diff options
Diffstat (limited to 'src/tree_sitter/unicode')
| -rw-r--r-- | src/tree_sitter/unicode/ICU_SHA | 1 | ||||
| -rw-r--r-- | src/tree_sitter/unicode/LICENSE | 414 | ||||
| -rw-r--r-- | src/tree_sitter/unicode/README.md | 29 | ||||
| -rw-r--r-- | src/tree_sitter/unicode/ptypes.h | 1 | ||||
| -rw-r--r-- | src/tree_sitter/unicode/umachine.h | 448 | ||||
| -rw-r--r-- | src/tree_sitter/unicode/urename.h | 1 | ||||
| -rw-r--r-- | src/tree_sitter/unicode/utf.h | 1 | ||||
| -rw-r--r-- | src/tree_sitter/unicode/utf16.h | 733 | ||||
| -rw-r--r-- | src/tree_sitter/unicode/utf8.h | 881 |
9 files changed, 2509 insertions, 0 deletions
diff --git a/src/tree_sitter/unicode/ICU_SHA b/src/tree_sitter/unicode/ICU_SHA new file mode 100644 index 0000000000..3622283ba3 --- /dev/null +++ b/src/tree_sitter/unicode/ICU_SHA @@ -0,0 +1 @@ +552b01f61127d30d6589aa4bf99468224979b661 diff --git a/src/tree_sitter/unicode/LICENSE b/src/tree_sitter/unicode/LICENSE new file mode 100644 index 0000000000..2e01e36876 --- /dev/null +++ b/src/tree_sitter/unicode/LICENSE @@ -0,0 +1,414 @@ +COPYRIGHT AND PERMISSION NOTICE (ICU 58 and later) + +Copyright © 1991-2019 Unicode, Inc. All rights reserved. +Distributed under the Terms of Use in https://www.unicode.org/copyright.html. + +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Unicode data files and any associated documentation +(the "Data Files") or Unicode software and any associated documentation +(the "Software") to deal in the Data Files or Software +without restriction, including without limitation the rights to use, +copy, modify, merge, publish, distribute, and/or sell copies of +the Data Files or Software, and to permit persons to whom the Data Files +or Software are furnished to do so, provided that either +(a) this copyright and permission notice appear with all copies +of the Data Files or Software, or +(b) this copyright and permission notice appear in associated +Documentation. + +THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF +ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE +WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND +NONINFRINGEMENT OF THIRD PARTY RIGHTS. +IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS INCLUDED IN THIS +NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL +DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, +DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER +TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR +PERFORMANCE OF THE DATA FILES OR SOFTWARE. + +Except as contained in this notice, the name of a copyright holder +shall not be used in advertising or otherwise to promote the sale, +use or other dealings in these Data Files or Software without prior +written authorization of the copyright holder. + +--------------------- + +Third-Party Software Licenses + +This section contains third-party software notices and/or additional +terms for licensed third-party software components included within ICU +libraries. + +1. ICU License - ICU 1.8.1 to ICU 57.1 + +COPYRIGHT AND PERMISSION NOTICE + +Copyright (c) 1995-2016 International Business Machines Corporation and others +All rights reserved. + +Permission is hereby granted, free of charge, to any person obtaining +a copy of this software and associated documentation files (the +"Software"), to deal in the Software without restriction, including +without limitation the rights to use, copy, modify, merge, publish, +distribute, and/or sell copies of the Software, and to permit persons +to whom the Software is furnished to do so, provided that the above +copyright notice(s) and this permission notice appear in all copies of +the Software and that both the above copyright notice(s) and this +permission notice appear in supporting documentation. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR +HOLDERS INCLUDED IN THIS NOTICE BE LIABLE FOR ANY CLAIM, OR ANY +SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER +RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF +CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN +CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + +Except as contained in this notice, the name of a copyright holder +shall not be used in advertising or otherwise to promote the sale, use +or other dealings in this Software without prior written authorization +of the copyright holder. + +All trademarks and registered trademarks mentioned herein are the +property of their respective owners. + +2. Chinese/Japanese Word Break Dictionary Data (cjdict.txt) + + # The Google Chrome software developed by Google is licensed under + # the BSD license. Other software included in this distribution is + # provided under other licenses, as set forth below. + # + # The BSD License + # http://opensource.org/licenses/bsd-license.php + # Copyright (C) 2006-2008, Google Inc. + # + # All rights reserved. + # + # Redistribution and use in source and binary forms, with or without + # modification, are permitted provided that the following conditions are met: + # + # Redistributions of source code must retain the above copyright notice, + # this list of conditions and the following disclaimer. + # Redistributions in binary form must reproduce the above + # copyright notice, this list of conditions and the following + # disclaimer in the documentation and/or other materials provided with + # the distribution. + # Neither the name of Google Inc. nor the names of its + # contributors may be used to endorse or promote products derived from + # this software without specific prior written permission. + # + # + # THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND + # CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, + # INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF + # MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + # DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + # LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + # CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + # SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR + # BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF + # LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING + # NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + # SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + # + # + # The word list in cjdict.txt are generated by combining three word lists + # listed below with further processing for compound word breaking. The + # frequency is generated with an iterative training against Google web + # corpora. + # + # * Libtabe (Chinese) + # - https://sourceforge.net/project/?group_id=1519 + # - Its license terms and conditions are shown below. + # + # * IPADIC (Japanese) + # - http://chasen.aist-nara.ac.jp/chasen/distribution.html + # - Its license terms and conditions are shown below. + # + # ---------COPYING.libtabe ---- BEGIN-------------------- + # + # /* + # * Copyright (c) 1999 TaBE Project. + # * Copyright (c) 1999 Pai-Hsiang Hsiao. + # * All rights reserved. + # * + # * Redistribution and use in source and binary forms, with or without + # * modification, are permitted provided that the following conditions + # * are met: + # * + # * . Redistributions of source code must retain the above copyright + # * notice, this list of conditions and the following disclaimer. + # * . Redistributions in binary form must reproduce the above copyright + # * notice, this list of conditions and the following disclaimer in + # * the documentation and/or other materials provided with the + # * distribution. + # * . Neither the name of the TaBE Project nor the names of its + # * contributors may be used to endorse or promote products derived + # * from this software without specific prior written permission. + # * + # * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + # * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + # * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS + # * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE + # * REGENTS OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, + # * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + # * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR + # * SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + # * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, + # * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + # * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED + # * OF THE POSSIBILITY OF SUCH DAMAGE. + # */ + # + # /* + # * Copyright (c) 1999 Computer Systems and Communication Lab, + # * Institute of Information Science, Academia + # * Sinica. All rights reserved. + # * + # * Redistribution and use in source and binary forms, with or without + # * modification, are permitted provided that the following conditions + # * are met: + # * + # * . Redistributions of source code must retain the above copyright + # * notice, this list of conditions and the following disclaimer. + # * . Redistributions in binary form must reproduce the above copyright + # * notice, this list of conditions and the following disclaimer in + # * the documentation and/or other materials provided with the + # * distribution. + # * . Neither the name of the Computer Systems and Communication Lab + # * nor the names of its contributors may be used to endorse or + # * promote products derived from this software without specific + # * prior written permission. + # * + # * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + # * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + # * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS + # * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE + # * REGENTS OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, + # * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + # * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR + # * SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + # * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, + # * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + # * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED + # * OF THE POSSIBILITY OF SUCH DAMAGE. + # */ + # + # Copyright 1996 Chih-Hao Tsai @ Beckman Institute, + # University of Illinois + # c-tsai4@uiuc.edu http://casper.beckman.uiuc.edu/~c-tsai4 + # + # ---------------COPYING.libtabe-----END-------------------------------- + # + # + # ---------------COPYING.ipadic-----BEGIN------------------------------- + # + # Copyright 2000, 2001, 2002, 2003 Nara Institute of Science + # and Technology. All Rights Reserved. + # + # Use, reproduction, and distribution of this software is permitted. + # Any copy of this software, whether in its original form or modified, + # must include both the above copyright notice and the following + # paragraphs. + # + # Nara Institute of Science and Technology (NAIST), + # the copyright holders, disclaims all warranties with regard to this + # software, including all implied warranties of merchantability and + # fitness, in no event shall NAIST be liable for + # any special, indirect or consequential damages or any damages + # whatsoever resulting from loss of use, data or profits, whether in an + # action of contract, negligence or other tortuous action, arising out + # of or in connection with the use or performance of this software. + # + # A large portion of the dictionary entries + # originate from ICOT Free Software. The following conditions for ICOT + # Free Software applies to the current dictionary as well. + # + # Each User may also freely distribute the Program, whether in its + # original form or modified, to any third party or parties, PROVIDED + # that the provisions of Section 3 ("NO WARRANTY") will ALWAYS appear + # on, or be attached to, the Program, which is distributed substantially + # in the same form as set out herein and that such intended + # distribution, if actually made, will neither violate or otherwise + # contravene any of the laws and regulations of the countries having + # jurisdiction over the User or the intended distribution itself. + # + # NO WARRANTY + # + # The program was produced on an experimental basis in the course of the + # research and development conducted during the project and is provided + # to users as so produced on an experimental basis. Accordingly, the + # program is provided without any warranty whatsoever, whether express, + # implied, statutory or otherwise. The term "warranty" used herein + # includes, but is not limited to, any warranty of the quality, + # performance, merchantability and fitness for a particular purpose of + # the program and the nonexistence of any infringement or violation of + # any right of any third party. + # + # Each user of the program will agree and understand, and be deemed to + # have agreed and understood, that there is no warranty whatsoever for + # the program and, accordingly, the entire risk arising from or + # otherwise connected with the program is assumed by the user. + # + # Therefore, neither ICOT, the copyright holder, or any other + # organization that participated in or was otherwise related to the + # development of the program and their respective officials, directors, + # officers and other employees shall be held liable for any and all + # damages, including, without limitation, general, special, incidental + # and consequential damages, arising out of or otherwise in connection + # with the use or inability to use the program or any product, material + # or result produced or otherwise obtained by using the program, + # regardless of whether they have been advised of, or otherwise had + # knowledge of, the possibility of such damages at any time during the + # project or thereafter. Each user will be deemed to have agreed to the + # foregoing by his or her commencement of use of the program. The term + # "use" as used herein includes, but is not limited to, the use, + # modification, copying and distribution of the program and the + # production of secondary products from the program. + # + # In the case where the program, whether in its original form or + # modified, was distributed or delivered to or received by a user from + # any person, organization or entity other than ICOT, unless it makes or + # grants independently of ICOT any specific warranty to the user in + # writing, such person, organization or entity, will also be exempted + # from and not be held liable to the user for any such damages as noted + # above as far as the program is concerned. + # + # ---------------COPYING.ipadic-----END---------------------------------- + +3. Lao Word Break Dictionary Data (laodict.txt) + + # Copyright (c) 2013 International Business Machines Corporation + # and others. All Rights Reserved. + # + # Project: http://code.google.com/p/lao-dictionary/ + # Dictionary: http://lao-dictionary.googlecode.com/git/Lao-Dictionary.txt + # License: http://lao-dictionary.googlecode.com/git/Lao-Dictionary-LICENSE.txt + # (copied below) + # + # This file is derived from the above dictionary, with slight + # modifications. + # ---------------------------------------------------------------------- + # Copyright (C) 2013 Brian Eugene Wilson, Robert Martin Campbell. + # All rights reserved. + # + # Redistribution and use in source and binary forms, with or without + # modification, + # are permitted provided that the following conditions are met: + # + # + # Redistributions of source code must retain the above copyright notice, this + # list of conditions and the following disclaimer. Redistributions in + # binary form must reproduce the above copyright notice, this list of + # conditions and the following disclaimer in the documentation and/or + # other materials provided with the distribution. + # + # + # THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + # "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + # LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS + # FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE + # COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, + # INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + # (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR + # SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + # HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, + # STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + # ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED + # OF THE POSSIBILITY OF SUCH DAMAGE. + # -------------------------------------------------------------------------- + +4. Burmese Word Break Dictionary Data (burmesedict.txt) + + # Copyright (c) 2014 International Business Machines Corporation + # and others. All Rights Reserved. + # + # This list is part of a project hosted at: + # github.com/kanyawtech/myanmar-karen-word-lists + # + # -------------------------------------------------------------------------- + # Copyright (c) 2013, LeRoy Benjamin Sharon + # All rights reserved. + # + # Redistribution and use in source and binary forms, with or without + # modification, are permitted provided that the following conditions + # are met: Redistributions of source code must retain the above + # copyright notice, this list of conditions and the following + # disclaimer. Redistributions in binary form must reproduce the + # above copyright notice, this list of conditions and the following + # disclaimer in the documentation and/or other materials provided + # with the distribution. + # + # Neither the name Myanmar Karen Word Lists, nor the names of its + # contributors may be used to endorse or promote products derived + # from this software without specific prior written permission. + # + # THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND + # CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, + # INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF + # MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + # DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS + # BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, + # EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED + # TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + # DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON + # ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR + # TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF + # THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + # SUCH DAMAGE. + # -------------------------------------------------------------------------- + +5. Time Zone Database + + ICU uses the public domain data and code derived from Time Zone +Database for its time zone support. The ownership of the TZ database +is explained in BCP 175: Procedure for Maintaining the Time Zone +Database section 7. + + # 7. Database Ownership + # + # The TZ database itself is not an IETF Contribution or an IETF + # document. Rather it is a pre-existing and regularly updated work + # that is in the public domain, and is intended to remain in the + # public domain. Therefore, BCPs 78 [RFC5378] and 79 [RFC3979] do + # not apply to the TZ Database or contributions that individuals make + # to it. Should any claims be made and substantiated against the TZ + # Database, the organization that is providing the IANA + # Considerations defined in this RFC, under the memorandum of + # understanding with the IETF, currently ICANN, may act in accordance + # with all competent court orders. No ownership claims will be made + # by ICANN or the IETF Trust on the database or the code. Any person + # making a contribution to the database or code waives all rights to + # future claims in that contribution or in the TZ Database. + +6. Google double-conversion + +Copyright 2006-2011, the V8 project authors. All rights reserved. +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are +met: + + * Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + * Redistributions in binary form must reproduce the above + copyright notice, this list of conditions and the following + disclaimer in the documentation and/or other materials provided + with the distribution. + * Neither the name of Google Inc. nor the names of its + contributors may be used to endorse or promote products derived + from this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT +LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, +DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY +THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. diff --git a/src/tree_sitter/unicode/README.md b/src/tree_sitter/unicode/README.md new file mode 100644 index 0000000000..623b8e3843 --- /dev/null +++ b/src/tree_sitter/unicode/README.md @@ -0,0 +1,29 @@ +# ICU Parts + +This directory contains a small subset of files from the Unicode organization's [ICU repository](https://github.com/unicode-org/icu). + +### License + +The license for these files is contained in the `LICENSE` file within this directory. + +### Contents + +* Source files taken from the [`icu4c/source/common/unicode`](https://github.com/unicode-org/icu/tree/552b01f61127d30d6589aa4bf99468224979b661/icu4c/source/common/unicode) directory: + * `utf8.h` + * `utf16.h` + * `umachine.h` +* Empty source files that are referenced by the above source files, but whose original contents in `libicu` are not needed: + * `ptypes.h` + * `urename.h` + * `utf.h` +* `ICU_SHA` - File containing the Git SHA of the commit in the `icu` repository from which the files were obtained. +* `LICENSE` - The license file from the [`icu4c`](https://github.com/unicode-org/icu/tree/552b01f61127d30d6589aa4bf99468224979b661/icu4c) directory of the `icu` repository. +* `README.md` - This text file. + +### Updating ICU + +To incorporate changes from the upstream `icu` repository: + +* Update `ICU_SHA` with the new Git SHA. +* Update `LICENSE` with the license text from the directory mentioned above. +* Update `utf8.h`, `utf16.h`, and `umachine.h` with their new contents in the `icu` repository. diff --git a/src/tree_sitter/unicode/ptypes.h b/src/tree_sitter/unicode/ptypes.h new file mode 100644 index 0000000000..ac79ad0f98 --- /dev/null +++ b/src/tree_sitter/unicode/ptypes.h @@ -0,0 +1 @@ +// This file must exist in order for `utf8.h` and `utf16.h` to be used. diff --git a/src/tree_sitter/unicode/umachine.h b/src/tree_sitter/unicode/umachine.h new file mode 100644 index 0000000000..bbf6ef9c8b --- /dev/null +++ b/src/tree_sitter/unicode/umachine.h @@ -0,0 +1,448 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +****************************************************************************** +* +* Copyright (C) 1999-2015, International Business Machines +* Corporation and others. All Rights Reserved. +* +****************************************************************************** +* file name: umachine.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 1999sep13 +* created by: Markus W. Scherer +* +* This file defines basic types and constants for ICU to be +* platform-independent. umachine.h and utf.h are included into +* utypes.h to provide all the general definitions for ICU. +* All of these definitions used to be in utypes.h before +* the UTF-handling macros made this unmaintainable. +*/ + +#ifndef __UMACHINE_H__ +#define __UMACHINE_H__ + + +/** + * \file + * \brief Basic types and constants for UTF + * + * <h2> Basic types and constants for UTF </h2> + * This file defines basic types and constants for utf.h to be + * platform-independent. umachine.h and utf.h are included into + * utypes.h to provide all the general definitions for ICU. + * All of these definitions used to be in utypes.h before + * the UTF-handling macros made this unmaintainable. + * + */ +/*==========================================================================*/ +/* Include platform-dependent definitions */ +/* which are contained in the platform-specific file platform.h */ +/*==========================================================================*/ + +#include "./ptypes.h" /* platform.h is included in ptypes.h */ + +/* + * ANSI C headers: + * stddef.h defines wchar_t + */ +#include <stddef.h> + +/*==========================================================================*/ +/* For C wrappers, we use the symbol U_STABLE. */ +/* This works properly if the includer is C or C++. */ +/* Functions are declared U_STABLE return-type U_EXPORT2 function-name()... */ +/*==========================================================================*/ + +/** + * \def U_CFUNC + * This is used in a declaration of a library private ICU C function. + * @stable ICU 2.4 + */ + +/** + * \def U_CDECL_BEGIN + * This is used to begin a declaration of a library private ICU C API. + * @stable ICU 2.4 + */ + +/** + * \def U_CDECL_END + * This is used to end a declaration of a library private ICU C API + * @stable ICU 2.4 + */ + +#ifdef __cplusplus +# define U_CFUNC extern "C" +# define U_CDECL_BEGIN extern "C" { +# define U_CDECL_END } +#else +# define U_CFUNC extern +# define U_CDECL_BEGIN +# define U_CDECL_END +#endif + +#ifndef U_ATTRIBUTE_DEPRECATED +/** + * \def U_ATTRIBUTE_DEPRECATED + * This is used for GCC specific attributes + * @internal + */ +#if U_GCC_MAJOR_MINOR >= 302 +# define U_ATTRIBUTE_DEPRECATED __attribute__ ((deprecated)) +/** + * \def U_ATTRIBUTE_DEPRECATED + * This is used for Visual C++ specific attributes + * @internal + */ +#elif defined(_MSC_VER) && (_MSC_VER >= 1400) +# define U_ATTRIBUTE_DEPRECATED __declspec(deprecated) +#else +# define U_ATTRIBUTE_DEPRECATED +#endif +#endif + +/** This is used to declare a function as a public ICU C API @stable ICU 2.0*/ +#define U_CAPI U_CFUNC U_EXPORT +/** This is used to declare a function as a stable public ICU C API*/ +#define U_STABLE U_CAPI +/** This is used to declare a function as a draft public ICU C API */ +#define U_DRAFT U_CAPI +/** This is used to declare a function as a deprecated public ICU C API */ +#define U_DEPRECATED U_CAPI U_ATTRIBUTE_DEPRECATED +/** This is used to declare a function as an obsolete public ICU C API */ +#define U_OBSOLETE U_CAPI +/** This is used to declare a function as an internal ICU C API */ +#define U_INTERNAL U_CAPI + +/** + * \def U_OVERRIDE + * Defined to the C++11 "override" keyword if available. + * Denotes a class or member which is an override of the base class. + * May result in an error if it applied to something not an override. + * @internal + */ +#ifndef U_OVERRIDE +#define U_OVERRIDE override +#endif + +/** + * \def U_FINAL + * Defined to the C++11 "final" keyword if available. + * Denotes a class or member which may not be overridden in subclasses. + * May result in an error if subclasses attempt to override. + * @internal + */ +#if !defined(U_FINAL) || defined(U_IN_DOXYGEN) +#define U_FINAL final +#endif + +// Before ICU 65, function-like, multi-statement ICU macros were just defined as +// series of statements wrapped in { } blocks and the caller could choose to +// either treat them as if they were actual functions and end the invocation +// with a trailing ; creating an empty statement after the block or else omit +// this trailing ; using the knowledge that the macro would expand to { }. +// +// But doing so doesn't work well with macros that look like functions and +// compiler warnings about empty statements (ICU-20601) and ICU 65 therefore +// switches to the standard solution of wrapping such macros in do { } while. +// +// This will however break existing code that depends on being able to invoke +// these macros without a trailing ; so to be able to remain compatible with +// such code the wrapper is itself defined as macros so that it's possible to +// build ICU 65 and later with the old macro behaviour, like this: +// +// CPPFLAGS='-DUPRV_BLOCK_MACRO_BEGIN="" -DUPRV_BLOCK_MACRO_END=""' +// runConfigureICU ... + +/** + * \def UPRV_BLOCK_MACRO_BEGIN + * Defined as the "do" keyword by default. + * @internal + */ +#ifndef UPRV_BLOCK_MACRO_BEGIN +#define UPRV_BLOCK_MACRO_BEGIN do +#endif + +/** + * \def UPRV_BLOCK_MACRO_END + * Defined as "while (FALSE)" by default. + * @internal + */ +#ifndef UPRV_BLOCK_MACRO_END +#define UPRV_BLOCK_MACRO_END while (FALSE) +#endif + +/*==========================================================================*/ +/* limits for int32_t etc., like in POSIX inttypes.h */ +/*==========================================================================*/ + +#ifndef INT8_MIN +/** The smallest value an 8 bit signed integer can hold @stable ICU 2.0 */ +# define INT8_MIN ((int8_t)(-128)) +#endif +#ifndef INT16_MIN +/** The smallest value a 16 bit signed integer can hold @stable ICU 2.0 */ +# define INT16_MIN ((int16_t)(-32767-1)) +#endif +#ifndef INT32_MIN +/** The smallest value a 32 bit signed integer can hold @stable ICU 2.0 */ +# define INT32_MIN ((int32_t)(-2147483647-1)) +#endif + +#ifndef INT8_MAX +/** The largest value an 8 bit signed integer can hold @stable ICU 2.0 */ +# define INT8_MAX ((int8_t)(127)) +#endif +#ifndef INT16_MAX +/** The largest value a 16 bit signed integer can hold @stable ICU 2.0 */ +# define INT16_MAX ((int16_t)(32767)) +#endif +#ifndef INT32_MAX +/** The largest value a 32 bit signed integer can hold @stable ICU 2.0 */ +# define INT32_MAX ((int32_t)(2147483647)) +#endif + +#ifndef UINT8_MAX +/** The largest value an 8 bit unsigned integer can hold @stable ICU 2.0 */ +# define UINT8_MAX ((uint8_t)(255U)) +#endif +#ifndef UINT16_MAX +/** The largest value a 16 bit unsigned integer can hold @stable ICU 2.0 */ +# define UINT16_MAX ((uint16_t)(65535U)) +#endif +#ifndef UINT32_MAX +/** The largest value a 32 bit unsigned integer can hold @stable ICU 2.0 */ +# define UINT32_MAX ((uint32_t)(4294967295U)) +#endif + +#if defined(U_INT64_T_UNAVAILABLE) +# error int64_t is required for decimal format and rule-based number format. +#else +# ifndef INT64_C +/** + * Provides a platform independent way to specify a signed 64-bit integer constant. + * note: may be wrong for some 64 bit platforms - ensure your compiler provides INT64_C + * @stable ICU 2.8 + */ +# define INT64_C(c) c ## LL +# endif +# ifndef UINT64_C +/** + * Provides a platform independent way to specify an unsigned 64-bit integer constant. + * note: may be wrong for some 64 bit platforms - ensure your compiler provides UINT64_C + * @stable ICU 2.8 + */ +# define UINT64_C(c) c ## ULL +# endif +# ifndef U_INT64_MIN +/** The smallest value a 64 bit signed integer can hold @stable ICU 2.8 */ +# define U_INT64_MIN ((int64_t)(INT64_C(-9223372036854775807)-1)) +# endif +# ifndef U_INT64_MAX +/** The largest value a 64 bit signed integer can hold @stable ICU 2.8 */ +# define U_INT64_MAX ((int64_t)(INT64_C(9223372036854775807))) +# endif +# ifndef U_UINT64_MAX +/** The largest value a 64 bit unsigned integer can hold @stable ICU 2.8 */ +# define U_UINT64_MAX ((uint64_t)(UINT64_C(18446744073709551615))) +# endif +#endif + +/*==========================================================================*/ +/* Boolean data type */ +/*==========================================================================*/ + +/** The ICU boolean type @stable ICU 2.0 */ +typedef int8_t UBool; + +#ifndef TRUE +/** The TRUE value of a UBool @stable ICU 2.0 */ +# define TRUE 1 +#endif +#ifndef FALSE +/** The FALSE value of a UBool @stable ICU 2.0 */ +# define FALSE 0 +#endif + + +/*==========================================================================*/ +/* Unicode data types */ +/*==========================================================================*/ + +/* wchar_t-related definitions -------------------------------------------- */ + +/* + * \def U_WCHAR_IS_UTF16 + * Defined if wchar_t uses UTF-16. + * + * @stable ICU 2.0 + */ +/* + * \def U_WCHAR_IS_UTF32 + * Defined if wchar_t uses UTF-32. + * + * @stable ICU 2.0 + */ +#if !defined(U_WCHAR_IS_UTF16) && !defined(U_WCHAR_IS_UTF32) +# ifdef __STDC_ISO_10646__ +# if (U_SIZEOF_WCHAR_T==2) +# define U_WCHAR_IS_UTF16 +# elif (U_SIZEOF_WCHAR_T==4) +# define U_WCHAR_IS_UTF32 +# endif +# elif defined __UCS2__ +# if (U_PF_OS390 <= U_PLATFORM && U_PLATFORM <= U_PF_OS400) && (U_SIZEOF_WCHAR_T==2) +# define U_WCHAR_IS_UTF16 +# endif +# elif defined(__UCS4__) || (U_PLATFORM == U_PF_OS400 && defined(__UTF32__)) +# if (U_SIZEOF_WCHAR_T==4) +# define U_WCHAR_IS_UTF32 +# endif +# elif U_PLATFORM_IS_DARWIN_BASED || (U_SIZEOF_WCHAR_T==4 && U_PLATFORM_IS_LINUX_BASED) +# define U_WCHAR_IS_UTF32 +# elif U_PLATFORM_HAS_WIN32_API +# define U_WCHAR_IS_UTF16 +# endif +#endif + +/* UChar and UChar32 definitions -------------------------------------------- */ + +/** Number of bytes in a UChar. @stable ICU 2.0 */ +#define U_SIZEOF_UCHAR 2 + +/** + * \def U_CHAR16_IS_TYPEDEF + * If 1, then char16_t is a typedef and not a real type (yet) + * @internal + */ +#if (U_PLATFORM == U_PF_AIX) && defined(__cplusplus) &&(U_CPLUSPLUS_VERSION < 11) +// for AIX, uchar.h needs to be included +# include <uchar.h> +# define U_CHAR16_IS_TYPEDEF 1 +#elif defined(_MSC_VER) && (_MSC_VER < 1900) +// Versions of Visual Studio/MSVC below 2015 do not support char16_t as a real type, +// and instead use a typedef. https://msdn.microsoft.com/library/bb531344.aspx +# define U_CHAR16_IS_TYPEDEF 1 +#else +# define U_CHAR16_IS_TYPEDEF 0 +#endif + + +/** + * \var UChar + * + * The base type for UTF-16 code units and pointers. + * Unsigned 16-bit integer. + * Starting with ICU 59, C++ API uses char16_t directly, while C API continues to use UChar. + * + * UChar is configurable by defining the macro UCHAR_TYPE + * on the preprocessor or compiler command line: + * -DUCHAR_TYPE=uint16_t or -DUCHAR_TYPE=wchar_t (if U_SIZEOF_WCHAR_T==2) etc. + * (The UCHAR_TYPE can also be \#defined earlier in this file, for outside the ICU library code.) + * This is for transitional use from application code that uses uint16_t or wchar_t for UTF-16. + * + * The default is UChar=char16_t. + * + * C++11 defines char16_t as bit-compatible with uint16_t, but as a distinct type. + * + * In C, char16_t is a simple typedef of uint_least16_t. + * ICU requires uint_least16_t=uint16_t for data memory mapping. + * On macOS, char16_t is not available because the uchar.h standard header is missing. + * + * @stable ICU 4.4 + */ + +#if 1 + // #if 1 is normal. UChar defaults to char16_t in C++. + // For configuration testing of UChar=uint16_t temporarily change this to #if 0. + // The intltest Makefile #defines UCHAR_TYPE=char16_t, + // so we only #define it to uint16_t if it is undefined so far. +#elif !defined(UCHAR_TYPE) +# define UCHAR_TYPE uint16_t +#endif + +#if defined(U_COMBINED_IMPLEMENTATION) || defined(U_COMMON_IMPLEMENTATION) || \ + defined(U_I18N_IMPLEMENTATION) || defined(U_IO_IMPLEMENTATION) + // Inside the ICU library code, never configurable. + typedef char16_t UChar; +#elif defined(UCHAR_TYPE) + typedef UCHAR_TYPE UChar; +#elif defined(__cplusplus) + typedef char16_t UChar; +#else + typedef uint16_t UChar; +#endif + +/** + * \var OldUChar + * Default ICU 58 definition of UChar. + * A base type for UTF-16 code units and pointers. + * Unsigned 16-bit integer. + * + * Define OldUChar to be wchar_t if that is 16 bits wide. + * If wchar_t is not 16 bits wide, then define UChar to be uint16_t. + * + * This makes the definition of OldUChar platform-dependent + * but allows direct string type compatibility with platforms with + * 16-bit wchar_t types. + * + * This is how UChar was defined in ICU 58, for transition convenience. + * Exception: ICU 58 UChar was defined to UCHAR_TYPE if that macro was defined. + * The current UChar responds to UCHAR_TYPE but OldUChar does not. + * + * @stable ICU 59 + */ +#if U_SIZEOF_WCHAR_T==2 + typedef wchar_t OldUChar; +#elif defined(__CHAR16_TYPE__) + typedef __CHAR16_TYPE__ OldUChar; +#else + typedef uint16_t OldUChar; +#endif + +/** + * Define UChar32 as a type for single Unicode code points. + * UChar32 is a signed 32-bit integer (same as int32_t). + * + * The Unicode code point range is 0..0x10ffff. + * All other values (negative or >=0x110000) are illegal as Unicode code points. + * They may be used as sentinel values to indicate "done", "error" + * or similar non-code point conditions. + * + * Before ICU 2.4 (Jitterbug 2146), UChar32 was defined + * to be wchar_t if that is 32 bits wide (wchar_t may be signed or unsigned) + * or else to be uint32_t. + * That is, the definition of UChar32 was platform-dependent. + * + * @see U_SENTINEL + * @stable ICU 2.4 + */ +typedef int32_t UChar32; + +/** + * This value is intended for sentinel values for APIs that + * (take or) return single code points (UChar32). + * It is outside of the Unicode code point range 0..0x10ffff. + * + * For example, a "done" or "error" value in a new API + * could be indicated with U_SENTINEL. + * + * ICU APIs designed before ICU 2.4 usually define service-specific "done" + * values, mostly 0xffff. + * Those may need to be distinguished from + * actual U+ffff text contents by calling functions like + * CharacterIterator::hasNext() or UnicodeString::length(). + * + * @return -1 + * @see UChar32 + * @stable ICU 2.4 + */ +#define U_SENTINEL (-1) + +#include "./urename.h" + +#endif diff --git a/src/tree_sitter/unicode/urename.h b/src/tree_sitter/unicode/urename.h new file mode 100644 index 0000000000..ac79ad0f98 --- /dev/null +++ b/src/tree_sitter/unicode/urename.h @@ -0,0 +1 @@ +// This file must exist in order for `utf8.h` and `utf16.h` to be used. diff --git a/src/tree_sitter/unicode/utf.h b/src/tree_sitter/unicode/utf.h new file mode 100644 index 0000000000..ac79ad0f98 --- /dev/null +++ b/src/tree_sitter/unicode/utf.h @@ -0,0 +1 @@ +// This file must exist in order for `utf8.h` and `utf16.h` to be used. diff --git a/src/tree_sitter/unicode/utf16.h b/src/tree_sitter/unicode/utf16.h new file mode 100644 index 0000000000..b547922441 --- /dev/null +++ b/src/tree_sitter/unicode/utf16.h @@ -0,0 +1,733 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* +* Copyright (C) 1999-2012, International Business Machines +* Corporation and others. All Rights Reserved. +* +******************************************************************************* +* file name: utf16.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 1999sep09 +* created by: Markus W. Scherer +*/ + +/** + * \file + * \brief C API: 16-bit Unicode handling macros + * + * This file defines macros to deal with 16-bit Unicode (UTF-16) code units and strings. + * + * For more information see utf.h and the ICU User Guide Strings chapter + * (http://userguide.icu-project.org/strings). + * + * <em>Usage:</em> + * ICU coding guidelines for if() statements should be followed when using these macros. + * Compound statements (curly braces {}) must be used for if-else-while... + * bodies and all macro statements should be terminated with semicolon. + */ + +#ifndef __UTF16_H__ +#define __UTF16_H__ + +#include "./umachine.h" +#ifndef __UTF_H__ +# include "./utf.h" +#endif + +/* single-code point definitions -------------------------------------------- */ + +/** + * Does this code unit alone encode a code point (BMP, not a surrogate)? + * @param c 16-bit code unit + * @return TRUE or FALSE + * @stable ICU 2.4 + */ +#define U16_IS_SINGLE(c) !U_IS_SURROGATE(c) + +/** + * Is this code unit a lead surrogate (U+d800..U+dbff)? + * @param c 16-bit code unit + * @return TRUE or FALSE + * @stable ICU 2.4 + */ +#define U16_IS_LEAD(c) (((c)&0xfffffc00)==0xd800) + +/** + * Is this code unit a trail surrogate (U+dc00..U+dfff)? + * @param c 16-bit code unit + * @return TRUE or FALSE + * @stable ICU 2.4 + */ +#define U16_IS_TRAIL(c) (((c)&0xfffffc00)==0xdc00) + +/** + * Is this code unit a surrogate (U+d800..U+dfff)? + * @param c 16-bit code unit + * @return TRUE or FALSE + * @stable ICU 2.4 + */ +#define U16_IS_SURROGATE(c) U_IS_SURROGATE(c) + +/** + * Assuming c is a surrogate code point (U16_IS_SURROGATE(c)), + * is it a lead surrogate? + * @param c 16-bit code unit + * @return TRUE or FALSE + * @stable ICU 2.4 + */ +#define U16_IS_SURROGATE_LEAD(c) (((c)&0x400)==0) + +/** + * Assuming c is a surrogate code point (U16_IS_SURROGATE(c)), + * is it a trail surrogate? + * @param c 16-bit code unit + * @return TRUE or FALSE + * @stable ICU 4.2 + */ +#define U16_IS_SURROGATE_TRAIL(c) (((c)&0x400)!=0) + +/** + * Helper constant for U16_GET_SUPPLEMENTARY. + * @internal + */ +#define U16_SURROGATE_OFFSET ((0xd800<<10UL)+0xdc00-0x10000) + +/** + * Get a supplementary code point value (U+10000..U+10ffff) + * from its lead and trail surrogates. + * The result is undefined if the input values are not + * lead and trail surrogates. + * + * @param lead lead surrogate (U+d800..U+dbff) + * @param trail trail surrogate (U+dc00..U+dfff) + * @return supplementary code point (U+10000..U+10ffff) + * @stable ICU 2.4 + */ +#define U16_GET_SUPPLEMENTARY(lead, trail) \ + (((UChar32)(lead)<<10UL)+(UChar32)(trail)-U16_SURROGATE_OFFSET) + + +/** + * Get the lead surrogate (0xd800..0xdbff) for a + * supplementary code point (0x10000..0x10ffff). + * @param supplementary 32-bit code point (U+10000..U+10ffff) + * @return lead surrogate (U+d800..U+dbff) for supplementary + * @stable ICU 2.4 + */ +#define U16_LEAD(supplementary) (UChar)(((supplementary)>>10)+0xd7c0) + +/** + * Get the trail surrogate (0xdc00..0xdfff) for a + * supplementary code point (0x10000..0x10ffff). + * @param supplementary 32-bit code point (U+10000..U+10ffff) + * @return trail surrogate (U+dc00..U+dfff) for supplementary + * @stable ICU 2.4 + */ +#define U16_TRAIL(supplementary) (UChar)(((supplementary)&0x3ff)|0xdc00) + +/** + * How many 16-bit code units are used to encode this Unicode code point? (1 or 2) + * The result is not defined if c is not a Unicode code point (U+0000..U+10ffff). + * @param c 32-bit code point + * @return 1 or 2 + * @stable ICU 2.4 + */ +#define U16_LENGTH(c) ((uint32_t)(c)<=0xffff ? 1 : 2) + +/** + * The maximum number of 16-bit code units per Unicode code point (U+0000..U+10ffff). + * @return 2 + * @stable ICU 2.4 + */ +#define U16_MAX_LENGTH 2 + +/** + * Get a code point from a string at a random-access offset, + * without changing the offset. + * "Unsafe" macro, assumes well-formed UTF-16. + * + * The offset may point to either the lead or trail surrogate unit + * for a supplementary code point, in which case the macro will read + * the adjacent matching surrogate as well. + * The result is undefined if the offset points to a single, unpaired surrogate. + * Iteration through a string is more efficient with U16_NEXT_UNSAFE or U16_NEXT. + * + * @param s const UChar * string + * @param i string offset + * @param c output UChar32 variable + * @see U16_GET + * @stable ICU 2.4 + */ +#define U16_GET_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[i]; \ + if(U16_IS_SURROGATE(c)) { \ + if(U16_IS_SURROGATE_LEAD(c)) { \ + (c)=U16_GET_SUPPLEMENTARY((c), (s)[(i)+1]); \ + } else { \ + (c)=U16_GET_SUPPLEMENTARY((s)[(i)-1], (c)); \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Get a code point from a string at a random-access offset, + * without changing the offset. + * "Safe" macro, handles unpaired surrogates and checks for string boundaries. + * + * The offset may point to either the lead or trail surrogate unit + * for a supplementary code point, in which case the macro will read + * the adjacent matching surrogate as well. + * + * The length can be negative for a NUL-terminated string. + * + * If the offset points to a single, unpaired surrogate, then + * c is set to that unpaired surrogate. + * Iteration through a string is more efficient with U16_NEXT_UNSAFE or U16_NEXT. + * + * @param s const UChar * string + * @param start starting string offset (usually 0) + * @param i string offset, must be start<=i<length + * @param length string length + * @param c output UChar32 variable + * @see U16_GET_UNSAFE + * @stable ICU 2.4 + */ +#define U16_GET(s, start, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[i]; \ + if(U16_IS_SURROGATE(c)) { \ + uint16_t __c2; \ + if(U16_IS_SURROGATE_LEAD(c)) { \ + if((i)+1!=(length) && U16_IS_TRAIL(__c2=(s)[(i)+1])) { \ + (c)=U16_GET_SUPPLEMENTARY((c), __c2); \ + } \ + } else { \ + if((i)>(start) && U16_IS_LEAD(__c2=(s)[(i)-1])) { \ + (c)=U16_GET_SUPPLEMENTARY(__c2, (c)); \ + } \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Get a code point from a string at a random-access offset, + * without changing the offset. + * "Safe" macro, handles unpaired surrogates and checks for string boundaries. + * + * The offset may point to either the lead or trail surrogate unit + * for a supplementary code point, in which case the macro will read + * the adjacent matching surrogate as well. + * + * The length can be negative for a NUL-terminated string. + * + * If the offset points to a single, unpaired surrogate, then + * c is set to U+FFFD. + * Iteration through a string is more efficient with U16_NEXT_UNSAFE or U16_NEXT_OR_FFFD. + * + * @param s const UChar * string + * @param start starting string offset (usually 0) + * @param i string offset, must be start<=i<length + * @param length string length + * @param c output UChar32 variable + * @see U16_GET_UNSAFE + * @stable ICU 60 + */ +#define U16_GET_OR_FFFD(s, start, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[i]; \ + if(U16_IS_SURROGATE(c)) { \ + uint16_t __c2; \ + if(U16_IS_SURROGATE_LEAD(c)) { \ + if((i)+1!=(length) && U16_IS_TRAIL(__c2=(s)[(i)+1])) { \ + (c)=U16_GET_SUPPLEMENTARY((c), __c2); \ + } else { \ + (c)=0xfffd; \ + } \ + } else { \ + if((i)>(start) && U16_IS_LEAD(__c2=(s)[(i)-1])) { \ + (c)=U16_GET_SUPPLEMENTARY(__c2, (c)); \ + } else { \ + (c)=0xfffd; \ + } \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/* definitions with forward iteration --------------------------------------- */ + +/** + * Get a code point from a string at a code point boundary offset, + * and advance the offset to the next code point boundary. + * (Post-incrementing forward iteration.) + * "Unsafe" macro, assumes well-formed UTF-16. + * + * The offset may point to the lead surrogate unit + * for a supplementary code point, in which case the macro will read + * the following trail surrogate as well. + * If the offset points to a trail surrogate, then that itself + * will be returned as the code point. + * The result is undefined if the offset points to a single, unpaired lead surrogate. + * + * @param s const UChar * string + * @param i string offset + * @param c output UChar32 variable + * @see U16_NEXT + * @stable ICU 2.4 + */ +#define U16_NEXT_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[(i)++]; \ + if(U16_IS_LEAD(c)) { \ + (c)=U16_GET_SUPPLEMENTARY((c), (s)[(i)++]); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Get a code point from a string at a code point boundary offset, + * and advance the offset to the next code point boundary. + * (Post-incrementing forward iteration.) + * "Safe" macro, handles unpaired surrogates and checks for string boundaries. + * + * The length can be negative for a NUL-terminated string. + * + * The offset may point to the lead surrogate unit + * for a supplementary code point, in which case the macro will read + * the following trail surrogate as well. + * If the offset points to a trail surrogate or + * to a single, unpaired lead surrogate, then c is set to that unpaired surrogate. + * + * @param s const UChar * string + * @param i string offset, must be i<length + * @param length string length + * @param c output UChar32 variable + * @see U16_NEXT_UNSAFE + * @stable ICU 2.4 + */ +#define U16_NEXT(s, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[(i)++]; \ + if(U16_IS_LEAD(c)) { \ + uint16_t __c2; \ + if((i)!=(length) && U16_IS_TRAIL(__c2=(s)[(i)])) { \ + ++(i); \ + (c)=U16_GET_SUPPLEMENTARY((c), __c2); \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Get a code point from a string at a code point boundary offset, + * and advance the offset to the next code point boundary. + * (Post-incrementing forward iteration.) + * "Safe" macro, handles unpaired surrogates and checks for string boundaries. + * + * The length can be negative for a NUL-terminated string. + * + * The offset may point to the lead surrogate unit + * for a supplementary code point, in which case the macro will read + * the following trail surrogate as well. + * If the offset points to a trail surrogate or + * to a single, unpaired lead surrogate, then c is set to U+FFFD. + * + * @param s const UChar * string + * @param i string offset, must be i<length + * @param length string length + * @param c output UChar32 variable + * @see U16_NEXT_UNSAFE + * @stable ICU 60 + */ +#define U16_NEXT_OR_FFFD(s, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[(i)++]; \ + if(U16_IS_SURROGATE(c)) { \ + uint16_t __c2; \ + if(U16_IS_SURROGATE_LEAD(c) && (i)!=(length) && U16_IS_TRAIL(__c2=(s)[(i)])) { \ + ++(i); \ + (c)=U16_GET_SUPPLEMENTARY((c), __c2); \ + } else { \ + (c)=0xfffd; \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Append a code point to a string, overwriting 1 or 2 code units. + * The offset points to the current end of the string contents + * and is advanced (post-increment). + * "Unsafe" macro, assumes a valid code point and sufficient space in the string. + * Otherwise, the result is undefined. + * + * @param s const UChar * string buffer + * @param i string offset + * @param c code point to append + * @see U16_APPEND + * @stable ICU 2.4 + */ +#define U16_APPEND_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + if((uint32_t)(c)<=0xffff) { \ + (s)[(i)++]=(uint16_t)(c); \ + } else { \ + (s)[(i)++]=(uint16_t)(((c)>>10)+0xd7c0); \ + (s)[(i)++]=(uint16_t)(((c)&0x3ff)|0xdc00); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Append a code point to a string, overwriting 1 or 2 code units. + * The offset points to the current end of the string contents + * and is advanced (post-increment). + * "Safe" macro, checks for a valid code point. + * If a surrogate pair is written, checks for sufficient space in the string. + * If the code point is not valid or a trail surrogate does not fit, + * then isError is set to TRUE. + * + * @param s const UChar * string buffer + * @param i string offset, must be i<capacity + * @param capacity size of the string buffer + * @param c code point to append + * @param isError output UBool set to TRUE if an error occurs, otherwise not modified + * @see U16_APPEND_UNSAFE + * @stable ICU 2.4 + */ +#define U16_APPEND(s, i, capacity, c, isError) UPRV_BLOCK_MACRO_BEGIN { \ + if((uint32_t)(c)<=0xffff) { \ + (s)[(i)++]=(uint16_t)(c); \ + } else if((uint32_t)(c)<=0x10ffff && (i)+1<(capacity)) { \ + (s)[(i)++]=(uint16_t)(((c)>>10)+0xd7c0); \ + (s)[(i)++]=(uint16_t)(((c)&0x3ff)|0xdc00); \ + } else /* c>0x10ffff or not enough space */ { \ + (isError)=TRUE; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Advance the string offset from one code point boundary to the next. + * (Post-incrementing iteration.) + * "Unsafe" macro, assumes well-formed UTF-16. + * + * @param s const UChar * string + * @param i string offset + * @see U16_FWD_1 + * @stable ICU 2.4 + */ +#define U16_FWD_1_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ + if(U16_IS_LEAD((s)[(i)++])) { \ + ++(i); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Advance the string offset from one code point boundary to the next. + * (Post-incrementing iteration.) + * "Safe" macro, handles unpaired surrogates and checks for string boundaries. + * + * The length can be negative for a NUL-terminated string. + * + * @param s const UChar * string + * @param i string offset, must be i<length + * @param length string length + * @see U16_FWD_1_UNSAFE + * @stable ICU 2.4 + */ +#define U16_FWD_1(s, i, length) UPRV_BLOCK_MACRO_BEGIN { \ + if(U16_IS_LEAD((s)[(i)++]) && (i)!=(length) && U16_IS_TRAIL((s)[i])) { \ + ++(i); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Advance the string offset from one code point boundary to the n-th next one, + * i.e., move forward by n code points. + * (Post-incrementing iteration.) + * "Unsafe" macro, assumes well-formed UTF-16. + * + * @param s const UChar * string + * @param i string offset + * @param n number of code points to skip + * @see U16_FWD_N + * @stable ICU 2.4 + */ +#define U16_FWD_N_UNSAFE(s, i, n) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t __N=(n); \ + while(__N>0) { \ + U16_FWD_1_UNSAFE(s, i); \ + --__N; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Advance the string offset from one code point boundary to the n-th next one, + * i.e., move forward by n code points. + * (Post-incrementing iteration.) + * "Safe" macro, handles unpaired surrogates and checks for string boundaries. + * + * The length can be negative for a NUL-terminated string. + * + * @param s const UChar * string + * @param i int32_t string offset, must be i<length + * @param length int32_t string length + * @param n number of code points to skip + * @see U16_FWD_N_UNSAFE + * @stable ICU 2.4 + */ +#define U16_FWD_N(s, i, length, n) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t __N=(n); \ + while(__N>0 && ((i)<(length) || ((length)<0 && (s)[i]!=0))) { \ + U16_FWD_1(s, i, length); \ + --__N; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Adjust a random-access offset to a code point boundary + * at the start of a code point. + * If the offset points to the trail surrogate of a surrogate pair, + * then the offset is decremented. + * Otherwise, it is not modified. + * "Unsafe" macro, assumes well-formed UTF-16. + * + * @param s const UChar * string + * @param i string offset + * @see U16_SET_CP_START + * @stable ICU 2.4 + */ +#define U16_SET_CP_START_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ + if(U16_IS_TRAIL((s)[i])) { \ + --(i); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Adjust a random-access offset to a code point boundary + * at the start of a code point. + * If the offset points to the trail surrogate of a surrogate pair, + * then the offset is decremented. + * Otherwise, it is not modified. + * "Safe" macro, handles unpaired surrogates and checks for string boundaries. + * + * @param s const UChar * string + * @param start starting string offset (usually 0) + * @param i string offset, must be start<=i + * @see U16_SET_CP_START_UNSAFE + * @stable ICU 2.4 + */ +#define U16_SET_CP_START(s, start, i) UPRV_BLOCK_MACRO_BEGIN { \ + if(U16_IS_TRAIL((s)[i]) && (i)>(start) && U16_IS_LEAD((s)[(i)-1])) { \ + --(i); \ + } \ +} UPRV_BLOCK_MACRO_END + +/* definitions with backward iteration -------------------------------------- */ + +/** + * Move the string offset from one code point boundary to the previous one + * and get the code point between them. + * (Pre-decrementing backward iteration.) + * "Unsafe" macro, assumes well-formed UTF-16. + * + * The input offset may be the same as the string length. + * If the offset is behind a trail surrogate unit + * for a supplementary code point, then the macro will read + * the preceding lead surrogate as well. + * If the offset is behind a lead surrogate, then that itself + * will be returned as the code point. + * The result is undefined if the offset is behind a single, unpaired trail surrogate. + * + * @param s const UChar * string + * @param i string offset + * @param c output UChar32 variable + * @see U16_PREV + * @stable ICU 2.4 + */ +#define U16_PREV_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[--(i)]; \ + if(U16_IS_TRAIL(c)) { \ + (c)=U16_GET_SUPPLEMENTARY((s)[--(i)], (c)); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Move the string offset from one code point boundary to the previous one + * and get the code point between them. + * (Pre-decrementing backward iteration.) + * "Safe" macro, handles unpaired surrogates and checks for string boundaries. + * + * The input offset may be the same as the string length. + * If the offset is behind a trail surrogate unit + * for a supplementary code point, then the macro will read + * the preceding lead surrogate as well. + * If the offset is behind a lead surrogate or behind a single, unpaired + * trail surrogate, then c is set to that unpaired surrogate. + * + * @param s const UChar * string + * @param start starting string offset (usually 0) + * @param i string offset, must be start<i + * @param c output UChar32 variable + * @see U16_PREV_UNSAFE + * @stable ICU 2.4 + */ +#define U16_PREV(s, start, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[--(i)]; \ + if(U16_IS_TRAIL(c)) { \ + uint16_t __c2; \ + if((i)>(start) && U16_IS_LEAD(__c2=(s)[(i)-1])) { \ + --(i); \ + (c)=U16_GET_SUPPLEMENTARY(__c2, (c)); \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Move the string offset from one code point boundary to the previous one + * and get the code point between them. + * (Pre-decrementing backward iteration.) + * "Safe" macro, handles unpaired surrogates and checks for string boundaries. + * + * The input offset may be the same as the string length. + * If the offset is behind a trail surrogate unit + * for a supplementary code point, then the macro will read + * the preceding lead surrogate as well. + * If the offset is behind a lead surrogate or behind a single, unpaired + * trail surrogate, then c is set to U+FFFD. + * + * @param s const UChar * string + * @param start starting string offset (usually 0) + * @param i string offset, must be start<i + * @param c output UChar32 variable + * @see U16_PREV_UNSAFE + * @stable ICU 60 + */ +#define U16_PREV_OR_FFFD(s, start, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[--(i)]; \ + if(U16_IS_SURROGATE(c)) { \ + uint16_t __c2; \ + if(U16_IS_SURROGATE_TRAIL(c) && (i)>(start) && U16_IS_LEAD(__c2=(s)[(i)-1])) { \ + --(i); \ + (c)=U16_GET_SUPPLEMENTARY(__c2, (c)); \ + } else { \ + (c)=0xfffd; \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Move the string offset from one code point boundary to the previous one. + * (Pre-decrementing backward iteration.) + * The input offset may be the same as the string length. + * "Unsafe" macro, assumes well-formed UTF-16. + * + * @param s const UChar * string + * @param i string offset + * @see U16_BACK_1 + * @stable ICU 2.4 + */ +#define U16_BACK_1_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ + if(U16_IS_TRAIL((s)[--(i)])) { \ + --(i); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Move the string offset from one code point boundary to the previous one. + * (Pre-decrementing backward iteration.) + * The input offset may be the same as the string length. + * "Safe" macro, handles unpaired surrogates and checks for string boundaries. + * + * @param s const UChar * string + * @param start starting string offset (usually 0) + * @param i string offset, must be start<i + * @see U16_BACK_1_UNSAFE + * @stable ICU 2.4 + */ +#define U16_BACK_1(s, start, i) UPRV_BLOCK_MACRO_BEGIN { \ + if(U16_IS_TRAIL((s)[--(i)]) && (i)>(start) && U16_IS_LEAD((s)[(i)-1])) { \ + --(i); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Move the string offset from one code point boundary to the n-th one before it, + * i.e., move backward by n code points. + * (Pre-decrementing backward iteration.) + * The input offset may be the same as the string length. + * "Unsafe" macro, assumes well-formed UTF-16. + * + * @param s const UChar * string + * @param i string offset + * @param n number of code points to skip + * @see U16_BACK_N + * @stable ICU 2.4 + */ +#define U16_BACK_N_UNSAFE(s, i, n) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t __N=(n); \ + while(__N>0) { \ + U16_BACK_1_UNSAFE(s, i); \ + --__N; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Move the string offset from one code point boundary to the n-th one before it, + * i.e., move backward by n code points. + * (Pre-decrementing backward iteration.) + * The input offset may be the same as the string length. + * "Safe" macro, handles unpaired surrogates and checks for string boundaries. + * + * @param s const UChar * string + * @param start start of string + * @param i string offset, must be start<i + * @param n number of code points to skip + * @see U16_BACK_N_UNSAFE + * @stable ICU 2.4 + */ +#define U16_BACK_N(s, start, i, n) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t __N=(n); \ + while(__N>0 && (i)>(start)) { \ + U16_BACK_1(s, start, i); \ + --__N; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Adjust a random-access offset to a code point boundary after a code point. + * If the offset is behind the lead surrogate of a surrogate pair, + * then the offset is incremented. + * Otherwise, it is not modified. + * The input offset may be the same as the string length. + * "Unsafe" macro, assumes well-formed UTF-16. + * + * @param s const UChar * string + * @param i string offset + * @see U16_SET_CP_LIMIT + * @stable ICU 2.4 + */ +#define U16_SET_CP_LIMIT_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ + if(U16_IS_LEAD((s)[(i)-1])) { \ + ++(i); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Adjust a random-access offset to a code point boundary after a code point. + * If the offset is behind the lead surrogate of a surrogate pair, + * then the offset is incremented. + * Otherwise, it is not modified. + * The input offset may be the same as the string length. + * "Safe" macro, handles unpaired surrogates and checks for string boundaries. + * + * The length can be negative for a NUL-terminated string. + * + * @param s const UChar * string + * @param start int32_t starting string offset (usually 0) + * @param i int32_t string offset, start<=i<=length + * @param length int32_t string length + * @see U16_SET_CP_LIMIT_UNSAFE + * @stable ICU 2.4 + */ +#define U16_SET_CP_LIMIT(s, start, i, length) UPRV_BLOCK_MACRO_BEGIN { \ + if((start)<(i) && ((i)<(length) || (length)<0) && U16_IS_LEAD((s)[(i)-1]) && U16_IS_TRAIL((s)[i])) { \ + ++(i); \ + } \ +} UPRV_BLOCK_MACRO_END + +#endif diff --git a/src/tree_sitter/unicode/utf8.h b/src/tree_sitter/unicode/utf8.h new file mode 100644 index 0000000000..3b37873e37 --- /dev/null +++ b/src/tree_sitter/unicode/utf8.h @@ -0,0 +1,881 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* +* Copyright (C) 1999-2015, International Business Machines +* Corporation and others. All Rights Reserved. +* +******************************************************************************* +* file name: utf8.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 1999sep13 +* created by: Markus W. Scherer +*/ + +/** + * \file + * \brief C API: 8-bit Unicode handling macros + * + * This file defines macros to deal with 8-bit Unicode (UTF-8) code units (bytes) and strings. + * + * For more information see utf.h and the ICU User Guide Strings chapter + * (http://userguide.icu-project.org/strings). + * + * <em>Usage:</em> + * ICU coding guidelines for if() statements should be followed when using these macros. + * Compound statements (curly braces {}) must be used for if-else-while... + * bodies and all macro statements should be terminated with semicolon. + */ + +#ifndef __UTF8_H__ +#define __UTF8_H__ + +#include "./umachine.h" +#ifndef __UTF_H__ +# include "./utf.h" +#endif + +/* internal definitions ----------------------------------------------------- */ + +/** + * Counts the trail bytes for a UTF-8 lead byte. + * Returns 0 for 0..0xc1 as well as for 0xf5..0xff. + * leadByte might be evaluated multiple times. + * + * This is internal since it is not meant to be called directly by external clients; + * however it is called by public macros in this file and thus must remain stable. + * + * @param leadByte The first byte of a UTF-8 sequence. Must be 0..0xff. + * @internal + */ +#define U8_COUNT_TRAIL_BYTES(leadByte) \ + (U8_IS_LEAD(leadByte) ? \ + ((uint8_t)(leadByte)>=0xe0)+((uint8_t)(leadByte)>=0xf0)+1 : 0) + +/** + * Counts the trail bytes for a UTF-8 lead byte of a valid UTF-8 sequence. + * Returns 0 for 0..0xc1. Undefined for 0xf5..0xff. + * leadByte might be evaluated multiple times. + * + * This is internal since it is not meant to be called directly by external clients; + * however it is called by public macros in this file and thus must remain stable. + * + * @param leadByte The first byte of a UTF-8 sequence. Must be 0..0xff. + * @internal + */ +#define U8_COUNT_TRAIL_BYTES_UNSAFE(leadByte) \ + (((uint8_t)(leadByte)>=0xc2)+((uint8_t)(leadByte)>=0xe0)+((uint8_t)(leadByte)>=0xf0)) + +/** + * Mask a UTF-8 lead byte, leave only the lower bits that form part of the code point value. + * + * This is internal since it is not meant to be called directly by external clients; + * however it is called by public macros in this file and thus must remain stable. + * @internal + */ +#define U8_MASK_LEAD_BYTE(leadByte, countTrailBytes) ((leadByte)&=(1<<(6-(countTrailBytes)))-1) + +/** + * Internal bit vector for 3-byte UTF-8 validity check, for use in U8_IS_VALID_LEAD3_AND_T1. + * Each bit indicates whether one lead byte + first trail byte pair starts a valid sequence. + * Lead byte E0..EF bits 3..0 are used as byte index, + * first trail byte bits 7..5 are used as bit index into that byte. + * @see U8_IS_VALID_LEAD3_AND_T1 + * @internal + */ +#define U8_LEAD3_T1_BITS "\x20\x30\x30\x30\x30\x30\x30\x30\x30\x30\x30\x30\x30\x10\x30\x30" + +/** + * Internal 3-byte UTF-8 validity check. + * Non-zero if lead byte E0..EF and first trail byte 00..FF start a valid sequence. + * @internal + */ +#define U8_IS_VALID_LEAD3_AND_T1(lead, t1) (U8_LEAD3_T1_BITS[(lead)&0xf]&(1<<((uint8_t)(t1)>>5))) + +/** + * Internal bit vector for 4-byte UTF-8 validity check, for use in U8_IS_VALID_LEAD4_AND_T1. + * Each bit indicates whether one lead byte + first trail byte pair starts a valid sequence. + * First trail byte bits 7..4 are used as byte index, + * lead byte F0..F4 bits 2..0 are used as bit index into that byte. + * @see U8_IS_VALID_LEAD4_AND_T1 + * @internal + */ +#define U8_LEAD4_T1_BITS "\x00\x00\x00\x00\x00\x00\x00\x00\x1E\x0F\x0F\x0F\x00\x00\x00\x00" + +/** + * Internal 4-byte UTF-8 validity check. + * Non-zero if lead byte F0..F4 and first trail byte 00..FF start a valid sequence. + * @internal + */ +#define U8_IS_VALID_LEAD4_AND_T1(lead, t1) (U8_LEAD4_T1_BITS[(uint8_t)(t1)>>4]&(1<<((lead)&7))) + +/** + * Function for handling "next code point" with error-checking. + * + * This is internal since it is not meant to be called directly by external clients; + * however it is U_STABLE (not U_INTERNAL) since it is called by public macros in this + * file and thus must remain stable, and should not be hidden when other internal + * functions are hidden (otherwise public macros would fail to compile). + * @internal + */ +U_STABLE UChar32 U_EXPORT2 +utf8_nextCharSafeBody(const uint8_t *s, int32_t *pi, int32_t length, UChar32 c, UBool strict); + +/** + * Function for handling "append code point" with error-checking. + * + * This is internal since it is not meant to be called directly by external clients; + * however it is U_STABLE (not U_INTERNAL) since it is called by public macros in this + * file and thus must remain stable, and should not be hidden when other internal + * functions are hidden (otherwise public macros would fail to compile). + * @internal + */ +U_STABLE int32_t U_EXPORT2 +utf8_appendCharSafeBody(uint8_t *s, int32_t i, int32_t length, UChar32 c, UBool *pIsError); + +/** + * Function for handling "previous code point" with error-checking. + * + * This is internal since it is not meant to be called directly by external clients; + * however it is U_STABLE (not U_INTERNAL) since it is called by public macros in this + * file and thus must remain stable, and should not be hidden when other internal + * functions are hidden (otherwise public macros would fail to compile). + * @internal + */ +U_STABLE UChar32 U_EXPORT2 +utf8_prevCharSafeBody(const uint8_t *s, int32_t start, int32_t *pi, UChar32 c, UBool strict); + +/** + * Function for handling "skip backward one code point" with error-checking. + * + * This is internal since it is not meant to be called directly by external clients; + * however it is U_STABLE (not U_INTERNAL) since it is called by public macros in this + * file and thus must remain stable, and should not be hidden when other internal + * functions are hidden (otherwise public macros would fail to compile). + * @internal + */ +U_STABLE int32_t U_EXPORT2 +utf8_back1SafeBody(const uint8_t *s, int32_t start, int32_t i); + +/* single-code point definitions -------------------------------------------- */ + +/** + * Does this code unit (byte) encode a code point by itself (US-ASCII 0..0x7f)? + * @param c 8-bit code unit (byte) + * @return TRUE or FALSE + * @stable ICU 2.4 + */ +#define U8_IS_SINGLE(c) (((c)&0x80)==0) + +/** + * Is this code unit (byte) a UTF-8 lead byte? (0xC2..0xF4) + * @param c 8-bit code unit (byte) + * @return TRUE or FALSE + * @stable ICU 2.4 + */ +#define U8_IS_LEAD(c) ((uint8_t)((c)-0xc2)<=0x32) +// 0x32=0xf4-0xc2 + +/** + * Is this code unit (byte) a UTF-8 trail byte? (0x80..0xBF) + * @param c 8-bit code unit (byte) + * @return TRUE or FALSE + * @stable ICU 2.4 + */ +#define U8_IS_TRAIL(c) ((int8_t)(c)<-0x40) + +/** + * How many code units (bytes) are used for the UTF-8 encoding + * of this Unicode code point? + * @param c 32-bit code point + * @return 1..4, or 0 if c is a surrogate or not a Unicode code point + * @stable ICU 2.4 + */ +#define U8_LENGTH(c) \ + ((uint32_t)(c)<=0x7f ? 1 : \ + ((uint32_t)(c)<=0x7ff ? 2 : \ + ((uint32_t)(c)<=0xd7ff ? 3 : \ + ((uint32_t)(c)<=0xdfff || (uint32_t)(c)>0x10ffff ? 0 : \ + ((uint32_t)(c)<=0xffff ? 3 : 4)\ + ) \ + ) \ + ) \ + ) + +/** + * The maximum number of UTF-8 code units (bytes) per Unicode code point (U+0000..U+10ffff). + * @return 4 + * @stable ICU 2.4 + */ +#define U8_MAX_LENGTH 4 + +/** + * Get a code point from a string at a random-access offset, + * without changing the offset. + * The offset may point to either the lead byte or one of the trail bytes + * for a code point, in which case the macro will read all of the bytes + * for the code point. + * The result is undefined if the offset points to an illegal UTF-8 + * byte sequence. + * Iteration through a string is more efficient with U8_NEXT_UNSAFE or U8_NEXT. + * + * @param s const uint8_t * string + * @param i string offset + * @param c output UChar32 variable + * @see U8_GET + * @stable ICU 2.4 + */ +#define U8_GET_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t _u8_get_unsafe_index=(int32_t)(i); \ + U8_SET_CP_START_UNSAFE(s, _u8_get_unsafe_index); \ + U8_NEXT_UNSAFE(s, _u8_get_unsafe_index, c); \ +} UPRV_BLOCK_MACRO_END + +/** + * Get a code point from a string at a random-access offset, + * without changing the offset. + * The offset may point to either the lead byte or one of the trail bytes + * for a code point, in which case the macro will read all of the bytes + * for the code point. + * + * The length can be negative for a NUL-terminated string. + * + * If the offset points to an illegal UTF-8 byte sequence, then + * c is set to a negative value. + * Iteration through a string is more efficient with U8_NEXT_UNSAFE or U8_NEXT. + * + * @param s const uint8_t * string + * @param start int32_t starting string offset + * @param i int32_t string offset, must be start<=i<length + * @param length int32_t string length + * @param c output UChar32 variable, set to <0 in case of an error + * @see U8_GET_UNSAFE + * @stable ICU 2.4 + */ +#define U8_GET(s, start, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t _u8_get_index=(i); \ + U8_SET_CP_START(s, start, _u8_get_index); \ + U8_NEXT(s, _u8_get_index, length, c); \ +} UPRV_BLOCK_MACRO_END + +/** + * Get a code point from a string at a random-access offset, + * without changing the offset. + * The offset may point to either the lead byte or one of the trail bytes + * for a code point, in which case the macro will read all of the bytes + * for the code point. + * + * The length can be negative for a NUL-terminated string. + * + * If the offset points to an illegal UTF-8 byte sequence, then + * c is set to U+FFFD. + * Iteration through a string is more efficient with U8_NEXT_UNSAFE or U8_NEXT_OR_FFFD. + * + * This macro does not distinguish between a real U+FFFD in the text + * and U+FFFD returned for an ill-formed sequence. + * Use U8_GET() if that distinction is important. + * + * @param s const uint8_t * string + * @param start int32_t starting string offset + * @param i int32_t string offset, must be start<=i<length + * @param length int32_t string length + * @param c output UChar32 variable, set to U+FFFD in case of an error + * @see U8_GET + * @stable ICU 51 + */ +#define U8_GET_OR_FFFD(s, start, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t _u8_get_index=(i); \ + U8_SET_CP_START(s, start, _u8_get_index); \ + U8_NEXT_OR_FFFD(s, _u8_get_index, length, c); \ +} UPRV_BLOCK_MACRO_END + +/* definitions with forward iteration --------------------------------------- */ + +/** + * Get a code point from a string at a code point boundary offset, + * and advance the offset to the next code point boundary. + * (Post-incrementing forward iteration.) + * "Unsafe" macro, assumes well-formed UTF-8. + * + * The offset may point to the lead byte of a multi-byte sequence, + * in which case the macro will read the whole sequence. + * The result is undefined if the offset points to a trail byte + * or an illegal UTF-8 sequence. + * + * @param s const uint8_t * string + * @param i string offset + * @param c output UChar32 variable + * @see U8_NEXT + * @stable ICU 2.4 + */ +#define U8_NEXT_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(uint8_t)(s)[(i)++]; \ + if(!U8_IS_SINGLE(c)) { \ + if((c)<0xe0) { \ + (c)=(((c)&0x1f)<<6)|((s)[(i)++]&0x3f); \ + } else if((c)<0xf0) { \ + /* no need for (c&0xf) because the upper bits are truncated after <<12 in the cast to (UChar) */ \ + (c)=(UChar)(((c)<<12)|(((s)[i]&0x3f)<<6)|((s)[(i)+1]&0x3f)); \ + (i)+=2; \ + } else { \ + (c)=(((c)&7)<<18)|(((s)[i]&0x3f)<<12)|(((s)[(i)+1]&0x3f)<<6)|((s)[(i)+2]&0x3f); \ + (i)+=3; \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Get a code point from a string at a code point boundary offset, + * and advance the offset to the next code point boundary. + * (Post-incrementing forward iteration.) + * "Safe" macro, checks for illegal sequences and for string boundaries. + * + * The length can be negative for a NUL-terminated string. + * + * The offset may point to the lead byte of a multi-byte sequence, + * in which case the macro will read the whole sequence. + * If the offset points to a trail byte or an illegal UTF-8 sequence, then + * c is set to a negative value. + * + * @param s const uint8_t * string + * @param i int32_t string offset, must be i<length + * @param length int32_t string length + * @param c output UChar32 variable, set to <0 in case of an error + * @see U8_NEXT_UNSAFE + * @stable ICU 2.4 + */ +#define U8_NEXT(s, i, length, c) U8_INTERNAL_NEXT_OR_SUB(s, i, length, c, U_SENTINEL) + +/** + * Get a code point from a string at a code point boundary offset, + * and advance the offset to the next code point boundary. + * (Post-incrementing forward iteration.) + * "Safe" macro, checks for illegal sequences and for string boundaries. + * + * The length can be negative for a NUL-terminated string. + * + * The offset may point to the lead byte of a multi-byte sequence, + * in which case the macro will read the whole sequence. + * If the offset points to a trail byte or an illegal UTF-8 sequence, then + * c is set to U+FFFD. + * + * This macro does not distinguish between a real U+FFFD in the text + * and U+FFFD returned for an ill-formed sequence. + * Use U8_NEXT() if that distinction is important. + * + * @param s const uint8_t * string + * @param i int32_t string offset, must be i<length + * @param length int32_t string length + * @param c output UChar32 variable, set to U+FFFD in case of an error + * @see U8_NEXT + * @stable ICU 51 + */ +#define U8_NEXT_OR_FFFD(s, i, length, c) U8_INTERNAL_NEXT_OR_SUB(s, i, length, c, 0xfffd) + +/** @internal */ +#define U8_INTERNAL_NEXT_OR_SUB(s, i, length, c, sub) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(uint8_t)(s)[(i)++]; \ + if(!U8_IS_SINGLE(c)) { \ + uint8_t __t = 0; \ + if((i)!=(length) && \ + /* fetch/validate/assemble all but last trail byte */ \ + ((c)>=0xe0 ? \ + ((c)<0xf0 ? /* U+0800..U+FFFF except surrogates */ \ + U8_LEAD3_T1_BITS[(c)&=0xf]&(1<<((__t=(s)[i])>>5)) && \ + (__t&=0x3f, 1) \ + : /* U+10000..U+10FFFF */ \ + ((c)-=0xf0)<=4 && \ + U8_LEAD4_T1_BITS[(__t=(s)[i])>>4]&(1<<(c)) && \ + ((c)=((c)<<6)|(__t&0x3f), ++(i)!=(length)) && \ + (__t=(s)[i]-0x80)<=0x3f) && \ + /* valid second-to-last trail byte */ \ + ((c)=((c)<<6)|__t, ++(i)!=(length)) \ + : /* U+0080..U+07FF */ \ + (c)>=0xc2 && ((c)&=0x1f, 1)) && \ + /* last trail byte */ \ + (__t=(s)[i]-0x80)<=0x3f && \ + ((c)=((c)<<6)|__t, ++(i), 1)) { \ + } else { \ + (c)=(sub); /* ill-formed*/ \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Append a code point to a string, overwriting 1 to 4 bytes. + * The offset points to the current end of the string contents + * and is advanced (post-increment). + * "Unsafe" macro, assumes a valid code point and sufficient space in the string. + * Otherwise, the result is undefined. + * + * @param s const uint8_t * string buffer + * @param i string offset + * @param c code point to append + * @see U8_APPEND + * @stable ICU 2.4 + */ +#define U8_APPEND_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + uint32_t __uc=(c); \ + if(__uc<=0x7f) { \ + (s)[(i)++]=(uint8_t)__uc; \ + } else { \ + if(__uc<=0x7ff) { \ + (s)[(i)++]=(uint8_t)((__uc>>6)|0xc0); \ + } else { \ + if(__uc<=0xffff) { \ + (s)[(i)++]=(uint8_t)((__uc>>12)|0xe0); \ + } else { \ + (s)[(i)++]=(uint8_t)((__uc>>18)|0xf0); \ + (s)[(i)++]=(uint8_t)(((__uc>>12)&0x3f)|0x80); \ + } \ + (s)[(i)++]=(uint8_t)(((__uc>>6)&0x3f)|0x80); \ + } \ + (s)[(i)++]=(uint8_t)((__uc&0x3f)|0x80); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Append a code point to a string, overwriting 1 to 4 bytes. + * The offset points to the current end of the string contents + * and is advanced (post-increment). + * "Safe" macro, checks for a valid code point. + * If a non-ASCII code point is written, checks for sufficient space in the string. + * If the code point is not valid or trail bytes do not fit, + * then isError is set to TRUE. + * + * @param s const uint8_t * string buffer + * @param i int32_t string offset, must be i<capacity + * @param capacity int32_t size of the string buffer + * @param c UChar32 code point to append + * @param isError output UBool set to TRUE if an error occurs, otherwise not modified + * @see U8_APPEND_UNSAFE + * @stable ICU 2.4 + */ +#define U8_APPEND(s, i, capacity, c, isError) UPRV_BLOCK_MACRO_BEGIN { \ + uint32_t __uc=(c); \ + if(__uc<=0x7f) { \ + (s)[(i)++]=(uint8_t)__uc; \ + } else if(__uc<=0x7ff && (i)+1<(capacity)) { \ + (s)[(i)++]=(uint8_t)((__uc>>6)|0xc0); \ + (s)[(i)++]=(uint8_t)((__uc&0x3f)|0x80); \ + } else if((__uc<=0xd7ff || (0xe000<=__uc && __uc<=0xffff)) && (i)+2<(capacity)) { \ + (s)[(i)++]=(uint8_t)((__uc>>12)|0xe0); \ + (s)[(i)++]=(uint8_t)(((__uc>>6)&0x3f)|0x80); \ + (s)[(i)++]=(uint8_t)((__uc&0x3f)|0x80); \ + } else if(0xffff<__uc && __uc<=0x10ffff && (i)+3<(capacity)) { \ + (s)[(i)++]=(uint8_t)((__uc>>18)|0xf0); \ + (s)[(i)++]=(uint8_t)(((__uc>>12)&0x3f)|0x80); \ + (s)[(i)++]=(uint8_t)(((__uc>>6)&0x3f)|0x80); \ + (s)[(i)++]=(uint8_t)((__uc&0x3f)|0x80); \ + } else { \ + (isError)=TRUE; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Advance the string offset from one code point boundary to the next. + * (Post-incrementing iteration.) + * "Unsafe" macro, assumes well-formed UTF-8. + * + * @param s const uint8_t * string + * @param i string offset + * @see U8_FWD_1 + * @stable ICU 2.4 + */ +#define U8_FWD_1_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ + (i)+=1+U8_COUNT_TRAIL_BYTES_UNSAFE((s)[i]); \ +} UPRV_BLOCK_MACRO_END + +/** + * Advance the string offset from one code point boundary to the next. + * (Post-incrementing iteration.) + * "Safe" macro, checks for illegal sequences and for string boundaries. + * + * The length can be negative for a NUL-terminated string. + * + * @param s const uint8_t * string + * @param i int32_t string offset, must be i<length + * @param length int32_t string length + * @see U8_FWD_1_UNSAFE + * @stable ICU 2.4 + */ +#define U8_FWD_1(s, i, length) UPRV_BLOCK_MACRO_BEGIN { \ + uint8_t __b=(s)[(i)++]; \ + if(U8_IS_LEAD(__b) && (i)!=(length)) { \ + uint8_t __t1=(s)[i]; \ + if((0xe0<=__b && __b<0xf0)) { \ + if(U8_IS_VALID_LEAD3_AND_T1(__b, __t1) && \ + ++(i)!=(length) && U8_IS_TRAIL((s)[i])) { \ + ++(i); \ + } \ + } else if(__b<0xe0) { \ + if(U8_IS_TRAIL(__t1)) { \ + ++(i); \ + } \ + } else /* c>=0xf0 */ { \ + if(U8_IS_VALID_LEAD4_AND_T1(__b, __t1) && \ + ++(i)!=(length) && U8_IS_TRAIL((s)[i]) && \ + ++(i)!=(length) && U8_IS_TRAIL((s)[i])) { \ + ++(i); \ + } \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Advance the string offset from one code point boundary to the n-th next one, + * i.e., move forward by n code points. + * (Post-incrementing iteration.) + * "Unsafe" macro, assumes well-formed UTF-8. + * + * @param s const uint8_t * string + * @param i string offset + * @param n number of code points to skip + * @see U8_FWD_N + * @stable ICU 2.4 + */ +#define U8_FWD_N_UNSAFE(s, i, n) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t __N=(n); \ + while(__N>0) { \ + U8_FWD_1_UNSAFE(s, i); \ + --__N; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Advance the string offset from one code point boundary to the n-th next one, + * i.e., move forward by n code points. + * (Post-incrementing iteration.) + * "Safe" macro, checks for illegal sequences and for string boundaries. + * + * The length can be negative for a NUL-terminated string. + * + * @param s const uint8_t * string + * @param i int32_t string offset, must be i<length + * @param length int32_t string length + * @param n number of code points to skip + * @see U8_FWD_N_UNSAFE + * @stable ICU 2.4 + */ +#define U8_FWD_N(s, i, length, n) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t __N=(n); \ + while(__N>0 && ((i)<(length) || ((length)<0 && (s)[i]!=0))) { \ + U8_FWD_1(s, i, length); \ + --__N; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Adjust a random-access offset to a code point boundary + * at the start of a code point. + * If the offset points to a UTF-8 trail byte, + * then the offset is moved backward to the corresponding lead byte. + * Otherwise, it is not modified. + * "Unsafe" macro, assumes well-formed UTF-8. + * + * @param s const uint8_t * string + * @param i string offset + * @see U8_SET_CP_START + * @stable ICU 2.4 + */ +#define U8_SET_CP_START_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ + while(U8_IS_TRAIL((s)[i])) { --(i); } \ +} UPRV_BLOCK_MACRO_END + +/** + * Adjust a random-access offset to a code point boundary + * at the start of a code point. + * If the offset points to a UTF-8 trail byte, + * then the offset is moved backward to the corresponding lead byte. + * Otherwise, it is not modified. + * + * "Safe" macro, checks for illegal sequences and for string boundaries. + * Unlike U8_TRUNCATE_IF_INCOMPLETE(), this macro always reads s[i]. + * + * @param s const uint8_t * string + * @param start int32_t starting string offset (usually 0) + * @param i int32_t string offset, must be start<=i + * @see U8_SET_CP_START_UNSAFE + * @see U8_TRUNCATE_IF_INCOMPLETE + * @stable ICU 2.4 + */ +#define U8_SET_CP_START(s, start, i) UPRV_BLOCK_MACRO_BEGIN { \ + if(U8_IS_TRAIL((s)[(i)])) { \ + (i)=utf8_back1SafeBody(s, start, (i)); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * If the string ends with a UTF-8 byte sequence that is valid so far + * but incomplete, then reduce the length of the string to end before + * the lead byte of that incomplete sequence. + * For example, if the string ends with E1 80, the length is reduced by 2. + * + * In all other cases (the string ends with a complete sequence, or it is not + * possible for any further trail byte to extend the trailing sequence) + * the length remains unchanged. + * + * Useful for processing text split across multiple buffers + * (save the incomplete sequence for later) + * and for optimizing iteration + * (check for string length only once per character). + * + * "Safe" macro, checks for illegal sequences and for string boundaries. + * Unlike U8_SET_CP_START(), this macro never reads s[length]. + * + * (In UTF-16, simply check for U16_IS_LEAD(last code unit).) + * + * @param s const uint8_t * string + * @param start int32_t starting string offset (usually 0) + * @param length int32_t string length (usually start<=length) + * @see U8_SET_CP_START + * @stable ICU 61 + */ +#define U8_TRUNCATE_IF_INCOMPLETE(s, start, length) UPRV_BLOCK_MACRO_BEGIN { \ + if((length)>(start)) { \ + uint8_t __b1=s[(length)-1]; \ + if(U8_IS_SINGLE(__b1)) { \ + /* common ASCII character */ \ + } else if(U8_IS_LEAD(__b1)) { \ + --(length); \ + } else if(U8_IS_TRAIL(__b1) && ((length)-2)>=(start)) { \ + uint8_t __b2=s[(length)-2]; \ + if(0xe0<=__b2 && __b2<=0xf4) { \ + if(__b2<0xf0 ? U8_IS_VALID_LEAD3_AND_T1(__b2, __b1) : \ + U8_IS_VALID_LEAD4_AND_T1(__b2, __b1)) { \ + (length)-=2; \ + } \ + } else if(U8_IS_TRAIL(__b2) && ((length)-3)>=(start)) { \ + uint8_t __b3=s[(length)-3]; \ + if(0xf0<=__b3 && __b3<=0xf4 && U8_IS_VALID_LEAD4_AND_T1(__b3, __b2)) { \ + (length)-=3; \ + } \ + } \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/* definitions with backward iteration -------------------------------------- */ + +/** + * Move the string offset from one code point boundary to the previous one + * and get the code point between them. + * (Pre-decrementing backward iteration.) + * "Unsafe" macro, assumes well-formed UTF-8. + * + * The input offset may be the same as the string length. + * If the offset is behind a multi-byte sequence, then the macro will read + * the whole sequence. + * If the offset is behind a lead byte, then that itself + * will be returned as the code point. + * The result is undefined if the offset is behind an illegal UTF-8 sequence. + * + * @param s const uint8_t * string + * @param i string offset + * @param c output UChar32 variable + * @see U8_PREV + * @stable ICU 2.4 + */ +#define U8_PREV_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(uint8_t)(s)[--(i)]; \ + if(U8_IS_TRAIL(c)) { \ + uint8_t __b, __count=1, __shift=6; \ +\ + /* c is a trail byte */ \ + (c)&=0x3f; \ + for(;;) { \ + __b=(s)[--(i)]; \ + if(__b>=0xc0) { \ + U8_MASK_LEAD_BYTE(__b, __count); \ + (c)|=(UChar32)__b<<__shift; \ + break; \ + } else { \ + (c)|=(UChar32)(__b&0x3f)<<__shift; \ + ++__count; \ + __shift+=6; \ + } \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Move the string offset from one code point boundary to the previous one + * and get the code point between them. + * (Pre-decrementing backward iteration.) + * "Safe" macro, checks for illegal sequences and for string boundaries. + * + * The input offset may be the same as the string length. + * If the offset is behind a multi-byte sequence, then the macro will read + * the whole sequence. + * If the offset is behind a lead byte, then that itself + * will be returned as the code point. + * If the offset is behind an illegal UTF-8 sequence, then c is set to a negative value. + * + * @param s const uint8_t * string + * @param start int32_t starting string offset (usually 0) + * @param i int32_t string offset, must be start<i + * @param c output UChar32 variable, set to <0 in case of an error + * @see U8_PREV_UNSAFE + * @stable ICU 2.4 + */ +#define U8_PREV(s, start, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(uint8_t)(s)[--(i)]; \ + if(!U8_IS_SINGLE(c)) { \ + (c)=utf8_prevCharSafeBody((const uint8_t *)s, start, &(i), c, -1); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Move the string offset from one code point boundary to the previous one + * and get the code point between them. + * (Pre-decrementing backward iteration.) + * "Safe" macro, checks for illegal sequences and for string boundaries. + * + * The input offset may be the same as the string length. + * If the offset is behind a multi-byte sequence, then the macro will read + * the whole sequence. + * If the offset is behind a lead byte, then that itself + * will be returned as the code point. + * If the offset is behind an illegal UTF-8 sequence, then c is set to U+FFFD. + * + * This macro does not distinguish between a real U+FFFD in the text + * and U+FFFD returned for an ill-formed sequence. + * Use U8_PREV() if that distinction is important. + * + * @param s const uint8_t * string + * @param start int32_t starting string offset (usually 0) + * @param i int32_t string offset, must be start<i + * @param c output UChar32 variable, set to U+FFFD in case of an error + * @see U8_PREV + * @stable ICU 51 + */ +#define U8_PREV_OR_FFFD(s, start, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(uint8_t)(s)[--(i)]; \ + if(!U8_IS_SINGLE(c)) { \ + (c)=utf8_prevCharSafeBody((const uint8_t *)s, start, &(i), c, -3); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Move the string offset from one code point boundary to the previous one. + * (Pre-decrementing backward iteration.) + * The input offset may be the same as the string length. + * "Unsafe" macro, assumes well-formed UTF-8. + * + * @param s const uint8_t * string + * @param i string offset + * @see U8_BACK_1 + * @stable ICU 2.4 + */ +#define U8_BACK_1_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ + while(U8_IS_TRAIL((s)[--(i)])) {} \ +} UPRV_BLOCK_MACRO_END + +/** + * Move the string offset from one code point boundary to the previous one. + * (Pre-decrementing backward iteration.) + * The input offset may be the same as the string length. + * "Safe" macro, checks for illegal sequences and for string boundaries. + * + * @param s const uint8_t * string + * @param start int32_t starting string offset (usually 0) + * @param i int32_t string offset, must be start<i + * @see U8_BACK_1_UNSAFE + * @stable ICU 2.4 + */ +#define U8_BACK_1(s, start, i) UPRV_BLOCK_MACRO_BEGIN { \ + if(U8_IS_TRAIL((s)[--(i)])) { \ + (i)=utf8_back1SafeBody(s, start, (i)); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Move the string offset from one code point boundary to the n-th one before it, + * i.e., move backward by n code points. + * (Pre-decrementing backward iteration.) + * The input offset may be the same as the string length. + * "Unsafe" macro, assumes well-formed UTF-8. + * + * @param s const uint8_t * string + * @param i string offset + * @param n number of code points to skip + * @see U8_BACK_N + * @stable ICU 2.4 + */ +#define U8_BACK_N_UNSAFE(s, i, n) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t __N=(n); \ + while(__N>0) { \ + U8_BACK_1_UNSAFE(s, i); \ + --__N; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Move the string offset from one code point boundary to the n-th one before it, + * i.e., move backward by n code points. + * (Pre-decrementing backward iteration.) + * The input offset may be the same as the string length. + * "Safe" macro, checks for illegal sequences and for string boundaries. + * + * @param s const uint8_t * string + * @param start int32_t index of the start of the string + * @param i int32_t string offset, must be start<i + * @param n number of code points to skip + * @see U8_BACK_N_UNSAFE + * @stable ICU 2.4 + */ +#define U8_BACK_N(s, start, i, n) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t __N=(n); \ + while(__N>0 && (i)>(start)) { \ + U8_BACK_1(s, start, i); \ + --__N; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Adjust a random-access offset to a code point boundary after a code point. + * If the offset is behind a partial multi-byte sequence, + * then the offset is incremented to behind the whole sequence. + * Otherwise, it is not modified. + * The input offset may be the same as the string length. + * "Unsafe" macro, assumes well-formed UTF-8. + * + * @param s const uint8_t * string + * @param i string offset + * @see U8_SET_CP_LIMIT + * @stable ICU 2.4 + */ +#define U8_SET_CP_LIMIT_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ + U8_BACK_1_UNSAFE(s, i); \ + U8_FWD_1_UNSAFE(s, i); \ +} UPRV_BLOCK_MACRO_END + +/** + * Adjust a random-access offset to a code point boundary after a code point. + * If the offset is behind a partial multi-byte sequence, + * then the offset is incremented to behind the whole sequence. + * Otherwise, it is not modified. + * The input offset may be the same as the string length. + * "Safe" macro, checks for illegal sequences and for string boundaries. + * + * The length can be negative for a NUL-terminated string. + * + * @param s const uint8_t * string + * @param start int32_t starting string offset (usually 0) + * @param i int32_t string offset, must be start<=i<=length + * @param length int32_t string length + * @see U8_SET_CP_LIMIT_UNSAFE + * @stable ICU 2.4 + */ +#define U8_SET_CP_LIMIT(s, start, i, length) UPRV_BLOCK_MACRO_BEGIN { \ + if((start)<(i) && ((i)<(length) || (length)<0)) { \ + U8_BACK_1(s, start, i); \ + U8_FWD_1(s, i, length); \ + } \ +} UPRV_BLOCK_MACRO_END + +#endif |