imported my solutions to this week's tasks, in Perl and C

15 files changed, 1035 insertions, 39 deletions

diff --git a/challenge-208/duncan-c-white/C/Makefile b/challenge-208/duncan-c-white/C/Makefile
new file mode 100644
index 0000000000..513f8703b6
--- /dev/null
+++ b/challenge-208/duncan-c-white/C/Makefile
@@ -0,0 +1,19 @@
+# Makefile rules generated by CB
+CC	= gcc
+CFLAGS	= -Wall -g
+BUILD	= ch-1 ch-2
+
+all:	$(BUILD)
+
+clean:
+	/bin/rm -f $(BUILD) *.o core a.out
+
+args.o:	args.c
+ch-1:	ch-1.o args.o csvsplit.o
+ch-1.o:	ch-1.c args.h csvsplit.h
+ch-2:	ch-2.o args.o parseints.o printarray.o
+ch-2.o:	ch-2.c args.h parseints.h printarray.h
+csvsplit.o:	csvsplit.c csvsplit.h
+parseints.o:	parseints.c args.h parseints.h printarray.h
+printarray.o:	printarray.c
+
diff --git a/challenge-208/duncan-c-white/C/README b/challenge-208/duncan-c-white/C/README
new file mode 100644
index 0000000000..dd5f3346f7
--- /dev/null
+++ b/challenge-208/duncan-c-white/C/README
@@ -0,0 +1,11 @@
+Thought I'd also have a go at translating ch-1.pl and ch-2.pl into C..
+
+Both C versions produce identical (non-debugging and debugging)
+output to the Perl originals.
+
+These C versions use most of my regular support modules:
+- a command-line argument processing module args.[ch],
+- a csvlist-of-int parsing module parseints.[ch], and
+- an int-array printing module printarray.[ch].
+- plus a (new for PWC) csv splitting module csvsplit.[ch] to split
+  a single argument into a wordlist
diff --git a/challenge-208/duncan-c-white/C/args.c b/challenge-208/duncan-c-white/C/args.c
new file mode 100644
index 0000000000..d4a2d38b9a
--- /dev/null
+++ b/challenge-208/duncan-c-white/C/args.c
@@ -0,0 +1,207 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <string.h>
+#include <ctype.h>
+#include <assert.h>
+
+
+bool debug = false;
+
+
+// process_flag_noarg( name, argc, argv );
+//	Process the -d flag, and check that there are no
+//	remaining arguments.
+void process_flag_noarg( char *name, int argc, char **argv )
+{
+	int arg=1;
+	if( argc>1 && strcmp( argv[arg], "-d" ) == 0 )
+	{
+		debug = true;
+		arg++;
+	}
+
+	int left = argc-arg;
+	if( left != 0 )
+	{
+		fprintf( stderr, "Usage: %s [-d]\n", name );
+		exit(1);
+	}
+}
+
+
+// int argno = process_flag_n_args( name, argc, argv, n, argmsg );
+//	Process the -d flag, and check that there are exactly
+//	n remaining arguments, return the index position of the first
+//	argument.  If not, generate a fatal Usage error using the argmsg.
+//	
+int process_flag_n_args( char *name, int argc, char **argv, int n, char *argmsg )
+{
+	int arg=1;
+	if( argc>1 && strcmp( argv[arg], "-d" ) == 0 )
+	{
+		debug = true;
+		arg++;
+	}
+
+	int left = argc-arg;
+	if( left != n )
+	{
+		fprintf( stderr, "Usage: %s [-d] %s\n       Exactly %d "
+			"arguments needed\n", name, argmsg, n );
+		exit(1);
+	}
+	return arg;
+}
+
+
+// int argno = process_flag_n_m_args( name, argc, argv, min, max, argmsg );
+//	Process the -d flag, and check that there are between
+//	min and max remaining arguments, return the index position of the first
+//	argument.  If not, generate a fatal Usage error using the argmsg.
+//	
+int process_flag_n_m_args( char *name, int argc, char **argv, int min, int max, char *argmsg )
+{
+	int arg=1;
+	if( argc>1 && strcmp( argv[arg], "-d" ) == 0 )
+	{
+		debug = true;
+		arg++;
+	}
+
+	int left = argc-arg;
+	if( left < min || left > max )
+	{
+		fprintf( stderr, "Usage: %s [-d] %s\n       Between %d and %d "
+			"arguments needed\n", name, argmsg, min, max );
+		exit(1);
+	}
+	return arg;
+}
+
+
+// process_onenumarg_default( name, argc, argv, defvalue, &n );
+//	Process the -d flag, and check that there is a single
+//	remaining numeric argument (or no arguments, in which case
+//	we use the defvalue), putting it into n
+void process_onenumarg_default( char *name, int argc, char **argv, int defvalue, int *n )
+{
+	char argmsg[100];
+	sprintf( argmsg, "[int default %d]", defvalue );
+	int arg = process_flag_n_m_args( name, argc, argv, 0, 1, argmsg );
+
+	*n = arg == argc ? defvalue : atoi( argv[arg] );
+}
+
+
+// process_onenumarg( name, argc, argv, &n );
+//	Process the -d flag, and check that there is a single
+//	remaining numeric argument, putting it into n
+void process_onenumarg( char *name, int argc, char **argv, int *n )
+{
+	int arg = process_flag_n_args( name, argc, argv, 1, "int" );
+
+	// argument is in argv[arg]
+	*n = atoi( argv[arg] );
+}
+
+
+// process_twonumargs( name, argc, argv, &m, &n );
+//	Process the -d flag, and check that there are 2
+//	remaining numeric arguments, putting them into m and n
+void process_twonumargs( char *name, int argc, char **argv, int *m, int *n )
+{
+	int arg = process_flag_n_args( name, argc, argv, 2, "int" );
+
+	// arguments are in argv[arg] and argv[arg+1]
+	*m = atoi( argv[arg++] );
+	*n = atoi( argv[arg] );
+}
+
+
+// process_twostrargs() IS DEPRECATED: use process_flag_n_m_args() instead
+
+
+// int arr[100];
+// int nel = process_listnumargs( name, argc, argv, arr, 100 );
+//	Process the -d flag, and check that there are >= 2
+//	remaining numeric arguments, putting them into arr[0..nel-1]
+//	and returning nel.
+int process_listnumargs( char *name, int argc, char **argv, int *arr, int maxel )
+{
+	int arg=1;
+	if( argc>1 && strcmp( argv[arg], "-d" ) == 0 )
+	{
+		debug = true;
+		arg++;
+	}
+
+	int left = argc-arg;
+	if( left < 2 )
+	{
+		fprintf( stderr, "Usage: %s [-d] list_of_numeric_args\n", name );
+		exit(1);
+	}
+	if( left > maxel )
+	{
+		fprintf( stderr, "%s: more than %d args\n", name, maxel );
+		exit(1);
+	}
+
+	// elements are in argv[arg], argv[arg+1]...
+
+	if( debug )
+	{
+		printf( "debug: remaining arguments are in arg=%d, "
+		        "firstn=%s, secondn=%s..\n",
+			arg, argv[arg], argv[arg+1] );
+	}
+
+	int nel = 0;
+	for( int i=arg; i<argc; i++ )
+	{
+		arr[nel++] = atoi( argv[i] );
+	}
+	arr[nel] = -1;
+	return nel;
+}
+
+
+//
+// bool isint = check_unsigned_int( char *val, int *n );
+//	Given an string val, check that there's an unsigned integer
+//	in it (after optional whitespace).  If there is a valid
+//	unsigned integer value, store that integer value in *n and
+//	return true; otherwise return false (and don't alter *n).
+bool check_unsigned_int( char *val, int *n )
+{
+	// skip whitespace in val
+	char *p;
+	for( p=val; isspace(*p); p++ )
+	{
+		/*EMPTY*/
+	}
+	if( ! isdigit(*p) ) return false;
+	*n = atoi(p);
+	return true;
+}
+
+
+//
+// bool ok = check_unsigned_real( char *val, double *n );
+//	Given an string val, check that there's an unsigned real
+//	in it (after optional whitespace).  If there is a valid
+//	unsigned real value, store that value in *n and
+//	return true; otherwise return false (and don't alter *n).
+bool check_unsigned_real( char *val, double *n )
+{
+	// skip whitespace in val
+	char *p;
+	for( p=val; isspace(*p); p++ )
+	{
+		/*EMPTY*/
+	}
+	if( ! isdigit(*p) ) return false;
+	*n = atof(p);
+	return true;
+}
diff --git a/challenge-208/duncan-c-white/C/args.h b/challenge-208/duncan-c-white/C/args.h
new file mode 100644
index 0000000000..8844a8f9c4
--- /dev/null
+++ b/challenge-208/duncan-c-white/C/args.h
@@ -0,0 +1,11 @@
+extern bool debug;
+
+extern void process_flag_noarg( char * name, int argc, char ** argv );
+extern int process_flag_n_args( char * name, int argc, char ** argv, int n, char * argmsg );
+extern int process_flag_n_m_args( char * name, int argc, char ** argv, int min, int max, char * argmsg );
+extern void process_onenumarg_default( char * name, int argc, char ** argv, int defvalue, int * n );
+extern void process_onenumarg( char * name, int argc, char ** argv, int * n );
+extern void process_twonumargs( char * name, int argc, char ** argv, int * m, int * n );
+extern int process_listnumargs( char * name, int argc, char ** argv, int * arr, int maxel );
+extern bool check_unsigned_int( char * val, int * n );
+extern bool check_unsigned_real( char * val, double * n );
diff --git a/challenge-208/duncan-c-white/C/ch-1.c b/challenge-208/duncan-c-white/C/ch-1.c
new file mode 100644
index 0000000000..a7d3a673e2
--- /dev/null
+++ b/challenge-208/duncan-c-white/C/ch-1.c
@@ -0,0 +1,176 @@
+//
+// Task 1: Minimum Index Sum
+// 
+// C version.
+// 
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <string.h>
+#include <ctype.h>
+#include <assert.h>
+
+#include "args.h"
+#include "csvsplit.h"
+
+
+typedef struct
+{
+	char **arr;	// array of 256 char *s
+	int nel;
+} strlist;
+
+
+void process1( char *str, void *extra )
+{
+	strlist *e = (strlist *)extra;
+	char *s = strdup( str );
+	assert( s != NULL );
+	e->arr[ e->nel++ ] = s;
+}
+
+
+void print_strlist( strlist *list )
+{
+	bool first = true;
+	for( int i=0; i<list->nel; i++ )
+	{
+		if( ! first ) putchar( ',' );
+		fputs( list->arr[i], stdout );
+		first = false;
+	}
+}
+
+
+// bool isin = in_strlist( word, &list );
+bool in_strlist( char *word, strlist *list )
+{
+	for( int i=0; i<list->nel; i++ )
+	{
+		if( strcmp( word, list->arr[i] ) == 0 )
+		{
+			return true;
+		}
+	}
+	return false;
+}
+
+
+// int sum = indexsum( word, &list1, &list2 );
+//	Calculate and return the index sum of word in the two lists.
+int indexsum( char *word, strlist *list1, strlist *list2 )
+{
+	int sum = 0;
+	for( int pos=0; pos < list1->nel; pos++ )
+	{
+		if( strcmp( list1->arr[pos], word ) == 0 )
+		{
+			sum += pos;
+		}
+	}
+	for( int pos=0; pos < list2->nel; pos++ )
+	{
+		if( strcmp( list2->arr[pos], word ) == 0 )
+		{
+			sum += pos;
+		}
+	}
+	return sum;
+}
+
+
+int main( int argc, char **argv )
+{
+	int argno = process_flag_n_args( "mis", argc, argv,
+		2, "wordlist wordlist" );
+
+	strlist list1;
+	list1.arr = malloc( 256*sizeof(char *) );
+	assert( list1.arr != NULL );
+	list1.nel = 0;
+	csvForeach( argv[argno++], &process1, &list1 );
+
+	strlist list2;
+	list2.arr = malloc( 256*sizeof(char *) );
+	assert( list2.arr != NULL );
+	list2.nel = 0;
+	csvForeach( argv[argno], &process1, &list2 );
+
+	if( debug )
+	{
+		printf( "list1: " );
+		print_strlist( &list1 );
+		putchar( '\n' );
+		printf( "list2: " );
+		print_strlist( &list2 );
+		putchar( '\n' );
+	}
+
+	strlist common;
+	common.arr = malloc( 256*sizeof(char *) );
+	assert( common.arr != NULL );
+	common.nel = 0;
+
+	for( int i=0; i<list1.nel; i++ )
+	{
+		// look for list1.arr[i] in list2
+		if( in_strlist( list1.arr[i], &list2 ) )
+		{
+			common.arr[common.nel++] = list1.arr[i];
+		}
+	}
+	if( debug )
+	{
+		printf( "There are %d common strings: ", common.nel );
+		print_strlist( &common );
+		putchar( '\n' );
+	}
+
+	int mis = list1.nel + list2.nel;
+	strlist best;
+	best.arr = malloc( 256*sizeof(char *) );
+	assert( best.arr != NULL );
+	best.nel = 0;
+
+	for( int pos=0; pos<common.nel; pos++ )
+	{
+		char *w = common.arr[pos];
+		int s = indexsum( w, &list1, &list2 );
+		if( debug )
+		{
+			printf( "The index sum of %s is %d\n", w, s );
+		}
+		if( s < mis )
+		{
+			mis = s;
+			best.arr[0] = w;
+			best.nel = 1;
+		} else if( s == mis )
+		{
+			best.arr[best.nel++] = w;
+		}
+	}
+
+	putchar( '(' );
+	print_strlist( &best );
+	putchar( ')' );
+	putchar( '\n' );
+
+	for( int i=0; i<list1.nel; i++ )
+	{
+		free( list1.arr[i] );
+	}
+	free( list1.arr );
+	for( int i=0; i<list2.nel; i++ )
+	{
+		free( list2.arr[i] );
+	}
+	free( list2.arr );
+
+	free( common.arr );
+
+	free( best.arr );
+
+	return 0;
+}
diff --git a/challenge-208/duncan-c-white/C/ch-2.c b/challenge-208/duncan-c-white/C/ch-2.c
new file mode 100644
index 0000000000..2a7c1c4bb4
--- /dev/null
+++ b/challenge-208/duncan-c-white/C/ch-2.c
@@ -0,0 +1,121 @@
+//
+// Task 2: Duplicate and Missing
+// 
+// C version.
+// 
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <string.h>
+#include <ctype.h>
+#include <assert.h>
+
+#include "args.h"
+#include "parseints.h"
+#include "printarray.h"
+
+
+// bool isin = in_list( target, arr, nel );
+bool in_list( int target, int *arr, int nel )
+{
+	for( int i=0; i<nel; i++ )
+	{
+		if( arr[i] == target ) return true;
+	}
+	return false;
+}
+
+
+int main( int argc, char **argv )
+{
+	int argno = process_flag_n_m_args( "h-index", argc, argv,
+		1, 1000, "intlist" );
+
+	int nel;
+	int *list = parse_int_args( argc, argv, argno, &nel );
+
+	if( debug )
+	{
+		printf( "debug: initial list: " );
+		print_int_array( 60, nel, list, ',', stdout );
+		putchar( '\n' );
+	}
+
+	// check that it's sorted
+	int prev = list[0];
+	for( int i=1; i<nel; i++ )
+	{
+		if( list[i] < prev )
+		{
+			fprintf( stderr, "dum: not sorted at element %d\n",
+				list[i] );
+			exit(1);
+		}
+		prev = list[i];
+	}
+
+	int base = list[0];
+	int dup = -1;
+
+	// find any duplicate, and die if there's only one duplicate
+	for( int i=0; i<nel; i++ )
+	{
+		int expect = base+i;
+		int el = list[i];
+		if( el > expect )
+		{
+			fprintf( stderr, "dum: bad input element %d\n", el );
+			exit(1);
+		}
+		if( in_list( el, list, i ) )
+		{
+			if( dup > -1 )
+			{
+				fprintf( stderr, "dum: multiple duplicates "
+					 "found at element %d\n", el );
+				exit(1);
+			}
+			dup = el;
+		}
+	}
+
+	if( dup == -1 )
+	{
+		printf( "-1\n" );
+		exit( 0 );
+	}
+
+	if( debug )
+	{
+		printf( "dup is %d\n", dup );
+	}
+
+	// missing is sole member of {B..B+N-1} - all el[i]
+	int missing = -1;
+
+	for( int i=0; i<nel; i++ )
+	{
+		int el = base+i;
+		if( ! in_list( el, list, nel ) )
+		{
+			missing = el;
+			if( debug )
+			{
+				printf( "found missing value %d\n", el );
+			}
+		}
+	}
+
+	if( missing == -1 )
+	{
+		fprintf( stderr, "No missing value found\n" );
+		exit(1);
+	}
+
+	printf( "(%d, %d)\n", dup, missing );
+
+	free( list );
+
+	return 0;
+}
diff --git a/challenge-208/duncan-c-white/C/csvsplit.c b/challenge-208/duncan-c-white/C/csvsplit.c
new file mode 100644
index 0000000000..20e375dabb
--- /dev/null
+++ b/challenge-208/duncan-c-white/C/csvsplit.c
@@ -0,0 +1,47 @@
+/*
+ * csvsplit.c: simple CSV splitting (csvForeach), useful utility function
+ *
+ * (C) Duncan C. White, May 2017
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdbool.h>
+#include <assert.h>
+
+#include "csvsplit.h"
+
+
+/*
+ * csvForeach( csvstring, &foreach_callback, (void *)extravalue );
+ *	Split csvstring into each comma-separated field, calling the
+ *	foreach calback for each comma-separated field, passing the
+ *	value and extravalue as parameters to it.  It doesn't deal
+ *	with commas in quoted strings, however.
+ */
+void csvForeach( char *csvstring, csvforeachcb cb, void *extra )
+{
+	// we need to modify the string, so make a mutable copy..
+	char *copy = strdup( csvstring );
+
+	char *start = copy;
+	for(;;)
+	{
+		char *comma=strchr( start, ',' );
+		if( comma != NULL )
+		{
+			// found the first comma after start
+			*comma = '\0';
+		}
+		//printf( "debug: csvForeach: found value %s\n", start );
+		(*cb)( start, extra );
+
+	if( comma == NULL ) break;
+
+		// move start to one beyond where comma was..
+		start = comma+1;
+	}
+	// don't forget to..
+	free( copy );
+}
diff --git a/challenge-208/duncan-c-white/C/csvsplit.h b/challenge-208/duncan-c-white/C/csvsplit.h
new file mode 100644
index 0000000000..c7f84857c1
--- /dev/null
+++ b/challenge-208/duncan-c-white/C/csvsplit.h
@@ -0,0 +1,14 @@
+/*
+ * csvsplit.h: simple CSV splitting (csvForeach) - doesn't handle
+ *	       quoted fields with nested commas.
+ *
+ * (C) Duncan C. White, May 2017
+ */
+
+// a csv foreach callback function takes
+// a char * (the csv value split out)
+// and a void * (an extra value).
+
+typedef void (*csvforeachcb)( char *, void * );
+
+extern void csvForeach( char * csvstring, csvforeachcb cb, void * extra );
diff --git a/challenge-208/duncan-c-white/C/parseints.c b/challenge-208/duncan-c-white/C/parseints.c
new file mode 100644
index 0000000000..80408d3382
--- /dev/null
+++ b/challenge-208/duncan-c-white/C/parseints.c
@@ -0,0 +1,114 @@
+// Simple routine to parse one or more arguments,
+// looking for individual +ints or comma-separated
+// lists of +ints.
+// 
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <string.h>
+#include <ctype.h>
+#include <assert.h>
+
+#include "args.h"
+#include "printarray.h"
+#include "parseints.h"
+
+typedef struct
+{
+	int nel;	// current number of elements 
+	int maxel;	// maximum number of elements allocated
+	int *list;	// malloc()d list of integers
+} intlist;
+
+
+//
+// intlist il.. then initialize il..  then:
+// add_one( element, &il );
+//	
+static void add_one( int x, intlist *p )
+{
+	if( p->nel > p->maxel )
+	{
+		p->maxel += 128;
+		p->list = realloc( p->list, p->maxel );
+		assert( p->list != NULL );
+	}
+	#if 0
+	if( debug )
+	{
+		printf( "PIA: appending %d to result at "
+			"pos %d\n", x, p->nel );
+	}
+	#endif
+	p->list[p->nel++] = x;
+}
+
+
+//
+// intlist il.. then initialize il..  then:
+// add_one_arg( argstr, &il );
+//	
+static void add_one_arg( char *argstr, intlist *p )
+{
+	int x;
+	if( !check_unsigned_int(argstr,&x) )
+	{
+		fprintf( stderr, "PIA: arg %s must be +int\n", argstr );
+		exit(1);
+	}
+	add_one( x, p );
+}
+
+
+//
+// int nel;
+// int *ilist = parse_int_args( argc, argv, argno, &nel );
+//	process all arguments argv[argno..argc-1], extracting either
+//	single ints or comma-separated lists of ints from those arguments,
+//	accumulate all integers in a dynarray list, storing the total number
+//	of elements in nel.  This list must be freed by the caller.
+//	Note that the list of elements used to be terminated by a -1 value,
+//	but I've commented this out from now on.
+//
+int *parse_int_args( int argc, char **argv, int argno, int *nel )
+{
+	int *result = malloc( 128 * sizeof(int) );
+	assert( result != NULL );
+	intlist il = { 0, 128, result };
+
+	#if 0
+	if( debug )
+	{
+		printf( "PIA: parsing ints from args %d..%d\n", argno, argc-1 );
+	}
+	#endif
+	for( int i=argno; i<argc; i++ )
+	{
+		assert( strlen(argv[i]) < 1024 );
+		char copy[1024];
+		strcpy( copy, argv[i] );
+		char *com;
+		char *s;
+		for( s=copy; (com = strchr(s,',')) != NULL; s=com+1 )
+		{
+			*com = '\0';
+			add_one_arg( s, &il );
+		}
+		add_one_arg( s, &il );
+	}
+
+	//add_one( -1, &il );
+
+	#if 0
+	if( debug )
+	{
+		printf( "PIA: final list is " );
+		print_int_array( 80, il.nel, il.list, ',', stdout );
+		putchar( '\n' );
+	}
+	#endif
+
+	*nel = il.nel;
+	return il.list;
+}
diff --git a/challenge-208/duncan-c-white/C/parseints.h b/challenge-208/duncan-c-white/C/parseints.h
new file mode 100644
index 0000000000..da5e145a86
--- /dev/null
+++ b/challenge-208/duncan-c-white/C/parseints.h
@@ -0,0 +1 @@
+extern int * parse_int_args( int argc, char ** argv, int argno, int * nel );
diff --git a/challenge-208/duncan-c-white/C/printarray.c b/challenge-208/duncan-c-white/C/printarray.c
new file mode 100644
index 0000000000..ddee597df3
--- /dev/null
+++ b/challenge-208/duncan-c-white/C/printarray.c
@@ -0,0 +1,39 @@
+#include <stdio.h>
+#include <string.h>
+
+
+// print_int_array( maxw, nelements, results[], sep, outfile );
+//	format results[0..nelements-1] as a <sep> separated
+//      list onto outfile with lines <= maxw chars long.
+//	produces a whole number of lines of output - without the trailing '\n'
+void print_int_array( int maxw, int nel, int *results, char sep, FILE *out )
+{
+	int linelen = 0;
+	for( int i=0; i<nel; i++ )
+	{
+		char buf[100];
+		sprintf( buf, "%d", results[i] );
+		int len = strlen(buf);
+		if( linelen + len + 2 > maxw )
+		{
+			fputc( '\n', out );
+			linelen = 0;
+		} else if( i>0 )
+		{
+			fputc( ' ', out );
+			linelen++;
+		}
+
+		linelen += len;
+		fprintf( out, "%s", buf );
+		if( i<nel-1 )
+		{
+			fputc( sep, out );
+			linelen++;
+		}
+	}
+	//if( linelen>0 )
+	//{
+	//	fputc( '\n', out );
+	//}
+}
diff --git a/challenge-208/duncan-c-white/C/printarray.h b/challenge-208/duncan-c-white/C/printarray.h
new file mode 100644
index 0000000000..40efb83277
--- /dev/null
+++ b/challenge-208/duncan-c-white/C/printarray.h
@@ -0,0 +1 @@
+extern void print_int_array( int maxw, int nel, int * results, char sep, FILE * out );
diff --git a/challenge-208/duncan-c-white/README b/challenge-208/duncan-c-white/README
index c6faef5c45..80916b64a2 100644
--- a/challenge-208/duncan-c-white/README
+++ b/challenge-208/duncan-c-white/README
@@ -1,67 +1,86 @@
-Task 1: Keyboard Word
+Task 1: Minimum Index Sum
 
-You are given an array of words.  Write a script to print all the words
-in the given array that can be typed using alphabet on only one row of
-the keyboard.
+You are given two arrays of strings.  Write a script to find out all
+common strings in the given two arrays with minimum index sum. If no
+common strings are found returns an empty list.
 
-Let us assume the keys are arranged as below:
+Example 1
 
-Row 1: qwertyuiop
-Row 2: asdfghjkl
-Row 3: zxcvbnm
+Input: @list1 = ("Perl", "Raku", "Love")
+       @list2 = ("Raku", "Perl", "Hate")
 
-Example 1
+Output: ("Perl", "Raku")
 
-  Input: @words = ("Hello","Alaska","Dad","Peace")
-  Output: ("Alaska","Dad")
+There are two common strings "Perl" and "Raku".
+Index sum of "Perl": 0 + 1 = 1
+Index sum of "Raku": 1 + 0 = 1
 
 Example 2
 
-  Input: @array = ("OMG","Bye")
-  Output: ()
+Input: @list1 = ("A", "B", "C")
+       @list2 = ("D", "E", "F")
+
+Output: ()
+
+No common string found, so no result.
+
+Example 3
 
-MY NOTES: very easy.  Lower case each word, then match it against /^[qwertyuiop]+$/ for the first row, similarly regexes for the second and third rows.
+Input: @list1 = ("A", "B", "C")
+       @list2 = ("C", "A", "B")
+
+Output: ("A")
+
+There are three common strings "A", "B" and "C".
+Index sum of "A": 0 + 1 = 1
+Index sum of "B": 1 + 2 = 3
+Index sum of "C": 2 + 0 = 2
+
+MY NOTES: very easy.  Identify whether any common strings exist: set
+intersection.  Then calculate index sum of all common strings and choose
+the minimum ones.  Trickiest thing to work out is how to input two lists
+of strings - let's choose an arbitrary separator ':'..
 
 GUEST LANGUAGE: As a bonus, I also had a go at translating ch-1.pl into C
-(look in the C directory for that).  replaced regexes with a custom: match a
-sequence of <these chars:string>.
+(look in the C directory for that).
 
 
-Task 2: H-Index
+Task 2: Duplicate and Missing
 
-You are given an array of integers containing citations a researcher
-has received for each paper.  Write a script to compute the researcher's
-H-Index. For more information please checkout:
+You are given an array of integers in sequence with one missing and one
+duplicate.  Write a script to find the duplicate and missing integer in
+the given array. Return -1 if none found.  For the sake of this task,
+let us assume the array contains no more than one duplicate and missing.
 
-https://en.wikipedia.org/wiki/H-index
+Example 1:
 
-The H-Index is the largest number h such that h articles have at least
-h citations each. For example, if an author has five publications, with
-9, 7, 6, 2, and 1 citations (ordered from greatest to least), then the
-author's H-index is 3, because the author has three publications with 3
-or more citations. However, the author does not have four publications
-with 4 or more citations.
+  Input: @nums = (1,2,2,4)
+  Output: (2,3)
 
+  Duplicate is 2 and Missing is 3.
 
-Example 1
+Example 2:
 
-  Input: @citations = (10,8,5,4,3)
-  Output: 4
+  Input: @nums =  1,2,3,4
+  Output: -1
 
-Because the 4th publication has 4 citations and the 5th has only 3.
+  No duplicate and missing found.
 
-Example 2
+Example 3:
 
-  Input: @citations = (25,8,5,3,3)
-  Output: 3
+  Input: @nums = (1,2,3,3)
+  Output: (3,4)
 
-The H-Index is 3 because the fourth paper has only 3 citations.
+  Duplicate is 3 and Missing is 4.
 
-MY NOTES: also pretty easy.  The Wikipedia entry sheds more light:
+MY NOTES: also pretty easy - especially if the list of integers should (if it
+were not for the one missing and one duplicated) form the sequence 1..N.
+if so: the duplicate is the element where el[i] != i.
+The missing is the sole member of set {1..N} - all el[i]
 
-"First we order the citations from the largest to the lowest value.
- Then, we look for the last position in which citation[h] >= h."
- (This assumes array indexes start at 1, I think).
+Let's generalise it slightly to B, B+1, .. B+N-1.  Then: find the element
+where el[i] != el[0]+i, that is the duplicate, and the missing is the sole
+member of {B..N+N-1} - all el[i]
 
 GUEST LANGUAGE: As a bonus, I also had a go at translating ch-2.pl into C
 (look in the C directory for that)
diff --git a/challenge-208/duncan-c-white/perl/ch-1.pl b/challenge-208/duncan-c-white/perl/ch-1.pl
new file mode 100755
index 0000000000..66a0357f0b
--- /dev/null
+++ b/challenge-208/duncan-c-white/perl/ch-1.pl
@@ -0,0 +1,108 @@
+#!/usr/bin/perl
+# 
+# Task 1: Minimum Index Sum
+# 
+# You are given two arrays of strings.  Write a script to find out all
+# common strings in the given two arrays with minimum index sum. If no
+# common strings are found returns an empty list.
+# 
+# Example 1
+# 
+# Input: @list1 = ("Perl", "Raku", "Love")
+#        @list2 = ("Raku", "Perl", "Hate")
+# 
+# Output: ("Perl", "Raku")
+# 
+# There are two common strings "Perl" and "Raku".
+# Index sum of "Perl": 0 + 1 = 1
+# Index sum of "Raku": 1 + 0 = 1
+# 
+# Example 2
+# 
+# Input: @list1 = ("A", "B", "C")
+#        @list2 = ("D", "E", "F")
+# 
+# Output: ()
+# 
+# No common string found, so no result.
+# 
+# Example 3
+# 
+# Input: @list1 = ("A", "B", "C")
+#        @list2 = ("C", "A", "B")
+# 
+# Output: ("A")
+# 
+# There are three common strings "A", "B" and "C".
+# Index sum of "A": 0 + 1 = 1
+# Index sum of "B": 1 + 2 = 3
+# Index sum of "C": 2 + 0 = 2
+# 
+# MY NOTES: very easy.  Identify whether any common strings exist: set
+# intersection.  Then calculate index sum of all common strings and choose
+# the minimum ones.  Trickiest thing to work out is how to input two lists
+# of strings - let's assume that they come as two command line args eg.
+# A,B,C and C,A,B
+# 
+# GUEST LANGUAGE: As a bonus, I also had a go at translating ch-1.pl into C
+# (look in the C directory for that).
+# 
+
+use strict;
+use warnings;
+use feature 'say';
+use Getopt::Long;
+use Data::Dumper;
+
+my $debug=0;
+die "Usage: mis [--debug] word-list word-list\n"
+	unless GetOptions( "debug"=>\$debug ) && @ARGV==2;
+
+my( $list1, $list2 ) = @ARGV;
+my @list1 = split( /,/, $list1 );
+my @list2 = split( /,/, $list2 );
+
+#say "list1: ", join(',',@list1) if $debug;
+#say "list2: ", join(',',@list2) if $debug;
+
+my %set1 = map { $_ => 1 } @list1;
+
+# my $sum = indexsum( $word, \@list1, \@list2 );
+#	Calculate and return the index sum of $word in the two lists.
+#
+sub indexsum
+{
+	my( $word, $list1, $list2 ) = @_;
+	my $sum = 0;
+	foreach my $pos (0..$#$list1)
+	{
+		$sum += $pos if $list1[$pos] eq $word;
+	}
+	foreach my $pos (0..$#$list2)
+	{
+		$sum += $pos if $list2[$pos] eq $word;
+	}
+	return $sum;
+}
+
+my @common = grep { $set1{$_} } @list2;
+my $nc = @common;
+say "There are $nc common strings: ", join(',',@common) if $debug;
+
+my $mis = @list1 + @list2;
+my @best = ();
+foreach my $w (@common)
+{
+	my $s = indexsum( $w, \@list1, \@list2 );