sooth 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 35b7050c2c66e43c65ee1afc05bb4534267d01e3
+  data.tar.gz: 79302a0867744f4cd86d4090adcc3b1c792f22c5
+SHA512:
+  metadata.gz: ae6731afecca1a16085d65601c7f01ff8157d9e5a2d2f9fff987b6bd74dec00efd1de9a8f51402327669101e6646dee2d9971e6b267240453247d2443efae39b
+  data.tar.gz: 44b75b169a0c4ffed66eb873d92c93f6ddb305dc037c6dc14e8411d39d50f1ee3bd8a0f16723cadbcd14d5cea2041bb403d5613003bd9ab7cfe573a8322d085b

data/Gemfile

@@ -0,0 +1,12 @@
+source 'https://rubygems.org'
+
+group :development do
+  gem 'rspec', '~> 3.1'
+  gem 'yard', '~> 0.8'
+  gem 'rdoc', '~> 4.1'
+  gem 'bundler', '~> 1.7'
+  gem 'jeweler', '~> 2.0'
+  gem 'simplecov', '~> 0.9'
+  gem 'byebug', '~> 3.5'
+  gem 'rake-compiler', '~> 0.9'
+end

data/Gemfile.lock

@@ -0,0 +1,90 @@
+GEM
+  remote: https://rubygems.org/
+  specs:
+    addressable (2.3.6)
+    builder (3.2.2)
+    byebug (3.5.1)
+      columnize (~> 0.8)
+      debugger-linecache (~> 1.2)
+      slop (~> 3.6)
+    columnize (0.9.0)
+    debugger-linecache (1.2.0)
+    descendants_tracker (0.0.4)
+      thread_safe (~> 0.3, >= 0.3.1)
+    diff-lcs (1.2.5)
+    docile (1.1.5)
+    faraday (0.9.0)
+      multipart-post (>= 1.2, < 3)
+    git (1.2.8)
+    github_api (0.12.2)
+      addressable (~> 2.3)
+      descendants_tracker (~> 0.0.4)
+      faraday (~> 0.8, < 0.10)
+      hashie (>= 3.3)
+      multi_json (>= 1.7.5, < 2.0)
+      nokogiri (~> 1.6.3)
+      oauth2
+    hashie (3.3.2)
+    highline (1.6.21)
+    jeweler (2.0.1)
+      builder
+      bundler (>= 1.0)
+      git (>= 1.2.5)
+      github_api
+      highline (>= 1.6.15)
+      nokogiri (>= 1.5.10)
+      rake
+      rdoc
+    json (1.8.1)
+    jwt (1.2.0)
+    mini_portile (0.6.1)
+    multi_json (1.10.1)
+    multi_xml (0.5.5)
+    multipart-post (2.0.0)
+    nokogiri (1.6.5)
+      mini_portile (~> 0.6.0)
+    oauth2 (1.0.0)
+      faraday (>= 0.8, < 0.10)
+      jwt (~> 1.0)
+      multi_json (~> 1.3)
+      multi_xml (~> 0.5)
+      rack (~> 1.2)
+    rack (1.5.2)
+    rake (10.4.2)
+    rake-compiler (0.9.3)
+      rake
+    rdoc (4.2.0)
+      json (~> 1.4)
+    rspec (3.1.0)
+      rspec-core (~> 3.1.0)
+      rspec-expectations (~> 3.1.0)
+      rspec-mocks (~> 3.1.0)
+    rspec-core (3.1.7)
+      rspec-support (~> 3.1.0)
+    rspec-expectations (3.1.2)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.1.0)
+    rspec-mocks (3.1.3)
+      rspec-support (~> 3.1.0)
+    rspec-support (3.1.2)
+    simplecov (0.9.1)
+      docile (~> 1.1.0)
+      multi_json (~> 1.0)
+      simplecov-html (~> 0.8.0)
+    simplecov-html (0.8.0)
+    slop (3.6.0)
+    thread_safe (0.3.4)
+    yard (0.8.7.6)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  bundler (~> 1.7)
+  byebug (~> 3.5)
+  jeweler (~> 2.0)
+  rake-compiler (~> 0.9)
+  rdoc (~> 4.1)
+  rspec (~> 3.1)
+  simplecov (~> 0.9)
+  yard (~> 0.8)

data/README.md

@@ -0,0 +1,28 @@
+[![Gem Version](https://badge.fury.io/rb/sooth.svg)](http://badge.fury.io/rb/sooth)
+[![Dependency Status](https://gemnasium.com/jasonhutchens/sooth.png)](https://gemnasium.com/jasonhutchens/sooth)
+[![Build Status](https://secure.travis-ci.org/jasonhutchens/sooth.png)](http://travis-ci.org/#!/jasonhutchens/sooth)
+[![Code Climate](https://codeclimate.com/github/jasonhutchens/sooth.png)](https://codeclimate.com/github/jasonhutchens/sooth)
+
+Sooth
+=====
+
+Sooth is a simple stochastic predictive model.
+
+Getting Started
+---------------
+
+Apart from the specs, look at the [API docs](http://rubydoc.info/github/jasonhutchens/sooth/master/frames) to get up to speed.
+
+Next
+----
+
+* Implement save and load (with specs)
+* Version 0.9
+* Hook up to all services
+* Version 1
+* MegaHAL that uses it
+
+Copyright
+---------
+
+Copyright (c) 2014 Jason Hutchens. See UNLICENSE for further details.

data/Rakefile

@@ -0,0 +1,47 @@
+# encoding: utf-8
+
+require 'rubygems'
+require 'bundler'
+begin
+  Bundler.setup(:default, :development)
+rescue Bundler::BundlerError => e
+  $stderr.puts e.message
+  $stderr.puts "Run `bundle install` to install missing gems"
+  exit e.status_code
+end
+require 'rake'
+
+require 'jeweler'
+Jeweler::Tasks.new do |gem|
+  # gem is a Gem::Specification... see http://guides.rubygems.org/specification-reference/ for more options
+  gem.name = "sooth"
+  gem.homepage = "http://github.com/jasonhutchens/sooth"
+  gem.license = "MIT"
+  gem.summary = %Q{A small thing for generating codes for users to type into places}
+  gem.description = %Q{Does what it says on the box}
+  gem.email = "jasonhutchens@gmail.com"
+  gem.authors = ["Jason Hutchens"]
+  gem.required_ruby_version = "~> 2.1"
+  # dependencies defined in Gemfile
+end
+Jeweler::RubygemsDotOrgTasks.new
+
+require 'rake/extensiontask'
+Rake::ExtensionTask.new('sooth_native')
+
+require 'rspec/core'
+require 'rspec/core/rake_task'
+RSpec::Core::RakeTask.new(:spec) do |spec|
+  spec.pattern = FileList['spec/**/*_spec.rb']
+end
+
+desc "Code coverage detail"
+task :simplecov do
+  ENV['COVERAGE'] = "true"
+  Rake::Task['spec'].execute
+end
+
+task :default => :spec
+
+require 'yard'
+YARD::Rake::YardocTask.new

data/UNLICENSE

@@ -0,0 +1,24 @@
+This is free and unencumbered software released into the public domain.
+
+Anyone is free to copy, modify, publish, use, compile, sell, or
+distribute this software, either in source code form or as a compiled
+binary, for any purpose, commercial or non-commercial, and by any
+means.
+
+In jurisdictions that recognize copyright laws, the author or authors
+of this software dedicate any and all copyright interest in the
+software to the public domain. We make this dedication for the benefit
+of the public at large and to the detriment of our heirs and
+successors. We intend this dedication to be an overt act of
+relinquishment in perpetuity of all present and future rights to this
+software under copyright law.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+OTHER DEALINGS IN THE SOFTWARE.
+
+For more information, please refer to <http://unlicense.org/>

data/VERSION

@@ -0,0 +1 @@
+0.1.0

data/ext/sooth_native/extconf.rb

@@ -0,0 +1,2 @@
+require 'mkmf'
+create_makefile('sooth_native')

data/ext/sooth_native/native.c

@@ -0,0 +1,190 @@
+//==============================================================================
+
+#include <ruby.h>
+
+#include "sooth_predictor.h"
+
+//------------------------------------------------------------------------------
+
+VALUE Sooth = Qnil;
+VALUE SoothNative = Qnil;
+
+VALUE method_sooth_native_allocate(VALUE klass);
+void method_sooth_native_deallocate(void * predictor);
+
+/* @!parse [ruby]
+ *   module Sooth
+ *     # A very simple stochastic predictor. Implemented in C for efficiency.
+ *     # The idea here is to build up more complicated learning algorithms using
+ *     # a trivial Markovian predictor.
+ *     class Predictor
+ *       def initialize(error_symbol)
+ *       end
+ *       def observe(bigram, symbol)
+ *         # (native code)
+ *       end
+ *       def count(bigram)
+ *         # (native code)
+ *       end
+ *       def select(bigram, limit)
+ *         # (native code)
+ *       end
+ *     end
+ *   end
+ *
+ * Returns a new Sooth::Predictor instance.
+ *
+ * @param [Fixnum] error_symbol The symbol to be returned by #select when no
+ *                              prediction can be made.
+ */
+VALUE method_sooth_native_initialize(VALUE self, VALUE error_symbol);
+
+/*
+ * Add an observation of the given symbol in the context of the bigram.
+ *
+ * @param [Array] bigram A pair of symbols that provide context, allowing the
+ *                       predictor to maintain observation statistics for
+ *                       different contexts.
+ * @param [Fixnum] symbol The symbol that has been observed.
+ * @return [Fixnum] A count of the number of times the symbol has been
+ *                  observed in the context of the bigram.
+ */
+VALUE method_sooth_native_observe(VALUE self, VALUE bigram, VALUE symbol);
+
+/*
+ * Return a count of the number of times the bigram has been observed.
+ *
+ * @param [Array] bigram A pair of symbols.
+ * @return [Fixnum] A count of the number of times the bigram has been
+ *                  observed. This is guaranteed to be equal to the sum
+ *                  of the counts of observations of all symbols in the
+ *                  context of the bigram.
+ */
+VALUE method_sooth_native_count(VALUE self, VALUE bigram);
+
+/*
+ * Return a symbol that may occur in the context of the bigram. The
+ * limit is used to select a symbol. This is done by iterating through
+ * all of the symbols that have been observed in the context of the
+ * bigram, subtracting the observation count of each symbol from the
+ * supplied limit. For this reason, limit should be between 1 and the
+ * observation count of the bigram itself, as returned by #count.
+ *
+ * @param [Array] bigram A pair of symbols.
+ * @param [Fixnum] limit The total numbe of symbol observations to be
+ *                       analysed before returning a symbol.
+ * @return [Fixnum] A symbol that has been observed previously in the
+ *                  context of the bigram, or the error_symbol if no
+ *                  such symbol exists, or if the supplied limit was
+ *                  too large.
+ */
+VALUE method_sooth_native_select(VALUE self, VALUE bigram, VALUE limit);
+
+//------------------------------------------------------------------------------
+
+void Init_sooth_native()
+{
+  Sooth = rb_define_module("Sooth");
+  SoothNative = rb_define_class_under(Sooth, "Predictor", rb_cObject);
+
+  rb_define_alloc_func(SoothNative, method_sooth_native_allocate);
+  rb_define_method(SoothNative, "initialize", method_sooth_native_initialize, 1);
+
+  rb_define_method(SoothNative, "observe", method_sooth_native_observe, 2);
+  rb_define_method(SoothNative, "count", method_sooth_native_count, 1);
+  rb_define_method(SoothNative, "select", method_sooth_native_select, 2);
+}
+
+//------------------------------------------------------------------------------
+
+VALUE
+method_sooth_native_allocate(VALUE klass)
+{
+  SoothPredictor * predictor = sooth_predictor_init();
+  if (predictor == NULL)
+  {
+    return Qnil;
+  }
+  return Data_Wrap_Struct(klass, NULL, method_sooth_native_deallocate, predictor);
+}
+
+//------------------------------------------------------------------------------
+
+void
+method_sooth_native_deallocate(void * predictor)
+{
+  sooth_predictor_free((SoothPredictor *)predictor);
+}
+
+//------------------------------------------------------------------------------
+
+VALUE
+method_sooth_native_initialize(VALUE self, VALUE error_symbol)
+{
+  SoothPredictor * predictor = NULL;
+  Check_Type(error_symbol, T_FIXNUM);
+  Data_Get_Struct(self, SoothPredictor, predictor);
+  predictor->error_symbol = NUM2UINT(error_symbol);
+  return self;
+}
+
+//------------------------------------------------------------------------------
+
+VALUE
+method_sooth_native_observe(VALUE self, VALUE bigram, VALUE symbol)
+{
+  SoothPredictor * predictor = NULL;
+  Check_Type(symbol, T_FIXNUM);
+  Check_Type(bigram, T_ARRAY);
+  if (RARRAY_LEN(bigram) != 2)
+  {
+    rb_raise(rb_eTypeError, "bigram must be an array of exactly two symbols");
+  }
+  Check_Type(RARRAY_PTR(bigram)[0], T_FIXNUM);
+  Check_Type(RARRAY_PTR(bigram)[1], T_FIXNUM);
+  Data_Get_Struct(self, SoothPredictor, predictor);
+  uint32_t c_bigram[2] = {NUM2UINT(RARRAY_PTR(bigram)[0]), NUM2UINT(RARRAY_PTR(bigram)[1])};
+  uint32_t count = sooth_predictor_observe(predictor, c_bigram, NUM2UINT(symbol));
+  return UINT2NUM(count);
+}
+
+//------------------------------------------------------------------------------
+
+VALUE
+method_sooth_native_count(VALUE self, VALUE bigram)
+{
+  SoothPredictor * predictor = NULL;
+  Check_Type(bigram, T_ARRAY);
+  if (RARRAY_LEN(bigram) != 2)
+  {
+    rb_raise(rb_eTypeError, "bigram must be an array of exactly two symbols");
+  }
+  Check_Type(RARRAY_PTR(bigram)[0], T_FIXNUM);
+  Check_Type(RARRAY_PTR(bigram)[1], T_FIXNUM);
+  Data_Get_Struct(self, SoothPredictor, predictor);
+  uint32_t c_bigram[2] = {NUM2UINT(RARRAY_PTR(bigram)[0]), NUM2UINT(RARRAY_PTR(bigram)[1])};
+  uint64_t count = sooth_predictor_count(predictor, c_bigram);
+  return UINT2NUM(count);
+}
+
+//------------------------------------------------------------------------------
+
+VALUE
+method_sooth_native_select(VALUE self, VALUE bigram, VALUE limit)
+{
+  SoothPredictor * predictor = NULL;
+  Check_Type(limit, T_FIXNUM);
+  Check_Type(bigram, T_ARRAY);
+  if (RARRAY_LEN(bigram) != 2)
+  {
+    rb_raise(rb_eTypeError, "bigram must be an array of exactly two symbols");
+  }
+  Check_Type(RARRAY_PTR(bigram)[0], T_FIXNUM);
+  Check_Type(RARRAY_PTR(bigram)[1], T_FIXNUM);
+  Data_Get_Struct(self, SoothPredictor, predictor);
+  uint32_t c_bigram[2] = {NUM2UINT(RARRAY_PTR(bigram)[0]), NUM2UINT(RARRAY_PTR(bigram)[1])};
+  uint32_t symbol = sooth_predictor_select(predictor, c_bigram, NUM2UINT(limit));
+  return UINT2NUM(symbol);
+}
+
+//==============================================================================

data/ext/sooth_native/sooth_context.h

@@ -0,0 +1,21 @@
+#ifndef SOOTH_CONTEXT_H
+#define SOOTH_CONTEXT_H
+
+//==============================================================================
+
+#include <stdint.h>
+
+typedef struct
+{
+  uint32_t bigram[2];
+  uint64_t count;
+  uint32_t statistics_size;
+  uint64_t statistics_offset;
+}
+SoothContext;
+
+//------------------------------------------------------------------------------
+
+//==============================================================================
+
+#endif

data/ext/sooth_native/sooth_predictor.c

@@ -0,0 +1,257 @@
+//==============================================================================
+
+#include <stdlib.h>
+#include <string.h>
+
+#include "sooth_predictor.h"
+
+//------------------------------------------------------------------------------
+
+SoothPredictor *
+sooth_predictor_init()
+{
+  SoothPredictor * predictor = malloc(sizeof(SoothPredictor));
+
+  if (predictor == NULL)
+  {
+    return NULL;
+  }
+
+  predictor->error_symbol = 0;
+
+  predictor->contexts = NULL;
+  predictor->contexts_size = 0;
+
+  predictor->statistics = NULL;
+  predictor->statistics_size = 0;
+
+  return predictor;
+}
+
+//------------------------------------------------------------------------------
+
+void
+sooth_predictor_free(SoothPredictor * predictor)
+{
+  free(predictor->contexts);
+  free(predictor->statistics);
+
+  predictor->contexts = NULL;
+  predictor->contexts_size = 0;
+
+  predictor->statistics = NULL;
+  predictor->statistics_size = 0;
+
+  free(predictor);
+}
+
+//------------------------------------------------------------------------------
+
+void
+sooth_predictor_save(const char * const filename, SoothPredictor * predictor)
+{
+}
+
+//------------------------------------------------------------------------------
+
+SoothPredictor *
+sooth_predictor_load(const char * const filename)
+{
+  return NULL;
+}
+
+//------------------------------------------------------------------------------
+SoothContext *
+sooth_predictor_find_context(SoothPredictor * predictor, uint32_t bigram[2])
+{
+  SoothContext * context = NULL;
+  uint64_t mid = 0;
+
+  if (predictor->contexts_size > 0)
+  {
+    uint64_t low = 0;
+    uint64_t high = predictor->contexts_size - 1;
+
+    while (low <= high)
+    {
+      mid = low + (high - low) / 2;
+      context = &(predictor->contexts[mid]);
+      if (context->bigram[0] < bigram[0] || context->bigram[0] == bigram[0] && context->bigram[1] < bigram[1])
+      {
+        low = mid + 1;
+      }
+      else if (context->bigram[0] > bigram[0] || context->bigram[0] == bigram[0] && context->bigram[1] > bigram[1])
+      {
+        if (mid == 0)
+        {
+          break;
+        }
+        high = mid - 1;
+      }
+      else
+      {
+        return context;
+      }
+    }
+
+    mid = low;
+  }
+
+  predictor->contexts_size += 1;
+  SoothContext * new_memory = realloc(predictor->contexts, sizeof(SoothContext) * predictor->contexts_size);
+  if (new_memory == NULL)
+  {
+    return NULL;
+  }
+  predictor->contexts = new_memory;
+
+  if ((mid + 1) < predictor->contexts_size)
+  {
+    SoothContext * src = &(predictor->contexts[mid]);
+    SoothContext * dest = &(predictor->contexts[mid+1]);
+    (void)memmove(dest, src, sizeof(SoothContext) * (predictor->contexts_size - mid - 1)); 
+  }
+
+  context = &(predictor->contexts[mid]);
+  context->bigram[0] = bigram[0];
+  context->bigram[1] = bigram[1];
+  context->count = 0;
+  context->statistics_size = 0;
+
+  return context;
+}
+
+//------------------------------------------------------------------------------
+
+SoothStatistic *
+sooth_predictor_find_statistic(SoothPredictor * predictor, SoothContext * context, uint32_t symbol)
+{
+  SoothStatistic * statistic = NULL;
+  uint64_t mid = 0;
+
+  if (context->statistics_size > 0)
+  {
+    uint64_t low = 0;
+    uint64_t high = context->statistics_size - 1;
+
+    while (low <= high)
+    {
+      mid = low + (high - low) / 2;
+      statistic = &(predictor->statistics[mid + context->statistics_offset]);
+      if (statistic->symbol < symbol)
+      {
+        low = mid + 1;
+      }
+      else if (statistic->symbol > symbol)
+      {
+        if (mid == 0)
+        {
+          break;
+        }
+        high = mid - 1;
+      }
+      else
+      {
+        return statistic;
+      }
+    }
+
+    mid = low;
+  }
+
+  if (context->statistics_size == 0)
+  {
+    context->statistics_offset = predictor->statistics_size;
+  }
+  context->statistics_size += 1;
+  mid += context -> statistics_offset;
+
+  predictor->statistics_size += 1;
+  SoothStatistic * new_memory = realloc(predictor->statistics, sizeof(SoothStatistic) * predictor->statistics_size);
+  if (new_memory == NULL)
+  {
+    return NULL;
+  }
+  predictor->statistics = new_memory;
+
+  if ((mid + 1) < predictor->statistics_size)
+  {
+    SoothStatistic * src = &(predictor->statistics[mid]);
+    SoothStatistic * dest = &(predictor->statistics[mid+1]);
+    (void)memmove(dest, src, sizeof(SoothStatistic) * (predictor->statistics_size - mid - 1)); 
+  }
+
+  statistic = &(predictor->statistics[mid]);
+  statistic->symbol = symbol;
+  statistic->count = 0;
+
+  return statistic;
+}
+
+//------------------------------------------------------------------------------
+
+uint32_t
+sooth_predictor_observe(SoothPredictor * predictor, uint32_t bigram[2], uint32_t symbol)
+{
+  SoothContext * context = sooth_predictor_find_context(predictor, bigram);
+
+  if (context == NULL)
+  {
+    return 0;
+  }
+
+  SoothStatistic * statistic = sooth_predictor_find_statistic(predictor, context, symbol);
+
+  if (statistic == NULL)
+  {
+    return 0;
+  }
+
+  statistic->count += 1;
+  context->count += 1;
+
+  return statistic->count;
+}
+
+//------------------------------------------------------------------------------
+
+uint64_t
+sooth_predictor_count(SoothPredictor * predictor, uint32_t bigram[2])
+{
+  SoothContext * context = sooth_predictor_find_context(predictor, bigram);
+  
+  if (context == NULL)
+  {
+    return 0;
+  }
+
+  return context->count;
+}
+
+//------------------------------------------------------------------------------
+
+uint32_t
+sooth_predictor_select(SoothPredictor * predictor, uint32_t bigram[2], uint64_t limit)
+{
+  SoothContext * context = sooth_predictor_find_context(predictor, bigram);
+
+  if (context == NULL || limit == 0)
+  {
+    return predictor->error_symbol;
+  }
+
+  for (uint64_t i = 0; i < context->statistics_size; ++i)
+  {
+    SoothStatistic statistic = predictor->statistics[context->statistics_offset + i];
+    if (limit > statistic.count)
+    {
+      limit -= statistic.count;
+      continue;
+    }
+    return statistic.symbol;
+  }
+
+  return predictor->error_symbol;
+}
+
+//==============================================================================

data/ext/sooth_native/sooth_predictor.h

@@ -0,0 +1,33 @@
+#ifndef SOOTH_PREDICTOR_H
+#define SOOTH_PREDICTOR_H
+
+//==============================================================================
+
+#include <stdint.h>
+
+#include "sooth_context.h"
+#include "sooth_statistic.h"
+
+typedef struct
+{
+  uint32_t error_symbol;
+  uint64_t contexts_size;
+  SoothContext * contexts;
+  uint64_t statistics_size;
+  SoothStatistic * statistics;
+}
+SoothPredictor;
+
+//------------------------------------------------------------------------------
+
+SoothPredictor * sooth_predictor_init();
+void sooth_predictor_free(SoothPredictor * predictor);
+void sooth_predictor_save(const char * const filename, SoothPredictor * predictor);
+SoothPredictor * sooth_predictor_load(const char * const filename);
+uint32_t sooth_predictor_observe(SoothPredictor * predictor, uint32_t bigram[2], uint32_t symbol);
+uint64_t sooth_predictor_count(SoothPredictor * predictor, uint32_t bigram[2]);
+uint32_t sooth_predictor_select(SoothPredictor * predictor, uint32_t bigram[2], uint64_t limit);
+
+//==============================================================================
+
+#endif

data/ext/sooth_native/sooth_statistic.h

@@ -0,0 +1,19 @@
+#ifndef SOOTH_STATISTIC_H
+#define SOOTH_STATISTIC_H
+
+//==============================================================================
+
+#include <stdint.h>
+
+typedef struct
+{
+  uint32_t symbol;
+  uint32_t count;
+}
+SoothStatistic;
+
+//------------------------------------------------------------------------------
+
+//==============================================================================
+
+#endif

data/lib/sooth.rb

@@ -0,0 +1 @@
+require 'sooth_native'

data/sooth.gemspec

@@ -0,0 +1,80 @@
+# Generated by jeweler
+# DO NOT EDIT THIS FILE DIRECTLY
+# Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
+# -*- encoding: utf-8 -*-
+# stub: sooth 0.1.0 ruby lib
+# stub: ext/sooth_native/extconf.rb
+
+Gem::Specification.new do |s|
+  s.name = "sooth"
+  s.version = "0.1.0"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.require_paths = ["lib"]
+  s.authors = ["Jason Hutchens"]
+  s.date = "2014-12-10"
+  s.description = "Does what it says on the box"
+  s.email = "jasonhutchens@gmail.com"
+  s.extensions = ["ext/sooth_native/extconf.rb"]
+  s.extra_rdoc_files = [
+    "README.md"
+  ]
+  s.files = [
+    "Gemfile",
+    "Gemfile.lock",
+    "README.md",
+    "Rakefile",
+    "UNLICENSE",
+    "VERSION",
+    "ext/sooth_native/extconf.rb",
+    "ext/sooth_native/native.c",
+    "ext/sooth_native/sooth_context.h",
+    "ext/sooth_native/sooth_predictor.c",
+    "ext/sooth_native/sooth_predictor.h",
+    "ext/sooth_native/sooth_statistic.h",
+    "lib/sooth.rb",
+    "sooth.gemspec",
+    "spec/memory_spec.rb",
+    "spec/predictor_spec.rb",
+    "spec/spec_helper.rb"
+  ]
+  s.homepage = "http://github.com/jasonhutchens/sooth"
+  s.licenses = ["MIT"]
+  s.required_ruby_version = Gem::Requirement.new("~> 2.1")
+  s.rubygems_version = "2.4.4"
+  s.summary = "A small thing for generating codes for users to type into places"
+
+  if s.respond_to? :specification_version then
+    s.specification_version = 4
+
+    if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
+      s.add_development_dependency(%q<rspec>, ["~> 3.1"])
+      s.add_development_dependency(%q<yard>, ["~> 0.8"])
+      s.add_development_dependency(%q<rdoc>, ["~> 4.1"])
+      s.add_development_dependency(%q<bundler>, ["~> 1.7"])
+      s.add_development_dependency(%q<jeweler>, ["~> 2.0"])
+      s.add_development_dependency(%q<simplecov>, ["~> 0.9"])
+      s.add_development_dependency(%q<byebug>, ["~> 3.5"])
+      s.add_development_dependency(%q<rake-compiler>, ["~> 0.9"])
+    else
+      s.add_dependency(%q<rspec>, ["~> 3.1"])
+      s.add_dependency(%q<yard>, ["~> 0.8"])
+      s.add_dependency(%q<rdoc>, ["~> 4.1"])
+      s.add_dependency(%q<bundler>, ["~> 1.7"])
+      s.add_dependency(%q<jeweler>, ["~> 2.0"])
+      s.add_dependency(%q<simplecov>, ["~> 0.9"])
+      s.add_dependency(%q<byebug>, ["~> 3.5"])
+      s.add_dependency(%q<rake-compiler>, ["~> 0.9"])
+    end
+  else
+    s.add_dependency(%q<rspec>, ["~> 3.1"])
+    s.add_dependency(%q<yard>, ["~> 0.8"])
+    s.add_dependency(%q<rdoc>, ["~> 4.1"])
+    s.add_dependency(%q<bundler>, ["~> 1.7"])
+    s.add_dependency(%q<jeweler>, ["~> 2.0"])
+    s.add_dependency(%q<simplecov>, ["~> 0.9"])
+    s.add_dependency(%q<byebug>, ["~> 3.5"])
+    s.add_dependency(%q<rake-compiler>, ["~> 0.9"])
+  end
+end
+

data/spec/memory_spec.rb

@@ -0,0 +1,35 @@
+require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
+
+describe Sooth::Predictor do
+  let(:predictor) { Sooth::Predictor.new(42) }
+
+  describe "#observe" do
+    it "does not segfault when sorting bigrams" do
+      expect(predictor.observe([3,3], 1)).to eq(1)
+      expect(predictor.observe([5,5], 1)).to eq(1)
+      expect(predictor.observe([4,4], 1)).to eq(1)
+      expect(predictor.observe([5,5], 1)).to eq(2)
+      expect(predictor.observe([3,3], 1)).to eq(2)
+      expect(predictor.observe([4,4], 1)).to eq(2)
+      expect(predictor.observe([2,2], 1)).to eq(1)
+      expect(predictor.observe([4,4], 1)).to eq(3)
+      expect(predictor.observe([2,2], 1)).to eq(2)
+      expect(predictor.observe([3,3], 1)).to eq(3)
+      expect(predictor.observe([5,5], 1)).to eq(3)
+    end
+
+    it "does not segfault when sorting symbols" do
+      expect(predictor.observe([1,2], 3)).to eq(1)
+      expect(predictor.observe([1,2], 5)).to eq(1)
+      expect(predictor.observe([1,2], 4)).to eq(1)
+      expect(predictor.observe([1,2], 5)).to eq(2)
+      expect(predictor.observe([1,2], 3)).to eq(2)
+      expect(predictor.observe([1,2], 4)).to eq(2)
+      expect(predictor.observe([1,2], 2)).to eq(1)
+      expect(predictor.observe([1,2], 4)).to eq(3)
+      expect(predictor.observe([1,2], 2)).to eq(2)
+      expect(predictor.observe([1,2], 3)).to eq(3)
+      expect(predictor.observe([1,2], 5)).to eq(3)
+    end
+  end
+end

data/spec/predictor_spec.rb

@@ -0,0 +1,64 @@
+require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
+
+describe Sooth::Predictor do
+  let(:predictor) { Sooth::Predictor.new(42) }
+
+  describe "#observe" do
+    it "increments observation counts" do
+      expect(predictor.observe([1,2], 3)).to eq(1)
+      expect(predictor.observe([1,2], 3)).to eq(2)
+      expect(predictor.observe([1,2], 3)).to eq(3)
+    end
+
+    it "properly sorts and finds bigrams" do
+      expect(predictor.observe([2,1], 3)).to eq(1)
+      expect(predictor.observe([1,3], 2)).to eq(1)
+      expect(predictor.observe([3,2], 1)).to eq(1)
+      expect(predictor.observe([1,3], 2)).to eq(2)
+      expect(predictor.observe([2,1], 3)).to eq(2)
+      expect(predictor.observe([3,2], 1)).to eq(2)
+    end
+  end
+
+  describe "#count" do
+    it "returns a zero count for an unobserved bigram" do
+      expect(predictor.count([1,2])).to eq(0)
+    end
+
+    it "returns the total count for an observed bigram" do
+      predictor.observe([1,2], 2)
+      predictor.observe([1,2], 1)
+      predictor.observe([1,2], 4)
+      predictor.observe([1,2], 3)
+      predictor.observe([1,2], 0)
+      predictor.observe([1,2], 1)
+      predictor.observe([1,2], 4)
+      expect(predictor.count([1,2])).to eq(7)
+    end
+  end
+
+  describe "#select" do
+    it "returns the error symbol for an unobserved bigram" do
+      expect(predictor.select([1,2], 1)).to eq(42)
+    end
+
+    it "returns the correct symbol for an observed bigram" do
+      predictor.observe([1,2], 4)
+      predictor.observe([1,2], 3)
+      predictor.observe([1,2], 4)
+      predictor.observe([1,2], 5)
+      expect(predictor.select([1,2], 1)).to eq(3)
+      expect(predictor.select([1,2], 2)).to eq(4)
+      expect(predictor.select([1,2], 3)).to eq(4)
+      expect(predictor.select([1,2], 4)).to eq(5)
+    end
+
+    it "returns the error symbol for a limit that is out of range" do
+      predictor.observe([1,2], 4)
+      predictor.observe([1,2], 3)
+      predictor.observe([1,2], 5)
+      expect(predictor.select([1,2], 0)).to eq(42)
+      expect(predictor.select([1,2], 4)).to eq(42)
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,30 @@
+require 'simplecov'
+
+module SimpleCov::Configuration
+  def clean_filters
+    @filters = []
+  end
+end
+
+SimpleCov.configure do
+  clean_filters
+  load_profile 'test_frameworks'
+end
+
+ENV["COVERAGE"] && SimpleCov.start do
+  add_filter "/.rvm/"
+end
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+
+require 'rspec'
+
+require 'sooth'
+
+# Requires supporting files with custom matchers and macros, etc,
+# in ./support/ and its subdirectories.
+Dir["#{File.dirname(__FILE__)}/support/**/*.rb"].each {|f| require f}
+
+RSpec.configure do |config|
+
+end

metadata

@@ -0,0 +1,174 @@
+--- !ruby/object:Gem::Specification
+name: sooth
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Jason Hutchens
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-12-10 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.1'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.1'
+- !ruby/object:Gem::Dependency
+  name: yard
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.8'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.8'
+- !ruby/object:Gem::Dependency
+  name: rdoc
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4.1'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4.1'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.7'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.7'
+- !ruby/object:Gem::Dependency
+  name: jeweler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+- !ruby/object:Gem::Dependency
+  name: simplecov
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.9'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.9'
+- !ruby/object:Gem::Dependency
+  name: byebug
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.5'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.5'
+- !ruby/object:Gem::Dependency
+  name: rake-compiler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.9'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.9'
+description: Does what it says on the box
+email: jasonhutchens@gmail.com
+executables: []
+extensions:
+- ext/sooth_native/extconf.rb
+extra_rdoc_files:
+- README.md
+files:
+- Gemfile
+- Gemfile.lock
+- README.md
+- Rakefile
+- UNLICENSE
+- VERSION
+- ext/sooth_native/extconf.rb
+- ext/sooth_native/native.c
+- ext/sooth_native/sooth_context.h
+- ext/sooth_native/sooth_predictor.c
+- ext/sooth_native/sooth_predictor.h
+- ext/sooth_native/sooth_statistic.h
+- lib/sooth.rb
+- sooth.gemspec
+- spec/memory_spec.rb
+- spec/predictor_spec.rb
+- spec/spec_helper.rb
+homepage: http://github.com/jasonhutchens/sooth
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - "~>"
+    - !ruby/object:Gem::Version
+      version: '2.1'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.4.4
+signing_key: 
+specification_version: 4
+summary: A small thing for generating codes for users to type into places
+test_files: []