From: Adam Dickmeiss Date: Tue, 14 Jun 2005 12:42:48 +0000 (+0000) Subject: Removed replace_tokens code that has not been used for quite some X-Git-Tag: before.bug.529~397 X-Git-Url: http://git.indexdata.com/?p=idzebra-moved-to-github.git;a=commitdiff_plain;h=f9e7e7c0cbaab295c911c44002eb7009dee03b7b Removed replace_tokens code that has not been used for quite some time. --- diff --git a/index/zrpn.c b/index/zrpn.c index 179f210..a928fa0 100644 --- a/index/zrpn.c +++ b/index/zrpn.c @@ -1,4 +1,4 @@ -/* $Id: zrpn.c,v 1.198 2005-06-09 10:39:53 adam Exp $ +/* $Id: zrpn.c,v 1.199 2005-06-14 12:42:48 adam Exp $ Copyright (C) 1995-2005 Index Data ApS @@ -1432,50 +1432,6 @@ static ZEBRA_RES trans_scan_term(ZebraHandle zh, Z_AttributesPlusTerm *zapt, return ZEBRA_OK; } -char *normalize_term(ZebraHandle zh, Z_AttributesPlusTerm *zapt, - const char *termz, NMEM stream, unsigned reg_id) -{ - WRBUF wrbuf = 0; - AttrType truncation; - int truncation_value; - char *ex_list = 0; - - attr_init(&truncation, zapt, 5); - truncation_value = attr_find(&truncation, NULL); - - switch (truncation_value) - { - default: - ex_list = ""; - break; - case 101: - ex_list = "#"; - break; - case 102: - case 103: - ex_list = 0; - break; - case 104: - ex_list = "!#"; - break; - case 105: - ex_list = "!*"; - break; - } - if (ex_list) - wrbuf = zebra_replace(zh->reg->zebra_maps, reg_id, ex_list, - termz, strlen(termz)); - if (!wrbuf) - return nmem_strdup(stream, termz); - else - { - char *buf = (char*) nmem_malloc(stream, wrbuf_len(wrbuf)+1); - memcpy (buf, wrbuf_buf(wrbuf), wrbuf_len(wrbuf)); - buf[wrbuf_len(wrbuf)] = '\0'; - return buf; - } -} - static void grep_info_delete(struct grep_info *grep_info) { #ifdef TERM_COUNT @@ -1533,7 +1489,7 @@ static ZEBRA_RES grep_info_prepare(ZebraHandle zh, /** \brief Create result set(s) for list of terms \param zh Zebra Handle - \param termz_org term as used in query but converted to UTF-8 + \param termz term as used in query but converted to UTF-8 \param attributeSet default attribute set \param stream memory for result \param reg_type register type ('w', 'p',..) @@ -1549,7 +1505,7 @@ static ZEBRA_RES grep_info_prepare(ZebraHandle zh, */ static ZEBRA_RES term_list_trunc(ZebraHandle zh, Z_AttributesPlusTerm *zapt, - const char *termz_org, + const char *termz, oid_value attributeSet, NMEM stream, int reg_type, int complete_flag, @@ -1561,7 +1517,6 @@ static ZEBRA_RES term_list_trunc(ZebraHandle zh, { char term_dst[IT_MAX_WORD+1]; struct grep_info grep_info; - char *termz = normalize_term(zh, zapt, termz_org, stream, reg_type); const char *termp = termz; int alloc_sets = 0; diff --git a/util/charmap.c b/util/charmap.c index bfcd963..2919837 100644 --- a/util/charmap.c +++ b/util/charmap.c @@ -1,4 +1,4 @@ -/* $Id: charmap.c,v 1.36 2005-03-11 17:56:36 adam Exp $ +/* $Id: charmap.c,v 1.37 2005-06-14 12:42:49 adam Exp $ Copyright (C) 1995-2005 Index Data ApS @@ -241,50 +241,6 @@ const char *chr_map_output(chrmaptab maptab, const char **from, int len) return (const char*) maptab->output[c]; } -unsigned char zebra_prim(char **s) -{ - unsigned char c; - unsigned int i = 0; - - yaz_log (YLOG_DEBUG, "prim %.3s", *s); - if (**s == '\\') - { - (*s)++; - c = **s; - switch (c) - { - case '\\': c = '\\'; (*s)++; break; - case 'r': c = '\r'; (*s)++; break; - case 'n': c = '\n'; (*s)++; break; - case 't': c = '\t'; (*s)++; break; - case 's': c = ' '; (*s)++; break; - case 'x': sscanf(*s, "x%2x", &i); c = i; *s += 3; break; - case '0': - case '1': - case '2': - case '3': - case '4': - case '5': - case '6': - case '7': - case '8': - case '9': - sscanf(*s, "%3o", &i); - c = i; - *s += 3; - break; - default: - (*s)++; - } - } - else - { - c = **s; - ++(*s); - } - return c; -} - static int zebra_ucs4_strlen(ucs4_t *s) { int i = 0; @@ -300,7 +256,7 @@ ucs4_t zebra_prim_w(ucs4_t **s) char fmtstr[8]; yaz_log (YLOG_DEBUG, "prim_w %.3s", (char *) *s); - if (**s == '\\') + if (**s == '\\' && 1[*s]) { (*s)++; c = **s; @@ -533,7 +489,6 @@ static int scan_string(char *s_native, (*fun)(str, data, num ? (*num)++ : 0); } break; - case '[': s++; abort(); break; case '(': ++s; s0 = s; i = 0; diff --git a/util/zebramap.c b/util/zebramap.c index 0a95eda..991d16b 100644 --- a/util/zebramap.c +++ b/util/zebramap.c @@ -1,4 +1,4 @@ -/* $Id: zebramap.c,v 1.40 2005-03-11 17:56:36 adam Exp $ +/* $Id: zebramap.c,v 1.41 2005-06-14 12:42:49 adam Exp $ Copyright (C) 1995-2005 Index Data ApS @@ -34,13 +34,6 @@ Free Software Foundation, 59 Temple Place - Suite 330, Boston, MA #define ZEBRA_REPLACE_ANY 300 -struct zm_token { - int *token_from; - char *token_to; - int token_min; - struct zm_token *next; -}; - struct zebra_map { unsigned reg_id; int completeness; @@ -57,7 +50,6 @@ struct zebra_map { chrmaptab maptab; const char *maptab_name; struct zebra_map *next; - struct zm_token *replace_tokens; }; struct zebra_maps { @@ -68,7 +60,7 @@ struct zebra_maps { char temp_map_str[2]; const char *temp_map_ptr[2]; struct zebra_map **lookup_array; - WRBUF wrbuf_1, wrbuf_2; + WRBUF wrbuf_1; }; void zebra_maps_close (ZebraMaps zms) @@ -81,7 +73,6 @@ void zebra_maps_close (ZebraMaps zms) zm = zm->next; } wrbuf_free (zms->wrbuf_1, 1); - wrbuf_free (zms->wrbuf_2, 1); nmem_destroy (zms->nmem); xfree (zms); } @@ -115,7 +106,6 @@ static void zebra_map_read (ZebraMaps zms, const char *name) (*zm)->type = ZEBRA_MAP_TYPE_INDEX; (*zm)->completeness = 0; (*zm)->positioned = 1; - (*zm)->replace_tokens = 0; } else if (!yaz_matchstr (argv[0], "sort") && argc == 2) { @@ -131,7 +121,6 @@ static void zebra_map_read (ZebraMaps zms, const char *name) (*zm)->maptab = NULL; (*zm)->completeness = 0; (*zm)->positioned = 0; - (*zm)->replace_tokens = 0; } else if (zm && !yaz_matchstr (argv[0], "charmap") && argc == 2) { @@ -150,58 +139,6 @@ static void zebra_map_read (ZebraMaps zms, const char *name) if ((*zm)->type == ZEBRA_MAP_TYPE_SORT) (*zm)->u.sort.entry_size = atoi (argv[1]); } - else if (zm && !yaz_matchstr (argv[0], "replace") && argc >= 2) - { - struct zm_token *token = nmem_malloc (zms->nmem, sizeof(*token)); - token->next = (*zm)->replace_tokens; - (*zm)->replace_tokens = token; -#if 0 - yaz_log (YLOG_LOG, "replace %s", argv[1]); -#endif - token->token_from = 0; - if (argc >= 2) - { - char *cp = argv[1]; - int *dp = token->token_from = (int *) - nmem_malloc (zms->nmem, (1+strlen(cp))*sizeof(int)); - while (*cp) - if (*cp == '$') - { - *dp++ = ' '; - cp++; - } - else if (*cp == '.') - { - *dp++ = ZEBRA_REPLACE_ANY; - cp++; - } - else - { - *dp++ = zebra_prim(&cp); -#if 0 - yaz_log (YLOG_LOG, " char %2X %c", dp[-1], dp[-1]); -#endif - } - *dp = '\0'; - } - if (argc >= 3) - { - char *cp = argv[2]; - char *dp = token->token_to = - nmem_malloc (zms->nmem, strlen(cp)+1); - while (*cp) - if (*cp == '$') - { - *dp++ = ' '; - cp++; - } - else - *dp++ = zebra_prim(&cp); - *dp = '\0'; - } - else - token->token_to = 0; - } } if (zm) (*zm)->next = NULL; @@ -246,7 +183,6 @@ ZebraMaps zebra_maps_open (Res res, const char *base) zebra_map_read (zms, "default.idx"); zms->wrbuf_1 = wrbuf_alloc(); - zms->wrbuf_2 = wrbuf_alloc(); return zms; } @@ -270,7 +206,6 @@ chrmaptab zebra_charmap_get (ZebraMaps zms, unsigned reg_id) zm->type = ZEBRA_MAP_TYPE_INDEX; zm->completeness = 0; zm->next = zms->map_list; - zm->replace_tokens = 0; zms->map_list = zm->next; zms->lookup_array[zm->reg_id & 255] = zm; @@ -558,108 +493,11 @@ int zebra_maps_attr (ZebraMaps zms, Z_AttributesPlusTerm *zapt, return 0; } -int zebra_replace_sub(ZebraMaps zms, unsigned reg_id, const char *ex_list, - const char *input_str, int input_len, WRBUF wrbuf); - WRBUF zebra_replace(ZebraMaps zms, unsigned reg_id, const char *ex_list, const char *input_str, int input_len) { - struct zebra_map *zm = zebra_map_get (zms, reg_id); - wrbuf_rewind(zms->wrbuf_1); wrbuf_write(zms->wrbuf_1, input_str, input_len); - if (!zm || !zm->replace_tokens) - return zms->wrbuf_1; - -#if 0 - yaz_log (YLOG_LOG, "in:%.*s:", wrbuf_len(zms->wrbuf_1), - wrbuf_buf(zms->wrbuf_1)); -#endif - for (;;) - { - if (!zebra_replace_sub(zms, reg_id, ex_list, wrbuf_buf(zms->wrbuf_1), - wrbuf_len(zms->wrbuf_1), zms->wrbuf_2)) - return zms->wrbuf_2; - if (!zebra_replace_sub(zms, reg_id, ex_list, wrbuf_buf(zms->wrbuf_2), - wrbuf_len(zms->wrbuf_2), zms->wrbuf_1)) - return zms->wrbuf_1; - } - return 0; + return zms->wrbuf_1; } -int zebra_replace_sub(ZebraMaps zms, unsigned reg_id, const char *ex_list, - const char *input_str, int input_len, WRBUF wrbuf) -{ - int i = -1; - int no_replaces = 0; - struct zebra_map *zm = zebra_map_get (zms, reg_id); - - wrbuf_rewind(wrbuf); - for (i = -1; i <= input_len; ) - { - struct zm_token *token; - char replace_string[128]; - int replace_out = 0; - int replace_in = 0; - - for (token = zm->replace_tokens; !replace_in && token; - token = token->next) - { - int j = 0; - int replace_done = 0; - replace_out = 0; - for (;; j++) - { - int c; - if (!token->token_from[j]) - { - replace_in = j; - break; - } - if (ex_list && strchr (ex_list, token->token_from[j])) - break; - if (i+j < 0 || j+i >= input_len) - c = ' '; - else - c = input_str[j+i] & 255; - if (token->token_from[j] == ZEBRA_REPLACE_ANY) - { - if (c == ' ') - break; - replace_string[replace_out++] = c; - } - else - { - if (c != token->token_from[j]) - { - break; - } - if (!replace_done) - { - const char *cp = token->token_to; - replace_done = 1; - for (; cp && *cp; cp++) - replace_string[replace_out++] = *cp; - } - } - } - } - if (!replace_in) - { - if (i >= 0 && i < input_len) - wrbuf_putc(wrbuf, input_str[i]); - i++; - } - else - { - no_replaces++; - if (replace_out) - wrbuf_write(wrbuf, replace_string, replace_out); - i += replace_in; - } - } -#if 0 - yaz_log (YLOG_LOG, "out:%.*s:", wrbuf_len(wrbuf), wrbuf_buf(wrbuf)); -#endif - return no_replaces; -}