1 /* $Id: api.h,v 1.28 2005-08-09 09:35:25 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);
180 \brief Set limit before Zebra does approx hit count
181 \param zh session handle
182 \param approx_limit the limit
184 Results will be approximiate if hit count is greater than the
185 limit specified. By default there is a high-limit (no limit).
187 ZEBRA_RES zebra_set_approx_limit(ZebraHandle zh, zint approx_limit);
190 \brief Search using PQF Query
191 \param zh session handle
192 \param pqf_query query
193 \param setname name of resultset
194 \param hits of hits is returned
197 ZEBRA_RES zebra_search_PQF(ZebraHandle zh, const char *pqf_query,
198 const char *setname, zint *hits);
200 /** \fn ZEBRA_RES zebra_search_RPN(ZebraHandle zh, ODR o, Z_RPNQuery *query, \
201 const char *setname, zint *hits)
202 \brief Search using RPN Query
203 \param zh session handle
205 \param query RPN query using YAZ structure
206 \param setname name of resultset
207 \param hits number of hits is returned
210 ZEBRA_RES zebra_search_RPN(ZebraHandle zh, ODR o, Z_RPNQuery *query,
211 const char *setname, zint *hits);
214 \fn ZEBRA_RES zebra_records_retrieve(ZebraHandle zh, ODR stream, \
215 const char *setname, Z_RecordComposition *comp, \
216 oid_value input_format, int num_recs, \
217 ZebraRetrievalRecord *recs)
218 \brief Retrieve records from result set (after search)
219 \param zh session handle
220 \param stream allocate records returned using this ODR
221 \param setname name of result set to retrieve records from
222 \param comp Z39.50 record composition
223 \param input_format transfer syntax (OID)
224 \param num_recs number of records to retrieve
225 \param recs store records in this structure (size is num_recs)
228 ZEBRA_RES zebra_records_retrieve(ZebraHandle zh, ODR stream,
230 Z_RecordComposition *comp,
231 oid_value input_format,
233 ZebraRetrievalRecord *recs);
235 \brief Deletes one or more resultsets
236 \param zh session handle
237 \param function Z_DeleteResultSetRequest_{list,all}
238 \param num_setnames number of result sets
239 \param setnames result set names
240 \param statuses status result
243 int zebra_deleteResultSet(ZebraHandle zh, int function,
244 int num_setnames, char **setnames,
250 ZEBRA_RES zebra_result_set_term_no(ZebraHandle zh, const char *setname,
254 ZEBRA_RES zebra_result_set_term_info(ZebraHandle zh, const char *setname,
255 int no, zint *count, int *approx,
256 char *termbuf, size_t *termlen,
257 const char **term_ref_id);
261 \brief performs Scan (Z39.50 style)
262 \param zh session handle
263 \param stream ODR handle for result
264 \param zapt Attribute plus Term (start term)
265 \param attributeset Attributeset for Attribute plus Term
266 \param position input/output position
267 \param num_entries number of terms requested / returned
268 \param entries list of resulting terms (ODR allocated)
269 \param is_partial upon return 1=partial, 0=complete
270 \param setname limit scan by this set (NULL means no limit)
272 YAZ_EXPORT ZEBRA_RES zebra_scan(ZebraHandle zh, ODR stream,
273 Z_AttributesPlusTerm *zapt,
274 oid_value attributeset,
275 int *position, int *num_entries,
276 ZebraScanEntry **entries,
278 const char *setname);
281 \brief performs Scan (taking PQF string)
282 \param zh session handle
283 \param stream ODR handle for result
284 \param query PQF scan query
285 \param position input/output position
286 \param num_entries number of terms requested / returned
287 \param entries list of resulting terms (ODR allocated)
288 \param is_partial upon return 1=partial, 0=complete
289 \param setname limit scan by this set (NULL means no limit)
292 ZEBRA_RES zebra_scan_PQF(ZebraHandle zh, ODR stream, const char *query,
293 int *position, int *num_entries, ZebraScanEntry **entries,
294 int *is_partial, const char *setname);
297 \brief authenticate user. Returns 0 if OK, != 0 on failure
298 \param zh session handle
299 \param user user name
303 ZEBRA_RES zebra_auth(ZebraHandle zh, const char *user, const char *pass);
306 \brief Normalize zebra term for register (subject to change!)
307 \param zh session handle
308 \param reg_id register ID, 'w', 'p',..
309 \param input_str input string buffer
310 \param input_len input string length
311 \param output_str output string buffer
312 \param output_len output string length
315 int zebra_string_norm(ZebraHandle zh, unsigned reg_id, const char *input_str,
316 int input_len, char *output_str, int output_len);
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 \brief Deletes a database (drop)
328 \param zh session handle
329 \param db database to be deleted
332 ZEBRA_RES zebra_drop_database(ZebraHandle zh, const char *db);
335 ZEBRA_RES zebra_admin_shutdown(ZebraHandle zh);
338 ZEBRA_RES zebra_admin_start(ZebraHandle zh);
341 ZEBRA_RES zebra_shutdown(ZebraService zs);
344 ZEBRA_RES zebra_admin_import_begin(ZebraHandle zh, const char *database,
345 const char *record_type);
348 ZEBRA_RES zebra_admin_import_segment(ZebraHandle zh,
352 ZEBRA_RES zebra_admin_import_end(ZebraHandle zh);
355 ZEBRA_RES zebra_admin_exchange_record(ZebraHandle zh,
358 const char *recid_buf, size_t recid_len,
362 ZEBRA_RES zebra_begin_trans(ZebraHandle zh, int rw);
365 ZEBRA_RES zebra_end_trans(ZebraHandle zh);
368 ZEBRA_RES zebra_end_transaction(ZebraHandle zh,
369 ZebraTransactionStatus *stat);
372 ZEBRA_RES zebra_commit(ZebraHandle zh);
375 ZEBRA_RES zebra_clean(ZebraHandle zh);
378 ZEBRA_RES zebra_init(ZebraHandle zh);
381 ZEBRA_RES zebra_compact(ZebraHandle zh);
383 YAZ_EXPORT int zebra_repository_update(ZebraHandle zh, const char *path);
384 YAZ_EXPORT int zebra_repository_delete(ZebraHandle zh, const char *path);
385 YAZ_EXPORT int zebra_repository_show(ZebraHandle zh, const char *path);
387 YAZ_EXPORT int zebra_add_record(ZebraHandle zh, const char *buf, int buf_size);
390 ZEBRA_RES zebra_insert_record(ZebraHandle zh,
391 const char *recordType,
392 SYSNO *sysno, const char *match,
394 const char *buf, int buf_size,
397 ZEBRA_RES zebra_update_record(ZebraHandle zh,
398 const char *recordType,
399 SYSNO *sysno, const char *match,
401 const char *buf, int buf_size,
404 ZEBRA_RES zebra_delete_record(ZebraHandle zh,
405 const char *recordType,
406 SYSNO *sysno, const char *match, const char *fname,
407 const char *buf, int buf_size,
411 int zebra_resultSetTerms(ZebraHandle zh, const char *setname,
413 int *type, char *out, size_t *len);
416 ZEBRA_RES zebra_sort(ZebraHandle zh, ODR stream,
417 int num_input_setnames,
418 const char **input_setnames,
419 const char *output_setname,
420 Z_SortKeySpecList *sort_sequence,
424 ZEBRA_RES zebra_select_databases(ZebraHandle zh, int num_bases,
425 const char **basenames);
428 ZEBRA_RES zebra_select_database(ZebraHandle zh, const char *basename);
431 void zebra_shadow_enable(ZebraHandle zh, int value);
434 int zebra_register_statistics(ZebraHandle zh, int dumpdict);
437 ZEBRA_RES zebra_record_encoding(ZebraHandle zh, const char *encoding);
440 ZEBRA_RES zebra_octet_term_encoding(ZebraHandle zh, const char *encoding);
444 void zebra_set_resource(ZebraHandle zh, const char *name, const char *value);
446 const char *zebra_get_resource(ZebraHandle zh,
447 const char *name, const char *defaultvalue);
451 void zebra_pidfname(ZebraService zs, char *path);
461 ZebraMetaRecord *zebra_meta_records_create(ZebraHandle zh,
463 int num, zint *positions);
467 ZebraMetaRecord *zebra_meta_records_create_range(ZebraHandle zh,
469 zint start, int num);
472 void zebra_meta_records_destroy(ZebraHandle zh, ZebraMetaRecord *records,
476 struct BFiles_struct *zebra_get_bfs(ZebraHandle zh);
479 ZEBRA_RES zebra_set_limit(ZebraHandle zh, int complement_flag, zint *ids);
485 * \section intro_sec Introduction
487 * Zebra is a search engine for structure data, such as XML, MARC
488 * and others. The following chapters briefly describe each of
489 * Zebra major modules/components.
491 * \section util Base Utilities
493 * The Zebra utilities (util.h) defines fundamental types and a few
494 * utilites for Zebra.
496 * \section res Resources
498 * The resources system (res.h) is a manager of configuration
499 * resources. The resources can be viewed as a simple database.
500 * Resources can be read from a configurtion file, they can be
501 * read or written by an application. Resources can also be written,
502 * but that facility is not currently in use.
504 * \section bfile Bfiles
506 * The Bfiles (bfile.h) provides a portable interface to the
507 * local file system. It also provides a facility for safe updates
508 * (shadow updates). All file system access is handle by this module
509 * (except for trival reads of configuration files).
511 * \section dict Dictionary
513 * The Zebra dictionary (dict.h) maps a search term (key) to a value. The
514 * value is a reference to the list of records identifers in which
515 * the term occurs. Zebra uses an ISAM data structure for the list
516 * of term occurrences. The Dictionary uses \ref bfile.
520 * Zebra maintains an ISAM for each term where each ISAM is a list
521 * of record identifiers corresponding to the records in which the
522 * term occur. Unlike traditional ISAM systems, the Zebra ISAM
523 * is compressed. The ISAM system uses \ref bfile.
525 * Zebra has more than one ISAM system. The old and stable ISAM system
526 * is named isamc (see isamc.h). Another version isams is a write-once
527 * isam system that is quite compact - suitable for CD-ROMs (isams.h).
528 * The newest ISAM system, isamb, is implemented as a B-Tree (see isamb.h).
530 * \section data1 Data-1
532 * The data1 (data1.h) module deals with structured documents. The module can
533 * can read, modify and write documents. The document structure was
534 * originally based on GRS-1 - a Z39.50 v3 structure that predates
535 * DOM. These days the data1 structure may describe XML/SGML as well.
536 * The data1, like DOM, is a tree structure. Each node in the tree
537 * can be of type element, text (cdata), preprocessing instruction,
538 * comment. Element nodes can point to attribute nodes.
540 * \section recctrl Record Control
542 * The record control module (recctrl.h) is responsible for
543 * managing the various record types ("classes" or filters).
545 * \section rset Result-Set
547 * The Result-Set module (rset.h) defines an interface that all
548 * Zebra Search Results must implement. Each operation (AND, OR, ..)
549 * correspond to an implementation of that interface.
553 * DFA (dfa.h) Deterministic Finite Automa is a regular expression engine.
554 * The module compiles a regular expression to a DFA. The DFA can then
555 * be used in various application to perform fast match against the
556 * origianl expression. The \ref Dict uses DFA to perform lookup
557 * using regular expressions.