Blob Blame History Raw
<?xml version="1.0" encoding="ascii"?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
          "DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
<head>
  <title>lxml.html.diff</title>
  <link rel="stylesheet" href="epydoc.css" type="text/css" />
  <script type="text/javascript" src="epydoc.js"></script>
</head>

<body bgcolor="white" text="black" link="blue" vlink="#204080"
      alink="#204080">
<!-- ==================== NAVIGATION BAR ==================== -->
<table class="navbar" border="0" width="100%" cellpadding="0"
       bgcolor="#a0c0ff" cellspacing="0">
  <tr valign="middle">
  <!-- Home link -->
      <th>&nbsp;&nbsp;&nbsp;<a
        href="lxml-module.html">Home</a>&nbsp;&nbsp;&nbsp;</th>

  <!-- Tree link -->
      <th>&nbsp;&nbsp;&nbsp;<a
        href="module-tree.html">Trees</a>&nbsp;&nbsp;&nbsp;</th>

  <!-- Index link -->
      <th>&nbsp;&nbsp;&nbsp;<a
        href="identifier-index.html">Indices</a>&nbsp;&nbsp;&nbsp;</th>

  <!-- Help link -->
      <th>&nbsp;&nbsp;&nbsp;<a
        href="help.html">Help</a>&nbsp;&nbsp;&nbsp;</th>

  <!-- Project homepage -->
      <th class="navbar" align="right" width="100%">
        <table border="0" cellpadding="0" cellspacing="0">
          <tr><th class="navbar" align="center"
            ><a class="navbar" target="_top" href="/">lxml API</a></th>
          </tr></table></th>
  </tr>
</table>
<table width="100%" cellpadding="0" cellspacing="0">
  <tr valign="top">
    <td width="100%">
      <span class="breadcrumbs">
        <a href="lxml-module.html">Package&nbsp;lxml</a> ::
        <a href="lxml.html-module.html">Package&nbsp;html</a> ::
        Module&nbsp;diff
      </span>
    </td>
    <td>
      <table cellpadding="0" cellspacing="0">
        <!-- hide/show private -->
        <tr><td align="right"><span class="options">[<a href="javascript:void(0);" class="privatelink"
    onclick="toggle_private();">hide&nbsp;private</a>]</span></td></tr>
        <tr><td align="right"><span class="options"
            >[<a href="frames.html" target="_top">frames</a
            >]&nbsp;|&nbsp;<a href="lxml.html.diff-pysrc.html"
            target="_top">no&nbsp;frames</a>]</span></td></tr>
      </table>
    </td>
  </tr>
</table>
<h1 class="epydoc">Source Code for <a href="lxml.html.diff-module.html">Module lxml.html.diff</a></h1>
<pre class="py-src">
<a name="L1"></a><tt class="py-lineno">  1</tt>  <tt class="py-line"><tt class="py-keyword">import</tt> <tt class="py-name">difflib</tt> </tt>
<a name="L2"></a><tt class="py-lineno">  2</tt>  <tt class="py-line"><tt class="py-keyword">from</tt> <tt id="link-0" class="py-name" targets="Package lxml=lxml-module.html"><a title="lxml" class="py-name" href="#" onclick="return doclink('link-0', 'lxml', 'link-0');">lxml</a></tt> <tt class="py-keyword">import</tt> <tt id="link-1" class="py-name" targets="Module lxml.etree=lxml.etree-module.html,Variable lxml.sax.ElementTreeContentHandler.etree=lxml.sax.ElementTreeContentHandler-class.html#etree,Variable lxml.tests.test_elementtree.CElementTreeTestCase.etree=lxml.tests.test_elementtree.CElementTreeTestCase-class.html#etree,Variable lxml.tests.test_elementtree._ETreeTestCaseBase.etree=lxml.tests.test_elementtree._ETreeTestCaseBase-class.html#etree,Variable lxml.tests.test_elementtree._XMLPullParserTest.etree=lxml.tests.test_elementtree._XMLPullParserTest-class.html#etree,Variable lxml.tests.test_io._IOTestCaseBase.etree=lxml.tests.test_io._IOTestCaseBase-class.html#etree"><a title="lxml.etree
lxml.sax.ElementTreeContentHandler.etree
lxml.tests.test_elementtree.CElementTreeTestCase.etree
lxml.tests.test_elementtree._ETreeTestCaseBase.etree
lxml.tests.test_elementtree._XMLPullParserTest.etree
lxml.tests.test_io._IOTestCaseBase.etree" class="py-name" href="#" onclick="return doclink('link-1', 'etree', 'link-1');">etree</a></tt> </tt>
<a name="L3"></a><tt class="py-lineno">  3</tt>  <tt class="py-line"><tt class="py-keyword">from</tt> <tt id="link-2" class="py-name"><a title="lxml" class="py-name" href="#" onclick="return doclink('link-2', 'lxml', 'link-0');">lxml</a></tt><tt class="py-op">.</tt><tt id="link-3" class="py-name" targets="Package lxml.html=lxml.html-module.html,Method lxml.html.diff.href_token.html()=lxml.html.diff.href_token-class.html#html,Method lxml.html.diff.tag_token.html()=lxml.html.diff.tag_token-class.html#html,Method lxml.html.diff.token.html()=lxml.html.diff.token-class.html#html"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-3', 'html', 'link-3');">html</a></tt> <tt class="py-keyword">import</tt> <tt id="link-4" class="py-name" targets="Function lxml.html.html5parser.fragment_fromstring()=lxml.html.html5parser-module.html#fragment_fromstring"><a title="lxml.html.html5parser.fragment_fromstring" class="py-name" href="#" onclick="return doclink('link-4', 'fragment_fromstring', 'link-4');">fragment_fromstring</a></tt> </tt>
<a name="L4"></a><tt class="py-lineno">  4</tt>  <tt class="py-line"><tt class="py-keyword">import</tt> <tt class="py-name">re</tt> </tt>
<a name="L5"></a><tt class="py-lineno">  5</tt>  <tt class="py-line"> </tt>
<a name="L6"></a><tt class="py-lineno">  6</tt>  <tt class="py-line"><tt class="py-name">__all__</tt> <tt class="py-op">=</tt> <tt class="py-op">[</tt><tt class="py-string">'html_annotate'</tt><tt class="py-op">,</tt> <tt class="py-string">'htmldiff'</tt><tt class="py-op">]</tt> </tt>
<a name="L7"></a><tt class="py-lineno">  7</tt>  <tt class="py-line"> </tt>
<a name="L8"></a><tt class="py-lineno">  8</tt>  <tt class="py-line"><tt class="py-keyword">try</tt><tt class="py-op">:</tt> </tt>
<a name="L9"></a><tt class="py-lineno">  9</tt>  <tt class="py-line">    <tt class="py-keyword">from</tt> <tt id="link-5" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-5', 'html', 'link-3');">html</a></tt> <tt class="py-keyword">import</tt> <tt class="py-name">escape</tt> <tt class="py-keyword">as</tt> <tt class="py-name">html_escape</tt> </tt>
<a name="L10"></a><tt class="py-lineno"> 10</tt>  <tt class="py-line"><tt class="py-keyword">except</tt> <tt class="py-name">ImportError</tt><tt class="py-op">:</tt> </tt>
<a name="L11"></a><tt class="py-lineno"> 11</tt>  <tt class="py-line">    <tt class="py-keyword">from</tt> <tt class="py-name">cgi</tt> <tt class="py-keyword">import</tt> <tt class="py-name">escape</tt> <tt class="py-keyword">as</tt> <tt class="py-name">html_escape</tt> </tt>
<a name="L12"></a><tt class="py-lineno"> 12</tt>  <tt class="py-line"><tt class="py-keyword">try</tt><tt class="py-op">:</tt> </tt>
<a name="L13"></a><tt class="py-lineno"> 13</tt>  <tt class="py-line">    <tt class="py-name">_unicode</tt> <tt class="py-op">=</tt> <tt class="py-name">unicode</tt> </tt>
<a name="L14"></a><tt class="py-lineno"> 14</tt>  <tt class="py-line"><tt class="py-keyword">except</tt> <tt class="py-name">NameError</tt><tt class="py-op">:</tt> </tt>
<a name="L15"></a><tt class="py-lineno"> 15</tt>  <tt class="py-line">    <tt class="py-comment"># Python 3</tt> </tt>
<a name="L16"></a><tt class="py-lineno"> 16</tt>  <tt class="py-line">    <tt class="py-name">_unicode</tt> <tt class="py-op">=</tt> <tt id="link-6" class="py-name" targets="Class str=str-class.html"><a title="str" class="py-name" href="#" onclick="return doclink('link-6', 'str', 'link-6');">str</a></tt> </tt>
<a name="L17"></a><tt class="py-lineno"> 17</tt>  <tt class="py-line"><tt class="py-keyword">try</tt><tt class="py-op">:</tt> </tt>
<a name="L18"></a><tt class="py-lineno"> 18</tt>  <tt class="py-line">    <tt id="link-7" class="py-name" targets="Variable lxml.html.clean.basestring=lxml.html.clean-module.html#basestring"><a title="lxml.html.clean.basestring" class="py-name" href="#" onclick="return doclink('link-7', 'basestring', 'link-7');">basestring</a></tt> </tt>
<a name="L19"></a><tt class="py-lineno"> 19</tt>  <tt class="py-line"><tt class="py-keyword">except</tt> <tt class="py-name">NameError</tt><tt class="py-op">:</tt> </tt>
<a name="L20"></a><tt class="py-lineno"> 20</tt>  <tt class="py-line">    <tt class="py-comment"># Python 3</tt> </tt>
<a name="L21"></a><tt class="py-lineno"> 21</tt>  <tt class="py-line">    <tt id="link-8" class="py-name"><a title="lxml.html.clean.basestring" class="py-name" href="#" onclick="return doclink('link-8', 'basestring', 'link-7');">basestring</a></tt> <tt class="py-op">=</tt> <tt id="link-9" class="py-name"><a title="str" class="py-name" href="#" onclick="return doclink('link-9', 'str', 'link-6');">str</a></tt> </tt>
<a name="L22"></a><tt class="py-lineno"> 22</tt>  <tt class="py-line"> </tt>
<a name="L23"></a><tt class="py-lineno"> 23</tt>  <tt class="py-line"><tt class="py-comment">############################################################</tt> </tt>
<a name="L24"></a><tt class="py-lineno"> 24</tt>  <tt class="py-line"><tt class="py-comment">## Annotation</tt> </tt>
<a name="L25"></a><tt class="py-lineno"> 25</tt>  <tt class="py-line"><tt class="py-comment">############################################################</tt> </tt>
<a name="L26"></a><tt class="py-lineno"> 26</tt>  <tt class="py-line"> </tt>
<a name="default_markup"></a><div id="default_markup-def"><a name="L27"></a><tt class="py-lineno"> 27</tt> <a class="py-toggle" href="#" id="default_markup-toggle" onclick="return toggle('default_markup');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#default_markup">default_markup</a><tt class="py-op">(</tt><tt class="py-param">text</tt><tt class="py-op">,</tt> <tt class="py-param">version</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="default_markup-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="default_markup-expanded"><a name="L28"></a><tt class="py-lineno"> 28</tt>  <tt class="py-line">    <tt class="py-keyword">return</tt> <tt class="py-string">'&lt;span title="%s"&gt;%s&lt;/span&gt;'</tt> <tt class="py-op">%</tt> <tt class="py-op">(</tt> </tt>
<a name="L29"></a><tt class="py-lineno"> 29</tt>  <tt class="py-line">        <tt class="py-name">html_escape</tt><tt class="py-op">(</tt><tt class="py-name">_unicode</tt><tt class="py-op">(</tt><tt id="link-10" class="py-name" targets="Variable lxml.etree.iterparse.version=lxml.etree.iterparse-class.html#version"><a title="lxml.etree.iterparse.version" class="py-name" href="#" onclick="return doclink('link-10', 'version', 'link-10');">version</a></tt><tt class="py-op">)</tt><tt class="py-op">,</tt> <tt class="py-number">1</tt><tt class="py-op">)</tt><tt class="py-op">,</tt> <tt id="link-11" class="py-name" targets="Variable lxml.etree.QName.text=lxml.etree.QName-class.html#text,Variable lxml.etree._Element.text=lxml.etree._Element-class.html#text,Variable lxml.etree._Entity.text=lxml.etree._Entity-class.html#text,Variable lxml.objectify.ObjectifiedElement.text=lxml.objectify.ObjectifiedElement-class.html#text,Variable xml.etree.ElementTree.Element.text=xml.etree.ElementTree.Element-class.html#text"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-11', 'text', 'link-11');">text</a></tt><tt class="py-op">)</tt> </tt>
</div><a name="L30"></a><tt class="py-lineno"> 30</tt>  <tt class="py-line"> </tt>
<a name="html_annotate"></a><div id="html_annotate-def"><a name="L31"></a><tt class="py-lineno"> 31</tt> <a class="py-toggle" href="#" id="html_annotate-toggle" onclick="return toggle('html_annotate');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#html_annotate">html_annotate</a><tt class="py-op">(</tt><tt class="py-param">doclist</tt><tt class="py-op">,</tt> <tt class="py-param">markup</tt><tt class="py-op">=</tt><tt id="link-12" class="py-name" targets="Function lxml.html.diff.default_markup()=lxml.html.diff-module.html#default_markup"><a title="lxml.html.diff.default_markup" class="py-name" href="#" onclick="return doclink('link-12', 'default_markup', 'link-12');">default_markup</a></tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="html_annotate-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="html_annotate-expanded"><a name="L32"></a><tt class="py-lineno"> 32</tt>  <tt class="py-line">    <tt class="py-docstring">"""</tt> </tt>
<a name="L33"></a><tt class="py-lineno"> 33</tt>  <tt class="py-line"><tt class="py-docstring">    doclist should be ordered from oldest to newest, like::</tt> </tt>
<a name="L34"></a><tt class="py-lineno"> 34</tt>  <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L35"></a><tt class="py-lineno"> 35</tt>  <tt class="py-line"><tt class="py-docstring">        &gt;&gt;&gt; version1 = 'Hello World'</tt> </tt>
<a name="L36"></a><tt class="py-lineno"> 36</tt>  <tt class="py-line"><tt class="py-docstring">        &gt;&gt;&gt; version2 = 'Goodbye World'</tt> </tt>
<a name="L37"></a><tt class="py-lineno"> 37</tt>  <tt class="py-line"><tt class="py-docstring">        &gt;&gt;&gt; print(html_annotate([(version1, 'version 1'),</tt> </tt>
<a name="L38"></a><tt class="py-lineno"> 38</tt>  <tt class="py-line"><tt class="py-docstring">        ...                      (version2, 'version 2')]))</tt> </tt>
<a name="L39"></a><tt class="py-lineno"> 39</tt>  <tt class="py-line"><tt class="py-docstring">        &lt;span title="version 2"&gt;Goodbye&lt;/span&gt; &lt;span title="version 1"&gt;World&lt;/span&gt;</tt> </tt>
<a name="L40"></a><tt class="py-lineno"> 40</tt>  <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L41"></a><tt class="py-lineno"> 41</tt>  <tt class="py-line"><tt class="py-docstring">    The documents must be *fragments* (str/UTF8 or unicode), not</tt> </tt>
<a name="L42"></a><tt class="py-lineno"> 42</tt>  <tt class="py-line"><tt class="py-docstring">    complete documents</tt> </tt>
<a name="L43"></a><tt class="py-lineno"> 43</tt>  <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L44"></a><tt class="py-lineno"> 44</tt>  <tt class="py-line"><tt class="py-docstring">    The markup argument is a function to markup the spans of words.</tt> </tt>
<a name="L45"></a><tt class="py-lineno"> 45</tt>  <tt class="py-line"><tt class="py-docstring">    This function is called like markup('Hello', 'version 2'), and</tt> </tt>
<a name="L46"></a><tt class="py-lineno"> 46</tt>  <tt class="py-line"><tt class="py-docstring">    returns HTML.  The first argument is text and never includes any</tt> </tt>
<a name="L47"></a><tt class="py-lineno"> 47</tt>  <tt class="py-line"><tt class="py-docstring">    markup.  The default uses a span with a title:</tt> </tt>
<a name="L48"></a><tt class="py-lineno"> 48</tt>  <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L49"></a><tt class="py-lineno"> 49</tt>  <tt class="py-line"><tt class="py-docstring">        &gt;&gt;&gt; print(default_markup('Some Text', 'by Joe'))</tt> </tt>
<a name="L50"></a><tt class="py-lineno"> 50</tt>  <tt class="py-line"><tt class="py-docstring">        &lt;span title="by Joe"&gt;Some Text&lt;/span&gt;</tt> </tt>
<a name="L51"></a><tt class="py-lineno"> 51</tt>  <tt class="py-line"><tt class="py-docstring">    """</tt> </tt>
<a name="L52"></a><tt class="py-lineno"> 52</tt>  <tt class="py-line">    <tt class="py-comment"># The basic strategy we have is to split the documents up into</tt> </tt>
<a name="L53"></a><tt class="py-lineno"> 53</tt>  <tt class="py-line">    <tt class="py-comment"># logical tokens (which are words with attached markup).  We then</tt> </tt>
<a name="L54"></a><tt class="py-lineno"> 54</tt>  <tt class="py-line">    <tt class="py-comment"># do diffs of each of the versions to track when a token first</tt> </tt>
<a name="L55"></a><tt class="py-lineno"> 55</tt>  <tt class="py-line">    <tt class="py-comment"># appeared in the document; the annotation attached to the token</tt> </tt>
<a name="L56"></a><tt class="py-lineno"> 56</tt>  <tt class="py-line">    <tt class="py-comment"># is the version where it first appeared.</tt> </tt>
<a name="L57"></a><tt class="py-lineno"> 57</tt>  <tt class="py-line">    <tt class="py-name">tokenlist</tt> <tt class="py-op">=</tt> <tt class="py-op">[</tt><tt id="link-13" class="py-name" targets="Function lxml.html.diff.tokenize_annotated()=lxml.html.diff-module.html#tokenize_annotated"><a title="lxml.html.diff.tokenize_annotated" class="py-name" href="#" onclick="return doclink('link-13', 'tokenize_annotated', 'link-13');">tokenize_annotated</a></tt><tt class="py-op">(</tt><tt class="py-name">doc</tt><tt class="py-op">,</tt> <tt id="link-14" class="py-name"><a title="lxml.etree.iterparse.version" class="py-name" href="#" onclick="return doclink('link-14', 'version', 'link-10');">version</a></tt><tt class="py-op">)</tt> </tt>
<a name="L58"></a><tt class="py-lineno"> 58</tt>  <tt class="py-line">                 <tt class="py-keyword">for</tt> <tt class="py-name">doc</tt><tt class="py-op">,</tt> <tt id="link-15" class="py-name"><a title="lxml.etree.iterparse.version" class="py-name" href="#" onclick="return doclink('link-15', 'version', 'link-10');">version</a></tt> <tt class="py-keyword">in</tt> <tt class="py-name">doclist</tt><tt class="py-op">]</tt> </tt>
<a name="L59"></a><tt class="py-lineno"> 59</tt>  <tt class="py-line">    <tt class="py-name">cur_tokens</tt> <tt class="py-op">=</tt> <tt class="py-name">tokenlist</tt><tt class="py-op">[</tt><tt class="py-number">0</tt><tt class="py-op">]</tt> </tt>
<a name="L60"></a><tt class="py-lineno"> 60</tt>  <tt class="py-line">    <tt class="py-keyword">for</tt> <tt class="py-name">tokens</tt> <tt class="py-keyword">in</tt> <tt class="py-name">tokenlist</tt><tt class="py-op">[</tt><tt class="py-number">1</tt><tt class="py-op">:</tt><tt class="py-op">]</tt><tt class="py-op">:</tt> </tt>
<a name="L61"></a><tt class="py-lineno"> 61</tt>  <tt class="py-line">        <tt id="link-16" class="py-name" targets="Function lxml.html.diff.html_annotate_merge_annotations()=lxml.html.diff-module.html#html_annotate_merge_annotations"><a title="lxml.html.diff.html_annotate_merge_annotations" class="py-name" href="#" onclick="return doclink('link-16', 'html_annotate_merge_annotations', 'link-16');">html_annotate_merge_annotations</a></tt><tt class="py-op">(</tt><tt class="py-name">cur_tokens</tt><tt class="py-op">,</tt> <tt class="py-name">tokens</tt><tt class="py-op">)</tt> </tt>
<a name="L62"></a><tt class="py-lineno"> 62</tt>  <tt class="py-line">        <tt class="py-name">cur_tokens</tt> <tt class="py-op">=</tt> <tt class="py-name">tokens</tt> </tt>
<a name="L63"></a><tt class="py-lineno"> 63</tt>  <tt class="py-line"> </tt>
<a name="L64"></a><tt class="py-lineno"> 64</tt>  <tt class="py-line">    <tt class="py-comment"># After we've tracked all the tokens, we can combine spans of text</tt> </tt>
<a name="L65"></a><tt class="py-lineno"> 65</tt>  <tt class="py-line">    <tt class="py-comment"># that are adjacent and have the same annotation</tt> </tt>
<a name="L66"></a><tt class="py-lineno"> 66</tt>  <tt class="py-line">    <tt class="py-name">cur_tokens</tt> <tt class="py-op">=</tt> <tt id="link-17" class="py-name" targets="Function lxml.html.diff.compress_tokens()=lxml.html.diff-module.html#compress_tokens"><a title="lxml.html.diff.compress_tokens" class="py-name" href="#" onclick="return doclink('link-17', 'compress_tokens', 'link-17');">compress_tokens</a></tt><tt class="py-op">(</tt><tt class="py-name">cur_tokens</tt><tt class="py-op">)</tt> </tt>
<a name="L67"></a><tt class="py-lineno"> 67</tt>  <tt class="py-line">    <tt class="py-comment"># And finally add markup</tt> </tt>
<a name="L68"></a><tt class="py-lineno"> 68</tt>  <tt class="py-line">    <tt class="py-name">result</tt> <tt class="py-op">=</tt> <tt id="link-18" class="py-name" targets="Function lxml.html.diff.markup_serialize_tokens()=lxml.html.diff-module.html#markup_serialize_tokens"><a title="lxml.html.diff.markup_serialize_tokens" class="py-name" href="#" onclick="return doclink('link-18', 'markup_serialize_tokens', 'link-18');">markup_serialize_tokens</a></tt><tt class="py-op">(</tt><tt class="py-name">cur_tokens</tt><tt class="py-op">,</tt> <tt class="py-name">markup</tt><tt class="py-op">)</tt> </tt>
<a name="L69"></a><tt class="py-lineno"> 69</tt>  <tt class="py-line">    <tt class="py-keyword">return</tt> <tt class="py-string">''</tt><tt class="py-op">.</tt><tt class="py-name">join</tt><tt class="py-op">(</tt><tt class="py-name">result</tt><tt class="py-op">)</tt><tt class="py-op">.</tt><tt id="link-19" class="py-name" targets="Function lxml.doctestcompare.strip()=lxml.doctestcompare-module.html#strip"><a title="lxml.doctestcompare.strip" class="py-name" href="#" onclick="return doclink('link-19', 'strip', 'link-19');">strip</a></tt><tt class="py-op">(</tt><tt class="py-op">)</tt> </tt>
</div><a name="L70"></a><tt class="py-lineno"> 70</tt>  <tt class="py-line"> </tt>
<a name="tokenize_annotated"></a><div id="tokenize_annotated-def"><a name="L71"></a><tt class="py-lineno"> 71</tt> <a class="py-toggle" href="#" id="tokenize_annotated-toggle" onclick="return toggle('tokenize_annotated');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#tokenize_annotated">tokenize_annotated</a><tt class="py-op">(</tt><tt class="py-param">doc</tt><tt class="py-op">,</tt> <tt class="py-param">annotation</tt><tt class="py-op">)</tt><tt class="py-op">:</tt>  </tt>
</div><a name="L72"></a><tt class="py-lineno"> 72</tt>  <tt class="py-line">    <tt class="py-docstring">"""Tokenize a document and add an annotation attribute to each token</tt> </tt>
<a name="L73"></a><tt class="py-lineno"> 73</tt>  <tt class="py-line"><tt class="py-docstring">    """</tt> </tt>
<a name="L74"></a><tt class="py-lineno"> 74</tt>  <tt class="py-line">    <tt class="py-name">tokens</tt> <tt class="py-op">=</tt> <tt id="link-20" class="py-name" targets="Function lxml.html.diff.tokenize()=lxml.html.diff-module.html#tokenize"><a title="lxml.html.diff.tokenize" class="py-name" href="#" onclick="return doclink('link-20', 'tokenize', 'link-20');">tokenize</a></tt><tt class="py-op">(</tt><tt class="py-name">doc</tt><tt class="py-op">,</tt> <tt class="py-name">include_hrefs</tt><tt class="py-op">=</tt><tt class="py-name">False</tt><tt class="py-op">)</tt> </tt>
<a name="L75"></a><tt class="py-lineno"> 75</tt>  <tt class="py-line">    <tt class="py-keyword">for</tt> <tt class="py-name">tok</tt> <tt class="py-keyword">in</tt> <tt class="py-name">tokens</tt><tt class="py-op">:</tt>  </tt>
<a name="L76"></a><tt class="py-lineno"> 76</tt>  <tt class="py-line">        <tt class="py-name">tok</tt><tt class="py-op">.</tt><tt class="py-name">annotation</tt> <tt class="py-op">=</tt> <tt class="py-name">annotation</tt> </tt>
<a name="L77"></a><tt class="py-lineno"> 77</tt>  <tt class="py-line">    <tt class="py-keyword">return</tt> <tt class="py-name">tokens</tt> </tt>
</div><a name="L78"></a><tt class="py-lineno"> 78</tt>  <tt class="py-line"> </tt>
<a name="html_annotate_merge_annotations"></a><div id="html_annotate_merge_annotations-def"><a name="L79"></a><tt class="py-lineno"> 79</tt> <a class="py-toggle" href="#" id="html_annotate_merge_annotations-toggle" onclick="return toggle('html_annotate_merge_annotations');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#html_annotate_merge_annotations">html_annotate_merge_annotations</a><tt class="py-op">(</tt><tt class="py-param">tokens_old</tt><tt class="py-op">,</tt> <tt class="py-param">tokens_new</tt><tt class="py-op">)</tt><tt class="py-op">:</tt>  </tt>
</div><a name="L80"></a><tt class="py-lineno"> 80</tt>  <tt class="py-line">    <tt class="py-docstring">"""Merge the annotations from tokens_old into tokens_new, when the</tt> </tt>
<a name="L81"></a><tt class="py-lineno"> 81</tt>  <tt class="py-line"><tt class="py-docstring">    tokens in the new document already existed in the old document.</tt> </tt>
<a name="L82"></a><tt class="py-lineno"> 82</tt>  <tt class="py-line"><tt class="py-docstring">    """</tt> </tt>
<a name="L83"></a><tt class="py-lineno"> 83</tt>  <tt class="py-line">    <tt class="py-name">s</tt> <tt class="py-op">=</tt> <tt id="link-21" class="py-name" targets="Class lxml.html.diff.InsensitiveSequenceMatcher=lxml.html.diff.InsensitiveSequenceMatcher-class.html"><a title="lxml.html.diff.InsensitiveSequenceMatcher" class="py-name" href="#" onclick="return doclink('link-21', 'InsensitiveSequenceMatcher', 'link-21');">InsensitiveSequenceMatcher</a></tt><tt class="py-op">(</tt><tt class="py-name">a</tt><tt class="py-op">=</tt><tt class="py-name">tokens_old</tt><tt class="py-op">,</tt> <tt class="py-name">b</tt><tt class="py-op">=</tt><tt class="py-name">tokens_new</tt><tt class="py-op">)</tt> </tt>
<a name="L84"></a><tt class="py-lineno"> 84</tt>  <tt class="py-line">    <tt class="py-name">commands</tt> <tt class="py-op">=</tt> <tt class="py-name">s</tt><tt class="py-op">.</tt><tt class="py-name">get_opcodes</tt><tt class="py-op">(</tt><tt class="py-op">)</tt> </tt>
<a name="L85"></a><tt class="py-lineno"> 85</tt>  <tt class="py-line"> </tt>
<a name="L86"></a><tt class="py-lineno"> 86</tt>  <tt class="py-line">    <tt class="py-keyword">for</tt> <tt class="py-name">command</tt><tt class="py-op">,</tt> <tt class="py-name">i1</tt><tt class="py-op">,</tt> <tt class="py-name">i2</tt><tt class="py-op">,</tt> <tt class="py-name">j1</tt><tt class="py-op">,</tt> <tt class="py-name">j2</tt> <tt class="py-keyword">in</tt> <tt class="py-name">commands</tt><tt class="py-op">:</tt> </tt>
<a name="L87"></a><tt class="py-lineno"> 87</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt class="py-name">command</tt> <tt class="py-op">==</tt> <tt class="py-string">'equal'</tt><tt class="py-op">:</tt>  </tt>
<a name="L88"></a><tt class="py-lineno"> 88</tt>  <tt class="py-line">            <tt class="py-name">eq_old</tt> <tt class="py-op">=</tt> <tt class="py-name">tokens_old</tt><tt class="py-op">[</tt><tt class="py-name">i1</tt><tt class="py-op">:</tt><tt class="py-name">i2</tt><tt class="py-op">]</tt> </tt>
<a name="L89"></a><tt class="py-lineno"> 89</tt>  <tt class="py-line">            <tt class="py-name">eq_new</tt> <tt class="py-op">=</tt> <tt class="py-name">tokens_new</tt><tt class="py-op">[</tt><tt class="py-name">j1</tt><tt class="py-op">:</tt><tt class="py-name">j2</tt><tt class="py-op">]</tt> </tt>
<a name="L90"></a><tt class="py-lineno"> 90</tt>  <tt class="py-line">            <tt id="link-22" class="py-name" targets="Function lxml.html.diff.copy_annotations()=lxml.html.diff-module.html#copy_annotations"><a title="lxml.html.diff.copy_annotations" class="py-name" href="#" onclick="return doclink('link-22', 'copy_annotations', 'link-22');">copy_annotations</a></tt><tt class="py-op">(</tt><tt class="py-name">eq_old</tt><tt class="py-op">,</tt> <tt class="py-name">eq_new</tt><tt class="py-op">)</tt> </tt>
</div><a name="L91"></a><tt class="py-lineno"> 91</tt>  <tt class="py-line"> </tt>
<a name="copy_annotations"></a><div id="copy_annotations-def"><a name="L92"></a><tt class="py-lineno"> 92</tt> <a class="py-toggle" href="#" id="copy_annotations-toggle" onclick="return toggle('copy_annotations');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#copy_annotations">copy_annotations</a><tt class="py-op">(</tt><tt class="py-param">src</tt><tt class="py-op">,</tt> <tt class="py-param">dest</tt><tt class="py-op">)</tt><tt class="py-op">:</tt>  </tt>
</div><a name="L93"></a><tt class="py-lineno"> 93</tt>  <tt class="py-line">    <tt class="py-docstring">"""</tt> </tt>
<a name="L94"></a><tt class="py-lineno"> 94</tt>  <tt class="py-line"><tt class="py-docstring">    Copy annotations from the tokens listed in src to the tokens in dest</tt> </tt>
<a name="L95"></a><tt class="py-lineno"> 95</tt>  <tt class="py-line"><tt class="py-docstring">    """</tt> </tt>
<a name="L96"></a><tt class="py-lineno"> 96</tt>  <tt class="py-line">    <tt class="py-keyword">assert</tt> <tt class="py-name">len</tt><tt class="py-op">(</tt><tt class="py-name">src</tt><tt class="py-op">)</tt> <tt class="py-op">==</tt> <tt class="py-name">len</tt><tt class="py-op">(</tt><tt class="py-name">dest</tt><tt class="py-op">)</tt> </tt>
<a name="L97"></a><tt class="py-lineno"> 97</tt>  <tt class="py-line">    <tt class="py-keyword">for</tt> <tt class="py-name">src_tok</tt><tt class="py-op">,</tt> <tt class="py-name">dest_tok</tt> <tt class="py-keyword">in</tt> <tt class="py-name">zip</tt><tt class="py-op">(</tt><tt class="py-name">src</tt><tt class="py-op">,</tt> <tt class="py-name">dest</tt><tt class="py-op">)</tt><tt class="py-op">:</tt>  </tt>
<a name="L98"></a><tt class="py-lineno"> 98</tt>  <tt class="py-line">        <tt class="py-name">dest_tok</tt><tt class="py-op">.</tt><tt class="py-name">annotation</tt> <tt class="py-op">=</tt> <tt class="py-name">src_tok</tt><tt class="py-op">.</tt><tt class="py-name">annotation</tt> </tt>
</div><a name="L99"></a><tt class="py-lineno"> 99</tt>  <tt class="py-line"> </tt>
<a name="compress_tokens"></a><div id="compress_tokens-def"><a name="L100"></a><tt class="py-lineno">100</tt> <a class="py-toggle" href="#" id="compress_tokens-toggle" onclick="return toggle('compress_tokens');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#compress_tokens">compress_tokens</a><tt class="py-op">(</tt><tt class="py-param">tokens</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="compress_tokens-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="compress_tokens-expanded"><a name="L101"></a><tt class="py-lineno">101</tt>  <tt class="py-line">    <tt class="py-docstring">"""</tt> </tt>
<a name="L102"></a><tt class="py-lineno">102</tt>  <tt class="py-line"><tt class="py-docstring">    Combine adjacent tokens when there is no HTML between the tokens, </tt> </tt>
<a name="L103"></a><tt class="py-lineno">103</tt>  <tt class="py-line"><tt class="py-docstring">    and they share an annotation</tt> </tt>
<a name="L104"></a><tt class="py-lineno">104</tt>  <tt class="py-line"><tt class="py-docstring">    """</tt> </tt>
<a name="L105"></a><tt class="py-lineno">105</tt>  <tt class="py-line">    <tt class="py-name">result</tt> <tt class="py-op">=</tt> <tt class="py-op">[</tt><tt class="py-name">tokens</tt><tt class="py-op">[</tt><tt class="py-number">0</tt><tt class="py-op">]</tt><tt class="py-op">]</tt>  </tt>
<a name="L106"></a><tt class="py-lineno">106</tt>  <tt class="py-line">    <tt class="py-keyword">for</tt> <tt class="py-name">tok</tt> <tt class="py-keyword">in</tt> <tt class="py-name">tokens</tt><tt class="py-op">[</tt><tt class="py-number">1</tt><tt class="py-op">:</tt><tt class="py-op">]</tt><tt class="py-op">:</tt>  </tt>
<a name="L107"></a><tt class="py-lineno">107</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt class="py-op">(</tt><tt class="py-keyword">not</tt> <tt class="py-name">result</tt><tt class="py-op">[</tt><tt class="py-op">-</tt><tt class="py-number">1</tt><tt class="py-op">]</tt><tt class="py-op">.</tt><tt class="py-name">post_tags</tt> <tt class="py-keyword">and</tt>  </tt>
<a name="L108"></a><tt class="py-lineno">108</tt>  <tt class="py-line">            <tt class="py-keyword">not</tt> <tt class="py-name">tok</tt><tt class="py-op">.</tt><tt class="py-name">pre_tags</tt> <tt class="py-keyword">and</tt>  </tt>
<a name="L109"></a><tt class="py-lineno">109</tt>  <tt class="py-line">            <tt class="py-name">result</tt><tt class="py-op">[</tt><tt class="py-op">-</tt><tt class="py-number">1</tt><tt class="py-op">]</tt><tt class="py-op">.</tt><tt class="py-name">annotation</tt> <tt class="py-op">==</tt> <tt class="py-name">tok</tt><tt class="py-op">.</tt><tt class="py-name">annotation</tt><tt class="py-op">)</tt><tt class="py-op">:</tt>  </tt>
<a name="L110"></a><tt class="py-lineno">110</tt>  <tt class="py-line">            <tt id="link-23" class="py-name" targets="Function lxml.html.diff.compress_merge_back()=lxml.html.diff-module.html#compress_merge_back"><a title="lxml.html.diff.compress_merge_back" class="py-name" href="#" onclick="return doclink('link-23', 'compress_merge_back', 'link-23');">compress_merge_back</a></tt><tt class="py-op">(</tt><tt class="py-name">result</tt><tt class="py-op">,</tt> <tt class="py-name">tok</tt><tt class="py-op">)</tt> </tt>
<a name="L111"></a><tt class="py-lineno">111</tt>  <tt class="py-line">        <tt class="py-keyword">else</tt><tt class="py-op">:</tt>  </tt>
<a name="L112"></a><tt class="py-lineno">112</tt>  <tt class="py-line">            <tt class="py-name">result</tt><tt class="py-op">.</tt><tt id="link-24" class="py-name" targets="Method lxml.etree._Element.append()=lxml.etree._Element-class.html#append"><a title="lxml.etree._Element.append" class="py-name" href="#" onclick="return doclink('link-24', 'append', 'link-24');">append</a></tt><tt class="py-op">(</tt><tt class="py-name">tok</tt><tt class="py-op">)</tt> </tt>
<a name="L113"></a><tt class="py-lineno">113</tt>  <tt class="py-line">    <tt class="py-keyword">return</tt> <tt class="py-name">result</tt> </tt>
</div><a name="L114"></a><tt class="py-lineno">114</tt>  <tt class="py-line"> </tt>
<a name="compress_merge_back"></a><div id="compress_merge_back-def"><a name="L115"></a><tt class="py-lineno">115</tt> <a class="py-toggle" href="#" id="compress_merge_back-toggle" onclick="return toggle('compress_merge_back');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#compress_merge_back">compress_merge_back</a><tt class="py-op">(</tt><tt class="py-param">tokens</tt><tt class="py-op">,</tt> <tt class="py-param">tok</tt><tt class="py-op">)</tt><tt class="py-op">:</tt>  </tt>
</div><a name="L116"></a><tt class="py-lineno">116</tt>  <tt class="py-line">    <tt class="py-docstring">""" Merge tok into the last element of tokens (modifying the list of</tt> </tt>
<a name="L117"></a><tt class="py-lineno">117</tt>  <tt class="py-line"><tt class="py-docstring">    tokens in-place).  """</tt> </tt>
<a name="L118"></a><tt class="py-lineno">118</tt>  <tt class="py-line">    <tt class="py-name">last</tt> <tt class="py-op">=</tt> <tt class="py-name">tokens</tt><tt class="py-op">[</tt><tt class="py-op">-</tt><tt class="py-number">1</tt><tt class="py-op">]</tt> </tt>
<a name="L119"></a><tt class="py-lineno">119</tt>  <tt class="py-line">    <tt class="py-keyword">if</tt> <tt id="link-25" class="py-name" targets="Variable lxml.etree._LogEntry.type=lxml.etree._LogEntry-class.html#type,Variable lxml.html.InputElement.type=lxml.html.InputElement-class.html#type"><a title="lxml.etree._LogEntry.type
lxml.html.InputElement.type" class="py-name" href="#" onclick="return doclink('link-25', 'type', 'link-25');">type</a></tt><tt class="py-op">(</tt><tt class="py-name">last</tt><tt class="py-op">)</tt> <tt class="py-keyword">is</tt> <tt class="py-keyword">not</tt> <tt id="link-26" class="py-name" targets="Class lxml.html.diff.token=lxml.html.diff.token-class.html"><a title="lxml.html.diff.token" class="py-name" href="#" onclick="return doclink('link-26', 'token', 'link-26');">token</a></tt> <tt class="py-keyword">or</tt> <tt id="link-27" class="py-name"><a title="lxml.etree._LogEntry.type
lxml.html.InputElement.type" class="py-name" href="#" onclick="return doclink('link-27', 'type', 'link-25');">type</a></tt><tt class="py-op">(</tt><tt class="py-name">tok</tt><tt class="py-op">)</tt> <tt class="py-keyword">is</tt> <tt class="py-keyword">not</tt> <tt id="link-28" class="py-name"><a title="lxml.html.diff.token" class="py-name" href="#" onclick="return doclink('link-28', 'token', 'link-26');">token</a></tt><tt class="py-op">:</tt>  </tt>
<a name="L120"></a><tt class="py-lineno">120</tt>  <tt class="py-line">        <tt class="py-name">tokens</tt><tt class="py-op">.</tt><tt id="link-29" class="py-name"><a title="lxml.etree._Element.append" class="py-name" href="#" onclick="return doclink('link-29', 'append', 'link-24');">append</a></tt><tt class="py-op">(</tt><tt class="py-name">tok</tt><tt class="py-op">)</tt> </tt>
<a name="L121"></a><tt class="py-lineno">121</tt>  <tt class="py-line">    <tt class="py-keyword">else</tt><tt class="py-op">:</tt> </tt>
<a name="L122"></a><tt class="py-lineno">122</tt>  <tt class="py-line">        <tt id="link-30" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-30', 'text', 'link-11');">text</a></tt> <tt class="py-op">=</tt> <tt class="py-name">_unicode</tt><tt class="py-op">(</tt><tt class="py-name">last</tt><tt class="py-op">)</tt> </tt>
<a name="L123"></a><tt class="py-lineno">123</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt class="py-name">last</tt><tt class="py-op">.</tt><tt class="py-name">trailing_whitespace</tt><tt class="py-op">:</tt> </tt>
<a name="L124"></a><tt class="py-lineno">124</tt>  <tt class="py-line">            <tt id="link-31" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-31', 'text', 'link-11');">text</a></tt> <tt class="py-op">+=</tt> <tt class="py-name">last</tt><tt class="py-op">.</tt><tt class="py-name">trailing_whitespace</tt> </tt>
<a name="L125"></a><tt class="py-lineno">125</tt>  <tt class="py-line">        <tt id="link-32" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-32', 'text', 'link-11');">text</a></tt> <tt class="py-op">+=</tt> <tt class="py-name">tok</tt> </tt>
<a name="L126"></a><tt class="py-lineno">126</tt>  <tt class="py-line">        <tt class="py-name">merged</tt> <tt class="py-op">=</tt> <tt id="link-33" class="py-name"><a title="lxml.html.diff.token" class="py-name" href="#" onclick="return doclink('link-33', 'token', 'link-26');">token</a></tt><tt class="py-op">(</tt><tt id="link-34" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-34', 'text', 'link-11');">text</a></tt><tt class="py-op">,</tt> </tt>
<a name="L127"></a><tt class="py-lineno">127</tt>  <tt class="py-line">                       <tt class="py-name">pre_tags</tt><tt class="py-op">=</tt><tt class="py-name">last</tt><tt class="py-op">.</tt><tt class="py-name">pre_tags</tt><tt class="py-op">,</tt> </tt>
<a name="L128"></a><tt class="py-lineno">128</tt>  <tt class="py-line">                       <tt class="py-name">post_tags</tt><tt class="py-op">=</tt><tt class="py-name">tok</tt><tt class="py-op">.</tt><tt class="py-name">post_tags</tt><tt class="py-op">,</tt> </tt>
<a name="L129"></a><tt class="py-lineno">129</tt>  <tt class="py-line">                       <tt class="py-name">trailing_whitespace</tt><tt class="py-op">=</tt><tt class="py-name">tok</tt><tt class="py-op">.</tt><tt class="py-name">trailing_whitespace</tt><tt class="py-op">)</tt> </tt>
<a name="L130"></a><tt class="py-lineno">130</tt>  <tt class="py-line">        <tt class="py-name">merged</tt><tt class="py-op">.</tt><tt class="py-name">annotation</tt> <tt class="py-op">=</tt> <tt class="py-name">last</tt><tt class="py-op">.</tt><tt class="py-name">annotation</tt> </tt>
<a name="L131"></a><tt class="py-lineno">131</tt>  <tt class="py-line">        <tt class="py-name">tokens</tt><tt class="py-op">[</tt><tt class="py-op">-</tt><tt class="py-number">1</tt><tt class="py-op">]</tt> <tt class="py-op">=</tt> <tt class="py-name">merged</tt> </tt>
</div><a name="L132"></a><tt class="py-lineno">132</tt>  <tt class="py-line">     </tt>
<a name="markup_serialize_tokens"></a><div id="markup_serialize_tokens-def"><a name="L133"></a><tt class="py-lineno">133</tt> <a class="py-toggle" href="#" id="markup_serialize_tokens-toggle" onclick="return toggle('markup_serialize_tokens');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#markup_serialize_tokens">markup_serialize_tokens</a><tt class="py-op">(</tt><tt class="py-param">tokens</tt><tt class="py-op">,</tt> <tt class="py-param">markup_func</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="markup_serialize_tokens-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="markup_serialize_tokens-expanded"><a name="L134"></a><tt class="py-lineno">134</tt>  <tt class="py-line">    <tt class="py-docstring">"""</tt> </tt>
<a name="L135"></a><tt class="py-lineno">135</tt>  <tt class="py-line"><tt class="py-docstring">    Serialize the list of tokens into a list of text chunks, calling</tt> </tt>
<a name="L136"></a><tt class="py-lineno">136</tt>  <tt class="py-line"><tt class="py-docstring">    markup_func around text to add annotations.</tt> </tt>
<a name="L137"></a><tt class="py-lineno">137</tt>  <tt class="py-line"><tt class="py-docstring">    """</tt> </tt>
<a name="L138"></a><tt class="py-lineno">138</tt>  <tt class="py-line">    <tt class="py-keyword">for</tt> <tt id="link-35" class="py-name"><a title="lxml.html.diff.token" class="py-name" href="#" onclick="return doclink('link-35', 'token', 'link-26');">token</a></tt> <tt class="py-keyword">in</tt> <tt class="py-name">tokens</tt><tt class="py-op">:</tt> </tt>
<a name="L139"></a><tt class="py-lineno">139</tt>  <tt class="py-line">        <tt class="py-keyword">for</tt> <tt class="py-name">pre</tt> <tt class="py-keyword">in</tt> <tt id="link-36" class="py-name"><a title="lxml.html.diff.token" class="py-name" href="#" onclick="return doclink('link-36', 'token', 'link-26');">token</a></tt><tt class="py-op">.</tt><tt class="py-name">pre_tags</tt><tt class="py-op">:</tt> </tt>
<a name="L140"></a><tt class="py-lineno">140</tt>  <tt class="py-line">            <tt class="py-keyword">yield</tt> <tt class="py-name">pre</tt> </tt>
<a name="L141"></a><tt class="py-lineno">141</tt>  <tt class="py-line">        <tt id="link-37" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-37', 'html', 'link-3');">html</a></tt> <tt class="py-op">=</tt> <tt id="link-38" class="py-name"><a title="lxml.html.diff.token" class="py-name" href="#" onclick="return doclink('link-38', 'token', 'link-26');">token</a></tt><tt class="py-op">.</tt><tt id="link-39" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-39', 'html', 'link-3');">html</a></tt><tt class="py-op">(</tt><tt class="py-op">)</tt> </tt>
<a name="L142"></a><tt class="py-lineno">142</tt>  <tt class="py-line">        <tt id="link-40" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-40', 'html', 'link-3');">html</a></tt> <tt class="py-op">=</tt> <tt class="py-name">markup_func</tt><tt class="py-op">(</tt><tt id="link-41" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-41', 'html', 'link-3');">html</a></tt><tt class="py-op">,</tt> <tt id="link-42" class="py-name"><a title="lxml.html.diff.token" class="py-name" href="#" onclick="return doclink('link-42', 'token', 'link-26');">token</a></tt><tt class="py-op">.</tt><tt class="py-name">annotation</tt><tt class="py-op">)</tt> </tt>
<a name="L143"></a><tt class="py-lineno">143</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt id="link-43" class="py-name"><a title="lxml.html.diff.token" class="py-name" href="#" onclick="return doclink('link-43', 'token', 'link-26');">token</a></tt><tt class="py-op">.</tt><tt class="py-name">trailing_whitespace</tt><tt class="py-op">:</tt> </tt>
<a name="L144"></a><tt class="py-lineno">144</tt>  <tt class="py-line">            <tt id="link-44" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-44', 'html', 'link-3');">html</a></tt> <tt class="py-op">+=</tt> <tt id="link-45" class="py-name"><a title="lxml.html.diff.token" class="py-name" href="#" onclick="return doclink('link-45', 'token', 'link-26');">token</a></tt><tt class="py-op">.</tt><tt class="py-name">trailing_whitespace</tt> </tt>
<a name="L145"></a><tt class="py-lineno">145</tt>  <tt class="py-line">        <tt class="py-keyword">yield</tt> <tt id="link-46" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-46', 'html', 'link-3');">html</a></tt> </tt>
<a name="L146"></a><tt class="py-lineno">146</tt>  <tt class="py-line">        <tt class="py-keyword">for</tt> <tt class="py-name">post</tt> <tt class="py-keyword">in</tt> <tt id="link-47" class="py-name"><a title="lxml.html.diff.token" class="py-name" href="#" onclick="return doclink('link-47', 'token', 'link-26');">token</a></tt><tt class="py-op">.</tt><tt class="py-name">post_tags</tt><tt class="py-op">:</tt> </tt>
<a name="L147"></a><tt class="py-lineno">147</tt>  <tt class="py-line">            <tt class="py-keyword">yield</tt> <tt class="py-name">post</tt> </tt>
</div><a name="L148"></a><tt class="py-lineno">148</tt>  <tt class="py-line"> </tt>
<a name="L149"></a><tt class="py-lineno">149</tt>  <tt class="py-line"> </tt>
<a name="L150"></a><tt class="py-lineno">150</tt>  <tt class="py-line"><tt class="py-comment">############################################################</tt> </tt>
<a name="L151"></a><tt class="py-lineno">151</tt>  <tt class="py-line"><tt class="py-comment">## HTML Diffs</tt> </tt>
<a name="L152"></a><tt class="py-lineno">152</tt>  <tt class="py-line"><tt class="py-comment">############################################################</tt> </tt>
<a name="L153"></a><tt class="py-lineno">153</tt>  <tt class="py-line"> </tt>
<a name="htmldiff"></a><div id="htmldiff-def"><a name="L154"></a><tt class="py-lineno">154</tt> <a class="py-toggle" href="#" id="htmldiff-toggle" onclick="return toggle('htmldiff');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#htmldiff">htmldiff</a><tt class="py-op">(</tt><tt class="py-param">old_html</tt><tt class="py-op">,</tt> <tt class="py-param">new_html</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="htmldiff-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="htmldiff-expanded"><a name="L155"></a><tt class="py-lineno">155</tt>  <tt class="py-line">    <tt class="py-comment">## FIXME: this should take parsed documents too, and use their body</tt> </tt>
<a name="L156"></a><tt class="py-lineno">156</tt>  <tt class="py-line">    <tt class="py-comment">## or other content.</tt> </tt>
<a name="L157"></a><tt class="py-lineno">157</tt>  <tt class="py-line">    <tt class="py-docstring">""" Do a diff of the old and new document.  The documents are HTML</tt> </tt>
<a name="L158"></a><tt class="py-lineno">158</tt>  <tt class="py-line"><tt class="py-docstring">    *fragments* (str/UTF8 or unicode), they are not complete documents</tt> </tt>
<a name="L159"></a><tt class="py-lineno">159</tt>  <tt class="py-line"><tt class="py-docstring">    (i.e., no &lt;html&gt; tag).</tt> </tt>
<a name="L160"></a><tt class="py-lineno">160</tt>  <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L161"></a><tt class="py-lineno">161</tt>  <tt class="py-line"><tt class="py-docstring">    Returns HTML with &lt;ins&gt; and &lt;del&gt; tags added around the</tt> </tt>
<a name="L162"></a><tt class="py-lineno">162</tt>  <tt class="py-line"><tt class="py-docstring">    appropriate text.  </tt> </tt>
<a name="L163"></a><tt class="py-lineno">163</tt>  <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L164"></a><tt class="py-lineno">164</tt>  <tt class="py-line"><tt class="py-docstring">    Markup is generally ignored, with the markup from new_html</tt> </tt>
<a name="L165"></a><tt class="py-lineno">165</tt>  <tt class="py-line"><tt class="py-docstring">    preserved, and possibly some markup from old_html (though it is</tt> </tt>
<a name="L166"></a><tt class="py-lineno">166</tt>  <tt class="py-line"><tt class="py-docstring">    considered acceptable to lose some of the old markup).  Only the</tt> </tt>
<a name="L167"></a><tt class="py-lineno">167</tt>  <tt class="py-line"><tt class="py-docstring">    words in the HTML are diffed.  The exception is &lt;img&gt; tags, which</tt> </tt>
<a name="L168"></a><tt class="py-lineno">168</tt>  <tt class="py-line"><tt class="py-docstring">    are treated like words, and the href attribute of &lt;a&gt; tags, which</tt> </tt>
<a name="L169"></a><tt class="py-lineno">169</tt>  <tt class="py-line"><tt class="py-docstring">    are noted inside the tag itself when there are changes.</tt> </tt>
<a name="L170"></a><tt class="py-lineno">170</tt>  <tt class="py-line"><tt class="py-docstring">    """</tt>  </tt>
<a name="L171"></a><tt class="py-lineno">171</tt>  <tt class="py-line">    <tt class="py-name">old_html_tokens</tt> <tt class="py-op">=</tt> <tt id="link-48" class="py-name"><a title="lxml.html.diff.tokenize" class="py-name" href="#" onclick="return doclink('link-48', 'tokenize', 'link-20');">tokenize</a></tt><tt class="py-op">(</tt><tt class="py-name">old_html</tt><tt class="py-op">)</tt> </tt>
<a name="L172"></a><tt class="py-lineno">172</tt>  <tt class="py-line">    <tt class="py-name">new_html_tokens</tt> <tt class="py-op">=</tt> <tt id="link-49" class="py-name"><a title="lxml.html.diff.tokenize" class="py-name" href="#" onclick="return doclink('link-49', 'tokenize', 'link-20');">tokenize</a></tt><tt class="py-op">(</tt><tt class="py-name">new_html</tt><tt class="py-op">)</tt> </tt>
<a name="L173"></a><tt class="py-lineno">173</tt>  <tt class="py-line">    <tt class="py-name">result</tt> <tt class="py-op">=</tt> <tt id="link-50" class="py-name" targets="Function lxml.html.diff.htmldiff_tokens()=lxml.html.diff-module.html#htmldiff_tokens"><a title="lxml.html.diff.htmldiff_tokens" class="py-name" href="#" onclick="return doclink('link-50', 'htmldiff_tokens', 'link-50');">htmldiff_tokens</a></tt><tt class="py-op">(</tt><tt class="py-name">old_html_tokens</tt><tt class="py-op">,</tt> <tt class="py-name">new_html_tokens</tt><tt class="py-op">)</tt> </tt>
<a name="L174"></a><tt class="py-lineno">174</tt>  <tt class="py-line">    <tt class="py-name">result</tt> <tt class="py-op">=</tt> <tt class="py-string">''</tt><tt class="py-op">.</tt><tt class="py-name">join</tt><tt class="py-op">(</tt><tt class="py-name">result</tt><tt class="py-op">)</tt><tt class="py-op">.</tt><tt id="link-51" class="py-name"><a title="lxml.doctestcompare.strip" class="py-name" href="#" onclick="return doclink('link-51', 'strip', 'link-19');">strip</a></tt><tt class="py-op">(</tt><tt class="py-op">)</tt> </tt>
<a name="L175"></a><tt class="py-lineno">175</tt>  <tt class="py-line">    <tt class="py-keyword">return</tt> <tt id="link-52" class="py-name" targets="Function lxml.html.diff.fixup_ins_del_tags()=lxml.html.diff-module.html#fixup_ins_del_tags"><a title="lxml.html.diff.fixup_ins_del_tags" class="py-name" href="#" onclick="return doclink('link-52', 'fixup_ins_del_tags', 'link-52');">fixup_ins_del_tags</a></tt><tt class="py-op">(</tt><tt class="py-name">result</tt><tt class="py-op">)</tt> </tt>
</div><a name="L176"></a><tt class="py-lineno">176</tt>  <tt class="py-line"> </tt>
<a name="htmldiff_tokens"></a><div id="htmldiff_tokens-def"><a name="L177"></a><tt class="py-lineno">177</tt> <a class="py-toggle" href="#" id="htmldiff_tokens-toggle" onclick="return toggle('htmldiff_tokens');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#htmldiff_tokens">htmldiff_tokens</a><tt class="py-op">(</tt><tt class="py-param">html1_tokens</tt><tt class="py-op">,</tt> <tt class="py-param">html2_tokens</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="htmldiff_tokens-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="htmldiff_tokens-expanded"><a name="L178"></a><tt class="py-lineno">178</tt>  <tt class="py-line">    <tt class="py-docstring">""" Does a diff on the tokens themselves, returning a list of text</tt> </tt>
<a name="L179"></a><tt class="py-lineno">179</tt>  <tt class="py-line"><tt class="py-docstring">    chunks (not tokens).</tt> </tt>
<a name="L180"></a><tt class="py-lineno">180</tt>  <tt class="py-line"><tt class="py-docstring">    """</tt> </tt>
<a name="L181"></a><tt class="py-lineno">181</tt>  <tt class="py-line">    <tt class="py-comment"># There are several passes as we do the differences.  The tokens</tt> </tt>
<a name="L182"></a><tt class="py-lineno">182</tt>  <tt class="py-line">    <tt class="py-comment"># isolate the portion of the content we care to diff; difflib does</tt> </tt>
<a name="L183"></a><tt class="py-lineno">183</tt>  <tt class="py-line">    <tt class="py-comment"># all the actual hard work at that point.  </tt> </tt>
<a name="L184"></a><tt class="py-lineno">184</tt>  <tt class="py-line">    <tt class="py-comment">#</tt> </tt>
<a name="L185"></a><tt class="py-lineno">185</tt>  <tt class="py-line">    <tt class="py-comment"># Then we must create a valid document from pieces of both the old</tt> </tt>
<a name="L186"></a><tt class="py-lineno">186</tt>  <tt class="py-line">    <tt class="py-comment"># document and the new document.  We generally prefer to take</tt> </tt>
<a name="L187"></a><tt class="py-lineno">187</tt>  <tt class="py-line">    <tt class="py-comment"># markup from the new document, and only do a best effort attempt</tt> </tt>
<a name="L188"></a><tt class="py-lineno">188</tt>  <tt class="py-line">    <tt class="py-comment"># to keep markup from the old document; anything that we can't</tt> </tt>
<a name="L189"></a><tt class="py-lineno">189</tt>  <tt class="py-line">    <tt class="py-comment"># resolve we throw away.  Also we try to put the deletes as close</tt> </tt>
<a name="L190"></a><tt class="py-lineno">190</tt>  <tt class="py-line">    <tt class="py-comment"># to the location where we think they would have been -- because</tt> </tt>
<a name="L191"></a><tt class="py-lineno">191</tt>  <tt class="py-line">    <tt class="py-comment"># we are only keeping the markup from the new document, it can be</tt> </tt>
<a name="L192"></a><tt class="py-lineno">192</tt>  <tt class="py-line">    <tt class="py-comment"># fuzzy where in the new document the old text would have gone.</tt> </tt>
<a name="L193"></a><tt class="py-lineno">193</tt>  <tt class="py-line">    <tt class="py-comment"># Again we just do a best effort attempt.</tt> </tt>
<a name="L194"></a><tt class="py-lineno">194</tt>  <tt class="py-line">    <tt class="py-name">s</tt> <tt class="py-op">=</tt> <tt id="link-53" class="py-name"><a title="lxml.html.diff.InsensitiveSequenceMatcher" class="py-name" href="#" onclick="return doclink('link-53', 'InsensitiveSequenceMatcher', 'link-21');">InsensitiveSequenceMatcher</a></tt><tt class="py-op">(</tt><tt class="py-name">a</tt><tt class="py-op">=</tt><tt class="py-name">html1_tokens</tt><tt class="py-op">,</tt> <tt class="py-name">b</tt><tt class="py-op">=</tt><tt class="py-name">html2_tokens</tt><tt class="py-op">)</tt> </tt>
<a name="L195"></a><tt class="py-lineno">195</tt>  <tt class="py-line">    <tt class="py-name">commands</tt> <tt class="py-op">=</tt> <tt class="py-name">s</tt><tt class="py-op">.</tt><tt class="py-name">get_opcodes</tt><tt class="py-op">(</tt><tt class="py-op">)</tt> </tt>
<a name="L196"></a><tt class="py-lineno">196</tt>  <tt class="py-line">    <tt class="py-name">result</tt> <tt class="py-op">=</tt> <tt class="py-op">[</tt><tt class="py-op">]</tt> </tt>
<a name="L197"></a><tt class="py-lineno">197</tt>  <tt class="py-line">    <tt class="py-keyword">for</tt> <tt class="py-name">command</tt><tt class="py-op">,</tt> <tt class="py-name">i1</tt><tt class="py-op">,</tt> <tt class="py-name">i2</tt><tt class="py-op">,</tt> <tt class="py-name">j1</tt><tt class="py-op">,</tt> <tt class="py-name">j2</tt> <tt class="py-keyword">in</tt> <tt class="py-name">commands</tt><tt class="py-op">:</tt> </tt>
<a name="L198"></a><tt class="py-lineno">198</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt class="py-name">command</tt> <tt class="py-op">==</tt> <tt class="py-string">'equal'</tt><tt class="py-op">:</tt> </tt>
<a name="L199"></a><tt class="py-lineno">199</tt>  <tt class="py-line">            <tt class="py-name">result</tt><tt class="py-op">.</tt><tt id="link-54" class="py-name" targets="Method lxml.etree._Element.extend()=lxml.etree._Element-class.html#extend"><a title="lxml.etree._Element.extend" class="py-name" href="#" onclick="return doclink('link-54', 'extend', 'link-54');">extend</a></tt><tt class="py-op">(</tt><tt id="link-55" class="py-name" targets="Function lxml.html.diff.expand_tokens()=lxml.html.diff-module.html#expand_tokens"><a title="lxml.html.diff.expand_tokens" class="py-name" href="#" onclick="return doclink('link-55', 'expand_tokens', 'link-55');">expand_tokens</a></tt><tt class="py-op">(</tt><tt class="py-name">html2_tokens</tt><tt class="py-op">[</tt><tt class="py-name">j1</tt><tt class="py-op">:</tt><tt class="py-name">j2</tt><tt class="py-op">]</tt><tt class="py-op">,</tt> <tt class="py-name">equal</tt><tt class="py-op">=</tt><tt class="py-name">True</tt><tt class="py-op">)</tt><tt class="py-op">)</tt> </tt>
<a name="L200"></a><tt class="py-lineno">200</tt>  <tt class="py-line">            <tt class="py-keyword">continue</tt> </tt>
<a name="L201"></a><tt class="py-lineno">201</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt class="py-name">command</tt> <tt class="py-op">==</tt> <tt class="py-string">'insert'</tt> <tt class="py-keyword">or</tt> <tt class="py-name">command</tt> <tt class="py-op">==</tt> <tt class="py-string">'replace'</tt><tt class="py-op">:</tt> </tt>
<a name="L202"></a><tt class="py-lineno">202</tt>  <tt class="py-line">            <tt class="py-name">ins_tokens</tt> <tt class="py-op">=</tt> <tt id="link-56" class="py-name"><a title="lxml.html.diff.expand_tokens" class="py-name" href="#" onclick="return doclink('link-56', 'expand_tokens', 'link-55');">expand_tokens</a></tt><tt class="py-op">(</tt><tt class="py-name">html2_tokens</tt><tt class="py-op">[</tt><tt class="py-name">j1</tt><tt class="py-op">:</tt><tt class="py-name">j2</tt><tt class="py-op">]</tt><tt class="py-op">)</tt> </tt>
<a name="L203"></a><tt class="py-lineno">203</tt>  <tt class="py-line">            <tt id="link-57" class="py-name" targets="Function lxml.html.diff.merge_insert()=lxml.html.diff-module.html#merge_insert"><a title="lxml.html.diff.merge_insert" class="py-name" href="#" onclick="return doclink('link-57', 'merge_insert', 'link-57');">merge_insert</a></tt><tt class="py-op">(</tt><tt class="py-name">ins_tokens</tt><tt class="py-op">,</tt> <tt class="py-name">result</tt><tt class="py-op">)</tt> </tt>
<a name="L204"></a><tt class="py-lineno">204</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt class="py-name">command</tt> <tt class="py-op">==</tt> <tt class="py-string">'delete'</tt> <tt class="py-keyword">or</tt> <tt class="py-name">command</tt> <tt class="py-op">==</tt> <tt class="py-string">'replace'</tt><tt class="py-op">:</tt> </tt>
<a name="L205"></a><tt class="py-lineno">205</tt>  <tt class="py-line">            <tt class="py-name">del_tokens</tt> <tt class="py-op">=</tt> <tt id="link-58" class="py-name"><a title="lxml.html.diff.expand_tokens" class="py-name" href="#" onclick="return doclink('link-58', 'expand_tokens', 'link-55');">expand_tokens</a></tt><tt class="py-op">(</tt><tt class="py-name">html1_tokens</tt><tt class="py-op">[</tt><tt class="py-name">i1</tt><tt class="py-op">:</tt><tt class="py-name">i2</tt><tt class="py-op">]</tt><tt class="py-op">)</tt> </tt>
<a name="L206"></a><tt class="py-lineno">206</tt>  <tt class="py-line">            <tt id="link-59" class="py-name" targets="Function lxml.html.diff.merge_delete()=lxml.html.diff-module.html#merge_delete"><a title="lxml.html.diff.merge_delete" class="py-name" href="#" onclick="return doclink('link-59', 'merge_delete', 'link-59');">merge_delete</a></tt><tt class="py-op">(</tt><tt class="py-name">del_tokens</tt><tt class="py-op">,</tt> <tt class="py-name">result</tt><tt class="py-op">)</tt> </tt>
<a name="L207"></a><tt class="py-lineno">207</tt>  <tt class="py-line">    <tt class="py-comment"># If deletes were inserted directly as &lt;del&gt; then we'd have an</tt> </tt>
<a name="L208"></a><tt class="py-lineno">208</tt>  <tt class="py-line">    <tt class="py-comment"># invalid document at this point.  Instead we put in special</tt> </tt>
<a name="L209"></a><tt class="py-lineno">209</tt>  <tt class="py-line">    <tt class="py-comment"># markers, and when the complete diffed document has been created</tt> </tt>
<a name="L210"></a><tt class="py-lineno">210</tt>  <tt class="py-line">    <tt class="py-comment"># we try to move the deletes around and resolve any problems.</tt> </tt>
<a name="L211"></a><tt class="py-lineno">211</tt>  <tt class="py-line">    <tt class="py-name">result</tt> <tt class="py-op">=</tt> <tt id="link-60" class="py-name" targets="Function lxml.html.diff.cleanup_delete()=lxml.html.diff-module.html#cleanup_delete"><a title="lxml.html.diff.cleanup_delete" class="py-name" href="#" onclick="return doclink('link-60', 'cleanup_delete', 'link-60');">cleanup_delete</a></tt><tt class="py-op">(</tt><tt class="py-name">result</tt><tt class="py-op">)</tt> </tt>
<a name="L212"></a><tt class="py-lineno">212</tt>  <tt class="py-line"> </tt>
<a name="L213"></a><tt class="py-lineno">213</tt>  <tt class="py-line">    <tt class="py-keyword">return</tt> <tt class="py-name">result</tt> </tt>
</div><a name="L214"></a><tt class="py-lineno">214</tt>  <tt class="py-line"> </tt>
<a name="expand_tokens"></a><div id="expand_tokens-def"><a name="L215"></a><tt class="py-lineno">215</tt> <a class="py-toggle" href="#" id="expand_tokens-toggle" onclick="return toggle('expand_tokens');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#expand_tokens">expand_tokens</a><tt class="py-op">(</tt><tt class="py-param">tokens</tt><tt class="py-op">,</tt> <tt class="py-param">equal</tt><tt class="py-op">=</tt><tt class="py-name">False</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="expand_tokens-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="expand_tokens-expanded"><a name="L216"></a><tt class="py-lineno">216</tt>  <tt class="py-line">    <tt class="py-docstring">"""Given a list of tokens, return a generator of the chunks of</tt> </tt>
<a name="L217"></a><tt class="py-lineno">217</tt>  <tt class="py-line"><tt class="py-docstring">    text for the data in the tokens.</tt> </tt>
<a name="L218"></a><tt class="py-lineno">218</tt>  <tt class="py-line"><tt class="py-docstring">    """</tt> </tt>
<a name="L219"></a><tt class="py-lineno">219</tt>  <tt class="py-line">    <tt class="py-keyword">for</tt> <tt id="link-61" class="py-name"><a title="lxml.html.diff.token" class="py-name" href="#" onclick="return doclink('link-61', 'token', 'link-26');">token</a></tt> <tt class="py-keyword">in</tt> <tt class="py-name">tokens</tt><tt class="py-op">:</tt> </tt>
<a name="L220"></a><tt class="py-lineno">220</tt>  <tt class="py-line">        <tt class="py-keyword">for</tt> <tt class="py-name">pre</tt> <tt class="py-keyword">in</tt> <tt id="link-62" class="py-name"><a title="lxml.html.diff.token" class="py-name" href="#" onclick="return doclink('link-62', 'token', 'link-26');">token</a></tt><tt class="py-op">.</tt><tt class="py-name">pre_tags</tt><tt class="py-op">:</tt> </tt>
<a name="L221"></a><tt class="py-lineno">221</tt>  <tt class="py-line">            <tt class="py-keyword">yield</tt> <tt class="py-name">pre</tt> </tt>
<a name="L222"></a><tt class="py-lineno">222</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt class="py-keyword">not</tt> <tt class="py-name">equal</tt> <tt class="py-keyword">or</tt> <tt class="py-keyword">not</tt> <tt id="link-63" class="py-name"><a title="lxml.html.diff.token" class="py-name" href="#" onclick="return doclink('link-63', 'token', 'link-26');">token</a></tt><tt class="py-op">.</tt><tt id="link-64" class="py-name" targets="Variable lxml.html.diff.href_token.hide_when_equal=lxml.html.diff.href_token-class.html#hide_when_equal,Variable lxml.html.diff.token.hide_when_equal=lxml.html.diff.token-class.html#hide_when_equal"><a title="lxml.html.diff.href_token.hide_when_equal
lxml.html.diff.token.hide_when_equal" class="py-name" href="#" onclick="return doclink('link-64', 'hide_when_equal', 'link-64');">hide_when_equal</a></tt><tt class="py-op">:</tt> </tt>
<a name="L223"></a><tt class="py-lineno">223</tt>  <tt class="py-line">            <tt class="py-keyword">if</tt> <tt id="link-65" class="py-name"><a title="lxml.html.diff.token" class="py-name" href="#" onclick="return doclink('link-65', 'token', 'link-26');">token</a></tt><tt class="py-op">.</tt><tt class="py-name">trailing_whitespace</tt><tt class="py-op">:</tt> </tt>
<a name="L224"></a><tt class="py-lineno">224</tt>  <tt class="py-line">                <tt class="py-keyword">yield</tt> <tt id="link-66" class="py-name"><a title="lxml.html.diff.token" class="py-name" href="#" onclick="return doclink('link-66', 'token', 'link-26');">token</a></tt><tt class="py-op">.</tt><tt id="link-67" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-67', 'html', 'link-3');">html</a></tt><tt class="py-op">(</tt><tt class="py-op">)</tt> <tt class="py-op">+</tt> <tt id="link-68" class="py-name"><a title="lxml.html.diff.token" class="py-name" href="#" onclick="return doclink('link-68', 'token', 'link-26');">token</a></tt><tt class="py-op">.</tt><tt class="py-name">trailing_whitespace</tt> </tt>
<a name="L225"></a><tt class="py-lineno">225</tt>  <tt class="py-line">            <tt class="py-keyword">else</tt><tt class="py-op">:</tt> </tt>
<a name="L226"></a><tt class="py-lineno">226</tt>  <tt class="py-line">                <tt class="py-keyword">yield</tt> <tt id="link-69" class="py-name"><a title="lxml.html.diff.token" class="py-name" href="#" onclick="return doclink('link-69', 'token', 'link-26');">token</a></tt><tt class="py-op">.</tt><tt id="link-70" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-70', 'html', 'link-3');">html</a></tt><tt class="py-op">(</tt><tt class="py-op">)</tt> </tt>
<a name="L227"></a><tt class="py-lineno">227</tt>  <tt class="py-line">        <tt class="py-keyword">for</tt> <tt class="py-name">post</tt> <tt class="py-keyword">in</tt> <tt id="link-71" class="py-name"><a title="lxml.html.diff.token" class="py-name" href="#" onclick="return doclink('link-71', 'token', 'link-26');">token</a></tt><tt class="py-op">.</tt><tt class="py-name">post_tags</tt><tt class="py-op">:</tt> </tt>
<a name="L228"></a><tt class="py-lineno">228</tt>  <tt class="py-line">            <tt class="py-keyword">yield</tt> <tt class="py-name">post</tt> </tt>
</div><a name="L229"></a><tt class="py-lineno">229</tt>  <tt class="py-line"> </tt>
<a name="merge_insert"></a><div id="merge_insert-def"><a name="L230"></a><tt class="py-lineno">230</tt> <a class="py-toggle" href="#" id="merge_insert-toggle" onclick="return toggle('merge_insert');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#merge_insert">merge_insert</a><tt class="py-op">(</tt><tt class="py-param">ins_chunks</tt><tt class="py-op">,</tt> <tt class="py-param">doc</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="merge_insert-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="merge_insert-expanded"><a name="L231"></a><tt class="py-lineno">231</tt>  <tt class="py-line">    <tt class="py-docstring">""" doc is the already-handled document (as a list of text chunks);</tt> </tt>
<a name="L232"></a><tt class="py-lineno">232</tt>  <tt class="py-line"><tt class="py-docstring">    here we add &lt;ins&gt;ins_chunks&lt;/ins&gt; to the end of that.  """</tt> </tt>
<a name="L233"></a><tt class="py-lineno">233</tt>  <tt class="py-line">    <tt class="py-comment"># Though we don't throw away unbalanced_start or unbalanced_end</tt> </tt>
<a name="L234"></a><tt class="py-lineno">234</tt>  <tt class="py-line">    <tt class="py-comment"># (we assume there is accompanying markup later or earlier in the</tt> </tt>
<a name="L235"></a><tt class="py-lineno">235</tt>  <tt class="py-line">    <tt class="py-comment"># document), we only put &lt;ins&gt; around the balanced portion.</tt> </tt>
<a name="L236"></a><tt class="py-lineno">236</tt>  <tt class="py-line">    <tt class="py-name">unbalanced_start</tt><tt class="py-op">,</tt> <tt class="py-name">balanced</tt><tt class="py-op">,</tt> <tt class="py-name">unbalanced_end</tt> <tt class="py-op">=</tt> <tt id="link-72" class="py-name" targets="Function lxml.html.diff.split_unbalanced()=lxml.html.diff-module.html#split_unbalanced"><a title="lxml.html.diff.split_unbalanced" class="py-name" href="#" onclick="return doclink('link-72', 'split_unbalanced', 'link-72');">split_unbalanced</a></tt><tt class="py-op">(</tt><tt class="py-name">ins_chunks</tt><tt class="py-op">)</tt> </tt>
<a name="L237"></a><tt class="py-lineno">237</tt>  <tt class="py-line">    <tt class="py-name">doc</tt><tt class="py-op">.</tt><tt id="link-73" class="py-name"><a title="lxml.etree._Element.extend" class="py-name" href="#" onclick="return doclink('link-73', 'extend', 'link-54');">extend</a></tt><tt class="py-op">(</tt><tt class="py-name">unbalanced_start</tt><tt class="py-op">)</tt> </tt>
<a name="L238"></a><tt class="py-lineno">238</tt>  <tt class="py-line">    <tt class="py-keyword">if</tt> <tt class="py-name">doc</tt> <tt class="py-keyword">and</tt> <tt class="py-keyword">not</tt> <tt class="py-name">doc</tt><tt class="py-op">[</tt><tt class="py-op">-</tt><tt class="py-number">1</tt><tt class="py-op">]</tt><tt class="py-op">.</tt><tt class="py-name">endswith</tt><tt class="py-op">(</tt><tt class="py-string">' '</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
<a name="L239"></a><tt class="py-lineno">239</tt>  <tt class="py-line">        <tt class="py-comment"># Fix up the case where the word before the insert didn't end with </tt> </tt>
<a name="L240"></a><tt class="py-lineno">240</tt>  <tt class="py-line">        <tt class="py-comment"># a space</tt> </tt>
<a name="L241"></a><tt class="py-lineno">241</tt>  <tt class="py-line">        <tt class="py-name">doc</tt><tt class="py-op">[</tt><tt class="py-op">-</tt><tt class="py-number">1</tt><tt class="py-op">]</tt> <tt class="py-op">+=</tt> <tt class="py-string">' '</tt> </tt>
<a name="L242"></a><tt class="py-lineno">242</tt>  <tt class="py-line">    <tt class="py-name">doc</tt><tt class="py-op">.</tt><tt id="link-74" class="py-name"><a title="lxml.etree._Element.append" class="py-name" href="#" onclick="return doclink('link-74', 'append', 'link-24');">append</a></tt><tt class="py-op">(</tt><tt class="py-string">'&lt;ins&gt;'</tt><tt class="py-op">)</tt> </tt>
<a name="L243"></a><tt class="py-lineno">243</tt>  <tt class="py-line">    <tt class="py-keyword">if</tt> <tt class="py-name">balanced</tt> <tt class="py-keyword">and</tt> <tt class="py-name">balanced</tt><tt class="py-op">[</tt><tt class="py-op">-</tt><tt class="py-number">1</tt><tt class="py-op">]</tt><tt class="py-op">.</tt><tt class="py-name">endswith</tt><tt class="py-op">(</tt><tt class="py-string">' '</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
<a name="L244"></a><tt class="py-lineno">244</tt>  <tt class="py-line">        <tt class="py-comment"># We move space outside of &lt;/ins&gt;</tt> </tt>
<a name="L245"></a><tt class="py-lineno">245</tt>  <tt class="py-line">        <tt class="py-name">balanced</tt><tt class="py-op">[</tt><tt class="py-op">-</tt><tt class="py-number">1</tt><tt class="py-op">]</tt> <tt class="py-op">=</tt> <tt class="py-name">balanced</tt><tt class="py-op">[</tt><tt class="py-op">-</tt><tt class="py-number">1</tt><tt class="py-op">]</tt><tt class="py-op">[</tt><tt class="py-op">:</tt><tt class="py-op">-</tt><tt class="py-number">1</tt><tt class="py-op">]</tt> </tt>
<a name="L246"></a><tt class="py-lineno">246</tt>  <tt class="py-line">    <tt class="py-name">doc</tt><tt class="py-op">.</tt><tt id="link-75" class="py-name"><a title="lxml.etree._Element.extend" class="py-name" href="#" onclick="return doclink('link-75', 'extend', 'link-54');">extend</a></tt><tt class="py-op">(</tt><tt class="py-name">balanced</tt><tt class="py-op">)</tt> </tt>
<a name="L247"></a><tt class="py-lineno">247</tt>  <tt class="py-line">    <tt class="py-name">doc</tt><tt class="py-op">.</tt><tt id="link-76" class="py-name"><a title="lxml.etree._Element.append" class="py-name" href="#" onclick="return doclink('link-76', 'append', 'link-24');">append</a></tt><tt class="py-op">(</tt><tt class="py-string">'&lt;/ins&gt; '</tt><tt class="py-op">)</tt> </tt>
<a name="L248"></a><tt class="py-lineno">248</tt>  <tt class="py-line">    <tt class="py-name">doc</tt><tt class="py-op">.</tt><tt id="link-77" class="py-name"><a title="lxml.etree._Element.extend" class="py-name" href="#" onclick="return doclink('link-77', 'extend', 'link-54');">extend</a></tt><tt class="py-op">(</tt><tt class="py-name">unbalanced_end</tt><tt class="py-op">)</tt> </tt>
</div><a name="L249"></a><tt class="py-lineno">249</tt>  <tt class="py-line"> </tt>
<a name="L250"></a><tt class="py-lineno">250</tt>  <tt class="py-line"><tt class="py-comment"># These are sentinals to represent the start and end of a &lt;del&gt;</tt> </tt>
<a name="L251"></a><tt class="py-lineno">251</tt>  <tt class="py-line"><tt class="py-comment"># segment, until we do the cleanup phase to turn them into proper</tt> </tt>
<a name="L252"></a><tt class="py-lineno">252</tt>  <tt class="py-line"><tt class="py-comment"># markup:</tt> </tt>
<a name="DEL_START"></a><div id="DEL_START-def"><a name="L253"></a><tt class="py-lineno">253</tt> <a class="py-toggle" href="#" id="DEL_START-toggle" onclick="return toggle('DEL_START');">-</a><tt class="py-line"><tt class="py-keyword">class</tt> <a class="py-def-name" href="lxml.html.diff.DEL_START-class.html">DEL_START</a><tt class="py-op">:</tt> </tt>
</div><div id="DEL_START-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="DEL_START-expanded"><a name="L254"></a><tt class="py-lineno">254</tt>  <tt class="py-line">    <tt class="py-keyword">pass</tt> </tt>
</div><a name="DEL_END"></a><div id="DEL_END-def"><a name="L255"></a><tt class="py-lineno">255</tt> <a class="py-toggle" href="#" id="DEL_END-toggle" onclick="return toggle('DEL_END');">-</a><tt class="py-line"><tt class="py-keyword">class</tt> <a class="py-def-name" href="lxml.html.diff.DEL_END-class.html">DEL_END</a><tt class="py-op">:</tt> </tt>
</div><div id="DEL_END-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="DEL_END-expanded"><a name="L256"></a><tt class="py-lineno">256</tt>  <tt class="py-line">    <tt class="py-keyword">pass</tt> </tt>
</div><a name="L257"></a><tt class="py-lineno">257</tt>  <tt class="py-line"> </tt>
<a name="NoDeletes"></a><div id="NoDeletes-def"><a name="L258"></a><tt class="py-lineno">258</tt> <a class="py-toggle" href="#" id="NoDeletes-toggle" onclick="return toggle('NoDeletes');">-</a><tt class="py-line"><tt class="py-keyword">class</tt> <a class="py-def-name" href="lxml.html.diff.NoDeletes-class.html">NoDeletes</a><tt class="py-op">(</tt><tt class="py-base-class">Exception</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="NoDeletes-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="NoDeletes-expanded"><a name="L259"></a><tt class="py-lineno">259</tt>  <tt class="py-line">    <tt class="py-docstring">""" Raised when the document no longer contains any pending deletes</tt> </tt>
<a name="L260"></a><tt class="py-lineno">260</tt>  <tt class="py-line"><tt class="py-docstring">    (DEL_START/DEL_END) """</tt> </tt>
</div><a name="L261"></a><tt class="py-lineno">261</tt>  <tt class="py-line"> </tt>
<a name="merge_delete"></a><div id="merge_delete-def"><a name="L262"></a><tt class="py-lineno">262</tt> <a class="py-toggle" href="#" id="merge_delete-toggle" onclick="return toggle('merge_delete');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#merge_delete">merge_delete</a><tt class="py-op">(</tt><tt class="py-param">del_chunks</tt><tt class="py-op">,</tt> <tt class="py-param">doc</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="merge_delete-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="merge_delete-expanded"><a name="L263"></a><tt class="py-lineno">263</tt>  <tt class="py-line">    <tt class="py-docstring">""" Adds the text chunks in del_chunks to the document doc (another</tt> </tt>
<a name="L264"></a><tt class="py-lineno">264</tt>  <tt class="py-line"><tt class="py-docstring">    list of text chunks) with marker to show it is a delete.</tt> </tt>
<a name="L265"></a><tt class="py-lineno">265</tt>  <tt class="py-line"><tt class="py-docstring">    cleanup_delete later resolves these markers into &lt;del&gt; tags."""</tt> </tt>
<a name="L266"></a><tt class="py-lineno">266</tt>  <tt class="py-line">    <tt class="py-name">doc</tt><tt class="py-op">.</tt><tt id="link-78" class="py-name"><a title="lxml.etree._Element.append" class="py-name" href="#" onclick="return doclink('link-78', 'append', 'link-24');">append</a></tt><tt class="py-op">(</tt><tt id="link-79" class="py-name" targets="Class lxml.html.diff.DEL_START=lxml.html.diff.DEL_START-class.html"><a title="lxml.html.diff.DEL_START" class="py-name" href="#" onclick="return doclink('link-79', 'DEL_START', 'link-79');">DEL_START</a></tt><tt class="py-op">)</tt> </tt>
<a name="L267"></a><tt class="py-lineno">267</tt>  <tt class="py-line">    <tt class="py-name">doc</tt><tt class="py-op">.</tt><tt id="link-80" class="py-name"><a title="lxml.etree._Element.extend" class="py-name" href="#" onclick="return doclink('link-80', 'extend', 'link-54');">extend</a></tt><tt class="py-op">(</tt><tt class="py-name">del_chunks</tt><tt class="py-op">)</tt> </tt>
<a name="L268"></a><tt class="py-lineno">268</tt>  <tt class="py-line">    <tt class="py-name">doc</tt><tt class="py-op">.</tt><tt id="link-81" class="py-name"><a title="lxml.etree._Element.append" class="py-name" href="#" onclick="return doclink('link-81', 'append', 'link-24');">append</a></tt><tt class="py-op">(</tt><tt id="link-82" class="py-name" targets="Class lxml.html.diff.DEL_END=lxml.html.diff.DEL_END-class.html"><a title="lxml.html.diff.DEL_END" class="py-name" href="#" onclick="return doclink('link-82', 'DEL_END', 'link-82');">DEL_END</a></tt><tt class="py-op">)</tt> </tt>
</div><a name="L269"></a><tt class="py-lineno">269</tt>  <tt class="py-line"> </tt>
<a name="cleanup_delete"></a><div id="cleanup_delete-def"><a name="L270"></a><tt class="py-lineno">270</tt> <a class="py-toggle" href="#" id="cleanup_delete-toggle" onclick="return toggle('cleanup_delete');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#cleanup_delete">cleanup_delete</a><tt class="py-op">(</tt><tt class="py-param">chunks</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="cleanup_delete-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="cleanup_delete-expanded"><a name="L271"></a><tt class="py-lineno">271</tt>  <tt class="py-line">    <tt class="py-docstring">""" Cleans up any DEL_START/DEL_END markers in the document, replacing</tt> </tt>
<a name="L272"></a><tt class="py-lineno">272</tt>  <tt class="py-line"><tt class="py-docstring">    them with &lt;del&gt;&lt;/del&gt;.  To do this while keeping the document</tt> </tt>
<a name="L273"></a><tt class="py-lineno">273</tt>  <tt class="py-line"><tt class="py-docstring">    valid, it may need to drop some tags (either start or end tags).</tt> </tt>
<a name="L274"></a><tt class="py-lineno">274</tt>  <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L275"></a><tt class="py-lineno">275</tt>  <tt class="py-line"><tt class="py-docstring">    It may also move the del into adjacent tags to try to move it to a</tt> </tt>
<a name="L276"></a><tt class="py-lineno">276</tt>  <tt class="py-line"><tt class="py-docstring">    similar location where it was originally located (e.g., moving a</tt> </tt>
<a name="L277"></a><tt class="py-lineno">277</tt>  <tt class="py-line"><tt class="py-docstring">    delete into preceding &lt;div&gt; tag, if the del looks like (DEL_START,</tt> </tt>
<a name="L278"></a><tt class="py-lineno">278</tt>  <tt class="py-line"><tt class="py-docstring">    'Text&lt;/div&gt;', DEL_END)"""</tt> </tt>
<a name="L279"></a><tt class="py-lineno">279</tt>  <tt class="py-line">    <tt class="py-keyword">while</tt> <tt class="py-number">1</tt><tt class="py-op">:</tt> </tt>
<a name="L280"></a><tt class="py-lineno">280</tt>  <tt class="py-line">        <tt class="py-comment"># Find a pending DEL_START/DEL_END, splitting the document</tt> </tt>
<a name="L281"></a><tt class="py-lineno">281</tt>  <tt class="py-line">        <tt class="py-comment"># into stuff-preceding-DEL_START, stuff-inside, and</tt> </tt>
<a name="L282"></a><tt class="py-lineno">282</tt>  <tt class="py-line">        <tt class="py-comment"># stuff-following-DEL_END</tt> </tt>
<a name="L283"></a><tt class="py-lineno">283</tt>  <tt class="py-line">        <tt class="py-keyword">try</tt><tt class="py-op">:</tt> </tt>
<a name="L284"></a><tt class="py-lineno">284</tt>  <tt class="py-line">            <tt class="py-name">pre_delete</tt><tt class="py-op">,</tt> <tt class="py-name">delete</tt><tt class="py-op">,</tt> <tt class="py-name">post_delete</tt> <tt class="py-op">=</tt> <tt id="link-83" class="py-name" targets="Function lxml.html.diff.split_delete()=lxml.html.diff-module.html#split_delete"><a title="lxml.html.diff.split_delete" class="py-name" href="#" onclick="return doclink('link-83', 'split_delete', 'link-83');">split_delete</a></tt><tt class="py-op">(</tt><tt class="py-name">chunks</tt><tt class="py-op">)</tt> </tt>
<a name="L285"></a><tt class="py-lineno">285</tt>  <tt class="py-line">        <tt class="py-keyword">except</tt> <tt id="link-84" class="py-name" targets="Class lxml.html.diff.NoDeletes=lxml.html.diff.NoDeletes-class.html"><a title="lxml.html.diff.NoDeletes" class="py-name" href="#" onclick="return doclink('link-84', 'NoDeletes', 'link-84');">NoDeletes</a></tt><tt class="py-op">:</tt> </tt>
<a name="L286"></a><tt class="py-lineno">286</tt>  <tt class="py-line">            <tt class="py-comment"># Nothing found, we've cleaned up the entire doc</tt> </tt>
<a name="L287"></a><tt class="py-lineno">287</tt>  <tt class="py-line">            <tt class="py-keyword">break</tt> </tt>
<a name="L288"></a><tt class="py-lineno">288</tt>  <tt class="py-line">        <tt class="py-comment"># The stuff-inside-DEL_START/END may not be well balanced</tt> </tt>
<a name="L289"></a><tt class="py-lineno">289</tt>  <tt class="py-line">        <tt class="py-comment"># markup.  First we figure out what unbalanced portions there are:</tt> </tt>
<a name="L290"></a><tt class="py-lineno">290</tt>  <tt class="py-line">        <tt class="py-name">unbalanced_start</tt><tt class="py-op">,</tt> <tt class="py-name">balanced</tt><tt class="py-op">,</tt> <tt class="py-name">unbalanced_end</tt> <tt class="py-op">=</tt> <tt id="link-85" class="py-name"><a title="lxml.html.diff.split_unbalanced" class="py-name" href="#" onclick="return doclink('link-85', 'split_unbalanced', 'link-72');">split_unbalanced</a></tt><tt class="py-op">(</tt><tt class="py-name">delete</tt><tt class="py-op">)</tt> </tt>
<a name="L291"></a><tt class="py-lineno">291</tt>  <tt class="py-line">        <tt class="py-comment"># Then we move the span forward and/or backward based on these</tt> </tt>
<a name="L292"></a><tt class="py-lineno">292</tt>  <tt class="py-line">        <tt class="py-comment"># unbalanced portions:</tt> </tt>
<a name="L293"></a><tt class="py-lineno">293</tt>  <tt class="py-line">        <tt id="link-86" class="py-name" targets="Function lxml.html.diff.locate_unbalanced_start()=lxml.html.diff-module.html#locate_unbalanced_start"><a title="lxml.html.diff.locate_unbalanced_start" class="py-name" href="#" onclick="return doclink('link-86', 'locate_unbalanced_start', 'link-86');">locate_unbalanced_start</a></tt><tt class="py-op">(</tt><tt class="py-name">unbalanced_start</tt><tt class="py-op">,</tt> <tt class="py-name">pre_delete</tt><tt class="py-op">,</tt> <tt class="py-name">post_delete</tt><tt class="py-op">)</tt> </tt>
<a name="L294"></a><tt class="py-lineno">294</tt>  <tt class="py-line">        <tt id="link-87" class="py-name" targets="Function lxml.html.diff.locate_unbalanced_end()=lxml.html.diff-module.html#locate_unbalanced_end"><a title="lxml.html.diff.locate_unbalanced_end" class="py-name" href="#" onclick="return doclink('link-87', 'locate_unbalanced_end', 'link-87');">locate_unbalanced_end</a></tt><tt class="py-op">(</tt><tt class="py-name">unbalanced_end</tt><tt class="py-op">,</tt> <tt class="py-name">pre_delete</tt><tt class="py-op">,</tt> <tt class="py-name">post_delete</tt><tt class="py-op">)</tt> </tt>
<a name="L295"></a><tt class="py-lineno">295</tt>  <tt class="py-line">        <tt class="py-name">doc</tt> <tt class="py-op">=</tt> <tt class="py-name">pre_delete</tt> </tt>
<a name="L296"></a><tt class="py-lineno">296</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt class="py-name">doc</tt> <tt class="py-keyword">and</tt> <tt class="py-keyword">not</tt> <tt class="py-name">doc</tt><tt class="py-op">[</tt><tt class="py-op">-</tt><tt class="py-number">1</tt><tt class="py-op">]</tt><tt class="py-op">.</tt><tt class="py-name">endswith</tt><tt class="py-op">(</tt><tt class="py-string">' '</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
<a name="L297"></a><tt class="py-lineno">297</tt>  <tt class="py-line">            <tt class="py-comment"># Fix up case where the word before us didn't have a trailing space</tt> </tt>
<a name="L298"></a><tt class="py-lineno">298</tt>  <tt class="py-line">            <tt class="py-name">doc</tt><tt class="py-op">[</tt><tt class="py-op">-</tt><tt class="py-number">1</tt><tt class="py-op">]</tt> <tt class="py-op">+=</tt> <tt class="py-string">' '</tt> </tt>
<a name="L299"></a><tt class="py-lineno">299</tt>  <tt class="py-line">        <tt class="py-name">doc</tt><tt class="py-op">.</tt><tt id="link-88" class="py-name"><a title="lxml.etree._Element.append" class="py-name" href="#" onclick="return doclink('link-88', 'append', 'link-24');">append</a></tt><tt class="py-op">(</tt><tt class="py-string">'&lt;del&gt;'</tt><tt class="py-op">)</tt> </tt>
<a name="L300"></a><tt class="py-lineno">300</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt class="py-name">balanced</tt> <tt class="py-keyword">and</tt> <tt class="py-name">balanced</tt><tt class="py-op">[</tt><tt class="py-op">-</tt><tt class="py-number">1</tt><tt class="py-op">]</tt><tt class="py-op">.</tt><tt class="py-name">endswith</tt><tt class="py-op">(</tt><tt class="py-string">' '</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
<a name="L301"></a><tt class="py-lineno">301</tt>  <tt class="py-line">            <tt class="py-comment"># We move space outside of &lt;/del&gt;</tt> </tt>
<a name="L302"></a><tt class="py-lineno">302</tt>  <tt class="py-line">            <tt class="py-name">balanced</tt><tt class="py-op">[</tt><tt class="py-op">-</tt><tt class="py-number">1</tt><tt class="py-op">]</tt> <tt class="py-op">=</tt> <tt class="py-name">balanced</tt><tt class="py-op">[</tt><tt class="py-op">-</tt><tt class="py-number">1</tt><tt class="py-op">]</tt><tt class="py-op">[</tt><tt class="py-op">:</tt><tt class="py-op">-</tt><tt class="py-number">1</tt><tt class="py-op">]</tt> </tt>
<a name="L303"></a><tt class="py-lineno">303</tt>  <tt class="py-line">        <tt class="py-name">doc</tt><tt class="py-op">.</tt><tt id="link-89" class="py-name"><a title="lxml.etree._Element.extend" class="py-name" href="#" onclick="return doclink('link-89', 'extend', 'link-54');">extend</a></tt><tt class="py-op">(</tt><tt class="py-name">balanced</tt><tt class="py-op">)</tt> </tt>
<a name="L304"></a><tt class="py-lineno">304</tt>  <tt class="py-line">        <tt class="py-name">doc</tt><tt class="py-op">.</tt><tt id="link-90" class="py-name"><a title="lxml.etree._Element.append" class="py-name" href="#" onclick="return doclink('link-90', 'append', 'link-24');">append</a></tt><tt class="py-op">(</tt><tt class="py-string">'&lt;/del&gt; '</tt><tt class="py-op">)</tt> </tt>
<a name="L305"></a><tt class="py-lineno">305</tt>  <tt class="py-line">        <tt class="py-name">doc</tt><tt class="py-op">.</tt><tt id="link-91" class="py-name"><a title="lxml.etree._Element.extend" class="py-name" href="#" onclick="return doclink('link-91', 'extend', 'link-54');">extend</a></tt><tt class="py-op">(</tt><tt class="py-name">post_delete</tt><tt class="py-op">)</tt> </tt>
<a name="L306"></a><tt class="py-lineno">306</tt>  <tt class="py-line">        <tt class="py-name">chunks</tt> <tt class="py-op">=</tt> <tt class="py-name">doc</tt> </tt>
<a name="L307"></a><tt class="py-lineno">307</tt>  <tt class="py-line">    <tt class="py-keyword">return</tt> <tt class="py-name">chunks</tt> </tt>
</div><a name="L308"></a><tt class="py-lineno">308</tt>  <tt class="py-line"> </tt>
<a name="split_unbalanced"></a><div id="split_unbalanced-def"><a name="L309"></a><tt class="py-lineno">309</tt> <a class="py-toggle" href="#" id="split_unbalanced-toggle" onclick="return toggle('split_unbalanced');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#split_unbalanced">split_unbalanced</a><tt class="py-op">(</tt><tt class="py-param">chunks</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="split_unbalanced-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="split_unbalanced-expanded"><a name="L310"></a><tt class="py-lineno">310</tt>  <tt class="py-line">    <tt class="py-docstring">"""Return (unbalanced_start, balanced, unbalanced_end), where each is</tt> </tt>
<a name="L311"></a><tt class="py-lineno">311</tt>  <tt class="py-line"><tt class="py-docstring">    a list of text and tag chunks.</tt> </tt>
<a name="L312"></a><tt class="py-lineno">312</tt>  <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L313"></a><tt class="py-lineno">313</tt>  <tt class="py-line"><tt class="py-docstring">    unbalanced_start is a list of all the tags that are opened, but</tt> </tt>
<a name="L314"></a><tt class="py-lineno">314</tt>  <tt class="py-line"><tt class="py-docstring">    not closed in this span.  Similarly, unbalanced_end is a list of</tt> </tt>
<a name="L315"></a><tt class="py-lineno">315</tt>  <tt class="py-line"><tt class="py-docstring">    tags that are closed but were not opened.  Extracting these might</tt> </tt>
<a name="L316"></a><tt class="py-lineno">316</tt>  <tt class="py-line"><tt class="py-docstring">    mean some reordering of the chunks."""</tt> </tt>
<a name="L317"></a><tt class="py-lineno">317</tt>  <tt class="py-line">    <tt id="link-92" class="py-name" targets="Method lxml.etree.TreeBuilder.start()=lxml.etree.TreeBuilder-class.html#start"><a title="lxml.etree.TreeBuilder.start" class="py-name" href="#" onclick="return doclink('link-92', 'start', 'link-92');">start</a></tt> <tt class="py-op">=</tt> <tt class="py-op">[</tt><tt class="py-op">]</tt> </tt>
<a name="L318"></a><tt class="py-lineno">318</tt>  <tt class="py-line">    <tt id="link-93" class="py-name" targets="Method lxml.etree.TreeBuilder.end()=lxml.etree.TreeBuilder-class.html#end"><a title="lxml.etree.TreeBuilder.end" class="py-name" href="#" onclick="return doclink('link-93', 'end', 'link-93');">end</a></tt> <tt class="py-op">=</tt> <tt class="py-op">[</tt><tt class="py-op">]</tt> </tt>
<a name="L319"></a><tt class="py-lineno">319</tt>  <tt class="py-line">    <tt class="py-name">tag_stack</tt> <tt class="py-op">=</tt> <tt class="py-op">[</tt><tt class="py-op">]</tt> </tt>
<a name="L320"></a><tt class="py-lineno">320</tt>  <tt class="py-line">    <tt class="py-name">balanced</tt> <tt class="py-op">=</tt> <tt class="py-op">[</tt><tt class="py-op">]</tt> </tt>
<a name="L321"></a><tt class="py-lineno">321</tt>  <tt class="py-line">    <tt class="py-keyword">for</tt> <tt class="py-name">chunk</tt> <tt class="py-keyword">in</tt> <tt class="py-name">chunks</tt><tt class="py-op">:</tt> </tt>
<a name="L322"></a><tt class="py-lineno">322</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt class="py-keyword">not</tt> <tt class="py-name">chunk</tt><tt class="py-op">.</tt><tt class="py-name">startswith</tt><tt class="py-op">(</tt><tt class="py-string">'&lt;'</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
<a name="L323"></a><tt class="py-lineno">323</tt>  <tt class="py-line">            <tt class="py-name">balanced</tt><tt class="py-op">.</tt><tt id="link-94" class="py-name"><a title="lxml.etree._Element.append" class="py-name" href="#" onclick="return doclink('link-94', 'append', 'link-24');">append</a></tt><tt class="py-op">(</tt><tt class="py-name">chunk</tt><tt class="py-op">)</tt> </tt>
<a name="L324"></a><tt class="py-lineno">324</tt>  <tt class="py-line">            <tt class="py-keyword">continue</tt> </tt>
<a name="L325"></a><tt class="py-lineno">325</tt>  <tt class="py-line">        <tt class="py-name">endtag</tt> <tt class="py-op">=</tt> <tt class="py-name">chunk</tt><tt class="py-op">[</tt><tt class="py-number">1</tt><tt class="py-op">]</tt> <tt class="py-op">==</tt> <tt class="py-string">'/'</tt> </tt>
<a name="L326"></a><tt class="py-lineno">326</tt>  <tt class="py-line">        <tt id="link-95" class="py-name" targets="Variable lxml.etree.DTD.name=lxml.etree.DTD-class.html#name,Variable lxml.etree._Entity.name=lxml.etree._Entity-class.html#name,Variable lxml.html.InputMixin.name=lxml.html.InputMixin-class.html#name,Variable lxml.objectify.PyType.name=lxml.objectify.PyType-class.html#name"><a title="lxml.etree.DTD.name
lxml.etree._Entity.name
lxml.html.InputMixin.name
lxml.objectify.PyType.name" class="py-name" href="#" onclick="return doclink('link-95', 'name', 'link-95');">name</a></tt> <tt class="py-op">=</tt> <tt class="py-name">chunk</tt><tt class="py-op">.</tt><tt class="py-name">split</tt><tt class="py-op">(</tt><tt class="py-op">)</tt><tt class="py-op">[</tt><tt class="py-number">0</tt><tt class="py-op">]</tt><tt class="py-op">.</tt><tt id="link-96" class="py-name"><a title="lxml.doctestcompare.strip" class="py-name" href="#" onclick="return doclink('link-96', 'strip', 'link-19');">strip</a></tt><tt class="py-op">(</tt><tt class="py-string">'&lt;&gt;/'</tt><tt class="py-op">)</tt> </tt>
<a name="L327"></a><tt class="py-lineno">327</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt id="link-97" class="py-name"><a title="lxml.etree.DTD.name
lxml.etree._Entity.name
lxml.html.InputMixin.name
lxml.objectify.PyType.name" class="py-name" href="#" onclick="return doclink('link-97', 'name', 'link-95');">name</a></tt> <tt class="py-keyword">in</tt> <tt id="link-98" class="py-name" targets="Variable lxml.doctestcompare.LXMLOutputChecker.empty_tags=lxml.doctestcompare.LXMLOutputChecker-class.html#empty_tags,Variable lxml.html.defs.empty_tags=lxml.html.defs-module.html#empty_tags,Variable lxml.html.diff.empty_tags=lxml.html.diff-module.html#empty_tags"><a title="lxml.doctestcompare.LXMLOutputChecker.empty_tags
lxml.html.defs.empty_tags
lxml.html.diff.empty_tags" class="py-name" href="#" onclick="return doclink('link-98', 'empty_tags', 'link-98');">empty_tags</a></tt><tt class="py-op">:</tt> </tt>
<a name="L328"></a><tt class="py-lineno">328</tt>  <tt class="py-line">            <tt class="py-name">balanced</tt><tt class="py-op">.</tt><tt id="link-99" class="py-name"><a title="lxml.etree._Element.append" class="py-name" href="#" onclick="return doclink('link-99', 'append', 'link-24');">append</a></tt><tt class="py-op">(</tt><tt class="py-name">chunk</tt><tt class="py-op">)</tt> </tt>
<a name="L329"></a><tt class="py-lineno">329</tt>  <tt class="py-line">            <tt class="py-keyword">continue</tt> </tt>
<a name="L330"></a><tt class="py-lineno">330</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt class="py-name">endtag</tt><tt class="py-op">:</tt> </tt>
<a name="L331"></a><tt class="py-lineno">331</tt>  <tt class="py-line">            <tt class="py-keyword">if</tt> <tt class="py-name">tag_stack</tt> <tt class="py-keyword">and</tt> <tt class="py-name">tag_stack</tt><tt class="py-op">[</tt><tt class="py-op">-</tt><tt class="py-number">1</tt><tt class="py-op">]</tt><tt class="py-op">[</tt><tt class="py-number">0</tt><tt class="py-op">]</tt> <tt class="py-op">==</tt> <tt id="link-100" class="py-name"><a title="lxml.etree.DTD.name
lxml.etree._Entity.name
lxml.html.InputMixin.name
lxml.objectify.PyType.name" class="py-name" href="#" onclick="return doclink('link-100', 'name', 'link-95');">name</a></tt><tt class="py-op">:</tt> </tt>
<a name="L332"></a><tt class="py-lineno">332</tt>  <tt class="py-line">                <tt class="py-name">balanced</tt><tt class="py-op">.</tt><tt id="link-101" class="py-name"><a title="lxml.etree._Element.append" class="py-name" href="#" onclick="return doclink('link-101', 'append', 'link-24');">append</a></tt><tt class="py-op">(</tt><tt class="py-name">chunk</tt><tt class="py-op">)</tt> </tt>
<a name="L333"></a><tt class="py-lineno">333</tt>  <tt class="py-line">                <tt id="link-102" class="py-name"><a title="lxml.etree.DTD.name
lxml.etree._Entity.name
lxml.html.InputMixin.name
lxml.objectify.PyType.name" class="py-name" href="#" onclick="return doclink('link-102', 'name', 'link-95');">name</a></tt><tt class="py-op">,</tt> <tt class="py-name">pos</tt><tt class="py-op">,</tt> <tt id="link-103" class="py-name" targets="Variable lxml.etree._Comment.tag=lxml.etree._Comment-class.html#tag,Variable lxml.etree._Element.tag=lxml.etree._Element-class.html#tag,Variable lxml.etree._Entity.tag=lxml.etree._Entity-class.html#tag,Variable lxml.etree._ProcessingInstruction.tag=lxml.etree._ProcessingInstruction-class.html#tag,Function lxml.tests.test_xpathevaluator.tag()=lxml.tests.test_xpathevaluator-module.html#tag,Variable xml.etree.ElementTree.Element.tag=xml.etree.ElementTree.Element-class.html#tag"><a title="lxml.etree._Comment.tag
lxml.etree._Element.tag
lxml.etree._Entity.tag
lxml.etree._ProcessingInstruction.tag
lxml.tests.test_xpathevaluator.tag
xml.etree.ElementTree.Element.tag" class="py-name" href="#" onclick="return doclink('link-103', 'tag', 'link-103');">tag</a></tt> <tt class="py-op">=</tt> <tt class="py-name">tag_stack</tt><tt class="py-op">.</tt><tt id="link-104" class="py-name" targets="Method lxml.etree._Attrib.pop()=lxml.etree._Attrib-class.html#pop"><a title="lxml.etree._Attrib.pop" class="py-name" href="#" onclick="return doclink('link-104', 'pop', 'link-104');">pop</a></tt><tt class="py-op">(</tt><tt class="py-op">)</tt> </tt>
<a name="L334"></a><tt class="py-lineno">334</tt>  <tt class="py-line">                <tt class="py-name">balanced</tt><tt class="py-op">[</tt><tt class="py-name">pos</tt><tt class="py-op">]</tt> <tt class="py-op">=</tt> <tt id="link-105" class="py-name"><a title="lxml.etree._Comment.tag
lxml.etree._Element.tag
lxml.etree._Entity.tag
lxml.etree._ProcessingInstruction.tag
lxml.tests.test_xpathevaluator.tag
xml.etree.ElementTree.Element.tag" class="py-name" href="#" onclick="return doclink('link-105', 'tag', 'link-103');">tag</a></tt> </tt>
<a name="L335"></a><tt class="py-lineno">335</tt>  <tt class="py-line">            <tt class="py-keyword">elif</tt> <tt class="py-name">tag_stack</tt><tt class="py-op">:</tt> </tt>
<a name="L336"></a><tt class="py-lineno">336</tt>  <tt class="py-line">                <tt id="link-106" class="py-name"><a title="lxml.etree.TreeBuilder.start" class="py-name" href="#" onclick="return doclink('link-106', 'start', 'link-92');">start</a></tt><tt class="py-op">.</tt><tt id="link-107" class="py-name"><a title="lxml.etree._Element.extend" class="py-name" href="#" onclick="return doclink('link-107', 'extend', 'link-54');">extend</a></tt><tt class="py-op">(</tt><tt class="py-op">[</tt><tt id="link-108" class="py-name"><a title="lxml.etree._Comment.tag
lxml.etree._Element.tag
lxml.etree._Entity.tag
lxml.etree._ProcessingInstruction.tag
lxml.tests.test_xpathevaluator.tag
xml.etree.ElementTree.Element.tag" class="py-name" href="#" onclick="return doclink('link-108', 'tag', 'link-103');">tag</a></tt> <tt class="py-keyword">for</tt> <tt id="link-109" class="py-name"><a title="lxml.etree.DTD.name
lxml.etree._Entity.name
lxml.html.InputMixin.name
lxml.objectify.PyType.name" class="py-name" href="#" onclick="return doclink('link-109', 'name', 'link-95');">name</a></tt><tt class="py-op">,</tt> <tt class="py-name">pos</tt><tt class="py-op">,</tt> <tt id="link-110" class="py-name"><a title="lxml.etree._Comment.tag
lxml.etree._Element.tag
lxml.etree._Entity.tag
lxml.etree._ProcessingInstruction.tag
lxml.tests.test_xpathevaluator.tag
xml.etree.ElementTree.Element.tag" class="py-name" href="#" onclick="return doclink('link-110', 'tag', 'link-103');">tag</a></tt> <tt class="py-keyword">in</tt> <tt class="py-name">tag_stack</tt><tt class="py-op">]</tt><tt class="py-op">)</tt> </tt>
<a name="L337"></a><tt class="py-lineno">337</tt>  <tt class="py-line">                <tt class="py-name">tag_stack</tt> <tt class="py-op">=</tt> <tt class="py-op">[</tt><tt class="py-op">]</tt> </tt>
<a name="L338"></a><tt class="py-lineno">338</tt>  <tt class="py-line">                <tt id="link-111" class="py-name"><a title="lxml.etree.TreeBuilder.end" class="py-name" href="#" onclick="return doclink('link-111', 'end', 'link-93');">end</a></tt><tt class="py-op">.</tt><tt id="link-112" class="py-name"><a title="lxml.etree._Element.append" class="py-name" href="#" onclick="return doclink('link-112', 'append', 'link-24');">append</a></tt><tt class="py-op">(</tt><tt class="py-name">chunk</tt><tt class="py-op">)</tt> </tt>
<a name="L339"></a><tt class="py-lineno">339</tt>  <tt class="py-line">            <tt class="py-keyword">else</tt><tt class="py-op">:</tt> </tt>
<a name="L340"></a><tt class="py-lineno">340</tt>  <tt class="py-line">                <tt id="link-113" class="py-name"><a title="lxml.etree.TreeBuilder.end" class="py-name" href="#" onclick="return doclink('link-113', 'end', 'link-93');">end</a></tt><tt class="py-op">.</tt><tt id="link-114" class="py-name"><a title="lxml.etree._Element.append" class="py-name" href="#" onclick="return doclink('link-114', 'append', 'link-24');">append</a></tt><tt class="py-op">(</tt><tt class="py-name">chunk</tt><tt class="py-op">)</tt> </tt>
<a name="L341"></a><tt class="py-lineno">341</tt>  <tt class="py-line">        <tt class="py-keyword">else</tt><tt class="py-op">:</tt> </tt>
<a name="L342"></a><tt class="py-lineno">342</tt>  <tt class="py-line">            <tt class="py-name">tag_stack</tt><tt class="py-op">.</tt><tt id="link-115" class="py-name"><a title="lxml.etree._Element.append" class="py-name" href="#" onclick="return doclink('link-115', 'append', 'link-24');">append</a></tt><tt class="py-op">(</tt><tt class="py-op">(</tt><tt id="link-116" class="py-name"><a title="lxml.etree.DTD.name
lxml.etree._Entity.name
lxml.html.InputMixin.name
lxml.objectify.PyType.name" class="py-name" href="#" onclick="return doclink('link-116', 'name', 'link-95');">name</a></tt><tt class="py-op">,</tt> <tt class="py-name">len</tt><tt class="py-op">(</tt><tt class="py-name">balanced</tt><tt class="py-op">)</tt><tt class="py-op">,</tt> <tt class="py-name">chunk</tt><tt class="py-op">)</tt><tt class="py-op">)</tt> </tt>
<a name="L343"></a><tt class="py-lineno">343</tt>  <tt class="py-line">            <tt class="py-name">balanced</tt><tt class="py-op">.</tt><tt id="link-117" class="py-name"><a title="lxml.etree._Element.append" class="py-name" href="#" onclick="return doclink('link-117', 'append', 'link-24');">append</a></tt><tt class="py-op">(</tt><tt class="py-name">None</tt><tt class="py-op">)</tt> </tt>
<a name="L344"></a><tt class="py-lineno">344</tt>  <tt class="py-line">    <tt id="link-118" class="py-name"><a title="lxml.etree.TreeBuilder.start" class="py-name" href="#" onclick="return doclink('link-118', 'start', 'link-92');">start</a></tt><tt class="py-op">.</tt><tt id="link-119" class="py-name"><a title="lxml.etree._Element.extend" class="py-name" href="#" onclick="return doclink('link-119', 'extend', 'link-54');">extend</a></tt><tt class="py-op">(</tt> </tt>
<a name="L345"></a><tt class="py-lineno">345</tt>  <tt class="py-line">        <tt class="py-op">[</tt><tt class="py-name">chunk</tt> <tt class="py-keyword">for</tt> <tt id="link-120" class="py-name"><a title="lxml.etree.DTD.name
lxml.etree._Entity.name
lxml.html.InputMixin.name
lxml.objectify.PyType.name" class="py-name" href="#" onclick="return doclink('link-120', 'name', 'link-95');">name</a></tt><tt class="py-op">,</tt> <tt class="py-name">pos</tt><tt class="py-op">,</tt> <tt class="py-name">chunk</tt> <tt class="py-keyword">in</tt> <tt class="py-name">tag_stack</tt><tt class="py-op">]</tt><tt class="py-op">)</tt> </tt>
<a name="L346"></a><tt class="py-lineno">346</tt>  <tt class="py-line">    <tt class="py-name">balanced</tt> <tt class="py-op">=</tt> <tt class="py-op">[</tt><tt class="py-name">chunk</tt> <tt class="py-keyword">for</tt> <tt class="py-name">chunk</tt> <tt class="py-keyword">in</tt> <tt class="py-name">balanced</tt> <tt class="py-keyword">if</tt> <tt class="py-name">chunk</tt> <tt class="py-keyword">is</tt> <tt class="py-keyword">not</tt> <tt class="py-name">None</tt><tt class="py-op">]</tt> </tt>
<a name="L347"></a><tt class="py-lineno">347</tt>  <tt class="py-line">    <tt class="py-keyword">return</tt> <tt id="link-121" class="py-name"><a title="lxml.etree.TreeBuilder.start" class="py-name" href="#" onclick="return doclink('link-121', 'start', 'link-92');">start</a></tt><tt class="py-op">,</tt> <tt class="py-name">balanced</tt><tt class="py-op">,</tt> <tt id="link-122" class="py-name"><a title="lxml.etree.TreeBuilder.end" class="py-name" href="#" onclick="return doclink('link-122', 'end', 'link-93');">end</a></tt> </tt>
</div><a name="L348"></a><tt class="py-lineno">348</tt>  <tt class="py-line"> </tt>
<a name="split_delete"></a><div id="split_delete-def"><a name="L349"></a><tt class="py-lineno">349</tt> <a class="py-toggle" href="#" id="split_delete-toggle" onclick="return toggle('split_delete');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#split_delete">split_delete</a><tt class="py-op">(</tt><tt class="py-param">chunks</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="split_delete-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="split_delete-expanded"><a name="L350"></a><tt class="py-lineno">350</tt>  <tt class="py-line">    <tt class="py-docstring">""" Returns (stuff_before_DEL_START, stuff_inside_DEL_START_END,</tt> </tt>
<a name="L351"></a><tt class="py-lineno">351</tt>  <tt class="py-line"><tt class="py-docstring">    stuff_after_DEL_END).  Returns the first case found (there may be</tt> </tt>
<a name="L352"></a><tt class="py-lineno">352</tt>  <tt class="py-line"><tt class="py-docstring">    more DEL_STARTs in stuff_after_DEL_END).  Raises NoDeletes if</tt> </tt>
<a name="L353"></a><tt class="py-lineno">353</tt>  <tt class="py-line"><tt class="py-docstring">    there's no DEL_START found. """</tt> </tt>
<a name="L354"></a><tt class="py-lineno">354</tt>  <tt class="py-line">    <tt class="py-keyword">try</tt><tt class="py-op">:</tt> </tt>
<a name="L355"></a><tt class="py-lineno">355</tt>  <tt class="py-line">        <tt class="py-name">pos</tt> <tt class="py-op">=</tt> <tt class="py-name">chunks</tt><tt class="py-op">.</tt><tt id="link-123" class="py-name" targets="Method lxml.etree._Element.index()=lxml.etree._Element-class.html#index"><a title="lxml.etree._Element.index" class="py-name" href="#" onclick="return doclink('link-123', 'index', 'link-123');">index</a></tt><tt class="py-op">(</tt><tt id="link-124" class="py-name"><a title="lxml.html.diff.DEL_START" class="py-name" href="#" onclick="return doclink('link-124', 'DEL_START', 'link-79');">DEL_START</a></tt><tt class="py-op">)</tt> </tt>
<a name="L356"></a><tt class="py-lineno">356</tt>  <tt class="py-line">    <tt class="py-keyword">except</tt> <tt class="py-name">ValueError</tt><tt class="py-op">:</tt> </tt>
<a name="L357"></a><tt class="py-lineno">357</tt>  <tt class="py-line">        <tt class="py-keyword">raise</tt> <tt id="link-125" class="py-name"><a title="lxml.html.diff.NoDeletes" class="py-name" href="#" onclick="return doclink('link-125', 'NoDeletes', 'link-84');">NoDeletes</a></tt> </tt>
<a name="L358"></a><tt class="py-lineno">358</tt>  <tt class="py-line">    <tt class="py-name">pos2</tt> <tt class="py-op">=</tt> <tt class="py-name">chunks</tt><tt class="py-op">.</tt><tt id="link-126" class="py-name"><a title="lxml.etree._Element.index" class="py-name" href="#" onclick="return doclink('link-126', 'index', 'link-123');">index</a></tt><tt class="py-op">(</tt><tt id="link-127" class="py-name"><a title="lxml.html.diff.DEL_END" class="py-name" href="#" onclick="return doclink('link-127', 'DEL_END', 'link-82');">DEL_END</a></tt><tt class="py-op">)</tt> </tt>
<a name="L359"></a><tt class="py-lineno">359</tt>  <tt class="py-line">    <tt class="py-keyword">return</tt> <tt class="py-name">chunks</tt><tt class="py-op">[</tt><tt class="py-op">:</tt><tt class="py-name">pos</tt><tt class="py-op">]</tt><tt class="py-op">,</tt> <tt class="py-name">chunks</tt><tt class="py-op">[</tt><tt class="py-name">pos</tt><tt class="py-op">+</tt><tt class="py-number">1</tt><tt class="py-op">:</tt><tt class="py-name">pos2</tt><tt class="py-op">]</tt><tt class="py-op">,</tt> <tt class="py-name">chunks</tt><tt class="py-op">[</tt><tt class="py-name">pos2</tt><tt class="py-op">+</tt><tt class="py-number">1</tt><tt class="py-op">:</tt><tt class="py-op">]</tt> </tt>
</div><a name="L360"></a><tt class="py-lineno">360</tt>  <tt class="py-line"> </tt>
<a name="locate_unbalanced_start"></a><div id="locate_unbalanced_start-def"><a name="L361"></a><tt class="py-lineno">361</tt> <a class="py-toggle" href="#" id="locate_unbalanced_start-toggle" onclick="return toggle('locate_unbalanced_start');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#locate_unbalanced_start">locate_unbalanced_start</a><tt class="py-op">(</tt><tt class="py-param">unbalanced_start</tt><tt class="py-op">,</tt> <tt class="py-param">pre_delete</tt><tt class="py-op">,</tt> <tt class="py-param">post_delete</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="locate_unbalanced_start-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="locate_unbalanced_start-expanded"><a name="L362"></a><tt class="py-lineno">362</tt>  <tt class="py-line">    <tt class="py-docstring">""" pre_delete and post_delete implicitly point to a place in the</tt> </tt>
<a name="L363"></a><tt class="py-lineno">363</tt>  <tt class="py-line"><tt class="py-docstring">    document (where the two were split).  This moves that point (by</tt> </tt>
<a name="L364"></a><tt class="py-lineno">364</tt>  <tt class="py-line"><tt class="py-docstring">    popping items from one and pushing them onto the other).  It moves</tt> </tt>
<a name="L365"></a><tt class="py-lineno">365</tt>  <tt class="py-line"><tt class="py-docstring">    the point to try to find a place where unbalanced_start applies.</tt> </tt>
<a name="L366"></a><tt class="py-lineno">366</tt>  <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L367"></a><tt class="py-lineno">367</tt>  <tt class="py-line"><tt class="py-docstring">    As an example::</tt> </tt>
<a name="L368"></a><tt class="py-lineno">368</tt>  <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L369"></a><tt class="py-lineno">369</tt>  <tt class="py-line"><tt class="py-docstring">        &gt;&gt;&gt; unbalanced_start = ['&lt;div&gt;']</tt> </tt>
<a name="L370"></a><tt class="py-lineno">370</tt>  <tt class="py-line"><tt class="py-docstring">        &gt;&gt;&gt; doc = ['&lt;p&gt;', 'Text', '&lt;/p&gt;', '&lt;div&gt;', 'More Text', '&lt;/div&gt;']</tt> </tt>
<a name="L371"></a><tt class="py-lineno">371</tt>  <tt class="py-line"><tt class="py-docstring">        &gt;&gt;&gt; pre, post = doc[:3], doc[3:]</tt> </tt>
<a name="L372"></a><tt class="py-lineno">372</tt>  <tt class="py-line"><tt class="py-docstring">        &gt;&gt;&gt; pre, post</tt> </tt>
<a name="L373"></a><tt class="py-lineno">373</tt>  <tt class="py-line"><tt class="py-docstring">        (['&lt;p&gt;', 'Text', '&lt;/p&gt;'], ['&lt;div&gt;', 'More Text', '&lt;/div&gt;'])</tt> </tt>
<a name="L374"></a><tt class="py-lineno">374</tt>  <tt class="py-line"><tt class="py-docstring">        &gt;&gt;&gt; locate_unbalanced_start(unbalanced_start, pre, post)</tt> </tt>
<a name="L375"></a><tt class="py-lineno">375</tt>  <tt class="py-line"><tt class="py-docstring">        &gt;&gt;&gt; pre, post</tt> </tt>
<a name="L376"></a><tt class="py-lineno">376</tt>  <tt class="py-line"><tt class="py-docstring">        (['&lt;p&gt;', 'Text', '&lt;/p&gt;', '&lt;div&gt;'], ['More Text', '&lt;/div&gt;'])</tt> </tt>
<a name="L377"></a><tt class="py-lineno">377</tt>  <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L378"></a><tt class="py-lineno">378</tt>  <tt class="py-line"><tt class="py-docstring">    As you can see, we moved the point so that the dangling &lt;div&gt; that</tt> </tt>
<a name="L379"></a><tt class="py-lineno">379</tt>  <tt class="py-line"><tt class="py-docstring">    we found will be effectively replaced by the div in the original</tt> </tt>
<a name="L380"></a><tt class="py-lineno">380</tt>  <tt class="py-line"><tt class="py-docstring">    document.  If this doesn't work out, we just throw away</tt> </tt>
<a name="L381"></a><tt class="py-lineno">381</tt>  <tt class="py-line"><tt class="py-docstring">    unbalanced_start without doing anything.</tt> </tt>
<a name="L382"></a><tt class="py-lineno">382</tt>  <tt class="py-line"><tt class="py-docstring">    """</tt> </tt>
<a name="L383"></a><tt class="py-lineno">383</tt>  <tt class="py-line">    <tt class="py-keyword">while</tt> <tt class="py-number">1</tt><tt class="py-op">:</tt> </tt>
<a name="L384"></a><tt class="py-lineno">384</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt class="py-keyword">not</tt> <tt class="py-name">unbalanced_start</tt><tt class="py-op">:</tt> </tt>
<a name="L385"></a><tt class="py-lineno">385</tt>  <tt class="py-line">            <tt class="py-comment"># We have totally succeeded in finding the position</tt> </tt>
<a name="L386"></a><tt class="py-lineno">386</tt>  <tt class="py-line">            <tt class="py-keyword">break</tt> </tt>
<a name="L387"></a><tt class="py-lineno">387</tt>  <tt class="py-line">        <tt class="py-name">finding</tt> <tt class="py-op">=</tt> <tt class="py-name">unbalanced_start</tt><tt class="py-op">[</tt><tt class="py-number">0</tt><tt class="py-op">]</tt> </tt>
<a name="L388"></a><tt class="py-lineno">388</tt>  <tt class="py-line">        <tt class="py-name">finding_name</tt> <tt class="py-op">=</tt> <tt class="py-name">finding</tt><tt class="py-op">.</tt><tt class="py-name">split</tt><tt class="py-op">(</tt><tt class="py-op">)</tt><tt class="py-op">[</tt><tt class="py-number">0</tt><tt class="py-op">]</tt><tt class="py-op">.</tt><tt id="link-128" class="py-name"><a title="lxml.doctestcompare.strip" class="py-name" href="#" onclick="return doclink('link-128', 'strip', 'link-19');">strip</a></tt><tt class="py-op">(</tt><tt class="py-string">'&lt;&gt;'</tt><tt class="py-op">)</tt> </tt>
<a name="L389"></a><tt class="py-lineno">389</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt class="py-keyword">not</tt> <tt class="py-name">post_delete</tt><tt class="py-op">:</tt> </tt>
<a name="L390"></a><tt class="py-lineno">390</tt>  <tt class="py-line">            <tt class="py-keyword">break</tt> </tt>
<a name="L391"></a><tt class="py-lineno">391</tt>  <tt class="py-line">        <tt id="link-129" class="py-name" targets="Method lxml.etree.ElementDepthFirstIterator.next()=lxml.etree.ElementDepthFirstIterator-class.html#next,Method lxml.etree.ElementTextIterator.next()=lxml.etree.ElementTextIterator-class.html#next,Method lxml.etree._ElementIterator.next()=lxml.etree._ElementIterator-class.html#next,Method lxml.etree._ElementMatchIterator.next()=lxml.etree._ElementMatchIterator-class.html#next,Method lxml.etree.iterparse.next()=lxml.etree.iterparse-class.html#next,Method lxml.etree.iterwalk.next()=lxml.etree.iterwalk-class.html#next"><a title="lxml.etree.ElementDepthFirstIterator.next
lxml.etree.ElementTextIterator.next
lxml.etree._ElementIterator.next
lxml.etree._ElementMatchIterator.next
lxml.etree.iterparse.next
lxml.etree.iterwalk.next" class="py-name" href="#" onclick="return doclink('link-129', 'next', 'link-129');">next</a></tt> <tt class="py-op">=</tt> <tt class="py-name">post_delete</tt><tt class="py-op">[</tt><tt class="py-number">0</tt><tt class="py-op">]</tt> </tt>
<a name="L392"></a><tt class="py-lineno">392</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt id="link-130" class="py-name"><a title="lxml.etree.ElementDepthFirstIterator.next
lxml.etree.ElementTextIterator.next
lxml.etree._ElementIterator.next
lxml.etree._ElementMatchIterator.next
lxml.etree.iterparse.next
lxml.etree.iterwalk.next" class="py-name" href="#" onclick="return doclink('link-130', 'next', 'link-129');">next</a></tt> <tt class="py-keyword">is</tt> <tt id="link-131" class="py-name"><a title="lxml.html.diff.DEL_START" class="py-name" href="#" onclick="return doclink('link-131', 'DEL_START', 'link-79');">DEL_START</a></tt> <tt class="py-keyword">or</tt> <tt class="py-keyword">not</tt> <tt id="link-132" class="py-name"><a title="lxml.etree.ElementDepthFirstIterator.next
lxml.etree.ElementTextIterator.next
lxml.etree._ElementIterator.next
lxml.etree._ElementMatchIterator.next
lxml.etree.iterparse.next
lxml.etree.iterwalk.next" class="py-name" href="#" onclick="return doclink('link-132', 'next', 'link-129');">next</a></tt><tt class="py-op">.</tt><tt class="py-name">startswith</tt><tt class="py-op">(</tt><tt class="py-string">'&lt;'</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
<a name="L393"></a><tt class="py-lineno">393</tt>  <tt class="py-line">            <tt class="py-comment"># Reached a word, we can't move the delete text forward</tt> </tt>
<a name="L394"></a><tt class="py-lineno">394</tt>  <tt class="py-line">            <tt class="py-keyword">break</tt> </tt>
<a name="L395"></a><tt class="py-lineno">395</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt id="link-133" class="py-name"><a title="lxml.etree.ElementDepthFirstIterator.next
lxml.etree.ElementTextIterator.next
lxml.etree._ElementIterator.next
lxml.etree._ElementMatchIterator.next
lxml.etree.iterparse.next
lxml.etree.iterwalk.next" class="py-name" href="#" onclick="return doclink('link-133', 'next', 'link-129');">next</a></tt><tt class="py-op">[</tt><tt class="py-number">1</tt><tt class="py-op">]</tt> <tt class="py-op">==</tt> <tt class="py-string">'/'</tt><tt class="py-op">:</tt> </tt>
<a name="L396"></a><tt class="py-lineno">396</tt>  <tt class="py-line">            <tt class="py-comment"># Reached a closing tag, can we go further?  Maybe not...</tt> </tt>
<a name="L397"></a><tt class="py-lineno">397</tt>  <tt class="py-line">            <tt class="py-keyword">break</tt> </tt>
<a name="L398"></a><tt class="py-lineno">398</tt>  <tt class="py-line">        <tt id="link-134" class="py-name"><a title="lxml.etree.DTD.name
lxml.etree._Entity.name
lxml.html.InputMixin.name
lxml.objectify.PyType.name" class="py-name" href="#" onclick="return doclink('link-134', 'name', 'link-95');">name</a></tt> <tt class="py-op">=</tt> <tt id="link-135" class="py-name"><a title="lxml.etree.ElementDepthFirstIterator.next
lxml.etree.ElementTextIterator.next
lxml.etree._ElementIterator.next
lxml.etree._ElementMatchIterator.next
lxml.etree.iterparse.next
lxml.etree.iterwalk.next" class="py-name" href="#" onclick="return doclink('link-135', 'next', 'link-129');">next</a></tt><tt class="py-op">.</tt><tt class="py-name">split</tt><tt class="py-op">(</tt><tt class="py-op">)</tt><tt class="py-op">[</tt><tt class="py-number">0</tt><tt class="py-op">]</tt><tt class="py-op">.</tt><tt id="link-136" class="py-name"><a title="lxml.doctestcompare.strip" class="py-name" href="#" onclick="return doclink('link-136', 'strip', 'link-19');">strip</a></tt><tt class="py-op">(</tt><tt class="py-string">'&lt;&gt;'</tt><tt class="py-op">)</tt> </tt>
<a name="L399"></a><tt class="py-lineno">399</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt id="link-137" class="py-name"><a title="lxml.etree.DTD.name
lxml.etree._Entity.name
lxml.html.InputMixin.name
lxml.objectify.PyType.name" class="py-name" href="#" onclick="return doclink('link-137', 'name', 'link-95');">name</a></tt> <tt class="py-op">==</tt> <tt class="py-string">'ins'</tt><tt class="py-op">:</tt> </tt>
<a name="L400"></a><tt class="py-lineno">400</tt>  <tt class="py-line">            <tt class="py-comment"># Can't move into an insert</tt> </tt>
<a name="L401"></a><tt class="py-lineno">401</tt>  <tt class="py-line">            <tt class="py-keyword">break</tt> </tt>
<a name="L402"></a><tt class="py-lineno">402</tt>  <tt class="py-line">        <tt class="py-keyword">assert</tt> <tt id="link-138" class="py-name"><a title="lxml.etree.DTD.name
lxml.etree._Entity.name
lxml.html.InputMixin.name
lxml.objectify.PyType.name" class="py-name" href="#" onclick="return doclink('link-138', 'name', 'link-95');">name</a></tt> <tt class="py-op">!=</tt> <tt class="py-string">'del'</tt><tt class="py-op">,</tt> <tt class="py-op">(</tt> </tt>
<a name="L403"></a><tt class="py-lineno">403</tt>  <tt class="py-line">            <tt class="py-string">"Unexpected delete tag: %r"</tt> <tt class="py-op">%</tt> <tt id="link-139" class="py-name"><a title="lxml.etree.ElementDepthFirstIterator.next
lxml.etree.ElementTextIterator.next
lxml.etree._ElementIterator.next
lxml.etree._ElementMatchIterator.next
lxml.etree.iterparse.next
lxml.etree.iterwalk.next" class="py-name" href="#" onclick="return doclink('link-139', 'next', 'link-129');">next</a></tt><tt class="py-op">)</tt> </tt>
<a name="L404"></a><tt class="py-lineno">404</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt id="link-140" class="py-name"><a title="lxml.etree.DTD.name
lxml.etree._Entity.name
lxml.html.InputMixin.name
lxml.objectify.PyType.name" class="py-name" href="#" onclick="return doclink('link-140', 'name', 'link-95');">name</a></tt> <tt class="py-op">==</tt> <tt class="py-name">finding_name</tt><tt class="py-op">:</tt> </tt>
<a name="L405"></a><tt class="py-lineno">405</tt>  <tt class="py-line">            <tt class="py-name">unbalanced_start</tt><tt class="py-op">.</tt><tt id="link-141" class="py-name"><a title="lxml.etree._Attrib.pop" class="py-name" href="#" onclick="return doclink('link-141', 'pop', 'link-104');">pop</a></tt><tt class="py-op">(</tt><tt class="py-number">0</tt><tt class="py-op">)</tt> </tt>
<a name="L406"></a><tt class="py-lineno">406</tt>  <tt class="py-line">            <tt class="py-name">pre_delete</tt><tt class="py-op">.</tt><tt id="link-142" class="py-name"><a title="lxml.etree._Element.append" class="py-name" href="#" onclick="return doclink('link-142', 'append', 'link-24');">append</a></tt><tt class="py-op">(</tt><tt class="py-name">post_delete</tt><tt class="py-op">.</tt><tt id="link-143" class="py-name"><a title="lxml.etree._Attrib.pop" class="py-name" href="#" onclick="return doclink('link-143', 'pop', 'link-104');">pop</a></tt><tt class="py-op">(</tt><tt class="py-number">0</tt><tt class="py-op">)</tt><tt class="py-op">)</tt> </tt>
<a name="L407"></a><tt class="py-lineno">407</tt>  <tt class="py-line">        <tt class="py-keyword">else</tt><tt class="py-op">:</tt> </tt>
<a name="L408"></a><tt class="py-lineno">408</tt>  <tt class="py-line">            <tt class="py-comment"># Found a tag that doesn't match</tt> </tt>
<a name="L409"></a><tt class="py-lineno">409</tt>  <tt class="py-line">            <tt class="py-keyword">break</tt> </tt>
</div><a name="L410"></a><tt class="py-lineno">410</tt>  <tt class="py-line"> </tt>
<a name="locate_unbalanced_end"></a><div id="locate_unbalanced_end-def"><a name="L411"></a><tt class="py-lineno">411</tt> <a class="py-toggle" href="#" id="locate_unbalanced_end-toggle" onclick="return toggle('locate_unbalanced_end');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#locate_unbalanced_end">locate_unbalanced_end</a><tt class="py-op">(</tt><tt class="py-param">unbalanced_end</tt><tt class="py-op">,</tt> <tt class="py-param">pre_delete</tt><tt class="py-op">,</tt> <tt class="py-param">post_delete</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="locate_unbalanced_end-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="locate_unbalanced_end-expanded"><a name="L412"></a><tt class="py-lineno">412</tt>  <tt class="py-line">    <tt class="py-docstring">""" like locate_unbalanced_start, except handling end tags and</tt> </tt>
<a name="L413"></a><tt class="py-lineno">413</tt>  <tt class="py-line"><tt class="py-docstring">    possibly moving the point earlier in the document.  """</tt> </tt>
<a name="L414"></a><tt class="py-lineno">414</tt>  <tt class="py-line">    <tt class="py-keyword">while</tt> <tt class="py-number">1</tt><tt class="py-op">:</tt> </tt>
<a name="L415"></a><tt class="py-lineno">415</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt class="py-keyword">not</tt> <tt class="py-name">unbalanced_end</tt><tt class="py-op">:</tt> </tt>
<a name="L416"></a><tt class="py-lineno">416</tt>  <tt class="py-line">            <tt class="py-comment"># Success</tt> </tt>
<a name="L417"></a><tt class="py-lineno">417</tt>  <tt class="py-line">            <tt class="py-keyword">break</tt> </tt>
<a name="L418"></a><tt class="py-lineno">418</tt>  <tt class="py-line">        <tt class="py-name">finding</tt> <tt class="py-op">=</tt> <tt class="py-name">unbalanced_end</tt><tt class="py-op">[</tt><tt class="py-op">-</tt><tt class="py-number">1</tt><tt class="py-op">]</tt> </tt>
<a name="L419"></a><tt class="py-lineno">419</tt>  <tt class="py-line">        <tt class="py-name">finding_name</tt> <tt class="py-op">=</tt> <tt class="py-name">finding</tt><tt class="py-op">.</tt><tt class="py-name">split</tt><tt class="py-op">(</tt><tt class="py-op">)</tt><tt class="py-op">[</tt><tt class="py-number">0</tt><tt class="py-op">]</tt><tt class="py-op">.</tt><tt id="link-144" class="py-name"><a title="lxml.doctestcompare.strip" class="py-name" href="#" onclick="return doclink('link-144', 'strip', 'link-19');">strip</a></tt><tt class="py-op">(</tt><tt class="py-string">'&lt;&gt;/'</tt><tt class="py-op">)</tt> </tt>
<a name="L420"></a><tt class="py-lineno">420</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt class="py-keyword">not</tt> <tt class="py-name">pre_delete</tt><tt class="py-op">:</tt> </tt>
<a name="L421"></a><tt class="py-lineno">421</tt>  <tt class="py-line">            <tt class="py-keyword">break</tt> </tt>
<a name="L422"></a><tt class="py-lineno">422</tt>  <tt class="py-line">        <tt id="link-145" class="py-name"><a title="lxml.etree.ElementDepthFirstIterator.next
lxml.etree.ElementTextIterator.next
lxml.etree._ElementIterator.next
lxml.etree._ElementMatchIterator.next
lxml.etree.iterparse.next
lxml.etree.iterwalk.next" class="py-name" href="#" onclick="return doclink('link-145', 'next', 'link-129');">next</a></tt> <tt class="py-op">=</tt> <tt class="py-name">pre_delete</tt><tt class="py-op">[</tt><tt class="py-op">-</tt><tt class="py-number">1</tt><tt class="py-op">]</tt> </tt>
<a name="L423"></a><tt class="py-lineno">423</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt id="link-146" class="py-name"><a title="lxml.etree.ElementDepthFirstIterator.next
lxml.etree.ElementTextIterator.next
lxml.etree._ElementIterator.next
lxml.etree._ElementMatchIterator.next
lxml.etree.iterparse.next
lxml.etree.iterwalk.next" class="py-name" href="#" onclick="return doclink('link-146', 'next', 'link-129');">next</a></tt> <tt class="py-keyword">is</tt> <tt id="link-147" class="py-name"><a title="lxml.html.diff.DEL_END" class="py-name" href="#" onclick="return doclink('link-147', 'DEL_END', 'link-82');">DEL_END</a></tt> <tt class="py-keyword">or</tt> <tt class="py-keyword">not</tt> <tt id="link-148" class="py-name"><a title="lxml.etree.ElementDepthFirstIterator.next
lxml.etree.ElementTextIterator.next
lxml.etree._ElementIterator.next
lxml.etree._ElementMatchIterator.next
lxml.etree.iterparse.next
lxml.etree.iterwalk.next" class="py-name" href="#" onclick="return doclink('link-148', 'next', 'link-129');">next</a></tt><tt class="py-op">.</tt><tt class="py-name">startswith</tt><tt class="py-op">(</tt><tt class="py-string">'&lt;/'</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
<a name="L424"></a><tt class="py-lineno">424</tt>  <tt class="py-line">            <tt class="py-comment"># A word or a start tag</tt> </tt>
<a name="L425"></a><tt class="py-lineno">425</tt>  <tt class="py-line">            <tt class="py-keyword">break</tt> </tt>
<a name="L426"></a><tt class="py-lineno">426</tt>  <tt class="py-line">        <tt id="link-149" class="py-name"><a title="lxml.etree.DTD.name
lxml.etree._Entity.name
lxml.html.InputMixin.name
lxml.objectify.PyType.name" class="py-name" href="#" onclick="return doclink('link-149', 'name', 'link-95');">name</a></tt> <tt class="py-op">=</tt> <tt id="link-150" class="py-name"><a title="lxml.etree.ElementDepthFirstIterator.next
lxml.etree.ElementTextIterator.next
lxml.etree._ElementIterator.next
lxml.etree._ElementMatchIterator.next
lxml.etree.iterparse.next
lxml.etree.iterwalk.next" class="py-name" href="#" onclick="return doclink('link-150', 'next', 'link-129');">next</a></tt><tt class="py-op">.</tt><tt class="py-name">split</tt><tt class="py-op">(</tt><tt class="py-op">)</tt><tt class="py-op">[</tt><tt class="py-number">0</tt><tt class="py-op">]</tt><tt class="py-op">.</tt><tt id="link-151" class="py-name"><a title="lxml.doctestcompare.strip" class="py-name" href="#" onclick="return doclink('link-151', 'strip', 'link-19');">strip</a></tt><tt class="py-op">(</tt><tt class="py-string">'&lt;&gt;/'</tt><tt class="py-op">)</tt> </tt>
<a name="L427"></a><tt class="py-lineno">427</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt id="link-152" class="py-name"><a title="lxml.etree.DTD.name
lxml.etree._Entity.name
lxml.html.InputMixin.name
lxml.objectify.PyType.name" class="py-name" href="#" onclick="return doclink('link-152', 'name', 'link-95');">name</a></tt> <tt class="py-op">==</tt> <tt class="py-string">'ins'</tt> <tt class="py-keyword">or</tt> <tt id="link-153" class="py-name"><a title="lxml.etree.DTD.name
lxml.etree._Entity.name
lxml.html.InputMixin.name
lxml.objectify.PyType.name" class="py-name" href="#" onclick="return doclink('link-153', 'name', 'link-95');">name</a></tt> <tt class="py-op">==</tt> <tt class="py-string">'del'</tt><tt class="py-op">:</tt> </tt>
<a name="L428"></a><tt class="py-lineno">428</tt>  <tt class="py-line">            <tt class="py-comment"># Can't move into an insert or delete</tt> </tt>
<a name="L429"></a><tt class="py-lineno">429</tt>  <tt class="py-line">            <tt class="py-keyword">break</tt> </tt>
<a name="L430"></a><tt class="py-lineno">430</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt id="link-154" class="py-name"><a title="lxml.etree.DTD.name
lxml.etree._Entity.name
lxml.html.InputMixin.name
lxml.objectify.PyType.name" class="py-name" href="#" onclick="return doclink('link-154', 'name', 'link-95');">name</a></tt> <tt class="py-op">==</tt> <tt class="py-name">finding_name</tt><tt class="py-op">:</tt> </tt>
<a name="L431"></a><tt class="py-lineno">431</tt>  <tt class="py-line">            <tt class="py-name">unbalanced_end</tt><tt class="py-op">.</tt><tt id="link-155" class="py-name"><a title="lxml.etree._Attrib.pop" class="py-name" href="#" onclick="return doclink('link-155', 'pop', 'link-104');">pop</a></tt><tt class="py-op">(</tt><tt class="py-op">)</tt> </tt>
<a name="L432"></a><tt class="py-lineno">432</tt>  <tt class="py-line">            <tt class="py-name">post_delete</tt><tt class="py-op">.</tt><tt id="link-156" class="py-name" targets="Method lxml.etree._Element.insert()=lxml.etree._Element-class.html#insert"><a title="lxml.etree._Element.insert" class="py-name" href="#" onclick="return doclink('link-156', 'insert', 'link-156');">insert</a></tt><tt class="py-op">(</tt><tt class="py-number">0</tt><tt class="py-op">,</tt> <tt class="py-name">pre_delete</tt><tt class="py-op">.</tt><tt id="link-157" class="py-name"><a title="lxml.etree._Attrib.pop" class="py-name" href="#" onclick="return doclink('link-157', 'pop', 'link-104');">pop</a></tt><tt class="py-op">(</tt><tt class="py-op">)</tt><tt class="py-op">)</tt> </tt>
<a name="L433"></a><tt class="py-lineno">433</tt>  <tt class="py-line">        <tt class="py-keyword">else</tt><tt class="py-op">:</tt> </tt>
<a name="L434"></a><tt class="py-lineno">434</tt>  <tt class="py-line">            <tt class="py-comment"># Found a tag that doesn't match</tt> </tt>
<a name="L435"></a><tt class="py-lineno">435</tt>  <tt class="py-line">            <tt class="py-keyword">break</tt> </tt>
</div><a name="L436"></a><tt class="py-lineno">436</tt>  <tt class="py-line"> </tt>
<a name="token"></a><div id="token-def"><a name="L437"></a><tt class="py-lineno">437</tt> <a class="py-toggle" href="#" id="token-toggle" onclick="return toggle('token');">-</a><tt class="py-line"><tt class="py-keyword">class</tt> <a class="py-def-name" href="lxml.html.diff.token-class.html">token</a><tt class="py-op">(</tt><tt class="py-base-class">_unicode</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="token-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="token-expanded"><a name="L438"></a><tt class="py-lineno">438</tt>  <tt class="py-line">    <tt class="py-docstring">""" Represents a diffable token, generally a word that is displayed to</tt> </tt>
<a name="L439"></a><tt class="py-lineno">439</tt>  <tt class="py-line"><tt class="py-docstring">    the user.  Opening tags are attached to this token when they are</tt> </tt>
<a name="L440"></a><tt class="py-lineno">440</tt>  <tt class="py-line"><tt class="py-docstring">    adjacent (pre_tags) and closing tags that follow the word</tt> </tt>
<a name="L441"></a><tt class="py-lineno">441</tt>  <tt class="py-line"><tt class="py-docstring">    (post_tags).  Some exceptions occur when there are empty tags</tt> </tt>
<a name="L442"></a><tt class="py-lineno">442</tt>  <tt class="py-line"><tt class="py-docstring">    adjacent to a word, so there may be close tags in pre_tags, or</tt> </tt>
<a name="L443"></a><tt class="py-lineno">443</tt>  <tt class="py-line"><tt class="py-docstring">    open tags in post_tags.</tt> </tt>
<a name="L444"></a><tt class="py-lineno">444</tt>  <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L445"></a><tt class="py-lineno">445</tt>  <tt class="py-line"><tt class="py-docstring">    We also keep track of whether the word was originally followed by</tt> </tt>
<a name="L446"></a><tt class="py-lineno">446</tt>  <tt class="py-line"><tt class="py-docstring">    whitespace, even though we do not want to treat the word as</tt> </tt>
<a name="L447"></a><tt class="py-lineno">447</tt>  <tt class="py-line"><tt class="py-docstring">    equivalent to a similar word that does not have a trailing</tt> </tt>
<a name="L448"></a><tt class="py-lineno">448</tt>  <tt class="py-line"><tt class="py-docstring">    space."""</tt> </tt>
<a name="L449"></a><tt class="py-lineno">449</tt>  <tt class="py-line"> </tt>
<a name="L450"></a><tt class="py-lineno">450</tt>  <tt class="py-line">    <tt class="py-comment"># When this is true, the token will be eliminated from the</tt> </tt>
<a name="L451"></a><tt class="py-lineno">451</tt>  <tt class="py-line">    <tt class="py-comment"># displayed diff if no change has occurred:</tt> </tt>
<a name="L452"></a><tt class="py-lineno">452</tt>  <tt class="py-line">    <tt id="link-158" class="py-name"><a title="lxml.html.diff.href_token.hide_when_equal
lxml.html.diff.token.hide_when_equal" class="py-name" href="#" onclick="return doclink('link-158', 'hide_when_equal', 'link-64');">hide_when_equal</a></tt> <tt class="py-op">=</tt> <tt class="py-name">False</tt> </tt>
<a name="L453"></a><tt class="py-lineno">453</tt>  <tt class="py-line"> </tt>
<a name="token.__new__"></a><div id="token.__new__-def"><a name="L454"></a><tt class="py-lineno">454</tt> <a class="py-toggle" href="#" id="token.__new__-toggle" onclick="return toggle('token.__new__');">-</a><tt class="py-line">    <tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff.token-class.html#__new__">__new__</a><tt class="py-op">(</tt><tt class="py-param">cls</tt><tt class="py-op">,</tt> <tt class="py-param">text</tt><tt class="py-op">,</tt> <tt class="py-param">pre_tags</tt><tt class="py-op">=</tt><tt class="py-name">None</tt><tt class="py-op">,</tt> <tt class="py-param">post_tags</tt><tt class="py-op">=</tt><tt class="py-name">None</tt><tt class="py-op">,</tt> <tt class="py-param">trailing_whitespace</tt><tt class="py-op">=</tt><tt class="py-string">""</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="token.__new__-collapsed" style="display:none;" pad="+++" indent="++++++++"></div><div id="token.__new__-expanded"><a name="L455"></a><tt class="py-lineno">455</tt>  <tt class="py-line">        <tt class="py-name">obj</tt> <tt class="py-op">=</tt> <tt class="py-name">_unicode</tt><tt class="py-op">.</tt><tt id="link-159" class="py-name" targets="Method lxml.builder.ElementMaker.__new__()=lxml.builder.ElementMaker-class.html#__new__,Method lxml.etree.AncestorsIterator.__new__()=lxml.etree.AncestorsIterator-class.html#__new__,Method lxml.etree.AttributeBasedElementClassLookup.__new__()=lxml.etree.AttributeBasedElementClassLookup-class.html#__new__,Method lxml.etree.C14NError.__new__()=lxml.etree.C14NError-class.html#__new__,Method lxml.etree.CDATA.__new__()=lxml.etree.CDATA-class.html#__new__,Method lxml.etree.CommentBase.__new__()=lxml.etree.CommentBase-class.html#__new__,Method lxml.etree.CustomElementClassLookup.__new__()=lxml.etree.CustomElementClassLookup-class.html#__new__,Method lxml.etree.DTD.__new__()=lxml.etree.DTD-class.html#__new__,Method lxml.etree.DTDError.__new__()=lxml.etree.DTDError-class.html#__new__,Method lxml.etree.DTDParseError.__new__()=lxml.etree.DTDParseError-class.html#__new__,Method lxml.etree.DTDValidateError.__new__()=lxml.etree.DTDValidateError-class.html#__new__,Method lxml.etree.DocInfo.__new__()=lxml.etree.DocInfo-class.html#__new__,Method lxml.etree.DocumentInvalid.__new__()=lxml.etree.DocumentInvalid-class.html#__new__,Method lxml.etree.ETCompatXMLParser.__new__()=lxml.etree.ETCompatXMLParser-class.html#__new__,Method lxml.etree.ETXPath.__new__()=lxml.etree.ETXPath-class.html#__new__,Method lxml.etree.ElementBase.__new__()=lxml.etree.ElementBase-class.html#__new__,Method lxml.etree.ElementChildIterator.__new__()=lxml.etree.ElementChildIterator-class.html#__new__,Method lxml.etree.ElementClassLookup.__new__()=lxml.etree.ElementClassLookup-class.html#__new__,Method lxml.etree.ElementDefaultClassLookup.__new__()=lxml.etree.ElementDefaultClassLookup-class.html#__new__,Method lxml.etree.ElementDepthFirstIterator.__new__()=lxml.etree.ElementDepthFirstIterator-class.html#__new__,Method lxml.etree.ElementNamespaceClassLookup.__new__()=lxml.etree.ElementNamespaceClassLookup-class.html#__new__,Method lxml.etree.ElementTextIterator.__new__()=lxml.etree.ElementTextIterator-class.html#__new__,Method lxml.etree.EntityBase.__new__()=lxml.etree.EntityBase-class.html#__new__,Method lxml.etree.Error.__new__()=lxml.etree.Error-class.html#__new__,Method lxml.etree.FallbackElementClassLookup.__new__()=lxml.etree.FallbackElementClassLookup-class.html#__new__,Method lxml.etree.HTMLParser.__new__()=lxml.etree.HTMLParser-class.html#__new__,Method lxml.etree.HTMLPullParser.__new__()=lxml.etree.HTMLPullParser-class.html#__new__,Method lxml.etree.LxmlError.__new__()=lxml.etree.LxmlError-class.html#__new__,Method lxml.etree.LxmlRegistryError.__new__()=lxml.etree.LxmlRegistryError-class.html#__new__,Method lxml.etree.NamespaceRegistryError.__new__()=lxml.etree.NamespaceRegistryError-class.html#__new__,Method lxml.etree.PIBase.__new__()=lxml.etree.PIBase-class.html#__new__,Method lxml.etree.ParserBasedElementClassLookup.__new__()=lxml.etree.ParserBasedElementClassLookup-class.html#__new__,Method lxml.etree.ParserError.__new__()=lxml.etree.ParserError-class.html#__new__,Method lxml.etree.PyErrorLog.__new__()=lxml.etree.PyErrorLog-class.html#__new__,Method lxml.etree.PythonElementClassLookup.__new__()=lxml.etree.PythonElementClassLookup-class.html#__new__,Method lxml.etree.QName.__new__()=lxml.etree.QName-class.html#__new__,Method lxml.etree.RelaxNG.__new__()=lxml.etree.RelaxNG-class.html#__new__,Method lxml.etree.RelaxNGError.__new__()=lxml.etree.RelaxNGError-class.html#__new__,Method lxml.etree.RelaxNGParseError.__new__()=lxml.etree.RelaxNGParseError-class.html#__new__,Method lxml.etree.RelaxNGValidateError.__new__()=lxml.etree.RelaxNGValidateError-class.html#__new__,Method lxml.etree.Resolver.__new__()=lxml.etree.Resolver-class.html#__new__,Method lxml.etree.Schematron.__new__()=lxml.etree.Schematron-class.html#__new__,Method lxml.etree.SchematronError.__new__()=lxml.etree.SchematronError-class.html#__new__,Method lxml.etree.SchematronParseError.__new__()=lxml.etree.SchematronParseError-class.html#__new__,Method lxml.etree.SchematronValidateError.__new__()=lxml.etree.SchematronValidateError-class.html#__new__,Method lxml.etree.SerialisationError.__new__()=lxml.etree.SerialisationError-class.html#__new__,Method lxml.etree.SiblingsIterator.__new__()=lxml.etree.SiblingsIterator-class.html#__new__,Method lxml.etree.TreeBuilder.__new__()=lxml.etree.TreeBuilder-class.html#__new__,Method lxml.etree.XInclude.__new__()=lxml.etree.XInclude-class.html#__new__,Method lxml.etree.XIncludeError.__new__()=lxml.etree.XIncludeError-class.html#__new__,Method lxml.etree.XMLParser.__new__()=lxml.etree.XMLParser-class.html#__new__,Method lxml.etree.XMLPullParser.__new__()=lxml.etree.XMLPullParser-class.html#__new__,Method lxml.etree.XMLSchema.__new__()=lxml.etree.XMLSchema-class.html#__new__,Method lxml.etree.XMLSchemaError.__new__()=lxml.etree.XMLSchemaError-class.html#__new__,Method lxml.etree.XMLSchemaParseError.__new__()=lxml.etree.XMLSchemaParseError-class.html#__new__,Method lxml.etree.XMLSchemaValidateError.__new__()=lxml.etree.XMLSchemaValidateError-class.html#__new__,Method lxml.etree.XPath.__new__()=lxml.etree.XPath-class.html#__new__,Method lxml.etree.XPathDocumentEvaluator.__new__()=lxml.etree.XPathDocumentEvaluator-class.html#__new__,Method lxml.etree.XPathElementEvaluator.__new__()=lxml.etree.XPathElementEvaluator-class.html#__new__,Method lxml.etree.XPathError.__new__()=lxml.etree.XPathError-class.html#__new__,Method lxml.etree.XPathEvalError.__new__()=lxml.etree.XPathEvalError-class.html#__new__,Method lxml.etree.XPathFunctionError.__new__()=lxml.etree.XPathFunctionError-class.html#__new__,Method lxml.etree.XPathResultError.__new__()=lxml.etree.XPathResultError-class.html#__new__,Method lxml.etree.XSLT.__new__()=lxml.etree.XSLT-class.html#__new__,Method lxml.etree.XSLTAccessControl.__new__()=lxml.etree.XSLTAccessControl-class.html#__new__,Method lxml.etree.XSLTApplyError.__new__()=lxml.etree.XSLTApplyError-class.html#__new__,Method lxml.etree.XSLTError.__new__()=lxml.etree.XSLTError-class.html#__new__,Method lxml.etree.XSLTExtension.__new__()=lxml.etree.XSLTExtension-class.html#__new__,Method lxml.etree.XSLTExtensionError.__new__()=lxml.etree.XSLTExtensionError-class.html#__new__,Method lxml.etree.XSLTParseError.__new__()=lxml.etree.XSLTParseError-class.html#__new__,Method lxml.etree._Attrib.__new__()=lxml.etree._Attrib-class.html#__new__,Method lxml.etree._BaseErrorLog.__new__()=lxml.etree._BaseErrorLog-class.html#__new__,Method lxml.etree._Comment.__new__()=lxml.etree._Comment-class.html#__new__,Method lxml.etree._Document.__new__()=lxml.etree._Document-class.html#__new__,Method lxml.etree._DomainErrorLog.__new__()=lxml.etree._DomainErrorLog-class.html#__new__,Method lxml.etree._Element.__new__()=lxml.etree._Element-class.html#__new__,Method lxml.etree._ElementIterator.__new__()=lxml.etree._ElementIterator-class.html#__new__,Method lxml.etree._ElementMatchIterator.__new__()=lxml.etree._ElementMatchIterator-class.html#__new__,Method lxml.etree._ElementTagMatcher.__new__()=lxml.etree._ElementTagMatcher-class.html#__new__,Method lxml.etree._ElementTree.__new__()=lxml.etree._ElementTree-class.html#__new__,Method lxml.etree._ElementUnicodeResult.__new__()=lxml.etree._ElementUnicodeResult-class.html#__new__,Method lxml.etree._Entity.__new__()=lxml.etree._Entity-class.html#__new__,Method lxml.etree._ErrorLog.__new__()=lxml.etree._ErrorLog-class.html#__new__,Method lxml.etree._FeedParser.__new__()=lxml.etree._FeedParser-class.html#__new__,Method lxml.etree._IDDict.__new__()=lxml.etree._IDDict-class.html#__new__,Method lxml.etree._ListErrorLog.__new__()=lxml.etree._ListErrorLog-class.html#__new__,Method lxml.etree._LogEntry.__new__()=lxml.etree._LogEntry-class.html#__new__,Method lxml.etree._ProcessingInstruction.__new__()=lxml.etree._ProcessingInstruction-class.html#__new__,Method lxml.etree._RotatingErrorLog.__new__()=lxml.etree._RotatingErrorLog-class.html#__new__,Method lxml.etree._SaxParserTarget.__new__()=lxml.etree._SaxParserTarget-class.html#__new__,Method lxml.etree._Validator.__new__()=lxml.etree._Validator-class.html#__new__,Method lxml.etree._XPathEvaluatorBase.__new__()=lxml.etree._XPathEvaluatorBase-class.html#__new__,Method lxml.etree._XSLTProcessingInstruction.__new__()=lxml.etree._XSLTProcessingInstruction-class.html#__new__,Method lxml.etree._XSLTResultTree.__new__()=lxml.etree._XSLTResultTree-class.html#__new__,Method lxml.etree.htmlfile.__new__()=lxml.etree.htmlfile-class.html#__new__,Method lxml.etree.iterparse.__new__()=lxml.etree.iterparse-class.html#__new__,Method lxml.etree.iterwalk.__new__()=lxml.etree.iterwalk-class.html#__new__,Method lxml.etree.xmlfile.__new__()=lxml.etree.xmlfile-class.html#__new__,Method lxml.html.diff.tag_token.__new__()=lxml.html.diff.tag_token-class.html#__new__,Method lxml.html.diff.token.__new__()=lxml.html.diff.token-class.html#__new__,Method lxml.objectify.BoolElement.__new__()=lxml.objectify.BoolElement-class.html#__new__,Method lxml.objectify.ElementMaker.__new__()=lxml.objectify.ElementMaker-class.html#__new__,Method lxml.objectify.FloatElement.__new__()=lxml.objectify.FloatElement-class.html#__new__,Method lxml.objectify.IntElement.__new__()=lxml.objectify.IntElement-class.html#__new__,Method lxml.objectify.LongElement.__new__()=lxml.objectify.LongElement-class.html#__new__,Method lxml.objectify.NoneElement.__new__()=lxml.objectify.NoneElement-class.html#__new__,Method lxml.objectify.NumberElement.__new__()=lxml.objectify.NumberElement-class.html#__new__,Method lxml.objectify.ObjectPath.__new__()=lxml.objectify.ObjectPath-class.html#__new__,Method lxml.objectify.ObjectifiedDataElement.__new__()=lxml.objectify.ObjectifiedDataElement-class.html#__new__,Method lxml.objectify.ObjectifiedElement.__new__()=lxml.objectify.ObjectifiedElement-class.html#__new__,Method lxml.objectify.ObjectifyElementClassLookup.__new__()=lxml.objectify.ObjectifyElementClassLookup-class.html#__new__,Method lxml.objectify.PyType.__new__()=lxml.objectify.PyType-class.html#__new__,Method lxml.objectify.StringElement.__new__()=lxml.objectify.StringElement-class.html#__new__"><a title="lxml.builder.ElementMaker.__new__
lxml.etree.AncestorsIterator.__new__
lxml.etree.AttributeBasedElementClassLookup.__new__
lxml.etree.C14NError.__new__
lxml.etree.CDATA.__new__
lxml.etree.CommentBase.__new__
lxml.etree.CustomElementClassLookup.__new__
lxml.etree.DTD.__new__
lxml.etree.DTDError.__new__
lxml.etree.DTDParseError.__new__
lxml.etree.DTDValidateError.__new__
lxml.etree.DocInfo.__new__
lxml.etree.DocumentInvalid.__new__
lxml.etree.ETCompatXMLParser.__new__
lxml.etree.ETXPath.__new__
lxml.etree.ElementBase.__new__
lxml.etree.ElementChildIterator.__new__
lxml.etree.ElementClassLookup.__new__
lxml.etree.ElementDefaultClassLookup.__new__
lxml.etree.ElementDepthFirstIterator.__new__
lxml.etree.ElementNamespaceClassLookup.__new__
lxml.etree.ElementTextIterator.__new__
lxml.etree.EntityBase.__new__
lxml.etree.Error.__new__
lxml.etree.FallbackElementClassLookup.__new__
lxml.etree.HTMLParser.__new__
lxml.etree.HTMLPullParser.__new__
lxml.etree.LxmlError.__new__
lxml.etree.LxmlRegistryError.__new__
lxml.etree.NamespaceRegistryError.__new__
lxml.etree.PIBase.__new__
lxml.etree.ParserBasedElementClassLookup.__new__
lxml.etree.ParserError.__new__
lxml.etree.PyErrorLog.__new__
lxml.etree.PythonElementClassLookup.__new__
lxml.etree.QName.__new__
lxml.etree.RelaxNG.__new__
lxml.etree.RelaxNGError.__new__
lxml.etree.RelaxNGParseError.__new__
lxml.etree.RelaxNGValidateError.__new__
lxml.etree.Resolver.__new__
lxml.etree.Schematron.__new__
lxml.etree.SchematronError.__new__
lxml.etree.SchematronParseError.__new__
lxml.etree.SchematronValidateError.__new__
lxml.etree.SerialisationError.__new__
lxml.etree.SiblingsIterator.__new__
lxml.etree.TreeBuilder.__new__
lxml.etree.XInclude.__new__
lxml.etree.XIncludeError.__new__
lxml.etree.XMLParser.__new__
lxml.etree.XMLPullParser.__new__
lxml.etree.XMLSchema.__new__
lxml.etree.XMLSchemaError.__new__
lxml.etree.XMLSchemaParseError.__new__
lxml.etree.XMLSchemaValidateError.__new__
lxml.etree.XPath.__new__
lxml.etree.XPathDocumentEvaluator.__new__
lxml.etree.XPathElementEvaluator.__new__
lxml.etree.XPathError.__new__
lxml.etree.XPathEvalError.__new__
lxml.etree.XPathFunctionError.__new__
lxml.etree.XPathResultError.__new__
lxml.etree.XSLT.__new__
lxml.etree.XSLTAccessControl.__new__
lxml.etree.XSLTApplyError.__new__
lxml.etree.XSLTError.__new__
lxml.etree.XSLTExtension.__new__
lxml.etree.XSLTExtensionError.__new__
lxml.etree.XSLTParseError.__new__
lxml.etree._Attrib.__new__
lxml.etree._BaseErrorLog.__new__
lxml.etree._Comment.__new__
lxml.etree._Document.__new__
lxml.etree._DomainErrorLog.__new__
lxml.etree._Element.__new__
lxml.etree._ElementIterator.__new__
lxml.etree._ElementMatchIterator.__new__
lxml.etree._ElementTagMatcher.__new__
lxml.etree._ElementTree.__new__
lxml.etree._ElementUnicodeResult.__new__
lxml.etree._Entity.__new__
lxml.etree._ErrorLog.__new__
lxml.etree._FeedParser.__new__
lxml.etree._IDDict.__new__
lxml.etree._ListErrorLog.__new__
lxml.etree._LogEntry.__new__
lxml.etree._ProcessingInstruction.__new__
lxml.etree._RotatingErrorLog.__new__
lxml.etree._SaxParserTarget.__new__
lxml.etree._Validator.__new__
lxml.etree._XPathEvaluatorBase.__new__
lxml.etree._XSLTProcessingInstruction.__new__
lxml.etree._XSLTResultTree.__new__
lxml.etree.htmlfile.__new__
lxml.etree.iterparse.__new__
lxml.etree.iterwalk.__new__
lxml.etree.xmlfile.__new__
lxml.html.diff.tag_token.__new__
lxml.html.diff.token.__new__
lxml.objectify.BoolElement.__new__
lxml.objectify.ElementMaker.__new__
lxml.objectify.FloatElement.__new__
lxml.objectify.IntElement.__new__
lxml.objectify.LongElement.__new__
lxml.objectify.NoneElement.__new__
lxml.objectify.NumberElement.__new__
lxml.objectify.ObjectPath.__new__
lxml.objectify.ObjectifiedDataElement.__new__
lxml.objectify.ObjectifiedElement.__new__
lxml.objectify.ObjectifyElementClassLookup.__new__
lxml.objectify.PyType.__new__
lxml.objectify.StringElement.__new__" class="py-name" href="#" onclick="return doclink('link-159', '__new__', 'link-159');">__new__</a></tt><tt class="py-op">(</tt><tt class="py-name">cls</tt><tt class="py-op">,</tt> <tt id="link-160" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-160', 'text', 'link-11');">text</a></tt><tt class="py-op">)</tt> </tt>
<a name="L456"></a><tt class="py-lineno">456</tt>  <tt class="py-line"> </tt>
<a name="L457"></a><tt class="py-lineno">457</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt class="py-name">pre_tags</tt> <tt class="py-keyword">is</tt> <tt class="py-keyword">not</tt> <tt class="py-name">None</tt><tt class="py-op">:</tt> </tt>
<a name="L458"></a><tt class="py-lineno">458</tt>  <tt class="py-line">            <tt class="py-name">obj</tt><tt class="py-op">.</tt><tt class="py-name">pre_tags</tt> <tt class="py-op">=</tt> <tt class="py-name">pre_tags</tt> </tt>
<a name="L459"></a><tt class="py-lineno">459</tt>  <tt class="py-line">        <tt class="py-keyword">else</tt><tt class="py-op">:</tt> </tt>
<a name="L460"></a><tt class="py-lineno">460</tt>  <tt class="py-line">            <tt class="py-name">obj</tt><tt class="py-op">.</tt><tt class="py-name">pre_tags</tt> <tt class="py-op">=</tt> <tt class="py-op">[</tt><tt class="py-op">]</tt> </tt>
<a name="L461"></a><tt class="py-lineno">461</tt>  <tt class="py-line"> </tt>
<a name="L462"></a><tt class="py-lineno">462</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt class="py-name">post_tags</tt> <tt class="py-keyword">is</tt> <tt class="py-keyword">not</tt> <tt class="py-name">None</tt><tt class="py-op">:</tt> </tt>
<a name="L463"></a><tt class="py-lineno">463</tt>  <tt class="py-line">            <tt class="py-name">obj</tt><tt class="py-op">.</tt><tt class="py-name">post_tags</tt> <tt class="py-op">=</tt> <tt class="py-name">post_tags</tt> </tt>
<a name="L464"></a><tt class="py-lineno">464</tt>  <tt class="py-line">        <tt class="py-keyword">else</tt><tt class="py-op">:</tt> </tt>
<a name="L465"></a><tt class="py-lineno">465</tt>  <tt class="py-line">            <tt class="py-name">obj</tt><tt class="py-op">.</tt><tt class="py-name">post_tags</tt> <tt class="py-op">=</tt> <tt class="py-op">[</tt><tt class="py-op">]</tt> </tt>
<a name="L466"></a><tt class="py-lineno">466</tt>  <tt class="py-line"> </tt>
<a name="L467"></a><tt class="py-lineno">467</tt>  <tt class="py-line">        <tt class="py-name">obj</tt><tt class="py-op">.</tt><tt class="py-name">trailing_whitespace</tt> <tt class="py-op">=</tt> <tt class="py-name">trailing_whitespace</tt> </tt>
<a name="L468"></a><tt class="py-lineno">468</tt>  <tt class="py-line"> </tt>
<a name="L469"></a><tt class="py-lineno">469</tt>  <tt class="py-line">        <tt class="py-keyword">return</tt> <tt class="py-name">obj</tt> </tt>
</div><a name="L470"></a><tt class="py-lineno">470</tt>  <tt class="py-line"> </tt>
<a name="token.__repr__"></a><div id="token.__repr__-def"><a name="L471"></a><tt class="py-lineno">471</tt> <a class="py-toggle" href="#" id="token.__repr__-toggle" onclick="return toggle('token.__repr__');">-</a><tt class="py-line">    <tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff.token-class.html#__repr__">__repr__</a><tt class="py-op">(</tt><tt class="py-param">self</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="token.__repr__-collapsed" style="display:none;" pad="+++" indent="++++++++"></div><div id="token.__repr__-expanded"><a name="L472"></a><tt class="py-lineno">472</tt>  <tt class="py-line">        <tt class="py-keyword">return</tt> <tt class="py-string">'token(%s, %r, %r, %r)'</tt> <tt class="py-op">%</tt> <tt class="py-op">(</tt><tt class="py-name">_unicode</tt><tt class="py-op">.</tt><tt id="link-161" class="py-name" targets="Method lxml.cssselect.CSSSelector.__repr__()=lxml.cssselect.CSSSelector-class.html#__repr__,Method lxml.etree.XPath.__repr__()=lxml.etree.XPath-class.html#__repr__,Method lxml.etree.XSLTAccessControl.__repr__()=lxml.etree.XSLTAccessControl-class.html#__repr__,Method lxml.etree._Attrib.__repr__()=lxml.etree._Attrib-class.html#__repr__,Method lxml.etree._BaseErrorLog.__repr__()=lxml.etree._BaseErrorLog-class.html#__repr__,Method lxml.etree._Comment.__repr__()=lxml.etree._Comment-class.html#__repr__,Method lxml.etree._Element.__repr__()=lxml.etree._Element-class.html#__repr__,Method lxml.etree._Entity.__repr__()=lxml.etree._Entity-class.html#__repr__,Method lxml.etree._IDDict.__repr__()=lxml.etree._IDDict-class.html#__repr__,Method lxml.etree._ListErrorLog.__repr__()=lxml.etree._ListErrorLog-class.html#__repr__,Method lxml.etree._LogEntry.__repr__()=lxml.etree._LogEntry-class.html#__repr__,Method lxml.etree._ProcessingInstruction.__repr__()=lxml.etree._ProcessingInstruction-class.html#__repr__,Method lxml.html.CheckboxGroup.__repr__()=lxml.html.CheckboxGroup-class.html#__repr__,Method lxml.html.CheckboxValues.__repr__()=lxml.html.CheckboxValues-class.html#__repr__,Method lxml.html.FieldsDict.__repr__()=lxml.html.FieldsDict-class.html#__repr__,Method lxml.html.InputGetter.__repr__()=lxml.html.InputGetter-class.html#__repr__,Method lxml.html.InputMixin.__repr__()=lxml.html.InputMixin-class.html#__repr__,Method lxml.html.MultipleSelectOptions.__repr__()=lxml.html.MultipleSelectOptions-class.html#__repr__,Method lxml.html.RadioGroup.__repr__()=lxml.html.RadioGroup-class.html#__repr__,Method lxml.html.diff.tag_token.__repr__()=lxml.html.diff.tag_token-class.html#__repr__,Method lxml.html.diff.token.__repr__()=lxml.html.diff.token-class.html#__repr__,Method lxml.objectify.BoolElement.__repr__()=lxml.objectify.BoolElement-class.html#__repr__,Method lxml.objectify.NoneElement.__repr__()=lxml.objectify.NoneElement-class.html#__repr__,Method lxml.objectify.NumberElement.__repr__()=lxml.objectify.NumberElement-class.html#__repr__,Method lxml.objectify.ObjectifiedDataElement.__repr__()=lxml.objectify.ObjectifiedDataElement-class.html#__repr__,Method lxml.objectify.PyType.__repr__()=lxml.objectify.PyType-class.html#__repr__,Method lxml.objectify.StringElement.__repr__()=lxml.objectify.StringElement-class.html#__repr__"><a title="lxml.cssselect.CSSSelector.__repr__
lxml.etree.XPath.__repr__
lxml.etree.XSLTAccessControl.__repr__
lxml.etree._Attrib.__repr__
lxml.etree._BaseErrorLog.__repr__
lxml.etree._Comment.__repr__
lxml.etree._Element.__repr__
lxml.etree._Entity.__repr__
lxml.etree._IDDict.__repr__
lxml.etree._ListErrorLog.__repr__
lxml.etree._LogEntry.__repr__
lxml.etree._ProcessingInstruction.__repr__
lxml.html.CheckboxGroup.__repr__
lxml.html.CheckboxValues.__repr__
lxml.html.FieldsDict.__repr__
lxml.html.InputGetter.__repr__
lxml.html.InputMixin.__repr__
lxml.html.MultipleSelectOptions.__repr__
lxml.html.RadioGroup.__repr__
lxml.html.diff.tag_token.__repr__
lxml.html.diff.token.__repr__
lxml.objectify.BoolElement.__repr__
lxml.objectify.NoneElement.__repr__
lxml.objectify.NumberElement.__repr__
lxml.objectify.ObjectifiedDataElement.__repr__
lxml.objectify.PyType.__repr__
lxml.objectify.StringElement.__repr__" class="py-name" href="#" onclick="return doclink('link-161', '__repr__', 'link-161');">__repr__</a></tt><tt class="py-op">(</tt><tt class="py-name">self</tt><tt class="py-op">)</tt><tt class="py-op">,</tt> <tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">pre_tags</tt><tt class="py-op">,</tt> </tt>
<a name="L473"></a><tt class="py-lineno">473</tt>  <tt class="py-line">                                          <tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">post_tags</tt><tt class="py-op">,</tt> <tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">trailing_whitespace</tt><tt class="py-op">)</tt> </tt>
</div><a name="L474"></a><tt class="py-lineno">474</tt>  <tt class="py-line"> </tt>
<a name="token.html"></a><div id="token.html-def"><a name="L475"></a><tt class="py-lineno">475</tt> <a class="py-toggle" href="#" id="token.html-toggle" onclick="return toggle('token.html');">-</a><tt class="py-line">    <tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff.token-class.html#html">html</a><tt class="py-op">(</tt><tt class="py-param">self</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="token.html-collapsed" style="display:none;" pad="+++" indent="++++++++"></div><div id="token.html-expanded"><a name="L476"></a><tt class="py-lineno">476</tt>  <tt class="py-line">        <tt class="py-keyword">return</tt> <tt class="py-name">_unicode</tt><tt class="py-op">(</tt><tt class="py-name">self</tt><tt class="py-op">)</tt> </tt>
</div></div><a name="L477"></a><tt class="py-lineno">477</tt>  <tt class="py-line"> </tt>
<a name="tag_token"></a><div id="tag_token-def"><a name="L478"></a><tt class="py-lineno">478</tt> <a class="py-toggle" href="#" id="tag_token-toggle" onclick="return toggle('tag_token');">-</a><tt class="py-line"><tt class="py-keyword">class</tt> <a class="py-def-name" href="lxml.html.diff.tag_token-class.html">tag_token</a><tt class="py-op">(</tt><tt class="py-base-class">token</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="tag_token-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="tag_token-expanded"><a name="L479"></a><tt class="py-lineno">479</tt>  <tt class="py-line"> </tt>
<a name="L480"></a><tt class="py-lineno">480</tt>  <tt class="py-line">    <tt class="py-docstring">""" Represents a token that is actually a tag.  Currently this is just</tt> </tt>
<a name="L481"></a><tt class="py-lineno">481</tt>  <tt class="py-line"><tt class="py-docstring">    the &lt;img&gt; tag, which takes up visible space just like a word but</tt> </tt>
<a name="L482"></a><tt class="py-lineno">482</tt>  <tt class="py-line"><tt class="py-docstring">    is only represented in a document by a tag.  """</tt> </tt>
<a name="L483"></a><tt class="py-lineno">483</tt>  <tt class="py-line"> </tt>
<a name="tag_token.__new__"></a><div id="tag_token.__new__-def"><a name="L484"></a><tt class="py-lineno">484</tt> <a class="py-toggle" href="#" id="tag_token.__new__-toggle" onclick="return toggle('tag_token.__new__');">-</a><tt class="py-line">    <tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff.tag_token-class.html#__new__">__new__</a><tt class="py-op">(</tt><tt class="py-param">cls</tt><tt class="py-op">,</tt> <tt class="py-param">tag</tt><tt class="py-op">,</tt> <tt class="py-param">data</tt><tt class="py-op">,</tt> <tt class="py-param">html_repr</tt><tt class="py-op">,</tt> <tt class="py-param">pre_tags</tt><tt class="py-op">=</tt><tt class="py-name">None</tt><tt class="py-op">,</tt>  </tt>
<a name="L485"></a><tt class="py-lineno">485</tt>  <tt class="py-line">                <tt class="py-param">post_tags</tt><tt class="py-op">=</tt><tt class="py-name">None</tt><tt class="py-op">,</tt> <tt class="py-param">trailing_whitespace</tt><tt class="py-op">=</tt><tt class="py-string">""</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="tag_token.__new__-collapsed" style="display:none;" pad="+++" indent="++++++++"></div><div id="tag_token.__new__-expanded"><a name="L486"></a><tt class="py-lineno">486</tt>  <tt class="py-line">        <tt class="py-name">obj</tt> <tt class="py-op">=</tt> <tt id="link-162" class="py-name"><a title="lxml.html.diff.token" class="py-name" href="#" onclick="return doclink('link-162', 'token', 'link-26');">token</a></tt><tt class="py-op">.</tt><tt id="link-163" class="py-name"><a title="lxml.builder.ElementMaker.__new__
lxml.etree.AncestorsIterator.__new__
lxml.etree.AttributeBasedElementClassLookup.__new__
lxml.etree.C14NError.__new__
lxml.etree.CDATA.__new__
lxml.etree.CommentBase.__new__
lxml.etree.CustomElementClassLookup.__new__
lxml.etree.DTD.__new__
lxml.etree.DTDError.__new__
lxml.etree.DTDParseError.__new__
lxml.etree.DTDValidateError.__new__
lxml.etree.DocInfo.__new__
lxml.etree.DocumentInvalid.__new__
lxml.etree.ETCompatXMLParser.__new__
lxml.etree.ETXPath.__new__
lxml.etree.ElementBase.__new__
lxml.etree.ElementChildIterator.__new__
lxml.etree.ElementClassLookup.__new__
lxml.etree.ElementDefaultClassLookup.__new__
lxml.etree.ElementDepthFirstIterator.__new__
lxml.etree.ElementNamespaceClassLookup.__new__
lxml.etree.ElementTextIterator.__new__
lxml.etree.EntityBase.__new__
lxml.etree.Error.__new__
lxml.etree.FallbackElementClassLookup.__new__
lxml.etree.HTMLParser.__new__
lxml.etree.HTMLPullParser.__new__
lxml.etree.LxmlError.__new__
lxml.etree.LxmlRegistryError.__new__
lxml.etree.NamespaceRegistryError.__new__
lxml.etree.PIBase.__new__
lxml.etree.ParserBasedElementClassLookup.__new__
lxml.etree.ParserError.__new__
lxml.etree.PyErrorLog.__new__
lxml.etree.PythonElementClassLookup.__new__
lxml.etree.QName.__new__
lxml.etree.RelaxNG.__new__
lxml.etree.RelaxNGError.__new__
lxml.etree.RelaxNGParseError.__new__
lxml.etree.RelaxNGValidateError.__new__
lxml.etree.Resolver.__new__
lxml.etree.Schematron.__new__
lxml.etree.SchematronError.__new__
lxml.etree.SchematronParseError.__new__
lxml.etree.SchematronValidateError.__new__
lxml.etree.SerialisationError.__new__
lxml.etree.SiblingsIterator.__new__
lxml.etree.TreeBuilder.__new__
lxml.etree.XInclude.__new__
lxml.etree.XIncludeError.__new__
lxml.etree.XMLParser.__new__
lxml.etree.XMLPullParser.__new__
lxml.etree.XMLSchema.__new__
lxml.etree.XMLSchemaError.__new__
lxml.etree.XMLSchemaParseError.__new__
lxml.etree.XMLSchemaValidateError.__new__
lxml.etree.XPath.__new__
lxml.etree.XPathDocumentEvaluator.__new__
lxml.etree.XPathElementEvaluator.__new__
lxml.etree.XPathError.__new__
lxml.etree.XPathEvalError.__new__
lxml.etree.XPathFunctionError.__new__
lxml.etree.XPathResultError.__new__
lxml.etree.XSLT.__new__
lxml.etree.XSLTAccessControl.__new__
lxml.etree.XSLTApplyError.__new__
lxml.etree.XSLTError.__new__
lxml.etree.XSLTExtension.__new__
lxml.etree.XSLTExtensionError.__new__
lxml.etree.XSLTParseError.__new__
lxml.etree._Attrib.__new__
lxml.etree._BaseErrorLog.__new__
lxml.etree._Comment.__new__
lxml.etree._Document.__new__
lxml.etree._DomainErrorLog.__new__
lxml.etree._Element.__new__
lxml.etree._ElementIterator.__new__
lxml.etree._ElementMatchIterator.__new__
lxml.etree._ElementTagMatcher.__new__
lxml.etree._ElementTree.__new__
lxml.etree._ElementUnicodeResult.__new__
lxml.etree._Entity.__new__
lxml.etree._ErrorLog.__new__
lxml.etree._FeedParser.__new__
lxml.etree._IDDict.__new__
lxml.etree._ListErrorLog.__new__
lxml.etree._LogEntry.__new__
lxml.etree._ProcessingInstruction.__new__
lxml.etree._RotatingErrorLog.__new__
lxml.etree._SaxParserTarget.__new__
lxml.etree._Validator.__new__
lxml.etree._XPathEvaluatorBase.__new__
lxml.etree._XSLTProcessingInstruction.__new__
lxml.etree._XSLTResultTree.__new__
lxml.etree.htmlfile.__new__
lxml.etree.iterparse.__new__
lxml.etree.iterwalk.__new__
lxml.etree.xmlfile.__new__
lxml.html.diff.tag_token.__new__
lxml.html.diff.token.__new__
lxml.objectify.BoolElement.__new__
lxml.objectify.ElementMaker.__new__
lxml.objectify.FloatElement.__new__
lxml.objectify.IntElement.__new__
lxml.objectify.LongElement.__new__
lxml.objectify.NoneElement.__new__
lxml.objectify.NumberElement.__new__
lxml.objectify.ObjectPath.__new__
lxml.objectify.ObjectifiedDataElement.__new__
lxml.objectify.ObjectifiedElement.__new__
lxml.objectify.ObjectifyElementClassLookup.__new__
lxml.objectify.PyType.__new__
lxml.objectify.StringElement.__new__" class="py-name" href="#" onclick="return doclink('link-163', '__new__', 'link-159');">__new__</a></tt><tt class="py-op">(</tt><tt class="py-name">cls</tt><tt class="py-op">,</tt> <tt class="py-string">"%s: %s"</tt> <tt class="py-op">%</tt> <tt class="py-op">(</tt><tt id="link-164" class="py-name"><a title="lxml.etree._LogEntry.type
lxml.html.InputElement.type" class="py-name" href="#" onclick="return doclink('link-164', 'type', 'link-25');">type</a></tt><tt class="py-op">,</tt> <tt id="link-165" class="py-name" targets="Method lxml.etree.TreeBuilder.data()=lxml.etree.TreeBuilder-class.html#data"><a title="lxml.etree.TreeBuilder.data" class="py-name" href="#" onclick="return doclink('link-165', 'data', 'link-165');">data</a></tt><tt class="py-op">)</tt><tt class="py-op">,</tt>  </tt>
<a name="L487"></a><tt class="py-lineno">487</tt>  <tt class="py-line">                            <tt class="py-name">pre_tags</tt><tt class="py-op">=</tt><tt class="py-name">pre_tags</tt><tt class="py-op">,</tt>  </tt>
<a name="L488"></a><tt class="py-lineno">488</tt>  <tt class="py-line">                            <tt class="py-name">post_tags</tt><tt class="py-op">=</tt><tt class="py-name">post_tags</tt><tt class="py-op">,</tt>  </tt>
<a name="L489"></a><tt class="py-lineno">489</tt>  <tt class="py-line">                            <tt class="py-name">trailing_whitespace</tt><tt class="py-op">=</tt><tt class="py-name">trailing_whitespace</tt><tt class="py-op">)</tt> </tt>
<a name="L490"></a><tt class="py-lineno">490</tt>  <tt class="py-line">        <tt class="py-name">obj</tt><tt class="py-op">.</tt><tt id="link-166" class="py-name"><a title="lxml.etree._Comment.tag
lxml.etree._Element.tag
lxml.etree._Entity.tag
lxml.etree._ProcessingInstruction.tag
lxml.tests.test_xpathevaluator.tag
xml.etree.ElementTree.Element.tag" class="py-name" href="#" onclick="return doclink('link-166', 'tag', 'link-103');">tag</a></tt> <tt class="py-op">=</tt> <tt id="link-167" class="py-name"><a title="lxml.etree._Comment.tag
lxml.etree._Element.tag
lxml.etree._Entity.tag
lxml.etree._ProcessingInstruction.tag
lxml.tests.test_xpathevaluator.tag
xml.etree.ElementTree.Element.tag" class="py-name" href="#" onclick="return doclink('link-167', 'tag', 'link-103');">tag</a></tt> </tt>
<a name="L491"></a><tt class="py-lineno">491</tt>  <tt class="py-line">        <tt class="py-name">obj</tt><tt class="py-op">.</tt><tt id="link-168" class="py-name"><a title="lxml.etree.TreeBuilder.data" class="py-name" href="#" onclick="return doclink('link-168', 'data', 'link-165');">data</a></tt> <tt class="py-op">=</tt> <tt id="link-169" class="py-name"><a title="lxml.etree.TreeBuilder.data" class="py-name" href="#" onclick="return doclink('link-169', 'data', 'link-165');">data</a></tt> </tt>
<a name="L492"></a><tt class="py-lineno">492</tt>  <tt class="py-line">        <tt class="py-name">obj</tt><tt class="py-op">.</tt><tt class="py-name">html_repr</tt> <tt class="py-op">=</tt> <tt class="py-name">html_repr</tt> </tt>
<a name="L493"></a><tt class="py-lineno">493</tt>  <tt class="py-line">        <tt class="py-keyword">return</tt> <tt class="py-name">obj</tt> </tt>
</div><a name="L494"></a><tt class="py-lineno">494</tt>  <tt class="py-line"> </tt>
<a name="tag_token.__repr__"></a><div id="tag_token.__repr__-def"><a name="L495"></a><tt class="py-lineno">495</tt> <a class="py-toggle" href="#" id="tag_token.__repr__-toggle" onclick="return toggle('tag_token.__repr__');">-</a><tt class="py-line">    <tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff.tag_token-class.html#__repr__">__repr__</a><tt class="py-op">(</tt><tt class="py-param">self</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="tag_token.__repr__-collapsed" style="display:none;" pad="+++" indent="++++++++"></div><div id="tag_token.__repr__-expanded"><a name="L496"></a><tt class="py-lineno">496</tt>  <tt class="py-line">        <tt class="py-keyword">return</tt> <tt class="py-string">'tag_token(%s, %s, html_repr=%s, post_tags=%r, pre_tags=%r, trailing_whitespace=%r)'</tt> <tt class="py-op">%</tt> <tt class="py-op">(</tt> </tt>
<a name="L497"></a><tt class="py-lineno">497</tt>  <tt class="py-line">            <tt class="py-name">self</tt><tt class="py-op">.</tt><tt id="link-170" class="py-name"><a title="lxml.etree._Comment.tag
lxml.etree._Element.tag
lxml.etree._Entity.tag
lxml.etree._ProcessingInstruction.tag
lxml.tests.test_xpathevaluator.tag
xml.etree.ElementTree.Element.tag" class="py-name" href="#" onclick="return doclink('link-170', 'tag', 'link-103');">tag</a></tt><tt class="py-op">,</tt>  </tt>
<a name="L498"></a><tt class="py-lineno">498</tt>  <tt class="py-line">            <tt class="py-name">self</tt><tt class="py-op">.</tt><tt id="link-171" class="py-name"><a title="lxml.etree.TreeBuilder.data" class="py-name" href="#" onclick="return doclink('link-171', 'data', 'link-165');">data</a></tt><tt class="py-op">,</tt>  </tt>
<a name="L499"></a><tt class="py-lineno">499</tt>  <tt class="py-line">            <tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">html_repr</tt><tt class="py-op">,</tt>  </tt>
<a name="L500"></a><tt class="py-lineno">500</tt>  <tt class="py-line">            <tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">pre_tags</tt><tt class="py-op">,</tt>  </tt>
<a name="L501"></a><tt class="py-lineno">501</tt>  <tt class="py-line">            <tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">post_tags</tt><tt class="py-op">,</tt>  </tt>
<a name="L502"></a><tt class="py-lineno">502</tt>  <tt class="py-line">            <tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">trailing_whitespace</tt><tt class="py-op">)</tt> </tt>
</div><a name="tag_token.html"></a><div id="tag_token.html-def"><a name="L503"></a><tt class="py-lineno">503</tt> <a class="py-toggle" href="#" id="tag_token.html-toggle" onclick="return toggle('tag_token.html');">-</a><tt class="py-line">    <tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff.tag_token-class.html#html">html</a><tt class="py-op">(</tt><tt class="py-param">self</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="tag_token.html-collapsed" style="display:none;" pad="+++" indent="++++++++"></div><div id="tag_token.html-expanded"><a name="L504"></a><tt class="py-lineno">504</tt>  <tt class="py-line">        <tt class="py-keyword">return</tt> <tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">html_repr</tt> </tt>
</div></div><a name="L505"></a><tt class="py-lineno">505</tt>  <tt class="py-line"> </tt>
<a name="href_token"></a><div id="href_token-def"><a name="L506"></a><tt class="py-lineno">506</tt> <a class="py-toggle" href="#" id="href_token-toggle" onclick="return toggle('href_token');">-</a><tt class="py-line"><tt class="py-keyword">class</tt> <a class="py-def-name" href="lxml.html.diff.href_token-class.html">href_token</a><tt class="py-op">(</tt><tt class="py-base-class">token</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="href_token-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="href_token-expanded"><a name="L507"></a><tt class="py-lineno">507</tt>  <tt class="py-line"> </tt>
<a name="L508"></a><tt class="py-lineno">508</tt>  <tt class="py-line">    <tt class="py-docstring">""" Represents the href in an anchor tag.  Unlike other words, we only</tt> </tt>
<a name="L509"></a><tt class="py-lineno">509</tt>  <tt class="py-line"><tt class="py-docstring">    show the href when it changes.  """</tt> </tt>
<a name="L510"></a><tt class="py-lineno">510</tt>  <tt class="py-line"> </tt>
<a name="L511"></a><tt class="py-lineno">511</tt>  <tt class="py-line">    <tt id="link-172" class="py-name"><a title="lxml.html.diff.href_token.hide_when_equal
lxml.html.diff.token.hide_when_equal" class="py-name" href="#" onclick="return doclink('link-172', 'hide_when_equal', 'link-64');">hide_when_equal</a></tt> <tt class="py-op">=</tt> <tt class="py-name">True</tt> </tt>
<a name="L512"></a><tt class="py-lineno">512</tt>  <tt class="py-line"> </tt>
<a name="href_token.html"></a><div id="href_token.html-def"><a name="L513"></a><tt class="py-lineno">513</tt> <a class="py-toggle" href="#" id="href_token.html-toggle" onclick="return toggle('href_token.html');">-</a><tt class="py-line">    <tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff.href_token-class.html#html">html</a><tt class="py-op">(</tt><tt class="py-param">self</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="href_token.html-collapsed" style="display:none;" pad="+++" indent="++++++++"></div><div id="href_token.html-expanded"><a name="L514"></a><tt class="py-lineno">514</tt>  <tt class="py-line">        <tt class="py-keyword">return</tt> <tt class="py-string">' Link: %s'</tt> <tt class="py-op">%</tt> <tt class="py-name">self</tt> </tt>
</div></div><a name="L515"></a><tt class="py-lineno">515</tt>  <tt class="py-line"> </tt>
<a name="tokenize"></a><div id="tokenize-def"><a name="L516"></a><tt class="py-lineno">516</tt> <a class="py-toggle" href="#" id="tokenize-toggle" onclick="return toggle('tokenize');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#tokenize">tokenize</a><tt class="py-op">(</tt><tt class="py-param">html</tt><tt class="py-op">,</tt> <tt class="py-param">include_hrefs</tt><tt class="py-op">=</tt><tt class="py-name">True</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="tokenize-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="tokenize-expanded"><a name="L517"></a><tt class="py-lineno">517</tt>  <tt class="py-line">    <tt class="py-docstring">"""</tt> </tt>
<a name="L518"></a><tt class="py-lineno">518</tt>  <tt class="py-line"><tt class="py-docstring">    Parse the given HTML and returns token objects (words with attached tags).</tt> </tt>
<a name="L519"></a><tt class="py-lineno">519</tt>  <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L520"></a><tt class="py-lineno">520</tt>  <tt class="py-line"><tt class="py-docstring">    This parses only the content of a page; anything in the head is</tt> </tt>
<a name="L521"></a><tt class="py-lineno">521</tt>  <tt class="py-line"><tt class="py-docstring">    ignored, and the &lt;head&gt; and &lt;body&gt; elements are themselves</tt> </tt>
<a name="L522"></a><tt class="py-lineno">522</tt>  <tt class="py-line"><tt class="py-docstring">    optional.  The content is then parsed by lxml, which ensures the</tt> </tt>
<a name="L523"></a><tt class="py-lineno">523</tt>  <tt class="py-line"><tt class="py-docstring">    validity of the resulting parsed document (though lxml may make</tt> </tt>
<a name="L524"></a><tt class="py-lineno">524</tt>  <tt class="py-line"><tt class="py-docstring">    incorrect guesses when the markup is particular bad).</tt> </tt>
<a name="L525"></a><tt class="py-lineno">525</tt>  <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L526"></a><tt class="py-lineno">526</tt>  <tt class="py-line"><tt class="py-docstring">    &lt;ins&gt; and &lt;del&gt; tags are also eliminated from the document, as</tt> </tt>
<a name="L527"></a><tt class="py-lineno">527</tt>  <tt class="py-line"><tt class="py-docstring">    that gets confusing.</tt> </tt>
<a name="L528"></a><tt class="py-lineno">528</tt>  <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L529"></a><tt class="py-lineno">529</tt>  <tt class="py-line"><tt class="py-docstring">    If include_hrefs is true, then the href attribute of &lt;a&gt; tags is</tt> </tt>
<a name="L530"></a><tt class="py-lineno">530</tt>  <tt class="py-line"><tt class="py-docstring">    included as a special kind of diffable token."""</tt> </tt>
<a name="L531"></a><tt class="py-lineno">531</tt>  <tt class="py-line">    <tt class="py-keyword">if</tt> <tt id="link-173" class="py-name"><a title="lxml.etree
lxml.sax.ElementTreeContentHandler.etree
lxml.tests.test_elementtree.CElementTreeTestCase.etree
lxml.tests.test_elementtree._ETreeTestCaseBase.etree
lxml.tests.test_elementtree._XMLPullParserTest.etree
lxml.tests.test_io._IOTestCaseBase.etree" class="py-name" href="#" onclick="return doclink('link-173', 'etree', 'link-1');">etree</a></tt><tt class="py-op">.</tt><tt id="link-174" class="py-name" targets="Function lxml.etree.iselement()=lxml.etree-module.html#iselement"><a title="lxml.etree.iselement" class="py-name" href="#" onclick="return doclink('link-174', 'iselement', 'link-174');">iselement</a></tt><tt class="py-op">(</tt><tt id="link-175" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-175', 'html', 'link-3');">html</a></tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
<a name="L532"></a><tt class="py-lineno">532</tt>  <tt class="py-line">        <tt class="py-name">body_el</tt> <tt class="py-op">=</tt> <tt id="link-176" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-176', 'html', 'link-3');">html</a></tt> </tt>
<a name="L533"></a><tt class="py-lineno">533</tt>  <tt class="py-line">    <tt class="py-keyword">else</tt><tt class="py-op">:</tt> </tt>
<a name="L534"></a><tt class="py-lineno">534</tt>  <tt class="py-line">        <tt class="py-name">body_el</tt> <tt class="py-op">=</tt> <tt id="link-177" class="py-name" targets="Function lxml.html.diff.parse_html()=lxml.html.diff-module.html#parse_html"><a title="lxml.html.diff.parse_html" class="py-name" href="#" onclick="return doclink('link-177', 'parse_html', 'link-177');">parse_html</a></tt><tt class="py-op">(</tt><tt id="link-178" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-178', 'html', 'link-3');">html</a></tt><tt class="py-op">,</tt> <tt class="py-name">cleanup</tt><tt class="py-op">=</tt><tt class="py-name">True</tt><tt class="py-op">)</tt> </tt>
<a name="L535"></a><tt class="py-lineno">535</tt>  <tt class="py-line">    <tt class="py-comment"># Then we split the document into text chunks for each tag, word, and end tag:</tt> </tt>
<a name="L536"></a><tt class="py-lineno">536</tt>  <tt class="py-line">    <tt class="py-name">chunks</tt> <tt class="py-op">=</tt> <tt id="link-179" class="py-name" targets="Function lxml.html.diff.flatten_el()=lxml.html.diff-module.html#flatten_el"><a title="lxml.html.diff.flatten_el" class="py-name" href="#" onclick="return doclink('link-179', 'flatten_el', 'link-179');">flatten_el</a></tt><tt class="py-op">(</tt><tt class="py-name">body_el</tt><tt class="py-op">,</tt> <tt class="py-name">skip_tag</tt><tt class="py-op">=</tt><tt class="py-name">True</tt><tt class="py-op">,</tt> <tt class="py-name">include_hrefs</tt><tt class="py-op">=</tt><tt class="py-name">include_hrefs</tt><tt class="py-op">)</tt> </tt>
<a name="L537"></a><tt class="py-lineno">537</tt>  <tt class="py-line">    <tt class="py-comment"># Finally re-joining them into token objects:</tt> </tt>
<a name="L538"></a><tt class="py-lineno">538</tt>  <tt class="py-line">    <tt class="py-keyword">return</tt> <tt id="link-180" class="py-name" targets="Function lxml.html.diff.fixup_chunks()=lxml.html.diff-module.html#fixup_chunks"><a title="lxml.html.diff.fixup_chunks" class="py-name" href="#" onclick="return doclink('link-180', 'fixup_chunks', 'link-180');">fixup_chunks</a></tt><tt class="py-op">(</tt><tt class="py-name">chunks</tt><tt class="py-op">)</tt> </tt>
</div><a name="L539"></a><tt class="py-lineno">539</tt>  <tt class="py-line"> </tt>
<a name="parse_html"></a><div id="parse_html-def"><a name="L540"></a><tt class="py-lineno">540</tt> <a class="py-toggle" href="#" id="parse_html-toggle" onclick="return toggle('parse_html');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#parse_html">parse_html</a><tt class="py-op">(</tt><tt class="py-param">html</tt><tt class="py-op">,</tt> <tt class="py-param">cleanup</tt><tt class="py-op">=</tt><tt class="py-name">True</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="parse_html-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="parse_html-expanded"><a name="L541"></a><tt class="py-lineno">541</tt>  <tt class="py-line">    <tt class="py-docstring">"""</tt> </tt>
<a name="L542"></a><tt class="py-lineno">542</tt>  <tt class="py-line"><tt class="py-docstring">    Parses an HTML fragment, returning an lxml element.  Note that the HTML will be</tt> </tt>
<a name="L543"></a><tt class="py-lineno">543</tt>  <tt class="py-line"><tt class="py-docstring">    wrapped in a &lt;div&gt; tag that was not in the original document.</tt> </tt>
<a name="L544"></a><tt class="py-lineno">544</tt>  <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L545"></a><tt class="py-lineno">545</tt>  <tt class="py-line"><tt class="py-docstring">    If cleanup is true, make sure there's no &lt;head&gt; or &lt;body&gt;, and get</tt> </tt>
<a name="L546"></a><tt class="py-lineno">546</tt>  <tt class="py-line"><tt class="py-docstring">    rid of any &lt;ins&gt; and &lt;del&gt; tags.</tt> </tt>
<a name="L547"></a><tt class="py-lineno">547</tt>  <tt class="py-line"><tt class="py-docstring">    """</tt> </tt>
<a name="L548"></a><tt class="py-lineno">548</tt>  <tt class="py-line">    <tt class="py-keyword">if</tt> <tt class="py-name">cleanup</tt><tt class="py-op">:</tt> </tt>
<a name="L549"></a><tt class="py-lineno">549</tt>  <tt class="py-line">        <tt class="py-comment"># This removes any extra markup or structure like &lt;head&gt;:</tt> </tt>
<a name="L550"></a><tt class="py-lineno">550</tt>  <tt class="py-line">        <tt id="link-181" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-181', 'html', 'link-3');">html</a></tt> <tt class="py-op">=</tt> <tt id="link-182" class="py-name" targets="Function lxml.html.diff.cleanup_html()=lxml.html.diff-module.html#cleanup_html"><a title="lxml.html.diff.cleanup_html" class="py-name" href="#" onclick="return doclink('link-182', 'cleanup_html', 'link-182');">cleanup_html</a></tt><tt class="py-op">(</tt><tt id="link-183" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-183', 'html', 'link-3');">html</a></tt><tt class="py-op">)</tt> </tt>
<a name="L551"></a><tt class="py-lineno">551</tt>  <tt class="py-line">    <tt class="py-keyword">return</tt> <tt id="link-184" class="py-name"><a title="lxml.html.html5parser.fragment_fromstring" class="py-name" href="#" onclick="return doclink('link-184', 'fragment_fromstring', 'link-4');">fragment_fromstring</a></tt><tt class="py-op">(</tt><tt id="link-185" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-185', 'html', 'link-3');">html</a></tt><tt class="py-op">,</tt> <tt class="py-name">create_parent</tt><tt class="py-op">=</tt><tt class="py-name">True</tt><tt class="py-op">)</tt> </tt>
</div><a name="L552"></a><tt class="py-lineno">552</tt>  <tt class="py-line"> </tt>
<a name="L553"></a><tt class="py-lineno">553</tt>  <tt class="py-line"><tt id="link-186" class="py-name" targets="Variable lxml.html.diff._body_re=lxml.html.diff-module.html#_body_re"><a title="lxml.html.diff._body_re" class="py-name" href="#" onclick="return doclink('link-186', '_body_re', 'link-186');">_body_re</a></tt> <tt class="py-op">=</tt> <tt class="py-name">re</tt><tt class="py-op">.</tt><tt class="py-name">compile</tt><tt class="py-op">(</tt><tt class="py-string">r'&lt;body.*?&gt;'</tt><tt class="py-op">,</tt> <tt class="py-name">re</tt><tt class="py-op">.</tt><tt id="link-187" class="py-name" targets="Variable lxml.html.builder.I=lxml.html.builder-module.html#I"><a title="lxml.html.builder.I" class="py-name" href="#" onclick="return doclink('link-187', 'I', 'link-187');">I</a></tt><tt class="py-op">|</tt><tt class="py-name">re</tt><tt class="py-op">.</tt><tt id="link-188" class="py-name" targets="Variable lxml.html.builder.S=lxml.html.builder-module.html#S"><a title="lxml.html.builder.S" class="py-name" href="#" onclick="return doclink('link-188', 'S', 'link-188');">S</a></tt><tt class="py-op">)</tt> </tt>
<a name="L554"></a><tt class="py-lineno">554</tt>  <tt class="py-line"><tt id="link-189" class="py-name" targets="Variable lxml.html.diff._end_body_re=lxml.html.diff-module.html#_end_body_re"><a title="lxml.html.diff._end_body_re" class="py-name" href="#" onclick="return doclink('link-189', '_end_body_re', 'link-189');">_end_body_re</a></tt> <tt class="py-op">=</tt> <tt class="py-name">re</tt><tt class="py-op">.</tt><tt class="py-name">compile</tt><tt class="py-op">(</tt><tt class="py-string">r'&lt;/body.*?&gt;'</tt><tt class="py-op">,</tt> <tt class="py-name">re</tt><tt class="py-op">.</tt><tt id="link-190" class="py-name"><a title="lxml.html.builder.I" class="py-name" href="#" onclick="return doclink('link-190', 'I', 'link-187');">I</a></tt><tt class="py-op">|</tt><tt class="py-name">re</tt><tt class="py-op">.</tt><tt id="link-191" class="py-name"><a title="lxml.html.builder.S" class="py-name" href="#" onclick="return doclink('link-191', 'S', 'link-188');">S</a></tt><tt class="py-op">)</tt> </tt>
<a name="L555"></a><tt class="py-lineno">555</tt>  <tt class="py-line"><tt id="link-192" class="py-name" targets="Variable lxml.html.diff._ins_del_re=lxml.html.diff-module.html#_ins_del_re"><a title="lxml.html.diff._ins_del_re" class="py-name" href="#" onclick="return doclink('link-192', '_ins_del_re', 'link-192');">_ins_del_re</a></tt> <tt class="py-op">=</tt> <tt class="py-name">re</tt><tt class="py-op">.</tt><tt class="py-name">compile</tt><tt class="py-op">(</tt><tt class="py-string">r'&lt;/?(ins|del).*?&gt;'</tt><tt class="py-op">,</tt> <tt class="py-name">re</tt><tt class="py-op">.</tt><tt id="link-193" class="py-name"><a title="lxml.html.builder.I" class="py-name" href="#" onclick="return doclink('link-193', 'I', 'link-187');">I</a></tt><tt class="py-op">|</tt><tt class="py-name">re</tt><tt class="py-op">.</tt><tt id="link-194" class="py-name"><a title="lxml.html.builder.S" class="py-name" href="#" onclick="return doclink('link-194', 'S', 'link-188');">S</a></tt><tt class="py-op">)</tt> </tt>
<a name="L556"></a><tt class="py-lineno">556</tt>  <tt class="py-line"> </tt>
<a name="cleanup_html"></a><div id="cleanup_html-def"><a name="L557"></a><tt class="py-lineno">557</tt> <a class="py-toggle" href="#" id="cleanup_html-toggle" onclick="return toggle('cleanup_html');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#cleanup_html">cleanup_html</a><tt class="py-op">(</tt><tt class="py-param">html</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="cleanup_html-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="cleanup_html-expanded"><a name="L558"></a><tt class="py-lineno">558</tt>  <tt class="py-line">    <tt class="py-docstring">""" This 'cleans' the HTML, meaning that any page structure is removed</tt> </tt>
<a name="L559"></a><tt class="py-lineno">559</tt>  <tt class="py-line"><tt class="py-docstring">    (only the contents of &lt;body&gt; are used, if there is any &lt;body).</tt> </tt>
<a name="L560"></a><tt class="py-lineno">560</tt>  <tt class="py-line"><tt class="py-docstring">    Also &lt;ins&gt; and &lt;del&gt; tags are removed.  """</tt> </tt>
<a name="L561"></a><tt class="py-lineno">561</tt>  <tt class="py-line">    <tt class="py-name">match</tt> <tt class="py-op">=</tt> <tt id="link-195" class="py-name"><a title="lxml.html.diff._body_re" class="py-name" href="#" onclick="return doclink('link-195', '_body_re', 'link-186');">_body_re</a></tt><tt class="py-op">.</tt><tt class="py-name">search</tt><tt class="py-op">(</tt><tt id="link-196" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-196', 'html', 'link-3');">html</a></tt><tt class="py-op">)</tt> </tt>
<a name="L562"></a><tt class="py-lineno">562</tt>  <tt class="py-line">    <tt class="py-keyword">if</tt> <tt class="py-name">match</tt><tt class="py-op">:</tt> </tt>
<a name="L563"></a><tt class="py-lineno">563</tt>  <tt class="py-line">        <tt id="link-197" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-197', 'html', 'link-3');">html</a></tt> <tt class="py-op">=</tt> <tt id="link-198" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-198', 'html', 'link-3');">html</a></tt><tt class="py-op">[</tt><tt class="py-name">match</tt><tt class="py-op">.</tt><tt id="link-199" class="py-name"><a title="lxml.etree.TreeBuilder.end" class="py-name" href="#" onclick="return doclink('link-199', 'end', 'link-93');">end</a></tt><tt class="py-op">(</tt><tt class="py-op">)</tt><tt class="py-op">:</tt><tt class="py-op">]</tt> </tt>
<a name="L564"></a><tt class="py-lineno">564</tt>  <tt class="py-line">    <tt class="py-name">match</tt> <tt class="py-op">=</tt> <tt id="link-200" class="py-name"><a title="lxml.html.diff._end_body_re" class="py-name" href="#" onclick="return doclink('link-200', '_end_body_re', 'link-189');">_end_body_re</a></tt><tt class="py-op">.</tt><tt class="py-name">search</tt><tt class="py-op">(</tt><tt id="link-201" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-201', 'html', 'link-3');">html</a></tt><tt class="py-op">)</tt> </tt>
<a name="L565"></a><tt class="py-lineno">565</tt>  <tt class="py-line">    <tt class="py-keyword">if</tt> <tt class="py-name">match</tt><tt class="py-op">:</tt> </tt>
<a name="L566"></a><tt class="py-lineno">566</tt>  <tt class="py-line">        <tt id="link-202" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-202', 'html', 'link-3');">html</a></tt> <tt class="py-op">=</tt> <tt id="link-203" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-203', 'html', 'link-3');">html</a></tt><tt class="py-op">[</tt><tt class="py-op">:</tt><tt class="py-name">match</tt><tt class="py-op">.</tt><tt id="link-204" class="py-name"><a title="lxml.etree.TreeBuilder.start" class="py-name" href="#" onclick="return doclink('link-204', 'start', 'link-92');">start</a></tt><tt class="py-op">(</tt><tt class="py-op">)</tt><tt class="py-op">]</tt> </tt>
<a name="L567"></a><tt class="py-lineno">567</tt>  <tt class="py-line">    <tt id="link-205" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-205', 'html', 'link-3');">html</a></tt> <tt class="py-op">=</tt> <tt id="link-206" class="py-name"><a title="lxml.html.diff._ins_del_re" class="py-name" href="#" onclick="return doclink('link-206', '_ins_del_re', 'link-192');">_ins_del_re</a></tt><tt class="py-op">.</tt><tt class="py-name">sub</tt><tt class="py-op">(</tt><tt class="py-string">''</tt><tt class="py-op">,</tt> <tt id="link-207" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-207', 'html', 'link-3');">html</a></tt><tt class="py-op">)</tt> </tt>
<a name="L568"></a><tt class="py-lineno">568</tt>  <tt class="py-line">    <tt class="py-keyword">return</tt> <tt id="link-208" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-208', 'html', 'link-3');">html</a></tt> </tt>
</div><a name="L569"></a><tt class="py-lineno">569</tt>  <tt class="py-line">     </tt>
<a name="L570"></a><tt class="py-lineno">570</tt>  <tt class="py-line"> </tt>
<a name="L571"></a><tt class="py-lineno">571</tt>  <tt class="py-line"><tt id="link-209" class="py-name" targets="Variable lxml.html.diff.end_whitespace_re=lxml.html.diff-module.html#end_whitespace_re"><a title="lxml.html.diff.end_whitespace_re" class="py-name" href="#" onclick="return doclink('link-209', 'end_whitespace_re', 'link-209');">end_whitespace_re</a></tt> <tt class="py-op">=</tt> <tt class="py-name">re</tt><tt class="py-op">.</tt><tt class="py-name">compile</tt><tt class="py-op">(</tt><tt class="py-string">r'[ \t\n\r]$'</tt><tt class="py-op">)</tt> </tt>
<a name="L572"></a><tt class="py-lineno">572</tt>  <tt class="py-line"> </tt>
<a name="split_trailing_whitespace"></a><div id="split_trailing_whitespace-def"><a name="L573"></a><tt class="py-lineno">573</tt> <a class="py-toggle" href="#" id="split_trailing_whitespace-toggle" onclick="return toggle('split_trailing_whitespace');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#split_trailing_whitespace">split_trailing_whitespace</a><tt class="py-op">(</tt><tt class="py-param">word</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="split_trailing_whitespace-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="split_trailing_whitespace-expanded"><a name="L574"></a><tt class="py-lineno">574</tt>  <tt class="py-line">    <tt class="py-docstring">"""</tt> </tt>
<a name="L575"></a><tt class="py-lineno">575</tt>  <tt class="py-line"><tt class="py-docstring">    This function takes a word, such as 'test\n\n' and returns ('test','\n\n')</tt> </tt>
<a name="L576"></a><tt class="py-lineno">576</tt>  <tt class="py-line"><tt class="py-docstring">    """</tt> </tt>
<a name="L577"></a><tt class="py-lineno">577</tt>  <tt class="py-line">    <tt class="py-name">stripped_length</tt> <tt class="py-op">=</tt> <tt class="py-name">len</tt><tt class="py-op">(</tt><tt class="py-name">word</tt><tt class="py-op">.</tt><tt class="py-name">rstrip</tt><tt class="py-op">(</tt><tt class="py-op">)</tt><tt class="py-op">)</tt> </tt>
<a name="L578"></a><tt class="py-lineno">578</tt>  <tt class="py-line">    <tt class="py-keyword">return</tt> <tt class="py-name">word</tt><tt class="py-op">[</tt><tt class="py-number">0</tt><tt class="py-op">:</tt><tt class="py-name">stripped_length</tt><tt class="py-op">]</tt><tt class="py-op">,</tt> <tt class="py-name">word</tt><tt class="py-op">[</tt><tt class="py-name">stripped_length</tt><tt class="py-op">:</tt><tt class="py-op">]</tt> </tt>
</div><a name="L579"></a><tt class="py-lineno">579</tt>  <tt class="py-line"> </tt>
<a name="L580"></a><tt class="py-lineno">580</tt>  <tt class="py-line"> </tt>
<a name="fixup_chunks"></a><div id="fixup_chunks-def"><a name="L581"></a><tt class="py-lineno">581</tt> <a class="py-toggle" href="#" id="fixup_chunks-toggle" onclick="return toggle('fixup_chunks');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#fixup_chunks">fixup_chunks</a><tt class="py-op">(</tt><tt class="py-param">chunks</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="fixup_chunks-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="fixup_chunks-expanded"><a name="L582"></a><tt class="py-lineno">582</tt>  <tt class="py-line">    <tt class="py-docstring">"""</tt> </tt>
<a name="L583"></a><tt class="py-lineno">583</tt>  <tt class="py-line"><tt class="py-docstring">    This function takes a list of chunks and produces a list of tokens.</tt> </tt>
<a name="L584"></a><tt class="py-lineno">584</tt>  <tt class="py-line"><tt class="py-docstring">    """</tt> </tt>
<a name="L585"></a><tt class="py-lineno">585</tt>  <tt class="py-line">    <tt class="py-name">tag_accum</tt> <tt class="py-op">=</tt> <tt class="py-op">[</tt><tt class="py-op">]</tt> </tt>
<a name="L586"></a><tt class="py-lineno">586</tt>  <tt class="py-line">    <tt class="py-name">cur_word</tt> <tt class="py-op">=</tt> <tt class="py-name">None</tt> </tt>
<a name="L587"></a><tt class="py-lineno">587</tt>  <tt class="py-line">    <tt class="py-name">result</tt> <tt class="py-op">=</tt> <tt class="py-op">[</tt><tt class="py-op">]</tt> </tt>
<a name="L588"></a><tt class="py-lineno">588</tt>  <tt class="py-line">    <tt class="py-keyword">for</tt> <tt class="py-name">chunk</tt> <tt class="py-keyword">in</tt> <tt class="py-name">chunks</tt><tt class="py-op">:</tt> </tt>
<a name="L589"></a><tt class="py-lineno">589</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt class="py-name">isinstance</tt><tt class="py-op">(</tt><tt class="py-name">chunk</tt><tt class="py-op">,</tt> <tt class="py-name">tuple</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
<a name="L590"></a><tt class="py-lineno">590</tt>  <tt class="py-line">            <tt class="py-keyword">if</tt> <tt class="py-name">chunk</tt><tt class="py-op">[</tt><tt class="py-number">0</tt><tt class="py-op">]</tt> <tt class="py-op">==</tt> <tt class="py-string">'img'</tt><tt class="py-op">:</tt> </tt>
<a name="L591"></a><tt class="py-lineno">591</tt>  <tt class="py-line">                <tt class="py-name">src</tt> <tt class="py-op">=</tt> <tt class="py-name">chunk</tt><tt class="py-op">[</tt><tt class="py-number">1</tt><tt class="py-op">]</tt> </tt>
<a name="L592"></a><tt class="py-lineno">592</tt>  <tt class="py-line">                <tt id="link-210" class="py-name"><a title="lxml.etree._Comment.tag
lxml.etree._Element.tag
lxml.etree._Entity.tag
lxml.etree._ProcessingInstruction.tag
lxml.tests.test_xpathevaluator.tag
xml.etree.ElementTree.Element.tag" class="py-name" href="#" onclick="return doclink('link-210', 'tag', 'link-103');">tag</a></tt><tt class="py-op">,</tt> <tt class="py-name">trailing_whitespace</tt> <tt class="py-op">=</tt> <tt id="link-211" class="py-name" targets="Function lxml.html.diff.split_trailing_whitespace()=lxml.html.diff-module.html#split_trailing_whitespace"><a title="lxml.html.diff.split_trailing_whitespace" class="py-name" href="#" onclick="return doclink('link-211', 'split_trailing_whitespace', 'link-211');">split_trailing_whitespace</a></tt><tt class="py-op">(</tt><tt class="py-name">chunk</tt><tt class="py-op">[</tt><tt class="py-number">2</tt><tt class="py-op">]</tt><tt class="py-op">)</tt> </tt>
<a name="L593"></a><tt class="py-lineno">593</tt>  <tt class="py-line">                <tt class="py-name">cur_word</tt> <tt class="py-op">=</tt> <tt id="link-212" class="py-name" targets="Class lxml.html.diff.tag_token=lxml.html.diff.tag_token-class.html"><a title="lxml.html.diff.tag_token" class="py-name" href="#" onclick="return doclink('link-212', 'tag_token', 'link-212');">tag_token</a></tt><tt class="py-op">(</tt><tt class="py-string">'img'</tt><tt class="py-op">,</tt> <tt class="py-name">src</tt><tt class="py-op">,</tt> <tt class="py-name">html_repr</tt><tt class="py-op">=</tt><tt id="link-213" class="py-name"><a title="lxml.etree._Comment.tag
lxml.etree._Element.tag
lxml.etree._Entity.tag
lxml.etree._ProcessingInstruction.tag
lxml.tests.test_xpathevaluator.tag
xml.etree.ElementTree.Element.tag" class="py-name" href="#" onclick="return doclink('link-213', 'tag', 'link-103');">tag</a></tt><tt class="py-op">,</tt> </tt>
<a name="L594"></a><tt class="py-lineno">594</tt>  <tt class="py-line">                                     <tt class="py-name">pre_tags</tt><tt class="py-op">=</tt><tt class="py-name">tag_accum</tt><tt class="py-op">,</tt> </tt>
<a name="L595"></a><tt class="py-lineno">595</tt>  <tt class="py-line">                                     <tt class="py-name">trailing_whitespace</tt><tt class="py-op">=</tt><tt class="py-name">trailing_whitespace</tt><tt class="py-op">)</tt> </tt>
<a name="L596"></a><tt class="py-lineno">596</tt>  <tt class="py-line">                <tt class="py-name">tag_accum</tt> <tt class="py-op">=</tt> <tt class="py-op">[</tt><tt class="py-op">]</tt> </tt>
<a name="L597"></a><tt class="py-lineno">597</tt>  <tt class="py-line">                <tt class="py-name">result</tt><tt class="py-op">.</tt><tt id="link-214" class="py-name"><a title="lxml.etree._Element.append" class="py-name" href="#" onclick="return doclink('link-214', 'append', 'link-24');">append</a></tt><tt class="py-op">(</tt><tt class="py-name">cur_word</tt><tt class="py-op">)</tt> </tt>
<a name="L598"></a><tt class="py-lineno">598</tt>  <tt class="py-line"> </tt>
<a name="L599"></a><tt class="py-lineno">599</tt>  <tt class="py-line">            <tt class="py-keyword">elif</tt> <tt class="py-name">chunk</tt><tt class="py-op">[</tt><tt class="py-number">0</tt><tt class="py-op">]</tt> <tt class="py-op">==</tt> <tt class="py-string">'href'</tt><tt class="py-op">:</tt> </tt>
<a name="L600"></a><tt class="py-lineno">600</tt>  <tt class="py-line">                <tt class="py-name">href</tt> <tt class="py-op">=</tt> <tt class="py-name">chunk</tt><tt class="py-op">[</tt><tt class="py-number">1</tt><tt class="py-op">]</tt> </tt>
<a name="L601"></a><tt class="py-lineno">601</tt>  <tt class="py-line">                <tt class="py-name">cur_word</tt> <tt class="py-op">=</tt> <tt id="link-215" class="py-name" targets="Class lxml.html.diff.href_token=lxml.html.diff.href_token-class.html"><a title="lxml.html.diff.href_token" class="py-name" href="#" onclick="return doclink('link-215', 'href_token', 'link-215');">href_token</a></tt><tt class="py-op">(</tt><tt class="py-name">href</tt><tt class="py-op">,</tt> <tt class="py-name">pre_tags</tt><tt class="py-op">=</tt><tt class="py-name">tag_accum</tt><tt class="py-op">,</tt> <tt class="py-name">trailing_whitespace</tt><tt class="py-op">=</tt><tt class="py-string">" "</tt><tt class="py-op">)</tt> </tt>
<a name="L602"></a><tt class="py-lineno">602</tt>  <tt class="py-line">                <tt class="py-name">tag_accum</tt> <tt class="py-op">=</tt> <tt class="py-op">[</tt><tt class="py-op">]</tt> </tt>
<a name="L603"></a><tt class="py-lineno">603</tt>  <tt class="py-line">                <tt class="py-name">result</tt><tt class="py-op">.</tt><tt id="link-216" class="py-name"><a title="lxml.etree._Element.append" class="py-name" href="#" onclick="return doclink('link-216', 'append', 'link-24');">append</a></tt><tt class="py-op">(</tt><tt class="py-name">cur_word</tt><tt class="py-op">)</tt> </tt>
<a name="L604"></a><tt class="py-lineno">604</tt>  <tt class="py-line">            <tt class="py-keyword">continue</tt> </tt>
<a name="L605"></a><tt class="py-lineno">605</tt>  <tt class="py-line"> </tt>
<a name="L606"></a><tt class="py-lineno">606</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt id="link-217" class="py-name" targets="Function lxml.html.diff.is_word()=lxml.html.diff-module.html#is_word"><a title="lxml.html.diff.is_word" class="py-name" href="#" onclick="return doclink('link-217', 'is_word', 'link-217');">is_word</a></tt><tt class="py-op">(</tt><tt class="py-name">chunk</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
<a name="L607"></a><tt class="py-lineno">607</tt>  <tt class="py-line">            <tt class="py-name">chunk</tt><tt class="py-op">,</tt> <tt class="py-name">trailing_whitespace</tt> <tt class="py-op">=</tt> <tt id="link-218" class="py-name"><a title="lxml.html.diff.split_trailing_whitespace" class="py-name" href="#" onclick="return doclink('link-218', 'split_trailing_whitespace', 'link-211');">split_trailing_whitespace</a></tt><tt class="py-op">(</tt><tt class="py-name">chunk</tt><tt class="py-op">)</tt> </tt>
<a name="L608"></a><tt class="py-lineno">608</tt>  <tt class="py-line">            <tt class="py-name">cur_word</tt> <tt class="py-op">=</tt> <tt id="link-219" class="py-name"><a title="lxml.html.diff.token" class="py-name" href="#" onclick="return doclink('link-219', 'token', 'link-26');">token</a></tt><tt class="py-op">(</tt><tt class="py-name">chunk</tt><tt class="py-op">,</tt> <tt class="py-name">pre_tags</tt><tt class="py-op">=</tt><tt class="py-name">tag_accum</tt><tt class="py-op">,</tt> <tt class="py-name">trailing_whitespace</tt><tt class="py-op">=</tt><tt class="py-name">trailing_whitespace</tt><tt class="py-op">)</tt> </tt>
<a name="L609"></a><tt class="py-lineno">609</tt>  <tt class="py-line">            <tt class="py-name">tag_accum</tt> <tt class="py-op">=</tt> <tt class="py-op">[</tt><tt class="py-op">]</tt> </tt>
<a name="L610"></a><tt class="py-lineno">610</tt>  <tt class="py-line">            <tt class="py-name">result</tt><tt class="py-op">.</tt><tt id="link-220" class="py-name"><a title="lxml.etree._Element.append" class="py-name" href="#" onclick="return doclink('link-220', 'append', 'link-24');">append</a></tt><tt class="py-op">(</tt><tt class="py-name">cur_word</tt><tt class="py-op">)</tt> </tt>
<a name="L611"></a><tt class="py-lineno">611</tt>  <tt class="py-line"> </tt>
<a name="L612"></a><tt class="py-lineno">612</tt>  <tt class="py-line">        <tt class="py-keyword">elif</tt> <tt id="link-221" class="py-name" targets="Function lxml.html.diff.is_start_tag()=lxml.html.diff-module.html#is_start_tag"><a title="lxml.html.diff.is_start_tag" class="py-name" href="#" onclick="return doclink('link-221', 'is_start_tag', 'link-221');">is_start_tag</a></tt><tt class="py-op">(</tt><tt class="py-name">chunk</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
<a name="L613"></a><tt class="py-lineno">613</tt>  <tt class="py-line">            <tt class="py-name">tag_accum</tt><tt class="py-op">.</tt><tt id="link-222" class="py-name"><a title="lxml.etree._Element.append" class="py-name" href="#" onclick="return doclink('link-222', 'append', 'link-24');">append</a></tt><tt class="py-op">(</tt><tt class="py-name">chunk</tt><tt class="py-op">)</tt> </tt>
<a name="L614"></a><tt class="py-lineno">614</tt>  <tt class="py-line"> </tt>
<a name="L615"></a><tt class="py-lineno">615</tt>  <tt class="py-line">        <tt class="py-keyword">elif</tt> <tt id="link-223" class="py-name" targets="Function lxml.html.diff.is_end_tag()=lxml.html.diff-module.html#is_end_tag"><a title="lxml.html.diff.is_end_tag" class="py-name" href="#" onclick="return doclink('link-223', 'is_end_tag', 'link-223');">is_end_tag</a></tt><tt class="py-op">(</tt><tt class="py-name">chunk</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
<a name="L616"></a><tt class="py-lineno">616</tt>  <tt class="py-line">            <tt class="py-keyword">if</tt> <tt class="py-name">tag_accum</tt><tt class="py-op">:</tt> </tt>
<a name="L617"></a><tt class="py-lineno">617</tt>  <tt class="py-line">                <tt class="py-name">tag_accum</tt><tt class="py-op">.</tt><tt id="link-224" class="py-name"><a title="lxml.etree._Element.append" class="py-name" href="#" onclick="return doclink('link-224', 'append', 'link-24');">append</a></tt><tt class="py-op">(</tt><tt class="py-name">chunk</tt><tt class="py-op">)</tt> </tt>
<a name="L618"></a><tt class="py-lineno">618</tt>  <tt class="py-line">            <tt class="py-keyword">else</tt><tt class="py-op">:</tt> </tt>
<a name="L619"></a><tt class="py-lineno">619</tt>  <tt class="py-line">                <tt class="py-keyword">assert</tt> <tt class="py-name">cur_word</tt><tt class="py-op">,</tt> <tt class="py-op">(</tt> </tt>
<a name="L620"></a><tt class="py-lineno">620</tt>  <tt class="py-line">                    <tt class="py-string">"Weird state, cur_word=%r, result=%r, chunks=%r of %r"</tt> </tt>
<a name="L621"></a><tt class="py-lineno">621</tt>  <tt class="py-line">                    <tt class="py-op">%</tt> <tt class="py-op">(</tt><tt class="py-name">cur_word</tt><tt class="py-op">,</tt> <tt class="py-name">result</tt><tt class="py-op">,</tt> <tt class="py-name">chunk</tt><tt class="py-op">,</tt> <tt class="py-name">chunks</tt><tt class="py-op">)</tt><tt class="py-op">)</tt> </tt>
<a name="L622"></a><tt class="py-lineno">622</tt>  <tt class="py-line">                <tt class="py-name">cur_word</tt><tt class="py-op">.</tt><tt class="py-name">post_tags</tt><tt class="py-op">.</tt><tt id="link-225" class="py-name"><a title="lxml.etree._Element.append" class="py-name" href="#" onclick="return doclink('link-225', 'append', 'link-24');">append</a></tt><tt class="py-op">(</tt><tt class="py-name">chunk</tt><tt class="py-op">)</tt> </tt>
<a name="L623"></a><tt class="py-lineno">623</tt>  <tt class="py-line">        <tt class="py-keyword">else</tt><tt class="py-op">:</tt> </tt>
<a name="L624"></a><tt class="py-lineno">624</tt>  <tt class="py-line">            <tt class="py-keyword">assert</tt><tt class="py-op">(</tt><tt class="py-number">0</tt><tt class="py-op">)</tt> </tt>
<a name="L625"></a><tt class="py-lineno">625</tt>  <tt class="py-line"> </tt>
<a name="L626"></a><tt class="py-lineno">626</tt>  <tt class="py-line">    <tt class="py-keyword">if</tt> <tt class="py-keyword">not</tt> <tt class="py-name">result</tt><tt class="py-op">:</tt> </tt>
<a name="L627"></a><tt class="py-lineno">627</tt>  <tt class="py-line">        <tt class="py-keyword">return</tt> <tt class="py-op">[</tt><tt id="link-226" class="py-name"><a title="lxml.html.diff.token" class="py-name" href="#" onclick="return doclink('link-226', 'token', 'link-26');">token</a></tt><tt class="py-op">(</tt><tt class="py-string">''</tt><tt class="py-op">,</tt> <tt class="py-name">pre_tags</tt><tt class="py-op">=</tt><tt class="py-name">tag_accum</tt><tt class="py-op">)</tt><tt class="py-op">]</tt> </tt>
<a name="L628"></a><tt class="py-lineno">628</tt>  <tt class="py-line">    <tt class="py-keyword">else</tt><tt class="py-op">:</tt> </tt>
<a name="L629"></a><tt class="py-lineno">629</tt>  <tt class="py-line">        <tt class="py-name">result</tt><tt class="py-op">[</tt><tt class="py-op">-</tt><tt class="py-number">1</tt><tt class="py-op">]</tt><tt class="py-op">.</tt><tt class="py-name">post_tags</tt><tt class="py-op">.</tt><tt id="link-227" class="py-name"><a title="lxml.etree._Element.extend" class="py-name" href="#" onclick="return doclink('link-227', 'extend', 'link-54');">extend</a></tt><tt class="py-op">(</tt><tt class="py-name">tag_accum</tt><tt class="py-op">)</tt> </tt>
<a name="L630"></a><tt class="py-lineno">630</tt>  <tt class="py-line"> </tt>
<a name="L631"></a><tt class="py-lineno">631</tt>  <tt class="py-line">    <tt class="py-keyword">return</tt> <tt class="py-name">result</tt> </tt>
</div><a name="L632"></a><tt class="py-lineno">632</tt>  <tt class="py-line"> </tt>
<a name="L633"></a><tt class="py-lineno">633</tt>  <tt class="py-line"> </tt>
<a name="L634"></a><tt class="py-lineno">634</tt>  <tt class="py-line"><tt class="py-comment"># All the tags in HTML that don't require end tags:</tt> </tt>
<a name="L635"></a><tt class="py-lineno">635</tt>  <tt class="py-line"><tt id="link-228" class="py-name"><a title="lxml.doctestcompare.LXMLOutputChecker.empty_tags
lxml.html.defs.empty_tags
lxml.html.diff.empty_tags" class="py-name" href="#" onclick="return doclink('link-228', 'empty_tags', 'link-98');">empty_tags</a></tt> <tt class="py-op">=</tt> <tt class="py-op">(</tt> </tt>
<a name="L636"></a><tt class="py-lineno">636</tt>  <tt class="py-line">    <tt class="py-string">'param'</tt><tt class="py-op">,</tt> <tt class="py-string">'img'</tt><tt class="py-op">,</tt> <tt class="py-string">'area'</tt><tt class="py-op">,</tt> <tt class="py-string">'br'</tt><tt class="py-op">,</tt> <tt class="py-string">'basefont'</tt><tt class="py-op">,</tt> <tt class="py-string">'input'</tt><tt class="py-op">,</tt> </tt>
<a name="L637"></a><tt class="py-lineno">637</tt>  <tt class="py-line">    <tt class="py-string">'base'</tt><tt class="py-op">,</tt> <tt class="py-string">'meta'</tt><tt class="py-op">,</tt> <tt class="py-string">'link'</tt><tt class="py-op">,</tt> <tt class="py-string">'col'</tt><tt class="py-op">)</tt> </tt>
<a name="L638"></a><tt class="py-lineno">638</tt>  <tt class="py-line"> </tt>
<a name="L639"></a><tt class="py-lineno">639</tt>  <tt class="py-line"><tt id="link-229" class="py-name" targets="Variable lxml.html.diff.block_level_tags=lxml.html.diff-module.html#block_level_tags"><a title="lxml.html.diff.block_level_tags" class="py-name" href="#" onclick="return doclink('link-229', 'block_level_tags', 'link-229');">block_level_tags</a></tt> <tt class="py-op">=</tt> <tt class="py-op">(</tt> </tt>
<a name="L640"></a><tt class="py-lineno">640</tt>  <tt class="py-line">    <tt class="py-string">'address'</tt><tt class="py-op">,</tt> </tt>
<a name="L641"></a><tt class="py-lineno">641</tt>  <tt class="py-line">    <tt class="py-string">'blockquote'</tt><tt class="py-op">,</tt> </tt>
<a name="L642"></a><tt class="py-lineno">642</tt>  <tt class="py-line">    <tt class="py-string">'center'</tt><tt class="py-op">,</tt> </tt>
<a name="L643"></a><tt class="py-lineno">643</tt>  <tt class="py-line">    <tt class="py-string">'dir'</tt><tt class="py-op">,</tt> </tt>
<a name="L644"></a><tt class="py-lineno">644</tt>  <tt class="py-line">    <tt class="py-string">'div'</tt><tt class="py-op">,</tt> </tt>
<a name="L645"></a><tt class="py-lineno">645</tt>  <tt class="py-line">    <tt class="py-string">'dl'</tt><tt class="py-op">,</tt> </tt>
<a name="L646"></a><tt class="py-lineno">646</tt>  <tt class="py-line">    <tt class="py-string">'fieldset'</tt><tt class="py-op">,</tt> </tt>
<a name="L647"></a><tt class="py-lineno">647</tt>  <tt class="py-line">    <tt class="py-string">'form'</tt><tt class="py-op">,</tt> </tt>
<a name="L648"></a><tt class="py-lineno">648</tt>  <tt class="py-line">    <tt class="py-string">'h1'</tt><tt class="py-op">,</tt> </tt>
<a name="L649"></a><tt class="py-lineno">649</tt>  <tt class="py-line">    <tt class="py-string">'h2'</tt><tt class="py-op">,</tt> </tt>
<a name="L650"></a><tt class="py-lineno">650</tt>  <tt class="py-line">    <tt class="py-string">'h3'</tt><tt class="py-op">,</tt> </tt>
<a name="L651"></a><tt class="py-lineno">651</tt>  <tt class="py-line">    <tt class="py-string">'h4'</tt><tt class="py-op">,</tt> </tt>
<a name="L652"></a><tt class="py-lineno">652</tt>  <tt class="py-line">    <tt class="py-string">'h5'</tt><tt class="py-op">,</tt> </tt>
<a name="L653"></a><tt class="py-lineno">653</tt>  <tt class="py-line">    <tt class="py-string">'h6'</tt><tt class="py-op">,</tt> </tt>
<a name="L654"></a><tt class="py-lineno">654</tt>  <tt class="py-line">    <tt class="py-string">'hr'</tt><tt class="py-op">,</tt> </tt>
<a name="L655"></a><tt class="py-lineno">655</tt>  <tt class="py-line">    <tt class="py-string">'isindex'</tt><tt class="py-op">,</tt> </tt>
<a name="L656"></a><tt class="py-lineno">656</tt>  <tt class="py-line">    <tt class="py-string">'menu'</tt><tt class="py-op">,</tt> </tt>
<a name="L657"></a><tt class="py-lineno">657</tt>  <tt class="py-line">    <tt class="py-string">'noframes'</tt><tt class="py-op">,</tt> </tt>
<a name="L658"></a><tt class="py-lineno">658</tt>  <tt class="py-line">    <tt class="py-string">'noscript'</tt><tt class="py-op">,</tt> </tt>
<a name="L659"></a><tt class="py-lineno">659</tt>  <tt class="py-line">    <tt class="py-string">'ol'</tt><tt class="py-op">,</tt> </tt>
<a name="L660"></a><tt class="py-lineno">660</tt>  <tt class="py-line">    <tt class="py-string">'p'</tt><tt class="py-op">,</tt> </tt>
<a name="L661"></a><tt class="py-lineno">661</tt>  <tt class="py-line">    <tt class="py-string">'pre'</tt><tt class="py-op">,</tt> </tt>
<a name="L662"></a><tt class="py-lineno">662</tt>  <tt class="py-line">    <tt class="py-string">'table'</tt><tt class="py-op">,</tt> </tt>
<a name="L663"></a><tt class="py-lineno">663</tt>  <tt class="py-line">    <tt class="py-string">'ul'</tt><tt class="py-op">,</tt> </tt>
<a name="L664"></a><tt class="py-lineno">664</tt>  <tt class="py-line">    <tt class="py-op">)</tt> </tt>
<a name="L665"></a><tt class="py-lineno">665</tt>  <tt class="py-line"> </tt>
<a name="L666"></a><tt class="py-lineno">666</tt>  <tt class="py-line"><tt id="link-230" class="py-name" targets="Variable lxml.html.diff.block_level_container_tags=lxml.html.diff-module.html#block_level_container_tags"><a title="lxml.html.diff.block_level_container_tags" class="py-name" href="#" onclick="return doclink('link-230', 'block_level_container_tags', 'link-230');">block_level_container_tags</a></tt> <tt class="py-op">=</tt> <tt class="py-op">(</tt> </tt>
<a name="L667"></a><tt class="py-lineno">667</tt>  <tt class="py-line">    <tt class="py-string">'dd'</tt><tt class="py-op">,</tt> </tt>
<a name="L668"></a><tt class="py-lineno">668</tt>  <tt class="py-line">    <tt class="py-string">'dt'</tt><tt class="py-op">,</tt> </tt>
<a name="L669"></a><tt class="py-lineno">669</tt>  <tt class="py-line">    <tt class="py-string">'frameset'</tt><tt class="py-op">,</tt> </tt>
<a name="L670"></a><tt class="py-lineno">670</tt>  <tt class="py-line">    <tt class="py-string">'li'</tt><tt class="py-op">,</tt> </tt>
<a name="L671"></a><tt class="py-lineno">671</tt>  <tt class="py-line">    <tt class="py-string">'tbody'</tt><tt class="py-op">,</tt> </tt>
<a name="L672"></a><tt class="py-lineno">672</tt>  <tt class="py-line">    <tt class="py-string">'td'</tt><tt class="py-op">,</tt> </tt>
<a name="L673"></a><tt class="py-lineno">673</tt>  <tt class="py-line">    <tt class="py-string">'tfoot'</tt><tt class="py-op">,</tt> </tt>
<a name="L674"></a><tt class="py-lineno">674</tt>  <tt class="py-line">    <tt class="py-string">'th'</tt><tt class="py-op">,</tt> </tt>
<a name="L675"></a><tt class="py-lineno">675</tt>  <tt class="py-line">    <tt class="py-string">'thead'</tt><tt class="py-op">,</tt> </tt>
<a name="L676"></a><tt class="py-lineno">676</tt>  <tt class="py-line">    <tt class="py-string">'tr'</tt><tt class="py-op">,</tt> </tt>
<a name="L677"></a><tt class="py-lineno">677</tt>  <tt class="py-line">    <tt class="py-op">)</tt> </tt>
<a name="L678"></a><tt class="py-lineno">678</tt>  <tt class="py-line"> </tt>
<a name="L679"></a><tt class="py-lineno">679</tt>  <tt class="py-line"> </tt>
<a name="flatten_el"></a><div id="flatten_el-def"><a name="L680"></a><tt class="py-lineno">680</tt> <a class="py-toggle" href="#" id="flatten_el-toggle" onclick="return toggle('flatten_el');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#flatten_el">flatten_el</a><tt class="py-op">(</tt><tt class="py-param">el</tt><tt class="py-op">,</tt> <tt class="py-param">include_hrefs</tt><tt class="py-op">,</tt> <tt class="py-param">skip_tag</tt><tt class="py-op">=</tt><tt class="py-name">False</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="flatten_el-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="flatten_el-expanded"><a name="L681"></a><tt class="py-lineno">681</tt>  <tt class="py-line">    <tt class="py-docstring">""" Takes an lxml element el, and generates all the text chunks for</tt> </tt>
<a name="L682"></a><tt class="py-lineno">682</tt>  <tt class="py-line"><tt class="py-docstring">    that tag.  Each start tag is a chunk, each word is a chunk, and each</tt> </tt>
<a name="L683"></a><tt class="py-lineno">683</tt>  <tt class="py-line"><tt class="py-docstring">    end tag is a chunk.</tt> </tt>
<a name="L684"></a><tt class="py-lineno">684</tt>  <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L685"></a><tt class="py-lineno">685</tt>  <tt class="py-line"><tt class="py-docstring">    If skip_tag is true, then the outermost container tag is</tt> </tt>
<a name="L686"></a><tt class="py-lineno">686</tt>  <tt class="py-line"><tt class="py-docstring">    not returned (just its contents)."""</tt> </tt>
<a name="L687"></a><tt class="py-lineno">687</tt>  <tt class="py-line">    <tt class="py-keyword">if</tt> <tt class="py-keyword">not</tt> <tt class="py-name">skip_tag</tt><tt class="py-op">:</tt> </tt>
<a name="L688"></a><tt class="py-lineno">688</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-231" class="py-name"><a title="lxml.etree._Comment.tag
lxml.etree._Element.tag
lxml.etree._Entity.tag
lxml.etree._ProcessingInstruction.tag
lxml.tests.test_xpathevaluator.tag
xml.etree.ElementTree.Element.tag" class="py-name" href="#" onclick="return doclink('link-231', 'tag', 'link-103');">tag</a></tt> <tt class="py-op">==</tt> <tt class="py-string">'img'</tt><tt class="py-op">:</tt> </tt>
<a name="L689"></a><tt class="py-lineno">689</tt>  <tt class="py-line">            <tt class="py-keyword">yield</tt> <tt class="py-op">(</tt><tt class="py-string">'img'</tt><tt class="py-op">,</tt> <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-232" class="py-name" targets="Method lxml.etree._Attrib.get()=lxml.etree._Attrib-class.html#get,Method lxml.etree._Element.get()=lxml.etree._Element-class.html#get,Method lxml.etree._IDDict.get()=lxml.etree._IDDict-class.html#get,Method lxml.etree._ProcessingInstruction.get()=lxml.etree._ProcessingInstruction-class.html#get"><a title="lxml.etree._Attrib.get
lxml.etree._Element.get
lxml.etree._IDDict.get
lxml.etree._ProcessingInstruction.get" class="py-name" href="#" onclick="return doclink('link-232', 'get', 'link-232');">get</a></tt><tt class="py-op">(</tt><tt class="py-string">'src'</tt><tt class="py-op">)</tt><tt class="py-op">,</tt> <tt id="link-233" class="py-name" targets="Function lxml.html.diff.start_tag()=lxml.html.diff-module.html#start_tag"><a title="lxml.html.diff.start_tag" class="py-name" href="#" onclick="return doclink('link-233', 'start_tag', 'link-233');">start_tag</a></tt><tt class="py-op">(</tt><tt class="py-name">el</tt><tt class="py-op">)</tt><tt class="py-op">)</tt> </tt>
<a name="L690"></a><tt class="py-lineno">690</tt>  <tt class="py-line">        <tt class="py-keyword">else</tt><tt class="py-op">:</tt> </tt>
<a name="L691"></a><tt class="py-lineno">691</tt>  <tt class="py-line">            <tt class="py-keyword">yield</tt> <tt id="link-234" class="py-name"><a title="lxml.html.diff.start_tag" class="py-name" href="#" onclick="return doclink('link-234', 'start_tag', 'link-233');">start_tag</a></tt><tt class="py-op">(</tt><tt class="py-name">el</tt><tt class="py-op">)</tt> </tt>
<a name="L692"></a><tt class="py-lineno">692</tt>  <tt class="py-line">    <tt class="py-keyword">if</tt> <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-235" class="py-name"><a title="lxml.etree._Comment.tag
lxml.etree._Element.tag
lxml.etree._Entity.tag
lxml.etree._ProcessingInstruction.tag
lxml.tests.test_xpathevaluator.tag
xml.etree.ElementTree.Element.tag" class="py-name" href="#" onclick="return doclink('link-235', 'tag', 'link-103');">tag</a></tt> <tt class="py-keyword">in</tt> <tt id="link-236" class="py-name"><a title="lxml.doctestcompare.LXMLOutputChecker.empty_tags
lxml.html.defs.empty_tags
lxml.html.diff.empty_tags" class="py-name" href="#" onclick="return doclink('link-236', 'empty_tags', 'link-98');">empty_tags</a></tt> <tt class="py-keyword">and</tt> <tt class="py-keyword">not</tt> <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-237" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-237', 'text', 'link-11');">text</a></tt> <tt class="py-keyword">and</tt> <tt class="py-keyword">not</tt> <tt class="py-name">len</tt><tt class="py-op">(</tt><tt class="py-name">el</tt><tt class="py-op">)</tt> <tt class="py-keyword">and</tt> <tt class="py-keyword">not</tt> <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-238" class="py-name" targets="Variable lxml.etree._Element.tail=lxml.etree._Element-class.html#tail,Variable xml.etree.ElementTree.Element.tail=xml.etree.ElementTree.Element-class.html#tail"><a title="lxml.etree._Element.tail
xml.etree.ElementTree.Element.tail" class="py-name" href="#" onclick="return doclink('link-238', 'tail', 'link-238');">tail</a></tt><tt class="py-op">:</tt> </tt>
<a name="L693"></a><tt class="py-lineno">693</tt>  <tt class="py-line">        <tt class="py-keyword">return</tt> </tt>
<a name="L694"></a><tt class="py-lineno">694</tt>  <tt class="py-line">    <tt class="py-name">start_words</tt> <tt class="py-op">=</tt> <tt id="link-239" class="py-name" targets="Function lxml.html.diff.split_words()=lxml.html.diff-module.html#split_words"><a title="lxml.html.diff.split_words" class="py-name" href="#" onclick="return doclink('link-239', 'split_words', 'link-239');">split_words</a></tt><tt class="py-op">(</tt><tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-240" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-240', 'text', 'link-11');">text</a></tt><tt class="py-op">)</tt> </tt>
<a name="L695"></a><tt class="py-lineno">695</tt>  <tt class="py-line">    <tt class="py-keyword">for</tt> <tt class="py-name">word</tt> <tt class="py-keyword">in</tt> <tt class="py-name">start_words</tt><tt class="py-op">:</tt> </tt>
<a name="L696"></a><tt class="py-lineno">696</tt>  <tt class="py-line">        <tt class="py-keyword">yield</tt> <tt class="py-name">html_escape</tt><tt class="py-op">(</tt><tt class="py-name">word</tt><tt class="py-op">)</tt> </tt>
<a name="L697"></a><tt class="py-lineno">697</tt>  <tt class="py-line">    <tt class="py-keyword">for</tt> <tt class="py-name">child</tt> <tt class="py-keyword">in</tt> <tt class="py-name">el</tt><tt class="py-op">:</tt> </tt>
<a name="L698"></a><tt class="py-lineno">698</tt>  <tt class="py-line">        <tt class="py-keyword">for</tt> <tt class="py-name">item</tt> <tt class="py-keyword">in</tt> <tt id="link-241" class="py-name"><a title="lxml.html.diff.flatten_el" class="py-name" href="#" onclick="return doclink('link-241', 'flatten_el', 'link-179');">flatten_el</a></tt><tt class="py-op">(</tt><tt class="py-name">child</tt><tt class="py-op">,</tt> <tt class="py-name">include_hrefs</tt><tt class="py-op">=</tt><tt class="py-name">include_hrefs</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
<a name="L699"></a><tt class="py-lineno">699</tt>  <tt class="py-line">            <tt class="py-keyword">yield</tt> <tt class="py-name">item</tt> </tt>
<a name="L700"></a><tt class="py-lineno">700</tt>  <tt class="py-line">    <tt class="py-keyword">if</tt> <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-242" class="py-name"><a title="lxml.etree._Comment.tag
lxml.etree._Element.tag
lxml.etree._Entity.tag
lxml.etree._ProcessingInstruction.tag
lxml.tests.test_xpathevaluator.tag
xml.etree.ElementTree.Element.tag" class="py-name" href="#" onclick="return doclink('link-242', 'tag', 'link-103');">tag</a></tt> <tt class="py-op">==</tt> <tt class="py-string">'a'</tt> <tt class="py-keyword">and</tt> <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-243" class="py-name"><a title="lxml.etree._Attrib.get
lxml.etree._Element.get
lxml.etree._IDDict.get
lxml.etree._ProcessingInstruction.get" class="py-name" href="#" onclick="return doclink('link-243', 'get', 'link-232');">get</a></tt><tt class="py-op">(</tt><tt class="py-string">'href'</tt><tt class="py-op">)</tt> <tt class="py-keyword">and</tt> <tt class="py-name">include_hrefs</tt><tt class="py-op">:</tt> </tt>
<a name="L701"></a><tt class="py-lineno">701</tt>  <tt class="py-line">        <tt class="py-keyword">yield</tt> <tt class="py-op">(</tt><tt class="py-string">'href'</tt><tt class="py-op">,</tt> <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-244" class="py-name"><a title="lxml.etree._Attrib.get
lxml.etree._Element.get
lxml.etree._IDDict.get
lxml.etree._ProcessingInstruction.get" class="py-name" href="#" onclick="return doclink('link-244', 'get', 'link-232');">get</a></tt><tt class="py-op">(</tt><tt class="py-string">'href'</tt><tt class="py-op">)</tt><tt class="py-op">)</tt> </tt>
<a name="L702"></a><tt class="py-lineno">702</tt>  <tt class="py-line">    <tt class="py-keyword">if</tt> <tt class="py-keyword">not</tt> <tt class="py-name">skip_tag</tt><tt class="py-op">:</tt> </tt>
<a name="L703"></a><tt class="py-lineno">703</tt>  <tt class="py-line">        <tt class="py-keyword">yield</tt> <tt id="link-245" class="py-name" targets="Function lxml.html.diff.end_tag()=lxml.html.diff-module.html#end_tag"><a title="lxml.html.diff.end_tag" class="py-name" href="#" onclick="return doclink('link-245', 'end_tag', 'link-245');">end_tag</a></tt><tt class="py-op">(</tt><tt class="py-name">el</tt><tt class="py-op">)</tt> </tt>
<a name="L704"></a><tt class="py-lineno">704</tt>  <tt class="py-line">        <tt class="py-name">end_words</tt> <tt class="py-op">=</tt> <tt id="link-246" class="py-name"><a title="lxml.html.diff.split_words" class="py-name" href="#" onclick="return doclink('link-246', 'split_words', 'link-239');">split_words</a></tt><tt class="py-op">(</tt><tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-247" class="py-name"><a title="lxml.etree._Element.tail
xml.etree.ElementTree.Element.tail" class="py-name" href="#" onclick="return doclink('link-247', 'tail', 'link-238');">tail</a></tt><tt class="py-op">)</tt> </tt>
<a name="L705"></a><tt class="py-lineno">705</tt>  <tt class="py-line">        <tt class="py-keyword">for</tt> <tt class="py-name">word</tt> <tt class="py-keyword">in</tt> <tt class="py-name">end_words</tt><tt class="py-op">:</tt> </tt>
<a name="L706"></a><tt class="py-lineno">706</tt>  <tt class="py-line">            <tt class="py-keyword">yield</tt> <tt class="py-name">html_escape</tt><tt class="py-op">(</tt><tt class="py-name">word</tt><tt class="py-op">)</tt> </tt>
</div><a name="L707"></a><tt class="py-lineno">707</tt>  <tt class="py-line"> </tt>
<a name="L708"></a><tt class="py-lineno">708</tt>  <tt class="py-line"><tt id="link-248" class="py-name" targets="Variable lxml.html.diff.split_words_re=lxml.html.diff-module.html#split_words_re"><a title="lxml.html.diff.split_words_re" class="py-name" href="#" onclick="return doclink('link-248', 'split_words_re', 'link-248');">split_words_re</a></tt> <tt class="py-op">=</tt> <tt class="py-name">re</tt><tt class="py-op">.</tt><tt class="py-name">compile</tt><tt class="py-op">(</tt><tt class="py-string">r'\S+(?:\s+|$)'</tt><tt class="py-op">,</tt> <tt class="py-name">re</tt><tt class="py-op">.</tt><tt id="link-249" class="py-name" targets="Variable lxml.html.builder.U=lxml.html.builder-module.html#U"><a title="lxml.html.builder.U" class="py-name" href="#" onclick="return doclink('link-249', 'U', 'link-249');">U</a></tt><tt class="py-op">)</tt> </tt>
<a name="L709"></a><tt class="py-lineno">709</tt>  <tt class="py-line"> </tt>
<a name="split_words"></a><div id="split_words-def"><a name="L710"></a><tt class="py-lineno">710</tt> <a class="py-toggle" href="#" id="split_words-toggle" onclick="return toggle('split_words');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#split_words">split_words</a><tt class="py-op">(</tt><tt class="py-param">text</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="split_words-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="split_words-expanded"><a name="L711"></a><tt class="py-lineno">711</tt>  <tt class="py-line">    <tt class="py-docstring">""" Splits some text into words. Includes trailing whitespace</tt> </tt>
<a name="L712"></a><tt class="py-lineno">712</tt>  <tt class="py-line"><tt class="py-docstring">    on each word when appropriate.  """</tt> </tt>
<a name="L713"></a><tt class="py-lineno">713</tt>  <tt class="py-line">    <tt class="py-keyword">if</tt> <tt class="py-keyword">not</tt> <tt id="link-250" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-250', 'text', 'link-11');">text</a></tt> <tt class="py-keyword">or</tt> <tt class="py-keyword">not</tt> <tt id="link-251" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-251', 'text', 'link-11');">text</a></tt><tt class="py-op">.</tt><tt id="link-252" class="py-name"><a title="lxml.doctestcompare.strip" class="py-name" href="#" onclick="return doclink('link-252', 'strip', 'link-19');">strip</a></tt><tt class="py-op">(</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
<a name="L714"></a><tt class="py-lineno">714</tt>  <tt class="py-line">        <tt class="py-keyword">return</tt> <tt class="py-op">[</tt><tt class="py-op">]</tt> </tt>
<a name="L715"></a><tt class="py-lineno">715</tt>  <tt class="py-line"> </tt>
<a name="L716"></a><tt class="py-lineno">716</tt>  <tt class="py-line">    <tt class="py-name">words</tt> <tt class="py-op">=</tt> <tt id="link-253" class="py-name"><a title="lxml.html.diff.split_words_re" class="py-name" href="#" onclick="return doclink('link-253', 'split_words_re', 'link-248');">split_words_re</a></tt><tt class="py-op">.</tt><tt id="link-254" class="py-name" targets="Method lxml.etree._Element.findall()=lxml.etree._Element-class.html#findall,Method lxml.etree._ElementTree.findall()=lxml.etree._ElementTree-class.html#findall"><a title="lxml.etree._Element.findall
lxml.etree._ElementTree.findall" class="py-name" href="#" onclick="return doclink('link-254', 'findall', 'link-254');">findall</a></tt><tt class="py-op">(</tt><tt id="link-255" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-255', 'text', 'link-11');">text</a></tt><tt class="py-op">)</tt> </tt>
<a name="L717"></a><tt class="py-lineno">717</tt>  <tt class="py-line">    <tt class="py-keyword">return</tt> <tt class="py-name">words</tt> </tt>
</div><a name="L718"></a><tt class="py-lineno">718</tt>  <tt class="py-line"> </tt>
<a name="L719"></a><tt class="py-lineno">719</tt>  <tt class="py-line"><tt id="link-256" class="py-name" targets="Variable lxml.html.diff.start_whitespace_re=lxml.html.diff-module.html#start_whitespace_re"><a title="lxml.html.diff.start_whitespace_re" class="py-name" href="#" onclick="return doclink('link-256', 'start_whitespace_re', 'link-256');">start_whitespace_re</a></tt> <tt class="py-op">=</tt> <tt class="py-name">re</tt><tt class="py-op">.</tt><tt class="py-name">compile</tt><tt class="py-op">(</tt><tt class="py-string">r'^[ \t\n\r]'</tt><tt class="py-op">)</tt> </tt>
<a name="L720"></a><tt class="py-lineno">720</tt>  <tt class="py-line"> </tt>
<a name="start_tag"></a><div id="start_tag-def"><a name="L721"></a><tt class="py-lineno">721</tt> <a class="py-toggle" href="#" id="start_tag-toggle" onclick="return toggle('start_tag');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#start_tag">start_tag</a><tt class="py-op">(</tt><tt class="py-param">el</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="start_tag-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="start_tag-expanded"><a name="L722"></a><tt class="py-lineno">722</tt>  <tt class="py-line">    <tt class="py-docstring">"""</tt> </tt>
<a name="L723"></a><tt class="py-lineno">723</tt>  <tt class="py-line"><tt class="py-docstring">    The text representation of the start tag for a tag.</tt> </tt>
<a name="L724"></a><tt class="py-lineno">724</tt>  <tt class="py-line"><tt class="py-docstring">    """</tt> </tt>
<a name="L725"></a><tt class="py-lineno">725</tt>  <tt class="py-line">    <tt class="py-keyword">return</tt> <tt class="py-string">'&lt;%s%s&gt;'</tt> <tt class="py-op">%</tt> <tt class="py-op">(</tt> </tt>
<a name="L726"></a><tt class="py-lineno">726</tt>  <tt class="py-line">        <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-257" class="py-name"><a title="lxml.etree._Comment.tag
lxml.etree._Element.tag
lxml.etree._Entity.tag
lxml.etree._ProcessingInstruction.tag
lxml.tests.test_xpathevaluator.tag
xml.etree.ElementTree.Element.tag" class="py-name" href="#" onclick="return doclink('link-257', 'tag', 'link-103');">tag</a></tt><tt class="py-op">,</tt> <tt class="py-string">''</tt><tt class="py-op">.</tt><tt class="py-name">join</tt><tt class="py-op">(</tt><tt class="py-op">[</tt><tt class="py-string">' %s="%s"'</tt> <tt class="py-op">%</tt> <tt class="py-op">(</tt><tt id="link-258" class="py-name"><a title="lxml.etree.DTD.name
lxml.etree._Entity.name
lxml.html.InputMixin.name
lxml.objectify.PyType.name" class="py-name" href="#" onclick="return doclink('link-258', 'name', 'link-95');">name</a></tt><tt class="py-op">,</tt> <tt class="py-name">html_escape</tt><tt class="py-op">(</tt><tt id="link-259" class="py-name" targets="Variable lxml.html.CheckboxGroup.value=lxml.html.CheckboxGroup-class.html#value,Variable lxml.html.InputElement.value=lxml.html.InputElement-class.html#value,Variable lxml.html.RadioGroup.value=lxml.html.RadioGroup-class.html#value,Variable lxml.html.SelectElement.value=lxml.html.SelectElement-class.html#value,Variable lxml.html.TextareaElement.value=lxml.html.TextareaElement-class.html#value"><a title="lxml.html.CheckboxGroup.value
lxml.html.InputElement.value
lxml.html.RadioGroup.value
lxml.html.SelectElement.value
lxml.html.TextareaElement.value" class="py-name" href="#" onclick="return doclink('link-259', 'value', 'link-259');">value</a></tt><tt class="py-op">,</tt> <tt class="py-name">True</tt><tt class="py-op">)</tt><tt class="py-op">)</tt> </tt>
<a name="L727"></a><tt class="py-lineno">727</tt>  <tt class="py-line">                         <tt class="py-keyword">for</tt> <tt id="link-260" class="py-name"><a title="lxml.etree.DTD.name
lxml.etree._Entity.name
lxml.html.InputMixin.name
lxml.objectify.PyType.name" class="py-name" href="#" onclick="return doclink('link-260', 'name', 'link-95');">name</a></tt><tt class="py-op">,</tt> <tt id="link-261" class="py-name"><a title="lxml.html.CheckboxGroup.value
lxml.html.InputElement.value
lxml.html.RadioGroup.value
lxml.html.SelectElement.value
lxml.html.TextareaElement.value" class="py-name" href="#" onclick="return doclink('link-261', 'value', 'link-259');">value</a></tt> <tt class="py-keyword">in</tt> <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-262" class="py-name" targets="Variable lxml.etree._Element.attrib=lxml.etree._Element-class.html#attrib,Variable lxml.etree._ProcessingInstruction.attrib=lxml.etree._ProcessingInstruction-class.html#attrib,Function lxml.tests.selftest2.attrib()=lxml.tests.selftest2-module.html#attrib,Variable xml.etree.ElementTree.Element.attrib=xml.etree.ElementTree.Element-class.html#attrib"><a title="lxml.etree._Element.attrib
lxml.etree._ProcessingInstruction.attrib
lxml.tests.selftest2.attrib
xml.etree.ElementTree.Element.attrib" class="py-name" href="#" onclick="return doclink('link-262', 'attrib', 'link-262');">attrib</a></tt><tt class="py-op">.</tt><tt id="link-263" class="py-name" targets="Method lxml.etree._Attrib.items()=lxml.etree._Attrib-class.html#items,Method lxml.etree._Element.items()=lxml.etree._Element-class.html#items,Method lxml.etree._IDDict.items()=lxml.etree._IDDict-class.html#items"><a title="lxml.etree._Attrib.items
lxml.etree._Element.items
lxml.etree._IDDict.items" class="py-name" href="#" onclick="return doclink('link-263', 'items', 'link-263');">items</a></tt><tt class="py-op">(</tt><tt class="py-op">)</tt><tt class="py-op">]</tt><tt class="py-op">)</tt><tt class="py-op">)</tt> </tt>
</div><a name="L728"></a><tt class="py-lineno">728</tt>  <tt class="py-line"> </tt>
<a name="end_tag"></a><div id="end_tag-def"><a name="L729"></a><tt class="py-lineno">729</tt> <a class="py-toggle" href="#" id="end_tag-toggle" onclick="return toggle('end_tag');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#end_tag">end_tag</a><tt class="py-op">(</tt><tt class="py-param">el</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="end_tag-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="end_tag-expanded"><a name="L730"></a><tt class="py-lineno">730</tt>  <tt class="py-line">    <tt class="py-docstring">""" The text representation of an end tag for a tag.  Includes</tt> </tt>
<a name="L731"></a><tt class="py-lineno">731</tt>  <tt class="py-line"><tt class="py-docstring">    trailing whitespace when appropriate.  """</tt> </tt>
<a name="L732"></a><tt class="py-lineno">732</tt>  <tt class="py-line">    <tt class="py-keyword">if</tt> <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-264" class="py-name"><a title="lxml.etree._Element.tail
xml.etree.ElementTree.Element.tail" class="py-name" href="#" onclick="return doclink('link-264', 'tail', 'link-238');">tail</a></tt> <tt class="py-keyword">and</tt> <tt id="link-265" class="py-name"><a title="lxml.html.diff.start_whitespace_re" class="py-name" href="#" onclick="return doclink('link-265', 'start_whitespace_re', 'link-256');">start_whitespace_re</a></tt><tt class="py-op">.</tt><tt class="py-name">search</tt><tt class="py-op">(</tt><tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-266" class="py-name"><a title="lxml.etree._Element.tail
xml.etree.ElementTree.Element.tail" class="py-name" href="#" onclick="return doclink('link-266', 'tail', 'link-238');">tail</a></tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
<a name="L733"></a><tt class="py-lineno">733</tt>  <tt class="py-line">        <tt class="py-name">extra</tt> <tt class="py-op">=</tt> <tt class="py-string">' '</tt> </tt>
<a name="L734"></a><tt class="py-lineno">734</tt>  <tt class="py-line">    <tt class="py-keyword">else</tt><tt class="py-op">:</tt> </tt>
<a name="L735"></a><tt class="py-lineno">735</tt>  <tt class="py-line">        <tt class="py-name">extra</tt> <tt class="py-op">=</tt> <tt class="py-string">''</tt> </tt>
<a name="L736"></a><tt class="py-lineno">736</tt>  <tt class="py-line">    <tt class="py-keyword">return</tt> <tt class="py-string">'&lt;/%s&gt;%s'</tt> <tt class="py-op">%</tt> <tt class="py-op">(</tt><tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-267" class="py-name"><a title="lxml.etree._Comment.tag
lxml.etree._Element.tag
lxml.etree._Entity.tag
lxml.etree._ProcessingInstruction.tag
lxml.tests.test_xpathevaluator.tag
xml.etree.ElementTree.Element.tag" class="py-name" href="#" onclick="return doclink('link-267', 'tag', 'link-103');">tag</a></tt><tt class="py-op">,</tt> <tt class="py-name">extra</tt><tt class="py-op">)</tt> </tt>
</div><a name="L737"></a><tt class="py-lineno">737</tt>  <tt class="py-line"> </tt>
<a name="is_word"></a><div id="is_word-def"><a name="L738"></a><tt class="py-lineno">738</tt> <a class="py-toggle" href="#" id="is_word-toggle" onclick="return toggle('is_word');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#is_word">is_word</a><tt class="py-op">(</tt><tt class="py-param">tok</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="is_word-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="is_word-expanded"><a name="L739"></a><tt class="py-lineno">739</tt>  <tt class="py-line">    <tt class="py-keyword">return</tt> <tt class="py-keyword">not</tt> <tt class="py-name">tok</tt><tt class="py-op">.</tt><tt class="py-name">startswith</tt><tt class="py-op">(</tt><tt class="py-string">'&lt;'</tt><tt class="py-op">)</tt> </tt>
</div><a name="L740"></a><tt class="py-lineno">740</tt>  <tt class="py-line"> </tt>
<a name="is_end_tag"></a><div id="is_end_tag-def"><a name="L741"></a><tt class="py-lineno">741</tt> <a class="py-toggle" href="#" id="is_end_tag-toggle" onclick="return toggle('is_end_tag');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#is_end_tag">is_end_tag</a><tt class="py-op">(</tt><tt class="py-param">tok</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="is_end_tag-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="is_end_tag-expanded"><a name="L742"></a><tt class="py-lineno">742</tt>  <tt class="py-line">    <tt class="py-keyword">return</tt> <tt class="py-name">tok</tt><tt class="py-op">.</tt><tt class="py-name">startswith</tt><tt class="py-op">(</tt><tt class="py-string">'&lt;/'</tt><tt class="py-op">)</tt> </tt>
</div><a name="L743"></a><tt class="py-lineno">743</tt>  <tt class="py-line"> </tt>
<a name="is_start_tag"></a><div id="is_start_tag-def"><a name="L744"></a><tt class="py-lineno">744</tt> <a class="py-toggle" href="#" id="is_start_tag-toggle" onclick="return toggle('is_start_tag');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#is_start_tag">is_start_tag</a><tt class="py-op">(</tt><tt class="py-param">tok</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="is_start_tag-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="is_start_tag-expanded"><a name="L745"></a><tt class="py-lineno">745</tt>  <tt class="py-line">    <tt class="py-keyword">return</tt> <tt class="py-name">tok</tt><tt class="py-op">.</tt><tt class="py-name">startswith</tt><tt class="py-op">(</tt><tt class="py-string">'&lt;'</tt><tt class="py-op">)</tt> <tt class="py-keyword">and</tt> <tt class="py-keyword">not</tt> <tt class="py-name">tok</tt><tt class="py-op">.</tt><tt class="py-name">startswith</tt><tt class="py-op">(</tt><tt class="py-string">'&lt;/'</tt><tt class="py-op">)</tt> </tt>
</div><a name="L746"></a><tt class="py-lineno">746</tt>  <tt class="py-line"> </tt>
<a name="fixup_ins_del_tags"></a><div id="fixup_ins_del_tags-def"><a name="L747"></a><tt class="py-lineno">747</tt> <a class="py-toggle" href="#" id="fixup_ins_del_tags-toggle" onclick="return toggle('fixup_ins_del_tags');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#fixup_ins_del_tags">fixup_ins_del_tags</a><tt class="py-op">(</tt><tt class="py-param">html</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="fixup_ins_del_tags-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="fixup_ins_del_tags-expanded"><a name="L748"></a><tt class="py-lineno">748</tt>  <tt class="py-line">    <tt class="py-docstring">""" Given an html string, move any &lt;ins&gt; or &lt;del&gt; tags inside of any</tt> </tt>
<a name="L749"></a><tt class="py-lineno">749</tt>  <tt class="py-line"><tt class="py-docstring">    block-level elements, e.g. transform &lt;ins&gt;&lt;p&gt;word&lt;/p&gt;&lt;/ins&gt; to</tt> </tt>
<a name="L750"></a><tt class="py-lineno">750</tt>  <tt class="py-line"><tt class="py-docstring">    &lt;p&gt;&lt;ins&gt;word&lt;/ins&gt;&lt;/p&gt; """</tt> </tt>
<a name="L751"></a><tt class="py-lineno">751</tt>  <tt class="py-line">    <tt class="py-name">doc</tt> <tt class="py-op">=</tt> <tt id="link-268" class="py-name"><a title="lxml.html.diff.parse_html" class="py-name" href="#" onclick="return doclink('link-268', 'parse_html', 'link-177');">parse_html</a></tt><tt class="py-op">(</tt><tt id="link-269" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-269', 'html', 'link-3');">html</a></tt><tt class="py-op">,</tt> <tt class="py-name">cleanup</tt><tt class="py-op">=</tt><tt class="py-name">False</tt><tt class="py-op">)</tt> </tt>
<a name="L752"></a><tt class="py-lineno">752</tt>  <tt class="py-line">    <tt id="link-270" class="py-name" targets="Function lxml.html.diff._fixup_ins_del_tags()=lxml.html.diff-module.html#_fixup_ins_del_tags"><a title="lxml.html.diff._fixup_ins_del_tags" class="py-name" href="#" onclick="return doclink('link-270', '_fixup_ins_del_tags', 'link-270');">_fixup_ins_del_tags</a></tt><tt class="py-op">(</tt><tt class="py-name">doc</tt><tt class="py-op">)</tt> </tt>
<a name="L753"></a><tt class="py-lineno">753</tt>  <tt class="py-line">    <tt id="link-271" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-271', 'html', 'link-3');">html</a></tt> <tt class="py-op">=</tt> <tt id="link-272" class="py-name" targets="Function lxml.html.diff.serialize_html_fragment()=lxml.html.diff-module.html#serialize_html_fragment"><a title="lxml.html.diff.serialize_html_fragment" class="py-name" href="#" onclick="return doclink('link-272', 'serialize_html_fragment', 'link-272');">serialize_html_fragment</a></tt><tt class="py-op">(</tt><tt class="py-name">doc</tt><tt class="py-op">,</tt> <tt class="py-name">skip_outer</tt><tt class="py-op">=</tt><tt class="py-name">True</tt><tt class="py-op">)</tt> </tt>
<a name="L754"></a><tt class="py-lineno">754</tt>  <tt class="py-line">    <tt class="py-keyword">return</tt> <tt id="link-273" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-273', 'html', 'link-3');">html</a></tt> </tt>
</div><a name="L755"></a><tt class="py-lineno">755</tt>  <tt class="py-line"> </tt>
<a name="serialize_html_fragment"></a><div id="serialize_html_fragment-def"><a name="L756"></a><tt class="py-lineno">756</tt> <a class="py-toggle" href="#" id="serialize_html_fragment-toggle" onclick="return toggle('serialize_html_fragment');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#serialize_html_fragment">serialize_html_fragment</a><tt class="py-op">(</tt><tt class="py-param">el</tt><tt class="py-op">,</tt> <tt class="py-param">skip_outer</tt><tt class="py-op">=</tt><tt class="py-name">False</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="serialize_html_fragment-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="serialize_html_fragment-expanded"><a name="L757"></a><tt class="py-lineno">757</tt>  <tt class="py-line">    <tt class="py-docstring">""" Serialize a single lxml element as HTML.  The serialized form</tt> </tt>
<a name="L758"></a><tt class="py-lineno">758</tt>  <tt class="py-line"><tt class="py-docstring">    includes the elements tail.  </tt> </tt>
<a name="L759"></a><tt class="py-lineno">759</tt>  <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L760"></a><tt class="py-lineno">760</tt>  <tt class="py-line"><tt class="py-docstring">    If skip_outer is true, then don't serialize the outermost tag</tt> </tt>
<a name="L761"></a><tt class="py-lineno">761</tt>  <tt class="py-line"><tt class="py-docstring">    """</tt> </tt>
<a name="L762"></a><tt class="py-lineno">762</tt>  <tt class="py-line">    <tt class="py-keyword">assert</tt> <tt class="py-keyword">not</tt> <tt class="py-name">isinstance</tt><tt class="py-op">(</tt><tt class="py-name">el</tt><tt class="py-op">,</tt> <tt id="link-274" class="py-name"><a title="lxml.html.clean.basestring" class="py-name" href="#" onclick="return doclink('link-274', 'basestring', 'link-7');">basestring</a></tt><tt class="py-op">)</tt><tt class="py-op">,</tt> <tt class="py-op">(</tt> </tt>
<a name="L763"></a><tt class="py-lineno">763</tt>  <tt class="py-line">        <tt class="py-string">"You should pass in an element, not a string like %r"</tt> <tt class="py-op">%</tt> <tt class="py-name">el</tt><tt class="py-op">)</tt> </tt>
<a name="L764"></a><tt class="py-lineno">764</tt>  <tt class="py-line">    <tt id="link-275" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-275', 'html', 'link-3');">html</a></tt> <tt class="py-op">=</tt> <tt id="link-276" class="py-name"><a title="lxml.etree
lxml.sax.ElementTreeContentHandler.etree
lxml.tests.test_elementtree.CElementTreeTestCase.etree
lxml.tests.test_elementtree._ETreeTestCaseBase.etree
lxml.tests.test_elementtree._XMLPullParserTest.etree
lxml.tests.test_io._IOTestCaseBase.etree" class="py-name" href="#" onclick="return doclink('link-276', 'etree', 'link-1');">etree</a></tt><tt class="py-op">.</tt><tt id="link-277" class="py-name" targets="Method lxml.etree.XSLT.tostring()=lxml.etree.XSLT-class.html#tostring,Function lxml.etree.tostring()=lxml.etree-module.html#tostring"><a title="lxml.etree.XSLT.tostring
lxml.etree.tostring" class="py-name" href="#" onclick="return doclink('link-277', 'tostring', 'link-277');">tostring</a></tt><tt class="py-op">(</tt><tt class="py-name">el</tt><tt class="py-op">,</tt> <tt id="link-278" class="py-name" targets="Variable lxml.html.FormElement.method=lxml.html.FormElement-class.html#method"><a title="lxml.html.FormElement.method" class="py-name" href="#" onclick="return doclink('link-278', 'method', 'link-278');">method</a></tt><tt class="py-op">=</tt><tt class="py-string">"html"</tt><tt class="py-op">,</tt> <tt id="link-279" class="py-name" targets="Variable lxml.etree.DocInfo.encoding=lxml.etree.DocInfo-class.html#encoding,Function lxml.tests.selftest.encoding()=lxml.tests.selftest-module.html#encoding,Function lxml.tests.selftest2.encoding()=lxml.tests.selftest2-module.html#encoding"><a title="lxml.etree.DocInfo.encoding
lxml.tests.selftest.encoding
lxml.tests.selftest2.encoding" class="py-name" href="#" onclick="return doclink('link-279', 'encoding', 'link-279');">encoding</a></tt><tt class="py-op">=</tt><tt class="py-name">_unicode</tt><tt class="py-op">)</tt> </tt>
<a name="L765"></a><tt class="py-lineno">765</tt>  <tt class="py-line">    <tt class="py-keyword">if</tt> <tt class="py-name">skip_outer</tt><tt class="py-op">:</tt> </tt>
<a name="L766"></a><tt class="py-lineno">766</tt>  <tt class="py-line">        <tt class="py-comment"># Get rid of the extra starting tag:</tt> </tt>
<a name="L767"></a><tt class="py-lineno">767</tt>  <tt class="py-line">        <tt id="link-280" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-280', 'html', 'link-3');">html</a></tt> <tt class="py-op">=</tt> <tt id="link-281" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-281', 'html', 'link-3');">html</a></tt><tt class="py-op">[</tt><tt id="link-282" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-282', 'html', 'link-3');">html</a></tt><tt class="py-op">.</tt><tt id="link-283" class="py-name" targets="Method lxml.etree._Element.find()=lxml.etree._Element-class.html#find,Method lxml.etree._ElementTree.find()=lxml.etree._ElementTree-class.html#find,Variable lxml.objectify.ObjectPath.find=lxml.objectify.ObjectPath-class.html#find,Function lxml.tests.selftest.find()=lxml.tests.selftest-module.html#find,Function lxml.tests.selftest2.find()=lxml.tests.selftest2-module.html#find"><a title="lxml.etree._Element.find
lxml.etree._ElementTree.find
lxml.objectify.ObjectPath.find
lxml.tests.selftest.find
lxml.tests.selftest2.find" class="py-name" href="#" onclick="return doclink('link-283', 'find', 'link-283');">find</a></tt><tt class="py-op">(</tt><tt class="py-string">'&gt;'</tt><tt class="py-op">)</tt><tt class="py-op">+</tt><tt class="py-number">1</tt><tt class="py-op">:</tt><tt class="py-op">]</tt> </tt>
<a name="L768"></a><tt class="py-lineno">768</tt>  <tt class="py-line">        <tt class="py-comment"># Get rid of the extra end tag:</tt> </tt>
<a name="L769"></a><tt class="py-lineno">769</tt>  <tt class="py-line">        <tt id="link-284" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-284', 'html', 'link-3');">html</a></tt> <tt class="py-op">=</tt> <tt id="link-285" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-285', 'html', 'link-3');">html</a></tt><tt class="py-op">[</tt><tt class="py-op">:</tt><tt id="link-286" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-286', 'html', 'link-3');">html</a></tt><tt class="py-op">.</tt><tt class="py-name">rfind</tt><tt class="py-op">(</tt><tt class="py-string">'&lt;'</tt><tt class="py-op">)</tt><tt class="py-op">]</tt> </tt>
<a name="L770"></a><tt class="py-lineno">770</tt>  <tt class="py-line">        <tt class="py-keyword">return</tt> <tt id="link-287" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-287', 'html', 'link-3');">html</a></tt><tt class="py-op">.</tt><tt id="link-288" class="py-name"><a title="lxml.doctestcompare.strip" class="py-name" href="#" onclick="return doclink('link-288', 'strip', 'link-19');">strip</a></tt><tt class="py-op">(</tt><tt class="py-op">)</tt> </tt>
<a name="L771"></a><tt class="py-lineno">771</tt>  <tt class="py-line">    <tt class="py-keyword">else</tt><tt class="py-op">:</tt> </tt>
<a name="L772"></a><tt class="py-lineno">772</tt>  <tt class="py-line">        <tt class="py-keyword">return</tt> <tt id="link-289" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-289', 'html', 'link-3');">html</a></tt> </tt>
</div><a name="L773"></a><tt class="py-lineno">773</tt>  <tt class="py-line"> </tt>
<a name="_fixup_ins_del_tags"></a><div id="_fixup_ins_del_tags-def"><a name="L774"></a><tt class="py-lineno">774</tt> <a class="py-toggle" href="#" id="_fixup_ins_del_tags-toggle" onclick="return toggle('_fixup_ins_del_tags');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#_fixup_ins_del_tags">_fixup_ins_del_tags</a><tt class="py-op">(</tt><tt class="py-param">doc</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="_fixup_ins_del_tags-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="_fixup_ins_del_tags-expanded"><a name="L775"></a><tt class="py-lineno">775</tt>  <tt class="py-line">    <tt class="py-docstring">"""fixup_ins_del_tags that works on an lxml document in-place</tt> </tt>
<a name="L776"></a><tt class="py-lineno">776</tt>  <tt class="py-line"><tt class="py-docstring">    """</tt> </tt>
<a name="L777"></a><tt class="py-lineno">777</tt>  <tt class="py-line">    <tt class="py-keyword">for</tt> <tt id="link-290" class="py-name"><a title="lxml.etree._Comment.tag
lxml.etree._Element.tag
lxml.etree._Entity.tag
lxml.etree._ProcessingInstruction.tag
lxml.tests.test_xpathevaluator.tag
xml.etree.ElementTree.Element.tag" class="py-name" href="#" onclick="return doclink('link-290', 'tag', 'link-103');">tag</a></tt> <tt class="py-keyword">in</tt> <tt class="py-op">[</tt><tt class="py-string">'ins'</tt><tt class="py-op">,</tt> <tt class="py-string">'del'</tt><tt class="py-op">]</tt><tt class="py-op">:</tt> </tt>
<a name="L778"></a><tt class="py-lineno">778</tt>  <tt class="py-line">        <tt class="py-keyword">for</tt> <tt class="py-name">el</tt> <tt class="py-keyword">in</tt> <tt class="py-name">doc</tt><tt class="py-op">.</tt><tt id="link-291" class="py-name" targets="Method lxml.etree._Element.xpath()=lxml.etree._Element-class.html#xpath,Method lxml.etree._ElementTree.xpath()=lxml.etree._ElementTree-class.html#xpath,Function lxml.tests.test_xpathevaluator.xpath()=lxml.tests.test_xpathevaluator-module.html#xpath"><a title="lxml.etree._Element.xpath
lxml.etree._ElementTree.xpath
lxml.tests.test_xpathevaluator.xpath" class="py-name" href="#" onclick="return doclink('link-291', 'xpath', 'link-291');">xpath</a></tt><tt class="py-op">(</tt><tt class="py-string">'descendant-or-self::%s'</tt> <tt class="py-op">%</tt> <tt id="link-292" class="py-name"><a title="lxml.etree._Comment.tag
lxml.etree._Element.tag
lxml.etree._Entity.tag
lxml.etree._ProcessingInstruction.tag
lxml.tests.test_xpathevaluator.tag
xml.etree.ElementTree.Element.tag" class="py-name" href="#" onclick="return doclink('link-292', 'tag', 'link-103');">tag</a></tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
<a name="L779"></a><tt class="py-lineno">779</tt>  <tt class="py-line">            <tt class="py-keyword">if</tt> <tt class="py-keyword">not</tt> <tt id="link-293" class="py-name" targets="Function lxml.html.diff._contains_block_level_tag()=lxml.html.diff-module.html#_contains_block_level_tag"><a title="lxml.html.diff._contains_block_level_tag" class="py-name" href="#" onclick="return doclink('link-293', '_contains_block_level_tag', 'link-293');">_contains_block_level_tag</a></tt><tt class="py-op">(</tt><tt class="py-name">el</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
<a name="L780"></a><tt class="py-lineno">780</tt>  <tt class="py-line">                <tt class="py-keyword">continue</tt> </tt>
<a name="L781"></a><tt class="py-lineno">781</tt>  <tt class="py-line">            <tt id="link-294" class="py-name" targets="Function lxml.html.diff._move_el_inside_block()=lxml.html.diff-module.html#_move_el_inside_block"><a title="lxml.html.diff._move_el_inside_block" class="py-name" href="#" onclick="return doclink('link-294', '_move_el_inside_block', 'link-294');">_move_el_inside_block</a></tt><tt class="py-op">(</tt><tt class="py-name">el</tt><tt class="py-op">,</tt> <tt id="link-295" class="py-name"><a title="lxml.etree._Comment.tag
lxml.etree._Element.tag
lxml.etree._Entity.tag
lxml.etree._ProcessingInstruction.tag
lxml.tests.test_xpathevaluator.tag
xml.etree.ElementTree.Element.tag" class="py-name" href="#" onclick="return doclink('link-295', 'tag', 'link-103');">tag</a></tt><tt class="py-op">=</tt><tt id="link-296" class="py-name"><a title="lxml.etree._Comment.tag
lxml.etree._Element.tag
lxml.etree._Entity.tag
lxml.etree._ProcessingInstruction.tag
lxml.tests.test_xpathevaluator.tag
xml.etree.ElementTree.Element.tag" class="py-name" href="#" onclick="return doclink('link-296', 'tag', 'link-103');">tag</a></tt><tt class="py-op">)</tt> </tt>
<a name="L782"></a><tt class="py-lineno">782</tt>  <tt class="py-line">            <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-297" class="py-name" targets="Method lxml.html.HtmlMixin.drop_tag()=lxml.html.HtmlMixin-class.html#drop_tag"><a title="lxml.html.HtmlMixin.drop_tag" class="py-name" href="#" onclick="return doclink('link-297', 'drop_tag', 'link-297');">drop_tag</a></tt><tt class="py-op">(</tt><tt class="py-op">)</tt> </tt>
</div><a name="L783"></a><tt class="py-lineno">783</tt>  <tt class="py-line">            <tt class="py-comment">#_merge_element_contents(el)</tt> </tt>
<a name="L784"></a><tt class="py-lineno">784</tt>  <tt class="py-line"> </tt>
<a name="_contains_block_level_tag"></a><div id="_contains_block_level_tag-def"><a name="L785"></a><tt class="py-lineno">785</tt> <a class="py-toggle" href="#" id="_contains_block_level_tag-toggle" onclick="return toggle('_contains_block_level_tag');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#_contains_block_level_tag">_contains_block_level_tag</a><tt class="py-op">(</tt><tt class="py-param">el</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="_contains_block_level_tag-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="_contains_block_level_tag-expanded"><a name="L786"></a><tt class="py-lineno">786</tt>  <tt class="py-line">    <tt class="py-docstring">"""True if the element contains any block-level elements, like &lt;p&gt;, &lt;td&gt;, etc.</tt> </tt>
<a name="L787"></a><tt class="py-lineno">787</tt>  <tt class="py-line"><tt class="py-docstring">    """</tt> </tt>
<a name="L788"></a><tt class="py-lineno">788</tt>  <tt class="py-line">    <tt class="py-keyword">if</tt> <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-298" class="py-name"><a title="lxml.etree._Comment.tag
lxml.etree._Element.tag
lxml.etree._Entity.tag
lxml.etree._ProcessingInstruction.tag
lxml.tests.test_xpathevaluator.tag
xml.etree.ElementTree.Element.tag" class="py-name" href="#" onclick="return doclink('link-298', 'tag', 'link-103');">tag</a></tt> <tt class="py-keyword">in</tt> <tt id="link-299" class="py-name"><a title="lxml.html.diff.block_level_tags" class="py-name" href="#" onclick="return doclink('link-299', 'block_level_tags', 'link-229');">block_level_tags</a></tt> <tt class="py-keyword">or</tt> <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-300" class="py-name"><a title="lxml.etree._Comment.tag
lxml.etree._Element.tag
lxml.etree._Entity.tag
lxml.etree._ProcessingInstruction.tag
lxml.tests.test_xpathevaluator.tag
xml.etree.ElementTree.Element.tag" class="py-name" href="#" onclick="return doclink('link-300', 'tag', 'link-103');">tag</a></tt> <tt class="py-keyword">in</tt> <tt id="link-301" class="py-name"><a title="lxml.html.diff.block_level_container_tags" class="py-name" href="#" onclick="return doclink('link-301', 'block_level_container_tags', 'link-230');">block_level_container_tags</a></tt><tt class="py-op">:</tt> </tt>
<a name="L789"></a><tt class="py-lineno">789</tt>  <tt class="py-line">        <tt class="py-keyword">return</tt> <tt class="py-name">True</tt> </tt>
<a name="L790"></a><tt class="py-lineno">790</tt>  <tt class="py-line">    <tt class="py-keyword">for</tt> <tt class="py-name">child</tt> <tt class="py-keyword">in</tt> <tt class="py-name">el</tt><tt class="py-op">:</tt> </tt>
<a name="L791"></a><tt class="py-lineno">791</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt id="link-302" class="py-name"><a title="lxml.html.diff._contains_block_level_tag" class="py-name" href="#" onclick="return doclink('link-302', '_contains_block_level_tag', 'link-293');">_contains_block_level_tag</a></tt><tt class="py-op">(</tt><tt class="py-name">child</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
<a name="L792"></a><tt class="py-lineno">792</tt>  <tt class="py-line">            <tt class="py-keyword">return</tt> <tt class="py-name">True</tt> </tt>
<a name="L793"></a><tt class="py-lineno">793</tt>  <tt class="py-line">    <tt class="py-keyword">return</tt> <tt class="py-name">False</tt> </tt>
</div><a name="L794"></a><tt class="py-lineno">794</tt>  <tt class="py-line"> </tt>
<a name="_move_el_inside_block"></a><div id="_move_el_inside_block-def"><a name="L795"></a><tt class="py-lineno">795</tt> <a class="py-toggle" href="#" id="_move_el_inside_block-toggle" onclick="return toggle('_move_el_inside_block');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#_move_el_inside_block">_move_el_inside_block</a><tt class="py-op">(</tt><tt class="py-param">el</tt><tt class="py-op">,</tt> <tt class="py-param">tag</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="_move_el_inside_block-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="_move_el_inside_block-expanded"><a name="L796"></a><tt class="py-lineno">796</tt>  <tt class="py-line">    <tt class="py-docstring">""" helper for _fixup_ins_del_tags; actually takes the &lt;ins&gt; etc tags</tt> </tt>
<a name="L797"></a><tt class="py-lineno">797</tt>  <tt class="py-line"><tt class="py-docstring">    and moves them inside any block-level tags.  """</tt> </tt>
<a name="L798"></a><tt class="py-lineno">798</tt>  <tt class="py-line">    <tt class="py-keyword">for</tt> <tt class="py-name">child</tt> <tt class="py-keyword">in</tt> <tt class="py-name">el</tt><tt class="py-op">:</tt> </tt>
<a name="L799"></a><tt class="py-lineno">799</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt id="link-303" class="py-name"><a title="lxml.html.diff._contains_block_level_tag" class="py-name" href="#" onclick="return doclink('link-303', '_contains_block_level_tag', 'link-293');">_contains_block_level_tag</a></tt><tt class="py-op">(</tt><tt class="py-name">child</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
<a name="L800"></a><tt class="py-lineno">800</tt>  <tt class="py-line">            <tt class="py-keyword">break</tt> </tt>
<a name="L801"></a><tt class="py-lineno">801</tt>  <tt class="py-line">    <tt class="py-keyword">else</tt><tt class="py-op">:</tt> </tt>
<a name="L802"></a><tt class="py-lineno">802</tt>  <tt class="py-line">        <tt class="py-keyword">import</tt> <tt class="py-name">sys</tt> </tt>
<a name="L803"></a><tt class="py-lineno">803</tt>  <tt class="py-line">        <tt class="py-comment"># No block-level tags in any child</tt> </tt>
<a name="L804"></a><tt class="py-lineno">804</tt>  <tt class="py-line">        <tt class="py-name">children_tag</tt> <tt class="py-op">=</tt> <tt id="link-304" class="py-name"><a title="lxml.etree
lxml.sax.ElementTreeContentHandler.etree
lxml.tests.test_elementtree.CElementTreeTestCase.etree
lxml.tests.test_elementtree._ETreeTestCaseBase.etree
lxml.tests.test_elementtree._XMLPullParserTest.etree
lxml.tests.test_io._IOTestCaseBase.etree" class="py-name" href="#" onclick="return doclink('link-304', 'etree', 'link-1');">etree</a></tt><tt class="py-op">.</tt><tt id="link-305" class="py-name" targets="Function lxml.etree.Element()=lxml.etree-module.html#Element,Function lxml.objectify.Element()=lxml.objectify-module.html#Element,Method lxml.tests.test_pyclasslookup.PyClassLookupTestCase.Element()=lxml.tests.test_pyclasslookup.PyClassLookupTestCase-class.html#Element,Class xml.etree.ElementTree.Element=xml.etree.ElementTree.Element-class.html"><a title="lxml.etree.Element
lxml.objectify.Element
lxml.tests.test_pyclasslookup.PyClassLookupTestCase.Element
xml.etree.ElementTree.Element" class="py-name" href="#" onclick="return doclink('link-305', 'Element', 'link-305');">Element</a></tt><tt class="py-op">(</tt><tt id="link-306" class="py-name"><a title="lxml.etree._Comment.tag
lxml.etree._Element.tag
lxml.etree._Entity.tag
lxml.etree._ProcessingInstruction.tag
lxml.tests.test_xpathevaluator.tag
xml.etree.ElementTree.Element.tag" class="py-name" href="#" onclick="return doclink('link-306', 'tag', 'link-103');">tag</a></tt><tt class="py-op">)</tt> </tt>
<a name="L805"></a><tt class="py-lineno">805</tt>  <tt class="py-line">        <tt class="py-name">children_tag</tt><tt class="py-op">.</tt><tt id="link-307" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-307', 'text', 'link-11');">text</a></tt> <tt class="py-op">=</tt> <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-308" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-308', 'text', 'link-11');">text</a></tt> </tt>
<a name="L806"></a><tt class="py-lineno">806</tt>  <tt class="py-line">        <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-309" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-309', 'text', 'link-11');">text</a></tt> <tt class="py-op">=</tt> <tt class="py-name">None</tt> </tt>
<a name="L807"></a><tt class="py-lineno">807</tt>  <tt class="py-line">        <tt class="py-name">children_tag</tt><tt class="py-op">.</tt><tt id="link-310" class="py-name"><a title="lxml.etree._Element.extend" class="py-name" href="#" onclick="return doclink('link-310', 'extend', 'link-54');">extend</a></tt><tt class="py-op">(</tt><tt class="py-name">list</tt><tt class="py-op">(</tt><tt class="py-name">el</tt><tt class="py-op">)</tt><tt class="py-op">)</tt> </tt>
<a name="L808"></a><tt class="py-lineno">808</tt>  <tt class="py-line">        <tt class="py-name">el</tt><tt class="py-op">[</tt><tt class="py-op">:</tt><tt class="py-op">]</tt> <tt class="py-op">=</tt> <tt class="py-op">[</tt><tt class="py-name">children_tag</tt><tt class="py-op">]</tt> </tt>
<a name="L809"></a><tt class="py-lineno">809</tt>  <tt class="py-line">        <tt class="py-keyword">return</tt> </tt>
<a name="L810"></a><tt class="py-lineno">810</tt>  <tt class="py-line">    <tt class="py-keyword">for</tt> <tt class="py-name">child</tt> <tt class="py-keyword">in</tt> <tt class="py-name">list</tt><tt class="py-op">(</tt><tt class="py-name">el</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
<a name="L811"></a><tt class="py-lineno">811</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt id="link-311" class="py-name"><a title="lxml.html.diff._contains_block_level_tag" class="py-name" href="#" onclick="return doclink('link-311', '_contains_block_level_tag', 'link-293');">_contains_block_level_tag</a></tt><tt class="py-op">(</tt><tt class="py-name">child</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
<a name="L812"></a><tt class="py-lineno">812</tt>  <tt class="py-line">            <tt id="link-312" class="py-name"><a title="lxml.html.diff._move_el_inside_block" class="py-name" href="#" onclick="return doclink('link-312', '_move_el_inside_block', 'link-294');">_move_el_inside_block</a></tt><tt class="py-op">(</tt><tt class="py-name">child</tt><tt class="py-op">,</tt> <tt id="link-313" class="py-name"><a title="lxml.etree._Comment.tag
lxml.etree._Element.tag
lxml.etree._Entity.tag
lxml.etree._ProcessingInstruction.tag
lxml.tests.test_xpathevaluator.tag
xml.etree.ElementTree.Element.tag" class="py-name" href="#" onclick="return doclink('link-313', 'tag', 'link-103');">tag</a></tt><tt class="py-op">)</tt> </tt>
<a name="L813"></a><tt class="py-lineno">813</tt>  <tt class="py-line">            <tt class="py-keyword">if</tt> <tt class="py-name">child</tt><tt class="py-op">.</tt><tt id="link-314" class="py-name"><a title="lxml.etree._Element.tail
xml.etree.ElementTree.Element.tail" class="py-name" href="#" onclick="return doclink('link-314', 'tail', 'link-238');">tail</a></tt><tt class="py-op">:</tt> </tt>
<a name="L814"></a><tt class="py-lineno">814</tt>  <tt class="py-line">                <tt class="py-name">tail_tag</tt> <tt class="py-op">=</tt> <tt id="link-315" class="py-name"><a title="lxml.etree
lxml.sax.ElementTreeContentHandler.etree
lxml.tests.test_elementtree.CElementTreeTestCase.etree
lxml.tests.test_elementtree._ETreeTestCaseBase.etree
lxml.tests.test_elementtree._XMLPullParserTest.etree
lxml.tests.test_io._IOTestCaseBase.etree" class="py-name" href="#" onclick="return doclink('link-315', 'etree', 'link-1');">etree</a></tt><tt class="py-op">.</tt><tt id="link-316" class="py-name"><a title="lxml.etree.Element
lxml.objectify.Element
lxml.tests.test_pyclasslookup.PyClassLookupTestCase.Element
xml.etree.ElementTree.Element" class="py-name" href="#" onclick="return doclink('link-316', 'Element', 'link-305');">Element</a></tt><tt class="py-op">(</tt><tt id="link-317" class="py-name"><a title="lxml.etree._Comment.tag
lxml.etree._Element.tag
lxml.etree._Entity.tag
lxml.etree._ProcessingInstruction.tag
lxml.tests.test_xpathevaluator.tag
xml.etree.ElementTree.Element.tag" class="py-name" href="#" onclick="return doclink('link-317', 'tag', 'link-103');">tag</a></tt><tt class="py-op">)</tt> </tt>
<a name="L815"></a><tt class="py-lineno">815</tt>  <tt class="py-line">                <tt class="py-name">tail_tag</tt><tt class="py-op">.</tt><tt id="link-318" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-318', 'text', 'link-11');">text</a></tt> <tt class="py-op">=</tt> <tt class="py-name">child</tt><tt class="py-op">.</tt><tt id="link-319" class="py-name"><a title="lxml.etree._Element.tail
xml.etree.ElementTree.Element.tail" class="py-name" href="#" onclick="return doclink('link-319', 'tail', 'link-238');">tail</a></tt> </tt>
<a name="L816"></a><tt class="py-lineno">816</tt>  <tt class="py-line">                <tt class="py-name">child</tt><tt class="py-op">.</tt><tt id="link-320" class="py-name"><a title="lxml.etree._Element.tail
xml.etree.ElementTree.Element.tail" class="py-name" href="#" onclick="return doclink('link-320', 'tail', 'link-238');">tail</a></tt> <tt class="py-op">=</tt> <tt class="py-name">None</tt> </tt>
<a name="L817"></a><tt class="py-lineno">817</tt>  <tt class="py-line">                <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-321" class="py-name"><a title="lxml.etree._Element.insert" class="py-name" href="#" onclick="return doclink('link-321', 'insert', 'link-156');">insert</a></tt><tt class="py-op">(</tt><tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-322" class="py-name"><a title="lxml.etree._Element.index" class="py-name" href="#" onclick="return doclink('link-322', 'index', 'link-123');">index</a></tt><tt class="py-op">(</tt><tt class="py-name">child</tt><tt class="py-op">)</tt><tt class="py-op">+</tt><tt class="py-number">1</tt><tt class="py-op">,</tt> <tt class="py-name">tail_tag</tt><tt class="py-op">)</tt> </tt>
<a name="L818"></a><tt class="py-lineno">818</tt>  <tt class="py-line">        <tt class="py-keyword">else</tt><tt class="py-op">:</tt> </tt>
<a name="L819"></a><tt class="py-lineno">819</tt>  <tt class="py-line">            <tt class="py-name">child_tag</tt> <tt class="py-op">=</tt> <tt id="link-323" class="py-name"><a title="lxml.etree
lxml.sax.ElementTreeContentHandler.etree
lxml.tests.test_elementtree.CElementTreeTestCase.etree
lxml.tests.test_elementtree._ETreeTestCaseBase.etree
lxml.tests.test_elementtree._XMLPullParserTest.etree
lxml.tests.test_io._IOTestCaseBase.etree" class="py-name" href="#" onclick="return doclink('link-323', 'etree', 'link-1');">etree</a></tt><tt class="py-op">.</tt><tt id="link-324" class="py-name"><a title="lxml.etree.Element
lxml.objectify.Element
lxml.tests.test_pyclasslookup.PyClassLookupTestCase.Element
xml.etree.ElementTree.Element" class="py-name" href="#" onclick="return doclink('link-324', 'Element', 'link-305');">Element</a></tt><tt class="py-op">(</tt><tt id="link-325" class="py-name"><a title="lxml.etree._Comment.tag
lxml.etree._Element.tag
lxml.etree._Entity.tag
lxml.etree._ProcessingInstruction.tag
lxml.tests.test_xpathevaluator.tag
xml.etree.ElementTree.Element.tag" class="py-name" href="#" onclick="return doclink('link-325', 'tag', 'link-103');">tag</a></tt><tt class="py-op">)</tt> </tt>
<a name="L820"></a><tt class="py-lineno">820</tt>  <tt class="py-line">            <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-326" class="py-name" targets="Method lxml.etree._Element.replace()=lxml.etree._Element-class.html#replace"><a title="lxml.etree._Element.replace" class="py-name" href="#" onclick="return doclink('link-326', 'replace', 'link-326');">replace</a></tt><tt class="py-op">(</tt><tt class="py-name">child</tt><tt class="py-op">,</tt> <tt class="py-name">child_tag</tt><tt class="py-op">)</tt> </tt>
<a name="L821"></a><tt class="py-lineno">821</tt>  <tt class="py-line">            <tt class="py-name">child_tag</tt><tt class="py-op">.</tt><tt id="link-327" class="py-name"><a title="lxml.etree._Element.append" class="py-name" href="#" onclick="return doclink('link-327', 'append', 'link-24');">append</a></tt><tt class="py-op">(</tt><tt class="py-name">child</tt><tt class="py-op">)</tt> </tt>
<a name="L822"></a><tt class="py-lineno">822</tt>  <tt class="py-line">    <tt class="py-keyword">if</tt> <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-328" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-328', 'text', 'link-11');">text</a></tt><tt class="py-op">:</tt> </tt>
<a name="L823"></a><tt class="py-lineno">823</tt>  <tt class="py-line">        <tt class="py-name">text_tag</tt> <tt class="py-op">=</tt> <tt id="link-329" class="py-name"><a title="lxml.etree
lxml.sax.ElementTreeContentHandler.etree
lxml.tests.test_elementtree.CElementTreeTestCase.etree
lxml.tests.test_elementtree._ETreeTestCaseBase.etree
lxml.tests.test_elementtree._XMLPullParserTest.etree
lxml.tests.test_io._IOTestCaseBase.etree" class="py-name" href="#" onclick="return doclink('link-329', 'etree', 'link-1');">etree</a></tt><tt class="py-op">.</tt><tt id="link-330" class="py-name"><a title="lxml.etree.Element
lxml.objectify.Element
lxml.tests.test_pyclasslookup.PyClassLookupTestCase.Element
xml.etree.ElementTree.Element" class="py-name" href="#" onclick="return doclink('link-330', 'Element', 'link-305');">Element</a></tt><tt class="py-op">(</tt><tt id="link-331" class="py-name"><a title="lxml.etree._Comment.tag
lxml.etree._Element.tag
lxml.etree._Entity.tag
lxml.etree._ProcessingInstruction.tag
lxml.tests.test_xpathevaluator.tag
xml.etree.ElementTree.Element.tag" class="py-name" href="#" onclick="return doclink('link-331', 'tag', 'link-103');">tag</a></tt><tt class="py-op">)</tt> </tt>
<a name="L824"></a><tt class="py-lineno">824</tt>  <tt class="py-line">        <tt class="py-name">text_tag</tt><tt class="py-op">.</tt><tt id="link-332" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-332', 'text', 'link-11');">text</a></tt> <tt class="py-op">=</tt> <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-333" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-333', 'text', 'link-11');">text</a></tt> </tt>
<a name="L825"></a><tt class="py-lineno">825</tt>  <tt class="py-line">        <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-334" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-334', 'text', 'link-11');">text</a></tt> <tt class="py-op">=</tt> <tt class="py-name">None</tt> </tt>
<a name="L826"></a><tt class="py-lineno">826</tt>  <tt class="py-line">        <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-335" class="py-name"><a title="lxml.etree._Element.insert" class="py-name" href="#" onclick="return doclink('link-335', 'insert', 'link-156');">insert</a></tt><tt class="py-op">(</tt><tt class="py-number">0</tt><tt class="py-op">,</tt> <tt class="py-name">text_tag</tt><tt class="py-op">)</tt> </tt>
</div><a name="L827"></a><tt class="py-lineno">827</tt>  <tt class="py-line">             </tt>
<a name="_merge_element_contents"></a><div id="_merge_element_contents-def"><a name="L828"></a><tt class="py-lineno">828</tt> <a class="py-toggle" href="#" id="_merge_element_contents-toggle" onclick="return toggle('_merge_element_contents');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff-module.html#_merge_element_contents">_merge_element_contents</a><tt class="py-op">(</tt><tt class="py-param">el</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="_merge_element_contents-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="_merge_element_contents-expanded"><a name="L829"></a><tt class="py-lineno">829</tt>  <tt class="py-line">    <tt class="py-docstring">"""</tt> </tt>
<a name="L830"></a><tt class="py-lineno">830</tt>  <tt class="py-line"><tt class="py-docstring">    Removes an element, but merges its contents into its place, e.g.,</tt> </tt>
<a name="L831"></a><tt class="py-lineno">831</tt>  <tt class="py-line"><tt class="py-docstring">    given &lt;p&gt;Hi &lt;i&gt;there!&lt;/i&gt;&lt;/p&gt;, if you remove the &lt;i&gt; element you get</tt> </tt>
<a name="L832"></a><tt class="py-lineno">832</tt>  <tt class="py-line"><tt class="py-docstring">    &lt;p&gt;Hi there!&lt;/p&gt;</tt> </tt>
<a name="L833"></a><tt class="py-lineno">833</tt>  <tt class="py-line"><tt class="py-docstring">    """</tt> </tt>
<a name="L834"></a><tt class="py-lineno">834</tt>  <tt class="py-line">    <tt class="py-name">parent</tt> <tt class="py-op">=</tt> <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-336" class="py-name" targets="Method lxml.etree._Element.getparent()=lxml.etree._Element-class.html#getparent,Method lxml.etree._ElementStringResult.getparent()=lxml.etree._ElementStringResult-class.html#getparent,Method lxml.etree._ElementUnicodeResult.getparent()=lxml.etree._ElementUnicodeResult-class.html#getparent"><a title="lxml.etree._Element.getparent
lxml.etree._ElementStringResult.getparent
lxml.etree._ElementUnicodeResult.getparent" class="py-name" href="#" onclick="return doclink('link-336', 'getparent', 'link-336');">getparent</a></tt><tt class="py-op">(</tt><tt class="py-op">)</tt> </tt>
<a name="L835"></a><tt class="py-lineno">835</tt>  <tt class="py-line">    <tt id="link-337" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-337', 'text', 'link-11');">text</a></tt> <tt class="py-op">=</tt> <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-338" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-338', 'text', 'link-11');">text</a></tt> <tt class="py-keyword">or</tt> <tt class="py-string">''</tt> </tt>
<a name="L836"></a><tt class="py-lineno">836</tt>  <tt class="py-line">    <tt class="py-keyword">if</tt> <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-339" class="py-name"><a title="lxml.etree._Element.tail
xml.etree.ElementTree.Element.tail" class="py-name" href="#" onclick="return doclink('link-339', 'tail', 'link-238');">tail</a></tt><tt class="py-op">:</tt> </tt>
<a name="L837"></a><tt class="py-lineno">837</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt class="py-keyword">not</tt> <tt class="py-name">len</tt><tt class="py-op">(</tt><tt class="py-name">el</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
<a name="L838"></a><tt class="py-lineno">838</tt>  <tt class="py-line">            <tt id="link-340" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-340', 'text', 'link-11');">text</a></tt> <tt class="py-op">+=</tt> <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-341" class="py-name"><a title="lxml.etree._Element.tail
xml.etree.ElementTree.Element.tail" class="py-name" href="#" onclick="return doclink('link-341', 'tail', 'link-238');">tail</a></tt> </tt>
<a name="L839"></a><tt class="py-lineno">839</tt>  <tt class="py-line">        <tt class="py-keyword">else</tt><tt class="py-op">:</tt> </tt>
<a name="L840"></a><tt class="py-lineno">840</tt>  <tt class="py-line">            <tt class="py-keyword">if</tt> <tt class="py-name">el</tt><tt class="py-op">[</tt><tt class="py-op">-</tt><tt class="py-number">1</tt><tt class="py-op">]</tt><tt class="py-op">.</tt><tt id="link-342" class="py-name"><a title="lxml.etree._Element.tail
xml.etree.ElementTree.Element.tail" class="py-name" href="#" onclick="return doclink('link-342', 'tail', 'link-238');">tail</a></tt><tt class="py-op">:</tt> </tt>
<a name="L841"></a><tt class="py-lineno">841</tt>  <tt class="py-line">                <tt class="py-name">el</tt><tt class="py-op">[</tt><tt class="py-op">-</tt><tt class="py-number">1</tt><tt class="py-op">]</tt><tt class="py-op">.</tt><tt id="link-343" class="py-name"><a title="lxml.etree._Element.tail
xml.etree.ElementTree.Element.tail" class="py-name" href="#" onclick="return doclink('link-343', 'tail', 'link-238');">tail</a></tt> <tt class="py-op">+=</tt> <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-344" class="py-name"><a title="lxml.etree._Element.tail
xml.etree.ElementTree.Element.tail" class="py-name" href="#" onclick="return doclink('link-344', 'tail', 'link-238');">tail</a></tt> </tt>
<a name="L842"></a><tt class="py-lineno">842</tt>  <tt class="py-line">            <tt class="py-keyword">else</tt><tt class="py-op">:</tt> </tt>
<a name="L843"></a><tt class="py-lineno">843</tt>  <tt class="py-line">                <tt class="py-name">el</tt><tt class="py-op">[</tt><tt class="py-op">-</tt><tt class="py-number">1</tt><tt class="py-op">]</tt><tt class="py-op">.</tt><tt id="link-345" class="py-name"><a title="lxml.etree._Element.tail
xml.etree.ElementTree.Element.tail" class="py-name" href="#" onclick="return doclink('link-345', 'tail', 'link-238');">tail</a></tt> <tt class="py-op">=</tt> <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-346" class="py-name"><a title="lxml.etree._Element.tail
xml.etree.ElementTree.Element.tail" class="py-name" href="#" onclick="return doclink('link-346', 'tail', 'link-238');">tail</a></tt> </tt>
<a name="L844"></a><tt class="py-lineno">844</tt>  <tt class="py-line">    <tt id="link-347" class="py-name"><a title="lxml.etree._Element.index" class="py-name" href="#" onclick="return doclink('link-347', 'index', 'link-123');">index</a></tt> <tt class="py-op">=</tt> <tt class="py-name">parent</tt><tt class="py-op">.</tt><tt id="link-348" class="py-name"><a title="lxml.etree._Element.index" class="py-name" href="#" onclick="return doclink('link-348', 'index', 'link-123');">index</a></tt><tt class="py-op">(</tt><tt class="py-name">el</tt><tt class="py-op">)</tt> </tt>
<a name="L845"></a><tt class="py-lineno">845</tt>  <tt class="py-line">    <tt class="py-keyword">if</tt> <tt id="link-349" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-349', 'text', 'link-11');">text</a></tt><tt class="py-op">:</tt> </tt>
<a name="L846"></a><tt class="py-lineno">846</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt id="link-350" class="py-name"><a title="lxml.etree._Element.index" class="py-name" href="#" onclick="return doclink('link-350', 'index', 'link-123');">index</a></tt> <tt class="py-op">==</tt> <tt class="py-number">0</tt><tt class="py-op">:</tt> </tt>
<a name="L847"></a><tt class="py-lineno">847</tt>  <tt class="py-line">            <tt class="py-name">previous</tt> <tt class="py-op">=</tt> <tt class="py-name">None</tt> </tt>
<a name="L848"></a><tt class="py-lineno">848</tt>  <tt class="py-line">        <tt class="py-keyword">else</tt><tt class="py-op">:</tt> </tt>
<a name="L849"></a><tt class="py-lineno">849</tt>  <tt class="py-line">            <tt class="py-name">previous</tt> <tt class="py-op">=</tt> <tt class="py-name">parent</tt><tt class="py-op">[</tt><tt id="link-351" class="py-name"><a title="lxml.etree._Element.index" class="py-name" href="#" onclick="return doclink('link-351', 'index', 'link-123');">index</a></tt><tt class="py-op">-</tt><tt class="py-number">1</tt><tt class="py-op">]</tt> </tt>
<a name="L850"></a><tt class="py-lineno">850</tt>  <tt class="py-line">        <tt class="py-keyword">if</tt> <tt class="py-name">previous</tt> <tt class="py-keyword">is</tt> <tt class="py-name">None</tt><tt class="py-op">:</tt> </tt>
<a name="L851"></a><tt class="py-lineno">851</tt>  <tt class="py-line">            <tt class="py-keyword">if</tt> <tt class="py-name">parent</tt><tt class="py-op">.</tt><tt id="link-352" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-352', 'text', 'link-11');">text</a></tt><tt class="py-op">:</tt> </tt>
<a name="L852"></a><tt class="py-lineno">852</tt>  <tt class="py-line">                <tt class="py-name">parent</tt><tt class="py-op">.</tt><tt id="link-353" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-353', 'text', 'link-11');">text</a></tt> <tt class="py-op">+=</tt> <tt id="link-354" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-354', 'text', 'link-11');">text</a></tt> </tt>
<a name="L853"></a><tt class="py-lineno">853</tt>  <tt class="py-line">            <tt class="py-keyword">else</tt><tt class="py-op">:</tt> </tt>
<a name="L854"></a><tt class="py-lineno">854</tt>  <tt class="py-line">                <tt class="py-name">parent</tt><tt class="py-op">.</tt><tt id="link-355" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-355', 'text', 'link-11');">text</a></tt> <tt class="py-op">=</tt> <tt id="link-356" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-356', 'text', 'link-11');">text</a></tt> </tt>
<a name="L855"></a><tt class="py-lineno">855</tt>  <tt class="py-line">        <tt class="py-keyword">else</tt><tt class="py-op">:</tt> </tt>
<a name="L856"></a><tt class="py-lineno">856</tt>  <tt class="py-line">            <tt class="py-keyword">if</tt> <tt class="py-name">previous</tt><tt class="py-op">.</tt><tt id="link-357" class="py-name"><a title="lxml.etree._Element.tail
xml.etree.ElementTree.Element.tail" class="py-name" href="#" onclick="return doclink('link-357', 'tail', 'link-238');">tail</a></tt><tt class="py-op">:</tt> </tt>
<a name="L857"></a><tt class="py-lineno">857</tt>  <tt class="py-line">                <tt class="py-name">previous</tt><tt class="py-op">.</tt><tt id="link-358" class="py-name"><a title="lxml.etree._Element.tail
xml.etree.ElementTree.Element.tail" class="py-name" href="#" onclick="return doclink('link-358', 'tail', 'link-238');">tail</a></tt> <tt class="py-op">+=</tt> <tt id="link-359" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-359', 'text', 'link-11');">text</a></tt> </tt>
<a name="L858"></a><tt class="py-lineno">858</tt>  <tt class="py-line">            <tt class="py-keyword">else</tt><tt class="py-op">:</tt> </tt>
<a name="L859"></a><tt class="py-lineno">859</tt>  <tt class="py-line">                <tt class="py-name">previous</tt><tt class="py-op">.</tt><tt id="link-360" class="py-name"><a title="lxml.etree._Element.tail
xml.etree.ElementTree.Element.tail" class="py-name" href="#" onclick="return doclink('link-360', 'tail', 'link-238');">tail</a></tt> <tt class="py-op">=</tt> <tt id="link-361" class="py-name"><a title="lxml.etree.QName.text
lxml.etree._Element.text
lxml.etree._Entity.text
lxml.objectify.ObjectifiedElement.text
xml.etree.ElementTree.Element.text" class="py-name" href="#" onclick="return doclink('link-361', 'text', 'link-11');">text</a></tt> </tt>
<a name="L860"></a><tt class="py-lineno">860</tt>  <tt class="py-line">    <tt class="py-name">parent</tt><tt class="py-op">[</tt><tt id="link-362" class="py-name"><a title="lxml.etree._Element.index" class="py-name" href="#" onclick="return doclink('link-362', 'index', 'link-123');">index</a></tt><tt class="py-op">:</tt><tt id="link-363" class="py-name"><a title="lxml.etree._Element.index" class="py-name" href="#" onclick="return doclink('link-363', 'index', 'link-123');">index</a></tt><tt class="py-op">+</tt><tt class="py-number">1</tt><tt class="py-op">]</tt> <tt class="py-op">=</tt> <tt class="py-name">el</tt><tt class="py-op">.</tt><tt id="link-364" class="py-name" targets="Method lxml.etree._Element.getchildren()=lxml.etree._Element-class.html#getchildren,Method lxml.objectify.ObjectifiedElement.getchildren()=lxml.objectify.ObjectifiedElement-class.html#getchildren"><a title="lxml.etree._Element.getchildren
lxml.objectify.ObjectifiedElement.getchildren" class="py-name" href="#" onclick="return doclink('link-364', 'getchildren', 'link-364');">getchildren</a></tt><tt class="py-op">(</tt><tt class="py-op">)</tt> </tt>
</div><a name="L861"></a><tt class="py-lineno">861</tt>  <tt class="py-line"> </tt>
<a name="InsensitiveSequenceMatcher"></a><div id="InsensitiveSequenceMatcher-def"><a name="L862"></a><tt class="py-lineno">862</tt> <a class="py-toggle" href="#" id="InsensitiveSequenceMatcher-toggle" onclick="return toggle('InsensitiveSequenceMatcher');">-</a><tt class="py-line"><tt class="py-keyword">class</tt> <a class="py-def-name" href="lxml.html.diff.InsensitiveSequenceMatcher-class.html">InsensitiveSequenceMatcher</a><tt class="py-op">(</tt><tt class="py-base-class">difflib</tt><tt class="py-op">.</tt><tt class="py-base-class">SequenceMatcher</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="InsensitiveSequenceMatcher-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="InsensitiveSequenceMatcher-expanded"><a name="L863"></a><tt class="py-lineno">863</tt>  <tt class="py-line">    <tt class="py-docstring">"""</tt> </tt>
<a name="L864"></a><tt class="py-lineno">864</tt>  <tt class="py-line"><tt class="py-docstring">    Acts like SequenceMatcher, but tries not to find very small equal</tt> </tt>
<a name="L865"></a><tt class="py-lineno">865</tt>  <tt class="py-line"><tt class="py-docstring">    blocks amidst large spans of changes</tt> </tt>
<a name="L866"></a><tt class="py-lineno">866</tt>  <tt class="py-line"><tt class="py-docstring">    """</tt> </tt>
<a name="L867"></a><tt class="py-lineno">867</tt>  <tt class="py-line"> </tt>
<a name="L868"></a><tt class="py-lineno">868</tt>  <tt class="py-line">    <tt id="link-365" class="py-name" targets="Variable lxml.html.diff.InsensitiveSequenceMatcher.threshold=lxml.html.diff.InsensitiveSequenceMatcher-class.html#threshold"><a title="lxml.html.diff.InsensitiveSequenceMatcher.threshold" class="py-name" href="#" onclick="return doclink('link-365', 'threshold', 'link-365');">threshold</a></tt> <tt class="py-op">=</tt> <tt class="py-number">2</tt> </tt>
<a name="L869"></a><tt class="py-lineno">869</tt>  <tt class="py-line">     </tt>
<a name="InsensitiveSequenceMatcher.get_matching_blocks"></a><div id="InsensitiveSequenceMatcher.get_matching_blocks-def"><a name="L870"></a><tt class="py-lineno">870</tt> <a class="py-toggle" href="#" id="InsensitiveSequenceMatcher.get_matching_blocks-toggle" onclick="return toggle('InsensitiveSequenceMatcher.get_matching_blocks');">-</a><tt class="py-line">    <tt class="py-keyword">def</tt> <a class="py-def-name" href="lxml.html.diff.InsensitiveSequenceMatcher-class.html#get_matching_blocks">get_matching_blocks</a><tt class="py-op">(</tt><tt class="py-param">self</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="InsensitiveSequenceMatcher.get_matching_blocks-collapsed" style="display:none;" pad="+++" indent="++++++++"></div><div id="InsensitiveSequenceMatcher.get_matching_blocks-expanded"><a name="L871"></a><tt class="py-lineno">871</tt>  <tt class="py-line">        <tt class="py-name">size</tt> <tt class="py-op">=</tt> <tt class="py-name">min</tt><tt class="py-op">(</tt><tt class="py-name">len</tt><tt class="py-op">(</tt><tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">b</tt><tt class="py-op">)</tt><tt class="py-op">,</tt> <tt class="py-name">len</tt><tt class="py-op">(</tt><tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">b</tt><tt class="py-op">)</tt><tt class="py-op">)</tt> </tt>
<a name="L872"></a><tt class="py-lineno">872</tt>  <tt class="py-line">        <tt id="link-366" class="py-name"><a title="lxml.html.diff.InsensitiveSequenceMatcher.threshold" class="py-name" href="#" onclick="return doclink('link-366', 'threshold', 'link-365');">threshold</a></tt> <tt class="py-op">=</tt> <tt class="py-name">min</tt><tt class="py-op">(</tt><tt class="py-name">self</tt><tt class="py-op">.</tt><tt id="link-367" class="py-name"><a title="lxml.html.diff.InsensitiveSequenceMatcher.threshold" class="py-name" href="#" onclick="return doclink('link-367', 'threshold', 'link-365');">threshold</a></tt><tt class="py-op">,</tt> <tt class="py-name">size</tt> <tt class="py-op">/</tt> <tt class="py-number">4</tt><tt class="py-op">)</tt> </tt>
<a name="L873"></a><tt class="py-lineno">873</tt>  <tt class="py-line">        <tt class="py-name">actual</tt> <tt class="py-op">=</tt> <tt class="py-name">difflib</tt><tt class="py-op">.</tt><tt class="py-name">SequenceMatcher</tt><tt class="py-op">.</tt><tt id="link-368" class="py-name" targets="Method lxml.html.diff.InsensitiveSequenceMatcher.get_matching_blocks()=lxml.html.diff.InsensitiveSequenceMatcher-class.html#get_matching_blocks"><a title="lxml.html.diff.InsensitiveSequenceMatcher.get_matching_blocks" class="py-name" href="#" onclick="return doclink('link-368', 'get_matching_blocks', 'link-368');">get_matching_blocks</a></tt><tt class="py-op">(</tt><tt class="py-name">self</tt><tt class="py-op">)</tt> </tt>
<a name="L874"></a><tt class="py-lineno">874</tt>  <tt class="py-line">        <tt class="py-keyword">return</tt> <tt class="py-op">[</tt><tt class="py-name">item</tt> <tt class="py-keyword">for</tt> <tt class="py-name">item</tt> <tt class="py-keyword">in</tt> <tt class="py-name">actual</tt> </tt>
<a name="L875"></a><tt class="py-lineno">875</tt>  <tt class="py-line">                <tt class="py-keyword">if</tt> <tt class="py-name">item</tt><tt class="py-op">[</tt><tt class="py-number">2</tt><tt class="py-op">]</tt> <tt class="py-op">&gt;</tt> <tt id="link-369" class="py-name"><a title="lxml.html.diff.InsensitiveSequenceMatcher.threshold" class="py-name" href="#" onclick="return doclink('link-369', 'threshold', 'link-365');">threshold</a></tt> </tt>
<a name="L876"></a><tt class="py-lineno">876</tt>  <tt class="py-line">                <tt class="py-keyword">or</tt> <tt class="py-keyword">not</tt> <tt class="py-name">item</tt><tt class="py-op">[</tt><tt class="py-number">2</tt><tt class="py-op">]</tt><tt class="py-op">]</tt> </tt>
</div></div><a name="L877"></a><tt class="py-lineno">877</tt>  <tt class="py-line"> </tt>
<a name="L878"></a><tt class="py-lineno">878</tt>  <tt class="py-line"><tt class="py-keyword">if</tt> <tt class="py-name">__name__</tt> <tt class="py-op">==</tt> <tt class="py-string">'__main__'</tt><tt class="py-op">:</tt> </tt>
<a name="L879"></a><tt class="py-lineno">879</tt>  <tt class="py-line">    <tt class="py-keyword">from</tt> <tt id="link-370" class="py-name"><a title="lxml" class="py-name" href="#" onclick="return doclink('link-370', 'lxml', 'link-0');">lxml</a></tt><tt class="py-op">.</tt><tt id="link-371" class="py-name"><a title="lxml.html
lxml.html.diff.href_token.html
lxml.html.diff.tag_token.html
lxml.html.diff.token.html" class="py-name" href="#" onclick="return doclink('link-371', 'html', 'link-3');">html</a></tt> <tt class="py-keyword">import</tt> <tt class="py-name">_diffcommand</tt> </tt>
<a name="L880"></a><tt class="py-lineno">880</tt>  <tt class="py-line">    <tt class="py-name">_diffcommand</tt><tt class="py-op">.</tt><tt class="py-name">main</tt><tt class="py-op">(</tt><tt class="py-op">)</tt> </tt>
<a name="L881"></a><tt class="py-lineno">881</tt>  <tt class="py-line"> </tt><script type="text/javascript">
<!--
expandto(location.href);
// -->
</script>
</pre>
<br />
<!-- ==================== NAVIGATION BAR ==================== -->
<table class="navbar" border="0" width="100%" cellpadding="0"
       bgcolor="#a0c0ff" cellspacing="0">
  <tr valign="middle">
  <!-- Home link -->
      <th>&nbsp;&nbsp;&nbsp;<a
        href="lxml-module.html">Home</a>&nbsp;&nbsp;&nbsp;</th>

  <!-- Tree link -->
      <th>&nbsp;&nbsp;&nbsp;<a
        href="module-tree.html">Trees</a>&nbsp;&nbsp;&nbsp;</th>

  <!-- Index link -->
      <th>&nbsp;&nbsp;&nbsp;<a
        href="identifier-index.html">Indices</a>&nbsp;&nbsp;&nbsp;</th>

  <!-- Help link -->
      <th>&nbsp;&nbsp;&nbsp;<a
        href="help.html">Help</a>&nbsp;&nbsp;&nbsp;</th>

  <!-- Project homepage -->
      <th class="navbar" align="right" width="100%">
        <table border="0" cellpadding="0" cellspacing="0">
          <tr><th class="navbar" align="center"
            ><a class="navbar" target="_top" href="/">lxml API</a></th>
          </tr></table></th>
  </tr>
</table>
<table border="0" cellpadding="0" cellspacing="0" width="100%%">
  <tr>
    <td align="left" class="footer">
    Generated by Epydoc 3.0.1
    on Wed Jun 27 16:05:05 2018
    </td>
    <td align="right" class="footer">
      <a target="mainFrame" href="http://epydoc.sourceforge.net"
        >http://epydoc.sourceforge.net</a>
    </td>
  </tr>
</table>

<script type="text/javascript">
  <!--
  // Private objects are initially displayed (because if
  // javascript is turned off then we want them to be
  // visible); but by default, we want to hide them.  So hide
  // them unless we have a cookie that says to show them.
  checkCookie();
  // -->
</script>
</body>
</html>