path_list 0.16

data/lib/path_list/patterns.rb

@@ -0,0 +1,33 @@
+# frozen-string-literal: true
+
+class PathList
+  class Patterns
+    def initialize(*patterns, from_file: nil, format: :gitignore, root: nil)
+      raise ArgumentError, "from_file: can't be used with patterns arguments" unless patterns.empty? || !from_file
+
+      @format = format
+      if from_file
+        @root = root || ::File.dirname(from_file)
+        @patterns = ::File.exist?(from_file) ? ::File.readlines(from_file) : []
+      else
+        @root = root || ::Dir.pwd
+        @patterns = patterns.flatten.flat_map { |string| string.to_s.lines }
+      end
+      @root += '/' unless @root.end_with?('/')
+    end
+
+    def build_matchers(include: false)
+      matchers = @patterns.flat_map { |p| ::PathList::RuleBuilder.build(p, include, @format, @root) }
+
+      return if matchers.empty?
+      return [::PathList::Matchers::WithinDir.new(matchers, @root)] unless include
+
+      [
+        ::PathList::Matchers::WithinDir.new(matchers, @root),
+        ::PathList::Matchers::WithinDir.new(
+          ::PathList::GitignoreIncludeRuleBuilder.new(@root).build_as_parent, '/'
+        )
+      ]
+    end
+  end
+end

data/lib/path_list/relative_candidate.rb

@@ -0,0 +1,20 @@
+# frozen-string-literal: true
+
+class PathList
+  class RelativeCandidate
+    attr_reader :relative_path
+
+    def initialize(relative_path, root_candidate)
+      @relative_path = relative_path
+      @root_candidate = root_candidate
+    end
+
+    def filename
+      @root_candidate.filename
+    end
+
+    def first_line
+      @root_candidate.first_line
+    end
+  end
+end

data/lib/path_list/root_candidate.rb

@@ -0,0 +1,56 @@
+# frozen-string-literal: true
+
+class PathList
+  class RootCandidate
+    attr_reader :full_path
+
+    def initialize(full_path, filename, directory, content)
+      @full_path = full_path
+      @filename = filename
+      (@directory = directory) unless directory.nil?
+      @first_line = content
+    end
+
+    def parent
+      @parent ||= ::PathList::RootCandidate.new(
+        ::File.dirname(@full_path),
+        nil,
+        true,
+        nil
+      )
+    end
+
+    def relative_to(dir)
+      return unless @full_path.start_with?(dir)
+
+      ::PathList::RelativeCandidate.new(@full_path.delete_prefix(dir), self)
+    end
+
+    def directory?
+      return @directory if defined?(@directory)
+
+      @directory ||= ::File.directory?(@full_path)
+    end
+
+    def filename
+      @filename ||= ::File.basename(@full_path)
+    end
+
+    # how long can a shebang be?
+    # https://www.in-ulm.de/~mascheck/various/shebang/
+    # 512 feels like a reasonable limit
+    def first_line # rubocop:disable Metrics/MethodLength
+      @first_line ||= begin
+        file = ::File.new(@full_path)
+        first_line = new_fragment = file.sysread(512)
+        file.close
+        first_line || ''
+      rescue ::EOFError, ::SystemCallError
+        # :nocov:
+        file&.close
+        # :nocov:
+        first_line || ''
+      end
+    end
+  end
+end

data/lib/path_list/rule_builder.rb

@@ -0,0 +1,42 @@
+# frozen_string_literal: true
+
+class PathList
+  module RuleBuilder
+    class << self
+      # :nocov:
+      using ::PathList::Backports::DeletePrefixSuffix if defined?(::PathList::Backports::DeletePrefixSuffix)
+      # :nocov:
+
+      def build(rule, allow, format, root)
+        if rule.delete_prefix!('#!:')
+          shebang_rules(rule, allow)
+        else
+          gitignore_rules(rule, allow, format, root)
+        end
+      end
+
+      private
+
+      # how long can a shebang be?
+      # https://www.in-ulm.de/~mascheck/various/shebang/
+      # Theoretically the limit is 65536, but that feels utterly unreasonable
+      def shebang_rules(shebang, allow)
+        shebang.strip!
+        pattern = /\A#![^\n]{,#{510 - shebang.length}}\b#{::Regexp.escape(shebang)}\b/i
+        rule = ::PathList::Matchers::ShebangRegexp.new(pattern, allow)
+        return rule unless allow
+
+        # also allow all directories in case they include a file with the matching shebang file
+        [::PathList::Matchers::AllowAnyDir, rule]
+      end
+
+      def gitignore_rules(rule, allow, format, root)
+        if allow
+          ::PathList::GitignoreIncludeRuleBuilder.new(rule, expand_path_with: (root if format == :expand_path)).build
+        else
+          ::PathList::GitignoreRuleBuilder.new(rule).build
+        end
+      end
+    end
+  end
+end

data/lib/path_list/rule_group.rb

@@ -0,0 +1,42 @@
+# frozen_string_literal: true
+
+class PathList
+  class RuleGroup
+    def initialize(patterns, allow)
+      @matchers = Array(patterns).flat_map { |x| x.build_matchers(include: allow) }.compact
+      @allow = allow
+      @allowed_recursive = { '/' => true }
+    end
+
+    def empty?
+      @matchers.empty? || @matchers.all?(&:empty?)
+    end
+
+    def weight
+      @matchers.sum(&:weight)
+    end
+
+    def freeze
+      @matchers.freeze
+
+      super
+    end
+
+    def allowed_recursive?(root_candidate)
+      @allowed_recursive.fetch(root_candidate.full_path) do
+        @allowed_recursive[root_candidate.full_path] =
+          allowed_recursive?(root_candidate.parent) &&
+          allowed_unrecursive?(root_candidate)
+      end
+    end
+
+    def allowed_unrecursive?(root_candidate)
+      @matchers.reverse_each do |matcher|
+        val = matcher.match?(root_candidate)
+        return val == :allow if val
+      end
+
+      not @allow
+    end
+  end
+end

data/lib/path_list/rule_groups.rb

@@ -0,0 +1,59 @@
+# frozen_string_literal: true
+
+class PathList
+  class RuleGroups
+    # :nocov:
+    using ::PathList::Backports::DeletePrefixSuffix if defined?(::PathList::Backports::DeletePrefixSuffix)
+    # :nocov:
+
+    def initialize( # rubocop:disable Metrics/ParameterLists, Metrics/AbcSize, Metrics/MethodLength
+      root:,
+      ignore_rules: nil,
+      ignore_files: nil,
+      gitignore: true,
+      include_rules: nil,
+      include_files: nil,
+      argv_rules: nil
+    )
+      @array = []
+      if gitignore
+        @gitignore_rule_group = ::PathList::GitignoreRuleGroup.new(root)
+        @array << @gitignore_rule_group
+      end
+      @array << ::PathList::RuleGroup.new(::PathList::Patterns.new(ignore_rules, root: root), false).freeze
+      @array << ::PathList::RuleGroup.new(::PathList::Patterns.new(include_rules, root: root), true).freeze
+      @array << ::PathList::RuleGroup.new(
+        ::PathList::Patterns.new(argv_rules, root: root, format: :expand_path),
+        true
+      ).freeze
+
+      Array(ignore_files).each do |f|
+        path = ::File.expand_path(f, root)
+        @array << ::PathList::RuleGroup.new(::PathList::Patterns.new(from_file: path), false).freeze
+      end
+      Array(include_files).each do |f|
+        path = ::File.expand_path(f, root)
+        @array << ::PathList::RuleGroup.new(::PathList::Patterns.new(from_file: path), true).freeze
+      end
+      @array.reject!(&:empty?)
+      @array.sort_by!(&:weight)
+      @array.freeze
+    end
+
+    def allowed_recursive?(candidate)
+      @array.all? { |r| r.allowed_recursive?(candidate) }
+    end
+
+    def allowed_unrecursive?(candidate)
+      @array.all? { |r| r.allowed_unrecursive?(candidate) }
+    end
+
+    def add_gitignore(dir)
+      @gitignore_rule_group.add_gitignore(dir)
+    end
+
+    def add_gitignore_to_root(path)
+      @gitignore_rule_group.add_gitignore_to_root(path)
+    end
+  end
+end

data/lib/path_list/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+class PathList
+  VERSION = '0.16'
+end

data/lib/path_list/walkers/file_system.rb

@@ -0,0 +1,45 @@
+# frozen-string-literal: true
+
+class PathList
+  module Walkers
+    class FileSystem
+      def initialize(rule_groups)
+        @rule_groups = rule_groups
+      end
+
+      def allowed?(path, directory: nil, content: nil)
+        full_path = ::File.expand_path(path)
+
+        return false if directory.nil? ? ::File.lstat(full_path).directory? : directory
+
+        candidate = ::PathList::RootCandidate.new(full_path, nil, directory, content)
+        @rule_groups.allowed_recursive?(candidate)
+      rescue ::Errno::ENOENT, ::Errno::EACCES, ::Errno::ENOTDIR, ::Errno::ELOOP, ::Errno::ENAMETOOLONG
+        false
+      end
+
+      def each(parent_full_path, parent_relative_path, &block) # rubocop:disable Metrics/MethodLength
+        children = ::Dir.children(parent_full_path)
+
+        children.each do |filename|
+          begin
+            full_path = parent_full_path + filename
+            relative_path = parent_relative_path + filename
+            dir = ::File.lstat(full_path).directory?
+            candidate = ::PathList::RootCandidate.new(full_path, filename, dir, nil)
+
+            next unless @rule_groups.allowed_unrecursive?(candidate)
+
+            if dir
+              each(full_path + '/', relative_path + '/', &block)
+            else
+              yield relative_path
+            end
+          rescue ::Errno::ENOENT, ::Errno::EACCES, ::Errno::ENOTDIR, ::Errno::ELOOP, ::Errno::ENAMETOOLONG
+            nil
+          end
+        end
+      end
+    end
+  end
+end

data/lib/path_list/walkers/gitignore_collecting_file_system.rb

@@ -0,0 +1,47 @@
+# frozen-string-literal: true
+
+class PathList
+  module Walkers
+    class GitignoreCollectingFileSystem
+      def initialize(rule_groups)
+        @rule_groups = rule_groups
+      end
+
+      def allowed?(path, directory: nil, content: nil)
+        full_path = ::File.expand_path(path)
+        return false if directory.nil? ? ::File.lstat(full_path).directory? : directory
+
+        @rule_groups.add_gitignore_to_root(full_path)
+
+        candidate = ::PathList::RootCandidate.new(full_path, nil, directory, content)
+        @rule_groups.allowed_recursive?(candidate)
+      rescue ::Errno::ENOENT, ::Errno::EACCES, ::Errno::ENOTDIR, ::Errno::ELOOP, ::Errno::ENAMETOOLONG
+        false
+      end
+
+      def each(parent_full_path, parent_relative_path, &block) # rubocop:disable Metrics/MethodLength
+        children = ::Dir.children(parent_full_path)
+        @rule_groups.add_gitignore(parent_full_path) if children.include?('.gitignore')
+
+        children.each do |filename|
+          begin
+            full_path = parent_full_path + filename
+            relative_path = parent_relative_path + filename
+            dir = ::File.lstat(full_path).directory?
+            candidate = ::PathList::RootCandidate.new(full_path, filename, dir, nil)
+
+            next unless @rule_groups.allowed_unrecursive?(candidate)
+
+            if dir
+              each(full_path + '/', relative_path + '/', &block)
+            else
+              yield relative_path
+            end
+          rescue ::Errno::ENOENT, ::Errno::EACCES, ::Errno::ENOTDIR, ::Errno::ELOOP, ::Errno::ENAMETOOLONG
+            nil
+          end
+        end
+      end
+    end
+  end
+end

metadata

@@ -0,0 +1,198 @@
+--- !ruby/object:Gem::Specification
+name: path_list
+version: !ruby/object:Gem::Version
+  version: '0.16'
+platform: ruby
+authors:
+- Dana Sherson
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2021-03-11 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '1.17'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '1.17'
+- !ruby/object:Gem::Dependency
+  name: leftovers
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.4.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.4.0
+- !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: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 12.3.3
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 12.3.3
+- !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: rubocop
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.93.1
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.93.1
+- !ruby/object:Gem::Dependency
+  name: rubocop-rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.44.1
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.44.1
+- !ruby/object:Gem::Dependency
+  name: simplecov
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.18.5
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.18.5
+- !ruby/object:Gem::Dependency
+  name: simplecov-console
+  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'
+description:
+email:
+- robot@dana.sh
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- CHANGELOG.md
+- LICENSE.txt
+- README.md
+- lib/path_list.rb
+- lib/path_list/backports.rb
+- lib/path_list/gitignore_include_rule_builder.rb
+- lib/path_list/gitignore_rule_builder.rb
+- lib/path_list/gitignore_rule_group.rb
+- lib/path_list/gitignore_rule_scanner.rb
+- lib/path_list/global_gitignore.rb
+- lib/path_list/matchers/allow_any_dir.rb
+- lib/path_list/matchers/allow_path_regexp.rb
+- lib/path_list/matchers/ignore_path_regexp.rb
+- lib/path_list/matchers/shebang_regexp.rb
+- lib/path_list/matchers/unmatchable.rb
+- lib/path_list/matchers/within_dir.rb
+- lib/path_list/path_regexp_builder.rb
+- lib/path_list/patterns.rb
+- lib/path_list/relative_candidate.rb
+- lib/path_list/root_candidate.rb
+- lib/path_list/rule_builder.rb
+- lib/path_list/rule_group.rb
+- lib/path_list/rule_groups.rb
+- lib/path_list/version.rb
+- lib/path_list/walkers/file_system.rb
+- lib/path_list/walkers/gitignore_collecting_file_system.rb
+homepage: https://github.com/robotdana/path_list
+licenses:
+- MIT
+metadata:
+  homepage_uri: https://github.com/robotdana/path_list
+  source_code_uri: https://github.com/robotdana/path_list
+  changelog_uri: https://github.com/robotdana/path_list/blob/main/CHANGELOG.md
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.4.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.1.2
+signing_key:
+specification_version: 4
+summary: Parse gitignore files, quickly
+test_files: []