read_xls 0.1.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (49) hide show
  1. checksums.yaml +7 -0
  2. data/.gitignore +9 -0
  3. data/.rspec +2 -0
  4. data/.travis.yml +4 -0
  5. data/CODE_OF_CONDUCT.md +13 -0
  6. data/Gemfile +4 -0
  7. data/LICENSE +21 -0
  8. data/README.md +52 -0
  9. data/Rakefile +6 -0
  10. data/bin/console +14 -0
  11. data/bin/setup +7 -0
  12. data/lib/read_xls.rb +49 -0
  13. data/lib/read_xls/evaluator/blank.rb +9 -0
  14. data/lib/read_xls/evaluator/boolean.rb +15 -0
  15. data/lib/read_xls/evaluator/extended_format.rb +20 -0
  16. data/lib/read_xls/evaluator/format_number.rb +47 -0
  17. data/lib/read_xls/evaluator/formula.rb +33 -0
  18. data/lib/read_xls/evaluator/number.rb +24 -0
  19. data/lib/read_xls/evaluator/rk_number.rb +38 -0
  20. data/lib/read_xls/evaluator/row.rb +26 -0
  21. data/lib/read_xls/evaluator/sst_string.rb +16 -0
  22. data/lib/read_xls/record_handler.rb +262 -0
  23. data/lib/read_xls/record_handler/base.rb +19 -0
  24. data/lib/read_xls/record_handler/blank.rb +11 -0
  25. data/lib/read_xls/record_handler/bof.rb +9 -0
  26. data/lib/read_xls/record_handler/boolerr.rb +11 -0
  27. data/lib/read_xls/record_handler/boundsheet.rb +45 -0
  28. data/lib/read_xls/record_handler/format.rb +20 -0
  29. data/lib/read_xls/record_handler/formula.rb +17 -0
  30. data/lib/read_xls/record_handler/label_sst.rb +15 -0
  31. data/lib/read_xls/record_handler/mul_rk.rb +30 -0
  32. data/lib/read_xls/record_handler/not_implemented.rb +11 -0
  33. data/lib/read_xls/record_handler/number.rb +18 -0
  34. data/lib/read_xls/record_handler/rk.rb +23 -0
  35. data/lib/read_xls/record_handler/row.rb +10 -0
  36. data/lib/read_xls/record_handler/skip.rb +8 -0
  37. data/lib/read_xls/record_handler/sst.rb +36 -0
  38. data/lib/read_xls/record_handler/string.rb +13 -0
  39. data/lib/read_xls/record_handler/xf.rb +19 -0
  40. data/lib/read_xls/spreadsheet.rb +60 -0
  41. data/lib/read_xls/type/extended_format.rb +25 -0
  42. data/lib/read_xls/version.rb +3 -0
  43. data/lib/read_xls/workbook.rb +11 -0
  44. data/lib/read_xls/workbook/shared_string_table.rb +15 -0
  45. data/lib/read_xls/workbook/worksheet.rb +11 -0
  46. data/lib/read_xls/workbook/worksheet_builder.rb +44 -0
  47. data/lib/read_xls/workbook_builder.rb +96 -0
  48. data/read_xls.gemspec +27 -0
  49. metadata +147 -0
@@ -0,0 +1,7 @@
1
+ ---
2
+ SHA1:
3
+ metadata.gz: 7e0b7f7a9fe0bc349e97f2bfebdd52f667d66b0d
4
+ data.tar.gz: d17fcbb0b353a085527b1c99e718541c973a7e3e
5
+ SHA512:
6
+ metadata.gz: 077662dd44d4b1aaef8fc044977762a895cda469664ac310f2c425ec6b375b27f4fafcfa0b5bec8a5c6c0b4e66fcba618eb7a5ae1870f4e3cf04f90da4659155
7
+ data.tar.gz: 64d26284538dcafc6f09de637ba807068f1e490c6ef22021dd05e8dd8c4b1ac8be82a6c5ee4bf79dd075a4fb1602175a7b7347a5b57b73db6faf5662c2bc4335
@@ -0,0 +1,9 @@
1
+ /.bundle/
2
+ /.yardoc
3
+ /Gemfile.lock
4
+ /_yardoc/
5
+ /coverage/
6
+ /doc/
7
+ /pkg/
8
+ /spec/reports/
9
+ /tmp/
data/.rspec ADDED
@@ -0,0 +1,2 @@
1
+ --format documentation
2
+ --color
@@ -0,0 +1,4 @@
1
+ language: ruby
2
+ rvm:
3
+ - 2.2.2
4
+ before_install: gem install bundler -v 1.10.6
@@ -0,0 +1,13 @@
1
+ # Contributor Code of Conduct
2
+
3
+ As contributors and maintainers of this project, we pledge to respect all people who contribute through reporting issues, posting feature requests, updating documentation, submitting pull requests or patches, and other activities.
4
+
5
+ We are committed to making participation in this project a harassment-free experience for everyone, regardless of level of experience, gender, gender identity and expression, sexual orientation, disability, personal appearance, body size, race, ethnicity, age, or religion.
6
+
7
+ Examples of unacceptable behavior by participants include the use of sexual language or imagery, derogatory comments or personal attacks, trolling, public or private harassment, insults, or other unprofessional conduct.
8
+
9
+ Project maintainers have the right and responsibility to remove, edit, or reject comments, commits, code, wiki edits, issues, and other contributions that are not aligned to this Code of Conduct. Project maintainers who do not follow the Code of Conduct may be removed from the project team.
10
+
11
+ Instances of abusive, harassing, or otherwise unacceptable behavior may be reported by opening an issue or contacting one or more of the project maintainers.
12
+
13
+ This Code of Conduct is adapted from the [Contributor Covenant](http://contributor-covenant.org), version 1.0.0, available at [http://contributor-covenant.org/version/1/0/0/](http://contributor-covenant.org/version/1/0/0/)
data/Gemfile ADDED
@@ -0,0 +1,4 @@
1
+ source 'https://rubygems.org'
2
+
3
+ # Specify your gem's dependencies in read_xls.gemspec
4
+ gemspec
data/LICENSE ADDED
@@ -0,0 +1,21 @@
1
+ The MIT License (MIT)
2
+
3
+ Copyright (c) 2016 P2Binvestor
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.
@@ -0,0 +1,52 @@
1
+ # ReadXls
2
+
3
+ A gem for parsing XLS docs.
4
+
5
+ ## Installation
6
+
7
+ Add this line to your application's Gemfile:
8
+
9
+ ```ruby
10
+ gem "read_xls"
11
+ ```
12
+
13
+ And then execute:
14
+
15
+ $ bundle
16
+
17
+ Or install it yourself as:
18
+
19
+ $ gem install read_xls
20
+
21
+ ## Usage
22
+
23
+ Simply use the `parse` command to get back a spreadsheet with many sheets. Each spreadsheet contains
24
+ a rows method which returns and array or arrays (rows x columns).
25
+
26
+ ```ruby
27
+ spreadsheet = ::ReadXls.parse("path/to/spreadsheet.xls")
28
+
29
+ spreadsheet.sheets.each do |sheet|
30
+ sheet.rows.each do |columns|
31
+ columns.each do |column|
32
+ puts column
33
+ end
34
+ end
35
+ end
36
+ ```
37
+
38
+ ## Development
39
+
40
+ After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
41
+
42
+ 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).
43
+
44
+ ## Contributing
45
+
46
+ Bug reports and pull requests are welcome on GitHub at https://github.com/p2bi/read_xls. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](contributor-covenant.org) code of conduct.
47
+
48
+
49
+ ## License
50
+
51
+ The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
52
+
@@ -0,0 +1,6 @@
1
+ require "bundler/gem_tasks"
2
+ require "rspec/core/rake_task"
3
+
4
+ RSpec::Core::RakeTask.new(:spec)
5
+
6
+ task :default => :spec
@@ -0,0 +1,14 @@
1
+ #!/usr/bin/env ruby
2
+
3
+ require "bundler/setup"
4
+ require "read_xls"
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
@@ -0,0 +1,7 @@
1
+ #!/bin/bash
2
+ set -euo pipefail
3
+ IFS=$'\n\t'
4
+
5
+ bundle install
6
+
7
+ # Do any other automated setup that you need to do here
@@ -0,0 +1,49 @@
1
+ require "read_xls/version"
2
+
3
+ require "bigdecimal"
4
+ require "ole/storage"
5
+
6
+ require "read_xls/evaluator/boolean"
7
+ require "read_xls/evaluator/blank"
8
+ require "read_xls/evaluator/extended_format"
9
+ require "read_xls/evaluator/format_number"
10
+ require "read_xls/evaluator/formula"
11
+ require "read_xls/evaluator/number"
12
+ require "read_xls/evaluator/rk_number"
13
+ require "read_xls/evaluator/row"
14
+ require "read_xls/evaluator/sst_string"
15
+
16
+ require "read_xls/type/extended_format"
17
+
18
+ require "read_xls/workbook"
19
+ require "read_xls/workbook_builder"
20
+ require "read_xls/workbook/worksheet"
21
+ require "read_xls/workbook/shared_string_table"
22
+ require "read_xls/workbook/worksheet_builder"
23
+
24
+ require "read_xls/record_handler/base"
25
+ require "read_xls/record_handler/blank"
26
+ require "read_xls/record_handler/bof"
27
+ require "read_xls/record_handler/boolerr"
28
+ require "read_xls/record_handler/boundsheet"
29
+ require "read_xls/record_handler/format"
30
+ require "read_xls/record_handler/formula"
31
+ require "read_xls/record_handler/label_sst"
32
+ require "read_xls/record_handler/mul_rk"
33
+ require "read_xls/record_handler/number"
34
+ require "read_xls/record_handler/not_implemented"
35
+ require "read_xls/record_handler/row"
36
+ require "read_xls/record_handler/rk"
37
+ require "read_xls/record_handler/skip"
38
+ require "read_xls/record_handler/sst"
39
+ require "read_xls/record_handler/string"
40
+ require "read_xls/record_handler/xf"
41
+ require "read_xls/record_handler"
42
+
43
+ require "read_xls/spreadsheet"
44
+
45
+ module ReadXls
46
+ def self.parse(xls_path)
47
+ Spreadsheet.parse(xls_path)
48
+ end
49
+ end
@@ -0,0 +1,9 @@
1
+ module ReadXls
2
+ module Evaluator
3
+ class Blank
4
+ def evaluate
5
+ nil
6
+ end
7
+ end
8
+ end
9
+ end
@@ -0,0 +1,15 @@
1
+ module ReadXls
2
+ module Evaluator
3
+ class Boolean
4
+ attr_accessor :value
5
+
6
+ def initialize(value)
7
+ self.value = value
8
+ end
9
+
10
+ def evaluate
11
+ value == 1
12
+ end
13
+ end
14
+ end
15
+ end
@@ -0,0 +1,20 @@
1
+ module ReadXls
2
+ module Evaluator
3
+ class ExtendedFormat
4
+ attr_accessor :builder, :format_index
5
+
6
+ def initialize(options)
7
+ self.builder = options.fetch(:builder)
8
+ self.format_index = options.fetch(:format_index)
9
+ end
10
+
11
+ def evaluate
12
+ format_string = builder.formats[format_index]
13
+
14
+ ::ReadXls::Type::ExtendedFormat.new(
15
+ :format_string => format_string
16
+ )
17
+ end
18
+ end
19
+ end
20
+ end
@@ -0,0 +1,47 @@
1
+ module ReadXls
2
+ module Evaluator
3
+ class FormatNumber
4
+ SECONDS_IN_DAY = 60 * 60 * 24
5
+
6
+ attr_accessor :number, :extended_format
7
+
8
+ def initialize(number, extended_format)
9
+ self.number = BigDecimal.new(number.to_s)
10
+ self.extended_format = extended_format
11
+ end
12
+
13
+ def evaluate
14
+ return number unless extended_format
15
+
16
+ case extended_format.format_type
17
+ when :date
18
+ days_since_datemode = number.to_i
19
+ inner_day_fraction = number.frac
20
+
21
+ date = build_date(days_since_datemode)
22
+
23
+ if inner_day_fraction == 0
24
+ date
25
+ else
26
+ build_time(date, inner_day_fraction)
27
+ end
28
+ else
29
+ number
30
+ end
31
+ end
32
+
33
+
34
+ private
35
+
36
+ def build_date(days_since_datemode)
37
+ Date.new(1899, 12, 30) + days_since_datemode
38
+ end
39
+
40
+
41
+ def build_time(date, inner_day_fraction)
42
+ time = Time.parse("#{date.year}-#{date.month}-#{date.day}T00:00:00Z")
43
+ time + (inner_day_fraction * SECONDS_IN_DAY).round(0)
44
+ end
45
+ end
46
+ end
47
+ end
@@ -0,0 +1,33 @@
1
+ module ReadXls
2
+ module Evaluator
3
+ class Formula
4
+ attr_accessor :builder, :result_number, :result_bytes
5
+
6
+ def initialize(builder, result_test, result_bytes)
7
+ self.builder = builder
8
+ self.result_number = result_test != 0xFFFF
9
+ self.result_bytes = result_bytes
10
+ end
11
+
12
+ def evaluate
13
+ if result_number?
14
+ result_bytes.unpack("E").first
15
+ elsif result_string?
16
+ builder.next_formula_string!
17
+ elsif result_boolerr?
18
+ raise NotImplementedError
19
+ else
20
+ raise NotImplementedError, "can't figure out what type of formula this is"
21
+ end
22
+ end
23
+
24
+ def result_number?
25
+ result_number
26
+ end
27
+
28
+ def result_string?
29
+ !result_number? && result_bytes.byteslice(0, 1).unpack("C").first == 0
30
+ end
31
+ end
32
+ end
33
+ end
@@ -0,0 +1,24 @@
1
+ module ReadXls
2
+ module Evaluator
3
+ class Number
4
+ attr_accessor :builder, :number, :xf_index
5
+
6
+ def initialize(builder, number, xf_index)
7
+ self.builder = builder
8
+ self.number = number
9
+ self.xf_index = xf_index
10
+ end
11
+
12
+ def evaluate
13
+ FormatNumber.new(number, extended_format).evaluate
14
+ end
15
+
16
+
17
+ private
18
+
19
+ def extended_format
20
+ builder.extended_formats[xf_index]
21
+ end
22
+ end
23
+ end
24
+ end
@@ -0,0 +1,38 @@
1
+ module ReadXls
2
+ module Evaluator
3
+ class RkNumber
4
+ attr_accessor :builder, :rk_bits, :xf_index
5
+
6
+ def initialize(builder, rk_bits, xf_index)
7
+ self.builder = builder
8
+ self.rk_bits = rk_bits
9
+ self.xf_index = xf_index
10
+ end
11
+
12
+ def evaluate
13
+ value = if (rk_bits & 0x02) == 0
14
+ rk_bits_without_last_2 = (rk_bits & 0xfffffffc)
15
+ float_in_64_bit_string_big_endian = (("%032b" % rk_bits_without_last_2) + "0"*32)
16
+ [float_in_64_bit_string_big_endian].pack("B*").unpack("G").first
17
+ else
18
+ rk_bits >> 2
19
+ end
20
+
21
+ value = if (rk_bits & 0x01) == 0
22
+ value
23
+ else
24
+ value / 100.0
25
+ end
26
+
27
+ FormatNumber.new(value, extended_format).evaluate
28
+ end
29
+
30
+
31
+ private
32
+
33
+ def extended_format
34
+ builder.extended_formats[xf_index]
35
+ end
36
+ end
37
+ end
38
+ end
@@ -0,0 +1,26 @@
1
+ module ReadXls
2
+ module Evaluator
3
+ class Row
4
+ attr_accessor :row_number, :first_col, :last_col, :columns
5
+
6
+ def initialize(row_number, first_col, last_col)
7
+ self.row_number = row_number
8
+ self.first_col = first_col
9
+ self.last_col = last_col
10
+ self.columns = []
11
+ end
12
+
13
+ def add_column(column_index, value)
14
+ columns[column_index] = value
15
+ end
16
+
17
+ def evaluate
18
+ columns.each_with_index.each do |_, column_index|
19
+ columns[column_index] ||= ::ReadXls::Evaluator::Blank.new
20
+ end
21
+
22
+ columns.map(&:evaluate)
23
+ end
24
+ end
25
+ end
26
+ end
@@ -0,0 +1,16 @@
1
+ module ReadXls
2
+ module Evaluator
3
+ class SstString
4
+ attr_accessor :sst_index, :builder
5
+
6
+ def initialize(sst_index, builder)
7
+ self.sst_index = sst_index
8
+ self.builder = builder
9
+ end
10
+
11
+ def evaluate
12
+ builder.sst.index(sst_index)
13
+ end
14
+ end
15
+ end
16
+ end