match_skeleton 1.0.3 → 1.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 5871a4eea2d9b69ce70caf1e809c1d692059daec
-  data.tar.gz: f370ed11a1ac8b1f8fc8464097671593406188e2
+SHA256:
+  metadata.gz: a53b8a88e9ca41def7dbc242ecde1d2fe43a1764a7a7058f33bb50d59cc2d609
+  data.tar.gz: 40c07f515ffd7a62c57e314770ee91986e48a83913d9e8ecac1554cdd481c106
 SHA512:
-  metadata.gz: 03c3d685b7f040519c54d9dedabe8657281b01e6b27629b66965eee5ef21ba129149e4afd0cc74bb3d4ccb661b19a502f19431a4b15bfd9296ae7c83eb361565
-  data.tar.gz: 85fa223207412a249af57f807cb5ae7854d4507d98422a337949adc06b4ced66dd707d09db7b4bfddb13119bf4e51367ccb788a20badccccb0e393c171c5ba72
+  metadata.gz: 4261a17c5977db97b8ee59bf6525c11d88c077cfc4e347e997446c36d60370601629505fe354583d859c0bc3285f55f609b132b6eb5b5550a8da1a9fd9a2ec24
+  data.tar.gz: d2f551aeb967751182bc57781dac18e0172af90f5098442200f211fcc7aa156ed5e8ed5cd99dfd68ee16e35107f01532d312cbf9f7be5d02ff22a54d6cf783be

data/.gitignore

@@ -1,3 +1,28 @@
+# See https://help.github.com/articles/ignoring-files for more about ignoring files.
+#
+# If you find yourself ignoring temporary files generated by your text editor
+# or operating system, you probably want to add a global ignore instead:
+#   git config --global core.excludesfile '~/.gitignore_global'
+
+# Ignore bundler config.
+/.bundle
+/vendor/bundle
+
+# Ignore all logfiles and tempfiles.
+/log/*
+/tmp/*
+!/log/.keep
+!/tmp/.keep
+
+.rbenv-version
+# unless supporting rvm < 1.11.0 or doing something fancy, ignore this:
+.rvmrc
+
+/node_modules
+/yarn-error.log
+
+.byebug_history
+
 *.[oa]
 *.so
 *~
@@ -8,3 +33,22 @@
 *.backup
 *.org
 *.orig
+*.elc
+*.pyc
+\#*\#
+
+# Elastic Beanstalk Files
+.elasticbeanstalk/*
+!.elasticbeanstalk/*.cfg.yml
+!.elasticbeanstalk/*.global.yml
+
+# macOS
+.DS_Store
+
+# yard
+*.yardoc
+
+# Ruby Gem doc
+*.gem
+doc/*
+

data/ChangeLog

@@ -1,3 +1,14 @@
+-----
+(Version: 1.1.0)
+2019-10-29  Masa Sakano
+  * Mainly bug-fix but some significant update.
+  * Fixed RangeError newly raised in Ruby 2.6 (https://rubyreferences.github.io/rubychanges/2.6.html#endless-range-1) in some cases.
+  * Updated .gitignore and deleted doc from the git repository.
+  * Makefile and .github/README.md added. News deleted.
+  * `==` compares post_match as well now.
+  * `.eql?` is not overwritten now and is left as default.
+  * Updating tests accordingly.
+
 -----
 (Version: 1.0.3)
 2016-05-27  Masa Sakano

data/Makefile

@@ -0,0 +1,23 @@
+ALL	= 
+
+objs	= 
+
+.SUFFIXES:	.so .o .c .f
+
+#.o.so:
+#	${LD} ${LFLAGS} -o $@ $< ${LINK_LIB}
+
+all: ${ALL}
+
+
+.PHONY: clean test doc
+clean:
+	$(RM) bin/*~
+
+## You may need RUBYLIB=`pwd`/lib:$RUBYLIB
+test:
+	rake test
+
+doc:
+	yard doc; [[ -x ".github" && ( "README.ja.rdoc" -nt ".github/README.md" ) ]] && ( ruby -r rdoc -e 'puts RDoc::Markup::ToMarkdown.new.convert ARGF.read' < README.ja.rdoc > .github/README.md ; echo ".github/README.md is updated." ) || exit 0
+

data/README.ja.rdoc

@@ -2,37 +2,34 @@
 = MatchSkeleton - Equivalent to MatchData with less memory use
 
 This package provides the class {MatchSkeleton}.
-It behaves almost exactly like {MatchData}, except it uses a greatly
+It behaves almost exactly like +MatchData+, except it uses a greatly
 less and practically negligible internal memory.
 
-The built-in {MatchData} class holds a copy of the original
-{String}, from which the matched data are derived, in a "freeze"
+The built-in +MatchData+ class holds a copy of the original
++String+, from which the matched data are derived, in a "freeze"
 state.  It is useful because no one can by chance destructively modify
 the original string.  However, if is memory-savvy.  Even if
-{MatchData} is the match of the first few characters of a 1-GB string,
++MatchData+ is the match of the first few characters of a 1-GB string,
 it internally holds the entire 1-GB of the original string.  If a code
 running holds 1000 of them, it needs a memory use of 1TB(!).
 
 This class holds the same information of the matched data as
-{MatchData} but as positional indices, and the original String object only.
++MatchData+ but as positional indices, and the original String object only.
 Therefore, as long as the original String is not destructively
 modified by an external process, any method of this class returns the
-equal result as {MatchData}.  Note that while the instance of this
+equal result as +MatchData+.  Note that while the instance of this
 class is kept, the original string is not garbage-collected by the
 Ruby interpreter.
 
 One additional function this class offers is the instance variable and
 method <tt>pos_begin</tt>.  It can be set by a user and hold the
-information ({Integer}) at which position the {Regexp} match has started to
+information (+Integer+) at which position the +Regexp+ match has started to
 generate the matched data.
 
-Note this library, when required, also modifies the operator {MatchData#==}
+Note this library, when required, also modifies the operator +MatchData#==+
 so that it can be compared with {MatchSkeleton} objects.
 Now the operator is simply based on duck-typing of
-{#string}, {#regexp}, and {#pre_match}.
-{MatchData#eql?} is not affected, and therefore any comparison between
-{MatchData} and {MatchSkeleton} objects with {MatchData#eql?} or
-{MatchSkeleton#eql?} returns false.
++#string+, +regexp+, and +pre_match+.
 
 == Install
 
@@ -40,6 +37,7 @@ The standard procedure to install a gem should work:
   gem install match_skeleton
 Or, get it from
 {https://rubygems.org/gems/match_skeleton}
+or {https://github.com/masasakano/match_skeleton}
 
 Then just require as
   require 'match_skeleton'
@@ -95,38 +93,34 @@ Versions:: The versions of this package follow Semantic Versioning (2.0.0) http:
 
 = MatchSkeleton - MatchDataに等価でメモリを節約するクラス
 
-クラス {MatchSkeleton} のGemです。
-{MatchData}とほぼ完全に等価な動作をします。ただし、メモリ使用量は
+クラス +MatchSkeleton+ のGemです。
++MatchData+とほぼ完全に等価な動作をします。ただし、メモリ使用量は
 比較してはるかに少なくなり、ほぼ無視できます。
 
-組込{MatchData}クラスは、正規表現マッチした元の文字列(String)のコピーを
+組込+MatchData+クラスは、正規表現マッチした元の文字列(String)のコピーを
 "freeze"した状態で保持します。おかげで、外部のプロセスが元文字列を
-破壊的に変更して{MatchData}のオブジェクトも影響を受ける、ということは
+破壊的に変更して+MatchData+のオブジェクトも影響を受ける、ということは
 ありません。しかし、それはメモリ使用量が巨大になり得ます。たとえば、
 {MatchData}オブジェクトが1GBの文字列の最初の数文字だけのマッチだったと
 しても、同オブジェクトは、その1GBの文字列を内部的に保持します。
 もし動作中のコードがそんなオブジェクトを1000個保持していたら、
 それだけで 1TB(!)のメモリを消費することになります。
 
-このクラスは、{MatchData}と同じ情報を保持しますが、それは内部的に、
+このクラスは、+MatchData+と同じ情報を保持しますが、それは内部的に、
 インデックスと(コピーではない)原文字列そのものだけです。したがって、
 原文字列が外部のプロセスで破壊的に変更されない限り、このクラスの
-メソッドの返り値は、{MatchData}と同じです。念のため、このクラスの
+メソッドの返り値は、+MatchData+と同じです。念のため、このクラスの
 インスタンスが生きている限り、原文字列がガーベージ・コレクトされる
 ことはありません。
 
 一点、このクラス独自のパラメーターとして、インスタンス変数かつ
 メソッドの<tt>pos_begin</tt>が導入されています。正規表現マッチの
-開始ポジション({Integer})を(ユーザーが設定することで)保持します。
+開始ポジション(+Integer+)を(ユーザーが設定することで)保持します。
 
-なお、このライブラリを require した時、演算子 {MatchData#==}
+なお、このライブラリを require した時、演算子 +MatchData#==+
 が変更され、{MatchSkeleton} と比較できるようになります。
 結果、同演算子は、ダック・タイピングとして、
-{#string}, {#regexp}, および {#pre_match}に依存するようになります。
-一方、{MatchData#eql?} は影響を受けません。すなわち、
-{MatchData#eql?} あるいは {MatchSkeleton#eql?}によって、
-{MatchData} と {MatchSkeleton} オブジェクトを比較すると常に
-偽(false)を返します。
++#string+, +regexp+, および +#pre_match+に依存するようになります。
 
 
 == インストール

data/lib/match_skeleton.rb

@@ -1,6 +1,14 @@
 # -*- coding: utf-8 -*-
 
-require 'match_skeleton/match_data'
+begin
+  require 'match_skeleton/match_data'
+rescue LoadError
+  if !MatchData.method_defined? :equal_before_match_skeleton
+    # Probably this file is read with its absolute path explicitly specified.
+    msg = 'WARNING(LoadError): "match_skeleton/match_data" - the library path to %s is not correctly set and hence failed to read some methods.'%(File.basename __FILE__)
+    warn msg
+  end
+end
 
 # =Class MatchSkeleton
 # 
@@ -24,9 +32,25 @@ class MatchSkeleton
   attr_accessor :pos_begin
 
 
+  # Constructor
+  #
+  # If the second argument is omitted, it is taken from the first argument
+  # with +MatchData#string+. However, it would spoil the whole point of
+  # using this class, given +MatchData#string+ always "dups" the original
+  # string and uses up extra memory space!  If you do not specify the second
+  # argument, this class offers almost identical functions but works slower,
+  # save from the bonus information of pos_begin, which can be added in this
+  # initialization in this class.
+  #
+  # The point of using this class is to save the memory when you make multiple
+  # applications with many Regexp to the identical instance of String (with
+  # the same object_id) *and* if you want to keep the results of the Regexp
+  # match as MatchData or equivalent.  So, do not forget to specify the second
+  # argument in this initialization!
+  #
   # @param md [MatchData]
-  # @param string [String] If not specified, it is taken from the first argument (however, that would spoil the whole point of using this class!)
-  # @param pos_begin: [Integer] The position {Regexp} match has started.
+  # @param string [String] If not specified, it is taken from the first argument.
+  # @param pos_begin: [Integer] The position where {Regexp} match has started.
   def initialize(md, string=nil, pos_begin: nil)
     size_str = md.string.size
     if string && string.size != size_str
@@ -37,7 +61,7 @@ class MatchSkeleton
     @pre_match  = (0...md.pre_match.size)	# {Range}
     @post_match = ((size_str-md.post_match.size)...size_str)	# {Range}
 
-    # @offsets is Hash with the keys of both Integer and possibly Symbol
+    # @offsets is Hash of Range-s with the keys of both Integer and possibly Symbol
     # if names exist.
     names  = md.names
     ar_off = (0..(md.size-1)).map do |n|
@@ -50,7 +74,6 @@ class MatchSkeleton
       ej = ei - 1
       @offsets[names[ej]] = ev if (ej >= 0 && names[ej])
     end
-    
 
     @pos_begin = pos_begin
   end
@@ -59,13 +82,14 @@ class MatchSkeleton
   #
   # A difference in {#pos_begin} is not taken into account.
   #
-  # @param [Object] The methods of {#string}, {#regexp}, {#pre_match} have to be defined and return the same to be true. Practically, only {MatchSkeleton} and {MatchData} may return true.
+  # @param obj [Object] The methods of {#string}, {#regexp}, {#pre_match} have to be defined and return the same to be true. Practically, only {MatchSkeleton} and {MatchData} may return true.
   # @return [Boolean]
   # @see #eql?
   def ==(obj)
-    !!((defined?(obj.string)    && string    == obj.string) &&
-       (defined?(obj.regexp)    && regexp    == obj.regexp) &&
-       (defined?(obj.pre_match) && pre_match == obj.pre_match))
+    !!((defined?(obj.string)     && string     == obj.string) &&
+       (defined?(obj.regexp)     && regexp     == obj.regexp) &&
+       (defined?(obj.pre_match)  && pre_match  == obj.pre_match) &&
+       (defined?(obj.post_match) && post_match == obj.post_match))
     # nb., defined?() can return nil, and then nil (not false) will be returned.
   end
 
@@ -110,22 +134,22 @@ class MatchSkeleton
     offset(n)[1]
   end
 
-  # The same as {#==} but stricter comparison.
-  #
-  # The comparison between {MatchSkeleton} and {MatchData} returns false and
-  # that between {MatchSkeleton} with different {#pos_begin} or
-  # those with strings of different Object-IDs also return false.
-  #
-  # @param [Object]
-  # @return [Boolean]
-  # @see #==
-  def eql?(obj)
-    return false if self != obj
-    return false if !defined?(obj.pos_begin)
-    return false if (string.object_id != obj.string.object_id)
-    return false if pos_begin != obj.pos_begin
-    return true
-  end
+  # # The same as {#==} but stricter comparison.
+  # #
+  # # The comparison between {MatchSkeleton} and {MatchData} returns false and
+  # # that between {MatchSkeleton} with different {#pos_begin} or
+  # # those with strings of different Object-IDs also return false.
+  # #
+  # # @param obj [Object]
+  # # @return [Boolean]
+  # # @see #==
+  # def eql?(obj)
+  #   return false if self != obj
+  #   return false if !defined?(obj.pos_begin)
+  #   return false if (string.object_id != obj.string.object_id)
+  #   return false if pos_begin != obj.pos_begin
+  #   return true
+  # end
 
   # Similar to {MatchData#inspect}
   #
@@ -148,6 +172,11 @@ class MatchSkeleton
 
   # The same as {MatchData#offset}
   #
+  # Due to the change in Ruby 2.6
+  # https://rubyreferences.github.io/rubychanges/2.6.html#endless-range-1
+  # the old routines would raise an Excetion when the end range is nil,
+  # that is, there is no match for MatchData#[n], hence needed updating.
+  #
   # @param n [Integer]
   # @return [Array<integer>]
   def offset(n)
@@ -155,8 +184,18 @@ class MatchSkeleton
       n = n.to_s 
       raise IndexError, sprintf("undefined group name reference: %s", n) if !names.include?(n)
     end
-    [@offsets[n].first, 
-     @offsets[n].last]
+
+    ## This used to work before Ruby 2.6
+    # [@offsets[n].first, 
+    #  @offsets[n].last]
+
+    [:first, :last].map do |ec|
+      begin
+        @offsets[n].public_send ec
+      rescue RangeError
+        nil
+      end
+    end
   end
 
   # The same as {MatchData#pre_match}
@@ -212,8 +251,12 @@ class MatchSkeleton
 
   private 
 
+  # @note Due to the change in Ruby 2.6, k.last may raise RangeError.
+  #   In this instance, k.first must be always nil when k.last is nil.
+  #   So, k.last would not be evaluated when k.last is nil.
+  #   But it is playing safe (by adding "rescue").
   def offset2string(i)
     k = @offsets[i]
-    (k.first && k.last) ? string[k] : nil
+    (k.first && (k.last rescue nil)) ? string[k] : nil
   end
 end	# class MatchSkeleton

data/lib/match_skeleton/match_data.rb

@@ -11,7 +11,7 @@ class MatchData
 
   # Compares with {MatchSkeleton}, in addition to {MatchData}
   #
-  # @param [#string, #regexp, #pre_match] All the methods have to be there. Practically, {MatchSkeleton} and {MatchData}
+  # @param obj [#string, #regexp, #pre_match] All the methods have to be there. Practically, {MatchSkeleton} and {MatchData}
   # @return [Boolean]
   def ==(obj)
     !!((defined?(obj.string)    && string    == obj.string) &&

data/test/test_match_skeleton.rb

@@ -143,12 +143,25 @@ class TestMatchSkeleton < Minitest::Test
     # pos_begin does not count.
     ms1p = ms1.dup
     assert_equal ms1.string.object_id, ms1p.string.object_id
+    assert_equal ms1.regexp.object_id, ms1p.regexp.object_id
+    assert_equal ms1.instance_variable_get(:@pre_match), ms1p.instance_variable_get(:@pre_match)
+    assert_equal ms1.instance_variable_get(:@offsets),   ms1p.instance_variable_get(:@offsets)
+    assert_equal ms1.instance_variable_get(:@pos_begin), ms1p.instance_variable_get(:@pos_begin)
     assert_equal true,  (ms1 == ms1p)
-    assert_equal true,  (ms1.eql?(ms1p))
+    # assert_equal true,  (ms1.eql?(ms1p))  # Not quite sure why.
     ms1p.pos_begin = 6
     assert_equal true,  (ms1 == ms1p)
     assert_equal false, (ms1.eql?(ms1p))
 
+    # clone
+    ms1q = ms1.clone
+    assert_equal ms1.string.object_id, ms1q.string.object_id
+    assert_equal true,  (ms1 == ms1q)
+    # assert_equal true,  (ms1.eql?(ms1q))  # Not quite sure why.
+    ms1q.pos_begin = 6
+    assert_equal true,  (ms1 == ms1q)
+    assert_equal false, (ms1.eql?(ms1q))
+
     # Different Object-ID
     s2 = s.dup
     md2 = s2.match(re1, pos)
@@ -158,7 +171,7 @@ class TestMatchSkeleton < Minitest::Test
     assert_equal true,  (md2 == ms1)
     assert_equal true,  (ms21== md2)
     assert_equal true,  (md2 == ms21)
-    assert_equal true,  (ms21.eql?(ms1))
+    # assert_equal true,  (ms21.eql?(ms1))
 
     ms2 = MatchSkeleton.new(md2, s2, pos_begin: pos)	# Equal MatchData, but non-identical string s (with the different Object-IDs)
     assert_equal true,  (ms1 == ms2)
@@ -241,8 +254,10 @@ class TestMatchSkeleton < Minitest::Test
     md1 = re.match(s)
     ms1 = MatchSkeleton.new(md1, s)
     assert_equal md1['foo'], ms1['foo']
-    assert_equal md1['baa'], ms1['baa']
-    assert_equal md1[:baa],  ms1[:baa]
+    assert_nil   md1['baa']
+    assert_nil   ms1['baa']
+    assert_nil   md1[:baa]
+    assert_nil   ms1[:baa]
   end
 
   def test_begin_end_int01
@@ -280,10 +295,21 @@ class TestMatchSkeleton < Minitest::Test
     re = /(ef)(g)?(hi)/
     md1 = re.match(s)
     ms1 = MatchSkeleton.new(md1, s)
-    assert_equal md1.begin(2), ms1.begin(2)
-    assert_equal nil,          ms1.begin(2)
-    assert_equal md1.end(2),   ms1.end(2)
-    assert_equal nil,          ms1.end(2)
+    #assert_equal md1.begin(2), ms1.begin(2)  # DEPRECATED: Use assert_nil
+    assert_nil md1.begin(2)
+    assert_nil ms1.begin(2)
+    assert_nil md1.end(2)
+    assert_nil ms1.end(2)
+  end
+
+  def test_begin_end_nil_to_a01
+    s = "efhi2"
+    re = /(ef)(g)?(hi)/
+    md1 = re.match(s)
+    ms1 = MatchSkeleton.new(md1, s)
+    ad1 = md1.to_a
+    as1 = ms1.to_a
+    assert_equal ad1,  as1
   end
 
   def test_captures01
@@ -327,6 +353,9 @@ class TestMatchSkeleton < Minitest::Test
     ms1 = MatchSkeleton.new(md1, s)
     assert_equal md1.names,  ms1.names
     assert_equal ["x", "y"], ms1.names
+    assert_equal md1[:x], ms1[:x]
+    assert_nil   md1[:y]
+    assert_nil   ms1[:y]
   end
 
   def test_offset_int01

metadata

@@ -1,18 +1,19 @@
 --- !ruby/object:Gem::Specification
 name: match_skeleton
 version: !ruby/object:Gem::Version
-  version: 1.0.3
+  version: 1.1.0
 platform: ruby
 authors:
 - Masa Sakano
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-05-27 00:00:00.000000000 Z
+date: 2019-10-29 00:00:00.000000000 Z
 dependencies: []
 description: MatchSkeleton is a class equivalent to MatchData with negligible memory
-  use.  As long as the original string is not destructively modified, it behaves almost
-  icentical to MatchData.
+  use when the identical strings are matched repeatedly while matched data are kept
+  in the memory.  As long as the original string is not destructively modified, it
+  behaves almost icentical to MatchData.
 email: info@wisebabel.com
 executables: []
 extensions: []
@@ -21,7 +22,7 @@ extra_rdoc_files:
 files:
 - ".gitignore"
 - ChangeLog
-- News
+- Makefile
 - README.ja.rdoc
 - Rakefile
 - lib/match_skeleton.rb
@@ -30,7 +31,8 @@ files:
 homepage: https://www.wisebabel.com/
 licenses:
 - MIT
-metadata: {}
+metadata:
+  yard.run: yri
 post_install_message: 
 rdoc_options:
 - "--charset=UTF-8"
@@ -47,11 +49,9 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.5.1
+rubygems_version: 3.0.3
 signing_key: 
 specification_version: 4
 summary: MatchSkeleton - class equivalent to MatchData with negligible memory use
 test_files:
 - test/test_match_skeleton.rb
-has_rdoc: 

data/News

@@ -1,3 +0,0 @@
------
-(Version: 0.1.0) 2016-05-19
- * First creation.