Awk

From Halfface
Jump to navigation Jump to search

basic

awk 'BEGIN           {initializations}
     search_pattern1 {actions}
     search_pattern2 {actions}
     ...
     END             {final actions}'  file

useful

Remove 2 first lines of file.

awk 'NR > 2' /tmp/tmp

Get media information. Pick encoded date, replace : with -, print row 6 and 7 and add .mov. Find just once.

mediainfo *.mov | awk '/Encoded date/ { gsub(/:/,"-") ; print $6 "_" $7 ".mov" ;exit }'

remove xml comments

 awk -v RS='<!--|-->' 'NR%2' file

print something between tags

 
awk -F'[<|>]' '/jndi/{print $3}'

print lines containing cat, dog and bird.

awk '/cat/ && /dog/ && /bird/' files

Print rows where first column doesnt contains ABC

awk '$1 !~ /ABC/' file # print lines whose 1st field doesn't

Print row 5 and 9.

awk 'NR==5 || NR==9' "file"

Print row betwen 5 and 9.

awk 'NR>=5&&NR<=9' "file"

Print column 4 to the end of passwd. Field separator set to :

cat /etc/passwd | awk ' BEGIN { FS=":" } {
for (i=4; i<=NF; i++)
printf("%s ", $i)
printf("\n") # CR at end of line
} '

Summarize size of files.

find . -type f -printf '%s\n' | awk '{ a+=$1 } END { print a }'

Summarize on 5 column. MB

awk '{ SUM +=  $5} END { print SUM/1024/1024 }' 

Summarize on 5 column. GB

awk '{ SUM +=  $5} END { print SUM/1024/1024/1024 }'

Print lines containing T2 in second column.

awk '$2 ~ /T2/' file

Print second column where 1 columnt contains nodev

awk '$1 == "nodev" { print $2 }'

Print lines where first column value is bigger than 10

awk '$1 > 10'

lenght

Print length of string.

awk '{ print length(), $0 }'

Print fields matching regexp in 5 column delimiter being ,

awk -F',' '$5 ~ /^10.[0-9]*.21.[0-9]*/'

Print lines where 4 column is empty

awk 'BEGIN {FS=","} $4=="" {print}'

awk one liners

FILE SPACING:

# double space a file
awk ‘1;{print “”}’
awk ‘BEGIN{ORS=”\n\n”};1′

# double space a file which already has blank lines in it. Output file
# should contain no more than one blank line between lines of text.
# NOTE: On Unix systems, DOS lines which have only CRLF (\r\n) are
# often treated as non-blank, and thus ‘NF’ alone will return TRUE.
awk ‘NF{print $0 “\n”}’

# triple space a file
awk ‘1;{print “\n”}’

NUMBERING AND CALCULATIONS:

# precede each line by its line number FOR THAT FILE (left alignment).
# Using a tab (\t) instead of space will preserve margins.
awk ‘{print FNR “\t” $0}’ files*

# precede each line by its line number FOR ALL FILES TOGETHER, with tab.
awk ‘{print NR “\t” $0}’ files*

# number each line of a file (number on left, right-aligned)
# Double the percent signs if typing from the DOS command prompt.
awk ‘{printf(”%5d : %s\n”, NR,$0)}’

# number each line of file, but only print numbers if line is not blank
# Remember caveats about Unix treatment of \r (mentioned above)
awk ‘NF{$0=++a ” :” $0};{print}’
awk ‘{print (NF? ++a ” :” :”") $0}’

# count lines (emulates “wc -l”)
awk ‘END{print NR}’

# print the sums of the fields of every line
awk ‘{s=0; for (i=1; i max {max=$1; maxline=$0}; END{ print max, maxline}’

# print the number of fields in each line, followed by the line
awk ‘{ print NF “:” $0 } ‘

# print the last field of each line
awk ‘{ print $NF }’

# print the last field of the last line
awk ‘{ field = $NF }; END{ print field }’

# print every line with more than 4 fields
awk ‘NF > 4′

# print every line where the value of the last field is > 4
awk ‘$NF > 4′

TEXT CONVERSION AND SUBSTITUTION:


# IN UNIX ENVIRONMENT: convert DOS newlines (CR/LF) to Unix format
awk ‘{sub(/\r$/,”");print}’ # assumes EACH line ends with Ctrl-M

# IN UNIX ENVIRONMENT: convert Unix newlines (LF) to DOS format
awk ‘{sub(/$/,”\r”);print}

# IN DOS ENVIRONMENT: convert Unix newlines (LF) to DOS format
awk 1

# IN DOS ENVIRONMENT: convert DOS newlines (CR/LF) to Unix format
# Cannot be done with DOS versions of awk, other than gawk:
gawk -v BINMODE=”w” ‘1′ infile >outfile

# Use “tr” instead.
tr -d \r outfile # GNU tr version 1.22 or higher

# delete leading whitespace (spaces, tabs) from front of each line
# aligns all text flush left
awk ‘{sub(/^[ \t]+/, “”); print}’

# delete trailing whitespace (spaces, tabs) from end of each line
awk ‘{sub(/[ \t]+$/, “”);print}’

# delete BOTH leading and trailing whitespace from each line
awk ‘{gsub(/^[ \t]+|[ \t]+$/,”");print}’
awk ‘{$1=$1;print}’ # also removes extra space between fields

# insert 5 blank spaces at beginning of each line (make page offset)
awk ‘{sub(/^/, ” “);print}’

# align all text flush right on a 79-column width
awk ‘{printf “%79s\n”, $0}’ file*

# center all text on a 79-character width
awk ‘{l=length();s=int((79-l)/2); printf “%”(s+l)”s\n”,$0}’ file*

# substitute (find and replace) “foo” with “bar” on each line
awk ‘{sub(/foo/,”bar”);print}’ # replaces only 1st instance
gawk ‘{$0=gensub(/foo/,”bar”,4);print}’ # replaces only 4th instance
awk ‘{gsub(/foo/,”bar”);print}’ # replaces ALL instances in a line

# substitute “foo” with “bar” ONLY for lines which contain “baz”
awk ‘/baz/{gsub(/foo/, “bar”)};{print}’

# substitute “foo” with “bar” EXCEPT for lines which contain “baz”
awk ‘!/baz/{gsub(/foo/, “bar”)};{print}’

# change “scarlet” or “ruby” or “puce” to “red”
awk ‘{gsub(/scarlet|ruby|puce/, “red”); print}’

# reverse order of lines (emulates “tac”)
awk ‘{a[i++]=$0} END {for (j=i-1; j>=0;) print a[j–] }’ file*

# if a line ends with a backslash, append the next line to it
# (fails if there are multiple lines ending with backslash…)
awk ‘/\\$/ {sub(/\\$/,”"); getline t; print $0 t; next}; 1′ file*

# print and sort the login names of all users
awk -F “:” ‘{ print $1 | “sort” }’ /etc/passwd

# print the first 2 fields, in opposite order, of every line
awk ‘{print $2, $1}’ file

# switch the first 2 fields of every line
awk ‘{temp = $1; $1 = $2; $2 = temp}’ file

# print every line, deleting the second field of that line
awk ‘{ $2 = “”; print }’

# print in reverse order the fields of every line
awk ‘{for (i=NF; i>0; i–) printf(”%s “,i);printf (”\n”)}’ file

# remove duplicate, consecutive lines (emulates “uniq”)
awk ‘a !~ $0; {a=$0}’

# remove duplicate, nonconsecutive lines
awk ‘! a[$0]++’ # most concise script
awk ‘!($0 in a) {a[$0];print}’ # most efficient script

# concatenate every 5 lines of input, using a comma separator
# between fields
awk ‘ORS=%NR%5?”,”:”\n”‘ file

SELECTIVE PRINTING OF CERTAIN LINES:

# print first 10 lines of file (emulates behavior of “head”)
awk ‘NR 1{exit};1′

# print the last 2 lines of a file (emulates “tail -2″)
awk ‘{y=x “\n” $0; x=$0};END{print y}’

# print the last line of a file (emulates “tail -1″)
awk ‘END{print}’

# print only lines which match regular expression (emulates “grep”)
awk ‘/regex/’

# print only lines which do NOT match regex (emulates “grep -v”)
awk ‘!/regex/’

# print the line immediately before a regex, but not the line
# containing the regex
awk ‘/regex/{print x};{x=$0}’
awk ‘/regex/{print (x==”" ? “match on line 1″ : x)};{x=$0}’

# print the line immediately after a regex, but not the line
# containing the regex
awk ‘/regex/{getline;print}’

# grep for AAA and BBB and CCC (in any order)
awk ‘/AAA/; /BBB/; /CCC/’

# grep for AAA and BBB and CCC (in that order)
awk ‘/AAA.*BBB.*CCC/’

# print only lines of 65 characters or longer
awk ‘length > 64′

# print only lines of less than 65 characters
awk ‘length

# print section of file from regular expression to end of file
 awk '/regex/,0'
 awk '/regex/,EOF'

 # print section of file based on line numbers (lines 8-12, inclusive)
 awk 'NR==8,NR==12'

 # print line number 52
 awk 'NR==52'
 awk 'NR==52 {print;exit}'          # more efficient on large files

 # print section of file between two regular expressions (inclusive)
 awk '/Iowa/,/Montana/'             # case sensitive


SELECTIVE DELETION OF CERTAIN LINES:

 # delete ALL blank lines from a file (same as "grep '.' ")
 awk NF
 awk '/./'