X-Git-Url: http://git.indexdata.com/?a=blobdiff_plain;f=doc%2Ftools.xml;h=d47683fc1d4dbb6bbe05dee6975880f0cb359a1e;hb=9c70253e4c7eedab806490b87a9a58e970998429;hp=accbb5959a0de907dd38cd964a85314928cc82b4;hpb=d1ad544488a515cb6ad80d1b98863baa57abb567;p=yaz-moved-to-github.git diff --git a/doc/tools.xml b/doc/tools.xml index accbb59..d47683f 100644 --- a/doc/tools.xml +++ b/doc/tools.xml @@ -1,4 +1,4 @@ - + Supporting Tools @@ -225,7 +225,7 @@ @and. Its semantics are described in section 3.7.2 (Proximity) of Z39.50 the standard itself, which can be read on-line at - + In PQF, the proximity operation is represented by a sequence @@ -294,108 +294,126 @@ (The numeric values of the relation and well-known unit-code parameters are taken straight from - the ASN.1 of the proximity structure in the standard.) PQF queries - Queries using simple terms. - - dylan - "bob dylan" - - - Boolean operators. - - @or "dylan" "zimmerman" - @and @or dylan zimmerman when - @and when @or dylan zimmerman - - - - Reference to result sets. - - @set Result-1 - @and @set seta setb - - - - Attributes for terms. - - @attr 1=4 computer - @attr 1=4 @attr 4=1 "self portrait" - @attrset exp1 @attr 1=1 CategoryList - @attr gils 1=2008 Copenhagen - @attr 1=/book/title computer - - - - Proximity. - - @prox 0 3 1 2 k 2 dylan zimmerman - - - Here the parameters 0, 3, 1, 2, k and 2 represent exclusion, - distance, ordered, relation, which-code and unit-code, in that - order. So: - - - exclusion = 0: the proximity condition must hold - - - distance = 3: the terms must be three units apart - - - ordered = 1: they must occur in the order they are specified - - - relation = 2: lessThanOrEqual (to the distance of 3 units) - - - which-code is ``known'', so the standard unit-codes are used - - - unit-code = 2: word. - - - So the whole proximity query means that the words - dylan and zimmerman must - both occur in the record, in that order, differing in position - by three or fewer words (i.e. with two or fewer words between - them.) The query would find ``Bob Dylan, aka. Robert - Zimmerman'', but not ``Bob Dylan, born as Robert Zimmerman'' - since the distance in this case is four. - - - - Specifying term type. - - @term string "a UTF-8 string, maybe?" - - - Mixed queries - - @or @and bob dylan @set Result-1 - - @attr 4=1 @and @attr 1=1 "bob dylan" @attr 1=4 "slow train coming" - - @and @attr 2=4 @attr gils 1=2038 -114 @attr 2=2 @attr gils 1=2039 -109 + PQF queries using simple terms + + + dylan + + "bob dylan" + + + + PQF boolean operators + + + @or "dylan" "zimmerman" + + @and @or dylan zimmerman when + + @and when @or dylan zimmerman + + + + PQF references to result sets + + + @set Result-1 + + @and @set seta @set setb + + + + Attributes for terms + + + @attr 1=4 computer + + @attr 1=4 @attr 4=1 "self portrait" + + @attrset exp1 @attr 1=1 CategoryList + + @attr gils 1=2008 Copenhagen + + @attr 1=/book/title computer + + + + PQF Proximity queries + + + @prox 0 3 1 2 k 2 dylan zimmerman + + + Here the parameters 0, 3, 1, 2, k and 2 represent exclusion, + distance, ordered, relation, which-code and unit-code, in that + order. So: + + + exclusion = 0: the proximity condition must hold + + + distance = 3: the terms must be three units apart + + + ordered = 1: they must occur in the order they are specified + + + relation = 2: lessThanOrEqual (to the distance of 3 units) + + + which-code is ``known'', so the standard unit-codes are used + + + unit-code = 2: word. + + + So the whole proximity query means that the words + dylan and zimmerman must + both occur in the record, in that order, differing in position + by three or fewer words (i.e. with two or fewer words between + them.) The query would find ``Bob Dylan, aka. Robert + Zimmerman'', but not ``Bob Dylan, born as Robert Zimmerman'' + since the distance in this case is four. + + + + PQF specification of search term + + + @term string "a UTF-8 string, maybe?" + + + + PQF mixed queries + + + @or @and bob dylan @set Result-1 + + @attr 4=1 @and @attr 1=1 "bob dylan" @attr 1=4 "slow train coming" + + @and @attr 2=4 @attr gils 1=2038 -114 @attr 2=2 @attr gils 1=2039 -109 - + - The last of these examples is a spatial search: in - the GILS attribute set, - access point - 2038 indicates West Bounding Coordinate and - 2030 indicates East Bounding Coordinate, - so the query is for areas extending from -114 degrees - to no more than -109 degrees. + access point + 2038 indicates West Bounding Coordinate and + 2030 indicates East Bounding Coordinate, + so the query is for areas extending from -114 degrees + to no more than -109 degrees. - - + + + CCL @@ -411,8 +429,7 @@ - The EUROPAGATE - research project working under the Libraries programme + The EUROPAGATE research project working under the Libraries programme of the European Commission's DG XIII has, amongst other useful tools, implemented a general-purpose CCL parser which produces an output structure that can be trivially converted to the internal RPN @@ -566,7 +583,7 @@ u=value - Use attribute. Common use attributes are + Use attribute (1). Common use attributes are 1 Personal-name, 4 Title, 7 ISBN, 8 ISSN, 30 Date, 62 Subject, 1003 Author), 1016 Any. Specify value as an integer. @@ -576,7 +593,7 @@ r=value - Relation attribute. Common values are + Relation attribute (2). Common values are 1 <, 2 <=, 3 =, 4 >=, 5 >, 6 <>, 100 phonetic, 101 stem, 102 relevance, 103 always matches. @@ -585,7 +602,7 @@ p=value - Position attribute. Values: 1 first in field, 2 + Position attribute (3). Values: 1 first in field, 2 first in any subfield, 3 any position in field. @@ -593,7 +610,7 @@ s=value - Structure attribute. Values: 1 phrase, 2 word, + Structure attribute (4). Values: 1 phrase, 2 word, 3 key, 4 year, 5 date, 6 word list, 100 date (un), 101 name (norm), 102 name (un), 103 structure, 104 urx, 105 free-form-text, 106 document-text, 107 local-number, @@ -604,7 +621,7 @@ t=value - Truncation attribute. Values: 1 right, 2 left, + Truncation attribute (5). Values: 1 right, 2 left, 3 left& right, 100 none, 101 process #, 102 regular-1, 103 regular-2, 104 CCL. @@ -613,7 +630,7 @@ c=value - Completeness attribute. Values: 1 incomplete subfield, + Completeness attribute (6). Values: 1 incomplete subfield, 2 complete subfield, 3 complete field. @@ -623,10 +640,8 @@ - The complete list of Bib-1 attributes can be found - - here - . + Refer to the complete + list of Bib-1 attributes It is also possible to specify non-numeric attribute values, @@ -664,8 +679,27 @@ r=o - Allows operators greather-than, less-than, ... equals and - sets relation attribute accordingly (relation ordered). + Allows ranges and the operators greather-than, less-than, ... + equals. + This sets Bib-1 relation attribute accordingly (relation + ordered). A query construct is only treated as a range if + dash is used and that is surrounded by white-space. So + -1980 is treated as term + "-1980" not <= 1980. + If - 1980 is used, however, that is + treated as a range. + + + + r=r + Similar to r=o but assumes that terms + are non-negative (not prefixed with -). + Thus, a dash will always be treated as a range. + The construct 1980-1990 is + treated as a range with r=r but as a + single term "1980-1990" with + r=o. The special attribute + r=r is available in YAZ 2.0.24 or later. @@ -713,11 +747,6 @@ date u=30 r=o - Four qualifiers are defined - ti, - au, ranked and - date. - - ti and au both set structure attribute to phrase (s=1). ti @@ -740,9 +769,9 @@ Query - year > 1980 + date > 1980 - is a valid query, while + is a valid query. But ti > 1980 @@ -763,7 +792,7 @@ be an alias for q1, q2... such that the CCL query q=x is equivalent to - q1=x or w2=x or .... + q1=x or q2=x or .... @@ -909,20 +938,18 @@ struct ccl_rpn_node *ccl_find_str (CCL_bibset bibset, const char *str, CQL - CQL + CQL - Common Query Language - was defined for the - SRW - protocol. + SRU protocol. In many ways CQL has a similar syntax to CCL. The objective of CQL is different. Where CCL aims to be an end-user language, CQL is the protocol - query language for SRW. + query language for SRU. If you are new to CQL, read the - Gentle - Introduction. + Gentle Introduction. @@ -942,17 +969,16 @@ struct ccl_rpn_node *ccl_find_str (CCL_bibset bibset, const char *str, The parser converts a valid CQL query to PQF, thus providing a - way to use CQL for both SRW/SRU servers and Z39.50 targets at the + way to use CQL for both SRU servers and Z39.50 targets at the same time. The parser converts CQL to - - XCQL. + XCQL. XCQL is an XML representation of CQL. - XCQL is part of the SRW specification. However, since SRU + XCQL is part of the SRU specification. However, since SRU supports CQL only, we don't expect XCQL to be widely used. Furthermore, CQL has the advantage over XCQL that it is easy to read. @@ -1026,34 +1052,28 @@ struct cql_node *cql_parser_result(CQL_parser cp); #define CQL_NODE_ST 1 #define CQL_NODE_BOOL 2 -#define CQL_NODE_MOD 3 struct cql_node { int which; union { struct { char *index; + char *index_uri; char *term; char *relation; + char *relation_uri; struct cql_node *modifiers; - struct cql_node *prefixes; } st; struct { char *value; struct cql_node *left; struct cql_node *right; struct cql_node *modifiers; - struct cql_node *prefixes; } boolean; - struct { - char *name; - char *value; - struct cql_node *next; - } mod; } u; }; - There are three kinds of nodes, search term (ST), boolean (BOOL), - and modifier (MOD). + There are two node types: search term (ST) and boolean (BOOL). + A modifier is treated as a search term too. The search term node has five members: @@ -1067,6 +1087,12 @@ struct cql_node { + index_uri: index URi for search term + or NULL if none could be resolved for the index. + + + + term: the search term itself. @@ -1077,18 +1103,14 @@ struct cql_node { - modifiers: relation modifiers for search - term. The modifiers is a simple linked - list (NULL for last entry). Each relation modifier node - is of type MOD. + relation_uri: relation URI for search term. - prefixes: index prefixes for search - term. The prefixes is a simple linked - list (NULL for last entry). Each prefix node - is of type MOD. + modifiers: relation modifiers for search + term. The modifiers list itself of cql_nodes + each of type ST. @@ -1110,37 +1132,6 @@ struct cql_node { modifiers: proximity arguments. - - - prefixes: index prefixes. - The prefixes is a simple linked - list (NULL for last entry). Each prefix node - is of type MOD. - - - - - - - The modifier node is a "utility" node used for name-value pairs, - such as prefixes, proximity arguements, etc. - - - - name name of mod node. - - - - - value value of mod node. - - - - - next: pointer to next node which is - always a mod node (NULL for last entry). - - @@ -1150,7 +1141,7 @@ struct cql_node { Conversion to PQF (and Z39.50 RPN) is tricky by the fact that the resulting RPN depends on the Z39.50 target capabilities (combinations of supported attributes). - In addition, the CQL and SRW operates on index prefixes + In addition, the CQL and SRU operates on index prefixes (URI or strings), whereas the RPN uses Object Identifiers for attribute sets. @@ -1185,10 +1176,10 @@ int cql_transform_buf(cql_transform_t ct, If conversion failed, cql_transform_buf - returns a non-zero SRW error code; otherwise zero is returned + returns a non-zero SRU error code; otherwise zero is returned (conversion successful). The meanings of the numeric error - codes are listed in the SRW specifications at - + codes are listed in the SRU specifications at + If conversion fails, more information can be obtained by calling @@ -1199,12 +1190,12 @@ int cql_transform_error(cql_transform_t ct, char **addinfop); error-code and sets the string-pointer at *addinfop to point to a string containing additional information about the error that occurred: for - example, if the error code is 15 (``Illegal or unsupported index + example, if the error code is 15 (``Illegal or unsupported context set''), the additional information is the name of the requested - index set that was not recognised. + context set that was not recognised. - The SRW error-codes may be translated into brief human-readable + The SRU error-codes may be translated into brief human-readable error messages using const char *cql_strerror(int code); @@ -1228,7 +1219,7 @@ int cql_transform_FILE(cql_transform_t ct, - Specification of CQL to RPN mapping + Specification of CQL to RPN mappings The file supplied to functions cql_transform_open_FILE, @@ -1257,26 +1248,37 @@ int cql_transform_FILE(cql_transform_t ct, The following CQL patterns are recognized: - qualifier.set.name + index.set.name - This pattern is invoked when a CQL qualifier, such as + This pattern is invoked when a CQL index, such as dc.title is converted. set - and name is the index set and qualifier + and name are the context set and index name respectively. Typically, the RPN specifies an equivalent use attribute. - For terms not bound by a qualifier the pattern - qualifier.srw.serverChoice is used. - Here, the prefix srw is defined as - http://www.loc.gov/zing/cql/srw-indexes/v1.0/. + For terms not bound by an index the pattern + index.cql.serverChoice is used. + Here, the prefix cql is defined as + http://www.loc.gov/zing/cql/cql-indexes/v1.0/. If this pattern is not defined, the mapping will fail. + qualifier.set.name + (DEPRECATED) + + + + For backwards compatibility, this is recognised as a synonym of + index.set.name + + + + relation.relation @@ -1358,10 +1360,10 @@ int cql_transform_FILE(cql_transform_t ct, - This specification defines a CQL index set for a given prefix. + This specification defines a CQL context set for a given prefix. The value on the right hand side is the URI for the set - not RPN. All prefixes used in - qualifier patterns must be defined this way. + index patterns must be defined this way. @@ -1369,16 +1371,16 @@ int cql_transform_FILE(cql_transform_t ct, CQL to RPN mapping file - This simple file defines two index sets, three qualifiers and three + This simple file defines two context sets, three indexes and three relations, a position pattern and a default structure. @attr 1=1016 @attr 2=3 @attr 4=1 @attr 3=3 @attr 6=1 "computer" - by rules qualifier.srw.serverChoice, + by rules index.cql.serverChoice, relation.scr, structure.*, position.any. @@ -1601,7 +1603,7 @@ typedef struct oident again, corresponding to the specific OIDs defined by the standard. Refer to the - + Registry of Z39.50 Object Identifiers for the whole list. @@ -1748,7 +1750,7 @@ typedef struct oident release the associated memory again. For the structures describing the Z39.50 PDUs and related structures, it is convenient to use the memory-management system of the &odr; subsystem (see - Using ODR). However, in some circumstances + ). However, in some circumstances where you might otherwise benefit from using a simple nibble memory management system, it may be impractical to use odr_malloc() and odr_reset(). @@ -1798,6 +1800,267 @@ typedef struct oident + + Log + + &yaz; has evolved a fairly complex log system which should be useful both + for debugging &yaz; itself, debugging applications that use &yaz;, and for + production use of those applications. + + + The log functions are declared in header yaz/log.h + and implemented in src/log.c. + Due to name clash with syslog and some math utilities the logging + interface has been modified as of YAZ 2.0.29. The obsolete interface + is still available if in header file yaz/log.h. + The key points of the interface are: + + + void yaz_log(int level, const char *fmt, ...) + + void yaz_log_init(int level, const char *prefix, const char *name); + void yaz_log_init_file(const char *fname); + void yaz_log_init_level(int level); + void yaz_log_init_prefix(const char *prefix); + void yaz_log_time_format(const char *fmt); + void yaz_log_init_max_size(int mx); + + int yaz_log_mask_str(const char *str); + int yaz_log_module_level(const char *name); + + + + The reason for the whole log module is the yaz_log + function. It takes a bitmask indicating the log levels, a + printf-like format string, and a variable number of + arguments to log. + + + + The log level is a bit mask, that says on which level(s) + the log entry should be made, and optionally set some behaviour of the + logging. In the most simple cases, it can be one of YLOG_FATAL, + YLOG_DEBUG, YLOG_WARN, YLOG_LOG. Those can be combined with bits + that modify the way the log entry is written:YLOG_ERRNO, + YLOG_NOTIME, YLOG_FLUSH. + Most of the rest of the bits are deprecated, and should not be used. Use + the dynamic log levels instead. + + + + Applications that use &yaz;, should not use the LOG_LOG for ordinary + messages, but should make use of the dynamic loglevel system. This consists + of two parts, defining the loglevel and checking it. + + + + To define the log levels, the (main) program should pass a string to + yaz_log_mask_str to define which log levels are to be + logged. This string should be a comma-separated list of log level names, + and can contain both hard-coded names and dynamic ones. The log level + calculation starts with YLOG_DEFAULT_LEVEL and adds a bit + for each word it meets, unless the word starts with a '-', in which case it + clears the bit. If the string 'none' is found, + all bits are cleared. Typically this string comes from the command-line, + often identified by -v. The + yaz_log_mask_str returns a log level that should be + passed to yaz_log_init_level for it to take effect. + + + + Each module should check what log bits it should be used, by calling + yaz_log_module_level with a suitable name for the + module. The name is cleared from a preceding path and an extension, if any, + so it is quite possible to use __FILE__ for it. If the + name has been passed to yaz_log_mask_str, the routine + returns a non-zero bitmask, which should then be used in consequent calls + to yaz_log. (It can also be tested, so as to avoid unnecessary calls to + yaz_log, in time-critical places, or when the log entry would take time + to construct.) + + + + Yaz uses the following dynamic log levels: + server, session, request, requestdetail for the server + functionality. + zoom for the zoom client api. + ztest for the simple test server. + malloc, nmem, odr, eventl for internal debugging of yaz itself. + Of course, any program using yaz is welcome to define as many new ones, as + it needs. + + + + By default the log is written to stderr, but this can be changed by a call + to yaz_log_init_file or + yaz_log_init. If the log is directed to a file, the + file size is checked at every write, and if it exceeds the limit given in + yaz_log_init_max_size, the log is rotated. The + rotation keeps one old version (with a .1 appended to + the name). The size defaults to 1GB. Setting it to zero will disable the + rotation feature. + + + + A typical yaz-log looks like this + 13:23:14-23/11 yaz-ztest(1) [session] Starting session from tcp:127.0.0.1 (pid=30968) + 13:23:14-23/11 yaz-ztest(1) [request] Init from 'YAZ' (81) (ver 2.0.28) OK + 13:23:17-23/11 yaz-ztest(1) [request] Search Z: @attrset Bib-1 foo OK:7 hits + 13:23:22-23/11 yaz-ztest(1) [request] Present: [1] 2+2 OK 2 records returned + 13:24:13-23/11 yaz-ztest(1) [request] Close OK + + + + The log entries start with a time stamp. This can be omitted by setting the + YLOG_NOTIME bit in the loglevel. This way automatic tests + can be hoped to produce identical log files, that are easy to diff. The + format of the time stamp can be set with + yaz_log_time_format, which takes a format string just + like strftime. + + + + Next in a log line comes the prefix, often the name of the program. For + yaz-based servers, it can also contain the session number. Then + comes one or more logbits in square brackets, depending on the logging + level set by yaz_log_init_level and the loglevel + passed to yaz_log_init_level. Finally comes the format + string and additional values passed to yaz_log + + + + The log level YLOG_LOGLVL, enabled by the string + loglevel, will log all the log-level affecting + operations. This can come in handy if you need to know what other log + levels would be useful. Grep the logfile for [loglevel]. + + + + The log system is almost independent of the rest of &yaz;, the only + important dependence is of nmem, and that only for + using the semaphore definition there. + + + + The dynamic log levels and log rotation were introduced in &yaz; 2.0.28. At + the same time, the log bit names were changed from + LOG_something to YLOG_something, + to avoid collision with syslog.h. + + + + + MARC + + + YAZ provides a fast utility that decodes MARC records and + encodes to a varity of output formats. The MARC records must + be encoded in ISO2709. + + + + /* create handler */ + yaz_marc_t yaz_marc_create(void); + /* destroy */ + void yaz_marc_destroy(yaz_marc_t mt); + + /* set XML mode YAZ_MARC_LINE, YAZ_MARC_SIMPLEXML, ... */ + void yaz_marc_xml(yaz_marc_t mt, int xmlmode); + #define YAZ_MARC_LINE 0 + #define YAZ_MARC_SIMPLEXML 1 + #define YAZ_MARC_OAIMARC 2 + #define YAZ_MARC_MARCXML 3 + #define YAZ_MARC_ISO2709 4 + #define YAZ_MARC_XCHANGE 5 + + /* supply iconv handle for character set conversion .. */ + void yaz_marc_iconv(yaz_marc_t mt, yaz_iconv_t cd); + + /* set debug level, 0=none, 1=more, 2=even more, .. */ + void yaz_marc_debug(yaz_marc_t mt, int level); + + /* decode MARC in buf of size bsize. Returns >0 on success; <=0 on failure. + On success, result in *result with size *rsize. */ + int yaz_marc_decode_buf (yaz_marc_t mt, const char *buf, int bsize, + char **result, int *rsize); + + /* decode MARC in buf of size bsize. Returns >0 on success; <=0 on failure. + On success, result in WRBUF */ + int yaz_marc_decode_wrbuf (yaz_marc_t mt, const char *buf, + int bsize, WRBUF wrbuf); +]]> + + + A MARC conversion handle must be created by using + yaz_marc_create and destroyed + by calling yaz_marc_destroy. + + + All other function operate on a yaz_marc_t handle. + The output is specified by a call to yaz_marc_xml. + The xmlmode must be one of + + + YAZ_MARC_LINE + + + A simple line-by-line format suitable for display but not + recommend for further (machine) processing. + + + + + + YAZ_MARC_MARXML + + + The resulting record is converted to MARCXML. + + + + + + YAZ_MARC_ISO2709 + + + The resulting record is converted to ISO2709 (MARC). + + + + + + + The actual conversion functions are + yaz_marc_decode_buf and + yaz_marc_decode_wrbuf which decodes and encodes + a MARC record. The former function operates on simple buffers, the + stores the resulting record in a WRBUF handle (WRBUF is a simple string + type). + + + Display of MARC record + + The followint program snippet illustrates how the MARC API may + be used to convert a MARC record to the line-by-line format: + + + + + +