plaintext 0.3.0 → 0.3.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: eb87c916a0f34e20251b5a97cbcf1e354fc046b0
-  data.tar.gz: e6dff85b7b0cec1ae3fdebbaabb950be1b563215
+  metadata.gz: 857600eeedad2b6b305655743d6dd4768faa5e5d
+  data.tar.gz: 17c78e4c90da3f07f5637c92a0891feb54b25b5b
 SHA512:
-  metadata.gz: 48be94f65a07c3e400bacfae575758494afbf3d6004b19a99f7838a032b26d4503ae3ea47b46548de0dd34b4892c551d5d7af3620a72375ae9a771afc0601cc2
-  data.tar.gz: 0b5dc9aa9abae205083d3dd4dcc89572bf36361fee098c6145472735ac6d10c810b07595be095565baa18b99534b61bbbc63b4e26c445ccdac94a3468b6c962c
+  metadata.gz: 436883566c3f9e1598a3f482c9146195646aa4e5d123aaedfe15876bb2876e93dd4c5bc964c515ece9b5f4e93b25974745bc176bd1aafb51aa4c64084221c7d5
+  data.tar.gz: 92969693830e20b3a1fb842bb9e60a5ed63a93f87903da8c7c88466df7a62e14dec0bb03f457ba7b28e3ce47bf82da3c9cc1a22fae4555a6cba6dce9ebc48405

data/CHANGELOG

@@ -6,6 +6,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.3.1] - 2019-01-16
+
+### Added
+- The max_plaintext_bytes limit introduced in 0.3.0 is now also enforced in the
+  zipped XML handlers responsible for office document parsing.
+
 ## [0.3.0] - 2019-01-09
 
 ### Added

data/lib/plaintext/file_handler/zipped_xml_handler.rb

@@ -9,16 +9,26 @@ module Plaintext
     class SaxDocument < Nokogiri::XML::SAX::Document
       attr_reader :text
 
-      def initialize(text_element, text_namespace)
+      def initialize(text_element, text_namespace, max_size = nil)
         @element = text_element
         @namespace_uri = text_namespace
+        @max_size = max_size
+
         @text = ''.dup
         @is_text = false
       end
 
+      def text_length_exceeded?
+        @max_size && (@text.length > @max_size)
+      end
+
+
       # Handle each element, expecting the name and any attributes
       def start_element_namespace(name, attrs = [], prefix = nil, uri = nil, ns = [])
-        if name == @element and uri == @namespace_uri
+        if name == @element and
+            uri == @namespace_uri and
+            !text_length_exceeded?
+
           @is_text = true
         end
       end
@@ -30,7 +40,10 @@ module Plaintext
 
       # Given the name of an element once its closing tag is reached
       def end_element_namespace(name, prefix = nil, uri = nil)
-        if name == @element and uri == @namespace_uri
+        if name == @element and
+            uri == @namespace_uri and
+            @is_text
+
           @text << ' '
           @is_text = false
         end
@@ -38,10 +51,11 @@ module Plaintext
     end
 
     def text(file, options = {})
+      max_size = options[:max_size]
       Zip::File.open(file) do |zip_file|
         zip_file.each do |entry|
           if entry.name == @file_name
-            return xml_to_text entry.get_input_stream
+            return xml_to_text entry.get_input_stream, max_size
           end
         end
       end
@@ -49,10 +63,11 @@ module Plaintext
 
     private
 
-    def xml_to_text(io)
-      sax_doc = SaxDocument.new @element, @namespace_uri
+    def xml_to_text(io, max_size)
+      sax_doc = SaxDocument.new @element, @namespace_uri, max_size
       Nokogiri::XML::SAX::Parser.new(sax_doc).parse(io)
-      sax_doc.text
+      text = sax_doc.text
+      max_size.present? ? text[0, max_size] : text
     end
   end
 end

data/lib/plaintext/file_handler/zipped_xml_handler/office_document_handler/pptx_handler.rb

@@ -15,16 +15,23 @@ module Plaintext
     end
 
     def text(file, options = {})
+      max_size = options[:max_size]
       slides = []
+      result = ''.dup
       Zip::File.open(file) do |zip_file|
         zip_file.each do |entry|
           if entry.name =~ /slide(\d+)\.xml/
-            slides << [$1, xml_to_text(entry.get_input_stream)]
+            slides << [$1, entry]
           end
         end
+
+        slides.sort!{|a, b| a.first <=> b.first}
+        slides.each do |id, entry|
+          result << xml_to_text(entry.get_input_stream, max_size)
+          break if max_size and result.length >= max_size
+        end
       end
-      slides.sort!{|a, b| a.first <=> b.first}
-      slides.map(&:last).join ' '
+      return result
     end
   end
 end

data/lib/plaintext/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Plaintext
-  VERSION = "0.3.0"
+  VERSION = "0.3.1"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: plaintext
 version: !ruby/object:Gem::Version
-  version: 0.3.0
+  version: 0.3.1
 platform: ruby
 authors:
 - Jens Krämer
@@ -10,7 +10,7 @@ authors:
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2019-01-09 00:00:00.000000000 Z
+date: 2019-01-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rubyzip
@@ -155,7 +155,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.5.2.1
+rubygems_version: 2.4.5.5
 signing_key: 
 specification_version: 4
 summary: Extract plain text from most common office documents.