Add doctype case-sensitive tests and update case-insensitive peek helpers

marcoroth · marcoroth · commit a6e4e04a461f · 2025-02-17T23:04:38.000+01:00
diff --git a/src/lexer_peek_helpers.c b/src/lexer_peek_helpers.c
@@ -32,23 +32,23 @@ bool lexer_peek_for_doctype(lexer_T* lexer, int offset) {
 }
 
 bool lexer_peek_for_html_comment_start(lexer_T* lexer, int offset) {
-  return lexer_peek_for(lexer, offset, "<!--", true);
+  return lexer_peek_for(lexer, offset, "<!--", false);
 }
 
 bool lexer_peek_for_html_comment_end(lexer_T* lexer, int offset) {
-  return lexer_peek_for(lexer, offset, "-->", true);
+  return lexer_peek_for(lexer, offset, "-->", false);
 }
 
 bool lexer_peek_erb_close_tag(lexer_T* lexer, int offset) {
-  return lexer_peek_for(lexer, offset, "%>", true);
+  return lexer_peek_for(lexer, offset, "%>", false);
 }
 
 bool lexer_peek_erb_dash_close_tag(lexer_T* lexer, int offset) {
-  return lexer_peek_for(lexer, offset, "-%>", true);
+  return lexer_peek_for(lexer, offset, "-%>", false);
 }
 
 bool lexer_peek_erb_percent_close_tag(lexer_T* lexer, int offset) {
-  return lexer_peek_for(lexer, offset, "%%>", true);
+  return lexer_peek_for(lexer, offset, "%%>", false);
 }
 
 bool lexer_peek_erb_end(lexer_T* lexer, int offset) {
diff --git a/test/lexer/doctype_test.rb b/test/lexer/doctype_test.rb
@@ -72,5 +72,19 @@ class DoctypeTest < Minitest::Spec
 
       assert_equal expected, result.array.items.map(&:type)
     end
+
+    test "doctype case insensitivity" do
+      doctypes = ["<!DOCTYPE>", "<!doctype>", "<!DoCtYpE>", "<!dOcTyPe>"]
+
+      expected = %w[
+        TOKEN_HTML_DOCTYPE
+        TOKEN_HTML_TAG_END
+        TOKEN_EOF
+      ]
+
+      doctypes.each do |doctype|
+        assert_equal expected, ERBX.lex(doctype).array.items.map(&:type), "#{doctype} didn't match"
+      end
+    end
   end
 end
diff --git a/test/parser/doctype_test.rb b/test/parser/doctype_test.rb
@@ -25,5 +25,13 @@ class DoctypeTest < Minitest::Spec
     test "html4 doctype" do
       assert_parsed_snapshot(%(<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd">))
     end
+
+    test "doctype case insensitivity" do
+      doctypes = ["<!DOCTYPE>", "<!doctype>", "<!DoCtYpE>", "<!dOcTyPe>"]
+
+      doctypes.each do |doctype|
+        assert_parsed_snapshot(doctype)
+      end
+    end
   end
 end
diff --git a/test/snapshots/parser/doctype_test/test_0006_doctype_case_insensitivity_2f56dc84fb5f8e284f42eae7d1f1c597.txt b/test/snapshots/parser/doctype_test/test_0006_doctype_case_insensitivity_2f56dc84fb5f8e284f42eae7d1f1c597.txt
diff --git a/test/snapshots/parser/doctype_test/test_0006_doctype_case_insensitivity_3e5902254c42ff2df6f6321086040dbe.txt b/test/snapshots/parser/doctype_test/test_0006_doctype_case_insensitivity_3e5902254c42ff2df6f6321086040dbe.txt
@@ -0,0 +1,7 @@
+@ DocumentNode (location: (0,0)-(0,0))
+├── name: ∅
+└── children: (1)
+    @ Doctype (location: (0,0)-(0,0))
+    ├── name: ""
+    └── children: []
+
diff --git a/test/snapshots/parser/doctype_test/test_0006_doctype_case_insensitivity_8bc9e797250fadb2f5af79f38cf7d74e.txt b/test/snapshots/parser/doctype_test/test_0006_doctype_case_insensitivity_8bc9e797250fadb2f5af79f38cf7d74e.txt
@@ -0,0 +1,7 @@
+@ DocumentNode (location: (0,0)-(0,0))
+├── name: ∅
+└── children: (1)
+    @ Doctype (location: (0,0)-(0,0))
+    ├── name: ""
+    └── children: []
+
diff --git a/test/snapshots/parser/doctype_test/test_0006_doctype_case_insensitivity_d50c7b32f19e4848938905f3dc675f44.txt b/test/snapshots/parser/doctype_test/test_0006_doctype_case_insensitivity_d50c7b32f19e4848938905f3dc675f44.txt
@@ -0,0 +1,7 @@
+@ DocumentNode (location: (0,0)-(0,0))
+├── name: ∅
+└── children: (1)
+    @ Doctype (location: (0,0)-(0,0))
+    ├── name: ""
+    └── children: []
+

Original file line number	Diff line number	Diff line change
`@@ -32,23 +32,23 @@ bool lexer_peek_for_doctype(lexer_T* lexer, int offset) {`
`32`	`32`	`}`
`33`	`33`
`34`	`34`	`bool lexer_peek_for_html_comment_start(lexer_T* lexer, int offset) {`
`35`		`- return lexer_peek_for(lexer, offset, "<!--", true);`
	`35`	`+ return lexer_peek_for(lexer, offset, "<!--", false);`
`36`	`36`	`}`
`37`	`37`
`38`	`38`	`bool lexer_peek_for_html_comment_end(lexer_T* lexer, int offset) {`
`39`		`- return lexer_peek_for(lexer, offset, "-->", true);`
	`39`	`+ return lexer_peek_for(lexer, offset, "-->", false);`
`40`	`40`	`}`
`41`	`41`
`42`	`42`	`bool lexer_peek_erb_close_tag(lexer_T* lexer, int offset) {`
`43`		`- return lexer_peek_for(lexer, offset, "%>", true);`
	`43`	`+ return lexer_peek_for(lexer, offset, "%>", false);`
`44`	`44`	`}`
`45`	`45`
`46`	`46`	`bool lexer_peek_erb_dash_close_tag(lexer_T* lexer, int offset) {`
`47`		`- return lexer_peek_for(lexer, offset, "-%>", true);`
	`47`	`+ return lexer_peek_for(lexer, offset, "-%>", false);`
`48`	`48`	`}`
`49`	`49`
`50`	`50`	`bool lexer_peek_erb_percent_close_tag(lexer_T* lexer, int offset) {`
`51`		`- return lexer_peek_for(lexer, offset, "%%>", true);`
	`51`	`+ return lexer_peek_for(lexer, offset, "%%>", false);`
`52`	`52`	`}`
`53`	`53`
`54`	`54`	`bool lexer_peek_erb_end(lexer_T* lexer, int offset) {`