mirror of
https://github.com/nim-lang/Nim.git
synced 2026-01-05 12:37:46 +00:00
662 lines
66 KiB
HTML
662 lines
66 KiB
HTML
<?xml version="1.0" encoding="utf-8" ?>
|
|
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "https://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
|
|
<!-- This file is generated by Nim. -->
|
|
<html xmlns="https://www.w3.org/1999/xhtml" xml:lang="en" lang="en" data-theme="auto">
|
|
<head>
|
|
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
|
<title>std/parsexml</title>
|
|
|
|
<!-- Google fonts -->
|
|
<link href='https://fonts.googleapis.com/css?family=Lato:400,600,900' rel='stylesheet' type='text/css'/>
|
|
<link href='https://fonts.googleapis.com/css?family=Source+Code+Pro:400,500,600' rel='stylesheet' type='text/css'/>
|
|
|
|
<!-- Favicon -->
|
|
<link rel="shortcut icon" href="data:image/x-icon;base64,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"/>
|
|
<link rel="icon" type="image/png" sizes="32x32" href="data:image/png;base64,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">
|
|
|
|
<!-- CSS -->
|
|
<link rel="stylesheet" type="text/css" href="nimdoc.out.css?v=2.3.1">
|
|
|
|
<!-- JS -->
|
|
<script type="text/javascript" src="dochack.js?v=2.3.1"></script>
|
|
</head>
|
|
<body>
|
|
<div class="document" id="documentId">
|
|
<div class="container">
|
|
<h1 class="title">std/parsexml</h1>
|
|
<div class="row">
|
|
<div class="three columns">
|
|
<div class="theme-select-wrapper">
|
|
<label for="theme-select">Theme: </label>
|
|
<select id="theme-select" onchange="setTheme(this.value)">
|
|
<option value="auto">🌗 Match OS</option>
|
|
<option value="dark">🌑 Dark</option>
|
|
<option value="light">🌕 Light</option>
|
|
</select>
|
|
</div>
|
|
<div id="global-links">
|
|
<ul class="simple-boot">
|
|
<li><a href="manual.html">Manual</a></li>
|
|
<li><a href="lib.html">Standard library</a></li>
|
|
<li> <a id="indexLink" href="theindex.html">Index</a></li>
|
|
<li><a href="compiler/theindex.html">Compiler docs</a></li>
|
|
<li><a href="https://nim-lang.github.io/fusion/theindex.html">Fusion docs</a></li>
|
|
<li><a href="https://nim-lang.github.io/Nim/">devel</a>, <a href="https://nim-lang.org/documentation.html">stable</a></li>
|
|
</ul>
|
|
</div>
|
|
<div id="searchInputDiv">
|
|
Search: <input type="search" id="searchInput"
|
|
oninput="search()" />
|
|
</div>
|
|
|
|
<ul class="simple simple-toc" id="toc-list">
|
|
<li><a class="reference" id="example-1colon-retrieve-html-title_toc" href="#example-1colon-retrieve-html-title">Example 1: Retrieve HTML title</a></li>
|
|
<li><a class="reference" id="example-2colon-retrieve-all-html-links_toc" href="#example-2colon-retrieve-all-html-links">Example 2: Retrieve all HTML links</a></li>
|
|
<li>
|
|
<a class="reference reference-toplevel" href="#6" id="56">Imports</a>
|
|
</li>
|
|
<li>
|
|
<details open>
|
|
<summary><a class="reference reference-toplevel" href="#7" id="57">Types</a></summary>
|
|
<ul class="simple simple-toc-section">
|
|
<li><a class="reference" href="#XmlErrorKind" title="XmlErrorKind = enum
|
|
errNone, ## no error
|
|
errEndOfCDataExpected, ## ``]]>`` expected
|
|
errNameExpected, ## name expected
|
|
errSemicolonExpected, ## ``;`` expected
|
|
errQmGtExpected, ## ``?>`` expected
|
|
errGtExpected, ## ``>`` expected
|
|
errEqExpected, ## ``=`` expected
|
|
errQuoteExpected, ## ``"`` or ``'`` expected
|
|
errEndOfCommentExpected, ## ``-->`` expected
|
|
errAttributeValueExpected ## non-empty attribute value expected">XmlErrorKind</a></li>
|
|
<li><a class="reference" href="#XmlEventKind" title="XmlEventKind = enum
|
|
xmlError, ## an error occurred during parsing
|
|
xmlEof, ## end of file reached
|
|
xmlCharData, ## character data
|
|
xmlWhitespace, ## whitespace has been parsed
|
|
xmlComment, ## a comment has been parsed
|
|
xmlPI, ## processing instruction (``<?name something ?>``)
|
|
xmlElementStart, ## ``<elem>``
|
|
xmlElementEnd, ## ``</elem>``
|
|
xmlElementOpen, ## ``<elem
|
|
xmlAttribute, ## ``key = "value"`` pair
|
|
xmlElementClose, ## ``>``
|
|
xmlCData, ## ``<![CDATA[`` ... data ... ``]]>``
|
|
xmlEntity, ## &entity;
|
|
xmlSpecial ## ``<! ... data ... >``">XmlEventKind</a></li>
|
|
<li><a class="reference" href="#XmlParseOption" title="XmlParseOption = enum
|
|
reportWhitespace, ## report whitespace
|
|
reportComments, ## report comments
|
|
allowUnquotedAttribs, ## allow unquoted attribute values (for HTML)
|
|
allowEmptyAttribs ## allow empty attributes (without explicit value)">XmlParseOption</a></li>
|
|
<li><a class="reference" href="#XmlParser" title="XmlParser = object of BaseLexer">XmlParser</a></li>
|
|
|
|
</ul>
|
|
</details>
|
|
</li>
|
|
<li>
|
|
<details open>
|
|
<summary><a class="reference reference-toplevel" href="#12" id="62">Procs</a></summary>
|
|
<ul class="simple simple-toc-section">
|
|
<ul class="simple nested-toc-section">close
|
|
<li><a class="reference" href="#close%2CXmlParser" title="close(my: var XmlParser)">close(my: var XmlParser)</a></li>
|
|
|
|
</ul>
|
|
<ul class="simple nested-toc-section">errorMsg
|
|
<li><a class="reference" href="#errorMsg%2CXmlParser" title="errorMsg(my: XmlParser): string">errorMsg(my: XmlParser): string</a></li>
|
|
<li><a class="reference" href="#errorMsg%2CXmlParser%2Cstring" title="errorMsg(my: XmlParser; msg: string): string">errorMsg(my: XmlParser; msg: string): string</a></li>
|
|
|
|
</ul>
|
|
<ul class="simple nested-toc-section">errorMsgExpected
|
|
<li><a class="reference" href="#errorMsgExpected%2CXmlParser%2Cstring" title="errorMsgExpected(my: XmlParser; tag: string): string">errorMsgExpected(my: XmlParser; tag: string): string</a></li>
|
|
|
|
</ul>
|
|
<ul class="simple nested-toc-section">getColumn
|
|
<li><a class="reference" href="#getColumn%2CXmlParser" title="getColumn(my: XmlParser): int">getColumn(my: XmlParser): int</a></li>
|
|
|
|
</ul>
|
|
<ul class="simple nested-toc-section">getFilename
|
|
<li><a class="reference" href="#getFilename%2CXmlParser" title="getFilename(my: XmlParser): string">getFilename(my: XmlParser): string</a></li>
|
|
|
|
</ul>
|
|
<ul class="simple nested-toc-section">getLine
|
|
<li><a class="reference" href="#getLine%2CXmlParser" title="getLine(my: XmlParser): int">getLine(my: XmlParser): int</a></li>
|
|
|
|
</ul>
|
|
<ul class="simple nested-toc-section">kind
|
|
<li><a class="reference" href="#kind%2CXmlParser" title="kind(my: XmlParser): XmlEventKind">kind(my: XmlParser): XmlEventKind</a></li>
|
|
|
|
</ul>
|
|
<ul class="simple nested-toc-section">next
|
|
<li><a class="reference" href="#next%2CXmlParser" title="next(my: var XmlParser)">next(my: var XmlParser)</a></li>
|
|
|
|
</ul>
|
|
<ul class="simple nested-toc-section">open
|
|
<li><a class="reference" href="#open%2CXmlParser%2CStream%2Cstring%2Cset%5BXmlParseOption%5D" title="open(my: var XmlParser; input: Stream; filename: string;
|
|
options: set[XmlParseOption] = {})">open(my: var XmlParser; input: Stream; filename: string;
|
|
options: set[XmlParseOption] = {})</a></li>
|
|
|
|
</ul>
|
|
<ul class="simple nested-toc-section">rawData
|
|
<li><a class="reference" href="#rawData%2CXmlParser" title="rawData(my: var XmlParser): lent string">rawData(my: var XmlParser): lent string</a></li>
|
|
|
|
</ul>
|
|
<ul class="simple nested-toc-section">rawData2
|
|
<li><a class="reference" href="#rawData2%2CXmlParser" title="rawData2(my: var XmlParser): lent string">rawData2(my: var XmlParser): lent string</a></li>
|
|
|
|
</ul>
|
|
|
|
</ul>
|
|
</details>
|
|
</li>
|
|
<li>
|
|
<details open>
|
|
<summary><a class="reference reference-toplevel" href="#18" id="68">Templates</a></summary>
|
|
<ul class="simple simple-toc-section">
|
|
<ul class="simple nested-toc-section">attrKey
|
|
<li><a class="reference" href="#attrKey.t%2CXmlParser" title="attrKey(my: XmlParser): string">attrKey(my: XmlParser): string</a></li>
|
|
|
|
</ul>
|
|
<ul class="simple nested-toc-section">attrValue
|
|
<li><a class="reference" href="#attrValue.t%2CXmlParser" title="attrValue(my: XmlParser): string">attrValue(my: XmlParser): string</a></li>
|
|
|
|
</ul>
|
|
<ul class="simple nested-toc-section">charData
|
|
<li><a class="reference" href="#charData.t%2CXmlParser" title="charData(my: XmlParser): string">charData(my: XmlParser): string</a></li>
|
|
|
|
</ul>
|
|
<ul class="simple nested-toc-section">elementName
|
|
<li><a class="reference" href="#elementName.t%2CXmlParser" title="elementName(my: XmlParser): string">elementName(my: XmlParser): string</a></li>
|
|
|
|
</ul>
|
|
<ul class="simple nested-toc-section">entityName
|
|
<li><a class="reference" href="#entityName.t%2CXmlParser" title="entityName(my: XmlParser): string">entityName(my: XmlParser): string</a></li>
|
|
|
|
</ul>
|
|
<ul class="simple nested-toc-section">piName
|
|
<li><a class="reference" href="#piName.t%2CXmlParser" title="piName(my: XmlParser): string">piName(my: XmlParser): string</a></li>
|
|
|
|
</ul>
|
|
<ul class="simple nested-toc-section">piRest
|
|
<li><a class="reference" href="#piRest.t%2CXmlParser" title="piRest(my: XmlParser): string">piRest(my: XmlParser): string</a></li>
|
|
|
|
</ul>
|
|
|
|
</ul>
|
|
</details>
|
|
</li>
|
|
|
|
</ul>
|
|
|
|
</div>
|
|
<div class="nine columns" id="content">
|
|
<a href="https://github.com/nim-lang/Nim/tree/devel/lib/pure/parsexml.nim#L1" class="link-seesrc" target="_blank">Source</a>
|
|
<a href="https://github.com/nim-lang/Nim/edit/devel/lib/pure/parsexml.nim#L1" class="link-seesrc" target="_blank" >Edit</a>
|
|
|
|
<div id="tocRoot"></div>
|
|
|
|
<p class="module-desc">This module implements a simple high performance <span id="xml_1">XML</span> / <span id="html_1">HTML</span> parser. The only encoding that is supported is UTF-8. The parser has been designed to be somewhat error correcting, so that even most "wild HTML" found on the web can be parsed with it. <strong>Note:</strong> This parser does not check that each <tt class="docutils literal"><span class="pre"><tag></span></tt> has a corresponding <tt class="docutils literal"><span class="pre"></tag></span></tt>! These checks have do be implemented by the client code for various reasons:<ul class="simple"><li>Old HTML contains tags that have no end tag: <tt class="docutils literal"><span class="pre"><br></span></tt> for example.</li>
|
|
<li>HTML tags are case insensitive, XML tags are case sensitive. Since this library can parse both, only the client knows which comparison is to be used.</li>
|
|
<li>Thus the checks would have been very difficult to implement properly with little benefit, especially since they are simple to implement in the client. The client should use the <tt class="docutils literal"><span class="pre"><span class="Identifier">errorMsgExpected</span></span></tt> proc to generate a nice error message that fits the other error messages this library creates.</li>
|
|
</ul>
|
|
|
|
<h1><a class="toc-backref" id="example-1colon-retrieve-html-title" href="#example-1colon-retrieve-html-title">Example 1: Retrieve HTML title</a></h1><p>The file <tt class="docutils literal"><span class="pre">examples/htmltitle.nim</span></tt> demonstrates how to use the XML parser to accomplish a simple task: To determine the title of an HTML document.</p>
|
|
<p><pre class="listing"><span class="Comment"># Example program to show the parsexml module</span>
|
|
<span class="Comment"># This program reads an HTML file and writes its title to stdout.</span>
|
|
<span class="Comment"># Errors and whitespace are ignored.</span>
|
|
|
|
<span class="Keyword">import</span> <span class="Identifier">std</span><span class="Operator">/</span><span class="Punctuation">[</span><span class="Identifier">os</span><span class="Punctuation">,</span> <span class="Identifier">streams</span><span class="Punctuation">,</span> <span class="Identifier">parsexml</span><span class="Punctuation">,</span> <span class="Identifier">strutils</span><span class="Punctuation">]</span>
|
|
|
|
<span class="Keyword">if</span> <span class="Identifier">paramCount</span><span class="Punctuation">(</span><span class="Punctuation">)</span> <span class="Operator"><</span> <span class="DecNumber">1</span><span class="Punctuation">:</span>
|
|
<span class="Identifier">quit</span><span class="Punctuation">(</span><span class="StringLit">"Usage: htmltitle filename[.html]"</span><span class="Punctuation">)</span>
|
|
|
|
<span class="Keyword">var</span> <span class="Identifier">filename</span> <span class="Operator">=</span> <span class="Identifier">addFileExt</span><span class="Punctuation">(</span><span class="Identifier">paramStr</span><span class="Punctuation">(</span><span class="DecNumber">1</span><span class="Punctuation">)</span><span class="Punctuation">,</span> <span class="StringLit">"html"</span><span class="Punctuation">)</span>
|
|
<span class="Keyword">var</span> <span class="Identifier">s</span> <span class="Operator">=</span> <span class="Identifier">newFileStream</span><span class="Punctuation">(</span><span class="Identifier">filename</span><span class="Punctuation">,</span> <span class="Identifier">fmRead</span><span class="Punctuation">)</span>
|
|
<span class="Keyword">if</span> <span class="Identifier">s</span> <span class="Operator">==</span> <span class="Keyword">nil</span><span class="Punctuation">:</span> <span class="Identifier">quit</span><span class="Punctuation">(</span><span class="StringLit">"cannot open the file "</span> <span class="Operator">&</span> <span class="Identifier">filename</span><span class="Punctuation">)</span>
|
|
<span class="Keyword">var</span> <span class="Identifier">x</span><span class="Punctuation">:</span> <span class="Identifier">XmlParser</span>
|
|
<span class="Identifier">open</span><span class="Punctuation">(</span><span class="Identifier">x</span><span class="Punctuation">,</span> <span class="Identifier">s</span><span class="Punctuation">,</span> <span class="Identifier">filename</span><span class="Punctuation">)</span>
|
|
<span class="Keyword">while</span> <span class="Identifier">true</span><span class="Punctuation">:</span>
|
|
<span class="Identifier">x</span><span class="Operator">.</span><span class="Identifier">next</span><span class="Punctuation">(</span><span class="Punctuation">)</span>
|
|
<span class="Keyword">case</span> <span class="Identifier">x</span><span class="Operator">.</span><span class="Identifier">kind</span>
|
|
<span class="Keyword">of</span> <span class="Identifier">xmlElementStart</span><span class="Punctuation">:</span>
|
|
<span class="Keyword">if</span> <span class="Identifier">cmpIgnoreCase</span><span class="Punctuation">(</span><span class="Identifier">x</span><span class="Operator">.</span><span class="Identifier">elementName</span><span class="Punctuation">,</span> <span class="StringLit">"title"</span><span class="Punctuation">)</span> <span class="Operator">==</span> <span class="DecNumber">0</span><span class="Punctuation">:</span>
|
|
<span class="Keyword">var</span> <span class="Identifier">title</span> <span class="Operator">=</span> <span class="StringLit">""</span>
|
|
<span class="Identifier">x</span><span class="Operator">.</span><span class="Identifier">next</span><span class="Punctuation">(</span><span class="Punctuation">)</span> <span class="Comment"># skip "<title>"</span>
|
|
<span class="Keyword">while</span> <span class="Identifier">x</span><span class="Operator">.</span><span class="Identifier">kind</span> <span class="Operator">==</span> <span class="Identifier">xmlCharData</span><span class="Punctuation">:</span>
|
|
<span class="Identifier">title</span><span class="Operator">.</span><span class="Identifier">add</span><span class="Punctuation">(</span><span class="Identifier">x</span><span class="Operator">.</span><span class="Identifier">charData</span><span class="Punctuation">)</span>
|
|
<span class="Identifier">x</span><span class="Operator">.</span><span class="Identifier">next</span><span class="Punctuation">(</span><span class="Punctuation">)</span>
|
|
<span class="Keyword">if</span> <span class="Identifier">x</span><span class="Operator">.</span><span class="Identifier">kind</span> <span class="Operator">==</span> <span class="Identifier">xmlElementEnd</span> <span class="Keyword">and</span> <span class="Identifier">cmpIgnoreCase</span><span class="Punctuation">(</span><span class="Identifier">x</span><span class="Operator">.</span><span class="Identifier">elementName</span><span class="Punctuation">,</span> <span class="StringLit">"title"</span><span class="Punctuation">)</span> <span class="Operator">==</span> <span class="DecNumber">0</span><span class="Punctuation">:</span>
|
|
<span class="Identifier">echo</span><span class="Punctuation">(</span><span class="StringLit">"Title: "</span> <span class="Operator">&</span> <span class="Identifier">title</span><span class="Punctuation">)</span>
|
|
<span class="Identifier">quit</span><span class="Punctuation">(</span><span class="DecNumber">0</span><span class="Punctuation">)</span> <span class="Comment"># Success!</span>
|
|
<span class="Keyword">else</span><span class="Punctuation">:</span>
|
|
<span class="Identifier">echo</span><span class="Punctuation">(</span><span class="Identifier">x</span><span class="Operator">.</span><span class="Identifier">errorMsgExpected</span><span class="Punctuation">(</span><span class="StringLit">"/title"</span><span class="Punctuation">)</span><span class="Punctuation">)</span>
|
|
|
|
<span class="Keyword">of</span> <span class="Identifier">xmlEof</span><span class="Punctuation">:</span> <span class="Keyword">break</span> <span class="Comment"># end of file reached</span>
|
|
<span class="Keyword">else</span><span class="Punctuation">:</span> <span class="Keyword">discard</span> <span class="Comment"># ignore other events</span>
|
|
|
|
<span class="Identifier">x</span><span class="Operator">.</span><span class="Identifier">close</span><span class="Punctuation">(</span><span class="Punctuation">)</span>
|
|
<span class="Identifier">quit</span><span class="Punctuation">(</span><span class="StringLit">"Could not determine title!"</span><span class="Punctuation">)</span></pre></p>
|
|
|
|
<h1><a class="toc-backref" id="example-2colon-retrieve-all-html-links" href="#example-2colon-retrieve-all-html-links">Example 2: Retrieve all HTML links</a></h1><p>The file <tt class="docutils literal"><span class="pre">examples/htmlrefs.nim</span></tt> demonstrates how to use the XML parser to accomplish another simple task: To determine all the links an HTML document contains.</p>
|
|
<p><pre class="listing"><span class="Comment"># Example program to show the new parsexml module</span>
|
|
<span class="Comment"># This program reads an HTML file and writes all its used links to stdout.</span>
|
|
<span class="Comment"># Errors and whitespace are ignored.</span>
|
|
|
|
<span class="Keyword">import</span> <span class="Identifier">std</span><span class="Operator">/</span><span class="Punctuation">[</span><span class="Identifier">os</span><span class="Punctuation">,</span> <span class="Identifier">streams</span><span class="Punctuation">,</span> <span class="Identifier">parsexml</span><span class="Punctuation">,</span> <span class="Identifier">strutils</span><span class="Punctuation">]</span>
|
|
|
|
<span class="Keyword">proc</span> <span class="Punctuation">`</span><span class="Operator">=?=</span><span class="Punctuation">`</span> <span class="Punctuation">(</span><span class="Identifier">a</span><span class="Punctuation">,</span> <span class="Identifier">b</span><span class="Punctuation">:</span> <span class="Identifier">string</span><span class="Punctuation">)</span><span class="Punctuation">:</span> <span class="Identifier">bool</span> <span class="Operator">=</span>
|
|
<span class="Comment"># little trick: define our own comparator that ignores case</span>
|
|
<span class="Keyword">return</span> <span class="Identifier">cmpIgnoreCase</span><span class="Punctuation">(</span><span class="Identifier">a</span><span class="Punctuation">,</span> <span class="Identifier">b</span><span class="Punctuation">)</span> <span class="Operator">==</span> <span class="DecNumber">0</span>
|
|
|
|
<span class="Keyword">if</span> <span class="Identifier">paramCount</span><span class="Punctuation">(</span><span class="Punctuation">)</span> <span class="Operator"><</span> <span class="DecNumber">1</span><span class="Punctuation">:</span>
|
|
<span class="Identifier">quit</span><span class="Punctuation">(</span><span class="StringLit">"Usage: htmlrefs filename[.html]"</span><span class="Punctuation">)</span>
|
|
|
|
<span class="Keyword">var</span> <span class="Identifier">links</span> <span class="Operator">=</span> <span class="DecNumber">0</span> <span class="Comment"># count the number of links</span>
|
|
<span class="Keyword">var</span> <span class="Identifier">filename</span> <span class="Operator">=</span> <span class="Identifier">addFileExt</span><span class="Punctuation">(</span><span class="Identifier">paramStr</span><span class="Punctuation">(</span><span class="DecNumber">1</span><span class="Punctuation">)</span><span class="Punctuation">,</span> <span class="StringLit">"html"</span><span class="Punctuation">)</span>
|
|
<span class="Keyword">var</span> <span class="Identifier">s</span> <span class="Operator">=</span> <span class="Identifier">newFileStream</span><span class="Punctuation">(</span><span class="Identifier">filename</span><span class="Punctuation">,</span> <span class="Identifier">fmRead</span><span class="Punctuation">)</span>
|
|
<span class="Keyword">if</span> <span class="Identifier">s</span> <span class="Operator">==</span> <span class="Keyword">nil</span><span class="Punctuation">:</span> <span class="Identifier">quit</span><span class="Punctuation">(</span><span class="StringLit">"cannot open the file "</span> <span class="Operator">&</span> <span class="Identifier">filename</span><span class="Punctuation">)</span>
|
|
<span class="Keyword">var</span> <span class="Identifier">x</span><span class="Punctuation">:</span> <span class="Identifier">XmlParser</span>
|
|
<span class="Identifier">open</span><span class="Punctuation">(</span><span class="Identifier">x</span><span class="Punctuation">,</span> <span class="Identifier">s</span><span class="Punctuation">,</span> <span class="Identifier">filename</span><span class="Punctuation">)</span>
|
|
<span class="Identifier">next</span><span class="Punctuation">(</span><span class="Identifier">x</span><span class="Punctuation">)</span> <span class="Comment"># get first event</span>
|
|
<span class="Keyword">block</span> <span class="Identifier">mainLoop</span><span class="Punctuation">:</span>
|
|
<span class="Keyword">while</span> <span class="Identifier">true</span><span class="Punctuation">:</span>
|
|
<span class="Keyword">case</span> <span class="Identifier">x</span><span class="Operator">.</span><span class="Identifier">kind</span>
|
|
<span class="Keyword">of</span> <span class="Identifier">xmlElementOpen</span><span class="Punctuation">:</span>
|
|
<span class="Comment"># the <a href = "xyz"> tag we are interested in always has an attribute,</span>
|
|
<span class="Comment"># thus we search for ``xmlElementOpen`` and not for ``xmlElementStart``</span>
|
|
<span class="Keyword">if</span> <span class="Identifier">x</span><span class="Operator">.</span><span class="Identifier">elementName</span> <span class="Operator">=?=</span> <span class="StringLit">"a"</span><span class="Punctuation">:</span>
|
|
<span class="Identifier">x</span><span class="Operator">.</span><span class="Identifier">next</span><span class="Punctuation">(</span><span class="Punctuation">)</span>
|
|
<span class="Keyword">if</span> <span class="Identifier">x</span><span class="Operator">.</span><span class="Identifier">kind</span> <span class="Operator">==</span> <span class="Identifier">xmlAttribute</span><span class="Punctuation">:</span>
|
|
<span class="Keyword">if</span> <span class="Identifier">x</span><span class="Operator">.</span><span class="Identifier">attrKey</span> <span class="Operator">=?=</span> <span class="StringLit">"href"</span><span class="Punctuation">:</span>
|
|
<span class="Keyword">var</span> <span class="Identifier">link</span> <span class="Operator">=</span> <span class="Identifier">x</span><span class="Operator">.</span><span class="Identifier">attrValue</span>
|
|
<span class="Identifier">inc</span><span class="Punctuation">(</span><span class="Identifier">links</span><span class="Punctuation">)</span>
|
|
<span class="Comment"># skip until we have an ``xmlElementClose`` event</span>
|
|
<span class="Keyword">while</span> <span class="Identifier">true</span><span class="Punctuation">:</span>
|
|
<span class="Identifier">x</span><span class="Operator">.</span><span class="Identifier">next</span><span class="Punctuation">(</span><span class="Punctuation">)</span>
|
|
<span class="Keyword">case</span> <span class="Identifier">x</span><span class="Operator">.</span><span class="Identifier">kind</span>
|
|
<span class="Keyword">of</span> <span class="Identifier">xmlEof</span><span class="Punctuation">:</span> <span class="Keyword">break</span> <span class="Identifier">mainLoop</span>
|
|
<span class="Keyword">of</span> <span class="Identifier">xmlElementClose</span><span class="Punctuation">:</span> <span class="Keyword">break</span>
|
|
<span class="Keyword">else</span><span class="Punctuation">:</span> <span class="Keyword">discard</span>
|
|
<span class="Identifier">x</span><span class="Operator">.</span><span class="Identifier">next</span><span class="Punctuation">(</span><span class="Punctuation">)</span> <span class="Comment"># skip ``xmlElementClose``</span>
|
|
<span class="Comment"># now we have the description for the ``a`` element</span>
|
|
<span class="Keyword">var</span> <span class="Identifier">desc</span> <span class="Operator">=</span> <span class="StringLit">""</span>
|
|
<span class="Keyword">while</span> <span class="Identifier">x</span><span class="Operator">.</span><span class="Identifier">kind</span> <span class="Operator">==</span> <span class="Identifier">xmlCharData</span><span class="Punctuation">:</span>
|
|
<span class="Identifier">desc</span><span class="Operator">.</span><span class="Identifier">add</span><span class="Punctuation">(</span><span class="Identifier">x</span><span class="Operator">.</span><span class="Identifier">charData</span><span class="Punctuation">)</span>
|
|
<span class="Identifier">x</span><span class="Operator">.</span><span class="Identifier">next</span><span class="Punctuation">(</span><span class="Punctuation">)</span>
|
|
<span class="Identifier">echo</span><span class="Punctuation">(</span><span class="Identifier">desc</span> <span class="Operator">&</span> <span class="StringLit">": "</span> <span class="Operator">&</span> <span class="Identifier">link</span><span class="Punctuation">)</span>
|
|
<span class="Keyword">else</span><span class="Punctuation">:</span>
|
|
<span class="Identifier">x</span><span class="Operator">.</span><span class="Identifier">next</span><span class="Punctuation">(</span><span class="Punctuation">)</span>
|
|
<span class="Keyword">of</span> <span class="Identifier">xmlEof</span><span class="Punctuation">:</span> <span class="Keyword">break</span> <span class="Comment"># end of file reached</span>
|
|
<span class="Keyword">of</span> <span class="Identifier">xmlError</span><span class="Punctuation">:</span>
|
|
<span class="Identifier">echo</span><span class="Punctuation">(</span><span class="Identifier">errorMsg</span><span class="Punctuation">(</span><span class="Identifier">x</span><span class="Punctuation">)</span><span class="Punctuation">)</span>
|
|
<span class="Identifier">x</span><span class="Operator">.</span><span class="Identifier">next</span><span class="Punctuation">(</span><span class="Punctuation">)</span>
|
|
<span class="Keyword">else</span><span class="Punctuation">:</span> <span class="Identifier">x</span><span class="Operator">.</span><span class="Identifier">next</span><span class="Punctuation">(</span><span class="Punctuation">)</span> <span class="Comment"># skip other events</span>
|
|
|
|
<span class="Identifier">echo</span><span class="Punctuation">(</span><span class="Operator">$</span><span class="Identifier">links</span> <span class="Operator">&</span> <span class="StringLit">" link(s) found!"</span><span class="Punctuation">)</span>
|
|
<span class="Identifier">x</span><span class="Operator">.</span><span class="Identifier">close</span><span class="Punctuation">(</span><span class="Punctuation">)</span></pre></p>
|
|
</p>
|
|
<div class="section" id="6">
|
|
<h1><a class="toc-backref" href="#6">Imports</a></h1>
|
|
<dl class="item">
|
|
<a class="reference external" href="strutils.html">strutils</a>, <a class="reference external" href="lexbase.html">lexbase</a>, <a class="reference external" href="streams.html">streams</a>, <a class="reference external" href="unicode.html">unicode</a>, <a class="reference external" href="assertions.html">assertions</a>, <a class="reference external" href="syncio.html">syncio</a>, <a class="reference external" href="os.html">os</a>
|
|
</dl>
|
|
</div>
|
|
<div class="section" id="7">
|
|
<h1><a class="toc-backref" href="#7">Types</a></h1>
|
|
<dl class="item">
|
|
<div id="XmlErrorKind">
|
|
<dt><pre><a href="parsexml.html#XmlErrorKind"><span class="Identifier">XmlErrorKind</span></a> <span class="Other">=</span> <span class="Keyword">enum</span>
|
|
<span class="Identifier">errNone</span><span class="Other">,</span> <span class="Comment">## no error</span>
|
|
<span class="Identifier">errEndOfCDataExpected</span><span class="Other">,</span> <span class="Comment">## ``]]>`` expected</span>
|
|
<span class="Identifier">errNameExpected</span><span class="Other">,</span> <span class="Comment">## name expected</span>
|
|
<span class="Identifier">errSemicolonExpected</span><span class="Other">,</span> <span class="Comment">## ``;`` expected</span>
|
|
<span class="Identifier">errQmGtExpected</span><span class="Other">,</span> <span class="Comment">## ``?>`` expected</span>
|
|
<span class="Identifier">errGtExpected</span><span class="Other">,</span> <span class="Comment">## ``>`` expected</span>
|
|
<span class="Identifier">errEqExpected</span><span class="Other">,</span> <span class="Comment">## ``=`` expected</span>
|
|
<span class="Identifier">errQuoteExpected</span><span class="Other">,</span> <span class="Comment">## ``"`` or ``'`` expected</span>
|
|
<span class="Identifier">errEndOfCommentExpected</span><span class="Other">,</span> <span class="Comment">## ``-->`` expected</span>
|
|
<span class="Identifier">errAttributeValueExpected</span> <span class="Comment">## non-empty attribute value expected</span></pre></dt>
|
|
<dd>
|
|
|
|
enumeration that lists all errors that can occur
|
|
<a href="https://github.com/nim-lang/Nim/tree/devel/lib/pure/parsexml.nim#L176" class="link-seesrc" target="_blank">Source</a>
|
|
<a href="https://github.com/nim-lang/Nim/edit/devel/lib/pure/parsexml.nim#L176" class="link-seesrc" target="_blank" >Edit</a>
|
|
|
|
</dd>
|
|
</div>
|
|
<div id="XmlEventKind">
|
|
<dt><pre><a href="parsexml.html#XmlEventKind"><span class="Identifier">XmlEventKind</span></a> <span class="Other">=</span> <span class="Keyword">enum</span>
|
|
<span class="Identifier">xmlError</span><span class="Other">,</span> <span class="Comment">## an error occurred during parsing</span>
|
|
<span class="Identifier">xmlEof</span><span class="Other">,</span> <span class="Comment">## end of file reached</span>
|
|
<span class="Identifier">xmlCharData</span><span class="Other">,</span> <span class="Comment">## character data</span>
|
|
<span class="Identifier">xmlWhitespace</span><span class="Other">,</span> <span class="Comment">## whitespace has been parsed</span>
|
|
<span class="Identifier">xmlComment</span><span class="Other">,</span> <span class="Comment">## a comment has been parsed</span>
|
|
<span class="Identifier">xmlPI</span><span class="Other">,</span> <span class="Comment">## processing instruction (``<?name something ?>``)</span>
|
|
<span class="Identifier">xmlElementStart</span><span class="Other">,</span> <span class="Comment">## ``<elem>``</span>
|
|
<span class="Identifier">xmlElementEnd</span><span class="Other">,</span> <span class="Comment">## ``</elem>``</span>
|
|
<span class="Identifier">xmlElementOpen</span><span class="Other">,</span> <span class="Comment">## ``<elem</span>
|
|
<span class="Identifier">xmlAttribute</span><span class="Other">,</span> <span class="Comment">## ``key = "value"`` pair</span>
|
|
<span class="Identifier">xmlElementClose</span><span class="Other">,</span> <span class="Comment">## ``>``</span>
|
|
<span class="Identifier">xmlCData</span><span class="Other">,</span> <span class="Comment">## ``<![CDATA[`` ... data ... ``]]>``</span>
|
|
<span class="Identifier">xmlEntity</span><span class="Other">,</span> <span class="Comment">## &entity;</span>
|
|
<span class="Identifier">xmlSpecial</span> <span class="Comment">## ``<! ... data ... >``</span></pre></dt>
|
|
<dd>
|
|
|
|
enumeration of all events that may occur when parsing
|
|
<a href="https://github.com/nim-lang/Nim/tree/devel/lib/pure/parsexml.nim#L160" class="link-seesrc" target="_blank">Source</a>
|
|
<a href="https://github.com/nim-lang/Nim/edit/devel/lib/pure/parsexml.nim#L160" class="link-seesrc" target="_blank" >Edit</a>
|
|
|
|
</dd>
|
|
</div>
|
|
<div id="XmlParseOption">
|
|
<dt><pre><a href="parsexml.html#XmlParseOption"><span class="Identifier">XmlParseOption</span></a> <span class="Other">=</span> <span class="Keyword">enum</span>
|
|
<span class="Identifier">reportWhitespace</span><span class="Other">,</span> <span class="Comment">## report whitespace</span>
|
|
<span class="Identifier">reportComments</span><span class="Other">,</span> <span class="Comment">## report comments</span>
|
|
<span class="Identifier">allowUnquotedAttribs</span><span class="Other">,</span> <span class="Comment">## allow unquoted attribute values (for HTML)</span>
|
|
<span class="Identifier">allowEmptyAttribs</span> <span class="Comment">## allow empty attributes (without explicit value)</span></pre></dt>
|
|
<dd>
|
|
|
|
options for the XML parser
|
|
<a href="https://github.com/nim-lang/Nim/tree/devel/lib/pure/parsexml.nim#L191" class="link-seesrc" target="_blank">Source</a>
|
|
<a href="https://github.com/nim-lang/Nim/edit/devel/lib/pure/parsexml.nim#L191" class="link-seesrc" target="_blank" >Edit</a>
|
|
|
|
</dd>
|
|
</div>
|
|
<div id="XmlParser">
|
|
<dt><pre><a href="parsexml.html#XmlParser"><span class="Identifier">XmlParser</span></a> <span class="Other">=</span> <span class="Keyword">object</span> <span class="Keyword">of</span> <a href="lexbase.html#BaseLexer"><span class="Identifier">BaseLexer</span></a></pre></dt>
|
|
<dd>
|
|
|
|
the parser object.
|
|
<a href="https://github.com/nim-lang/Nim/tree/devel/lib/pure/parsexml.nim#L197" class="link-seesrc" target="_blank">Source</a>
|
|
<a href="https://github.com/nim-lang/Nim/edit/devel/lib/pure/parsexml.nim#L197" class="link-seesrc" target="_blank" >Edit</a>
|
|
|
|
</dd>
|
|
</div>
|
|
|
|
</dl>
|
|
</div>
|
|
<div class="section" id="12">
|
|
<h1><a class="toc-backref" href="#12">Procs</a></h1>
|
|
<dl class="item">
|
|
<div id="close-procs-all">
|
|
<div id="close,XmlParser">
|
|
<dt><pre><span class="Keyword">proc</span> <a href="#close%2CXmlParser"><span class="Identifier">close</span></a><span class="Other">(</span><span class="Identifier">my</span><span class="Other">:</span> <span class="Keyword">var</span> <a href="parsexml.html#XmlParser"><span class="Identifier">XmlParser</span></a><span class="Other">)</span> {.<span class="Identifier">inline</span><span class="Other">,</span> <span><span class="Other pragmadots">...</span></span><span class="pragmawrap"><span class="Identifier">raises</span><span class="Other">:</span> <span class="Other">[</span><span class="Identifier">IOError</span><span class="Other">,</span> <span class="Identifier">OSError</span><span class="Other">]</span><span class="Other">,</span>
|
|
<span class="Identifier">tags</span><span class="Other">:</span> <span class="Other">[</span><span class="Identifier">WriteIOEffect</span><span class="Other">]</span><span class="Other">,</span> <span class="Identifier">forbids</span><span class="Other">:</span> <span class="Other">[</span><span class="Other">]</span></span>.}</pre></dt>
|
|
<dd>
|
|
|
|
closes the parser <tt class="docutils literal"><span class="pre"><span class="Identifier">my</span></span></tt> and its associated input stream.
|
|
<a href="https://github.com/nim-lang/Nim/tree/devel/lib/pure/parsexml.nim#L238" class="link-seesrc" target="_blank">Source</a>
|
|
<a href="https://github.com/nim-lang/Nim/edit/devel/lib/pure/parsexml.nim#L238" class="link-seesrc" target="_blank" >Edit</a>
|
|
|
|
</dd>
|
|
</div>
|
|
|
|
</div>
|
|
<div id="errorMsg-procs-all">
|
|
<div id="errorMsg,XmlParser">
|
|
<dt><pre><span class="Keyword">proc</span> <a href="#errorMsg%2CXmlParser"><span class="Identifier">errorMsg</span></a><span class="Other">(</span><span class="Identifier">my</span><span class="Other">:</span> <a href="parsexml.html#XmlParser"><span class="Identifier">XmlParser</span></a><span class="Other">)</span><span class="Other">:</span> <a href="system.html#string"><span class="Identifier">string</span></a> {.<span><span class="Other pragmadots">...</span></span><span class="pragmawrap"><span class="Identifier">raises</span><span class="Other">:</span> <span class="Other">[</span><span class="Identifier">ValueError</span><span class="Other">]</span><span class="Other">,</span> <span class="Identifier">tags</span><span class="Other">:</span> <span class="Other">[</span><span class="Other">]</span><span class="Other">,</span>
|
|
<span class="Identifier">forbids</span><span class="Other">:</span> <span class="Other">[</span><span class="Other">]</span></span>.}</pre></dt>
|
|
<dd>
|
|
|
|
returns a helpful error message for the event <tt class="docutils literal"><span class="pre">xmlError</span></tt>
|
|
<a href="https://github.com/nim-lang/Nim/tree/devel/lib/pure/parsexml.nim#L327" class="link-seesrc" target="_blank">Source</a>
|
|
<a href="https://github.com/nim-lang/Nim/edit/devel/lib/pure/parsexml.nim#L327" class="link-seesrc" target="_blank" >Edit</a>
|
|
|
|
</dd>
|
|
</div>
|
|
<div id="errorMsg,XmlParser,string">
|
|
<dt><pre><span class="Keyword">proc</span> <a href="#errorMsg%2CXmlParser%2Cstring"><span class="Identifier">errorMsg</span></a><span class="Other">(</span><span class="Identifier">my</span><span class="Other">:</span> <a href="parsexml.html#XmlParser"><span class="Identifier">XmlParser</span></a><span class="Other">;</span> <span class="Identifier">msg</span><span class="Other">:</span> <a href="system.html#string"><span class="Identifier">string</span></a><span class="Other">)</span><span class="Other">:</span> <a href="system.html#string"><span class="Identifier">string</span></a> {.<span><span class="Other pragmadots">...</span></span><span class="pragmawrap"><span class="Identifier">raises</span><span class="Other">:</span> <span class="Other">[</span><span class="Identifier">ValueError</span><span class="Other">]</span><span class="Other">,</span>
|
|
<span class="Identifier">tags</span><span class="Other">:</span> <span class="Other">[</span><span class="Other">]</span><span class="Other">,</span> <span class="Identifier">forbids</span><span class="Other">:</span> <span class="Other">[</span><span class="Other">]</span></span>.}</pre></dt>
|
|
<dd>
|
|
|
|
returns an error message with text <tt class="docutils literal"><span class="pre"><span class="Identifier">msg</span></span></tt> in the same format as the other error messages
|
|
<a href="https://github.com/nim-lang/Nim/tree/devel/lib/pure/parsexml.nim#L339" class="link-seesrc" target="_blank">Source</a>
|
|
<a href="https://github.com/nim-lang/Nim/edit/devel/lib/pure/parsexml.nim#L339" class="link-seesrc" target="_blank" >Edit</a>
|
|
|
|
</dd>
|
|
</div>
|
|
|
|
</div>
|
|
<div id="errorMsgExpected-procs-all">
|
|
<div id="errorMsgExpected,XmlParser,string">
|
|
<dt><pre><span class="Keyword">proc</span> <a href="#errorMsgExpected%2CXmlParser%2Cstring"><span class="Identifier">errorMsgExpected</span></a><span class="Other">(</span><span class="Identifier">my</span><span class="Other">:</span> <a href="parsexml.html#XmlParser"><span class="Identifier">XmlParser</span></a><span class="Other">;</span> <span class="Identifier">tag</span><span class="Other">:</span> <a href="system.html#string"><span class="Identifier">string</span></a><span class="Other">)</span><span class="Other">:</span> <a href="system.html#string"><span class="Identifier">string</span></a> {.
|
|
<span><span class="Other pragmadots">...</span></span><span class="pragmawrap"><span class="Identifier">raises</span><span class="Other">:</span> <span class="Other">[</span><span class="Identifier">ValueError</span><span class="Other">]</span><span class="Other">,</span> <span class="Identifier">tags</span><span class="Other">:</span> <span class="Other">[</span><span class="Other">]</span><span class="Other">,</span> <span class="Identifier">forbids</span><span class="Other">:</span> <span class="Other">[</span><span class="Other">]</span></span>.}</pre></dt>
|
|
<dd>
|
|
|
|
returns an error message "<tag> expected" in the same format as the other error messages
|
|
<a href="https://github.com/nim-lang/Nim/tree/devel/lib/pure/parsexml.nim#L333" class="link-seesrc" target="_blank">Source</a>
|
|
<a href="https://github.com/nim-lang/Nim/edit/devel/lib/pure/parsexml.nim#L333" class="link-seesrc" target="_blank" >Edit</a>
|
|
|
|
</dd>
|
|
</div>
|
|
|
|
</div>
|
|
<div id="getColumn-procs-all">
|
|
<div id="getColumn,XmlParser">
|
|
<dt><pre><span class="Keyword">proc</span> <a href="#getColumn%2CXmlParser"><span class="Identifier">getColumn</span></a><span class="Other">(</span><span class="Identifier">my</span><span class="Other">:</span> <a href="parsexml.html#XmlParser"><span class="Identifier">XmlParser</span></a><span class="Other">)</span><span class="Other">:</span> <a href="system.html#int"><span class="Identifier">int</span></a> {.<span class="Identifier">inline</span><span class="Other">,</span> <span><span class="Other pragmadots">...</span></span><span class="pragmawrap"><span class="Identifier">raises</span><span class="Other">:</span> <span class="Other">[</span><span class="Other">]</span><span class="Other">,</span> <span class="Identifier">tags</span><span class="Other">:</span> <span class="Other">[</span><span class="Other">]</span><span class="Other">,</span> <span class="Identifier">forbids</span><span class="Other">:</span> <span class="Other">[</span><span class="Other">]</span></span>.}</pre></dt>
|
|
<dd>
|
|
|
|
get the current column the parser has arrived at.
|
|
<a href="https://github.com/nim-lang/Nim/tree/devel/lib/pure/parsexml.nim#L315" class="link-seesrc" target="_blank">Source</a>
|
|
<a href="https://github.com/nim-lang/Nim/edit/devel/lib/pure/parsexml.nim#L315" class="link-seesrc" target="_blank" >Edit</a>
|
|
|
|
</dd>
|
|
</div>
|
|
|
|
</div>
|
|
<div id="getFilename-procs-all">
|
|
<div id="getFilename,XmlParser">
|
|
<dt><pre><span class="Keyword">proc</span> <a href="#getFilename%2CXmlParser"><span class="Identifier">getFilename</span></a><span class="Other">(</span><span class="Identifier">my</span><span class="Other">:</span> <a href="parsexml.html#XmlParser"><span class="Identifier">XmlParser</span></a><span class="Other">)</span><span class="Other">:</span> <a href="system.html#string"><span class="Identifier">string</span></a> {.<span class="Identifier">inline</span><span class="Other">,</span> <span><span class="Other pragmadots">...</span></span><span class="pragmawrap"><span class="Identifier">raises</span><span class="Other">:</span> <span class="Other">[</span><span class="Other">]</span><span class="Other">,</span> <span class="Identifier">tags</span><span class="Other">:</span> <span class="Other">[</span><span class="Other">]</span><span class="Other">,</span>
|
|
<span class="Identifier">forbids</span><span class="Other">:</span> <span class="Other">[</span><span class="Other">]</span></span>.}</pre></dt>
|
|
<dd>
|
|
|
|
get the filename of the file that the parser processes.
|
|
<a href="https://github.com/nim-lang/Nim/tree/devel/lib/pure/parsexml.nim#L323" class="link-seesrc" target="_blank">Source</a>
|
|
<a href="https://github.com/nim-lang/Nim/edit/devel/lib/pure/parsexml.nim#L323" class="link-seesrc" target="_blank" >Edit</a>
|
|
|
|
</dd>
|
|
</div>
|
|
|
|
</div>
|
|
<div id="getLine-procs-all">
|
|
<div id="getLine,XmlParser">
|
|
<dt><pre><span class="Keyword">proc</span> <a href="#getLine%2CXmlParser"><span class="Identifier">getLine</span></a><span class="Other">(</span><span class="Identifier">my</span><span class="Other">:</span> <a href="parsexml.html#XmlParser"><span class="Identifier">XmlParser</span></a><span class="Other">)</span><span class="Other">:</span> <a href="system.html#int"><span class="Identifier">int</span></a> {.<span class="Identifier">inline</span><span class="Other">,</span> <span><span class="Other pragmadots">...</span></span><span class="pragmawrap"><span class="Identifier">raises</span><span class="Other">:</span> <span class="Other">[</span><span class="Other">]</span><span class="Other">,</span> <span class="Identifier">tags</span><span class="Other">:</span> <span class="Other">[</span><span class="Other">]</span><span class="Other">,</span> <span class="Identifier">forbids</span><span class="Other">:</span> <span class="Other">[</span><span class="Other">]</span></span>.}</pre></dt>
|
|
<dd>
|
|
|
|
get the current line the parser has arrived at.
|
|
<a href="https://github.com/nim-lang/Nim/tree/devel/lib/pure/parsexml.nim#L319" class="link-seesrc" target="_blank">Source</a>
|
|
<a href="https://github.com/nim-lang/Nim/edit/devel/lib/pure/parsexml.nim#L319" class="link-seesrc" target="_blank" >Edit</a>
|
|
|
|
</dd>
|
|
</div>
|
|
|
|
</div>
|
|
<div id="kind-procs-all">
|
|
<div id="kind,XmlParser">
|
|
<dt><pre><span class="Keyword">proc</span> <a href="#kind%2CXmlParser"><span class="Identifier">kind</span></a><span class="Other">(</span><span class="Identifier">my</span><span class="Other">:</span> <a href="parsexml.html#XmlParser"><span class="Identifier">XmlParser</span></a><span class="Other">)</span><span class="Other">:</span> <a href="parsexml.html#XmlEventKind"><span class="Identifier">XmlEventKind</span></a> {.<span class="Identifier">inline</span><span class="Other">,</span> <span><span class="Other pragmadots">...</span></span><span class="pragmawrap"><span class="Identifier">raises</span><span class="Other">:</span> <span class="Other">[</span><span class="Other">]</span><span class="Other">,</span> <span class="Identifier">tags</span><span class="Other">:</span> <span class="Other">[</span><span class="Other">]</span><span class="Other">,</span>
|
|
<span class="Identifier">forbids</span><span class="Other">:</span> <span class="Other">[</span><span class="Other">]</span></span>.}</pre></dt>
|
|
<dd>
|
|
|
|
returns the current event type for the XML parser
|
|
<a href="https://github.com/nim-lang/Nim/tree/devel/lib/pure/parsexml.nim#L242" class="link-seesrc" target="_blank">Source</a>
|
|
<a href="https://github.com/nim-lang/Nim/edit/devel/lib/pure/parsexml.nim#L242" class="link-seesrc" target="_blank" >Edit</a>
|
|
|
|
</dd>
|
|
</div>
|
|
|
|
</div>
|
|
<div id="next-procs-all">
|
|
<div id="next,XmlParser">
|
|
<dt><pre><span class="Keyword">proc</span> <a href="#next%2CXmlParser"><span class="Identifier">next</span></a><span class="Other">(</span><span class="Identifier">my</span><span class="Other">:</span> <span class="Keyword">var</span> <a href="parsexml.html#XmlParser"><span class="Identifier">XmlParser</span></a><span class="Other">)</span> {.<span><span class="Other pragmadots">...</span></span><span class="pragmawrap"><span class="Identifier">raises</span><span class="Other">:</span> <span class="Other">[</span><span class="Identifier">IOError</span><span class="Other">,</span> <span class="Identifier">OSError</span><span class="Other">]</span><span class="Other">,</span> <span class="Identifier">tags</span><span class="Other">:</span> <span class="Other">[</span><span class="Identifier">ReadIOEffect</span><span class="Other">]</span><span class="Other">,</span>
|
|
<span class="Identifier">forbids</span><span class="Other">:</span> <span class="Other">[</span><span class="Other">]</span></span>.}</pre></dt>
|
|
<dd>
|
|
|
|
retrieves the first/next event. This controls the parser.
|
|
<a href="https://github.com/nim-lang/Nim/tree/devel/lib/pure/parsexml.nim#L757" class="link-seesrc" target="_blank">Source</a>
|
|
<a href="https://github.com/nim-lang/Nim/edit/devel/lib/pure/parsexml.nim#L757" class="link-seesrc" target="_blank" >Edit</a>
|
|
|
|
</dd>
|
|
</div>
|
|
|
|
</div>
|
|
<div id="open-procs-all">
|
|
<div id="open,XmlParser,Stream,string,set[XmlParseOption]">
|
|
<dt><pre><span class="Keyword">proc</span> <a href="#open%2CXmlParser%2CStream%2Cstring%2Cset%5BXmlParseOption%5D"><span class="Identifier">open</span></a><span class="Other">(</span><span class="Identifier">my</span><span class="Other">:</span> <span class="Keyword">var</span> <a href="parsexml.html#XmlParser"><span class="Identifier">XmlParser</span></a><span class="Other">;</span> <span class="Identifier">input</span><span class="Other">:</span> <a href="streams.html#Stream"><span class="Identifier">Stream</span></a><span class="Other">;</span> <span class="Identifier">filename</span><span class="Other">:</span> <a href="system.html#string"><span class="Identifier">string</span></a><span class="Other">;</span>
|
|
<span class="Identifier">options</span><span class="Other">:</span> <a href="system.html#set"><span class="Identifier">set</span></a><span class="Other">[</span><a href="parsexml.html#XmlParseOption"><span class="Identifier">XmlParseOption</span></a><span class="Other">]</span> <span class="Other">=</span> <span class="Other">{</span><span class="Other">}</span><span class="Other">)</span> {.<span><span class="Other pragmadots">...</span></span><span class="pragmawrap"><span class="Identifier">raises</span><span class="Other">:</span> <span class="Other">[</span><span class="Identifier">IOError</span><span class="Other">,</span> <span class="Identifier">OSError</span><span class="Other">]</span><span class="Other">,</span>
|
|
<span class="Identifier">tags</span><span class="Other">:</span> <span class="Other">[</span><span class="Identifier">ReadIOEffect</span><span class="Other">]</span><span class="Other">,</span> <span class="Identifier">forbids</span><span class="Other">:</span> <span class="Other">[</span><span class="Other">]</span></span>.}</pre></dt>
|
|
<dd>
|
|
|
|
initializes the parser with an input stream. <tt class="docutils literal"><span class="pre"><span class="Identifier">Filename</span></span></tt> is only used for nice error messages. The parser's behaviour can be controlled by the <tt class="docutils literal"><span class="pre"><span class="Identifier">options</span></span></tt> parameter: If <tt class="docutils literal"><span class="pre"><span class="Identifier">options</span></span></tt> contains <tt class="docutils literal"><span class="pre">reportWhitespace</span></tt> a whitespace token is reported as an <tt class="docutils literal"><span class="pre">xmlWhitespace</span></tt> event. If <tt class="docutils literal"><span class="pre"><span class="Identifier">options</span></span></tt> contains <tt class="docutils literal"><span class="pre">reportComments</span></tt> a comment token is reported as an <tt class="docutils literal"><span class="pre">xmlComment</span></tt> event.
|
|
<a href="https://github.com/nim-lang/Nim/tree/devel/lib/pure/parsexml.nim#L220" class="link-seesrc" target="_blank">Source</a>
|
|
<a href="https://github.com/nim-lang/Nim/edit/devel/lib/pure/parsexml.nim#L220" class="link-seesrc" target="_blank" >Edit</a>
|
|
|
|
</dd>
|
|
</div>
|
|
|
|
</div>
|
|
<div id="rawData-procs-all">
|
|
<div id="rawData,XmlParser">
|
|
<dt><pre><span class="Keyword">proc</span> <a href="#rawData%2CXmlParser"><span class="Identifier">rawData</span></a><span class="Other">(</span><span class="Identifier">my</span><span class="Other">:</span> <span class="Keyword">var</span> <a href="parsexml.html#XmlParser"><span class="Identifier">XmlParser</span></a><span class="Other">)</span><span class="Other">:</span> <a href="system.html#lent"><span class="Identifier">lent</span></a> <a href="system.html#string"><span class="Identifier">string</span></a> {.<span class="Identifier">inline</span><span class="Other">,</span> <span><span class="Other pragmadots">...</span></span><span class="pragmawrap"><span class="Identifier">raises</span><span class="Other">:</span> <span class="Other">[</span><span class="Other">]</span><span class="Other">,</span> <span class="Identifier">tags</span><span class="Other">:</span> <span class="Other">[</span><span class="Other">]</span><span class="Other">,</span>
|
|
<span class="Identifier">forbids</span><span class="Other">:</span> <span class="Other">[</span><span class="Other">]</span></span>.}</pre></dt>
|
|
<dd>
|
|
|
|
returns the underlying 'data' string by reference. This is only used for speed hacks.
|
|
<a href="https://github.com/nim-lang/Nim/tree/devel/lib/pure/parsexml.nim#L305" class="link-seesrc" target="_blank">Source</a>
|
|
<a href="https://github.com/nim-lang/Nim/edit/devel/lib/pure/parsexml.nim#L305" class="link-seesrc" target="_blank" >Edit</a>
|
|
|
|
</dd>
|
|
</div>
|
|
|
|
</div>
|
|
<div id="rawData2-procs-all">
|
|
<div id="rawData2,XmlParser">
|
|
<dt><pre><span class="Keyword">proc</span> <a href="#rawData2%2CXmlParser"><span class="Identifier">rawData2</span></a><span class="Other">(</span><span class="Identifier">my</span><span class="Other">:</span> <span class="Keyword">var</span> <a href="parsexml.html#XmlParser"><span class="Identifier">XmlParser</span></a><span class="Other">)</span><span class="Other">:</span> <a href="system.html#lent"><span class="Identifier">lent</span></a> <a href="system.html#string"><span class="Identifier">string</span></a> {.<span class="Identifier">inline</span><span class="Other">,</span> <span><span class="Other pragmadots">...</span></span><span class="pragmawrap"><span class="Identifier">raises</span><span class="Other">:</span> <span class="Other">[</span><span class="Other">]</span><span class="Other">,</span> <span class="Identifier">tags</span><span class="Other">:</span> <span class="Other">[</span><span class="Other">]</span><span class="Other">,</span>
|
|
<span class="Identifier">forbids</span><span class="Other">:</span> <span class="Other">[</span><span class="Other">]</span></span>.}</pre></dt>
|
|
<dd>
|
|
|
|
returns the underlying second 'data' string by reference. This is only used for speed hacks.
|
|
<a href="https://github.com/nim-lang/Nim/tree/devel/lib/pure/parsexml.nim#L310" class="link-seesrc" target="_blank">Source</a>
|
|
<a href="https://github.com/nim-lang/Nim/edit/devel/lib/pure/parsexml.nim#L310" class="link-seesrc" target="_blank" >Edit</a>
|
|
|
|
</dd>
|
|
</div>
|
|
|
|
</div>
|
|
|
|
</dl>
|
|
</div>
|
|
<div class="section" id="18">
|
|
<h1><a class="toc-backref" href="#18">Templates</a></h1>
|
|
<dl class="item">
|
|
<div id="attrKey-templates-all">
|
|
<div id="attrKey.t,XmlParser">
|
|
<dt><pre><span class="Keyword">template</span> <a href="#attrKey.t%2CXmlParser"><span class="Identifier">attrKey</span></a><span class="Other">(</span><span class="Identifier">my</span><span class="Other">:</span> <a href="parsexml.html#XmlParser"><span class="Identifier">XmlParser</span></a><span class="Other">)</span><span class="Other">:</span> <a href="system.html#string"><span class="Identifier">string</span></a></pre></dt>
|
|
<dd>
|
|
|
|
returns the attribute key for the event <tt class="docutils literal"><span class="pre">xmlAttribute</span></tt> Raises an assertion in debug mode if <tt class="docutils literal"><span class="pre">my.kind</span></tt> is not <tt class="docutils literal"><span class="pre">xmlAttribute</span></tt>. In release mode, this will not trigger an error but the value returned will not be valid.
|
|
<a href="https://github.com/nim-lang/Nim/tree/devel/lib/pure/parsexml.nim#L273" class="link-seesrc" target="_blank">Source</a>
|
|
<a href="https://github.com/nim-lang/Nim/edit/devel/lib/pure/parsexml.nim#L273" class="link-seesrc" target="_blank" >Edit</a>
|
|
|
|
</dd>
|
|
</div>
|
|
|
|
</div>
|
|
<div id="attrValue-templates-all">
|
|
<div id="attrValue.t,XmlParser">
|
|
<dt><pre><span class="Keyword">template</span> <a href="#attrValue.t%2CXmlParser"><span class="Identifier">attrValue</span></a><span class="Other">(</span><span class="Identifier">my</span><span class="Other">:</span> <a href="parsexml.html#XmlParser"><span class="Identifier">XmlParser</span></a><span class="Other">)</span><span class="Other">:</span> <a href="system.html#string"><span class="Identifier">string</span></a></pre></dt>
|
|
<dd>
|
|
|
|
returns the attribute value for the event <tt class="docutils literal"><span class="pre">xmlAttribute</span></tt> Raises an assertion in debug mode if <tt class="docutils literal"><span class="pre">my.kind</span></tt> is not <tt class="docutils literal"><span class="pre">xmlAttribute</span></tt>. In release mode, this will not trigger an error but the value returned will not be valid.
|
|
<a href="https://github.com/nim-lang/Nim/tree/devel/lib/pure/parsexml.nim#L281" class="link-seesrc" target="_blank">Source</a>
|
|
<a href="https://github.com/nim-lang/Nim/edit/devel/lib/pure/parsexml.nim#L281" class="link-seesrc" target="_blank" >Edit</a>
|
|
|
|
</dd>
|
|
</div>
|
|
|
|
</div>
|
|
<div id="charData-templates-all">
|
|
<div id="charData.t,XmlParser">
|
|
<dt><pre><span class="Keyword">template</span> <a href="#charData.t%2CXmlParser"><span class="Identifier">charData</span></a><span class="Other">(</span><span class="Identifier">my</span><span class="Other">:</span> <a href="parsexml.html#XmlParser"><span class="Identifier">XmlParser</span></a><span class="Other">)</span><span class="Other">:</span> <a href="system.html#string"><span class="Identifier">string</span></a></pre></dt>
|
|
<dd>
|
|
|
|
returns the character data for the events: <tt class="docutils literal"><span class="pre">xmlCharData</span></tt>, <tt class="docutils literal"><span class="pre">xmlWhitespace</span></tt>, <tt class="docutils literal"><span class="pre">xmlComment</span></tt>, <tt class="docutils literal"><span class="pre">xmlCData</span></tt>, <tt class="docutils literal"><span class="pre">xmlSpecial</span></tt> Raises an assertion in debug mode if <tt class="docutils literal"><span class="pre">my.kind</span></tt> is not one of those events. In release mode, this will not trigger an error but the value returned will not be valid.
|
|
<a href="https://github.com/nim-lang/Nim/tree/devel/lib/pure/parsexml.nim#L246" class="link-seesrc" target="_blank">Source</a>
|
|
<a href="https://github.com/nim-lang/Nim/edit/devel/lib/pure/parsexml.nim#L246" class="link-seesrc" target="_blank" >Edit</a>
|
|
|
|
</dd>
|
|
</div>
|
|
|
|
</div>
|
|
<div id="elementName-templates-all">
|
|
<div id="elementName.t,XmlParser">
|
|
<dt><pre><span class="Keyword">template</span> <a href="#elementName.t%2CXmlParser"><span class="Identifier">elementName</span></a><span class="Other">(</span><span class="Identifier">my</span><span class="Other">:</span> <a href="parsexml.html#XmlParser"><span class="Identifier">XmlParser</span></a><span class="Other">)</span><span class="Other">:</span> <a href="system.html#string"><span class="Identifier">string</span></a></pre></dt>
|
|
<dd>
|
|
|
|
returns the element name for the events: <tt class="docutils literal"><span class="pre">xmlElementStart</span></tt>, <tt class="docutils literal"><span class="pre">xmlElementEnd</span></tt>, <tt class="docutils literal"><span class="pre">xmlElementOpen</span></tt> Raises an assertion in debug mode if <tt class="docutils literal"><span class="pre">my.kind</span></tt> is not one of those events. In release mode, this will not trigger an error but the value returned will not be valid.
|
|
<a href="https://github.com/nim-lang/Nim/tree/devel/lib/pure/parsexml.nim#L256" class="link-seesrc" target="_blank">Source</a>
|
|
<a href="https://github.com/nim-lang/Nim/edit/devel/lib/pure/parsexml.nim#L256" class="link-seesrc" target="_blank" >Edit</a>
|
|
|
|
</dd>
|
|
</div>
|
|
|
|
</div>
|
|
<div id="entityName-templates-all">
|
|
<div id="entityName.t,XmlParser">
|
|
<dt><pre><span class="Keyword">template</span> <a href="#entityName.t%2CXmlParser"><span class="Identifier">entityName</span></a><span class="Other">(</span><span class="Identifier">my</span><span class="Other">:</span> <a href="parsexml.html#XmlParser"><span class="Identifier">XmlParser</span></a><span class="Other">)</span><span class="Other">:</span> <a href="system.html#string"><span class="Identifier">string</span></a></pre></dt>
|
|
<dd>
|
|
|
|
returns the entity name for the event: <tt class="docutils literal"><span class="pre">xmlEntity</span></tt> Raises an assertion in debug mode if <tt class="docutils literal"><span class="pre">my.kind</span></tt> is not <tt class="docutils literal"><span class="pre">xmlEntity</span></tt>. In release mode, this will not trigger an error but the value returned will not be valid.
|
|
<a href="https://github.com/nim-lang/Nim/tree/devel/lib/pure/parsexml.nim#L265" class="link-seesrc" target="_blank">Source</a>
|
|
<a href="https://github.com/nim-lang/Nim/edit/devel/lib/pure/parsexml.nim#L265" class="link-seesrc" target="_blank" >Edit</a>
|
|
|
|
</dd>
|
|
</div>
|
|
|
|
</div>
|
|
<div id="piName-templates-all">
|
|
<div id="piName.t,XmlParser">
|
|
<dt><pre><span class="Keyword">template</span> <a href="#piName.t%2CXmlParser"><span class="Identifier">piName</span></a><span class="Other">(</span><span class="Identifier">my</span><span class="Other">:</span> <a href="parsexml.html#XmlParser"><span class="Identifier">XmlParser</span></a><span class="Other">)</span><span class="Other">:</span> <a href="system.html#string"><span class="Identifier">string</span></a></pre></dt>
|
|
<dd>
|
|
|
|
returns the processing instruction name for the event <tt class="docutils literal"><span class="pre">xmlPI</span></tt> Raises an assertion in debug mode if <tt class="docutils literal"><span class="pre">my.kind</span></tt> is not <tt class="docutils literal"><span class="pre">xmlPI</span></tt>. In release mode, this will not trigger an error but the value returned will not be valid.
|
|
<a href="https://github.com/nim-lang/Nim/tree/devel/lib/pure/parsexml.nim#L289" class="link-seesrc" target="_blank">Source</a>
|
|
<a href="https://github.com/nim-lang/Nim/edit/devel/lib/pure/parsexml.nim#L289" class="link-seesrc" target="_blank" >Edit</a>
|
|
|
|
</dd>
|
|
</div>
|
|
|
|
</div>
|
|
<div id="piRest-templates-all">
|
|
<div id="piRest.t,XmlParser">
|
|
<dt><pre><span class="Keyword">template</span> <a href="#piRest.t%2CXmlParser"><span class="Identifier">piRest</span></a><span class="Other">(</span><span class="Identifier">my</span><span class="Other">:</span> <a href="parsexml.html#XmlParser"><span class="Identifier">XmlParser</span></a><span class="Other">)</span><span class="Other">:</span> <a href="system.html#string"><span class="Identifier">string</span></a></pre></dt>
|
|
<dd>
|
|
|
|
returns the rest of the processing instruction for the event <tt class="docutils literal"><span class="pre">xmlPI</span></tt> Raises an assertion in debug mode if <tt class="docutils literal"><span class="pre">my.kind</span></tt> is not <tt class="docutils literal"><span class="pre">xmlPI</span></tt>. In release mode, this will not trigger an error but the value returned will not be valid.
|
|
<a href="https://github.com/nim-lang/Nim/tree/devel/lib/pure/parsexml.nim#L297" class="link-seesrc" target="_blank">Source</a>
|
|
<a href="https://github.com/nim-lang/Nim/edit/devel/lib/pure/parsexml.nim#L297" class="link-seesrc" target="_blank" >Edit</a>
|
|
|
|
</dd>
|
|
</div>
|
|
|
|
</div>
|
|
|
|
</dl>
|
|
</div>
|
|
|
|
</div>
|
|
</div>
|
|
|
|
<div class="twelve-columns footer">
|
|
<span class="nim-sprite"></span>
|
|
<br>
|
|
<small style="color: var(--hint);">Made with Nim. Generated: 2025-09-27 04:02:07 UTC</small>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
<script defer data-domain="nim-lang.org" src="https://plausible.io/js/plausible.js"></script>
|
|
|
|
</body>
|
|
</html>
|