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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797
|
/***************************************************************************
* Copyright (C) 2004-2011 by Thomas Fischer *
* fischer@unix-ag.uni-kl.de *
* *
* 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 <typeinfo>
#include <QTextCodec>
#include <QIODevice>
#include <QRegExp>
#include <QCoreApplication>
#include <QRegExp>
#include <QStringList>
#include <KDebug>
#include <fileinfo.h>
#include <file.h>
#include <comment.h>
#include <macro.h>
#include <preamble.h>
#include <entry.h>
#include <element.h>
#include <encoderlatex.h>
#include <value.h>
#include <bibtexentries.h>
#include <bibtexfields.h>
#include "fileimporterbibtex.h"
const QString extraAlphaNumChars = QString("?'`-_:.+/$\\\"&");
const QRegExp htmlRegExp = QRegExp("</?(a|pre|p|br|span|i|b|italic)\\b[^>]*>", Qt::CaseInsensitive);
FileImporterBibTeX::FileImporterBibTeX(bool ignoreComments, KBibTeX::Casing keywordCasing)
: FileImporter(), m_cancelFlag(false), m_lineNo(1), m_textStream(NULL), m_currentChar(' '), m_ignoreComments(ignoreComments), m_keywordCasing(keywordCasing)
{
// nothing
}
FileImporterBibTeX::~FileImporterBibTeX()
{
}
File* FileImporterBibTeX::load(QIODevice *iodevice)
{
m_cancelFlag = false;
File *result = new File();
m_textStreamLastPos = 0;
m_textStream = new QTextStream(iodevice);
m_textStream->setCodec("us-ascii"); ///< unless we learn something else, assume 7-bit US-ASCII
QString rawText = "";
while (!m_textStream->atEnd()) {
QString line = m_textStream->readLine();
bool skipline = evaluateParameterComments(m_textStream, line.toLower(), result);
if (!skipline)
rawText.append(line).append("\n");
}
delete m_textStream;
/** Remove HTML code from the input source */
rawText = rawText.replace(htmlRegExp, "");
rawText = EncoderLaTeX::currentEncoderLaTeX() ->decode(rawText);
unescapeLaTeXChars(rawText);
m_textStreamLastPos = 0;
m_textStream = new QTextStream(&rawText, QIODevice::ReadOnly);
m_textStream->setCodec("UTF-8");
m_lineNo = 1;
while (!m_cancelFlag && !m_textStream->atEnd()) {
emit progress(m_textStream->pos(), rawText.length());
Element * element = nextElement();
if (element != NULL) {
if (!m_ignoreComments || typeid(*element) != typeid(Comment))
result->append(element);
else
delete element;
}
}
emit progress(100, 100);
if (m_cancelFlag) {
kWarning() << "Loading file has been canceled";
delete result;
result = NULL;
}
delete m_textStream;
return result;
}
bool FileImporterBibTeX::guessCanDecode(const QString & rawText)
{
QString text = EncoderLaTeX::currentEncoderLaTeX()->decode(rawText);
return text.indexOf(QRegExp("@\\w+\\{.+\\}")) >= 0;
}
void FileImporterBibTeX::cancel()
{
m_cancelFlag = TRUE;
}
Element *FileImporterBibTeX::nextElement()
{
Token token = nextToken();
if (token == tAt) {
QString elementType = readSimpleString();
if (elementType.toLower() == "comment")
return readCommentElement();
else if (elementType.toLower() == "string")
return readMacroElement();
else if (elementType.toLower() == "preamble")
return readPreambleElement();
else if (elementType.toLower() == QLatin1String("import")) {
kDebug() << "Skipping potential HTML/JavaScript @import statement";
return NULL;
} else if (!elementType.isEmpty())
return readEntryElement(elementType);
else {
kWarning() << "ElementType is empty";
return NULL;
}
} else if (token == tUnknown) {
kDebug() << "Unknown token \"" << m_currentChar << "(" << m_currentChar.unicode() << ")" << "\" near line " << m_lineNo << ", treating as comment";
return readPlainCommentElement();
}
if (token != tEOF)
kWarning() << "Don't know how to parse next token of type " << tokenidToString(token) << " in line " << m_lineNo << endl;
return NULL;
}
Comment *FileImporterBibTeX::readCommentElement()
{
while (m_currentChar != '{' && m_currentChar != '(' && !m_textStream->atEnd()) {
if (m_currentChar == '\n') ++m_lineNo;
*m_textStream >> m_currentChar;
}
return new Comment(readBracketString(m_currentChar));
}
Comment *FileImporterBibTeX::readPlainCommentElement()
{
QString result = readLine();
if (m_currentChar == '\n') ++m_lineNo;
*m_textStream >> m_currentChar;
while (!m_textStream->atEnd() && m_currentChar != '@' && !m_currentChar.isSpace()) {
result.append('\n').append(m_currentChar);
if (m_currentChar == '\n') ++m_lineNo;
*m_textStream >> m_currentChar;
result.append(readLine());
if (m_currentChar == '\n') ++m_lineNo;
*m_textStream >> m_currentChar;
}
if (result.startsWith(QLatin1String("x-kbibtex"))) {
/// ignore special comments
return NULL;
}
return new Comment(result);
}
Macro *FileImporterBibTeX::readMacroElement()
{
Token token = nextToken();
while (token != tBracketOpen) {
if (token == tEOF) {
kWarning() << "Error in parsing unknown macro' (near line " << m_lineNo << "): Opening curly brace ({) expected";
return NULL;
}
token = nextToken();
}
QString key = readSimpleString();
if (nextToken() != tAssign) {
kError() << "Error in parsing macro '" << key << "'' (near line " << m_lineNo << "): Assign symbol (=) expected";
return NULL;
}
Macro *macro = new Macro(key);
do {
bool isStringKey = false;
QString text = readString(isStringKey).simplified();
if (isStringKey)
macro->value().append(new MacroKey(text));
else
macro->value().append(new PlainText(text));
token = nextToken();
} while (token == tDoublecross);
return macro;
}
Preamble *FileImporterBibTeX::readPreambleElement()
{
Token token = nextToken();
while (token != tBracketOpen) {
if (token == tEOF) {
kWarning() << "Error in parsing unknown preamble' (near line " << m_lineNo << "): Opening curly brace ({) expected";
return NULL;
}
token = nextToken();
}
Preamble *preamble = new Preamble();
do {
bool isStringKey = FALSE;
QString text = readString(isStringKey).simplified();
if (isStringKey)
preamble->value().append(new MacroKey(text));
else
preamble->value().append(new PlainText(text));
token = nextToken();
} while (token == tDoublecross);
return preamble;
}
Entry *FileImporterBibTeX::readEntryElement(const QString& typeString)
{
BibTeXEntries *be = BibTeXEntries::self();
BibTeXFields *bf = BibTeXFields::self();
EncoderLaTeX *encoder = EncoderLaTeX::currentEncoderLaTeX();
Token token = nextToken();
while (token != tBracketOpen) {
if (token == tEOF) {
kWarning() << "Error in parsing unknown entry' (near line " << m_lineNo << "): Opening curly brace ({) expected";
return NULL;
}
token = nextToken();
}
QString id = readSimpleString(',');
/// try to avoid non-ascii characters in ids
encoder->convertToPlainAscii(id);
Entry *entry = new Entry(be->format(typeString, m_keywordCasing), id);
token = nextToken();
do {
if (token == tBracketClose || token == tEOF)
break;
else if (token != tComma) {
if (m_currentChar.isLetter())
kWarning() << "Error in parsing entry '" << id << "' (near line " << m_lineNo << "): Comma symbol (,) expected but got letter " << m_currentChar << " (token " << tokenidToString(token) << ")";
else
kWarning() << "Error in parsing entry '" << id << "' (near line " << m_lineNo << "): Comma symbol (,) expected but got character 0x" << QString::number(m_currentChar.unicode(), 16) << " (token " << tokenidToString(token) << ")";
delete entry;
return NULL;
}
QString keyName = bf->format(readSimpleString(), m_keywordCasing);
/// try to avoid non-ascii characters in keys
encoder->convertToPlainAscii(keyName);
token = nextToken();
if (keyName == QString::null || token == tBracketClose) {
// entry is buggy, but we still accept it
break;
} else if (token != tAssign) {
kError() << "Error in parsing entry '" << id << "'' (near line " << m_lineNo << "): Assign symbol (=) expected after field name '" << keyName << "'";
delete entry;
return NULL;
}
Value value;
/** check for duplicate fields */
if (entry->contains(keyName)) {
if (keyName.toLower() == Entry::ftKeywords || keyName.toLower() == Entry::ftUrl) {
/// special handling of keywords: instead of using fallback names
/// like "keywords2", "keywords3", ..., append new keywords to
/// already existing keyword value
value = entry->value(keyName);
} else {
int i = 2;
QString appendix = QString::number(i);
while (entry->contains(keyName + appendix)) {
++i;
appendix = QString::number(i);
}
kDebug() << "Entry already contains a key " << keyName << "' (near line " << m_lineNo << "), using " << (keyName + appendix);
keyName += appendix;
}
}
token = readValue(value, keyName);
entry->insert(keyName, value);
} while (true);
return entry;
}
FileImporterBibTeX::Token FileImporterBibTeX::nextToken()
{
if (m_textStream->atEnd())
return tEOF;
if (m_textStream->pos() == m_textStreamLastPos)
*m_textStream >> m_currentChar;
Token curToken = tUnknown;
while (!m_textStream->atEnd() && (m_currentChar.isSpace() || m_currentChar == '\t')) {
if (m_currentChar == '\n') ++m_lineNo;
*m_textStream >> m_currentChar;
}
switch (m_currentChar.toAscii()) {
case '@':
curToken = tAt;
break;
case '{':
case '(':
curToken = tBracketOpen;
break;
case '}':
case ')':
curToken = tBracketClose;
break;
case ',':
curToken = tComma;
break;
case '=':
curToken = tAssign;
break;
case '#':
curToken = tDoublecross;
break;
default:
if (m_textStream->atEnd())
curToken = tEOF;
}
if (curToken != tUnknown && curToken != tEOF) {
if (m_currentChar == '\n') ++m_lineNo;
*m_textStream >> m_currentChar;
}
m_textStreamLastPos = m_textStream->pos();
return curToken;
}
QString FileImporterBibTeX::readString(bool &isStringKey)
{
if (m_currentChar.isSpace()) {
m_textStream->skipWhiteSpace();
if (m_currentChar == '\n') ++m_lineNo;
*m_textStream >> m_currentChar;
}
isStringKey = FALSE;
switch (m_currentChar.toAscii()) {
case '{':
case '(':
return readBracketString(m_currentChar);
case '"':
return readQuotedString();
default:
isStringKey = TRUE;
return readSimpleString();
}
}
QString FileImporterBibTeX::readSimpleString(QChar until)
{
QString result;
while (m_currentChar.isSpace()) {
m_textStream->skipWhiteSpace();
if (m_currentChar == '\n') ++m_lineNo;
*m_textStream >> m_currentChar;
}
if (m_currentChar.isLetterOrNumber() || extraAlphaNumChars.contains(m_currentChar)) {
result.append(m_currentChar);
if (m_currentChar == '\n') ++m_lineNo;
*m_textStream >> m_currentChar;
}
while (!m_textStream->atEnd()) {
if (until != '\0') {
if (m_currentChar != until)
result.append(m_currentChar);
else
break;
} else
if (m_currentChar.isLetterOrNumber() || extraAlphaNumChars.contains(m_currentChar))
result.append(m_currentChar);
else
break;
if (m_currentChar == '\n') ++m_lineNo;
*m_textStream >> m_currentChar;
}
return result;
}
QString FileImporterBibTeX::readQuotedString()
{
QString result;
QChar lastChar = m_currentChar;
if (m_currentChar == '\n') ++m_lineNo;
*m_textStream >> m_currentChar;
while (!m_textStream->atEnd()) {
if (m_currentChar != '"' || lastChar == '\\')
result.append(m_currentChar);
else
break;
lastChar = m_currentChar;
if (m_currentChar == '\n') ++m_lineNo;
*m_textStream >> m_currentChar;
}
/** read character after closing " */
if (m_currentChar == '\n') ++m_lineNo;
*m_textStream >> m_currentChar;
return result;
}
QString FileImporterBibTeX::readLine()
{
QString result;
while (!m_textStream->atEnd() && m_currentChar != '\n') {
result.append(m_currentChar);
if (m_currentChar == '\n') ++m_lineNo;
*m_textStream >> m_currentChar;
}
return result;
}
QString FileImporterBibTeX::readBracketString(const QChar openingBracket) ///< do not use reference on QChar here!
{
QString result;
QChar closingBracket = '}';
if (openingBracket == '(')
closingBracket = ')';
int counter = 1;
if (m_currentChar == '\n') ++m_lineNo;
*m_textStream >> m_currentChar;
while (!m_textStream->atEnd()) {
if (m_currentChar == openingBracket)
counter++;
else if (m_currentChar == closingBracket)
counter--;
if (counter == 0)
break;
else
result.append(m_currentChar);
if (m_currentChar == '\n') ++m_lineNo;
*m_textStream >> m_currentChar;
}
if (m_currentChar == '\n') ++m_lineNo;
*m_textStream >> m_currentChar;
return result;
}
FileImporterBibTeX::Token FileImporterBibTeX::readValue(Value& value, const QString& key)
{
Token token = tUnknown;
QString iKey = key.toLower();
do {
bool isStringKey = false;
QString text = readString(isStringKey).simplified();
/// for all entries except for abstracts ...
if (iKey != Entry::ftAbstract) {
/// ... remove redundant spaces including newlines
text = text.simplified();
}
/// abstracts will keep their formatting (regarding line breaks)
/// as requested by Thomas Jensch via mail (20 October 2010)
if (iKey == Entry::ftAuthor || iKey == Entry::ftEditor) {
if (isStringKey)
value.append(new MacroKey(text));
else {
QStringList persons;
/// handle "et al." i.e. "and others"
bool hasOthers = false;
if (text.endsWith(QLatin1String("and others"))) {
hasOthers = true;
text = text.left(text.length() - 10);
}
splitPersonList(text, persons);
for (QStringList::ConstIterator pit = persons.constBegin(); pit != persons.constEnd(); ++pit) {
Person *person = splitName(*pit);
if (person != NULL)
value.append(person);
}
if (hasOthers)
value.append(new PlainText(QLatin1String("others")));
}
} else if (iKey == Entry::ftPages) {
text.replace(QRegExp("\\s*--?\\s*"), QChar(0x2013));
if (isStringKey)
value.append(new MacroKey(text));
else
value.append(new PlainText(text));
} else if ((iKey.startsWith(Entry::ftUrl) && !iKey.startsWith(Entry::ftUrlDate)) || iKey.startsWith(Entry::ftLocalFile) || iKey.compare(QLatin1String("ee"), Qt::CaseInsensitive) == 0 || iKey.compare(QLatin1String("biburl"), Qt::CaseInsensitive) == 0) {
if (isStringKey)
value.append(new MacroKey(text));
else {
/// Assumption: in fields like Url or LocalFile, file names are separated by ; or ,
static const QRegExp semicolonSpace = QRegExp("[;]\\s*");
QStringList fileList = text.split(semicolonSpace, QString::SkipEmptyParts);
foreach(const QString &filename, fileList) {
value.append(new VerbatimText(filename));
}
}
} else if (iKey == Entry::ftMonth) {
if (isStringKey) {
if (QRegExp("^[a-z]{3}", Qt::CaseInsensitive).indexIn(text) == 0)
text = text.left(3).toLower();
value.append(new MacroKey(text));
} else
value.append(new PlainText(text));
} else if (iKey.startsWith(Entry::ftDOI)) {
if (isStringKey)
value.append(new MacroKey(text));
else {
int p = -5;
while ((p = KBibTeX::doiRegExp.indexIn(text, p + 5)) >= 0)
value.append(new VerbatimText(KBibTeX::doiRegExp.cap(0)));
}
} else if (iKey == Entry::ftColor) {
if (isStringKey)
value.append(new MacroKey(text));
else
value.append(new VerbatimText(text));
} else if (iKey == Entry::ftCrossRef) {
if (isStringKey)
value.append(new MacroKey(text));
else
value.append(new VerbatimText(text));
} else if (iKey == Entry::ftKeywords) {
if (isStringKey)
value.append(new MacroKey(text));
else {
QList<Keyword*> keywords = splitKeywords(text);
for (QList<Keyword*>::Iterator it = keywords.begin(); it != keywords.end(); ++it)
value.append(*it);
}
} else {
if (isStringKey)
value.append(new MacroKey(text));
else
value.append(new PlainText(text));
}
token = nextToken();
} while (token == tDoublecross);
return token;
}
void FileImporterBibTeX::unescapeLaTeXChars(QString &text)
{
text.replace("\\&", "&");
}
QList<Keyword*> FileImporterBibTeX::splitKeywords(const QString& text)
{
QList<Keyword*> result;
/// define a list of characters where keywords will be split along
/// finalize list with null character
char splitChars[] = ";,\0";
char *curSplitChar = splitChars;
/// for each char in list ...
while (*curSplitChar != '\0') {
/// check if character is contained in text (should be cheap to test)
if (text.contains(*curSplitChar)) {
/// split text along a pattern like spaces-splitchar-spaces
QRegExp splitAlong(QString("\\s*%1\\s*").arg(*curSplitChar));
/// extract keywords
QStringList keywords = text.split(splitAlong, QString::SkipEmptyParts);
/// build QList of Keyword objects from keywords
foreach(QString keyword, keywords) {
result.append(new Keyword(keyword));
}
/// no more splits neccessary
break;
}
/// no success so far, test next splitting character
++curSplitChar;
}
/// no split was performed, so whole text must be a single keyword
if (result.isEmpty())
result.append(new Keyword(text));
return result;
}
void FileImporterBibTeX::splitPersonList(const QString& text, QStringList &resultList)
{
QStringList wordList;
QString word;
int bracketCounter = 0;
resultList.clear();
for (int pos = 0; pos < text.length(); ++pos) {
if (text[pos] == '{')
++bracketCounter;
else if (text[pos] == '}')
--bracketCounter;
if (text[pos] == ' ' || text[pos] == '\t' || text[pos] == '\n' || text[pos] == '\r') {
if (word == "and" && bracketCounter == 0) {
resultList.append(wordList.join(" "));
wordList.clear();
} else if (!word.isEmpty())
wordList.append(word);
word = "";
} else
word.append(text[pos]);
}
if (!word.isEmpty())
wordList.append(word);
if (!wordList.isEmpty())
resultList.append(wordList.join(" "));
}
Person *FileImporterBibTeX::splitName(const QString& text)
{
QStringList segments;
CommaContainment commaContainment = splitName(text, segments);
QString firstName = "";
QString lastName = "";
if (segments.isEmpty())
return NULL;
if (commaContainment == ccNoComma) {
/** PubMed uses a special writing style for names, where the last name is followed by single capital letter,
* each being the first letter of each first name
* So, check how many single capital letters are at the end of the given segment list */
int singleCapitalLettersCounter = 0;
int p = segments.count() - 1;
while (p >= 0 && segments[p].length() == 1 && segments[p][0].isUpper()) {
--p;
++singleCapitalLettersCounter;
}
if (singleCapitalLettersCounter > 0) {
/** this is a special case for names from PubMed, which are formatted like "Fischer T"
* all segment values until the first single letter segment are last name parts */
for (int i = 0; i < p; ++i)
lastName.append(segments[i]).append(" ");
lastName.append(segments[p]);
/** single letter segments are first name parts */
for (int i = p + 1; i < segments.count() - 1; ++i)
firstName.append(segments[i]).append(" ");
firstName.append(segments[segments.count() - 1]);
} else {
int from = segments.count() - 1;
lastName = segments[from];
/** check for lower case parts of the last name such as "van", "von", "de", ... */
while (from > 0) {
if (segments[from - 1].compare(segments[from - 1].toLower()) != 0)
break;
--from;
lastName.prepend(" ");
lastName.prepend(segments[from]);
}
if (from > 0) {
/** there are segments left for the first name */
firstName = *segments.begin();
for (QStringList::Iterator it = ++segments.begin(); from > 1; ++it, --from) {
firstName.append(" ");
firstName.append(*it);
}
}
}
} else {
bool inLastName = TRUE;
for (int i = 0; i < segments.count(); ++i) {
if (segments[i] == ",")
inLastName = FALSE;
else if (inLastName) {
if (!lastName.isEmpty()) lastName.append(" ");
lastName.append(segments[i]);
} else {
if (!firstName.isEmpty()) firstName.append(" ");
firstName.append(segments[i]);
}
}
}
return new Person(firstName, lastName);
}
/** Splits a name into single words. If the name's text was reversed (Last, First), the result will be true and the comma will be added to segments. Otherwise the functions result will be false. This function respects protecting {...}. */
FileImporterBibTeX::CommaContainment FileImporterBibTeX::splitName(const QString& text, QStringList& segments)
{
int bracketCounter = 0;
CommaContainment result = ccNoComma;
QString buffer = "";
for (int pos = 0; pos < text.length(); ++pos) {
if (text[pos] == '{')
++bracketCounter;
else if (text[pos] == '}')
--bracketCounter;
if (text[pos] == ' ' && bracketCounter == 0) {
if (!buffer.isEmpty()) {
segments.append(buffer);
buffer = "";
}
} else if (text[pos] == ',' && bracketCounter == 0) {
if (!buffer.isEmpty()) {
segments.append(buffer);
buffer = "";
}
segments.append(",");
result = ccContainsComma;
} else
buffer.append(text[pos]);
}
if (!buffer.isEmpty())
segments.append(buffer);
return result;
}
bool FileImporterBibTeX::evaluateParameterComments(QTextStream *textStream, const QString &line, File *file)
{
/** check if this file requests a special encoding */
if (line.startsWith("@comment{x-kbibtex-encoding=") && line.endsWith("}")) {
QString encoding = line.mid(28, line.length() - 29).toLower();
textStream->setCodec(encoding == "latex" ? "UTF-8" : encoding.toAscii());
encoding = textStream->codec()->name();
file->setProperty(File::Encoding, encoding);
return true;
} else if (line.startsWith("@comment{x-kbibtex-personnameformatting=") && line.endsWith("}")) {
QString personNameFormatting = line.mid(40, line.length() - 41);
file->setProperty(File::NameFormatting, personNameFormatting);
return true;
}
return false;
}
QString FileImporterBibTeX::tokenidToString(Token token)
{
switch (token) {
case tAt: return QString("At");
case tBracketClose: return QString("BracketClose");
case tBracketOpen: return QString("BracketOpen");
case tAlphaNumText: return QString("AlphaNumText");
case tAssign: return QString("Assign");
case tComma: return QString("Comma");
case tDoublecross: return QString("Doublecross");
case tEOF: return QString("EOF");
case tUnknown: return QString("Unknown");
default: return QString("<Unknown>");
}
}
|