From mboxrd@z Thu Jan  1 00:00:00 1970
From: erik quanstrom <quanstro@quanstro.net>
Date: Tue, 13 Jul 2010 14:57:40 -0400
To: 9fans@9fans.net
Message-ID: <b546afe5c6506091e0329de81bcde1b7@brasstown.quanstro.net>
In-Reply-To: <AANLkTinMrkIBafWVXrlLQmo5lPPRmq-IEqNoyNX-5MIo@mail.gmail.com>
References: <AANLkTil4cAbJUFnGfnkVuOamXTaRcs-BfQjNQXPYV2qE@mail.gmail.com>
	<136f4778140ad5331b980f5d45eff3c5@coraid.com>
	<AANLkTimt-N7AHo_3d9sOnHKH-dpDNsD_H0ZzogJ8_EB5@mail.gmail.com>
	<b5d8f679ca37f573d37735ce19235184@coraid.com>
	<AANLkTinMrkIBafWVXrlLQmo5lPPRmq-IEqNoyNX-5MIo@mail.gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset="US-ASCII"
Content-Transfer-Encoding: 7bit
Subject: Re: [9fans] regexp doubt
Topicbox-Message-UUID: 3ef2d358-ead6-11e9-9d60-3106f5b1d025

patch:

/n/dump/2010/0713/sys/src/cmd/acme/regx.c:20,26 - regx.c:20,26
  typedef struct Inst Inst;
  struct Inst
  {
- 	uint	type;	/* < 0x10000 ==> literal, otherwise action */
+ 	uint	type;	/* < 0x1000000 ==> literal, otherwise action */
  	union {
  		int sid;
  		int subid;
/n/dump/2010/0713/sys/src/cmd/acme/regx.c:61,85 - regx.c:61,85
   *	0x100xx are operators, value == precedence
   *	0x200xx are tokens, i.e. operands for operators
   */
- #define	OPERATOR	0x10000	/* Bitmask of all operators */
- #define	START		0x10000	/* Start, used for marker on stack */
- #define	RBRA		0x10001	/* Right bracket, ) */
- #define	LBRA		0x10002	/* Left bracket, ( */
- #define	OR		0x10003	/* Alternation, | */
- #define	CAT		0x10004	/* Concatentation, implicit operator */
- #define	STAR		0x10005	/* Closure, * */
- #define	PLUS		0x10006	/* a+ == aa* */
- #define	QUEST		0x10007	/* a? == a|nothing, i.e. 0 or 1 a's */
- #define	ANY		0x20000	/* Any character but newline, . */
- #define	NOP		0x20001	/* No operation, internal use only */
- #define	BOL		0x20002	/* Beginning of line, ^ */
- #define	EOL		0x20003	/* End of line, $ */
- #define	CCLASS		0x20004	/* Character class, [] */
- #define	NCCLASS		0x20005	/* Negated character class, [^] */
- #define	END		0x20077	/* Terminate: match found */
+ #define	OPERATOR	0x1000000	/* Bitmask of all operators */
+ #define	START		0x1000000	/* Start, used for marker on stack */
+ #define	RBRA		0x1000001	/* Right bracket, ) */
+ #define	LBRA		0x1000002	/* Left bracket, ( */
+ #define	OR		0x1000003	/* Alternation, | */
+ #define	CAT		0x1000004	/* Concatentation, implicit operator */
+ #define	STAR		0x1000005	/* Closure, * */
+ #define	PLUS		0x1000006	/* a+ == aa* */
+ #define	QUEST		0x1000007	/* a? == a|nothing, i.e. 0 or 1 a's */
+ #define	ANY		0x2000000	/* Any character but newline, . */
+ #define	NOP		0x2000001	/* No operation, internal use only */
+ #define	BOL		0x2000002	/* Beginning of line, ^ */
+ #define	EOL		0x2000003	/* End of line, $ */
+ #define	CCLASS	0x2000004	/* Character class, [] */
+ #define	NCCLASS	0x2000005	/* Negated character class, [^] */
+ #define	END		0x2000077	/* Terminate: match found */

- #define	ISATOR		0x10000
- #define	ISAND		0x20000
+ #define	ISATOR		0x1000000
+ #define	ISAND		0x2000000

  /*
   * Parser Information
/n/dump/2010/0713/sys/src/cmd/acme/regx.c:452,458 - regx.c:452,458
  			exprp++;
  			return '\n';
  		}
- 		return *exprp++|0x10000;
+ 		return *exprp++|0x1000000;
  	}
  	return *exprp++;
  }
/n/dump/2010/0713/sys/src/cmd/acme/regx.c:492,498 - regx.c:492,498
  			classp[n+2] = c2;
  			n += 3;
  		}else
- 			classp[n++] = c1;
+ 			classp[n++] = c1 & ~0x1000000;
  	}
  	classp[n] = 0;
  	if(nclass == Nclass){