[haiku-commits] r37498 - in haiku/trunk: build/jam headers/libs/icu headers/libs/icu/unicode headers/os/locale src/build ...
- From: pulkomandy@xxxxxxxxxxxxxxxxx
- To: haiku-commits@xxxxxxxxxxxxx
- Date: Tue, 13 Jul 2010 21:04:41 +0200 (CEST)
Author: pulkomandy
Date: 2010-07-13 21:04:40 +0200 (Tue, 13 Jul 2010)
New Revision: 37498
Changeset: http://dev.haiku-os.org/changeset/37498
Added:
haiku/trunk/headers/libs/icu/unicode/
haiku/trunk/headers/libs/icu/unicode/basictz.h
haiku/trunk/headers/libs/icu/unicode/bms.h
haiku/trunk/headers/libs/icu/unicode/bmsearch.h
haiku/trunk/headers/libs/icu/unicode/brkiter.h
haiku/trunk/headers/libs/icu/unicode/bytestream.h
haiku/trunk/headers/libs/icu/unicode/calendar.h
haiku/trunk/headers/libs/icu/unicode/caniter.h
haiku/trunk/headers/libs/icu/unicode/chariter.h
haiku/trunk/headers/libs/icu/unicode/choicfmt.h
haiku/trunk/headers/libs/icu/unicode/coleitr.h
haiku/trunk/headers/libs/icu/unicode/coll.h
haiku/trunk/headers/libs/icu/unicode/colldata.h
haiku/trunk/headers/libs/icu/unicode/curramt.h
haiku/trunk/headers/libs/icu/unicode/currpinf.h
haiku/trunk/headers/libs/icu/unicode/currunit.h
haiku/trunk/headers/libs/icu/unicode/datefmt.h
haiku/trunk/headers/libs/icu/unicode/dbbi.h
haiku/trunk/headers/libs/icu/unicode/dcfmtsym.h
haiku/trunk/headers/libs/icu/unicode/decimfmt.h
haiku/trunk/headers/libs/icu/unicode/docmain.h
haiku/trunk/headers/libs/icu/unicode/dtfmtsym.h
haiku/trunk/headers/libs/icu/unicode/dtintrv.h
haiku/trunk/headers/libs/icu/unicode/dtitvfmt.h
haiku/trunk/headers/libs/icu/unicode/dtitvinf.h
haiku/trunk/headers/libs/icu/unicode/dtptngen.h
haiku/trunk/headers/libs/icu/unicode/dtrule.h
haiku/trunk/headers/libs/icu/unicode/errorcode.h
haiku/trunk/headers/libs/icu/unicode/fieldpos.h
haiku/trunk/headers/libs/icu/unicode/fmtable.h
haiku/trunk/headers/libs/icu/unicode/format.h
haiku/trunk/headers/libs/icu/unicode/fpositer.h
haiku/trunk/headers/libs/icu/unicode/gregocal.h
haiku/trunk/headers/libs/icu/unicode/icudataver.h
haiku/trunk/headers/libs/icu/unicode/icuplug.h
haiku/trunk/headers/libs/icu/unicode/localpointer.h
haiku/trunk/headers/libs/icu/unicode/locdspnm.h
haiku/trunk/headers/libs/icu/unicode/locid.h
haiku/trunk/headers/libs/icu/unicode/measfmt.h
haiku/trunk/headers/libs/icu/unicode/measunit.h
haiku/trunk/headers/libs/icu/unicode/measure.h
haiku/trunk/headers/libs/icu/unicode/msgfmt.h
haiku/trunk/headers/libs/icu/unicode/normalizer2.h
haiku/trunk/headers/libs/icu/unicode/normlzr.h
haiku/trunk/headers/libs/icu/unicode/numfmt.h
haiku/trunk/headers/libs/icu/unicode/numsys.h
haiku/trunk/headers/libs/icu/unicode/parseerr.h
haiku/trunk/headers/libs/icu/unicode/parsepos.h
haiku/trunk/headers/libs/icu/unicode/platform.h
haiku/trunk/headers/libs/icu/unicode/platform.h.in
haiku/trunk/headers/libs/icu/unicode/plurfmt.h
haiku/trunk/headers/libs/icu/unicode/plurrule.h
haiku/trunk/headers/libs/icu/unicode/ppalmos.h
haiku/trunk/headers/libs/icu/unicode/ptypes.h
haiku/trunk/headers/libs/icu/unicode/putil.h
haiku/trunk/headers/libs/icu/unicode/pwin32.h
haiku/trunk/headers/libs/icu/unicode/rbbi.h
haiku/trunk/headers/libs/icu/unicode/rbnf.h
haiku/trunk/headers/libs/icu/unicode/rbtz.h
haiku/trunk/headers/libs/icu/unicode/regex.h
haiku/trunk/headers/libs/icu/unicode/rep.h
haiku/trunk/headers/libs/icu/unicode/resbund.h
haiku/trunk/headers/libs/icu/unicode/schriter.h
haiku/trunk/headers/libs/icu/unicode/search.h
haiku/trunk/headers/libs/icu/unicode/selfmt.h
haiku/trunk/headers/libs/icu/unicode/simpletz.h
haiku/trunk/headers/libs/icu/unicode/smpdtfmt.h
haiku/trunk/headers/libs/icu/unicode/sortkey.h
haiku/trunk/headers/libs/icu/unicode/std_string.h
haiku/trunk/headers/libs/icu/unicode/strenum.h
haiku/trunk/headers/libs/icu/unicode/stringpiece.h
haiku/trunk/headers/libs/icu/unicode/stsearch.h
haiku/trunk/headers/libs/icu/unicode/symtable.h
haiku/trunk/headers/libs/icu/unicode/tblcoll.h
haiku/trunk/headers/libs/icu/unicode/timezone.h
haiku/trunk/headers/libs/icu/unicode/tmunit.h
haiku/trunk/headers/libs/icu/unicode/tmutamt.h
haiku/trunk/headers/libs/icu/unicode/tmutfmt.h
haiku/trunk/headers/libs/icu/unicode/translit.h
haiku/trunk/headers/libs/icu/unicode/tzrule.h
haiku/trunk/headers/libs/icu/unicode/tztrans.h
haiku/trunk/headers/libs/icu/unicode/ubidi.h
haiku/trunk/headers/libs/icu/unicode/ubrk.h
haiku/trunk/headers/libs/icu/unicode/ucal.h
haiku/trunk/headers/libs/icu/unicode/ucasemap.h
haiku/trunk/headers/libs/icu/unicode/ucat.h
haiku/trunk/headers/libs/icu/unicode/uchar.h
haiku/trunk/headers/libs/icu/unicode/uchriter.h
haiku/trunk/headers/libs/icu/unicode/uclean.h
haiku/trunk/headers/libs/icu/unicode/ucnv.h
haiku/trunk/headers/libs/icu/unicode/ucnv_cb.h
haiku/trunk/headers/libs/icu/unicode/ucnv_err.h
haiku/trunk/headers/libs/icu/unicode/ucnvsel.h
haiku/trunk/headers/libs/icu/unicode/ucol.h
haiku/trunk/headers/libs/icu/unicode/ucoleitr.h
haiku/trunk/headers/libs/icu/unicode/uconfig.h
haiku/trunk/headers/libs/icu/unicode/ucsdet.h
haiku/trunk/headers/libs/icu/unicode/ucurr.h
haiku/trunk/headers/libs/icu/unicode/udat.h
haiku/trunk/headers/libs/icu/unicode/udata.h
[... truncated: 50 added files follow ...]
Removed:
haiku/trunk/headers/libs/icu/unicode/
haiku/trunk/src/build/icu/
haiku/trunk/src/libs/icu/
haiku/trunk/src/tools/icu/
Modified:
haiku/trunk/build/jam/HaikuImage
haiku/trunk/build/jam/OptionalBuildFeatures
haiku/trunk/headers/os/locale/Country.h
haiku/trunk/headers/os/locale/Language.h
haiku/trunk/src/build/Jamfile
haiku/trunk/src/kits/locale/Country.cpp
haiku/trunk/src/kits/locale/Jamfile
haiku/trunk/src/kits/locale/Language.cpp
haiku/trunk/src/kits/locale/TimeFormat.cpp
haiku/trunk/src/libs/Jamfile
haiku/trunk/src/preferences/locale/Jamfile
haiku/trunk/src/preferences/time/DateTimeEdit.cpp
haiku/trunk/src/preferences/time/DateTimeEdit.h
haiku/trunk/src/preferences/time/DateTimeView.cpp
haiku/trunk/src/preferences/time/SectionEdit.h
haiku/trunk/src/tests/kits/locale/Jamfile
haiku/trunk/src/tools/Jamfile
Log:
Update ICU to 4.4
* Remove 4.2 sourcecode
* ICU is now an optional package (mandatory)
* Adjust the namespaces and libraries names where needed
Modified: haiku/trunk/build/jam/HaikuImage
===================================================================
--- haiku/trunk/build/jam/HaikuImage 2010-07-13 17:57:47 UTC (rev 37497)
+++ haiku/trunk/build/jam/HaikuImage 2010-07-13 19:04:40 UTC (rev 37498)
@@ -77,8 +77,6 @@
SYSTEM_DEMOS = BSnow Chart Clock Cortex FontDemo
GLTeapot Haiku3d Mandelbrot Pairs Playground Pulse Sudoku
;
-ICU_LIBS = libicu-common.so libicu-data.so libicu-i18n.so
-;
SYSTEM_LIBS =
libbe.so libbsd.so libbnetapi.so
libdebug.so libdevice.so
@@ -100,7 +98,6 @@
libfluidsynth.so
libilmimf.so
liblinprog.so liblpsolve55.so
- $(ICU_LIBS)
;
SYSTEM_SERVERS = app_server cddb_daemon debug_server input_server mail_daemon
media_addon_server media_server midi_server mount_server net_server
Modified: haiku/trunk/build/jam/OptionalBuildFeatures
===================================================================
--- haiku/trunk/build/jam/OptionalBuildFeatures 2010-07-13 17:57:47 UTC (rev
37497)
+++ haiku/trunk/build/jam/OptionalBuildFeatures 2010-07-13 19:04:40 UTC (rev
37498)
@@ -45,3 +45,50 @@
= [ FDirName $(HAIKU_OPENSSL_DIR) common include ] ;
}
}
+
+
+# ICU
+
+# Note ICU isn't actually optional, but is still an external package
+local isHybridBuild ;
+if $(HAIKU_ADD_ALTERNATIVE_GCC_LIBS) = 1
+ && $(HAIKU_ALTERNATIVE_GCC_OUTPUT_DIR) {
+ isHybridBuild = 1 ;
+}
+if $(HAIKU_GCC_VERSION[1]) < 4 && !isHybridBuild) {
+ HAIKU_ICU_PACKAGE = icu-4.4.1-r1a2-x86-gcc2-2010-07-13-a.zip ;
+} else {
+ HAIKU_ICU_PACKAGE = icu-4.4.1-r1a2-x86-gcc4-2010-07-13-a.zip ;
+}
+
+HAIKU_ICU_URL = $(baseURL)/$(HAIKU_ICU_PACKAGE) ;
+
+if $(TARGET_ARCH) != x86 {
+ Echo "ICU not available for $(TARGET_ARCH)" ;
+} else {
+ local zipFile = [ DownloadFile $(HAIKU_ICU_PACKAGE) : $(HAIKU_ICU_URL)
] ;
+
+ # zip file and output directory
+ HAIKU_ICU_ZIP_FILE = $(zipFile) ;
+ HAIKU_ICU_DIR = [ FDirName $(HAIKU_OPTIONAL_BUILD_PACKAGES_DIR)
+ $(HAIKU_ICU_PACKAGE:B) ] ;
+
+ # extract headers and libraries
+ # HAIKU_ICU_HEADERS_DEPENDENCY = [ ExtractArchive $(HAIKU_ICU_DIR)
+ # : common/include/ : $(zipFile) ] ;
+
+ HAIKU_ICU_LIBS = [ ExtractArchive $(HAIKU_ICU_DIR)
+ :
+ system/lib/libicudata.so
+ system/lib/libicui18n.so
+ system/lib/libicuio.so
+ system/lib/libicule.so
+ system/lib/libiculx.so
+ system/lib/libicutu.so
+ system/lib/libicuuc.so
+ : $(zipFile)
+ ] ;
+
+ HAIKU_ICU_HEADERS
+ = [ FDirName $(HAIKU_ICU_DIR) common include ] ;
+}
Added: haiku/trunk/headers/libs/icu/unicode/basictz.h
===================================================================
--- haiku/trunk/headers/libs/icu/unicode/basictz.h
(rev 0)
+++ haiku/trunk/headers/libs/icu/unicode/basictz.h 2010-07-13 19:04:40 UTC
(rev 37498)
@@ -0,0 +1,210 @@
+/*
+*******************************************************************************
+* Copyright (C) 2007-2008, International Business Machines Corporation and
*
+* others. All Rights Reserved. *
+*******************************************************************************
+*/
+#ifndef BASICTZ_H
+#define BASICTZ_H
+
+/**
+ * \file
+ * \brief C++ API: ICU TimeZone base class
+ */
+
+#include "unicode/utypes.h"
+
+#if !UCONFIG_NO_FORMATTING
+
+#include "unicode/timezone.h"
+#include "unicode/tzrule.h"
+#include "unicode/tztrans.h"
+
+U_NAMESPACE_BEGIN
+
+// forward declarations
+class UVector;
+
+/**
+ * <code>BasicTimeZone</code> is an abstract class extending
<code>TimeZone</code>.
+ * This class provides some additional methods to access time zone transitions
and rules.
+ * All ICU <code>TimeZone</code> concrete subclasses extend this class.
+ * @stable ICU 3.8
+ */
+class U_I18N_API BasicTimeZone: public TimeZone {
+public:
+ /**
+ * Destructor.
+ * @stable ICU 3.8
+ */
+ virtual ~BasicTimeZone();
+
+ /**
+ * Gets the first time zone transition after the base time.
+ * @param base The base time.
+ * @param inclusive Whether the base time is inclusive or not.
+ * @param result Receives the first transition after the base time.
+ * @return TRUE if the transition is found.
+ * @stable ICU 3.8
+ */
+ virtual UBool getNextTransition(UDate base, UBool inclusive,
TimeZoneTransition& result) /*const*/ = 0;
+
+ /**
+ * Gets the most recent time zone transition before the base time.
+ * @param base The base time.
+ * @param inclusive Whether the base time is inclusive or not.
+ * @param result Receives the most recent transition before the base
time.
+ * @return TRUE if the transition is found.
+ * @stable ICU 3.8
+ */
+ virtual UBool getPreviousTransition(UDate base, UBool inclusive,
TimeZoneTransition& result) /*const*/ = 0;
+
+ /**
+ * Checks if the time zone has equivalent transitions in the time range.
+ * This method returns true when all of transition times, from/to standard
+ * offsets and DST savings used by this time zone match the other in the
+ * time range.
+ * @param tz The <code>BasicTimeZone</code> object to be compared with.
+ * @param start The start time of the evaluated time range (inclusive)
+ * @param end The end time of the evaluated time range (inclusive)
+ * @param ignoreDstAmount
+ * When true, any transitions with only daylight saving amount
+ * changes will be ignored, except either of them is zero.
+ * For example, a transition from rawoffset 3:00/dstsavings
1:00
+ * to rawoffset 2:00/dstsavings 2:00 is excluded from the
comparison,
+ * but a transtion from rawoffset 2:00/dstsavings 1:00 to
+ * rawoffset 3:00/dstsavings 0:00 is included.
+ * @param ec Output param to filled in with a success or an error.
+ * @return true if the other time zone has the equivalent transitions
in the
+ * time range.
+ * @stable ICU 3.8
+ */
+ virtual UBool hasEquivalentTransitions(/*const*/ BasicTimeZone& tz, UDate
start, UDate end,
+ UBool ignoreDstAmount, UErrorCode& ec) /*const*/;
+
+ /**
+ * Returns the number of <code>TimeZoneRule</code>s which represents time
transitions,
+ * for this time zone, that is, all <code>TimeZoneRule</code>s for this
time zone except
+ * <code>InitialTimeZoneRule</code>. The return value range is 0 or any
positive value.
+ * @param status Receives error status code.
+ * @return The number of <code>TimeZoneRule</code>s representing time
transitions.
+ * @stable ICU 3.8
+ */
+ virtual int32_t countTransitionRules(UErrorCode& status) /*const*/ = 0;
+
+ /**
+ * Gets the <code>InitialTimeZoneRule</code> and the set of
<code>TimeZoneRule</code>
+ * which represent time transitions for this time zone. On successful
return,
+ * the argument initial points to non-NULL
<code>InitialTimeZoneRule</code> and
+ * the array trsrules is filled with 0 or multiple
<code>TimeZoneRule</code>
+ * instances up to the size specified by trscount. The results are
referencing the
+ * rule instance held by this time zone instance. Therefore, after this
time zone
+ * is destructed, they are no longer available.
+ * @param initial Receives the initial timezone rule
+ * @param trsrules Receives the timezone transition rules
+ * @param trscount On input, specify the size of the array
'transitions' receiving
+ * the timezone transition rules. On output, actual
number of
+ * rules filled in the array will be set.
+ * @param status Receives error status code.
+ * @stable ICU 3.8
+ */
+ virtual void getTimeZoneRules(const InitialTimeZoneRule*& initial,
+ const TimeZoneRule* trsrules[], int32_t& trscount, UErrorCode& status)
/*const*/ = 0;
+
+ /**
+ * Gets the set of time zone rules valid at the specified time. Some
known external time zone
+ * implementations are not capable to handle historic time zone rule
changes. Also some
+ * implementations can only handle certain type of rule definitions.
+ * If this time zone does not use any daylight saving time within about 1
year from the specified
+ * time, only the <code>InitialTimeZone</code> is returned. Otherwise,
the rule for standard
+ * time and daylight saving time transitions are returned in addition to
the
+ * <code>InitialTimeZoneRule</code>. The standard and daylight saving
time transition rules are
+ * represented by <code>AnnualTimeZoneRule</code> with
<code>DateTimeRule::DOW</code> for its date
+ * rule and <code>DateTimeRule::WALL_TIME</code> for its time rule.
Because daylight saving time
+ * rule is changing time to time in many time zones and also mapping a
transition time rule to
+ * different type is lossy transformation, the set of rules returned by
this method may be valid
+ * for short period of time.
+ * The time zone rule objects returned by this method is owned by the
caller, so the caller is
+ * responsible for deleting them after use.
+ * @param date The date used for extracting time zone rules.
+ * @param initial Receives the <code>InitialTimeZone</code>, always not
NULL.
+ * @param std Receives the <code>AnnualTimeZoneRule</code> for
standard time transitions.
+ * When this time time zone does not observe daylight
saving times around the
+ * specified date, NULL is set.
+ * @param dst Receives the <code>AnnualTimeZoneRule</code> for
daylight saving time
+ * transitions. When this time zone does not observer
daylight saving times
+ * around the specified date, NULL is set.
+ * @param status Receives error status code.
+ * @stable ICU 3.8
+ */
+ virtual void getSimpleRulesNear(UDate date, InitialTimeZoneRule*& initial,
+ AnnualTimeZoneRule*& std, AnnualTimeZoneRule*& dst, UErrorCode&
status) /*const*/;
+
+
+ /**
+ * The time type option bit flags used by getOffsetFromLocal
+ * @internal
+ */
+ enum {
+ kStandard = 0x01,
+ kDaylight = 0x03,
+ kFormer = 0x04,
+ kLatter = 0x0C
+ };
+
+ /**
+ * Get time zone offsets from local wall time.
+ * @internal
+ */
+ virtual void getOffsetFromLocal(UDate date, int32_t nonExistingTimeOpt,
int32_t duplicatedTimeOpt,
+ int32_t& rawOffset, int32_t& dstOffset, UErrorCode& status) /*const*/;
+
+protected:
+
+ /**
+ * The time type option bit masks used by getOffsetFromLocal
+ * @internal
+ */
+ enum {
+ kStdDstMask = kDaylight,
+ kFormerLatterMask = kLatter
+ };
+
+ /**
+ * Default constructor.
+ * @stable ICU 3.8
+ */
+ BasicTimeZone();
+
+ /**
+ * Construct a timezone with a given ID.
+ * @param id a system time zone ID
+ * @stable ICU 3.8
+ */
+ BasicTimeZone(const UnicodeString &id);
+
+ /**
+ * Copy constructor.
+ * @param source the object to be copied.
+ * @stable ICU 3.8
+ */
+ BasicTimeZone(const BasicTimeZone& source);
+
+ /**
+ * Gets the set of TimeZoneRule instances applicable to the specified time
and after.
+ * @param start The start date used for extracting time zone rules
+ * @param initial Receives the InitialTimeZone, always not NULL
+ * @param transitionRules Receives the transition rules, could be NULL
+ * @param status Receives error status code
+ */
+ void getTimeZoneRulesAfter(UDate start, InitialTimeZoneRule*& initial,
UVector*& transitionRules,
+ UErrorCode& status) /*const*/;
+};
+
+U_NAMESPACE_END
+
+#endif /* #if !UCONFIG_NO_FORMATTING */
+
+#endif // BASICTZ_H
+
+//eof
Added: haiku/trunk/headers/libs/icu/unicode/bms.h
===================================================================
--- haiku/trunk/headers/libs/icu/unicode/bms.h (rev 0)
+++ haiku/trunk/headers/libs/icu/unicode/bms.h 2010-07-13 19:04:40 UTC (rev
37498)
@@ -0,0 +1,274 @@
+/*
+ * Copyright (C) 1996-2010, International Business Machines Corporation and
Others.
+ * All rights reserved.
+ */
+
+/**
+ * \file
+ * \brief C API: Boyer-Moore StringSearch prototype.
+ * \internal
+ */
+
+#ifndef _BMS_H
+#define _BMS_H
+
+#include "unicode/utypes.h"
+
+#if !UCONFIG_NO_COLLATION && !UCONFIG_NO_BREAK_ITERATION
+
+#include "unicode/ucol.h"
+
+/**
+ * A <code>UCD</code> object holds the Collator-specific data needed to
+ * compute the length of the shortest string that can
+ * generate a partcular list of CEs.
+ *
+ * <code>UCD</code> objects are quite expensive to compute. Because
+ * of this, they are cached. When you call <code>ucd_open</code> it
+ * returns a reference counted cached object. When you call
<code>ucd_close</code>
+ * the reference count on the object is decremented but the object is not
deleted.
+ *
+ * If you do not need to reuse any unreferenced objects in the cache, you can
call
+ * <code>ucd_flushCCache</code>. If you no longer need any <code>UCD</code>
+ * objects, you can call <code>ucd_freeCache</code>
+ */
+typedef void UCD;
+
+/**
+ * Open a <code>UCD</code> object.
+ *
+ * @param coll - the collator
+ * @param status - will be set if any errors occur.
+ *
+ * @return the <code>UCD</code> object. You must call
+ * <code>ucd_close</code> when you are done using the object.
+ *
+ * Note: if on return status is set to an error, the only safe
+ * thing to do with the returned object is to call <code>ucd_close</code>.
+ *
+ * @internal ICU 4.0.1 technology preview
+ */
+U_CAPI UCD * U_EXPORT2
+ucd_open(UCollator *coll, UErrorCode *status);
+
+/**
+ * Release a <code>UCD</code> object.
+ *
+ * @param ucd - the object
+ *
+ * @internal ICU 4.0.1 technology preview
+ */
+U_CAPI void U_EXPORT2
+ucd_close(UCD *ucd);
+
+/**
+ * Get the <code>UCollator</code> object used to create a <code>UCD</code>
object.
+ * The <code>UCollator</code> object returned may not be the exact
+ * object that was used to create this object, but it will have the
+ * same behavior.
+ *
+ * @param ucd - the <code>UCD</code> object
+ *
+ * @return the <code>UCollator</code> used to create the given
+ * <code>UCD</code> object.
+ *
+ * @internal ICU 4.0.1 technology preview
+ */
+U_CAPI UCollator * U_EXPORT2
+ucd_getCollator(UCD *ucd);
+
+/**
+ * <code>UCD</code> objects are expensive to compute, and so
+ * may be cached. This routine will free the cached objects and delete
+ * the cache.
+ *
+ * WARNING: Don't call this until you are have called <code>close</code>
+ * for each <code>UCD</code> object that you have used. also,
+ * DO NOT call this if another thread may be calling
<code>ucd_flushCache</code>
+ * at the same time.
+ *
+ * @internal ICU 4.0.1 technology preview
+ */
+U_CAPI void U_EXPORT2
+ucd_freeCache();
+
+/**
+ * <code>UCD</code> objects are expensive to compute, and so
+ * may be cached. This routine will remove any unused <code>UCD</code>
+ * objects from the cache.
+ *
+ * @internal 4.0.1 technology preview
+ */
+U_CAPI void U_EXPORT2
+ucd_flushCache();
+
+/**
+ * BMS
+ *
+ * This object holds the information needed to do a Collation sensitive
Boyer-Moore search. It encapulates
+ * the pattern, the "bad character" and "good suffix" tables, the
Collator-based data needed to compute them,
+ * and a reference to the text being searched.
+ *
+ * To do a search, you first need to get a <code>UCD</code> object by calling
<code>ucd_open</code>.
+ * Then you construct a <code>BMS</code> object from the <code>UCD</code>
object, the pattern
+ * string and the target string. Then you call the <code>search</code> method.
Here's a code sample:
+ *
+ * <pre>
+ * void boyerMooreExample(UCollator *collator, UChar *pattern, int32_t
patternLen, UChar *target, int32_t targetLength)
+ * {
+ * UErrorCode status = U_ZERO_ERROR;
+ * int32_t offset = 0, start = -1, end = -1;
+ * UCD *ucd = NULL);
+ * BMS *bms = NULL;
+ *
+ * ucd = ucd_open(collator, &status);
+ * if (U_FAILURE(status)) {
+ * // could not create a UCD object
+ * return;
+ * }
+ *
+ * BMS *bms = bms_open(ucd, pattern, patternLength, target, targetlength,
&status);
+ * if (U_FAILURE(status)) {
+ * // could not create a BMS object
+ * ucd_close(ucd);
+ * return;
+ * }
+ *
+ *
+ * // Find all matches
+ * while (bms_search(bms, offset, &start, &end)) {
+ * // process the match between start and end
+ * ...
+ *
+ * // advance past the match
+ * offset = end;
+ * }
+ *
+ * // at this point, if offset == 0, there were no matches
+ * if (offset == 0) {
+ * // handle the case of no matches
+ * }
+ *
+ * bms_close(bms);
+ * ucd_close(ucd);
+ *
+ * // UCD objects are cached, so the call to
+ * // ucd_close doesn't delete the object.
+ * // Call this if you don't need the object any more.
+ * ucd_flushCache();
+ * }
+ * </pre>
+ *
+ * NOTE: This is a technology preview. The final version of this API may not
bear any resenblence to this API.
+ *
+ * Knows linitations:
+ * 1) Backwards searching has not been implemented.
+ *
+ * 2) For Han and Hangul characters, this code ignores any Collation
tailorings. In general,
+ * this isn't a problem, but in Korean locals, at strength 1, Hangul
characters are tailored
+ * to be equal to Han characters with the same pronounciation. Because
this code ignroes
+ * tailorings, searching for a Hangul character will not find a Han
character and visa-versa.
+ *
+ * 3) In some cases, searching for a pattern that needs to be normalized and
ends
+ * in a discontiguous contraction may fail. The only known cases of this
are with
+ * the Tibetan script. For example searching for the pattern
+ * "\u0F7F\u0F80\u0F81\u0F82\u0F83\u0F84\u0F85" will fail. (This case is
artificial. We've
+ * been unable to find a pratical, real-world example of this failure.)
+ *
+ * NOTE: This is a technology preview. The final version of this API may not
bear any resenblence to this API.
+ *
+ * @internal ICU 4.0.1 technology preview
+ */
+struct BMS;
+typedef struct BMS BMS; /**< @see BMS */
+
+/**
+ * Construct a <code>MBS</code> object.
+ *
+ * @param ucd - A <code>UCD</code> object holding the Collator-sensitive data
+ * @param pattern - the string for which to search
+ * @param patternLength - the length of the string for which to search
+ * @param target - the string in which to search
+ * @param targetLength - the length of the string in which to search
+ * @param status - will be set if any errors occur.
+ *
+ * @return the <code>BMS</code> object.
+ *
+ * Note: if on return status is set to an error, the only safe
+ * thing to do with the returned object is to call
+ * <code>bms_close</code>.
+ *
+ * @internal ICU 4.0.1 technology preview
+ */
+U_CAPI BMS * U_EXPORT2
+bms_open(UCD *ucd,
+ const UChar *pattern, int32_t patternLength,
+ const UChar *target, int32_t targetLength,
+ UErrorCode *status);
+
+/**
+ * Close a <code>BMS</code> object and release all the
+ * storage associated with it.
+ *
+ * @param bms - the <code>BMS</code> object to close.
+ * @internal ICU 4.0.1 technology preview
+ */
+U_CAPI void U_EXPORT2
+bms_close(BMS *bms);
+
+/**
+ * Test the pattern to see if it generates any CEs.
+ *
+ * @param bms - the <code>BMS</code> object
+ * @return <code>TRUE</code> if the pattern string did not generate any CEs
+ *
+ * @internal ICU 4.0.1 technology preview
+ */
+U_CAPI UBool U_EXPORT2
+bms_empty(BMS *bms);
+
+/**
+ * Get the <code>UCD</code> object used to create
+ * a given <code>BMS</code> object.
+ *
+ * @param bms - the <code>BMS</code> object
+ *
+ * @return - the <code>UCD</code> object used to create
+ * the given <code>BMS</code> object.
+ *
+ * @internal ICU 4.0.1 technology preview
+ */
+U_CAPI UCD * U_EXPORT2
+bms_getData(BMS *bms);
+
+/**
+ * Search for the pattern string in the target string.
+ *
+ * @param bms - the <code>BMS</code> object
+ * @param offset - the offset in the target string at which to begin the search
+ * @param start - will be set to the starting offset of the match, or -1 if
there's no match
+ * @param end - will be set to the ending offset of the match, or -1 if
there's no match
+ *
+ * @return <code>TRUE</code> if the match succeeds, <code>FALSE</code>
otherwise.
+ *
+ * @internal ICU 4.0.1 technology preview
+ */
+U_CAPI UBool U_EXPORT2
+bms_search(BMS *bms, int32_t offset, int32_t *start, int32_t *end);
+
+/**
+ * Set the target string for the match.
+ *
+ * @param bms - the <code>BMS</code> object
+ * @param target - the new target string
+ * @param targetLength - the length of the new target string
+ * @param status - will be set if any errors occur.
+ *
+ * @internal ICU 4.0.1 technology preview
+ */
+U_CAPI void U_EXPORT2
+bms_setTargetString(BMS *bms, const UChar *target, int32_t targetLength,
UErrorCode *status);
+
+#endif
+
+#endif /* _BMS_H */
Added: haiku/trunk/headers/libs/icu/unicode/bmsearch.h
===================================================================
--- haiku/trunk/headers/libs/icu/unicode/bmsearch.h
(rev 0)
+++ haiku/trunk/headers/libs/icu/unicode/bmsearch.h 2010-07-13 19:04:40 UTC
(rev 37498)
@@ -0,0 +1,226 @@
+/*
+ ******************************************************************************
+ * Copyright (C) 1996-2010, International Business Machines *
+ * Corporation and others. All Rights Reserved. *
+ ******************************************************************************
+ */
+
+/**
+ * \file
+ * \brief C++ API: Boyer-Moore StringSearch technology preview
+ * \internal ICU 4.0.1 technology preview
+ */
+
+#ifndef B_M_SEARCH_H
+#define B_M_SEARCH_H
+
+#include "unicode/utypes.h"
+
+#if !UCONFIG_NO_COLLATION && !UCONFIG_NO_BREAK_ITERATION
+
+#include "unicode/uobject.h"
+#include "unicode/ucol.h"
+
+#include "unicode/colldata.h"
+
+U_NAMESPACE_BEGIN
+
+class BadCharacterTable;
+class GoodSuffixTable;
+class Target;
+
+/**
+ * BoyerMooreSearch
+ *
+ * This object holds the information needed to do a Collation sensitive
Boyer-Moore search. It encapulates
+ * the pattern, the "bad character" and "good suffix" tables, the
Collator-based data needed to compute them,
+ * and a reference to the text being searched.
+ *
+ * To do a search, you fist need to get a <code>CollData</code> object by
calling <code>CollData::open</code>.
+ * Then you construct a <code>BoyerMooreSearch</code> object from the
<code>CollData</code> object, the pattern
+ * string and the target string. Then you call the <code>search</code> method.
Here's a code sample:
+ *
+ * <pre>
+ * void boyerMooreExample(UCollator *collator, UnicodeString *pattern,
UnicodeString *target)
+ * {
+ * UErrorCode status = U_ZERO_ERROR;
+ * CollData *collData = CollData::open(collator, status);
+ *
+ * if (U_FAILURE(status)) {
+ * // could not create a CollData object
+ * return;
+ * }
+ *
+ * BoyerMooreSearch *search = new BoyerMooreSearch(collData,
*patternString, target, status);
+ *
+ * if (U_FAILURE(status)) {
+ * // could not create a BoyerMooreSearch object
+ * CollData::close(collData);
+ * return;
+ * }
+ *
+ * int32_t offset = 0, start = -1, end = -1;
+ *
+ * // Find all matches
+ * while (search->search(offset, start, end)) {
+ * // process the match between start and end
+ * ...
+ * // advance past the match
+ * offset = end;
+ * }
+ *
+ * // at this point, if offset == 0, there were no matches
+ * if (offset == 0) {
+ * // handle the case of no matches
+ * }
+ *
+ * delete search;
+ * CollData::close(collData);
+ *
+ * // CollData objects are cached, so the call to
+ * // CollData::close doesn't delete the object.
+ * // Call this if you don't need the object any more.
+ * CollData::flushCollDataCache();
+ * }
+ * </pre>
+ *
+ * NOTE: This is a technology preview. The final version of this API may not
bear any resenblence to this API.
+ *
+ * Knows linitations:
+ * 1) Backwards searching has not been implemented.
+ *
+ * 2) For Han and Hangul characters, this code ignores any Collation
tailorings. In general,
+ * this isn't a problem, but in Korean locals, at strength 1, Hangul
characters are tailored
+ * to be equal to Han characters with the same pronounciation. Because
this code ignroes
+ * tailorings, searching for a Hangul character will not find a Han
character and visa-versa.
+ *
+ * 3) In some cases, searching for a pattern that needs to be normalized and
ends
+ * in a discontiguous contraction may fail. The only known cases of this
are with
+ * the Tibetan script. For example searching for the pattern
+ * "\u0F7F\u0F80\u0F81\u0F82\u0F83\u0F84\u0F85" will fail. (This case is
artificial. We've
+ * been unable to find a pratical, real-world example of this failure.)
+ *
+ * @internal ICU 4.0.1 technology preview
+ *
+ * @see CollData
+ */
+class U_I18N_API BoyerMooreSearch : public UObject
+{
+public:
+ /**
+ * Construct a <code>BoyerMooreSearch</code> object.
+ *
+ * @param theData - A <code>CollData</code> object holding the
Collator-sensitive data
+ * @param patternString - the string for which to search
+ * @param targetString - the string in which to search or
<code>NULL</code> if youu will
+ * set it later by calling
<code>setTargetString</code>.
+ * @param status - will be set if any errors occur.
+ *
+ * Note: if on return, status is set to an error code,
+ * the only safe thing to do with this object is to call
+ * the destructor.
+ *
+ * @internal ICU 4.0.1 technology preview
+ */
+ BoyerMooreSearch(CollData *theData, const UnicodeString &patternString,
const UnicodeString *targetString, UErrorCode &status);
+
+ /**
+ * The desstructor
+ *
+ * @internal ICU 4.0.1 technology preview
+ */
+ ~BoyerMooreSearch();
+
+ /**
+ * Test the pattern to see if it generates any CEs.
+ *
+ * @return <code>TRUE</code> if the pattern string did not generate any CEs
+ *
+ * @internal ICU 4.0.1 technology preview
+ */
+ UBool empty();
+
+ /**
+ * Search for the pattern string in the target string.
+ *
+ * @param offset - the offset in the target string at which to begin the
search
+ * @param start - will be set to the starting offset of the match, or -1
if there's no match
+ * @param end - will be set to the ending offset of the match, or -1 if
there's no match
+ *
+ * @return <code>TRUE</code> if the match succeeds, <code>FALSE</code>
otherwise.
+ *
+ * @internal ICU 4.0.1 technology preview
+ */
+ UBool search(int32_t offset, int32_t &start, int32_t &end);
+
+ /**
+ * Set the target string for the match.
+ *
+ * @param targetString - the new target string
+ * @param status - will be set if any errors occur.
+ *
+ * @internal ICU 4.0.1 technology preview
+ */
+ void setTargetString(const UnicodeString *targetString, UErrorCode
&status);
+
+ // **** no longer need these? ****
+ /**
+ * Return the <code>CollData</code> object used for searching
+ *
+ * @return the <code>CollData</code> object used for searching
+ *
+ * @internal ICU 4.0.1 technology preview
+ */
+ CollData *getData();
+
+ /**
+ * Return the CEs generated by the pattern string.
+ *
+ * @return a <code>CEList</code> object holding the CEs generated by the
pattern string.
+ *
+ * @internal ICU 4.0.1 technology preview
+ */
+ CEList *getPatternCEs();
+
+ /**
+ * Return the <code>BadCharacterTable</code> object computed for the
pattern string.
+ *
+ * @return the <code>BadCharacterTable</code> object.
+ *
+ * @internal ICU 4.0.1 technology preview
+ */
+ BadCharacterTable *getBadCharacterTable();
+
+ /**
+ * Return the <code>GoodSuffixTable</code> object computed for the pattern
string.
+ *
+ * @return the <code>GoodSuffixTable</code> object computed for the
pattern string.
+ *
+ * @internal ICU 4.0.1 technology preview
+ */
+ GoodSuffixTable *getGoodSuffixTable();
+
+ /**
+ * UObject glue...
+ * @internal ICU 4.0.1 technology preview
+ */
+ virtual UClassID getDynamicClassID() const;
+ /**
+ * UObject glue...
+ * @internal ICU 4.0.1 technology preview
+ */
+ static UClassID getStaticClassID();
+
+private:
+ CollData *data;
+ CEList *patCEs;
+ BadCharacterTable *badCharacterTable;
+ GoodSuffixTable *goodSuffixTable;
+ UnicodeString pattern;
+ Target *target;
+};
+
+U_NAMESPACE_END
+
+#endif // #if !UCONFIG_NO_COLLATION
+#endif // #ifndef B_M_SEARCH_H
Added: haiku/trunk/headers/libs/icu/unicode/brkiter.h
===================================================================
--- haiku/trunk/headers/libs/icu/unicode/brkiter.h
(rev 0)
+++ haiku/trunk/headers/libs/icu/unicode/brkiter.h 2010-07-13 19:04:40 UTC
(rev 37498)
@@ -0,0 +1,557 @@
+/*
+********************************************************************************
+* Copyright (C) 1997-2010, International Business Machines
+* Corporation and others. All Rights Reserved.
+********************************************************************************
+*
+* File brkiter.h
+*
+* Modification History:
+*
+* Date Name Description
+* 02/18/97 aliu Added typedef for TextCount. Made DONE const.
+* 05/07/97 aliu Fixed DLL declaration.
+* 07/09/97 jfitz Renamed BreakIterator and interface synced with JDK
+* 08/11/98 helena Sync-up JDK1.2.
+* 01/13/2000 helena Added UErrorCode parameter to createXXXInstance
methods.
+********************************************************************************
+*/
+
+#ifndef BRKITER_H
+#define BRKITER_H
+
+#include "unicode/utypes.h"
+
+/**
+ * \file
+ * \brief C++ API: Break Iterator.
+ */
+
+#if UCONFIG_NO_BREAK_ITERATION
+
+U_NAMESPACE_BEGIN
+
+/*
+ * Allow the declaration of APIs with pointers to BreakIterator
+ * even when break iteration is removed from the build.
+ */
+class BreakIterator;
+
+U_NAMESPACE_END
+
+#else
+
+#include "unicode/uobject.h"
+#include "unicode/unistr.h"
+#include "unicode/chariter.h"
+#include "unicode/locid.h"
+#include "unicode/ubrk.h"
+#include "unicode/strenum.h"
+#include "unicode/utext.h"
+#include "unicode/umisc.h"
+
+U_NAMESPACE_BEGIN
+
+/**
+ * The BreakIterator class implements methods for finding the location
+ * of boundaries in text. BreakIterator is an abstract base class.
+ * Instances of BreakIterator maintain a current position and scan over
+ * text returning the index of characters where boundaries occur.
+ * <p>
+ * Line boundary analysis determines where a text string can be broken
+ * when line-wrapping. The mechanism correctly handles punctuation and
+ * hyphenated words.
+ * <p>
+ * Sentence boundary analysis allows selection with correct
+ * interpretation of periods within numbers and abbreviations, and
+ * trailing punctuation marks such as quotation marks and parentheses.
+ * <p>
+ * Word boundary analysis is used by search and replace functions, as
+ * well as within text editing applications that allow the user to
+ * select words with a double click. Word selection provides correct
+ * interpretation of punctuation marks within and following
+ * words. Characters that are not part of a word, such as symbols or
+ * punctuation marks, have word-breaks on both sides.
+ * <p>
+ * Character boundary analysis allows users to interact with
+ * characters as they expect to, for example, when moving the cursor
+ * through a text string. Character boundary analysis provides correct
+ * navigation of through character strings, regardless of how the
+ * character is stored. For example, an accented character might be
+ * stored as a base character and a diacritical mark. What users
+ * consider to be a character can differ between languages.
+ * <p>
+ * The text boundary positions are found according to the rules
+ * described in Unicode Standard Annex #29, Text Boundaries, and
+ * Unicode Standard Annex #14, Line Breaking Properties. These
+ * are available at http://www.unicode.org/reports/tr14/ and
+ * http://www.unicode.org/reports/tr29/.
+ * <p>
+ * In addition to the C++ API defined in this header file, a
+ * plain C API with equivalent functionality is defined in the
+ * file ubrk.h
+ * <p>
+ * Code snippets illustrating the use of the Break Iterator APIs
+ * are available in the ICU User Guide,
+ * http://icu-project.org/userguide/boundaryAnalysis.html
+ * and in the sample program icu/source/samples/break/break.cpp
+ *
+ */
+class U_COMMON_API BreakIterator : public UObject {
+public:
+ /**
+ * destructor
+ * @stable ICU 2.0
+ */
+ virtual ~BreakIterator();
+
+ /**
+ * Return true if another object is semantically equal to this
+ * one. The other object should be an instance of the same subclass of
+ * BreakIterator. Objects of different subclasses are considered
+ * unequal.
+ * <P>
+ * Return true if this BreakIterator is at the same position in the
+ * same text, and is the same class and type (word, line, etc.) of
+ * BreakIterator, as the argument. Text is considered the same if
+ * it contains the same characters, it need not be the same
+ * object, and styles are not considered.
+ * @stable ICU 2.0
+ */
+ virtual UBool operator==(const BreakIterator&) const = 0;
+
+ /**
+ * Returns the complement of the result of operator==
+ * @param rhs The BreakIterator to be compared for inequality
+ * @return the complement of the result of operator==
+ * @stable ICU 2.0
+ */
+ UBool operator!=(const BreakIterator& rhs) const { return
!operator==(rhs); }
+
+ /**
+ * Return a polymorphic copy of this object. This is an abstract
+ * method which subclasses implement.
+ * @stable ICU 2.0
+ */
+ virtual BreakIterator* clone(void) const = 0;
+
+ /**
+ * Return a polymorphic class ID for this object. Different subclasses
+ * will return distinct unequal values.
+ * @stable ICU 2.0
+ */
+ virtual UClassID getDynamicClassID(void) const = 0;
+
+ /**
+ * Return a CharacterIterator over the text being analyzed.
+ * @stable ICU 2.0
+ */
+ virtual CharacterIterator& getText(void) const = 0;
+
+
+ /**
+ * Get a UText for the text being analyzed.
+ * The returned UText is a shallow clone of the UText used internally
+ * by the break iterator implementation. It can safely be used to
+ * access the text without impacting any break iterator operations,
+ * but the underlying text itself must not be altered.
+ *
+ * @param fillIn A UText to be filled in. If NULL, a new UText will be
+ * allocated to hold the result.
+ * @param status receives any error codes.
+ * @return The current UText for this break iterator. If an input
+ * UText was provided, it will always be returned.
+ * @stable ICU 3.4
+ */
+ virtual UText *getUText(UText *fillIn, UErrorCode &status) const = 0;
+
+ /**
+ * Change the text over which this operates. The text boundary is
+ * reset to the start.
+ * @param text The UnicodeString used to change the text.
+ * @stable ICU 2.0
+ */
+ virtual void setText(const UnicodeString &text) = 0;
+
+ /**
+ * Reset the break iterator to operate over the text represented by
+ * the UText. The iterator position is reset to the start.
+ *
+ * This function makes a shallow clone of the supplied UText. This means
+ * that the caller is free to immediately close or otherwise reuse the
+ * Utext that was passed as a parameter, but that the underlying text
itself
+ * must not be altered while being referenced by the break iterator.
+ *
+ * @param text The UText used to change the text.
+ * @param status receives any error codes.
+ * @stable ICU 3.4
+ */
+ virtual void setText(UText *text, UErrorCode &status) = 0;
[... truncated: 86570 lines follow ...]
Other related posts: