
return $parts;
}
}

33
src/infrastructure/diff/prose/__tests__/PhutilProseDiffTestCase.php
View file

@ -3,6 +3,39 @@
final class PhutilProseDiffTestCase
extends PhabricatorTestCase {
public function testTrimApart() {
$map = array(
'' => array(),
'a' => array('a'),
' a ' => array(
' ',
'a',
' ',
),
' a' => array(
' ',
'a',
),
'a ' => array(
'a',
' ',
),
' a b ' => array(
' ',
'a b',
' ',
),
);
foreach ($map as $input => $expect) {
$actual = PhutilProseDifferenceEngine::trimApart($input);
$this->assertEqual(
$expect,
$actual,
pht('Trim Apart: %s', $input));
}
}
public function testProseDiffsDistance() {
$this->assertProseParts(
'',