Common Regex's for your coding pleasure.
$NAME_REGEX     = '[a-zA-Z]+';
$ADDRESS_REGEX  = '[.-\w]+';
$CITY_REGEX     = '\w+';
$PHONE_REGEX    = '^1?[-\s\.\/]?\s*\(?(\d\d\d)\)?[-\s\.\/]?\s*(\d\d\d)
+?[-\s\.\/]?(\d\d\d\d)\s*$';
$ZIP_REGEX      = '^\d{5}(([-\s])?\d{4})?\s*$';
$DOB_REGEX      = '^\d?\d[-\s\.\/]\s*\d?\d[-\s\.\/]\d\d\d?\d?s*$';
$EMAIL_REGEX    = '[-.\w]+\@[-.\w]+';
$COMMENT_REGEX  = '\w+';
$SSN_REGEX      = '^\d\d\d([\s\.\/-])?\d\d([\s\.\/-]>?\d\d\d\d\s*$';
$HTTP_CLEAN_HEADER_REGEX =~ s/%([a-fA-F0-9][a-fA-F0-9])/pack("C", hex(
+$1))/eg; #i.e., get rid of %20 et. al nauseaum from post headers.

[download]

Replies are listed 'Best First'.
RE: Common Regex's
by merlyn (Sage) on Aug 07, 2000 at 19:27 UTC
    The $EMAIL_REGEX is very wrong. The right one (for some version of "right") is over 6000 characters. Please don't use the one given here for ANYTHING.

    -- Randal L. Schwartz, Perl hacker

[reply]
[reply]
RE: Common Regex's
by KM (Priest) on Aug 07, 2000 at 19:53 UTC
    You can find the script which generates the pattern in Mastering Regular Expressions chapter 7 or here. Just add a print $mailbox at the end and redirect to a new file. If there is anything out there newer than this, let us know.

    Cheers,
    KM

[reply]
      Or you can just use this. This came from the same book as KM mentioned above. 

      
[\040\t]*(?:\([^\\\x80-\xff\n\015()]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-\
+xff\n\015()]*(?:\\[^\x80-\xff][^\\\x80-\
xff\n\015()]*)*\))[^\\\x80-\xff\n\015()]*)*\)[\040\t]*)*(?:(?:[^(\040)
+<>@,;:".\\\[\]\000-\037\x80-\xff]+(?![^(
\040)<>@,;:".\\\[\]\000-\037\x80-\xff])|"[^\\\x80-\xff\n\015"]*(?:\\[^
+\x80-\xff][^\\\x80-\xff\n\015"]*)*")[\04
0\t]*(?:\([^\\\x80-\xff\n\015()]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-\xff\
+n\015()]*(?:\\[^\x80-\xff][^\\\x80-\xff\
n\015()]*)*\))[^\\\x80-\xff\n\015()]*)*\)[\040\t]*)*(?:\.[\040\t]*(?:\
+([^\\\x80-\xff\n\015()]*(?:(?:\\[^\x80-\
xff]|\([^\\\x80-\xff\n\015()]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015()]*
+)*\))[^\\\x80-\xff\n\015()]*)*\)[\040\t]
*)*(?:[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+(?![^(\040)<>@,;:".\\\
+[\]\000-\037\x80-\xff])|"[^\\\x80-\xff\n
\015"]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015"]*)*")[\040\t]*(?:\([^\\\x
+80-\xff\n\015()]*(?:(?:\\[^\x80-\xff]|\(
[^\\\x80-\xff\n\015()]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015()]*)*\))[^
+\\\x80-\xff\n\015()]*)*\)[\040\t]*)*)*@[
\040\t]*(?:\([^\\\x80-\xff\n\015()]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-\x
+ff\n\015()]*(?:\\[^\x80-\xff][^\\\x80-\x
ff\n\015()]*)*\))[^\\\x80-\xff\n\015()]*)*\)[\040\t]*)*(?:[^(\040)<>@,
+;:".\\\[\]\000-\037\x80-\xff]+(?![^(\040
)<>@,;:".\\\[\]\000-\037\x80-\xff])|\[(?:[^\\\x80-\xff\n\015\[\]]|\\[^
+\x80-\xff])*\])[\040\t]*(?:\([^\\\x80-\x
ff\n\015()]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-\xff\n\015()]*(?:\\[^\x80-
+\xff][^\\\x80-\xff\n\015()]*)*\))[^\\\x8
0-\xff\n\015()]*)*\)[\040\t]*)*(?:\.[\040\t]*(?:\([^\\\x80-\xff\n\015(
+)]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-\xff\
n\015()]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015()]*)*\))[^\\\x80-\xff\n\
+015()]*)*\)[\040\t]*)*(?:[^(\040)<>@,;:"
.\\\[\]\000-\037\x80-\xff]+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff
+])|\[(?:[^\\\x80-\xff\n\015\[\]]|\\[^\x8
0-\xff])*\])[\040\t]*(?:\([^\\\x80-\xff\n\015()]*(?:(?:\\[^\x80-\xff]|
+\([^\\\x80-\xff\n\015()]*(?:\\[^\x80-\xf
f][^\\\x80-\xff\n\015()]*)*\))[^\\\x80-\xff\n\015()]*)*\)[\040\t]*)*)*
+|(?:[^(\040)<>@,;:".\\\[\]\000-\037\x80-
\xff]+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff])|"[^\\\x80-\xff\n\0
+15"]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\01
5"]*)*")[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037]*(?:(?:\([^\\\x8
+0-\xff\n\015()]*(?:(?:\\[^\x80-\xff]|\([
^\\\x80-\xff\n\015()]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015()]*)*\))[^\
+\\x80-\xff\n\015()]*)*\)|"[^\\\x80-\xff\
n\015"]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015"]*)*")[^()<>@,;:".\\\[\]\
+x80-\xff\000-\010\012-\037]*)*<[\040\t]*
(?:\([^\\\x80-\xff\n\015()]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-\xff\n\015
+()]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015
()]*)*\))[^\\\x80-\xff\n\015()]*)*\)[\040\t]*)*(?:@[\040\t]*(?:\([^\\\
+x80-\xff\n\015()]*(?:(?:\\[^\x80-\xff]|\
([^\\\x80-\xff\n\015()]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015()]*)*\))[
+^\\\x80-\xff\n\015()]*)*\)[\040\t]*)*(?:
[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+(?![^(\040)<>@,;:".\\\[\]\00
+0-\037\x80-\xff])|\[(?:[^\\\x80-\xff\n\0
15\[\]]|\\[^\x80-\xff])*\])[\040\t]*(?:\([^\\\x80-\xff\n\015()]*(?:(?:
+\\[^\x80-\xff]|\([^\\\x80-\xff\n\015()]*
(?:\\[^\x80-\xff][^\\\x80-\xff\n\015()]*)*\))[^\\\x80-\xff\n\015()]*)*
+\)[\040\t]*)*(?:\.[\040\t]*(?:\([^\\\x80
-\xff\n\015()]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-\xff\n\015()]*(?:\\[^\x
+80-\xff][^\\\x80-\xff\n\015()]*)*\))[^\\
\x80-\xff\n\015()]*)*\)[\040\t]*)*(?:[^(\040)<>@,;:".\\\[\]\000-\037\x
+80-\xff]+(?![^(\040)<>@,;:".\\\[\]\000-\
037\x80-\xff])|\[(?:[^\\\x80-\xff\n\015\[\]]|\\[^\x80-\xff])*\])[\040\
+t]*(?:\([^\\\x80-\xff\n\015()]*(?:(?:\\[
^\x80-\xff]|\([^\\\x80-\xff\n\015()]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\
+015()]*)*\))[^\\\x80-\xff\n\015()]*)*\)[
\040\t]*)*)*(?:,[\040\t]*(?:\([^\\\x80-\xff\n\015()]*(?:(?:\\[^\x80-\x
+ff]|\([^\\\x80-\xff\n\015()]*(?:\\[^\x80
-\xff][^\\\x80-\xff\n\015()]*)*\))[^\\\x80-\xff\n\015()]*)*\)[\040\t]*
+)*@[\040\t]*(?:\([^\\\x80-\xff\n\015()]*
(?:(?:\\[^\x80-\xff]|\([^\\\x80-\xff\n\015()]*(?:\\[^\x80-\xff][^\\\x8
+0-\xff\n\015()]*)*\))[^\\\x80-\xff\n\015
()]*)*\)[\040\t]*)*(?:[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+(?![^(
+\040)<>@,;:".\\\[\]\000-\037\x80-\xff])|
\[(?:[^\\\x80-\xff\n\015\[\]]|\\[^\x80-\xff])*\])[\040\t]*(?:\([^\\\x8
+0-\xff\n\015()]*(?:(?:\\[^\x80-\xff]|\([
^\\\x80-\xff\n\015()]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015()]*)*\))[^\
+\\x80-\xff\n\015()]*)*\)[\040\t]*)*(?:\.
[\040\t]*(?:\([^\\\x80-\xff\n\015()]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-\
+xff\n\015()]*(?:\\[^\x80-\xff][^\\\x80-\
xff\n\015()]*)*\))[^\\\x80-\xff\n\015()]*)*\)[\040\t]*)*(?:[^(\040)<>@
+,;:".\\\[\]\000-\037\x80-\xff]+(?![^(\04
0)<>@,;:".\\\[\]\000-\037\x80-\xff])|\[(?:[^\\\x80-\xff\n\015\[\]]|\\[
+^\x80-\xff])*\])[\040\t]*(?:\([^\\\x80-\
xff\n\015()]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-\xff\n\015()]*(?:\\[^\x80
+-\xff][^\\\x80-\xff\n\015()]*)*\))[^\\\x
80-\xff\n\015()]*)*\)[\040\t]*)*)*)*:[\040\t]*(?:\([^\\\x80-\xff\n\015
+()]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-\xff
\n\015()]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015()]*)*\))[^\\\x80-\xff\n
+\015()]*)*\)[\040\t]*)*)?(?:[^(\040)<>@,
;:".\\\[\]\000-\037\x80-\xff]+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\
+xff])|"[^\\\x80-\xff\n\015"]*(?:\\[^\x80
-\xff][^\\\x80-\xff\n\015"]*)*")[\040\t]*(?:\([^\\\x80-\xff\n\015()]*(
+?:(?:\\[^\x80-\xff]|\([^\\\x80-\xff\n\01
5()]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015()]*)*\))[^\\\x80-\xff\n\015(
+)]*)*\)[\040\t]*)*(?:\.[\040\t]*(?:\([^\
\\x80-\xff\n\015()]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-\xff\n\015()]*(?:\
+\[^\x80-\xff][^\\\x80-\xff\n\015()]*)*\)
)[^\\\x80-\xff\n\015()]*)*\)[\040\t]*)*(?:[^(\040)<>@,;:".\\\[\]\000-\
+037\x80-\xff]+(?![^(\040)<>@,;:".\\\[\]\
000-\037\x80-\xff])|"[^\\\x80-\xff\n\015"]*(?:\\[^\x80-\xff][^\\\x80-\
+xff\n\015"]*)*")[\040\t]*(?:\([^\\\x80-\
xff\n\015()]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-\xff\n\015()]*(?:\\[^\x80
+-\xff][^\\\x80-\xff\n\015()]*)*\))[^\\\x
80-\xff\n\015()]*)*\)[\040\t]*)*)*@[\040\t]*(?:\([^\\\x80-\xff\n\015()
+]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-\xff\n
\015()]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015()]*)*\))[^\\\x80-\xff\n\0
+15()]*)*\)[\040\t]*)*(?:[^(\040)<>@,;:".
\\\[\]\000-\037\x80-\xff]+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]
+)|\[(?:[^\\\x80-\xff\n\015\[\]]|\\[^\x80
-\xff])*\])[\040\t]*(?:\([^\\\x80-\xff\n\015()]*(?:(?:\\[^\x80-\xff]|\
+([^\\\x80-\xff\n\015()]*(?:\\[^\x80-\xff
][^\\\x80-\xff\n\015()]*)*\))[^\\\x80-\xff\n\015()]*)*\)[\040\t]*)*(?:
+\.[\040\t]*(?:\([^\\\x80-\xff\n\015()]*(
?:(?:\\[^\x80-\xff]|\([^\\\x80-\xff\n\015()]*(?:\\[^\x80-\xff][^\\\x80
+-\xff\n\015()]*)*\))[^\\\x80-\xff\n\015(
)]*)*\)[\040\t]*)*(?:[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+(?![^(\
+040)<>@,;:".\\\[\]\000-\037\x80-\xff])|\
[(?:[^\\\x80-\xff\n\015\[\]]|\\[^\x80-\xff])*\])[\040\t]*(?:\([^\\\x80
+-\xff\n\015()]*(?:(?:\\[^\x80-\xff]|\([^
\\\x80-\xff\n\015()]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015()]*)*\))[^\\
+\x80-\xff\n\015()]*)*\)[\040\t]*)*)*>)

      [download]

      LeGo <hr

[reply]
[d/l]

Back to Cool Uses for Perl