forked from WarrenWeckesser/las
-
Notifications
You must be signed in to change notification settings - Fork 0
/
las.py
408 lines (338 loc) · 14.1 KB
/
las.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
"""LAS File Reader
The main class defined here is LASReader, a class that reads a LAS file
and makes the data available as a Python object.
"""
# Copyright (c) 2011, 2014 Warren Weckesser
#
# Permission to use, copy, modify, and/or distribute this software for any
# purpose with or without fee is hereby granted, provided that the above
# copyright notice and this permission notice appear in all copies.
#
# THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
# WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
# MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
# ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
# WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
# ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
# OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
from __future__ import print_function
import re
import keyword
import numpy as np
def isidentifier(s):
if s in keyword.kwlist:
return False
return re.match(r'^[a-z_][a-z0-9_]*$', s, re.I) is not None
def _convert_to_value(s):
try:
value = int(s)
except ValueError:
try:
value = float(s)
except ValueError:
value = s
return value
def _read_line(f, ignore_blank_lines=True):
"""Read a line from stdin, skipping blank lines and comments."""
ignore = True
while ignore:
line = f.readline()
sline = line.strip()
ignore = sline.startswith('#') or (ignore_blank_lines and sline == '')
return line
class LASError(Exception):
pass
class LASItem(object):
"""This class is just a namespace, holding the attributes 'name',
'units', 'data', 'value', and 'descr'. 'value' is the numerical
value of 'data', if it has a numerical value (specifically, if
int() or float() don't raise an exception when given the value
of the 'data' attribute).
A class method, from_line(cls, line), is provided to parse
a line from a LAS file and create a LASItem instance.
"""
def __init__(self, name, units='', data='', descr=''):
self.name = name
self.units = units
self.data = data
self.value = _convert_to_value(data)
self.descr = descr
def __str__(self):
s = ("name='%s', units='%s', data='%s', descr='%s'" %
(self.name, self.units, self.data, self.descr))
return s
def __repr__(self):
s = str(self)
return "LASItem(%s)" % s
@classmethod
def from_line(cls, line):
first, descr = line.rsplit(':', 1)
descr = descr.strip()
name, mid = first.split('.', 1)
name = name.strip()
if mid.startswith(' '):
# No units
units = ''
data = mid
else:
units_data = mid.split(None, 1)
if len(units_data) == 1:
units = units_data[0]
data = ''
else:
units, data = units_data
return LASItem(name=name, units=units, data=data.strip(),
descr=descr.strip())
def _read_wrapped_row(f, n):
"""Read a "row" of data from the Ascii section of a "wrapped" LAS file.
`f` must be a file object opened for reading.
`n` is the number of fields in the row.
Returns the list of floats read from the file.
"""
depth = float(f.readline().strip())
values = [depth]
while len(values) < n:
new_values = [float(s) for s in f.readline().split()]
values.extend(new_values)
return values
def _read_wrapped_data(f, dt):
data = []
ncols = len(dt.names)
while True:
try:
row = _read_wrapped_row(f, ncols)
except Exception:
break
data.append(tuple(row))
data = np.array(data, dtype=dt)
return data
class LASSection(object):
"""Represents a "section" of a LAS file.
A section is basically a collection of items, where each item has the
attributes 'name', 'units', 'data' and 'descr'.
Any item in the section whose name is a valid Python identifier is
also attached to the object as an attribute. For example, if `s` is a
LASSection instance, and the corresponding section in the LAS file
contained this line:
FD .K/M3 999.9999 : Fluid Density
then the item may be referred to as `s.FD` (in addition to the longer
`s.items['FD']`).
Attributes
----------
items : dict
The keys are the item names, and the values are LASItem instances.
names : list
List of item names, in the order they were read from the LAS file.
"""
def __init__(self):
# Note: In Python 2.7, 'items' could be an OrderedDict, and
# then 'names' would not be necessary--one could use items.keys().
self.items = dict()
self.names = []
def add_item(self, item):
# XXX If the name is already used, this modifies item.name in place.
original_name = item.name
dupcount = 0
while item.name in self.items:
# Duplicate name.
dupcount += 1
item.name = original_name + str(dupcount)
self.items[item.name] = item
self.names.append(item.name)
if isidentifier(item.name) and not hasattr(self, item.name):
setattr(self, item.name, item)
def display(self):
for name in self.names:
item = self.items[name]
namestr = name
if item.units != '':
namestr = namestr + (" (%s)" % item.units)
print("%-16s %-30s [%s]" % (namestr, "'" + item.data + "'",
item.descr))
class LASReader(object):
"""The LASReader class holds data from a LAS file.
This reader only handles LAS 2.0 files (as far as I know).
Constructor
-----------
LASReader(f, null_subs=None)
f : file object or string
If f is a file object, it must be opened for reading.
If f is a string, it must be the filename of a LAS file.
In that case, the file will be opened and read.
Attributes for LAS Sections
---------------------------
version : LASSection instance
This LASSection holds the items from the '~V' section.
well : LASSection instance
This LASSection holds the items from the '~W' section.
curves : LASection instance
This LASSection holds the items from the '~C' section.
parameters : LASSection instance
This LASSection holds the items from the '~P' section.
other : str
Holds the contents of the '~O' section as a single string.
data : numpy 1D structured array
The numerical data from the '~A' section. The data type
of the array is constructed from the items in the '~C'
section.
Other attributes
----------------
data2d : numpy 2D array of floats
The numerical data from the '~A' section, as a 2D array.
This is a view of the same data as in the `data` attribute.
wrap : bool
True if the LAS file was wrapped. (More specifically, this
attribute is True if the data field of the item with the
name 'WRAP' in the '~V' section has the value 'YES'.)
vers : str
The LAS version. (More specifically, the value of the data
field of the item with the name 'VERS' in the '~V' section).
null : float or None
The numerical value of the 'NULL' item in the '~W' section.
The value will be None if the 'NULL' item was missing.
null_subs : float or None
The value given in the constructor, to be used as the
replacement value of each occurrence of `null_value` in
the log data. The value will be None (and no substitution
will be done) if the `null_subs` argument is not given to
the constructor.
start : float, or None
Numerical value of the 'STRT' item from the '~W' section.
The value will be None if 'STRT' was not given in the file.
start_units : str
Units of the 'STRT' item from the '~W' section.
The value will be None if 'STRT' was not given in the file.
stop : float
Numerical value of the 'STOP' item from the '~W' section.
The value will be None if 'STOP' was not given in the file.
stop_units : str
Units of the 'STOP' item from the '~W' section.
The value will be None if 'STOP' was not given in the file.
step : float
Numerical value of the 'STEP' item from the '~W' section.
The value will be None if 'STEP' was not given in the file.
step_units : str
Units of the 'STEP' item from the '~W' section.
The value will be None if 'STEP' was not given in the file.
"""
def __init__(self, f, null_subs=None):
"""f can be a filename (str) or a file object.
If 'null_subs' is not None, its value replaces any values in the data
that matches the NULL value specified in the Version section of the LAS
file.
"""
self.null = None
self.null_subs = null_subs
self.start = None
self.start_units = None
self.stop = None
self.stop_units = None
self.step = None
self.step_units = None
self.version = LASSection()
self.well = LASSection()
self.curves = LASSection()
self.parameters = LASSection()
self.other = ''
self.data = None
self._read_las(f)
self.data2d = self.data.view(float).reshape(-1, len(self.curves.items))
if null_subs is not None:
self.data2d[self.data2d == self.null] = null_subs
def _read_las(self, f):
"""Read a LAS file.
Returns a dictionary with keys 'V', 'W', 'C', 'P', 'O' and 'A',
corresponding to the sections of a LAS file. The values associated
with keys 'V', 'W', 'C' and 'P' will be lists of Item instances. The
value associated with the 'O' key is a list of strings. The value
associated with the 'A' key is a numpy structured array containing the
log data. The field names of the array are the mnemonics from the
Curve section of the file.
"""
opened_here = False
try:
string_type = basestring
except NameError:
string_type = str
if isinstance(f, string_type):
opened_here = True
f = open(f, 'r')
self.wrap = False
ignore_blank_lines = True
current_section = None
current_section_label = ''
line = _read_line(f, ignore_blank_lines)
line_lstrip = line.lstrip(' ')
while not line_lstrip.startswith('~A'):
if line_lstrip.startswith('~'):
if len(line_lstrip) < 2:
raise LASError("Missing section character after '~'.")
current_section_label = line_lstrip[1:2]
other = False
if current_section_label == 'V':
current_section = self.version
ignore_blank_lines = True
elif current_section_label == 'W':
current_section = self.well
ignore_blank_lines = True
elif current_section_label == 'C':
current_section = self.curves
ignore_blank_lines = True
elif current_section_label == 'P':
current_section = self.parameters
ignore_blank_lines = True
elif current_section_label == 'O':
current_section = self.other
ignore_blank_lines = False
other = True
else:
raise LASError("Unknown section '%s'" % line)
elif current_section is None:
raise LASError("Missing first section.")
else:
if other:
# The 'Other' section is just lines of text, so we
# assemble them into a single string.
self.other += line
current_section = self.other
else:
# Parse the line into a LASItem and add it to the
# current section.
m = LASItem.from_line(line_lstrip)
current_section.add_item(m)
# Check for the required items whose values we'll
# store as attributes of the LASReader instance.
if current_section == self.version:
if m.name == 'WRAP':
if m.data.strip() == 'YES':
self.wrap = True
if m.name == 'VERS':
self.vers = m.data.strip()
if current_section == self.well:
if m.name == 'NULL':
self.null = float(m.data)
elif m.name == 'STRT':
self.start = float(m.data)
self.start_units = m.units
elif m.name == 'STOP':
self.stop = float(m.data)
self.stop_units = m.units
elif m.name == 'STEP':
self.step = float(m.data)
self.step_units = m.units
line = _read_line(f, ignore_blank_lines)
line_lstrip = line.lstrip(' ')
# Finished reading the header--all that is left is the numerical
# data that follows the '~A' line. We'll construct a structured
# data type, and, if the data is not wrapped, use numpy.loadtext
# to read the data into an array. For wrapped rows, we use the
# function _read_wrapped() defined elsewhere in this module.
# The data type is determined by the items from the '~Curves' section.
dt = np.dtype([(name, float) for name in self.curves.names])
if self.wrap:
a = _read_wrapped_data(f, dt)
else:
a = np.loadtxt(f, dtype=dt)
self.data = a
if opened_here:
f.close()