aboutsummaryrefslogtreecommitdiff
path: root/nixpkgs/pkgs/tools/text/ocrmypdf/0001-Make-compatible-with-pdfminer.six-version-20200720.patch
blob: 967bcd3948c2b3fe31a7e502f1a2253e5e123d6a (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
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