| 1 | /* $Id: pathhost-posix.cpp 98103 2023-01-17 14:15:46Z vboxsync $ */
|
|---|
| 2 | /** @file
|
|---|
| 3 | * IPRT - Path Conversions, POSIX.
|
|---|
| 4 | */
|
|---|
| 5 |
|
|---|
| 6 | /*
|
|---|
| 7 | * Copyright (C) 2006-2023 Oracle and/or its affiliates.
|
|---|
| 8 | *
|
|---|
| 9 | * This file is part of VirtualBox base platform packages, as
|
|---|
| 10 | * available from https://www.virtualbox.org.
|
|---|
| 11 | *
|
|---|
| 12 | * This program is free software; you can redistribute it and/or
|
|---|
| 13 | * modify it under the terms of the GNU General Public License
|
|---|
| 14 | * as published by the Free Software Foundation, in version 3 of the
|
|---|
| 15 | * License.
|
|---|
| 16 | *
|
|---|
| 17 | * This program is distributed in the hope that it will be useful, but
|
|---|
| 18 | * WITHOUT ANY WARRANTY; without even the implied warranty of
|
|---|
| 19 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|---|
| 20 | * General Public License for more details.
|
|---|
| 21 | *
|
|---|
| 22 | * You should have received a copy of the GNU General Public License
|
|---|
| 23 | * along with this program; if not, see <https://www.gnu.org/licenses>.
|
|---|
| 24 | *
|
|---|
| 25 | * The contents of this file may alternatively be used under the terms
|
|---|
| 26 | * of the Common Development and Distribution License Version 1.0
|
|---|
| 27 | * (CDDL), a copy of it is provided in the "COPYING.CDDL" file included
|
|---|
| 28 | * in the VirtualBox distribution, in which case the provisions of the
|
|---|
| 29 | * CDDL are applicable instead of those of the GPL.
|
|---|
| 30 | *
|
|---|
| 31 | * You may elect to license modified versions of this file under the
|
|---|
| 32 | * terms and conditions of either the GPL or the CDDL or both.
|
|---|
| 33 | *
|
|---|
| 34 | * SPDX-License-Identifier: GPL-3.0-only OR CDDL-1.0
|
|---|
| 35 | */
|
|---|
| 36 |
|
|---|
| 37 |
|
|---|
| 38 | /*********************************************************************************************************************************
|
|---|
| 39 | * Header Files *
|
|---|
| 40 | *********************************************************************************************************************************/
|
|---|
| 41 | #define LOG_GROUP RTLOGGROUP_PATH
|
|---|
| 42 | #include "internal/iprt.h"
|
|---|
| 43 | #include "internal/path.h"
|
|---|
| 44 | #include "internal/string.h"
|
|---|
| 45 | #include "internal/thread.h"
|
|---|
| 46 |
|
|---|
| 47 | #include <iprt/env.h>
|
|---|
| 48 | #include <iprt/err.h>
|
|---|
| 49 | #include <iprt/string.h>
|
|---|
| 50 | #include <iprt/once.h>
|
|---|
| 51 |
|
|---|
| 52 |
|
|---|
| 53 | /*********************************************************************************************************************************
|
|---|
| 54 | * Global Variables *
|
|---|
| 55 | *********************************************************************************************************************************/
|
|---|
| 56 | /** Initialize once object. */
|
|---|
| 57 | static RTONCE g_OnceInitPathConv = RTONCE_INITIALIZER;
|
|---|
| 58 | /** If set, then we can pass UTF-8 thru directly. */
|
|---|
| 59 | static bool g_fPassthruUtf8 = false;
|
|---|
| 60 | /** The UTF-8 to FS iconv cache entry. */
|
|---|
| 61 | static RTSTRICONV g_enmUtf8ToFsIdx = RTSTRICONV_UTF8_TO_LOCALE;
|
|---|
| 62 | /** The FS to UTF-8 iconv cache entry. */
|
|---|
| 63 | static RTSTRICONV g_enmFsToUtf8Idx = RTSTRICONV_LOCALE_TO_UTF8;
|
|---|
| 64 | /** The codeset we're using. */
|
|---|
| 65 | static char g_szFsCodeset[32];
|
|---|
| 66 |
|
|---|
| 67 |
|
|---|
| 68 | /**
|
|---|
| 69 | * Do a case insensitive compare where the 2nd string is known and can be case
|
|---|
| 70 | * folded when writing the code.
|
|---|
| 71 | *
|
|---|
| 72 | * @returns see strcmp.
|
|---|
| 73 | * @param pszStr1 The string to compare against pszLower and
|
|---|
| 74 | * pszUpper.
|
|---|
| 75 | * @param pszUpper The upper case edition of the 2nd string.
|
|---|
| 76 | * @param pszLower The lower case edition of the 2nd string.
|
|---|
| 77 | */
|
|---|
| 78 | static int rtPathStrICmp(const char *pszStr1, const char *pszUpper, const char *pszLower)
|
|---|
| 79 | {
|
|---|
| 80 | Assert(strlen(pszLower) == strlen(pszUpper));
|
|---|
| 81 | for (;;)
|
|---|
| 82 | {
|
|---|
| 83 | char ch1 = *pszStr1++;
|
|---|
| 84 | char ch2Upper = *pszUpper++;
|
|---|
| 85 | char ch2Lower = *pszLower++;
|
|---|
| 86 | if ( ch1 != ch2Upper
|
|---|
| 87 | && ch1 != ch2Lower)
|
|---|
| 88 | return ch1 < ch2Upper ? -1 : 1;
|
|---|
| 89 | if (!ch1)
|
|---|
| 90 | return 0;
|
|---|
| 91 | }
|
|---|
| 92 | }
|
|---|
| 93 |
|
|---|
| 94 | /**
|
|---|
| 95 | * Is the specified codeset something we can treat as UTF-8.
|
|---|
| 96 | *
|
|---|
| 97 | * @returns true if we can do UTF-8 passthru, false if not.
|
|---|
| 98 | * @param pszCodeset The codeset in question.
|
|---|
| 99 | */
|
|---|
| 100 | static bool rtPathConvInitIsUtf8(const char *pszCodeset)
|
|---|
| 101 | {
|
|---|
| 102 | /* Paranoia. */
|
|---|
| 103 | if (!pszCodeset)
|
|---|
| 104 | return false;
|
|---|
| 105 |
|
|---|
| 106 | /*
|
|---|
| 107 | * Avoid RTStrICmp at this point.
|
|---|
| 108 | */
|
|---|
| 109 | static struct
|
|---|
| 110 | {
|
|---|
| 111 | const char *pszUpper;
|
|---|
| 112 | const char *pszLower;
|
|---|
| 113 | } const s_aUtf8Compatible[] =
|
|---|
| 114 | {
|
|---|
| 115 | /* The default locale. */
|
|---|
| 116 | { "C" , "c" },
|
|---|
| 117 | { "POSIX" , "posix" },
|
|---|
| 118 | /* 7-bit ASCII. */
|
|---|
| 119 | { "ANSI_X3.4-1968" , "ansi_x3.4-1968" },
|
|---|
| 120 | { "ANSI_X3.4-1986" , "ansi_x3.4-1986" },
|
|---|
| 121 | { "US-ASCII" , "us-ascii" },
|
|---|
| 122 | { "ISO646-US" , "iso646-us" },
|
|---|
| 123 | { "ISO_646.IRV:1991" , "iso_646.irv:1991" },
|
|---|
| 124 | { "ISO-IR-6" , "iso-ir-6" },
|
|---|
| 125 | { "IBM367" , "ibm367" },
|
|---|
| 126 | /* UTF-8 */
|
|---|
| 127 | { "UTF-8" , "utf-8" },
|
|---|
| 128 | { "UTF8" , "utf8" },
|
|---|
| 129 | { "ISO-10646/UTF-8" , "iso-10646/utf-8" },
|
|---|
| 130 | { "ISO-10646/UTF8" , "iso-10646/utf8" }
|
|---|
| 131 | };
|
|---|
| 132 |
|
|---|
| 133 | for (size_t i = 0; i < RT_ELEMENTS(s_aUtf8Compatible); i++)
|
|---|
| 134 | if (!rtPathStrICmp(pszCodeset, s_aUtf8Compatible[i].pszUpper, s_aUtf8Compatible[i].pszLower))
|
|---|
| 135 | return true;
|
|---|
| 136 |
|
|---|
| 137 | return false;
|
|---|
| 138 | }
|
|---|
| 139 |
|
|---|
| 140 |
|
|---|
| 141 | /**
|
|---|
| 142 | * Init once for the path conversion code.
|
|---|
| 143 | *
|
|---|
| 144 | * @returns IPRT status code.
|
|---|
| 145 | * @param pvUser1 Unused.
|
|---|
| 146 | * @param pvUser2 Unused.
|
|---|
| 147 | */
|
|---|
| 148 | static DECLCALLBACK(int32_t) rtPathConvInitOnce(void *pvUser)
|
|---|
| 149 | {
|
|---|
| 150 | /*
|
|---|
| 151 | * Read the environment variable, no mercy on misconfigs here except that
|
|---|
| 152 | * empty values are quietly ignored. (We use a temp buffer for stripping.)
|
|---|
| 153 | */
|
|---|
| 154 | char *pszEnvValue = NULL;
|
|---|
| 155 | char szEnvValue[sizeof(g_szFsCodeset)];
|
|---|
| 156 | int rc = RTEnvGetEx(RTENV_DEFAULT, RTPATH_CODESET_ENV_VAR, szEnvValue, sizeof(szEnvValue), NULL);
|
|---|
| 157 | if (rc != VERR_ENV_VAR_NOT_FOUND && RT_FAILURE(rc))
|
|---|
| 158 | return rc;
|
|---|
| 159 | if (RT_SUCCESS(rc))
|
|---|
| 160 | pszEnvValue = RTStrStrip(szEnvValue);
|
|---|
| 161 |
|
|---|
| 162 | if (pszEnvValue && *pszEnvValue)
|
|---|
| 163 | {
|
|---|
| 164 | g_fPassthruUtf8 = rtPathConvInitIsUtf8(pszEnvValue);
|
|---|
| 165 | g_enmFsToUtf8Idx = RTSTRICONV_FS_TO_UTF8;
|
|---|
| 166 | g_enmUtf8ToFsIdx = RTSTRICONV_UTF8_TO_FS;
|
|---|
| 167 | strcpy(g_szFsCodeset, pszEnvValue);
|
|---|
| 168 | }
|
|---|
| 169 | else
|
|---|
| 170 | {
|
|---|
| 171 | const char *pszCodeset = rtStrGetLocaleCodeset();
|
|---|
| 172 | size_t cchCodeset = pszCodeset ? strlen(pszCodeset) : sizeof(g_szFsCodeset);
|
|---|
| 173 | if (cchCodeset >= sizeof(g_szFsCodeset))
|
|---|
| 174 | /* This shouldn't happen, but we'll manage. */
|
|---|
| 175 | g_szFsCodeset[0] = '\0';
|
|---|
| 176 | else
|
|---|
| 177 | {
|
|---|
| 178 | memcpy(g_szFsCodeset, pszCodeset, cchCodeset + 1);
|
|---|
| 179 | pszCodeset = g_szFsCodeset;
|
|---|
| 180 | }
|
|---|
| 181 | g_fPassthruUtf8 = rtPathConvInitIsUtf8(pszCodeset);
|
|---|
| 182 | g_enmFsToUtf8Idx = RTSTRICONV_LOCALE_TO_UTF8;
|
|---|
| 183 | g_enmUtf8ToFsIdx = RTSTRICONV_UTF8_TO_LOCALE;
|
|---|
| 184 | }
|
|---|
| 185 |
|
|---|
| 186 | NOREF(pvUser);
|
|---|
| 187 | return VINF_SUCCESS;
|
|---|
| 188 | }
|
|---|
| 189 |
|
|---|
| 190 |
|
|---|
| 191 | int rtPathToNative(char const **ppszNativePath, const char *pszPath, const char *pszBasePath)
|
|---|
| 192 | {
|
|---|
| 193 | *ppszNativePath = NULL;
|
|---|
| 194 |
|
|---|
| 195 | int rc = RTOnce(&g_OnceInitPathConv, rtPathConvInitOnce, NULL);
|
|---|
| 196 | if (RT_SUCCESS(rc))
|
|---|
| 197 | {
|
|---|
| 198 | if (g_fPassthruUtf8 || !*pszPath)
|
|---|
| 199 | *ppszNativePath = pszPath;
|
|---|
| 200 | else
|
|---|
| 201 | rc = rtStrConvert(pszPath, strlen(pszPath), "UTF-8",
|
|---|
| 202 | (char **)ppszNativePath, 0, g_szFsCodeset,
|
|---|
| 203 | 2, g_enmUtf8ToFsIdx);
|
|---|
| 204 | }
|
|---|
| 205 | NOREF(pszBasePath); /* We don't query the FS for codeset preferences. */
|
|---|
| 206 | return rc;
|
|---|
| 207 | }
|
|---|
| 208 |
|
|---|
| 209 |
|
|---|
| 210 | void rtPathFreeNative(char const *pszNativePath, const char *pszPath)
|
|---|
| 211 | {
|
|---|
| 212 | if ( pszNativePath != pszPath
|
|---|
| 213 | && pszNativePath)
|
|---|
| 214 | RTStrFree((char *)pszNativePath);
|
|---|
| 215 | }
|
|---|
| 216 |
|
|---|
| 217 |
|
|---|
| 218 | int rtPathFromNative(const char **ppszPath, const char *pszNativePath, const char *pszBasePath)
|
|---|
| 219 | {
|
|---|
| 220 | *ppszPath = NULL;
|
|---|
| 221 |
|
|---|
| 222 | int rc = RTOnce(&g_OnceInitPathConv, rtPathConvInitOnce, NULL);
|
|---|
| 223 | if (RT_SUCCESS(rc))
|
|---|
| 224 | {
|
|---|
| 225 | if (g_fPassthruUtf8 || !*pszNativePath)
|
|---|
| 226 | {
|
|---|
| 227 | size_t cCpsIgnored;
|
|---|
| 228 | size_t cchNativePath;
|
|---|
| 229 | rc = rtUtf8Length(pszNativePath, RTSTR_MAX, &cCpsIgnored, &cchNativePath);
|
|---|
| 230 | if (RT_SUCCESS(rc))
|
|---|
| 231 | {
|
|---|
| 232 | char *pszPath;
|
|---|
| 233 | *ppszPath = pszPath = RTStrAlloc(cchNativePath + 1);
|
|---|
| 234 | if (pszPath)
|
|---|
| 235 | memcpy(pszPath, pszNativePath, cchNativePath + 1);
|
|---|
| 236 | else
|
|---|
| 237 | rc = VERR_NO_STR_MEMORY;
|
|---|
| 238 | }
|
|---|
| 239 | }
|
|---|
| 240 | else
|
|---|
| 241 | rc = rtStrConvert(pszNativePath, strlen(pszNativePath), g_szFsCodeset,
|
|---|
| 242 | (char **)ppszPath, 0, "UTF-8",
|
|---|
| 243 | 2, g_enmFsToUtf8Idx);
|
|---|
| 244 | }
|
|---|
| 245 | NOREF(pszBasePath); /* We don't query the FS for codeset preferences. */
|
|---|
| 246 | return rc;
|
|---|
| 247 | }
|
|---|
| 248 |
|
|---|
| 249 |
|
|---|
| 250 | void rtPathFreeIprt(const char *pszPath, const char *pszNativePath)
|
|---|
| 251 | {
|
|---|
| 252 | if ( pszPath != pszNativePath
|
|---|
| 253 | && pszPath)
|
|---|
| 254 | RTStrFree((char *)pszPath);
|
|---|
| 255 | }
|
|---|
| 256 |
|
|---|
| 257 |
|
|---|
| 258 | int rtPathFromNativeCopy(char *pszPath, size_t cbPath, const char *pszNativePath, const char *pszBasePath)
|
|---|
| 259 | {
|
|---|
| 260 | int rc = RTOnce(&g_OnceInitPathConv, rtPathConvInitOnce, NULL);
|
|---|
| 261 | if (RT_SUCCESS(rc))
|
|---|
| 262 | {
|
|---|
| 263 | if (g_fPassthruUtf8 || !*pszNativePath)
|
|---|
| 264 | rc = RTStrCopy(pszPath, cbPath, pszNativePath);
|
|---|
| 265 | else if (cbPath)
|
|---|
| 266 | rc = rtStrConvert(pszNativePath, strlen(pszNativePath), g_szFsCodeset,
|
|---|
| 267 | &pszPath, cbPath, "UTF-8",
|
|---|
| 268 | 2, g_enmFsToUtf8Idx);
|
|---|
| 269 | else
|
|---|
| 270 | rc = VERR_BUFFER_OVERFLOW;
|
|---|
| 271 | }
|
|---|
| 272 |
|
|---|
| 273 | NOREF(pszBasePath); /* We don't query the FS for codeset preferences. */
|
|---|
| 274 | return rc;
|
|---|
| 275 | }
|
|---|
| 276 |
|
|---|
| 277 |
|
|---|
| 278 | int rtPathFromNativeDup(char **ppszPath, const char *pszNativePath, const char *pszBasePath)
|
|---|
| 279 | {
|
|---|
| 280 | int rc = RTOnce(&g_OnceInitPathConv, rtPathConvInitOnce, NULL);
|
|---|
| 281 | if (RT_SUCCESS(rc))
|
|---|
| 282 | {
|
|---|
| 283 | if (g_fPassthruUtf8 || !*pszNativePath)
|
|---|
| 284 | rc = RTStrDupEx(ppszPath, pszNativePath);
|
|---|
| 285 | else
|
|---|
| 286 | rc = rtStrConvert(pszNativePath, strlen(pszNativePath), g_szFsCodeset,
|
|---|
| 287 | ppszPath, 0, "UTF-8",
|
|---|
| 288 | 2, g_enmFsToUtf8Idx);
|
|---|
| 289 | }
|
|---|
| 290 |
|
|---|
| 291 | NOREF(pszBasePath); /* We don't query the FS for codeset preferences. */
|
|---|
| 292 | return rc;
|
|---|
| 293 | }
|
|---|
| 294 |
|
|---|
