mirrors/ladybird
0
0
Fork 0
mirror of https://github.com/LadybirdBrowser/ladybird.git synced 2025-05-01 08:48:49 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 9

LibTextCodec: Start fleshing out a simple text codec library

Browse source 
We're starting with a very basic decoding API and only ISO-8859-1 and
UTF-8 decoding (and UTF-8 decoding is really a no-op since String is
expected to be UTF-8.)
This commit is contained in:
Andreas Kling 2020-05-03 22:41:34 +02:00
parent f3676ebef5
commit e09b83c60c
Notes: sideshowbarker 2024-07-19 07:00:24 +09:00
10 changed files with 148 additions and 21 deletions
Download patch file Download diff file Expand all files Collapse all files

19
Libraries/LibWeb/Parser/HTMLParser.cpp
View file

@ -27,6 +27,7 @@
#include <AK/Function.h>
#include <AK/NonnullRefPtrVector.h>
#include <AK/StringBuilder.h>
#include <LibTextCodec/Decoder.h>
#include <LibWeb/DOM/Comment.h>
#include <LibWeb/DOM/DocumentFragment.h>
#include <LibWeb/DOM/DocumentType.h>
@ -385,21 +386,9 @@ static bool parse_html_document(const StringView& html, Document& document, Pare
String to_utf8(const StringView& input, const String& encoding)
{
String output;
if (encoding == "utf-8") {
output = input;
} else if (encoding == "iso-8859-1") {
StringBuilder builder(input.length());
for (size_t i = 0; i < input.length(); ++i) {
u8 ch = input[i];
builder.append(ch >= 0x80 ? '?' : ch);
}
output = builder.to_string();
} else {
dbg() << "Unknown encoding " << encoding;
ASSERT_NOT_REACHED();
}
return output;
auto* decoder = TextCodec::decoder_for(encoding);
ASSERT(decoder);
return decoder->to_utf8(input);
}
RefPtr<DocumentFragment> parse_html_fragment(Document& document, const StringView& raw_html, const String& encoding)