1 /* $Id: api.h,v 1.25 2005-06-02 11:59:53 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);
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);
113 \brief Lists enabled Zebra filters
114 \param zs service handle
115 \param cd callback parameter (opaque)
116 \param cb callback function
119 void zebra_filter_info(ZebraService zs, void *cd,
120 void (*cb)(void *cd, const char *name));
124 \brief Creates a Zebra session handle within service.
125 \param zs service handle.
127 There should be one handle for each thread doing something
128 with zebra, be that searching or indexing. In simple apps
129 one handle is sufficient
132 ZebraHandle zebra_open(ZebraService zs);
135 \brief Destroys Zebra session handle.
136 \param zh zebra session handle.
139 ZEBRA_RES zebra_close(ZebraHandle zh);
142 \brief Returns error code for last error
143 \param zh zebra session handle.
146 int zebra_errCode(ZebraHandle zh);
149 \brief Returns error string for last error
150 \param zh zebra session handle.
153 const char *zebra_errString(ZebraHandle zh);
156 \brief Returns additional info for last error
157 \param zh zebra session handle.
160 char *zebra_errAdd(ZebraHandle zh);
163 \brief Returns error code and additional info for last error
164 \param zh zebra session handle.
165 \param code pointer to returned error code
166 \param addinfo pointer to returned additional info
169 void zebra_result(ZebraHandle zh, int *code, char **addinfo);
172 \brief Clears last error.
173 \param zh zebra session handle.
176 void zebra_clearError(ZebraHandle zh);
179 \brief Search using PQF Query
180 \param zh session handle
181 \param pqf_query query
182 \param setname name of resultset
183 \param hits of hits is returned
186 ZEBRA_RES zebra_search_PQF(ZebraHandle zh, const char *pqf_query,
187 const char *setname, zint *hits);
189 /** \fn ZEBRA_RES zebra_search_RPN(ZebraHandle zh, ODR o, Z_RPNQuery *query, \
190 const char *setname, zint *hits)
191 \brief Search using RPN Query
192 \param zh session handle
194 \param query RPN query using YAZ structure
195 \param setname name of resultset
196 \param hits number of hits is returned
199 ZEBRA_RES zebra_search_RPN(ZebraHandle zh, ODR o, Z_RPNQuery *query,
200 const char *setname, zint *hits);
203 \fn ZEBRA_RES zebra_records_retrieve(ZebraHandle zh, ODR stream, \
204 const char *setname, Z_RecordComposition *comp, \
205 oid_value input_format, int num_recs, \
206 ZebraRetrievalRecord *recs)
207 \brief Retrieve records from result set (after search)
208 \param zh session handle
209 \param stream allocate records returned using this ODR
210 \param setname name of result set to retrieve records from
211 \param comp Z39.50 record composition
212 \param input_format transfer syntax (OID)
213 \param num_recs number of records to retrieve
214 \param recs store records in this structure (size is num_recs)
217 ZEBRA_RES zebra_records_retrieve(ZebraHandle zh, ODR stream,
219 Z_RecordComposition *comp,
220 oid_value input_format,
222 ZebraRetrievalRecord *recs);
224 \brief Deletes one or more resultsets
225 \param zh session handle
226 \param function Z_DeleteResultSetRequest_{list,all}
227 \param num_setnames number of result sets
228 \param setnames result set names
229 \param statuses status result
232 int zebra_deleteResultSet(ZebraHandle zh, int function,
233 int num_setnames, char **setnames,
239 ZEBRA_RES zebra_result_set_term_no(ZebraHandle zh, const char *setname,
243 ZEBRA_RES zebra_result_set_term_info(ZebraHandle zh, const char *setname,
244 int no, zint *count, int *approx,
245 char *termbuf, size_t *termlen);
249 \brief performs Scan (Z39.50 style)
250 \param zh session handle
251 \param stream ODR handle for result
252 \param zapt Attribute plus Term (start term)
253 \param attributeset Attributeset for Attribute plus Term
254 \param position input/output position
255 \param num_entries number of terms requested / returned
256 \param entries list of resulting terms (ODR allocated)
257 \param is_partial upon return 1=partial, 0=complete
259 YAZ_EXPORT ZEBRA_RES zebra_scan(ZebraHandle zh, ODR stream,
260 Z_AttributesPlusTerm *zapt,
261 oid_value attributeset,
262 int *position, int *num_entries,
263 ZebraScanEntry **entries,
267 \brief performs Scan (taking PQF string)
268 \param zh session handle
269 \param stream ODR handle for result
270 \param query PQF scan query
271 \param position input/output position
272 \param num_entries number of terms requested / returned
273 \param entries list of resulting terms (ODR allocated)
274 \param is_partial upon return 1=partial, 0=complete
277 ZEBRA_RES zebra_scan_PQF(ZebraHandle zh, ODR stream, const char *query,
278 int *position, int *num_entries, ZebraScanEntry **entries,
282 \brief authenticate user. Returns 0 if OK, != 0 on failure
283 \param zh session handle
284 \param user user name
288 ZEBRA_RES zebra_auth(ZebraHandle zh, const char *user, const char *pass);
291 \brief Normalize zebra term for register (subject to change!)
292 \param zh session handle
293 \param reg_id register ID, 'w', 'p',..
294 \param input_str input string buffer
295 \param input_len input string length
296 \param output_str output string buffer
297 \param output_len output string length
300 int zebra_string_norm(ZebraHandle zh, unsigned reg_id, const char *input_str,
301 int input_len, char *output_str, int output_len);
304 \brief Creates a database
305 \param zh session handle
306 \param db database to be created
309 ZEBRA_RES zebra_create_database(ZebraHandle zh, const char *db);
312 \brief Deletes a database (drop)
313 \param zh session handle
314 \param db database to be deleted
317 ZEBRA_RES zebra_drop_database(ZebraHandle zh, const char *db);
320 ZEBRA_RES zebra_admin_shutdown(ZebraHandle zh);
323 ZEBRA_RES zebra_admin_start(ZebraHandle zh);
326 ZEBRA_RES zebra_shutdown(ZebraService zs);
329 ZEBRA_RES zebra_admin_import_begin(ZebraHandle zh, const char *database,
330 const char *record_type);
333 ZEBRA_RES zebra_admin_import_segment(ZebraHandle zh,
337 ZEBRA_RES zebra_admin_import_end(ZebraHandle zh);
340 ZEBRA_RES zebra_admin_exchange_record(ZebraHandle zh,
343 const char *recid_buf, size_t recid_len,
347 ZEBRA_RES zebra_begin_trans(ZebraHandle zh, int rw);
350 ZEBRA_RES zebra_end_trans(ZebraHandle zh);
353 ZEBRA_RES zebra_end_transaction(ZebraHandle zh,
354 ZebraTransactionStatus *stat);
357 ZEBRA_RES zebra_commit(ZebraHandle zh);
360 ZEBRA_RES zebra_clean(ZebraHandle zh);
363 ZEBRA_RES zebra_init(ZebraHandle zh);
366 ZEBRA_RES zebra_compact(ZebraHandle zh);
368 YAZ_EXPORT int zebra_repository_update(ZebraHandle zh, const char *path);
369 YAZ_EXPORT int zebra_repository_delete(ZebraHandle zh, const char *path);
370 YAZ_EXPORT int zebra_repository_show(ZebraHandle zh, const char *path);
372 YAZ_EXPORT int zebra_add_record(ZebraHandle zh, const char *buf, int buf_size);
375 ZEBRA_RES zebra_insert_record(ZebraHandle zh,
376 const char *recordType,
377 SYSNO *sysno, const char *match,
379 const char *buf, int buf_size,
382 ZEBRA_RES zebra_update_record(ZebraHandle zh,
383 const char *recordType,
384 SYSNO *sysno, const char *match,
386 const char *buf, int buf_size,
389 ZEBRA_RES zebra_delete_record(ZebraHandle zh,
390 const char *recordType,
391 SYSNO *sysno, const char *match, const char *fname,
392 const char *buf, int buf_size,
396 int zebra_resultSetTerms(ZebraHandle zh, const char *setname,
398 int *type, char *out, size_t *len);
401 ZEBRA_RES zebra_sort(ZebraHandle zh, ODR stream,
402 int num_input_setnames,
403 const char **input_setnames,
404 const char *output_setname,
405 Z_SortKeySpecList *sort_sequence,
409 ZEBRA_RES zebra_select_databases(ZebraHandle zh, int num_bases,
410 const char **basenames);
413 ZEBRA_RES zebra_select_database(ZebraHandle zh, const char *basename);
416 void zebra_shadow_enable(ZebraHandle zh, int value);
419 int zebra_register_statistics(ZebraHandle zh, int dumpdict);
422 ZEBRA_RES zebra_record_encoding(ZebraHandle zh, const char *encoding);
425 ZEBRA_RES zebra_octet_term_encoding(ZebraHandle zh, const char *encoding);
429 void zebra_set_resource(ZebraHandle zh, const char *name, const char *value);
431 const char *zebra_get_resource(ZebraHandle zh,
432 const char *name, const char *defaultvalue);
436 void zebra_pidfname(ZebraService zs, char *path);
446 ZebraMetaRecord *zebra_meta_records_create(ZebraHandle zh,
448 int num, zint *positions);
452 ZebraMetaRecord *zebra_meta_records_create_range(ZebraHandle zh,
454 zint start, int num);
457 void zebra_meta_records_destroy(ZebraHandle zh, ZebraMetaRecord *records,
461 struct BFiles_struct *zebra_get_bfs(ZebraHandle zh);
464 ZEBRA_RES zebra_set_limit(ZebraHandle zh, int complement_flag, zint *ids);
470 * \section intro_sec Introduction
472 * Zebra is a search engine for structure data, such as XML, MARC
473 * and others. The following chapters briefly describe each of
474 * Zebra major modules/components.
476 * \section util Base Utilities
478 * The Zebra utilities (util.h) defines fundamental types and a few
479 * utilites for Zebra.
481 * \section res Resources
483 * The resources system (res.h) is a manager of configuration
484 * resources. The resources can be viewed as a simple database.
485 * Resources can be read from a configurtion file, they can be
486 * read or written by an application. Resources can also be written,
487 * but that facility is not currently in use.
489 * \section bfile Bfiles
491 * The Bfiles (bfile.h) provides a portable interface to the
492 * local file system. It also provides a facility for safe updates
493 * (shadow updates). All file system access is handle by this module
494 * (except for trival reads of configuration files).
496 * \section dict Dictionary
498 * The Zebra dictionary (dict.h) maps a search term (key) to a value. The
499 * value is a reference to the list of records identifers in which
500 * the term occurs. Zebra uses an ISAM data structure for the list
501 * of term occurrences. The Dictionary uses \ref bfile.
505 * Zebra maintains an ISAM for each term where each ISAM is a list
506 * of record identifiers corresponding to the records in which the
507 * term occur. Unlike traditional ISAM systems, the Zebra ISAM
508 * is compressed. The ISAM system uses \ref bfile.
510 * Zebra has more than one ISAM system. The old and stable ISAM system
511 * is named isamc (see isamc.h). Another version isams is a write-once
512 * isam system that is quite compact - suitable for CD-ROMs (isams.h).
513 * The newest ISAM system, isamb, is implemented as a B-Tree (see isamb.h).
515 * \section data1 Data-1
517 * The data1 (data1.h) module deals with structured documents. The module can
518 * can read, modify and write documents. The document structure was
519 * originally based on GRS-1 - a Z39.50 v3 structure that predates
520 * DOM. These days the data1 structure may describe XML/SGML as well.
521 * The data1, like DOM, is a tree structure. Each node in the tree
522 * can be of type element, text (cdata), preprocessing instruction,
523 * comment. Element nodes can point to attribute nodes.
525 * \section recctrl Record Control
527 * The record control module (recctrl.h) is responsible for
528 * managing the various record types ("classes" or filters).
530 * \section rset Result-Set
532 * The Result-Set module (rset.h) defines an interface that all
533 * Zebra Search Results must implement. Each operation (AND, OR, ..)
534 * correspond to an implementation of that interface.
538 * DFA (dfa.h) Deterministic Finite Automa is a regular expression engine.
539 * The module compiles a regular expression to a DFA. The DFA can then
540 * be used in various application to perform fast match against the
541 * origianl expression. The \ref Dict uses DFA to perform lookup
542 * using regular expressions.