Remove last vestiges of command line usage of qpdf - change to check_pdf

src/ocrmypdf/_sync.py

@@ -64,8 +64,7 @@ from ._validation import (
     report_output_file_size,
 )
 from .exceptions import ExitCode, ExitCodeException
-from .exec import qpdf
-from .helpers import available_cpu_count
+from .helpers import available_cpu_count, check_pdf
 from .pdfa import file_claims_pdfa
 
 log = logging.getLogger(__name__)
@@ -357,7 +356,7 @@ def run_pipeline(options, api=False):
                         pdfa_info['conformance'],
                     )
                     return ExitCode.pdfa_conversion_failed
-            if not qpdf.check(options.output_file):
+            if not check_pdf(options.output_file):
                 log.warning('Output file: The generated PDF is INVALID')
                 return ExitCode.invalid_output_pdf
             report_output_file_size(options, start_input_file, options.output_file)

src/ocrmypdf/_validation.py

@@ -38,7 +38,6 @@ from .exec import (
     ghostscript,
     jbig2enc,
     pngquant,
-    qpdf,
     tesseract,
     unpaper,
 )
@@ -473,9 +472,3 @@ def check_dependency_versions(options):
             "supported. Please upgrade to a newer version, or downgrade to the "
             "previous version."
         )
-    check_external_program(
-        program='qpdf',
-        package='qpdf',
-        version_checker=qpdf.version,
-        need_version='8.0.2',
-    )

src/ocrmypdf/exec/qpdf.py

@@ -1,63 +0,0 @@
-# © 2017 James R. Barlow: github.com/jbarlow83
-#
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
-
-"""Interface to qpdf executable"""
-
-import logging
-from io import StringIO
-
-import pikepdf
-
-log = logging.getLogger(__name__)
-
-
-def version():
-    return pikepdf.__libqpdf_version__
-
-
-def check(input_file):
-    pdf = None
-    try:
-        pdf = pikepdf.open(input_file)
-    except pikepdf.PdfError as e:
-        log.error(e)
-        return False
-    else:
-        messages = pdf.check()
-        for msg in messages:
-            if 'error' in msg.lower():
-                log.error(msg)
-            else:
-                log.warning(msg)
-
-        sio = StringIO()
-        linearize = None
-        try:
-            pdf.check_linearization(sio)
-        except RuntimeError:
-            pass
-        else:
-            linearize = sio.getvalue()
-            if linearize:
-                log.warning(linearize)
-
-        if not messages and not linearize:
-            return True
-        return False
-    finally:
-        if pdf:
-            pdf.close()

src/ocrmypdf/helpers.py

@@ -24,9 +24,12 @@ from collections import namedtuple
 from collections.abc import Iterable
 from contextlib import suppress
 from functools import wraps
+from io import StringIO
 from math import inf, isclose
 from pathlib import Path
 
+import pikepdf
+
 log = logging.getLogger(__name__)
 
 
@@ -165,6 +168,40 @@ def is_file_writable(test_file: os.PathLike):
         return False
 
 
+def check_pdf(input_file):
+    pdf = None
+    try:
+        pdf = pikepdf.open(input_file)
+    except pikepdf.PdfError as e:
+        log.error(e)
+        return False
+    else:
+        messages = pdf.check()
+        for msg in messages:
+            if 'error' in msg.lower():
+                log.error(msg)
+            else:
+                log.warning(msg)
+
+        sio = StringIO()
+        linearize = None
+        try:
+            pdf.check_linearization(sio)
+        except RuntimeError:
+            pass
+        else:
+            linearize = sio.getvalue()
+            if linearize:
+                log.warning(linearize)
+
+        if not messages and not linearize:
+            return True
+        return False
+    finally:
+        if pdf:
+            pdf.close()
+
+
 def deprecated(func):
     """Warn that function is deprecated"""