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
|
/* Copyright (C) 2006 J.F.Dockes
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the
* Free Software Foundation, Inc.,
* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
*/
#include "autoconfig.h"
#include <iostream>
#include <algorithm>
#include "wasatorcl.h"
#include "wasaparserdriver.h"
#include "searchdata.h"
#include "log.h"
#include "rclconfig.h"
#define YYDEBUG 1
// bison-generated file
#include "wasaparse.hpp"
using namespace std;
using namespace Rcl;
void
yy::parser::error (const location_type&, const std::string& m)
{
d->setreason(m);
}
std::shared_ptr<SearchData> wasaStringToRcl(
const RclConfig *config, const std::string& stemlang,
const std::string& query, string &reason, const std::string& autosuffs)
{
WasaParserDriver d(config, stemlang, autosuffs);
auto sd = std::shared_ptr<Rcl::SearchData>(d.parse(query));
if (!sd)
reason = d.getreason();
return sd;
}
SearchData *WasaParserDriver::parse(const std::string& in)
{
m_input = in;
m_index = 0;
delete m_result;
m_result = 0;
m_returns = stack<int>();
yy::parser parser(this);
parser.set_debug_level(0);
if (parser.parse() != 0) {
delete m_result;
m_result = 0;
}
if (m_result == 0)
return m_result;
// Set the top level filters (types, dates, size)
for (const auto& ft : m_filetypes) {
m_result->addFiletype(ft);
}
for (const auto& ft : m_nfiletypes) {
m_result->remFiletype(ft);
}
if (m_haveDates) {
m_result->setDateSpan(&m_dates);
}
#ifdef EXT4_BIRTH_TIME
if (m_haveBrDates) {
m_result->setBrDateSpan(&m_brdates);
}
#endif
if (m_minSize != -1) {
m_result->setMinSize(m_minSize);
}
if (m_maxSize != -1) {
m_result->setMaxSize(m_maxSize);
}
if (m_subSpec != Rcl::SearchData::SUBDOC_ANY) {
m_result->setSubSpec(m_subSpec);
}
//if (m_result) m_result->dump(cout);
return m_result;
}
int WasaParserDriver::GETCHAR()
{
if (!m_returns.empty()) {
int c = m_returns.top();
m_returns.pop();
return c;
}
if (m_index < m_input.size())
return m_input[m_index++];
return 0;
}
void WasaParserDriver::UNGETCHAR(int c)
{
m_returns.push(c);
}
// Add clause to query, handling special pseudo-clauses for size/date
// etc. (mostly determined on field name).
bool WasaParserDriver::addClause(SearchData *sd, SearchDataClauseSimple* cl)
{
if (cl->getfield().empty()) {
// Simple clause with empty field spec.
// Possibly change terms found in the "autosuffs" list into "ext"
// field queries
if (!m_autosuffs.empty()) {
vector<string> asfv;
if (stringToStrings(m_autosuffs, asfv)) {
if (find_if(asfv.begin(), asfv.end(),
StringIcmpPred(cl->gettext())) != asfv.end()) {
cl->setfield("ext");
cl->addModifier(SearchDataClause::SDCM_NOSTEMMING);
}
}
}
return sd->addClause(cl);
}
const string& ofld = cl->getfield();
string fld = stringtolower(ofld);
// MIME types and categories
if (!fld.compare("mime") || !fld.compare("format")) {
if (cl->getexclude()) {
m_nfiletypes.push_back(cl->gettext());
} else {
m_filetypes.push_back(cl->gettext());
}
delete cl;
return false;
}
// Filtering for standalone- or sub-documents
if (!fld.compare("issub")) {
m_subSpec = atoi(cl->gettext().c_str());
delete cl;
return false;
}
if (!fld.compare("rclcat") || !fld.compare("type")) {
vector<string> mtypes;
if (m_config && m_config->getMimeCatTypes(cl->gettext(), mtypes)) {
for (vector<string>::iterator mit = mtypes.begin();
mit != mtypes.end(); mit++) {
if (cl->getexclude()) {
m_nfiletypes.push_back(*mit);
} else {
m_filetypes.push_back(*mit);
}
}
}
delete cl;
return false;
}
// Handle "date" spec
if (!fld.compare("date")
#ifdef EXT4_BIRTH_TIME
|| !fld.compare("birtime")
#endif
) {
DateInterval di;
if (!parsedateinterval(cl->gettext(), &di)) {
LOGERR("Bad date interval format: " << cl->gettext() << "\n");
m_reason = "Bad date interval format";
delete cl;
return false;
}
LOGDEB("addClause:: date/brdate span: " << di.y1 << "-" << di.m1 << "-"
<< di.d1 << "/" << di.y2 << "-" << di.m2 << "-" << di.d2 << "\n");
#ifdef EXT4_BIRTH_TIME
if (fld.compare("date")) {
m_haveBrDates = true;
m_brdates = di;
} else
#endif
{
m_haveDates = true;
m_dates = di;
}
delete cl;
return false;
}
// Handle "size" spec
if (!fld.compare("size")) {
char *cp;
int64_t size = strtoll(cl->gettext().c_str(), &cp, 10);
if (*cp != 0) {
switch (*cp) {
case 'k': case 'K': size *= 1000;break;
case 'm': case 'M': size *= 1000*1000;break;
case 'g': case 'G': size *= 1000*1000*1000;break;
case 't': case 'T': size *= int64_t(1000)*1000*1000*1000;break;
default:
m_reason = string("Bad multiplier suffix: ") + *cp;
delete cl;
return false;
}
}
SearchDataClause::Relation rel = cl->getrel();
delete cl;
switch (rel) {
case SearchDataClause::REL_EQUALS:
m_maxSize = m_minSize = size;
break;
case SearchDataClause::REL_LT:
case SearchDataClause::REL_LTE:
m_maxSize = size;
break;
case SearchDataClause::REL_GT:
case SearchDataClause::REL_GTE:
m_minSize = size;
break;
default:
m_reason = "Bad relation operator with size query. Use > < or =";
return false;
}
return false;
}
if (!fld.compare("dir")) {
// dir filtering special case
SearchDataClausePath *nclause = new SearchDataClausePath(cl->gettext(), cl->getexclude());
delete cl;
return sd->addClause(nclause);
}
if (cl->getTp() == SCLT_OR || cl->getTp() == SCLT_AND) {
// If this is a normal clause and the term has commas or
// slashes inside, take it as a list, turn the slashes/commas
// to spaces, leave unquoted. Otherwise, this would end up as
// a phrase query. This is a handy way to enter multiple terms
// to be searched inside a field. We interpret ',' as AND, and
// '/' as OR. No mixes allowed and ',' wins.
SClType tp = SCLT_FILENAME;// impossible value
string ns = neutchars(cl->gettext(), ",");
if (ns.compare(cl->gettext())) {
// had ','
tp = SCLT_AND;
} else {
ns = neutchars(cl->gettext(), "/");
if (ns.compare(cl->gettext())) {
// had not ',' but has '/'
tp = SCLT_OR;
}
}
if (tp != SCLT_FILENAME) {
SearchDataClauseSimple *ncl = new SearchDataClauseSimple(tp, ns, ofld);
delete cl;
return sd->addClause(ncl);
}
}
return sd->addClause(cl);
}
|