def test_upgrade_txt_richstr(segyio_all_test_files):
file, segyio_kwargs = segyio_all_test_files
text = get_segy_texthead(file, no_richstr=True, **segyio_kwargs)
text = _upgrade_txt_richstr(text)
assert isinstance(text, str)
assert hasattr(text, "_repr_html_")
assert hasattr(text, "_repr_pretty_")
def scrape(filename, ebcidc=False, trace_headers=False):
"""Scrape the file meta information and output it to text file.
If no options are specified both will be output. The output file will be
<filename>.txt for the EBCIDC and <filename>.csv for
trace headers.
The trace headers can be read back into Python using
pandas.read_csv(<filename>.csv, index_col=0)
"""
for file in tqdm(filename, desc="File"):
file = pathlib.Path(file)
ebcidc_name = file.with_suffix(".txt")
header_name = file.with_suffix(".csv")
if ebcidc == False and trace_headers == False:
ebcidc = True
trace_headers = True
if ebcidc:
txt = get_segy_texthead(file)
with open(ebcidc_name, "w") as txtfile:
txtfile.writelines(txt)
if trace_headers:
head_df = segy_header_scrape(file)
head_df.to_csv(header_name)
def _action_ebcidc_out(arg, input_file):
try:
ebcidc = get_segy_texthead(input_file)
except IOError:
LOGGER.error("Input SEGY file was not found - check name and path")
raise SystemExit
if arg is None:
print(ebcidc)
else:
ebcidc = fix_bad_chars(ebcidc)
with open(arg, 'w') as f:
f.write(ebcidc)
def main():
# how to track down warnings
#import warnings
#warnings.filterwarnings('error', category=UnicodeWarning)
#warnings.filterwarnings('error', category=DeprecationWarning, module='numpy')
#parse args
sys_parser = segysakArgsParser()
args = sys_parser.parse_args()
# gaffe
print(f'SEGY-SAK - v{version}')
# initialise logging
LOGGER.info(f'segysak v{version}')
# check inputs
checked_files = check_file(args.files)
# Generate or Load Configuration File
for input_file in checked_files:
print(input_file.name)
# Print EBCIDC header
if args.ebcidc:
try:
print(get_segy_texthead(input_file))
except IOError:
LOGGER.error(
"Input SEGY file was not found - check name and path")
if args.scan > 0:
hscan, nscan = segy_header_scan(input_file,
max_traces_scan=args.scan)
width = 10
print(f'Traces scanned: {nscan}')
print("{:>40s} {:>8s} {:>10s} {:>10s}".format(
'Item', 'Byte Loc', 'Min', 'Max'))
for key, item in hscan.items():
print("{:>40s} {:>8d} {:>10.0f} {:>10.0f}".format(
key, item[0], item[1], item[2]))
iline = args.iline
xline = args.xline
if args.netCDF is None or args.netCDF is not False:
if args.netCDF is None:
outfile = input_file.stem + '.SEISNC'
else:
outfile = args.netCDF
_ = segy_loader(input_file,
ncfile=outfile,
iline=iline,
xline=xline,
ix_crop=args.crop)
LOGGER.info(f"NetCDF output written to {outfile}")
if args.SEGY is None or args.SEGY is not False:
if args.SEGY is None:
outfile = input_file.stem + '.segy'
else:
outfile = args.SEGY
ncdf2segy(input_file, outfile, iline=iline,
xline=xline) #, crop=args.crop)
LOGGER.info(f"SEGY output written to {outfile}")
def test_get_segy_texthead(temp_dir, temp_segy):
ebcidc = get_segy_texthead(temp_segy)
assert isinstance(ebcidc, str)
assert len(ebcidc) < 3200
assert ebcidc[:3] == "C01"
# %%
V3D_path = pathlib.Path("data/volve10r12-full-twt-sub3d.sgy")
print("3D", V3D_path, V3D_path.exists())
# %% [markdown]
# ## Scan SEGY headers
#
# %% [markdown]
# A basic operation would be to check the text header included in the SEG-Y file. The *get_segy_texthead*
# function accounts for commong encoding issues and returns the header as a text string.
# %%
from segysak.segy import get_segy_texthead
get_segy_texthead(V3D_path)
# %% [markdown]
# If you need to investigate the trace header data more deeply, then *segy_header_scan* can be used to report
# basic statistic of each byte position for a limited number of traces.
#
# *segy_header_scan* returns a `pandas.DataFrame`. To see the full DataFrame use the `pandas` option_context manager.
# %%
from segysak.segy import segy_header_scan
scan = segy_header_scan(V3D_path)
scan
# %% [markdown]
# The header report can also be reduced by filtering blank byte locations. Here we use the standard deviation `std`
def ebcidc(filename):
input_file = pathlib.Path(filename)
click.echo(get_segy_texthead(input_file))