detect.c File Reference

#include <assert.h>
#include <stdbool.h>
#include <string.h>
#include <strings.h>
#include <parserutils/charset/mibenum.h>
#include <hubbub/types.h>
#include "utils/utils.h"
#include "detect.h"

Include dependency graph for detect.c:

Macros
#define	PEEK(a)
#define	ADVANCE(a)
#define	ISSPACE(a)

Functions
parserutils_error	hubbub_charset_extract (const uint8_t *data, size_t len, uint16_t *mibenum, uint32_t *source)
uint16_t	hubbub_charset_parse_content (const uint8_t *value, uint32_t valuelen)
void	hubbub_charset_fix_charset (uint16_t *charset)

Macro Definition Documentation

ADVANCE

#define ADVANCE

(

a

)

Value:

    while (pos < end - SLEN(a)) {                   \
        if (PEEK(a))                        \
            break;                      \
        pos++;                          \
    }                               \
                                    \
    if (pos == end - SLEN(a))                   \
        return 0;

ISSPACE

#define ISSPACE

(

a

)

Value:

    (a == 0x09 || a == 0x0a || a == 0x0c ||             \
            a == 0x0d || a == 0x20 || a == 0x2f)

PEEK

#define PEEK

(

a

)

Value:

    (pos < end - SLEN(a) &&                     \
        strncasecmp((const char *) pos, a, SLEN(a)) == 0)

Function Documentation

hubbub_charset_extract()

parserutils_error hubbub_charset_extract	(	const uint8_t *	data,
		size_t	len,
		uint16_t *	mibenum,
		uint32_t *	source
	)

Extract a charset from a chunk of data

Parameters

data	Pointer to buffer containing data
len	Buffer length
mibenum	Pointer to location containing current MIB enum
source	Pointer to location containint current charset source

Returns

PARSERUTILS_OK on success, appropriate error otherwise

mibenum and source will be updated on exit

The larger a chunk of data fed to this routine, the better, as it allows charset autodetection access to a larger dataset for analysis.

Meaning of *source on entry:

CONFIDENT - Do not pass Go, do not attempt auto-detection. TENTATIVE - We've tried to autodetect already, but subsequently discovered that we don't actually support the detected charset. Thus, we've defaulted to Windows-1252. Don't perform auto-detection again, as it would be futile. (This bit diverges from the spec) UNKNOWN - No autodetection performed yet. Get on with it.

Todo:

We probably want to wait for ~512 bytes of data / 500ms here

Todo:

Charset autodetection

hubbub_charset_fix_charset()

void hubbub_charset_fix_charset

(

uint16_t *

charset

)

Fix charsets, according to the override table in HTML5, section 8.2.2.2. Character encoding requirements http://www.whatwg.org/specs/web-apps/current-work/#character0

Parameters

charset

Pointer to charset value to fix

hubbub_charset_parse_content()

uint16_t hubbub_charset_parse_content	(	const uint8_t *	value,
		uint32_t	valuelen
	)

Parse a content= attribute's value

Parameters

value	Attribute's value
valuelen	Length of value

Returns

MIB enum of detected encoding, or 0 if none found