Merge pull request peggyjs#73 from jaubourg/main

Adds top level initializer block.

AUTHORS

@@ -18,6 +18,7 @@ Futago-za Ryuu <[email protected]> (https://github.com/futagoza/)
 Jakub Vrana <[email protected]> (https://github.com/vrana/)
 Jason Davies <[email protected]> (https://github.com/jasondavies/)
 Joseph Frazier <[email protected]> (https://github.com/joseph-onsip/)
+Julian Aubourg <[email protected]> (https://github.com/jaubourg)
 Justin Blank <[email protected]> (https://github.com/hyperpape/)
 Marco Baumgartl <[email protected]>
 Mingun <[email protected]> (https://github.com/Mingun/)

README.md

@@ -153,12 +153,15 @@ object to `peg.generate`. The following options are supported:
   `false`)
 - `dependencies` — parser dependencies, the value is an object which maps
   variables used to access the dependencies in the parser to module IDs used
-  to load them; valid only when `format` is set to `"amd"`, `"commonjs"`, `"es"`, or
-  `"umd"` (default: `{}`)
+  to load them; valid only when `format` is set to `"amd"`, `"commonjs"`,
+  `"es"`, or `"umd"`. Dependencies variables will be available in both the
+  _general initializer_ and the _per-parse initializer_. Unless the parser is
+  to be generated in different formats, it is recommended to rather import
+  dependencies from within the _global initializer_. (default: `{}`)
 - `exportVar` — name of a global variable into which the parser object is
   assigned to when no module loader is detected; valid only when `format` is
   set to `"globals"` or `"umd"` (default: `null`)
-- `format` — format of the genreated parser (`"amd"`, `"bare"`, `"commonjs"`,
+- `format` — format of the generated parser (`"amd"`, `"bare"`, `"commonjs"`,
   `"es"`, `"globals"`, or `"umd"`); valid only when `output` is set to `"source"`
   (default: `"bare"`)
 - `optimize`— selects between optimizing the generated parser for parsing
@@ -235,19 +238,39 @@ written as a JavaScript string between the name and separating equality sign.
 Rules need to be separated only by whitespace (their beginning is easily
 recognizable), but a semicolon (“;”) after the parsing expression is allowed.
 
-The first rule can be preceded by an _initializer_ — a piece of JavaScript code
-in curly braces (“{” and “}”). This code is executed before the generated parser
-starts parsing. All variables and functions defined in the initializer are
-accessible in rule actions and semantic predicates. The code inside the
-initializer can access options passed to the parser using the `options`
-variable. Curly braces in the initializer code must be balanced. Let's look at
-the example grammar from above using a simple initializer.
+The first rule can be preceded by a _global initializer_ and/or a _per-parse
+initializer_, in that order. Both are pieces of JavaScript code in double
+curly braces (“{{” and “}}”) and single curly braces (“{” and “}”) respectively.
+All variables and functions defined in both _initializers_ are accessible in
+rule actions and semantic predicates. Curly braces in both _initializers_ code
+must be balanced.
+
+The _global initializer_ is executed once and only once, when the generated
+parser is loaded (through a `require` or an `import` statement for instance). It
+is the ideal location to require, to import or to declare utility functions to
+be used in rule actions and semantic predicates.
+
+The _per-parse initializer_ is called before the generated parser starts
+parsing. The code inside the _per-parse initializer_ can access the input
+string and the options passed to the parser using the `input` variable and the
+`options` variable respectively. It is the ideal location to create data
+structures that are unique to each parse or to modify the input before the
+parse.
+
+Let's look at the example grammar from above using a _global initializer_ and
+a _per-parse initializer_:
 
 ```peggy
-{
+{{
   function makeInteger(o) {
     return parseInt(o.join(""), 10);
   }
+}}
+
+{
+  if (options.multiplier) {
+    input = "(" + input + ")*(" + options.multiplier + ")";
+  }
 }
 
 start

docs/documentation.html

@@ -211,7 +211,11 @@ <h3 id="generating-a-parser-javascript-api">JavaScript API</h3>
   <dd>Parser dependencies, the value is an object which maps variables used to
   access the dependencies in the parser to module IDs used to load them; valid
   only when <code>format</code> is set to <code>"amd"</code>,
-  <code>"commonjs"</code>, or <code>"umd"</code> (default:
+  <code>"commonjs"</code>, <code>"es"</code>, or <code>"umd"</code>.
+  Dependencies variables will be available in both the <em>general
+  initializer</em> and the <em>per-parse initializer</em>. Unless the parser is
+  to be generated in different formats, it is recommended to rather import
+  dependencies from within the <em>global initializer</em> (default:
   <code>{}</code>).</dd>
 
   <dt><code>exportVar</code></dt>
@@ -222,9 +226,9 @@ <h3 id="generating-a-parser-javascript-api">JavaScript API</h3>
 
   <dt><code>format</code></dt>
   <dd>format of the generated parser (<code>"amd"</code>, <code>"bare"</code>,
-  <code>"commonjs"</code>, <code>"globals"</code>, or <code>"umd"</code>); valid
-  only when <code>output</code> is set to <code>"source"</code> (default:
-  <code>"bare"</code>).</dd>
+  <code>"commonjs"</code>, <code>"es"</code>, <code>"globals"</code>, or
+  <code>"umd"</code>); valid only when <code>output</code> is set to
+  <code>"source"</code> (default: <code>"bare"</code>).</dd>
 
   <dt><code>optimize</code></dt>
   <dd>Selects between optimizing the generated parser for parsing speed
@@ -316,19 +320,36 @@ <h2 id="grammar-syntax-and-semantics">Grammar Syntax and Semantics</h2>
 recognizable), but a semicolon (“;”) after the parsing expression is
 allowed.</p>
 
-<p>The first rule can be preceded by an <em>initializer</em> &mdash; a piece of
-JavaScript code in curly braces (“{” and “}”). This code is executed before the
-generated parser starts parsing. All variables and functions defined in the
-initializer are accessible in rule actions and semantic predicates. The code
-inside the initializer can access options passed to the parser using the
-<code>options</code> variable. Curly braces in the initializer code must be
-balanced. Let's look at the example grammar from above using a simple
-initializer.</p>
-
-<pre><code>{
+<p>The first rule can be preceded by a <em>global initializer</em> and/or a
+<em>per-parse initializer</em>, in that order. Both are pieces of JavaScript
+code in double curly braces (“{{” and “}}”) and single curly braces (“{” and
+“}”) respectively. All variables and functions defined in both
+<em>initializers</em> are accessible in rule actions and semantic predicates.
+Curly braces in both <em>initializers</em> code must be balanced.</p>
+<p>The <em>global initializer</em> is executed once and only once, when the
+generated parser is loaded (through a <code>require</code> or an
+<code>import</code> statement for instance). It is the ideal location to
+require, to import or to declare utility functions to be used in rule actions
+and semantic predicates.</p>
+<p>The <em>per-parse initializer</em> is called before the generated parser
+starts parsing. The code inside the <em>per-parse initializer</em> can access
+the input string and the options passed to the parser using the
+<code>input</code> variable and the <code>options</code> variable respectively.
+It is the ideal location to create data structures that are unique to each
+parse or to modify the input before the parse.</p>
+<p>Let's look at the example grammar from above using a <em>global
+initializer</em> and a <em>per-parse initializer</em>:</p>
+
+<pre><code>{{
   function makeInteger(o) {
     return parseInt(o.join(""), 10);
   }
+}}
+
+{
+  if (options.multiplier) {
+    input = "(" + input + ")*(" + options.multiplier + ")";
+  }
 }
 
 start

examples/css.pegjs

@@ -17,7 +17,7 @@
 // [2] http://www.w3.org/Style/css2-updates/REC-CSS2-20110607-errata.html
 // [3] http://www.w3.org/TR/DOM-Level-2-Style/css.html
 
-{
+{{
   function extractOptional(optional, index) {
     return optional ? optional[index] : null;
   }
@@ -41,7 +41,7 @@
       };
     }, head);
   }
-}
+}}
 
 start
   = stylesheet:stylesheet comment* { return stylesheet; }

examples/javascript.pegjs

@@ -30,7 +30,7 @@
 // [3] http://inimino.org/~inimino/blog/
 // [4] http://boshi.inimino.org/3box/asof/1270029991384/PEG/ECMAScript_unified.peg
 
-{
+{{
   var TYPES_TO_PROPERTY_NAMES = {
     CallExpression:   "callee",
     MemberExpression: "object",
@@ -78,7 +78,7 @@
   function optionalList(value) {
     return value !== null ? value : [];
   }
-}
+}}
 
 Start
   = __ program:Program __ { return program; }

lib/compiler/passes/generate-js.js

@@ -743,6 +743,11 @@ function generateJS(ast, options) {
   function generateToplevel() {
     const parts = [];
 
+    if (ast.topLevelInitializer) {
+      parts.push(ast.topLevelInitializer.code);
+      parts.push("");
+    }
+
     parts.push([
       "function peg$subclass(child, parent) {",
       "  function C() { this.constructor = child; }",

lib/compiler/visitor.js

@@ -31,6 +31,10 @@ const visitor = {
       grammar(node) {
         const extraArgs = Array.prototype.slice.call(arguments, 1);
 
+        if (node.topLevelInitializer) {
+          visit.apply(null, [node.topLevelInitializer].concat(extraArgs));
+        }
+
         if (node.initializer) {
           visit.apply(null, [node.initializer].concat(extraArgs));
         }
@@ -40,6 +44,7 @@ const visitor = {
         });
       },
 
+      top_level_initializer: visitNop,
       initializer: visitNop,
       rule: visitExpression,
       named: visitExpression,