From d118132fa6f0c52210276acfde80d9f91be37f4f Mon Sep 17 00:00:00 2001 From: "James R. Barlow" Date: Wed, 3 Jun 2020 13:16:55 -0700 Subject: [PATCH] layout: look for text in XObjects too --- src/ocrmypdf/pdfinfo/layout.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/src/ocrmypdf/pdfinfo/layout.py b/src/ocrmypdf/pdfinfo/layout.py index af9d7961..1368a75b 100644 --- a/src/ocrmypdf/pdfinfo/layout.py +++ b/src/ocrmypdf/pdfinfo/layout.py @@ -269,7 +269,9 @@ class TextPositionTracker(PDFLayoutAnalyzer): def get_page_analysis(infile, pageno, pscript5_mode): rman = pdfminer.pdfinterp.PDFResourceManager(caching=True) - dev = TextPositionTracker(rman, laparams=LAParams()) + dev = TextPositionTracker( + rman, laparams=LAParams(all_texts=True, detect_vertical=True) + ) interp = pdfminer.pdfinterp.PDFPageInterpreter(rman, dev) if pscript5_mode: