creek 1.1.1 → 1.1.2

checksums.yaml

@@ -1,7 +1,15 @@
 ---
-SHA1:
-  metadata.gz: 144f13f0eba1b81962017976302f6b2db2b47b60
-  data.tar.gz: fa8fe5d9aecd0eab818f06027425a0bd28a15808
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    M2M3NGQxMDJmMTc3NDk5MDUzMjFiNTU4NWI1ODZmMjBiNThkYzgyYg==
+  data.tar.gz: !binary |-
+    NWE3YmRhNGI5NTkwMDgzNDFiMDJkMmYzYzI1NjNiYjY2MDE0NmQ0Yw==
 SHA512:
-  metadata.gz: 6ae590ddf3d095381c2cde2109b90bd1b44637120bcbc24257325fa3283cae6f5fcf35f75778f7b425556bc6c9aeff3c897c018c91f3726e66004d9a56d1b510
-  data.tar.gz: 2f7abb6a3889bbf25fe78165244ed62e265a60b4ea4a3d598a6c0865c8188d4037d281b93c1069f694dcac3ec14c4bcd5765bc0cd1469247adeb714dc6c55e68
+  metadata.gz: !binary |-
+    ZjdmNjdmOTM1Zjc1OGIyNjI1YWZiNjlmNmJhZDliZDViMDJjODE5NDEzNzJi
+    NjI5MTkxMTYyNTRhMDhkODkxOGExY2E1MTVlMmZkODEwMTM4M2NlYjgyODI2
+    MDcxMjFmMzNmZDA2ZWU3MWM3OWJmNWRhMzAyYzgxM2E0NzdkODk=
+  data.tar.gz: !binary |-
+    ZmYxNDFiYzU0MDM1Y2FlMjgxZmI4OGI2OTRiYTQzMTI2OGRhMGYxNjlhNTU0
+    MzFjNTY5MjA5M2ZjY2MyODA3MDljYzYwZTNhNmZjZTAzMGQ4ZDFmMTNjNzU1
+    MTU5Y2I1M2Q3ZGU3YWE1Y2VjZDVhMDY3NTVlYzc1NmEyNmZlODU=

data/lib/creek/book.rb

@@ -1,5 +1,6 @@
 require 'zip/filesystem'
 require 'nokogiri'
+require 'date'
 
 module Creek
 
@@ -9,6 +10,9 @@ module Creek
                 :sheets,
                 :shared_strings
 
+    DATE_1900 = Date.new(1899, 12, 30).freeze
+    DATE_1904 = Date.new(1904, 1, 1).freeze
+
     def initialize path, options = {}
       check_file_extension = options.fetch(:check_file_extension, true)
       if check_file_extension
@@ -37,5 +41,26 @@ module Creek
     def close
       @files.close
     end
+
+    def base_date
+      @base_date ||=
+      begin
+        # Default to 1900 (minus one day due to excel quirk) but use 1904 if
+        # it's set in the Workbook's workbookPr
+        # http://msdn.microsoft.com/en-us/library/ff530155(v=office.12).aspx
+        result = DATE_1900 # default
+
+        doc = @files.file.open "xl/workbook.xml"
+        xml = Nokogiri::XML::Document.parse doc
+        xml.css('workbookPr[date1904]').each do |workbookPr|
+          if workbookPr['date1904'] =~ /true|1/i
+            result = DATE_1904
+            break
+          end
+        end
+
+        result
+      end
+    end
   end
 end

data/lib/creek/sheet.rb

@@ -21,13 +21,6 @@ module Creek
       @rid = rid
       @state = state
       @sheetfile = sheetfile
-
-      # An XLS file has only 256 columns, however, an XLSX or XLSM file can contain up to 16384 columns.
-      # This function creates a hash with all valid XLSX column names and associated indices.
-      @excel_col_names = Hash.new
-      (0...16384).each do |i|
-        @excel_col_names[col_name(i)] = i
-      end
     end
 
     ##
@@ -45,13 +38,6 @@ module Creek
     end
 
     private
-    ##
-    # Returns valid Excel column name for a given column index.
-    # For example, returns "A" for 0, "B" for 1 and "AQ" for 42.
-    def col_name i
-      quot = i/26
-      (quot>0 ? col_name(quot-1) : "") + (i%26+65).chr
-    end
 
     ##
     # Returns a hash per row that includes the cell ids and values.
@@ -64,7 +50,7 @@ module Creek
         opener = Nokogiri::XML::Reader::TYPE_ELEMENT
         closer = Nokogiri::XML::Reader::TYPE_END_ELEMENT
         Enumerator.new do |y|
-          shared, row, cells, cell = false, nil, {}, nil
+          row, cells, cell = nil, {}, nil
           cell_type  = nil
           cell_style_idx = nil
           @book.files.file.open(path) do |xml|
@@ -82,9 +68,8 @@ module Creek
                 cell_type      = node.attributes['t']
                 cell_style_idx = node.attributes['s']
                 cell           = node.attributes['r']
-
               elsif (node.name.eql? 'v') and (node.node_type.eql? opener)
-                if !cell.nil?
+                unless cell.nil?
                   cells[cell] = convert(node.inner_xml, cell_type, cell_style_idx)
                 end
               end
@@ -100,29 +85,28 @@ module Creek
     end
 
     def converter_options
-      @converter_options ||= {shared_strings: @book.shared_strings.dictionary}
+      @converter_options ||= {
+        shared_strings: @book.shared_strings.dictionary,
+        base_date: @book.base_date
+      }
     end
 
     ##
     # The unzipped XML file does not contain any node for empty cells.
     # Empty cells are being padded in using this function
-    def fill_in_empty_cells cells, row_number, last_col
+    def fill_in_empty_cells(cells, row_number, last_col)
       new_cells = Hash.new
+
       unless cells.empty?
-        keys = cells.keys.sort
         last_col = last_col.gsub(row_number, '')
-        last_col_index = @excel_col_names[last_col]
-        [*(0..last_col_index)].each do |i|
-          col = col_name i
-          id = "#{col}#{row_number}"
-          unless cells.has_key? id
-              new_cells[id] = nil
-          else
-            new_cells[id] = cells[id]
-          end
+
+        ("A"..last_col).to_a.each do |column|
+          id = "#{column}#{row_number}"
+          new_cells[id] = cells[id]
         end
       end
+
       new_cells
     end
   end
-end
+end

data/lib/creek/styles/constants.rb

@@ -1,5 +1,3 @@
-require 'date'
-
 module Creek
   class Styles
     module Constants
@@ -38,9 +36,6 @@ module Creek
         48 => :bignum,         # ##0.0E+0
         49 => :unsupported     # @
       }
-
-      DATE_SYSTEM_1900 = Date.new(1899, 12, 30)
-      DATE_SYSTEM_1904 = Date.new(1904, 1, 1)
     end
   end
 end

data/lib/creek/styles/converter.rb

@@ -81,7 +81,7 @@ module Creek
         fraction_of_24               = value - days_since_date_system_start
 
         # http://stackoverflow.com/questions/10559767/how-to-convert-ms-excel-date-from-float-to-date-format-in-ruby
-        date = options.fetch(:base_date, DATE_SYSTEM_1900) + days_since_date_system_start
+        date = options.fetch(:base_date, Date.new(1899, 12, 30)) + days_since_date_system_start
 
         if fraction_of_24 > 0 # there is a time associated
           seconds = (fraction_of_24 * 86400).round
@@ -98,21 +98,6 @@ module Creek
           value.to_f
         end
       end
-
-      ## Returns the base_date from which to calculate dates.
-      # Defaults to 1900 (minus two days due to excel quirk), but use 1904 if
-      # it's set in the Workbook's workbookPr.
-      # http://msdn.microsoft.com/en-us/library/ff530155(v=office.12).aspx
-      def base_date
-        @base_date ||= begin
-          # return DATE_SYSTEM_1900 if xml.workbook == nil
-          # xml.workbook.xpath("//workbook/workbookPr[@date1904]").each do |workbookPr|
-          #   return DATE_SYSTEM_1904 if workbookPr["date1904"] =~ /true|1/i
-          # end
-          DATE_SYSTEM_1900
-        end
-      end
-
     end
   end
 end

data/lib/creek/version.rb

@@ -1,3 +1,3 @@
 module Creek
-  VERSION = "1.1.1"
+  VERSION = "1.1.2"
 end

metadata

@@ -1,97 +1,97 @@
 --- !ruby/object:Gem::Specification
 name: creek
 version: !ruby/object:Gem::Version
-  version: 1.1.1
+  version: 1.1.2
 platform: ruby
 authors:
 - pythonicrubyist
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-10-18 00:00:00.000000000 Z
+date: 2016-04-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ~>
       - !ruby/object:Gem::Version
         version: '1.3'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ~>
       - !ruby/object:Gem::Version
         version: '1.3'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ~>
       - !ruby/object:Gem::Version
         version: 2.13.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ~>
       - !ruby/object:Gem::Version
         version: 2.13.0
 - !ruby/object:Gem::Dependency
   name: pry
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: nokogiri
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ~>
       - !ruby/object:Gem::Version
         version: 1.6.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ~>
       - !ruby/object:Gem::Version
         version: 1.6.0
 - !ruby/object:Gem::Dependency
   name: rubyzip
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - ! '>='
       - !ruby/object:Gem::Version
         version: 1.0.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - ! '>='
       - !ruby/object:Gem::Version
         version: 1.0.0
 description: A Ruby gem that streams and parses large Excel(xlsx and xlsm) files fast
@@ -102,7 +102,7 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- ".gitignore"
+- .gitignore
 - Gemfile
 - LICENSE.txt
 - README.rdoc
@@ -139,17 +139,17 @@ require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ">="
+  - - ! '>='
     - !ruby/object:Gem::Version
       version: 1.9.2
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ">="
+  - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.4.8
+rubygems_version: 2.4.3
 signing_key: 
 specification_version: 4
 summary: A Ruby gem for parsing large Excel(xlsx and xlsm) files.