ooxl 0.0.1.5.3 → 0.0.1.5.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 72289ba7eb6dba7ef0e3feec1b329f59d5ed9547
-  data.tar.gz: 568bfdd6c97d43698e665eac15f0e453fac151e3
+SHA256:
+  metadata.gz: feba34a102bb13498ce6cfbbdad7ae2d9f02e4d5f872a92a1bd80a5f74c59d83
+  data.tar.gz: 94ab7441bbbe828a0a4fe0f3d98b97f62d2ae25f6aa052ce657f1567b868abca
 SHA512:
-  metadata.gz: 4a8c5d321345da254a3c397dccc77d090435408f895c7b16b2877d6d24f59721c9cb1caffd4e39337e8ebec02495f15e3c0133f0e0faa6d58cb5f602ee419951
-  data.tar.gz: e4e7aca211e24fb842b959b431850671191aed6292f7f5ef7cd8c31267564dde3ab467c9aca19351f2f3012c1d24e7b9cee6a8a231510b4073b1b7b077ef480e
+  metadata.gz: 8653a2a872e73055569eff3f7114a24ca76769f0251dd71e52bfb2a15e5c81f51fd6f4fd9ad8ce9d046099c2f07a44f16ab61e7e1d02380f98b6474e132571d4
+  data.tar.gz: 8e12f9a5b9f101a01ab33b991c6923f32daa926e16c3ffd2a9ce984b2a94d7e9a9e3a3cf8714b709051004af336fbd7d132c92e5f7de14bddc9bb5f9f0dc50fc

data/bin/console

@@ -1,7 +1,7 @@
 #!/usr/bin/env ruby
 
 require "bundler/setup"
-require "ooxml_excel"
+require "./lib/ooxl"
 
 # You can add fixtures and/or initialization code here to make experimenting
 # with your gem easier. You can also use a different console, if you like.
@@ -10,5 +10,5 @@ require "ooxml_excel"
 # require "pry"
 # Pry.start
 
-require "irb"
-IRB.start
+require "pry"
+Pry.start

data/lib/ooxl/ooxl.rb

@@ -3,20 +3,33 @@ class OOXL
   include ListHelper
   attr_reader :filename
   
-  def initialize(spreadsheet_filepath, options={})
+  def initialize(filepath = nil, contents: nil, **options)
     @workbook = nil
     @sheets = {}
     @styles = []
     @comments = {}
-    @relationships = {}
+    @workbook_relationships = nil
+    @sheet_relationships = {}
     @options = options
     @tables = []
-    @filename = File.basename(spreadsheet_filepath)
-    parse_spreadsheet_contents(spreadsheet_filepath)
+
+    @filename = filepath && File.basename(filepath)
+    if contents.present?
+      parse_spreadsheet_contents(contents)
+    elsif filepath.present?
+      parse_spreadsheet_file(filepath)
+    else
+      raise 'no file path or contents were provided'
+    end
   end
 
   def self.open(spreadsheet_filepath, options={})
-    new(spreadsheet_filepath, options)
+    new(spreadsheet_filepath, **options)
+  end
+
+  def self.parse(spreadsheet_contents, options={})
+    spreadsheet_contents.force_encoding('ASCII-8BIT') if spreadsheet_contents.respond_to?(:force_encoding)
+    new(nil, contents: spreadsheet_contents, **options)
   end
 
   def sheets(skip_hidden: false)
@@ -36,7 +49,7 @@ class OOXL
     sheet_meta = @workbook.sheets.find { |sheet| sheet[:name] == sheet_name }
     raise "No #{sheet_name} in workbook." if sheet_meta.nil?
 
-    sheet_index = sheet_meta[:sheet_id]
+    sheet_index = @workbook_relationships[sheet_meta[:relationship_id]].scan(/\d+/).first
     sheet = @sheets.fetch(sheet_index)
 
     # shared variables
@@ -75,37 +88,46 @@ class OOXL
   end
 
   def fetch_comments(sheet_index)
-    relationship = @relationships[sheet_index]
+    relationship = @sheet_relationships[sheet_index]
     @comments[relationship.comment_id] if relationship.present?
   end
 
-  def parse_spreadsheet_contents(spreadsheet)
+  def parse_spreadsheet_file(file_path)
+    Zip::File.open(file_path) { |zip| parse_zip(zip) }
+  end
+
+  def parse_spreadsheet_contents(file_contents)
+    # open_buffer works for strings and IO streams
+    Zip::File.open_buffer(file_contents) { |zip| parse_zip(zip) }
+  end
+
+  def parse_zip(spreadsheet_zip)
     shared_strings = []
-    Zip::File.open(spreadsheet) do |spreadsheet_zip|
-      spreadsheet_zip.each do |entry|
-        case entry.name
-        when /xl\/worksheets\/sheet(\d+)?\.xml/
-          sheet_id = entry.name.scan(/xl\/worksheets\/sheet(\d+)?\.xml/).flatten.first
-          @sheets[sheet_id] = OOXL::Sheet.new(entry.get_input_stream.read, shared_strings, @options)
-        when /xl\/styles\.xml/
-          @styles = OOXL::Styles.load_from_stream(entry.get_input_stream.read)
-        when /xl\/comments(\d+)?\.xml/
-          comment_id = entry.name.scan(/xl\/comments(\d+)\.xml/).flatten.first
-          @comments[comment_id] = OOXL::Comments.load_from_stream(entry.get_input_stream.read)
-        when "xl/sharedStrings.xml"
-          Nokogiri.XML(entry.get_input_stream.read).remove_namespaces!.xpath('sst/si').each do |shared_string_node|
-            shared_strings << shared_string_node.xpath('r/t|t').map { |value_node| value_node.text}.join('')
-          end
-        when /xl\/tables\/.*?/i
-          @tables << OOXL::Table.new(entry.get_input_stream.read)
-        when "xl/workbook.xml"
-          @workbook = OOXL::Workbook.load_from_stream(entry.get_input_stream.read)
-        when /xl\/worksheets\/_rels\/sheet\d+\.xml\.rels/
-          sheet_id = entry.name.scan(/sheet(\d+)/).flatten.first
-          @relationships[sheet_id] = Relationships.new(entry.get_input_stream.read)
-        else
-          # unsupported for now..
+    spreadsheet_zip.each do |entry|
+      case entry.name
+      when /xl\/worksheets\/sheet(\d+)?\.xml/
+        sheet_id = entry.name.scan(/xl\/worksheets\/sheet(\d+)?\.xml/).flatten.first
+        @sheets[sheet_id] = OOXL::Sheet.new(entry.get_input_stream.read, shared_strings, @options)
+      when /xl\/styles\.xml/
+        @styles = OOXL::Styles.load_from_stream(entry.get_input_stream.read)
+      when /xl\/comments(\d+)?\.xml/
+        comment_id = entry.name.scan(/xl\/comments(\d+)\.xml/).flatten.first
+        @comments[comment_id] = OOXL::Comments.load_from_stream(entry.get_input_stream.read)
+      when "xl/sharedStrings.xml"
+        Nokogiri.XML(entry.get_input_stream.read).remove_namespaces!.xpath('sst/si').each do |shared_string_node|
+          shared_strings << shared_string_node.xpath('r/t|t').map { |value_node| value_node.text}.join('')
         end
+      when /xl\/tables\/.*?/i
+        @tables << OOXL::Table.new(entry.get_input_stream.read)
+      when "xl/workbook.xml"
+        @workbook = OOXL::Workbook.load_from_stream(entry.get_input_stream.read)
+      when /xl\/worksheets\/_rels\/sheet\d+\.xml\.rels/
+        sheet_id = entry.name.scan(/sheet(\d+)/).flatten.first
+        @sheet_relationships[sheet_id] = Relationships.new(entry.get_input_stream.read)
+      when /xl\/_rels\/workbook\.xml\.rels/
+        @workbook_relationships = Relationships.new(entry.get_input_stream.read)
+      else
+        # unsupported for now..
       end
     end
   end

data/lib/ooxl/version.rb

@@ -1,3 +1,3 @@
 class OOXL
-  VERSION = "0.0.1.5.3"
+  VERSION = "0.0.1.5.4"
 end

data/lib/ooxl/xl_objects/relationships.rb

@@ -1,29 +1,41 @@
 class OOXL
   class Relationships
     SUPPORTED_TYPES = ['http://schemas.openxmlformats.org/officeDocument/2006/relationships/comments']
+
     def initialize(relationships_node)
-      @types = {}
+      @relationships = []
       parse_relationships(relationships_node)
     end
 
     def comment_id
-      @types['comments']
+      comment_target = by_type('comments').first
+      comment_target && extract_file_reference(comment_target)
+    end
+
+    def [](id)
+      @relationships.find { |rel| rel.id == id }&.target
+    end
+
+    def by_type(type)
+      @relationships.select { |rel| rel.type == type }.map(&:target)
     end
 
     private
+
     def parse_relationships(relationships_node)
       relationships_node = Nokogiri.XML(relationships_node).remove_namespaces!
       relationships_node.xpath('//Relationship').each do |relationship_node|
         relationship_type = relationship_node.attributes["Type"].value
         target = relationship_node.attributes["Target"].value
-        if supported_type?(relationship_type)
-          @types[extract_type(relationship_type)] = extract_file_reference(target)
-        end
+        id = extract_number(relationship_node.attributes["Id"].value)
+        type = extract_type(relationship_type)
+        target = relationship_node.attributes["Target"].value
+        @relationships << Relationship.new(id, type, target)
       end
     end
 
-    def supported_type?(type)
-      SUPPORTED_TYPES.include?(type)
+    def extract_number(str)
+      str.scan(/(\d+)/).flatten.first
     end
 
     def extract_type(type)
@@ -34,6 +46,7 @@ class OOXL
       file.scan(/(\d+)\.[\w]/).flatten.first
     end
 
+    Relationship = Struct.new(:id, :type, :target)
   end
 end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: ooxl
 version: !ruby/object:Gem::Version
-  version: 0.0.1.5.3
+  version: 0.0.1.5.4
 platform: ruby
 authors:
 - James Mones
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2020-10-01 00:00:00.000000000 Z
+date: 2020-10-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activesupport
@@ -168,8 +168,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project:
-rubygems_version: 2.6.12
+rubygems_version: 3.0.3
 signing_key:
 specification_version: 4
 summary: OOXL Excel - Parse Excel Spreadsheets (xlsx, xlsm).