tiered_category_expressions 0.1.3 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 5501de321cdb8513c0913ceb5163822615701500
-  data.tar.gz: 24748da10d31e3f935e315582cbc98cc6c6c069f
+SHA256:
+  metadata.gz: 9ac6214a3dfb2749c9257aa613e50769f52300ce5575b6abaee93e72fbbf7211
+  data.tar.gz: 5974153a9628f5af2f5150641f89e1e92ba9c34e9a82cf94b1bff676b9250e89
 SHA512:
-  metadata.gz: 6829ffcf02a4b9bc5fb9d0dd1ef0c80161fed35220eaee6689c867b817261bfcd2d2fcb8f4329a02fc4df887d706e42ccc58cadfb0dd55dda75c60450ce9cc5d
-  data.tar.gz: 49fc8d928beabb5d4a165aa5d9f4a0f7ff11156e5e11006667ed83cec416dbd5d0386f6c5785beb7e3cbbc5f9c5b49740da2349a25345f435fa0eed309d90625
+  metadata.gz: 650310edc447e6449185ea5e29758144bc1144006fdb3d69bdf6d421554fe27980b5725669813c2d6595f2d4a60850911319ba8be280f0210a9ba019b647f97b
+  data.tar.gz: 959601a68c6762110177bd954b044b95de5a4d62a3f2f6b4212d1ad3bcca2d13986d28fb118d7d712fbfba99ca4e9b14dbb52994441542e0a57ad8caac1dda17

data/.github/dependabot.yml

@@ -0,0 +1,54 @@
+# This configures how Dependabot presents us with dependency updates.
+#
+# Security updates are by definition urgent and bypass this configuration. They are offered as soon as available.
+# Regular updates are offered based on the schedule defined here
+#
+# Docs: https://docs.github.com/en/github/administering-a-repository/keeping-your-dependencies-updated-automatically
+# Config options: https://docs.github.com/en/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file#configuration-options-for-the-dependabotyml-file
+#
+# Choice: update on Tuesday
+#
+# A lot of open source updates happen in the weekend.
+# A lot of companies apply these updates on Monday and discover bugs. Critical bugs will get fixed within 24h.
+# Waiting until Tuesday to update likely results in slightly more stable updates than Monday.
+#
+#
+# Choice: update a few small dependencies each week, to keep the time investment small (max 1h)
+#
+# Making a small, continuous effort to stay up-to-date is more important than always being on the bleeding edge.
+# Dependabot updates are intended for the low-hanging fruit.
+#
+#
+# Choice: major updates (such as Rails) don't have to be applied this way
+#
+# Updates that don't apply cleanly can be ignored. Just turn them into a Maintenance Issue so someone can pick it up later.
+
+version: 2
+updates:
+  # GitHub Actions
+  - package-ecosystem: github-actions
+    directory: '/'
+    open-pull-requests-limit: 5
+    schedule:
+      interval: weekly
+      day: tuesday
+      time: "07:00"
+      timezone: "Europe/Amsterdam"
+    pull-request-branch-name:
+      separator: "-"
+    reviewers:
+      - "wvengen"
+
+  # Ruby gems
+  - package-ecosystem: bundler
+    directory: '/'
+    open-pull-requests-limit: 5
+    schedule:
+      interval: weekly
+      day: tuesday
+      time: "07:00"
+      timezone: "Europe/Amsterdam"
+    pull-request-branch-name:
+      separator: "-"
+    reviewers:
+      - "wvengen"

data/.github/workflows/main.yml

@@ -0,0 +1,29 @@
+name: CI
+
+on:
+  push:
+    branches:
+      - main
+
+  pull_request:
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    name: On Ruby ${{ matrix.ruby }}
+    strategy:
+      matrix:
+        ruby:
+          - '2.7.6'
+          - '3.0.4'
+          - '3.1.2'
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Ruby
+      uses: ruby/setup-ruby@v1
+      with:
+        ruby-version: ${{ matrix.ruby }}
+        bundler-cache: true
+    - name: Run the CI task, which runs tests, rubocop and builds the gem
+      run: bundle exec rake ci

data/Gemfile

@@ -1,4 +1,19 @@
-source 'https://rubygems.org'
+# frozen_string_literal: true
 
-# Specify your gem's dependencies in tiered_category_expressions.gemspec
+source "https://rubygems.org"
+
+# Specify your gem's runtime dependencies in questionmark-barcodes.gemspec
 gemspec
+
+#
+# These dependencies are only used for development.
+#
+
+# Rake wraps common tasks such as running tools and generating releases
+gem "rake", "~> 13.0"
+
+# RSpec is our test framework
+gem "rspec", "~> 3.12"
+
+# Documentation
+gem "yard", "~> 0.9.34"

data/LANGREF.md

@@ -1,4 +1,4 @@
-# TCE language reference
+# TCE v1.1 language reference
 
 ## Introduction
 
@@ -14,6 +14,7 @@ TCEs follow the same structure. They consist of category tier names separated by
 
   - `agf > groente`
   - `agf > groente > komkommer`
+  - `agf > groente > komkommer.`
   - `agf > groente > kom%`
   - `agf > groente | fruit > komkommer`
   - `agf > groente > !tomaat`
@@ -27,7 +28,7 @@ When a TCE is matched with a category:
   - Letter case is ignored, e.g. both "NONFOOD" and "NonFood" match "nonfood" and vice versa.
   - Everything other than alphabetic and numeric characters (including spaces) is ignored, e.g. "nonfood" matches both "non-food" and "non food".
   - Accents are ignored, e.g. "knäckebröd" matches "knackebrod" and vice versa.
-  - It matches a _subtree_ of categories, e.g. the TCE `"nonfood"` matches the category `["Nonfood"]` as well as `["Nonfood", "Schoonmaak", "Soda"]`.
+  - By default it matches a _subtree_ of categories, e.g. the TCE `"nonfood"` matches the category `["Nonfood"]` as well as `["Nonfood", "Schoonmaak", "Soda"]`.
 
 Even though they are ignored, tier names in TCEs may contain spaces, upper and lowercase characters and accented characters. To the contrary, they **cannot** contain special characters.
 
@@ -105,6 +106,41 @@ Note that TCEs are considered equal if they match the same categories. E.g. thes
 ["Rucola"]
 ```
 
+### Explicit last tier(s) `.`
+```ruby
+"agf > groente > komkommer."
+
+# Matches
+["AGF", "Groente", "Komkommer"]
+
+# Does not match
+["AGF", "Groente", "Komkommer", "Snack komkommer"]
+```
+
+```ruby
+"agf > groente. > komkommer"
+
+# Matches
+["AGF", "Groente"]
+["AGF", "Groente", "Komkommer"]
+["AGF", "Groente", "Komkommer", "Snack komkommer"]
+
+# Does not match
+["AGF", "Groente", "Tomaat"]
+```
+
+```ruby
+"agf > groente. > komkommer."
+
+# Matches
+["AGF", "Groente"]
+["AGF", "Groente", "Komkommer"]
+
+# Does not match
+["AGF", "Groente", "Tomaat"]
+["AGF", "Groente", "Komkommer", "Snack komkommer"]
+```
+
 ### Combining patterns
 ```ruby
 "groente > seizoensgroente > %"
@@ -142,3 +178,21 @@ Note that TCEs are considered equal if they match the same categories. E.g. thes
 ["Nonfood", "Diervoeding"]
 ["Nonfood"]
 ```
+
+```ruby
+"voeding. >> %voeding."
+
+# Matches
+["Voeding"]
+["Voeding", "Babyvoeding"]
+["Voeding", "Diervoeding"]
+["Voeding", "Baby", "Babyvoeding"]
+["Voeding", "Dier", "Diervoeding"]
+
+# Does not match
+["Voeding", "AGF"]
+["Voeding", "Babyvoeding", "Newborn"]
+["Voeding", "Diervoeding", "Hond"]
+["Voeding", "Baby", "Babyvoeding", "Newborn"]
+["Voeding", "Dier", "Diervoeding", "Hond"]
+```

data/README.md

@@ -1,6 +1,10 @@
+<div style="float: right">
+<a href="https://badge.fury.io/rb/tiered_category_expressions"><img src="https://badge.fury.io/rb/tiered_category_expressions.svg" alt="Rubygem" height="18" /></a>
+</div>
+
 # Tiered Category Expressions
 
-Work with TCEs in Ruby.
+Work with TCE v1.1 in Ruby.
 
 ## Installation
 
@@ -34,12 +38,13 @@ require 'tiered_category_expressions/core'
 
   - [Library documentation](https://www.rubydoc.info/gems/tiered_category_expressions/)
   - [TCE language reference](https://www.rubydoc.info/gems/tiered_category_expressions/file/LANGREF.md)
+  - [Introductory blogpost](https://developers.thequestionmark.org/2019/07/24/pattern-matching-expert-system-classification)
 
 ## Usage examples
 
 ```ruby
 tce = TCE("groceries > nonfood | pharmacy >> !baby formula")
-# => TieredCategoryExpressions::Expression[groceries > nonfood | pharmacy >> !baby formula]
+# => TieredCategoryExpressions::Expression
 
 tce.matches?(["Groceries", "Non-food", "Cleaning", "Soap"])
 # => true
@@ -51,13 +56,13 @@ tce.matches?(["Groceries", "Pharmacy", "Baby", "Pacifiers"])
 # => true
 
 tce.to_regexp
-# => /^(groceries)>(nonfood|pharmacy)>(?!(.+>)*(babyformula)>).+>/i
+# => Regexp
 
 tce.as_regexp
-# => "^(groceries)>(nonfood|pharmacy)>(?!(.+>)*(babyformula)>).+>"
+# => String
 
 TCE("groceries > nonfood") > TCE("baby") > ">> pacifiers"
-# => TieredCategoryExpressions::Expression[groceries > nonfood > baby >> pacifiers]
+# => TieredCategoryExpressions::Expression
 ```
 
 ## Development

data/Rakefile

@@ -1,9 +1,16 @@
+# frozen_string_literal: true
+
+# Disable pushing the gem to rubygems
+# Source: https://github.com/rubygems/rubygems/blob/master/bundler/lib/bundler/gem_helper.rb#L231
+ENV["gem_push"] = "no"
+
 require "bundler/gem_tasks"
 require "rspec/core/rake_task"
 
 RSpec::Core::RakeTask.new(:spec)
 
-task :default => :spec
+desc "Run all tasks required to pass CI"
+task ci: %i[spec build]
 
 namespace :docs do
   desc "Build the YARD documentation"
@@ -20,3 +27,5 @@ end
 
 desc "Build and view the YARD documentation"
 task :docs => ["docs:build", "docs:view"]
+
+task default: %i[ci]

data/lib/tiered_category_expressions/expression.rb

@@ -36,9 +36,12 @@ module TieredCategoryExpressions
       raise ParseError, "unexpected input at character #{column}"
     end
 
+    # @param strict [Boolean] If +true+ is given then the object should not match categories with tiers that extend
+    #   beyond those specified by the TCE. This is the case when the TCE ends with ".".
     # @!visibility private
-    def initialize(tiers)
+    def initialize(tiers, strict:)
       @tiers = tiers
+      @strict = !!strict
     end
 
     # @!visibility private
@@ -46,14 +49,18 @@ module TieredCategoryExpressions
       "TieredCategoryExpressions::Expression[#{self}]"
     end
 
+    # @param implied_root [Boolean] If +true+ no leading ">" is included.
     # @return [String] String representation of the expression
-    def to_s
-      @tiers.join(" ").sub(/^>(?!>)\s*/, "") # Initial ">" is implied (but ">>" is not)
+    def to_s(implied_root: true)
+      str = @tiers.join(" ")
+      str << "." if @strict
+      str = str.sub(/^>(?!>)\s*/, "") if implied_root # Initial ">" is implied (but ">>" is not)
+      str
     end
 
     # @return [Regexp] Regexp representation of the expression as a string (does not include flags)
     def as_regexp
-      "^#{@tiers.map(&:as_regexp).join}"
+      "^#{@tiers.map(&:as_regexp).join}#{'$' if @strict}"
     end
 
     # @return [String] Regexp representation of the expression
@@ -65,6 +72,7 @@ module TieredCategoryExpressions
     #
     # @param category [Array<String>] Category to match
     # @return [Boolean]
+    #
     def matches?(category)
       to_regexp.match?(Preprocessor.call(category))
     end
@@ -89,14 +97,21 @@ module TieredCategoryExpressions
     # @return [Expression]
     #
     def >(other)
-      self.class.new(@tiers + TieredCategoryExpressions::TCE(other).tiers)
+      TieredCategoryExpressions::TCE(to_s + TieredCategoryExpressions::TCE(other).to_s(implied_root: false))
+    end
+
+    # @return [Boolean] +true+ if the TCE object does not match categories with tiers that extend beyond those
+    #   specified by the TCE. This is the case when the TCE ends with ".".
+    #
+    def strict?
+      @strict
     end
 
     # Returns an SQL LIKE query that may be used to speed up certain SQL queries.
     #
     # SQL queries that involve matching some input against stored TCE regexps can be slow. Possibly, they can be
     # optimized by applying a much faster LIKE query first, which reduces the number of regexps to apply. The LIKE
-    # query alone still yields false positives, so it must be combined with the corresponding regexp.
+    # query alone can still yield false positives, so it must be combined with the corresponding regexp.
     #
     # For instance:
     #
@@ -109,7 +124,9 @@ module TieredCategoryExpressions
     # Depending on the TCEs in the _mappings_ table.
     #
     def as_sql_like_query
-      @tiers.map(&:as_sql_like_query).join + "%"
+      q = @tiers.map(&:as_sql_like_query).join
+      q += "%" unless @strict || q.end_with?("%")
+      q
     end
 
     protected

data/lib/tiered_category_expressions/generator.rb

@@ -11,14 +11,18 @@ module TieredCategoryExpressions
       #  # => TieredCategoryExpressions::Expression[Nonfood > Baby > Baby formula]
       #
       # @param category [Array<String>]
+      # @param strict [Boolean] If +true+ is given then the resulting TCE will not match subcategories of the given
+      #   category.
       # @return [Expression, nil]
       #
-      def call(category)
+      def call(category, strict: false)
         return if category.empty?
 
         tiers = category.map { |t| sanitize_name(t) or return nil }
+        expression = tiers.join(">")
+        expression << "." if strict
 
-        TieredCategoryExpressions::TCE(tiers.join(" > "))
+        TieredCategoryExpressions::TCE(expression)
       end
 
       private

data/lib/tiered_category_expressions/parser.rb

@@ -17,9 +17,16 @@ module TieredCategoryExpressions
 
     rule(:word)      { (match["[:alnum:]"] | str("%")).repeat(1) >> space? }
     rule(:name)      { word.repeat(1).as(:name) }
-    rule(:namelist)  { (name >> (namesep >> name).repeat).as(:namelist) }
+    rule(:namelist)  { (name.repeat(1, 1) >> (namesep >> name).repeat).as(:namelist) }
+
+    rule(:stop)      { str(".") >> space? }
+
+    rule(:tier1)     { (connector | negator).maybe.as(:operator) >> namelist }
+    rule(:tier)      { connector.as(:operator) >> namelist }
+    rule(:tiers)     { tier.repeat >> (stop >> (tier.repeat(1, 1) >> tiers).as(:tail)).maybe }
+
+    rule(:tce)       { space? >> (tier1.repeat(1, 1) >> tiers).as(:tiers) >> stop.maybe.as(:eoct) }
 
-    rule(:tce)       { space? >> (((connector | negator).as(:operator).maybe >> namelist).as(:tier) >> (connector.as(:operator) >> namelist).as(:tier).repeat).as(:expression) }
     root(:tce)
   end
 end

data/lib/tiered_category_expressions/tail.rb

@@ -0,0 +1,19 @@
+module TieredCategoryExpressions
+  class Tail
+    def initialize(tiers)
+      @tiers = tiers
+    end
+
+    def to_s
+      ". " + @tiers.join(" ")
+    end
+
+    def as_regexp
+      "($|(#{@tiers.map(&:as_regexp).join}))"
+    end
+
+    def as_sql_like_query
+      "%"
+    end
+  end
+end

data/lib/tiered_category_expressions/tiers.rb

@@ -1,5 +1,18 @@
 module TieredCategoryExpressions
   class Tier < Struct.new(:operator, :namelist)
+    def self.build(operator, names)
+      klass = case operator&.to_s&.tr(" ", "")
+      when ">",  nil then Child
+      when ">!", "!" then IChild
+      when ">>"      then Descendant
+      when ">>!"     then IDescendant
+      else raise "no such operator #{operator.inspect}"
+      end
+
+      namelist = Namelist.new(names)
+      klass.new(namelist)
+    end
+
     def to_s
       "#{operator} #{namelist}"
     end
@@ -32,7 +45,7 @@ module TieredCategoryExpressions
       end
 
       def as_regexp
-        "(?!#{namelist.as_regexp}>).+>"
+        "(?!#{namelist.as_regexp}>)[a-z0-9]+>"
       end
 
       def as_sql_like_query
@@ -46,7 +59,7 @@ module TieredCategoryExpressions
       end
 
       def as_regexp
-        "(.+>)*#{namelist.as_regexp}>"
+        "([a-z0-9]+>)*#{namelist.as_regexp}>"
       end
 
       def as_sql_like_query
@@ -60,7 +73,7 @@ module TieredCategoryExpressions
       end
 
       def as_regexp
-        "(?!(.+>)*#{namelist.as_regexp}>).+>"
+        "(?!([a-z0-9]+>)*#{namelist.as_regexp}>)([a-z0-9]+>)+"
       end
 
       def as_sql_like_query

data/lib/tiered_category_expressions/transformer.rb

@@ -2,25 +2,25 @@ require "parslet"
 require "tiered_category_expressions/name"
 require "tiered_category_expressions/namelist"
 require "tiered_category_expressions/tiers"
+require "tiered_category_expressions/tail"
 require "tiered_category_expressions/expression"
 
 module TieredCategoryExpressions
   class Transformer < Parslet::Transform
-    rule(:name => simple(:name)) { Name.new(name.to_s) }
+    rule(:name => simple(:name)) do
+      Name.new(name.to_s)
+    end
 
-    rule(:tier => subtree(:tier)) do
-      klass = case tier[:operator]&.to_s&.tr(" ", "")
-      when ">",  nil then Tier::Child
-      when ">!", "!" then Tier::IChild
-      when ">>"      then Tier::Descendant
-      when ">>!"     then Tier::IDescendant
-      else raise "no such operator #{tier[:operator].inspect}"
-      end
+    rule(:operator => simple(:op), :namelist => sequence(:names)) do
+      Tier.build(op, names)
+    end
 
-      namelist = Namelist.new([tier[:namelist]].flatten)
-      klass.new(namelist)
+    rule(:tail => sequence(:tiers)) do
+      Tail.new(tiers)
     end
 
-    rule(:expression => subtree(:tiers)) { Expression.new([tiers].flatten) }
+    rule(:tiers => sequence(:tiers), :eoct => simple(:eoct)) do
+      Expression.new(tiers, strict: !!eoct)
+    end
   end
 end

data/lib/tiered_category_expressions/version.rb

@@ -1,3 +1,3 @@
 module TieredCategoryExpressions
-  VERSION = "0.1.3"
+  VERSION = "0.3.0"
 end

data/tiered_category_expressions.gemspec

@@ -29,10 +29,5 @@ Gem::Specification.new do |spec|
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
   spec.require_paths = ["lib"]
 
-  spec.add_development_dependency "bundler", "~> 1.13"
-  spec.add_development_dependency "rake", "~> 10.0"
-  spec.add_development_dependency "rspec", "~> 3.0"
-  spec.add_development_dependency "pry"
-  spec.add_development_dependency "pry-coolline"
-  spec.add_runtime_dependency "parslet", "~> 1.8"
+  spec.add_runtime_dependency "parslet", "~> 2.0"
 end

metadata

@@ -1,99 +1,29 @@
 --- !ruby/object:Gem::Specification
 name: tiered_category_expressions
 version: !ruby/object:Gem::Version
-  version: 0.1.3
+  version: 0.3.0
 platform: ruby
 authors:
 - Sjoerd Andringa
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2019-05-03 00:00:00.000000000 Z
+date: 2023-08-22 00:00:00.000000000 Z
 dependencies:
-- !ruby/object:Gem::Dependency
-  name: bundler
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1.13'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1.13'
-- !ruby/object:Gem::Dependency
-  name: rake
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '10.0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '10.0'
-- !ruby/object:Gem::Dependency
-  name: rspec
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '3.0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '3.0'
-- !ruby/object:Gem::Dependency
-  name: pry
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: pry-coolline
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
 - !ruby/object:Gem::Dependency
   name: parslet
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.8'
+        version: '2.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.8'
+        version: '2.0'
 description: 
 email:
 - sjoerd@thequestionmark.org
@@ -101,10 +31,11 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- ".github/dependabot.yml"
+- ".github/workflows/main.yml"
 - ".gitignore"
 - ".rspec"
 - ".ruby-version"
-- ".travis.yml"
 - ".yardopts"
 - Gemfile
 - LANGREF.md
@@ -122,6 +53,7 @@ files:
 - lib/tiered_category_expressions/namelist.rb
 - lib/tiered_category_expressions/parser.rb
 - lib/tiered_category_expressions/preprocessor.rb
+- lib/tiered_category_expressions/tail.rb
 - lib/tiered_category_expressions/tiers.rb
 - lib/tiered_category_expressions/transformer.rb
 - lib/tiered_category_expressions/util.rb
@@ -147,8 +79,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.6.14.3
+rubygems_version: 3.1.6
 signing_key: 
 specification_version: 4
 summary: Tiered category expressions

data/.travis.yml

@@ -1,5 +0,0 @@
-sudo: false
-language: ruby
-rvm:
-  - 2.4.5
-before_install: gem install bundler -v 1.13.6