dxtitle_search 0.2.2 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ce1fbac8b03c6ed8f54bd015c10f8d0cff189489daef845e2ba7334d51c2f43a
-  data.tar.gz: 1097753eb43800ed8a1361e605fd4e51b427aef0fffcd67649cec7b04a0c12b7
+  metadata.gz: 74ea6c681b08bebcc9fa822a185562a19a262544abf12e674a150428470c8396
+  data.tar.gz: 1ea0ffc0e631086452ef97e51b5e154f21169d4f4274f5538a4ce7c4e476b67b
 SHA512:
-  metadata.gz: ef562657ad220e26e087f672a178475fb15c4e41874f7eacf270c1872e0461763a2b145b509541323467c48ad02e74c91b04d0c14cd15e515a22dd08de90644c
-  data.tar.gz: 812c6c680a264edd2c0ae95fb63b86fb66485642ddb7e2d41696ac1ff51463e6e73cabd4c7fc29cfc8c9fcd9b6e49bb0374f1d1a2f6676e7bfc903afd515dedc
+  metadata.gz: 4e4e998c4df64f0e18ac5556ad197d13ecec2804c9abc7f4ded1a2c7a0a1e89f5c73a73da7ffd8ed418ee5f2eea23233b675eb79412cf68e09c3bb0e333d2def
+  data.tar.gz: 45fc402f35aa22ff4bc66ecf752f8bb946acfeea84106513b382ba921b41c5f68882eb5b415146e13f40be5b28bdb238dc49f68c3ecdd41e7aab5662af00df87

data/lib/dxtitle_search.rb

@@ -2,102 +2,54 @@
 
 # file: dxtitle_search.rb
 
-require 'dynarex'
+require 'indexer101'
 
 
 class DxTitleSearch
 
-  def initialize(obj=nil, sources: obj, debug: false)
+  def initialize(obj=nil, sources: nil, debug: false)
 
     @debug = debug
+    @indexer = Indexer101.new debug: debug
 
     s = if sources then
     
-      dx = Dynarex.new(sources)
-      dx.all.map {|x| read x.uri }.join
+      dx = Dynarex.new(sources)      
+      @indexer.scan_dxindex dx.all.map(&:uri), level: 1
     
-    elsif obj then
-      
-      # is it a Dynarex file location?
-      if obj.lines.length < 2 then
+    elsif obj and obj.lines.length < 2 
 
-        read obj
-
-      else
-        
-        obj
+      @indexer.scan_dxindex  obj, level: 1
         
-      end
     end
   
-    @h = h = s.lines.inject({}) do |r,x|
-      key, value = x.split(/\s+(?=[^\s]+$)/,2)
-      r.merge(key.rstrip => value)
-    end
-
-    @a = h.keys
+    @indexer.build
 
   end
 
-  def search(keywords)
-    
-    phrases = @a.grep /#{keywords}/i
-
-    # find out the keywords count for each entry found
-    a0 = keywords.split.flat_map do |x| 
-      next if @a.length < 2
-      @a.grep /#{x}/i 
-    end
-    
-    a = a0.uniq.map do |entry|
-      [entry, entry.scan(/#{keywords.split.join('|')}/).uniq.count]
-    end
-
-    # sort by keywords found per entry and then date
-    #a2 = (phrases + a).uniq.sort do |x, x2|
-    a2 = a.sort do |x, x2| 
-      -([x.last, x.first[/^\d+/], ] <=> [x2.last, x2.first[/^\d+/]])
-    end
+  def search(keywords)    
 
+    a2 = @indexer.search keywords.split(/[\s:"!\?\(\)£]+(?=[\w#_'-]+)/)
     # format each result as a Hash object
-    a3 = (phrases + a2).map do |x|
+    a3 = a2.map do |date, title, url|
 
-      if x.length > 1 then
-        line, _ = x
-      else
-        line = x
-      end
-      
-      puts 'line: ' + line.inspect if @debug
-     
-      rawtime, title = line.split(/ +/,2)
-      puts 'title: ' + title.inspect if @debug
-
-      {title: title, url: @h[line].chomp, date: Time.at(rawtime.to_i)}
+      {title: title, url: url, date: date}
 
     end
 
     puts 'a3: ' + a3.inspect if @debug
+    
+    def a3.to_dx()
+      Dynarex.new('results/result(title, url, date)').import(self)
+    end
 
     return a3
 
   end
   
-  def tag_search(keywords)
-    a = @a.flat_map {|x| x.split(/#/,2).last.split(/\s*#/)}
-    a.grep(/^#{keywords}/i).map(&:downcase).uniq
-  end
-  
-  private
-  
-  def read(source)
-
-    dx = Dynarex.new(source)
-
-    dx.all.map do |x|
-      "%d %s %s" % [Time.parse(x.created).to_i, x.title, x.url]
-    end.join("\n")
-    
-  end
+  def tag_search(keywords)    
+    r = @indexer.lookup *keywords.split(/[\W]+(?=[\w]+)/).map {|x| "#" + x}
+    r.map {|x| x.to_s[1..-1]}
+  end  
 
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: dxtitle_search
 version: !ruby/object:Gem::Version
-  version: 0.2.2
+  version: 0.3.0
 platform: ruby
 authors:
 - James Robertson
@@ -35,28 +35,28 @@ cert_chain:
   ODgOmcgAsTin0T9l0vWQJnj2OClh1pcC6tFnQXXcYuwTpbtM2v4OmUfUDvJmwQ42
   POydZUYZg49X9TlTDqPMKed0
   -----END CERTIFICATE-----
-date: 2019-08-11 00:00:00.000000000 Z
+date: 2019-11-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: dynarex
+  name: indexer101
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.8'
+        version: '0.2'
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.8.19
+        version: 0.2.1
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.8'
+        version: '0.2'
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.8.19
+        version: 0.2.1
 description: 
 email: james@jamesrobertson.eu
 executables: []
@@ -83,8 +83,9 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.1
+rubygems_version: 3.0.3
 signing_key: 
 specification_version: 4
-summary: Search title entries from plain text (derived from a Dynarex document).
+summary: Originally intended to search title entries from plain text (derived from
+  a Dynarex document).
 test_files: []