PureBasic

Code : Tout sélectionner

If OpenFile(0, "FichierSource.txt")
     While Not Eof(0)
          Full_Text$ + ReadString(0) + #CRLF$
     Wend 
     CloseFile(0)
Else
     End
EndIf

RegEx$ = "\b[A-Z0-9._%+-]+@[A-Z0-9.-]+\.[A-Z]{2,}\b"

If CreateRegularExpression(1, RegEx$, #PB_RegularExpression_NoCase)
     If ExamineRegularExpression(1, Full_Text$)
          While NextRegularExpressionMatch(1)
               Debug RegularExpressionMatchString(1)
          Wend 
     EndIf
EndIf

Code : Tout sélectionner

    Procedure.i RegExMatch (text$, regex$ = "")
    ; [DESC]
    ; Verify if a regular expression match with the passed string.
    ;
    ; [INPUT]
    ; text$ : The string to be checked.
    ; regex$ : The regular expression to be used.
    ;    
    ; [RETURN]
    ; 1 if there is a match, 0 if not, -1 if the regular expression is invalid.
    ;
    ; [NOTES]
    ; You can omit the regular expression between multiple calls it the regex doesn't change.
    ;
    ; Here is a list of some of the more useful commands for pattern matching and rember:
    ; the regex engine is eager, and ?, *, +, are greedy
    ;
    ; ^     = look at the start of the line (if used at the begin of the expression)
    ; $     = look at the end of the line
    ; \A    = look at the start of the string
    ; \Z    = look at the end of the string
    ; |     = OR
    ; ^     = NOT (if not at the begin)
    ;
    ; .     = any char that is not a newline (equivalent to [^\r\n] under Windows)
    ; ?     = the preceding char/token is optional (also used to switch from greedy to lazy, ie: *?)
    ;\s     = any whitespace such as [ \t\r\n]
    ;\S     = anything that is not a whitespace
    ;\d     = any decimal digit [0-9]
    ;\D     = anything that is not a decimal digit
    ;\w     = any "word" character [A-Za-z0-9_]
    ;\W     = anything that is not a "word" character
    ;\b     = a boundary between a word and a non-word
    ;\B     = no boundary between word characters
    ;\Q \E  = interpret all the characters between the \Q and the \E are as literal characters
    ;
    ; *     = 0 or many times  {0,}
    ; +     = 1 or many times  {1,} (also used to switch from greedy to possessive, ie: *+)
    ; (     = start sub expression
    ; )     = end sub expression
    ; {n}   = repeated n times
    ; {n,m} = repeated n times min, but no more than m
    ; {n,}  = repeated n times min, unlimited max
    ; [     = start char specifier
    ; ]     = end char specifier
    ; (?i)  = case insensitive matching
    ; (?-i) = case sensitive matching
    ;
    ; ?:    = turn off capturing
    ; ?!    = negative lookahed, usually to match something not followed by something else
    ;         example: a(?!b) = a not followed by b
    ;
    ; \     = the escape character
    ; \e    = escape ($1B)
    ; \n    = newline ($0A)
    ; \r    = carriage return ($0D)
    ; \t    = tab ($09)
    ; \xhh  = character with hex code hh
    ;
    ; Character classes, for example: [[:alpha:]]
    ;
    ; alnum    letters and digits
    ; alpha    letters
    ; ascii    character codes 0 - 127
    ; blank    space or tab only
    ; cntrl    control characters
    ; digit    decimal digits (same as \d)
    ; graph    printing characters, excluding space
    ; lower    lower case letters
    ; print    printing characters, including space
    ; punct    printing characters, excluding letters and digits and space
    ; space    white space (not quite the same as \s)
    ; upper    upper case letters
    ; word     "word" characters (same as \w)
    ; xdigit   hexadecimal digits
    ;
    ; refer to PCRESYNTAX(3) at http://www.pcre.org/pcre.txt for more info about the syntax

     Static iRegEx
     Protected iRetVal = -1 ; regex error
     
     If regex$
        If iRegEx > 0
            FreeRegularExpression(iRegEx)
        EndIf   
        iRegEx = CreateRegularExpression(#PB_Any, regex$)
     EndIf
     
     If iRegEx
        iRetVal = MatchRegularExpression(iRegEx, text$)   
     EndIf
     
     ProcedureReturn iRetVal
    EndProcedure



r$ = "^(?i)[A-Z0-9+_.-]+@[A-Z0-9.-]+$" ; not too strict email address validator
Debug RegExMatch("president@whitehouse.org", r$) ; 1
Debug RegExMatch("president") ; 0
Debug RegExMatch("@whitehouse.org") ; 0
Debug RegExMatch("pre$ident@whitehouse.org") ; 0
Debug RegExMatch("user@host")                ; 1
Debug RegExMatch("toto48.bob@oranget.fr")                ; 1
Debug RegExMatch("tito-jean01.bob@orange-nt.fr")                ; 1

Code : Tout sélectionner

If OpenFile(0, "FichierSource.txt")
  While Not Eof(0)
    Full_Text$ + ReadString(0) + #CRLF$
  Wend 
  CloseFile(0)
Else
  End
EndIf

RegEx$ = "\S+@\S+|\{(?:\w+, *)+\w+\}@[\w.-]+"


If CreateRegularExpression(1, RegEx$, #PB_RegularExpression_NoCase)
  If ExamineRegularExpression(1, Full_Text$)
    While NextRegularExpressionMatch(1)
      Email$ = RegularExpressionMatchString(1)
      Debug Email$
    Wend
  Else
    End
  EndIf
EndIf

Code : Tout sélectionner

^(?i)[A-Z0-9+_.-]+@[A-Z0-9.-]+$

Code : Tout sélectionner

\S+@\S+|\{(?:\w+, *)+\w+\}@[\w.-]+

Code : Tout sélectionner

Exemples d'adresses valides :

    Abc@example.com
    Abc@10.42.0.1
    Abc.123@example.com
    user+mailbox/department=shipping@example.com
    !#$%&'*+-/=?^_`.{|}~@example.com
    "Abc@def"@example.com
    "Fred Bloggs"@example.com
    "Joe.\\Blow"@example.com
    Loïc.Accentué@voilà.fr8
    prettyandsimple@example.com
    very.common@example.com
    disposable.style.email.with+symbol@example.com
    other.email-with-dash@example.com
    x@example.com (one-letter local-part)
    "much.more unusual"@example.com
    "very.unusual.@.unusual.com"@example.com
    "very.(),:;<>[]\".VERY.\"very@\\ \"very\".unusual"@strange.example.com
    example-indeed@strange-example.com
    admin@mailserver1 (local domain name with no TLD)
    #!$%&'*+-/=?^_`{}|~@example.org
    "()<>[]:,;@\\\"!#$%&'-/=?^_`{}| ~.a"@example.org
    " "@example.org (space between the quotes)
    example@localhost (sent from localhost)
    example@s.solutions (see the List of Internet top-level domains)
    user@localserver
    user@tt (although ICANN highly discourages dotless email addresses)
    user@[IPv6:2001:DB8::1] 

Exemples d'adresses non valides :

    Abc.example.com le caractère @ manque.
    Abc.@example.com Le caractère . est situé juste avant le caractère @ .
    Abc..123@example.com  Le caractère . apparaît deux fois de suite.
    Abc.example.com (no @ character)
    A@b@c@example.com (only one @ is allowed outside quotation marks)
    a"b(c)d,e:f;g<h>i[j\k]l@example.com (none of the special characters in this local-part are allowed outside quotation marks)
    just"not"right@example.com (quoted strings must be dot separated or the only element making up the local-part)
    this is"not\allowed@example.com (spaces, quotes, and backslashes may only exist when within quoted strings and preceded by a backslash)
    this\ still\"not\\allowed@example.com (even if escaped (preceded by a backslash), spaces, quotes, and backslashes must still be contained by quotes)
    1234567890123456789012345678901234567890123456789012345678901234+x@example.com (too long)
    john..doe@example.com (double dot before @) 

Code : Tout sélectionner

[A-Z0-9àçéèêëîïôöùüÂÇÉÈÊËÎÏÔÖÙÜ.+-\\/]+@([A-Z0-9àçéèêëîïôöùüÂÇÉÈÊËÎÏÔÖÙÜ.+-\\/]+\.[A-Z0-9]+|[A-Z0-9àçéèêëîïôöùüÂÇÉÈÊËÎÏÔÖÙÜ.+-\\/]+)

Code : Tout sélectionner

text$ = "ceci est markatrouver un exemple markatrouver de comment utiliser markatrouver la fonction markatrouver stringfield"
For loop = 1 To CountString(text$,"markatrouver")+1
  Debug StringField(text$,loop,"markatrouver")
Next loop

Code : Tout sélectionner

([\w\d.+-=/]+|"[\w\d \.+-=/\\@]+")@([\w\d.+-=]+.|[\w\d\:\[\]]+)

Code : Tout sélectionner

RegEx$ = "([\w\d.+-=/!]+|" + Chr(34) + "[\w\d \.+-=/\\@]+" + Chr(34) + ")@([\w\d.+-=]+.|[\w\d\:\[\]]+)"