Rosetta Code

Text processing/2: Difference between revisions

Page Discussion

Text processing/2 (view source)

Revision as of 04:34, 8 August 2015

275 bytes added ,  8 years ago
m
→‎{{header|REXX}}: added/changed whitespace and comments, simplified the COMMAS subroutine.
m (→‎{{header|REXX}}: added/changed whitespace and comments, simplified the COMMAS subroutine.)
Line 2,241:
 
=={{header|REXX}}==
This REXX program process the file mentioned in "text processing 1" and does further valiidatevalidate on the dates, flags, and data.
<br><br>
Some of the checks performed are:
::* &nbsp; checks for duplicated date records.
::* &nbsp; checks for a bad date (YYYY-MM-DD) format, among:
::* &nbsp; wrong length
::* &nbsp; year > current year
::* &nbsp; year < 1970 (to allow for posthumous data)
::* &nbsp; mm < 1 or mm > 12
::* &nbsp; dd < 1 or dd > days for the month
::* &nbsp; yyyy, dd, mm isn't numeric
::* &nbsp; missing data (or flags)
::* &nbsp; flag isn't an integer
::* &nbsp; flag contains a decimal point
::* &nbsp; data isn't numeric
In addition, all of the presented numbers (may) have commas inserted.
<br><br>
The program has (negated) code to write the report to a file in addition to the console.
<lang rexx>/*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' /*the outut" file. " " output " */
grandSum=0 /*grand sum of the whole file. */
grandflggrandFlg=0 /*grand numnumber of flagged data. */
grandOKs=0
longFlagLflag=0 /*longest period of flagged data. */
contFlagCflag=0 /*longest continouscontinuous flagged data. */
oldDate =0 /*placeholder of penutilmatepenultimate date. */
w =16 /*width of fields when displayed. */
dupDates=0 /*count of duplicated timestamps. */
badflagsbadFlags=0 /*count of bad flags (¬not integer). */
badDates=0 /*count of bad dates (bad format). */
badData =0 /*count of bad datasdata (¬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. */
/*February# days in Feb. is figured on the fly.*/
monDD.4 =30
monDD.6 =30
Line 2,284:
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 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 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 |,
Line 2,306:
yyyy<1970 |,
yyyy>yyyyCurr |,
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 number ignoredRecs.*/
iterate /*ignore this bad date record. */
end
oldDate=datestamp /*save datestamp for the next read. */
sum=0
flg=0
OKs=0
 
do j=1 until Idata='' /*process the instrument data. */
parse var Idata data.j flag.j Idata
 
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=badflagsbadFlags+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 flag.j>0 then do /*if good data, ...~~~ */
OKs=OKs+1
sum=sum+data.j
if contFlagCflag>longFlagLflag then do
longdateLdate=datestamp
longFlagLflag=contFlagCflag
end
contFlag Cflag=0
end
else do /*flagged data ...~~~ */
flg=flg+1
contFlag Cflag=contFlagCflag+1
end
end /*j*/
 
if j>maxInstruments then do
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]'
grandOKs=grandOKs+OKs
_=right(commacommas(avg),w)
grandSum=grandSum+sum
grandFlg=grandFlg+flg
Line 2,370:
end /*records*/
 
records=records-1 /*adjust for reading end-of-filethe 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(commacommas(records ),w)
call sy ' records ignored:' right(commacommas(ignoredR),w)
call sy ' grand sum:' right(commacommas(grandSum),w+4)
call sy ' grand average:' right(commacommas(grandAvg),w+4)
call sy ' grand OK data:' right(commacommas(grandOKs),w)
call sy ' grand flagged:' right(commacommas(grandFlg),w)
call sy ' duplicate dates:' right(commacommas(dupDates),w)
call sy ' bad dates:' right(commacommas(badDates),w)
call sy ' bad data:' right(commacommas(badData ),w)
call sy ' bad flags:' right(commacommas(badflagsbadFlags),w)
if Lflag\==0 then call sy ' longest flagged:' right(commacommas(longFlagLFlag),w) " ending at " longdateLdate▼
if longFlag\==0 then
▲call sy ' longest flagged:' right(comma(longFlag),w) " ending at " longdate
call sy copies('=',60)
exit /*stick a fork in it, we're all done.*/▼
call sy
/*────────────────────────────────────────────────────────────────────────────*/
▲exit /*stick a fork in it, we're done.*/
commas: procedure; parse arg _; n=_'.9'; #=123456789; b=verify(n,#,"M")
/*──────────────────────────────────LEAPYEAR subroutine─────────────────*/
e=verify(n,#'0',,verify(n,#"0.",'M'))-p-1;end4▼
leapyear: procedure; arg y /*year could be: Y, YY, YYY, YYYY*/
do j=e to b by -p3; while k<t;_=insert(c',',_,j);k=k+1; end /*j*/; return _</lang>▼
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.*/▼
returnleapyear: y//100\==0procedure; |arg y//400==0 /*applyyear 100could andbe: 400 yearY, YY, rule. YYY, or YYYY*/
▲if length(y)==2 then y=left(right(date(),4),2)y /*adjust for YY year.*/
/*──────────────────────────────────SY subroutine───────────────────────*/
▲if y//4\==0 then return 0 /* not ≈divisible by 4? Not a leapyear.*/
sy: procedure; parse arg stuff; say stuff
return y//100\==0 | y//400==0 /*apply the 100 and the 400 year rule.*/
if 1==0 then call lineout ofid,stuff
/*────────────────────────────────────────────────────────────────────────────*/
return
sy: say arg(1); call lineout ofid,arg(1); return</lang>
/*──────────────────────────────────COMMA subroutine────────────────────*/
'''output''' &nbsp; when using the default input file:
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 _</lang>
'''output'''
<pre style="height:35ex">
∙
Retrieved from "https://rosettacode.org/wiki/Special:MobileDiff/86955"