Compare commits

...

2 Commits

Author SHA1 Message Date
chris 09bb318d6a Changes for NTU Student Affairs 2013-09-13 15:10:33 +08:00
chris d766eea9f4 Changes for NTU common
Conflicts:
	lib/tasks/migrate.rake

Conflicts:
	lib/tasks/migrate.rake

Conflicts:
	config/resque_schedule.yml
	lib/tasks/migrate.rake
2013-09-13 15:10:10 +08:00
18 changed files with 445 additions and 22 deletions

2
.gitignore vendored
View File

@ -4,6 +4,8 @@
.rvmrc
Gemfile.lock
Procfile
log/*
db/*.sqlite3
log/*.log

View File

@ -0,0 +1,7 @@
class GetAnnouncementFromRss
@queue = :high
def self.perform()
%x(ruby "#{Rails.root}/lib/rss_ntu_job.rb")
end
end

View File

@ -17,4 +17,4 @@
<%= render :partial=> "widget_ext_options" %>
</div>
</div>
<% end %>
<% end %>

View File

@ -1,6 +1,17 @@
<!DOCTYPE HTML>
<html class="<%= I18n.locale.to_s %>">
<head>
<script type="text/javascript">
var _gaq = _gaq || [];
_gaq.push(['_setAccount', 'UA-39393439-1']);
_gaq.push(['_trackPageview']);
(function() {
var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true;
ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s);
})();
</script>
<meta charset="utf-8">
<%= page_title(@item).html_safe %>
<link rel="shortcut icon" href="<%= asset_path "ncculogo.ico" %>">

View File

@ -3,9 +3,6 @@
<% end %>
<ul>
<li>總機電話:<a href="tel:+886229393091">02-29393091</a></li>
<li>傳真02-29379611</li>
<li>緊急重大事件通聯窗口:校內分機 66119、66110</li>
<li>總值日室:<a href="tel:+88229387132">02-29387132</a></li>
<li>駐警衛室:<a href="tel:+88229387129">02-29387129</a></li>
<li>學務處電話:<a href="tel:+886-2-3366-2995~2997">+886-2-3366-2995~2997</a></li>
<li>學務處傳真:+886-2-2391-9095</li>
</ul>

View File

@ -5,6 +5,6 @@
<div id='map_canvas'></div>
<script type='text/javascript'>
var $map_center = "24.987449, 121.576117"
var $map_center = "25.015205, 121.535491"
var $map_zoom = 17
</script>

View File

@ -4,10 +4,10 @@ en:
bulletin: Bulletin
contact: Contact
copyright: Copyright
copyright_text: Thisi University © All RIGHTS RESERVED.
copyright_text: Copyright© 2008 National Taiwan University ALL RIGHTS RESERVED
copyright_orbit: Powered by RulingDigital
home: Home
language: Language
location: Location
location_description: '<h3>This University</h3>No.101,Sec. 2, Jiafeng S Road, Zhubei City, Hsinchu County 302, Taiwan'
location_description: '<h3>National Taiwan University</h3>No. 1, Sec. 4, Roosevelt Road, Taipei, 10617 Taiwan (R.O.C)'
page: Page

View File

@ -4,10 +4,10 @@ zh_tw:
bulletin: 公告
contact: 聯絡資訊
copyright: 著作權宣告
copyright_text: 本網站著作權屬於本大學。
copyright_text: 本網站著作權屬於國立臺灣大學 學生事務處
copyright_orbit: 銳綸數位建置
home: 首頁
language: 語言
location: 地理位置
location_description: '<h3>本大學</h3>302新竹縣竹北市嘉豐南路二段101號'
location_description: '<h3>臺灣大學總務處 版權所有</h3>10617 臺北市大安區羅斯福路四段一號'
page: 頁面

View File

@ -0,0 +1,4 @@
en:
ntu:
rss_origin: Back to NTU Announcements

View File

@ -0,0 +1,4 @@
zh_tw:
ntu:
rss_origin: 回臺大校園公佈欄

View File

@ -11,7 +11,7 @@ backup_server:
description: BackupServer and remove old backups
update_tag_cloud:
cron: 0 0 [0,12] * * *
cron: 0 30 2 * * *
class: UpdateTagCloud
args:
description: UpdateTagCloud
@ -27,3 +27,9 @@ email_cron:
class: EmailCron
args:
description: EmailCron
get_announcement_from_rss:
cron: 0 0 [2,12] * * *
class: GetAnnouncementFromRss
args:
description: Loop through the announcement RSS until 24h ago

99
lib/rss_ntu_job.rb Normal file
View File

@ -0,0 +1,99 @@
# encoding: utf-8
# encoding: utf-8
require 'rss'
require 'mongo'
AUTHORS = %w[ 學生事務處-學生住宿服務組
-
-
-
-
-
-
-
-
-]
DB_BASE_NAME = "site"
all = []
continue = true
i = 1
yesterday = Time.now - 86400
while continue do
open("http://ann.cc.ntu.edu.tw/asp/rss.asp?page=#{i}") do |rss|
feed = RSS::Parser.parse(rss.read.encode('utf-8', 'big5', invalid: :replace, undef: :replace, replace: '').gsub('<pubDate>Wes,', '<pubDate>Wed,').gsub(/(encoding=\"big5\")/, 'encoding="utf-8"'))
feed.items.each do |item|
if item.pubDate > yesterday
if AUTHORS.include?(item.author)
author = item.author.strip
category = item.category.to_s.gsub(/\<(\/)*category\>/, '')
all << {title: item.title.strip, author: author, link: item.link.strip, date: item.pubDate, category: category, description: item.description.gsub("\r\n", '<br/>').strip}
end
else
continue = false
break
end
end
end
i += 1
end
# Get corresponding category_id or create a new one
def get_category_id(category, categories, coll_cat)
if categories.keys.include? "rss_#{category}"
[categories["rss_#{category}"], categories]
else
cat = {
_type: "BulletinCategory",
key: "rss_#{category}",
disable: false,
title: {:zh_tw => category},
created_at: Time.now,
updated_at: Time.now
}
categories["rss_#{category}"] = result = coll_cat.save(cat)
[result, categories]
end
end
# Get categories and id based on a given site number
def get_mongo_and_categories(site_number="0")
db = Mongo::Connection.new("localhost", 27017).db("#{DB_BASE_NAME}_#{site_number}")
coll_bulletin = db["bulletins"]
coll_cat = db["bulletin_categories"]
categories = coll_cat.find().to_a.inject({}) do |categories, category|
categories[category['key']] = category['_id']
categories
end
[categories, coll_bulletin, coll_cat]
end
# Get categories
categories, coll_bulletin, coll_cat = get_mongo_and_categories
all.each do |bul| # Loop through all the items
category_id, categories = get_category_id(bul[:category], categories, coll_cat)
unless coll_bulletin.find_one(rss_link: bul[:link])
bulletin = { _type: "Bulletin",
postdate: bul[:date],
created_at: bul[:date],
updated_at: bul[:date],
is_checked: true,
is_pending: false,
is_rejected: false,
bulletin_category_id: category_id,
title: {:zh_tw => bul[:title]},
text: {:zh_tw => bul[:description]},
available_for_zh_tw: true,
rss_link: bul[:link] }
coll_bulletin.save(bulletin)
end
end

91
lib/rss_ntu_migrate.rb Normal file
View File

@ -0,0 +1,91 @@
# encoding: utf-8
require 'rss'
require 'mongo'
AUTHORS = %w[ 學生事務處-學生住宿服務組
-
-
-
-
-
-
-
-
-]
DB_BASE_NAME = "site"
all = []
continue = true
i = 1
while continue do
open("http://ann.cc.ntu.edu.tw/asp/rss.asp?page=#{i}") do |rss|
feed = RSS::Parser.parse(rss.read.encode('utf-8', 'big5', invalid: :replace, undef: :replace, replace: '').gsub('<pubDate>Wes,', '<pubDate>Wed,').gsub(/(encoding=\"big5\")/, 'encoding="utf-8"'))
feed.items.size
feed.items.each do |item|
if AUTHORS.include?(item.author)
author = item.author.strip
category = item.category.to_s.gsub(/\<(\/)*category\>/, '')
all << {title: item.title.strip, author: author, link: item.link.strip, date: item.pubDate, category: category, description: item.description.gsub("\r\n", '<br/>').strip}
end
end
continue = false if feed.items.size < 100
end
i += 1
end
# Get corresponding category_id or create a new one
def get_category_id(category, categories, coll_cat)
if categories.keys.include? "rss_#{category}"
[categories["rss_#{category}"], categories]
else
cat = {
_type: "BulletinCategory",
key: "rss_#{category}",
disable: false,
title: {:zh_tw => category},
created_at: Time.now,
updated_at: Time.now
}
categories["rss_#{category}"] = result = coll_cat.save(cat)
[result, categories]
end
end
# Get categories and id based on a given site number
def get_mongo_and_categories(site_number="0")
db = Mongo::Connection.new("localhost", 27017).db("#{DB_BASE_NAME}_#{site_number}")
coll_bulletin = db["bulletins"]
coll_cat = db["bulletin_categories"]
categories = coll_cat.find().to_a.inject({}) do |categories, category|
categories[category['key']] = category['_id']
categories
end
[categories, coll_bulletin, coll_cat]
end
# Get categories
categories, coll_bulletin, coll_cat = get_mongo_and_categories
all.each do |bul| # Loop through all the items
category_id, categories = get_category_id(bul[:category], categories, coll_cat)
unless coll_bulletin.find_one(rss_link: bul[:link])
bulletin = { _type: "Bulletin",
postdate: bul[:date],
created_at: bul[:date],
updated_at: bul[:date],
is_checked: true,
is_pending: false,
is_rejected: false,
bulletin_category_id: category_id,
title: {:zh_tw => bul[:title]},
text: {:zh_tw => bul[:description]},
available_for_zh_tw: true,
rss_link: bul[:link] }
coll_bulletin.save(bulletin)
end
end

View File

@ -310,6 +310,34 @@ namespace :migrate do
Rake::Task["web_link_url:web_link_url_i18n"].execute
end
task :save_users => :environment do
User.where(:email.not => /guest/).each{|s|s.save}
end
task :fix_bulletin_rss_available_lang => :environment do
Bulletin.all.each do |bull|
if bull.create_user_id.nil?
bull.update_attribute(:available_for_zh_tw, true)
end
end
end
task :fix_imported_rss => :environment do
categories = BulletinCategory.where(key: /rss_/).entries
unless categories.blank?
categories.each do |category|
bulletins = category.bulletins
unless bulletins.blank?
bulletins.each do |bulletin|
bulletin.update_attribute(:is_top, false) unless bulletin.is_top?
bulletin.update_attribute(:is_hot, false) unless bulletin.is_hot?
bulletin.update_attribute(:is_hidden, false) unless bulletin.is_hidden?
end
end
end
end
end
task :fix_tagged_ids => :environment do
Tag.all.each do |tag|
tag.taggings.each do |tagging|

View File

@ -0,0 +1,168 @@
# encoding: utf-8
namespace :mongo_files do
MODELS = { 'ad_image' => 'file',
'archive_file_multiple' => 'file',
'asset' => 'data',
'bulletin' => 'image',
'bulletin_file' => 'file',
'design' => 'zip_file',
'design_file' => 'file',
'gallery_image' => 'file',
'image' => 'file',
'lab_file' => 'file',
'location_info' => 'file',
'preview_file' => 'file',
'project_file' => 'file',
'research_file' => 'file',
'site' => 'default_image',
'stylesheet' => 'file_orig',
'user' => 'avatar',
'writing_book_file' => 'file',
'writing_conference_file' => 'file',
'writing_journal_file' => 'file',
'writing_patent_file' => 'file' }
IMAGE_UPLOADER_MODELS = %w[ad_image bulletin image site]
task :clean => :environment do
@files = Mongoid.database['fs.files']
@chunks = Mongoid.database['fs.chunks']
clean_duplicates
clean_unused
remove_objects
end
# Remove unused files from db
def clean_unused
db_array = @files.find().inject([]) do |db_files, file|
db_files << file['filename']
db_files
end
p "# of files in db: #{db_array.size}"
name_array = MODELS.inject([]) do |model_files, (model, type)|
model.classify.constantize.all.each do |item|
url = item.send(type).url
thumb_url = item.send(type).thumb.url rescue nil
if url && !url.eql?('sign-in-logo.png')
url = url.gsub('/gridfs/', '')
model_files << url
end
if thumb_url && !thumb_url.eql?('sign-in-logo.png')
thumb_url = thumb_url.gsub('/gridfs/', '')
model_files << thumb_url
end
end
model_files
end
p "# of files from uploaders: #{name_array.size}"
useless_files = db_array - name_array
p "# of unmatched files: #{useless_files.size}"
useless_files.each do |file|
id = @files.find_one('filename' => file)['_id']
@files.remove('_id' => id)
@chunks.remove('files_id' => id)
end
# p files.remove('filename' => { "$in" => useless_files})
end
# Remove duplicate files from db
def clean_duplicates
p "# of files in db: #{@files.count}"
file_hash = @files.find().sort({uploadDate: -1}).inject({}) do |db_files, file|
name = file['filename']
if db_files[name]
db_files[name] += [file['_id']]
else
db_files[name] = [file['_id']]
end
db_files
end
file_array = file_hash.inject([]) do |files, (key, value)|
files += value.drop(1) if value.size > 1
files
end
p "# of duplicate ids to delete: #{file_array.size}"
file_array.each do |id|
@files.remove('_id' => id)
@chunks.remove('files_id' => id)
end
end
task :file_size => :environment do
files = Mongoid.database['fs.files']
size_array = files.find().inject([]) do |size, file|
# size << [file['length'], file['filename']]
size << [file['filename'], file['length']]
size
end
size_array.sort.each do |pair|
p "#{pair[0]} - #{pair[1]}"
end
p size_array.size
end
def remove_objects
# Destroy writing_journals and writing_journal_files
Mongoid.database['writing_journals'].remove()
Mongoid.database['writing_journal_files'].remove()
db_array = @files.find().inject([]) do |db_files, file|
db_files << file['filename'] if file['filename'] =~ /writing_journal_file|news_bulletin_file|image\/image/
db_files
end
p db_array.size
db_array.each do |file|
id = @files.find_one('filename' => file)['_id']
@files.remove('_id' => id)
@chunks.remove('files_id' => id)
end
end
def remove_unlinked
# name_array = AdBanner.all.inject([]) do |files, banner|
# banner.ad_images.inject(files) do |image_files, image|
# url = image.file.url
# thumb_url = image.file.thumb.url rescue nil
# if url && !url.eql?('sign-in-logo.png')
# url = url.gsub('/gridfs/', '')
# image_files << url
# end
# if thumb_url && !thumb_url.eql?('sign-in-logo.png')
# thumb_url = thumb_url.gsub('/gridfs/', '')
# image_files << thumb_url
# end
# image_files
# end
# files
# end
name_array = Design.all.inject([]) do |files, design|
files += design.images.inject(files) do |image_files, image|
p image_files += get_url_and_thumb(image.file)
image_files
end
files
end
p name_array.size
end
def get_url_and_thumb(file)
url = file.url
thumb_url = file.thumb.url rescue nil
files = [url, thumb_url].inject([]) do |urls, current|
urls << current.gsub('/gridfs/', '') if current && !current.eql?('sign-in-logo.png')
urls
end
files
end
task :delete_rss_ann => :environment do
Bulletin.where(create_user_id: nil).destroy
end
end

View File

@ -9,17 +9,17 @@ namespace :web_link_url do
@weblinks.each do |wl|
if wl.url.nil?
if wl.url_translations.is_a?(String)
@wlurl = wl.url_translations
wl.url_translations = {}
wl.url_translations["zh_tw"] = @wlurl
wl.url_translations["en"] = @wlurl
@wlurl = wl.url_translations
wl.url_translations = {}
wl.url_translations["zh_tw"] = @wlurl
wl.url_translations["en"] = @wlurl
wl.save
wl.save
else
puts 'no data'

View File

@ -40,6 +40,7 @@ class Bulletin
field :not_checked_reason
field :public, :type => Boolean, :default => true
field :rss_link
scope :can_display, where(is_checked: true, is_rejected: false, is_pending: false)
scope :available_for_lang, ->(locale){ where("available_for_#{locale}".to_sym => true) }

View File

@ -36,6 +36,11 @@
</div>
</div>
<% end %>
<% unless @bulletin.rss_link.blank? %>
<div>
<%= link_to t('ntu.rss_origin'), @bulletin.rss_link %>
</div>
<% end %>
</div>
<%= share_links(@bulletin, 'announcement') %>