<?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> <a
href="lxml-module.html">Home</a> </th>
<!-- Tree link -->
<th> <a
href="module-tree.html">Trees</a> </th>
<!-- Index link -->
<th> <a
href="identifier-index.html">Indices</a> </th>
<!-- Help link -->
<th> <a
href="help.html">Help</a> </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 lxml</a> ::
<a href="lxml.html-module.html">Package html</a> ::
Module 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 private</a>]</span></td></tr>
<tr><td align="right"><span class="options"
>[<a href="frames.html" target="_top">frames</a
>] | <a href="lxml.html.diff-module.html"
target="_top">no frames</a>]</span></td></tr>
</table>
</td>
</tr>
</table>
<!-- ==================== MODULE DESCRIPTION ==================== -->
<h1 class="epydoc">Module diff</h1><p class="nomargin-top"><span class="codelink"><a href="lxml.html.diff-pysrc.html">source code</a></span></p>
<!-- ==================== CLASSES ==================== -->
<a name="section-Classes"></a>
<table class="summary" border="1" cellpadding="3"
cellspacing="0" width="100%" bgcolor="white">
<tr bgcolor="#70b0f0" class="table-header">
<td colspan="2" class="table-header">
<table border="0" cellpadding="0" cellspacing="0" width="100%">
<tr valign="top">
<td align="left"><span class="table-header">Classes</span></td>
<td align="right" valign="top"
><span class="options">[<a href="#section-Classes"
class="privatelink" onclick="toggle_private();"
>hide private</a>]</span></td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<a href="str-class.html" class="summary-name" onclick="show_private();">basestring</a><br />
str(object='') -> string
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<a href="lxml.html.diff.DEL_START-class.html" class="summary-name" onclick="show_private();">DEL_START</a>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<a href="lxml.html.diff.DEL_END-class.html" class="summary-name" onclick="show_private();">DEL_END</a>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<a href="lxml.html.diff.NoDeletes-class.html" class="summary-name" onclick="show_private();">NoDeletes</a><br />
Raised when the document no longer contains any pending deletes
(DEL_START/DEL_END)
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<a href="lxml.html.diff.token-class.html" class="summary-name" onclick="show_private();">token</a><br />
Represents a diffable token, generally a word that is displayed to
the user. Opening tags are attached to this token when they are
adjacent (pre_tags) and closing tags that follow the word
(post_tags). Some exceptions occur when there are empty tags
adjacent to a word, so there may be close tags in pre_tags, or
open tags in post_tags.
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<a href="lxml.html.diff.tag_token-class.html" class="summary-name" onclick="show_private();">tag_token</a><br />
Represents a token that is actually a tag. Currently this is just
the <img> tag, which takes up visible space just like a word but
is only represented in a document by a tag.
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<a href="lxml.html.diff.href_token-class.html" class="summary-name" onclick="show_private();">href_token</a><br />
Represents the href in an anchor tag. Unlike other words, we only
show the href when it changes.
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<a href="lxml.html.diff.InsensitiveSequenceMatcher-class.html" class="summary-name" onclick="show_private();">InsensitiveSequenceMatcher</a><br />
Acts like SequenceMatcher, but tries not to find very small equal
blocks amidst large spans of changes
</td>
</tr>
</table>
<!-- ==================== FUNCTIONS ==================== -->
<a name="section-Functions"></a>
<table class="summary" border="1" cellpadding="3"
cellspacing="0" width="100%" bgcolor="white">
<tr bgcolor="#70b0f0" class="table-header">
<td colspan="2" class="table-header">
<table border="0" cellpadding="0" cellspacing="0" width="100%">
<tr valign="top">
<td align="left"><span class="table-header">Functions</span></td>
<td align="right" valign="top"
><span class="options">[<a href="#section-Functions"
class="privatelink" onclick="toggle_private();"
>hide private</a>]</span></td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a name="default_markup"></a><span class="summary-sig-name">default_markup</span>(<span class="summary-sig-arg">text</span>,
<span class="summary-sig-arg">version</span>)</span></td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#default_markup">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr>
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a href="lxml.html.diff-module.html#html_annotate" class="summary-sig-name">html_annotate</a>(<span class="summary-sig-arg">doclist</span>,
<span class="summary-sig-arg">markup</span>=<span class="summary-sig-default">default_markup</span>)</span><br />
doclist should be ordered from oldest to newest, like:</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#html_annotate">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a name="tokenize_annotated"></a><span class="summary-sig-name">tokenize_annotated</span>(<span class="summary-sig-arg">doc</span>,
<span class="summary-sig-arg">annotation</span>)</span><br />
Tokenize a document and add an annotation attribute to each token</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#tokenize_annotated">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a name="html_annotate_merge_annotations"></a><span class="summary-sig-name">html_annotate_merge_annotations</span>(<span class="summary-sig-arg">tokens_old</span>,
<span class="summary-sig-arg">tokens_new</span>)</span><br />
Merge the annotations from tokens_old into tokens_new, when the
tokens in the new document already existed in the old document.</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#html_annotate_merge_annotations">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a name="copy_annotations"></a><span class="summary-sig-name">copy_annotations</span>(<span class="summary-sig-arg">src</span>,
<span class="summary-sig-arg">dest</span>)</span><br />
Copy annotations from the tokens listed in src to the tokens in dest</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#copy_annotations">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a name="compress_tokens"></a><span class="summary-sig-name">compress_tokens</span>(<span class="summary-sig-arg">tokens</span>)</span><br />
Combine adjacent tokens when there is no HTML between the tokens,
and they share an annotation</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#compress_tokens">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a name="compress_merge_back"></a><span class="summary-sig-name">compress_merge_back</span>(<span class="summary-sig-arg">tokens</span>,
<span class="summary-sig-arg">tok</span>)</span><br />
Merge tok into the last element of tokens (modifying the list of
tokens in-place).</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#compress_merge_back">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a name="markup_serialize_tokens"></a><span class="summary-sig-name">markup_serialize_tokens</span>(<span class="summary-sig-arg">tokens</span>,
<span class="summary-sig-arg">markup_func</span>)</span><br />
Serialize the list of tokens into a list of text chunks, calling
markup_func around text to add annotations.</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#markup_serialize_tokens">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr>
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a href="lxml.html.diff-module.html#htmldiff" class="summary-sig-name">htmldiff</a>(<span class="summary-sig-arg">old_html</span>,
<span class="summary-sig-arg">new_html</span>)</span><br />
Do a diff of the old and new document. The documents are HTML
<em>fragments</em> (str/UTF8 or unicode), they are not complete documents
(i.e., no <html> tag).</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#htmldiff">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a name="htmldiff_tokens"></a><span class="summary-sig-name">htmldiff_tokens</span>(<span class="summary-sig-arg">html1_tokens</span>,
<span class="summary-sig-arg">html2_tokens</span>)</span><br />
Does a diff on the tokens themselves, returning a list of text
chunks (not tokens).</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#htmldiff_tokens">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a name="expand_tokens"></a><span class="summary-sig-name">expand_tokens</span>(<span class="summary-sig-arg">tokens</span>,
<span class="summary-sig-arg">equal</span>=<span class="summary-sig-default">False</span>)</span><br />
Given a list of tokens, return a generator of the chunks of
text for the data in the tokens.</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#expand_tokens">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a name="merge_insert"></a><span class="summary-sig-name">merge_insert</span>(<span class="summary-sig-arg">ins_chunks</span>,
<span class="summary-sig-arg">doc</span>)</span><br />
doc is the already-handled document (as a list of text chunks);
here we add <ins>ins_chunks</ins> to the end of that.</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#merge_insert">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a name="merge_delete"></a><span class="summary-sig-name">merge_delete</span>(<span class="summary-sig-arg">del_chunks</span>,
<span class="summary-sig-arg">doc</span>)</span><br />
Adds the text chunks in del_chunks to the document doc (another
list of text chunks) with marker to show it is a delete.
cleanup_delete later resolves these markers into <del> tags.</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#merge_delete">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a href="lxml.html.diff-module.html#cleanup_delete" class="summary-sig-name" onclick="show_private();">cleanup_delete</a>(<span class="summary-sig-arg">chunks</span>)</span><br />
Cleans up any DEL_START/DEL_END markers in the document, replacing
them with <del></del>. To do this while keeping the document
valid, it may need to drop some tags (either start or end tags).</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#cleanup_delete">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a href="lxml.html.diff-module.html#split_unbalanced" class="summary-sig-name" onclick="show_private();">split_unbalanced</a>(<span class="summary-sig-arg">chunks</span>)</span><br />
Return (unbalanced_start, balanced, unbalanced_end), where each is
a list of text and tag chunks.</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#split_unbalanced">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a name="split_delete"></a><span class="summary-sig-name">split_delete</span>(<span class="summary-sig-arg">chunks</span>)</span><br />
Returns (stuff_before_DEL_START, stuff_inside_DEL_START_END,
stuff_after_DEL_END). Returns the first case found (there may be
more DEL_STARTs in stuff_after_DEL_END). Raises NoDeletes if
there's no DEL_START found.</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#split_delete">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a href="lxml.html.diff-module.html#locate_unbalanced_start" class="summary-sig-name" onclick="show_private();">locate_unbalanced_start</a>(<span class="summary-sig-arg">unbalanced_start</span>,
<span class="summary-sig-arg">pre_delete</span>,
<span class="summary-sig-arg">post_delete</span>)</span><br />
pre_delete and post_delete implicitly point to a place in the
document (where the two were split). This moves that point (by
popping items from one and pushing them onto the other). It moves
the point to try to find a place where unbalanced_start applies.</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#locate_unbalanced_start">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a name="locate_unbalanced_end"></a><span class="summary-sig-name">locate_unbalanced_end</span>(<span class="summary-sig-arg">unbalanced_end</span>,
<span class="summary-sig-arg">pre_delete</span>,
<span class="summary-sig-arg">post_delete</span>)</span><br />
like locate_unbalanced_start, except handling end tags and
possibly moving the point earlier in the document.</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#locate_unbalanced_end">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a href="lxml.html.diff-module.html#tokenize" class="summary-sig-name" onclick="show_private();">tokenize</a>(<span class="summary-sig-arg">html</span>,
<span class="summary-sig-arg">include_hrefs</span>=<span class="summary-sig-default">True</span>)</span><br />
Parse the given HTML and returns token objects (words with attached tags).</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#tokenize">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a href="lxml.html.diff-module.html#parse_html" class="summary-sig-name" onclick="show_private();">parse_html</a>(<span class="summary-sig-arg">html</span>,
<span class="summary-sig-arg">cleanup</span>=<span class="summary-sig-default">True</span>)</span><br />
Parses an HTML fragment, returning an lxml element. Note that the HTML will be
wrapped in a <div> tag that was not in the original document.</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#parse_html">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a name="cleanup_html"></a><span class="summary-sig-name">cleanup_html</span>(<span class="summary-sig-arg">html</span>)</span><br />
This 'cleans' the HTML, meaning that any page structure is removed
(only the contents of <body> are used, if there is any <body).
Also <ins> and <del> tags are removed.</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#cleanup_html">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a href="lxml.html.diff-module.html#split_trailing_whitespace" class="summary-sig-name" onclick="show_private();">split_trailing_whitespace</a>(<span class="summary-sig-arg">word</span>)</span><br />
This function takes a word, such as 'test</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#split_trailing_whitespace">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a name="fixup_chunks"></a><span class="summary-sig-name">fixup_chunks</span>(<span class="summary-sig-arg">chunks</span>)</span><br />
This function takes a list of chunks and produces a list of tokens.</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#fixup_chunks">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a href="lxml.html.diff-module.html#flatten_el" class="summary-sig-name" onclick="show_private();">flatten_el</a>(<span class="summary-sig-arg">el</span>,
<span class="summary-sig-arg">include_hrefs</span>,
<span class="summary-sig-arg">skip_tag</span>=<span class="summary-sig-default">False</span>)</span><br />
Takes an lxml element el, and generates all the text chunks for
that tag. Each start tag is a chunk, each word is a chunk, and each
end tag is a chunk.</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#flatten_el">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a name="split_words"></a><span class="summary-sig-name">split_words</span>(<span class="summary-sig-arg">text</span>)</span><br />
Splits some text into words. Includes trailing whitespace
on each word when appropriate.</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#split_words">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a name="start_tag"></a><span class="summary-sig-name">start_tag</span>(<span class="summary-sig-arg">el</span>)</span><br />
The text representation of the start tag for a tag.</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#start_tag">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a name="end_tag"></a><span class="summary-sig-name">end_tag</span>(<span class="summary-sig-arg">el</span>)</span><br />
The text representation of an end tag for a tag. Includes
trailing whitespace when appropriate.</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#end_tag">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a name="is_word"></a><span class="summary-sig-name">is_word</span>(<span class="summary-sig-arg">tok</span>)</span></td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#is_word">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a name="is_end_tag"></a><span class="summary-sig-name">is_end_tag</span>(<span class="summary-sig-arg">tok</span>)</span></td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#is_end_tag">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a name="is_start_tag"></a><span class="summary-sig-name">is_start_tag</span>(<span class="summary-sig-arg">tok</span>)</span></td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#is_start_tag">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a name="fixup_ins_del_tags"></a><span class="summary-sig-name">fixup_ins_del_tags</span>(<span class="summary-sig-arg">html</span>)</span><br />
Given an html string, move any <ins> or <del> tags inside of any
block-level elements, e.g. transform <ins><p>word</p></ins> to
<p><ins>word</ins></p></td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#fixup_ins_del_tags">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a href="lxml.html.diff-module.html#serialize_html_fragment" class="summary-sig-name" onclick="show_private();">serialize_html_fragment</a>(<span class="summary-sig-arg">el</span>,
<span class="summary-sig-arg">skip_outer</span>=<span class="summary-sig-default">False</span>)</span><br />
Serialize a single lxml element as HTML. The serialized form
includes the elements tail.</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#serialize_html_fragment">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a name="_fixup_ins_del_tags"></a><span class="summary-sig-name">_fixup_ins_del_tags</span>(<span class="summary-sig-arg">doc</span>)</span><br />
fixup_ins_del_tags that works on an lxml document in-place</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#_fixup_ins_del_tags">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a name="_contains_block_level_tag"></a><span class="summary-sig-name">_contains_block_level_tag</span>(<span class="summary-sig-arg">el</span>)</span><br />
True if the element contains any block-level elements, like <p>, <td>, etc.</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#_contains_block_level_tag">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a name="_move_el_inside_block"></a><span class="summary-sig-name">_move_el_inside_block</span>(<span class="summary-sig-arg">el</span>,
<span class="summary-sig-arg">tag</span>)</span><br />
helper for _fixup_ins_del_tags; actually takes the <ins> etc tags
and moves them inside any block-level tags.</td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#_move_el_inside_block">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr>
<td><span class="summary-sig"><a name="_merge_element_contents"></a><span class="summary-sig-name">_merge_element_contents</span>(<span class="summary-sig-arg">el</span>)</span><br />
Removes an element, but merges its contents into its place, e.g.,
given <p>Hi <i>there!</i></p>, if you remove the <i> element you get
<p>Hi there!</p></td>
<td align="right" valign="top">
<span class="codelink"><a href="lxml.html.diff-pysrc.html#_merge_element_contents">source code</a></span>
</td>
</tr>
</table>
</td>
</tr>
</table>
<!-- ==================== VARIABLES ==================== -->
<a name="section-Variables"></a>
<table class="summary" border="1" cellpadding="3"
cellspacing="0" width="100%" bgcolor="white">
<tr bgcolor="#70b0f0" class="table-header">
<td colspan="2" class="table-header">
<table border="0" cellpadding="0" cellspacing="0" width="100%">
<tr valign="top">
<td align="left"><span class="table-header">Variables</span></td>
<td align="right" valign="top"
><span class="options">[<a href="#section-Variables"
class="privatelink" onclick="toggle_private();"
>hide private</a>]</span></td>
</tr>
</table>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<a name="_body_re"></a><span class="summary-name">_body_re</span> = <code title="re.compile(r'(?is)<body.*?>')">re.compile(r'<code class="re-flags">(?is)</code><body.<code class="re-op">*?</code>>')</code>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<a name="_end_body_re"></a><span class="summary-name">_end_body_re</span> = <code title="re.compile(r'(?is)</body.*?>')">re.compile(r'<code class="re-flags">(?is)</code></body.<code class="re-op">*?</code>>')</code>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<a name="_ins_del_re"></a><span class="summary-name">_ins_del_re</span> = <code title="re.compile(r'(?is)</?(ins|del).*?>')">re.compile(r'<code class="re-flags">(?is)</code></<code class="re-op">?</code><code class="re-group">(</code>ins<code class="re-op">|</code>del<code class="re-group">)</code>.<code class="re-op">*?</code>>')</code>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<a name="end_whitespace_re"></a><span class="summary-name">end_whitespace_re</span> = <code title="re.compile(r'[ \t\n\r]$')">re.compile(r'<code class="re-group">[</code> \t\n\r<code class="re-group">]</code>$')</code>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<a href="lxml.html.diff-module.html#empty_tags" class="summary-name" onclick="show_private();">empty_tags</a> = <code title="('param',
'img',
'area',
'br',
'basefont',
'input',
'base',
'meta',
..."><code class="variable-group">(</code><code class="variable-quote">'</code><code class="variable-string">param</code><code class="variable-quote">'</code><code class="variable-op">, </code><code class="variable-quote">'</code><code class="variable-string">img</code><code class="variable-quote">'</code><code class="variable-op">, </code><code class="variable-quote">'</code><code class="variable-string">area</code><code class="variable-quote">'</code><code class="variable-op">, </code><code class="variable-quote">'</code><code class="variable-string">br</code><code class="variable-quote">'</code><code class="variable-op">, </code><code class="variable-quote">'</code><code class="variable-string">basefont</code><code class="variable-quote">'</code><code class="variable-op">, </code><code class="variable-quote">'</code><code class="variable-string">input</code><code class="variable-ellipsis">...</code></code>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<a href="lxml.html.diff-module.html#block_level_tags" class="summary-name" onclick="show_private();">block_level_tags</a> = <code title="('address',
'blockquote',
'center',
'dir',
'div',
'dl',
'fieldset',
'form',
..."><code class="variable-group">(</code><code class="variable-quote">'</code><code class="variable-string">address</code><code class="variable-quote">'</code><code class="variable-op">, </code><code class="variable-quote">'</code><code class="variable-string">blockquote</code><code class="variable-quote">'</code><code class="variable-op">, </code><code class="variable-quote">'</code><code class="variable-string">center</code><code class="variable-quote">'</code><code class="variable-op">, </code><code class="variable-quote">'</code><code class="variable-string">dir</code><code class="variable-quote">'</code><code class="variable-op">, </code><code class="variable-ellipsis">...</code></code>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<a href="lxml.html.diff-module.html#block_level_container_tags" class="summary-name" onclick="show_private();">block_level_container_tags</a> = <code title="('dd',
'dt',
'frameset',
'li',
'tbody',
'td',
'tfoot',
'th',
..."><code class="variable-group">(</code><code class="variable-quote">'</code><code class="variable-string">dd</code><code class="variable-quote">'</code><code class="variable-op">, </code><code class="variable-quote">'</code><code class="variable-string">dt</code><code class="variable-quote">'</code><code class="variable-op">, </code><code class="variable-quote">'</code><code class="variable-string">frameset</code><code class="variable-quote">'</code><code class="variable-op">, </code><code class="variable-quote">'</code><code class="variable-string">li</code><code class="variable-quote">'</code><code class="variable-op">, </code><code class="variable-quote">'</code><code class="variable-string">t</code><code class="variable-ellipsis">...</code></code>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<a name="split_words_re"></a><span class="summary-name">split_words_re</span> = <code title="re.compile(r'(?u)\S+(?:\s+|$)')">re.compile(r'<code class="re-flags">(?u)</code>\S<code class="re-op">+</code><code class="re-group">(?:</code>\s<code class="re-op">+</code><code class="re-op">|</code>$<code class="re-group">)</code>')</code>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<a name="start_whitespace_re"></a><span class="summary-name">start_whitespace_re</span> = <code title="re.compile(r'^[ \t\n\r]')">re.compile(r'^<code class="re-group">[</code> \t\n\r<code class="re-group">]</code>')</code>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<a name="__package__"></a><span class="summary-name">__package__</span> = <code title="'lxml.html'"><code class="variable-quote">'</code><code class="variable-string">lxml.html</code><code class="variable-quote">'</code></code>
</td>
</tr>
<tr class="private">
<td width="15%" align="right" valign="top" class="summary">
<span class="summary-type"> </span>
</td><td class="summary">
<a href="lxml.html.diff-module.html#__test__" class="summary-name" onclick="show_private();">__test__</a> = <code title="{u'html_annotate (line 31)': u'''
doclist should be ordered from oldest to newest, like::
>>> version1 = 'Hello World'
>>> version2 = 'Goodbye World'
>>> print(html_annotate([(version1, 'version 1'),
... (version2, 'version 2')]))
<span title="version 2">Goodbye</span> <span title="version 1"\
..."><code class="variable-group">{</code><code class="variable-quote">u'</code><code class="variable-string">html_annotate (line 31)</code><code class="variable-quote">'</code><code class="variable-op">:</code><code class="variable-ellipsis">...</code></code>
</td>
</tr>
</table>
<!-- ==================== FUNCTION DETAILS ==================== -->
<a name="section-FunctionDetails"></a>
<table class="details" border="1" cellpadding="3"
cellspacing="0" width="100%" bgcolor="white">
<tr bgcolor="#70b0f0" class="table-header">
<td colspan="2" class="table-header">
<table border="0" cellpadding="0" cellspacing="0" width="100%">
<tr valign="top">
<td align="left"><span class="table-header">Function Details</span></td>
<td align="right" valign="top"
><span class="options">[<a href="#section-FunctionDetails"
class="privatelink" onclick="toggle_private();"
>hide private</a>]</span></td>
</tr>
</table>
</td>
</tr>
</table>
<a name="html_annotate"></a>
<div>
<table class="details" border="1" cellpadding="3"
cellspacing="0" width="100%" bgcolor="white">
<tr><td>
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr valign="top"><td>
<h3 class="epydoc"><span class="sig"><span class="sig-name">html_annotate</span>(<span class="sig-arg">doclist</span>,
<span class="sig-arg">markup</span>=<span class="sig-default">default_markup</span>)</span>
</h3>
</td><td align="right" valign="top"
><span class="codelink"><a href="lxml.html.diff-pysrc.html#html_annotate">source code</a></span>
</td>
</tr></table>
<p>doclist should be ordered from oldest to newest, like:</p>
<pre class="rst-literal-block">
>>> version1 = 'Hello World'
>>> version2 = 'Goodbye World'
>>> print(html_annotate([(version1, 'version 1'),
... (version2, 'version 2')]))
<span title="version 2">Goodbye</span> <span title="version 1">World</span>
</pre>
<p>The documents must be <em>fragments</em> (str/UTF8 or unicode), not
complete documents</p>
<p>The markup argument is a function to markup the spans of words.
This function is called like markup('Hello', 'version 2'), and
returns HTML. The first argument is text and never includes any
markup. The default uses a span with a title:</p>
<blockquote>
<pre class="py-doctest">
<span class="py-prompt">>>> </span><span class="py-keyword">print</span>(default_markup(<span class="py-string">'Some Text'</span>, <span class="py-string">'by Joe'</span>))
<span class="py-output"><span title="by Joe">Some Text</span></span></pre>
</blockquote>
<dl class="fields">
</dl>
</td></tr></table>
</div>
<a name="htmldiff"></a>
<div>
<table class="details" border="1" cellpadding="3"
cellspacing="0" width="100%" bgcolor="white">
<tr><td>
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr valign="top"><td>
<h3 class="epydoc"><span class="sig"><span class="sig-name">htmldiff</span>(<span class="sig-arg">old_html</span>,
<span class="sig-arg">new_html</span>)</span>
</h3>
</td><td align="right" valign="top"
><span class="codelink"><a href="lxml.html.diff-pysrc.html#htmldiff">source code</a></span>
</td>
</tr></table>
<p>Do a diff of the old and new document. The documents are HTML
<em>fragments</em> (str/UTF8 or unicode), they are not complete documents
(i.e., no <html> tag).</p>
<p>Returns HTML with <ins> and <del> tags added around the
appropriate text.</p>
<p>Markup is generally ignored, with the markup from new_html
preserved, and possibly some markup from old_html (though it is
considered acceptable to lose some of the old markup). Only the
words in the HTML are diffed. The exception is <img> tags, which
are treated like words, and the href attribute of <a> tags, which
are noted inside the tag itself when there are changes.</p>
<dl class="fields">
</dl>
</td></tr></table>
</div>
<a name="cleanup_delete"></a>
<div class="private">
<table class="details" border="1" cellpadding="3"
cellspacing="0" width="100%" bgcolor="white">
<tr><td>
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr valign="top"><td>
<h3 class="epydoc"><span class="sig"><span class="sig-name">cleanup_delete</span>(<span class="sig-arg">chunks</span>)</span>
</h3>
</td><td align="right" valign="top"
><span class="codelink"><a href="lxml.html.diff-pysrc.html#cleanup_delete">source code</a></span>
</td>
</tr></table>
<p>Cleans up any DEL_START/DEL_END markers in the document, replacing
them with <del></del>. To do this while keeping the document
valid, it may need to drop some tags (either start or end tags).</p>
<p>It may also move the del into adjacent tags to try to move it to a
similar location where it was originally located (e.g., moving a
delete into preceding <div> tag, if the del looks like (DEL_START,
'Text</div>', DEL_END)</p>
<dl class="fields">
</dl>
</td></tr></table>
</div>
<a name="split_unbalanced"></a>
<div class="private">
<table class="details" border="1" cellpadding="3"
cellspacing="0" width="100%" bgcolor="white">
<tr><td>
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr valign="top"><td>
<h3 class="epydoc"><span class="sig"><span class="sig-name">split_unbalanced</span>(<span class="sig-arg">chunks</span>)</span>
</h3>
</td><td align="right" valign="top"
><span class="codelink"><a href="lxml.html.diff-pysrc.html#split_unbalanced">source code</a></span>
</td>
</tr></table>
<p>Return (unbalanced_start, balanced, unbalanced_end), where each is
a list of text and tag chunks.</p>
<p>unbalanced_start is a list of all the tags that are opened, but
not closed in this span. Similarly, unbalanced_end is a list of
tags that are closed but were not opened. Extracting these might
mean some reordering of the chunks.</p>
<dl class="fields">
</dl>
</td></tr></table>
</div>
<a name="locate_unbalanced_start"></a>
<div class="private">
<table class="details" border="1" cellpadding="3"
cellspacing="0" width="100%" bgcolor="white">
<tr><td>
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr valign="top"><td>
<h3 class="epydoc"><span class="sig"><span class="sig-name">locate_unbalanced_start</span>(<span class="sig-arg">unbalanced_start</span>,
<span class="sig-arg">pre_delete</span>,
<span class="sig-arg">post_delete</span>)</span>
</h3>
</td><td align="right" valign="top"
><span class="codelink"><a href="lxml.html.diff-pysrc.html#locate_unbalanced_start">source code</a></span>
</td>
</tr></table>
<p>pre_delete and post_delete implicitly point to a place in the
document (where the two were split). This moves that point (by
popping items from one and pushing them onto the other). It moves
the point to try to find a place where unbalanced_start applies.</p>
<p>As an example:</p>
<pre class="rst-literal-block">
>>> unbalanced_start = ['<div>']
>>> doc = ['<p>', 'Text', '</p>', '<div>', 'More Text', '</div>']
>>> pre, post = doc[:3], doc[3:]
>>> pre, post
(['<p>', 'Text', '</p>'], ['<div>', 'More Text', '</div>'])
>>> locate_unbalanced_start(unbalanced_start, pre, post)
>>> pre, post
(['<p>', 'Text', '</p>', '<div>'], ['More Text', '</div>'])
</pre>
<p>As you can see, we moved the point so that the dangling <div> that
we found will be effectively replaced by the div in the original
document. If this doesn't work out, we just throw away
unbalanced_start without doing anything.</p>
<dl class="fields">
</dl>
</td></tr></table>
</div>
<a name="tokenize"></a>
<div class="private">
<table class="details" border="1" cellpadding="3"
cellspacing="0" width="100%" bgcolor="white">
<tr><td>
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr valign="top"><td>
<h3 class="epydoc"><span class="sig"><span class="sig-name">tokenize</span>(<span class="sig-arg">html</span>,
<span class="sig-arg">include_hrefs</span>=<span class="sig-default">True</span>)</span>
</h3>
</td><td align="right" valign="top"
><span class="codelink"><a href="lxml.html.diff-pysrc.html#tokenize">source code</a></span>
</td>
</tr></table>
<p>Parse the given HTML and returns token objects (words with attached tags).</p>
<p>This parses only the content of a page; anything in the head is
ignored, and the <head> and <body> elements are themselves
optional. The content is then parsed by lxml, which ensures the
validity of the resulting parsed document (though lxml may make
incorrect guesses when the markup is particular bad).</p>
<p><ins> and <del> tags are also eliminated from the document, as
that gets confusing.</p>
<p>If include_hrefs is true, then the href attribute of <a> tags is
included as a special kind of diffable token.</p>
<dl class="fields">
</dl>
</td></tr></table>
</div>
<a name="parse_html"></a>
<div class="private">
<table class="details" border="1" cellpadding="3"
cellspacing="0" width="100%" bgcolor="white">
<tr><td>
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr valign="top"><td>
<h3 class="epydoc"><span class="sig"><span class="sig-name">parse_html</span>(<span class="sig-arg">html</span>,
<span class="sig-arg">cleanup</span>=<span class="sig-default">True</span>)</span>
</h3>
</td><td align="right" valign="top"
><span class="codelink"><a href="lxml.html.diff-pysrc.html#parse_html">source code</a></span>
</td>
</tr></table>
<p>Parses an HTML fragment, returning an lxml element. Note that the HTML will be
wrapped in a <div> tag that was not in the original document.</p>
<p>If cleanup is true, make sure there's no <head> or <body>, and get
rid of any <ins> and <del> tags.</p>
<dl class="fields">
</dl>
</td></tr></table>
</div>
<a name="split_trailing_whitespace"></a>
<div class="private">
<table class="details" border="1" cellpadding="3"
cellspacing="0" width="100%" bgcolor="white">
<tr><td>
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr valign="top"><td>
<h3 class="epydoc"><span class="sig"><span class="sig-name">split_trailing_whitespace</span>(<span class="sig-arg">word</span>)</span>
</h3>
</td><td align="right" valign="top"
><span class="codelink"><a href="lxml.html.diff-pysrc.html#split_trailing_whitespace">source code</a></span>
</td>
</tr></table>
<blockquote>
This function takes a word, such as 'test</blockquote>
<p>' and returns ('test','</p>
<p>')</p>
<dl class="fields">
</dl>
</td></tr></table>
</div>
<a name="flatten_el"></a>
<div class="private">
<table class="details" border="1" cellpadding="3"
cellspacing="0" width="100%" bgcolor="white">
<tr><td>
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr valign="top"><td>
<h3 class="epydoc"><span class="sig"><span class="sig-name">flatten_el</span>(<span class="sig-arg">el</span>,
<span class="sig-arg">include_hrefs</span>,
<span class="sig-arg">skip_tag</span>=<span class="sig-default">False</span>)</span>
</h3>
</td><td align="right" valign="top"
><span class="codelink"><a href="lxml.html.diff-pysrc.html#flatten_el">source code</a></span>
</td>
</tr></table>
<p>Takes an lxml element el, and generates all the text chunks for
that tag. Each start tag is a chunk, each word is a chunk, and each
end tag is a chunk.</p>
<p>If skip_tag is true, then the outermost container tag is
not returned (just its contents).</p>
<dl class="fields">
</dl>
</td></tr></table>
</div>
<a name="serialize_html_fragment"></a>
<div class="private">
<table class="details" border="1" cellpadding="3"
cellspacing="0" width="100%" bgcolor="white">
<tr><td>
<table width="100%" cellpadding="0" cellspacing="0" border="0">
<tr valign="top"><td>
<h3 class="epydoc"><span class="sig"><span class="sig-name">serialize_html_fragment</span>(<span class="sig-arg">el</span>,
<span class="sig-arg">skip_outer</span>=<span class="sig-default">False</span>)</span>
</h3>
</td><td align="right" valign="top"
><span class="codelink"><a href="lxml.html.diff-pysrc.html#serialize_html_fragment">source code</a></span>
</td>
</tr></table>
<p>Serialize a single lxml element as HTML. The serialized form
includes the elements tail.</p>
<p>If skip_outer is true, then don't serialize the outermost tag</p>
<dl class="fields">
</dl>
</td></tr></table>
</div>
<br />
<!-- ==================== VARIABLES DETAILS ==================== -->
<a name="section-VariablesDetails"></a>
<table class="details" border="1" cellpadding="3"
cellspacing="0" width="100%" bgcolor="white">
<tr bgcolor="#70b0f0" class="table-header">
<td colspan="2" class="table-header">
<table border="0" cellpadding="0" cellspacing="0" width="100%">
<tr valign="top">
<td align="left"><span class="table-header">Variables Details</span></td>
<td align="right" valign="top"
><span class="options">[<a href="#section-VariablesDetails"
class="privatelink" onclick="toggle_private();"
>hide private</a>]</span></td>
</tr>
</table>
</td>
</tr>
</table>
<a name="empty_tags"></a>
<div class="private">
<table class="details" border="1" cellpadding="3"
cellspacing="0" width="100%" bgcolor="white">
<tr><td>
<h3 class="epydoc">empty_tags</h3>
<dl class="fields">
</dl>
<dl class="fields">
<dt>Value:</dt>
<dd><table><tr><td><pre class="variable">
<code class="variable-group">(</code><code class="variable-quote">'</code><code class="variable-string">param</code><code class="variable-quote">'</code><code class="variable-op">,</code>
<code class="variable-quote">'</code><code class="variable-string">img</code><code class="variable-quote">'</code><code class="variable-op">,</code>
<code class="variable-quote">'</code><code class="variable-string">area</code><code class="variable-quote">'</code><code class="variable-op">,</code>
<code class="variable-quote">'</code><code class="variable-string">br</code><code class="variable-quote">'</code><code class="variable-op">,</code>
<code class="variable-quote">'</code><code class="variable-string">basefont</code><code class="variable-quote">'</code><code class="variable-op">,</code>
<code class="variable-quote">'</code><code class="variable-string">input</code><code class="variable-quote">'</code><code class="variable-op">,</code>
<code class="variable-quote">'</code><code class="variable-string">base</code><code class="variable-quote">'</code><code class="variable-op">,</code>
<code class="variable-quote">'</code><code class="variable-string">meta</code><code class="variable-quote">'</code><code class="variable-op">,</code>
<code class="variable-ellipsis">...</code>
</pre></td></tr></table>
</dd>
</dl>
</td></tr></table>
</div>
<a name="block_level_tags"></a>
<div class="private">
<table class="details" border="1" cellpadding="3"
cellspacing="0" width="100%" bgcolor="white">
<tr><td>
<h3 class="epydoc">block_level_tags</h3>
<dl class="fields">
</dl>
<dl class="fields">
<dt>Value:</dt>
<dd><table><tr><td><pre class="variable">
<code class="variable-group">(</code><code class="variable-quote">'</code><code class="variable-string">address</code><code class="variable-quote">'</code><code class="variable-op">,</code>
<code class="variable-quote">'</code><code class="variable-string">blockquote</code><code class="variable-quote">'</code><code class="variable-op">,</code>
<code class="variable-quote">'</code><code class="variable-string">center</code><code class="variable-quote">'</code><code class="variable-op">,</code>
<code class="variable-quote">'</code><code class="variable-string">dir</code><code class="variable-quote">'</code><code class="variable-op">,</code>
<code class="variable-quote">'</code><code class="variable-string">div</code><code class="variable-quote">'</code><code class="variable-op">,</code>
<code class="variable-quote">'</code><code class="variable-string">dl</code><code class="variable-quote">'</code><code class="variable-op">,</code>
<code class="variable-quote">'</code><code class="variable-string">fieldset</code><code class="variable-quote">'</code><code class="variable-op">,</code>
<code class="variable-quote">'</code><code class="variable-string">form</code><code class="variable-quote">'</code><code class="variable-op">,</code>
<code class="variable-ellipsis">...</code>
</pre></td></tr></table>
</dd>
</dl>
</td></tr></table>
</div>
<a name="block_level_container_tags"></a>
<div class="private">
<table class="details" border="1" cellpadding="3"
cellspacing="0" width="100%" bgcolor="white">
<tr><td>
<h3 class="epydoc">block_level_container_tags</h3>
<dl class="fields">
</dl>
<dl class="fields">
<dt>Value:</dt>
<dd><table><tr><td><pre class="variable">
<code class="variable-group">(</code><code class="variable-quote">'</code><code class="variable-string">dd</code><code class="variable-quote">'</code><code class="variable-op">,</code>
<code class="variable-quote">'</code><code class="variable-string">dt</code><code class="variable-quote">'</code><code class="variable-op">,</code>
<code class="variable-quote">'</code><code class="variable-string">frameset</code><code class="variable-quote">'</code><code class="variable-op">,</code>
<code class="variable-quote">'</code><code class="variable-string">li</code><code class="variable-quote">'</code><code class="variable-op">,</code>
<code class="variable-quote">'</code><code class="variable-string">tbody</code><code class="variable-quote">'</code><code class="variable-op">,</code>
<code class="variable-quote">'</code><code class="variable-string">td</code><code class="variable-quote">'</code><code class="variable-op">,</code>
<code class="variable-quote">'</code><code class="variable-string">tfoot</code><code class="variable-quote">'</code><code class="variable-op">,</code>
<code class="variable-quote">'</code><code class="variable-string">th</code><code class="variable-quote">'</code><code class="variable-op">,</code>
<code class="variable-ellipsis">...</code>
</pre></td></tr></table>
</dd>
</dl>
</td></tr></table>
</div>
<a name="__test__"></a>
<div class="private">
<table class="details" border="1" cellpadding="3"
cellspacing="0" width="100%" bgcolor="white">
<tr><td>
<h3 class="epydoc">__test__</h3>
<dl class="fields">
</dl>
<dl class="fields">
<dt>Value:</dt>
<dd><table><tr><td><pre class="variable">
<code class="variable-group">{</code><code class="variable-quote">u'</code><code class="variable-string">html_annotate (line 31)</code><code class="variable-quote">'</code><code class="variable-op">: </code><code class="variable-quote">u'''</code><code class="variable-string"></code>
<code class="variable-string"> doclist should be ordered from oldest to newest, like::</code>
<code class="variable-string"></code>
<code class="variable-string"> >>> version1 = 'Hello World'</code>
<code class="variable-string"> >>> version2 = 'Goodbye World'</code>
<code class="variable-string"> >>> print(html_annotate([(version1, 'version 1'),</code>
<code class="variable-string"> ... (version2, 'version 2')]))</code>
<code class="variable-string"> <span title="version 2">Goodbye</span> <span title="version 1"</code><span class="variable-linewrap"><img src="crarr.png" alt="\" /></span>
<code class="variable-ellipsis">...</code>
</pre></td></tr></table>
</dd>
</dl>
</td></tr></table>
</div>
<br />
<!-- ==================== NAVIGATION BAR ==================== -->
<table class="navbar" border="0" width="100%" cellpadding="0"
bgcolor="#a0c0ff" cellspacing="0">
<tr valign="middle">
<!-- Home link -->
<th> <a
href="lxml-module.html">Home</a> </th>
<!-- Tree link -->
<th> <a
href="module-tree.html">Trees</a> </th>
<!-- Index link -->
<th> <a
href="identifier-index.html">Indices</a> </th>
<!-- Help link -->
<th> <a
href="help.html">Help</a> </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 Sun Sep 9 15:24:18 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>
distrib
>
Mageia
>
6
>
x86_64
>
media
>
core-updates
>
by-pkgid
>
d5ca09083fa1e0650b386d1b93516003
>
files
>
217
