{"id":7077,"date":"2022-12-20T19:35:12","date_gmt":"2022-12-20T22:35:12","guid":{"rendered":"http:\/\/lode.uno\/linux-man\/index.php\/2022\/12\/20\/utf-man3-3\/"},"modified":"2022-12-20T19:35:12","modified_gmt":"2022-12-20T22:35:12","slug":"utf-man3-3","status":"publish","type":"post","link":"https:\/\/lode.uno\/linux-man\/2022\/12\/20\/utf-man3-3\/","title":{"rendered":"Utf (man3)"},"content":{"rendered":"

Utf<\/h1>\n

NAME<\/a>
SYNOPSIS<\/a>
ARGUMENTS<\/a>
DESCRIPTION<\/a>
KEYWORDS<\/a> <\/p>\n

\n

______________________________________________________________________________<\/p>\n

NAME <\/a> <\/h2>\n

Tcl_UniChar, Tcl_UniCharToUtf, Tcl_UtfToUniChar, Tcl_UniCharToUtfDString, Tcl_UtfToUniCharDString, Tcl_UniCharLen, Tcl_UniCharNcmp, Tcl_UniCharNcasecmp, Tcl_UniCharCaseMatch, Tcl_UtfNcmp, Tcl_UtfNcasecmp, Tcl_UtfCharComplete, Tcl_NumUtfChars, Tcl_UtfFindFirst, Tcl_UtfFindLast, Tcl_UtfNext, Tcl_UtfPrev, Tcl_UniCharAtIndex, Tcl_UtfAtIndex, Tcl_UtfBackslash \u2212 routines for manipulating UTF-8 strings<\/p>\n

SYNOPSIS <\/a> <\/h2>\n

#include <\/b><\/p>\n

typedef … Tcl_UniChar<\/b>;<\/p>\n

int
Tcl_UniCharToUtf<\/b>(ch, buf<\/i>)<\/p>\n

int
Tcl_UtfToUniChar<\/b>(src, chPtr<\/i>)<\/p>\n

char bodies manpages.csv script_extrae_body.sh script.sh usr
Tcl_UniCharToUtfDString<\/b>(uniStr, uniLength, dsPtr<\/i>)<\/p>\n

Tcl_UniChar bodies manpages.csv script_extrae_body.sh script.sh usr
Tcl_UtfToUniCharDString<\/b>(src, length, dsPtr<\/i>)<\/p>\n

int
Tcl_UniCharLen<\/b>(uniStr<\/i>)<\/p>\n

int
Tcl_UniCharNcmp<\/b>(ucs, uct, numChars<\/i>)<\/p>\n

int
Tcl_UniCharNcasecmp<\/b>(ucs, uct, numChars<\/i>)<\/p>\n

int
Tcl_UniCharCaseMatch<\/b>(uniStr, uniPattern, nocase<\/i>)<\/p>\n

int
Tcl_UtfNcmp<\/b>(cs, ct, numChars<\/i>)<\/p>\n

int
Tcl_UtfNcasecmp<\/b>(cs, ct, numChars<\/i>)<\/p>\n

int
Tcl_UtfCharComplete<\/b>(src, length<\/i>)<\/p>\n

int
Tcl_NumUtfChars<\/b>(src, length<\/i>)<\/p>\n

const char bodies manpages.csv script_extrae_body.sh script.sh usr
Tcl_UtfFindFirst<\/b>(src, ch<\/i>)<\/p>\n

const char bodies manpages.csv script_extrae_body.sh script.sh usr
Tcl_UtfFindLast<\/b>(src, ch<\/i>)<\/p>\n

const char bodies manpages.csv script_extrae_body.sh script.sh usr
Tcl_UtfNext<\/b>(src<\/i>)<\/p>\n

const char bodies manpages.csv script_extrae_body.sh script.sh usr
Tcl_UtfPrev<\/b>(src, start<\/i>)<\/p>\n

Tcl_UniChar
Tcl_UniCharAtIndex<\/b>(src, index<\/i>)<\/p>\n

const char bodies manpages.csv script_extrae_body.sh script.sh usr
Tcl_UtfAtIndex<\/b>(src, index<\/i>)<\/p>\n

int
Tcl_UtfBackslash<\/b>(src, readPtr, dst<\/i>)<\/p>\n

ARGUMENTS <\/a> <\/h2>\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
<\/td>\n\n

char *buf<\/i> (out)<\/p>\n<\/td>\n

<\/td>\n\n

Buffer in which the UTF-8 representation of the Tcl_UniChar is stored. At most TCL_UTF_MAX<\/b> bytes are stored in the buffer.<\/p>\n<\/td>\n<\/tr>\n

<\/td>\n\n

int ch<\/i> (in)<\/p>\n<\/td>\n

<\/td>\n\n

The Unicode character to be converted or examined.<\/p>\n<\/td>\n<\/tr>\n

<\/td>\n\n

Tcl_UniChar *chPtr<\/i> (out)<\/p>\n<\/td>\n

<\/td>\n\n

Filled with the Tcl_UniChar represented by the head of the UTF-8 string.<\/p>\n<\/td>\n<\/tr>\n

<\/td>\n\n

const char *src<\/i> (in)<\/p>\n<\/td>\n

<\/td>\n\n

Pointer to a UTF-8 string.<\/p>\n<\/td>\n<\/tr>\n

<\/td>\n\n

const char *cs<\/i> (in)<\/p>\n<\/td>\n

<\/td>\n\n

Pointer to a UTF-8 string.<\/p>\n<\/td>\n<\/tr>\n

<\/td>\n\n

const char *ct<\/i> (in)<\/p>\n<\/td>\n

<\/td>\n\n

Pointer to a UTF-8 string.<\/p>\n<\/td>\n<\/tr>\n

<\/td>\n\n

const Tcl_UniChar *uniStr<\/i> (in)<\/p>\n<\/td>\n

<\/td>\n\n

A null-terminated Unicode string.<\/p>\n<\/td>\n<\/tr>\n

<\/td>\n\n

const Tcl_UniChar *ucs<\/i> (in)<\/p>\n<\/td>\n

<\/td>\n\n

A null-terminated Unicode string.<\/p>\n<\/td>\n<\/tr>\n

<\/td>\n\n

const Tcl_UniChar *uct<\/i> (in)<\/p>\n<\/td>\n

<\/td>\n\n

A null-terminated Unicode string.<\/p>\n<\/td>\n<\/tr>\n

<\/td>\n\n

const Tcl_UniChar *uniPattern<\/i> (in)<\/p>\n<\/td>\n

<\/td>\n\n

A null-terminated Unicode string.<\/p>\n<\/td>\n<\/tr>\n

<\/td>\n\n

int length<\/i> (in)<\/p>\n<\/td>\n

<\/td>\n\n

The length of the UTF-8 string in bytes (not UTF-8 characters). If negative, all bytes up to the first null byte are used.<\/p>\n<\/td>\n<\/tr>\n

<\/td>\n\n

int uniLength<\/i> (in)<\/p>\n<\/td>\n

<\/td>\n\n

The length of the Unicode string in characters. Must be greater than or equal to 0.<\/p>\n<\/td>\n<\/tr>\n

<\/td>\n\n

Tcl_DString *dsPtr<\/i> (in\/out)<\/p>\n<\/td>\n

<\/td>\n\n

A pointer to a previously initialized Tcl_DString<\/b>.<\/p>\n<\/td>\n<\/tr>\n

<\/td>\n\n

unsigned long numChars<\/i> (in)<\/p>\n<\/td>\n

<\/td>\n\n

The number of characters to compare.<\/p>\n<\/td>\n<\/tr>\n

<\/td>\n\n

const char *start<\/i> (in)<\/p>\n<\/td>\n

<\/td>\n\n

Pointer to the beginning of a UTF-8 string.<\/p>\n<\/td>\n<\/tr>\n

<\/td>\n\n

int index<\/i> (in)<\/p>\n<\/td>\n

<\/td>\n\n

The index of a character (not byte) in the UTF-8 string.<\/p>\n<\/td>\n<\/tr>\n

<\/td>\n\n

int *readPtr<\/i> (out)<\/p>\n<\/td>\n

<\/td>\n\n

If non-NULL, filled with the number of bytes in the backslash sequence, including the backslash character.<\/p>\n<\/td>\n<\/tr>\n

<\/td>\n\n

char *dst<\/i> (out)<\/p>\n<\/td>\n

<\/td>\n\n

Buffer in which the bytes represented by the backslash sequence are stored. At most TCL_UTF_MAX<\/b> bytes are stored in the buffer.<\/p>\n<\/td>\n<\/tr>\n

<\/td>\n\n

int nocase<\/i> (in)<\/p>\n<\/td>\n

<\/td>\n\n

Specifies whether the match should be done case-sensitive (0) or case-insensitive (1).<\/p>\n<\/td>\n<\/tr>\n<\/table>\n

______________________________________________________________________________<\/p>\n

DESCRIPTION <\/a> <\/h2>\n

These routines convert between UTF-8 strings and Tcl_UniChars. A Tcl_UniChar is a Unicode character represented as an unsigned, fixed-size quantity. A UTF-8 character is a Unicode character represented as a varying-length sequence of up to TCL_UTF_MAX<\/b> bytes. A multibyte UTF-8 sequence consists of a lead byte followed by some number of trail bytes.<\/p>\n

TCL_UTF_MAX<\/b> is the maximum number of bytes that it takes to represent one Unicode character in the UTF-8 representation.<\/p>\n

Tcl_UniCharToUtf<\/b> stores the Tcl_UniChar ch<\/i> as a UTF-8 string in starting at buf<\/i>. The return value is the number of bytes stored in buf<\/i>.<\/p>\n

Tcl_UtfToUniChar<\/b> reads one UTF-8 character starting at src<\/i> and stores it as a Tcl_UniChar in *chPtr<\/i>. The return value is the number of bytes read from src<\/i>. The caller must ensure that the source buffer is long enough such that this routine does not run off the end and dereference non-existent or random memory; if the source buffer is known to be null-terminated, this will not happen. If the input is not in proper UTF-8 format, Tcl_UtfToUniChar<\/b> will store the first byte of src<\/i> in *chPtr<\/i> as a Tcl_UniChar between 0x0000 and 0x00ff and return 1.<\/p>\n

Tcl_UniCharToUtfDString<\/b> converts the given Unicode string to UTF-8, storing the result in a previously initialized Tcl_DString<\/b>. You must specify uniLength<\/i>, the length of the given Unicode string. The return value is a pointer to the UTF-8 representation of the Unicode string. Storage for the return value is appended to the end of the Tcl_DString<\/b>.<\/p>\n

Tcl_UtfToUniCharDString<\/b> converts the given UTF-8 string to Unicode, storing the result in the previously initialized Tcl_DString<\/b>. In the argument length<\/i>, you may either specify the length of the given UTF-8 string in bytes or \u201c\u22121\u201d, in which case Tcl_UtfToUniCharDString<\/b> uses strlen<\/b> to calculate the length. The return value is a pointer to the Unicode representation of the UTF-8 string. Storage for the return value is appended to the end of the Tcl_DString<\/b>. The Unicode string is terminated with a Unicode null character.<\/p>\n

Tcl_UniCharLen<\/b> corresponds to strlen<\/b> for Unicode characters. It accepts a null-terminated Unicode string and returns the number of Unicode characters (not bytes) in that string.<\/p>\n

Tcl_UniCharNcmp<\/b> and Tcl_UniCharNcasecmp<\/b> correspond to strncmp<\/b> and strncasecmp<\/b>, respectively, for Unicode characters. They accept two null-terminated Unicode strings and the number of characters to compare. Both strings are assumed to be at least numChars<\/i> characters long. Tcl_UniCharNcmp<\/b> compares the two strings character-by-character according to the Unicode character ordering. It returns an integer greater than, equal to, or less than 0 if the first string is greater than, equal to, or less than the second string respectively. Tcl_UniCharNcasecmp<\/b> is the Unicode case insensitive version.<\/p>\n

Tcl_UniCharCaseMatch<\/b> is the Unicode equivalent to Tcl_StringCaseMatch<\/b>. It accepts a null-terminated Unicode string, a Unicode pattern, and a boolean value specifying whether the match should be case sensitive and returns whether the string matches the pattern.<\/p>\n

Tcl_UtfNcmp<\/b> corresponds to strncmp<\/b> for UTF-8 strings. It accepts two null-terminated UTF-8 strings and the number of characters to compare. (Both strings are assumed to be at least numChars<\/i> characters long.) Tcl_UtfNcmp<\/b> compares the two strings character-by-character according to the Unicode character ordering. It returns an integer greater than, equal to, or less than 0 if the first string is greater than, equal to, or less than the second string respectively.<\/p>\n

Tcl_UtfNcasecmp<\/b> corresponds to strncasecmp<\/b> for UTF-8 strings. It is similar to Tcl_UtfNcmp<\/b> except comparisons ignore differences in case when comparing upper, lower or title case characters.<\/p>\n

Tcl_UtfCharComplete<\/b> returns 1 if the source UTF-8 string src<\/i> of length<\/i> bytes is long enough to be decoded by Tcl_UtfToUniChar<\/b>, or 0 otherwise. This function does not guarantee that the UTF-8 string is properly formed. This routine is used by procedures that are operating on a byte at a time and need to know if a full Tcl_UniChar has been seen.<\/p>\n

Tcl_NumUtfChars<\/b> corresponds to strlen<\/b> for UTF-8 strings. It returns the number of Tcl_UniChars that are represented by the UTF-8 string src<\/i>. The length of the source string is length<\/i> bytes. If the length is negative, all bytes up to the first null byte are used.<\/p>\n

Tcl_UtfFindFirst<\/b> corresponds to strchr<\/b> for UTF-8 strings. It returns a pointer to the first occurrence of the Tcl_UniChar ch<\/i> in the null-terminated UTF-8 string src<\/i>. The null terminator is considered part of the UTF-8 string.<\/p>\n

Tcl_UtfFindLast<\/b> corresponds to strrchr<\/b> for UTF-8 strings. It returns a pointer to the last occurrence of the Tcl_UniChar ch<\/i> in the null-terminated UTF-8 string src<\/i>. The null terminator is considered part of the UTF-8 string.<\/p>\n

Given src<\/i>, a pointer to some location in a UTF-8 string, Tcl_UtfNext<\/b> returns a pointer to the next UTF-8 character in the string. The caller must not ask for the next character after the last character in the string if the string is not terminated by a null character.<\/p>\n

Given src<\/i>, a pointer to some location in a UTF-8 string (or to a null byte immediately following such a string), Tcl_UtfPrev<\/b> returns a pointer to the closest preceding byte that starts a UTF-8 character. This function will not back up to a position before start<\/i>, the start of the UTF-8 string. If src<\/i> was already at start<\/i>, the return value will be start<\/i>.<\/p>\n

Tcl_UniCharAtIndex<\/b> corresponds to a C string array dereference or the Pascal Ord() function. It returns the Tcl_UniChar represented at the specified character (not byte) index<\/i> in the UTF-8 string src<\/i>. The source string must contain at least index<\/i> characters. Behavior is undefined if a negative index<\/i> is given.<\/p>\n

Tcl_UtfAtIndex<\/b> returns a pointer to the specified character (not byte) index<\/i> in the UTF-8 string src<\/i>. The source string must contain at least index<\/i> characters. This is equivalent to calling Tcl_UtfNext<\/b> index<\/i> times. If a negative index<\/i> is given, the return pointer points to the first character in the source string.<\/p>\n

Tcl_UtfBackslash<\/b> is a utility procedure used by several of the Tcl commands. It parses a backslash sequence and stores the properly formed UTF-8 character represented by the backslash sequence in the output buffer dst<\/i>. At most TCL_UTF_MAX<\/b> bytes are stored in the buffer. Tcl_UtfBackslash<\/b> modifies *readPtr<\/i> to contain the number of bytes in the backslash sequence, including the backslash character. The return value is the number of bytes stored in the output buffer.<\/p>\n

See the Tcl<\/b> manual entry for information on the valid backslash sequences. All of the sequences described in the Tcl manual entry are supported by Tcl_UtfBackslash<\/b>.<\/p>\n

KEYWORDS <\/a> <\/h2>\n

utf, unicode, backslash<\/p>\n

\n","protected":false},"excerpt":{"rendered":"

Tcl_UniChar, Tcl_UniCharToUtf, Tcl_UtfToUniChar, Tcl_UniCharToUtfDString, Tcl_UtfToUniCharDString, Tcl_UniCharLen, Tcl_UniCharNcmp, Tcl_UniCharNcasecmp, Tcl_UniCharCaseMatch, Tcl_UtfNcmp, Tcl_UtfNcasecmp, Tcl_UtfCharComplete, Tcl_NumUtfChars, Tcl_UtfFindFirst, Tcl_UtfFindLast, Tcl_UtfNext, Tcl_UtfPrev, Tcl_UniCharAtIndex, Tcl_UtfAtIndex, Tcl_UtfBackslash \u2212 routines for manipulating UTF-8 strings <\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2536],"tags":[2538,3007,3421],"class_list":["post-7077","post","type-post","status-publish","format-standard","hentry","category-3-llamadas-de-bibliotecas","tag-2538","tag-man3","tag-tcl_unicharatindex"],"gutentor_comment":0,"_links":{"self":[{"href":"https:\/\/lode.uno\/linux-man\/wp-json\/wp\/v2\/posts\/7077","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lode.uno\/linux-man\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lode.uno\/linux-man\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lode.uno\/linux-man\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/lode.uno\/linux-man\/wp-json\/wp\/v2\/comments?post=7077"}],"version-history":[{"count":0,"href":"https:\/\/lode.uno\/linux-man\/wp-json\/wp\/v2\/posts\/7077\/revisions"}],"wp:attachment":[{"href":"https:\/\/lode.uno\/linux-man\/wp-json\/wp\/v2\/media?parent=7077"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lode.uno\/linux-man\/wp-json\/wp\/v2\/categories?post=7077"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lode.uno\/linux-man\/wp-json\/wp\/v2\/tags?post=7077"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}