creek 2.4.1 → 2.4.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: ddab26a3269b8c9367e6e891bd9aff7e21c96310
-  data.tar.gz: 1959b38cd75e8836c39b2e2d0f8e332a8145f7bd
+SHA256:
+  metadata.gz: 997fbfad1c0930d6cc9afa229a7d4e43f4f157ac2a8cda3df9863994a7b4a3fe
+  data.tar.gz: 38988cdecc3124a3ab9f6d70a99ab43a562b826475d17d04f6b556643aa56f8f
 SHA512:
-  metadata.gz: 35d72aab09ffc085e5869fe6a93d3249733820175e711749c7b13574f0545e9101cde0acb28dc800eb8be3900c46860095df32de728eda269724de3849a5a7d1
-  data.tar.gz: 88eb9a761857575f87dcf45d72362e7bc4000c410ce7ccc924a54383987cf2a64fa3693a8b19a38ed4fc3544e8c6fc63b0aef540332f140aa70a15ca949bdda5
+  metadata.gz: f4b31ff774645765b4c7b06e314ac3dfbdcf61a164f77dbf68effefdd343fa3848373ebbcf07e82a12fd6141c39be711dc9fb127301867cb4a4eea70f21888ae
+  data.tar.gz: 841f1fd8bbb98db165913e1bbc3c8f3adef2b7c93e1c145c75049110a2386763a4ed2aa72a659f971297fdef95f664c561e0ded1902d7701b68c990a9e77827f

data/README.md

@@ -1,3 +1,6 @@
+[![version](https://badge.fury.io/rb/creek.svg)](https://badge.fury.io/rb/creek)
+[![downloads](https://ruby-gem-downloads-badge.herokuapp.com/creek?type=total&total_label=downloads)](https://ruby-gem-downloads-badge.herokuapp.com/creek?type=total&total_label=downloads)
+
 # Creek - Stream parser for large Excel (xlsx and xlsm) files.
 
 Creek is a Ruby gem that provides a fast, simple and efficient method of parsing large Excel (xlsx and xlsm) files.

data/lib/creek/shared_strings.rb

@@ -31,9 +31,9 @@ module Creek
       xml.css('si').each_with_index do |si, idx|
         text_nodes = si.css('t')
         if text_nodes.count == 1 # plain text node
-          dictionary[idx] = text_nodes.first.content
+          dictionary[idx] = Creek::Styles::Converter.unescape_string(text_nodes.first.content)
         else # rich text nodes with text fragments
-          dictionary[idx] = text_nodes.map(&:content).join('')
+          dictionary[idx] = text_nodes.map { |n| Creek::Styles::Converter.unescape_string(n.content) }.join('')
         end
       end
 

data/lib/creek/sheet.rb

@@ -116,7 +116,8 @@ module Creek
                 cell           = node.attributes['r']
               elsif (['v', 't'].include? node.name) and (node.node_type.eql? opener)
                 unless cell.nil?
-                  cells[(use_simple_rows_format ? cell.tr("0-9", "") : cell)] = convert(node.inner_xml, cell_type, cell_style_idx)
+                  node.read
+                  cells[(use_simple_rows_format ? cell.tr("0-9", "") : cell)] = convert(node.value, cell_type, cell_style_idx)
                 end
               end
             end

data/lib/creek/styles/converter.rb

@@ -4,6 +4,10 @@ module Creek
   class Styles
     class Converter
       include Creek::Styles::Constants
+
+      # Excel non-printable character escape sequence
+      HEX_ESCAPE_REGEXP = /_x[0-9A-Za-z]{4}_/
+
       ##
       # The heart of typecasting. The ruby type is determined either explicitly
       # from the cell xml or implicitly from the cell style, and this
@@ -45,9 +49,9 @@ module Creek
         when 'b'
           value.to_i == 1
         when 'str'
-          value
+          unescape_string(value)
         when 'inlineStr'
-          value
+          unescape_string(value)
 
         ##
         # Type can also be determined by a style,
@@ -112,6 +116,12 @@ module Creek
         end
       end
 
+      def self.unescape_string(value)
+        # excel encodes some non-printable characters using a hex code in the format _xHHHH_
+        # e.g. Carriage Return (\r) is encoded as _x000D_
+        value.gsub(HEX_ESCAPE_REGEXP) { |match| match[2, 4].to_i(16).chr(Encoding::UTF_8) }
+      end
+
       private
 
         def self.base_date(options)

data/lib/creek/version.rb

@@ -1,3 +1,3 @@
 module Creek
-  VERSION = "2.4.1"
+  VERSION = "2.4.2"
 end

data/spec/fixtures/sst.xml

@@ -75,4 +75,7 @@
             <t>B2</t>
         </r>
     </si>
+    <si>
+        <t>Cell with_x000D_escaped_x000D_characters</t>
+    </si>
 </sst>

data/spec/shared_string_spec.rb

@@ -7,12 +7,13 @@ describe 'shared strings' do
     doc = Nokogiri::XML(shared_strings_xml_file)
     dictionary = Creek::SharedStrings.parse_shared_string_from_document(doc)
 
-    expect(dictionary.keys.size).to eq(5)
+    expect(dictionary.keys.size).to eq(6)
     expect(dictionary[0]).to eq('Cell A1')
     expect(dictionary[1]).to eq('Cell B1')
     expect(dictionary[2]).to eq('My Cell')
     expect(dictionary[3]).to eq('Cell A2')
     expect(dictionary[4]).to eq('Cell B2')
+    expect(dictionary[5]).to eq("Cell with\rescaped\rcharacters")
   end
 
 end

data/spec/sheet_spec.rb

@@ -12,6 +12,18 @@ describe 'sheet' do
     cell[cell_name] if cell
   end
 
+  context 'escaped ampersand' do
+    let(:book_escaped) { Creek::Book.new('spec/fixtures/escaped.xlsx') }
+    it 'does NOT escape ampersand' do
+      expect(book_escaped.sheets[0].rows.to_enum.map(&:values)).to eq([["abc", "def"], ["ghi", "j&k"]])
+    end
+
+    let(:book_escaped2) { Creek::Book.new('spec/fixtures/escaped2.xlsx') }
+    it 'does escape ampersand' do
+      expect(book_escaped2.sheets[0].rows.to_enum.map(&:values)).to eq([["abc", "def"], ["ghi", "j&k"]])
+    end
+  end
+
   describe '#rows' do
     context 'with excel with images' do
       context 'with images preloading' do

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: creek
 version: !ruby/object:Gem::Version
-  version: 2.4.1
+  version: 2.4.2
 platform: ruby
 authors:
 - pythonicrubyist
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-07-13 00:00:00.000000000 Z
+date: 2019-03-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -136,6 +136,8 @@ files:
 - lib/creek/version.rb
 - spec/.DS_Store
 - spec/drawing_spec.rb
+- spec/fixtures/escaped.xlsx
+- spec/fixtures/escaped2.xlsx
 - spec/fixtures/invalid.xls
 - spec/fixtures/large_numbers.xlsx
 - spec/fixtures/sample-as-zip.zip
@@ -174,13 +176,15 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.6.14
+rubygems_version: 2.7.8
 signing_key: 
 specification_version: 4
 summary: A Ruby gem for parsing large Excel(xlsx and xlsm) files.
 test_files:
 - spec/.DS_Store
 - spec/drawing_spec.rb
+- spec/fixtures/escaped.xlsx
+- spec/fixtures/escaped2.xlsx
 - spec/fixtures/invalid.xls
 - spec/fixtures/large_numbers.xlsx
 - spec/fixtures/sample-as-zip.zip