Ensure specified destination is writable before starting pipeline process

ocrmypdf/__main__.py

@@ -26,7 +26,7 @@ import ruffus.proxy_logger as proxy_logger
 from .pipeline import JobContext, JobContextManager, re_symlink, \
     cleanup_working_files, build_pipeline
 from .pdfa import file_claims_pdfa
-from .helpers import is_iterable_notstr, re_symlink
+from .helpers import is_iterable_notstr, re_symlink, is_file_writable
 from .exec import tesseract, qpdf
 from . import PROGRAM_NAME, VERSION
 
@@ -518,6 +518,10 @@ def run_pipeline():
                     is connected to a terminal.  Please redirect stdout to a
                     file."""))
                 return ExitCode.bad_args
+        elif not is_file_writable(options.output_file):
+                _log.error(textwrap.dedent("""\
+                    Cutput file location is not writable."""))
+                return ExitCode.file_access_error
 
         manager = JobContextManager()
         manager.register('JobContext', JobContext)

ocrmypdf/helpers.py

@@ -3,6 +3,7 @@
 
 from functools import partial
 from collections.abc import Iterable
+from contextlib import suppress
 import sys
 import os
 
@@ -53,3 +54,26 @@ def is_iterable_notstr(thing):
 
 def page_number(input_file):
     return int(os.path.basename(input_file)[0:6])
+
+
+def is_file_writable(test_file):
+    """Intentionally racy test if target is writable.
+
+    We intend to write to the output file if and only if we succeed and
+    can replace it atomically. Before doing the OCR work, make sure
+    the location is writable.
+    """
+    if os.path.exists(test_file):
+        return os.access(
+            test_file, os.W_OK,
+            effective_ids=(os.access in os.supports_effective_ids))
+    else:
+        try:
+            fp = open(test_file, 'wb')
+        except OSError as e:
+            return False
+        else:
+            fp.close()
+            with suppress(OSError):
+                os.unlink(test_file)
+        return True

tests/test_main.py

@@ -680,3 +680,13 @@ def test_very_high_dpi(spoof_tesseract_cache, resources, outpdf):
 def test_overlay(spoof_tesseract_noop, resources, outpdf):
     check_ocrmypdf(resources / 'overlay.pdf', outpdf,
                    env=spoof_tesseract_noop)
+
+
+def test_destination_not_writable(spoof_tesseract_noop, resources, outdir):
+    protected_file = outdir / 'protected.pdf'
+    protected_file.touch()
+    protected_file.chmod(0o400)  # Read-only
+    p, out, err = run_ocrmypdf(
+        resources / 'jbig2.pdf', protected_file,
+        env=spoof_tesseract_noop)
+    assert p.returncode == ExitCode.file_access_error, "Expected error"

tests/test_tess4.py

@@ -15,20 +15,13 @@ from ocrmypdf.pdfa import file_claims_pdfa
 from ocrmypdf.exec import tesseract
 
 
-TESTS_ROOT = os.path.abspath(os.path.dirname(__file__))
-SPOOF_PATH = os.path.join(TESTS_ROOT, 'spoof')
-PROJECT_ROOT = os.path.dirname(TESTS_ROOT)
-TEST_RESOURCES = os.path.join(PROJECT_ROOT, 'tests', 'resources')
-OCRMYPDF = [sys.executable, '-m', 'ocrmypdf']
-
-
 # Skip all tests in this file if not tesseract 4
 pytestmark = pytest.mark.skipif(not tesseract.v4(),
                                 reason="tesseract 4.0 required")
 
 
 @pytest.mark.skipif(not tesseract.has_textonly_pdf(),
-                    reason="requires textonly_pdf parameter")
+                    reason="requires textonly_pdf feature")
 def test_textonly_pdf(resources, outdir):
     pytest.helpers.check_ocrmypdf(
         resources / 'linn.pdf',