xsv 0.3.11 → 0.3.12

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 601dc989cf2bdf62aa50002b0293a387df53bf20022fd16fb2f8885c344e9013
-  data.tar.gz: 6afb26f05ad129280b823540cb3d0e957ab88ea01b877d1758d8c2b376d2d69a
+  metadata.gz: 36eeca38d2791f71dafba9b1ae6308e63b3554efd98e2949448c4715863b7616
+  data.tar.gz: cf90d5ff1def79ee8b17877523a5e8233b7c5253801c98eb0e725724a6e3f48d
 SHA512:
-  metadata.gz: 1e946848856a07d1b95fa22f9f97b22fa4bc9fcb7d6b5985b9ff7a9e2ec4e8dc42f74964ec6c2872f22c80773c7f5ca2188e857af32f1f51345d7feebf77047c
-  data.tar.gz: f1ff12b091a4fcd8172064ea6f215011bc43e95bd5dcec586d189b72eb0ef0662eaf48b85ac7794ba82a27d824d61459025ed676a4e7b729be7e71f957cc48bd
+  metadata.gz: cc203883d561d86a51eb35c11f4c4547929605387a43d38c16eb48f975a2da1ea332c7cbb4aab21e4760424ceb015de2e4d50aeeddd9bf595ccd3bf1f363ac63
+  data.tar.gz: b91d7d210c6894c17bfbb2b40dd0c243f2c5228f35c780f8e5d8afba9367303d2df1897ae734bec636f8eab615cda7188d63e63b270b3f543fafc39d91d1aa7e

data/CHANGELOG.md

@@ -1,5 +1,9 @@
 # Xsv Changelog
 
+## 0.3.12 - 2020-04-15
+
+- Accessing worksheets by name (texpert)
+
 ## 0.3.11 - 2020-04-03
 
 - Backward compatibility with Ruby 2.5 (texpert)

data/README.md

@@ -83,6 +83,22 @@ columns with the same name!
 `Xsv::Sheet` implements `Enumerable` so you can call methods like `#first`,
 `#filter`/`#select` and `#map` on it.
 
+The sheets could be accessed by index or by name:
+
+```ruby
+x = Xsv::Workbook.open("sheet.xlsx")
+
+sheet = x.sheets[0] # gets sheet by index
+
+sheet = x.sheets_by_name('Name').first # gets sheet by name
+```
+
+To get all the workbook's sheets names:
+
+```ruby
+sheet_names = x.sheets.map(&:name)
+```
+
 ### Assumptions
 
 Since Xsv treats worksheets like csv files it makes certain assumptions about your

data/lib/xsv.rb

@@ -3,10 +3,12 @@ require "date"
 require "ox"
 
 require "xsv/helpers"
+require "xsv/relationships_handler"
 require "xsv/shared_strings_parser"
 require "xsv/sheet"
 require "xsv/sheet_bounds_handler"
 require "xsv/sheet_rows_handler"
+require 'xsv/sheets_ids_handler'
 require "xsv/styles_handler"
 require "xsv/version"
 require "xsv/workbook"

data/lib/xsv/relationships_handler.rb

@@ -0,0 +1,39 @@
+# frozen_string_literal: true
+module Xsv
+  # RelationshipsHandler parses the "xl/_rels/workbook.xml.rels" file to get the existing relationships.
+  # This is used internally  when opening a workbook.
+  class RelationshipsHandler < Ox::Sax
+    def self.get_relations(io)
+      relations = []
+      handler = new do |relation|
+        relations << relation
+      end
+
+      Ox.sax_parse(handler, io.read)
+      return relations
+    end
+
+    # Ox::Sax implementation
+
+    def initialize(&block)
+      @block = block
+    end
+
+    def start_element(name)
+      @relationship = {} if name == :Relationship
+    end
+
+    def attr(name, value)
+      case name
+        when :Id, :Type, :Target
+          @relationship[name] = value
+      end
+    end
+
+    def end_element(name)
+      return unless name == :Relationship
+
+      @block.call(@relationship)
+    end
+  end
+end

data/lib/xsv/sheet.rb

@@ -17,7 +17,7 @@ module Xsv
 
     # Returns the current mode. Call {#parse_headers!} to switch to `:hash` mode
     # @return [Symbol] `:hash` or `:array`
-    attr_reader :mode
+    attr_reader :id, :mode, :name
 
     # Set a number of rows to skip at the top of the sheet (header row offset).
     # For hash mode, do not skip the header row as this will be automatically
@@ -30,9 +30,11 @@ module Xsv
     # @param workbook [Workbook] The Workbook with shared data such as shared strings and styles
     # @param io [IO] A handle to an open worksheet XML file
     # @param size [Number] size of the XML file
-    def initialize(workbook, io, size)
+    def initialize(workbook, io, size, ids)
       @workbook = workbook
+      @id = ids[:sheetId].to_i
       @io = io
+      @name = ids[:name]
       @size = size
       @headers = []
       @mode = :array

data/lib/xsv/sheets_ids_handler.rb

@@ -0,0 +1,49 @@
+# frozen_string_literal: true
+module Xsv
+  # SheetsIdsHandler interprets the relevant parts of workbook.xml
+  # This is used internally to get the sheets ids, relationship_ids, and names when opening a workbook.
+  class SheetsIdsHandler < Ox::Sax
+    def self.get_sheets_ids(io)
+      sheets_ids = []
+      handler = new do |sheet_ids|
+        sheets_ids << sheet_ids
+      end
+
+      Ox.sax_parse(handler, io.read)
+      return sheets_ids
+    end
+
+    # Ox::Sax implementation
+
+    def initialize(&block)
+      @block = block
+    end
+
+    def start_element(name)
+      return @parsing = true if name == :sheets
+
+      return unless name == :sheet
+
+      @sheet_ids = {}
+    end
+
+    def attr(name, value)
+      return unless @parsing
+
+      case name
+        when :name, :sheetId
+          @sheet_ids[name] = value
+        when :'r:id'
+          @sheet_ids[:r_id] = value
+      end
+    end
+
+    def end_element(name)
+      return @parsing = false if name == :sheets
+
+      return unless name == :sheet
+
+      @block.call(@sheet_ids)
+    end
+  end
+end

data/lib/xsv/version.rb

@@ -1,4 +1,4 @@
 # frozen_string_literal: true
 module Xsv
-  VERSION = "0.3.11"
+  VERSION = "0.3.12"
 end

data/lib/xsv/workbook.rb

@@ -41,6 +41,8 @@ module Xsv
 
       fetch_shared_strings
       fetch_styles
+      fetch_sheets_ids
+      fetch_relationships
       fetch_sheets
     end
 
@@ -56,11 +58,20 @@ module Xsv
       @sheets = nil
       @xfs = nil
       @numFmts = nil
+      @relationships = nil
       @shared_strings = nil
+      @sheets_ids = nil
 
       true
     end
 
+    # Returns an array of sheets for the case of same name sheets.
+    # @param [String] name
+    # @return [Array<Xsv::Sheet>]
+    def sheets_by_name(name)
+      @sheets.select { |s| s.name == name }
+    end
+
     private
 
     def fetch_shared_strings
@@ -80,8 +91,24 @@ module Xsv
       @zip.glob("xl/worksheets/sheet*.xml").sort do |a, b|
         a.name[/\d+/].to_i <=> b.name[/\d+/].to_i
       end.each do |entry|
-        @sheets << Xsv::Sheet.new(self, entry.get_input_stream, entry.size)
+        rel = @relationships.detect { |r| entry.name.end_with?(r[:Target]) && r[:Type].end_with?('worksheet') }
+        sheet_ids = @sheets_ids.detect { |i| i[:r_id] == rel[:Id] }
+        @sheets << Xsv::Sheet.new(self, entry.get_input_stream, entry.size, sheet_ids)
       end
     end
+
+    def fetch_sheets_ids
+      stream = @zip.glob("xl/workbook.xml").first.get_input_stream
+      @sheets_ids = SheetsIdsHandler.get_sheets_ids(stream)
+
+      stream.close
+    end
+
+    def fetch_relationships
+      stream = @zip.glob("xl/_rels/workbook.xml.rels").first.get_input_stream
+      @relationships = RelationshipsHandler.get_relations(stream)
+
+      stream.close
+    end
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: xsv
 version: !ruby/object:Gem::Version
-  version: 0.3.11
+  version: 0.3.12
 platform: ruby
 authors:
 - Martijn Storck
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2020-04-03 00:00:00.000000000 Z
+date: 2020-04-15 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rubyzip
@@ -108,10 +108,12 @@ files:
 - bin/setup
 - lib/xsv.rb
 - lib/xsv/helpers.rb
+- lib/xsv/relationships_handler.rb
 - lib/xsv/shared_strings_parser.rb
 - lib/xsv/sheet.rb
 - lib/xsv/sheet_bounds_handler.rb
 - lib/xsv/sheet_rows_handler.rb
+- lib/xsv/sheets_ids_handler.rb
 - lib/xsv/styles_handler.rb
 - lib/xsv/version.rb
 - lib/xsv/workbook.rb