1berry/nodejs
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

src: remove explicit UTF-8 validity check in url

Browse Source 
This step was never part of the URL Standard's host parser algorithm,
and is rendered unnecessary after IDNA errors are no longer ignored.

PR-URL: https://github.com/nodejs/node/pull/11859
Refs: c2a302c50b3787666339371 "src: do not ignore IDNA conversion error"
Refs: https://url.spec.whatwg.org/#concept-host-parser
Reviewed-By: Ben Noordhuis <info@bnoordhuis.nl>
Reviewed-By: Daijiro Wachi <daijiro.wachi@gmail.com>
Reviewed-By: Anna Henningsen <anna@addaleax.net>
Reviewed-By: James M Snell <jasnell@gmail.com>
Reviewed-By: Colin Ihrig <cjihrig@gmail.com>
This commit is contained in:
Timothy Gu 2017-03-14 23:41:57 -07:00
parent 4cdb0e89d8
commit d099f8e317
1 changed files with 0 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
src/node_url.cc
View File

@ -15,11 +15,6 @@
#include <stdio.h>
#include <cmath>
#if defined(NODE_HAVE_I18N_SUPPORT)
#include <unicode/utf8.h>
#include <unicode/utf.h>
#endif
#define UNICODE_REPLACEMENT_CHARACTER 0xFFFD
namespace node {
@ -113,21 +108,6 @@ namespace url {
output->assign(*buf, buf.length());
return true;
}
// Unfortunately there's not really a better way to do this.
// Iterate through each encoded codepoint and verify that
// it is a valid unicode codepoint.
static bool IsValidUTF8(std::string* input) {
const char* p = input->c_str();
int32_t len = input->length();
for (int32_t i = 0; i < len;) {
UChar32 c;
U8_NEXT_UNSAFE(p, i, c);
if (!U_IS_UNICODE_CHAR(c))
return false;
}
return true;
}
#else
// Intentional non-ops if ICU is not present.
static bool ToUnicode(std::string* input, std::string* output) {
@ -139,10 +119,6 @@ namespace url {
*output = *input;
return true;
}
static bool IsValidUTF8(std::string* input) {
return true;
}
#endif
// If a UTF-16 character is a low/trailing surrogate.
@ -395,12 +371,6 @@ namespace url {
if (PercentDecode(input, length, &decoded) < 0)
goto end;
// If there are any invalid UTF8 byte sequences, we have to fail.
// Unfortunately this means iterating through the string and checking
// each decoded codepoint.
if (!IsValidUTF8(&decoded))
goto end;
// Then we have to punycode toASCII
if (!ToASCII(&decoded, &decoded))
goto end;