From e3b65d42885c92fd5bb3ab91eda673dfdd1945ca Mon Sep 17 00:00:00 2001 From: "James R. Barlow" Date: Thu, 15 Nov 2018 12:02:08 -0800 Subject: [PATCH] Fix detailed page analysis enabled at wrong time --- src/ocrmypdf/_pipeline.py | 2 +- src/ocrmypdf/pdfinfo/__init__.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/src/ocrmypdf/_pipeline.py b/src/ocrmypdf/_pipeline.py index 3d63cc47..89fbbea3 100644 --- a/src/ocrmypdf/_pipeline.py +++ b/src/ocrmypdf/_pipeline.py @@ -167,7 +167,7 @@ def repair_and_parse_pdf( detailed_page_analysis = True try: - pdfinfo = PdfInfo(output_file, log=log) + pdfinfo = PdfInfo(output_file, detailed_page_analysis=detailed_page_analysis, log=log) except pikepdf.PasswordError as e: raise EncryptedPdfError() except pikepdf.PdfError as e: diff --git a/src/ocrmypdf/pdfinfo/__init__.py b/src/ocrmypdf/pdfinfo/__init__.py index 0b783259..a084aa66 100644 --- a/src/ocrmypdf/pdfinfo/__init__.py +++ b/src/ocrmypdf/pdfinfo/__init__.py @@ -593,7 +593,7 @@ def _pdf_get_all_pageinfo(infile, detailed_page_analysis, log=None): log = Mock() pdf = pikepdf.open(infile) - if not detailed_page_analysis: + if detailed_page_analysis: pages_xml = None else: pages_xml = ghosttext.extract_text_xml(infile, pdf, pageno=None, log=log)