2018-09-正規表現 / 2018-09 regular expression

Transcript

1. 
   
   
   / 4
   =
   088 4 92 3 4 9 42 1 # 04: / 4 .
   

   View Slide

2. 
   
   
   
   

   View Slide

3. 
   
   
   
   l "Cybozu" == "Cybozu"
   
   l "Cybozu" in "Cybozu, Inc."
   

   View Slide

4. 
   
   s = 'If the condition is true, then do the indented statements.'
   if s != 'This is a pen':
   print('s is not "This is a pen")
   if 'cond' in s:
   print('s contains "cond"')
   if s.startswith('If '):
   print('s starts with "If ")
   

   View Slide

5. 
   
   ls /usr/bin/vi*
   l * G
   l ? G
   l [abc] G
   :
   ) )( 1 .1 1 //
   

   View Slide

6. :
   [a-zA-Z0-9_-]{1,64}@[a-zA-Z0-9_-]{1,64}[a-zA-Z0-9_-¥.]{1,64}
   l
   l Abc@gmail.com
   l takahiro-tsuruda@cybozu.co.jp
   

   View Slide

7. 
   
   l %$
   ,/'#
   !
   +
   l *)" -. (&
   

   View Slide

8. 
   :
   "
   /
   .
   /
   

   View Slide

9. 
   
   
   Ab
   l "
   

   View Slide

10. 
    
    | "
    
    (...) $&(' () %)
    *
    l a|b|c : "a", "b", "c"
    l a(bc|ef) : "abc", "aef"
    l! +# > $&
    

    View Slide

11. 
    
    ? 01
    
    + 1
    
    * 0
    
    {min, max} minmax
    
    
    bc*: "b", "bcccc"
    l >
    (ab)+: "ab", "abababab"
    (ab|cd){1,3}: "ababcd", "cdab", "cd"
    

    View Slide

12. 
    "HTTP/1.1", "HTTP/2.0"
    
    "."
    
    "¥."
    

    View Slide

13. 
    
    . 1
    […]
    1
    [^…]
    1
    [a-z] [abcdefghijklmnopqrfzuvwzyz]
    
    l a.c : "abc", "a1c"
    l [abc] : "a", "b", "c"
    l [^abc] : "d", "1", "@"
    l [abc]+ : "a", "aabcaac", "b"
    

    View Slide

14. 
    
    ^
    
    $
    
    
    ^default_type +[a-zA-Z/-]+;$
    "default_type application/octet-stream;"
    
    

    View Slide

15. 
    ¥1, ¥2 :1,2()
    
    <(div|p)>.*<¥/¥1>
    l "aaa"
    l ""
    
    
    

    View Slide

16. (
    3:
    "Author:Taro""User:Jiro" 0&4
    TaroJiro./
    '(
    (User|Author):(¥w+) ! $*
    ¥1 "User" "Author" ,¥2 "Taro" , ¥1-2…
    
    (?:User|Author): (¥w+)
    * %)#"1+
    ¥1 Taro Jiro ,
    

    View Slide

17. 
    [a-zA-Z0-9_-]{1,64}@[a-zA-Z0-9_-]{1,64}[a-zA-Z0-9_-¥.]{1,64}
    l [a-zA-Z0-9_-] : "_" "-"
    l {1,64} :
    164
    

    View Slide

18. 
    HTTP"$'-
    " (=GET)"URI(=/index.html)HTTP
    !#(=1.1),+ #*
    /: "GET /index.html HTTP/1.1"
    "GET", "/index.html", "1.1" ,+
    https://regexr.com ( Tools Details ,+
    
    &%).
    

    View Slide

19. 33 / 3 /. 3
    pat = re.compile(r'[kK]intone')
    l N
    m = pat.match('Kintone')
    l :
    l /.
    l
    

    View Slide

20. ¥w [a-zA-Z0-9_]
    l
    ¥W [^a-zA-Z0-9_]
    ¥s [ ¥t¥n¥r¥f¥v]
    l
    ¥S [^ ¥t¥n¥r¥f¥v]
    :
    3# 3 / - .- - 33 / 3 /
    

    View Slide

21. pat = re.compile(r'~~~')
    r '~~~' raw string
    l ¥ $
    !
    $
    # "%& $
    ': ¥n
    

    View Slide

22. r…
    ¥Python2-% $&0+1,#2-(
    
    ¥
    2-4*.
    
    ¥¥ /
    raw string % $&
    ¥2-" !'/
    
    ¥¥¥¥/)3
    

    View Slide

23. E cE e E
    I gM _
    / # / 3 . / / / 3
    g I Mad
    / # / 3 . / .
    T
    / # / 3 . /
    b M
    / # / 3 . : / : 3
    

    View Slide

24. 
    
    $ ls /bin | grep -E 'le?s'
    l | %
    
    )"!+%
    
    
    )"(+$&
    l -E '#*
    grep
    re regular expression
    re
    

    View Slide

25. 
    
    
    9/. cl r c
    l pb r oa gi h
    sed "/^user/ s/[tT]suruda/suzuki/"
    l user c tsuruda suzuki m
    sed -e "s/^#?¥s*PermitEmptyPasswords.*/PermitEmptyPasswords yes/" /etc/ssh/sshd_config
    l /etc/ssh/sshd_config PermitEmptyPasswords c PermitEmptyPasswords yes
    d n 9/. e
    1:: 9 56: 1 25/. 1 :/5 360 64 /5:8
    

    View Slide

26. 
    
    7 8 . 5 I
    l 55 / 7 8 . 5 7
    C
    import re
    re.compile(r'(¥w|[_-]){1,64}@').match("_" * 25)
    :
    

    View Slide

27. 
    o t M y V
    P PMe ( )
    l P P M h n M
    n n
    M
    {1,64} : r
    

    View Slide

28. 
    a(b|c) )
    
    
    
    
    
    
    (
    

    View Slide

29. 
    
    (¥w|[_-]){1,64}@
    

    View Slide

30. 
    
    (¥w|[_-]){1,64}@
    ¥w : [a-zA-Z0-9_]
    
    

    View Slide

31. 
    
    (¥w|[_-]){1,64}@
    ¥w : [a-zA-Z0-9_]
    (¥w|[_-])
    "
    

    View Slide

32. (¥w|[_-]){1,64}@
    "__"
    
    
    ( ) , - (
    ( ) , - (
    ( ) , - @ 1
    ( ) , - @
    ( ) , -
    ( ) , - @ 1
    ( ) , -
    ( ) , - (
    ( ) , - @ 1
    ( ) , - @
    ( ) , -
    ( ) , - @ 1
    ( ) , - 46 4 2 6
    

    View Slide

33. (¥w|[_-]){1,64}@ "
    2
    2
    l " 2
    _ 2
    l (¥w|-){1,64}@
    1 R
    l
    l 51_ E
    

    View Slide

34. 
    (".%/&.% -#0
    1
    $ )'
    
    ,*!+
    

    View Slide

35. 
    jq : *0&-0JSON'!72$.
    JSON25/8:(.341
    ?@
    ) %
    96
    $ curl –s 'https://api.github.com/repos/stedolan/jq/commits?per_page=5' |
    jq '[.[].commit.message]'
    

    View Slide

36. 
    :
    l / . .
    
    l / . . .
    
    l / . . .
    

    View Slide

37. 
    
    
    
    l J
    

    View Slide

38. 
    /etc/network/interfaces
    IP,-(# )
    
    import re
    ip_addr_pat = re.compile(r'!+$')
    with open(…) as f:
    for line in f:
    m = ip_addr_pat.search(line)
    if m is None:
    continue
    print(…)
    
    m.group(0)
    *+,-
    %&"'
    

    View Slide

39. 
    /usr/share/dict/words 3/#/,&-$
    */#(/
    # 0
    2
    $ grep -iE "%. '" /usr/share/dict/words
    aba
    aga
    aha
    ...
    
    l !1")
    l +/# ^ $
    

    View Slide

40. 
    ""-- "
    !$
    
    
    l ": tyos
    l : 20182030
    l : 020
    #
    l ty-2018-15
    l os-2019-0
    

    View Slide

41. 
    !&,1- (3$4 $4*'
    )
    080-1234-5678 // -
    090(9876)5432 // ( ).
    08015247682 // .
    0
    $ echo "080-1234-5678
    090(9876)5432
    08015247682" | sed -E "s/%.)/¥1 ¥2 ¥3/"
    
    ()
    ? /#+"
    

    View Slide