Merge pull request #93717 from bachp/ocrmypdf-10.3.0

ocrmypdf: 10.2.0 -> 10.3.0

pkgs/tools/text/ocrmypdf/0001-Make-compatible-with-pdfminer.six-version-20200720.patch

@@ -0,0 +1,52 @@
+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
+

pkgs/tools/text/ocrmypdf/default.nix

@@ -29,14 +29,14 @@ let
 in
 buildPythonApplication rec {
   pname = "ocrmypdf";
-  version = "10.2.0";
+  version = "10.3.0";
   disabled = ! python3Packages.isPy3k;
 
   src = fetchFromGitHub {
     owner = "jbarlow83";
     repo = "OCRmyPDF";
     rev = "v${version}";
-    sha256 = "1dkxhy3bjl48948jj2k6d684sd76xw1q427qc4hmxncr0wxj0ljp";
+    sha256 = "0c6v7846lmkmbyfla07s35mpba4h09h0fx6pxqf0yvdjxmj46q8c";
   };
 
   nativeBuildInputs = with python3Packages; [
@@ -76,6 +76,8 @@ buildPythonApplication rec {
       src = ./liblept.patch;
       liblept = "${stdenv.lib.getLib leptonica}/lib/liblept${stdenv.hostPlatform.extensions.sharedLibrary}";
     })
+    # https://github.com/jbarlow83/OCRmyPDF/pull/596
+    ./0001-Make-compatible-with-pdfminer.six-version-20200720.patch
   ];
 
   makeWrapperArgs = [ "--prefix PATH : ${stdenv.lib.makeBinPath [ ghostscript jbig2enc pngquant qpdf tesseract4 unpaper ]}" ];