gkosae-spreadshot 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +10 -0
- data/.rspec +1 -0
- data/.yardopts +1 -0
- data/CHANGELOG.md +3 -0
- data/Gemfile +4 -0
- data/Gemfile.lock +47 -0
- data/LICENSE.txt +21 -0
- data/README.md +143 -0
- data/Rakefile +2 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/lib/spreadshot.rb +17 -0
- data/lib/spreadshot/backends.rb +4 -0
- data/lib/spreadshot/backends/reader_backend.rb +37 -0
- data/lib/spreadshot/backends/ruby_xl_backend.rb +92 -0
- data/lib/spreadshot/backends/smarter_csv_backend.rb +44 -0
- data/lib/spreadshot/reader.rb +132 -0
- data/lib/spreadshot/version.rb +3 -0
- data/spreadshot.gemspec +37 -0
- metadata +149 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: d791d40e930be4758677eaf69b0e06626a6bf3d486f450f613f9f1fe44414024
|
4
|
+
data.tar.gz: 80828c259225f8b85a8596f6a28592add0331763b424d85ec8fb09a748365c2f
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 1ce21cdac4b7f5b2bdcf5cc988b5ecca9e3369871fab128d85ccf05f82fe087991a077525962edd600b3c08aa2eaf4b3c694e5004e0372546d13f6170102651a
|
7
|
+
data.tar.gz: 04504d3c45b1daaa784b4c52b18c46bbdb53420de53ec59e5b6638ee5d237f50f9abb71772570388e47c58908f66c47070fe03c7b45bcbbdd97c60dbf4693999
|
data/.gitignore
ADDED
data/.rspec
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
--require spec_helper
|
data/.yardopts
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
--private
|
data/CHANGELOG.md
ADDED
data/Gemfile
ADDED
data/Gemfile.lock
ADDED
@@ -0,0 +1,47 @@
|
|
1
|
+
PATH
|
2
|
+
remote: .
|
3
|
+
specs:
|
4
|
+
gkosae-spreadshot (0.1.0)
|
5
|
+
rubyXL (~> 3.3.33)
|
6
|
+
smarter_csv (~> 1.2.6)
|
7
|
+
|
8
|
+
GEM
|
9
|
+
remote: https://rubygems.org/
|
10
|
+
specs:
|
11
|
+
byebug (11.0.1)
|
12
|
+
diff-lcs (1.3)
|
13
|
+
mini_portile2 (2.4.0)
|
14
|
+
nokogiri (1.10.4)
|
15
|
+
mini_portile2 (~> 2.4.0)
|
16
|
+
rake (10.5.0)
|
17
|
+
rspec (3.9.0)
|
18
|
+
rspec-core (~> 3.9.0)
|
19
|
+
rspec-expectations (~> 3.9.0)
|
20
|
+
rspec-mocks (~> 3.9.0)
|
21
|
+
rspec-core (3.9.0)
|
22
|
+
rspec-support (~> 3.9.0)
|
23
|
+
rspec-expectations (3.9.0)
|
24
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
25
|
+
rspec-support (~> 3.9.0)
|
26
|
+
rspec-mocks (3.9.0)
|
27
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
28
|
+
rspec-support (~> 3.9.0)
|
29
|
+
rspec-support (3.9.0)
|
30
|
+
rubyXL (3.3.33)
|
31
|
+
nokogiri (>= 1.4.4)
|
32
|
+
rubyzip (>= 1.1.6)
|
33
|
+
rubyzip (2.0.0)
|
34
|
+
smarter_csv (1.2.6)
|
35
|
+
|
36
|
+
PLATFORMS
|
37
|
+
ruby
|
38
|
+
|
39
|
+
DEPENDENCIES
|
40
|
+
bundler (~> 2.0)
|
41
|
+
byebug (~> 11.0)
|
42
|
+
gkosae-spreadshot!
|
43
|
+
rake (~> 10.0)
|
44
|
+
rspec (~> 3.0)
|
45
|
+
|
46
|
+
BUNDLED WITH
|
47
|
+
2.0.2
|
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2019 DarkWasp
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,143 @@
|
|
1
|
+
# Spreadshot
|
2
|
+
A Ruby library for reading spreadsheets with support for multiple backends. This is an attempt to:
|
3
|
+
- Provide a uniform interface for reading different formats of spreadsheets.
|
4
|
+
- Reduce the amount of code changed when you decide to switch reader backends for any reason
|
5
|
+
|
6
|
+
[SmarterCSV](https://github.com/tilo/smarter_csv) (for csv files) and [RubyXL](https://github.com/weshatheleopard/rubyXL) (for xlsx files) backends are provided out of the box.
|
7
|
+
|
8
|
+
The name was inspired by the names of [battle chips from Megaman Battle Network 3](https://megaman.fandom.com/wiki/List_of_Mega_Man_Battle_Network_3_Battle_Chips).
|
9
|
+
|
10
|
+
## Installation
|
11
|
+
|
12
|
+
Add this line to your application's Gemfile:
|
13
|
+
|
14
|
+
```ruby
|
15
|
+
gem 'spreadshot'
|
16
|
+
```
|
17
|
+
|
18
|
+
And then execute:
|
19
|
+
|
20
|
+
$ bundle
|
21
|
+
|
22
|
+
Or install it yourself as:
|
23
|
+
|
24
|
+
$ gem install spreadshot
|
25
|
+
|
26
|
+
## Usage
|
27
|
+
|
28
|
+
Require gem with:
|
29
|
+
|
30
|
+
```ruby
|
31
|
+
require 'spreadshot'
|
32
|
+
```
|
33
|
+
|
34
|
+
Read spreadsheet with one of the provided backends
|
35
|
+
```ruby
|
36
|
+
csv_reader = Spreadshot::Reader.new(backend: :smarter_csv)
|
37
|
+
|
38
|
+
begin
|
39
|
+
csv_reader.read(path_to_sample_csv_file) do |row_index, row_data|
|
40
|
+
puts "#{row_index} - #{row_data}"
|
41
|
+
end
|
42
|
+
rescue Spreadshot::ReaderError
|
43
|
+
# Handle error
|
44
|
+
end
|
45
|
+
|
46
|
+
# A cell_index_to_field_mapper must be provided for the RubyXL backend to map values read from a column to a unique key in the yielded hash
|
47
|
+
xlsx_reader = Spreadshot::Reader.new(
|
48
|
+
backend: :ruby_xl,
|
49
|
+
cell_index_to_field_mapper: {0 => :h1, 1 => :h2, 2 => :h3, 3 => :h4}
|
50
|
+
)
|
51
|
+
|
52
|
+
begin
|
53
|
+
xlsx_reader.read(path_to_sample_xlsx_file) do |row_index, row_data|
|
54
|
+
puts "#{row_index} - #{row_data}"
|
55
|
+
end
|
56
|
+
rescue Spreadshot::ReaderError
|
57
|
+
# Handle error
|
58
|
+
end
|
59
|
+
|
60
|
+
# SAMPLE OUTPUT
|
61
|
+
# 2 - {:h1=>11, :h2=>22, :h3=>33, :h4=>44}
|
62
|
+
# 3 - {:h1=>111, :h2=>222, :h3=>333, :h4=>444}
|
63
|
+
# 4 - {:h1=>1111, :h2=>2222, :h3=>3333, :h4=>4444}
|
64
|
+
```
|
65
|
+
|
66
|
+
`row_index` begins from 2 because index 1 is used for headers. But if the spreadsheet does not contain headers then the backend can be configured with `headers: false` to begin reading from index 1 (This is only available for the RubyXL backend. To the best of my knowledge SmarterCSV does not support reading files without headers).
|
67
|
+
|
68
|
+
```ruby
|
69
|
+
xlsx_reader = Spreadshot::Reader.new(
|
70
|
+
backend: :ruby_xl,
|
71
|
+
worksheet_index: 1, # Index of the worksheet to read from (defaults to 0, i.e. the first worksheet)
|
72
|
+
headers: false,
|
73
|
+
cell_index_to_field_mapper: {0 => :h1, 1 => :h2, 2 => :h3, 3 => :h4}
|
74
|
+
)
|
75
|
+
begin
|
76
|
+
xlsx_reader.read(path_to_sample_xlsx_file) do |row_index, row_data|
|
77
|
+
puts "#{row_index} - #{row_data}"
|
78
|
+
end
|
79
|
+
rescue Spreadshot::ReaderError
|
80
|
+
# Handle error
|
81
|
+
end
|
82
|
+
|
83
|
+
# SAMPLE OUTPUT
|
84
|
+
# 1 - {:h1=>11, :h2=>22, :h3=>33, :h4=>44}
|
85
|
+
# 2 - {:h1=>111, :h2=>222, :h3=>333, :h4=>444}
|
86
|
+
# 3 - {:h1=>1111, :h2=>2222, :h3=>3333, :h4=>4444}
|
87
|
+
```
|
88
|
+
|
89
|
+
OR<br/><br/>
|
90
|
+
Read spreadsheet with a custom backend. The custom backend MUST inherit from `Spreadshot::Backends::ReaderBackend` and override `#read`. `#read` MUST yield the index and content(as a Hash) of each row read.<br/><br/>
|
91
|
+
Example:
|
92
|
+
```ruby
|
93
|
+
class SmarterCSVBackend < Spreadshot::Backends::ReaderBackend
|
94
|
+
def initialize(options = {})
|
95
|
+
options ||= {}
|
96
|
+
options[:headers] = true
|
97
|
+
super(options)
|
98
|
+
end
|
99
|
+
|
100
|
+
def read(path_to_spreadsheet)
|
101
|
+
SmarterCSV.process(path_to_spreadsheet) do |row|
|
102
|
+
current_row_data = row.first
|
103
|
+
yield(@current_row_index, current_row_data)
|
104
|
+
@current_row_index += 1
|
105
|
+
end
|
106
|
+
rescue => e
|
107
|
+
raise Spreadshot::ReaderError, e.message
|
108
|
+
end
|
109
|
+
end
|
110
|
+
|
111
|
+
csv_backend = Spreadshot::Backends::SmarterCSVBackend.new
|
112
|
+
csv_reader = Spreadshot::Reader.new(backend: csv_backend)
|
113
|
+
```
|
114
|
+
|
115
|
+
Reader backends can also be switched dynamically with the `#set_backend` method
|
116
|
+
```ruby
|
117
|
+
reader = Spreadshot::Reader.new(backend: :smarter_csv)
|
118
|
+
|
119
|
+
xlsx = Spreadshot::Backends::RubyXLBackend.new(
|
120
|
+
worksheet_index: 0,
|
121
|
+
cell_index_to_field_mapper: {0 => :h1, 1 => :h2, 2 => :h3, 3 => :h4}
|
122
|
+
)
|
123
|
+
reader.set_backend(xlsx)
|
124
|
+
|
125
|
+
#OR
|
126
|
+
|
127
|
+
reader.set_backend(:ruby_xl)
|
128
|
+
```
|
129
|
+
|
130
|
+
|
131
|
+
## Development
|
132
|
+
|
133
|
+
After checking out the repo, run `bin/setup` to install dependencies. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
134
|
+
|
135
|
+
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).
|
136
|
+
|
137
|
+
## Contributing
|
138
|
+
|
139
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/gkosae/spreadshot.git
|
140
|
+
|
141
|
+
## License
|
142
|
+
|
143
|
+
The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "spreadshot"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start(__FILE__)
|
data/bin/setup
ADDED
data/lib/spreadshot.rb
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
require 'spreadshot/version'
|
2
|
+
require 'spreadshot/backends/reader_backend'
|
3
|
+
require 'spreadshot/backends/ruby_xl_backend'
|
4
|
+
require 'spreadshot/backends/smarter_csv_backend'
|
5
|
+
require 'spreadshot/reader'
|
6
|
+
|
7
|
+
module Spreadshot
|
8
|
+
class SpreadshotError < StandardError
|
9
|
+
def initialize(*args)
|
10
|
+
super(*args)
|
11
|
+
set_backtrace($!.backtrace) if $!
|
12
|
+
end
|
13
|
+
end
|
14
|
+
|
15
|
+
class BackendNotFound < SpreadshotError; end
|
16
|
+
class ReaderError < SpreadshotError; end
|
17
|
+
end
|
@@ -0,0 +1,37 @@
|
|
1
|
+
module Spreadshot
|
2
|
+
module Backends
|
3
|
+
|
4
|
+
# Base class for all spreadshot reader backends.
|
5
|
+
class ReaderBackend
|
6
|
+
|
7
|
+
# @param [Hash] options
|
8
|
+
# @option options [Boolean] :headers
|
9
|
+
# Specifies whether the spreadsheet to be read contains headers
|
10
|
+
def initialize(options = {})
|
11
|
+
options ||= {}
|
12
|
+
@headers = (options.has_key?(:headers)) ? options[:headers] : true
|
13
|
+
@current_row_index = @headers ? 2 : 1
|
14
|
+
end
|
15
|
+
|
16
|
+
|
17
|
+
|
18
|
+
|
19
|
+
# Reads data from the specified spreadsheet
|
20
|
+
# @note
|
21
|
+
# Must be overriden by subclasses.
|
22
|
+
# Override must raise {Spreadshot::ReaderError Spreadshot::ReaderError} if something goes wrong while reading
|
23
|
+
#
|
24
|
+
#
|
25
|
+
# @param [String] path_to_spreadsheet
|
26
|
+
#
|
27
|
+
# @yield [row_index, row_data]
|
28
|
+
# @yieldparam [Integer] row_index
|
29
|
+
# The index of the current row being read. The first row has an index of 1
|
30
|
+
# @yieldparam [Hash] row_data
|
31
|
+
# A hash representation of the data read from the current row
|
32
|
+
def read(path_to_spreadsheet)
|
33
|
+
raise NotImplementedError
|
34
|
+
end
|
35
|
+
end
|
36
|
+
end
|
37
|
+
end
|
@@ -0,0 +1,92 @@
|
|
1
|
+
require 'rubyXL'
|
2
|
+
|
3
|
+
module Spreadshot
|
4
|
+
module Backends
|
5
|
+
|
6
|
+
# Adapter for the RubyXL Gem ({https://github.com/weshatheleopard/rubyXL})
|
7
|
+
class RubyXLBackend < ReaderBackend
|
8
|
+
|
9
|
+
# Returns a new instance of RubyXLBackend (See {ReaderBackend#initialize Spreadshot::ReaderBackends::ReaderBackend})
|
10
|
+
#
|
11
|
+
# @param [Hash] options
|
12
|
+
# @option options [Boolean] :headers
|
13
|
+
# Specifies whether the spreadsheet to be read contains headers.
|
14
|
+
# Defaults to true
|
15
|
+
# @option options [Integer] :worksheet_index
|
16
|
+
# The index of the worksheet to be read. Used for the RubyXL backend.
|
17
|
+
# Defaults to 0
|
18
|
+
# @option options [Hash] :cell_index_to_field_mapper
|
19
|
+
# A hash which maps each cell in a row of the spreadsheet to a key in the
|
20
|
+
# hash created for that row. Must be provided
|
21
|
+
#
|
22
|
+
# @raise [ArgumentError] if cell_index_to_field_mapper option is not provided
|
23
|
+
# @raise [ArgumentError] if cell_index_to_field_mapper option is not a Hash
|
24
|
+
def initialize(options = {})
|
25
|
+
options ||= {}
|
26
|
+
super(options)
|
27
|
+
|
28
|
+
begin
|
29
|
+
@worksheet_index = Integer(options[:worksheet_index])
|
30
|
+
rescue TypeError
|
31
|
+
@worksheet_index = 0
|
32
|
+
end
|
33
|
+
|
34
|
+
begin
|
35
|
+
@cell_index_to_field_mapper = Hash(options[:cell_index_to_field_mapper])
|
36
|
+
rescue TypeError
|
37
|
+
@cell_index_to_field_mapper = options[:cell_index_to_field_mapper]
|
38
|
+
end
|
39
|
+
|
40
|
+
raise ArgumentError, 'cell_index_to_field_mapper is invalid' unless @cell_index_to_field_mapper.is_a?(Hash)
|
41
|
+
raise ArgumentError, 'cell_index_to_field_mapper cannot be empty' if @cell_index_to_field_mapper.empty?
|
42
|
+
end
|
43
|
+
|
44
|
+
|
45
|
+
|
46
|
+
|
47
|
+
# Reads data from the specified spreadsheet
|
48
|
+
# (See {ReaderBackend#read Spreadshot::ReaderBackends::ReaderBackend})
|
49
|
+
#
|
50
|
+
# @param [String] path_to_spreadsheet
|
51
|
+
#
|
52
|
+
# @yield [row_index, row_data]
|
53
|
+
# @yieldparam [Integer] row_index
|
54
|
+
# The index of the current row being read. The first row has an index of 1
|
55
|
+
# @yieldparam [Hash] row_data
|
56
|
+
# A hash representation of the data read from the current row
|
57
|
+
#
|
58
|
+
# @raise [Spreadshot::ReaderError]
|
59
|
+
def read(path_to_spreadsheet)
|
60
|
+
worksheet = RubyXL::Parser.parse(path_to_spreadsheet)[@worksheet_index]
|
61
|
+
headers = @headers
|
62
|
+
|
63
|
+
worksheet.each do |row|
|
64
|
+
if headers
|
65
|
+
headers = false
|
66
|
+
next
|
67
|
+
end
|
68
|
+
|
69
|
+
cell_index = 0
|
70
|
+
current_row_data = {}
|
71
|
+
|
72
|
+
row && row.cells.each do |cell|
|
73
|
+
val = cell && cell.value
|
74
|
+
|
75
|
+
if @cell_index_to_field_mapper[cell_index]
|
76
|
+
current_row_data[@cell_index_to_field_mapper[cell_index]] = val
|
77
|
+
end
|
78
|
+
|
79
|
+
cell_index += 1
|
80
|
+
end
|
81
|
+
|
82
|
+
yield(@current_row_index, current_row_data)
|
83
|
+
@current_row_index += 1
|
84
|
+
end
|
85
|
+
|
86
|
+
return nil
|
87
|
+
rescue => e
|
88
|
+
raise Spreadshot::ReaderError, e.message
|
89
|
+
end
|
90
|
+
end
|
91
|
+
end
|
92
|
+
end
|
@@ -0,0 +1,44 @@
|
|
1
|
+
require 'smarter_csv'
|
2
|
+
|
3
|
+
module Spreadshot
|
4
|
+
module Backends
|
5
|
+
|
6
|
+
# Adapter for the SmarterCSV Gem ({https://github.com/tilo/smarter_csv})
|
7
|
+
class SmarterCSVBackend < ReaderBackend
|
8
|
+
|
9
|
+
# Returns a new instance of SmarterCSVBackend (See {ReaderBackend#initialize Spreadshot::ReaderBackends::ReaderBackend})
|
10
|
+
# @param [Hash] options
|
11
|
+
# @note Ignores :header option
|
12
|
+
def initialize(options = {})
|
13
|
+
options ||= {}
|
14
|
+
options[:headers] = true
|
15
|
+
super(options)
|
16
|
+
end
|
17
|
+
|
18
|
+
|
19
|
+
|
20
|
+
|
21
|
+
# Reads data from the specified CSV file
|
22
|
+
# (See {ReaderBackend#read Spreadshot::ReaderBackends::ReaderBackend})
|
23
|
+
#
|
24
|
+
# @param [String] path_to_spreadsheet
|
25
|
+
#
|
26
|
+
# @yield [row_index, row_data]
|
27
|
+
# @yieldparam [Integer] row_index
|
28
|
+
# The index of the current row being read. The first row has an index of 1
|
29
|
+
# @yieldparam [Hash] row_data
|
30
|
+
# A hash representation of the data read from the current row
|
31
|
+
#
|
32
|
+
# @raise [Spreadshot::ReaderError]
|
33
|
+
def read(path_to_spreadsheet)
|
34
|
+
SmarterCSV.process(path_to_spreadsheet) do |row|
|
35
|
+
current_row_data = row.first
|
36
|
+
yield(@current_row_index, current_row_data)
|
37
|
+
@current_row_index += 1
|
38
|
+
end
|
39
|
+
rescue => e
|
40
|
+
raise Spreadshot::ReaderError, e.message
|
41
|
+
end
|
42
|
+
end
|
43
|
+
end
|
44
|
+
end
|
@@ -0,0 +1,132 @@
|
|
1
|
+
module Spreadshot
|
2
|
+
class Reader
|
3
|
+
|
4
|
+
# @param [Hash] options
|
5
|
+
# @option options [Symbol, Spreadshot::ReaderBackend] :backend
|
6
|
+
# The reader backend to use or the id if one of the provided backends
|
7
|
+
# @option options [Hash] :backend_options
|
8
|
+
# Required if one of the provided backends is used
|
9
|
+
# * :headers (Boolean) [true] Specifies whether the spreadsheet to be read contains headers. Will be ignored if the backend doesn't provide this option (E.g. SmarterCSV expects headers)
|
10
|
+
# * :worksheet_index (Integer) [0] The index of the worksheet to be read. Used for the RubyXL backend
|
11
|
+
# * :cell_index_to_field_mapper (Hash<Integer, [String, Symbol]>) A hash which maps each cell in a row of the spreadsheet to a key in the result hash created for that row. Must be provided for the RubyXL backend
|
12
|
+
#
|
13
|
+
# @example
|
14
|
+
# reader = Spreadshot::Reader.new(backend: :smarter_csv)
|
15
|
+
#
|
16
|
+
# reader = Spreadshot::Reader.new(backend: :ruby_xl, worksheet_index: 0, cell_index_to_field_mapper: {0 => :H1, 1 => :H2, 2 => :H3, 3 => :H4})
|
17
|
+
#
|
18
|
+
# xlsx_backend = Spreadshot::Backends::RubyXLBackend.new(worksheet_index: 0, cell_index_to_field_mapper: {0 => :H1, 1 => :H2, 2 => :H3, 3 => :H4})
|
19
|
+
# reader = Spreadshot::Reader.new(backend: xlsx_backend)
|
20
|
+
def initialize(options)
|
21
|
+
set_backend(options[:backend], options[:backend_options])
|
22
|
+
end
|
23
|
+
|
24
|
+
|
25
|
+
|
26
|
+
|
27
|
+
# Set the backend to use
|
28
|
+
#
|
29
|
+
# @param [Symbol, Spreadshot::Backends::ReaderBackend] backend
|
30
|
+
# The new backend or id of one of the provided backends
|
31
|
+
# @param [Hash] backend_options
|
32
|
+
# Required if one of the provided backends is used
|
33
|
+
# @option backend_options [Boolean] :headers
|
34
|
+
# Specifies whether the spreadsheet to be read contains headers.
|
35
|
+
# Will be ignored if the backend doesn't provide this option (E.g. SmarterCSV expects headers)
|
36
|
+
# Defaults to true
|
37
|
+
# @option backend_options [Integer] :worksheet_index
|
38
|
+
# The index of the worksheet to be read. Used for the RubyXL backend.
|
39
|
+
# Defaults to 0
|
40
|
+
# @option backend_options [Hash<Integer, [Symbol, String]>] :cell_index_to_field_mapper
|
41
|
+
# A hash which maps each cell in a row of the spreadsheet to a key in the
|
42
|
+
# result hash created for that row. Used for the RubyXL backend.
|
43
|
+
# Must be provided
|
44
|
+
#
|
45
|
+
# @raise [Spreadshot::BackendNotFound]
|
46
|
+
# If no backend is provided or if one of the provided backends is not specified
|
47
|
+
#
|
48
|
+
# @example
|
49
|
+
# reader = Spreadshot::Reader.new(backend: :ruby_xl, worksheet_index: 0, cell_index_to_field_mapper: {0 => :H1, 1 => :H2, 2 => :H3, 3 => :H4})
|
50
|
+
# csv_backend = Spreadshot::Backends::SmarterCSVBackend.new
|
51
|
+
# reader.set_backend(csv_backend)
|
52
|
+
def set_backend(backend, backend_options = {})
|
53
|
+
@backend = (backend.is_a?(Spreadshot::Backends::ReaderBackend)) ? backend : build_backend(
|
54
|
+
backend,
|
55
|
+
backend_options
|
56
|
+
)
|
57
|
+
|
58
|
+
raise Spreadshot::BackendNotFound if @backend.nil?
|
59
|
+
end
|
60
|
+
|
61
|
+
|
62
|
+
|
63
|
+
|
64
|
+
# Reads data from the specified spreadsheet
|
65
|
+
#
|
66
|
+
# @param [String] path_to_spreadsheet
|
67
|
+
#
|
68
|
+
# @yield [row_index, row_data]
|
69
|
+
# @yieldparam [Integer] row_index
|
70
|
+
# The index of the current row being read. The first row has an index of 1
|
71
|
+
# @yieldparam [Hash] row_data
|
72
|
+
# A hash representation of the data read from the current row
|
73
|
+
#
|
74
|
+
# @note This method delegates actual reading to the backend
|
75
|
+
#
|
76
|
+
# @example
|
77
|
+
# reader = Spreadshot::Reader.new(backend: :ruby_xl, worksheet_index: 0, cell_index_to_field_mapper: {0 => :H1, 1 => :H2, 2 => :H3, 3 => :H4})
|
78
|
+
# reader.read('spreadshot_test.xlsx'){|row_index, row_data| puts "#{row_index} - #{row_data}"}
|
79
|
+
#
|
80
|
+
# Sample output
|
81
|
+
# 2 - {:H1=>11, :H2=>22, :H3=>33, :H4=>44}
|
82
|
+
# 3 - {:H1=>111, :H2=>222, :H3=>333, :H4=>444}
|
83
|
+
# 4 - {:H1=>1111, :H2=>2222, :H3=>3333, :H4=>4444}
|
84
|
+
|
85
|
+
def read(path_to_spreadsheet)
|
86
|
+
@backend.read(path_to_spreadsheet) {|row_index, row_data| yield(row_index, row_data)}
|
87
|
+
end
|
88
|
+
|
89
|
+
|
90
|
+
|
91
|
+
|
92
|
+
private
|
93
|
+
|
94
|
+
# Creates a reader backend using the backend (id) and options/backend_options provided in #initialize or #set_backend
|
95
|
+
#
|
96
|
+
# @param [Symbol] backend_id the id(key) of the desired backend
|
97
|
+
# @param [Hash] backend_options
|
98
|
+
# options to build the backend with
|
99
|
+
# @option backend_options [Boolean] :headers
|
100
|
+
# Specifies whether the spreadsheet to be read contains headers.
|
101
|
+
# Will be ignored if the backend doesn't provide this option (E.g. SmarterCSV expects headers)
|
102
|
+
# Defaults to true
|
103
|
+
# @option backend_options [Integer] :worksheet_index
|
104
|
+
# The index of the worksheet to be read. Used for the RubyXL backend.
|
105
|
+
# Defaults to true
|
106
|
+
# @option backend_options [Hash<Integer, [Symbol, String]>] :cell_index_to_field_mapper
|
107
|
+
# A hash which maps each cell in a row of the spreadsheet to a key in the
|
108
|
+
# result hash created for that row. Used for the RubyXL backend.
|
109
|
+
# Must be provided
|
110
|
+
#
|
111
|
+
# @return [Spreadshot::Backends::ReaderBackend]
|
112
|
+
def build_backend(backend_id, backend_options = {})
|
113
|
+
backend_options ||= {}
|
114
|
+
return provided_backends[backend_id].call(backend_options)
|
115
|
+
rescue NoMethodError
|
116
|
+
return nil
|
117
|
+
end
|
118
|
+
|
119
|
+
|
120
|
+
|
121
|
+
|
122
|
+
# The provided backends
|
123
|
+
#
|
124
|
+
# @return [Hash]
|
125
|
+
def provided_backends
|
126
|
+
{
|
127
|
+
smarter_csv: ->(backend_options){ Spreadshot::Backends::SmarterCSVBackend.new(backend_options) },
|
128
|
+
ruby_xl: ->(backend_options){ Spreadshot::Backends::RubyXLBackend.new(backend_options) },
|
129
|
+
}
|
130
|
+
end
|
131
|
+
end
|
132
|
+
end
|
data/spreadshot.gemspec
ADDED
@@ -0,0 +1,37 @@
|
|
1
|
+
lib = File.expand_path("lib", __dir__)
|
2
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
3
|
+
require "spreadshot/version"
|
4
|
+
|
5
|
+
Gem::Specification.new do |spec|
|
6
|
+
spec.name = "gkosae-spreadshot"
|
7
|
+
spec.version = Spreadshot::VERSION
|
8
|
+
spec.authors = ["George Osae"]
|
9
|
+
spec.email = ["coderwasp@gmail.com"]
|
10
|
+
|
11
|
+
spec.summary = %q{Library for reading spreadsheets with support for multiple backends}
|
12
|
+
spec.homepage = "https://github.com/gkosae/spreadshot.git"
|
13
|
+
spec.license = "MIT"
|
14
|
+
|
15
|
+
spec.metadata["allowed_push_host"] = "https://rubygems.org"
|
16
|
+
|
17
|
+
spec.metadata["homepage_uri"] = spec.homepage
|
18
|
+
spec.metadata["source_code_uri"] = "https://github.com/gkosae/spreadshot.git"
|
19
|
+
# spec.metadata["changelog_uri"] = "TODO: Put your gem's CHANGELOG.md URL here."
|
20
|
+
|
21
|
+
# Specify which files should be added to the gem when it is released.
|
22
|
+
# The `git ls-files -z` loads the files in the RubyGem that have been added into git.
|
23
|
+
spec.files = Dir.chdir(File.expand_path('..', __FILE__)) do
|
24
|
+
`git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
25
|
+
end
|
26
|
+
spec.bindir = "exe"
|
27
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
28
|
+
spec.require_paths = ["lib"]
|
29
|
+
|
30
|
+
spec.add_dependency "smarter_csv", "~> 1.2.6"
|
31
|
+
spec.add_dependency "rubyXL", "~> 3.3.33"
|
32
|
+
|
33
|
+
spec.add_development_dependency "bundler", "~> 2.0"
|
34
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
35
|
+
spec.add_development_dependency "byebug", "~> 11.0"
|
36
|
+
spec.add_development_dependency "rspec", "~> 3.0"
|
37
|
+
end
|
metadata
ADDED
@@ -0,0 +1,149 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: gkosae-spreadshot
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- George Osae
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2019-10-31 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: smarter_csv
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: 1.2.6
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: 1.2.6
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rubyXL
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: 3.3.33
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: 3.3.33
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: bundler
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '2.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '2.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: rake
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '10.0'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '10.0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: byebug
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '11.0'
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - "~>"
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '11.0'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: rspec
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - "~>"
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '3.0'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - "~>"
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '3.0'
|
97
|
+
description:
|
98
|
+
email:
|
99
|
+
- coderwasp@gmail.com
|
100
|
+
executables: []
|
101
|
+
extensions: []
|
102
|
+
extra_rdoc_files: []
|
103
|
+
files:
|
104
|
+
- ".gitignore"
|
105
|
+
- ".rspec"
|
106
|
+
- ".yardopts"
|
107
|
+
- CHANGELOG.md
|
108
|
+
- Gemfile
|
109
|
+
- Gemfile.lock
|
110
|
+
- LICENSE.txt
|
111
|
+
- README.md
|
112
|
+
- Rakefile
|
113
|
+
- bin/console
|
114
|
+
- bin/setup
|
115
|
+
- lib/spreadshot.rb
|
116
|
+
- lib/spreadshot/backends.rb
|
117
|
+
- lib/spreadshot/backends/reader_backend.rb
|
118
|
+
- lib/spreadshot/backends/ruby_xl_backend.rb
|
119
|
+
- lib/spreadshot/backends/smarter_csv_backend.rb
|
120
|
+
- lib/spreadshot/reader.rb
|
121
|
+
- lib/spreadshot/version.rb
|
122
|
+
- spreadshot.gemspec
|
123
|
+
homepage: https://github.com/gkosae/spreadshot.git
|
124
|
+
licenses:
|
125
|
+
- MIT
|
126
|
+
metadata:
|
127
|
+
allowed_push_host: https://rubygems.org
|
128
|
+
homepage_uri: https://github.com/gkosae/spreadshot.git
|
129
|
+
source_code_uri: https://github.com/gkosae/spreadshot.git
|
130
|
+
post_install_message:
|
131
|
+
rdoc_options: []
|
132
|
+
require_paths:
|
133
|
+
- lib
|
134
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
135
|
+
requirements:
|
136
|
+
- - ">="
|
137
|
+
- !ruby/object:Gem::Version
|
138
|
+
version: '0'
|
139
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
140
|
+
requirements:
|
141
|
+
- - ">="
|
142
|
+
- !ruby/object:Gem::Version
|
143
|
+
version: '0'
|
144
|
+
requirements: []
|
145
|
+
rubygems_version: 3.0.6
|
146
|
+
signing_key:
|
147
|
+
specification_version: 4
|
148
|
+
summary: Library for reading spreadsheets with support for multiple backends
|
149
|
+
test_files: []
|