Add test for arabic

tests/data.py

@@ -486,3 +486,11 @@ data_lattice_shift_text_right_bottom = [
     ["", "2400", "Men (≥ 18 yrs)", "-", "-", "-", "1728"],
     ["Knowledge &Practices on HTN &DM", "2400", "Women (≥ 18 yrs)", "-", "-", "-", "1728"]
 ]
+
+data_arabic = [
+    ['ً\n\xa0\nﺎﺒﺣﺮﻣ', 'ﻥﺎﻄﻠﺳ\xa0ﻲﻤﺳﺍ'],
+    ['ﻝﺎﻤﺸﻟﺍ\xa0ﺎﻨﻴﻟﻭﺭﺎﻛ\xa0ﺔﻳﻻﻭ\xa0ﻦﻣ\xa0ﺎﻧﺍ', '؟ﺖﻧﺍ\xa0ﻦﻳﺍ\xa0ﻦﻣ'],
+    ['1234', 'ﻂﻄﻗ\xa047\xa0ﻱﺪﻨﻋ'],
+    ['؟ﻙﺎﺒﺷ\xa0ﺖﻧﺍ\xa0ﻞﻫ', 'ﺔﻳﺰﻴﻠﺠﻧﻻﺍ\xa0ﻲﻓ\xa0Jeremy\xa0ﻲﻤﺳﺍ'],
+    ['Jeremy\xa0is\xa0ﻲﻣﺮﺟ\xa0in\xa0Arabic', '']
+]

tests/test_common.py

@@ -179,3 +179,11 @@ def test_repr():
     assert repr(tables) == "<TableList n=1>"
     assert repr(tables[0]) == "<Table shape=(7, 7)>"
     assert repr(tables[0].cells[0][0]) == "<Cell x1=120.48 y1=218.42 x2=164.64 y2=233.89>"
+
+
+def test_arabic():
+    df = pd.DataFrame(data_arabic)
+
+    filename = os.path.join(testdir, "tabula/arabic.pdf")
+    tables = camelot.read_pdf(filename)
+    assert df.equals(tables[0].df)