1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515
/// WritableDatabase flags
pub const DB_BACKEND_GLASS: i32 = 0x100;
/// the chert backend, No longer supported as of Xapian 1.5.0
pub const DB_BACKEND_CHERT: i32 = 0x200;
/// Open a stub database file
pub const DB_BACKEND_STUB: i32 = 0x300;
/** Use the "in memory" backend.
*
* The filename is currently ignored when this flag is used, but an empty
* string should be passed to allow for future expansion.
*
* A new empty database is created, so when creating a Database object this
* creates an empty read-only database - sometimes useful to avoid special
* casing this situation, but otherwise of limited use. It's more useful
* when creating a WritableDatabase object, though beware that the current
* inmemory backend implementation was not built for performance and
* scalability.
*
* This provides an equivalent to Xapian::InMemory::open() in Xapian 1.2.
*/
pub const DB_BACKEND_INMEMORY: i32 = 0x400;
/** Use the honey backend.
*
* When opening a WritableDatabase, this means create a honey database if a
* new database is created. If there's an existing database (of any type)
* at the specified path, this flag has no effect.
*
* When opening a Database, this flag means to only open it if it's a honey
* database. There's rarely a good reason to do this - it's mostly provided
* as equivalent functionality to that provided by the namespaced open()
* functions in Xapian 1.2.
*/
pub const DB_BACKEND_HONEY: i32 = 0x500;
/** Create database if it doesn't already exist.
*
* If no opening mode is specified, this is the default.
*/
pub const DB_CREATE_OR_OPEN: i32 = 0x00;
/** Create database if it doesn't already exist, or overwrite if it does. */
pub const DB_CREATE_OR_OVERWRITE: i32 = 0x01;
/** Create a new database.
*
* If the database already exists, an exception will be thrown.
*/
pub const DB_CREATE: i32 = 0x02;
/** Open an existing database.
*
* If the database doesn't exist, an exception will be thrown.
*/
pub const DB_OPEN: i32 = 0x03;
/// Enum of possible query operations
/// #[repr(i32)]
pub enum XapianOp {
/// Return iff both subqueries are satisfied
OpAnd,
/// Return if either subquery is satisfied
OpOr,
/// Return if left but not right satisfied
OpAndNot,
/// Return if one query satisfied, but not both
OpXor,
/// Return iff left satisfied, but use weights from both
OpAndMaybe,
/// As AND, but use only weights from left subquery
OpFilter,
/** Find occurrences of a list of terms with all the terms
* occurring within a specified window of positions.
*
* Each occurrence of a term must be at a different position,
* but the order they appear in is irrelevant.
*
* The window parameter should be specified for this operation,
* but will default to the number of terms in the list.
*/
OpNear,
/** Find occurrences of a list of terms with all the terms
* occurring within a specified window of positions, and all
* the terms appearing in the order specified.
*
* Each occurrence of a term must be at a different position.
*
* The window parameter should be specified for this operation,
* but will default to the number of terms in the list.
*/
OpPhrase,
/** Filter by a range test on a document value. */
OpValueRange,
/** Scale the weight of a subquery by the specified factor.
*
* A factor of 0 means this subquery will contribute no weight to
* the query - it will act as a purely boolean subquery.
*
* If the factor is negative, Xapian::InvalidArgumentError will
* be thrown.
*/
OpScaleWeight,
/** Pick the best N subqueries and combine with OP_OR.
*
* If you want to implement a feature which finds documents
* similar to a piece of text, an obvious approach is to build an
* "OR" query from all the terms in the text, and run this query
* against a database containing the documents. However such a
* query can contain a lots of terms and be quite slow to perform,
* yet many of these terms don't contribute usefully to the
* results.
*
* The OP_ELITE_SET operator can be used instead of OP_OR in this
* situation. OP_ELITE_SET selects the most important ''N'' terms
* and then acts as an OP_OR query with just these, ignoring any
* other terms. This will usually return results just as good as
* the full OP_OR query, but much faster.
*
* In general, the OP_ELITE_SET operator can be used when you have
* a large OR query, but it doesn't matter if the search
* completely ignores some of the less important terms in the
* query.
*
* The subqueries don't have to be terms, but if they aren't then
* OP_ELITE_SET will look at the estimated frequencies of the
* subqueries and so could pick a subset which don't actually
* match any documents even if the full OR would match some.
*
* You can specify a parameter to the query constructor which
* control the number of terms which OP_ELITE_SET will pick. If
* not specified, this defaults to 10 (or
* <code>ceil(sqrt(number_of_subqueries))</code> if there are more
* than 100 subqueries, but this rather arbitrary special case
* will be dropped in 1.3.0). For example, this will pick the
* best 7 terms:
*
* <pre>
* Xapian::Query query(Xapian::Query::OP_ELITE_SET, subqs.begin(), subqs.end(), 7);
* </pre>
*
* If the number of subqueries is less than this threshold,
* OP_ELITE_SET behaves identically to OP_OR.
*/
OpEliteSet,
/** Filter by a greater-than-or-equal test on a document value. */
OpValueGe,
/** Filter by a less-than-or-equal test on a document value. */
OpValueLe,
/** Treat a set of queries as synonyms.
*
* This returns all results which match at least one of the
* queries, but weighting as if all the sub-queries are instances
* of the same term: so multiple matching terms for a document
* increase the wdf value used, and the term frequency is based on
* the number of documents which would match an OR of all the
* subqueries.
*
* The term frequency used will usually be an approximation,
* because calculating the precise combined term frequency would
* be overly expensive.
*
* Identical to OP_OR, except for the weightings returned.
*/
OpSynonym,
}
/// Flags to OR together and pass to TermGenerator::set_flags().
#[allow(non_camel_case_types)]
#[repr(i32)]
pub enum TermGeneratorFlag {
FLAG_DEFAULT = 0,
/// Index data required for spelling correction.
FLAG_SPELLING = 128, // Value matches QueryParser flag.
/** Generate n-grams for scripts without explicit word breaks.
*
* Spans of characters in such scripts are split into unigrams
* and bigrams, with the unigrams carrying positional information.
* Text in other scripts is split into words as normal.
*
* The QueryParser::FLAG_NGRAMS flag needs to be passed to
* QueryParser.
*
* This mode can also be enabled in 1.2.8 and later by setting
* environment variable XAPIAN_CJK_NGRAM to a non-empty value (but
* doing so was deprecated in 1.4.11).
*
* In 1.4.x this feature was specific to CJK (Chinese, Japanese and
* Korean), but in 1.5.0 it's been extended to other languages. To
* reflect this change the new and preferred name is FLAG_NGRAMS,
* which was added as an alias for forward compatibility in Xapian
* 1.4.23. Use FLAG_CJK_NGRAM instead if you aim to support Xapian
* < 1.4.23.
*
* @since Added in Xapian 1.4.23.
*/
FLAG_NGRAMS = 2048, // Value matches QueryParser flag.
/** Find word breaks for text in scripts without explicit word breaks.
*
* With this option enabled, spans of text written in such scripts are
* split into words using ICU (which uses heuristics and/or
* dictionaries to do so). Text in other scripts is split into words
* as normal.
*
* The QueryParser::FLAG_WORD_BREAKS flag needs to be passed to
* QueryParser.
*
* @since Added in Xapian 1.5.0.
*/
FLAG_WORD_BREAKS = 4096 // Value matches QueryParser flag
}
/// QueryParser::feature_flag
#[allow(non_camel_case_types)]
#[repr(i32)]
#[derive(Debug)]
pub enum QueryParserFeatureFlag {
/// Support AND, OR, etc and bracketed subexpressions.
FLAG_BOOLEAN = 1,
/// Support quoted phrases.
FLAG_PHRASE = 2,
/// Support + and -.
FLAG_LOVEHATE = 4,
/// Support AND, OR, etc even if they aren't in ALLCAPS.
FLAG_BOOLEAN_ANY_CASE = 8,
/** Support wildcards.
*
* At present only right truncation (e.g. Xap*) is supported.
*
* Currently you can't use wildcards with boolean filter prefixes,
* or in a phrase (either an explicitly quoted one, or one implicitly
* generated by hyphens or other punctuation).
*
* In Xapian 1.2.x, you needed to tell the QueryParser object which
* database to expand wildcards from by calling set_database(). In
* Xapian 1.3.3, OP_WILDCARD was added and wildcards are now
* expanded when Enquire::get_mset() is called, with the expansion
* using the database being searched.
*/
FLAG_WILDCARD = 16,
/** Allow queries such as 'NOT apples'.
*
* These require the use of a list of all documents in the database
* which is potentially expensive, so this feature isn't enabled by
* default.
*/
FLAG_PURE_NOT = 32,
/** Enable partial matching.
*
* Partial matching causes the parser to treat the query as a
* "partially entered" search. This will automatically treat the
* final word as a wildcarded match, unless it is followed by
* whitespace, to produce more stable results from interactive
* searches.
*
* Currently FLAG_PARTIAL doesn't do anything if the final word
* in the query has a boolean filter prefix, or if it is in a phrase
* (either an explicitly quoted one, or one implicitly generated by
* hyphens or other punctuation). It also doesn't do anything if
* if the final word is part of a value range.
*
* In Xapian 1.2.x, you needed to tell the QueryParser object which
* database to expand wildcards from by calling set_database(). In
* Xapian 1.3.3, OP_WILDCARD was added and wildcards are now
* expanded when Enquire::get_mset() is called, with the expansion
* using the database being searched.
*/
FLAG_PARTIAL = 64,
/** Enable spelling correction.
*
* For each word in the query which doesn't exist as a term in the
* database, Database::get_spelling_suggestion() will be called and if
* a suggestion is returned, a corrected version of the query string
* will be built up which can be read using
* QueryParser::get_corrected_query_string(). The query returned is
* based on the uncorrected query string however - if you want a
* parsed query based on the corrected query string, you must call
* QueryParser::parse_query() again.
*
* NB: You must also call set_database() for this to work.
*/
FLAG_SPELLING_CORRECTION = 128,
/** Enable synonym operator '~'.
*
* NB: You must also call set_database() for this to work.
*/
FLAG_SYNONYM = 256,
/** Enable automatic use of synonyms for single terms.
*
* NB: You must also call set_database() for this to work.
*/
FLAG_AUTO_SYNONYMS = 512,
/** Enable automatic use of synonyms for single terms and groups of
* terms.
*
* NB: You must also call set_database() for this to work.
*/
FLAG_AUTO_MULTIWORD_SYNONYMS = 1024,
/** Generate n-grams for scripts without explicit word breaks.
*
* Spans of characters in such scripts are split into unigrams
* and bigrams, with the unigrams carrying positional information.
* Text in other scripts is split into words as normal.
*
* The TermGenerator::FLAG_NGRAMS flag needs to have been used at
* index time.
*
* This mode can also be enabled in 1.2.8 and later by setting
* environment variable XAPIAN_CJK_NGRAM to a non-empty value (but
* doing so was deprecated in 1.4.11).
*
* In 1.4.x this feature was specific to CJK (Chinese, Japanese and
* Korean), but in 1.5.0 it's been extended to other languages. To
* reflect this change the new and preferred name is FLAG_NGRAMS,
* which was added as an alias for forward compatibility in Xapian
* 1.4.23. Use FLAG_CJK_NGRAM instead if you aim to support Xapian
* < 1.4.23.
*
* @since Added in Xapian 1.4.23.
*/
FLAG_NGRAMS = 2048,
/** Find word breaks for text in scripts without explicit word breaks.
*
* With this option enabled, spans of text written in such scripts are
* split into words using ICU (which uses heuristics and/or
* dictionaries to do so). Text in other scripts is split into words
* as normal.
*
* The TermGenerator::FLAG_WORD_BREAKS flag needs to have been used at
* index time.
*
* @since Added in Xapian 1.5.0.
*/
FLAG_WORD_BREAKS = 4096,
/** Support extended wildcard '*'.
*
* This flag enables support for wildcard '*' matching zero
* or more characters, which may be used anywhere in a word.
*
* Such wildcards can be relatively expensive to expand and to match
* so benchmark your system carefully if you have a lot of documents
* and/or a high search load.
*
* FLAG_WILDCARD is ignored if this flag is specified.
*
* @since Added in Xapian 1.5.0.
*/
FLAG_WILDCARD_MULTI = 8192,
/** Support extended wildcard '?'.
*
* This flag enables support for wildcard '?' matching exactly one
* character, which may be use anywhere in a word.
*
* Such wildcards can be relatively expensive to expand and to match
* so benchmark your system carefully if you have a lot of documents
* and/or a high search load.
*
* FLAG_WILDCARD is ignored if this flag is specified.
*
* @since Added in Xapian 1.5.0.
*/
FLAG_WILDCARD_SINGLE = 16384,
/** Enable glob-style wildcarding.
*
* This enables all supported glob-style wildcard pattern flags
* - currently that's FLAG_WILDCARD_MULTI and FLAG_WILDCARD_SINGLE.
*
* FLAG_WILDCARD is ignored if this flag is specified.
*
* @since Added in Xapian 1.5.0.
*/
FLAG_WILDCARD_GLOB = Self::FLAG_WILDCARD_MULTI as i32 | Self::FLAG_WILDCARD_SINGLE as i32,
/** Support fuzzy matching.
*
* E.g. "unserten~3" would expand to "uncertain" (and likely other
* terms).
*
* foo~ uses edit distance of 2
* since~0.2 uses edit distance of length("since") * 0.2 = 5 * 0.2 = 1
*
* @since Added in Xapian 1.5.0.
*/
FLAG_FUZZY = 32768,
/** Accumulate unstem and stoplist results.
*
* By default, the unstem and stoplist data is reset by a call to
* parse_query(), which makes sense if you use the same QueryParser
* object to parse a series of independent queries.
*
* If you're using the same QueryParser object to parse several
* fields on the same query form, you may want to have the unstem
* and stoplist data combined for all of them, in which case you
* can use this flag to prevent this data from being reset.
*
* @since Added in Xapian 1.4.18.
*/
FLAG_ACCUMULATE = 65536,
/** Produce a query which doesn't use positional information.
*
* With this flag enabled, no positional information will be used
* and any query operations which would use it are replaced by
* the nearest equivalent which doesn't (so phrase searches, NEAR
* and ADJ will result in OP_AND).
*
* @since Added in Xapian 1.4.19.
*/
FLAG_NO_POSITIONS = 0x20000,
/** The default flags.
*
* Used if you don't explicitly pass any to @a parse_query().
* The default flags are FLAG_PHRASE|FLAG_BOOLEAN|FLAG_LOVEHATE.
*
* @since Added in Xapian 1.0.11.
*/
FLAG_DEFAULT = Self::FLAG_PHRASE as i32 | Self::FLAG_BOOLEAN as i32 | Self::FLAG_LOVEHATE as i32,
}
/// Enum of possible query operations
#[allow(non_camel_case_types)]
/// #[repr(i32)]
pub enum RangeProcessorFlags {
RP_PREFIX = 0,
/// as a suffix
RP_SUFFIX = 1,
/// optionally allow str_ on both ends of the range - e.g. $1..$10 or 5m..50m.
RP_REPEATED = 2,
RP_DATE_PREFER_MDY = 4,
}
#[allow(non_camel_case_types)]
#[repr(i32)]
#[derive(Debug)]
pub enum SnippetFlags {
/** Model the relevancy of non-query terms in MSet::snippet().
*
* Non-query terms will be assigned a small weight, and the snippet
* will tend to prefer snippets which contain a more interesting
* background (where the query term content is equivalent).
*/
SNIPPET_BACKGROUND_MODEL = 1,
/** Exhaustively evaluate candidate snippets in MSet::snippet().
*
* Without this flag, snippet generation will stop once it thinks
* it has found a "good enough" snippet, which will generally reduce
* the time taken to generate a snippet.
*/
SNIPPET_EXHAUSTIVE = 2,
/** Return the empty string if no term got matched.
*
* If enabled, snippet() returns an empty string if not a single match
* was found in text. If not enabled, snippet() returns a (sub)string
* of text without any highlighted terms.
*/
SNIPPET_EMPTY_WITHOUT_MATCH = 4,
/** Enable generation of n-grams from CJK text.
*
* This option highlights CJK searches made using the QueryParser
* FLAG_CJK_NGRAM flag. Non-CJK characters are split into words as
* normal.
*
* The TermGenerator FLAG_CJK_NGRAM flag needs to have been used at
* index time.
*
* This mode can also be enabled by setting environment variable
* XAPIAN_CJK_NGRAM to a non-empty value (but doing so was deprecated
* in 1.4.11).
*
* @since Added in Xapian 1.4.11.
*/
SNIPPET_CJK_NGRAM = 2048,
}
// Enquire::docid_order
#[allow(non_camel_case_types)]
#[repr(i32)]
#[derive(Debug)]
pub enum EnquireDocidOrder {
/** docids sort in ascending order (default) */
ASCENDING = 1,
/** docids sort in descending order. */
DESCENDING = 0,
/** docids sort in whatever order is most efficient for the backend. */
DONT_CARE = 2
}