scripref 1.2.2 → 2.1.0

data/lib/scripref/parser.rb

@@ -6,7 +6,7 @@ require 'strscan'
 
 module Scripref
 
-  class Parser < StringScanner
+  class Parser
 
     attr_reader :error
 
@@ -21,12 +21,28 @@ module Scripref
     # Parsing a string of a scripture reference
     # @param str string to parse
     def parse str
-      self.string = str
+      @scanner = StringScanner.new(str)
       @result = []
       @error = nil
       start
     end
 
+    def format_error
+      if error
+        format("%s\n%s\n%s^", error, @scanner.string, ' ' * @scanner.pointer)
+      else
+        ''
+      end
+    end
+
+    def inspect
+      "#<#{self.class} #{@mods.inspect}>"
+    end
+
+    alias << parse
+
+    private
+
     # start of parsing grammer
     def start
       @text = ''
@@ -35,14 +51,14 @@ module Scripref
 
     # try to parse first book
     def b1
-      s = scan(book_re) or return nil
+      s = @scanner.scan(book_re) or return nil
       @text << s
-      @b1 = @b2 = abbrev2osis_book_id(s)
+      @b1 = @b2 = str2book_id(s)
       @c1 = @v1 = @c2 = @v2 = nil
 
       if pass_sep
         b1 or give_up 'EOS or book expected!'
-      elsif check(Regexp.new(chapter_re.source + cv_sep_re.source))
+      elsif @scanner.check(Regexp.new(chapter_re.source + cv_sep_re.source))
         @c1 = @v1 = nil
         @c2 = @v2 = nil
         c1
@@ -60,7 +76,7 @@ module Scripref
 
     # try parse first chapter
     def c1
-      s = scan(chapter_re) or return nil
+      s = @scanner.scan(chapter_re) or return nil
       @text << s
       @c1 = @c2 = s.to_i
       @v1 = @v2 = nil
@@ -78,7 +94,7 @@ module Scripref
 
     # try to parse first verse
     def v1
-      s = scan(verse_re) or return nil
+      s = @scanner.scan(verse_re) or return nil
       @text << s
       @v1 = @v2 = s.to_i
 
@@ -92,7 +108,7 @@ module Scripref
 
       if hyphen
         b2 or (
-        if check(Regexp.new(chapter_re.source + cv_sep_re.source))
+        if @scanner.check(Regexp.new(chapter_re.source + cv_sep_re.source))
           c2
         else
           v2 or give_up 'Chapter or verse expected!'
@@ -108,14 +124,14 @@ module Scripref
 
     # try to parse second book
     def b2
-      s = scan(book_re) or return nil
+      s = @scanner.scan(book_re) or return nil
       @text << s
-      @b2 = abbrev2osis_book_id(s)
+      @b2 = str2book_id(s)
       @c2 = @v2 = nil
 
       if pass_sep
         b1 or give_up 'EOS or book expected!'
-      elsif check(Regexp.new(chapter_re.source + cv_sep_re.source))
+      elsif @scanner.check(Regexp.new(chapter_re.source + cv_sep_re.source))
         c2
       else
         if book_has_only_one_chapter?(@b2)
@@ -129,7 +145,7 @@ module Scripref
 
     # try to parse second chapter
     def c2
-      s = scan(chapter_re) or return nil
+      s = @scanner.scan(chapter_re) or return nil
       @text << s
       @c2 = s.to_i
 
@@ -144,7 +160,7 @@ module Scripref
 
     # try to parse second verse
     def v2
-      s = scan(verse_re) or return nil
+      s = @scanner.scan(verse_re) or return nil
       @text << s
       @v2 = s.to_i
 
@@ -163,16 +179,16 @@ module Scripref
 
     # try to parse <tt>end of string</tt>
     def epsilon
-      if eos?
+      if @scanner.eos?
         push_passage
         return @result
       end
       nil
     end
 
-    # try to parse separator or chapter and verse
+    # try to parse separator of chapter and verse
     def cv_sep
-      if s = scan(cv_sep_re)
+      if s = @scanner.scan(cv_sep_re)
         @text << s
         s
       else
@@ -182,7 +198,7 @@ module Scripref
 
     # try to parse hyphen
     def hyphen
-      if s = scan(hyphen_re)
+      if s = @scanner.scan(hyphen_re)
         @text << s
         s
       else
@@ -192,7 +208,7 @@ module Scripref
 
     # try to parse separator between passages
     def pass_sep
-      if s = scan(pass_sep_re)
+      if s = @scanner.scan(pass_sep_re)
         push_passage
         @result << PassSep.new(s)
         s
@@ -203,7 +219,7 @@ module Scripref
 
     # try to parse verse separator
     def verse_sep
-      if s = scan(verse_sep_re)
+      if s = @scanner.scan(verse_sep_re)
         push_passage
         @result << VerseSep.new(s)
         s
@@ -214,7 +230,7 @@ module Scripref
 
     # try to parse addons for verses
     def verse_addon
-      if s = scan(verse_addon_re)
+      if s = @scanner.scan(verse_addon_re)
         @text << s
         s.to_sym
       else
@@ -224,7 +240,7 @@ module Scripref
 
     # try to parse postfixes for verse
     def verse_postfix
-      s = (scan(postfix_one_following_verse_re) or scan(postfix_more_following_verses_re))
+      s = (@scanner.scan(postfix_one_following_verse_re) or @scanner.scan(postfix_more_following_verses_re))
       if s
         @text << s
         s.to_sym
@@ -239,48 +255,43 @@ module Scripref
       @a1 = @a2 = nil
     end
 
-    def abbrev2osis_book_id str
+    def str2book_id str
       s = str.strip
       s.sub! /\.$/, ''
-      str2osis_book_id(s) or str2osis_book_id(abbrev2book(s))
+      str2book_id_cache(s) or calculate_str2book_id(s)
     end
 
-    def abbrev2book str
+    def calculate_str2book_id str
       s = str.strip
       s.sub! /\.$/, ''
-      @books_str ||= ('#' << book_names.map(&:names).flatten.join('#') << '#')
+      @books_str ||= ('#' << each_bookname.map(&:each_name).flat_map(&:to_a).join('#') << '#')
       pattern = s.chars.map {|c| Regexp.escape(c) << '[^#]*'}.join
       re = /(?<=#)#{pattern}(?=#)/
       names = @books_str.scan(re)
-      uniq_numbers = names.map {|n| str2osis_book_id(n)}.uniq
+      uniq_numbers = names.map {|n| str2book_id_cache(n)}.uniq
       if uniq_numbers.size != 1
-        unscan
+        @scanner.unscan
         give_up format("Abbreviation %s is ambiguous it matches %s!", s, names.join(', '))
       end
-      names.first
+      book_id = str2book_id_cache(names.first)
+      @str2book_id_cache[s] = book_id
+      book_id
     end
 
-    def init_str2osis_book_id
-      unless @str2osis_book_id
-        @str2osis_book_id = {}
-        book_names.each do |bn|
-          bn.names.each do |n|
-            @str2osis_book_id[n] = bn.osis_id
-          end
-          bn.abbrevs.each do |n|
-            @str2osis_book_id[n] = bn.osis_id
+    def init_str2book_id_cache
+      unless @str2book_id_cache
+        @str2book_id_cache = {}
+        each_bookname do |bn|
+          bn.each_string do |s|
+            @str2book_id_cache[s] = bn.book_id
           end
         end
       end
     end
 
-    def str2osis_book_id str
-      init_str2osis_book_id
-      @str2osis_book_id[str]
-    end
-
-    def inspect
-      "#<#{self.class} #{@mods.inspect}>"
+    def str2book_id_cache str
+      init_str2book_id_cache
+      @str2book_id_cache[str]
     end
 
     def give_up msg
@@ -288,16 +299,6 @@ module Scripref
       fail ParserError, format_error
     end
 
-    def format_error
-      if error
-        format("%s\n%s\n%s^", error, string, ' ' * pointer)
-      else
-        ''
-      end
-    end
-
-    alias << parse
-
   end
 
   class ParserError < RuntimeError; end

data/lib/scripref/passage.rb

@@ -5,70 +5,17 @@ module Scripref
 
   Passage = Struct.new(:text, :b1, :c1, :v1, :b2, :c2, :v2, :a1, :a2, keyword_init: true) do
 
-    include Comparable
-
     def to_a
-      [b1, c1, v1, b2, c2, v2]
-    end
-
-    def <=> other
-      return unless other.kind_of? Passage
-      self.to_numeric_array <=> other.to_numeric_array
-    end
-
-    # Returns true if the instance and the given passage overlap.
-    # That means both has at least one verse in common.
-    def overlap? passage
-      fail ArgumentError, 'value must be a passage' unless passage.kind_of? Passage
-      a = self.to_numeric_array
-      b = passage.to_numeric_array
-      [a[0..2] <=> b[3..5], b[0..2] <=> a[3..5]].max < 1
-    end
-
-    # Returns an array of b1, c1, v1
-    def start
-      [b1, c1, v1]
+      [b1, c1, v1, a1, b2, c2, v2, a2]
     end
 
-    # Returns an array of b2, c2, v2
-    def end
-      [b2, c2, v2]
-    end
-
-    def to_numeric_array max: 999, ff: 3
-      _b1 = Passage.book_id2num[b1]
-      _c1 = c1 || 1
-      _v1 = v1 || 1
-      _b2 = Passage.book_id2num[b2]
-      _c2 = c2 || max
-      _v2 = v2 || max
-      if _v2 == :f
-        _v2 = _v1 + 1
-      end
-      if _v2 == :ff
-        _v2 = _v1 + ff
-      end
-      [_b1, _c1, _v1, _b2, _c2, _v2]
+    def == other
+      return false unless other.kind_of? Passage
+      to_a == other.to_a
     end
 
     alias to_s text
 
-    @book_id2num = {}
-    osis_book_ids = %i[
-      Gen Exod Lev Num Deut Josh Judg Ruth 1Sam 2Sam 1Kgs 2Kgs 1Chr 2Chr Ezra
-      Neh Esth Job Ps Prov Eccl Song Isa Jer Lam Ezek Dan Hos Joel Amos Obad
-      Jonah Mic Nah Hab Zeph Hag Zech Mal Matt Mark Luke John Acts Rom 1Cor
-      2Cor Gal Eph Phil Col 1Thess 2Thess 1Tim 2Tim Titus Phlm Heb Jas 1Pet
-      2Pet 1John 2John 3John Jude Rev
-    ]
-    osis_book_ids.each_with_index do |book_id, i|
-      @book_id2num[book_id] = i+1
-    end
-
-    class << self
-      attr_reader :book_id2num
-    end
-
   end
 
 end

data/lib/scripref/processor.rb

@@ -71,6 +71,8 @@ module Scripref
       @reference_re = Regexp.compile(re_parts.join, nil)
     end
 
+    private
+
     def fix_scanner_and_results scanner
       text = scanner[1]
       ref = scanner[2]

data/lib/scripref/sorter.rb

@@ -0,0 +1,85 @@
+# encoding: utf-8
+# frozen_string_literal: true
+
+module Scripref
+
+  class Sorter
+
+    def initialize *mods
+      @mods = mods
+      mods.each {|m| extend m}
+    end
+
+    def sort *references
+      passages = references.flatten.select {|e| e.kind_of? Scripref::Passage}
+      passages.sort do |p1, p2|
+        signum(p1, p2)
+      end
+    end
+
+    alias << sort
+
+    # Mixin to sort ascending by start verse and desending by end verse of passages
+    module SortUpDown
+      def signum pass1, pass2
+        a, b = passage2arr(pass1), passage2arr(pass2)
+        a[0, 4] + b[4, 4] <=> b[0, 4] + a[4, 4]
+      end
+    end
+
+    # Mixin to sort ascending by start verse and ascending by end verse of passages
+    module SortUpUp
+      def signum pass1, pass2
+        a, b = passage2arr(pass1), passage2arr(pass2)
+        a <=> b
+      end
+    end
+
+    # Default sorting
+
+    include SortUpDown
+
+    private
+
+    def passage2arr pass
+      b1 = book2num(pass.b1)
+      c1 = pass.c1 || 1
+      v1 = pass.v1 || 1
+      a1 = case pass.a1.to_s
+           when ''
+             0
+           when 'a'
+             1
+           when 'b'
+             2
+           when 'c'
+             3
+           end
+      b2 = book2num(pass.b2)
+      c2 = pass.c2 || Float::INFINITY
+      v2 = case pass.v2
+           when nil
+             Float::INFINITY
+           when Integer
+             pass.v2
+           when :f
+             pass.v1.to_i + 1
+           when :ff
+             pass.v1.to_i + 3
+           end
+      a2 = case pass.a2.to_s
+           when ''
+             0
+           when 'a'
+             -3
+           when 'b'
+             -2
+           when 'c'
+             -1
+           end
+      [b1, c1, v1, a1, b2, c2, v2, a2]
+    end
+
+  end
+
+end

data/lib/scripref.rb

@@ -5,7 +5,7 @@ require 'delegate'
 
 module Scripref
 
-  VERSION = '1.2.2'
+  VERSION = '2.1.0'
 
   require_relative 'scripref/bookname'
   require_relative 'scripref/bookorder'
@@ -15,6 +15,7 @@ module Scripref
   require_relative 'scripref/parser'
   require_relative 'scripref/passage'
   require_relative 'scripref/processor'
+  require_relative 'scripref/sorter'
 
   class Token < DelegateClass(String)
     def initialize *args

data/test/test_bookname.rb

@@ -8,15 +8,23 @@ class TestBookname < Test::Unit::TestCase
   include Scripref
 
   def setup
-    @zef = Bookname.new(osis_id: :Zeph, names: %w(Zefanja Zephanja), abbrevs: %w(Zef Zefan Zeph Zephan))
+    @zef = Bookname.new(book_id: :Zeph, name: 'Zefanja', abbrevs: %w(Zefan Zef), alternatives: Bookname.new(book_id: :Zeph, name: 'Zephanja', abbrevs: 'Zeph'))
   end
 
-  def test_name
-    assert_equal 'Zefanja', @zef.name
+  def test_each_name
+    assert_equal %w(Zefanja Zephanja), @zef.each_name.to_a
   end
 
-  def test_abbrev
-    assert_equal 'Zef', @zef.abbrev
+  def test_each_string
+    assert_equal %w(Zefanja Zefan Zef Zephanja Zeph), @zef.each_string.to_a
+  end
+
+  def test_parse
+    assert_equal @zef, Bookname.parse('Zeph: Zefanja|Zefan|Zef, Zephanja|Zeph')
+  end
+
+  def test_dump
+    assert_equal 'Zeph: Zefanja|Zefan|Zef, Zephanja|Zeph', @zef.dump
   end
 
 end

data/test/test_english.rb

@@ -13,7 +13,7 @@ class TestEnglish < Test::Unit::TestCase
   end
 
   def test_size_of_book_array
-    assert_equal 66, English::BOOK_NAMES.size
+    assert_equal 66, English::BOOKNAMES_HASH.size
   end
 
   def test_book_re
@@ -32,20 +32,20 @@ class TestEnglish < Test::Unit::TestCase
     assert_match book_re, 'Rev'
   end
 
-  def test_book2osis_id
-    assert_osis_book_id :Gen, 'Genesis'
-    assert_osis_book_id :Matt, 'Matthew'
-    assert_osis_book_id :Rev, 'Revelation'
-    assert_osis_book_id :Gen, 'Gen'
-    assert_osis_book_id :Gen, 'Ge'
-    assert_osis_book_id :'2Tim', '2 Tim'
-    assert_osis_book_id :'2Tim', '2Tim'
-    assert_osis_book_id :'2Tim', '2Tm'
-    assert_osis_book_id :Matt, 'Mat'
-    assert_osis_book_id :Rev, 'Rev'
+  def test_book2book_id
+    assert_book_id :Gen, 'Genesis'
+    assert_book_id :Matt, 'Matthew'
+    assert_book_id :Rev, 'Revelation'
+    assert_book_id :Gen, 'Gen'
+    assert_book_id :Gen, 'Ge'
+    assert_book_id :'2Tim', '2 Tim'
+    assert_book_id :'2Tim', '2Tim'
+    assert_book_id :'2Tim', '2Tm'
+    assert_book_id :Matt, 'Mat'
+    assert_book_id :Rev, 'Rev'
   end
 
-  def assert_osis_book_id id, str
+  def assert_book_id id, str
     assert_equal id, @parser.parse(str).first.b1
   end
 

data/test/test_formatter.rb

@@ -170,7 +170,8 @@ class TestFormatter < Test::Unit::TestCase
 
   def test_two_refs_with_book_with_only_one_chapter
     text = 'Obadja 3.5'
-    assert_formated_text_for_ast text, [pass(text: text, b1: :Obad, c1: 1, v1: 3, b2: :Obad, c2: 1, v2: 3), pass(b1: :Obad, c1: 1, v1: 5, b2: :Obad, c2: 1, v2: 5)]
+    t1, t2 = text.split(dot)
+    assert_formated_text_for_ast text, [pass(text: t1, b1: :Obad, c1: 1, v1: 3, b2: :Obad, c2: 1, v2: 3), dot, pass(text: t2, b1: :Obad, c1: 1, v1: 5, b2: :Obad, c2: 1, v2: 5)]
   end
 
   ######################################################################
@@ -261,18 +262,12 @@ class TestFormatter < Test::Unit::TestCase
   ######################################################################
 
   def test_formatting_with_book_abbrevs
-    @german_formatter.bookformat = :abbrev
+    @german_formatter.abbrev_level = 1
     text = 'Mat 3,4; Mar; Joh 3,16'
     t1, t2, t3 = text.split(semi)
     assert_formated_text_for_ast text, [pass(text: t1, b1: :Matt, c1: 3, v1: 4, b2: :Matt, c2: 3, v2: 4), semi, pass(text: t2, b1: :Mark, b2: :Mark), semi, pass(text: t3, b1: :John, c1: 3, v1: 16, b2: :John, c2: 3, v2: 16)]
   end
 
-  def test_exception_for_unhandled_bookformat
-    assert_raise NoMethodError do
-      @german_formatter.bookformat = :unknown
-      @german_formatter.format [pass(text: 1, b1: :Exod, c1: 3, v1: 4, b2: :Deut, c2: 6, v2: 7)]
-    end
-  end
   private
 
   def assert_formated_text_for_ast text, ast

data/test/test_german.rb

@@ -13,7 +13,7 @@ class TestGerman < Test::Unit::TestCase
   end
 
   def test_size_of_book_array
-    assert_equal 66, German::BOOK_NAMES.size
+    assert_equal 66, German::BOOKNAMES_HASH.size
   end
 
   def test_book_re
@@ -32,19 +32,19 @@ class TestGerman < Test::Unit::TestCase
     assert_match book_re, 'Off'
   end
 
-  def test_book2osis_id
-    assert_osis_book_id :Gen, '1. Mose'
-    assert_osis_book_id :Matt, 'Matthäus'
-    assert_osis_book_id :Rev, 'Offenbarung'
-    assert_osis_book_id :Gen, '1. Mo'
-    assert_osis_book_id :Gen, '1.Mo'
-    assert_osis_book_id :Gen, '1M'
-    assert_osis_book_id :Matt, 'Mat'
-    assert_osis_book_id :Phil, 'Phil'
-    assert_osis_book_id :Rev, 'Off'
+  def test_book2book_id
+    assert_book_id :Gen, '1. Mose'
+    assert_book_id :Matt, 'Matthäus'
+    assert_book_id :Rev, 'Offenbarung'
+    assert_book_id :Gen, '1. Mo'
+    assert_book_id :Gen, '1.Mo'
+    assert_book_id :Gen, '1M'
+    assert_book_id :Matt, 'Mat'
+    assert_book_id :Phil, 'Phil'
+    assert_book_id :Rev, 'Off'
   end
 
-  def assert_osis_book_id id, str
+  def assert_book_id id, str
     @parser ||= Scripref::Parser.new(Scripref::German)
     assert_equal id, @parser.parse(str).first.b1
   end

data/test/test_parser.rb

@@ -333,6 +333,17 @@ class TestParser < Test::Unit::TestCase
     assert_parsed_ast_for_text [pass(text: text, b1: :Ps, c1: 23, v1: 6, b2: :Ps, c2: 23, v2: 6)], text
   end
 
+  def test_alternatives
+    # In German Zephanja is alternative name for Zefanja
+    a = pass(b1: :Zeph, c1: 2, b2: :Zeph, c2: 2).to_a
+    assert_equal a, @parser.parse('Zefanja 2').first.to_a
+    assert_equal a, @parser.parse('Zefa 2').first.to_a
+    assert_equal a, @parser.parse('Zef 2').first.to_a
+    assert_equal a, @parser.parse('Zephanja 2').first.to_a
+    assert_equal a, @parser.parse('Zepha 2').first.to_a
+    assert_equal a, @parser.parse('Zeph 2').first.to_a
+  end
+
   private
 
   def assert_equal_passage expected, actual

data/test/test_processor.rb

@@ -83,7 +83,7 @@ class TestProcessorVariousContexts < Test::Unit::TestCase
   def test_verse_addon_or_postfix
     text = 'Mt 1,1a'
     processor = Processor.new(text, German)
-    ast = [[pass(text: text, b1: :Matt, c1: 1, v1: 1, b2: :Matt, c2: 1, v2: 1, a1: 'a')]]
+    ast = [[pass(text: text, b1: :Matt, c1: 1, v1: 1, b2: :Matt, c2: 1, v2: 1, a1: :a)]]
     assert_equal ast, processor.each.to_a
     text = 'Mt 1,1f'
     processor = Processor.new(text, German)
@@ -98,7 +98,7 @@ class TestProcessorVariousContexts < Test::Unit::TestCase
   def test_verse_addon_or_postfix_for_books_with_only_one_chapter
     text = '2. Joh 5b'
     processor = Processor.new(text, German)
-    ast = [[pass(text: text, b1: :'2John', c1: 1, v1: 5, b2: :'2John', c2: 1, v2: 5, a1: 'b')]]
+    ast = [[pass(text: text, b1: :'2John', c1: 1, v1: 5, b2: :'2John', c2: 1, v2: 5, a1: :b)]]
     assert_equal ast, processor.each.to_a
     text = '2. Joh 5f'
     processor = Processor.new(text, German)