pdftdx 1.1.8 → 1.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 0f4d29312cf65b9cdb06d6f67a5a6c00a0dba8ad
-  data.tar.gz: 53f54c86ef77df038ac25091d771c8d7a32d3ea0
+  metadata.gz: 369947ea208604dcb52e6a9f329df412709d0f0f
+  data.tar.gz: 14d1803d485efed81cfc14e89d720f8da9e0d5bc
 SHA512:
-  metadata.gz: 10f71afdd59fae8a75ccce78955bd5465e72efc1bfdf6e600269e119479a3b09d444e414eb0be83e33c6d7c4cdb98904e1b145e713cd8f0ea2c49bb2a439a68e
-  data.tar.gz: 3de4e256aa6dec1969c1d0c65e75a09228bb0ab072cc1ec7283f705e29d4e1203d2e1d244b46f7aad5c91dbdb3847728db6f1ec49ff171926d8e910e5908afa9
+  metadata.gz: 71965bd9e8648e4be72546718891ea87d3d521080711396adaf50325359a0d90d445b0a56e0c210307698561f49f6c93379b47c4416d6a0fb05ad0211886b9db
+  data.tar.gz: bb9f966e063c2a8d3e83b60c9e8af61635ed8e7e7d9e98508ebc456bf2cca3b40e2a243bafb1d3036fc5eb5fab30ea1ce8a4b0437e80119e08432a3416d8aadc

data/lib/pdftdx/parser.rb

@@ -152,6 +152,28 @@ module PDFTDX
 			Hash[*(r.to_a.sort { |a, b| ((a[0] == b[0]) ? 0 : (a[0] > b[0] ? 1 : -1)) }.flatten)]
 		end
 
+		# Fix Dupes
+		# Shifts Duplicate Cells (Cells which share their x-offset with others) to the right (so they don't get overwritten)
+		# @param [Array] r A row of data in the form [[xoffset, cell]] (Example: [[120, 'cell 0'], [200, 'cell 1'], [280, 'cell 2']])
+		# @param [Array] The same row of data, but with duplicate cells shifted so that no x-offset-collisions occur
+		def self.fix_dupes r
+
+			# Deep-Duplicate Row
+			nr = r.collect { |e| e.clone }
+
+			# Run through Cells
+			nr.length.times do |i|
+
+				# Acquire Duplicate Length
+				dupes = nr.slice(i + 1, nr.length).inject(0) { |a, c| a + (c[0] == nr[i][0] ? 1 : 0) }
+
+				# Fix Dupes
+				dupes.times { |j| nr[i + j + 1][0] = nr[i + j + 1][0] + 1 }
+			end
+
+			nr
+		end
+
 		# Touch up Table
 		# Splits Table into multiple headered tables.
 		# Also, strips Left Offset info from Table Cells.
@@ -177,8 +199,8 @@ module PDFTDX
 				# Compute Row Base (Default Columns)
 				row_base = Hash[*(cols.collect { |c| [c, ''] }.flatten)]
 
-				# Tables
-				{ head: t[:head], data: t[:data].collect { |r| sort_row row_base.merge(Hash[*(r.collect { |o, c| [(cols.reverse.find { |co| co <= o }) || o, c] }.flatten)]) } }
+				# Re-Build Table
+				{ head: t[:head], data: t[:data].collect { |r| sort_row row_base.merge(Hash[*((fix_dupes r.collect { |o, c| [(cols.reverse.find { |co| co <= o }) || o, c] }).flatten)]) } }
 			end
 
 			# Drop Offsets

data/lib/pdftdx/version.rb

@@ -5,5 +5,5 @@
 module PDFTDX
 
 	# Version
-	VERSION = '1.1.8'
+	VERSION = '1.2.0'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: pdftdx
 version: !ruby/object:Gem::Version
-  version: 1.1.8
+  version: 1.2.0
 platform: ruby
 authors:
 - Eresse