ae_easy-text 0.0.4 → 0.0.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: '043945fa52e59d4b712944fc7ada1ac2de17b7d4aca575a74a329e6804676f8c'
-  data.tar.gz: 06fe3a253c11ad468646fb2ed23db2ff5fcaf1f9dd387f8e8f4a18961f519916
+  metadata.gz: ca70d3930261e598c1ec9ebbb7abfdfbe9f330b616ac1b2319fc3fcf51f6e80c
+  data.tar.gz: 16e7e08587840e7aedd9b37171ccbbc84d21c8f97a0fcfcd2a7cf2daee86a9a1
 SHA512:
-  metadata.gz: 247d51ceb25d3805bbc440f7475d4254c4c28cb297d83e598ccb5594f7428a9a4e6e1fda389ef3668a596f2660c5cc55422e3c6e438c6aae6cf7e4d1076ac1d5
-  data.tar.gz: 005c59ad17927b016948d6a7b62af827910df99d9e4c31c4ba79e40fcd1953caf54da36ef5e555dd13d9ced4cce0f376ceb0a6104b5e8caee2ccd21eb6f339fb
+  metadata.gz: 44bcb6b53f4bae2385afc655835771dc20f10d5da9f17158049793292e837a06981b787bf23ad604f2bdfda7d7bdcc1128a2d31f38b4da0ee169e1508b0c555a
+  data.tar.gz: dd27481084e95be832506ec25235b674e2d2b13f47176b3b3a9f05fa9fa3114b14b88b7e7cfa76a0b1a5d30114f6912815bb23174701f3a75ebdb469cd193d76

data/CODE_OF_CONDUCT.md

@@ -55,7 +55,7 @@ further defined and clarified by project maintainers.
 ## Enforcement
 
 Instances of abusive, harassing, or otherwise unacceptable behavior may be
-reported by contacting the project team at parama@answersengine.com. All
+reported by contacting the project team at perry@datahen.com. All
 complaints will be reviewed and investigated and will result in a response that
 is deemed necessary and appropriate to the circumstances. The project team is
 obligated to maintain confidentiality with regard to the reporter of an incident.

data/Gemfile

@@ -2,5 +2,5 @@ source "https://rubygems.org"
 
 git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
 
-# Specify your gem's dependencies in answersengine.gemspec
+# Specify your gem's dependencies in ae_easy-text.gemspec
 gemspec

data/README.md

@@ -5,12 +5,16 @@
 # AeEasy text module
 ## Description
 
-AeEasy text is part of AeEasy gem collection. It provides multiple text parsing helpers to ease common text parsing user cases.
+AeEasy text is part of AeEasy gem collection and an alias to [dh_easy-text](https://github.com/DataHenOfficial/dh_easy-text/) gem. It provides multiple text parsing helpers to ease common text parsing user cases.
 
 Install gem:
-```gem install 'ae_easy-text'```
+```ruby
+gem install 'ae_easy-text'
+```
 
 Require gem:
-```require 'ae_easy/text'```
+```ruby
+require 'ae_easy/text'
+```
 
-Documentation can be found [here](http://rubydoc.org/gems/ae_easy-text/frames).
+See [dh_easy-text](https://github.com/DataHenOfficial/dh_easy-text/) gem for documentation.

data/Rakefile

@@ -9,14 +9,4 @@ Rake::TestTask.new do |t|
   t.test_files = FileList['./test/**/*_test.rb']
 end
 
-desc 'Benchmark another task execution | usage example: benchmark[my_task, param1, param2]'
-task :benchmark, [:task] do |task, args|
-  task_name = args[:task]
-  if task_name.nil?
-    puts "Should select a task."
-    exit 1
-  end
-  puts Benchmark.measure{ Rake::Task[task_name].invoke *args.extras }
-end
-
 task default: :test

data/ae_easy-text.gemspec

@@ -1,17 +1,16 @@
 
 lib = File.expand_path("../lib", __FILE__)
 $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
-require "ae_easy/text/version"
 
 Gem::Specification.new do |spec|
   spec.name          = "ae_easy-text"
-  spec.version       = AeEasy::Text::VERSION
+  spec.version       = "0.0.5"
   spec.authors       = ["Eduardo Rosales"]
   spec.email         = ["eduardo@datahen.com"]
 
-  spec.summary       = %q{AnswersEngine Easy toolkit text module}
-  spec.description   = %q{AnswersEngine Easy toolkit text module contains multiple text parsing helpers.}
-  spec.homepage      = "https://answersengine.com"
+  spec.summary       = %q{(Deprecated: Use datahen gem instead.) Compatibility alias for Datahen Easy toolkit text module}
+  spec.description   = %q{(Deprecated: Use datahen gem instead.) Compatibility alias for Datahen Easy toolkit text module contains multiple text parsing helpers.}
+  spec.homepage      = "https://datahen.com"
   spec.license       = "MIT"
 
   # spec.cert_chain  = ['certs/ae_easy.pem']
@@ -38,12 +37,10 @@ Gem::Specification.new do |spec|
   spec.require_paths = ["lib"]
   spec.required_ruby_version = '>= 2.2.2'
 
-  spec.add_dependency 'ae_easy-core', '~> 0'
+  spec.add_dependency 'dh_easy-text', '~> 0'
+  spec.add_dependency 'ae_easy-core', '>= 0.2.1'
   spec.add_development_dependency 'bundler', '>= 1'
   spec.add_development_dependency 'rake', '~> 10'
   spec.add_development_dependency 'minitest', '~> 5'
-  spec.add_development_dependency 'simplecov', '~> 0'
-  spec.add_development_dependency 'simplecov-console', '~> 0'
-  spec.add_development_dependency 'timecop', '~> 0'
   spec.add_development_dependency 'byebug', '>= 0'
 end

data/lib/ae_easy/text.rb

@@ -1,311 +1,5 @@
-require 'cgi'
-require 'json'
-require 'digest/sha1'
+require 'dh_easy/text'
 require 'ae_easy/core'
-require 'ae_easy/text/version'
 
-module AeEasy
-  module Text
-    # Create a hash from object
-    #
-    # @param [String,Hash,Object] object Object to create hash from.
-    #
-    # @return [String]
-    def self.hash object
-      object = object.hash if object.is_a? Hash
-      Digest::SHA1.hexdigest object.to_s
-    end
-
-    # Encode text for valid HTML entities.
-    #
-    # @param [String] text Text to encode.
-    #
-    # @return [String]
-    def self.encode_html text
-      CGI.escapeHTML text
-    end
-
-    # Decode HTML entities from text .
-    #
-    # @param [String] text Text to decode.
-    #
-    # @return [String]
-    def self.decode_html text
-      CGI.unescapeHTML text
-    end
-
-    # Strip a value by trimming spaces, reducing secuential spaces into a
-    #   single space, decode HTML entities and change encoding to UTF-8.
-    #
-    # @param [String,Object,nil] raw_text Text to strip.
-    # @param [String] orig_encoding Text original encoding.
-    #
-    # @return [String,nil] `nil` when +raw_text+ is nil, else `String`.
-    def self.strip raw_text, orig_encoding = 'ASCII'
-      return nil if raw_text.nil?
-      raw_text = raw_text.to_s unless raw_text.is_a? String
-      regex = /(\s|\u3000|\u00a0)+/
-      good_encoding = (raw_text =~ /\u3000/ || true) rescue false
-      unless good_encoding
-        raw_text = raw_text.force_encoding(orig_encoding).encode('UTF-8', invalid: :replace, undef: :replace)
-        regex = /(\s|\u3000|\u00a0|\u00c2\u00a0)+/
-      end
-      text = raw_text.gsub(regex, ' ').strip
-      text.nil? ? nil : decode_html(text)
-    end
-
-    # Default cell content parser used to parse cell element.
-    #
-    # @param [Nokogiri::Element] cell_element Cell element to parse.
-    # @param [Hash] data Data hash to save parsed data into.
-    # @param [String,Symbol] key Header column key being parsed.
-    def self.default_parser cell_element, data, key
-      return if cell_element.nil?
-      cell_element.search('//i').remove if cell_element.search('//i').count > 0
-      data[key] = strip cell_element.text
-    end
-
-    # Parse row data matching a selector using a header map to translate
-    #   between columns and friendly keys.
-    #
-    # @param [Hash] opts ({}) Configuration options.
-    # @option opts [Nokogiri::Element] :html Container element to search into.
-    # @option opts [String] :selector CSS selector to match content cells.
-    # @option opts [Boolean] :first_row_header (false) If true then first
-    #   matching element will be assumed to be header and ignored.
-    # @option opts [Hash{Symbol,String => Integer}] :header_map Header key vs
-    #   index dictionary.
-    # @option opts [Hash{Symbol,String => lambda,proc}] :column_parsers ({})
-    #   Custom column parsers for advance data extraction.
-    # @option opts [Boolean] :ignore_text_nodes (true) Ignore text nodes when
-    #   retriving content cells and rows.
-    #
-    # @yieldparam [Hash{Symbol,String => Object}] data Parsed row data.
-    # @yieldparam [Array] row Raw row data.
-    # @yieldparam [Hash{Symbol,String => Integer}] header_map Header map used.
-    # @yieldreturn [Boolean] `true` when valid, else `false`.
-    #
-    # @return [Array<Hash>,nil] Parsed rows data.
-    def self.parse_content opts, &filter
-      opts = {
-        html: nil,
-        selector: nil,
-        first_row_header: false,
-        header_map: {},
-        column_parsers: {},
-        ignore_text_nodes: true
-      }.merge opts
-
-      # Setup config
-      data = []
-      row_data = child_element = nil
-      first = first_row_header = opts[:first_row_header]
-      header_map = opts[:header_map]
-      column_parsers = opts[:column_parsers]
-      ignore_text_nodes = opts[:ignore_text_nodes]
-
-      # Get and parse rows
-      html_rows = opts[:html].css(opts[:selector])
-      html_rows.each do |row|
-        next if ignore_text_nodes && row.name == 'text'
-
-        # First row header validation
-        if first && first_row_header
-          first = false
-          next
-        end
-
-        # Extract content data
-        row_data = {}
-        header_map.each do |key, index|
-          # Parse column html with default or custom parser
-          children = row.children
-          children = children.select{|i|i.name != 'text'} if ignore_text_nodes
-          child_element = children[index]
-          column_parsers[key].nil? ?
-            default_parser(child_element, row_data, key) :
-            column_parsers[key].call(child_element, row_data, key)
-        end
-        next unless filter.nil? || filter.call(row_data, row, header_map)
-        data << row_data
-      end
-      data
-    end
-
-    # Extract column label and translate it into a frienly key.
-    #
-    # @param [Nokogiri::Element] element Html element to parse.
-    # @param [Hash{Symbol,String => Regex,String}] label_map Label dictionary
-    #   for translation into key.
-    #
-    # @return [Symbol,String] Translated key.
-    def self.translate_label_to_key element, label_map
-      return nil if element.nil?
-      element.search('//i').remove if element.search('//i').count > 0
-      text = strip element.text
-      key_pair = label_map.find do |k,v|
-        v.is_a?(Regexp) ? (text =~ v) : (text == v)
-      end
-      key = key_pair.nil? ? nil : key_pair[0]
-    end
-
-    # Parse header from selector and create a header map to match a column key
-    #   with column index.
-    #
-    # @param [Hash] opts ({}) Configuration options.
-    # @option opts [Nokogiri::Element] :html Container element to search into.
-    # @option opts [String] :selector CSS selector to match header cells.
-    # @option opts [Hash{Symbol,String => Regex,String}] :column_key_label_map
-    #   Key vs. label dictionary.
-    # @option opts [Boolean] :first_row_header (false) If true then selector
-    #   first matching row will be used as header for parsing.
-    # @option opts [Boolean] :ignore_text_nodes (true) Ignore text nodes when
-    #   retriving header cells and rows.
-    #
-    # @return [Hash{Symbol,String => Integer},nil] Key vs. column index map.
-    def self.parse_header_map opts = {}
-      opts = {
-        html: nil,
-        selector: nil,
-        column_key_label_map: {},
-        first_row_header: false,
-        ignore_text_nodes: true
-      }.merge opts
-
-      # Setup config
-      dictionary = opts[:column_key_label_map]
-      ignore_text_nodes = opts[:ignore_text_nodes]
-      data = []
-      column_map = nil
-
-      # Extract and parse header rows
-      html_rows = opts[:html].css(opts[:selector]) rescue nil
-      return nil if html_rows.nil?
-      html_rows = [html_rows.first] if opts[:first_row_header]
-      html_rows.each do |row|
-        next if ignore_text_nodes && row.name == 'text'
-
-        column_map = {}
-        children = row.children
-        children = children.select{|i|i.name != 'text'} if ignore_text_nodes
-        children.each_with_index do |col, index|
-          # Parse and map column header
-          column_key = translate_label_to_key col, dictionary
-          next if column_key.nil?
-          column_map[column_key] = index
-        end
-        data << column_map
-      end
-      data&.first
-    end
-
-    # Parse data from a horizontal table like structure matching a selectors and
-    #   using a header map to match columns.
-    #
-    # @param [Hash] opts ({}) Configuration options.
-    # @option opts [Nokogiri::Element] :html Container element to search into.
-    # @option opts [String] :header_selector Header column elements selector.
-    # @option opts [Hash{Symbol,String => Regex,String}] :header_key_label_map
-    #   Header key vs. label dictionary to match column indexes.
-    # @option opts [String] :content_selector Content row elements selector.
-    # @option opts [Boolean] :first_row_header (false) If true then selector
-    #   first matching row will be used as header for parsing.
-    # @option opts [Hash{Symbol,String => lambda,proc}] :column_parsers ({})
-    #   Custom column parsers for advance data extraction.
-    # @option opts [Boolean] :ignore_text_nodes (true) Ignore text nodes when
-    #   retriving cells and rows.
-    #
-    # @yieldparam [Hash{Symbol,String => Object}] data Parsed content row data.
-    # @yieldparam [Array] row Raw content row data.
-    # @yieldparam [Hash{Symbol,String => Integer}] header_map Header map used.
-    # @yieldreturn [Boolean] `true` when valid, else `false`.
-    #
-    # @return [Hash{Symbol => Array,Hash,nil}] Hash data is as follows:
-    #   * `[Hash] :header_map` Header map used.
-    #   * `[Array<Hash>,nil] :data` Parsed rows data.
-    def self.parse_table opts = {}, &filter
-      opts = {
-        html: nil,
-        header_selector: nil,
-        header_key_label_map: {},
-        content_selector: nil,
-        first_row_header: false,
-        column_parsers: {},
-        ignore_text_nodes: true
-      }.merge opts
-      return nil if opts[:html].nil?
-      header_map = self.parse_header_map html: opts[:html],
-        selector: opts[:header_selector],
-        column_key_label_map: opts[:header_key_label_map],
-        first_row_header: opts[:first_row_header],
-        ignore_text_nodes: opts[:ignore_text_nodes]
-      return nil if header_map.nil?
-      data = self.parse_content html: opts[:html],
-        selector: opts[:content_selector],
-        header_map: header_map,
-        first_row_header: opts[:first_row_header],
-        column_parsers: opts[:column_parsers],
-        ignore_text_nodes: opts[:ignore_text_nodes],
-        &filter
-      {header_map: header_map, data: data}
-    end
-
-    # Parse data from a vertical table like structure matching a selectors and
-    #   using a header map to match columns.
-    #
-    # @param [Hash] opts ({}) Configuration options.
-    # @option opts [Nokogiri::Element] :html Container element to search into.
-    # @option opts [String] :row_selector Vertical row like elements selector.
-    # @option opts [String] :header_selector Header column elements selector.
-    # @option opts [Hash{Symbol,String => Regex,String}] :header_key_label_map
-    #   Header key vs. label dictionary to match column indexes.
-    # @option opts [String] :content_selector Content row elements selector.
-    # @option opts [Hash{Symbol,String => lambda,proc}] :column_parsers ({})
-    #   Custom column parsers for advance data extraction.
-    # @option opts [Boolean] :ignore_text_nodes (true) Ignore text nodes when
-    #   retriving cells and rows.
-    #
-    # @yieldparam [Hash{Symbol,String => Object}] data Parsed content row data.
-    # @yieldparam [Array] row Raw content row data.
-    # @yieldparam [Hash{Symbol,String => Integer}] header_map Header map used.
-    # @yieldreturn [Boolean] `true` when valid, else `false`.
-    #
-    # @return [Hash{Symbol => Array,Hash,nil}] Hash data is as follows:
-    #   * `[Hash] :header_map` Header map used.
-    #   * `[Array<Hash>,nil] :data` Parsed rows data.
-    def self.parse_vertical_table opts = {}, &filter
-      opts = {
-        html: nil,
-        row_selector: nil,
-        header_selector: nil,
-        header_key_label_map: {},
-        content_selector: nil,
-        column_parsers: {},
-        ignore_text_nodes: true
-      }.merge opts
-      return nil if opts[:html].nil?
-
-      # Setup config
-      data = {}
-      dictionary = opts[:header_key_label_map]
-      column_parsers = opts[:column_parsers]
-
-      # Extract headers and content
-      html_rows = opts[:html].css(opts[:row_selector]) rescue nil
-      return nil if html_rows.nil?
-      html_rows.each do |row|
-        # Parse and map column header
-        header_element = row.css(opts[:header_selector])
-        key = translate_label_to_key header_element, dictionary
-        next if key.nil? || key == ''
-
-        # Parse column html with default or custom parser
-        content_element = row.css(opts[:content_selector])
-        column_parsers[key].nil? ?
-          default_parser(content_element, data, key) :
-          column_parsers[key].call(content_element, data, key)
-      end
-      data
-    end
-  end
-end
+# (Deprecated) Alias to DhEasy module.
+AeEasy = ::DhEasy unless defined? ::AeEasy

metadata

@@ -1,17 +1,17 @@
 --- !ruby/object:Gem::Specification
 name: ae_easy-text
 version: !ruby/object:Gem::Version
-  version: 0.0.4
+  version: 0.0.5
 platform: ruby
 authors:
 - Eduardo Rosales
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-03-11 00:00:00.000000000 Z
+date: 2019-12-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: ae_easy-core
+  name: dh_easy-text
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
@@ -24,6 +24,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: ae_easy-core
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.2.1
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.2.1
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
@@ -66,48 +80,6 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '5'
-- !ruby/object:Gem::Dependency
-  name: simplecov
-  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: 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'
-- !ruby/object:Gem::Dependency
-  name: timecop
-  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: byebug
   requirement: !ruby/object:Gem::Requirement
@@ -122,8 +94,8 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-description: AnswersEngine Easy toolkit text module contains multiple text parsing
-  helpers.
+description: "(Deprecated: Use datahen gem instead.) Compatibility alias for Datahen
+  Easy toolkit text module contains multiple text parsing helpers."
 email:
 - eduardo@datahen.com
 executables: []
@@ -139,29 +111,12 @@ files:
 - README.md
 - Rakefile
 - ae_easy-text.gemspec
-- doc/AeEasy.html
-- doc/AeEasy/Text.html
-- doc/_index.html
-- doc/class_list.html
-- doc/css/common.css
-- doc/css/full_list.css
-- doc/css/style.css
-- doc/file.README.html
-- doc/file_list.html
-- doc/frames.html
-- doc/index.html
-- doc/js/app.js
-- doc/js/full_list.js
-- doc/js/jquery.js
-- doc/method_list.html
-- doc/top-level-namespace.html
 - lib/ae_easy/text.rb
-- lib/ae_easy/text/version.rb
-homepage: https://answersengine.com
+homepage: https://datahen.com
 licenses:
 - MIT
 metadata:
-  homepage_uri: https://answersengine.com
+  homepage_uri: https://datahen.com
   source_code_uri: https://github.com/answersengine/ae_easy-text
 post_install_message: 
 rdoc_options: []
@@ -182,5 +137,6 @@ rubyforge_project:
 rubygems_version: 2.7.6
 signing_key: 
 specification_version: 4
-summary: AnswersEngine Easy toolkit text module
+summary: "(Deprecated: Use datahen gem instead.) Compatibility alias for Datahen Easy
+  toolkit text module"
 test_files: []