ingestion: strip repeated front-matter blocks from notes

corpus/sources/estate.py

@@ -692,14 +692,26 @@ def _make_document(**values) -> loader.Document:
 
 
 def _strip_front_matter(text: str) -> str:
-    """Drop a leading YAML block. The Note path parses it; files only need it gone."""
+    """Drop leading YAML blocks. The Note path parses them; files only need them gone.
-    lines = text.splitlines()
+
-    if not lines or lines[0].strip() != "---":
+    Some notes carry two blocks in a row (a stale export, or a block followed by
-        return text
+    a horizontal rule that closes), so this repeats. It never strips a body that
-    for index in range(1, len(lines)):
+    does not have a closing delimiter.
-        if lines[index].strip() in ("---", "..."):
+    """
-            return "\n".join(lines[index + 1 :]).strip()
+    body = text
-    return text
+    for _ in range(3):
+        lines = body.splitlines()
+        if not lines or lines[0].strip() != "---":
+            return body
+        closing = None
+        for index in range(1, len(lines)):
+            if lines[index].strip() in ("---", "..."):
+                closing = index
+                break
+        if closing is None:
+            return body
+        body = "\n".join(lines[closing + 1 :]).strip()
+    return body
 
 
 def _split_note(text: str, validator) -> tuple:
@@ -724,7 +736,9 @@ def _split_note(text: str, validator) -> tuple:
             fields = parsed
     except validator.YamlError:
         fields = {}
-    return fields, "\n".join(lines[end + 1 :]).strip()
+    # Strip any further leading block as well, so a duplicate front-matter block
+    # never reaches the chunker.
+    return fields, _strip_front_matter("\n".join(lines[end + 1 :]).strip())
 
 
 def _source_row(name: str, enabled: bool, documents: list, extra: dict = None) -> dict: