-
Notifications
You must be signed in to change notification settings - Fork 1.6k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Signed-off-by: Eduardo Silva <[email protected]>
- Loading branch information
Showing
1 changed file
with
103 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,103 @@ | ||
/* -*- Mode: C; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */ | ||
|
||
/* Fluent Bit | ||
* ========== | ||
* Copyright (C) 2015-2017 Treasure Data Inc. | ||
* | ||
* Licensed under the Apache License, Version 2.0 (the "License"); | ||
* you may not use this file except in compliance with the License. | ||
* You may obtain a copy of the License at | ||
* | ||
* https://www.apache.org/licenses/LICENSE-2.0 | ||
* | ||
* Unless required by applicable law or agreed to in writing, software | ||
* distributed under the License is distributed on an "AS IS" BASIS, | ||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
* See the License for the specific language governing permissions and | ||
* limitations under the License. | ||
*/ | ||
|
||
#ifndef FLB_UTF8_H | ||
#define FLB_UTF8_H | ||
|
||
#include <fluent-bit/flb_info.h> | ||
#include <inttypes.h> | ||
|
||
/* is the start of a UTF-8 string ? */ | ||
#define flb_utf8_check(c) (((c) & 0xC0) != 0x80) | ||
|
||
static const char trailingBytesForUTF8[256] = { | ||
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, | ||
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, | ||
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, | ||
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, | ||
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, | ||
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, | ||
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, | ||
2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 | ||
}; | ||
|
||
/* returns length of next utf-8 sequence */ | ||
int flb_utf8_len(char *s) | ||
{ | ||
return trailingBytesForUTF8[(unsigned int)(unsigned char)s[0]] + 1; | ||
} | ||
|
||
/* | ||
* UTF-8 Decoding routines are originally written by Bjoern Hoehrmann | ||
* <[email protected]> and taken from the following web site: | ||
* | ||
* https://bjoern.hoehrmann.de/utf-8/decoder/dfa/ | ||
* | ||
* They have been siglhy renamed to follow Fluent Bit naming requirements. | ||
*/ | ||
|
||
#define FLB_UTF8_ACCEPT 0 | ||
#define FLB_UTF8_REJECT 1 | ||
|
||
static const uint8_t utf8d[] = { | ||
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, // 00..1f | ||
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, // 20..3f | ||
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, // 40..5f | ||
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, // 60..7f | ||
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9, // 80..9f | ||
7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7, // a0..bf | ||
8,8,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, // c0..df | ||
0xa,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x4,0x3,0x3, // e0..ef | ||
0xb,0x6,0x6,0x6,0x5,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8, // f0..ff | ||
0x0,0x1,0x2,0x3,0x5,0x8,0x7,0x1,0x1,0x1,0x4,0x6,0x1,0x1,0x1,0x1, // s0..s0 | ||
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,0,1,1,1,1,1,0,1,0,1,1,1,1,1,1, // s1..s2 | ||
1,2,1,1,1,1,1,2,1,2,1,1,1,1,1,1,1,1,1,1,1,1,1,2,1,1,1,1,1,1,1,1, // s3..s4 | ||
1,2,1,1,1,1,1,1,1,2,1,1,1,1,1,1,1,1,1,1,1,1,1,3,1,3,1,1,1,1,1,1, // s5..s6 | ||
1,3,1,1,1,1,1,3,1,3,1,1,1,1,1,1,1,3,1,1,1,1,1,1,1,1,1,1,1,1,1,1, // s7..s8 | ||
}; | ||
|
||
static inline uint32_t flb_utf8_decode(uint32_t *state, uint32_t *codep, | ||
uint32_t byte) | ||
{ | ||
uint32_t type = utf8d[byte]; | ||
|
||
*codep = (*state != FLB_UTF8_ACCEPT) ? | ||
(byte & 0x3fu) | (*codep << 6) : | ||
(0xff >> type) & (byte); | ||
|
||
*state = utf8d[256 + *state*16 + type]; | ||
return *state; | ||
} | ||
|
||
|
||
void flb_utf8_print(uint8_t *s) { | ||
uint32_t codepoint; | ||
uint32_t state = 0; | ||
|
||
for (; *s; ++s) | ||
if (!flb_utf8_decode(&state, &codepoint, *s)) { | ||
printf("\\u%04x\n", codepoint); | ||
} | ||
|
||
if (state != FLB_UTF8_ACCEPT) { | ||
printf("The string is not well-formed\n"); | ||
} | ||
} | ||
|
||
#endif |