[188] | 1 | /**********************************************************************
|
---|
| 2 | *
|
---|
| 3 | * OIDtools.cpp --
|
---|
| 4 | * Copyright (C) 1999 The New Zealand Digital Library Project
|
---|
| 5 | *
|
---|
[533] | 6 | * A component of the Greenstone digital library software
|
---|
| 7 | * from the New Zealand Digital Library Project at the
|
---|
| 8 | * University of Waikato, New Zealand.
|
---|
[188] | 9 | *
|
---|
[533] | 10 | * This program is free software; you can redistribute it and/or modify
|
---|
| 11 | * it under the terms of the GNU General Public License as published by
|
---|
| 12 | * the Free Software Foundation; either version 2 of the License, or
|
---|
| 13 | * (at your option) any later version.
|
---|
| 14 | *
|
---|
| 15 | * This program is distributed in the hope that it will be useful,
|
---|
| 16 | * but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
| 17 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
| 18 | * GNU General Public License for more details.
|
---|
| 19 | *
|
---|
| 20 | * You should have received a copy of the GNU General Public License
|
---|
| 21 | * along with this program; if not, write to the Free Software
|
---|
| 22 | * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
| 23 | *
|
---|
[188] | 24 | *********************************************************************/
|
---|
| 25 |
|
---|
| 26 | #include "OIDtools.h"
|
---|
[1695] | 27 | #include <assert.h>
|
---|
[188] | 28 |
|
---|
[211] | 29 | // returns (in top) the top level of OID (i.e. everything
|
---|
[189] | 30 | // up until the first dot)
|
---|
[211] | 31 | void get_top (const text_t &OID, text_t &top) {
|
---|
[189] | 32 |
|
---|
| 33 | top.clear();
|
---|
[248] | 34 | if (OID.empty()) return;
|
---|
| 35 |
|
---|
[211] | 36 | text_t::const_iterator begin = OID.begin();
|
---|
| 37 | text_t::const_iterator end = OID.end();
|
---|
[189] | 38 |
|
---|
| 39 | top.appendrange (begin, findchar(begin, end, '.'));
|
---|
| 40 | }
|
---|
| 41 |
|
---|
| 42 |
|
---|
[211] | 43 | // checks if OID is top level (i.e. contains no dots)
|
---|
| 44 | bool is_top (const text_t &OID) {
|
---|
[189] | 45 |
|
---|
[211] | 46 | if (OID.empty()) return true;
|
---|
| 47 |
|
---|
| 48 | text_t::const_iterator here = OID.begin();
|
---|
| 49 | text_t::const_iterator end = OID.end();
|
---|
[189] | 50 | here = findchar (here, end, '.');
|
---|
| 51 |
|
---|
| 52 | if (here == end) return true;
|
---|
| 53 | return false;
|
---|
| 54 | }
|
---|
[211] | 55 |
|
---|
| 56 |
|
---|
| 57 | // get_parents_array loads the parents array with all the parents of the
|
---|
[274] | 58 | // document or classification specified by OID (not including OID itself)
|
---|
[211] | 59 | void get_parents_array (const text_t &OID, text_tarray &parents) {
|
---|
| 60 |
|
---|
| 61 | text_t::const_iterator here = OID.begin ();
|
---|
| 62 | text_t::const_iterator end = OID.end ();
|
---|
| 63 | text_t thisparent;
|
---|
| 64 |
|
---|
| 65 | while (here != end) {
|
---|
| 66 | if (*here == '.') parents.push_back(thisparent);
|
---|
| 67 | thisparent.push_back(*here);
|
---|
[7414] | 68 | ++here;
|
---|
[211] | 69 | }
|
---|
| 70 | }
|
---|
| 71 |
|
---|
| 72 |
|
---|
[248] | 73 | // get_info does a protocol call and returns (in response) the metadata
|
---|
[649] | 74 | // associated with OID. Metadata should be loaded with whatever
|
---|
[248] | 75 | // metadata fields are to be requested.
|
---|
[211] | 76 |
|
---|
[7414] | 77 | bool get_info (const text_t &OID, const text_t &collection, const text_t &lang,
|
---|
[649] | 78 | const text_tset &metadata, bool getParents,
|
---|
[472] | 79 | recptproto *collectproto, FilterResponse_t &response,
|
---|
[278] | 80 | ostream &logout) {
|
---|
[211] | 81 |
|
---|
[248] | 82 | response.clear();
|
---|
| 83 |
|
---|
[2261] | 84 | comerror_t err = noError;
|
---|
[248] | 85 | FilterRequest_t request;
|
---|
[1443] | 86 | request.clear();
|
---|
[248] | 87 |
|
---|
| 88 | request.filterName = "NullFilter";
|
---|
[7414] | 89 | request.filterLang = lang;
|
---|
[248] | 90 | request.filterResultOptions = FRmetadata;
|
---|
[278] | 91 | request.getParents = getParents;
|
---|
[248] | 92 | request.fields = metadata;
|
---|
[472] | 93 | request.docSet.push_back (OID);
|
---|
[1695] | 94 | assert (collectproto != NULL);
|
---|
[1860] | 95 |
|
---|
[248] | 96 | collectproto->filter (collection, request, response, err, logout);
|
---|
| 97 | if (err != noError) {
|
---|
| 98 | outconvertclass text_t2ascii;
|
---|
| 99 | logout << text_t2ascii
|
---|
| 100 | << "Error: call to filter failed for " << OID
|
---|
| 101 | << " in OIDtools::get_info ("
|
---|
| 102 | << get_comerror_string (err) << ")\n";
|
---|
| 103 | return false;
|
---|
| 104 | }
|
---|
[505] | 105 |
|
---|
[248] | 106 | return true;
|
---|
[211] | 107 | }
|
---|
| 108 |
|
---|
[1347] | 109 | // overloaded, to allow "custom" filter options.
|
---|
[7414] | 110 | bool get_info (const text_t &OID, const text_t &collection, const text_t &lang,
|
---|
[1347] | 111 | const text_tset &metadata, const OptionValue_tarray &options,
|
---|
| 112 | bool getParents,
|
---|
| 113 | recptproto *collectproto, FilterResponse_t &response,
|
---|
| 114 | ostream &logout) {
|
---|
| 115 |
|
---|
| 116 | response.clear();
|
---|
| 117 |
|
---|
[2261] | 118 | comerror_t err = noError;
|
---|
[1347] | 119 | FilterRequest_t request;
|
---|
| 120 |
|
---|
| 121 | request.filterName = "NullFilter";
|
---|
[7414] | 122 | request.filterLang = lang;
|
---|
[1347] | 123 | request.filterResultOptions = FRmetadata;
|
---|
| 124 | request.getParents = getParents;
|
---|
| 125 | request.filterOptions = options;
|
---|
| 126 | request.fields = metadata;
|
---|
| 127 | request.docSet.push_back (OID);
|
---|
[1695] | 128 |
|
---|
| 129 | assert (collectproto != NULL);
|
---|
[1347] | 130 | collectproto->filter (collection, request, response, err, logout);
|
---|
| 131 | if (err != noError) {
|
---|
| 132 | outconvertclass text_t2ascii;
|
---|
| 133 | logout << text_t2ascii
|
---|
| 134 | << "Error: call to filter failed for " << OID
|
---|
| 135 | << " in OIDtools::get_info ("
|
---|
| 136 | << get_comerror_string (err) << ")\n";
|
---|
| 137 | return false;
|
---|
| 138 | }
|
---|
| 139 |
|
---|
| 140 | return true;
|
---|
| 141 | }
|
---|
| 142 |
|
---|
[7414] | 143 | bool get_info (const text_tarray &OIDs, const text_t &collection, const text_t &lang,
|
---|
[649] | 144 | const text_tset &metadata, bool getParents,
|
---|
[472] | 145 | recptproto *collectproto, FilterResponse_t &response,
|
---|
[423] | 146 | ostream &logout) {
|
---|
| 147 |
|
---|
| 148 | response.clear();
|
---|
| 149 | if (OIDs.empty()) return true;
|
---|
| 150 |
|
---|
[2261] | 151 | comerror_t err = noError;
|
---|
[423] | 152 | FilterRequest_t request;
|
---|
| 153 |
|
---|
| 154 | request.filterName = "NullFilter";
|
---|
[7414] | 155 | request.filterLang = lang;
|
---|
[423] | 156 | request.filterResultOptions = FRmetadata;
|
---|
| 157 | request.getParents = getParents;
|
---|
| 158 | request.fields = metadata;
|
---|
| 159 |
|
---|
[472] | 160 | request.docSet = OIDs;
|
---|
[423] | 161 |
|
---|
| 162 | collectproto->filter (collection, request, response, err, logout);
|
---|
| 163 | if (err != noError) {
|
---|
| 164 | outconvertclass text_t2ascii;
|
---|
| 165 | logout << text_t2ascii
|
---|
| 166 | << "Error: call to filter failed in OIDtools::get_info ("
|
---|
| 167 | << get_comerror_string (err) << ")\n";
|
---|
| 168 | return false;
|
---|
| 169 | }
|
---|
[505] | 170 |
|
---|
[423] | 171 | return true;
|
---|
| 172 | }
|
---|
| 173 |
|
---|
[1347] | 174 |
|
---|
| 175 |
|
---|
[257] | 176 | // has_children returns true if OID has children
|
---|
[7414] | 177 | bool has_children (const text_t &OID, const text_t &collection, const text_t &lang,
|
---|
[257] | 178 | recptproto *collectproto, ostream &logout) {
|
---|
| 179 |
|
---|
| 180 | FilterResponse_t response;
|
---|
[649] | 181 | text_tset metadata;
|
---|
| 182 | metadata.insert ("haschildren");
|
---|
[257] | 183 |
|
---|
[7414] | 184 | if (get_info (OID, collection, lang, metadata, false, collectproto, response, logout)) {
|
---|
[649] | 185 | if (response.docInfo[0].metadata["haschildren"].values[0] == "1")
|
---|
[257] | 186 | return true;
|
---|
| 187 | }
|
---|
| 188 | return false;
|
---|
| 189 | }
|
---|
| 190 |
|
---|
| 191 |
|
---|
[248] | 192 | // get_children does a protocol call and returns (in response) the OIDs and
|
---|
[649] | 193 | // metadata of all the children of OID. The metadata set should be loaded
|
---|
[248] | 194 | // with whatever metadata fields are to be requested.
|
---|
[211] | 195 |
|
---|
[7414] | 196 | bool get_children (const text_t &OID, const text_t &collection, const text_t &lang,
|
---|
[649] | 197 | const text_tset &metadata, bool getParents,
|
---|
[406] | 198 | recptproto *collectproto, FilterResponse_t &response,
|
---|
| 199 | ostream &logout) {
|
---|
[248] | 200 |
|
---|
| 201 | response.clear();
|
---|
| 202 |
|
---|
[2261] | 203 | comerror_t err = noError;
|
---|
[248] | 204 | FilterRequest_t request;
|
---|
| 205 | OptionValue_t option;
|
---|
| 206 |
|
---|
| 207 | option.name = "ParentNode";
|
---|
| 208 | option.value = OID;
|
---|
| 209 | request.filterOptions.push_back (option);
|
---|
| 210 | request.filterName = "BrowseFilter";
|
---|
[7414] | 211 | request.filterLang = lang;
|
---|
[248] | 212 | request.filterResultOptions = FROID | FRmetadata;
|
---|
| 213 | request.fields = metadata;
|
---|
[406] | 214 | request.getParents = getParents;
|
---|
[248] | 215 |
|
---|
| 216 | collectproto->filter (collection, request, response, err, logout);
|
---|
| 217 |
|
---|
| 218 | if (err != noError) {
|
---|
| 219 | outconvertclass text_t2ascii;
|
---|
| 220 | logout << text_t2ascii
|
---|
| 221 | << "Error: call to filter failed for " << OID
|
---|
| 222 | << " in OIDtools::get_children ("
|
---|
| 223 | << get_comerror_string (err) << ")\n";
|
---|
| 224 | return false;
|
---|
| 225 | }
|
---|
| 226 | return true;
|
---|
| 227 | }
|
---|
| 228 |
|
---|
[211] | 229 | // get_parent returns the parent of the document or classification
|
---|
| 230 | // specified by OID
|
---|
[11259] | 231 | text_t get_parent (const text_t& OID)
|
---|
| 232 | {
|
---|
| 233 | if (OID.empty() || is_top (OID)) return g_EmptyText;
|
---|
[211] | 234 |
|
---|
| 235 | text_t::const_iterator begin = OID.begin();
|
---|
| 236 | text_t::const_iterator here = (OID.end() - 1);
|
---|
| 237 |
|
---|
| 238 | while (here >= begin) {
|
---|
[11259] | 239 | if (*here == '.')
|
---|
| 240 | break;
|
---|
| 241 | if (here == begin)
|
---|
| 242 | break;
|
---|
[9620] | 243 | --here;
|
---|
[211] | 244 | }
|
---|
[11259] | 245 |
|
---|
| 246 | if (here != begin) {
|
---|
| 247 | text_t parentOID;
|
---|
| 248 | parentOID.appendrange(begin, here);
|
---|
| 249 | return parentOID;
|
---|
| 250 | }
|
---|
| 251 |
|
---|
| 252 | return g_EmptyText;
|
---|
[211] | 253 | }
|
---|
| 254 |
|
---|
[257] | 255 | // takes an OID like ".2 and replaces the " with parent
|
---|
[248] | 256 | void translate_parent (text_t &OID, const text_t &parent) {
|
---|
[211] | 257 |
|
---|
[248] | 258 | text_t::const_iterator here = OID.begin();
|
---|
| 259 | text_t::const_iterator end = OID.end();
|
---|
| 260 | text_t temp;
|
---|
| 261 |
|
---|
| 262 | while (here != end) {
|
---|
| 263 | if (*here == '"') temp += parent;
|
---|
| 264 | else temp.push_back (*here);
|
---|
[7414] | 265 | ++here;
|
---|
[248] | 266 | }
|
---|
| 267 | OID = temp;
|
---|
[211] | 268 | }
|
---|
[248] | 269 |
|
---|
| 270 | // shrink_parent does the opposite to translate_parent
|
---|
| 271 | void shrink_parent (text_t &OID) {
|
---|
| 272 |
|
---|
[257] | 273 | text_tarray tmp;
|
---|
| 274 | splitchar (OID.begin(), OID.end(), '.', tmp);
|
---|
| 275 | OID = "\"." + tmp.back();
|
---|
[248] | 276 | }
|
---|
| 277 |
|
---|
| 278 | // checks if OID uses ".fc", ".lc", ".pr", ".ns",
|
---|
| 279 | // or ".ps" syntax (first child, last child, parent,
|
---|
| 280 | // next sibling, previous sibling)
|
---|
| 281 | bool needs_translating (const text_t &OID) {
|
---|
| 282 |
|
---|
| 283 | if (OID.size() < 4) return false;
|
---|
| 284 |
|
---|
| 285 | text_t tail = substr (OID.end()-3, OID.end());
|
---|
| 286 | if (tail == ".fc" || tail == ".lc" || tail == ".pr" ||
|
---|
| 287 | tail == ".ns" || tail == ".ps") return true;
|
---|
| 288 |
|
---|
| 289 | return false;
|
---|
| 290 | }
|
---|
[257] | 291 |
|
---|
[280] | 292 | // strips the ".fc", ".lc", ".pr", ".ns",
|
---|
| 293 | // or ".ps" suffix from the end of OID
|
---|
| 294 | void strip_suffix (text_t &OID) {
|
---|
[257] | 295 |
|
---|
[280] | 296 | text_t tail = substr (OID.end()-3, OID.end());
|
---|
| 297 | while (tail == ".fc" || tail == ".lc" || tail == ".pr" ||
|
---|
| 298 | tail == ".ns" || tail == ".ps") {
|
---|
| 299 | OID.erase (OID.end()-3, OID.end());
|
---|
| 300 | tail = substr (OID.end()-3, OID.end());
|
---|
| 301 | }
|
---|
| 302 | }
|
---|
| 303 |
|
---|
[649] | 304 | static void recurse_contents (ResultDocInfo_t section, const bool &is_classify,
|
---|
[7414] | 305 | const text_t &collection, const text_t &lang,
|
---|
| 306 | const text_tset &metadata,
|
---|
[649] | 307 | recptproto *collectproto, FilterResponse_t &response,
|
---|
| 308 | ostream &logout) {
|
---|
[445] | 309 |
|
---|
[649] | 310 | int haschildren = section.metadata["haschildren"].values[0].getint();
|
---|
| 311 | const text_t &doctype = section.metadata["doctype"].values[0];
|
---|
[257] | 312 |
|
---|
[649] | 313 | if ((haschildren == 1) && ((!is_classify) || (doctype == "classify"))) {
|
---|
[257] | 314 | FilterResponse_t tmp;
|
---|
[406] | 315 | bool getParents = false;
|
---|
[7414] | 316 | get_children (section.OID, collection, lang, metadata, getParents, collectproto, tmp, logout);
|
---|
[649] | 317 | ResultDocInfo_tarray::iterator thisdoc = tmp.docInfo.begin();
|
---|
| 318 | ResultDocInfo_tarray::iterator lastdoc = tmp.docInfo.end();
|
---|
[257] | 319 | while (thisdoc != lastdoc) {
|
---|
| 320 | response.docInfo.push_back (*thisdoc);
|
---|
[7414] | 321 | recurse_contents (*thisdoc, is_classify, collection, lang, metadata,
|
---|
[649] | 322 | collectproto, response, logout);
|
---|
[7414] | 323 | ++thisdoc;
|
---|
[257] | 324 | }
|
---|
| 325 | }
|
---|
| 326 | }
|
---|
| 327 |
|
---|
| 328 | // get_contents returns OIDs and metadata of all contents
|
---|
| 329 | // below (and including) OID.
|
---|
[649] | 330 | void get_contents (const text_t &topOID, const bool &is_classify,
|
---|
[7414] | 331 | text_tset &metadata, const text_t &collection, const text_t &lang,
|
---|
[649] | 332 | recptproto *collectproto, FilterResponse_t &response,
|
---|
| 333 | ostream &logout) {
|
---|
[257] | 334 |
|
---|
[445] | 335 | if (topOID.empty()) return;
|
---|
[257] | 336 | response.clear();
|
---|
| 337 |
|
---|
[649] | 338 | metadata.insert ("haschildren");
|
---|
| 339 | metadata.insert ("doctype");
|
---|
[445] | 340 |
|
---|
[257] | 341 | // get topOIDs info
|
---|
[7414] | 342 | if (get_info (topOID, collection, lang, metadata, false, collectproto, response, logout)) {
|
---|
| 343 | recurse_contents (response.docInfo[0], is_classify, collection, lang,
|
---|
| 344 | metadata, collectproto, response, logout);
|
---|
| 345 | }
|
---|
[257] | 346 | }
|
---|
[346] | 347 |
|
---|
| 348 | // is_child_of returns true if OID2 is a child of OID1
|
---|
| 349 | bool is_child_of(const text_t &OID1, const text_t &OID2) {
|
---|
| 350 |
|
---|
| 351 | text_t parent = get_parent(OID2);
|
---|
| 352 |
|
---|
| 353 | while (!parent.empty()) {
|
---|
| 354 | if (parent == OID1) return true;
|
---|
| 355 | parent = get_parent(parent);
|
---|
| 356 | }
|
---|
| 357 | return false;
|
---|
| 358 | }
|
---|