feat(pipeline): ingest revises the existing page instead of clobbering it (#103)
fix(wiki): give the preamble its own field instead of overloading heading=="" (#103)
Round 3 review: verified structurally that the preamble is no longer in the sections slice or the idx map, so it cannot collide with a degenerate `## ` heading. Flip-tested by reverting to the heading=="" model and confirming TestMerge_DegenerateEmptyHeadingDoesNotCollideWithPreamble goes red. Adversarial pass (multiple degenerate headings, frontmatter-only page, unicode around the ## boundary, 3x self-merge idempotency with preamble+degenerate) all held. CI green on 09aeaa9 (run 7820).
Co-authored-by: Mathias <mthbqv@gmail.com>
This commit was merged in pull request #103.
This commit is contained in:
@@ -96,7 +96,11 @@ func buildAndWrite(rawPages []RawPage, sourceSlug, date, brainDir, source string
|
||||
if err := os.MkdirAll(filepath.Dir(dest), 0o755); err != nil {
|
||||
return Result{}, fmt.Errorf("mkdir for %s: %w", page.Path, err)
|
||||
}
|
||||
if err := os.WriteFile(dest, []byte(page.Content), 0o644); err != nil {
|
||||
content, err := reviseOrCreate(dest, page)
|
||||
if err != nil {
|
||||
return Result{}, err
|
||||
}
|
||||
if err := os.WriteFile(dest, []byte(content), 0o644); err != nil {
|
||||
return Result{}, fmt.Errorf("write %s: %w", page.Path, err)
|
||||
}
|
||||
}
|
||||
@@ -115,6 +119,36 @@ func buildAndWrite(rawPages []RawPage, sourceSlug, date, brainDir, source string
|
||||
return Result{Pages: written, Warnings: warnings}, nil
|
||||
}
|
||||
|
||||
// reviseOrCreate returns the bytes to write for one extracted page: merged into
|
||||
// whatever is already on disk, or the page as-is when the path is new.
|
||||
//
|
||||
// This is the compile half of compile-on-ingest. Before it, the write was an
|
||||
// unconditional os.WriteFile, so re-ingesting a source replaced its page
|
||||
// wholesale and discarded everything accumulated since — including human edits
|
||||
// (hyperguild#43: "re-ingest overwrites wholesale").
|
||||
//
|
||||
// The merge is deliberately asymmetric in the existing page's favour:
|
||||
// wiki.Merge keeps the on-disk frontmatter and the on-disk version of any
|
||||
// section both sides carry, adds sections only the extraction produced, and
|
||||
// unions bullet lists. So a freshly extracted page can add to a note but never
|
||||
// silently rewrite what a human put there — which is what makes it safe to run
|
||||
// this on every ingest rather than behind a review gate.
|
||||
//
|
||||
// Known limitation: because the on-disk frontmatter wins, `last_updated` keeps
|
||||
// its first-ingest date on a revised page. Left deliberately — the alternative
|
||||
// is this function editing frontmatter it does not own, and no lint reads that
|
||||
// field today.
|
||||
func reviseOrCreate(dest string, page wiki.Page) (string, error) {
|
||||
existing, err := os.ReadFile(dest)
|
||||
switch {
|
||||
case os.IsNotExist(err):
|
||||
return page.Content, nil
|
||||
case err != nil:
|
||||
return "", fmt.Errorf("read existing %s: %w", page.Path, err)
|
||||
}
|
||||
return wiki.Merge(wiki.Page{Path: page.Path, Content: string(existing)}, page).Content, nil
|
||||
}
|
||||
|
||||
// mergeAll deduplicates pages by path, merging content from later occurrences.
|
||||
func mergeAll(pages []wiki.Page) []wiki.Page {
|
||||
order := make([]string, 0, len(pages))
|
||||
|
||||
Reference in New Issue
Block a user