From 4c1a14ddb2c650b935bc8dff4dc3f8a98ff7531c Mon Sep 17 00:00:00 2001 From: Adam Dickmeiss Date: Tue, 29 Jan 2013 14:46:21 +0100 Subject: [PATCH] Complete XML to OPAC conversion --- include/yaz/marcdisp.h | 6 ++- src/xml_to_opac.c | 107 +++++++++++++++++++++++++++++++++++++++++++++-- test/test_record_conv.c | 69 ++++++++++++++++++++++++++++-- 3 files changed, 173 insertions(+), 9 deletions(-) diff --git a/include/yaz/marcdisp.h b/include/yaz/marcdisp.h index 3c98b5b..752de41 100644 --- a/include/yaz/marcdisp.h +++ b/include/yaz/marcdisp.h @@ -441,14 +441,16 @@ YAZ_EXPORT void yaz_opac_decode_wrbuf2(yaz_marc_t mt, Z_OPACRecord *r, #if YAZ_HAVE_XML2 /** \brief Converts XML to OPAC \param mt marc handle - \param src XML root node (presumably opacRecord node) + \param buf_in XML buffer + \param size_in size of XML buffer \param dst Z39.50 OPAC result - allocated by NMEM on marc handle \param cd iconv handle for the OPAC content (not ISO2709 part) \param nmem memory for OPACRecord (if NULL, mt NMEM memory is used) \retval 1 conversion OK \retval 0 conversion NOT OK \*/ -YAZ_EXPORT int yaz_xml_to_opac(yaz_marc_t mt, xmlNode *src, +YAZ_EXPORT int yaz_xml_to_opac(yaz_marc_t mt, + const char *buf_in, size_t size_in, Z_OPACRecord **dst, yaz_iconv_t cd, NMEM nmem); #endif diff --git a/src/xml_to_opac.c b/src/xml_to_opac.c index 004f308..e6735c9 100644 --- a/src/xml_to_opac.c +++ b/src/xml_to_opac.c @@ -63,6 +63,37 @@ static int match_element_next(xmlNode **ptr, const char *elem, NMEM nmem, return 0; } +static int match_v_next(xmlNode **ptr, const char *elem, NMEM nmem, + Odr_bool **val) +{ + while (*ptr && (*ptr)->type != XML_ELEMENT_NODE) + (*ptr) = (*ptr)->next; + *val = nmem_booldup(nmem, 0); + if (*ptr && match_element(*ptr, elem)) + { + struct _xmlAttr *attr = (*ptr)->properties; + + *ptr = (*ptr)->next; + for (; attr; attr = attr->next) + { + if (!strcmp((const char *) attr->name, "value")) + { + if (attr->children->type == XML_TEXT_NODE) + { + if (attr->children->content[0] == '0') + return 1; + else if (attr->children->content[0] == '1') + { + **val = 1; + return 1; + } + } + } + } + } + return 0; +} + static int bibliographicRecord(yaz_marc_t mt, xmlNode *ptr, Z_External **ext, yaz_iconv_t cd, NMEM nmem) { @@ -100,6 +131,8 @@ static int volumes(xmlNode *ptr, Z_Volume ***volp, int *num, NMEM nmem) { while (ptr && ptr->type != XML_ELEMENT_NODE) ptr = ptr->next; + if (!ptr) + break; if (!match_element(ptr, "volume")) return 0; ptr = ptr->next; @@ -111,6 +144,8 @@ static int volumes(xmlNode *ptr, Z_Volume ***volp, int *num, NMEM nmem) { while (ptr && ptr->type != XML_ELEMENT_NODE) ptr = ptr->next; + if (!ptr) + break; if (!match_element(ptr, "volume")) return 0; volume(ptr->children, (*volp) + i, nmem); @@ -119,10 +154,57 @@ static int volumes(xmlNode *ptr, Z_Volume ***volp, int *num, NMEM nmem) return 1; } -static void circulations(xmlNode *ptr, Z_CircRecord ***circp, - int *num, NMEM nmem) +static int circulation(xmlNode *ptr, Z_CircRecord **circp, NMEM nmem) { + *circp = (Z_CircRecord *) nmem_malloc(nmem, sizeof(Z_CircRecord)); + match_v_next(&ptr, "availableNow", nmem, &(*circp)->availableNow); + /* note the spelling of the ASN.1 member below */ + match_element_next(&ptr, "availabilityDate", nmem, + &(*circp)->availablityDate); + match_element_next(&ptr, "availableThru", nmem, &(*circp)->availableThru); + match_element_next(&ptr, "restrictions", nmem, &(*circp)->restrictions); + match_element_next(&ptr, "itemId", nmem, &(*circp)->itemId); + match_v_next(&ptr, "renewable", nmem, &(*circp)->renewable); + match_v_next(&ptr, "onHold", nmem, &(*circp)->onHold); + match_element_next(&ptr, "enumAndChron", nmem, &(*circp)->enumAndChron); + match_element_next(&ptr, "midspine", nmem, &(*circp)->midspine); + match_element_next(&ptr, "temporaryLocation", nmem, + &(*circp)->temporaryLocation); + return 1; +} + +static int circulations(xmlNode *ptr, Z_CircRecord ***circp, + int *num, NMEM nmem) +{ + int i; + xmlNode *ptr0 = ptr; + + for (i = 0; ptr; i++) + { + while (ptr && ptr->type != XML_ELEMENT_NODE) + ptr = ptr->next; + if (!ptr) + break; + if (!match_element(ptr, "circulation")) + return 0; + ptr = ptr->next; + } + *num = i; + *circp = (Z_CircRecord **) nmem_malloc(nmem, sizeof(**circp) * i); + ptr = ptr0; + for (i = 0; ptr; i++) + { + while (ptr && ptr->type != XML_ELEMENT_NODE) + ptr = ptr->next; + if (!ptr) + break; + if (!match_element(ptr, "circulation")) + return 0; + circulation(ptr->children, (*circp) + i, nmem); + ptr = ptr->next; + } + return 1; } static int holdingsRecord(xmlNode *ptr, Z_HoldingsRecord **r, NMEM nmem) @@ -176,8 +258,9 @@ static int holdingsRecord(xmlNode *ptr, Z_HoldingsRecord **r, NMEM nmem) return 1; } -int yaz_xml_to_opac(yaz_marc_t mt, xmlNode *ptr, Z_OPACRecord **dst, - yaz_iconv_t cd, NMEM nmem) +static int yaz_xml_to_opac_ptr(yaz_marc_t mt, xmlNode *ptr, + Z_OPACRecord **dst, + yaz_iconv_t cd, NMEM nmem) { int i; Z_External *ext = 0; @@ -200,6 +283,7 @@ int yaz_xml_to_opac(yaz_marc_t mt, xmlNode *ptr, Z_OPACRecord **dst, opac->holdingsData = 0; opac->bibliographicRecord = ext; + ptr = ptr->next; while (ptr && ptr->type != XML_ELEMENT_NODE) ptr = ptr->next; if (!match_element(ptr, "holdings")) @@ -236,6 +320,21 @@ int yaz_xml_to_opac(yaz_marc_t mt, xmlNode *ptr, Z_OPACRecord **dst, } return 1; } + +int yaz_xml_to_opac(yaz_marc_t mt, const char *buf_in, size_t size_in, + Z_OPACRecord **dst, yaz_iconv_t cd, NMEM nmem) +{ + xmlDocPtr doc = xmlParseMemory(buf_in, size_in); + int r = 0; + if (doc) + { + r = yaz_xml_to_opac_ptr(mt, xmlDocGetRootElement(doc), dst, cd, nmem); + xmlFreeDoc(doc); + } + return r; +} + + #endif /* diff --git a/test/test_record_conv.c b/test/test_record_conv.c index 1e1d2b0..3cb5bfd 100644 --- a/test/test_record_conv.c +++ b/test/test_record_conv.c @@ -363,7 +363,7 @@ static void tst_convert3(void) " 00077nam a22000498a 4500\n" " 11224466 \n" " \n" - " k" "\xc3" "\xb8" /* oslash in UTF_8 */ + " k" "\xc3" "\xb8" /* oslash in UTF_8 */ "benhavn\n" " \n" "\n" @@ -379,9 +379,22 @@ static void tst_convert3(void) " MLCM 89/00602 (N)\n" " FT MEADE\n" " Copy 1\n" + " \n" + " \n" + " 1\n" + " 2\n" + " 3\n" + " \n" + " \n" + " 1\n" + " 2\n" + " 3\n" + " \n" + " \n" " \n" " \n" " \n" + " 20130129\n" " 1226176\n" " \n" " \n" @@ -425,15 +438,27 @@ static void tst_convert3(void) h->reproductionNote = 0; h->termsUseRepro = 0; h->enumAndChron = 0; - h->num_volumes = 0; + h->num_volumes = 2; h->volumes = 0; + + h->volumes = (Z_Volume **) + nmem_malloc(nmem, 2 * sizeof(Z_Volume *)); + + h->volumes[0] = (Z_Volume *) + nmem_malloc(nmem, sizeof(Z_Volume)); + h->volumes[1] = h->volumes[0]; + + h->volumes[0]->enumeration = nmem_strdup(nmem, "1"); + h->volumes[0]->chronology = nmem_strdup(nmem, "2"); + h->volumes[0]->enumAndChron = nmem_strdup(nmem, "3"); + h->num_circulationData = 1; h->circulationData = (Z_CircRecord **) nmem_malloc(nmem, 1 * sizeof(Z_CircRecord *)); circ = h->circulationData[0] = (Z_CircRecord *) nmem_malloc(nmem, sizeof(Z_CircRecord)); circ->availableNow = nmem_booldup(nmem, 1); - circ->availablityDate = 0; + circ->availablityDate = nmem_strdup(nmem, "20130129"); circ->availableThru = 0; circ->restrictions = 0; circ->itemId = nmem_strdup(nmem, "1226176"); @@ -475,6 +500,44 @@ static void tst_convert3(void) yaz_record_conv_destroy(p); wrbuf_destroy(output_record); } + { + Z_OPACRecord *opac = 0; + yaz_marc_t mt = yaz_marc_create(); + ret = yaz_xml_to_opac(mt, opacxml_rec, strlen(opacxml_rec), + &opac, 0 /* iconv */, nmem); + YAZ_CHECK(ret); + YAZ_CHECK(opac); + + if (opac) + { + WRBUF output_record = wrbuf_alloc(); + char *p; + + yaz_marc_xml(mt, YAZ_MARC_MARCXML); + yaz_opac_decode_wrbuf(mt, opac, output_record); + + /* change MARC size to 00077 from 00078, due to + encoding of the aring (two bytes in UTF-8) */ + p = strstr(wrbuf_buf(output_record), "00078"); + YAZ_CHECK(p); + if (p) + p[4] = '7'; + + ret = strcmp(wrbuf_cstr(output_record), opacxml_rec); + YAZ_CHECK(ret == 0); + if (ret) + { + printf("got-output_record len=%ld: %s\n", + (long) wrbuf_len(output_record), + wrbuf_cstr(output_record)); + printf("output_expect_record len=%ld %s\n", + (long) strlen(opacxml_rec), + opacxml_rec); + } + wrbuf_destroy(output_record); + } + yaz_marc_destroy(mt); + } nmem_destroy(nmem); } -- 1.7.10.4