simple_xlsx_reader 3.0.0 → 3.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 5449525d4e46a013f92e8406a2ec2d07b06bb795efc7c8d76b9ffbcace22a38f
-  data.tar.gz: 5c664baa8d88692767f5bb6d2879e24c27098206695b88da42f3bc0d30bb9bce
+  metadata.gz: 1f51a4ca0ca865cc2a9ddebeb72fa3db9cc3f309ce2d1a3d34a492f09e22789c
+  data.tar.gz: 90a2b1ac9071fcef0797f5839652d919169cfcf6862de8926b7b605dcc53cd7e
 SHA512:
-  metadata.gz: 90d5fedde0aa4cc2bcb8b4d9134859890bbf4357efbf6ba9aa0aaf3bd21ad1cd9f54a279d1126938a300dee36fbb8a10d63b66f945c9f7eeb8edc880bb23327a
-  data.tar.gz: ab684cc09075a0b9a1054c045bf4202718159b258c87f62b10e18aafa4faaa7a527ba95f8e765f7609ab7ba24c43a31176906ecefd612c85badbdefee9164184
+  metadata.gz: 38f0844bfa6e30cd9af9414057a767cc3bd7cf6ed11023a7306b18686ad3cb250a70191d9b77f8cbc2a590aaa24f822cbec6c546f667fe6e820bb356ddd369f9
+  data.tar.gz: 69af022e15fa95404ab0208be1b4b6661ae14033c73477b98b78f01795712313d63952dce0674ba34ee3aecc19105ef28adfa708de738682583f3b672668a251

data/CHANGELOG.md

@@ -1,3 +1,7 @@
+### 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

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/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module SimpleXlsxReader
-  VERSION = '3.0.0'
+  VERSION = '3.0.1'
 end

data/test/simple_xlsx_reader_test.rb

@@ -1001,4 +1001,18 @@ describe SimpleXlsxReader 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: 3.0.0
+  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
@@ -145,6 +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