gorgeous 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- data/README.md +22 -0
- data/bin/gorgeous +126 -0
- data/lib/gorgeous.rb +241 -0
- metadata +69 -0
data/README.md
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Usage:
|
2
|
+
|
3
|
+
gorgeous [-i] [-F <in-format>] [-T <out-format>] [-q <query>] [-o <destination>] FILE ...
|
4
|
+
|
5
|
+
This utility converts data between different formats.
|
6
|
+
Formats are one of: json, xml, yaml, ruby, email, url
|
7
|
+
|
8
|
+
Input can be read from STDIN as well as files given on the command-line.
|
9
|
+
|
10
|
+
Options:
|
11
|
+
|
12
|
+
-i Convert file in-place
|
13
|
+
-F Input format
|
14
|
+
-T Output format
|
15
|
+
-q Query selector in format similar to XPath (see below)
|
16
|
+
-o Write output to file instead of STDOUT
|
17
|
+
|
18
|
+
Query format:
|
19
|
+
|
20
|
+
"/items/comments[1]/text" -- 2nd comment body of each item
|
21
|
+
"/items[-1]/user/full_name" -- name of user for last item
|
22
|
+
"//user/username" -- usernames of all users anywhere in the document
|
data/bin/gorgeous
ADDED
@@ -0,0 +1,126 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
help = <<-MSG
|
4
|
+
Usage: gorgeous [-i] [-F <in-format>] [-T <out-format>] [-q <query>] [-o <destination>] FILE ...
|
5
|
+
|
6
|
+
This utility converts data between different formats.
|
7
|
+
Formats are one of: json, xml, yaml, ruby, email, url
|
8
|
+
|
9
|
+
Input can be read from STDIN as well as files given on the command-line.
|
10
|
+
|
11
|
+
Options:
|
12
|
+
-i Convert file in-place
|
13
|
+
-F Input format
|
14
|
+
-T Output format
|
15
|
+
-q Query selector in format similar to XPath (see below)
|
16
|
+
-o Write output to file instead of STDOUT
|
17
|
+
|
18
|
+
Query format:
|
19
|
+
"/items/comments[1]/text" -- 2nd comment body of each item
|
20
|
+
"/items[-1]/user/full_name" -- name of user for last item
|
21
|
+
"//user/username" -- usernames of all users anywhere in the document
|
22
|
+
|
23
|
+
MSG
|
24
|
+
|
25
|
+
if ARGV.index('-h') or ARGV.index('--help')
|
26
|
+
puts help
|
27
|
+
exit
|
28
|
+
end
|
29
|
+
|
30
|
+
require 'gorgeous'
|
31
|
+
|
32
|
+
help_usage = help.split("\n", 2).first
|
33
|
+
|
34
|
+
options = help_usage.scan(/[^\w-](-[a-z])(?: <(.+?)>)?/i).inject({}) do |opts, (flag, value)|
|
35
|
+
if value.nil?
|
36
|
+
opts[flag] = true if ARGV.delete flag
|
37
|
+
elsif idx = ARGV.index(flag)
|
38
|
+
opts[flag] = ARGV[idx + 1]
|
39
|
+
2.times { ARGV.delete_at idx }
|
40
|
+
end
|
41
|
+
opts
|
42
|
+
end
|
43
|
+
|
44
|
+
in_place = options['-i']
|
45
|
+
query_path = options['-q']
|
46
|
+
input_format = options['-F'] && options['-F'].to_sym
|
47
|
+
output_format ||= options['-T'] && options['-T'].to_sym
|
48
|
+
destination = options['-o']
|
49
|
+
from_stdin = !$stdin.tty?
|
50
|
+
|
51
|
+
if from_stdin
|
52
|
+
if in_place
|
53
|
+
warn "can't edit stdin in place"
|
54
|
+
exit 1
|
55
|
+
end
|
56
|
+
elsif in_place and destination
|
57
|
+
warn "can't combine -i and -o flags"
|
58
|
+
exit 1
|
59
|
+
elsif ARGV.empty?
|
60
|
+
warn help_usage
|
61
|
+
exit 1
|
62
|
+
end
|
63
|
+
|
64
|
+
# clobber the input file
|
65
|
+
destination = ARGV.first if in_place
|
66
|
+
|
67
|
+
input = Gorgeous.new(ARGF, :filename => ARGV.first, :format => input_format, :query => query_path)
|
68
|
+
|
69
|
+
unless input.format
|
70
|
+
warn "unrecognized input format; specify explicit format with `-F <format>`"
|
71
|
+
exit 1
|
72
|
+
end
|
73
|
+
|
74
|
+
output_format ||= if destination
|
75
|
+
Gorgeous.filename_to_format(destination)
|
76
|
+
else
|
77
|
+
input.format
|
78
|
+
end
|
79
|
+
|
80
|
+
if output_format == :ruby
|
81
|
+
require 'pp'
|
82
|
+
output = input.data.pretty_inspect
|
83
|
+
elsif output_format == :json
|
84
|
+
require 'yajl/json_gem'
|
85
|
+
output = JSON.pretty_generate input.data
|
86
|
+
elsif output_format == :yaml
|
87
|
+
require 'yaml'
|
88
|
+
output = YAML.dump input.data
|
89
|
+
elsif input_format == :email and output_format == :xml
|
90
|
+
require 'nokogiri'
|
91
|
+
email = input.to_mail
|
92
|
+
part = email.html_part
|
93
|
+
html = Gorgeous.convert_utf8(part.decode_body, part.charset)
|
94
|
+
ugly = Nokogiri::HTML html
|
95
|
+
output = Gorgeous.pretty_xml(ugly)
|
96
|
+
elsif input_format == :email and output_format == :txt and not input.filtered?
|
97
|
+
email = input.to_mail
|
98
|
+
part = email.text_part
|
99
|
+
output = Gorgeous.convert_utf8(part.decode_body.strip, part.charset)
|
100
|
+
elsif output_format == :xml
|
101
|
+
output = Gorgeous.pretty_xml(input.to_xml)
|
102
|
+
elsif output_format == :url
|
103
|
+
require 'rack/utils'
|
104
|
+
output = Rack::Utils.build_nested_query(input.data)
|
105
|
+
elsif output_format == :txt
|
106
|
+
data = input.data
|
107
|
+
output = Array === data ? data.join("\n") : data.to_s
|
108
|
+
else
|
109
|
+
warn "don't know how to convert #{input_format} to #{output_format}"
|
110
|
+
exit 1
|
111
|
+
end
|
112
|
+
|
113
|
+
if destination
|
114
|
+
begin
|
115
|
+
File.open(destination, 'w') { |f| f << output }
|
116
|
+
rescue Errno::ENOENT
|
117
|
+
warn "error opening #{destination} for writing"
|
118
|
+
exit 1
|
119
|
+
end
|
120
|
+
else
|
121
|
+
begin
|
122
|
+
puts output
|
123
|
+
rescue Errno::EPIPE
|
124
|
+
# ignore "broken pipe" exception
|
125
|
+
end
|
126
|
+
end
|
data/lib/gorgeous.rb
ADDED
@@ -0,0 +1,241 @@
|
|
1
|
+
class Gorgeous
|
2
|
+
def self.filename_to_format(filename)
|
3
|
+
case File.extname(filename)
|
4
|
+
when '.json' then :json
|
5
|
+
when '.xml', '.html' then :xml
|
6
|
+
when '.rb' then :ruby
|
7
|
+
when '.yml', '.yaml' then :yaml
|
8
|
+
when '.mail', '.email' then :email
|
9
|
+
end
|
10
|
+
end
|
11
|
+
|
12
|
+
def self.pretty_xml(ugly)
|
13
|
+
tidy = Nokogiri::XSLT DATA.read
|
14
|
+
tidy.transform(ugly).to_s
|
15
|
+
end
|
16
|
+
|
17
|
+
def self.convert_utf8(string, from_charset)
|
18
|
+
if from_charset.nil? or from_charset.downcase.tr('-', '') == 'utf8'
|
19
|
+
string
|
20
|
+
else
|
21
|
+
require 'iconv'
|
22
|
+
Iconv.conv 'utf-8', from_charset, string
|
23
|
+
end
|
24
|
+
end
|
25
|
+
|
26
|
+
def self.headers_from_mail(email)
|
27
|
+
require 'active_support/ordered_hash'
|
28
|
+
require 'active_support/core_ext/object/blank'
|
29
|
+
|
30
|
+
address_field = lambda { |name|
|
31
|
+
if field = email.header[name]
|
32
|
+
values = field.addrs.map { |a|
|
33
|
+
Mail::Encodings.unquote_and_convert_to(a.format, 'utf-8')
|
34
|
+
}
|
35
|
+
values.size < 2 ? values.first : values
|
36
|
+
end
|
37
|
+
}
|
38
|
+
header_value = lambda { |name|
|
39
|
+
field = email.header[name] and field.value.to_s
|
40
|
+
}
|
41
|
+
decoded_value = lambda { |name|
|
42
|
+
field = email.header[name]
|
43
|
+
Mail::Encodings.unquote_and_convert_to(field.value, 'utf-8') if field
|
44
|
+
}
|
45
|
+
|
46
|
+
data = ActiveSupport::OrderedHash.new
|
47
|
+
data[:subject] = decoded_value['subject']
|
48
|
+
data[:from] = address_field['from']
|
49
|
+
data[:to] = address_field['to']
|
50
|
+
data[:cc] = address_field['cc']
|
51
|
+
data[:bcc] = address_field['bcc']
|
52
|
+
data[:reply_to] = address_field['reply-to']
|
53
|
+
data[:return_path] = email.return_path
|
54
|
+
|
55
|
+
data[:message_id] = email.message_id
|
56
|
+
data[:in_reply_to] = email.in_reply_to
|
57
|
+
data[:references] = email.references
|
58
|
+
|
59
|
+
data[:date] = email.date
|
60
|
+
data[:sender] = address_field['sender']
|
61
|
+
data[:delivered_to] = header_value['delivered-to']
|
62
|
+
data[:original_sender] = header_value['x-original-sender']
|
63
|
+
data[:content_type] = email.content_type.to_s.split(';', 2).first.presence
|
64
|
+
data[:precedence] = header_value['precedence']
|
65
|
+
|
66
|
+
data.tap { |hash| hash.reject! { |k,v| v.nil? } }
|
67
|
+
end
|
68
|
+
|
69
|
+
# adapted from webmock
|
70
|
+
def self.http_from_string(raw_response)
|
71
|
+
if raw_response.is_a?(IO)
|
72
|
+
string = raw_response.read
|
73
|
+
raw_response.close
|
74
|
+
raw_response = string
|
75
|
+
end
|
76
|
+
socket = ::Net::BufferedIO.new(raw_response)
|
77
|
+
response = ::Net::HTTPResponse.read_new(socket)
|
78
|
+
transfer_encoding = response.delete('transfer-encoding') # chunks were already read
|
79
|
+
response.reading_body(socket, true) {}
|
80
|
+
|
81
|
+
options = {}
|
82
|
+
options[:headers] = {}
|
83
|
+
response.each_header { |name, value| options[:headers][name] = value }
|
84
|
+
options[:headers]['transfer-encoding'] = transfer_encoding if transfer_encoding
|
85
|
+
options[:body] = response.read_body
|
86
|
+
options[:status] = [response.code.to_i, response.message]
|
87
|
+
options
|
88
|
+
end
|
89
|
+
|
90
|
+
def initialize(input, options = {})
|
91
|
+
@input = input
|
92
|
+
@format = options[:format]
|
93
|
+
@options = options
|
94
|
+
end
|
95
|
+
|
96
|
+
def filtered?
|
97
|
+
!!@options[:query]
|
98
|
+
end
|
99
|
+
|
100
|
+
def to_s
|
101
|
+
@str ||= @input.respond_to?(:read) ? @input.read : @input
|
102
|
+
end
|
103
|
+
|
104
|
+
def format
|
105
|
+
@format ||= begin
|
106
|
+
if @options[:filename]
|
107
|
+
self.class.filename_to_format(@options[:filename])
|
108
|
+
else
|
109
|
+
guess_format
|
110
|
+
end
|
111
|
+
end
|
112
|
+
end
|
113
|
+
|
114
|
+
# typically hash or array
|
115
|
+
def data
|
116
|
+
apply_query case format
|
117
|
+
when :xml
|
118
|
+
require 'active_support/core_ext/hash/conversions'
|
119
|
+
Hash.from_xml(to_s)
|
120
|
+
when :json
|
121
|
+
require 'yajl/json_gem'
|
122
|
+
JSON.parse to_s
|
123
|
+
when :yaml
|
124
|
+
require 'yaml'
|
125
|
+
YAML.load to_s
|
126
|
+
when :email
|
127
|
+
self.class.headers_from_mail to_mail
|
128
|
+
when :ruby
|
129
|
+
eval to_s # TODO: sandbox
|
130
|
+
when :url
|
131
|
+
require 'rack/utils'
|
132
|
+
Rack::Utils.parse_nested_query(to_s.strip)
|
133
|
+
when :http
|
134
|
+
require 'net/http'
|
135
|
+
self.class.http_from_string(to_s)[:headers]
|
136
|
+
else
|
137
|
+
raise ArgumentError, "don't know how to decode #{format}"
|
138
|
+
end
|
139
|
+
end
|
140
|
+
|
141
|
+
def to_xml
|
142
|
+
require 'nokogiri'
|
143
|
+
Nokogiri to_s
|
144
|
+
end
|
145
|
+
|
146
|
+
def to_mail
|
147
|
+
require 'mail'
|
148
|
+
raw = to_s.lstrip
|
149
|
+
raw << "\n" unless raw[-1, 1] == "\n"
|
150
|
+
Mail.new raw
|
151
|
+
end
|
152
|
+
|
153
|
+
private
|
154
|
+
|
155
|
+
def guess_format
|
156
|
+
case to_s
|
157
|
+
when /\A\s*[\[\{]/ then :json
|
158
|
+
when /\A\s*</ then :xml
|
159
|
+
when /\A---\s/ then :yaml
|
160
|
+
when /\A\S+=\S+\Z/ then :url
|
161
|
+
end
|
162
|
+
end
|
163
|
+
|
164
|
+
def apply_query(obj)
|
165
|
+
if filtered?
|
166
|
+
require 'active_support/core_ext/object/blank'
|
167
|
+
query = @options[:query].dup
|
168
|
+
while query.sub!(%r{(//?)(\w+)(?:\[(-?\d+)\])?}, '')
|
169
|
+
obj = filter_resultset(obj, $2, $3, $1.length == 2)
|
170
|
+
break if obj.nil?
|
171
|
+
end
|
172
|
+
end
|
173
|
+
obj
|
174
|
+
end
|
175
|
+
|
176
|
+
def filter_resultset(obj, key, idx = nil, deep = false)
|
177
|
+
if Array === obj
|
178
|
+
obj.map { |o| filter_resultset(o, key, idx, deep) }.flatten.compact.presence
|
179
|
+
elsif Hash === obj
|
180
|
+
if deep
|
181
|
+
result = obj.map do |k, value|
|
182
|
+
if k.to_s == key.to_s then value
|
183
|
+
else filter_resultset(value, key, nil, deep)
|
184
|
+
end
|
185
|
+
end.flatten.compact.presence
|
186
|
+
else
|
187
|
+
result = obj[key.to_s] || obj[key.to_sym]
|
188
|
+
end
|
189
|
+
result = result[idx.to_i] if result and idx
|
190
|
+
result
|
191
|
+
end
|
192
|
+
end
|
193
|
+
end
|
194
|
+
|
195
|
+
__END__
|
196
|
+
<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
|
197
|
+
<xsl:output method="xml" encoding="UTF-8"/>
|
198
|
+
<xsl:param name="indent-increment" select="' '"/>
|
199
|
+
|
200
|
+
<xsl:template name="newline">
|
201
|
+
<xsl:text disable-output-escaping="yes">
|
202
|
+
</xsl:text>
|
203
|
+
</xsl:template>
|
204
|
+
|
205
|
+
<xsl:template match="comment() | processing-instruction()">
|
206
|
+
<xsl:param name="indent" select="''"/>
|
207
|
+
<xsl:call-template name="newline"/>
|
208
|
+
<xsl:value-of select="$indent"/>
|
209
|
+
<xsl:copy />
|
210
|
+
</xsl:template>
|
211
|
+
|
212
|
+
<xsl:template match="text()">
|
213
|
+
<xsl:param name="indent" select="''"/>
|
214
|
+
<xsl:call-template name="newline"/>
|
215
|
+
<xsl:value-of select="$indent"/>
|
216
|
+
<xsl:value-of select="normalize-space(.)"/>
|
217
|
+
</xsl:template>
|
218
|
+
|
219
|
+
<xsl:template match="text()[normalize-space(.)='']"/>
|
220
|
+
|
221
|
+
<xsl:template match="*">
|
222
|
+
<xsl:param name="indent" select="''"/>
|
223
|
+
<xsl:call-template name="newline"/>
|
224
|
+
<xsl:value-of select="$indent"/>
|
225
|
+
<xsl:choose>
|
226
|
+
<xsl:when test="count(child::*) > 0">
|
227
|
+
<xsl:copy>
|
228
|
+
<xsl:copy-of select="@*"/>
|
229
|
+
<xsl:apply-templates select="*|text()">
|
230
|
+
<xsl:with-param name="indent" select="concat ($indent, $indent-increment)"/>
|
231
|
+
</xsl:apply-templates>
|
232
|
+
<xsl:call-template name="newline"/>
|
233
|
+
<xsl:value-of select="$indent"/>
|
234
|
+
</xsl:copy>
|
235
|
+
</xsl:when>
|
236
|
+
<xsl:otherwise>
|
237
|
+
<xsl:copy-of select="."/>
|
238
|
+
</xsl:otherwise>
|
239
|
+
</xsl:choose>
|
240
|
+
</xsl:template>
|
241
|
+
</xsl:stylesheet>
|
metadata
ADDED
@@ -0,0 +1,69 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: gorgeous
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
hash: 27
|
5
|
+
prerelease:
|
6
|
+
segments:
|
7
|
+
- 0
|
8
|
+
- 1
|
9
|
+
- 0
|
10
|
+
version: 0.1.0
|
11
|
+
platform: ruby
|
12
|
+
authors:
|
13
|
+
- "Mislav Marohni\xC4\x87"
|
14
|
+
autorequire:
|
15
|
+
bindir: bin
|
16
|
+
cert_chain: []
|
17
|
+
|
18
|
+
date: 2011-02-10 00:00:00 +01:00
|
19
|
+
default_executable:
|
20
|
+
dependencies: []
|
21
|
+
|
22
|
+
description:
|
23
|
+
email: mislav.marohnic@gmail.com
|
24
|
+
executables:
|
25
|
+
- gorgeous
|
26
|
+
extensions: []
|
27
|
+
|
28
|
+
extra_rdoc_files: []
|
29
|
+
|
30
|
+
files:
|
31
|
+
- bin/gorgeous
|
32
|
+
- lib/gorgeous.rb
|
33
|
+
- README.md
|
34
|
+
has_rdoc: false
|
35
|
+
homepage: http://github.com/mislav/gorgeous
|
36
|
+
licenses: []
|
37
|
+
|
38
|
+
post_install_message:
|
39
|
+
rdoc_options: []
|
40
|
+
|
41
|
+
require_paths:
|
42
|
+
- lib
|
43
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
44
|
+
none: false
|
45
|
+
requirements:
|
46
|
+
- - ">="
|
47
|
+
- !ruby/object:Gem::Version
|
48
|
+
hash: 3
|
49
|
+
segments:
|
50
|
+
- 0
|
51
|
+
version: "0"
|
52
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
53
|
+
none: false
|
54
|
+
requirements:
|
55
|
+
- - ">="
|
56
|
+
- !ruby/object:Gem::Version
|
57
|
+
hash: 3
|
58
|
+
segments:
|
59
|
+
- 0
|
60
|
+
version: "0"
|
61
|
+
requirements: []
|
62
|
+
|
63
|
+
rubyforge_project:
|
64
|
+
rubygems_version: 1.5.0
|
65
|
+
signing_key:
|
66
|
+
specification_version: 3
|
67
|
+
summary: Convert between different data formats
|
68
|
+
test_files: []
|
69
|
+
|