jekyll 0.10.0 → 0.11.0

data/lib/jekyll/migrators/marley.rb

@@ -3,7 +3,6 @@ require 'fileutils'
 
 module Jekyll
   module Marley
-
     def self.regexp
       { :id    => /^\d{0,4}-{0,1}(.*)$/,
         :title => /^#\s*(.*)\s+$/,

data/lib/jekyll/migrators/mephisto.rb

@@ -36,11 +36,22 @@ module Jekyll
     # 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     # you've got unpublished, deleted or otherwise hidden posts please sift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"
+    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')
+      db = Sequel.mysql(dbname, :user => user,
+                                :password => pass,
+                                :host => host,
+                                :encoding => 'utf8')
 
       FileUtils.mkdir_p "_posts"
 
@@ -49,16 +60,10 @@ module Jekyll
         slug = post[:permalink]
         date = post[:published_at]
         content = post[:body]
-#         more_content = ''
-
-        # Be sure to include the body and extended body.
-#         if more_content != nil
-#           content = content + " \n" + more_content
-#         end
 
-        # 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.
+        # 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 = {

data/lib/jekyll/migrators/mt.rb

@@ -18,7 +18,14 @@ module Jekyll
     # 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     # you've got unpublished, deleted or otherwise hidden posts please sift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 entry_id, entry_basename, entry_text, entry_text_more, entry_authored_on, entry_title, entry_convert_breaks FROM mt_entry"
+    QUERY = "SELECT entry_id, \
+                    entry_basename, \
+                    entry_text, \
+                    entry_text_more, \
+                    entry_authored_on, \
+                    entry_title, \
+                    entry_convert_breaks \
+             FROM mt_entry"
 
     def self.process(dbname, user, pass, host = 'localhost')
       db = Sequel.mysql(dbname, :user => user, :password => pass, :host => host, :encoding => 'utf8')
@@ -38,17 +45,18 @@ module Jekyll
           content = content + " \n" + more_content
         end
 
-        # 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('-') + '.' + self.suffix(entry_convert_breaks)
+        # 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('-') + '.' +
+               self.suffix(entry_convert_breaks)
 
         data = {
            'layout' => 'post',
            'title' => title.to_s,
            'mt_id' => post[:entry_id],
            'date' => date
-         }.delete_if { |k,v| v.nil? || v == ''}.to_yaml
+         }.delete_if { |k,v| v.nil? || v == '' }.to_yaml
 
         File.open("_posts/#{name}", "w") do |f|
           f.puts data
@@ -60,17 +68,18 @@ module Jekyll
 
     def self.suffix(entry_type)
       if entry_type.nil? || entry_type.include?("markdown")
-          # The markdown plugin I have saves this as "markdown_with_smarty_pants", so I just look for "markdown".
-          "markdown"
-        elsif entry_type.include?("textile")
-          # This is saved as "textile_2" on my installation of MT 5.1.
-          "textile"
-        elsif entry_type == "0" || entry_type.include?("richtext")
-          # richtext looks to me like it's saved as HTML, so I include it here.
-          "html"
-        else
-          # Other values might need custom work.
-          entry_type
+        # The markdown plugin I have saves this as
+        # "markdown_with_smarty_pants", so I just look for "markdown".
+        "markdown"
+      elsif entry_type.include?("textile")
+        # This is saved as "textile_2" on my installation of MT 5.1.
+        "textile"
+      elsif entry_type == "0" || entry_type.include?("richtext")
+        # Richtext looks to me like it's saved as HTML, so I include it here.
+        "html"
+      else
+        # Other values might need custom work.
+        entry_type
       end
     end
   end

data/lib/jekyll/migrators/posterous.rb

@@ -0,0 +1,68 @@
+require 'rubygems'
+require 'jekyll'
+require 'fileutils'
+require 'net/http'
+require 'uri'
+require "json"
+
+# ruby -r './lib/jekyll/migrators/posterous.rb' -e 'Jekyll::Posterous.process(email, pass, blog)'
+
+module Jekyll
+  module Posterous
+    def self.fetch(uri_str, limit = 10)
+      # You should choose better exception.
+      raise ArgumentError, 'Stuck in a redirect loop. Please double check your email and password' if limit == 0
+
+      response = nil
+      Net::HTTP.start('posterous.com') do |http|
+        req = Net::HTTP::Get.new(uri_str)
+        req.basic_auth @email, @pass
+        response = http.request(req)
+      end
+
+      case response
+        when Net::HTTPSuccess     then response
+        when Net::HTTPRedirection then fetch(response['location'], limit - 1)
+        else response.error!
+      end
+    end
+
+    def self.process(email, pass, blog = 'primary')
+      @email, @pass = email, pass
+      @api_token = JSON.parse(self.fetch("/api/2/auth/token").body)['api_token']
+      FileUtils.mkdir_p "_posts"
+
+      posts = JSON.parse(self.fetch("/api/v2/users/me/sites/#{blog}/posts?api_token=#{@api_token}").body)
+      page = 1
+
+      while posts.any?
+        posts.each do |post|
+          title = post["title"]
+          slug = title.gsub(/[^[:alnum:]]+/, '-').downcase
+          date = Date.parse(post["display_date"])
+          content = post["body_html"]
+          published = !post["is_private"]
+          name = "%02d-%02d-%02d-%s.html" % [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,
+             'published' => published
+           }.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
+
+        page += 1
+        posts = JSON.parse(self.fetch("/api/v2/users/me/sites/#{blog}/posts?api_token=#{@api_token}&page=#{page}").body)
+      end
+    end
+  end
+end

data/lib/jekyll/migrators/textpattern.rb

@@ -11,10 +11,17 @@ require 'fileutils'
 module Jekyll
   module TextPattern
     # Reads a MySQL database via Sequel and creates a post file for each post.
-    # The only posts selected are those with a status of 4 or 5, which means "live"
-    # and "sticky" respectively.
-    # Other statuses is 1 => draft, 2 => hidden and 3 => pending
-    QUERY = "select Title, url_title, Posted, Body, Keywords from textpattern where Status = '4' or Status = '5'"
+    # The only posts selected are those with a status of 4 or 5, which means
+    # "live" and "sticky" respectively.
+    # Other statuses are 1 => draft, 2 => hidden and 3 => pending.
+    QUERY = "SELECT Title, \
+                    url_title, \
+                    Posted, \
+                    Body, \
+                    Keywords \
+             FROM textpattern \
+             WHERE Status = '4' OR \
+                   Status = '5'"
 
     def self.process(dbname, user, pass, host = 'localhost')
       db = Sequel.mysql(dbname, :user => user, :password => pass, :host => host, :encoding => 'utf8')
@@ -22,7 +29,7 @@ module Jekyll
       FileUtils.mkdir_p "_posts"
 
       db[QUERY].each do |post|
-        # Get required fields and construct Jekyll compatible name
+        # Get required fields and construct Jekyll compatible name.
         title = post[:Title]
         slug = post[:url_title]
         date = post[:Posted]
@@ -31,14 +38,14 @@ module Jekyll
         name = [date.strftime("%Y-%m-%d"), slug].join('-') + ".textile"
 
         # Get the relevant fields as a hash, delete empty fields and convert
-        # to YAML for the header
+        # to YAML for the header.
         data = {
            'layout' => 'post',
            'title' => title.to_s,
            'tags' => post[:Keywords].split(',')
          }.delete_if { |k,v| v.nil? || v == ''}.to_yaml
 
-        # Write out the data and content to file
+        # Write out the data and content to file.
         File.open("_posts/#{name}", "w") do |f|
           f.puts data
           f.puts "---"
@@ -47,4 +54,4 @@ module Jekyll
       end
     end
   end
-end
+end

data/lib/jekyll/migrators/tumblr.rb

@@ -0,0 +1,119 @@
+require 'rubygems'
+require 'nokogiri'
+require 'open-uri'
+require 'fileutils'
+require 'CGI'
+require 'iconv'
+require 'date'
+
+module Jekyll
+  module Tumblr
+    def self.process(url, grab_images = false)
+      current_page = 0
+
+      while true
+        f = open(url + "/api/read?num=50&start=#{current_page * 50}")
+        doc = Nokogiri::HTML(Iconv.conv("utf-8", f.charset, f.readlines.join("\n")))
+
+        puts "Page: #{current_page + 1} - Posts: #{(doc/:tumblr/:posts/:post).size}"
+
+        FileUtils.mkdir_p "_posts/tumblr"
+
+        (doc/:tumblr/:posts/:post).each do |post|
+          title = ""
+          content = nil
+          name = nil
+
+          if post['type'] == "regular"
+            title_element = post.at("regular-title")
+            title = title_element.inner_text unless title_element == nil
+            content = CGI::unescapeHTML post.at("regular-body").inner_html unless post.at("regular-body") == nil
+          elsif post['type'] == "link"
+            title = post.at("link-text").inner_html unless post.at("link-text") == nil
+
+            if post.at("link-text") != nil
+              content = "<a href=\"#{post.at("link-url").inner_html}\">#{post.at("link-text").inner_html}</a>"
+            else
+              content = "<a href=\"#{post.at("link-url").inner_html}\">#{post.at("link-url").inner_html}</a>"
+            end
+
+            content << "<br/>" + CGI::unescapeHTML(post.at("link-description").inner_html) unless post.at("link-description") == nil
+          elsif post['type'] == "photo"
+            content = ""
+
+            if post.at("photo-link-url") != nil
+              content = "<a href=\"#{post.at("photo-link-url").inner_html}\"><img src=\"#{save_file((post/"photo-url")[1].inner_html, grab_images)}\"/></a>"
+            else
+              content = "<img src=\"#{save_file((post/"photo-url")[1].inner_html, grab_images)}\"/>"
+            end
+
+            if post.at("photo-caption") != nil
+              content << "<br/>" unless content == nil
+              content << CGI::unescapeHTML(post.at("photo-caption").inner_html)
+            end
+          elsif post['type'] == "audio"
+            content = CGI::unescapeHTML(post.at("audio-player").inner_html)
+            content << CGI::unescapeHTML(post.at("audio-caption").inner_html) unless post.at("audio-caption") == nil
+          elsif post['type'] == "quote"
+            content = "<blockquote>" + CGI::unescapeHTML(post.at("quote-text").inner_html) + "</blockquote>"
+            content << "&#8212;" + CGI::unescapeHTML(post.at("quote-source").inner_html) unless post.at("quote-source") == nil
+          elsif post['type'] == "conversation"
+            title = post.at("conversation-title").inner_html unless post.at("conversation-title") == nil
+            content = "<section><dialog>"
+
+            (post/:conversation/:line).each do |line|
+              content << "<dt>" + line['label'] + "</dt><dd>" + line.inner_html + "</dd>" unless line['label'] == nil || line == nil
+            end
+
+            content << "</section></dialog>"
+          elsif post['type'] == "video"
+            title = post.at("video-title").inner_html unless post.at("video-title") == nil
+            content = CGI::unescapeHTML(post.at("video-player").inner_html)
+            content << CGI::unescapeHTML(post.at("video-caption").inner_html) unless post.at("video-caption") == nil
+          end # End post types
+
+          name = "#{Date.parse(post['date']).to_s}-#{post['id'].downcase.gsub(/[^a-z0-9]/, '-')}.html"
+
+          if title != nil || content != nil && name != nil
+            File.open("_posts/tumblr/#{name}", "w") do |f|
+
+              f.puts <<-HEADER
+---
+layout: post
+title: #{title}
+---
+
+HEADER
+
+              f.puts content
+            end # End file
+          end
+
+        end # End post XML
+
+        if (doc/:tumblr/:posts/:post).size < 50
+          break
+        else
+          current_page = current_page + 1
+        end
+
+      end # End while loop
+    end # End method
+
+    private
+
+    def self.save_file(url, grab_image = false)
+      unless grab_image == false
+        FileUtils.mkdir_p "tumblr_files"
+
+        File.open("tumblr_files/#{url.split('/').last}", "w") do |f|
+          f.write(open(url).read)
+        end
+
+        return "/tumblr_files/#{url.split('/').last}"
+      else
+        return url
+      end
+    end
+  end
+end

data/lib/jekyll/migrators/typo.rb

@@ -2,11 +2,12 @@
 require 'fileutils'
 require 'rubygems'
 require 'sequel'
+require 'yaml'
 
 module Jekyll
   module Typo
-    # this SQL *should* work for both MySQL and PostgreSQL, but I haven't
-    # tested PostgreSQL yet (as of 2008-12-16)
+    # This SQL *should* work for both MySQL and PostgreSQL, but I haven't
+    # tested PostgreSQL yet (as of 2008-12-16).
     SQL = <<-EOS
     SELECT c.id id,
            c.title title,
@@ -24,14 +25,15 @@ module Jekyll
       FileUtils.mkdir_p '_posts'
       db = Sequel.mysql(dbname, :user => user, :password => pass, :host => host, :encoding => 'utf8')
       db[SQL].each do |post|
-        next unless post[:state] =~ /Published/
+        next unless post[:state] =~ /published/
 
         name = [ sprintf("%.04d", post[:date].year),
                  sprintf("%.02d", post[:date].month),
                  sprintf("%.02d", post[:date].day),
                  post[:slug].strip ].join('-')
+
         # Can have more than one text filter in this field, but we just want
-        # the first one for this
+        # the first one for this.
         name += '.' + post[:filter].split(' ')[0]
 
         File.open("_posts/#{name}", 'w') do |f|
@@ -45,5 +47,5 @@ module Jekyll
       end
     end
 
-  end   # module Typo
-end   # module Jekyll
+  end
+end

data/lib/jekyll/migrators/wordpress.rb

@@ -11,20 +11,27 @@ require 'yaml'
 
 module Jekyll
   module WordPress
-
-    # 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 post_title, post_name, post_date, post_content, post_excerpt, ID, guid from wp_posts where post_status = 'publish' and post_type = 'post'"
-
-    def self.process(dbname, user, pass, host = 'localhost')
+    def self.process(dbname, user, pass, host = 'localhost', table_prefix = 'wp_')
       db = Sequel.mysql(dbname, :user => user, :password => pass, :host => host, :encoding => 'utf8')
 
-      FileUtils.mkdir_p "_posts"
-
-      db[QUERY].each do |post|
-        # Get required fields and construct Jekyll compatible name
+      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 post_title, \
+                      post_name, \
+                      post_date, \
+                      post_content, \
+                      post_excerpt, \
+                      ID, \
+                      guid \
+               FROM #{table_prefix}posts \
+               WHERE post_status = 'publish' AND \
+                     post_type = 'post'"
+
+      db[query].each do |post|
+        # Get required fields and construct Jekyll compatible name.
         title = post[:post_title]
         slug = post[:post_name]
         date = post[:post_date]
@@ -33,14 +40,15 @@ module Jekyll
                                                slug]
 
         # Get the relevant fields as a hash, delete empty fields and convert
-        # to YAML for the header
+        # to YAML for the header.
         data = {
            'layout' => 'post',
            'title' => title.to_s,
            'excerpt' => post[:post_excerpt].to_s,
            'wordpress_id' => post[:ID],
-           'wordpress_url' => post[:guid]
-         }.delete_if { |k,v| v.nil? || v == ''}.to_yaml
+           'wordpress_url' => post[:guid],
+           '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|
@@ -49,7 +57,6 @@ module Jekyll
           f.puts content
         end
       end
-
     end
   end
 end