litter 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: a6adfd002bc8d05155ebf3c70440cc438e91784d71f48ebff1fe0d4e63085572
+  data.tar.gz: 558de515de4733799ef558f38e0f3d69d12768b3bbc728d015317d151d12fee8
+SHA512:
+  metadata.gz: e598c143cb95112c5701d278117101815757faf8e372733467339dd77e2a16ffde2be378afbbc121f43bc713150dbe7f17e2bbde7bb6fdacea29b5225c9b7314
+  data.tar.gz: cfd284c206c0d12aee126563e03328acf3074d8c2dd8e6cd6f26909c596243ddb16b5e3315a552cd86d1abb69fc206b9cbc3d30280ffb5409ce105e105b7c158

data/bin/litter

@@ -0,0 +1,23 @@
+#!/usr/bin/env ruby
+
+# Parses a litter file and shows stats.
+#
+# Usage:
+# Run on the command line:
+#   litter "<file path>"
+#
+# Example:
+#   litter ~/trash.txt
+
+require_relative "../lib/litter/litter"
+require "amazing_print"
+
+path = ARGV[0]
+unless path
+  raise ArgumentError, "File path argument required."
+end
+
+# TODO show stats instead of the raw parser output.
+parsed = Litter.parse(path)
+
+ap parsed

data/lib/litter/config.rb

@@ -0,0 +1,30 @@
+module Litter
+  # Builds a hash config.
+  class Config
+    using Util::HashDeepMerge
+
+    attr_reader :hash
+
+    # @param custom_config [Hash] a custom config which overrides the defaults,
+    #   e.g. { parser: { date_sep: '-' } }
+    def initialize(custom_config = {})
+      @hash = default_config.deep_merge(custom_config)
+    end
+
+    private
+
+    # The default config, excluding Regex config (see further down).
+    # @return [Hash]
+    def default_config
+      {
+        parser:
+          {
+            date_sep: '/',
+            loc_char: '@',
+            qty_char: '*',
+            tag_char: '#',
+          },
+      }
+    end
+  end
+end

data/lib/litter/errors.rb

@@ -0,0 +1,4 @@
+module Litter
+  # Means there was a problem accessing a file.
+  class FileError < StandardError; end
+end

data/lib/litter/litter.rb

@@ -0,0 +1,15 @@
+require "parslet"
+require "date"
+
+require_relative "util/hash_deep_merge"
+require_relative "config"
+require_relative "errors"
+require_relative "parsing/litter_file"
+
+module Litter
+  # Parses a file. See Parser::LitterFile#initialize and #parse for details.
+  def self.parse(...)
+    file = Parsing::LitterFile.new(...)
+    file.parse
+  end
+end

data/lib/litter/parsing/litter_file.rb

@@ -0,0 +1,48 @@
+require_relative "parser"
+require_relative "transform"
+
+module Litter
+  module Parsing
+    class LitterFile
+      attr_reader :string, :config
+
+      # @param path [String] the path of the file to be parsed; if nil, uses file instead.
+      # @param path [File] the file to be parsed.
+      # @param config [Hash] custom config that overrides defaults in config.rb.
+      def initialize(path = nil, file: nil, config: {})
+        validate_path_or_file(path, file)
+
+        @string = path ? File.read(path) : file.read
+        @config = Config.new(config || {}).hash
+      end
+
+      # Parses the file.
+      # @return [Hash] a hash of items and their finds; see parse_test.rb for an example.
+      def parse
+        parsed = Parser.new(config[:parser]).parse(string)
+        hashes = Transform.new.apply(parsed)
+
+        hashes
+      end
+
+      private
+
+      # Checks on the given file path.
+      # @raise [FileError] if the given path is invalid.
+      # @raise [ArgumentError] if both path and file are nil.
+      def validate_path_or_file(path, file)
+        return true if file && file.respond_to?(:read)
+
+        if path
+          if !File.exist?(path)
+            raise FileError, "File not found! #{path}"
+          elsif File.directory?(path)
+            raise FileError, "A file is expected, but the path given is a directory: #{path}"
+          end
+        else
+          raise ArgumentError, "Either a string or a file path must be provided."
+        end
+      end
+    end
+  end
+end

data/lib/litter/parsing/parser.rb

@@ -0,0 +1,58 @@
+module Litter
+  module Parsing
+    # Example output from the example in parse_test.rb.
+    # Note: what looks like strings followed by "@" are actually Parslet::Slice.
+    #
+    # [{:date=>"2023/03/08"@0,
+    #   :location=>"west wildwood"@12,
+    #   :items=>
+    #    [{:name=>"car mat"@26},
+    #     {:name=>"folding chair "@34, :quantity=>"2"@49, :tag=>"kept"@52},
+    #     {:name=>"concrete-filled bucket "@57, :location=>"bridge"@81}]},
+    #  {:date=>"2023/4/1"@89,
+    #   :items=>
+    #    [{:name=>"concrete-filled bucket "@98, :quantity=>"2"@122, :location=>"west wildwood "@125, :tag=>"TODO"@140},
+    #     {:name=>"shopping cart "@145, :location=>"bridge"@160},
+    #     {:name=>"car mat "@167, :tag=>"kept"@176}]}]
+    #
+    class Parser < Parslet::Parser
+      attr_reader :config
+
+      # @param config [Hash] the parser config, such as Config#default_config[:parser]
+      def initialize(config)
+        @config = config
+        super()
+      end
+
+      rule(:newline) { str("\n") }
+      rule(:space) { match('\s').repeat(1) }
+      rule(:date_sep) { str(config.fetch(:date_sep)) }
+      rule(:loc_char) { str(config.fetch(:loc_char)) }
+      rule(:qty_char) { str(config.fetch(:qty_char)) }
+      rule(:tag_char) { str(config.fetch(:tag_char)) }
+      rule(:not_tag) { match( "[^\\n\\#{config.fetch(:tag_char)}]") }
+      rule(:not_special) {
+        match("[^\\n\\#{config[:qty_char]}\\#{config[:loc_char]}\\#{config[:tag_char]}]")
+      }
+
+      rule(:year) { match('[0-9]').repeat(4,4) }
+      rule(:day_or_month) { match('[0-9]').repeat(1,2) }
+      rule(:date) { (year >> date_sep >> day_or_month >> date_sep >> day_or_month).as(:date) }
+
+      rule(:location) { space.maybe >> loc_char >> not_tag.repeat(1).as(:location)}
+      rule(:date_line) { date >> location.maybe >> newline }
+
+      rule(:name) { not_special.repeat(1).as(:name) }
+      rule(:quantity) { qty_char >> match('[0-9]').repeat(1).as(:quantity) }
+      rule(:tag) { space.maybe >> tag_char >> match('[^\n]').repeat(1).as(:tag) }
+      rule(:item) { name >> quantity.maybe >> location.maybe >> tag.maybe }
+
+      rule(:items) { (item >> newline).repeat.as(:items) }
+      rule(:entry) { date_line >> items >> newline.repeat }
+
+      rule(:document) { entry.repeat }
+
+      root :document
+    end
+  end
+end

data/lib/litter/parsing/transform.rb

@@ -0,0 +1,39 @@
+module Litter
+  module Parsing
+    class Transform
+      # Transforms output from Parser (an array of entry hashes) into a hash of
+      # arrays containing item finds.
+      # @param parsed [Array<Hash>] output from Parser.
+      # @return [Hash] a hash of items and their finds; see parse_test.rb for an example.
+      def apply(parsed)
+        all_items = {}
+
+        parsed.each do |entry|
+          extract_entry_into_all_items(entry, all_items)
+        end
+
+        all_items
+      end
+
+      private
+
+      # Adds the given entry's item finds to the given hash of all items.
+      # @param entry [Hash] an entry (items found on a date).
+      # @param all_items [Hash] all items extracted from entries so far.
+      def extract_entry_into_all_items(entry, all_items)
+        entry[:items].each do |item|
+          name = item[:name].to_s.strip
+          date = Date.parse(entry[:date])
+          quantity = Integer(item[:quantity].to_s, exception: false) || 1
+          location = (item[:location] || entry[:location])&.to_s&.strip
+          tag = item[:tag]&.to_s
+
+          all_items[name] ||= []
+          quantity.times do
+            all_items[name] << { date:, location:, tag: }
+          end
+        end
+      end
+    end
+  end
+end

data/lib/litter/util/hash_deep_merge.rb

@@ -0,0 +1,44 @@
+module Litter
+  module Util
+    # Modified from active_support/core_ext/hash/deep_merge
+    # https://github.com/rails/rails/blob/main/activesupport/lib/active_support/core_ext/hash/deep_merge.rb
+    #
+    # This deep_merge also iterates through arrays of hashes and merges them.
+    module HashDeepMerge
+      refine Hash do
+        def deep_merge(other_hash, &block)
+          dup.deep_merge!(other_hash, &block)
+        end
+
+        def deep_merge!(other_hash, &block)
+          merge!(other_hash) do |key, this_val, other_val|
+            if this_val.is_a?(Hash) && other_val.is_a?(Hash)
+              this_val.deep_merge(other_val, &block)
+            # I added this part for merging values that are arrays of hashes.
+            elsif this_val.is_a?(Array) && other_val.is_a?(Array) &&
+                  this_val.all? { |el| el.is_a?(Hash) } &&
+                  other_val.all? { |el| el.is_a?(Hash) }
+              zip =
+                if other_val.length >= this_val.length
+                  other_val.zip(this_val)
+                else
+                  this_val.zip(other_val).map(&:reverse)
+                end
+              zip.map { |other_el, this_el|
+                if this_el.nil?
+                  other_el
+                else
+                  this_el.deep_merge(other_el || {}, &block)
+                end
+              }
+            elsif block_given?
+              block.call(key, this_val, other_val)
+            else
+              other_val
+            end
+          end
+        end
+      end
+    end
+  end
+end

data/lib/litter/version.rb

@@ -0,0 +1,3 @@
+module Litter
+  VERSION = "0.1.0"
+end

metadata

@@ -0,0 +1,155 @@
+--- !ruby/object:Gem::Specification
+name: litter
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Felipe Vogel
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2023-03-15 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: parslet
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: debug
+  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: minitest
+  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: minitest-reporters
+  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: pretty-diffs
+  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: amazing_print
+  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: rubycritic
+  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:
+- fps.vogel@gmail.com
+executables:
+- litter
+extensions: []
+extra_rdoc_files: []
+files:
+- bin/litter
+- lib/litter/config.rb
+- lib/litter/errors.rb
+- lib/litter/litter.rb
+- lib/litter/parsing/litter_file.rb
+- lib/litter/parsing/parser.rb
+- lib/litter/parsing/transform.rb
+- lib/litter/util/hash_deep_merge.rb
+- lib/litter/version.rb
+homepage: https://github.com/fpsvogel/litter
+licenses:
+- MIT
+metadata:
+  allowed_push_host: https://rubygems.org
+  homepage_uri: https://github.com/fpsvogel/litter
+  source_code_uri: https://github.com/fpsvogel/litter
+  changelog_uri: https://github.com/fpsvogel/litter/blob/master/CHANGELOG.md
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 3.0.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.4.7
+signing_key: 
+specification_version: 4
+summary: Parses a log of collected litter. For avid trash-picker-uppers.
+test_files: []