aparler/RosettaCodeData
1
0
Fork 0
Code Issues 12 Pull requests 3 Projects Releases Packages Wiki Activity Actions

Another update from ingydotnet^djgoku

Browse source
This commit is contained in:
Ingy döt Net 2015-11-18 06:14:39 +00:00
parent 91df62d461
commit 948b86eafa
7604 changed files with 108452 additions and 22726 deletions
Download patch file Download diff file Expand all files Collapse all files

12
Task/Text-processing-2/00DESCRIPTION
View file

@ -1,12 +1,10 @@
The following data shows a few lines from the file readings.txt (as used in the [[Data Munging]] task).
The data comes from a pollution monitoring station with twenty four instruments monitoring twenty four aspects of pollution in the air. Periodically a record is added to the file constituting a line of 49 white-space separated fields, where white-space can be one or more space or tab characters.
The following task concerns data that came from a pollution monitoring station with twenty-four instruments monitoring twenty-four aspects of pollution in the air. Periodically a record is added to the file, each record being a line of 49 fields separated by white-space, which can be one or more space or tab characters.
The fields (from the left) are:
DATESTAMP [ VALUEn FLAGn ] * 24
i.e. a datestamp followed by twenty four repetitions of a floating point instrument value and that instruments associated integer flag. Flag values are >= 1 if the instrument is working and < 1 if there is some problem with that instrument, in which case that instrument's value should be ignored.
i.e. a datestamp followed by twenty-four repetitions of a floating-point instrument value and that instrument's associated integer flag. Flag values are >= 1 if the instrument is working and < 1 if there is some problem with it, in which case that instrument's value should be ignored.
A sample from the full data file [http://rosettacode.org/resources/readings.zip readings.txt] is:
A sample from the full data file [http://rosettacode.org/resources/readings.zip readings.txt], which is also used in the [[Data Munging]] task, follows:
<pre style="height:17ex;overflow:scroll">
1991-03-30 10.000 1 10.000 1 10.000 1 10.000 1 10.000 1 10.000 1 10.000 1 10.000 1 10.000 1 10.000 1 10.000 1 10.000 1 10.000 1 10.000 1 10.000 1 10.000 1 10.000 1 10.000 1 10.000 1 10.000 1 10.000 1 10.000 1 10.000 1 10.000 1
1991-03-31 10.000 1 10.000 1 10.000 1 10.000 1 10.000 1 10.000 1 10.000 1 20.000 1 20.000 1 20.000 1 35.000 1 50.000 1 60.000 1 40.000 1 30.000 1 30.000 1 30.000 1 25.000 1 20.000 1 20.000 1 20.000 1 20.000 1 20.000 1 35.000 1
@ -17,6 +15,6 @@ A sample from the full data file [http://rosettacode.org/resources/readings.zip
</pre>
The task:
# Confirm the general field format of the file
# Confirm the general field format of the file.
# Identify any DATESTAMPs that are duplicated.
# What number of records have good readings for all instruments.
# Report the number of records that have good readings for all instruments.

115
Task/Text-processing-2/Eiffel/text-processing-2.e Normal file
View file

@ -0,0 +1,115 @@
class
APPLICATION
create
make
feature
make
-- Finds double date stamps and wrong formats.
local
found: INTEGER
double: STRING
do
read_wordlist
fill_hash_table
across
hash as h
loop
if h.key.has_substring ("_double") then
io.put_string ("Double date stamp: %N")
double := h.key
double.remove_tail (7)
io.put_string (double)
io.new_line
end
if h.item.count /= 24 then
io.put_string (h.key.out + " has the wrong format. %N")
found := found + 1
end
end
io.put_string (found.out + " records have not 24 readings.%N")
good_records
end
good_records
-- Number of records that have flag values > 0 for all readings.
local
count, total: INTEGER
end_date: STRING
do
create end_date.make_empty
across
hash as h
loop
count := 0
across
h.item as d
loop
if d.item.flag > 0 then
count := count + 1
end
end
if count = 24 then
total := total + 1
end
end
io.put_string ("%NGood records: " + total.out + ". %N")
end
original_list: STRING = "readings.txt"
read_wordlist
--Preprocesses data in 'data'.
local
l_file: PLAIN_TEXT_FILE
do
create l_file.make_open_read_write (original_list)
l_file.read_stream (l_file.count)
data := l_file.last_string.split ('%N')
l_file.close
end
data: LIST [STRING]
fill_hash_table
--Fills 'hash' using the date as key.
local
by_dates: LIST [STRING]
date: STRING
data_tup: TUPLE [val: REAL; flag: INTEGER]
data_arr: ARRAY [TUPLE [val: REAL; flag: INTEGER]]
i: INTEGER
do
create hash.make (data.count)
across
data as d
loop
if not d.item.is_empty then
by_dates := d.item.split ('%T')
date := by_dates [1]
by_dates.prune (date)
create data_tup
create data_arr.make_empty
from
i := 1
until
i > by_dates.count - 1
loop
data_tup := [by_dates [i].to_real, by_dates [i + 1].to_integer]
data_arr.force (data_tup, data_arr.count + 1)
i := i + 2
end
hash.put (data_arr, date)
if not hash.inserted then
date.append ("_double")
hash.put (data_arr, date)
end
end
end
end
hash: HASH_TABLE [ARRAY [TUPLE [val: REAL; flag: INTEGER]], STRING]
end

62
Task/Text-processing-2/Fortran/text-processing-2.f Normal file
View file

@ -0,0 +1,62 @@
Crunches a set of hourly data. Starts with a date, then 24 pairs of value,indicator for that day, on one line.
INTEGER Y,M,D !Year, month, and day.
INTEGER GOOD(24,2) !The indicators.
REAL*8 V(24,2) !The grist.
CHARACTER*10 DATE(2) !Along with the starting date.
INTEGER IT,TI !A flipper and its antiflipper.
INTEGER NV !Number of entirely good records.
INTEGER I,NREC,HIC !Some counters.
LOGICAL INGOOD !State flipper for the runs of data.
INTEGER IN,MSG !I/O mnemonics.
CHARACTER*666 ACARD !Scratchpad, of sufficient length for all expectation.
IN = 10 !Unit number for the input file.
MSG = 6 !Output.
OPEN (IN,FILE="Readings1.txt", FORM="FORMATTED", !This should be a function.
1 STATUS ="OLD",ACTION="READ") !Returning success, or failure.
NV = 0 !No pure records seen.
NREC = 0 !No records read.
HIC = 0 !Provoking no complaints.
DATE = "snargle" !No date should look like this!
IT = 2 !Syncopation for the 1-2 flip flop.
Chew into the file.
10 READ (IN,11,END=100,ERR=666) L,ACARD(1:MIN(L,LEN(ACARD))) !With some protection.
NREC = NREC + 1 !So, a record has been read.
11 FORMAT (Q,A) !Obviously, Q ascertains the length of the record being read.
READ (ACARD,12,END=600,ERR=601) Y,M,D !The date part is trouble, as always.
12 FORMAT (I4,2(1X,I2)) !Because there are no delimiters between the parts.
TI = IT !Thus finger the previous value.
IT = 3 - IT !Flip between 1 and 2.
DATE(IT) = ACARD(1:10) !Save the date field.
READ (ACARD(11:L),*,END=600,ERR=601) (V(I,IT),GOOD(I,IT),I = 1,24) !But after the date, delimiters abound.
Comparisons. Should really convert the date to a daynumber, check it by reversion, and then check for + 1 day only.
20 IF (DATE(IT).EQ.DATE(TI)) THEN !Same date?
IF (ALL(V(:,IT) .EQ.V(:,TI)) .AND. !Yes. What about the data?
1 ALL(GOOD(:,IT).EQ.GOOD(:,TI))) THEN !This disregards details of the spacing of the data.
WRITE (MSG,21) NREC,DATE(IT),"same." !Also trailing zeroes, spurious + signs, blah blah.
21 FORMAT ("Record",I8," Duplicate date field (",A,"), data ",A) !Say it.
ELSE !But if they're not all equal,
WRITE (MSG,21) NREC,DATE(IT),"different!" !They're different!
END IF !So much for comparing the data.
END IF !So much for just comparing the date's text.
IF (ALL(GOOD(:,IT).GT.0)) NV = NV + 1 !A fully healthy record, either way?
GO TO 10 !More! More! I want more!!
Complaints. Should really distinguish between trouble in the date part and in the data part.
600 WRITE (MSG,*) '"END" declared - insufficient data?' !Not enough numbers, presumably.
GO TO 602 !Reveal the record.
601 WRITE (MSG,*) '"ERR" declared - improper number format?' !Ah, but which number?
602 WRITE (MSG,603) NREC,L,ACARD(1:L) !Anyway, reveal the uninterpreted record.
603 FORMAT("Record",I8,", length ",I0," reads ",A) !Just so.
HIC = HIC + 1 !This may grow into a habit.
IF (HIC.LE.12) GO TO 10 !But if not yet, try the next record.
STOP "Enough distaste." !Or, give up.
666 WRITE (MSG,101) NREC,"format error!" !For A-style data? Should never happen!
GO TO 900 !But if it does, give up!
Closedown.
100 WRITE (MSG,101) NREC,"then end-of-file" !Discovered on the next attempt.
101 FORMAT ("Record",I8,": ",A) !A record number plus a remark.
WRITE (MSG,102) NV !The overall results.
102 FORMAT (" with",I8," having all values good.") !This should do.
900 CLOSE(IN) !Done.
END !Spaghetti rules.

202
Task/Text-processing-2/REXX/text-processing-2.rexx
View file

@ -1,43 +1,43 @@
/*REXX program to process instrument data from a data file. */
numeric digits 20 /*allow for bigger numbers. */
ifid='READINGS.TXT' /*the input file. */
ofid='READINGS.OUT' /*the outut file. */
grandSum=0 /*grand sum of whole file. */
grandflg=0 /*grand num of flagged data. */
/*REXX program to process instrument data from a data file. */
numeric digits 20 /*allow for bigger numbers. */
ifid='READINGS.TXT' /*name of the input file. */
ofid='READINGS.OUT' /* " " " output " */
grandSum=0 /*grand sum of the whole file. */
grandFlg=0 /*grand number of flagged data. */
grandOKs=0
longFlag=0 /*longest period of flagged data.*/
contFlag=0 /*longest continous flagged data.*/
oldDate =0 /*placeholder of penutilmate date*/
w =16 /*width of fields when displayed.*/
dupDates=0 /*count of duplicated timestamps.*/
badflags=0 /*count of bad flags (¬ integer).*/
badDates=0 /*count of bad dates (bad format)*/
badData =0 /*count of bad datas (¬ numeric).*/
ignoredR=0 /*count of ignored records (bad).*/
maxInstruments=24 /*maximum number of instruments. */
yyyyCurr=right(date(),4) /*get the current year (today). */
monDD. =31 /*number of days in every month. */
/*February is figured on the fly.*/
Lflag=0 /*longest period of flagged data. */
Cflag=0 /*longest continuous flagged data. */
oldDate =0 /*placeholder of penultimate date. */
w =16 /*width of fields when displayed. */
dupDates=0 /*count of duplicated timestamps. */
badFlags=0 /*count of bad flags (not integer). */
badDates=0 /*count of bad dates (bad format). */
badData =0 /*count of bad data (not numeric). */
ignoredR=0 /*count of ignored records, bad records*/
maxInstruments=24 /*maximum number of instruments. */
yyyyCurr=right(date(),4) /*get the current year (today). */
monDD. =31 /*number of days in every month. */
/*# days in Feb. is figured on the fly.*/
monDD.4 =30
monDD.6 =30
monDD.9 =30
monDD.11=30
do records=1 while lines(ifid)\==0 /*read until finished. */
rec=linein(ifid) /*read the next record (line). */
parse var rec datestamp Idata /*pick off the dateStamp & data. */
if datestamp==oldDate then do /*found a duplicate timestamp. */
dupDates=dupDates+1 /*bump the counter.*/
call sy datestamp copies('~',30),
'is a duplicate of the',
"previous datestamp."
ignoredR=ignoredR+1 /*bump ignoredRecs.*/
iterate /*ignore this duplicate record. */
end
do records=1 while lines(ifid)\==0 /*read until finished. */
rec=linein(ifid) /*read the next record (line). */
parse var rec datestamp Idata /*pick off the the dateStamp and data. */
if datestamp==oldDate then do /*found a duplicate timestamp. */
dupDates=dupDates+1 /*bump the dupDate counter*/
call sy datestamp copies('~',30),
'is a duplicate of the',
"previous datestamp."
ignoredR=ignoredR+1 /*bump # of ignoredRecs.*/
iterate /*ignore this duplicate record. */
end
parse var datestamp yyyy '-' mm '-' dd /*obtain YYYY, MM, and DD. */
monDD.2=28+leapyear(yyyy) /*how long is February in YYYY ? */
/*check for various bad formats. */
parse var datestamp yyyy '-' mm '-' dd /*obtain YYYY, MM, and the DD. */
monDD.2=28+leapyear(yyyy) /*how long is February in year YYYY ? */
/*check for various bad formats. */
if verify(yyyy||mm||dd,1234567890)\==0 |,
length(datestamp)\==10 |,
length(yyyy)\==4 |,
@ -45,104 +45,96 @@ monDD.11=30
length(dd )\==2 |,
yyyy<1970 |,
yyyy>yyyyCurr |,
mm=0 | dd=0 |,
mm>12 | dd>monDD.mm then do
mm=0 | dd=0 |,
mm>12 | dd>monDD.mm then do
badDates=badDates+1
call sy datestamp copies('~'),
'has an illegal format.'
ignoredR=ignoredR+1 /*bump ignoredRecs.*/
iterate /*ignore this bad date record. */
ignoredR=ignoredR+1 /*bump number ignoredRecs.*/
iterate /*ignore this bad record. */
end
oldDate=datestamp /*save datestamp for next read. */
oldDate=datestamp /*save datestamp for the next read. */
sum=0
flg=0
OKs=0
do j=1 until Idata='' /*process the instrument data. */
do j=1 until Idata='' /*process the instrument data. */
parse var Idata data.j flag.j Idata
if pos('.',flag.j)\==0 |, /*flag have a decimal point -or-*/
\datatype(flag.j,'W') then do /*is the flag not a whole number?*/
badflags=badflags+1 /*bump counter.*/
call sy datestamp copies('~'),
'instrument' j "has a bad flag:",
flag.j
iterate /*ignore it & it's data.*/
end
if pos('.',flag.j)\==0 |, /*does flag have a decimal point -or- */
\datatype(flag.j,'W') then do /* ··· is the flag not a whole number? */
badFlags=badFlags+1 /*bump badFlags counter*/
call sy datestamp copies('~'),
'instrument' j "has a bad flag:",
flag.j
iterate /*ignore it and it's data. */
end
if \datatype(data.j,'N') then do /*is the flag not a whole number?*/
badData=badData+1 /*bump counter.*/
call sy datestamp copies('~'),
'instrument' j "has bad data:",
data.j
iterate /*ignore it & it's flag.*/
end
if \datatype(data.j,'N') then do /*is the flag not a whole number?*/
badData=badData+1 /*bump counter.*/
call sy datestamp copies('~'),
'instrument' j "has bad data:",
data.j
iterate /*ignore it & it's flag.*/
end
if flag.j>0 then do /*if good data, ... */
OKs=OKs+1
sum=sum+data.j
if contFlag>longFlag then do
longdate=datestamp
longFlag=contFlag
end
contFlag=0
end
else do /*flagged data ... */
flg=flg+1
contFlag=contFlag+1
end
if flag.j>0 then do /*if good data, ~~~ */
OKs=OKs+1
sum=sum+data.j
if Cflag>Lflag then do
Ldate=datestamp
Lflag=Cflag
end
Cflag=0
end
else do /*flagged data ~~~ */
flg=flg+1
Cflag=Cflag+1
end
end /*j*/
if j>maxInstruments then do
badData=badData+1 /*bump counter.*/
badData=badData+1 /*bump the badData counter.*/
call sy datestamp copies('~'),
'too many instrument datum'
end
if OKs\==0 then avg=format(sum/OKs,,3)
else avg='[n/a]'
if OKs\==0 then avg=format(sum/OKs,,3)
else avg='[n/a]'
grandOKs=grandOKs+OKs
_=right(comma(avg),w)
_=right(commas(avg),w)
grandSum=grandSum+sum
grandFlg=grandFlg+flg
if flg==0 then call sy datestamp ' average='_
else call sy datestamp ' average='_ ' flagged='right(flg,2)
end /*records*/
records=records-1 /*adjust for reading end-of-file.*/
if grandOKs\==0 then grandAvg=format(grandsum/grandOKs,,3)
else grandAvg='[n/a]'
records=records-1 /*adjust for reading the end─of─file. */
if grandOKs\==0 then grandAvg=format(grandsum/grandOKs,,3)
else grandAvg='[n/a]'
call sy
call sy copies('=',60)
call sy ' records read:' right(comma(records ),w)
call sy ' records ignored:' right(comma(ignoredR),w)
call sy ' grand sum:' right(comma(grandSum),w+4)
call sy ' grand average:' right(comma(grandAvg),w+4)
call sy ' grand OK data:' right(comma(grandOKs),w)
call sy ' grand flagged:' right(comma(grandFlg),w)
call sy ' duplicate dates:' right(comma(dupDates),w)
call sy ' bad dates:' right(comma(badDates),w)
call sy ' bad data:' right(comma(badData ),w)
call sy ' bad flags:' right(comma(badflags),w)
if longFlag\==0 then
call sy ' longest flagged:' right(comma(longFlag),w) " ending at " longdate
call sy ' records read:' right(commas(records ),w)
call sy ' records ignored:' right(commas(ignoredR),w)
call sy ' grand sum:' right(commas(grandSum),w+4)
call sy ' grand average:' right(commas(grandAvg),w+4)
call sy ' grand OK data:' right(commas(grandOKs),w)
call sy ' grand flagged:' right(commas(grandFlg),w)
call sy ' duplicate dates:' right(commas(dupDates),w)
call sy ' bad dates:' right(commas(badDates),w)
call sy ' bad data:' right(commas(badData ),w)
call sy ' bad flags:' right(commas(badFlags),w)
if Lflag\==0 then call sy ' longest flagged:' right(commas(LFlag),w) " ending at " Ldate
call sy copies('=',60)
call sy
exit /*stick a fork in it, we're done.*/
/*──────────────────────────────────LEAPYEAR subroutine─────────────────*/
leapyear: procedure; arg y /*year could be: Y, YY, YYY, YYYY*/
if length(y)==2 then y=left(right(date(),4),2)y /*adjust for YY year.*/
if y//4\==0 then return 0 /* not ≈ by 4? Not a leapyear.*/
return y//100\==0 | y//400==0 /*apply 100 and 400 year rule. */
/*──────────────────────────────────SY subroutine───────────────────────*/
sy: procedure; parse arg stuff; say stuff
if 1==0 then call lineout ofid,stuff
return
/*──────────────────────────────────COMMA subroutine────────────────────*/
comma: procedure; parse arg _,c,p,t;arg ,cu;c=word(c ",",1)
if cu=='BLANK' then c=' ';o=word(p 3,1);p=abs(o);t=word(t 999999999,1)
if \datatype(p,'W')|\datatype(t,'W')|p==0|arg()>4 then return _;n=_'.9'
#=123456789;k=0;if o<0 then do;b=verify(_,' ');if b==0 then return _
e=length(_)-verify(reverse(_),' ')+1;end;else do;b=verify(n,#,"M")
e=verify(n,#'0',,verify(n,#"0.",'M'))-p-1;end
do j=e to b by -p while k<t;_=insert(c,_,j);k=k+1;end;return _
exit /*stick a fork in it, we're all done.*/
/*────────────────────────────────────────────────────────────────────────────*/
commas: procedure; parse arg _; n=_'.9'; #=123456789; b=verify(n,#,"M")
e=verify(n,#'0',,verify(n,#"0.",'M'))-4
do j=e to b by -3; _=insert(',',_,j); end /*j*/; return _
/*────────────────────────────────────────────────────────────────────────────*/
leapyear: procedure; arg y /*year could be: Y, YY, YYY, or YYYY*/
if length(y)==2 then y=left(right(date(),4),2)y /*adjust for YY year.*/
if y//4\==0 then return 0 /* not divisible by 4? Not a leapyear*/
return y//100\==0 | y//400==0 /*apply the 100 and the 400 year rule.*/
/*────────────────────────────────────────────────────────────────────────────*/
sy: say arg(1); call lineout ofid,arg(1); return

54
Task/Text-processing-2/VBScript/text-processing-2.vb Normal file
View file

@ -0,0 +1,54 @@
Set objFSO = CreateObject("Scripting.FileSystemObject")
Set objFile = objFSO.OpenTextFile(objFSO.GetParentFolderName(WScript.ScriptFullName) &_
"\readings.txt",1)
Set objDateStamp = CreateObject("Scripting.Dictionary")
Total_Records = 0
Valid_Records = 0
Duplicate_TimeStamps = ""
Do Until objFile.AtEndOfStream
line = objFile.ReadLine
If line <> "" Then
token = Split(line,vbTab)
If objDateStamp.Exists(token(0)) = False Then
objDateStamp.Add token(0),""
Total_Records = Total_Records + 1
If IsValid(token) Then
Valid_Records = Valid_Records + 1
End If
Else
Duplicate_TimeStamps = Duplicate_TimeStamps & token(0) & vbCrLf
Total_Records = Total_Records + 1
End If
End If
Loop
Function IsValid(arr)
IsValid = True
Bad_Readings = 0
n = 1
Do While n <= UBound(arr)
If n + 1 <= UBound(arr) Then
If CInt(arr(n+1)) < 1 Then
Bad_Readings = Bad_Readings + 1
End If
End If
n = n + 2
Loop
If Bad_Readings > 0 Then
IsValid = False
End If
End Function
WScript.StdOut.Write "Total Number of Records = " & Total_Records
WScript.StdOut.WriteLine
WScript.StdOut.Write "Total Valid Records = " & Valid_Records
WScript.StdOut.WriteLine
WScript.StdOut.Write "Duplicate Timestamps:"
WScript.StdOut.WriteLine
WScript.StdOut.Write Duplicate_TimeStamps
WScript.StdOut.WriteLine
objFile.Close
Set objFSO = Nothing