jekyll-import 0.1.0.beta3 → 0.1.0.beta4

Sign up to get free protection for your applications and to get access to all the features.
Files changed (50) hide show
  1. checksums.yaml +6 -14
  2. data/History.markdown +18 -0
  3. data/README.markdown +12 -1
  4. data/jekyll-import.gemspec +31 -25
  5. data/lib/jekyll-import.rb +50 -1
  6. data/lib/jekyll-import/importer.rb +11 -0
  7. data/lib/jekyll-import/importers.rb +10 -0
  8. data/lib/jekyll-import/importers/csv.rb +50 -0
  9. data/lib/jekyll-import/importers/drupal6.rb +139 -0
  10. data/lib/jekyll-import/importers/drupal7.rb +102 -0
  11. data/lib/jekyll-import/importers/enki.rb +76 -0
  12. data/lib/jekyll-import/importers/google_reader.rb +68 -0
  13. data/lib/jekyll-import/importers/joomla.rb +83 -0
  14. data/lib/jekyll-import/importers/jrnl.rb +127 -0
  15. data/lib/jekyll-import/importers/marley.rb +72 -0
  16. data/lib/jekyll-import/importers/mephisto.rb +109 -0
  17. data/lib/jekyll-import/importers/mt.rb +169 -0
  18. data/lib/jekyll-import/importers/posterous.rb +139 -0
  19. data/lib/jekyll-import/importers/rss.rb +71 -0
  20. data/lib/jekyll-import/importers/s9y.rb +67 -0
  21. data/lib/jekyll-import/importers/textpattern.rb +76 -0
  22. data/lib/jekyll-import/importers/tumblr.rb +265 -0
  23. data/lib/jekyll-import/importers/typo.rb +89 -0
  24. data/lib/jekyll-import/importers/wordpress.rb +323 -0
  25. data/lib/jekyll-import/importers/wordpressdotcom.rb +97 -0
  26. data/lib/jekyll/commands/import.rb +1 -0
  27. data/test/helper.rb +3 -1
  28. data/test/test_jrnl_importer.rb +39 -0
  29. data/test/test_mt_importer.rb +16 -16
  30. data/test/test_tumblr_importer.rb +61 -0
  31. data/test/test_wordpress_importer.rb +1 -1
  32. data/test/test_wordpressdotcom_importer.rb +1 -1
  33. metadata +53 -32
  34. data/lib/jekyll/jekyll-import/csv.rb +0 -30
  35. data/lib/jekyll/jekyll-import/drupal6.rb +0 -112
  36. data/lib/jekyll/jekyll-import/drupal7.rb +0 -74
  37. data/lib/jekyll/jekyll-import/enki.rb +0 -49
  38. data/lib/jekyll/jekyll-import/google_reader.rb +0 -61
  39. data/lib/jekyll/jekyll-import/joomla.rb +0 -53
  40. data/lib/jekyll/jekyll-import/marley.rb +0 -52
  41. data/lib/jekyll/jekyll-import/mephisto.rb +0 -84
  42. data/lib/jekyll/jekyll-import/mt.rb +0 -142
  43. data/lib/jekyll/jekyll-import/posterous.rb +0 -122
  44. data/lib/jekyll/jekyll-import/rss.rb +0 -63
  45. data/lib/jekyll/jekyll-import/s9y.rb +0 -59
  46. data/lib/jekyll/jekyll-import/textpattern.rb +0 -58
  47. data/lib/jekyll/jekyll-import/tumblr.rb +0 -242
  48. data/lib/jekyll/jekyll-import/typo.rb +0 -69
  49. data/lib/jekyll/jekyll-import/wordpress.rb +0 -299
  50. data/lib/jekyll/jekyll-import/wordpressdotcom.rb +0 -84
@@ -0,0 +1,89 @@
1
+ # Author: Toby DiPasquale <toby@cbcg.net>
2
+ module JekyllImport
3
+ module Importers
4
+ class Typo < Importer
5
+ # This SQL *should* work for both MySQL and PostgreSQL.
6
+ SQL = <<-EOS
7
+ SELECT c.id id,
8
+ c.title title,
9
+ c.permalink slug,
10
+ c.body body,
11
+ c.extended extended,
12
+ c.published_at date,
13
+ c.state state,
14
+ c.keywords keywords,
15
+ COALESCE(tf.name, 'html') filter
16
+ FROM contents c
17
+ LEFT OUTER JOIN text_filters tf
18
+ ON c.text_filter_id = tf.id
19
+ EOS
20
+
21
+ def self.require_deps
22
+ JekyllImport.require_with_fallback(%w[
23
+ rubygems
24
+ sequel
25
+ fileutils
26
+ safe_yaml
27
+ ])
28
+ end
29
+
30
+ def self.specify_options(c)
31
+ c.option 'server', '--server TYPE', 'Server type ("mysql" or "postgres")'
32
+ c.option 'dbname', '--dbname DB', 'Database name'
33
+ c.option 'user', '--user USER', 'Database user name'
34
+ c.option 'password', '--password PW', "Database user's password (default: '')"
35
+ c.option 'host', '--host HOST', 'Database host name'
36
+ end
37
+
38
+ def self.process(options)
39
+ server = options.fetch('server')
40
+ dbname = options.fetch('dbname')
41
+ user = options.fetch('user')
42
+ pass = options.fetch('password', '')
43
+ host = options.fetch('host', "localhost")
44
+
45
+ FileUtils.mkdir_p '_posts'
46
+ case server.intern
47
+ when :postgres
48
+ db = Sequel.postgres(dbname, :user => user, :password => pass, :host => host, :encoding => 'utf8')
49
+ when :mysql
50
+ db = Sequel.mysql(dbname, :user => user, :password => pass, :host => host, :encoding => 'utf8')
51
+ else
52
+ raise "Unknown database server '#{server}'"
53
+ end
54
+ db[SQL].each do |post|
55
+ next unless post[:state] =~ /published/i
56
+
57
+ if post[:slug] == nil
58
+ post[:slug] = "no slug"
59
+ end
60
+
61
+ if post[:extended]
62
+ post[:body] << "\n<!-- more -->\n"
63
+ post[:body] << post[:extended]
64
+ end
65
+
66
+ name = [ sprintf("%.04d", post[:date].year),
67
+ sprintf("%.02d", post[:date].month),
68
+ sprintf("%.02d", post[:date].day),
69
+ post[:slug].strip ].join('-')
70
+
71
+ # Can have more than one text filter in this field, but we just want
72
+ # the first one for this.
73
+ name += '.' + post[:filter].split(' ')[0]
74
+
75
+ File.open("_posts/#{name}", 'w') do |f|
76
+ f.puts({ 'layout' => 'post',
77
+ 'title' => (post[:title] and post[:title].to_s.force_encoding('UTF-8')),
78
+ 'tags' => (post[:keywords] and post[:keywords].to_s.force_encoding('UTF-8')),
79
+ 'typo_id' => post[:id]
80
+ }.delete_if { |k, v| v.nil? || v == '' }.to_yaml)
81
+ f.puts '---'
82
+ f.puts post[:body].delete("\r")
83
+ end
84
+ end
85
+ end
86
+
87
+ end
88
+ end
89
+ end
@@ -0,0 +1,323 @@
1
+ # NOTE: This converter requires Sequel and the MySQL gems.
2
+ # The MySQL gem can be difficult to install on OS X. Once you have MySQL
3
+ # installed, running the following commands should work:
4
+ # $ sudo gem install sequel
5
+ # $ sudo gem install mysql -- --with-mysql-config=/usr/local/mysql/bin/mysql_config
6
+ #
7
+ # If you are running MacPorts, it the mysql2 gem can be installed like this:
8
+ # $ gem install mysql2 -- --with-mysql-lib=/opt/local/lib/mysql56/mysql/ --with-mysql-include=/opt/local/include/mysql56/mysql
9
+
10
+ module JekyllImport
11
+ module Importers
12
+ class WordPress < Importer
13
+
14
+ def self.require_deps
15
+ JekyllImport.require_with_fallback(%w[
16
+ rubygems
17
+ sequel
18
+ fileutils
19
+ safe_yaml
20
+ ])
21
+ end
22
+
23
+ def self.specify_options(c)
24
+ c.option 'dbname', '--dbname DB', 'Database name (default: "")'
25
+ c.option 'user', '--user USER', 'Database user name (default: "")'
26
+ c.option 'password', '--password PW', "Database user's password (default: "")"
27
+ c.option 'host', '--host HOST', 'Database host name (default: "localhost")'
28
+ c.option 'table_prefix', '--prefix PREFIX', 'Table prefix name (default: "wp_")'
29
+ c.option 'clean_entities', '--clean_entities', 'Whether to clean entities (default: true)'
30
+ c.option 'comments', '--comments', 'Whether to import comments (default: true)'
31
+ c.option 'categories', '--categories', 'Whether to import categories (default: true)'
32
+ c.option 'tags', '--tags', 'Whether to import tags (default: true)'
33
+ c.option 'more_excerpt', '--more_excerpt', 'Whether to use more excerpt (default: true)'
34
+ c.option 'more_anchor', '--more_anchor', 'Whether to use more anchor (default: true)'
35
+ c.option 'status', '--status STATUS,STATUS2', Array, 'Array of allowed statuses (default: ["publish"], other options: "draft", "private", "revision")'
36
+ end
37
+
38
+ # Main migrator function. Call this to perform the migration.
39
+ #
40
+ # dbname:: The name of the database
41
+ # user:: The database user name
42
+ # pass:: The database user's password
43
+ # host:: The address of the MySQL database host. Default: 'localhost'
44
+ # options:: A hash table of configuration options.
45
+ #
46
+ # Supported options are:
47
+ #
48
+ # :table_prefix:: Prefix of database tables used by WordPress.
49
+ # Default: 'wp_'
50
+ # :clean_entities:: If true, convert non-ASCII characters to HTML
51
+ # entities in the posts, comments, titles, and
52
+ # names. Requires the 'htmlentities' gem to
53
+ # work. Default: true.
54
+ # :comments:: If true, migrate post comments too. Comments
55
+ # are saved in the post's YAML front matter.
56
+ # Default: true.
57
+ # :categories:: If true, save the post's categories in its
58
+ # YAML front matter.
59
+ # :tags:: If true, save the post's tags in its
60
+ # YAML front matter.
61
+ # :more_excerpt:: If true, when a post has no excerpt but
62
+ # does have a <!-- more --> tag, use the
63
+ # preceding post content as the excerpt.
64
+ # Default: true.
65
+ # :more_anchor:: If true, convert a <!-- more --> tag into
66
+ # two HTML anchors with ids "more" and
67
+ # "more-NNN" (where NNN is the post number).
68
+ # Default: true.
69
+ # :status:: Array of allowed post statuses. Only
70
+ # posts with matching status will be migrated.
71
+ # Known statuses are :publish, :draft, :private,
72
+ # and :revision. If this is nil or an empty
73
+ # array, all posts are migrated regardless of
74
+ # status. Default: [:publish].
75
+ #
76
+ def self.process(opts)
77
+ options = {
78
+ :user => opts.fetch('user', ''),
79
+ :pass => opts.fetch('password', ''),
80
+ :host => opts.fetch('host', 'localhost'),
81
+ :dbname => opts.fetch('dbname', ''),
82
+ :table_prefix => opts.fetch('prefix', 'wp_'),
83
+ :clean_entities => opts.fetch('clean_entities', true),
84
+ :comments => opts.fetch('comments', true),
85
+ :categories => opts.fetch('categories', true),
86
+ :tags => opts.fetch('tags', true),
87
+ :more_excerpt => opts.fetch('more_excerpt', true),
88
+ :more_anchor => opts.fetch('more_anchor', true),
89
+ :status => opts.fetch('status', ["publish"]).map(&:to_sym) # :draft, :private, :revision
90
+ }
91
+
92
+ if options[:clean_entities]
93
+ begin
94
+ require 'htmlentities'
95
+ rescue LoadError
96
+ STDERR.puts "Could not require 'htmlentities', so the " +
97
+ ":clean_entities option is now disabled."
98
+ options[:clean_entities] = false
99
+ end
100
+ end
101
+
102
+ FileUtils.mkdir_p("_posts")
103
+
104
+ db = Sequel.mysql2(options[:dbname], :user => options[:user], :password => options[:pass],
105
+ :host => options[:host], :encoding => 'utf8')
106
+
107
+ px = options[:table_prefix]
108
+
109
+ posts_query = "
110
+ SELECT
111
+ posts.ID AS `id`,
112
+ posts.guid AS `guid`,
113
+ posts.post_type AS `type`,
114
+ posts.post_status AS `status`,
115
+ posts.post_title AS `title`,
116
+ posts.post_name AS `slug`,
117
+ posts.post_date AS `date`,
118
+ posts.post_content AS `content`,
119
+ posts.post_excerpt AS `excerpt`,
120
+ posts.comment_count AS `comment_count`,
121
+ users.display_name AS `author`,
122
+ users.user_login AS `author_login`,
123
+ users.user_email AS `author_email`,
124
+ users.user_url AS `author_url`
125
+ FROM #{px}posts AS `posts`
126
+ LEFT JOIN #{px}users AS `users`
127
+ ON posts.post_author = users.ID"
128
+
129
+ if options[:status] and not options[:status].empty?
130
+ status = options[:status][0]
131
+ posts_query << "
132
+ WHERE posts.post_status = '#{status.to_s}'"
133
+ options[:status][1..-1].each do |status|
134
+ posts_query << " OR
135
+ posts.post_status = '#{status.to_s}'"
136
+ end
137
+ end
138
+
139
+ db[posts_query].each do |post|
140
+ process_post(post, db, options)
141
+ end
142
+ end
143
+
144
+
145
+ def self.process_post(post, db, options)
146
+ px = options[:table_prefix]
147
+
148
+ title = post[:title]
149
+ if options[:clean_entities]
150
+ title = clean_entities(title)
151
+ end
152
+
153
+ slug = post[:slug]
154
+ if !slug or slug.empty?
155
+ slug = sluggify(title)
156
+ end
157
+
158
+ date = post[:date] || Time.now
159
+ name = "%02d-%02d-%02d-%s.markdown" % [date.year, date.month,
160
+ date.day, slug]
161
+ content = post[:content].to_s
162
+ if options[:clean_entities]
163
+ content = clean_entities(content)
164
+ end
165
+
166
+ excerpt = post[:excerpt].to_s
167
+
168
+ more_index = content.index(/<!-- *more *-->/)
169
+ more_anchor = nil
170
+ if more_index
171
+ if options[:more_excerpt] and
172
+ (post[:excerpt].nil? or post[:excerpt].empty?)
173
+ excerpt = content[0...more_index]
174
+ end
175
+ if options[:more_anchor]
176
+ more_link = "more"
177
+ content.sub!(/<!-- *more *-->/,
178
+ "<a id=\"more\"></a>" +
179
+ "<a id=\"more-#{post[:id]}\"></a>")
180
+ end
181
+ end
182
+
183
+ categories = []
184
+ tags = []
185
+
186
+ if options[:categories] or options[:tags]
187
+
188
+ cquery =
189
+ "SELECT
190
+ terms.name AS `name`,
191
+ ttax.taxonomy AS `type`
192
+ FROM
193
+ #{px}terms AS `terms`,
194
+ #{px}term_relationships AS `trels`,
195
+ #{px}term_taxonomy AS `ttax`
196
+ WHERE
197
+ trels.object_id = '#{post[:id]}' AND
198
+ trels.term_taxonomy_id = ttax.term_taxonomy_id AND
199
+ terms.term_id = ttax.term_id"
200
+
201
+ db[cquery].each do |term|
202
+ if options[:categories] and term[:type] == "category"
203
+ if options[:clean_entities]
204
+ categories << clean_entities(term[:name])
205
+ else
206
+ categories << term[:name]
207
+ end
208
+ elsif options[:tags] and term[:type] == "post_tag"
209
+ if options[:clean_entities]
210
+ tags << clean_entities(term[:name])
211
+ else
212
+ tags << term[:name]
213
+ end
214
+ end
215
+ end
216
+ end
217
+
218
+ comments = []
219
+
220
+ if options[:comments] and post[:comment_count].to_i > 0
221
+ cquery =
222
+ "SELECT
223
+ comment_ID AS `id`,
224
+ comment_author AS `author`,
225
+ comment_author_email AS `author_email`,
226
+ comment_author_url AS `author_url`,
227
+ comment_date AS `date`,
228
+ comment_date_gmt AS `date_gmt`,
229
+ comment_content AS `content`
230
+ FROM #{px}comments
231
+ WHERE
232
+ comment_post_ID = '#{post[:id]}' AND
233
+ comment_approved != 'spam'"
234
+
235
+
236
+ db[cquery].each do |comment|
237
+
238
+ comcontent = comment[:content].to_s
239
+ if comcontent.respond_to?(:force_encoding)
240
+ comcontent.force_encoding("UTF-8")
241
+ end
242
+ if options[:clean_entities]
243
+ comcontent = clean_entities(comcontent)
244
+ end
245
+ comauthor = comment[:author].to_s
246
+ if options[:clean_entities]
247
+ comauthor = clean_entities(comauthor)
248
+ end
249
+
250
+ comments << {
251
+ 'id' => comment[:id].to_i,
252
+ 'author' => comauthor,
253
+ 'author_email' => comment[:author_email].to_s,
254
+ 'author_url' => comment[:author_url].to_s,
255
+ 'date' => comment[:date].to_s,
256
+ 'date_gmt' => comment[:date_gmt].to_s,
257
+ 'content' => comcontent,
258
+ }
259
+ end
260
+
261
+ comments.sort!{ |a,b| a['id'] <=> b['id'] }
262
+ end
263
+
264
+ # Get the relevant fields as a hash, delete empty fields and
265
+ # convert to YAML for the header.
266
+ data = {
267
+ 'layout' => post[:type].to_s,
268
+ 'status' => post[:status].to_s,
269
+ 'published' => (post[:status].to_s == "publish"),
270
+ 'title' => title.to_s,
271
+ 'author' => post[:author].to_s,
272
+ 'author_login' => post[:author_login].to_s,
273
+ 'author_email' => post[:author_email].to_s,
274
+ 'author_url' => post[:author_url].to_s,
275
+ 'excerpt' => excerpt,
276
+ 'more_anchor' => more_anchor,
277
+ 'wordpress_id' => post[:id],
278
+ 'wordpress_url' => post[:guid].to_s,
279
+ 'date' => date,
280
+ 'categories' => options[:categories] ? categories : nil,
281
+ 'tags' => options[:tags] ? tags : nil,
282
+ 'comments' => options[:comments] ? comments : nil,
283
+ }.delete_if { |k,v| v.nil? || v == '' }.to_yaml
284
+
285
+ # Write out the data and content to file
286
+ File.open("_posts/#{name}", "w") do |f|
287
+ f.puts data
288
+ f.puts "---"
289
+ f.puts content
290
+ end
291
+ end
292
+
293
+
294
+ def self.clean_entities( text )
295
+ if text.respond_to?(:force_encoding)
296
+ text.force_encoding("UTF-8")
297
+ end
298
+ text = HTMLEntities.new.encode(text, :named)
299
+ # We don't want to convert these, it would break all
300
+ # HTML tags in the post and comments.
301
+ text.gsub!("&amp;", "&")
302
+ text.gsub!("&lt;", "<")
303
+ text.gsub!("&gt;", ">")
304
+ text.gsub!("&quot;", '"')
305
+ text.gsub!("&apos;", "'")
306
+ text.gsub!("/", "&#47;")
307
+ text
308
+ end
309
+
310
+
311
+ def self.sluggify( title )
312
+ begin
313
+ require 'unidecode'
314
+ title = title.to_ascii
315
+ rescue LoadError
316
+ STDERR.puts "Could not require 'unidecode'. If your post titles have non-ASCII characters, you could get nicer permalinks by installing unidecode."
317
+ end
318
+ title.downcase.gsub(/[^0-9A-Za-z]+/, " ").strip.gsub(" ", "-")
319
+ end
320
+
321
+ end
322
+ end
323
+ end
@@ -0,0 +1,97 @@
1
+ # coding: utf-8
2
+ # This importer takes a wordpress.xml file, which can be exported from your
3
+ # wordpress.com blog (/wp-admin/export.php).
4
+
5
+ module JekyllImport
6
+ module Importers
7
+ class WordpressDotCom < Importer
8
+ def self.require_deps
9
+ JekyllImport.require_with_fallback(%w[
10
+ rubygems
11
+ sequel
12
+ fileutils
13
+ safe_yaml
14
+ hpricot
15
+ time
16
+ ])
17
+ end
18
+
19
+ def self.specify_options(c)
20
+ c.option 'source', '--source FILE', 'WordPress export XML file (default: "wordpress.xml")'
21
+ end
22
+
23
+ def self.process(options)
24
+ source = options.fetch('source', "wordpress.xml")
25
+
26
+ import_count = Hash.new(0)
27
+ doc = Hpricot::XML(File.read(source))
28
+
29
+ (doc/:channel/:item).each do |item|
30
+ title = item.at(:title).inner_text.strip
31
+ permalink_title = item.at('wp:post_name').inner_text
32
+ # Fallback to "prettified" title if post_name is empty (can happen)
33
+ if permalink_title == ""
34
+ permalink_title = sluggify(title)
35
+ end
36
+
37
+ date = Time.parse(item.at('wp:post_date').inner_text)
38
+ status = item.at('wp:status').inner_text
39
+
40
+ if status == "publish"
41
+ published = true
42
+ else
43
+ published = false
44
+ end
45
+
46
+ type = item.at('wp:post_type').inner_text
47
+ categories = item.search('category[@domain="category"]').map{|c| c.inner_text}.reject{|c| c == 'Uncategorized'}.uniq
48
+ tags = item.search('category[@domain="post_tag"]').map{|t| t.inner_text}.uniq
49
+
50
+ metas = Hash.new
51
+ item.search("wp:postmeta").each do |meta|
52
+ key = meta.at('wp:meta_key').inner_text
53
+ value = meta.at('wp:meta_value').inner_text
54
+ metas[key] = value;
55
+ end
56
+
57
+ name = "#{date.strftime('%Y-%m-%d')}-#{permalink_title}.html"
58
+ header = {
59
+ 'layout' => type,
60
+ 'title' => title,
61
+ 'categories' => categories,
62
+ 'tags' => tags,
63
+ 'status' => status,
64
+ 'type' => type,
65
+ 'published' => published,
66
+ 'meta' => metas
67
+ }
68
+
69
+ begin
70
+ FileUtils.mkdir_p "_#{type}s"
71
+ File.open("_#{type}s/#{name}", "w") do |f|
72
+ f.puts header.to_yaml
73
+ f.puts '---'
74
+ f.puts item.at('content:encoded').inner_text
75
+ end
76
+ rescue => e
77
+ puts "Couldn't import post!"
78
+ puts "Title: #{title}"
79
+ puts "Name/Slug: #{name}\n"
80
+ puts "Error: #{e.message}"
81
+ next
82
+ end
83
+
84
+ import_count[type] += 1
85
+ end
86
+
87
+ import_count.each do |key, value|
88
+ puts "Imported #{value} #{key}s"
89
+ end
90
+ end
91
+
92
+ def self.sluggify(title)
93
+ title.gsub(/[^[:alnum:]]+/, '-').downcase
94
+ end
95
+ end
96
+ end
97
+ end