1 /* $Id: api.h,v 1.39 2006-08-22 13:59:02 adam Exp $
2 Copyright (C) 1995-2006
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>
43 expand GCC_ATTRIBUTE if GCC is in use. See :
44 http://gcc.gnu.org/onlinedocs/gcc/Function-Attributes.html
46 To see gcc pre-defines for c:
47 gcc -E -dM -x c /dev/null
52 #define ZEBRA_GCC_ATTR(x) __attribute__ (x)
56 #ifndef ZEBRA_GCC_ATTR
57 #define ZEBRA_GCC_ATTR(x)
67 } ZebraTransactionStatus;
69 /** Retrieval Record Descriptor */
71 int errCode; /* non-zero if error when fetching this */
72 char *errString; /* error string */
73 int position; /* position of record in result set (1,2,..) */
74 char *buf; /* record buffer (void pointer really) */
76 oid_value format; /* record syntax */
80 } ZebraRetrievalRecord;
82 /** Scan Term Descriptor */
84 zint occurrences; /* scan term occurrences */
85 char *term; /* scan term string */
89 \brief a Zebra Handle - (session)
91 typedef struct zebra_session *ZebraHandle;
94 \brief a Zebra Service handle
96 typedef struct zebra_service *ZebraService;
98 /** \brief Creates a Zebra Service.
99 \param configName name of configuration file
101 This function is a simplified version of zebra_start_res.
104 ZebraService zebra_start(const char *configName
105 ) ZEBRA_GCC_ATTR((warn_unused_result));
107 /** \brief Creates a Zebra service with resources.
108 \param configName name of configuration file
109 \param def_res default resources
110 \param over_res overriding resources
112 This function typically called once in a program. A Zebra Service
113 acts as a factory for Zebra session handles.
116 ZebraService zebra_start_res(const char *configName,
117 Res def_res, Res over_res
118 ) ZEBRA_GCC_ATTR((warn_unused_result));
120 /** \brief stops a Zebra service.
121 \param zs service handle
123 Frees resources used by the service.
126 ZEBRA_RES zebra_stop(ZebraService zs);
128 /** \brief Lists enabled Zebra filters
129 \param zs service handle
130 \param cd callback parameter (opaque)
131 \param cb callback function
134 void zebra_filter_info(ZebraService zs, void *cd,
135 void (*cb)(void *cd, const char *name));
138 /** \brief Creates a Zebra session handle within service.
139 \param zs service handle.
140 \param res resources to be used for the service (NULL for none)
142 There should be one handle for each thread doing something
143 with zebra, be that searching or indexing. In simple apps
144 one handle is sufficient
147 ZebraHandle zebra_open(ZebraService zs, Res res
148 ) ZEBRA_GCC_ATTR((warn_unused_result));
150 /** \brief Destroys Zebra session handle.
151 \param zh zebra session handle.
154 ZEBRA_RES zebra_close(ZebraHandle zh);
156 /** \brief Returns error code for last error
157 \param zh zebra session handle.
160 int zebra_errCode(ZebraHandle zh);
162 /** \brief Returns error string for last error
163 \param zh zebra session handle.
166 const char *zebra_errString(ZebraHandle zh);
168 /** \brief Returns additional info for last error
169 \param zh zebra session handle.
172 char *zebra_errAdd(ZebraHandle zh);
174 /** \brief Returns error code and additional info for last error
175 \param zh zebra session handle.
176 \param code pointer to returned error code
177 \param addinfo pointer to returned additional info
180 void zebra_result(ZebraHandle zh, int *code, char **addinfo);
182 /** \brief Set limit before Zebra does approx hit count
183 \param zh session handle
184 \param approx_limit the limit
186 Results will be approximiate if hit count is greater than the
187 limit specified. By default there is a high-limit (no limit).
189 ZEBRA_RES zebra_set_approx_limit(ZebraHandle zh, zint approx_limit);
191 /** \brief Search using PQF Query String
192 \param zh session handle
193 \param pqf_query query
194 \param setname name of resultset
195 \param hits of hits is returned
198 ZEBRA_RES zebra_search_PQF(ZebraHandle zh, const char *pqf_query,
199 const char *setname, zint *hits);
201 /** \brief Search using RPN Query structure (from ASN.1)
202 \param zh session handle
204 \param query RPN query using YAZ structure
205 \param setname name of resultset
206 \param hits number of hits is returned
209 ZEBRA_RES zebra_search_RPN(ZebraHandle zh, ODR o, Z_RPNQuery *query,
210 const char *setname, zint *hits);
212 /** \brief Retrieve records from result set (after search)
213 \param zh session handle
214 \param stream allocate records returned using this ODR
215 \param setname name of result set to retrieve records from
216 \param comp Z39.50 record composition
217 \param input_format transfer syntax (OID)
218 \param num_recs number of records to retrieve
219 \param recs store records in this structure (size is num_recs)
222 ZEBRA_RES zebra_records_retrieve(ZebraHandle zh, ODR stream,
224 Z_RecordComposition *comp,
225 oid_value input_format,
227 ZebraRetrievalRecord *recs);
228 /** \brief Deletes 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,
241 /** \brief returns number of term info terms assocaited with result set
242 \param zh session handle
243 \param setname result set name
244 \param num_terms number of terms returned in this integer
246 This function is used in conjunction with zebra_result_set_term_info.
247 If operation was successful, ZEBRA_OK is returned; otherwise
248 ZEBRA_FAIL is returned (typically non-existing setname)
251 ZEBRA_RES zebra_result_set_term_no(ZebraHandle zh, const char *setname,
254 /** \brief returns information about a term assocated with a result set
255 \param zh session handle
256 \param setname result set name
257 \param no the term we want to know about (0=first, 1=second,..)
258 \param count the number of occurrences of this term, aka hits (output)
259 \param approx about hits: 0=exact,1=approx (output)
260 \param termbuf buffer for term string (intput, output)
261 \param termlen size of termbuf (input=max, output=actual length)
262 \param term_ref_id if non-NULL *term_ref_id holds term reference
264 Returns information about one search term associated with result set.
265 Use zebra_result_set_term_no to read total number of terms associated
266 with result set. If this function can not return information,
267 due to no out of range or bad result set name, ZEBRA_FAIL is
269 The passed termbuf must be able to hold at least *termlen characters.
270 Upon completion, *termlen holds actual length of search term.
273 ZEBRA_RES zebra_result_set_term_info(ZebraHandle zh, const char *setname,
274 int no, zint *count, int *approx,
275 char *termbuf, size_t *termlen,
276 const char **term_ref_id);
279 /** \brief performs Scan (Z39.50 style)
280 \param zh session handle
281 \param stream ODR handle for result
282 \param zapt Attribute plus Term (start term)
283 \param attributeset Attributeset for Attribute plus Term
284 \param position input/output position
285 \param num_entries number of terms requested / returned
286 \param entries list of resulting terms (ODR allocated)
287 \param is_partial upon return 1=partial, 0=complete
288 \param setname limit scan by this set (NULL means no limit)
290 YAZ_EXPORT ZEBRA_RES zebra_scan(ZebraHandle zh, ODR stream,
291 Z_AttributesPlusTerm *zapt,
292 oid_value attributeset,
293 int *position, int *num_entries,
294 ZebraScanEntry **entries,
296 const char *setname);
298 /** \brief performs Scan (taking PQF string)
299 \param zh session handle
300 \param stream ODR handle for result
301 \param query PQF scan query
302 \param position input/output position
303 \param num_entries number of terms requested / returned
304 \param entries list of resulting terms (ODR allocated)
305 \param is_partial upon return 1=partial, 0=complete
306 \param setname limit scan by this set (NULL means no limit)
309 ZEBRA_RES zebra_scan_PQF(ZebraHandle zh, ODR stream, const char *query,
310 int *position, int *num_entries,
311 ZebraScanEntry **entries,
312 int *is_partial, const char *setname);
314 /** \brief authenticate user. Returns 0 if OK, != 0 on failure
315 \param zh session handle
316 \param user user name
320 ZEBRA_RES zebra_auth(ZebraHandle zh, const char *user, const char *pass);
322 /** \brief Normalize zebra term for register (subject to change!)
323 \param zh session handle
324 \param reg_id register ID, 'w', 'p',..
325 \param input_str input string buffer
326 \param input_len input string length
327 \param output_str output string buffer
328 \param output_len output string length
331 int zebra_string_norm(ZebraHandle zh, unsigned reg_id, const char *input_str,
332 int input_len, char *output_str, int output_len);
334 /** \brief Creates a database
335 \param zh session handle
336 \param db database to be created
339 ZEBRA_RES zebra_create_database(ZebraHandle zh, const char *db);
341 /** \brief Deletes a database (drop)
342 \param zh session handle
343 \param db database to be deleted
346 ZEBRA_RES zebra_drop_database(ZebraHandle zh, const char *db);
349 ZEBRA_RES zebra_admin_shutdown(ZebraHandle zh);
352 ZEBRA_RES zebra_admin_start(ZebraHandle zh);
355 ZEBRA_RES zebra_shutdown(ZebraService zs);
358 ZEBRA_RES zebra_admin_import_begin(ZebraHandle zh, const char *database,
359 const char *record_type);
362 ZEBRA_RES zebra_admin_import_segment(ZebraHandle zh,
366 ZEBRA_RES zebra_admin_import_end(ZebraHandle zh);
369 ZEBRA_RES zebra_admin_exchange_record(ZebraHandle zh,
372 const char *recid_buf, size_t recid_len,
376 ZEBRA_RES zebra_begin_trans(ZebraHandle zh, int rw
377 ) ZEBRA_GCC_ATTR((warn_unused_result));
380 ZEBRA_RES zebra_end_trans(ZebraHandle zh
381 ) ZEBRA_GCC_ATTR((warn_unused_result));
384 ZEBRA_RES zebra_end_transaction(ZebraHandle zh,
385 ZebraTransactionStatus *stat);
388 ZEBRA_RES zebra_commit(ZebraHandle zh);
391 ZEBRA_RES zebra_clean(ZebraHandle zh);
394 ZEBRA_RES zebra_init(ZebraHandle zh);
397 ZEBRA_RES zebra_compact(ZebraHandle zh);
400 ZEBRA_RES zebra_repository_update(ZebraHandle zh, const char *path);
403 ZEBRA_RES zebra_repository_delete(ZebraHandle zh, const char *path);
406 ZEBRA_RES zebra_repository_show(ZebraHandle zh, const char *path);
409 ZEBRA_RES zebra_add_record(ZebraHandle zh, const char *buf, int buf_size);
412 ZEBRA_RES zebra_insert_record(ZebraHandle zh,
413 const char *recordType,
414 SYSNO *sysno, const char *match,
416 const char *buf, int buf_size,
419 ZEBRA_RES zebra_update_record(ZebraHandle zh,
420 const char *recordType,
421 SYSNO *sysno, const char *match,
423 const char *buf, int buf_size,
426 ZEBRA_RES zebra_delete_record(ZebraHandle zh,
427 const char *recordType,
428 SYSNO *sysno, const char *match, const char *fname,
429 const char *buf, int buf_size,
433 ZEBRA_RES zebra_sort(ZebraHandle zh, ODR stream,
434 int num_input_setnames,
435 const char **input_setnames,
436 const char *output_setname,
437 Z_SortKeySpecList *sort_sequence,
439 ) ZEBRA_GCC_ATTR((warn_unused_result));
442 ZEBRA_RES zebra_select_databases(ZebraHandle zh, int num_bases,
443 const char **basenames
444 ) ZEBRA_GCC_ATTR((warn_unused_result));
447 ZEBRA_RES zebra_select_database(ZebraHandle zh, const char *basename
448 ) ZEBRA_GCC_ATTR((warn_unused_result));
451 void zebra_shadow_enable(ZebraHandle zh, int value);
454 int zebra_register_statistics(ZebraHandle zh, int dumpdict);
457 ZEBRA_RES zebra_record_encoding(ZebraHandle zh, const char *encoding);
460 ZEBRA_RES zebra_octet_term_encoding(ZebraHandle zh, const char *encoding);
464 void zebra_set_resource(ZebraHandle zh, const char *name, const char *value);
466 const char *zebra_get_resource(ZebraHandle zh,
467 const char *name, const char *defaultvalue);
471 void zebra_pidfname(ZebraService zs, char *path);
481 ZebraMetaRecord *zebra_meta_records_create(ZebraHandle zh,
483 int num, zint *positions);
487 ZebraMetaRecord *zebra_meta_records_create_range(ZebraHandle zh,
489 zint start, int num);
492 void zebra_meta_records_destroy(ZebraHandle zh, ZebraMetaRecord *records,
496 struct BFiles_struct *zebra_get_bfs(ZebraHandle zh);
499 ZEBRA_RES zebra_set_limit(ZebraHandle zh, int complement_flag, zint *ids);
505 * \section intro_sec Introduction
507 * Zebra is a search engine for structure data, such as XML, MARC
510 * API users should read the api.h for all the public definitions.
512 * The remaining sections briefly describe each of
513 * Zebra major modules/components.
515 * \section util Base Utilities
517 * The Zebra utilities (util.h) defines fundamental types and a few
518 * utilites for Zebra.
520 * \section res Resources
522 * The resources system (res.h) is a manager of configuration
523 * resources. The resources can be viewed as a simple database.
524 * Resources can be read from a configurtion file, they can be
525 * read or written by an application. Resources can also be written,
526 * but that facility is not currently in use.
528 * \section bfile Bfiles
530 * The Bfiles (bfile.h) provides a portable interface to the
531 * local file system. It also provides a facility for safe updates
532 * (shadow updates). All file system access is handle by this module
533 * (except for trival reads of configuration files).
535 * \section dict Dictionary
537 * The Zebra dictionary (dict.h) maps a search term (key) to a value. The
538 * value is a reference to the list of records identifers in which
539 * the term occurs. Zebra uses an ISAM data structure for the list
540 * of term occurrences. The Dictionary uses \ref bfile.
544 * Zebra maintains an ISAM for each term where each ISAM is a list
545 * of record identifiers corresponding to the records in which the
546 * term occur. Unlike traditional ISAM systems, the Zebra ISAM
547 * is compressed. The ISAM system uses \ref bfile.
549 * Zebra has more than one ISAM system. The old and stable ISAM system
550 * is named isamc (see isamc.h). Another version isams is a write-once
551 * isam system that is quite compact - suitable for CD-ROMs (isams.h).
552 * The newest ISAM system, isamb, is implemented as a B-Tree (see isamb.h).
554 * \section data1 Data-1
556 * The data1 (data1.h) module deals with structured documents. The module can
557 * can read, modify and write documents. The document structure was
558 * originally based on GRS-1 - a Z39.50 v3 structure that predates
559 * DOM. These days the data1 structure may describe XML/SGML as well.
560 * The data1, like DOM, is a tree structure. Each node in the tree
561 * can be of type element, text (cdata), preprocessing instruction,
562 * comment. Element nodes can point to attribute nodes.
564 * \section recctrl Record Control
566 * The record control module (recctrl.h) is responsible for
567 * managing the various record types ("classes" or filters).
569 * \section rset Result-Set
571 * The Result-Set module (rset.h) defines an interface that all
572 * Zebra Search Results must implement. Each operation (AND, OR, ..)
573 * correspond to an implementation of that interface.
577 * DFA (dfa.h) Deterministic Finite Automa is a regular expression engine.
578 * The module compiles a regular expression to a DFA. The DFA can then
579 * be used in various application to perform fast match against the
580 * origianl expression. The \ref Dict uses DFA to perform lookup
581 * using regular expressions.
588 * indent-tabs-mode: nil
590 * vim: shiftwidth=4 tabstop=8 expandtab