From 378f54361929b0e3ff9390f9a2e45d57eb84e277 Mon Sep 17 00:00:00 2001 From: "James R. Barlow" Date: Tue, 30 Jun 2020 00:41:36 -0700 Subject: [PATCH] TextPositionTracker: set boxes_flow=None We don't care about the order of lines in our analysis, and this is an expensive calculation in pdfminer. --- src/ocrmypdf/pdfinfo/layout.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/ocrmypdf/pdfinfo/layout.py b/src/ocrmypdf/pdfinfo/layout.py index 9eb8306a..98bd82e0 100644 --- a/src/ocrmypdf/pdfinfo/layout.py +++ b/src/ocrmypdf/pdfinfo/layout.py @@ -221,7 +221,7 @@ class TextPositionTracker(PDFLayoutAnalyzer): def get_page_analysis(infile, pageno, pscript5_mode): rman = pdfminer.pdfinterp.PDFResourceManager(caching=True) dev = TextPositionTracker( - rman, laparams=LAParams(all_texts=True, detect_vertical=True) + rman, laparams=LAParams(all_texts=True, detect_vertical=True, boxes_flow=None) ) interp = pdfminer.pdfinterp.PDFPageInterpreter(rman, dev)