linsc 0.0.5 → 0.0.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 6592e6700dca1d71ba381695184a01b2893dd35a
-  data.tar.gz: 229bb6f3900be5049e472400c75c6d447e62b0ed
+  metadata.gz: 2a7c54e13a9f1ade26f5330d410af6e23d6fcb72
+  data.tar.gz: b5f5b89e4169506b415f8a3fceeaff678a0615ca
 SHA512:
-  metadata.gz: 50f58ae940d139005e6ba95aad136a9bb263c0df45a07db492500c3c6153a2942d8c735ade047648df7ed46bf45f7fadbdc1a125d7fcd279270346f98791d784
-  data.tar.gz: 279f1cfe337987b1e348a8a2beb7240a82dc2253123284f9244aa1b4081c2d4b69f12e7ec857f8134155250654439ddc2c1ec276be8d011912d061b59f24b568
+  metadata.gz: e79102d02acfcec2064b49611aa352b193d89bb90b93ff126995ea0e5a5e5584da6d3624208ce7bafcd223f82ea6c5baed1964d2cd1fa204dfdee0e326e19015
+  data.tar.gz: 48b1af2a42a580a5ad495abe53dd6f550057c7280c6942bde0126fe6226d792dbdcba62016054f9bfdbf2639e0bf57086a478f67a04fa2dec2d3a16a5f0aa7a7

data/lib/linsc/cross_ref.rb

@@ -42,20 +42,20 @@ class CrossRef
       b = y[@master_lookup_field]
       a && b ? a <=> b : a ? -1 : 1
     end
-    master_lookup_values = master_data.collect {|row| row[@master_lookup_field]&.downcase}
+    master_lookup_values = master_data.collect {|row| row[@master_lookup_field] && row[@master_lookup_field].downcase}
     i = 0
     CSV.foreach(@child_path, headers: true, encoding: 'utf-8') do |child_row|
       i += 1
       puts "email lookup - row: #{i}/#{@child_length}"
-      child_lookup_value = child_row[@child_lookup_field]&.downcase
-      if child_lookup_value&.include?('@') || !@email_key ## generalize this
+      child_lookup_value = child_row[@child_lookup_field].downcase if child_row[@child_lookup_field]
+      if (child_lookup_value && child_lookup_value.include?('@')) || !@email_key ## generalize this
         match_index = master_lookup_values.bsearch_index do |master_lookup_value|
            child_lookup_value && master_lookup_value ?
                 child_lookup_value <=> master_lookup_value : child_lookup_value ? -1 : 1
         end
         if !match_index
           match_index = master_data.find_index do |master_row|
-            master_secondary_lookups = @master_secondary_lookups.collect{|x| x&.downcase}
+            master_secondary_lookups = @master_secondary_lookups.collect{|x| x && x.downcase}
             master_secondary_lookups.include?(child_lookup_value)
           end
         end
@@ -94,7 +94,7 @@ class CrossRef
     end
     master_row_new = CSV::Row.new(@headers, [])
     master_row.each do |key, value|
-      master_row_new[key] = value&.encode('utf-8', invalid: :replace, undef: :replace, replace: '#')
+      master_row_new[key] = value.encode('utf-8', invalid: :replace, undef: :replace, replace: '#') if value
     end
     master_row_new
   end

data/lib/linsc/csv_handlers.rb

@@ -3,7 +3,7 @@ module CSVHandlers
     values = []
     headers.each do |header|
       if encoding
-        values << row[header]&.encode(encoding)
+        values << row[header].encode(encoding) if row[header]
       else
         values << row[header]
       end
@@ -33,7 +33,7 @@ module CSVHandlers
     unless File.exist?(f)
       FileUtils.touch(f)
       csv = CSV.open(f, "w+")
-      csv << @headers.collect {|x| x&.encode('utf-8')}
+      csv << @headers.collect {|x| x && x.encode('utf-8')}
       csv.close
     end
   end
@@ -42,7 +42,7 @@ module CSVHandlers
     unless File.exist?(f)
       FileUtils.touch(f)
       csv = CSV.open(f, "w+")
-      csv << headers.collect {|x| x&.encode('utf-8')}
+      csv << headers.collect {|x| x && x.encode('utf-8')}
       csv.close
     end
   end

data/lib/linsc/duck.rb

@@ -42,7 +42,11 @@ class DuckScraper
     CSV.foreach(@input_file, headers: true) do |input_row|
       count += 1
       next if @start && @start >= count
-      tries = @proxies&.length || 3
+      if @proxies
+        tries = @proxies.length
+      else
+        tries = 3
+      end
       puts "ddg #{count}/#{@input_length}"
       begin
         unless sufficient_data?(input_row)

data/lib/linsc/merger.rb

@@ -29,7 +29,7 @@ class Merger
       clean_file = File.read(lin_file, encoding: 'windows-1252').strip
       CSV.parse(clean_file, headers: true, encoding: 'windows-1252') do |row|
         row["Recruiter"] = recruiter_name
-        email = row['E-mail Address']&.downcase
+        email = row['E-mail Address'].downcase if row['E-mail Address']
         if emails.has_key?(email)
           emails[email] << row
         else
@@ -56,10 +56,10 @@ class Merger
         output_row = CSV::Row.new(@headers, [])
         correct_row.each do |key, value|
           if @mapping[key]
-            output_row[@mapping[key]] = value&.encode('utf-8')
+            output_row[@mapping[key]] = value.encode('utf-8') if value
           end
         end
-        output_row['Email'] = output_row['Email']&.downcase
+        output_row['Email'] = output_row['Email'].downcase if output_row['Email']
       else
         output_row = create_row(correct_row, @headers, 'utf-8')
       end

data/lib/linsc/parsers.rb

@@ -1,7 +1,7 @@
 module Parsers
   def scrape_contact(input_row, page, mode)
     row = CSV::Row.new(@headers, [])
-    name = page.at_css("#name")&.text&.split
+    name = page.at_css("#name").text.split
     contact_id = input_row["Contact ID"]
     lin_id = input_row["LIN ID"]
     cv_tr = input_row["CV TR"]
@@ -11,53 +11,53 @@ module Parsers
     lin_profile = input_row["Linkedin Profile"]
     cand_id = input_row["Candidate ID"]
     cand_source = input_row["LIN 1st Degree"]
-    title = page.at_css(".headline.title")&.text
-    country = page.at_css("#demographics .locality")&.text
-    sector = page.at_css("#demographics .descriptor:not(.adr)")&.text
+    title = page.at_css(".headline.title").text
+    country = page.at_css("#demographics .locality").text
+    sector = page.at_css("#demographics .descriptor:not(.adr)").text
 
     positions = page.css("#experience .positions .position")
     if positions
-      e1_title = positions[0]&.at_css(".item-title")&.text
-      e1_org = positions[0]&.at_css(".item-subtitle")&.text
-      e1_start = positions[0]&.css(".date-range time")[0]&.text
-      e1_end = positions[0]&.css(".date-range time")[1]&.text
-      e1_loc = positions[0]&.at_css(".location")&.text
-      e1_desc = positions[0]&.at_css(".description")&.text
-      e2_title = positions[1]&.at_css(".item-title")&.text
-      e2_org = positions[1]&.at_css(".item-subtitle")&.text
-      e2_start = positions[1]&.css(".date-range time")[0]&.text
-      e2_end = positions[1]&.css(".date-range time")[1]&.text
-      e2_loc = positions[1]&.at_css(".location")&.text
-      e2_desc = positions[1]&.at_css(".description")&.text
-      e3_title = positions[2]&.at_css(".item-title")&.text
-      e3_org = positions[2]&.at_css(".item-subtitle")&.text
-      e3_start = positions[2]&.css(".date-range time")[0]&.text
-      e3_end = positions[2]&.css(".date-range time")[1]&.text
-      e3_loc = positions[2]&.at_css(".location")&.text
-      e3_desc = positions[2]&.at_css(".description")&.text
+      e1_title = positions[0].at_css(".item-title").text
+      e1_org = positions[0].at_css(".item-subtitle").text
+      e1_start = positions[0].css(".date-range time")[0].text
+      e1_end = positions[0].css(".date-range time")[1].text
+      e1_loc = positions[0].at_css(".location").text
+      e1_desc = positions[0].at_css(".description").text
+      e2_title = positions[1].at_css(".item-title").text
+      e2_org = positions[1].at_css(".item-subtitle").text
+      e2_start = positions[1].css(".date-range time")[0].text
+      e2_end = positions[1].css(".date-range time")[1].text
+      e2_loc = positions[1].at_css(".location").text
+      e2_desc = positions[1].at_css(".description").text
+      e3_title = positions[2].at_css(".item-title").text
+      e3_org = positions[2].at_css(".item-subtitle").text
+      e3_start = positions[2].css(".date-range time")[0].text
+      e3_end = positions[2].css(".date-range time")[1].text
+      e3_loc = positions[2].at_css(".location").text
+      e3_desc = positions[2].at_css(".description").text
     end
 
     certs = page.css(".certifications .certification")
     if certs
-      c1_name = certs[0]&.at_css(".item-title")&.text
-      c2_name = certs[1]&.at_css(".item-title")&.text
-      c_type  = certs[0]&.at_css(".item-subtitle")&.text
+      c1_name = certs[0].at_css(".item-title").text
+      c2_name = certs[1].at_css(".item-title").text
+      c_type  = certs[0].at_css(".item-subtitle").text
     end
 
     schools = page.css("#education .schools .school")
     if schools
-      s1_name = schools[0]&.at_css(".item-title")&.text
-      s2_name = schools[1]&.at_css(".item-title")&.text
-      s1_start = schools[0]&.css(".date-range time")[0]&.text
-      s2_start = schools[1]&.css(".date-range time")[0]&.text
-      s1_end = schools[0]&.css(".date-range time")[1]&.text
-      s2_end = schools[1]&.css(".date-range time")[1]&.text
-      s1_degree = schools[0]&.at_css(".item-subtitle")&.text
-      s2_degree = schools[1]&.at_css(".item-subtitle")&.text
+      s1_name = schools[0].at_css(".item-title").text
+      s2_name = schools[1].at_css(".item-title").text
+      s1_start = schools[0].css(".date-range time")[0].text
+      s2_start = schools[1].css(".date-range time")[0].text
+      s1_end = schools[0].css(".date-range time")[1].text
+      s2_end = schools[1].css(".date-range time")[1].text
+      s1_degree = schools[0].at_css(".item-subtitle").text
+      s2_degree = schools[1].at_css(".item-subtitle").text
     end
 
     summary = page.at_css("#summary .description")
-    summary&.css('br').each{|br| br.replace "\n"} if summary
+    summary.css('br').each{|br| br.replace "\n"} if summary
 
     text_resume = "\n\n***IMPORTED FROM LINKEDIN***\n#{lin_profile}\n\n"
     text_resume += name.join(" ")
@@ -105,7 +105,7 @@ module Parsers
     text_resume += "\nINTERESTS\n" if interests && interests.length > 0
     ints = []
     interests.each do |interest|
-      int = interest.at_css(".wrap")&.text
+      int = interest.at_css(".wrap").text
       if int
         ints << int unless (int == "See less") || (int.match(/See \d+\+/))
       end
@@ -115,7 +115,7 @@ module Parsers
     text_resume += "\n\nSKILLS\n" if skills && skills.length > 0
     sks = []
     skills.each do |skill|
-      sk = skill.at_css(".wrap")&.text
+      sk = skill.at_css(".wrap").text
       if sk
         sks << sk unless (sk == "See less") || (sk.match(/See \d+\+/))
       end
@@ -125,7 +125,7 @@ module Parsers
     text_resume += "\n\nLANGUAGES\n" if languages.length > 0
     langs = []
     languages.each do |language|
-      lang = language.at_css(".name")&.text
+      lang = language.at_css(".name").text
       prof = language.at_css(".proficiency")
       lang += " (#{prof.text})" if prof && prof.text.length > 0
       langs << lang if lang
@@ -230,43 +230,43 @@ module Parsers
     row["CV TR"] = "1"
     row["Account Name"] = acc_name
     row["Linkedin Import Status"] = import_status
-    row["First Name"] = name[0]&.slice(0, 39)
-    row["Last Name"] = name[1..-1]&.join(" ")&.slice(0, 79)
+    row["First Name"] = name[0].slice(0, 39)
+    row["Last Name"] = name[1..-1].join(" ").slice(0, 79)
     row["Email"] = email
     row["Candidate ID"] = cand_id
     row["LIN 1st Degree"] = cand_source
-    row["Title"] = title&.slice(0, 127)
+    row["Title"] = title.slice(0, 127)
     row["Contact Country"] = country
-    row["Contact LIN Sector"] = sector&.slice(0, 99)
-    row["Employer 1 Title"] = e1_title&.slice(0, 31999)
-    row["Employer Organization Name 1"] = e1_org&.slice(0, 254)
+    row["Contact LIN Sector"] = sector.slice(0, 99)
+    row["Employer 1 Title"] = e1_title.slice(0, 31999)
+    row["Employer Organization Name 1"] = e1_org.slice(0, 254)
     row["Employer 1 Start Date"] = format_date(e1_start) #format
     row["Employer 1 End Date"] = format_date(e1_end) #format
-    row["Employer 1 Location"] = e1_loc&.slice(0, 254)
-    row["Employer 1 Description"] = e1_desc&.slice(0, 31999)
-    row["Employer 2 Title"] = e2_title&.slice(0, 31999)
-    row["Employer Organization Name 2"] = e2_org&.slice(0, 254)
+    row["Employer 1 Location"] = e1_loc.slice(0, 254)
+    row["Employer 1 Description"] = e1_desc.slice(0, 31999)
+    row["Employer 2 Title"] = e2_title.slice(0, 31999)
+    row["Employer Organization Name 2"] = e2_org.slice(0, 254)
     row["Employer 2 Start Date"] = format_date(e2_start) #format
     row["Employer 2 End Date"] = format_date(e2_end) #format
-    row["Employer 2 Location"] = e2_loc&.slice(0, 254)
-    row["Employer 2 Description"] = e2_desc&.slice(0, 31999)
-    row["Employer 3 Title"] = e3_title&.slice(0, 31999)
-    row["Employer Organization Name 3"] = e3_org&.slice(0, 254)
+    row["Employer 2 Location"] = e2_loc.slice(0, 254)
+    row["Employer 2 Description"] = e2_desc.slice(0, 31999)
+    row["Employer 3 Title"] = e3_title.slice(0, 31999)
+    row["Employer Organization Name 3"] = e3_org.slice(0, 254)
     row["Employer 3 Start Date"] = format_date(e3_start) #format
     row["Employer 3 End Date"] = format_date(e3_end) #format
-    row["Employer 3 Location"] = e3_loc&.slice(0, 254)
-    row["Employer 3 Description"] = e3_desc&.slice(0, 31999)
-    row["License or Certification Name 1"] = c1_name&.slice(0, 254)
-    row["License or Certification Name 2"] = c2_name&.slice(0, 254)
-    row["License or Certification Credential Type"] = c_type&.slice(0, 254)
-    row["Education School 1"] = s1_name&.slice(0, 124)
-    row["Education Degree Name 1"] = s1_degree&.slice(0, 254)
+    row["Employer 3 Location"] = e3_loc.slice(0, 254)
+    row["Employer 3 Description"] = e3_desc.slice(0, 31999)
+    row["License or Certification Name 1"] = c1_name.slice(0, 254)
+    row["License or Certification Name 2"] = c2_name.slice(0, 254)
+    row["License or Certification Credential Type"] = c_type.slice(0, 254)
+    row["Education School 1"] = s1_name.slice(0, 124)
+    row["Education Degree Name 1"] = s1_degree.slice(0, 254)
     row["Education Degree Date 1"] = format_date(s1_end)
-    row["Education School 2"] = s2_name&.slice(0, 124)
-    row["Education Degree Name 2"] = s2_degree&.slice(0, 254)
+    row["Education School 2"] = s2_name.slice(0, 124)
+    row["Education Degree Name 2"] = s2_degree.slice(0, 254)
     row["Education Degree Date 2"] = format_date(s2_end)
-    row["Text Resume"] = text_resume&.slice(0, 31999)
-    row["LinkedIn Profile"] = lin_profile&.slice(0, 254)
+    row["Text Resume"] = text_resume.slice(0, 31999)
+    row["LinkedIn Profile"] = lin_profile.slice(0, 254)
     row["Resume Last Updated"] = Time.now.strftime('%Y-%m-%d %H:%M:%S')
     row["LIN Import Date"] = Time.now.strftime('%Y-%m-%d')
     row["CV Uploaded"] = "1"
@@ -281,7 +281,7 @@ module Parsers
 
     schools.each do |school|
       row = CSV::Row.new(@education_headers, [])
-      row["Contact"] = input_row["Contact ID"]
+      row["Contact ID"] = input_row["Contact ID"]
       row["LIN ID"] = input_row["LIN ID"]
       row["School Name"] = school.at_css(".item-title").text.slice(0, 149)
       row["Major"] = school.at_css(".item-subtitle").text.slice(0, 254)
@@ -303,7 +303,7 @@ module Parsers
 
     positions.each do |position|
       row = CSV::Row.new(@employment_headers, [])
-      row["Contact"] = input_row["Contact ID"]
+      row["Contact ID"] = input_row["Contact ID"]
       row["LIN ID"] = input_row["LIN ID"]
       row["Job Title"] = position.at_css(".item-title").text.slice(0, 74)
       row["Employer Name"] = position.at_css(".item-subtitle").text.slice(0, 149)

data/lib/linsc.rb

@@ -135,7 +135,7 @@ class Linsc
       else
         @options[:insert] = false
       end
-      if ids.any?{|id| id && id&.length > 0}
+      if ids.any?{|id| id && id.length > 0}
         @options[:update] = true
       else
         @options[:update] = false

data/linsc.gemspec

@@ -4,7 +4,7 @@ $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
 
 Gem::Specification.new do |spec|
   spec.name          = "linsc"
-  spec.version       = "0.0.5"
+  spec.version       = "0.0.6"
   spec.authors       = ["Dan Molloy"]
   spec.email         = ["danieljmolloy1@gmail.com"]
   spec.date = '2016-03-31'

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: linsc
 version: !ruby/object:Gem::Version
-  version: 0.0.5
+  version: 0.0.6
 platform: ruby
 authors:
 - Dan Molloy