pdf-reader 2.2.0 → 2.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: cfc4ed13692a51d8b78fc181d67fcf8b5e00fb1679dbca36137961f63365edaf
-  data.tar.gz: de5556fabc41642746fd242a2623c92c9424c56da2d845507c49624c312b646b
+  metadata.gz: e1d87a1e4cc6989cb579c5c720ebe8277ab8099a2a6d7044a5c6f843cfabe2a7
+  data.tar.gz: '02693bdcc7d21572494ffa3f7e4a7e7ecaa558601951590f6c348c97c892ead3'
 SHA512:
-  metadata.gz: 4074d5dd87f1ad9286f4022ad46a4160f44c6afed2341f9115029770770ae80b248ace9a8d5df0e444046bed662f9aa5a9334822b23222abec9574523d9e7c36
-  data.tar.gz: a69837921f7581d2aeb9226d0791b4b0dd5925a9f83e9cb4cee4dbaf43af33e6a7a570292650a14006ffc9d1759f2ea4ef268381e5aa63fc6da5c1a6d38f46a7
+  metadata.gz: ae3845f040bff4089ba8e4b2df1e22c10ddea1019475e4525b89fdf3889ffd904f98c72162cfe451ff7cfbe2f697e9462d5b2efe4a4144fdfa34568343c51f2c
+  data.tar.gz: 26755a0cc78cd490e7013f548ed8b46999629995109986f4ee474fff430fd77913888e6172512630118a2b99ef14546a3e94a38681ff66ac9b80482f7504351b

data/CHANGELOG

@@ -1,3 +1,6 @@
+v2.2.1 (27th July 2019)
+- Improve utf8 text extraction from CMaps that contain surrogate pair ligatures
+
 v2.2.0 (18th December 2018)
 - Support additional XRef Stream variants (thanks Stefan Wienert)
 - Add frozen_strings pragma to reduce object allocations on ruby 2.3+

data/lib/pdf/reader/cmap.rb

@@ -98,23 +98,24 @@ class PDF::Reader
 
     def str_to_int(str)
       return nil if str.nil? || str.size == 0
-      unpacked_string = if str.size == 1 # UTF-8
+      unpacked_string = if str.bytesize == 1 # UTF-8
         str.unpack("C*")
       else # UTF-16
          str.unpack("n*")
       end
-      if unpacked_string.size == 1
-        unpacked_string
-      elsif unpacked_string.size == 2 && unpacked_string[0] > 0xD800 && unpacked_string[0] < 0xDBFF
-        # this is a Unicode UTF-16 "Surrogate Pair" see Unicode Spec. Chapter 3.7
-        # lets convert to a UTF-32. (the high bit is between 0xD800-0xDBFF, the
-        # low bit is between 0xDC00-0xDFFF) for example: U+1D44E (U+D835 U+DC4E)
-        [(unpacked_string[0] - 0xD800) * 0x400 + (unpacked_string[1] - 0xDC00) + 0x10000]
-      else
-        # it is a bad idea to just return the first 16 bits, as this doesn't allow
-        # for ligatures for example fi (U+0066 U+0069)
-        unpacked_string
+      result = []
+      while unpacked_string.any? do
+        if unpacked_string.size >= 2 && unpacked_string[0] > 0xD800 && unpacked_string[0] < 0xDBFF
+          # this is a Unicode UTF-16 "Surrogate Pair" see Unicode Spec. Chapter 3.7
+          # lets convert to a UTF-32. (the high bit is between 0xD800-0xDBFF, the
+          # low bit is between 0xDC00-0xDFFF) for example: U+1D44E (U+D835 U+DC4E)
+          points = [unpacked_string.shift, unpacked_string.shift]
+          result << (points[0] - 0xD800) * 0x400 + (points[1] - 0xDC00) + 0x10000
+        else
+          result << unpacked_string.shift
+        end
       end
+      result
     end
 
     def process_bfchar_instructions(instructions)

data/lib/pdf/reader/orientation_detector.rb

@@ -25,9 +25,9 @@ class PDF::Reader
       width           = urx.to_i - llx.to_i
       height          = ury.to_i - lly.to_i
       if width > height
-        [0,180].include?(rotation) ? 'landscape' : 'portrait'
+        (rotation % 180).zero? ? 'landscape' : 'portrait'
       else
-        [0,180].include?(rotation) ? 'portrait' : 'landscape'
+        (rotation % 180).zero? ? 'portrait' : 'landscape'
       end
     end
   end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: pdf-reader
 version: !ruby/object:Gem::Version
-  version: 2.2.0
+  version: 2.2.1
 platform: ruby
 authors:
 - James Healy
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-12-18 00:00:00.000000000 Z
+date: 2019-07-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -167,7 +167,7 @@ dependencies:
 description: The PDF::Reader library implements a PDF parser conforming as much as
   possible to the PDF specification from Adobe
 email:
-- jimmy@deefa.com
+- james@yob.id.au
 executables:
 - pdf_object
 - pdf_text
@@ -295,8 +295,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.6
+rubygems_version: 3.0.1
 signing_key: 
 specification_version: 4
 summary: A library for accessing the content of PDF files