fix(brain): a one-word tunnel title must match the prose case-exactly
AutoTunnel matched note titles case-insensitively, so a one-word title linked
every entry that happened to use that word. Measured on the live corpus: 185
entries carry an auto-written See-also link to wiki/telos/decisions/wrong.md
(title "WRONG") and 136 to .../status.md — the two most-linked nodes in the
whole graph, and both of them artifacts of the English language rather than
references. telos's projects/problems/strategies/goals/beliefs entries account
for another ~60 between them.
That pollution is not cosmetic: inbound-link count is what the duplicate
Fixer picks survivors by, what orphan detection reads, and what brain_graph
shows.
One-word titles now need the title's own casing in the prose ("WRONG", "BERT",
"NLP" — an entity name in a sentence still links). Multi-word titles keep the
case-insensitive match: "risk tier middleware" is a real mention however it is
capitalised, and a three-word collision is not an accident.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
@@ -54,11 +54,24 @@ func DetectTunnels(brainDir, content string) ([]TunnelCandidate, error) {
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
title, _ := readTitleAndCreated(path, strings.TrimSuffix(d.Name(), ".md"))
|
title, _ := readTitleAndCreated(path, strings.TrimSuffix(d.Name(), ".md"))
|
||||||
needle := strings.ToLower(strings.TrimSpace(title))
|
title = strings.TrimSpace(title)
|
||||||
if needle == "" {
|
if title == "" {
|
||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
idx := strings.Index(lowerContent, needle)
|
|
||||||
|
// A one-word title has to match the prose case-exactly. Matched
|
||||||
|
// case-insensitively, it links every entry that happens to use the
|
||||||
|
// word: "WRONG" (wiki/telos/decisions/wrong.md) collected 185 inbound
|
||||||
|
// See-also links and "Status" 136, making the two most-linked nodes in
|
||||||
|
// the graph artifacts of the English language rather than references.
|
||||||
|
// Multi-word titles keep the case-insensitive match — "risk tier
|
||||||
|
// middleware" in prose is a real mention however it is capitalised,
|
||||||
|
// and a three-word collision is not an accident.
|
||||||
|
haystack, needle := lowerContent, strings.ToLower(title)
|
||||||
|
if isSingleWord(title) {
|
||||||
|
haystack, needle = content, title
|
||||||
|
}
|
||||||
|
idx := strings.Index(haystack, needle)
|
||||||
if idx == -1 {
|
if idx == -1 {
|
||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
@@ -69,7 +82,7 @@ func DetectTunnels(brainDir, content string) ([]TunnelCandidate, error) {
|
|||||||
out = append(out, TunnelCandidate{
|
out = append(out, TunnelCandidate{
|
||||||
TargetPath: filepath.ToSlash(rel),
|
TargetPath: filepath.ToSlash(rel),
|
||||||
MatchedTerm: title,
|
MatchedTerm: title,
|
||||||
Exact: isWholeWord(lowerContent, idx, len(needle)),
|
Exact: isWholeWord(haystack, idx, len(needle)),
|
||||||
})
|
})
|
||||||
return nil
|
return nil
|
||||||
})
|
})
|
||||||
@@ -79,6 +92,11 @@ func DetectTunnels(brainDir, content string) ([]TunnelCandidate, error) {
|
|||||||
return out, nil
|
return out, nil
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// isSingleWord reports whether title is one whitespace-free token.
|
||||||
|
func isSingleWord(title string) bool {
|
||||||
|
return !strings.ContainsAny(title, " \t")
|
||||||
|
}
|
||||||
|
|
||||||
// isWholeWord reports whether the substring at [idx, idx+n) in s is
|
// isWholeWord reports whether the substring at [idx, idx+n) in s is
|
||||||
// bounded by non-alphanumeric characters (or string edges).
|
// bounded by non-alphanumeric characters (or string edges).
|
||||||
func isWholeWord(s string, idx, n int) bool {
|
func isWholeWord(s string, idx, n int) bool {
|
||||||
|
|||||||
@@ -102,16 +102,29 @@ func TestDetectTunnels_ExactTitleMatch(t *testing.T) {
|
|||||||
|
|
||||||
func TestDetectTunnels_FuzzyMatch(t *testing.T) {
|
func TestDetectTunnels_FuzzyMatch(t *testing.T) {
|
||||||
dir := t.TempDir()
|
dir := t.TempDir()
|
||||||
seedNote(t, dir, "wiki/x/facts/routing.md",
|
seedNote(t, dir, "wiki/x/facts/routing-table.md",
|
||||||
"---\ntitle: Routing\n---\nbody.\n")
|
"---\ntitle: 'Routing Table'\n---\nbody.\n")
|
||||||
|
|
||||||
// Substring of title appears in content, but not as a whole word.
|
// Substring of title appears in content, but not as a whole word.
|
||||||
candidates, err := brain.DetectTunnels(dir, "rerouting handles failover")
|
candidates, err := brain.DetectTunnels(dir, "the routing tables were rebuilt")
|
||||||
require.NoError(t, err)
|
require.NoError(t, err)
|
||||||
require.Len(t, candidates, 1)
|
require.Len(t, candidates, 1)
|
||||||
assert.False(t, candidates[0].Exact, "substring-only match should be fuzzy")
|
assert.False(t, candidates[0].Exact, "substring-only match should be fuzzy")
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// A one-word title whose only appearance is lowercase inside another word is
|
||||||
|
// not even a candidate: it would fill the review file with English rather than
|
||||||
|
// with references.
|
||||||
|
func TestDetectTunnels_SingleWordSubstringIsNotACandidate(t *testing.T) {
|
||||||
|
dir := t.TempDir()
|
||||||
|
seedNote(t, dir, "wiki/x/facts/routing.md",
|
||||||
|
"---\ntitle: Routing\n---\nbody.\n")
|
||||||
|
|
||||||
|
candidates, err := brain.DetectTunnels(dir, "rerouting handles failover")
|
||||||
|
require.NoError(t, err)
|
||||||
|
assert.Empty(t, candidates)
|
||||||
|
}
|
||||||
|
|
||||||
func TestDetectTunnels_NoFrontmatterFallsBackToSlug(t *testing.T) {
|
func TestDetectTunnels_NoFrontmatterFallsBackToSlug(t *testing.T) {
|
||||||
dir := t.TempDir()
|
dir := t.TempDir()
|
||||||
seedNote(t, dir, "wiki/x/facts/widget-flags.md", "# widget flags\n\nbody.\n")
|
seedNote(t, dir, "wiki/x/facts/widget-flags.md", "# widget flags\n\nbody.\n")
|
||||||
@@ -126,20 +139,21 @@ func TestDetectTunnels_NoFrontmatterFallsBackToSlug(t *testing.T) {
|
|||||||
|
|
||||||
func TestAutoTunnel_FuzzyGoesToCandidatesFile(t *testing.T) {
|
func TestAutoTunnel_FuzzyGoesToCandidatesFile(t *testing.T) {
|
||||||
dir := t.TempDir()
|
dir := t.TempDir()
|
||||||
// Existing note in a different wing whose title is "Routing".
|
// Existing note in a different wing whose title is "Routing Table".
|
||||||
seedNote(t, dir, "wiki/other/facts/routing.md",
|
seedNote(t, dir, "wiki/other/facts/routing-table.md",
|
||||||
"---\nwing: other\nhall: facts\ntitle: Routing\n---\nbody.\n")
|
"---\nwing: other\nhall: facts\ntitle: 'Routing Table'\n---\nbody.\n")
|
||||||
// Source note in another wing whose body mentions "rerouting" (substring match only).
|
// Source note in another wing whose body mentions "routing tables"
|
||||||
|
// (substring match only — the title is not there as a whole word).
|
||||||
seedNote(t, dir, "wiki/jepa-fx/facts/new.md",
|
seedNote(t, dir, "wiki/jepa-fx/facts/new.md",
|
||||||
"---\nwing: jepa-fx\nhall: facts\n---\nrerouting traffic\n")
|
"---\nwing: jepa-fx\nhall: facts\n---\nrouting tables rebuilt\n")
|
||||||
|
|
||||||
require.NoError(t, brain.AutoTunnel(dir,
|
require.NoError(t, brain.AutoTunnel(dir,
|
||||||
"wiki/jepa-fx/facts/new.md", "rerouting traffic"))
|
"wiki/jepa-fx/facts/new.md", "routing tables rebuilt"))
|
||||||
|
|
||||||
// Source must not get auto-linked (fuzzy).
|
// Source must not get auto-linked (fuzzy).
|
||||||
got, err := os.ReadFile(filepath.Join(dir, "wiki/jepa-fx/facts/new.md"))
|
got, err := os.ReadFile(filepath.Join(dir, "wiki/jepa-fx/facts/new.md"))
|
||||||
require.NoError(t, err)
|
require.NoError(t, err)
|
||||||
assert.NotContains(t, string(got), "[[other/facts/routing]]")
|
assert.NotContains(t, string(got), "[[other/facts/routing-table]]")
|
||||||
|
|
||||||
// Candidates file must list the pair.
|
// Candidates file must list the pair.
|
||||||
matches, err := filepath.Glob(filepath.Join(dir, "raw", "tunnel-candidates-*.md"))
|
matches, err := filepath.Glob(filepath.Join(dir, "raw", "tunnel-candidates-*.md"))
|
||||||
@@ -148,7 +162,7 @@ func TestAutoTunnel_FuzzyGoesToCandidatesFile(t *testing.T) {
|
|||||||
body, err := os.ReadFile(matches[0])
|
body, err := os.ReadFile(matches[0])
|
||||||
require.NoError(t, err)
|
require.NoError(t, err)
|
||||||
assert.Contains(t, string(body), "wiki/jepa-fx/facts/new.md")
|
assert.Contains(t, string(body), "wiki/jepa-fx/facts/new.md")
|
||||||
assert.Contains(t, string(body), "wiki/other/facts/routing.md")
|
assert.Contains(t, string(body), "wiki/other/facts/routing-table.md")
|
||||||
assert.Contains(t, string(body), "Routing")
|
assert.Contains(t, string(body), "Routing")
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -175,3 +189,35 @@ func TestWriteTunnel_AppendsToExistingSeeAlso(t *testing.T) {
|
|||||||
assert.Contains(t, s, "[[a/facts/old]]")
|
assert.Contains(t, s, "[[a/facts/old]]")
|
||||||
assert.Contains(t, s, "[[b/facts/y]]")
|
assert.Contains(t, s, "[[b/facts/y]]")
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// A one-word title matched case-insensitively links every entry that happens
|
||||||
|
// to use that word. Live cost before this rule: 185 entries auto-linked to
|
||||||
|
// wiki/telos/decisions/wrong.md (title "WRONG") and 136 to .../status.md,
|
||||||
|
// making the two most-linked nodes in the graph pure artifacts.
|
||||||
|
func TestDetectTunnels_SingleWordTitleNeedsAnExactCaseMatch(t *testing.T) {
|
||||||
|
dir := t.TempDir()
|
||||||
|
seedNote(t, dir, "wiki/telos/decisions/wrong.md",
|
||||||
|
"---\nwing: telos\nhall: decisions\ntitle: WRONG\n---\n# WRONG\n\nRetired beliefs.\n")
|
||||||
|
|
||||||
|
got, err := brain.DetectTunnels(dir, "The obvious fix was to reject the write. Wrong here.")
|
||||||
|
require.NoError(t, err)
|
||||||
|
for _, c := range got {
|
||||||
|
assert.False(t, c.Exact, "a lowercase prose word must not auto-link a one-word title: %+v", c)
|
||||||
|
}
|
||||||
|
|
||||||
|
got, err = brain.DetectTunnels(dir, "The beliefs listed under WRONG were retired.")
|
||||||
|
require.NoError(t, err)
|
||||||
|
require.Len(t, got, 1)
|
||||||
|
assert.True(t, got[0].Exact, "the title's own casing appearing in prose is a real reference")
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestDetectTunnels_MultiWordTitleStaysCaseInsensitive(t *testing.T) {
|
||||||
|
dir := t.TempDir()
|
||||||
|
seedNote(t, dir, "wiki/homelab/facts/risk-tier.md",
|
||||||
|
"---\nwing: homelab\nhall: facts\ntitle: 'Risk Tier Middleware'\n---\nbody\n")
|
||||||
|
|
||||||
|
got, err := brain.DetectTunnels(dir, "We rebuilt the risk tier middleware last week.")
|
||||||
|
require.NoError(t, err)
|
||||||
|
require.Len(t, got, 1)
|
||||||
|
assert.True(t, got[0].Exact)
|
||||||
|
}
|
||||||
|
|||||||
Reference in New Issue
Block a user