embulk-parser-flexml 0.0.1 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 70dc509b53da61f755e0991ef539092f5e5b30ab
-  data.tar.gz: 5183d09472fde46d526af247a02b262d1e7eb2c6
+  metadata.gz: b76e551255f6f521fd1f4523bc51b996b55f9e27
+  data.tar.gz: 0e90b31b02642200bc23010cd87486968c752492
 SHA512:
-  metadata.gz: 2c6f7f8cc4251e0bfeb7777a7f6de57b392ce16df2af57632e8d1a59f3c2f879d02594040f46c6d26fdc385974ada848e84a9c5c8dbcfe9180c137b3bdccd93a
-  data.tar.gz: bea0d8c2363080e866e2b12a8ed96467c9e61c894a6508efcc4aef2796ebe8444c04736c7f76bdc6908a5bb6e90dd92c23eca248fe6ee3064f53767df9ba6f10
+  metadata.gz: 93dd096b3c715506298bf007c9b68177182071d49da644d1519811a82af2e1649ff263ea3d5da0da7914b802f79ee0184a1565f86926fa7a5735966521002479
+  data.tar.gz: 2e37018a51524203ff8d9011627e9133b55b8fcd3c6fc24bff415ad844ee9bf1922042e5a01a288a67af5fae801fb4b12baec83a5515a6b947847a98610d8d44

data/README.md

@@ -1,2 +1,55 @@
 # embulk-parser-flexml
-Flexible xml parser for embulk - supports xpath and attributes
+
+Parser plugin for [Embulk](https://github.com/embulk/embulk).
+
+Flexible xml parser for embulk. read data using xpath and from attributes
+
+* **Plugin type**: parser
+* **Load all or nothing**: yes
+* **Resume supported**: no
+
+## Configuration
+
+- **type**: specify this plugin as `flexml` .
+- **root**: root property to start fetching each entries, specify in *path/to/node* style (string, required)
+- **schema**: specify the attribute of table and data type (required)
+    - **name**: name of the attribute (string, required)
+    - **type**: type of the attribute (string, required)
+    - **attribute**: if specified, value of this attribute will be the output, otherwise child will be the output (string, optional)
+    - **xpath**: child element to select (string, required)
+    - **format**: timestamp format to parse (string, required)
+    - **timezone**: timestamp will be parsed in this timezone (string, optional)
+
+
+## Example
+
+### Configuration
+
+```yaml
+parser:
+    type: flexml
+    root: Team/Players/Player
+    schema:
+        - { name: name, type: string, attribute: name }
+        - { name: age, type: long, attribute: age }
+        - { name: about, type: string, xpath: About }
+        - { name: facebook, type: string, xpath: "SocialMedia[@type='facebook']", attribute: url }
+        - { name: twitter, type: string, xpath: "SocialMedia[@type='twitter']", attribute: url }
+```
+
+### XML
+
+```xml
+<?xml version="1.0" encoding="utf-8" standalone="no"?>
+<Team>
+    <Players>
+        <Player name="Locatelli" age="23">
+            <About>
+                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.
+            </About>
+            <SocialMedia type="facebook" url="https://www.facebook.com/locamanuel73"/>
+            <SocialMedia type="twitter" url="https://twitter.com/locamanuel73"/>
+        </Player>
+    </Players>
+</Team>
+```

data/embulk-parser-flexml.gemspec

@@ -3,7 +3,7 @@ $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
 
 Gem::Specification.new do |spec|
   spec.name          = "embulk-parser-flexml"
-  spec.version       = "0.0.1"
+  spec.version       = "0.2.0"
   spec.authors       = ["Surya Asriadie"]
   spec.email         = ["surya.asriadie@gmail.com"]
   spec.summary       = %q{Flexible Embulk parser plugin for XML}
@@ -15,7 +15,7 @@ Gem::Specification.new do |spec|
   spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
   spec.require_paths = ["lib"]
 
-  spec.add_dependency "rexml", "~> 3.1"
+  spec.add_dependency "rexml", "~> 3.1.9"
   spec.add_development_dependency "bundler", "~> 1.0"
   spec.add_development_dependency 'embulk', ['>= 0.9.15']
   spec.add_development_dependency "rake", "~> 10.0"

data/lib/embulk/parser/flexml.rb

@@ -14,7 +14,7 @@ module Embulk
           if s["type"] == "timestamp"
             memo[s["name"]].merge!({
               "format" => s["format"],
-              "timezone" => s["timezone"] || "+0900"
+              "timezone" => s["timezone"]
             })
           end
           memo
@@ -38,8 +38,6 @@ module Embulk
               values = @task[:schema].map do |f, c|
                 row = if c.has_key?("xpath")
                     XPath.first(e, c["xpath"])
-                  elsif c.has_key?("element")
-                    e.element(c["element"])
                   else
                     e
                   end
@@ -55,7 +53,7 @@ module Embulk
               @page_builder.add(values)
             end
           rescue Exception => e
-            puts "=>>>> ERROR: #{e}"
+            Embulk.logger.error "Failed to parse xml: #{e.message}"
           end
         end
 
@@ -76,6 +74,8 @@ module Embulk
         when "timestamp"
           unless v.empty?
             dest = Time.strptime(v, config["format"])
+            return dest.utc if config["timezone"].empty?
+
             utc_offset = dest.utc_offset
             zone_offset = Time.zone_offset(config["timezone"])
             dest.localtime(zone_offset) + utc_offset - zone_offset

metadata

@@ -1,21 +1,21 @@
 --- !ruby/object:Gem::Specification
 name: embulk-parser-flexml
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.2.0
 platform: ruby
 authors:
 - Surya Asriadie
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-11-15 00:00:00.000000000 Z
+date: 2021-12-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.1'
+        version: 3.1.9
   name: rexml
   prerelease: false
   type: :runtime
@@ -23,7 +23,7 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.1'
+        version: 3.1.9
 - !ruby/object:Gem::Dependency
   requirement: !ruby/object:Gem::Requirement
     requirements: