Regex Grep搜索某些字符任意顺序任意大小写
我需要搜索“詹姆斯”这个角色。问题是它们可以是任意顺序的，任何一个都可以资本化。例如，需要找到以下内容Regex Grep搜索某些字符任意顺序任意大小写,regex,grep,Regex,Grep,我需要搜索“詹姆斯”这个角色。问题是它们可以是任意顺序的，任何一个都可以资本化。例如，需要找到以下内容 Aemjs 埃马伊斯 塞马吉 这只是一些可能性，显然还有更多的组合 如果可能，这需要用一条grep语句来完成。grep搜索是使用软件包进行的，而不是在unix机器上。输入仅接受一个grep命令。可以用一句话来表达吗？这里有一个有趣的正则表达式： / (?=.{0,4}j)(?=.{0,4}a)(?=.{0,4}m)(?=.{0,4}e)(?=.{0,4}s).{5} /i 这将要做的是向
- Aemjs
- 埃马伊斯
- 塞马吉
如果可能，这需要用一条grep语句来完成。grep搜索是使用软件包进行的，而不是在unix机器上。输入仅接受一个grep命令。可以用一句话来表达吗？这里有一个有趣的正则表达式：
/ (?=.{0,4}j)(?=.{0,4}a)(?=.{0,4}m)(?=.{0,4}e)(?=.{0,4}s).{5} /i
igrepgrep -Pi " (?=.{0,4}j)(?=.{0,4}a)(?=.{0,4}m)(?=.{0,4}e)(?=.{0,4}s).{5} " $file
.....&.*D.*&.*O.*&.*L.*L.*&.*Y.*
其中
$filegrep-Pgrepgrep-E-i#!/usr/local/bin/txr --lisp
(let ((regex (regex-compile (first *args*))))
(whilet ((line (get-line)))
(whenlet ((mlist (rra regex line))) ;; rra: regex ranges all
(put-line line)
(let ((carets (mkstring (to (find-max mlist)) #\space)))
(mapdo (op mapdo (do set [carets @1] #\^) (range* (from @1) (to @1)))
mlist)
(put-line carets)))))
..*J.*agrep -Pi " (?=.{0,4}j)(?=.{0,4}a)(?=.{0,4}m)(?=.{0,4}e)(?=.{0,4}s).{5} " $file
.....&.*D.*&.*O.*&.*L.*L.*&.*Y.*
L*L.*L.*..&.*J.&.*A.*&.*M.*.&.*E.*.&.*S.&A&B）（~A | ~B）--> ~(~.....|~.*J.*|~.*A.*|~.*M.*|~.*E.*|~.*S.*)
~…~(|.|..|...|....|......+)
~.*J.*J[^J]*~(|.|..|...|....|......+|[^J]*|[^A]*|[^M]*|[^E]*|[^S]*)
$ ./txgrep '~(|.|..|...|....|......+|[^J]*|[^A]*|[^M]*|[^E]*|[^S]*)'
JAMES
JAMES
^^^^^
Hey there, JAMES, meet AMSEJAMS.
Hey there, JAMES, meet AMSEJAMS.
^^^^^ ^^^^^
SJAMSSEMASMSJEMSAMSESAMJESESJASMAS
SJAMSSEMASMSJEMSAMSESAMJESESJASMAS
^^^^^ ^^^^^
J
AJAMES
AJAMES
^^^^^
grep-v$ grep -v -E '\<(|.|..|...|....|......+|[^J]*|[^A]*|[^M]*|[^E]*|[^S]*)\>'
grep-i[Jj]JJAMESJ(A(M(ES|SE)|E(MS|SM)|S(ME|EM)))
JAMES|JAMSE|JAEMS|JAESM|JASME|JASEM
M（ES | SE）| E（MS | SM）| S（ME | EM）JAAJ(AJ|JA)(M(ES|SE)|E(MS|SM)|S(ME|EM))
JAMESJAMES（AJ | JA）M（ES | SE）| E（MS | SM）| S（ME | EM）(AJ|JA)(M(ES|SE)|E(MS|SM)|S(ME|EM))
(JM|MJ)(A(ES|SE)|E(AS|SA)|S(EA|AE))
... eight more
JAMESregex compile;; This produces S-exp based regex abstract syntax (AST) not
;; regex character syntax.
(defun trie-to-regex (trie)
(typecase trie
(null nil)
(cons ^(compound ,(car trie) ,(trie-to-regex (cdr trie))))
(hash (iflet ((pairs (hash-pairs trie)))
(reduce-left (ret ^(or ,@1 ,@2))
(mapcar (aret ^(compound ,@1 ,(trie-to-regex @2)))
pairs))))))
$ txr -i trie-to-regex.tl
1> (defvar tr (make-trie))
tr
2> (perm "JAMES")
("JAMES" "JAMSE" "JAEMS" "JAESM" "JASME" "JASEM" "JMAES" "JMASE"
"JMEAS" "JMESA" "JMSAE" "JMSEA" "JEAMS" "JEASM" "JEMAS" "JEMSA"
"JESAM" "JESMA" "JSAME" "JSAEM" "JSMAE" "JSMEA" "JSEAM" "JSEMA"
"AJMES" "AJMSE" "AJEMS" "AJESM" "AJSME" "AJSEM" "AMJES" "AMJSE"
"AMEJS" "AMESJ" "AMSJE" "AMSEJ" "AEJMS" "AEJSM" "AEMJS" "AEMSJ"
"AESJM" "AESMJ" "ASJME" "ASJEM" "ASMJE" "ASMEJ" "ASEJM" "ASEMJ"
"MJAES" "MJASE" "MJEAS" "MJESA" "MJSAE" "MJSEA" "MAJES" "MAJSE"
"MAEJS" "MAESJ" "MASJE" "MASEJ" "MEJAS" "MEJSA" "MEAJS" "MEASJ"
"MESJA" "MESAJ" "MSJAE" "MSJEA" "MSAJE" "MSAEJ" "MSEJA" "MSEAJ"
"EJAMS" "EJASM" "EJMAS" "EJMSA" "EJSAM" "EJSMA" "EAJMS" "EAJSM"
"EAMJS" "EAMSJ" "EASJM" "EASMJ" "EMJAS" "EMJSA" "EMAJS" "EMASJ"
"EMSJA" "EMSAJ" "ESJAM" "ESJMA" "ESAJM" "ESAMJ" "ESMJA" "ESMAJ"
"SJAME" "SJAEM" "SJMAE" "SJMEA" "SJEAM" "SJEMA" "SAJME" "SAJEM"
"SAMJE" "SAMEJ" "SAEJM" "SAEMJ" "SMJAE" "SMJEA" "SMAJE" "SMAEJ"
"SMEJA" "SMEAJ" "SEJAM" "SEJMA" "SEAJM" "SEAMJ" "SEMJA" "SEMAJ")
3> (mapdo (op trie-add tr @1 t) (perm "JAMES")) ;; add above to trie
nil
4> (regex-compile (trie-to-regex tr)) ;; compile, get printed rep as side effect
#/A(E(J(MS|SM)|M(JS|SJ)|S(JM|MJ))|J(E(MS|SM)|M(ES|SE)|S(EM|ME))|M(E(JS|SJ)|J(ES|SE)|S(EJ|JE))|S(E(JM|MJ)|J(EM|ME)|M(EJ|JE)))|
E(A(J(MS|SM)|M(JS|SJ)|S(JM|MJ))|J(A(MS|SM)|M(AS|SA)|S(AM|MA))|M(A(JS|SJ)|J(AS|SA)|S(AJ|JA))|S(A(JM|MJ)|J(AM|MA)|M(AJ|JA)))|
J(A(E(MS|SM)|M(ES|SE)|S(EM|ME))|E(A(MS|SM)|M(AS|SA)|S(AM|MA))|M(A(ES|SE)|E(AS|SA)|S(AE|EA))|S(A(EM|ME)|E(AM|MA)|M(AE|EA)))|
M(A(E(JS|SJ)|J(ES|SE)|S(EJ|JE))|E(A(JS|SJ)|J(AS|SA)|S(AJ|JA))|J(A(ES|SE)|E(AS|SA)|S(AE|EA))|S(A(EJ|JE)|E(AJ|JA)|J(AE|EA)))|
S(A(E(JM|MJ)|J(EM|ME)|M(EJ|JE))|E(A(JM|MJ)|J(AM|MA)|M(AJ|JA))|J(A(EM|ME)|E(AM|MA)|M(AE|EA))|M(A(EJ|JE)|E(AJ|JA)|J(AE|EA)))/
/\b(?=\w*j)(?=\w*a)(?=\w*m)(?=\w*e)(?=\w*s)\w{5}\b/i
(defun break-trigraphs (string)
(if (<= (length string) 3)
string
(mapcar (ret (list @1 (break-trigraphs (set-diff string @1))))
(comb string 3))))
(defun trigraph-tree-to-regex (dtree)
(typecase dtree
(str (caseql (length dtree)
(1 dtree)
((2 3) (reduce-right (ret ^(or ,@1 ,@2)) (perm dtree)))
(t (error "bad trigraph tree"))))
(cons
(whenlet ((exprs (collect-each ((elem dtree))
^(compound ,(trigraph-tree-to-regex (first elem))
,(trigraph-tree-to-regex (second elem))))))
(reduce-right (ret ^(or ,@1 ,@2)) exprs)))))
$ txr -i trigraphs.tl
1> (break-trigraphs "JAMES")
(("JAM" "ES") ("JAE" "MS") ("JAS" "ME") ("JME" "AS") ("JMS" "AE")
("JES" "AM") ("AMS" "JE") ("AES" "JM") ("MES" "JA"))
2> (trigraph-tree-to-regex *1)
(or (compound (or "JAM" (or "JMA" (or "AJM" (or "AMJ" (or "MJA" "MAJ")))))
(or "ES" "SE"))
(or (compound (or "JAE" (or "JEA" (or "AJE" (or "AEJ" (or "EJA" "EAJ")))))
(or "MS" "SM"))
(or (compound (or "JAS" (or "JSA" (or "AJS" (or "ASJ" (or "SJA" "SAJ")))))
(or "ME" "EM"))
(or (compound (or "JME" (or "JEM" (or "MJE" (or "MEJ" (or "EJM" "EMJ")))))
(or "AS" "SA"))
(or (compound (or "JMS" (or "JSM" (or "MJS" (or "MSJ" (or "SJM" "SMJ")))))
(or "AE" "EA"))
(or (compound (or "JES" (or "JSE" (or "EJS" (or "ESJ" (or "SJE" "SEJ")))))
(or "AM" "MA"))
(or (compound (or "AMS" (or "ASM" (or "MAS" (or "MSA" (or "SAM" "SMA")))))
(or "JE" "EJ"))
(or (compound (or "AES" (or "ASE" (or "EAS" (or "ESA" (or "SAE" "SEA")))))
(or "JM" "MJ"))
(compound (or "MES" (or "MSE" (or "EMS" (or "ESM" (or "SME" "SEM")))))
(or "JA" "AJ"))))))))))
3> (regex-compile *2)
#/(JAM|JMA|AJM|AMJ|MJA|MAJ)(ES|SE)|(JAE|JEA|AJE|AEJ|EJA|EAJ)(MS|SM)|(JAS|JSA|AJS|ASJ|SJA|SAJ)(ME|EM)|(JME|JEM|MJE|MEJ|EJM|EMJ)(AS|SA)|(JMS|JSM|MJS|MSJ|SJM|SMJ)(AE|EA)|(JES|JSE|EJS|ESJ|SJE|SEJ)(AM|MA)|(AMS|ASM|MAS|MSA|SAM|SMA)(JE|EJ)|(AES|ASE|EAS|ESA|SAE|SEA)(JM|MJ)|(MES|MSE|EMS|ESM|SME|SEM)(JA|AJ)/