saxy 0.7.0 → 0.7.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 145b19ea70344eb97cb37dab58b172d07766a654
-  data.tar.gz: 9b0a3482befc1f5270f8bfe5665a68b4cc0a87f4
+  metadata.gz: 52a8b74342fe631ae2787bd38fedcb3600b24730
+  data.tar.gz: 37ef8a7e143494b48ba13c3d7470c84e459d0bf7
 SHA512:
-  metadata.gz: 229a5ceede847656383a9b86a8521d17030c97329233cc36a0a32f6beceb2efcacff06a9e2d030a05c81014f41b9dc3f7c31f83b5cbce933827136149e48bab8
-  data.tar.gz: dd980f2f3fc39731e19776316bde8f16abb8f28be32d7f036cfca65db6867fa7dd1d7362360a96e3759b2f389a6e48e6aa3ab88df568ebfb3334174e9492af6c
+  metadata.gz: 468d1551a3fdafc0c0b37cdffb5482f1ecd5cf2fac2c8f63b23c7d75dc38c1d13b47ac8a7d195b8031251d62a5ea13492674cf418f25cf732d30e073a8f99f9b
+  data.tar.gz: d026bfaa8643b1eeb12ce00eecc13e4f1d27e531308706e14d05f1a9bc2d22755a5e2479482d5024ce298732373ea62498314d083fe4a2fa2aa8e5da3399c6a9

data/.travis.yml

@@ -2,6 +2,7 @@ script: "bundle exec rspec ./spec/"
 sudo: false
 language: ruby
 rvm:
+  - 2.5
   - 2.4
   - 2.3
   - 2.2

data/CHANGELOG.md

@@ -1,5 +1,10 @@
 # Saxy Changelog
 
+## 0.7.1
+
+* Fixed whitespace stripping from elements' contents, now only leading and trailing whitespace is stripped (reported by @wzcolon, thanks!).
+* Added `error_handler` option to make it possible to handle errors on-the-fly instead of raising them.
+
 ## 0.7.0
 
 * [BREAKING] Yielded hashes now have strings as keys instead of symbols (performance and security fix).

data/README.md

@@ -64,6 +64,14 @@ end
 * `encoding` - Forces the parser to work in given encoding
 * `recovery` - Should this parser recover from structural errors? It will not stop processing file on structural errors if set to `true`.
 * `replace_entities` - Should this parser replace entities? `&` will get converted to `&` if set to `true`.
+* `error_handler` - If set to a callable, parser will call it with any error it encounters instead of raising exceptions.
+
+Combination of `error_handler` and `recovery` options allows for continued processing when encountering recoverable errors (e.g. unescaped [predefined entities](https://en.wikipedia.org/wiki/List_of_XML_and_HTML_character_entity_references#Predefined_entities_in_XML)).
+
+```ruby
+error_handler = proc { |e| $stderr.puts "#{e.message} at line #{e.context.line}, column #{e.context.column}." }
+Saxy.parse(path_or_io, object_tag, error_handler: error_handler, recovery: true) { ... }
+```
 
 ## Example
 

data/lib/saxy/element.rb

@@ -1,6 +1,6 @@
 module Saxy
   class Element
-    attr_reader :attributes, :value
+    attr_reader :attributes
 
     def initialize
       @attributes = {}
@@ -9,23 +9,30 @@ module Saxy
 
     def set_attribute(name, value)
       name = attribute_name(name)
+
       attributes[name] ||= []
       attributes[name] << value
     end
 
     def append_value(string)
-      unless (string = string.strip).empty?
+      if @value || !string.strip.empty?
         @value ||= ""
         @value << string
       end
     end
 
+    def value
+      @value && @value.strip
+    end
+
     def to_h
       return value unless attributes.any?
+
       data = attributes.reduce({}) do |memo, (name, value)|
         memo[name] = value.size == 1 ? value.first : value
         memo
       end
+
       data["contents"] = value
       data
     end
@@ -37,12 +44,11 @@ module Saxy
     private
 
     def underscore(word)
-      word = word.dup
-      word.gsub!(/([A-Z\d]+)([A-Z][a-z])/, '\1_\2')
-      word.gsub!(/([a-z\d])([A-Z])/, '\1_\2')
-      word.tr!("-", "_")
-      word.downcase!
       word
+        .gsub(/([A-Z\d]+)([A-Z][a-z])/, '\1_\2')
+        .gsub(/([a-z\d])([A-Z])/, '\1_\2')
+        .tr("-", "_")
+        .downcase
     end
   end
 end

data/lib/saxy/parser.rb

@@ -41,6 +41,7 @@ module Saxy
 
     def end_element(tag)
       tags.pop
+
       if element = elements.pop
         object = element.to_h
 
@@ -61,7 +62,13 @@ module Saxy
     end
 
     def error(message)
-      raise ParsingError.new(message, context)
+      error = ParsingError.new(message, context)
+
+      if options[:error_handler].respond_to?(:call)
+        options[:error_handler].call(error)
+      else
+        raise error
+      end
     end
 
     def current_element
@@ -73,8 +80,7 @@ module Saxy
 
       @callback = blk
 
-      args = [self, options[:encoding]].compact
-
+      args   = [self, options[:encoding]].compact
       parser = Nokogiri::XML::SAX::Parser.new(*args)
 
       if @object.respond_to?(:read) && @object.respond_to?(:close)

data/lib/saxy/version.rb

@@ -1,3 +1,3 @@
 module Saxy
-  VERSION = "0.7.0"
+  VERSION = "0.7.1"
 end

data/spec/fixtures/invalid.xml

@@ -3,7 +3,7 @@
   <products>
     <product>
       <uid>FFCF177</uid>
-      <name>No closing tag...
+      <name>Unescaped & ampersand</name>
     </product>
   </products>
 </webstore>

data/spec/saxy/element_spec.rb

@@ -8,10 +8,12 @@ describe Saxy::Element do
     expect(element.value).to be_nil
   end
 
-  it "should append stripped value" do
-    element.append_value(" foo ")
-    element.append_value(" bar ")
-    expect(element.value).to eq("foobar")
+  it "should strip leading and trailing whitespace" do
+    element.append_value(" one two ")
+    element.append_value("&")
+    element.append_value(" three\nfour")
+    element.append_value("\t\t")
+    expect(element.value).to eq("one two & three\nfour")
   end
 
   it "should dump as string when no attributes are set" do

data/spec/saxy/parser_spec.rb

@@ -4,7 +4,6 @@ describe Saxy::Parser do
   include FixturesHelper
 
   let(:parser) { Saxy::Parser.new(fixture_file("webstore.xml"), "product") }
-  let(:invalid_parser) { Saxy::Parser.new(fixture_file("invalid.xml"), "product") }
   let(:file_io) { File.new(fixture_file("webstore.xml")) }
   let(:io_like) { IOLike.new(file_io) }
 
@@ -165,12 +164,26 @@ describe Saxy::Parser do
     end
   end
 
-  it "should raise Saxy::ParsingError on error" do
-    expect { invalid_parser.each.to_a }.to raise_error { |error|
-      expect(error).to be_a(Saxy::ParsingError)
-      expect(error.message).to match(/Opening and ending tag mismatch/)
-      expect(error.context).to be_a(Nokogiri::XML::SAX::ParserContext)
-    }
+  context "when error handler is not set" do
+    let(:parser) { Saxy::Parser.new(fixture_file("invalid.xml"), "product") }
+
+    it "should raise Saxy::ParsingError on error" do
+      expect { parser.each.to_a }.to raise_error { |error|
+        expect(error).to be_a(Saxy::ParsingError)
+        expect(error.message).to match(/xmlParseEntityRef: no name/)
+        expect(error.context).to be_a(Nokogiri::XML::SAX::ParserContext)
+      }
+    end
+  end
+
+  context "when error handler is set" do
+    let(:handler) { proc { |error| error } }
+    let(:parser) { Saxy::Parser.new(fixture_file("invalid.xml"), "product", error_handler: handler) }
+
+    it "should call error handler passing Saxy::ParsingError instance" do
+      expect(handler).to receive(:call).with(Saxy::ParsingError)
+      parser.each.to_a
+    end
   end
 
   it "should return Enumerator when calling #each without a block" do

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: saxy
 version: !ruby/object:Gem::Version
-  version: 0.7.0
+  version: 0.7.1
 platform: ruby
 authors:
 - Michał Szajbe
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-11-04 00:00:00.000000000 Z
+date: 2018-04-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri