pdf-reader 2.4.1 → 2.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2b38615953615bfbca1a80ab344f26166377d8c08d2ba2e05badf43c10682415
-  data.tar.gz: 658b5d05a14300ad056ee31c10ea998533ccb1b91600e8bc9097070605d003ea
+  metadata.gz: 652d05cf6a22fad5ecb4b92de1e27ba60cafc6525c5ca524e24c7f9796fe1b83
+  data.tar.gz: 2c7448e97890a9fcbd10ec2cd5bafb9025db2fb75dabaf71a4074c542b1065a1
 SHA512:
-  metadata.gz: 210b0bee8c4ac009808555c8ba945f3b17b85af22126ac1440eb9b49d91f542f1974b0984efb22726985f2cf8e03440511ebc4664ac5c4d91a6bddea9a43687e
-  data.tar.gz: 8fb60cb59dc4430179a4b9ba83d30ae6dc23aa13dbef5e8febe1569311ddf7e531783da7e7dd0a6542f0087748e97898af56d540e7c088832f213b48059aa7d3
+  metadata.gz: ac82452924cf46af98ee15f2a20642b1d06d5b9c22104fe171b5b4612665e482f341e12473805016ccb9d921fc15324ba51675170b369adeace8b278cd1279fb
+  data.tar.gz: b1dc1c4422b0e6bf01092cf724630ba7424fdef1fdaf34f33aaa3a31397caf6ef5a73185a98e6e2828a9e082d87cbca311565397cb064cac20d86e72be27626f

data/CHANGELOG

@@ -1,3 +1,14 @@
+v2.5.0 (6th June 2021)
+- bump minimum ruby version to 2.0
+- Correctly handle trascoding to UTF-8 from some fonts that use a difference table [#344](https://github.com/yob/pdf-reader/pull/344/) 
+- Fix some character spacing issues with the TJ operator [#343](https://github.com/yob/pdf-reader/pull/343)
+- Fix crash with some encrypted PDFs [#348](https://github.com/yob/pdf-reader/pull/348/)
+- Fix positions of text on some PDFs with pages rotated 90° [#350](https://github.com/yob/pdf-reader/pull/350/)
+
+v2.4.2 (28th January 2021)
+- relax ASCII85 dependency to allow 1.x
+- improved support for decompressing objects with slightly malformed zlib data
+
 v.2.4.1 (24th September 2020)
 - Re-vendor font metrics from Adobe to clarify their license
 

data/lib/pdf/reader/filter/flate.rb

@@ -9,6 +9,7 @@ class PDF::Reader
     # implementation of the Flate (zlib) stream filter
     class Flate
       ZLIB_AUTO_DETECT_ZLIB_OR_GZIP = 47  # Zlib::MAX_WBITS + 32
+      ZLIB_RAW_DEFLATE              = -15 # Zlib::MAX_WBITS * -1
 
       def initialize(options = {})
         @options = options
@@ -17,24 +18,34 @@ class PDF::Reader
       ################################################################################
       # Decode the specified data with the Zlib compression algorithm
       def filter(data)
-        deflated = nil
+        deflated = zlib_inflate(data) || zlib_inflate(data[0, data.bytesize-1])
+
+        if deflated.nil?
+          raise MalformedPDFError,
+            "Error while inflating a compressed stream (no suitable inflation algorithm found)"
+        end
+        Depredict.new(@options).filter(deflated)
+      end
+
+      private
+
+      def zlib_inflate(data)
         begin
-          deflated = Zlib::Inflate.new(ZLIB_AUTO_DETECT_ZLIB_OR_GZIP).inflate(data)
-        rescue Zlib::DataError => e
+          return Zlib::Inflate.new(ZLIB_AUTO_DETECT_ZLIB_OR_GZIP).inflate(data)
+        rescue Zlib::DataError
           # by default, Ruby's Zlib assumes the data it's inflating
           # is RFC1951 deflated data, wrapped in a RFC1950 zlib container. If that
-          # fails, then use a lightly-documented 'feature' to attempt to inflate
-          # the data as a raw RFC1951 stream.
-          #
-          # See
-          # - http://blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-talk/243545
-          deflated = Zlib::Inflate.new(-Zlib::MAX_WBITS).inflate(data)
+          # fails, swallow the exception and attempt to inflate the data as a raw
+          # RFC1951 stream.
         end
-        Depredict.new(@options).filter(deflated)
-      rescue Exception => e
-        # Oops, there was a problem inflating the stream
-        raise MalformedPDFError,
-          "Error occured while inflating a compressed stream (#{e.class.to_s}: #{e.to_s})"
+
+        begin
+          return Zlib::Inflate.new(ZLIB_RAW_DEFLATE).inflate(data)
+        rescue StandardError
+          # swallow this one too, so we can try some other fallback options
+        end
+
+        nil
       end
     end
   end

data/lib/pdf/reader/object_hash.rb

@@ -331,7 +331,9 @@ class PDF::Reader
     def decrypt(ref, obj)
       case obj
       when PDF::Reader::Stream then
-        obj.data = sec_handler.decrypt(obj.data, ref)
+        # PDF 32000-1:2008 7.5.8.2: "The cross-reference stream shall not be encrypted [...]."
+        # Therefore we shouldn't try to decrypt it.
+        obj.data = sec_handler.decrypt(obj.data, ref) unless obj.hash[:Type] == :XRef
         obj
       when Hash                then
         arr = obj.map { |key,val| [key, decrypt(ref, val)] }.flatten(1)

data/lib/pdf/reader/page_layout.rb

@@ -30,6 +30,7 @@ class PDF::Reader
 
     def to_s
       return "" if @runs.empty?
+      return "" if row_count == 0
 
       page = row_count.times.map { |i| " " * col_count }
       @runs.each do |run|

data/lib/pdf/reader/page_state.rb

@@ -30,15 +30,7 @@ class PDF::Reader
         @xobject_stack = [page.xobjects]
         @cs_stack      = [page.color_spaces]
         @stack         = [DEFAULT_GRAPHICS_STATE.dup]
-        if page.rotate == 0
-          state[:ctm]  = identity_matrix
-        else
-          rotate_cos = Math.cos(page.rotate * (Math::PI/180.0)).round(2)
-          rotate_sin = Math.sin(page.rotate * (Math::PI/180.0)).round(2)
-          state[:ctm] = TransformationMatrix.new(rotate_cos, rotate_sin,
-                                                 rotate_sin * -1, rotate_cos,
-                                                 0, 0)
-        end
+        state[:ctm]  = identity_matrix
       end
 
       #####################################################
@@ -330,11 +322,13 @@ class PDF::Reader
         th = state[:h_scaling]
         # optimise the common path to reduce Float allocations
         if th == 1 && tj == 0 && tc == 0 && tw == 0
-          glyph_width = w0 * fs
-          tx = glyph_width
+          tx = w0 * fs
+        elsif tj != 0
+          # don't apply spacing to TJ displacement
+          tx = (w0 - (tj/1000.0)) * fs * th
         else
-          glyph_width = ((w0 - (tj/1000.0)) * fs) * th
-          tx = glyph_width + ((tc + tw) * th)
+          # apply horizontal scaling to spacing values but not font size
+          tx = ((w0 * fs) + tc + tw) * th
         end
 
         # TODO: I'm pretty sure that tx shouldn't need to be divided by

data/lib/pdf/reader/page_text_receiver.rb

@@ -41,6 +41,7 @@ module PDF
       # starting a new page
       def page=(page)
         @state = PageState.new(page)
+        @page = page
         @content = []
         @characters = []
         @mediabox = page.objects.deref(page.attributes[:MediaBox])
@@ -104,6 +105,8 @@ module PDF
         glyphs.each_with_index do |glyph_code, index|
           # paint the current glyph
           newx, newy = @state.trm_transform(0,0)
+          newx, newy = apply_rotation(newx, newy)
+
           utf8_chars = @state.current_font.to_utf8(glyph_code)
 
           # apply to glyph displacment for the current glyph so the next
@@ -118,6 +121,21 @@ module PDF
         end
       end
 
+      def apply_rotation(x, y)
+        if @page.rotate == 90
+          tmp = x
+          x = y
+          y = tmp * -1
+        elsif @page.rotate == 180
+          y *= -1
+        elsif @page.rotate == 270
+          tmp = x
+          x = y * -1
+          y = tmp * -1
+        end
+        return x, y
+      end
+
     end
   end
 end

data/lib/pdf/reader/width_calculator/built_in.rb

@@ -37,23 +37,15 @@ class PDF::Reader
       def glyph_width(code_point)
         return 0 if code_point.nil? || code_point < 0
 
-        m = @metrics.char_metrics_by_code[code_point]
-        if m.nil?
-          names = @font.encoding.int_to_name(code_point)
+        names = @font.encoding.int_to_name(code_point)
+        metrics = names.map { |name|
+          @metrics.char_metrics[name.to_s]
+        }.compact.first
 
-          m = names.map { |name|
-            @metrics.char_metrics[name.to_s]
-          }.compact.first
-        end
-
-        if m
-          m[:wx]
-        elsif @font.widths[code_point - 1]
-          @font.widths[code_point - 1]
-        elsif control_character?(code_point)
-          0
+        if metrics
+          metrics[:wx]
         else
-          0
+          @font.widths[code_point - 1] || 0
         end
       end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: pdf-reader
 version: !ruby/object:Gem::Version
-  version: 2.4.1
+  version: 2.5.0
 platform: ruby
 authors:
 - James Healy
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-09-24 00:00:00.000000000 Z
+date: 2021-06-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -100,14 +100,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.0.0
+        version: '1.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.0.0
+        version: '1.0'
 - !ruby/object:Gem::Dependency
   name: ruby-rc4
   requirement: !ruby/object:Gem::Requirement
@@ -277,10 +277,10 @@ licenses:
 - MIT
 metadata:
   bug_tracker_uri: https://github.com/yob/pdf-reader/issues
-  changelog_uri: https://github.com/yob/pdf-reader/blob/v2.4.1/CHANGELOG
-  documentation_uri: https://www.rubydoc.info/gems/pdf-reader/2.4.1
-  source_code_uri: https://github.com/yob/pdf-reader/tree/v2.4.1
-post_install_message: 
+  changelog_uri: https://github.com/yob/pdf-reader/blob/v2.5.0/CHANGELOG
+  documentation_uri: https://www.rubydoc.info/gems/pdf-reader/2.5.0
+  source_code_uri: https://github.com/yob/pdf-reader/tree/v2.5.0
+post_install_message:
 rdoc_options:
 - "--title"
 - PDF::Reader Documentation
@@ -293,15 +293,15 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 1.9.3
+      version: '2.0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.3
-signing_key: 
+rubygems_version: 3.2.3
+signing_key:
 specification_version: 4
 summary: A library for accessing the content of PDF files
 test_files: []