xml_row_finder 0.1.0 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: cfc152e03ec51b624550b4b4bf031eae3e7205c42e1dccbdd4d45219d684860d
-  data.tar.gz: 77be8ae4da89aded4ec73a653e9fe1e3d9815a144a29a37a73158b97174da984
+  metadata.gz: e993dbcc7aa78609f6da7dad8044858a117ad8f2a35dbaffb8a4bef967d1c2fa
+  data.tar.gz: c73231bd44d7845a132c740ef02c48afc187459470e877c63372f6f82f99b03d
 SHA512:
-  metadata.gz: e83c208f4dfeac7827b9f8ca453baba4f19ff4be9d4341bbd15f46695948afd7af42ae5ad0c71efb994b58832c46b9cf836fcb2d115ffb126a49ebfc26065772
-  data.tar.gz: 24335ada2416257aa9caebd29b687562e92fe2d0ca2ac71f59824448c98eee018e15f95ee60352ed326440a50cb5445d3fb5bd4cbb1a0c47eed58ffc85ff12ec
+  metadata.gz: 996c4a63be86e7abe8948ef5dd6860f2b9226e1e429ef0f51c7ece7efb4b54cb35b18b48488403264149183b0b61d3f7d05eecc52d1dd9841f9ab0c654ffc2c6
+  data.tar.gz: fe7558dbaf9a183e860b8214bac3dfc0ca797364775c3b49ddded4c24acea51a8c600e0d3e1dc53ac74f6557dd72eb4de5284212be15bfe3df0fba7d8ca86d89

checksums.yaml.gz.sig

@@ -1 +1,6 @@
-;�Ac.���n�g�r;�%�6,z{ma��j��~�zJJ����Ù4�r�c{���E�޵��i�lDp��:R=[W�mJ����=#M�b�F���n�@�E��O�F���_FK�-��4Z�*wT��x�RH;�L�G�d�&��Y�遲�Lo&��7�Eב-$:�1�؏��U���)y��"�v{��/nD*:%����^�kz�8�n�%m14Ȯ�I�c\�YGNu�軀�J���{����Xs���=�@V;���M���ʺ���p�p����������Kb<#�J6
��}�k���X��~��Hc�b���Ҏ���=���L��N��Գ*k�Rw��������B������jd�F�`WXx����J
+�u�3h�Bju���4/+H��wt��:��H!����q�!9v��@/Ad䳹na$�]x�vw���.�r��X	�5��d����2����	���ٽR�J�O�O�:�k\��{􊒔�1��T��;��	1�
+�V��=��Ų�
+I&�3�s���Q�.V")��������&c��E+��i�͢Ԧa��eyK�ո�D~}r�PM�ߞw��h���u�{^�R?%�ۮi����
++I�����6`��h>��
���y6l+��@�Iq=�/"���v�׵����HN�>���s4G3�/�H
+�2���?նͰ;��8O�W�߯�M�����E��
+�~���7��

data/lib/xml_row_finder.rb

@@ -15,6 +15,7 @@ class XMLRowFinder
 
     @debug = debug
     doc = Rexle.new(s)
+    @doc2 = Document.new(s)
 
     a = []
 
@@ -23,51 +24,31 @@ class XMLRowFinder
       a << e.backtrack.to_xpath
     end
 
-    a2 = a.select{ |e| a.count(e) > 1 }.map {|x| x.split('/')}.uniq
+    @to_a = a2 = a.map {|e| [a.count(e), e] }
+    xpath = a2.max_by(&:first).last
 
-    # remove parent nodes on the same branch
-    #
-    a2.reject!.with_index do |x,i| 
-      next if i == a2.length-1
-      x == a2[i+1][0..-2]
-    end
+    a3 = xpath.split('/')
+    a4 = [xpath]
+    p1 = []
 
-    # remove elements from rows which only exist once in the document
-    #
-    a3 = a2.map do |row|
-      row.reject do |x|
-        found = doc.root.xpath('//' + x)
-        found.length < 2
-      end
+    until (a3.length < 1) do
+      p1 << a3.pop; a4 << a3.join('/') + "[%s]" % p1.reverse.join('/')
     end
 
-    # add parent node to the row as a reference for the xpath
-    #
-    a4 = a3.map.with_index do |row,i|
-      a2[i][-(row.length+1)..-1]
+    a5 = a4[0..-2].map do |xpath2|
+      [XPath.match(@doc2, xpath2).length, xpath2]
     end
 
-    # find the parent node attributes
-    #
-    @to_a = a4.map do |col|
-
-      # currently using REXML for this XPath since there is a bug in 
-      #   Rexle when attempting the following
-      # 
-      doc2 = Document.new(s)
-      xpath = "//%s[%s]" % [col[0], col[1..-1].join('/')]
-      puts 'xpath: ' + xpath.inspect if @debug
-      r = XPath.first(doc2, xpath)
-      xpath_a = BacktrackXPath.new(r).to_xpath
-
-      if col.length >= 3
-        "%s/%s[%s]" % [xpath_a, col[1], col[2..-1].join('/')]
-      else
-        "%s/%s" % [xpath_a, col[1]]
-      end
-    end
-    
+    @xpath = a5.reverse.detect {|num, xpath2| num > 1}.last
+
   end
 
-end
+  def rows()
+    XPath.match(@doc2, @xpath)
+  end
+
+  def to_xpath()
+    @xpath
+  end
 
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: xml_row_finder
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.2.0
 platform: ruby
 authors:
 - James Robertson
@@ -35,7 +35,7 @@ cert_chain:
   a/pAsvo0jT6QTnSB7xzsx8LSFDT5tfHKR9Dcn1Y3R06fsh02JvwxaSAMgDBM2aFb
   2A7/BQ1hD7SU82VTxB1gFIHl
   -----END CERTIFICATE-----
-date: 2022-01-21 00:00:00.000000000 Z
+date: 2022-01-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rexle
@@ -83,7 +83,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.22
+rubyforge_project: 
+rubygems_version: 2.7.10
 signing_key: 
 specification_version: 4
 summary: Attempts to find repeating rows in XHTML and returns the associated xpath.