idata 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +17 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +29 -0
- data/Rakefile +1 -0
- data/bin/ieval +222 -0
- data/bin/iexport +163 -0
- data/bin/iload +276 -0
- data/bin/ipatch +107 -0
- data/bin/isanitize +4 -0
- data/bin/ivalidate +258 -0
- data/idata.gemspec +27 -0
- data/lib/idata/version.rb +3 -0
- data/lib/idata.rb +5 -0
- metadata +120 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 27e594b49b95b536a5d01ed6f90155751104ec1a
|
4
|
+
data.tar.gz: a4e52832bccdc2ab55ae33e7e6f659857b800991
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: f55f15be3fbc959bcfacdb68f2b45e5b97fa560ee953890a66eb5a4715366019240e61c1b9ef36df9ed77d0ba396d6e38b32177a555d75aeb4f0deb04ae99757
|
7
|
+
data.tar.gz: 0e8061590a8d5da84ee9f74d137c2f6d022a58009d9d56ca965241c10e064a9cde59fb1f0d784cab643d88d19c1cdbe3a2f688ce2bbfcc42f4cd50b14e2bcfda
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2014 TODO: Write your name
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
# Idata
|
2
|
+
|
3
|
+
TODO: Write a gem description
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'idata'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install idata
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
TODO: Write usage instructions here
|
22
|
+
|
23
|
+
## Contributing
|
24
|
+
|
25
|
+
1. Fork it
|
26
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
27
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
28
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
29
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
data/bin/ieval
ADDED
@@ -0,0 +1,222 @@
|
|
1
|
+
# DATA LOADER
|
2
|
+
#
|
3
|
+
# @author Nghi Pham
|
4
|
+
# @date April 2014
|
5
|
+
#
|
6
|
+
# The script loads data from a fixed-width text file or a CSV file and fills in
|
7
|
+
# a corresponding table in the specified database
|
8
|
+
# Issue ruby load.rb --help for guideline/examples
|
9
|
+
#
|
10
|
+
# @todo Make the script OOP
|
11
|
+
# @todo Constantize default values
|
12
|
+
require 'optparse'
|
13
|
+
require 'csv'
|
14
|
+
require 'active_record'
|
15
|
+
require 'rubygems'
|
16
|
+
require 'digest/sha1'
|
17
|
+
require 'fileutils'
|
18
|
+
|
19
|
+
# Default configuration settings
|
20
|
+
POSTGRESQL_PORT = 5432
|
21
|
+
|
22
|
+
# Parse script inputs
|
23
|
+
$options = {}
|
24
|
+
parser = OptionParser.new("", 24) do |opts|
|
25
|
+
opts.banner = "\nProgram: Data Loader\nAuthor: MCKI\n\n"
|
26
|
+
|
27
|
+
opts.on("-e", "--eval SCRIPT", "Ruby SCRIPT to execute") do |v|
|
28
|
+
$options[:eval] = v
|
29
|
+
end
|
30
|
+
|
31
|
+
opts.on("-t", "--table TABLE", "Table name to be created") do |v|
|
32
|
+
$options[:table] = v
|
33
|
+
end
|
34
|
+
|
35
|
+
opts.on("-h", "--host HOST", "PostgreSQL host") do |v|
|
36
|
+
$options[:host] = v
|
37
|
+
end
|
38
|
+
|
39
|
+
opts.on("-d", "--database DATABASE", "PostgreSQL database") do |v|
|
40
|
+
$options[:database] = v
|
41
|
+
end
|
42
|
+
|
43
|
+
opts.on("-u", "--username USER", "PostgreSQL username") do |v|
|
44
|
+
$options[:username] = v
|
45
|
+
end
|
46
|
+
|
47
|
+
opts.on("-p", "--password PASSWORD", "PostgreSQL password") do |v|
|
48
|
+
$options[:password] = v
|
49
|
+
end
|
50
|
+
|
51
|
+
opts.on("-l", "--listen PORT", "PostgreSQL listen port (default to 5432)") do |v|
|
52
|
+
$options[:listen] = v
|
53
|
+
end
|
54
|
+
|
55
|
+
opts.on_tail('--help', 'Displays this help') do
|
56
|
+
puts opts, "", help
|
57
|
+
exit
|
58
|
+
end
|
59
|
+
end
|
60
|
+
|
61
|
+
# Help message
|
62
|
+
def help
|
63
|
+
return <<-eos
|
64
|
+
|
65
|
+
EXAMPLES
|
66
|
+
-------------------------------------------------------
|
67
|
+
Run a custom Ruby command on the every record represented by the `item` variable
|
68
|
+
|
69
|
+
ruby eval.rb --host=localhost --username=postgres --password=postgres \\
|
70
|
+
--table=vendors --database=db \\
|
71
|
+
--eval="item.last_name = item.full_name.split(/\\s+/).last"
|
72
|
+
|
73
|
+
eos
|
74
|
+
end
|
75
|
+
|
76
|
+
begin
|
77
|
+
parser.parse!
|
78
|
+
rescue SystemExit => ex
|
79
|
+
exit
|
80
|
+
end
|
81
|
+
|
82
|
+
# Certain arguments are required
|
83
|
+
if $options[:eval].nil?
|
84
|
+
puts "\nPlease specify Ruby script to execute: -e\n\n"
|
85
|
+
exit
|
86
|
+
end
|
87
|
+
|
88
|
+
if $options[:table].nil?
|
89
|
+
puts "\nPlease specify SQL table name: -t\n\n"
|
90
|
+
exit
|
91
|
+
end
|
92
|
+
|
93
|
+
if $options[:host].nil?
|
94
|
+
puts "\nPlease specify host name: -h\n\n"
|
95
|
+
exit
|
96
|
+
end
|
97
|
+
|
98
|
+
if $options[:database].nil?
|
99
|
+
puts "\nPlease specify PostgreSQL database name: -d\n\n"
|
100
|
+
exit
|
101
|
+
end
|
102
|
+
|
103
|
+
if $options[:username].nil?
|
104
|
+
puts "\nPlease specify PostgreSQL username: -d\n\n"
|
105
|
+
exit
|
106
|
+
end
|
107
|
+
|
108
|
+
# Default in case arguments are not provided
|
109
|
+
$options[:listen] ||= POSTGRESQL_PORT
|
110
|
+
|
111
|
+
# Connect to PostgreSQL
|
112
|
+
# $options = {host: 'localhost', database: 'db', username: 'postgres', password: 'postgres', table: 'products', listen: 5432}
|
113
|
+
ActiveRecord::Base.establish_connection(
|
114
|
+
'adapter' => 'postgresql',
|
115
|
+
'host' => $options[:host],
|
116
|
+
'database' => $options[:database],
|
117
|
+
'username' => $options[:username],
|
118
|
+
'password' => $options[:password],
|
119
|
+
'port' => $options[:listen],
|
120
|
+
'timeout' => 15000
|
121
|
+
)
|
122
|
+
|
123
|
+
class Product < ActiveRecord::Base
|
124
|
+
self.primary_key = :id
|
125
|
+
self.table_name = $options[:table]
|
126
|
+
end
|
127
|
+
|
128
|
+
# Temp file & temp table name
|
129
|
+
$tmpfile = "/tmp/#{Digest::SHA1.hexdigest(rand(100000).to_s)}.csv"
|
130
|
+
$tmpname = "_tmp_#{Digest::SHA1.hexdigest(rand(100000).to_s)}"
|
131
|
+
|
132
|
+
# Check if PostgreSQL host is local
|
133
|
+
def local?
|
134
|
+
return ['localhost', '127.0.0.1'].include?($options[:host])
|
135
|
+
end
|
136
|
+
|
137
|
+
# Execute query
|
138
|
+
def query(*query_str)
|
139
|
+
ActiveRecord::Base.connection.execute(query_str.join("; "))
|
140
|
+
end
|
141
|
+
|
142
|
+
# Create table from CSV
|
143
|
+
def create_table_from_csv(name, csv_path)
|
144
|
+
# Get headers
|
145
|
+
csv = CSV.open(csv_path, :headers => true)
|
146
|
+
first = csv.first
|
147
|
+
unless first
|
148
|
+
raise "File Empty!!!"
|
149
|
+
end
|
150
|
+
|
151
|
+
# sanitize
|
152
|
+
headers = first.headers
|
153
|
+
headers.each_with_index {|e, index|
|
154
|
+
if e.nil? or e.empty?
|
155
|
+
headers[index] = "column_#{index + 1}"
|
156
|
+
end
|
157
|
+
}
|
158
|
+
headers.map!{|e| e.downcase.underscore }
|
159
|
+
|
160
|
+
# check if every field name is unique
|
161
|
+
if headers.count != headers.uniq.count
|
162
|
+
raise "Field name must be UNIQUE: \nPlease check your input headers: [#{headers.join(', ')}]"
|
163
|
+
end
|
164
|
+
|
165
|
+
# Create table
|
166
|
+
create_table_sql = headers.map{|e| e == 'id' ? "\"#{e}\" integer" : "\"#{e}\" text"}.join(",")
|
167
|
+
create_table_sql = "drop table if exists #{name}; create table #{name}( #{create_table_sql} );"
|
168
|
+
query(create_table_sql)
|
169
|
+
|
170
|
+
# Dump data
|
171
|
+
insert_data_sql = headers.map{|e| "\"#{e}\""}.join(",")
|
172
|
+
insert_data_sql = "COPY #{name}( #{insert_data_sql} ) FROM '#{csv_path}' DELIMITER ',' CSV HEADER;"
|
173
|
+
|
174
|
+
# Change output file permission so that postgres user can read it
|
175
|
+
begin
|
176
|
+
FileUtils.chmod 0755, csv_path
|
177
|
+
rescue Exception => ex
|
178
|
+
puts "Error while changing file permission"
|
179
|
+
end
|
180
|
+
|
181
|
+
if local?
|
182
|
+
query(insert_data_sql)
|
183
|
+
else
|
184
|
+
puts "\nWARNING: pushing data to remote server [#{$options[:host]}].\nBe sure you have the correct version of `psql` command installed\n\n"
|
185
|
+
insert_data_sql = "PGPASSWORD=#{$options[:username]} psql -U #{$options[:username]} -h #{$options[:host]} -p #{$options[:listen]} #{$options[:database]} -c \"\\#{insert_data_sql}\""
|
186
|
+
|
187
|
+
`#{insert_data_sql}`
|
188
|
+
`PGPASSWORD=""`
|
189
|
+
end
|
190
|
+
end
|
191
|
+
|
192
|
+
if !local? and $options[:password].nil?
|
193
|
+
puts "\n\nERROR: You are connecting to a remote server\nPlease make sure you specify SQL password: --password \n\n"
|
194
|
+
exit
|
195
|
+
end
|
196
|
+
|
197
|
+
fields_changed = []
|
198
|
+
|
199
|
+
CSV.open($tmpfile, "wb", :col_sep => ',') do |csv|
|
200
|
+
csv << Product.first.attributes.keys
|
201
|
+
|
202
|
+
Product.all.each do |item|
|
203
|
+
# Execute the script provided on every record
|
204
|
+
eval($options[:eval])
|
205
|
+
fields_changed += item.changes.keys
|
206
|
+
fields_changed.uniq!
|
207
|
+
csv << item.attributes.values
|
208
|
+
end
|
209
|
+
end
|
210
|
+
|
211
|
+
unless fields_changed.empty?
|
212
|
+
create_table_from_csv($tmpname, $tmpfile)
|
213
|
+
update_sql = fields_changed.map{|f| "\"#{f}\" = tmp.\"#{f}\""}.join(", ")
|
214
|
+
update_sql = "UPDATE #{$options[:table]} origin SET #{update_sql} FROM #{$tmpname} tmp WHERE origin.id = tmp.id"
|
215
|
+
query(update_sql)
|
216
|
+
|
217
|
+
cleanup_sql = "DROP TABLE #{$tmpname};"
|
218
|
+
query(cleanup_sql)
|
219
|
+
|
220
|
+
puts "\nDone\n\n"
|
221
|
+
end
|
222
|
+
|
data/bin/iexport
ADDED
@@ -0,0 +1,163 @@
|
|
1
|
+
# DATA LOADER
|
2
|
+
#
|
3
|
+
# @author Nghi Pham
|
4
|
+
# @date April 2014
|
5
|
+
#
|
6
|
+
# The script loads data from a fixed-width text file or a CSV file and fills in
|
7
|
+
# a corresponding table in the specified database
|
8
|
+
# Issue ruby load.rb --help for guideline/examples
|
9
|
+
#
|
10
|
+
require 'optparse'
|
11
|
+
require 'csv'
|
12
|
+
require 'active_record'
|
13
|
+
require 'rubygems'
|
14
|
+
require 'digest/sha1'
|
15
|
+
require 'fileutils'
|
16
|
+
|
17
|
+
SUPPORTED_INPUT_FORMATS = ['CSV']
|
18
|
+
POSTGRESQL_PORT = 5432
|
19
|
+
CSV_DEFAULT_DELIMITER = ','
|
20
|
+
|
21
|
+
$options = {}
|
22
|
+
parser = OptionParser.new("", 24) do |opts|
|
23
|
+
opts.banner = "\nProgram: Data Exporter\nAuthor: MCKI\n\n"
|
24
|
+
|
25
|
+
opts.on("-f", "--format FORMAT", "Output file format") do |v|
|
26
|
+
$options[:format] = v
|
27
|
+
end
|
28
|
+
|
29
|
+
opts.on("--delim DELIMITER", "CSV delimiter") do |v|
|
30
|
+
$options[:delim] = v
|
31
|
+
end
|
32
|
+
|
33
|
+
opts.on("-t", "--table TABLE", "Table name to be created") do |v|
|
34
|
+
$options[:table] = v
|
35
|
+
end
|
36
|
+
|
37
|
+
opts.on("-s", "--select FIELDS", "Fields to export") do |v|
|
38
|
+
$options[:select] = v
|
39
|
+
end
|
40
|
+
|
41
|
+
opts.on("-w", "--where CONDITION", "CONDITION") do |v|
|
42
|
+
$options[:where] = v
|
43
|
+
end
|
44
|
+
|
45
|
+
opts.on("-o", "--output FILE", "Output file") do |v|
|
46
|
+
$options[:output] = v
|
47
|
+
end
|
48
|
+
|
49
|
+
opts.on("-h", "--host HOST", "PostgreSQL host") do |v|
|
50
|
+
$options[:host] = v
|
51
|
+
end
|
52
|
+
|
53
|
+
opts.on("-d", "--database DATABASE", "PostgreSQL database") do |v|
|
54
|
+
$options[:database] = v
|
55
|
+
end
|
56
|
+
|
57
|
+
opts.on("-u", "--username USER", "PostgreSQL username") do |v|
|
58
|
+
$options[:username] = v
|
59
|
+
end
|
60
|
+
|
61
|
+
opts.on("-p", "--password PASSWORD", "PostgreSQL password") do |v|
|
62
|
+
$options[:password] = v
|
63
|
+
end
|
64
|
+
|
65
|
+
opts.on("-l", "--listen PORT", "PostgreSQL listen port (default to 5432)") do |v|
|
66
|
+
$options[:listen] = v
|
67
|
+
end
|
68
|
+
|
69
|
+
opts.on_tail('--help', 'Displays this help') do
|
70
|
+
puts opts, "", help
|
71
|
+
exit
|
72
|
+
end
|
73
|
+
end
|
74
|
+
|
75
|
+
def help
|
76
|
+
return <<-eos
|
77
|
+
|
78
|
+
EXAMPLES
|
79
|
+
-------------------------------------------------------
|
80
|
+
|
81
|
+
ruby export.rb --host=localhost --username=postgres --database=db --table=items \\
|
82
|
+
--output=/tmp/data.csv --format=csv --delim="\\t" \\
|
83
|
+
--select="id, name AS vendor_name, age" --where="active = 1"
|
84
|
+
|
85
|
+
eos
|
86
|
+
end
|
87
|
+
|
88
|
+
begin
|
89
|
+
parser.parse!
|
90
|
+
rescue SystemExit => ex
|
91
|
+
exit
|
92
|
+
end
|
93
|
+
|
94
|
+
if $options[:format].nil?
|
95
|
+
puts "\nPlease specify input file format: -f\n\n"
|
96
|
+
exit
|
97
|
+
end
|
98
|
+
|
99
|
+
# downcase for consistency
|
100
|
+
$options[:format].upcase!
|
101
|
+
|
102
|
+
if !SUPPORTED_INPUT_FORMATS.include?($options[:format])
|
103
|
+
puts "\nInvalid input file format, supported formats are: #{SUPPORTED_INPUT_FORMATS.join(', ')}\n\n"
|
104
|
+
exit
|
105
|
+
end
|
106
|
+
|
107
|
+
if $options[:table].nil?
|
108
|
+
puts "\nPlease specify SQL table name: -t\n\n"
|
109
|
+
exit
|
110
|
+
end
|
111
|
+
|
112
|
+
if $options[:output].nil?
|
113
|
+
puts "\nPlease specify output file: -o\n\n"
|
114
|
+
exit
|
115
|
+
end
|
116
|
+
|
117
|
+
if $options[:host].nil?
|
118
|
+
puts "\nPlease specify host name: -h\n\n"
|
119
|
+
exit
|
120
|
+
end
|
121
|
+
|
122
|
+
if $options[:database].nil?
|
123
|
+
puts "\nPlease specify PostgreSQL database name: -d\n\n"
|
124
|
+
exit
|
125
|
+
end
|
126
|
+
|
127
|
+
if $options[:username].nil?
|
128
|
+
puts "\nPlease specify PostgreSQL username: -d\n\n"
|
129
|
+
exit
|
130
|
+
end
|
131
|
+
|
132
|
+
# Default value
|
133
|
+
$options[:listen] ||= POSTGRESQL_PORT
|
134
|
+
$options[:delim] ||= CSV_DEFAULT_DELIMITER
|
135
|
+
$options[:delim] = "\t" if $options[:delim] == '\t'
|
136
|
+
$options[:select] ||= '*'
|
137
|
+
$options[:where] ||= 'true'
|
138
|
+
|
139
|
+
#$options = {host: 'localhost', database: 'db', username: 'postgres', password: 'postgres', table: 'products', listen: 5432}
|
140
|
+
ActiveRecord::Base.establish_connection(
|
141
|
+
'adapter' => 'postgresql',
|
142
|
+
'host' => $options[:host],
|
143
|
+
'database' => $options[:database],
|
144
|
+
'username' => $options[:username],
|
145
|
+
'password' => $options[:password],
|
146
|
+
'port' => $options[:listen],
|
147
|
+
'timeout' => 15000
|
148
|
+
)
|
149
|
+
|
150
|
+
class Product < ActiveRecord::Base
|
151
|
+
self.table_name = $options[:table]
|
152
|
+
end
|
153
|
+
|
154
|
+
CSV.open($options[:output], "wb", :col_sep => $options[:delim]) do |csv|
|
155
|
+
scope = Product.select($options[:select]).where($options[:where])
|
156
|
+
csv << scope.first.attributes.keys
|
157
|
+
|
158
|
+
scope.each do |item|
|
159
|
+
csv << item.attributes.values
|
160
|
+
end
|
161
|
+
end
|
162
|
+
|
163
|
+
puts "\nFile #{$options[:output]} created!\n\n"
|
data/bin/iload
ADDED
@@ -0,0 +1,276 @@
|
|
1
|
+
# DATA LOADER
|
2
|
+
#
|
3
|
+
# @author Nghi Pham
|
4
|
+
# @date April 2014
|
5
|
+
#
|
6
|
+
# The script loads data from a fixed-width text file or a CSV file and fills in
|
7
|
+
# a corresponding table in the specified database
|
8
|
+
# Issue ruby load.rb --help for guideline/examples
|
9
|
+
#
|
10
|
+
require 'optparse'
|
11
|
+
require 'csv'
|
12
|
+
require 'active_record'
|
13
|
+
require 'rubygems'
|
14
|
+
require 'digest/sha1'
|
15
|
+
require 'fileutils'
|
16
|
+
|
17
|
+
SUPPORTED_INPUT_FORMATS = ['CSV', 'FX']
|
18
|
+
POSTGRESQL_PORT = 5432
|
19
|
+
CSV_DEFAULT_DELIMITER = ','
|
20
|
+
|
21
|
+
$options = {}
|
22
|
+
parser = OptionParser.new("", 24) do |opts|
|
23
|
+
opts.banner = "\nProgram: Data Loader\nAuthor: MCKI\n\n"
|
24
|
+
|
25
|
+
opts.on("-i", "--input INPUT", "INPUT text file (fixed-width)") do |v|
|
26
|
+
$options[:input] = v
|
27
|
+
end
|
28
|
+
|
29
|
+
opts.on("-f", "--format FORMAT", "Input file format, available values include (CSV|FX) ") do |v|
|
30
|
+
$options[:format] = v
|
31
|
+
end
|
32
|
+
|
33
|
+
opts.on("--delim DELIMITER", "Field DELIMITER (for CSV format only - default to COMMA ',')") do |v|
|
34
|
+
$options[:delim] = v
|
35
|
+
end
|
36
|
+
|
37
|
+
# opts.on("-o", "--output CSV", "Temporary CSV output file") do |v|
|
38
|
+
# $options[:output] = v
|
39
|
+
# end
|
40
|
+
|
41
|
+
opts.on("-t", "--table TABLE", "Table name to be created") do |v|
|
42
|
+
$options[:table] = v
|
43
|
+
end
|
44
|
+
|
45
|
+
opts.on("-h", "--host HOST", "PostgreSQL host") do |v|
|
46
|
+
$options[:host] = v
|
47
|
+
end
|
48
|
+
|
49
|
+
opts.on("-d", "--database DATABASE", "PostgreSQL database") do |v|
|
50
|
+
$options[:database] = v
|
51
|
+
end
|
52
|
+
|
53
|
+
opts.on("-u", "--username USER", "PostgreSQL username") do |v|
|
54
|
+
$options[:username] = v
|
55
|
+
end
|
56
|
+
|
57
|
+
opts.on("-p", "--password PASSWORD", "PostgreSQL password") do |v|
|
58
|
+
$options[:password] = v
|
59
|
+
end
|
60
|
+
|
61
|
+
opts.on("-l", "--listen PORT", "PostgreSQL listen port (default to 5432)") do |v|
|
62
|
+
$options[:listen] = v
|
63
|
+
end
|
64
|
+
|
65
|
+
opts.on_tail('--help', 'Displays this help') do
|
66
|
+
puts opts, "", help
|
67
|
+
exit
|
68
|
+
end
|
69
|
+
end
|
70
|
+
|
71
|
+
def help
|
72
|
+
return <<-eos
|
73
|
+
|
74
|
+
EXAMPLES
|
75
|
+
-------------------------------------------------------
|
76
|
+
Load data from text file and store to a table name "vendors"
|
77
|
+
|
78
|
+
ruby load.rb --host=localhost --username=postgres --password=postgres \\
|
79
|
+
--input=/home/administrator/VendorMaster.txt --format=fx \\
|
80
|
+
--table=vendors --database=db
|
81
|
+
|
82
|
+
|
83
|
+
The same usage in short form:
|
84
|
+
|
85
|
+
ruby load.rb -h localhost -u postgres -p postgres \\
|
86
|
+
-i /home/administrator/VendorMaster.txt -f fx \\
|
87
|
+
-t vendors -d db
|
88
|
+
|
89
|
+
eos
|
90
|
+
end
|
91
|
+
|
92
|
+
begin
|
93
|
+
parser.parse!
|
94
|
+
rescue SystemExit => ex
|
95
|
+
exit
|
96
|
+
end
|
97
|
+
|
98
|
+
if $options[:input].nil?
|
99
|
+
puts "\nPlease specify input file: -i\n\n"
|
100
|
+
exit
|
101
|
+
end
|
102
|
+
|
103
|
+
if $options[:format].nil?
|
104
|
+
puts "\nPlease specify input file format: -f\n\n"
|
105
|
+
exit
|
106
|
+
end
|
107
|
+
|
108
|
+
# downcase for consistency
|
109
|
+
$options[:format].upcase!
|
110
|
+
|
111
|
+
if !SUPPORTED_INPUT_FORMATS.include?($options[:format])
|
112
|
+
puts "\nInvalid input file format, supported formats are: #{SUPPORTED_INPUT_FORMATS.join(', ')}\n\n"
|
113
|
+
exit
|
114
|
+
end
|
115
|
+
|
116
|
+
if $options[:table].nil?
|
117
|
+
puts "\nPlease specify table name: -t\n\n"
|
118
|
+
exit
|
119
|
+
end
|
120
|
+
|
121
|
+
unless File.exists?($options[:input])
|
122
|
+
puts "\nFile does not exist"
|
123
|
+
exit
|
124
|
+
end
|
125
|
+
|
126
|
+
if $options[:host].nil?
|
127
|
+
puts "\nPlease specify host name: -h\n\n"
|
128
|
+
exit
|
129
|
+
end
|
130
|
+
|
131
|
+
if $options[:database].nil?
|
132
|
+
puts "\nPlease specify PostgreSQL database name: -d\n\n"
|
133
|
+
exit
|
134
|
+
end
|
135
|
+
|
136
|
+
if $options[:username].nil?
|
137
|
+
puts "\nPlease specify PostgreSQL username: -d\n\n"
|
138
|
+
exit
|
139
|
+
end
|
140
|
+
|
141
|
+
# Default value
|
142
|
+
$options[:listen] ||= POSTGRESQL_PORT
|
143
|
+
$options[:delim] ||= CSV_DEFAULT_DELIMITER
|
144
|
+
$options[:delim] = "\t" if $options[:delim] == '\t'
|
145
|
+
$tmpfile = "/tmp/#{Digest::SHA1.hexdigest(rand(100000).to_s)}.csv"
|
146
|
+
|
147
|
+
# Database dump
|
148
|
+
ActiveRecord::Base.establish_connection(
|
149
|
+
'adapter' => 'postgresql',
|
150
|
+
'host' => $options[:host],
|
151
|
+
'database' => $options[:database],
|
152
|
+
'username' => $options[:username],
|
153
|
+
'password' => $options[:password],
|
154
|
+
'port' => $options[:listen],
|
155
|
+
'timeout' => 15000
|
156
|
+
)
|
157
|
+
|
158
|
+
class String
|
159
|
+
def underscore
|
160
|
+
return self if self.nil?
|
161
|
+
return self.strip.gsub(/[^a-z0-9]+/, "_")
|
162
|
+
end
|
163
|
+
end
|
164
|
+
|
165
|
+
class MyParser
|
166
|
+
def initialize
|
167
|
+
# remote server always requires password
|
168
|
+
if !local? and $options[:password].nil?
|
169
|
+
raise "You are connecting to a remote server\nPlease make sure you specify SQL password: --password "
|
170
|
+
end
|
171
|
+
end
|
172
|
+
|
173
|
+
def run
|
174
|
+
load_fx if $options[:format] == 'FX'
|
175
|
+
load_csv if $options[:format] == 'CSV'
|
176
|
+
end
|
177
|
+
|
178
|
+
def load_csv
|
179
|
+
# Copy file to /tmp/ folder to prevent Permission Error
|
180
|
+
FileUtils.cp $options[:input], $tmpfile
|
181
|
+
create_table_from_csv($tmpfile)
|
182
|
+
end
|
183
|
+
|
184
|
+
def load_fx
|
185
|
+
# Load data
|
186
|
+
data = IO.read($options[:input]).split("\n")
|
187
|
+
header = data.shift
|
188
|
+
headers = header.scan(/[^\s]+\s+/)
|
189
|
+
|
190
|
+
# Parse
|
191
|
+
ranges = headers.map{|s| "a#{s.size}"}.join("")
|
192
|
+
headers.map!{|s| s.downcase.strip }
|
193
|
+
|
194
|
+
# Write
|
195
|
+
CSV.open($tmpfile, "wb", :col_sep => CSV_DEFAULT_DELIMITER, quote_char: "\b") do |csv|
|
196
|
+
csv << headers
|
197
|
+
|
198
|
+
data.each_with_index{|s, index|
|
199
|
+
record = s.unpack(ranges).map{|e| e.strip}
|
200
|
+
csv << record
|
201
|
+
}
|
202
|
+
end
|
203
|
+
|
204
|
+
create_table_from_csv($tmpfile)
|
205
|
+
end
|
206
|
+
|
207
|
+
def create_table_from_csv(csv_path)
|
208
|
+
# Get headers
|
209
|
+
csv = CSV.open(csv_path, :headers => true, :col_sep => $options[:delim], quote_char: "\b")
|
210
|
+
|
211
|
+
first = csv.first
|
212
|
+
unless first
|
213
|
+
raise "File Empty!!!"
|
214
|
+
end
|
215
|
+
|
216
|
+
# sanitize
|
217
|
+
headers = first.headers
|
218
|
+
headers.each_with_index {|e, index|
|
219
|
+
if e.nil? or e.empty?
|
220
|
+
headers[index] = "column_#{index + 1}"
|
221
|
+
end
|
222
|
+
}
|
223
|
+
headers.map!{|e| e.downcase.underscore }
|
224
|
+
|
225
|
+
# check if every field name is unique
|
226
|
+
if headers.count != headers.uniq.count
|
227
|
+
raise "Field name must be UNIQUE: \nPlease check your input headers: [#{headers.sort.join(', ')}]"
|
228
|
+
end
|
229
|
+
|
230
|
+
# Create table
|
231
|
+
create_table_sql = headers.map{|e| "\"#{e}\" text"}.join(",")
|
232
|
+
create_table_sql = "drop table if exists #{$options[:table]}; create table #{$options[:table]}( id serial not null, #{create_table_sql} );"
|
233
|
+
query(create_table_sql)
|
234
|
+
|
235
|
+
# Dump data
|
236
|
+
pg_tab = "E'\t'" if $options[:delim] == "\t"
|
237
|
+
insert_data_sql = headers.map{|e| "\"#{e}\""}.join(",")
|
238
|
+
insert_data_sql = "COPY #{$options[:table]}( #{insert_data_sql} ) FROM '#{csv_path}' DELIMITER #{pg_tab} CSV HEADER QUOTE E'\b';"
|
239
|
+
|
240
|
+
# Change output file permission so that postgres user can read it
|
241
|
+
begin
|
242
|
+
FileUtils.chmod 0755, csv_path
|
243
|
+
rescue Exception => ex
|
244
|
+
puts "Error while changing file permission"
|
245
|
+
end
|
246
|
+
|
247
|
+
if local?
|
248
|
+
query(insert_data_sql)
|
249
|
+
else
|
250
|
+
puts "\nWARNING: pushing data to remote server [#{$options[:host]}].\nBe sure you have the correct version of `psql` command installed\n\n"
|
251
|
+
insert_data_sql = "PGPASSWORD=#{$options[:username]} psql -U #{$options[:username]} -h #{$options[:host]} -p #{$options[:listen]} #{$options[:database]} -c \"\\#{insert_data_sql}\""
|
252
|
+
|
253
|
+
`#{insert_data_sql}`
|
254
|
+
`PGPASSWORD=""`
|
255
|
+
end
|
256
|
+
|
257
|
+
puts "\nTable `#{$options[:table]}` loaded \n\n"
|
258
|
+
end
|
259
|
+
|
260
|
+
private
|
261
|
+
def query(*query_str)
|
262
|
+
ActiveRecord::Base.connection.execute(query_str.join("; "))
|
263
|
+
end
|
264
|
+
|
265
|
+
def local?
|
266
|
+
return ['localhost', '127.0.0.1'].include?($options[:host])
|
267
|
+
end
|
268
|
+
end
|
269
|
+
|
270
|
+
begin
|
271
|
+
e = MyParser.new
|
272
|
+
e.run
|
273
|
+
rescue Exception => ex
|
274
|
+
puts "\n\n*********** ERROR ***********\n#{ex.message}\n\n"
|
275
|
+
exit
|
276
|
+
end
|
data/bin/ipatch
ADDED
@@ -0,0 +1,107 @@
|
|
1
|
+
# DATA PATCHER
|
2
|
+
#
|
3
|
+
# @author Nghi Pham
|
4
|
+
# @date April 2014
|
5
|
+
#
|
6
|
+
# Any custom patches to the database goes here
|
7
|
+
#
|
8
|
+
require 'optparse'
|
9
|
+
require 'csv'
|
10
|
+
require 'active_record'
|
11
|
+
require 'rubygems'
|
12
|
+
|
13
|
+
# Default values
|
14
|
+
POSTGRESQL_PORT = 5432
|
15
|
+
|
16
|
+
# User input
|
17
|
+
$options = {}
|
18
|
+
parser = OptionParser.new("", 24) do |opts|
|
19
|
+
opts.banner = "\nProgram: Data Patcher\nAuthor: MCKI\n\n"
|
20
|
+
|
21
|
+
opts.on("-q", "--query QUERY", "Custom query") do |v|
|
22
|
+
$options[:query] = v
|
23
|
+
end
|
24
|
+
|
25
|
+
opts.on("-h", "--host HOST", "PostgreSQL host") do |v|
|
26
|
+
$options[:host] = v
|
27
|
+
end
|
28
|
+
|
29
|
+
opts.on("-d", "--database DATABASE", "PostgreSQL database") do |v|
|
30
|
+
$options[:database] = v
|
31
|
+
end
|
32
|
+
|
33
|
+
opts.on("-u", "--username USER", "PostgreSQL username") do |v|
|
34
|
+
$options[:username] = v
|
35
|
+
end
|
36
|
+
|
37
|
+
opts.on("-p", "--password PASSWORD", "PostgreSQL password") do |v|
|
38
|
+
$options[:password] = v
|
39
|
+
end
|
40
|
+
|
41
|
+
opts.on("-l", "--listen PORT", "PostgreSQL listen port (default to 5432)") do |v|
|
42
|
+
$options[:listen] = v
|
43
|
+
end
|
44
|
+
|
45
|
+
opts.on_tail('--help', 'Displays this help') do
|
46
|
+
puts opts, "", help
|
47
|
+
exit
|
48
|
+
end
|
49
|
+
end
|
50
|
+
|
51
|
+
def help
|
52
|
+
return <<-eos
|
53
|
+
|
54
|
+
EXAMPLES
|
55
|
+
-------------------------------------------------------
|
56
|
+
Send custom SQL to a data table
|
57
|
+
|
58
|
+
ruby patch.rb --host=localhost --username=postgres --password=postgres --database=db \\
|
59
|
+
--query="ALTER TABLE vendors ADD COLUMN tmp text; UPDATE vendors SET tmp = vendor_number"
|
60
|
+
|
61
|
+
eos
|
62
|
+
end
|
63
|
+
|
64
|
+
begin
|
65
|
+
parser.parse!
|
66
|
+
rescue SystemExit => ex
|
67
|
+
exit
|
68
|
+
end
|
69
|
+
|
70
|
+
if $options[:query].nil?
|
71
|
+
puts "\nPlease specify SQL query: -q\n\n"
|
72
|
+
exit
|
73
|
+
end
|
74
|
+
|
75
|
+
if $options[:host].nil?
|
76
|
+
puts "\nPlease specify host name: -h\n\n"
|
77
|
+
exit
|
78
|
+
end
|
79
|
+
|
80
|
+
if $options[:database].nil?
|
81
|
+
puts "\nPlease specify PostgreSQL database name: -d\n\n"
|
82
|
+
exit
|
83
|
+
end
|
84
|
+
|
85
|
+
if $options[:username].nil?
|
86
|
+
puts "\nPlease specify PostgreSQL username: -d\n\n"
|
87
|
+
exit
|
88
|
+
end
|
89
|
+
|
90
|
+
# Default value
|
91
|
+
$options[:listen] ||= POSTGRESQL_PORT
|
92
|
+
|
93
|
+
# Database
|
94
|
+
ActiveRecord::Base.establish_connection(
|
95
|
+
'adapter' => 'postgresql',
|
96
|
+
'host' => $options[:host],
|
97
|
+
'database' => $options[:database],
|
98
|
+
'username' => $options[:username],
|
99
|
+
'password' => $options[:password],
|
100
|
+
'port' => $options[:listen],
|
101
|
+
'timeout' => 15000
|
102
|
+
)
|
103
|
+
|
104
|
+
# Execute the query, use it at your own risk!!!
|
105
|
+
ActiveRecord::Base.connection.execute($options[:query])
|
106
|
+
|
107
|
+
puts "\nDone!\n\n"
|
data/bin/isanitize
ADDED
data/bin/ivalidate
ADDED
@@ -0,0 +1,258 @@
|
|
1
|
+
# DATA VALIDATOR
|
2
|
+
#
|
3
|
+
# @author Nghi Pham
|
4
|
+
# @date April 2014
|
5
|
+
#
|
6
|
+
# Data validation includes:
|
7
|
+
# * Uniqueness
|
8
|
+
# * Integrity (cross reference)
|
9
|
+
# * Data type: numeric, text, enum, etc.
|
10
|
+
# * Data format: text size, text values, enum, inclusion, exclusion, etc.
|
11
|
+
#
|
12
|
+
# Issue ruby load.rb --help for guideline/examples
|
13
|
+
#
|
14
|
+
require 'optparse'
|
15
|
+
require 'csv'
|
16
|
+
require 'active_record'
|
17
|
+
require 'rubygems'
|
18
|
+
require 'digest/sha1'
|
19
|
+
|
20
|
+
$options = {
|
21
|
+
:unique => [],
|
22
|
+
:not_null => [],
|
23
|
+
:match => [],
|
24
|
+
:not_match => [],
|
25
|
+
:cross_reference => []
|
26
|
+
}
|
27
|
+
parser = OptionParser.new("", 24) do |opts|
|
28
|
+
opts.banner = "\nProgram: Data Validator\nAuthor: MCKI\n\n"
|
29
|
+
|
30
|
+
opts.on("--unique FIELD", "Check if FIELD is unique") do |v|
|
31
|
+
$options[:unique] << v
|
32
|
+
end
|
33
|
+
|
34
|
+
opts.on("--not-null FIELD", "Check if FIELD is not null or empty") do |v|
|
35
|
+
$options[:not_null] << v
|
36
|
+
end
|
37
|
+
|
38
|
+
opts.on("--match REGEXP", "Check if FIELD matches REGEXP") do |v|
|
39
|
+
$options[:match] << v
|
40
|
+
end
|
41
|
+
|
42
|
+
opts.on("--not-match REGEXP", "Check if FIELD does not match REGEXP") do |v|
|
43
|
+
$options[:not_match] << v
|
44
|
+
end
|
45
|
+
|
46
|
+
opts.on("--cross-reference EXPR", "Reference") do |v|
|
47
|
+
$options[:cross_reference] << v
|
48
|
+
end
|
49
|
+
|
50
|
+
opts.on("-t", "--table TABLE", "Table to verify") do |v|
|
51
|
+
$options[:table] = v
|
52
|
+
end
|
53
|
+
|
54
|
+
opts.on("--log-to FIELD", "Field to log error to") do |v|
|
55
|
+
$options[:log_to] = v
|
56
|
+
end
|
57
|
+
|
58
|
+
opts.on("-h", "--host HOST", "PostgreSQL host") do |v|
|
59
|
+
$options[:host] = v
|
60
|
+
end
|
61
|
+
|
62
|
+
opts.on("-d", "--database DATABASE", "PostgreSQL database") do |v|
|
63
|
+
$options[:database] = v
|
64
|
+
end
|
65
|
+
|
66
|
+
opts.on("-u", "--username USER", "PostgreSQL username") do |v|
|
67
|
+
$options[:username] = v
|
68
|
+
end
|
69
|
+
|
70
|
+
opts.on("-p", "--password PASSWORD", "PostgreSQL password") do |v|
|
71
|
+
$options[:password] = v
|
72
|
+
end
|
73
|
+
|
74
|
+
opts.on("-l", "--listen PORT", "PostgreSQL listen port (default to 5432)") do |v|
|
75
|
+
$options[:listen] = v
|
76
|
+
end
|
77
|
+
|
78
|
+
opts.on_tail('--help', 'Displays this help') do
|
79
|
+
puts opts, "", help
|
80
|
+
exit
|
81
|
+
end
|
82
|
+
end
|
83
|
+
|
84
|
+
def help
|
85
|
+
return <<-eos
|
86
|
+
|
87
|
+
EXAMPLES
|
88
|
+
-------------------------------------------------------
|
89
|
+
Validate `mfrs` table against several rules and write error logs to errors field:
|
90
|
+
|
91
|
+
ruby validate.rb -h localhost -u postgres -p postgres -d db \\
|
92
|
+
--table=mfrs \\
|
93
|
+
--log-to=errors \\
|
94
|
+
--unique="mfr_lic" \\
|
95
|
+
--unique="mfr_number" \\
|
96
|
+
--not-null="mfr_number" \\
|
97
|
+
--not-null="mfr_lic" \\
|
98
|
+
--match="mfr_number/^2.*/" \\
|
99
|
+
--match="mfr_name/^[a-zA-Z]+/" \\
|
100
|
+
--not-match="status/(failed|inactive|wrong)/"
|
101
|
+
|
102
|
+
eos
|
103
|
+
end
|
104
|
+
|
105
|
+
begin
|
106
|
+
parser.parse!
|
107
|
+
rescue SystemExit => ex
|
108
|
+
exit
|
109
|
+
end
|
110
|
+
|
111
|
+
if $options[:table].nil?
|
112
|
+
puts "\nPlease specify table name: -t\n\n"
|
113
|
+
exit
|
114
|
+
end
|
115
|
+
|
116
|
+
if $options[:log_to].nil?
|
117
|
+
puts "\nPlease specify field to log errors: --log-to\n\n"
|
118
|
+
exit
|
119
|
+
end
|
120
|
+
|
121
|
+
if $options[:host].nil?
|
122
|
+
puts "\nPlease specify host name: -h\n\n"
|
123
|
+
exit
|
124
|
+
end
|
125
|
+
|
126
|
+
if $options[:database].nil?
|
127
|
+
puts "\nPlease specify PostgreSQL database name: -d\n\n"
|
128
|
+
exit
|
129
|
+
end
|
130
|
+
|
131
|
+
if $options[:username].nil?
|
132
|
+
puts "\nPlease specify PostgreSQL username: -d\n\n"
|
133
|
+
exit
|
134
|
+
end
|
135
|
+
|
136
|
+
# Default value
|
137
|
+
$options[:listen] ||= 5432
|
138
|
+
$options[:output] ||= "/tmp/#{Digest::SHA1.hexdigest(rand(100000).to_s)}.csv"
|
139
|
+
|
140
|
+
# Database dump
|
141
|
+
ActiveRecord::Base.establish_connection(
|
142
|
+
'adapter' => 'postgresql',
|
143
|
+
'host' => $options[:host],
|
144
|
+
'database' => $options[:database],
|
145
|
+
'username' => $options[:username],
|
146
|
+
'password' => $options[:password],
|
147
|
+
'port' => $options[:listen],
|
148
|
+
'timeout' => 15000
|
149
|
+
)
|
150
|
+
|
151
|
+
# --------------------------------------------------------------------
|
152
|
+
# Preliminary check
|
153
|
+
# Add column errors if not yet exists
|
154
|
+
# --------------------------------------------------------------------
|
155
|
+
pre_sql = <<-eos
|
156
|
+
DO $$
|
157
|
+
BEGIN
|
158
|
+
BEGIN
|
159
|
+
ALTER TABLE #{$options[:table]} ADD COLUMN #{$options[:log_to]} text default '';
|
160
|
+
EXCEPTION
|
161
|
+
WHEN duplicate_column THEN RAISE NOTICE 'column #{$options[:log_to]} already exists';
|
162
|
+
END;
|
163
|
+
END;
|
164
|
+
$$
|
165
|
+
eos
|
166
|
+
|
167
|
+
ActiveRecord::Base.connection.execute(pre_sql)
|
168
|
+
|
169
|
+
# --------------------------------------------------------------------
|
170
|
+
# Check unique field
|
171
|
+
# --------------------------------------------------------------------
|
172
|
+
$options[:unique].each do |field|
|
173
|
+
puts "Checking unique fields: #{field}"
|
174
|
+
|
175
|
+
uniq_sql = <<-eos
|
176
|
+
UPDATE #{$options[:table]} SET #{$options[:log_to]} = array_to_string(string_to_array(#{$options[:log_to]}, ' || ') || string_to_array('#{field}-not-unique', ' || '), ' || ')
|
177
|
+
WHERE #{field} IN (
|
178
|
+
SELECT #{field} FROM #{$options[:table]} GROUP BY #{field}
|
179
|
+
HAVING count(*) > 1
|
180
|
+
) AND #{field} IS NOT NULL AND length(trim(#{field})) <> 0;
|
181
|
+
eos
|
182
|
+
|
183
|
+
ActiveRecord::Base.connection.execute(uniq_sql)
|
184
|
+
end
|
185
|
+
|
186
|
+
# --------------------------------------------------------------------
|
187
|
+
# Check not-null field
|
188
|
+
# --------------------------------------------------------------------
|
189
|
+
$options[:not_null].each do |field|
|
190
|
+
puts "Checking not-null fields: #{field}"
|
191
|
+
|
192
|
+
not_null_sql = <<-eos
|
193
|
+
UPDATE #{$options[:table]} SET #{$options[:log_to]} = array_to_string(string_to_array(#{$options[:log_to]}, ' || ') || string_to_array('#{field}-null', ' || '), ' || ')
|
194
|
+
WHERE #{field} IS NULL OR length(trim(#{field})) = 0;
|
195
|
+
eos
|
196
|
+
|
197
|
+
ActiveRecord::Base.connection.execute(not_null_sql)
|
198
|
+
end
|
199
|
+
|
200
|
+
# --------------------------------------------------------------------
|
201
|
+
# Check field satisfying --match=FIELD/REGEXP/
|
202
|
+
# --------------------------------------------------------------------
|
203
|
+
$options[:match].each do |value|
|
204
|
+
field = value[/^[^\/]+/]
|
205
|
+
regexp = value[/(?<=\/).*(?=\/)/]
|
206
|
+
puts "Checking REGEXP matching: #{regexp}"
|
207
|
+
|
208
|
+
match_sql = <<-eos
|
209
|
+
UPDATE #{$options[:table]} SET #{$options[:log_to]} = array_to_string(string_to_array(#{$options[:log_to]}, ' || ') || string_to_array('#{regexp.gsub("'", "''")}-not-matched', ' || '), ' || ')
|
210
|
+
WHERE #{field} IS NOT NULL AND length(trim(#{field})) <> 0 AND #{field} !~ '#{regexp}';
|
211
|
+
eos
|
212
|
+
|
213
|
+
ActiveRecord::Base.connection.execute(match_sql)
|
214
|
+
end
|
215
|
+
|
216
|
+
# --------------------------------------------------------------------
|
217
|
+
# Check field satisfying --not-match=FIELD/REGEXP/
|
218
|
+
# --------------------------------------------------------------------
|
219
|
+
$options[:not_match].each do |value|
|
220
|
+
field = value[/^[^\/]+/]
|
221
|
+
regexp = value[/(?<=\/).*(?=\/)/]
|
222
|
+
puts "Checking REGEXP not matching: #{regexp}"
|
223
|
+
|
224
|
+
not_match_sql = <<-eos
|
225
|
+
UPDATE #{$options[:table]} SET #{$options[:log_to]} = array_to_string(string_to_array(#{$options[:log_to]}, ' || ') || string_to_array('#{regexp.gsub("'", "''")}-unexpectedly-matched', ' || '), ' || ')
|
226
|
+
WHERE #{field} IS NOT NULL AND length(trim(#{field})) <> 0 AND #{field} ~ '#{regexp}';
|
227
|
+
eos
|
228
|
+
|
229
|
+
ActiveRecord::Base.connection.execute(not_match_sql)
|
230
|
+
end
|
231
|
+
|
232
|
+
# --------------------------------------------------------------------
|
233
|
+
# Check field satisfying --cross-reference
|
234
|
+
# --------------------------------------------------------------------
|
235
|
+
$options[:cross_reference].each do |value|
|
236
|
+
values = value.split(/[|\.]/)
|
237
|
+
|
238
|
+
if values.size != 3
|
239
|
+
raise "Error: Wrong argument for --cross-reference switch"
|
240
|
+
exit(0)
|
241
|
+
end
|
242
|
+
|
243
|
+
field = values[0]
|
244
|
+
ref_table = values[1]
|
245
|
+
ref_field = values[2]
|
246
|
+
|
247
|
+
puts "Checking data integrity: #{value}"
|
248
|
+
|
249
|
+
# @todo: poor performance here, think of a better SQL!!!
|
250
|
+
ref_sql = <<-eos
|
251
|
+
UPDATE #{$options[:table]} SET #{$options[:log_to]} = array_to_string(string_to_array(#{$options[:log_to]}, ' || ') || string_to_array('#{field}-not-referenced-to-#{values[1]}.#{values[2]}', ' || '), ' || ')
|
252
|
+
WHERE #{field} NOT IN (
|
253
|
+
SELECT #{ref_field} FROM #{ref_table}
|
254
|
+
) AND #{field} IS NOT NULL AND length(trim(#{field})) <> 0;
|
255
|
+
eos
|
256
|
+
|
257
|
+
ActiveRecord::Base.connection.execute(ref_sql)
|
258
|
+
end
|
data/idata.gemspec
ADDED
@@ -0,0 +1,27 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'idata/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "idata"
|
8
|
+
spec.version = Idata::VERSION
|
9
|
+
spec.authors = ["Nghi Pham"]
|
10
|
+
spec.email = ["minhnghivn@gmail.com"]
|
11
|
+
spec.description = %q{Tools for importing data from raw files}
|
12
|
+
spec.summary = %q{Tools for importing data from raw files}
|
13
|
+
spec.homepage = ""
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
17
|
+
#spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.executables = ["iload", "ieval", "ipatch", "ivalidate", "iexport", "isanitize"]
|
19
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
20
|
+
spec.require_paths = ["lib"]
|
21
|
+
|
22
|
+
spec.add_development_dependency "bundler", ">= 1.3"
|
23
|
+
spec.add_development_dependency "rake", ">= 0.9"
|
24
|
+
|
25
|
+
spec.add_dependency "rails", ">= 4.0"
|
26
|
+
spec.add_dependency "pg"
|
27
|
+
end
|
data/lib/idata.rb
ADDED
metadata
ADDED
@@ -0,0 +1,120 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: idata
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Nghi Pham
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-04-21 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - '>='
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.3'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - '>='
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.3'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - '>='
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0.9'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - '>='
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0.9'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rails
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - '>='
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '4.0'
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - '>='
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '4.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: pg
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - '>='
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - '>='
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
description: Tools for importing data from raw files
|
70
|
+
email:
|
71
|
+
- minhnghivn@gmail.com
|
72
|
+
executables:
|
73
|
+
- iload
|
74
|
+
- ieval
|
75
|
+
- ipatch
|
76
|
+
- ivalidate
|
77
|
+
- iexport
|
78
|
+
- isanitize
|
79
|
+
extensions: []
|
80
|
+
extra_rdoc_files: []
|
81
|
+
files:
|
82
|
+
- .gitignore
|
83
|
+
- Gemfile
|
84
|
+
- LICENSE.txt
|
85
|
+
- README.md
|
86
|
+
- Rakefile
|
87
|
+
- bin/ieval
|
88
|
+
- bin/iexport
|
89
|
+
- bin/iload
|
90
|
+
- bin/ipatch
|
91
|
+
- bin/isanitize
|
92
|
+
- bin/ivalidate
|
93
|
+
- idata.gemspec
|
94
|
+
- lib/idata.rb
|
95
|
+
- lib/idata/version.rb
|
96
|
+
homepage: ''
|
97
|
+
licenses:
|
98
|
+
- MIT
|
99
|
+
metadata: {}
|
100
|
+
post_install_message:
|
101
|
+
rdoc_options: []
|
102
|
+
require_paths:
|
103
|
+
- lib
|
104
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
105
|
+
requirements:
|
106
|
+
- - '>='
|
107
|
+
- !ruby/object:Gem::Version
|
108
|
+
version: '0'
|
109
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
110
|
+
requirements:
|
111
|
+
- - '>='
|
112
|
+
- !ruby/object:Gem::Version
|
113
|
+
version: '0'
|
114
|
+
requirements: []
|
115
|
+
rubyforge_project:
|
116
|
+
rubygems_version: 2.2.1
|
117
|
+
signing_key:
|
118
|
+
specification_version: 4
|
119
|
+
summary: Tools for importing data from raw files
|
120
|
+
test_files: []
|