xsv 0.3.5 → 0.3.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 4ebd402667e57a9db010846048605e8afa079fcac62a71020857c792446a81ba
-  data.tar.gz: 56702a4f106aa26c9dae4bcca624ca6ba80ccd1287c4e8138469c8215a918333
+  metadata.gz: 4c6b42a947e6f518a9284de8262e1c1327267a6e1fdd55ea6d14fffba1f1b19d
+  data.tar.gz: '04887e8c4e50d3bb5762c6738237442d3b6360f4b96304b5a802215d7f4240ca'
 SHA512:
-  metadata.gz: '02875bc9d2b26fda74f1da6cdfdf1af01d2a0d77735d18cf8c00a5a350bd8f9e2c11129985819f59e8876e51bde140ef163ae18040c251e4caa8fecd420da60f'
-  data.tar.gz: c9bb1f599cd28175792d86cb92d019906c0b39d67bdf2529021a412dcd91a06a7510da0e71d0a186edef9cd4519c0f466f9325941a613211d19e97ecf50f829f
+  metadata.gz: e8ad674f6735a1711190469836f30911bb2ebce502d3e99bc268c1c439c7cf9b8f6841189c76950c1722a0861a769a00b6ee7f15e5ab1cb2763a3d6b05342057
+  data.tar.gz: 07c01bc46762348b87f745fd1c7b3aa9d16c0051916b46473a0c0c76bf4d1551f5d2cabc724a612069f3ce83eb959cbe06f4114bef361e615fc37b9ceae51193

data/README.md

@@ -1,10 +1,18 @@
 # Xsv .xlsx reader
 
-Xsv is a very basic parser for Office Open XML spreadsheet files (.xlsx files)
-that aims to provide feature parity with common CSV readers with high
-performance. This means it only parses values to basic Ruby types and does not
-deal with most formatting or more advanced functionality. The goal is to allow
-for fast parsing of large worksheets with minimal RAM and CPU consumption.
+[![Travis CI](https://img.shields.io/travis/martijn/xsv/master)](https://travis-ci.org/martijn/xsv)
+[![Yard Docs](http://img.shields.io/badge/yard-docs-blue.svg)](https://rubydoc.info/github/martijn/xsv)
+
+Xsv is a fast, lightweight parser for Office Open XML spreadsheet files
+(commonly known as Excel or .xlsx files). It strives to be minimal in the
+sense that it provides nothing a CSV reader wouldn't, meaning it only
+deals with minimal formatting and cannot create or modify documents.
+
+Xsv is designed for worksheets with a single table of data, optionally
+with a header row. It only casts values to basic Ruby types (integer, float,
+date and time) and does not deal with most formatting or more advanced
+functionality. The goal is to allow for fast parsing of large worksheets with
+minimal RAM and CPU consumption.
 
 Xsv stands for 'Excel Separated Values', because Excel just gets in the way.
 
@@ -80,9 +88,9 @@ sheet:
 
 - In array mode, your data starts on the first row
 
-- In has mode the first row of the sheet contains headers, followed by rows of data
+- In hash mode the first row of the sheet contains headers, followed by rows of data
 
-If your data or headers does not start on the first row of the sheet you can
+If your data or headers do not start on the first row of the sheet you can
 tell Xsv to skip a number of rows:
 
 ```ruby

data/lib/xsv/shared_strings_parser.rb

@@ -6,7 +6,7 @@ module Xsv
     def self.parse(io)
       strings = []
       handler = new { |s| strings << s }
-      Ox.sax_parse(handler, io)
+      Ox.sax_parse(handler, io.read)
       return strings
     end
 

data/lib/xsv/sheet.rb

@@ -28,7 +28,7 @@ module Xsv
     # There is no need to create Sheets from application code.
     #
     # @param workbook [Workbook] The Workbook with shared data such as shared strings and styles
-    # @param io [IO] A handle to an open worksheet XML file
+    # @param io [IO] A handle to an open worksheet XML file or a string with the XML contents
     def initialize(workbook, io)
       @workbook = workbook
       @io = io
@@ -45,12 +45,10 @@ module Xsv
     end
 
     # Iterate over rows, returning either hashes or arrays based on the current mode.
-    def each_row
-      @io.rewind
+    def each_row(&block)
+      @io.rewind if @io.respond_to?(:rewind)
 
-      handler = SheetRowsHandler.new(@mode, empty_row, @workbook, @row_skip, @last_row) do |row|
-        yield(row)
-      end
+      handler = SheetRowsHandler.new(@mode, empty_row, @workbook, @row_skip, @last_row, &block)
 
       Ox.sax_parse(handler, @io)
 

data/lib/xsv/sheet_bounds_handler.rb

@@ -17,7 +17,7 @@ module Xsv
         return rows, cols
       end
 
-      sheet.rewind
+      sheet.rewind if sheet.respond_to?(:rewind)
       Ox.sax_parse(handler, sheet)
 
       return rows, cols

data/lib/xsv/sheet_rows_handler.rb

@@ -16,9 +16,7 @@ module Xsv
       when "e" # N/A
         nil
       when nil
-        if @current_value == ""
-          nil
-        elsif @current_cell[:s]
+        if @current_cell[:s]
           style = @workbook.xfs[@current_cell[:s].to_i]
           numFmt = @workbook.numFmts[style[:numFmtId].to_i]
 
@@ -50,7 +48,7 @@ module Xsv
       @current_row = {}
       @current_row_attrs = {}
       @current_cell = {}
-      @current_value = nil
+      @current_value = String.new
       @last_row = last_row
 
       if @mode == :hash
@@ -62,14 +60,14 @@ module Xsv
       case name
       when :c
         @state = name
-        @current_cell = {}
-        @current_value = String.new
+        @current_cell.clear
+        @current_value.clear
       when :v
         @state = name
       when :row
         @state = name
         @current_row = @empty_row.dup
-        @current_row_attrs = {}
+        @current_row_attrs.clear
       else
         @state = nil
       end

data/lib/xsv/styles_handler.rb

@@ -11,7 +11,7 @@ module Xsv
          @numFmts = numFmts
       end
 
-      Ox.sax_parse(handler, io)
+      Ox.sax_parse(handler, io.read)
       return @xfs, @numFmts
     end
 

data/lib/xsv/version.rb

@@ -1,4 +1,4 @@
 # frozen_string_literal: true
 module Xsv
-  VERSION = "0.3.5"
+  VERSION = "0.3.6"
 end

data/lib/xsv/workbook.rb

@@ -80,7 +80,15 @@ module Xsv
       @zip.glob("xl/worksheets/sheet*.xml").sort do |a, b|
         a.name[/\d+/].to_i <=> b.name[/\d+/].to_i
       end.each do |entry|
-        @sheets << Xsv::Sheet.new(self, entry.get_input_stream)
+        # For smaller sheets, memory performance is a lot better if Ox is
+        # handed a string. For larger sheets this leads to awful performance.
+        # This is probably caused by either something in SheetRowsHandler or
+        # the interaction between Zip::InputStream and Ox
+        if entry.size > 100_000_000
+          @sheets << Xsv::Sheet.new(self, entry.get_input_stream)
+        else
+          @sheets << Xsv::Sheet.new(self, entry.get_input_stream.read)
+        end
       end
     end
   end

data/xsv.gemspec

@@ -11,7 +11,7 @@ Gem::Specification.new do |spec|
 
   spec.summary       = "A fast and lightweiggt xlsx parser that provides nothing a CSV parser wouldn't"
   spec.description    = <<-EOF
-                            XSV is a fast, lightweight parser for Office Open XML spreadsheet files
+                            Xsv is a fast, lightweight parser for Office Open XML spreadsheet files
                             (commonly known as Excel or .xlsx files). It strives to be minimal in the
                             sense that it provides nothing a CSV reader wouldn't, meaning it only
                             deals with minimal formatting and cannot create or modify documents.
@@ -42,7 +42,7 @@ Gem::Specification.new do |spec|
   spec.add_dependency "rubyzip", "~> 2.2"
   spec.add_dependency "ox", "~> 2.13"
 
-  spec.add_development_dependency "bundler", "~> 1.17"
+  spec.add_development_dependency "bundler", "< 3"
   spec.add_development_dependency "rake", "~> 13.0"
   spec.add_development_dependency "minitest", "~> 5.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: xsv
 version: !ruby/object:Gem::Version
-  version: 0.3.5
+  version: 0.3.6
 platform: ruby
 authors:
 - Martijn Storck
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2020-03-02 00:00:00.000000000 Z
+date: 2020-03-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rubyzip
@@ -42,16 +42,16 @@ dependencies:
   name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - "<"
       - !ruby/object:Gem::Version
-        version: '1.17'
+        version: '3'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - "<"
       - !ruby/object:Gem::Version
-        version: '1.17'
+        version: '3'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -81,7 +81,7 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '5.0'
 description: |2
-                              XSV is a fast, lightweight parser for Office Open XML spreadsheet files
+                              Xsv is a fast, lightweight parser for Office Open XML spreadsheet files
                               (commonly known as Excel or .xlsx files). It strives to be minimal in the
                               sense that it provides nothing a CSV reader wouldn't, meaning it only
                               deals with minimal formatting and cannot create or modify documents.