happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge commit '4ae1b7517a787f5b37776b0598ed2b69e6caf5bd' into hotfix/validate-filepath 

# Conflicts:
#	common/common.cpp
This commit is contained in:
Jan Boon 2026-02-12 07:47:58 +00:00
parent 2dfa2edf48 4ae1b7517a
commit df63ccc3dc
1 changed files with 23 additions and 41 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

64
common/common.cpp
View File

@ -1,7 +1,3 @@
#if defined(_MSC_VER)
#define _SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING
#endif
#include "ggml.h"
#include "gguf.h"
@ -9,12 +5,12 @@
#include "log.h"
#include "llama.h"
#include "sampling.h"
#include "unicode.h"
#include <algorithm>
#include <cinttypes>
#include <climits>
#include <cmath>
#include <codecvt>
#include <chrono>
#include <cstdarg>
#include <cstring>
@ -748,46 +744,30 @@ bool fs_validate_filename(const std::string & filename, bool allow_subdirs) {
return false;
}
std::u32string filename_utf32;
try {
#if defined(__clang__)
// disable C++17 deprecation warning for std::codecvt_utf8
# pragma clang diagnostic push
# pragma clang diagnostic ignored "-Wdeprecated-declarations"
#elif defined(__GNUC__)
# pragma GCC diagnostic push
# pragma GCC diagnostic ignored "-Wdeprecated-declarations"
#endif
uint32_t prev = 0;
size_t offset = 0;
while (offset < filename.size()) {
utf8_parse_result result = parse_utf8_codepoint(filename, offset);
std::wstring_convert<std::codecvt_utf8<char32_t>, char32_t> converter;
#if defined(__clang__)
# pragma clang diagnostic pop
#elif defined(__GNUC__)
# pragma GCC diagnostic pop
#endif
filename_utf32 = converter.from_bytes(filename);
// If the reverse conversion mismatches, it means overlong UTF-8 sequences were used,
// or invalid encodings were encountered. Reject such attempts
std::string filename_reencoded = converter.to_bytes(filename_utf32);
if (filename_reencoded != filename) {
if (result.status != utf8_parse_result::SUCCESS) {
return false;
}
} catch (const std::exception &) {
return false;
}
uint32_t c = result.codepoint;
// Check for forbidden codepoints:
// - Control characters
// - Unicode equivalents of path traversal characters
// - UTF-16 surrogate pairs
// - UTF-8 replacement character
// - Byte order mark (BOM)
// - Illegal characters: / \ : * ? " < > |
char32_t prev = 0;
for (char32_t c : filename_utf32) {
// Check for overlong UTF-8 sequences
if ((result.bytes_consumed == 2 && c < 0x80) ||
(result.bytes_consumed == 3 && c < 0x800) ||
(result.bytes_consumed == 4 && c < 0x10000)) {
return false;
}
// Check for forbidden codepoints:
// - Control characters
// - Unicode equivalents of path traversal characters
// - UTF-16 surrogate pairs
// - UTF-8 replacement character
// - Byte order mark (BOM)
// - Illegal characters: / \ : * ? " < > |
if (c <= 0x1F // Control characters (C0)
|| c == 0x7F // Control characters (DEL)
|| (c >= 0x80 && c <= 0x9F) // Control characters (C1)
@ -804,6 +784,7 @@ bool fs_validate_filename(const std::string & filename, bool allow_subdirs) {
|| c == 0x20A9 // Won Sign (backslash equivalent, CP 949, 1361 Korean)
|| c == 0x00B4 // Acute Accent (forward slash equivalent, CP 1253 Greek)
|| (c >= 0xD800 && c <= 0xDFFF) // UTF-16 surrogate pairs
|| c > 0x10FFFF // Max Unicode limit
|| c == 0xFFFD // Replacement Character (UTF-8)
|| c == 0xFEFF // Byte Order Mark (BOM)
|| c == ':' || c == '*' // Illegal characters
@ -825,6 +806,7 @@ bool fs_validate_filename(const std::string & filename, bool allow_subdirs) {
return false;
}
prev = c;
offset += result.bytes_consumed;
}
// Reject any leading or trailing ' ', or any trailing '.', these are stripped on Windows and will cause a different filename