Handles doctype more freely (#56)

- Support ERB-tags before DOCTYPE. - Parse error on multiple DOCTYPE elements.
davidwessman · Aug 20, 2023 · cf23af0 · cf23af0
1 parent 375d720
commit cf23af0
Show file tree

Hide file tree

Showing 5 changed files with 36 additions and 8 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -6,6 +6,12 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/) a
 
 ## [Unreleased]
 
+## [0.10.1] - 2023-08-20
+
+### Added
+
+- Allow `DOCTYPE` to be after other tags, to work with e.g. ERB-tags on first line.
+
 ## [0.10.0] - 2023-08-20
 
 - Changes how whitespace and newlines are handled.
@@ -70,7 +76,8 @@ Output:
 - Can format a lot of .html.erb-syntax and works as a plugin to syntax_tree.
 - This is still early and there are a lot of different weird syntaxes out there.
 
-[unreleased]: https://github.com/davidwessman/syntax_tree-erb/compare/v0.10.0...HEAD
+[unreleased]: https://github.com/davidwessman/syntax_tree-erb/compare/v0.10.1...HEAD
+[0.10.1]: https://github.com/davidwessman/syntax_tree-erb/compare/v0.10.0...v0.10.1
 [0.10.0]: https://github.com/davidwessman/syntax_tree-erb/compare/v0.9.5...v0.10.0
 [0.9.5]: https://github.com/davidwessman/syntax_tree-erb/compare/v0.9.4...v0.9.5
 [0.9.4]: https://github.com/davidwessman/syntax_tree-erb/compare/v0.9.3...v0.9.4

diff --git a/Gemfile.lock b/Gemfile.lock
@@ -1,7 +1,7 @@
 PATH
  remote: .
  specs:
- w_syntax_tree-erb (0.10.0)
+ w_syntax_tree-erb (0.10.1)
  prettier_print (~> 1.2, >= 1.2.0)
  syntax_tree (~> 6.1, >= 6.1.1)
 

diff --git a/lib/syntax_tree/erb/parser.rb b/lib/syntax_tree/erb/parser.rb
@@ -20,16 +20,16 @@ class MissingTokenError < ParseError
  def initialize(source)
  @source = source
  @tokens = make_tokens
+ @found_doctype = false
  end
 
  def parse
- doctype = maybe { parse_doctype }
  elements = many { parse_any_tag }
 
  location =
  elements.first.location.to(elements.last.location) if elements.any?
 
- Document.new(elements: [doctype].compact + elements, location: location)
+ Document.new(elements: elements, location: location)
  end
 
  def debug_tokens
@@ -44,11 +44,19 @@ def parse_any_tag
  loop do
  tag =
  atleast do
- maybe { parse_html_comment } || maybe { parse_erb_tag } ||
- maybe { parse_erb_comment } || maybe { parse_html_element } ||
- maybe { parse_new_line } || maybe { parse_chardata }
+ maybe { parse_doctype } || maybe { parse_html_comment } ||
+ maybe { parse_erb_tag } || maybe { parse_erb_comment } ||
+ maybe { parse_html_element } || maybe { parse_new_line } ||
+ maybe { parse_chardata }
  end
 
+ if tag.is_a?(Doctype)
+ if @found_doctype
+ raise(ParseError, "Only one doctype element is allowed")
+ else
+ @found_doctype = true
+ end
+ end
  # Allow skipping empty CharData
  return tag unless tag.skip?
  end

diff --git a/lib/syntax_tree/erb/version.rb b/lib/syntax_tree/erb/version.rb
@@ -2,6 +2,6 @@
 
 module SyntaxTree
  module ERB
- VERSION = "0.10.0"
+ VERSION = "0.10.1"
  end
 end
diff --git a/test/html_test.rb b/test/html_test.rb
@@ -34,6 +34,19 @@ def test_html_doctype
 
  parsed = ERB.parse("<!doctype html>")
  assert_instance_of(SyntaxTree::ERB::Doctype, parsed.elements.first)
+
+ # Allow doctype to not be the first element
+ parsed = ERB.parse("<% theme = \"general\" %> <!DOCTYPE html>")
+ assert_equal(2, parsed.elements.size)
+ assert_equal(
+ [SyntaxTree::ERB::ErbNode, SyntaxTree::ERB::Doctype],
+ parsed.elements.map(&:class)
+ )
+
+ # Do not allow multiple doctype elements
+ assert_raises(SyntaxTree::ERB::Parser::ParseError) do
+ ERB.parse("<!DOCTYPE html>\n<!DOCTYPE html>\n")
+ end
  end
 
  def test_html_comment