engtagger 0.4.5 → 0.4.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: be5e5dcb477d743356b79d58eadb358a4bd1a47e2b318011313ea46a577402f9
-  data.tar.gz: c8c0fa1024e6d2ad2bb3d619eb92b259f7fe25076ad82119345c5ceab192af45
+  metadata.gz: 61101478ee5332b3ba91df6598db0e4822832be62edaf5ac8613256d8ba8d7d4
+  data.tar.gz: 903c665fd059b5095f2f240c2522f2a593d92bbf8cb500b142f6af373d48802c
 SHA512:
-  metadata.gz: 2cd4aa320c5c01fa830b68163c8a0b88acc5a87eb91e6ccc2880adb033d6d291be75542867efc7fe8610257cb4cafd61714abaff59f1cb674e07ae5e38820be3
-  data.tar.gz: 5ad319a0decea08e49b1b68022d86d0b9e856524bbaa684fe518199139f7cfd7e708d218910780ec052a633b685f8a9bb68876b7b3c27f87da446d5d06f3b434
+  metadata.gz: 066d0510e7a585c38273a4fb28f33e05f9eb6f64a340b22ca3a6e05e8946866b769dc1966fc729f5351d16a318e6f6d2c41f4929a2bc627ad9d384654ba3a85f
+  data.tar.gz: d19da0ed3236dcc64963cb64fe5a7833b3c3790433c9b4dee06c87e2abb2cdf30733cdf55a6b9409396096c0f95e383d47a8cd168f7fda954874c544646227d8

data/CHANGELOG.md

@@ -1,5 +1,11 @@
 # Changelog
 
+## 0.4.6 (2026-11-14)
+
+- Fix `get_noun_phrases`, `get_words` and `add_tags` taking time quadratic in
+  the input length on long runs of nouns and on long texts. Output is
+  unchanged. Upgrade if you tag text from untrusted sources.
+
 ## 0.4.5 (2026-08-14)
 
 License metadata correction; no code changes. This library is a port (2009) of

data/Rakefile

@@ -18,3 +18,8 @@ task :normalize_permissions do
 end
 
 Rake::Task["build"].enhance([:normalize_permissions])
+
+# Pre-release gate: after building, open the .gem and verify its payload
+# against spec.files in both directions, then scan names, contents and modes.
+# `rake release` depends on `build`, so a FAIL here stops the push.
+Rake::Task["build"].enhance { sh "ruby", "scripts/verify_gem.rb" }

data/engtagger.gemspec

@@ -11,7 +11,7 @@ Gem::Specification.new do |gem|
   gem.license       = "GPL-3.0-only"
   gem.required_ruby_version = Gem::Requirement.new(">= 2.6")
   gem.files = Dir.chdir(File.expand_path(__dir__)) do
-    `git ls-files -z`.split("\x0").reject { |f| f.match(%r{\A(?:test|spec|features|tools|docs)/}) }
+    `git ls-files -z`.split("\x0").reject { |f| f.match(%r{\A(?:test|spec|features|tools|docs|scripts)/}) }
   end
   gem.executables   = gem.files.grep(%r{^bin/}).map { |f| File.basename(f) }
   gem.name          = "engtagger"

data/lib/engtagger/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 class EngTagger
-  VERSION = "0.4.5"
+  VERSION = "0.4.6"
 end

data/lib/engtagger.rb

@@ -545,23 +545,27 @@ class EngTagger
 
     found = Hash.new(0)
     phrase_ext = /(?:#{PREP}|#{DET}|#{NUM})+/xo
+    noun = /#{NN}/o
+    longest = @conf[:longest_noun_phrase]
     scanned = tagged.scan(@@mnp)
     # Find MNPs in the text, one sentence at a time
     # Record and split if the phrase is extended by a (?:PREP|DET|NUM)
     mn_phrases = []
     scanned.each do |m|
       found[m] += 1 if phrase_ext =~ m
-      mn_phrases += m.split(phrase_ext)
+      mn_phrases.concat(m.split(phrase_ext))
     end
     mn_phrases.each do |mnp|
       # Split the phrase into an array of words, and create a loop for each word,
       # shortening the phrase by removing the word in the first position.
       # Record the phrase and any single nouns that are found
       words = mnp.split
-      words.length.times do
-        found[words.join(" ")] += 1 if words.length > 1
-        w = words.shift
-        found[w] += 1 if w =~ /#{NN}/
+      words.each_index do |i|
+        # Longer phrases would be dropped by the length limit below, so they
+        # are not built in the first place.
+        length = words.length - i
+        found[words[i..].join(" ")] += 1 if length > 1 && length <= longest
+        found[words[i]] += 1 if noun.match?(words[i])
       end
     end
     ret = Hash.new(0)
@@ -677,7 +681,7 @@ class EngTagger
     tokenized = []
     # Tokenize the text (splitting on punctuation as you go)
     cleaned_text.split(/\s+/).each do |line|
-      tokenized += split_punct(line)
+      tokenized.concat(split_punct(line))
     end
     split_sentences(tokenized)
   end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: engtagger
 version: !ruby/object:Gem::Version
-  version: 0.4.5
+  version: 0.4.6
 platform: ruby
 authors:
 - Yoichiro Hasebe
@@ -80,7 +80,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.6.9
+rubygems_version: 4.0.24
 specification_version: 4
 summary: A probability based, corpus-trained English POS tagger
 test_files: []