mirror of
https://github.com/mozilla/gecko-dev.git
synced 2024-10-30 05:35:31 +00:00
790694c449
--HG-- rename : intl/lwbrk/src/Makefile.in => intl/lwbrk/Makefile.in rename : intl/lwbrk/src/crashtests/416721.html => intl/lwbrk/crashtests/416721.html rename : intl/lwbrk/src/crashtests/crashtests.list => intl/lwbrk/crashtests/crashtests.list rename : intl/lwbrk/src/jisx4051class.h => intl/lwbrk/jisx4051class.h rename : intl/lwbrk/src/jisx4051pairtable.txt => intl/lwbrk/jisx4051pairtable.txt rename : intl/lwbrk/src/nsCarbonBreaker.cpp => intl/lwbrk/nsCarbonBreaker.cpp rename : intl/lwbrk/src/nsComplexBreaker.h => intl/lwbrk/nsComplexBreaker.h rename : intl/lwbrk/public/nsILineBreaker.h => intl/lwbrk/nsILineBreaker.h rename : intl/lwbrk/idl/nsISemanticUnitScanner.idl => intl/lwbrk/nsISemanticUnitScanner.idl rename : intl/lwbrk/public/nsIWordBreaker.h => intl/lwbrk/nsIWordBreaker.h rename : intl/lwbrk/src/nsJISx4051LineBreaker.cpp => intl/lwbrk/nsJISx4051LineBreaker.cpp rename : intl/lwbrk/src/nsJISx4051LineBreaker.h => intl/lwbrk/nsJISx4051LineBreaker.h rename : intl/lwbrk/public/nsLWBrkCIID.h => intl/lwbrk/nsLWBrkCIID.h rename : intl/lwbrk/src/nsPangoBreaker.cpp => intl/lwbrk/nsPangoBreaker.cpp rename : intl/lwbrk/src/nsRuleBreaker.cpp => intl/lwbrk/nsRuleBreaker.cpp rename : intl/lwbrk/src/nsSampleWordBreaker.cpp => intl/lwbrk/nsSampleWordBreaker.cpp rename : intl/lwbrk/src/nsSampleWordBreaker.h => intl/lwbrk/nsSampleWordBreaker.h rename : intl/lwbrk/src/nsSemanticUnitScanner.cpp => intl/lwbrk/nsSemanticUnitScanner.cpp rename : intl/lwbrk/src/nsSemanticUnitScanner.h => intl/lwbrk/nsSemanticUnitScanner.h rename : intl/lwbrk/src/nsUniscribeBreaker.cpp => intl/lwbrk/nsUniscribeBreaker.cpp rename : intl/lwbrk/src/rulebrk.c => intl/lwbrk/rulebrk.c rename : intl/lwbrk/src/rulebrk.h => intl/lwbrk/rulebrk.h rename : intl/lwbrk/src/th_char.h => intl/lwbrk/th_char.h
49 lines
1.8 KiB
Plaintext
49 lines
1.8 KiB
Plaintext
/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
|
|
/* This Source Code Form is subject to the terms of the Mozilla Public
|
|
* License, v. 2.0. If a copy of the MPL was not distributed with this
|
|
* file, You can obtain one at http://mozilla.org/MPL/2.0/. */
|
|
|
|
#include "nsISupports.idl"
|
|
|
|
%{C++
|
|
// {ADF42751-1CEF-4ad2-AA8E-BCB849D8D31F}
|
|
#define NS_SEMANTICUNITSCANNER_CID { 0xadf42751, 0x1cef, 0x4ad2, { 0xaa, 0x8e, 0xbc, 0xb8, 0x49, 0xd8, 0xd3, 0x1f}}
|
|
#define NS_SEMANTICUNITSCANNER_CONTRACTID "@mozilla.org/intl/semanticunitscanner;1"
|
|
%}
|
|
|
|
/**
|
|
* Provides a language independent way to break UNICODE
|
|
* text into meaningful semantic units (e.g. words).
|
|
*/
|
|
[scriptable, uuid(9f620be4-e535-11d6-b254-00039310a47a)]
|
|
interface nsISemanticUnitScanner : nsISupports {
|
|
/**
|
|
* start()
|
|
*
|
|
* Starts up the semantic unit scanner with an optional
|
|
* character set, which acts as a hint to optimize the heuristics
|
|
* used to determine the language(s) of the processed text.
|
|
*
|
|
* @param characterSet the character set the text was originally
|
|
* encoded in (can be NULL)
|
|
*/
|
|
void start(in string characterSet);
|
|
|
|
/**
|
|
* next()
|
|
* Get the begin / end offset of the next unit in the current text
|
|
*
|
|
* @param text the text to be scanned
|
|
* @param length the number of characters in the text to be processed
|
|
* @param pos the current position
|
|
* @param isLastBuffer, the buffer is the last one
|
|
* @param begin the begin offset of the next unit
|
|
* @param begin the end offset of the next unit
|
|
* @return has more unit in the current text
|
|
*/
|
|
boolean next(in wstring text, in long length, in long pos,
|
|
in boolean isLastBuffer,
|
|
out long begin, out long end );
|
|
|
|
};
|