mirror of
https://github.com/unicode-org/icu.git
synced 2025-04-04 13:05:31 +00:00
ICU-21580 Fix typos in icu4c/
Found via `codespell -q 3 -L ans,anumber,atleast,ba,bre,hace,nd,nin,ois,rsource,som,sur,tht -S icu4c/source/data/zone,icu4c/source/data/lang` ICU-21580 Fix source (related) typos ICU-21580 Revert extraneous auto-encoding ICU-21580 Re-add previous reverted fix without auto-encoding
This commit is contained in:
luz paz
Erik Torres
parent
ac51a1921f
commit
73eca0a9c9
295 changed files with 636 additions and 636 deletions
|
|
@ -302,7 +302,7 @@ property of their respective owners.
|
|||
# Redistributions of source code must retain the above copyright notice, this
|
||||
# list of conditions and the following disclaimer. Redistributions in binary
|
||||
# form must reproduce the above copyright notice, this list of conditions and
|
||||
# the following disclaimer in the documentation and/or ther materials
|
||||
# the following disclaimer in the documentation and/or other materials
|
||||
# provided with the distribution.
|
||||
#
|
||||
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
|
|
|
|||
|
|
@ -60,9 +60,9 @@ in addition to platform-specific settings (like a specific mandir or
|
|||
sysconfdir). Note that the use of --disable-rpath assumes that the
|
||||
packaging is made for a standard location, or that the package
|
||||
installation/deinstallation will correctly manage the configuration
|
||||
of the system's dyanmic loader. This is the right way of doing things.
|
||||
of the system's dynamic loader. This is the right way of doing things.
|
||||
|
||||
The configure script invokation should also be done with
|
||||
The configure script invocation should also be done with
|
||||
|
||||
CFLAGS="-O2"
|
||||
|
||||
|
|
@ -119,7 +119,7 @@ This package contains:
|
|||
|
||||
+ The ICU development package
|
||||
|
||||
The ICU developpment package is named `libicu-dev'. It provides all
|
||||
The ICU development package is named `libicu-dev'. It provides all
|
||||
the files necessary to write applications that use ICU, along with
|
||||
examples and some documentation.
|
||||
|
||||
|
|
@ -130,7 +130,7 @@ headers.
|
|||
- The .so symbolic links used by the linker to link against the
|
||||
latest version of the libraries.
|
||||
- A sample Makefile fragment that can be included by applications
|
||||
using ICU, to faciliate their building, along with a platform-specific
|
||||
using ICU, to facilitate their building, along with a platform-specific
|
||||
configuration file included by this fragment.
|
||||
- The sample applications from the ICU source tree, in an appropriate
|
||||
location for the system that the package is installed on (for example,
|
||||
|
|
|
|||
2
icu4c/source/aclocal.m4
vendored
2
icu4c/source/aclocal.m4
vendored
|
|
@ -100,7 +100,7 @@ dnl Check to see whether a particular set of modules exists. Similar to
|
|||
dnl PKG_CHECK_MODULES(), but does not set variables or print errors.
|
||||
dnl
|
||||
dnl Please remember that m4 expands AC_REQUIRE([PKG_PROG_PKG_CONFIG])
|
||||
dnl only at the first occurence in configure.ac, so if the first place
|
||||
dnl only at the first occurrence in configure.ac, so if the first place
|
||||
dnl it's called might be skipped (such as if it is within an "if", you
|
||||
dnl have to call PKG_CHECK_EXISTS manually
|
||||
AC_DEFUN([PKG_CHECK_EXISTS],
|
||||
|
|
|
|||
|
|
@ -14,7 +14,7 @@
|
|||
C4661 No suitable definition provided for explicit template instantiation request.
|
||||
C4715 Not all control paths return a value.
|
||||
C4706 Assignment within conditional expression.
|
||||
C4005 Macro redifintion.
|
||||
C4005 Macro redefinition.
|
||||
C4068 Unknown pragma.
|
||||
C4267 Conversion from size_t to type, possible loss of data.
|
||||
C4910 __declspec(dllexport) and extern are incompatible on an explicit instantiation.
|
||||
|
|
|
|||
|
|
@ -494,7 +494,7 @@ Hashtable *CanonicalIterator::getEquivalents2(Hashtable *fillinResult, const UCh
|
|||
|
||||
/**
|
||||
* See if the decomposition of cp2 is at segment starting at segmentPos
|
||||
* (with canonical rearrangment!)
|
||||
* (with canonical rearrangement!)
|
||||
* If so, take the remainder, and return the equivalents
|
||||
*/
|
||||
Hashtable *CanonicalIterator::extract(Hashtable *fillinResult, UChar32 comp, const UChar *segment, int32_t segLen, int32_t segmentPos, UErrorCode &status) {
|
||||
|
|
|
|||
|
|
@ -28,7 +28,7 @@
|
|||
* default code page conversion, which will do the best job possible,
|
||||
* but may be lossy, depending on the platform.
|
||||
*
|
||||
* If no other conversion is available, use invariant conversion and substitue
|
||||
* If no other conversion is available, use invariant conversion and substitute
|
||||
* '?' for non-invariant characters.
|
||||
*
|
||||
* Example Usage:
|
||||
|
|
|
|||
|
|
@ -181,7 +181,7 @@ static const int32_t THAI_ROOT_COMBINE_THRESHOLD = 3;
|
|||
// dictionary word, with a preceding word
|
||||
static const int32_t THAI_PREFIX_COMBINE_THRESHOLD = 3;
|
||||
|
||||
// Ellision character
|
||||
// Elision character
|
||||
static const int32_t THAI_PAIYANNOI = 0x0E2F;
|
||||
|
||||
// Repeat character
|
||||
|
|
@ -531,7 +531,7 @@ foundBest:
|
|||
}
|
||||
|
||||
// We come here after having either found a word or not. We look ahead to the
|
||||
// next word. If it's not a dictionary word, we will combine it withe the word we
|
||||
// next word. If it's not a dictionary word, we will combine it with the word we
|
||||
// just found (if there is one), but only if the preceding word does not exceed
|
||||
// the threshold.
|
||||
// The text iterator should now be positioned at the end of the word we found.
|
||||
|
|
@ -724,7 +724,7 @@ foundBest:
|
|||
}
|
||||
|
||||
// We come here after having either found a word or not. We look ahead to the
|
||||
// next word. If it's not a dictionary word, we will combine it withe the word we
|
||||
// next word. If it's not a dictionary word, we will combine it with the word we
|
||||
// just found (if there is one), but only if the preceding word does not exceed
|
||||
// the threshold.
|
||||
// The text iterator should now be positioned at the end of the word we found.
|
||||
|
|
|
|||
|
|
@ -526,7 +526,7 @@ uplug_getPlugLoadStatus(UPlugData *plug) {
|
|||
|
||||
|
||||
/**
|
||||
* Initialize a plugin fron an entrypoint and library - but don't load it.
|
||||
* Initialize a plugin from an entrypoint and library - but don't load it.
|
||||
*/
|
||||
static UPlugData* uplug_initPlugFromEntrypointAndLibrary(UPlugEntrypoint *entrypoint, const char *config, void *lib, const char *sym,
|
||||
UErrorCode *status) {
|
||||
|
|
|
|||
|
|
@ -752,7 +752,7 @@ AliasDataBuilder::readLanguageAlias(
|
|||
alias, strings, types, replacementIndexes, length,
|
||||
#if U_DEBUG
|
||||
[](const char* type) {
|
||||
// Assert the aliasFrom only contains the following possibilties
|
||||
// Assert the aliasFrom only contains the following possibilities
|
||||
// language_REGION_variant
|
||||
// language_REGION
|
||||
// language_variant
|
||||
|
|
@ -1351,7 +1351,7 @@ AliasReplacer::replaceLanguage(
|
|||
}
|
||||
if (replacedExtensions != nullptr) {
|
||||
// DO NOTHING
|
||||
// UTS35 does not specifiy what should we do if we have extensions in the
|
||||
// UTS35 does not specify what should we do if we have extensions in the
|
||||
// replacement. Currently we know only the following 4 "BCP47 LegacyRules" have
|
||||
// extensions in them languageAlias:
|
||||
// i_default => en_x_i_default
|
||||
|
|
@ -1710,7 +1710,7 @@ AliasReplacer::replace(const Locale& locale, CharString& out, UErrorCode& status
|
|||
} // while(1)
|
||||
|
||||
if (U_FAILURE(status)) { return false; }
|
||||
// Nothing changed and we know the order of the vaiants are not change
|
||||
// Nothing changed and we know the order of the variants are not change
|
||||
// because we have no variant or only one.
|
||||
const char* extensionsStr = locale_getKeywordsStart(locale.getName());
|
||||
if (changed == 0 && variants.size() <= 1 && extensionsStr == nullptr) {
|
||||
|
|
|
|||
|
|
@ -115,7 +115,7 @@ findLikelySubtags(const char* localeID,
|
|||
* @param tag The tag to add.
|
||||
* @param tagLength The length of the tag.
|
||||
* @param buffer The output buffer.
|
||||
* @param bufferLength The length of the output buffer. This is an input/ouput parameter.
|
||||
* @param bufferLength The length of the output buffer. This is an input/output parameter.
|
||||
**/
|
||||
static void U_CALLCONV
|
||||
appendTag(
|
||||
|
|
|
|||
|
|
@ -28,7 +28,7 @@
|
|||
|
||||
U_NAMESPACE_BEGIN
|
||||
|
||||
// Uncomment the follwoing #define to debug.
|
||||
// Uncomment the following #define to debug.
|
||||
// #define LSTM_DEBUG 1
|
||||
// #define LSTM_VECTORIZER_DEBUG 1
|
||||
|
||||
|
|
@ -554,7 +554,7 @@ GraphemeClusterVectorizer::~GraphemeClusterVectorizer()
|
|||
{
|
||||
}
|
||||
|
||||
constexpr int32_t MAX_GRAPHEME_CLSTER_LENTH = 10;
|
||||
constexpr int32_t MAX_GRAPHEME_CLSTER_LENGTH = 10;
|
||||
|
||||
void GraphemeClusterVectorizer::vectorize(
|
||||
UText *text, int32_t startPos, int32_t endPos,
|
||||
|
|
@ -576,13 +576,13 @@ void GraphemeClusterVectorizer::vectorize(
|
|||
}
|
||||
int32_t last = startPos;
|
||||
int32_t current = startPos;
|
||||
UChar str[MAX_GRAPHEME_CLSTER_LENTH];
|
||||
UChar str[MAX_GRAPHEME_CLSTER_LENGTH];
|
||||
while ((current = graphemeIter->next()) != BreakIterator::DONE) {
|
||||
if (current >= endPos) {
|
||||
break;
|
||||
}
|
||||
if (current > startPos) {
|
||||
utext_extract(text, last, current, str, MAX_GRAPHEME_CLSTER_LENTH, &status);
|
||||
utext_extract(text, last, current, str, MAX_GRAPHEME_CLSTER_LENGTH, &status);
|
||||
if (U_FAILURE(status)) return;
|
||||
offsets.addElement(last, status);
|
||||
indices.addElement(stringToIndex(str), status);
|
||||
|
|
@ -593,7 +593,7 @@ void GraphemeClusterVectorizer::vectorize(
|
|||
if (U_FAILURE(status) || last >= endPos) {
|
||||
return;
|
||||
}
|
||||
utext_extract(text, last, endPos, str, MAX_GRAPHEME_CLSTER_LENTH, &status);
|
||||
utext_extract(text, last, endPos, str, MAX_GRAPHEME_CLSTER_LENGTH, &status);
|
||||
if (U_SUCCESS(status)) {
|
||||
offsets.addElement(last, status);
|
||||
indices.addElement(stringToIndex(str), status);
|
||||
|
|
|
|||
|
|
@ -46,7 +46,7 @@ public:
|
|||
|
||||
/**
|
||||
* Converts a category name such as "zero", "one", "two", "few", "many"
|
||||
* or "other" to a category enum. Returns NONE for urecongized
|
||||
* or "other" to a category enum. Returns NONE for unrecognized
|
||||
* category name.
|
||||
*/
|
||||
static Category toCategory(const UnicodeString &categoryName);
|
||||
|
|
|
|||
|
|
@ -918,7 +918,7 @@ static UBool compareBinaryFiles(const char* defaultTZFileName, const char* TZFil
|
|||
if (sizeFile != tzInfo->defaultTZFileSize) {
|
||||
result = FALSE;
|
||||
} else {
|
||||
/* Store the data from the files in seperate buffers and
|
||||
/* Store the data from the files in separate buffers and
|
||||
* compare each byte to determine equality.
|
||||
*/
|
||||
if (tzInfo->defaultTZBuffer == NULL) {
|
||||
|
|
|
|||
|
|
@ -671,7 +671,7 @@ int32_t RuleBasedBreakIterator::preceding(int32_t offset) {
|
|||
}
|
||||
|
||||
/**
|
||||
* Returns true if the specfied position is a boundary position. As a side
|
||||
* Returns true if the specified position is a boundary position. As a side
|
||||
* effect, leaves the iterator pointing to the first boundary position at
|
||||
* or after "offset".
|
||||
*
|
||||
|
|
@ -1037,7 +1037,7 @@ int32_t RuleBasedBreakIterator::handleSafePrevious(int32_t fromPosition) {
|
|||
|
||||
if (state == STOP_STATE) {
|
||||
// This is the normal exit from the lookup state machine.
|
||||
// Transistion to state zero means we have found a safe point.
|
||||
// Transition to state zero means we have found a safe point.
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -7,7 +7,7 @@
|
|||
# and others. All rights reserved.
|
||||
#**************************************************************************
|
||||
#
|
||||
# rbbicst Compile the RBBI rule paser state table data into initialized C data.
|
||||
# rbbicst Compile the RBBI rule parser state table data into initialized C data.
|
||||
# Usage:
|
||||
# cd icu/source/common
|
||||
# perl rbbicst.pl < rbbirpt.txt > rbbirpt.h
|
||||
|
|
@ -357,7 +357,7 @@ else
|
|||
print "U_NAMESPACE_BEGIN\n";
|
||||
|
||||
#
|
||||
# Emit the constants for indicies of Unicode Sets
|
||||
# Emit the constants for indices of Unicode Sets
|
||||
# Define one constant for each of the character classes encountered.
|
||||
# At the same time, store the index corresponding to the set name back into hash.
|
||||
#
|
||||
|
|
@ -382,7 +382,7 @@ else
|
|||
print " rbbiLastAction};\n\n";
|
||||
|
||||
#
|
||||
# Emit the struct definition for transtion table elements.
|
||||
# Emit the struct definition for transition table elements.
|
||||
#
|
||||
print "//-------------------------------------------------------------------------------\n";
|
||||
print "//\n";
|
||||
|
|
|
|||
|
|
@ -283,7 +283,7 @@ void RBBIDataWrapper::printData() {
|
|||
printTable("Forward State Transition Table", fForwardTable);
|
||||
printTable("Reverse State Transition Table", fReverseTable);
|
||||
|
||||
RBBIDebugPrintf("\nOrignal Rules source:\n");
|
||||
RBBIDebugPrintf("\nOriginal Rules source:\n");
|
||||
for (int32_t c=0; fRuleSource[c] != 0; c++) {
|
||||
RBBIDebugPrintf("%c", fRuleSource[c]);
|
||||
}
|
||||
|
|
|
|||
|
|
@ -351,7 +351,7 @@ void RBBINode::printTree(const RBBINode *node, UBool printHeading) {
|
|||
printNode(node);
|
||||
if (node != NULL) {
|
||||
// Only dump the definition under a variable reference if asked to.
|
||||
// Unconditinally dump children of all other node types.
|
||||
// Unconditionally dump children of all other node types.
|
||||
if (node->fType != varRef) {
|
||||
if (node->fLeftChild != NULL) {
|
||||
printTree(node->fLeftChild, FALSE);
|
||||
|
|
|
|||
|
|
@ -71,7 +71,7 @@ class RBBINode : public UMemory {
|
|||
int fLastPos; // Last position in the rule source string
|
||||
// of any text associated with this node.
|
||||
// If there's a right child, this will be the same
|
||||
// as that child's last postion.
|
||||
// as that child's last position.
|
||||
|
||||
UBool fNullable; // See Aho.
|
||||
int32_t fVal; // For leafChar nodes, the value.
|
||||
|
|
@ -108,7 +108,7 @@ class RBBINode : public UMemory {
|
|||
|
||||
private:
|
||||
RBBINode &operator = (const RBBINode &other); // No defs.
|
||||
UBool operator == (const RBBINode &other); // Private, so these functions won't accidently be used.
|
||||
UBool operator == (const RBBINode &other); // Private, so these functions won't accidentally be used.
|
||||
|
||||
#ifdef RBBI_DEBUG
|
||||
public:
|
||||
|
|
|
|||
|
|
@ -50,7 +50,7 @@
|
|||
# | character from the input only if 'n' appears here.
|
||||
# |
|
||||
# |--- Character or named character classes to test for. If the current character being scanned
|
||||
# matches, peform the actions and go to the state specified on this line.
|
||||
# matches, perform the actions and go to the state specified on this line.
|
||||
# The input character is tested sequentally, in the order written. The characters and
|
||||
# character classes tested for do not need to be mutually exclusive. The first match wins.
|
||||
#
|
||||
|
|
@ -258,7 +258,7 @@ expr-cont-no-tag:
|
|||
# to go to after completion of the variable name scanning.
|
||||
#
|
||||
# The current input character must be the $ that introduces the name.
|
||||
# The $ is consummed here rather than in the state that first detected it
|
||||
# The $ is consumed here rather than in the state that first detected it
|
||||
# so that the doStartVariableName action only needs to happen in one
|
||||
# place (here), and the other states don't need to worry about it.
|
||||
#
|
||||
|
|
|
|||
|
|
@ -175,7 +175,7 @@ RBBIRuleScanner::~RBBIRuleScanner() {
|
|||
|
||||
// Node Stack.
|
||||
// Normally has one entry, which is the entire parse tree for the rules.
|
||||
// If errors occured, there may be additional subtrees left on the stack.
|
||||
// If errors occurred, there may be additional subtrees left on the stack.
|
||||
while (fNodeStackPtr > 0) {
|
||||
delete fNodeStack[fNodeStackPtr];
|
||||
fNodeStackPtr--;
|
||||
|
|
@ -375,7 +375,7 @@ UBool RBBIRuleScanner::doParseActions(int32_t action)
|
|||
RBBINode **destRules = (fReverseRule? &fRB->fSafeRevTree : fRB->fDefaultTree);
|
||||
|
||||
if (*destRules != NULL) {
|
||||
// This is not the first rule encounted.
|
||||
// This is not the first rule encountered.
|
||||
// OR previous stuff (from *destRules)
|
||||
// with the current rule expression (on the Node Stack)
|
||||
// with the resulting OR expression going to *destRules
|
||||
|
|
@ -1223,7 +1223,7 @@ void RBBIRuleScanner::scanSet() {
|
|||
// TODO: Get more accurate position of the error from UnicodeSet's return info.
|
||||
// UnicodeSet appears to not be reporting correctly at this time.
|
||||
#ifdef RBBI_DEBUG
|
||||
RBBIDebugPrintf("UnicodeSet parse postion.ErrorIndex = %d\n", pos.getIndex());
|
||||
RBBIDebugPrintf("UnicodeSet parse position.ErrorIndex = %d\n", pos.getIndex());
|
||||
#endif
|
||||
error(localStatus);
|
||||
delete uset;
|
||||
|
|
@ -1244,7 +1244,7 @@ void RBBIRuleScanner::scanSet() {
|
|||
}
|
||||
|
||||
|
||||
// Advance the RBBI parse postion over the UnicodeSet pattern.
|
||||
// Advance the RBBI parse position over the UnicodeSet pattern.
|
||||
// Don't just set fScanIndex because the line/char positions maintained
|
||||
// for error reporting would be thrown off.
|
||||
i = pos.getIndex();
|
||||
|
|
@ -1267,7 +1267,7 @@ void RBBIRuleScanner::scanSet() {
|
|||
fRB->fRules.extractBetween(n->fFirstPos, n->fLastPos, n->fText);
|
||||
// findSetFor() serves several purposes here:
|
||||
// - Adopts storage for the UnicodeSet, will be responsible for deleting.
|
||||
// - Mantains collection of all sets in use, needed later for establishing
|
||||
// - Maintains collection of all sets in use, needed later for establishing
|
||||
// character categories for run time engine.
|
||||
// - Eliminates mulitiple instances of the same set.
|
||||
// - Creates a new uset node if necessary (if this isn't a duplicate.)
|
||||
|
|
|
|||
|
|
@ -79,7 +79,7 @@ void RBBITableBuilder::buildForwardTable() {
|
|||
|
||||
//
|
||||
// Walk through the tree, replacing any references to $variables with a copy of the
|
||||
// parse tree for the substition expression.
|
||||
// parse tree for the substitution expression.
|
||||
//
|
||||
fTree = fTree->flattenVariables();
|
||||
#ifdef RBBI_DEBUG
|
||||
|
|
@ -694,7 +694,7 @@ void RBBITableBuilder::buildStateTable() {
|
|||
}
|
||||
}
|
||||
return;
|
||||
// delete local pointers only if error occured.
|
||||
// delete local pointers only if error occurred.
|
||||
ExitBuildSTdeleteall:
|
||||
delete initialState;
|
||||
delete failState;
|
||||
|
|
@ -1445,7 +1445,7 @@ void RBBITableBuilder::buildSafeReverseTable(UErrorCode &status) {
|
|||
// the first of a pair. In each of these rows, the entry for the second character
|
||||
// of a safe pair is set to the stop state (0), indicating that a match was found.
|
||||
// All other table entries are set to the state corresponding the current input
|
||||
// character, allowing that charcter to be the of a start following pair.
|
||||
// character, allowing that character to be the of a start following pair.
|
||||
//
|
||||
// Because the safe rules are to be run in reverse, moving backwards in the text,
|
||||
// the first and second pair categories are swapped when building the table.
|
||||
|
|
@ -1490,7 +1490,7 @@ void RBBITableBuilder::buildSafeReverseTable(UErrorCode &status) {
|
|||
// The table as a whole is UVector<UnicodeString>
|
||||
// Each row is represented by a UnicodeString, being used as a Vector<int16>.
|
||||
// Row 0 is the stop state.
|
||||
// Row 1 is the start sate.
|
||||
// Row 1 is the start state.
|
||||
// Row 2 and beyond are other states, initially one per char class, but
|
||||
// after initial construction, many of the states will be combined, compacting the table.
|
||||
// The String holds the nextState data only. The four leading fields of a row, fAccepting,
|
||||
|
|
|
|||
|
|
@ -69,12 +69,12 @@ public:
|
|||
bool findDuplCharClassFrom(IntPair *categories);
|
||||
|
||||
/** Remove a column from the state table. Used when two character categories
|
||||
* have been found equivalent, and merged together, to eliminate the uneeded table column.
|
||||
* have been found equivalent, and merged together, to eliminate the unneeded table column.
|
||||
*/
|
||||
void removeColumn(int32_t column);
|
||||
|
||||
/**
|
||||
* Check for, and remove dupicate states (table rows).
|
||||
* Check for, and remove duplicate states (table rows).
|
||||
* @return the number of states removed.
|
||||
*/
|
||||
int32_t removeDuplicateStates();
|
||||
|
|
|
|||
|
|
@ -135,7 +135,7 @@ U_NAMESPACE_BEGIN
|
|||
* so forth, until the chain is exhausted or the tag is found.
|
||||
*
|
||||
* Thread-safety is implemented around caches, both the cache that
|
||||
* stores all the resouce data, and the cache that stores flags
|
||||
* stores all the resource data, and the cache that stores flags
|
||||
* indicating whether or not a file has been visited. These caches
|
||||
* delete their storage at static cleanup time, when the process
|
||||
* quits.
|
||||
|
|
|
|||
|
|
@ -238,7 +238,7 @@ public:
|
|||
* you're removing pointer to this somewhere. Management of that
|
||||
* pointer will have to know how to deal with refcounts. Once
|
||||
* the refcount drops to zero, the resource is released. Return
|
||||
* false if the resouce has been released.
|
||||
* false if the resource has been released.
|
||||
*/
|
||||
CacheEntry* unref() {
|
||||
if ((--refcount) == 0) {
|
||||
|
|
|
|||
|
|
@ -363,7 +363,7 @@ public:
|
|||
|
||||
/**
|
||||
* <p>ServiceListener is the listener that ICUService provides by default.
|
||||
* ICUService will notifiy this listener when factories are added to
|
||||
* ICUService will notify this listener when factories are added to
|
||||
* or removed from the service. Subclasses can provide
|
||||
* different listener interfaces that extend EventListener, and modify
|
||||
* acceptsListener and notifyListener as appropriate.</p>
|
||||
|
|
|
|||
|
|
@ -2147,7 +2147,7 @@ escape:
|
|||
changeState_2022(args->converter,&(mySource),
|
||||
mySourceLimit, ISO_2022_JP,err);
|
||||
|
||||
/* If in ISO-2022-JP only and we successully completed an escape sequence, but previous segment was empty, create an error */
|
||||
/* If in ISO-2022-JP only and we successfully completed an escape sequence, but previous segment was empty, create an error */
|
||||
if(myData->version==0 && myData->key==0 && U_SUCCESS(*err) && myData->isEmptySegment) {
|
||||
*err = U_ILLEGAL_ESCAPE_SEQUENCE;
|
||||
args->converter->toUCallbackReason = UCNV_IRREGULAR;
|
||||
|
|
@ -2849,21 +2849,21 @@ getTrailByte:
|
|||
* SS2 is a Chinese character as defined in CNS
|
||||
* 11643-plane-2, until another SS2designation
|
||||
* appears
|
||||
* (Meaning <ESC>N must preceed every 2 byte
|
||||
* (Meaning <ESC>N must precede every 2 byte
|
||||
* sequence.)
|
||||
*
|
||||
* ESC $ + I Indicates the immediate two bytes following SS3
|
||||
* is a Chinese character as defined in CNS
|
||||
* 11643-plane-3, until another SS3designation
|
||||
* appears
|
||||
* (Meaning <ESC>O must preceed every 2 byte
|
||||
* (Meaning <ESC>O must precede every 2 byte
|
||||
* sequence.)
|
||||
*
|
||||
* ESC $ + J Indicates the immediate two bytes following SS3
|
||||
* is a Chinese character as defined in CNS
|
||||
* 11643-plane-4, until another SS3designation
|
||||
* appears
|
||||
* (In English: <ESC>O must preceed every 2 byte
|
||||
* (In English: <ESC>O must precede every 2 byte
|
||||
* sequence.)
|
||||
*
|
||||
* ESC $ + K Indicates the immediate two bytes following SS3
|
||||
|
|
|
|||
|
|
@ -164,7 +164,7 @@ typedef const char * (*UConverterGetName) (const UConverter *cnv);
|
|||
* If this function is not set, then ucnv_cbFromUWriteSub() writes
|
||||
* the substitution character from UConverter.
|
||||
* For stateful converters, it is typically necessary to handle this
|
||||
* specificially for the converter in order to properly maintain the state.
|
||||
* specifically for the converter in order to properly maintain the state.
|
||||
*/
|
||||
typedef void (*UConverterWriteSub) (UConverterFromUnicodeArgs *pArgs, int32_t offsetIndex, UErrorCode *pErrorCode);
|
||||
|
||||
|
|
|
|||
|
|
@ -9,7 +9,7 @@
|
|||
*
|
||||
* ucnv_imp.h:
|
||||
* Contains all internal and external data structure definitions
|
||||
* Created & Maitained by Bertrand A. Damiba
|
||||
* Created & Maintained by Bertrand A. Damiba
|
||||
*
|
||||
*
|
||||
*
|
||||
|
|
|
|||
|
|
@ -878,7 +878,7 @@ _LMBCSFromUnicode(UConverterFromUnicodeArgs* args,
|
|||
A) The optimization group
|
||||
B) The locale group
|
||||
C) The last group that succeeded with this string.
|
||||
D) every other group that's relevent (single or double)
|
||||
D) every other group that's relevant (single or double)
|
||||
E) If its single-byte ambiguous, try the exceptions group
|
||||
|
||||
4. And as a grand fallback: Unicode
|
||||
|
|
@ -1049,7 +1049,7 @@ _LMBCSFromUnicode(UConverterFromUnicodeArgs* args,
|
|||
}
|
||||
}
|
||||
|
||||
/* we have a translation. increment source and write as much as posible to target */
|
||||
/* we have a translation. increment source and write as much as possible to target */
|
||||
args->source++;
|
||||
pLMBCS = LMBCS;
|
||||
while (args->target < args->targetLimit && bytes_written--)
|
||||
|
|
|
|||
|
|
@ -488,7 +488,7 @@ static const UConverterImpl _UTF32BEImpl = {
|
|||
NULL
|
||||
};
|
||||
|
||||
/* The 1232 CCSID refers to any version of Unicode with any endianess of UTF-32 */
|
||||
/* The 1232 CCSID refers to any version of Unicode with any endianness of UTF-32 */
|
||||
static const UConverterStaticData _UTF32BEStaticData = {
|
||||
sizeof(UConverterStaticData),
|
||||
"UTF-32BE",
|
||||
|
|
@ -983,7 +983,7 @@ static const UConverterImpl _UTF32LEImpl = {
|
|||
NULL
|
||||
};
|
||||
|
||||
/* The 1232 CCSID refers to any version of Unicode with any endianess of UTF-32 */
|
||||
/* The 1232 CCSID refers to any version of Unicode with any endianness of UTF-32 */
|
||||
static const UConverterStaticData _UTF32LEStaticData = {
|
||||
sizeof(UConverterStaticData),
|
||||
"UTF-32LE",
|
||||
|
|
@ -1230,7 +1230,7 @@ static const UConverterImpl _UTF32Impl = {
|
|||
NULL
|
||||
};
|
||||
|
||||
/* The 1236 CCSID refers to any version of Unicode with a BOM sensitive endianess of UTF-32 */
|
||||
/* The 1236 CCSID refers to any version of Unicode with a BOM sensitive endianness of UTF-32 */
|
||||
static const UConverterStaticData _UTF32StaticData = {
|
||||
sizeof(UConverterStaticData),
|
||||
"UTF-32",
|
||||
|
|
|
|||
|
|
@ -128,7 +128,7 @@ typedef struct {
|
|||
MaskEnum currentMaskToUnicode; /* mask for current state in toUnicode */
|
||||
MaskEnum defMaskToUnicode; /* mask for default state in toUnicode */
|
||||
UBool isFirstBuffer; /* boolean for fromUnicode to see if we need to announce the first script */
|
||||
UBool resetToDefaultToUnicode; /* boolean for reseting to default delta and mask when a newline is encountered*/
|
||||
UBool resetToDefaultToUnicode; /* boolean for resetting to default delta and mask when a newline is encountered*/
|
||||
char name[sizeof(ISCII_CNV_PREFIX) + 1];
|
||||
UChar32 prevToUnicodeStatus; /* Hold the previous toUnicodeStatus. This is necessary because we may need to know the last two code points. */
|
||||
} UConverterDataISCII;
|
||||
|
|
@ -1105,7 +1105,7 @@ getTrail:
|
|||
}
|
||||
|
||||
static const uint16_t lookupTable[][2]={
|
||||
{ ZERO, ZERO }, /*DEFALT*/
|
||||
{ ZERO, ZERO }, /*DEFAULT*/
|
||||
{ ZERO, ZERO }, /*ROMAN*/
|
||||
{ DEVANAGARI, DEV_MASK },
|
||||
{ BENGALI, BNG_MASK },
|
||||
|
|
@ -1167,12 +1167,12 @@ static const uint16_t lookupTable[][2]={
|
|||
* ii) EXT : Extension code is used to declare switching to Sanskrit and for obscure,
|
||||
* obsolete characters
|
||||
* Pre context
|
||||
* i) Halant: if preceeded by a halant then it is a explicit halant
|
||||
* i) Halant: if preceded by a halant then it is a explicit halant
|
||||
* ii) Nukta :
|
||||
* a) if preceeded by a halant then it is a soft halant
|
||||
* b) if preceeded by specific consonants and the ligatures have pre-composed
|
||||
* a) if preceded by a halant then it is a soft halant
|
||||
* b) if preceded by specific consonants and the ligatures have pre-composed
|
||||
* characters in Unicode then convert to pre-composed characters
|
||||
* iii) Danda: If Danda is preceeded by a Danda then convert to Double Danda
|
||||
* iii) Danda: If Danda is preceded by a Danda then convert to Double Danda
|
||||
*
|
||||
*/
|
||||
|
||||
|
|
@ -1208,7 +1208,7 @@ UConverter_toUnicode_ISCII_OFFSETS_LOGIC(UConverterToUnicodeArgs *args, UErrorCo
|
|||
if (target < targetLimit) {
|
||||
sourceChar = (unsigned char)*(source)++;
|
||||
|
||||
/* look at the post-context preform special processing */
|
||||
/* look at the post-context perform special processing */
|
||||
if (*contextCharToUnicode==ATR) {
|
||||
|
||||
/* If we have ATR in *contextCharToUnicode then we need to change our
|
||||
|
|
|
|||
|
|
@ -4444,7 +4444,7 @@ getTrail:
|
|||
* For EUC encodings that use only either 0x8e or 0x8f as the first
|
||||
* byte of their longest byte sequences, the first two bytes in
|
||||
* this third stage indicate with their 7th bits whether these bytes
|
||||
* are to be written directly or actually need to be preceeded by
|
||||
* are to be written directly or actually need to be preceded by
|
||||
* one of the two Single-Shift codes. With this, the third stage
|
||||
* stores one byte fewer per character than the actual maximum length of
|
||||
* EUC byte sequences.
|
||||
|
|
|
|||
|
|
@ -287,7 +287,7 @@ myUCharsToChars(char* resultOfLen4, const UChar* currency) {
|
|||
* four integers. The first is the fraction digits. The second is the
|
||||
* rounding increment, or 0 if none. The rounding increment is in
|
||||
* units of 10^(-fraction_digits). The third and fourth are the same
|
||||
* except that they are those used in cash transations ( cashDigits
|
||||
* except that they are those used in cash transactions ( cashDigits
|
||||
* and cashRounding ).
|
||||
*/
|
||||
static const int32_t*
|
||||
|
|
@ -1312,7 +1312,7 @@ searchCurrencyName(const CurrencyNameStruct* currencyNames,
|
|||
// The 2nd round binary search search the second "B" in the text against
|
||||
// the 2nd char in currency names, and narrow the matching range to
|
||||
// "BB BBEX BBEXYZ" (and the maximum matching "BB").
|
||||
// The 3rd round returnes the range as "BBEX BBEXYZ" (without changing
|
||||
// The 3rd round returns the range as "BBEX BBEXYZ" (without changing
|
||||
// maximum matching).
|
||||
// The 4th round returns the same range (the maximum matching is "BBEX").
|
||||
// The 5th round returns no matching range.
|
||||
|
|
|
|||
|
|
@ -320,7 +320,7 @@ _uhash_create(UHashFunction *keyHash,
|
|||
* Stop if it is identical or empty, otherwise continue by adding a
|
||||
* "jump" value (moduloing by the length again to keep it within
|
||||
* range) and retesting. For efficiency, there need enough empty
|
||||
* values so that the searchs stop within a reasonable amount of time.
|
||||
* values so that the searches stop within a reasonable amount of time.
|
||||
* This can be changed by changing the high/low water marks.
|
||||
*
|
||||
* In theory, this function can return NULL, if it is full (no empty
|
||||
|
|
|
|||
|
|
@ -2310,7 +2310,7 @@ ultag_parse(const char* tag, int32_t tagLen, int32_t* parsedLen, UErrorCode* sta
|
|||
if (next & EXTV) {
|
||||
if (_isExtensionSubtag(pSubtag, subtagLen)) {
|
||||
if (pExtValueSubtag == NULL) {
|
||||
/* if the start postion of this extension's value is not yet,
|
||||
/* if the start position of this extension's value is not yet,
|
||||
this one is the first value subtag */
|
||||
pExtValueSubtag = pSubtag;
|
||||
}
|
||||
|
|
|
|||
|
|
@ -194,7 +194,7 @@ private:
|
|||
|
||||
/**
|
||||
* See if the decomposition of cp2 is at segment starting at segmentPos
|
||||
* (with canonical rearrangment!)
|
||||
* (with canonical rearrangement!)
|
||||
* If so, take the remainder, and return the equivalents
|
||||
*/
|
||||
//Set extract(int comp, String segment, int segmentPos, StringBuffer buffer);
|
||||
|
|
|
|||
|
|
@ -66,7 +66,7 @@ U_NAMESPACE_BEGIN
|
|||
|
||||
/**
|
||||
* A class representing a collection of resource information pertaining to a given
|
||||
* locale. A resource bundle provides a way of accessing locale- specfic information in
|
||||
* locale. A resource bundle provides a way of accessing locale- specific information in
|
||||
* a data file. You create a resource bundle that manages the resources for a given
|
||||
* locale and then ask it for individual resources.
|
||||
* <P>
|
||||
|
|
|
|||
|
|
@ -149,7 +149,7 @@ public:
|
|||
* and handles the conversion.
|
||||
*
|
||||
* @param status the error code.
|
||||
* @param resultLength a ponter to receive the length, can be NULL.
|
||||
* @param resultLength a pointer to receive the length, can be NULL.
|
||||
* @return a pointer to the string, or NULL.
|
||||
*
|
||||
* @stable ICU 2.4
|
||||
|
|
|
|||
|
|
@ -1007,7 +1007,7 @@ ucnv_getUnicodeSet(const UConverter *cnv,
|
|||
UErrorCode *pErrorCode);
|
||||
|
||||
/**
|
||||
* Gets the current calback function used by the converter when an illegal
|
||||
* Gets the current callback function used by the converter when an illegal
|
||||
* or invalid codepage sequence is found.
|
||||
* Context pointers are always owned by the caller.
|
||||
*
|
||||
|
|
@ -2032,7 +2032,7 @@ ucnv_toUCountPending(const UConverter* cnv, UErrorCode* status);
|
|||
* fixed ratio of bytes to Unicode codes <i>units</i> for any particular Unicode encoding form.
|
||||
* false is returned with the UErrorCode if error occurs or cnv is NULL.
|
||||
* @param cnv The converter to be tested
|
||||
* @param status ICU error code in/out paramter
|
||||
* @param status ICU error code in/out parameter
|
||||
* @return true if the converter is fixed-width
|
||||
* @stable ICU 4.8
|
||||
*/
|
||||
|
|
|
|||
|
|
@ -268,7 +268,7 @@ U_CAPI void U_EXPORT2 UCNV_TO_U_CALLBACK_STOP (
|
|||
/**
|
||||
* DO NOT CALL THIS FUNCTION DIRECTLY!
|
||||
* This From Unicode callback skips any ILLEGAL_SEQUENCE, or
|
||||
* skips only UNASSINGED_SEQUENCE depending on the context parameter
|
||||
* skips only UNASSIGNED_SEQUENCE depending on the context parameter
|
||||
* simply ignoring those characters.
|
||||
*
|
||||
* @param context The function currently recognizes the callback options:
|
||||
|
|
@ -330,31 +330,31 @@ U_CAPI void U_EXPORT2 UCNV_FROM_U_CALLBACK_SUBSTITUTE (
|
|||
*
|
||||
* @param context The function currently recognizes the callback options:
|
||||
* <ul>
|
||||
* <li>UCNV_ESCAPE_ICU: Substitues the ILLEGAL SEQUENCE with the hexadecimal
|
||||
* <li>UCNV_ESCAPE_ICU: Substitutes the ILLEGAL SEQUENCE with the hexadecimal
|
||||
* representation in the format %UXXXX, e.g. "%uFFFE%u00AC%uC8FE").
|
||||
* In the Event the converter doesn't support the characters {%,U}[A-F][0-9],
|
||||
* it will substitute the illegal sequence with the substitution characters.
|
||||
* Note that codeUnit(32bit int eg: unit of a surrogate pair) is represented as
|
||||
* %UD84D%UDC56</li>
|
||||
* <li>UCNV_ESCAPE_JAVA: Substitues the ILLEGAL SEQUENCE with the hexadecimal
|
||||
* <li>UCNV_ESCAPE_JAVA: Substitutes the ILLEGAL SEQUENCE with the hexadecimal
|
||||
* representation in the format \\uXXXX, e.g. "\\uFFFE\\u00AC\\uC8FE").
|
||||
* In the Event the converter doesn't support the characters {\,u}[A-F][0-9],
|
||||
* it will substitute the illegal sequence with the substitution characters.
|
||||
* Note that codeUnit(32bit int eg: unit of a surrogate pair) is represented as
|
||||
* \\uD84D\\uDC56</li>
|
||||
* <li>UCNV_ESCAPE_C: Substitues the ILLEGAL SEQUENCE with the hexadecimal
|
||||
* <li>UCNV_ESCAPE_C: Substitutes the ILLEGAL SEQUENCE with the hexadecimal
|
||||
* representation in the format \\uXXXX, e.g. "\\uFFFE\\u00AC\\uC8FE").
|
||||
* In the Event the converter doesn't support the characters {\,u,U}[A-F][0-9],
|
||||
* it will substitute the illegal sequence with the substitution characters.
|
||||
* Note that codeUnit(32bit int eg: unit of a surrogate pair) is represented as
|
||||
* \\U00023456</li>
|
||||
* <li>UCNV_ESCAPE_XML_DEC: Substitues the ILLEGAL SEQUENCE with the decimal
|
||||
* <li>UCNV_ESCAPE_XML_DEC: Substitutes the ILLEGAL SEQUENCE with the decimal
|
||||
* representation in the format \htmlonly&#DDDDDDDD;, e.g. "&#65534;&#172;&#51454;")\endhtmlonly.
|
||||
* In the Event the converter doesn't support the characters {&,#}[0-9],
|
||||
* it will substitute the illegal sequence with the substitution characters.
|
||||
* Note that codeUnit(32bit int eg: unit of a surrogate pair) is represented as
|
||||
* &#144470; and Zero padding is ignored.</li>
|
||||
* <li>UCNV_ESCAPE_XML_HEX:Substitues the ILLEGAL SEQUENCE with the decimal
|
||||
* <li>UCNV_ESCAPE_XML_HEX:Substitutes the ILLEGAL SEQUENCE with the decimal
|
||||
* representation in the format \htmlonly&#xXXXX; e.g. "&#xFFFE;&#x00AC;&#xC8FE;")\endhtmlonly.
|
||||
* In the Event the converter doesn't support the characters {&,#,x}[0-9],
|
||||
* it will substitute the illegal sequence with the substitution characters.
|
||||
|
|
@ -383,7 +383,7 @@ U_CAPI void U_EXPORT2 UCNV_FROM_U_CALLBACK_ESCAPE (
|
|||
/**
|
||||
* DO NOT CALL THIS FUNCTION DIRECTLY!
|
||||
* This To Unicode callback skips any ILLEGAL_SEQUENCE, or
|
||||
* skips only UNASSINGED_SEQUENCE depending on the context parameter
|
||||
* skips only UNASSIGNED_SEQUENCE depending on the context parameter
|
||||
* simply ignoring those characters.
|
||||
*
|
||||
* @param context The function currently recognizes the callback options:
|
||||
|
|
|
|||
|
|
@ -362,7 +362,7 @@ udata_setCommonData(const void *data, UErrorCode *err);
|
|||
*
|
||||
*
|
||||
* Warning: setAppData will set a U_USING_DEFAULT_WARNING code if
|
||||
* data with the specifed path that has already been opened, or
|
||||
* data with the specified path that has already been opened, or
|
||||
* if setAppData with the same path has already been called.
|
||||
* Any such calls to setAppData will have no effect.
|
||||
*
|
||||
|
|
|
|||
|
|
@ -1545,7 +1545,7 @@ public:
|
|||
* @param target the target buffer for extraction, can be NULL
|
||||
* if targetLength is 0
|
||||
* @param targetCapacity the length of the target buffer
|
||||
* @param inv Signature-distinguishing paramater, use US_INV.
|
||||
* @param inv Signature-distinguishing parameter, use US_INV.
|
||||
* @return the output string length, not including the terminating NUL
|
||||
* @stable ICU 3.2
|
||||
*/
|
||||
|
|
@ -3274,7 +3274,7 @@ public:
|
|||
* \endcode
|
||||
* @param src String using only invariant characters.
|
||||
* @param textLength Length of src, or -1 if NUL-terminated.
|
||||
* @param inv Signature-distinguishing paramater, use US_INV.
|
||||
* @param inv Signature-distinguishing parameter, use US_INV.
|
||||
*
|
||||
* @see US_INV
|
||||
* @stable ICU 3.2
|
||||
|
|
|
|||
|
|
@ -719,7 +719,7 @@ uset_retainAll(USet* set, const USet* retain);
|
|||
* possible space, without changing this object's value.
|
||||
* A frozen set will not be modified.
|
||||
*
|
||||
* @param set the object on which to perfrom the compact
|
||||
* @param set the object on which to perform the compact
|
||||
* @stable ICU 3.2
|
||||
*/
|
||||
U_CAPI void U_EXPORT2
|
||||
|
|
|
|||
|
|
@ -465,7 +465,7 @@ class U_COMMON_API UnifiedCache : public UnifiedCacheBase {
|
|||
/**
|
||||
* Register a primary cache entry. A primary key is the first key to create
|
||||
* a given SharedObject value. Subsequent keys whose create function
|
||||
* produce referneces to an already existing SharedObject are not primary -
|
||||
* produce references to an already existing SharedObject are not primary -
|
||||
* they can be evicted and subsequently recreated.
|
||||
*
|
||||
* On entry, gCacheMutex must be held.
|
||||
|
|
|
|||
|
|
@ -328,7 +328,7 @@ ures_getVersionNumberInternal(const UResourceBundle *resourceBundle);
|
|||
* you to query for the real locale of the resource. For example, if you requested
|
||||
* "en_US_CALIFORNIA" and only "en_US" bundle exists, "en_US" will be returned.
|
||||
* For subresources, the locale where this resource comes from will be returned.
|
||||
* If fallback has occured, getLocale will reflect this.
|
||||
* If fallback has occurred, getLocale will reflect this.
|
||||
*
|
||||
* This internal version avoids deprecated-warnings in ICU code.
|
||||
*
|
||||
|
|
|
|||
|
|
@ -33,7 +33,7 @@
|
|||
*
|
||||
* Scripts are chosen based on the <code>UScriptCode</code> enumeration.
|
||||
* No attempt is made to combine related scripts into a single run. In
|
||||
* particular, Hiragana, Katakana, and Han characters will appear in seperate
|
||||
* particular, Hiragana, Katakana, and Han characters will appear in separate
|
||||
* runs.
|
||||
|
||||
* Here is an example of how to iterate over script runs:
|
||||
|
|
|
|||
|
|
@ -360,7 +360,7 @@ uset_getItem(const USet* uset, int32_t itemIndex,
|
|||
* therefore all BMP code points precede all supplementary code points.
|
||||
*
|
||||
* Store each supplementary code point in 2 16-bit units,
|
||||
* simply with higher-then-lower 16-bit halfs.
|
||||
* simply with higher-then-lower 16-bit halves.
|
||||
*
|
||||
* Precede the entire list with the length.
|
||||
* If there are supplementary code points, then set bit 15 in the length
|
||||
|
|
|
|||
|
|
@ -282,8 +282,8 @@ loadData(UStringPrepProfile* profile,
|
|||
udata_close(dataMemory);
|
||||
return FALSE;
|
||||
}
|
||||
if( normUniVer < sprepUniVer && /* the Unicode version of SPREP file must be less than the Unicode Vesion of the normalization data */
|
||||
normUniVer < normCorrVer && /* the Unicode version of the NormalizationCorrections.txt file should be less than the Unicode Vesion of the normalization data */
|
||||
if( normUniVer < sprepUniVer && /* the Unicode version of SPREP file must be less than the Unicode Version of the normalization data */
|
||||
normUniVer < normCorrVer && /* the Unicode version of the NormalizationCorrections.txt file should be less than the Unicode Version of the normalization data */
|
||||
((profile->indexes[_SPREP_OPTIONS] & _SPREP_NORMALIZATION_ON) > 0) /* normalization turned on*/
|
||||
){
|
||||
*errorCode = U_INVALID_FORMAT_ERROR;
|
||||
|
|
|
|||
|
|
@ -755,7 +755,7 @@ uprv_strCompare(const UChar *s1, int32_t length1,
|
|||
length2=u_strlen(s2);
|
||||
}
|
||||
|
||||
/* limit1=start1+min(lenght1, length2) */
|
||||
/* limit1=start1+min(length1, length2) */
|
||||
if(length1<length2) {
|
||||
lengthResult=-1;
|
||||
limit1=start1+length1;
|
||||
|
|
|
|||
|
|
@ -1359,7 +1359,7 @@ fillReverse:
|
|||
int32_t sIx = srcIx; // ix of last byte of multi-byte u8 char
|
||||
|
||||
// Get the full character from the UTF8 string.
|
||||
// use code derived from tbe macros in utf8.h
|
||||
// use code derived from the macros in utf8.h
|
||||
// Leaves srcIx pointing at the first byte of the UTF-8 char.
|
||||
//
|
||||
c=utf8_prevCharSafeBody(s8, 0, &srcIx, c, -3);
|
||||
|
|
@ -1570,7 +1570,7 @@ utf8TextClone(UText *dest, const UText *src, UBool deep, UErrorCode *status)
|
|||
// For deep clones, make a copy of the string.
|
||||
// The copied storage is owned by the newly created clone.
|
||||
//
|
||||
// TODO: There is an isssue with using utext_nativeLength().
|
||||
// TODO: There is an issue with using utext_nativeLength().
|
||||
// That function is non-const in cases where the input was NUL terminated
|
||||
// and the length has not yet been determined.
|
||||
// This function (clone()) is const.
|
||||
|
|
|
|||
|
|
@ -199,7 +199,7 @@ class U_COMMON_API ICU_Utility /* not : public UObject because all methods are s
|
|||
* position. Return the identifier, or an empty string if there
|
||||
* is no identifier.
|
||||
* @param str the string to parse
|
||||
* @param pos INPUT-OUPUT parameter. On INPUT, pos is the
|
||||
* @param pos INPUT-OUTPUT parameter. On INPUT, pos is the
|
||||
* first character to examine. It must be less than str.length(),
|
||||
* and it must not point to a whitespace character. That is, must
|
||||
* have pos < str.length() and
|
||||
|
|
|
|||
|
|
@ -135,7 +135,7 @@ int32_t ICU_Utility::parsePattern(const UnicodeString& rule, int32_t pos, int32_
|
|||
* position. Return the identifier, or an empty string if there
|
||||
* is no identifier.
|
||||
* @param str the string to parse
|
||||
* @param pos INPUT-OUPUT parameter. On INPUT, pos is the
|
||||
* @param pos INPUT-OUTPUT parameter. On INPUT, pos is the
|
||||
* first character to examine. It must be less than str.length(),
|
||||
* and it must not point to a whitespace character. That is, must
|
||||
* have pos < str.length(). On
|
||||
|
|
|
|||
|
|
@ -93,7 +93,7 @@ static void outputChar(char c, char *outBuf, int32_t *outIx, int32_t capacity, i
|
|||
int32_t i;
|
||||
/* Check whether a start of line indenting is needed. Three cases:
|
||||
* 1. At the start of the first line (output index == 0).
|
||||
* 2. At the start of subsequent lines (preceeding char in buffer == '\n')
|
||||
* 2. At the start of subsequent lines (preceding char in buffer == '\n')
|
||||
* 3. When preflighting buffer len (buffer capacity is exceeded), when
|
||||
* a \n is output. Ideally we wouldn't do the indent until the following char
|
||||
* is received, but that won't work because there's no place to remember that
|
||||
|
|
@ -369,13 +369,13 @@ utrace_vformat(char *outBuf, int32_t capacity, int32_t indent, const char *fmt,
|
|||
default:
|
||||
/* %. in format string, where . is some character not in the set
|
||||
* of recognized format chars. Just output it as if % wasn't there.
|
||||
* (Covers "%%" outputing a single '%')
|
||||
* (Covers "%%" outputting a single '%')
|
||||
*/
|
||||
outputChar(fmtC, outBuf, &outIx, capacity, indent);
|
||||
}
|
||||
}
|
||||
outputChar(0, outBuf, &outIx, capacity, indent); /* Make sure that output is null terminated */
|
||||
return outIx + 1; /* outIx + 1 because outIx does not increment when outputing final null. */
|
||||
outputChar(0, outBuf, &outIx, capacity, indent); /* Make sure that output is null terminated */
|
||||
return outIx + 1; /* outIx + 1 because outIx does not increment when outputting final null. */
|
||||
}
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -36,7 +36,7 @@
|
|||
|
||||
U_NAMESPACE_BEGIN
|
||||
|
||||
// Note these constants and the struct are only used when dealing with the fallback path for RDP sesssions.
|
||||
// Note these constants and the struct are only used when dealing with the fallback path for RDP sessions.
|
||||
|
||||
// This is the location of the time zones in the registry on Vista+ systems.
|
||||
// See: https://docs.microsoft.com/windows/win32/api/timezoneapi/ns-timezoneapi-dynamic_time_zone_information
|
||||
|
|
|
|||
|
|
@ -38,7 +38,7 @@ DISTY_DAT:=$(firstword $(wildcard data/out/tmp/icudt$(SO_TARGET_VERSION_MAJOR)*.
|
|||
|
||||
DISTY_FILES_SRC=$(DISTY_FILE_TGZ) $(DISTY_FILE_ZIP)
|
||||
DISTY_FILES=$(DISTY_FILES_SRC) $(DISTY_DOC_ZIP)
|
||||
# colon-equals because we watn to run this once!
|
||||
# colon-equals because we want to run this once!
|
||||
EXCLUDES_FILE:=$(shell mktemp)
|
||||
|
||||
$(DISTY_FILE_DIR):
|
||||
|
|
|
|||
|
|
@ -154,10 +154,10 @@ endif
|
|||
|
||||
|
||||
## Dependency rules
|
||||
## This is a start to how depdendencies could work
|
||||
## This is a start to how dependencies could work
|
||||
# The commented out rules may not properly delete the file when ^C is pressed
|
||||
# or the compiler fails.
|
||||
# make currently doesn't like rules with C:\\PROGRA~1\\.. in the depedency.
|
||||
# make currently doesn't like rules with C:\\PROGRA~1\\.. in the dependency.
|
||||
# So system headers are ignored by ignoring \\
|
||||
%.d : $(srcdir)/%.c
|
||||
@echo "generating dependency information for $<"
|
||||
|
|
|
|||
|
|
@ -5,7 +5,7 @@
|
|||
## Copyright (c) 2003-2004, International Business Machines Corporation and
|
||||
## others. All Rights Reserved.
|
||||
##
|
||||
## Original contributer: Jason Gordon from NCR
|
||||
## Original contributor: Jason Gordon from NCR
|
||||
|
||||
## Flags for position independent code
|
||||
SHAREDLIBCFLAGS = -K PIC
|
||||
|
|
|
|||
|
|
@ -143,10 +143,10 @@ LDFLAGSICUTOOLUTIL=# Unused for now.
|
|||
|
||||
|
||||
## Dependency rules
|
||||
## This is a start to how depdendencies could work
|
||||
## This is a start to how dependencies could work
|
||||
# The commented out rules may not properly delete the file when ^C is pressed
|
||||
# or the compiler fails.
|
||||
# make currently doesn't like rules with C:\\PROGRA~1\\.. in the depedency.
|
||||
# make currently doesn't like rules with C:\\PROGRA~1\\.. in the dependency.
|
||||
# So system headers are ignored by ignoring \\
|
||||
%.d : $(srcdir)/%.c
|
||||
@echo "generating dependency information for $<"
|
||||
|
|
|
|||
|
|
@ -80,7 +80,7 @@ ARFLAGS = -cr
|
|||
ifeq (${OS390_XPLINK}, 1)
|
||||
#SH# if [ "x$OS390_XPLINK" = "x1" ]; then
|
||||
# These lines must be the last options specified.
|
||||
# GOFF is is the strategic object module format for S/390. It is required for XPLINK.
|
||||
# GOFF is the strategic object module format for S/390. It is required for XPLINK.
|
||||
# NOTEMPINC could be used if ICU starts using templates.
|
||||
ICU_XPLINK_C = -Wc,'xplink(backchain,storeargs),goff'
|
||||
ICU_XPLINK_CXX = -Wc,'xplink(backchain,storeargs),goff' -Wc,'NOTEMPINC'
|
||||
|
|
|
|||
6
icu4c/source/configure
vendored
6
icu4c/source/configure
vendored
|
|
@ -6046,7 +6046,7 @@ done
|
|||
fi
|
||||
fi
|
||||
|
||||
# Check for miscellanous functions.
|
||||
# Check for miscellaneous functions.
|
||||
# So, use for putil / tools only.
|
||||
# Note that this will generate HAVE_GETTIMEOFDAY, not U_HAVE_GETTIMEOFDAY
|
||||
for ac_func in gettimeofday
|
||||
|
|
@ -6167,7 +6167,7 @@ ac_compiler_gnu=$ac_cv_c_compiler_gnu
|
|||
OLD_LIBS=${LIBS}
|
||||
|
||||
# For Compaq Tru64 (OSF1), we must look for pthread_attr_init
|
||||
# and must do this before seaching for pthread_mutex_destroy, or
|
||||
# and must do this before searching for pthread_mutex_destroy, or
|
||||
# we will pick up libpthreads.so not libpthread.so
|
||||
# If this fails, then we must test for HPUX specials, before
|
||||
# moving on to a more generic test
|
||||
|
|
@ -7818,7 +7818,7 @@ fi
|
|||
|
||||
datapackaging_dir=`eval echo $thedatadir`"/icu/${VERSION}"
|
||||
|
||||
datapackaging_msg="(No explaination for mode $datapackaging.)"
|
||||
datapackaging_msg="(No explanation for mode $datapackaging.)"
|
||||
|
||||
datapackaging_msg_path="ICU will look in $datapackaging_dir which is the installation location. Call u_setDataDirectory() or use the ICU_DATA environment variable to override."
|
||||
datapackaging_msg_set="ICU will use the linked data library. If linked with the stub library located in stubdata/, the application can use udata_setCommonData() or set a data path to override."
|
||||
|
|
|
|||
|
|
@ -481,7 +481,7 @@ if test "$enable" = "yes"; then
|
|||
fi
|
||||
fi
|
||||
|
||||
# Check for miscellanous functions.
|
||||
# Check for miscellaneous functions.
|
||||
# So, use for putil / tools only.
|
||||
# Note that this will generate HAVE_GETTIMEOFDAY, not U_HAVE_GETTIMEOFDAY
|
||||
AC_CHECK_FUNCS([gettimeofday])
|
||||
|
|
@ -541,7 +541,7 @@ AC_LANG_POP([C++])
|
|||
OLD_LIBS=${LIBS}
|
||||
|
||||
# For Compaq Tru64 (OSF1), we must look for pthread_attr_init
|
||||
# and must do this before seaching for pthread_mutex_destroy, or
|
||||
# and must do this before searching for pthread_mutex_destroy, or
|
||||
# we will pick up libpthreads.so not libpthread.so
|
||||
# If this fails, then we must test for HPUX specials, before
|
||||
# moving on to a more generic test
|
||||
|
|
@ -1190,7 +1190,7 @@ fi
|
|||
|
||||
datapackaging_dir=`eval echo $thedatadir`"/icu/${VERSION}"
|
||||
|
||||
datapackaging_msg="(No explaination for mode $datapackaging.)"
|
||||
datapackaging_msg="(No explanation for mode $datapackaging.)"
|
||||
|
||||
datapackaging_msg_path="ICU will look in $datapackaging_dir which is the installation location. Call u_setDataDirectory() or use the ICU_DATA environment variable to override."
|
||||
datapackaging_msg_set="ICU will use the linked data library. If linked with the stub library located in stubdata/, the application can use udata_setCommonData() or set a data path to override."
|
||||
|
|
|
|||
|
|
@ -143,7 +143,7 @@ check-local:
|
|||
ICUDATA_SOURCE_ARCHIVE = $(wildcard $(srcdir)/in/$(ICUDATA_PLATFORM_NAME).dat)
|
||||
ifeq ($(ICUDATA_SOURCE_ARCHIVE),)
|
||||
ICUDATA_ARCHIVE = $(firstword $(wildcard $(srcdir)/in/$(ICUDATA_BASENAME_VERSION)*.dat))
|
||||
# We don't have the data in the current endianess or charset.
|
||||
# We don't have the data in the current endianness or charset.
|
||||
# See if we can find data of any archive type,
|
||||
# and convert it to the current type.
|
||||
ifneq ($(ICUDATA_ARCHIVE),)
|
||||
|
|
@ -159,7 +159,7 @@ endif
|
|||
else
|
||||
ifneq ($(ENABLE_STATIC),YES)
|
||||
ifeq ($(PKGDATA_MODE),common)
|
||||
# We have a source data common archive in the native endianess,
|
||||
# We have a source data common archive in the native endianness,
|
||||
# and it's what we want to build. Try to not run any of ICU's tools.
|
||||
ICUDATA_SOURCE_IS_NATIVE_TARGET=YES
|
||||
endif
|
||||
|
|
|
|||
|
|
@ -41,7 +41,7 @@ $T = [\p{Grapheme_Cluster_Break = T}];
|
|||
$LV = [\p{Grapheme_Cluster_Break = LV}];
|
||||
$LVT = [\p{Grapheme_Cluster_Break = LVT}];
|
||||
|
||||
# Emoji defintions
|
||||
# Emoji definitions
|
||||
|
||||
$Extended_Pict = [:ExtPict:];
|
||||
|
||||
|
|
|
|||
|
|
@ -182,7 +182,7 @@ $GL $CM* .;
|
|||
|
||||
|
||||
|
||||
# LB 13 Don't break before ']' or '!' or or '/', even after spaces.
|
||||
# LB 13 Don't break before ']' or '!' or '/', even after spaces.
|
||||
#
|
||||
$LB8NonBreaks $CL;
|
||||
$CAN_CM $CM* $CL;
|
||||
|
|
|
|||
|
|
@ -183,7 +183,7 @@ $GL $CM* .;
|
|||
|
||||
|
||||
|
||||
# LB 13 Don't break before ']' or '!' or or '/', even after spaces.
|
||||
# LB 13 Don't break before ']' or '!' or '/', even after spaces.
|
||||
#
|
||||
$LB8NonBreaks $CL;
|
||||
$CAN_CM $CM* $CL;
|
||||
|
|
|
|||
|
|
@ -189,7 +189,7 @@ $GL $CM* .;
|
|||
|
||||
|
||||
|
||||
# LB 13 Don't break before ']' or '!' or or '/', even after spaces.
|
||||
# LB 13 Don't break before ']' or '!' or '/', even after spaces.
|
||||
#
|
||||
$LB8NonBreaks $CL;
|
||||
$CAN_CM $CM* $CL;
|
||||
|
|
|
|||
|
|
@ -199,7 +199,7 @@ $GL $CM* .;
|
|||
|
||||
|
||||
|
||||
# LB 13 Don't break before ']' or '!' or or '/', even after spaces.
|
||||
# LB 13 Don't break before ']' or '!' or '/', even after spaces.
|
||||
#
|
||||
# Do not include $EXX here
|
||||
$LB8NonBreaks $CL;
|
||||
|
|
|
|||
|
|
@ -184,7 +184,7 @@ $GL $CM* .;
|
|||
|
||||
|
||||
|
||||
# LB 13 Don't break before ']' or '!' or or '/', even after spaces.
|
||||
# LB 13 Don't break before ']' or '!' or '/', even after spaces.
|
||||
#
|
||||
$LB8NonBreaks $CL;
|
||||
$CAN_CM $CM* $CL;
|
||||
|
|
|
|||
|
|
@ -188,7 +188,7 @@ $GL $CM* .;
|
|||
|
||||
|
||||
|
||||
# LB 13 Don't break before ']' or '!' or or '/', even after spaces.
|
||||
# LB 13 Don't break before ']' or '!' or '/', even after spaces.
|
||||
#
|
||||
$LB8NonBreaks $CL;
|
||||
$CAN_CM $CM* $CL;
|
||||
|
|
|
|||
|
|
@ -657,7 +657,7 @@ java-euc_jp_linux-1.6_P { UTR22* }
|
|||
java-sjis_0213-1.6_P { UTR22* }
|
||||
x-SJIS_0213 { JAVA* }
|
||||
|
||||
# Here are various interpretations and extentions of Big5
|
||||
# Here are various interpretations and extensions of Big5
|
||||
ibm-1373_P100-2002 { UTR22* } # IBM's interpretation of Windows' Taiwan Big-5 without HKSCS extensions
|
||||
ibm-1373 { IBM* }
|
||||
windows-950 # Alternate mapping. Leave untagged. This is the IBM interpretation of a Windows codepage.
|
||||
|
|
@ -1091,7 +1091,7 @@ ibm-16684_P110-2003 { UTR22* } ibm-16684 { IBM* } ibm-20780 { IBM } # DBCS Jis
|
|||
ibm-4899_P100-1998 { UTR22* } ibm-4899 { IBM* } # Old EBCDIC Hebrew. Update of ibm-803
|
||||
ibm-4971_P100-1999 { UTR22* } ibm-4971 { IBM* } # EBCDIC Greek. Update of ibm-875 and superceded by ibm-9067
|
||||
ibm-9067_X100-2005 { UTR22* } ibm-9067 { IBM* } # EBCDIC Greek. Update of ibm-875 and ibm-4971
|
||||
ibm-12712_P100-1998 { UTR22* } ibm-12712 { IBM* } ebcdic-he # EBCDIC Hebrew (new sheqel, control charaters update). Update of ibm-424
|
||||
ibm-12712_P100-1998 { UTR22* } ibm-12712 { IBM* } ebcdic-he # EBCDIC Hebrew (new sheqel, control characters update). Update of ibm-424
|
||||
ibm-16804_X110-1999 { UTR22* } ibm-16804 { IBM* } ebcdic-ar # EBCDIC Arabic. Update of ibm-420
|
||||
|
||||
java-Cp1399A-1.6_P { UTR22* } x-IBM1399A { JAVA* }
|
||||
|
|
|
|||
|
|
@ -9,7 +9,7 @@
|
|||
:: NFD (NFC) ;
|
||||
# to do: make reversible
|
||||
# define special conversion characters.
|
||||
# varients of this could use different characters, or set one or the other to null.
|
||||
# variants of this could use different characters, or set one or the other to null.
|
||||
$pre = \← ;
|
||||
$post = \→ ;
|
||||
# Provide keyboard equivalents for common diacritics used in transliteration
|
||||
|
|
|
|||
|
|
@ -37,7 +37,7 @@ $caron = \u030C;
|
|||
$afterLetter = [:L:] [\'$accent]* ;
|
||||
$beforeLetter = [\'$accent]* [:L:] ;
|
||||
# Fix punctuation
|
||||
# preserve orginal
|
||||
# preserve original
|
||||
\: ↔ \: $under ;
|
||||
\? ↔ \? $under ;
|
||||
\; ↔ \? ;
|
||||
|
|
|
|||
|
|
@ -12,7 +12,7 @@ $vowel = [ਅ-ਔ ਾ-\u0A4D];
|
|||
$consonant = [ਕ-ਹ];
|
||||
\uE001→\u0A01; # SIGN CHANDRABINDU
|
||||
#rules for BINDI
|
||||
# Anusvara is equivalent to BINDI when preceeded by a vowel
|
||||
# Anusvara is equivalent to BINDI when preceded by a vowel
|
||||
$vowel{\uE002→\u0A02; # SIGN ANUSVARA (\u0A02 = SIGN BINDI)
|
||||
# else is equivalent to TIPPI
|
||||
$consonant{\uE002→\u0A70; # SIGN TIPPI
|
||||
|
|
|
|||
|
|
@ -99,7 +99,7 @@ $om=\uE050; # OM
|
|||
$lm = \uE055;# Telugu Length Mark
|
||||
$ailm=\uE056;# AI Length Mark
|
||||
$aulm=\uE057;# AU Length Mark
|
||||
#urdu compatibity forms
|
||||
#urdu compatibility forms
|
||||
$uka=\uE058;
|
||||
$ukha=\uE059;
|
||||
$ugha=\uE05A;
|
||||
|
|
@ -405,7 +405,7 @@ $wco} $x → o\u0306\u0314;
|
|||
$wse} $x → e\u0314;
|
||||
$wso} $x → o\u0314;
|
||||
$om} $x → ''om\u0314;
|
||||
# independent vowels when preceeded by vowels
|
||||
# independent vowels when preceded by vowels
|
||||
$vowels{$waa → ''a\u0304;
|
||||
$vowels{$wai → ''ai;
|
||||
$vowels{$wau → ''au;
|
||||
|
|
|
|||
|
|
@ -49,7 +49,7 @@
|
|||
# after it. Continue with the rest of the consonants.
|
||||
# -- If there is one consonant, attach to the following vowel
|
||||
# -- If there are two consonants and a following vowel, attach one to the
|
||||
# preceeding vowel, and one to the following vowel.
|
||||
# preceding vowel, and one to the following vowel.
|
||||
# -- If there are more than two consonants, join the first two together if you
|
||||
# can: L + G =→ LG
|
||||
# -- If you still end up with more than 2 consonants, insert EU after the
|
||||
|
|
|
|||
|
|
@ -100,7 +100,7 @@ $om = \uE050; # OM
|
|||
$lm = \uE055;# Telugu Length Mark
|
||||
$ailm=\uE056;# AI Length Mark
|
||||
$aulm=\uE057;# AU Length Mark
|
||||
#urdu compatibity forms
|
||||
#urdu compatibility forms
|
||||
$uka=\uE058;
|
||||
$ukha=\uE059;
|
||||
$ugha=\uE05A;
|
||||
|
|
@ -180,7 +180,7 @@ x→$ka$virama$sa;
|
|||
\u0314o\u0306→$co;
|
||||
\u0314e→$se;
|
||||
\u0314o→$so;
|
||||
# preceeded by consonants
|
||||
# preceded by consonants
|
||||
$consonants{ a\u0304→$aa;
|
||||
$consonants{ ai→$ai;
|
||||
$consonants{ au→$au;
|
||||
|
|
|
|||
|
|
@ -567,7 +567,7 @@ $LABIALIZABLE_BEFORE_A = [p{pʼ}t{tʼ} {t\u0361ʃ}{t\u0361ʃʼ}{d\u0361ʒ}{d\u03
|
|||
፦ → ' '; # U+1366 ETHIOPIC PREFACE COLON
|
||||
፧ → ' '; # U+1367 ETHIOPIC QUESTION MARK
|
||||
፨ → ' '; # U+1368 ETHIOPIC PARAGRAPH SEPARATOR
|
||||
# Likewise, Ethiopic numberals cannot be pronounced by these rules,
|
||||
# Likewise, Ethiopic numerals cannot be pronounced by these rules,
|
||||
# so we replace them by whitespace in the output IPA notation.
|
||||
# Applications will typically pre-process text before calling
|
||||
# the am → am_FONIPA transform.
|
||||
|
|
|
|||
|
|
@ -228,7 +228,7 @@ $bulgarian { [Ъъ] } $wordBoundary > ;
|
|||
ѣ → ye ; # CYRILLIC SMALL LETTER YAT
|
||||
#
|
||||
#
|
||||
# Alternative rule where appropriate for local pronounciation. To apply
|
||||
# Alternative rule where appropriate for local pronunciation. To apply
|
||||
# uncomment the following by removing the '#' mark at the start of the
|
||||
# line and insert before the three rule lines above.
|
||||
#
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@
|
|||
# Generated from CLDR
|
||||
#
|
||||
|
||||
# Tranformation from Czech to Czech in IPA transcription (cs_FONIPA).
|
||||
# Transformation from Czech to Czech in IPA transcription (cs_FONIPA).
|
||||
# The transcription is not fully phonemic since we mark allophonic variations
|
||||
# of /m/, /n/, /x/ and /ɦ/.
|
||||
#
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@
|
|||
# Generated from CLDR
|
||||
#
|
||||
|
||||
# Tranforms Spanish to Mandarin Chinese. The input Spanish string must be in
|
||||
# Transforms Spanish to Mandarin Chinese. The input Spanish string must be in
|
||||
# phonemic IPA transcription (es_FONIPA); the output is in Simplified Chinese.
|
||||
$word_boundary = [-\ $];
|
||||
$vowel = [aeijouw]; # Vowels and glides
|
||||
|
|
@ -504,7 +504,7 @@ xwe → 胡埃 ;
|
|||
xwi → 惠 ;
|
||||
xwo → 霍 ;
|
||||
x → 赫 ;
|
||||
# 尔 simplification pass. The idea is to drop most occurences of 尔
|
||||
# 尔 simplification pass. The idea is to drop most occurrences of 尔
|
||||
# corresponding to <r> (not to <l> or <ll>) from a word if there is another /l/
|
||||
# sound nearby. There is a vague pattern like this in the data, but the details
|
||||
# remain to be determined. At the moment, this does nothing, it just puts 尔 in
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@
|
|||
# Generated from CLDR
|
||||
#
|
||||
|
||||
# Tranformation from Spanish to Spanish in IPA transcription (es_FONIPA).
|
||||
# Transformation from Spanish to Spanish in IPA transcription (es_FONIPA).
|
||||
# Not fully phonemic, since we mark up allophonic variants of voiced stops,
|
||||
# e.g. we break down /b/ into [b] and [β].
|
||||
#
|
||||
|
|
|
|||
|
|
@ -255,7 +255,7 @@ z → ツ;
|
|||
#
|
||||
# Latin hyphen should be transliterated to U+30A0 (KATAKANA-HIRAGANA
|
||||
# DOUBLE HYPHEN), ideally. But since the character isn't supported by
|
||||
# many fonts or softwares, we use U+FF1D (FULLWIDTH EQUALS SIGN),
|
||||
# many fonts or software, we use U+FF1D (FULLWIDTH EQUALS SIGN),
|
||||
# which is widely used as "double hyphen".
|
||||
#
|
||||
\- → ＝;
|
||||
|
|
|
|||
|
|
@ -59,7 +59,7 @@ $inword = [[:L:][:M:]];
|
|||
# Some online texts use U+1C7C PHAARKAA instead of U+1C7B RELAA for indicating
|
||||
# long phonemes, presumably because the graphemes look similar in some fonts.
|
||||
# Since phaarkaa is used for voicing ejectives and plosives (which cannot
|
||||
# be lenghtened), we rewrite phaarkaa to relaa.
|
||||
# be lengthened), we rewrite phaarkaa to relaa.
|
||||
[ᱚᱟᱤᱩᱮᱳᱶᱢᱝᱞᱱ] [ᱹᱸᱺ]* {ᱼ} → ᱻ ;
|
||||
::null();
|
||||
ᱚᱹᱻ → ɔː ;
|
||||
|
|
|
|||
|
|
@ -106,7 +106,7 @@ root
|
|||
|
||||
U_USING_FALLBACK_ERROR { "Using fallback data" }
|
||||
U_USING_DEFAULT_ERROR { "Using default data" }
|
||||
U_ZERO_ERROR { "No error has occured" }
|
||||
U_ZERO_ERROR { "No error has occurred" }
|
||||
U_ILLEGAL_ARGUMENT_ERROR { "Illegal argument" }
|
||||
U_MISSING_RESOURCE_ERROR { "A resource was missing" }
|
||||
U_INVALID_FORMAT_ERROR { "Invalid format" }
|
||||
|
|
|
|||
|
|
@ -379,7 +379,7 @@ double CalendarAstronomer::getJulianCentury() {
|
|||
*/
|
||||
double CalendarAstronomer::getGreenwichSidereal() {
|
||||
if (isINVALID(siderealTime)) {
|
||||
// See page 86 of "Practial Astronomy with your Calculator",
|
||||
// See page 86 of "Practical Astronomy with your Calculator",
|
||||
// by Peter Duffet-Smith, for details on the algorithm.
|
||||
|
||||
double UT = normalize(fTime/(double)HOUR_MS, 24.);
|
||||
|
|
@ -460,7 +460,7 @@ CalendarAstronomer::Equatorial& CalendarAstronomer::eclipticToEquatorial(Calenda
|
|||
*/
|
||||
CalendarAstronomer::Equatorial& CalendarAstronomer::eclipticToEquatorial(CalendarAstronomer::Equatorial& result, double eclipLong, double eclipLat)
|
||||
{
|
||||
// See page 42 of "Practial Astronomy with your Calculator",
|
||||
// See page 42 of "Practical Astronomy with your Calculator",
|
||||
// by Peter Duffet-Smith, for details on the algorithm.
|
||||
|
||||
double obliq = eclipticObliquity();
|
||||
|
|
@ -623,7 +623,7 @@ static double trueAnomaly(double meanAnomaly, double eccentricity)
|
|||
*/
|
||||
double CalendarAstronomer::getSunLongitude()
|
||||
{
|
||||
// See page 86 of "Practial Astronomy with your Calculator",
|
||||
// See page 86 of "Practical Astronomy with your Calculator",
|
||||
// by Peter Duffet-Smith, for details on the algorithm.
|
||||
|
||||
if (isINVALID(sunLongitude)) {
|
||||
|
|
@ -637,7 +637,7 @@ double CalendarAstronomer::getSunLongitude()
|
|||
*/
|
||||
/*public*/ void CalendarAstronomer::getSunLongitude(double jDay, double &longitude, double &meanAnomaly)
|
||||
{
|
||||
// See page 86 of "Practial Astronomy with your Calculator",
|
||||
// See page 86 of "Practical Astronomy with your Calculator",
|
||||
// by Peter Duffet-Smith, for details on the algorithm.
|
||||
|
||||
double day = jDay - JD_EPOCH; // Days since epoch
|
||||
|
|
@ -1066,7 +1066,7 @@ UDate CalendarAstronomer::getSunRiseSet(UBool rise)
|
|||
const CalendarAstronomer::Equatorial& CalendarAstronomer::getMoonPosition()
|
||||
{
|
||||
//
|
||||
// See page 142 of "Practial Astronomy with your Calculator",
|
||||
// See page 142 of "Practical Astronomy with your Calculator",
|
||||
// by Peter Duffet-Smith, for details on the algorithm.
|
||||
//
|
||||
if (moonPositionSet == FALSE) {
|
||||
|
|
@ -1154,7 +1154,7 @@ const CalendarAstronomer::Equatorial& CalendarAstronomer::getMoonPosition()
|
|||
* @deprecated ICU 2.4. This class may be removed or modified.
|
||||
*/
|
||||
double CalendarAstronomer::getMoonAge() {
|
||||
// See page 147 of "Practial Astronomy with your Calculator",
|
||||
// See page 147 of "Practical Astronomy with your Calculator",
|
||||
// by Peter Duffet-Smith, for details on the algorithm.
|
||||
//
|
||||
// Force the moon's position to be calculated. We're going to use
|
||||
|
|
@ -1181,7 +1181,7 @@ double CalendarAstronomer::getMoonAge() {
|
|||
* @deprecated ICU 2.4. This class may be removed or modified.
|
||||
*/
|
||||
double CalendarAstronomer::getMoonPhase() {
|
||||
// See page 147 of "Practial Astronomy with your Calculator",
|
||||
// See page 147 of "Practical Astronomy with your Calculator",
|
||||
// by Peter Duffet-Smith, for details on the algorithm.
|
||||
return 0.5 * (1 - cos(getMoonAge()));
|
||||
}
|
||||
|
|
@ -1239,8 +1239,8 @@ MoonTimeAngleFunc::~MoonTimeAngleFunc() {}
|
|||
* longitude will have the desired value.
|
||||
* <p>
|
||||
* @param desired The desired longitude.
|
||||
* @param next <tt>true</tt> if the next occurrance of the phase
|
||||
* is desired, <tt>false</tt> for the previous occurrance.
|
||||
* @param next <tt>true</tt> if the next occurrence of the phase
|
||||
* is desired, <tt>false</tt> for the previous occurrence.
|
||||
* @internal
|
||||
* @deprecated ICU 2.4. This class may be removed or modified.
|
||||
*/
|
||||
|
|
@ -1259,8 +1259,8 @@ UDate CalendarAstronomer::getMoonTime(double desired, UBool next)
|
|||
* desired phase.
|
||||
* <p>
|
||||
* @param desired The desired phase of the moon.
|
||||
* @param next <tt>true</tt> if the next occurrance of the phase
|
||||
* is desired, <tt>false</tt> for the previous occurrance.
|
||||
* @param next <tt>true</tt> if the next occurrence of the phase
|
||||
* is desired, <tt>false</tt> for the previous occurrence.
|
||||
* @internal
|
||||
* @deprecated ICU 2.4. This class may be removed or modified.
|
||||
*/
|
||||
|
|
|
|||
|
|
@ -626,8 +626,8 @@ public:
|
|||
* longitude will have the desired value.
|
||||
* <p>
|
||||
* @param desired The desired longitude.
|
||||
* @param next <tt>true</tt> if the next occurrance of the phase
|
||||
* is desired, <tt>false</tt> for the previous occurrance.
|
||||
* @param next <tt>true</tt> if the next occurrence of the phase
|
||||
* is desired, <tt>false</tt> for the previous occurrence.
|
||||
* @internal
|
||||
*/
|
||||
UDate getMoonTime(double desired, UBool next);
|
||||
|
|
|
|||
|
|
@ -106,7 +106,7 @@ void BreakTransliterator::handleTransliterate(Replaceable& text, UTransPosition&
|
|||
int32_t boundary;
|
||||
for(boundary = bi->next(); boundary != UBRK_DONE && boundary < offsets.limit; boundary = bi->next()) {
|
||||
if (boundary == 0) continue;
|
||||
// HACK: Check to see that preceeding item was a letter
|
||||
// HACK: Check to see that preceding item was a letter
|
||||
|
||||
UChar32 cp = sText.char32At(boundary-1);
|
||||
int type = u_charType(cp);
|
||||
|
|
|
|||
|
|
@ -3083,7 +3083,7 @@ void Calendar::computeTime(UErrorCode& status) {
|
|||
}
|
||||
|
||||
/**
|
||||
* Find the previous zone transtion near the given time.
|
||||
* Find the previous zone transition near the given time.
|
||||
*/
|
||||
UBool Calendar::getImmediatePreviousZoneTransition(UDate base, UDate *transitionTime, UErrorCode& status) const {
|
||||
BasicTimeZone *btz = getBasicTimeZone();
|
||||
|
|
@ -3197,7 +3197,7 @@ int32_t Calendar::computeZoneOffset(double millis, double millisInDay, UErrorCod
|
|||
// recalculate offsets from the resolved time (non-wall).
|
||||
// When the given wall time falls into skipped wall time,
|
||||
// the offsets will be based on the zone offsets AFTER
|
||||
// the transition (which means, earliest possibe interpretation).
|
||||
// the transition (which means, earliest possible interpretation).
|
||||
UDate tgmt = wall - (rawOffset + dstOffset);
|
||||
tz.getOffset(tgmt, FALSE, rawOffset, dstOffset, ec);
|
||||
}
|
||||
|
|
|
|||
|
|
@ -99,7 +99,7 @@ int32_t CollationElementIterator::getOffset() const
|
|||
/**
|
||||
* Get the ordering priority of the next character in the string.
|
||||
* @return the next character's ordering. Returns NULLORDER if an error has
|
||||
* occured or if the end of string has been reached
|
||||
* occurred or if the end of string has been reached
|
||||
*/
|
||||
int32_t CollationElementIterator::next(UErrorCode& status)
|
||||
{
|
||||
|
|
@ -162,7 +162,7 @@ UBool CollationElementIterator::operator==(
|
|||
* Get the ordering priority of the previous collation element in the string.
|
||||
* @param status the error code status.
|
||||
* @return the previous element's ordering. Returns NULLORDER if an error has
|
||||
* occured or if the start of string has been reached.
|
||||
* occurred or if the start of string has been reached.
|
||||
*/
|
||||
int32_t CollationElementIterator::previous(UErrorCode& status)
|
||||
{
|
||||
|
|
|
|||
|
|
@ -385,7 +385,7 @@ enumNext(UEnumeration *en, int32_t *resultLength, UErrorCode * /*status*/) {
|
|||
// ucsdet_getDetectableCharsets
|
||||
UBool *enabledArray = ((Context *)en->context)->enabledRecognizers;
|
||||
if (enabledArray != NULL) {
|
||||
// custome set
|
||||
// custom set
|
||||
while (currName == NULL && ((Context *)en->context)->currIndex < fCSRecognizers_size) {
|
||||
if (enabledArray[((Context *)en->context)->currIndex]) {
|
||||
currName = fCSRecognizers[((Context *)en->context)->currIndex]->recognizer->getName();
|
||||
|
|
|
|||
|
|
@ -83,7 +83,7 @@ scanInput:
|
|||
}
|
||||
|
||||
//
|
||||
// Initial quality is based on relative proportion of recongized vs.
|
||||
// Initial quality is based on relative proportion of recognized vs.
|
||||
// unrecognized escape sequences.
|
||||
// All good: quality = 100;
|
||||
// half or less good: quality = 0;
|
||||
|
|
|
|||
|
|
@ -209,7 +209,7 @@ int32_t CharsetRecog_mbcs::match_mbcs(InputText *det, const uint16_t commonChars
|
|||
}
|
||||
|
||||
if (commonChars == 0) {
|
||||
// We have no statistics on frequently occuring characters.
|
||||
// We have no statistics on frequently occurring characters.
|
||||
// Assess confidence purely on having a reasonable number of
|
||||
// multi-byte characters (the more the better)
|
||||
confidence = 30 + doubleByteCharCount - 20*badCharCount;
|
||||
|
|
@ -219,7 +219,7 @@ int32_t CharsetRecog_mbcs::match_mbcs(InputText *det, const uint16_t commonChars
|
|||
}
|
||||
} else {
|
||||
//
|
||||
// Frequency of occurence statistics exist.
|
||||
// Frequency of occurrence statistics exist.
|
||||
//
|
||||
|
||||
double maxVal = log((double)doubleByteCharCount / 4); /*(float)?*/
|
||||
|
|
|
|||
|
|
@ -144,7 +144,7 @@ UBool CharsetRecog_UTF_32::match(InputText* textIn, CharsetMatch *results) const
|
|||
}
|
||||
|
||||
|
||||
// Cook up some sort of confidence score, based on presense of a BOM
|
||||
// Cook up some sort of confidence score, based on presence of a BOM
|
||||
// and the existence of valid and/or invalid multi-byte sequences.
|
||||
if (hasBOM && numInvalid==0) {
|
||||
confidence = 100;
|
||||
|
|
|
|||
|
|
@ -221,7 +221,7 @@ struct DecFmtSymDataSink : public ResourceSink {
|
|||
// Destination for data, modified via setters.
|
||||
DecimalFormatSymbols& dfs;
|
||||
// Boolean array of whether or not we have seen a particular symbol yet.
|
||||
// Can't simpy check fSymbols because it is pre-populated with defaults.
|
||||
// Can't simply check fSymbols because it is pre-populated with defaults.
|
||||
UBool seenSymbol[DecimalFormatSymbols::kFormatSymbolCount];
|
||||
|
||||
// Constructor/Destructor
|
||||
|
|
|
|||
|
|
@ -3776,7 +3776,7 @@ static void decToString(const decNumber *dn, char *string, Flag eng) {
|
|||
|
||||
/* Finally add the E-part, if needed. It will never be 0, has a
|
||||
base maximum and minimum of +999999999 through -999999999, but
|
||||
could range down to -1999999998 for anormal numbers */
|
||||
could range down to -1999999998 for abnormal numbers */
|
||||
if (e!=0) {
|
||||
Flag had=0; /* 1=had non-zero */
|
||||
*c='E'; c++;
|
||||
|
|
@ -5616,7 +5616,7 @@ static const uShort LNnn[90]={9016, 8652, 8316, 8008, 7724, 7456, 7208,
|
|||
/* would certainly save at least one if it were made ten times */
|
||||
/* bigger, too (for truncated fractions 0.100 through 0.999). */
|
||||
/* However, for most practical evaluations, at least four or five */
|
||||
/* iterations will be neede -- so this would only speed up by */
|
||||
/* iterations will be needed -- so this would only speed up by */
|
||||
/* 20-25% and that probably does not justify increasing the table */
|
||||
/* size. */
|
||||
/* */
|
||||
|
|
|
|||
|
|
@ -290,7 +290,7 @@ static void GenerateShortestDigits(Bignum* numerator, Bignum* denominator,
|
|||
|
||||
// Let v = numerator / denominator < 10.
|
||||
// Then we generate 'count' digits of d = x.xxxxx... (without the decimal point)
|
||||
// from left to right. Once 'count' digits have been produced we decide wether
|
||||
// from left to right. Once 'count' digits have been produced we decide whether
|
||||
// to round up or down. Remainders of exactly .5 round upwards. Numbers such
|
||||
// as 9.999999 propagate a carry all the way, and change the
|
||||
// exponent (decimal_point), when rounding upwards.
|
||||
|
|
|
|||
|
|
@ -138,7 +138,7 @@ class DoubleToStringConverter {
|
|||
// Example with max_leading_padding_zeroes_in_precision_mode = 6.
|
||||
// ToPrecision(0.0000012345, 2) -> "0.0000012"
|
||||
// ToPrecision(0.00000012345, 2) -> "1.2e-7"
|
||||
// Similarily the converter may add up to
|
||||
// Similarly the converter may add up to
|
||||
// max_trailing_padding_zeroes_in_precision_mode in precision mode to avoid
|
||||
// returning an exponential representation. A zero added by the
|
||||
// EMIT_TRAILING_ZERO_AFTER_POINT flag is counted for this limit.
|
||||
|
|
@ -196,7 +196,7 @@ class DoubleToStringConverter {
|
|||
// Example with decimal_in_shortest_low = -6,
|
||||
// decimal_in_shortest_high = 21,
|
||||
// EMIT_POSITIVE_EXPONENT_SIGN activated, and
|
||||
// EMIT_TRAILING_DECIMAL_POINT deactived:
|
||||
// EMIT_TRAILING_DECIMAL_POINT deactivated:
|
||||
// ToShortest(0.000001) -> "0.000001"
|
||||
// ToShortest(0.0000001) -> "1e-7"
|
||||
// ToShortest(111111111111111111111.0) -> "111111111111111110000"
|
||||
|
|
@ -320,7 +320,7 @@ class DoubleToStringConverter {
|
|||
// Example with max_leading_padding_zeroes_in_precision_mode = 6.
|
||||
// ToPrecision(0.0000012345, 2) -> "0.0000012"
|
||||
// ToPrecision(0.00000012345, 2) -> "1.2e-7"
|
||||
// Similarily the converter may add up to
|
||||
// Similarly the converter may add up to
|
||||
// max_trailing_padding_zeroes_in_precision_mode in precision mode to avoid
|
||||
// returning an exponential representation. A zero added by the
|
||||
// EMIT_TRAILING_ZERO_AFTER_POINT flag is counted for this limit.
|
||||
|
|
|
|||
|
|
@ -566,7 +566,7 @@ float StrtofTrimmed(Vector<const char> trimmed, int exponent) {
|
|||
// low-precision (3 digits):
|
||||
// when read from input: 123
|
||||
// when rounded from high precision: 124.
|
||||
// To do this we simply look at the neigbors of the correct result and see
|
||||
// To do this we simply look at the neighbors of the correct result and see
|
||||
// if they would round to the same float. If the guess is not correct we have
|
||||
// to look at four values (since two different doubles could be the correct
|
||||
// double).
|
||||
|
|
|
|||
|
|
@ -2103,7 +2103,7 @@ DateFormatSymbols::initializeData(const Locale& locale, const char *type, UError
|
|||
|
||||
if (U_FAILURE(status)) return;
|
||||
|
||||
// Create a CalendarDataSink to process this data and the resouce bundles
|
||||
// Create a CalendarDataSink to process this data and the resource bundles
|
||||
CalendarDataSink calendarSink(status);
|
||||
UResourceBundle *rb = ures_open(NULL, locale.getBaseName(), &status);
|
||||
UResourceBundle *cb = ures_getByKey(rb, gCalendarTag, NULL, &status);
|
||||
|
|
|
|||
|
|
@ -177,7 +177,7 @@ Formattable::Formattable(const UnicodeString& stringToCopy)
|
|||
|
||||
// -------------------------------------
|
||||
// Creates a formattable object with a UnicodeString* value.
|
||||
// (adopting symantics)
|
||||
// (adopting semantics)
|
||||
|
||||
Formattable::Formattable(UnicodeString* stringToAdopt)
|
||||
{
|
||||
|
|
|
|||
Some files were not shown because too many files have changed in this diff Show more
Loading…
Add table
Reference in a new issue