simple_xlsx_reader 3.0.0 → 4.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 5449525d4e46a013f92e8406a2ec2d07b06bb795efc7c8d76b9ffbcace22a38f
-  data.tar.gz: 5c664baa8d88692767f5bb6d2879e24c27098206695b88da42f3bc0d30bb9bce
+  metadata.gz: d60e969d7d2db69578d543b6ebab36d29b3e3e88b4d62d67d00218b09b644cc5
+  data.tar.gz: 36e12c7d95b6319f8f3bb565a1bc1b8eea6d1ca44928b3188a6892bf1f0c6513
 SHA512:
-  metadata.gz: 90d5fedde0aa4cc2bcb8b4d9134859890bbf4357efbf6ba9aa0aaf3bd21ad1cd9f54a279d1126938a300dee36fbb8a10d63b66f945c9f7eeb8edc880bb23327a
-  data.tar.gz: ab684cc09075a0b9a1054c045bf4202718159b258c87f62b10e18aafa4faaa7a527ba95f8e765f7609ab7ba24c43a31176906ecefd612c85badbdefee9164184
+  metadata.gz: 6610958e6cb393e6013d303dd541f80a19d91415f6ebbe1d03162b52580ac361ad3f7e8e9fef5904a1daae72fe0774a5a83f47617c75ac185748c78e2c828e5a
+  data.tar.gz: f556a9d31d48aa7cfeb0a1a9194736f2740ae3a2c868ed6a65fc197411351b28751d9caa72fd2bbbeb7eb22acd9ba0e2d53606f414bd36843f811ccb93d80ed2

data/CHANGELOG.md

@@ -1,3 +1,16 @@
+### 4.0.0
+
+* Fix percentage rounding errors. Previously we were dividing by 100, when we
+  actually don't need to, so percentage types were 100x too small. Fixes #21.
+  Major bump because workarounds might have been implemented for previous
+  incorrect behavior.
+* Fix small oddity in one currency format where round numbers would be cast
+  to an integer instead of a float.
+
+### 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 +102,16 @@ 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 +144,10 @@ 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/style_types_parser.rb

@@ -9,38 +9,39 @@ module SimpleXlsxReader
 
       # Map of non-custom numFmtId to casting symbol
       NumFmtMap = {
-        0 => :string,         # General
-        1 => :fixnum,         # 0
-        2 => :float,          # 0.00
-        3 => :fixnum,         # #,##0
-        4 => :float,          # #,##0.00
-        5 => :unsupported,    # $#,##0_);($#,##0)
-        6 => :unsupported,    # $#,##0_);[Red]($#,##0)
-        7 => :unsupported,    # $#,##0.00_);($#,##0.00)
-        8 => :unsupported,    # $#,##0.00_);[Red]($#,##0.00)
-        9 => :percentage,     # 0%
-        10 => :percentage,     # 0.00%
-        11 => :bignum,         # 0.00E+00
-        12 => :unsupported,    # # ?/?
-        13 => :unsupported,    # # ??/??
-        14 => :date,           # mm-dd-yy
-        15 => :date,           # d-mmm-yy
-        16 => :date,           # d-mmm
-        17 => :date,           # mmm-yy
-        18 => :time,           # h:mm AM/PM
-        19 => :time,           # h:mm:ss AM/PM
-        20 => :time,           # h:mm
-        21 => :time,           # h:mm:ss
-        22 => :date_time,      # m/d/yy h:mm
-        37 => :unsupported,    # #,##0 ;(#,##0)
-        38 => :unsupported,    # #,##0 ;[Red](#,##0)
-        39 => :unsupported,    # #,##0.00;(#,##0.00)
-        40 => :unsupported,    # #,##0.00;[Red](#,##0.00)
-        45 => :time,           # mm:ss
-        46 => :time,           # [h]:mm:ss
-        47 => :time,           # mmss.0
-        48 => :bignum,         # ##0.0E+0
-        49 => :unsupported     # @
+        0 => :string,        # General
+        1 => :fixnum,        # 0
+        2 => :float,         # 0.00
+        3 => :fixnum,        # #,##0
+        4 => :float,         # #,##0.00
+        5 => :unsupported,   # $#,##0_);($#,##0)
+        6 => :unsupported,   # $#,##0_);[Red]($#,##0)
+        7 => :unsupported,   # $#,##0.00_);($#,##0.00)
+        8 => :unsupported,   # $#,##0.00_);[Red]($#,##0.00)
+        9 => :percentage,    # 0%
+        10 => :percentage,   # 0.00%
+        11 => :bignum,       # 0.00E+00
+        12 => :unsupported,  # # ?/?
+        13 => :unsupported,  # # ??/??
+        14 => :date,         # mm-dd-yy
+        15 => :date,         # d-mmm-yy
+        16 => :date,         # d-mmm
+        17 => :date,         # mmm-yy
+        18 => :time,         # h:mm AM/PM
+        19 => :time,         # h:mm:ss AM/PM
+        20 => :time,         # h:mm
+        21 => :time,         # h:mm:ss
+        22 => :date_time,    # m/d/yy h:mm
+        37 => :unsupported,  # #,##0 ;(#,##0)
+        38 => :unsupported,  # #,##0 ;[Red](#,##0)
+        39 => :unsupported,  # #,##0.00;(#,##0.00)
+        40 => :unsupported,  # #,##0.00;[Red](#,##0.00)
+        44 => :float,        # some odd currency format ?from Office 2007?
+        45 => :time,         # mm:ss
+        46 => :time,         # [h]:mm:ss
+        47 => :time,         # mmss.0
+        48 => :bignum,       # ##0.0E+0
+        49 => :unsupported   # @
       }.freeze
 
       def parse

data/lib/simple_xlsx_reader/loader.rb

@@ -162,7 +162,7 @@ module SimpleXlsxReader
         when :float
           value.to_f
         when :percentage
-          value.to_f / 100
+          value.to_f
         # the trickiest. note that  all these formats can vary on
         # whether they actually contain a date, time, or datetime.
         when :date, :time, :date_time

data/lib/simple_xlsx_reader/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module SimpleXlsxReader
-  VERSION = '3.0.0'
+  VERSION = '4.0.0'
 end

data/test/simple_xlsx_reader_test.rb

@@ -1001,4 +1001,35 @@ 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
+
+  describe 'when using percentages & currencies' do
+    let(:pnc_path) do
+      # This file provided by a GitHub user having parse errors in these fields
+      File.join(File.dirname(__FILE__), 'percentages_n_currencies.xlsx')
+    end
+
+    let(:sheet) { SimpleXlsxReader.open(pnc_path).sheets[0] }
+
+    it 'reads percentages as floats of the form 0.XX' do
+      _(sheet.rows.slurp[1][2]).must_equal(0.87)
+    end
+
+    it 'reads currencies as floats' do
+      _(sheet.rows.slurp[1][4]).must_equal(300.0)
+    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: 4.0.0
 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
@@ -114,6 +115,7 @@ files:
 - test/lower_case_sharedstrings.xlsx
 - test/lower_case_sharedstrings_test.rb
 - test/misc_numbers.xlsx
+- test/percentages_n_currencies.xlsx
 - test/performance_test.rb
 - test/sesame_street_blog.xlsx
 - test/shared_strings.xml
@@ -145,6 +147,7 @@ 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
@@ -154,6 +157,7 @@ test_files:
 - test/lower_case_sharedstrings.xlsx
 - test/lower_case_sharedstrings_test.rb
 - test/misc_numbers.xlsx
+- test/percentages_n_currencies.xlsx
 - test/performance_test.rb
 - test/sesame_street_blog.xlsx
 - test/shared_strings.xml