openstax_content 0.0.2 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 578cf5b445c79d9e7dd1a904da90cb3daf527d2d8b7de128d07640e15d8bd066
-  data.tar.gz: b2bfe3524398a047b6722a047aa245de8ed52d02e4c9c37ca28f0b36840ba081
+  metadata.gz: 4aebb8f3f720b66d54a35964a2c7471a4c1791b1eddf3a79278fb42974c1b03b
+  data.tar.gz: 743c42fe074b7e8aabc47540785d53ff2dec03c0f3b40eb12f79f0624d1e0f9c
 SHA512:
-  metadata.gz: c2f7708cce0fb71727d985dcef91f6b0844f1b3ba2b134a55cc6f4eb3bddf0132c633cce04ed8221d16f8aac785a08f1ef16fe17e6f184c7f481c479054e496b
-  data.tar.gz: 07bd028f00e935ef240585da56b2fd88e82959da61213787f03421e1f07c0afecb8f3257b9b269ff1affea5483a227f70d299e1782a528e7ebb1c4d96dd2dd6b
+  metadata.gz: af95d3a223033476027839a1c4d49e01a9e8d72c8be9185059d83dd13bf8544e79d291984eec3ac2473ff63850ddb45e1d5bca4a1bfc70d6e86fa99429db2c7f
+  data.tar.gz: 0eae65c706c57ef7a9e27125124972e62c8edaa77d22a9d16785ac2efcb6723693b1f18bc1c9ffdb82d699c6134bfa3453b1b491e6d7ccffc73df399e470aa11

data/lib/openstax/content/archive.rb

@@ -28,10 +28,6 @@ class OpenStax::Content::Archive
     end
 
     if uri.absolute?
-      OpenStax::Content.logger.warn do
-        "#{self.class.name} received an unexpected absolute URL in url_for: \"#{object}\""
-      end
-
       # Force absolute URLs to be https
       uri.scheme = 'https'
       return uri.to_s
@@ -48,6 +44,10 @@ class OpenStax::Content::Archive
     if uri.path.start_with?('../')
       uri.path = uri.path.sub('..', '')
       "#{base_url}#{uri.to_s}"
+    elsif uri.path.start_with?(OpenStax::Content.archive_path) ||
+          uri.path.start_with?("/#{OpenStax::Content.archive_path}")
+      uri.path.start_with?('/') ? "https://#{OpenStax::Content.domain}#{uri.to_s}" :
+                                  "https://#{OpenStax::Content.domain}/#{uri.to_s}"
     else
       uri.path = "#{uri.path.chomp('.json').chomp('.xhtml')}.json"
 
@@ -101,4 +101,29 @@ class OpenStax::Content::Archive
       slug
     end
   end
+
+  def webview_uri_for(page)
+    uri = if page.is_a?(Addressable::URI)
+      page
+    else
+      begin
+        Addressable::URI.parse page
+      rescue Addressable::URI::InvalidURIError
+        begin
+          Addressable::URI.parse "/#{page}"
+        rescue Addressable::URI::InvalidURIError
+          OpenStax::Content.logger.warn { "Invalid page url: \"#{page}\"" }
+
+          return page
+        end
+      end
+    end
+    object = uri.path.split('/').last
+    book_id, page_id = object.split(':', 2)
+    page_uuid = page_id.split('@', 2).first
+    book_slug = slug book_id
+    page_slug = slug object
+    uri.path = "books/#{book_slug}/pages/#{page_slug}"
+    Addressable::URI.join "https://#{OpenStax::Content.domain}", uri
+  end
 end

data/lib/openstax/content/fragment/html.rb

@@ -12,17 +12,28 @@ class OpenStax::Content::Fragment::Html < OpenStax::Content::Fragment
     @to_html = @node.to_html
   end
 
-  def as_json(*args)
-    # Don't attempt to serialize @node (it would fail)
-    super.except('node')
+  # Serialization methods use #instance_variables to iterate through and dump all instance variables
+  # Nokogiri classes are not serializable, so we do not want to dump the @node variable
+  # Instead, we recreate it by parsing the HTML again if needed
+  def instance_variables
+    super - [ :@node ]
   end
 
-  def html?
-    !to_html.empty?
+  def blank?
+    return @blank unless @blank.nil?
+
+    @blank = if to_html.nil? || to_html.strip.empty?
+      true
+    else
+      node_without_title = node.dup
+      node_without_title.css('[data-type="document-title"]').remove
+      text = node_without_title.text
+      text.nil? || text.strip.empty?
+    end
   end
 
-  def blank?
-    !html?
+  def html?
+    !blank?
   end
 
   def node

data/lib/openstax/content/fragment_splitter.rb

@@ -40,9 +40,11 @@ class OpenStax::Content::FragmentSplitter
     # Flatten, remove empty nodes and transform remaining nodes into reading fragments
     result.map do |obj|
       next obj unless obj.is_a?(Nokogiri::XML::Node)
-      next if obj.content.nil? || obj.content.strip.empty?
 
-      OpenStax::Content::Fragment::Reading.new node: obj, reference_view_url: reference_view_url
+      fragment = OpenStax::Content::Fragment::Reading.new(
+        node: obj, reference_view_url: reference_view_url
+      )
+      fragment unless fragment.blank?
     end.compact.tap do |result|
       @media_nodes.each do |node|
         # Media processing instructions

data/lib/openstax/content/s3.rb

@@ -2,7 +2,7 @@ require 'aws-sdk-s3'
 
 class OpenStax::Content::S3
   def initialize
-    @ls = {}
+    @ls = Hash.new { |hash, key| hash[key] = Hash.new { |hash, key| hash[key] = {} } }
   end
 
   def bucket_name
@@ -21,24 +21,65 @@ class OpenStax::Content::S3
     )
   end
 
-  def ls(archive_version = nil)
-    return @ls[archive_version] unless @ls[archive_version].nil?
-    return unless bucket_configured?
-
+  # Returns the archive path for the given archive_version, book_id, page_uuid and extension
+  # If not all arguments are given, returns the prefix instead
+  def path_for(archive_version = nil, book_id = nil, page_uuid = nil, extension = nil)
     archive_path = OpenStax::Content.archive_path.chomp('/')
 
     if archive_version.nil?
-      prefix = "#{archive_path}/"
-      delimiter = '/'
+      "#{archive_path}/"
+    elsif book_id.nil?
+      "#{archive_path}/#{archive_version}/contents/"
+    elsif page_uuid.nil?
+      "#{archive_path}/#{archive_version}/contents/#{book_id}:"
+    elsif extension.nil?
+      "#{archive_path}/#{archive_version}/contents/#{book_id}:#{page_uuid}."
+    else
+      "#{archive_path}/#{archive_version}/contents/#{book_id}:#{page_uuid}.#{extension}"
+    end
+  end
+
+  # Without an archive version, returns a list of archive versions
+  # With an archive version, returns a list of book ids (uuid@version)
+  # With an archive version and a book, returns a list of page uuids
+  # With an archive version, book id and page uuid, returns the available extensions, if any
+  def ls(archive_version = nil, book_id = nil, page_uuid = nil)
+    return @ls[archive_version][book_id][page_uuid] \
+      unless @ls[archive_version][book_id][page_uuid].nil?
+    return unless bucket_configured?
+
+    prefix = path_for archive_version, book_id, page_uuid
+
+    delimiter = if archive_version.nil?
+      '/'
+    elsif book_id.nil?
+      ':'
+    elsif page_uuid.nil?
+      '.'
+    else
+      nil
+    end
+
+    responses = client.list_objects_v2 bucket: bucket_name, prefix: prefix, delimiter: delimiter
+
+    @ls[archive_version][book_id][page_uuid] = if page_uuid.nil?
+      responses.flat_map(&:common_prefixes).map do |common_prefix|
+        common_prefix.prefix.sub(prefix, '').chomp(delimiter)
+      end
     else
-      prefix = "#{archive_path}/#{archive_version}/contents/"
-      delimiter = ':'
+      responses.flat_map(&:contents).map { |content| content.key.sub(prefix, '') }
     end
+  end
 
-    @ls[archive_version] = client.list_objects_v2(
-      bucket: bucket_name, prefix: prefix, delimiter: delimiter
-    ).flat_map(&:common_prefixes).map do |common_prefix|
-      common_prefix.prefix.sub(prefix, '').chomp(delimiter)
+  # Checks all books for the given page uuid and returns the path to the first one found
+  def find_page(page_uuid, archive_version: nil, extension: 'json')
+    archive_version ||= ls.last
+
+    ls(archive_version).each do |book_id|
+      return path_for(archive_version, book_id, page_uuid, extension) \
+        if ls(archive_version, book_id, page_uuid).include?(extension)
     end
+
+    nil
   end
 end

data/lib/openstax/content/version.rb

@@ -1,5 +1,5 @@
 module OpenStax
   module Content
-    VERSION = '0.0.2'
+    VERSION = '0.3.0'
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: openstax_content
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.3.0
 platform: ruby
 authors:
 - Dante Soares
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-06-11 00:00:00.000000000 Z
+date: 2021-10-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: aws-sdk-s3
@@ -168,7 +168,7 @@ homepage: https://github.com/openstax/content-ruby
 licenses:
 - AGPL-3.0
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -184,7 +184,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubygems_version: 3.2.19
-signing_key: 
+signing_key:
 specification_version: 4
 summary: Ruby bindings to read and parse the OpenStax ABL and the content archive
 test_files: []