incsv 0.2.1 → 0.2.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.yardopts +6 -0
- data/README.md +3 -3
- data/exe/incsv +4 -0
- data/incsv.gemspec +1 -0
- data/lib/incsv/column_type.rb +24 -0
- data/lib/incsv/database.rb +26 -0
- data/lib/incsv/schema.rb +8 -0
- data/lib/incsv/types/currency.rb +14 -0
- data/lib/incsv/types/date.rb +2 -0
- data/lib/incsv/types/string.rb +9 -0
- data/lib/incsv/version.rb +1 -1
- metadata +18 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: a48352c382c9de59e29eb0f294f75f68cc7f8de0
|
4
|
+
data.tar.gz: 749abf80150e9181ef61c0d85746ed685459a754
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: e9b77efaf5628776671a0c113f8082335702f33ececab4e62c9f21cd1013d65bbc12f2be5b7e8f769cad9257ec2d5387ea6655b561a1803cc142613bc44e762f
|
7
|
+
data.tar.gz: 909a26477f6065c4a7ff04bc54f38e74c9a6fff4d32e94d73bb15b38f841ace0f120ac483b7b3e89daa9008272a117d64a9c72c4d3452694f455e865c3830aea
|
data/.yardopts
ADDED
data/README.md
CHANGED
@@ -7,8 +7,8 @@ It works by loading the CSV into an [SQLite][] database and then
|
|
7
7
|
dropping you into an interactive Ruby shell. You can then use the
|
8
8
|
[Sequel][] database library to perform further exploratory analysis.
|
9
9
|
|
10
|
-
[
|
11
|
-
[
|
10
|
+
[SQLite]: https://www.sqlite.org/
|
11
|
+
[Sequel]: http://sequel.jeremyevans.net/
|
12
12
|
|
13
13
|
## Installation
|
14
14
|
|
@@ -38,7 +38,7 @@ A quick example:
|
|
38
38
|
{:name=>"enhanced targeting card"},
|
39
39
|
{:name=>"Giddyup Buttercup"}]
|
40
40
|
|
41
|
-
[
|
41
|
+
[REPL]: https://en.wikipedia.org/wiki/Read%E2%80%93eval%E2%80%93print_loop
|
42
42
|
|
43
43
|
### The less-quick version
|
44
44
|
|
data/exe/incsv
CHANGED
@@ -8,6 +8,9 @@ require "pry"
|
|
8
8
|
require "incsv"
|
9
9
|
|
10
10
|
module InCSV
|
11
|
+
# A cut-down class, the binding of which is used for the REPL console.
|
12
|
+
# Any methods and instance variables defined here, therefore, are
|
13
|
+
# accessible from the console.
|
11
14
|
class Console
|
12
15
|
def initialize(db)
|
13
16
|
@db = db
|
@@ -18,6 +21,7 @@ module InCSV
|
|
18
21
|
end
|
19
22
|
end
|
20
23
|
|
24
|
+
# The command-line interface to InCSV.
|
21
25
|
class CLI < Thor
|
22
26
|
desc "create CSV_FILE", "Creates a database file with the appropriate schema for the given CSV file, but doesn't import any data."
|
23
27
|
method_option :force, type: :boolean, default: false
|
data/incsv.gemspec
CHANGED
@@ -22,6 +22,7 @@ Gem::Specification.new do |spec|
|
|
22
22
|
spec.add_development_dependency "bundler", "~> 1.11"
|
23
23
|
spec.add_development_dependency "rake", "~> 10.0"
|
24
24
|
spec.add_development_dependency "rspec", "~> 3.0"
|
25
|
+
spec.add_development_dependency "yard", "~> 0.8"
|
25
26
|
|
26
27
|
spec.add_runtime_dependency "thor", "~> 0.19.1"
|
27
28
|
spec.add_runtime_dependency "pry", "~> 0.10"
|
data/lib/incsv/column_type.rb
CHANGED
@@ -1,9 +1,28 @@
|
|
1
1
|
module InCSV
|
2
|
+
# An abstract class, inherited by all types of column. Specifies the
|
3
|
+
# interface that all these classes must adhere to.
|
2
4
|
class ColumnType
|
5
|
+
# A symbol representation of what type of data this ColumnType
|
6
|
+
# represents. By default this is taken from the class name (so this
|
7
|
+
# class would be :columntype).
|
3
8
|
def self.name
|
4
9
|
self.to_s.sub(/.*::/, "").downcase.to_sym
|
5
10
|
end
|
6
11
|
|
12
|
+
# The type of the column from the perspective of the database. By
|
13
|
+
# default this is the same as the class name, so a column of type
|
14
|
+
# String would go into the database as a :string.
|
15
|
+
#
|
16
|
+
# Possible column types can be found here:
|
17
|
+
#
|
18
|
+
# http://sequel.jeremyevans.net/rdoc/files/doc/schema_modification_rdoc.html#label-Column+types
|
19
|
+
#
|
20
|
+
# This can also be a string, for database-specific features or in
|
21
|
+
# order to specify lengths easily. Examples might be:
|
22
|
+
#
|
23
|
+
# VARCHAR(255)
|
24
|
+
# DECIMAL(10, 2)
|
25
|
+
# BOOLEAN
|
7
26
|
def self.for_database
|
8
27
|
self.to_s.sub(/.*::/, "").downcase.to_sym
|
9
28
|
end
|
@@ -12,14 +31,19 @@ module InCSV
|
|
12
31
|
@value = value
|
13
32
|
end
|
14
33
|
|
34
|
+
# Returns true if the given value (supplied in the constructor)
|
35
|
+
# is of the type represented by this column; returns false
|
36
|
+
# otherwise.
|
15
37
|
def match?
|
16
38
|
false
|
17
39
|
end
|
18
40
|
|
41
|
+
# Returns a cleaned/preprocessed version of the given value.
|
19
42
|
def clean_value
|
20
43
|
self.class.clean_value(@value)
|
21
44
|
end
|
22
45
|
|
46
|
+
# Returns a cleaned/preprocessed version of an arbitrary value.
|
23
47
|
def self.clean_value(value)
|
24
48
|
value
|
25
49
|
end
|
data/lib/incsv/database.rb
CHANGED
@@ -3,6 +3,9 @@ require "sequel"
|
|
3
3
|
require "pathname"
|
4
4
|
|
5
5
|
module InCSV
|
6
|
+
# Represents a database file, handling the creation of the database
|
7
|
+
# and of the table within the database, as well as the importing of
|
8
|
+
# data from a CSV file into the database.
|
6
9
|
class Database
|
7
10
|
def initialize(csv)
|
8
11
|
@csv = csv
|
@@ -14,29 +17,47 @@ module InCSV
|
|
14
17
|
|
15
18
|
attr_reader :db
|
16
19
|
|
20
|
+
# Returns true if the primary database table within the database has
|
21
|
+
# been created.
|
17
22
|
def table_created?
|
18
23
|
@db.table_exists?(table_name)
|
19
24
|
end
|
20
25
|
|
26
|
+
# Returns true if there is data in the primary table. There are
|
27
|
+
# perhaps more accurate ways to calculate this, but only by
|
28
|
+
# comparing samples from the CSV to the table; this is faster and
|
29
|
+
# will in practice be accurate.
|
21
30
|
def imported?
|
22
31
|
table_created? && @db[table_name].count > 0
|
23
32
|
end
|
24
33
|
|
34
|
+
# Returns true if the database file exists; makes no effort to check
|
35
|
+
# whether it is in fact a valid SQLite database.
|
25
36
|
def exists?
|
26
37
|
File.exist?(db_path)
|
27
38
|
end
|
28
39
|
|
40
|
+
# Returns the path to the database file, generated based on the
|
41
|
+
# filename of the CSV passed to the class. For example, a CSV called
|
42
|
+
# `products.csv` will be stored in a database called `products.db`
|
43
|
+
# in the same directory.
|
29
44
|
def db_path
|
30
45
|
path = Pathname(csv)
|
31
46
|
(path.dirname + (path.basename(".csv").to_s + ".db")).to_s
|
32
47
|
end
|
33
48
|
|
49
|
+
# Returns the table name, by default generated based on the filename
|
50
|
+
# of the CSV. For example, a CSV called `products.csv` will produce
|
51
|
+
# a table called `products`.
|
34
52
|
def table_name
|
35
53
|
@table_name ||= begin
|
36
54
|
File.basename(csv, ".csv").downcase.gsub(/[^a-z_]/, "").to_sym
|
37
55
|
end
|
38
56
|
end
|
39
57
|
|
58
|
+
# Creates a table in the database, with one column in the database
|
59
|
+
# for each column in the CSV, the type of which is the best guess
|
60
|
+
# for the data found in that column in the CSV data.
|
40
61
|
def create_table
|
41
62
|
@db.create_table!(table_name) do
|
42
63
|
primary_key :_incsv_id
|
@@ -49,6 +70,11 @@ module InCSV
|
|
49
70
|
end
|
50
71
|
end
|
51
72
|
|
73
|
+
# Imports data from the CSV file into the database, applying any
|
74
|
+
# preprocessing specified by the column type (e.g. stripping
|
75
|
+
# currency prefixes).
|
76
|
+
#
|
77
|
+
# Data is imported in transactions, in chunks of 200 rows at a time.
|
52
78
|
def import
|
53
79
|
return if imported?
|
54
80
|
|
data/lib/incsv/schema.rb
CHANGED
@@ -1,11 +1,15 @@
|
|
1
1
|
require "csv"
|
2
2
|
|
3
3
|
module InCSV
|
4
|
+
# Given a CSV file, samples data from it in order to establish what
|
5
|
+
# data types its columns are.
|
4
6
|
class Schema
|
5
7
|
def initialize(csv)
|
6
8
|
@csv = csv
|
7
9
|
end
|
8
10
|
|
11
|
+
# Returns the column types found in the CSV. Memoises the result, so
|
12
|
+
# can be called repeatedly.
|
9
13
|
def columns
|
10
14
|
@columns ||= parsed_columns
|
11
15
|
end
|
@@ -14,6 +18,10 @@ module InCSV
|
|
14
18
|
|
15
19
|
attr_reader :csv
|
16
20
|
|
21
|
+
# Returns an array with one element for each column in the CSV. The
|
22
|
+
# value is a Column object, which has responsibility for determining
|
23
|
+
# the type of the data stored in the column; a sample of 50 rows
|
24
|
+
# from the column is provided to the Column class for this purpose.
|
17
25
|
def parsed_columns
|
18
26
|
samples(50).map do |name, values|
|
19
27
|
Column.new(name, values)
|
data/lib/incsv/types/currency.rb
CHANGED
@@ -1,16 +1,30 @@
|
|
1
1
|
module InCSV
|
2
2
|
module Types
|
3
|
+
# Represents a currency value, without its symbol/identifier, stored
|
4
|
+
# as a DECIMAL(10, 2) to avoid rounding errors.
|
5
|
+
#
|
6
|
+
# Not storing the identifier is an issue that should be resolved at
|
7
|
+
# some point, ideally; it's obviously an issue in files that have
|
8
|
+
# multiple currencies in the same column.
|
3
9
|
class Currency < ColumnType
|
10
|
+
# A regular expression which matches all supported currency types.
|
4
11
|
MATCH_EXPRESSION = /\A(\$|£)([0-9,\.]+)\z/
|
5
12
|
|
13
|
+
# What type of column to create in the database.
|
6
14
|
def self.for_database
|
7
15
|
"DECIMAL(10,2)"
|
8
16
|
end
|
9
17
|
|
18
|
+
# Returns true if the given value is a supported currency type, or
|
19
|
+
# false otherwise.
|
10
20
|
def match?
|
11
21
|
value.strip.match(MATCH_EXPRESSION)
|
12
22
|
end
|
13
23
|
|
24
|
+
# Strip the currency symbol, and remove any comma separators. This
|
25
|
+
# creates an issue with locales other than English, in which
|
26
|
+
# commas are used for decimal points, but this will work for
|
27
|
+
# English.
|
14
28
|
def self.clean_value(value)
|
15
29
|
return unless value
|
16
30
|
|
data/lib/incsv/types/date.rb
CHANGED
data/lib/incsv/types/string.rb
CHANGED
@@ -1,6 +1,15 @@
|
|
1
1
|
module InCSV
|
2
2
|
module Types
|
3
|
+
# Represents a String, stored in the database as a VARCHAR(255).
|
4
|
+
# This is the fallback datatype, used for anything that doesn't
|
5
|
+
# match any of the other more specific types. Its matching logic is
|
6
|
+
# therefore simple: it matches anything. For this reason it must be
|
7
|
+
# matched last; this is achieved via require order.
|
3
8
|
class String < ColumnType
|
9
|
+
def self.for_database
|
10
|
+
"TEXT"
|
11
|
+
end
|
12
|
+
|
4
13
|
def match?
|
5
14
|
true
|
6
15
|
end
|
data/lib/incsv/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: incsv
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.2.
|
4
|
+
version: 0.2.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Rob Miller
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2016-
|
11
|
+
date: 2016-03-01 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
@@ -52,6 +52,20 @@ dependencies:
|
|
52
52
|
- - "~>"
|
53
53
|
- !ruby/object:Gem::Version
|
54
54
|
version: '3.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: yard
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0.8'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0.8'
|
55
69
|
- !ruby/object:Gem::Dependency
|
56
70
|
name: thor
|
57
71
|
requirement: !ruby/object:Gem::Requirement
|
@@ -120,6 +134,7 @@ files:
|
|
120
134
|
- ".gitignore"
|
121
135
|
- ".rspec"
|
122
136
|
- ".travis.yml"
|
137
|
+
- ".yardopts"
|
123
138
|
- CODE_OF_CONDUCT.md
|
124
139
|
- Gemfile
|
125
140
|
- LICENSE.txt
|
@@ -164,3 +179,4 @@ signing_key:
|
|
164
179
|
specification_version: 4
|
165
180
|
summary: A tool for interrogating CSV data using SQLite and Sequel.
|
166
181
|
test_files: []
|
182
|
+
has_rdoc:
|