xsv 0.3.10 → 0.3.15

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 5107cc27c9d49216c411efdf521acaf9f098980734e879221f8a36f980d55e16
-  data.tar.gz: 16471ebf80a5cd2c69d8163e0d0b76a5b0744f78ab10d4178832541baef98986
+  metadata.gz: 84691bdf67411e4a1e2d28c23a04e6656285247820d65c3124382261b0aba27e
+  data.tar.gz: 2ae8332a7e5e857039b729abee1478f063663e29b4eb8b9f45a4ae3ac2632916
 SHA512:
-  metadata.gz: 3de0117ee959c4dd081aaae6904b47a05c4ca9351209fb8cac36aa1159c279147e2faf40294bab050f03ae1632b5e703479b4d0752ad59e7c024e35cc88911a5
-  data.tar.gz: 85dc373294b772737f5b161b0c2566461cb7ab24175658e91e0f55ae4067085e74e65075482c8b0ca366e987081dab9e2f8b8dbbfc2a0f0754ea0d96db171d20
+  metadata.gz: 666a4b190de6a64d676fc5dd66d5d836255b7c5b8114f21f53ce57b9d09deaa1cfd4f644c31018a48619449d5962dd86b6bdd41355861462275601fc7486c386
+  data.tar.gz: 3c6c957f46e31dac95f7c77f533ab43c52db1733f1d309b7a6e6bdc7e503da72963a3fe4f80a8269d46db436977bbc37c0b425203c2d75c8a6ef1be889714eb3

data/.travis.yml

@@ -3,8 +3,8 @@ sudo: false
 language: ruby
 cache: bundler
 rvm:
-  - 2.6.5
-  - 2.7.0
+  - 2.5.8
+  - 2.7.1
 env:
   - "rubyzip=1.3.0"
   - "rubyzip=2.2.0"

data/CHANGELOG.md

@@ -1,5 +1,29 @@
 # Xsv Changelog
 
+## 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?
+
+- Clean up code; get rid of some deprecation warnings
+
+## 0.3.12 - 2020-04-15
+
+- Accessing worksheets by name (texpert)
+
+## 0.3.11 - 2020-04-03
+
+- Backward compatibility with Ruby 2.5 (texpert)
+
 ## 0.3.10 - 2020-03-19
 
 - Relax version requirements for dependencies

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

@@ -81,7 +81,23 @@ columns with the same name!
 `Xsv::Workbook.open` accepts a filename, or a IO or String containing a workbook.
 
 `Xsv::Sheet` implements `Enumerable` so you can call methods like `#first`,
-`#filter` and `#map` on it.
+`#filter`/`#select` and `#map` on it.
+
+The sheets could be accessed by index or by name:
+
+```ruby
+x = Xsv::Workbook.open("sheet.xlsx")
+
+sheet = x.sheets[0] # gets sheet by index
+
+sheet = x.sheets_by_name('Name').first # gets sheet by name
+```
+
+To get all the workbook's sheets names:
+
+```ruby
+sheet_names = x.sheets.map(&:name)
+```
 
 ### Assumptions
 

data/Rakefile

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

data/lib/xsv.rb

@@ -3,10 +3,12 @@ require "date"
 require "ox"
 
 require "xsv/helpers"
+require "xsv/relationships_handler"
 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/styles_handler"
 require "xsv/version"
 require "xsv/workbook"
@@ -17,6 +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

data/lib/xsv/relationships_handler.rb

@@ -0,0 +1,40 @@
+# frozen_string_literal: true
+module Xsv
+  # RelationshipsHandler parses the "xl/_rels/workbook.xml.rels" file to get the existing relationships.
+  # This is used internally  when opening a workbook.
+  class RelationshipsHandler < Ox::Sax
+    def self.get_relations(io)
+      relations = []
+      handler = new do |relation|
+        relations << relation
+      end
+
+      Ox.sax_parse(handler, io.read)
+      return relations
+    end
+
+    # Ox::Sax implementation
+
+    def initialize(&block)
+      @block = block
+      @relationship = {}
+    end
+
+    def start_element(name)
+      @relationship = {} if name == :Relationship
+    end
+
+    def attr(name, value)
+      case name
+      when :Id, :Type, :Target
+        @relationship[name] = value
+      end
+    end
+
+    def end_element(name)
+      return unless name == :Relationship
+
+      @block.call(@relationship)
+    end
+  end
+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

@@ -17,7 +17,7 @@ module Xsv
 
     # Returns the current mode. Call {#parse_headers!} to switch to `:hash` mode
     # @return [Symbol] `:hash` or `:array`
-    attr_reader :mode
+    attr_reader :id, :mode, :name
 
     # Set a number of rows to skip at the top of the sheet (header row offset).
     # For hash mode, do not skip the header row as this will be automatically
@@ -30,13 +30,16 @@ module Xsv
     # @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 size [Number] size of the XML file
-    def initialize(workbook, io, size)
+    def initialize(workbook, io, size, ids)
       @workbook = workbook
+      @id = ids[:sheetId].to_i
       @io = io
+      @name = ids[:name]
       @size = size
       @headers = []
       @mode = :array
       @row_skip = 0
+      @hidden = ids[:state] == "hidden"
 
       @last_row, @column_count = SheetBoundsHandler.get_bounds(@io, @workbook)
     end
@@ -46,6 +49,11 @@ module Xsv
       "#<#{self.class.name}:#{self.object_id}>"
     end
 
+    # Returns true if the worksheet is hidden
+    def hidden?
+      @hidden
+    end
+
     # Iterate over rows, returning either hashes or arrays based on the current mode.
     def each_row(&block)
       @io.rewind

data/lib/xsv/sheets_ids_handler.rb

@@ -0,0 +1,56 @@
+# frozen_string_literal: true
+module Xsv
+  # SheetsIdsHandler interprets the relevant parts of workbook.xml
+  # This is used internally to get the sheets ids, relationship_ids, and names when opening a workbook.
+  class SheetsIdsHandler < Ox::Sax
+    def self.get_sheets_ids(io)
+      sheets_ids = []
+      handler = new do |sheet_ids|
+        sheets_ids << sheet_ids
+      end
+
+      Ox.sax_parse(handler, io.read)
+      return sheets_ids
+    end
+
+    # Ox::Sax implementation
+
+    def initialize(&block)
+      @block = block
+      @parsing = false
+    end
+
+    def start_element(name)
+      if name == :sheets
+        @parsing = true
+        return
+      end
+
+      return unless name == :sheet
+
+      @sheet_ids = {}
+    end
+
+    def attr(name, value)
+      return unless @parsing
+
+      case name
+      when :name, :sheetId, :state
+        @sheet_ids[name] = value
+      when :'r:id'
+        @sheet_ids[:r_id] = value
+      end
+    end
+
+    def end_element(name)
+      if name == :sheets
+        @parsing = false
+        return
+      end
+
+      return unless name == :sheet
+
+      @block.call(@sheet_ids)
+    end
+  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 = "0.3.10"
+  VERSION = "0.3.15"
 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
@@ -41,6 +41,8 @@ module Xsv
 
       fetch_shared_strings
       fetch_styles
+      fetch_sheets_ids
+      fetch_relationships
       fetch_sheets
     end
 
@@ -56,15 +58,27 @@ module Xsv
       @sheets = nil
       @xfs = nil
       @numFmts = nil
+      @relationships = nil
       @shared_strings = nil
+      @sheets_ids = nil
 
       true
     end
 
+    # Returns an array of sheets for the case of same name sheets.
+    # @param [String] name
+    # @return [Array<Xsv::Sheet>]
+    def sheets_by_name(name)
+      @sheets.select { |s| s.name == name }
+    end
+
     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
@@ -80,8 +94,24 @@ 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, entry.size)
+        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
     end
+
+    def fetch_sheets_ids
+      stream = @zip.glob("xl/workbook.xml").first.get_input_stream
+      @sheets_ids = SheetsIdsHandler.get_sheets_ids(stream)
+
+      stream.close
+    end
+
+    def fetch_relationships
+      stream = @zip.glob("xl/_rels/workbook.xml.rels").first.get_input_stream
+      @relationships = RelationshipsHandler.get_relations(stream)
+
+      stream.close
+    end
   end
 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 = '~> 2.6'
+  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: 0.3.10
+  version: 0.3.15
 platform: ruby
 authors:
 - Martijn Storck
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2020-03-19 00:00:00.000000000 Z
+date: 2020-06-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rubyzip
@@ -108,14 +108,15 @@ files:
 - bin/setup
 - lib/xsv.rb
 - lib/xsv/helpers.rb
+- lib/xsv/relationships_handler.rb
 - lib/xsv/shared_strings_parser.rb
 - lib/xsv/sheet.rb
 - lib/xsv/sheet_bounds_handler.rb
 - lib/xsv/sheet_rows_handler.rb
+- lib/xsv/sheets_ids_handler.rb
 - lib/xsv/styles_handler.rb
 - lib/xsv/version.rb
 - lib/xsv/workbook.rb
-- test.sh
 - xsv.gemspec
 homepage: https://github.com/martijn/xsv
 licenses:
@@ -132,7 +133,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - "~>"
     - !ruby/object:Gem::Version
-      version: '2.6'
+      version: '2.5'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="

data/test.sh

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