Ensure sidecar is not input or output file

src/ocrmypdf/_validation.py

@@ -112,6 +112,10 @@ def check_options_sidecar(options):
                 "--sidecar filename must be specified when output file is stdout."
             )
         options.sidecar = options.output_file + '.txt'
+    if options.sidecar == options.input_file or options.sidecar == options.output_file:
+        raise BadArgsError(
+            "--sidecar file must be different from the input and output files"
+        )
 
 
 def check_options_preprocessing(options):

src/ocrmypdf/cli.py

@@ -167,7 +167,8 @@ Online documentation is located at:
         metavar='FILE',
         help="Generate sidecar text files that contain the same text recognized "
         "by Tesseract. This may be useful for building a OCR text database. "
-        "If FILE is omitted, the sidecar file be named {output_file}.txt "
+        "If FILE is omitted, the sidecar file be named {output_file}.txt; the next "
+        "argument must NOT be the name of the input PDF. "
         "If FILE is set to '-', the sidecar is written to stdout (a "
         "convenient way to preview OCR quality). The output file and sidecar "
         "may not both use stdout at the same time.",

tests/test_validation.py

@@ -18,6 +18,8 @@ from ocrmypdf.cli import get_parser
 from ocrmypdf.exceptions import BadArgsError, MissingDependencyError
 from ocrmypdf.pdfinfo import PdfInfo
 
+run_ocrmypdf_api = pytest.helpers.run_ocrmypdf_api
+
 
 def make_opts_pm(input_file='a.pdf', output_file='b.pdf', language='eng', **kwargs):
     if language is not None:
@@ -270,3 +272,9 @@ def test_two_languages():
             *make_opts_pm(language='fakelang1+fakelang2'), {'fakelang1', 'fakelang2'}
         )
         mock.assert_called()
+
+
+def test_sidecar_equals_output(resources, no_outpdf):
+    op = no_outpdf
+    with pytest.raises(BadArgsError, match=r'--sidecar'):
+        run_ocrmypdf_api(resources / 'trivial.pdf', op, '--sidecar', op)