combine_pdf 0.0.12 → 0.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: a8c0bc3044a3d626227cd92230f5469ab88daac5
-  data.tar.gz: 1fbf45c126ddf79754f2660f9802d489d8583031
+  metadata.gz: 20e1c50aa5948f3a2ba3ad9c170ba08bc3e8ec38
+  data.tar.gz: 75ed75edadc4fcdee63ab579419f83f8685a8c47
 SHA512:
-  metadata.gz: 39080aa09fef9475249937e92d0eb5c425a840c6663762ef2c896ad6326fc717e35bfcc1f698f9aa882cae6e05d47bb5caad8c0073b2e96043a49a9856a7f044
-  data.tar.gz: 95cd39ba719bd65323c84da9f5d86195faa9e68874158c40e4c872c060d328bc0a3b212d1b79841efc3240b8d09b6c505a28b57dd62aad7c2cc306b2c105b9df
+  metadata.gz: 8b70a1624d699441aab808da4ee0461796d643607622a42c2ecd58342bebd8ee8f1edcc633962e93b36dba82c0ba89400f29b06f7e115d3e21eaf0803130f032
+  data.tar.gz: 8e5d4f16d65cd2306149dc69012aae66d5295f54d18760a335cf32fd68c3d9bd2563689bee87e44724c260653d232ddb2db93ef7e91d4c27265a48da96e7b616

data/lib/combine_pdf.rb

@@ -32,11 +32,9 @@ load "combine_pdf/combine_pdf_pdf.rb"
 
 
 
-# This is a pure ruby library to merge PDF files.
+# This is a pure ruby library to combine/merge, stmap/overlay and number PDF files.
 #
-# In the future, this library will also allow stamping and watermarking PDFs (it allows this now, only with some issues).
-#
-# PDF objects can be used to combine or to inject data.
+# You can also use this library for writing basic text content into new or existing PDF files (For authoring new PDF files look at the Prawn ruby library).
 #
 # here is the most basic application for the library, a one-liner that combines the PDF files and saves them:
 #   (CombinePDF.new("file1.pdf") << CombinePDF.new("file2.pdf") << CombinePDF.new("file3.pdf")).save("combined.pdf")
@@ -59,7 +57,7 @@ load "combine_pdf/combine_pdf_pdf.rb"
 #   pdf.save "combined.pdf"
 # as demonstrated above, these can be chained for into a one-liner.
 #
-# you can also only selected pages.
+# you can also choose to add only specific pages.
 #
 # in this example, only even pages will be added:
 #   pdf = CombinePDF.new
@@ -77,15 +75,14 @@ load "combine_pdf/combine_pdf_pdf.rb"
 # in this example, a company logo will be stamped over each page:
 #   company_logo = CombinePDF.new("company_logo.pdf").pages[0]
 #   pdf = CombinePDF.new "content_file.pdf"
-#   pdf.pages.each {|page| page << company_logo} # notice the << operator is on a page and not a PDF object.
+#   pdf.pages.each {|page| page << company_logo}
 #   pdf.save "content_with_logo.pdf"
 # Notice the << operator is on a page and not a PDF object. The << operator acts differently on PDF objects and on Pages.
 #
-# The << operator defaults to secure injection by renaming references to avoid conflics. For overlaying pages using compressed data that might not be editable (due to limited filter support), you can use:
-#   pdf.pages(nil, false).each {|page| page << stamp_page}
-#
+# The << operator defaults to secure injection by renaming references to avoid conflics.
 #
-# Notice that page objects are Hash class objects and the << operator was added to the Page instances without altering the class.
+# Less recommended, but available - for overlaying pages using compressed data that might not be editable (due to limited filter support), you can use:
+#   pdf.pages(nil, false).each {|page| page << stamp_page}
 #
 # == Page Numbering
 # adding page numbers to a PDF object or file is as simple as can be:

data/lib/combine_pdf/combine_pdf_basic_writer.rb

@@ -406,14 +406,20 @@ module CombinePDF
 			out = []
 			scanner = StringScanner.new text
 			until scanner.eos? do
-				if scanner.scan /[#{rtl_characters}]/
-					out.unshift scanner.matched
-				end
-				if scanner.scan /[^#{rtl_characters}]+/
+				if scanner.scan /[#{rtl_characters} ]/
 					out.unshift scanner.matched
+				elsif scanner.scan /[^#{rtl_characters}]+/
+					if out.empty? && scanner.matched.match(/[\s]$/) && !scanner.eos?
+						warn "MOVING SPACE: #{scanner.matched}"
+						white_space_to_move = scanner.matched.match(/[\s]+$/).to_s
+						out.unshift scanner.matched[0..-1-white_space_to_move.length]
+						out.unshift white_space_to_move
+					else
+						out.unshift scanner.matched
+					end
 				end
 			end
-			out.join
+			out.join.strip
 		end
 	end
 	

data/lib/combine_pdf/combine_pdf_operations.rb

@@ -15,7 +15,7 @@ module CombinePDF
 	#
 	# this Hash lists the private Hash keys that the CombinePDF library uses to
 	# differentiate between complex PDF objects.
-	PRIVATE_HASH_KEYS = [:indirect_reference_id, :indirect_generation_number, :raw_stream_content, :is_reference_only, :referenced_object, :indirect_without_dictionary, :linked_fonts]
+	PRIVATE_HASH_KEYS = [:indirect_reference_id, :indirect_generation_number, :raw_stream_content, :is_reference_only, :referenced_object, :indirect_without_dictionary]
 	#@private
 	#:nodoc: all
 
@@ -130,6 +130,8 @@ module CombinePDF
 				names_dictionary.each do |old_key, new_key|
 					stream[:raw_stream_content].gsub! _object_to_pdf(old_key), _object_to_pdf(new_key)  ##### PRAY(!) that the parsed datawill be correctly reproduced! 
 				end
+				# patch back to PDF defaults, for OCRed PDF files.
+				stream[:raw_stream_content] = "q\nq\nq\nDeviceRGB CS\nDeviceRGB cs\n0 0 0 rg\n0 0 0 RG\n0 Tr\n%s\nQ\nQ\nQ\n" % stream[:raw_stream_content]
 			end
 
 			new_page

data/lib/combine_pdf/combine_pdf_pdf.rb

@@ -48,9 +48,6 @@ module CombinePDF
 	# The << operator defaults to secure injection by renaming references to avoid conflics. For overlaying pages using compressed data that might not be editable (due to limited filter support), you can use:
 	#   pdf.pages(nil, false).each {|page| page << stamp_page}
 	#
-	#
-	# Notice that page objects are Hash class objects and the << operator was added to the Page instances without altering the class.
-	#
 	# == Page Numbering
 	# adding page numbers to a PDF object or file is as simple as can be:
 	#   pdf = CombinePDF.new "file_to_number.pdf"
@@ -281,8 +278,11 @@ module CombinePDF
 			return self #return self object for injection chaining (pdf << page << page << page)
 		end
 
-		# LATIN ONLY - NO UNICODE SUPPORT YET
 		# add page numbers to the PDF
+		#
+		# For unicode text, a unicode font(s) must first be registered. the registered font(s) must supply the
+		# subset of characters used in the text. UNICODE IS AN ISSUE WITH THE PDF FORMAT - USE CAUSION.
+		#
 		# options:: a Hash of options setting the behavior and format of the page numbers:
 		# - :number_format a string representing the format for page number. defaults to ' - %s - ' (allows for letter numbering as well, such as "a", "b"...).
 		# - :number_location an Array containing the location for the page numbers, can be :top, :buttom, :top_left, :top_right, :bottom_left, :bottom_right. defaults to [:top, :buttom].

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: combine_pdf
 version: !ruby/object:Gem::Version
-  version: 0.0.12
+  version: 0.1.0
 platform: ruby
 authors:
 - Boaz Segev