Skip to content

Added the possibility to read FormFields from Word2007 documents #2282

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.

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

Closed
Closed
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
147 changes: 145 additions & 2 deletions src/PhpWord/Reader/Word2007/AbstractPart.php
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,7 @@
use DOMElement;
use PhpOffice\PhpWord\ComplexType\TblWidth as TblWidthComplexType;
use PhpOffice\PhpWord\Element\AbstractContainer;
use PhpOffice\PhpWord\Element\FormField;
use PhpOffice\PhpWord\Element\TextRun;
use PhpOffice\PhpWord\Element\TrackChange;
use PhpOffice\PhpWord\PhpWord;
Expand Down Expand Up @@ -112,8 +113,47 @@ protected function readParagraph(XMLReader $xmlReader, DOMElement $domNode, $par
$headingDepth = $this->getHeadingDepth($paragraphStyle);
}

// PreserveText
if ($xmlReader->elementExists('w:r/w:instrText', $domNode)) {
if ($xmlReader->elementExists('w:r/w:fldChar/w:ffData', $domNode)) {
// FormField
$partOfFormField = false;
$formNodes = [];
$formType = null;
// $field = new FormField("type", "forntsyle", "paragraphstyle"):
$textRunContainers = $xmlReader->countElements('w:r|w:ins|w:del|w:hyperlink|w:smartTag', $domNode);
if (0 === $textRunContainers) {
$parent->addTextBreak(null, $paragraphStyle);
} else {
$nodes = $xmlReader->getElements('*', $domNode);
$paragraph = $parent->addTextRun($paragraphStyle);
foreach ($nodes as $node) {
if ($xmlReader->elementExists('w:fldChar/w:ffData', $node)) {
$partOfFormField = true;
$formNodes[] = $node;
if ($xmlReader->elementExists('w:fldChar/w:ffData/w:ddList', $node)) {
$formType = 'dropdown';
} elseif ($xmlReader->elementExists('w:fldChar/w:ffData/w:textInput', $node)) {
$formType = 'textinput';
} elseif ($xmlReader->elementExists('w:fldChar/w:ffData/w:checkBox', $node)) {
$formType = 'checkbox';
}
} elseif ($partOfFormField &&
$xmlReader->elementExists('w:fldChar', $node) &&
'end' == $xmlReader->getAttribute('w:fldCharType', $node, 'w:fldChar')
) {
$formNodes[] = $node;
$partOfFormField = false;
// Process the form fields
$this->readFormField($xmlReader, $formNodes, $paragraph, $paragraphStyle, $formType);
} elseif ($partOfFormField) {
$formNodes[] = $node;
} else {
// normal runs
$this->readRun($xmlReader, $node, $paragraph, $docPart, $paragraphStyle);
}
}
}
} elseif ($xmlReader->elementExists('w:r/w:instrText', $domNode)) {
// PreserveText
$ignoreText = false;
$textContent = '';
$fontStyle = $this->readFontStyle($xmlReader, $domNode);
Expand Down Expand Up @@ -176,6 +216,109 @@ protected function readParagraph(XMLReader $xmlReader, DOMElement $domNode, $par
}
}

/**
* @param DOMElement[] $domNodes
* @param AbstractContainer $parent
* @param mixed $paragraphStyle
* @param string $formType
*/
private function readFormField(XMLReader $xmlReader, array $domNodes, $parent, $paragraphStyle, $formType): void
{
if (!in_array($formType, ['textinput', 'checkbox', 'dropdown'])) {
return;
}

$formField = $parent->addFormField($formType, null, $paragraphStyle);
$ffData = $xmlReader->getElement('w:fldChar/w:ffData', $domNodes[0]);

foreach ($xmlReader->getElements('*', $ffData) as $node) {
/** @var DOMElement $node */
switch ($node->localName) {
case 'name':
$formField->setName($node->getAttribute('w:val'));

break;
case 'ddList':
$listEntries = [];
foreach ($xmlReader->getElements('*', $node) as $ddListNode) {
switch ($ddListNode->localName) {
case 'result':
$formField->setValue($xmlReader->getAttribute('w:val', $ddListNode));

break;
case 'default':
$formField->setDefault($xmlReader->getAttribute('w:val', $ddListNode));

break;
case 'listEntry':
$listEntries[] = $xmlReader->getAttribute('w:val', $ddListNode);

break;
}
}
$formField->setEntries($listEntries);
if (null !== $formField->getValue()) {
$formField->setText($listEntries[$formField->getValue()]);
}

break;
case 'textInput':
foreach ($xmlReader->getElements('*', $node) as $ddListNode) {
switch ($ddListNode->localName) {
case 'default':
$formField->setDefault($xmlReader->getAttribute('w:val', $ddListNode));

break;
case 'format':
case 'maxLength':
break;
}
}

break;
case 'checkBox':
foreach ($xmlReader->getElements('*', $node) as $ddListNode) {
switch ($ddListNode->localName) {
case 'default':
$formField->setDefault($xmlReader->getAttribute('w:val', $ddListNode));

break;
case 'checked':
$formField->setValue($xmlReader->getAttribute('w:val', $ddListNode));

break;
case 'size':
case 'sizeAuto':
break;
}
}

break;
}
}

if ('textinput' == $formType) {
$ignoreText = true;
$textContent = '';
foreach ($domNodes as $node) {
if ($xmlReader->elementExists('w:fldChar', $node)) {
$fldCharType = $xmlReader->getAttribute('w:fldCharType', $node, 'w:fldChar');
if ('separate' == $fldCharType) {
$ignoreText = false;
} elseif ('end' == $fldCharType) {
$ignoreText = true;
}
}

if (false === $ignoreText) {
$textContent .= $xmlReader->getValue('w:t', $node);
}
}
$formField->setValue(htmlspecialchars($textContent, ENT_QUOTES, 'UTF-8'));
$formField->setText(htmlspecialchars($textContent, ENT_QUOTES, 'UTF-8'));
}
}

/**
* Returns the depth of the Heading, returns 0 for a Title.
*
Expand Down
188 changes: 188 additions & 0 deletions tests/PhpWordTests/Reader/Word2007/ElementTest.php
Original file line number Diff line number Diff line change
Expand Up @@ -312,4 +312,192 @@ public function testReadDrawing(): void
$elements = $phpWord->getSection(0)->getElements();
self::assertInstanceOf('PhpOffice\PhpWord\Element\TextRun', $elements[0]);
}

/**
* Test reading FormField - DROPDOWN.
*/
public function testReadFormFieldDropdown(): void
{
$documentXml = '<w:p>
<w:r>
<w:t>Reference</w:t>
</w:r>
<w:r>
<w:fldChar w:fldCharType="begin">
<w:ffData>
<w:name w:val="DropDownList1"/>
<w:enabled/>
<w:calcOnExit w:val="0"/>
<w:ddList>
<w:result w:val="2"/>
<w:listEntry w:val="TBD"/>
<w:listEntry w:val="Option One"/>
<w:listEntry w:val="Option Two"/>
<w:listEntry w:val="Option Three"/>
<w:listEntry w:val="Other"/>
</w:ddList>
</w:ffData>
</w:fldChar>
</w:r>
<w:r>
<w:instrText xml:space="preserve"> FORMDROPDOWN </w:instrText>
</w:r>
<w:r>
<w:rPr>
<w:lang w:val="en-GB"/>
</w:rPr>
</w:r>
<w:r>
<w:rPr>
<w:lang w:val="en-GB"/>
</w:rPr>
<w:fldChar w:fldCharType="separate"/>
</w:r>
<w:r>
<w:rPr>
<w:lang w:val="en-GB"/>
</w:rPr>
<w:fldChar w:fldCharType="end"/>
</w:r>
</w:p>';

$phpWord = $this->getDocumentFromString(['document' => $documentXml]);

$elements = $phpWord->getSection(0)->getElements();
self::assertInstanceOf('PhpOffice\PhpWord\Element\TextRun', $elements[0]);

$subElements = $elements[0]->getElements();

self::assertInstanceOf('PhpOffice\PhpWord\Element\Text', $subElements[0]);
self::assertEquals('Reference', $subElements[0]->getText());

self::assertInstanceOf('PhpOffice\PhpWord\Element\FormField', $subElements[1]);
self::assertEquals('dropdown', $subElements[1]->getType());
self::assertEquals('DropDownList1', $subElements[1]->getName());
self::assertEquals('2', $subElements[1]->getValue());
self::assertEquals('Option Two', $subElements[1]->getText());
self::assertEquals(['TBD', 'Option One', 'Option Two', 'Option Three', 'Other'], $subElements[1]->getEntries());
}

/**
* Test reading FormField - textinput.
*/
public function testReadFormFieldTextinput(): void
{
$documentXml = '<w:p>
<w:r>
<w:t>Fieldname</w:t>
</w:r>
<w:r>
<w:fldChar w:fldCharType="begin">
<w:ffData>
<w:name w:val="TextInput2"/>
<w:enabled/>
<w:calcOnExit w:val="0"/>
<w:textInput>
<w:default w:val="TBD"/>
<w:maxLength w:val="200"/>
</w:textInput>
</w:ffData>
</w:fldChar>
</w:r>
<w:r>
<w:instrText xml:space="preserve"> FORMTEXT </w:instrText>
</w:r>
<w:r>
<w:rPr>
<w:lang w:val="en-GB"/>
</w:rPr>
</w:r>
<w:r>
<w:rPr>
<w:lang w:val="en-GB"/>
</w:rPr>
<w:fldChar w:fldCharType="separate"/>
</w:r>
<w:r w:rsidR="00807709">
<w:rPr>
<w:noProof/>
<w:lang w:val="en-GB"/>
</w:rPr>
<w:t>This is some sample text</w:t>
</w:r>
<w:r>
<w:rPr>
<w:lang w:val="en-GB"/>
</w:rPr>
<w:fldChar w:fldCharType="end"/>
</w:r>
</w:p>';

$phpWord = $this->getDocumentFromString(['document' => $documentXml]);

$elements = $phpWord->getSection(0)->getElements();
self::assertInstanceOf('PhpOffice\PhpWord\Element\TextRun', $elements[0]);

$subElements = $elements[0]->getElements();

self::assertInstanceOf('PhpOffice\PhpWord\Element\Text', $subElements[0]);
self::assertEquals('Fieldname', $subElements[0]->getText());

self::assertInstanceOf('PhpOffice\PhpWord\Element\FormField', $subElements[1]);
self::assertEquals('textinput', $subElements[1]->getType());
self::assertEquals('TextInput2', $subElements[1]->getName());
self::assertEquals('This is some sample text', $subElements[1]->getValue());
self::assertEquals('This is some sample text', $subElements[1]->getText());
}

/**
* Test reading FormField - checkbox.
*/
public function testReadFormFieldCheckbox(): void
{
$documentXml = '<w:p>
<w:pPr/>
<w:r>
<w:fldChar w:fldCharType="begin">
<w:ffData>
<w:enabled w:val="1"/>
<w:name w:val="SomeCheckbox"/>
<w:calcOnExit w:val="0"/>
<w:checkBox>
<w:sizeAuto w:val=""/>
<w:default w:val="0"/>
<w:checked w:val="0"/>
</w:checkBox>
</w:ffData>
</w:fldChar>
</w:r>
<w:r>
<w:rPr/>
<w:instrText xml:space="preserve">FORMCHECKBOX</w:instrText>
</w:r>
<w:r>
<w:rPr/>
<w:fldChar w:fldCharType="separate"/>
</w:r>
<w:r>
<w:rPr/>
<w:t xml:space="preserve"> </w:t>
</w:r>
<w:r>
<w:rPr/>
<w:fldChar w:fldCharType="end"/>
</w:r>
</w:p>';

$phpWord = $this->getDocumentFromString(['document' => $documentXml]);

$elements = $phpWord->getSection(0)->getElements();
self::assertInstanceOf('PhpOffice\PhpWord\Element\TextRun', $elements[0]);

$subElements = $elements[0]->getElements();

// $this->assertInstanceOf('PhpOffice\PhpWord\Element\Text', $subElements[0]);
// $this->assertEquals('Fieldname', $subElements[0]->getText());

self::assertInstanceOf('PhpOffice\PhpWord\Element\FormField', $subElements[0]);
self::assertEquals('checkbox', $subElements[0]->getType());
self::assertEquals('SomeCheckbox', $subElements[0]->getName());
}
}