fast_trie 0.5.0 → 0.5.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: d100a816d2493736f2d1f351d8bd0def2916b366
+  data.tar.gz: a0d1ef512cc1ed7a2bddbf41a38749748f8b6bdb
+SHA512:
+  metadata.gz: d75a83ba5eb51fbb6037e3cb6273bbfc334d434bcab7e57978f15fe21c0040483cfd31a1af57e53c35b4bfc6d4fa1ffc271a23b3d8acd7be605e0e8a8f9adb29
+  data.tar.gz: 284623b2d2986f2c67f10143f8d043ffe0872b42cdaeca6b2ae10cb232b9867f2bc85b929dba5260046a8be9ed1114aa33d63a2e2cd89d87ee55e7d34bf29bff

data/Gemfile.lock

@@ -0,0 +1,69 @@
+GEM
+  remote: https://rubygems.org/
+  specs:
+    addressable (2.3.5)
+    builder (3.2.2)
+    descendants_tracker (0.0.3)
+    diff-lcs (1.2.5)
+    faraday (0.9.0)
+      multipart-post (>= 1.2, < 3)
+    git (1.2.6)
+    github_api (0.11.2)
+      addressable (~> 2.3)
+      descendants_tracker (~> 0.0.1)
+      faraday (~> 0.8, < 0.10)
+      hashie (>= 1.2)
+      multi_json (>= 1.7.5, < 2.0)
+      nokogiri (~> 1.6.0)
+      oauth2
+    hashie (2.0.5)
+    highline (1.6.20)
+    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 (0.1.11)
+      multi_json (>= 1.5)
+    mini_portile (0.5.2)
+    multi_json (1.8.4)
+    multi_xml (0.5.5)
+    multipart-post (2.0.0)
+    nokogiri (1.6.1-x86-mingw32)
+      mini_portile (~> 0.5.0)
+    oauth2 (0.9.3)
+      faraday (>= 0.8, < 0.10)
+      jwt (~> 0.1.8)
+      multi_json (~> 1.3)
+      multi_xml (~> 0.5)
+      rack (~> 1.2)
+    rack (1.5.2)
+    rake (10.1.1)
+    rake-compiler (0.9.2)
+      rake
+    rdoc (3.12.2)
+      json (~> 1.4)
+    rspec (2.14.1)
+      rspec-core (~> 2.14.0)
+      rspec-expectations (~> 2.14.0)
+      rspec-mocks (~> 2.14.0)
+    rspec-core (2.14.7)
+    rspec-expectations (2.14.5)
+      diff-lcs (>= 1.1.3, < 2.0)
+    rspec-mocks (2.14.5)
+
+PLATFORMS
+  x86-mingw32
+
+DEPENDENCIES
+  bundler (~> 1.0)
+  jeweler (~> 2.0.1)
+  rake
+  rake-compiler
+  rdoc (~> 3.12)
+  rspec

data/README.textile

@@ -1,6 +1,8 @@
 h1. Trie
 
-This is a trie for Ruby using libdatrie. It uses a dual-array system, meaning it has best-in-class memory usage and search time.
+!https://badge.fury.io/rb/fast_trie.svg!:https://rubygems.org/gems/fast_trie !https://travis-ci.org/tyler/trie.svg!:https://travis-ci.org/tyler/trie
+
+This is a trie for Ruby using "libdatrie":http://linux.thai.net/~thep/datrie/. It uses a dual-array system, meaning it has best-in-class memory usage and search time.
 
 
 h2. What is a trie?
@@ -19,12 +21,20 @@ But in short a trie is a data structure that holds strings in a tree.  So if you
 
 It's easy to see how this can have pretty neat implications for things like searching through lists of strings, sorting lists of strings, and things like spelling correction and autocompletion.
 
+h2. Installation
+
+From RubyGems https://rubygems.org/gems/fast_trie
+
+<pre><code>
+  gem install fast_trie
+</code></pre>
 
 h2. Tutorial
 
-Let's go through building a simple autocompleter using Trie.
+Let's go through building a simple autocompleter using "Trie":http://rubydoc.info/gems/fast_trie/Trie object.
 
 <pre><code>
+  require 'trie'
   Trie.new
 </code></pre>
 
@@ -85,8 +95,9 @@ There are, of course, some more interesting and advanced ways to use a trie.  Fo
   end
 </code></pre>
 
-By calling <code>root</code> on a Trie object, you get a TrieNode, pointed at the root of the trie.  You can then use this node to walk the trie and perceive things about each word.
+By calling <code>root</code> on a Trie, you get a "TrieNode":http://rubydoc.info/gems/fast_trie/TrieNode, pointed at the root of the trie.  You can then use this node to walk the trie and perceive things about each word.
 
+You can read the reference documentation at http://rubydoc.info/gems/fast_trie/frames/Trie
 
 h2. Performance Characteristics
 
@@ -115,7 +126,7 @@ For keys that are 40 characters long:
 
 There are a few takeaways from this. First, there is no strong correlation between length of keys and insert or retrieve time. They stay fairly constant as the length of keys increase. Secondly, doing prefix searches with this trie gets slower linearly with the length of the keys in the trie.
 
-This points to a limitation of this type of trie.  It is based on libdatrie, which is a dual-array trie.  When finding branches from a particular node, we must query all possible branches to determine whether or not they exist.  So for each node we do 255 of these queries.
+This points to a limitation of this type of trie.  It is based on "libdatrie":http://linux.thai.net/~thep/datrie/ ("version 0.1.99":http://linux.thai.net/svn/software/datrie/trunk/NEWS), which is a dual-array trie.  When finding branches from a particular node, we must query all possible branches to determine whether or not they exist.  So for each node we do 255 of these queries.
 
 There may be some tricks to speed this up, but for now it is simply a limitation of this trie.
 
@@ -129,4 +140,4 @@ The reason the insertion times takes such a beating is due, again, to a limitati
 
 
 
-Copyright (c) 2008 Tyler McMullen. See LICENSE for details.
+Copyright (c) 2008 Tyler McMullen. See LICENSE for details.

data/VERSION.yml

@@ -1,5 +1,5 @@
 --- 
 :major: 0
 :minor: 5
-:patch: 0
+:patch: 1
 :build: 

data/ext/trie/trie.c

@@ -21,7 +21,7 @@ static VALUE rb_trie_alloc(VALUE klass) {
 
 void raise_ioerror(const char * message) {
     VALUE rb_eIOError = rb_const_get(rb_cObject, rb_intern("IOError"));
-    rb_raise(rb_eIOError, message);
+    rb_raise(rb_eIOError, "%s", message);
 }
 
 /*
@@ -179,6 +179,19 @@ static VALUE walk_all_paths(Trie *trie, VALUE children, TrieState *state, char *
     }
 }
 
+
+static Bool traverse(TrieState *state, TrieChar *char_prefix) {
+	const TrieChar *iterator = char_prefix;
+	while(*iterator != 0) {
+		if(!trie_state_is_walkable(state, *iterator))
+			return FALSE;
+		trie_state_walk(state, *iterator);
+		iterator++;
+	}
+	return TRUE;
+}
+
+
 /*
  * call-seq:
  *   children(prefix) -> [ key, ... ]
@@ -200,12 +213,8 @@ static VALUE rb_trie_children(VALUE self, VALUE prefix) {
     VALUE children = rb_ary_new();
 	TrieChar *char_prefix = (TrieChar*)RSTRING_PTR(prefix);
     
-    const TrieChar *iterator = char_prefix;
-    while(*iterator != 0) {
-		if(!trie_state_is_walkable(state, *iterator))
-			return children;
-		trie_state_walk(state, *iterator);
-		iterator++;
+    if(!traverse(state, char_prefix)) {
+    	return children;
     }
 
     if(trie_state_is_terminal(state))
@@ -221,6 +230,64 @@ static VALUE rb_trie_children(VALUE self, VALUE prefix) {
     return children;
 }
 
+static Bool walk_all_paths_until_first_terminal(Trie *trie, TrieState *state, char *prefix, int prefix_size) {
+	int c;
+	Bool ret = FALSE;
+    for(c = 1; c < 256; c++) {
+		if(trie_state_is_walkable(state,c)) {
+			TrieState *next_state = trie_state_clone(state);
+			trie_state_walk(next_state, c);
+
+			prefix[prefix_size] = c;
+			prefix[prefix_size + 1] = 0;
+
+			if(trie_state_is_terminal(next_state)) {
+				return TRUE;
+			}
+
+			ret = walk_all_paths_until_first_terminal(trie, next_state, prefix, prefix_size + 1);
+
+			prefix[prefix_size] = 0;
+			trie_state_free(next_state);
+
+			if (ret == TRUE) {
+				return ret;
+			}
+		}
+    }
+
+    return ret;
+}
+
+static VALUE rb_trie_has_children(VALUE self, VALUE prefix) {
+    if(NIL_P(prefix))
+		return rb_ary_new();
+
+	StringValue(prefix);
+
+    Trie *trie;
+    Data_Get_Struct(self, Trie, trie);
+
+	int prefix_size = RSTRING_LEN(prefix);
+    TrieState *state = trie_root(trie);
+	TrieChar *char_prefix = (TrieChar*)RSTRING_PTR(prefix);
+
+    if(!traverse(state, char_prefix)) {
+		return Qfalse;
+	}
+
+    if(trie_state_is_terminal(state))
+        return Qtrue;
+
+	char prefix_buffer[1024];
+	memcpy(prefix_buffer, char_prefix, prefix_size);
+	prefix_buffer[prefix_size] = 0;
+
+    Bool ret = walk_all_paths_until_first_terminal(trie, state, prefix_buffer, prefix_size);
+
+    trie_state_free(state);
+    return ret == TRUE ? Qtrue : Qfalse;
+}
 
 static VALUE walk_all_paths_with_values(Trie *trie, VALUE children, TrieState *state, char *prefix, int prefix_size) {
 	int c;
@@ -280,13 +347,9 @@ static VALUE rb_trie_children_with_values(VALUE self, VALUE prefix) {
 
     TrieState *state = trie_root(trie);
     
-    const TrieChar *iterator = char_prefix;
-    while(*iterator != 0) {
-		if(!trie_state_is_walkable(state, *iterator))
-			return rb_ary_new();
-		trie_state_walk(state, *iterator);
-		iterator++;
-    }
+    if(!traverse(state, char_prefix)) {
+		return children;
+	}
 
     if(trie_state_is_terminal(state)) {
 		TrieState *end_state = trie_state_clone(state);
@@ -541,6 +604,7 @@ void Init_trie() {
     rb_define_method(cTrie, "delete", rb_trie_delete, 1);
     rb_define_method(cTrie, "children", rb_trie_children, 1);
     rb_define_method(cTrie, "children_with_values", rb_trie_children_with_values, 1);
+    rb_define_method(cTrie, "has_children?", rb_trie_has_children, 1);
     rb_define_method(cTrie, "root", rb_trie_root, 0);
     rb_define_method(cTrie, "save", rb_trie_save, 1);
 

data/ext/trie/typedefs.h

@@ -10,7 +10,11 @@
 
 #include <limits.h>
 
-typedef enum { FALSE = 0, TRUE = 1 } Bool;
+// fix for fast_trie on Windows. Should be easy to merge with future changes to libdatrie. MH
+#include <stdbool.h>
+#define Bool  bool
+#define FALSE false
+#define TRUE  true
 
 # if UCHAR_MAX == 0xff
 #   ifndef UINT8_TYPEDEF

data/fast_trie.gemspec

@@ -0,0 +1,75 @@
+# Generated by jeweler
+# DO NOT EDIT THIS FILE DIRECTLY
+# Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
+# -*- encoding: utf-8 -*-
+# stub: fast_trie 0.5.1 ruby ext
+# stub: ext/trie/extconf.rb
+
+Gem::Specification.new do |s|
+  s.name = "fast_trie"
+  s.version = "0.5.1"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.require_paths = ["ext"]
+  s.authors = ["Tyler McMullen", "Matt Hickford"]
+  s.date = "2015-07-27"
+  s.description = "Ruby Trie based on libdatrie."
+  s.email = "tyler@scribd.com"
+  s.extensions = ["ext/trie/extconf.rb"]
+  s.extra_rdoc_files = [
+    "LICENSE",
+    "README.textile"
+  ]
+  s.files = [
+    "Gemfile.lock",
+    "README.textile",
+    "VERSION.yml",
+    "ext/trie/darray.c",
+    "ext/trie/darray.h",
+    "ext/trie/extconf.rb",
+    "ext/trie/fileutils.c",
+    "ext/trie/fileutils.h",
+    "ext/trie/tail.c",
+    "ext/trie/tail.h",
+    "ext/trie/trie-private.c",
+    "ext/trie/trie-private.h",
+    "ext/trie/trie.c",
+    "ext/trie/trie.h",
+    "ext/trie/triedefs.h",
+    "ext/trie/typedefs.h",
+    "fast_trie.gemspec",
+    "spec/trie_spec.rb"
+  ]
+  s.homepage = "http://github.com/tyler/trie"
+  s.rdoc_options = ["--title", "Trie", "--line-numbers", "--op", "rdoc", "--main", "ext/trie/trie.c", "README"]
+  s.rubygems_version = "2.4.5"
+  s.summary = "Ruby Trie based on libdatrie."
+
+  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<rake>, [">= 0"])
+      s.add_development_dependency(%q<rspec>, [">= 0"])
+      s.add_development_dependency(%q<rdoc>, ["~> 3.12"])
+      s.add_development_dependency(%q<bundler>, ["~> 1.0"])
+      s.add_development_dependency(%q<jeweler>, ["~> 2.0.1"])
+      s.add_development_dependency(%q<rake-compiler>, [">= 0"])
+    else
+      s.add_dependency(%q<rake>, [">= 0"])
+      s.add_dependency(%q<rspec>, [">= 0"])
+      s.add_dependency(%q<rdoc>, ["~> 3.12"])
+      s.add_dependency(%q<bundler>, ["~> 1.0"])
+      s.add_dependency(%q<jeweler>, ["~> 2.0.1"])
+      s.add_dependency(%q<rake-compiler>, [">= 0"])
+    end
+  else
+    s.add_dependency(%q<rake>, [">= 0"])
+    s.add_dependency(%q<rspec>, [">= 0"])
+    s.add_dependency(%q<rdoc>, ["~> 3.12"])
+    s.add_dependency(%q<bundler>, ["~> 1.0"])
+    s.add_dependency(%q<jeweler>, ["~> 2.0.1"])
+    s.add_dependency(%q<rake-compiler>, [">= 0"])
+  end
+end
+

data/spec/trie_spec.rb

@@ -144,31 +144,46 @@ describe Trie do
       FileUtils.mkdir_p(dir)
       File.join(dir, 'trie')
     end
-    
+
     context 'when I save the populated trie to disk' do
       before(:each) do
         @trie.add('omgwtflolbbq', 123)
         @trie.save(filename_base)
       end
-      
+
       it 'should contain the same data when reading from disk' do
         trie2 = Trie.read(filename_base)
         trie2.get('omgwtflolbbq').should == 123
       end
     end
   end
-  
+
   describe :read do
     context 'when the files to read from do not exist' do
       let(:filename_base) do
         "phantasy/file/path/that/does/not/exist"
       end
-      
+
       it 'should raise an error when attempting a read' do
         lambda { Trie.read(filename_base) }.should raise_error(IOError)
       end
     end
   end
+
+  describe :has_children? do
+    it 'returns true when there are children matching prefix' do
+      @trie.has_children?('r').should be_true
+
+      @trie.has_children?('rock').should be_true
+      @trie.has_children?('rocket').should be_true
+    end
+
+    it 'returns false when there are no children matching prefix' do
+      @trie.has_children?('no').should be_false
+      @trie.has_children?('rome').should be_false
+      @trie.has_children?('roc_').should be_false
+    end
+  end
 end
 
 describe TrieNode do

metadata

@@ -1,33 +1,111 @@
---- !ruby/object:Gem::Specification 
+--- !ruby/object:Gem::Specification
 name: fast_trie
-version: !ruby/object:Gem::Version 
-  prerelease: false
-  segments: 
-  - 0
-  - 5
-  - 0
-  version: 0.5.0
+version: !ruby/object:Gem::Version
+  version: 0.5.1
 platform: ruby
-authors: 
+authors:
 - Tyler McMullen
+- Matt Hickford
 autorequire: 
 bindir: bin
 cert_chain: []
-
-date: 2010-12-21 00:00:00 -08:00
-default_executable: 
-dependencies: []
-
+date: 2015-07-27 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rdoc
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.12'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.12'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+- !ruby/object:Gem::Dependency
+  name: jeweler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 2.0.1
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 2.0.1
+- !ruby/object:Gem::Dependency
+  name: rake-compiler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 description: Ruby Trie based on libdatrie.
 email: tyler@scribd.com
 executables: []
-
-extensions: 
+extensions:
 - ext/trie/extconf.rb
-extra_rdoc_files: 
+extra_rdoc_files:
 - LICENSE
 - README.textile
-files: 
+files:
+- Gemfile.lock
+- LICENSE
 - README.textile
 - VERSION.yml
 - ext/trie/darray.c
@@ -43,46 +121,37 @@ files:
 - ext/trie/trie.h
 - ext/trie/triedefs.h
 - ext/trie/typedefs.h
+- fast_trie.gemspec
 - spec/trie_spec.rb
-- LICENSE
-has_rdoc: true
 homepage: http://github.com/tyler/trie
 licenses: []
-
+metadata: {}
 post_install_message: 
-rdoc_options: 
-- --title
+rdoc_options:
+- "--title"
 - Trie
-- --line-numbers
-- --op
+- "--line-numbers"
+- "--op"
 - rdoc
-- --main
+- "--main"
 - ext/trie/trie.c
 - README
-require_paths: 
+require_paths:
 - ext
-required_ruby_version: !ruby/object:Gem::Requirement 
-  none: false
-  requirements: 
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
   - - ">="
-    - !ruby/object:Gem::Version 
-      segments: 
-      - 0
-      version: "0"
-required_rubygems_version: !ruby/object:Gem::Requirement 
-  none: false
-  requirements: 
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
   - - ">="
-    - !ruby/object:Gem::Version 
-      segments: 
-      - 0
-      version: "0"
+    - !ruby/object:Gem::Version
+      version: '0'
 requirements: []
-
 rubyforge_project: 
-rubygems_version: 1.3.7
+rubygems_version: 2.2.2
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: Ruby Trie based on libdatrie.
-test_files: 
-- spec/trie_spec.rb
+test_files: []