RubyGems - jekyll-import - Versions diffs - 0.1.0.beta3 → 0.1.0.beta4 - Mend

jekyll-import 0.1.0.beta3 → 0.1.0.beta4

Files changed (50) hide show

checksums.yaml +6 -14
data/History.markdown +18 -0
data/README.markdown +12 -1
data/jekyll-import.gemspec +31 -25
data/lib/jekyll-import.rb +50 -1
data/lib/jekyll-import/importer.rb +11 -0
data/lib/jekyll-import/importers.rb +10 -0
data/lib/jekyll-import/importers/csv.rb +50 -0
data/lib/jekyll-import/importers/drupal6.rb +139 -0
data/lib/jekyll-import/importers/drupal7.rb +102 -0
data/lib/jekyll-import/importers/enki.rb +76 -0
data/lib/jekyll-import/importers/google_reader.rb +68 -0
data/lib/jekyll-import/importers/joomla.rb +83 -0
data/lib/jekyll-import/importers/jrnl.rb +127 -0
data/lib/jekyll-import/importers/marley.rb +72 -0
data/lib/jekyll-import/importers/mephisto.rb +109 -0
data/lib/jekyll-import/importers/mt.rb +169 -0
data/lib/jekyll-import/importers/posterous.rb +139 -0
data/lib/jekyll-import/importers/rss.rb +71 -0
data/lib/jekyll-import/importers/s9y.rb +67 -0
data/lib/jekyll-import/importers/textpattern.rb +76 -0
data/lib/jekyll-import/importers/tumblr.rb +265 -0
data/lib/jekyll-import/importers/typo.rb +89 -0
data/lib/jekyll-import/importers/wordpress.rb +323 -0
data/lib/jekyll-import/importers/wordpressdotcom.rb +97 -0
data/lib/jekyll/commands/import.rb +1 -0
data/test/helper.rb +3 -1
data/test/test_jrnl_importer.rb +39 -0
data/test/test_mt_importer.rb +16 -16
data/test/test_tumblr_importer.rb +61 -0
data/test/test_wordpress_importer.rb +1 -1
data/test/test_wordpressdotcom_importer.rb +1 -1
metadata +53 -32
data/lib/jekyll/jekyll-import/csv.rb +0 -30
data/lib/jekyll/jekyll-import/drupal6.rb +0 -112
data/lib/jekyll/jekyll-import/drupal7.rb +0 -74
data/lib/jekyll/jekyll-import/enki.rb +0 -49
data/lib/jekyll/jekyll-import/google_reader.rb +0 -61
data/lib/jekyll/jekyll-import/joomla.rb +0 -53
data/lib/jekyll/jekyll-import/marley.rb +0 -52
data/lib/jekyll/jekyll-import/mephisto.rb +0 -84
data/lib/jekyll/jekyll-import/mt.rb +0 -142
data/lib/jekyll/jekyll-import/posterous.rb +0 -122
data/lib/jekyll/jekyll-import/rss.rb +0 -63
data/lib/jekyll/jekyll-import/s9y.rb +0 -59
data/lib/jekyll/jekyll-import/textpattern.rb +0 -58
data/lib/jekyll/jekyll-import/tumblr.rb +0 -242
data/lib/jekyll/jekyll-import/typo.rb +0 -69
data/lib/jekyll/jekyll-import/wordpress.rb +0 -299
data/lib/jekyll/jekyll-import/wordpressdotcom.rb +0 -84

data/lib/jekyll/jekyll-import/drupal6.rb DELETED Viewed

@@ -1,112 +0,0 @@
-require 'rubygems'
-require 'sequel'
-require 'fileutils'
-require 'safe_yaml'
-# NOTE: This converter requires Sequel and the MySQL gems.
-# The MySQL gem can be difficult to install on OS X. Once you have MySQL
-# installed, running the following commands should work:
-# $ sudo gem install sequel
-# $ sudo gem install mysql -- --with-mysql-config=/usr/local/mysql/bin/mysql_config
-module JekyllImport
-  module Drupal6
-    # Reads a MySQL database via Sequel and creates a post file for each story
-    # and blog node in table node.
-    QUERY = "SELECT n.nid, \
-                    n.title, \
-                    nr.body, \
-                    n.created, \
-                    n.status, \
-                    GROUP_CONCAT( td.name SEPARATOR ' ' ) AS 'tags' \
-               FROM node_revisions AS nr, \
-                    node AS n \
-               JOIN term_node AS tn ON tn.nid = n.nid \
-               JOIN term_data AS td ON tn.tid = td.tid \
-              WHERE (n.type = 'blog' OR n.type = 'story') \
-                AND n.vid = nr.vid \
-           GROUP BY n.nid"
-    def self.process(dbname, user, pass, host = 'localhost', prefix = '')
-      db = Sequel.mysql(dbname, :user => user, :password => pass, :host => host, :encoding => 'utf8')
-      if prefix != ''
-        QUERY[" node "] = " " + prefix + "node "
-        QUERY[" node_revisions "] = " " + prefix + "node_revisions "
-        QUERY[" term_node "] = " " + prefix + "term_node "
-        QUERY[" term_data "] = " " + prefix + "term_data "
-      end
-      FileUtils.mkdir_p "_posts"
-      FileUtils.mkdir_p "_drafts"
-      # Create the refresh layout
-      # Change the refresh url if you customized your permalink config
-      File.open("_layouts/refresh.html", "w") do |f|
-        f.puts <<EOF
-<!DOCTYPE html>
-<html>
-<head>
-<meta http-equiv="content-type" content="text/html; charset=utf-8" />
-<meta http-equiv="refresh" content="0;url={{ page.refresh_to_post_id }}.html" />
-</head>
-</html>
-EOF
-      end
-      db[QUERY].each do |post|
-        # Get required fields and construct Jekyll compatible name
-        node_id = post[:nid]
-        title = post[:title]
-        content = post[:body]
-        tags = post[:tags].downcase.strip
-        created = post[:created]
-        time = Time.at(created)
-        is_published = post[:status] == 1
-        dir = is_published ? "_posts" : "_drafts"
-        slug = title.strip.downcase.gsub(/(&|&amp;)/, ' and ').gsub(/[\s\.\/\\]/, '-').gsub(/[^\w-]/, '').gsub(/[-_]{2,}/, '-').gsub(/^[-_]/, '').gsub(/[-_]$/, '')
-        name = time.strftime("%Y-%m-%d-") + slug + '.md'
-        # Get the relevant fields as a hash, delete empty fields and convert
-        # to YAML for the header
-        data = {
-           'layout' => 'post',
-           'title' => title.to_s,
-           'created' => created,
-           'categories' => tags
-         }.delete_if { |k,v| v.nil? || v == ''}.each_pair {
-            |k,v| ((v.is_a? String) ? v.force_encoding("UTF-8") : v)
-         }.to_yaml
-        # Write out the data and content to file
-        File.open("#{dir}/#{name}", "w") do |f|
-          f.puts data
-          f.puts "---"
-          f.puts content
-        end
-        # Make a file to redirect from the old Drupal URL
-        if is_published
-          aliases = db["SELECT dst FROM #{prefix}url_alias WHERE src = ?", "node/#{node_id}"].all
-          aliases.push(:dst => "node/#{node_id}")
-          aliases.each do |url_alias|
-            FileUtils.mkdir_p url_alias[:dst]
-            File.open("#{url_alias[:dst]}/index.md", "w") do |f|
-              f.puts "---"
-              f.puts "layout: refresh"
-              f.puts "refresh_to_post_id: /#{time.strftime("%Y/%m/%d/") + slug}"
-              f.puts "---"
-            end
-          end
-        end
-      end
-      # TODO: Make dirs & files for nodes of type 'page'
-        # Make refresh pages for these as well
-      # TODO: Make refresh dirs & files according to entries in url_alias table
-    end
-  end
-end

data/lib/jekyll/jekyll-import/drupal7.rb DELETED Viewed

@@ -1,74 +0,0 @@
-require 'rubygems'
-require 'sequel'
-require 'fileutils'
-require 'yaml'
-# NOTE: This converter requires Sequel and the MySQL gems.
-# The MySQL gem can be difficult to install on OS X. Once you have MySQL
-# installed, running the following commands should work:
-# $ sudo gem install sequel
-# $ sudo gem install mysql -- --with-mysql-config=/usr/local/mysql/bin/mysql_config
-module JekyllImport
-  module Drupal7
-    # Reads a MySQL database via Sequel and creates a post file for each post
-    # in wp_posts that has post_status = 'publish'. This restriction is made
-    # because 'draft' posts are not guaranteed to have valid dates.
-    QUERY = "SELECT n.nid, \
-                    n.title, \
-                    fdb.body_value, \
-                    n.created, \
-                    n.status \
-             FROM node AS n, \
-                  field_data_body AS fdb \
-             WHERE (n.type = 'blog' OR n.type = 'story') \
-             AND n.nid = fdb.entity_id \
-             AND n.vid = fdb.revision_id"
-    def self.process(dbname, user, pass, host = 'localhost', prefix = '')
-      db = Sequel.mysql(dbname, :user => user, :password => pass, :host => host, :encoding => 'utf8')
-      if prefix != ''
-        QUERY[" node "] = " " + prefix + "node "
-        QUERY[" field_data_body "] = " " + prefix + "field_data_body "
-      end
-      FileUtils.mkdir_p "_posts"
-      FileUtils.mkdir_p "_drafts"
-      db[QUERY].each do |post|
-        # Get required fields and construct Jekyll compatible name
-        node_id = post[:nid]
-        title = post[:title]
-        content = post[:body_value]
-        created = post[:created]
-        time = Time.at(created)
-        is_published = post[:status] == 1
-        dir = is_published ? "_posts" : "_drafts"
-        slug = title.strip.downcase.gsub(/(&|&amp;)/, ' and ').gsub(/[\s\.\/\\]/, '-').gsub(/[^\w-]/, '').gsub(/[-_]{2,}/, '-').gsub(/^[-_]/, '').gsub(/[-_]$/, '')
-        name = time.strftime("%Y-%m-%d-") + slug + '.md'
-        # Get the relevant fields as a hash, delete empty fields and convert
-        # to YAML for the header
-        data = {
-           'layout' => 'default',
-           'title' => title.to_s,
-           'created' => created,
-         }.delete_if { |k,v| v.nil? || v == ''}.to_yaml
-        # Write out the data and content to file
-        File.open("#{dir}/#{name}", "w") do |f|
-          f.puts data
-          f.puts "---"
-          f.puts content
-        end
-      end
-      # TODO: Make dirs & files for nodes of type 'page'
-        # Make refresh pages for these as well
-      # TODO: Make refresh dirs & files according to entries in url_alias table
-    end
-  end
-end

data/lib/jekyll/jekyll-import/enki.rb DELETED Viewed

@@ -1,49 +0,0 @@
-# Adapted by Rodrigo Pinto <rodrigopqn@gmail.com>
-# Based on typo.rb by Toby DiPasquale
-require 'fileutils'
-require 'rubygems'
-require 'sequel'
-module JekyllImport
-  module Enki
-    SQL = <<-EOS
-      SELECT p.id,
-             p.title,
-             p.slug,
-             p.body,
-             p.published_at as date,
-             p.cached_tag_list as tags
-      FROM posts p
-    EOS
-    # Just working with postgres, but can be easily adapted
-    # to work with both mysql and postgres.
-    def self.process(dbname, user, pass, host = 'localhost')
-      FileUtils.mkdir_p('_posts')
-      db = Sequel.postgres(:database => dbname,
-                           :user => user,
-                           :password => pass,
-                           :host => host,
-                           :encoding => 'utf8')
-      db[SQL].each do |post|
-        name = [ sprintf("%.04d", post[:date].year),
-                 sprintf("%.02d", post[:date].month),
-                 sprintf("%.02d", post[:date].day),
-                 post[:slug].strip ].join('-')
-        name += '.textile'
-        File.open("_posts/#{name}", 'w') do |f|
-          f.puts({ 'layout'   => 'post',
-                   'title'    => post[:title].to_s,
-                   'enki_id'  => post[:id],
-                   'categories'  => post[:tags]
-                 }.delete_if { |k, v| v.nil? || v == '' }.to_yaml)
-          f.puts '---'
-          f.puts post[:body].delete("\r")
-        end
-      end
-    end
-  end
-end

data/lib/jekyll/jekyll-import/google_reader.rb DELETED Viewed

@@ -1,61 +0,0 @@
-# Usage:
-#   (Local file)
-#   ruby -r 'jekyll/jekyll-import/rss' -e "JekyllImport::GoogleReader.process(:source => './somefile/on/your/computer.xml')"
-require 'rss'
-require 'open-uri'
-require 'fileutils'
-require 'safe_yaml'
-require 'rexml/document'
-require 'date'
-module JekyllImport
-  module GoogleReader
-    def self.validate(options)
-      if !options[:source]
-        abort "Missing mandatory option --source."
-      end
-    end
-    # Process the import.
-    #
-    # source - a URL or a local file String.
-    #
-    # Returns nothing.
-    def self.process(options)
-      validate(options)
-      source = options[:source]
-      open(source) do |content|
-        feed = RSS::Parser.parse(content)
-        raise "There doesn't appear to be any RSS items at the source (#{source}) provided." unless feed
-        feed.items.each do |item|
-          title = item.title.content.to_s
-          formatted_date = Date.parse(item.published.to_s)
-          post_name = title.split(%r{ |!|/|:|&|-|$|,}).map do |i|
-            i.downcase if i != ''
-          end.compact.join('-')
-          name = "#{formatted_date}-#{post_name}"
-          header = {
-            'layout' => 'post',
-            'title' => title
-          }
-          FileUtils.mkdir_p("_posts")
-          File.open("_posts/#{name}.html", "w") do |f|
-            f.puts header.to_yaml
-            f.puts "---\n\n"
-            f.puts item.content.content.to_s
-          end
-        end
-      end
-    end
-  end
-end

data/lib/jekyll/jekyll-import/joomla.rb DELETED Viewed

@@ -1,53 +0,0 @@
-require 'rubygems'
-require 'sequel'
-require 'fileutils'
-require 'safe_yaml'
-# NOTE: This migrator is made for Joomla 1.5 databases.
-# NOTE: This converter requires Sequel and the MySQL gems.
-# The MySQL gem can be difficult to install on OS X. Once you have MySQL
-# installed, running the following commands should work:
-# $ sudo gem install sequel
-# $ sudo gem install mysql -- --with-mysql-config=/usr/local/mysql/bin/mysql_config
-module JekyllImport
-  module Joomla
-    def self.process(dbname, user, pass, host = 'localhost', table_prefix = 'jos_', section = '1')
-      db = Sequel.mysql(dbname, :user => user, :password => pass, :host => host, :encoding => 'utf8')
-      FileUtils.mkdir_p("_posts")
-      # Reads a MySQL database via Sequel and creates a post file for each
-      # post in wp_posts that has post_status = 'publish'. This restriction is
-      # made because 'draft' posts are not guaranteed to have valid dates.
-      query = "SELECT `title`, `alias`, CONCAT(`introtext`,`fulltext`) as content, `created`, `id` FROM #{table_prefix}content WHERE state = '0' OR state = '1' AND sectionid = '#{section}'"
-      db[query].each do |post|
-        # Get required fields and construct Jekyll compatible name.
-        title = post[:title]
-        slug = post[:alias]
-        date = post[:created]
-        content = post[:content]
-        name = "%02d-%02d-%02d-%s.markdown" % [date.year, date.month, date.day,
-                                               slug]
-        # Get the relevant fields as a hash, delete empty fields and convert
-        # to YAML for the header.
-        data = {
-           'layout' => 'post',
-           'title' => title.to_s,
-           'joomla_id' => post[:id],
-           'joomla_url' => post[:alias],
-           'date' => date
-         }.delete_if { |k,v| v.nil? || v == '' }.to_yaml
-        # Write out the data and content to file
-        File.open("_posts/#{name}", "w") do |f|
-          f.puts data
-          f.puts "---"
-          f.puts content
-        end
-      end
-    end
-  end
-end

data/lib/jekyll/jekyll-import/marley.rb DELETED Viewed

@@ -1,52 +0,0 @@
-require 'safe_yaml'
-require 'fileutils'
-module JekyllImport
-  module Marley
-    def self.regexp
-      { :id    => /^\d{0,4}-{0,1}(.*)$/,
-        :title => /^#\s*(.*)\s+$/,
-        :title_with_date => /^#\s*(.*)\s+\(([0-9\/]+)\)$/,
-        :published_on => /.*\s+\(([0-9\/]+)\)$/,
-        :perex => /^([^\#\n]+\n)$/,
-        :meta  => /^\{\{\n(.*)\}\}\n$/mi # Multiline Regexp
-      }
-    end
-    def self.process(marley_data_dir)
-      raise ArgumentError, "marley dir #{marley_data_dir} not found" unless File.directory?(marley_data_dir)
-      FileUtils.mkdir_p "_posts"
-      posts = 0
-      Dir["#{marley_data_dir}/**/*.txt"].each do |f|
-        next unless File.exists?(f)
-        #copied over from marley's app/lib/post.rb
-        file_content  = File.read(f)
-        meta_content  = file_content.slice!( self.regexp[:meta] )
-        body          = file_content.sub( self.regexp[:title], '').sub( self.regexp[:perex], '').strip
-        title = file_content.scan( self.regexp[:title] ).first.to_s.strip
-        prerex = file_content.scan( self.regexp[:perex] ).first.to_s.strip
-        published_on = DateTime.parse( post[:published_on] ) rescue File.mtime( File.dirname(f) )
-        meta          = ( meta_content ) ? YAML::load( meta_content.scan( self.regexp[:meta]).to_s ) : {}
-        meta['title'] = title
-        meta['layout'] = 'post'
-        formatted_date = published_on.strftime('%Y-%m-%d')
-        post_name =  File.dirname(f).split(%r{/}).last.gsub(/\A\d+-/, '')
-        name = "#{formatted_date}-#{post_name}"
-        File.open("_posts/#{name}.markdown", "w") do |f|
-          f.puts meta.to_yaml
-          f.puts "---\n"
-          f.puts "\n#{prerex}\n\n" if prerex
-          f.puts body
-        end
-        posts += 1
-      end
-      "Created #{posts} posts!"
-    end
-  end
-end

data/lib/jekyll/jekyll-import/mephisto.rb DELETED Viewed

@@ -1,84 +0,0 @@
-# Quickly hacked together my Michael Ivey
-# Based on mt.rb by Nick Gerakines, open source and publically
-# available under the MIT license. Use this module at your own risk.
-require 'rubygems'
-require 'sequel'
-require 'fastercsv'
-require 'fileutils'
-require File.join(File.dirname(__FILE__),"csv.rb")
-# NOTE: This converter requires Sequel and the MySQL gems.
-# The MySQL gem can be difficult to install on OS X. Once you have MySQL
-# installed, running the following commands should work:
-# $ sudo gem install sequel
-# $ sudo gem install mysql -- --with-mysql-config=/usr/local/mysql/bin/mysql_config
-module JekyllImport
-  module Mephisto
-    #Accepts a hash with database config variables, exports mephisto posts into a csv
-    #export PGPASSWORD if you must
-    def self.postgres(c)
-      sql = <<-SQL
-      BEGIN;
-      CREATE TEMP TABLE jekyll AS
-        SELECT title, permalink, body, published_at, filter FROM contents
-        WHERE user_id = 1 AND type = 'Article' ORDER BY published_at;
-      COPY jekyll TO STDOUT WITH CSV HEADER;
-      ROLLBACK;
-      SQL
-      command = %Q(psql -h #{c[:host] || "localhost"} -c "#{sql.strip}" #{c[:database]} #{c[:username]} -o #{c[:filename] || "posts.csv"})
-      puts command
-      `#{command}`
-      CSV.process
-    end
-    # This query will pull blog posts from all entries across all blogs. If
-    # you've got unpublished, deleted or otherwise hidden posts please sift
-    # through the created posts to make sure nothing is accidently published.
-    QUERY = "SELECT id, \
-                    permalink, \
-                    body, \
-                    published_at, \
-                    title \
-             FROM contents \
-             WHERE user_id = 1 AND \
-                   type = 'Article' AND \
-                   published_at IS NOT NULL \
-             ORDER BY published_at"
-    def self.process(dbname, user, pass, host = 'localhost')
-      db = Sequel.mysql(dbname, :user => user,
-                                :password => pass,
-                                :host => host,
-                                :encoding => 'utf8')
-      FileUtils.mkdir_p "_posts"
-      db[QUERY].each do |post|
-        title = post[:title]
-        slug = post[:permalink]
-        date = post[:published_at]
-        content = post[:body]
-        # Ideally, this script would determine the post format (markdown,
-        # html, etc) and create files with proper extensions. At this point
-        # it just assumes that markdown will be acceptable.
-        name = [date.year, date.month, date.day, slug].join('-') + ".markdown"
-        data = {
-           'layout' => 'post',
-           'title' => title.to_s,
-           'mt_id' => post[:entry_id],
-         }.delete_if { |k,v| v.nil? || v == ''}.to_yaml
-        File.open("_posts/#{name}", "w") do |f|
-          f.puts data
-          f.puts "---"
-          f.puts content
-        end
-      end
-    end
-  end
-end