scripref 0.10.0 → 0.11.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 605d0d995b512d6af69e3b2152228dc201085b2b
-  data.tar.gz: a400e265c6d777d287170fbef3edb56c0143fcc6
+  metadata.gz: 223ae6028e566b369b6848eef6374fe2bc52706a
+  data.tar.gz: 6b9f27eee78bc4c6ca03254851e80911a9846da6
 SHA512:
-  metadata.gz: 37506e93da2d733beaa800db74ef5d1f16fe7aee313312298752a3f442549434b5360646b62d7d754dc189efa6edf1b09372be04b0a85e8f39dca290f2082b1a
-  data.tar.gz: 1e74214d77ed1f74256c102ea448eba2ba703d90269dc697360494dee102900d9f2503c8310f95ce783d1c92512a9eacba62e734adb8e411729d28dacccf3f98
+  metadata.gz: 2f85ed0888401fb880980fd31552720e23494ae879cc6dbc9834dc36d2ffaca33fdbaf62fa4f8856c9bc2754820c53e5701cf6ca44fb73172d452f139916d927
+  data.tar.gz: 6261f6a48f837d69701270e0083758ded7b3a47c26eb7a4e48f5b345ce9a8ddfc1ca228afea8ac692c2ad208eaa7c625aae87f469a33d0a0c804859ad9b0383a

data/Changelog

@@ -1,3 +1,9 @@
+0.11.0
+Add class Bookname and methods Passage#+ and Passage#-.
+Make processor working for complex contexts.
+Use autoload.
+Lots of refactorings and internal improvements.
+
 0.10.0
 Add methods Passage#make_comparable, #make_comparable!, #comparable?,
 #overlap?, #start, #end and #<=>.

data/LICENSE

@@ -1,4 +1,4 @@
-Copyright (c) 2010-2016 Jan Friedrich
+Copyright (c) 2010-2017 Jan Friedrich
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

data/Rakefile

@@ -12,4 +12,8 @@ Rim.setup do
   homepage 'https://github.com/janfri/scripref'
   version Scripref::VERSION
   summary 'Library for parsing scripture references in real texts.'
+  if feature_loaded? 'rim/irb'
+    irb_requires %w(scripref scripref/include scripref/pipelining)
+  end
+  test_warning false
 end

data/lib/scripref/basic_methods.rb

@@ -0,0 +1,32 @@
+# - encoding: utf-8 -
+module Scripref
+
+  # Mixin with methods of basic functionality
+  module BasicMethods
+
+    NUMBER_RE = /\d+\s*/o
+
+    # Regular expression to match a chapter
+    def chapter_re
+      NUMBER_RE
+    end
+
+    # Regular expression to match a verse
+    def verse_re
+      NUMBER_RE
+    end
+
+    # Regular expression to match a book.
+    def book_re
+      return @book_re if @book_re
+      books_res_as_strings = book_names.map do |bn|
+        bn.names.map do |n|
+          (n.gsub(/([^\dA-Z])/, '\1?').gsub('.', '\.'))
+        end
+      end.flatten
+      @book_re = Regexp.compile(books_res_as_strings.map {|s| '(\b' << s << '\b\s*)' }.join('|'), nil)
+    end
+
+  end
+
+end

data/lib/scripref/bookname.rb

@@ -0,0 +1,30 @@
+# - encoding: utf-8 -
+
+module Scripref
+
+  class Bookname
+
+    attr_reader :names, :abbrevs
+
+    def initialize names, abbrevs
+      @names = Array(names)
+      @abbrevs = Array(abbrevs)
+    end
+
+    def name
+      @names.first
+    end
+
+    def abbrev level=0
+      @abbrevs[level] || @abbrevs[-1]
+    end
+
+    def to_s
+      @names.first
+    end
+
+    alias to_str to_s
+
+  end
+
+end

data/lib/scripref/english.rb

@@ -1,4 +1,5 @@
 # - encoding: utf-8 -
+require 'scripref/bookname'
 require 'scripref/const_reader'
 
 module Scripref
@@ -6,8 +7,7 @@ module Scripref
   # Mixin for parsing references in English.
   module English
 
-    # Array of book names.
-    BOOK_NAMES = <<-END.strip.split(/,\s*/)
+    book_names = <<-END.strip.split(/,\s*/)
       Genesis, Exodus, Leviticus, Numbers, Deuteronomy, Joshua, Judges,
       Ruth, 1 Samuel, 2 Samuel, 1 Kings, 2 Kings, 1 Chronicles,
       2 Chronicles, Ezra, Nehemiah, Esther, Job, Psalms, Proverbs,
@@ -21,6 +21,18 @@ module Scripref
       Jude, Revelation
     END
 
+    book_abbrevs = <<-END.strip.split(/,\s*/)
+      Gen, Ex, Lev, Num, Deut, Josh, Judg, Rth, 1 Sam, 2 Sam, 1 Kgs, 2 Kgs,
+      1 Chron, 2 Chron, Ezr, Neh, Esth, Job, Ps, Prov, Eccles, Song, Isa,
+      Jer, Lam, Ezek, Dan, Hos, Joel, Am, Obad, Jon, Mic, Nah, Hab, Zeph, Hag,
+      Zech, Mal, Matt, Mrk, Luk, John, Acts, Rom, 1 Cor, 2 Cor, Gal, Eph, Phil,
+      Col, 1 Thess, 2 Thess, 1 Tim, 2 Tim, Tit, Philem, Heb, Jas, 1 Pet, 2 Pet,
+      1 Joh, 2 Joh, 3 Joh, Jud, Rev
+    END
+
+    # Array of book names.
+    BOOK_NAMES = book_names.zip(book_abbrevs).map {|name, abbrev| Bookname.new(name, abbrev)}
+
     # Separator between chapter and verse.
     CV_SEPARATOR = ':'
 
@@ -60,11 +72,6 @@ module Scripref
     # Regular expression to match postfix for more following verses
     POSTFIX_MORE_FOLLOWING_VERSES_RE = /ff\b\s*/o
 
-    pass = '([1-3]\s*)?[A-Z][a-z]+\.?\s*(\d+\s*[,.\-]\s*)*\d+\s*'
-
-    # Regular expression to parse a reference
-    REFERENCE_RE = /#{pass}(;\s*#{pass})*/o
-
     # Check if book has only one chapter
     # @param book book as number
     def book_has_only_one_chapter? book

data/lib/scripref/formatter.rb

@@ -4,16 +4,17 @@ module Scripref
 
   class Formatter
 
-    attr_accessor :cv_separator, :hyphen_separator, :pass_separator
-
+    attr_accessor :bookformat, :cv_separator, :hyphen_separator, :pass_separator
 
     # @param mods one or more modules to include
-    def initialize *mods
+    # @param bookformat (:short use abbreviations, :long use full names of books)
+    def initialize *mods, bookformat: :name
       @mods = mods
       mods.each {|m| extend m}
+      @bookformat = bookformat
     end
 
-    # Formats a reference (array of passages)
+    # Formats a reference (array of passages and maybe separators)
     def format *reference
       @last_b = @last_c = @last_v = :undefined
       @result = []
@@ -25,22 +26,30 @@ module Scripref
       @result.join
     end
 
+    # Formats a book
+    # @param num number of book (starting at 1)
     def format_book num
-      Array(book_names[num - 1]).first
+      book_names[num - 1].send @bookformat
     end
 
+    # Formats a chapter
+    # @param num number of chapter
     def format_chapter num
       num.to_s
     end
 
+    # Formats a verse
+    # @param num number of verse
     def format_verse num
       num.to_s
     end
 
+    # Formats a verse addon
     def format_addon a
       a.to_s
     end
 
+    # Formats a verse postfix
     def format_postfix p
       p.to_s
     end

data/lib/scripref/german.rb

@@ -1,4 +1,5 @@
 # - encoding: utf-8 -
+require 'scripref/bookname'
 require 'scripref/const_reader'
 
 module Scripref
@@ -6,8 +7,7 @@ module Scripref
   # Mixin for parsing references in German.
   module German
 
-    # Array of book names.
-    BOOK_NAMES = <<-END.strip.split(/,\s*/).map {|e| e.split('|')}
+    book_names = <<-END.strip.split(/,\s*/).map {|e| e.split('|')}
       1. Mose, 2. Mose, 3. Mose, 4. Mose, 5. Mose, Josua, Richter, Ruth, 1. Samuel, 2. Samuel,
       1. Könige, 2. Könige, 1. Chronika, 2. Chronika, Esra, Nehemia, Esther, Hiob, Psalm|Psalmen,
       Sprüche, Prediger, Hohelied, Jesaja, Jeremia, Klagelieder, Hesekiel, Daniel, Hosea, Joel,
@@ -18,6 +18,17 @@ module Scripref
       2. Johannes, 3. Johannes, Judas, Offenbarung
     END
 
+    book_abbrevs = <<-END.strip.split(/,\s*/).map {|e| e.split('|')}
+      1.Mo, 2.Mo, 3.Mo, 4.Mo, 5.Mo, Jos, Ri, Ruth, 1.Sam, 2.Sam, 1.Kön, 2.Kön, 1.Chr, 2.Chr,
+      Esr, Neh, Est, Hi, Ps, Spr, Pred, Hohel, Jes, Jer, Klag, Hes, Dan, Hos, Joel, Amos, Obad,
+      Jona, Mich, Nah, Hab, Zef, Hag, Sach, Mal, Mat, Mar, Luk, Joh, Apg, Röm, 1.Ko, 2.Ko,
+      Gal, Eph, Phil, Kol, 1.Thes, 2.Thes, 1.Tim, 2.Tim, Tit, Philem, Heb, Jak, 1.Pet, 2.Pet,
+      1.Joh, 2.Joh, 3.Joh, Jud, Off
+    END
+
+    # Array of book names.
+    BOOK_NAMES = book_names.zip(book_abbrevs).map {|name, abbrev| Bookname.new(name, abbrev)}
+
     # Separator between chapter and verse.
     CV_SEPARATOR = ','
 
@@ -43,7 +54,7 @@ module Scripref
     VERSE_SEPARATOR = '.'
 
     # Regular expression to match addons for a verse.
-    VERSE_ADDON_RE = /[ab]\s*/o
+    VERSE_ADDON_RE = /[ab]\b\s*/o
 
     # Postfix for one following verse
     POSTFIX_ONE_FOLLOWING_VERSE = 'f'
@@ -57,20 +68,12 @@ module Scripref
     # Regular expression to match postfix for more following verses
     POSTFIX_MORE_FOLLOWING_VERSES_RE = /ff\b\s*/o
 
-    pass = '([1-5]\.?\s*)?[A-Z][a-zäöü]+\.?\s*(\d+\s*[,.\-]\s*)*\d+\s*'
-
-    # Regular expression to parse a reference
-    REFERENCE_RE = /#{pass}(;\s*#{pass})*/o
-
     # Check if book has only one chapter
     # @param book book as number
     def book_has_only_one_chapter? book
       [31, 57, 63, 64, 65].include?(book)
     end
 
-    # Hash with special abbreviations
-    SPECIAL_ABBREV_MAPPING = {'Phil' => 'Philipper'}
-
     # Generate attr_reader methods for all constants
     extend ConstReader
     const_reader constants

data/lib/scripref/include.rb

@@ -0,0 +1,4 @@
+# - encoding: utf-8 -
+require 'scripref'
+
+include Scripref

data/lib/scripref/parser.rb

@@ -1,4 +1,5 @@
 # - encoding: utf-8 -
+require 'scripref/basic_methods'
 require 'strscan'
 
 module Scripref
@@ -7,7 +8,7 @@ module Scripref
 
     attr_reader :error
 
-    NUMBER_RE = /\d+\s*/o
+    include BasicMethods
 
     # @param mods one or more modules to include
     def initialize *mods
@@ -15,23 +16,6 @@ module Scripref
       mods.each {|m| extend m}
     end
 
-    # Regular expression to match a chapter
-    def chapter_re
-      NUMBER_RE
-    end
-
-    # Regular expression to match a verse
-    def verse_re
-      NUMBER_RE
-    end
-
-    # Hash with special abbreviations
-    # for example {'Phil' => 'Philipper'}
-    # usual overwritten in Mixins
-    def special_abbrev_mapping
-      @special_abbrev_mapping ||= {}
-    end
-
     # Parsing a string of a scripture reference
     # @param str string to parse
     def parse str
@@ -253,25 +237,14 @@ module Scripref
       @a1 = @a2 = nil
     end
 
-    # Regular expression to match a book.
-    def book_re
-      return @book_re if @book_re
-      books_res_as_strings = book_names.flatten.map do |bn|
-        (bn.gsub(/([^\dA-Z])/, '\1?').gsub('.', '\.')) << '\b\s*'
-      end
-      @book_re = Regexp.compile(books_res_as_strings.map {|s| '(^' << s << ')' }.join('|'), nil)
-    end
-
     def abbrev2num str
-      book2num(abbrev2book(str))
+      s = str.strip
+      str2book_num(s) or str2book_num(abbrev2book(s))
     end
 
     def abbrev2book str
       s = str.strip
-      if name = special_abbrev_mapping[s]
-        return name
-      end
-      @books_str ||= ('#' << book_names.flatten.join('#') << '#')
+      @books_str ||= ('#' << book_names.map(&:names).flatten.join('#') << '#')
       pattern = s.chars.map {|c| Regexp.escape(c) << '[^#]*'}.join
       re = /(?<=#)#{pattern}(?=#)/
       names = @books_str.scan(re)
@@ -282,16 +255,23 @@ module Scripref
       names.first
     end
 
-    def book2num str
-      unless @book2num
-        @book2num = {}
-        book_names.each_with_index do |bns, i|
-          Array(bns).each do |bn|
-            @book2num[bn] = i+1
+    def init_str2book_num
+      unless @str2book_num
+        @str2book_num = {}
+        book_names.each_with_index do |bn, i|
+          bn.names.each do |n|
+            @str2book_num[n] = i+1
+          end
+          bn.abbrevs.each do |n|
+            @str2book_num[n] = i+1
           end
         end
       end
-      @book2num[str]
+    end
+
+    def str2book_num str
+      init_str2book_num
+      @str2book_num[str]
     end
 
     def inspect

data/lib/scripref/passage.rb

@@ -9,6 +9,14 @@ module Scripref
       super text, b1, c1, v1, b2, c2, v2, a1, a2
     end
 
+    def + other
+      to_a.zip(other.to_a).map {|a, b| a + b}
+    end
+
+    def - other
+      to_a.zip(other.to_a).map {|a, b| b - a}
+    end
+
     def to_a
       [b1, c1, v1, b2, c2, v2]
     end

data/lib/scripref/processor.rb

@@ -1,5 +1,6 @@
 # - encoding: utf-8 -
 require 'strscan'
+require 'scripref/basic_methods'
 require 'scripref/parser'
 
 module Scripref
@@ -7,6 +8,7 @@ module Scripref
   class Processor
 
     include Enumerable
+    include BasicMethods
 
     attr_accessor :text
 
@@ -38,11 +40,11 @@ module Scripref
     def each
       if block_given?
         scanner = StringScanner.new(text)
-        while scanner.scan(/(.*?)(#{Regexp.new(reference_re.to_s)})/)
-          yield scanner[1]
+        while scanner.scan(/(.*?)(#{reference_re.source})/)
+          yield scanner[1] unless scanner[1].empty?
           yield @parser.parse(scanner[2])
         end
-        yield scanner.rest if scanner.rest
+        yield scanner.rest if scanner.rest?
         self
       else
         enum_for :each
@@ -53,6 +55,25 @@ module Scripref
       "#<#{self.class} #{@mods.inspect}>"
     end
 
+#    private
+
+    # Regular expression to heuristically identify a reference
+    def reference_re
+      return @reference_re if @reference_re
+      verse_with_optional_addon_or_postfix = '(' << [postfix_one_following_verse_re, postfix_more_following_verses_re, verse_addon_re].map {|e| verse_re.source << e.source}.join(')|(') << ')'
+      re_parts = [
+        '(', book_re, ')', '((', verse_with_optional_addon_or_postfix, ')|(', chapter_re, ')|(', verse_re, '))',
+        '(',
+        '(', book_re, ')',
+        '|',
+        verse_with_optional_addon_or_postfix,
+        '|',
+        '(', [chapter_re, cv_sep_re, verse_re, verse_sep_re, hyphen_re, pass_sep_re].map(&:source).join(')|('), ')',
+        ')*'
+      ].map {|e| Regexp === e ? e.source : e}
+      @reference_re = Regexp.compile(re_parts.join, nil)
+    end
+
   end
 
 end

data/lib/scripref.rb

@@ -1,15 +1,17 @@
 # - encoding: utf-8 -
 require 'delegate'
-require 'scripref/parser'
-require 'scripref/passage'
-require 'scripref/processor'
-require 'scripref/formatter'
-require 'scripref/english'
-require 'scripref/german'
 
 module Scripref
 
-  VERSION = '0.10.0'
+  VERSION = '0.11.0'
+
+  autoload :Bookname, 'scripref/bookname'
+  autoload :English, 'scripref/english'
+  autoload :Formatter, 'scripref/formatter'
+  autoload :German, 'scripref/german'
+  autoload :Parser, 'scripref/parser'
+  autoload :Passage, 'scripref/passage'
+  autoload :Processor, 'scripref/processor'
 
   class Token < DelegateClass(String)
     def initialize *args

data/regtest/parser.yml

@@ -99,7 +99,7 @@ sample: Ruth 2,1a11.15a; 3,7b.9-12b; Markus 4; 5,3a.18b-21a
 exception: |-
   EOS or passage separator or verse separator or hyphen expected!
   Ruth 2,1a11.15a; 3,7b.9-12b; Markus 4; 5,3a.18b-21a
-           ^
+          ^
 ---
 sample: Ruth 2,1a-.15a; 3,7b.9-12b; Markus 4; 5,3a.18b-21a
 exception: |-
@@ -179,7 +179,7 @@ sample: Ruth 2,1a-11.15a3,7b.9-12b; Markus 4; 5,3a.18b-21a
 exception: |-
   EOS or passage separator or verse separator or hyphen expected!
   Ruth 2,1a-11.15a3,7b.9-12b; Markus 4; 5,3a.18b-21a
-                  ^
+                 ^
 ---
 sample: Ruth 2,1a-11.15a; ,7b.9-12b; Markus 4; 5,3a.18b-21a
 exception: |-
@@ -203,7 +203,7 @@ sample: Ruth 2,1a-11.15a; 3,7b9-12b; Markus 4; 5,3a.18b-21a
 exception: |-
   EOS or passage separator or verse separator or hyphen expected!
   Ruth 2,1a-11.15a; 3,7b9-12b; Markus 4; 5,3a.18b-21a
-                        ^
+                       ^
 ---
 sample: Ruth 2,1a-11.15a; 3,7b.-12b; Markus 4; 5,3a.18b-21a
 exception: |-
@@ -293,7 +293,7 @@ sample: Ruth 2,1a-11.15a; 3,7b.9-12bMarkus 4; 5,3a.18b-21a
 exception: |-
   EOS or verse separator or passage separator expected!
   Ruth 2,1a-11.15a; 3,7b.9-12bMarkus 4; 5,3a.18b-21a
-                              ^
+                             ^
 ---
 sample: Ruth 2,1a-11.15a; 3,7b.9-12b;  4; 5,3a.18b-21a
 result:
@@ -457,7 +457,7 @@ sample: Ruth 2,1a-11.15a; 3,7b.9-12b; Markus 4; 5,3a18b-21a
 exception: |-
   EOS or passage separator or verse separator or hyphen expected!
   Ruth 2,1a-11.15a; 3,7b.9-12b; Markus 4; 5,3a18b-21a
-                                              ^
+                                             ^
 ---
 sample: Ruth 2,1a-11.15a; 3,7b.9-12b; Markus 4; 5,3a.-21a
 exception: |-
@@ -469,7 +469,7 @@ sample: Ruth 2,1a-11.15a; 3,7b.9-12b; Markus 4; 5,3a.18b21a
 exception: |-
   EOS or passage separator or verse separator or hyphen expected!
   Ruth 2,1a-11.15a; 3,7b.9-12b; Markus 4; 5,3a.18b21a
-                                                  ^
+                                                 ^
 ---
 sample: Ruth 2,1a-11.15a; 3,7b.9-12b; Markus 4; 5,3a.18b-
 exception: |-

data/regtest/processor.rb

@@ -0,0 +1,25 @@
+require 'regtest'
+require 'scripref'
+
+include Regtest
+include Scripref
+
+def s text
+  sample text do
+    p = Processor.new(text, German)
+    p.each.to_a
+  end
+end
+
+text = 'Ruth 2,1a-11.15a; 3,7b.9-12b; Markus 4; 5,3a.18b-21a'
+
+s text
+
+a = text.split(/\b/)
+a.each_with_index do |e, i|
+  next if e =~ /^\s+$/
+  a2 = a.clone
+  a2.delete_at(i)
+  t = a2.join
+  s t
+end