X-Git-Url: http://jsfdemo.indexdata.com/?a=blobdiff_plain;f=src%2Fcharsets.c;h=f931445cd3d5fb934febe429d94e9f37aae4ff3d;hb=20bc8b17d60373c2c93ab6bb777d19dd92ed2960;hp=f0f1af03e62b15b126db5392abfde4e4af932fe1;hpb=ecc2d7d3b2289501b5b28e4d34299b54934b733f;p=pazpar2-moved-to-github.git diff --git a/src/charsets.c b/src/charsets.c index f0f1af0..f931445 100644 --- a/src/charsets.c +++ b/src/charsets.c @@ -1,5 +1,5 @@ /* This file is part of Pazpar2. - Copyright (C) 2006-2011 Index Data + Copyright (C) 2006-2013 Index Data Pazpar2 is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free @@ -36,17 +36,18 @@ Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA #include "charsets.h" #include "normalize7bit.h" -#if YAZ_HAVE_ICU -#include -#endif - typedef struct pp2_charset_s *pp2_charset_t; static pp2_charset_t pp2_charset_create_xml(xmlNode *xml_node); -static pp2_charset_t pp2_charset_create(struct icu_chain * icu_chn); +static pp2_charset_t pp2_charset_create(void); static pp2_charset_t pp2_charset_create_a_to_z(void); static void pp2_charset_destroy(pp2_charset_t pct); static pp2_charset_token_t pp2_charset_tokenize(pp2_charset_t pct); +#if YAZ_HAVE_ICU +#include +static pp2_charset_t pp2_charset_create_icu(struct icu_chain *icu_chn); +#endif + /* charset handle */ struct pp2_charset_s { const char *(*token_next_handler)(pp2_charset_token_t prt); @@ -105,7 +106,7 @@ pp2_charset_fact_t pp2_charset_fact_create(void) pp2_charset_fact_add(pft, pp2_charset_create_a_to_z(), "relevance"); pp2_charset_fact_add(pft, pp2_charset_create_a_to_z(), "sort"); pp2_charset_fact_add(pft, pp2_charset_create_a_to_z(), "mergekey"); - pp2_charset_fact_add(pft, pp2_charset_create(0), "facet"); + pp2_charset_fact_add(pft, pp2_charset_create(), "facet"); return pft; } @@ -201,31 +202,24 @@ pp2_charset_t pp2_charset_create_xml(xmlNode *xml_node) //xmlChar *xmlstr = 0; //int size = 0; //xmlDocDumpMemory(icu_doc, size); - + yaz_log(YLOG_FATAL, "Could not parse ICU chain config:\n" "<%s>\n ... \n", xml_node->name, xml_node->name); return 0; } - return pp2_charset_create(chain); + return pp2_charset_create_icu(chain); #else // YAZ_HAVE_ICU yaz_log(YLOG_FATAL, "Error: ICU support requested with element:\n" "<%s>\n ... \n", xml_node->name, xml_node->name); - yaz_log(YLOG_FATAL, + yaz_log(YLOG_FATAL, "But no ICU support is compiled into the YAZ library."); return 0; #endif // YAZ_HAVE_ICU } -pp2_charset_t pp2_charset_create_a_to_z(void) -{ - pp2_charset_t pct = pp2_charset_create(0); - pct->token_next_handler = pp2_charset_token_a_to_z; - return pct; -} - -pp2_charset_t pp2_charset_create(struct icu_chain *icu_chn) +pp2_charset_t pp2_charset_create(void) { pp2_charset_t pct = xmalloc(sizeof(*pct)); @@ -234,6 +228,21 @@ pp2_charset_t pp2_charset_create(struct icu_chain *icu_chn) pct->get_display_handler = pp2_get_display_ascii; #if YAZ_HAVE_ICU pct->icu_chn = 0; +#endif // YAZ_HAVE_ICU + return pct; +} + +pp2_charset_t pp2_charset_create_a_to_z(void) +{ + pp2_charset_t pct = pp2_charset_create(); + pct->token_next_handler = pp2_charset_token_a_to_z; + return pct; +} + +#if YAZ_HAVE_ICU +pp2_charset_t pp2_charset_create_icu(struct icu_chain *icu_chn) +{ + pp2_charset_t pct = pp2_charset_create(); if (icu_chn) { pct->icu_chn = icu_chn; @@ -242,9 +251,9 @@ pp2_charset_t pp2_charset_create(struct icu_chain *icu_chn) pct->get_sort_handler = pp2_get_sort_icu; pct->get_display_handler = pp2_get_display_icu; } -#endif // YAZ_HAVE_ICU return pct; } +#endif // YAZ_HAVE_ICU void pp2_charset_destroy(pp2_charset_t pct) { @@ -286,14 +295,14 @@ pp2_charset_token_t pp2_charset_tokenize(pp2_charset_t pct) void pp2_charset_token_first(pp2_charset_token_t prt, const char *buf, int skip_article) -{ +{ if (skip_article) { const char *p = buf; char firstword[64]; char *pout = firstword; char articles[] = "the den der die des an a "; // must end in space - + for (; *p && *p != ' ' && pout - firstword < (sizeof(firstword)-2); p++) *pout++ = tolower(*(unsigned char *)p); *pout++ = ' '; @@ -322,9 +331,9 @@ void pp2_charset_token_destroy(pp2_charset_token_t prt) if (prt->iter) icu_iter_destroy(prt->iter); #endif - if(prt->norm_str) + if(prt->norm_str) wrbuf_destroy(prt->norm_str); - if(prt->sort_str) + if(prt->sort_str) wrbuf_destroy(prt->sort_str); xfree(prt); } @@ -385,7 +394,7 @@ static const char *pp2_get_sort_ascii(pp2_charset_token_t prt) char *tmp = xstrdup(prt->last_cp); char *result = 0; result = normalize7bit_mergekey(tmp); - + wrbuf_rewind(prt->sort_str); wrbuf_puts(prt->sort_str, result); xfree(tmp);