[IMP] Add conversion exception message to feedback

[IMP] Ghostscriptbackend add exception message passtrough

[IMP] Error tests and feedback message

camelot/backends/ghostscript_backend.py

@@ -25,7 +25,7 @@ def convert(self, pdf_path: str, png_path: str, resolution: int = 300) -> None:
  """
  try:
  import ghostscript # type: ignore[import-untyped]
- except RuntimeError:
+ except ModuleNotFoundError as ex:
  raise OSError(
  "Ghostscript is not installed. You can install it using the instructions"
  " here: https://pypdf-table-extraction.readthedocs.io/en/latest/user/install-deps.html"

camelot/backends/image_conversion.py

@@ -73,10 +73,10 @@ def convert(self, pdf_path: str, png_path: str) -> None:
  converter = BACKENDS[fallback]()
  converter.convert(pdf_path, png_path)
  except Exception as e:
- msg = f"Image conversion failed with image conversion backend {fallback!r}"
+ msg = f"Image conversion failed with image conversion backend {fallback!r}\n error: {e}"
  raise ImageConversionError(msg) from e
  else:
  break
  else:
- msg = f"Image conversion failed with image conversion backend {self.backend!r}"
+ msg = f"Image conversion failed with image conversion backend {self.backend!r}\n error: {f}"
  raise ImageConversionError(msg) from f

tests/test_common.py

@@ -73,17 +73,17 @@ def test_url_ghostscript(testdir):
 @skip_pdftopng
 def test_pages_poppler():
  url = "https://pypdf-table-extraction.readthedocs.io/en/latest/_static/pdf/foo.pdf"
- tables = camelot.read_pdf(url, backend="poppler")
+ tables = camelot.read_pdf(url, backend="poppler", use_fallback=False)
  assert repr(tables) == "<TableList n=1>"
  assert repr(tables[0]) == "<Table shape=(7, 7)>"
  assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=219 x2=165 y2=234>"
 
- tables = camelot.read_pdf(url, pages="1-end", backend="poppler")
+ tables = camelot.read_pdf(url, pages="1-end", backend="poppler", use_fallback=False)
  assert repr(tables) == "<TableList n=1>"
  assert repr(tables[0]) == "<Table shape=(7, 7)>"
  assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=219 x2=165 y2=234>"
 
- tables = camelot.read_pdf(url, pages="all", backend="poppler")
+ tables = camelot.read_pdf(url, pages="all", backend="poppler", use_fallback=False)
  assert repr(tables) == "<TableList n=1>"
  assert repr(tables[0]) == "<Table shape=(7, 7)>"
  assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=219 x2=165 y2=234>"
@@ -92,17 +92,21 @@ def test_pages_poppler():
 @skip_on_windows
 def test_pages_ghostscript():
  url = "https://pypdf-table-extraction.readthedocs.io/en/latest/_static/pdf/foo.pdf"
- tables = camelot.read_pdf(url, backend="ghostscript")
+ tables = camelot.read_pdf(url, backend="ghostscript", use_fallback=False)
  assert repr(tables) == "<TableList n=1>"
  assert repr(tables[0]) == "<Table shape=(7, 7)>"
  assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=218 x2=165 y2=234>"
 
- tables = camelot.read_pdf(url, pages="1-end", backend="ghostscript")
+ tables = camelot.read_pdf(
+ url, pages="1-end", backend="ghostscript", use_fallback=False
+ )
  assert repr(tables) == "<TableList n=1>"
  assert repr(tables[0]) == "<Table shape=(7, 7)>"
  assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=218 x2=165 y2=234>"
 
- tables = camelot.read_pdf(url, pages="all", backend="ghostscript")
+ tables = camelot.read_pdf(
+ url, pages="all", backend="ghostscript", use_fallback=False
+ )
  assert repr(tables) == "<TableList n=1>"
  assert repr(tables[0]) == "<Table shape=(7, 7)>"
  assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=218 x2=165 y2=234>"

tests/test_errors.py

@@ -1,9 +1,12 @@
 import os
+import sys
 import warnings
+from unittest import mock
 
 import pytest
 
 import camelot
+from camelot.backends.image_conversion import ImageConversionError
 from camelot.utils import is_url
 from tests.conftest import skip_on_windows
 
@@ -122,7 +125,9 @@ def test_lattice_no_tables_on_page(testdir):
 def test_lattice_unknown_backend(foo_pdf):
  message = "Unknown backend 'mupdf' specified. Please use either 'poppler' or 'ghostscript'."
  with pytest.raises(NotImplementedError, match=message):
- tables = camelot.read_pdf(foo_pdf, backend="mupdf")
+ tables = camelot.read_pdf(
+ foo_pdf, flavor="lattice", backend="mupdf", use_fallback=False
+ )
 
 
 def test_lattice_no_convert_method(foo_pdf):
@@ -131,7 +136,9 @@ class ConversionBackend:
 
  message = "must implement a 'convert' method"
  with pytest.raises(NotImplementedError, match=message):
- camelot.read_pdf(foo_pdf, backend=ConversionBackend())
+ camelot.read_pdf(
+ foo_pdf, flavor="lattice", backend=ConversionBackend(), use_fallback=False
+ )
 
 
 def test_invalid_url():
@@ -140,3 +147,17 @@ def test_invalid_url():
  with pytest.raises(Exception, match=message):
  url = camelot.read_pdf(url)
  assert is_url(url) == False
+
+
+def test_ghostscript_backend_import_error(testdir):
+ filename = os.path.join(testdir, "table_region.pdf")
+ with mock.patch.dict(sys.modules, {"ghostscript": None}):
+ message = "Ghostscript is not installed"
+ with pytest.raises(ImageConversionError) as e:
+ tables = camelot.read_pdf(
+ filename,
+ flavor="lattice",
+ backend="ghostscript",
+ use_fallback=False,
+ )
+ assert message in str(e.value)

tests/test_image_conversion_backend.py

@@ -54,6 +54,6 @@ def test_ghostscript_backend_error_when_use_fallback(monkeypatch):
  )
  backend = ImageConversionBackend(backend="ghostscript")
 
- message = "Image conversion failed with image conversion backend 'ghostscript'"
+ message = "Image conversion failed with image conversion backend 'poppler'\n error: Image conversion failed"
  with pytest.raises(ValueError, match=message):
  backend.convert("foo", "bar")