8000 [DomCrawler] Allow pipe (|) character in link tags when using Xpath expressions by nicolas-grekas · Pull Request #20235 · symfony/symfony · GitHub
[go: up one dir, main page]
Skip to content

[DomCrawler] Allow pipe (|) character in link tags when using Xpath expressions #20235

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
merged 2 commits into from
Oct 18, 2016
Merged

[DomCrawler] Allow pipe (|) character in link tags when using Xpath expressions #20235

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5b26e33
[DomCrawler] Allow pipe (|) character in link tags when using Xpath e…
klausi Oct 16, 2016
17757d8
[DomCrawler] Optimize DomCrawler::relativize()
nicolas-grekas Oct 18, 2016
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
58 changes: 45 additions & 13 deletions src/Symfony/Component/DomCrawler/Crawler.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -856,22 +856,47 @@ private function relativize($xpath)
{
$expressions = array();

$unionPattern = '/\|(?![^\[]*\])/';
// An expression which will never match to replace expressions which cannot match in the crawler
// We cannot simply drop
$nonMatchingExpression = 'a[name() = "b"]';

// Split any unions into individual expressions.
foreach (preg_split($unionPattern, $xpath) as $expression) {
$expression = trim($expression);
$parenthesis = '';
$xpathLen = strlen($xpath);
$openedBrackets = 0;
$startPosition = strspn($xpath, " \t\n\r\0\x0B");

// If the union is inside some braces, we need to preserve the opening braces and apply
// the change only inside it.
if (preg_match('/^[\(\s*]+/', $expression, $matches)) {
$parenthesis = $matches[0];
$expression = substr($expression, strlen($parenthesis));
for ($i = $startPosition; $i <= $xpathLen; ++$i) {
$i += strcspn($xpath, '"\'[]|', $i);

if ($i < $xpathLen) {
switch ($xpath[$i]) {
case '"':
case "'":
if (false === $i = strpos($xpath, $xpath[$i], $i + 1)) {
Copy link
Contributor

Choose a reason for hiding this comment

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

I wouldn't do assignments in the if condition, I think you can move the assignment just one line before.

Copy link
Member Author
@nicolas-grekas nicolas-grekas Oct 18, 2016 •
edited
Loading

Choose a reason for hiding this comment

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

On the contrary, I like dealing with the return value of strpos on the same line than it is called, to make things more readable as far as var types is concerned... so unless there is a strong push to change it, I'd personally prefer to keep it this way...

return $xpath; // The XPath expression is invalid
}
continue 2;
case '[':
++$openedBrackets;
continue 2;
case ']':
--$openedBrackets;
continue 2;
}
}
if ($openedBrackets) {
continue;
}

if ($startPosition < $xpathLen && '(' === $xpath[$startPosition]) {
// If the union is inside some braces, we need to preserve the opening braces and apply
// the change only inside it.
$j = 1 + strspn($xpath, "( \t\n\r\0\x0B", $startPosition + 1);
$parenthesis = substr($xpath, $startPosition, $j);
$startPosition += $j;
} else {
$parenthesis = '';
}
$expression = rtrim(substr($xpath, $startPosition, $i - $startPosition));

// BC for Symfony 2.4 and lower were elements were adding in a fake _root parent
if (0 === strpos($expression, '/_root/')) {
Expand All @@ -881,7 +906,7 @@ private function relativize($xpath)
}

// add prefix before absolute element selector
if (empty($expression)) {
if ('' === $expression) {
$expression = $nonMatchingExpression;
} elseif (0 === strpos($expression, '//')) {
$expression = 'descendant-or-self::'.substr($expression, 2);
Expand All @@ -899,17 +924,24 @@ private function relativize($xpath)
// '.' is the fake root element in Symfony 2.4 and lower, which is excluded from results
$expression = $nonMatchingExpression;
} elseif (0 === strpos($expression, 'descendant::')) {
$expression = 'descendant-or-self::'.substr($expression, strlen('descendant::'));
$expression = 'descendant-or-self::'.substr($expression, 12);
} elseif (preg_match('/^(ancestor|ancestor-or-self|attribute|following|following-sibling|namespace|parent|preceding|preceding-sibling)::/', $expression)) {
// the fake root has no parent, preceding or following nodes and also no attributes (even no namespace attributes)
$expression = $nonMatchingExpression;
} elseif (0 !== strpos($expression, 'descendant-or-self::')) {
$expression = 'self::'.$expression;
}
$expressions[] = $parenthesis.$expression;

if ($i === $xpathLen) {
return implode(' | ', $expressions);
}

$i += strspn($xpath, " \t\n\r\0\x0B", $i + 1);
$startPosition = $i + 1;
}

return implode(' | ', $expressions);
return $xpath; // The XPath expression is invalid
}

/**
Expand Down
5 changes: 4 additions & 1 deletion src/Symfony/Component/DomCrawler/Tests/CrawlerTest.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -387,6 +387,7 @@ public function testFilterXpathComplexQueries()
$this->assertCount(5, $crawler->filterXPath('(//a | //div)//img'));
$this->assertCount(7, $crawler->filterXPath('((//a | //div)//img | //ul)'));
$this->assertCount(7, $crawler->filterXPath('( ( //a | //div )//img | //ul )'));
$this->assertCount(1, $crawler->filterXPath("//a[./@href][((./@id = 'Klausi|Claudiu' or normalize-space(string(.)) = 'Klausi|Claudiu' or ./@title = 'Klausi|Claudiu' or ./@rel = 'Klausi|Claudiu') or .//img[./@alt = 'Klausi|Claudiu'])]"));
}

public function testFilterXPath()
Expand Down Expand Up @@ -548,7 +549,7 @@ public function testFilterXPathWithSelfAxes()

$this->assertCount(0, $crawler->filterXPath('self::a'), 'The fake root node has no "real" element name');
$this->assertCount(0, $crawler->filterXPath('self::a/img'), 'The fake root node has no "real" element name');
$this->assertCount(9, $crawler->filterXPath('self::*/a'));
$this->assertCount(10, $crawler->filterXPath('self::*/a'));
}

public function testFilter()
Expand Down Expand Up @@ -969,6 +970,8 @@ public function createTestCrawler($uri = null)

<a href="?get=param">GetLink</a>

<a href="/example">Klausi|Claudiu</a>

<form action="foo" id="FooFormId">
<input type="text" value="TextValue" name="TextName" />
<input type="submit" value="FooValue" name="FooName" id="FooId" />
Expand Down
0