rpdf2txt 0.8.3 → 0.8.4

data/History.txt

@@ -1,3 +1,7 @@
+=== 0.8.4 / 06.01.2012
+
+* Updated Manifest.txt to include the _*grammer_files
+
 === 0.8.3 / 05.01.2012
 
 * Getting ready for Ruby 1.9.3, partially, see README for more.

data/Manifest.txt

@@ -1,5 +1,5 @@
-LICENCE
 History.txt
+LICENCE
 Manifest.txt
 README.txt
 Rakefile
@@ -31,6 +31,10 @@ lib/rpdf2txt-rockit/token.rb
 lib/rpdf2txt-rockit/version.rb
 lib/rpdf2txt/attributesparser.rb
 lib/rpdf2txt/cmapparser.rb
+lib/rpdf2txt/data/_cmap.grammar
+lib/rpdf2txt/data/_cmap_range.grammar
+lib/rpdf2txt/data/_pdfattributes.grammar
+lib/rpdf2txt/data/_pdftext.grammar
 lib/rpdf2txt/data/cmap.grammar
 lib/rpdf2txt/data/cmap.rb
 lib/rpdf2txt/data/cmap_range.grammar
@@ -111,6 +115,7 @@ test/data/working_obj
 test/data/working_obj2
 test/mock.rb
 test/suite.rb
+test/test_object.rb
 test/test_pdf_object.rb
 test/test_pdf_parser.rb
 test/test_pdf_text.rb

data/lib/rpdf2txt/data/_cmap.grammar

@@ -0,0 +1,11 @@
+Grammar CMap
+	Tokens
+		SPACE = /\s+/n [:Skip]
+		HEXSNIPPET = /[0-9A-F]+/in
+	Productions
+		HexArray			->	RangeDef+
+											[^: values ]
+		RangeDef			->	HexElement HexElement
+											[: source, target ]
+	  HexElement		->	'<' HEXSNIPPET '>'
+											[^: _, hexsnip, _ ]

data/lib/rpdf2txt/data/_cmap_range.grammar

@@ -0,0 +1,15 @@
+Grammar CMap
+	Tokens
+		SPACE = /\s+/n [:Skip]
+		HEXSNIPPET = /[0-9A-F]+/in
+	Productions
+		HexArray			->	RangeDef+
+											[^: values ]
+		RangeDef			->	HexElement HexElement HexElement
+											[: start, stop, offset ]
+									|		HexElement HexElement Explicit
+											[: start, stop, explicit ]
+		Explicit			->	'[' HexElement+ ']'
+											[^: _, explicit, _ ]
+	  HexElement		->	'<' HEXSNIPPET '>'
+											[^: _, hexsnip, _ ]

data/lib/rpdf2txt/data/_pdfattributes.grammar

@@ -0,0 +1,32 @@
+Grammar PdfAttributes
+	Tokens
+		IDENTIFIER = /^\/[\w:+\#\-\.]*(, ?[\w:+\#\-\.]*)*/n
+		NUMERIC = /-?[0-9]+([.,][0-9]+)?/n
+		REFERENCE = /[0-9]+\s+[0-9]+\s+R/n
+		WORD = /[a-z\.]{2,}/in
+		SPACE = /\s+/mn [:Skip]
+		COMMENT = /%[^%]*%/mn [:Skip]
+		FILEIDENTIFIER = /<[a-zA-Z0-9\n]+>/n
+	Productions
+		Expr				->	IDENTIFIER [^: val]
+								|		Hash [^: val]
+								|		Array [^: val]
+								|		REFERENCE [^: val]
+								|		NUMERIC [^: val]
+								|		Text [^: val]
+								|		Date [^: val]
+								|		WORD [^: val]
+								|   FILEIDENTIFIER [^: val]
+		Array				->	'[' ArrayElements ']'
+										[: _, values, _]
+								|  '[' ']'
+										[: _, _]
+		ArrayElements -> ArrayElement+
+										[^: values]
+		ArrayElement -> (Array|Hash|NUMERIC|IDENTIFIER|REFERENCE|WORD|FILEIDENTIFIER|Text)
+										[^: _]
+		Hash				->	'<<' (IDENTIFIER Expr)* '>>'
+										[: _, pairs, _]
+		Date				->	'(D:' /[\d+']+/n ')'
+		Text				->	/\(([^\)\\]|\\[\(\)\\]?)*?\)/n
+										[: text]

data/lib/rpdf2txt/data/_pdftext.grammar

@@ -0,0 +1,102 @@
+Grammar PdfText
+	Tokens
+		NUMERIC = /-?(([0-9]*[.,_][0-9]+)|([0-9]+))/n
+		SPACE = /\s+/n [:Skip]
+		HEXSNIPPET = /[0-9A-F]+/in
+		ALPHANUMERIC  = /[A-Z0-9\-_?\.]+/in
+		TEXTSNIPPET = /\(([^\)\\]|\\[\)\\]?)+\)/n
+		TJSNIPPET = /\((\\\(|\([^\(\)]*\)|[^\)\\]|\\[\)\\]?)*\)/n
+		IDENTIFIER = /^\/[\w:+\#\-\.]*(, ?[\w:+\#\-\.]*)*/n
+		WORD = /[a-z\.]{2,}/in
+	Productions
+		Target			->	'BT' Exprs 'ET'	[: _, values, _]
+		Exprs				->	Expr+ [^: values]
+		Expr				->	TmElement [^: val]
+								|		Array		[^: val]
+								|		TDElement [^: val]
+								|		TdElement [^: val]
+								|		TcElement [^: val]
+								|		TWElement [^: val]	
+								|		TfElement [^: val]
+								|		TjElement [^: val]
+								|		TrElement [^: val]
+							  |		TjHex			[^: val]
+								|		TStarElement [^: val]
+								|		TSElement [^: val]
+								|		TLElement [^: val]
+								|		TZElement	[^: val]
+								|		RgElement[^: val]
+								|		Apostroph [^: val]
+								|		Quotes [^: val]
+                |   LineWidth [^: val]
+								|		UElement  [^: val]
+		Array			->	'[' TJArrayElements /\]\s*TJ/n
+										 [: _, values, _]
+		TmElement		->	NUMERIC NUMERIC NUMERIC NUMERIC
+										NUMERIC NUMERIC 'Tm'
+										[Tm: xscale, alpha, beta, yscale, tmx, tmy, _]
+		TDElement		->	NUMERIC NUMERIC 'TD'
+										[TD: tdleadx, tdleady,_]
+		TdElement		->	NUMERIC NUMERIC 'Td'
+										[Td: xpos, ypos,_]
+		TcElement		->	NUMERIC 'Tc'
+										[Tc: charspace, _]
+		TWElement		->	NUMERIC 'Tw'
+										[TW: wordspace, _]
+		TfElement		->	'/' ALPHANUMERIC NUMERIC 'Tf' 
+										[Tf: _, fontname, fontsize, _]
+		TLElement		->	NUMERIC 'TL'
+										[TL: lead, _]
+		TjElement		->	TJSNIPPET 'Tj'
+										[Tj: snippet, _ ]
+		HexElement	->	'<' HEXSNIPPET '>'
+										[^: _, hex, _ ]
+                |   '<' '>'
+										[^: _, _ ]
+	  TjHex				->	HexElement 'Tj'
+										[Tjhex: hexsnippet, _ ]
+		TJArrayElements	->	TJSingleElement+
+												[^: values ]
+		TJSingleElement	->	TJSNIPPET
+												[: snippet ]
+										|		NUMERIC
+												[: kerning ]
+										|		HexElement
+												[: hexsnippet ]
+                    |   '())'
+		TSElement		->	NUMERIC 'Ts'
+										[Ts: textrise]
+		TStarElement ->	'T*'
+										[TStar: linebreak ]
+		TZElement		->	NUMERIC 'Tz'
+										[Tz: hscaling]
+		RgElement		->	NUMERIC NUMERIC NUMERIC 'rg'
+										[Rg: _, _, _, _]
+		TrElement		->  NUMERIC 'Tr'
+										[Tr: render]
+		Apostroph		->	TJSNIPPET	"'"
+										[Apo: aposnippet, _]
+		Quotes			->	NUMERIC NUMERIC	TJSNIPPET '"'
+										[Quo: wordspace, charspace, aposnippet, _]
+    LineWidth   ->  NUMERIC 'w'
+										[Width: width, _]
+		BTElement		->	/^BT$/n
+										[BT: _]
+		ETElement		->	/^ET$/n
+										[ET: _]
+		Hash				->	'<<' (IDENTIFIER HashExpr)* '>>'
+										[: _, pairs, _]
+		HashExpr		->	IDENTIFIER [^: val]
+								|		NUMERIC [^: val]
+								|		WORD [^: val]
+		UElement		->	NUMERIC NUMERIC NUMERIC NUMERIC 'k'
+								|		'/' ALPHANUMERIC /[gc]s/in
+								|		'/' ALPHANUMERIC Hash /BDC|BMC/
+								|		'EMC'
+								|		CNElements /scn?/in
+								|		NUMERIC /[gijJMG]/n
+								|		NUMERIC NUMERIC NUMERIC 'RG'
+								|		'[]' NUMERIC 'd'
+    CNElements  ->  CNElement+
+    CNElement   ->  ALPHANUMERIC
+                |   '/' ALPHANUMERIC ALPHANUMERIC?

data/lib/rpdf2txt/parser.rb

@@ -29,7 +29,7 @@ require	'rpdf2txt/default_handler'
 require 'digest/md5'
 
 module Rpdf2txt
-  VERSION = '0.8.3'
+  VERSION = '0.8.4'
   class Parser
 		attr_accessor :encrypt
 		def initialize(pdf_stream, target_encoding='utf8')

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: rpdf2txt
 version: !ruby/object:Gem::Version 
-  hash: 57
+  hash: 55
   prerelease: 
   segments: 
   - 0
   - 8
-  - 3
-  version: 0.8.3
+  - 4
+  version: 0.8.4
 platform: ruby
 authors: 
 - Masaomi Hatakeyama, Zeno R.R. Davatz
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2012-01-05 00:00:00 +01:00
+date: 2012-01-06 00:00:00 +01:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -50,8 +50,8 @@ extra_rdoc_files:
 - usage-en.txt
 - user-stories/UserStories_Rpdf2Txt.txt
 files: 
-- LICENCE
 - History.txt
+- LICENCE
 - Manifest.txt
 - README.txt
 - Rakefile
@@ -83,6 +83,10 @@ files:
 - lib/rpdf2txt-rockit/version.rb
 - lib/rpdf2txt/attributesparser.rb
 - lib/rpdf2txt/cmapparser.rb
+- lib/rpdf2txt/data/_cmap.grammar
+- lib/rpdf2txt/data/_cmap_range.grammar
+- lib/rpdf2txt/data/_pdfattributes.grammar
+- lib/rpdf2txt/data/_pdftext.grammar
 - lib/rpdf2txt/data/cmap.grammar
 - lib/rpdf2txt/data/cmap.rb
 - lib/rpdf2txt/data/cmap_range.grammar
@@ -163,6 +167,7 @@ files:
 - test/data/working_obj2
 - test/mock.rb
 - test/suite.rb
+- test/test_object.rb
 - test/test_pdf_object.rb
 - test/test_pdf_parser.rb
 - test/test_pdf_text.rb
@@ -172,7 +177,6 @@ files:
 - usage-en.txt
 - user-stories/UserStories_Rpdf2Txt.txt
 - user-stories/documents/swissmedicjournal/04_2004.pdf
-- test/test_object.rb
 - .gemtest
 has_rdoc: true
 homepage: http://scm.ywesee.com/?p=rpdf2txt/.git;a=summary