golden hour

/opt/alt/libicu/usr/include/unicode

File/Folder	Size	Actions
alphaindex.h	26.42 KB
appendable.h	8.43 KB
basictz.h	8.84 KB
brkiter.h	27.53 KB
bytestream.h	9.54 KB
bytestrie.h	19.26 KB
bytestriebuilder.h	7.02 KB
calendar.h	105.06 KB
caniter.h	7.37 KB
casemap.h	25.26 KB
char16ptr.h	7.16 KB
chariter.h	24 KB
choicfmt.h	23.85 KB
coleitr.h	13.7 KB
coll.h	55.59 KB
compactdecimalformat.h	6.81 KB
curramt.h	3.69 KB
currpinf.h	7.24 KB
currunit.h	3.52 KB
datefmt.h	40.37 KB
dbbi.h	1.11 KB
dcfmtsym.h	20.1 KB
decimfmt.h	86.4 KB
docmain.h	6.72 KB
dtfmtsym.h	37.64 KB
dtintrv.h	3.76 KB
dtitvfmt.h	42.87 KB
dtitvinf.h	18.46 KB
dtptngen.h	25.03 KB
dtrule.h	8.62 KB
edits.h	20.67 KB
enumset.h	2.08 KB
errorcode.h	4.78 KB
fieldpos.h	8.63 KB
filteredbrk.h	5.24 KB
fmtable.h	24.36 KB
format.h	12.44 KB
fpositer.h	2.98 KB
gender.h	3.27 KB
gregocal.h	31.57 KB
icudataver.h	1.03 KB
icuplug.h	11.88 KB
idna.h	12.63 KB
listformatter.h	6.18 KB
localpointer.h	16.88 KB
locdspnm.h	7.05 KB
locid.h	44.92 KB
measfmt.h	12.01 KB
measunit.h	38.5 KB
measure.h	4.26 KB
messagepattern.h	33.65 KB
msgfmt.h	43.36 KB
normalizer2.h	33.97 KB
normlzr.h	30.74 KB
nounit.h	2.63 KB
numberformatter.h	87.07 KB
numberrangeformatter.h	28.74 KB
numfmt.h	49.14 KB
numsys.h	6.73 KB
parseerr.h	3.08 KB
parsepos.h	5.45 KB
platform.h	27.1 KB
plurfmt.h	25.18 KB
plurrule.h	17.42 KB
ptypes.h	3.49 KB
putil.h	6.33 KB
rbbi.h	26.41 KB
rbnf.h	49.79 KB
rbtz.h	15.47 KB
regex.h	84.91 KB
region.h	9.12 KB
reldatefmt.h	14.46 KB
rep.h	9.5 KB
resbund.h	18.01 KB
schriter.h	6.26 KB
scientificnumberformatter.h	6.32 KB
search.h	22.21 KB
selfmt.h	14.24 KB
simpleformatter.h	11.43 KB
simpletz.h	45.3 KB
smpdtfmt.h	70.74 KB
sortkey.h	11.12 KB
std_string.h	1015 B
strenum.h	10.04 KB
stringoptions.h	5.79 KB
stringpiece.h	6.46 KB
stringtriebuilder.h	15.27 KB
stsearch.h	21.29 KB
symtable.h	4.21 KB
tblcoll.h	36.4 KB
timezone.h	40.88 KB
tmunit.h	3.29 KB
tmutamt.h	4.8 KB
tmutfmt.h	7.79 KB
translit.h	65.76 KB
tzfmt.h	42.82 KB
tznames.h	16.79 KB
tzrule.h	35.32 KB
tztrans.h	6.07 KB
ubidi.h	89.56 KB
ubiditransform.h	12.65 KB
ubrk.h	23.97 KB
ucal.h	55.2 KB
ucasemap.h	15.18 KB
ucat.h	5.36 KB
uchar.h	139.96 KB
ucharstrie.h	21.06 KB
ucharstriebuilder.h	7.14 KB
uchriter.h	13.14 KB
uclean.h	11.21 KB
ucnv.h	83.09 KB
ucnv_cb.h	6.59 KB
ucnv_err.h	20.99 KB
ucnvsel.h	6.14 KB
ucol.h	61.39 KB
ucoleitr.h	9.46 KB
uconfig.h	11.67 KB
ucpmap.h	5.58 KB
ucptrie.h	22.29 KB
ucsdet.h	14.67 KB
ucurr.h	15.57 KB
udat.h	60.13 KB
udata.h	15.53 KB
udateintervalformat.h	6.79 KB
udatpg.h	26.04 KB
udisplaycontext.h	5.89 KB
uenum.h	7.78 KB
ufieldpositer.h	4.36 KB
uformattable.h	10.94 KB
ugender.h	2 KB
uidna.h	33.37 KB
uiter.h	22.77 KB
uldnames.h	10.45 KB
ulistformatter.h	5.03 KB
uloc.h	50.75 KB
ulocdata.h	11.26 KB
umachine.h	13.19 KB
umisc.h	1.33 KB
umsg.h	24.23 KB
umutablecptrie.h	8.28 KB
unifilt.h	3.63 KB
unifunct.h	3.98 KB
unimatch.h	6.04 KB
unirepl.h	3.32 KB
uniset.h	64.25 KB
unistr.h	174.4 KB
unorm.h	20.45 KB
unorm2.h	24.66 KB
unum.h	53.38 KB
unumberformatter.h	23.76 KB
unumsys.h	7.14 KB
uobject.h	10.7 KB
upluralrules.h	6.72 KB
uregex.h	72.05 KB
uregion.h	9.84 KB
ureldatefmt.h	12.22 KB
urename.h	127.73 KB
urep.h	5.38 KB
ures.h	36.53 KB
uscript.h	26.52 KB
usearch.h	38.12 KB
uset.h	40 KB
usetiter.h	9.49 KB
ushape.h	18 KB
uspoof.h	66.03 KB
usprep.h	8.14 KB
ustdio.h	38.54 KB
ustream.h	1.8 KB
ustring.h	72.47 KB
ustringtrie.h	3.15 KB
utext.h	58.11 KB
utf.h	7.86 KB
utf16.h	22.33 KB
utf32.h	763 B
utf8.h	30.01 KB
utf_old.h	43.78 KB
utmscale.h	13.78 KB
utrace.h	13.89 KB
utrans.h	25.54 KB
utypes.h	30.48 KB
uvernum.h	6.06 KB
uversion.h	6.7 KB
vtzone.h	20.17 KB

Edit: ucsdet.h

// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
 **********************************************************************
 *   Copyright (C) 2005-2013, International Business Machines
 *   Corporation and others.  All Rights Reserved.
 **********************************************************************
 *   file name:  ucsdet.h
 *   encoding:   UTF-8
 *   indentation:4
 *
 *   created on: 2005Aug04
 *   created by: Andy Heninger
 *
 *   ICU Character Set Detection, API for C
 *
 *   Draft version 18 Oct 2005
 *
 */

#ifndef __UCSDET_H
#define __UCSDET_H

#include "unicode/utypes.h"

#if !UCONFIG_NO_CONVERSION

#include "unicode/localpointer.h"
#include "unicode/uenum.h"

/**
 * \file 
 * \brief C API: Charset Detection API
 *
 * This API provides a facility for detecting the
 * charset or encoding of character data in an unknown text format.
 * The input data can be from an array of bytes.
 * 
 * Character set detection is at best an imprecise operation. The detection
 * process will attempt to identify the charset that best matches the characteristics
 * of the byte data, but the process is partly statistical in nature, and
 * the results can not be guaranteed to always be correct.
 * 
 * For best accuracy in charset detection, the input data should be primarily
 * in a single language, and a minimum of a few hundred bytes worth of plain text
 * in the language are needed. The detection process will attempt to
 * ignore html or xml style markup that could otherwise obscure the content.
 * 
 * An alternative to the ICU Charset Detector is the
 * Compact Encoding Detector, https://github.com/google/compact_enc_det.
 * It often gives more accurate results, especially with short input samples.
 */

struct UCharsetDetector;
/**
  * Structure representing a charset detector
  * @stable ICU 3.6
  */
typedef struct UCharsetDetector UCharsetDetector;

struct UCharsetMatch;
/**
  *  Opaque structure representing a match that was identified
  *  from a charset detection operation.
  *  @stable ICU 3.6
  */
typedef struct UCharsetMatch UCharsetMatch;

/**
  *  Open a charset detector.
  *
  *  @param status Any error conditions occurring during the open
  *                operation are reported back in this variable.
  *  @return the newly opened charset detector.
  *  @stable ICU 3.6
  */
U_STABLE UCharsetDetector * U_EXPORT2
ucsdet_open(UErrorCode   *status);

/**
  * Close a charset detector.  All storage and any other resources
  *   owned by this charset detector will be released.  Failure to
  *   close a charset detector when finished with it can result in
  *   memory leaks in the application.
  *
  *  @param ucsd  The charset detector to be closed.
  *  @stable ICU 3.6
  */
U_STABLE void U_EXPORT2
ucsdet_close(UCharsetDetector *ucsd);

#if U_SHOW_CPLUSPLUS_API

U_NAMESPACE_BEGIN

/**
 * \class LocalUCharsetDetectorPointer
 * "Smart pointer" class, closes a UCharsetDetector via ucsdet_close().
 * For most methods see the LocalPointerBase base class.
 *
 * @see LocalPointerBase
 * @see LocalPointer
 * @stable ICU 4.4
 */
U_DEFINE_LOCAL_OPEN_POINTER(LocalUCharsetDetectorPointer, UCharsetDetector, ucsdet_close);

U_NAMESPACE_END

#endif

/**
  * Set the input byte data whose charset is to detected.
  *
  * Ownership of the input  text byte array remains with the caller.
  * The input string must not be altered or deleted until the charset
  * detector is either closed or reset to refer to different input text.
  *
  * @param ucsd   the charset detector to be used.
  * @param textIn the input text of unknown encoding.   .
  * @param len    the length of the input text, or -1 if the text
  *               is NUL terminated.
  * @param status any error conditions are reported back in this variable.
  *
  * @stable ICU 3.6
  */
U_STABLE void U_EXPORT2
ucsdet_setText(UCharsetDetector *ucsd, const char *textIn, int32_t len, UErrorCode *status);

/** Set the declared encoding for charset detection.
 *  The declared encoding of an input text is an encoding obtained
 *  by the user from an http header or xml declaration or similar source that
 *  can be provided as an additional hint to the charset detector.
 *
 *  How and whether the declared encoding will be used during the
 *  detection process is TBD.
 *
 * @param ucsd      the charset detector to be used.
 * @param encoding  an encoding for the current data obtained from
 *                  a header or declaration or other source outside
 *                  of the byte data itself.
 * @param length    the length of the encoding name, or -1 if the name string
 *                  is NUL terminated.
 * @param status    any error conditions are reported back in this variable.
 *
 * @stable ICU 3.6
 */
U_STABLE void U_EXPORT2
ucsdet_setDeclaredEncoding(UCharsetDetector *ucsd, const char *encoding, int32_t length, UErrorCode *status);

/**
 * Return the charset that best matches the supplied input data.
 * 
 * Note though, that because the detection 
 * only looks at the start of the input data,
 * there is a possibility that the returned charset will fail to handle
 * the full set of input data.
 * 
 * The returned UCharsetMatch object is owned by the UCharsetDetector.
 * It will remain valid until the detector input is reset, or until
 * the detector is closed.
 * 
 * The function will fail if
 * <ul>
 * <li>no charset appears to match the data.</li>
 * <li>no input text has been provided</li>
 * </ul>
 *
 * @param ucsd the charset detector to be used.
 * @param status any error conditions are reported back in this variable.
 * @return a UCharsetMatch representing the best matching charset,
 * or NULL if no charset matches the byte data.
 *
 * @stable ICU 3.6
 */
U_STABLE const UCharsetMatch * U_EXPORT2
ucsdet_detect(UCharsetDetector *ucsd, UErrorCode *status);

/**
 * Find all charset matches that appear to be consistent with the input,
 * returning an array of results. The results are ordered with the
 * best quality match first.
 *
 * Because the detection only looks at a limited amount of the
 * input byte data, some of the returned charsets may fail to handle
 * the all of input data.
 * 
 * The returned UCharsetMatch objects are owned by the UCharsetDetector.
 * They will remain valid until the detector is closed or modified
 * 
 * 
 * Return an error if 
 * <ul>
 * <li>no charsets appear to match the input data.</li>
 * <li>no input text has been provided</li>
 * </ul>
 * 
 * @param ucsd the charset detector to be used.
 * @param matchesFound pointer to a variable that will be set to the
 * number of charsets identified that are consistent with
 * the input data. Output only.
 * @param status any error conditions are reported back in this variable.
 * @return A pointer to an array of pointers to UCharSetMatch objects.
 * This array, and the UCharSetMatch instances to which it refers,
 * are owned by the UCharsetDetector, and will remain valid until
 * the detector is closed or modified.
 * @stable ICU 3.6
 */
U_STABLE const UCharsetMatch ** U_EXPORT2
ucsdet_detectAll(UCharsetDetector *ucsd, int32_t *matchesFound, UErrorCode *status);

/**
 *  Get the name of the charset represented by a UCharsetMatch.
 *
 *  The storage for the returned name string is owned by the
 *  UCharsetMatch, and will remain valid while the UCharsetMatch
 *  is valid.
 *
 *  The name returned is suitable for use with the ICU conversion APIs.
 *
 *  @param ucsm    The charset match object.
 *  @param status  Any error conditions are reported back in this variable.
 *  @return        The name of the matching charset.
 *
 *  @stable ICU 3.6
 */
U_STABLE const char * U_EXPORT2
ucsdet_getName(const UCharsetMatch *ucsm, UErrorCode *status);

/**
 *  Get a confidence number for the quality of the match of the byte
 *  data with the charset.  Confidence numbers range from zero to 100,
 *  with 100 representing complete confidence and zero representing
 *  no confidence.
 *
 *  The confidence values are somewhat arbitrary.  They define an
 *  an ordering within the results for any single detection operation
 *  but are not generally comparable between the results for different input.
 *
 *  A confidence value of ten does have a general meaning - it is used
 *  for charsets that can represent the input data, but for which there
 *  is no other indication that suggests that the charset is the correct one.
 *  Pure 7 bit ASCII data, for example, is compatible with a
 *  great many charsets, most of which will appear as possible matches
 *  with a confidence of 10.
 *
 *  @param ucsm    The charset match object.
 *  @param status  Any error conditions are reported back in this variable.
 *  @return        A confidence number for the charset match.
 *
 *  @stable ICU 3.6
 */
U_STABLE int32_t U_EXPORT2
ucsdet_getConfidence(const UCharsetMatch *ucsm, UErrorCode *status);

/**
 *  Get the RFC 3066 code for the language of the input data.
 *
 *  The Charset Detection service is intended primarily for detecting
 *  charsets, not language.  For some, but not all, charsets, a language is
 *  identified as a byproduct of the detection process, and that is what
 *  is returned by this function.
 *
 *  CAUTION:
 *    1.  Language information is not available for input data encoded in
 *        all charsets. In particular, no language is identified
 *        for UTF-8 input data.
 *
 *    2.  Closely related languages may sometimes be confused.
 *
 *  If more accurate language detection is required, a linguistic
 *  analysis package should be used.
 *
 *  The storage for the returned name string is owned by the
 *  UCharsetMatch, and will remain valid while the UCharsetMatch
 *  is valid.
 *
 *  @param ucsm    The charset match object.
 *  @param status  Any error conditions are reported back in this variable.
 *  @return        The RFC 3066 code for the language of the input data, or
 *                 an empty string if the language could not be determined.
 *
 *  @stable ICU 3.6
 */
U_STABLE const char * U_EXPORT2
ucsdet_getLanguage(const UCharsetMatch *ucsm, UErrorCode *status);

/**
  *  Get the entire input text as a UChar string, placing it into
  *  a caller-supplied buffer.  A terminating
  *  NUL character will be appended to the buffer if space is available.
  *
  *  The number of UChars in the output string, not including the terminating
  *  NUL, is returned. 
  *
  *  If the supplied buffer is smaller than required to hold the output,
  *  the contents of the buffer are undefined.  The full output string length
  *  (in UChars) is returned as always, and can be used to allocate a buffer
  *  of the correct size.
  *
  *
  * @param ucsm    The charset match object.
  * @param buf     A UChar buffer to be filled with the converted text data.
  * @param cap     The capacity of the buffer in UChars.
  * @param status  Any error conditions are reported back in this variable.
  * @return        The number of UChars in the output string.
  *
  * @stable ICU 3.6
  */
U_STABLE  int32_t U_EXPORT2
ucsdet_getUChars(const UCharsetMatch *ucsm,
                 UChar *buf, int32_t cap, UErrorCode *status);

/**
 * Get an iterator over the set of all detectable charsets - 
 * over the charsets that are known to the charset detection
 * service.
 *
 * The returned UEnumeration provides access to the names of
 * the charsets.
 *
 * 
 * The state of the Charset detector that is passed in does not
 * affect the result of this function, but requiring a valid, open
 * charset detector as a parameter insures that the charset detection
 * service has been safely initialized and that the required detection
 * data is available.
 *
 * 
 * Note: Multiple different charset encodings in a same family may use
 * a single shared name in this implementation. For example, this method returns
 * an array including "ISO-8859-1" (ISO Latin 1), but not including "windows-1252"
 * (Windows Latin 1). However, actual detection result could be "windows-1252"
 * when the input data matches Latin 1 code points with any points only available
 * in "windows-1252".
 *
 * @param ucsd a Charset detector.
 * @param status Any error conditions are reported back in this variable.
 * @return an iterator providing access to the detectable charset names.
 * @stable ICU 3.6
 */
U_STABLE UEnumeration * U_EXPORT2
ucsdet_getAllDetectableCharsets(const UCharsetDetector *ucsd, UErrorCode *status);

/**
  *  Test whether input filtering is enabled for this charset detector.
  *  Input filtering removes text that appears to be HTML or xml
  *  markup from the input before applying the code page detection
  *  heuristics.
  *
  *  @param ucsd  The charset detector to check.
  *  @return TRUE if filtering is enabled.
  *  @stable ICU 3.6
  */

U_STABLE  UBool U_EXPORT2
ucsdet_isInputFilterEnabled(const UCharsetDetector *ucsd);

/**
 * Enable filtering of input text. If filtering is enabled,
 * text within angle brackets ("<" and ">") will be removed
 * before detection, which will remove most HTML or xml markup.
 *
 * @param ucsd the charset detector to be modified.
 * @param filter <code>true</code> to enable input text filtering.
 * @return The previous setting.
 *
 * @stable ICU 3.6
 */
U_STABLE UBool U_EXPORT2
ucsdet_enableInputFilter(UCharsetDetector *ucsd, UBool filter);

#ifndef U_HIDE_INTERNAL_API
/**
  *  Get an iterator over the set of detectable charsets -
  *  over the charsets that are enabled by the specified charset detector.
  *
  *  The returned UEnumeration provides access to the names of
  *  the charsets.
  *
  *  @param ucsd a Charset detector.
  *  @param status  Any error conditions are reported back in this variable.
  *  @return an iterator providing access to the detectable charset names by
  *  the specified charset detector.
  *  @internal
  */
U_INTERNAL UEnumeration * U_EXPORT2
ucsdet_getDetectableCharsets(const UCharsetDetector *ucsd,  UErrorCode *status);

/**
 * Enable or disable individual charset encoding.
 * A name of charset encoding must be included in the names returned by
 * {@link #ucsdet_getAllDetectableCharsets()}.
 *
 * @param ucsd a Charset detector.
 * @param encoding encoding the name of charset encoding.
 * @param enabled <code>TRUE</code> to enable, or <code>FALSE</code> to disable the
 * charset encoding.
 * @param status receives the return status. When the name of charset encoding
 * is not supported, U_ILLEGAL_ARGUMENT_ERROR is set.
 * @internal
 */
U_INTERNAL void U_EXPORT2
ucsdet_setDetectableCharset(UCharsetDetector *ucsd, const char *encoding, UBool enabled, UErrorCode *status);
#endif /* U_HIDE_INTERNAL_API */

#endif
#endif   /* __UCSDET_H */