Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(10)

Unified Diff: third_party/brotli/enc/utf8_util.cc

Issue 2537133002: Update brotli to v1.0.0-snapshot. (Closed)
Patch Set: Fixed typo Created 4 years ago
Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.
Jump to:
View side-by-side diff with in-line comments
Download patch
« no previous file with comments | « third_party/brotli/enc/utf8_util.c ('k') | third_party/brotli/enc/write_bits.h » ('j') | no next file with comments »
Expand Comments ('e') | Collapse Comments ('c') | Show Comments Hide Comments ('s')
Index: third_party/brotli/enc/utf8_util.cc
diff --git a/third_party/brotli/enc/utf8_util.cc b/third_party/brotli/enc/utf8_util.cc
deleted file mode 100644
index a2b5c3a6776477af0b1132667fb8d6b05e4ccee6..0000000000000000000000000000000000000000
--- a/third_party/brotli/enc/utf8_util.cc
+++ /dev/null
@@ -1,83 +0,0 @@
-/* Copyright 2013 Google Inc. All Rights Reserved.
-
- Distributed under MIT license.
- See file LICENSE for detail or copy at https://opensource.org/licenses/MIT
-*/
-
-// Heuristics for deciding about the UTF8-ness of strings.
-
-#include "./utf8_util.h"
-
-#include "./types.h"
-
-namespace brotli {
-
-namespace {
-
-size_t ParseAsUTF8(int* symbol, const uint8_t* input, size_t size) {
- // ASCII
- if ((input[0] & 0x80) == 0) {
- *symbol = input[0];
- if (*symbol > 0) {
- return 1;
- }
- }
- // 2-byte UTF8
- if (size > 1u &&
- (input[0] & 0xe0) == 0xc0 &&
- (input[1] & 0xc0) == 0x80) {
- *symbol = (((input[0] & 0x1f) << 6) |
- (input[1] & 0x3f));
- if (*symbol > 0x7f) {
- return 2;
- }
- }
- // 3-byte UFT8
- if (size > 2u &&
- (input[0] & 0xf0) == 0xe0 &&
- (input[1] & 0xc0) == 0x80 &&
- (input[2] & 0xc0) == 0x80) {
- *symbol = (((input[0] & 0x0f) << 12) |
- ((input[1] & 0x3f) << 6) |
- (input[2] & 0x3f));
- if (*symbol > 0x7ff) {
- return 3;
- }
- }
- // 4-byte UFT8
- if (size > 3u &&
- (input[0] & 0xf8) == 0xf0 &&
- (input[1] & 0xc0) == 0x80 &&
- (input[2] & 0xc0) == 0x80 &&
- (input[3] & 0xc0) == 0x80) {
- *symbol = (((input[0] & 0x07) << 18) |
- ((input[1] & 0x3f) << 12) |
- ((input[2] & 0x3f) << 6) |
- (input[3] & 0x3f));
- if (*symbol > 0xffff && *symbol <= 0x10ffff) {
- return 4;
- }
- }
- // Not UTF8, emit a special symbol above the UTF8-code space
- *symbol = 0x110000 | input[0];
- return 1;
-}
-
-} // namespace
-
-// Returns true if at least min_fraction of the data is UTF8-encoded.
-bool IsMostlyUTF8(const uint8_t* data, const size_t pos, const size_t mask,
- const size_t length, const double min_fraction) {
- size_t size_utf8 = 0;
- size_t i = 0;
- while (i < length) {
- int symbol;
- size_t bytes_read = ParseAsUTF8(
- &symbol, &data[(pos + i) & mask], length - i);
- i += bytes_read;
- if (symbol < 0x110000) size_utf8 += bytes_read;
- }
- return size_utf8 > min_fraction * static_cast<double>(length);
-}
-
-} // namespace brotli
« no previous file with comments | « third_party/brotli/enc/utf8_util.c ('k') | third_party/brotli/enc/write_bits.h » ('j') | no next file with comments »

Powered by Google App Engine
This is Rietveld 408576698