resumr 0.0.1 → 0.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 278cfda8054f2ada90d9b2e7d2a91e423dd1395fb0c220581c623f40f18e3632
-  data.tar.gz: 1b9406e4e6147833e570150583759f9bb019ef3e5502c1c059bcfcf3e044cf16
+  metadata.gz: ec390ba5a36ac086457d9d3f011bcfb45faa65b72a37c887470472441ad691d2
+  data.tar.gz: f8e0f03baffef2ce9c05167af5b5eb13fecbc10d0bc4f0fe76d13130fa8d42b9
 SHA512:
-  metadata.gz: 83a55ed5e30ef1693ad80148a85c4ba67279e780ea73f73078441ffbe9c4d37f6fe1392fb6eadf4d3789756927538ccb0425e0caef9cf589c8ea38391b4ef817
-  data.tar.gz: f4714777ed28ab6a8eaf16338f40300488ab6de860dec721804d2e018837875b6bdda2dab217b5df65ade8312405751561d7b5c16a64315da7e58c581077ea26
+  metadata.gz: feaf08ef21f23f66133de45e342517cd8a0c4df01e3f72e4a6baa2572547505558e0edebe53284512c80eeee37cef876aa4ca2ca142f68500b2f7cdaa718687f
+  data.tar.gz: 26a6171bcca22eee7402d51ab088bb8118195445304e88ae27db3157a99af235883961d7c20b716c66ad3b9e886585f70bc498a2e562f378bc6f152a7e75f13a

data/lib/resumr.rb

@@ -1,9 +1,100 @@
+require 'pdf-reader'
+
 class Resumr
-    def self.parse(file)
-        require 'pdf-reader'
+    def self.new(file)
         reader = PDF::Reader.new(file)
         info = reader.info
         pages = reader.pages
-        return {info: info, pages: pages}
+
+        text = pages.map{|x| x.text}.reduce{|x,y| x << y}.gsub(/Page \w of \w/,"")
+        right, left = "", ""
+
+        text.each_line do |line|
+            if line.length <= 40 || line.include?("Top Skills") || line.include?("Contact")
+                left += line.strip + "\n"
+            else
+                left += line.slice(0,40).strip + "\n"
+                right += line.slice(40,line.length).strip + "\n"
+            end
+        end
+
+        linkedin_url_start_index = left.index("www.linkedin.com")
+        linkedin_url_end_index = left.index("(LinkedIn)")
+        
+        resume =  {
+            source: info[:Author],
+            time: Time.new(info[:CreationDate].gsub(/D:/,"")),
+            text: text,
+            left: left,
+            right: right,
+            pdf_reader: reader,
+            sections: subsection_title_list(left).merge!(subsection_title_list(right,true)),
+            linkedin_url: left[linkedin_url_start_index..linkedin_url_end_index-1].gsub("\n","").strip
+        }
+
+        name = resume[:sections][:beginning].lines[1].split("\n").first
+        resume.merge!({name: name})
+
+        return resume
+    end
+
+    def self.subsection_title_list(str, with_first_block_sepparate = false)
+        possible_titles = [
+            ["Top Skills", "Principais competências"],
+            ["Certifications"], 
+            ["Contact", "Contato", "Contatar"],
+            ["Experience","Experiência"],
+            ["Education", "Formação Acadêmica"],
+            ["Summary","Resumo"],
+            ["Languages"],
+            ["Publications"]
+        ]
+        indexes = {}
+        possible_titles.each do |tit|
+            new_keyvalue = {}
+            title = tit[0]
+            index = nil
+            tit.each do |synonym|
+                index = str.index(synonym) if index.nil?
+            end
+            if ! index.nil?
+                new_keyvalue.store(
+                    index,
+                    title.gsub(" ","_").downcase.to_sym
+                )
+                indexes.merge!(new_keyvalue)
+            end
+        end
+        
+        retorn = {}
+        sorted_indexes = indexes.keys.sort
+
+        if with_first_block_sepparate
+            first_block_index = sorted_indexes[0]
+
+            retorn.merge!(
+                {beginning: 
+                    str[0..(first_block_index-1)]
+                }
+            )
+
+        end
+
+        sorted_indexes.each.with_index do |current_block_index, k|
+            new_keyvalue = {}
+            next_block_index = 0
+            if k == (sorted_indexes.length - 1)
+                next_block_index = str.length
+            else
+                next_block_index = sorted_indexes[k+1]
+            end
+            new_keyvalue.store(
+                indexes[current_block_index],
+                str[current_block_index..next_block_index].lines[1..-1].join
+            )
+            retorn.merge!(new_keyvalue)
+        end 
+
+        return retorn
     end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: resumr
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.2
 platform: ruby
 authors:
 - Sal, the Developer
@@ -14,17 +14,31 @@ dependencies:
   name: pdf-reader
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 1.0.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 1.0.0
-description: A resume parsing gem
+- !ruby/object:Gem::Dependency
+  name: awesome_print
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.8'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.8'
+description: A resume parsing gem. Specifically for LinkedIn PDFs
 email: sal@salthedeveloper.com
 executables: []
 extensions: []