xsv 0.3.13 → 0.3.18

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: bdd18155c813e1b242f54bf1b9b5696334ec496058a65ce281950d5971b91450
-  data.tar.gz: efb138a131f1e4799d26d823c3b3ddd45b34add899054d1cf8986b7d9143d26a
+  metadata.gz: 75a753e746b55f6e75f168b41da7ded523a4373fab7ea4d696339efe8e05372e
+  data.tar.gz: 501389046d3a77d87e1287fba7e1d138fb5ca50fdfdbaffce7294e7131506970
 SHA512:
-  metadata.gz: 44a8ac8f904193b9a03db187a6bd7cb292793c1751261e063003d4a8bfcb61233f55c5303b22066dfb7d36f0b7519d238aee6023aa51793f30e0dab33d9f1491
-  data.tar.gz: c1c00561d544eb4666e411fb6b59205ce242394005bdead120ef73e852d0fac03bf6ed929becbe1e819b3f8226535093dc25d42ed3a655dd892c57a2a4890828
+  metadata.gz: f569bae5677287af25722206784cba96057191cf518e868f1db719e53cdbe4dc75135925247f88b15337ea1cc8fb036a89ac0d2ffd88e4d4cebe63285ffa2326
+  data.tar.gz: 5a8b4084ca13108cbd9b3e4dab5eef27456aeb287241b600d65c78d0e0ef2cc5cd8fa54bf9ca3f1015d826d3e9740765f5bb9c3c349ea818591befd18ac5944d

data/.travis.yml

@@ -4,8 +4,7 @@ language: ruby
 cache: bundler
 rvm:
   - 2.5.8
-  - 2.6.5
-  - 2.7.0
+  - 2.7.1
 env:
   - "rubyzip=1.3.0"
   - "rubyzip=2.2.0"

data/CHANGELOG.md

@@ -1,6 +1,28 @@
 # Xsv Changelog
 
-## HEAD
+## 0.3.18 2020-09-30
+
+-  Improve inline string support (#18)
+
+## 0.3.17 2020-07-03
+
+- Fix parsing of empty worksheets (#17)
+
+## 0.3.16 2020-06-03
+
+- Support complex numbers (#16)
+
+## 0.3.15 2020-06-02
+
+- Fix issue with workbooks that don't contain shared strings (#15)
+
+## 0.3.14 2020-05-22
+
+- Allow opening workbooks from Tempfile and anything that responds to #read
+
+- Preserve whitespace in text cells
+
+## 0.3.13 2020-05-12
 
 - Add Sheet#hidden?
 

data/Gemfile

@@ -1,6 +1,6 @@
 source "https://rubygems.org"
 
-git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
+git_source(:github) { |repo_name| "https://github.com/#{repo_name}" }
 
 # Specify your gem's dependencies in xsv.gemspec
 gemspec

data/README.md

@@ -11,8 +11,9 @@ 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.
+functionality. It strives for fast processing of large worksheets with
+minimal RAM and CPU consumption and has been in production use since the earliest
+versions.
 
 Xsv stands for 'Excel Separated Values', because Excel just gets in the way.
 
@@ -36,7 +37,7 @@ Xsv targets ruby ~> 2.6 and depends on `rubyzip` and `ox`.
 
 ## Usage
 
-Xsv has two modes of operation. By default it returns an array for
+Xsv has two modes of operation. By default, it returns an array for
 each row in the sheet:
 
 ```ruby
@@ -123,6 +124,14 @@ After checking out the repo, run `bin/setup` to install dependencies. Then, run
 
 To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
 
+## Performance and Benchmarks
+
+Xsv is faster and more memory efficient than other gems because of two things: it only _reads values_ from Excel files and it's based on a SAX-based parser instead of a DOM-based parser. If you want to read some background on this, check out my blog post on
+[Efficient XML parsing in Ruby](https://storck.io/posts/efficient-xml-parsing-in-ruby/).
+
+Jamie Schembri did a shootout of Xsv against various other Excel reading gems comparing parsing speed, memory usage and allocations.
+Check our his blog post: [Faster Excel parsing in Ruby](https://blog.schembri.me/post/faster-excel-parsing-in-ruby/).
+
 ## Contributing
 
 Bug reports and pull requests are welcome on GitHub at https://github.com/martijn/xsv.

data/Rakefile

@@ -14,4 +14,3 @@ Rake::TestTask.new(:bench) do |t|
 end
 
 task :default => [:test, :bench]
-

data/lib/xsv.rb

@@ -8,7 +8,7 @@ require "xsv/shared_strings_parser"
 require "xsv/sheet"
 require "xsv/sheet_bounds_handler"
 require "xsv/sheet_rows_handler"
-require 'xsv/sheets_ids_handler'
+require "xsv/sheets_ids_handler"
 require "xsv/styles_handler"
 require "xsv/version"
 require "xsv/workbook"
@@ -19,6 +19,7 @@ require "xsv/workbook"
 # deals with minimal formatting and cannot create or modify documents.
 module Xsv
   class Error < StandardError; end
+
   # An AssertionFailed error indicates an unexpected condition, meaning a bug
   # or misinterpreted .xlsx document
   class AssertionFailed < StandardError; end

data/lib/xsv/helpers.rb

@@ -39,7 +39,7 @@ module Xsv
 
     MINUTE = 60.freeze
     HOUR = 3600.freeze
-    A_CODEPOINT = 'A'.ord.freeze
+    A_CODEPOINT = "A".ord.freeze
     # The epoch for all dates in OOXML Spreadsheet documents
     EPOCH = Date.new(1899, 12, 30).freeze
 
@@ -53,7 +53,7 @@ module Xsv
 
     # Return a Date for the given Excel date value
     def parse_date(number)
-       EPOCH + number
+      EPOCH + number
     end
 
     # Return a time as a string for the given Excel time value
@@ -94,6 +94,8 @@ module Xsv
     def parse_number(string)
       if string.include? "."
         string.to_f
+      elsif string.include? "E"
+        Complex(string).to_f
       else
         string.to_i
       end

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.read)
+      Ox.sax_parse(handler, io.read, skip: :skip_none)
       return strings
     end
 

data/lib/xsv/sheet.rb

@@ -112,7 +112,7 @@ module Xsv
       elsif @mode == :hash
         @mode = :array
         headers.tap { @mode = :hash }
-      end
+      end || []
     end
 
     def empty_row

data/lib/xsv/sheet_rows_handler.rb

@@ -64,19 +64,21 @@ module Xsv
         @state = name
         @current_cell.clear
         @current_value.clear
-      when :v
+      when :v, :is
         @state = name
       when :row
         @state = name
         @current_row = @empty_row.dup
         @current_row_attrs.clear
+      when :t
+        @state = nil unless @state == :is
       else
         @state = nil
       end
     end
 
     def text(value)
-      if @state == :v
+      if @state == :v || @state == :is
         @current_value << value
       end
     end

data/lib/xsv/styles_handler.rb

@@ -7,8 +7,8 @@ module Xsv
       @xfs = nil
       @numFmts = nil
       handler = new(numFmts) do |xfs, numFmts|
-         @xfs = xfs
-         @numFmts = numFmts
+        @xfs = xfs
+        @numFmts = numFmts
       end
 
       Ox.sax_parse(handler, io.read)

data/lib/xsv/version.rb

@@ -1,4 +1,4 @@
 # frozen_string_literal: true
 module Xsv
-  VERSION = "0.3.13"
+  VERSION = "0.3.18"
 end

data/lib/xsv/workbook.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
-require 'zip'
+require "zip"
 
 module Xsv
   # An OOXML Spreadsheet document is called a Workbook. A Workbook consists of
@@ -15,11 +15,11 @@ module Xsv
     # Open the workbook of the given filename, string or buffer. For additional
     # options see {.initialize}
     def self.open(data, **kws)
-      if data.is_a?(IO)
+      if data.is_a?(IO) || data.respond_to?(:read) # is it a buffer?
         @workbook = self.new(Zip::File.open_buffer(data), **kws)
-      elsif data.start_with?("PK\x03\x04")
+      elsif data.start_with?("PK\x03\x04") # is it a string containing a filename?
         @workbook = self.new(Zip::File.open_buffer(data), **kws)
-      else
+      else # must be a filename
         @workbook = self.new(Zip::File.open(data), **kws)
       end
     end
@@ -75,7 +75,10 @@ module Xsv
     private
 
     def fetch_shared_strings
-      stream = @zip.glob("xl/sharedStrings.xml").first.get_input_stream
+      handle = @zip.glob("xl/sharedStrings.xml").first
+      return if handle.nil?
+
+      stream = handle.get_input_stream
       @shared_strings = SharedStringsParser.parse(stream)
 
       stream.close
@@ -91,7 +94,7 @@ 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|
-        rel = @relationships.detect { |r| entry.name.end_with?(r[:Target]) && r[:Type].end_with?('worksheet') }
+        rel = @relationships.detect { |r| entry.name.end_with?(r[:Target]) && r[:Type].end_with?("worksheet") }
         sheet_ids = @sheets_ids.detect { |i| i[:r_id] == rel[:Id] }
         @sheets << Xsv::Sheet.new(self, entry.get_input_stream, entry.size, sheet_ids)
       end

data/xsv.gemspec

@@ -1,23 +1,22 @@
-
 lib = File.expand_path("../lib", __FILE__)
 $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
 require "xsv/version"
 
 Gem::Specification.new do |spec|
-  spec.name          = "xsv"
-  spec.version       = Xsv::VERSION
-  spec.authors       = ["Martijn Storck"]
-  spec.email         = ["martijn@storck.io"]
+  spec.name = "xsv"
+  spec.version = Xsv::VERSION
+  spec.authors = ["Martijn Storck"]
+  spec.email = ["martijn@storck.io"]
 
-  spec.summary       = "A fast and lightweiggt xlsx parser that provides nothing a CSV parser wouldn't"
-  spec.description    = <<-EOF
+  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
                             (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.
                           EOF
-  spec.homepage      = "https://github.com/martijn/xsv"
-  spec.license       = "MIT"
+  spec.homepage = "https://github.com/martijn/xsv"
+  spec.license = "MIT"
 
   if spec.respond_to?(:metadata)
     spec.metadata["homepage_uri"] = spec.homepage
@@ -25,19 +24,19 @@ Gem::Specification.new do |spec|
     spec.metadata["changelog_uri"] = "https://github.com/martijn/xsv/CHANGELOG.md"
   else
     raise "RubyGems 2.0 or newer is required to protect against " \
-      "public gem pushes."
+          "public gem pushes."
   end
 
   # Specify which files should be added to the gem when it is released.
   # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
-  spec.files         = Dir.chdir(File.expand_path('..', __FILE__)) do
+  spec.files = Dir.chdir(File.expand_path("..", __FILE__)) do
     `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
   end
-  spec.bindir        = "exe"
-  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.bindir = "exe"
+  spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
   spec.require_paths = ["lib"]
 
-  spec.required_ruby_version = '~> 2.5'
+  spec.required_ruby_version = "~> 2.5"
 
   spec.add_dependency "rubyzip", ">= 1.3", "< 3"
   spec.add_dependency "ox", ">= 2.9"

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: xsv
 version: !ruby/object:Gem::Version
-  version: 0.3.13
+  version: 0.3.18
 platform: ruby
 authors:
 - Martijn Storck
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2020-05-12 00:00:00.000000000 Z
+date: 2020-09-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rubyzip
@@ -117,7 +117,6 @@ files:
 - lib/xsv/styles_handler.rb
 - lib/xsv/version.rb
 - lib/xsv/workbook.rb
-- test.sh
 - xsv.gemspec
 homepage: https://github.com/martijn/xsv
 licenses:

data/test.sh

@@ -1,3 +0,0 @@
-#!/bin/sh
-
-ruby -Ilib:test test/*_test.rb