awkcode.txt

c programming pearls answer

# unbundle - unpack a bundle into separate files

$1 != prev { close(prev); prev = $1 }
           { print substr($0, index($0, " ") + 1) >$1 }
emp.data Beth	4.00	0
emp.data Dan	3.75	0
emp.data Kathy	4.00	10
emp.data Mark	5.00	20
emp.data Mary	5.50	22
emp.data Susie	4.25	18
05.awk { print $1, $3 }
28.awk { print NF, $1, $NF }
06.awk { print $1, $2 * $3 }
07.awk { print NR, $0 }
10.awk { print "total pay for", $1, "is", $2 * $3 }
11.awk { printf("total pay for %s is $%.2f\n", $1, $2 * $3) }
11a.awk { printf("%-8s $%6.2f\n", $1, $2 * $3) }
08.sh awk '{ printf("%6.2f  %s\n", $2 * $3, $0) }' emp.data | sort
12.awk $2 >= 5
13.awk $2 * $3 > 50 { printf("$%.2f for %s\n", $2 * $3, $1) }
14.awk $1 == "Susie"
15.awk /Susie/
20.awk $2 >= 4 || $3 >= 20
21.awk $2 >= 4
21.awk $3 >= 20
22.awk !($2 < 4 && $3 < 20)
26.awk NF != 3   { print $0, "number of fields is not equal to 3" }
26.awk $2 < 3.35 { print $0, "rate is below minimum wage" }
26.awk $2 > 10   { print $0, "rate exceeds $10 per hour" }
26.awk $3 < 0    { print $0, "negative hours worked" }
26.awk $3 > 60   { print $0, "too many hours worked" }
30.awk BEGIN { print "NAME    RATE   HOURS";  print "" }
30.awk       { print }
31.awk $3 > 15 { emp = emp + 1 }
31.awk END     { print emp, "employees worked more than 15 hours" }
31a.awk END { print NR, "employees" }
32.awk     { pay = pay + $2 * $3 }
32.awk END { print NR, "employees"
32.awk       print "total pay is", pay
32.awk       print "average pay is", pay/NR
32.awk     }
33.awk $2 > maxrate { maxrate = $2; maxemp = $1 }
33.awk END { print "highest hourly rate:", maxrate, "for", maxemp }
34.awk     { names = names $1 " " }
34.awk END { print names }
33a.awk     { last = $0 }
33a.awk END { print last }
40.awk { print $1, length($1) }
40a.awk     { nc = nc + length($0) + 1
40a.awk       nw = nw + NF
40a.awk     }
40a.awk END { print NR, "lines,", nw, "words,", nc, "characters" }
41.awk $2 > 6 { n = n + 1; pay = pay + $2 * $3 }
41.awk END    { if (n > 0)
41.awk              print n, "employees, total pay is", pay,
41.awk                       "average pay is", pay/n
41.awk          else
41.awk              print "no employees are paid more than $6/hour"
41.awk        }
interest1.awk # interest1 - compute compound interest
interest1.awk #   input:  amount  rate  years
interest1.awk #   output: compounded value at the end of each year
interest1.awk 
interest1.awk {   i = 1
interest1.awk     while (i <= $3) {
interest1.awk         printf("\t%.2f\n", $1 * (1 + $2) ^ i)
interest1.awk         i = i + 1
interest1.awk     }
interest1.awk }
forint.awk # interest2 - compute compound interest
forint.awk #   input:  amount  rate  years
forint.awk #   output: compounded value at the end of each year
forint.awk 
forint.awk {   for (i = 1; i <= $3; i = i + 1)
forint.awk         printf("\t%.2f\n", $1 * (1 + $2) ^ i)
forint.awk }
50.awk # reverse - print input in reverse order by line
50.awk 
50.awk     { line[NR] = $0 }  # remember each input line
50.awk 
50.awk END { i = NR           # print lines in reverse order
50.awk       while (i > 0) {
50.awk           print line[i]
50.awk           i = i - 1
50.awk       }
50.awk     }
51.awk # reverse - print input in reverse order by line
51.awk 
51.awk     { line[NR] = $0 }  # remember each input line
51.awk 
51.awk END { for (i = NR; i > 0; i = i - 1)
51.awk           print line[i]
51.awk     }
61.awk END { print NR }
62.awk NR == 10
66.awk { print $NF }
63.awk     { field = $NF}
63.awk END { print field }
64.awk NF > 4
65.awk $NF > 4
67.awk     { nf = nf + NF }
67.awk END { print nf }
68.awk /Beth/ { nlines = nlines + 1 }
68.awk END    { print nlines }
69.awk $1 > max { max = $1; maxline = $0 }
69.awk END      { print max, maxline }
70.awk NF > 0
71.awk length($0) > 80
72.awk { print NF, $0 }
73.awk { print $2, $1 }
74.awk { temp = $1; $1 = $2; $2 = temp; print }
75.awk { $1 = NR; print }
76.awk { $2 = ""; print }
77.awk { for (i = NF; i > 0; i = i - 1) printf("%s ", $i)
77.awk   printf("\n")
77.awk }
78.awk { sum = 0
78.awk   for (i = 1; i <= NF; i = i + 1) sum = sum + $i
78.awk   print sum
78.awk }
79.awk     { for (i = 1; i <= NF; i = i + 1) sum = sum + $i }
79.awk END { print sum }
80.awk { for (i = 1; i <= NF; i = i + 1) if ($i < 0) $i = -$i
80.awk   print
80.awk }
countries USSR	8649	275	Asia
countries Canada	3852	25	North America
countries China	3705	1032	Asia
countries USA	3615	237	North America
countries Brazil	3286	134	South America
countries India	1267	746	Asia
countries Mexico	762	78	North America
countries France	211	55	Europe
countries Japan	144	120	Asia
countries Germany	96	61	Europe
countries England	94	56	Europe
p11.awk # print countries with column headers and totals
p11.awk 
p11.awk BEGIN { FS = "\t"   # make tab the field separator
p11.awk         printf("%10s %6s %5s   %s\n\n",
p11.awk               "COUNTRY", "AREA", "POP", "CONTINENT")
p11.awk       }
p11.awk       { printf("%10s %6d %5d   %s\n", $1, $2, $3, $4)
p11.awk         area = area + $2
p11.awk         pop = pop + $3
p11.awk       }
p11.awk END   { printf("\n%10s %6d %5d\n", "TOTAL", area, pop) }
p12.awk $0 >= "M"
p13.awk $1 < $4
p13a.awk /Asia/
re1.awk /^[0-9]+$/
re2.awk /^[0-9][0-9][0-9]$/
re3.awk /^(\+|-)?[0-9]+\.?[0-9]*$/
re4.awk /^[+-]?[0-9]+[.]?[0-9]*$/
re5.awk /^[+-]?([0-9]+[.]?[0-9]*|[.][0-9]+)([eE][+-]?[0-9]+)?$/
re6.awk /^[A-Za-z][A-Za-z0-9]*$/
re7.awk /^[A-Za-z]$|^[A-Za-z][0-9]$/
re8.awk /^[A-Za-z][0-9]?$/
p16.awk $2 !~ /^[0-9]+$/
p18.awk $4 == "Asia" && $3 > 500
p19.awk $4 == "Asia" || $4 == "Europe"
p20.awk $4 ~ /^(Asia|Europe)$/
p20a.awk /Asia/ || /Europe/
p20b.awk /Asia|Europe/
p21.awk /Europe/, /Africa/
p22.awk FNR == 1, FNR == 5 { print FILENAME ": " $0 }
p22a.awk FNR <= 5 { print FILENAME ": " $0 }
p23.awk $4 == "Asia" { print $1, 1000 * $2 }
p41.awk { $2 = $2 / 1000; print }
p42.awk BEGIN			{ FS = OFS = "\t" }
p42.awk $4 == "North America"	{ $4 = "NA" }
p42.awk $4 == "South America"	{ $4 = "SA" }
p42.awk 			{ print }
p43.awk BEGIN	{ FS = OFS = "\t" }
p43.awk 	{ $5 = 1000 * $3 / $2; print }
p43a.awk { print ($1 != 0 ? 1/$1 : "$1 is zero, line " NR) }
p32.awk $4 == "Asia" { pop = pop + $3; n = n + 1 }
p32.awk END          { print "Total population of the", n,
p32.awk                    "Asian countries is", pop, "million."
p32.awk              }
p34.awk $3 > maxpop  { maxpop = $3; country = $1 }
p34.awk END          { print "country with largest population:",
p34.awk                    country, maxpop
p34.awk              }
p24.awk { $2 /= 1000; print }
p35.awk { print NR ":" $0 }
p17.awk BEGIN	{ digits = "^[0-9]+$" }
p17.awk $2 ~ digits
builtup.awk BEGIN {
builtup.awk     sign = "[+-]?"
builtup.awk     decimal = "[0-9]+[.]?[0-9]*"
builtup.awk     fraction = "[.][0-9]+"
builtup.awk     exponent = "([eE]" sign "[0-9]+)?"
builtup.awk     number = "^" sign "(" decimal "|" fraction ")" exponent "$"
builtup.awk }
builtup.awk $0 ~ number
p36.awk { gsub(/USA/, "United States"); print }
p39.awk { $1 = substr($1, 1, 3); print $0 }
p40.awk     { s = s substr($1, 1, 3) " " }
p40.awk END { print s }
p40a.awk BEGIN { print "1E2"+0, "12E"+0, "E12"+0, "1X2Y3"+0 }
p40b.awk BEGIN { print 1E2 "", 12E-2 "", E12 "", 1.23456789 "" }
p45.awk {    i = 1
p45.awk      while (i <= NF) {
p45.awk          print $i
p45.awk          i++
p45.awk      }
p45.awk }
p46.awk { for (i = 1; i <= NF; i++)
p46.awk       print $i
p46.awk }
empty.awk BEGIN { FS = "\t" }
empty.awk       { for (i = 1; i <= NF && $i != ""; i++)
empty.awk             ;
empty.awk         if (i <= NF)
empty.awk             print
empty.awk       }
revline.awk     { x[NR] = $0 }
revline.awk END { for (i = NR; i > 0; i--) print x[i] }
p47.awk /Asia/   { pop["Asia"] += $3 }
p47.awk /Europe/ { pop["Europe"] += $3 }
p47.awk END      { print "Asian population is",
p47.awk                pop["Asia"], "million."
p47.awk            print "European population is",
p47.awk                pop["Europe"], "million."
p47.awk          }
p48.awk BEGIN { FS = "\t" }
p48.awk       { pop[$4] += $3 }
p48.awk END   { for (name in pop)
p48.awk             print name, pop[name]
p48.awk       }
p51.awk function max(m, n) {
p51.awk     return m > n ? m : n
p51.awk }
p51a.awk { print max($1,max($2,$3)) }  # print maximum of $1, $2, $3
p51a.awk 
p51a.awk function max(m, n) {
p51a.awk     return m > n ? m : n
p51a.awk }
p52.awk BEGIN	{ OFS = ":"; ORS = "\n\n" }
p52.awk 	{ print $1, $2 }
p53.awk $3 > 100   { print $1, $3 >"bigpop" }
p53.awk $3 <= 100  { print $1, $3 >"smallpop" }
p53a.awk { print($1, $3) > ($3 > 100 ? "bigpop" : "smallpop") }
p53b.awk { print > $1 }
p54.awk # print continents and populations, sorted by population
p54.awk 
p54.awk BEGIN { FS = "\t" }
p54.awk       { pop[$4] += $3 }
p54.awk END   { for (c in pop)
p54.awk           printf("%15s\t%6d\n", c, pop[c]) | "sort -t'\t' +1rn"
p54.awk       }
p60.awk # include - replace #include "f" by contents of file f
p60.awk 
p60.awk /^#include/ {
p60.awk     gsub(/"/, "", $2)
p60.awk     while (getline x <$2 > 0)
p60.awk         print x
p60.awk     next
p60.awk }
p60.awk { print }
p61.awk # echo - print command-line arguments
p61.awk 
p61.awk BEGIN {
p61.awk     for (i = 1; i < ARGC; i++)
p61.awk         printf "%s ", ARGV[i]
p61.awk     printf "\n"
p61.awk }
p44.awk # seq - print sequences of integers
p44.awk #   input:  arguments q, p q, or p q r;  q >= p; r > 0
p44.awk #   output: integers 1 to q, p to q, or p to q in steps of r
p44.awk 
p44.awk BEGIN {
p44.awk     if (ARGC == 2)
p44.awk         for (i = 1; i <= ARGV[1]; i++)
p44.awk             print i
p44.awk     else if (ARGC == 3)
p44.awk         for (i = ARGV[1]; i <= ARGV[2]; i++)
p44.awk             print i
p44.awk     else if (ARGC == 4)
p44.awk         for (i = ARGV[1]; i <= ARGV[2]; i += ARGV[3])
p44.awk             print i
p44.awk }
p62.awk $1 == "#include" { gsub(/"/, "", $2); system("cat " $2); next }
p62.awk                  { print }
field.awk # field - print named fields of each input line
field.awk #   usage:  field n n n ... file file file ...
field.awk 
field.awk awk '
field.awk BEGIN {
field.awk     for (i = 1; ARGV[i] ~ /^[0-9]+$/; i++) { # collect numbers
field.awk         fld[++nf] = ARGV[i]
field.awk         ARGV[i] = ""
field.awk     }
field.awk     if (i >= ARGC)   # no file names so force stdin
field.awk         ARGV[ARGC++] = "-"
field.awk }
field.awk {   for (i = 1; i <= nf; i++)
field.awk         printf("%s%s", $fld[i], i < nf ? " " : "\n")
field.awk }
field.awk ' $*
sum1 # sum1 - print column sums
sum1 #   input:  rows of numbers
sum1 #   output: sum of each column
sum1 #     missing entries are treated as zeros
sum1 
sum1     { for (i = 1; i <= NF; i++)
sum1           sum[i] += $i
sum1       if (NF > maxfld)
sum1           maxfld = NF
sum1     }
sum1 END { for (i = 1; i <= maxfld; i++) {
sum1           printf("%g", sum[i])
sum1           if (i < maxfld)
sum1               printf("\t")
sum1           else
sum1               printf("\n")
sum1       }
sum1     }
sum2 # sum2 - print column sums
sum2 #     check that each line has the same number of fields
sum2 #        as line one
sum2 
sum2 NR==1 { nfld = NF }
sum2       { for (i = 1; i <= NF; i++)
sum2             sum[i] += $i
sum2         if (NF != nfld)
sum2             print "line " NR " has " NF " entries, not " nfld
sum2       }
sum2 END   { for (i = 1; i <= nfld; i++)
sum2             printf("%g%s", sum[i], i < nfld ? "\t" : "\n")
sum2       }
sum3 # sum3 - print sums of numeric columns
sum3 #     input:  rows of integers and strings
sum3 #     output: sums of numeric columns
sum3 #       assumes every line has same layout
sum3 
sum3 NR==1 { nfld = NF
sum3         for (i = 1; i <= NF; i++)
sum3             numcol[i] = isnum($i)
sum3       }
sum3 
sum3       { for (i = 1; i <= NF; i++)
sum3             if (numcol[i])
sum3                 sum[i] += $i
sum3       }
sum3 
sum3 END   { for (i = 1; i <= nfld; i++) {
sum3             if (numcol[i])
sum3                 printf("%g", sum[i])
sum3             else
sum3                 printf("--")
sum3             printf(i < nfld ? "\t" : "\n")
sum3         }
sum3       }
sum3 
sum3 function isnum(n) { return n ~ /^[+-]?[0-9]+$/ }
3-4.ans     { total[$1] += $2 }
3-4.ans END { for (x in total) print x, total[x] | "sort" }
percent # percent
percent #   input:  a column of nonnegative numbers
percent #   output: each number and its percentage of the total
percent 
percent     { x[NR] = $1; sum += $1 }
percent 
percent END { if (sum != 0)
percent           for (i = 1; i <= NR; i++)