1 /* $Id: api.h,v 1.43 2007-01-16 15:01:15 adam Exp $
2 Copyright (C) 1995-2007
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 this program; if not, write to the Free Software
19 Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
27 Most functions has return type 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 zint 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 /** \brief Creates a Zebra Service.
81 \param configName name of configuration file
83 This function is a simplified version of zebra_start_res.
86 ZebraService zebra_start(const char *configName
87 ) ZEBRA_GCC_ATTR((warn_unused_result));
89 /** \brief Creates a Zebra service with resources.
90 \param configName name of configuration file
91 \param def_res default resources
92 \param over_res overriding resources
94 This function typically called once in a program. A Zebra Service
95 acts as a factory for Zebra session handles.
98 ZebraService zebra_start_res(const char *configName,
99 Res def_res, Res over_res
100 ) ZEBRA_GCC_ATTR((warn_unused_result));
102 /** \brief stops a Zebra service.
103 \param zs service handle
105 Frees resources used by the service.
108 ZEBRA_RES zebra_stop(ZebraService zs);
110 /** \brief Lists enabled Zebra filters
111 \param zs service handle
112 \param cd callback parameter (opaque)
113 \param cb callback function
116 void zebra_filter_info(ZebraService zs, void *cd,
117 void (*cb)(void *cd, const char *name));
120 /** \brief Creates a Zebra session handle within service.
121 \param zs service handle.
122 \param res resources to be used for the service (NULL for none)
124 There should be one handle for each thread doing something
125 with zebra, be that searching or indexing. In simple apps
126 one handle is sufficient
129 ZebraHandle zebra_open(ZebraService zs, Res res
130 ) ZEBRA_GCC_ATTR((warn_unused_result));
132 /** \brief Destroys Zebra session handle.
133 \param zh zebra session handle.
136 ZEBRA_RES zebra_close(ZebraHandle zh);
138 /** \brief Returns error code for last error
139 \param zh zebra session handle.
142 int zebra_errCode(ZebraHandle zh);
144 /** \brief Returns error string for last error
145 \param zh zebra session handle.
148 const char *zebra_errString(ZebraHandle zh);
150 /** \brief Returns additional info for last error
151 \param zh zebra session handle.
154 char *zebra_errAdd(ZebraHandle zh);
156 /** \brief Returns error code and additional info for last error
157 \param zh zebra session handle.
158 \param code pointer to returned error code
159 \param addinfo pointer to returned additional info
162 void zebra_result(ZebraHandle zh, int *code, char **addinfo);
164 /** \brief Set limit before Zebra does approx hit count
165 \param zh session handle
166 \param approx_limit the limit
168 Results will be approximiate if hit count is greater than the
169 limit specified. By default there is a high-limit (no limit).
171 ZEBRA_RES zebra_set_approx_limit(ZebraHandle zh, zint approx_limit);
173 /** \brief Search using PQF Query String
174 \param zh session handle
175 \param pqf_query query
176 \param setname name of resultset
177 \param hits of hits is returned
180 ZEBRA_RES zebra_search_PQF(ZebraHandle zh, const char *pqf_query,
181 const char *setname, zint *hits);
183 /** \brief Search using RPN Query structure (from ASN.1)
184 \param zh session handle
186 \param query RPN query using YAZ structure
187 \param setname name of resultset
188 \param hits number of hits is returned
189 \param estimated_hit_count whether hit count is an estimate
190 \param partial_resultset whether result is only partially evaluated
193 ZEBRA_RES zebra_search_RPN_x(ZebraHandle zh, ODR o, Z_RPNQuery *query,
194 const char *setname, zint *hits,
195 int *estimated_hit_count,
196 int *partial_resultset);
199 /** \brief Search using RPN Query structure (from ASN.1)
200 \param zh session handle
202 \param query RPN query using YAZ structure
203 \param setname name of resultset
204 \param hits number of hits is returned
207 ZEBRA_RES zebra_search_RPN(ZebraHandle zh, ODR o, Z_RPNQuery *query,
208 const char *setname, zint *hits);
210 /** \brief Retrieve records from result set (after search)
211 \param zh session handle
212 \param stream allocate records returned using this ODR
213 \param setname name of result set to retrieve records from
214 \param comp Z39.50 record composition
215 \param input_format transfer syntax (OID)
216 \param num_recs number of records to retrieve
217 \param recs store records in this structure (size is num_recs)
220 ZEBRA_RES zebra_records_retrieve(ZebraHandle zh, ODR stream,
222 Z_RecordComposition *comp,
223 oid_value input_format,
225 ZebraRetrievalRecord *recs);
226 /** \brief Deletes one or more resultsets
227 \param zh session handle
228 \param function Z_DeleteResultSetRequest_{list,all}
229 \param num_setnames number of result sets
230 \param setnames result set names
231 \param statuses status result
234 int zebra_deleteResultSet(ZebraHandle zh, int function,
235 int num_setnames, char **setnames,
239 /** \brief returns number of term info terms assocaited with result set
240 \param zh session handle
241 \param setname result set name
242 \param num_terms number of terms returned in this integer
244 This function is used in conjunction with zebra_result_set_term_info.
245 If operation was successful, ZEBRA_OK is returned; otherwise
246 ZEBRA_FAIL is returned (typically non-existing setname)
249 ZEBRA_RES zebra_result_set_term_no(ZebraHandle zh, const char *setname,
252 /** \brief returns information about a term assocated with a result set
253 \param zh session handle
254 \param setname result set name
255 \param no the term we want to know about (0=first, 1=second,..)
256 \param count the number of occurrences of this term, aka hits (output)
257 \param approx about hits: 0=exact,1=approx (output)
258 \param termbuf buffer for term string (intput, output)
259 \param termlen size of termbuf (input=max, output=actual length)
260 \param term_ref_id if non-NULL *term_ref_id holds term reference
262 Returns information about one search term associated with result set.
263 Use zebra_result_set_term_no to read total number of terms associated
264 with result set. If this function can not return information,
265 due to no out of range or bad result set name, ZEBRA_FAIL is
267 The passed termbuf must be able to hold at least *termlen characters.
268 Upon completion, *termlen holds actual length of search term.
271 ZEBRA_RES zebra_result_set_term_info(ZebraHandle zh, const char *setname,
272 int no, zint *count, int *approx,
273 char *termbuf, size_t *termlen,
274 const char **term_ref_id);
277 /** \brief performs Scan (Z39.50 style)
278 \param zh session handle
279 \param stream ODR handle for result
280 \param zapt Attribute plus Term (start term)
281 \param attributeset Attributeset for Attribute plus Term
282 \param position input/output position
283 \param num_entries number of terms requested / returned
284 \param entries list of resulting terms (ODR allocated)
285 \param is_partial upon return 1=partial, 0=complete
286 \param setname limit scan by this set (NULL means no limit)
288 YAZ_EXPORT ZEBRA_RES zebra_scan(ZebraHandle zh, ODR stream,
289 Z_AttributesPlusTerm *zapt,
290 oid_value attributeset,
291 int *position, int *num_entries,
292 ZebraScanEntry **entries,
294 const char *setname);
296 /** \brief performs Scan (taking PQF string)
297 \param zh session handle
298 \param stream ODR handle for result
299 \param query PQF scan query
300 \param position input/output position
301 \param num_entries number of terms requested / returned
302 \param entries list of resulting terms (ODR allocated)
303 \param is_partial upon return 1=partial, 0=complete
304 \param setname limit scan by this set (NULL means no limit)
307 ZEBRA_RES zebra_scan_PQF(ZebraHandle zh, ODR stream, const char *query,
308 int *position, int *num_entries,
309 ZebraScanEntry **entries,
310 int *is_partial, const char *setname);
312 /** \brief authenticate user. Returns 0 if OK, != 0 on failure
313 \param zh session handle
314 \param user user name
318 ZEBRA_RES zebra_auth(ZebraHandle zh, const char *user, const char *pass);
320 /** \brief Normalize zebra term for register (subject to change!)
321 \param zh session handle
322 \param reg_id register ID, 'w', 'p',..
323 \param input_str input string buffer
324 \param input_len input string length
325 \param output_str output string buffer
326 \param output_len output string length
329 int zebra_string_norm(ZebraHandle zh, unsigned reg_id, const char *input_str,
330 int input_len, char *output_str, int output_len);
332 /** \brief Creates a database
333 \param zh session handle
334 \param db database to be created
337 ZEBRA_RES zebra_create_database(ZebraHandle zh, const char *db);
339 /** \brief Deletes a database (drop)
340 \param zh session handle
341 \param db database to be deleted
344 ZEBRA_RES zebra_drop_database(ZebraHandle zh, const char *db);
347 ZEBRA_RES zebra_admin_shutdown(ZebraHandle zh);
350 ZEBRA_RES zebra_admin_start(ZebraHandle zh);
353 ZEBRA_RES zebra_shutdown(ZebraService zs);
356 ZEBRA_RES zebra_admin_import_begin(ZebraHandle zh, const char *database,
357 const char *record_type);
360 ZEBRA_RES zebra_admin_import_segment(ZebraHandle zh,
364 ZEBRA_RES zebra_admin_import_end(ZebraHandle zh);
367 ZEBRA_RES zebra_admin_exchange_record(ZebraHandle zh,
370 const char *recid_buf, size_t recid_len,
374 ZEBRA_RES zebra_begin_trans(ZebraHandle zh, int rw
375 ) ZEBRA_GCC_ATTR((warn_unused_result));
378 ZEBRA_RES zebra_end_trans(ZebraHandle zh
379 ) ZEBRA_GCC_ATTR((warn_unused_result));
382 ZEBRA_RES zebra_end_transaction(ZebraHandle zh,
383 ZebraTransactionStatus *stat);
386 ZEBRA_RES zebra_commit(ZebraHandle zh);
389 ZEBRA_RES zebra_clean(ZebraHandle zh);
392 ZEBRA_RES zebra_init(ZebraHandle zh);
395 ZEBRA_RES zebra_compact(ZebraHandle zh);
398 ZEBRA_RES zebra_repository_update(ZebraHandle zh, const char *path);
401 ZEBRA_RES zebra_repository_delete(ZebraHandle zh, const char *path);
404 ZEBRA_RES zebra_repository_show(ZebraHandle zh, const char *path);
407 ZEBRA_RES zebra_add_record(ZebraHandle zh, const char *buf, int buf_size);
410 ZEBRA_RES zebra_insert_record(ZebraHandle zh,
411 const char *recordType,
412 zint *sysno, const char *match,
414 const char *buf, int buf_size,
417 ZEBRA_RES zebra_update_record(ZebraHandle zh,
418 const char *recordType,
419 zint *sysno, const char *match,
421 const char *buf, int buf_size,
424 ZEBRA_RES zebra_delete_record(ZebraHandle zh,
425 const char *recordType,
426 zint *sysno, const char *match,
428 const char *buf, int buf_size,
432 ZEBRA_RES zebra_sort(ZebraHandle zh, ODR stream,
433 int num_input_setnames,
434 const char **input_setnames,
435 const char *output_setname,
436 Z_SortKeySpecList *sort_sequence,
438 ) ZEBRA_GCC_ATTR((warn_unused_result));
441 ZEBRA_RES zebra_select_databases(ZebraHandle zh, int num_bases,
442 const char **basenames
443 ) ZEBRA_GCC_ATTR((warn_unused_result));
446 ZEBRA_RES zebra_select_database(ZebraHandle zh, const char *basename
447 ) ZEBRA_GCC_ATTR((warn_unused_result));
450 void zebra_shadow_enable(ZebraHandle zh, int value);
453 int zebra_register_statistics(ZebraHandle zh, int dumpdict);
456 ZEBRA_RES zebra_record_encoding(ZebraHandle zh, const char *encoding);
459 ZEBRA_RES zebra_octet_term_encoding(ZebraHandle zh, const char *encoding);
463 void zebra_set_resource(ZebraHandle zh, const char *name, const char *value);
465 const char *zebra_get_resource(ZebraHandle zh,
466 const char *name, const char *defaultvalue);
470 void zebra_pidfname(ZebraService zs, char *path);
480 ZebraMetaRecord *zebra_meta_records_create(ZebraHandle zh,
482 int num, zint *positions);
486 ZebraMetaRecord *zebra_meta_records_create_range(ZebraHandle zh,
488 zint start, int num);
491 void zebra_meta_records_destroy(ZebraHandle zh, ZebraMetaRecord *records,
495 struct BFiles_struct *zebra_get_bfs(ZebraHandle zh);
498 ZEBRA_RES zebra_set_limit(ZebraHandle zh, int complement_flag, zint *ids);
504 * \section intro_sec Introduction
506 * Zebra is a search engine for structure data, such as XML, MARC
509 * API users should read the api.h for all the public definitions.
511 * The remaining sections briefly describe each of
512 * Zebra major modules/components.
514 * \section util Base Utilities
516 * The Zebra utilities (util.h) defines fundamental types and a few
517 * utilites for Zebra.
519 * \section res Resources
521 * The resources system (res.h) is a manager of configuration
522 * resources. The resources can be viewed as a simple database.
523 * Resources can be read from a configurtion file, they can be
524 * read or written by an application. Resources can also be written,
525 * but that facility is not currently in use.
527 * \section bfile Bfiles
529 * The Bfiles (bfile.h) provides a portable interface to the
530 * local file system. It also provides a facility for safe updates
531 * (shadow updates). All file system access is handle by this module
532 * (except for trival reads of configuration files).
534 * \section dict Dictionary
536 * The Zebra dictionary (dict.h) maps a search term (key) to a value. The
537 * value is a reference to the list of records identifers in which
538 * the term occurs. Zebra uses an ISAM data structure for the list
539 * of term occurrences. The Dictionary uses \ref bfile.
543 * Zebra maintains an ISAM for each term where each ISAM is a list
544 * of record identifiers corresponding to the records in which the
545 * term occur. Unlike traditional ISAM systems, the Zebra ISAM
546 * is compressed. The ISAM system uses \ref bfile.
548 * Zebra has more than one ISAM system. The old and stable ISAM system
549 * is named isamc (see isamc.h). Another version isams is a write-once
550 * isam system that is quite compact - suitable for CD-ROMs (isams.h).
551 * The newest ISAM system, isamb, is implemented as a B-Tree (see isamb.h).
553 * \section data1 Data-1
555 * The data1 (data1.h) module deals with structured documents. The module can
556 * can read, modify and write documents. The document structure was
557 * originally based on GRS-1 - a Z39.50 v3 structure that predates
558 * DOM. These days the data1 structure may describe XML/SGML as well.
559 * The data1, like DOM, is a tree structure. Each node in the tree
560 * can be of type element, text (cdata), preprocessing instruction,
561 * comment. Element nodes can point to attribute nodes.
563 * \section recctrl Record Control
565 * The record control module (recctrl.h) is responsible for
566 * managing the various record types ("classes" or filters).
568 * \section rset Result-Set
570 * The Result-Set module (rset.h) defines an interface that all
571 * Zebra Search Results must implement. Each operation (AND, OR, ..)
572 * correspond to an implementation of that interface.
576 * DFA (dfa.h) Deterministic Finite Automa is a regular expression engine.
577 * The module compiles a regular expression to a DFA. The DFA can then
578 * be used in various application to perform fast match against the
579 * origianl expression. The \ref Dict uses DFA to perform lookup
580 * using regular expressions.
587 * indent-tabs-mode: nil
589 * vim: shiftwidth=4 tabstop=8 expandtab