fix(frontmatter): consolidate 3 independent fence-parsers into one (#139)

Co-authored-by: Mathias <mthbqv@gmail.com>

ingestion/internal/frontmatter/frontmatter_test.go

@@ -168,9 +168,9 @@ func TestFix_PreservesBodyExactly(t *testing.T) {
 	require.True(t, changed)
 	assert.True(t, len(got) > 0)
 
-	_, rest, ok := split([]byte(doc))
+	_, rest, ok := Split([]byte(doc))
 	require.True(t, ok)
-	_, gotRest, ok := split(got)
+	_, gotRest, ok := Split(got)
 	require.True(t, ok)
 	assert.Equal(t, string(rest), string(gotRest), "the body must not be touched")
 }
@@ -186,3 +186,55 @@ func TestFix_RefusesToReturnAnUnparseableResult(t *testing.T) {
 	assert.False(t, changed)
 	assert.Equal(t, doc, string(got), "an unfixable document must come back byte-identical")
 }
+
+// TestSplit_NormalizesCRLFBeforeFenceDetection is hyperguild#138: a note
+// whose fence lines use CRLF ("---\r\n") failed strings.HasPrefix(doc,
+// "---\n") on the precondition read in internal/mcp's independent
+// reimplementation -- encoding alone, no adversarial input, silently
+// defeated fence detection there before this consolidation. Split must
+// never repeat that.
+func TestSplit_NormalizesCRLFBeforeFenceDetection(t *testing.T) {
+	doc := "---\r\ntitle: 'n'\r\nhalf_life: durable\r\n---\r\n\r\nbody\r\n"
+	block, rest, ok := Split([]byte(doc))
+	require.True(t, ok)
+	assert.Contains(t, string(block), "half_life: durable")
+	assert.Contains(t, string(rest), "body")
+}
+
+// TestSplit_StripsALeadingUTF8BOM is the same mechanism one layer earlier:
+// a leading BOM (Notepad's default "UTF-8" save, PowerShell's pre-v6
+// Out-File/Set-Content) defeats the same HasPrefix check before CRLF
+// normalization even applies.
+func TestSplit_StripsALeadingUTF8BOM(t *testing.T) {
+	doc := "\xef\xbb\xbf---\ntitle: 'n'\n---\n\nbody\n"
+	block, rest, ok := Split([]byte(doc))
+	require.True(t, ok)
+	assert.Contains(t, string(block), "title: 'n'")
+	assert.Contains(t, string(rest), "body")
+}
+
+// TestSplit_RequiresANewlineAfterTheClosingFence closes the looser match
+// internal/api's independent reimplementation carried (strings.Index(body,
+// "\n"+fence) with no trailing-newline requirement): a document ending in
+// "\n---extra" with no newline separating the fence from what follows it is
+// not a valid closing fence and must not be treated as one.
+func TestSplit_RequiresANewlineAfterTheClosingFence(t *testing.T) {
+	doc := "---\ntitle: 'n'\n---extra-not-a-real-close"
+	_, _, ok := Split([]byte(doc))
+	assert.False(t, ok, "a fence line not followed by a newline is not a valid closing fence")
+}
+
+// TestSplit_AcceptsAClosingFenceThatIsTheLastBytesOfTheDocument is a
+// regression pin found in review of hyperguild#138: the fix for the
+// "\n---extra" bypass above must not also reject the legitimate case of a
+// closing fence with nothing after it at all (no trailing newline because
+// there's no body, not because a bypass is being attempted) -- this
+// package's own private split() accepted that shape before the
+// consolidation, and cmd/frontmatterlint's Lint/Fix relied on it.
+func TestSplit_AcceptsAClosingFenceThatIsTheLastBytesOfTheDocument(t *testing.T) {
+	doc := "---\ntitle: 'n'\n---"
+	block, rest, ok := Split([]byte(doc))
+	require.True(t, ok, "a closing fence at literal end-of-file, with nothing after it, is valid -- there is no body to require a newline before")
+	assert.Contains(t, string(block), "title: 'n'")
+	assert.Equal(t, "", string(rest))
+}