simple_xlsx_reader 2.0.1 → 3.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 20c74bef372629ffb807d50df274c90682e17d53eed296a1e05fbb99533d4a8e
-  data.tar.gz: 9c4311913e79ad139414a4fe064d89fb246a1d46f30b7736c87f049985801660
+  metadata.gz: 1f51a4ca0ca865cc2a9ddebeb72fa3db9cc3f309ce2d1a3d34a492f09e22789c
+  data.tar.gz: 90a2b1ac9071fcef0797f5839652d919169cfcf6862de8926b7b605dcc53cd7e
 SHA512:
-  metadata.gz: 18db8595a36d4d9bb0f1dfee5da58753b799a6358530dfb9436f9c7b72e8e06bb9101d86d8dc617669c075fced44db8c24fdca6c5a3b2cb6b908cc0cd645eeb1
-  data.tar.gz: 23d4b057060c5f66ad3d57d0d65fa6e127ed4c7faa622ec0d236b58dd439179b41dff041ec2dd955c2ec893d577d9660465d2dcea0fe9a9f3af5e911ac5aa8e7
+  metadata.gz: 38f0844bfa6e30cd9af9414057a767cc3bd7cf6ed11023a7306b18686ad3cb250a70191d9b77f8cbc2a590aaa24f822cbec6c546f667fe6e820bb356ddd369f9
+  data.tar.gz: 69af022e15fa95404ab0208be1b4b6661ae14033c73477b98b78f01795712313d63952dce0674ba34ee3aecc19105ef28adfa708de738682583f3b672668a251

data/CHANGELOG.md

@@ -1,3 +1,20 @@
+### 3.0.1
+
+* Fix parsing "chunky" UTF-8 workbooks. Closes issues #39 and #45. See ce67f0d4.
+
+### 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)

data/lib/simple_xlsx_reader/loader/sheet_parser.rb

@@ -77,7 +77,7 @@ module SimpleXlsxReader
 
         return unless @capture
 
-        @current_row[cell_idx] =
+        captured =
           begin
             SimpleXlsxReader::Loader.cast(
               string.strip, @type, @style,
@@ -102,6 +102,17 @@ module SimpleXlsxReader
               string.strip
             end
           end
+
+
+        # For some reason I can't figure out in a reasonable timeframe,
+        # SAX parsing some workbooks captures separate strings in the same cell
+        # when we encounter UTF-8, although I can't get workbooks made in my
+        # own version of excel to repro it. Our fix is just to keep building
+        # the string in this case, although maybe there's a setting in Nokogiri
+        # to make it not do this (looked, couldn't find it).
+        #
+        # Loading the workbook test/chunky_utf8.xlsx repros the issue.
+        @captured = @captured ? @captured + captured : captured
       end
 
       def end_element(name)
@@ -134,7 +145,10 @@ module SimpleXlsxReader
           # isn't the most robust strategy, but it likely fits 99% of use cases
           # considering it's not a problem with actual excel docs.
           @dimension = "A1:#{@cell_name}" if @dimension.nil?
-        when 'v', 't' then @capture = false
+        when 'v', 't'
+          @current_row[cell_idx] = @captured
+          @capture = false
+          @captured = nil
         when 'f' then @function = false
         when 'c' then @url = nil
         end

data/lib/simple_xlsx_reader/loader.rb

@@ -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 = '2.0.1'
+  VERSION = '3.0.1'
 end

data/test/simple_xlsx_reader_test.rb

@@ -827,6 +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>
 
@@ -925,6 +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
@@ -936,7 +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">
@@ -967,13 +975,44 @@ 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
+
+  describe 'with mysteriously chunky UTF-8 text' do
+    let(:chunky_utf8_path) do
+      File.join(File.dirname(__FILE__), 'chunky_utf8.xlsx')
+    end
+
+    let(:sheet) { SimpleXlsxReader.open(chunky_utf8_path).sheets[0] }
+
+    it 'reads the whole cell text' do
+      _(sheet.rows.slurp[1]).must_equal(
+        ["sample-company-1", "Korntal-Münchingen", "Bronholmer straße"]
+      )
+    end
+  end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: simple_xlsx_reader
 version: !ruby/object:Gem::Version
-  version: 2.0.1
+  version: 3.0.1
 platform: ruby
 authors:
 - Woody Peterson
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-03-01 00:00:00.000000000 Z
+date: 2023-03-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -105,6 +105,7 @@ files:
 - lib/simple_xlsx_reader/loader/workbook_parser.rb
 - lib/simple_xlsx_reader/version.rb
 - simple_xlsx_reader.gemspec
+- test/chunky_utf8.xlsx
 - test/date1904.xlsx
 - test/date1904_test.rb
 - test/datetime_test.rb
@@ -113,6 +114,7 @@ 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
@@ -144,6 +146,7 @@ signing_key:
 specification_version: 4
 summary: Read xlsx data the Ruby way
 test_files:
+- test/chunky_utf8.xlsx
 - test/date1904.xlsx
 - test/date1904_test.rb
 - test/datetime_test.rb
@@ -152,6 +155,7 @@ 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