employ_me 0.0.4 → 0.0.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 4346c4379f4120da39b6e2e0998de13d941ed0aa475ef86b94c27fcb551a736e
-  data.tar.gz: 64a712333b97dbb6b782e443ad8ed64eb0cccaa2f1ccfc52900528194d20934c
+  metadata.gz: 1813eaad2894ab155c996fa0d4f367daff60858f2b9eecf63fd6d95b742ab4f4
+  data.tar.gz: a548d8c649421f6e56353ad9041c3745aec9c96d32b6b50c550aecff6a3754e6
 SHA512:
-  metadata.gz: a825a154b544a483a34dacd641161ee8a253394c94c0083575f55d8cb6c9161ba6353fe7380e5f500b18b07d135cc5a2d9988029b402e35f19ba72295ba0b663
-  data.tar.gz: 790b7854de9a3fbb3c643c16ab27eb7a07602f2e0499848967ef5a4fdf4f25ced68bcb5e1a7c1fc840c5b4baa032c672280db1a9ef8095556fbb74413bfe9a69
+  metadata.gz: 62d89c14f54be3eaab64d5431903b0a31512a347800b1c01245e3db4a0fb2755c8fbe5674acf5baa459c34a3e20f9c92ab76dd18c5d03eea9405337986ec981a
+  data.tar.gz: e87268900fc62ff2e5f29d7dc17e1b8c5a45fd9d45f56ef8b52807422c8c3679dbf20bda64d580d4b0204afa0a9526446c7dd5ae8dcfae4b2b5f1a4a6aab7b37

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

@@ -0,0 +1,76 @@
+module EmployMe
+  module Parser
+    module Location
+      module Strategies
+        class PatternMatch
+          # Return [state code, city name, state name]
+          def self.perform(root_node)
+            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
+
+                # Remote Jobs
+                regex = Regexp.new('US & Canada Remote', Regexp::IGNORECASE)
+                return ['REMOTE', nil, nil] if regex.match(curr_node_text)
+
+                # San Francisco, CA Jobs
+                regex = Regexp.new('San Francisco, CA', 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)
+
+                # Boca Raton, FL Jobs
+                regex = Regexp.new('Boca Raton, FL', Regexp::IGNORECASE)
+                return ['FL', 'Boca Raton', 'FL'] if regex.match(curr_node_text)
+
+                regex = Regexp.new('Boca Raton, Florida', Regexp::IGNORECASE)
+                return ['FL', 'Boca Raton', 'FL'] if regex.match(curr_node_text)
+
+                regex = Regexp.new('Boca Raton, Florida, United States', Regexp::IGNORECASE)
+                return ['FL', 'Boca Raton', 'FL'] if regex.match(curr_node_text)
+
+                # Raleigh, NC Jobs
+                regex = Regexp.new('Raleigh, NC', Regexp::IGNORECASE)
+                return ['NC', 'Raleigh', 'NC'] if regex.match(curr_node_text)
+
+                # New York, NY Jobs
+                regex = Regexp.new('New York, NY', Regexp::IGNORECASE)
+                return ['NY', 'New York', 'NY'] if regex.match(curr_node_text)
+
+                regex = Regexp.new('New York, New York', Regexp::IGNORECASE)
+                return ['NY', 'New York', 'NY'] if regex.match(curr_node_text)
+
+                regex = Regexp.new('New York, New York, United States', Regexp::IGNORECASE)
+                return ['NY', 'New York', 'NY'] if regex.match(curr_node_text)
+
+                regex = Regexp.new('New York Office', Regexp::IGNORECASE)
+                return ['NY', 'New York', 'NY'] if regex.match(curr_node_text)
+
+                # Seattle, WA Jobs
+                regex = Regexp.new('Seattle, WA', Regexp::IGNORECASE)
+                return ['WA', 'Seattle', 'WA'] if regex.match(curr_node_text)
+
+                regex = Regexp.new('Seattle, Washington', Regexp::IGNORECASE)
+                return ['WA', 'Seattle', 'WA'] if regex.match(curr_node_text)
+
+                regex = Regexp.new('Seattle, Washington, United States', Regexp::IGNORECASE)
+                return ['WA', 'Seattle', 'WA'] if regex.match(curr_node_text)
+              end
+
+              tree.concat(curr_node.children)
+            end
+
+            nil
+          end
+        end
+      end
+    end
+  end
+end

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

@@ -0,0 +1,71 @@
+module EmployMe
+  module Parser
+    module Salary
+      module Strategies
+        class PatternMatch
+          # Return [salary floor, salary ceiling]
+          def self.perform(root_node)
+            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
+
+                # Salary Format: $100K - $200K
+                regex = Regexp.new('\\$([0-9]+)K \S \\$([0-9]+)K', 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
+
+                # Salary Format: $100,000 - $200,000
+                regex = Regexp.new('\\$([0-9]+),[0-9]+ - \\$([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
+
+                # Salary Format: $100,000 to $200,000
+                regex = Regexp.new('\\$([0-9]+),[0-9]+ 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
+
+                # Salary Format: $100,000 - $200,000 USD
+                regex = Regexp.new('\\$([0-9]+),[0-9]+ - \\$([0-9]+),[0-9]+ USD', 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)
+            end
+
+            nil
+          end
+        end
+      end
+    end
+  end
+end

data/lib/employ_me.rb

@@ -1,2 +1,4 @@
+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/title/strategies/pattern_match.rb'

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: employ_me
 version: !ruby/object:Gem::Version
-  version: 0.0.4
+  version: 0.0.6
 platform: ruby
 authors:
 - dgonzdev
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2025-10-14 00:00:00.000000000 Z
+date: 2025-10-18 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -31,7 +31,9 @@ extensions: []
 extra_rdoc_files: []
 files:
 - lib/employ_me.rb
+- 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/title/strategies/pattern_match.rb
 homepage: https://rubygems.org/gems/employ_me
 licenses: []