utrac.h File Reference

#include <sys/types.h>
#include "ut_error.h"
#include "ut_text.h"
#include "ut_charset.h"

Include dependency graph for utrac.h:

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

Go to the source code of this file.

Classes

struct UtLangSys

Structure containing different languages or systems used. More...

struct UtSession

Structure containing all required information for Utrac. More...

Defines

#define true   1

#define false   0

#define UT_VERSION   "0.3.0"

#define UT_EOL_CHAR   0x0

Character code for end of line.

#define UT_EOL_ALT_CHAR   0xD

Character code for end of line 2 (see UtEolType).

#define UT_SKIP_CHAR   0x1

Character code for character to skip during conversion.

#define UT_EOF_CHAR   0x0

Character code for end of file.

#define UT_UNICODE_NONCHAR   0xFFFF

Illegal character, also used to indicate "no character".

#define UT_UNSET   -1

Unset variable (often used for indexes).

#define UT_THRESHOLD_CONTROL_CHAR   0.05

Maximum percentage of illegal control chars accepted in a file.

#define UT_THRESHOLD_UTF8   0.01

Maximum percentage of utf-8 errors in an UTF-8 file.

#define UT_LOAD_STEP   1*1024*1024

Step in bytes between two calls of the "progress bar" function during loading.

#define UT_PROCESS_STEP   1*1024*1024

Step in bytes between two calls of the "progress bar" function during processing.

#define UT_COEF_MAX   5

Maximum number of coefficients for languages and systems.

#define UT_LANG_SYS_ALLOC_STEP   8

Initial size for dynamic array UtLangSys.

#define UT_ERROR_STRING_SIZE   128

Size of UtSession::error_string.

#define UT_STDIN_BUFFER_SIZE   65536

Initial size for dynamic buffer in ut_load_text_stdin().

#define UT_TRY(func)

Typedefs

typedef unsigned short int bool

typedef UtLangSys UtLangSys

Structure containing different languages or systems used.

typedef UtSession UtSession

Structure containing all required information for Utrac.

Functions

UtCode ut_init ()

Initialize the Utrac library.

UtCode ut_init_noalloc ()

Initialize the Utrac library, without allocating memory for UtSession. Used internally.

void ut_finish ()

Free ressources allocated during initialization of Utrac.

void ut_finish_nofree ()

Free ressources allocated during initialization of Utrac, without freeing UtSession. Used internally.

UtText * ut_init_text_heap ()

Allocates and initalizes an UtText structure.

void ut_init_text (UtText *new_text)

Initalizes an UtText structure.

void ut_free_text_heap (UtText *text)

Free an UtText structure.

void ut_free_text (UtText *text)

Free the contents of an UtText structure, without freeing the structure itself.

UtCode ut_init_progress (UtText *text)

Initialize an UtText structure before using the 'progress bar' callback feature.

UtCode ut_load (UtText *text, const char *filename)

Load a file in an UtText structure.

UtCode ut_recognize (UtText *text)

Recognize charset and EOL of a text.

UtCode ut_convert (UtText *src_text, UtText *dst_text)

Convert a text.

UtCode ut_load_charsets ()

Loads and parses file charset.dat.

UtCode ut_load_charset_file (const char *filename, char **buffer)

Load a file in a buffer.

UtCharsetIndex ut_find_charset (char *charset_name)

get charset index from a string

UtEolType ut_find_eol (char *eol_name)

int ut_find_lang_sys (char *language_name, UtLangSys *lang_sys)

double ut_get_charset_coef (UtCharsetIndex i)

bool ut_str_fuzzy_cmp (const char *str1, const char *str2, char stop_char)

Approximative comparaison between two strings.

bool ut_update_progress (struct UtText *, ulong, bool)

ulong ut_crc32 (ushort, ulong)

Function which call the user-defined function UtText::progress_function.

void ut_print_binary (ulong src)

Print a number in binary form on stdout (debug).

UtCode ut_debug_text (struct UtText *)

UtCode ut_debug_text_rating (struct UtText *)

const char * ut_error_message (UtCode code)

UtCode ut_load_file_pass (UtText *text, const char *filename)

Load a text in a buffer.

UtCode ut_load_stdin_pass (UtText *text)

Load a text from stdin.

UtCode ut_distrib_utf_pass (struct UtText *)

UtCode ut_eol_pass (struct UtText *)

UtCode ut_xascii_pass (struct UtText *)

int ut_size_char (char **src_p, UtCharsetIndex src_charset, UtCharsetIndex dst_charset)

Return size in byte of a character after conversion.

void ut_conv_char (char **src_p, char **dst_p, UtCharsetIndex src_charset, UtCharsetIndex dst_charset)

Convert a character.

void ut_insert_eol (char **dst_p, UtEolType dst_eol)

uint ut_count_ext_char (UtText *text)

Count the number of extended character in a text.

int ut_size_difference (UtText *src_text, UtText *dst_text)

Return the difference between the size of a text and its size after conversion.

UtCode ut_conversion_pass (UtText *src_text, UtText *dst_text)

Convert extended characters and EOL.

Variables

const float UT_LANG_SYS_COEF []

Language and system coeficients applied to charset rating, depending on language or system selected.

const char * UT_CHARMAPS_FILENAME

Path 1 to file containing charset informations.

const char * UT_CHARMAPS_FILENAME2

Path 2 to file containing charset informations.

const char * UT_DEFAULT_ENCODING_UNIX

Default encoding on Unix systems.

UtSession * ut_session

Detailed Description

Author:: Antoine Calando (antoine@alliancemca.net)

Definition in file utrac.h.

Define Documentation

#define UT_TRY ( func )

Value:
{\ UtCode rcode = func;\ if (rcode != UT_OK) return rcode;\ }

Definition at line 149 of file utrac.h.

Typedef Documentation

typedef struct UtLangSys UtLangSys

Structure containing different languages or systems used.
This structure is a dynamic array containing the list of languages or systems defined in the charset data file

typedef struct UtSession UtSession

Structure containing all required information for Utrac.
This structure contains all the required information for an utrac session (charsets data, language, system and charset default...). Its unique instance can be accessed with the ut_session pointer which is defined as a global variable. It is created with ut_init() and destroyed with ut_finish().
See also:
ut_session.

Function Documentation

void ut_conv_char ( char ** src_p,

char ** dst_p,

UtCharsetIndex src_charset,

UtCharsetIndex dst_charset

)

Convert a character.

Parameters:

text UtText structure containing the source charset and the destination charset.

src_p Address of the pointer on the beginning of the character encoded with the source charset . This pointer will be incremented to the beginning of the following character.

dst_p address of the pointer on the buffer where the converted character will be written. This pointer is incremented to the end of the character + 1 after conversion.

Todo:
EC Il y a des cas d'erreur (ERROR), on doit donc pourvoir retourner l'erreur. AC Les erreurs sont gérées : elles sont indiquées par un 'ut_session->nomapping_char' dans le texte.

Definition at line 259 of file ut_conversion.c.
References UtSession::charset, UtSession::charset_default, UtSession::nomapping_char, UtCharset::type, UtCharset::unicode, ut_unicode_to_utf8c(), UT_UNSET, and ut_utf8c_to_unicode().
Referenced by ut_conversion_pass().