使用shell腳本從文件中提取唯一的行塊

Question

從文件中提取行塊時，我遇到的問題很少。 考慮以下兩個文件

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

現在，對於File-1中的每一行，我想從File-2中提取相關的行塊。 File-2中的塊定義如下

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

到目前為止，我已經設法通過以下腳本從File-2中提取相關塊

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 .

這個腳本的問題是

1. 它為File-1的每一行遍歷File-2需要一些時間。 我想知道是否有更好的解決方案，我只需要遍歷File-2一次。

2. 該腳本確實解決了我的問題，但我留下的文件中有重復的行塊。 我想知道有沒有辦法刪除重復的行塊。

這是我執行腳本時的輸出

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

我嘗試通過網絡搜索我的答案，但無法找到符合我需求的答案。

給定File-1和File-2這是我希望我的腳本輸出的內容（我列出了我期望FILE-1中每行的輸出）

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

所以我的最終輸出應該類似（塊的順序無關緊要）

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

如果有人能給我一些關於如何繼續的指示，那將是非常好的。 是的，我忘了提，這不是一個功課問題:-)。

非常感謝

Answer 1

如果行順序無關緊要，您可以通過以下方式從文件中刪除重復項：

sort filename | uniq

為了找到兩個文件中存在哪些行，我使用了一個創建哈希（或關聯數組，如果你願意）的perl腳本。 然后我通過文件A掃描，將每行添加到哈希，使用行作為鍵，並將值設置為1.然后我對文件A執行相同操作，但將值設置為2，如果鍵已經存在，我添加了2。 結果只會遍歷每個文件一次，最后我知道如果密鑰的值為1，它只存在於文件A中，如果它的值為2，它只存在於文件B中，並且如果它的值為3，則兩者都存在。

編輯：我發現了一些項目中存在的perl代碼，正如我上面所描述的那樣。 在這段代碼中，我只是在差異之后，但應該很容易根據您的需要進行修改

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

以下假設“setup”行對於每個塊是唯一的。 我們使用這一行作為關聯數組的關鍵，它跟蹤我們已經打印的塊。

第一行腳本將第一個文件讀入一個名為regex的變量，該變量從第一個文件中收集我們想要匹配的行（成語NR==FNR表示當前文件的行號等於行號的行號）收集所有文件，也就是說，只有當我們從參數列表中讀取第一個文件時才會這樣。 我應該希望腳本的其余部分相當簡單。

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“設置”行不一定是唯一的，也許您可​​以使用collected的值作為鍵。

這應該（我希望）對File-1與File-2的相同塊匹配的多行是強健的。

我知道我在評論中暗示了一個sed解決方案，但事實證明這是awk感覺更自然的問題。 當然，它可以用Perl或Python完成，也可以用你做的。

Answer 3

感謝@tripleee和@Jarmund的建議。 根據您的意見，我終於能夠找到問題的解決方案。 我從關聯數組中得到提示，為每個塊創建唯一鍵，所以這就是我所做的

• 取file-2並將每個塊轉換為單行

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

• 現在，此文件中的每一行都是唯一的條目

• 在此之后，我使用grep為File-1中的每一行，並找到相應的塊（現在轉換為單行）
• 然后我使用awk或sort -u在我的解決方案文件中查找唯一條目

也許這個解決方案並不是最好的，但它比前一個快得多。

這是我的新腳本

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

這是輸出

$ 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
$