embulk-parser-flexml 0.0.0 → 0.1.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 4a99a2091abdafdf69fdcc88e000bc6ce2c8e5cb
-  data.tar.gz: e157fc931e663f42d69011eacfae825dfb860790
+  metadata.gz: 7adaffddc6300c0dab74df9372121d310acbdaeb
+  data.tar.gz: 5ef5446c5dfc8746dbdebb12941819305a6f8820
 SHA512:
-  metadata.gz: 15c101ea8ccaac10911ae71de566684d246824b9ff3bcbd0dbb9c118784434074299fe31ee9f2fd88191ab0d37ee25467f59004f93d4dfa84316a5e1c6fb52f1
-  data.tar.gz: 79f44d9eaede4fd1b1f62775bf728fceb9304e25bc9c2a492507f6f4c2ca1c3db386d25a85c022b3187d597f3d7a72f64d9f25621f6bb31e42e2944dd5257093
+  metadata.gz: 4e89dbac3ec544f4cfee5bd51fbaccc997751977e204c9bdbca2493153c4e4c928ab42c10e11fa4a5e009c8550fdf160284ec7999cfa55221e439d99c1b79171
+  data.tar.gz: 3bb2d3ed00c8ef58505f212fcf6613a02836e4fe74f2f578c54f9d42ed809ab99b137cfdd3f856896f74349cbb35230e33753005b902cfdc2cc5a2badf702330

data/README.md

@@ -1,2 +1,52 @@
 # 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)
+
+## 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       = "0.0.0"
+  spec.version       = "0.1.1"
   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

@@ -1,9 +1,9 @@
 require 'rexml/document'
 
+include REXML
+
 module Embulk
   module Parser
-    include REXML
-
     class Flexml < ParserPlugin
       Plugin.register_parser("flexml", self)
 
@@ -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
 

metadata

@@ -1,21 +1,21 @@
 --- !ruby/object:Gem::Specification
 name: embulk-parser-flexml
 version: !ruby/object:Gem::Version
-  version: 0.0.0
+  version: 0.1.1
 platform: ruby
 authors:
 - Surya Asriadie
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-11-15 00:00:00.000000000 Z
+date: 2021-12-08 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: