Parent: [beebb1] (diff)

Download this file

reslistpager.cpp    532 lines (469 with data), 15.5 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
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
516
517
518
519
520
521
522
523
524
525
526
527
528
529
/* Copyright (C) 2007 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.,
* 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
*/
#ifdef HAVE_CONFIG_H
#include "autoconfig.h"
#endif
#include <stdio.h>
#include <stdlib.h>
#include <math.h>
#include <time.h>
#include <stdint.h>
#include <sstream>
#include <iostream>
#include <list>
using std::ostringstream;
using std::endl;
using std::list;
#include "cstr.h"
#include "reslistpager.h"
#include "log.h"
#include "rclconfig.h"
#include "smallut.h"
#include "rclutil.h"
#include "plaintorich.h"
#include "mimehandler.h"
#include "transcode.h"
// Default highlighter. No need for locking, this is query-only.
static const string cstr_hlfontcolor("<span style='color: blue;'>");
static const string cstr_hlendfont("</span>");
class PlainToRichHtReslist : public PlainToRich {
public:
virtual string startMatch(unsigned int)
{
return cstr_hlfontcolor;
}
virtual string endMatch()
{
return cstr_hlendfont;
}
};
static PlainToRichHtReslist g_hiliter;
ResListPager::ResListPager(int pagesize)
: m_pagesize(pagesize),
m_newpagesize(pagesize),
m_resultsInCurrentPage(0),
m_winfirst(-1),
m_hasNext(true),
m_hiliter(&g_hiliter)
{
}
void ResListPager::resultPageNext()
{
if (!m_docSource) {
LOGDEB("ResListPager::resultPageNext: null source\n");
return;
}
int resCnt = m_docSource->getResCnt();
LOGDEB("ResListPager::resultPageNext: rescnt " << resCnt <<
", winfirst " << m_winfirst << "\n");
if (m_winfirst < 0) {
m_winfirst = 0;
} else {
m_winfirst += int(m_respage.size());
}
// Get the next page of results. Note that we look ahead by one to
// determine if there is actually a next page
vector<ResListEntry> npage;
int pagelen = m_docSource->getSeqSlice(m_winfirst, m_pagesize + 1, npage);
// If page was truncated, there is no next
m_hasNext = (pagelen == m_pagesize + 1);
// Get rid of the possible excess result
if (pagelen == m_pagesize + 1) {
npage.resize(m_pagesize);
pagelen--;
}
if (pagelen <= 0) {
// No results ? This can only happen on the first page or if the
// actual result list size is a multiple of the page pref (else
// there would have been no Next on the last page)
if (m_winfirst > 0) {
// Have already results. Let them show, just disable the
// Next button. We'd need to remove the Next link from the page
// too.
// Restore the m_winfirst value, let the current result vector alone
m_winfirst -= int(m_respage.size());
} else {
// No results at all (on first page)
m_winfirst = -1;
}
return;
}
m_resultsInCurrentPage = pagelen;
m_respage = npage;
}
static string maybeEscapeHtml(const string& fld)
{
if (fld.compare(0, cstr_fldhtm.size(), cstr_fldhtm))
return escapeHtml(fld);
else
return fld.substr(cstr_fldhtm.size());
}
void ResListPager::resultPageFor(int docnum)
{
if (!m_docSource) {
LOGDEB("ResListPager::resultPageFor: null source\n");
return;
}
int resCnt = m_docSource->getResCnt();
LOGDEB("ResListPager::resultPageFor(" << docnum << "): rescnt " <<
resCnt << ", winfirst " << m_winfirst << "\n");
m_winfirst = (docnum / m_pagesize) * m_pagesize;
// Get the next page of results.
vector<ResListEntry> npage;
int pagelen = m_docSource->getSeqSlice(m_winfirst, m_pagesize, npage);
// If page was truncated, there is no next
m_hasNext = (pagelen == m_pagesize);
if (pagelen <= 0) {
m_winfirst = -1;
return;
}
m_respage = npage;
}
void ResListPager::displayDoc(RclConfig *config, int i, Rcl::Doc& doc,
const HighlightData& hdata, const string& sh)
{
ostringstream chunk;
// Determine icon to display if any
string iconurl = iconUrl(config, doc);
// Printable url: either utf-8 if transcoding succeeds, or url-encoded
string url;
printableUrl(config->getDefCharset(), doc.url, url);
// Same as url, but with file:// possibly stripped. output by %u instead
// of %U.
string urlOrLocal;
urlOrLocal = fileurltolocalpath(url);
if (urlOrLocal.empty())
urlOrLocal = url;
// Make title out of file name if none yet
string titleOrFilename;
string utf8fn;
doc.getmeta(Rcl::Doc::keytt, &titleOrFilename);
doc.getmeta(Rcl::Doc::keyfn, &utf8fn);
if (utf8fn.empty()) {
utf8fn = path_getsimple(url);
}
if (titleOrFilename.empty()) {
titleOrFilename = utf8fn;
}
// Url for the parent directory. We strip the file:// part for local
// paths
string parenturl = url_parentfolder(url);
{
string localpath = fileurltolocalpath(parenturl);
if (!localpath.empty())
parenturl = localpath;
}
// Result number
char numbuf[20];
int docnumforlinks = m_winfirst + 1 + i;
sprintf(numbuf, "%d", docnumforlinks);
// Document date: either doc or file modification times
string datebuf;
if (!doc.dmtime.empty() || !doc.fmtime.empty()) {
char cdate[100];
cdate[0] = 0;
time_t mtime = doc.dmtime.empty() ?
atoll(doc.fmtime.c_str()) : atoll(doc.dmtime.c_str());
struct tm *tm = localtime(&mtime);
strftime(cdate, 99, dateFormat().c_str(), tm);
transcode(cdate, datebuf, RclConfig::getLocaleCharset(), "UTF-8");
}
// Size information. We print both doc and file if they differ a lot
int64_t fsize = -1, dsize = -1;
if (!doc.dbytes.empty())
dsize = static_cast<int64_t>(atoll(doc.dbytes.c_str()));
if (!doc.fbytes.empty())
fsize = static_cast<int64_t>(atoll(doc.fbytes.c_str()));
string sizebuf;
if (dsize > 0) {
sizebuf = displayableBytes(dsize);
if (fsize > 10 * dsize && fsize - dsize > 1000)
sizebuf += string(" / ") + displayableBytes(fsize);
} else if (fsize >= 0) {
sizebuf = displayableBytes(fsize);
}
string richabst;
bool needabstract = parFormat().find("%A") != string::npos;
if (needabstract && m_docSource) {
vector<string> vabs;
m_docSource->getAbstract(doc, vabs);
m_hiliter->set_inputhtml(false);
for (vector<string>::const_iterator it = vabs.begin();
it != vabs.end(); it++) {
if (!it->empty()) {
// No need to call escapeHtml(), plaintorich handles it
list<string> lr;
// There may be data like page numbers before the snippet text.
// will be in brackets.
string::size_type bckt = it->find("]");
if (bckt == string::npos) {
m_hiliter->plaintorich(*it, lr, hdata);
} else {
m_hiliter->plaintorich(it->substr(bckt), lr, hdata);
lr.front() = it->substr(0, bckt) + lr.front();
}
richabst += lr.front();
richabst += absSep();
}
}
}
// Links;
ostringstream linksbuf;
if (canIntern(doc.mimetype, config)) {
linksbuf << "<a href=\""<< linkPrefix()<< "P" << docnumforlinks << "\">"
<< trans("Preview") << "</a>&nbsp;&nbsp;";
}
string apptag;
doc.getmeta(Rcl::Doc::keyapptg, &apptag);
if (!config->getMimeViewerDef(doc.mimetype, apptag, false).empty()) {
linksbuf << "<a href=\"" <<linkPrefix() + "E" <<docnumforlinks << "\">"
<< trans("Open") << "</a>";
}
ostringstream snipsbuf;
if (doc.haspages) {
snipsbuf << "<a href=\"" <<linkPrefix()<<"A" << docnumforlinks << "\">"
<< trans("Snippets") << "</a>&nbsp;&nbsp;";
linksbuf << "&nbsp;&nbsp;" << snipsbuf.str();
}
string collapscnt;
if (doc.getmeta(Rcl::Doc::keycc, &collapscnt) && !collapscnt.empty()) {
ostringstream collpsbuf;
int clc = atoi(collapscnt.c_str()) + 1;
collpsbuf << "<a href=\""<<linkPrefix()<<"D" << docnumforlinks << "\">"
<< trans("Dups") << "(" << clc << ")" << "</a>&nbsp;&nbsp;";
linksbuf << "&nbsp;&nbsp;" << collpsbuf.str();
}
// Build the result list paragraph:
// Subheader: this is used by history
if (!sh.empty())
chunk << "<p style='clear: both;'><b>" << sh << "</p>\n<p>";
else
chunk << "<p style='margin: 0px;padding: 0px;clear: both;'>";
char xdocidbuf[100];
sprintf(xdocidbuf, "%lu", doc.xdocid);
// Configurable stuff
map<string, string> subs;
subs["A"] = !richabst.empty() ? richabst : "";
subs["D"] = datebuf;
subs["E"] = snipsbuf.str();
subs["I"] = iconurl;
subs["i"] = doc.ipath;
subs["K"] = !doc.meta[Rcl::Doc::keykw].empty() ?
string("[") + maybeEscapeHtml(doc.meta[Rcl::Doc::keykw]) + "]" : "";
subs["L"] = linksbuf.str();
subs["N"] = numbuf;
subs["M"] = doc.mimetype;
subs["P"] = parenturl;
subs["R"] = doc.meta[Rcl::Doc::keyrr];
subs["S"] = sizebuf;
subs["T"] = maybeEscapeHtml(titleOrFilename);
subs["t"] = maybeEscapeHtml(doc.meta[Rcl::Doc::keytt]);
subs["U"] = url;
subs["u"] = urlOrLocal;
subs["x"] = xdocidbuf;
// Let %(xx) access all metadata. HTML-neuter everything:
for (map<string,string>::iterator it = doc.meta.begin();
it != doc.meta.end(); it++) {
if (!it->first.empty())
subs[it->first] = maybeEscapeHtml(it->second);
}
string formatted;
pcSubst(parFormat(), formatted, subs);
chunk << formatted;
chunk << "</p>" << endl;
// This was to force qt 4.x to clear the margins (which it should do
// anyway because of the paragraph's style), but we finally took
// the table approach for 1.15 for now (in guiutils.cpp)
// chunk << "<br style='clear:both;height:0;line-height:0;'>" << endl;
LOGDEB2("Chunk: [" << chunk.rdbuf()->str() << "]\n");
append(chunk.rdbuf()->str(), i, doc);
}
bool ResListPager::getDoc(int num, Rcl::Doc& doc)
{
if (m_winfirst < 0 || m_respage.size() == 0)
return false;
if (num < m_winfirst || num >= m_winfirst + int(m_respage.size()))
return false;
doc = m_respage[num-m_winfirst].doc;
return true;
}
void ResListPager::displayPage(RclConfig *config)
{
LOGDEB("ResListPager::displayPage. linkPrefix: " << linkPrefix() << "\n");
if (!m_docSource) {
LOGDEB("ResListPager::displayPage: null source\n");
return;
}
if (m_winfirst < 0 && !pageEmpty()) {
LOGDEB("ResListPager::displayPage: sequence error: winfirst < 0\n");
return;
}
ostringstream chunk;
// Display list header
// We could use a <title> but the textedit doesnt display
// it prominently
// Note: have to append text in chunks that make sense
// html-wise. If we break things up too much, the editor
// gets confused. Hence the use of the 'chunk' text
// accumulator
// Also note that there can be results beyond the estimated resCnt.
chunk << "<html><head>" << endl
<< "<meta http-equiv=\"content-type\""
<< " content=\"text/html; charset=utf-8\">" << endl
<< headerContent()
<< "</head><body>" << endl
<< pageTop()
<< "<p><span style=\"font-size:110%;\"><b>"
<< m_docSource->title()
<< "</b></span>&nbsp;&nbsp;&nbsp;";
if (pageEmpty()) {
chunk << trans("<p><b>No results found</b><br>");
string reason = m_docSource->getReason();
if (!reason.empty()) {
chunk << "<blockquote>" << escapeHtml(reason) <<
"</blockquote></p>";
} else {
HighlightData hldata;
m_docSource->getTerms(hldata);
vector<string> uterms(hldata.uterms.begin(), hldata.uterms.end());
if (!uterms.empty()) {
map<string, vector<string> > spellings;
suggest(uterms, spellings);
if (!spellings.empty()) {
if (o_index_stripchars) {
chunk <<
trans("<p><i>Alternate spellings (accents suppressed): </i>")
<< "<br /><blockquote>";
} else {
chunk <<
trans("<p><i>Alternate spellings: </i>")
<< "<br /><blockquote>";
}
for (const auto& entry: spellings) {
chunk << "<b>" << entry.first << "</b> : ";
for (const auto& spelling : entry.second) {
chunk << spelling << " ";
}
chunk << "<br />";
}
chunk << "</blockquote></p>";
}
}
}
} else {
unsigned int resCnt = m_docSource->getResCnt();
if (m_winfirst + m_respage.size() < resCnt) {
chunk << trans("Documents") << " <b>" << m_winfirst + 1
<< "-" << m_winfirst + m_respage.size() << "</b> "
<< trans("out of at least") << " "
<< resCnt << " " << trans("for") << " " ;
} else {
chunk << trans("Documents") << " <b>"
<< m_winfirst + 1 << "-" << m_winfirst + m_respage.size()
<< "</b> " << trans("for") << " ";
}
}
chunk << detailsLink();
if (hasPrev() || hasNext()) {
chunk << "&nbsp;&nbsp;";
if (hasPrev()) {
chunk << "<a href=\"" << linkPrefix() + prevUrl() + "\"><b>"
<< trans("Previous")
<< "</b></a>&nbsp;&nbsp;&nbsp;";
}
if (hasNext()) {
chunk << "<a href=\"" << linkPrefix() + nextUrl() + "\"><b>"
<< trans("Next")
<< "</b></a>";
}
}
chunk << "</p>" << endl;
append(chunk.rdbuf()->str());
chunk.rdbuf()->str("");
if (pageEmpty())
return;
HighlightData hdata;
m_docSource->getTerms(hdata);
// Emit data for result entry paragraph. Do it in chunks that make sense
// html-wise, else our client may get confused
for (int i = 0; i < (int)m_respage.size(); i++) {
Rcl::Doc& doc(m_respage[i].doc);
string& sh(m_respage[i].subHeader);
displayDoc(config, i, doc, hdata, sh);
}
// Footer
chunk << "<p align=\"center\">";
if (hasPrev() || hasNext()) {
if (hasPrev()) {
chunk << "<a href=\"" + linkPrefix() + prevUrl() + "\"><b>"
<< trans("Previous")
<< "</b></a>&nbsp;&nbsp;&nbsp;";
}
if (hasNext()) {
chunk << "<a href=\"" << linkPrefix() + nextUrl() + "\"><b>"
<< trans("Next")
<< "</b></a>";
}
}
chunk << "</p>" << endl;
chunk << "</body></html>" << endl;
append(chunk.rdbuf()->str());
}
// Default implementations for things that should be implemented by
// specializations
string ResListPager::nextUrl()
{
return "n-1";
}
string ResListPager::prevUrl()
{
return "p-1";
}
string ResListPager::iconUrl(RclConfig *config, Rcl::Doc& doc)
{
string apptag;
doc.getmeta(Rcl::Doc::keyapptg, &apptag);
return path_pathtofileurl(config->getMimeIconPath(doc.mimetype, apptag));
}
bool ResListPager::append(const string& data)
{
fprintf(stderr, "%s", data.c_str());
return true;
}
string ResListPager::trans(const string& in)
{
return in;
}
string ResListPager::detailsLink()
{
string chunk = string("<a href=\"") + linkPrefix() + "H-1\">";
chunk += trans("(show query)") + "</a>";
return chunk;
}
const string &ResListPager::parFormat()
{
static const string cstr_format("<img src=\"%I\" align=\"left\">"
"%R %S %L &nbsp;&nbsp;<b>%T</b><br>"
"%M&nbsp;%D&nbsp;&nbsp;&nbsp;<i>%U</i><br>"
"%A %K");
return cstr_format;
}
const string &ResListPager::dateFormat()
{
static const string cstr_format("&nbsp;%Y-%m-%d&nbsp;%H:%M:%S&nbsp;%z");
return cstr_format;
}