embulk-parser-flexml 0.0.2 → 0.2.1
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 +4 -4
- data/README.md +54 -1
- data/embulk-parser-flexml.gemspec +1 -1
- data/lib/embulk/parser/flexml.rb +4 -4
- metadata +2 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 88bcb05c13577d9578dba6cf39f3cb715b022a8e
|
|
4
|
+
data.tar.gz: 8ffb9d31f11f38bf02b439704a52d38339e2d5db
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 0cefedddeb0dfcbed1818a7f954e7d37e106e2c19199548afa2ba279cb1a17514906bcd2006e203c1e1e747600291ae6747027fc7d813d1ed86db6d343e3bb63
|
|
7
|
+
data.tar.gz: 3c5b4a1569a2bf86f1af37e96d0a6bfcbb31c6506b983b8a4cd8fbe5a681c78bc76fd4aff2bbed620a6b2b7e361d3392174ddd8fa208a72bd915323007e85647
|
data/README.md
CHANGED
|
@@ -1,2 +1,55 @@
|
|
|
1
1
|
# embulk-parser-flexml
|
|
2
|
-
|
|
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.
|
|
6
|
+
spec.version = "0.2.1"
|
|
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}
|
data/lib/embulk/parser/flexml.rb
CHANGED
|
@@ -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"]
|
|
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
|
-
Embulk.logger.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"].nil?
|
|
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
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: embulk-parser-flexml
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.
|
|
4
|
+
version: 0.2.1
|
|
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
|
+
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
|