dullard 0.1.0 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 9d02ed091d258d5d690ba9e3ba350c392488664e
-  data.tar.gz: 9f61befa4e3003f7e469a26ff7c4412ffa4d6e55
+  metadata.gz: e3a941a2433fc527bc868fd41ef33ab4af46acc8
+  data.tar.gz: 6c0a1f95069ac0c0751e1452b2e6e3464872bd46
 SHA512:
-  metadata.gz: 87d7d94d530d337ba92623146e5d0a115e44b04d15b1ee91fcf4c49bc76e90ace74bbf29f6e707ad3853d3e314e000cb4a3ec96a9b256576755adaeacce8022c
-  data.tar.gz: 2d10be78032321162cc1e2416771946c02cecea129f2959f12ec9a3bc49e2e9d68563ac18b9896159fef1a097d1d90fa5bf6ac7698985a2ec1fc3afcf8248297
+  metadata.gz: 1ac8f461122aaa0fb5d90a3702fac5cdd2524c21e7b78ddfc02355585ba3e0288971e660c4664a78d92e7ca2c0c9afe73c41ba8de71db56ddce6d41d8055129e
+  data.tar.gz: a6a2774cb28d125ab7e5b59026395cc671842e450c36c2cef0cafd98744bde274c6b662efa8764e1e0343eae8367ac8206eae0f4c7e64a315ad54ce83dacc786

data/LICENSE

@@ -1,4 +1,4 @@
-Copyright (c) 2013 Edward Kaplan
+Copyright (c) 2015 Edward Kaplan
 
 MIT License
 

data/README.md

@@ -1,3 +1,5 @@
+# dullard
+
 Super simple, super fast stream-based XLSX parsing.  Suitable for very large
 files.
 
@@ -7,5 +9,11 @@ Requires Ruby 2.0.
 
     workbook = Dullard::Workbook.new "file.xlsx"
     workbook.sheets[0].rows.each do |row|
-      puts row # => ["a","b","c",...]
+      p row # => ["a","b","c", 0.3, #<DateTime: -4712-01-01....>, ...]
     end
+
+## Current limitations
+ * Limited validation and error handling.
+ * Formatted cells are read, but formatting is not accessible.
+ * May be buggy.  Pull requests welcome!
+ * Rows that end with empty cells may be truncated.

data/lib/dullard/reader.rb

@@ -1,7 +1,12 @@
 require 'zip/filesystem'
 require 'nokogiri'
 
-module Dullard; end
+module Dullard
+  class Error < StandardError; end
+  OOXMLEpoch = DateTime.new(1899,12,30)
+  SharedStringPath = 'xl/sharedStrings.xml'
+  StylesPath = 'xl/styles.xml'
+end
 
 class Dullard::Workbook
   # Code borrowed from Roo (https://github.com/hmcgowan/roo/blob/master/lib/roo/excelx.rb)
@@ -12,8 +17,8 @@ class Dullard::Workbook
     '0.00' => :float,
     '#,##0' => :float,
     '#,##0.00' => :float,
-    '0%' => :percentage,
-    '0.00%' => :percentage,
+    '0%' => :float,
+    '0.00%' => :float,
     '0.00E+00' => :float,
     '# ?/?' => :float, #??? TODO:
     '# ??/??' => :float, #??? TODO:
@@ -78,24 +83,42 @@ class Dullard::Workbook
 
   def initialize(file, user_defined_formats = {})
     @file = file
-    @zipfs = Zip::File.open(@file)
+    begin
+      @zipfs = Zip::File.open(@file)
+    rescue Zip::Error => e
+      raise Dullard::Error, e.message
+    end
     @user_defined_formats = user_defined_formats
     read_styles
   end
 
   def sheets
-    workbook = Nokogiri::XML::Document.parse(@zipfs.file.open("xl/workbook.xml"))
-    @sheets = workbook.css("sheet").each_with_index.map {|n,i| Dullard::Sheet.new(self, n.attr("name"), n.attr("sheetId"), i+1) }
+    begin
+      workbook = Nokogiri::XML::Document.parse(@zipfs.file.open('xl/workbook.xml'))
+    rescue Zip::Error
+      raise Dullard::Error, 'Invalid file, could not open xl/workbook.xml'
+    end
+    @sheets = workbook.css('sheet').each_with_index.map do |n, i|
+      Dullard::Sheet.new(self, n.attr('name'), n.attr('sheetId'), i+1)
+    end
   end
 
   def string_table
-    @string_tabe ||= read_string_table
+    @string_table ||= read_string_table
   end
 
   def read_string_table
-    @string_table = []
+    return [] unless @zipfs.file.exist? Dullard::SharedStringPath
+
+    begin
+      shared_string = @zipfs.file.open(Dullard::SharedStringPath)
+    rescue Zip::Error
+      raise Dullard::Error, 'Invalid file, could not open shared string file.'
+    end
+
     entry = ''
-    Nokogiri::XML::Reader(@zipfs.file.open("xl/sharedStrings.xml")).each do |node|
+    @string_table = []
+    Nokogiri::XML::Reader(shared_string).each do |node|
       if node.name == "si" and node.node_type == Nokogiri::XML::Reader::TYPE_ELEMENT
         entry = ''
       elsif node.name == "si" and node.node_type == Nokogiri::XML::Reader::TYPE_END_ELEMENT
@@ -108,20 +131,29 @@ class Dullard::Workbook
   end
 
   def read_styles
-    doc = Nokogiri::XML(@zipfs.file.open("xl/styles.xml"))
-    
     @num_formats = {}
     @cell_xfs = []
+    return unless @zipfs.file.exist? Dullard::StylesPath
+
+    begin
+      doc = Nokogiri::XML(@zipfs.file.open(Dullard::StylesPath))
+    rescue Zip::Error
+      raise Dullard::Error, 'Invalid file, could not open styles'
+    end
     
     doc.css('/styleSheet/numFmts/numFmt').each do |numFmt|
-      numFmtId = numFmt.attributes['numFmtId'].value.to_i
-      formatCode = numFmt.attributes['formatCode'].value
-      @num_formats[numFmtId] = formatCode
+      if numFmt.attributes['numFmtId'] && numFmt.attributes['formatCode']
+        numFmtId = numFmt.attributes['numFmtId'].value.to_i
+        formatCode = numFmt.attributes['formatCode'].value
+        @num_formats[numFmtId] = formatCode
+      end
     end
 
     doc.css('/styleSheet/cellXfs/xf').each do |xf|
-      numFmtId = xf.attributes['numFmtId'].value.to_i
-      @cell_xfs << numFmtId
+      if xf.attributes['numFmtId']
+        numFmtId = xf.attributes['numFmtId'].value.to_i
+        @cell_xfs << numFmtId
+      end
     end
   end
 
@@ -168,11 +200,15 @@ class Dullard::Sheet
     @name = name
     @id = id
     @index = index
-    @file = @workbook.zipfs.file.open(path) if @workbook.zipfs.file.exist?(path)
+    begin
+      @file = @workbook.zipfs.file.open(path) if @workbook.zipfs.file.exist?(path)
+    rescue Zip::Error => e
+      raise Dullard::Error, "Couldn't open sheet #{index}: #{e.message}"
+    end
   end
 
   def string_lookup(i)
-    @workbook.string_table[i]
+    @workbook.string_table[i] || (raise Dullard::Error, 'File invalid, invalid string table.')
   end
 
   def rows
@@ -181,6 +217,7 @@ class Dullard::Sheet
       @file.rewind
       shared = false
       row = nil
+      cell_map = nil # Map of column letter to cell value for a row
       column = nil
       cell_type = nil
       Nokogiri::XML::Reader(@file).each do |node|
@@ -188,55 +225,65 @@ class Dullard::Sheet
         when Nokogiri::XML::Reader::TYPE_ELEMENT
           case node.name
           when "row"
-            row = []
-            column = 0
+            cell_map = {}
             next
-          when "c"
-            if node.attributes['t'] != 's' && node.attributes['t'] != 'b'
+          when 'c'
+            node_type = node.attributes['t']
+            cell_index = node.attributes['r']
+            if !cell_index
+              raise Dullard::Error, 'Invalid spreadsheet XML.'
+            end
+
+            if node_type != 's' && node_type != 'b'
               cell_format_index = node.attributes['s'].to_i
               cell_type = @workbook.format2type(@workbook.attribute2format(cell_format_index))
             end
 
-            rcolumn = node.attributes["r"]
-            if rcolumn
-              rcolumn.delete!("0-9")
-              while column < self.class.column_names.size and rcolumn != self.class.column_names[column]
-                row << nil
-                column += 1
-              end
-            end
-            shared = (node.attribute("t") == "s")
-            column += 1
+            column = cell_index.delete('0-9')
+            shared = (node_type == 's')
             next
           end
         when Nokogiri::XML::Reader::TYPE_END_ELEMENT
-          if node.name == "row"
-            y << row
-            next
+          if node.name == 'row'
+            y << process_row(cell_map)
           end
+          next
         end
-        value = node.value
 
-        if value
+        if node.value
+          value = (shared ? string_lookup(value.to_i) : value)
           case cell_type
             when :datetime
             when :time
             when :date
-              value = (DateTime.new(1899,12,30) + value.to_f)
-            when :percentage # ? TODO
+              value = (Dullard::OOXMLEpoch + node.value.to_f)
             when :float
-              value = value.to_f
+              value = node.value.to_f
             else
               # leave as string
           end
           cell_type = nil
-
-          row << (shared ? string_lookup(value.to_i) : value)
+          cell_map[column] = value
         end
       end
     end
   end
 
+  def process_row(cell_map)
+    max = cell_map.keys.map {|c| self.class.column_name_to_index c }.max
+    row = []
+    self.class.column_names[0..max].each do |col|
+      if self.class.column_name_to_index(col) > max
+        break
+      else
+        row << cell_map[col]
+      end
+    end
+    row
+  end
+
+
+
   # Returns A to ZZZ.
   def self.column_names
     if @column_names
@@ -252,6 +299,16 @@ class Dullard::Sheet
     end
   end
 
+  def self.column_name_to_index(name)
+    if not @column_names_to_indices
+      @column_names_to_indices = {}
+      self.column_names.each_with_index do |name, i|
+        @column_names_to_indices[name] = i
+      end
+    end
+    @column_names_to_indices[name]
+  end
+
   def row_count
     if defined? @row_count
       @row_count
@@ -260,11 +317,11 @@ class Dullard::Sheet
       Nokogiri::XML::Reader(@file).each do |node|
         if node.node_type == Nokogiri::XML::Reader::TYPE_ELEMENT
           case node.name
-          when "dimension"
+          when 'dimension'
             if ref = node.attributes["ref"]
               break @row_count = ref.scan(/\d+$/).first.to_i
             end
-          when "sheetData"
+          when 'sheetData'
             break @row_count = nil
           end
         end

data/lib/dullard/version.rb

@@ -1,3 +1,3 @@
 module Dullard
-  VERSION = "0.1.0"
+  VERSION = "0.2.0"
 end

data/spec/dullard_spec.rb

@@ -1,6 +1,6 @@
 require 'dullard'
 
-describe "dullard," do
+describe "test.xlsx," do
   before(:each) do
     @file = File.open(File.expand_path("../test.xlsx", __FILE__))
   end
@@ -22,7 +22,6 @@ describe "dullard," do
       rows = @xlsx.sheets[0].rows
       rows.next.count.should == 300
       rows.next.count.should == 9
-      rows.next.count.should == 1
     end
 
     it "reads the right number of rows" do
@@ -71,3 +70,47 @@ describe "dullard," do
     end
   end
 end
+
+describe "test2.xlsx" do
+  before(:each) do
+    @file = File.open(File.expand_path("../test2.xlsx", __FILE__))
+  end
+
+  it "should not skip nils" do
+    rows = Dullard::Workbook.new(@file).sheets[0].rows.to_a
+    rows.should == [
+      [1],
+      [nil, 2],
+      [nil, nil, 3]
+    ]
+  end
+end
+
+describe "error handling" do
+  it "should raise an error when a cell is missing r attr" do
+    @file = File.expand_path("../error_missing_r.xlsx", __FILE__)
+    book = Dullard::Workbook.new(@file)
+    sheet = book.sheets[0]
+    expect {
+      sheet.rows.to_a
+    }.to raise_error(Dullard::Error)
+  end
+
+  it "should succeed when styles are missing" do
+    file = File.expand_path("../error_missing_metadata.xlsx", __FILE__)
+    book = Dullard::Workbook.new(file)
+    sheet = book.sheets[0]
+    expect {
+      sheet.rows.to_a
+    }.not_to raise_error
+  end
+
+  it "should raise an error with invalid shared string index" do
+    file = File.expand_path("../error_missing_ss.xlsx", __FILE__)
+    book = Dullard::Workbook.new(file)
+    sheet = book.sheets[0]
+    expect {
+      sheet.rows.to_a
+    }.to raise_error(Dullard::Error)
+  end
+end

metadata

@@ -1,69 +1,69 @@
 --- !ruby/object:Gem::Specification
 name: dullard
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.2.0
 platform: ruby
 authors:
 - Ted Kaplan
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-03-30 00:00:00.000000000 Z
+date: 2015-01-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '2.14'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '2.14'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '10.1'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '10.1'
 - !ruby/object:Gem::Dependency
   name: nokogiri
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1.6'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1.6'
 - !ruby/object:Gem::Dependency
   name: rubyzip
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1.1'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1.1'
 description: 
@@ -73,7 +73,7 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- .gitignore
+- ".gitignore"
 - Gemfile
 - LICENSE
 - README.md
@@ -83,6 +83,9 @@ files:
 - lib/dullard/reader.rb
 - lib/dullard/version.rb
 - spec/dullard_spec.rb
+- spec/error_missing_metadata.xlsx
+- spec/error_missing_r.xlsx
+- spec/error_missing_ss.xlsx
 - spec/test.xlsx
 homepage: http://github.com/thirtyseven/dullard
 licenses:
@@ -94,20 +97,23 @@ require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.0.5
+rubygems_version: 2.4.3
 signing_key: 
 specification_version: 4
 summary: A fast XLSX parser using Nokogiri
 test_files:
 - spec/dullard_spec.rb
+- spec/error_missing_metadata.xlsx
+- spec/error_missing_r.xlsx
+- spec/error_missing_ss.xlsx
 - spec/test.xlsx