ICU 4.2.1
|
A MessageFormat produces concatenated messages in a language-neutral way. More...
#include <msgfmt.h>
Public Types | |
enum | EFormatNumber { kMaxFormat = 10 } |
Enum type for kMaxFormat. More... | |
Public Member Functions | |
MessageFormat (const UnicodeString &pattern, UErrorCode &status) | |
Constructs a new MessageFormat using the given pattern and the default locale. More... | |
MessageFormat (const UnicodeString &pattern, const Locale &newLocale, UErrorCode &status) | |
Constructs a new MessageFormat using the given pattern and locale. More... | |
MessageFormat (const UnicodeString &pattern, const Locale &newLocale, UParseError &parseError, UErrorCode &status) | |
Constructs a new MessageFormat using the given pattern and locale. More... | |
MessageFormat (const MessageFormat &) | |
Constructs a new MessageFormat from an existing one. More... | |
const MessageFormat & | operator= (const MessageFormat &) |
Assignment operator. More... | |
virtual | ~MessageFormat () |
Destructor. More... | |
virtual Format * | clone (void) const |
Clones this Format object polymorphically. More... | |
virtual UBool | operator== (const Format &other) const |
Returns true if the given Format objects are semantically equal. More... | |
virtual void | setLocale (const Locale &theLocale) |
Sets the locale. More... | |
virtual const Locale & | getLocale (void) const |
Gets the locale. More... | |
virtual void | applyPattern (const UnicodeString &pattern, UErrorCode &status) |
Applies the given pattern string to this message format. More... | |
virtual void | applyPattern (const UnicodeString &pattern, UParseError &parseError, UErrorCode &status) |
Applies the given pattern string to this message format. More... | |
virtual UnicodeString & | toPattern (UnicodeString &appendTo) const |
Returns a pattern that can be used to recreate this object. More... | |
virtual void | adoptFormats (Format **formatsToAdopt, int32_t count) |
Sets subformats. More... | |
virtual void | setFormats (const Format **newFormats, int32_t cnt) |
Sets subformats. More... | |
virtual void | adoptFormat (int32_t formatNumber, Format *formatToAdopt) |
Sets one subformat. More... | |
virtual void | setFormat (int32_t formatNumber, const Format &format) |
Sets one subformat. More... | |
virtual StringEnumeration * | getFormatNames (UErrorCode &status) |
Gets format names. More... | |
virtual Format * | getFormat (const UnicodeString &formatName, UErrorCode &status) |
Gets subformat pointer for given format name. More... | |
virtual void | setFormat (const UnicodeString &formatName, const Format &format, UErrorCode &status) |
Sets one subformat for given format name. More... | |
virtual void | adoptFormat (const UnicodeString &formatName, Format *formatToAdopt, UErrorCode &status) |
Sets one subformat for given format name. More... | |
virtual const Format ** | getFormats (int32_t &count) const |
Gets an array of subformats of this object. More... | |
UnicodeString & | format (const Formattable *source, int32_t count, UnicodeString &appendTo, FieldPosition &ignore, UErrorCode &status) const |
Formats the given array of arguments into a user-readable string. More... | |
virtual UnicodeString & | format (const Formattable &obj, UnicodeString &appendTo, FieldPosition &pos, UErrorCode &status) const |
Formats the given array of arguments into a user-readable string. More... | |
UnicodeString & | format (const Formattable &obj, UnicodeString &appendTo, UErrorCode &status) const |
Formats the given array of arguments into a user-readable string. More... | |
UnicodeString & | format (const UnicodeString *argumentNames, const Formattable *arguments, int32_t count, UnicodeString &appendTo, UErrorCode &status) const |
Formats the given array of arguments into a user-defined argument name array. More... | |
virtual Formattable * | parse (const UnicodeString &source, ParsePosition &pos, int32_t &count) const |
Parses the given string into an array of output arguments. More... | |
virtual Formattable * | parse (const UnicodeString &source, int32_t &count, UErrorCode &status) const |
Parses the given string into an array of output arguments. More... | |
virtual void | parseObject (const UnicodeString &source, Formattable &result, ParsePosition &pos) const |
Parses the given string into an array of output arguments stored within a single Formattable of type kArray. More... | |
UBool | usesNamedArguments () const |
Returns true if this MessageFormat uses named arguments, and false otherwise. More... | |
int32_t | getArgTypeCount () const |
This API is for ICU internal use only. More... | |
virtual UClassID | getDynamicClassID (void) const |
Returns a unique class ID POLYMORPHICALLY. More... | |
![]() | |
virtual | ~Format () |
Destructor. More... | |
UBool | operator!= (const Format &other) const |
Return true if the given Format objects are not semantically equal. More... | |
UnicodeString & | format (const Formattable &obj, UnicodeString &appendTo, UErrorCode &status) const |
Formats an object to produce a string. More... | |
void | parseObject (const UnicodeString &source, Formattable &result, UErrorCode &status) const |
Parses a string to produce an object. More... | |
Locale | getLocale (ULocDataLocaleType type, UErrorCode &status) const |
Get the locale for this format object. More... | |
const char * | getLocaleID (ULocDataLocaleType type, UErrorCode &status) const |
Get the locale for this format object. More... | |
![]() | |
virtual | ~UObject () |
Destructor. More... | |
Static Public Member Functions | |
static UnicodeString & | format (const UnicodeString &pattern, const Formattable *arguments, int32_t count, UnicodeString &appendTo, UErrorCode &status) |
Formats the given array of arguments into a user-readable string using the given pattern. More... | |
static UnicodeString | autoQuoteApostrophe (const UnicodeString &pattern, UErrorCode &status) |
Convert an 'apostrophe-friendly' pattern into a standard pattern. More... | |
static UClassID | getStaticClassID (void) |
Return the class ID for this class. More... | |
![]() | |
static void * | operator new (size_t size) |
Override for ICU4C C++ memory management. More... | |
static void * | operator new[] (size_t size) |
Override for ICU4C C++ memory management. More... | |
static void | operator delete (void *p) |
Override for ICU4C C++ memory management. More... | |
static void | operator delete[] (void *p) |
Override for ICU4C C++ memory management. More... | |
static void * | operator new (size_t, void *ptr) |
Override for ICU4C C++ memory management for STL. More... | |
static void | operator delete (void *, void *) |
Override for ICU4C C++ memory management for STL. More... | |
Friends | |
class | MessageFormatAdapter |
Additional Inherited Members | |
![]() | |
void | setLocaleIDs (const char *valid, const char *actual) |
Format () | |
Default constructor for subclass use only. More... | |
Format (const Format &) | |
Format & | operator= (const Format &) |
![]() | |
static void | syntaxError (const UnicodeString &pattern, int32_t pos, UParseError &parseError) |
Simple function for initializing a UParseError from a UnicodeString. More... | |
A MessageFormat produces concatenated messages in a language-neutral way.
It should be used for all string concatenations that are visible to end users.
A MessageFormat contains an array of subformats arranged within a template string. Together, the subformats and template string determine how the MessageFormat will operate during formatting and parsing.
Typically, both the subformats and the template string are specified at once in a pattern. By using different patterns for different locales, messages may be localized.
During formatting, the MessageFormat takes an array of arguments and produces a user-readable string. Each argument is a Formattable object; they may be passed in in an array, or as a single Formattable object which itself contains an array. Each argument is matched up with its corresponding subformat, which then formats it into a string. The resultant strings are then assembled within the string template of the MessageFormat to produce the final output string.
Note: In ICU 4.0 MessageFormat supports named arguments. If a named argument is used, all arguments must be named. Names start with a character in UCHAR_ID_START
and continue with characters in UCHARID_CONTINUE
, in particular they do not start with a digit. If named arguments are used, usesNamedArguments() will return true.
The other new methods supporting named arguments are getFormatNames(UErrorCode& status), getFormat(const UnicodeString& formatName, UErrorCode& status) setFormat(const UnicodeString& formatName, const Format& format, UErrorCode& status), adoptFormat(const UnicodeString& formatName, Format* formatToAdopt, UErrorCode& status), format(const Formattable* arguments, const UnicodeString <em>argumentNames, int32_t cnt, UnicodeString& appendTo, FieldPosition& status, int32_t recursionProtection, UErrorCode& success), format(const UnicodeString</em> argumentNames, const Formattable* arguments, int32_t count, UnicodeString& appendTo,UErrorCode& status). These methods are all compatible with patterns that do not used named arguments– in these cases the keys in the input or output use UnicodeString
s that name the argument indices, e.g. "0", "1", "2"... etc.
When named arguments are used, certain methods on MessageFormat that take or return arrays do not perform any action, since it is not possible to identify positions in an array using a name. UErrorCode is set to U_ARGUMENT_TYPE_MISMATCH if there is a status/success field in the method. These methods are adoptFormats(Format** formatsToAdopt, int32_t count), setFormats(const Format** newFormats,int32_t count), adoptFormat(int32_t n, Format <em>newFormat), getFormats(int32_t& count), format(const Formattable</em> source,int32_t cnt,UnicodeString& appendTo, FieldPosition& ignore, UErrorCode& success), format(const UnicodeString& pattern,const Formattable* arguments,int32_t cnt,UnicodeString& appendTo,UErrorCode& success), format(const Formattable& source, UnicodeString& appendTo,FieldPosition& ignore, UErrorCode& success), format(const Formattable* arguments, int32_t cnt, UnicodeString& appendTo, FieldPosition& status, int32_t recursionProtection,UErrorCode& success), parse(const UnicodeString& source, ParsePosition& pos,int32_t& count), parse(const UnicodeString& source, int32_t& cnt, UErrorCode& status)
During parsing, an input string is matched against the string template of the MessageFormat to produce an array of Formattable objects. Plain text of the template string is matched directly against intput text. At each position in the template string where a subformat is located, the subformat is called to parse the corresponding segment of input text to produce an output argument. In this way, an array of arguments is created which together constitute the parse result.
Parsing may fail or produce unexpected results in a number of circumstances.
Here are some examples of usage:
Example 1:
* UErrorCode success = U_ZERO_ERROR;* GregorianCalendar cal(success);* Formattable arguments[] = {* 7L,* Formattable( (Date) cal.getTime(success), Formattable::kIsDate),* "a disturbance in the Force"* };** UnicodeString result;* "At {1,time} on {1,date}, there was {2} on planet {0,number}.",* arguments, 3, result, success );** cout << "result: " << result << endl;* //<output>: At 4:34:20 PM on 23-Mar-98, there was a disturbance* // in the Force on planet 7.*
Typically, the message format will come from resources, and the arguments will be dynamically set at runtime.
Example 2:
* success = U_ZERO_ERROR;* Formattable testArgs[] = {3L, "MyDisk"};** MessageFormat form(* "The disk \"{1}\" contains {0} file(s).", success );** UnicodeString string;* FieldPosition fpos = 0;** // output, with different testArgs:* // output: The disk "MyDisk" contains 0 file(s).* // output: The disk "MyDisk" contains 1 file(s).* // output: The disk "MyDisk" contains 1,273 file(s).*
The pattern is of the following form. Legend:
* {optional item}* (group that may be repeated)**
Do not confuse optional items with items inside quotes braces, such as this: "{". Quoted braces are literals.
* messageFormatPattern := string ( "{" messageFormatElement "}" string )*** messageFormatElement := argumentIndex | argumentName { "," elementFormat }** elementFormat := "time" { "," datetimeStyle }* | "date" { "," datetimeStyle }* | "number" { "," numberStyle }* | "choice" "," choiceStyle** datetimeStyle := "short"* | "medium"* | "long"* | "full"* | dateFormatPattern** numberStyle := "currency"* | "percent"* | "integer"* | numberFormatPattern** choiceStyle := choiceFormatPattern** pluralStyle := pluralFormatPattern*
If there is no elementFormat, then the argument must be a string, which is substituted. If there is no dateTimeStyle or numberStyle, then the default format is used (e.g. NumberFormat::createInstance(), DateFormat::createTimeInstance(DateFormat::kDefault, ...) or DateFormat::createDateInstance(DateFormat::kDefault, ...). For a ChoiceFormat, the pattern must always be specified, since there is no default.
In strings, single quotes can be used to quote syntax characters. A literal single quote is represented by '', both within and outside of single-quoted segments. Inside a messageFormatElement, quotes are not removed. For example, {1,number,$'#',##} will produce a number format with the pound-sign quoted, with a result such as: "$#31,45".
If a pattern is used, then unquoted braces in the pattern, if any, must match: that is, "ab {0} de" and "ab '}' de" are ok, but "ab {0'}' de" and "ab } de" are not.
The rules for using quotes within message format patterns unfortunately have shown to be somewhat confusing. In particular, it isn't always obvious to localizers whether single quotes need to be doubled or not. Make sure to inform localizers about the rules, and tell them (for example, by using comments in resource bundle source files) which strings will be processed by MessageFormat. Note that localizers may need to use single quotes in translated strings where the original version doesn't have them.
Note also that the simplest way to avoid the problem is to use the real apostrophe (single quote) character U+2019 (') for human-readable text, and to use the ASCII apostrophe (U+0027 ' ) only in program syntax, like quoting in MessageFormat. See the annotations for U+0027 Apostrophe in The Unicode Standard.
The argumentIndex is a non-negative integer, which corresponds to the index of the arguments presented in an array to be formatted. The first argument has argumentIndex 0.
It is acceptable to have unused arguments in the array. With missing arguments or arguments that are not of the right class for the specified format, a failing UErrorCode result is set.
For more sophisticated patterns, you can use a ChoiceFormat to get output:
* UErrorCode success = U_ZERO_ERROR;* MessageFormat* form("The disk \"{1}\" contains {0}.", success);* double filelimits[] = {0,1,2};* form.setFormat(1, *fileform); // NOT zero, see below** Formattable testArgs[] = {1273L, "MyDisk"};** UnicodeString string;* FieldPosition fpos = 0;* cout << form.format(testArgs, 2, string, fpos, success) << endl;** // output, with different testArgs* // output: The disk "MyDisk" contains no files.* // output: The disk "MyDisk" contains one file.* // output: The disk "MyDisk" contains 1,273 files.*
You can either do this programmatically, as in the above example, or by using a pattern (see ChoiceFormat for more information) as in:
* form.applyPattern(* "There {0,choice,0#are no files|1#is one file|1<are {0,number,integer} files}.");*
Note: As we see above, the string produced by a ChoiceFormat in MessageFormat is treated specially; occurences of '{' are used to indicated subformats, and cause recursion. If you create both a MessageFormat and ChoiceFormat programmatically (instead of using the string patterns), then be careful not to produce a format that recurses on itself, which will cause an infinite loop.
Note: Subformats are numbered by their order in the pattern. This is not the same as the argumentIndex.
* For example: with "abc{2}def{3}ghi{0}...",** format0 affects the first variable {2}* format1 affects the second variable {3}* format2 affects the second variable {0}*
User subclasses are not supported. While clients may write subclasses, such code will not necessarily work and will not be guaranteed to work stably from release to release.
MessageFormat::MessageFormat | ( | const UnicodeString & | pattern, |
UErrorCode & | status | ||
) |
Constructs a new MessageFormat using the given pattern and the default locale.
pattern | Pattern used to construct object. |
status | Input/output error code. If the pattern cannot be parsed, set to failure code. |
MessageFormat::MessageFormat | ( | const UnicodeString & | pattern, |
const Locale & | newLocale, | ||
UErrorCode & | status | ||
) |
Constructs a new MessageFormat using the given pattern and locale.
pattern | Pattern used to construct object. |
newLocale | The locale to use for formatting dates and numbers. |
status | Input/output error code. If the pattern cannot be parsed, set to failure code. |
MessageFormat::MessageFormat | ( | const UnicodeString & | pattern, |
const Locale & | newLocale, | ||
UParseError & | parseError, | ||
UErrorCode & | status | ||
) |
Constructs a new MessageFormat using the given pattern and locale.
pattern | Pattern used to construct object. |
newLocale | The locale to use for formatting dates and numbers. |
parseError | Struct to recieve information on position of error within the pattern. |
status | Input/output error code. If the pattern cannot be parsed, set to failure code. |
MessageFormat::MessageFormat | ( | const MessageFormat & | ) |
Constructs a new MessageFormat from an existing one.
|
virtual |
Destructor.
Sets one subformat.
See the class description about format numbering. The caller should not delete the Format object after this call. If the number is over the number of formats already set, the item will be deleted and ignored.
formatNumber | index of the subformat. |
formatToAdopt | the format to be adopted. |
|
virtual |
Sets one subformat for given format name.
See the class description about format name. This function supports both named and numbered arguments– if numbered, the formatName is the corresponding UnicodeStrings (e.g. "0", "1", "2"...). If there is no matched formatName or wrong type, the item will be ignored. The caller should not delete the Format object after this call.
formatName | Name of the subformat. |
formatToAdopt | Format to be adopted. |
status | output param set to success/failure code. |
Sets subformats.
See the class description about format numbering. The caller should not delete the Format objects after this call. The array formatsToAdopt is not itself adopted. Its ownership is retained by the caller. If the call fails because memory cannot be allocated, then the formats will be deleted by this method, and this object will remain unchanged.
formatsToAdopt | the format to be adopted. |
count | the size of the array. |
|
virtual |
Applies the given pattern string to this message format.
pattern | The pattern to be applied. |
status | Input/output error code. If the pattern cannot be parsed, set to failure code. |
|
virtual |
Applies the given pattern string to this message format.
pattern | The pattern to be applied. |
parseError | Struct to recieve information on position of error within pattern. |
status | Input/output error code. If the pattern cannot be parsed, set to failure code. |
|
static |
Convert an 'apostrophe-friendly' pattern into a standard pattern.
Standard patterns treat all apostrophes as quotes, which is problematic in some languages, e.g. French, where apostrophe is commonly used. This utility assumes that only an unpaired apostrophe immediately before a brace is a true quote. Other unpaired apostrophes are paired, and the resulting standard pattern string is returned.
Note it is not guaranteed that the returned pattern is indeed a valid pattern. The only effect is to convert between patterns having different quoting semantics.
pattern | the 'apostrophe-friendly' patttern to convert |
status | Input/output error code. If the pattern cannot be parsed, the failure code is set. |
|
virtual |
UnicodeString& MessageFormat::format | ( | const Formattable * | source, |
int32_t | count, | ||
UnicodeString & | appendTo, | ||
FieldPosition & | ignore, | ||
UErrorCode & | status | ||
) | const |
Formats the given array of arguments into a user-readable string.
Does not take ownership of the Formattable* array or its contents.
source | An array of objects to be formatted. |
count | The number of elements of 'source'. |
appendTo | Output parameter to receive result. Result is appended to existing contents. |
ignore | Not used; inherited from base class API. |
status | Input/output error code. If the pattern cannot be parsed, set to failure code. |
|
static |
Formats the given array of arguments into a user-readable string using the given pattern.
pattern | The pattern. |
arguments | An array of objects to be formatted. |
count | The number of elements of 'source'. |
appendTo | Output parameter to receive result. Result is appended to existing contents. |
status | Input/output error code. If the pattern cannot be parsed, set to failure code. |
|
virtual |
Formats the given array of arguments into a user-readable string.
The array must be stored within a single Formattable object of type kArray. If the Formattable object type is not of type kArray, then returns a failing UErrorCode.
obj | A Formattable of type kArray containing arguments to be formatted. |
appendTo | Output parameter to receive result. Result is appended to existing contents. |
pos | On input: an alignment field, if desired. On output: the offsets of the alignment field. |
status | Input/output error code. If the pattern cannot be parsed, set to failure code. |
Implements Format.
|
inline |
Formats the given array of arguments into a user-readable string.
The array must be stored within a single Formattable object of type kArray. If the Formattable object type is not of type kArray, then returns a failing UErrorCode.
obj | The object to format |
appendTo | Output parameter to receive result. Result is appended to existing contents. |
status | Input/output error code. If the pattern cannot be parsed, set to failure code. |
Definition at line 942 of file msgfmt.h.
References Format::format().
UnicodeString& MessageFormat::format | ( | const UnicodeString * | argumentNames, |
const Formattable * | arguments, | ||
int32_t | count, | ||
UnicodeString & | appendTo, | ||
UErrorCode & | status | ||
) | const |
Formats the given array of arguments into a user-defined argument name array.
This function supports both named and numbered arguments– if numbered, the formatName is the corresponding UnicodeStrings (e.g. "0", "1", "2"...).
argumentNames | argument name array |
arguments | An array of objects to be formatted. |
count | The number of elements of 'argumentNames' and arguments. The number of argumentNames and arguments must be the same. |
appendTo | Output parameter to receive result. Result is appended to existing contents. |
status | Input/output error code. If the pattern cannot be parsed, set to failure code. |
int32_t MessageFormat::getArgTypeCount | ( | ) | const |
This API is for ICU internal use only.
Please do not use it.
Returns argument types count in the parsed pattern. Used to distinguish pattern "{0} d" and "d".
|
virtual |
Returns a unique class ID POLYMORPHICALLY.
Pure virtual override. This method is to implement a simple version of RTTI, since not all C++ compilers support genuine RTTI. Polymorphic operator==() and clone() methods call this method.
Implements Format.
|
virtual |
Gets subformat pointer for given format name.
This function supports both named and numbered arguments– if numbered, the formatName is the corresponding UnicodeStrings (e.g. "0", "1", "2"...). The returned Format object should not be deleted by the caller, nor should the ponter of other object . The pointer and its contents remain valid only until the next call to any method of this class is made with this object.
formatName | the name or number specifying a format |
status | output param set to success/failure code. |
|
virtual |
Gets format names.
This function returns formatNames in StringEnumerations which can be used with getFormat() and setFormat() to export formattable array from current MessageFormat to another. It is caller's resposibility to delete the returned formatNames.
status | output param set to success/failure code. |
Gets an array of subformats of this object.
The returned array should not be deleted by the caller, nor should the pointers within the array. The array and its contents remain valid only until the next call to any method of this class is made with this object. See the class description about format numbering.
count | output parameter to receive the size of the array |
|
virtual |
Gets the locale.
This locale is used for fetching default number or date format information.
|
static |
Return the class ID for this class.
This is useful only for comparing to a return value from getDynamicClassID(). For example:
. Base* polymorphic_pointer = createPolymorphicObject(); . if (polymorphic_pointer->getDynamicClassID() == . Derived::getStaticClassID()) ...
const MessageFormat& MessageFormat::operator= | ( | const MessageFormat & | ) |
Assignment operator.
|
virtual |
Parses the given string into an array of output arguments.
source | String to be parsed. |
pos | On input, starting position for parse. On output, final position after parse. Unchanged if parse fails. |
count | Output parameter to receive the number of arguments parsed. |
|
virtual |
Parses the given string into an array of output arguments.
source | String to be parsed. |
count | Output param to receive size of returned array. |
status | Input/output error code. If the pattern cannot be parsed, set to failure code. If the MessageFormat is named argument, the status is set to U_ARGUMENT_TYPE_MISMATCH. |
|
virtual |
Parses the given string into an array of output arguments stored within a single Formattable of type kArray.
source | The string to be parsed into an object. |
result | Formattable to be set to the parse result. If parse fails, return contents are undefined. |
pos | On input, starting position for parse. On output, final position after parse. Unchanged if parse fails. |
Implements Format.
Sets one subformat.
See the class description about format numbering. If the number is over the number of formats already set, the item will be ignored.
formatNumber | index of the subformat. |
format | the format to be set. |
|
virtual |
Sets one subformat for given format name.
See the class description about format name. This function supports both named and numbered arguments– if numbered, the formatName is the corresponding UnicodeStrings (e.g. "0", "1", "2"...). If there is no matched formatName or wrong type, the item will be ignored.
formatName | Name of the subformat. |
format | the format to be set. |
status | output param set to success/failure code. |
Sets subformats.
See the class description about format numbering. Each item in the array is cloned into the internal array. If the call fails because memory cannot be allocated, then this object will remain unchanged.
newFormats | the new format to be set. |
cnt | the size of the array. |
|
virtual |
Sets the locale.
This locale is used for fetching default number or date format information.
theLocale | the new locale value to be set. |
|
virtual |
Returns a pattern that can be used to recreate this object.
appendTo | Output parameter to receive the pattern. Result is appended to existing contents. |
UBool MessageFormat::usesNamedArguments | ( | ) | const |
Returns true if this MessageFormat uses named arguments, and false otherwise.
See class description.