#!./pyenv/bin/python
from pyquery import PyQuery as pq
import recordhelper as helper
def sanitize(cell):
if cell.text is None:
return ""
else:
return cell.text.strip()
def process_rec(key, rec):
cells = pq(rec)("table")("td")
records = [cells[x : x + 13] for x in xrange(0, len(cells), 13)]
for record in records:
helper.emit("\t".join([sanitize(cell) for cell in record]))
def parse_key(text):
return text.split()[0]
helper.process_records(process_rec, parse_key, "__key")
#!./pyenv/bin/python
#LAS standard spec:
#https://esd.halliburton.com/support/LSM/GGT/ProMAXSuite/ProMAX/5000/5000_8/Help/promax/las_overview.pdf
import json, las
import recordhelper as helper
def process_record(filename, record):
if '~' not in record: return 'No proper start of record'
halves = record[record.index('~'):].strip().split('~A')
if len(halves) < 2: return 'Improperly separated metadata & data blocks'
metadata = las.parse_metadata(\
las.sanitize(line.strip('.').strip()) for line in las.filter_lines(halves[0], ['-'])\
)
if len(metadata['curveAliases']) < 1: return 'Improperly formatted metadata block'
for block in ['V', 'W', 'C']:
if block in metadata:
for mnemonic, val in metadata[block].iteritems():
helper.emit('%s\t%s\t%s\t%s\t%s' % \
(filename, block, mnemonic, val.get('UOM', ''), val.get('description', '')))
helper.process_records(process_record, las.parse_filename, '__key')
halves[1] = halves[1][halves[1].index('\n'):]
#filter blank and lines starting with #, split resulting text into tokens
tokens = '\t'.join(las.filter_lines(halves[1], ['#'])).split()
except:
return 'bad separation between metadata and curve data'
if len(tokens) % len(metadata['curveAliases']) != 0:
return 'mismatched reading count'
null_vals = get_nulls(metadata)
curve_aliases = metadata['curveAliases']
step_type = curve_aliases[0]
for idx in xrange(
0, len(tokens),
len(curve_aliases)): # idx is index of first reading on a step
step_values = tokens[
idx:idx + len(curve_aliases)] # get all readings for the next step
try:
for idy, reading in enumerate(
filter(lambda x: float(x) not in null_vals,
step_values)[1:]):
helper.emit('\t'.join([
filename, step_type, step_values[0], curve_aliases[idy],
metadata['C'][curve_aliases[idy]].get('UOM', ''), reading
]))
except ValueError:
pass
helper.process_records(process_record, las.parse_filename, '__key')
#Append extracted field value for each field in list of fields
for field in fields:
if field in text:
vals.append(text.split(field + ': ')[1].split(' ')[0])
else:
vals.append('null')
return vals
def emit(fields, cells):
#Print tab separated list of fields concatted with array of extracted cell values
helper.emit('\t'.join(fields + [cell.text_content() for cell in cells]))
def process_rec(key, rec):
if 'Average PSI' in rec:
fields = extract_fields(['File No'], pq(rec).text())
cells = pq(rec)('table').eq(2)('td')
#Split each 7 cell values into one row and emit record
[
emit(fields, record)
for record in [cells[x:x + 7] for x in xrange(0, len(cells), 7)]
]
def parse_key(text):
return text.split()[0]
helper.process_records(process_rec, parse_key, '__key')
#!./pyenv/bin/python
from pyquery import PyQuery as pq
import recordhelper as helper
def extract_fields(fields, text):
vals = []
#Append extracted field value for each field in list of fields
for field in fields:
if field in text: vals.append(text.split(field + ': ')[1].split(' ')[0].replace(u'\xa0', 'null'))
else: vals.append('null')
return vals
#Print tab separated list of fields concatted with array of extracted cell values
def emit(fields, cells): helper.emit('\t'.join(fields + [cell.text_content() for cell in cells]))
def process_rec(key, rec):
if 'Vent/Flare' in rec:
fields = extract_fields(['File No', 'Perfs', 'Spacing', 'Total Depth'], pq(rec).text())
cells = pq(rec)('table').eq(2)('td')
#Split each 9 cell values into one row and emit record
[emit(fields, record) for record in [cells[x:x+9] for x in xrange(0, len(cells), 9)]]
def parse_key(text): return text.split()[0]
#read all of input and run it through process_rec
helper.process_records(process_rec, parse_key, '__key')