Add tasks for all the new languages

This commit is contained in:
Tina Müller 2016-12-05 23:44:36 +01:00
parent 9dc3c2bb62
commit bba7bfd280
13208 changed files with 134745 additions and 0 deletions

View file

@ -0,0 +1,66 @@
import strutils, tables
const NumFields = 49
const DateField = 0
const FlagGoodValue = 1
var badRecords: int # the number of records that have invalid formatted values
var totalRecords: int # the total number of records in the file
var badInstruments: int # the total number of records that have at least one instrument showing error
var seenDates = newTable[string,bool]() # table that keeps track of what dates we have seen
# ensure we can parse all records as floats (except the date stamp)
proc checkFloats(floats:seq[string]): bool =
for index in 1..NumFields-1:
try:
# we're assuming all instrument flags are floats not integers
discard parseFloat(floats[index])
except ValueError:
return false
true
# ensure that all sensor flags are ok
proc areAllFlagsOk(instruments: seq[string]): bool =
#flags start at index 2, and occur every 2 fields
for index in countup(2,NumFields,2):
# we're assuming all instrument flags are floats not integers
var flag = parseFloat(instruments[index])
if flag < FlagGoodValue: return false
true
# Note: we're not checking the format of the date stamp
# main
var lines = readFile("readings.txt")
var currentLine: int
for line in lines.splitLines:
currentLine.inc
#empty lines don't count as records
if line.len == 0: continue
var tokens = line.split({' ','\t'})
totalRecords.inc
if tokens.len != NumFields:
badRecords.inc
continue
if not checkFloats(tokens):
badRecords.inc
continue
if not areAllFlagsOk(tokens):
badInstruments.inc
if seenDates.hasKeyOrPut(tokens[DateField], true):
echo tokens[DateField], " duplicated on line ", currentLine
var goodRecords = totalRecords - badRecords
var goodInstruments = goodRecords - badInstruments
echo "Total Records:", totalRecords
echo "Good Records:", goodRecords
echo "Records where all instuments were OK:", goodInstruments

View file

@ -0,0 +1,14 @@
var good_records = 0;
var dates = Hash();
ARGF.each { |line|
var m = /^(\d\d\d\d-\d\d-\d\d)((?:\h+\d+\.\d+\h+-?\d+){24})\s*$/.match(line);
m || (warn "Bad format at line #{$.}"; next);
dates{m[0]} := 0 ++;
var i = 0;
m[1].words.all{|n| i++.is_even || (n.to_num >= 1) } && ++good_records;
}
say "#{good_records} good records out of #{$.} total";
say 'Repeated timestamps:';
say dates.to_a.grep{ .value > 1 }.map { .key }.sort.join("\n");

View file

@ -0,0 +1 @@
$ jq -R '[splits("[ \t]+")]' Text_processing_2.txt

View file

@ -0,0 +1,16 @@
# Given any array, produce an array of [item, count] pairs for each run.
def runs:
reduce .[] as $item
( [];
if . == [] then [ [ $item, 1] ]
else .[length-1] as $last
| if $last[0] == $item then (.[0:length-1] + [ [$item, $last[1] + 1] ] )
else . + [[$item, 1]]
end
end ) ;
def is_float: test("^[-+]?[0-9]*[.][0-9]*([eE][-+]?[0-9]+)?$");
def is_integral: test("^[-+]?[0-9]+$");
def is_date: test("[12][0-9]{3}-[0-9][0-9]-[0-9][0-9]");

View file

@ -0,0 +1,19 @@
# Report line and column numbers using conventional numbering (IO=1).
def validate_line(nr):
def validate_date:
if is_date then empty else "field 1 in line \(nr) has an invalid date: \(.)" end;
def validate_length(n):
if length == n then empty else "line \(nr) has \(length) fields" end;
def validate_pair(i):
( .[2*i + 1] as $n
| if ($n | is_float) then empty else "field \(2*i + 2) in line \(nr) is not a float: \($n)" end),
( .[2*i + 2] as $n
| if ($n | is_integral) then empty else "field \(2*i + 3) in line \(nr) is not an integer: \($n)" end);
(.[0] | validate_date),
(validate_length(49)),
(range(0; (length-1) / 2) as $i | validate_pair($i)) ;
def validate_lines:
. as $in
| range(0; length) as $i | ($in[$i] | validate_line($i + 1));

View file

@ -0,0 +1,2 @@
def duplicate_timestamps:
[.[][0]] | sort | runs | map( select(.[1]>1) );

View file

@ -0,0 +1,11 @@
# The following ignores any issues with respect to duplicate dates,
# but does check the validity of the record, including the date format:
def number_of_valid_readings:
def check:
. as $in
| (.[0] | is_date)
and length == 49
and all(range(0; 24) | $in[2*. + 1] | is_float)
and all(range(0; 24) | $in[2*. + 2] | (is_integral and tonumber >= 1) );
map(select(check)) | length ;

View file

@ -0,0 +1,4 @@
validate_lines,
"\nChecking for duplicate timestamps:",
duplicate_timestamps,
"\nThere are \(number_of_valid_readings) valid rows altogether."

View file

@ -0,0 +1,16 @@
$ jq -R '[splits("[ \t]+")]' Text_processing_2.txt | jq -s -r -f Text_processing_2.jq
field 1 in line 6 has an invalid date: 991-04-03
line 6 has 47 fields
field 2 in line 6 is not a float: 10000
field 3 in line 6 is not an integer: 1.0
field 47 in line 6 is not an integer: x
Checking for duplicate timestamps:
[
[
"1991-03-31",
2
]
]
There are 5 valid rows altogether.

View file

@ -0,0 +1,26 @@
$ jq -R '[splits("[ \t]+")]' readings.txt | jq -s -r -f Text_processing_2.jq
Checking for duplicate timestamps:
[
[
"1990-03-25",
2
],
[
"1991-03-31",
2
],
[
"1992-03-29",
2
],
[
"1993-03-28",
2
],
[
"1995-03-26",
2
]
]
There are 5017 valid rows altogether.