mirror of
https://github.com/LadybirdBrowser/ladybird.git
synced 2024-11-21 23:20:20 +00:00
AK: Put invalid UTF8 debug spam behind a flag
This is very annoying if we're (intentionally) passing invalid UTF8 into Utf8View.
This commit is contained in:
parent
c65a6b6b22
commit
df57536c40
Notes:
sideshowbarker
2024-07-17 11:30:48 +09:00
Author: https://github.com/kleinesfilmroellchen Commit: https://github.com/SerenityOS/serenity/commit/df57536c40 Pull-request: https://github.com/SerenityOS/serenity/pull/13640 Reviewed-by: https://github.com/alimpfard Reviewed-by: https://github.com/gmta Reviewed-by: https://github.com/linusg
3 changed files with 10 additions and 4 deletions
|
@ -462,6 +462,10 @@
|
|||
#cmakedefine01 URL_PARSER_DEBUG
|
||||
#endif
|
||||
|
||||
#ifndef UTF8_DEBUG
|
||||
#cmakedefine01 UTF8_DEBUG
|
||||
#endif
|
||||
|
||||
#ifndef WASM_BINPARSER_DEBUG
|
||||
#cmakedefine01 WASM_BINPARSER_DEBUG
|
||||
#endif
|
||||
|
|
|
@ -7,6 +7,7 @@
|
|||
|
||||
#include <AK/Assertions.h>
|
||||
#include <AK/CharacterTypes.h>
|
||||
#include <AK/Debug.h>
|
||||
#include <AK/Format.h>
|
||||
#include <AK/Utf8View.h>
|
||||
|
||||
|
@ -203,7 +204,7 @@ Utf8CodePointIterator& Utf8CodePointIterator::operator++()
|
|||
if (code_point_length_in_bytes > m_length) {
|
||||
// We don't have enough data for the next code point. Skip one character and try again.
|
||||
// The rest of the code will output replacement characters as needed for any eventual extension bytes we might encounter afterwards.
|
||||
dbgln("Expected code point size {} is too big for the remaining length {}. Moving forward one byte.", code_point_length_in_bytes, m_length);
|
||||
dbgln_if(UTF8_DEBUG, "Expected code point size {} is too big for the remaining length {}. Moving forward one byte.", code_point_length_in_bytes, m_length);
|
||||
m_ptr += 1;
|
||||
m_length -= 1;
|
||||
return *this;
|
||||
|
@ -252,20 +253,20 @@ u32 Utf8CodePointIterator::operator*() const
|
|||
|
||||
if (!first_byte_makes_sense) {
|
||||
// The first byte of the code point doesn't make sense: output a replacement character
|
||||
dbgln("First byte doesn't make sense: {:#02x}.", m_ptr[0]);
|
||||
dbgln_if(UTF8_DEBUG, "First byte doesn't make sense: {:#02x}.", m_ptr[0]);
|
||||
return 0xFFFD;
|
||||
}
|
||||
|
||||
if (code_point_length_in_bytes > m_length) {
|
||||
// There is not enough data left for the full code point: output a replacement character
|
||||
dbgln("Not enough bytes (need {}, have {}), first byte is: {:#02x}.", code_point_length_in_bytes, m_length, m_ptr[0]);
|
||||
dbgln_if(UTF8_DEBUG, "Not enough bytes (need {}, have {}), first byte is: {:#02x}.", code_point_length_in_bytes, m_length, m_ptr[0]);
|
||||
return 0xFFFD;
|
||||
}
|
||||
|
||||
for (size_t offset = 1; offset < code_point_length_in_bytes; offset++) {
|
||||
if (m_ptr[offset] >> 6 != 2) {
|
||||
// One of the extension bytes of the code point doesn't make sense: output a replacement character
|
||||
dbgln("Extension byte {:#02x} in {} position after first byte {:#02x} doesn't make sense.", m_ptr[offset], offset, m_ptr[0]);
|
||||
dbgln_if(UTF8_DEBUG, "Extension byte {:#02x} in {} position after first byte {:#02x} doesn't make sense.", m_ptr[offset], offset, m_ptr[0]);
|
||||
return 0xFFFD;
|
||||
}
|
||||
|
||||
|
|
|
@ -195,6 +195,7 @@ set(UHCI_VERBOSE_DEBUG ON)
|
|||
set(UPDATE_COALESCING_DEBUG ON)
|
||||
set(URL_PARSER_DEBUG ON)
|
||||
set(USB_DEBUG ON)
|
||||
set(UTF8_DEBUG ON)
|
||||
set(VFS_DEBUG ON)
|
||||
set(VIRTIO_DEBUG ON)
|
||||
set(VIRTUAL_CONSOLE_DEBUG ON)
|
||||
|
|
Loading…
Reference in a new issue