diff options
author | Michele Calgaro <[email protected]> | 2024-05-11 21:28:48 +0900 |
---|---|---|
committer | Michele Calgaro <[email protected]> | 2024-05-11 21:28:48 +0900 |
commit | 2462d03f322261bd616721c2b2065c4004b36c9c (patch) | |
tree | 239947a0737bb8386703a1497f12c09aebd3080a /fbreader/src/formats/html/HtmlDescriptionReader.cpp | |
download | tde-ebook-reader-2462d03f322261bd616721c2b2065c4004b36c9c.tar.gz tde-ebook-reader-2462d03f322261bd616721c2b2065c4004b36c9c.zip |
Initial import (as is) from Debian Snapshot's 'fbreader' source code (https://snapshot.debian.org/package/fbreader/0.99.4%2Bdfsg-6).
The Debian code is provided under GPL2 license.
Signed-off-by: Michele Calgaro <[email protected]>
Diffstat (limited to 'fbreader/src/formats/html/HtmlDescriptionReader.cpp')
-rw-r--r-- | fbreader/src/formats/html/HtmlDescriptionReader.cpp | 82 |
1 files changed, 82 insertions, 0 deletions
diff --git a/fbreader/src/formats/html/HtmlDescriptionReader.cpp b/fbreader/src/formats/html/HtmlDescriptionReader.cpp new file mode 100644 index 0000000..6ebcb8b --- /dev/null +++ b/fbreader/src/formats/html/HtmlDescriptionReader.cpp @@ -0,0 +1,82 @@ +/* + * Copyright (C) 2004-2012 Geometer Plus <[email protected]> + * + * 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 "HtmlDescriptionReader.h" + +#include "../../library/Book.h" + +HtmlDescriptionReader::HtmlDescriptionReader(Book &book) : HtmlReader(book.encoding()), myBook(book) { + myBook.setTitle(""); +} + +void HtmlDescriptionReader::startDocumentHandler() { + myReadTitle = false; +} + +void HtmlDescriptionReader::endDocumentHandler() { + if (!myBook.title().empty()) { + const char *titleStart = myBook.title().data(); + const char *titleEnd = titleStart + myBook.title().length(); + std::string newTitle; + myConverter->convert(newTitle, titleStart, titleEnd); + myBook.setTitle(newTitle); + } +} + +bool HtmlDescriptionReader::tagHandler(const HtmlTag &tag) { + if (tag.Name == "TITLE") { + if (myReadTitle && !tag.Start) { + myBook.setTitle(myBuffer); + myBuffer.erase(); + } + myReadTitle = tag.Start && myBook.title().empty(); + return true; + } else if (tag.Start && tag.Name == "META") { + std::vector<HtmlAttribute>::const_iterator it = tag.Attributes.begin(); + for (; it != tag.Attributes.end(); ++it) { + if (it->Name == "CONTENT") { + break; + } + } + if (it != tag.Attributes.end()) { + const std::string prefix = "charset="; + std::size_t index = it->Value.find(prefix); + if (index != std::string::npos) { + std::string charset = it->Value.substr(index + prefix.length()); + index = charset.find(';'); + if (index != std::string::npos) { + charset = charset.substr(0, index); + } + index = charset.find(' '); + if (index != std::string::npos) { + charset = charset.substr(0, index); + } + myBook.setEncoding(charset); + } + } + } + return tag.Name != "BODY"; +} + +bool HtmlDescriptionReader::characterDataHandler(const char *text, std::size_t len, bool) { + if (myReadTitle) { + myBuffer.append(text, len); + } + return true; +} |