Update CLI
Vinayak Mehta
parent
75f667ccd5
commit
93b4dabcc2
162
camelot/cli.py
162
camelot/cli.py
|
|
@ -20,21 +20,21 @@ pass_config = click.make_pass_decorator(Config)
|
|||
|
||||
@click.group()
|
||||
@click.version_option(version=__version__)
|
||||
@click.option("-p", "--pages", default="1", help="Comma-separated page numbers"
|
||||
" to parse. Example: 1,3,4 or 1,4-end")
|
||||
@click.option("-o", "--output", help="Output filepath.")
|
||||
@click.option("-f", "--format",
|
||||
type=click.Choice(["csv", "json", "excel", "html"]),
|
||||
help="Output file format.")
|
||||
@click.option("-z", "--zip", is_flag=True, help="Whether or not to create a ZIP"
|
||||
" archive.")
|
||||
@click.option("-split", "--split_text", is_flag=True, help="Whether or not to"
|
||||
" split text if it spans across multiple cells.")
|
||||
@click.option("-flag", "--flag_size", is_flag=True, help="(inactive) Whether or"
|
||||
" not to flag text which has uncommon size. (Useful to detect"
|
||||
" super/subscripts)")
|
||||
@click.option("-M", "--margins", nargs=3, default=(1.0, 0.5, 0.1),
|
||||
help="char_margin, line_margin, word_margin for PDFMiner.")
|
||||
@click.option('-p', '--pages', default='1', help='Comma-separated page numbers'
|
||||
' to parse. Example: 1,3,4 or 1,4-end')
|
||||
@click.option('-o', '--output', help='Output filepath.')
|
||||
@click.option('-f', '--format',
|
||||
type=click.Choice(['csv', 'json', 'excel', 'html']),
|
||||
help='Output file format.')
|
||||
@click.option('-z', '--zip', is_flag=True, help='Whether or not to create a ZIP'
|
||||
' archive.')
|
||||
@click.option('-split', '--split_text', is_flag=True, help='Whether or not to'
|
||||
' split text if it spans across multiple cells.')
|
||||
@click.option('-flag', '--flag_size', is_flag=True, help='(inactive) Whether or'
|
||||
' not to flag text which has uncommon size. (Useful to detect'
|
||||
' super/subscripts)')
|
||||
@click.option('-M', '--margins', nargs=3, default=(1.0, 0.5, 0.1),
|
||||
help='char_margin, line_margin, word_margin for PDFMiner.')
|
||||
@click.pass_context
|
||||
def cli(ctx, *args, **kwargs):
|
||||
ctx.obj = Config()
|
||||
|
|
@ -43,53 +43,53 @@ def cli(ctx, *args, **kwargs):
|
|||
|
||||
|
||||
@cli.command('lattice')
|
||||
@click.option("-T", "--table_area", default=[], multiple=True,
|
||||
help="Table areas (x1,y1,x2,y2) to process.\n"
|
||||
" x1, y1 -> left-top and x2, y2 -> right-bottom")
|
||||
@click.option("-back", "--process_background", is_flag=True,
|
||||
help="(with --mesh) Whether or not to process lines that are in"
|
||||
" background.")
|
||||
@click.option("-scale", "--line_size_scaling", default=15,
|
||||
help="(with --mesh) Factor by which the page dimensions will be"
|
||||
" divided to get smallest length of detected lines.")
|
||||
@click.option("-copy", "--copy_text", default=[], type=click.Choice(["h", "v"]),
|
||||
multiple=True, help="(with --mesh) Specify direction"
|
||||
" in which text will be copied over in a spanning cell.")
|
||||
@click.option("-shift", "--shift_text", default=["l", "t"],
|
||||
type=click.Choice(["", "l", "r", "t", "b"]), multiple=True,
|
||||
help="(with --mesh) Specify direction in which text in a spanning"
|
||||
" cell should flow.")
|
||||
@click.option("-l", "--line_close_tol", default=2,
|
||||
help="(with --mesh) Tolerance parameter used to merge close vertical"
|
||||
" lines and close horizontal lines.")
|
||||
@click.option("-j", "--joint_close_tol", default=2,
|
||||
help="(with --mesh) Tolerance parameter used to decide whether"
|
||||
" the detected lines and points lie close to each other.")
|
||||
@click.option("-block", "--threshold_blocksize", default=15,
|
||||
help="(with --mesh) For adaptive thresholding, size of a pixel"
|
||||
" neighborhood that is used to calculate a threshold value for"
|
||||
" the pixel: 3, 5, 7, and so on.")
|
||||
@click.option("-const", "--threshold_constant", default=-2,
|
||||
help="(with --mesh) For adaptive thresholding, constant subtracted"
|
||||
" from the mean or weighted mean.\nNormally, it is positive but"
|
||||
" may be zero or negative as well.")
|
||||
@click.option("-I", "--iterations", default=0,
|
||||
help="(with --mesh) Number of times for erosion/dilation is"
|
||||
" applied.")
|
||||
@click.option("-plot", "--plot_type",
|
||||
type=click.Choice(["text", "table", "contour", "joint", "line"]),
|
||||
help="Plot geometry found on PDF page for debugging.")
|
||||
@click.argument("filepath", type=click.Path(exists=True))
|
||||
@click.option('-T', '--table_area', default=[], multiple=True,
|
||||
help='Table areas (x1,y1,x2,y2) to process.\n'
|
||||
' x1, y1 -> left-top and x2, y2 -> right-bottom')
|
||||
@click.option('-back', '--process_background', is_flag=True,
|
||||
help='Whether or not to process lines that are in'
|
||||
' background.')
|
||||
@click.option('-scale', '--line_size_scaling', default=15,
|
||||
help='Factor by which the page dimensions will be'
|
||||
' divided to get smallest length of detected lines.')
|
||||
@click.option('-copy', '--copy_text', default=[], type=click.Choice(['h', 'v']),
|
||||
multiple=True, help='Specify direction'
|
||||
' in which text will be copied over in a spanning cell.')
|
||||
@click.option('-shift', '--shift_text', default=['l', 't'],
|
||||
type=click.Choice(['', 'l', 'r', 't', 'b']), multiple=True,
|
||||
help='Specify direction in which text in a spanning'
|
||||
' cell should flow.')
|
||||
@click.option('-l', '--line_close_tol', default=2,
|
||||
help='Tolerance parameter used to merge close vertical'
|
||||
' lines and close horizontal lines.')
|
||||
@click.option('-j', '--joint_close_tol', default=2,
|
||||
help='Tolerance parameter used to decide whether'
|
||||
' the detected lines and points lie close to each other.')
|
||||
@click.option('-block', '--threshold_blocksize', default=15,
|
||||
help='For adaptive thresholding, size of a pixel'
|
||||
' neighborhood that is used to calculate a threshold value for'
|
||||
' the pixel: 3, 5, 7, and so on.')
|
||||
@click.option('-const', '--threshold_constant', default=-2,
|
||||
help='For adaptive thresholding, constant subtracted'
|
||||
' from the mean or weighted mean.\nNormally, it is positive but'
|
||||
' may be zero or negative as well.')
|
||||
@click.option('-I', '--iterations', default=0,
|
||||
help='Number of times for erosion/dilation is'
|
||||
' applied.')
|
||||
@click.option('-plot', '--plot_type',
|
||||
type=click.Choice(['text', 'table', 'contour', 'joint', 'line']),
|
||||
help='Plot geometry found on PDF page for debugging.')
|
||||
@click.argument('filepath', type=click.Path(exists=True))
|
||||
@pass_config
|
||||
def lattice(c, *args, **kwargs):
|
||||
"""Use lines between text to parse table."""
|
||||
conf = c.config
|
||||
pages = conf.pop("pages")
|
||||
output = conf.pop("output")
|
||||
f = conf.pop("format")
|
||||
compress = conf.pop("zip")
|
||||
pages = conf.pop('pages')
|
||||
output = conf.pop('output')
|
||||
f = conf.pop('format')
|
||||
compress = conf.pop('zip')
|
||||
plot_type = kwargs.pop('plot_type')
|
||||
filepath = kwargs.pop("filepath")
|
||||
filepath = kwargs.pop('filepath')
|
||||
kwargs.update(conf)
|
||||
|
||||
table_area = list(kwargs['table_area'])
|
||||
|
|
@ -99,42 +99,42 @@ def lattice(c, *args, **kwargs):
|
|||
kwargs['shift_text'] = list(kwargs['shift_text'])
|
||||
|
||||
tables = read_pdf(filepath, pages=pages, flavor='lattice', **kwargs)
|
||||
click.echo(tables)
|
||||
click.echo('Found {} tables'.format(tables.n))
|
||||
if plot_type is not None:
|
||||
for table in tables:
|
||||
table.plot(plot_type)
|
||||
else:
|
||||
if output is None:
|
||||
raise click.UsageError("Please specify output filepath using --output")
|
||||
raise click.UsageError('Please specify output filepath using --output')
|
||||
if f is None:
|
||||
raise click.UsageError("Please specify output format using --format")
|
||||
raise click.UsageError('Please specify output format using --format')
|
||||
tables.export(output, f=f, compress=compress)
|
||||
|
||||
|
||||
@cli.command('stream')
|
||||
@click.option("-T", "--table_area", default=[], multiple=True,
|
||||
help="Table areas (x1,y1,x2,y2) to process.\n"
|
||||
" x1, y1 -> left-top and x2, y2 -> right-bottom")
|
||||
@click.option("-C", "--columns", default=[], multiple=True,
|
||||
help="x-coordinates of column separators.")
|
||||
@click.option("-r", "--row_close_tol", default=2, help="Rows will be"
|
||||
" formed by combining text vertically within this tolerance.")
|
||||
@click.option("-c", "--col_close_tol", default=0, help="Columns will"
|
||||
" be formed by combining text horizontally within this tolerance.")
|
||||
@click.option("-plot", "--plot_type",
|
||||
type=click.Choice(["text", "table"]),
|
||||
help="Plot geometry found on PDF page for debugging.")
|
||||
@click.argument("filepath", type=click.Path(exists=True))
|
||||
@click.option('-T', '--table_area', default=[], multiple=True,
|
||||
help='Table areas (x1,y1,x2,y2) to process.\n'
|
||||
' x1, y1 -> left-top and x2, y2 -> right-bottom')
|
||||
@click.option('-C', '--columns', default=[], multiple=True,
|
||||
help='x-coordinates of column separators.')
|
||||
@click.option('-r', '--row_close_tol', default=2, help='Rows will be'
|
||||
' formed by combining text vertically within this tolerance.')
|
||||
@click.option('-c', '--col_close_tol', default=0, help='Columns will'
|
||||
' be formed by combining text horizontally within this tolerance.')
|
||||
@click.option('-plot', '--plot_type',
|
||||
type=click.Choice(['text', 'table']),
|
||||
help='Plot geometry found on PDF page for debugging.')
|
||||
@click.argument('filepath', type=click.Path(exists=True))
|
||||
@pass_config
|
||||
def stream(c, *args, **kwargs):
|
||||
"""Use spaces between text to parse table."""
|
||||
conf = c.config
|
||||
pages = conf.pop("pages")
|
||||
output = conf.pop("output")
|
||||
f = conf.pop("format")
|
||||
compress = conf.pop("zip")
|
||||
pages = conf.pop('pages')
|
||||
output = conf.pop('output')
|
||||
f = conf.pop('format')
|
||||
compress = conf.pop('zip')
|
||||
plot_type = kwargs.pop('plot_type')
|
||||
filepath = kwargs.pop("filepath")
|
||||
filepath = kwargs.pop('filepath')
|
||||
kwargs.update(conf)
|
||||
|
||||
table_area = list(kwargs['table_area'])
|
||||
|
|
@ -143,13 +143,13 @@ def stream(c, *args, **kwargs):
|
|||
kwargs['columns'] = None if not columns else columns
|
||||
|
||||
tables = read_pdf(filepath, pages=pages, flavor='stream', **kwargs)
|
||||
click.echo(tables)
|
||||
click.echo('Found {} tables'.format(tables.n))
|
||||
if plot_type is not None:
|
||||
for table in tables:
|
||||
table.plot(plot_type)
|
||||
else:
|
||||
if output is None:
|
||||
raise click.UsageError("Please specify output filepath using --output")
|
||||
raise click.UsageError('Please specify output filepath using --output')
|
||||
if f is None:
|
||||
raise click.UsageError("Please specify output format using --format")
|
||||
raise click.UsageError('Please specify output format using --format')
|
||||
tables.export(output, f=f, compress=compress)
|
||||
Loading…
Reference in New Issue