Workflow: sparse partial checkout (code and _incoming only), book lookup before processing, safe rebase retry; revert cancel-in-progress

_pipeline/pdftext.py

@@ -85,11 +85,12 @@ def align(raw_lines, boxes, window=8):
     return result
 
 
-def units(pdf):
+def units(pdf, first_pages=None):
     """Reading units in order: [{'pdf_page', 'half', 'text', 'geom'}]. Text keeps the layout (indentation, hyphens).
     'geom' is parallel to text.split('\\n'): the position of each line on the page (see align)."""
     result = []
-    for p, (w, h) in enumerate(page_geometry(pdf), start=1):
+    geo = page_geometry(pdf)
+    for p, (w, h) in enumerate(geo[:first_pages] if first_pages else geo, start=1):
         boxes = page_lines(pdf, p)
         for half, x, width in halves(w, h):
             text = _run(["pdftotext", "-layout", "-f", str(p), "-l", str(p),