From 63032d304d9076c748fcc960fe3203650c69d890 Mon Sep 17 00:00:00 2001
From: "James R. Barlow" <jim@purplerock.ca>
Date: Thu, 10 May 2018 16:27:17 -0700
Subject: [PATCH] Revert "Since PyMuPDF 1.13.3 corrupts text, pin 1.12.5 and
 work around it"

This reverts commit b0ce7c63dd27257d9c979fde9013243b8ae38c98.
---
 setup.py                | 2 +-
 src/ocrmypdf/pdfinfo.py | 7 +------
 2 files changed, 2 insertions(+), 7 deletions(-)

diff --git a/setup.py b/setup.py
index ccb85522..ab634951 100644
--- a/setup.py
+++ b/setup.py
@@ -251,7 +251,7 @@ setup(
         'ruffus == 2.6.3',        # pinned - ocrmypdf implements a 2.6.3 workaround
     ],
     extras_require={
-        'fitz': ['PyMuPDF == 1.12.5'],
+        'fitz': ['PyMuPDF >= 1.13.3'],
     },
     tests_require=tests_require,
     entry_points={
diff --git a/src/ocrmypdf/pdfinfo.py b/src/ocrmypdf/pdfinfo.py
index cf6ff54c..aafa69da 100644
--- a/src/ocrmypdf/pdfinfo.py
+++ b/src/ocrmypdf/pdfinfo.py
@@ -586,12 +586,7 @@ def _page_get_textblocks(infile, pageno):
     "Smarter text detection"
 
     doc = fitz.Document(infile)
-    if fitz.version[0] >= '1.13.0':
-        text = doc[pageno].getText('dict')
-    else:
-        import json
-        textjson = doc[pageno].getText('json')
-        text = json.loads(textjson)
+    text = doc[pageno].getText('dict')
     if not text:
         return