def process_record(filename, record):
if '~' not in record: return 'No proper start of record'
if '~A' not in record: return 'No delimited data block'
halves = record[record.index('~'):].strip().split('~A')
metadata = las.parse_metadata(\
las.sanitize(line.strip('.').strip()) for line in las.filter_lines(halves[0], ['-'])\
)
if len(metadata['curveAliases']) < 1: return 'bad format in metadata block'
try:
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
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', '')))
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', '')))
def process_record(filename, record):
if '~' not in record: return 'No proper start of record'
if '~A' not in record: return 'No delimited data block'
halves = record[record.index('~'):].strip().split('~A')
metadata = las.parse_metadata(\
las.sanitize(line.strip('.').strip()) for line in las.filter_lines(halves[0], ['-'])\
)
if len(metadata['curveAliases']) < 1: return 'bad format in metadata block'
try:
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
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 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 emit(fields, text):
helper.emit('\t'.join(fields + [text]))
def emit(fields, cells): helper.emit('\t'.join(fields + [cell.text_content() for cell in cells]))
def process_rec(key, rec):
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):
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 emit(fields, cells):
helper.emit('\t'.join(fields + [cell.text_content() for cell in cells]))
def emit(fields, text): helper.emit('\t'.join(fields + [text]))
def process_rec(key, rec):
