blob: 2ecbe6b3ac536e4587d5d8e6c133221bfa3a60a0 [file] [log] [blame]
<!DOCTYPE html><html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><meta name="generator" content="rustdoc"><meta name="description" content="Source of the Rust file `/root/.cargo/registry/src/github.com-1ecc6299db9ec823/htmlescape-0.3.1/src/decode.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>decode.rs - source</title><link rel="preload" as="font" type="font/woff2" crossorigin href="../../SourceSerif4-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../FiraSans-Regular.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../FiraSans-Medium.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../SourceCodePro-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../SourceSerif4-Bold.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../SourceCodePro-Semibold.ttf.woff2"><link rel="stylesheet" href="../../normalize.css"><link rel="stylesheet" href="../../rustdoc.css" id="mainThemeStyle"><link rel="stylesheet" href="../../ayu.css" disabled><link rel="stylesheet" href="../../dark.css" disabled><link rel="stylesheet" href="../../light.css" id="themeStyle"><script id="default-settings" ></script><script src="../../storage.js"></script><script defer src="../../source-script.js"></script><script defer src="../../source-files.js"></script><script defer src="../../main.js"></script><noscript><link rel="stylesheet" href="../../noscript.css"></noscript><link rel="alternate icon" type="image/png" href="../../favicon-16x16.png"><link rel="alternate icon" type="image/png" href="../../favicon-32x32.png"><link rel="icon" type="image/svg+xml" href="../../favicon.svg"></head><body class="rustdoc source"><!--[if lte IE 11]><div class="warning">This old browser is unsupported and will most likely display funky things.</div><![endif]--><nav class="sidebar"><a class="sidebar-logo" href="../../htmlescape/index.html"><div class="logo-container"><img class="rust-logo" src="../../rust-logo.svg" alt="logo"></div></a></nav><main><div class="width-limiter"><nav class="sub"><a class="sub-logo-container" href="../../htmlescape/index.html"><img class="rust-logo" src="../../rust-logo.svg" alt="logo"></a><form class="search-form"><div class="search-container"><span></span><input class="search-input" name="search" autocomplete="off" spellcheck="false" placeholder="Click or press ‘S’ to search, ‘?’ for more options…" type="search"><div id="help-button" title="help" tabindex="-1"><a href="../../help.html">?</a></div><div id="settings-menu" tabindex="-1"><a href="../../settings.html" title="settings"><img width="22" height="22" alt="Change settings" src="../../wheel.svg"></a></div></div></form></nav><section id="main-content" class="content"><div class="example-wrap"><pre class="src-line-numbers"><span id="1">1</span>
<span id="2">2</span>
<span id="3">3</span>
<span id="4">4</span>
<span id="5">5</span>
<span id="6">6</span>
<span id="7">7</span>
<span id="8">8</span>
<span id="9">9</span>
<span id="10">10</span>
<span id="11">11</span>
<span id="12">12</span>
<span id="13">13</span>
<span id="14">14</span>
<span id="15">15</span>
<span id="16">16</span>
<span id="17">17</span>
<span id="18">18</span>
<span id="19">19</span>
<span id="20">20</span>
<span id="21">21</span>
<span id="22">22</span>
<span id="23">23</span>
<span id="24">24</span>
<span id="25">25</span>
<span id="26">26</span>
<span id="27">27</span>
<span id="28">28</span>
<span id="29">29</span>
<span id="30">30</span>
<span id="31">31</span>
<span id="32">32</span>
<span id="33">33</span>
<span id="34">34</span>
<span id="35">35</span>
<span id="36">36</span>
<span id="37">37</span>
<span id="38">38</span>
<span id="39">39</span>
<span id="40">40</span>
<span id="41">41</span>
<span id="42">42</span>
<span id="43">43</span>
<span id="44">44</span>
<span id="45">45</span>
<span id="46">46</span>
<span id="47">47</span>
<span id="48">48</span>
<span id="49">49</span>
<span id="50">50</span>
<span id="51">51</span>
<span id="52">52</span>
<span id="53">53</span>
<span id="54">54</span>
<span id="55">55</span>
<span id="56">56</span>
<span id="57">57</span>
<span id="58">58</span>
<span id="59">59</span>
<span id="60">60</span>
<span id="61">61</span>
<span id="62">62</span>
<span id="63">63</span>
<span id="64">64</span>
<span id="65">65</span>
<span id="66">66</span>
<span id="67">67</span>
<span id="68">68</span>
<span id="69">69</span>
<span id="70">70</span>
<span id="71">71</span>
<span id="72">72</span>
<span id="73">73</span>
<span id="74">74</span>
<span id="75">75</span>
<span id="76">76</span>
<span id="77">77</span>
<span id="78">78</span>
<span id="79">79</span>
<span id="80">80</span>
<span id="81">81</span>
<span id="82">82</span>
<span id="83">83</span>
<span id="84">84</span>
<span id="85">85</span>
<span id="86">86</span>
<span id="87">87</span>
<span id="88">88</span>
<span id="89">89</span>
<span id="90">90</span>
<span id="91">91</span>
<span id="92">92</span>
<span id="93">93</span>
<span id="94">94</span>
<span id="95">95</span>
<span id="96">96</span>
<span id="97">97</span>
<span id="98">98</span>
<span id="99">99</span>
<span id="100">100</span>
<span id="101">101</span>
<span id="102">102</span>
<span id="103">103</span>
<span id="104">104</span>
<span id="105">105</span>
<span id="106">106</span>
<span id="107">107</span>
<span id="108">108</span>
<span id="109">109</span>
<span id="110">110</span>
<span id="111">111</span>
<span id="112">112</span>
<span id="113">113</span>
<span id="114">114</span>
<span id="115">115</span>
<span id="116">116</span>
<span id="117">117</span>
<span id="118">118</span>
<span id="119">119</span>
<span id="120">120</span>
<span id="121">121</span>
<span id="122">122</span>
<span id="123">123</span>
<span id="124">124</span>
<span id="125">125</span>
<span id="126">126</span>
<span id="127">127</span>
<span id="128">128</span>
<span id="129">129</span>
<span id="130">130</span>
<span id="131">131</span>
<span id="132">132</span>
<span id="133">133</span>
<span id="134">134</span>
<span id="135">135</span>
<span id="136">136</span>
<span id="137">137</span>
<span id="138">138</span>
<span id="139">139</span>
<span id="140">140</span>
<span id="141">141</span>
<span id="142">142</span>
<span id="143">143</span>
<span id="144">144</span>
<span id="145">145</span>
<span id="146">146</span>
<span id="147">147</span>
<span id="148">148</span>
<span id="149">149</span>
<span id="150">150</span>
<span id="151">151</span>
<span id="152">152</span>
<span id="153">153</span>
<span id="154">154</span>
<span id="155">155</span>
<span id="156">156</span>
<span id="157">157</span>
<span id="158">158</span>
<span id="159">159</span>
<span id="160">160</span>
<span id="161">161</span>
<span id="162">162</span>
<span id="163">163</span>
<span id="164">164</span>
<span id="165">165</span>
<span id="166">166</span>
<span id="167">167</span>
<span id="168">168</span>
<span id="169">169</span>
<span id="170">170</span>
<span id="171">171</span>
<span id="172">172</span>
<span id="173">173</span>
<span id="174">174</span>
<span id="175">175</span>
<span id="176">176</span>
<span id="177">177</span>
<span id="178">178</span>
<span id="179">179</span>
<span id="180">180</span>
<span id="181">181</span>
<span id="182">182</span>
<span id="183">183</span>
<span id="184">184</span>
<span id="185">185</span>
<span id="186">186</span>
<span id="187">187</span>
<span id="188">188</span>
<span id="189">189</span>
<span id="190">190</span>
<span id="191">191</span>
<span id="192">192</span>
<span id="193">193</span>
<span id="194">194</span>
<span id="195">195</span>
<span id="196">196</span>
<span id="197">197</span>
<span id="198">198</span>
<span id="199">199</span>
<span id="200">200</span>
<span id="201">201</span>
<span id="202">202</span>
<span id="203">203</span>
<span id="204">204</span>
<span id="205">205</span>
<span id="206">206</span>
<span id="207">207</span>
<span id="208">208</span>
<span id="209">209</span>
<span id="210">210</span>
</pre><pre class="rust"><code><span class="kw">use </span>std::io::{<span class="self">self</span>, Write, BufRead, Cursor};
<span class="kw">use </span>std::char;
<span class="kw">use </span><span class="self">self</span>::DecodeState::<span class="kw-2">*</span>;
<span class="kw">use </span><span class="self">self</span>::DecodeErrKind::<span class="kw-2">*</span>;
<span class="kw">use </span>io_support::{<span class="self">self</span>, write_char, CharsError};
<span class="kw">use </span>entities::<span class="kw-2">*</span>;
<span class="attribute">#[derive(Debug)]
</span><span class="kw">pub enum </span>DecodeErrKind {
<span class="doccomment">/// A non-existent named entity was referenced.
/// Example: &amp;thisentitydoesnotexist
</span>UnknownEntity,
<span class="doccomment">/// A numerical escape sequence (&amp;# or &amp;#x) containing an invalid character.
/// Examples: `&amp;#32a`, `&amp;#xfoo`
</span>MalformedNumEscape,
<span class="doccomment">/// A numerical escape sequence (&amp;# or &amp;#x) resolved to an invalid unicode code point.
/// Example: `&amp;#xffffff`
</span>InvalidCharacter,
<span class="doccomment">/// The input ended prematurely (ie. inside an unterminated named entity sequence).
</span>PrematureEnd,
<span class="doccomment">/// An IO error occured.
</span>IoError(io::Error),
<span class="doccomment">/// The supplied Reader produces invalid UTF-8.
</span>EncodingError,
}
<span class="kw">impl </span>PartialEq <span class="kw">for </span>DecodeErrKind {
<span class="kw">fn </span>eq(<span class="kw-2">&amp;</span><span class="self">self</span>, other: <span class="kw-2">&amp;</span>DecodeErrKind) -&gt; bool {
<span class="kw">match </span>(<span class="self">self</span>, other) {
(<span class="kw-2">&amp;</span>UnknownEntity, <span class="kw-2">&amp;</span>UnknownEntity) =&gt; <span class="bool-val">true</span>,
(<span class="kw-2">&amp;</span>MalformedNumEscape, <span class="kw-2">&amp;</span>MalformedNumEscape) =&gt; <span class="bool-val">true</span>,
(<span class="kw-2">&amp;</span>InvalidCharacter, <span class="kw-2">&amp;</span>InvalidCharacter) =&gt; <span class="bool-val">true</span>,
(<span class="kw-2">&amp;</span>PrematureEnd, <span class="kw-2">&amp;</span>PrematureEnd) =&gt; <span class="bool-val">true</span>,
(<span class="kw-2">&amp;</span>IoError(<span class="kw">_</span>), <span class="kw-2">&amp;</span>IoError(<span class="kw">_</span>)) =&gt; <span class="bool-val">true</span>,
(<span class="kw-2">&amp;</span>EncodingError, <span class="kw-2">&amp;</span>EncodingError) =&gt; <span class="bool-val">true</span>,
<span class="kw">_ </span>=&gt; <span class="bool-val">false
</span>}
}
}
<span class="kw">impl </span>Eq <span class="kw">for </span>DecodeErrKind {}
<span class="doccomment">/// Error from decoding a entity-encoded string.
</span><span class="attribute">#[derive(Debug, Eq, PartialEq)]
</span><span class="kw">pub struct </span>DecodeErr {
<span class="doccomment">/// Number of characters read from the input before encountering an error
</span><span class="kw">pub </span>position: usize,
<span class="doccomment">/// Type of error
</span><span class="kw">pub </span>kind: DecodeErrKind
}
<span class="attribute">#[derive(PartialEq, Eq)]
</span><span class="kw">enum </span>DecodeState {
Normal,
Entity,
Named,
Numeric,
Hex,
Dec
}
<span class="macro">macro_rules! </span>try_parse(
(<span class="macro-nonterminal">$parse</span>:expr, <span class="macro-nonterminal">$pos</span>:expr) =&gt; (
<span class="kw">match </span><span class="macro-nonterminal">$parse </span>{
<span class="prelude-val">Err</span>(reason) =&gt; <span class="kw">return </span><span class="prelude-val">Err</span>(DecodeErr{ position: <span class="macro-nonterminal">$pos</span>, kind: reason}),
<span class="prelude-val">Ok</span>(res) =&gt; res
}
););
<span class="macro">macro_rules! </span>try_dec_io(
(<span class="macro-nonterminal">$io</span>:expr, <span class="macro-nonterminal">$pos</span>:expr) =&gt; (
<span class="kw">match </span><span class="macro-nonterminal">$io </span>{
<span class="prelude-val">Err</span>(e) =&gt; <span class="kw">return </span><span class="prelude-val">Err</span>(DecodeErr{ position: <span class="macro-nonterminal">$pos</span>, kind: IoError(e)}),
<span class="prelude-val">Ok</span>(res) =&gt; res
}
););
<span class="doccomment">/// Decodes an entity-encoded string from a reader to a writer.
///
/// Similar to `decode_html`, except reading from a reader rather than a string, and
/// writing to a writer rather than returning a `String`.
///
/// # Arguments
/// - `reader` - UTF-8 encoded data is read from here.
/// - `writer` - UTF8- decoded data is written to here.
///
/// # Errors
/// Errors can be caused by IO errors, `reader` producing invalid UTF-8, or by syntax errors.
</span><span class="kw">pub fn </span>decode_html_rw&lt;R: BufRead, W: Write&gt;(reader: R, writer: <span class="kw-2">&amp;mut </span>W) -&gt; <span class="prelude-ty">Result</span>&lt;(), DecodeErr&gt; {
<span class="kw">let </span><span class="kw-2">mut </span>state: DecodeState = Normal;
<span class="kw">let </span><span class="kw-2">mut </span>pos = <span class="number">0</span>;
<span class="kw">let </span><span class="kw-2">mut </span>good_pos = <span class="number">0</span>;
<span class="kw">let </span><span class="kw-2">mut </span>buf = String::with_capacity(<span class="number">8</span>);
<span class="kw">for </span>c <span class="kw">in </span>io_support::chars(reader) {
<span class="kw">let </span>c = <span class="kw">match </span>c {
<span class="prelude-val">Err</span>(e) =&gt; {
<span class="kw">let </span>kind = <span class="kw">match </span>e {
CharsError::NotUtf8 =&gt; EncodingError,
CharsError::Other(io) =&gt; IoError(io)
};
<span class="kw">return </span><span class="prelude-val">Err</span>(DecodeErr{ position: pos, kind: kind });
}
<span class="prelude-val">Ok</span>(c) =&gt; c
};
<span class="kw">match </span>state {
Normal <span class="kw">if </span>c == <span class="string">&#39;&amp;&#39; </span>=&gt; state = Entity,
Normal =&gt; <span class="macro">try_dec_io!</span>(write_char(writer, c), good_pos),
Entity <span class="kw">if </span>c == <span class="string">&#39;#&#39; </span>=&gt; state = Numeric,
Entity <span class="kw">if </span>c == <span class="string">&#39;;&#39; </span>=&gt; <span class="kw">return </span><span class="prelude-val">Err</span>(DecodeErr{ position: good_pos, kind: UnknownEntity }),
Entity =&gt; {
state = Named;
buf.push(c);
}
Named <span class="kw">if </span>c == <span class="string">&#39;;&#39; </span>=&gt; {
state = Normal;
<span class="kw">let </span>ch = <span class="macro">try_parse!</span>(decode_named_entity(<span class="kw-2">&amp;</span>buf), good_pos);
<span class="macro">try_dec_io!</span>(write_char(writer, ch), good_pos);
buf.clear();
}
Named =&gt; buf.push(c),
Numeric <span class="kw">if </span>is_digit(c) =&gt; {
state = Dec;
buf.push(c);
}
Numeric <span class="kw">if </span>c == <span class="string">&#39;x&#39; </span>=&gt; state = Hex,
Dec <span class="kw">if </span>c == <span class="string">&#39;;&#39; </span>=&gt; {
state = Normal;
<span class="kw">let </span>ch = <span class="macro">try_parse!</span>(decode_numeric(<span class="kw-2">&amp;</span>buf, <span class="number">10</span>), good_pos);
<span class="macro">try_dec_io!</span>(write_char(writer, ch), good_pos);
buf.clear();
}
Hex <span class="kw">if </span>c == <span class="string">&#39;;&#39; </span>=&gt; {
state = Normal;
<span class="kw">let </span>ch = <span class="macro">try_parse!</span>(decode_numeric(<span class="kw-2">&amp;</span>buf, <span class="number">16</span>), good_pos);
<span class="macro">try_dec_io!</span>(write_char(writer, ch), good_pos);
buf.clear();
}
Hex <span class="kw">if </span>is_hex_digit(c) =&gt; buf.push(c),
Dec <span class="kw">if </span>is_digit(c) =&gt; buf.push(c),
Numeric | Hex | Dec =&gt; <span class="kw">return </span><span class="prelude-val">Err</span>(DecodeErr{ position: good_pos, kind: MalformedNumEscape}),
}
pos += <span class="number">1</span>;
<span class="kw">if </span>state == Normal {
good_pos = pos;
}
}
<span class="kw">if </span>state != Normal {
<span class="prelude-val">Err</span>(DecodeErr{ position: good_pos, kind: PrematureEnd})
} <span class="kw">else </span>{
<span class="prelude-val">Ok</span>(())
}
}
<span class="doccomment">/// Decodes an entity-encoded string.
///
/// Decodes an entity encoded string, replacing HTML entities (`&amp;amp;`, `&amp;#20;` ...) with the
/// the corresponding character. Case matters for named entities, ie. `&amp;Amp;` is invalid.
/// Case does not matter for hex entities, so `&amp;#x2E;` and `&amp;#x2e;` are treated the same.
///
/// # Arguments
/// - `s` - Entity-encoded string to decode.
///
/// # Failure
/// The function will fail if input string contains invalid named entities (eg. `&amp;nosuchentity;`),
/// invalid hex entities (eg. `&amp;#xRT;`), invalid decimal entities (eg. `&amp;#-1;), unclosed entities
/// (`s == &quot;&amp;amp hej och hå&quot;`) or otherwise malformed entities.
///
/// This function will never return errors with `kind` set to `IoError` or `EncodingError`.
</span><span class="kw">pub fn </span>decode_html(s: <span class="kw-2">&amp;</span>str) -&gt; <span class="prelude-ty">Result</span>&lt;String, DecodeErr&gt; {
<span class="kw">let </span><span class="kw-2">mut </span>writer = Vec::with_capacity(s.len());
<span class="kw">let </span>bytes = s.as_bytes();
<span class="kw">let </span><span class="kw-2">mut </span>reader = Cursor::new(bytes);
<span class="kw">let </span>res = decode_html_rw(<span class="kw-2">&amp;mut </span>reader, <span class="kw-2">&amp;mut </span>writer);
<span class="kw">match </span>res {
<span class="prelude-val">Ok</span>(<span class="kw">_</span>) =&gt; <span class="prelude-val">Ok</span>(String::from_utf8(writer).unwrap()),
<span class="prelude-val">Err</span>(err) =&gt; <span class="prelude-val">Err</span>(err)
}
}
<span class="kw">fn </span>is_digit(c: char) -&gt; bool { c &gt;= <span class="string">&#39;0&#39; </span>&amp;&amp; c &lt;= <span class="string">&#39;9&#39; </span>}
<span class="kw">fn </span>is_hex_digit(c: char) -&gt; bool {
is_digit(c) || (c &gt;= <span class="string">&#39;a&#39; </span>&amp;&amp; c &lt;= <span class="string">&#39;f&#39;</span>) || (c &gt;= <span class="string">&#39;A&#39; </span>&amp;&amp; c &lt;= <span class="string">&#39;F&#39;</span>)
}
<span class="kw">fn </span>decode_named_entity(entity: <span class="kw-2">&amp;</span>str) -&gt; <span class="prelude-ty">Result</span>&lt;char, DecodeErrKind&gt; {
<span class="kw">match </span>NAMED_ENTITIES.binary_search_by(|<span class="kw-2">&amp;</span>(ent, <span class="kw">_</span>)| ent.cmp(entity)) {
<span class="prelude-val">Err</span>(..) =&gt; <span class="prelude-val">Err</span>(UnknownEntity),
<span class="prelude-val">Ok</span>(idx) =&gt; {
<span class="kw">let </span>(<span class="kw">_</span>, c) = NAMED_ENTITIES[idx];
<span class="prelude-val">Ok</span>(c)
}
}
}
<span class="kw">fn </span>decode_numeric(esc: <span class="kw-2">&amp;</span>str, radix: u32) -&gt; <span class="prelude-ty">Result</span>&lt;char, DecodeErrKind&gt; {
<span class="kw">match </span>u32::from_str_radix(esc, radix) {
<span class="prelude-val">Ok</span>(n) =&gt; <span class="kw">match </span>char::from_u32(n) {
<span class="prelude-val">Some</span>(c) =&gt; <span class="prelude-val">Ok</span>(c),
<span class="prelude-val">None </span>=&gt; <span class="prelude-val">Err</span>(InvalidCharacter)
},
<span class="prelude-val">Err</span>(..) =&gt; <span class="prelude-val">Err</span>(MalformedNumEscape)
}
}
</code></pre></div>
</section></div></main><div id="rustdoc-vars" data-root-path="../../" data-current-crate="htmlescape" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html>