embulk-parser-flexml 0.0.1 → 0.2.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA1:
3
- metadata.gz: 70dc509b53da61f755e0991ef539092f5e5b30ab
4
- data.tar.gz: 5183d09472fde46d526af247a02b262d1e7eb2c6
3
+ metadata.gz: b76e551255f6f521fd1f4523bc51b996b55f9e27
4
+ data.tar.gz: 0e90b31b02642200bc23010cd87486968c752492
5
5
  SHA512:
6
- metadata.gz: 2c6f7f8cc4251e0bfeb7777a7f6de57b392ce16df2af57632e8d1a59f3c2f879d02594040f46c6d26fdc385974ada848e84a9c5c8dbcfe9180c137b3bdccd93a
7
- data.tar.gz: bea0d8c2363080e866e2b12a8ed96467c9e61c894a6508efcc4aef2796ebe8444c04736c7f76bdc6908a5bb6e90dd92c23eca248fe6ee3064f53767df9ba6f10
6
+ metadata.gz: 93dd096b3c715506298bf007c9b68177182071d49da644d1519811a82af2e1649ff263ea3d5da0da7914b802f79ee0184a1565f86926fa7a5735966521002479
7
+ data.tar.gz: 2e37018a51524203ff8d9011627e9133b55b8fcd3c6fc24bff415ad844ee9bf1922042e5a01a288a67af5fae801fb4b12baec83a5515a6b947847a98610d8d44
data/README.md CHANGED
@@ -1,2 +1,55 @@
1
1
  # embulk-parser-flexml
2
- Flexible xml parser for embulk - supports xpath and attributes
2
+
3
+ Parser plugin for [Embulk](https://github.com/embulk/embulk).
4
+
5
+ Flexible xml parser for embulk. read data using xpath and from attributes
6
+
7
+ * **Plugin type**: parser
8
+ * **Load all or nothing**: yes
9
+ * **Resume supported**: no
10
+
11
+ ## Configuration
12
+
13
+ - **type**: specify this plugin as `flexml` .
14
+ - **root**: root property to start fetching each entries, specify in *path/to/node* style (string, required)
15
+ - **schema**: specify the attribute of table and data type (required)
16
+ - **name**: name of the attribute (string, required)
17
+ - **type**: type of the attribute (string, required)
18
+ - **attribute**: if specified, value of this attribute will be the output, otherwise child will be the output (string, optional)
19
+ - **xpath**: child element to select (string, required)
20
+ - **format**: timestamp format to parse (string, required)
21
+ - **timezone**: timestamp will be parsed in this timezone (string, optional)
22
+
23
+
24
+ ## Example
25
+
26
+ ### Configuration
27
+
28
+ ```yaml
29
+ parser:
30
+ type: flexml
31
+ root: Team/Players/Player
32
+ schema:
33
+ - { name: name, type: string, attribute: name }
34
+ - { name: age, type: long, attribute: age }
35
+ - { name: about, type: string, xpath: About }
36
+ - { name: facebook, type: string, xpath: "SocialMedia[@type='facebook']", attribute: url }
37
+ - { name: twitter, type: string, xpath: "SocialMedia[@type='twitter']", attribute: url }
38
+ ```
39
+
40
+ ### XML
41
+
42
+ ```xml
43
+ <?xml version="1.0" encoding="utf-8" standalone="no"?>
44
+ <Team>
45
+ <Players>
46
+ <Player name="Locatelli" age="23">
47
+ <About>
48
+ Manuel Locatelli Cavaliere OMRI (born 8 January 1998) is an Italian professional footballer who plays as a midfielder for Serie A club Juventus, on loan from Serie A club Sassuolo, and the Italy national team.
49
+ </About>
50
+ <SocialMedia type="facebook" url="https://www.facebook.com/locamanuel73"/>
51
+ <SocialMedia type="twitter" url="https://twitter.com/locamanuel73"/>
52
+ </Player>
53
+ </Players>
54
+ </Team>
55
+ ```
@@ -3,7 +3,7 @@ $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
3
3
 
4
4
  Gem::Specification.new do |spec|
5
5
  spec.name = "embulk-parser-flexml"
6
- spec.version = "0.0.1"
6
+ spec.version = "0.2.0"
7
7
  spec.authors = ["Surya Asriadie"]
8
8
  spec.email = ["surya.asriadie@gmail.com"]
9
9
  spec.summary = %q{Flexible Embulk parser plugin for XML}
@@ -15,7 +15,7 @@ Gem::Specification.new do |spec|
15
15
  spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
16
16
  spec.require_paths = ["lib"]
17
17
 
18
- spec.add_dependency "rexml", "~> 3.1"
18
+ spec.add_dependency "rexml", "~> 3.1.9"
19
19
  spec.add_development_dependency "bundler", "~> 1.0"
20
20
  spec.add_development_dependency 'embulk', ['>= 0.9.15']
21
21
  spec.add_development_dependency "rake", "~> 10.0"
@@ -14,7 +14,7 @@ module Embulk
14
14
  if s["type"] == "timestamp"
15
15
  memo[s["name"]].merge!({
16
16
  "format" => s["format"],
17
- "timezone" => s["timezone"] || "+0900"
17
+ "timezone" => s["timezone"]
18
18
  })
19
19
  end
20
20
  memo
@@ -38,8 +38,6 @@ module Embulk
38
38
  values = @task[:schema].map do |f, c|
39
39
  row = if c.has_key?("xpath")
40
40
  XPath.first(e, c["xpath"])
41
- elsif c.has_key?("element")
42
- e.element(c["element"])
43
41
  else
44
42
  e
45
43
  end
@@ -55,7 +53,7 @@ module Embulk
55
53
  @page_builder.add(values)
56
54
  end
57
55
  rescue Exception => e
58
- puts "=>>>> ERROR: #{e}"
56
+ Embulk.logger.error "Failed to parse xml: #{e.message}"
59
57
  end
60
58
  end
61
59
 
@@ -76,6 +74,8 @@ module Embulk
76
74
  when "timestamp"
77
75
  unless v.empty?
78
76
  dest = Time.strptime(v, config["format"])
77
+ return dest.utc if config["timezone"].empty?
78
+
79
79
  utc_offset = dest.utc_offset
80
80
  zone_offset = Time.zone_offset(config["timezone"])
81
81
  dest.localtime(zone_offset) + utc_offset - zone_offset
metadata CHANGED
@@ -1,21 +1,21 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: embulk-parser-flexml
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.0.1
4
+ version: 0.2.0
5
5
  platform: ruby
6
6
  authors:
7
7
  - Surya Asriadie
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2021-11-15 00:00:00.000000000 Z
11
+ date: 2021-12-09 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  requirement: !ruby/object:Gem::Requirement
15
15
  requirements:
16
16
  - - "~>"
17
17
  - !ruby/object:Gem::Version
18
- version: '3.1'
18
+ version: 3.1.9
19
19
  name: rexml
20
20
  prerelease: false
21
21
  type: :runtime
@@ -23,7 +23,7 @@ dependencies:
23
23
  requirements:
24
24
  - - "~>"
25
25
  - !ruby/object:Gem::Version
26
- version: '3.1'
26
+ version: 3.1.9
27
27
  - !ruby/object:Gem::Dependency
28
28
  requirement: !ruby/object:Gem::Requirement
29
29
  requirements: