Briq
/
camelot-py
6
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Raise ghostscript deprecation warning and skip ghostscript tests on windows

pull/253/head
Vinayak Mehta 2021-07-11 18:55:56 +05:30
parent 793ddaf42f
commit f160c1d44d
No known key found for this signature in database
GPG Key ID: 2DE013537A15A9A4
7 changed files with 57 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
camelot/parsers/lattice.py
View File

@ -141,6 +141,12 @@ class Lattice(BaseParser):
if isinstance(backend, str):
if backend in BACKENDS.keys():
if backend == "ghostscript":
raise DeprecationWarning(
"'ghostscript' will be replaced by 'poppler' as the default image conversion"
" backend in v0.12.0. You can try out 'poppler' with backend='poppler'."
)
return BACKENDS[backend]()
else:
raise NotImplementedError(

16
docs/user/advanced.rst
View File

@ -629,7 +629,14 @@ To deal with such cases, you can tweak PDFMiner's `LAParams kwargs <https://gith
Use alternate image conversion backends
---------------------------------------
When using the :ref:`Lattice <lattice>` flavor, Camelot uses `pdftopng <https://github.com/vinayak-mehta/pdftopng>`_ to convert PDF pages to images for line recognition. This should work out of the box on most operating systems. However, if you get an error, you can supply your own image conversion backend to Camelot::
When using the :ref:`Lattice <lattice>` flavor, Camelot uses ``ghostscript`` to convert PDF pages to images for line recognition. If you face installation issues with ``ghostscript``, you can use an alternate image conversion backend called ``poppler``. You can specify which image conversion backend you want to use with::
>>> tables = camelot.read_pdf(filename, backend="ghostscript") # default
>>> tables = camelot.read_pdf(filename, backend="poppler")
.. note:: ``poppler`` will be made the default image conversion backend (replacing ``ghostscript``) with ``v0.12.0``.
If you face issues with both ``ghostscript`` and ``poppler``, you can supply your own image conversion backend::
>>> class ConversionBackend(object):
>>> def convert(pdf_path, png_path):
@ -639,10 +646,3 @@ When using the :ref:`Lattice <lattice>` flavor, Camelot uses `pdftopng <https://
>>> pass
>>>
>>> tables = camelot.read_pdf(filename, backend=ConversionBackend())
.. note:: If image conversion using ``pdftopng`` fails, Camelot falls back to ``ghostscript`` to try image conversion again, and if that fails, it raises an error.
In case you want to be explicit about the image conversion backend that Camelot should use, you can supply them like this::
>>> tables = camelot.read_pdf(filename, backend="poppler")
>>> tables = camelot.read_pdf(filename, backend="ghostscript")

3
tests/test_cli.py
View File

@ -11,6 +11,8 @@ from camelot.utils import TemporaryDirectory
testdir = os.path.dirname(os.path.abspath(__file__))
testdir = os.path.join(testdir, "files")
skip_on_windows = pytest.mark.skip(sys.platform.startswith("win"))
def test_help_output():
runner = CliRunner()
@ -26,6 +28,7 @@ def test_help_output():
)
@skip_on_windows
def test_cli_lattice():
with TemporaryDirectory() as tempdir:
infile = os.path.join(testdir, "foo.pdf")

15
tests/test_common.py
View File

@ -16,6 +16,8 @@ from .data import *
testdir = os.path.dirname(os.path.abspath(__file__))
testdir = os.path.join(testdir, "files")
skip_on_windows = pytest.mark.skip(sys.platform.startswith("win"))
def test_version_generation():
version = (0, 7, 3)
@ -32,6 +34,7 @@ def test_version_generation_with_prerelease_revision():
)
@skip_on_windows
def test_parsing_report():
parsing_report = {"accuracy": 99.02, "whitespace": 12.24, "order": 1, "page": 1}
@ -61,10 +64,8 @@ def test_repr_poppler():
assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=219 x2=165 y2=234>"
@skip_on_windows
def test_repr_ghostscript():
if sys.platform not in ["linux", "darwin"]:
return True
filename = os.path.join(testdir, "foo.pdf")
tables = camelot.read_pdf(
filename,
@ -85,10 +86,8 @@ def test_url_poppler():
assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=219 x2=165 y2=234>"
@skip_on_windows
def test_url_ghostscript():
if sys.platform not in ["linux", "darwin"]:
return True
url = "https://camelot-py.readthedocs.io/en/master/_static/pdf/foo.pdf"
tables = camelot.read_pdf(
url, backend=ImageConversionBackend(backend="ghostscript", use_fallback=False)
@ -126,10 +125,8 @@ def test_pages_poppler():
assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=219 x2=165 y2=234>"
@skip_on_windows
def test_pages_ghostscript():
if sys.platform not in ["linux", "darwin"]:
return True
url = "https://camelot-py.readthedocs.io/en/master/_static/pdf/foo.pdf"
tables = camelot.read_pdf(
url, backend=ImageConversionBackend(backend="ghostscript", use_fallback=False)

16
tests/test_errors.py
View File

@ -12,6 +12,8 @@ testdir = os.path.dirname(os.path.abspath(__file__))
testdir = os.path.join(testdir, "files")
filename = os.path.join(testdir, "foo.pdf")
skip_on_windows = pytest.mark.skip(sys.platform.startswith("win"))
def test_unknown_flavor():
message = "Unknown flavor specified." " Use either 'lattice' or 'stream'"
@ -32,6 +34,7 @@ def test_unsupported_format():
tables = camelot.read_pdf(filename)
@skip_on_windows
def test_no_tables_found_logs_suppressed():
filename = os.path.join(testdir, "foo.pdf")
with warnings.catch_warnings():
@ -133,3 +136,16 @@ def test_lattice_no_convert_method():
message = "must implement a 'convert' method"
with pytest.raises(NotImplementedError, match=message):
tables = camelot.read_pdf(filename, backend=ConversionBackend())
def test_lattice_ghostscript_deprecation_warning():
ghostscript_deprecation_warning = (
"'ghostscript' will be replaced by 'poppler' as the default image conversion"
" backend in v0.12.0. You can try out 'poppler' with backend='poppler'."
)
with warnings.catch_warnings():
warnings.simplefilter("error")
with pytest.raises(DeprecationWarning) as e:
tables = camelot.read_pdf(filename)
assert str(e.value) == ghostscript_deprecation_warning

11
tests/test_lattice.py
View File

@ -14,7 +14,10 @@ from .data import *
testdir = os.path.dirname(os.path.abspath(__file__))
testdir = os.path.join(testdir, "files")
skip_on_windows = pytest.mark.skip(sys.platform.startswith("win"))
@skip_on_windows
def test_lattice():
df = pd.DataFrame(data_lattice)
@ -25,6 +28,7 @@ def test_lattice():
assert_frame_equal(df, tables[0].df)
@skip_on_windows
def test_lattice_table_rotated():
df = pd.DataFrame(data_lattice_table_rotated)
@ -37,6 +41,7 @@ def test_lattice_table_rotated():
assert_frame_equal(df, tables[0].df)
@skip_on_windows
def test_lattice_two_tables():
df1 = pd.DataFrame(data_lattice_two_tables_1)
df2 = pd.DataFrame(data_lattice_two_tables_2)
@ -48,6 +53,7 @@ def test_lattice_two_tables():
assert df2.equals(tables[1].df)
@skip_on_windows
def test_lattice_table_regions():
df = pd.DataFrame(data_lattice_table_regions)
@ -56,6 +62,7 @@ def test_lattice_table_regions():
assert_frame_equal(df, tables[0].df)
@skip_on_windows
def test_lattice_table_areas():
df = pd.DataFrame(data_lattice_table_areas)
@ -64,6 +71,7 @@ def test_lattice_table_areas():
assert_frame_equal(df, tables[0].df)
@skip_on_windows
def test_lattice_process_background():
df = pd.DataFrame(data_lattice_process_background)
@ -72,6 +80,7 @@ def test_lattice_process_background():
assert_frame_equal(df, tables[1].df)
@skip_on_windows
def test_lattice_copy_text():
df = pd.DataFrame(data_lattice_copy_text)
@ -80,6 +89,7 @@ def test_lattice_copy_text():
assert_frame_equal(df, tables[0].df)
@skip_on_windows
def test_lattice_shift_text():
df_lt = pd.DataFrame(data_lattice_shift_text_left_top)
df_disable = pd.DataFrame(data_lattice_shift_text_disable)
@ -96,6 +106,7 @@ def test_lattice_shift_text():
assert df_rb.equals(tables[0].df)
@skip_on_windows
def test_lattice_arabic():
df = pd.DataFrame(data_arabic)

19
tests/test_plotting.py
View File

@ -10,7 +10,10 @@ import camelot
testdir = os.path.dirname(os.path.abspath(__file__))
testdir = os.path.join(testdir, "files")
skip_on_windows = pytest.mark.skip(sys.platform.startswith("win"))
@skip_on_windows
@pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
def test_text_plot():
filename = os.path.join(testdir, "foo.pdf")
@ -32,11 +35,9 @@ def test_lattice_contour_plot_poppler():
return camelot.plot(tables[0], kind="contour")
@skip_on_windows
@pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
def test_lattice_contour_plot_ghostscript():
if sys.platform not in ["linux", "darwin"]:
pytest.skip("Skipping ghostscript test on Windows")
filename = os.path.join(testdir, "foo.pdf")
tables = camelot.read_pdf(filename, backend="ghostscript")
return camelot.plot(tables[0], kind="contour")
@ -56,11 +57,9 @@ def test_line_plot_poppler():
return camelot.plot(tables[0], kind="line")
@skip_on_windows
@pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
def test_line_plot_ghostscript():
if sys.platform not in ["linux", "darwin"]:
pytest.skip("Skipping ghostscript test on Windows")
filename = os.path.join(testdir, "foo.pdf")
tables = camelot.read_pdf(filename, backend="ghostscript")
return camelot.plot(tables[0], kind="line")
@ -73,11 +72,9 @@ def test_joint_plot_poppler():
return camelot.plot(tables[0], kind="joint")
@skip_on_windows
@pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
def test_joint_plot_ghostscript():
if sys.platform not in ["linux", "darwin"]:
pytest.skip("Skipping ghostscript test on Windows")
filename = os.path.join(testdir, "foo.pdf")
tables = camelot.read_pdf(filename, backend="ghostscript")
return camelot.plot(tables[0], kind="joint")
@ -90,11 +87,9 @@ def test_grid_plot_poppler():
return camelot.plot(tables[0], kind="grid")
@skip_on_windows
@pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
def test_grid_plot_ghostscript():
if sys.platform not in ["linux", "darwin"]:
pytest.skip("Skipping ghostscript test on Windows")
filename = os.path.join(testdir, "foo.pdf")
tables = camelot.read_pdf(filename, backend="ghostscript")
return camelot.plot(tables[0], kind="grid")