intl/lwbrk/idl/nsISemanticUnitScanner.idl@fc2d59ddac77 (annotated)
intl/lwbrk/idl/nsISemanticUnitScanner.idl
Wed, 31 Dec 2014 07:22:50 +0100
- author
- Michael Schloh von Bennewitz <michael@schloh.com>
- date
- Wed, 31 Dec 2014 07:22:50 +0100
- branch
- TOR_BUG_3246
- changeset 4
- fc2d59ddac77
- permissions
- -rw-r--r--
Correct previous dual key logic pending first delivery installment.
| michael@0 | 1 | /* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */ |
| michael@0 | 2 | /* This Source Code Form is subject to the terms of the Mozilla Public |
| michael@0 | 3 | * License, v. 2.0. If a copy of the MPL was not distributed with this |
| michael@0 | 4 | * file, You can obtain one at http://mozilla.org/MPL/2.0/. */ |
| michael@0 | 5 | |
| michael@0 | 6 | #include "nsISupports.idl" |
| michael@0 | 7 | |
| michael@0 | 8 | %{C++ |
| michael@0 | 9 | // {ADF42751-1CEF-4ad2-AA8E-BCB849D8D31F} |
| michael@0 | 10 | #define NS_SEMANTICUNITSCANNER_CID { 0xadf42751, 0x1cef, 0x4ad2, { 0xaa, 0x8e, 0xbc, 0xb8, 0x49, 0xd8, 0xd3, 0x1f}} |
| michael@0 | 11 | #define NS_SEMANTICUNITSCANNER_CONTRACTID "@mozilla.org/intl/semanticunitscanner;1" |
| michael@0 | 12 | %} |
| michael@0 | 13 | |
| michael@0 | 14 | /** |
| michael@0 | 15 | * Provides a language independent way to break UNICODE |
| michael@0 | 16 | * text into meaningful semantic units (e.g. words). |
| michael@0 | 17 | */ |
| michael@0 | 18 | [scriptable, uuid(9f620be4-e535-11d6-b254-00039310a47a)] |
| michael@0 | 19 | interface nsISemanticUnitScanner : nsISupports { |
| michael@0 | 20 | /** |
| michael@0 | 21 | * start() |
| michael@0 | 22 | * |
| michael@0 | 23 | * Starts up the semantic unit scanner with an optional |
| michael@0 | 24 | * character set, which acts as a hint to optimize the heuristics |
| michael@0 | 25 | * used to determine the language(s) of the processed text. |
| michael@0 | 26 | * |
| michael@0 | 27 | * @param characterSet the character set the text was originally |
| michael@0 | 28 | * encoded in (can be NULL) |
| michael@0 | 29 | */ |
| michael@0 | 30 | void start(in string characterSet); |
| michael@0 | 31 | |
| michael@0 | 32 | /** |
| michael@0 | 33 | * next() |
| michael@0 | 34 | * Get the begin / end offset of the next unit in the current text |
| michael@0 | 35 | * |
| michael@0 | 36 | * @param text the text to be scanned |
| michael@0 | 37 | * @param length the number of characters in the text to be processed |
| michael@0 | 38 | * @param pos the current position |
| michael@0 | 39 | * @param isLastBuffer, the buffer is the last one |
| michael@0 | 40 | * @param begin the begin offset of the next unit |
| michael@0 | 41 | * @param begin the end offset of the next unit |
| michael@0 | 42 | * @return has more unit in the current text |
| michael@0 | 43 | */ |
| michael@0 | 44 | boolean next(in wstring text, in long length, in long pos, |
| michael@0 | 45 | in boolean isLastBuffer, |
| michael@0 | 46 | out long begin, out long end ); |
| michael@0 | 47 | |
| michael@0 | 48 | }; |
