xsv 0.3.2 → 0.3.3
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +5 -0
- data/Gemfile.lock +2 -2
- data/Rakefile +9 -2
- data/lib/xsv/helpers.rb +11 -4
- data/lib/xsv/shared_strings_parser.rb +2 -0
- data/lib/xsv/sheet.rb +27 -3
- data/lib/xsv/sheet_bounds_handler.rb +3 -1
- data/lib/xsv/sheet_rows_handler.rb +4 -0
- data/lib/xsv/styles_handler.rb +1 -0
- data/lib/xsv/version.rb +1 -1
- data/lib/xsv/workbook.rb +24 -3
- data/lib/xsv.rb +4 -0
- data/xsv.gemspec +8 -2
- metadata +11 -6
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 14550b4494b57e9363e5b189222e242177e9c1328377d5458bb475231a6726b7
|
4
|
+
data.tar.gz: bddb0f2b94dcd67563f8d1b5525c6dffae2f3718fd08d4800e9e09ac21c57d59
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 38a39e5b4484214a1a530ddb5f5add47d56c3cff4df1b20e519bc4712e693c1ab6cca6270779f3dd24c7e019835f7b98daccc16f42fc5f905a66fe02623323c0
|
7
|
+
data.tar.gz: b60b28263fcf0352f85b254a61866463dca7ac7e077314ff1e3584ccfd6b90ccd03d7edf8e33f3f63441db17fa15f2ed7139cb4f55ae7c912a555ea5ff008e39
|
data/CHANGELOG.md
ADDED
data/Gemfile.lock
CHANGED
@@ -10,7 +10,7 @@ GEM
|
|
10
10
|
specs:
|
11
11
|
minitest (5.14.0)
|
12
12
|
ox (2.13.2)
|
13
|
-
rake (
|
13
|
+
rake (13.0.1)
|
14
14
|
rubyzip (2.2.0)
|
15
15
|
|
16
16
|
PLATFORMS
|
@@ -19,7 +19,7 @@ PLATFORMS
|
|
19
19
|
DEPENDENCIES
|
20
20
|
bundler (~> 1.17)
|
21
21
|
minitest (~> 5.0)
|
22
|
-
rake (~>
|
22
|
+
rake (~> 13.0)
|
23
23
|
xsv!
|
24
24
|
|
25
25
|
BUNDLED WITH
|
data/Rakefile
CHANGED
@@ -2,9 +2,16 @@ require "bundler/gem_tasks"
|
|
2
2
|
require "rake/testtask"
|
3
3
|
|
4
4
|
Rake::TestTask.new(:test) do |t|
|
5
|
-
t.libs << "test"
|
6
5
|
t.libs << "lib"
|
6
|
+
t.libs << "test"
|
7
7
|
t.test_files = FileList["test/**/*_test.rb"]
|
8
8
|
end
|
9
9
|
|
10
|
-
|
10
|
+
Rake::TestTask.new(:bench) do |t|
|
11
|
+
t.libs << "lib"
|
12
|
+
t.libs << "test"
|
13
|
+
t.test_files = FileList["test/**/*_benchmark.rb"]
|
14
|
+
end
|
15
|
+
|
16
|
+
task :default => [:test, :bench]
|
17
|
+
|
data/lib/xsv/helpers.rb
CHANGED
@@ -1,6 +1,8 @@
|
|
1
1
|
# frozen_string_literal: true
|
2
2
|
module Xsv
|
3
3
|
module Helpers
|
4
|
+
# The default OOXML Spreadheet number formats according to the ECMA standard
|
5
|
+
# User formats are appended from index 174 onward
|
4
6
|
BUILT_IN_NUMBER_FORMATS = {
|
5
7
|
1 => "0",
|
6
8
|
2 => "0.00",
|
@@ -38,13 +40,15 @@ module Xsv
|
|
38
40
|
MINUTE = 60.freeze
|
39
41
|
HOUR = 3600.freeze
|
40
42
|
A_CODEPOINT = 'A'.ord.freeze
|
43
|
+
# The epoch for all dates in OOXML Spreadsheet documents
|
41
44
|
EPOCH = Date.new(1899, 12, 30).freeze
|
42
45
|
|
43
|
-
# Return the index number for the given Excel column name
|
46
|
+
# Return the index number for the given Excel column name (i.e. "A1" => 0)
|
44
47
|
def column_index(col)
|
45
|
-
col
|
46
|
-
|
47
|
-
|
48
|
+
col.each_codepoint.reduce(0) do |sum, n|
|
49
|
+
break sum - 1 if n < A_CODEPOINT # reached a number
|
50
|
+
sum * 26 + (n - A_CODEPOINT + 1)
|
51
|
+
end
|
48
52
|
end
|
49
53
|
|
50
54
|
# Return a Date for the given Excel date value
|
@@ -73,6 +77,7 @@ module Xsv
|
|
73
77
|
"%02d:%02d" % [hours, minutes]
|
74
78
|
end
|
75
79
|
|
80
|
+
# Returns a time including a date as a {Time} object
|
76
81
|
def parse_datetime(number)
|
77
82
|
date_base = number.truncate
|
78
83
|
time = parse_date(date_base).to_time
|
@@ -85,6 +90,7 @@ module Xsv
|
|
85
90
|
time + hours * HOUR + minutes.round * MINUTE
|
86
91
|
end
|
87
92
|
|
93
|
+
# Returns a number as either Integer or Float
|
88
94
|
def parse_number(string)
|
89
95
|
if string.include? "."
|
90
96
|
string.to_f
|
@@ -93,6 +99,7 @@ module Xsv
|
|
93
99
|
end
|
94
100
|
end
|
95
101
|
|
102
|
+
# Apply date or time number formats, if applicable
|
96
103
|
def parse_number_format(number, format)
|
97
104
|
number = parse_number(number) if number.is_a?(String)
|
98
105
|
|
data/lib/xsv/sheet.rb
CHANGED
@@ -1,14 +1,34 @@
|
|
1
1
|
# frozen_string_literal: true
|
2
2
|
module Xsv
|
3
|
+
# Sheet represents a single worksheet from a workbook and is normally accessed through {Workbook#sheets}
|
4
|
+
#
|
5
|
+
# Xsv is designed for worksheets with a single table of data, optionally with a header row. Because sheet implements
|
6
|
+
# {Enumerable} the rows in the worksheet can be iterated over using methods such as `#each` and `#map`
|
7
|
+
#
|
8
|
+
# By default Sheet will return rows as arrays. But by calling the {#parse_headers!} method the first row of the sheet
|
9
|
+
# will be parsed and Sheet will switch to hash mode, returning each row as a hash with the values from the first
|
10
|
+
# row as keys.
|
11
|
+
#
|
12
|
+
# If the sheet contains leading data before the first row of data or the header row, this can be skipped by setting the
|
13
|
+
# {row_skip} attribute.
|
3
14
|
class Sheet
|
4
15
|
include Enumerable
|
5
16
|
include Xsv::Helpers
|
6
17
|
|
18
|
+
# Returns the current mode. Call {#parse_headers!} to switch to `:hash` mode
|
19
|
+
# @return [Symbol] `:hash` or `:array`
|
7
20
|
attr_reader :mode
|
8
21
|
|
9
|
-
# Set a number of rows to skip at the top of the sheet (header row offset)
|
22
|
+
# Set a number of rows to skip at the top of the sheet (header row offset).
|
23
|
+
# For hash mode, do not skip the header row as this will be automatically
|
24
|
+
# skipped.
|
10
25
|
attr_accessor :row_skip
|
11
26
|
|
27
|
+
# Create a new instance of Sheet. This is used internally by the {Workbook}.
|
28
|
+
# There is no need to create Sheets from application code.
|
29
|
+
#
|
30
|
+
# @param workbook [Workbook] The Workbook with shared data such as shared strings and styles
|
31
|
+
# @param io [IO] A handle to an open worksheet XML file
|
12
32
|
def initialize(workbook, io)
|
13
33
|
@workbook = workbook
|
14
34
|
@io = io
|
@@ -19,11 +39,12 @@ module Xsv
|
|
19
39
|
@last_row, @column_count = SheetBoundsHandler.get_bounds(@io, @workbook)
|
20
40
|
end
|
21
41
|
|
42
|
+
# @return [String]
|
22
43
|
def inspect
|
23
44
|
"#<#{self.class.name}:#{self.object_id}>"
|
24
45
|
end
|
25
46
|
|
26
|
-
# Iterate over rows
|
47
|
+
# Iterate over rows, returning either hashes or arrays based on the current mode.
|
27
48
|
def each_row
|
28
49
|
@io.rewind
|
29
50
|
|
@@ -38,7 +59,8 @@ module Xsv
|
|
38
59
|
|
39
60
|
alias each each_row
|
40
61
|
|
41
|
-
# Get row by number, starting at 0
|
62
|
+
# Get row by number, starting at 0. Returns either a hash or an array based on the current row.
|
63
|
+
# If the specified index is out of bounds an empty row is returned.
|
42
64
|
def [](number)
|
43
65
|
each_with_index do |row, i|
|
44
66
|
return row if i == number
|
@@ -49,6 +71,7 @@ module Xsv
|
|
49
71
|
|
50
72
|
# Load headers in the top row of the worksheet. After parsing of headers
|
51
73
|
# all methods return hashes instead of arrays
|
74
|
+
# @return [true]
|
52
75
|
def parse_headers!
|
53
76
|
@headers = parse_headers
|
54
77
|
@mode = :hash
|
@@ -56,6 +79,7 @@ module Xsv
|
|
56
79
|
true
|
57
80
|
end
|
58
81
|
|
82
|
+
# Return the headers of the sheet as an array
|
59
83
|
def headers
|
60
84
|
if @headers.any?
|
61
85
|
@headers
|
@@ -1,6 +1,8 @@
|
|
1
1
|
# frozen_string_literal: true
|
2
2
|
module Xsv
|
3
|
-
# SheetBoundsHandler scans a sheet looking for the outer bounds of the content within
|
3
|
+
# SheetBoundsHandler scans a sheet looking for the outer bounds of the content within.
|
4
|
+
# This is used internally when opening a sheet to deal with worksheets that do not
|
5
|
+
# have a correct dimension tag.
|
4
6
|
class SheetBoundsHandler < Ox::Sax
|
5
7
|
include Xsv::Helpers
|
6
8
|
|
@@ -1,9 +1,13 @@
|
|
1
1
|
# frozen_string_literal: true
|
2
2
|
module Xsv
|
3
|
+
# This is the core worksheet parser, implemented as an Ox::Sax handler. This is
|
4
|
+
# used internally to enumerate rows.
|
3
5
|
class SheetRowsHandler < Ox::Sax
|
4
6
|
include Xsv::Helpers
|
5
7
|
|
6
8
|
def format_cell
|
9
|
+
return nil if @current_value.empty?
|
10
|
+
|
7
11
|
case @current_cell[:t]
|
8
12
|
when "s"
|
9
13
|
@workbook.shared_strings[@current_value.to_i]
|
data/lib/xsv/styles_handler.rb
CHANGED
data/lib/xsv/version.rb
CHANGED
data/lib/xsv/workbook.rb
CHANGED
@@ -2,11 +2,18 @@
|
|
2
2
|
require 'zip'
|
3
3
|
|
4
4
|
module Xsv
|
5
|
+
# An OOXML Spreadsheet document is called a Workbook. A Workbook consists of
|
6
|
+
# multiple Sheets that are available in the array that's accessible through {#sheets}
|
5
7
|
class Workbook
|
6
8
|
|
7
|
-
|
9
|
+
# Access the Sheet objects contained in the workbook
|
10
|
+
# @return [Array<Sheet>]
|
11
|
+
attr_reader :sheets
|
8
12
|
|
9
|
-
|
13
|
+
attr_reader :shared_strings, :xfs, :numFmts, :trim_empty_rows
|
14
|
+
|
15
|
+
# Open the workbook of the given filename, string or buffer. For additional
|
16
|
+
# options see {.initialize}
|
10
17
|
def self.open(data, **kws)
|
11
18
|
if data.is_a?(IO)
|
12
19
|
@workbook = self.new(Zip::File.open_buffer(data), **kws)
|
@@ -17,7 +24,8 @@ module Xsv
|
|
17
24
|
end
|
18
25
|
end
|
19
26
|
|
20
|
-
# Open a workbook from an instance of Zip::File
|
27
|
+
# Open a workbook from an instance of {Zip::File}. Generally it's recommended
|
28
|
+
# to use the {.open} method instead of the constructor.
|
21
29
|
#
|
22
30
|
# Options:
|
23
31
|
#
|
@@ -36,10 +44,23 @@ module Xsv
|
|
36
44
|
fetch_sheets
|
37
45
|
end
|
38
46
|
|
47
|
+
# @return [String]
|
39
48
|
def inspect
|
40
49
|
"#<#{self.class.name}:#{self.object_id}>"
|
41
50
|
end
|
42
51
|
|
52
|
+
# Close the handle to the workbook file and leave all resources for the GC to collect
|
53
|
+
# @return [true]
|
54
|
+
def close
|
55
|
+
@zip.close
|
56
|
+
@sheets = nil
|
57
|
+
@xfs = nil
|
58
|
+
@numFmts = nil
|
59
|
+
@shared_strings = nil
|
60
|
+
|
61
|
+
true
|
62
|
+
end
|
63
|
+
|
43
64
|
private
|
44
65
|
|
45
66
|
def fetch_shared_strings
|
data/lib/xsv.rb
CHANGED
@@ -11,6 +11,10 @@ require "xsv/styles_handler"
|
|
11
11
|
require "xsv/version"
|
12
12
|
require "xsv/workbook"
|
13
13
|
|
14
|
+
# XSV is a fast, lightweight parser for Office Open XML spreadsheet files
|
15
|
+
# (commonly known as Excel or .xlsx files). It strives to be minimal in the
|
16
|
+
# sense that it provides nothing a CSV reader wouldn't, meaning it only
|
17
|
+
# deals with minimal formatting and cannot create or modify documents.
|
14
18
|
module Xsv
|
15
19
|
class Error < StandardError; end
|
16
20
|
# An AssertionFailed error indicates an unexpected condition, meaning a bug
|
data/xsv.gemspec
CHANGED
@@ -9,7 +9,13 @@ Gem::Specification.new do |spec|
|
|
9
9
|
spec.authors = ["Martijn Storck"]
|
10
10
|
spec.email = ["martijn@storck.io"]
|
11
11
|
|
12
|
-
spec.summary = "
|
12
|
+
spec.summary = "A fast and lightweiggt xlsx parser that provides nothing a CSV parser wouldn't"
|
13
|
+
spec.description = <<-EOF
|
14
|
+
XSV is a fast, lightweight parser for Office Open XML spreadsheet files
|
15
|
+
(commonly known as Excel or .xlsx files). It strives to be minimal in the
|
16
|
+
sense that it provides nothing a CSV reader wouldn't, meaning it only
|
17
|
+
deals with minimal formatting and cannot create or modify documents.
|
18
|
+
EOF
|
13
19
|
spec.homepage = "https://github.com/martijn/xsv"
|
14
20
|
spec.license = "MIT"
|
15
21
|
|
@@ -37,6 +43,6 @@ Gem::Specification.new do |spec|
|
|
37
43
|
spec.add_dependency "ox", "~> 2.13"
|
38
44
|
|
39
45
|
spec.add_development_dependency "bundler", "~> 1.17"
|
40
|
-
spec.add_development_dependency "rake", "~>
|
46
|
+
spec.add_development_dependency "rake", "~> 13.0"
|
41
47
|
spec.add_development_dependency "minitest", "~> 5.0"
|
42
48
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: xsv
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.3.
|
4
|
+
version: 0.3.3
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Martijn Storck
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2020-02
|
11
|
+
date: 2020-03-02 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: rubyzip
|
@@ -58,14 +58,14 @@ dependencies:
|
|
58
58
|
requirements:
|
59
59
|
- - "~>"
|
60
60
|
- !ruby/object:Gem::Version
|
61
|
-
version: '
|
61
|
+
version: '13.0'
|
62
62
|
type: :development
|
63
63
|
prerelease: false
|
64
64
|
version_requirements: !ruby/object:Gem::Requirement
|
65
65
|
requirements:
|
66
66
|
- - "~>"
|
67
67
|
- !ruby/object:Gem::Version
|
68
|
-
version: '
|
68
|
+
version: '13.0'
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
70
|
name: minitest
|
71
71
|
requirement: !ruby/object:Gem::Requirement
|
@@ -80,7 +80,11 @@ dependencies:
|
|
80
80
|
- - "~>"
|
81
81
|
- !ruby/object:Gem::Version
|
82
82
|
version: '5.0'
|
83
|
-
description:
|
83
|
+
description: |2
|
84
|
+
XSV is a fast, lightweight parser for Office Open XML spreadsheet files
|
85
|
+
(commonly known as Excel or .xlsx files). It strives to be minimal in the
|
86
|
+
sense that it provides nothing a CSV reader wouldn't, meaning it only
|
87
|
+
deals with minimal formatting and cannot create or modify documents.
|
84
88
|
email:
|
85
89
|
- martijn@storck.io
|
86
90
|
executables: []
|
@@ -89,6 +93,7 @@ extra_rdoc_files: []
|
|
89
93
|
files:
|
90
94
|
- ".gitignore"
|
91
95
|
- ".travis.yml"
|
96
|
+
- CHANGELOG.md
|
92
97
|
- Gemfile
|
93
98
|
- Gemfile.lock
|
94
99
|
- LICENSE.txt
|
@@ -132,5 +137,5 @@ requirements: []
|
|
132
137
|
rubygems_version: 3.1.2
|
133
138
|
signing_key:
|
134
139
|
specification_version: 4
|
135
|
-
summary:
|
140
|
+
summary: A fast and lightweiggt xlsx parser that provides nothing a CSV parser wouldn't
|
136
141
|
test_files: []
|