<!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 `src/lexer.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>lexer.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="mobile-topbar"><button class="sidebar-menu-toggle">☰</button><a class="sidebar-logo" href="../../llvm_kaleidoscope_rs/index.html"><div class="logo-container"><img class="rust-logo" src="../../rust-logo.svg" alt="logo"></div></a><h2 class="location"></h2></nav><nav class="sidebar"><a class="sidebar-logo" href="../../llvm_kaleidoscope_rs/index.html"><div class="logo-container"><img class="rust-logo" src="../../rust-logo.svg" alt="logo"></div></a></nav><main><div class="width-limiter"><div class="sub-container"><a class="sub-logo-container" href="../../llvm_kaleidoscope_rs/index.html"><img class="rust-logo" src="../../rust-logo.svg" alt="logo"></a><nav class="sub"><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"><button type="button">?</button></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></div><section id="main-content" class="content"><div class="example-wrap"><pre class="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>
</pre><pre class="rust"><code><span class="attribute">#[derive(Debug, PartialEq)]
</span><span class="kw">pub enum </span>Token {
Eof,
Def,
Extern,
Identifier(String),
Number(f64),
Char(char),
If,
Then,
Else,
For,
In,
}
<span class="kw">pub struct </span>Lexer<I>
<span class="kw">where
</span>I: Iterator<Item = char>,
{
input: I,
last_char: <span class="prelude-ty">Option</span><char>,
}
<span class="kw">impl</span><I> Lexer<I>
<span class="kw">where
</span>I: Iterator<Item = char>,
{
<span class="kw">pub fn </span>new(<span class="kw-2">mut </span>input: I) -> Lexer<I> {
<span class="kw">let </span>last_char = input.next();
Lexer { input, last_char }
}
<span class="kw">fn </span>step(<span class="kw-2">&mut </span><span class="self">self</span>) -> <span class="prelude-ty">Option</span><char> {
<span class="self">self</span>.last_char = <span class="self">self</span>.input.next();
<span class="self">self</span>.last_char
}
<span class="doccomment">/// Lex and return the next token.
///
/// Implement `int gettok();` from the tutorial.
</span><span class="kw">pub fn </span>gettok(<span class="kw-2">&mut </span><span class="self">self</span>) -> Token {
<span class="comment">// Eat up whitespaces.
</span><span class="kw">while </span><span class="macro">matches!</span>(<span class="self">self</span>.last_char, <span class="prelude-val">Some</span>(c) <span class="kw">if </span>c.is_ascii_whitespace()) {
<span class="self">self</span>.step();
}
<span class="comment">// Unpack last char or return EOF.
</span><span class="kw">let </span>last_char = <span class="kw">if let </span><span class="prelude-val">Some</span>(c) = <span class="self">self</span>.last_char {
c
} <span class="kw">else </span>{
<span class="kw">return </span>Token::Eof;
};
<span class="comment">// Identifier: [a-zA-Z][a-zA-Z0-9]*
</span><span class="kw">if </span>last_char.is_ascii_alphabetic() {
<span class="kw">let </span><span class="kw-2">mut </span>ident = String::new();
ident.push(last_char);
<span class="kw">while let </span><span class="prelude-val">Some</span>(c) = <span class="self">self</span>.step() {
<span class="kw">if </span>c.is_ascii_alphanumeric() {
ident.push(c)
} <span class="kw">else </span>{
<span class="kw">break</span>;
}
}
<span class="kw">match </span>ident.as_ref() {
<span class="string">"def" </span>=> <span class="kw">return </span>Token::Def,
<span class="string">"extern" </span>=> <span class="kw">return </span>Token::Extern,
<span class="string">"if" </span>=> <span class="kw">return </span>Token::If,
<span class="string">"then" </span>=> <span class="kw">return </span>Token::Then,
<span class="string">"else" </span>=> <span class="kw">return </span>Token::Else,
<span class="string">"for" </span>=> <span class="kw">return </span>Token::For,
<span class="string">"in" </span>=> <span class="kw">return </span>Token::In,
<span class="kw">_ </span>=> {}
}
<span class="kw">return </span>Token::Identifier(ident);
}
<span class="comment">// Number: [0-9.]+
</span><span class="kw">if </span>last_char.is_ascii_digit() || last_char == <span class="string">'.' </span>{
<span class="kw">let </span><span class="kw-2">mut </span>num = String::new();
num.push(last_char);
<span class="kw">while let </span><span class="prelude-val">Some</span>(c) = <span class="self">self</span>.step() {
<span class="kw">if </span>c.is_ascii_digit() || c == <span class="string">'.' </span>{
num.push(c)
} <span class="kw">else </span>{
<span class="kw">break</span>;
}
}
<span class="kw">let </span>num: f64 = num.parse().unwrap_or_default();
<span class="kw">return </span>Token::Number(num);
}
<span class="comment">// Eat up comment.
</span><span class="kw">if </span>last_char == <span class="string">'#' </span>{
<span class="kw">loop </span>{
<span class="kw">match </span><span class="self">self</span>.step() {
<span class="prelude-val">Some</span>(c) <span class="kw">if </span>c == <span class="string">'\r' </span>|| c == <span class="string">'\n' </span>=> <span class="kw">return </span><span class="self">self</span>.gettok(),
<span class="prelude-val">None </span>=> <span class="kw">return </span>Token::Eof,
<span class="kw">_ </span>=> { <span class="comment">/* consume comment */ </span>}
}
}
}
<span class="comment">// Advance last char and return currently last char.
</span><span class="self">self</span>.step();
Token::Char(last_char)
}
}
<span class="attribute">#[cfg(test)]
</span><span class="kw">mod </span>test {
<span class="kw">use super</span>::{Lexer, Token};
<span class="attribute">#[test]
</span><span class="kw">fn </span>test_identifier() {
<span class="kw">let </span><span class="kw-2">mut </span>lex = Lexer::new(<span class="string">"a b c"</span>.chars());
<span class="macro">assert_eq!</span>(Token::Identifier(<span class="string">"a"</span>.into()), lex.gettok());
<span class="macro">assert_eq!</span>(Token::Identifier(<span class="string">"b"</span>.into()), lex.gettok());
<span class="macro">assert_eq!</span>(Token::Identifier(<span class="string">"c"</span>.into()), lex.gettok());
<span class="macro">assert_eq!</span>(Token::Eof, lex.gettok());
}
<span class="attribute">#[test]
</span><span class="kw">fn </span>test_keyword() {
<span class="kw">let </span><span class="kw-2">mut </span>lex = Lexer::new(<span class="string">"def extern"</span>.chars());
<span class="macro">assert_eq!</span>(Token::Def, lex.gettok());
<span class="macro">assert_eq!</span>(Token::Extern, lex.gettok());
<span class="macro">assert_eq!</span>(Token::Eof, lex.gettok());
}
<span class="attribute">#[test]
</span><span class="kw">fn </span>test_number() {
<span class="kw">let </span><span class="kw-2">mut </span>lex = Lexer::new(<span class="string">"12.34"</span>.chars());
<span class="macro">assert_eq!</span>(Token::Number(<span class="number">12.34f64</span>), lex.gettok());
<span class="macro">assert_eq!</span>(Token::Eof, lex.gettok());
<span class="kw">let </span><span class="kw-2">mut </span>lex = Lexer::new(<span class="string">" 1.0 2.0 3.0"</span>.chars());
<span class="macro">assert_eq!</span>(Token::Number(<span class="number">1.0f64</span>), lex.gettok());
<span class="macro">assert_eq!</span>(Token::Number(<span class="number">2.0f64</span>), lex.gettok());
<span class="macro">assert_eq!</span>(Token::Number(<span class="number">3.0f64</span>), lex.gettok());
<span class="macro">assert_eq!</span>(Token::Eof, lex.gettok());
<span class="kw">let </span><span class="kw-2">mut </span>lex = Lexer::new(<span class="string">"12.34.56"</span>.chars());
<span class="macro">assert_eq!</span>(Token::Number(<span class="number">0f64</span>), lex.gettok());
<span class="macro">assert_eq!</span>(Token::Eof, lex.gettok());
}
<span class="attribute">#[test]
</span><span class="kw">fn </span>test_comment() {
<span class="kw">let </span><span class="kw-2">mut </span>lex = Lexer::new(<span class="string">"# some comment"</span>.chars());
<span class="macro">assert_eq!</span>(Token::Eof, lex.gettok());
<span class="kw">let </span><span class="kw-2">mut </span>lex = Lexer::new(<span class="string">"abc # some comment \n xyz"</span>.chars());
<span class="macro">assert_eq!</span>(Token::Identifier(<span class="string">"abc"</span>.into()), lex.gettok());
<span class="macro">assert_eq!</span>(Token::Identifier(<span class="string">"xyz"</span>.into()), lex.gettok());
<span class="macro">assert_eq!</span>(Token::Eof, lex.gettok());
}
<span class="attribute">#[test]
</span><span class="kw">fn </span>test_chars() {
<span class="kw">let </span><span class="kw-2">mut </span>lex = Lexer::new(<span class="string">"a+b-c"</span>.chars());
<span class="macro">assert_eq!</span>(Token::Identifier(<span class="string">"a"</span>.into()), lex.gettok());
<span class="macro">assert_eq!</span>(Token::Char(<span class="string">'+'</span>), lex.gettok());
<span class="macro">assert_eq!</span>(Token::Identifier(<span class="string">"b"</span>.into()), lex.gettok());
<span class="macro">assert_eq!</span>(Token::Char(<span class="string">'-'</span>), lex.gettok());
<span class="macro">assert_eq!</span>(Token::Identifier(<span class="string">"c"</span>.into()), lex.gettok());
<span class="macro">assert_eq!</span>(Token::Eof, lex.gettok());
}
<span class="attribute">#[test]
</span><span class="kw">fn </span>test_whitespaces() {
<span class="kw">let </span><span class="kw-2">mut </span>lex = Lexer::new(<span class="string">" +a b c! "</span>.chars());
<span class="macro">assert_eq!</span>(Token::Char(<span class="string">'+'</span>), lex.gettok());
<span class="macro">assert_eq!</span>(Token::Identifier(<span class="string">"a"</span>.into()), lex.gettok());
<span class="macro">assert_eq!</span>(Token::Identifier(<span class="string">"b"</span>.into()), lex.gettok());
<span class="macro">assert_eq!</span>(Token::Identifier(<span class="string">"c"</span>.into()), lex.gettok());
<span class="macro">assert_eq!</span>(Token::Char(<span class="string">'!'</span>), lex.gettok());
<span class="macro">assert_eq!</span>(Token::Eof, lex.gettok());
<span class="kw">let </span><span class="kw-2">mut </span>lex = Lexer::new(<span class="string">"\n a \n\r b \r \n c \r\r \n "</span>.chars());
<span class="macro">assert_eq!</span>(Token::Identifier(<span class="string">"a"</span>.into()), lex.gettok());
<span class="macro">assert_eq!</span>(Token::Identifier(<span class="string">"b"</span>.into()), lex.gettok());
<span class="macro">assert_eq!</span>(Token::Identifier(<span class="string">"c"</span>.into()), lex.gettok());
<span class="macro">assert_eq!</span>(Token::Eof, lex.gettok());
}
<span class="attribute">#[test]
</span><span class="kw">fn </span>test_ite() {
<span class="kw">let </span><span class="kw-2">mut </span>lex = Lexer::new(<span class="string">"if then else"</span>.chars());
<span class="macro">assert_eq!</span>(Token::If, lex.gettok());
<span class="macro">assert_eq!</span>(Token::Then, lex.gettok());
<span class="macro">assert_eq!</span>(Token::Else, lex.gettok());
}
<span class="attribute">#[test]
</span><span class="kw">fn </span>test_for() {
<span class="kw">let </span><span class="kw-2">mut </span>lex = Lexer::new(<span class="string">"for in"</span>.chars());
<span class="macro">assert_eq!</span>(Token::For, lex.gettok());
<span class="macro">assert_eq!</span>(Token::In, lex.gettok());
}
}
</code></pre></div>
</section></div></main><div id="rustdoc-vars" data-root-path="../../" data-current-crate="llvm_kaleidoscope_rs" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.65.0 (897e37553 2022-11-02)" ></div></body></html>
