The Tor Browser / file comparison
comparison: intl/lwbrk/idl/nsISemanticUnitScanner.idl
intl/lwbrk/idl/nsISemanticUnitScanner.idl
- branch
- TOR_BUG_9701
- changeset 8
- 97036ab72558
equal
deleted
inserted
replaced
| -1:000000000000 | 0:3017508ec72f |
|---|---|
| 1 /* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */ | |
| 2 /* This Source Code Form is subject to the terms of the Mozilla Public | |
| 3 * License, v. 2.0. If a copy of the MPL was not distributed with this | |
| 4 * file, You can obtain one at http://mozilla.org/MPL/2.0/. */ | |
| 5 | |
| 6 #include "nsISupports.idl" | |
| 7 | |
| 8 %{C++ | |
| 9 // {ADF42751-1CEF-4ad2-AA8E-BCB849D8D31F} | |
| 10 #define NS_SEMANTICUNITSCANNER_CID { 0xadf42751, 0x1cef, 0x4ad2, { 0xaa, 0x8e, 0xbc, 0xb8, 0x49, 0xd8, 0xd3, 0x1f}} | |
| 11 #define NS_SEMANTICUNITSCANNER_CONTRACTID "@mozilla.org/intl/semanticunitscanner;1" | |
| 12 %} | |
| 13 | |
| 14 /** | |
| 15 * Provides a language independent way to break UNICODE | |
| 16 * text into meaningful semantic units (e.g. words). | |
| 17 */ | |
| 18 [scriptable, uuid(9f620be4-e535-11d6-b254-00039310a47a)] | |
| 19 interface nsISemanticUnitScanner : nsISupports { | |
| 20 /** | |
| 21 * start() | |
| 22 * | |
| 23 * Starts up the semantic unit scanner with an optional | |
| 24 * character set, which acts as a hint to optimize the heuristics | |
| 25 * used to determine the language(s) of the processed text. | |
| 26 * | |
| 27 * @param characterSet the character set the text was originally | |
| 28 * encoded in (can be NULL) | |
| 29 */ | |
| 30 void start(in string characterSet); | |
| 31 | |
| 32 /** | |
| 33 * next() | |
| 34 * Get the begin / end offset of the next unit in the current text | |
| 35 * | |
| 36 * @param text the text to be scanned | |
| 37 * @param length the number of characters in the text to be processed | |
| 38 * @param pos the current position | |
| 39 * @param isLastBuffer, the buffer is the last one | |
| 40 * @param begin the begin offset of the next unit | |
| 41 * @param begin the end offset of the next unit | |
| 42 * @return has more unit in the current text | |
| 43 */ | |
| 44 boolean next(in wstring text, in long length, in long pos, | |
| 45 in boolean isLastBuffer, | |
| 46 out long begin, out long end ); | |
| 47 | |
| 48 }; |
