linux - 如何使用 shell 脚本查找具有最大上下文长度的行号？

Question

我有一个文件，每一行都包含一个字符串。

我需要找到最大的 N 行。

我能够找到行数最多的行。例如，largest-1 可以通过以下方式找到:

cat ./test.txt | awk '{ 打印长度}' |排序-n |尾部-1

或者最大的 10 可以通过以下方式找到:

cat ./test.txt | awk '{ 打印长度}' |排序-n |尾部-10

但我还需要使用 shell 脚本并排获取这些行的行号。

感谢任何帮助。

输入文件中的一些行:

testTweeVaderOverLedenInNLPeriodeGeboorte ( ) { java . util . List < nl . bzk . brp . model . objecttype . operationeel . BetrokkenheidModel > echtgenoten = java . util . Arrays . asList ( maakBetrokkenheden ( 20110701 , 20120101 , ( ( short ) ( 1 ) ) ) , maakBetrokkenheden ( 20120201 , 20120504 , ( ( short ) ( 1 ) ) ) ) ; org . mockito . Mockito . when ( relatieRepository . haalOpBetrokkenhedenVanPersoon ( org . mockito . Matchers . any ( nl . bzk . brp . model . objecttype . operationeel . PersoonModel . class ) , org . mockito . Matchers . any ( nl . bzk . brp . dataaccess . selectie . RelatieSelectieFilter . class ) ) ) . thenReturn ( echtgenoten ) ; org . mockito . Mockito . when ( persoonRepository . haalPersoonOpMetAdresViaBetrokkenheid ( echtgenoten . get ( 0 ) ) ) . thenReturn ( echtgenoten . get ( 0 ) . getBetrokkene ( ) ) ; org . mockito . Mockito . when ( persoonRepository . haalPersoonOpMetAdresViaBetrokkenheid ( echtgenoten . get ( 1 ) ) ) . thenReturn ( echtgenoten . get ( 1 ) . getBetrokkene ( ) ) ; java . util . List < nl . bzk . brp . model . objecttype . operationeel . PersoonModel > kandidaten = kandidaatVader . bepaalKandidatenVader ( new nl . bzk . brp . model . objecttype . operationeel . PersoonModel ( new nl . bzk . brp . model . objecttype . bericht . PersoonBericht ( ) ) , new nl . bzk . brp . model . attribuuttype . Datum ( 20120506 ) ) ; org . mockito . Mockito . verify ( persoonRepository , org . mockito . Mockito . times ( 2 ) ) . haalPersoonOpMetAdresViaBetrokkenheid ( ( ( nl . bzk . brp . model . objecttype . operationeel . BetrokkenheidModel ) ( org . mockito . Matchers . any ( ) ) ) ) ; "<AssertPlaceHolder>" ; } size ( ) { return elementen . size ( ) ; }
putListeners ( ) { final java . util . concurrent . atomic . AtomicInteger counter = new java . util . concurrent . atomic . AtomicInteger ( ) ; map . addListener ( new LRUMap . ModificationListener < java . lang . String , java . lang . Integer > ( ) { @ java . lang . Override public void onPut ( java . lang . String key , java . lang . Integer value ) { counter . incrementAndGet ( ) ; } @ java . lang . Override public void onRemove ( java . lang . String key , java . lang . Integer value ) { } } ) ; map . put ( "hello" , 1 ) ; map . put ( "hello2" , 2 ) ; "<AssertPlaceHolder>" ; } put ( java . lang . String , org . codehaus . httpcache4j . List ) { return super . put ( new org . codehaus . httpcache4j . util . CaseInsensitiveKey ( key ) , value ) ; }
testStatelessKieSession ( ) { org . kie . api . runtime . StatelessKieSession ksession = ( ( org . kie . api . runtime . StatelessKieSession ) ( org . kie . spring . tests . KieSpringComponentScanTest . context . getBean ( "ksession1" ) ) ) ; "<AssertPlaceHolder>" ; }
shouldHashSha1 ( ) { java . lang . String [ ] correctHashes = new java . lang . String [ ] { "da39a3ee5e6b4b0d3255bfef95601890afd80709" , "5baa61e4c9b93f3f0682250b6cf8331b7ee68fd8" , "285d0c707f9644b75e1a87a62f25d0efb56800f0" , "a42ef8e61e890af80461ca5dcded25cbfcf407a4" } ; java . util . List < java . lang . String > result = new java . util . ArrayList ( ) ; for ( java . lang . String password : fr . xephi . authme . security . HashUtilsTest . GIVEN_PASSWORDS ) { result . add ( fr . xephi . authme . security . HashUtils . sha1 ( password ) ) ; } "<AssertPlaceHolder>" ; } contains ( java . lang . String ) { return ( getObject ( path ) ) != null ; }
equalsOtherNullReturnsFalse ( ) { com . rackspacecloud . blueflood . types . BluefloodCounterRollup rollup = new com . rackspacecloud . blueflood . types . BluefloodCounterRollup ( ) ; "<AssertPlaceHolder>" ; } equals ( java . lang . Object ) { if ( ! ( obj instanceof com . rackspacecloud . blueflood . rollup . Granularity ) ) return false ; else return obj == ( this ) ; }
testFlatten ( ) { org . teiid . translator . document . Document doc = new org . teiid . translator . document . Document ( ) ; doc . addProperty ( "B" 4 , "AA" ) ; doc . addProperty ( "B" , "B" 2 ) ; org . teiid . translator . document . Document c1 = new org . teiid . translator . document . Document ( "c1" , false , doc ) ; c1 . addProperty ( "B" 1 , "11" ) ; org . teiid . translator . document . Document c2 = new org . teiid . translator . document . Document ( "c1" , false , doc ) ; c2 . addProperty ( "B" 3 , "B" 7 ) ; doc . addChildDocuments ( "c1" , java . util . Arrays . asList ( c1 , c2 ) ) ; org . teiid . translator . document . Document c4 = new org . teiid . translator . document . Document ( "c2" , false , doc ) ; c4 . addProperty ( "4" , "B" 0 ) ; org . teiid . translator . document . Document c5 = new org . teiid . translator . document . Document ( "c2" , false , doc ) ; c5 . addProperty ( "5" , "B" 6 ) ; doc . addChildDocuments ( "c2" , java . util . Arrays . asList ( c4 , c5 ) ) ; java . util . List < java . util . Map < java . lang . String , java . lang . Object > > result = doc . flatten ( ) ; java . util . List < java . util . Map < java . lang . String , java . lang . Object > > expected = java . util . Arrays . asList ( map ( "B" 4 , "AA" , "B" , "B" 2 , "c1/1" , "11" , "B" 5 , "B" 0 ) , map ( "B" 4 , "AA" , "B" , "B" 2 , "c1/2" , "B" 7 , "B" 5 , "B" 0 ) , map ( "B" 4 , "AA" , "B" , "B" 2 , "c1/1" , "11" , "c2/5" , "B" 6 ) , map ( "B" 4 , "AA" , "B" , "B" 2 , "c1/2" , "B" 7 , "c2/5" , "B" 6 ) ) ; "<AssertPlaceHolder>" ; } toArray ( ) { return java . util . Arrays . copyOf ( elementData , size ) ; }
testSetUnread ( ) { contact . setUnread ( 1 ) ; "<AssertPlaceHolder>" ; } getUnread ( ) { return unread ; }
testOracleDatabase ( ) { try { java . lang . String expectedSQL = ( org . pentaho . di . core . database . SelectCountIT . NonHiveSelect ) + ( org . pentaho . di . core . database . SelectCountIT . TableName ) ; org . pentaho . di . core . database . DatabaseMeta databaseMeta = new org . pentaho . di . core . database . DatabaseMeta ( org . pentaho . di . core . database . SelectCountIT . OracleDatabaseXML ) ; java . lang . String sql = databaseMeta . getDatabaseInterface ( ) . getSelectCountStatement ( org . pentaho . di . core . database . SelectCountIT . TableName ) ; "<AssertPlaceHolder>" ; } catch ( java . lang . Exception e ) { e . printStackTrace ( ) ; } } getSelectCountStatement ( java . lang . String ) { if ( ( databaseDialect ) != null ) { return databaseDialect . getSelectCountStatement ( tableName ) ; } return super . getSelectCountStatement ( tableName ) ; }

预期输出:

linenumber,length
5,5000
10,3850
2,2000
...

Answer 1

使用每个 Unix 机器上存在的这些工具的任何版本:

$ awk -v OFS=',' '{print NR, length($0)}' file | sort -t, -rnk2 | head -n 5
1,1717
6,1649
8,883
2,762
4,656

如果您确实需要，只需在开头添加 echo 'linenumber,length'; 即可获得标题行。

上面是输出 5 行而不是 10 行来演示最大 N 的选择，因为 OP 只提供了 8 行样本输入。