summaryrefslogtreecommitdiff
path: root/doc/libunistring_13.html
diff options
context:
space:
mode:
Diffstat (limited to 'doc/libunistring_13.html')
-rw-r--r--doc/libunistring_13.html105
1 files changed, 55 insertions, 50 deletions
diff --git a/doc/libunistring_13.html b/doc/libunistring_13.html
index 5dc6f854..4edcbca1 100644
--- a/doc/libunistring_13.html
+++ b/doc/libunistring_13.html
@@ -1,6 +1,6 @@
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html401/loose.dtd">
<html>
-<!-- Created on December, 2 2016 by texi2html 1.78a -->
+<!-- Created on November, 30 2017 by texi2html 1.78a -->
<!--
Written by: Lionel Cons <Lionel.Cons@cern.ch> (original author)
Karl Berry <karl@freefriends.org>
@@ -76,21 +76,21 @@ Unicode character.
</p>
<dl>
<dt><u>Constant:</u> int <b>UC_DECOMP_CANONICAL</b>
-<a name="IDX767"></a>
+<a name="IDX783"></a>
</dt>
<dd><p>Denotes canonical decomposition.
</p></dd></dl>
<dl>
<dt><u>Constant:</u> int <b>UC_DECOMP_FONT</b>
-<a name="IDX768"></a>
+<a name="IDX784"></a>
</dt>
<dd><p>UCD marker: <code>&lt;font&gt;</code>. Denotes a font variant (e.g. a blackletter form).
</p></dd></dl>
<dl>
<dt><u>Constant:</u> int <b>UC_DECOMP_NOBREAK</b>
-<a name="IDX769"></a>
+<a name="IDX785"></a>
</dt>
<dd><p>UCD marker: <code>&lt;noBreak&gt;</code>.
Denotes a no-break version of a space or hyphen.
@@ -98,7 +98,7 @@ Denotes a no-break version of a space or hyphen.
<dl>
<dt><u>Constant:</u> int <b>UC_DECOMP_INITIAL</b>
-<a name="IDX770"></a>
+<a name="IDX786"></a>
</dt>
<dd><p>UCD marker: <code>&lt;initial&gt;</code>.
Denotes an initial presentation form (Arabic).
@@ -106,7 +106,7 @@ Denotes an initial presentation form (Arabic).
<dl>
<dt><u>Constant:</u> int <b>UC_DECOMP_MEDIAL</b>
-<a name="IDX771"></a>
+<a name="IDX787"></a>
</dt>
<dd><p>UCD marker: <code>&lt;medial&gt;</code>.
Denotes a medial presentation form (Arabic).
@@ -114,7 +114,7 @@ Denotes a medial presentation form (Arabic).
<dl>
<dt><u>Constant:</u> int <b>UC_DECOMP_FINAL</b>
-<a name="IDX772"></a>
+<a name="IDX788"></a>
</dt>
<dd><p>UCD marker: <code>&lt;final&gt;</code>.
Denotes a final presentation form (Arabic).
@@ -122,7 +122,7 @@ Denotes a final presentation form (Arabic).
<dl>
<dt><u>Constant:</u> int <b>UC_DECOMP_ISOLATED</b>
-<a name="IDX773"></a>
+<a name="IDX789"></a>
</dt>
<dd><p>UCD marker: <code>&lt;isolated&gt;</code>.
Denotes an isolated presentation form (Arabic).
@@ -130,7 +130,7 @@ Denotes an isolated presentation form (Arabic).
<dl>
<dt><u>Constant:</u> int <b>UC_DECOMP_CIRCLE</b>
-<a name="IDX774"></a>
+<a name="IDX790"></a>
</dt>
<dd><p>UCD marker: <code>&lt;circle&gt;</code>.
Denotes an encircled form.
@@ -138,7 +138,7 @@ Denotes an encircled form.
<dl>
<dt><u>Constant:</u> int <b>UC_DECOMP_SUPER</b>
-<a name="IDX775"></a>
+<a name="IDX791"></a>
</dt>
<dd><p>UCD marker: <code>&lt;super&gt;</code>.
Denotes a superscript form.
@@ -146,7 +146,7 @@ Denotes a superscript form.
<dl>
<dt><u>Constant:</u> int <b>UC_DECOMP_SUB</b>
-<a name="IDX776"></a>
+<a name="IDX792"></a>
</dt>
<dd><p>UCD marker: <code>&lt;sub&gt;</code>.
Denotes a subscript form.
@@ -154,7 +154,7 @@ Denotes a subscript form.
<dl>
<dt><u>Constant:</u> int <b>UC_DECOMP_VERTICAL</b>
-<a name="IDX777"></a>
+<a name="IDX793"></a>
</dt>
<dd><p>UCD marker: <code>&lt;vertical&gt;</code>.
Denotes a vertical layout presentation form.
@@ -162,7 +162,7 @@ Denotes a vertical layout presentation form.
<dl>
<dt><u>Constant:</u> int <b>UC_DECOMP_WIDE</b>
-<a name="IDX778"></a>
+<a name="IDX794"></a>
</dt>
<dd><p>UCD marker: <code>&lt;wide&gt;</code>.
Denotes a wide (or zenkaku) compatibility character.
@@ -170,7 +170,7 @@ Denotes a wide (or zenkaku) compatibility character.
<dl>
<dt><u>Constant:</u> int <b>UC_DECOMP_NARROW</b>
-<a name="IDX779"></a>
+<a name="IDX795"></a>
</dt>
<dd><p>UCD marker: <code>&lt;narrow&gt;</code>.
Denotes a narrow (or hankaku) compatibility character.
@@ -178,7 +178,7 @@ Denotes a narrow (or hankaku) compatibility character.
<dl>
<dt><u>Constant:</u> int <b>UC_DECOMP_SMALL</b>
-<a name="IDX780"></a>
+<a name="IDX796"></a>
</dt>
<dd><p>UCD marker: <code>&lt;small&gt;</code>.
Denotes a small variant form (CNS compatibility).
@@ -186,7 +186,7 @@ Denotes a small variant form (CNS compatibility).
<dl>
<dt><u>Constant:</u> int <b>UC_DECOMP_SQUARE</b>
-<a name="IDX781"></a>
+<a name="IDX797"></a>
</dt>
<dd><p>UCD marker: <code>&lt;square&gt;</code>.
Denotes a CJK squared font variant.
@@ -194,7 +194,7 @@ Denotes a CJK squared font variant.
<dl>
<dt><u>Constant:</u> int <b>UC_DECOMP_FRACTION</b>
-<a name="IDX782"></a>
+<a name="IDX798"></a>
</dt>
<dd><p>UCD marker: <code>&lt;fraction&gt;</code>.
Denotes a vulgar fraction form.
@@ -202,7 +202,7 @@ Denotes a vulgar fraction form.
<dl>
<dt><u>Constant:</u> int <b>UC_DECOMP_COMPAT</b>
-<a name="IDX783"></a>
+<a name="IDX799"></a>
</dt>
<dd><p>UCD marker: <code>&lt;compat&gt;</code>.
Denotes an otherwise unspecified compatibility character.
@@ -213,7 +213,7 @@ Unicode character.
</p>
<dl>
<dt><u>Macro:</u> unsigned int <b>UC_DECOMPOSITION_MAX_LENGTH</b>
-<a name="IDX784"></a>
+<a name="IDX800"></a>
</dt>
<dd><p>This macro expands to a constant that is the required size of buffer passed to
the <code>uc_decomposition</code> and <code>uc_canonical_decomposition</code> functions.
@@ -223,7 +223,7 @@ the <code>uc_decomposition</code> and <code>uc_canonical_decomposition</code> fu
</p>
<dl>
<dt><u>Function:</u> int <b>uc_decomposition</b><i> (ucs4_t <var>uc</var>, int *<var>decomp_tag</var>, ucs4_t *<var>decomposition</var>)</i>
-<a name="IDX785"></a>
+<a name="IDX801"></a>
</dt>
<dd><p>Returns the character decomposition mapping of the Unicode character <var>uc</var>.
<var>decomposition</var> must point to an array of at least
@@ -236,7 +236,7 @@ returned.
<dl>
<dt><u>Function:</u> int <b>uc_canonical_decomposition</b><i> (ucs4_t <var>uc</var>, ucs4_t *<var>decomposition</var>)</i>
-<a name="IDX786"></a>
+<a name="IDX802"></a>
</dt>
<dd><p>Returns the canonical character decomposition mapping of the Unicode character
<var>uc</var>. <var>decomposition</var> must point to an array of at least
@@ -244,6 +244,11 @@ returned.
</p>
<p>When a decomposition exists, <code><var>decomposition</var>[0..<var>n</var>-1]</code> is filled
and <var>n</var> is returned. Otherwise -1 is returned.
+</p>
+<p>Note: This function returns the (simple) &ldquo;canonical decomposition&rdquo; of
+<var>uc</var>. If you want the &ldquo;full canonical decomposition&rdquo; of <var>uc</var>,
+that is, the recursive application of &ldquo;canonical decomposition&rdquo;, use the
+function <code>u*_normalize</code> with argument <code>UNINORM_NFD</code> instead.
</p></dd></dl>
<hr size="6">
@@ -256,7 +261,7 @@ characters.
</p>
<dl>
<dt><u>Function:</u> ucs4_t <b>uc_composition</b><i> (ucs4_t <var>uc1</var>, ucs4_t <var>uc2</var>)</i>
-<a name="IDX787"></a>
+<a name="IDX803"></a>
</dt>
<dd><p>Attempts to combine the Unicode characters <var>uc1</var>, <var>uc2</var>.
<var>uc1</var> is known to have canonical combining class 0.
@@ -278,7 +283,7 @@ The following type is used to denote a normalization form.
</p>
<dl>
<dt><u>Type:</u> <b>uninorm_t</b>
-<a name="IDX788"></a>
+<a name="IDX804"></a>
</dt>
<dd><p>An object of type <code>uninorm_t</code> denotes a Unicode normalization form.
This is a scalar type; its values can be compared with <code>==</code>.
@@ -288,28 +293,28 @@ This is a scalar type; its values can be compared with <code>==</code>.
</p>
<dl>
<dt><u>Macro:</u> uninorm_t <b>UNINORM_NFD</b>
-<a name="IDX789"></a>
+<a name="IDX805"></a>
</dt>
<dd><p>Denotes Normalization form D: canonical decomposition.
</p></dd></dl>
<dl>
<dt><u>Macro:</u> uninorm_t <b>UNINORM_NFC</b>
-<a name="IDX790"></a>
+<a name="IDX806"></a>
</dt>
<dd><p>Normalization form C: canonical decomposition, then canonical composition.
</p></dd></dl>
<dl>
<dt><u>Macro:</u> uninorm_t <b>UNINORM_NFKD</b>
-<a name="IDX791"></a>
+<a name="IDX807"></a>
</dt>
<dd><p>Normalization form KD: compatibility decomposition.
</p></dd></dl>
<dl>
<dt><u>Macro:</u> uninorm_t <b>UNINORM_NFKC</b>
-<a name="IDX792"></a>
+<a name="IDX808"></a>
</dt>
<dd><p>Normalization form KC: compatibility decomposition, then canonical composition.
</p></dd></dl>
@@ -318,21 +323,21 @@ This is a scalar type; its values can be compared with <code>==</code>.
</p>
<dl>
<dt><u>Function:</u> bool <b>uninorm_is_compat_decomposing</b><i> (uninorm_t <var>nf</var>)</i>
-<a name="IDX793"></a>
+<a name="IDX809"></a>
</dt>
<dd><p>Tests whether the normalization form <var>nf</var> does compatibility decomposition.
</p></dd></dl>
<dl>
<dt><u>Function:</u> bool <b>uninorm_is_composing</b><i> (uninorm_t <var>nf</var>)</i>
-<a name="IDX794"></a>
+<a name="IDX810"></a>
</dt>
<dd><p>Tests whether the normalization form <var>nf</var> includes canonical composition.
</p></dd></dl>
<dl>
<dt><u>Function:</u> uninorm_t <b>uninorm_decomposing_form</b><i> (uninorm_t <var>nf</var>)</i>
-<a name="IDX795"></a>
+<a name="IDX811"></a>
</dt>
<dd><p>Returns the decomposing variant of the normalization form <var>nf</var>.
This maps NFC,NFD → NFD and NFKC,NFKD → NFKD.
@@ -342,13 +347,13 @@ This maps NFC,NFD → NFD and NFKC,NFKD → NFKD.
</p>
<dl>
<dt><u>Function:</u> uint8_t * <b>u8_normalize</b><i> (uninorm_t <var>nf</var>, const uint8_t *<var>s</var>, size_t <var>n</var>, uint8_t *<var>resultbuf</var>, size_t *<var>lengthp</var>)</i>
-<a name="IDX796"></a>
+<a name="IDX812"></a>
</dt>
<dt><u>Function:</u> uint16_t * <b>u16_normalize</b><i> (uninorm_t <var>nf</var>, const uint16_t *<var>s</var>, size_t <var>n</var>, uint16_t *<var>resultbuf</var>, size_t *<var>lengthp</var>)</i>
-<a name="IDX797"></a>
+<a name="IDX813"></a>
</dt>
<dt><u>Function:</u> uint32_t * <b>u32_normalize</b><i> (uninorm_t <var>nf</var>, const uint32_t *<var>s</var>, size_t <var>n</var>, uint32_t *<var>resultbuf</var>, size_t *<var>lengthp</var>)</i>
-<a name="IDX798"></a>
+<a name="IDX814"></a>
</dt>
<dd><p>Returns the specified normalization form of a string.
</p></dd></dl>
@@ -363,13 +368,13 @@ normalization.
</p>
<dl>
<dt><u>Function:</u> int <b>u8_normcmp</b><i> (const uint8_t *<var>s1</var>, size_t <var>n1</var>, const uint8_t *<var>s2</var>, size_t <var>n2</var>, uninorm_t <var>nf</var>, int *<var>resultp</var>)</i>
-<a name="IDX799"></a>
+<a name="IDX815"></a>
</dt>
<dt><u>Function:</u> int <b>u16_normcmp</b><i> (const uint16_t *<var>s1</var>, size_t <var>n1</var>, const uint16_t *<var>s2</var>, size_t <var>n2</var>, uninorm_t <var>nf</var>, int *<var>resultp</var>)</i>
-<a name="IDX800"></a>
+<a name="IDX816"></a>
</dt>
<dt><u>Function:</u> int <b>u32_normcmp</b><i> (const uint32_t *<var>s1</var>, size_t <var>n1</var>, const uint32_t *<var>s2</var>, size_t <var>n2</var>, uninorm_t <var>nf</var>, int *<var>resultp</var>)</i>
-<a name="IDX801"></a>
+<a name="IDX817"></a>
</dt>
<dd><p>Compares <var>s1</var> and <var>s2</var>, ignoring differences in normalization.
</p>
@@ -380,17 +385,17 @@ normalization.
Upon failure, returns -1 with <code>errno</code> set.
</p></dd></dl>
-<a name="IDX802"></a>
-<a name="IDX803"></a>
+<a name="IDX818"></a>
+<a name="IDX819"></a>
<dl>
<dt><u>Function:</u> char * <b>u8_normxfrm</b><i> (const uint8_t *<var>s</var>, size_t <var>n</var>, uninorm_t <var>nf</var>, char *<var>resultbuf</var>, size_t *<var>lengthp</var>)</i>
-<a name="IDX804"></a>
+<a name="IDX820"></a>
</dt>
<dt><u>Function:</u> char * <b>u16_normxfrm</b><i> (const uint16_t *<var>s</var>, size_t <var>n</var>, uninorm_t <var>nf</var>, char *<var>resultbuf</var>, size_t *<var>lengthp</var>)</i>
-<a name="IDX805"></a>
+<a name="IDX821"></a>
</dt>
<dt><u>Function:</u> char * <b>u32_normxfrm</b><i> (const uint32_t *<var>s</var>, size_t <var>n</var>, uninorm_t <var>nf</var>, char *<var>resultbuf</var>, size_t *<var>lengthp</var>)</i>
-<a name="IDX806"></a>
+<a name="IDX822"></a>
</dt>
<dd><p>Converts the string <var>s</var> of length <var>n</var> to a NUL-terminated byte
sequence, in such a way that comparing <code>u8_normxfrm (<var>s1</var>)</code> and
@@ -402,13 +407,13 @@ comparing <var>s1</var> and <var>s2</var> with the <code>u8_normcoll</code> func
<dl>
<dt><u>Function:</u> int <b>u8_normcoll</b><i> (const uint8_t *<var>s1</var>, size_t <var>n1</var>, const uint8_t *<var>s2</var>, size_t <var>n2</var>, uninorm_t <var>nf</var>, int *<var>resultp</var>)</i>
-<a name="IDX807"></a>
+<a name="IDX823"></a>
</dt>
<dt><u>Function:</u> int <b>u16_normcoll</b><i> (const uint16_t *<var>s1</var>, size_t <var>n1</var>, const uint16_t *<var>s2</var>, size_t <var>n2</var>, uninorm_t <var>nf</var>, int *<var>resultp</var>)</i>
-<a name="IDX808"></a>
+<a name="IDX824"></a>
</dt>
<dt><u>Function:</u> int <b>u32_normcoll</b><i> (const uint32_t *<var>s1</var>, size_t <var>n1</var>, const uint32_t *<var>s2</var>, size_t <var>n2</var>, uninorm_t <var>nf</var>, int *<var>resultp</var>)</i>
-<a name="IDX809"></a>
+<a name="IDX825"></a>
</dt>
<dd><p>Compares <var>s1</var> and <var>s2</var>, ignoring differences in normalization, using
the collation rules of the current locale.
@@ -431,7 +436,7 @@ Upon failure, returns -1 with <code>errno</code> set.
</p>
<dl>
<dt><u>Type:</u> <b>struct uninorm_filter</b>
-<a name="IDX810"></a>
+<a name="IDX826"></a>
</dt>
<dd><p>This is the data type of a stream of Unicode characters that normalizes its
input according to a given normalization form and passes the normalized
@@ -440,7 +445,7 @@ character sequence to the encapsulated stream of Unicode characters.
<dl>
<dt><u>Function:</u> struct uninorm_filter * <b>uninorm_filter_create</b><i> (uninorm_t <var>nf</var>, int (*<var>stream_func</var>) (void *<var>stream_data</var>, ucs4_t <var>uc</var>), void *<var>stream_data</var>)</i>
-<a name="IDX811"></a>
+<a name="IDX827"></a>
</dt>
<dd><p>Creates and returns a normalization filter for Unicode characters.
</p>
@@ -454,7 +459,7 @@ upon failure.
<dl>
<dt><u>Function:</u> int <b>uninorm_filter_write</b><i> (struct uninorm_filter *<var>filter</var>, ucs4_t <var>uc</var>)</i>
-<a name="IDX812"></a>
+<a name="IDX828"></a>
</dt>
<dd><p>Stuffs a Unicode character into a normalizing filter.
Returns 0 if successful, or -1 with <code>errno</code> set upon failure.
@@ -462,7 +467,7 @@ Returns 0 if successful, or -1 with <code>errno</code> set upon failure.
<dl>
<dt><u>Function:</u> int <b>uninorm_filter_flush</b><i> (struct uninorm_filter *<var>filter</var>)</i>
-<a name="IDX813"></a>
+<a name="IDX829"></a>
</dt>
<dd><p>Brings data buffered in the filter to its destination, the encapsulated stream.
</p>
@@ -475,7 +480,7 @@ will not necessarily be normalized.
<dl>
<dt><u>Function:</u> int <b>uninorm_filter_free</b><i> (struct uninorm_filter *<var>filter</var>)</i>
-<a name="IDX814"></a>
+<a name="IDX830"></a>
</dt>
<dd><p>Brings data buffered in the filter to its destination, the encapsulated stream,
then closes and frees the filter.
@@ -498,7 +503,7 @@ then closes and frees the filter.
</tr></table>
<p>
<font size="-1">
- This document was generated by <em>Daiki Ueno</em> on <em>December, 2 2016</em> using <a href="http://www.nongnu.org/texi2html/"><em>texi2html 1.78a</em></a>.
+ This document was generated by <em>Daiki Ueno</em> on <em>November, 30 2017</em> using <a href="http://www.nongnu.org/texi2html/"><em>texi2html 1.78a</em></a>.
</font>
<br>