umsg.h File Reference

C API: MessageFormat. More...

#include "unicode/utypes.h"
#include "unicode/localpointer.h"
#include "unicode/uloc.h"
#include "unicode/parseerr.h"
#include <stdarg.h>

Go to the source code of this file.

Typedefs

typedef void * UMessageFormat
 The message format object.

Functions

int32_t u_formatMessage (const char *locale, const UChar *pattern, int32_t patternLength, UChar *result, int32_t resultLength, UErrorCode *status,...)
 Format a message for a locale.
int32_t u_vformatMessage (const char *locale, const UChar *pattern, int32_t patternLength, UChar *result, int32_t resultLength, va_list ap, UErrorCode *status)
 Format a message for a locale.
void u_parseMessage (const char *locale, const UChar *pattern, int32_t patternLength, const UChar *source, int32_t sourceLength, UErrorCode *status,...)
 Parse a message.
void u_vparseMessage (const char *locale, const UChar *pattern, int32_t patternLength, const UChar *source, int32_t sourceLength, va_list ap, UErrorCode *status)
 Parse a message.
int32_t u_formatMessageWithError (const char *locale, const UChar *pattern, int32_t patternLength, UChar *result, int32_t resultLength, UParseError *parseError, UErrorCode *status,...)
 Format a message for a locale.
int32_t u_vformatMessageWithError (const char *locale, const UChar *pattern, int32_t patternLength, UChar *result, int32_t resultLength, UParseError *parseError, va_list ap, UErrorCode *status)
 Format a message for a locale.
void u_parseMessageWithError (const char *locale, const UChar *pattern, int32_t patternLength, const UChar *source, int32_t sourceLength, UParseError *parseError, UErrorCode *status,...)
 Parse a message.
void u_vparseMessageWithError (const char *locale, const UChar *pattern, int32_t patternLength, const UChar *source, int32_t sourceLength, va_list ap, UParseError *parseError, UErrorCode *status)
 Parse a message.
UMessageFormatumsg_open (const UChar *pattern, int32_t patternLength, const char *locale, UParseError *parseError, UErrorCode *status)
 Open a message formatter with given pattern and for the given locale.
void umsg_close (UMessageFormat *format)
 Close a UMessageFormat.
UMessageFormat umsg_clone (const UMessageFormat *fmt, UErrorCode *status)
 Open a copy of a UMessageFormat.
void umsg_setLocale (UMessageFormat *fmt, const char *locale)
 Sets the locale.
const char * umsg_getLocale (const UMessageFormat *fmt)
 Gets the locale.
void umsg_applyPattern (UMessageFormat *fmt, const UChar *pattern, int32_t patternLength, UParseError *parseError, UErrorCode *status)
 Sets the pattern.
int32_t umsg_toPattern (const UMessageFormat *fmt, UChar *result, int32_t resultLength, UErrorCode *status)
 Gets the pattern.
int32_t umsg_format (const UMessageFormat *fmt, UChar *result, int32_t resultLength, UErrorCode *status,...)
 Format a message for a locale.
int32_t umsg_vformat (const UMessageFormat *fmt, UChar *result, int32_t resultLength, va_list ap, UErrorCode *status)
 Format a message for a locale.
void umsg_parse (const UMessageFormat *fmt, const UChar *source, int32_t sourceLength, int32_t *count, UErrorCode *status,...)
 Parse a message.
void umsg_vparse (const UMessageFormat *fmt, const UChar *source, int32_t sourceLength, int32_t *count, va_list ap, UErrorCode *status)
 Parse a message.
int32_t umsg_autoQuoteApostrophe (const UChar *pattern, int32_t patternLength, UChar *dest, int32_t destCapacity, UErrorCode *ec)
 Convert an 'apostrophe-friendly' pattern into a standard pattern.

Detailed Description

C API: MessageFormat.

Message Format C API

Provides means to produce concatenated messages in language-neutral way. Use this for all concatenations that show up to end users.

Takes a set of objects, formats them, then inserts the formatted strings into the pattern at the appropriate places.

Here are some examples of usage: Example 1:

 
     UChar *result, *tzID, *str;
     UChar pattern[100];
     int32_t resultLengthOut, resultlength;
     UCalendar *cal;
     UDate d1;
     UDateFormat *def1;
     UErrorCode status = U_ZERO_ERROR;

     str=(UChar*)malloc(sizeof(UChar) * (strlen("disturbance in force") +1));
     u_uastrcpy(str, "disturbance in force");
     tzID=(UChar*)malloc(sizeof(UChar) * 4);
     u_uastrcpy(tzID, "PST");
     cal=ucal_open(tzID, u_strlen(tzID), "en_US", UCAL_TRADITIONAL, &status);
     ucal_setDateTime(cal, 1999, UCAL_MARCH, 18, 0, 0, 0, &status);
     d1=ucal_getMillis(cal, &status);
     u_uastrcpy(pattern, "On {0, date, long}, there was a {1} on planet {2,number,integer}");
     resultlength=0;
     resultLengthOut=u_formatMessage( "en_US", pattern, u_strlen(pattern), NULL, resultlength, &status, d1, str, 7);
     if(status==U_BUFFER_OVERFLOW_ERROR){
         status=U_ZERO_ERROR;
         resultlength=resultLengthOut+1;
         result=(UChar*)realloc(result, sizeof(UChar) * resultlength);
         u_formatMessage( "en_US", pattern, u_strlen(pattern), result, resultlength, &status, d1, str, 7);
     }
     printf("%s\n", austrdup(result) );//austrdup( a function used to convert UChar* to char*)
     //output>: "On March 18, 1999, there was a disturbance in force on planet 7

Typically, the message format will come from resources, and the arguments will be dynamically set at runtime.

Example 2:

 
     UChar* str;
     UErrorCode status = U_ZERO_ERROR;
     UChar *result;
     UChar pattern[100];
     int32_t resultlength, resultLengthOut, i;
     double testArgs= { 100.0, 1.0, 0.0};

     str=(UChar*)malloc(sizeof(UChar) * 10);
     u_uastrcpy(str, "MyDisk");
     u_uastrcpy(pattern, "The disk {1} contains {0,choice,0#no files|1#one file|1<{0,number,integer} files}");
     for(i=0; i<3; i++){
       resultlength=0; 
       resultLengthOut=u_formatMessage( "en_US", pattern, u_strlen(pattern), NULL, resultlength, &status, testArgs[i], str); 
       if(status==U_BUFFER_OVERFLOW_ERROR){
         status=U_ZERO_ERROR;
         resultlength=resultLengthOut+1;
         result=(UChar*)malloc(sizeof(UChar) * resultlength);
         u_formatMessage( "en_US", pattern, u_strlen(pattern), result, resultlength, &status, testArgs[i], str);
       }
       printf("%s\n", austrdup(result) );  //austrdup( a function used to convert UChar* to char*)
       free(result);
     }
     // output, with different testArgs:
     // output: The disk "MyDisk" contains 100 files.
     // output: The disk "MyDisk" contains one file.
     // output: The disk "MyDisk" contains no files.

Example 3:

 
 UChar* str;
 UChar* str1;
 UErrorCode status = U_ZERO_ERROR;
 UChar *result;
 UChar pattern[100];
 UChar expected[100];
 int32_t resultlength,resultLengthOut;

 str=(UChar*)malloc(sizeof(UChar) * 25);
 u_uastrcpy(str, "Kirti");
 str1=(UChar*)malloc(sizeof(UChar) * 25);
 u_uastrcpy(str1, "female");
 log_verbose("Testing message format with Select test #1\n:");
 u_uastrcpy(pattern, "{0} est {1, select, female {all\\u00E9e} other {all\\u00E9}} \\u00E0 Paris.");
 u_uastrcpy(expected, "Kirti est all\\u00E9e \\u00E0 Paris.");
 resultlength=0;
 resultLengthOut=u_formatMessage( "fr", pattern, u_strlen(pattern), NULL, resultlength, &status, str , str1);
 if(status==U_BUFFER_OVERFLOW_ERROR)
  {
      status=U_ZERO_ERROR;
      resultlength=resultLengthOut+1;
      result=(UChar*)malloc(sizeof(UChar) * resultlength);
      u_formatMessage( "fr", pattern, u_strlen(pattern), result, resultlength, &status, str , str1);
      if(u_strcmp(result, expected)==0)
          log_verbose("PASS: MessagFormat successful on Select test#1\n");
      else{
          log_err("FAIL: Error in MessageFormat on Select test#1\n GOT %s EXPECTED %s\n", austrdup(result),
          austrdup(expected) );
      }
      free(result);
 }

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 := argument { "," elementFormat }

       elementFormat := "time" { "," datetimeStyle }
                      | "date" { "," datetimeStyle }
                      | "number" { "," numberStyle }
                      | "choice" "," choiceStyle
                      | "select" "," selectStyle

       datetimeStyle := "short"
                      | "medium"
                      | "long"
                      | "full"
                      | dateFormatPattern

       numberStyle :=   "currency"
                      | "percent"
                      | "integer"
                      | numberFormatPattern

       choiceStyle :=   choiceFormatPattern

       selectStyle :=   selectFormatPattern

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.getInstance(), DateFormat.getDefaultTime() or DateFormat.getDefaultDate(). For a ChoiceFormat, the pattern must always be specified, since there is no default.

In strings, single quotes can be used to quote the "{" sign if necessary. A real single quote is represented by ''. 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.

Warning:
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 argument is a number from 0 to 9, which corresponds to the arguments presented in an array to be formatted.

It is ok 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.

[Note:] As we see above, the string produced by a choice Format in MessageFormat is treated specially; occurances of '{' are used to indicated subformats.

[Note:] Formats are numbered by order of variable in the string. This is [not] the same as the argument numbering!

 
    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}

and so on.

Definition in file umsg.h.


Typedef Documentation

typedef void* UMessageFormat

The message format object.

Stable:
ICU 2.0

Definition at line 468 of file umsg.h.


Function Documentation

int32_t u_formatMessage ( const char *  locale,
const UChar pattern,
int32_t  patternLength,
UChar result,
int32_t  resultLength,
UErrorCode status,
  ... 
)

Format a message for a locale.

This function may perform re-ordering of the arguments depending on the locale. For all numeric arguments, double is assumed unless the type is explicitly integer. All choice format arguments must be of type double.

Parameters:
locale The locale for which the message will be formatted
pattern The pattern specifying the message's format
patternLength The length of pattern
result A pointer to a buffer to receive the formatted message.
resultLength The maximum size of result.
status A pointer to an UErrorCode to receive any errors
... A variable-length argument list containing the arguments specified in pattern.
Returns:
The total buffer size needed; if greater than resultLength, the output was truncated.
See also:
u_parseMessage
Stable:
ICU 2.0
int32_t u_formatMessageWithError ( const char *  locale,
const UChar pattern,
int32_t  patternLength,
UChar result,
int32_t  resultLength,
UParseError parseError,
UErrorCode status,
  ... 
)

Format a message for a locale.

This function may perform re-ordering of the arguments depending on the locale. For all numeric arguments, double is assumed unless the type is explicitly integer. All choice format arguments must be of type double.

Parameters:
locale The locale for which the message will be formatted
pattern The pattern specifying the message's format
patternLength The length of pattern
result A pointer to a buffer to receive the formatted message.
resultLength The maximum size of result.
status A pointer to an UErrorCode to receive any errors
... A variable-length argument list containing the arguments specified in pattern.
parseError A pointer to UParseError to receive information about errors occurred during parsing.
Returns:
The total buffer size needed; if greater than resultLength, the output was truncated.
See also:
u_parseMessage
Stable:
ICU 2.0
void u_parseMessage ( const char *  locale,
const UChar pattern,
int32_t  patternLength,
const UChar source,
int32_t  sourceLength,
UErrorCode status,
  ... 
)

Parse a message.

For numeric arguments, this function will always use doubles. Integer types should not be passed. This function is not able to parse all output from u_formatMessage.

Parameters:
locale The locale for which the message is formatted
pattern The pattern specifying the message's format
patternLength The length of pattern
source The text to parse.
sourceLength The length of source, or -1 if null-terminated.
status A pointer to an UErrorCode to receive any errors
... A variable-length argument list containing the arguments specified in pattern.
See also:
u_formatMessage
Stable:
ICU 2.0
void u_parseMessageWithError ( const char *  locale,
const UChar pattern,
int32_t  patternLength,
const UChar source,
int32_t  sourceLength,
UParseError parseError,
UErrorCode status,
  ... 
)

Parse a message.

For numeric arguments, this function will always use doubles. Integer types should not be passed. This function is not able to parse all output from u_formatMessage.

Parameters:
locale The locale for which the message is formatted
pattern The pattern specifying the message's format
patternLength The length of pattern
source The text to parse.
sourceLength The length of source, or -1 if null-terminated.
parseError A pointer to UParseError to receive information about errors occurred during parsing.
status A pointer to an UErrorCode to receive any errors
... A variable-length argument list containing the arguments specified in pattern.
See also:
u_formatMessage
Stable:
ICU 2.0
int32_t u_vformatMessage ( const char *  locale,
const UChar pattern,
int32_t  patternLength,
UChar result,
int32_t  resultLength,
va_list  ap,
UErrorCode status 
)

Format a message for a locale.

This function may perform re-ordering of the arguments depending on the locale. For all numeric arguments, double is assumed unless the type is explicitly integer. All choice format arguments must be of type double.

Parameters:
locale The locale for which the message will be formatted
pattern The pattern specifying the message's format
patternLength The length of pattern
result A pointer to a buffer to receive the formatted message.
resultLength The maximum size of result.
ap A variable-length argument list containing the arguments specified
status A pointer to an UErrorCode to receive any errors in pattern.
Returns:
The total buffer size needed; if greater than resultLength, the output was truncated.
See also:
u_parseMessage
Stable:
ICU 2.0
int32_t u_vformatMessageWithError ( const char *  locale,
const UChar pattern,
int32_t  patternLength,
UChar result,
int32_t  resultLength,
UParseError parseError,
va_list  ap,
UErrorCode status 
)

Format a message for a locale.

This function may perform re-ordering of the arguments depending on the locale. For all numeric arguments, double is assumed unless the type is explicitly integer. All choice format arguments must be of type double.

Parameters:
locale The locale for which the message will be formatted
pattern The pattern specifying the message's format
patternLength The length of pattern
result A pointer to a buffer to receive the formatted message.
resultLength The maximum size of result.
parseError A pointer to UParseError to receive information about errors occurred during parsing.
ap A variable-length argument list containing the arguments specified
status A pointer to an UErrorCode to receive any errors in pattern.
Returns:
The total buffer size needed; if greater than resultLength, the output was truncated.
Stable:
ICU 2.0
void u_vparseMessage ( const char *  locale,
const UChar pattern,
int32_t  patternLength,
const UChar source,
int32_t  sourceLength,
va_list  ap,
UErrorCode status 
)

Parse a message.

For numeric arguments, this function will always use doubles. Integer types should not be passed. This function is not able to parse all output from u_formatMessage.

Parameters:
locale The locale for which the message is formatted
pattern The pattern specifying the message's format
patternLength The length of pattern
source The text to parse.
sourceLength The length of source, or -1 if null-terminated.
ap A variable-length argument list containing the arguments
status A pointer to an UErrorCode to receive any errors specified in pattern.
See also:
u_formatMessage
Stable:
ICU 2.0
void u_vparseMessageWithError ( const char *  locale,
const UChar pattern,
int32_t  patternLength,
const UChar source,
int32_t  sourceLength,
va_list  ap,
UParseError parseError,
UErrorCode status 
)

Parse a message.

For numeric arguments, this function will always use doubles. Integer types should not be passed. This function is not able to parse all output from u_formatMessage.

Parameters:
locale The locale for which the message is formatted
pattern The pattern specifying the message's format
patternLength The length of pattern
source The text to parse.
sourceLength The length of source, or -1 if null-terminated.
ap A variable-length argument list containing the arguments
parseError A pointer to UParseError to receive information about errors occurred during parsing.
status A pointer to an UErrorCode to receive any errors specified in pattern.
See also:
u_formatMessage
Stable:
ICU 2.0
void umsg_applyPattern ( UMessageFormat fmt,
const UChar pattern,
int32_t  patternLength,
UParseError parseError,
UErrorCode status 
)

Sets the pattern.

Parameters:
fmt The formatter to use
pattern The pattern to be applied.
patternLength Length of the pattern to use
parseError Struct to receive information on position of error if an error is encountered.Can be NULL.
status Output param set to success/failure code on exit. If the pattern is invalid, this will be set to a failure result.
Stable:
ICU 2.0
int32_t umsg_autoQuoteApostrophe ( const UChar pattern,
int32_t  patternLength,
UChar dest,
int32_t  destCapacity,
UErrorCode ec 
)

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.

Parameters:
pattern the 'apostrophe-friendly' patttern to convert
patternLength the length of pattern, or -1 if unknown and pattern is null-terminated
dest the buffer for the result, or NULL if preflight only
destCapacity the length of the buffer, or 0 if preflighting
ec the error code
Returns:
the length of the resulting text, not including trailing null if buffer has room for the trailing null, it is provided, otherwise not
Stable:
ICU 3.4
UMessageFormat umsg_clone ( const UMessageFormat fmt,
UErrorCode status 
)

Open a copy of a UMessageFormat.

This function performs a deep copy.

Parameters:
fmt The formatter to copy
status A pointer to an UErrorCode to receive any errors.
Returns:
A pointer to a UDateFormat identical to fmt.
Stable:
ICU 2.0
void umsg_close ( UMessageFormat format  ) 

Close a UMessageFormat.

Once closed, a UMessageFormat may no longer be used.

Parameters:
format The formatter to close.
Stable:
ICU 2.0
int32_t umsg_format ( const UMessageFormat fmt,
UChar result,
int32_t  resultLength,
UErrorCode status,
  ... 
)

Format a message for a locale.

This function may perform re-ordering of the arguments depending on the locale. For all numeric arguments, double is assumed unless the type is explicitly integer. All choice format arguments must be of type double.

Parameters:
fmt The formatter to use
result A pointer to a buffer to receive the formatted message.
resultLength The maximum size of result.
status A pointer to an UErrorCode to receive any errors
... A variable-length argument list containing the arguments specified in pattern.
Returns:
The total buffer size needed; if greater than resultLength, the output was truncated.
Stable:
ICU 2.0
const char* umsg_getLocale ( const UMessageFormat fmt  ) 

Gets the locale.

This locale is used for fetching default number or date format information.

Parameters:
fmt The formatter to querry
Returns:
the locale.
Stable:
ICU 2.0
UMessageFormat* umsg_open ( const UChar pattern,
int32_t  patternLength,
const char *  locale,
UParseError parseError,
UErrorCode status 
)

Open a message formatter with given pattern and for the given locale.

Parameters:
pattern A pattern specifying the format to use.
patternLength Length of the pattern to use
locale The locale for which the messages are formatted.
parseError A pointer to UParseError struct to receive any errors occured during parsing. Can be NULL.
status A pointer to an UErrorCode to receive any errors.
Returns:
A pointer to a UMessageFormat to use for formatting messages, or 0 if an error occurred.
Stable:
ICU 2.0
void umsg_parse ( const UMessageFormat fmt,
const UChar source,
int32_t  sourceLength,
int32_t *  count,
UErrorCode status,
  ... 
)

Parse a message.

For numeric arguments, this function will always use doubles. Integer types should not be passed. This function is not able to parse all output from umsg_format.

Parameters:
fmt The formatter to use
source The text to parse.
sourceLength The length of source, or -1 if null-terminated.
count Output param to receive number of elements returned.
status A pointer to an UErrorCode to receive any errors
... A variable-length argument list containing the arguments specified in pattern.
Stable:
ICU 2.0
void umsg_setLocale ( UMessageFormat fmt,
const char *  locale 
)

Sets the locale.

This locale is used for fetching default number or date format information.

Parameters:
fmt The formatter to set
locale The locale the formatter should use.
Stable:
ICU 2.0
int32_t umsg_toPattern ( const UMessageFormat fmt,
UChar result,
int32_t  resultLength,
UErrorCode status 
)

Gets the pattern.

Parameters:
fmt The formatter to use
result A pointer to a buffer to receive the pattern.
resultLength The maximum size of result.
status Output param set to success/failure code on exit. If the pattern is invalid, this will be set to a failure result.
Returns:
the pattern of the format
Stable:
ICU 2.0
int32_t umsg_vformat ( const UMessageFormat fmt,
UChar result,
int32_t  resultLength,
va_list  ap,
UErrorCode status 
)

Format a message for a locale.

This function may perform re-ordering of the arguments depending on the locale. For all numeric arguments, double is assumed unless the type is explicitly integer. All choice format arguments must be of type double.

Parameters:
fmt The formatter to use
result A pointer to a buffer to receive the formatted message.
resultLength The maximum size of result.
ap A variable-length argument list containing the arguments
status A pointer to an UErrorCode to receive any errors specified in pattern.
Returns:
The total buffer size needed; if greater than resultLength, the output was truncated.
Stable:
ICU 2.0
void umsg_vparse ( const UMessageFormat fmt,
const UChar source,
int32_t  sourceLength,
int32_t *  count,
va_list  ap,
UErrorCode status 
)

Parse a message.

For numeric arguments, this function will always use doubles. Integer types should not be passed. This function is not able to parse all output from umsg_format.

Parameters:
fmt The formatter to use
source The text to parse.
sourceLength The length of source, or -1 if null-terminated.
count Output param to receive number of elements returned.
ap A variable-length argument list containing the arguments
status A pointer to an UErrorCode to receive any errors specified in pattern.
See also:
u_formatMessage
Stable:
ICU 2.0
 All Data Structures Files Functions Variables Typedefs Enumerations Enumerator Friends Defines

Generated on Sat Jan 23 15:17:39 2010 for ICU 4.3.4 by  doxygen 1.6.1