From 9a9886df9d54f155e7d90c9fd6667b67f72d3e9b Mon Sep 17 00:00:00 2001
From: Jeff Yates <jeff@z800.lab.doublehack.me>
Date: Sat, 21 Nov 2020 16:45:55 -0500
Subject: [PATCH] made pn option operate on each date section

---
 sorter.rb | 53 +++++++++++++++++++++++++++++++++++++++--------------
 1 file changed, 39 insertions(+), 14 deletions(-)

diff --git a/sorter.rb b/sorter.rb
index b642075..b86f4e6 100755
--- a/sorter.rb
+++ b/sorter.rb
@@ -123,27 +123,52 @@ end
 #
 #This method is the meat and potatos. Preforms the text stripping, word counting, and creates output files.
 def process_file (file_name, binfile, type)
+  #text = split_text(text, 'Narrative:', 'Signatures:') if type == 'pn'
   csv = CSV.read(binfile)
   text = File.read(file_name)
-  text = strip_text(text, 'PLOVEINTAKE', 'PLOVECLOSING') if type == 'iat'
-  text = split_text(text, 'Narrative:', 'Signatures:') if type == 'pn'
-  output = Hash.new #Creating the output storage object
   bins = Hash.new #This hash stores the bins
+  csv.each { |bin| bins[bin[0]] = bin[1..].compact } #turn the csv array into a hash, remove nils
   outfile = file_name
   outfile.slice!('.txt')
+  if type == 'iat'
+    text = strip_text(text, 'PLOVEINTAKE', 'PLOVECLOSING') if type == 'iat'
+    output = Hash.new #Creating the output storage object
   #puts outfile
-  output[:filename] = outfile
-  output[:total_words] = text.split.size
-  puts output
-  csv.each { |bin| bins[bin[0]] = bin[1..].compact } #turn the csv array into a hash, remove nils
-  bins.each_key do |bin_number|
-    key = bin_number.to_sym
-    output[key] = Hash.new
-    output[key][:words] = bin_counter(bins[bin_number], text)
-    output[key][:total] = count_total(output[key])
+    output[:filename] = outfile
+    output[:total_words] = text.split.size
+    bins.each_key do |bin_number|
+      key = bin_number.to_sym
+      output[key] = Hash.new
+      output[key][:words] = bin_counter(bins[bin_number], text)
+      output[key][:total] = count_total(output[key])
+    end
+    write_output_json(output,outfile + '-out.json')
+    write_output_csv(output,outfile + '-out.csv')
+  elsif type == 'pn'
+    puts 'pn'
+    sections = text.lines("Date and time:", chomp: true) #sections is an arrary of each date section from the text
+    sections.delete_at(0) #we can ignore the first chunk of text
+    sections.each do |chunk|
+      timestamp = chunk.lines.delete_if {|line| line == "\r\n"}[0] #pulling out the timestamp
+      timestamp.tr!('/','').tr!(':','').tr!(' ','_') #remove slashes and colons from timestamp, replaces spaces with unserscores
+      timestamp.strip!
+      output = Hash.new #Creating the output storage object
+      outfile = file_name + '_' + timestamp
+      outfile.slice!('.txt')
+      puts outfile
+      text = strip_text(chunk, 'Narrative:', 'Signatures:')
+      output[:filename] = outfile
+      output[:total_words] = text.split.size
+      bins.each_key do |bin_number|
+        key = bin_number.to_sym
+        output[key] = Hash.new
+        output[key][:words] = bin_counter(bins[bin_number], text)
+        output[key][:total] = count_total(output[key])
+      end
+      write_output_json(output,outfile + '-out.json')
+      write_output_csv(output,outfile + '-out.csv')
+    end
   end
-  write_output_json(output,outfile + '-out.json')
-  write_output_csv(output,outfile + '-out.csv')
 end
 
 #process_dir expects: