simple_xlsx_reader 1.0.1 → 1.0.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 94422da0193805c579ba37c7c3e58b35a996dfbc
-  data.tar.gz: a9c5e1f01acc0c60165a13adc1af087743a60935
+SHA256:
+  metadata.gz: e2b04473235c5ed2c2764f62a627fa6f16816c36e0fcff3497be229f8666a0f7
+  data.tar.gz: 9367b0082f31e9cb208d9f97ed6cb67d5276a459562809460694602339dfdaad
 SHA512:
-  metadata.gz: 33338f8fcf3c180ea346548061598953842358a21acd6d97bf451c07d8655f179af0cf7b7791f7c9de1a8411578e3623faab178b3cd74893aaf6d040a7abde96
-  data.tar.gz: 50035b920f6811eed88c318c17b47bf8823aa1ac4bf114af3bc29174edcf08ebd5d16902177aa6a48b70f8e70a745249bb8494101f9f310f24d5f5d5bbc13f27
+  metadata.gz: cd42f7a0b8830a2f01703dca10ae779b973566ad25e3b74d31dc3693977fa5b2b3442e47bc1a3b50723bae3bb9f31facd923f1eaba06b51cc8b927e7fb207cf3
+  data.tar.gz: 38ecb026b0ad5a1985d88349a839a9d2972f85596504e6f300686f9751169a3c8d62582e79119106085a9cadc066517206da117993c3a30f48a5a0c58f256b4c

data/.travis.yml

@@ -0,0 +1,8 @@
+language: ruby
+cache: bundler
+before_install:
+  - gem update bundler
+rvm:
+  - 2.5.8
+  - 2.7.2
+  - 3.0.0

data/CHANGELOG.md

@@ -1,3 +1,26 @@
+### 1.0.5
+
+* Support string or io input via `SimpleXlsxReader#parse` (@kalsan, @til)
+
+### 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]
+* Better support for non-excel-generated xlsx files [bwlang]
+  * 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
 
 * Add support for the 1904 date system [zilverline]

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.
@@ -35,14 +35,21 @@ Here's the totality of the public api, in code:
 
     module SimpleXlsxReader
       def self.open(file_path)
-        Document.new(file_path).tap(&:sheets)
+        Document.new(file_path: file_path).tap(&:sheets)
+      end
+
+      def self.parse(string_or_io)
+        Document.new(string_or_io: string_or_io).tap(&:sheets)
       end
 
       class Document
-        attr_reader :file_path
+        attr_reader :string_or_io
+
+        def initialize(legacy_file_path = nil, file_path: nil, string_or_io: nil)
+          ((file_path || legacy_file_path).nil? ^ string_or_io.nil?) ||
+            fail(ArgumentError, 'either file_path or string_or_io must be provided')
 
-        def initialize(file_path)
-          @file_path = file_path
+          @string_or_io = string_or_io || File.new(file_path || legacy_file_path)
         end
 
         def sheets
@@ -54,7 +61,7 @@ Here's the totality of the public api, in code:
         end
 
         def xml
-          Xml.load(file_path)
+          Xml.load(string_or_io)
         end
 
         class Sheet < Struct.new(:name, :rows)

data/lib/simple_xlsx_reader/version.rb

@@ -1,3 +1,3 @@
 module SimpleXlsxReader
-  VERSION = "1.0.1"
+  VERSION = "1.0.5"
 end

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
@@ -26,14 +53,21 @@ module SimpleXlsxReader
   end
 
   def self.open(file_path)
-    Document.new(file_path).tap(&:sheets)
+    Document.new(file_path: file_path).tap(&:sheets)
+  end
+
+  def self.parse(string_or_io)
+    Document.new(string_or_io: string_or_io).tap(&:sheets)
   end
 
   class Document
-    attr_reader :file_path
+    attr_reader :string_or_io
+
+    def initialize(legacy_file_path = nil, file_path: nil, string_or_io: nil)
+      ((file_path || legacy_file_path).nil? ^ string_or_io.nil?) ||
+        fail(ArgumentError, 'either file_path or string_or_io must be provided')
 
-    def initialize(file_path)
-      @file_path = file_path
+      @string_or_io = string_or_io || File.new(file_path || legacy_file_path)
     end
 
     def sheets
@@ -45,7 +79,7 @@ module SimpleXlsxReader
     end
 
     def xml
-      Xml.load(file_path)
+      Xml.load(string_or_io)
     end
 
     class Sheet < Struct.new(:name, :rows)
@@ -69,28 +103,54 @@ 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)
+      def self.load(string_or_io)
         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
-            if zip.file.file?('xl/sharedStrings.xml')
-              xml.shared_strings = Nokogiri::XML(zip.read('xl/sharedStrings.xml')).remove_namespaces!
-            end
-
+          SimpleXlsxReader::Zip.open_buffer(string_or_io) do |zip|
             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
@@ -105,7 +165,7 @@ 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
 
@@ -121,9 +181,10 @@ 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|
@@ -148,10 +209,21 @@ 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
@@ -218,11 +290,13 @@ module SimpleXlsxReader
       # 'ABA' = 26 * 26 * 1 + 26 * 2  + 1
       # 'BZA' = 26 * 26 * 2 + 26 * 26 + 1
       def column_letter_to_number(column_letter)
-        pow = -1
-        column_letter.codepoints.reverse.inject(0) do |acc, charcode|
-          pow += 1
-          acc + 26**pow * (charcode - 64)
+        pow = column_letter.length - 1
+        result = 0
+        column_letter.each_byte do |b|
+          result += 26**pow * (b - 64)
+          pow -= 1
         end
+        result
       end
 
       # Excel doesn't record types for some cells, only its display style, so
@@ -241,21 +315,32 @@ module SimpleXlsxReader
       # type.
       def style_types
         @style_types ||=
-          xml.styles.xpath('/styleSheet/cellXfs/xf').map {|xstyle|
-            style_type_by_num_fmt_id(xstyle.attributes['numFmtId'].value)}
+            xml.styles.xpath('/styleSheet/cellXfs/xf').map {|xstyle|
+              style_type_by_num_fmt_id(num_fmt_id(xstyle))}
+      end
+
+      #returns the numFmtId value if it's available
+      def num_fmt_id(xstyle)
+        if xstyle.attributes['numFmtId']
+          xstyle.attributes['numFmtId'].value
+        else
+          nil
+        end
       end
 
       # Finds the type we think a style is; For example, fmtId 14 is a date
-      # style, so this would return :date
+      # style, so this would return :date.
+      #
+      # Note, custom styles usually (are supposed to?) have a numFmtId >= 164,
+      # but in practice can sometimes be simply out of the usual "Any Language"
+      # id range that goes up to 49. For example, I have seen a numFmtId of
+      # 59 specified as a date. In Thai, 59 is a number format, so this seems
+      # like a bad idea, but we try to be flexible and just go with it.
       def style_type_by_num_fmt_id(id)
         return nil if id.nil?
 
         id = id.to_i
-        if id >= 164 # custom style, arg!
-          custom_style_types[id]
-        else # we should know this one
-          NumFmtMap[id]
-        end
+        NumFmtMap[id] || custom_style_types[id]
       end
 
       # Map of (numFmtId >= 164) (custom styles) to our best guess at the type
@@ -314,7 +399,7 @@ module SimpleXlsxReader
           type = style
         end
 
-        case type
+        casted = case type
 
         ##
         # There are few built-in types
@@ -347,15 +432,15 @@ 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
-          days_since_date_system_start, fraction_of_24 = value.split('.')
+          value = Float(value)
+          days_since_date_system_start = value.to_i
+          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) + Integer(days_since_date_system_start)
-
-          if fraction_of_24 # there is a time associated
-            fraction_of_24 = "0.#{fraction_of_24}".to_f
-            seconds        = (fraction_of_24 * 86400).round
+          date = options.fetch(:base_date, DATE_SYSTEM_1900) + days_since_date_system_start
 
+          if fraction_of_24 > 0 # there is a time associated
+            seconds = (fraction_of_24 * 86400).round
             return Time.utc(date.year, date.month, date.day) + seconds
           else
             return date
@@ -374,6 +459,12 @@ 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/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/date1904_test.rb

@@ -1,4 +1,4 @@
-require 'test_helper'
+require_relative 'test_helper'
 
 describe SimpleXlsxReader do
   let(:date1904_file) { File.join(File.dirname(__FILE__), 'date1904.xlsx') }

data/test/datetime_test.rb

@@ -1,4 +1,4 @@
-require 'test_helper'
+require_relative 'test_helper'
 
 describe SimpleXlsxReader do
   let(:datetimes_file) { File.join(File.dirname(__FILE__),
@@ -11,7 +11,8 @@ describe SimpleXlsxReader do
       "Datetimes" =>
         [[Time.parse("2013-08-19 18:29:59 UTC")],
          [Time.parse("2013-08-19 18:30:00 UTC")],
-         [Time.parse("2013-08-19 18:30:01 UTC")]]
+         [Time.parse("2013-08-19 18:30:01 UTC")],
+         [Time.parse("1899-12-30 00:30:00 UTC")]]
     })
   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/lower_case_sharedstrings_test.rb

@@ -0,0 +1,15 @@
+require_relative 'test_helper'
+
+describe SimpleXlsxReader do
+  let(:lower_case_shared_strings) { File.join(File.dirname(__FILE__),
+                                                'lower_case_sharedstrings.xlsx') }
+
+  let(:subject) { SimpleXlsxReader::Document.new(lower_case_shared_strings) }
+
+
+  describe '#to_hash' do
+    it 'should have the word Well in the first row' do
+      subject.sheets.first.rows[0].must_include('Well')
+    end
+  end
+end

data/test/performance_test.rb

@@ -1,4 +1,4 @@
-require 'test_helper'
+require_relative 'test_helper'
 require 'minitest/benchmark'
 
 describe 'SimpleXlsxReader Benchmark' do
@@ -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

@@ -1,26 +1,66 @@
-require 'test_helper'
+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') }
-
-  let(:subject) { SimpleXlsxReader::Document.new(sesame_street_blog_file) }
-
-  describe '#to_hash' do
-    it 'reads an xlsx file into a hash of {[sheet name] => [data]}' do
-      subject.to_hash.must_equal({
-        "Authors"=>
-          [["Name", "Occupation"],
-           ["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]]
-      })
+  let(:sesame_street_blog_file_path) { File.join(File.dirname(__FILE__), 'sesame_street_blog.xlsx') }
+  let(:sesame_street_blog_io) { File.new(sesame_street_blog_file_path) }
+  let(:expected_result) do
+    {
+      "Authors"=>
+        [["Name", "Occupation"],
+          ["Big Bird", "Teacher"]],
+      "Posts"=>
+        [["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
+
+  describe SimpleXlsxReader do
+    describe 'load from file path' do
+      let(:subject) { SimpleXlsxReader.open(sesame_street_blog_file_path) }
+
+      it 'reads an xlsx file into a hash of {[sheet name] => [data]}' do
+        subject.to_hash.must_equal(expected_result)
+      end
+    end
+
+    describe 'load from buffer' do
+      let(:subject) { SimpleXlsxReader.parse(sesame_street_blog_io) }
+
+      it 'reads an xlsx buffer into a hash of {[sheet name] => [data]}' do
+        subject.to_hash.must_equal(expected_result)
+      end
+    end
+  end
+
+  describe SimpleXlsxReader::Document do
+    describe 'load from file path' do
+      let(:subject) { SimpleXlsxReader::Document.new(file_path: sesame_street_blog_file_path) }
+
+      it 'reads an xlsx file into a hash of {[sheet name] => [data]}' do
+        subject.to_hash.must_equal(expected_result)
+      end
+    end
+
+    describe 'load from buffer' do
+      let(:subject) { SimpleXlsxReader::Document.new(string_or_io: sesame_street_blog_io) }
+
+      it 'reads an xlsx buffer into a hash of {[sheet name] => [data]}' do
+        subject.to_hash.must_equal(expected_result)
+      end
+    end
+
+    describe 'load from file path (legacy API)' do
+      let(:subject) { SimpleXlsxReader::Document.new(sesame_street_blog_file_path) }
+
+      it 'reads an xlsx file into a hash of {[sheet name] => [data]}' do
+        subject.to_hash.must_equal(expected_result)
+      end
     end
   end
 
@@ -63,10 +103,33 @@ 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
@@ -102,6 +165,13 @@ describe SimpleXlsxReader do
 
       it 'reads custom formatted styles (numFmtId >= 164)' do
         mapper.style_types[1].must_equal :date_time
+        mapper.custom_style_types[164].must_equal :date_time
+      end
+
+      # something I've seen in the wild; don't think it's correct, but let's be flexible.
+      it 'reads custom formatted styles given an id < 164, but not explicitly defined in the SpreadsheetML spec' do
+        mapper.style_types[2].must_equal :date_time
+        mapper.custom_style_types[59].must_equal :date_time
       end
     end
 
@@ -246,16 +316,55 @@ 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
+
+    describe "missing numFmtId attributes" do
+
+      let(:xml) do
+        SimpleXlsxReader::Document::Xml.new.tap do |xml|
+          xml.sheets = [Nokogiri::XML(
+                            <<-XML
+            <worksheet xmlns="http://schemas.openxmlformats.org/spreadsheetml/2006/main">
+              <dimension ref="A1:A1" />
+              <sheetData>
+                <row>
+                  <c r='A1' s='s'>
+                    <v>some content</v>
+                  </c>
+                </row>
+              </sheetData>
+            </worksheet>
+                        XML
+                        ).remove_namespaces!]
+
+          xml.styles = Nokogiri::XML(
+              <<-XML
+            <styleSheet xmlns="http://schemas.openxmlformats.org/spreadsheetml/2006/main">
+
+            </styleSheet>
+          XML
+          ).remove_namespaces!
+        end
+      end
+
+      before do
+        @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
+        @row[0].must_equal 'some content'
+      end
+
     end
 
     describe 'parsing types' do
@@ -284,8 +393,21 @@ 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!]
@@ -303,11 +425,28 @@ 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
@@ -341,6 +480,18 @@ 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
@@ -389,7 +540,7 @@ 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

data/test/styles.xml

@@ -1,6 +1,7 @@
 <?xml version="1.0" encoding="UTF-8" standalone="yes"?>
 <styleSheet xmlns="http://schemas.openxmlformats.org/spreadsheetml/2006/main" xmlns:mc="http://schemas.openxmlformats.org/markup-compatibility/2006" xmlns:x14ac="http://schemas.microsoft.com/office/spreadsheetml/2009/9/ac" mc:Ignorable="x14ac">
-  <numFmts count="1">
+  <numFmts count="2">
+    <numFmt numFmtId="59" formatCode="dd/mm/yyyy"/>
     <numFmt numFmtId="164" formatCode="[$-409]m/d/yy\ h:mm\ AM/PM;@"/>
   </numFmts>
   <fonts count="3" x14ac:knownFonts="1">
@@ -50,9 +51,10 @@
     <xf numFmtId="0" fontId="1" fillId="0" borderId="0" applyNumberFormat="0" applyFill="0" applyBorder="0" applyAlignment="0" applyProtection="0"/>
     <xf numFmtId="0" fontId="2" fillId="0" borderId="0" applyNumberFormat="0" applyFill="0" applyBorder="0" applyAlignment="0" applyProtection="0"/>
   </cellStyleXfs>
-  <cellXfs count="3">
+  <cellXfs count="4">
     <xf numFmtId="0" fontId="0" fillId="0" borderId="0" xfId="0"/>
     <xf numFmtId="164" fontId="0" fillId="0" borderId="0" xfId="0" applyNumberFormat="1"/>
+    <xf numFmtId="59" fontId="0" fillId="0" borderId="0" xfId="0" applyNumberFormat="1"/>
     <xf numFmtId="1" fontId="0" fillId="0" borderId="0" xfId="0" applyNumberFormat="1"/>
   </cellXfs>
   <cellStyles count="3">

data/test/test_helper.rb

@@ -2,6 +2,7 @@ gem 'minitest'
 require 'minitest/autorun'
 require 'minitest/spec'
 require 'pry'
+require 'time'
 
 $:.unshift File.expand_path("lib")
 require 'simple_xlsx_reader'

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: simple_xlsx_reader
 version: !ruby/object:Gem::Version
-  version: 1.0.1
+  version: 1.0.5
 platform: ruby
 authors:
 - Woody Peterson
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-09-02 00:00:00.000000000 Z
+date: 2022-05-19 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 +101,10 @@ 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
 - test/sesame_street_blog.xlsx
 - test/shared_strings.xml
@@ -93,7 +112,8 @@ files:
 - test/styles.xml
 - test/test_helper.rb
 homepage: ''
-licenses: []
+licenses:
+- MIT
 metadata: {}
 post_install_message: 
 rdoc_options: []
@@ -110,8 +130,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.2.0
+rubygems_version: 3.1.6
 signing_key: 
 specification_version: 4
 summary: Read xlsx data the Ruby way
@@ -120,6 +139,10 @@ 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
 - test/sesame_street_blog.xlsx
 - test/shared_strings.xml