feat(pipeline): skip extraction when the source has not changed (#105) #126
@@ -108,9 +108,18 @@ func parseFrontmatterBlock(block string) (lines []fmLine, ok bool) {
|
|||||||
return nil, false
|
return nil, false
|
||||||
}
|
}
|
||||||
for _, line := range strings.Split(rest[:end], "\n") {
|
for _, line := range strings.Split(rest[:end], "\n") {
|
||||||
|
// An indented line is a continuation (a YAML block-list item, a
|
||||||
|
// wrapped value) never a top-level key, regardless of whether it
|
||||||
|
// happens to contain a colon — " - 'Chapter 3: The Reckoning'"
|
||||||
|
// is not a key named "- 'Chapter 3". Checked before Cut so a
|
||||||
|
// colon inside one never reaches the key/value path at all.
|
||||||
|
if line != "" && (line[0] == ' ' || line[0] == '\t') {
|
||||||
|
lines = append(lines, fmLine{raw: line})
|
||||||
|
continue
|
||||||
|
}
|
||||||
key, val, found := strings.Cut(line, ":")
|
key, val, found := strings.Cut(line, ":")
|
||||||
key = strings.TrimSpace(key)
|
key = strings.TrimSpace(key)
|
||||||
if !found || key == "" {
|
if !found || key == "" || strings.HasPrefix(strings.TrimSpace(line), "#") {
|
||||||
lines = append(lines, fmLine{raw: line})
|
lines = append(lines, fmLine{raw: line})
|
||||||
continue
|
continue
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -304,3 +304,31 @@ Rewritten by the model.
|
|||||||
want := "---\ntitle: 'X'\nlast_updated: 2026-08-22\nsource_hash: bbbb\n---\n\n## Summary\n\nOriginal.\n"
|
want := "---\ntitle: 'X'\nlast_updated: 2026-08-22\nsource_hash: bbbb\n---\n\n## Summary\n\nOriginal.\n"
|
||||||
assert.Equal(t, want, got)
|
assert.Equal(t, want, got)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
func TestRefreshOwned_CommentLinesSurviveUnmangled(t *testing.T) {
|
||||||
|
// Third review round on PR #126: parseFrontmatterBlock dropped the
|
||||||
|
// sibling api package's comment guard (strings.HasPrefix(trimmed, "#")).
|
||||||
|
// Without it, a comment line containing a colon gets cut at the colon
|
||||||
|
// and re-rendered with collapsed whitespace instead of surviving
|
||||||
|
// verbatim.
|
||||||
|
a := "---\n#see also: https://x/y\ntitle: 'X'\n---\n"
|
||||||
|
b := "---\nsource_hash: bbbb\n---\n"
|
||||||
|
|
||||||
|
got := refreshOwned(a, b)
|
||||||
|
assert.Equal(t, "---\n#see also: https://x/y\ntitle: 'X'\nsource_hash: bbbb\n---\n", got)
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestRefreshOwned_IndentedListItemsWithColonsAreNotMisparsedAsKeys(t *testing.T) {
|
||||||
|
// Same round: an indented YAML block-list item that happens to contain a
|
||||||
|
// colon (e.g. a title with a subtitle) is a continuation line, never a
|
||||||
|
// top-level key, regardless of what strings.Cut finds in it. Misparsing
|
||||||
|
// it as a key/value pair and re-rendering strips its indentation,
|
||||||
|
// de-indenting it out of the list it belongs to -- and refreshOwned
|
||||||
|
// re-renders this block on essentially every non-skipped ingest, so this
|
||||||
|
// is the normal path, not an edge case.
|
||||||
|
a := "---\naliases:\n - 'Chapter 3: The Reckoning'\ntitle: 'X'\n---\n"
|
||||||
|
b := "---\nsource_hash: bbbb\n---\n"
|
||||||
|
|
||||||
|
got := refreshOwned(a, b)
|
||||||
|
assert.Equal(t, "---\naliases:\n - 'Chapter 3: The Reckoning'\ntitle: 'X'\nsource_hash: bbbb\n---\n", got)
|
||||||
|
}
|
||||||
|
|||||||
Reference in New Issue
Block a user