mormor 0.0.1 → 0.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2293b20144e224eff386a73bc985a03e360dcd9a73afcde01af33ec0b0bc9d32
-  data.tar.gz: 2e0e577ee7925c5cdc453870152b8d30698371b9c31f65dc1aa0bff3c0475e4a
+  metadata.gz: e56bbee95de83605fba20dc4f49fddf100e28a8da1151eb0138d7bf69e3e3093
+  data.tar.gz: c1a02c07b147374335616c60078a1ce6167ed12becf20b1a09855467da570649
 SHA512:
-  metadata.gz: 63f3bb8643b13a296a8fc3dfecab97dd88f948660b9aed395d9264066edd666137c321a35efeeeda2640099d98641784064495039fa9e3a3339102a2ea6f04ed
-  data.tar.gz: 3c42a83dfcfbfe52348559d8171ea7d10a5bb5fa4087d90824b9e82d07057cfb9748e5f55e9a586561726106c6e37a25b8ec46d67cd4bf1872118a5704c54beb
+  metadata.gz: 15d7965789cec21ef0275d5dd2c018bb6a4c0fe33b5922e176946f7ae3f5723aa11b30476a2825d3840678e531ebb39a95bc457c27f68f84167f1b3f1aefb7e4
+  data.tar.gz: f794bd2f339c105e0975990c21e377f6862b91c01ecac679f06128ae816f602277903290111bc7b4425af2a8bb0ff2999ade4aa349a959dddcf3ae56731f32e2

data/Changelog.md

@@ -0,0 +1,11 @@
+# MorMor changelog
+
+## 0.0.2 / 2022-09-18
+
+* Minimum Ruby version is 2.7
+* Fixed bug with `Array.slice!`, affecting German dictionary reading ([@glaszig](https://github.com/glaszig))
+* Improved handling of `utf8` encoding (seems to be common way for Morfologik dictionaries to spell it)
+
+## 0.0.1 / 2019-06-21
+
+Initial release

data/exe/mormor-dump

@@ -4,4 +4,4 @@ require_relative '../lib/mormor'
 path = ARGV.shift or abort "Usage: mormor-dump <dictionary>.dict"
 File.exist?(path) or abort "#{path} does not exist"
 
-MorMor::FSA.new(path).each_sequence(&method(:puts))
+MorMor::FSA.read(path).each_sequence(&method(:puts))

data/lib/mormor/dictionary.rb

@@ -25,6 +25,9 @@ module MorMor
     # @private
     DECODERS = {'SUFFIX' => :suffix, 'PREFIX' => :prefix_suffix}.freeze
 
+    # @private
+    ENCODING_ALIASES = {'utf8' => 'UTF-8'}.freeze
+
     # @private
     attr_reader :fsa
     # @return [Hash]
@@ -92,7 +95,7 @@ module MorMor
       # NB: All possible values described in DictionaryAttribute.java
 
       # Cache it to be quickly accessible
-      @encoding = @info.fetch('fsa.dict.encoding')
+      @encoding = @info.fetch('fsa.dict.encoding').then { ENCODING_ALIASES.fetch(_1, _1) }
       @separator = @info.fetch('fsa.dict.separator')
       @sepbyte = @separator.bytes.first
 
@@ -102,9 +105,8 @@ module MorMor
     def read_values(path)
       File.exist?(path) or fail ArgumentError, "#{path} does not exist"
       File.read(path).split("\n")
-          .map { |ln| ln.sub(/\#.*$/, '').strip }.reject(&:empty?)
-          .map { |ln| ln.split('=', 2) }
-          .to_h
+          .map { _1.sub(/\#.*$/, '').strip }.reject(&:empty?)
+          .to_h { _1.split('=', 2) }
     end
 
     def choose_decoder(name)
@@ -115,14 +117,14 @@ module MorMor
     def suffix(source, encoded)
       truncate_suf = encoded[0...1].bytes.first.-(65) & 0xff # 65 is 'A'
       # TODO: If remove == 255, means "remove all"
-      source[0...source.size - truncate_suf] + encoded[1..-1]
+      source[0...source.size - truncate_suf] + encoded[1..]
     end
 
     def prefix_suffix(source, encoded)
       truncate_pref, truncate_suf = encoded[0...2].bytes.first(2).map { |b| (b - 65) & 0xff } # 65 is 'A'
       # TODO: If remove == 255, means "remove all"
 
-      source[truncate_pref...source.size - truncate_suf] + encoded[2..-1]
+      source[truncate_pref...source.size - truncate_suf] + encoded[2..]
     end
   end
 end

data/lib/mormor/fsa/enumerator.rb

@@ -54,7 +54,7 @@ module MorMor
           arcs_stack.push(fsa.end_node(arc)) unless fsa.terminal_arc?(arc)
 
           if fsa.final_arc?(arc)
-            sequence.slice!(arcs_stack.count)
+            sequence.slice!(arcs_stack.count..)
             return sequence
           end
         end

data/lib/mormor/fsa.rb

@@ -49,7 +49,7 @@ module MorMor
     end
 
     def each_sequence(from: root_node, &block)
-      Enumerator.new(self, from).then { |e| block ? e.each(&block) : e }
+      Enumerator.new(self, from).then { block ? _1.each(&block) : _1 }
     end
 
     def next_arc(arc)
@@ -67,12 +67,12 @@ module MorMor
     end
 
     def find_arc(node, label)
-      each_arc(from: node).detect { |a| arc_label(a) == label } || 0
+      each_arc(from: node).detect { arc_label(_1) == label } || 0
     end
 
     # Port of FSATraversal.java
     # Method is left unsplit to leave original algorithm recognizable, hence rubocop:disable's
-    def match(sequence, node = root_node) # rubocop:disable Metrics/AbcSize,Metrics/CyclomaticComplexity
+    def match(sequence, node = root_node) # rubocop:disable Metrics/AbcSize,Metrics/CyclomaticComplexity,Metrics/PerceivedComplexity
       return Match.new(:no) if node.zero?
 
       sequence.each_with_index do |byte, i|

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: mormor
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.2
 platform: ruby
 authors:
 - Victor Shepelev
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2019-06-21 00:00:00.000000000 Z
+date: 2022-09-18 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: backports
@@ -87,6 +87,7 @@ executables:
 extensions: []
 extra_rdoc_files: []
 files:
+- Changelog.md
 - LICENSE.txt
 - README.md
 - exe/mormor-dump
@@ -108,15 +109,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 2.3.0
+      version: 2.7.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.7
+rubygems_version: 3.1.6
 signing_key: 
 specification_version: 4
 summary: 'Morfologik dictionaries client in pure Ruby: POS tagging & spellcheck'