Subversion Repositories HelenOS

Rev

Rev 4055 | Rev 4296 | Go to most recent revision | Blame | Compare with Previous | Last modification | View Log | Download | RSS feed

  1. /*
  2.  * Copyright (c) 2001-2004 Jakub Jermar
  3.  * All rights reserved.
  4.  *
  5.  * Redistribution and use in source and binary forms, with or without
  6.  * modification, are permitted provided that the following conditions
  7.  * are met:
  8.  *
  9.  * - Redistributions of source code must retain the above copyright
  10.  *   notice, this list of conditions and the following disclaimer.
  11.  * - Redistributions in binary form must reproduce the above copyright
  12.  *   notice, this list of conditions and the following disclaimer in the
  13.  *   documentation and/or other materials provided with the distribution.
  14.  * - The name of the author may not be used to endorse or promote products
  15.  *   derived from this software without specific prior written permission.
  16.  *
  17.  * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
  18.  * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
  19.  * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
  20.  * IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
  21.  * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
  22.  * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
  23.  * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
  24.  * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
  25.  * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
  26.  * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  27.  */
  28.  
  29. /** @addtogroup generic
  30.  * @{
  31.  */
  32.  
  33. /**
  34.  * @file
  35.  * @brief Miscellaneous functions.
  36.  */
  37.  
  38. #include <string.h>
  39. #include <print.h>
  40. #include <cpu.h>
  41. #include <arch/asm.h>
  42. #include <arch.h>
  43. #include <console/kconsole.h>
  44.  
  45. char invalch = '?';
  46.  
  47. /** Byte mask consisting of lowest @n bits (out of eight). */
  48. #define LO_MASK_8(n) ((uint8_t)((1 << (n)) - 1))
  49.  
  50. /** Byte mask consisting of lowest @n bits (out of 32). */
  51. #define LO_MASK_32(n) ((uint32_t)((1 << (n)) - 1))
  52.  
  53. /** Byte mask consisting of highest @n bits (out of eight). */
  54. #define HI_MASK_8(n) (~LO_MASK_8(8 - (n)))
  55.  
  56. /** Number of data bits in a UTF-8 continuation byte. */
  57. #define CONT_BITS 6
  58.  
  59. /** Decode a single character from a substring.
  60.  *
  61.  * Decode a single character from a substring of size @a sz. Decoding starts
  62.  * at @a offset and this offset is moved to the beginning of the next
  63.  * character. In case of decoding error, offset generally advances at least
  64.  * by one. However, offset is never moved beyond (str + sz).
  65.  *
  66.  * @param str   String (not necessarily NULL-terminated).
  67.  * @param index Index (counted in plain characters) where to start
  68.  *              the decoding.
  69.  * @param limit Size of the substring.
  70.  *
  71.  * @return  Value of decoded character or '?' on decoding error.
  72.  *
  73.  */
  74. wchar_t chr_decode(const char *str, size_t *offset, size_t sz)
  75. {
  76.     uint8_t b0, b;          /* Bytes read from str. */
  77.     wchar_t ch;
  78.  
  79.     int b0_bits;        /* Data bits in first byte. */
  80.     int cbytes;     /* Number of continuation bytes. */
  81.  
  82.     if (*offset + 1 > sz)
  83.         return invalch;
  84.  
  85.     b0 = (uint8_t) str[(*offset)++];
  86.  
  87.     /* Determine code length. */
  88.  
  89.     if ((b0 & 0x80) == 0) {
  90.         /* 0xxxxxxx (Plain ASCII) */
  91.         b0_bits = 7;
  92.         cbytes = 0;
  93.     } else if ((b0 & 0xe0) == 0xc0) {
  94.         /* 110xxxxx 10xxxxxx */
  95.         b0_bits = 5;
  96.         cbytes = 1;
  97.     } else if ((b0 & 0xf0) == 0xe0) {
  98.         /* 1110xxxx 10xxxxxx 10xxxxxx */
  99.         b0_bits = 4;
  100.         cbytes = 2;
  101.     } else if ((b0 & 0xf8) == 0xf0) {
  102.         /* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */
  103.         b0_bits = 3;
  104.         cbytes = 3;
  105.     } else {
  106.         /* 10xxxxxx -- unexpected continuation byte. */
  107.         return invalch;
  108.     }
  109.  
  110.     if (*offset + cbytes > sz) {
  111.         return invalch;
  112.     }
  113.  
  114.     ch = b0 & LO_MASK_8(b0_bits);
  115.  
  116.     /* Decode continuation bytes. */
  117.     while (cbytes > 0) {
  118.         b = (uint8_t) str[(*offset)++];
  119.  
  120.         /* Must be 10xxxxxx. */
  121.         if ((b & 0xc0) != 0x80) {
  122.             return invalch;
  123.         }
  124.  
  125.         /* Shift data bits to ch. */
  126.         ch = (ch << CONT_BITS) | (wchar_t) (b & LO_MASK_8(CONT_BITS));
  127.         --cbytes;
  128.     }
  129.  
  130.     return ch;
  131. }
  132.  
  133. /** Encode a single character to string representation.
  134.  *
  135.  * Encode a single character to string representation (i.e. UTF-8) and store
  136.  * it into a buffer at @a offset. Encoding starts at @a offset and this offset
  137.  * is moved to the position where the next character can be written to.
  138.  *
  139.  * @param ch        Input character.
  140.  * @param str       Output buffer.
  141.  * @param offset    Offset (in bytes) where to start writing.
  142.  * @param sz        Size of the output buffer.
  143.  *
  144.  * @return True if the character was encoded successfully or false if there
  145.  *     was not enough space in the output buffer or the character code
  146.  *     was invalid.
  147.  */
  148. bool chr_encode(const wchar_t ch, char *str, size_t *offset, size_t sz)
  149. {
  150.     uint32_t cc;        /* Unsigned version of ch. */
  151.  
  152.     int cbytes;     /* Number of continuation bytes. */
  153.     int b0_bits;        /* Number of data bits in first byte. */
  154.     int i;
  155.  
  156.     if (*offset >= sz)
  157.         return false;
  158.  
  159.     if (ch < 0)
  160.         return false;
  161.  
  162.     /* Bit operations should only be done on unsigned numbers. */
  163.     cc = (uint32_t) ch;
  164.  
  165.     /* Determine how many continuation bytes are needed. */
  166.     if ((cc & ~LO_MASK_32(7)) == 0) {
  167.         b0_bits = 7;
  168.         cbytes = 0;
  169.     } else if ((cc & ~LO_MASK_32(11)) == 0) {
  170.         b0_bits = 5;
  171.         cbytes = 1;
  172.     } else if ((cc & ~LO_MASK_32(16)) == 0) {
  173.         b0_bits = 4;
  174.         cbytes = 2;
  175.     } else if ((cc & ~LO_MASK_32(21)) == 0) {
  176.         b0_bits = 3;
  177.         cbytes = 3;
  178.     } else {
  179.         /* Codes longer than 21 bits are not supported. */
  180.         return false;
  181.     }
  182.  
  183.     /* Check for available space in buffer. */
  184.     if (*offset + cbytes >= sz)
  185.         return false;
  186.  
  187.     /* Encode continuation bytes. */
  188.     for (i = cbytes; i > 0; --i) {
  189.         str[*offset + i] = 0x80 | (cc & LO_MASK_32(CONT_BITS));
  190.         cc = cc >> CONT_BITS;
  191.     }
  192.  
  193.     /* Encode first byte. */
  194.     str[*offset] = (cc & LO_MASK_32(b0_bits)) | HI_MASK_8(8 - b0_bits - 1);
  195.  
  196.     /* Advance offset. */
  197.     *offset += (1 + cbytes);
  198.    
  199.     return true;
  200. }
  201.  
  202. /** Get bytes used by UTF-8 characters.
  203.  *
  204.  * Get the number of bytes (count of plain characters) which
  205.  * are used by a given count of UTF-8 characters in a string.
  206.  * As UTF-8 encoding is multibyte, there is no constant
  207.  * correspondence between number of characters and used bytes.
  208.  *
  209.  * @param str   UTF-8 string to consider.
  210.  * @param count Number of UTF-8 characters to count.
  211.  *
  212.  * @return Number of bytes used by the characters.
  213.  *
  214.  */
  215. size_t utf8_count_bytes(const char *str, count_t count)
  216. {
  217.     size_t size = 0;
  218.     index_t index = 0;
  219.     index_t iprev;
  220.     wchar_t ch;
  221.    
  222.     while (true) {
  223.         iprev = index;
  224.         if (size >= count)
  225.             break;
  226.         ch = chr_decode(str, &index, UTF8_NO_LIMIT);
  227.         if (ch == '\0') break;
  228.  
  229.         size++;
  230.     }
  231.    
  232.     return iprev;
  233. }
  234.  
  235. /** Check whether character is plain ASCII.
  236.  *
  237.  * @return True if character is plain ASCII.
  238.  *
  239.  */
  240. bool ascii_check(const wchar_t ch)
  241. {
  242.     if ((ch >= 0) && (ch <= 127))
  243.         return true;
  244.    
  245.     return false;
  246. }
  247.  
  248. /** Check whether character is Unicode.
  249.  *
  250.  * @return True if character is valid Unicode code point.
  251.  *
  252.  */
  253. bool unicode_check(const wchar_t ch)
  254. {
  255.     if ((ch >= 0) && (ch <= 1114111))
  256.         return true;
  257.    
  258.     return false;
  259. }
  260.  
  261. /** Return number of plain characters in a string.
  262.  *
  263.  * @param str NULL-terminated string.
  264.  *
  265.  * @return Number of characters in str.
  266.  *
  267.  */
  268. size_t strlen(const char *str)
  269. {
  270.     size_t size;
  271.     for (size = 0; str[size]; size++);
  272.    
  273.     return size;
  274. }
  275.  
  276. /** Return number of UTF-8 characters in a string.
  277.  *
  278.  * @param str NULL-terminated UTF-8 string.
  279.  *
  280.  * @return Number of UTF-8 characters in str.
  281.  *
  282.  */
  283. size_t strlen_utf8(const char *str)
  284. {
  285.     size_t size = 0;
  286.     index_t index = 0;
  287.    
  288.     while (chr_decode(str, &index, UTF8_NO_LIMIT) != 0) {
  289.         size++;
  290.     }
  291.    
  292.     return size;
  293. }
  294.  
  295. /** Return number of UTF-32 characters in a string.
  296.  *
  297.  * @param str NULL-terminated UTF-32 string.
  298.  *
  299.  * @return Number of UTF-32 characters in str.
  300.  *
  301.  */
  302. size_t strlen_utf32(const wchar_t *str)
  303. {
  304.     size_t size;
  305.     for (size = 0; str[size]; size++);
  306.    
  307.     return size;
  308. }
  309.  
  310. /** Compare two NULL terminated strings
  311.  *
  312.  * Do a char-by-char comparison of two NULL terminated strings.
  313.  * The strings are considered equal iff they consist of the same
  314.  * characters on the minimum of their lengths.
  315.  *
  316.  * @param src First string to compare.
  317.  * @param dst Second string to compare.
  318.  *
  319.  * @return 0 if the strings are equal, -1 if first is smaller, 1 if second smaller.
  320.  *
  321.  */
  322. int strcmp(const char *src, const char *dst)
  323. {
  324.     for (; *src && *dst; src++, dst++) {
  325.         if (*src < *dst)
  326.             return -1;
  327.         if (*src > *dst)
  328.             return 1;
  329.     }
  330.     if (*src == *dst)
  331.         return 0;
  332.    
  333.     if (!*src)
  334.         return -1;
  335.    
  336.     return 1;
  337. }
  338.  
  339.  
  340. /** Compare two NULL terminated strings
  341.  *
  342.  * Do a char-by-char comparison of two NULL terminated strings.
  343.  * The strings are considered equal iff they consist of the same
  344.  * characters on the minimum of their lengths and specified maximal
  345.  * length.
  346.  *
  347.  * @param src First string to compare.
  348.  * @param dst Second string to compare.
  349.  * @param len Maximal length for comparison.
  350.  *
  351.  * @return 0 if the strings are equal, -1 if first is smaller, 1 if second smaller.
  352.  *
  353.  */
  354. int strncmp(const char *src, const char *dst, size_t len)
  355. {
  356.     unsigned int i;
  357.    
  358.     for (i = 0; (*src) && (*dst) && (i < len); src++, dst++, i++) {
  359.         if (*src < *dst)
  360.             return -1;
  361.        
  362.         if (*src > *dst)
  363.             return 1;
  364.     }
  365.    
  366.     if (i == len || *src == *dst)
  367.         return 0;
  368.    
  369.     if (!*src)
  370.         return -1;
  371.    
  372.     return 1;
  373. }
  374.  
  375.  
  376.  
  377. /** Copy NULL terminated string.
  378.  *
  379.  * Copy at most 'len' characters from string 'src' to 'dest'.
  380.  * If 'src' is shorter than 'len', '\0' is inserted behind the
  381.  * last copied character.
  382.  *
  383.  * @param src  Source string.
  384.  * @param dest Destination buffer.
  385.  * @param len  Size of destination buffer.
  386.  *
  387.  */
  388. void strncpy(char *dest, const char *src, size_t len)
  389. {
  390.     unsigned int i;
  391.    
  392.     for (i = 0; i < len; i++) {
  393.         if (!(dest[i] = src[i]))
  394.             return;
  395.     }
  396.    
  397.     dest[i - 1] = '\0';
  398. }
  399.  
  400. /** Find first occurence of character in string.
  401.  *
  402.  * @param s String to search.
  403.  * @param i Character to look for.
  404.  *
  405.  * @return Pointer to character in @a s or NULL if not found.
  406.  */
  407. extern char *strchr(const char *s, int i)
  408. {
  409.     while (*s != '\0') {
  410.         if (*s == i)
  411.             return (char *) s;
  412.         ++s;
  413.     }
  414.    
  415.     return NULL;
  416. }
  417.  
  418. /** @}
  419.  */
  420.