Gecko [ dallasfobana2023.variationbd.com ]

Name	Size	Permission
alphaindex.h	26.42 KB	-rw-r--r--
appendable.h	8.43 KB	-rw-r--r--
basictz.h	8.84 KB	-rw-r--r--
brkiter.h	27.64 KB	-rw-r--r--
bytestream.h	9.54 KB	-rw-r--r--
bytestrie.h	19.26 KB	-rw-r--r--
bytestriebuilder.h	7.02 KB	-rw-r--r--
calendar.h	105.06 KB	-rw-r--r--
caniter.h	7.37 KB	-rw-r--r--
casemap.h	25.26 KB	-rw-r--r--
char16ptr.h	7.16 KB	-rw-r--r--
chariter.h	24 KB	-rw-r--r--
choicfmt.h	23.85 KB	-rw-r--r--
coleitr.h	13.7 KB	-rw-r--r--
coll.h	55.59 KB	-rw-r--r--
compactdecimalformat.h	6.81 KB	-rw-r--r--
curramt.h	3.69 KB	-rw-r--r--
currpinf.h	7.24 KB	-rw-r--r--
currunit.h	3.99 KB	-rw-r--r--
datefmt.h	40.37 KB	-rw-r--r--
dbbi.h	1.11 KB	-rw-r--r--
dcfmtsym.h	20.1 KB	-rw-r--r--
decimfmt.h	87.82 KB	-rw-r--r--
docmain.h	6.96 KB	-rw-r--r--
dtfmtsym.h	37.64 KB	-rw-r--r--
dtintrv.h	3.78 KB	-rw-r--r--
dtitvfmt.h	46.56 KB	-rw-r--r--
dtitvinf.h	18.46 KB	-rw-r--r--
dtptngen.h	25.08 KB	-rw-r--r--
dtrule.h	8.62 KB	-rw-r--r--
edits.h	20.67 KB	-rw-r--r--
enumset.h	2.08 KB	-rw-r--r--
errorcode.h	4.78 KB	-rw-r--r--
fieldpos.h	8.63 KB	-rw-r--r--
filteredbrk.h	5.24 KB	-rw-r--r--
fmtable.h	24.36 KB	-rw-r--r--
format.h	12.44 KB	-rw-r--r--
formattedvalue.h	9.73 KB	-rw-r--r--
fpositer.h	2.98 KB	-rw-r--r--
gender.h	3.27 KB	-rw-r--r--
gregocal.h	31.57 KB	-rw-r--r--
icudataver.h	1.03 KB	-rw-r--r--
icuplug.h	11.88 KB	-rw-r--r--
idna.h	12.63 KB	-rw-r--r--
listformatter.h	9.42 KB	-rw-r--r--
localebuilder.h	10.54 KB	-rw-r--r--
localpointer.h	19.69 KB	-rw-r--r--
locdspnm.h	7.06 KB	-rw-r--r--
locid.h	44.94 KB	-rw-r--r--
measfmt.h	11.44 KB	-rw-r--r--
measunit.h	88.17 KB	-rw-r--r--
measure.h	4.26 KB	-rw-r--r--
messagepattern.h	33.65 KB	-rw-r--r--
msgfmt.h	44.04 KB	-rw-r--r--
normalizer2.h	33.97 KB	-rw-r--r--
normlzr.h	30.74 KB	-rw-r--r--
nounit.h	2.63 KB	-rw-r--r--
numberformatter.h	84.62 KB	-rw-r--r--
numberrangeformatter.h	29.93 KB	-rw-r--r--
numfmt.h	49.35 KB	-rw-r--r--
numsys.h	7.13 KB	-rw-r--r--
parseerr.h	3.08 KB	-rw-r--r--
parsepos.h	5.5 KB	-rw-r--r--
platform.h	27.1 KB	-rw-r--r--
plurfmt.h	25.18 KB	-rw-r--r--
plurrule.h	18.33 KB	-rw-r--r--
ptypes.h	3.49 KB	-rw-r--r--
putil.h	6.33 KB	-rw-r--r--
rbbi.h	26.42 KB	-rw-r--r--
rbnf.h	49.79 KB	-rw-r--r--
rbtz.h	15.47 KB	-rw-r--r--
regex.h	84.3 KB	-rw-r--r--
region.h	9.12 KB	-rw-r--r--
reldatefmt.h	22.37 KB	-rw-r--r--
rep.h	9.5 KB	-rw-r--r--
resbund.h	18.01 KB	-rw-r--r--
schriter.h	6.26 KB	-rw-r--r--
scientificnumberformatter.h	6.32 KB	-rw-r--r--
search.h	22.21 KB	-rw-r--r--
selfmt.h	14.24 KB	-rw-r--r--
simpleformatter.h	12.53 KB	-rw-r--r--
simpletz.h	45.3 KB	-rw-r--r--
smpdtfmt.h	70.9 KB	-rw-r--r--
sortkey.h	11.12 KB	-rw-r--r--
std_string.h	1015 B	-rw-r--r--
strenum.h	10.04 KB	-rw-r--r--
stringoptions.h	5.79 KB	-rw-r--r--
stringpiece.h	6.46 KB	-rw-r--r--
stringtriebuilder.h	15.27 KB	-rw-r--r--
stsearch.h	21.29 KB	-rw-r--r--
symtable.h	4.21 KB	-rw-r--r--
tblcoll.h	36.4 KB	-rw-r--r--
timezone.h	41.2 KB	-rw-r--r--
tmunit.h	3.29 KB	-rw-r--r--
tmutamt.h	4.8 KB	-rw-r--r--
tmutfmt.h	7.79 KB	-rw-r--r--
translit.h	65.76 KB	-rw-r--r--
tzfmt.h	42.82 KB	-rw-r--r--
tznames.h	16.79 KB	-rw-r--r--
tzrule.h	35.32 KB	-rw-r--r--
tztrans.h	6.07 KB	-rw-r--r--
ubidi.h	89.56 KB	-rw-r--r--
ubiditransform.h	12.65 KB	-rw-r--r--
ubrk.h	23.97 KB	-rw-r--r--
ucal.h	55.54 KB	-rw-r--r--
ucasemap.h	15.18 KB	-rw-r--r--
ucat.h	5.36 KB	-rw-r--r--
uchar.h	140.66 KB	-rw-r--r--
ucharstrie.h	21.06 KB	-rw-r--r--
ucharstriebuilder.h	7.14 KB	-rw-r--r--
uchriter.h	13.14 KB	-rw-r--r--
uclean.h	11.21 KB	-rw-r--r--
ucnv.h	83.09 KB	-rw-r--r--
ucnv_cb.h	6.59 KB	-rw-r--r--
ucnv_err.h	20.99 KB	-rw-r--r--
ucnvsel.h	6.14 KB	-rw-r--r--
ucol.h	61.39 KB	-rw-r--r--
ucoleitr.h	9.46 KB	-rw-r--r--
uconfig.h	12.05 KB	-rw-r--r--
ucpmap.h	5.58 KB	-rw-r--r--
ucptrie.h	22.29 KB	-rw-r--r--
ucsdet.h	14.67 KB	-rw-r--r--
ucurr.h	16.15 KB	-rw-r--r--
udat.h	60.81 KB	-rw-r--r--
udata.h	15.53 KB	-rw-r--r--
udateintervalformat.h	10.03 KB	-rw-r--r--
udatpg.h	25.94 KB	-rw-r--r--
udisplaycontext.h	5.89 KB	-rw-r--r--
uenum.h	7.78 KB	-rw-r--r--
ufieldpositer.h	4.36 KB	-rw-r--r--
uformattable.h	10.94 KB	-rw-r--r--
uformattedvalue.h	12.14 KB	-rw-r--r--
ugender.h	2 KB	-rw-r--r--
uidna.h	33.37 KB	-rw-r--r--
uiter.h	22.77 KB	-rw-r--r--
uldnames.h	10.45 KB	-rw-r--r--
ulistformatter.h	8.83 KB	-rw-r--r--
uloc.h	50.75 KB	-rw-r--r--
ulocdata.h	11.26 KB	-rw-r--r--
umachine.h	13.19 KB	-rw-r--r--
umisc.h	1.33 KB	-rw-r--r--
umsg.h	24.23 KB	-rw-r--r--
umutablecptrie.h	8.28 KB	-rw-r--r--
unifilt.h	3.63 KB	-rw-r--r--
unifunct.h	3.98 KB	-rw-r--r--
unimatch.h	6.04 KB	-rw-r--r--
unirepl.h	3.32 KB	-rw-r--r--
uniset.h	64.88 KB	-rw-r--r--
unistr.h	170.39 KB	-rw-r--r--
unorm.h	20.45 KB	-rw-r--r--
unorm2.h	24.66 KB	-rw-r--r--
unum.h	53.55 KB	-rw-r--r--
unumberformatter.h	25.19 KB	-rw-r--r--
unumsys.h	7.21 KB	-rw-r--r--
uobject.h	10.85 KB	-rw-r--r--
upluralrules.h	7.88 KB	-rw-r--r--
uregex.h	72.05 KB	-rw-r--r--
uregion.h	9.84 KB	-rw-r--r--
ureldatefmt.h	17.26 KB	-rw-r--r--
urename.h	131.4 KB	-rw-r--r--
urep.h	5.38 KB	-rw-r--r--
ures.h	36.54 KB	-rw-r--r--
uscript.h	26.87 KB	-rw-r--r--
usearch.h	38.12 KB	-rw-r--r--
uset.h	40 KB	-rw-r--r--
usetiter.h	9.49 KB	-rw-r--r--
ushape.h	18 KB	-rw-r--r--
uspoof.h	66.03 KB	-rw-r--r--
usprep.h	8.14 KB	-rw-r--r--
ustdio.h	38.54 KB	-rw-r--r--
ustream.h	1.8 KB	-rw-r--r--
ustring.h	72.47 KB	-rw-r--r--
ustringtrie.h	3.15 KB	-rw-r--r--
utext.h	58.11 KB	-rw-r--r--
utf.h	7.86 KB	-rw-r--r--
utf16.h	22.33 KB	-rw-r--r--
utf32.h	763 B	-rw-r--r--
utf8.h	29.96 KB	-rw-r--r--
utf_old.h	43.78 KB	-rw-r--r--
utmscale.h	13.78 KB	-rw-r--r--
utrace.h	13.89 KB	-rw-r--r--
utrans.h	25.54 KB	-rw-r--r--
utypes.h	30.38 KB	-rw-r--r--
uvernum.h	6.67 KB	-rw-r--r--
uversion.h	6.7 KB	-rw-r--r--
vtzone.h	20.17 KB	-rw-r--r--

Code Editor : 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 */

${this.title}

Code Editor : ucsdet.h