feat(docs): optimize PDF via Ghostscript pdfwrite

Add oo docs optimize for native-text PDFs (OO-friendly rewrite without
ocrmypdf overlay). Default ocr --force to false when text layer exists.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
2026-08-28 10:02:58 +01:00
co-authored by Cursor
parent ba8148a9e1
commit 6b3f40e1a1
3 changed files with 115 additions and 13 deletions
+27
View File
@@ -128,6 +128,33 @@ func TestMDDocxRoundTrip(t *testing.T) {
}
}
func TestOptimizePDF(t *testing.T) {
tools := LookPath()
if tools.Ghostscript == "" || tools.PDFToText == "" {
t.Skip("ghostscript/pdftotext not installed")
}
in := "/tmp/ccgg-original.pdf"
if _, err := os.Stat(in); err != nil {
t.Skip("local fixture not present")
}
dir := t.TempDir()
out := filepath.Join(dir, "out.pdf")
charsIn, err := tools.PDFTextLayerChars(in)
if err != nil || charsIn < 1000 {
t.Skip("fixture has no text layer")
}
if err := tools.OptimizePDF(in, out); err != nil {
t.Fatal(err)
}
charsOut, err := tools.PDFTextLayerChars(out)
if err != nil {
t.Fatal(err)
}
if charsOut < charsIn/2 {
t.Fatalf("text layer lost: in=%d out=%d", charsIn, charsOut)
}
}
func TestToMarkdown_PlainMD(t *testing.T) {
tools := LookPath()
dir := t.TempDir()