scripref 0.12.0 → 0.13.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 21205b3151c514f536d81a727778d0ec3ad46a48
-  data.tar.gz: 6869a6575b30d177406baa6a9867a7f1534eb3e4
+SHA256:
+  metadata.gz: aa9e6be87d748d3bd5a78a583cd7cffe7785548debe997f15478da1d19454b2d
+  data.tar.gz: c1cd0125bf8fdee4befaf21409746f1f71bbcc7931e67d91f4abfb68d67dd624
 SHA512:
-  metadata.gz: cf00d9e8951725ad7551eafbaf9e841c8549a56d7c90a9aa7de82e158702403bcdc63816dab72f415e996bf0de8807a9e7b75c2c66b09d1690568bc0771b3871
-  data.tar.gz: 53d7ed2ade506a9adaa0933537884657b86e2dc89aa596a922c9b51a65a908417a041312173c6583e0dc23027eb745678920ed0fa93dea55543d88ca75d8a4d6
+  metadata.gz: 813b10551e8a03e2c8cf0419316372a304d080b987adaaa0f5fe8e8ab80edb67c150a49abeea26db81a10a8b6e72f7a873674ff4773ac3368cb5c1c5d03007a2
+  data.tar.gz: a336bb178df986af14dc04e90619680c9853dd8e12433cd0b6c070486d3a565e50394c3d069421eb1d5a2db82974b0da8cea70016525c48da09825453e4619df

data/.aspell.pws

@@ -0,0 +1,22 @@
+personal_ws-1.1 en 21 
+Bookname
+ParserError
+PassSep
+Philipper
+Psalmen
+Psm
+Scripref
+VerseSep
+addons
+autoload
+formatter
+fullref
+mixins
+pipelining
+postfix
+postfixes
+refactoring
+refactorings
+regtest
+sep
+struct

data/Changelog

@@ -1,3 +1,12 @@
+0.13.0
+Use keyword arguments for Passage.
+Adapt regular expression to match multiple lines.
+New approach to handle punctuation marks in processor: use explicit regular
+expression.
+Allow parsing of abbrevs which matches more spellings of the same book (e.g.
+Psm -> Psalm/Psalmen in German).
+A lot of other improvements for corner cases.
+
 0.12.0
 Allow periods at the end of book abbreviations.
 

data/Rakefile

@@ -15,5 +15,6 @@ Rim.setup do
   if feature_loaded? 'rim/irb'
     irb_requires %w(scripref scripref/include scripref/pipelining)
   end
+  ruby_version '>=2.5.0'
   test_warning false
 end

data/lib/scripref/english.rb

@@ -78,6 +78,9 @@ module Scripref
       [31, 57, 63, 64, 65].include?(book)
     end
 
+    # Regular expression to match punctuation marks
+    PUNCTUATION_MARKS_RE = /[:;.\-]\s*/
+
     # Generate attr_reader methods for all constants
     extend ConstReader
     const_reader constants

data/lib/scripref/german.rb

@@ -74,6 +74,9 @@ module Scripref
       [31, 57, 63, 64, 65].include?(book)
     end
 
+    # Regular expression to match punctuation marks
+    PUNCTUATION_MARKS_RE = /[,;.\-]\s*/
+
     # Generate attr_reader methods for all constants
     extend ConstReader
     const_reader constants

data/lib/scripref/parser.rb

@@ -232,13 +232,14 @@ module Scripref
     end
 
     def push_passage
-      @result << Passage.new(@text, @b1, @c1, @v1, @b2, @c2, @v2, a1: @a1, a2: @a2)
+      @result << Passage.new(text: @text, b1: @b1, c1: @c1, v1: @v1, b2: @b2, c2: @c2, v2: @v2, a1: @a1, a2: @a2)
       @text = ''
       @a1 = @a2 = nil
     end
 
     def abbrev2num str
       s = str.strip
+      s.sub! /\.$/, ''
       str2book_num(s) or str2book_num(abbrev2book(s))
     end
 
@@ -249,7 +250,8 @@ module Scripref
       pattern = s.chars.map {|c| Regexp.escape(c) << '[^#]*'}.join
       re = /(?<=#)#{pattern}(?=#)/
       names = @books_str.scan(re)
-      if names.size != 1
+      uniq_numbers = names.map {|n| str2book_num(n)}.uniq
+      if uniq_numbers.size != 1
         unscan
         give_up format("Abbreviation %s is ambiguous it matches %s!", s, names.join(', '))
       end

data/lib/scripref/passage.rb

@@ -1,14 +1,10 @@
 # - encoding: utf-8 -
 module Scripref
 
-  Passage = Struct.new(:text, :b1, :c1, :v1, :b2, :c2, :v2, :a1, :a2) do
+  Passage = Struct.new(:text, :b1, :c1, :v1, :b2, :c2, :v2, :a1, :a2, keyword_init: true) do
 
     include Comparable
 
-    def initialize text, b1, c1, v1, b2, c2, v2, a1: nil, a2: nil
-      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

data/lib/scripref/processor.rb

@@ -26,8 +26,9 @@ module Scripref
     def each_ref
       if block_given?
         scanner = StringScanner.new(text)
-        while scanner.scan_until(reference_re)
-          yield @parser.parse(scanner.matched)
+        while scanner.scan(/(.*?)(#{reference_re.source})/m)
+          _, ref = fix_scanner_and_results(scanner)
+          yield @parser.parse(ref)
         end
         self
       else
@@ -40,9 +41,10 @@ module Scripref
     def each
       if block_given?
         scanner = StringScanner.new(text)
-        while scanner.scan(/(.*?)(#{reference_re.source})/)
-          yield scanner[1] unless scanner[1].empty?
-          yield @parser.parse(scanner[2])
+        while scanner.scan(/(.*?)(#{reference_re.source})/m)
+          text, ref = fix_scanner_and_results(scanner)
+          yield text unless text.empty?
+          yield @parser.parse(ref)
         end
         yield scanner.rest if scanner.rest?
         self
@@ -55,25 +57,30 @@ 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(')|(') << ')'
+      verse_with_optional_addon_or_postfix =
+        [verse_re, '(', postfix_one_following_verse_re, '|', postfix_more_following_verses_re, '|', verse_addon_re, ')?']
       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(')|('), ')',
-        ')*'
+         '(', book_re, ')', '(', verse_with_optional_addon_or_postfix, '|', chapter_re, ')',
+        # more than one passage
+        '(', verse_with_optional_addon_or_postfix, '|', Regexp.union(cv_sep_re, verse_sep_re, hyphen_re, pass_sep_re, book_re, chapter_re), ')*'
       ].map {|e| Regexp === e ? e.source : e}
       @reference_re = Regexp.compile(re_parts.join, nil)
     end
 
+    def fix_scanner_and_results scanner
+      text = scanner[1]
+      ref = scanner[2]
+      re = /#{punctuation_marks_re.source}$/
+      if ref =~ re
+        scanner.pos -= $&.size
+        ref.sub! re, ''
+      end
+      [text, ref]
+    end
+
   end
 
 end

data/lib/scripref.rb

@@ -3,7 +3,7 @@ require 'delegate'
 
 module Scripref
 
-  VERSION = '0.12.0'
+  VERSION = '0.13.0'
 
   autoload :Bookname, 'scripref/bookname'
   autoload :English, 'scripref/english'

data/regtest/formatter.rb

@@ -2,7 +2,6 @@ require 'ostruct'
 require 'regtest'
 require 'scripref'
 
-include Regtest
 include Scripref
 
 o = OpenStruct.new
@@ -15,12 +14,11 @@ o.v2 = [4, nil]
 
 formatter = Formatter.new(German)
 
-combinations(o).each do |c|
-  a = [c.b1, c.c1, c.v1, c.b2, c.c2, c.v2]
-  pass = Passage.new('', *a)
+Regtest.combinations(o).each do |c|
+  pass = Passage.new(text: '', b1: c.b1, c1: c.c1, v1: c.v1, b2: c.b2, c2: c.c2, v2: c.v2)
   h = pass.to_h
   h.shift
-  sample h do
+  Regtest.sample h do
     formatter.format([pass])
   end
 end

data/regtest/parser.rb

@@ -1,11 +1,10 @@
 require 'regtest'
 require 'scripref'
 
-include Regtest
 include Scripref
 
 def s text
-  sample text do
+  Regtest.sample text do
     res = Parser.new(German).parse(text)
     res.map {|r| r.respond_to?(:to_h) ? r.to_h : r.to_s}
   end

data/regtest/processor.rb

@@ -1,11 +1,10 @@
 require 'regtest'
 require 'scripref'
 
-include Regtest
 include Scripref
 
 def s text
-  sample text do
+  Regtest.sample text do
     p = Processor.new(text, German)
     p.each.to_a
   end