def _decode_table_lines_ocr(ocr_prose):
titles = []
values = []
for line in ocr_prose:
# Fix some common number replacements in OCR
line = line.replace('§', '5').replace('£', '[-')
matches = TABLE_LINE_PARSE_RE.match(line)
if not matches:
continue
groups = matches.groups()
title = groups[0]
try:
value = (forgiving_float(groups[-3]),
forgiving_float(groups[-2]),
forgiving_float(groups[-1]))
value = sanity_check_values(value)
titles.append(title.replace("Cl", "CI"))
values.append(value)
except AttributeError:
continue
return titles, values
def _decode_table_values_ocr(ocr_prose):
# Fix some common number replacements in OCR
ocr_prose = ocr_prose.replace('§', '5').replace('$', '5').replace('£', '[-')
parts = TABLE_VALUE_SPLIT_RE.split(ocr_prose)
values = []
for part in parts:
try:
groups = TABLE_VALUE_GROK_RE.match(part).groups()
value = (forgiving_float(groups[0]), forgiving_float(groups[1]), forgiving_float(groups[2]))
value = sanity_check_values(value)
values.append(value)
except (AttributeError, ValueError):
if part == "(Excluded)":
values.append(("Excluded", "Excluded", "Excluded"))
return values
def _decode_values_ocr(ocr_prose):
# Fix some common number replacements in OCR
ocr_prose = ocr_prose.replace('§', '5').replace('$', '5').replace('£', '[-')
lines = [x.strip() for x in ocr_prose.split('\n') if x.strip()]
values = []
weights = []
# first find the values
for line in lines:
parts = TABLE_VALUE_GROK_RE.split(line)
if len(parts) == 5:
try:
value = (forgiving_float(parts[1]), forgiving_float(parts[2]), forgiving_float(parts[3]))
value = sanity_check_values(value)
values.append(value)
except ValueError:
if parts == "(Excluded)":
values.append(("Excluded", "Excluded", "Excluded"))
try:
weight = forgiving_float(parts[4].strip())
weights.append(weight)
except ValueError:
pass
else:
try:
weight = forgiving_float(line)
weights.append(weight)
except ValueError:
pass
if len(values) != len(weights):
raise ValueError
res = []
for value, weight in zip(values, weights):
res.append((value[0], value[1], value[2], weight))
return res