Removing unused utf8 C validators.

This commit is contained in:
Thomas Hintz 2014-10-18 10:07:53 -07:00
parent 91396e71e0
commit 195d55732d
4 changed files with 0 additions and 166 deletions

View File

@ -1,56 +0,0 @@
// Copyright (c) 2008-2009 Bjoern Hoehrmann <bjoern@hoehrmann.de>
// See http://bjoern.hoehrmann.de/utf-8/decoder/dfa/ for details.
#include "utf8decode.h"
#define UTF8_ACCEPT 0
#define 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 uint32_t inline
decode(uint32_t* state, uint32_t* codep, uint32_t byte) {
uint32_t type = utf8d[byte];
*codep = (*state != UTF8_ACCEPT) ?
(byte & 0x3fu) | (*codep << 6) :
(0xff >> type) & (byte);
*state = utf8d[256 + *state*16 + type];
return *state;
}
int
countCodePoints(uint8_t* s, size_t len) {
uint32_t codepoint;
uint32_t state = 0;
size_t count = 0;
// for (count = 0; *s; ++s)
for (int i = len; i != 0; --i) {
//if (!decode(&state, &codepoint, *s))
++s;
if (!decode(&state, &codepoint, *s)) {
count += 1;
}
}
return state != UTF8_ACCEPT;
// return state;
// return count;
}

View File

@ -1,25 +0,0 @@
#ifndef UTF8_DECODE_H
#define UTF8_DECODE_H
#include <stdlib.h>
#include <stdint.h>
//inline uint32_t decode(uint32_t* state, uint32_t* codep, uint32_t byte);
extern int countCodePoints(uint8_t* s, size_t count);
/* typedef struct {
size_t current_index;
size_t total_index;
int state;
int is_valid;
int ends_on_codepoint;
} utf8_validator_t;
extern void utf8vld_reset (utf8_validator_t* validator);
extern void utf8vld_validate (utf8_validator_t* validator, const uint8_t* data, size_t offset, size_t length);
extern int utf8_valid(const uint8_t* data, size_t len); */
#endif // UTF8_DECODE_H

View File

@ -1,64 +0,0 @@
#include "utf8validator.h"
static const uint8_t UTF8VALIDATOR_DFA[] =
{
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
};
#define UTF8_ACCEPT 0
#define UTF8_REJECT 1
void utf8vld_reset (utf8_validator_t* validator) {
validator->state = UTF8_ACCEPT;
validator->current_index = 0;
validator->total_index = 0;
validator->is_valid = 1;
validator->ends_on_codepoint = 1;
}
void utf8vld_validate (utf8_validator_t* validator, const uint8_t* data, size_t offset, size_t length) {
int state = validator->state;
for (size_t i = offset; i < length + offset; ++i) {
state = UTF8VALIDATOR_DFA[256 + (state << 4) + UTF8VALIDATOR_DFA[data[i]]];
if (state == UTF8_REJECT)
{
validator->state = state;
validator->current_index = i - offset;
validator->total_index += i - offset;
validator->is_valid = 0;
validator->ends_on_codepoint = 0;
return;
}
}
validator->state = state;
validator->current_index = length;
validator->total_index += length;
validator->is_valid = 1;
validator->ends_on_codepoint = validator->state == UTF8_ACCEPT;
}
int utf8_valid(const uint8_t* data, size_t len) {
utf8_validator_t validator;
utf8vld_reset(&validator);
utf8vld_validate(&validator, data, 0, len);
return validator.is_valid;
}

View File

@ -1,21 +0,0 @@
#ifndef UTF8_VALIDATOR_H
#define UTF8_VALIDATOR_H
#include <stdlib.h>
#include <stdint.h>
typedef struct {
size_t current_index;
size_t total_index;
int state;
int is_valid;
int ends_on_codepoint;
} utf8_validator_t;
extern void utf8vld_reset (utf8_validator_t* validator);
extern void utf8vld_validate (utf8_validator_t* validator, const uint8_t* data, size_t offset, size_t length);
extern int utf8_valid(const uint8_t* data, size_t len);
#endif // UTF8_VALIDATOR_H