RosettaCodeData/Task/Text-processing-2/11l/text-processing-2.11l

47 lines
1.4 KiB
Plaintext
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

V debug = 0B
V datePat = re:\d{4}-\d{2}-\d{2}
V valuPat = re:[-+]?\d+\.\d+
V statPat = re:-?\d+
V totalLines = 0
Set[String] dupdate
Set[String] badform
Set[String] badlen
V badreading = 0
Set[String] datestamps
L(line) File(readings.txt).read().rtrim("\n").split("\n")
totalLines++
V fields = line.split("\t")
V date = fields[0]
V pairs = (1 .< fields.len).step(2).map(i -> (@fields[i], @fields[i + 1]))
V lineFormatOk = datePat.match(date)
& all(pairs.map(p -> :valuPat.match(p[0])))
& all(pairs.map(p -> :statPat.match(p[1])))
I !lineFormatOk
I debug
print(Bad formatting line)
badform.add(date)
I pairs.len != 24 | any(pairs.map(p -> Int(p[1]) < 1))
I debug
print(Missing values line)
I pairs.len != 24
badlen.add(date)
I any(pairs.map(p -> Int(p[1]) < 1))
badreading++
I date C datestamps
I debug
print(Duplicate datestamp line)
dupdate.add(date)
datestamps.add(date)
print("Duplicate dates:\n "sorted(Array(dupdate)).join("\n "))
print("Bad format:\n "sorted(Array(badform)).join("\n "))
print("Bad number of fields:\n "sorted(Array(badlen)).join("\n "))
print("Records with good readings: #. = #2.2%\n".format(
totalLines - badreading, (totalLines - badreading) / Float(totalLines) * 100))
print(Total records: totalLines)