Merge pull request #112411 from fabaff/license-ocrmypdf

From 4315b58e0bffedd145cec61f96062292cd98278e Mon Sep 17 00:00:00 2001

From: Pascal Bach <pascal.bach@nextrem.ch>

Date: Thu, 23 Jul 2020 21:37:33 +0200

Subject: [PATCH] Make compatible with pdfminer.six version 20200720

---

 setup.py                       | 2 +-

 src/ocrmypdf/pdfinfo/layout.py | 8 ++++++--

 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/setup.py b/setup.py

index bd95ed9..d1f4ab1 100644

--- a/setup.py

+++ b/setup.py

@@ -83,7 +83,7 @@ setup(

         'cffi >= 1.9.1',  # must be a setup and install requirement

         'coloredlogs >= 14.0',  # strictly optional

         'img2pdf >= 0.3.0, < 0.4',  # pure Python, so track HEAD closely

-        'pdfminer.six >= 20191110, <= 20200517',

+        'pdfminer.six >= 20191110, <= 20200720',

         'pikepdf >= 1.14.0, < 2',

         'Pillow >= 7.0.0',

         'pluggy >= 0.13.0',

diff --git a/src/ocrmypdf/pdfinfo/layout.py b/src/ocrmypdf/pdfinfo/layout.py

index 98bd82e..8b41e14 100644

--- a/src/ocrmypdf/pdfinfo/layout.py

+++ b/src/ocrmypdf/pdfinfo/layout.py

@@ -26,7 +26,11 @@ import pdfminer.pdfdevice

 import pdfminer.pdfinterp

 from pdfminer.converter import PDFLayoutAnalyzer

 from pdfminer.layout import LAParams, LTChar, LTPage, LTTextBox

-from pdfminer.pdfdocument import PDFTextExtractionNotAllowed

+try:

+    from pdfminer.pdfdocument import PDFTextExtractionNotAllowedError

+except ImportError:

+    # Fallback for pdfminer < 20200720

+    from pdfminer.pdfdocument import PDFTextExtractionNotAllowed as PDFTextExtractionNotAllowedError

 from pdfminer.pdffont import PDFSimpleFont, PDFUnicodeNotDefined

 from pdfminer.pdfpage import PDFPage

 from pdfminer.utils import bbox2str, matrix2str

@@ -239,7 +243,7 @@ def get_page_analysis(infile, pageno, pscript5_mode):

         with Path(infile).open('rb') as f:

             page = PDFPage.get_pages(f, pagenos=[pageno], maxpages=0)

             interp.process_page(next(page))

-    except PDFTextExtractionNotAllowed:

+    except PDFTextExtractionNotAllowedError:

         raise EncryptedPdfError()

     finally:

         if pscript5_mode:

-- 

2.27.0

, python3

, python3Packages

, qpdf

, lib, stdenv

, lib

, stdenv

, tesseract4

, unpaper

, substituteAll

in

buildPythonApplication rec {

  pname = "ocrmypdf";

  version = "11.3.3";

  version = "11.6.0";

  disabled = ! python3Packages.isPy3k;

  src = fetchFromGitHub {

    owner = "jbarlow83";

    repo = "OCRmyPDF";

    rev = "v${version}";

    sha256 = "0qv34clid65p11dgqalyk7b7myn5ibiz8i9xxhxkmjblw297p6ak";

    sha256 = "0inmmpam0vcm5n4sm6lh9p5swk44clknvm1cdwk9cax01mdqljza";

  };

  nativeBuildInputs = with python3Packages; [

    pytestrunner

    setuptools

    setuptools-scm-git-archive

    setuptools_scm

    pytest

    pytest-helpers-namespace

    pytest_xdist

    pytestcov

    pytestrunner

    pytest-cov

    python-xmp-toolkit

    pytestCheckHook

  ] ++ runtimeDeps;

  meta = with lib; {

    homepage = "https://github.com/jbarlow83/OCRmyPDF";

    description = "Adds an OCR text layer to scanned PDF files, allowing them to be searched";

    license = licenses.gpl3;

    license = with licenses; [ mpl20 mit ];

    platforms = platforms.linux;

    maintainers = [ maintainers.kiwi ];

  };