simple_xlsx_reader 1.0.2 → 1.0.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: d3b2fbcc0148d773ed19a266e64877600863730c
-  data.tar.gz: 61be9bbca611e49dc7ca725dd33d1560eec98018
+  metadata.gz: 1dd4b96753ca2dafcfadf59469c3a9357742ab7e
+  data.tar.gz: ffb23c6b020a55b893743206c236fea2abb07b65
 SHA512:
-  metadata.gz: 041cd7eb5b2ebeeb310da52c0e173ff7c04ac95b55ae1c35cc510280c7d10e9ea6af703d10f2bed1f5f5678c77465fdd5807de2d8b3e4ccf7f1a01475178f487
-  data.tar.gz: 8587c21a003e2bf4af53b2c67348102d85713e997bc15e248f2b806d4d7388b078bb7a5315c503931a0f287e1a7771d990913878d916d010c36040b6777b98ab
+  metadata.gz: 01a2326f942c455c665d5c135aa4115edd87a307e4aa5dff5e1d177ef61dcd326bcc33ad342f3b164ac7996731f0e31e97a9471973b98682757624f44052f6a2
+  data.tar.gz: b5371713dd232d5f1134ab810ea69447a3ad59bb781f917df2bc3a49e7b1c86c765ab0a074b1ddce021390f1b1d54e1507326abf22a65f1d83de1cf568ce7896

data/.travis.yml

@@ -0,0 +1,7 @@
+language: ruby
+cache: bundler
+before_install:
+  - gem update bundler
+rvm:
+  - 1.9.3
+  - 2.3.0

data/CHANGELOG.md

@@ -1,3 +1,13 @@
+### 1.0.4
+
+* Fix Windows + RubyZip 1.2.1 bug preventing files from being read
+* Add ability to parse hyperlinks
+* Support files exported from Google Docs (@Strnadj)
+
+### 1.0.3
+
+Broken on Ruby 1.9; yanked.
+
 ### 1.0.2
 
 * Fix Ruby 1.9.3-specific bug preventing parsing most sheets [middagj, eritiro]
@@ -5,6 +15,7 @@
   * You don't always have a numFmtId column, and that's OK
   * Sometimes 'sharedStrings.xml' can be 'sharedstrings.xml'
 * Fixed parsing times very close to 12/30/1899 [Valeriy Utyaganov]
+* Be more flexible with custom formats using a numFmtId < 164
 
 ### 1.0.1
 

data/README.md

@@ -1,4 +1,4 @@
-# SimpleXlsxReader
+# SimpleXlsxReader [![Build Status](https://travis-ci.org/woahdae/simple_xlsx_reader.svg?branch=master)](https://travis-ci.org/woahdae/simple_xlsx_reader)
 
 An xlsx reader for Ruby that parses xlsx cell values into plain ruby
 primitives and dates/times.

data/lib/simple_xlsx_reader.rb

@@ -19,6 +19,33 @@ end
 module SimpleXlsxReader
   class CellLoadError < StandardError; end
 
+  # We support hyperlinks as a "type" even though they're technically
+  # represented either as a function or an external reference in the xlsx spec.
+  #
+  # Since having hyperlink data in our sheet usually means we might want to do
+  # something primarily with the URL (store it in the database, download it, etc),
+  # we go through extra effort to parse the function or follow the reference
+  # to represent the hyperlink primarily as a URL. However, maybe we do want
+  # the hyperlink "friendly name" part (as MS calls it), so here we've subclassed
+  # string to tack on the friendly name. This means 80% of us that just want
+  # the URL value will have to do nothing extra, but the 20% that might want the
+  # friendly name can access it.
+  #
+  # Note, by default, the value we would get by just asking the cell would
+  # be the "friendly name" and *not* the URL, which is tucked away in the
+  # function definition or a separate "relationships" meta-document.
+  #
+  # See MS documentation on the HYPERLINK function for some background:
+  # https://support.office.com/en-us/article/HYPERLINK-function-333c7ce6-c5ae-4164-9c47-7de9b76f577f
+  class Hyperlink < String
+    attr_reader :friendly_name
+
+    def initialize(url, friendly_name = nil)
+      @friendly_name = friendly_name
+      super(url)
+    end
+  end
+
   def self.configuration
     @configuration ||= Struct.new(:catch_cell_load_errors).new.tap do |c|
       c.catch_cell_load_errors = false
@@ -69,29 +96,54 @@ module SimpleXlsxReader
     ##
     # For internal use; stores source xml in nokogiri documents
     class Xml
-      attr_accessor :workbook, :shared_strings, :sheets, :styles
+      attr_accessor :workbook, :shared_strings, :sheets, :sheet_rels, :styles
 
       def self.load(file_path)
         self.new.tap do |xml|
           SimpleXlsxReader::Zip.open(file_path) do |zip|
-            xml.workbook = Nokogiri::XML(zip.read('xl/workbook.xml')).remove_namespaces!
-            xml.styles   = Nokogiri::XML(zip.read('xl/styles.xml')).remove_namespaces!
-
-            # optional feature used by excel, but not often used by xlsx
-            # generation libraries
-            ss_file =  (zip.to_a.map(&:name) & ['xl/sharedStrings.xml','xl/sharedstrings.xml'])[0]
-            if ss_file
-              xml.shared_strings = Nokogiri::XML(zip.read(ss_file)).remove_namespaces!
-            end
-
             xml.sheets = []
-            i = 0
-            loop do
-              i += 1
-              break if !zip.file.file?("xl/worksheets/sheet#{i}.xml")
+            xml.sheet_rels = []
+
+            # This weird style of enumerating over the entries lets us
+            # concisely assign entries in a case insensitive and
+            # slash insensitive ('/' vs '\') manner.
+            #
+            # RubyZip used to normalize the slashes, but doesn't now:
+            # https://github.com/rubyzip/rubyzip/issues/324
+            zip.entries.each do |entry|
+              if entry.name.match(/^xl.workbook\.xml$/) # xl/workbook.xml
+                xml.workbook = Nokogiri::XML(zip.read(entry)).remove_namespaces!
+              elsif entry.name.match(/^xl.styles\.xml$/) # xl/styles.xml
+                xml.styles   = Nokogiri::XML(zip.read(entry)).remove_namespaces!
+              elsif entry.name.match(/^xl.sharedStrings\.xml$/i) # xl/sharedStrings.xml
+                # optional feature used by excel, but not often used by xlsx
+                # generation libraries. Path name is sometimes lowercase, too.
+                xml.shared_strings = Nokogiri::XML(zip.read(entry)).remove_namespaces!
+              elsif match = entry.name.match(/^xl.worksheets.sheet([0-9]*)\.xml$/)
+                sheet_number = match.captures.first.to_i
+                xml.sheets[sheet_number] =
+                  Nokogiri::XML(zip.read(entry)).remove_namespaces!
+              elsif match = entry.name.match(/^xl.worksheets._rels.sheet([0-9]*)\.xml\.rels$/)
+                sheet_number = match.captures.first.to_i
+                xml.sheet_rels[sheet_number] =
+                  Nokogiri::XML(zip.read(entry)).remove_namespaces!
+              end
+            end
 
-              xml.sheets <<
-                Nokogiri::XML(zip.read("xl/worksheets/sheet#{i}.xml")).remove_namespaces!
+            # Sometimes there's a zero-index sheet.xml, ex.
+            # Google Docs creates:
+            #
+            # xl/worksheets/sheet.xml
+            # xl/worksheets/sheet1.xml
+            # xl/worksheets/sheet2.xml
+            # While Excel creates:
+            # xl/worksheets/sheet1.xml
+            # xl/worksheets/sheet2.xml
+            #
+            # So, for the latter case, let's shift [null, <Sheet 1>, <Sheet 2>]
+            if !xml.sheets[0]
+              xml.sheets.shift
+              xml.sheet_rels.shift
             end
           end
         end
@@ -106,7 +158,7 @@ module SimpleXlsxReader
 
       def load_sheets
         sheet_toc.each_with_index.map do |(sheet_name, _sheet_number), i|
-          parse_sheet(sheet_name, xml.sheets[i])  # sheet_number is *not* the index into xml.sheets
+          parse_sheet(sheet_name, xml.sheets[i], xml.sheet_rels[i])  # sheet_number is *not* the index into xml.sheets
         end
       end
 
@@ -122,9 +174,10 @@ module SimpleXlsxReader
         end
       end
 
-      def parse_sheet(sheet_name, xsheet)
+      def parse_sheet(sheet_name, xsheet, xrels)
         sheet = Sheet.new(sheet_name)
         sheet_width, sheet_height = *sheet_dimensions(xsheet)
+        cells_w_links = xsheet.xpath('//hyperlinks/hyperlink').inject({}) {|acc, e| acc[e.attr(:ref)] = e.attr(:id); acc}
 
         sheet.rows = Array.new(sheet_height) { Array.new(sheet_width) }
         xsheet.xpath("/worksheet/sheetData/row/c").each do |xcell|
@@ -149,10 +202,21 @@ module SimpleXlsxReader
           # by about 60%. Odd.
           xvalue = type == 'inlineStr' ?
             (xis = xcell.children.find {|c| c.name == 'is'}) && xis.children.find {|c| c.name == 't'} :
-            xcell.children.find {|c| c.name == 'v'}
+            xcell.children.find {|c| c.name == 'f' && c.text.start_with?('HYPERLINK(') || c.name == 'v'}
+
+          if xvalue
+            value = xvalue.text.strip
+
+            if rel_id = cells_w_links[xcell.attr('r')] # a hyperlink made via GUI
+              url = xrels.at_xpath(%(//*[@Id="#{rel_id}"])).attr('Target')
+            elsif xvalue.name == 'f' # only time we have a function is if it's a hyperlink
+              url = value.slice(/HYPERLINK\("(.*?)"/, 1)
+            end
+          end
 
           cell = begin
-            self.class.cast(xvalue && xvalue.text.strip, type, style,
+            self.class.cast(value, type, style,
+                            :url => url,
                             :shared_strings => shared_strings,
                             :base_date => base_date)
           rescue => e
@@ -328,7 +392,7 @@ module SimpleXlsxReader
           type = style
         end
 
-        case type
+        casted = case type
 
         ##
         # There are few built-in types
@@ -361,7 +425,7 @@ module SimpleXlsxReader
         # the trickiest. note that  all these formats can vary on
         # whether they actually contain a date, time, or datetime.
         when :date, :time, :date_time
-          value = value.to_f
+          value = Float(value)
           days_since_date_system_start = value.to_i
           fraction_of_24 = value - days_since_date_system_start
 
@@ -388,6 +452,12 @@ module SimpleXlsxReader
         else
           value
         end
+
+        if options[:url]
+          Hyperlink.new(options[:url], casted)
+        else
+          casted
+        end
       end
 
       ## Returns the base_date from which to calculate dates.

data/lib/simple_xlsx_reader/version.rb

@@ -1,3 +1,3 @@
 module SimpleXlsxReader
-  VERSION = "1.0.2"
+  VERSION = "1.0.4"
 end

data/simple_xlsx_reader.gemspec

@@ -7,19 +7,21 @@ Gem::Specification.new do |gem|
   gem.name          = "simple_xlsx_reader"
   gem.version       = SimpleXlsxReader::VERSION
   gem.authors       = ["Woody Peterson"]
-  gem.email         = ["woody@sigby.com"]
+  gem.email         = ["woody.peterson@gmail.com"]
   gem.description   = %q{Read xlsx data the Ruby way}
   gem.summary       = %q{Read xlsx data the Ruby way}
   gem.homepage      = ""
+  gem.license       = "MIT"
 
   gem.add_dependency 'nokogiri'
   gem.add_dependency 'rubyzip'
 
   gem.add_development_dependency 'minitest', '>= 5.0'
+  gem.add_development_dependency 'rake'
   gem.add_development_dependency 'pry'
 
   gem.files         = `git ls-files`.split($/)
   gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
-  gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
+  gem.test_files    = gem.files.grep(%r{^test/})
   gem.require_paths = ["lib"]
 end

data/test/gdocs_sheet_test.rb

@@ -0,0 +1,15 @@
+require_relative 'test_helper'
+require 'time'
+
+describe SimpleXlsxReader do
+  let(:one_sheet_file) { File.join(File.dirname(__FILE__), 'gdocs_sheet.xlsx') }
+  let(:subject) { SimpleXlsxReader::Document.new(one_sheet_file) }
+
+  it 'able to load file from google docs' do
+    subject.to_hash.must_equal({
+      "List 1" => [["Empty gdocs list 1"]],
+      "List 2" => [["Empty gdocs list 2"]]
+    })
+  end
+
+end

data/test/performance_test.rb

@@ -96,13 +96,13 @@ describe 'SimpleXlsxReader Benchmark' do
     bench_exp(1,10000)
   end
 
-  bench_performance_linear 'parses sheets in linear time', 0.9999 do |n|
+  bench_performance_linear 'parses sheets in linear time', 0.999 do |n|
 
     raise "not enough sample data; asked for #{n}, only have #{@xml.sheets.size}"\
       if @xml.sheets[n].nil?
 
     sheet = SimpleXlsxReader::Document::Mapper.new(@xml).
-      parse_sheet('test', @xml.sheets[n])
+      parse_sheet('test', @xml.sheets[n], nil)
 
     raise "sheet didn't parse correctly; expected #{n + 1} rows, got #{sheet.rows.size}"\
       if sheet.rows.size != n + 1

data/test/simple_xlsx_reader_test.rb

@@ -1,6 +1,8 @@
 require_relative 'test_helper'
 require 'time'
 
+SXR = SimpleXlsxReader
+
 describe SimpleXlsxReader do
   let(:sesame_street_blog_file) { File.join(File.dirname(__FILE__),
                                             'sesame_street_blog.xlsx') }
@@ -15,11 +17,11 @@ describe SimpleXlsxReader do
            ["Big Bird", "Teacher"]],
 
         "Posts"=>
-          [["Author Name", "Title", "Body", "Created At", "Comment Count"],
-           ["Big Bird", "The Number 1", "The Greatest", Time.parse("2002-01-01 11:00:00 UTC"), 1],
-           ["Big Bird", "The Number 2", "Second Best", Time.parse("2002-01-02 14:00:00 UTC"), 2],
-           ["Big Bird", "Formula Dates", "Tricky tricky", Time.parse("2002-01-03 14:00:00 UTC"), 0],
-           ["Empty Eagress", nil, "The title, date, and comment have types, but no values", nil, nil]]
+          [["Author Name", "Title", "Body", "Created At", "Comment Count", "URL"],
+           ["Big Bird", "The Number 1", "The Greatest", Time.parse("2002-01-01 11:00:00 UTC"), 1, SXR::Hyperlink.new("http://www.example.com/hyperlink-function", "This uses the HYPERLINK() function")],
+           ["Big Bird", "The Number 2", "Second Best", Time.parse("2002-01-02 14:00:00 UTC"), 2, SXR::Hyperlink.new("http://www.example.com/hyperlink-gui", "This uses the hyperlink GUI option")],
+           ["Big Bird", "Formula Dates", "Tricky tricky", Time.parse("2002-01-03 14:00:00 UTC"), 0, nil],
+           ["Empty Eagress", nil, "The title, date, and comment have types, but no values", nil, nil, nil]]
       })
     end
   end
@@ -63,10 +65,33 @@ describe SimpleXlsxReader do
           must_equal Time.parse('2013-08-19 18:30 UTC')
       end
 
+      it 'reads less-than-zero complex number types styled as times' do
+        described_class.cast('6.25E-2', 'n', :time).
+          must_equal Time.parse('1899-12-30 01:30:00 UTC')
+      end
+
       it 'reads number types styled as date_times' do
         described_class.cast('41505.77083', 'n', :date_time).
           must_equal Time.parse('2013-08-19 18:30 UTC')
       end
+
+      it 'raises when date-styled values are not numerical' do
+        lambda { described_class.cast('14 is not a valid date', nil, :date) }.
+          must_raise(ArgumentError)
+      end
+
+      describe "with the url option" do
+        let(:url) { "http://www.example.com/hyperlink" }
+        it 'creates a hyperlink with a string type' do
+          described_class.cast("A link", 'str', :string, url: url).
+            must_equal SXR::Hyperlink.new(url, "A link")
+        end
+
+        it 'creates a hyperlink with a shared string type' do
+          described_class.cast("2", 's', nil, shared_strings: ['a','b','c'], url: url).
+            must_equal SXR::Hyperlink.new(url, 'c')
+        end
+      end
     end
 
     describe '#shared_strings' do
@@ -253,15 +278,15 @@ describe SimpleXlsxReader do
       it 'raises if configuration.catch_cell_load_errors' do
         SimpleXlsxReader.configuration.catch_cell_load_errors = false
 
-        lambda { described_class.new(xml).parse_sheet('test', xml.sheets.first) }.
+        lambda { described_class.new(xml).parse_sheet('test', xml.sheets.first, nil) }.
           must_raise(SimpleXlsxReader::CellLoadError)
       end
 
       it 'records a load error if not configuration.catch_cell_load_errors' do
         SimpleXlsxReader.configuration.catch_cell_load_errors = true
 
-        sheet = described_class.new(xml).parse_sheet('test', xml.sheets.first)
-        sheet.load_errors[[0,0]].must_include 'invalid value for Integer'
+        sheet = described_class.new(xml).parse_sheet('test', xml.sheets.first, nil)
+        sheet.load_errors[[0,0]].must_include 'invalid value for Float'
       end
     end
 
@@ -295,7 +320,7 @@ describe SimpleXlsxReader do
       end
 
       before do
-        @row = described_class.new(xml).parse_sheet('test', xml.sheets.first).rows[0]
+        @row = described_class.new(xml).parse_sheet('test', xml.sheets.first, nil).rows[0]
       end
 
       it 'continues even when cells are missing numFmtId attributes ' do
@@ -330,8 +355,21 @@ describe SimpleXlsxReader do
                     <c r='G1' t='inlineStr' s='0'>
                       <is><t>Cell G1</t></is>
                     </c>
+
+                    <c r='H1' s='0'>
+                      <f>HYPERLINK("http://www.example.com/hyperlink-function", "HYPERLINK function")</f>
+                      <v>HYPERLINK function</v>
+                    </c>
+
+                    <c r='I1' s='0'>
+                      <v>GUI-made hyperlink</v>
+                    </c>
                   </row>
                 </sheetData>
+
+                <hyperlinks>
+                  <hyperlink ref="I1" id="rId1"/>
+                </hyperlinks>
               </worksheet>
             XML
           ).remove_namespaces!]
@@ -349,11 +387,28 @@ describe SimpleXlsxReader do
               </styleSheet>
             XML
           ).remove_namespaces!
+
+          # Although not a "type" or "style" according to xlsx spec,
+          # it sure could/should be, so let's test it with the rest of our
+          # typecasting code.
+          xml.sheet_rels = [Nokogiri::XML(
+            <<-XML
+              <Relationships>
+                <Relationship
+                  Id="rId1"
+                  Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/hyperlink"
+                  Target="http://www.example.com/hyperlink-gui"
+                  TargetMode="External"
+                />
+              </Relationships>
+            XML
+          ).remove_namespaces!]
+
         end
       end
 
       before do
-        @row = described_class.new(xml).parse_sheet('test', xml.sheets.first).rows[0]
+        @row = described_class.new(xml).parse_sheet('test', xml.sheets.first, xml.sheet_rels.first).rows[0]
       end
 
       it "reads 'Generic' cells as strings" do
@@ -387,6 +442,18 @@ describe SimpleXlsxReader do
       it "reads strings formatted as inlineStr" do
         @row[6].must_equal 'Cell G1'
       end
+
+      it "reads hyperlinks created via HYPERLINK()" do
+        @row[7].must_equal(
+          SXR::Hyperlink.new(
+            "http://www.example.com/hyperlink-function", "HYPERLINK function"))
+      end
+
+      it "reads hyperlinks created via the GUI" do
+        @row[8].must_equal(
+          SXR::Hyperlink.new(
+            "http://www.example.com/hyperlink-gui", "GUI-made hyperlink"))
+      end
     end
 
     describe 'parsing documents with blank rows' do
@@ -435,7 +502,7 @@ describe SimpleXlsxReader do
       end
 
       before do
-        @rows = described_class.new(xml).parse_sheet('test', xml.sheets.first).rows
+        @rows = described_class.new(xml).parse_sheet('test', xml.sheets.first, nil).rows
       end
 
       it "reads row data despite gaps in row numbering" do

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: simple_xlsx_reader
 version: !ruby/object:Gem::Version
-  version: 1.0.2
+  version: 1.0.4
 platform: ruby
 authors:
 - Woody Peterson
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-02-24 00:00:00.000000000 Z
+date: 2018-07-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -52,6 +52,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '5.0'
+- !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: pry
   requirement: !ruby/object:Gem::Requirement
@@ -68,12 +82,13 @@ dependencies:
         version: '0'
 description: Read xlsx data the Ruby way
 email:
-- woody@sigby.com
+- woody.peterson@gmail.com
 executables: []
 extensions: []
 extra_rdoc_files: []
 files:
 - ".gitignore"
+- ".travis.yml"
 - CHANGELOG.md
 - Gemfile
 - LICENSE.txt
@@ -86,6 +101,8 @@ files:
 - test/date1904_test.rb
 - test/datetime_test.rb
 - test/datetimes.xlsx
+- test/gdocs_sheet.xlsx
+- test/gdocs_sheet_test.rb
 - test/lower_case_sharedstrings.xlsx
 - test/lower_case_sharedstrings_test.rb
 - test/performance_test.rb
@@ -95,7 +112,8 @@ files:
 - test/styles.xml
 - test/test_helper.rb
 homepage: ''
-licenses: []
+licenses:
+- MIT
 metadata: {}
 post_install_message: 
 rdoc_options: []
@@ -113,7 +131,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.2.2
+rubygems_version: 2.5.2
 signing_key: 
 specification_version: 4
 summary: Read xlsx data the Ruby way
@@ -122,6 +140,8 @@ test_files:
 - test/date1904_test.rb
 - test/datetime_test.rb
 - test/datetimes.xlsx
+- test/gdocs_sheet.xlsx
+- test/gdocs_sheet_test.rb
 - test/lower_case_sharedstrings.xlsx
 - test/lower_case_sharedstrings_test.rb
 - test/performance_test.rb