jtag 0.1.22 → 0.2.0

data/lib/jtag/string.rb

@@ -1,244 +1,48 @@
-# frozen_string_literal: true
-
-module JekyllTag
-  ## String helpers
-  class ::String
-    ##
-    ## normalize bool string to symbo
-    ##
-    ## @return [Symbol] :and :or :not
-    ##
-    def to_bool
-      case self.downcase
-      when /^a/i
-        :and
-      when /^o/i
-        :or
-      when /^n/i
-        :not
-      else
-        raise ArgumentError, "Invalid boolean string: #{self}"
-      end
-    end
-
-    ##
-    ## Convert a string to a format symbol (:csv, :complete, :json, :plist, :yaml)
-    ##
-    ## @return [Symbol] format symbol
-    ##
-    def to_format
-      case self.downcase
-      when /^j/i
-        :json
-      when /^p/i
-        :plist
-      when /^y/i
-        :yaml
-      when /^cs/i
-        :csv
-      when /^c/i
-        :complete
-      else
-        raise ArgumentError, "Invalid format string: #{self}"
-      end
-    end
-
-    ## Check if a string is a list of files
-    ##
-    ## @param null [Boolean] check for null-delimited list
-    ##
-    ## @example Check if a string is a list of files
-    ##   "file1\nfile2\nfile3".file_list?
-    ##   # => true
-    ##
-    ## @return [Boolean]
-    def file_list?(null = false)
-      self.strip.split(null ? "\x00" : "\n").each do |line|
-        return false unless File.exist?(line)
-      end
-      true
-    end
-
-    ##
-    ## Check if string is YAML
-    ##
-    ## @example Check if a string is YAML
-    ##   "tags:\n  - tag1\n  - tag2".yaml?
-    ##   # => true
-    ##
-    ## @example Check if a string is not YAML
-    ##   "test string".yaml?
-    ##   # => false
-    ##
-    ## @return [Boolean]
-    ##
-    def yaml?
-      begin
-        YAML.load(self)
-      rescue
-        return false
-      end
-      true
-    end
-
-    ##
-    ## Matches the string against a given keyword based on various options.
-    ##
-    ## @param keyword [String] the keyword to match against the string.
-    ## @param options [Hash] a hash of options to customize the matching behavior.
-    ## @option options [Boolean] :case_sensitive (false) whether the match should be case-sensitive.
-    ## @option options [Boolean] :starts_with (false) whether the match should check if the string starts with the keyword.
-    ## @option options [Boolean] :exact (false) whether the match should be exact.
-    ## @option options [Boolean] :fuzzy (true) whether the match should be fuzzy.
-    ## @option options [Integer] :distance (2) the maximum distance between characters for a fuzzy match.
-    ##
-    ## @return [Boolean] true if the string matches the keyword based on the given options, false otherwise.
-    ##
-    def match_keyword(keyword, options = {})
-      options = {
-        case_sensitive: false,
-        starts_with: false,
-        exact: false,
-        fuzzy: false,
-        contains: false,
-        distance: 2,
-      }.merge(options)
-
-      keyword = Regexp.escape(keyword)
-
-      if options[:exact]
-        re = "^#{keyword}$"
-      elsif options[:starts_with]
-        re = "^#{keyword}"
-      elsif options[:fuzzy]
-        re = ".*#{keyword.split(//).join(".{,#{options[:distance] - 1}}")}.*"
-      else
-        re = ".*#{keyword}.*"
-      end
-
-      if options[:case_sensitive]
-        self.match?(/#{re}/)
-      else
-        self.match?(/#{re}/i)
-      end
-    end
-
-    ##
-    ## Check if a string is JSON
-    ##
-    ## @example Check if a string is JSON
-    ##   '{"tags": ["tag1", "tag2"]}'.json?
-    ##   # => true
-    ##
-    ## @example Check if a string is not JSON
-    ##   "test string".json?
-    ##   # => false
-    ##
-    ## @return [Boolean]
-    ##
-    ## @note JSON must be a hash or array
-    ##
-    def json?
-      begin
-        JSON.parse(self).is_a?(Hash) || JSON.parse(self).is_a?(Array)
-      rescue
-        return false
-      end
-      true
-    end
-
-    ##
-    ## Convert parenthetical count to hash
-    ##
-    ## @example Convert a string to a hash
-    ##   "tag (5)".to_count
-    ##   # => { "name" => "tag", "count" => 5 }
-    ##
-    ## @example Convert a string to a hash with no count
-    ##   "tag".to_count
-    ##   # => { "name" => "tag", "count" => 0 }
-    ##
-    ## @return [Hash] hash with name and count
-    ##
-    def to_count
-      tag = dup.strip.sub(/^[[:punct:]] /, "")
-      if tag =~ /(.*) \((\d+)\)/
-        { "name" => $1, "count" => $2.to_i }
-      else
-        { "name" => tag, "count" => 0 }
-      end
-    end
-
-    ##
-    ## Check if a string is a list of tags
-    ##
-    ## @example Check if a string is a list of tags
-    ##   "tag1\ntag2".tag_list?
-    ##   # => true
-    ##
-    ## @return [Boolean]
-    ##
-    ## @note One tag per line
-    ##   Tags are assumed to be alphanumeric and lowercase
-    ##   (spaces, underscores, and dashes allowed) with no
-    ##   leading or preceding or trailing punctuation
-    ##
-    def tag_list?
-      self.strip.split("\n").each do |tag|
-        return false unless tag.match?(/^(?![[:punct:]] )[a-z0-9 -_]+(?<![[:punct:]]) *$/)
-      end
-      true
-    end
-
-    def root_words
-      words = break_camel.split("[\s-]")
-      words.delete_if { |word| word =~ /^[^a-z]+$/i || word.length < 4 }
-      words.map { |word| word = Text::PorterStemming.stem(word).downcase }.join(" ")
-    end
-
-    # convert "WikiLink" to "Wiki link"
-    def break_camel
-      return downcase if match(/\A[A-Z]+\z/)
-      gsub(/([A-Z]+)([A-Z][a-z])/, '\1 \2').
-        gsub(/([a-z])([A-Z])/, '\1 \2').
-        downcase
-    end
+# encoding: utf-8
+class String
+  # convert "WikiLink" to "Wiki link"
+  def break_camel
+    return downcase if match(/\A[A-Z]+\z/)
+    gsub(/([A-Z]+)([A-Z][a-z])/, '\1 \2').
+    gsub(/([a-z])([A-Z])/, '\1 \2').
+    downcase
+  end
 
-    def strip_markdown
-      # strip all Markdown and Liquid tags
-      gsub(/\{%.*?%\}/, "").
-        gsub(/\[\^.+?\](\: .*?$)?/, "").
-        gsub(/\s{0,2}\[.*?\]: .*?$/, "").
-        gsub(/\!\[.*?\][\[\(].*?[\]\)]/, "").
-        gsub(/\[(.*?)\][\[\(].*?[\]\)]/, "\\1").
-        gsub(/^\s{1,2}\[(.*?)\]: (\S+)( ".*?")?\s*$/, "").
-        gsub(/^\#{1,6}\s*/, "").
-        gsub(/(\*{1,2})(\S.*?\S)\1/, "\\2").
-        gsub(/(`{3,})(.*?)\1/m, "\\2").
-        gsub(/^-{3,}\s*$/, "").
-        gsub(/`(.+)`/, "\\1").
-        gsub(/\n{2,}/, "\n\n")
-    end
+  def strip_markdown
+    # strip all Markdown and Liquid tags
+    gsub(/\{%.*?%\}/,'').
+    gsub(/\[\^.+?\](\: .*?$)?/,'').
+    gsub(/\s{0,2}\[.*?\]: .*?$/,'').
+    gsub(/\!\[.*?\][\[\(].*?[\]\)]/,"").
+    gsub(/\[(.*?)\][\[\(].*?[\]\)]/,"\\1").
+    gsub(/^\s{1,2}\[(.*?)\]: (\S+)( ".*?")?\s*$/,'').
+    gsub(/^\#{1,6}\s*/,'').
+    gsub(/(\*{1,2})(\S.*?\S)\1/,"\\2").
+    gsub(/(`{3,})(.*?)\1/m,"\\2").
+    gsub(/^-{3,}\s*$/,"").
+    gsub(/`(.+)`/,"\\1").
+    gsub(/\n{2,}/,"\n\n")
+  end
 
-    def strip_tags
-      return CGI.unescapeHTML(
-               gsub(/<(script|style|pre|code|figure).*?>.*?<\/\1>/im, "").
-                 gsub(/<!--.*?-->/m, "").
-                 gsub(/<(img|hr|br).*?>/i, " ").
-                 gsub(/<(dd|a|h\d|p|small|b|i|blockquote|li)( [^>]*?)?>(.*?)<\/\1>/i, " \\3 ").
-                 gsub(/<\/?(dt|a|ul|ol)( [^>]+)?>/i, " ").
-                 gsub(/<[^>]+?>/, "").
-                 gsub(/\[\d+\]/, "").
-                 gsub(/&#8217;/, "'").gsub(/&.*?;/, " ").gsub(/;/, " ")
-             ).lstrip.gsub("\xE2\x80\x98", "'").gsub("\xE2\x80\x99", "'").gsub("\xCA\xBC", "'").gsub("\xE2\x80\x9C", '"').gsub("\xE2\x80\x9D", '"').gsub("\xCB\xAE", '"').squeeze(" ")
-    end
+  def strip_tags
+    return CGI.unescapeHTML(
+        gsub(/<(script|style|pre|code|figure).*?>.*?<\/\1>/im, '').
+        gsub(/<!--.*?-->/m, '').
+        gsub(/<(img|hr|br).*?>/i, " ").
+        gsub(/<(dd|a|h\d|p|small|b|i|blockquote|li)( [^>]*?)?>(.*?)<\/\1>/i, " \\3 ").
+        gsub(/<\/?(dt|a|ul|ol)( [^>]+)?>/i, " ").
+        gsub(/<[^>]+?>/, '').
+        gsub(/\[\d+\]/, '').
+        gsub(/&#8217;/,"'").gsub(/&.*?;/,' ').gsub(/;/,' ')
+    ).lstrip.gsub("\xE2\x80\x98","'").gsub("\xE2\x80\x99","'").gsub("\xCA\xBC","'").gsub("\xE2\x80\x9C",'"').gsub("\xE2\x80\x9D",'"').gsub("\xCB\xAE",'"').squeeze(" ")
+  end
 
-    def strip_urls
-      gsub(/(https?:\/\/)?([\da-z\.-]+)\.([a-z\.]{2,6})([\/\w \.-]*)*\/?/i, "")
-    end
+  def strip_urls
+    gsub(/(https?:\/\/)?([\da-z\.-]+)\.([a-z\.]{2,6})([\/\w \.-]*)*\/?/i,"")
+  end
 
-    def strip_all
-      strip_tags.strip_markdown.strip
-    end
+  def strip_all
+    strip_tags.strip_markdown.strip
   end
+
 end

data/lib/jtag/version.rb

@@ -1,3 +1,3 @@
 module Jtag
-  VERSION = "0.1.22"
+  VERSION = '0.2.0'
 end

data/lib/jtag.rb

@@ -1,19 +1,13 @@
-# frozen_string_literal: true
-
-require "net/http"
-require "cgi"
-require "fileutils"
-require "yaml"
-require "csv"
-require "json"
-require "plist"
-require "tmpdir"
-require "logger"
-require_relative "jtag/errors.rb"
-require_relative "jtag/array.rb"
-require_relative "jtag/hash.rb"
-require_relative "jtag/version.rb"
-require_relative "jtag/string.rb"
-require_relative "jtag/porter_stemming.rb"
-require_relative "jtag/jekylltag.rb"
-require_relative "jtag/util.rb"
+require 'net/http'
+require 'cgi'
+require 'fileutils'
+require 'yaml'
+require 'csv'
+require 'json'
+require 'plist'
+require 'jtag/version.rb'
+require 'jtag/string.rb'
+require 'jtag/porter_stemming.rb'
+require 'jtag/jekylltag.rb'
+require 'tmpdir'
+require 'logger'

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: jtag
 version: !ruby/object:Gem::Version
-  version: 0.1.22
+  version: 0.2.0
 platform: ruby
 authors:
 - Brett Terpstra
 bindir: bin
 cert_chain: []
-date: 2025-02-24 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -55,14 +55,14 @@ dependencies:
   name: gli
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '='
+    - - "~>"
       - !ruby/object:Gem::Version
         version: 2.20.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '='
+    - - "~>"
       - !ruby/object:Gem::Version
         version: 2.20.0
 - !ruby/object:Gem::Dependency
@@ -93,6 +93,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: ostruct
+  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'
 email: me@brettterpstra.com
 executables:
 - jtag
@@ -101,33 +115,18 @@ extra_rdoc_files:
 - README.rdoc
 - jtag.rdoc
 files:
-- ".irbrc"
-- CHANGELOG.md
-- Gemfile
-- Jekyll/plugins/autotag_gen.rb
-- Jekyll/source/_layouts/tags_json.html
-- README.md
 - README.rdoc
-- Rakefile
 - bin/jtag
-- jtag.completion.bash
-- jtag.gemspec
 - jtag.rdoc
 - lib/jtag.rb
-- lib/jtag/array.rb
 - lib/jtag/config_files/blacklist.txt
 - lib/jtag/config_files/config.yml
 - lib/jtag/config_files/stopwords.txt
 - lib/jtag/config_files/synonyms.yml
-- lib/jtag/errors.rb
-- lib/jtag/hash.rb
 - lib/jtag/jekylltag.rb
 - lib/jtag/porter_stemming.rb
 - lib/jtag/string.rb
-- lib/jtag/stupid_json.rb
-- lib/jtag/util.rb
 - lib/jtag/version.rb
-- mise.toml
 homepage: http://brettterpstra.com
 licenses: []
 metadata: {}
@@ -150,7 +149,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.6.4
+rubygems_version: 3.6.7
 specification_version: 4
 summary: Auto-tagging and tagging tools for Jekyll
 test_files: []

data/.irbrc

@@ -1,6 +0,0 @@
-# frozen_string_literal: true
-`gem rdoc binbundle --ri`
-
-# rubocop:disable Style/MixinUsage
-include JekyllTag # standard:disable all
-# rubocop:enable Style/MixinUsage

data/CHANGELOG.md

@@ -1,15 +0,0 @@
-### 0.1.19
-
-2024-09-16 13:15
-
-#### NEW
-
-- Allows piping of file lists. For actions to which it applies, you can pipe a file list, either from a previous jtag command or from another source (newline separated) to act on only those files, e.g. `jtag posts_tagged keyboard | jtag tags`
-
-#### FIXED
-
-- File.exists? => File.exist? for Ruby 3
-
-### 1.0
-
-Initial release

data/Gemfile

@@ -1,3 +0,0 @@
-source 'https://rubygems.org'
-gemspec
-

data/Jekyll/plugins/autotag_gen.rb

@@ -1,58 +0,0 @@
-#
-# Author: Brett Terpstra
-# Page generator for /data/tags.json, a list of all the tags on your blog and a list of the top 50 tags.
-# Part of the AutoTag tool for Jekyll, but usable in other applications
-#
-# Looks for a tags_json.html template in your _layouts folder, see the example provided.
-# Provides page.json_tags and page.json_tags_count as arrays for looping
-#
-# Config options for _config.yml
-# tag_excludes: array of tags to exclude from all listings
-# tags_json_dir: alternate of folder for the data.json file. Set to blank for root, defaults to 'data'
-#
-# If using tags.json with a javascript application, be sure you have the proper headers defined in .htaccess:
-# AddType application/json               json
-# ExpiresByType application/json         "access plus 0 seconds"
-
-require 'json'
-
-module Jekyll
-
-  class AutoTag < Page
-    def initialize(site, base, dir)
-      @site = site
-      @base = base
-      @dir = dir
-      @name = 'tags.json'
-      self.process(@name)
-      self.read_yaml(File.join(base, '_layouts'), 'tags_json.html')
-      tags_with_counts = site.tags.delete_if {|k,v|
-        site.config['tag_excludes'].include?(k) unless site.config['tag_excludes'].nil?
-      }.sort_by { |k,v| v.count }.reverse
-
-      self.data['json_tags'] = tags_with_counts.sort {|a,b| a[0].downcase <=> b[0].downcase }.map {|k,v| k }
-      self.data['json_tags_count'] = []
-      tags_with_counts.each { |k,v|
-        self.data['json_tags_count'] << {
-          "name" => k,
-          "count" => v.count
-        }
-      }
-    end
-  end
-  class AutoTagGenerator < Generator
-    safe true
-    def generate(site)
-      if site.layouts.key? 'tags_json'
-        dir = site.config['tag_json_dir'] || 'data'
-        write_tag_json(site, dir)
-      end
-    end
-    def write_tag_json(site, dir)
-      index = AutoTag.new(site, site.source, dir)
-      index.render(site.layouts, site.site_payload)
-      index.write(site.dest)
-      site.pages << index
-    end
-  end
-end

data/Jekyll/source/_layouts/tags_json.html

@@ -1,11 +0,0 @@
----
-layout: nil
----
-{
-	"tags_count": [{% for tag in page.json_tags_count %}
-		{"name":"{{tag.name}}","count":{{tag.count}}},{% endfor %}
-		false],
-	"tags": [{% for tag in page.json_tags %}
-		"{{tag}}",{% endfor %}
-		false]
-}