simple_xlsx_reader 2.0.0 → 3.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 979490ce3bd7f0482879fb5fb5465e10ad1b07c1488d0a544950131d9063050a
-  data.tar.gz: 412d0040a586cc5ee4acdd4a2f74dd74f3bf9eb781a35d8a36c12f6caadc566c
+  metadata.gz: 5449525d4e46a013f92e8406a2ec2d07b06bb795efc7c8d76b9ffbcace22a38f
+  data.tar.gz: 5c664baa8d88692767f5bb6d2879e24c27098206695b88da42f3bc0d30bb9bce
 SHA512:
-  metadata.gz: 00c01bc0c2a393eb35e458411dfeab55b8bf30cee2661324cbd97a175baf0ceb31a881b1b2b7bd668a2b475ff008372c1428908340e30769308884355fdd46e8
-  data.tar.gz: 81b1b26806a97c56710cab64aa22212985dea82b308e2fbba6835f4ea7a69b79067268bb13537999594dc5722928f1df235938355a7d4a51b58ae7ed4af1d093
+  metadata.gz: 90d5fedde0aa4cc2bcb8b4d9134859890bbf4357efbf6ba9aa0aaf3bd21ad1cd9f54a279d1126938a300dee36fbb8a10d63b66f945c9f7eeb8edc880bb23327a
+  data.tar.gz: ab684cc09075a0b9a1054c045bf4202718159b258c87f62b10e18aafa4faaa7a527ba95f8e765f7609ab7ba24c43a31176906ecefd612c85badbdefee9164184

data/.github/workflows/ruby.yml

@@ -22,15 +22,12 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        ruby-version: ['2.6', '2.7', '3.0']
+        ruby-version: ['2.6', '2.7', '3.0', '3.1', '3.2']
 
     steps:
     - uses: actions/checkout@v3
     - name: Set up Ruby
-    # To automatically get bug fixes and new Ruby versions for ruby/setup-ruby,
-    # change this to (see https://github.com/ruby/setup-ruby#versioning):
-    # uses: ruby/setup-ruby@v1
-      uses: ruby/setup-ruby@2b019609e2b0f1ea1a2bc8ca11cb82ab46ada124
+      uses: ruby/setup-ruby@v1
       with:
         ruby-version: ${{ matrix.ruby-version }}
         bundler-cache: true # runs 'bundle install' and caches installed gems automatically

data/CHANGELOG.md

@@ -1,3 +1,21 @@
+### 3.0.0
+
+* Change the way we typecast cells in the General format. This probably won't
+  break anything in your app, but it's a change in behavior that theoretically
+  could.
+
+  Previously, we were treating cells using General the format as strings, when
+  according to the Office XML standard, they should be treated as numbers. We
+  now attempt to cast such cells as numbers, and fall back to strings if number
+  casting fails.
+
+  Thanks @jrodrigosm
+
+### 2.0.1
+
+* Restore ability to parse IO strings (@robbevp)
+* Add Ruby 3.1 and 3.2 to CI (@taichi-ishitani)
+
 ### 2.0.0
 
 * SPEED

data/lib/simple_xlsx_reader/document.rb

@@ -8,14 +8,16 @@ module SimpleXlsxReader
   # Main class for the public API. See the README for usage examples,
   # or read the code, it's pretty friendly.
   class Document
-    attr_reader :file_path
+    attr_reader :string_or_io
 
-    def initialize(file_path)
-      @file_path = file_path
+    def initialize(legacy_file_path = nil, file_path: nil, string_or_io: nil)
+      fail(ArgumentError, 'either file_path or string_or_io must be provided') if legacy_file_path.nil? && file_path.nil? && string_or_io.nil?
+  
+      @string_or_io = string_or_io || File.new(legacy_file_path || file_path)
     end
 
     def sheets
-      @sheets ||= Loader.new(file_path).init_sheets
+      @sheets ||= Loader.new(string_or_io).init_sheets
     end
 
     # Expensive because it slurps all the sheets into memory,

data/lib/simple_xlsx_reader/loader.rb

@@ -1,12 +1,12 @@
 # frozen_string_literal: true
 
 module SimpleXlsxReader
-  class Loader < Struct.new(:file_path)
+  class Loader < Struct.new(:string_or_io)
     attr_accessor :shared_strings, :sheet_parsers, :sheet_toc, :style_types, :base_date
 
     def init_sheets
       ZipReader.new(
-        file_path: file_path,
+        string_or_io: string_or_io,
         loader: self
       ).read
 
@@ -19,12 +19,12 @@ module SimpleXlsxReader
       end
     end
 
-    ZipReader = Struct.new(:file_path, :loader, keyword_init: true) do
+    ZipReader = Struct.new(:string_or_io, :loader, keyword_init: true) do
       attr_reader :zip
 
       def initialize(*args)
         super
-        @zip = SimpleXlsxReader::Zip.open(file_path)
+        @zip = SimpleXlsxReader::Zip.open_buffer(string_or_io)
       end
 
       def read
@@ -149,7 +149,13 @@ module SimpleXlsxReader
         # detected earlier and cast here by its standardized symbol
         ##
 
-        when :string, :unsupported
+        # no type encoded with the the General format defaults to a number type
+        when nil, :string
+          retval = Integer(value, exception: false)
+          retval ||= Float(value, exception: false)
+          retval ||= value
+          retval
+        when :unsupported
           value
         when :fixnum
           value.to_i

data/lib/simple_xlsx_reader/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module SimpleXlsxReader
-  VERSION = '2.0.0'
+  VERSION = '3.0.0'
 end

data/lib/simple_xlsx_reader.rb

@@ -42,8 +42,11 @@ module SimpleXlsxReader
     end
 
     def open(file_path)
-      Document.new(file_path).tap(&:sheets)
+      Document.new(file_path: file_path).tap(&:sheets)
+    end
+    
+    def parse(string_or_io)
+      Document.new(string_or_io: string_or_io).tap(&:sheets)
     end
-    alias parse open
   end
 end

data/test/simple_xlsx_reader_test.rb

@@ -18,6 +18,7 @@ describe SimpleXlsxReader do
 
   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(:sesame_street_blog_string) { IO.read(sesame_street_blog_file_path) }
 
   let(:expected_result) do
     {
@@ -54,6 +55,14 @@ describe SimpleXlsxReader do
       end
     end
 
+    describe 'load from string' do
+      let(:subject) { SimpleXlsxReader.parse(sesame_street_blog_io) }
+
+      it 'reads an xlsx string into a hash of {[sheet name] => [data]}' do
+        _(subject.to_hash).must_equal(expected_result)
+      end
+    end
+
     it 'outputs strings in UTF-8 encoding' do
       document = SimpleXlsxReader.parse(sesame_street_blog_io)
       _(document.sheets[0].rows.to_a.flatten.map(&:encoding).uniq)
@@ -818,6 +827,10 @@ describe SimpleXlsxReader do
                 <c r='I1' s='0'>
                   <v>GUI-made hyperlink</v>
                 </c>
+
+                <c r='J1' s='0'>
+                  <v>1</v>
+                </c>
               </row>
             </sheetData>
 
@@ -916,6 +929,10 @@ describe SimpleXlsxReader do
         )
       )
     end
+    
+    it "reads 'Generic' cells with numbers as numbers" do
+      _(@row[9]).must_equal 1
+    end
   end
 
   describe 'parsing documents with blank rows' do
@@ -927,7 +944,7 @@ describe SimpleXlsxReader do
             <sheetData>
             <row r="2" spans="1:1">
               <c r="A2" s="0">
-                <v>0</v>
+                <v>a</v>
               </c>
             </row>
             <row r="4" spans="1:1">
@@ -958,13 +975,30 @@ describe SimpleXlsxReader do
     it 'reads row data despite gaps in row numbering' do
       _(@rows).must_equal [
         [nil, nil, nil, nil],
-        ['0', nil, nil, nil],
+        ['a', nil, nil, nil],
         [nil, nil, nil, nil],
-        [nil, '1', nil, nil],
-        [nil, nil, '2', nil],
+        [nil, 1, nil, nil],
+        [nil, nil, 2, nil],
         [nil, nil, nil, nil],
-        [nil, nil, nil, '3']
+        [nil, nil, nil, 3]
       ]
     end
   end
+
+  # https://support.microsoft.com/en-us/office/available-number-formats-in-excel-0afe8f52-97db-41f1-b972-4b46e9f1e8d2
+  describe 'numeric fields styled as "General"' do
+    let(:misc_numbers_path) do
+      File.join(File.dirname(__FILE__), 'misc_numbers.xlsx')
+    end
+
+    let(:sheet) { SimpleXlsxReader.open(misc_numbers_path).sheets[0] }
+
+    it 'reads medium sized integers as integers' do
+      _(sheet.rows.slurp[1][0]).must_equal 98070
+    end
+
+    it 'reads large (>12 char) integers as integers' do
+      _(sheet.rows.slurp[1][1]).must_equal 1234567890123
+    end
+  end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: simple_xlsx_reader
 version: !ruby/object:Gem::Version
-  version: 2.0.0
+  version: 3.0.0
 platform: ruby
 authors:
 - Woody Peterson
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2022-08-18 00:00:00.000000000 Z
+date: 2023-03-01 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -113,6 +113,7 @@ files:
 - test/gdocs_sheet_test.rb
 - test/lower_case_sharedstrings.xlsx
 - test/lower_case_sharedstrings_test.rb
+- test/misc_numbers.xlsx
 - test/performance_test.rb
 - test/sesame_street_blog.xlsx
 - test/shared_strings.xml
@@ -152,6 +153,7 @@ test_files:
 - test/gdocs_sheet_test.rb
 - test/lower_case_sharedstrings.xlsx
 - test/lower_case_sharedstrings_test.rb
+- test/misc_numbers.xlsx
 - test/performance_test.rb
 - test/sesame_street_blog.xlsx
 - test/shared_strings.xml