employ_me 0.0.9 → 0.0.10

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 02c911e5f836e7642e080b1d4cb5dea8483c6b05bf264f8b058360b630e3373b
-  data.tar.gz: eaee80fb48587798dde888d452a211641c38cd9dabb55da7764b472cc00e3639
+  metadata.gz: f276d820ba553a0fc83946daa695d492b3fd38526d8b284d42969a089c91cff3
+  data.tar.gz: 0d3feec149da139bd74b9cf1162806ca9615db06bab8a1c61a1c345b00b46504
 SHA512:
-  metadata.gz: b72c8b61b1e6a24a35eb5679772e374df9490a68445f436ad39f809e4d1fff16bbc9f00d4775194c35df0bfad3832d1a098ad762730f983fd0bebc3b4212e3b7
-  data.tar.gz: 42647cc8005642ee2d9bb05585afac543bb65dda0ab8977b28895211b14f9e3775b3734334a7089c6b636fac02211a19d529f5b58e5a104fd9b44d20d7882b71
+  metadata.gz: ca8fda64fbd28af29ab2ce1c0a3ec9b7b4d7871d5f6f092ca4689ffe862eb72489709f4b2034985e07ca2dcddf76e7597d6c6c972fb015a8b55ad133d0c76cf6
+  data.tar.gz: eed7d599ff2aca71ae428141d5b6820d27f353d5ee3aa7b66ea6f6faffbbc79fd9b9ff5e4c9b36087dcfe32b1d067114358f552b9773627b7ef685f9b602b805

data/lib/employ_me/parser/location/strategies/pattern_match.rb

@@ -25,6 +25,9 @@ module EmployMe
                 regex = Regexp.new('San Francisco, CA', Regexp::IGNORECASE)
                 return ['CA', 'San Francisco', 'CA'] if regex.match(curr_node_text)
 
+                regex = Regexp.new('San Francisco', Regexp::IGNORECASE)
+                return ['CA', 'San Francisco', 'CA'] if regex.match(curr_node_text)
+
                 # San Mateo, CA Jobs
                 regex = Regexp.new('San Mateo, CA', Regexp::IGNORECASE)
                 return ['CA', 'San Mateo', 'CA'] if regex.match(curr_node_text)

data/lib/employ_me/parser/salary/strategies/pattern_match.rb

@@ -68,6 +68,17 @@ module EmployMe
 
                   return [low, high]
                 end
+
+                # Salary Format: $100,000 and up to $200,000
+                regex = Regexp.new('\\$([0-9]+),[0-9]+ and up to \\$([0-9]+),[0-9]+', Regexp::IGNORECASE)
+                result = regex.match(curr_node_text)
+
+                if result
+                  low = result[1].to_i * 1000
+                  high = result[2].to_i * 1000
+
+                  return [low, high]
+                end
               end
 
               tree.concat(curr_node.children)

data/lib/employ_me/parser/technologies/strategies/pattern_match.rb

@@ -0,0 +1,148 @@
+module EmployMe
+  module Parser
+    module Technologies
+      module Strategies
+        class PatternMatch
+          # Return Set of technologies
+          def self.perform(root_node)
+            technologies = Set.new
+
+            tree = [root_node]
+
+            # Depth First Search
+            while tree.size > 0
+              curr_node = tree.shift
+
+              if curr_node.children.all? { |child| child.name == "comment" || child.name == 'text' }
+                curr_node_text = curr_node.text
+
+                # .NET
+                regex = Regexp.new('\\.NET', Regexp::IGNORECASE)
+                technologies.add(:dotnet) if regex.match(curr_node_text)
+
+                # Airflow
+                regex = Regexp.new('Airflow', Regexp::IGNORECASE)
+                technologies.add(:airflow) if regex.match(curr_node_text)
+
+                # Android
+                regex = Regexp.new('Android', Regexp::IGNORECASE)
+                technologies.add(:android) if regex.match(curr_node_text)
+
+                # AWS
+                regex = Regexp.new('AWS', Regexp::IGNORECASE)
+                technologies.add(:aws) if regex.match(curr_node_text)
+
+                # CSS
+                # regex = Regexp.new('CSS', Regexp::IGNORECASE)
+                # technologies.add(:css) if regex.match(curr_node_text)
+
+                # Docker
+                regex = Regexp.new('Docker', Regexp::IGNORECASE)
+                technologies.add(:docker) if regex.match(curr_node_text)
+
+                # Flink
+                regex = Regexp.new('Flink', Regexp::IGNORECASE)
+                technologies.add(:flink) if regex.match(curr_node_text)
+
+                # Firestore
+                regex = Regexp.new('Firestore', Regexp::IGNORECASE)
+                technologies.add(:firestore) if regex.match(curr_node_text)
+
+                # GCP
+                regex = Regexp.new('GCP', Regexp::IGNORECASE)
+                technologies.add(:gcp) if regex.match(curr_node_text)
+
+                # Helm
+                regex = Regexp.new('Helm', Regexp::IGNORECASE)
+                technologies.add(:helm) if regex.match(curr_node_text)
+
+                # HTML
+                # regex = Regexp.new('HTML', Regexp::IGNORECASE)
+                # technologies.add(:html) if regex.match(curr_node_text)
+
+                # iOS
+                regex = Regexp.new('iOS', Regexp::IGNORECASE)
+                technologies.add(:ios) if regex.match(curr_node_text)
+
+                # Istio
+                regex = Regexp.new('Istio', Regexp::IGNORECASE)
+                technologies.add(:istio) if regex.match(curr_node_text)
+
+                # Kafka
+                regex = Regexp.new('Kafka', Regexp::IGNORECASE)
+                technologies.add(:kafka) if regex.match(curr_node_text)
+
+                # Karpenter
+                regex = Regexp.new('Karpenter', Regexp::IGNORECASE)
+                technologies.add(:karpenter) if regex.match(curr_node_text)
+
+                # Kubeflow
+                regex = Regexp.new('Kubeflow', Regexp::IGNORECASE)
+                technologies.add(:kubeflow) if regex.match(curr_node_text)
+
+                # Kubernetes
+                regex = Regexp.new('Kubernetes', Regexp::IGNORECASE)
+                technologies.add(:kubernetes) if regex.match(curr_node_text)
+
+                # Linux
+                regex = Regexp.new('Linux', Regexp::IGNORECASE)
+                technologies.add(:linux) if regex.match(curr_node_text)
+
+                # Node
+                regex = Regexp.new('Node', Regexp::IGNORECASE)
+                technologies.add(:node) if regex.match(curr_node_text)
+
+                # PostgreSQL
+                regex = Regexp.new('Postgres', Regexp::IGNORECASE)
+                technologies.add(:postgresql) if regex.match(curr_node_text)
+
+                regex = Regexp.new('PostgreSQL', Regexp::IGNORECASE)
+                technologies.add(:postgresql) if regex.match(curr_node_text)
+
+                # Pulsar
+                regex = Regexp.new('Pulsar', Regexp::IGNORECASE)
+                technologies.add(:pulsar) if regex.match(curr_node_text)
+
+                # React
+                regex = Regexp.new('React', Regexp::IGNORECASE)
+                technologies.add(:react) if regex.match(curr_node_text)
+
+                # Redux
+                regex = Regexp.new('Redux', Regexp::IGNORECASE)
+                technologies.add(:redux) if regex.match(curr_node_text)
+
+                # Ruby on Rails
+                regex = Regexp.new('Ruby on Rails', Regexp::IGNORECASE)
+                technologies.add(:ruby_on_rails) if regex.match(curr_node_text)
+
+                # Snowflake
+                regex = Regexp.new('Snowflake', Regexp::IGNORECASE)
+                technologies.add(:snowflake) if regex.match(curr_node_text)
+
+                # Spark
+                regex = Regexp.new('Spark', Regexp::IGNORECASE)
+                technologies.add(:spark) if regex.match(curr_node_text)
+
+                # Tensorflow
+                regex = Regexp.new('Tensorflow', Regexp::IGNORECASE)
+                technologies.add(:tensorflow) if regex.match(curr_node_text)
+
+                # Terraform
+                regex = Regexp.new('Terraform', Regexp::IGNORECASE)
+                technologies.add(:terraform) if regex.match(curr_node_text)
+
+                # Typescript
+                regex = Regexp.new('Typescript', Regexp::IGNORECASE)
+                technologies.add(:typescript) if regex.match(curr_node_text)
+              end
+
+              tree.concat(curr_node.children)
+            end
+
+            technologies
+          end
+        end
+      end
+    end
+  end
+end

data/lib/employ_me.rb

@@ -1,4 +1,5 @@
 require 'employ_me/parser/location/strategies/pattern_match.rb'
 require 'employ_me/parser/programming_language/strategies/pattern_match.rb'
 require 'employ_me/parser/salary/strategies/pattern_match.rb'
+require 'employ_me/parser/technologies/strategies/pattern_match.rb'
 require 'employ_me/parser/title/strategies/pattern_match.rb'

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: employ_me
 version: !ruby/object:Gem::Version
-  version: 0.0.9
+  version: 0.0.10
 platform: ruby
 authors:
 - dgonzdev
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2025-11-07 00:00:00.000000000 Z
+date: 2025-11-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -34,6 +34,7 @@ files:
 - lib/employ_me/parser/location/strategies/pattern_match.rb
 - lib/employ_me/parser/programming_language/strategies/pattern_match.rb
 - lib/employ_me/parser/salary/strategies/pattern_match.rb
+- lib/employ_me/parser/technologies/strategies/pattern_match.rb
 - lib/employ_me/parser/title/strategies/pattern_match.rb
 homepage: https://github.com/dgonzdev/employ_me
 licenses: []