utils.cpp File Reference

#include <cassert>
#include <ctype.h>
#include <stdio.h>
#include <string.h>
#include <sys/types.h>
#include <iconv.h>
#include "utils.h"
#include "log.h"

Include dependency graph for utils.cpp:

Go to the source code of this file.

Functions
int	get_free_memory ()
	Get free memory.
unsigned int	make_hash_code (const char *buffer, unsigned int len)
	Generate hash code given by a buffe with fixed length.
const char *	utf8_strichr (const char *str, int len, gunichar c)
	Finds the leftmost occurrence of the given unicode character in a UTF-8 encoded string, while limiting the search to len bytes. Ignore case.
const char *	utf8_strirchr (const char *str, int len, gunichar c)
	Finds the rightmost occurrence of the given unicode character in a UTF-8 encoded string, while limiting the search to len bytes. Ignore case.
const char *	utf8_strstr (const char *str, const char *sub, bool case_sensitive)
	Finds the leftmost occurrence of substring in a string.
const char *	utf8_strrstr (const char *str, int len, const char *sub, bool case_sensitive)
	Finds the rightmost occurrence of substring in a string.
bool	is_whole_word (const char *str, const char *sub, size_t sub_len)
	Check if the sub string is a whole word.
bool	get_dir_path (const char *filename, char *dir, int dir_len)
	Get the dir path of 'filename'.
bool	get_file_name (const char *filename, char *name, int name_len)
	Get the name of 'filename'.
bool	get_ext_name (const char *filename, char *ext, int ext_len)
	Get the extension name from a filename.
bool	ucs2utf8 (char *ucs_str, size_t input_len, char *utf_str, size_t output_len)
	Convert the unicode string to utf-8 string.
Variables
static iconv_t	conv = (iconv_t) -1

---

Function Documentation

bool get_dir_path	(	const char *	filename,
		char *	dir,
		int	dir_len
	)

Get the dir path of 'filename'.

Parameters:

	filename	e.g. /data/wa/sample/rome.jpg
	dir	dir path e.g. /data/wa/sample
	dir_len	the max len of 'dir'

Returns:

true has dir, false no dir or error

Definition at line 251 of file utils.cpp.

References LOGPRINTF.

{
    bool has_dir = false;

    if (filename && dir)
    {
       char * ptr = g_path_get_dirname(filename);
       if (ptr)
       {
           has_dir = true;
           
           g_snprintf(dir, dir_len, "%s", ptr);
           g_free(ptr);
       }
    }

    LOGPRINTF("%s %s %d", filename, dir, has_dir);

    return has_dir;
}

bool get_ext_name	(	const char *	filename,
		char *	ext,
		int	ext_len
	)

Get the extension name from a filename.

Parameters:

	filename	e.g. /data/wa/sample/rome.jpg, or rome.jpg
	ext	extension name e.g. jpg
	ext_len	the max len of 'ext'

Returns:

true has extension, false no extension or error

Definition at line 299 of file utils.cpp.

References get_file_name(), LOGPRINTF, MAX_PATH_LEN, and name.

{
    bool has_ext = false;
  
    if (filename && ext)
    {
        char name[MAX_PATH_LEN];
        
        if (get_file_name(filename, name, MAX_PATH_LEN))
        {
            char * ptr = g_strrstr(name, ".");
            if (ptr)
            {
                has_ext = true;

                ptr++;
                g_snprintf(ext, ext_len, "%s", ptr);
            }
        }
    }

    LOGPRINTF("%s %s %d", filename, ext, has_ext);

    return has_ext;
}

Here is the call graph for this function:

bool get_file_name	(	const char *	filename,
		char *	name,
		int	name_len
	)

Get the name of 'filename'.

Parameters:

	filename	e.g. /data/wa/sample/rome.jpg
	name	name e.g. rome.jpg
	name_len	the max len of 'name'

Returns:

true has name, false no name or error

Definition at line 272 of file utils.cpp.

References LOGPRINTF.

Referenced by get_ext_name(), and images::ImagesDocument::get_page_name().

{
    bool has_name = false;

    if (filename && name)
    {
        if (filename[strlen(filename)-1] != G_DIR_SEPARATOR)
        {
            char * ptr = g_path_get_basename(filename);
            if (ptr)
            {
                if (strcmp(ptr, G_DIR_SEPARATOR_S)
                   && strcmp(ptr, "."))
                {
                    has_name = true;
                    g_snprintf(name, name_len, "%s", ptr);
                }
                g_free(ptr);
            }
        }
    }

    LOGPRINTF("%s %s %d", filename, name, has_name);

    return has_name;
}

Here is the caller graph for this function:

int get_free_memory

(

)

Get free memory.

Copyright (C) 2008 iRex Technologies B.V. All rights reserved.

Definition at line 38 of file utils.cpp.

{
    /*
    struct sysinfo info;
    
    if (0 == sysinfo(&info))
    {
        return info.freeram;
    }
    */
    return 0;
}

bool is_whole_word	(	const char *	str,
		const char *	sub,
		size_t	sub_len
	)

Check if the sub string is a whole word.

Parameters:

	str	The UTF-8 encoded string.
	sub	The sub string to be checked.
	sub_len	The length of the sub string.

Returns:

true if sub is a whole word.

Definition at line 210 of file utils.cpp.

Referenced by text::TextModel::search().

{
    // Check the input parameters.
    if (   !str
        || !sub
        || sub_len == 0)
    {
        return false;
    }

    // Check the first char before 'sub'.
    const char *p = g_utf8_find_prev_char(str, sub);
    if (p)
    {
        gunichar prev_char = g_utf8_get_char(p);
        if (   g_unichar_isalpha(prev_char) 
            || g_unichar_isdigit(prev_char) 
            || prev_char == '_'   )
        {
            return false;
        }
    }

    // Check the first char after 'sub'.
    const char *n = sub + sub_len;
    if (*n)
    {
        gunichar next_char = g_utf8_get_char_validated(n, -1);
        if (   next_char > 0
            && (   g_unichar_isalpha(next_char)
                || g_unichar_isdigit(next_char)
                || next_char == '_'             ) )
        {
            return false;
        }
    }

    // Otherwise 'sub' is a whole word.
    return true;
}

Here is the caller graph for this function:

unsigned int make_hash_code	(	const char *	buffer,
		unsigned int	len
	)

Generate hash code given by a buffe with fixed length.

Definition at line 53 of file utils.cpp.

Referenced by images::ImagePage::calc_key(), and text::TextView::set_font_size().

{
    assert(buffer);
    assert(len != 0);

    const char *p = buffer;
    unsigned int h = 0;

    while (len--)
    {
        h = (h << 5) - h + *p;
        p++;
    }

    return h;
}

Here is the caller graph for this function:

bool ucs2utf8	(	char *	ucs_str,
		size_t	input_len,
		char *	utf_str,
		size_t	output_len
	)

Convert the unicode string to utf-8 string.

Parameters:

	ucs_str	The input unicode string.
	input_len	The length of input buffer.
	utf_str	The output utf-8 string buffer.
	output_len	The buffer length of output buffer.

Returns:

true if conversion succeed, otherwise false is returned.

Definition at line 326 of file utils.cpp.

References conv.

{
    if (conv == (iconv_t) -1)
    {
        conv = iconv_open("UTF-8", "Unicode");
    }

    assert(conv != (iconv_t) -1);

    char* in_buf  = ucs_str;
    char* out_buf = utf_str;
    size_t in_bytes_left  = input_len;
    size_t out_bytes_left = output_len;

#ifdef WIN32
    if (-1 == iconv(conv, const_cast<const char **>(&in_buf), &in_bytes_left, &out_buf, &out_bytes_left))
#else
    if ((size_t)-1 == iconv(conv, &in_buf, &in_bytes_left, &out_buf, &out_bytes_left))
#endif
    {
        return false;
    }

    if (in_bytes_left != 0)
    {
        // Either we encountered an error, or the output buffer is too small.
        return false;
    }

    // Add '\0' terminator.
    *out_buf = 0;
    return true;
}

const char* utf8_strichr	(	const char *	str,
		int	len,
		gunichar	c
	)

Finds the leftmost occurrence of the given unicode character in a UTF-8 encoded string, while limiting the search to len bytes. Ignore case.

Definition at line 70 of file utils.cpp.

Referenced by utf8_strstr().

{
    if (g_unichar_isalpha(c))
    {
        // Only alphabetic character is case related.
        c = g_unichar_toupper(c);
        for (const char* p=str; (len == -1 && *p != 0) || (p-str<len); p = g_utf8_next_char(p))
        {
            gunichar i = g_utf8_get_char(p);
            if (i == c || i-c == 32)
            {
                return p;
            }
        }
        return NULL;
    }
    else
    {
        return g_utf8_strchr(str, len, c);
    }
}

Here is the caller graph for this function:

const char* utf8_strirchr	(	const char *	str,
		int	len,
		gunichar	c
	)

Finds the rightmost occurrence of the given unicode character in a UTF-8 encoded string, while limiting the search to len bytes. Ignore case.

Definition at line 92 of file utils.cpp.

Referenced by utf8_strrstr().

{
    if (g_unichar_isalpha(c))
    {
        // Only alphabetic character is case related.
        c = g_unichar_toupper(c);
        const char *p = str + len;
        while (true)
        {
            // Try previous character.
            p = g_utf8_find_prev_char(str, p);
            if (p == NULL)
            {
                return NULL;
            }
            
            gunichar i = g_utf8_get_char(p);
            if (i == c || i-c == 32)
            {
                return p;
            }
        }
    }
    else
    {
        return g_utf8_strrchr(str, len, c);
    }
}

Here is the caller graph for this function:

const char* utf8_strrstr	(	const char *	str,
		int	len,
		const char *	sub,
		bool	case_sensitive
	)

Finds the rightmost occurrence of substring in a string.

Definition at line 161 of file utils.cpp.

References utf8_strirchr().

Referenced by text::TextModel::search().

{
    gunichar first_char = g_utf8_get_char(sub);
    size_t sub_len = strlen(sub);

    while (len > 0)
    {
        const char *p = NULL;
        if (case_sensitive)
        {
            p = g_utf8_strrchr(str, len, first_char);
        }
        else
        {
            // Ignore case.
            p = utf8_strirchr(str, len, first_char);
        }

        if (p == NULL)
        {
            return NULL;
        }

        // The first char of sub string is found.
        int ret;
        if (case_sensitive)
        {
            ret = strncmp(p, sub, sub_len);
        }
        else
        {
#ifdef WIN32
            ret = _strnicmp(p, sub, sub_len);
#else
            ret = strncasecmp(p, sub, sub_len);
#endif
        }
        
        if (ret == 0)
        {
            // Pattern found
            return p;
        }
        len = static_cast<int>(p - str);
    }

    return NULL;
}

Here is the call graph for this function:

Here is the caller graph for this function:

const char* utf8_strstr	(	const char *	str,
		const char *	sub,
		bool	case_sensitive
	)

Finds the leftmost occurrence of substring in a string.

Definition at line 121 of file utils.cpp.

References utf8_strichr().

Referenced by text::TextModel::search().

{
    if (case_sensitive)
    {
        return strstr(str, sub);
    }
    else
    {
        // Ignore case.
        gunichar first_char = g_utf8_get_char(sub);
        size_t sub_len = strlen(sub);

        for (const char *p=str; *p != 0;)
        {
            const char *find = utf8_strichr(p, -1, first_char);
            if (find != NULL)
            {
#ifdef WIN32
                if (_strnicmp(find, sub, sub_len) == 0)
#else
                if (strncasecmp(find, sub, sub_len) == 0)
#endif
                {
                    return find;
                }
                else
                {
                    p = g_utf8_next_char(find);
                }
            }
            else
            {
                return NULL;
            }
        }

        return NULL;
    }
}

Here is the call graph for this function:

Here is the caller graph for this function:

---

Variable Documentation

iconv_t conv = (iconv_t) -1 [static]

Definition at line 325 of file utils.cpp.

Referenced by main(), and ucs2utf8().