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

Update stream table regions logic

pull/2/head
Vinayak Mehta 2019-01-04 20:27:53 +05:30
parent d064f716e9
commit f94777038a
1 changed files with 7 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
camelot/parsers/stream.py
View File

@ -281,11 +281,16 @@ class Stream(BaseParser):
def _generate_table_bbox(self): def _generate_table_bbox(self):
self.textedges = [] self.textedges = []
if self.table_areas is None: if self.table_areas is None:
hor_text = self.horizontal_text
if self.table_regions is not None: if self.table_regions is not None:
# filter horizontal text # filter horizontal text
pass hor_text = []
for region in self.table_regions:
x1, y1, x2, y2 = region
region_text = text_in_bbox((x1, y2, x2, y1), self.horizontal_text)
hor_text.extend(region_text)
# find tables based on nurminen's detection algorithm # find tables based on nurminen's detection algorithm
table_bbox = self._nurminen_table_detection(self.horizontal_text) table_bbox = self._nurminen_table_detection(hor_text)
else: else:
table_bbox = {} table_bbox = {}
for area in self.table_areas: for area in self.table_areas: