v1.1.0

Gemfile

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

Gemfile.lock

@@ -2,6 +2,7 @@ GEM
   remote: https://rubygems.org/
   specs:
     diff-lcs (1.5.0)
+    docile (1.4.0)
     psych (5.1.0)
       stringio
     rake (13.0.6)
@@ -21,6 +22,12 @@ GEM
       diff-lcs (>= 1.2.0, < 2.0)
       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)
 
@@ -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 +1,113 @@
 # 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
+  * target C or D language outputs
   * 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.c.erb

@@ -0,0 +1,955 @@
+#include "<%= File.basename(output_file).sub(%r{\.[a-z]+$}, "") %>.h"
+#include <stdbool.h>
+#include <stdlib.h>
+#include <string.h>
+
+/**************************************************************************
+ * User code blocks
+ *************************************************************************/
+
+<%= @grammar.code_blocks.fetch("", "") %>
+
+/**************************************************************************
+ * Private types
+ *************************************************************************/
+
+<% if @grammar.prefix.upcase != "P_" %>
+/* Result codes. */
+#define P_SUCCESS 0u
+#define P_DECODE_ERROR 1u
+#define P_UNEXPECTED_INPUT 2u
+#define P_UNEXPECTED_TOKEN 3u
+#define P_DROP 4u
+#define P_EOF 5u
+#define P_USER_TERMINATED 6u
+<% end %>
+
+/* An invalid ID value. */
+#define INVALID_ID ((size_t)-1)
+
+/**************************************************************************
+ * State initialization
+ *************************************************************************/
+
+/**
+ * Initialize lexer/parser context structure.
+ *
+ * @param[out] context
+ *   Lexer/parser context structure.
+ * @param input
+ *   Text input.
+ * @param input_length
+ *   Text input length.
+ */
+void <%= @grammar.prefix %>context_init(<%= @grammar.prefix %>context_t * context, uint8_t const * input, size_t input_length)
+{
+    /* New default-initialized context structure. */
+    <%= @grammar.prefix %>context_t newcontext = {0};
+
+    /* Lexer initialization. */
+    newcontext.input = input;
+    newcontext.input_length = input_length;
+    newcontext.mode = <%= @lexer.mode_id("default") %>;
+
+    /* Copy to the user's context structure. */
+    *context = newcontext;
+}
+
+/**************************************************************************
+ * Decoder
+ *************************************************************************/
+
+/**
+ * Decode a UTF-8 code point.
+ *
+ * @param input
+ *   Text input to decode.
+ * @param input_length
+ *   Input text length.
+ * @param[out] out_code_point
+ *   The decoded code point is stored here if the return value is P_SUCCESS.
+ * @param[out] out_code_point_length
+ *   The number of bytes the code point used is stored here if the return value
+ *   is P_SUCCESS.
+ *
+ * @retval P_SUCCESS on a successful code point decode
+ * @retval P_DECODE_ERROR when an encoding error is observed
+ * @retval P_EOF when the end of the text input is reached
+ */
+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)
+{
+    if (input_length == 0u)
+    {
+        return P_EOF;
+    }
+    char c = input[0];
+    <%= @grammar.prefix %>code_point_t code_point;
+    uint8_t code_point_length;
+    if ((c & 0x80u) == 0u)
+    {
+        code_point = c;
+        code_point_length = 1u;
+    }
+    else
+    {
+        uint8_t following_bytes;
+        if ((c & 0xE0u) == 0xC0u)
+        {
+            code_point = c & 0x1Fu;
+            following_bytes = 1u;
+        }
+        else if ((c & 0xF0u) == 0xE0u)
+        {
+            code_point = c & 0x0Fu;
+            following_bytes = 2u;
+        }
+        else if ((c & 0xF8u) == 0xF0u)
+        {
+            code_point = c & 0x07u;
+            following_bytes = 3u;
+        }
+        else if ((c & 0xFCu) == 0xF8u)
+        {
+            code_point = c & 0x03u;
+            following_bytes = 4u;
+        }
+        else if ((c & 0xFEu) == 0xFCu)
+        {
+            code_point = c & 0x01u;
+            following_bytes = 5u;
+        }
+        else
+        {
+            return P_DECODE_ERROR;
+        }
+        if (input_length <= following_bytes)
+        {
+            return P_DECODE_ERROR;
+        }
+        code_point_length = (uint8_t)(following_bytes + 1u);
+        for (size_t i = 0u; i < following_bytes; i++)
+        {
+            char b = input[i + 1u];
+            if ((b & 0xC0u) != 0x80u)
+            {
+                return P_DECODE_ERROR;
+            }
+            code_point = (code_point << 6u) | (b & 0x3Fu);
+        }
+    }
+    *out_code_point = code_point;
+    *out_code_point_length = code_point_length;
+    return P_SUCCESS;
+}
+
+/**************************************************************************
+ * Lexer
+ *************************************************************************/
+
+/** Lexer state ID type. */
+typedef <%= get_type_for(@lexer.state_table.size) %> lexer_state_id_t;
+
+/** Invalid lexer state ID. */
+#define INVALID_LEXER_STATE_ID <%= @lexer.state_table.size %>u
+
+/** Lexer user code ID type. */
+<% user_code_id_count = (@grammar.patterns.map(&:code_id).compact.max || 0) + 1 %>
+typedef <%= get_type_for(user_code_id_count) %> lexer_user_code_id_t;
+
+/** Invalid lexer user code ID. */
+#define INVALID_USER_CODE_ID <%= user_code_id_count %>u
+
+/**
+ * Lexer transition table entry.
+ *
+ * An incoming code point matching the range for a transition entry will cause
+ * the lexer to progress to the destination state.
+ */
+typedef struct
+{
+    /** First code point in the range for this transition. */
+    <%= @grammar.prefix %>code_point_t first;
+
+    /** Last code point in the range for this transition. */
+    <%= @grammar.prefix %>code_point_t last;
+
+    /** Destination lexer state ID for this transition. */
+    lexer_state_id_t destination_state;
+} lexer_transition_t;
+
+/** Lexer state table entry. */
+typedef struct
+{
+    /** Index to the transition table for this state. */
+    <%= get_type_for(@lexer.transition_table.size - 1) %> transition_table_index;
+
+    /** Number of transition table entries for this state. */
+    <%= get_type_for(@lexer.state_table.map {|ste| ste[:n_transitions]}.max) %> n_transitions;
+
+    /** Lexer token formed at this state. */
+    <%= @grammar.prefix %>token_t token;
+
+    /** Lexer user code ID to execute at this state. */
+    lexer_user_code_id_t code_id;
+
+    /** Whether this state matches a lexer pattern. */
+    bool accepts;
+} lexer_state_t;
+
+/** Lexer mode table entry. */
+typedef struct
+{
+    /** Offset in the state table to be used for this mode. */
+    uint32_t state_table_offset;
+} lexer_mode_t;
+
+/**
+ * Lexer match info structure.
+ *
+ * This structure holds output values from the lexer upon a successful pattern
+ * match.
+ */
+typedef struct
+{
+    /** Number of bytes of input text used to match. */
+    size_t length;
+
+    /** Input text position delta. */
+    <%= @grammar.prefix %>position_t delta_position;
+
+    /** Accepting lexer state from the match. */
+    lexer_state_t const * accepting_state;
+} lexer_match_info_t;
+
+/** Lexer transition table. */
+static lexer_transition_t lexer_transition_table[] = {
+<% @lexer.transition_table.each do |transition_table_entry| %>
+    {<%= transition_table_entry[:first] %>u, <%= transition_table_entry[:last] %>u, <%= transition_table_entry[:destination] %>u},
+<% end %>
+};
+
+/** Lexer state table. */
+static lexer_state_t lexer_state_table[] = {
+<% @lexer.state_table.each do |state_table_entry| %>
+    {<%= state_table_entry[:transition_table_index] %>u, <%= state_table_entry[:n_transitions] %>u, <%= state_table_entry[:token] || "INVALID_TOKEN_ID" %>, <%= state_table_entry[:code_id] || "INVALID_USER_CODE_ID" %>, <%= state_table_entry[:accepts] %>},
+<% end %>
+};
+
+/** Lexer mode table. */
+static lexer_mode_t lexer_mode_table[] = {
+<% @lexer.mode_table.each do |mode_table_entry| %>
+    {<%= mode_table_entry[:state_table_offset] %>},
+<% end %>
+};
+
+/**
+ * Execute user code associated with a lexer pattern.
+ *
+ * @param context
+ *   Lexer/parser context structure.
+ * @param code_id
+ *   The ID of the user code block to execute.
+ * @param match
+ *   Matched text for this pattern.
+ * @param match_length
+ *   Matched text length.
+ * @param out_token_info
+ *   Lexer token info in progress.
+ *
+ * @return Token to accept, or invalid token if the user code does
+ *   not explicitly return a token.
+ */
+static <%= @grammar.prefix %>token_t lexer_user_code(<%= @grammar.prefix %>context_t * context,
+    lexer_user_code_id_t code_id, uint8_t const * match,
+    size_t match_length, <%= @grammar.prefix %>token_info_t * out_token_info)
+{
+    switch (code_id)
+    {
+<% @grammar.patterns.each do |pattern| %>
+<%   if pattern.code_id %>
+    case <%= pattern.code_id %>u: {
+<%= expand_code(pattern.code, false, nil, pattern) %>
+    } break;
+<%   end %>
+<% end %>
+    default: break;
+    }
+
+    return INVALID_TOKEN_ID;
+}
+
+/**
+ * Check if there is a transition from the current lexer state to another
+ * based on the given input code point.
+ *
+ * @param current_state
+ *   Current lexer state.
+ * @param code_point
+ *   Input code point.
+ *
+ * @return Lexer state to transition to, or INVALID_LEXER_STATE_ID if none.
+ */
+static lexer_state_id_t check_lexer_transition(uint32_t current_state, uint32_t code_point)
+{
+    uint32_t transition_table_index = lexer_state_table[current_state].transition_table_index;
+    for (uint32_t i = 0u; i < lexer_state_table[current_state].n_transitions; i++)
+    {
+        if ((lexer_transition_table[transition_table_index + i].first <= code_point) &&
+            (code_point <= lexer_transition_table[transition_table_index + i].last))
+        {
+            return lexer_transition_table[transition_table_index + i].destination_state;
+        }
+    }
+    return INVALID_LEXER_STATE_ID;
+}
+
+/**
+ * Find the longest lexer pattern match at the current position.
+ *
+ * @param context
+ *   Lexer/parser context structure.
+ * @param[out] out_token_info
+ *   The lexed token information is stored here if the return value is
+ *   P_SUCCESS.
+ *
+ * @reval P_SUCCESS
+ *   A token was successfully lexed.
+ * @reval P_DECODE_ERROR
+ *   The decoder encountered invalid text encoding.
+ * @reval P_UNEXPECTED_INPUT
+ *   Input text does not match any lexer pattern.
+ * @retval P_EOF
+ *   The end of the text input was reached.
+ */
+static size_t find_longest_match(<%= @grammar.prefix %>context_t * context,
+    lexer_match_info_t * out_match_info, size_t * out_unexpected_input_length)
+{
+    lexer_match_info_t longest_match = {0};
+    lexer_match_info_t attempt_match = {0};
+    *out_match_info = longest_match;
+    uint32_t current_state = lexer_mode_table[context->mode].state_table_offset;
+    for (;;)
+    {
+        size_t const input_index = context->input_index + attempt_match.length;
+        uint8_t const * input = &context->input[input_index];
+        size_t input_length = context->input_length - input_index;
+        <%= @grammar.prefix %>code_point_t code_point;
+        uint8_t code_point_length;
+        size_t result = <%= @grammar.prefix %>decode_code_point(input, input_length, &code_point, &code_point_length);
+        switch (result)
+        {
+        case P_SUCCESS:
+            lexer_state_id_t transition_state = check_lexer_transition(current_state, code_point);
+            if (transition_state != INVALID_LEXER_STATE_ID)
+            {
+                attempt_match.length += code_point_length;
+                if (code_point == '\n')
+                {
+                    attempt_match.delta_position.row++;
+                    attempt_match.delta_position.col = 0u;
+                }
+                else
+                {
+                    attempt_match.delta_position.col++;
+                }
+                current_state = transition_state;
+                if (lexer_state_table[current_state].accepts)
+                {
+                    attempt_match.accepting_state = &lexer_state_table[current_state];
+                    longest_match = attempt_match;
+                }
+            }
+            else if (longest_match.length > 0)
+            {
+                *out_match_info = longest_match;
+                return P_SUCCESS;
+            }
+            else
+            {
+                *out_unexpected_input_length = attempt_match.length + code_point_length;
+                return P_UNEXPECTED_INPUT;
+            }
+            break;
+
+        case P_EOF:
+            /* We hit EOF. */
+            if (longest_match.length > 0)
+            {
+                /* We have a match, so use it. */
+                *out_match_info = longest_match;
+                return P_SUCCESS;
+            }
+            else if (attempt_match.length != 0)
+            {
+                /* There is a partial match - error! */
+                *out_unexpected_input_length = attempt_match.length;
+                return P_UNEXPECTED_INPUT;
+            }
+            else
+            {
+                /* Valid EOF return. */
+                return P_EOF;
+            }
+
+        case P_DECODE_ERROR:
+            /* If we see a decode error, we may be partially in the middle of
+             * matching a pattern, so return the attempted match info so that
+             * the input text position can be updated. */
+            *out_match_info = attempt_match;
+            return result;
+
+        default:
+            return result;
+        }
+    }
+}
+
+/**
+ * Attempt to lex the next token in the input stream.
+ *
+ * @param context
+ *   Lexer/parser context structure.
+ * @param[out] out_token_info
+ *   The lexed token information is stored here if the return value is
+ *   P_SUCCESS.
+ *
+ * @reval P_SUCCESS
+ *   A token was successfully lexed.
+ * @reval P_DECODE_ERROR
+ *   The decoder encountered invalid text encoding.
+ * @reval P_UNEXPECTED_INPUT
+ *   Input text does not match any lexer pattern.
+ * @retval P_DROP
+ *   A drop pattern was matched so the lexer should continue.
+ */
+static size_t attempt_lex_token(<%= @grammar.prefix %>context_t * context, <%= @grammar.prefix %>token_info_t * out_token_info)
+{
+    <%= @grammar.prefix %>token_info_t token_info = {0};
+    token_info.position = context->text_position;
+    token_info.token = INVALID_TOKEN_ID;
+    *out_token_info = token_info; // TODO: remove
+    lexer_match_info_t match_info;
+    size_t unexpected_input_length;
+    size_t result = find_longest_match(context, &match_info, &unexpected_input_length);
+    switch (result)
+    {
+    case P_SUCCESS:
+        <%= @grammar.prefix %>token_t token_to_accept = match_info.accepting_state->token;
+        if (match_info.accepting_state->code_id != INVALID_USER_CODE_ID)
+        {
+            uint8_t const * match = &context->input[context->input_index];
+            <%= @grammar.prefix %>token_t user_code_token = lexer_user_code(context,
+                match_info.accepting_state->code_id, match, match_info.length, &token_info);
+            /* An invalid token returned from lexer_user_code() means that the
+             * user code did not explicitly return a token. So only override
+             * the token to return if the user code does explicitly return a
+             * token. */
+            if (user_code_token != INVALID_TOKEN_ID)
+            {
+                token_to_accept = user_code_token;
+            }
+        }
+
+        /* Update the input position tracking. */
+        context->input_index += match_info.length;
+        context->text_position.row += match_info.delta_position.row;
+        if (match_info.delta_position.row != 0u)
+        {
+            context->text_position.col = match_info.delta_position.col;
+        }
+        else
+        {
+            context->text_position.col += match_info.delta_position.col;
+        }
+
+        if (token_to_accept == INVALID_TOKEN_ID)
+        {
+            return P_DROP;
+        }
+        token_info.token = token_to_accept;
+        token_info.length = match_info.length;
+        *out_token_info = token_info;
+        return P_SUCCESS;
+
+    case P_EOF:
+        token_info.token = TOKEN___EOF;
+        *out_token_info = token_info;
+        return P_SUCCESS;
+
+    case P_DECODE_ERROR:
+        /* Update the input position tracking. */
+        context->input_index += match_info.length;
+        context->text_position.row += match_info.delta_position.row;
+        if (match_info.delta_position.row != 0u)
+        {
+            context->text_position.col = match_info.delta_position.col;
+        }
+        else
+        {
+            context->text_position.col += match_info.delta_position.col;
+        }
+        return result;
+
+    default:
+        return result;
+    }
+}
+
+/**
+ * Lex the next token in the input stream.
+ *
+ * @param context
+ *   Lexer/parser context structure.
+ * @param[out] out_token_info
+ *   The lexed token information is stored here if the return value is
+ *   P_SUCCESS.
+ *
+ * @reval P_SUCCESS
+ *   A token was successfully lexed.
+ * @reval P_DECODE_ERROR
+ *   The decoder encountered invalid text encoding.
+ * @reval P_UNEXPECTED_INPUT
+ *   Input text does not match any lexer pattern.
+ */
+size_t <%= @grammar.prefix %>lex(<%= @grammar.prefix %>context_t * context, <%= @grammar.prefix %>token_info_t * out_token_info)
+{
+    for (;;)
+    {
+        size_t result = attempt_lex_token(context, out_token_info);
+        if (result != P_DROP)
+        {
+            return result;
+        }
+    }
+}
+
+/**************************************************************************
+ * Parser
+ *************************************************************************/
+
+/** Reduce ID type. */
+typedef <%= get_type_for(@parser.reduce_table.size) %> reduce_id_t;
+
+/**
+ * A symbol ID can hold either a token ID or a rule set ID.
+ *
+ * Token IDs and rule set IDs share the same namespace, with rule set IDs
+ * beginning after token IDs end.
+ */
+typedef <%= get_type_for(@parser.rule_sets.map(&:last).map(&:id).max) %> symbol_id_t;
+
+/** Parser state ID type. */
+typedef <%= get_type_for(@parser.state_table.size) %> parser_state_id_t;
+
+/** Parser rule ID type. */
+typedef <%= get_type_for(@grammar.rules.size) %> rule_id_t;
+
+/** Parser shift ID type. */
+typedef <%= get_type_for(@parser.shift_table.size) %> shift_id_t;
+
+/** Shift table entry. */
+typedef struct
+{
+    /** Token or rule set ID. */
+    symbol_id_t symbol_id;
+
+    /** Parser state to shift to. */
+    parser_state_id_t state_id;
+} shift_t;
+
+/** Reduce table entry. */
+typedef struct
+{
+    /** Lookahead token. */
+    <%= @grammar.prefix %>token_t token;
+
+    /**
+     * Rule ID.
+     *
+     * This is used to execute the parser user code block associated with a
+     * grammar rule.
+     */
+    rule_id_t rule;
+
+    /**
+     * Rule set ID.
+     *
+     * This is used as the new top symbol ID of the parse stack after this
+     * reduce action.
+     */
+    symbol_id_t rule_set;
+
+    /**
+     * Number of states leading to this reduce action.
+     *
+     * This is the number of entries popped from the parse stack after this
+     * reduce action.
+     */
+    parser_state_id_t n_states;
+} reduce_t;
+
+/** Parser state entry. */
+typedef struct
+{
+    /** First shift table entry for this parser state. */
+    shift_id_t shift_table_index;
+
+    /** Number of shift table entries for this parser state. */
+    shift_id_t n_shift_entries;
+
+    /** First reduce table entry for this parser state. */
+    reduce_id_t reduce_table_index;
+
+    /** Number of reduce table entries for this parser state. */
+    reduce_id_t n_reduce_entries;
+} parser_state_t;
+
+/**
+ * Structure to hold a state ID and value pair.
+ *
+ * A stack of these structures makes up the parse stack.
+ */
+typedef struct
+{
+    /** Parser state ID. */
+    size_t state_id;
+
+    /** Parser value from this state. */
+    <%= @grammar.prefix %>value_t pvalue;
+} state_value_t;
+
+/** Parser shift table. */
+static const shift_t parser_shift_table[] = {
+<%   @parser.shift_table.each do |shift| %>
+    {<%= shift[:symbol_id] %>u, <%= shift[:state_id] %>u},
+<%   end %>
+};
+
+/** Parser reduce table. */
+static const reduce_t parser_reduce_table[] = {
+<%   @parser.reduce_table.each do |reduce| %>
+    {<%= reduce[:token_id] %>u, <%= reduce[:rule_id] %>u, <%= reduce[:rule_set_id] %>u, <%= reduce[:n_states] %>u},
+<%   end %>
+};
+
+/** Parser state table. */
+static const parser_state_t parser_state_table[] = {
+<%   @parser.state_table.each do |state| %>
+    {<%= state[:shift_index] %>u, <%= state[:n_shifts] %>u, <%= state[:reduce_index] %>u, <%= state[:n_reduces] %>u},
+<%   end %>
+};
+
+/* state_values stack functionality */
+
+/** state_values stack type. */
+typedef struct
+{
+    size_t length;
+    size_t capacity;
+    state_value_t * entries;
+} state_values_stack_t;
+
+/**
+ * Initialize state_values stack structure.
+ *
+ * @param stack
+ *   state_values stack structure.
+ */
+static void state_values_stack_init(state_values_stack_t * stack)
+{
+    const size_t initial_capacity = 10u;
+    stack->length = 0u;
+    stack->capacity = initial_capacity;
+    stack->entries = (state_value_t *)malloc(initial_capacity * sizeof(state_value_t));
+}
+
+/**
+ * Index a state_values stack.
+ *
+ * @param stack
+ *   state_values stack structure.
+ * @param index
+ *   Index to the stack.
+ *
+ * @return Pointer to the state value structure at the given index.
+ */
+static state_value_t * state_values_stack_index(state_values_stack_t * stack, int index)
+{
+    if (index >= 0)
+    {
+        return &stack->entries[index];
+    }
+    else
+    {
+        return &stack->entries[stack->length - (size_t)(unsigned int)(-index)];
+    }
+}
+
+/**
+ * Push a new state_value to the state_values stack.
+ *
+ * @param stack
+ *   state_values stack structure.
+ */
+static void state_values_stack_push(state_values_stack_t * stack)
+{
+    size_t const current_capacity = stack->capacity;
+    size_t const current_length = stack->length;
+    if (current_length >= current_capacity)
+    {
+        size_t const new_capacity = current_capacity * 2u;
+        state_value_t * new_entries = malloc(new_capacity * sizeof(state_value_t));
+        memcpy(new_entries, stack->entries, current_length * sizeof(state_value_t));
+        free(stack->entries);
+        stack->capacity = new_capacity;
+        stack->entries = new_entries;
+    }
+    memset(&stack->entries[current_length], 0, sizeof(state_value_t));
+    stack->length = current_length + 1u;
+}
+
+/**
+ * Pop entries from a state_values stack.
+ *
+ * @param stack
+ *   state_values stack structure.
+ * @param n
+ *   Number of states to pop.
+ */
+static void state_values_stack_pop(state_values_stack_t * stack, size_t n)
+{
+    stack->length -= n;
+}
+
+/**
+ * Free memory for a state_values stack structure.
+ *
+ * @param stack
+ *   state_values stack structure.
+ */
+static void state_values_stack_free(state_values_stack_t * stack)
+{
+     free(stack->entries);
+}
+
+/**
+ * Execute user code associated with a parser rule.
+ *
+ * @param rule The ID of the rule.
+ *
+ * @retval P_SUCCESS
+ *   Continue parsing.
+ * @retval P_USER_TERMINATED
+ *   User requested to terminate parsing.
+ */
+static size_t parser_user_code(<%= @grammar.prefix %>value_t * _pvalue, uint32_t rule, state_values_stack_t * statevalues, uint32_t n_states, <%= @grammar.prefix %>context_t * context)
+{
+    switch (rule)
+    {
+<% @grammar.rules.each do |rule| %>
+<%   if rule.code %>
+    case <%= rule.id %>u: {
+<%= expand_code(rule.code, true, rule, nil) %>
+    } break;
+<%   end %>
+<% end %>
+    default: break;
+    }
+
+    return P_SUCCESS;
+}
+
+/**
+ * Check if the parser should shift to a new state.
+ *
+ * @param state_id
+ *   Parser state ID.
+ * @param symbol_id
+ *   Incoming token/rule set ID.
+ *
+ * @return State to shift to, or INVALID_ID if none.
+ */
+static size_t check_shift(size_t state_id, size_t symbol_id)
+{
+    uint32_t start = parser_state_table[state_id].shift_table_index;
+    uint32_t end = start + parser_state_table[state_id].n_shift_entries;
+    for (uint32_t i = start; i < end; i++)
+    {
+        if (parser_shift_table[i].symbol_id == symbol_id)
+        {
+            return parser_shift_table[i].state_id;
+        }
+    }
+    return INVALID_ID;
+}
+
+/**
+ * Check if the parser should reduce to a new state.
+ *
+ * @param state_id
+ *   Parser state ID.
+ * @param token
+ *   Incoming token.
+ *
+ * @return State to reduce to, or INVALID_ID if none.
+ */
+static size_t check_reduce(size_t state_id, <%= @grammar.prefix %>token_t token)
+{
+    size_t start = parser_state_table[state_id].reduce_table_index;
+    size_t end = start + parser_state_table[state_id].n_reduce_entries;
+    for (size_t i = start; i < end; i++)
+    {
+        if ((parser_reduce_table[i].token == token) ||
+            (parser_reduce_table[i].token == INVALID_TOKEN_ID))
+        {
+            return i;
+        }
+    }
+    return INVALID_ID;
+}
+
+/**
+ * Run the parser.
+ *
+ * @param context
+ *   Lexer/parser context structure.
+ *
+ * @retval P_SUCCESS
+ *   The parser successfully matched the input text. The parse result value
+ *   can be accessed with <%= @grammar.prefix %>result().
+ * @retval P_UNEXPECTED_TOKEN
+ *   An unexpected token was encountered that does not match any grammar rule.
+ *   The value context->token holds the unexpected token.
+ * @reval P_DECODE_ERROR
+ *   The decoder encountered invalid text encoding.
+ * @reval P_UNEXPECTED_INPUT
+ *   Input text does not match any lexer pattern.
+ */
+size_t <%= @grammar.prefix %>parse(<%= @grammar.prefix %>context_t * context)
+{
+    <%= @grammar.prefix %>token_info_t token_info;
+    <%= @grammar.prefix %>token_t token = INVALID_TOKEN_ID;
+    state_values_stack_t statevalues;
+    size_t reduced_rule_set = INVALID_ID;
+    <%= @grammar.prefix %>value_t reduced_parser_value;
+    state_values_stack_init(&statevalues);
+    state_values_stack_push(&statevalues);
+    size_t result;
+    for (;;)
+    {
+        if (token == INVALID_TOKEN_ID)
+        {
+            size_t lexer_result = <%= @grammar.prefix %>lex(context, &token_info);
+            if (lexer_result != P_SUCCESS)
+            {
+                result = lexer_result;
+                break;
+            }
+            token = token_info.token;
+        }
+        size_t shift_state = INVALID_ID;
+        if (reduced_rule_set != INVALID_ID)
+        {
+            shift_state = check_shift(state_values_stack_index(&statevalues, -1)->state_id, reduced_rule_set);
+        }
+        if (shift_state == INVALID_ID)
+        {
+            shift_state = check_shift(state_values_stack_index(&statevalues, -1)->state_id, token);
+            if ((shift_state != INVALID_ID) && (token == TOKEN___EOF))
+            {
+                /* Successful parse. */
+                context->parse_result = state_values_stack_index(&statevalues, -1)->pvalue;
+                result = P_SUCCESS;
+                break;
+            }
+        }
+        if (shift_state != INVALID_ID)
+        {
+            /* We have something to shift. */
+            state_values_stack_push(&statevalues);
+            state_values_stack_index(&statevalues, -1)->state_id = shift_state;
+            if (reduced_rule_set == INVALID_ID)
+            {
+                /* We shifted a token, mark it consumed. */
+                token = INVALID_TOKEN_ID;
+                state_values_stack_index(&statevalues, -1)->pvalue = token_info.pvalue;
+            }
+            else
+            {
+                /* We shifted a RuleSet. */
+                state_values_stack_index(&statevalues, -1)->pvalue = reduced_parser_value;
+                <%= @grammar.prefix %>value_t new_parse_result = {0};
+                reduced_parser_value = new_parse_result;
+                reduced_rule_set = INVALID_ID;
+            }
+            continue;
+        }
+
+        size_t reduce_index = check_reduce(state_values_stack_index(&statevalues, -1)->state_id, token);
+        if (reduce_index != INVALID_ID)
+        {
+            /* We have something to reduce. */
+            <%= @grammar.prefix %>value_t reduced_parser_value2 = {0};
+            if (parser_user_code(&reduced_parser_value2, parser_reduce_table[reduce_index].rule, &statevalues, parser_reduce_table[reduce_index].n_states, context) == P_USER_TERMINATED)
+            {
+                return P_USER_TERMINATED;
+            }
+            reduced_parser_value = reduced_parser_value2;
+            reduced_rule_set = parser_reduce_table[reduce_index].rule_set;
+            state_values_stack_pop(&statevalues, parser_reduce_table[reduce_index].n_states);
+            continue;
+        }
+
+        /* A token was successfully lexed, so the input text position was
+         * advanced. However, this is an unexpected token, so we want to reset
+         * the context text position to point to the token rather than the text
+         * after it, so that if the caller wants to report the error position,
+         * it will point to the correct position of the unexpected token. */
+        context->text_position = token_info.position;
+        context->token = token;
+        result = P_UNEXPECTED_TOKEN;
+        break;
+    }
+    state_values_stack_free(&statevalues);
+    return result;
+}
+
+/**
+ * Get the parse result value.
+ *
+ * @param context
+ *   Lexer/parser context structure.
+ *
+ * @return Parse result value.
+ */
+<%= start_rule_type[1] %> <%= @grammar.prefix %>result(<%= @grammar.prefix %>context_t * context)
+{
+    return context->parse_result.v_<%= start_rule_type[0] %>;
+}
+
+/**
+ * Get the current text input position.
+ *
+ * @param context
+ *   Lexer/parser context structure.
+ *
+ * @return Current text position.
+ */
+<%= @grammar.prefix %>position_t <%= @grammar.prefix %>position(<%= @grammar.prefix %>context_t * context)
+{
+    return context->text_position;
+}
+
+/**
+ * Get the user terminate code.
+ *
+ * @param context
+ *   Lexer/parser context structure.
+ *
+ * @return User terminate code.
+ */
+size_t <%= @grammar.prefix %>user_terminate_code(<%= @grammar.prefix %>context_t * context)
+{
+    return context->user_terminate_code;
+}

assets/parser.d.erb

@@ -12,9 +12,7 @@ module <%= @grammar.modulename %>;
  * User code blocks
  *************************************************************************/
 
-<% @grammar.code_blocks.each do |code| %>
+<%= @grammar.code_blocks.fetch("", "") %>
-<%= code %>
-<% end %>
 
 /**************************************************************************
  * Public types
@@ -29,6 +27,7 @@ public enum : size_t
     <%= @grammar.prefix.upcase %>UNEXPECTED_TOKEN,
     <%= @grammar.prefix.upcase %>DROP,
     <%= @grammar.prefix.upcase %>EOF,
+    <%= @grammar.prefix.upcase %>USER_TERMINATED,
 }
 
 /** Token type. */
@@ -116,6 +115,9 @@ public struct <%= @grammar.prefix %>context_t
 
     /** Unexpected token received. */
     <%= @grammar.prefix %>token_t token;
+
+    /** User terminate code. */
+    size_t user_terminate_code;
 }
 
 /**************************************************************************
@@ -143,6 +145,7 @@ private enum : size_t
     P_UNEXPECTED_TOKEN,
     P_DROP,
     P_EOF,
+    P_USER_TERMINATED,
 }
 <% end %>
 
@@ -504,7 +507,6 @@ private size_t find_longest_match(<%= @grammar.prefix %>context_t * context,
                 /* Valid EOF return. */
                 return P_EOF;
             }
-            break;
 
         case P_DECODE_ERROR:
             /* If we see a decode error, we may be partially in the middle of
@@ -764,12 +766,13 @@ private immutable parser_state_t[] parser_state_table = [
  *
  * @param rule The ID of the rule.
  *
- * @return Parse value.
+ * @retval P_SUCCESS
+ *   Continue parsing.
+ * @retval P_USER_TERMINATED
+ *   User requested to terminate parsing.
  */
-private <%= @grammar.prefix %>value_t parser_user_code(uint rule, state_value_t[] statevalues, uint n_states)
+private size_t parser_user_code(<%= @grammar.prefix %>value_t * _pvalue, uint rule, state_value_t[] statevalues, uint n_states, <%= @grammar.prefix %>context_t * context)
 {
-    <%= @grammar.prefix %>value_t _pvalue;
-
     switch (rule)
     {
 <% @grammar.rules.each do |rule| %>
@@ -782,7 +785,7 @@ private <%= @grammar.prefix %>value_t parser_user_code(uint rule, state_value_t[
     default: break;
     }
 
-    return _pvalue;
+    return P_SUCCESS;
 }
 
 /**
@@ -909,7 +912,12 @@ public size_t <%= @grammar.prefix %>parse(<%= @grammar.prefix %>context_t * cont
         if (reduce_index != INVALID_ID)
         {
             /* We have something to reduce. */
-            reduced_parser_value = parser_user_code(parser_reduce_table[reduce_index].rule, statevalues, parser_reduce_table[reduce_index].n_states);
+            <%= @grammar.prefix %>value_t reduced_parser_value2;
+            if (parser_user_code(&reduced_parser_value2, parser_reduce_table[reduce_index].rule, statevalues, parser_reduce_table[reduce_index].n_states, context) == P_USER_TERMINATED)
+            {
+                return P_USER_TERMINATED;
+            }
+            reduced_parser_value = reduced_parser_value2;
             reduced_rule_set = parser_reduce_table[reduce_index].rule_set;
             statevalues.length -= parser_reduce_table[reduce_index].n_states;
             continue;
@@ -951,3 +959,16 @@ public <%= @grammar.prefix %>position_t <%= @grammar.prefix %>position(<%= @gram
 {
     return context.text_position;
 }
+
+/**
+ * Get the user terminate code.
+ *
+ * @param context
+ *   Lexer/parser context structure.
+ *
+ * @return User terminate code.
+ */
+public size_t <%= @grammar.prefix %>user_terminate_code(<%= @grammar.prefix %>context_t * context)
+{
+    return context.user_terminate_code;
+}

assets/parser.h.erb

@@ -0,0 +1,131 @@
+/**
+ * @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.invalid_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
+
+/** Code point type. */
+typedef uint32_t <%= @grammar.prefix %>code_point_t;
+
+/** User header code blocks. */
+<%= @grammar.code_blocks.fetch("header", "") %>
+
+/** Parser values type(s). */
+typedef union
+{
+<% @grammar.ptypes.each do |name, typestring| %>
+    <%= typestring %> v_<%= name %>;
+<% end %>
+} <%= @grammar.prefix %>value_t;
+
+/**
+ * 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. */
+    <%= @grammar.prefix %>value_t parse_result;
+
+    /** Unexpected token received. */
+    <%= @grammar.prefix %>token_t token;
+
+    /** User terminate code. */
+    size_t user_terminate_code;
+} <%= @grammar.prefix %>context_t;
+
+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);
+
+<%= start_rule_type[1] %> <%= @grammar.prefix %>result(<%= @grammar.prefix %>context_t * context);
+
+<%= @grammar.prefix %>position_t <%= @grammar.prefix %>position(<%= @grammar.prefix %>context_t * context);
+
+size_t <%= @grammar.prefix %>user_terminate_code(<%= @grammar.prefix %>context_t * context);

doc/user_guide.md

@@ -7,15 +7,15 @@ ${/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
   * is MIT-licensed
   * is distributable as a standalone Ruby script
-  * supports D language
 
 #> Installation
 
@@ -56,8 +56,10 @@ Example grammar file:
 import std.math;
 >>
 
+# Parser values are unsigned integers.
 ptype ulong;
 
+# A few basic arithmetic operators.
 token plus /\\+/;
 token times /\\*/;
 token power /\\*\\*/;
@@ -72,6 +74,7 @@ token integer /\\d+/ <<
 >>
 token lparen /\\(/;
 token rparen /\\)/;
+# Drop whitespace.
 drop /\\s+/;
 
 Start -> E1 <<
@@ -103,6 +106,618 @@ E4 -> lparen E1 rparen <<
 >>
 ```
 
+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 with the line following a "<<" token and end with the
+line preceding a grammar line consisting of solely the ">>" token.
+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...
+
+##> 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 `\d` sequence matches any character `0` through `9`.
+    * The `\s` sequence matches a space, horizontal tab `\t`, carriage return
+    `\r`, a form feed `\f`, or a vertical tab `\v` character.
+    * 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]`.
+
+##> 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 grammar file must define a rule with the name `Start` which will be used as
+the top-level starting rule that the parser attempts to reduce.
+
+Example:
+
+```
+ptype ulong;
+token word /[a-z]+/ <<
+  $$ = match.length;
+>>
+Start -> word <<
+  $$ = $1;
+>>
+```
+
+In the above example the `Start` rule is defined to match a single `word`
+token.
+
+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 <<
+  $$ = $2;
+>>
+```
+
+A parser rule has zero or more terms on the right side of its definition.
+Each of these terms is either a token name or a rule name.
+
+In a parser rule code block, parser values for the right side terms are
+accessible as `$1` for the first term's parser value, `$2` for the second
+term's parser value, etc...
+The `$$` 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.
+
+##> 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 parser
+
+Propane supports allowing parser user code blocks to terminate execution of the
+parser.
+One example use of this functionality is to detect and report an error before
+the parser continues parsing the remainder of the input.
+Another use of this features is to begin parsing input and determine whether a
+different parser should be used instead.
+
+To terminate parsing from a 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.
+
+##> 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.
+
+Example:
+
+```
+p_context_t context;
+p_context_init(&context, input, input_length);
+```
+
+### `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);
+}
+```
+
+### `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);
+}
+```
+
 #> 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/generator.rb

@@ -10,16 +10,29 @@ 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: "<>")
+      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|
+        File.open(output_file, "wb") do |fh|
           fh.write(result)
         end
+      end
       @log.close
     end
 
@@ -187,25 +200,54 @@ class Propane
       end
       if parser
         code = code.gsub(/\$\$/) do |match|
+          case @language
+          when "c"
+            "_pvalue->v_#{rule.ptypename}"
+          when "d"
             "_pvalue.v_#{rule.ptypename}"
           end
+        end
         code = code.gsub(/\$(\d+)/) do |match|
           index = $1.to_i
+          case @language
+          when "c"
+            "state_values_stack_index(statevalues, -1 - (int)n_states + #{index})->pvalue.v_#{rule.components[index - 1].ptypename}"
+          when "d"
             "statevalues[$-1-n_states+#{index}].pvalue.v_#{rule.components[index - 1].ptypename}"
           end
+        end
+        code = code.gsub(/\$terminate\((.*)\);/) do |match|
+          user_terminate_code = $1
+          case @language
+          when "c"
+            "context->user_terminate_code = (#{user_terminate_code}); return P_USER_TERMINATED;"
+          when "d"
+            "context.user_terminate_code = (#{user_terminate_code}); return P_USER_TERMINATED;"
+          end
+        end
       else
         code = code.gsub(/\$\$/) do |match|
+          case @language
+          when "c"
+            "out_token_info->pvalue.v_#{pattern.ptypename}"
+          when "d"
             "out_token_info.pvalue.v_#{pattern.ptypename}"
           end
+        end
         code = code.gsub(/\$mode\(([a-zA-Z_][a-zA-Z_0-9]*)\)/) do |match|
           mode_name = $1
           mode_id = @lexer.mode_id(mode_name)
           unless mode_id
             raise Error.new("Lexer mode '#{mode_name}' not found")
           end
+          case @language
+          when "c"
+            "context->mode = #{mode_id}u"
+          when "d"
             "context.mode = #{mode_id}u"
           end
         end
+      end
       code
     end
 
@@ -229,13 +271,28 @@ class Propane
     #   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
 

lib/propane/grammar.rb

@@ -5,7 +5,6 @@ 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 :modulename
     attr_reader :patterns
     attr_reader :rules
@@ -18,7 +17,7 @@ class Propane
       @patterns = []
       @tokens = []
       @rules = []
-      @code_blocks = []
+      @code_blocks = {}
       @line_number = 1
       @next_line_number = @line_number
       @mode = nil
@@ -49,7 +48,6 @@ class Propane
       elsif parse_comment_line!
       elsif @mode.nil? && parse_mode_label!
       elsif parse_module_statement!
-      elsif parse_class_statement!
       elsif parse_ptype_statement!
       elsif parse_pattern_statement!
       elsif parse_token_statement!
@@ -90,16 +88,6 @@ 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"
@@ -191,8 +179,13 @@ class Propane
     end
 
     def parse_code_block_statement!
-      if code = parse_code_block!
+      if md = consume!(/<<([a-z]*)\n(.*?)^>>\n/m)
-        @code_blocks << code
+        name, code = md[1..2]
+        if @code_blocks[name]
+          @code_blocks[name] += code
+        else
+          @code_blocks[name] = code
+        end
         @mode = nil
         true
       end

lib/propane/version.rb

@@ -1,3 +1,3 @@
 class Propane
-  VERSION = "0.1.0"
+  VERSION = "1.1.0"
 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 = []
 
@@ -25,8 +44,12 @@ combine_files = lambda do |file|
         if File.exist?(path)
           unless files_processed[path]
             files_processed[path] = true
+            if require_name == "propane/assets"
+              combined_file << assets_module
+            else
               combine_files[path]
             end
+          end
         else
           raise "require path #{path.inspect} not found"
         end

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;
@@ -30,7 +29,6 @@ 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  *")
@@ -38,44 +36,44 @@ EOF
 
       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
 
@@ -84,19 +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
 

spec/propane_spec.rb

@@ -4,14 +4,52 @@ require "open3"
 Results = Struct.new(:stdout, :stderr, :status)
 
 describe Propane do
+  before(:all) do
+    @statics = {}
+  end
+
   def write_grammar(grammar, options = {})
     options[:name] ||= ""
     File.write("spec/run/testparser#{options[:name]}.propane", grammar)
   end
 
   def build_parser(options = {})
-    options[:name] ||= ""
+    @statics[:build_test_id] ||= 0
-    command = %W[./propane.sh spec/run/testparser#{options[:name]}.propane spec/run/testparser#{options[:name]}.d --log spec/run/testparser#{options[:name]}.log]
+    @statics[:build_test_id] += 1
+    if ENV["dist_specs"]
+      command = %W[dist/propane]
+    else
+      command = %W[ruby -I spec/run -r _simplecov_setup -I lib bin/propane]
+      command_prefix =
+        if ENV["partial_specs"]
+          "p"
+        else
+          "b"
+        end
+      command_name = "#{command_prefix}#{@statics[:build_test_id]}"
+      File.open("spec/run/_simplecov_setup.rb", "w") do |fh|
+        fh.puts <<EOF
+require "bundler"
+Bundler.setup
+require "simplecov"
+class MyFormatter
+  def format(*args)
+  end
+end
+SimpleCov.start do
+  command_name(#{command_name.inspect})
+  filters.clear
+  add_filter do |src|
+    !(src.filename[SimpleCov.root])
+  end
+  formatter(MyFormatter)
+end
+# force color off
+ENV["TERM"] = nil
+EOF
+      end
+    end
+    command += %W[spec/run/testparser#{options[:name]}.propane spec/run/testparser#{options[:name]}.#{options[:language]} --log spec/run/testparser#{options[:name]}.log]
     if (options[:capture])
       stdout, stderr, status = Open3.capture3(*command)
       Results.new(stdout, stderr, status)
@@ -25,9 +63,14 @@ describe Propane do
     test_files = Array(test_files)
     options[:parsers] ||= [""]
     parsers = options[:parsers].map do |name|
-      "spec/run/testparser#{name}.d"
+      "spec/run/testparser#{name}.#{options[:language]}"
     end
+    case options[:language]
+    when "c"
+      result = system(*%w[gcc -Wall -o spec/run/testparser -Ispec -Ispec/run], *parsers, *test_files, "spec/testutils.c", "-lm")
+    when "d"
       result = system(*%w[ldc2 --unittest -of spec/run/testparser -Ispec], *parsers, *test_files, "spec/testutils.d")
+    end
     expect(result).to be_truthy
   end
 
@@ -69,6 +112,10 @@ describe Propane do
     FileUtils.mkdir_p("spec/run")
   end
 
+  %w[d c].each do |language|
+
+    context "#{language.upcase} language" do
+
       it "generates a lexer" do
         write_grammar <<EOF
 token int /\\d+/;
@@ -81,14 +128,32 @@ Foo -> int <<
 Foo -> plus <<
 >>
 EOF
-    build_parser
+        build_parser(language: language)
-    compile("spec/test_lexer.d")
+        compile("spec/test_lexer.#{language}", language: language)
         results = run
         expect(results.stderr).to eq ""
         expect(results.status).to eq 0
       end
 
       it "detects a lexer error when an unknown character is seen" do
+        case language
+        when "c"
+          write_grammar <<EOF
+ptype int;
+token int /\\d+/ <<
+  int v = 0;
+  for (size_t i = 0u; i < match_length; i++)
+  {
+    v *= 10;
+    v += (match[i] - '0');
+  }
+  $$ = v;
+>>
+Start -> int <<
+  $$ = $1;
+>>
+EOF
+        when "d"
           write_grammar <<EOF
 ptype int;
 token int /\\d+/ <<
@@ -104,8 +169,9 @@ Start -> int <<
   $$ = $1;
 >>
 EOF
-    build_parser
+        end
-    compile("spec/test_lexer_unknown_character.d")
+        build_parser(language: language)
+        compile("spec/test_lexer_unknown_character.#{language}", language: language)
         results = run
         expect(results.stderr).to eq ""
         expect(results.status).to eq 0
@@ -124,10 +190,64 @@ E -> B;
 B -> zero;
 B -> one;
 EOF
-    build_parser
+        build_parser(language: language)
       end
 
       it "generates a parser that does basic math - user guide example" do
+        case language
+        when "c"
+          write_grammar <<EOF
+<<
+#include <math.h>
+>>
+
+ptype size_t;
+
+token plus /\\+/;
+token times /\\*/;
+token power /\\*\\*/;
+token integer /\\d+/ <<
+  size_t v = 0u;
+  for (size_t i = 0u; i < match_length; i++)
+  {
+    v *= 10;
+    v += (match[i] - '0');
+  }
+  $$ = v;
+>>
+token lparen /\\(/;
+token rparen /\\)/;
+drop /\\s+/;
+
+Start -> E1 <<
+  $$ = $1;
+>>
+E1 -> E2 <<
+  $$ = $1;
+>>
+E1 -> E1 plus E2 <<
+  $$ = $1 + $3;
+>>
+E2 -> E3 <<
+  $$ = $1;
+>>
+E2 -> E2 times E3 <<
+  $$ = $1 * $3;
+>>
+E3 -> E4 <<
+  $$ = $1;
+>>
+E3 -> E3 power E4 <<
+  $$ = (size_t)pow($1, $3);
+>>
+E4 -> integer <<
+  $$ = $1;
+>>
+E4 -> lparen E1 rparen <<
+  $$ = $2;
+>>
+EOF
+        when "d"
           write_grammar <<EOF
 <<
 import std.math;
@@ -179,8 +299,9 @@ E4 -> lparen E1 rparen <<
   $$ = $2;
 >>
 EOF
-    build_parser
+        end
-    compile("spec/test_basic_math_grammar.d")
+        build_parser(language: language)
+        compile("spec/test_basic_math_grammar.#{language}", language: language)
         results = run
         expect(results.stderr).to eq ""
         expect(results.status).to eq 0
@@ -193,7 +314,7 @@ Start -> E;
 E -> one E;
 E -> one;
 EOF
-    build_parser
+        build_parser(language: language)
       end
 
       it "distinguishes between multiple identical rules with lookahead symbol" do
@@ -205,8 +326,8 @@ Start -> R2 b;
 R1 -> a b;
 R2 -> a b;
 EOF
-    build_parser
+        build_parser(language: language)
-    compile("spec/test_parser_identical_rules_lookahead.d")
+        compile("spec/test_parser_identical_rules_lookahead.#{language}", language: language)
         results = run
         expect(results.status).to eq 0
       end
@@ -220,13 +341,28 @@ Start -> a R1;
 Start -> b R1;
 R1 -> b;
 EOF
-    build_parser
+        build_parser(language: language)
-    compile("spec/test_parser_rule_from_multiple_states.d")
+        compile("spec/test_parser_rule_from_multiple_states.#{language}", language: language)
         results = run
         expect(results.status).to eq 0
       end
 
       it "executes user code when matching lexer token" do
+        case language
+        when "c"
+          write_grammar <<EOF
+<<
+#include <stdio.h>
+>>
+token abc <<
+  printf("abc!\\n");
+>>
+token def;
+Start -> Abcs def;
+Abcs -> ;
+Abcs -> abc Abcs;
+EOF
+        when "d"
           write_grammar <<EOF
 <<
 import std.stdio;
@@ -239,8 +375,9 @@ Start -> Abcs def;
 Abcs -> ;
 Abcs -> abc Abcs;
 EOF
-    build_parser
+        end
-    compile("spec/test_user_code.d")
+        build_parser(language: language)
+        compile("spec/test_user_code.#{language}", language: language)
         results = run
         expect(results.status).to eq 0
         verify_lines(results.stdout, [
@@ -253,6 +390,19 @@ EOF
       end
 
       it "supports a pattern statement" do
+        case language
+        when "c"
+          write_grammar <<EOF
+<<
+#include <stdio.h>
+>>
+token abc;
+/def/ <<
+  printf("def!\\n");
+>>
+Start -> abc;
+EOF
+        when "d"
           write_grammar <<EOF
 <<
 import std.stdio;
@@ -263,8 +413,9 @@ token abc;
 >>
 Start -> abc;
 EOF
-    build_parser
+        end
-    compile("spec/test_pattern.d")
+        build_parser(language: language)
+        compile("spec/test_pattern.#{language}", language: language)
         results = run
         expect(results.status).to eq 0
         verify_lines(results.stdout, [
@@ -277,6 +428,23 @@ EOF
       end
 
       it "supports returning tokens from pattern code blocks" do
+        case language
+        when "c"
+          write_grammar <<EOF
+<<
+#include <stdio.h>
+>>
+token abc;
+/def/ <<
+  printf("def!\\n");
+>>
+/ghi/ <<
+  printf("ghi!\\n");
+  return $token(abc);
+>>
+Start -> abc;
+EOF
+        when "d"
           write_grammar <<EOF
 <<
 import std.stdio;
@@ -291,8 +459,9 @@ token abc;
 >>
 Start -> abc;
 EOF
-    build_parser
+        end
-    compile("spec/test_return_token_from_pattern.d")
+        build_parser(language: language)
+        compile("spec/test_return_token_from_pattern.#{language}", language: language)
         results = run
         expect(results.status).to eq 0
         verify_lines(results.stdout, [
@@ -303,6 +472,30 @@ EOF
       end
 
       it "supports lexer modes" do
+        case language
+        when "c"
+          write_grammar <<EOF
+<<
+#include <stdio.h>
+>>
+token abc;
+token def;
+tokenid string;
+drop /\\s+/;
+/"/ <<
+  printf("begin string mode\\n");
+  $mode(string);
+>>
+string: /[^"]+/ <<
+  printf("captured string\\n");
+>>
+string: /"/ <<
+  $mode(default);
+  return $token(string);
+>>
+Start -> abc string def;
+EOF
+        when "d"
           write_grammar <<EOF
 <<
 import std.stdio;
@@ -324,8 +517,9 @@ string: /"/ <<
 >>
 Start -> abc string def;
 EOF
-    build_parser
+        end
-    compile("spec/test_lexer_modes.d")
+        build_parser(language: language)
+        compile("spec/test_lexer_modes.#{language}", language: language)
         results = run
         expect(results.status).to eq 0
         verify_lines(results.stdout, [
@@ -339,6 +533,25 @@ EOF
       end
 
       it "executes user code associated with a parser rule" do
+        case language
+        when "c"
+          write_grammar <<EOF
+<<
+#include <stdio.h>
+>>
+token a;
+token b;
+Start -> A B <<
+  printf("Start!\\n");
+>>
+A -> a <<
+  printf("A!\\n");
+>>
+B -> b <<
+  printf("B!\\n");
+>>
+EOF
+        when "d"
           write_grammar <<EOF
 <<
 import std.stdio;
@@ -355,8 +568,9 @@ B -> b <<
   writeln("B!");
 >>
 EOF
-    build_parser
+        end
-    compile("spec/test_parser_rule_user_code.d")
+        build_parser(language: language)
+        compile("spec/test_parser_rule_user_code.#{language}", language: language)
         results = run
         expect(results.status).to eq 0
         verify_lines(results.stdout, [
@@ -368,7 +582,7 @@ EOF
 
       it "parses lists" do
         write_grammar <<EOF
-ptype uint;
+ptype #{language == "c" ? "uint32_t" : "uint"};
 token a;
 Start -> As <<
   $$ = $1;
@@ -380,8 +594,8 @@ As -> As a <<
   $$ = $1 + 1u;
 >>
 EOF
-    build_parser
+        build_parser(language: language)
-    compile("spec/test_parsing_lists.d")
+        compile("spec/test_parsing_lists.#{language}", language: language)
         results = run
         expect(results.status).to eq 0
         expect(results.stderr).to eq ""
@@ -401,12 +615,28 @@ Start -> b E d;
 E -> e;
 F -> e;
 EOF
-    results = build_parser(capture: true)
+        results = build_parser(capture: true, language: language)
         expect(results.status).to_not eq 0
         expect(results.stderr).to match %r{reduce/reduce conflict.*\(E\).*\(F\)}
       end
 
       it "provides matched text to user code blocks" do
+        case language
+        when "c"
+          write_grammar <<EOF
+<<
+#include <stdio.h>
+#include <stdlib.h>
+>>
+token id /[a-zA-Z_][a-zA-Z0-9_]*/ <<
+  char * t = malloc(match_length + 1);
+  strncpy(t, (char *)match, match_length);
+  printf("Matched token is %s\\n", t);
+  free(t);
+>>
+Start -> id;
+EOF
+        when "d"
           write_grammar <<EOF
 <<
 import std.stdio;
@@ -416,8 +646,9 @@ token id /[a-zA-Z_][a-zA-Z0-9_]*/ <<
 >>
 Start -> id;
 EOF
-    build_parser
+        end
-    compile("spec/test_lexer_match_text.d")
+        build_parser(language: language)
+        compile("spec/test_lexer_match_text.#{language}", language: language)
         results = run
         expect(results.status).to eq 0
         verify_lines(results.stdout, [
@@ -427,6 +658,18 @@ EOF
       end
 
       it "allows storing a result value for the lexer" do
+        case language
+        when "c"
+          write_grammar <<EOF
+ptype uint64_t;
+token word /[a-z]+/ <<
+  $$ = match_length;
+>>
+Start -> word <<
+  $$ = $1;
+>>
+EOF
+        when "d"
           write_grammar <<EOF
 ptype ulong;
 token word /[a-z]+/ <<
@@ -436,8 +679,9 @@ Start -> word <<
   $$ = $1;
 >>
 EOF
-    build_parser
+        end
-    compile("spec/test_lexer_result_value.d")
+        build_parser(language: language)
+        compile("spec/test_lexer_result_value.#{language}", language: language)
         results = run
         expect(results.stderr).to eq ""
         expect(results.status).to eq 0
@@ -451,17 +695,17 @@ drop /\\s+/;
 Start -> a num Start;
 Start -> a num;
 EOF
-    build_parser
+        build_parser(language: language)
-    compile("spec/test_error_positions.d")
+        compile("spec/test_error_positions.#{language}", language: language)
         results = run
         expect(results.stderr).to eq ""
         expect(results.status).to eq 0
       end
 
       it "allows creating a JSON parser" do
-    write_grammar(File.read("spec/json_parser.propane"))
+        write_grammar(File.read("spec/json_parser.#{language}.propane"))
-    build_parser
+        build_parser(language: language)
-    compile(["spec/test_parsing_json.d", "spec/json_types.d"])
+        compile(["spec/test_parsing_json.#{language}", "spec/json_types.#{language}"], language: language)
       end
 
       it "allows generating multiple parsers in the same program" do
@@ -472,17 +716,39 @@ token num /\\d+/;
 drop /\\s+/;
 Start -> a num;
 EOF
-    build_parser(name: "myp1")
+        build_parser(name: "myp1", language: language)
         write_grammar(<<EOF, name: "myp2")
 prefix myp2_;
 token b;
 token c;
 Start -> b c b;
 EOF
-    build_parser(name: "myp2")
+        build_parser(name: "myp2", language: language)
-    compile("spec/test_multiple_parsers.d", parsers: %w[myp1 myp2])
+        compile("spec/test_multiple_parsers.#{language}", parsers: %w[myp1 myp2], language: language)
         results = run
         expect(results.stderr).to eq ""
         expect(results.status).to eq 0
       end
+
+      it "allows the user to terminate the parser" do
+        write_grammar <<EOF
+token a;
+token b;
+token c;
+Start -> Any;
+Any -> a Any;
+Any -> b Any <<
+  $terminate(4200);
+>>
+Any -> c Any;
+Any -> ;
+EOF
+        build_parser(language: language)
+        compile("spec/test_user_terminate.#{language}", language: language)
+        results = run
+        expect(results.stderr).to eq ""
+        expect(results.status).to eq 0
+      end
+    end
+  end
 end

spec/spec_helper.rb

@@ -1,11 +1,27 @@
-require "bundler/setup"
+unless ENV["dist_specs"]
-require "propane"
+  require "bundler/setup"
+  require "simplecov"
 
-RSpec.configure do |config|
+  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
+
+  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_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_error_positions.c

@@ -0,0 +1,39 @@
+#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(context.token == 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(context.token == 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);
+
+    return 0;
+}

spec/test_error_positions.d

@@ -33,6 +33,5 @@ unittest
     input = "a 12\n\na\n\n77\na   \xAA";
     p_context_init(&context, input);
     assert(p_parse(&context) == P_DECODE_ERROR);
-    writeln(p_position(&context));
     assert(p_position(&context) == p_position_t(5, 4));
 }

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_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_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_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_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_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_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_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_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_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_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_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_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_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_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/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.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;
+}