xlsxtream 0.3.0 → 0.3.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 9f6d507fcaf88af59b20094f992ba4e921ca610b
-  data.tar.gz: 81f6f7d9a0312be08a7e394ef2e27be1f5f51a09
+  metadata.gz: 3059ae91a1d37f8af53f001f209956b099020ffe
+  data.tar.gz: 14cdbda940cfd0f71cb426c1c646b4434dddff7a
 SHA512:
-  metadata.gz: 2890495ed08670099470e514836ee399481bdd261e12207a3df454be1e4e7ef6a8489e2b2b662f7cb3286dc5cb82af7c5fa5354b4e801847a95b0307812e008e
-  data.tar.gz: 19f3812cdb16465b87e86c1aa2ff78605092729cd1fdbd767ae64abe3ba4cbea57d1ad63e5b1760c4a2bf5015a1629a5cb3834c9cafee6c33836a058f004a803
+  metadata.gz: 5894ce04ab5f8720e2da65e09de45a5d20b8c4df0f260e94cf2db1ec025b05832e69e8dce6edf1d6a9a938ea089408063dacf026f9185992a24c8e69a73847a5
+  data.tar.gz: 762faa3c9c0b2c29aacf150ed1610ae6af0badd373f770d33f348ac3bbd9dceaa98cbf98ff6ee35b6422fc554cbce4eb7729deb3887a392989c38b73be6bc10f

data/CHANGELOG.md

@@ -1,5 +1,9 @@
 # Changelog
 
+## 0.3.1 (2017-10-22)
+
+- Escape invalid XML 1.0 characters (#11)
+
 ## 0.3.0 (2017-07-12)
 
 - Add support for auto-formatting

data/README.md

@@ -1,5 +1,8 @@
 # Xlsxtream
 
+[![Gem Version](https://badge.fury.io/rb/xlsxtream.svg)](https://rubygems.org/gems/xlsxtream)
+[![Build Status](https://travis-ci.org/felixbuenemann/xlsxtream.svg)](https://travis-ci.org/felixbuenemann/xlsxtream)
+
 Xlsxtream is a streaming writer for XLSX spreadsheets. It supports multiple worksheets and optional string
 deduplication via a shared string table (SST). Its purpose is to replace CSV for large exports, because using
 CSV in Excel is very buggy and error prone. It's very efficient and can quickly write millions of rows with

data/lib/xlsxtream/io/hash.rb

@@ -0,0 +1,46 @@
+module Xlsxtream
+  module IO
+    class Hash
+      def initialize(stream)
+        @stream = stream
+        @hash = {}
+        @path = nil
+      end
+
+      def <<(data)
+        @stream << data
+      end
+
+      def add_file(path)
+        close
+        @path = path
+        @hash[@path] = [@stream.tell]
+      end
+
+      def close
+        @hash[@path] << @stream.tell if @path
+      end
+
+      def fetch(path)
+        old = @stream.tell
+        from, to = @hash.fetch(path)
+        size = to - from
+        @stream.seek(from)
+        data = @stream.read(size)
+        @stream.seek(old)
+        data
+      end
+
+      def [](path)
+        fetch(path)
+      rescue KeyError
+        nil
+      end
+
+      def to_h
+        @hash.keys.map {|path| [path, fetch(path)] }.to_h
+      end
+    end
+  end
+end
+

data/lib/xlsxtream/version.rb

@@ -1,3 +1,3 @@
 module Xlsxtream
-  VERSION = "0.3.0"
+  VERSION = "0.3.1"
 end

data/lib/xlsxtream/xml.rb

@@ -14,6 +14,13 @@ module Xlsxtream
     UNSAFE_ATTR_CHARS = /[&"<>]/.freeze
     UNSAFE_VALUE_CHARS = /[&<>]/.freeze
 
+    # http://www.w3.org/TR/REC-xml/#NT-Char:
+    # Char ::= #x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF]
+    INVALID_XML10_CHARS = /[^\x09\x0A\x0D\x20-\uD7FF\uE000-\uFFFD\u10000-\u10FFFF]/.freeze
+
+    # ST_Xstring escaping
+    ESCAPE_CHAR = lambda { |c| '_x%04X_'.freeze % c.ord }.freeze
+
     class << self
 
       def header
@@ -29,7 +36,7 @@ module Xlsxtream
       end
 
       def escape_value(string)
-        string.gsub(UNSAFE_VALUE_CHARS, XML_ESCAPES)
+        string.gsub(UNSAFE_VALUE_CHARS, XML_ESCAPES).gsub(INVALID_XML10_CHARS, &ESCAPE_CHAR)
       end
 
     end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: xlsxtream
 version: !ruby/object:Gem::Version
-  version: 0.3.0
+  version: 0.3.1
 platform: ruby
 authors:
 - Felix Bünemann
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2017-09-14 00:00:00.000000000 Z
+date: 2017-10-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rubyzip
@@ -99,6 +99,7 @@ files:
 - bin/setup
 - lib/xlsxtream.rb
 - lib/xlsxtream/io/directory.rb
+- lib/xlsxtream/io/hash.rb
 - lib/xlsxtream/io/rubyzip.rb
 - lib/xlsxtream/io/stream.rb
 - lib/xlsxtream/row.rb