Create a Liquid::Tokenizer class in the C extension.

This commit is contained in:
Dylan Thacker-Smith
2014-02-27 15:20:22 -05:00
parent 8bb3bca64a
commit ea8406e36e
9 changed files with 220 additions and 34 deletions
-20
View File
@@ -25,26 +25,6 @@ end
class TemplateTest < Test::Unit::TestCase
include Liquid
def test_tokenize_strings
assert_equal [' '], Template.new.send(:tokenize, ' ')
assert_equal ['hello world'], Template.new.send(:tokenize, 'hello world')
end
def test_tokenize_variables
assert_equal ['{{funk}}'], Template.new.send(:tokenize, '{{funk}}')
assert_equal [' ', '{{funk}}', ' '], Template.new.send(:tokenize, ' {{funk}} ')
assert_equal [' ', '{{funk}}', ' ', '{{so}}', ' ', '{{brother}}', ' '], Template.new.send(:tokenize, ' {{funk}} {{so}} {{brother}} ')
assert_equal [' ', '{{ funk }}', ' '], Template.new.send(:tokenize, ' {{ funk }} ')
end
def test_tokenize_blocks
assert_equal ['{%comment%}'], Template.new.send(:tokenize, '{%comment%}')
assert_equal [' ', '{%comment%}', ' '], Template.new.send(:tokenize, ' {%comment%} ')
assert_equal [' ', '{%comment%}', ' ', '{%endcomment%}', ' '], Template.new.send(:tokenize, ' {%comment%} {%endcomment%} ')
assert_equal [' ', '{% comment %}', ' ', '{% endcomment %}', ' '], Template.new.send(:tokenize, " {% comment %} {% endcomment %} ")
end
def test_instance_assigns_persist_on_same_template_object_between_parses
t = Template.new
assert_equal 'from instance assigns', t.parse("{% assign foo = 'from instance assigns' %}{{ foo }}").render
+64
View File
@@ -0,0 +1,64 @@
require 'test_helper'
class TokenizerTest < Test::Unit::TestCase
def test_tokenize_strings
assert_equal [' '], tokenize(' ')
assert_equal ['hello world'], tokenize('hello world')
end
def test_tokenize_variables
assert_equal ['{{funk}}'], tokenize('{{funk}}')
assert_equal [' ', '{{funk}}', ' '], tokenize(' {{funk}} ')
assert_equal [' ', '{{funk}}', ' ', '{{so}}', ' ', '{{brother}}', ' '], tokenize(' {{funk}} {{so}} {{brother}} ')
assert_equal [' ', '{{ funk }}', ' '], tokenize(' {{ funk }} ')
end
def test_tokenize_blocks
assert_equal ['{%comment%}'], tokenize('{%comment%}')
assert_equal [' ', '{%comment%}', ' '], tokenize(' {%comment%} ')
assert_equal [' ', '{%comment%}', ' ', '{%endcomment%}', ' '], tokenize(' {%comment%} {%endcomment%} ')
assert_equal [' ', '{% comment %}', ' ', '{% endcomment %}', ' '], tokenize(" {% comment %} {% endcomment %} ")
end
def test_tokenize_incomplete_end
assert_tokens 'before{{ incomplete }after', ['before', '{{ incomplete }', 'after']
assert_tokens 'before{% incomplete %after', ['before', '{%', ' incomplete %after']
end
def test_tokenize_no_end
assert_tokens 'before{{ unterminated ', ['before', '{{', ' unterminated ']
assert_tokens 'before{% unterminated ', ['before', '{%', ' unterminated ']
end
private
def assert_tokens(source, expected)
assert_equal expected, tokenize(source)
assert_equal expected, old_tokenize(source)
end
def tokenize(source)
tokenizer = Liquid::Tokenizer.new(source)
tokens = []
while token = tokenizer.next
tokens << token
end
tokens
end
AnyStartingTag = /\{\{|\{\%/
VariableIncompleteEnd = /\}\}?/
PartialTemplateParser = /#{Liquid::TagStart}.*?#{Liquid::TagEnd}|#{Liquid::VariableStart}.*?#{VariableIncompleteEnd}/o
TemplateParser = /(#{PartialTemplateParser}|#{AnyStartingTag})/o
def old_tokenize(source)
return [] if source.to_s.empty?
tokens = source.split(TemplateParser)
# removes the rogue empty element at the beginning of the array
tokens.shift if tokens[0] and tokens[0].empty?
tokens
end
end