FM / unicode

/usr/include/unicode

Name	Size	Mode	Actions
alphaindex.h	27158	0644	edit dl rm
appendable.h	8739	0644	edit dl rm
basictz.h	10163	0644	edit dl rm
brkiter.h	28478	0644	edit dl rm
bytestream.h	11013	0644	edit dl rm
bytestrie.h	21268	0644	edit dl rm
bytestriebuilder.h	7640	0644	edit dl rm
calendar.h	108424	0644	edit dl rm
caniter.h	7621	0644	edit dl rm
casemap.h	25933	0644	edit dl rm
char16ptr.h	7393	0644	edit dl rm
chariter.h	24638	0644	edit dl rm
choicfmt.h	24544	0644	edit dl rm
coleitr.h	14102	0644	edit dl rm
coll.h	57615	0644	edit dl rm
compactdecimalformat.h	7047	0644	edit dl rm
curramt.h	3869	0644	edit dl rm
currpinf.h	7479	0644	edit dl rm
currunit.h	4112	0644	edit dl rm
datefmt.h	41690	0644	edit dl rm
dbbi.h	1223	0644	edit dl rm
dcfmtsym.h	21101	0644	edit dl rm
decimfmt.h	89676	0644	edit dl rm
docmain.h	7380	0644	edit dl rm
dtfmtsym.h	39126	0644	edit dl rm
dtintrv.h	3935	0644	edit dl rm
dtitvfmt.h	50448	0644	edit dl rm
dtitvinf.h	19072	0644	edit dl rm
dtptngen.h	26692	0644	edit dl rm
dtrule.h	8898	0644	edit dl rm
edits.h	21237	0644	edit dl rm
enumset.h	2130	0644	edit dl rm
errorcode.h	4956	0644	edit dl rm
fieldpos.h	8906	0644	edit dl rm
filteredbrk.h	5501	0644	edit dl rm
fmtable.h	25020	0644	edit dl rm
format.h	12802	0644	edit dl rm
formattedvalue.h	9987	0644	edit dl rm
fpositer.h	3107	0644	edit dl rm
gender.h	3408	0644	edit dl rm
gregocal.h	32642	0644	edit dl rm
icudataver.h	1049	0644	edit dl rm
icuplug.h	12109	0644	edit dl rm
idna.h	13000	0644	edit dl rm
listformatter.h	9004	0644	edit dl rm
localebuilder.h	11350	0644	edit dl rm
localematcher.h	27467	0644	edit dl rm
localpointer.h	19825	0644	edit dl rm
locdspnm.h	7292	0644	edit dl rm
locid.h	48804	0644	edit dl rm
measfmt.h	11690	0644	edit dl rm
measunit.h	107613	0644	edit dl rm
measure.h	4431	0644	edit dl rm
messagepattern.h	34517	0644	edit dl rm
msgfmt.h	45278	0644	edit dl rm
normalizer2.h	34466	0644	edit dl rm
normlzr.h	31690	0644	edit dl rm
nounit.h	2305	0644	edit dl rm
numberformatter.h	94505	0644	edit dl rm
numberrangeformatter.h	25790	0644	edit dl rm
numfmt.h	51034	0644	edit dl rm
numsys.h	7509	0644	edit dl rm
parseerr.h	3155	0644	edit dl rm
parsepos.h	5699	0644	edit dl rm
platform.h	28768	0644	edit dl rm
plurfmt.h	25847	0644	edit dl rm
plurrule.h	21316	0644	edit dl rm
ptypes.h	3577	0644	edit dl rm
putil.h	6471	0644	edit dl rm
rbbi.h	28413	0644	edit dl rm
rbnf.h	50021	0644	edit dl rm
rbtz.h	16210	0644	edit dl rm
regex.h	86385	0644	edit dl rm
region.h	9402	0644	edit dl rm
reldatefmt.h	22751	0644	edit dl rm
rep.h	9599	0644	edit dl rm
resbund.h	18513	0644	edit dl rm
schriter.h	6511	0644	edit dl rm
scientificnumberformatter.h	6589	0644	edit dl rm
search.h	22755	0644	edit dl rm
selfmt.h	14686	0644	edit dl rm
simpleformatter.h	12888	0644	edit dl rm
simpletz.h	46798	0644	edit dl rm
smpdtfmt.h	72778	0644	edit dl rm
sortkey.h	11452	0644	edit dl rm
std_string.h	1076	0644	edit dl rm
strenum.h	10157	0644	edit dl rm
stringoptions.h	5926	0644	edit dl rm
stringpiece.h	10287	0644	edit dl rm
stringtriebuilder.h	15842	0644	edit dl rm
stsearch.h	21926	0644	edit dl rm
symtable.h	4374	0644	edit dl rm
tblcoll.h	37801	0644	edit dl rm
timezone.h	44858	0644	edit dl rm
tmunit.h	3479	0644	edit dl rm
tmutamt.h	5029	0644	edit dl rm
tmutfmt.h	7602	0644	edit dl rm
translit.h	67397	0644	edit dl rm
tzfmt.h	43961	0644	edit dl rm
tznames.h	17251	0644	edit dl rm
tzrule.h	36450	0644	edit dl rm
tztrans.h	6278	0644	edit dl rm
ubidi.h	91759	0644	edit dl rm
ubiditransform.h	13003	0644	edit dl rm
ubrk.h	25043	0644	edit dl rm
ucal.h	62463	0644	edit dl rm
ucasemap.h	15579	0644	edit dl rm
ucat.h	5478	0644	edit dl rm
uchar.h	148111	0644	edit dl rm
ucharstrie.h	23066	0644	edit dl rm
ucharstriebuilder.h	7645	0644	edit dl rm
uchriter.h	13747	0644	edit dl rm
uclean.h	11468	0644	edit dl rm
ucnv.h	85051	0644	edit dl rm
ucnvsel.h	6339	0644	edit dl rm
ucnv_cb.h	6738	0644	edit dl rm
ucnv_err.h	21481	0644	edit dl rm
ucol.h	62987	0644	edit dl rm
ucoleitr.h	10056	0644	edit dl rm
uconfig.h	12356	0644	edit dl rm
ucpmap.h	5663	0644	edit dl rm
ucptrie.h	23044	0644	edit dl rm
ucsdet.h	15043	0644	edit dl rm
ucurr.h	17122	0644	edit dl rm
udat.h	63902	0644	edit dl rm
udata.h	16004	0644	edit dl rm
udateintervalformat.h	12218	0644	edit dl rm
udatpg.h	27405	0644	edit dl rm
udisplaycontext.h	6084	0644	edit dl rm
uenum.h	7981	0644	edit dl rm
ufieldpositer.h	4513	0644	edit dl rm
uformattable.h	11233	0644	edit dl rm
uformattedvalue.h	12600	0644	edit dl rm
ugender.h	2106	0644	edit dl rm
uidna.h	34229	0644	edit dl rm
uiter.h	23299	0644	edit dl rm
uldnames.h	10733	0644	edit dl rm
ulistformatter.h	11043	0644	edit dl rm
uloc.h	55936	0644	edit dl rm
ulocdata.h	11572	0644	edit dl rm
umachine.h	16439	0644	edit dl rm
umisc.h	1365	0644	edit dl rm
umsg.h	24832	0644	edit dl rm
umutablecptrie.h	8490	0644	edit dl rm
unifilt.h	4091	0644	edit dl rm
unifunct.h	4151	0644	edit dl rm
unimatch.h	6244	0644	edit dl rm
unirepl.h	3464	0644	edit dl rm
uniset.h	68108	0644	edit dl rm
unistr.h	174627	0644	edit dl rm
unorm.h	21042	0644	edit dl rm
unorm2.h	25269	0644	edit dl rm
unum.h	56269	0644	edit dl rm
unumberformatter.h	31177	0644	edit dl rm
unumberrangeformatter.h	15737	0644	edit dl rm
unumsys.h	7430	0644	edit dl rm
uobject.h	10934	0644	edit dl rm
upluralrules.h	8997	0644	edit dl rm
uregex.h	73719	0644	edit dl rm
uregion.h	10047	0644	edit dl rm
ureldatefmt.h	17448	0644	edit dl rm
urename.h	137853	0644	edit dl rm
urep.h	5507	0644	edit dl rm
ures.h	37418	0644	edit dl rm
uscript.h	28291	0644	edit dl rm
usearch.h	40153	0644	edit dl rm
uset.h	45503	0644	edit dl rm
usetiter.h	9910	0644	edit dl rm
ushape.h	18430	0644	edit dl rm
uspoof.h	67425	0644	edit dl rm
usprep.h	8382	0644	edit dl rm
ustdio.h	39482	0644	edit dl rm
ustream.h	1934	0644	edit dl rm
ustring.h	74096	0644	edit dl rm
ustringtrie.h	3224	0644	edit dl rm
utext.h	59471	0644	edit dl rm
utf.h	8057	0644	edit dl rm
utf8.h	31572	0644	edit dl rm
utf16.h	23910	0644	edit dl rm
utf32.h	763	0644	edit dl rm
utf_old.h	46929	0644	edit dl rm
utmscale.h	14107	0644	edit dl rm
utrace.h	17595	0644	edit dl rm
utrans.h	26157	0644	edit dl rm
utypes.h	31807	0644	edit dl rm
uvernum.h	6839	0644	edit dl rm
uversion.h	6137	0644	edit dl rm
vtzone.h	21303	0644	edit dl rm

Edit: /usr/include/unicode/ucsdet.h (15043B)

// © 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/uenum.h"

#if U_SHOW_CPLUSPLUS_API
#include "unicode/localpointer.h"
#endif   // U_SHOW_CPLUSPLUS_API

/**
 * \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_CAPI 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_CAPI 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_CAPI 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_CAPI 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_CAPI 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_CAPI 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_CAPI 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_CAPI 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_CAPI 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_CAPI  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_CAPI 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_CAPI  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_CAPI 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_CAPI 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_CAPI void U_EXPORT2
ucsdet_setDetectableCharset(UCharsetDetector *ucsd, const char *encoding, UBool enabled, UErrorCode *status);
#endif /* U_HIDE_INTERNAL_API */

#endif
#endif   /* __UCSDET_H */

cmd: