1 /* $Id: api.h,v 1.24 2005-05-24 11:35:41 adam Exp $
2 Copyright (C) 1995-2005
5 This file is part of the Zebra server.
7 Zebra is free software; you can redistribute it and/or modify it under
8 the terms of the GNU General Public License as published by the Free
9 Software Foundation; either version 2, or (at your option) any later
12 Zebra is distributed in the hope that it will be useful, but WITHOUT ANY
13 WARRANTY; without even the implied warranty of MERCHANTABILITY or
14 FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
17 You should have received a copy of the GNU General Public License
18 along with Zebra; see the file LICENSE.zebra. If not, write to the
19 Free Software Foundation, 59 Temple Place - Suite 330, Boston, MA
27 Most functions return ZEBRA_RES, where ZEBRA_FAIL indicates
28 failure; ZEBRA_OK indicates success.
36 #include <yaz/proto.h>
37 #include <idzebra/res.h>
38 #include <idzebra/version.h>
49 } ZebraTransactionStatus;
51 /** Retrieval Record Descriptor */
53 int errCode; /* non-zero if error when fetching this */
54 char *errString; /* error string */
55 int position; /* position of record in result set (1,2,..) */
56 char *buf; /* record buffer (void pointer really) */
58 oid_value format; /* record syntax */
62 } ZebraRetrievalRecord;
64 /** Scan Term Descriptor */
66 int occurrences; /* scan term occurrences */
67 char *term; /* scan term string */
71 \brief a Zebra Handle - (session)
73 typedef struct zebra_session *ZebraHandle;
76 \brief a Zebra Service handle
78 typedef struct zebra_service *ZebraService;
80 /** \fn ZebraService zebra_start(const char *configName)
81 \brief starts a Zebra service.
82 \param configName name of configuration file
84 This function is a simplified version of zebra_start_res.
87 ZebraService zebra_start(const char *configName);
89 /** \fn ZebraService zebra_start_res(const char *configName, \
90 Res def_res, Res over_res)
91 \brief starts a Zebra service with resources.
92 \param configName name of configuration file
93 \param def_res default resources
94 \param over_res overriding resources
96 This function typically called once in a program. A Zebra Service
97 acts as a factory for Zebra session handles.
100 ZebraService zebra_start_res(const char *configName,
101 Res def_res, Res over_res);
103 /** \fn ZEBRA_RES zebra_stop(ZebraService zs)
104 \brief stops a Zebra service.
105 \param zs service handle
107 Frees resources used by the service.
110 ZEBRA_RES zebra_stop(ZebraService zs);
112 /** \fn void zebra_filter_info(ZebraService zs, void *cd, \
113 void(*cb)(void *cd, const char *name))
114 \brief lists enabled Zebra filters
115 \param zs service handle
116 \param cd callback parameter (opaque)
117 \param cb callback function
120 void zebra_filter_info(ZebraService zs, void *cd,
121 void (*cb)(void *cd, const char *name));
124 /** \fn ZebraHandle zebra_open(ZebraService zs)
125 \brief creates a Zebra session handle within service.
126 \param zs service handle.
128 There should be one handle for each thread doing something
129 with zebra, be that searching or indexing. In simple apps
130 one handle is sufficient
133 ZebraHandle zebra_open(ZebraService zs);
135 /** \fn int zebra_close(ZebraHandle zh)
136 \brief destroys Zebra session handle.
137 \param zh zebra session handle.
140 ZEBRA_RES zebra_close(ZebraHandle zh);
142 /** \fn int zebra_errCode(ZebraHandle zh)
143 \brief returns error code for last error
144 \param zh zebra session handle.
147 int zebra_errCode(ZebraHandle zh);
149 /** \fn const char *zebra_errString(ZebraHandle zh)
150 \brief returns error string for last error
151 \param zh zebra session handle.
154 const char *zebra_errString(ZebraHandle zh);
156 /** \fn char *zebra_errAdd(ZebraHandle zh)
157 \brief returns additional info for last error
158 \param zh zebra session handle.
161 char *zebra_errAdd(ZebraHandle zh);
163 /** \fn int zebra_result(ZebraHandle zh, int *code, char **addinfo)
164 \brief returns error code and additional info for last error
165 \param zh zebra session handle.
166 \param code pointer to returned error code
167 \param addinfo pointer to returned additional info
170 void zebra_result(ZebraHandle zh, int *code, char **addinfo);
172 /** \fn void zebra_clearError(ZebraHandle zh)
173 \brief clears last error.
174 \param zh zebra session handle.
177 void zebra_clearError(ZebraHandle zh);
179 /** \fn ZEBRA_RES zebra_search_PQF(ZebraHandle zh, const char *pqf_query, \
180 const char *setname, zint *hits)
181 \brief Search using PQF Query
182 \param zh session handle
183 \param pqf_query query
184 \param setname name of resultset
185 \param hits of hits is returned
188 ZEBRA_RES zebra_search_PQF(ZebraHandle zh, const char *pqf_query,
189 const char *setname, zint *hits);
191 /** \fn ZEBRA_RES zebra_search_RPN(ZebraHandle zh, ODR o, Z_RPNQuery *query, \
192 const char *setname, zint *hits)
193 \brief Search using RPN Query
194 \param zh session handle
196 \param query RPN query using YAZ structure
197 \param setname name of resultset
198 \param hits number of hits is returned
201 ZEBRA_RES zebra_search_RPN(ZebraHandle zh, ODR o, Z_RPNQuery *query,
202 const char *setname, zint *hits);
205 \fn ZEBRA_RES zebra_records_retrieve(ZebraHandle zh, ODR stream, \
206 const char *setname, Z_RecordComposition *comp, \
207 oid_value input_format, int num_recs, \
208 ZebraRetrievalRecord *recs)
209 \brief retrieve records from result set (after search)
210 \param zh session handle
211 \param stream allocate records returned using this ODR
212 \param setname name of result set to retrieve records from
213 \param comp Z39.50 record composition
214 \param input_format transfer syntax (OID)
215 \param num_recs number of records to retrieve
216 \param recs store records in this structure (size is num_recs)
219 ZEBRA_RES zebra_records_retrieve(ZebraHandle zh, ODR stream,
221 Z_RecordComposition *comp,
222 oid_value input_format,
224 ZebraRetrievalRecord *recs);
226 \fn int zebra_deleteResultSet(ZebraHandle zh, int function, \
227 int num_setnames, char **setnames, int *statuses)
228 \brief delete one or more resultsets
229 \param zh session handle
230 \param function Z_DeleteResultSetRequest_{list,all}
231 \param num_setnames number of result sets
232 \param setnames result set names
233 \param statuses status result
236 int zebra_deleteResultSet(ZebraHandle zh, int function,
237 int num_setnames, char **setnames,
243 ZEBRA_RES zebra_result_set_term_no(ZebraHandle zh, const char *setname,
247 ZEBRA_RES zebra_result_set_term_info(ZebraHandle zh, const char *setname,
248 int no, zint *count, int *approx,
249 char *termbuf, size_t *termlen);
253 \fn ZEBRA_RES zebra_scan(ZebraHandle zh, ODR stream, \
254 Z_AttributesPlusTerm *zapt, oid_value attributeset, \
255 int *position, int *num_entries, ZebraScanEntry **list, \
257 \brief performs Scan (Z39.50 style)
258 \param zh session handle
259 \param stream ODR handle for result
260 \param zapt Attribute plus Term (start term)
261 \param attributeset Attributeset for Attribute plus Term
262 \param position input/output position
263 \param num_entries number of terms requested / returned
264 \param list list of resulting terms (ODR allocated)
265 \param is_partial upon return 1=partial, 0=complete
267 YAZ_EXPORT ZEBRA_RES zebra_scan(ZebraHandle zh, ODR stream,
268 Z_AttributesPlusTerm *zapt,
269 oid_value attributeset,
270 int *position, int *num_entries,
271 ZebraScanEntry **list,
275 \fn ZEBRA_RES zebra_scan_PQF(ZebraHandle zh, ODR stream, \
276 const char *query, int *position, int *num_entries, \
277 ZebraScanEntry **list, int *is_partial)
278 \brief performs Scan (taking PQF string)
279 \param zh session handle
280 \param stream ODR handle for result
281 \param query PQF scan query
282 \param position input/output position
283 \param num_entries number of terms requested / returned
284 \param list list of resulting terms (ODR allocated)
285 \param is_partial upon return 1=partial, 0=complete
288 ZEBRA_RES zebra_scan_PQF(ZebraHandle zh, ODR stream, const char *query,
289 int *position, int *num_entries, ZebraScanEntry **entries,
292 \fn ZEBRA_RES zebra_auth(ZebraHandle zh, const char *user, const char *pass)
293 \brief authenticate user. Returns 0 if OK, != 0 on failure
294 \param zh session handle
295 \param user user name
299 ZEBRA_RES zebra_auth(ZebraHandle zh, const char *user, const char *pass);
302 \fn int zebra_string_norm(ZebraHandle zh, unsigned reg_id, \
303 const char *input_str, int input_len, \
304 char *output_str, int output_len)
305 \brief normalize zebra term for register (subject to change!)
306 \param zh session handle
307 \param reg_id register ID, 'w', 'p',..
308 \param input_str input string buffer
309 \param input_len input string length
310 \param output_str output string buffer
311 \param output_len output string length
314 int zebra_string_norm(ZebraHandle zh, unsigned reg_id, const char *input_str,
315 int input_len, char *output_str, int output_len);
318 \fn ZEBRA_RES zebra_create_database(ZebraHandle zh, const char *db)
319 \brief creates a database
320 \param zh session handle
321 \param db database to be created
324 ZEBRA_RES zebra_create_database(ZebraHandle zh, const char *db);
327 \fn int zebra_drop_database(ZebraHandle zh, const char *db)
328 \brief deletes a database (drop)
329 \param zh session handle
330 \param db database to be deleted
333 ZEBRA_RES zebra_drop_database(ZebraHandle zh, const char *db);
336 ZEBRA_RES zebra_admin_shutdown(ZebraHandle zh);
339 ZEBRA_RES zebra_admin_start(ZebraHandle zh);
342 ZEBRA_RES zebra_shutdown(ZebraService zs);
345 ZEBRA_RES zebra_admin_import_begin(ZebraHandle zh, const char *database,
346 const char *record_type);
349 ZEBRA_RES zebra_admin_import_segment(ZebraHandle zh,
353 ZEBRA_RES zebra_admin_import_end(ZebraHandle zh);
356 ZEBRA_RES zebra_admin_exchange_record(ZebraHandle zh,
359 const char *recid_buf, size_t recid_len,
363 ZEBRA_RES zebra_begin_trans(ZebraHandle zh, int rw);
366 ZEBRA_RES zebra_end_trans(ZebraHandle zh);
369 ZEBRA_RES zebra_end_transaction(ZebraHandle zh,
370 ZebraTransactionStatus *stat);
373 ZEBRA_RES zebra_commit(ZebraHandle zh);
376 ZEBRA_RES zebra_clean(ZebraHandle zh);
379 ZEBRA_RES zebra_init(ZebraHandle zh);
382 ZEBRA_RES zebra_compact(ZebraHandle zh);
384 YAZ_EXPORT int zebra_repository_update(ZebraHandle zh, const char *path);
385 YAZ_EXPORT int zebra_repository_delete(ZebraHandle zh, const char *path);
386 YAZ_EXPORT int zebra_repository_show(ZebraHandle zh, const char *path);
388 YAZ_EXPORT int zebra_add_record(ZebraHandle zh, const char *buf, int buf_size);
391 ZEBRA_RES zebra_insert_record(ZebraHandle zh,
392 const char *recordType,
393 SYSNO *sysno, const char *match,
395 const char *buf, int buf_size,
398 ZEBRA_RES zebra_update_record(ZebraHandle zh,
399 const char *recordType,
400 SYSNO *sysno, const char *match,
402 const char *buf, int buf_size,
405 ZEBRA_RES zebra_delete_record(ZebraHandle zh,
406 const char *recordType,
407 SYSNO *sysno, const char *match, const char *fname,
408 const char *buf, int buf_size,
412 int zebra_resultSetTerms(ZebraHandle zh, const char *setname,
414 int *type, char *out, size_t *len);
417 ZEBRA_RES zebra_sort(ZebraHandle zh, ODR stream,
418 int num_input_setnames,
419 const char **input_setnames,
420 const char *output_setname,
421 Z_SortKeySpecList *sort_sequence,
425 ZEBRA_RES zebra_select_databases(ZebraHandle zh, int num_bases,
426 const char **basenames);
429 ZEBRA_RES zebra_select_database(ZebraHandle zh, const char *basename);
432 void zebra_shadow_enable(ZebraHandle zh, int value);
435 int zebra_register_statistics(ZebraHandle zh, int dumpdict);
438 ZEBRA_RES zebra_record_encoding(ZebraHandle zh, const char *encoding);
441 ZEBRA_RES zebra_octet_term_encoding(ZebraHandle zh, const char *encoding);
445 void zebra_set_resource(ZebraHandle zh, const char *name, const char *value);
447 const char *zebra_get_resource(ZebraHandle zh,
448 const char *name, const char *defaultvalue);
452 void zebra_pidfname(ZebraService zs, char *path);
462 ZebraMetaRecord *zebra_meta_records_create(ZebraHandle zh,
464 int num, zint *positions);
468 ZebraMetaRecord *zebra_meta_records_create_range(ZebraHandle zh,
470 zint start, int num);
473 void zebra_meta_records_destroy(ZebraHandle zh, ZebraMetaRecord *records,
477 struct BFiles_struct *zebra_get_bfs(ZebraHandle zh);
480 ZEBRA_RES zebra_set_limit(ZebraHandle zh, int complement_flag, zint *ids);
486 * \section intro_sec Introduction
488 * Zebra is a search engine for structure data, such as XML, MARC
489 * and others. The following chapters briefly describe each of
490 * Zebra major modules/components.
492 * \section util Base Utilities
494 * The Zebra utilities (util.h) defines fundamental types and a few
495 * utilites for Zebra.
497 * \section res Resources
499 * The resources system (res.h) is a manager of configuration
500 * resources. The resources can be viewed as a simple database.
501 * Resources can be read from a configurtion file, they can be
502 * read or written by an application. Resources can also be written,
503 * but that facility is not currently in use.
505 * \section bfile Bfiles
507 * The Bfiles (bfile.h) provides a portable interface to the
508 * local file system. It also provides a facility for safe updates
509 * (shadow updates). All file system access is handle by this module
510 * (except for trival reads of configuration files).
512 * \section dict Dictionary
514 * The Zebra dictionary (dict.h) maps a search term (key) to a value. The
515 * value is a reference to the list of records identifers in which
516 * the term occurs. Zebra uses an ISAM data structure for the list
517 * of term occurrences. The Dictionary uses \ref bfile.
521 * Zebra maintains an ISAM for each term where each ISAM is a list
522 * of record identifiers corresponding to the records in which the
523 * term occur. Unlike traditional ISAM systems, the Zebra ISAM
524 * is compressed. The ISAM system uses \ref bfile.
526 * Zebra has more than one ISAM system. The old and stable ISAM system
527 * is named isamc (see isamc.h). Another version isams is a write-once
528 * isam system that is quite compact - suitable for CD-ROMs (isams.h).
529 * The newest ISAM system, isamb, is implemented as a B-Tree (see isamb.h).
531 * \section data1 Data-1
533 * The data1 (data1.h) module deals with structured documents. The module can
534 * can read, modify and write documents. The document structure was
535 * originally based on GRS-1 - a Z39.50 v3 structure that predates
536 * DOM. These days the data1 structure may describe XML/SGML as well.
537 * The data1, like DOM, is a tree structure. Each node in the tree
538 * can be of type element, text (cdata), preprocessing instruction,
539 * comment. Element nodes can point to attribute nodes.
541 * \section recctrl Record Control
543 * The record control module (recctrl.h) is responsible for
544 * managing the various record types ("classes" or filters).
546 * \section rset Result-Set
548 * The Result-Set module (rset.h) defines an interface that all
549 * Zebra Search Results must implement. Each operation (AND, OR, ..)
550 * correspond to an implementation of that interface.
554 * DFA (dfa.h) Deterministic Finite Automa is a regular expression engine.
555 * The module compiles a regular expression to a DFA. The DFA can then
556 * be used in various application to perform fast match against the
557 * origianl expression. The \ref Dict uses DFA to perform lookup
558 * using regular expressions.