Renames the keyword table_area to table_areas (#171)
`table_areas` sounds more apt since it is a list and there can be multiple table areas on a page. Closes #165
This commit is contained in:
committed by
Vinayak Mehta
parent
8205e0e9ab
commit
32df09ad1c
+6
-6
@@ -48,7 +48,7 @@ def cli(ctx, *args, **kwargs):
|
||||
|
||||
|
||||
@cli.command('lattice')
|
||||
@click.option('-T', '--table_area', default=[], multiple=True,
|
||||
@click.option('-T', '--table_areas', default=[], multiple=True,
|
||||
help='Table areas to process. Example: x1,y1,x2,y2'
|
||||
' where x1, y1 -> left-top and x2, y2 -> right-bottom.')
|
||||
@click.option('-back', '--process_background', is_flag=True,
|
||||
@@ -95,8 +95,8 @@ def lattice(c, *args, **kwargs):
|
||||
filepath = kwargs.pop('filepath')
|
||||
kwargs.update(conf)
|
||||
|
||||
table_area = list(kwargs['table_area'])
|
||||
kwargs['table_area'] = None if not table_area else table_area
|
||||
table_areas = list(kwargs['table_areas'])
|
||||
kwargs['table_areas'] = None if not table_areas else table_areas
|
||||
copy_text = list(kwargs['copy_text'])
|
||||
kwargs['copy_text'] = None if not copy_text else copy_text
|
||||
kwargs['shift_text'] = list(kwargs['shift_text'])
|
||||
@@ -116,7 +116,7 @@ def lattice(c, *args, **kwargs):
|
||||
|
||||
|
||||
@cli.command('stream')
|
||||
@click.option('-T', '--table_area', default=[], multiple=True,
|
||||
@click.option('-T', '--table_areas', default=[], multiple=True,
|
||||
help='Table areas to process. Example: x1,y1,x2,y2'
|
||||
' where x1, y1 -> left-top and x2, y2 -> right-bottom.')
|
||||
@click.option('-C', '--columns', default=[], multiple=True,
|
||||
@@ -142,8 +142,8 @@ def stream(c, *args, **kwargs):
|
||||
filepath = kwargs.pop('filepath')
|
||||
kwargs.update(conf)
|
||||
|
||||
table_area = list(kwargs['table_area'])
|
||||
kwargs['table_area'] = None if not table_area else table_area
|
||||
table_areas = list(kwargs['table_areas'])
|
||||
kwargs['table_areas'] = None if not table_areas else table_areas
|
||||
columns = list(kwargs['columns'])
|
||||
kwargs['columns'] = None if not columns else columns
|
||||
|
||||
|
||||
+1
-1
@@ -24,7 +24,7 @@ def read_pdf(filepath, pages='1', flavor='lattice', suppress_warnings=False,
|
||||
Lattice is used by default.
|
||||
suppress_warnings : bool, optional (default: False)
|
||||
Prevent warnings from being emitted by Camelot.
|
||||
table_area : list, optional (default: None)
|
||||
table_areas : list, optional (default: None)
|
||||
List of table area strings of the form x1,y1,x2,y2
|
||||
where (x1, y1) -> left-top and (x2, y2) -> right-bottom
|
||||
in PDF coordinate space.
|
||||
|
||||
@@ -28,7 +28,7 @@ class Lattice(BaseParser):
|
||||
|
||||
Parameters
|
||||
----------
|
||||
table_area : list, optional (default: None)
|
||||
table_areas : list, optional (default: None)
|
||||
List of table area strings of the form x1,y1,x2,y2
|
||||
where (x1, y1) -> left-top and (x2, y2) -> right-bottom
|
||||
in PDF coordinate space.
|
||||
@@ -76,12 +76,12 @@ class Lattice(BaseParser):
|
||||
For more information, refer `PDFMiner docs <https://euske.github.io/pdfminer/>`_.
|
||||
|
||||
"""
|
||||
def __init__(self, table_area=None, process_background=False,
|
||||
def __init__(self, table_areas=None, process_background=False,
|
||||
line_size_scaling=15, copy_text=None, shift_text=['l', 't'],
|
||||
split_text=False, flag_size=False, line_close_tol=2,
|
||||
joint_close_tol=2, threshold_blocksize=15, threshold_constant=-2,
|
||||
iterations=0, margins=(1.0, 0.5, 0.1), **kwargs):
|
||||
self.table_area = table_area
|
||||
self.table_areas = table_areas
|
||||
self.process_background = process_background
|
||||
self.line_size_scaling = line_size_scaling
|
||||
self.copy_text = copy_text
|
||||
@@ -244,9 +244,9 @@ class Lattice(BaseParser):
|
||||
self.threshold, direction='horizontal',
|
||||
line_size_scaling=self.line_size_scaling, iterations=self.iterations)
|
||||
|
||||
if self.table_area is not None:
|
||||
if self.table_areas is not None:
|
||||
areas = []
|
||||
for area in self.table_area:
|
||||
for area in self.table_areas:
|
||||
x1, y1, x2, y2 = area.split(",")
|
||||
x1 = float(x1)
|
||||
y1 = float(y1)
|
||||
|
||||
@@ -26,7 +26,7 @@ class Stream(BaseParser):
|
||||
|
||||
Parameters
|
||||
----------
|
||||
table_area : list, optional (default: None)
|
||||
table_areas : list, optional (default: None)
|
||||
List of table area strings of the form x1,y1,x2,y2
|
||||
where (x1, y1) -> left-top and (x2, y2) -> right-bottom
|
||||
in PDF coordinate space.
|
||||
@@ -50,10 +50,10 @@ class Stream(BaseParser):
|
||||
For more information, refer `PDFMiner docs <https://euske.github.io/pdfminer/>`_.
|
||||
|
||||
"""
|
||||
def __init__(self, table_area=None, columns=None, split_text=False,
|
||||
def __init__(self, table_areas=None, columns=None, split_text=False,
|
||||
flag_size=False, row_close_tol=2, col_close_tol=0,
|
||||
margins=(1.0, 0.5, 0.1), **kwargs):
|
||||
self.table_area = table_area
|
||||
self.table_areas = table_areas
|
||||
self.columns = columns
|
||||
self._validate_columns()
|
||||
self.split_text = split_text
|
||||
@@ -241,15 +241,15 @@ class Stream(BaseParser):
|
||||
return cols
|
||||
|
||||
def _validate_columns(self):
|
||||
if self.table_area is not None and self.columns is not None:
|
||||
if len(self.table_area) != len(self.columns):
|
||||
raise ValueError("Length of table_area and columns"
|
||||
if self.table_areas is not None and self.columns is not None:
|
||||
if len(self.table_areas) != len(self.columns):
|
||||
raise ValueError("Length of table_areas and columns"
|
||||
" should be equal")
|
||||
|
||||
def _generate_table_bbox(self):
|
||||
if self.table_area is not None:
|
||||
if self.table_areas is not None:
|
||||
table_bbox = {}
|
||||
for area in self.table_area:
|
||||
for area in self.table_areas:
|
||||
x1, y1, x2, y2 = area.split(",")
|
||||
x1 = float(x1)
|
||||
y1 = float(y1)
|
||||
|
||||
Reference in New Issue
Block a user