1 | <?php |
||
2 | /** |
||
3 | * DocX Parser |
||
4 | * |
||
5 | * For namespaces use | instead of : |
||
6 | * |
||
7 | * |
||
8 | * @author Emily Brand |
||
9 | * @license LGPL The GNU Lesser GPL (LGPL) or an MIT-like license. |
||
10 | * @see http://www.urbandictionary.com/ |
||
11 | */ |
||
12 | require_once '../src/QueryPath/QueryPath.php'; |
||
13 | $path = 'http://eabrand.com/images/test.docx'; |
||
14 | |||
15 | //$path = 'docx_document.xml'; |
||
16 | |||
17 | $data = docx2text('test.docx'); |
||
18 | |||
19 | $path = $data; |
||
20 | |||
21 | |||
22 | foreach(qp($path, 'w|p') as $qp) { |
||
23 | $qr = $qp->branch(); |
||
24 | print format($qr->find('w|r:first'), 'w|r:first').' '; |
||
25 | $qp->find('w|r:first'); |
||
26 | while($qp->next('w|r')->html() != null) { |
||
27 | $qr = $qp->branch(); |
||
28 | print format($qr->find('w|r'), 'w|r').' '; |
||
29 | // print $qp->text(); |
||
30 | } |
||
31 | print '</br>'; |
||
32 | } |
||
33 | |||
34 | /** |
||
35 | * |
||
36 | * @param QueryPath $qp |
||
37 | * @param String $findSelector |
||
38 | * @return String |
||
39 | */ |
||
40 | function format($qp, $findSelector = null) { |
||
41 | |||
42 | // Create a new branch for printing later. |
||
43 | $qr = $qp->branch(); |
||
44 | |||
45 | $text = ""; |
||
0 ignored issues
–
show
Unused Code
introduced
by
![]() |
|||
46 | |||
47 | $text = $qr->find($findSelector)->find('w|t')->text(); |
||
48 | |||
49 | $text = (checkUnderline($qp->branch())) ? '<u>'.$text.'</u>' : $text; |
||
50 | $text = (checkBold($qp->branch())) ? '<b>'.$text.'</b>' : $text; |
||
51 | |||
52 | return $text; |
||
53 | } |
||
54 | |||
55 | /** |
||
56 | * |
||
57 | * @param QueryPath $qp |
||
58 | * @return String |
||
59 | */ |
||
60 | function checkBold($qp) { |
||
61 | $qp->children("w|rPr"); |
||
62 | return ($qp->children('w|b')->html()) ? true : false; |
||
0 ignored issues
–
show
|
|||
63 | } |
||
64 | |||
65 | /** |
||
66 | * |
||
67 | * @param QueryPath $qp |
||
68 | * @return String |
||
69 | */ |
||
70 | function checkUnderline($qp) { |
||
71 | $qp->children("w|rPr"); |
||
72 | return ($qp->children('w|u')->html()) ? true : false; |
||
0 ignored issues
–
show
|
|||
73 | } |
||
74 | |||
75 | |||
76 | function docx2text($filename) { |
||
77 | return readZippedXML($filename, "word/document.xml"); |
||
78 | } |
||
79 | |||
80 | function readZippedXML($archiveFile, $dataFile) { |
||
81 | if (!class_exists('ZipArchive', false)) { |
||
82 | return "ZipArchive Class Doesn't Exist."; |
||
83 | } |
||
84 | // Create new ZIP archive |
||
85 | $zip = new ZipArchive(); |
||
86 | // Open received archive file |
||
87 | if (true === $zip->open($archiveFile)) { |
||
88 | // If done, search for the data file in the archive |
||
89 | if (($index = $zip->locateName($dataFile)) !== false) { |
||
90 | // If found, read it to the string |
||
91 | $data = $zip->getFromIndex($index); |
||
92 | // Close archive file |
||
93 | $zip->close(); |
||
94 | // Load XML from a string |
||
95 | // Skip errors and warnings |
||
96 | return $data; |
||
97 | // $xml = DOMDocument::loadXML($data, LIBXML_NOENT | LIBXML_XINCLUDE | LIBXML_NOERROR | LIBXML_NOWARNING); |
||
98 | // // Return data without XML formatting tags |
||
99 | // return strip_tags($xml->saveXML()); |
||
100 | } |
||
101 | $zip->close(); |
||
102 | } |
||
103 | |||
104 | // In case of failure return empty string |
||
105 | return $zip->getStatusString(); |
||
106 | } |
||
107 |