pericope 0.6.1 → 0.6.2

data/lib/cli/base.rb

@@ -1,30 +1,30 @@
 module CLI
   class Base
-    
-    
-    
+
+
+
     def self.command(name, description, &block)
-      
+
     end
-    
-    
-    
+
+
+
     def self.print_commands
       usage = ""
-      
+
     end
-    
-    
-    
+
+
+
   private
-    
-    
-    
+
+
+
     def commands
       @commands || {}
     end
-    
-    
-    
+
+
+
   end
-end
+end

data/lib/cli/command.rb

@@ -1,23 +1,23 @@
 module CLI
   class Command
-    
-    
-    
+
+
+
     def initialize(name, description, &block)
       @name, @description, @block = name, description, &block
     end
-    
-    
-    
+
+
+
     attr_reader :name, :description
-    
-    
-    
+
+
+
     def execute
       @block.call
     end
-    
-    
-    
+
+
+
   end
-end
+end

data/lib/pericope.rb

@@ -8,53 +8,57 @@ class Pericope
               :book_name,
               :original_string,
               :ranges
-  
-  
+
+
+
   def self.book_names
-    @book_names ||= ["Genesis", "Exodus", "Leviticus", "Numbers", "Deuteronomy", "Joshua", "Judges", "Ruth", "1 Samuel", "2 Samuel", "1 Kings", "2 Kings", "1 Chronicles", "2 Chronicles", "Ezra", "Nehemiah", "Esther", "Job", "Psalm", "Proverbs", "Ecclesiastes", "Song of Songs", "Isaiah", "Jeremiah", "Lamentations", "Ezekiel", "Daniel",  "Hosea", "Joel", "Amos", "Obadiah", "Jonah", "Micah", "Nahum", "Habakkuk", "Zephaniah", "Haggai", "Zechariah", "Malachi", "Matthew", "Mark", "Luke", "John", "Acts", "Romans", "1 Corinthians", "2 Corinthians", "Galatians", "Ephesians", "Philippians", "Colossians", "1 Thessalonians", "2 Thessalonians", "1 Timothy", "2 Timothy", "Titus", "Philemon", "Hebrews", "James", "1 Peter", "2 Peter", "1 John ", "2 John", "3 John", "Jude", "Revelation"]
+    load_book_abbreviations! unless defined?(@book_names)
+    @book_names
   end
-  
+
   def self.book_name_regexes
-    @book_name_regexes ||= book_abbreviations.map { |book_number, book_regex| [book_number, /\b#{book_regex}\b/] }
+    load_book_abbreviations! unless defined?(@book_name_regexes)
+    @book_name_regexes
   end
-  
-  
-  
+
+
+
   def initialize(arg)
     case arg
     when String
       attributes = Pericope.match_one(arg)
       raise "no pericope found in #{arg} (#{arg.class})" if attributes.nil?
-      
+
       @original_string = attributes[:original_string]
       set_book attributes[:book]
       @ranges = attributes[:ranges]
-      
+
     when Array
+      arg = arg.map(&:to_i)
       set_book Pericope.get_book(arg.first)
       @ranges = Pericope.group_array_into_ranges(arg)
-      
+
     else
       attributes = arg
       @original_string = attributes[:original_string]
       set_book attributes[:book]
       @ranges = attributes[:ranges]
-      
+
     end
   end
-  
-  
-  
+
+
+
   def self.book_has_chapters?(book)
     book_chapter_counts[book - 1] > 1
   end
-  
+
   def book_has_chapters?
     book_chapter_count > 1
   end
-  
-  
-  
+
+
+
   # Differs from Pericope.new in that it won't raise an exception
   # if text does not contain a pericope but will return nil instead.
   def self.parse_one(text)
@@ -63,9 +67,9 @@ class Pericope
     end
     nil
   end
-  
-  
-  
+
+
+
   def self.parse(text)
     pericopes = []
     match_all(text) do |attributes|
@@ -78,39 +82,39 @@ class Pericope
     end
     block_given? ? text : pericopes
   end
-  
-  
-  
+
+
+
   def self.split(text, pattern=nil)
     puts "DEPRECATION NOTICE: split will no longer accept a 'pattern' argument in Pericope 0.7.0" if pattern
     segments = []
     start = 0
-    
+
     match_all(text) do |attributes, match|
-      
+
       pretext = text.slice(start...match.begin(0))
       if pretext.length > 0
         segments << pretext
         yield pretext if block_given?
       end
-      
+
       pericope = Pericope.new(attributes)
       segments << pericope
       yield pericope if block_given?
-      
+
       start = match.end(0)
     end
-    
+
     pretext = text.slice(start...text.length)
     if pretext.length > 0
       segments << pretext
       yield pretext if block_given?
     end
-    
+
     segments = ___split_segments_by_pattern(segments, pattern) if pattern
     segments
   end
-  
+
   def self.___split_segments_by_pattern(segments, pattern)
     segments2 = []
     segments.each do |segment|
@@ -122,9 +126,9 @@ class Pericope
     end
     segments2
   end
-  
-  
-  
+
+
+
   def self.extract(text)
     puts "DEPRECATION NOTICE: the 'extract' method will be removed in Pericope 0.7.0"
     segments = split(text)
@@ -139,9 +143,9 @@ class Pericope
     end
     {:text => text, :pericopes => pericopes}
   end
-  
-  
-  
+
+
+
   def self.sub(text)
     segments = split(text)
     segments.inject("") do |text, segment|
@@ -152,31 +156,31 @@ class Pericope
       end
     end
   end
-  
-  
-  
+
+
+
   def self.rsub(text)
     text.gsub(/\{\{(\d{7,8} ?)+\}\}/) do |match|
       ids = match[2...-2].split.collect(&:to_i)
       Pericope.new(ids).to_s
     end
   end
-  
-  
-  
+
+
+
   def to_s
     "#{book_name} #{self.well_formatted_reference}"
   end
-  
-  
-  
+
+
+
   def report
     puts "DEPRECATION NOTICE: the 'report' method will be removed in Pericope 0.7.0"
     "  #{self.original_string} => #{self}"
   end
-  
-  
-  
+
+
+
   def to_a
     # one range per chapter
     chapter_ranges = []
@@ -195,12 +199,12 @@ class Pericope
         chapter_ranges << Range.new(Pericope.get_first_verse(book, max_chapter), range.end)
       end
     end
-    
+
     chapter_ranges.inject([]) {|array, range| array.concat(range.to_a)}
   end
-  
-  
-  
+
+
+
   def well_formatted_reference
     recent_chapter = nil # e.g. in 12:1-8, remember that 12 is the chapter when we parse the 8
     recent_chapter = 1 unless book_has_chapters?
@@ -210,7 +214,7 @@ class Pericope
       max_chapter = Pericope.get_chapter(range.end)
       max_verse = Pericope.get_verse(range.end)
       s = ""
-      
+
       if min_verse == 1 and max_verse >= Pericope.get_max_verse(book, max_chapter)
         s << min_chapter.to_s
         s << "-#{max_chapter}" if max_chapter > min_chapter
@@ -221,9 +225,9 @@ class Pericope
           recent_chapter = min_chapter
           s << "#{min_chapter}:#{min_verse}"
         end
-        
+
         if range.count > 1
-          
+
           s << "-"
           if min_chapter == max_chapter
             s << max_verse.to_s
@@ -233,124 +237,124 @@ class Pericope
           end
         end
       end
-      
+
       s
     end.join(", ")
   end
-  
-  
-  
+
+
+
   def intersects?(pericope)
     return false unless pericope.is_a?(Pericope)
     return false unless (self.book == pericope.book)
-    
+
     self.ranges.each do |self_range|
       pericope.ranges.each do |other_range|
         return true if (self_range.end >= other_range.begin) and (self_range.begin <= other_range.end)
       end
     end
-    
+
     false
   end
-  
-  
-  
+
+
+
   def self.get_max_verse(book, chapter)
     id = (book * 1000000) + (chapter * 1000)
     chapter_verse_counts[id]
   end
-  
+
   def self.get_max_chapter(book)
     book_chapter_counts[book - 1]
   end
-  
-  
-  
+
+
+
 private
-  
-  
-  
+
+
+
   def set_book(value)
     @book = value || raise(ArgumentError, "must specify book")
     @book_name = Pericope.book_names[@book - 1]
     @book_chapter_count = Pericope.book_chapter_counts[@book - 1]
   end
-  
-  
-  
+
+
+
   def self.get_first_verse(book, chapter)
     get_id(book, chapter, 1)
   end
-  
+
   def self.get_last_verse(book, chapter)
     get_id(book, chapter, get_max_verse(book, chapter))
   end
-  
+
   def self.get_next_verse(id)
     id + 1
   end
-  
+
   def self.get_start_of_next_chapter(id)
     book = get_book(id)
     chapter = get_chapter(id) + 1
     verse = 1
     get_id(book, chapter, verse)
   end
-  
+
   def self.to_valid_book(book)
     coerce_to_range(book, 1..66)
   end
-  
+
   def self.to_valid_chapter(book, chapter)
     coerce_to_range(chapter, 1..get_max_chapter(book))
   end
-  
+
   def self.to_valid_verse(book, chapter, verse)
     coerce_to_range(verse, 1..get_max_verse(book, chapter))
   end
-  
+
   def self.coerce_to_range(number, range)
     return range.begin if number < range.begin
     return range.end if number > range.end
     number
   end
-  
+
   def self.get_id(book, chapter, verse)
     book = to_valid_book(book)
     chapter = to_valid_chapter(book, chapter)
     verse = to_valid_verse(book, chapter, verse)
-    
+
     (book * 1000000) + (chapter * 1000) + verse
   end
-  
+
   def self.get_book(id)
     id / 1000000 # the book is everything left of the least significant 6 digits
   end
-  
+
   def self.get_chapter(id)
     (id % 1000000) / 1000 # the chapter is the 3rd through 6th most significant digits
   end
-  
+
   def self.get_verse(id)
     id % 1000 # the verse is the 3 least significant digits
   end
-  
-  
-  
+
+
+
   def self.group_array_into_ranges(array)
     return [] if array.nil? or array.empty?
-    
+
     array.flatten!
     array.compact!
     array.sort!
-    
+
     ranges = []
     range_start = array.shift
     range_end = range_start
     while true
       next_value = array.shift
       break if next_value.nil?
-      
+
       if (next_value == get_next_verse(range_end)) ||
          (next_value == get_start_of_next_chapter(range_end))
         range_end = next_value
@@ -360,12 +364,12 @@ private
       end
     end
     ranges << (range_start..range_end)
-    
+
     ranges
   end
-  
-  
-  
+
+
+
   # matches the first valid Bible reference in the supplied string
   def self.match_one(text)
     match_all(text) do |attributes|
@@ -373,30 +377,30 @@ private
     end
     nil
   end
-  
-  
-  
+
+
+
   # matches all valid Bible references in the supplied string
   def self.match_all(text)
     text.scan(Pericope::PERICOPE_PATTERN) do
       match = Regexp.last_match
-      
+
       book = recognize_book(match[1])
       next unless book
-      
+
       ranges = parse_reference(book, match[2])
       next if ranges.empty?
-      
+
       attributes = {
         :original_string => match.to_s,
         :book => book,
         :ranges => ranges
       }
-      
+
       yield attributes, match
     end
   end
-  
+
   def self.recognize_book(book)
     book = book.to_s.downcase
     book_name_regexes.each do |book_regex|
@@ -404,18 +408,18 @@ private
     end
     nil
   end
-  
+
   def self.parse_reference(book, reference)
     reference = normalize_reference(reference)
     parse_ranges(book, reference.split(/[,;]/))
   end
-  
+
   def self.normalize_reference(reference)
     reference = reference.to_s
     NORMALIZATIONS.each { |(regex, replacement)| reference.gsub!(regex, replacement) }
     reference
   end
-  
+
   def self.parse_ranges(book, ranges)
     recent_chapter = nil # e.g. in 12:1-8, remember that 12 is the chapter when we parse the 8
     recent_chapter = 1 if !book_has_chapters?(book)
@@ -424,14 +428,14 @@ private
       range << range[0] if (range.length < 2) # treat 12:4 as 12:4-12:4
       lower_chapter_verse = range[0].split(':').map(&:to_i) # parse "3:28" to [3,28]
       upper_chapter_verse = range[1].split(':').map(&:to_i) # parse "3:28" to [3,28]
-      
+
       # treat Mark 3-1 as Mark 3-3 and, eventually, Mark 3:1-35
       if (lower_chapter_verse.length == 1) &&
          (upper_chapter_verse.length == 1) &&
          (upper_chapter_verse[0] < lower_chapter_verse[0])
         upper_chapter_verse = lower_chapter_verse.dup
       end
-      
+
       # make sure the low end of the range and the high end of the range
       # are composed of arrays with two appropriate values: [chapter, verse]
       chapter_range = false
@@ -447,7 +451,7 @@ private
         lower_chapter_verse[0] = Pericope.to_valid_chapter(book, lower_chapter_verse[0])
       end
       lower_chapter_verse[1] = Pericope.to_valid_verse(book, *lower_chapter_verse)
-      
+
       if upper_chapter_verse.length < 2
         if chapter_range
           upper_chapter_verse[0] = Pericope.to_valid_chapter(book, upper_chapter_verse[0])
@@ -459,147 +463,91 @@ private
         upper_chapter_verse[0] = Pericope.to_valid_chapter(book, upper_chapter_verse[0])
       end
       upper_chapter_verse[1] = Pericope.to_valid_verse(book, *upper_chapter_verse)
-      
+
       recent_chapter = upper_chapter_verse[0] # remember the last chapter
-      
+
       Range.new(
         Pericope.get_id(book, *lower_chapter_verse),
         Pericope.get_id(book, *upper_chapter_verse))
     end
   end
-  
-  
-  
-  def self.load_chapter_verse_counts
+
+
+
+  def self.load_chapter_verse_count_books!
+    current_book_id = nil
+    chapters = 0
+    @chapter_verse_counts = {}
+    @book_chapter_counts = []
+
     path = File.expand_path(File.dirname(__FILE__) + "/../data/chapter_verse_count.txt")
-    chapter_verse_counts = []
     File.open(path) do |file|
       file.each do |text|
-        chapter_verse_counts << text.chomp.split("\t")[0..1].map(&:to_i)
+        row = text.chomp.split("\t")
+        id, verses = row[0].to_i, row[1].to_i
+        book_id = get_book(id)
+
+        @chapter_verse_counts[id] = verses
+
+        unless current_book_id == book_id
+          @book_chapter_counts.push chapters if current_book_id
+          current_book_id = book_id
+        end
+
+        chapters = get_chapter(id)
       end
     end
-    Hash[chapter_verse_counts]
+
+    @book_chapter_counts.push chapters
   end
-  
-  
-  
-  def self.load_book_abbreviations
+
+
+
+  def self.load_book_abbreviations!
+    @book_names = []
+    @book_name_regexes = {}
+
     path = File.expand_path(File.dirname(__FILE__) + "/../data/book_abbreviations.txt")
-    book_abbreviations = []
     File.open(path) do |file|
       file.each do |text|
-        unless text.start_with?("#") # skip comments
-          
-          # the file contains tab-separated values.
-          # the first value is the ordinal of the book, subsequent values
-          # represent abbreviations and misspellings that should be recognized
-          # as the aforementioned book.
-          segments = text.chomp.split("\t")
-          book_abbreviations << [segments.shift.to_i, "(?:#{segments.join("|")})"]
-        end
+        next if text.start_with?("#") # skip comments
+
+        # the file contains tab-separated values.
+        # the first value is the ordinal of the book, subsequent values
+        # represent abbreviations and misspellings that should be recognized
+        # as the aforementioned book.
+        segments = text.chomp.split("\t")
+        book_id = segments.shift.to_i
+        @book_names[book_id - 1] = segments.shift
+        @book_name_regexes[book_id] = /\b(?:#{segments.join("|")})\b/
       end
     end
-    Hash[book_abbreviations]
   end
-  
-  
-  
+
+
+
   def self.chapter_verse_counts
-    @chapter_verse_counts ||= load_chapter_verse_counts
+    load_chapter_verse_count_books! unless defined?(@chapter_verse_counts)
+    @chapter_verse_counts
   end
-  
-  
-  
-  def self.book_abbreviations
-    @book_abbreviations ||= load_book_abbreviations
-  end
-  
-  
-  
+
+
+
   def self.book_chapter_counts
-    @book_chapter_counts ||= [
-    # Chapters    Book Name        Book Number
-      50,       # Genesis          1
-      40,       # Exodus           2
-      27,       # Leviticus        3
-      36,       # Numbers          4
-      34,       # Deuteronomy      5
-      24,       # Joshua           6
-      21,       # Judges           7
-      4,        # Ruth             8
-      31,       # 1 Samuel         9
-      24,       # 2 Samuel        10
-      22,       # 1 Kings         11
-      25,       # 2 Kings         12
-      29,       # 1 Chronicles    13
-      36,       # 2 Chronicles    14
-      10,       # Ezra            15
-      13,       # Nehemiah        16
-      10,       # Esther          17
-      42,       # Job             18
-      150,      # Psalm           19
-      31,       # Proverbs        20
-      12,       # Ecclesiastes    21
-      8,        # Song of Songs   22
-      66,       # Isaiah          23
-      52,       # Jeremiah        24
-      5,        # Lamentations    25
-      48,       # Ezekiel         26
-      12,       # Daniel          27
-      14,       # Hosea           28
-      3,        # Joel            29
-      9,        # Amos            30
-      1,        # Obadiah         31
-      4,        # Jonah           32
-      7,        # Micah           33
-      3,        # Nahum           34
-      3,        # Habakkuk        35
-      3,        # Zephaniah       36
-      2,        # Haggai          37
-      14,       # Zechariah       38
-      4,        # Malachi         39
-      28,       # Matthew         40
-      16,       # Mark            41
-      24,       # Luke            42
-      21,       # John            43
-      28,       # Acts            44
-      16,       # Romans          45
-      16,       # 1 Corinthians   46
-      13,       # 2 Corinthians   47
-      6,        # Galatians       48
-      6,        # Ephesians       49
-      4,        # Philippians     50
-      4,        # Colossians      51
-      5,        # 1 Thessalonians 52
-      3,        # 2 Thessalonians 53
-      6,        # 1 Timothy       54
-      4,        # 2 Timothy       55
-      3,        # Titus           56
-      1,        # Philemon        57
-      13,       # Hebrews         58
-      5,        # James           59
-      5,        # 1 Peter         60
-      3,        # 2 Peter         61
-      5,        # 1 John          62
-      1,        # 2 John          63
-      1,        # 3 John          64
-      1,        # Jude            65
-      22]       # Revelation      66
-  end
-  
-  
+    load_chapter_verse_count_books! unless defined?(@book_chapter_counts)
+    @book_chapter_counts
+  end
+
+
   BOOK_PATTERN = /\b(?:(?:1|2|3|i+|first|second|third|1st|2nd|3rd) )?(?:\w+| of )\b/
-  
+
   REFERENCE_PATTERN = '(?:\s*\d{1,3})(?:\s*[:\"\.]\s*\d{1,3}[ab]?(?:\s*[,;]\s*(?:\d{1,3}[:\"\.])?\s*\d{1,3}[ab]?)*)?(?:\s*[-–—]\s*(?:\d{1,3}\s*[:\"\.])?(?:\d{1,3}[ab]?)(?:\s*[,;]\s*(?:\d{1,3}\s*[:\"\.])?\s*\d{1,3}[ab]?)*)*'
-  
+
   PERICOPE_PATTERN = /(#{BOOK_PATTERN})\.? (#{REFERENCE_PATTERN})/i
-  
+
   NORMALIZATIONS = [
     [/(\d+)[".](\d+)/, '\1:\2'], # 12"5 and 12.5 -> 12:5
     [/[–—]/,           '-'],     # convert em dash and en dash to -
     [/[^0-9,:;\-–—]/,  '']       # remove everything but [0-9,;:-]
   ]
-  
-  
-  
 end