Corpus by contract kind: pin the fence and escaping rules, hold two questions

corpus/README.md

@@ -1,8 +1,15 @@
 # The corpus
 
-`<name>.json` is an ADF document; `<name>.md` is the markdown `adfToMarkdown` must emit for it,
-byte for byte including the trailing newline, and that `markdownToAdf` must read back to that same
-document (AGENTS.md §2). Directories mirror `spec/flavour.md`'s sections.
+One directory per contract kind:
 
-The JSON is editor-normal — empty `attrs`, `marks` and `content` as the absent key, adjacent
-identical-mark text nodes merged — two-space indent, keys sorted.
+- `round-trip/` — `<name>.json` + `<name>.md`: the markdown `adfToMarkdown` must emit for that
+  document, byte for byte, and that `markdownToAdf` must read back to it (AGENTS.md §2). Grouped
+  by node family: `commonmark-subset/`, `block-nodes/`, `inline-nodes/`, `opaque-carry/`,
+  `combinations/`.
+- `normalization/` — `<name>.md` + `<name>.json`: markdown input, and the document
+  `markdownToAdf` must build from it. One-way; the markdown is not canonical.
+- `errors/` — `<name>.md` + `<name>.error`: markdown input that must not convert.
+- `real-payloads/` — `<name>.json`: sanitized live ADF, round-tripped ADF→markdown→ADF. No
+  expected markdown.
+
+JSON is editor-normal (AGENTS.md §2), two-space indent, keys sorted.

corpus/canonical-form/ordered-list.json

@@ -1,53 +0,0 @@
-{
-  "content": [
-    {
-      "content": [
-        {
-          "content": [
-            {
-              "content": [
-                {
-                  "text": "Bolt M8",
-                  "type": "text"
-                }
-              ],
-              "type": "paragraph"
-            }
-          ],
-          "type": "listItem"
-        },
-        {
-          "content": [
-            {
-              "content": [
-                {
-                  "text": "Nut M8",
-                  "type": "text"
-                }
-              ],
-              "type": "paragraph"
-            }
-          ],
-          "type": "listItem"
-        },
-        {
-          "content": [
-            {
-              "content": [
-                {
-                  "text": "Washer M8",
-                  "type": "text"
-                }
-              ],
-              "type": "paragraph"
-            }
-          ],
-          "type": "listItem"
-        }
-      ],
-      "type": "orderedList"
-    }
-  ],
-  "type": "doc",
-  "version": 1
-}

corpus/canonical-form/ordered-list.md

@@ -1,3 +0,0 @@
-1. Bolt M8
-2. Nut M8
-3. Washer M8

corpus/round-trip/commonmark-subset/code-block-backtick-run-mid-line.json

@@ -0,0 +1,18 @@
+{
+  "content": [
+    {
+      "attrs": {
+        "language": "bash"
+      },
+      "content": [
+        {
+          "text": "echo \"```\" >> notes.md",
+          "type": "text"
+        }
+      ],
+      "type": "codeBlock"
+    }
+  ],
+  "type": "doc",
+  "version": 1
+}

corpus/round-trip/commonmark-subset/code-block-backtick-run-mid-line.md

@@ -0,0 +1,3 @@
+````bash
+echo "```" >> notes.md
+````

corpus/round-trip/commonmark-subset/code-block-backtick-run.json

@@ -1,6 +1,9 @@
 {
   "content": [
     {
+      "attrs": {
+        "language": "markdown"
+      },
       "content": [
         {
           "text": "```\ncode\n```",

corpus/round-trip/commonmark-subset/code-block-backtick-run.md

@@ -1,4 +1,4 @@
-````
+````markdown
 ```
 code
 ```

corpus/round-trip/commonmark-subset/document-empty.json

@@ -0,0 +1,4 @@
+{
+  "type": "doc",
+  "version": 1
+}

corpus/round-trip/commonmark-subset/text-escaping.json

@@ -35,6 +35,15 @@
         }
       ],
       "type": "paragraph"
+    },
+    {
+      "content": [
+        {
+          "text": "*not emphasis*",
+          "type": "text"
+        }
+      ],
+      "type": "paragraph"
     }
   ],
   "type": "doc",

corpus/round-trip/commonmark-subset/text-escaping.md

@@ -5,3 +5,5 @@
 2 * 3 * 4 = 24
 
 snake_case_name
+
+\*not emphasis*