html_tokenizer 0.0.5 → 0.0.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: a45a481e7310c22092c48de49f62315d7ae19700
-  data.tar.gz: fda14319ce3a8b6770c074b68384e3c7e16d3fa7
+  metadata.gz: cf47920a7a89b9806ac9b1e830b6965e2ec0e98e
+  data.tar.gz: 97dbc221ee255a3d6a9d17f20e1807cdddec3eb3
 SHA512:
-  metadata.gz: b55f2ae076aa4cbf3b55fca42435bcfa63ec4e9e032a91ad55260cf0b6cc74ae75b484b0c7ad70cb08a6bf3fe75d9499feec9df768f85fdac2fdfe29cc8262ca
-  data.tar.gz: 8e3726c0471524c66270d8ed187a807b5c6bf906312e754c69e0e4da915db46ee28729f0400347413ddaf147c48a21fd4d628454e01f09eec2a104ace6452d17
+  metadata.gz: e9865b029658f9ad0186863319ecbb9a9d62f7de43b7763c91f455848c79cfd0fed2008f5f86d7b79b5434a97b547464716e5a9ebb67ac6248ceec5b8c85cd4a
+  data.tar.gz: 0c092d6501187b4eff8d0981831b3df3a25b957516c138b7989ae57c92c139ade5952a90df7f80ed928252c724de9cc2bc37d0921540d4da0d1bd13faf6462aa

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    html_tokenizer (0.0.5)
+    html_tokenizer (0.0.6)
 
 GEM
   remote: https://rubygems.org/

data/ext/html_tokenizer_ext/parser.c

@@ -82,6 +82,8 @@ static void parser_add_error(struct parser_t *parser, const char *message)
 {
   REALLOC_N(parser->errors, struct parser_document_error_t, parser->errors_count + 1);
   parser->errors[parser->errors_count].message = strdup(message);
+  parser->errors[parser->errors_count].pos = parser->tk.scan.cursor;
+  parser->errors[parser->errors_count].mb_pos = parser->tk.scan.mb_cursor;
   parser->errors[parser->errors_count].line_number = parser->doc.line_number;
   parser->errors[parser->errors_count].column_number = parser->doc.column_number;
   parser->errors_count += 1;
@@ -723,12 +725,13 @@ static VALUE create_parser_error(struct parser_document_error_t *error)
 {
   VALUE module = rb_const_get(rb_cObject, rb_intern("HtmlTokenizer"));
   VALUE klass = rb_const_get(module, rb_intern("ParserError"));
-  VALUE args[3] = {
+  VALUE args[4] = {
     rb_str_new2(error->message),
+    ULONG2NUM(error->mb_pos),
     ULONG2NUM(error->line_number),
     ULONG2NUM(error->column_number),
   };
-  return rb_class_new_instance(3, args, klass);
+  return rb_class_new_instance(4, args, klass);
 }
 
 static VALUE parser_errors_method(VALUE self, VALUE error_p)

data/ext/html_tokenizer_ext/parser.h

@@ -19,6 +19,8 @@ enum parser_context {
 
 struct parser_document_error_t {
   char *message;
+  long unsigned int pos;
+  long unsigned int mb_pos;
   long unsigned int line_number;
   long unsigned int column_number;
 };

data/html_tokenizer.gemspec

@@ -1,6 +1,6 @@
 Gem::Specification.new do |spec|
   spec.name    = "html_tokenizer"
-  spec.version = "0.0.5"
+  spec.version = "0.0.6"
   spec.summary = "HTML Tokenizer"
   spec.author  = "Francois Chagnon"
 

data/lib/html_tokenizer.rb

@@ -2,9 +2,10 @@ require 'html_tokenizer_ext'
 
 module HtmlTokenizer
   class ParserError < RuntimeError
-    attr_reader :line, :column
-    def initialize(message, line, column)
+    attr_reader :position, :line, :column
+    def initialize(message, position, line, column)
       super(message)
+      @position = position
       @line = line
       @column = column
     end

data/test/unit/parser_test.rb

@@ -437,6 +437,7 @@ class HtmlTokenizer::ParserTest < Minitest::Test
     parse('<>')
     assert_equal 1, @parser.errors_count
     assert_equal "expected '/' or tag name", @parser.errors.first.to_s
+    assert_equal 1, @parser.errors.first.position
     assert_equal 1, @parser.errors.first.line
     assert_equal 1, @parser.errors.first.column
   end
@@ -445,6 +446,7 @@ class HtmlTokenizer::ParserTest < Minitest::Test
     parse('< ')
     assert_equal 1, @parser.errors_count
     assert_equal "expected '/' or tag name", @parser.errors.first.to_s
+    assert_equal 1, @parser.errors.first.position
     assert_equal 1, @parser.errors.first.line
     assert_equal 1, @parser.errors.first.column
   end
@@ -453,6 +455,7 @@ class HtmlTokenizer::ParserTest < Minitest::Test
     parse('<foo =')
     assert_equal 1, @parser.errors_count
     assert_equal "expected whitespace, '>', attribute name or value", @parser.errors.first.to_s
+    assert_equal 5, @parser.errors.first.position
     assert_equal 1, @parser.errors.first.line
     assert_equal 5, @parser.errors.first.column
   end
@@ -461,6 +464,7 @@ class HtmlTokenizer::ParserTest < Minitest::Test
     parse('<foo /x')
     assert_equal 1, @parser.errors_count
     assert_equal "expected '>' after '/'", @parser.errors.first.to_s
+    assert_equal 6, @parser.errors.first.position
     assert_equal 1, @parser.errors.first.line
     assert_equal 6, @parser.errors.first.column
   end
@@ -469,6 +473,7 @@ class HtmlTokenizer::ParserTest < Minitest::Test
     parse('<foo / ')
     assert_equal 1, @parser.errors_count
     assert_equal "expected '>' after '/'", @parser.errors.first.to_s
+    assert_equal 6, @parser.errors.first.position
     assert_equal 1, @parser.errors.first.line
     assert_equal 6, @parser.errors.first.column
   end
@@ -476,29 +481,33 @@ class HtmlTokenizer::ParserTest < Minitest::Test
   def test_attribute_name_error
     parse('<foo bar~')
     assert_equal 2, @parser.errors_count
-    assert_equal "expected whitespace, '>' or '=' after attribute name", @parser.errors.first.to_s
-    assert_equal 1, @parser.errors.first.line
-    assert_equal 8, @parser.errors.first.column
     assert_equal "expected whitespace, '>' or '=' after attribute name", @parser.errors[0].to_s
+    assert_equal 8, @parser.errors.first.position
     assert_equal 1, @parser.errors[0].line
     assert_equal 8, @parser.errors[0].column
+    assert_equal "expected whitespace, '>', attribute name or value", @parser.errors[1].to_s
+    assert_equal 8, @parser.errors.first.position
+    assert_equal 1, @parser.errors[1].line
+    assert_equal 8, @parser.errors[1].column
   end
 
   def test_attribute_whitespace_or_equal_error
     parse('<foo bar ~')
     assert_equal 2, @parser.errors_count
-    assert_equal "expected '/', '>', \", ' or '=' after attribute name", @parser.errors.first.to_s
-    assert_equal 1, @parser.errors.first.line
-    assert_equal 9, @parser.errors.first.column
     assert_equal "expected '/', '>', \", ' or '=' after attribute name", @parser.errors[0].to_s
     assert_equal 1, @parser.errors[0].line
     assert_equal 9, @parser.errors[0].column
+    assert_equal "expected whitespace, '>', attribute name or value", @parser.errors[1].to_s
+    assert_equal 9, @parser.errors.first.position
+    assert_equal 1, @parser.errors[1].line
+    assert_equal 9, @parser.errors[1].column
   end
 
   def test_attribute_whitespace_or_equal_error_2
     parse('<foo bar = >')
     assert_equal 1, @parser.errors_count
     assert_equal "expected attribute value after '='", @parser.errors.first.to_s
+    assert_equal 11, @parser.errors.first.position
     assert_equal 1, @parser.errors.first.line
     assert_equal 11, @parser.errors.first.column
   end
@@ -507,6 +516,7 @@ class HtmlTokenizer::ParserTest < Minitest::Test
     parse('<foo bar=""x')
     assert_equal 1, @parser.errors_count
     assert_equal "expected space after attribute value", @parser.errors.first.to_s
+    assert_equal 11, @parser.errors.first.position
     assert_equal 1, @parser.errors.first.line
     assert_equal 11, @parser.errors.first.column
   end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: html_tokenizer
 version: !ruby/object:Gem::Version
-  version: 0.0.5
+  version: 0.0.6
 platform: ruby
 authors:
 - Francois Chagnon
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-11-23 00:00:00.000000000 Z
+date: 2018-01-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -100,7 +100,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.6.8
+rubygems_version: 2.6.14
 signing_key: 
 specification_version: 4
 summary: HTML Tokenizer