|
| 1 | +# XML-Processor |
| 2 | + |
| 3 | +PHP XML-Processor based on XMLReader. |
| 4 | + |
| 5 | +The [`XMLProcessor`] walks through the XML-file with the `\XMLReader` and fires events on each node of the `\XMLReader`. |
| 6 | +So its ease to process huge XML files with low memory usage. |
| 7 | + |
| 8 | +## Events |
| 9 | + |
| 10 | +The following events are available: |
| 11 | + |
| 12 | +| Event | XMLReader NodeType<br>event const | react on | callback arguments | |
| 13 | +|---------------|--------------------------------------|-----------------------------------|--------------------------| |
| 14 | +| `openFile` | `XmlProcessor::EVENT_OPEN_FILE` | after open file before first read | [`NodeProcessorContext`] | |
| 15 | +| `endOfFile` | `XmlProcessor::EVENT_END_OF_FILE` | after last read before close | [`NodeProcessorContext`] | |
| 16 | +| `NodeType_0` | `\XMLReader::NONE` | No node type | [`NodeProcessorContext`] | |
| 17 | +| `NodeType_1` | `\XMLReader::ELEMENT` | Start element | [`OpenContext`] | |
| 18 | +| `NodeType_2` | `\XMLReader::ATTRIBUTE` | Attribute node | [`NodeProcessorContext`] | |
| 19 | +| `NodeType_3` | `\XMLReader::TEXT` | Text node | [`TextContext`] | |
| 20 | +| `NodeType_4` | `\XMLReader::CDATA` | CDATA node | [`NodeProcessorContext`] | |
| 21 | +| `NodeType_5` | `\XMLReader::ENTITY_REF` | Entity Reference node | [`NodeProcessorContext`] | |
| 22 | +| `NodeType_6` | `\XMLReader::ENTITY` | Entity Declaration node | [`NodeProcessorContext`] | |
| 23 | +| `NodeType_7` | `\XMLReader::PI` | Processing Instruction node | [`NodeProcessorContext`] | |
| 24 | +| `NodeType_8` | `\XMLReader::COMMENT` | Comment node | [`NodeProcessorContext`] | |
| 25 | +| `NodeType_9` | `\XMLReader::DOC` | Document node | [`NodeProcessorContext`] | |
| 26 | +| `NodeType_10` | `\XMLReader::DOC_TYPE` | Document Type node | [`NodeProcessorContext`] | |
| 27 | +| `NodeType_11` | `\XMLReader::DOC_FRAGMENT` | Document Fragment node | [`NodeProcessorContext`] | |
| 28 | +| `NodeType_12` | `\XMLReader::NOTATION` | Notation node | [`NodeProcessorContext`] | |
| 29 | +| `NodeType_13` | `\XMLReader::WHITESPACE` | Whitespace node | [`NodeProcessorContext`] | |
| 30 | +| `NodeType_14` | `\XMLReader::SIGNIFICANT_WHITESPACE` | Significant Whitespace node | [`NodeProcessorContext`] | |
| 31 | +| `NodeType_15` | `\XMLReader::END_ELEMENT` | End Element | [`CloseContext`] | |
| 32 | +| `NodeType_16` | `\XMLReader::END_ENTITY` | End Entity | [`NodeProcessorContext`] | |
| 33 | +| `NodeType_17` | `\XMLReader::XML_DECLARATION` | XML Declaration node | [`NodeProcessorContext`] | |
| 34 | + |
| 35 | +## How to use |
| 36 | + |
| 37 | +To process an XML file, you need to create a nodeProcessor class. |
| 38 | +It has to implement the [`NodeProcessorInterface`]. |
| 39 | + |
| 40 | +Where you can define `NodeProcessorInterface::getSubscribedEvents` on which events you want to react. |
| 41 | + |
| 42 | +For easier use, you can extend the [`AbstractNodeProcessor`] class and implement one of the following interfaces: |
| 43 | + |
| 44 | +| Interface | description | |
| 45 | +|---------------------------------|-------------------------------| |
| 46 | +| [`OpenNodeProcessorInterface`] | To react on opening tags | |
| 47 | +| [`CloseNodeProcessorInterface`] | To react on closing tags | |
| 48 | +| [`TextNodeProcessorInterface`] | To react on text between tags | |
| 49 | + |
| 50 | +## Example |
| 51 | + |
| 52 | +To extract all values of `<value>` nodes of the following XML: |
| 53 | + |
| 54 | +**file.xml** |
| 55 | + |
| 56 | +```xml |
| 57 | +<?xml version="1.0" encoding="UTF-8"?> |
| 58 | +<root> |
| 59 | + <value>foo</value> |
| 60 | + <value>bar</value> |
| 61 | + <value>baz</value> |
| 62 | +</root> |
| 63 | +``` |
| 64 | + |
| 65 | +Create a simple nodeProcessor class which collect all values of the `<value>` nodes. |
| 66 | + |
| 67 | +**OpenTestNodeProcessor.php** |
| 68 | + |
| 69 | +```php |
| 70 | +use Netlogix\XmlProcessor\NodeProcessor\AbstractNodeProcessor; |
| 71 | +use Netlogix\XmlProcessor\NodeProcessor\OpenNodeProcessorInterface; |
| 72 | +use Netlogix\XmlProcessor\NodeProcessor\Context\OpenContext; |
| 73 | + |
| 74 | +class OpenValueNodeProcessor extends AbstractNodeProcessor implements OpenNodeProcessorInterface |
| 75 | +{ |
| 76 | + const NODE_PATH = 'value'; |
| 77 | + private $nodeValues = []; |
| 78 | + |
| 79 | + public function openElement(OpenContext $context) |
| 80 | + { |
| 81 | + $xml = $context->getXmlProcessorContext()->getXmlReader(); |
| 82 | + $node = $xml->expand(); |
| 83 | + $this->nodeValues[] = $node->nodeValue; |
| 84 | + } |
| 85 | + |
| 86 | + function getNodeValues(): array |
| 87 | + { |
| 88 | + return $this->nodeValues; |
| 89 | + } |
| 90 | +} |
| 91 | +``` |
| 92 | + |
| 93 | +Create a new instance of the [`XmlProcessor`] class and attach the new nodeProcessor. |
| 94 | + |
| 95 | +```php |
| 96 | +require_once 'OpenTestNodeProcessor.php'; |
| 97 | + |
| 98 | +require_once 'vendor/autoload.php'; |
| 99 | + |
| 100 | +$valueNodeProcessor = new OpenValueNodeProcessor(); |
| 101 | +$processor = new XMLProcessor([$valueNodeProcessor]); |
| 102 | +$processor->processFile('file.xml'); |
| 103 | + |
| 104 | +var_dump($valueNodeProcessor->getNodeValues()); |
| 105 | +``` |
| 106 | + |
| 107 | +**result:** |
| 108 | + |
| 109 | +```php |
| 110 | +array(3) { |
| 111 | + [0]=> |
| 112 | + string(3) "foo" |
| 113 | + [1]=> |
| 114 | + string(3) "bar" |
| 115 | + [2]=> |
| 116 | + string(3) "baz" |
| 117 | +} |
| 118 | +``` |
| 119 | + |
| 120 | +[`XmlProcessor`]: src/XmlProcessor.php |
| 121 | + |
| 122 | +[`NodeProcessorInterface`]: src/NodeProcessor/NodeProcessorInterface.php |
| 123 | + |
| 124 | +[`AbstractNodeProcessor`]: src/NodeProcessor/AbstractNodeProcessor.php |
| 125 | + |
| 126 | +[`OpenNodeProcessorInterface`]: src/NodeProcessor/OpenNodeProcessorInterface.php |
| 127 | + |
| 128 | +[`CloseNodeProcessorInterface`]: src/NodeProcessor/CloseNodeProcessorInterface.php |
| 129 | + |
| 130 | +[`TextNodeProcessorInterface`]: src/NodeProcessor/TextNodeProcessorInterface.php |
| 131 | + |
| 132 | +[`NodeProcessorContext`]: src/NodeProcessor/Context/NodeProcessorContext.php |
| 133 | + |
| 134 | +[`OpenContext]: src/NodeProcessor/Context/OpenContext.php |
| 135 | + |
| 136 | +[`TextContext`]: src/NodeProcessor/Context/TextContext.php |
| 137 | + |
| 138 | +[`CloseContext`]: src/NodeProcessor/Context/CloseContext.php |
0 commit comments