From mboxrd@z Thu Jan  1 00:00:00 1970
Message-ID: <c81f095d27120d7e3f269c19dcb46ac6@plan9.bell-labs.com>
To: 9fans@cse.psu.edu
Subject: Re: [9fans] slight glossing over 8) ?
From: "Russ Cox" <rsc@plan9.bell-labs.com>
MIME-Version: 1.0
Content-Type: text/plain; charset="US-ASCII"
Content-Transfer-Encoding: 7bit
Date: Tue, 12 Nov 2002 14:21:02 -0500
Topicbox-Message-UUID: 1bfbb992-eacb-11e9-9e20-41e7f4b1d025

if you _really_ want the right regexp, you should
use the ones from webfs, due to jeff brown.

/* RE character-class components -- these go in brackets */
#define PUNCT			"\\-_.!~*'()"
#define RES			";/?:@&=+$,"
#define ALNUM		"a-zA-Z0-9"
#define HEX			"0-9a-fA-F"
#define UNRES			ALNUM PUNCT

/* RE components; _N => has N parenthesized subexpressions when expanded */
#define ESCAPED_1			"(%[" HEX "][" HEX "])"
#define URIC_2			"([" RES UNRES "]|" ESCAPED_1 ")"
#define URICNOSLASH_2		"([" UNRES ";?:@&=+$,]|" ESCAPED_1 ")"
#define USERINFO_2		"([" UNRES ";:&=+$,]|" ESCAPED_1 ")"
#define PCHAR_2			"([" UNRES ":@&=+$,]|" ESCAPED_1 ")"
#define PSEGCHAR_3		"([/;]|" PCHAR_2 ")"

Retab retab[] =	/* view in constant width Font */
{
[REsplit]
	"^(([^:/?#]+):)?(//([^/?#]*))?([^?#]+)?(\\?([^#]*))?(#(.*))?$", nil, 0,
	/* |-scheme-|      |-auth.-|  |path--|    |query|     |--|frag */
	{  2,              4,         5,          7,          9},

[REscheme]
	"^[a-z][a-z0-9+-.]*$", nil, 0,
	{ 0, },

[REunknowndata]
	"^" URICNOSLASH_2 URIC_2 "*$", nil, 0,
	{ 0, },

[REauthority]
	"^(((" USERINFO_2 "*)@)?(((\\[[^\\]@]+\\])|([^:\\[@]+))(:([0-9]*))?)?)?$", nil, 0,
	/* |----user info-----|  |--------host----------------|  |-port-| */
	{  2,                    7,                              12, },

[REhost]
	"^(([a-zA-Z0-9\\-.]+)|(\\[([a-fA-F0-9.:]+)\\]))$", nil, 0,
	/* |--regular host--|     |-IPv6 literal-| */
	{  2,                     4, },

[REuserinfo]
	"^(([^:]*)(:([^:]*))?)$", nil, 0,
	/* |user-|  |pass-| */
	{  2,       4, },

[REabspath]
	"^/" PSEGCHAR_3 "*$", nil, 0,
	{ 0, },

[REquery]
	"^" URIC_2 "*$", nil, 0,
	{ 0, },

[REfragment]
	"^" URIC_2 "*$", nil, 0,
	{ 0, },

[REhttppath]
	"^.*$", nil, 0,
	{ 0, },

[REftppath]
	"^(.+)(;[tT][yY][pP][eE]=([aAiIdD]))?$", nil, 0,
	/*|--|-path              |ftptype-| */
	{ 1,                     3, },

[REfilepath]
	"^.*$", nil, 0,
	{ 0, },
};