licensee 9.12.0 → 9.14.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d7dc009b0467cfb305e8dac051ed4e78d2f35d0454f2e14cef0952338540f8ae
-  data.tar.gz: 3c27bb3dd3cea6d62fab826b81fab93d9152893851b541c91d69406cdf9fcbd8
+  metadata.gz: 0cdac44039e6185c028d41ab8112b43d7e1ba66f2c8bd02be490255d14dfac38
+  data.tar.gz: 895ffc0aa9296fef49193b6282edb6286a9115ba4b3207be4c15df5755ca3bf7
 SHA512:
-  metadata.gz: 07f19b33f70b0b73611d34e474f2aa4e4d7f62c7451cdf70f76774beceac2c75ab3d1cc5048061a848b979a54032aad6dd1ba278c79cd798029efd6873d54425
-  data.tar.gz: 96c5e66f65307e7feb2c00b3f06661b093c60995d049f7fd19cc27b76881965a1d33768a16b0a3a3b085e9392ef828dce9cf692ee04255dd9ea2c6d22da38da6
+  metadata.gz: eb7c6c9d1b2a8c8258b8d499efa96ab7b25b83108bb47ed163eabd5d78e83a2443a0bbf6f43eb1abda0b441e8696a17f79066ec4356c80a1b88d3c40338c726b
+  data.tar.gz: e1bfeb5c75d28b334d880351acf7977c71e5efa9b61c407c204921475070c3ede8b2331b82cc64446fa81577ede499cf8d2d5b6d70ae1fc507cc238ee4a52a08

data/LICENSE.md

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2014-2017 Ben Balter
+Copyright (c) 2014-2020 Ben Balter and Licensee contributors
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

data/bin/licensee

@@ -16,9 +16,9 @@ class LicenseeCLI < Thor
 
   def path
     @path ||= if !options[:remote] || args.first =~ %r{^https://}
-      args.first || Dir.pwd
-    else
-      "https://github.com/#{args.first}"
+                args.first || Dir.pwd
+              else
+                "https://github.com/#{args.first}"
     end
   end
 
@@ -33,6 +33,6 @@ class LicenseeCLI < Thor
 end
 
 commands_dir = File.expand_path '../lib/licensee/commands/', __dir__
-Dir["#{commands_dir}/*.rb"].each { |c| require(c) }
+Dir["#{commands_dir}/*.rb"].sort.each { |c| require(c) }
 
 LicenseeCLI.start(ARGV)

data/lib/licensee.rb

@@ -38,12 +38,12 @@ module Licensee
 
     def project(path, **args)
       if path =~ %r{\Ahttps://github.com}
-        Licensee::Projects::GitHubProject.new(path, args)
+        Licensee::Projects::GitHubProject.new(path, **args)
       else
-        Licensee::Projects::GitProject.new(path, args)
+        Licensee::Projects::GitProject.new(path, **args)
       end
     rescue Licensee::Projects::GitProject::InvalidRepository
-      Licensee::Projects::FSProject.new(path, args)
+      Licensee::Projects::FSProject.new(path, **args)
     end
 
     def confidence_threshold

data/lib/licensee/commands/detect.rb

@@ -23,11 +23,11 @@ class LicenseeCLI < Thor
 
     rows = []
     rows << if project.license
-      ['License:', project.license.spdx_id]
-    elsif !project.licenses.empty?
-      ['Licenses:', project.licenses.map(&:spdx_id)]
-    else
-      ['License:', set_color('None', :red)]
+              ['License:', project.license.spdx_id]
+            elsif !project.licenses.empty?
+              ['Licenses:', project.licenses.map(&:spdx_id)]
+            else
+              ['License:', set_color('None', :red)]
     end
 
     unless project.matched_files.empty?
@@ -88,7 +88,7 @@ class LicenseeCLI < Thor
     when :confidence
       Licensee::ContentHelper.format_percent(value)
     when :method
-      value.to_s.tr('_', ' ').capitalize + ':'
+      "#{value.to_s.tr('_', ' ').capitalize}:"
     else
       value
     end

data/lib/licensee/commands/diff.rb

@@ -41,10 +41,10 @@ class LicenseeCLI < Thor
 
   def license_to_diff
     return options[:license_to_diff] if options[:license_to_diff]
-    return project.license_file if remote? || STDIN.tty? && project.license_file
+    return project.license_file if remote? || $stdin.tty? && project.license_file
 
     @license_to_diff ||= begin
-      Licensee::ProjectFiles::LicenseFile.new(STDIN.read, 'LICENSE')
+      Licensee::ProjectFiles::LicenseFile.new($stdin.read, 'LICENSE')
     end
   end
 

data/lib/licensee/content_helper.rb

@@ -7,24 +7,28 @@ module Licensee
   module ContentHelper
     DIGEST = Digest::SHA1
     START_REGEX = /\A\s*/.freeze
-    END_OF_TERMS_REGEX = /^[\s#*_]*end of terms and conditions\s*$/i.freeze
-    ALT_TITLE_REGEX = License::ALT_TITLE_REGEX
+    END_OF_TERMS_REGEX = /^[\s#*_]*end of terms and conditions[\s#*_]*$/i.freeze
     REGEXES = {
-      hrs:                 /^\s*[=\-\*]{3,}\s*$/,
+      bom:                 /#{START_REGEX}\xEF\xBB\xBF/,
+      hrs:                 /^\s*[=\-*]{3,}\s*$/,
       all_rights_reserved: /#{START_REGEX}all rights reserved\.?$/i,
       whitespace:          /\s+/,
-      markdown_headings:   /#{START_REGEX}#+/,
+      markdown_headings:   /^\s*#+/,
       version:             /#{START_REGEX}version.*$/i,
       span_markup:         /[_*~]+(.*?)[_*~]+/,
       link_markup:         /\[(.+?)\]\(.+?\)/,
       block_markup:        /^\s*>/,
-      border_markup:       /^[\*-](.*?)[\*-]$/,
-      comment_markup:      %r{^\s*?[/\*]{1,2}},
+      border_markup:       /^[*-](.*?)[*-]$/,
+      comment_markup:      %r{^\s*?[/*]{1,2}},
       url:                 %r{#{START_REGEX}https?://[^ ]+\n},
-      bullet:              /\n\n\s*(?:[*-]|\(?[\da-z]{1,2}[)\.])\s+/i,
+      bullet:              /\n\n\s*(?:[*-]|\(?[\da-z]{1,2}[).])\s+/i,
       developed_by:        /#{START_REGEX}developed by:.*?\n\n/im,
       quote_begin:         /[`'"‘“]/,
       quote_end:           /[`'"’”]/,
+      cc_legal_code:       /^\s*Creative Commons Legal Code\s*$/i,
+      cc0_info:            /For more information, please see\s*\S+zero\S+/im,
+      cc0_disclaimer:      /CREATIVE COMMONS CORPORATION.*?\n\n/im,
+      unlicense_info:      /For more information, please.*\S+unlicense\S+/im,
       mit_optional:        /\(including the next paragraph\)/i
     }.freeze
     NORMALIZATIONS = {
@@ -85,43 +89,51 @@ module Licensee
       'owner'           => 'holder'
     }.freeze
     STRIP_METHODS = %i[
-      hrs markdown_headings borders title version url copyright
-      block_markup span_markup link_markup
-      all_rights_reserved developed_by end_of_terms whitespace
+      bom
+      cc0_optional
+      unlicense_optional
+      hrs
+      markdown_headings
+      borders
+      title
+      version
+      url
+      copyright
+      title
+      block_markup
+      link_markup
+      developed_by
+      end_of_terms
+      whitespace
       mit_optional
     ].freeze
 
     # A set of each word in the license, without duplicates
     def wordset
-      @wordset ||= content_normalized&.scan(/(?:\w(?:'s|(?<=s)')?)+/)&.to_set
+      @wordset ||= content_normalized&.scan(%r{(?:[\w/](?:'s|(?<=s)')?)+})&.to_set
     end
 
-    # Number of characteres in the normalized content
+    # Number of characters in the normalized content
     def length
       return 0 unless content_normalized
 
       content_normalized.length
     end
 
-    # Number of characters that could be added/removed to still be
-    # considered a potential match
-    def max_delta
-      @max_delta ||= (length * Licensee.inverse_confidence_threshold).to_i
-    end
-
     # Given another license or project file, calculates the difference in length
     def length_delta(other)
       (length - other.length).abs
     end
 
     # Given another license or project file, calculates the similarity
-    # as a percentage of words in common
+    # as a percentage of words in common, minus a tiny penalty that
+    # increases with size difference between licenses so that false
+    # positives for long licnses are ruled out by this score alone.
     def similarity(other)
-      wordset_fieldless = wordset - LicenseField.keys
-      fields_removed = wordset.size - wordset_fieldless.size
       overlap = (wordset_fieldless & other.wordset).size
-      total = wordset_fieldless.size + other.wordset.size - fields_removed
-      100.0 * (overlap * 2.0 / total)
+      total = wordset_fieldless.size + other.wordset.size -
+              fields_normalized_set.size
+      (overlap * 200.0) / (total + fields_adjusted_length_delta(other) / 10)
     end
 
     # SHA1 of the normalized content
@@ -146,7 +158,7 @@ module Licensee
       @content_normalized ||= begin
         @_content = content_without_title_and_version.downcase
 
-        (NORMALIZATIONS.keys + %i[spelling bullets]).each { |op| normalize(op) }
+        (NORMALIZATIONS.keys + %i[spelling span_markup bullets]).each { |op| normalize(op) }
         STRIP_METHODS.each { |op| strip(op) }
 
         _content
@@ -250,16 +262,30 @@ module Licensee
     end
 
     def strip_copyright
-      regex = Matchers::Copyright::REGEX
+      regex = Regexp.union(Matchers::Copyright::REGEX, REGEXES[:all_rights_reserved])
       strip(regex) while _content =~ regex
     end
 
+    def strip_cc0_optional
+      return unless _content.include? 'associating cc0'
+
+      strip(REGEXES[:cc_legal_code])
+      strip(REGEXES[:cc0_info])
+      strip(REGEXES[:cc0_disclaimer])
+    end
+
+    def strip_unlicense_optional
+      return unless _content.include? 'unlicense'
+
+      strip(REGEXES[:unlicense_info])
+    end
+
     def strip_end_of_terms
       body, _partition, _instructions = _content.partition(END_OF_TERMS_REGEX)
       @_content = body
     end
 
-    def strip_span_markup
+    def normalize_span_markup
       normalize(REGEXES[:span_markup], '\1')
     end
 
@@ -296,5 +322,25 @@ module Licensee
       normalize(REGEXES[:bullet], "\n\n* ")
       normalize(/\)\s+\(/, ')(')
     end
+
+    def wordset_fieldless
+      @wordset_fieldless ||= wordset - fields_normalized_set
+    end
+
+    # Returns an array of strings of substitutable fields in normalized content
+    def fields_normalized
+      @fields_normalized ||=
+        content_normalized.scan(LicenseField::FIELD_REGEX).flatten
+    end
+
+    def fields_normalized_set
+      @fields_normalized_set ||= fields_normalized.to_set
+    end
+
+    def fields_adjusted_length_delta(other)
+      delta = length_delta(other)
+      adjusted_delta = delta - fields_normalized.size * 2
+      adjusted_delta.positive? ? adjusted_delta : delta
+    end
   end
 end

data/lib/licensee/hash_helper.rb

@@ -8,11 +8,11 @@ module Licensee
         key = method.to_s.delete('?').to_sym
         value = public_send(method)
         hash[key] = if value.is_a?(Array)
-          value.map { |v| v.respond_to?(:to_h) ? v.to_h : v }
-        elsif value.respond_to?(:to_h) && !value.nil?
-          value.to_h
-        else
-          value
+                      value.map { |v| v.respond_to?(:to_h) ? v.to_h : v }
+                    elsif value.respond_to?(:to_h) && !value.nil?
+                      value.to_h
+                    else
+                      value
         end
       end
 

data/lib/licensee/license.rb

@@ -92,14 +92,8 @@ module Licensee
       pseudo:   true
     }.freeze
 
-    ALT_TITLE_REGEX = {
-      'bsd-2-clause'       => /bsd 2-clause(?: \"simplified\")?/i,
-      'bsd-3-clause'       => /bsd 3-clause(?: \"new\" or \"revised\")?/i,
-      'bsd-3-clause-clear' => /(?:clear bsd|bsd 3-clause(?: clear)?)/i
-    }.freeze
-
     SOURCE_PREFIX = %r{https?://(?:www\.)?}i.freeze
-    SOURCE_SUFFIX = %r{(?:\.html?|\.txt|\/)(?:\?[^\s]*)?}i.freeze
+    SOURCE_SUFFIX = %r{(?:\.html?|\.txt|/)(?:\?[^\s]*)?}i.freeze
 
     HASH_METHODS = %i[
       key spdx_id meta url rules fields other? gpl? lgpl? cc?
@@ -144,20 +138,22 @@ module Licensee
     def title_regex
       return @title_regex if defined? @title_regex
 
-      title_regex = ALT_TITLE_REGEX[key]
-      title_regex ||= begin
-        string = name.downcase.sub('*', 'u')
-        string.sub!(/\Athe /i, '')
-        string.sub!(/,? version /, ' ')
-        string.sub!(/v(\d+\.\d+)/, '\1')
-        string = Regexp.escape(string)
-        string = string.sub(/\\ licen[sc]e/i, '(?:\ licen[sc]e)?')
-        string = string.sub(/\\ (\d+\\.\d+)/, ',?\s+(?:version\ |v(?:\. )?)?\1')
-        string = string.sub(/\bgnu\\ /, '(?:GNU )?')
-        Regexp.new string, 'i'
-      end
-
-      parts = [title_regex, key]
+      string = name.downcase.sub('*', 'u')
+      string.sub!(/\Athe /i, '')
+      string.sub!(/,? version /, ' ')
+      string.sub!(/v(\d+\.\d+)/, '\1')
+      string = Regexp.escape(string)
+      string = string.sub(/\\ licen[sc]e/i, '(?:\ licen[sc]e)?')
+      string = string.sub(/\\ (\d+\\.\d+)/, ',?\s+(?:version\ |v(?:\. )?)?\1')
+      string = string.sub(/\bgnu\\ /, '(?:GNU )?')
+      title_regex = Regexp.new string, 'i'
+
+      string = key.sub('-', '[- ]')
+      string.sub!('.', '\.')
+      string << '(?:\ licen[sc]e)?'
+      key_regex = Regexp.new string, 'i'
+
+      parts = [title_regex, key_regex]
       if meta.nickname
         parts.push Regexp.new meta.nickname.sub(/\bGNU /i, '(?:GNU )?')
       end

data/lib/licensee/matchers.rb

@@ -12,6 +12,7 @@ module Licensee
     autoload :Exact,     'licensee/matchers/exact'
     autoload :Gemspec,   'licensee/matchers/gemspec'
     autoload :NpmBower,  'licensee/matchers/npm_bower'
+    autoload :NuGet,     'licensee/matchers/nuget'
     autoload :Package,   'licensee/matchers/package'
     autoload :Reference, 'licensee/matchers/reference'
     autoload :Spdx,      'licensee/matchers/spdx'

data/lib/licensee/matchers/cabal.rb

@@ -5,7 +5,7 @@ module Licensee
     class Cabal < Licensee::Matchers::Package
       # While we could parse the cabal file, prefer
       # a lenient regex for speed and security. Moar parsing moar problems.
-      LICENSE_REGEX = /^\s*license\s*\:\s*([a-z\-0-9\.]+)\s*$/ix.freeze
+      LICENSE_REGEX = /^\s*license\s*:\s*([a-z\-0-9.]+)\s*$/ix.freeze
       LICENSE_CONVERSIONS = {
         'GPL-2'  => 'GPL-2.0',
         'GPL-3'  => 'GPL-3.0',

data/lib/licensee/matchers/cargo.rb

@@ -4,7 +4,7 @@ module Licensee
   module Matchers
     class Cargo < Licensee::Matchers::Package
       LICENSE_REGEX = %r{
-        ^\s*[\'\"]?license[\'\"]?\s*=\s*[\'\"]([a-z\-0-9\. +()\/]+)[\'\"]\s*
+        ^\s*['"]?license['"]?\s*=\s*['"]([a-z\-0-9. +()/]+)['"]\s*
       }ix.freeze
 
       private

data/lib/licensee/matchers/copyright.rb

@@ -5,10 +5,10 @@ module Licensee
     class Copyright < Licensee::Matchers::Matcher
       attr_reader :file
 
-      # rubocop:disable Metrics/LineLength
+      # rubocop:disable Layout/LineLength
       COPYRIGHT_SYMBOLS = Regexp.union([/copyright/i, /\(c\)/i, "\u00A9", "\xC2\xA9"])
-      REGEX = /#{ContentHelper::START_REGEX}(?:portions )?(\s*#{COPYRIGHT_SYMBOLS}.*$)+$/i.freeze
-      # rubocop:enable Metrics/LineLength
+      REGEX = /#{ContentHelper::START_REGEX}(?:portions )?([_*\-\s]*#{COPYRIGHT_SYMBOLS}.*$)+$/i.freeze
+      # rubocop:enable Layout/LineLength
 
       def match
         # Note: must use content, and not content_normalized here

data/lib/licensee/matchers/dice.rb

@@ -7,9 +7,9 @@ module Licensee
       # than the confidence threshold
       def match
         @match ||= if matches.empty?
-          nil
-        else
-          matches.first[0]
+                     nil
+                   else
+                     matches.first[0]
         end
       end
 
@@ -26,7 +26,7 @@ module Licensee
             if license.creative_commons? && file.potential_false_positive?
               false
             else
-              license.wordset && license.length_delta(file) <= license.max_delta
+              license.wordset
             end
           end
         end

data/lib/licensee/matchers/dist_zilla.rb

@@ -5,7 +5,7 @@ module Licensee
     class DistZilla < Licensee::Matchers::Package
       attr_reader :file
 
-      LICENSE_REGEX = /^license\s*=\s*([a-z\-0-9\._]+)/i.freeze
+      LICENSE_REGEX = /^license\s*=\s*([a-z\-0-9._]+)/i.freeze
 
       private
 

data/lib/licensee/matchers/gemspec.rb

@@ -5,7 +5,7 @@ module Licensee
     class Gemspec < Licensee::Matchers::Package
       # a value is a string surrounded by any amount of whitespace
       # optionally ended with (non-captured) ".freeze"
-      VALUE_REGEX = /\s*[\'\"]([a-z\-0-9\.]+)[\'\"](?:\.freeze)?\s*/i.freeze
+      VALUE_REGEX = /\s*['"]([a-z\-0-9.]+)['"](?:\.freeze)?\s*/i.freeze
 
       # an array contains one or more values. all values, or array itself,
       # can be surrounded by any amount of whitespace.  do not capture
@@ -13,15 +13,15 @@ module Licensee
       ARRAY_REGEX = /\s*\[#{VALUE_REGEX}(?:,#{VALUE_REGEX})*\]\s*/i.freeze
 
       DECLARATION_REGEX = /
-        ^\s*[a-z0-9_]+\.([a-z0-9_]+)\s*\=#{VALUE_REGEX}$
+        ^\s*[a-z0-9_]+\.([a-z0-9_]+)\s*=#{VALUE_REGEX}$
       /ix.freeze
 
       LICENSE_REGEX = /
-        ^\s*[a-z0-9_]+\.license\s*\=#{VALUE_REGEX}$
+        ^\s*[a-z0-9_]+\.license\s*=#{VALUE_REGEX}$
       /ix.freeze
 
       LICENSE_ARRAY_REGEX = /
-        ^\s*[a-z0-9_]+\.licenses\s*\=#{ARRAY_REGEX}$
+        ^\s*[a-z0-9_]+\.licenses\s*=#{ARRAY_REGEX}$
       /ix.freeze
 
       private

data/lib/licensee/matchers/npm_bower.rb

@@ -6,14 +6,17 @@ module Licensee
       # While we could parse the package.json or bower.json file, prefer
       # a lenient regex for speed and security. Moar parsing moar problems.
       LICENSE_REGEX = /
-        \s*[\"\']license[\"\']\s*\:\s*[\'\"]([a-z\-0-9\.+ ()]+)[\'\"],?\s*
+        \s*["']license["']\s*:\s*['"]([a-z\-0-9.+ ()]+)['"],?\s*
       /ix.freeze
 
       private
 
       def license_property
         match = @file.content.match LICENSE_REGEX
-        match[1].downcase if match && match[1]
+        return unless match && match[1]
+        return 'no-license' if match[1] == 'UNLICENSED'
+
+        match[1].downcase
       end
     end
   end