awk干货汇总

awk ‘{pattern + action}’ 或者 awk ‘pattern {action}’

awk [options] 'script' var=value file(s)
awk [options] -f scriptfile var=value file(s)

awk 'BEGIN{ i=0 } { i++ } END{ print i }' filename
awk "BEGIN{ i=0 } { i++ } END{ print i }" filename

awk 'BEGIN{ commands } pattern{ commands } END{ commands }' file

VAR=10000
echo | awk -v VARIABLE=$VAR '{ print VARIABLE }'

var1="aaa"
var2="bbb"
echo | awk '{ print v1,v2 }' v1=$var1 v2=$var2

awk '{ print v1,v2 }' v1=$var1 v2=$var2 filename

awk 'BEGIN{a="100testa";if(a ~ /^100*/){print "ok";}}'
ok

for(变量 in 数组)
{语句}

for(变量;条件;表达式)
{语句}

while(表达式)
    {语句}

do
{语句} while(条件)

awk 'BEGIN{
        Array[1]="sun"
        Array[2]="kai"
        Array["first"]="www"
        Array["last"]="name"
        Array["birth"]="1987"

        info = "it is a test";
        lens = split(info,tA," ");
        for(item in tA)
        {print tA[item];}
        for(i=1;i<=lens;i++)
        {print tA[i];}
        print length(tA[lens]);
        } {
        print "item in array";
        for(item in Array) {print Array[item]};
        print "print in i++";
        for(i=1;i<=length(Array);i++) {print Array[i]};
        }'

#错误的判断方法，awk数组是关联数组，只要通过数组引用它的KEY，就会自动创建。
awk 'BEGIN{
    tB["a"]="a1";
    tB["b"]="b1";
    if(tB["c"]!="1"){   #tB["c"]没有定义，但是循环的时候会输出
        print "no found";
    };
    for(k in tB){
        print k,tB[k];
    }}'

#正确的判定方法：使用 if ( key in array) 判断数组中是否包含 键值
awk 'BEGIN{
        tB["a"]="a1";
        tB["b"]="b1";
        if( "c" in tB){
            print "ok";
        };
        for(k in tB){
            print k,tB[k];
        }}'

awk 'BEGIN{
        tB["a"]="a1";
        tB["b"]="b1";
        delete tB["a"];
        for(k in tB){
            print k,tB[k];
        }}'

$ awk 'BEGIN {
  PI = 3.14159265
  x = -10
  y = 10
  result = atan2 (y,x) * 180 / PI;

  printf "The arc tangent for (x=%f, y=%f) is %f degrees\n", x, y, result
}'

$ awk 'BEGIN {
  PI = 3.14159265
  param = 60
  result = cos(param * PI / 180.0);

  printf "The cosine of %f degrees is %f.\n", param, result
}'

$ awk 'BEGIN {
  PI = 3.14159265
  param = 30.0
  result = sin(param * PI /180)

  printf "The sine of %f degrees is %f.\n", param, result
}'

$ awk 'BEGIN {
  param = 5
  result = exp(param);

  printf "The exponential value of %f is %f.\n", param, result
}'

$ awk 'BEGIN {
  param = 5.5
  result = log (param)

  printf "log(%f) = %f\n", param, result
}'

$ awk 'BEGIN {
  param = 1024.0
  result = sqrt(param)

  printf "sqrt(%f) = %f\n", param, result
}'

$ awk 'BEGIN {
  param = 5.12345
  result = int(param)

  print "Truncated value =", result
}'

$ awk 'BEGIN {
  print "Random num1 =" , rand()
  print "Random num2 =" , rand()
  print "Random num3 =" , rand()
}'

$ awk 'BEGIN {
  param = 10

  printf "srand() = %d\n", srand()
  printf "srand(%d) = %d\n", param, srand(param)
}'

$ awk 'BEGIN{info="this is a test2012test!";gsub(/[0-9]+/,"||",info);print info}'

$ awk 'BEGIN {
    str = "Hello, World"

    print "String before replacement = " str

    sub("World", "Jerry", str)

    print "String after replacement = " str
}'

$ awk 'BEGIN {
    str = "Hello, World !!!"
    subs = substr(str, 1, 5)

    print "Substring = " subs
}'

$ awk 'BEGIN {
    str = "One Two Three"
    subs = "Two"

    ret = index(str, subs)

    printf "Substring \"%s\" found at %d location.\n", subs, ret
}'

$ awk 'BEGIN {
    str = "Hello, World !!!"

    print "Length = ", length(str)
}'

$ awk 'BEGIN {
    str = "Hello, World !!!"
    subs = substr(str, 1, 5)

    print "Substring = " subs
}'

$ awk 'BEGIN {
    str = "One Two Three"
    subs = "Two"

    ret = match(str, subs)

    printf "Substring \"%s\" found at %d location.\n", subs, ret
}'

$ awk 'BEGIN {
    str = "One,Two,Three,Four"

    split(str, arr, ",")

    print "Array contains following values"

    for (i in arr) {
        print arr[i]
    }
}'

$ awk 'BEGIN {
    str = "HELLO, WORLD !!!"

    print "Lowercase string = " tolower(str)
}'

$ awk 'BEGIN {
    str = "hello, world !!!"

    print "Uppercase string = " toupper(str)
}'

$ awk 'BEGIN {
    print "Decimal num = " strtonum("123")
    print "Octal num = " strtonum("0123")
    print "Hexadecimal num = " strtonum("0x123")
}'

$ awk 'BEGIN {
    str = sprintf("%s", "Hello, World !!!")

    print str
}'

$ awk 'BEGIN {
    print "Number of seconds since the Epoch = " mktime("2014 12 14 30 20 10")
}'

$ awk 'BEGIN {
    print strftime("Time = %m/%d/%Y %H:%M:%S", systime())
}'

awk 'BEGIN{now=systime();print now}'

$ awk 'BEGIN { ret = system("date"); print "Return value = " ret }'

awk '{print $0 }' col_print.txt

cat col_print.txt  | awk '{print $NF }'

cat col_print.txt  | awk '{print $(NF-1)}'

cat col_print.txt  | awk '{print  NF}'

cat  col_print.txt | awk '{print $2,$3}'

#!/bin/bash

echo "用户修改区－开始"
#要替换的源代码所在的根目录,该脚本文件与根目录处于同级文件夹
ROOTFOLDER="MyCode" # KYSecurityDefenseDemo

echo "当前工程名："$ROOTFOLDER

BUILD_VERSION="3.8.1"

echo "当前版本："$BUILD_VERSION

#要排除的文件夹,例如demo中用到的第三方库AFNetworking，pods的第三方库等
EXCLUDE_DIR=" --exclude-dir=Pods --exclude-dir=buildAppstore --exclude-dir=Carthage --exclude-dir=Images.xcassets  --exclude-dir=Assets.xcassets  --exclude-dir=Certificates --exclude-dir=fastlane --exclude-dir=fastlanelog --exclude-dir=${ROOTFOLDER}Tests --exclude-dir=${ROOTFOLDER}Tests"

echo "要排除的文件夹 "${EXCLUDE_DIR}

ROOT_NEW_DIR=$ROOTFOLDER"_"$BUILD_VERSION

if [ ! -d $ROOT_NEW_DIR ]; then
mkdir -p -m 755 $ROOT_NEW_DIR
echo "创建工程目录 "$ROOT_NEW_DIR" 成功"
fi

cp  -Rf  ${ROOTFOLDER}/*  ${ROOT_NEW_DIR}/

ROOTFOLDER=$ROOTFOLDER"_"$BUILD_VERSION

echo "用户修改区－结束"

#自定义的保留关键字,相当与白名单，添加到该文件中，一行一个，加入该文件的关键字将不被混淆;如工程中自定义的文件夹名称
RESCUSTOM="resCustom.txt"

#保留关键字文件不可删除
RESERVEDKEYWORDS="./reskeys.txt"
#最终的保留关键字＝保留关键字＋文件名
RESKEYSALL="./reskeysall.txt"
#提取的所有关键字
SOURCECODEKEYWORDS="./srckeys.txt"
#过滤后，最终要替换的关键字，混淆结束后，不删除，用于bug分析
REPLACEKEYWORDS="./replacekeys.txt"
#过滤后，最终要替换的文件名，混淆结束后，不删除，用于bug分析
REPLACEFILES="./replacefiles.txt"

#删除已经存在的临时文件
rm -f $SOURCECODEKEYWORDS
rm -f $REPLACEKEYWORDS
rm -f $REPLACEFILES
rm -f $RESKEYSALL
rm -f temp.res

#提取文件名列表
echo '' > f.list
find $ROOTFOLDER -type f | sed "/\/\./d" >f.list
#根据要排除的文件目录，将文件列表分离
#Exclude=$(echo $EXCLUDE_DIR | sed "s/--exclude-dir\=//g" |sed "s/ $//g" | sed "s/[*.]//g" | sed "s/ /\\\|/g")
Exclude=$(echo $EXCLUDE_DIR | sed "s/--exclude-dir\=//g" |sed "s/ $//g" | sed "s/ /\\\|/g")
#保留文件列表
if [ $Exclude ]; then
    rm -f f_res.list
	cat f.list | grep "$Exclude" >f_res.list
fi

#混淆文件列表
rm -f f_rep.list
cat f.list | grep -v "$Exclude" >f_rep.list
#rm -f f.list

echo "[step1] - 提取文件名"
rm -f filter_file.txt

AssignSrcKeys="my.txt"
if [ $AssignSrcKeys ]; then
    echo "[step2] - 指定关键字"
    cat `echo $AssignSrcKeys` | sed "/^$/d"| sort | uniq >$SOURCECODEKEYWORDS
else
    echo "[step2] - 提取要过滤的函数关键字"
    #提取文件名
    cat f_rep.list | awk -F/ '{print $NF;}'| awk -F. '{print $1;}' | sed "/^$/d" | sort | uniq >filter_file.txt
    #从源代码目录中提取要过滤的函数关键字
    rm -f filter_fun.txt
    grep -h -r -I  "^[-+]" $FIND_DIR $EXCLUDE_DIR $INCLUDE_DIR --include '*.[mh]' |sed "s/[+-]//g"|sed "s/[();,: *\^\/\{]/ /g"|sed "s/[ ]*</</"|awk '{split($0,b," ");print b[2];}'| sort|uniq |sed "/^$/d"|sed "/^init/d" >filter_fun.txt

    echo "[step3] - 提取要过滤的属性关键字"
    #从源代码目录中提取要过滤的属性关键字
    rm -f filter_property.txt
    grep -r -h -I  ^@property $FIND_DIR  $EXCLUDE_DIR $INCLUDE_DIR --include '*.[mh]' | sed "s/(.*)/ /g"  | sed "s/<.*>//g" |sed "s/[,*;]/ /g" | sed "s/IBOutlet/ /g" |awk '{split($0,s," ");print s[3];}'|sed "/^$/d" | sort |uniq >filter_property.txt

    echo "[step4] - 提取要过滤的类关键字"
    #从源代码目录中提取要过滤的类关键字
    rm -f filter_class.txt
    grep -h -r -I  "^@interface" $FIND_DIR  $EXCLUDE_DIR $INCLUDE_DIR  --include '*.[mh]' | sed "s/[:(]/ /" |awk '{split($0,s," ");print s[2];}'|sort|uniq >filter_class.txt

    echo "[step5] - 提取要过滤的协议关键字"
    #从源代码目录中提取要过滤的协议关键字
    grep -h -r -I  "^@protocol" $FIND_DIR  $EXCLUDE_DIR $INCLUDE_DIR  --include '*.[mh]'| sed "s/[\<,;].*$//g"|awk '{print $2;}' | sort | uniq >>filter_class.txt

    echo "[step6] - 合并要过滤的关键字"
    #合并要过滤的关键字，并重新排序过滤
    rm -f $SOURCECODEKEYWORDS
    cat filter_fun.txt filter_property.txt filter_class.txt filter_file.txt |sed "/^$/d" | sort | uniq >$SOURCECODEKEYWORDS
    rm -f filter_fun.txt
    rm -f filter_class.txt
    rm -f filter_file.txt
fi

echo "[step7] - 自动获取保留字，工程名等"
#自动获取保留字，工程名等
rm -f temp.res
cat `cat f_rep.list | grep project.pbxproj` | grep -w productName | sed "s/;//g"|awk '{print $NF;}'>temp.res
#提取要保留的文件名
cat f_res.list | awk -F/ '{print $NF;}'| awk -F. '{print $1;}' | sed "/^$/d" | sort | uniq >>temp.res
rm -f f_res.list
#合并自定义保留字
#判断自定义保留字文件是否存在，不存在即创建一个空的
if [ ! -f "$RESCUSTOM" ]; then 
touch "$RESCUSTOM" 
fi 
cat $RESERVEDKEYWORDS $RESCUSTOM temp.res | sort |uniq >$RESKEYSALL
#rm -f temp.res

echo "[step8] - 过滤保留字，将需要混淆的关键字加密后写入文件"
#过滤保留字，将需要混淆的关键字加密后写入文件
rm -f $REPLACEKEYWORDS
echo "REPLACEKEYWORDS"$REPLACEKEYWORDS
cat $SOURCECODEKEYWORDS | 
while read line
do
if grep $line $RESKEYSALL
then
echo filter1: $line
else
#使用md5对关键字进行加密
md5 -r -s $line  | sed s/\"//g >> $REPLACEKEYWORDS
fi
done
rm -f $SOURCECODEKEYWORDS

echo "[step9] - 开始混淆，替换源代码中的关键字为加密后的"
#开始混淆，替换源代码中的关键字为加密后的,防止开头为数字的情况
cat $REPLACEKEYWORDS |
while read line
do
var1=$(echo "$line"|awk '{print "z"$1"m"}')
var2=$(echo "$line"|awk '{print $2}')
underline1=$(echo "$line"|awk '{print "_z"$1"m"}')
underline2=$(echo "$line"|awk '{print "_"$2}')
rm -f rep.tmp
assignDir="./ZAInsurance_3.8.1/ZAInsurance/ZAIFoundation/ZAIManagers/SignInWithAppleID/ZAISignInWithAppleIDManager.m"
# 查找带关键字的那一行代码，输出到rep.tmp
if grep -r -n -I -w "[_]\{0,1\}$var2" $ROOTFOLDER $EXCLUDE_DIR $INCLUDE_DIR  --include="*.[mhc]" --include="*.mm" --include="*.pch" --include="*.storyboard" --include="*.xib" --include="*.nib" --include="contents" --include="*.pbxproj" >rep.tmp
then
cat rep.tmp |
while read -r l
do
#获取文件路径
v1=$(echo "$l"|cut -d: -f 1 )
#获取行号
v2=$(echo "$l"|cut -d: -f 2 )
#获取指定行数据
v3=$(sed -n "$v2"p "$v1")
##sed自带文件文本替换功能，不符合我们的期望，故放弃使用；有无适合的脚本命令，还希望脚本高手予以指点～
#sed -i '' ''"$v2"'s/'"$var2"'/'"$var1"'/g' $v1
#特殊字符转义替换，echo中 输出的变量 一定要加双引号！！！
v4=$(echo "$v3" | awk '{gsub(/"/, "\\\"", $0);gsub(/</, "\\\<", $0);gsub(/>/, "\\\>", $0);gsub(/\*/, "\\\*", $0);gsub(/\//, "\\\/", $0);gsub(/\[/, "\\\[", $0);gsub(/\]/, "\\\]", $0);gsub(/\{/, "\\\{", $0);gsub(/\}/, "\\\}", $0);gsub(/\&/, "\\\\\&", $0); print $0;}')

#判断是否包含双引号
quoteRes=$(echo $v4 | grep "\"")
if [[ "$quoteRes" != "" ]]; then
    #包含引号，引号中的不处理
    idx=0
    newV3=$(echo "$v3"|sed 's/\\n/|line|/'|sed  's/ /|nbsp|/')
    echo "$newV3"  | awk -F '\"' '{for(i=1;i<=NF;i++) print $i;}' |
    while read line
    do
    let idx+=1
    if [ $idx -gt 1 ]; then
    newStr=$newStr"\\\""
    fi
    #echo -E "line:$idx$line"
    if [ $(($idx%2)) -eq 1 ]; then
    newStr=$newStr$(./KYReplacewords.run "$line" "$var2" "$var1")
    newStr=$(./KYReplacewords.run "$newStr" "$underline2" "$underline1")
    else
    newStr=$newStr$line
    fi
    #整行替换
    sed -i '' "$v2"'s/.*/'"$newStr"'/g' "$v1"
    sed -i '' "$v2"'s/|nbsp|/ /g' "$v1"
    sed -i '' "$v2"'s/|line|/\\n/g' "$v1"
    done
else
    #单词替换
    var3=$(./KYReplacewords.run "$v4" "$var2" "$var1") 
    var3=$(./KYReplacewords.run "$var3" "$underline2" "$underline1") 
    #整行替换
    sed -i '' "$v2"'s/.*/'"$var3"'/g' "$v1"
fi

sed -i '' "$v2"'s/|_|/_/g' "$v1"

echo "step2:$l"
done
else
echo "step2:do not find:$var2"
fi
done
rm -f tmp.txt

echo "[step10] - 过滤保留字，用于属性设置函数混淆"
#过滤保留字，用于属性设置函数混淆，将需要混淆的关键字加密后写入文件
rm -f repProperty.txt
cat filter_property.txt | 
while read line
do
if grep $line $RESKEYSALL
then
echo filter1: $line
else
md5 -r -s $line  | sed s/\"//g >> repProperty.txt
fi
done
rm -f filter_property.txt

echo "[step11] - 开始混淆，替换属性前带下划线的地方"
#开始混淆，替换属性前带下划线的地方
cat repProperty.txt |
while read line
do
ar=(`echo "$line"|cut -f 1-2 -d " "`)
lastFind=`echo _${ar[1]}`
lastRep=`echo _z${ar[0]}m`
rm -f rep.tmp
if grep -r -n -I -w "$lastFind"  $ROOTFOLDER $EXCLUDE_DIR $INCLUDE_DIR   --include="*.[mhc]" --include="*.mm" --include="*.storyboard" --include="*.xib" >rep.tmp
then
cat rep.tmp |
while read l
do
v1=$(echo "$l"|cut -d: -f 1 )
v2=$(echo "$l"|cut -d: -f 2 )
sed -i '' ''"$v2"'s/'"$lastFind"'/'"$lastRep"'/g' $v1
echo "step3:"$l
done
else
echo "step3:do not find:"$lastFind
fi
done
rm -f rep.tmp

echo "[step12] - 开始混淆，替换属性设置函数"
#开始混淆，替换属性设置函数
cat repProperty.txt |
while read line
do
ar=(`echo "$line"|cut -f 1-2 -d " "`)
first=`echo ${ar[1]}|cut -c -1| sed "y/abcdefghijklmnopqrstuvwxyz/ABCDEFGHIJKLMNOPQRSTUVWXYZ/"`
second=`echo ${ar[1]}|cut -c 2-`
lastFind=`echo set$first$second`
lastRep=`echo setZ${ar[0]}m`
rm -f rep.tmp
if grep -r -n -I -w "$lastFind"  $ROOTFOLDER $EXCLUDE_DIR $INCLUDE_DIR  --include="*.[mhc]" --include="*.mm" --include="*.storyboard" --include="*.xib" >rep.tmp
then
cat rep.tmp |
while read l
do
v1=$(echo "$l"|cut -d: -f 1 )
v2=$(echo "$l"|cut -d: -f 2 )
sed -i '' ''"$v2"'s/'"$lastFind"'/'"$lastRep"'/g' $v1
echo "step3:"$l
done
else
echo "step3:do not find:"$lastFind
fi
done
rm -f rep.tmp
rm -f repProperty.txt

echo "###########################  恭喜您，代码混淆完成！  ###########################"
echo "###########################  运行混淆后的工程！  ###########################"

exit