pombola_extract_info_pages 1.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 3f89154a61ff407e6881aa03a37f7f229ee4dac7
+  data.tar.gz: dabf5fdeca23e6ca5de8479080a4cd4c10552524
+SHA512:
+  metadata.gz: 05a6c6c2f7684f8e54aea1ae755c7c636d9e2b12120d6a5dff471fec9a7a1ee1cb896a6195148edd4cee5fb897351a884199596ed56613929cce7dc3a23212f5
+  data.tar.gz: 77820583f3178164b4172551872195c5bd74d0b7e093d9dff9e333cb7543934393e681488d71d28c011dc7c0621e8896a8fae723e1e0c194f2f8a1bdaf7cb788

data/bin/pombola_extract_info_pages

@@ -0,0 +1,62 @@
+#!/usr/bin/env ruby
+require 'sequel'
+require 'fileutils'
+require 'yaml'
+
+abort "Usage: DATABASE_URL=postgres://localhost/mzalendo-zw #$0" unless ENV['DATABASE_URL']
+
+DB = Sequel.connect(ENV['DATABASE_URL'])
+
+LINK_REGEX = /\[(?<text>.+?)\]\((?<url>.+?)(?: (?<title>".*?"))?\)/
+
+def tidy_markdown(markdown)
+  markdown.tr!("\r\n", "\n")
+  markdown.gsub!(/\n+$/, "\n")
+  markdown.gsub!("\n\n**\n", "**\n")
+  markdown.strip!
+  links = markdown.to_enum(:scan, LINK_REGEX).map { Regexp.last_match }
+  return markdown unless links.any?
+  links.each do |link|
+    if link[:title] == '""'
+      # Get rid of empty title
+      markdown.sub!(link.to_s, "[#{link[:text].strip}](#{link[:url].strip})")
+    end
+    if !link[:url].lstrip.start_with?('/') && !link[:url].lstrip.start_with?('http')
+      # Fix relative links to be absolute
+      markdown.sub!(link.to_s, "[#{link[:text].strip}](/info/#{link[:url].strip})")
+    end
+  end
+  markdown
+end
+
+def content_for(item, front_matter = {})
+  <<CONTENT
+#{YAML.dump(front_matter)}---
+
+#{tidy_markdown(item[:markdown_content])}
+CONTENT
+end
+
+infopages_path = 'info'
+FileUtils.mkdir_p(infopages_path)
+
+DB[:info_infopage].where(kind: 'page').each do |page|
+  front_matter = {
+    'title' => page[:title].strip,
+    'slug' => page[:slug],
+    'permalink' => "/info/#{page[:slug]}/"
+  }
+  File.write(File.join(infopages_path, "#{page[:slug]}.md"), content_for(page, front_matter))
+end
+
+posts_path = '_posts'
+FileUtils.mkdir_p(posts_path)
+
+DB[:info_infopage].exclude(kind: 'page').each do |post|
+  front_matter = {
+    'title' => post[:title].strip,
+    'slug' => post[:slug],
+    'layout' => 'post'
+  }
+  File.write(File.join(posts_path, "#{post[:publication_date].to_date.to_s}-#{post[:slug]}.md"), content_for(post, front_matter))
+end

metadata

@@ -0,0 +1,60 @@
+--- !ruby/object:Gem::Specification
+name: pombola_extract_info_pages
+version: !ruby/object:Gem::Version
+  version: 1.0.0
+platform: ruby
+authors:
+- Chris Mytton
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2016-02-22 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: sequel
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4.31'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4.31'
+description: 
+email: chrism@mysociety.org
+executables:
+- pombola_extract_info_pages
+extensions: []
+extra_rdoc_files: []
+files:
+- bin/pombola_extract_info_pages
+homepage: https://github.com/mysociety/pombola_extract_info_pages
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.5.1
+signing_key: 
+specification_version: 4
+summary: Extract infopages from a Pombola database dump
+test_files: []
+has_rdoc: