使用shell脚本从文件中提取唯一的行块

Question

从文件中提取行块时，我遇到的问题很少。 考虑以下两个文件

File-1
1.20/abc/this_is_test_1
perl/RRP/RRP-1.30/JEDI/JEDIExportSuccess2
exec perl/RRP/RRP-1.30/JEDI/CommonReq/confAbvExp
perl/LRP/BaseLibs/close-MMM
exec perl/LRP/BaseLibs/launchLRPCHURRTA("TYRE")
this/or/that

File-2
exec 1.20/setup/testird
exec 1.20/sql/temp/Test3
exec 1.20/setup/testxyz
exec 1.20/sql/fondle_opr_sql_labels
exec 1.20/setup/testird
exec 1.20/sql/temp/NEWTest
exec 1.20/setup/testxyz
exec 1.20/sql/fondle_opr_sql_xfer
exec 1.20/setup/testird
exec 1.20/sql/set_sec_not_0
exec 1.20/setup/testpqr
exec 1.20/sql/sql_ba_statuses_on_mult
exec perl/RRP/SetupReq/testdef_ijk
exec perl/RRP/RRP-1.30/JEDI/SetupReq/confAbvExp
exec perl/RRP/RRP-1.30/JEDI/JEDIExportSuccess1
exec perl/RRP/SetupReq/testdef_ijk
exec perl/RRP/RRP-1.30/JEDI/SetupReq/confAbvExp
exec perl/RRP/RRP-1.30/JEDI/JEDIExportSuccess2
exec perl/RRP/SetupReq/testdef_ijk
exec perl/RRP/RRP-1.30/JEDI/SetupReq/confAbvExp
exec perl/RRP/RRP-1.30/JEDI/JEDIExportSuccess3
exec 1.20/setup/testird
exec 1.20/sql/sqlmenu_purr_labl
exec 1.20/sql/est_time_at_non_drp_plc
exec 1.20/sql/half_Brd_Supply_mix_single
exec 1.20/setup/testird
exec 1.20/sql/temp/Test
exec 1.20/setup/testird
exec 1.20/sql/temp/Test2
exec perl/LRP/SetupReq/testird_LRP("LRP")
exec perl/BaseLibs/launch_client("LRP")
exec perl/LRP/LRP-classic-4.14/churrip/chorSingle
exec perl/LRP/BaseLibs/setupLRPMMMTab
exec perl/LRP/BaseLibs/launchMMM
exec perl/LRP/BaseLibs/launchLRPCHURRTA("TYRE")
#PAUSE Expand Churrip tree view & open all nodes
exec perl/LRP/LRP-classic-4.14/Corrugator/multipleSeriesWeb
exec perl/BaseLibs/ShutApp("Self Destruction System")
exec perl/LRP/BaseLibs/close-MMM
exec 1.20/setup/testmiddle
exec 1.20/sql/collective_reads
exec 1.20/setup/testinit
exec 1.20/abc/this_is_test_1
exec 1.20/abc/this_is_test_1
exec perl/LRP/SetupReq/abcDEF
exec perl/BaseLibs/launch_client("sqlC","LRP")
exec perl/LRP/LRP-perl-4.20/fireTrigger

现在，对于File-1中的每一行，我想从File-2中提取相关的行块。 File-2中的块定义如下

exec 1.20/setup/xxxxx
blah blah blah
blah blah blah
.
.
.
all lines till next setup line is found

例如

exec 1.20/setup/testinit
exec 1.20/abc/this_is_test_1
exec 1.20/abc/this_is_test_1

要么

exec perl/LRP/SetupReq/xxxxx
blah blah blah
blah blah blah
.
.
.
all lines till next setup line is found

例如

exec perl/LRP/SetupReq/testird_LRP("LRP")
exec perl/BaseLibs/launch_client("LRP")
exec perl/LRP/LRP-classic-4.14/churrip/chorSingle
exec perl/LRP/BaseLibs/setupLRPMMMTab
exec perl/LRP/BaseLibs/launchMMM
exec perl/LRP/BaseLibs/launchLRPCHURRTA("TYRE")
#PAUSE Expand Churrip tree view & open all nodes
exec perl/LRP/LRP-classic-4.14/Corrugator/multipleSeriesWeb
exec perl/BaseLibs/ShutApp("Self Destruction System")
exec perl/LRP/BaseLibs/close-MMM

到目前为止，我已经设法通过以下脚本从File-2中提取相关块

Shell Script
#set -x
FLBATCHLIST=$1
BATCHFILE=$2

TEMPDIR="/usr/tmp/tempBatchDir"
rm -rf $TEMPDIR/*

WORKFILE="$TEMPDIR/failedTestList.txt"
CPBATCHFILE="$TEMPDIR/orig.test"
TESTSETFILE="$TEMPDIR/testset.txt"
TEMPFILE="$TEMPDIR/temp.txt"
DIFFFILE="$TEMPDIR/diff.txt"

#Output
FAILEDBATCH="$TEMPDIR/FailedBatch.test"
LOGFILE="$TEMPDIR/log.txt"

createBatch ()
{

TESTNAME=$1
#First process the $CPBATCHFILE to not have any blank lines, leading and trailing whitespaces
# delete BOTH leading and trailing whitespace from each line and blank lines from file
sed -i 's/^[[:space:]]*//;s/[[:space:]]*$//g;/^$/d' $CPBATCHFILE
FOUND=0
STATUS=1
while [ $STATUS -ne "0" ]
do
        if [ ! -s $CPBATCHFILE ]; then
                echo "$CPBATCHFILE is empty" >> $LOGFILE
                STATUS=0
        fi
        awk '/[Ss]etup.*[Tt]est/ || /perl\/[[:alpha:]]*\/[Ss]etup[rR]eq/{if(b) exit; else b=1}1' $CPBATCHFILE > $TESTSETFILE
        grep -i "$TESTNAME$" $TESTSETFILE >> $LOGFILE 2>&1
        if [ $? -eq "0" ]; then
                echo "test found" >> $LOGFILE
                cat $TESTSETFILE >> $FAILEDBATCH
                FOUND=1
        fi
        TSTFLLINES=`wc -l < $TESTSETFILE`
        CPBTCHLINES=`wc -l < $CPBATCHFILE`
        DIFF=`expr $CPBTCHLINES - $TSTFLLINES`
        tail -n $DIFF $CPBATCHFILE > $DIFFFILE
        mv $DIFFFILE $CPBATCHFILE
done

if [ $FOUND -eq 0 ]; then
        echo $TESTNAME > $TEMPDIR/test.txt
        ABSTEST=$(echo $TESTNAME | sed 's/\\//g')
        echo "FATAL ERROR: Test \"$ABSTEST\" not found in batch" | tee -a $LOGFILE
fi

}

####STARTS HERE####
mkdir -p $TEMPDIR
#cat  $TEMPDIR/test.txt
#FLBATCHLIST="$TEMPDIR/test.txt"
# delete run, BOTH leading and trailing whitespace and blank lines from file
sed 's/^[eE][xX][eE][cC]//g;s/^[[:space:]]*//;s/[[:space:]]*$//g;/^$/d' $FLBATCHLIST > $WORKFILE

# escaping special characters like '\' and '.' in the path names for better grepping
sed -i 's/\([\/\.\"]\)/\\\1/g' $WORKFILE

for fltest in $(cat $WORKFILE)
do
        echo $fltest >> $LOGFILE
        cp $BATCHFILE $CPBATCHFILE
        createBatch $fltest
done

sed -i 's/\//\\/g' $FAILEDBATCH
## Clean up
cp $FAILEDBATCH .

这个脚本的问题是

1. 它为File-1的每一行遍历File-2需要一些时间。 我想知道是否有更好的解决方案，我只需要遍历File-2一次。

2. 该脚本确实解决了我的问题，但我留下的文件中有重复的行块。 我想知道有没有办法删除重复的行块。

这是我执行脚本时的输出

exec 1.20\setup\testinit
exec 1.20\abc\this_is_test_1
exec 1.20\abc\this_is_test_1
exec perl\RRP\SetupReq\testdef_ijk
exec perl\RRP\RRP-1.30\JEDI\SetupReq\confAbvExp
exec perl\RRP\RRP-1.30\JEDI\JEDIExportSuccess2
exec perl\RRP\SetupReq\testdef_ijk
exec perl\RRP\RRP-1.30\JEDI\SetupReq\confAbvExp
exec perl\RRP\RRP-1.30\JEDI\JEDIExportSuccess1
exec perl\RRP\SetupReq\testdef_ijk
exec perl\RRP\RRP-1.30\JEDI\SetupReq\confAbvExp
exec perl\RRP\RRP-1.30\JEDI\JEDIExportSuccess2
exec perl\RRP\SetupReq\testdef_ijk
exec perl\RRP\RRP-1.30\JEDI\SetupReq\confAbvExp
exec perl\RRP\RRP-1.30\JEDI\JEDIExportSuccess3
exec perl\LRP\SetupReq\testird_LRP("LRP")
exec perl\BaseLibs\launch_client("LRP")
exec perl\LRP\LRP-classic-4.14\churrip\chorSingle
exec perl\LRP\BaseLibs\setupLRPMMMTab
exec perl\LRP\BaseLibs\launchMMM
exec perl\LRP\BaseLibs\launchLRPCHURRTA("TYRE")
#PAUSE Expand Churrip tree view & open all nodes
exec perl\LRP\LRP-classic-4.14\Corrugator\multipleSeriesWeb
exec perl\BaseLibs\ShutApp("Self Destruction System")
exec perl\LRP\BaseLibs\close-MMM
exec perl\LRP\SetupReq\testird_LRP("LRP")
exec perl\BaseLibs\launch_client("LRP")
exec perl\LRP\LRP-classic-4.14\churrip\chorSingle
exec perl\LRP\BaseLibs\setupLRPMMMTab
exec perl\LRP\BaseLibs\launchMMM
exec perl\LRP\BaseLibs\launchLRPCHURRTA("TYRE")
#PAUSE Expand Churrip tree view & open all nodes
exec perl\LRP\LRP-classic-4.14\Corrugator\multipleSeriesWeb
exec perl\BaseLibs\ShutApp("Self Destruction System")
exec perl\LRP\BaseLibs\close-MMM

我尝试通过网络搜索我的答案，但无法找到符合我需求的答案。

给定File-1和File-2这是我希望我的脚本输出的内容（我列出了我期望FILE-1中每行的输出）

For line "1.20/abc/this_is_test_1" in FILE-1
Output
exec 1.20/setup/testinit
exec 1.20/abc/this_is_test_1
exec 1.20/abc/this_is_test_1

For line "perl/RRP/RRP-1.30/JEDI/JEDIExportSuccess2" in FILE-1
Output
exec perl/RRP/SetupReq/testdef_ijk
exec perl/RRP/RRP-1.30/JEDI/SetupReq/confAbvExp
exec perl/RRP/RRP-1.30/JEDI/JEDIExportSuccess2

For line "exec perl/RRP/RRP-1.30/JEDI/CommonReq/confAbvExp" in FILE-1
Output
do nothing as there is no line matching this is in FILE-2

For line "perl/LRP/BaseLibs/close-MMM" in FILE-1
Output
exec perl/LRP/SetupReq/testird_LRP("LRP")
exec perl/BaseLibs/launch_client("LRP")
exec perl/LRP/LRP-classic-4.14/churrip/chorSingle
exec perl/LRP/BaseLibs/setupLRPMMMTab
exec perl/LRP/BaseLibs/launchMMM
exec perl/LRP/BaseLibs/launchLRPCHURRTA("TYRE")
#PAUSE Expand Churrip tree view & open all nodes
exec perl/LRP/LRP-classic-4.14/Corrugator/multipleSeriesWeb
exec perl/BaseLibs/ShutApp("Self Destruction System")
exec perl/LRP/BaseLibs/close-MMM    

For line "exec perl/LRP/BaseLibs/launchLRPCHURRTA("TYRE")" in FILE-1
Output
Do nothing as it would generate the same black as line "perl/LRP/BaseLibs/close-MMM" in FILE-1 did

For Line "this/or/that" in FILE-1
Output
Do nothing as there is no line matching this is in FILE-2

所以我的最终输出应该类似（块的顺序无关紧要）

exec 1.20/setup/testinit
exec 1.20/abc/this_is_test_1
exec 1.20/abc/this_is_test_1

exec perl/RRP/SetupReq/testdef_ijk
exec perl/RRP/RRP-1.30/JEDI/SetupReq/confAbvExp
exec perl/RRP/RRP-1.30/JEDI/JEDIExportSuccess2

exec perl/LRP/SetupReq/testird_LRP("LRP")
exec perl/BaseLibs/launch_client("LRP")
exec perl/LRP/LRP-classic-4.14/churrip/chorSingle
exec perl/LRP/BaseLibs/setupLRPMMMTab
exec perl/LRP/BaseLibs/launchMMM
exec perl/LRP/BaseLibs/launchLRPCHURRTA("TYRE")
#PAUSE Expand Churrip tree view & open all nodes
exec perl/LRP/LRP-classic-4.14/Corrugator/multipleSeriesWeb
exec perl/BaseLibs/ShutApp("Self Destruction System")
exec perl/LRP/BaseLibs/close-MMM

如果有人能给我一些关于如何继续的指示，那将是非常好的。 是的，我忘了提，这不是一个功课问题:-)。

非常感谢

Answer 1

如果行顺序无关紧要，您可以通过以下方式从文件中删除重复项：

sort filename | uniq

为了找到两个文件中存在哪些行，我使用了一个创建哈希（或关联数组，如果你愿意）的perl脚本。 然后我通过文件A扫描，将每行添加到哈希，使用行作为键，并将值设置为1.然后我对文件A执行相同操作，但将值设置为2，如果键已经存在，我添加了2。 结果只会遍历每个文件一次，最后我知道如果密钥的值为1，它只存在于文件A中，如果它的值为2，它只存在于文件B中，并且如果它的值为3，则两者都存在。

编辑：我发现了一些项目中存在的perl代码，正如我上面所描述的那样。 在这段代码中，我只是在差异之后，但应该很容易根据您的需要进行修改

my %found;
foreach my $item (@qlist) { $found{$item} += 2 };
foreach my $item (@xlist) { $found{$item} += 1 };

foreach my $found (keys(%found))
{
  if    ($found{$found} == 3)
  {
    # It's in both files. Not doing anything.
  }
  elsif ($found{$found} == 2)
  {
    print "$found found in the QC-list, but not the x-list.\n";
  }
  elsif ($found{$found} == 1)
  {
    print "$found found in the x-list, but not the QC-list.\n";
  }
}

Answer 2

以下假设“setup”行对于每个块是唯一的。 我们使用这一行作为关联数组的关键，它跟踪我们已经打印的块。

第一行脚本将第一个文件读入一个名为regex的变量，该变量从第一个文件中收集我们想要匹配的行（成语NR==FNR表示当前文件的行号等于行号的行号）收集所有文件，也就是说，只有当我们从参数列表中读取第一个文件时才会这样。 我应该希望脚本的其余部分相当简单。

awk 'NR==FNR { gsub(/\//,"\\/"); regex = regex sep $0; sep = "|" ; next}
    /[Ss]etup/ { label = $0; printing = 0; collected = nl = "" }
    { collected = collected nl $0; nl=RS }
    $0 ~ regex { if(!printed[label]) {
        printed[label] = printing = 1; print collected } }
    printing { print }' File-1 File-2

如果“设置”行不一定是唯一的，也许您可​​以使用collected的值作为键。

这应该（我希望）对File-1与File-2的相同块匹配的多行是强健的。

我知道我在评论中暗示了一个sed解决方案，但事实证明这是awk感觉更自然的问题。 当然，它可以用Perl或Python完成，也可以用你做的。

Answer 3

感谢@tripleee和@Jarmund的建议。 根据您的意见，我终于能够找到问题的解决方案。 我从关联数组中得到提示，为每个块创建唯一键，所以这就是我所做的

• 取file-2并将每个块转换为单行

  awk'/ [Ss] etup。 [Tt] est / || / perl / [[：alpha：]] / [Ss] etup [Rr] eq / {if（b）退出; 否则b = 1} 1'file-2> $ TESTSETFILE cat $ TESTSETFILE | sed'：a; N; $！ba; s / \\ n // g; s / // g'>> $ SINGLELINEFILE

• 现在，此文件中的每一行都是唯一的条目

• 在此之后，我使用grep为File-1中的每一行，并找到相应的块（现在转换为单行）
• 然后我使用awk或sort -u在我的解决方案文件中查找唯一条目

也许这个解决方案并不是最好的，但它比前一个快得多。

这是我的新脚本

FLBATCHLIST=$1
BATCHFILE=$2

TEMPDIR="./tempBatchdir"
rm -rf $TEMPDIR/*
WORKFILE="$TEMPDIR/failedTestList.txt"
CPBATCHFILE="$TEMPDIR/orig.test"
TESTSETFILE="$TEMPDIR/testset.txt"
DIFFFILE="$TEMPDIR/diff.txt"
SINGLELINEFILE="$TEMPDIR/singleline.txt"
TEMPFILE="$TEMPDIR/temp.txt"
#Output
FAILEDBATCH="$TEMPDIR/FailedBatch.test"
LOGFILE="$TEMPDIR/log.txt"

convertSingleLine ()
{
sed -i 's/^[[:space:]]*//;s/[[:space:]]*$//g;/^$/d' $CPBATCHFILE
STATUS=1
while [ $STATUS -ne "0" ]
do
        if [ ! -s $CPBATCHFILE ]; then
                echo "$CPBATCHFILE is empty" >> $LOGFILE
                STATUS=0
        fi
        awk '/[Ss]etup.*[Tt]est/ || /perl\/[[:alpha:]]*\/[Ss]etup[Rr]eq/{if(b) exit; else b=1}1' $CPBATCHFILE > $TESTSETFILE
        cat $TESTSETFILE | sed ':a;N;$!ba;s/\n//g;s/ //g' >> $SINGLELINEFILE
        echo "**" >> $SINGLELINEFILE
        TSTFLLINES=`wc -l < $TESTSETFILE`
        CPBTCHLINES=`wc -l < $CPBATCHFILE`
        DIFF=`expr $CPBTCHLINES - $TSTFLLINES`
        tail -n $DIFF $CPBATCHFILE > $DIFFFILE
        mv $DIFFFILE $CPBATCHFILE
done
}

####STARTS HERE####
mkdir -p $TEMPDIR

sed 's/^[eE][xX][eE][cC]//g;s/^[[:space:]]*//;s/[[:space:]]*$//g;/^$/d' $FLBATCHLIST > $WORKFILE
sed -i 's/\([\/\.\"]\)/\\\1/g' $WORKFILE

cp $BATCHFILE $CPBATCHFILE
convertSingleLine

for fltest in $(cat $WORKFILE)
do
        echo $fltest >> $LOGFILE
        grep "$fltest" $SINGLELINEFILE >> $FAILEDBATCH
        if [ $? -eq "0" ]; then
                echo "TEST FOUND" >> $LOGFILE
        else
                ABSTEST=$(echo $fltest | sed 's/\\//g')
                echo "FATAL ERROR: Test \"$ABSTEST\" not found in $BATCHFILE" | tee -a $LOGFILE
        fi
done

awk '!x[$0]++' $FAILEDBATCH > $TEMPFILE
mv $TEMPFILE $FAILEDBATCH

sed -i "s/exec/\\nexec /g;s/#/\\n#/g" $FAILEDBATCH
sed -i '1d;s/\//\\/g' $FAILEDBATCH

这是输出

$ crflbatch file-1 file-2
FATAL ERROR: Test "perl/RRP/RRP-1.30/JEDI/CommonReq/confAbvExp" not found in file-2
FATAL ERROR: Test "this/or/that" not found in file-2

$ cat tempBatchdir/FailedBatch.test
exec 1.20\setup\testinit
exec 1.20\abc\this_is_test_1
exec 1.20\abc\this_is_test_1

exec perl\RRP\SetupReq\testdef_ijk
exec perl\RRP\RRP-1.30\JEDI\SetupReq\confAbvExp
exec perl\RRP\RRP-1.30\JEDI\JEDIExportSuccess2

exec perl\LRP\SetupReq\testird_LRP("LRP")
exec perl\BaseLibs\launch_client("LRP")
exec perl\LRP\LRP-classic-4.14\churrip\chorSingle
exec perl\LRP\BaseLibs\setupLRPMMMTab
exec perl\LRP\BaseLibs\launchMMM
exec perl\LRP\BaseLibs\launchLRPCHURRTA("TYRE")
#PAUSEExpandChurriptreeview&openallnodes
exec perl\LRP\LRP-classic-4.14\Corrugator\multipleSeriesWeb
exec perl\BaseLibs\ShutApp("SelfDestructionSystem")
exec perl\LRP\BaseLibs\close-MMM
$