name_popularity 0.1.0

data/lib/name_popularity/cache.rb

@@ -0,0 +1,42 @@
+# frozen_string_literal: true
+
+module NamePopularity
+  # Cache maintains threshold-specific sets of popular names per gender
+  class Cache
+    def initialize
+      # structure: { gender_sym => { threshold_int => Set("NAME", ...) } }
+      @store = Hash.new { |h, k| h[k] = {} }
+    end
+
+    # Returns a Set of names meeting threshold for the gender, building and caching on first use
+    def fetch(gender, threshold)
+      thr = Integer(threshold)
+      @store[gender][thr] ||= build_set(gender, thr)
+    end
+
+    private
+
+    def build_set(gender, threshold)
+      require 'set'
+      if gender == :any
+        sums = Hash.new(0)
+        Dataset.for(:male).each_row { |name, count| sums[name] += count }
+        Dataset.for(:female).each_row { |name, count| sums[name] += count }
+        set = Set.new
+        sums.each do |name, total|
+          set.add(name) if total >= threshold
+        end
+        set
+      else
+        set = Set.new
+        dataset = Dataset.for(gender)
+        dataset.each_row do |name, count|
+          next unless count >= threshold
+
+          set.add(name)
+        end
+        set
+      end
+    end
+  end
+end

data/lib/name_popularity/dataset.rb

@@ -0,0 +1,49 @@
+# frozen_string_literal: true
+
+module NamePopularity
+  # Dataset reads the packaged TSVs and yields [NAME, COUNT]
+  class Dataset
+    DATA_DIR = File.expand_path("../../data", __dir__)
+
+    # Source: SCB (Statistics Sweden) 2024
+    FILES = {
+      male: File.join(DATA_DIR, "male_names.tsv"),
+      female: File.join(DATA_DIR, "female_names.tsv")
+    }.freeze
+
+    def self.for(gender)
+      path = FILES[gender]
+      raise ArgumentError, "Unknown gender: #{gender.inspect}" unless path
+
+      new(path)
+    end
+
+    def initialize(path)
+      @path = path
+    end
+
+    # Iterates rows as [NAME, COUNT(Integer)]
+    def each_row
+      return enum_for(:each_row) unless block_given?
+
+      File.foreach(@path) do |line|
+        line = line.strip
+        next if line.empty?
+
+        name, count_txt = line.split(/\t/, 2)
+        next unless name && count_txt
+
+        count = parse_count(count_txt)
+        yield(name, count)
+      end
+    end
+
+    private
+
+    # Handles spaces and non-breaking spaces in integers: "1 234" -> 1234
+    def parse_count(text)
+      cleaned = text.tr("\u00A0", ' ').delete(' ')
+      cleaned.to_i
+    end
+  end
+end

data/lib/name_popularity/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module NamePopularity
+  VERSION = "0.1.0"
+end

data/lib/name_popularity.rb

@@ -0,0 +1,32 @@
+# frozen_string_literal: true
+
+require_relative "name_popularity/version"
+require_relative "name_popularity/cache"
+require_relative "name_popularity/dataset"
+
+module NamePopularity
+  DEFAULT_THRESHOLD = 500
+
+  class << self
+    # Determine if a name has at least `threshold` occurrences across male or female datasets.
+    # - name: String (any case). Converted to uppercase to match dataset.
+    # - threshold: Integer, default 500
+    # - cache: optional NamePopularity::Cache
+    def popular_name?(name, threshold: DEFAULT_THRESHOLD, cache: default_cache)
+      norm = normalize(name)
+      # Use sum of male + female counts at this threshold
+      combined = cache.fetch(:any, threshold)
+      combined.include?(norm)
+    end
+
+    private
+
+    def normalize(name)
+      name.to_s.strip.upcase
+    end
+
+    def default_cache
+      @default_cache ||= NamePopularity::Cache.new
+    end
+  end
+end

metadata

@@ -0,0 +1,79 @@
+--- !ruby/object:Gem::Specification
+name: name_popularity
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Joel E. Svensson
+bindir: bin
+cert_chain: []
+date: 1980-01-02 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '13'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '13'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.12'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.12'
+description: Provides popular_name? and gender inference using compressed, threshold-keyed
+  caches backed by TSV datasets for male and female names.
+email:
+- joel.e.svensson@skiftet.org
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- LICENSE
+- README.md
+- data/female_names.tsv
+- data/male_names.tsv
+- lib/name_popularity.rb
+- lib/name_popularity/cache.rb
+- lib/name_popularity/dataset.rb
+- lib/name_popularity/version.rb
+homepage: https://rubygems.org/gems/name_popularity
+licenses:
+- GPL-3.0-only
+metadata:
+  allowed_push_host: https://rubygems.org
+  homepage_uri: https://rubygems.org/gems/name_popularity
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '3.1'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.6.9
+specification_version: 4
+summary: Fast lookups for name popularity and likely gender from TSV datasets
+test_files: []