FM / unicode

/usr/include/unicode

Name	Size	Mode	Actions
basictz.h	8913	0644	edit dl rm
bms.h	8664	0644	edit dl rm
bmsearch.h	7316	0644	edit dl rm
brkiter.h	23001	0644	edit dl rm
bytestream.h	8531	0644	edit dl rm
calendar.h	90659	0644	edit dl rm
caniter.h	7288	0644	edit dl rm
chariter.h	24186	0644	edit dl rm
choicfmt.h	29528	0644	edit dl rm
coleitr.h	12990	0644	edit dl rm
coll.h	48468	0644	edit dl rm
colldata.h	11957	0644	edit dl rm
curramt.h	3659	0644	edit dl rm
currpinf.h	7061	0644	edit dl rm
currunit.h	3057	0644	edit dl rm
datefmt.h	27946	0644	edit dl rm
dbbi.h	966	0644	edit dl rm
dcfmtsym.h	14040	0644	edit dl rm
decimfmt.h	88612	0644	edit dl rm
docmain.h	6003	0644	edit dl rm
dtfmtsym.h	26145	0644	edit dl rm
dtintrv.h	3734	0644	edit dl rm
dtitvfmt.h	39700	0644	edit dl rm
dtitvinf.h	18704	0644	edit dl rm
dtptngen.h	17303	0644	edit dl rm
dtrule.h	8718	0644	edit dl rm
errorcode.h	4361	0644	edit dl rm
fieldpos.h	8713	0644	edit dl rm
fmtable.h	18794	0644	edit dl rm
format.h	12083	0644	edit dl rm
gregocal.h	33797	0644	edit dl rm
locid.h	30241	0644	edit dl rm
measfmt.h	1897	0644	edit dl rm
measunit.h	1635	0644	edit dl rm
measure.h	3321	0644	edit dl rm
msgfmt.h	39435	0644	edit dl rm
normlzr.h	30337	0644	edit dl rm
numfmt.h	33987	0644	edit dl rm
numsys.h	5004	0644	edit dl rm
parseerr.h	3044	0644	edit dl rm
parsepos.h	5468	0644	edit dl rm
platform.h	9961	0644	edit dl rm
plurfmt.h	23079	0644	edit dl rm
plurrule.h	9901	0644	edit dl rm
ppalmos.h	6992	0644	edit dl rm
putil.h	6686	0644	edit dl rm
pwin32.h	8668	0644	edit dl rm
rbbi.h	26993	0644	edit dl rm
rbnf.h	45681	0644	edit dl rm
rbtz.h	15695	0644	edit dl rm
regex.h	52316	0644	edit dl rm
rep.h	9559	0644	edit dl rm
resbund.h	18130	0644	edit dl rm
schriter.h	6293	0644	edit dl rm
search.h	22357	0644	edit dl rm
simpletz.h	46179	0644	edit dl rm
smpdtfmt.h	48325	0644	edit dl rm
sortkey.h	11111	0644	edit dl rm
std_string.h	1769	0644	edit dl rm
strenum.h	9888	0644	edit dl rm
stringpiece.h	5484	0644	edit dl rm
stsearch.h	22287	0644	edit dl rm
symtable.h	4199	0644	edit dl rm
tblcoll.h	38199	0644	edit dl rm
timezone.h	34584	0644	edit dl rm
tmunit.h	3454	0644	edit dl rm
tmutamt.h	4787	0644	edit dl rm
tmutfmt.h	8669	0644	edit dl rm
translit.h	54780	0644	edit dl rm
tzrule.h	36057	0644	edit dl rm
tztrans.h	6101	0644	edit dl rm
ubidi.h	83092	0644	edit dl rm
ubrk.h	17688	0644	edit dl rm
ucal.h	40177	0644	edit dl rm
ucasemap.h	16420	0644	edit dl rm
ucat.h	5371	0644	edit dl rm
uchar.h	111062	0644	edit dl rm
uchriter.h	13132	0644	edit dl rm
uclean.h	11855	0644	edit dl rm
ucnv.h	83111	0644	edit dl rm
ucnvsel.h	5630	0644	edit dl rm
ucnv_cb.h	6635	0644	edit dl rm
ucnv_err.h	21375	0644	edit dl rm
ucol.h	48826	0644	edit dl rm
ucoleitr.h	12356	0644	edit dl rm
uconfig.h	6035	0644	edit dl rm
ucsdet.h	12464	0644	edit dl rm
ucurr.h	11572	0644	edit dl rm
udat.h	34496	0644	edit dl rm
udata.h	14265	0644	edit dl rm
udatpg.h	18715	0644	edit dl rm
udeprctd.h	2284	0644	edit dl rm
udraft.h	7600	0644	edit dl rm
uenum.h	5796	0644	edit dl rm
uidna.h	15918	0644	edit dl rm
uintrnal.h	15752	0644	edit dl rm
uiter.h	23234	0644	edit dl rm
uloc.h	44548	0644	edit dl rm
ulocdata.h	9739	0644	edit dl rm
umachine.h	11360	0644	edit dl rm
umisc.h	1255	0644	edit dl rm
umsg.h	26076	0644	edit dl rm
unifilt.h	3770	0644	edit dl rm
unifunct.h	3966	0644	edit dl rm
unimatch.h	6071	0644	edit dl rm
unirepl.h	3290	0644	edit dl rm
uniset.h	61771	0644	edit dl rm
unistr.h	161321	0644	edit dl rm
unorm.h	23621	0644	edit dl rm
unum.h	32145	0644	edit dl rm
uobject.h	11393	0644	edit dl rm
uobslete.h	852	0644	edit dl rm
uregex.h	43948	0644	edit dl rm
urename.h	92538	0644	edit dl rm
urep.h	5394	0644	edit dl rm
ures.h	36348	0644	edit dl rm
uscript.h	11360	0644	edit dl rm
usearch.h	34223	0644	edit dl rm
uset.h	39868	0644	edit dl rm
usetiter.h	9606	0644	edit dl rm
ushape.h	17907	0644	edit dl rm
uspoof.h	38752	0644	edit dl rm
usprep.h	7750	0644	edit dl rm
ustdio.h	35333	0644	edit dl rm
ustream.h	1891	0644	edit dl rm
ustring.h	69383	0644	edit dl rm
usystem.h	1925	0644	edit dl rm
utext.h	58394	0644	edit dl rm
utf.h	8273	0644	edit dl rm
utf8.h	20512	0644	edit dl rm
utf16.h	18776	0644	edit dl rm
utf32.h	653	0644	edit dl rm
utf_old.h	43646	0644	edit dl rm
utmscale.h	13689	0644	edit dl rm
utrace.h	13355	0644	edit dl rm
utrans.h	23129	0644	edit dl rm
utypes.h	34513	0644	edit dl rm
uversion.h	10902	0644	edit dl rm
vtzone.h	20048	0644	edit dl rm

Edit: /usr/include/unicode/ucsdet.h (12464B)

/*
 **********************************************************************
 *   Copyright (C) 2005-2007, International Business Machines
 *   Corporation and others.  All Rights Reserved.
 **********************************************************************
 *   file name:  ucsdet.h
 *   encoding:   US-ASCII
 *   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"

/**
 * \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.
 */

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);

/**
  * 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.
  *
  *  @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);

#endif
#endif   /* __UCSDET_H */

cmd: