From 83c63e03b9fd860569c7e6944ad9c1a5c9d19f7e Mon Sep 17 00:00:00 2001 Message-Id: <83c63e03b9fd860569c7e6944ad9c1a5c9d19f7e.1714103110.git.mdw@distorted.org.uk> From: Mark Wooding Date: Sun, 13 Jan 2002 13:33:01 +0000 Subject: [PATCH] Pass line length to line handler function. Provide a @typedef@ for handler functions. Allow run-time configuration of line delimiters. Organization: Straylight/Edgeware From: mdw --- lbuf.c | 70 +++++++++++++++++++++++++++--------------------------- lbuf.h | 24 ++++++++++++++----- man/lbuf.3 | 41 +++++++++++++++++++++++--------- 3 files changed, 83 insertions(+), 52 deletions(-) diff --git a/lbuf.c b/lbuf.c index 8b93076..ba18678 100644 --- a/lbuf.c +++ b/lbuf.c @@ -1,6 +1,6 @@ /* -*-c-*- * - * $Id: lbuf.c,v 1.5 2001/02/03 16:23:33 mdw Exp $ + * $Id: lbuf.c,v 1.6 2002/01/13 13:32:52 mdw Exp $ * * Block-to-line buffering * @@ -30,6 +30,10 @@ /*----- Revision history --------------------------------------------------* * * $Log: lbuf.c,v $ + * Revision 1.6 2002/01/13 13:32:52 mdw + * Pass line length to line handler function. Provide a @typedef@ for + * handler functions. Allow run-time configuration of line delimiters. + * * Revision 1.5 2001/02/03 16:23:33 mdw * Bug fix: handle a disable during a close-induced flush without dumping * core. @@ -92,7 +96,7 @@ void lbuf_flush(lbuf *b, char *p, size_t len) int cr; /* Carriage return state */ if (b->f & LBUF_CLOSE) { - b->func(0, b->p); + b->func(0, 0, b->p); return; } @@ -120,39 +124,36 @@ void lbuf_flush(lbuf *b, char *p, size_t len) /* --- Quickly discard uninteresting characters --- */ - if (*q != '\r' && *q != '\n') { - cr = 0; - continue; - } - if (*q == '\r') { - cr = 1; - continue; + switch (b->delim) { + case LBUF_CRLF: + case LBUF_STRICTCRLF: + if (*q != '\r' && *q != '\n') { + cr = 0; + continue; + } + if (*q == '\r') { + cr = 1; + continue; + } + if (!cr && b->delim == LBUF_STRICTCRLF) + continue; + break; + default: + if (*q != b->delim) + continue; } - /* --- Two choices here --- * - * - * I can either be strict about CRLF line ends, or I can be shoddy - * and allow bare LFs. I'll do the latter, although I oughtn't, - * because it makes testing interactively and with Unix text files - * easier. - */ - -#ifdef STRICT_CRLF - if (!cr) - continue; -#endif - - /* --- I have a positive ID on a linefeed --- * + /* --- I have a positive ID on a delimiter --- * * * If I'm interested in this string, report it to my owner. */ if (base) { + len = q - base; if (cr) - q[-1] = 0; /* Exercise: why is this safe? */ - else - *q = 0; - b->func(base, b->p); + len--; /* Exercise: why is this safe? */ + base[len] = 0; + b->func(base, len, b->p); if (!(b->f & LBUF_ENABLE)) { base = q + 1; break; @@ -165,10 +166,10 @@ void lbuf_flush(lbuf *b, char *p, size_t len) /* --- Sift through the aftermath --- */ if (base) { - size_t len = l - base; + len = l - base; if (len == b->sz) { b->buf[len - 1] = 0; - b->func(base, b->p); + b->func(base, len - 1, b->p); } else if (base != b->buf) memmove(b->buf, base, len); b->len = len; @@ -195,7 +196,7 @@ void lbuf_close(lbuf *b) { if (b->len && b->len != b->sz) { b->buf[b->len] = 0; - b->func(b->buf, b->p); + b->func(b->buf, b->len, b->p); } if (b->buf) { x_free(b->a, b->buf); @@ -203,7 +204,7 @@ void lbuf_close(lbuf *b) } b->f |= LBUF_CLOSE; if (b->f & LBUF_ENABLE) - b->func(0, b->p); + b->func(0, 0, b->p); } /* --- @lbuf_free@ --- * @@ -298,7 +299,7 @@ void lbuf_setsize(lbuf *b, size_t sz) /* --- @lbuf_init@ --- * * * Arguments: @lbuf *b@ = pointer to buffer block - * @void (*func)(char *s, void *p)@ = handler function + * @lbuf_func *func@ = handler function * @void *p@ = argument pointer for @func@ * * Returns: --- @@ -309,14 +310,13 @@ void lbuf_setsize(lbuf *b, size_t sz) * for the first time. */ -void lbuf_init(lbuf *b, - void (*func)(char */*s*/, void */*p*/), - void *p) +void lbuf_init(lbuf *b, lbuf_func *func, void *p) { b->func = func; b->p = p; b->len = 0; b->f = LBUF_ENABLE; + b->delim = LBUF_CRLF; b->buf = 0; b->a = arena_global; lbuf_setsize(b, 256); diff --git a/lbuf.h b/lbuf.h index fb04b5f..df8fdff 100644 --- a/lbuf.h +++ b/lbuf.h @@ -1,6 +1,6 @@ /* -*-c-*- * - * $Id: lbuf.h,v 1.6 2001/02/03 16:23:33 mdw Exp $ + * $Id: lbuf.h,v 1.7 2002/01/13 13:32:52 mdw Exp $ * * Block-to-line buffering * @@ -30,6 +30,10 @@ /*----- Revision history --------------------------------------------------* * * $Log: lbuf.h,v $ + * Revision 1.7 2002/01/13 13:32:52 mdw + * Pass line length to line handler function. Provide a @typedef@ for + * handler functions. Allow run-time configuration of line delimiters. + * * Revision 1.6 2001/02/03 16:23:33 mdw * Bug fix: handle a disable during a close-induced flush without dumping * core. @@ -116,11 +120,16 @@ * that. */ +struct lbuf; + +typedef void lbuf_func(char */*s*/, size_t /*len*/, void */*p*/); + typedef struct lbuf { - void (*func)(char */*s*/, void */*p*/); /* Handler function */ + lbuf_func *func; /* Handler function */ void *p; /* Argument for handler */ size_t len; /* Length of data in buffer */ size_t sz; /* Buffer size */ + unsigned delim; /* Delimiter to look for */ unsigned f; /* Various useful state flags */ arena *a; /* Memory allocation arena */ char *buf; /* The actual buffer */ @@ -130,6 +139,11 @@ typedef struct lbuf { #define LBUF_ENABLE 2u /* Buffer is currently enabled */ #define LBUF_CLOSE 4u /* Buffer is now closed */ +enum { + LBUF_CRLF = 256, + LBUF_STRICTCRLF = 257 +}; + /*----- Functions provided ------------------------------------------------*/ /* --- @lbuf_flush@ --- * @@ -216,7 +230,7 @@ extern void lbuf_setsize(lbuf */*b*/, size_t /*sz*/); /* --- @lbuf_init@ --- * * * Arguments: @lbuf *b@ = pointer to buffer block - * @void (*func)(char *s, void *p)@ = handler function + * @lbuf_func *func@ = handler function * @void *p@ = argument pointer for @func@ * * Returns: --- @@ -225,9 +239,7 @@ extern void lbuf_setsize(lbuf */*b*/, size_t /*sz*/); * passed to @func@ for processing. */ -extern void lbuf_init(lbuf */*b*/, - void (*/*func*/)(char */*s*/, void */*p*/), - void */*p*/); +extern void lbuf_init(lbuf */*b*/, lbuf_func */*func*/, void */*p*/); /* --- @lbuf_destroy@ --- * * diff --git a/man/lbuf.3 b/man/lbuf.3 index 87f41a3..b887130 100644 --- a/man/lbuf.3 +++ b/man/lbuf.3 @@ -18,9 +18,7 @@ lbuf \- split lines out of asynchronously received blocks .BI "size_t lbuf_free(lbuf *" b ", char **" p ); .BI "void lbuf_snarf(lbuf *" b ", const void *" p ", size_t " sz ); .BI "void lbuf_setsize(lbuf *" b ", size_t " sz ); -.BI "void lbuf_init(lbuf *" b , -.BI " void (*" func ")(char *" s ", void *" p ), -.BI " void *" p ); +.BI "void lbuf_init(lbuf *" b ", lbuf_func *" func ", void *" p ); .BI "void lbuf_destroy(lbuf *" b ); .fi .SH "DESCRIPTION" @@ -51,10 +49,13 @@ A pointer to the block of memory to use for the line buffer. The line buffer will allocate memory to store incoming data automatically: this structure just contains bookkeeping information. .TP -.BI "void (*" func ")(char *" s ", void *" p ) +.BI "lbuf_func *" func The .I line-handler function to which the line buffer should pass completed lines of text. +See +.B "Line-handler functions" +below for a description of this function. .TP .BI "void *" p A pointer argument to be passed to the function when a completed line of @@ -138,9 +139,19 @@ function is trivially implemented in terms of the more complex .BR lbuf_free / lbuf_flush interface. .SS "Line breaking" -The line buffer considers a line to end with either a simple linefeed -character (the normal Unix convention) or a carriage-return/linefeed -pair (the Internet convention). +By default, the line buffer considers a line to end with either a simple +linefeed character (the normal Unix convention) or a +carriage-return/linefeed pair (the Internet convention). This can be +changed by modifying the +.B delim +member of the +.B lbuf +structure: the default value is +.BR LBUF_CRLF . +If set to +.BR LBUF_STRICTCRLF , +only a carriage-return/linefeed pair will terminate a line. Any other +value is a single character which is considered to be the line terminator. .PP The line buffer has a fixed amount of memory available to it. This is deliberate, to prevent a trivial attack whereby a remote user sends a @@ -150,10 +161,16 @@ and return only the initial portion. It will ignore the rest of the line completely. .SS "Line-handler functions" Completed lines, as already said, are passed to the caller's -line-handler function. The function is given two arguments: -the address +line-handler function. This function has the signature +.IP +.B "void" +.IB func "(char *" s ", size_t " len ", void *" p ); +.PP +It is given three arguments: the address .I s -of the line which has just been read, and the pointer +of the line which has just been read; the length +.I len +of the line (not including the null terminator), and the pointer .I p which was set up in the call to .BR lbuf_init . @@ -164,7 +181,9 @@ terminating zero byte is not permitted. .PP The line pointer argument .I s -may be null to signify end-of-file. See the next section. +may be null to signify end-of-file; in this case, the length +.I len +will be zero. See the next section. .SS "Flushing the remaining data" When the client program knows that there's no more data arriving (for example, an end-of-file condition exists on its data source) it should -- [mdw]