pytest picky about list vs tuple

Fixes #523

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,36 @@
+---
+name: Bug report
+about: Create a report to help us improve
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+**To Reproduce**
+What command line or API call were you trying to run?
+
+```bash
+ocrmypdf  ...arguments... input.pdf output.pdf
+```
+
+Run with verbosity or higher `-v1` to see more detailed logging. This information may be helpful.
+
+**Example file**
+Please include an example *input* PDF (or image). The input file is more helpful.
+
+If possible, use an input file with no personal or confidential information. At your option you may GPG-encrypt the file for OCRmyPDF's author only.
+
+**Expected behavior**
+A clear and concise description of what you expected to happen.
+
+**Screenshots**
+If applicable, add screenshots to help explain your problem.
+
+**System**
+ - OS: [e.g. Linux, Windows, macOS]
+ - OCRmyPDF Version: ``ocrmypdf --version``
+ - How did you install ocrmypdf? Did you use a system package manager, `pip`, or a Docker image?

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,17 @@
+---
+name: Feature request
+about: Suggest an idea for this project
+title: ''
+labels: enhancement
+assignees: ''
+
+---
+
+**Is your feature request related to a problem? Please describe.**
+A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
+
+**Describe the solution you'd like**
+A clear and concise description of what you want to happen.
+
+**Additional context**
+Add any other context or screenshots about the feature request here.

docs/api.rst

@@ -51,6 +51,14 @@ Forking a child process to call ``ocrmypdf.ocr()`` is suggested. That
 way your application will survive and remain interactive even if
 OCRmyPDF does not.
 
+.. warning::
+
+    On Windows, the script that calls ``ocrmypdf.ocr()`` must be protected
+    by an "ifmain" guard (``if __name__ == '__main__'``) or you must use
+    ``ocrmypdf.ocr(...use_threads=True)``. If you do not take at least one
+    of these steps, Windows fork semantics will prevent OCRmyPDF from working
+    correct.
+
 Logging
 -------
 

docs/batch.rst

@@ -202,6 +202,13 @@ Alternatives
 -  `Watchman <https://facebook.github.io/watchman/>`__ is a more
    powerful alternative to ``watchmedo``.
 
+AWS Lambda is not viable
+------------------------
+
+AWS Lambda and its equivalents have low limits on execution time and payload
+size, relative to OCRmyPDF's needs. As of this writing, the request/response
+payload for AWS Lambda was 6 MB, which means many PDFs will not fit.
+
 macOS Automator
 ===============
 

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 +13,19 @@ 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
+======
+
+-  Fixed version check failing when used with qpdf 10.0.0.
+-  Added some missing type annotations.
+-  Updated documentation to warn about need for "ifmain" guard and Windows.
 
 v9.7.0
 ======

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
 
@@ -67,7 +67,11 @@ class Verbosity(IntEnum):
     debug_all = 2  #: More detailed debugging from ocrmypdf and dependent modules
 
 
-def configure_logging(verbosity, progress_bar_friendly=True, manage_root_logger=False):
+def configure_logging(
+    verbosity: Verbosity,
+    progress_bar_friendly: bool = True,
+    manage_root_logger: bool = False,
+):
     """Set up logging.
 
     Library users may wish to use this function if they want their log output to be
@@ -128,7 +132,7 @@ def configure_logging(verbosity, progress_bar_friendly=True, manage_root_logger=
     return log
 
 
-def create_options(*, input_file, output_file, **kwargs):
+def create_options(*, input_file: os.PathLike, output_file: os.PathLike, **kwargs):
     cmdline = []
     deferred = []
 
@@ -150,6 +154,12 @@ def create_options(*, input_file, output_file, **kwargs):
                 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)):
@@ -180,7 +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,
@@ -210,7 +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,

src/ocrmypdf/exec/__init__.py

@@ -23,6 +23,7 @@ import re
 import shutil
 import sys
 from collections.abc import Mapping
+from distutils.version import LooseVersion
 from functools import lru_cache
 from subprocess import PIPE, STDOUT, CalledProcessError
 from subprocess import run as subprocess_run
@@ -270,7 +271,15 @@ def check_external_program(
             raise MissingDependencyError()
         return
 
-    if found_version < need_version:
+    def remove_leading_v(s):
+        if s.startswith('v'):
+            return s[1:]
+        return s
+
+    found_version = remove_leading_v(found_version)
+    need_version = remove_leading_v(need_version)
+
+    if LooseVersion(found_version) < LooseVersion(need_version):
         _error_old_version(program, package, need_version, found_version, required_for)
         if not recommended:
             raise MissingDependencyError()

src/ocrmypdf/helpers.py

@@ -28,7 +28,7 @@ from pathlib import Path
 log = logging.getLogger(__name__)
 
 
-def safe_symlink(input_file, soft_link_name, *args, **kwargs):
+def safe_symlink(input_file: os.PathLike, soft_link_name: os.PathLike, *args, **kwargs):
     """
     Helper function: relinks soft symbolic link if necessary
     """
@@ -76,12 +76,12 @@ def is_iterable_notstr(thing):
     return isinstance(thing, Iterable) and not isinstance(thing, str)
 
 
-def monotonic(L):
+def monotonic(L: Iterable):
     """Does list increase monotonically?"""
     return all(b > a for a, b in zip(L, L[1:]))
 
 
-def page_number(input_file):
+def page_number(input_file: os.PathLike):
     """Get one-based page number implied by filename (000002.pdf -> 2)"""
     return int(os.path.basename(os.fspath(input_file))[0:6])
 
@@ -97,7 +97,7 @@ def available_cpu_count():
     return 1
 
 
-def is_file_writable(test_file):
+def is_file_writable(test_file: os.PathLike):
     """Intentionally racy test if target is writable.
 
     We intend to write to the output file if and only if we succeed and

src/ocrmypdf/pdfinfo/info.py

@@ -22,7 +22,7 @@ from collections import defaultdict, namedtuple
 from decimal import Decimal
 from enum import Enum
 from math import hypot, isclose
-from os import fspath
+from os import PathLike, fspath
 from pathlib import Path
 from warnings import warn
 
@@ -40,7 +40,7 @@ logger = logging.getLogger()
 Colorspace = Enum('Colorspace', 'gray rgb cmyk lab icc index sep devn pattern jpeg2000')
 
 Encoding = Enum(
-    'Encoding', 'ccitt jpeg jpeg2000 jbig2 asciihex ascii85 lzw flate ' + 'runlength'
+    'Encoding', 'ccitt jpeg jpeg2000 jbig2 asciihex ascii85 lzw flate runlength'
 )
 
 FRIENDLY_COLORSPACE = {
@@ -558,7 +558,7 @@ def simplify_textboxes(miner, textbox_getter):
         yield TextboxInfo(box.bbox, visible, corrupt)
 
 
-def _pdf_get_pageinfo(pdf, pageno: int, infile, xmltext):
+def _pdf_get_pageinfo(pdf, pageno: int, infile: PathLike, xmltext: str):
     pageinfo = {}
     pageinfo['pageno'] = pageno
     pageinfo['images'] = []

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'])

tests/test_validation.py

@@ -176,3 +176,37 @@ def test_language_warning(caplog):
         vd.check_options_languages(opts)
         assert opts.language == ['eng']
         assert 'assuming --language' in caplog.text
+
+
+def test_version_comparison():
+    vd.check_external_program(
+        program="dummy_basic",
+        package="dummy",
+        version_checker=lambda: '9.0',
+        need_version='8.0.2',
+    )
+    vd.check_external_program(
+        program="dummy_doubledigit",
+        package="dummy",
+        version_checker=lambda: '10.0',
+        need_version='8.0.2',
+    )
+    vd.check_external_program(
+        program="tesseract",
+        package="tesseract",
+        version_checker=lambda: '4.0.0-beta.1',
+        need_version='4.0.0',
+    )
+    vd.check_external_program(
+        program="tesseract",
+        package="tesseract",
+        version_checker=lambda: 'v5.0.0-alpha.20200201',
+        need_version='4.0.0',
+    )
+    with pytest.raises(MissingDependencyError):
+        vd.check_external_program(
+            program="dummy_fails",
+            package="dummy",
+            version_checker=lambda: '1.0',
+            need_version='2.0',
+        )