jekyll-import 0.18.0 → 0.20.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d3f964d35053d8b6d57507e51d0f6512da6090196fbc64d5b27707841bd911dd
-  data.tar.gz: 6473e0c7e9619af1e666c845337bff7f553ec104106bfec56f366c5623446431
+  metadata.gz: 334724ebd0dbdc9774dd2e4799dea04dc5adaacc911d05cfc26f2a5daf23bbfa
+  data.tar.gz: 79a4f8c6de087aebca9f726275ebb3c234361b7341a01ce10c544ff65a0b6bac
 SHA512:
-  metadata.gz: f549ada882d1255c0bcb35a7945b19101de4b7b2c352ae13631b452da9f3dd59fd5dc36f45a51cf815c4c15c89f04575eba7d172d222e3bc21a18c42857e2796
-  data.tar.gz: bc2dd8ed440e6df361aefcf6059a9762e9692d1726b95a4748498819626e595f7c36a7d7d09acf10fa79b22f79b344e7f89f6207f2bbdd4825db131164c16e39
+  metadata.gz: d716d81c1e596e1004a65eadaa6c4df3e130d134d0b3db0fef7e06151350a90525f59db50aefd6f771950b0698f174fe19311dca7134c3488be970b85e76737a
+  data.tar.gz: f5ee7ba0c29bfad8267482789e2f571ee2d6ccafd343d173c9e9408b1c6c9c25941f28476386c3076310ec630fc5ff84c7ef12aaac2bc934aa1b8ee8e11010f5

data/lib/jekyll-import/importer.rb

@@ -12,7 +12,7 @@ module JekyllImport
 
     def self.stringify_keys(hash)
       the_hash = hash.clone
-      the_hash.keys.each do |key|
+      hash.each_key do |key|
         the_hash[(key.to_s rescue key) || key] = the_hash.delete(key)
       end
       the_hash

data/lib/jekyll-import/importers/blogger.rb

@@ -258,8 +258,8 @@ module JekyllImport
             body = @in_entry_elem[:body]
 
             # body escaping associated with liquid
-            body.gsub!(%r!{{!, '{{ "{{" }}') if body =~ %r!{{!
-            body.gsub!(%r!{%!, '{{ "{%" }}') if body =~ %r!{%!
+            body.gsub!(%r!{{!, '{{ "{{" }}') if %r!{{!.match?(body)
+            body.gsub!(%r!{%!, '{{ "{%" }}') if %r!{%!.match?(body)
 
             { :filename => filename, :header => header, :body => body }
           elsif @in_entry_elem[:meta][:kind] == "comment"
@@ -291,8 +291,8 @@ module JekyllImport
             body = @in_entry_elem[:body]
 
             # body escaping associated with liquid
-            body.gsub!(%r!{{!, '{{ "{{" }}') if body =~ %r!{{!
-            body.gsub!(%r!{%!, '{{ "{%" }}') if body =~ %r!{%!
+            body.gsub!(%r!{{!, '{{ "{{" }}') if %r!{{!.match?(body)
+            body.gsub!(%r!{%!, '{{ "{%" }}') if %r!{%!.match?(body)
 
             { :filename => filename, :header => header, :body => body }
           end

data/lib/jekyll-import/importers/dotclear.rb

@@ -0,0 +1,124 @@
+# frozen_string_literal: true
+
+# Tested with dotClear 2.1.5
+module JekyllImport
+  module Importers
+    class Dotclear < Importer
+      def self.specify_options(c)
+        c.option "datafile", "--datafile PATH", "dotClear export file"
+        c.option "mediafolder", "--mediafolder PATH", "dotClear media export folder (media.zip inflated)"
+      end
+
+      def self.require_deps
+        JekyllImport.require_with_fallback(%w(
+          rubygems
+          fileutils
+          safe_yaml
+          date
+          active_support
+          active_support/core_ext/string/inflections
+          csv
+          pp
+        ))
+      end
+
+      def self.validate(opts)
+        abort "Specify a data file !" if opts["datafile"].nil? || opts["datafile"].empty?
+        abort "Specify a media folder !" if opts["mediafolder"].nil? || opts["mediafolder"].empty?
+      end
+
+      def self.extract_headers_section(str)
+        str[1..-2].split(" ")[1].split(",")
+      end
+
+      def self.extract_data_section(str)
+        str.gsub(%r!^"!, "").gsub(%r!"$!, "").split('","')
+      end
+
+      def self.process(opts)
+        options = {
+          :datafile    => opts.fetch("datafile", ""),
+          :mediafolder => opts.fetch("mediafolder", ""),
+        }
+
+        FileUtils.mkdir_p("_posts")
+        FileUtils.mkdir_p("_drafts")
+
+        type_data = ""
+        headers = {}
+        posts_and_drafts = {}
+        keywords = {}
+
+        File.readlines(options[:datafile]).each do |lineraw|
+          line = lineraw.strip.gsub(%r!\n$!, "")
+
+          next if line.empty?
+
+          if line.start_with?("[") # post | media \ meta | comment...
+            type_data = line.split(" ").first[1..-1]
+            headers[type_data] = extract_headers_section(line)
+            next
+          end
+
+          elts = extract_data_section(line)
+
+          if type_data == "post"
+            draft = (elts[headers[type_data].index("post_status")] != "1")
+
+            date_str = elts[headers[type_data].index("post_creadt")]
+            date_blank = (date_str.nil? || date_str.empty?)
+            date_str_formatted = date_blank ? Date.today : Date.parse(date_str).strftime("%Y-%m-%d")
+            title_param = elts[headers[type_data].index("post_title")].to_s.parameterize
+
+            content = elts[headers[type_data].index("post_content_xhtml")].to_s
+            content = content.gsub('\"', '"').gsub('\n', "\n").gsub("/public/", "/assets/images/")
+
+            filepath = File.join(Dir.pwd, (draft ? "_drafts" : "_posts"), "#{date_str_formatted}-#{title_param}.html")
+
+            entire_content_file = <<~POST_FILE
+              ---
+              layout: post
+              title: "#{elts[headers[type_data].index("post_title")]}"
+              date: #{elts[headers[type_data].index("post_creadt")]} +0100
+              tags: ABC
+              ---
+
+              #{content}
+            POST_FILE
+
+            posts_and_drafts[elts[headers[type_data].index("post_id")]] = { :path => filepath, :content => entire_content_file }
+          elsif type_data == "media"
+            elts[headers[type_data].index("media_title")]
+            mediafilepath = elts[headers[type_data].index("media_file")]
+
+            src_path = File.join(options[:mediafolder], mediafilepath)
+            dst_path = File.join(Dir.pwd, "assets", "images", mediafilepath.to_s)
+
+            FileUtils.mkdir_p(File.dirname(dst_path))
+            FileUtils.cp(src_path, dst_path)
+          elsif type_data == "meta"
+            keywords[elts[headers[type_data].index("post_id")]] ||= []
+            keywords[elts[headers[type_data].index("post_id")]] << elts[headers[type_data].index("meta_id")]
+          elsif type_data == "link"
+
+          elsif type_data == "setting"
+
+          elsif type_data == "comment"
+
+          end
+        end
+
+        # POST-process : Change media path in posts and drafts
+        posts_and_drafts.each do |post_id, hsh|
+          keywords_str = keywords[post_id].to_a.join(", ")
+          content_file = hsh[:content]
+          content_file = content_file.gsub("tags: ABC", "tags: [#{keywords_str}]")
+
+          File.open(hsh[:path], "wb") do |f|
+            f.write(content_file)
+          end
+        end
+      end
+    end
+  end
+end

data/lib/jekyll-import/importers/marley.rb

@@ -48,7 +48,7 @@ module JekyllImport
           title = file_content.scan(regexp[:title]).first.to_s.strip
           prerex = file_content.scan(regexp[:perex]).first.to_s.strip
           published_on = DateTime.parse(post[:published_on]) rescue File.mtime(File.dirname(f))
-          meta          = meta_content ? YAML.safe_load(meta_content.scan(regexp[:meta]).to_s) : {}
+          meta = meta_content ? YAML.safe_load(meta_content.scan(regexp[:meta]).to_s) : {}
           meta["title"] = title
           meta["layout"] = "post"
 

data/lib/jekyll-import/importers/mephisto.rb

@@ -31,7 +31,7 @@ module JekyllImport
           rubygems
           sequel
           mysql2
-          fastercsv
+          csv
           fileutils
         ))
       end

data/lib/jekyll-import/importers/mt.rb

@@ -69,7 +69,7 @@ module JekyllImport
       # comments::        If true, output comments in _comments directory, like the one
       #                   mentioned at https://github.com/mpalmer/jekyll-static-comments/
       def self.process(options)
-        options  = default_options.merge(options)
+        options = default_options.merge(options)
 
         comments = options.fetch("comments")
         posts_name_by_id = {} if comments

data/lib/jekyll-import/importers/pluxml.rb

@@ -0,0 +1,82 @@
+# frozen_string_literal: true
+
+module JekyllImport
+  module Importers
+    class Pluxml < Importer
+      def self.require_deps
+        JekyllImport.require_with_fallback(%w(
+          nokogiri
+          fileutils
+          safe_yaml
+        ))
+      end
+
+      def self.specify_options(c)
+        c.option "source", "--source NAME", "The PluXML data directory to import"
+        c.option "layout", "--layout NAME", "The layout to apply"
+        c.option "avoid_liquid", "--avoid_liquid true", "Will add render_with_liquid: false in frontmatter"
+      end
+
+      def self.validate(options)
+        abort "Missing mandatory option --source." if options["source"].nil?
+        # no layout option, layout by default is post
+        options["layout"] = "post" if options["layout"].nil?
+        # no avoid_liquid option, avoid_liquid by default is false
+        options["avoid_liquid"] = false if options["avoid_liquid"].nil?
+      end
+
+      def self.process(options)
+        source       = options.fetch("source")
+        layout       = options.fetch("layout")
+        avoid_liquid = options.fetch("avoid_liquid")
+
+        FileUtils.mkdir_p("_posts")
+        FileUtils.mkdir_p("_drafts")
+
+        # for each XML file in source location
+        Dir.glob("*.xml", :base => source).each do |df|
+          df = File.join(source, df)
+          filename = File.basename(df, ".*")
+
+          # prepare post file name in Jekyll format
+          a_filename = filename.split(".")
+          post_name  = a_filename.pop
+          file_date  = a_filename.pop
+          post_date  = file_date[0..3] + "-" + file_date[4..5] + "-" + file_date[6..7]
+
+          # if draft, only take post name
+          if filename.split(".")[1].split(",")[0] == "draft"
+            directory = "_drafts"
+            name      = post_name.to_s
+          # if post, post date precede post name
+          else
+            directory = "_posts"
+            name      = "#{post_date}-#{post_name}"
+          end
+
+          xml = File.open(df) { |f| Nokogiri::XML(f) }
+          raise "There doesn't appear to be any XML items at the source (#{df}) provided." unless xml
+
+          doc = xml.xpath("document")
+          header = {
+            "layout" => layout,
+            "title"  => doc.xpath("title").text,
+            "tags"   => doc.xpath("tags").text.split(", "),
+          }
+          header["render_with_liquid"] = false if avoid_liquid
+
+          path = File.join(directory, "#{name}.html")
+          File.open(path, "w") do |f|
+            f.puts header.to_yaml
+            f.puts "---\n\n"
+            f.puts doc.xpath("chapo").text
+            f.puts doc.xpath("content").text
+          end
+
+          Jekyll.logger.info "Wrote file #{path} successfully!"
+        end
+        nil
+      end
+    end
+  end
+end

data/lib/jekyll-import/importers/roller.rb

@@ -80,7 +80,7 @@ module JekyllImport
           begin
             require "htmlentities"
           rescue LoadError
-            STDERR.puts "Could not require 'htmlentities', so the :clean_entities option is now disabled."
+            warn "Could not require 'htmlentities', so the :clean_entities option is now disabled."
             options[:clean_entities] = false
           end
         end

data/lib/jekyll-import/importers/rss.rb

@@ -41,9 +41,7 @@ module JekyllImport
 
         rss.items.each do |item|
           formatted_date = item.date.strftime("%Y-%m-%d")
-          post_name = item.title.split(%r{ |!|/|:|&|-|$|,}).map do |i|
-            i.downcase if i != ""
-          end.compact.join("-")
+          post_name = Jekyll::Utils.slugify(item.title, :mode => "latin")
           name = "#{formatted_date}-#{post_name}"
 
           header = {
@@ -51,18 +49,21 @@ module JekyllImport
             "title"  => item.title,
           }
 
-          header["tag"] = options["tag"] unless options.to_s.empty?
+          header["tag"] = options["tag"] unless options["tag"].nil? || options["tag"].empty?
 
           frontmatter.each do |value|
             header[value] = item.send(value)
           end
 
-          output = ""
+          output = +""
 
           body.each do |row|
-            output += item.send(row)
+            output << item.send(row).to_s
           end
 
+          output.strip!
+          output = item.content_encoded if output.empty?
+
           FileUtils.mkdir_p("_posts")
 
           File.open("_posts/#{name}.html", "w") do |f|

data/lib/jekyll-import/importers/s9y_database.rb

@@ -207,7 +207,7 @@ module JekyllImport
         require gem_name
         true
       rescue LoadError
-        STDERR.puts "Could not require '#{gem_name}', so the :#{option_name} option is now disabled."
+        warn "Could not require '#{gem_name}', so the :#{option_name} option is now disabled."
         true
       end
 
@@ -278,7 +278,7 @@ module JekyllImport
       end
 
       def self.process_tags(db, options, post)
-        return [] unless options[:categories]
+        return [] unless options[:tags]
 
         px = options[:table_prefix]
 

data/lib/jekyll-import/importers/tumblr.rb

@@ -266,7 +266,7 @@ module JekyllImport
               lang  = "python"
               start = i
             elsif block
-              lang  = "javascript" if line =~ %r!;$!
+              lang  = "javascript" if %r!;$!.match?(line)
               block = line =~ indent && i < lines.size - 1 # Also handle EOF
               unless block
                 lines[start] = "{% highlight #{lang} %}"
@@ -283,7 +283,7 @@ module JekyllImport
           return url unless @grab_images
 
           path = "tumblr_files/#{url.split("/").last}"
-          path += ext unless path =~ %r!#{ext}$!
+          path += ext unless %r!#{ext}$!.match?(path)
           FileUtils.mkdir_p "tumblr_files"
 
           # Don't fetch if we've already cached this file

data/lib/jekyll-import/importers/typo.rb

@@ -55,7 +55,7 @@ module JekyllImport
           raise "Unknown database server '#{server}'"
         end
         db[SQL].each do |post|
-          next unless post[:state] =~ %r!published!i
+          next unless %r!published!i.match?(post[:state])
 
           post[:slug] = "no slug" if post[:slug].nil?
 
@@ -77,8 +77,8 @@ module JekyllImport
 
           File.open("_posts/#{name}", "w") do |f|
             f.puts({ "layout"  => "post",
-                     "title"   => (post[:title]&.to_s&.force_encoding("UTF-8")),
-                     "tags"    => (post[:keywords]&.to_s&.force_encoding("UTF-8")),
+                     "title"   => post[:title]&.to_s&.force_encoding("UTF-8"),
+                     "tags"    => post[:keywords]&.to_s&.force_encoding("UTF-8"),
                      "typo_id" => post[:id], }.delete_if { |_k, v| v.nil? || v == "" }.to_yaml)
             f.puts "---"
             f.puts post[:body].delete("\r")

data/lib/jekyll-import/importers/wordpress.rb

@@ -101,7 +101,7 @@ module JekyllImport
           begin
             require "htmlentities"
           rescue LoadError
-            STDERR.puts "Could not require 'htmlentities', so the " \
+            warn "Could not require 'htmlentities', so the " \
                         ":clean_entities option is now disabled."
             options[:clean_entities] = false
           end

data/lib/jekyll-import/importers/wordpressdotcom.rb

@@ -30,14 +30,15 @@ module JekyllImport
         images.each do |i|
           uri = i["src"]
 
-          i["src"] = format("{{ site.baseurl }}/%s/%s", assets_folder, File.basename(uri))
           dst = File.join(assets_folder, File.basename(uri))
+          i["src"] = File.join("{{ site.baseurl }}", dst)
           Jekyll.logger.info uri
           if File.exist?(dst)
             Jekyll.logger.info "Already in cache. Clean assets folder if you want a redownload."
             next
           end
           begin
+            FileUtils.mkdir_p assets_folder
             OpenURI.open_uri(uri, :allow_redirections => :safe) do |f|
               File.open(dst, "wb") do |out|
                 out.puts f.read
@@ -191,7 +192,16 @@ module JekyllImport
             content = Hpricot(item.text_for("content:encoded"))
             header["excerpt"] = item.excerpt if item.excerpt
 
-            download_images(item.title, content, assets_folder) if fetch
+            if fetch
+              # Put the images into a /yyyy/mm/ subfolder to reduce clashes
+              assets_dir_path = if item.published_at
+                                  File.join(assets_folder, item.published_at.strftime("/%Y/%m"))
+                                else
+                                  assets_folder
+                                end
+
+              download_images(item.title, content, assets_dir_path)
+            end
 
             FileUtils.mkdir_p item.directory_name
             File.open(File.join(item.directory_name, item.file_name), "w") do |f|

data/lib/jekyll-import/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module JekyllImport
-  VERSION = "0.18.0"
+  VERSION = "0.20.0"
 end

data/lib/jekyll/commands/import.rb

@@ -64,7 +64,7 @@ module Jekyll
 
         def abort_on_invalid_migrator(migrator)
           warn "Sorry, '#{migrator}' isn't a valid migrator. Valid choices:"
-          IMPORTERS.keys.each { |k| warn "* #{k}" }
+          IMPORTERS.each_key { |k| warn "* #{k}" }
           raise "'#{migrator}' is not a valid migrator."
         end
       end

metadata

@@ -1,38 +1,24 @@
 --- !ruby/object:Gem::Specification
 name: jekyll-import
 version: !ruby/object:Gem::Version
-  version: 0.18.0
+  version: 0.20.0
 platform: ruby
 authors:
 - Tom Preston-Werner
 - Parker Moore
 - Matt Rogers
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2019-03-22 00:00:00.000000000 Z
+date: 2020-09-08 00:00:00.000000000 Z
 dependencies:
-- !ruby/object:Gem::Dependency
-  name: fastercsv
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1.0'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1.0'
 - !ruby/object:Gem::Dependency
   name: jekyll
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 4.0.0.pre.alpha1
+        version: '3.7'
     - - "<"
       - !ruby/object:Gem::Version
         version: '5.0'
@@ -40,9 +26,9 @@ dependencies:
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 4.0.0.pre.alpha1
+        version: '3.7'
     - - "<"
       - !ruby/object:Gem::Version
         version: '5.0'
@@ -164,14 +150,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.4'
+        version: 0.11.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.4'
+        version: 0.11.0
 - !ruby/object:Gem::Dependency
   name: shoulda
   requirement: !ruby/object:Gem::Requirement
@@ -370,6 +356,7 @@ files:
 - lib/jekyll-import/importers/behance.rb
 - lib/jekyll-import/importers/blogger.rb
 - lib/jekyll-import/importers/csv.rb
+- lib/jekyll-import/importers/dotclear.rb
 - lib/jekyll-import/importers/drupal6.rb
 - lib/jekyll-import/importers/drupal7.rb
 - lib/jekyll-import/importers/drupal_common.rb
@@ -383,6 +370,7 @@ files:
 - lib/jekyll-import/importers/marley.rb
 - lib/jekyll-import/importers/mephisto.rb
 - lib/jekyll-import/importers/mt.rb
+- lib/jekyll-import/importers/pluxml.rb
 - lib/jekyll-import/importers/posterous.rb
 - lib/jekyll-import/importers/roller.rb
 - lib/jekyll-import/importers/rss.rb
@@ -400,7 +388,7 @@ homepage: http://github.com/jekyll/jekyll-import
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options:
 - "--charset=UTF-8"
 require_paths:
@@ -417,7 +405,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubygems_version: 3.0.3
-signing_key: 
+signing_key:
 specification_version: 4
 summary: Import command for Jekyll (static site generator).
 test_files: []