v1.4.0

Add ast_prefix and ast_suffix grammar statements.

CHANGELOG.md

@@ -1,3 +1,43 @@
+## v1.4.0
+
+### New Features
+
+- Allow user to specify AST node name prefix or suffix
+- Allow specifying the start rule name
+- Allow rule terms to be marked as optional
+
+### Improvements
+
+- Give a better error message when a referenced ptype has not been declared
+
+## v1.3.0
+
+### New Features
+
+- Add AST generation (#22)
+
+## v1.2.0
+
+### New Features
+
+- Allow one line user code blocks (#21)
+- Add backslash escape codes (#19)
+- Add API to access unexpected token found (#18)
+- Add token_names API (#17)
+- Add D example to user guide for p_context_init() (#16)
+- Allow user termination from lexer code blocks (#15)
+
+### Fixes
+
+- Fix generator hang when state transition cycle is present (#20)
+
+## v1.1.0
+
+### New Features
+
+- Add user parser terminations (#13)
+- Document generated parser API in user guide (#14)
+
 ## v1.0.0
 
 - Initial release

Gemfile

@@ -5,3 +5,4 @@ gem "rspec"
 gem "rdoc"
 gem "redcarpet"
 gem "syntax"
+gem "simplecov"

Gemfile.lock

@@ -2,26 +2,33 @@ GEM
   remote: https://rubygems.org/
   specs:
     diff-lcs (1.5.0)
-    psych (5.0.1)
+    docile (1.4.0)
+    psych (5.1.0)
       stringio
     rake (13.0.6)
     rdoc (6.5.0)
       psych (>= 4.0.0)
-    redcarpet (3.5.1)
-    rspec (3.11.0)
-      rspec-core (~> 3.11.0)
-      rspec-expectations (~> 3.11.0)
-      rspec-mocks (~> 3.11.0)
-    rspec-core (3.11.0)
-      rspec-support (~> 3.11.0)
-    rspec-expectations (3.11.0)
+    redcarpet (3.6.0)
+    rspec (3.12.0)
+      rspec-core (~> 3.12.0)
+      rspec-expectations (~> 3.12.0)
+      rspec-mocks (~> 3.12.0)
+    rspec-core (3.12.2)
+      rspec-support (~> 3.12.0)
+    rspec-expectations (3.12.3)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.11.0)
-    rspec-mocks (3.11.1)
+      rspec-support (~> 3.12.0)
+    rspec-mocks (3.12.6)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.11.0)
-    rspec-support (3.11.0)
-    stringio (3.0.4)
+      rspec-support (~> 3.12.0)
+    rspec-support (3.12.1)
+    simplecov (0.22.0)
+      docile (~> 1.1)
+      simplecov-html (~> 0.11)
+      simplecov_json_formatter (~> 0.1)
+    simplecov-html (0.12.3)
+    simplecov_json_formatter (0.1.4)
+    stringio (3.0.7)
     syntax (1.2.2)
 
 PLATFORMS
@@ -32,6 +39,7 @@ DEPENDENCIES
   rdoc
   redcarpet
   rspec
+  simplecov
   syntax
 
 BUNDLED WITH

LICENSE.txt

@@ -1,6 +1,6 @@
 The MIT License (MIT)
 
-Copyright (c) 2010-2023 Josh Holtrop
+Copyright (c) 2010-2024 Josh Holtrop
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

README.md

@@ -1,21 +1,99 @@
 # The Propane Parser Generator
 
-Propane is an LR Parser Generator (LPG) which:
+Propane is a LALR Parser Generator (LPG) which:
 
   * accepts LR(0), SLR, and LALR grammars
   * generates a built-in lexer to tokenize input
   * supports UTF-8 lexer inputs
-  * generates a table-driven parser to parse input in linear time
+  * generates a table-driven shift/reduce parser to parse input in linear time
+  * targets C or D language outputs
+  * optionally supports automatic full AST generation
   * is MIT-licensed
   * is distributable as a standalone Ruby script
 
 ## Installation
 
-TODO
+Propane is designed to be distributed as a stand-alone single file script that
+can be copied into and versioned in a project's source tree.
+The only requirement to run Propane is that the system has a Ruby interpreter
+installed.
+The latest release can be downloaded from [https://github.com/holtrop/propane/releases](https://github.com/holtrop/propane/releases).
+
+Simply copy the `propane` executable script into the desired location within
+the project to be built (typically the root of the repository) and mark it
+executable.
 
 ## Usage
 
-TODO: Write usage instructions here
+### Command Line Interface
+
+Propane is typically invoked from the command-line as `./propane`.
+
+    Usage: ./propane [options] <input-file> <output-file>
+    Options:
+      --log LOG   Write log file
+      --version   Show program version and exit
+      -h, --help  Show this usage and exit
+
+The user must specify the path to a Propane input grammar file and a path to an
+output file.
+The generated source code will be written to the output file.
+If a log file path is specified, Propane will write a log file containing
+detailed information about the parser states and transitions.
+
+### Propane Grammar File
+
+A Propane grammar file provides Propane with the patterns, tokens, grammar
+rules, and user code blocks from which to build the generated lexer and parser.
+
+Example grammar file:
+
+```
+<<
+import std.math;
+>>
+
+# Parser values are unsigned integers.
+ptype ulong;
+
+# A few basic arithmetic operators.
+token plus /\+/;
+token times /\*/;
+token power /\*\*/;
+token integer /\d+/ <<
+  ulong v;
+  foreach (c; match)
+  {
+    v *= 10;
+    v += (c - '0');
+  }
+  $$ = v;
+>>
+token lparen /\(/;
+token rparen /\)/;
+# Drop whitespace.
+drop /\s+/;
+
+Start -> E1 << $$ = $1; >>
+E1 -> E2 << $$ = $1; >>
+E1 -> E1 plus E2 << $$ = $1 + $3; >>
+E2 -> E3 << $$ = $1; >>
+E2 -> E2 times E3 << $$ = $1 * $3; >>
+E3 -> E4 << $$ = $1; >>
+E3 -> E3 power E4 <<
+  $$ = pow($1, $3);
+>>
+E4 -> integer << $$ = $1; >>
+E4 -> lparen E1 rparen << $$ = $2; >>
+```
+
+Grammar files can contain comment lines beginning with `#` which are ignored.
+White space in the grammar file is also ignored.
+
+It is convention to use the extension `.propane` for the Propane grammar file,
+however any file name is accepted by Propane.
+
+See [https://holtrop.github.io/propane/index.html](https://holtrop.github.io/propane/index.html) for the full User Guide.
 
 ## Development
 

Rakefile

@@ -1,5 +1,8 @@
+require "rake/clean"
 require "rspec/core/rake_task"
 
+CLEAN.include %w[spec/run gen .yardoc yard coverage dist]
+
 task :build_dist do
   sh "ruby rb/build_dist.rb"
 end
@@ -10,9 +13,20 @@ RSpec::Core::RakeTask.new(:spec, :example_pattern) do |task, args|
   end
 end
 
+# dspec task is useful to test the distributable release script, but is not
+# useful for coverage information.
+desc "Dist Specs"
+task :dspec, [:example_string] => :build_dist do |task, args|
+  ENV["dist_specs"] = "1"
+  Rake::Task["spec"].execute(args)
+  ENV.delete("dist_specs")
+end
+
 task :default => :spec
 
 desc "Build user guide"
 task :user_guide do
   system("ruby", "-Ilib", "rb/gen_user_guide.rb")
 end
+
+task :all => [:spec, :dspec, :user_guide]

assets/parser.h.erb

@@ -0,0 +1,187 @@
+/**
+ * @file
+ *
+ * This file is generated by Propane.
+ */
+
+#pragma once
+
+#include <stdint.h>
+#include <stddef.h>
+
+/**************************************************************************
+ * Public types
+ *************************************************************************/
+
+/* Result codes. */
+#define <%= @grammar.prefix.upcase %>SUCCESS 0u
+#define <%= @grammar.prefix.upcase %>DECODE_ERROR 1u
+#define <%= @grammar.prefix.upcase %>UNEXPECTED_INPUT 2u
+#define <%= @grammar.prefix.upcase %>UNEXPECTED_TOKEN 3u
+#define <%= @grammar.prefix.upcase %>DROP 4u
+#define <%= @grammar.prefix.upcase %>EOF 5u
+#define <%= @grammar.prefix.upcase %>USER_TERMINATED 6u
+
+/** Token type. */
+typedef <%= get_type_for(@grammar.terminate_token_id) %> <%= @grammar.prefix %>token_t;
+
+/** Token IDs. */
+<% @grammar.tokens.each_with_index do |token, index| %>
+#define TOKEN_<%= token.code_name %> <%= index %>u
+<%   unless token.id == index %>
+<%     raise "Token ID (#{token.id}) does not match index (#{index}) for token #{token.name}!" %>
+<%   end %>
+<% end %>
+#define INVALID_TOKEN_ID <%= @grammar.invalid_token_id %>u
+#define TERMINATE_TOKEN_ID <%= @grammar.terminate_token_id %>u
+
+/** Code point type. */
+typedef uint32_t <%= @grammar.prefix %>code_point_t;
+
+/** User header code blocks. */
+<%= @grammar.code_blocks.fetch("header", "") %>
+
+<% if @grammar.ast %>
+/** Parser values type. */
+typedef <%= @grammar.ptype %> <%= @grammar.prefix %>value_t;
+<% else %>
+/** Parser values type(s). */
+typedef union
+{
+<%   @grammar.ptypes.each do |name, typestring| %>
+    <%= typestring %> v_<%= name %>;
+<%   end %>
+} <%= @grammar.prefix %>value_t;
+<% end %>
+
+<% if @grammar.ast %>
+/** AST node types. @{ */
+typedef struct <%= @grammar.ast_prefix %>Token<%= @grammar.ast_suffix %>
+{
+    <%= @grammar.prefix %>token_t token;
+    <%= @grammar.prefix %>value_t pvalue;
+} <%= @grammar.ast_prefix %>Token<%= @grammar.ast_suffix %>;
+
+<%   @parser.rule_sets.each do |name, rule_set| %>
+<%     next if name.start_with?("$") %>
+<%     next if rule_set.optional? %>
+struct <%= name %>;
+<%   end %>
+
+<%   @parser.rule_sets.each do |name, rule_set| %>
+<%     next if name.start_with?("$") %>
+<%     next if rule_set.optional? %>
+typedef struct <%= @grammar.ast_prefix %><%= name %><%= @grammar.ast_suffix %>
+{
+<%     rule_set.ast_fields.each do |fields| %>
+    union
+    {
+<%       fields.each do |field_name, type| %>
+        struct <%= type %> * <%= field_name %>;
+<%       end %>
+    };
+<%     end %>
+} <%= @grammar.ast_prefix %><%= name %><%= @grammar.ast_suffix %>;
+
+<%   end %>
+/** @} */
+<% end %>
+
+/**
+ * A structure to keep track of parser position.
+ *
+ * This is useful for reporting errors, etc...
+ */
+typedef struct
+{
+    /** Input text row (0-based). */
+    uint32_t row;
+
+    /** Input text column (0-based). */
+    uint32_t col;
+} <%= @grammar.prefix %>position_t;
+
+/** Lexed token information. */
+typedef struct
+{
+    /** Text position where the token was found. */
+    <%= @grammar.prefix %>position_t position;
+
+    /** Number of input bytes used by the token. */
+    size_t length;
+
+    /** Token that was lexed. */
+    <%= @grammar.prefix %>token_t token;
+
+    /** Parser value associated with the token. */
+    <%= @grammar.prefix %>value_t pvalue;
+} <%= @grammar.prefix %>token_info_t;
+
+/**
+ * Lexer and parser context.
+ *
+ * The user must allocate an instance of this structure and pass it to any
+ * public API function.
+ */
+typedef struct
+{
+    /* Lexer context data. */
+
+    /** Input text. */
+    uint8_t const * input;
+
+    /** Input text length. */
+    size_t input_length;
+
+    /** Input text index (byte offset). */
+    size_t input_index;
+
+    /** Input text position (row/column). */
+    <%= @grammar.prefix %>position_t text_position;
+
+    /** Current lexer mode. */
+    size_t mode;
+
+    /* Parser context data. */
+
+    /** Parse result value. */
+<% if @grammar.ast %>
+    <%= @grammar.ast_prefix %><%= @grammar.start_rule %><%= @grammar.ast_suffix %> * parse_result;
+<% else %>
+    <%= @grammar.prefix %>value_t parse_result;
+<% end %>
+
+    /** Unexpected token received. */
+    <%= @grammar.prefix %>token_t token;
+
+    /** User terminate code. */
+    size_t user_terminate_code;
+} <%= @grammar.prefix %>context_t;
+
+/**************************************************************************
+ * Public data
+ *************************************************************************/
+
+/** Token names. */
+extern const char * <%= @grammar.prefix %>token_names[];
+
+void <%= @grammar.prefix %>context_init(<%= @grammar.prefix %>context_t * context, uint8_t const * input, size_t input_length);
+
+size_t <%= @grammar.prefix %>decode_code_point(uint8_t const * input, size_t input_length,
+        <%= @grammar.prefix %>code_point_t * out_code_point, uint8_t * out_code_point_length);
+
+size_t <%= @grammar.prefix %>lex(<%= @grammar.prefix %>context_t * context, <%= @grammar.prefix %>token_info_t * out_token_info);
+
+size_t <%= @grammar.prefix %>parse(<%= @grammar.prefix %>context_t * context);
+
+<% if @grammar.ast %>
+<%= @grammar.ast_prefix %><%= @grammar.start_rule %><%= @grammar.ast_suffix %> * <%= @grammar.prefix %>result(<%= @grammar.prefix %>context_t * context);
+<% else %>
+<%= start_rule_type[1] %> <%= @grammar.prefix %>result(<%= @grammar.prefix %>context_t * context);
+<% end %>
+
+<%= @grammar.prefix %>position_t <%= @grammar.prefix %>position(<%= @grammar.prefix %>context_t * context);
+
+size_t <%= @grammar.prefix %>user_terminate_code(<%= @grammar.prefix %>context_t * context);
+
+<%= @grammar.prefix %>token_t <%= @grammar.prefix %>token(<%= @grammar.prefix %>context_t * context);

doc/user_guide.md

@@ -7,15 +7,16 @@ ${/remove}
 
 #> Overview
 
-Propane is an LR Parser Generator (LPG) which:
+Propane is a LALR Parser Generator (LPG) which:
 
   * accepts LR(0), SLR, and LALR grammars
   * generates a built-in lexer to tokenize input
   * supports UTF-8 lexer inputs
-  * generates a table-driven parser to parse input in linear time
+  * generates a table-driven shift/reduce parser to parse input in linear time
+  * targets C or D language outputs
+  * optionally supports automatic full AST generation
   * is MIT-licensed
   * is distributable as a standalone Ruby script
-  * supports D language
 
 #> Installation
 
@@ -49,6 +50,909 @@ detailed information about the parser states and transitions.
 A Propane grammar file provides Propane with the patterns, tokens, grammar
 rules, and user code blocks from which to build the generated lexer and parser.
 
+Example grammar file:
+
+```
+<<
+import std.math;
+>>
+
+# Parser values are unsigned integers.
+ptype ulong;
+
+# A few basic arithmetic operators.
+token plus /\\+/;
+token times /\\*/;
+token power /\\*\\*/;
+token integer /\\d+/ <<
+  ulong v;
+  foreach (c; match)
+  {
+    v *= 10;
+    v += (c - '0');
+  }
+  $$ = v;
+>>
+token lparen /\\(/;
+token rparen /\\)/;
+# Drop whitespace.
+drop /\\s+/;
+
+Start -> E1 << $$ = $1; >>
+E1 -> E2 << $$ = $1; >>
+E1 -> E1 plus E2 << $$ = $1 + $3; >>
+E2 -> E3 << $$ = $1; >>
+E2 -> E2 times E3 << $$ = $1 * $3; >>
+E3 -> E4 << $$ = $1; >>
+E3 -> E3 power E4 << $$ = pow($1, $3); >>
+E4 -> integer << $$ = $1; >>
+E4 -> lparen E1 rparen << $$ = $2; >>
+```
+
+Grammar files can contain comment lines beginning with `#` which are ignored.
+White space in the grammar file is also ignored.
+
+It is convention to use the extension `.propane` for the Propane grammar file,
+however any file name is accepted by Propane.
+
+This user guide follows the convention of beginning a token name with a
+lowercase character and beginning a rule name with an uppercase character.
+
+##> User Code Blocks
+
+User code blocks begin following a "<<" token and end with a ">>" token found
+at the end of a line.
+All text lines in the code block are copied verbatim into the output file.
+
+### Standalone Code Blocks
+
+C example:
+
+```
+<<
+#include &lt;stdio.h>
+>>
+```
+
+D example:
+
+```
+<<
+import std.stdio;
+>>
+```
+
+Standalone code blocks are emitted early in the output file as top-level code
+outside the context of any function.
+Standalone code blocks are a good place to include/import any other necessary
+supporting code modules.
+They can also define helper functions that can be reused by lexer or parser
+user code blocks.
+They are emitted in the order they are defined in the grammar file.
+
+For a C target, the word "header" may immediately follow the "<<" token to
+cause Propane to emit the code block in the generated header file rather than
+the generated implementation file.
+This allows including another header that may be necessary to define any types
+needed by a `ptype` directive, for example:
+
+```
+<&lt;header
+#include "mytypes.h"
+>>
+```
+
+### Lexer pattern code blocks
+
+Example:
+
+```
+ptype ulong;
+
+token integer /\\d+/ <<
+  ulong v;
+  foreach (c; match)
+  {
+    v *= 10;
+    v += (c - '0');
+  }
+  $$ = v;
+>>
+```
+
+Lexer code blocks appear following a `token` or pattern expression.
+User code in a lexer code block will be executed when the lexer matches the
+given pattern.
+Assignment to the `$$` symbol will associate a parser value with the lexed
+token.
+This parser value can then be used later in a parser rule.
+
+### Parser rule code blocks
+
+Example:
+
+```
+E1 -> E1 plus E2 << $$ = $1 + $3; >>
+```
+
+Parser rule code blocks appear following a rule expression.
+User code in a parser rule code block will be executed when the parser reduces
+the given rule.
+Assignment to the `$$` symbol will associate a parser value with the reduced
+rule.
+Parser values for the rules or tokens in the rule pattern can be accessed
+positionally with tokens `$1`, `$2`, `$3`, etc...
+
+Parser rule code blocks are not available in AST generation mode.
+In AST generation mode, a full parse tree is automatically constructed in
+memory for user code to traverse after parsing is complete.
+
+##> AST generation mode - the `ast` statement
+
+To activate AST generation mode, place the `ast` statement in your grammar file:
+
+```
+ast;
+```
+
+It is recommended to place this statement early in the grammar.
+
+In AST generation mode various aspects of propane's behavior are changed:
+
+  * Only one `ptype` is allowed.
+  * Parser user code blocks are not supported.
+  * Structure types are generated to represent the parsed tokens and rules as
+  defined in the grammar.
+  * The parse result from `p_result()` points to a `Start` struct containing
+  the entire parse tree for the input. If the user has changed the start rule
+  with the `start` grammar statement, the name of the start struct will be
+  given by the user-specified start rule instead of `Start`.
+
+Example AST generation grammar:
+
+```
+ast;
+
+ptype int;
+
+token a << $$ = 11; >>
+token b << $$ = 22; >>
+token one /1/;
+token two /2/;
+token comma /,/ <<
+  $$ = 42;
+>>
+token lparen /\\(/;
+token rparen /\\)/;
+drop /\\s+/;
+
+Start -> Items;
+
+Items -> Item ItemsMore;
+Items -> ;
+
+ItemsMore -> comma Item ItemsMore;
+ItemsMore -> ;
+
+Item -> a;
+Item -> b;
+Item -> lparen Item rparen;
+Item -> Dual;
+
+Dual -> One Two;
+Dual -> Two One;
+One -> one;
+Two -> two;
+```
+
+The following unit test describes the fields that will be present for an
+example parse:
+
+```
+string input = "a, ((b)), b";
+p_context_t context;
+p_context_init(&context, input);
+assert_eq(P_SUCCESS, p_parse(&context));
+Start * start = p_result(&context);
+assert(start.pItems1 !is null);
+assert(start.pItems !is null);
+Items * items = start.pItems;
+assert(items.pItem !is null);
+assert(items.pItem.pToken1 !is null);
+assert_eq(TOKEN_a, items.pItem.pToken1.token);
+assert_eq(11, items.pItem.pToken1.pvalue);
+assert(items.pItemsMore !is null);
+ItemsMore * itemsmore = items.pItemsMore;
+assert(itemsmore.pItem !is null);
+assert(itemsmore.pItem.pItem !is null);
+assert(itemsmore.pItem.pItem.pItem !is null);
+assert(itemsmore.pItem.pItem.pItem.pToken1 !is null);
+assert_eq(TOKEN_b, itemsmore.pItem.pItem.pItem.pToken1.token);
+assert_eq(22, itemsmore.pItem.pItem.pItem.pToken1.pvalue);
+assert(itemsmore.pItemsMore !is null);
+itemsmore = itemsmore.pItemsMore;
+assert(itemsmore.pItem !is null);
+assert(itemsmore.pItem.pToken1 !is null);
+assert_eq(TOKEN_b, itemsmore.pItem.pToken1.token);
+assert_eq(22, itemsmore.pItem.pToken1.pvalue);
+assert(itemsmore.pItemsMore is null);
+```
+
+## `ast_prefix` and `ast_suffix` statements
+
+In AST generation mode, structure types are defined and named based on the
+rules in the grammar.
+Additionally, a structure type called `Token` is generated to hold parsed
+token information.
+
+These structure names can be modified by using the `ast_prefix` or `ast_suffix`
+statements in the grammar file.
+The field names that point to instances of the structures are not affected by
+the `ast_prefix` or `ast_suffix` values.
+
+For example, if the following two lines were added to the example above:
+
+```
+ast_prefix ABC;
+ast_suffix XYZ;
+```
+
+Then the types would be used as such instead:
+
+```
+string input = "a, ((b)), b";
+p_context_t context;
+p_context_init(&context, input);
+assert_eq(P_SUCCESS, p_parse(&context));
+ABCStartXYZ * start = p_result(&context);
+assert(start.pItems1 !is null);
+assert(start.pItems !is null);
+ABCItemsXYZ * items = start.pItems;
+assert(items.pItem !is null);
+assert(items.pItem.pToken1 !is null);
+assert_eq(TOKEN_a, items.pItem.pToken1.token);
+assert_eq(11, items.pItem.pToken1.pvalue);
+assert(items.pItemsMore !is null);
+ABCItemsMoreXYZ * itemsmore = items.pItemsMore;
+assert(itemsmore.pItem !is null);
+assert(itemsmore.pItem.pItem !is null);
+assert(itemsmore.pItem.pItem.pItem !is null);
+assert(itemsmore.pItem.pItem.pItem.pToken1 !is null);
+```
+
+##> Specifying tokens - the `token` statement
+
+The `token` statement allows defining a lexer token and a pattern to match that
+token.
+The name of the token must be specified immediately following the `token`
+keyword.
+A regular expression pattern may optionally follow the token name.
+If a regular expression pattern is not specified, the name of the token is
+taken to be the pattern.
+See also: ${#Regular expression syntax}.
+
+Example:
+
+```
+token for;
+```
+
+In this example, the token name is `for` and the pattern to match it is
+`/for/`.
+
+Example:
+
+```
+token lbrace /\{/;
+```
+
+In this example, the token name is `lbrace` and a single left curly brace will
+match it.
+
+The `token` statement can also include a user code block.
+The user code block will be executed whenever the token is matched by the
+lexer.
+
+Example:
+
+```
+token if << writeln("'if' keyword lexed"); >>
+```
+
+The `token` statement is actually a shortcut statement for a combination of a
+`tokenid` statement and a pattern statement.
+To define a lexer token without an associated pattern to match it, use a
+`tokenid` statement.
+To define a lexer pattern that may or may not result in a matched token, use
+a pattern statement.
+
+##> Defining tokens without a matching pattern - the `tokenid` statement
+
+The `tokenid` statement can be used to define a token without associating it
+with a lexer pattern that matches it.
+
+Example:
+
+```
+tokenid string;
+```
+
+The `tokenid` statement can be useful when defining a token that may optionally
+be returned by user code associated with a pattern.
+
+It is also useful when lexer modes and multiple lexer patterns are required to
+build up a full token.
+A common example is parsing a string.
+See the ${#Lexer modes} chapter for more information.
+
+##> Specifying a lexer pattern - the pattern statement
+
+A pattern statement is used to define a lexer pattern that can execute user
+code but may not result in a matched token.
+
+Example:
+
+```
+/foo+/ << writeln("saw a foo pattern"); >>
+```
+
+This can be especially useful with ${#Lexer modes}.
+
+See also ${#Regular expression syntax}.
+
+##> Ignoring input sections - the `drop` statement
+
+A `drop` statement can be used to specify a lexer pattern that when matched
+should result in the matched input being dropped and lexing continuing after
+the matched input.
+
+A common use for a `drop` statement would be to ignore whitespace sequences in
+the user input.
+
+Example:
+
+```
+drop /\s+/;
+```
+
+See also ${#Regular expression syntax}.
+
+##> Regular expression syntax
+
+A regular expression ("regex") is used to define lexer patterns in `token`,
+pattern, and `drop` statements.
+A regular expression begins and ends with a `/` character.
+
+Example:
+
+```
+/#.*$/
+```
+
+Regular expressions can include many special characters:
+
+  * The `.` character matches any input character other than a newline.
+  * The `*` character matches any number of the previous regex element.
+  * The `+` character matches one or more of the previous regex element.
+  * The `?` character matches 0 or 1 of the previous regex element.
+  * The `[` character begins a character class.
+  * The `(` character begins a matching group.
+  * The `{` character begins a count qualifier.
+  * The `\` character escapes the following character and changes its meaning:
+    * The `\a` sequence matches an ASCII bell character (0x07).
+    * The `\b` sequence matches an ASCII backspace character (0x08).
+    * The `\d` sequence matches any character `0` through `9`.
+    * The `\f` sequence matches an ASCII form feed character (0x0C).
+    * The `\n` sequence matches an ASCII new line character (0x0A).
+    * The `\r` sequence matches an ASCII carriage return character (0x0D).
+    * The `\s` sequence matches a space, horizontal tab `\t`, carriage return
+    `\r`, a form feed `\f`, or a vertical tab `\v` character.
+    * The `\t` sequence matches an ASCII tab character (0x09).
+    * The `\v` sequence matches an ASCII vertical tab character (0x0B).
+    * Any other character matches itself.
+  * The `|` character creates an alternate match.
+
+Any other character just matches itself in the input stream.
+
+A character class consists of a list of character alternates or character
+ranges that can be matched by the character class.
+For example `[a-zA-Z_]` matches any lowercase character between `a` and `z` or
+any uppercase character between `A` and `Z` or the underscore `_` character.
+Character classes can also be negative character classes if the first character
+after the `[` is a `^` character.
+In this case, the set of characters matched by the character class is the
+inverse of what it otherwise would have been.
+For example, `[^0-9]` matches any character other than 0 through 9.
+
+A matching group can be used to override the pattern sequence that multiplicity
+specifiers apply to.
+For example, the pattern `/foo+/` matches "foo" or "foooo", while the pattern
+`/(foo)+/` matches "foo" or "foofoofoo", but not "foooo".
+
+A count qualifier in curly braces can be used to restrict the number of matches
+of the preceding atom to an explicit minimum and maximum range.
+For example, the pattern `\d{3}` matches exactly 3 digits 0-9.
+Both a minimum and maximum multiplicity count can be specified and separated by
+a comma.
+For example, `/a{1,5}/` matches between 1 and 5 `a` characters.
+Either the minimum or maximum count can be omitted to omit the corresponding
+restriction in the number of matches allowed.
+
+An alternate match is created with the `|` character.
+For example, the pattern `/foo|bar/` matches either the sequence "foo" or the
+sequence "bar".
+
+##> Lexer modes
+
+Lexer modes can be used to change the set of patterns that are matched by the
+lexer.
+A common use for lexer modes is to match strings.
+
+Example:
+
+```
+<<
+string mystringvalue;
+>>
+
+tokenid str;
+
+# String processing
+/"/ <<
+  mystringvalue = "";
+  $mode(string);
+>>
+string: /[^"]+/ << mystringvalue += match; >>
+string: /"/ <<
+  $mode(default);
+  return $token(str);
+>>
+```
+
+A lexer mode is defined by placing the name before a colon (`:`) character that
+precedes a token or pattern statement.
+The token or pattern statement is restricted to only applying if the named mode
+is active.
+
+By default, the active lexer mode is named `default`.
+A `$mode()` call within a lexer code block can be used to change lexer modes.
+
+In the above example, when the lexer in the default mode sees a doublequote
+(`"`) character, the lexer code block will clear the `mystringvalue` variable
+and will set the lexer mode to `string`.
+When the lexer begins looking for patterns to match against the input, it will
+now look only for patterns tagged for the `string` lexer mode.
+Any non-`"` character will be appended to the `mystringvalue` string.
+A `"` character will end the `string` lexer mode and return to the `default`
+lexer mode.
+It also returns the `str` token now that the token is complete.
+
+Note that the token name `str` above could have been `string` instead - the
+namespace for token names is distinct from the namespace for lexer modes.
+
+##> Specifying parser value types - the `ptype` statement
+
+The `ptype` statement is used to define parser value type(s).
+Example:
+
+```
+ptype void *;
+```
+
+This defines the default parser value type to be `void *` (this is, in fact,
+the default parser value type if the grammar file does not specify otherwise).
+
+Each defined lexer token type and parser rule has an associated parser value
+type.
+When the lexer runs, each lexed token has a parser value associated with it.
+When the parser runs, each instance of a reduced rule has a parser value
+associated with it.
+Propane supports using different parser value types for different rules and
+token types.
+The example `ptype` statement above defines the default parser value type.
+A parser value type name can optionally be specified following the `ptype`
+keyword.
+For example:
+
+```
+ptype Value;
+ptype array = Value[];
+ptype dict = Value[string];
+
+Object -> lbrace rbrace << $$ = new Value(); >>
+
+Values (array) -> Value << $$ = [$1]; >>
+Values -> Values comma Value << $$ = $1 ~ [$3]; >>
+
+KeyValue (dict) -> string colon Value << $$ = [$1: $3]; >>
+```
+
+In this example, the default parser value type is `Value`.
+A parser value type named `array` is defined to mean `Value[]`.
+A parser value type named `dict` is defined to mean `Value[string]`.
+Any defined tokens or rules that do not specify a parser value type will have
+the default parser value type associated with them.
+To associate a different parser value type with a token or rule, write the
+parser value type name in parentheses following the name of the token or rule.
+In this example:
+
+  * a reduced `Object`'s parser value has a type of `Value`.
+  * a reduced `Values`'s parser value has a type of `Value[]`.
+  * a reduced `KeyValue`'s parser value has a type of `Value[string]`.
+
+When AST generation mode is active, the `ptype` functionality works differently.
+In this mode, only one `ptype` is used by the parser.
+Lexer user code blocks may assign a parse value to the generated `Token` node
+by assigning to `$$` within a lexer code block.
+The type of the parse value `$$` is given by the global `ptype` type.
+
+##> Specifying a parser rule - the rule statement
+
+Rule statements create parser rules which define the grammar that will be
+parsed by the generated parser.
+
+Multiple rules with the same name can be specified.
+Rules with the same name define a rule set for that name and act as
+alternatives that the parser can accept when attempting to match a reference to
+that rule.
+
+The default start rule name is `Start`.
+This can be changed with the `start` statement.
+The grammar file must define a rule with the name of the start rule name which
+will be used as the top-level starting rule that the parser attempts to reduce.
+
+Example:
+
+```
+ptype ulong;
+start Top;
+token word /[a-z]+/ << $$ = match.length; >>
+Top -> word << $$ = $1; >>
+```
+
+In the above example the `Top` rule is defined to match a single `word`
+token.
+
+Another example:
+
+```
+Start -> E1 << $$ = $1; >>
+E1 -> E2 << $$ = $1; >>
+E1 -> E1 plus E2 << $$ = $1 + $3; >>
+E2 -> E3 << $$ = $1; >>
+E2 -> E2 times E3 << $$ = $1 * $3; >>
+E3 -> E4 << $$ = $1; >>
+E3 -> E3 power E4 << $$ = pow($1, $3); >>
+E4 -> integer << $$ = $1; >>
+E4 -> lparen E1 rparen << $$ = $2; >>
+```
+
+This example uses the default start rule name of `Start`.
+
+A parser rule has zero or more terms on the right side of its definition.
+Each of these terms is either a token name or a rule name.
+A term can be immediately followed by a `?` character to signify that it is
+optional.
+Another example:
+
+```
+token public;
+token private;
+token int;
+token ident /[a-zA-Z_][a-zA-Z_0-9]*/;
+token semicolon /;/;
+IntegerDeclaration -> Visibility? int ident semicolon;
+Visibility -> public;
+Visibility -> private;
+```
+
+In a parser rule code block, parser values for the right side terms are
+accessible as `$1` for the first term's parser value, `$2` for the second
+term's parser value, etc...
+The `$$` symbol accesses the output parser value for this rule.
+The above examples demonstrate how the parser values for the rule components
+can be used to produce the parser value for the accepted rule.
+
+Parser rule code blocks are not allowed and not used when AST generation mode
+is active.
+
+##> Specifying the parser start rule name - the `start` statement
+
+The start rule can be changed from the default of `Start` by using the `start`
+statement.
+Example:
+
+```
+start MyStartRule;
+```
+
+##> Specifying the parser module name - the `module` statement
+
+The `module` statement can be used to specify the module name for a generated
+D module.
+
+```
+module proj.parser;
+```
+
+If a module statement is not present, then the generated D module will not
+contain a module statement and the default module name will be used.
+
+##> Specifying the generated API prefix - the `prefix` statement
+
+By default the public API (types, constants, and functions) of the generated
+lexer and parser uses a prefix of `p_`.
+
+This prefix can be changed with the `prefix` statement.
+
+Example:
+
+```
+prefix myparser_;
+```
+
+With a parser generated with this `prefix` statement, instead of calling
+`p_context_init()` you would call `myparser_context_init()`.
+
+The `prefix` statement can be optionally used if you would like to change the
+prefix used by your generated lexer and parser to something other than the
+default.
+
+It can also be used when generating multiple lexers/parsers to be used in the
+same program to avoid symbol collisions.
+
+##> User termination of the lexer or parser
+
+Propane supports allowing lexer or parser user code blocks to terminate
+execution of the parser.
+Some example uses of this functionality could be to:
+
+  * Detect integer overflow when lexing an integer literal constant.
+  * Detect and report an error as soon as possible during parsing before continuing to parse any more of the input.
+  * Determine whether parsing should stop and instead be performed using a different parser version.
+
+To terminate parsing from a lexer or parser user code block, use the
+`$terminate(code)` function, passing an integer expression argument.
+For example:
+
+```
+NewExpression -> new Expression << $terminate(42); >>
+```
+
+The value passed to the `$terminate()` function is known as the "user terminate
+code".
+If the parser returns a `P_USER_TERMINATED` result code, then the user
+terminate code can be accessed using the `p_user_terminate_code()` API
+function.
+
+#> Propane generated API
+
+By default, Propane uses a prefix of `p_` when generating a lexer/parser.
+This prefix is used for all publicly declared types and functions.
+The uppercase version of the prefix is used for all constant values.
+
+This section documents the generated API using the default `p_` or `P_` names.
+
+##> Constants
+
+Propane generates the following result code constants:
+
+* `P_SUCCESS`: A successful decode/lex/parse operation has taken place.
+* `P_DECODE_ERROR`: An error occurred when decoding UTF-8 input.
+* `P_UNEXPECTED_INPUT`: Input was received by the lexer that does not match any lexer pattern.
+* `P_UNEXPECTED_TOKEN`: A token was seen in a location that does not match any parser rule.
+* `P_DROP`: The lexer matched a drop pattern.
+* `P_EOF`: The lexer reached the end of the input string.
+* `P_USER_TERMINATED`: A parser user code block has requested to terminate the parser.
+
+Result codes are returned by the functions `p_decode_input()`, `p_lex()`, and `p_parse()`.
+
+##> Types
+
+### `p_context_t`
+
+Propane defines a `p_context_t` structure type.
+The structure is intended to be used opaquely and stores information related to
+the state of the lexer and parser.
+Integrating code must define an instance of the `p_context_t` structure.
+A pointer to this instance is passed to the generated functions.
+
+### `p_position_t`
+
+The `p_position_t` structure contains two fields `row` and `col`.
+These fields contain the 0-based row and column describing a parser position.
+
+### AST Node Types
+
+If AST generation mode is enabled, a structure type for each rule will be
+generated.
+The name of the structure type is given by the name of the rule.
+Additionally a structure type called `Token` is generated to represent an
+AST node which refers to a raw parser token rather than a composite rule.
+
+#### AST Node Fields
+
+A `Token` node has two fields:
+
+  * `token` which specifies which token was parsed (one of `TOKEN_*`)
+  * `pvalue` which specifies the parser value for the token. If a lexer user
+  code block assigned to `$$`, the assigned value will be stored here.
+
+The other generated AST node structures have fields generated based on the
+right hand side components specified for all rules of a given name.
+
+In this example:
+
+```
+Start -> Items;
+
+Items -> Item ItemsMore;
+Items -> ;
+```
+
+The `Start` structure will have a field called `pItems` and another field of
+the same name but with a positional suffix (`pItems1`) which both point to the
+parsed `Items` node.
+Their value will be null if the parsed `Items` rule was empty.
+
+The `Items` structure will have fields:
+
+  * `pItem` and `pItem1` which point to the parsed `Item` structure.
+  * `pItemsMore` and `pItemsMore2` which point to the parsed `ItemsMore` structure.
+
+If a rule can be empty (for example in the second `Items` rule above), then
+an instance of a pointer to that rule's generated AST node will be null if the
+parser matches the empty rule definition.
+
+The non-positional AST node field pointer will not be generated if there are
+multiple positions in which an instance of the node it points to could be
+present.
+For example, in the below rules:
+
+```
+Dual -> One Two;
+Dual -> Two One;
+```
+
+The generated `Dual` structure will contain `pOne1`, `pTwo2`, `pTwo1`, and
+`pOne2` fields.
+However, a `pOne` field and `pTwo` field will not be generated since it would
+be ambiguous which one was matched.
+
+If the first rule is matched, then `pOne1` and `pTwo2` will be non-null while
+`pTwo1` and `pOne2` will be null.
+If the second rule is matched instead, then the opposite would be the case.
+
+##> Functions
+
+### `p_context_init`
+
+The `p_context_init()` function must be called to initialize the context
+structure.
+The input to be used for lexing/parsing is passed in when initializing the
+context structure.
+
+C example:
+
+```
+p_context_t context;
+p_context_init(&context, input, input_length);
+```
+
+D example:
+
+```
+p_context_t context;
+p_context_init(&context, input);
+```
+
+### `p_parse`
+
+The `p_parse()` function is the main entry point to the parser.
+It must be passed a pointer to an initialized context structure.
+
+Example:
+
+```
+p_context_t context;
+p_context_init(&context, input, input_length);
+size_t result = p_parse(&context);
+```
+
+### `p_result`
+
+The `p_result()` function can be used to retrieve the final parse value after
+`p_parse()` returns a `P_SUCCESS` value.
+
+Example:
+
+```
+p_context_t context;
+p_context_init(&context, input, input_length);
+size_t result = p_parse(&context);
+if (p_parse(&context) == P_SUCCESS)
+{
+    result = p_result(&context);
+}
+```
+
+If AST generation mode is active, then the `p_result()` function returns a
+`Start *` pointing to the `Start` AST structure.
+
+### `p_position`
+
+The `p_position()` function can be used to retrieve the parser position where
+an error occurred.
+
+Example:
+
+```
+p_context_t context;
+p_context_init(&context, input, input_length);
+size_t result = p_parse(&context);
+if (p_parse(&context) == P_UNEXPECTED_TOKEN)
+{
+    p_position_t error_position = p_position(&context);
+    fprintf(stderr, "Error: unexpected token at row %u column %u\n",
+        error_position.row + 1, error_position.col + 1);
+}
+```
+
+### `p_user_terminate_code`
+
+The `p_user_terminate_code()` function can be used to retrieve the user
+terminate code after `p_parse()` returns a `P_USER_TERMINATED` value.
+User terminate codes are arbitrary values that can be defined by the user to
+be returned when the user requests to terminate parsing.
+They have no particular meaning to Propane.
+
+Example:
+
+```
+if (p_parse(&context) == P_USER_TERMINATED)
+{
+    size_t user_terminate_code = p_user_terminate_code(&context);
+}
+```
+
+### `p_token`
+
+The `p_token()` function can be used to retrieve the current parse token.
+This is useful after `p_parse()` returns a `P_UNEXPECTED_TOKEN` value.
+terminate code after `p_parse()` returns a `P_USER_TERMINATED` value to
+indicate what token the parser was not expecting.
+
+Example:
+
+```
+if (p_parse(&context) == P_UNEXPECTED_TOKEN)
+{
+    p_token_t unexpected_token = p_token(&context);
+}
+```
+
+##> Data
+
+### `p_token_names`
+
+The `p_token_names` array contains the grammar-specified token names.
+It is indexed by the token ID.
+
+C example:
+
+```
+p_context_t context;
+p_context_init(&context, input, input_length);
+size_t result = p_parse(&context);
+if (p_parse(&context) == P_UNEXPECTED_TOKEN)
+{
+    p_position_t error_position = p_position(&context);
+    fprintf(stderr, "Error: unexpected token `%s' at row %u column %u\n",
+        p_token_names[context.token],
+        error_position.row + 1, error_position.col + 1);
+}
+```
+
 #> License
 
 Propane is licensed under the terms of the MIT License:

lib/propane.rb

@@ -1,6 +1,7 @@
 require "erb"
 require "set"
 require "stringio"
+require_relative "propane/assets"
 require_relative "propane/cli"
 require_relative "propane/code_point_range"
 require_relative "propane/fa"

lib/propane/assets.rb

@@ -0,0 +1,10 @@
+class Propane
+  module Assets
+    class << self
+      def get(name)
+        path = File.join(File.dirname(File.expand_path(__FILE__)), "../../assets/#{name}")
+        File.binread(path)
+      end
+    end
+  end
+end

lib/propane/cli.rb

@@ -24,7 +24,7 @@ EOF
               log_file = args[i]
             end
           when "--version"
-            puts "propane v#{VERSION}"
+            puts "propane version #{VERSION}"
             return 0
           when "-h", "--help"
             puts USAGE

lib/propane/generator.rb

@@ -10,15 +10,28 @@ class Propane
       else
         @log = StringIO.new
       end
-      @classname = @grammar.classname || File.basename(output_file).sub(%r{[^a-zA-Z0-9].*}, "").capitalize
+      @language =
+        if output_file =~ /\.([a-z]+)$/
+          $1
+        else
+          "d"
+        end
       process_grammar!
     end
 
     def generate
-      erb = ERB.new(File.read(File.join(File.dirname(File.expand_path(__FILE__)), "../../assets/parser.d.erb")), trim_mode: "<>")
-      result = erb.result(binding.clone)
-      File.open(@output_file, "wb") do |fh|
-        fh.write(result)
+      extensions = [@language]
+      if @language == "c"
+        extensions += %w[h]
+      end
+      extensions.each do |extension|
+        template = Assets.get("parser.#{extension}.erb")
+        erb = ERB.new(template, trim_mode: "<>")
+        output_file = @output_file.sub(%r{\.[a-z]+$}, ".#{extension}")
+        result = erb.result(binding.clone)
+        File.open(output_file, "wb") do |fh|
+          fh.write(result)
+        end
       end
       @log.close
     end
@@ -38,6 +51,7 @@ class Propane
       unless found_default
         raise Error.new("No patterns found for default mode")
       end
+      check_ptypes!
       # Add EOF token.
       @grammar.tokens << Token.new("$EOF", nil, nil)
       tokens_by_name = {}
@@ -53,11 +67,14 @@ class Propane
         tokens_by_name[token.name] = token
       end
       # Check for user start rule.
-      unless @grammar.rules.find {|rule| rule.name == "Start"}
-        raise Error.new("Start rule not found")
+      unless @grammar.rules.find {|rule| rule.name == @grammar.start_rule}
+        raise Error.new("Start rule `#{@grammar.start_rule}` not found")
       end
       # Add "real" start rule.
-      @grammar.rules.unshift(Rule.new("$Start", ["Start", "$EOF"], nil, nil, nil))
+      @grammar.rules.unshift(Rule.new("$Start", [@grammar.start_rule, "$EOF"], nil, nil, nil))
+      # Generate and add rules for optional components.
+      generate_optional_component_rules!(tokens_by_name)
+      # Build rule sets.
       rule_sets = {}
       rule_set_id = @grammar.tokens.size
       @grammar.rules.each_with_index do |rule, rule_id|
@@ -106,12 +123,57 @@ class Propane
         end
       end
       determine_possibly_empty_rulesets!(rule_sets)
+      rule_sets.each do |name, rule_set|
+        rule_set.finalize(@grammar)
+      end
       # Generate the lexer.
       @lexer = Lexer.new(@grammar)
       # Generate the parser.
       @parser = Parser.new(@grammar, rule_sets, @log)
     end
 
+    # Check that any referenced ptypes have been defined.
+    def check_ptypes!
+      (@grammar.patterns + @grammar.tokens + @grammar.rules).each do |potor|
+        if potor.ptypename
+          unless @grammar.ptypes.include?(potor.ptypename)
+            raise Error.new("Error: Line #{potor.line_number}: ptype #{potor.ptypename} not declared. Declare with `ptype` statement.")
+          end
+        end
+      end
+    end
+
+    # Generate and add rules for any optional components.
+    def generate_optional_component_rules!(tokens_by_name)
+      optional_rules_added = Set.new
+      @grammar.rules.each do |rule|
+        rule.components.each do |component|
+          if component =~ /^(.*)\?$/
+            c = $1
+            unless optional_rules_added.include?(component)
+              # Create two rules for the optional component: one empty and
+              # one just matching the component.
+              # We need to find the ptypename for the optional component in
+              # order to copy it to the generated rules.
+              if tokens_by_name[c]
+                # The optional component is a token.
+                ptypename = tokens_by_name[c].ptypename
+              else
+                # The optional component must be a rule, so find any instance
+                # of that rule that specifies a ptypename.
+                ptypename = @grammar.rules.reduce(nil) do |result, rule|
+                  rule.name == c && rule.ptypename ? rule.ptypename : result
+                end
+              end
+              @grammar.rules << Rule.new(component, [], nil, ptypename, rule.line_number)
+              @grammar.rules << Rule.new(component, [c], "$$ = $1;\n", ptypename, rule.line_number)
+              optional_rules_added << component
+            end
+          end
+        end
+      end
+    end
+
     # Determine which grammar rules could expand to empty sequences.
     #
     # @param rule_sets [Hash]
@@ -183,19 +245,53 @@ class Propane
     #   Expanded user code block.
     def expand_code(code, parser, rule, pattern)
       code = code.gsub(/\$token\(([$\w]+)\)/) do |match|
-        "Token(TOKEN_#{Token.code_name($1)})"
+        "TOKEN_#{Token.code_name($1)}"
+      end
+      code = code.gsub(/\$terminate\((.*)\);/) do |match|
+        user_terminate_code = $1
+        retval = rule ? "P_USER_TERMINATED" : "TERMINATE_TOKEN_ID"
+        case @language
+        when "c"
+          "context->user_terminate_code = (#{user_terminate_code}); return #{retval};"
+        when "d"
+          "context.user_terminate_code = (#{user_terminate_code}); return #{retval};"
+        end
       end
       if parser
         code = code.gsub(/\$\$/) do |match|
-          "_pvalue.v_#{rule.ptypename}"
+          case @language
+          when "c"
+            "_pvalue->v_#{rule.ptypename}"
+          when "d"
+            "_pvalue.v_#{rule.ptypename}"
+          end
         end
         code = code.gsub(/\$(\d+)/) do |match|
           index = $1.to_i
-          "statevalues[$-1-n_states+#{index}].pvalue.v_#{rule.components[index - 1].ptypename}"
+          case @language
+          when "c"
+            "state_values_stack_index(statevalues, -1 - (int)n_states + #{index})->pvalue.v_#{rule.components[index - 1].ptypename}"
+          when "d"
+            "statevalues[$-1-n_states+#{index}].pvalue.v_#{rule.components[index - 1].ptypename}"
+          end
         end
       else
         code = code.gsub(/\$\$/) do |match|
-          "result.pvalue.v_#{pattern.ptypename}"
+          if @grammar.ast
+            case @language
+            when "c"
+              "out_token_info->pvalue"
+            when "d"
+              "out_token_info.pvalue"
+            end
+          else
+            case @language
+            when "c"
+              "out_token_info->pvalue.v_#{pattern.ptypename}"
+            when "d"
+              "out_token_info.pvalue.v_#{pattern.ptypename}"
+            end
+          end
         end
         code = code.gsub(/\$mode\(([a-zA-Z_][a-zA-Z_0-9]*)\)/) do |match|
           mode_name = $1
@@ -203,7 +299,12 @@ class Propane
           unless mode_id
             raise Error.new("Lexer mode '#{mode_name}' not found")
           end
-          "m_mode = #{mode_id}u"
+          case @language
+          when "c"
+            "context->mode = #{mode_id}u"
+          when "d"
+            "context.mode = #{mode_id}u"
+          end
         end
       end
       code
@@ -215,11 +316,43 @@ class Propane
     #   Start rule parser value type name and type string.
     def start_rule_type
       start_rule = @grammar.rules.find do |rule|
-        rule.name == "Start"
+        rule.name == @grammar.start_rule
       end
       [start_rule.ptypename, @grammar.ptypes[start_rule.ptypename]]
     end
 
+    # Get an unsigned integer type that can hold the given maximum value.
+    #
+    # @param max [Integer]
+    #   Maximum value to store.
+    #
+    # @return [String]
+    #   Type.
+    def get_type_for(max)
+      if max <= 0xFF
+        case @language
+        when "c"
+          "uint8_t"
+        when "d"
+          "ubyte"
+        end
+      elsif max <= 0xFFFF
+        case @language
+        when "c"
+          "uint16_t"
+        when "d"
+          "ushort"
+        end
+      else
+        case @language
+        when "c"
+          "uint32_t"
+        else
+          "uint"
+        end
+      end
+    end
+
   end
 
 end

lib/propane/grammar.rb

@@ -5,24 +5,33 @@ class Propane
     # Reserve identifiers beginning with a double-underscore for internal use.
     IDENTIFIER_REGEX = /(?:[a-zA-Z]|_[a-zA-Z0-9])[a-zA-Z_0-9]*/
 
-    attr_reader :classname
+    attr_reader :ast
+    attr_reader :ast_prefix
+    attr_reader :ast_suffix
     attr_reader :modulename
     attr_reader :patterns
     attr_reader :rules
+    attr_reader :start_rule
     attr_reader :tokens
     attr_reader :code_blocks
     attr_reader :ptypes
+    attr_reader :prefix
 
     def initialize(input)
       @patterns = []
+      @start_rule = "Start"
       @tokens = []
       @rules = []
-      @code_blocks = []
+      @code_blocks = {}
       @line_number = 1
       @next_line_number = @line_number
       @mode = nil
       @input = input.gsub("\r\n", "\n")
       @ptypes = {"default" => "void *"}
+      @prefix = "p_"
+      @ast = false
+      @ast_prefix = ""
+      @ast_suffix = ""
       parse_grammar!
     end
 
@@ -30,6 +39,14 @@ class Propane
       @ptypes["default"]
     end
 
+    def invalid_token_id
+      @tokens.size
+    end
+
+    def terminate_token_id
+      @tokens.size + 1
+    end
+
     private
 
     def parse_grammar!
@@ -42,15 +59,19 @@ class Propane
       if parse_white_space!
       elsif parse_comment_line!
       elsif @mode.nil? && parse_mode_label!
+      elsif parse_ast_statement!
+      elsif parse_ast_prefix_statement!
+      elsif parse_ast_suffix_statement!
       elsif parse_module_statement!
-      elsif parse_class_statement!
       elsif parse_ptype_statement!
       elsif parse_pattern_statement!
+      elsif parse_start_statement!
       elsif parse_token_statement!
       elsif parse_tokenid_statement!
       elsif parse_drop_statement!
       elsif parse_rule_statement!
       elsif parse_code_block_statement!
+      elsif parse_prefix_statement!
       else
         if @input.size > 25
           @input = @input.slice(0..20) + "..."
@@ -73,6 +94,24 @@ class Propane
       consume!(/#.*\n/)
     end
 
+    def parse_ast_statement!
+      if consume!(/ast\s*;/)
+        @ast = true
+      end
+    end
+
+    def parse_ast_prefix_statement!
+      if md = consume!(/ast_prefix\s+(\w+)\s*;/)
+        @ast_prefix = md[1]
+      end
+    end
+
+    def parse_ast_suffix_statement!
+      if md = consume!(/ast_suffix\s+(\w+)\s*;/)
+        @ast_suffix = md[1]
+      end
+    end
+
     def parse_module_statement!
       if consume!(/module\s+/)
         md = consume!(/([\w.]+)\s*/, "expected module name")
@@ -83,20 +122,13 @@ class Propane
       end
     end
 
-    def parse_class_statement!
-      if consume!(/class\s+/)
-        md = consume!(/([\w.]+)\s*/, "expected class name")
-        @classname = md[1]
-        consume!(/;/, "expected `;'")
-        @mode = nil
-        true
-      end
-    end
-
     def parse_ptype_statement!
       if consume!(/ptype\s+/)
         name = "default"
         if md = consume!(/(#{IDENTIFIER_REGEX})\s*=\s*/)
+          if @ast
+            raise Error.new("Multiple ptypes are unsupported in AST mode")
+          end
           name = md[1]
         end
         md = consume!(/([^;]+);/, "expected parser result type expression")
@@ -109,12 +141,15 @@ class Propane
         md = consume!(/(#{IDENTIFIER_REGEX})\s*/, "expected token name")
         name = md[1]
         if md = consume!(/\((#{IDENTIFIER_REGEX})\)\s*/)
+          if @ast
+            raise Error.new("Multiple ptypes are unsupported in AST mode")
+          end
           ptypename = md[1]
         end
         pattern = parse_pattern! || name
         consume!(/\s+/)
         unless code = parse_code_block!
-          consume!(/;/, "expected pattern or `;' or code block")
+          consume!(/;/, "expected `;' or code block")
         end
         token = Token.new(name, ptypename, @line_number)
         @tokens << token
@@ -130,6 +165,9 @@ class Propane
         md = consume!(/(#{IDENTIFIER_REGEX})\s*/, "expected token name")
         name = md[1]
         if md = consume!(/\((#{IDENTIFIER_REGEX})\)\s*/)
+          if @ast
+            raise Error.new("Multiple ptypes are unsupported in AST mode")
+          end
           ptypename = md[1]
         end
         consume!(/;/, "expected `;'");
@@ -148,7 +186,7 @@ class Propane
         end
         consume!(/\s+/)
         consume!(/;/, "expected `;'")
-        @patterns << Pattern.new(pattern: pattern, line_number: @line_number, drop: true, mode: @mode)
+        @patterns << Pattern.new(pattern: pattern, line_number: @line_number, mode: @mode)
         @mode = nil
         true
       end
@@ -157,10 +195,17 @@ class Propane
     def parse_rule_statement!
       if md = consume!(/(#{IDENTIFIER_REGEX})\s*(?:\((#{IDENTIFIER_REGEX})\))?\s*->\s*/)
         rule_name, ptypename = *md[1, 2]
-        md = consume!(/((?:#{IDENTIFIER_REGEX}\s*)*)\s*/, "expected rule component list")
+        if @ast && ptypename
+          raise Error.new("Multiple ptypes are unsupported in AST mode")
+        end
+        md = consume!(/((?:#{IDENTIFIER_REGEX}\??\s*)*)\s*/, "expected rule component list")
         components = md[1].strip.split(/\s+/)
-        unless code = parse_code_block!
-          consume!(/;/, "expected pattern or `;' or code block")
+        if @ast
+          consume!(/;/, "expected `;'")
+        else
+          unless code = parse_code_block!
+            consume!(/;/, "expected `;' or code block")
+          end
         end
         @rules << Rule.new(rule_name, components, code, ptypename, @line_number)
         @mode = nil
@@ -172,6 +217,9 @@ class Propane
       if pattern = parse_pattern!
         consume!(/\s+/)
         if md = consume!(/\((#{IDENTIFIER_REGEX})\)\s*/)
+          if @ast
+            raise Error.new("Multiple ptypes are unsupported in AST mode")
+          end
           ptypename = md[1]
         end
         unless code = parse_code_block!
@@ -183,14 +231,34 @@ class Propane
       end
     end
 
+    def parse_start_statement!
+      if md = consume!(/start\s+(\w+)\s*;/)
+        @start_rule = md[1]
+      end
+    end
+
     def parse_code_block_statement!
-      if code = parse_code_block!
-        @code_blocks << code
+      if md = consume!(/<<([a-z]*)(.*?)>>\n/m)
+        name, code = md[1..2]
+        code.sub!(/\A\n/, "")
+        code += "\n" unless code.end_with?("\n")
+        if @code_blocks[name]
+          @code_blocks[name] += code
+        else
+          @code_blocks[name] = code
+        end
         @mode = nil
         true
       end
     end
 
+    def parse_prefix_statement!
+      if md = consume!(/prefix\s+(#{IDENTIFIER_REGEX})\s*;/)
+        @prefix = md[1]
+        true
+      end
+    end
+
     def parse_pattern!
       if md = consume!(%r{/})
         pattern = ""
@@ -211,8 +279,11 @@ class Propane
     end
 
     def parse_code_block!
-      if md = consume!(/<<\n(.*?)^>>\n/m)
-        md[1]
+      if md = consume!(/<<(.*?)>>\n/m)
+        code = md[1]
+        code.sub!(/\A\n/, "")
+        code += "\n" unless code.end_with?("\n")
+        code
       end
     end
 

lib/propane/lexer.rb

@@ -1,55 +1,13 @@
 class Propane
   class Lexer
 
+    attr_reader :state_table
+    attr_reader :transition_table
+    attr_reader :mode_table
+
     def initialize(grammar)
       @grammar = grammar
-    end
-
-    def build_tables
-      @modes = @grammar.patterns.group_by do |pattern|
-        pattern.mode
-      end.transform_values do |patterns|
-        {dfa: DFA.new(patterns)}
-      end
-      @modes.each_with_index do |(mode_name, mode_info), index|
-        mode_info[:id] = index
-      end
-      transition_table = []
-      state_table = []
-      mode_table = []
-      @modes.each do |mode_name, mode_info|
-        state_table_offset = state_table.size
-        mode_table << {
-          state_table_offset: state_table_offset,
-        }
-        states = mode_info[:dfa].enumerate
-        states.each do |state, id|
-          drop = state.accepts && state.accepts.drop?
-          token =
-            if state.accepts && state.accepts.token
-              state.accepts.token.id
-            end
-          code_id =
-            if state.accepts && state.accepts.code_id
-              state.accepts.code_id
-            end
-          state_table << {
-            transition_table_index: transition_table.size,
-            n_transitions: state.transitions.size,
-            drop: drop,
-            token: token,
-            code_id: code_id,
-          }
-          state.transitions.each do |transition|
-            transition_table << {
-              first: transition.code_point_range.first,
-              last: transition.code_point_range.last,
-              destination: states[transition.destination] + state_table_offset,
-            }
-          end
-        end
-      end
-      [transition_table, state_table, mode_table]
+      build_tables!
     end
 
     # Get ID for a mode.
@@ -65,5 +23,46 @@ class Propane
       end
     end
 
+    private
+
+    def build_tables!
+      @modes = @grammar.patterns.group_by do |pattern|
+        pattern.mode
+      end.transform_values do |patterns|
+        {dfa: DFA.new(patterns)}
+      end
+      @modes.each_with_index do |(mode_name, mode_info), index|
+        mode_info[:id] = index
+      end
+      @state_table = []
+      @transition_table = []
+      @mode_table = []
+      @modes.each do |mode_name, mode_info|
+        state_table_offset = @state_table.size
+        @mode_table << {
+          state_table_offset: state_table_offset,
+        }
+        states = mode_info[:dfa].enumerate
+        states.each do |state, id|
+          token = state.accepts && state.accepts.token && state.accepts.token.id
+          code_id = state.accepts && state.accepts.code_id && state.accepts.code_id
+          @state_table << {
+            transition_table_index: @transition_table.size,
+            n_transitions: state.transitions.size,
+            accepts: !!state.accepts,
+            token: token,
+            code_id: code_id,
+          }
+          state.transitions.each do |transition|
+            @transition_table << {
+              first: transition.code_point_range.first,
+              last: transition.code_point_range.last,
+              destination: states[transition.destination] + state_table_offset,
+            }
+          end
+        end
+      end
+    end
+
   end
 end

lib/propane/parser.rb

@@ -2,6 +2,11 @@ class Propane
 
   class Parser
 
+    attr_reader :state_table
+    attr_reader :shift_table
+    attr_reader :reduce_table
+    attr_reader :rule_sets
+
     def initialize(grammar, rule_sets, log)
       @grammar = grammar
       @rule_sets = rule_sets
@@ -33,12 +38,15 @@ class Propane
 
       build_reduce_actions!
       write_log!
+      build_tables!
     end
 
-    def build_tables
-      shift_table = []
-      state_table = []
-      reduce_table = []
+    private
+
+    def build_tables!
+      @state_table = []
+      @shift_table = []
+      @reduce_table = []
       @item_sets.each do |item_set|
         shift_entries = item_set.following_symbols.map do |following_symbol|
           state_id =
@@ -48,37 +56,36 @@ class Propane
               item_set.following_item_set[following_symbol].id
             end
           {
-            token_id: following_symbol.id,
+            symbol_id: following_symbol.id,
             state_id: state_id,
           }
         end
         reduce_entries =
           case ra = item_set.reduce_actions
           when Rule
-            [{token_id: @grammar.tokens.size, rule_id: ra.id,
-              rule_set_id: ra.rule_set.id, n_states: ra.components.size}]
+            [{token_id: @grammar.invalid_token_id, rule_id: ra.id, rule: ra,
+              rule_set_id: ra.rule_set.id, n_states: ra.components.size,
+              propagate_optional_target: ra.optional? && ra.components.size == 1}]
           when Hash
             ra.map do |token, rule|
-              {token_id: token.id, rule_id: rule.id,
-               rule_set_id: rule.rule_set.id, n_states: rule.components.size}
+              {token_id: token.id, rule_id: rule.id, rule: rule,
+               rule_set_id: rule.rule_set.id, n_states: rule.components.size,
+               propagate_optional_target: rule.optional? && rule.components.size == 1}
             end
           else
             []
           end
-        state_table << {
-          shift_index: shift_table.size,
+        @state_table << {
+          shift_index: @shift_table.size,
           n_shifts: shift_entries.size,
-          reduce_index: reduce_table.size,
+          reduce_index: @reduce_table.size,
           n_reduces: reduce_entries.size,
         }
-        shift_table += shift_entries
-        reduce_table += reduce_entries
+        @shift_table += shift_entries
+        @reduce_table += reduce_entries
       end
-      [state_table, shift_table, reduce_table]
     end
 
-    private
-
     def process_item_set(item_set)
       item_set.following_symbols.each do |following_symbol|
         unless following_symbol.name == "$EOF"
@@ -129,7 +136,7 @@ class Propane
       # possible following tokens, we will only look in the item sets leading
       # up to this one. This restriction gives us a more precise lookahead set,
       # and allows us to parse LALR grammars.
-      item_sets = item_set.leading_item_sets
+      item_sets = Set[item_set] + item_set.leading_item_sets
       reduce_rules.reduce({}) do |reduce_actions, reduce_rule|
         lookahead_tokens_for_rule = build_lookahead_tokens_to_reduce(reduce_rule, item_sets)
         lookahead_tokens_for_rule.each do |lookahead_token|
@@ -242,7 +249,7 @@ class Propane
         @log.puts "  Reduce actions:"
         case item_set.reduce_actions
         when Rule
-          @log.puts "    * => #{item_set.reduce_actions.id} (#{item_set.reduce_actions.name})"
+          @log.puts "    * => rule #{item_set.reduce_actions.id}, rule set #{@rule_sets[item_set.reduce_actions.name].id} (#{item_set.reduce_actions.name})"
         when Hash
           item_set.reduce_actions.each do |token, rule|
             @log.puts "    lookahead #{token.name} => #{rule.name} (#{rule.id}), rule set ##{rule.rule_set.id}"

lib/propane/parser/item_set.rb

@@ -87,14 +87,24 @@ class Propane
 
       # Set of ItemSets that lead to this ItemSet.
       #
-      # This set includes this ItemSet.
-      #
       # @return [Set<ItemSet>]
       #   Set of all ItemSets that lead up to this ItemSet.
       def leading_item_sets
-        @in_sets.reduce(Set[self]) do |result, item_set|
-          result + item_set.leading_item_sets
+        result = Set.new
+        eval_sets = Set[self]
+        evaled = Set.new
+        while eval_sets.size > 0
+          eval_set = eval_sets.first
+          eval_sets.delete(eval_set)
+          evaled << eval_set
+          eval_set.in_sets.each do |in_set|
+            result << in_set
+            unless evaled.include?(in_set)
+              eval_sets << in_set
+            end
+          end
         end
+        result
       end
 
       # Represent the ItemSet as a String.

lib/propane/pattern.rb

@@ -40,8 +40,6 @@ class Propane
     #   Optional parameters.
     # @option options [String, nil] :code
     #   Code block to execute when the pattern is matched.
-    # @option options [Boolean] :drop
-    #   Whether this is a drop pattern.
     # @option options [String, nil] :pattern
     #   Pattern.
     # @option options [Token, nil] :token
@@ -52,7 +50,6 @@ class Propane
     #   Lexer mode for this pattern.
     def initialize(options)
       @code = options[:code]
-      @drop = options[:drop]
       @pattern = options[:pattern]
       @token = options[:token]
       @line_number = options[:line_number]
@@ -63,14 +60,6 @@ class Propane
       @nfa = regex.nfa
     end
 
-    # Whether the pattern is a drop pattern.
-    #
-    # @return [Boolean]
-    #   Whether the pattern is a drop pattern.
-    def drop?
-      @drop
-    end
-
   end
 
 end

lib/propane/regex.rb

@@ -134,8 +134,18 @@ class Propane
       else
         c = @pattern.slice!(0)
         case c
+        when "a"
+          CharacterRangeUnit.new("\a", "\a")
+        when "b"
+          CharacterRangeUnit.new("\b", "\b")
         when "d"
           CharacterRangeUnit.new("0", "9")
+        when "f"
+          CharacterRangeUnit.new("\f", "\f")
+        when "n"
+          CharacterRangeUnit.new("\n", "\n")
+        when "r"
+          CharacterRangeUnit.new("\r", "\r")
         when "s"
           ccu = CharacterClassUnit.new
           ccu << CharacterRangeUnit.new(" ")
@@ -145,6 +155,10 @@ class Propane
           ccu << CharacterRangeUnit.new("\f")
           ccu << CharacterRangeUnit.new("\v")
           ccu
+        when "t"
+          CharacterRangeUnit.new("\t", "\t")
+        when "v"
+          CharacterRangeUnit.new("\v", "\v")
         else
           CharacterRangeUnit.new(c)
         end

lib/propane/rule.rb

@@ -30,6 +30,11 @@ class Propane
     #   The RuleSet that this Rule is a part of.
     attr_accessor :rule_set
 
+    # @return [Array<Integer>]
+    #   Map this rule's components to their positions in the parent RuleSet's
+    #   node field pointer array. This is used for AST construction.
+    attr_accessor :rule_set_node_field_index_map
+
     # Construct a Rule.
     #
     # @param name [String]
@@ -45,6 +50,7 @@ class Propane
     def initialize(name, components, code, ptypename, line_number)
       @name = name
       @components = components
+      @rule_set_node_field_index_map = components.map {0}
       @code = code
       @ptypename = ptypename
       @line_number = line_number
@@ -60,6 +66,14 @@ class Propane
       @components.empty?
     end
 
+    # Return whether this is an optional Rule.
+    #
+    # @return [Boolean]
+    #   Whether this is an optional Rule.
+    def optional?
+      @name.end_with?("?")
+    end
+
     # Represent the Rule as a String.
     #
     # @return [String]
@@ -68,6 +82,17 @@ class Propane
       "#{@name} -> #{@components.map(&:name).join(" ")}"
     end
 
+    # Check whether the rule set node field index map is just a 1:1 mapping.
+    #
+    # @return [Boolean]
+    #   Boolean indicating whether the rule set node field index map is just a
+    #   1:1 mapping.
+    def flat_rule_set_node_field_index_map?
+      @rule_set_node_field_index_map.each_with_index.all? do |v, i|
+        v == i
+      end
+    end
+
   end
 
 end

lib/propane/rule_set.rb

@@ -1,10 +1,15 @@
 class Propane
 
+  # A RuleSet collects all grammar rules of the same name.
   class RuleSet
 
+    # @return [Array<Hash>]
+    #   AST fields.
+    attr_reader :ast_fields
+
     # @return [Integer]
     #   ID of the RuleSet.
-    attr_accessor :id
+    attr_reader :id
 
     # @return [String]
     #   Name of the RuleSet.
@@ -51,6 +56,24 @@ class Propane
       @could_be_empty
     end
 
+    # Return whether this is an optional RuleSet.
+    #
+    # @return [Boolean]
+    #   Whether this is an optional RuleSet.
+    def optional?
+      @name.end_with?("?")
+    end
+
+    # For optional rule sets, return the underlying component that is optional.
+    def option_target
+      @rules.each do |rule|
+        if rule.components.size > 0
+          return rule.components[0]
+        end
+      end
+      raise "Optional rule target not found"
+    end
+
     # Build the start token set for the RuleSet.
     #
     # @return [Set<Token>]
@@ -75,6 +98,58 @@ class Propane
       @_start_token_set
     end
 
+    # Finalize a RuleSet after adding all Rules to it.
+    def finalize(grammar)
+      build_ast_fields(grammar)
+    end
+
+    private
+
+    # Build the set of AST fields for this RuleSet.
+    #
+    # This is an Array of Hashes. Each entry in the Array corresponds to a
+    # field location in the AST node. The entry is a Hash. It could have one or
+    # two keys. It will always have the field name with a positional suffix as
+    # a key. It may also have the field name without the positional suffix if
+    # that field only exists in one position across all Rules in the RuleSet.
+    #
+    # @return [void]
+    def build_ast_fields(grammar)
+      field_ast_node_indexes = {}
+      field_indexes_across_all_rules = {}
+      @ast_fields = []
+      @rules.each do |rule|
+        rule.components.each_with_index do |component, i|
+          if component.is_a?(RuleSet) && component.optional?
+            component = component.option_target
+          end
+          if component.is_a?(Token)
+            node_name = "Token"
+          else
+            node_name = component.name
+          end
+          struct_name = "#{grammar.ast_prefix}#{node_name}#{grammar.ast_suffix}"
+          field_name = "p#{node_name}#{i + 1}"
+          unless field_ast_node_indexes[field_name]
+            field_ast_node_indexes[field_name] = @ast_fields.size
+            @ast_fields << {field_name => struct_name}
+          end
+          field_indexes_across_all_rules[node_name] ||= Set.new
+          field_indexes_across_all_rules[node_name] << field_ast_node_indexes[field_name]
+          rule.rule_set_node_field_index_map[i] = field_ast_node_indexes[field_name]
+        end
+      end
+      field_indexes_across_all_rules.each do |node_name, indexes_across_all_rules|
+        if indexes_across_all_rules.size == 1
+          # If this field was only seen in one position across all rules,
+          # then add an alias to the positional field name that does not
+          # include the position.
+          @ast_fields[indexes_across_all_rules.first]["p#{node_name}"] =
+            "#{grammar.ast_prefix}#{node_name}#{grammar.ast_suffix}"
+        end
+      end
+    end
+
   end
 
 end

lib/propane/version.rb

@@ -1,3 +1,3 @@
 class Propane
-  VERSION = "0.1.0"
+  VERSION = "1.4.0"
 end

propane.sh

@@ -1,2 +0,0 @@
-#!/bin/sh
-exec bundle exec ruby -Ilib bin/propane "$@"

rb/build_dist.rb

@@ -1,5 +1,6 @@
 #!/usr/bin/env ruby
 
+require "erb"
 require "fileutils"
 require "digest/md5"
 
@@ -13,6 +14,24 @@ START_FILE = "bin/#{PROG_NAME}"
 LIB_DIR = "lib"
 DIST = "dist"
 
+ASSETS_TEMPLATE = <<EOF
+class Propane
+  module Assets
+    class << self
+      def get(name)
+        case name
+<% Dir.glob("assets/*").each  do |asset_file| %>
+        when <%= File.basename(asset_file).inspect %>
+          <%= File.binread(asset_file).inspect %>
+<% end  %>
+        end
+      end
+    end
+  end
+end
+EOF
+
+assets_module = ERB.new(ASSETS_TEMPLATE, trim_mode: "<>").result
 files_processed = {}
 combined_file = []
 
@@ -25,7 +44,11 @@ combine_files = lambda do |file|
         if File.exist?(path)
           unless files_processed[path]
             files_processed[path] = true
-            combine_files[path]
+            if require_name == "propane/assets"
+              combined_file << assets_module
+            else
+              combine_files[path]
+            end
           end
         else
           raise "require path #{path.inspect} not found"

spec/json_parser.c.propane

@@ -0,0 +1,183 @@
+<<header
+#include "json_types.h"
+#include "testutils.h"
+>>
+<<
+#include "math.h"
+#include <stdbool.h>
+static str_t string_value;
+>>
+
+ptype JSONValue *;
+
+drop /\s+/;
+token lbrace /\{/;
+token rbrace /\}/;
+token lbracket /\[/;
+token rbracket /\]/;
+token comma /,/;
+token colon /:/;
+token number /-?(0|[1-9][0-9]*)(\.[0-9]+)?([eE][-+]?[0-9]+)?/ <<
+    double n = 0.0;
+    bool negative = false;
+    size_t i = 0u;
+    if (match[i] == '-')
+    {
+        negative = true;
+        i++;
+    }
+    while ('0' <= match[i] && match[i] <= '9')
+    {
+        n *= 10.0;
+        n += (match[i] - '0');
+        i++;
+    }
+    if (match[i] == '.')
+    {
+        i++;
+        double mult = 0.1;
+        while ('0' <= match[i] && match[i] <= '9')
+        {
+            n += mult * (match[i] - '0');
+            mult /= 10.0;
+            i++;
+        }
+    }
+    if (match[i] == 'e' || match[i] == 'E')
+    {
+        bool exp_negative = false;
+        i++;
+        if (match[i] == '-')
+        {
+            exp_negative = true;
+            i++;
+        }
+        else if (match[i] == '+')
+        {
+            i++;
+        }
+        long exp = 0.0;
+        while ('0' <= match[i] && match[i] <= '9')
+        {
+            exp *= 10;
+            exp += (match[i] - '0');
+            i++;
+        }
+        if (exp_negative)
+        {
+            exp = -exp;
+        }
+        n = pow(n, exp);
+    }
+    if (negative)
+    {
+        n = -n;
+    }
+    $$ = JSONValue_new(JSON_NUMBER);
+    $$->number = n;
+>>
+token true <<
+  $$ = JSONValue_new(JSON_TRUE);
+>>
+token false <<
+  $$ = JSONValue_new(JSON_FALSE);
+>>
+token null <<
+  $$ = JSONValue_new(JSON_NULL);
+>>
+/"/ <<
+  $mode(string);
+  str_init(&string_value, "");
+>>
+string: token string /"/ <<
+  $$ = JSONValue_new(JSON_STRING);
+  $$->string = string_value;
+  $mode(default);
+>>
+string: /\\"/ <<
+  str_append(&string_value, "\"");
+>>
+string: /\\\\/ <<
+  str_append(&string_value, "\\");
+>>
+string: /\\\// <<
+  str_append(&string_value, "/");
+>>
+string: /\\b/ <<
+  str_append(&string_value, "\b");
+>>
+string: /\\f/ <<
+  str_append(&string_value, "\f");
+>>
+string: /\\n/ <<
+  str_append(&string_value, "\n");
+>>
+string: /\\r/ <<
+  str_append(&string_value, "\r");
+>>
+string: /\\t/ <<
+  str_append(&string_value, "\t");
+>>
+string: /\\u[0-9a-fA-F]{4}/ <<
+  /* Not actually going to encode the code point for this example... */
+  char s[] = {'{', match[2], match[3], match[4], match[5], '}', 0};
+  str_append(&string_value, s);
+>>
+string: /[^\\]/ <<
+  char s[] = {match[0], 0};
+  str_append(&string_value, s);
+>>
+Start -> Value <<
+  $$ = $1;
+>>
+Value -> string <<
+  $$ = $1;
+>>
+Value -> number <<
+  $$ = $1;
+>>
+Value -> Object <<
+  $$ = $1;
+>>
+Value -> Array <<
+  $$ = $1;
+>>
+Value -> true <<
+  $$ = $1;
+>>
+Value -> false <<
+  $$ = $1;
+>>
+Value -> null <<
+  $$ = $1;
+>>
+Object -> lbrace rbrace <<
+  $$ = JSONObject_new();
+>>
+Object -> lbrace KeyValues rbrace <<
+  $$ = $2;
+>>
+KeyValues -> KeyValue <<
+  $$ = $1;
+>>
+KeyValues -> KeyValues comma KeyValue <<
+  JSONObject_append($1, $3->object.entries[0].name, $3->object.entries[0].value);
+  $$ = $1;
+>>
+KeyValue -> string colon Value <<
+  $$ = JSONObject_new();
+  JSONObject_append($$, str_cstr(&$1->string), $3);
+>>
+Array -> lbracket rbracket <<
+  $$ = JSONArray_new();
+>>
+Array -> lbracket Values rbracket <<
+  $$ = $2;
+>>
+Values -> Value <<
+  $$ = $1;
+>>
+Values -> Values comma Value <<
+  JSONArray_append($1, $3);
+  $$ = $1;
+>>

spec/json_types.c

@@ -0,0 +1,64 @@
+#include "json_types.h"
+#include <string.h>
+#include <stdlib.h>
+#include "testutils.h"
+
+JSONValue * JSONValue_new(size_t id)
+{
+    JSONValue * jv = calloc(1, sizeof(JSONValue));
+    jv->id = id;
+    return jv;
+}
+
+JSONValue * JSONObject_new(void)
+{
+    JSONValue * jv = JSONValue_new(JSON_OBJECT);
+    jv->object.size = 0u;
+    return jv;
+}
+
+void JSONObject_append(JSONValue * object, char const * name, JSONValue * value)
+{
+    size_t const size = object->object.size;
+    for (size_t i = 0u; i < size; i++)
+    {
+        if (strcmp(name, object->object.entries[i].name) == 0)
+        {
+            object->object.entries[i].value = value;
+            return;
+        }
+    }
+    size_t const new_size = size + 1;
+    void * new_entries = malloc(sizeof(object->object.entries[0]) * new_size);
+    if (size > 0)
+    {
+        memcpy(new_entries, object->object.entries, size * sizeof(object->object.entries[0]));
+        free(object->object.entries);
+    }
+    object->object.entries = new_entries;
+    object->object.entries[size].name = name;
+    object->object.entries[size].value = value;
+    object->object.size = new_size;
+}
+
+JSONValue * JSONArray_new(void)
+{
+    JSONValue * jv = JSONValue_new(JSON_ARRAY);
+    jv->array.size = 0u;
+    return jv;
+}
+
+void JSONArray_append(JSONValue * array, JSONValue * value)
+{
+    size_t const size = array->array.size;
+    size_t const new_size = size + 1;
+    JSONValue ** new_entries = malloc(sizeof(JSONValue *) * new_size);
+    if (array->array.size > 0)
+    {
+        memcpy(new_entries, array->array.entries, sizeof(JSONValue *) * size);
+        free(array->array.entries);
+    }
+    array->array.entries = new_entries;
+    array->array.entries[size] = value;
+    array->array.size = new_size;
+}

spec/json_types.h

@@ -0,0 +1,46 @@
+#pragma once
+
+#include <stddef.h>
+#include "testutils.h"
+
+#define JSON_OBJECT 0u
+#define JSON_ARRAY 1u
+#define JSON_NUMBER 2u
+#define JSON_STRING 3u
+#define JSON_TRUE 4u
+#define JSON_FALSE 5u
+#define JSON_NULL 6u
+
+typedef struct JSONValue_s
+{
+    size_t id;
+    union
+    {
+        struct
+        {
+            size_t size;
+            struct
+            {
+                char const * name;
+                struct JSONValue_s * value;
+            } * entries;
+        } object;
+        struct
+        {
+            size_t size;
+            struct JSONValue_s ** entries;
+        } array;
+        double number;
+        str_t string;
+    };
+} JSONValue;
+
+JSONValue * JSONValue_new(size_t id);
+
+JSONValue * JSONObject_new(void);
+
+void JSONObject_append(JSONValue * object, char const * name, JSONValue * value);
+
+JSONValue * JSONArray_new(void);
+
+void JSONArray_append(JSONValue * array, JSONValue * value);

spec/propane/grammar_spec.rb

@@ -5,7 +5,6 @@ class Propane
 # Comment line
 
 module a.b;
-class Foobar;
 ptype   XYZ  *  ;
 
 token while;
@@ -30,51 +29,51 @@ B -> <<
 >>
 EOF
       grammar = Grammar.new(input)
-      expect(grammar.classname).to eq "Foobar"
       expect(grammar.modulename).to eq "a.b"
       expect(grammar.ptype).to eq "XYZ  *"
       expect(grammar.ptypes).to eq("default" => "XYZ  *")
+      expect(grammar.prefix).to eq "p_"
 
       o = grammar.tokens.find {|token| token.name == "while"}
       expect(o).to_not be_nil
-      expect(o.line_number).to eq 7
+      expect(o.line_number).to eq 6
 
       o = grammar.patterns.find {|pattern| pattern.token == o}
       expect(o).to_not be_nil
       expect(o.pattern).to eq "while"
-      expect(o.line_number).to eq 7
+      expect(o.line_number).to eq 6
       expect(o.code).to be_nil
 
       o = grammar.tokens.find {|token| token.name == "id"}
       expect(o).to_not be_nil
-      expect(o.line_number).to eq 10
+      expect(o.line_number).to eq 9
 
       o = grammar.patterns.find {|pattern| pattern.token == o}
       expect(o).to_not be_nil
       expect(o.pattern).to eq "[a-zA-Z_][a-zA-Z_0-9]*"
-      expect(o.line_number).to eq 10
+      expect(o.line_number).to eq 9
       expect(o.code).to be_nil
 
       o = grammar.tokens.find {|token| token.name == "token_with_code"}
       expect(o).to_not be_nil
-      expect(o.line_number).to eq 12
+      expect(o.line_number).to eq 11
 
       o = grammar.patterns.find {|pattern| pattern.token == o}
       expect(o).to_not be_nil
       expect(o.pattern).to eq "token_with_code"
-      expect(o.line_number).to eq 12
+      expect(o.line_number).to eq 11
       expect(o.code).to eq "Code for the token\n"
 
       o = grammar.tokens.find {|token| token.name == "token_with_no_pattern"}
       expect(o).to_not be_nil
-      expect(o.line_number).to eq 16
+      expect(o.line_number).to eq 15
 
       o = grammar.patterns.find {|pattern| pattern.token == o}
       expect(o).to be_nil
 
       o = grammar.patterns.find {|pattern| pattern.pattern == "\\s+"}
       expect(o).to_not be_nil
-      expect(o.line_number).to eq 18
+      expect(o.line_number).to eq 17
       expect(o.token).to be_nil
       expect(o.code).to be_nil
 
@@ -83,19 +82,19 @@ EOF
       o = grammar.rules[0]
       expect(o.name).to eq "A"
       expect(o.components).to eq %w[B]
-      expect(o.line_number).to eq 20
+      expect(o.line_number).to eq 19
       expect(o.code).to eq "  a = 42;\n"
 
       o = grammar.rules[1]
       expect(o.name).to eq "B"
       expect(o.components).to eq %w[C while id]
-      expect(o.line_number).to eq 23
+      expect(o.line_number).to eq 22
       expect(o.code).to be_nil
 
       o = grammar.rules[2]
       expect(o.name).to eq "B"
       expect(o.components).to eq []
-      expect(o.line_number).to eq 24
+      expect(o.line_number).to eq 23
       expect(o.code).to eq "  b = 0;\n"
     end
 
@@ -111,8 +110,11 @@ token code2 <<
 >>
 
 tokenid token_with_no_pattern;
+
+prefix myparser_;
 EOF
       grammar = Grammar.new(input)
+      expect(grammar.prefix).to eq "myparser_"
 
       o = grammar.tokens.find {|token| token.name == "code1"}
       expect(o).to_not be_nil

spec/spec_helper.rb

@@ -1,11 +1,27 @@
-require "bundler/setup"
-require "propane"
+unless ENV["dist_specs"]
+  require "bundler/setup"
+  require "simplecov"
 
-RSpec.configure do |config|
-  # Enable flags like --only-failures and --next-failure
-  config.example_status_persistence_file_path = ".rspec_status"
+  SimpleCov.start do
+    add_filter "/spec/"
+    add_filter "/.bundle/"
+    if ENV["partial_specs"]
+      command_name "RSpec-partial"
+    else
+      command_name "RSpec"
+    end
+    project_name "Propane"
+    merge_timeout 3600
+  end
 
-  config.expect_with :rspec do |c|
-    c.syntax = :expect
+  RSpec.configure do |config|
+    # Enable flags like --only-failures and --next-failure
+    config.example_status_persistence_file_path = ".rspec_status"
+
+    config.expect_with :rspec do |c|
+      c.syntax = :expect
+    end
   end
 end
+
+require "propane"

spec/test_ast.c

@@ -0,0 +1,55 @@
+#include "testparser.h"
+#include <assert.h>
+#include <string.h>
+#include "testutils.h"
+
+int main()
+{
+    char const * input = "a, ((b)), b";
+    p_context_t context;
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert_eq(P_SUCCESS, p_parse(&context));
+    Start * start = p_result(&context);
+    assert(start->pItems1 != NULL);
+    assert(start->pItems != NULL);
+    Items * items = start->pItems;
+    assert(items->pItem != NULL);
+    assert(items->pItem->pToken1 != NULL);
+    assert_eq(TOKEN_a, items->pItem->pToken1->token);
+    assert_eq(11, items->pItem->pToken1->pvalue);
+    assert(items->pItemsMore != NULL);
+    ItemsMore * itemsmore = items->pItemsMore;
+    assert(itemsmore->pItem != NULL);
+    assert(itemsmore->pItem->pItem != NULL);
+    assert(itemsmore->pItem->pItem->pItem != NULL);
+    assert(itemsmore->pItem->pItem->pItem->pToken1 != NULL);
+    assert_eq(TOKEN_b, itemsmore->pItem->pItem->pItem->pToken1->token);
+    assert_eq(22, itemsmore->pItem->pItem->pItem->pToken1->pvalue);
+    assert(itemsmore->pItemsMore != NULL);
+    itemsmore = itemsmore->pItemsMore;
+    assert(itemsmore->pItem != NULL);
+    assert(itemsmore->pItem->pToken1 != NULL);
+    assert_eq(TOKEN_b, itemsmore->pItem->pToken1->token);
+    assert_eq(22, itemsmore->pItem->pToken1->pvalue);
+    assert(itemsmore->pItemsMore == NULL);
+
+    input = "";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert_eq(P_SUCCESS, p_parse(&context));
+    start = p_result(&context);
+    assert(start->pItems == NULL);
+
+    input = "2 1";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert_eq(P_SUCCESS, p_parse(&context));
+    start = p_result(&context);
+    assert(start->pItems != NULL);
+    assert(start->pItems->pItem != NULL);
+    assert(start->pItems->pItem->pDual != NULL);
+    assert(start->pItems->pItem->pDual->pTwo1 != NULL);
+    assert(start->pItems->pItem->pDual->pOne2 != NULL);
+    assert(start->pItems->pItem->pDual->pTwo2 == NULL);
+    assert(start->pItems->pItem->pDual->pOne1 == NULL);
+
+    return 0;
+}

spec/test_ast.d

@@ -0,0 +1,57 @@
+import testparser;
+import std.stdio;
+import testutils;
+
+int main()
+{
+    return 0;
+}
+
+unittest
+{
+    string input = "a, ((b)), b";
+    p_context_t context;
+    p_context_init(&context, input);
+    assert_eq(P_SUCCESS, p_parse(&context));
+    Start * start = p_result(&context);
+    assert(start.pItems1 !is null);
+    assert(start.pItems !is null);
+    Items * items = start.pItems;
+    assert(items.pItem !is null);
+    assert(items.pItem.pToken1 !is null);
+    assert_eq(TOKEN_a, items.pItem.pToken1.token);
+    assert_eq(11, items.pItem.pToken1.pvalue);
+    assert(items.pItemsMore !is null);
+    ItemsMore * itemsmore = items.pItemsMore;
+    assert(itemsmore.pItem !is null);
+    assert(itemsmore.pItem.pItem !is null);
+    assert(itemsmore.pItem.pItem.pItem !is null);
+    assert(itemsmore.pItem.pItem.pItem.pToken1 !is null);
+    assert_eq(TOKEN_b, itemsmore.pItem.pItem.pItem.pToken1.token);
+    assert_eq(22, itemsmore.pItem.pItem.pItem.pToken1.pvalue);
+    assert(itemsmore.pItemsMore !is null);
+    itemsmore = itemsmore.pItemsMore;
+    assert(itemsmore.pItem !is null);
+    assert(itemsmore.pItem.pToken1 !is null);
+    assert_eq(TOKEN_b, itemsmore.pItem.pToken1.token);
+    assert_eq(22, itemsmore.pItem.pToken1.pvalue);
+    assert(itemsmore.pItemsMore is null);
+
+    input = "";
+    p_context_init(&context, input);
+    assert_eq(P_SUCCESS, p_parse(&context));
+    start = p_result(&context);
+    assert(start.pItems is null);
+
+    input = "2 1";
+    p_context_init(&context, input);
+    assert_eq(P_SUCCESS, p_parse(&context));
+    start = p_result(&context);
+    assert(start.pItems !is null);
+    assert(start.pItems.pItem !is null);
+    assert(start.pItems.pItem.pDual !is null);
+    assert(start.pItems.pItem.pDual.pTwo1 !is null);
+    assert(start.pItems.pItem.pDual.pOne2 !is null);
+    assert(start.pItems.pItem.pDual.pTwo2 is null);
+    assert(start.pItems.pItem.pDual.pOne1 is null);
+}

spec/test_ast_ps.c

@@ -0,0 +1,55 @@
+#include "testparser.h"
+#include <assert.h>
+#include <string.h>
+#include "testutils.h"
+
+int main()
+{
+    char const * input = "a, ((b)), b";
+    p_context_t context;
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert_eq(P_SUCCESS, p_parse(&context));
+    PStartS * start = p_result(&context);
+    assert(start->pItems1 != NULL);
+    assert(start->pItems != NULL);
+    PItemsS * items = start->pItems;
+    assert(items->pItem != NULL);
+    assert(items->pItem->pToken1 != NULL);
+    assert_eq(TOKEN_a, items->pItem->pToken1->token);
+    assert_eq(11, items->pItem->pToken1->pvalue);
+    assert(items->pItemsMore != NULL);
+    PItemsMoreS * itemsmore = items->pItemsMore;
+    assert(itemsmore->pItem != NULL);
+    assert(itemsmore->pItem->pItem != NULL);
+    assert(itemsmore->pItem->pItem->pItem != NULL);
+    assert(itemsmore->pItem->pItem->pItem->pToken1 != NULL);
+    assert_eq(TOKEN_b, itemsmore->pItem->pItem->pItem->pToken1->token);
+    assert_eq(22, itemsmore->pItem->pItem->pItem->pToken1->pvalue);
+    assert(itemsmore->pItemsMore != NULL);
+    itemsmore = itemsmore->pItemsMore;
+    assert(itemsmore->pItem != NULL);
+    assert(itemsmore->pItem->pToken1 != NULL);
+    assert_eq(TOKEN_b, itemsmore->pItem->pToken1->token);
+    assert_eq(22, itemsmore->pItem->pToken1->pvalue);
+    assert(itemsmore->pItemsMore == NULL);
+
+    input = "";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert_eq(P_SUCCESS, p_parse(&context));
+    start = p_result(&context);
+    assert(start->pItems == NULL);
+
+    input = "2 1";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert_eq(P_SUCCESS, p_parse(&context));
+    start = p_result(&context);
+    assert(start->pItems != NULL);
+    assert(start->pItems->pItem != NULL);
+    assert(start->pItems->pItem->pDual != NULL);
+    assert(start->pItems->pItem->pDual->pTwo1 != NULL);
+    assert(start->pItems->pItem->pDual->pOne2 != NULL);
+    assert(start->pItems->pItem->pDual->pTwo2 == NULL);
+    assert(start->pItems->pItem->pDual->pOne1 == NULL);
+
+    return 0;
+}

spec/test_ast_ps.d

@@ -0,0 +1,57 @@
+import testparser;
+import std.stdio;
+import testutils;
+
+int main()
+{
+    return 0;
+}
+
+unittest
+{
+    string input = "a, ((b)), b";
+    p_context_t context;
+    p_context_init(&context, input);
+    assert_eq(P_SUCCESS, p_parse(&context));
+    PStartS * start = p_result(&context);
+    assert(start.pItems1 !is null);
+    assert(start.pItems !is null);
+    PItemsS * items = start.pItems;
+    assert(items.pItem !is null);
+    assert(items.pItem.pToken1 !is null);
+    assert_eq(TOKEN_a, items.pItem.pToken1.token);
+    assert_eq(11, items.pItem.pToken1.pvalue);
+    assert(items.pItemsMore !is null);
+    PItemsMoreS * itemsmore = items.pItemsMore;
+    assert(itemsmore.pItem !is null);
+    assert(itemsmore.pItem.pItem !is null);
+    assert(itemsmore.pItem.pItem.pItem !is null);
+    assert(itemsmore.pItem.pItem.pItem.pToken1 !is null);
+    assert_eq(TOKEN_b, itemsmore.pItem.pItem.pItem.pToken1.token);
+    assert_eq(22, itemsmore.pItem.pItem.pItem.pToken1.pvalue);
+    assert(itemsmore.pItemsMore !is null);
+    itemsmore = itemsmore.pItemsMore;
+    assert(itemsmore.pItem !is null);
+    assert(itemsmore.pItem.pToken1 !is null);
+    assert_eq(TOKEN_b, itemsmore.pItem.pToken1.token);
+    assert_eq(22, itemsmore.pItem.pToken1.pvalue);
+    assert(itemsmore.pItemsMore is null);
+
+    input = "";
+    p_context_init(&context, input);
+    assert_eq(P_SUCCESS, p_parse(&context));
+    start = p_result(&context);
+    assert(start.pItems is null);
+
+    input = "2 1";
+    p_context_init(&context, input);
+    assert_eq(P_SUCCESS, p_parse(&context));
+    start = p_result(&context);
+    assert(start.pItems !is null);
+    assert(start.pItems.pItem !is null);
+    assert(start.pItems.pItem.pDual !is null);
+    assert(start.pItems.pItem.pDual.pTwo1 !is null);
+    assert(start.pItems.pItem.pDual.pOne2 !is null);
+    assert(start.pItems.pItem.pDual.pTwo2 is null);
+    assert(start.pItems.pItem.pDual.pOne1 is null);
+}

spec/test_basic_math_grammar.c

@@ -0,0 +1,29 @@
+#include "testparser.h"
+#include "testutils.h"
+#include <string.h>
+
+int main()
+{
+    char const * input = "1 + 2 * 3 + 4";
+    p_context_t context;
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert_eq(P_SUCCESS, p_parse(&context));
+    assert_eq(11, p_result(&context));
+
+    input = "1 * 2 ** 4 * 3";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert_eq(P_SUCCESS, p_parse(&context));
+    assert_eq(48, p_result(&context));
+
+    input = "(1 + 2) * 3 + 4";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert_eq(P_SUCCESS, p_parse(&context));
+    assert_eq(13, p_result(&context));
+
+    input = "(2 * 2) ** 3 + 4 + 5";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert_eq(P_SUCCESS, p_parse(&context));
+    assert_eq(73, p_result(&context));
+
+    return 0;
+}

spec/test_basic_math_grammar.d

@@ -0,0 +1,32 @@
+import testparser;
+import std.stdio;
+import testutils;
+
+int main()
+{
+    return 0;
+}
+
+unittest
+{
+    string input = "1 + 2 * 3 + 4";
+    p_context_t context;
+    p_context_init(&context, input);
+    assert_eq(P_SUCCESS, p_parse(&context));
+    assert_eq(11, p_result(&context));
+
+    input = "1 * 2 ** 4 * 3";
+    p_context_init(&context, input);
+    assert_eq(P_SUCCESS, p_parse(&context));
+    assert_eq(48, p_result(&context));
+
+    input = "(1 + 2) * 3 + 4";
+    p_context_init(&context, input);
+    assert_eq(P_SUCCESS, p_parse(&context));
+    assert_eq(13, p_result(&context));
+
+    input = "(2 * 2) ** 3 + 4 + 5";
+    p_context_init(&context, input);
+    assert_eq(P_SUCCESS, p_parse(&context));
+    assert_eq(73, p_result(&context));
+}

spec/test_d_lexer.d

@@ -1,52 +0,0 @@
-import testparser;
-import std.stdio;
-
-int main()
-{
-    return 0;
-}
-
-unittest
-{
-    alias Result = Testparser.Decoder.Result;
-    Result result;
-
-    result = Testparser.Decoder.decode_code_point("5");
-    assert(result == Result.success('5', 1u));
-
-    result = Testparser.Decoder.decode_code_point("");
-    assert(result == Result.eof());
-
-    result = Testparser.Decoder.decode_code_point("\xC2\xA9");
-    assert(result == Result.success(0xA9u, 2u));
-
-    result = Testparser.Decoder.decode_code_point("\xf0\x9f\xa7\xa1");
-    assert(result == Result.success(0x1F9E1, 4u));
-
-    result = Testparser.Decoder.decode_code_point("\xf0\x9f\x27");
-    assert(result == Result.decode_error());
-
-    result = Testparser.Decoder.decode_code_point("\xf0\x9f\xa7\xFF");
-    assert(result == Result.decode_error());
-
-    result = Testparser.Decoder.decode_code_point("\xfe");
-    assert(result == Result.decode_error());
-}
-
-unittest
-{
-    alias Result = Testparser.Lexer.Result;
-    string input = "5 + 4 * \n677 + 567";
-    Testparser.Lexer lexer = new Testparser.Lexer(input);
-    assert(lexer.lex_token() == Result(Result.Type.TOKEN, 0, 0, 1, Testparser.TOKEN_int));
-    assert(lexer.lex_token() == Result(Result.Type.TOKEN, 0, 2, 1, Testparser.TOKEN_plus));
-    assert(lexer.lex_token() == Result(Result.Type.TOKEN, 0, 4, 1, Testparser.TOKEN_int));
-    assert(lexer.lex_token() == Result(Result.Type.TOKEN, 0, 6, 1, Testparser.TOKEN_times));
-    assert(lexer.lex_token() == Result(Result.Type.TOKEN, 1, 0, 3, Testparser.TOKEN_int));
-    assert(lexer.lex_token() == Result(Result.Type.TOKEN, 1, 4, 1, Testparser.TOKEN_plus));
-    assert(lexer.lex_token() == Result(Result.Type.TOKEN, 1, 6, 3, Testparser.TOKEN_int));
-    assert(lexer.lex_token() == Result(Result.Type.TOKEN, 1, 9, 0, Testparser.TOKEN___EOF));
-
-    lexer = new Testparser.Lexer("");
-    assert(lexer.lex_token() == Result(Result.Type.TOKEN, 0, 0, 0, Testparser.TOKEN___EOF));
-}

spec/test_d_parser_identical_rules_lookahead.d

@@ -1,18 +0,0 @@
-import testparser;
-import std.stdio;
-
-int main()
-{
-    return 0;
-}
-
-unittest
-{
-    string input = "aba";
-    auto parser = new Testparser.Parser(input);
-    assert(parser.parse() == true);
-
-    input = "abb";
-    parser = new Testparser.Parser(input);
-    assert(parser.parse() == true);
-}

spec/test_d_parser_rule_from_multiple_states.d

@@ -1,22 +0,0 @@
-import testparser;
-import std.stdio;
-
-int main()
-{
-    return 0;
-}
-
-unittest
-{
-    string input = "a";
-    auto parser = new Testparser.Parser(input);
-    assert(parser.parse() == false);
-
-    input = "a b";
-    parser = new Testparser.Parser(input);
-    assert(parser.parse() == true);
-
-    input = "bb";
-    parser = new Testparser.Parser(input);
-    assert(parser.parse() == true);
-}

spec/test_error_positions.c

@@ -0,0 +1,42 @@
+#include "testparser.h"
+#include <assert.h>
+#include <string.h>
+
+int main()
+{
+    char const * input = "a 42";
+    p_context_t context;
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+
+    input = "a\n123\na  a";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_UNEXPECTED_TOKEN);
+    assert(p_position(&context).row == 2);
+    assert(p_position(&context).col == 3);
+    assert(p_token(&context) == TOKEN_a);
+
+    input = "12";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_UNEXPECTED_TOKEN);
+    assert(p_position(&context).row == 0);
+    assert(p_position(&context).col == 0);
+    assert(p_token(&context) == TOKEN_num);
+
+    input = "a 12\n\nab";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_UNEXPECTED_INPUT);
+    assert(p_position(&context).row == 2);
+    assert(p_position(&context).col == 1);
+
+    input = "a 12\n\na\n\n77\na   \xAA";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_DECODE_ERROR);
+    assert(p_position(&context).row == 5);
+    assert(p_position(&context).col == 4);
+
+    assert(strcmp(p_token_names[TOKEN_a], "a") == 0);
+    assert(strcmp(p_token_names[TOKEN_num], "num") == 0);
+
+    return 0;
+}

spec/test_error_positions.d

@@ -0,0 +1,40 @@
+import testparser;
+import std.stdio;
+
+int main()
+{
+    return 0;
+}
+
+unittest
+{
+    string input = "a 42";
+    p_context_t context;
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
+
+    input = "a\n123\na  a";
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_UNEXPECTED_TOKEN);
+    assert(p_position(&context) == p_position_t(2, 3));
+    assert(p_token(&context) == TOKEN_a);
+
+    input = "12";
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_UNEXPECTED_TOKEN);
+    assert(p_position(&context) == p_position_t(0, 0));
+    assert(p_token(&context) == TOKEN_num);
+
+    input = "a 12\n\nab";
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_UNEXPECTED_INPUT);
+    assert(p_position(&context) == p_position_t(2, 1));
+
+    input = "a 12\n\na\n\n77\na   \xAA";
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_DECODE_ERROR);
+    assert(p_position(&context) == p_position_t(5, 4));
+
+    assert(p_token_names[TOKEN_a] == "a");
+    assert(p_token_names[TOKEN_num] == "num");
+}

spec/test_lexer.c

@@ -0,0 +1,92 @@
+#include "testparser.h"
+#include <assert.h>
+#include <string.h>
+
+int main()
+{
+    size_t result;
+    p_code_point_t code_point;
+    uint8_t code_point_length;
+
+    result = p_decode_code_point((uint8_t const *)"5", 1u, &code_point, &code_point_length);
+    assert(result == P_SUCCESS);
+    assert(code_point == '5');
+    assert(code_point_length == 1u);
+
+    result = p_decode_code_point((uint8_t const *)"", 0u, &code_point, &code_point_length);
+    assert(result == P_EOF);
+
+    result = p_decode_code_point((uint8_t const *)"\xC2\xA9", 2u, &code_point, &code_point_length);
+    assert(result == P_SUCCESS);
+    assert(code_point == 0xA9u);
+    assert(code_point_length == 2u);
+
+    result = p_decode_code_point((uint8_t const *)"\xf0\x9f\xa7\xa1", 4u, &code_point, &code_point_length);
+    assert(result == P_SUCCESS);
+    assert(code_point == 0x1F9E1u);
+    assert(code_point_length == 4u);
+
+    result = p_decode_code_point((uint8_t const *)"\xf0\x9f\x27", 3u, &code_point, &code_point_length);
+    assert(result == P_DECODE_ERROR);
+
+    result = p_decode_code_point((uint8_t const *)"\xf0\x9f\xa7\xFF", 4u, &code_point, &code_point_length);
+    assert(result == P_DECODE_ERROR);
+
+    result = p_decode_code_point((uint8_t const *)"\xfe", 1u, &code_point, &code_point_length);
+    assert(result == P_DECODE_ERROR);
+
+
+    p_token_info_t token_info;
+    char const * input = "5 + 4 * \n677 + 567";
+    p_context_t context;
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_lex(&context, &token_info) == P_SUCCESS);
+    assert(token_info.position.row == 0u);
+    assert(token_info.position.col == 0u);
+    assert(token_info.length == 1u);
+    assert(token_info.token == TOKEN_int);
+    assert(p_lex(&context, &token_info) == P_SUCCESS);
+    assert(token_info.position.row == 0u);
+    assert(token_info.position.col == 2u);
+    assert(token_info.length == 1u);
+    assert(token_info.token == TOKEN_plus);
+    assert(p_lex(&context, &token_info) == P_SUCCESS);
+    assert(token_info.position.row == 0u);
+    assert(token_info.position.col == 4u);
+    assert(token_info.length == 1u);
+    assert(token_info.token == TOKEN_int);
+    assert(p_lex(&context, &token_info) == P_SUCCESS);
+    assert(token_info.position.row == 0u);
+    assert(token_info.position.col == 6u);
+    assert(token_info.length == 1u);
+    assert(token_info.token == TOKEN_times);
+    assert(p_lex(&context, &token_info) == P_SUCCESS);
+    assert(token_info.position.row == 1u);
+    assert(token_info.position.col == 0u);
+    assert(token_info.length == 3u);
+    assert(token_info.token == TOKEN_int);
+    assert(p_lex(&context, &token_info) == P_SUCCESS);
+    assert(token_info.position.row == 1u);
+    assert(token_info.position.col == 4u);
+    assert(token_info.length == 1u);
+    assert(token_info.token == TOKEN_plus);
+    assert(p_lex(&context, &token_info) == P_SUCCESS);
+    assert(token_info.position.row == 1u);
+    assert(token_info.position.col == 6u);
+    assert(token_info.length == 3u);
+    assert(token_info.token == TOKEN_int);
+    assert(p_lex(&context, &token_info) == P_SUCCESS);
+    assert(token_info.position.row == 1u);
+    assert(token_info.position.col == 9u);
+    assert(token_info.length == 0u);
+    assert(token_info.token == TOKEN___EOF);
+
+    p_context_init(&context, (uint8_t const *)"", 0u);
+    assert(p_lex(&context, &token_info) == P_SUCCESS);
+    assert(token_info.position.row == 0u);
+    assert(token_info.position.col == 0u);
+    assert(token_info.length == 0u);
+    assert(token_info.token == TOKEN___EOF);
+
+    return 0;
+}

spec/test_lexer.d

@@ -0,0 +1,69 @@
+import testparser;
+import std.stdio;
+
+int main()
+{
+    return 0;
+}
+
+unittest
+{
+    size_t result;
+    p_code_point_t code_point;
+    ubyte code_point_length;
+
+    result = p_decode_code_point("5", &code_point, &code_point_length);
+    assert(result == P_SUCCESS);
+    assert(code_point == '5');
+    assert(code_point_length == 1u);
+
+    result = p_decode_code_point("", &code_point, &code_point_length);
+    assert(result == P_EOF);
+
+    result = p_decode_code_point("\xC2\xA9", &code_point, &code_point_length);
+    assert(result == P_SUCCESS);
+    assert(code_point == 0xA9u);
+    assert(code_point_length == 2u);
+
+    result = p_decode_code_point("\xf0\x9f\xa7\xa1", &code_point, &code_point_length);
+    assert(result == P_SUCCESS);
+    assert(code_point == 0x1F9E1u);
+    assert(code_point_length == 4u);
+
+    result = p_decode_code_point("\xf0\x9f\x27", &code_point, &code_point_length);
+    assert(result == P_DECODE_ERROR);
+
+    result = p_decode_code_point("\xf0\x9f\xa7\xFF", &code_point, &code_point_length);
+    assert(result == P_DECODE_ERROR);
+
+    result = p_decode_code_point("\xfe", &code_point, &code_point_length);
+    assert(result == P_DECODE_ERROR);
+}
+
+unittest
+{
+    p_token_info_t token_info;
+    string input = "5 + 4 * \n677 + 567";
+    p_context_t context;
+    p_context_init(&context, input);
+    assert(p_lex(&context, &token_info) == P_SUCCESS);
+    assert(token_info == p_token_info_t(p_position_t(0, 0), 1, TOKEN_int));
+    assert(p_lex(&context, &token_info) == P_SUCCESS);
+    assert(token_info == p_token_info_t(p_position_t(0, 2), 1, TOKEN_plus));
+    assert(p_lex(&context, &token_info) == P_SUCCESS);
+    assert(token_info == p_token_info_t(p_position_t(0, 4), 1, TOKEN_int));
+    assert(p_lex(&context, &token_info) == P_SUCCESS);
+    assert(token_info == p_token_info_t(p_position_t(0, 6), 1, TOKEN_times));
+    assert(p_lex(&context, &token_info) == P_SUCCESS);
+    assert(token_info == p_token_info_t(p_position_t(1, 0), 3, TOKEN_int));
+    assert(p_lex(&context, &token_info) == P_SUCCESS);
+    assert(token_info == p_token_info_t(p_position_t(1, 4), 1, TOKEN_plus));
+    assert(p_lex(&context, &token_info) == P_SUCCESS);
+    assert(token_info == p_token_info_t(p_position_t(1, 6), 3, TOKEN_int));
+    assert(p_lex(&context, &token_info) == P_SUCCESS);
+    assert(token_info == p_token_info_t(p_position_t(1, 9), 0, TOKEN___EOF));
+
+    p_context_init(&context, "");
+    assert(p_lex(&context, &token_info) == P_SUCCESS);
+    assert(token_info == p_token_info_t(p_position_t(0, 0), 0, TOKEN___EOF));
+}

spec/test_lexer_match_text.c

@@ -0,0 +1,15 @@
+#include "testparser.h"
+#include <assert.h>
+#include <string.h>
+#include <stdio.h>
+
+int main()
+{
+    char const * input = "identifier_123";
+    p_context_t context;
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+    printf("pass1\n");
+
+    return 0;
+}

spec/test_lexer_match_text.d

@@ -9,7 +9,8 @@ int main()
 unittest
 {
     string input = `identifier_123`;
-    auto parser = new Testparser.Parser(input);
-    assert(parser.parse() == true);
+    p_context_t context;
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
     writeln("pass1");
 }

spec/test_lexer_modes.c

@@ -0,0 +1,20 @@
+#include "testparser.h"
+#include <assert.h>
+#include <string.h>
+#include <stdio.h>
+
+int main()
+{
+    char const * input = "abc \"a string\" def";
+    p_context_t context;
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+    printf("pass1\n");
+
+    input = "abc \"abc def\" def";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+    printf("pass2\n");
+
+    return 0;
+}

spec/test_lexer_modes.d

@@ -9,12 +9,13 @@ int main()
 unittest
 {
     string input = `abc "a string" def`;
-    auto parser = new Testparser.Parser(input);
-    assert(parser.parse() == true);
+    p_context_t context;
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
     writeln("pass1");
 
     input = `abc "abc def" def`;
-    parser = new Testparser.Parser(input);
-    assert(parser.parse() == true);
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
     writeln("pass2");
 }

spec/test_lexer_result_value.c

@@ -0,0 +1,19 @@
+#include "testparser.h"
+#include <assert.h>
+#include <string.h>
+
+int main()
+{
+    char const * input = "x";
+    p_context_t context;
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+    assert(p_result(&context) == 1u);
+
+    input = "fabulous";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+    assert(p_result(&context) == 8u);
+
+    return 0;
+}

spec/test_lexer_result_value.d

@@ -9,12 +9,13 @@ int main()
 unittest
 {
     string input = `x`;
-    auto parser = new Testparser.Parser(input);
-    assert(parser.parse() == true);
-    assert(parser.result == 1u);
+    p_context_t context;
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
+    assert(p_result(&context) == 1u);
 
     input = `fabulous`;
-    parser = new Testparser.Parser(input);
-    assert(parser.parse() == true);
-    assert(parser.result == 8u);
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
+    assert(p_result(&context) == 8u);
 }

spec/test_lexer_unknown_character.c

@@ -0,0 +1,18 @@
+#include "testparser.h"
+#include <assert.h>
+#include <string.h>
+
+int main()
+{
+    char const * input = "x";
+    p_context_t context;
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_UNEXPECTED_INPUT);
+
+    input = "123";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+    assert(p_result(&context) == 123u);
+
+    return 0;
+}

spec/test_lexer_unknown_character.d

@@ -0,0 +1,20 @@
+import testparser;
+import std.stdio;
+
+int main()
+{
+    return 0;
+}
+
+unittest
+{
+    string input = `x`;
+    p_context_t context;
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_UNEXPECTED_INPUT);
+
+    input = `123`;
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
+    assert(p_result(&context) == 123u);
+}

spec/test_match_backslashes.c

@@ -0,0 +1,13 @@
+#include "testparser.h"
+#include <assert.h>
+#include <string.h>
+
+int main()
+{
+    char const * input = "\a\b\t\n\v\f\rt";
+    p_context_t context;
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+
+    return 0;
+}

spec/test_match_backslashes.d

@@ -0,0 +1,15 @@
+import testparser;
+import std.stdio;
+
+int main()
+{
+    return 0;
+}
+
+unittest
+{
+    string input = "\a\b\t\n\v\f\rt";
+    p_context_t context;
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
+}

spec/test_multiple_parsers.c

@@ -0,0 +1,19 @@
+#include "testparsermyp1.h"
+#include "testparsermyp2.h"
+#include <assert.h>
+#include <string.h>
+
+int main()
+{
+    char const * input1 = "a\n1";
+    myp1_context_t context1;
+    myp1_context_init(&context1, (uint8_t const *)input1, strlen(input1));
+    assert(myp1_parse(&context1) == MYP1_SUCCESS);
+
+    char const * input2 = "bcb";
+    myp2_context_t context2;
+    myp2_context_init(&context2, (uint8_t const *)input2, strlen(input2));
+    assert(myp2_parse(&context2) == MYP2_SUCCESS);
+
+    return 0;
+}

spec/test_multiple_parsers.d

@@ -0,0 +1,21 @@
+import testparsermyp1;
+import testparsermyp2;
+import std.stdio;
+
+int main()
+{
+    return 0;
+}
+
+unittest
+{
+    string input1 = "a\n1";
+    myp1_context_t context1;
+    myp1_context_init(&context1, input1);
+    assert(myp1_parse(&context1) == MYP1_SUCCESS);
+
+    string input2 = "bcb";
+    myp2_context_t context2;
+    myp2_context_init(&context2, input2);
+    assert(myp2_parse(&context2) == MYP2_SUCCESS);
+}

spec/test_optional_rule_component.c

@@ -0,0 +1,22 @@
+#include "testparser.h"
+#include <assert.h>
+#include <string.h>
+
+int main()
+{
+    char const * input = "b";
+    p_context_t context;
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+
+    input = "abcd";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+
+    input = "abdc";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+
+    return 0;
+}
+

spec/test_optional_rule_component.d

@@ -0,0 +1,23 @@
+import testparser;
+import std.stdio;
+
+int main()
+{
+    return 0;
+}
+
+unittest
+{
+    string input = "b";
+    p_context_t context;
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
+
+    input = "abcd";
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
+
+    input = "abdc";
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
+}

spec/test_optional_rule_component_ast.c

@@ -0,0 +1,42 @@
+#include "testparser.h"
+#include <assert.h>
+#include <string.h>
+#include "testutils.h"
+
+int main()
+{
+    char const * input = "b";
+    p_context_t context;
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+    Start * start = p_result(&context);
+    assert(start->pToken1 == NULL);
+    assert(start->pToken2 != NULL);
+    assert_eq(TOKEN_b, start->pToken2->token);
+    assert(start->pR3 == NULL);
+    assert(start->pR == NULL);
+
+    input = "abcd";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+    start = p_result(&context);
+    assert(start->pToken1 != NULL);
+    assert_eq(TOKEN_a, start->pToken1->token);
+    assert(start->pToken2 != NULL);
+    assert(start->pR3 != NULL);
+    assert(start->pR != NULL);
+    assert(start->pR == start->pR3);
+    assert_eq(TOKEN_c, start->pR->pToken1->token);
+
+    input = "bdc";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+    start = p_result(&context);
+    assert(start->pToken1 == NULL);
+    assert(start->pToken2 != NULL);
+    assert(start->pR != NULL);
+    assert_eq(TOKEN_d, start->pR->pToken1->token);
+
+    return 0;
+}
+

spec/test_optional_rule_component_ast.d

@@ -0,0 +1,43 @@
+import testparser;
+import std.stdio;
+import testutils;
+
+int main()
+{
+    return 0;
+}
+
+unittest
+{
+    string input = "b";
+    p_context_t context;
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
+    Start * start = p_result(&context);
+    assert(start.pToken1 is null);
+    assert(start.pToken2 !is null);
+    assert_eq(TOKEN_b, start.pToken2.token);
+    assert(start.pR3 is null);
+    assert(start.pR is null);
+
+    input = "abcd";
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
+    start = p_result(&context);
+    assert(start.pToken1 != null);
+    assert_eq(TOKEN_a, start.pToken1.token);
+    assert(start.pToken2 != null);
+    assert(start.pR3 != null);
+    assert(start.pR != null);
+    assert(start.pR == start.pR3);
+    assert_eq(TOKEN_c, start.pR.pToken1.token);
+
+    input = "bdc";
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
+    start = p_result(&context);
+    assert(start.pToken1 is null);
+    assert(start.pToken2 !is null);
+    assert(start.pR !is null);
+    assert_eq(TOKEN_d, start.pR.pToken1.token);
+}

spec/test_parser_identical_rules_lookahead.c

@@ -0,0 +1,17 @@
+#include "testparser.h"
+#include <string.h>
+#include <assert.h>
+
+int main()
+{
+    char const * input = "aba";
+    p_context_t context;
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+
+    input = "abb";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+
+    return 0;
+}

spec/test_parser_identical_rules_lookahead.d

@@ -0,0 +1,19 @@
+import testparser;
+import std.stdio;
+
+int main()
+{
+    return 0;
+}
+
+unittest
+{
+    string input = "aba";
+    p_context_t context;
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
+
+    input = "abb";
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
+}

spec/test_parser_rule_from_multiple_states.c

@@ -0,0 +1,24 @@
+#include "testparser.h"
+#include <assert.h>
+#include <string.h>
+
+int main()
+{
+    char const * input = "a";
+    p_context_t context;
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_UNEXPECTED_TOKEN);
+    assert(p_position(&context).row == 0);
+    assert(p_position(&context).col == 1);
+    assert(context.token == TOKEN___EOF);
+
+    input = "a b";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+
+    input = "bb";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+
+    return 0;
+}

spec/test_parser_rule_from_multiple_states.d

@@ -0,0 +1,25 @@
+import testparser;
+import std.stdio;
+
+int main()
+{
+    return 0;
+}
+
+unittest
+{
+    string input = "a";
+    p_context_t context;
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_UNEXPECTED_TOKEN);
+    assert(p_position(&context) == p_position_t(0, 1));
+    assert(context.token == TOKEN___EOF);
+
+    input = "a b";
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
+
+    input = "bb";
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
+}

spec/test_parser_rule_user_code.c

@@ -0,0 +1,13 @@
+#include "testparser.h"
+#include <assert.h>
+#include <string.h>
+
+int main()
+{
+    char const * input = "ab";
+    p_context_t context;
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+
+    return 0;
+}

spec/test_parser_rule_user_code.d

@@ -9,6 +9,7 @@ int main()
 unittest
 {
     string input = "ab";
-    auto parser = new Testparser.Parser(input);
-    assert(parser.parse() == true);
+    p_context_t context;
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
 }

spec/test_parsing_json.c

@@ -0,0 +1,56 @@
+#include "testparser.h"
+#include "json_types.h"
+#include <string.h>
+#include <assert.h>
+
+int main()
+{
+    char const * input = "";
+    p_context_t context;
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+
+    input = "{}";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+    assert(p_result(&context)->id == JSON_OBJECT);
+
+    input = "[]";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+    assert(p_result(&context)->id == JSON_ARRAY);
+
+    input = "-45.6";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+    assert(p_result(&context)->id == JSON_NUMBER);
+    assert(p_result(&context)->number == -45.6);
+
+    input = "2E-2";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+    assert(p_result(&context)->id == JSON_NUMBER);
+    assert(p_result(&context)->number == 0.02);
+
+    input = "{\"hi\":true}";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+    JSONValue * o = p_result(&context);
+    assert(o->id == JSON_OBJECT);
+    assert_eq(1, o->object.size);
+    assert(strcmp(o->object.entries[0].name, "hi") == 0);
+    assert(o->object.entries[0].value->id == JSON_TRUE);
+
+    input = "{\"ff\": false, \"nn\": null}";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+    o = p_result(&context);
+    assert(o->id == JSON_OBJECT);
+    assert_eq(2, o->object.size);
+    assert(strcmp(o->object.entries[0].name, "ff") == 0);
+    assert(o->object.entries[0].value->id == JSON_FALSE);
+    assert(strcmp(o->object.entries[1].name, "nn") == 0);
+    assert(o->object.entries[1].value->id == JSON_NULL);
+
+    return 0;
+}

spec/test_parsing_json.d

@@ -10,44 +10,45 @@ int main()
 unittest
 {
     string input = ``;
-    auto parser = new Testparser.Parser(input);
-    assert(parser.parse());
+    p_context_t context;
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
 
     input = `{}`;
-    parser = new Testparser.Parser(input);
-    assert(parser.parse());
-    assert(cast(JSONObject)parser.result);
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
+    assert(cast(JSONObject)p_result(&context));
 
     input = `[]`;
-    parser = new Testparser.Parser(input);
-    assert(parser.parse());
-    assert(cast(JSONArray)parser.result);
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
+    assert(cast(JSONArray)p_result(&context));
 
     input = `-45.6`;
-    parser = new Testparser.Parser(input);
-    assert(parser.parse());
-    assert(cast(JSONNumber)parser.result);
-    assert((cast(JSONNumber)parser.result).value == -45.6);
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
+    assert(cast(JSONNumber)p_result(&context));
+    assert((cast(JSONNumber)p_result(&context)).value == -45.6);
 
     input = `2E-2`;
-    parser = new Testparser.Parser(input);
-    assert(parser.parse());
-    assert(cast(JSONNumber)parser.result);
-    assert((cast(JSONNumber)parser.result).value == 0.02);
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
+    assert(cast(JSONNumber)p_result(&context));
+    assert((cast(JSONNumber)p_result(&context)).value == 0.02);
 
     input = `{"hi":true}`;
-    parser = new Testparser.Parser(input);
-    assert(parser.parse());
-    assert(cast(JSONObject)parser.result);
-    JSONObject o = cast(JSONObject)parser.result;
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
+    assert(cast(JSONObject)p_result(&context));
+    JSONObject o = cast(JSONObject)p_result(&context);
     assert(o.value["hi"]);
     assert(cast(JSONTrue)o.value["hi"]);
 
     input = `{"ff": false, "nn": null}`;
-    parser = new Testparser.Parser(input);
-    assert(parser.parse());
-    assert(cast(JSONObject)parser.result);
-    o = cast(JSONObject)parser.result;
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
+    assert(cast(JSONObject)p_result(&context));
+    o = cast(JSONObject)p_result(&context);
     assert(o.value["ff"]);
     assert(cast(JSONFalse)o.value["ff"]);
     assert(o.value["nn"]);

spec/test_parsing_lists.c

@@ -0,0 +1,24 @@
+#include "testparser.h"
+#include <assert.h>
+#include <string.h>
+
+int main()
+{
+    char const * input = "a";
+    p_context_t context;
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+    assert(p_result(&context) == 1u);
+
+    input = "";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+    assert(p_result(&context) == 0u);
+
+    input = "aaaaaaaaaaaaaaaa";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+    assert(p_result(&context) == 16u);
+
+    return 0;
+}

spec/test_parsing_lists.d

@@ -9,17 +9,18 @@ int main()
 unittest
 {
     string input = "a";
-    auto parser = new Testparser.Parser(input);
-    assert(parser.parse() == true);
-    assert(parser.result == 1u);
+    p_context_t context;
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
+    assert(p_result(&context) == 1u);
 
     input = "";
-    parser = new Testparser.Parser(input);
-    assert(parser.parse() == true);
-    assert(parser.result == 0u);
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
+    assert(p_result(&context) == 0u);
 
     input = "aaaaaaaaaaaaaaaa";
-    parser = new Testparser.Parser(input);
-    assert(parser.parse() == true);
-    assert(parser.result == 16u);
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
+    assert(p_result(&context) == 16u);
 }

spec/test_pattern.c

@@ -0,0 +1,20 @@
+#include "testparser.h"
+#include <stdio.h>
+#include <assert.h>
+#include <string.h>
+
+int main()
+{
+    char const * input = "abcdef";
+    p_context_t context;
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+    printf("pass1\n");
+
+    input = "defabcdef";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+    printf("pass2\n");
+
+    return 0;
+}

spec/test_pattern.d

@@ -9,12 +9,13 @@ int main()
 unittest
 {
     string input = "abcdef";
-    auto parser = new Testparser.Parser(input);
-    assert(parser.parse() == true);
+    p_context_t context;
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
     writeln("pass1");
 
     input = "defabcdef";
-    parser = new Testparser.Parser(input);
-    assert(parser.parse() == true);
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
     writeln("pass2");
 }

spec/test_return_token_from_pattern.c

@@ -0,0 +1,13 @@
+#include "testparser.h"
+#include <assert.h>
+#include <string.h>
+
+int main()
+{
+    char const * input = "defghidef";
+    p_context_t context;
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+
+    return 0;
+}

spec/test_return_token_from_pattern.d

@@ -9,6 +9,7 @@ int main()
 unittest
 {
     string input = "defghidef";
-    auto parser = new Testparser.Parser(input);
-    assert(parser.parse() == true);
+    p_context_t context;
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
 }

spec/test_start_rule.c

@@ -0,0 +1,9 @@
+#include "testparser.h"
+#include <assert.h>
+#include <string.h>
+#include "testutils.h"
+
+int main()
+{
+    return 0;
+}

spec/test_start_rule.d

@@ -0,0 +1,8 @@
+import testparser;
+import std.stdio;
+import testutils;
+
+int main()
+{
+    return 0;
+}

spec/test_start_rule_ast.c

@@ -0,0 +1,17 @@
+#include "testparser.h"
+#include <assert.h>
+#include <string.h>
+#include "testutils.h"
+
+int main()
+{
+    char const * input = "hi";
+    p_context_t context;
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert_eq(P_SUCCESS, p_parse(&context));
+    Top * top = p_result(&context);
+    assert(top->pToken != NULL);
+    assert_eq(TOKEN_hi, top->pToken->token);
+
+    return 0;
+}

spec/test_start_rule_ast.d

@@ -0,0 +1,19 @@
+import testparser;
+import std.stdio;
+import testutils;
+
+int main()
+{
+    return 0;
+}
+
+unittest
+{
+    string input = "hi";
+    p_context_t context;
+    p_context_init(&context, input);
+    assert_eq(P_SUCCESS, p_parse(&context));
+    Top * top = p_result(&context);
+    assert(top.pToken !is null);
+    assert_eq(TOKEN_hi, top.pToken.token);
+}

spec/test_user_code.c

@@ -0,0 +1,20 @@
+#include "testparser.h"
+#include <assert.h>
+#include <stdio.h>
+#include <string.h>
+
+int main()
+{
+    char const * input = "abcdef";
+    p_context_t context;
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+    printf("pass1\n");
+
+    input = "abcabcdef";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+    printf("pass2\n");
+
+    return 0;
+}

spec/test_user_code.d

@@ -9,12 +9,13 @@ int main()
 unittest
 {
     string input = "abcdef";
-    auto parser = new Testparser.Parser(input);
-    assert(parser.parse() == true);
+    p_context_t context;
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
     writeln("pass1");
 
     input = "abcabcdef";
-    parser = new Testparser.Parser(input);
-    assert(parser.parse() == true);
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
     writeln("pass2");
 }

spec/test_user_terminate.c

@@ -0,0 +1,19 @@
+#include "testparser.h"
+#include <assert.h>
+#include <stdio.h>
+#include <string.h>
+
+int main()
+{
+    char const * input = "aacc";
+    p_context_t context;
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+
+    input = "abc";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_USER_TERMINATED);
+    assert(p_user_terminate_code(&context) == 4200);
+
+    return 0;
+}

spec/test_user_terminate.d

@@ -0,0 +1,20 @@
+import testparser;
+import std.stdio;
+
+int main()
+{
+    return 0;
+}
+
+unittest
+{
+    string input = "aacc";
+    p_context_t context;
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
+
+    input = "abc";
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_USER_TERMINATED);
+    assert(p_user_terminate_code(&context) == 4200);
+}

spec/test_user_terminate_lexer.c

@@ -0,0 +1,19 @@
+#include "testparser.h"
+#include <assert.h>
+#include <stdio.h>
+#include <string.h>
+
+int main()
+{
+    char const * input = "a";
+    p_context_t context;
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_SUCCESS);
+
+    input = "b";
+    p_context_init(&context, (uint8_t const *)input, strlen(input));
+    assert(p_parse(&context) == P_USER_TERMINATED);
+    assert(p_user_terminate_code(&context) == 8675309);
+
+    return 0;
+}

spec/test_user_terminate_lexer.d

@@ -0,0 +1,20 @@
+import testparser;
+import std.stdio;
+
+int main()
+{
+    return 0;
+}
+
+unittest
+{
+    string input = "a";
+    p_context_t context;
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_SUCCESS);
+
+    input = "b";
+    p_context_init(&context, input);
+    assert(p_parse(&context) == P_USER_TERMINATED);
+    assert(p_user_terminate_code(&context) == 8675309);
+}

spec/testutils.c

@@ -0,0 +1,38 @@
+#include <stdio.h>
+#include <assert.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <string.h>
+#include "testutils.h"
+
+void assert_eq_size_t_i(size_t expected, size_t actual, char const * file, size_t line)
+{
+    if (expected != actual)
+    {
+        fprintf(stderr, "%s:%lu: expected %lu, got %lu\n", file, line, expected, actual);
+        assert(false);
+    }
+}
+
+void str_init(str_t * str, char const * cs)
+{
+    size_t length = strlen(cs);
+    str->cs = malloc(length + 1u);
+    strcpy(str->cs, cs);
+}
+
+void str_append(str_t * str, char const * cs)
+{
+    size_t length = strlen(str->cs);
+    size_t length2 = strlen(cs);
+    char * new_cs = malloc(length + length2 + 1u);
+    memcpy(new_cs, str->cs, length);
+    strcpy(&new_cs[length], cs);
+    free(str->cs);
+    str->cs = new_cs;
+}
+
+void str_free(str_t * str)
+{
+    free(str->cs);
+}

spec/testutils.d

@@ -0,0 +1,10 @@
+import std.stdio;
+
+void assert_eq(T)(T expected, T actual, string file = __FILE__, size_t line = __LINE__)
+{
+    if (expected != actual)
+    {
+        stderr.writeln(file, ":", line, ": expected ", expected, ", got ", actual);
+        assert(false);
+    }
+}

spec/testutils.h

@@ -0,0 +1,19 @@
+#pragma once
+
+void assert_eq_size_t_i(size_t expected, size_t actual, char const * file, size_t line);
+
+#define assert_eq(expected, actual) \
+    assert_eq_size_t_i(expected, actual, __FILE__, __LINE__)
+
+typedef struct
+{
+    char * cs;
+} str_t;
+
+void str_init(str_t * str, char const * cs);
+void str_append(str_t * str, char const * cs);
+void str_free(str_t * str);
+static inline char * str_cstr(str_t * str)
+{
+    return str->cs;
+}