string-util.h File Reference

#include "mupdf/fitz/system.h"
#include "mupdf/fitz/context.h"

Include dependency graph for string-util.h:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Macros
#define	FZ_REPLACEMENT_CHARACTER   0xFFFD

Enumerations
enum	{ FZ_UTFMAX = 4 }

Functions
size_t	fz_strnlen (const char *s, size_t maxlen)
char *	fz_strsep (char **stringp, const char *delim)
size_t	fz_strlcpy (char *dst, const char *src, size_t n)
size_t	fz_strlcat (char *dst, const char *src, size_t n)
const char *	fz_strstr (const char *haystack, const char *needle)
const char *	fz_strstrcase (const char *haystack, const char *needle)
void *	fz_memmem (const void *haystack, size_t haystacklen, const void *needle, size_t needlelen)
void	fz_dirname (char *dir, const char *path, size_t dirsize)
const char *	fz_basename (const char *path)
int	fz_strverscmp (const char *s1, const char *s2)
char *	fz_urldecode (char *url)
char *	fz_decode_uri (fz_context *ctx, const char *s)
char *	fz_decode_uri_component (fz_context *ctx, const char *s)
char *	fz_encode_uri (fz_context *ctx, const char *s)
char *	fz_encode_uri_component (fz_context *ctx, const char *s)
char *	fz_encode_uri_pathname (fz_context *ctx, const char *s)
void	fz_format_output_path (fz_context *ctx, char *path, size_t size, const char *fmt, int page)
char *	fz_cleanname (char *name)
char *	fz_cleanname_strdup (fz_context *ctx, const char *name)
char *	fz_realpath (const char *path, char *resolved_path)
int	fz_strcasecmp (const char *a, const char *b)
int	fz_strncasecmp (const char *a, const char *b, size_t n)
int	fz_chartorune (int *rune, const char *str)
int	fz_chartorunen (int *rune, const char *str, size_t n)
int	fz_runetochar (char *str, int rune)
int	fz_runelen (int rune)
int	fz_runeidx (const char *str, const char *p)
const char *	fz_runeptr (const char *str, int idx)
int	fz_utflen (const char *s)
char *	fz_utf8_from_wchar (fz_context *ctx, const wchar_t *s)
wchar_t *	fz_wchar_from_utf8 (fz_context *ctx, const char *path)
float	fz_strtof (const char *s, char **es)
int	fz_grisu (float f, char *s, int *exp)
int	fz_is_page_range (fz_context *ctx, const char *s)
const char *	fz_parse_page_range (fz_context *ctx, const char *s, int *a, int *b, int n)
int	fz_tolower (int c)
int	fz_toupper (int c)

Macro Definition Documentation

FZ_REPLACEMENT_CHARACTER

#define FZ_REPLACEMENT_CHARACTER   0xFFFD

Enumeration Type Documentation

anonymous enum

anonymous enum

FZ_UTFMAX: Maximum number of bytes in a decoded rune (maximum length returned by fz_chartorune).

Enumerator
FZ_UTFMAX

Function Documentation

fz_basename()

const char * fz_basename

(

const char *

path

)

Find the filename component in a path.

fz_chartorune()

int fz_chartorune	(	int *	rune,
		const char *	str )

UTF8 decode a single rune from a sequence of chars.

rune: Pointer to an int to assign the decoded 'rune' to. (0xFFFD on error).

str: Pointer to a UTF8 encoded string.

Returns the number of bytes consumed.

fz_chartorunen()

int fz_chartorunen	(	int *	rune,
		const char *	str,
		size_t	n )

UTF8 decode a single rune from a sequence of chars of given length.

rune: Pointer to an int to assign the decoded 'rune' to. (0xFFFD on error).

str: Pointer to a UTF8 encoded string.

n: The number of bytes available at str.

Returns the number of bytes consumed.

fz_cleanname()

char * fz_cleanname

(

char *

name

)

rewrite path to the shortest string that names the same path.

Eliminates multiple and trailing slashes, interprets "." and "..". Overwrites the string in place.

fz_cleanname_strdup()

char * fz_cleanname_strdup	(	fz_context *	ctx,
		const char *	name )

rewrite path to the shortest string that names the same path.

Eliminates multiple and trailing slashes, interprets "." and "..". Allocates a new string that the caller must free.

fz_decode_uri()

char * fz_decode_uri	(	fz_context *	ctx,
		const char *	s )

Return a new string representing the unencoded version of the given URI. This decodes all escape sequences except those that would result in a reserved character that are part of the URI syntax (; / ? : @ & = + $ , #).

fz_decode_uri_component()

char * fz_decode_uri_component	(	fz_context *	ctx,
		const char *	s )

Return a new string representing the unencoded version of the given URI component. This decodes all escape sequences!

fz_dirname()

void fz_dirname	(	char *	dir,
		const char *	path,
		size_t	dirsize )

extract the directory component from a path.

fz_encode_uri()

char * fz_encode_uri	(	fz_context *	ctx,
		const char *	s )

Return a new string representing the provided string encoded as a URI.

fz_encode_uri_component()

char * fz_encode_uri_component	(	fz_context *	ctx,
		const char *	s )

Return a new string representing the provided string encoded as an URI component. This also encodes the special reserved characters (; / ? : @ & = + $ , #).

fz_encode_uri_pathname()

char * fz_encode_uri_pathname	(	fz_context *	ctx,
		const char *	s )

Return a new string representing the provided string encoded as an URI path name. This also encodes the special reserved characters except /.

fz_format_output_path()

void fz_format_output_path	(	fz_context *	ctx,
		char *	path,
		size_t	size,
		const char *	fmt,
		int	page )

create output file name using a template.

If the path contains %[0-9]*d, the first such pattern will be replaced with the page number. If the template does not contain such a pattern, the page number will be inserted before the filename extension. If the template does not have a filename extension, the page number will be added to the end.

fz_grisu()

int fz_grisu	(	float	f,
		char *	s,
		int *	exp )

fz_is_page_range()

int fz_is_page_range	(	fz_context *	ctx,
		const char *	s )

Check and parse string into page ranges: /,?(-?\d+|N)(-(-?\d+|N))?/

fz_memmem()

void * fz_memmem	(	const void *	haystack,
		size_t	haystacklen,
		const void *	needle,
		size_t	needlelen )

Find the start of the first occurrence of the substring needle in haystack.

fz_parse_page_range()

const char * fz_parse_page_range	(	fz_context *	ctx,
		const char *	s,
		int *	a,
		int *	b,
		int	n )

fz_realpath()

char * fz_realpath	(	const char *	path,
		char *	resolved_path )

Resolve a path to an absolute file name. The resolved path buffer must be of at least PATH_MAX size.

fz_runeidx()

int fz_runeidx	(	const char *	str,
		const char *	p )

Compute the index of a rune in a string.

str: Pointer to beginning of a string.

p: Pointer to a char in str.

Returns the index of the rune pointed to by p in str.

fz_runelen()

int fz_runelen

(

int

rune

)

Count how many chars are required to represent a rune.

rune: The rune to encode.

Returns the number of bytes required to represent this run in UTF8.

fz_runeptr()

const char * fz_runeptr	(	const char *	str,
		int	idx )

Obtain a pointer to the char representing the rune at a given index.

str: Pointer to beginning of a string.

idx: Index of a rune to return a char pointer to.

Returns a pointer to the char where the desired rune starts, or NULL if the string ends before the index is reached.

fz_runetochar()

int fz_runetochar	(	char *	str,
		int	rune )

UTF8 encode a rune to a sequence of chars.

str: Pointer to a place to put the UTF8 encoded character.

rune: Pointer to a 'rune'.

Returns the number of bytes the rune took to output.

fz_strcasecmp()

int fz_strcasecmp	(	const char *	a,
		const char *	b )

Case insensitive (UTF8) string comparison.

fz_strlcat()

size_t fz_strlcat	(	char *	dst,
		const char *	src,
		size_t	n )

Concatenate 2 strings, with a maximum length.

dst: pointer to first string in a buffer of n bytes.

src: pointer to string to concatenate.

n: Size (in bytes) of buffer that dst is in.

Returns the real length that a concatenated dst + src would have been (not including terminator).

fz_strlcpy()

size_t fz_strlcpy	(	char *	dst,
		const char *	src,
		size_t	n )

Copy at most n-1 chars of a string into a destination buffer with null termination, returning the real length of the initial string (excluding terminator).

dst: Destination buffer, at least n bytes long.

src: C string (non-NULL).

n: Size of dst buffer in bytes.

Returns the length (excluding terminator) of src.

fz_strncasecmp()

int fz_strncasecmp	(	const char *	a,
		const char *	b,
		size_t	n )

Case insensitive (UTF8) string comparison.

n = maximum number of bytes to read from either a or b.

fz_strnlen()

size_t fz_strnlen	(	const char *	s,
		size_t	maxlen )

Safe string functions Return strlen(s), if that is less than maxlen, or maxlen if there is no null byte ('\0') among the first maxlen bytes.

fz_strsep()

char * fz_strsep	(	char **	stringp,
		const char *	delim )

Given a pointer to a C string (or a pointer to NULL) break it at the first occurrence of a delimiter char (from a given set).

stringp: Pointer to a C string pointer (or NULL). Updated on exit to point to the first char of the string after the delimiter that was found. The string pointed to by stringp will be corrupted by this call (as the found delimiter will be overwritten by 0).

delim: A C string of acceptable delimiter characters.

Returns a pointer to a C string containing the chars of stringp up to the first delimiter char (or the end of the string), or NULL.

fz_strstr()

const char * fz_strstr	(	const char *	haystack,
		const char *	needle )

Safe strstr function.

haystack: Where to look (may be NULL).

needled: What to look for.

Returns NULL if unmatched, or pointer to start of match.

fz_strstrcase()

const char * fz_strstrcase	(	const char *	haystack,
		const char *	needle )

Safe case-insensitive strstr function. (Accepts UTF-8).

haystack: Where to look (may be NULL).

needled: What to look for.

Returns NULL if unmatched, or pointer to start of match.

fz_strtof()

float fz_strtof	(	const char *	s,
		char **	es )

Locale-independent decimal to binary conversion. On overflow return (-)INFINITY and set errno to ERANGE. On underflow return 0 and set errno to ERANGE. Special inputs (case insensitive): "NAN", "INF" or "INFINITY".

fz_strverscmp()

int fz_strverscmp	(	const char *	s1,
		const char *	s2 )

portable strverscmp(3) function

fz_tolower()

int fz_tolower

(

int

c

)

Unicode aware tolower and toupper functions.

fz_toupper()

int fz_toupper

(

int

c

)

fz_urldecode()

char * fz_urldecode

(

char *

url

)

Like fz_decode_uri_component but in-place.

fz_utf8_from_wchar()

char * fz_utf8_from_wchar	(	fz_context *	ctx,
		const wchar_t *	s )

fz_utflen()

int fz_utflen

(

const char *

s

)

Count how many runes the UTF-8 encoded string consists of.

s: The UTF-8 encoded, NUL-terminated text string.

Returns the number of runes in the string.

fz_wchar_from_utf8()

wchar_t * fz_wchar_from_utf8	(	fz_context *	ctx,
		const char *	path )