Parent: [cf0757] (diff)

Child: [a769ad] (diff)

Download this file

plaintorich.cpp    177 lines (164 with data), 5.4 kB

  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
#ifndef lint
static char rcsid[] = "@(#$Id: plaintorich.cpp,v 1.11 2006-09-13 14:57:56 dockes Exp $ (C) 2005 J.F.Dockes";
#endif
/*
* 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.,
* 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
*/
#include <string>
#include <utility>
#include <list>
#include <set>
#ifndef NO_NAMESPACES
using std::list;
using std::pair;
using std::set;
#endif /* NO_NAMESPACES */
#include "rcldb.h"
#include "rclconfig.h"
#include "debuglog.h"
#include "textsplit.h"
#include "utf8iter.h"
#include "transcode.h"
#include "smallut.h"
#include "plaintorich.h"
#include "cancelcheck.h"
// Text splitter callback used to take note of the position of query terms
// inside the result text. This is then used to post highlight tags.
class myTextSplitCB : public TextSplitCB {
public:
string firstTerm;
set<string> terms; // in: user query terms
list<pair<int, int> > tboffs; // out: begin and end positions of
// query terms in text
myTextSplitCB(const list<string>& its) {
for (list<string>::const_iterator it = its.begin(); it != its.end();
it++) {
string s;
Rcl::dumb_string(*it, s);
terms.insert(s);
}
}
// Callback called by the text-to-words breaker for each word
virtual bool takeword(const std::string& term, int, int bts, int bte) {
string dumb;
Rcl::dumb_string(term, dumb);
//LOGDEB(("Input dumbbed term: '%s' %d %d %d\n", dumb.c_str(),
// pos, bts, bte));
if (terms.find(dumb) != terms.end()) {
tboffs.push_back(pair<int, int>(bts, bte));
if (firstTerm.empty())
firstTerm = term;
}
CancelCheck::instance().checkCancel();
return true;
}
};
// Fix result text for display inside the gui text window.
//
// To compute the term character positions in the output text, we used
// to emulate how qt's textedit counts chars (ignoring tags and
// duplicate whitespace etc...). This was tricky business, dependant
// on qtextedit internals, and we don't do it any more, so we finally
// don't know the term par/car positions in the editor text. Instead,
// we return the first term encountered, and the caller will use the
// editor's find() function to position on it
bool plaintorich(const string& in, string& out, const list<string>& terms,
string *firstTerm, bool noHeader)
{
Chrono chron;
LOGDEB(("plaintorich: terms: %s\n",
stringlistdisp(terms).c_str()));
out.erase();
// We first use the text splitter to break the text into words,
// and compare the words to the search terms, which yields the
// query terms positions inside the text
myTextSplitCB cb(terms);
TextSplit splitter(&cb, true);
// Note that splitter returns the term locations in byte, not
// character offset
splitter.text_to_words(in);
if (firstTerm)
*firstTerm = cb.firstTerm;
LOGDEB(("plaintorich: split done %d mS\n", chron.millis()));
// Rich text output
if (noHeader)
out = "";
else
out = "<qt><head><title></title></head><body><p>";
// Iterator for the list of input term positions. We use it to
// output highlight tags and to compute term positions in the
// output text
list<pair<int, int> >::iterator tPosIt = cb.tboffs.begin();
// Input character iterator
Utf8Iter chariter(in);
// State variable used to limitate the number of consecutive empty lines
int ateol = 0;
// State variable to update the char pos only for the first of
// consecutive blank chars
int atblank = 0;
for (string::size_type pos = 0; pos != string::npos; pos = chariter++) {
if (pos && (pos % 1000) == 0) {
CancelCheck::instance().checkCancel();
}
// If we still have terms positions, check (byte) position
if (tPosIt != cb.tboffs.end()) {
int ibyteidx = chariter.getBpos();
if (ibyteidx == tPosIt->first) {
out += "<termtag>";
} else if (ibyteidx == tPosIt->second) {
if (tPosIt != cb.tboffs.end())
tPosIt++;
out += "</termtag>";
}
}
switch(*chariter) {
case '\n':
if (ateol < 2) {
out += "<br>\n";
ateol++;
}
break;
case '\r':
break;
case '<':
ateol = 0;
out += "&lt;";
break;
case '&':
ateol = 0;
out += "&amp;";
break;
default:
// We don't change the eol status for whitespace, want a real line
if (*chariter == ' ' || *chariter == '\t') {
atblank = 1;
} else {
ateol = 0;
atblank = 0;
}
chariter.appendchartostring(out);
}
}
#if 0
{
FILE *fp = fopen("/tmp/debugplaintorich", "w");
fprintf(fp, "%s\n", out.c_str());
fclose(fp);
}
#endif
LOGDEB(("plaintorich: done %d mS\n", chron.millis()));
return true;
}