bible_parser 1.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 81b20722da2fe055932ce55362c9b9856b1b8263
+  data.tar.gz: 9c7c29b4fd023897ddc4d0263113bedef3cabe19
+SHA512:
+  metadata.gz: b0e8c2264b7ea234ea116c46e0090b67915e28b9a596ae80517cc6725b2bd06c0d24e1411768449f8b2ece2bc97e373cb2ecd6fde7b49ddf1b717a3a212323aa
+  data.tar.gz: eaa58f82526d4a717c77ec58e8b2ce0f3c4b4d200d402839a899dfda0bdf769c2201205f960dc66c411391c861eb871ebb73903fae976a16bc6b9e8b54464efb

data/README.md

@@ -0,0 +1,31 @@
+# BibleParser
+
+[![Build Status](https://travis-ci.org/seven1m/bible_parser.svg?branch=master)](https://travis-ci.org/seven1m/bible_parser)
+
+This is a Ruby library for parsing different bible XML formats.
+
+For now, it only supports USFX and OSIS, but I hope to add support for other formats also.
+
+## Install
+
+```
+gem install bible_parser
+```
+
+## Use
+
+You can get the a bible in XML format [here](https://github.com/seven1m/open-bibles).
+
+```ruby
+require 'bible_parser'
+
+bible = BibleParser.new(File.open('web.usfx.xml'))
+verse = bible.books.first.chapters.first.verses.first
+# => <Genesis 1:1>
+verse.text
+# => "In the beginning, God created the heavens and the earth.\n"
+```
+
+## License
+
+Copyright (c) 2015 Tim Morgan. Licensed MIT. See LICENSE file.

data/lib/bible_parser.rb

@@ -0,0 +1,68 @@
+require_relative 'bible_parser/parsers'
+require_relative 'bible_parser/errors'
+require_relative 'bible_parser/book'
+require_relative 'bible_parser/chapter'
+require_relative 'bible_parser/verse'
+
+require 'stringio'
+
+class BibleParser
+  attr_reader :format
+
+  def initialize(io, format: nil)
+    if io.is_a?(String)
+      @io = StringIO.new(io)
+    elsif io.respond_to?(:read)
+      @io = io
+    else
+      fail(
+        Errors::UnknownIoObjectError,
+        "#{io.inspect} is neither a File nor a String object. Please pass a File or a String."
+      )
+    end
+    @format = format || detect_format
+  end
+
+  def each_book(&block)
+    @io.rewind
+    if block
+      parser.each_book(&block)
+    else
+      parser.enum_for(:each_book)
+    end
+  end
+
+  def books
+    each_book.to_a
+  end
+
+  def each_verse(&block)
+    @io.rewind
+    if block
+      parser.each_verse(&block)
+    else
+      parser.enum_for(:each_verse)
+    end
+  end
+
+  def verses
+    each_verse.to_a
+  end
+
+  private
+
+  def parser
+    parser_class.new(@io)
+  end
+
+  def parser_class
+    PARSERS[format] or fail(Errors::ParserUnavailableError, "Parser for #{format.inspect} could not be loaded.")
+  end
+
+  def detect_format
+    PARSERS.each do |name, parser|
+      @io.rewind
+      return name if parser.new(@io).valid?
+    end
+  end
+end

data/lib/bible_parser/book.rb

@@ -0,0 +1,42 @@
+class BibleParser
+  class Book
+    attr_reader :num, :id, :title
+
+    def initialize(num:, id:, title:, parser:)
+      @num = num
+      @id = id
+      @title = title
+      @parser = parser
+    end
+
+    def each_chapter(&block)
+      if block
+        @parser.each_chapter(book_id: id, &block)
+      else
+        enum_for(:each_chapter)
+      end
+    end
+
+    def chapters
+      each_chapter.to_a
+    end
+
+    def ==(other)
+      id == other.id
+    end
+
+    def inspect
+      "<#{to_s}>"
+    end
+
+    alias_method :to_s, :title
+
+    def to_h
+      {
+        num:   num,
+        id:    id,
+        title: title
+      }
+    end
+  end
+end

data/lib/bible_parser/chapter.rb

@@ -0,0 +1,55 @@
+class BibleParser
+  class Chapter
+    attr_reader :num, :book_id, :book_num, :book_title
+
+    def initialize(num:, book_id:, book_num:, book_title:, parser:)
+      @num = num
+      @book_id = book_id
+      @book_num = book_num
+      @book_title = book_title
+      @parser = parser
+    end
+
+    def each_verse(&block)
+      if block
+        @parser.each_verse(book_id: book_id, chapter_num: num, &block)
+      else
+        enum_for(:each_verse)
+      end
+    end
+
+    def verses
+      each_verse.to_a
+    end
+
+    def book
+      Book.new(
+        id: book_id,
+        num: book_num,
+        title: book_title,
+        parser: @parser
+      )
+    end
+
+    def ==(other)
+      book_id == other.book_id && num == other.num
+    end
+
+    def inspect
+      "<#{to_s}>"
+    end
+
+    def to_s
+      "#{book_title} #{num}"
+    end
+
+    def to_h
+      {
+        num:         num,
+        book_id:     book_id,
+        book_num:    book_num,
+        book_title:  book_title
+      }
+    end
+  end
+end

data/lib/bible_parser/errors.rb

@@ -0,0 +1,6 @@
+class BibleParser
+  module Errors
+    class UnknownIoObjectError   < StandardError; end
+    class ParserUnavailableError < StandardError; end
+  end
+end

data/lib/bible_parser/parsers.rb

@@ -0,0 +1,10 @@
+require_relative 'parsers/base'
+require_relative 'parsers/usfx'
+require_relative 'parsers/osis'
+
+class BibleParser
+  PARSERS = {
+    'USFX' => Parsers::USFX::Parser,
+    'OSIS' => Parsers::OSIS::Parser
+  }
+end

data/lib/bible_parser/parsers/base.rb

@@ -0,0 +1,9 @@
+require_relative 'base/parser'
+require_relative 'base/document'
+
+class BibleParser
+  module Parsers
+    module Base
+    end
+  end
+end

data/lib/bible_parser/parsers/base/document.rb

@@ -0,0 +1,56 @@
+require 'nokogiri'
+
+class BibleParser
+  module Parsers
+    module Base
+      class Document < Nokogiri::XML::SAX::Document
+        def initialize(io:, iterator: :verse, iterate_book_id: nil, iterate_chapter_num: nil, &block)
+          super()
+          @book_num = 0
+          @io = io
+          @iterator = iterator
+          @iterate_book_id = iterate_book_id
+          @iterate_chapter_num = iterate_chapter_num
+          @block = block
+        end
+
+        def end_book
+          return unless @book_title
+          return unless @iterator == :book
+          @block.call(
+            num: @book_num,
+            id: @book_id,
+            title: @book_title
+          )
+        end
+
+        def end_chapter
+          return unless @chapter
+          return unless @iterator == :chapter
+          return if @iterate_book_id && @iterate_book_id != @book_id
+          @block.call(
+            num: @chapter,
+            book_id: @book_id,
+            book_num: @book_num,
+            book_title: @book_title
+          )
+        end
+
+        def end_verse
+          @mode = nil
+          return unless @iterator == :verse
+          return if @iterate_book_id && @iterate_book_id != @book_id
+          return if @iterate_chapter_num && @iterate_chapter_num != @chapter
+          @block.call(
+            num: @verse,
+            book_id: @book_id,
+            book_num: @book_num,
+            book_title: @book_title,
+            chapter_num: @chapter,
+            text: @text
+          )
+        end
+      end
+    end
+  end
+end

data/lib/bible_parser/parsers/base/parser.rb

@@ -0,0 +1,68 @@
+require 'nokogiri'
+
+class BibleParser
+  module Parsers
+    module Base
+      class Parser
+        def initialize(io)
+          @io = io
+        end
+
+        def valid?
+          fail NotImplementedError, "override #valid? in your Parser class"
+        end
+
+        def document_class
+          module_name = self.class.name.sub(/::Parser$/, '')
+          Kernel.const_get("#{module_name}::Document")
+        end
+
+        def each_book
+          @io.rewind
+          document = document_class.new(io: @io, iterator: :book) do |book|
+            yield Book.new(
+              num: book[:num],
+              id: book[:id],
+              title: book[:title],
+              parser: self
+            )
+          end
+          sax_parser = Nokogiri::XML::SAX::Parser.new(document)
+          sax_parser.parse(@io)
+        end
+
+        def each_chapter(book_id: nil, &block)
+          @io.rewind
+          document = document_class.new(io: @io, iterator: :chapter, iterate_book_id: book_id) do |chapter|
+            yield Chapter.new(
+              num: chapter[:num],
+              book_id: chapter[:book_id],
+              book_num: chapter[:book_num],
+              book_title: chapter[:book_title],
+              parser: self
+            )
+          end
+          sax_parser = Nokogiri::XML::SAX::Parser.new(document)
+          sax_parser.parse(@io)
+        end
+
+        def each_verse(book_id: nil, chapter_num: nil, &block)
+          @io.rewind
+          document = document_class.new(io: @io, iterator: :verse, iterate_book_id: book_id, iterate_chapter_num: chapter_num) do |verse|
+            yield Verse.new(
+              num: verse[:num],
+              text: verse[:text],
+              book_id: verse[:book_id],
+              book_num: verse[:book_num],
+              book_title: verse[:book_title],
+              chapter_num: verse[:chapter_num],
+              parser: self
+            )
+          end
+          sax_parser = Nokogiri::XML::SAX::Parser.new(document)
+          sax_parser.parse(@io)
+        end
+      end
+    end
+  end
+end

data/lib/bible_parser/parsers/osis.rb

@@ -0,0 +1,2 @@
+require_relative 'osis/parser'
+require_relative 'osis/document'

data/lib/bible_parser/parsers/osis/book_ids.rb

@@ -0,0 +1,94 @@
+class BibleParser
+  module Parsers
+    module OSIS
+      module BookIDs
+        BOOK_IDS = {
+          'Gen'    => 'GEN',
+          'Exod'   => 'EXO',
+          'Lev'    => 'LEV',
+          'Num'    => 'NUM',
+          'Deut'   => 'DEU',
+          'Josh'   => 'JOS',
+          'Judg'   => 'JDG',
+          'Ruth'   => 'RUT',
+          '1Sam'   => '1SA',
+          '2Sam'   => '2SA',
+          '1Kgs'   => '1KI',
+          '2Kgs'   => '2KI',
+          '1Chr'   => '1CH',
+          '2Chr'   => '2CH',
+          'Ezra'   => 'EZR',
+          'Neh'    => 'NEH',
+          'Esth'   => 'EST',
+          'Job'    => 'JOB',
+          'Ps'     => 'PSA',
+          'Prov'   => 'PRO',
+          'Eccl'   => 'ECC',
+          'Song'   => 'SNG',
+          'Isa'    => 'ISA',
+          'Jer'    => 'JER',
+          'Lam'    => 'LAM',
+          'Ezek'   => 'EZK',
+          'Dan'    => 'DAN',
+          'Hos'    => 'HOS',
+          'Joel'   => 'JOL',
+          'Amos'   => 'AMO',
+          'Obad'   => 'OBA',
+          'Jonah'  => 'JON',
+          'Mic'    => 'MIC',
+          'Nah'    => 'NAM',
+          'Hab'    => 'HAB',
+          'Zeph'   => 'ZEP',
+          'Hag'    => 'HAG',
+          'Zech'   => 'ZEC',
+          'Mal'    => 'MAL',
+          'Tob'    => 'TOB',
+          'Jdt'    => 'JDT',
+          'EsthGr' => 'ESG',
+          'Wis'    => 'WIS',
+          'Sir'    => 'SIR',
+          'Bar'    => 'BAR',
+          'EpJer'  => 'LJE',
+          'PrAzar' => 'S3Y',
+          'Sus'    => 'SUS',
+          'Bel'    => 'BEL',
+          '1Macc'  => '1MA',
+          '2Macc'  => '2MA',
+          '3Macc'  => '3MA',
+          '4Macc'  => '4MA',
+          '1Esd'   => '1ES',
+          '2Esd'   => '2ES',
+          'PrMan'  => 'MAN',
+          '2Esd'   => 'PS2',
+          'Matt'   => 'MAT',
+          'Mark'   => 'MRK',
+          'Luke'   => 'LUK',
+          'John'   => 'JHN',
+          'Acts'   => 'ACT',
+          'Rom'    => 'ROM',
+          '1Cor'   => '1CO',
+          '2Cor'   => '2CO',
+          'Gal'    => 'GAL',
+          'Eph'    => 'EPH',
+          'Phil'   => 'PHP',
+          'Col'    => 'COL',
+          '1Thess' => '1TH',
+          '2Thess' => '2TH',
+          '1Tim'   => '1TI',
+          '2Tim'   => '2TI',
+          'Titus'  => 'TIT',
+          'Phlm'   => 'PHM',
+          'Heb'    => 'HEB',
+          'Jas'    => 'JAS',
+          '1Pet'   => '1PE',
+          '2Pet'   => '2PE',
+          '1John'  => '1JN',
+          '2John'  => '2JN',
+          '3John'  => '3JN',
+          'Jude'   => 'JUD',
+          'Rev'    => 'REV'
+        }
+      end
+    end
+  end
+end

data/lib/bible_parser/parsers/osis/document.rb

@@ -0,0 +1,81 @@
+require_relative 'book_ids'
+
+class BibleParser
+  module Parsers
+    module OSIS
+      class Document < Base::Document
+        include BookIDs
+
+        def start_element(name, attributes)
+          case name
+          when 'div'
+            end_verse if @mode == 'verse'
+            start_book(attributes)
+          when 'title'
+            set_book_title(attributes)
+          when 'chapter'
+            end_verse if @mode == 'verse'
+            start_chapter(attributes)
+          when 'verse'
+            end_verse if @mode == 'verse'
+            start_verse(attributes)
+          end
+        end
+
+        def end_element(name)
+          case name
+          when 'div'
+            if @book_id
+              end_book
+              @book_id = nil
+            end
+          end
+        end
+
+        def start_book(attributes)
+          attributes = Hash[attributes]
+          return unless attributes['type'] == 'book'
+          id = attributes['osisID']
+          @book_num += 1
+          @book_id = BOOK_IDS[id] || id.upcase[0..2]
+          @mode = 'book'
+          @book_title = nil
+        end
+
+        def set_book_title(attributes)
+          attributes = Hash[attributes]
+          return unless attributes['type'] == 'main'
+          @book_title = attributes['short']
+        end
+
+        def end_book_title
+          @mode = nil
+        end
+
+        def start_chapter(attributes)
+          attributes = Hash[attributes]
+          if attributes['sID']
+            @chapter = attributes['n'].to_i
+          else
+            end_chapter
+          end
+        end
+
+        def start_verse(attributes)
+          attributes = Hash[attributes]
+          return unless attributes['sID']
+          @verse = attributes['n'].to_i
+          @text = ''
+          @mode = 'verse'
+        end
+
+        def characters(string)
+          case @mode
+          when 'verse'
+            @text << string
+          end
+        end
+      end
+    end
+  end
+end

data/lib/bible_parser/parsers/osis/parser.rb

@@ -0,0 +1,13 @@
+class BibleParser
+  module Parsers
+    module OSIS
+      class Parser < Base::Parser
+        def valid?
+          (@io.read(1024) =~ /<osis.*>/i).tap do
+            @io.rewind
+          end
+        end
+      end
+    end
+  end
+end

data/lib/bible_parser/parsers/usfx.rb

@@ -0,0 +1,2 @@
+require_relative 'usfx/parser'
+require_relative 'usfx/document'

data/lib/bible_parser/parsers/usfx/document.rb

@@ -0,0 +1,90 @@
+require 'nokogiri'
+
+class BibleParser
+  module Parsers
+    module USFX
+      class Document < Base::Document
+        # list of book ids that should be skipped
+        IGNORE_BOOK_IDS = %w(FRT)
+
+        def start_element(name, attributes)
+          case name
+          when 'book'
+            start_book(attributes)
+          when 'h'
+            start_book_title(attributes)
+          when 'c'
+            start_chapter(attributes)
+          when 'v'
+            end_verse if @mode == 'verse'
+            start_verse(attributes)
+          when 've'
+            end_verse
+          when 'f', 'x'
+            start_footnote(attributes)
+          end
+        end
+
+        def end_element(name)
+          case name
+          when 'book'
+            end_book
+            end_verse if @mode == 'verse'
+          when 'c'
+            end_chapter
+            end_verse if @mode == 'verse'
+          when 'h'
+            end_book_title
+          when 'f', 'x'
+            end_footnote
+          end
+        end
+
+        def start_book(attributes)
+          id = Hash[attributes]['id']
+          return if IGNORE_BOOK_IDS.include?(id)
+          @book_num += 1
+          @book_id = id
+          @mode = 'book'
+          @book_title = ''
+        end
+
+        def start_book_title(_attributes)
+          @mode = 'book-title' if @mode == 'book'
+        end
+
+        def end_book_title
+          @book_title.strip! if @book_title
+          @mode = nil
+        end
+
+        def start_chapter(attributes)
+          @chapter = Hash[attributes]['id'].to_i
+        end
+
+        def start_verse(attributes)
+          @verse = Hash[attributes]['id'].to_i
+          @text = ''
+          @mode = 'verse'
+        end
+
+        def start_footnote(_attributes)
+          @mode = "footnote|#{@mode}"
+        end
+
+        def end_footnote
+          @mode = @mode.split('|').last
+        end
+
+        def characters(string)
+          case @mode
+          when 'book-title'
+            @book_title << string.gsub(/\n/, '')
+          when 'verse'
+            @text << string
+          end
+        end
+      end
+    end
+  end
+end

data/lib/bible_parser/parsers/usfx/parser.rb

@@ -0,0 +1,13 @@
+class BibleParser
+  module Parsers
+    module USFX
+      class Parser < Base::Parser
+        def valid?
+          (@io.read(1024) =~ /<usfx.*>/i).tap do
+            @io.rewind
+          end
+        end
+      end
+    end
+  end
+end

data/lib/bible_parser/verse.rb

@@ -0,0 +1,54 @@
+class BibleParser
+  class Verse
+    attr_reader :num, :book_id, :book_num, :book_title, :chapter_num, :text
+
+    def initialize(num:, book_id:, book_num:, book_title:, chapter_num:, text:, parser:)
+      @num = num
+      @book_id = book_id
+      @book_num = book_num
+      @book_title = book_title
+      @chapter_num = chapter_num
+      @text = text
+      @parser = parser
+    end
+
+    def inspect
+      "<#{to_s}>"
+    end
+
+    def to_s
+      "#{book_title} #{chapter_num}:#{num}"
+    end
+
+
+    def book
+      Book.new(
+        id: book_id,
+        num: book_num,
+        title: book_title,
+        parser: @parser
+      )
+    end
+
+    def chapter
+      Chapter.new(
+        book_id: book_id,
+        book_num: book_num,
+        book_title: book_title,
+        num: chapter_num,
+        parser: @parser
+      )
+    end
+
+    def to_h
+      {
+        num:         num,
+        book_id:     book_id,
+        book_num:    book_num,
+        book_title:  book_title,
+        chapter_num: chapter_num,
+        text:        text
+      }
+    end
+  end
+end

metadata

@@ -0,0 +1,101 @@
+--- !ruby/object:Gem::Specification
+name: bible_parser
+version: !ruby/object:Gem::Version
+  version: 1.0.0
+platform: ruby
+authors:
+- Tim Morgan
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2015-05-10 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.6.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.6.0
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 3.2.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 3.2.0
+- !ruby/object:Gem::Dependency
+  name: pry
+  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: 
+email: tim@timmorgan.org
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- README.md
+- lib/bible_parser.rb
+- lib/bible_parser/book.rb
+- lib/bible_parser/chapter.rb
+- lib/bible_parser/errors.rb
+- lib/bible_parser/parsers.rb
+- lib/bible_parser/parsers/base.rb
+- lib/bible_parser/parsers/base/document.rb
+- lib/bible_parser/parsers/base/parser.rb
+- lib/bible_parser/parsers/osis.rb
+- lib/bible_parser/parsers/osis/book_ids.rb
+- lib/bible_parser/parsers/osis/document.rb
+- lib/bible_parser/parsers/osis/parser.rb
+- lib/bible_parser/parsers/usfx.rb
+- lib/bible_parser/parsers/usfx/document.rb
+- lib/bible_parser/parsers/usfx/parser.rb
+- lib/bible_parser/verse.rb
+homepage: https://github.com/seven1m/bible_parser
+licenses: []
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.4.3
+signing_key: 
+specification_version: 4
+summary: Library for parsing the bible in various formats
+test_files: []