EVOLUTION-MANAGER
Edit File: modification.html
<!DOCTYPE html> <html> <head> <meta charset="utf-8" /> <meta name="generator" content="pandoc" /> <meta http-equiv="X-UA-Compatible" content="IE=EDGE" /> <meta name="viewport" content="width=device-width, initial-scale=1" /> <meta name="author" content="Jim Hester" /> <meta name="date" content="2020-04-23" /> <title>Node Modification</title> <script>// Pandoc 2.9 adds attributes on both header and div. We remove the former (to // be compatible with the behavior of Pandoc < 2.8). document.addEventListener('DOMContentLoaded', function(e) { var hs = document.querySelectorAll("div.section[class*='level'] > :first-child"); var i, h, a; for (i = 0; i < hs.length; i++) { h = hs[i]; if (!/^h[1-6]$/i.test(h.tagName)) continue; // it should be a header h1-h6 a = h.attributes; while (a.length > 0) h.removeAttribute(a[0].name); } }); </script> <style type="text/css">code{white-space: pre;}</style> <style type="text/css" data-origin="pandoc"> pre > code.sourceCode { white-space: pre; position: relative; } pre > code.sourceCode > span { display: inline-block; line-height: 1.25; } pre > code.sourceCode > span:empty { height: 1.2em; } code.sourceCode > span { color: inherit; text-decoration: inherit; } div.sourceCode { margin: 1em 0; } pre.sourceCode { margin: 0; } @media screen { div.sourceCode { overflow: auto; } } @media print { pre > code.sourceCode { white-space: pre-wrap; } pre > code.sourceCode > span { text-indent: -5em; padding-left: 5em; } } pre.numberSource code { counter-reset: source-line 0; } pre.numberSource code > span { position: relative; left: -4em; counter-increment: source-line; } pre.numberSource code > span > a:first-child::before { content: counter(source-line); position: relative; left: -1em; text-align: right; vertical-align: baseline; border: none; display: inline-block; -webkit-touch-callout: none; -webkit-user-select: none; -khtml-user-select: none; -moz-user-select: none; -ms-user-select: none; user-select: none; padding: 0 4px; width: 4em; color: #aaaaaa; } pre.numberSource { margin-left: 3em; border-left: 1px solid #aaaaaa; padding-left: 4px; } div.sourceCode { } @media screen { pre > code.sourceCode > span > a:first-child::before { text-decoration: underline; } } code span.al { color: #ff0000; font-weight: bold; } /* Alert */ code span.an { color: #60a0b0; font-weight: bold; font-style: italic; } /* Annotation */ code span.at { color: #7d9029; } /* Attribute */ code span.bn { color: #40a070; } /* BaseN */ code span.bu { } /* BuiltIn */ code span.cf { color: #007020; font-weight: bold; } /* ControlFlow */ code span.ch { color: #4070a0; } /* Char */ code span.cn { color: #880000; } /* Constant */ code span.co { color: #60a0b0; font-style: italic; } /* Comment */ code span.cv { color: #60a0b0; font-weight: bold; font-style: italic; } /* CommentVar */ code span.do { color: #ba2121; font-style: italic; } /* Documentation */ code span.dt { color: #902000; } /* DataType */ code span.dv { color: #40a070; } /* DecVal */ code span.er { color: #ff0000; font-weight: bold; } /* Error */ code span.ex { } /* Extension */ code span.fl { color: #40a070; } /* Float */ code span.fu { color: #06287e; } /* Function */ code span.im { } /* Import */ code span.in { color: #60a0b0; font-weight: bold; font-style: italic; } /* Information */ code span.kw { color: #007020; font-weight: bold; } /* Keyword */ code span.op { color: #666666; } /* Operator */ code span.ot { color: #007020; } /* Other */ code span.pp { color: #bc7a00; } /* Preprocessor */ code span.sc { color: #4070a0; } /* SpecialChar */ code span.ss { color: #bb6688; } /* SpecialString */ code span.st { color: #4070a0; } /* String */ code span.va { color: #19177c; } /* Variable */ code span.vs { color: #4070a0; } /* VerbatimString */ code span.wa { color: #60a0b0; font-weight: bold; font-style: italic; } /* Warning */ </style> <script> // apply pandoc div.sourceCode style to pre.sourceCode instead (function() { var sheets = document.styleSheets; for (var i = 0; i < sheets.length; i++) { if (sheets[i].ownerNode.dataset["origin"] !== "pandoc") continue; try { var rules = sheets[i].cssRules; } catch (e) { continue; } for (var j = 0; j < rules.length; j++) { var rule = rules[j]; // check if there is a div.sourceCode rule if (rule.type !== rule.STYLE_RULE || rule.selectorText !== "div.sourceCode") continue; var style = rule.style.cssText; // check if color or background-color is set if (rule.style.color === '' && rule.style.backgroundColor === '') continue; // replace div.sourceCode by a pre.sourceCode rule sheets[i].deleteRule(j); sheets[i].insertRule('pre.sourceCode{' + style + '}', j); } } })(); </script> <style type="text/css">body { background-color: #fff; margin: 1em auto; max-width: 700px; overflow: visible; padding-left: 2em; padding-right: 2em; font-family: "Open Sans", "Helvetica Neue", Helvetica, Arial, sans-serif; font-size: 14px; line-height: 1.35; } #TOC { clear: both; margin: 0 0 10px 10px; padding: 4px; width: 400px; border: 1px solid #CCCCCC; border-radius: 5px; background-color: #f6f6f6; font-size: 13px; line-height: 1.3; } #TOC .toctitle { font-weight: bold; font-size: 15px; margin-left: 5px; } #TOC ul { padding-left: 40px; margin-left: -1.5em; margin-top: 5px; margin-bottom: 5px; } #TOC ul ul { margin-left: -2em; } #TOC li { line-height: 16px; } table { margin: 1em auto; border-width: 1px; border-color: #DDDDDD; border-style: outset; border-collapse: collapse; } table th { border-width: 2px; padding: 5px; border-style: inset; } table td { border-width: 1px; border-style: inset; line-height: 18px; padding: 5px 5px; } table, table th, table td { border-left-style: none; border-right-style: none; } table thead, table tr.even { background-color: #f7f7f7; } p { margin: 0.5em 0; } blockquote { background-color: #f6f6f6; padding: 0.25em 0.75em; } hr { border-style: solid; border: none; border-top: 1px solid #777; margin: 28px 0; } dl { margin-left: 0; } dl dd { margin-bottom: 13px; margin-left: 13px; } dl dt { font-weight: bold; } ul { margin-top: 0; } ul li { list-style: circle outside; } ul ul { margin-bottom: 0; } pre, code { background-color: #f7f7f7; border-radius: 3px; color: #333; white-space: pre-wrap; } pre { border-radius: 3px; margin: 5px 0px 10px 0px; padding: 10px; } pre:not([class]) { background-color: #f7f7f7; } code { font-family: Consolas, Monaco, 'Courier New', monospace; font-size: 85%; } p > code, li > code { padding: 2px 0px; } div.figure { text-align: center; } img { background-color: #FFFFFF; padding: 2px; border: 1px solid #DDDDDD; border-radius: 3px; border: 1px solid #CCCCCC; margin: 0 5px; } h1 { margin-top: 0; font-size: 35px; line-height: 40px; } h2 { border-bottom: 4px solid #f7f7f7; padding-top: 10px; padding-bottom: 2px; font-size: 145%; } h3 { border-bottom: 2px solid #f7f7f7; padding-top: 10px; font-size: 120%; } h4 { border-bottom: 1px solid #f7f7f7; margin-left: 8px; font-size: 105%; } h5, h6 { border-bottom: 1px solid #ccc; font-size: 105%; } a { color: #0033dd; text-decoration: none; } a:hover { color: #6666ff; } a:visited { color: #800080; } a:visited:hover { color: #BB00BB; } a[href^="http:"] { text-decoration: underline; } a[href^="https:"] { text-decoration: underline; } code > span.kw { color: #555; font-weight: bold; } code > span.dt { color: #902000; } code > span.dv { color: #40a070; } code > span.bn { color: #d14; } code > span.fl { color: #d14; } code > span.ch { color: #d14; } code > span.st { color: #d14; } code > span.co { color: #888888; font-style: italic; } code > span.ot { color: #007020; } code > span.al { color: #ff0000; font-weight: bold; } code > span.fu { color: #900; font-weight: bold; } code > span.er { color: #a61717; background-color: #e3d2d2; } </style> </head> <body> <h1 class="title toc-ignore">Node Modification</h1> <h4 class="author">Jim Hester</h4> <h4 class="date">2020-04-23</h4> <div id="modifying-existing-xml" class="section level1"> <h1>Modifying Existing XML</h1> <p>Modifying existing XML can be done in xml2 by using the replacement functions of the accessors. They all have methods for both individual <code>xml_node</code> objects as well as <code>xml_nodeset</code> objects. If a vector of values is provided it is applied piecewise over the nodeset, otherwise the value is recycled.</p> <div id="text-modification" class="section level2"> <h2>Text Modification</h2> <p>Text modification only happens on text nodes. If a given node has more than one text node only the first will be affected. If you want to modify additional text nodes you need to select them explicitly with <code>/text()</code>.</p> <div class="sourceCode" id="cb1"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb1-1"><a href="#cb1-1"></a>x <-<span class="st"> </span><span class="kw">read_xml</span>(<span class="st">"<p>This is some <b>text</b>. This is more.</p>"</span>)</span> <span id="cb1-2"><a href="#cb1-2"></a><span class="kw">xml_text</span>(x)</span> <span id="cb1-3"><a href="#cb1-3"></a><span class="co">#> [1] "This is some text. This is more."</span></span> <span id="cb1-4"><a href="#cb1-4"></a></span> <span id="cb1-5"><a href="#cb1-5"></a><span class="kw">xml_text</span>(x) <-<span class="st"> "This is some other text."</span></span> <span id="cb1-6"><a href="#cb1-6"></a><span class="kw">xml_text</span>(x)</span> <span id="cb1-7"><a href="#cb1-7"></a><span class="co">#> [1] "This is some other text.text. This is more."</span></span> <span id="cb1-8"><a href="#cb1-8"></a></span> <span id="cb1-9"><a href="#cb1-9"></a><span class="co"># You can avoid this by explicitly selecting the text node.</span></span> <span id="cb1-10"><a href="#cb1-10"></a>x <-<span class="st"> </span><span class="kw">read_xml</span>(<span class="st">"<p>This is some text. This is <b>bold!</b></p>"</span>)</span> <span id="cb1-11"><a href="#cb1-11"></a>text_only <-<span class="st"> </span><span class="kw">xml_find_all</span>(x, <span class="st">"//text()"</span>)</span> <span id="cb1-12"><a href="#cb1-12"></a></span> <span id="cb1-13"><a href="#cb1-13"></a><span class="kw">xml_text</span>(text_only) <-<span class="st"> </span><span class="kw">c</span>(<span class="st">"This is some other text. "</span>, <span class="st">"Still bold!"</span>)</span> <span id="cb1-14"><a href="#cb1-14"></a><span class="kw">xml_text</span>(x)</span> <span id="cb1-15"><a href="#cb1-15"></a><span class="co">#> [1] "This is some other text. Still bold!"</span></span> <span id="cb1-16"><a href="#cb1-16"></a><span class="kw">xml_structure</span>(x)</span> <span id="cb1-17"><a href="#cb1-17"></a><span class="co">#> <p></span></span> <span id="cb1-18"><a href="#cb1-18"></a><span class="co">#> {text}</span></span> <span id="cb1-19"><a href="#cb1-19"></a><span class="co">#> <b></span></span> <span id="cb1-20"><a href="#cb1-20"></a><span class="co">#> {text}</span></span></code></pre></div> </div> <div id="attribute-and-namespace-definition-modification" class="section level2"> <h2>Attribute and Namespace Definition Modification</h2> <p>Attributes and namespace definitions are modified one at a time with <code>xml_attr()</code> or all at once with <code>xml_attrs()</code>. In both cases using <code>NULL</code> as the value will remove the attribute completely.</p> <div class="sourceCode" id="cb2"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb2-1"><a href="#cb2-1"></a>x <-<span class="st"> </span><span class="kw">read_xml</span>(<span class="st">"<a href='invalid!'>xml2</a>"</span>)</span> <span id="cb2-2"><a href="#cb2-2"></a><span class="kw">xml_attr</span>(x, <span class="st">"href"</span>)</span> <span id="cb2-3"><a href="#cb2-3"></a><span class="co">#> [1] "invalid!"</span></span> <span id="cb2-4"><a href="#cb2-4"></a></span> <span id="cb2-5"><a href="#cb2-5"></a><span class="kw">xml_attr</span>(x, <span class="st">"href"</span>) <-<span class="st"> "https://github.com/r-lib/xml2"</span></span> <span id="cb2-6"><a href="#cb2-6"></a><span class="kw">xml_attr</span>(x, <span class="st">"href"</span>)</span> <span id="cb2-7"><a href="#cb2-7"></a><span class="co">#> [1] "https://github.com/r-lib/xml2"</span></span> <span id="cb2-8"><a href="#cb2-8"></a></span> <span id="cb2-9"><a href="#cb2-9"></a><span class="kw">xml_attrs</span>(x) <-<span class="st"> </span><span class="kw">c</span>(<span class="dt">id =</span> <span class="st">"xml2"</span>, <span class="dt">href =</span> <span class="st">"https://github.com/r-lib/xml2"</span>)</span> <span id="cb2-10"><a href="#cb2-10"></a><span class="kw">xml_attrs</span>(x)</span> <span id="cb2-11"><a href="#cb2-11"></a><span class="co">#> href id </span></span> <span id="cb2-12"><a href="#cb2-12"></a><span class="co">#> "https://github.com/r-lib/xml2" "xml2"</span></span> <span id="cb2-13"><a href="#cb2-13"></a>x</span> <span id="cb2-14"><a href="#cb2-14"></a><span class="co">#> {xml_document}</span></span> <span id="cb2-15"><a href="#cb2-15"></a><span class="co">#> <a href="https://github.com/r-lib/xml2" id="xml2"></span></span> <span id="cb2-16"><a href="#cb2-16"></a></span> <span id="cb2-17"><a href="#cb2-17"></a><span class="kw">xml_attrs</span>(x) <-<span class="st"> </span><span class="ot">NULL</span></span> <span id="cb2-18"><a href="#cb2-18"></a>x</span> <span id="cb2-19"><a href="#cb2-19"></a><span class="co">#> {xml_document}</span></span> <span id="cb2-20"><a href="#cb2-20"></a><span class="co">#> <a></span></span> <span id="cb2-21"><a href="#cb2-21"></a></span> <span id="cb2-22"><a href="#cb2-22"></a><span class="co"># Namespaces are added with as a xmlns or xmlns:prefix attribute</span></span> <span id="cb2-23"><a href="#cb2-23"></a><span class="kw">xml_attr</span>(x, <span class="st">"xmlns"</span>) <-<span class="st"> "http://foo"</span></span> <span id="cb2-24"><a href="#cb2-24"></a>x</span> <span id="cb2-25"><a href="#cb2-25"></a><span class="co">#> {xml_document}</span></span> <span id="cb2-26"><a href="#cb2-26"></a><span class="co">#> <a xmlns="http://foo"></span></span> <span id="cb2-27"><a href="#cb2-27"></a></span> <span id="cb2-28"><a href="#cb2-28"></a><span class="kw">xml_attr</span>(x, <span class="st">"xmlns:bar"</span>) <-<span class="st"> "http://bar"</span></span> <span id="cb2-29"><a href="#cb2-29"></a>x</span> <span id="cb2-30"><a href="#cb2-30"></a><span class="co">#> {xml_document}</span></span> <span id="cb2-31"><a href="#cb2-31"></a><span class="co">#> <a xmlns="http://foo" xmlns:bar="http://bar"></span></span></code></pre></div> </div> <div id="name-modification" class="section level2"> <h2>Name Modification</h2> <p>Node names are modified with <code>xml_name()</code>.</p> <div class="sourceCode" id="cb3"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb3-1"><a href="#cb3-1"></a>x <-<span class="st"> </span><span class="kw">read_xml</span>(<span class="st">"<a><b/></a>"</span>)</span> <span id="cb3-2"><a href="#cb3-2"></a>x</span> <span id="cb3-3"><a href="#cb3-3"></a><span class="co">#> {xml_document}</span></span> <span id="cb3-4"><a href="#cb3-4"></a><span class="co">#> <a></span></span> <span id="cb3-5"><a href="#cb3-5"></a><span class="co">#> [1] <b/></span></span> <span id="cb3-6"><a href="#cb3-6"></a><span class="kw">xml_name</span>(x)</span> <span id="cb3-7"><a href="#cb3-7"></a><span class="co">#> [1] "a"</span></span> <span id="cb3-8"><a href="#cb3-8"></a><span class="kw">xml_name</span>(x) <-<span class="st"> "c"</span></span> <span id="cb3-9"><a href="#cb3-9"></a>x</span> <span id="cb3-10"><a href="#cb3-10"></a><span class="co">#> {xml_document}</span></span> <span id="cb3-11"><a href="#cb3-11"></a><span class="co">#> <c></span></span> <span id="cb3-12"><a href="#cb3-12"></a><span class="co">#> [1] <b/></span></span></code></pre></div> </div> </div> <div id="node-modification" class="section level1"> <h1>Node modification</h1> <p>All of these functions have a <code>.copy</code> argument. If this is set to <code>FALSE</code> they will remove the new node from its location before inserting it into the new location. Otherwise they make a copy of the node before insertion.</p> <div id="replacing-existing-nodes" class="section level2"> <h2>Replacing existing nodes</h2> <div class="sourceCode" id="cb4"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb4-1"><a href="#cb4-1"></a>x <-<span class="st"> </span><span class="kw">read_xml</span>(<span class="st">"<parent><child>1</child><child>2<child>3</child></child></parent>"</span>)</span> <span id="cb4-2"><a href="#cb4-2"></a>children <-<span class="st"> </span><span class="kw">xml_children</span>(x)</span> <span id="cb4-3"><a href="#cb4-3"></a>t1 <-<span class="st"> </span>children[[<span class="dv">1</span>]]</span> <span id="cb4-4"><a href="#cb4-4"></a>t2 <-<span class="st"> </span>children[[<span class="dv">2</span>]]</span> <span id="cb4-5"><a href="#cb4-5"></a>t3 <-<span class="st"> </span><span class="kw">xml_children</span>(children[[<span class="dv">2</span>]])[[<span class="dv">1</span>]]</span> <span id="cb4-6"><a href="#cb4-6"></a></span> <span id="cb4-7"><a href="#cb4-7"></a><span class="kw">xml_replace</span>(t1, t3)</span> <span id="cb4-8"><a href="#cb4-8"></a><span class="co">#> {xml_node}</span></span> <span id="cb4-9"><a href="#cb4-9"></a><span class="co">#> <child></span></span> <span id="cb4-10"><a href="#cb4-10"></a>x</span> <span id="cb4-11"><a href="#cb4-11"></a><span class="co">#> {xml_document}</span></span> <span id="cb4-12"><a href="#cb4-12"></a><span class="co">#> <parent></span></span> <span id="cb4-13"><a href="#cb4-13"></a><span class="co">#> [1] <child>3</child></span></span> <span id="cb4-14"><a href="#cb4-14"></a><span class="co">#> [2] <child>2<child>3</child></child></span></span></code></pre></div> </div> <div id="add-a-sibling" class="section level2"> <h2>Add a sibling</h2> <div class="sourceCode" id="cb5"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb5-1"><a href="#cb5-1"></a>x <-<span class="st"> </span><span class="kw">read_xml</span>(<span class="st">"<parent><child>1</child><child>2<child>3</child></child></parent>"</span>)</span> <span id="cb5-2"><a href="#cb5-2"></a>children <-<span class="st"> </span><span class="kw">xml_children</span>(x)</span> <span id="cb5-3"><a href="#cb5-3"></a>t1 <-<span class="st"> </span>children[[<span class="dv">1</span>]]</span> <span id="cb5-4"><a href="#cb5-4"></a>t2 <-<span class="st"> </span>children[[<span class="dv">2</span>]]</span> <span id="cb5-5"><a href="#cb5-5"></a>t3 <-<span class="st"> </span><span class="kw">xml_children</span>(children[[<span class="dv">2</span>]])[[<span class="dv">1</span>]]</span> <span id="cb5-6"><a href="#cb5-6"></a></span> <span id="cb5-7"><a href="#cb5-7"></a><span class="kw">xml_add_sibling</span>(t1, t3)</span> <span id="cb5-8"><a href="#cb5-8"></a>x</span> <span id="cb5-9"><a href="#cb5-9"></a><span class="co">#> {xml_document}</span></span> <span id="cb5-10"><a href="#cb5-10"></a><span class="co">#> <parent></span></span> <span id="cb5-11"><a href="#cb5-11"></a><span class="co">#> [1] <child>1</child></span></span> <span id="cb5-12"><a href="#cb5-12"></a><span class="co">#> [2] <child>3</child></span></span> <span id="cb5-13"><a href="#cb5-13"></a><span class="co">#> [3] <child>2<child>3</child></child></span></span> <span id="cb5-14"><a href="#cb5-14"></a></span> <span id="cb5-15"><a href="#cb5-15"></a><span class="kw">xml_add_sibling</span>(t3, t1, <span class="dt">where =</span> <span class="st">"before"</span>)</span> <span id="cb5-16"><a href="#cb5-16"></a>x</span> <span id="cb5-17"><a href="#cb5-17"></a><span class="co">#> {xml_document}</span></span> <span id="cb5-18"><a href="#cb5-18"></a><span class="co">#> <parent></span></span> <span id="cb5-19"><a href="#cb5-19"></a><span class="co">#> [1] <child>1</child></span></span> <span id="cb5-20"><a href="#cb5-20"></a><span class="co">#> [2] <child>3</child></span></span> <span id="cb5-21"><a href="#cb5-21"></a><span class="co">#> [3] <child>2<child>3</child><child>1</child></child></span></span></code></pre></div> </div> <div id="add-a-child" class="section level2"> <h2>Add a child</h2> <div class="sourceCode" id="cb6"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb6-1"><a href="#cb6-1"></a>x <-<span class="st"> </span><span class="kw">read_xml</span>(<span class="st">"<parent><child>1</child><child>2<child>3</child></child></parent>"</span>)</span> <span id="cb6-2"><a href="#cb6-2"></a>children <-<span class="st"> </span><span class="kw">xml_children</span>(x)</span> <span id="cb6-3"><a href="#cb6-3"></a>t1 <-<span class="st"> </span>children[[<span class="dv">1</span>]]</span> <span id="cb6-4"><a href="#cb6-4"></a>t2 <-<span class="st"> </span>children[[<span class="dv">2</span>]]</span> <span id="cb6-5"><a href="#cb6-5"></a>t3 <-<span class="st"> </span><span class="kw">xml_children</span>(children[[<span class="dv">2</span>]])[[<span class="dv">1</span>]]</span> <span id="cb6-6"><a href="#cb6-6"></a></span> <span id="cb6-7"><a href="#cb6-7"></a><span class="kw">xml_add_child</span>(t1, t3)</span> <span id="cb6-8"><a href="#cb6-8"></a>x</span> <span id="cb6-9"><a href="#cb6-9"></a><span class="co">#> {xml_document}</span></span> <span id="cb6-10"><a href="#cb6-10"></a><span class="co">#> <parent></span></span> <span id="cb6-11"><a href="#cb6-11"></a><span class="co">#> [1] <child>1<child>3</child></child></span></span> <span id="cb6-12"><a href="#cb6-12"></a><span class="co">#> [2] <child>2<child>3</child></child></span></span> <span id="cb6-13"><a href="#cb6-13"></a></span> <span id="cb6-14"><a href="#cb6-14"></a><span class="kw">xml_add_child</span>(t1, <span class="kw">read_xml</span>(<span class="st">"<test/>"</span>))</span> <span id="cb6-15"><a href="#cb6-15"></a>x</span> <span id="cb6-16"><a href="#cb6-16"></a><span class="co">#> {xml_document}</span></span> <span id="cb6-17"><a href="#cb6-17"></a><span class="co">#> <parent></span></span> <span id="cb6-18"><a href="#cb6-18"></a><span class="co">#> [1] <child>1<child>3</child><test/></child></span></span> <span id="cb6-19"><a href="#cb6-19"></a><span class="co">#> [2] <child>2<child>3</child></child></span></span></code></pre></div> </div> <div id="removing-nodes" class="section level2"> <h2>Removing nodes</h2> <p>The <code>xml_remove()</code> can be used to remove a node (and its children) from a tree. The default behavior is to unlink the node from the tree, but does <em>not</em> free the memory for the node, so R objects pointing to the node are still valid.</p> <p>This allows code like the following to work without crashing R</p> <div class="sourceCode" id="cb7"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb7-1"><a href="#cb7-1"></a>x <-<span class="st"> </span><span class="kw">read_xml</span>(<span class="st">"<foo><bar><baz/></bar></foo>"</span>)</span> <span id="cb7-2"><a href="#cb7-2"></a>x1 <-<span class="st"> </span>x <span class="op">%>%</span><span class="st"> </span><span class="kw">xml_children</span>() <span class="op">%>%</span><span class="st"> </span>.[[<span class="dv">1</span>]]</span> <span id="cb7-3"><a href="#cb7-3"></a>x2 <-<span class="st"> </span>x1 <span class="op">%>%</span><span class="st"> </span><span class="kw">xml_children</span>() <span class="op">%>%</span><span class="st"> </span>.[[<span class="dv">1</span>]]</span> <span id="cb7-4"><a href="#cb7-4"></a></span> <span id="cb7-5"><a href="#cb7-5"></a><span class="kw">xml_remove</span>(x1)</span> <span id="cb7-6"><a href="#cb7-6"></a><span class="kw">rm</span>(x1)</span> <span id="cb7-7"><a href="#cb7-7"></a><span class="kw">gc</span>()</span> <span id="cb7-8"><a href="#cb7-8"></a><span class="co">#> used (Mb) gc trigger (Mb) limit (Mb) max used (Mb)</span></span> <span id="cb7-9"><a href="#cb7-9"></a><span class="co">#> Ncells 572576 30.6 1277514 68.3 NA 1277473 68.3</span></span> <span id="cb7-10"><a href="#cb7-10"></a><span class="co">#> Vcells 1102609 8.5 8388608 64.0 32768 2040863 15.6</span></span> <span id="cb7-11"><a href="#cb7-11"></a></span> <span id="cb7-12"><a href="#cb7-12"></a>x2</span> <span id="cb7-13"><a href="#cb7-13"></a><span class="co">#> {xml_node}</span></span> <span id="cb7-14"><a href="#cb7-14"></a><span class="co">#> <baz></span></span></code></pre></div> <p>If you are not planning on referencing these nodes again this memory is wasted. Calling <code>xml_remove(free = TRUE)</code> will remove the nodes <em>and</em> free the memory used to store them. <strong>Note</strong> In this case <em>any</em> node which previously pointed to the node or its children will instead be pointing to free memory and may cause R to crash. xml2 can’t figure this out for you, so it’s your responsibility to remove any objects which are no longer valid.</p> <p>In particular <code>xml_find_*()</code> results are easy to overlook, for example</p> <div class="sourceCode" id="cb8"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb8-1"><a href="#cb8-1"></a>x <-<span class="st"> </span><span class="kw">read_xml</span>(<span class="st">"<a><b /><b><b /></b></a>"</span>)</span> <span id="cb8-2"><a href="#cb8-2"></a>bees <-<span class="st"> </span><span class="kw">xml_find_all</span>(x, <span class="st">"//b"</span>)</span> <span id="cb8-3"><a href="#cb8-3"></a><span class="kw">xml_remove</span>(<span class="kw">xml_child</span>(x), <span class="dt">free =</span> <span class="ot">TRUE</span>)</span> <span id="cb8-4"><a href="#cb8-4"></a><span class="co"># bees[[1]] is no longer valid!!!</span></span> <span id="cb8-5"><a href="#cb8-5"></a><span class="kw">rm</span>(bees)</span> <span id="cb8-6"><a href="#cb8-6"></a><span class="kw">gc</span>()</span> <span id="cb8-7"><a href="#cb8-7"></a><span class="co">#> used (Mb) gc trigger (Mb) limit (Mb) max used (Mb)</span></span> <span id="cb8-8"><a href="#cb8-8"></a><span class="co">#> Ncells 572623 30.6 1277514 68.3 NA 1277473 68.3</span></span> <span id="cb8-9"><a href="#cb8-9"></a><span class="co">#> Vcells 1102660 8.5 8388608 64.0 32768 2040863 15.6</span></span></code></pre></div> </div> <div id="namespaces" class="section level2"> <h2>Namespaces</h2> <p>We want to construct a document with the following namespace layout. (From <a href="http://stackoverflow.com/questions/32939229/creating-xml-in-r-with-namespaces/32941524#32941524" class="uri">http://stackoverflow.com/questions/32939229/creating-xml-in-r-with-namespaces/32941524#32941524</a>).</p> <div class="sourceCode" id="cb9"><pre class="sourceCode xml"><code class="sourceCode xml"><span id="cb9-1"><a href="#cb9-1"></a><span class="kw"><?xml</span> version = "1.0" encoding="UTF-8"<span class="kw">?></span></span> <span id="cb9-2"><a href="#cb9-2"></a><span class="kw"><sld</span><span class="ot"> xmlns=</span><span class="st">"http://www.o.net/sld"</span></span> <span id="cb9-3"><a href="#cb9-3"></a><span class="ot"> xmlns:ogc=</span><span class="st">"http://www.o.net/ogc"</span></span> <span id="cb9-4"><a href="#cb9-4"></a><span class="ot"> xmlns:se=</span><span class="st">"http://www.o.net/se"</span></span> <span id="cb9-5"><a href="#cb9-5"></a><span class="ot"> version=</span><span class="st">"1.1.0"</span> <span class="kw">></span></span> <span id="cb9-6"><a href="#cb9-6"></a><span class="kw"><layer></span></span> <span id="cb9-7"><a href="#cb9-7"></a><span class="kw"><se:Name></span>My Layer<span class="kw"></se:Name></span></span> <span id="cb9-8"><a href="#cb9-8"></a><span class="kw"></layer></span></span> <span id="cb9-9"><a href="#cb9-9"></a><span class="kw"></sld></span></span></code></pre></div> <div class="sourceCode" id="cb10"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb10-1"><a href="#cb10-1"></a>d <-<span class="st"> </span><span class="kw">xml_new_root</span>(<span class="st">"sld"</span>,</span> <span id="cb10-2"><a href="#cb10-2"></a> <span class="dt">xmlns =</span> <span class="st">"http://www.o.net/sld"</span>,</span> <span id="cb10-3"><a href="#cb10-3"></a> <span class="st">"xmlns:ogc"</span> =<span class="st"> "http://www.o.net/ogc"</span>,</span> <span id="cb10-4"><a href="#cb10-4"></a> <span class="st">"xmlns:se"</span> =<span class="st"> "http://www.o.net/se"</span>,</span> <span id="cb10-5"><a href="#cb10-5"></a> <span class="dt">version =</span> <span class="st">"1.1.0"</span>) <span class="op">%>%</span></span> <span id="cb10-6"><a href="#cb10-6"></a><span class="st"> </span><span class="kw">xml_add_child</span>(<span class="st">"layer"</span>) <span class="op">%>%</span></span> <span id="cb10-7"><a href="#cb10-7"></a><span class="st"> </span><span class="kw">xml_add_child</span>(<span class="st">"se:Name"</span>, <span class="st">"My Layer"</span>) <span class="op">%>%</span></span> <span id="cb10-8"><a href="#cb10-8"></a><span class="st"> </span><span class="kw">xml_root</span>()</span> <span id="cb10-9"><a href="#cb10-9"></a></span> <span id="cb10-10"><a href="#cb10-10"></a>d</span> <span id="cb10-11"><a href="#cb10-11"></a><span class="co">#> {xml_document}</span></span> <span id="cb10-12"><a href="#cb10-12"></a><span class="co">#> <sld version="1.1.0" xmlns="http://www.o.net/sld" xmlns:ogc="http://www.o.net/ogc" xmlns:se="http://www.o.net/se"></span></span> <span id="cb10-13"><a href="#cb10-13"></a><span class="co">#> [1] <layer>\n <se:Name>My Layer</se:Name>\n</layer></span></span></code></pre></div> </div> </div> <!-- code folding --> <!-- dynamically load mathjax for compatibility with self-contained --> <script> (function () { var script = document.createElement("script"); script.type = "text/javascript"; script.src = "https://mathjax.rstudio.com/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML"; document.getElementsByTagName("head")[0].appendChild(script); })(); </script> </body> </html>