pytest picky about list vs tuple

Fixes #523

docs/docker.rst

@@ -90,10 +90,8 @@ Docker volume:
 
 .. code-block:: bash
 
-   docker run --rm -v $(pwd):/data ocrmypdf /data/input.pdf /data/output.pdf
-
-(However, when done this way, ``output.pdf`` may be owned by the root
-user.)
+   alias docker_ocrmypdf='docker run --rm  -i --user "$(id -u):$(id -g)" --workdir /data -v "$PWD:/data" ocrmypdf'
+   docker_ocrmypdf /data/input.pdf /data/output.pdf
 
 .. _docker-lang-packs:
 

docs/release_notes.rst

@@ -13,6 +13,12 @@ Note that it is licensed under GPLv3, so scripts that
 ``import ocrmypdf`` and are released publicly should probably also be
 licensed under GPLv3.
 
+v9.7.2
+======
+
+-  Fixed an issue with ``ocrmypdf.ocr(...language=)`` not accepting a list of
+   languages as documented.
+-  Updated setup.py to confirm that pdfminer.six version 20200402 is supported.
 
 v9.7.1
 ======

requirements/main.txt

@@ -3,7 +3,7 @@
 # installation
 cffi == 1.14.0
 img2pdf == 0.3.3
-pdfminer.six == 20200124
+pdfminer.six == 20200402
 pikepdf == 1.10.2
 Pillow == 7.0.0
 reportlab == 3.5.34

setup.py

@@ -98,7 +98,7 @@ setup(
         'chardet >= 3.0.4, < 4',  # unlisted requirement of pdfminer.six 20181108
         'cffi >= 1.9.1',  # must be a setup and install requirement
         'img2pdf >= 0.3.0, < 0.4',  # pure Python, so track HEAD closely
-        'pdfminer.six >= 20181108, <= 20200124',
+        'pdfminer.six >= 20181108, <= 20200402',
         'pikepdf >= 1.8.1, < 2',
         'Pillow >= 6.2.0',
         'reportlab >= 3.3.0',  # oldest released version with sane image handling

src/ocrmypdf/api.py

@@ -21,7 +21,7 @@ import sys
 from contextlib import suppress
 from enum import IntEnum
 from pathlib import Path
-from typing import Dict, List
+from typing import Dict, Iterable
 
 from tqdm import tqdm
 
@@ -154,6 +154,12 @@ def create_options(*, input_file: os.PathLike, output_file: os.PathLike, **kwarg
                 cmdline.append(f"--{cmd_style_arg}")
             continue
 
+        if isinstance(val, Iterable) and not isinstance(val, str):
+            for elem in val:
+                cmdline.append(f"--{cmd_style_arg}")
+                cmdline.append(elem)
+            continue
+
         # We have a parameter
         cmdline.append(f"--{cmd_style_arg}")
         if isinstance(val, (int, float)):
@@ -184,7 +190,7 @@ def ocr(  # pylint: disable=unused-argument
     input_file: os.PathLike,
     output_file: os.PathLike,
     *,
-    language: List[str] = None,
+    language: Iterable[str] = None,
     image_dpi: int = None,
     output_type=None,
     sidecar: os.PathLike = None,
@@ -214,7 +220,7 @@ def ocr(  # pylint: disable=unused-argument
     jbig2_page_group_size: int = None,
     pages: str = None,
     max_image_mpixels: float = None,
-    tesseract_config: List[str] = None,
+    tesseract_config: Iterable[str] = None,
     tesseract_pagesegmode: int = None,
     tesseract_oem: int = None,
     pdf_renderer=None,

tests/test_api.py

@@ -59,3 +59,10 @@ def test_tqdm_console():
 
     log.info("done")
     assert not before_pbar("done")
+
+
+def test_language_list():
+    with pytest.raises(
+        (ocrmypdf.exceptions.InputFileError, ocrmypdf.exceptions.MissingDependencyError)
+    ):
+        ocrmypdf.ocr('doesnotexist.pdf', '_.pdf', language=['eng', 'deu'])