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

Add test

pull/2/head
Vinayak Mehta 2019-05-27 22:18:23 +05:30
parent b2a8348f13
commit de3281c1b6
2 changed files with 12 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
camelot/parsers/stream.py
View File

@ -287,6 +287,10 @@ class Stream(BaseParser):
hor_text = [] hor_text = []
for region in self.table_regions: for region in self.table_regions:
x1, y1, x2, y2 = region.split(",") x1, y1, x2, y2 = region.split(",")
x1 = float(x1)
y1 = float(y1)
x2 = float(x2)
y2 = float(y2)
region_text = text_in_bbox((x1, y2, x2, y1), self.horizontal_text) region_text = text_in_bbox((x1, y2, x2, y1), self.horizontal_text)
hor_text.extend(region_text) hor_text.extend(region_text)
# find tables based on nurminen's detection algorithm # find tables based on nurminen's detection algorithm

8
tests/test_common.py
View File

@ -69,6 +69,14 @@ def test_stream_two_tables():
assert df2.equals(tables[1].df) assert df2.equals(tables[1].df)
def test_stream_table_regions():
df = pd.DataFrame(data_stream_table_areas)
filename = os.path.join(testdir, "tabula/us-007.pdf")
tables = camelot.read_pdf(filename, flavor="stream", table_areas=["320,460,573,335"])
assert df.equals(tables[0].df)
def test_stream_table_areas(): def test_stream_table_areas():
df = pd.DataFrame(data_stream_table_areas) df = pd.DataFrame(data_stream_table_areas)