X-Git-Url: http://git.indexdata.com/?p=idzebra-moved-to-github.git;a=blobdiff_plain;f=recctrl%2Frectext.c;h=bcc9d26dd873d1109042b1bbbc0fd028cd067927;hp=ace66cf4ca9ca51a7c94af4e522c3f5262edc2f7;hb=ef696645cc3b7e0f4027008d1dc589c0f0f90c1f;hpb=6ccabd72334e17c9621a73b1b50469d2a89030c9 diff --git a/recctrl/rectext.c b/recctrl/rectext.c index ace66cf..bcc9d26 100644 --- a/recctrl/rectext.c +++ b/recctrl/rectext.c @@ -1,10 +1,41 @@ /* - * Copyright (C) 1994-1995, Index Data I/S + * Copyright (C) 1994-1998, Index Data * All rights reserved. * Sebastian Hammer, Adam Dickmeiss * * $Log: rectext.c,v $ - * Revision 1.3 1996-11-01 09:00:33 adam + * Revision 1.12 1999-05-26 07:49:14 adam + * C++ compilation. + * + * Revision 1.11 1999/05/21 12:00:17 adam + * Better diagnostics for extraction process. + * + * Revision 1.10 1999/05/20 12:57:18 adam + * Implemented TCL filter. Updated recctrl system. + * + * Revision 1.9 1998/10/16 08:14:38 adam + * Updated record control system. + * + * Revision 1.8 1998/05/20 10:12:27 adam + * Implemented automatic EXPLAIN database maintenance. + * Modified Zebra to work with ASN.1 compiled version of YAZ. + * + * Revision 1.7 1998/03/11 11:19:05 adam + * Changed the way sequence numbers are generated. + * + * Revision 1.6 1998/02/10 12:03:06 adam + * Implemented Sort. + * + * Revision 1.5 1997/10/27 14:33:06 adam + * Moved towards generic character mapping depending on "structure" + * field in abstract syntax file. Fixed a few memory leaks. Fixed + * bug with negative integers when doing searches with relational + * operators. + * + * Revision 1.4 1996/11/04 14:09:16 adam + * Minor changes. + * + * Revision 1.3 1996/11/01 09:00:33 adam * This simple "text" format now supports element specs B and M. * * Revision 1.2 1996/10/29 14:02:45 adam @@ -45,7 +76,12 @@ #include #include "rectext.h" -static void text_init (void) +static void *text_init (RecType recType) +{ + return 0; +} + +static void text_destroy (void *clientData) { } @@ -58,10 +94,10 @@ struct buf_info { struct buf_info *buf_open (struct recExtractCtrl *p) { - struct buf_info *fi = xmalloc (sizeof(*fi)); + struct buf_info *fi = (struct buf_info *) xmalloc (sizeof(*fi)); fi->p = p; - fi->buf = xmalloc (4096); + fi->buf = (char *) xmalloc (4096); fi->offset = 1; fi->max = 1; return fi; @@ -69,10 +105,10 @@ struct buf_info *buf_open (struct recExtractCtrl *p) int buf_read (struct buf_info *fi, char *dst) { - if (fi->max <= 0) - return 0; if (fi->offset >= fi->max) { + if (fi->max <= 0) + return 0; fi->max = (*fi->p->readf)(fi->p->fh, fi->buf, 4096); fi->offset = 0; if (fi->max <= 0) @@ -88,41 +124,37 @@ void buf_close (struct buf_info *fi) xfree (fi); } -static int text_extract (struct recExtractCtrl *p) +static int text_extract (void *clientData, struct recExtractCtrl *p) { - char w[256]; + char w[512]; RecWord recWord; - int r, seqno = 1; + int r; struct buf_info *fi = buf_open (p); - (*p->init)(&recWord); - recWord.which = Word_String; + (*p->init)(p, &recWord); + recWord.reg_type = 'w'; do { int i = 0; r = buf_read (fi, w); - while (r > 0 && i < 255 && isalnum(w[i])) + while (r > 0 && i < 511 && w[i] != '\n' && w[i] != '\r') { i++; r = buf_read (fi, w + i); } if (i) { - int j; - for (j = 0; jadd)(&recWord); + recWord.string = w; + recWord.length = i; + (*p->addWord)(&recWord); } } while (r > 0); buf_close (fi); - return 0; + return RECCTRL_EXTRACT_OK; } -static int text_retrieve (struct recRetrieveCtrl *p) +static int text_retrieve (void *clientData, struct recRetrieveCtrl *p) { int r, text_ptr = 0; static char *text_buf = NULL; @@ -142,7 +174,7 @@ static int text_retrieve (struct recRetrieveCtrl *p) char *nb; text_size = 2*text_size + 8192; - nb = xmalloc (text_size); + nb = (char *) xmalloc (text_size); if (text_buf) { memcpy (nb, text_buf, text_ptr); @@ -196,6 +228,7 @@ static int text_retrieve (struct recRetrieveCtrl *p) static struct recType text_type = { "text", text_init, + text_destroy, text_extract, text_retrieve };