xml_data_extractor 0.5.0 → 0.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b8705267e58445a552f2821a726e431ca93259e0782be80f2d47c2bcf1603aad
-  data.tar.gz: bd59596a4a0d554b055920a09891efeecc8589532b7d02e9e7b4715c54294eee
+  metadata.gz: 334896bd178759618062d648f74af638a88fde5c5cccfaf255279589207670a6
+  data.tar.gz: 6b85212f452f62bfa75a97c66f76c889cc39382d726d26b93a05800eb69e6dbe
 SHA512:
-  metadata.gz: 736fa4908c03918c71417b73e519fcfc658f65a1d7b4b2762ff00e73854e4f0a6f7495963ae68081403e52b50a26aae5dc9393dad66df9f366bd89c4e9af6ba9
-  data.tar.gz: 4ae406899d4538f2f92ec470502b1905a80bbda13273521a2b8d0d94207401cd9c0495ff20bc4c69351d2f4dc34aa21b4606504f716e019148734fe3d45f4f49
+  metadata.gz: 6899c3dafed6462fcb816edbe341a33e7a7388b2f3ba2724d5c2e0bab190f7ce00256c8bda35fbeaed7eaeb58ccfad8c3597c94a1e332ef7e5c125efd6a50924
+  data.tar.gz: 1b0b37b90adba98c9b2085d6a300473dca39bcafd4c801c58a5877ae57ad518be8d6079d0c61725f73809779ea3ace7590e4258494e2d1e0a61b7e914f8e5f69

data/.editorconfig

@@ -0,0 +1,8 @@
+[*]
+end_of_line = lf
+
+[*.{js,rb,yml,json,css,scss,html,erb,rake,slim}]
+insert_final_newline = true
+indent_style = space
+indent_size = 2
+trim_trailing_whitespace = true

data/.github/workflows/ci.yml

@@ -1,6 +1,6 @@
 name: ci
-on:
-  push:
+
+on: [push, pull_request]
 
 jobs:
   qa:
@@ -8,7 +8,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@v2.3.4
+        uses: actions/checkout@v3
 
       - name: Freeze autogenerated files
         run: |
@@ -18,7 +18,7 @@ jobs:
         uses: ruby/setup-ruby@v1
 
       - name: Cache Ruby Dependencies
-        uses: actions/cache@v2.1.4
+        uses: actions/cache@v3
         with:
           path: vendor/bundle
           key: ${{ runner.os }}-gem-${{ hashFiles('.ruby-version') }}-${{ hashFiles('**/Gemfile.lock') }}
@@ -28,4 +28,4 @@ jobs:
 
       - name: Run tests
         run: |
-          bin/rspec
+          bin/rspec

data/.gitignore

@@ -6,6 +6,7 @@
 /pkg/
 /spec/reports/
 /tmp/
+*.gem
 
 # rspec failure tracking
 .rspec_status

data/Gemfile.lock

@@ -1,46 +1,46 @@
 PATH
   remote: .
   specs:
-    xml_data_extractor (0.4.0)
+    xml_data_extractor (0.6.0)
       activesupport (~> 6.0)
       nokogiri (~> 1.0)
 
 GEM
   remote: https://rubygems.org/
   specs:
-    activesupport (6.1.3)
+    activesupport (6.1.5)
       concurrent-ruby (~> 1.0, >= 1.0.2)
       i18n (>= 1.6, < 2)
       minitest (>= 5.1)
       tzinfo (~> 2.0)
       zeitwerk (~> 2.3)
-    concurrent-ruby (1.1.8)
-    diff-lcs (1.4.4)
-    i18n (1.8.9)
+    concurrent-ruby (1.1.10)
+    diff-lcs (1.5.0)
+    i18n (1.10.0)
       concurrent-ruby (~> 1.0)
-    mini_portile2 (2.5.0)
-    minitest (5.14.3)
-    nokogiri (1.11.2)
-      mini_portile2 (~> 2.5.0)
+    mini_portile2 (2.8.0)
+    minitest (5.15.0)
+    nokogiri (1.13.3)
+      mini_portile2 (~> 2.8.0)
       racc (~> 1.4)
-    racc (1.5.2)
+    racc (1.6.0)
     rake (12.3.3)
-    rspec (3.10.0)
-      rspec-core (~> 3.10.0)
-      rspec-expectations (~> 3.10.0)
-      rspec-mocks (~> 3.10.0)
-    rspec-core (3.10.1)
-      rspec-support (~> 3.10.0)
-    rspec-expectations (3.10.1)
+    rspec (3.11.0)
+      rspec-core (~> 3.11.0)
+      rspec-expectations (~> 3.11.0)
+      rspec-mocks (~> 3.11.0)
+    rspec-core (3.11.0)
+      rspec-support (~> 3.11.0)
+    rspec-expectations (3.11.0)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.10.0)
-    rspec-mocks (3.10.1)
+      rspec-support (~> 3.11.0)
+    rspec-mocks (3.11.0)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.10.0)
-    rspec-support (3.10.1)
+      rspec-support (~> 3.11.0)
+    rspec-support (3.11.0)
     tzinfo (2.0.4)
       concurrent-ruby (~> 1.0)
-    zeitwerk (2.4.2)
+    zeitwerk (2.5.4)
 
 PLATFORMS
   ruby
@@ -51,4 +51,4 @@ DEPENDENCIES
   xml_data_extractor!
 
 BUNDLED WITH
-   2.1.4
+   2.2.6

data/README.md

@@ -300,6 +300,295 @@ schemas:
 }
 ```
 
+### link
+
+This command is useful when the XML contains references to other nodes, it works as a SQL JOIN. The path must be and expression containing the `<link>` identifier, which will be replaced by the value fetched from the `link:` command.
+
+Example:
+```yml
+schemas:
+  bookings:
+    array_of: booking
+    date: booking_date
+    document: id
+    products:
+      array_of:
+      accomodation:
+        path: ../hotel[booking_id=<link>]/accomodation
+        link: id
+```
+```xml
+<xml>
+  <booking>
+    <id>1</id>
+    <booking_date>2020-01-01</booking_date>
+  </booking>
+  <booking>
+    <id>2</id>
+    <booking_date>2020-01-02</booking_date>
+  </booking>
+  <hotel>
+    <booking_id>1</booking_id>
+    <accomodation>Standard</accomodation>
+  </hotel>
+  <hotel>
+    <booking_id>2</booking_id>
+    <accomodation>Premium</accomodation>
+  </hotel>
+</xml>
+```
+```ruby
+{
+  bookings: [
+    {
+      date: "2020-01-01",
+      document: "1"
+      products: [
+        { accomodation: "Standard" }
+      ]
+    },
+    {
+      date: "2020-01-02",
+      document: "2"
+      products: [
+        { accomodation: "Premium" }
+      ]
+    }
+  ]
+}
+```
+
+In this example if I didn't use the `link` to get only the hotel of each booking, it would have returned two accomodations for each booking and instead of extract a string with the accomodation it would extract an array with all the accomodations for each booking.
+
+You can combine the `link` with `array_of` if you want search for a list of elements filtering by some field, just provide the `path` and the `link`:
+
+```yml
+schemas:
+  bookings:
+    array_of: booking
+    date: date
+    document: id
+    products:
+      array_of:
+        path: ../products[booking_id=<link>]
+        link: id
+      ....
+```
+
+### uniq_by
+
+Can only be used with **array_of**.
+
+This functionality is useful when some XML nodes are duplicated and you want to extract data from the first occurrence only. It has a behavior similar to Ruby **uniq** method on arrays.
+For each path generated from `array_of`, the value fetched using `uniq_by` will be checked against the generated collection and the path will be discarded if the value already exists.
+
+```yml
+schemas:
+  bookings:
+    array_of:
+      path: booking
+      uniq_by: id
+    date: bdate
+    document: id
+```
+```xml
+<xml>
+  <booking>
+    <id>1</id>
+    <bdate>2020-01-01</bdate>
+  </booking>
+  <booking>
+    <id>1</id>
+    <bdate>2020-01-01</bdate>
+  </booking>
+</xml>
+```
+```ruby
+{
+  bookings: [
+    {
+      date: "2020-01-01",
+      document: "1"
+    }
+  ]
+}
+```
+
+In this example if we don't use the tag `uniq_by` there would be extracted two elements with the same data, like:
+
+```ruby
+{
+  bookings: [
+    {
+      date: "2020-01-01",
+      document: "1"
+    },
+    {
+      date: "2020-01-01",
+      document: "1"
+    }
+  ]
+}
+```
+
+### array_presence: first_only
+
+The field that contains this property will be only added to the first item of the array.
+
+Can only be used in fields that belong to a node of `array_of`.
+
+```yml
+passengers:
+  array_of: bookings/booking/passengers/passenger
+  id:
+    path: document
+    modifier: to_s
+  name:
+    attr: [FirstName, LastName]
+    modifier:
+      - name: join
+        params: [" "]
+  rav_tax:
+    array_presence: first_only
+    path: ../rav
+    modifier: to_f
+```
+```xml
+<bookings>
+  <booking>
+    <rav>150<rav>
+    <passengers>
+      <passenger>
+        <document>109.111.019-79</document>
+        <FirstName>Marcelo</FirstName>
+        <LastName>Lauxen</LastName>
+      </passenger>
+      <passenger>
+        <document>110.155.019-78</document>
+        <FirstName>Corona</FirstName>
+        <LastName>Virus</LastName>
+      </passenger>
+    </passengers>
+  </booking>
+</bookings>
+```
+```ruby
+{
+  bookings: [
+    {
+      passengers: [
+        { 
+          id: "109.111.019-79",
+          name: "Marcelo Lauxen",
+          tax_rav: 150.00 
+        },
+        { 
+          id: "110.155.019-78",
+          name: "Corona Virus"
+        }
+      ]
+    }
+  ]
+}
+```
+
+In this example the field `tax_rav` was only included on the first passenger because this field has the `array_presence: first_only` property.
+
+### in_parent
+
+This option allows you to navigate to a parent node of the current node.
+
+```yml
+passengers:
+  array_of: bookings/booking/passengers/passenger
+  id:
+    path: document
+    modifier: to_s
+  bookings_id:
+    in_parent: bookings
+    path: id
+```
+```xml
+<bookings>
+  <bookings_id>8888</bookings_id>
+  <booking>
+    <passengers>
+      <passenger>
+        <document>109.111.019-79</document>
+      </passenger>
+      <passenger>
+        <document>110.155.019-78</document>
+      </passenger>
+    </passengers>
+  </booking>
+</bookings>
+```
+```ruby
+{
+  bookings: [
+    {
+      passengers: [
+        { 
+          id: "109.111.019-79",
+          bookings_id: 8888
+        },
+        { 
+          id: "110.155.019-78",
+          bookings_id: 8888
+        }
+      ]
+    }
+  ]
+}
+```
+
+In this example the value of `bookings_id` will be extracted starting at the node provided in `in_parent` instead of the current node. It's possible to navigate to a parent node with `../` too (xpath provides this functionality), but using `in_parent` you just need to provide the name of the parent node, it will navigate up until the parent node is found, no matter how many levels.
+
+### keep_if
+
+This option allows you to keep the part of the block of the hash in the final result only if the condition matches.
+
+```yml
+schemas:
+  dummy:
+    within: data
+    description: additional_desc
+    exchange: currency_info/value
+    price: price
+    payment:
+      type: payment_info/method
+      value: payment_info/price
+      keep_if: "'type' == 'invoice'"
+```
+```xml
+<data>
+  <additional_desc>Keep walking</additional_desc>
+  <currency_info kind="USD">
+    <value>4.15</value>
+  </currency_info>
+  <price>55.09</price>
+  <payment_info>
+    <method>card</method>
+    <price>55.48</price>
+    <payment>
+      <installments>2</installments>
+      <card_number>333</card_number>
+    </payment>
+  </payment>
+<data>
+```
+```ruby
+{
+  dummy: {
+    description: "Keep walking",
+    exchange: "4.15",
+    price: "55.09"
+  }
+}
+```
+
+In this example the condition didn't match since the payment method was `card` instead of `invoice` and then the extracted payment hash was removed from the final result.
+
 ### Formatting:
 
 #### fixed
@@ -379,7 +668,7 @@ schemas:
     path: [firstname, lastname]
     modifier: 
       - name: join
-        params: [" "]    
+        params: [" "]
       - downcase      
 ```
 ```xml

data/lib/src/extract/array_of.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module Extract
   class ArrayOf < Base
     def initialize(node, extractor, index = 0)

data/lib/src/extract/array_value.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module Extract
   class ArrayValue < Base
     def value

data/lib/src/extract/base.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module Extract
   class Base
     def initialize(node, extractor)

data/lib/src/extract/expression.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module Extract
   class Expression
     def initialize(expression, hash)

data/lib/src/extract/hash_builder.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module Extract
   class HashBuilder < Base
     INTERNAL_FIELDS = %i[array_of keep_if within unescape].freeze

data/lib/src/extract/string_value.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module Extract
   class StringValue < Base
     def value

data/lib/src/extract/unescape.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module Extract
   class Unescape < Base
     def unescape!

data/lib/src/extract/value_builder.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require_relative "base"
 require_relative "array_value"
 require_relative "array_of"
@@ -25,7 +27,7 @@ module Extract
 
     def value_for_hash
       props = node.props
-      
+
       Unescape.new(node, extractor).unescape! if props[:unescape]
 
       fixed_value = props[:fixed]

data/lib/src/extract/within.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module Extract
   class Within < Base
     def value

data/lib/src/extractor.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "cgi"
 require "active_support/core_ext/string"
 require_relative "format/formatter"
@@ -37,7 +39,7 @@ class PathBuilder < Struct.new(:base, :parent, :tag, keyword_init: true)
   end
 
   def matching_tags?(item, tag)
-    item.gsub(/\[\d\]/, "") == tag
+    item.gsub(/\[\d+\]/, "") == tag
   end
 end
 

data/lib/src/format/formatter.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require_relative "mapper"
 require_relative "modifier"
 

data/lib/src/format/mapper.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module Format
   class Mapper
     def initialize(yml)

data/lib/src/format/modifier.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module Format
   class Modifier
     def initialize(yml, helper)

data/lib/src/node.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 class Node < Struct.new(:props, :path)
   def initialize(*)
     super

data/xml_data_extractor.gemspec

@@ -1,13 +1,13 @@
 Gem::Specification.new do |spec|
   spec.name          = "xml_data_extractor"
-  spec.version       = "0.5.0"
+  spec.version       = "0.6.0"
   spec.authors       = ["Fernando Almeida"]
   spec.email         = ["fernandoprsbr@gmail.com"]
 
   spec.summary       = "Provides a simples DSL for extracting data from XML documents"
   spec.homepage      = "https://github.com/monde-sistemas/xml_data_extractor"
   spec.license       = "MIT"
-  spec.required_ruby_version = Gem::Requirement.new(">= 2.3.0")
+  spec.required_ruby_version = Gem::Requirement.new(">= 2.5")
 
   spec.metadata["homepage_uri"] = spec.homepage
   spec.metadata["source_code_uri"] = spec.homepage

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: xml_data_extractor
 version: !ruby/object:Gem::Version
-  version: 0.5.0
+  version: 0.6.0
 platform: ruby
 authors:
 - Fernando Almeida
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2021-03-12 00:00:00.000000000 Z
+date: 2022-04-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -73,13 +73,13 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- ".editorconfig"
 - ".github/dependabot.yml"
 - ".github/workflows/ci.yml"
 - ".gitignore"
 - ".kodiak.toml"
 - ".rspec"
 - ".ruby-version"
-- ".travis.yml"
 - Gemfile
 - Gemfile.lock
 - LICENSE.txt
@@ -119,14 +119,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 2.3.0
+      version: '2.5'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.3
+rubygems_version: 3.2.25
 signing_key: 
 specification_version: 4
 summary: Provides a simples DSL for extracting data from XML documents

data/.travis.yml

@@ -1,6 +0,0 @@
----
-language: ruby
-cache: bundler
-rvm:
-  - 2.6.6
-before_install: gem install bundler -v 2.1.4