Restore the tree construction tests used by the feedback tests.

.gitattributes

@@ -3,3 +3,6 @@
 tests/data/** linguist-vendored
 benches/data/** linguist-vendored
 fuzz/corpus/** linguist-vendored
+
+# Keep the tree construction tests byte-for-byte: some of them contain CR characters.
+tests/data/tree-construction/*.dat -text diff

tests/data/tree-construction/README.md

@@ -0,0 +1,25 @@
+# Tree construction tests
+
+These are the html5lib tree construction tests, copied from [html5lib-tests][html5lib-tests] at
+revision `9329e64694e7835d0dcff9811e22856ef6ad16f9`, the last one before they were removed from
+that repository. They are now maintained in [web-platform-tests][wpt] (WPT).
+
+We only use the inputs (the `#data` sections): the feedback tests compare our tokens against the
+ones html5ever produces for the same input. The scripted tests are not included (`scripted/` in
+html5lib-tests, `scripted_*.dat` in WPT), since they require script execution.
+
+To replace the files with the ones from WPT revision `$rev`, run this from the root of the
+repository (and update the source revision above):
+
+```sh
+url=https://raw.githubusercontent.com/web-platform-tests/wpt/$rev/html/syntax/parsing/resources
+rm tests/data/tree-construction/*.dat
+gh api "repos/web-platform-tests/wpt/contents/html/syntax/parsing/resources?ref=$rev" \
+    --jq '.[].name | select(endswith(".dat") and (startswith("scripted_") | not))' |
+    while read -r name; do
+        curl -sSfLo "tests/data/tree-construction/$name" "$url/$name"
+    done
+```
+
+[html5lib-tests]: https://github.com/html5lib/html5lib-tests
+[wpt]: https://github.com/web-platform-tests/wpt/tree/master/html/syntax/parsing/resources

tests/data/tree-construction/adoption01.dat

@@ -0,0 +1,354 @@
+#data
+<a><p></a></p>
+#errors
+(1,3): expected-doctype-but-got-start-tag
+(1,10): adoption-agency-1.3
+#document
+| <html>
+|   <head>
+|   <body>
+|     <a>
+|     <p>
+|       <a>
+
+#data
+<a>1<p>2</a>3</p>
+#errors
+(1,3): expected-doctype-but-got-start-tag
+(1,12): adoption-agency-1.3
+#document
+| <html>
+|   <head>
+|   <body>
+|     <a>
+|       "1"
+|     <p>
+|       <a>
+|         "2"
+|       "3"
+
+#data
+<a>1<button>2</a>3</button>
+#errors
+(1,3): expected-doctype-but-got-start-tag
+(1,17): adoption-agency-1.3
+#document
+| <html>
+|   <head>
+|   <body>
+|     <a>
+|       "1"
+|     <button>
+|       <a>
+|         "2"
+|       "3"
+
+#data
+<a>1<b>2</a>3</b>
+#errors
+(1,3): expected-doctype-but-got-start-tag
+(1,12): adoption-agency-1.3
+#document
+| <html>
+|   <head>
+|   <body>
+|     <a>
+|       "1"
+|       <b>
+|         "2"
+|     <b>
+|       "3"
+
+#data
+<a>1<div>2<div>3</a>4</div>5</div>
+#errors
+(1,3): expected-doctype-but-got-start-tag
+(1,20): adoption-agency-1.3
+(1,20): adoption-agency-1.3
+#document
+| <html>
+|   <head>
+|   <body>
+|     <a>
+|       "1"
+|     <div>
+|       <a>
+|         "2"
+|       <div>
+|         <a>
+|           "3"
+|         "4"
+|       "5"
+
+#data
+<table><a>1<p>2</a>3</p>
+#errors
+(1,7): expected-doctype-but-got-start-tag
+(1,10): unexpected-start-tag-implies-table-voodoo
+(1,11): unexpected-character-implies-table-voodoo
+(1,14): unexpected-start-tag-implies-table-voodoo
+(1,15): unexpected-character-implies-table-voodoo
+(1,19): unexpected-end-tag-implies-table-voodoo
+(1,19): adoption-agency-1.3
+(1,20): unexpected-character-implies-table-voodoo
+(1,24): unexpected-end-tag-implies-table-voodoo
+(1,24): eof-in-table
+#document
+| <html>
+|   <head>
+|   <body>
+|     <a>
+|       "1"
+|     <p>
+|       <a>
+|         "2"
+|       "3"
+|     <table>
+
+#data
+<b><b><a><p></a>
+#errors
+(1,3): expected-doctype-but-got-start-tag
+(1,16): adoption-agency-1.3
+(1,16): expected-closing-tag-but-got-eof
+#document
+| <html>
+|   <head>
+|   <body>
+|     <b>
+|       <b>
+|         <a>
+|         <p>
+|           <a>
+
+#data
+<b><a><b><p></a>
+#errors
+(1,3): expected-doctype-but-got-start-tag
+(1,16): adoption-agency-1.3
+(1,16): expected-closing-tag-but-got-eof
+#document
+| <html>
+|   <head>
+|   <body>
+|     <b>
+|       <a>
+|         <b>
+|       <b>
+|         <p>
+|           <a>
+
+#data
+<a><b><b><p></a>
+#errors
+(1,3): expected-doctype-but-got-start-tag
+(1,16): adoption-agency-1.3
+(1,16): expected-closing-tag-but-got-eof
+#document
+| <html>
+|   <head>
+|   <body>
+|     <a>
+|       <b>
+|         <b>
+|     <b>
+|       <b>
+|         <p>
+|           <a>
+
+#data
+<p>1<s id="A">2<b id="B">3</p>4</s>5</b>
+#errors
+(1,3): expected-doctype-but-got-start-tag
+(1,30): unexpected-end-tag
+(1,35): adoption-agency-1.3
+#document
+| <html>
+|   <head>
+|   <body>
+|     <p>
+|       "1"
+|       <s>
+|         id="A"
+|         "2"
+|         <b>
+|           id="B"
+|           "3"
+|     <s>
+|       id="A"
+|       <b>
+|         id="B"
+|         "4"
+|     <b>
+|       id="B"
+|       "5"
+
+#data
+<table><a>1<td>2</td>3</table>
+#errors
+(1,7): expected-doctype-but-got-start-tag
+(1,10): unexpected-start-tag-implies-table-voodoo
+(1,11): unexpected-character-implies-table-voodoo
+(1,15): unexpected-cell-in-table-body
+(1,30): unexpected-implied-end-tag-in-table-view
+#document
+| <html>
+|   <head>
+|   <body>
+|     <a>
+|       "1"
+|     <a>
+|       "3"
+|     <table>
+|       <tbody>
+|         <tr>
+|           <td>
+|             "2"
+
+#data
+<table>A<td>B</td>C</table>
+#errors
+(1,7): expected-doctype-but-got-start-tag
+(1,8): unexpected-character-implies-table-voodoo
+(1,12): unexpected-cell-in-table-body
+(1,22): unexpected-character-implies-table-voodoo
+#document
+| <html>
+|   <head>
+|   <body>
+|     "AC"
+|     <table>
+|       <tbody>
+|         <tr>
+|           <td>
+|             "B"
+
+#data
+<a><svg><tr><input></a>
+#errors
+(1,3): expected-doctype-but-got-start-tag
+(1,23): unexpected-end-tag
+(1,23): adoption-agency-1.3
+#document
+| <html>
+|   <head>
+|   <body>
+|     <a>
+|       <svg svg>
+|         <svg tr>
+|           <svg input>
+
+#data
+<div><a><b><div><div><div><div><div><div><div><div><div><div></a>
+#errors
+(1,5): expected-doctype-but-got-start-tag
+(1,65): adoption-agency-1.3
+(1,65): adoption-agency-1.3
+(1,65): adoption-agency-1.3
+(1,65): adoption-agency-1.3
+(1,65): adoption-agency-1.3
+(1,65): adoption-agency-1.3
+(1,65): adoption-agency-1.3
+(1,65): adoption-agency-1.3
+(1,65): expected-closing-tag-but-got-eof
+#document
+| <html>
+|   <head>
+|   <body>
+|     <div>
+|       <a>
+|         <b>
+|       <b>
+|         <div>
+|           <a>
+|           <div>
+|             <a>
+|             <div>
+|               <a>
+|               <div>
+|                 <a>
+|                 <div>
+|                   <a>
+|                   <div>
+|                     <a>
+|                     <div>
+|                       <a>
+|                       <div>
+|                         <a>
+|                           <div>
+|                             <div>
+
+#data
+<div><a><b><u><i><code><div></a>
+#errors
+(1,5): expected-doctype-but-got-start-tag
+(1,32): adoption-agency-1.3
+(1,32): expected-closing-tag-but-got-eof
+#document
+| <html>
+|   <head>
+|   <body>
+|     <div>
+|       <a>
+|         <b>
+|           <u>
+|             <i>
+|               <code>
+|       <u>
+|         <i>
+|           <code>
+|             <div>
+|               <a>
+
+#data
+<b><b><b><b>x</b></b></b></b>y
+#errors
+(1,3): expected-doctype-but-got-start-tag
+#document
+| <html>
+|   <head>
+|   <body>
+|     <b>
+|       <b>
+|         <b>
+|           <b>
+|             "x"
+|     "y"
+
+#data
+<p><b><b><b><b><p>x
+#errors
+(1,3): expected-doctype-but-got-start-tag
+(1,18): unexpected-end-tag
+(1,19): expected-closing-tag-but-got-eof
+#document
+| <html>
+|   <head>
+|   <body>
+|     <p>
+|       <b>
+|         <b>
+|           <b>
+|             <b>
+|     <p>
+|       <b>
+|         <b>
+|           <b>
+|             "x"
+
+#data
+<b><em><foo><foob><fooc><aside></b></em>
+#errors
+(1,35): adoption-agency-1.3
+(1,40): adoption-agency-1.3
+(1,40): expected-closing-tag-but-got-eof
+#document-fragment
+div
+#document
+| <b>
+|   <em>
+|     <foo>
+|       <foob>
+|         <fooc>
+| <aside>
+|   <b>