<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"> <html xmlns="http://www.w3.org/1999/xhtml"> <head> <meta http-equiv="X-UA-Compatible" content="IE=Edge" /> <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> <title>2. Kaleidoscope: Implementing a Parser and AST — LLVM 8 documentation</title> <link rel="stylesheet" href="../_static/llvm-theme.css" type="text/css" /> <link rel="stylesheet" href="../_static/pygments.css" type="text/css" /> <script type="text/javascript" id="documentation_options" data-url_root="../" src="../_static/documentation_options.js"></script> <script type="text/javascript" src="../_static/jquery.js"></script> <script type="text/javascript" src="../_static/underscore.js"></script> <script type="text/javascript" src="../_static/doctools.js"></script> <script type="text/javascript" src="../_static/language_data.js"></script> <link rel="index" title="Index" href="../genindex.html" /> <link rel="search" title="Search" href="../search.html" /> <link rel="next" title="3. Kaleidoscope: Code generation to LLVM IR" href="OCamlLangImpl3.html" /> <link rel="prev" title="1. Kaleidoscope: Tutorial Introduction and the Lexer" href="OCamlLangImpl1.html" /> <style type="text/css"> table.right { float: right; margin-left: 20px; } table.right td { border: 1px solid #ccc; } </style> </head><body> <div class="logo"> <a href="../index.html"> <img src="../_static/logo.png" alt="LLVM Logo" width="250" height="88"/></a> </div> <div class="related" role="navigation" aria-label="related navigation"> <h3>Navigation</h3> <ul> <li class="right" style="margin-right: 10px"> <a href="../genindex.html" title="General Index" accesskey="I">index</a></li> <li class="right" > <a href="OCamlLangImpl3.html" title="3. Kaleidoscope: Code generation to LLVM IR" accesskey="N">next</a> |</li> <li class="right" > <a href="OCamlLangImpl1.html" title="1. Kaleidoscope: Tutorial Introduction and the Lexer" accesskey="P">previous</a> |</li> <li><a href="http://llvm.org/">LLVM Home</a> | </li> <li><a href="../index.html">Documentation</a>»</li> <li class="nav-item nav-item-1"><a href="index.html" accesskey="U">LLVM Tutorial: Table of Contents</a> »</li> </ul> </div> <div class="document"> <div class="documentwrapper"> <div class="body" role="main"> <div class="section" id="kaleidoscope-implementing-a-parser-and-ast"> <h1>2. Kaleidoscope: Implementing a Parser and AST<a class="headerlink" href="#kaleidoscope-implementing-a-parser-and-ast" title="Permalink to this headline">¶</a></h1> <div class="contents local topic" id="contents"> <ul class="simple"> <li><a class="reference internal" href="#chapter-2-introduction" id="id2">Chapter 2 Introduction</a></li> <li><a class="reference internal" href="#the-abstract-syntax-tree-ast" id="id3">The Abstract Syntax Tree (AST)</a></li> <li><a class="reference internal" href="#parser-basics" id="id4">Parser Basics</a></li> <li><a class="reference internal" href="#basic-expression-parsing" id="id5">Basic Expression Parsing</a></li> <li><a class="reference internal" href="#binary-expression-parsing" id="id6">Binary Expression Parsing</a></li> <li><a class="reference internal" href="#parsing-the-rest" id="id7">Parsing the Rest</a></li> <li><a class="reference internal" href="#the-driver" id="id8">The Driver</a></li> <li><a class="reference internal" href="#conclusions" id="id9">Conclusions</a></li> <li><a class="reference internal" href="#full-code-listing" id="id10">Full Code Listing</a></li> </ul> </div> <div class="section" id="chapter-2-introduction"> <h2><a class="toc-backref" href="#id2">2.1. Chapter 2 Introduction</a><a class="headerlink" href="#chapter-2-introduction" title="Permalink to this headline">¶</a></h2> <p>Welcome to Chapter 2 of the “<a class="reference external" href="index.html">Implementing a language with LLVM in Objective Caml</a>” tutorial. This chapter shows you how to use the lexer, built in <a class="reference external" href="OCamlLangImpl1.html">Chapter 1</a>, to build a full <a class="reference external" href="http://en.wikipedia.org/wiki/Parsing">parser</a> for our Kaleidoscope language. Once we have a parser, we’ll define and build an <a class="reference external" href="http://en.wikipedia.org/wiki/Abstract_syntax_tree">Abstract Syntax Tree</a> (AST).</p> <p>The parser we will build uses a combination of <a class="reference external" href="http://en.wikipedia.org/wiki/Recursive_descent_parser">Recursive Descent Parsing</a> and <a class="reference external" href="http://en.wikipedia.org/wiki/Operator-precedence_parser">Operator-Precedence Parsing</a> to parse the Kaleidoscope language (the latter for binary expressions and the former for everything else). Before we get to parsing though, lets talk about the output of the parser: the Abstract Syntax Tree.</p> </div> <div class="section" id="the-abstract-syntax-tree-ast"> <h2><a class="toc-backref" href="#id3">2.2. The Abstract Syntax Tree (AST)</a><a class="headerlink" href="#the-abstract-syntax-tree-ast" title="Permalink to this headline">¶</a></h2> <p>The AST for a program captures its behavior in such a way that it is easy for later stages of the compiler (e.g. code generation) to interpret. We basically want one object for each construct in the language, and the AST should closely model the language. In Kaleidoscope, we have expressions, a prototype, and a function object. We’ll start with expressions first:</p> <div class="highlight-ocaml notranslate"><div class="highlight"><pre><span></span><span class="c">(* expr - Base type for all expression nodes. *)</span> <span class="k">type</span> <span class="n">expr</span> <span class="o">=</span> <span class="c">(* variant for numeric literals like "1.0". *)</span> <span class="o">|</span> <span class="nc">Number</span> <span class="k">of</span> <span class="kt">float</span> </pre></div> </div> <p>The code above shows the definition of the base ExprAST class and one subclass which we use for numeric literals. The important thing to note about this code is that the Number variant captures the numeric value of the literal as an instance variable. This allows later phases of the compiler to know what the stored numeric value is.</p> <p>Right now we only create the AST, so there are no useful functions on them. It would be very easy to add a function to pretty print the code, for example. Here are the other expression AST node definitions that we’ll use in the basic form of the Kaleidoscope language:</p> <div class="highlight-ocaml notranslate"><div class="highlight"><pre><span></span><span class="c">(* variant for referencing a variable, like "a". *)</span> <span class="o">|</span> <span class="nc">Variable</span> <span class="k">of</span> <span class="kt">string</span> <span class="c">(* variant for a binary operator. *)</span> <span class="o">|</span> <span class="nc">Binary</span> <span class="k">of</span> <span class="kt">char</span> <span class="o">*</span> <span class="n">expr</span> <span class="o">*</span> <span class="n">expr</span> <span class="c">(* variant for function calls. *)</span> <span class="o">|</span> <span class="nc">Call</span> <span class="k">of</span> <span class="kt">string</span> <span class="o">*</span> <span class="n">expr</span> <span class="kt">array</span> </pre></div> </div> <p>This is all (intentionally) rather straight-forward: variables capture the variable name, binary operators capture their opcode (e.g. ‘+’), and calls capture a function name as well as a list of any argument expressions. One thing that is nice about our AST is that it captures the language features without talking about the syntax of the language. Note that there is no discussion about precedence of binary operators, lexical structure, etc.</p> <p>For our basic language, these are all of the expression nodes we’ll define. Because it doesn’t have conditional control flow, it isn’t Turing-complete; we’ll fix that in a later installment. The two things we need next are a way to talk about the interface to a function, and a way to talk about functions themselves:</p> <div class="highlight-ocaml notranslate"><div class="highlight"><pre><span></span><span class="c">(* proto - This type represents the "prototype" for a function, which captures</span> <span class="c"> * its name, and its argument names (thus implicitly the number of arguments the</span> <span class="c"> * function takes). *)</span> <span class="k">type</span> <span class="n">proto</span> <span class="o">=</span> <span class="nc">Prototype</span> <span class="k">of</span> <span class="kt">string</span> <span class="o">*</span> <span class="kt">string</span> <span class="kt">array</span> <span class="c">(* func - This type represents a function definition itself. *)</span> <span class="k">type</span> <span class="n">func</span> <span class="o">=</span> <span class="nc">Function</span> <span class="k">of</span> <span class="n">proto</span> <span class="o">*</span> <span class="n">expr</span> </pre></div> </div> <p>In Kaleidoscope, functions are typed with just a count of their arguments. Since all values are double precision floating point, the type of each argument doesn’t need to be stored anywhere. In a more aggressive and realistic language, the “expr” variants would probably have a type field.</p> <p>With this scaffolding, we can now talk about parsing expressions and function bodies in Kaleidoscope.</p> </div> <div class="section" id="parser-basics"> <h2><a class="toc-backref" href="#id4">2.3. Parser Basics</a><a class="headerlink" href="#parser-basics" title="Permalink to this headline">¶</a></h2> <p>Now that we have an AST to build, we need to define the parser code to build it. The idea here is that we want to parse something like “x+y” (which is returned as three tokens by the lexer) into an AST that could be generated with calls like this:</p> <div class="highlight-ocaml notranslate"><div class="highlight"><pre><span></span><span class="k">let</span> <span class="n">x</span> <span class="o">=</span> <span class="nc">Variable</span> <span class="s2">"x"</span> <span class="k">in</span> <span class="k">let</span> <span class="n">y</span> <span class="o">=</span> <span class="nc">Variable</span> <span class="s2">"y"</span> <span class="k">in</span> <span class="k">let</span> <span class="n">result</span> <span class="o">=</span> <span class="nc">Binary</span> <span class="o">(</span><span class="sc">'+'</span><span class="o">,</span> <span class="n">x</span><span class="o">,</span> <span class="n">y</span><span class="o">)</span> <span class="k">in</span> <span class="o">...</span> </pre></div> </div> <p>The error handling routines make use of the builtin <code class="docutils literal notranslate"><span class="pre">Stream.Failure</span></code> and <code class="docutils literal notranslate"><span class="pre">Stream.Error``s.</span> <span class="pre">``Stream.Failure</span></code> is raised when the parser is unable to find any matching token in the first position of a pattern. <code class="docutils literal notranslate"><span class="pre">Stream.Error</span></code> is raised when the first token matches, but the rest do not. The error recovery in our parser will not be the best and is not particular user-friendly, but it will be enough for our tutorial. These exceptions make it easier to handle errors in routines that have various return types.</p> <p>With these basic types and exceptions, we can implement the first piece of our grammar: numeric literals.</p> </div> <div class="section" id="basic-expression-parsing"> <h2><a class="toc-backref" href="#id5">2.4. Basic Expression Parsing</a><a class="headerlink" href="#basic-expression-parsing" title="Permalink to this headline">¶</a></h2> <p>We start with numeric literals, because they are the simplest to process. For each production in our grammar, we’ll define a function which parses that production. We call this class of expressions “primary” expressions, for reasons that will become more clear <a class="reference external" href="OCamlLangImpl6.html#user-defined-unary-operators">later in the tutorial</a>. In order to parse an arbitrary primary expression, we need to determine what sort of expression it is. For numeric literals, we have:</p> <div class="highlight-ocaml notranslate"><div class="highlight"><pre><span></span><span class="c">(* primary</span> <span class="c"> * ::= identifier</span> <span class="c"> * ::= numberexpr</span> <span class="c"> * ::= parenexpr *)</span> <span class="n">parse_primary</span> <span class="o">=</span> <span class="n">parser</span> <span class="c">(* numberexpr ::= number *)</span> <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Number</span> <span class="n">n</span> <span class="o">>]</span> <span class="o">-></span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Number</span> <span class="n">n</span> </pre></div> </div> <p>This routine is very simple: it expects to be called when the current token is a <code class="docutils literal notranslate"><span class="pre">Token.Number</span></code> token. It takes the current number value, creates a <code class="docutils literal notranslate"><span class="pre">Ast.Number</span></code> node, advances the lexer to the next token, and finally returns.</p> <p>There are some interesting aspects to this. The most important one is that this routine eats all of the tokens that correspond to the production and returns the lexer buffer with the next token (which is not part of the grammar production) ready to go. This is a fairly standard way to go for recursive descent parsers. For a better example, the parenthesis operator is defined like this:</p> <div class="highlight-ocaml notranslate"><div class="highlight"><pre><span></span><span class="c">(* parenexpr ::= '(' expression ')' *)</span> <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">'('</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_expr</span><span class="o">;</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">')'</span> <span class="o">??</span> <span class="s2">"expected ')'"</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span> </pre></div> </div> <p>This function illustrates a number of interesting things about the parser:</p> <p>1) It shows how we use the <code class="docutils literal notranslate"><span class="pre">Stream.Error</span></code> exception. When called, this function expects that the current token is a ‘(‘ token, but after parsing the subexpression, it is possible that there is no ‘)’ waiting. For example, if the user types in “(4 x” instead of “(4)”, the parser should emit an error. Because errors can occur, the parser needs a way to indicate that they happened. In our parser, we use the camlp4 shortcut syntax <code class="docutils literal notranslate"><span class="pre">token</span> <span class="pre">??</span> <span class="pre">"parse</span> <span class="pre">error"</span></code>, where if the token before the <code class="docutils literal notranslate"><span class="pre">??</span></code> does not match, then <code class="docutils literal notranslate"><span class="pre">Stream.Error</span> <span class="pre">"parse</span> <span class="pre">error"</span></code> will be raised.</p> <p>2) Another interesting aspect of this function is that it uses recursion by calling <code class="docutils literal notranslate"><span class="pre">Parser.parse_primary</span></code> (we will soon see that <code class="docutils literal notranslate"><span class="pre">Parser.parse_primary</span></code> can call <code class="docutils literal notranslate"><span class="pre">Parser.parse_primary</span></code>). This is powerful because it allows us to handle recursive grammars, and keeps each production very simple. Note that parentheses do not cause construction of AST nodes themselves. While we could do it this way, the most important role of parentheses are to guide the parser and provide grouping. Once the parser constructs the AST, parentheses are not needed.</p> <p>The next simple production is for handling variable references and function calls:</p> <div class="highlight-ocaml notranslate"><div class="highlight"><pre><span></span><span class="c">(* identifierexpr</span> <span class="c"> * ::= identifier</span> <span class="c"> * ::= identifier '(' argumentexpr ')' *)</span> <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Ident</span> <span class="n">id</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span> <span class="k">let</span> <span class="k">rec</span> <span class="n">parse_args</span> <span class="n">accumulator</span> <span class="o">=</span> <span class="n">parser</span> <span class="o">|</span> <span class="o">[<</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_expr</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span> <span class="k">begin</span> <span class="n">parser</span> <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">','</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_args</span> <span class="o">(</span><span class="n">e</span> <span class="o">::</span> <span class="n">accumulator</span><span class="o">)</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span> <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span> <span class="o">::</span> <span class="n">accumulator</span> <span class="k">end</span> <span class="n">stream</span> <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">accumulator</span> <span class="k">in</span> <span class="k">let</span> <span class="k">rec</span> <span class="n">parse_ident</span> <span class="n">id</span> <span class="o">=</span> <span class="n">parser</span> <span class="c">(* Call. *)</span> <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">'('</span><span class="o">;</span> <span class="n">args</span><span class="o">=</span><span class="n">parse_args</span> <span class="bp">[]</span><span class="o">;</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">')'</span> <span class="o">??</span> <span class="s2">"expected ')'"</span><span class="o">>]</span> <span class="o">-></span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Call</span> <span class="o">(</span><span class="n">id</span><span class="o">,</span> <span class="nn">Array</span><span class="p">.</span><span class="n">of_list</span> <span class="o">(</span><span class="nn">List</span><span class="p">.</span><span class="n">rev</span> <span class="n">args</span><span class="o">))</span> <span class="c">(* Simple variable ref. *)</span> <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Variable</span> <span class="n">id</span> <span class="k">in</span> <span class="n">parse_ident</span> <span class="n">id</span> <span class="n">stream</span> </pre></div> </div> <p>This routine follows the same style as the other routines. (It expects to be called if the current token is a <code class="docutils literal notranslate"><span class="pre">Token.Ident</span></code> token). It also has recursion and error handling. One interesting aspect of this is that it uses <em>look-ahead</em> to determine if the current identifier is a stand alone variable reference or if it is a function call expression. It handles this by checking to see if the token after the identifier is a ‘(‘ token, constructing either a <code class="docutils literal notranslate"><span class="pre">Ast.Variable</span></code> or <code class="docutils literal notranslate"><span class="pre">Ast.Call</span></code> node as appropriate.</p> <p>We finish up by raising an exception if we received a token we didn’t expect:</p> <div class="highlight-ocaml notranslate"><div class="highlight"><pre><span></span><span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="k">raise</span> <span class="o">(</span><span class="nn">Stream</span><span class="p">.</span><span class="nc">Error</span> <span class="s2">"unknown token when expecting an expression."</span><span class="o">)</span> </pre></div> </div> <p>Now that basic expressions are handled, we need to handle binary expressions. They are a bit more complex.</p> </div> <div class="section" id="binary-expression-parsing"> <h2><a class="toc-backref" href="#id6">2.5. Binary Expression Parsing</a><a class="headerlink" href="#binary-expression-parsing" title="Permalink to this headline">¶</a></h2> <p>Binary expressions are significantly harder to parse because they are often ambiguous. For example, when given the string “x+y*z”, the parser can choose to parse it as either “(x+y)*z” or “x+(y*z)”. With common definitions from mathematics, we expect the later parse, because “*” (multiplication) has higher <em>precedence</em> than “+” (addition).</p> <p>There are many ways to handle this, but an elegant and efficient way is to use <a class="reference external" href="http://en.wikipedia.org/wiki/Operator-precedence_parser">Operator-Precedence Parsing</a>. This parsing technique uses the precedence of binary operators to guide recursion. To start with, we need a table of precedences:</p> <div class="highlight-ocaml notranslate"><div class="highlight"><pre><span></span><span class="c">(* binop_precedence - This holds the precedence for each binary operator that is</span> <span class="c"> * defined *)</span> <span class="k">let</span> <span class="n">binop_precedence</span><span class="o">:(</span><span class="kt">char</span><span class="o">,</span> <span class="kt">int</span><span class="o">)</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">t</span> <span class="o">=</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">create</span> <span class="mi">10</span> <span class="c">(* precedence - Get the precedence of the pending binary operator token. *)</span> <span class="k">let</span> <span class="n">precedence</span> <span class="n">c</span> <span class="o">=</span> <span class="k">try</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">find</span> <span class="n">binop_precedence</span> <span class="n">c</span> <span class="k">with</span> <span class="nc">Not_found</span> <span class="o">-></span> <span class="o">-</span><span class="mi">1</span> <span class="o">...</span> <span class="k">let</span> <span class="n">main</span> <span class="bp">()</span> <span class="o">=</span> <span class="c">(* Install standard binary operators.</span> <span class="c"> * 1 is the lowest precedence. *)</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">binop_precedence</span> <span class="sc">'<'</span> <span class="mi">10</span><span class="o">;</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">binop_precedence</span> <span class="sc">'+'</span> <span class="mi">20</span><span class="o">;</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">binop_precedence</span> <span class="sc">'-'</span> <span class="mi">20</span><span class="o">;</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">binop_precedence</span> <span class="sc">'*'</span> <span class="mi">40</span><span class="o">;</span> <span class="c">(* highest. *)</span> <span class="o">...</span> </pre></div> </div> <p>For the basic form of Kaleidoscope, we will only support 4 binary operators (this can obviously be extended by you, our brave and intrepid reader). The <code class="docutils literal notranslate"><span class="pre">Parser.precedence</span></code> function returns the precedence for the current token, or -1 if the token is not a binary operator. Having a <code class="docutils literal notranslate"><span class="pre">Hashtbl.t</span></code> makes it easy to add new operators and makes it clear that the algorithm doesn’t depend on the specific operators involved, but it would be easy enough to eliminate the <code class="docutils literal notranslate"><span class="pre">Hashtbl.t</span></code> and do the comparisons in the <code class="docutils literal notranslate"><span class="pre">Parser.precedence</span></code> function. (Or just use a fixed-size array).</p> <p>With the helper above defined, we can now start parsing binary expressions. The basic idea of operator precedence parsing is to break down an expression with potentially ambiguous binary operators into pieces. Consider, for example, the expression “a+b+(c+d)*e*f+g”. Operator precedence parsing considers this as a stream of primary expressions separated by binary operators. As such, it will first parse the leading primary expression “a”, then it will see the pairs [+, b] [+, (c+d)] [*, e] [*, f] and [+, g]. Note that because parentheses are primary expressions, the binary expression parser doesn’t need to worry about nested subexpressions like (c+d) at all.</p> <p>To start, an expression is a primary expression potentially followed by a sequence of [binop,primaryexpr] pairs:</p> <div class="highlight-ocaml notranslate"><div class="highlight"><pre><span></span><span class="c">(* expression</span> <span class="c"> * ::= primary binoprhs *)</span> <span class="ow">and</span> <span class="n">parse_expr</span> <span class="o">=</span> <span class="n">parser</span> <span class="o">|</span> <span class="o">[<</span> <span class="n">lhs</span><span class="o">=</span><span class="n">parse_primary</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">parse_bin_rhs</span> <span class="mi">0</span> <span class="n">lhs</span> <span class="n">stream</span> </pre></div> </div> <p><code class="docutils literal notranslate"><span class="pre">Parser.parse_bin_rhs</span></code> is the function that parses the sequence of pairs for us. It takes a precedence and a pointer to an expression for the part that has been parsed so far. Note that “x” is a perfectly valid expression: As such, “binoprhs” is allowed to be empty, in which case it returns the expression that is passed into it. In our example above, the code passes the expression for “a” into <code class="docutils literal notranslate"><span class="pre">Parser.parse_bin_rhs</span></code> and the current token is “+”.</p> <p>The precedence value passed into <code class="docutils literal notranslate"><span class="pre">Parser.parse_bin_rhs</span></code> indicates the <em>minimal operator precedence</em> that the function is allowed to eat. For example, if the current pair stream is [+, x] and <code class="docutils literal notranslate"><span class="pre">Parser.parse_bin_rhs</span></code> is passed in a precedence of 40, it will not consume any tokens (because the precedence of ‘+’ is only 20). With this in mind, <code class="docutils literal notranslate"><span class="pre">Parser.parse_bin_rhs</span></code> starts with:</p> <div class="highlight-ocaml notranslate"><div class="highlight"><pre><span></span><span class="c">(* binoprhs</span> <span class="c"> * ::= ('+' primary)* *)</span> <span class="ow">and</span> <span class="n">parse_bin_rhs</span> <span class="n">expr_prec</span> <span class="n">lhs</span> <span class="n">stream</span> <span class="o">=</span> <span class="k">match</span> <span class="nn">Stream</span><span class="p">.</span><span class="n">peek</span> <span class="n">stream</span> <span class="k">with</span> <span class="c">(* If this is a binop, find its precedence. *)</span> <span class="o">|</span> <span class="nc">Some</span> <span class="o">(</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="n">c</span><span class="o">)</span> <span class="k">when</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">mem</span> <span class="n">binop_precedence</span> <span class="n">c</span> <span class="o">-></span> <span class="k">let</span> <span class="n">token_prec</span> <span class="o">=</span> <span class="n">precedence</span> <span class="n">c</span> <span class="k">in</span> <span class="c">(* If this is a binop that binds at least as tightly as the current binop,</span> <span class="c"> * consume it, otherwise we are done. *)</span> <span class="k">if</span> <span class="n">token_prec</span> <span class="o"><</span> <span class="n">expr_prec</span> <span class="k">then</span> <span class="n">lhs</span> <span class="k">else</span> <span class="k">begin</span> </pre></div> </div> <p>This code gets the precedence of the current token and checks to see if if is too low. Because we defined invalid tokens to have a precedence of -1, this check implicitly knows that the pair-stream ends when the token stream runs out of binary operators. If this check succeeds, we know that the token is a binary operator and that it will be included in this expression:</p> <div class="highlight-ocaml notranslate"><div class="highlight"><pre><span></span><span class="c">(* Eat the binop. *)</span> <span class="nn">Stream</span><span class="p">.</span><span class="n">junk</span> <span class="n">stream</span><span class="o">;</span> <span class="c">(* Parse the primary expression after the binary operator *)</span> <span class="k">let</span> <span class="n">rhs</span> <span class="o">=</span> <span class="n">parse_primary</span> <span class="n">stream</span> <span class="k">in</span> <span class="c">(* Okay, we know this is a binop. *)</span> <span class="k">let</span> <span class="n">rhs</span> <span class="o">=</span> <span class="k">match</span> <span class="nn">Stream</span><span class="p">.</span><span class="n">peek</span> <span class="n">stream</span> <span class="k">with</span> <span class="o">|</span> <span class="nc">Some</span> <span class="o">(</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="n">c2</span><span class="o">)</span> <span class="o">-></span> </pre></div> </div> <p>As such, this code eats (and remembers) the binary operator and then parses the primary expression that follows. This builds up the whole pair, the first of which is [+, b] for the running example.</p> <p>Now that we parsed the left-hand side of an expression and one pair of the RHS sequence, we have to decide which way the expression associates. In particular, we could have “(a+b) binop unparsed” or “a + (b binop unparsed)”. To determine this, we look ahead at “binop” to determine its precedence and compare it to BinOp’s precedence (which is ‘+’ in this case):</p> <div class="highlight-ocaml notranslate"><div class="highlight"><pre><span></span><span class="c">(* If BinOp binds less tightly with rhs than the operator after</span> <span class="c"> * rhs, let the pending operator take rhs as its lhs. *)</span> <span class="k">let</span> <span class="n">next_prec</span> <span class="o">=</span> <span class="n">precedence</span> <span class="n">c2</span> <span class="k">in</span> <span class="k">if</span> <span class="n">token_prec</span> <span class="o"><</span> <span class="n">next_prec</span> </pre></div> </div> <p>If the precedence of the binop to the right of “RHS” is lower or equal to the precedence of our current operator, then we know that the parentheses associate as “(a+b) binop …”. In our example, the current operator is “+” and the next operator is “+”, we know that they have the same precedence. In this case we’ll create the AST node for “a+b”, and then continue parsing:</p> <div class="highlight-ocaml notranslate"><div class="highlight"><pre><span></span> <span class="o">...</span> <span class="k">if</span> <span class="n">body</span> <span class="n">omitted</span> <span class="o">...</span> <span class="k">in</span> <span class="c">(* Merge lhs/rhs. *)</span> <span class="k">let</span> <span class="n">lhs</span> <span class="o">=</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Binary</span> <span class="o">(</span><span class="n">c</span><span class="o">,</span> <span class="n">lhs</span><span class="o">,</span> <span class="n">rhs</span><span class="o">)</span> <span class="k">in</span> <span class="n">parse_bin_rhs</span> <span class="n">expr_prec</span> <span class="n">lhs</span> <span class="n">stream</span> <span class="k">end</span> </pre></div> </div> <p>In our example above, this will turn “a+b+” into “(a+b)” and execute the next iteration of the loop, with “+” as the current token. The code above will eat, remember, and parse “(c+d)” as the primary expression, which makes the current pair equal to [+, (c+d)]. It will then evaluate the ‘if’ conditional above with “*” as the binop to the right of the primary. In this case, the precedence of “*” is higher than the precedence of “+” so the if condition will be entered.</p> <p>The critical question left here is “how can the if condition parse the right hand side in full”? In particular, to build the AST correctly for our example, it needs to get all of “(c+d)*e*f” as the RHS expression variable. The code to do this is surprisingly simple (code from the above two blocks duplicated for context):</p> <div class="highlight-ocaml notranslate"><div class="highlight"><pre><span></span> <span class="k">match</span> <span class="nn">Stream</span><span class="p">.</span><span class="n">peek</span> <span class="n">stream</span> <span class="k">with</span> <span class="o">|</span> <span class="nc">Some</span> <span class="o">(</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="n">c2</span><span class="o">)</span> <span class="o">-></span> <span class="c">(* If BinOp binds less tightly with rhs than the operator after</span> <span class="c"> * rhs, let the pending operator take rhs as its lhs. *)</span> <span class="k">if</span> <span class="n">token_prec</span> <span class="o"><</span> <span class="n">precedence</span> <span class="n">c2</span> <span class="k">then</span> <span class="n">parse_bin_rhs</span> <span class="o">(</span><span class="n">token_prec</span> <span class="o">+</span> <span class="mi">1</span><span class="o">)</span> <span class="n">rhs</span> <span class="n">stream</span> <span class="k">else</span> <span class="n">rhs</span> <span class="o">|</span> <span class="o">_</span> <span class="o">-></span> <span class="n">rhs</span> <span class="k">in</span> <span class="c">(* Merge lhs/rhs. *)</span> <span class="k">let</span> <span class="n">lhs</span> <span class="o">=</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Binary</span> <span class="o">(</span><span class="n">c</span><span class="o">,</span> <span class="n">lhs</span><span class="o">,</span> <span class="n">rhs</span><span class="o">)</span> <span class="k">in</span> <span class="n">parse_bin_rhs</span> <span class="n">expr_prec</span> <span class="n">lhs</span> <span class="n">stream</span> <span class="k">end</span> </pre></div> </div> <p>At this point, we know that the binary operator to the RHS of our primary has higher precedence than the binop we are currently parsing. As such, we know that any sequence of pairs whose operators are all higher precedence than “+” should be parsed together and returned as “RHS”. To do this, we recursively invoke the <code class="docutils literal notranslate"><span class="pre">Parser.parse_bin_rhs</span></code> function specifying “token_prec+1” as the minimum precedence required for it to continue. In our example above, this will cause it to return the AST node for “(c+d)*e*f” as RHS, which is then set as the RHS of the ‘+’ expression.</p> <p>Finally, on the next iteration of the while loop, the “+g” piece is parsed and added to the AST. With this little bit of code (14 non-trivial lines), we correctly handle fully general binary expression parsing in a very elegant way. This was a whirlwind tour of this code, and it is somewhat subtle. I recommend running through it with a few tough examples to see how it works.</p> <p>This wraps up handling of expressions. At this point, we can point the parser at an arbitrary token stream and build an expression from it, stopping at the first token that is not part of the expression. Next up we need to handle function definitions, etc.</p> </div> <div class="section" id="parsing-the-rest"> <h2><a class="toc-backref" href="#id7">2.6. Parsing the Rest</a><a class="headerlink" href="#parsing-the-rest" title="Permalink to this headline">¶</a></h2> <p>The next thing missing is handling of function prototypes. In Kaleidoscope, these are used both for ‘extern’ function declarations as well as function body definitions. The code to do this is straight-forward and not very interesting (once you’ve survived expressions):</p> <div class="highlight-ocaml notranslate"><div class="highlight"><pre><span></span><span class="c">(* prototype</span> <span class="c"> * ::= id '(' id* ')' *)</span> <span class="k">let</span> <span class="n">parse_prototype</span> <span class="o">=</span> <span class="k">let</span> <span class="k">rec</span> <span class="n">parse_args</span> <span class="n">accumulator</span> <span class="o">=</span> <span class="n">parser</span> <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Ident</span> <span class="n">id</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_args</span> <span class="o">(</span><span class="n">id</span><span class="o">::</span><span class="n">accumulator</span><span class="o">)</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span> <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">accumulator</span> <span class="k">in</span> <span class="n">parser</span> <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Ident</span> <span class="n">id</span><span class="o">;</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">'('</span> <span class="o">??</span> <span class="s2">"expected '(' in prototype"</span><span class="o">;</span> <span class="n">args</span><span class="o">=</span><span class="n">parse_args</span> <span class="bp">[]</span><span class="o">;</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">')'</span> <span class="o">??</span> <span class="s2">"expected ')' in prototype"</span> <span class="o">>]</span> <span class="o">-></span> <span class="c">(* success. *)</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Prototype</span> <span class="o">(</span><span class="n">id</span><span class="o">,</span> <span class="nn">Array</span><span class="p">.</span><span class="n">of_list</span> <span class="o">(</span><span class="nn">List</span><span class="p">.</span><span class="n">rev</span> <span class="n">args</span><span class="o">))</span> <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="k">raise</span> <span class="o">(</span><span class="nn">Stream</span><span class="p">.</span><span class="nc">Error</span> <span class="s2">"expected function name in prototype"</span><span class="o">)</span> </pre></div> </div> <p>Given this, a function definition is very simple, just a prototype plus an expression to implement the body:</p> <div class="highlight-ocaml notranslate"><div class="highlight"><pre><span></span><span class="c">(* definition ::= 'def' prototype expression *)</span> <span class="k">let</span> <span class="n">parse_definition</span> <span class="o">=</span> <span class="n">parser</span> <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Def</span><span class="o">;</span> <span class="n">p</span><span class="o">=</span><span class="n">parse_prototype</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_expr</span> <span class="o">>]</span> <span class="o">-></span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Function</span> <span class="o">(</span><span class="n">p</span><span class="o">,</span> <span class="n">e</span><span class="o">)</span> </pre></div> </div> <p>In addition, we support ‘extern’ to declare functions like ‘sin’ and ‘cos’ as well as to support forward declaration of user functions. These ‘extern’s are just prototypes with no body:</p> <div class="highlight-ocaml notranslate"><div class="highlight"><pre><span></span><span class="c">(* external ::= 'extern' prototype *)</span> <span class="k">let</span> <span class="n">parse_extern</span> <span class="o">=</span> <span class="n">parser</span> <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Extern</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_prototype</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span> </pre></div> </div> <p>Finally, we’ll also let the user type in arbitrary top-level expressions and evaluate them on the fly. We will handle this by defining anonymous nullary (zero argument) functions for them:</p> <div class="highlight-ocaml notranslate"><div class="highlight"><pre><span></span><span class="c">(* toplevelexpr ::= expression *)</span> <span class="k">let</span> <span class="n">parse_toplevel</span> <span class="o">=</span> <span class="n">parser</span> <span class="o">|</span> <span class="o">[<</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_expr</span> <span class="o">>]</span> <span class="o">-></span> <span class="c">(* Make an anonymous proto. *)</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Function</span> <span class="o">(</span><span class="nn">Ast</span><span class="p">.</span><span class="nc">Prototype</span> <span class="o">(</span><span class="s2">""</span><span class="o">,</span> <span class="o">[||]),</span> <span class="n">e</span><span class="o">)</span> </pre></div> </div> <p>Now that we have all the pieces, let’s build a little driver that will let us actually <em>execute</em> this code we’ve built!</p> </div> <div class="section" id="the-driver"> <h2><a class="toc-backref" href="#id8">2.7. The Driver</a><a class="headerlink" href="#the-driver" title="Permalink to this headline">¶</a></h2> <p>The driver for this simply invokes all of the parsing pieces with a top-level dispatch loop. There isn’t much interesting here, so I’ll just include the top-level loop. See <a class="reference external" href="#full-code-listing">below</a> for full code in the “Top-Level Parsing” section.</p> <div class="highlight-ocaml notranslate"><div class="highlight"><pre><span></span><span class="c">(* top ::= definition | external | expression | ';' *)</span> <span class="k">let</span> <span class="k">rec</span> <span class="n">main_loop</span> <span class="n">stream</span> <span class="o">=</span> <span class="k">match</span> <span class="nn">Stream</span><span class="p">.</span><span class="n">peek</span> <span class="n">stream</span> <span class="k">with</span> <span class="o">|</span> <span class="nc">None</span> <span class="o">-></span> <span class="bp">()</span> <span class="c">(* ignore top-level semicolons. *)</span> <span class="o">|</span> <span class="nc">Some</span> <span class="o">(</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">';'</span><span class="o">)</span> <span class="o">-></span> <span class="nn">Stream</span><span class="p">.</span><span class="n">junk</span> <span class="n">stream</span><span class="o">;</span> <span class="n">main_loop</span> <span class="n">stream</span> <span class="o">|</span> <span class="nc">Some</span> <span class="n">token</span> <span class="o">-></span> <span class="k">begin</span> <span class="k">try</span> <span class="k">match</span> <span class="n">token</span> <span class="k">with</span> <span class="o">|</span> <span class="nn">Token</span><span class="p">.</span><span class="nc">Def</span> <span class="o">-></span> <span class="n">ignore</span><span class="o">(</span><span class="nn">Parser</span><span class="p">.</span><span class="n">parse_definition</span> <span class="n">stream</span><span class="o">);</span> <span class="n">print_endline</span> <span class="s2">"parsed a function definition."</span><span class="o">;</span> <span class="o">|</span> <span class="nn">Token</span><span class="p">.</span><span class="nc">Extern</span> <span class="o">-></span> <span class="n">ignore</span><span class="o">(</span><span class="nn">Parser</span><span class="p">.</span><span class="n">parse_extern</span> <span class="n">stream</span><span class="o">);</span> <span class="n">print_endline</span> <span class="s2">"parsed an extern."</span><span class="o">;</span> <span class="o">|</span> <span class="o">_</span> <span class="o">-></span> <span class="c">(* Evaluate a top-level expression into an anonymous function. *)</span> <span class="n">ignore</span><span class="o">(</span><span class="nn">Parser</span><span class="p">.</span><span class="n">parse_toplevel</span> <span class="n">stream</span><span class="o">);</span> <span class="n">print_endline</span> <span class="s2">"parsed a top-level expr"</span><span class="o">;</span> <span class="k">with</span> <span class="nn">Stream</span><span class="p">.</span><span class="nc">Error</span> <span class="n">s</span> <span class="o">-></span> <span class="c">(* Skip token for error recovery. *)</span> <span class="nn">Stream</span><span class="p">.</span><span class="n">junk</span> <span class="n">stream</span><span class="o">;</span> <span class="n">print_endline</span> <span class="n">s</span><span class="o">;</span> <span class="k">end</span><span class="o">;</span> <span class="n">print_string</span> <span class="s2">"ready> "</span><span class="o">;</span> <span class="n">flush</span> <span class="n">stdout</span><span class="o">;</span> <span class="n">main_loop</span> <span class="n">stream</span> </pre></div> </div> <p>The most interesting part of this is that we ignore top-level semicolons. Why is this, you ask? The basic reason is that if you type “4 + 5” at the command line, the parser doesn’t know whether that is the end of what you will type or not. For example, on the next line you could type “def foo…” in which case 4+5 is the end of a top-level expression. Alternatively you could type “* 6”, which would continue the expression. Having top-level semicolons allows you to type “4+5;”, and the parser will know you are done.</p> </div> <div class="section" id="conclusions"> <h2><a class="toc-backref" href="#id9">2.8. Conclusions</a><a class="headerlink" href="#conclusions" title="Permalink to this headline">¶</a></h2> <p>With just under 300 lines of commented code (240 lines of non-comment, non-blank code), we fully defined our minimal language, including a lexer, parser, and AST builder. With this done, the executable will validate Kaleidoscope code and tell us if it is grammatically invalid. For example, here is a sample interaction:</p> <div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>$ ./toy.byte ready> def foo<span class="o">(</span>x y<span class="o">)</span> x+foo<span class="o">(</span>y, <span class="m">4</span>.0<span class="o">)</span><span class="p">;</span> Parsed a <span class="k">function</span> definition. ready> def foo<span class="o">(</span>x y<span class="o">)</span> x+y y<span class="p">;</span> Parsed a <span class="k">function</span> definition. Parsed a top-level expr ready> def foo<span class="o">(</span>x y<span class="o">)</span> x+y <span class="o">)</span><span class="p">;</span> Parsed a <span class="k">function</span> definition. Error: unknown token when expecting an expression ready> extern sin<span class="o">(</span>a<span class="o">)</span><span class="p">;</span> ready> Parsed an extern ready> ^D $ </pre></div> </div> <p>There is a lot of room for extension here. You can define new AST nodes, extend the language in many ways, etc. In the <a class="reference external" href="OCamlLangImpl3.html">next installment</a>, we will describe how to generate LLVM Intermediate Representation (IR) from the AST.</p> </div> <div class="section" id="full-code-listing"> <h2><a class="toc-backref" href="#id10">2.9. Full Code Listing</a><a class="headerlink" href="#full-code-listing" title="Permalink to this headline">¶</a></h2> <p>Here is the complete code listing for this and the previous chapter. Note that it is fully self-contained: you don’t need LLVM or any external libraries at all for this. (Besides the ocaml standard libraries, of course.) To build this, just compile with:</p> <div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="c1"># Compile</span> ocamlbuild toy.byte <span class="c1"># Run</span> ./toy.byte </pre></div> </div> <p>Here is the code:</p> <dl class="docutils"> <dt>_tags:</dt> <dd><div class="first last highlight-default notranslate"><div class="highlight"><pre><span></span><span class="o"><</span><span class="p">{</span><span class="n">lexer</span><span class="p">,</span><span class="n">parser</span><span class="p">}</span><span class="o">.</span><span class="n">ml</span><span class="o">></span><span class="p">:</span> <span class="n">use_camlp4</span><span class="p">,</span> <span class="n">pp</span><span class="p">(</span><span class="n">camlp4of</span><span class="p">)</span> </pre></div> </div> </dd> <dt>token.ml:</dt> <dd><div class="first last highlight-ocaml notranslate"><div class="highlight"><pre><span></span><span class="c">(*===----------------------------------------------------------------------===</span> <span class="c"> * Lexer Tokens</span> <span class="c"> *===----------------------------------------------------------------------===*)</span> <span class="c">(* The lexer returns these 'Kwd' if it is an unknown character, otherwise one of</span> <span class="c"> * these others for known things. *)</span> <span class="k">type</span> <span class="n">token</span> <span class="o">=</span> <span class="c">(* commands *)</span> <span class="o">|</span> <span class="nc">Def</span> <span class="o">|</span> <span class="nc">Extern</span> <span class="c">(* primary *)</span> <span class="o">|</span> <span class="nc">Ident</span> <span class="k">of</span> <span class="kt">string</span> <span class="o">|</span> <span class="nc">Number</span> <span class="k">of</span> <span class="kt">float</span> <span class="c">(* unknown *)</span> <span class="o">|</span> <span class="nc">Kwd</span> <span class="k">of</span> <span class="kt">char</span> </pre></div> </div> </dd> <dt>lexer.ml:</dt> <dd><div class="first last highlight-ocaml notranslate"><div class="highlight"><pre><span></span><span class="c">(*===----------------------------------------------------------------------===</span> <span class="c"> * Lexer</span> <span class="c"> *===----------------------------------------------------------------------===*)</span> <span class="k">let</span> <span class="k">rec</span> <span class="n">lex</span> <span class="o">=</span> <span class="n">parser</span> <span class="c">(* Skip any whitespace. *)</span> <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">' '</span> <span class="o">|</span> <span class="sc">'\n'</span> <span class="o">|</span> <span class="sc">'\r'</span> <span class="o">|</span> <span class="sc">'\t'</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">lex</span> <span class="n">stream</span> <span class="c">(* identifier: [a-zA-Z][a-zA-Z0-9] *)</span> <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'A'</span> <span class="o">..</span> <span class="sc">'Z'</span> <span class="o">|</span> <span class="sc">'a'</span> <span class="o">..</span> <span class="sc">'z'</span> <span class="k">as</span> <span class="n">c</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span> <span class="k">let</span> <span class="n">buffer</span> <span class="o">=</span> <span class="nn">Buffer</span><span class="p">.</span><span class="n">create</span> <span class="mi">1</span> <span class="k">in</span> <span class="nn">Buffer</span><span class="p">.</span><span class="n">add_char</span> <span class="n">buffer</span> <span class="n">c</span><span class="o">;</span> <span class="n">lex_ident</span> <span class="n">buffer</span> <span class="n">stream</span> <span class="c">(* number: [0-9.]+ *)</span> <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'0'</span> <span class="o">..</span> <span class="sc">'9'</span> <span class="k">as</span> <span class="n">c</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span> <span class="k">let</span> <span class="n">buffer</span> <span class="o">=</span> <span class="nn">Buffer</span><span class="p">.</span><span class="n">create</span> <span class="mi">1</span> <span class="k">in</span> <span class="nn">Buffer</span><span class="p">.</span><span class="n">add_char</span> <span class="n">buffer</span> <span class="n">c</span><span class="o">;</span> <span class="n">lex_number</span> <span class="n">buffer</span> <span class="n">stream</span> <span class="c">(* Comment until end of line. *)</span> <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'#'</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">lex_comment</span> <span class="n">stream</span> <span class="c">(* Otherwise, just return the character as its ascii value. *)</span> <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="n">c</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="n">c</span><span class="o">;</span> <span class="n">lex</span> <span class="n">stream</span> <span class="o">>]</span> <span class="c">(* end of stream. *)</span> <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="o">[<</span> <span class="o">>]</span> <span class="ow">and</span> <span class="n">lex_number</span> <span class="n">buffer</span> <span class="o">=</span> <span class="n">parser</span> <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'0'</span> <span class="o">..</span> <span class="sc">'9'</span> <span class="o">|</span> <span class="sc">'.'</span> <span class="k">as</span> <span class="n">c</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span> <span class="nn">Buffer</span><span class="p">.</span><span class="n">add_char</span> <span class="n">buffer</span> <span class="n">c</span><span class="o">;</span> <span class="n">lex_number</span> <span class="n">buffer</span> <span class="n">stream</span> <span class="o">|</span> <span class="o">[<</span> <span class="n">stream</span><span class="o">=</span><span class="n">lex</span> <span class="o">>]</span> <span class="o">-></span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Number</span> <span class="o">(</span><span class="n">float_of_string</span> <span class="o">(</span><span class="nn">Buffer</span><span class="p">.</span><span class="n">contents</span> <span class="n">buffer</span><span class="o">));</span> <span class="n">stream</span> <span class="o">>]</span> <span class="ow">and</span> <span class="n">lex_ident</span> <span class="n">buffer</span> <span class="o">=</span> <span class="n">parser</span> <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'A'</span> <span class="o">..</span> <span class="sc">'Z'</span> <span class="o">|</span> <span class="sc">'a'</span> <span class="o">..</span> <span class="sc">'z'</span> <span class="o">|</span> <span class="sc">'0'</span> <span class="o">..</span> <span class="sc">'9'</span> <span class="k">as</span> <span class="n">c</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span> <span class="nn">Buffer</span><span class="p">.</span><span class="n">add_char</span> <span class="n">buffer</span> <span class="n">c</span><span class="o">;</span> <span class="n">lex_ident</span> <span class="n">buffer</span> <span class="n">stream</span> <span class="o">|</span> <span class="o">[<</span> <span class="n">stream</span><span class="o">=</span><span class="n">lex</span> <span class="o">>]</span> <span class="o">-></span> <span class="k">match</span> <span class="nn">Buffer</span><span class="p">.</span><span class="n">contents</span> <span class="n">buffer</span> <span class="k">with</span> <span class="o">|</span> <span class="s2">"def"</span> <span class="o">-></span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Def</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">|</span> <span class="s2">"extern"</span> <span class="o">-></span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Extern</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">|</span> <span class="n">id</span> <span class="o">-></span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Ident</span> <span class="n">id</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span> <span class="ow">and</span> <span class="n">lex_comment</span> <span class="o">=</span> <span class="n">parser</span> <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'\n'</span><span class="o">);</span> <span class="n">stream</span><span class="o">=</span><span class="n">lex</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">stream</span> <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="n">c</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">lex_comment</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span> <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="o">[<</span> <span class="o">>]</span> </pre></div> </div> </dd> <dt>ast.ml:</dt> <dd><div class="first last highlight-ocaml notranslate"><div class="highlight"><pre><span></span><span class="c">(*===----------------------------------------------------------------------===</span> <span class="c"> * Abstract Syntax Tree (aka Parse Tree)</span> <span class="c"> *===----------------------------------------------------------------------===*)</span> <span class="c">(* expr - Base type for all expression nodes. *)</span> <span class="k">type</span> <span class="n">expr</span> <span class="o">=</span> <span class="c">(* variant for numeric literals like "1.0". *)</span> <span class="o">|</span> <span class="nc">Number</span> <span class="k">of</span> <span class="kt">float</span> <span class="c">(* variant for referencing a variable, like "a". *)</span> <span class="o">|</span> <span class="nc">Variable</span> <span class="k">of</span> <span class="kt">string</span> <span class="c">(* variant for a binary operator. *)</span> <span class="o">|</span> <span class="nc">Binary</span> <span class="k">of</span> <span class="kt">char</span> <span class="o">*</span> <span class="n">expr</span> <span class="o">*</span> <span class="n">expr</span> <span class="c">(* variant for function calls. *)</span> <span class="o">|</span> <span class="nc">Call</span> <span class="k">of</span> <span class="kt">string</span> <span class="o">*</span> <span class="n">expr</span> <span class="kt">array</span> <span class="c">(* proto - This type represents the "prototype" for a function, which captures</span> <span class="c"> * its name, and its argument names (thus implicitly the number of arguments the</span> <span class="c"> * function takes). *)</span> <span class="k">type</span> <span class="n">proto</span> <span class="o">=</span> <span class="nc">Prototype</span> <span class="k">of</span> <span class="kt">string</span> <span class="o">*</span> <span class="kt">string</span> <span class="kt">array</span> <span class="c">(* func - This type represents a function definition itself. *)</span> <span class="k">type</span> <span class="n">func</span> <span class="o">=</span> <span class="nc">Function</span> <span class="k">of</span> <span class="n">proto</span> <span class="o">*</span> <span class="n">expr</span> </pre></div> </div> </dd> <dt>parser.ml:</dt> <dd><div class="first last highlight-ocaml notranslate"><div class="highlight"><pre><span></span><span class="c">(*===---------------------------------------------------------------------===</span> <span class="c"> * Parser</span> <span class="c"> *===---------------------------------------------------------------------===*)</span> <span class="c">(* binop_precedence - This holds the precedence for each binary operator that is</span> <span class="c"> * defined *)</span> <span class="k">let</span> <span class="n">binop_precedence</span><span class="o">:(</span><span class="kt">char</span><span class="o">,</span> <span class="kt">int</span><span class="o">)</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">t</span> <span class="o">=</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">create</span> <span class="mi">10</span> <span class="c">(* precedence - Get the precedence of the pending binary operator token. *)</span> <span class="k">let</span> <span class="n">precedence</span> <span class="n">c</span> <span class="o">=</span> <span class="k">try</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">find</span> <span class="n">binop_precedence</span> <span class="n">c</span> <span class="k">with</span> <span class="nc">Not_found</span> <span class="o">-></span> <span class="o">-</span><span class="mi">1</span> <span class="c">(* primary</span> <span class="c"> * ::= identifier</span> <span class="c"> * ::= numberexpr</span> <span class="c"> * ::= parenexpr *)</span> <span class="k">let</span> <span class="k">rec</span> <span class="n">parse_primary</span> <span class="o">=</span> <span class="n">parser</span> <span class="c">(* numberexpr ::= number *)</span> <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Number</span> <span class="n">n</span> <span class="o">>]</span> <span class="o">-></span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Number</span> <span class="n">n</span> <span class="c">(* parenexpr ::= '(' expression ')' *)</span> <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">'('</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_expr</span><span class="o">;</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">')'</span> <span class="o">??</span> <span class="s2">"expected ')'"</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span> <span class="c">(* identifierexpr</span> <span class="c"> * ::= identifier</span> <span class="c"> * ::= identifier '(' argumentexpr ')' *)</span> <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Ident</span> <span class="n">id</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span> <span class="k">let</span> <span class="k">rec</span> <span class="n">parse_args</span> <span class="n">accumulator</span> <span class="o">=</span> <span class="n">parser</span> <span class="o">|</span> <span class="o">[<</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_expr</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span> <span class="k">begin</span> <span class="n">parser</span> <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">','</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_args</span> <span class="o">(</span><span class="n">e</span> <span class="o">::</span> <span class="n">accumulator</span><span class="o">)</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span> <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span> <span class="o">::</span> <span class="n">accumulator</span> <span class="k">end</span> <span class="n">stream</span> <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">accumulator</span> <span class="k">in</span> <span class="k">let</span> <span class="k">rec</span> <span class="n">parse_ident</span> <span class="n">id</span> <span class="o">=</span> <span class="n">parser</span> <span class="c">(* Call. *)</span> <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">'('</span><span class="o">;</span> <span class="n">args</span><span class="o">=</span><span class="n">parse_args</span> <span class="bp">[]</span><span class="o">;</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">')'</span> <span class="o">??</span> <span class="s2">"expected ')'"</span><span class="o">>]</span> <span class="o">-></span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Call</span> <span class="o">(</span><span class="n">id</span><span class="o">,</span> <span class="nn">Array</span><span class="p">.</span><span class="n">of_list</span> <span class="o">(</span><span class="nn">List</span><span class="p">.</span><span class="n">rev</span> <span class="n">args</span><span class="o">))</span> <span class="c">(* Simple variable ref. *)</span> <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Variable</span> <span class="n">id</span> <span class="k">in</span> <span class="n">parse_ident</span> <span class="n">id</span> <span class="n">stream</span> <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="k">raise</span> <span class="o">(</span><span class="nn">Stream</span><span class="p">.</span><span class="nc">Error</span> <span class="s2">"unknown token when expecting an expression."</span><span class="o">)</span> <span class="c">(* binoprhs</span> <span class="c"> * ::= ('+' primary)* *)</span> <span class="ow">and</span> <span class="n">parse_bin_rhs</span> <span class="n">expr_prec</span> <span class="n">lhs</span> <span class="n">stream</span> <span class="o">=</span> <span class="k">match</span> <span class="nn">Stream</span><span class="p">.</span><span class="n">peek</span> <span class="n">stream</span> <span class="k">with</span> <span class="c">(* If this is a binop, find its precedence. *)</span> <span class="o">|</span> <span class="nc">Some</span> <span class="o">(</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="n">c</span><span class="o">)</span> <span class="k">when</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">mem</span> <span class="n">binop_precedence</span> <span class="n">c</span> <span class="o">-></span> <span class="k">let</span> <span class="n">token_prec</span> <span class="o">=</span> <span class="n">precedence</span> <span class="n">c</span> <span class="k">in</span> <span class="c">(* If this is a binop that binds at least as tightly as the current binop,</span> <span class="c"> * consume it, otherwise we are done. *)</span> <span class="k">if</span> <span class="n">token_prec</span> <span class="o"><</span> <span class="n">expr_prec</span> <span class="k">then</span> <span class="n">lhs</span> <span class="k">else</span> <span class="k">begin</span> <span class="c">(* Eat the binop. *)</span> <span class="nn">Stream</span><span class="p">.</span><span class="n">junk</span> <span class="n">stream</span><span class="o">;</span> <span class="c">(* Parse the primary expression after the binary operator. *)</span> <span class="k">let</span> <span class="n">rhs</span> <span class="o">=</span> <span class="n">parse_primary</span> <span class="n">stream</span> <span class="k">in</span> <span class="c">(* Okay, we know this is a binop. *)</span> <span class="k">let</span> <span class="n">rhs</span> <span class="o">=</span> <span class="k">match</span> <span class="nn">Stream</span><span class="p">.</span><span class="n">peek</span> <span class="n">stream</span> <span class="k">with</span> <span class="o">|</span> <span class="nc">Some</span> <span class="o">(</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="n">c2</span><span class="o">)</span> <span class="o">-></span> <span class="c">(* If BinOp binds less tightly with rhs than the operator after</span> <span class="c"> * rhs, let the pending operator take rhs as its lhs. *)</span> <span class="k">let</span> <span class="n">next_prec</span> <span class="o">=</span> <span class="n">precedence</span> <span class="n">c2</span> <span class="k">in</span> <span class="k">if</span> <span class="n">token_prec</span> <span class="o"><</span> <span class="n">next_prec</span> <span class="k">then</span> <span class="n">parse_bin_rhs</span> <span class="o">(</span><span class="n">token_prec</span> <span class="o">+</span> <span class="mi">1</span><span class="o">)</span> <span class="n">rhs</span> <span class="n">stream</span> <span class="k">else</span> <span class="n">rhs</span> <span class="o">|</span> <span class="o">_</span> <span class="o">-></span> <span class="n">rhs</span> <span class="k">in</span> <span class="c">(* Merge lhs/rhs. *)</span> <span class="k">let</span> <span class="n">lhs</span> <span class="o">=</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Binary</span> <span class="o">(</span><span class="n">c</span><span class="o">,</span> <span class="n">lhs</span><span class="o">,</span> <span class="n">rhs</span><span class="o">)</span> <span class="k">in</span> <span class="n">parse_bin_rhs</span> <span class="n">expr_prec</span> <span class="n">lhs</span> <span class="n">stream</span> <span class="k">end</span> <span class="o">|</span> <span class="o">_</span> <span class="o">-></span> <span class="n">lhs</span> <span class="c">(* expression</span> <span class="c"> * ::= primary binoprhs *)</span> <span class="ow">and</span> <span class="n">parse_expr</span> <span class="o">=</span> <span class="n">parser</span> <span class="o">|</span> <span class="o">[<</span> <span class="n">lhs</span><span class="o">=</span><span class="n">parse_primary</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">parse_bin_rhs</span> <span class="mi">0</span> <span class="n">lhs</span> <span class="n">stream</span> <span class="c">(* prototype</span> <span class="c"> * ::= id '(' id* ')' *)</span> <span class="k">let</span> <span class="n">parse_prototype</span> <span class="o">=</span> <span class="k">let</span> <span class="k">rec</span> <span class="n">parse_args</span> <span class="n">accumulator</span> <span class="o">=</span> <span class="n">parser</span> <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Ident</span> <span class="n">id</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_args</span> <span class="o">(</span><span class="n">id</span><span class="o">::</span><span class="n">accumulator</span><span class="o">)</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span> <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">accumulator</span> <span class="k">in</span> <span class="n">parser</span> <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Ident</span> <span class="n">id</span><span class="o">;</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">'('</span> <span class="o">??</span> <span class="s2">"expected '(' in prototype"</span><span class="o">;</span> <span class="n">args</span><span class="o">=</span><span class="n">parse_args</span> <span class="bp">[]</span><span class="o">;</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">')'</span> <span class="o">??</span> <span class="s2">"expected ')' in prototype"</span> <span class="o">>]</span> <span class="o">-></span> <span class="c">(* success. *)</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Prototype</span> <span class="o">(</span><span class="n">id</span><span class="o">,</span> <span class="nn">Array</span><span class="p">.</span><span class="n">of_list</span> <span class="o">(</span><span class="nn">List</span><span class="p">.</span><span class="n">rev</span> <span class="n">args</span><span class="o">))</span> <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="k">raise</span> <span class="o">(</span><span class="nn">Stream</span><span class="p">.</span><span class="nc">Error</span> <span class="s2">"expected function name in prototype"</span><span class="o">)</span> <span class="c">(* definition ::= 'def' prototype expression *)</span> <span class="k">let</span> <span class="n">parse_definition</span> <span class="o">=</span> <span class="n">parser</span> <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Def</span><span class="o">;</span> <span class="n">p</span><span class="o">=</span><span class="n">parse_prototype</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_expr</span> <span class="o">>]</span> <span class="o">-></span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Function</span> <span class="o">(</span><span class="n">p</span><span class="o">,</span> <span class="n">e</span><span class="o">)</span> <span class="c">(* toplevelexpr ::= expression *)</span> <span class="k">let</span> <span class="n">parse_toplevel</span> <span class="o">=</span> <span class="n">parser</span> <span class="o">|</span> <span class="o">[<</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_expr</span> <span class="o">>]</span> <span class="o">-></span> <span class="c">(* Make an anonymous proto. *)</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Function</span> <span class="o">(</span><span class="nn">Ast</span><span class="p">.</span><span class="nc">Prototype</span> <span class="o">(</span><span class="s2">""</span><span class="o">,</span> <span class="o">[||]),</span> <span class="n">e</span><span class="o">)</span> <span class="c">(* external ::= 'extern' prototype *)</span> <span class="k">let</span> <span class="n">parse_extern</span> <span class="o">=</span> <span class="n">parser</span> <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Extern</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_prototype</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span> </pre></div> </div> </dd> <dt>toplevel.ml:</dt> <dd><div class="first last highlight-ocaml notranslate"><div class="highlight"><pre><span></span><span class="c">(*===----------------------------------------------------------------------===</span> <span class="c"> * Top-Level parsing and JIT Driver</span> <span class="c"> *===----------------------------------------------------------------------===*)</span> <span class="c">(* top ::= definition | external | expression | ';' *)</span> <span class="k">let</span> <span class="k">rec</span> <span class="n">main_loop</span> <span class="n">stream</span> <span class="o">=</span> <span class="k">match</span> <span class="nn">Stream</span><span class="p">.</span><span class="n">peek</span> <span class="n">stream</span> <span class="k">with</span> <span class="o">|</span> <span class="nc">None</span> <span class="o">-></span> <span class="bp">()</span> <span class="c">(* ignore top-level semicolons. *)</span> <span class="o">|</span> <span class="nc">Some</span> <span class="o">(</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">';'</span><span class="o">)</span> <span class="o">-></span> <span class="nn">Stream</span><span class="p">.</span><span class="n">junk</span> <span class="n">stream</span><span class="o">;</span> <span class="n">main_loop</span> <span class="n">stream</span> <span class="o">|</span> <span class="nc">Some</span> <span class="n">token</span> <span class="o">-></span> <span class="k">begin</span> <span class="k">try</span> <span class="k">match</span> <span class="n">token</span> <span class="k">with</span> <span class="o">|</span> <span class="nn">Token</span><span class="p">.</span><span class="nc">Def</span> <span class="o">-></span> <span class="n">ignore</span><span class="o">(</span><span class="nn">Parser</span><span class="p">.</span><span class="n">parse_definition</span> <span class="n">stream</span><span class="o">);</span> <span class="n">print_endline</span> <span class="s2">"parsed a function definition."</span><span class="o">;</span> <span class="o">|</span> <span class="nn">Token</span><span class="p">.</span><span class="nc">Extern</span> <span class="o">-></span> <span class="n">ignore</span><span class="o">(</span><span class="nn">Parser</span><span class="p">.</span><span class="n">parse_extern</span> <span class="n">stream</span><span class="o">);</span> <span class="n">print_endline</span> <span class="s2">"parsed an extern."</span><span class="o">;</span> <span class="o">|</span> <span class="o">_</span> <span class="o">-></span> <span class="c">(* Evaluate a top-level expression into an anonymous function. *)</span> <span class="n">ignore</span><span class="o">(</span><span class="nn">Parser</span><span class="p">.</span><span class="n">parse_toplevel</span> <span class="n">stream</span><span class="o">);</span> <span class="n">print_endline</span> <span class="s2">"parsed a top-level expr"</span><span class="o">;</span> <span class="k">with</span> <span class="nn">Stream</span><span class="p">.</span><span class="nc">Error</span> <span class="n">s</span> <span class="o">-></span> <span class="c">(* Skip token for error recovery. *)</span> <span class="nn">Stream</span><span class="p">.</span><span class="n">junk</span> <span class="n">stream</span><span class="o">;</span> <span class="n">print_endline</span> <span class="n">s</span><span class="o">;</span> <span class="k">end</span><span class="o">;</span> <span class="n">print_string</span> <span class="s2">"ready> "</span><span class="o">;</span> <span class="n">flush</span> <span class="n">stdout</span><span class="o">;</span> <span class="n">main_loop</span> <span class="n">stream</span> </pre></div> </div> </dd> <dt>toy.ml:</dt> <dd><div class="first last highlight-ocaml notranslate"><div class="highlight"><pre><span></span><span class="c">(*===----------------------------------------------------------------------===</span> <span class="c"> * Main driver code.</span> <span class="c"> *===----------------------------------------------------------------------===*)</span> <span class="k">let</span> <span class="n">main</span> <span class="bp">()</span> <span class="o">=</span> <span class="c">(* Install standard binary operators.</span> <span class="c"> * 1 is the lowest precedence. *)</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">binop_precedence</span> <span class="sc">'<'</span> <span class="mi">10</span><span class="o">;</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">binop_precedence</span> <span class="sc">'+'</span> <span class="mi">20</span><span class="o">;</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">binop_precedence</span> <span class="sc">'-'</span> <span class="mi">20</span><span class="o">;</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">binop_precedence</span> <span class="sc">'*'</span> <span class="mi">40</span><span class="o">;</span> <span class="c">(* highest. *)</span> <span class="c">(* Prime the first token. *)</span> <span class="n">print_string</span> <span class="s2">"ready> "</span><span class="o">;</span> <span class="n">flush</span> <span class="n">stdout</span><span class="o">;</span> <span class="k">let</span> <span class="n">stream</span> <span class="o">=</span> <span class="nn">Lexer</span><span class="p">.</span><span class="n">lex</span> <span class="o">(</span><span class="nn">Stream</span><span class="p">.</span><span class="n">of_channel</span> <span class="n">stdin</span><span class="o">)</span> <span class="k">in</span> <span class="c">(* Run the main "interpreter loop" now. *)</span> <span class="nn">Toplevel</span><span class="p">.</span><span class="n">main_loop</span> <span class="n">stream</span><span class="o">;</span> <span class="o">;;</span> <span class="n">main</span> <span class="bp">()</span> </pre></div> </div> </dd> </dl> <p><a class="reference external" href="OCamlLangImpl3.html">Next: Implementing Code Generation to LLVM IR</a></p> </div> </div> </div> </div> <div class="clearer"></div> </div> <div class="related" role="navigation" aria-label="related navigation"> <h3>Navigation</h3> <ul> <li class="right" style="margin-right: 10px"> <a href="../genindex.html" title="General Index" >index</a></li> <li class="right" > <a href="OCamlLangImpl3.html" title="3. Kaleidoscope: Code generation to LLVM IR" >next</a> |</li> <li class="right" > <a href="OCamlLangImpl1.html" title="1. Kaleidoscope: Tutorial Introduction and the Lexer" >previous</a> |</li> <li><a href="http://llvm.org/">LLVM Home</a> | </li> <li><a href="../index.html">Documentation</a>»</li> <li class="nav-item nav-item-1"><a href="index.html" >LLVM Tutorial: Table of Contents</a> »</li> </ul> </div> <div class="footer" role="contentinfo"> © Copyright 2003-2020, LLVM Project. Last updated on 2020-09-07. Created using <a href="http://sphinx-doc.org/">Sphinx</a> 1.8.4. </div> </body> </html>