all tasks

2013-04-11 01:07:29 -07:00 · 2013-04-11 01:07:29 -07:00 · 68f8f3e56b
commit 68f8f3e56b
parent b83f433714
14735 changed files with 178959 additions and 0 deletions
--- a/Task/Text-processing-1/0DESCRIPTION
+++ b/Task/Text-processing-1/0DESCRIPTION
@ -0,0 +1,34 @@
+{{Template:clarify task}}
+
+Often data is produced by one program, in the wrong format for later use by another program or person. In these situations another program can be written to parse and transform the original data into a format useful to the other. The term "Data Munging" is [http://www.google.co.uk/search?q=%22data+munging%22 often] used in programming circles for this task.
+
+A [http://groups.google.co.uk/group/comp.lang.awk/msg/0ecba3a3fbf247d8?hl=en request] on the comp.lang.awk newsgroup lead to a typical data munging task:
+<pre>I have to analyse data files that have the following format:
+Each row corresponds to 1 day and the field logic is: $1 is the date,
+followed by 24 value/flag pairs, representing measurements at 01:00,
+02:00 ... 24:00 of the respective day. In short:
+
+<date> <val1> <flag1> <val2> <flag2> ...  <val24> <flag24>
+
+Some test data is available at:
+... (nolonger available at original location)
+
+I have to sum up the values (per day and only valid data, i.e. with
+flag>0) in order to calculate the mean. That's not too difficult.
+However, I also need to know what the "maximum data gap" is, i.e. the
+longest period with successive invalid measurements (i.e values with
+flag<=0)</pre>
+
+The data is [http://www.eea.europa.eu/help/eea-help-centre/faqs/how-do-i-obtain-eea-reports free to download and use] and is of this format:
+<pre style="height:20ex;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
+1991-03-31	40.000	1	0.000	-2	0.000	-2	0.000	-2	0.000	-2	0.000	-2	0.000	-2	0.000	-2	0.000	-2	0.000	-2	0.000	-2	0.000	-2	0.000	-2	0.000	-2	0.000	-2	0.000	-2	0.000	-2	0.000	-2	0.000	-2	0.000	-2	0.000	-2	0.000	-2	0.000	-2	0.000	-2
+1991-04-01	0.000	-2	13.000	1	16.000	1	21.000	1	24.000	1	22.000	1	20.000	1	18.000	1	29.000	1	44.000	1	50.000	1	43.000	1	38.000	1	27.000	1	27.000	1	24.000	1	23.000	1	18.000	1	12.000	1	13.000	1	14.000	1	15.000	1	13.000	1	10.000	1
+1991-04-02	8.000	1	9.000	1	11.000	1	12.000	1	12.000	1	12.000	1	27.000	1	26.000	1	27.000	1	33.000	1	32.000	1	31.000	1	29.000	1	31.000	1	25.000	1	25.000	1	24.000	1	21.000	1	17.000	1	14.000	1	15.000	1	12.000	1	12.000	1	10.000	1
+1991-04-03	10.000	1	9.000	1	10.000	1	10.000	1	9.000	1	10.000	1	15.000	1	24.000	1	28.000	1	24.000	1	18.000	1	14.000	1	12.000	1	13.000	1	14.000	1	15.000	1	14.000	1	15.000	1	13.000	1	13.000	1	13.000	1	12.000	1	10.000	1	10.000	1
+</pre>
+
+Only a sample of the data showing its format is given above. The full example file may be downloaded [http://rosettacode.org/resources/readings.zip here].
+
+Structure your program to show statistics for each line of the file, (similar to the original Python, Perl, and AWK examples below), followed by summary statistics for the file. When showing example output just show a few line statistics and the full end summary.
--- a/Task/Text-processing-1/1META.yaml
+++ b/Task/Text-processing-1/1META.yaml
@ -0,0 +1,2 @@
+---
+note: Text processing
--- a/Task/Text-processing-1/ALGOL-68/text-processing-1.alg
+++ b/Task/Text-processing-1/ALGOL-68/text-processing-1.alg
@ -0,0 +1,95 @@
+INT no data := 0;               # Current run of consecutive flags<0 in lines of file #
+INT no data max := -1;          # Max consecutive flags<0 in lines of file #
+FLEX[0]STRING no data max line; # ... and line number(s) where it occurs #
+
+REAL tot file := 0;             # Sum of file data #
+INT num file := 0;              # Number of file data items with flag>0 #
+
+# CHAR fs = " "; #
+INT nf = 24;
+
+INT upb list := nf;
+FORMAT list repr = $n(upb list-1)(g", ")g$;
+
+PROC exception = ([]STRING args)VOID:(
+  putf(stand error, ($"Exception"$, $", "g$, args, $l$));
+  stop
+);
+
+PROC raise io error = (STRING message)VOID:exception(("io error", message));
+
+OP +:= = (REF FLEX []STRING rhs, STRING append)REF FLEX[]STRING: (
+  HEAP [UPB rhs+1]STRING out rhs;
+  out rhs[:UPB rhs] := rhs;
+  out rhs[UPB rhs+1] := append;
+  rhs := out rhs;
+  out rhs
+);
+
+INT upb opts = 3; # these are "a68g" "./Data_Munging.a68" & "-" #
+[argc - upb opts]STRING in files;
+FOR arg TO UPB in files DO in files[arg] := argv(upb opts + arg) OD;
+
+MODE FIELD = STRUCT(REAL data, INT flag);
+FORMAT field repr = $2(g)$;
+
+FOR index file TO UPB in files DO
+  STRING file name = in files[index file], FILE file;
+  IF open(file, file name, stand in channel) NE 0 THEN
+    raise io error("Cannot open """+file name+"""") FI;
+  on logical file end(file, (REF FILE f)BOOL: logical file end done);
+  REAL tot line, INT num line;
+  # make term(file, ", ") for CSV data #
+  STRING date;
+  DO
+    tot line := 0;             # sum of line data #
+    num line := 0;             # number of line data items with flag>0 #
+    # extract field info #
+    [nf]FIELD data;
+    getf(file, ($10a$, date, field repr, data, $l$));
+
+    FOR key TO UPB data DO
+      FIELD field = data[key];
+      IF flag OF field<1 THEN
+        no data +:= 1
+      ELSE
+        # check run of data-absent data #
+        IF no data max = no data AND no data>0 THEN
+          no data max line +:= date FI;
+        IF no data max<no data AND no data>0 THEN
+          no data max := no data;
+          no data max line := date FI;
+        # re-initialise run of no data counter #
+        no data := 0;
+        # gather values for averaging #
+        tot line +:= data OF field;
+        num line +:= 1
+      FI
+    OD;
+
+    # totals for the file so far #
+    tot file +:= tot line;
+    num file +:= num line;
+
+    printf(($"Line: "g"  Reject: "g(-2)"  Accept: "g(-2)"  Line tot: "g(-14, 3)"  Line avg: "g(-14, 3)l$,
+          date,
+          UPB(data) -num line,
+          num line, tot line,
+          IF num line>0 THEN tot line/num line ELSE 0 FI))
+  OD;
+  logical file end done:
+    close(file)
+OD;
+
+FORMAT plural = $b(" ", "s")$,
+       p = $b("", "s")$;
+
+upb list := UPB in files;
+printf(($l"File"f(plural)"    = "$, upb list = 1, list repr, in files, $l$,
+        $"Total    = "g(-0, 3)l$, tot file,
+        $"Readings = "g(-0)l$, num file,
+        $"Average  = "g(-0, 3)l$, tot file / num file));
+
+upb list := UPB no data max line;
+printf(($l"Maximum run"f(p)" of "g(-0)" consecutive false reading"f(p)" ends at line starting with date"f(p)": "$,
+    upb list = 1, no data max, no data max = 0, upb list = 1, list repr, no data max line, $l$))
--- a/Task/Text-processing-1/AWK/text-processing-1.awk
+++ b/Task/Text-processing-1/AWK/text-processing-1.awk
@ -0,0 +1,63 @@
+BEGIN{
+  nodata = 0;             # Current run of consecutive flags<0 in lines of file
+  nodata_max=-1;          # Max consecutive flags<0 in lines of file
+  nodata_maxline="!";     # ... and line number(s) where it occurs
+}
+FNR==1 {
+  # Accumulate input file names
+  if(infiles){
+    infiles = infiles "," infiles
+  } else {
+    infiles = FILENAME
+  }
+}
+{
+  tot_line=0;             # sum of line data
+  num_line=0;             # number of line data items with flag>0
+
+  # extract field info, skipping initial date field
+  for(field=2; field<=NF; field+=2){
+    datum=$field;
+    flag=$(field+1);
+    if(flag<1){
+      nodata++
+    }else{
+      # check run of data-absent fields
+      if(nodata_max==nodata && (nodata>0)){
+        nodata_maxline=nodata_maxline ", " $1
+      }
+      if(nodata_max<nodata && (nodata>0)){
+        nodata_max=nodata
+        nodata_maxline=$1
+      }
+      # re-initialise run of nodata counter
+      nodata=0;
+      # gather values for averaging
+      tot_line+=datum
+      num_line++;
+    }
+  }
+
+  # totals for the file so far
+  tot_file += tot_line
+  num_file += num_line
+
+  printf "Line: %11s  Reject: %2i  Accept: %2i  Line_tot: %10.3f  Line_avg: %10.3f\n", \
+         $1, ((NF -1)/2) -num_line, num_line, tot_line, (num_line>0)? tot_line/num_line: 0
+
+  # debug prints of original data plus some of the computed values
+  #printf "%s  %15.3g  %4i\n", $0, tot_line, num_line
+  #printf "%s\n  %15.3f  %4i  %4i  %4i  %s\n", $0, tot_line, num_line,  nodata, nodata_max, nodata_maxline
+
+
+}
+
+END{
+  printf "\n"
+  printf "File(s)  = %s\n", infiles
+  printf "Total    = %10.3f\n", tot_file
+  printf "Readings = %6i\n", num_file
+  printf "Average  = %10.3f\n", tot_file / num_file
+
+  printf "\nMaximum run(s) of %i consecutive false readings ends at line starting with date(s): %s\n", nodata_max, nodata_maxline
+}
--- a/Task/Text-processing-1/Ada/text-processing-1.ada
+++ b/Task/Text-processing-1/Ada/text-processing-1.ada
@ -0,0 +1,76 @@
+with Ada.Text_IO;            use Ada.Text_IO;
+with Strings_Edit;           use Strings_Edit;
+with Strings_Edit.Floats;    use Strings_Edit.Floats;
+with Strings_Edit.Integers;  use Strings_Edit.Integers;
+
+procedure Data_Munging is
+   Syntax_Error : exception;
+   type Gap_Data is record
+      Count   : Natural := 0;
+      Line    : Natural := 0;
+      Pointer : Integer;
+      Year    : Integer;
+      Month   : Integer;
+      Day     : Integer;
+   end record;
+   File    : File_Type;
+   Max     : Gap_Data;
+   This    : Gap_Data;
+   Current : Gap_Data;
+   Count   : Natural := 0;
+   Sum     : Float   := 0.0;
+begin
+   Open (File, In_File, "readings.txt");
+   loop
+      declare
+         Line    : constant String := Get_Line (File);
+         Pointer : Integer := Line'First;
+         Flag    : Integer;
+         Data    : Float;
+      begin
+         Current.Line := Current.Line + 1;
+         Get (Line, Pointer, SpaceAndTab);
+         Get (Line, Pointer, Current.Year);
+         Get (Line, Pointer, Current.Month);
+         Get (Line, Pointer, Current.Day);
+         while Pointer <= Line'Last loop
+            Get (Line, Pointer, SpaceAndTab);
+            Current.Pointer := Pointer;
+            Get (Line, Pointer, Data);
+            Get (Line, Pointer, SpaceAndTab);
+            Get (Line, Pointer, Flag);
+            if Flag < 0 then
+               if This.Count = 0 then
+                  This := Current;
+               end if;
+               This.Count := This.Count + 1;
+            else
+               if This.Count > 0 and then Max.Count < This.Count then
+                  Max := This;
+               end if;
+               This.Count := 0;
+               Count := Count + 1;
+               Sum   := Sum + Data;
+            end if;
+         end loop;
+      exception
+         when End_Error =>
+            raise Syntax_Error;
+      end;
+   end loop;
+exception
+   when End_Error =>
+      Close (File);
+      if This.Count > 0 and then Max.Count < This.Count then
+         Max := This;
+      end if;
+      Put_Line ("Average " & Image (Sum / Float (Count)) & " over " & Image (Count));
+      if Max.Count > 0 then
+         Put ("Max. " & Image (Max.Count) & " false readings start at ");
+         Put (Image (Max.Line) & ':' & Image (Max.Pointer) & " stamped ");
+         Put_Line (Image (Max.Year) & Image (Max.Month) & Image (Max.Day));
+      end if;
+   when others =>
+      Close (File);
+      Put_Line ("Syntax error at " & Image (Current.Line) & ':' & Image (Max.Pointer));
+end Data_Munging;
--- a/Task/Text-processing-1/Aime/text-processing-1.aime
+++ b/Task/Text-processing-1/Aime/text-processing-1.aime
@ -0,0 +1,48 @@
+integer bads, count, max_bads;
+file f;
+list l;
+real s;
+text bad_day, worst_day;
+
+f_affix(f, "/dev/stdin");
+
+max_bads = 0;
+count = 0;
+bads = 0;
+s = 0;
+
+while (f_list(f, l, 0) ^ -1) {
+    integer e, i;
+
+    i = 2;
+    while (i < 49) {
+	e = atoi(l_q_text(l, i));
+	if (0 < e) {
+	    count += 1;
+	    s += atof(l_q_text(l, i - 1));
+	    if (max_bads < bads) {
+		max_bads = bads;
+		worst_day = bad_day;
+	    }
+	    bads = 0;
+	} else {
+	    if (!bads) {
+		bad_day = l_q_text(l, 0);
+	    }
+	    bads += 1;
+	}
+	i += 2;
+    }
+}
+
+o_text("Averaged ");
+o_real(3, s / count);
+o_text(" over ");
+o_integer(count);
+o_text(" readings.\n");
+
+o_text("Longest bad run ");
+o_integer(max_bads);
+o_text(", started ");
+o_text(worst_day);
+o_text(".\n");
--- a/Task/Text-processing-1/AutoHotkey/text-processing-1.ahk
+++ b/Task/Text-processing-1/AutoHotkey/text-processing-1.ahk
@ -0,0 +1,74 @@
+# Author AlephX Aug 17 2011
+
+SetFormat, float, 4.2
+SetFormat, FloatFast, 4.2
+
+data = %A_scriptdir%\readings.txt
+result = %A_scriptdir%\results.txt
+totvalid := 0
+totsum := 0
+totavg:= 0
+
+Loop, Read, %data%, %result%
+	{
+	sum := 0
+	Valid := 0
+	Couples := 0
+	Lines := A_Index
+    Loop, parse, A_LoopReadLine, %A_Tab%
+		{
+        ;MsgBox, Field number %A_Index% is %A_LoopField%
+		if A_index = 1
+			{
+			Date := A_LoopField
+			Counter := 0
+			}
+		else
+			{
+			Counter++
+			couples := Couples + 0.5
+			if Counter = 1
+				{
+				value := A_LoopField / 1
+				}
+			else
+				{
+				if A_loopfield > 0
+					{
+					Sum := Sum + value
+					Valid++
+					
+					if (wrong > maxwrong)
+						{
+						maxwrong := wrong
+						lastwrongdate := currwrongdate
+						startwrongdate := firstwrongdate
+						startoccurrence := firstoccurrence
+						lastoccurrence := curroccurrence
+						}
+					wrong := 0
+					}
+				else
+					{
+					wrong++
+					currwrongdate := date
+					curroccurrence := (A_index-1) / 2	
+					if (wrong = 1)
+						{
+						firstwrongdate := date
+						firstoccurrence := curroccurrence
+						}
+					}				
+				Counter := 0
+				}
+			}			
+		}
+	avg := sum / valid
+	TotValid := Totvalid+valid
+	TotSum := Totsum+sum
+	FileAppend, Day: %date% sum: %sum% avg: %avg% Readings: %valid%/%couples%`n	
+	}
+	
+Totavg := TotSum / TotValid
+FileAppend, `n`nDays %Lines%`nMaximal wrong readings: %maxwrong% from %startwrongdate% at %startoccurrence% to %lastwrongdate% at %lastoccurrence%`n`n, %result%
+FileAppend, Valid readings: %TotValid%`nTotal Value: %TotSUm%`nAverage: %TotAvg%, %result%
--- a/Task/Text-processing-1/BBC-BASIC/text-processing-1.bbc
+++ b/Task/Text-processing-1/BBC-BASIC/text-processing-1.bbc
@ -0,0 +1,43 @@
+      file% = OPENIN("readings.txt")
+      IF file% = 0 THEN PRINT "Could not open test data file" : END
+
+      Total = 0
+      Count% = 0
+      BadMax% = 0
+      bad% = 0
+      WHILE NOT EOF#file%
+        text$ = GET$#file%
+        IF text$<>"" THEN
+          tab% = INSTR(text$, CHR$(9))
+          date$ = LEFT$(text$, tab% - 1)
+          acc = 0
+          cnt% = 0
+          FOR field% = 1 TO 24
+            dval = VALMID$(text$, tab%+1)
+            tab% = INSTR(text$, CHR$(9), tab%+1)
+            flag% = VALMID$(text$, tab%+1)
+            tab% = INSTR(text$, CHR$(9), tab%+1)
+            IF flag% > 0 THEN
+              acc += dval
+              cnt% += 1
+              bad% = 0
+            ELSE
+              bad% += 1
+              IF bad% > BadMax% BadMax% = bad% : BadDate$ = date$
+            ENDIF
+          NEXT field%
+          @% = &90A
+          PRINT "Date: " date$ "  Good = "; cnt%, "  Bad = "; 24-cnt%, ;
+          @% = &20308
+          IF cnt% THEN PRINT "  Total = " acc "  Mean = " acc / cnt% ;
+          PRINT
+          Total += acc
+          Count% += cnt%
+        ENDIF
+      ENDWHILE
+      CLOSE #file%
+      PRINT ' "Grand total = " ; Total
+      PRINT "Number of valid readings = " ; STR$(Count%)
+      PRINT "Overall mean = " ; Total / Count%
+      @% = &90A
+      PRINT '"Longest run of bad readings = " ; BadMax% " ending " BadDate$
--- a/Task/Text-processing-1/Batch-File/text-processing-1.bat
+++ b/Task/Text-processing-1/Batch-File/text-processing-1.bat
@ -0,0 +1,67 @@
+@echo off
+setlocal ENABLEDELAYEDEXPANSION
+set maxrun=    0
+set maxstart=
+set maxend=
+set notok=0
+set inputfile=%1
+for /F "tokens=1,*" %%i in (%inputfile%) do (
+    set date=%%i
+    call :processline %%j
+)
+
+echo\
+echo max false: %maxrun%  from %maxstart% until %maxend%
+
+goto :EOF
+
+:processline
+set sum=0000
+set count=0
+set hour=1
+:loop
+if "%1"=="" goto :result
+set num=%1
+if "%2"=="1" (
+    if "%notok%" NEQ "0" (
+        set notok=     !notok!
+        if /I "!notok:~-5!" GTR "%maxrun%" (
+            set maxrun=!notok:~-5!
+            set maxstart=%nok0date% %nok0hour%
+            set maxend=%nok1date% %nok1hour%
+        )
+        set notok=0
+    )
+    set /a sum+=%num:.=%
+    set /a count+=1
+) else (
+    if "%notok%" EQU "0" (
+        set nok0date=%date%
+        set nok0hour=%hour%
+    ) else (
+        set nok1date=%date%
+        set nok1hour=%hour%
+    )
+    set /a notok+=1
+)
+shift
+shift
+set /a hour+=1
+goto :loop
+
+:result
+if "%count%"=="0" (
+    set mean=0
+) else (
+    set /a mean=%sum%/%count%
+)
+if "%mean%"=="0" set mean=0000
+if "%sum%"=="0" set sum=0000
+set mean=%mean:~0,-3%.%mean:~-3%
+set sum=%sum:~0,-3%.%sum:~-3%
+set count=   %count%
+set sum=    %sum%
+set mean=    %mean%
+echo Line: %date% Accept: %count:~-3%  tot: %sum:~-8%  avg: %mean:~-8%
+
+goto :EOF
--- a/Task/Text-processing-1/C++/text-processing-1.cpp
+++ b/Task/Text-processing-1/C++/text-processing-1.cpp
@ -0,0 +1,67 @@
+#include <iostream>
+#include <fstream>
+#include <string>
+#include <vector>
+#include <iomanip>
+#include <boost/lexical_cast.hpp>
+#include <boost/algorithm/string.hpp>
+
+using std::cout;
+using std::endl;
+const int NumFlags = 24;
+
+int main()
+{
+    std::fstream file("readings.txt");
+
+    int badCount = 0;
+    std::string badDate;
+    int badCountMax = 0;
+    while(true)
+    {
+        std::string line;
+        getline(file, line);
+        if(!file.good())
+            break;
+
+        std::vector<std::string> tokens;
+        boost::algorithm::split(tokens, line, boost::is_space());
+
+        if(tokens.size() != NumFlags * 2 + 1)
+        {
+            cout << "Bad input file." << endl;
+            return 0;
+        }
+
+        double total = 0.0;
+        int accepted = 0;
+        for(size_t i = 1; i < tokens.size(); i += 2)
+        {
+            double val = boost::lexical_cast<double>(tokens[i]);
+            int flag = boost::lexical_cast<int>(tokens[i+1]);
+            if(flag > 0)
+            {
+                total += val;
+                ++accepted;
+                badCount = 0;
+            }
+            else
+            {
+                ++badCount;
+                if(badCount > badCountMax)
+                {
+                    badCountMax = badCount;
+                    badDate = tokens[0];
+                }
+            }
+        }
+
+        cout << tokens[0];
+        cout << "  Reject: " << std::setw(2) << (NumFlags - accepted);
+        cout << "  Accept: " << std::setw(2) << accepted;
+        cout << "  Average: " << std::setprecision(5) << total / accepted << endl;
+    }
+    cout << endl;
+    cout << "Maximum number of consecutive bad readings is " << badCountMax << endl;
+    cout << "Ends on date " << badDate << endl;
+}
--- a/Task/Text-processing-1/C/text-processing-1.c
+++ b/Task/Text-processing-1/C/text-processing-1.c
@ -0,0 +1,85 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+static int badHrs, maxBadHrs;
+
+static double hrsTot = 0.0;
+static int rdgsTot = 0;
+char bhEndDate[40];
+
+int mungeLine( char *line, int lno, FILE *fout )
+{
+    char date[40], *tkn;
+    int   dHrs, flag, hrs2, hrs;
+    double hrsSum;
+    int   hrsCnt = 0;
+    double avg;
+
+    tkn = strtok(line, ".");
+    if (tkn) {
+        int n = sscanf(tkn, "%s %d", &date, &hrs2);
+        if (n<2) {
+            printf("badly formated line - %d %s\n", lno, tkn);
+            return 0;
+        }
+        hrsSum = 0.0;
+        while( tkn= strtok(NULL, ".")) {
+            n = sscanf(tkn,"%d %d %d", &dHrs, &flag, &hrs);
+            if (n>=2) {
+                if (flag > 0) {
+                    hrsSum += 1.0*hrs2 + .001*dHrs;
+                    hrsCnt += 1;
+                    if (maxBadHrs < badHrs) {
+                        maxBadHrs = badHrs;
+                        strcpy(bhEndDate, date);
+                    }
+                    badHrs = 0;
+                }
+                else {
+                    badHrs += 1;
+                }
+                hrs2 = hrs;
+            }
+            else {
+                printf("bad file syntax line %d: %s\n",lno, tkn);
+            }
+        }
+        avg = (hrsCnt > 0)? hrsSum/hrsCnt : 0.0;
+        fprintf(fout, "%s  Reject: %2d  Accept: %2d  Average: %7.3f\n",
+                date, 24-hrsCnt, hrsCnt, hrsSum/hrsCnt);
+        hrsTot += hrsSum;
+        rdgsTot += hrsCnt;
+    }
+    return 1;
+}
+
+int main()
+{
+    FILE *infile, *outfile;
+    int lineNo = 0;
+    char line[512];
+    const char *ifilename = "readings.txt";
+    outfile = fopen("V0.txt", "w");
+
+    infile = fopen(ifilename, "rb");
+    if (!infile) {
+        printf("Can't open %s\n", ifilename);
+        exit(1);
+    }
+    while (NULL != fgets(line, 512, infile)) {
+        lineNo += 1;
+        if (0 == mungeLine(line, lineNo, outfile))
+            printf("Bad line at %d",lineNo);
+    }
+    fclose(infile);
+
+    fprintf(outfile, "File:     %s\n", ifilename);
+    fprintf(outfile, "Total:    %.3f\n", hrsTot);
+    fprintf(outfile, "Readings: %d\n", rdgsTot);
+    fprintf(outfile, "Average:  %.3f\n", hrsTot/rdgsTot);
+    fprintf(outfile, "\nMaximum number of consecutive bad readings is %d\n", maxBadHrs);
+    fprintf(outfile, "Ends on date %s\n", bhEndDate);
+    fclose(outfile);
+    return 0;
+}
--- a/Task/Text-processing-1/Common-Lisp/text-processing-1.lisp
+++ b/Task/Text-processing-1/Common-Lisp/text-processing-1.lisp
@ -0,0 +1,101 @@
+(defstruct (measurement
+	     (:conc-name "MEASUREMENT-")
+	     (:constructor make-measurement (counter line date flag value)))
+  (counter 0 :type (integer 0))
+  (line 0 :type (integer 0))
+  (date nil :type symbol)
+  (flag 0 :type integer)
+  (value 0 :type real))
+
+(defun measurement-valid-p (m)
+  (> (measurement-flag m) 0))
+
+(defun map-data-stream (function stream)
+  (flet ((scan (&optional (errorp t)) (read stream errorp nil)))
+    (loop
+       :with global-count = 0
+       :for date = (scan nil) :then (scan nil)
+       :for line-number :upfrom 1
+       :while date
+       :do (loop
+	      :for count :upfrom 0 :below 24
+	      :do (let* ((value (scan)) (flag (scan)))
+		    (funcall function (make-measurement global-count line-number date flag value))
+		    (incf global-count)))
+       :finally (return global-count))))
+
+(defun map-data-file (function pathname)
+  (with-open-file (stream pathname
+			  :element-type 'character
+			  :direction :input
+			  :if-does-not-exist :error)
+    (map-data-stream function stream)))
+
+(defmacro do-data-stream ((variable stream) &body body)
+  `(map-data-stream
+     (lambda (,variable) ,@body)
+     ,stream))
+
+(defmacro do-data-file ((variable file) &body body)
+  `(map-data-file
+     (lambda (,variable) ,@body)
+     ,file))
+
+(let ((current-day nil)
+      (current-line 0)
+      (beginning-of-misreadings nil)
+      (current-length 0)
+      (worst-beginning nil)
+      (worst-length 0)
+      (sum-of-day 0)
+      (count-of-day 0))
+
+  (flet ((write-end-of-day-report ()
+	   (when current-day
+	     (format t "Line ~5D Date ~A: Accepted ~2D Total ~8,3F Average ~8,3F~%"
+		     current-line current-day count-of-day sum-of-day
+		     (if (> count-of-day 0) (/ sum-of-day count-of-day) sum-of-day)))))
+
+    (do-data-file (m #P"D:/Scratch/data.txt")
+
+      (let* ((date (measurement-date m))
+	     (line-number (measurement-line m))
+	     (validp (measurement-valid-p m))
+	     (day-changed-p (/= current-line line-number))
+	     (value (measurement-value m)))
+
+	(when day-changed-p
+	  (write-end-of-day-report)
+	  (setf current-day date)
+	  (setf current-line line-number)
+	  (setf sum-of-day 0)
+	  (setf count-of-day 0))
+
+	(if (not validp)
+	    (if beginning-of-misreadings
+		(incf current-length)
+		(progn
+		  (setf beginning-of-misreadings m)
+		  (setf current-length 1)))
+	    (progn
+	      (when beginning-of-misreadings
+		(if (> current-length worst-length)
+		    (progn
+		      (setf worst-beginning beginning-of-misreadings)
+		      (setf worst-length current-length))
+		    (progn
+		      (setf beginning-of-misreadings nil)
+		      (setf current-length 0))))
+	      (incf sum-of-day value)
+	      (incf count-of-day)))))
+
+    (when (and beginning-of-misreadings (> current-length worst-length))
+      (setf worst-beginning beginning-of-misreadings)
+      (setf worst-length current-length))
+
+    (write-end-of-day-report))
+
+  (format t "Worst run started ~A (~D) and has length ~D~%"
+	  (measurement-date worst-beginning)
+	  (measurement-counter worst-beginning)
+	  worst-length))
--- a/Task/Text-processing-1/D/text-processing-1.d
+++ b/Task/Text-processing-1/D/text-processing-1.d
@ -0,0 +1,75 @@
+import std.stdio, std.conv, std.string;
+
+void main(string[] args) {
+    /*const*/ auto fileNames = (args.length == 1) ? ["readings.txt"] :
+                                                    args[1 .. $];
+
+    int noData, noDataMax = -1;
+    string[] noDataMaxLine;
+
+    double fileTotal = 0.0;
+    int fileValues;
+
+    foreach (fileName; fileNames) {
+        foreach (char[] line; File(fileName).byLine()) {
+            double lineTotal = 0.0;
+            int lineValues;
+
+            // Extract field info
+            const parts = line.split();
+            const date = parts[0];
+            const fields = parts[1 .. $];
+            assert(fields.length % 2 == 0,
+                   format("Expected even number of fields, not %d.",
+                          fields.length));
+
+            for (int i; i < fields.length; i += 2) {
+                immutable value = to!double(fields[i]);
+                immutable flag = to!int(fields[i + 1]);
+
+                if (flag < 1) {
+                    noData++;
+                    continue;
+                }
+
+                // Check run of data-absent fields
+                if (noDataMax == noData && noData > 0)
+                    noDataMaxLine ~= date.idup;
+
+                if (noDataMax < noData && noData > 0) {
+                    noDataMax = noData;
+                    noDataMaxLine.length = 1;
+                    noDataMaxLine[0] = date.idup;
+                }
+
+                // Re-initialise run of noData counter
+                noData = 0;
+
+                // Gather values for averaging
+                lineTotal += value;
+                lineValues++;
+            }
+
+            // Totals for the file so far
+            fileTotal += lineTotal;
+            fileValues += lineValues;
+
+            writefln("Line: %11s  Reject: %2d  Accept: %2d" ~
+                     "  Line_tot: %10.3f  Line_avg: %10.3f",
+                     date,
+                     fields.length / 2 - lineValues,
+                     lineValues,
+                     lineTotal,
+                     (lineValues > 0) ? lineTotal / lineValues : 0.0);
+        }
+    }
+
+    writeln("\nFile(s)  = ", fileNames.join(", "));
+    writefln("Total    = %10.3f", fileTotal);
+    writefln("Readings = %6d", fileValues);
+    writefln("Average  = %10.3f", fileTotal / fileValues);
+
+    writefln("\nMaximum run(s) of %d consecutive false " ~
+             "readings ends at line starting with date(s): %s",
+             noDataMax, join(noDataMaxLine, ", "));
+}
--- a/Task/Text-processing-1/Forth/text-processing-1.fth
+++ b/Task/Text-processing-1/Forth/text-processing-1.fth
@ -0,0 +1,93 @@
+\ data munging
+
+\ 1991-03-30[\t10.000\t[-]1]*24
+
+\ 1. mean of valid (flag > 0) values per day and overall
+\ 2. length of longest run of invalid values, and when it happened
+
+fvariable day-sum
+variable day-n
+
+fvariable total-sum
+variable total-n
+
+10 constant date-size    \ yyyy-mm-dd
+create cur-date date-size allot
+
+create bad-date date-size allot
+variable bad-n
+
+create worst-date date-size allot
+variable worst-n
+
+: split ( buf len char -- buf' l2  buf l1 )  \ where buf'[0] = char, l1 = len-l2
+  >r 2dup r> scan
+  2swap 2 pick - ;
+
+: next-sample ( buf len -- buf' len' fvalue flag )
+  #tab split >float   drop    1 /string
+  #tab split snumber? drop >r 1 /string r> ;
+
+: ok?  0> ;
+
+: add-sample ( value -- )
+  day-sum f@ f+ day-sum f!
+  1 day-n +! ;
+
+: add-day
+  day-sum f@ total-sum f@ f+ total-sum f!
+  day-n @ total-n +! ;
+
+: add-bad-run
+  bad-n @ 0= if
+    cur-date bad-date date-size move
+  then
+  1 bad-n +! ;
+
+: check-worst-run
+  bad-n @ worst-n @ > if
+    bad-n @ worst-n !
+    bad-date worst-date date-size move
+  then
+  0 bad-n ! ;
+
+: hour ( buf len -- buf' len' )
+  next-sample ok? if
+    add-sample
+    check-worst-run
+  else
+    fdrop
+    add-bad-run
+  then ;
+
+: .mean ( sum count -- ) 0 d>f f/ f. ;
+
+: day ( line len -- )
+  2dup + #tab swap c! 1+			\ append tab for parsing
+  #tab split cur-date swap move 1 /string	\ skip date
+  0e day-sum f!
+  0  day-n !
+  24 0 do hour loop 2drop
+  cur-date date-size type ."  mean = "
+  day-sum f@ day-n @ .mean cr
+  add-day ;
+
+stdin value input
+
+: main
+  s" input.txt" r/o open-file throw to input
+  0e total-sum f!
+  0 total-n !
+  0 worst-n !
+  begin  pad 512 input read-line throw
+  while  pad swap day
+  repeat
+  input close-file throw
+  worst-n @ if
+    ."  Longest interruption: " worst-n @ .
+    ." hours starting " worst-date date-size type cr
+  then
+  ."  Total mean = "
+  total-sum f@ total-n @ .mean cr ;
+
+main bye
--- a/Task/Text-processing-1/Go/text-processing-1.go
+++ b/Task/Text-processing-1/Go/text-processing-1.go
@ -0,0 +1,101 @@
+package main
+
+import (
+    "bufio"
+    "fmt"
+    "io"
+    "os"
+    "strconv"
+    "strings"
+)
+
+var fn = "readings.txt"
+
+func main() {
+    f, err := os.Open(fn)
+    if err != nil {
+        fmt.Println(err)
+        return
+    }
+    defer f.Close()
+    var (
+        badRun, maxRun   int
+        badDate, maxDate string
+        fileSum          float64
+        fileAccept       int
+    )
+    for lr := bufio.NewReader(f); ; {
+        line, pref, err := lr.ReadLine()
+        if err == io.EOF {
+            break
+        }
+        if err != nil {
+            fmt.Println(err)
+            return
+        }
+        if pref {
+            fmt.Println("Unexpected long line.")
+            return
+        }
+        f := strings.Fields(string(line))
+        if len(f) != 49 {
+            fmt.Println("unexpected format,", len(f), "fields.")
+            return
+        }
+        var accept int
+        var sum float64
+        for i := 1; i < 49; i += 2 {
+            flag, err := strconv.Atoi(f[i+1])
+            if err != nil {
+                fmt.Println(err)
+                return
+            }
+            if flag > 0 { // value is good
+                if badRun > 0 { // terminate bad run
+                    if badRun > maxRun {
+                        maxRun = badRun
+                        maxDate = badDate
+                    }
+                    badRun = 0
+                }
+                value, err := strconv.ParseFloat(f[i], 64)
+                if err != nil {
+                    fmt.Println(err)
+                    return
+                }
+                sum += value
+                accept++
+            } else { // value is bad
+                if badRun == 0 {
+                    badDate = f[0]
+                }
+                badRun++
+            }
+        }
+        fmt.Printf("Line: %s  Reject %2d  Accept: %2d  Line_tot:%9.3f",
+            f[0], 24-accept, accept, sum)
+        if accept > 0 {
+            fmt.Printf("  Line_avg:%8.3f\n", sum/float64(accept))
+        } else {
+            fmt.Println("")
+        }
+        fileSum += sum
+        fileAccept += accept
+    }
+    fmt.Println("\nFile     =", fn)
+    fmt.Printf("Total    = %.3f\n", fileSum)
+    fmt.Println("Readings = ", fileAccept)
+    if fileAccept > 0 {
+        fmt.Printf("Average  =  %.3f\n", fileSum/float64(fileAccept))
+    }
+    if badRun > 0 && badRun > maxRun {
+        maxRun = badRun
+        maxDate = badDate
+    }
+    if maxRun == 0 {
+        fmt.Println("\nAll data valid.")
+    } else {
+        fmt.Printf("\nMax data gap = %d, beginning on line %s.\n",
+            maxRun, maxDate)
+    }
+}
--- a/Task/Text-processing-1/Haskell/text-processing-1-1.hs
+++ b/Task/Text-processing-1/Haskell/text-processing-1-1.hs
@ -0,0 +1,47 @@
+import Data.List
+import Numeric
+import Control.Arrow
+import Control.Monad
+import Text.Printf
+import System.Environment
+import Data.Function
+
+type Date = String
+type Value = Double
+type Flag = Bool
+
+readFlg :: String -> Flag
+readFlg = (> 0).read
+
+readNum :: String -> Value
+readNum = fst.head.readFloat
+
+take2 = takeWhile(not.null).unfoldr (Just.splitAt 2)
+
+parseData :: [String] -> (Date,[(Value,Flag)])
+parseData = head &&& map(readNum.head &&& readFlg.last).take2.tail
+
+sumAccs :: (Date,[(Value,Flag)]) -> (Date, ((Value,Int),[Flag]))
+sumAccs = second (((sum &&& length).concat.uncurry(zipWith(\v f -> [v|f])) &&& snd).unzip)
+
+maxNAseq :: [Flag] -> [(Int,Int)]
+maxNAseq = head.groupBy((==) `on` fst).sortBy(flip compare)
+           . concat.uncurry(zipWith(\i (r,b)->[(r,i)|not b]))
+           . first(init.scanl(+)0). unzip
+           . map ((fst &&& id).(length &&& head)). group
+
+main = do
+    file:_ <- getArgs
+    f <- readFile file
+    let dat :: [(Date,((Value,Int),[Flag]))]
+        dat      = map (sumAccs. parseData. words).lines $ f
+        summ     = ((sum *** sum). unzip *** maxNAseq.concat). unzip $ map snd dat
+        totalFmt = "\nSummary\t\t accept: %d\t total: %.3f \taverage: %6.3f\n\n"
+        lineFmt  = "%8s\t accept: %2d\t total: %11.3f \taverage: %6.3f\n"
+        maxFmt   =  "Maximum of %d consecutive false readings, starting on line /%s/ and ending on line /%s/\n"
+-- output statistics
+    putStrLn "\nSome lines:\n"
+    mapM_ (\(d,((v,n),_)) -> printf lineFmt d n v (v/fromIntegral n)) $ take 4 $ drop 2200 dat
+    (\(t,n) -> printf totalFmt  n t (t/fromIntegral n)) $ fst summ
+    mapM_ ((\(l, d1,d2) -> printf maxFmt l d1 d2)
+              . (\(a,b)-> (a,(fst.(dat!!).(`div`24))b,(fst.(dat!!).(`div`24))(a+b)))) $ snd summ
--- a/Task/Text-processing-1/Haskell/text-processing-1-2.hs
+++ b/Task/Text-processing-1/Haskell/text-processing-1-2.hs
@ -0,0 +1 @@
+*Main> :main ["./RC/readings.txt"]
--- a/Task/Text-processing-1/Icon/text-processing-1.icon
+++ b/Task/Text-processing-1/Icon/text-processing-1.icon
@ -0,0 +1,51 @@
+record badrun(count,fromdate,todate)  # record to track bad runs
+
+procedure main()
+return mungetask1("readings1-input.txt","readings1-output.txt")
+end
+
+procedure mungetask1(fin,fout)
+
+fin  := open(fin)      | stop("Unable to open input file ",fin)
+fout := open(fout,"w") | stop("Unable to open output file ",fout)
+
+F_tot := F_acc := F_rej := 0                       # data set totals
+rejmax := badrun(-1)                               # longest reject runs
+rejcur := badrun(0)                                # current reject runs
+
+while line := read(fin) do {
+   line ? {
+      ldate := tab(many(&digits ++ '-'))           # date (poorly checked)
+      fields := tot := rej := 0                    # record counters & totals
+
+      while tab(many(' \t')) do {                  # whitespace before every pair
+         value := real(tab(many(&digits++'-.')))   | stop("Bad value in ",ldate)
+         tab(many(' \t'))
+         flag := integer(tab(many(&digits++'-')))  | stop("Bad flag in ",ldate)
+         fields +:= 1
+
+         if flag > 0 then {                        # good data, ends a bad run
+            if rejcur.count > rejmax.count then rejmax := rejcur
+            rejcur := badrun(0)
+            tot +:= value
+            }
+         else {                                    # bad (flagged) data
+            if rejcur.count = 0 then rejcur.fromdate := ldate
+            rejcur.todate := ldate
+            rejcur.count +:= 1
+            rej +:= 1
+            }
+         }
+      }
+   F_tot +:= tot
+   F_acc +:= acc := fields - rej
+   F_rej +:= rej
+   write(fout,"Line: ",ldate," Reject: ", rej," Accept: ", acc," Line_tot: ",tot," Line_avg: ", if acc > 0 then tot / acc else 0)
+   }
+
+write(fout,"\nTotal    = ",F_tot,"\nReadings = ",F_acc,"\nRejects  = ",F_rej,"\nAverage  = ",F_tot / F_acc)
+if rejmax.count > 0 then
+   write(fout,"Maximum run of bad data was ",rejmax.count," readings from ",rejmax.fromdate," to ",rejmax.todate)
+else
+   write(fout,"No bad runs of data")
+end
--- a/Task/Text-processing-1/J/text-processing-1-1.j
+++ b/Task/Text-processing-1/J/text-processing-1-1.j
@ -0,0 +1,14 @@
+  load 'files'
+  parseLine=: 10&({. ,&< (_99&".;._1)@:}.)  NB. custom parser
+  summarize=: # , +/ , +/ % #               NB. count,sum,mean
+  filter=: #~ 0&<                           NB. keep valid measurements
+
+  'Dates dat'=: |: parseLine;._2 CR -.~ fread jpath '~temp/readings.txt'
+  Vals=:  (+: i.24){"1 dat
+  Flags=: (>: +: i.24){"1 dat
+  DailySummary=: Vals summarize@filter"1 Flags
+  RunLengths=: ([: #(;.1) 0 , }. *. }:) , 0 >: Flags
+   ]MaxRun=: >./ RunLengths
+589
+   ]StartDates=: Dates {~ (>:@I.@e.&MaxRun (24 <.@%~ +/)@{. ]) RunLengths
+1993-03-05
--- a/Task/Text-processing-1/J/text-processing-1-2.j
+++ b/Task/Text-processing-1/J/text-processing-1-2.j
@ -0,0 +1,11 @@
+formatDailySumry=: dyad define
+  labels=. , ];.2 'Line: Accept: Line_tot: Line_avg: '
+  labels , x ,. 7j0 10j3 10j3 ": y
+)
+formatFileSumry=: dyad define
+  labels=. ];.2 'Total: Readings: Average: '
+  sumryvals=. (, %/) 1 0{ +/y
+  out=. labels ,. 12j3 12j0 12j3 ":&> sumryvals
+  'maxrun dates'=. x
+  out=. out,LF,'Maximum run(s) of ',(": maxrun),' consecutive false readings ends at line(s) starting with date(s): ',dates
+)
--- a/Task/Text-processing-1/J/text-processing-1-3.j
+++ b/Task/Text-processing-1/J/text-processing-1-3.j
@ -0,0 +1,13 @@
+   (_4{.Dates) formatDailySumry _4{. DailySummary
+Line:     Accept:   Line_tot: Line_avg:
+2004-12-28     23    77.800     3.383
+2004-12-29     23    56.300     2.448
+2004-12-30     23    65.300     2.839
+2004-12-31     23    47.300     2.057
+
+   (MaxRun;StartDates) formatFileSumry DailySummary
+Total:     1358393.400
+Readings:       129403
+Average:        10.497
+
+Maximum run(s) of 589 consecutive false readings ends at line(s) starting with date(s): 1993-03-05
--- a/Task/Text-processing-1/JavaScript/text-processing-1.js
+++ b/Task/Text-processing-1/JavaScript/text-processing-1.js
@ -0,0 +1,69 @@
+var filename = 'readings.txt';
+var show_lines = 5;
+var file_stats = {
+    'num_readings': 0,
+    'total': 0,
+    'reject_run': 0,
+    'reject_run_max': 0,
+    'reject_run_date': ''
+};
+
+var fh = new ActiveXObject("Scripting.FileSystemObject").openTextFile(filename, 1); // 1 = for reading
+while ( ! fh.atEndOfStream) {
+    var line = fh.ReadLine();
+    line_stats(line, (show_lines-- > 0));
+}
+fh.close();
+
+WScript.echo(
+    "\nFile(s)  = " + filename + "\n" +
+    "Total    = " + dec3(file_stats.total) + "\n" +
+    "Readings = " + file_stats.num_readings + "\n" +
+    "Average  = " + dec3(file_stats.total / file_stats.num_readings) + "\n\n" +
+    "Maximum run of " + file_stats.reject_run_max +
+    " consecutive false readings ends at " + file_stats.reject_run_date
+);
+
+function line_stats(line, print_line) {
+    var readings = 0;
+    var rejects = 0;
+    var total = 0;
+    var fields = line.split('\t');
+    var date = fields.shift();
+
+    while (fields.length > 0) {
+        var value = parseFloat(fields.shift());
+        var flag = parseInt(fields.shift(), 10);
+        readings++;
+        if (flag <= 0) {
+            rejects++;
+            file_stats.reject_run++;
+        }
+        else {
+            total += value;
+            if (file_stats.reject_run > file_stats.reject_run_max) {
+                file_stats.reject_run_max = file_stats.reject_run;
+                file_stats.reject_run_date = date;
+            }
+            file_stats.reject_run = 0;
+        }
+    }
+
+    file_stats.num_readings += readings - rejects;
+    file_stats.total += total;
+
+    if (print_line) {
+        WScript.echo(
+            "Line: " + date + "\t" +
+            "Reject: " + rejects + "\t" +
+            "Accept: " + (readings - rejects) + "\t" +
+            "Line_tot: " + dec3(total) + "\t" +
+            "Line_avg: " + ((readings == rejects) ? "0.0" : dec3(total / (readings - rejects)))
+        );
+    }
+}
+
+// round a number to 3 decimal places
+function dec3(value) {
+    return Math.round(value * 1e3) / 1e3;
+}
--- a/Task/Text-processing-1/Lua/text-processing-1.lua
+++ b/Task/Text-processing-1/Lua/text-processing-1.lua
@ -0,0 +1,49 @@
+filename = "readings.txt"
+io.input( filename )
+
+file_sum, file_cnt_data, file_lines = 0, 0, 0
+max_rejected, n_rejected = 0, 0
+max_rejected_date, rejected_date = "", ""
+
+while true do
+    data = io.read("*line")
+    if data == nil then break end
+
+    date = string.match( data, "%d+%-%d+%-%d+" )
+    if date == nil then break end
+	
+    val = {}
+    for w in string.gmatch( data, "%s%-*%d+[%.%d]*" ) do
+        val[#val+1] = tonumber(w)
+    end
+
+    sum, cnt = 0, 0
+    for i = 1, #val, 2 do
+    	if val[i+1] > 0 then
+    	    sum = sum + val[i]
+    	    cnt = cnt + 1
+    	    n_rejected = 0
+    	else
+	    if n_rejected == 0 then
+	        rejected_date = date
+  	    end
+    	    n_rejected = n_rejected + 1
+    	    if n_rejected > max_rejected then
+    	        max_rejected = n_rejected
+    	        max_rejected_date = rejected_date
+    	    end
+    	end
+    end
+
+    file_sum = file_sum + sum
+    file_cnt_data = file_cnt_data + cnt
+    file_lines = file_lines + 1
+
+    print( string.format( "%s:\tRejected: %d\tAccepted: %d\tLine_total: %f\tLine_average: %f", date, #val/2-cnt, cnt, sum, sum/cnt ) )
+end
+
+print( string.format( "\nFile:\t  %s", filename ) )
+print( string.format( "Total:\t  %f", file_sum ) )
+print( string.format( "Readings: %d", file_lines ) )
+print( string.format( "Average:  %f", file_sum/file_cnt_data ) )
+print( string.format( "Maximum %d consecutive false readings starting at %s.", max_rejected, max_rejected_date ) )
--- a/Task/Text-processing-1/Mathematica/text-processing-1.math
+++ b/Task/Text-processing-1/Mathematica/text-processing-1.math
@ -0,0 +1,16 @@
+FileName = "Readings.txt"; data = Import[FileName,"TSV"];
+
+Scan[(a=Position[#[[3;;All;;2]],1];
+Print["Line:",#[[1]] ,"\tReject:", 24 - Length[a], "\t Accept:", Length[a], "\tLine_tot:",
+Total@Part[#, Flatten[2*a]] , "\tLine_avg:", Total@Part[#, Flatten[2*a]]/Length[a]])&, data]
+
+GlobalSum = Nb = Running = MaxRunRecorded =  0; MaxRunTime = {};
+Scan[ For[i = 3, i < 50, i = i + 2,
+   If[#[[i]] == 1,
+    Running=0; GlobalSum += #[[i-1]]; Nb++;,
+    Running ++;  If[MaxRunRecorded < Running, MaxRunRecorded = Running;MaxRunTime={ #[[1]]}; ];
+   ]] &, data ]
+
+Print["\nFile(s) : ",FileName,"\nTotal : ",AccountingForm@GlobalSum,"\nReadings : ",Nb,
+"\nAverage : ",GlobalSum/Nb,"\n\nMaximum run(s) of ",MaxRunRecorded,
+" consecutive false readings ends at line starting with date(s):",MaxRunTime]
--- a/Task/Text-processing-1/OCaml/text-processing-1.ocaml
+++ b/Task/Text-processing-1/OCaml/text-processing-1.ocaml
@ -0,0 +1,67 @@
+let input_line ic =
+  try Some(input_line ic)
+  with End_of_file -> None
+
+let fold_input f ini ic =
+  let rec fold ac =
+    match input_line ic with
+    | Some line -> fold (f ac line)
+    | None -> ac
+  in
+  fold ini
+
+let ic = open_in "readings.txt"
+
+let scan line =
+  Scanf.sscanf line "%s\
+    \t%f\t%d\t%f\t%d\t%f\t%d\t%f\t%d\t%f\t%d\t%f\t%d\
+    \t%f\t%d\t%f\t%d\t%f\t%d\t%f\t%d\t%f\t%d\t%f\t%d\
+    \t%f\t%d\t%f\t%d\t%f\t%d\t%f\t%d\t%f\t%d\t%f\t%d\
+    \t%f\t%d\t%f\t%d\t%f\t%d\t%f\t%d\t%f\t%d\t%f\t%d"
+    (fun date
+         v1  f1  v2  f2  v3  f3  v4  f4  v5  f5  v6  f6
+         v7  f7  v8  f8  v9  f9  v10 f10 v11 f11 v12 f12
+         v13 f13 v14 f14 v15 f15 v16 f16 v17 f17 v18 f18
+         v19 f19 v20 f20 v21 f21 v22 f22 v23 f23 v24 f24 ->
+      (date),
+      [ (v1,  f1 ); (v2,  f2 ); (v3,  f3 ); (v4,  f4 ); (v5,  f5 ); (v6,  f6 );
+        (v7,  f7 ); (v8,  f8 ); (v9,  f9 ); (v10, f10); (v11, f11); (v12, f12);
+        (v13, f13); (v14, f14); (v15, f15); (v16, f16); (v17, f17); (v18, f18);
+        (v19, f19); (v20, f20); (v21, f21); (v22, f22); (v23, f23); (v24, f24); ])
+
+let tot_file, num_file, _, nodata_max, nodata_maxline =
+  fold_input
+    (fun (tot_file, num_file, nodata, nodata_max, nodata_maxline) line ->
+       let date, datas = scan line in
+       let _datas = List.filter (fun (_, flag) -> flag > 0) datas in
+       let ok = List.length _datas in
+       let tot = List.fold_left (fun ac (value, _) -> ac +. value) 0.0 _datas in
+       let nodata, nodata_max, nodata_maxline =
+         List.fold_left
+             (fun (nodata, nodata_max, nodata_maxline) (_, flag) ->
+                if flag <= 0
+                then (succ nodata, nodata_max, nodata_maxline)
+                else
+                  if nodata_max = nodata && nodata > 0
+                  then (0, nodata_max, date::nodata_maxline)
+                  else if nodata_max < nodata && nodata > 0
+                  then (0, nodata, [date])
+                  else (0, nodata_max, nodata_maxline)
+             )
+             (nodata, nodata_max, nodata_maxline) datas in
+       Printf.printf "Line: %s" date;
+       Printf.printf "  Reject: %2d  Accept: %2d" (24 - ok) ok;
+       Printf.printf "\tLine_tot: %8.3f" tot;
+       Printf.printf "\tLine_avg: %8.3f\n" (tot /. float ok);
+       (tot_file +. tot, num_file + ok, nodata, nodata_max, nodata_maxline))
+    (0.0, 0, 0, 0, [])
+    ic ;;
+
+close_in ic ;;
+
+Printf.printf "Total    = %f\n" tot_file;
+Printf.printf "Readings = %d\n" num_file;
+Printf.printf "Average  = %f\n" (tot_file /. float num_file);
+Printf.printf "Maximum run(s) of %d consecutive false readings \
+               ends at line starting with date(s): %s\n"
+               nodata_max (String.concat ", " nodata_maxline);
--- a/Task/Text-processing-1/PL-I/text-processing-1.pli
+++ b/Task/Text-processing-1/PL-I/text-processing-1.pli
@ -0,0 +1,54 @@
+text1: procedure options (main); /* 13 May 2010 */
+
+   declare line character (2000) varying;
+   declare 1 pairs(24),
+               2 value fixed (10,4),
+               2 flag  fixed;
+   declare date character (12) varying;
+   declare no_items fixed decimal (10);
+   declare (nv, sum, line_no, ndud_values, max_ndud_values) fixed;
+   declare (i, k) fixed binary;
+   declare in file input;
+
+   open file (in) title ('/TEXT1.DAT,TYPE(TEXT),RECSIZE(2000)' );
+
+   on endfile (in) go to finish_up;
+
+   line_no = 0;
+loop:
+   do forever;
+      get file (in) edit (line) (L);
+      /* put skip list (line); */
+      line = translate(line, ' ', '09'x);
+      line_no = line_no + 1;
+      line = trim(line);
+      no_items = tally(line, ' ') - tally(line, '  ') + 1;
+      if no_items ^= 49 then
+         do; put skip list ('There are not 49 items on this line'); iterate loop; end;
+      k = index(line, ' '); /* Find the first blank in the line. */
+      date = substr(line, 1, k);
+      line = substr(line, k) || ' ';
+      on conversion go to loop;
+      get string (line) list (pairs);
+      sum, nv, ndud_values, max_ndud_values = 0;
+      do i = 1 to 24;
+         if flag(i) > 0 then
+            do; sum = sum + value(i); nv = nv + 1;
+            ndud_values = 0; /* reset the counter of dud values */
+            end;
+         else
+            do; /* we have a dud reading. */
+                ndud_values = ndud_values + 1;
+                if ndud_values > max_ndud_values then
+                  max_ndud_values = ndud_values;
+            end;
+      end;
+      if nv = 0 then iterate;
+      put skip list ('Line ' || trim(line_no) || ' average=', divide(sum, nv, 10,4) );
+      if max_ndud_values > 0 then
+         put skip list ('Maximum run of dud readings =', max_ndud_values);
+   end;
+
+finish_up:
+
+end text1;
--- a/Task/Text-processing-1/Perl-6/text-processing-1.pl6
+++ b/Task/Text-processing-1/Perl-6/text-processing-1.pl6
@ -0,0 +1,33 @@
+my @gaps;
+my $previous = 'valid';
+
+for $*IN.lines -> $line {
+    my ($date, @readings) = split /\s+/, $line;
+    my @valid;
+    my $hour = 0;
+    for @readings -> $reading, $flag {
+        if $flag > 0 {
+            @valid.push($reading);
+            if $previous eq 'invalid' {
+                @gaps[*-1]{'end'} = "$date $hour:00";
+                $previous = 'valid';
+            }
+        }
+        else
+        {
+            if $previous eq 'valid' {
+                @gaps.push( {start => "$date $hour:00"} );
+            }
+            @gaps[*-1]{'count'}++;
+            $previous = 'invalid';
+        }
+        $hour++;
+    }
+    say "$date: { ( +@valid ?? ( ( [+] @valid ) / +@valid ).fmt("%.3f") !! 0 ).fmt("%8s") }",
+        " mean from { (+@valid).fmt("%2s") } valid.";
+};
+
+my $longest = @gaps.sort({-$^a<count>})[0];
+
+say "Longest period of invalid readings was {$longest<count>} hours,\n",
+    "from {$longest<start>} till {$longest<end>}."
--- a/Task/Text-processing-1/Perl/text-processing-1-1.pl
+++ b/Task/Text-processing-1/Perl/text-processing-1-1.pl
@ -0,0 +1,59 @@
+use strict;
+use warnings;
+
+my $nodata = 0;               # Current run of consecutive flags<0 in lines of file
+my $nodata_max = -1;          # Max consecutive flags<0 in lines of file
+my $nodata_maxline = "!";     # ... and line number(s) where it occurs
+
+my $infiles = join ", ", @ARGV;
+
+my $tot_file = 0;
+my $num_file = 0;
+
+while (<>) {
+  chomp;
+  my $tot_line = 0;             # sum of line data
+  my $num_line = 0;             # number of line data items with flag>0
+  my $rejects  = 0;
+
+  # extract field info, skipping initial date field
+  my ($date, @fields) = split;
+  while (@fields and my ($datum, $flag) = splice @fields, 0, 2) {
+    if ($flag+1 < 2) {
+      $nodata++;
+      $rejects++;
+      next;
+    }
+
+    # check run of data-absent fields
+    if($nodata_max == $nodata and $nodata > 0){
+      $nodata_maxline = "$nodata_maxline, $date";
+    }
+    if($nodata_max < $nodata and $nodata > 0){
+      $nodata_max = $nodata;
+      $nodata_maxline = $date;
+    }
+    # re-initialise run of nodata counter
+    $nodata = 0;
+    # gather values for averaging
+    $tot_line += $datum;
+    $num_line++;
+  }
+
+  # totals for the file so far
+  $tot_file += $tot_line;
+  $num_file += $num_line;
+
+  printf "Line: %11s  Reject: %2i  Accept: %2i  Line_tot: %10.3f  Line_avg: %10.3f\n",
+         $date, $rejects, $num_line, $tot_line, ($num_line>0)? $tot_line/$num_line: 0;
+
+}
+
+printf "\n";
+printf "File(s)  = %s\n", $infiles;
+printf "Total    = %10.3f\n", $tot_file;
+printf "Readings = %6i\n", $num_file;
+printf "Average  = %10.3f\n", $tot_file / $num_file;
+
+printf "\nMaximum run(s) of %i consecutive false readings ends at line starting with date(s): %s\n",
+       $nodata_max, $nodata_maxline;
--- a/Task/Text-processing-1/Perl/text-processing-1-2.pl
+++ b/Task/Text-processing-1/Perl/text-processing-1-2.pl
@ -0,0 +1,115 @@
+use strict;
+use warnings;
+
+use constant RESULT_TEMPLATE => "%-19s = %12.3f / %-6u = %.3f\n";
+
+my $parser = Parser->new;
+
+# parse lines and print results
+printf RESULT_TEMPLATE, $parser->parse(split)
+    while <>;
+
+$parser->finish;
+
+# print total and summary
+printf "\n".RESULT_TEMPLATE."\n", $parser->result;
+printf "the maximum of %u consecutive bad values was reached %u time(s)\n",
+    $parser->bad_max, scalar $parser->bad_ranges;
+
+# print bad ranges
+print for map { '  '.join(' - ', @$_)."\n" } $parser->bad_ranges;
+
+BEGIN {
+    package main::Parser;
+
+    sub new {
+        my $obj = {
+            SUM => 0,
+            COUNT => 0,
+            CURRENT_DATE => undef,
+            BAD_DATE => undef,
+            BAD_RANGES => [],
+            BAD_MAX => 0,
+            BAD_COUNT => 0
+        };
+
+        return bless $obj;
+    }
+
+    sub _average {
+        my ($sum, $count) = @_;
+        return ($sum, $count, $count && $sum / $count);
+    }
+
+    sub _push_bad_range_if_necessary {
+        my ($parser) = @_;
+        my ($count, $max) = @$parser{qw(BAD_COUNT BAD_MAX)};
+
+        return if $count < $max;
+
+        if ($count > $max) {
+            $parser->{BAD_RANGES} = [];
+            $parser->{BAD_MAX} = $count;
+        }
+
+        push @{$parser->{BAD_RANGES}}, [ @$parser{qw(BAD_DATE CURRENT_DATE)} ];
+    }
+
+    sub _check {
+        my ($parser, $flag) = @_;
+        if ($flag <= 0) {
+            ++$parser->{BAD_COUNT};
+            $parser->{BAD_DATE} = $parser->{CURRENT_DATE}
+                unless defined $parser->{BAD_DATE};
+
+            return 0;
+        }
+        else {
+            $parser->_push_bad_range_if_necessary;
+            $parser->{BAD_COUNT} = 0;
+            $parser->{BAD_DATE} = undef;
+            return 1;
+        }
+    }
+
+    sub bad_max {
+        my ($parser) = @_;
+        return $parser->{BAD_MAX}
+    }
+
+    sub bad_ranges {
+        my ($parser) = @_;
+        return @{$parser->{BAD_RANGES}}
+    }
+
+    sub parse {
+        my $parser = shift;
+        my $date = shift;
+
+        $parser->{CURRENT_DATE} = $date;
+
+        my $sum = 0;
+        my $count = 0;
+
+        while (my ($value, $flag) = splice @_, 0, 2) {
+            next unless $parser->_check($flag);
+            $sum += $value;
+            ++$count;
+        }
+
+        $parser->{SUM} += $sum;
+        $parser->{COUNT} += $count;
+
+        return ("average($date)", _average($sum, $count));
+    }
+
+    sub result {
+        my ($parser) = @_;
+        return ('total-average', _average(@$parser{qw(SUM COUNT)}));
+    }
+
+    sub finish {
+        my ($parser) = @_;
+        $parser->_push_bad_range_if_necessary
+    }
+}
--- a/Task/Text-processing-1/PicoLisp/text-processing-1.l
+++ b/Task/Text-processing-1/PicoLisp/text-processing-1.l
@ -0,0 +1,43 @@
+#!/usr/bin/picolisp /usr/lib/picolisp/lib.l
+
+(let (NoData 0  NoDataMax -1  NoDataMaxline "!"  TotFile 0  NumFile 0)
+   (let InFiles
+      (glue ","
+         (mapcar
+            '((File)
+               (in File
+                  (while (split (line) "^I")
+                     (let (Len (length @)  Date (car @)  TotLine 0  NumLine 0)
+                        (for (L (cdr @)  L  (cddr L))
+                           (if (> 1 (format (cadr L)))
+                              (inc 'NoData)
+                              (when (gt0 NoData)
+                                 (when (= NoDataMax NoData)
+                                    (setq NoDataMaxline (pack NoDataMaxline ", " Date)) )
+                                 (when (> NoData NoDataMax)
+                                    (setq NoDataMax NoData  NoDataMaxline Date) ) )
+                              (zero NoData)
+                              (inc 'TotLine (format (car L) 3))
+                              (inc 'NumLine) ) )
+                        (inc 'TotFile TotLine)
+                        (inc 'NumFile NumLine)
+                        (tab (-7 -12 -7 3 -9 3 -11 11 -11 11)
+                           "Line:" Date
+                           "Reject:" (- (/ (dec Len) 2) NumLine)
+                           "  Accept:" NumLine
+                           "  Line_tot:" (format TotLine 3)
+                           "  Line_avg:"
+                           (and (gt0 NumLine) (format (*/ TotLine @) 3)) ) ) ) )
+               File )
+            (argv) ) )
+      (prinl)
+      (prinl "File(s)  = " InFiles)
+      (prinl "Total    = " (format TotFile 3))
+      (prinl "Readings = " NumFile)
+      (prinl "Average  = " (format (*/ TotFile NumFile) 3))
+      (prinl)
+      (prinl
+         "Maximum run(s) of " NoDataMax
+         " consecutive false readings ends at line starting with date(s): " NoDataMaxline ) ) )
+
+(bye)
--- a/Task/Text-processing-1/PureBasic/text-processing-1.purebasic
+++ b/Task/Text-processing-1/PureBasic/text-processing-1.purebasic
@ -0,0 +1,47 @@
+#TASK="Text processing/1"
+Define File$, InLine$, Part$, i, Out$, ErrEnds$, Errcnt, ErrMax
+Define lsum.d, tsum.d, rejects, val.d, readings
+
+File$=OpenFileRequester(#TASK,"readings.txt","",0)
+If OpenConsole() And ReadFile(0,File$)
+  While Not Eof(0)
+    InLine$=ReadString(0)
+    For i=1 To 1+2*24
+      Part$=StringField(InLine$,i,#TAB$)
+      If i=1        ; Date
+        Out$=Part$: lsum=0: rejects=0
+      ElseIf i%2=0  ; Recorded value
+        val=ValD(Part$)
+      Else          ; Status part
+        If Val(Part$)>0
+          Errcnt=0 : readings+1
+          lsum+val : tsum+val
+        Else
+          rejects+1: Errcnt+1
+          If Errcnt>ErrMax
+            ErrMax=Errcnt
+            ErrEnds$=Out$
+          EndIf
+        EndIf
+      EndIf
+    Next i
+    Out$+" Rejects: " + Str(rejects)
+    Out$+" Accepts: " + Str(24-rejects)
+    Out$+" Line_tot: "+ StrD(lsum,3)
+    If rejects<24
+      Out$+" Line_avg: "+StrD(lsum/(24-rejects),3)
+    Else
+      Out$+" Line_avg: N/A"
+    EndIf
+    PrintN("Line: "+Out$)
+  Wend
+  PrintN(#CRLF$+"File     = "+GetFilePart(File$))
+  PrintN("Total    = "+ StrD(tsum,3))
+  PrintN("Readings = "+ Str(readings))
+  PrintN("Average  = "+ StrD(tsum/readings,3))
+  Print(#CRLF$+"Maximum of "+Str(ErrMax))
+  PrintN(" consecutive false readings, ends at "+ErrEnds$)
+  CloseFile(0)
+  ;
+  Print("Press ENTER to exit"): Input()
+EndIf
--- a/Task/Text-processing-1/Python/text-processing-1.py
+++ b/Task/Text-processing-1/Python/text-processing-1.py
@ -0,0 +1,56 @@
+import fileinput
+import sys
+
+nodata = 0;             # Current run of consecutive flags<0 in lines of file
+nodata_max=-1;          # Max consecutive flags<0 in lines of file
+nodata_maxline=[];      # ... and line number(s) where it occurs
+
+tot_file = 0            # Sum of file data
+num_file = 0            # Number of file data items with flag>0
+
+infiles = sys.argv[1:]
+
+for line in fileinput.input():
+  tot_line=0;             # sum of line data
+  num_line=0;             # number of line data items with flag>0
+
+  # extract field info
+  field = line.split()
+  date  = field[0]
+  data  = [float(f) for f in field[1::2]]
+  flags = [int(f)   for f in field[2::2]]
+
+  for datum, flag in zip(data, flags):
+    if flag<1:
+      nodata += 1
+    else:
+      # check run of data-absent fields
+      if nodata_max==nodata and nodata>0:
+        nodata_maxline.append(date)
+      if nodata_max<nodata and nodata>0:
+        nodata_max=nodata
+        nodata_maxline=[date]
+      # re-initialise run of nodata counter
+      nodata=0;
+      # gather values for averaging
+      tot_line += datum
+      num_line += 1
+
+  # totals for the file so far
+  tot_file += tot_line
+  num_file += num_line
+
+  print "Line: %11s  Reject: %2i  Accept: %2i  Line_tot: %10.3f  Line_avg: %10.3f" % (
+        date,
+        len(data) -num_line,
+        num_line, tot_line,
+        tot_line/num_line if (num_line>0) else 0)
+
+print ""
+print "File(s)  = %s" % (", ".join(infiles),)
+print "Total    = %10.3f" % (tot_file,)
+print "Readings = %6i" % (num_file,)
+print "Average  = %10.3f" % (tot_file / num_file,)
+
+print "\nMaximum run(s) of %i consecutive false readings ends at line starting with date(s): %s" % (
+    nodata_max, ", ".join(nodata_maxline))
--- a/Task/Text-processing-1/R/text-processing-1.r
+++ b/Task/Text-processing-1/R/text-processing-1.r
@ -0,0 +1,9 @@
+#Read in data from file
+dfr <- read.delim("readings.txt")
+#Calculate daily means
+flags <- as.matrix(dfr[,seq(3,49,2)])>0
+vals <- as.matrix(dfr[,seq(2,49,2)])
+daily.means <- rowSums(ifelse(flags, vals, 0))/rowSums(flags)
+#Calculate time between good measurements
+times <- strptime(dfr[1,1], "%Y-%m-%d", tz="GMT") + 3600*seq(1,24*nrow(dfr),1)
+hours.between.good.measurements <- diff(times[t(flags)])/3600
--- a/Task/Text-processing-1/REXX/text-processing-1.rexx
+++ b/Task/Text-processing-1/REXX/text-processing-1.rexx
@ -0,0 +1,72 @@
+/*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.     */
+grandOKs=0
+longFlag=0                             /*longest period of flagged data.*/
+contFlag=0                             /*longest continous flagged data.*/
+w=16                                   /*width of fields when displayed.*/
+
+  do recs=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. */
+  sum=0
+  flg=0
+  OKs=0
+
+    do j=1  until Idata=''             /*process the instrument data.  */
+    parse var Idata data.j flag.j Idata
+
+    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
+    end   /*j*/
+
+  if OKs\==0 then avg=format(sum/OKs,,3)
+             else avg='[n/a]'
+  grandOKs=grandOKs+OKs
+  _=right(comma(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   /*recs*/
+
+recs=recs-1                            /*adjust for reading end-of-file.*/
+if grandOKs\==0 then Gavg=format(grandsum/grandOKs,,3)
+                else Gavg='[n/a]'
+call sy
+call sy copies('═',60)
+call sy '      records read:' right(comma(recs),w)
+call sy '     grand     sum:' right(comma(grandSum),w+4)
+call sy '     grand average:' right(comma(Gavg),w+4)
+call sy '     grand OK data:' right(comma(grandOKs),w)
+call sy '     grand flagged:' right(comma(grandFlg),w)
+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 done.*/
+/*──────────────────────────────────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 _
--- a/Task/Text-processing-1/Racket/text-processing-1.rkt
+++ b/Task/Text-processing-1/Racket/text-processing-1.rkt
@ -0,0 +1,54 @@
+#lang racket
+;; Use SRFI 48 to make %n.nf formats convenient.
+(require (prefix-in srfi/48: srfi/48)) ; SRFI 48: Intermediate Format Strings
+
+;; Parameter allows us to used exact decimal strings
+(read-decimal-as-inexact #f)
+
+;; files to read is a sequence, so it could be either a list or vector of files
+(define (text-processing/1 files-to-read)
+
+  (define (print-line-info d r a t)
+    (srfi/48:format #t "Line: ~11F  Reject: ~2F  Accept: ~2F  Line_tot: ~10,3F  Line_avg: ~10,3F~%"
+                    d r a t (if (zero? a) +nan.0 (/ t a))))
+
+  ;; returns something that can be used as args to an apply
+  (define (handle-and-tag-max consecutive-false tag max-consecutive-false max-false-tags)
+   (let ((consecutive-false+1 (add1 consecutive-false)))
+     (list consecutive-false+1
+           (max max-consecutive-false consecutive-false+1)
+           (cond ((= consecutive-false+1 max-consecutive-false) (cons tag max-false-tags))
+                 ((= consecutive-false max-consecutive-false) (list tag))
+                 (else max-false-tags)))))
+
+  (define (sub-t-p/1 N sum consecutive-false max-consecutive-false max-false-tags)
+    (for/fold ((N N) (sum sum) (consecutive-false consecutive-false) (max-consecutive-false max-consecutive-false) (max-false-tags max-false-tags))
+      ((l (in-lines)))
+      (match l
+        [(app string-split `(,tag ,(app string->number vs.ss) ...))
+         (let get-line-pairs
+           ((vs.ss vs.ss) (line-N 0) (reject 0) (line-sum 0) (consecutive-false consecutive-false)
+            (max-consecutive-false max-consecutive-false) (max-false-tags max-false-tags))
+           (match vs.ss
+             ['()
+              (print-line-info tag reject line-N line-sum)
+              (values (+ N line-N) (+ sum line-sum) consecutive-false max-consecutive-false max-false-tags)]
+             [(list-rest v (? positive?) tl)
+              (get-line-pairs tl (add1 line-N) reject (+ line-sum v) 0 max-consecutive-false max-false-tags)]
+             [(list-rest _ _ tl)
+                (apply get-line-pairs tl line-N (add1 reject) line-sum
+                       (handle-and-tag-max consecutive-false tag max-consecutive-false max-false-tags))]))]
+        (x (fprintf (current-error-port) "mismatch ~s~%" x)
+           (values N sum consecutive-false max-consecutive-false max-false-tags)))))
+
+  (for/fold ((N 0) (sum 0) (consecutive-false 0) (max-consecutive-false 0) (max-false-tags null))
+    ((f files-to-read))
+    (with-input-from-file f
+      (lambda () (sub-t-p/1 N sum consecutive-false max-consecutive-false max-false-tags)))))
+
+(let ((files (vector->list (current-command-line-arguments))))
+  (let-values (([N sum consecutive-false max-consecutive-false max-false-tags] (text-processing/1 files)))
+    (srfi/48:format #t "~%File(s)  = ~a~%Total    = ~10,3F~%Readings = ~6F~%" (string-join files) sum N)
+    (unless (zero? N) (srfi/48:format #t "Average  = ~10,3F~%" (/ sum N)))
+    (srfi/48:format #t "~%Maximum run(s) of ~a consecutive false readings ends at line starting with date(s): ~a~%"
+                    max-consecutive-false (string-join max-false-tags))))
--- a/Task/Text-processing-1/Ruby/text-processing-1.rb
+++ b/Task/Text-processing-1/Ruby/text-processing-1.rb
@ -0,0 +1,43 @@
+filename = "readings.txt"
+total = { "num_readings" => 0, "num_good_readings" => 0, "sum_readings" => 0.0 }
+invalid_count = 0
+max_invalid_count = 0
+invalid_run_end = ""
+
+File.new(filename).each do |line|
+  num_readings = 0
+  num_good_readings = 0
+  sum_readings = 0.0
+
+  fields = line.split
+  fields[1..-1].each_slice(2) do |reading, flag|
+    num_readings += 1
+    if Integer(flag) > 0
+      num_good_readings += 1
+      sum_readings += Float(reading)
+      invalid_count = 0
+    else
+      invalid_count += 1
+      if invalid_count > max_invalid_count
+        max_invalid_count = invalid_count
+        invalid_run_end = fields[0]
+      end
+    end
+  end
+
+  printf "Line: %11s  Reject: %2d  Accept: %2d  Line_tot: %10.3f  Line_avg: %10.3f\n",
+    fields[0], num_readings - num_good_readings, num_good_readings, sum_readings,
+    num_good_readings > 0 ? sum_readings/num_good_readings : 0.0
+
+  total["num_readings"] += num_readings
+  total["num_good_readings"] += num_good_readings
+  total["sum_readings"] += sum_readings
+end
+
+puts ""
+puts "File(s)  = #{filename}"
+printf "Total    = %.3f\n", total['sum_readings']
+puts "Readings = #{total['num_good_readings']}"
+printf "Average  = %.3f\n", total['sum_readings']/total['num_good_readings']
+puts ""
+puts "Maximum run(s) of #{max_invalid_count} consecutive false readings ends at #{invalid_run_end}"
--- a/Task/Text-processing-1/Scala/text-processing-1-1.scala
+++ b/Task/Text-processing-1/Scala/text-processing-1-1.scala
@ -0,0 +1,58 @@
+object DataMunging {
+  import scala.io.Source
+
+  def spans[A](list: List[A]) = list.tail.foldLeft(List((list.head, 1))) {
+    case ((a, n) :: tail, b) if a == b => (a, n + 1) :: tail
+    case (l, b) => (b, 1) :: l
+  }
+
+  type Flag = ((Boolean, Int), String)
+  type Flags = List[Flag]
+  type LineIterator = Iterator[Option[(Double, Int, Flags)]]
+
+  val pattern = """^(\d+-\d+-\d+)""" + """\s+(\d+\.\d+)\s+(-?\d+)""" * 24 + "$" r;
+
+  def linesIterator(file: java.io.File) = Source.fromFile(file).getLines().map(
+    pattern findFirstMatchIn _ map (
+      _.subgroups match {
+        case List(date, rawData @ _*) =>
+          val dataset = (rawData map (_ toDouble) iterator) grouped 2 toList;
+          val valid = dataset filter (_.last > 0) map (_.head)
+          val validSize = valid length;
+          val validSum = valid sum;
+          val flags = spans(dataset map (_.last > 0)) map ((_, date))
+          println("Line: %11s  Reject: %2d  Accept: %2d  Line_tot: %10.3f  Line_avg: %10.3f" format
+                  (date, 24 - validSize, validSize, validSum, validSum / validSize))
+          (validSum, validSize, flags)
+      }
+    )
+  )
+
+  def totalizeLines(fileIterator: LineIterator) =
+    fileIterator.foldLeft(0.0, 0, List[Flag]()) {
+      case ((totalSum, totalSize, ((flag, size), date) :: tail), Some((validSum, validSize, flags))) =>
+        val ((firstFlag, firstSize), _) = flags.last
+        if (firstFlag == flag) {
+          (totalSum + validSum, totalSize + validSize, flags.init ::: ((flag, size + firstSize), date) :: tail)
+        } else {
+          (totalSum + validSum, totalSize + validSize, flags ::: ((flag, size), date) :: tail)
+        }
+      case ((_, _, Nil), Some(partials)) => partials
+      case (totals, None) => totals
+    }
+
+  def main(args: Array[String]) {
+    val files = args map (new java.io.File(_)) filter (file => file.isFile && file.canRead)
+    val lines =  files.iterator flatMap linesIterator
+    val (totalSum, totalSize, flags) = totalizeLines(lines)
+    val ((_, invalidCount), startDate) = flags.filter(!_._1._1).max
+    val report = """|
+                    |File(s)  = %s
+                    |Total    = %10.3f
+                    |Readings = %6d
+                    |Average  = %10.3f
+                    |
+                    |Maximum run(s) of %d consecutive false readings began at %s""".stripMargin
+    println(report format (files mkString " ", totalSum, totalSize, totalSum / totalSize, invalidCount, startDate))
+  }
+}
--- a/Task/Text-processing-1/Scala/text-processing-1-2.scala
+++ b/Task/Text-processing-1/Scala/text-processing-1-2.scala
@ -0,0 +1,42 @@
+object AltDataMunging {
+  def main(args: Array[String]) {
+    var totalSum = 0.0
+    var totalSize  = 0
+    var maxInvalidDate = ""
+    var maxInvalidCount = 0
+    var invalidDate = ""
+    var invalidCount = 0
+    val files = args map (new java.io.File(_)) filter (file => file.isFile && file.canRead)
+
+    files.iterator flatMap (file => Source fromFile file getLines ()) map (_.trim split "\\s+") foreach {
+      case Array(date, rawData @ _*) =>
+        val dataset = (rawData map (_ toDouble) iterator) grouped 2 toList;
+        val valid = dataset filter (_.last > 0) map (_.head)
+        val flags = spans(dataset map (_.last > 0)) map ((_, date))
+        println("Line: %11s  Reject: %2d  Accept: %2d  Line_tot: %10.3f  Line_avg: %10.3f" format
+                (date, 24 - valid.size, valid.size, valid.sum, valid.sum / valid.size))
+        totalSum += valid.sum
+        totalSize += valid.size
+        dataset foreach {
+          case _ :: flag :: Nil if flag > 0 =>
+            if (invalidCount > maxInvalidCount) {
+              maxInvalidDate = invalidDate
+              maxInvalidCount = invalidCount
+            }
+            invalidCount = 0
+          case _ =>
+            if (invalidCount == 0) invalidDate = date
+            invalidCount += 1
+        }
+    }
+
+    val report = """|
+                    |File(s)  = %s
+                    |Total    = %10.3f
+                    |Readings = %6d
+                    |Average  = %10.3f
+                    |
+                    |Maximum run(s) of %d consecutive false readings began at %s""".stripMargin
+    println(report format (files mkString " ", totalSum, totalSize, totalSum / totalSize, maxInvalidCount, maxInvalidDate))
+  }
+}
--- a/Task/Text-processing-1/Tcl/text-processing-1.tcl
+++ b/Task/Text-processing-1/Tcl/text-processing-1.tcl
@ -0,0 +1,41 @@
+set max_invalid_run 0
+set max_invalid_run_end ""
+set tot_file 0
+set num_file 0
+
+set linefmt "Line: %11s  Reject: %2d  Accept: %2d  Line_tot: %10.3f  Line_avg: %10.3f"
+
+set filename readings.txt
+set fh [open $filename]
+while {[gets $fh line] != -1} {
+    set tot_line [set count [set num_line 0]]
+    set fields [regexp -all -inline {\S+} $line]
+    set date [lindex $fields 0]
+    foreach {val flag} [lrange $fields 1 end] {
+        incr count
+        if {$flag > 0} {
+            incr num_line
+            incr num_file
+            set tot_line [expr {$tot_line + $val}]
+            set invalid_run_count 0
+        } else {
+            incr invalid_run_count
+            if {$invalid_run_count > $max_invalid_run} {
+                set max_invalid_run $invalid_run_count
+                set max_invalid_run_end $date
+            }
+        }
+    }
+    set tot_file [expr {$tot_file + $tot_line}]
+    puts [format $linefmt $date [expr {$count - $num_line}] $num_line $tot_line \
+                 [expr {$num_line > 0 ? $tot_line / $num_line : 0}]]
+}
+close $fh
+
+puts ""
+puts "File(s)  = $filename"
+puts "Total    = [format %.3f $tot_file]"
+puts "Readings = $num_file"
+puts "Average  = [format %.3f [expr {$tot_file / $num_file}]]"
+puts ""
+puts "Maximum run(s) of $max_invalid_run consecutive false readings ends at $max_invalid_run_end"
--- a/Task/Text-processing-1/Ursala/text-processing-1.ursala
+++ b/Task/Text-processing-1/Ursala/text-processing-1.ursala
@ -0,0 +1,21 @@
+#import std
+#import nat
+#import flo
+
+parsed_data = ^|A(~&,* ^|/%ep@iNC ~&h==`1)*htK27K28pPCS (sep 9%cOi&)*FyS readings_dot_txt
+
+daily_stats =
+
+* ^|A(~&,@rFlS ^/length ^/plus:-0. ||0.! ~&i&& mean); mat` + <.
+   ~&n,
+   'accept: '--+ @ml printf/'%7.0f'+ float,
+   'total: '--+ @mrl printf/'%10.1f',
+   'average: '--+ @mrr printf/'%7.3f'>
+
+long_run =
+
+-+
+   ~&i&& ^|TNC('maximum of '--@h+ %nP,' consecutive false readings ending on line '--),
+   @nmrSPDSL -&~&,leql$^; ^/length ~&zn&-@hrZPF+ rlc both ~&rZ+-
+
+main = ^T(daily_stats^lrNCT/~& @mSL 'summary   ':,long_run) parsed_data
--- a/Task/Text-processing-1/Vedit-macro-language/text-processing-1.vedit
+++ b/Task/Text-processing-1/Vedit-macro-language/text-processing-1.vedit
@ -0,0 +1,68 @@
+#50 = Buf_Num		// Current edit buffer (source data)
+File_Open("output.txt")
+#51 = Buf_Num		// Edit buffer for output file
+Buf_Switch(#50)
+#10 = 0			// total sum of file data
+#11 = 0			// number of valid data items in file
+#12 = 0			// Current run of consecutive flags<0 in lines of file
+#13 = -1		// Max consecutive flags<0 in lines of file
+Reg_Empty(15)		// ... and date tag(s) at line(s) where it occurs
+
+While(!At_EOF) {
+    #20 = 0		// sum of line data
+    #21 = 0		// number of line data items with flag>0
+    #22 = 0		// number of line data items with flag<0
+    Reg_Copy_Block(14, Cur_Pos, Cur_Pos+10)	// date field
+
+    // extract field info, skipping initial date field
+    Repeat(ALL) {
+	Search("|{|T,|N}", ADVANCE+ERRBREAK)	// next Tab or Newline
+	if (Match_Item==2) { Break }		// end of line
+	#30 = Num_Eval(ADVANCE) * 1000		// #30 = value
+	Char					//  fixed point, 3 decimal digits
+	#30 += Num_Eval(ADVANCE+SUPPRESS)
+	#31 = Num_Eval(ADVANCE)			// #31 = flag
+	if (#31 < 1) {				// not valid field?
+	    #12++
+	    #22++
+	} else {				// valid field
+	    // check run of data-absent fields
+	    if(#13 == #12 && #12 > 0) {
+	        Reg_Set(15, ", ", APPEND)
+	        Reg_Set(15, @14, APPEND)
+	    }
+	    if(#13 < #12 && #12 > 0) {
+	        #13 = #12
+	        Reg_Set(15, @14)
+	    }
+
+	    // re-initialise run of nodata counter
+	    #12 = 0
+	    // gather values for averaging
+	    #20 += #30
+	    #21++
+	}
+    }
+
+    // totals for the file so far
+    #10 += #20
+    #11 += #21
+
+    Buf_Switch(#51)	// buffer for output data
+    IT("Line: ") Reg_Ins(14)
+    IT("  Reject:") Num_Ins(#22, COUNT, 3)
+    IT("  Accept:") Num_Ins(#21, COUNT, 3)
+    IT("  Line tot:") Num_Ins(#20, COUNT, 8) Char(-3) IC('.') EOL
+    IT("  Line avg:") Num_Ins((#20+#21/2)/#21, COUNT, 7) Char(-3) IC('.') EOL IN
+    Buf_Switch(#50)	// buffer for input data
+}
+
+Buf_Switch(#51)		// buffer for output data
+IN
+IT("Total:   ") Num_Ins(#10, FORCE+NOCR) Char(-3) IC('.') EOL IN
+IT("Readings: ") Num_Ins(#11, FORCE)
+IT("Average: ") Num_Ins((#10+#11/2)/#11, FORCE+NOCR) Char(-3) IC('.') EOL IN
+IN
+IT("Maximum run(s) of ") Num_Ins(#13, LEFT+NOCR)
+IT(" consecutive false readings ends at line starting with date(s): ") Reg_Ins(15)
+IN