cskit-strongs 1.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: d7941f8a82f4f5a278f04de2bc5d6d3f0ca20648
+  data.tar.gz: f390d7dd72906a498697e2c95a4cf10e0e5066e2
+SHA512:
+  metadata.gz: c8776a05144695defad440b71f64d82dbddbb9a3a03a5e298a7b227a6df318691a10479a8a322f2ecefe5999ac4636f2cee01283ba5e50e5dade7136e233b768
+  data.tar.gz: 698f74412e0083b4324aa20f61fb7696086b0fb4879c4b46b7aa46b40d8abd0e0cdb62cc93ac94bcedc5d72a6761983593793020eea7a8c6a2dd2c8b34273d72

data/Gemfile

@@ -0,0 +1,8 @@
+source "http://rubygems.org"
+
+gemspec
+
+group :development do
+  gem "pry"
+  gem "pry-nav"
+end

data/History.txt

@@ -0,0 +1,3 @@
+== 1.0.0
+
+* Birthday!

data/LICENSE

@@ -0,0 +1,177 @@
+
+                              Apache License
+                        Version 2.0, January 2004
+                     http://www.apache.org/licenses/
+
+TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+1. Definitions.
+
+   "License" shall mean the terms and conditions for use, reproduction,
+   and distribution as defined by Sections 1 through 9 of this document.
+
+   "Licensor" shall mean the copyright owner or entity authorized by
+   the copyright owner that is granting the License.
+
+   "Legal Entity" shall mean the union of the acting entity and all
+   other entities that control, are controlled by, or are under common
+   control with that entity. For the purposes of this definition,
+   "control" means (i) the power, direct or indirect, to cause the
+   direction or management of such entity, whether by contract or
+   otherwise, or (ii) ownership of fifty percent (50%) or more of the
+   outstanding shares, or (iii) beneficial ownership of such entity.
+
+   "You" (or "Your") shall mean an individual or Legal Entity
+   exercising permissions granted by this License.
+
+   "Source" form shall mean the preferred form for making modifications,
+   including but not limited to software source code, documentation
+   source, and configuration files.
+
+   "Object" form shall mean any form resulting from mechanical
+   transformation or translation of a Source form, including but
+   not limited to compiled object code, generated documentation,
+   and conversions to other media types.
+
+   "Work" shall mean the work of authorship, whether in Source or
+   Object form, made available under the License, as indicated by a
+   copyright notice that is included in or attached to the work
+   (an example is provided in the Appendix below).
+
+   "Derivative Works" shall mean any work, whether in Source or Object
+   form, that is based on (or derived from) the Work and for which the
+   editorial revisions, annotations, elaborations, or other modifications
+   represent, as a whole, an original work of authorship. For the purposes
+   of this License, Derivative Works shall not include works that remain
+   separable from, or merely link (or bind by name) to the interfaces of,
+   the Work and Derivative Works thereof.
+
+   "Contribution" shall mean any work of authorship, including
+   the original version of the Work and any modifications or additions
+   to that Work or Derivative Works thereof, that is intentionally
+   submitted to Licensor for inclusion in the Work by the copyright owner
+   or by an individual or Legal Entity authorized to submit on behalf of
+   the copyright owner. For the purposes of this definition, "submitted"
+   means any form of electronic, verbal, or written communication sent
+   to the Licensor or its representatives, including but not limited to
+   communication on electronic mailing lists, source code control systems,
+   and issue tracking systems that are managed by, or on behalf of, the
+   Licensor for the purpose of discussing and improving the Work, but
+   excluding communication that is conspicuously marked or otherwise
+   designated in writing by the copyright owner as "Not a Contribution."
+
+   "Contributor" shall mean Licensor and any individual or Legal Entity
+   on behalf of whom a Contribution has been received by Licensor and
+   subsequently incorporated within the Work.
+
+2. Grant of Copyright License. Subject to the terms and conditions of
+   this License, each Contributor hereby grants to You a perpetual,
+   worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+   copyright license to reproduce, prepare Derivative Works of,
+   publicly display, publicly perform, sublicense, and distribute the
+   Work and such Derivative Works in Source or Object form.
+
+3. Grant of Patent License. Subject to the terms and conditions of
+   this License, each Contributor hereby grants to You a perpetual,
+   worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+   (except as stated in this section) patent license to make, have made,
+   use, offer to sell, sell, import, and otherwise transfer the Work,
+   where such license applies only to those patent claims licensable
+   by such Contributor that are necessarily infringed by their
+   Contribution(s) alone or by combination of their Contribution(s)
+   with the Work to which such Contribution(s) was submitted. If You
+   institute patent litigation against any entity (including a
+   cross-claim or counterclaim in a lawsuit) alleging that the Work
+   or a Contribution incorporated within the Work constitutes direct
+   or contributory patent infringement, then any patent licenses
+   granted to You under this License for that Work shall terminate
+   as of the date such litigation is filed.
+
+4. Redistribution. You may reproduce and distribute copies of the
+   Work or Derivative Works thereof in any medium, with or without
+   modifications, and in Source or Object form, provided that You
+   meet the following conditions:
+
+   (a) You must give any other recipients of the Work or
+       Derivative Works a copy of this License; and
+
+   (b) You must cause any modified files to carry prominent notices
+       stating that You changed the files; and
+
+   (c) You must retain, in the Source form of any Derivative Works
+       that You distribute, all copyright, patent, trademark, and
+       attribution notices from the Source form of the Work,
+       excluding those notices that do not pertain to any part of
+       the Derivative Works; and
+
+   (d) If the Work includes a "NOTICE" text file as part of its
+       distribution, then any Derivative Works that You distribute must
+       include a readable copy of the attribution notices contained
+       within such NOTICE file, excluding those notices that do not
+       pertain to any part of the Derivative Works, in at least one
+       of the following places: within a NOTICE text file distributed
+       as part of the Derivative Works; within the Source form or
+       documentation, if provided along with the Derivative Works; or,
+       within a display generated by the Derivative Works, if and
+       wherever such third-party notices normally appear. The contents
+       of the NOTICE file are for informational purposes only and
+       do not modify the License. You may add Your own attribution
+       notices within Derivative Works that You distribute, alongside
+       or as an addendum to the NOTICE text from the Work, provided
+       that such additional attribution notices cannot be construed
+       as modifying the License.
+
+   You may add Your own copyright statement to Your modifications and
+   may provide additional or different license terms and conditions
+   for use, reproduction, or distribution of Your modifications, or
+   for any such Derivative Works as a whole, provided Your use,
+   reproduction, and distribution of the Work otherwise complies with
+   the conditions stated in this License.
+
+5. Submission of Contributions. Unless You explicitly state otherwise,
+   any Contribution intentionally submitted for inclusion in the Work
+   by You to the Licensor shall be under the terms and conditions of
+   this License, without any additional terms or conditions.
+   Notwithstanding the above, nothing herein shall supersede or modify
+   the terms of any separate license agreement you may have executed
+   with Licensor regarding such Contributions.
+
+6. Trademarks. This License does not grant permission to use the trade
+   names, trademarks, service marks, or product names of the Licensor,
+   except as required for reasonable and customary use in describing the
+   origin of the Work and reproducing the content of the NOTICE file.
+
+7. Disclaimer of Warranty. Unless required by applicable law or
+   agreed to in writing, Licensor provides the Work (and each
+   Contributor provides its Contributions) on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+   implied, including, without limitation, any warranties or conditions
+   of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+   PARTICULAR PURPOSE. You are solely responsible for determining the
+   appropriateness of using or redistributing the Work and assume any
+   risks associated with Your exercise of permissions under this License.
+
+8. Limitation of Liability. In no event and under no legal theory,
+   whether in tort (including negligence), contract, or otherwise,
+   unless required by applicable law (such as deliberate and grossly
+   negligent acts) or agreed to in writing, shall any Contributor be
+   liable to You for damages, including any direct, indirect, special,
+   incidental, or consequential damages of any character arising as a
+   result of this License or out of the use or inability to use the
+   Work (including but not limited to damages for loss of goodwill,
+   work stoppage, computer failure or malfunction, or any and all
+   other commercial damages or losses), even if such Contributor
+   has been advised of the possibility of such damages.
+
+9. Accepting Warranty or Additional Liability. While redistributing
+   the Work or Derivative Works thereof, You may choose to offer,
+   and charge a fee for, acceptance of support, warranty, indemnity,
+   or other liability obligations and/or rights consistent with this
+   License. However, in accepting such obligations, You may act only
+   on Your own behalf and on Your sole responsibility, not on behalf
+   of any other Contributor, and only if You agree to indemnify,
+   defend, and hold each Contributor harmless for any liability
+   incurred by, or claims asserted against, such Contributor by reason
+   of your accepting any such warranty or additional liability.
+
+END OF TERMS AND CONDITIONS

data/Rakefile

@@ -0,0 +1,129 @@
+# encoding: UTF-8
+
+# Copyright 2012 Twitter, Inc
+# http://www.apache.org/licenses/LICENSE-2.0
+
+require 'rubygems' unless ENV['NO_RUBYGEMS']
+
+require 'bundler'
+require 'digest'
+require 'fileutils'
+
+require 'rubygems/package_task'
+
+require './lib/cskit-strongs'
+require 'cskit'
+
+Bundler::GemHelper.install_tasks
+
+class LexiconUpdater
+  BLOCK_SIZE = 100
+
+  attr_reader :lexicon_lang, :splitter_class
+
+  def initialize(lexicon_lang, splitter_class)
+    @lexicon_lang = lexicon_lang
+    @splitter_class = splitter_class
+  end
+
+  def update
+    splitter = splitter_class.new(input_file)
+    FileUtils.mkdir_p(output_dir)
+
+    puts "Processing #{lexicon_lang} lexicon..."
+
+    splitter.each_slice(BLOCK_SIZE).with_index do |entries, index|
+      File.open(File.join(output_dir, "#{index}.json"), "w+") do |f|
+        f.write(
+          entries.inject({}) do |ret, entry|
+            ret[entry.first] = entry.last
+            ret
+          end.to_json
+        )
+      end
+    end
+
+    puts "Done."
+  end
+
+  private
+
+  def input_file
+    @input_file ||= File.join(CSKitStrongs.vendor_dir, "#{lexicon_lang}_lexicon.xml")
+  end
+
+  def output_dir
+    @output_dir ||= File.join(CSKitStrongs.resource_dir, "lexicon/#{lexicon_lang}")
+  end
+end
+
+class ConcordanceUpdater
+  def update
+    puts "Processing concordance..."
+    file_contents = split
+
+    puts "\nWriting to disk..."
+    write_to_disk(file_contents)
+
+    puts "Done."
+  end
+
+  private
+
+  def write_to_disk(file_contents)
+    file_contents.each do |path, contents|
+      FileUtils.mkdir_p(File.dirname(path))
+      File.open(path, "w+") { |f| f.write(contents.to_json) }
+    end
+  end
+
+  def split
+    total_lines = `wc -l #{input_file}`.strip.to_i
+    splitter = CSKitStrongs::Splitters::ConcordanceSplitter.new(input_file)
+    file_contents = {}
+
+    splitter.each_with_index do |(language, number, text, citation), index|
+      book = citation.book.strip.downcase.gsub(" ", "_")
+      chapter = citation.chapter_list.first.chapter_number
+      verse = citation.chapter_list.first.verse_list.first.start.to_i
+      path = File.join(output_dir, book, "#{chapter}.json")
+
+      ((file_contents[path] ||= {})[verse] ||= []) << {
+        :text => text,
+        :number => number
+      }
+
+      if index % 1000 == 0
+        $stdout.write("\rProcessing #{index} of #{total_lines} (#{((index.to_f / total_lines.to_f) * 100).round(2)})")
+      end
+    end
+
+    file_contents
+  end
+
+  def input_file
+    @input_file ||= File.join(CSKitStrongs.vendor_dir, "concordance.txt")
+  end
+
+  def output_dir
+    @output_dir ||= File.join(CSKitStrongs.resource_dir, "concordance")
+  end
+end
+
+namespace :update do
+  task :default => [:concordance, :lexicon]
+
+  task :concordance do
+    ConcordanceUpdater.new.update
+  end
+
+  task :greek_lexicon do
+    splitter_class = CSKitStrongs::Splitters::GreekLexiconSplitter
+    LexiconUpdater.new("greek", splitter_class).update
+  end
+
+  task :hebrew_lexicon do
+    splitter_class = CSKitStrongs::Splitters::HebrewLexiconSplitter
+    LexiconUpdater.new("hebrew", splitter_class).update
+  end
+end

data/cskit-strongs.gemspec

@@ -0,0 +1,26 @@
+# encoding: UTF-8
+
+$:.unshift File.join(File.dirname(__FILE__), 'lib')
+require 'cskit-strongs/version'
+
+Gem::Specification.new do |s|
+  s.name     = "cskit-strongs"
+  s.version  = ::CSKitStrongs::VERSION
+  s.authors  = ["Cameron Dutro"]
+  s.email    = ["camertron@gmail.com"]
+  s.homepage = "http://github.com/camertron"
+
+  s.description = s.summary = "Strong's Concordance resources for CSKit."
+
+  s.platform = Gem::Platform::RUBY
+  s.has_rdoc = true
+
+  s.add_dependency 'json'
+  s.add_dependency 'cskit', '~> 1.0.0'
+
+  s.add_development_dependency 'rake'
+  s.add_development_dependency 'nokogiri'
+
+  s.require_path = 'lib'
+  s.files = Dir["{lib,spec,resources}/**/*", "Gemfile", "History.txt", "LICENSE", "README.md", "Rakefile", "cskit-strongs.gemspec"]
+end

data/lib/cskit/concordances/strongs.rb

@@ -0,0 +1,15 @@
+# encoding: UTF-8
+
+require 'cskit'
+require 'cskit/bible/kjv'
+require 'cskit-strongs'
+
+CSKit.register_annotator({
+  :type => :concordance,
+  :id => :strongs,
+  :name => "Strong's Exhaustive Concordance of the Bible",
+  :author => "James Strong",
+  :language => "English",
+  :volumes => [CSKitBibleKJV::Volume],
+  :annotator => CSKitStrongs::Annotator
+})

data/lib/cskit-strongs/annotator.rb

@@ -0,0 +1,102 @@
+# encoding: UTF-8
+
+require 'json'
+
+module CSKitStrongs
+  class Annotator < CSKit::Annotator
+
+    def annotate(reading, volume)
+      annotated_reading = reading.to_annotated_reading
+      resource = concordance_resource_for(reading, volume)
+
+      reading.texts.each_with_index do |text, index|
+        verse_num = reading.verse.start + index
+        corresponding_verse_texts = resource[verse_num.to_s]
+
+        each_annotation_for(text, corresponding_verse_texts) do |annotation|
+          annotated_reading.add_annotation(index, annotation)
+        end
+      end
+
+      annotated_reading
+    end
+
+    private
+
+    BATCH_SIZE = 100
+
+    def each_annotation_for(text, corresponding_verse_texts, &block)
+      enum = Enumerator.new do |yielder|
+        corresponding_verse_texts.each do |verse_text|
+          parts = split_on_last_word(verse_text["text"])
+          regex = /#{Regexp.escape(parts.first)}(#{Regexp.escape(parts.last)})/
+
+          if matches = text.match(regex)
+            start, finish = matches.offset(1)
+            strongs_number = StrongsNumber.from_string(verse_text["number"])
+            lexicon_entry = lexicon_entry_for(strongs_number)
+
+            if lexicon_entry
+              yielder.yield(CSKit::Annotation.new(start, finish - 1, lexicon_entry))
+            end
+          end
+        end
+      end
+
+      block_given? ? enum.each(&block) : enum
+    end
+
+    def lexicon_entry_for(strongs_number)
+      batch_number = batch_number_for(strongs_number)
+      path = lexicon_path_for(batch_number, strongs_number.language)
+      lexicon = (lexicon_cache[batch_number] ||= JSON.parse(File.read(path)))
+      LexiconEntry.from_hash(lexicon[strongs_number.to_s])
+    rescue Errno::ENOENT  # couldn't load file
+      nil
+    end
+
+    def split_on_last_word(text)
+      if idx = text.rindex(" ")
+        [text[0..idx], text[(idx + 1)..-1]]
+      else
+        ["", text]
+      end
+    end
+
+    def concordance_resource_for(reading, volume)
+      path = concordance_path_for(reading, volume)
+      concordance_cache[path] ||= JSON.parse(File.read(path))
+    end
+
+    def concordance_path_for(reading, volume)
+      book = volume.unabbreviate_book_name(reading.citation.book)
+      chapter = reading.chapter.chapter_number
+      File.join(concordance_base_path, book, "#{chapter}.json")
+    end
+
+    def lexicon_path_for(batch_number, language)
+      File.join(lexicon_base_path, language, "#{batch_number}.json")
+    end
+
+    def batch_number_for(strongs_number)
+      (strongs_number.number - 1) / BATCH_SIZE
+    end
+
+    def concordance_base_path
+      @concordance_base_path ||= File.join(CSKitStrongs.resource_dir, "concordance")
+    end
+
+    def lexicon_base_path
+      @lexicon_base_path ||= File.join(CSKitStrongs.resource_dir, "lexicon")
+    end
+
+    def concordance_cache
+      @concordance_cache ||= {}
+    end
+
+    def lexicon_cache
+      @lexicon_cache ||= {}
+    end
+
+  end
+end

data/lib/cskit-strongs/formatters/strongs_html_formatter.rb

@@ -0,0 +1,20 @@
+# encoding: UTF-8
+
+module CSKitStrongs
+  module Formatters
+    class StrongsHtmlFormatter < StrongsPlainTextFormatter
+
+      def format_annotation(annotation, text)
+        "<span class='cskit-strongs-word' %{data_attrs} data-definition='%{definition}'>%{text}</span>" % {
+          :text => text,
+          :definition => "[#{annotation.data.unicode}] #{annotation.data.definition}",
+          :data_attrs => [:pronunciation, :translit, :unicode].map do |data_attr|
+            value = annotation.data.send(data_attr)
+            "data-#{data_attr}='#{value.gsub("'", "&#39;")}'"
+          end.join(" ")
+        }
+      end
+
+    end
+  end
+end

data/lib/cskit-strongs/formatters/strongs_plain_text_formatter.rb

@@ -0,0 +1,22 @@
+# encoding: UTF-8
+
+module CSKitStrongs
+  module Formatters
+    class StrongsPlainTextFormatter < CSKit::Formatters::Formatter
+
+      RLE = "\u202b"  # right-to-left embedding
+      PDF = "\u202c"  # pop directional formatting
+
+      def format_annotation(annotation, text)
+        unicode = if StrongsNumber.from_string(annotation.data.strongs_number).hebrew?
+          "#{RLE}#{annotation.data.unicode}#{PDF}"
+        else
+          annotation.data.unicode
+        end
+
+        "#{text} [#{unicode}]"
+      end
+
+    end
+  end
+end

data/lib/cskit-strongs/formatters.rb

@@ -0,0 +1,10 @@
+# encoding: UTF-8
+
+module CSKitStrongs
+  module Formatters
+
+    autoload :StrongsHtmlFormatter,      "cskit-strongs/formatters/strongs_html_formatter"
+    autoload :StrongsPlainTextFormatter, "cskit-strongs/formatters/strongs_plain_text_formatter"
+
+  end
+end

data/lib/cskit-strongs/lexicon_entry.rb

@@ -0,0 +1,17 @@
+# encoding: UTF-8
+
+module CSKitStrongs
+
+  LEXICON_ATTRS = [:pronunciation, :unicode, :translit, :definition, :strongs_number]
+
+  LexiconEntry = Struct.new(*LEXICON_ATTRS) do
+    def self.from_hash(hash = {})
+      new(
+        *(LEXICON_ATTRS.map do |attr|
+          hash[attr.to_sym] || hash[attr.to_s]
+        end)
+      )
+    end
+  end
+
+end

data/lib/cskit-strongs/splitters/concordance_splitter.rb

@@ -0,0 +1,50 @@
+# encoding: UTF-8
+
+require 'json'
+
+module CSKitStrongs
+  module Splitters
+    class ConcordanceSplitter
+
+      include Enumerable
+      include CSKitStrongs::Splitters::Utilities
+      attr_reader :input_file
+
+      PARSER_CONST = CSKit::Parsers::BibleParser
+
+      def initialize(input_file)
+        @input_file = input_file
+      end
+
+      def each
+        File.open(input_file) do |f|
+          until f.eof?
+            # split strongs line into [number, text, citation], split citation into [book, "chapter:verse"]
+            parts = f.readline.match(/([hg]\d{4})(.*)(\-[\w\d]{2,3}.*)/).captures.map(&:strip)
+            citation_parts = parts.last.match(/\-([\w\d]{2,3})(.*)/).captures
+
+            # replace strong's book name with something we understand
+            citation_text = "#{book_map[citation_parts.first]}#{citation_parts.last}"
+
+            number = strip_zeroes(parts[0])
+            text = parts[1]
+            citation = parser.parse(citation_text).to_object
+
+            yield language, number, text, citation
+          end
+        end
+      end
+
+      private
+
+      def book_map
+        @book_map = JSON.parse(File.read(File.join(CSKitStrongs.vendor_dir, "book_map.json")))
+      end
+
+      def parser
+        @parser ||= PARSER_CONST.new
+      end
+
+    end
+  end
+end

data/lib/cskit-strongs/splitters/greek_lexicon_splitter.rb

@@ -0,0 +1,86 @@
+# encoding: UTF-8
+
+require 'nokogiri'
+
+module CSKitStrongs
+  module Splitters
+    class GreekLexiconSplitter
+
+      LANG = :greek
+
+      include Enumerable
+      include CSKitStrongs::Splitters::Utilities
+      attr_reader :input_file
+
+      def initialize(input_file)
+        @input_file = input_file
+      end
+
+      def each
+        doc = parse_file(input_file)
+
+        results = (doc / :entry).each do |entry|
+          attrs = pronunciation_for(entry).
+            merge(lang_attrs_for(entry, LANG)).
+            merge(definition_for(entry))
+
+          number = "g#{strip_zeroes(entry.attributes["strongs"].value)}"
+          attrs.merge!(:strongs_number => number)
+
+          yield number, attrs
+        end
+      end
+
+      private
+
+      def parse_file(file)
+        Nokogiri::XML(File.read(file))
+      end
+
+      def pronunciation_for(entry)
+        attrs = (entry / :pronunciation).first
+        { :pronunciation => attrs ? attrs.attributes["strongs"].value : nil }
+      end
+
+      def lang_attrs_for(entry, lang)
+        attrs = (entry / lang).first
+        {
+          :unicode  => attrs ? attrs.attributes["unicode"].value : nil,
+          :translit => attrs ? attrs.attributes["translit"].value : nil
+        }
+      end
+
+      def definition_for(entry)
+        parts = definition_parts_for(entry)
+
+        definition = parts[1..-1].map do |part|
+          part.gsub("\n", "")
+        end.join
+
+        { :definition => "[#{parts.first}] #{definition}" }
+      end
+
+      def definition_parts_for(node)
+        node.children.flat_map do |child|
+          case child.name
+            when "strongs_derivation", "strongs_def"
+              definition_parts_for(child)
+            when "greek"
+              [child.attributes["unicode"].value.strip]
+            when "strongsref"
+              lang = child.attributes["language"].value.chars.first.downcase
+              number = strip_zeroes(child.attributes["strongs"].value.to_s)
+              "{{#{lang}#{number}}}"
+            when "text"
+              if child.text.strip.empty?
+                nil
+              else
+                child.text
+              end
+          end
+        end.compact
+      end
+
+    end
+  end
+end