From 9c174b447598f6e63e589a59c26e3ecd22b1c2fb Mon Sep 17 00:00:00 2001 From: Narendra Date: Tue, 8 Sep 2026 22:45:41 +0530 Subject: [PATCH] GH-51007: [C++] Make uriparser an external dependency --- LICENSE.txt | 42 - ci/conda_env_cpp.txt | 1 + ci/docker/alpine-linux-3.22-cpp.dockerfile | 1 + ci/docker/debian-13-cpp.dockerfile | 1 + ci/docker/debian-experimental-cpp.dockerfile | 1 + ci/docker/fedora-42-cpp.dockerfile | 1 + ci/docker/ubuntu-22.04-cpp.dockerfile | 1 + ci/docker/ubuntu-24.04-cpp.dockerfile | 1 + ci/scripts/PKGBUILD | 1 + ci/scripts/cpp_build.sh | 1 + ci/scripts/msys2_setup.sh | 1 + ci/scripts/r_windows_build.sh | 6 +- ci/vcpkg/vcpkg.json | 1 + cpp/Brewfile | 1 + cpp/cmake_modules/FinduriparserAlt.cmake | 90 + cpp/cmake_modules/ThirdpartyToolchain.cmake | 70 + cpp/src/arrow/CMakeLists.txt | 28 +- cpp/src/arrow/meson.build | 44 +- cpp/src/arrow/util/uri.cc | 2 +- cpp/src/arrow/vendored/uriparser/README.md | 25 - cpp/src/arrow/vendored/uriparser/Uri.h | 1090 -------- cpp/src/arrow/vendored/uriparser/UriBase.h | 377 --- cpp/src/arrow/vendored/uriparser/UriCommon.c | 572 ---- cpp/src/arrow/vendored/uriparser/UriCommon.h | 109 - cpp/src/arrow/vendored/uriparser/UriCompare.c | 168 -- .../arrow/vendored/uriparser/UriDefsAnsi.h | 82 - .../arrow/vendored/uriparser/UriDefsConfig.h | 102 - .../arrow/vendored/uriparser/UriDefsUnicode.h | 82 - cpp/src/arrow/vendored/uriparser/UriEscape.c | 453 ---- cpp/src/arrow/vendored/uriparser/UriFile.c | 242 -- cpp/src/arrow/vendored/uriparser/UriIp4.c | 329 --- cpp/src/arrow/vendored/uriparser/UriIp4.h | 110 - cpp/src/arrow/vendored/uriparser/UriIp4Base.c | 96 - cpp/src/arrow/vendored/uriparser/UriIp4Base.h | 59 - cpp/src/arrow/vendored/uriparser/UriMemory.c | 468 ---- cpp/src/arrow/vendored/uriparser/UriMemory.h | 78 - .../arrow/vendored/uriparser/UriNormalize.c | 771 ------ .../vendored/uriparser/UriNormalizeBase.c | 119 - .../vendored/uriparser/UriNormalizeBase.h | 53 - cpp/src/arrow/vendored/uriparser/UriParse.c | 2410 ----------------- .../arrow/vendored/uriparser/UriParseBase.c | 90 - .../arrow/vendored/uriparser/UriParseBase.h | 55 - cpp/src/arrow/vendored/uriparser/UriQuery.c | 501 ---- .../arrow/vendored/uriparser/UriRecompose.c | 577 ---- cpp/src/arrow/vendored/uriparser/UriResolve.c | 329 --- cpp/src/arrow/vendored/uriparser/UriShorten.c | 324 --- cpp/src/arrow/vendored/uriparser/config.h | 47 - cpp/subprojects/uriparser.wrap | 23 + cpp/thirdparty/versions.txt | 3 + cpp/vcpkg.json | 1 + docs/source/developers/cpp/building.rst | 1 + 51 files changed, 238 insertions(+), 9802 deletions(-) create mode 100644 cpp/cmake_modules/FinduriparserAlt.cmake delete mode 100644 cpp/src/arrow/vendored/uriparser/README.md delete mode 100644 cpp/src/arrow/vendored/uriparser/Uri.h delete mode 100644 cpp/src/arrow/vendored/uriparser/UriBase.h delete mode 100644 cpp/src/arrow/vendored/uriparser/UriCommon.c delete mode 100644 cpp/src/arrow/vendored/uriparser/UriCommon.h delete mode 100644 cpp/src/arrow/vendored/uriparser/UriCompare.c delete mode 100644 cpp/src/arrow/vendored/uriparser/UriDefsAnsi.h delete mode 100644 cpp/src/arrow/vendored/uriparser/UriDefsConfig.h delete mode 100644 cpp/src/arrow/vendored/uriparser/UriDefsUnicode.h delete mode 100644 cpp/src/arrow/vendored/uriparser/UriEscape.c delete mode 100644 cpp/src/arrow/vendored/uriparser/UriFile.c delete mode 100644 cpp/src/arrow/vendored/uriparser/UriIp4.c delete mode 100644 cpp/src/arrow/vendored/uriparser/UriIp4.h delete mode 100644 cpp/src/arrow/vendored/uriparser/UriIp4Base.c delete mode 100644 cpp/src/arrow/vendored/uriparser/UriIp4Base.h delete mode 100644 cpp/src/arrow/vendored/uriparser/UriMemory.c delete mode 100644 cpp/src/arrow/vendored/uriparser/UriMemory.h delete mode 100644 cpp/src/arrow/vendored/uriparser/UriNormalize.c delete mode 100644 cpp/src/arrow/vendored/uriparser/UriNormalizeBase.c delete mode 100644 cpp/src/arrow/vendored/uriparser/UriNormalizeBase.h delete mode 100644 cpp/src/arrow/vendored/uriparser/UriParse.c delete mode 100644 cpp/src/arrow/vendored/uriparser/UriParseBase.c delete mode 100644 cpp/src/arrow/vendored/uriparser/UriParseBase.h delete mode 100644 cpp/src/arrow/vendored/uriparser/UriQuery.c delete mode 100644 cpp/src/arrow/vendored/uriparser/UriRecompose.c delete mode 100644 cpp/src/arrow/vendored/uriparser/UriResolve.c delete mode 100644 cpp/src/arrow/vendored/uriparser/UriShorten.c delete mode 100644 cpp/src/arrow/vendored/uriparser/config.h create mode 100644 cpp/subprojects/uriparser.wrap diff --git a/LICENSE.txt b/LICENSE.txt index 5382ddfa5d1e..c6616a5b4501 100644 --- a/LICENSE.txt +++ b/LICENSE.txt @@ -624,48 +624,6 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. -------------------------------------------------------------------------------- -The files in cpp/src/arrow/vendored/uriparser/ have the following license -(BSD 3-Clause License) - -uriparser - RFC 3986 URI parsing library - -Copyright (C) 2007, Weijia Song -Copyright (C) 2007, Sebastian Pipping -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 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 files under dev/tasks/conda-recipes have the following license BSD 3-clause license diff --git a/ci/conda_env_cpp.txt b/ci/conda_env_cpp.txt index 3986f7736e0f..24911fb35ac2 100644 --- a/ci/conda_env_cpp.txt +++ b/ci/conda_env_cpp.txt @@ -48,6 +48,7 @@ re2 simdjson snappy thrift-cpp>=0.11.0 +uriparser xsimd>=14.2 zlib zstd diff --git a/ci/docker/alpine-linux-3.22-cpp.dockerfile b/ci/docker/alpine-linux-3.22-cpp.dockerfile index 766e02e24cbf..ae4f8eb0f54a 100644 --- a/ci/docker/alpine-linux-3.22-cpp.dockerfile +++ b/ci/docker/alpine-linux-3.22-cpp.dockerfile @@ -65,6 +65,7 @@ RUN apk add \ sqlite-dev \ thrift-dev \ tzdata \ + uriparser-dev \ utf8proc-dev \ zlib-dev \ zstd-dev && \ diff --git a/ci/docker/debian-13-cpp.dockerfile b/ci/docker/debian-13-cpp.dockerfile index ebda8f3847dc..2e4b040fbe05 100644 --- a/ci/docker/debian-13-cpp.dockerfile +++ b/ci/docker/debian-13-cpp.dockerfile @@ -70,6 +70,7 @@ RUN apt-get update -y -q && \ libsqlite3-dev \ libssl-dev \ libthrift-dev \ + liburiparser-dev \ libutf8proc-dev \ libxml2-dev \ libzstd-dev \ diff --git a/ci/docker/debian-experimental-cpp.dockerfile b/ci/docker/debian-experimental-cpp.dockerfile index 359ac700806b..e21e77325370 100644 --- a/ci/docker/debian-experimental-cpp.dockerfile +++ b/ci/docker/debian-experimental-cpp.dockerfile @@ -73,6 +73,7 @@ RUN if [ -n "${gcc}" ]; then \ libssh2-1-dev \ libssl-dev \ libthrift-dev \ + liburiparser-dev \ libutf8proc-dev \ libxml2-dev \ libzstd-dev \ diff --git a/ci/docker/fedora-42-cpp.dockerfile b/ci/docker/fedora-42-cpp.dockerfile index f3bdda00a1b4..09621cfc83f2 100644 --- a/ci/docker/fedora-42-cpp.dockerfile +++ b/ci/docker/fedora-42-cpp.dockerfile @@ -63,6 +63,7 @@ RUN dnf update -y && \ simdjson-devel \ snappy-devel \ thrift-devel \ + uriparser-devel \ utf8proc-devel \ wget \ which \ diff --git a/ci/docker/ubuntu-22.04-cpp.dockerfile b/ci/docker/ubuntu-22.04-cpp.dockerfile index 54b671c7a57e..a6f4191327f3 100644 --- a/ci/docker/ubuntu-22.04-cpp.dockerfile +++ b/ci/docker/ubuntu-22.04-cpp.dockerfile @@ -101,6 +101,7 @@ RUN apt-get update -y -q && \ libssh2-1-dev \ libssl-dev \ libthrift-dev \ + liburiparser-dev \ libutf8proc-dev \ libxml2-dev \ libzstd-dev \ diff --git a/ci/docker/ubuntu-24.04-cpp.dockerfile b/ci/docker/ubuntu-24.04-cpp.dockerfile index 00cc8796c546..dd9e2bf8d656 100644 --- a/ci/docker/ubuntu-24.04-cpp.dockerfile +++ b/ci/docker/ubuntu-24.04-cpp.dockerfile @@ -102,6 +102,7 @@ RUN apt-get update -y -q && \ libssh2-1-dev \ libssl-dev \ libthrift-dev \ + liburiparser-dev \ libutf8proc-dev \ libxml2-dev \ libzstd-dev \ diff --git a/ci/scripts/PKGBUILD b/ci/scripts/PKGBUILD index e726372dae23..cb3a493bef91 100644 --- a/ci/scripts/PKGBUILD +++ b/ci/scripts/PKGBUILD @@ -27,6 +27,7 @@ license=("Apache-2.0") depends=("${MINGW_PACKAGE_PREFIX}-bzip2" "${MINGW_PACKAGE_PREFIX}-curl" # for google-cloud-cpp bundled build "${MINGW_PACKAGE_PREFIX}-libutf8proc" + "${MINGW_PACKAGE_PREFIX}-uriparser" "${MINGW_PACKAGE_PREFIX}-re2" "${MINGW_PACKAGE_PREFIX}-snappy" "${MINGW_PACKAGE_PREFIX}-zlib" diff --git a/ci/scripts/cpp_build.sh b/ci/scripts/cpp_build.sh index 32ccf654bf82..66fac106a498 100755 --- a/ci/scripts/cpp_build.sh +++ b/ci/scripts/cpp_build.sh @@ -294,6 +294,7 @@ else -Dsimdjson_SOURCE="${simdjson_SOURCE:-}" \ -DSnappy_SOURCE="${Snappy_SOURCE:-}" \ -DThrift_SOURCE="${Thrift_SOURCE:-}" \ + -Duriparser_SOURCE="${uriparser_SOURCE:-}" \ -Dutf8proc_SOURCE="${utf8proc_SOURCE:-}" \ -Dzstd_SOURCE="${zstd_SOURCE:-}" \ -Dxsimd_SOURCE="${xsimd_SOURCE:-}" \ diff --git a/ci/scripts/msys2_setup.sh b/ci/scripts/msys2_setup.sh index d2b06e749001..72d59eec21bc 100755 --- a/ci/scripts/msys2_setup.sh +++ b/ci/scripts/msys2_setup.sh @@ -36,6 +36,7 @@ case "${target}" in packages+=("${MINGW_PACKAGE_PREFIX}-gflags") packages+=("${MINGW_PACKAGE_PREFIX}-grpc") packages+=("${MINGW_PACKAGE_PREFIX}-gtest") + packages+=("${MINGW_PACKAGE_PREFIX}-uriparser") packages+=("${MINGW_PACKAGE_PREFIX}-libutf8proc") packages+=("${MINGW_PACKAGE_PREFIX}-libxml2") packages+=("${MINGW_PACKAGE_PREFIX}-llvm") diff --git a/ci/scripts/r_windows_build.sh b/ci/scripts/r_windows_build.sh index 7eb8c0c2b55e..29c1094291d0 100755 --- a/ci/scripts/r_windows_build.sh +++ b/ci/scripts/r_windows_build.sh @@ -65,7 +65,7 @@ if [ -d mingw64/lib/ ]; then # Move the 64-bit versions of libarrow into the expected location mv mingw64/lib/*.a "${DST_DIR}/lib/x64" # These are from https://dl.bintray.com/rtools/mingw{32,64}/ - cp "${MSYS_LIB_DIR}"/mingw64/lib/lib{snappy,zstd,lz4,brotli*,bz2,crypto,curl,ss*,utf8proc,re2,nghttp2}.a "${DST_DIR}/lib/x64" + cp "${MSYS_LIB_DIR}"/mingw64/lib/lib{snappy,zstd,lz4,brotli*,bz2,crypto,curl,ss*,uriparser,utf8proc,re2,nghttp2}.a "${DST_DIR}/lib/x64" fi # Same for the 32-bit versions @@ -73,7 +73,7 @@ if [ -d mingw32/lib/ ]; then ls "${MSYS_LIB_DIR}/mingw32/lib/" mkdir -p "${DST_DIR}/lib/i386" mv mingw32/lib/*.a "${DST_DIR}/lib/i386" - cp "${MSYS_LIB_DIR}"/mingw32/lib/lib{snappy,zstd,lz4,brotli*,bz2,crypto,curl,ss*,utf8proc,re2,nghttp2}.a "${DST_DIR}/lib/i386" + cp "${MSYS_LIB_DIR}"/mingw32/lib/lib{snappy,zstd,lz4,brotli*,bz2,crypto,curl,ss*,uriparser,utf8proc,re2,nghttp2}.a "${DST_DIR}/lib/i386" fi # Do the same also for ucrt64 @@ -81,7 +81,7 @@ if [ -d ucrt64/lib/ ]; then ls "${MSYS_LIB_DIR}/ucrt64/lib/" mkdir -p "${DST_DIR}/lib/x64-ucrt" mv ucrt64/lib/*.a "${DST_DIR}/lib/x64-ucrt" - cp "${MSYS_LIB_DIR}"/ucrt64/lib/lib{snappy,zstd,lz4,brotli*,bz2,crypto,curl,ss*,utf8proc,re2,nghttp2}.a "$DST_DIR"/lib/x64-ucrt + cp "${MSYS_LIB_DIR}"/ucrt64/lib/lib{snappy,zstd,lz4,brotli*,bz2,crypto,curl,ss*,uriparser,utf8proc,re2,nghttp2}.a "$DST_DIR"/lib/x64-ucrt fi # Create build artifact diff --git a/ci/vcpkg/vcpkg.json b/ci/vcpkg/vcpkg.json index 2418e3b64d86..d069dbe99b7d 100644 --- a/ci/vcpkg/vcpkg.json +++ b/ci/vcpkg/vcpkg.json @@ -18,6 +18,7 @@ "openssl", "re2", "snappy", + "uriparser", "utf8proc", "xsimd", "zlib", diff --git a/cpp/Brewfile b/cpp/Brewfile index 811712516bf7..744dcba2d895 100644 --- a/cpp/Brewfile +++ b/cpp/Brewfile @@ -42,6 +42,7 @@ brew "rapidjson" brew "re2" brew "snappy" brew "thrift" +brew "uriparser" brew "utf8proc" brew "wget" brew "xsimd" diff --git a/cpp/cmake_modules/FinduriparserAlt.cmake b/cpp/cmake_modules/FinduriparserAlt.cmake new file mode 100644 index 000000000000..0116dfc0f9d4 --- /dev/null +++ b/cpp/cmake_modules/FinduriparserAlt.cmake @@ -0,0 +1,90 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. + +# Find uriparser. +# +# Debian, Ubuntu and several other distributions ship a liburiparser-dev that +# provides only a pkg-config file, while upstream (and vcpkg, conda-forge) +# also install a CMake package configuration. Try the CMake config first, then +# fall back to pkg-config and finally to a plain library search. + +if(uriparserAlt_FOUND) + return() +endif() + +set(find_package_args) +if(uriparserAlt_FIND_VERSION) + list(APPEND find_package_args ${uriparserAlt_FIND_VERSION}) +endif() +if(uriparserAlt_FIND_QUIETLY) + list(APPEND find_package_args QUIET) +endif() +find_package(uriparser ${find_package_args} CONFIG) +if(uriparser_FOUND) + set(uriparserAlt_FOUND TRUE) + return() +endif() + +if(URIPARSER_ROOT) + find_library(URIPARSER_LIB + NAMES uriparser + PATHS ${URIPARSER_ROOT} + PATH_SUFFIXES ${ARROW_LIBRARY_PATH_SUFFIXES} + NO_DEFAULT_PATH) + find_path(URIPARSER_INCLUDE_DIR + NAMES uriparser/Uri.h + PATHS ${URIPARSER_ROOT} + NO_DEFAULT_PATH + PATH_SUFFIXES ${ARROW_INCLUDE_PATH_SUFFIXES}) +else() + find_package(PkgConfig QUIET) + pkg_check_modules(URIPARSER_PC liburiparser) + if(URIPARSER_PC_FOUND) + set(URIPARSER_INCLUDE_DIR "${URIPARSER_PC_INCLUDEDIR}") + list(APPEND URIPARSER_PC_LIBRARY_DIRS "${URIPARSER_PC_LIBDIR}") + find_library(URIPARSER_LIB + NAMES uriparser + PATHS ${URIPARSER_PC_LIBRARY_DIRS} + NO_DEFAULT_PATH + PATH_SUFFIXES ${ARROW_LIBRARY_PATH_SUFFIXES}) + set(URIPARSER_VERSION "${URIPARSER_PC_VERSION}") + else() + find_library(URIPARSER_LIB + NAMES uriparser + PATH_SUFFIXES ${ARROW_LIBRARY_PATH_SUFFIXES}) + find_path(URIPARSER_INCLUDE_DIR + NAMES uriparser/Uri.h + PATH_SUFFIXES ${ARROW_INCLUDE_PATH_SUFFIXES}) + endif() +endif() + +find_package_handle_standard_args(uriparserAlt + REQUIRED_VARS + URIPARSER_LIB + URIPARSER_INCLUDE_DIR + VERSION_VAR + URIPARSER_VERSION) + +if(uriparserAlt_FOUND) + if(NOT TARGET uriparser::uriparser) + add_library(uriparser::uriparser UNKNOWN IMPORTED) + set_target_properties(uriparser::uriparser + PROPERTIES IMPORTED_LOCATION "${URIPARSER_LIB}" + INTERFACE_INCLUDE_DIRECTORIES + "${URIPARSER_INCLUDE_DIR}") + endif() +endif() diff --git a/cpp/cmake_modules/ThirdpartyToolchain.cmake b/cpp/cmake_modules/ThirdpartyToolchain.cmake index acb59a747f29..a729349f2941 100644 --- a/cpp/cmake_modules/ThirdpartyToolchain.cmake +++ b/cpp/cmake_modules/ThirdpartyToolchain.cmake @@ -68,6 +68,7 @@ set(ARROW_THIRDPARTY_DEPENDENCIES Snappy Substrait Thrift + uriparser utf8proc xsimd ZLIB @@ -220,6 +221,8 @@ macro(build_dependency DEPENDENCY_NAME) build_substrait() elseif("${DEPENDENCY_NAME}" STREQUAL "Thrift") build_thrift() + elseif("${DEPENDENCY_NAME}" STREQUAL "uriparser") + build_uriparser() elseif("${DEPENDENCY_NAME}" STREQUAL "utf8proc") build_utf8proc() elseif("${DEPENDENCY_NAME}" STREQUAL "xsimd") @@ -810,6 +813,14 @@ else() ) endif() +if(DEFINED ENV{ARROW_URIPARSER_URL}) + set(ARROW_URIPARSER_SOURCE_URL "$ENV{ARROW_URIPARSER_URL}") +else() + set_urls(ARROW_URIPARSER_SOURCE_URL + "https://github.com/uriparser/uriparser/releases/download/uriparser-${ARROW_URIPARSER_BUILD_VERSION}/uriparser-${ARROW_URIPARSER_BUILD_VERSION}.tar.bz2" + ) +endif() + if(DEFINED ENV{ARROW_UTF8PROC_URL}) set(ARROW_UTF8PROC_SOURCE_URL "$ENV{ARROW_UTF8PROC_URL}") else() @@ -3250,6 +3261,65 @@ if(ARROW_WITH_BZ2) endif() endif() +# ---------------------------------------------------------------------- +# uriparser library + +macro(build_uriparser) + message(STATUS "Building uriparser from source") + set(URIPARSER_PREFIX "${CMAKE_CURRENT_BINARY_DIR}/uriparser_ep-install") + if(MSVC) + set(URIPARSER_STATIC_LIB "${URIPARSER_PREFIX}/lib/uriparser.lib") + else() + set(URIPARSER_STATIC_LIB + "${URIPARSER_PREFIX}/lib/${CMAKE_STATIC_LIBRARY_PREFIX}uriparser${CMAKE_STATIC_LIBRARY_SUFFIX}" + ) + endif() + + set(URIPARSER_CMAKE_ARGS + ${EP_COMMON_CMAKE_ARGS} + -DBUILD_SHARED_LIBS=OFF + -DCMAKE_INSTALL_LIBDIR=lib + "-DCMAKE_INSTALL_PREFIX=${URIPARSER_PREFIX}" + -DURIPARSER_BUILD_DOCS=OFF + -DURIPARSER_BUILD_TESTS=OFF + -DURIPARSER_BUILD_TOOLS=OFF + # Arrow only uses the char (not wchar_t) flavor of the API. + -DURIPARSER_BUILD_WCHAR_T=OFF) + + if(MSVC AND ARROW_USE_STATIC_CRT) + list(APPEND URIPARSER_CMAKE_ARGS -DURIPARSER_MSVC_STATIC_CRT=ON) + endif() + + externalproject_add(uriparser_ep + ${EP_COMMON_OPTIONS} + CMAKE_ARGS ${URIPARSER_CMAKE_ARGS} + INSTALL_DIR ${URIPARSER_PREFIX} + URL ${ARROW_URIPARSER_SOURCE_URL} + URL_HASH "SHA256=${ARROW_URIPARSER_BUILD_SHA256_CHECKSUM}" + BUILD_BYPRODUCTS "${URIPARSER_STATIC_LIB}") + + file(MAKE_DIRECTORY "${URIPARSER_PREFIX}/include") + add_library(uriparser::uriparser STATIC IMPORTED) + set_target_properties(uriparser::uriparser + PROPERTIES IMPORTED_LOCATION "${URIPARSER_STATIC_LIB}" + INTERFACE_COMPILE_DEFINITIONS "URI_STATIC_BUILD") + target_include_directories(uriparser::uriparser BEFORE + INTERFACE "${URIPARSER_PREFIX}/include") + + add_dependencies(uriparser::uriparser uriparser_ep) + + list(PREPEND ARROW_BUNDLED_STATIC_LIBS uriparser::uriparser) +endmacro() + +# uriparser is mandatory: arrow::util::Uri is part of core Arrow. +resolve_dependency(uriparser + HAVE_ALT + TRUE + REQUIRED_VERSION + "1.0.2" + PC_PACKAGE_NAMES + liburiparser) + macro(build_utf8proc) message(STATUS "Building utf8proc from source") set(UTF8PROC_PREFIX "${CMAKE_CURRENT_BINARY_DIR}/utf8proc_ep-install") diff --git a/cpp/src/arrow/CMakeLists.txt b/cpp/src/arrow/CMakeLists.txt index d7086773a1fd..f82480530da2 100644 --- a/cpp/src/arrow/CMakeLists.txt +++ b/cpp/src/arrow/CMakeLists.txt @@ -120,6 +120,10 @@ if(ARROW_WITH_OPENTELEMETRY) list(APPEND ARROW_STATIC_INSTALL_INTERFACE_LIBS CURL::libcurl) endif() +if(uriparser_SOURCE STREQUAL "SYSTEM") + list(APPEND ARROW_STATIC_INSTALL_INTERFACE_LIBS uriparser::uriparser) +endif() + if(ARROW_WITH_UTF8PROC) if(utf8proc_SOURCE STREQUAL "SYSTEM") list(APPEND ARROW_STATIC_INSTALL_INTERFACE_LIBS utf8proc::utf8proc) @@ -533,32 +537,13 @@ set(ARROW_VENDORED_SRCS vendored/double-conversion/fixed-dtoa.cc vendored/double-conversion/string-to-double.cc vendored/double-conversion/strtod.cc - vendored/musl/strptime.c - vendored/uriparser/UriCommon.c - vendored/uriparser/UriCompare.c - vendored/uriparser/UriEscape.c - vendored/uriparser/UriFile.c - vendored/uriparser/UriIp4.c - vendored/uriparser/UriIp4Base.c - vendored/uriparser/UriMemory.c - vendored/uriparser/UriNormalize.c - vendored/uriparser/UriNormalizeBase.c - vendored/uriparser/UriParse.c - vendored/uriparser/UriParseBase.c - vendored/uriparser/UriQuery.c - vendored/uriparser/UriRecompose.c - vendored/uriparser/UriResolve.c - vendored/uriparser/UriShorten.c) + vendored/musl/strptime.c) if(APPLE) list(APPEND ARROW_VENDORED_SRCS vendored/datetime/ios.mm) endif() set_source_files_properties(vendored/datetime.cpp PROPERTIES SKIP_UNITY_BUILD_INCLUSION ON) arrow_add_object_library(ARROW_VENDORED ${ARROW_VENDORED_SRCS}) -# Disable DLL exports in vendored uriparser library -foreach(ARROW_VENDORED_TARGET ${ARROW_VENDORED_TARGETS}) - target_compile_definitions(${ARROW_VENDORED_TARGET} PRIVATE URI_STATIC_BUILD) -endforeach() set(ARROW_UTIL_SRCS util/align_util.cc @@ -659,9 +644,8 @@ endif() arrow_add_object_library(ARROW_UTIL ${ARROW_UTIL_SRCS}) -# Disable DLL exports in vendored uriparser library foreach(ARROW_UTIL_TARGET ${ARROW_UTIL_TARGETS}) - target_compile_definitions(${ARROW_UTIL_TARGET} PRIVATE URI_STATIC_BUILD) + target_link_libraries(${ARROW_UTIL_TARGET} PRIVATE uriparser::uriparser) endforeach() foreach(ARROW_UTIL_TARGET ${ARROW_UTIL_TARGETS}) target_link_libraries(${ARROW_UTIL_TARGET} PRIVATE ${ARROW_XSIMD}) diff --git a/cpp/src/arrow/meson.build b/cpp/src/arrow/meson.build index f181321aaab7..08345b443314 100644 --- a/cpp/src/arrow/meson.build +++ b/cpp/src/arrow/meson.build @@ -126,21 +126,6 @@ arrow_components = { 'vendored/double-conversion/string-to-double.cc', 'vendored/double-conversion/strtod.cc', 'vendored/musl/strptime.c', - 'vendored/uriparser/UriCommon.c', - 'vendored/uriparser/UriCompare.c', - 'vendored/uriparser/UriEscape.c', - 'vendored/uriparser/UriFile.c', - 'vendored/uriparser/UriIp4.c', - 'vendored/uriparser/UriIp4Base.c', - 'vendored/uriparser/UriMemory.c', - 'vendored/uriparser/UriNormalize.c', - 'vendored/uriparser/UriNormalizeBase.c', - 'vendored/uriparser/UriParse.c', - 'vendored/uriparser/UriParseBase.c', - 'vendored/uriparser/UriQuery.c', - 'vendored/uriparser/UriRecompose.c', - 'vendored/uriparser/UriResolve.c', - 'vendored/uriparser/UriShorten.c', ], }, 'arrow_base': { @@ -238,7 +223,34 @@ arrow_util_srcs = [ 'util/value_parsing.cc', ] -arrow_util_deps = [threads_dep] +uriparser_dep = dependency( + 'liburiparser', + version: '>=1.0.2', + allow_fallback: false, + required: false, +) + +if not uriparser_dep.found() + cmake = import('cmake') + uriparser_opts = cmake.subproject_options() + + uriparser_opts.add_cmake_defines( + { + 'BUILD_SHARED_LIBS': 'OFF', + # Required to link the static subproject into libarrow.so. + 'CMAKE_POSITION_INDEPENDENT_CODE': 'ON', + 'URIPARSER_BUILD_DOCS': 'OFF', + 'URIPARSER_BUILD_TESTS': 'OFF', + 'URIPARSER_BUILD_TOOLS': 'OFF', + 'URIPARSER_BUILD_WCHAR_T': 'OFF', + }, + ) + + uriparser_proj = cmake.subproject('uriparser', options: uriparser_opts) + uriparser_dep = uriparser_proj.dependency('uriparser') +endif + +arrow_util_deps = [threads_dep, uriparser_dep] if needs_simdjson arrow_util_srcs += ['util/simdjson_internal.cc'] diff --git a/cpp/src/arrow/util/uri.cc b/cpp/src/arrow/util/uri.cc index 25af8a74c385..ba1c151b3f69 100644 --- a/cpp/src/arrow/util/uri.cc +++ b/cpp/src/arrow/util/uri.cc @@ -25,7 +25,7 @@ #include "arrow/util/logging.h" #include "arrow/util/value_parsing.h" -#include "arrow/vendored/uriparser/Uri.h" +#include namespace arrow::util { diff --git a/cpp/src/arrow/vendored/uriparser/README.md b/cpp/src/arrow/vendored/uriparser/README.md deleted file mode 100644 index b3a219c7f34e..000000000000 --- a/cpp/src/arrow/vendored/uriparser/README.md +++ /dev/null @@ -1,25 +0,0 @@ - - -The files in this directory are vendored from uriparser git tag "uriparser-0.9.3". - -Include paths fixed using: -``` -sed -E -i 's:include :include "\1.h":g' src/arrow/vendored/uriparser/* -``` diff --git a/cpp/src/arrow/vendored/uriparser/Uri.h b/cpp/src/arrow/vendored/uriparser/Uri.h deleted file mode 100644 index 9315a12c3fe9..000000000000 --- a/cpp/src/arrow/vendored/uriparser/Uri.h +++ /dev/null @@ -1,1090 +0,0 @@ -/* 8cd64b75589a7efa22989ae85f71e620a99e3c44776338f7d3114eacf73d27a3 (0.9.3+) - * - * uriparser - RFC 3986 URI parsing library - * - * Copyright (C) 2007, Weijia Song - * Copyright (C) 2007, Sebastian Pipping - * 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 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. - */ - -/** - * @file Uri.h - * Holds the RFC 3986 %URI parser interface. - * NOTE: This header includes itself twice. - */ - -#if (defined(URI_PASS_ANSI) && !defined(URI_H_ANSI)) \ - || (defined(URI_PASS_UNICODE) && !defined(URI_H_UNICODE)) \ - || (!defined(URI_PASS_ANSI) && !defined(URI_PASS_UNICODE)) -/* What encodings are enabled? */ -#include "UriDefsConfig.h" -#if (!defined(URI_PASS_ANSI) && !defined(URI_PASS_UNICODE)) -/* Include SELF twice */ -# ifdef URI_ENABLE_ANSI -# define URI_PASS_ANSI 1 -# include "Uri.h" -# undef URI_PASS_ANSI -# endif -# ifdef URI_ENABLE_UNICODE -# define URI_PASS_UNICODE 1 -# include "Uri.h" -# undef URI_PASS_UNICODE -# endif -/* Only one pass for each encoding */ -#elif (defined(URI_PASS_ANSI) && !defined(URI_H_ANSI) \ - && defined(URI_ENABLE_ANSI)) || (defined(URI_PASS_UNICODE) \ - && !defined(URI_H_UNICODE) && defined(URI_ENABLE_UNICODE)) -# ifdef URI_PASS_ANSI -# define URI_H_ANSI 1 -# include "UriDefsAnsi.h" -# else -# define URI_H_UNICODE 1 -# include "UriDefsUnicode.h" -# endif - - - -#ifdef __cplusplus -extern "C" { -#endif - - - -#ifndef URI_DOXYGEN -# include "UriBase.h" -#endif - - - -/** - * Specifies a range of characters within a string. - * The range includes all characters from first - * to one before afterLast. So if both are - * non-NULL the difference is the length of the text range. - * - * @see UriUriA - * @see UriPathSegmentA - * @see UriHostDataA - * @since 0.3.0 - */ -typedef struct URI_TYPE(TextRangeStruct) { - const URI_CHAR * first; /**< Pointer to first character */ - const URI_CHAR * afterLast; /**< Pointer to character after the last one still in */ -} URI_TYPE(TextRange); /**< @copydoc UriTextRangeStructA */ - - - -/** - * Represents a path segment within a %URI path. - * More precisely it is a node in a linked - * list of path segments. - * - * @see UriUriA - * @since 0.3.0 - */ -typedef struct URI_TYPE(PathSegmentStruct) { - URI_TYPE(TextRange) text; /**< Path segment name */ - struct URI_TYPE(PathSegmentStruct) * next; /**< Pointer to the next path segment in the list, can be NULL if last already */ - - void * reserved; /**< Reserved to the parser */ -} URI_TYPE(PathSegment); /**< @copydoc UriPathSegmentStructA */ - - - -/** - * Holds structured host information. - * This is either a IPv4, IPv6, plain - * text for IPvFuture or all zero for - * a registered name. - * - * @see UriUriA - * @since 0.3.0 - */ -typedef struct URI_TYPE(HostDataStruct) { - UriIp4 * ip4; /**< IPv4 address */ - UriIp6 * ip6; /**< IPv6 address */ - URI_TYPE(TextRange) ipFuture; /**< IPvFuture address */ -} URI_TYPE(HostData); /**< @copydoc UriHostDataStructA */ - - - -/** - * Represents an RFC 3986 %URI. - * Missing components can be {NULL, NULL} ranges. - * - * @see uriFreeUriMembersA - * @see uriFreeUriMembersMmA - * @see UriParserStateA - * @since 0.3.0 - */ -typedef struct URI_TYPE(UriStruct) { - URI_TYPE(TextRange) scheme; /**< Scheme (e.g. "http") */ - URI_TYPE(TextRange) userInfo; /**< User info (e.g. "user:pass") */ - URI_TYPE(TextRange) hostText; /**< Host text (set for all hosts, excluding square brackets) */ - URI_TYPE(HostData) hostData; /**< Structured host type specific data */ - URI_TYPE(TextRange) portText; /**< Port (e.g. "80") */ - URI_TYPE(PathSegment) * pathHead; /**< Head of a linked list of path segments */ - URI_TYPE(PathSegment) * pathTail; /**< Tail of the list behind pathHead */ - URI_TYPE(TextRange) query; /**< Query without leading "?" */ - URI_TYPE(TextRange) fragment; /**< Query without leading "#" */ - UriBool absolutePath; /**< Absolute path flag, distincting "a" and "/a"; - always URI_FALSE for URIs with host */ - UriBool owner; /**< Memory owner flag */ - - void * reserved; /**< Reserved to the parser */ -} URI_TYPE(Uri); /**< @copydoc UriUriStructA */ - - - -/** - * Represents a state of the %URI parser. - * Missing components can be NULL to reflect - * a components absence. - * - * @see uriFreeUriMembersA - * @see uriFreeUriMembersMmA - * @since 0.3.0 - */ -typedef struct URI_TYPE(ParserStateStruct) { - URI_TYPE(Uri) * uri; /**< Plug in the %URI structure to be filled while parsing here */ - int errorCode; /**< Code identifying the error which occurred */ - const URI_CHAR * errorPos; /**< Pointer to position in case of a syntax error */ - - void * reserved; /**< Reserved to the parser */ -} URI_TYPE(ParserState); /**< @copydoc UriParserStateStructA */ - - - -/** - * Represents a query element. - * More precisely it is a node in a linked - * list of query elements. - * - * @since 0.7.0 - */ -typedef struct URI_TYPE(QueryListStruct) { - const URI_CHAR * key; /**< Key of the query element */ - const URI_CHAR * value; /**< Value of the query element, can be NULL */ - - struct URI_TYPE(QueryListStruct) * next; /**< Pointer to the next key/value pair in the list, can be NULL if last already */ -} URI_TYPE(QueryList); /**< @copydoc UriQueryListStructA */ - - - -/** - * Parses a RFC 3986 %URI. - * Uses default libc-based memory manager. - * - * @param state INOUT: Parser state with set output %URI, must not be NULL - * @param first IN: Pointer to the first character to parse, must not be NULL - * @param afterLast IN: Pointer to the character after the last to parse, must not be NULL - * @return 0 on success, error code otherwise - * - * @see uriParseUriA - * @see uriParseSingleUriA - * @see uriParseSingleUriExA - * @see uriToStringA - * @since 0.3.0 - * @deprecated Deprecated since 0.9.0, please migrate to uriParseSingleUriExA (with "Single"). - */ -URI_PUBLIC int URI_FUNC(ParseUriEx)(URI_TYPE(ParserState) * state, - const URI_CHAR * first, const URI_CHAR * afterLast); - - - -/** - * Parses a RFC 3986 %URI. - * Uses default libc-based memory manager. - * - * @param state INOUT: Parser state with set output %URI, must not be NULL - * @param text IN: Text to parse, must not be NULL - * @return 0 on success, error code otherwise - * - * @see uriParseUriExA - * @see uriParseSingleUriA - * @see uriParseSingleUriExA - * @see uriToStringA - * @since 0.3.0 - * @deprecated Deprecated since 0.9.0, please migrate to uriParseSingleUriA (with "Single"). - */ -URI_PUBLIC int URI_FUNC(ParseUri)(URI_TYPE(ParserState) * state, - const URI_CHAR * text); - - - -/** - * Parses a single RFC 3986 %URI. - * Uses default libc-based memory manager. - * - * @param uri OUT: Output %URI, must not be NULL - * @param text IN: Pointer to the first character to parse, - * must not be NULL - * @param errorPos OUT: Pointer to a pointer to the first character - * causing a syntax error, can be NULL; - * only set when URI_ERROR_SYNTAX was returned - * @return 0 on success, error code otherwise - * - * @see uriParseSingleUriExA - * @see uriParseSingleUriExMmA - * @see uriToStringA - * @since 0.9.0 - */ -URI_PUBLIC int URI_FUNC(ParseSingleUri)(URI_TYPE(Uri) * uri, - const URI_CHAR * text, const URI_CHAR ** errorPos); - - - -/** - * Parses a single RFC 3986 %URI. - * Uses default libc-based memory manager. - * - * @param uri OUT: Output %URI, must not be NULL - * @param first IN: Pointer to the first character to parse, - * must not be NULL - * @param afterLast IN: Pointer to the character after the last to - * parse, can be NULL - * (to use first + strlen(first)) - * @param errorPos OUT: Pointer to a pointer to the first character - * causing a syntax error, can be NULL; - * only set when URI_ERROR_SYNTAX was returned - * @return 0 on success, error code otherwise - * - * @see uriParseSingleUriA - * @see uriParseSingleUriExMmA - * @see uriToStringA - * @since 0.9.0 - */ -URI_PUBLIC int URI_FUNC(ParseSingleUriEx)(URI_TYPE(Uri) * uri, - const URI_CHAR * first, const URI_CHAR * afterLast, - const URI_CHAR ** errorPos); - - - -/** - * Parses a single RFC 3986 %URI. - * - * @param uri OUT: Output %URI, must not be NULL - * @param first IN: Pointer to the first character to parse, - * must not be NULL - * @param afterLast IN: Pointer to the character after the last to - * parse, can be NULL - * (to use first + strlen(first)) - * @param errorPos OUT: Pointer to a pointer to the first character - * causing a syntax error, can be NULL; - * only set when URI_ERROR_SYNTAX was returned - * @param memory IN: Memory manager to use, NULL for default libc - * @return 0 on success, error code otherwise - * - * @see uriParseSingleUriA - * @see uriParseSingleUriExA - * @see uriToStringA - * @since 0.9.0 - */ -URI_PUBLIC int URI_FUNC(ParseSingleUriExMm)(URI_TYPE(Uri) * uri, - const URI_CHAR * first, const URI_CHAR * afterLast, - const URI_CHAR ** errorPos, UriMemoryManager * memory); - - - -/** - * Frees all memory associated with the members - * of the %URI structure. Note that the structure - * itself is not freed, only its members. - * Uses default libc-based memory manager. - * - * @param uri INOUT: %URI structure whose members should be freed - * - * @see uriFreeUriMembersMmA - * @since 0.3.0 - */ -URI_PUBLIC void URI_FUNC(FreeUriMembers)(URI_TYPE(Uri) * uri); - - - -/** - * Frees all memory associated with the members - * of the %URI structure. Note that the structure - * itself is not freed, only its members. - * - * @param uri INOUT: %URI structure whose members should be freed - * @param memory IN: Memory manager to use, NULL for default libc - * @return 0 on success, error code otherwise - * - * @see uriFreeUriMembersA - * @since 0.9.0 - */ -URI_PUBLIC int URI_FUNC(FreeUriMembersMm)(URI_TYPE(Uri) * uri, - UriMemoryManager * memory); - - - -/** - * Percent-encodes all unreserved characters from the input string and - * writes the encoded version to the output string. - * Be sure to allocate 3 times the space of the input buffer for - * the output buffer for normalizeBreaks == URI_FALSE and 6 times - * the space for normalizeBreaks == URI_TRUE - * (since e.g. "\x0d" becomes "%0D%0A" in that case) - * - * @param inFirst IN: Pointer to first character of the input text - * @param inAfterLast IN: Pointer after the last character of the input text - * @param out OUT: Encoded text destination - * @param spaceToPlus IN: Whether to convert ' ' to '+' or not - * @param normalizeBreaks IN: Whether to convert CR and LF to CR-LF or not. - * @return Position of terminator in output string - * - * @see uriEscapeA - * @see uriUnescapeInPlaceExA - * @since 0.5.2 - */ -URI_PUBLIC URI_CHAR * URI_FUNC(EscapeEx)(const URI_CHAR * inFirst, - const URI_CHAR * inAfterLast, URI_CHAR * out, - UriBool spaceToPlus, UriBool normalizeBreaks); - - - -/** - * Percent-encodes all unreserved characters from the input string and - * writes the encoded version to the output string. - * Be sure to allocate 3 times the space of the input buffer for - * the output buffer for normalizeBreaks == URI_FALSE and 6 times - * the space for normalizeBreaks == URI_TRUE - * (since e.g. "\x0d" becomes "%0D%0A" in that case) - * - * @param in IN: Text source - * @param out OUT: Encoded text destination - * @param spaceToPlus IN: Whether to convert ' ' to '+' or not - * @param normalizeBreaks IN: Whether to convert CR and LF to CR-LF or not. - * @return Position of terminator in output string - * - * @see uriEscapeExA - * @see uriUnescapeInPlaceA - * @since 0.5.0 - */ -URI_PUBLIC URI_CHAR * URI_FUNC(Escape)(const URI_CHAR * in, URI_CHAR * out, - UriBool spaceToPlus, UriBool normalizeBreaks); - - - -/** - * Unescapes percent-encoded groups in a given string. - * E.g. "%20" will become " ". Unescaping is done in place. - * The return value will be point to the new position - * of the terminating zero. Use this value to get the new - * length of the string. NULL is only returned if inout - * is NULL. - * - * @param inout INOUT: Text to unescape/decode - * @param plusToSpace IN: Whether to convert '+' to ' ' or not - * @param breakConversion IN: Line break conversion mode - * @return Pointer to new position of the terminating zero - * - * @see uriUnescapeInPlaceA - * @see uriEscapeExA - * @since 0.5.0 - */ -URI_PUBLIC const URI_CHAR * URI_FUNC(UnescapeInPlaceEx)(URI_CHAR * inout, - UriBool plusToSpace, UriBreakConversion breakConversion); - - - -/** - * Unescapes percent-encoded groups in a given string. - * E.g. "%20" will become " ". Unescaping is done in place. - * The return value will be point to the new position - * of the terminating zero. Use this value to get the new - * length of the string. NULL is only returned if inout - * is NULL. - * - * NOTE: '+' is not decoded to ' ' and line breaks are not converted. - * Use the more advanced UnescapeInPlaceEx for that features instead. - * - * @param inout INOUT: Text to unescape/decode - * @return Pointer to new position of the terminating zero - * - * @see uriUnescapeInPlaceExA - * @see uriEscapeA - * @since 0.3.0 - */ -URI_PUBLIC const URI_CHAR * URI_FUNC(UnescapeInPlace)(URI_CHAR * inout); - - - -/** - * Performs reference resolution as described in - * section 5.2.2 of RFC 3986. - * Uses default libc-based memory manager. - * NOTE: On success you have to call uriFreeUriMembersA on \p absoluteDest manually later. - * - * @param absoluteDest OUT: Result %URI - * @param relativeSource IN: Reference to resolve - * @param absoluteBase IN: Base %URI to apply - * @return Error code or 0 on success - * - * @see uriRemoveBaseUriA - * @see uriRemoveBaseUriMmA - * @see uriAddBaseUriExA - * @see uriAddBaseUriExMmA - * @since 0.4.0 - */ -URI_PUBLIC int URI_FUNC(AddBaseUri)(URI_TYPE(Uri) * absoluteDest, - const URI_TYPE(Uri) * relativeSource, - const URI_TYPE(Uri) * absoluteBase); - - - -/** - * Performs reference resolution as described in - * section 5.2.2 of RFC 3986. - * Uses default libc-based memory manager. - * NOTE: On success you have to call uriFreeUriMembersA on \p absoluteDest manually later. - * - * @param absoluteDest OUT: Result %URI - * @param relativeSource IN: Reference to resolve - * @param absoluteBase IN: Base %URI to apply - * @param options IN: Configuration to apply - * @return Error code or 0 on success - * - * @see uriRemoveBaseUriA - * @see uriAddBaseUriA - * @see uriAddBaseUriExMmA - * @since 0.8.1 - */ -URI_PUBLIC int URI_FUNC(AddBaseUriEx)(URI_TYPE(Uri) * absoluteDest, - const URI_TYPE(Uri) * relativeSource, - const URI_TYPE(Uri) * absoluteBase, - UriResolutionOptions options); - - - -/** - * Performs reference resolution as described in - * section 5.2.2 of RFC 3986. - * NOTE: On success you have to call uriFreeUriMembersMmA on \p absoluteDest manually later. - * - * @param absoluteDest OUT: Result %URI - * @param relativeSource IN: Reference to resolve - * @param absoluteBase IN: Base %URI to apply - * @param options IN: Configuration to apply - * @param memory IN: Memory manager to use, NULL for default libc - * @return Error code or 0 on success - * - * @see uriRemoveBaseUriA - * @see uriRemoveBaseUriMmA - * @see uriAddBaseUriA - * @see uriAddBaseUriExA - * @since 0.9.0 - */ -URI_PUBLIC int URI_FUNC(AddBaseUriExMm)(URI_TYPE(Uri) * absoluteDest, - const URI_TYPE(Uri) * relativeSource, - const URI_TYPE(Uri) * absoluteBase, - UriResolutionOptions options, UriMemoryManager * memory); - - - -/** - * Tries to make a relative %URI (a reference) from an - * absolute %URI and a given base %URI. The resulting %URI is going to be - * relative if the absolute %URI and base %UI share both scheme and authority. - * If that is not the case, the result will still be - * an absolute URI (with scheme part if necessary). - * Uses default libc-based memory manager. - * NOTE: On success you have to call uriFreeUriMembersA on - * \p dest manually later. - * - * @param dest OUT: Result %URI - * @param absoluteSource IN: Absolute %URI to make relative - * @param absoluteBase IN: Base %URI - * @param domainRootMode IN: Create %URI with path relative to domain root - * @return Error code or 0 on success - * - * @see uriRemoveBaseUriMmA - * @see uriAddBaseUriA - * @see uriAddBaseUriExA - * @see uriAddBaseUriExMmA - * @since 0.5.2 - */ -URI_PUBLIC int URI_FUNC(RemoveBaseUri)(URI_TYPE(Uri) * dest, - const URI_TYPE(Uri) * absoluteSource, - const URI_TYPE(Uri) * absoluteBase, - UriBool domainRootMode); - - - -/** - * Tries to make a relative %URI (a reference) from an - * absolute %URI and a given base %URI. The resulting %URI is going to be - * relative if the absolute %URI and base %UI share both scheme and authority. - * If that is not the case, the result will still be - * an absolute URI (with scheme part if necessary). - * NOTE: On success you have to call uriFreeUriMembersMmA on - * \p dest manually later. - * - * @param dest OUT: Result %URI - * @param absoluteSource IN: Absolute %URI to make relative - * @param absoluteBase IN: Base %URI - * @param domainRootMode IN: Create %URI with path relative to domain root - * @param memory IN: Memory manager to use, NULL for default libc - * @return Error code or 0 on success - * - * @see uriRemoveBaseUriA - * @see uriAddBaseUriA - * @see uriAddBaseUriExA - * @see uriAddBaseUriExMmA - * @since 0.9.0 - */ -URI_PUBLIC int URI_FUNC(RemoveBaseUriMm)(URI_TYPE(Uri) * dest, - const URI_TYPE(Uri) * absoluteSource, - const URI_TYPE(Uri) * absoluteBase, - UriBool domainRootMode, UriMemoryManager * memory); - - - -/** - * Checks two URIs for equivalence. Comparison is done - * the naive way, without prior normalization. - * NOTE: Two NULL URIs are equal as well. - * - * @param a IN: First %URI - * @param b IN: Second %URI - * @return URI_TRUE when equal, URI_FAlSE else - * - * @since 0.4.0 - */ -URI_PUBLIC UriBool URI_FUNC(EqualsUri)(const URI_TYPE(Uri) * a, - const URI_TYPE(Uri) * b); - - - -/** - * Calculates the number of characters needed to store the - * string representation of the given %URI excluding the - * terminator. - * - * @param uri IN: %URI to measure - * @param charsRequired OUT: Length of the string representation in characters excluding terminator - * @return Error code or 0 on success - * - * @see uriToStringA - * @since 0.5.0 - */ -URI_PUBLIC int URI_FUNC(ToStringCharsRequired)(const URI_TYPE(Uri) * uri, - int * charsRequired); - - - -/** - * Converts a %URI structure back to text as described in - * section 5.3 of RFC 3986. - * - * @param dest OUT: Output destination - * @param uri IN: %URI to convert - * @param maxChars IN: Maximum number of characters to copy including terminator - * @param charsWritten OUT: Number of characters written, can be lower than maxChars even if the %URI is too long! - * @return Error code or 0 on success - * - * @see uriToStringCharsRequiredA - * @since 0.4.0 - */ -URI_PUBLIC int URI_FUNC(ToString)(URI_CHAR * dest, const URI_TYPE(Uri) * uri, - int maxChars, int * charsWritten); - - - -/** - * Determines the components of a %URI that are not normalized. - * - * @param uri IN: %URI to check - * @return Normalization job mask - * - * @see uriNormalizeSyntaxA - * @see uriNormalizeSyntaxExA - * @see uriNormalizeSyntaxExMmA - * @see uriNormalizeSyntaxMaskRequiredExA - * @since 0.5.0 - * @deprecated Deprecated since 0.9.0, please migrate to uriNormalizeSyntaxMaskRequiredExA (with "Ex"). - */ -URI_PUBLIC unsigned int URI_FUNC(NormalizeSyntaxMaskRequired)( - const URI_TYPE(Uri) * uri); - - - -/** - * Determines the components of a %URI that are not normalized. - * - * @param uri IN: %URI to check - * @param outMask OUT: Normalization job mask - * @return Error code or 0 on success - * - * @see uriNormalizeSyntaxA - * @see uriNormalizeSyntaxExA - * @see uriNormalizeSyntaxExMmA - * @see uriNormalizeSyntaxMaskRequiredA - * @since 0.9.0 - */ -URI_PUBLIC int URI_FUNC(NormalizeSyntaxMaskRequiredEx)( - const URI_TYPE(Uri) * uri, unsigned int * outMask); - - - -/** - * Normalizes a %URI using a normalization mask. - * The normalization mask decides what components are normalized. - * - * NOTE: If necessary the %URI becomes owner of all memory - * behind the text pointed to. Text is duplicated in that case. - * Uses default libc-based memory manager. - * - * @param uri INOUT: %URI to normalize - * @param mask IN: Normalization mask - * @return Error code or 0 on success - * - * @see uriNormalizeSyntaxA - * @see uriNormalizeSyntaxExMmA - * @see uriNormalizeSyntaxMaskRequiredA - * @since 0.5.0 - */ -URI_PUBLIC int URI_FUNC(NormalizeSyntaxEx)(URI_TYPE(Uri) * uri, - unsigned int mask); - - - -/** - * Normalizes a %URI using a normalization mask. - * The normalization mask decides what components are normalized. - * - * NOTE: If necessary the %URI becomes owner of all memory - * behind the text pointed to. Text is duplicated in that case. - * - * @param uri INOUT: %URI to normalize - * @param mask IN: Normalization mask - * @param memory IN: Memory manager to use, NULL for default libc - * @return Error code or 0 on success - * - * @see uriNormalizeSyntaxA - * @see uriNormalizeSyntaxExA - * @see uriNormalizeSyntaxMaskRequiredA - * @since 0.9.0 - */ -URI_PUBLIC int URI_FUNC(NormalizeSyntaxExMm)(URI_TYPE(Uri) * uri, - unsigned int mask, UriMemoryManager * memory); - - - -/** - * Normalizes all components of a %URI. - * - * NOTE: If necessary the %URI becomes owner of all memory - * behind the text pointed to. Text is duplicated in that case. - * Uses default libc-based memory manager. - * - * @param uri INOUT: %URI to normalize - * @return Error code or 0 on success - * - * @see uriNormalizeSyntaxExA - * @see uriNormalizeSyntaxExMmA - * @see uriNormalizeSyntaxMaskRequiredA - * @since 0.5.0 - */ -URI_PUBLIC int URI_FUNC(NormalizeSyntax)(URI_TYPE(Uri) * uri); - - - -/** - * Converts a Unix filename to a %URI string. - * The destination buffer must be large enough to hold 7 + 3 * len(filename) + 1 - * characters in case of an absolute filename or 3 * len(filename) + 1 in case - * of a relative filename. - * - * EXAMPLE - * Input: "/bin/bash" - * Output: "file:///bin/bash" - * - * @param filename IN: Unix filename to convert - * @param uriString OUT: Destination to write %URI string to - * @return Error code or 0 on success - * - * @see uriUriStringToUnixFilenameA - * @see uriWindowsFilenameToUriStringA - * @since 0.5.2 - */ -URI_PUBLIC int URI_FUNC(UnixFilenameToUriString)(const URI_CHAR * filename, - URI_CHAR * uriString); - - - -/** - * Converts a Windows filename to a %URI string. - * The destination buffer must be large enough to hold 8 + 3 * len(filename) + 1 - * characters in case of an absolute filename or 3 * len(filename) + 1 in case - * of a relative filename. - * - * EXAMPLE - * Input: "E:\\Documents and Settings" - * Output: "file:///E:/Documents%20and%20Settings" - * - * @param filename IN: Windows filename to convert - * @param uriString OUT: Destination to write %URI string to - * @return Error code or 0 on success - * - * @see uriUriStringToWindowsFilenameA - * @see uriUnixFilenameToUriStringA - * @since 0.5.2 - */ -URI_PUBLIC int URI_FUNC(WindowsFilenameToUriString)(const URI_CHAR * filename, - URI_CHAR * uriString); - - - -/** - * Extracts a Unix filename from a %URI string. - * The destination buffer must be large enough to hold len(uriString) + 1 - 7 - * characters in case of an absolute %URI or len(uriString) + 1 in case - * of a relative %URI. - * - * @param uriString IN: %URI string to convert - * @param filename OUT: Destination to write filename to - * @return Error code or 0 on success - * - * @see uriUnixFilenameToUriStringA - * @see uriUriStringToWindowsFilenameA - * @since 0.5.2 - */ -URI_PUBLIC int URI_FUNC(UriStringToUnixFilename)(const URI_CHAR * uriString, - URI_CHAR * filename); - - - -/** - * Extracts a Windows filename from a %URI string. - * The destination buffer must be large enough to hold len(uriString) + 1 - 5 - * characters in case of an absolute %URI or len(uriString) + 1 in case - * of a relative %URI. - * - * @param uriString IN: %URI string to convert - * @param filename OUT: Destination to write filename to - * @return Error code or 0 on success - * - * @see uriWindowsFilenameToUriStringA - * @see uriUriStringToUnixFilenameA - * @since 0.5.2 - */ -URI_PUBLIC int URI_FUNC(UriStringToWindowsFilename)(const URI_CHAR * uriString, - URI_CHAR * filename); - - - -/** - * Calculates the number of characters needed to store the - * string representation of the given query list excluding the - * terminator. It is assumed that line breaks are will be - * normalized to "%0D%0A". - * - * @param queryList IN: Query list to measure - * @param charsRequired OUT: Length of the string representation in characters excluding terminator - * @return Error code or 0 on success - * - * @see uriComposeQueryCharsRequiredExA - * @see uriComposeQueryA - * @since 0.7.0 - */ -URI_PUBLIC int URI_FUNC(ComposeQueryCharsRequired)( - const URI_TYPE(QueryList) * queryList, int * charsRequired); - - - -/** - * Calculates the number of characters needed to store the - * string representation of the given query list excluding the - * terminator. - * - * @param queryList IN: Query list to measure - * @param charsRequired OUT: Length of the string representation in characters excluding terminator - * @param spaceToPlus IN: Whether to convert ' ' to '+' or not - * @param normalizeBreaks IN: Whether to convert CR and LF to CR-LF or not. - * @return Error code or 0 on success - * - * @see uriComposeQueryCharsRequiredA - * @see uriComposeQueryExA - * @since 0.7.0 - */ -URI_PUBLIC int URI_FUNC(ComposeQueryCharsRequiredEx)( - const URI_TYPE(QueryList) * queryList, - int * charsRequired, UriBool spaceToPlus, UriBool normalizeBreaks); - - - -/** - * Converts a query list structure back to a query string. - * The composed string does not start with '?', - * on the way ' ' is converted to '+' and line breaks are - * normalized to "%0D%0A". - * - * @param dest OUT: Output destination - * @param queryList IN: Query list to convert - * @param maxChars IN: Maximum number of characters to copy including terminator - * @param charsWritten OUT: Number of characters written, can be lower than maxChars even if the query list is too long! - * @return Error code or 0 on success - * - * @see uriComposeQueryExA - * @see uriComposeQueryMallocA - * @see uriComposeQueryMallocExA - * @see uriComposeQueryMallocExMmA - * @see uriComposeQueryCharsRequiredA - * @see uriDissectQueryMallocA - * @see uriDissectQueryMallocExA - * @see uriDissectQueryMallocExMmA - * @since 0.7.0 - */ -URI_PUBLIC int URI_FUNC(ComposeQuery)(URI_CHAR * dest, - const URI_TYPE(QueryList) * queryList, int maxChars, int * charsWritten); - - - -/** - * Converts a query list structure back to a query string. - * The composed string does not start with '?'. - * - * @param dest OUT: Output destination - * @param queryList IN: Query list to convert - * @param maxChars IN: Maximum number of characters to copy including terminator - * @param charsWritten OUT: Number of characters written, can be lower than maxChars even if the query list is too long! - * @param spaceToPlus IN: Whether to convert ' ' to '+' or not - * @param normalizeBreaks IN: Whether to convert CR and LF to CR-LF or not. - * @return Error code or 0 on success - * - * @see uriComposeQueryA - * @see uriComposeQueryMallocA - * @see uriComposeQueryMallocExA - * @see uriComposeQueryMallocExMmA - * @see uriComposeQueryCharsRequiredExA - * @see uriDissectQueryMallocA - * @see uriDissectQueryMallocExA - * @see uriDissectQueryMallocExMmA - * @since 0.7.0 - */ -URI_PUBLIC int URI_FUNC(ComposeQueryEx)(URI_CHAR * dest, - const URI_TYPE(QueryList) * queryList, int maxChars, int * charsWritten, - UriBool spaceToPlus, UriBool normalizeBreaks); - - - -/** - * Converts a query list structure back to a query string. - * Memory for this string is allocated internally. - * The composed string does not start with '?', - * on the way ' ' is converted to '+' and line breaks are - * normalized to "%0D%0A". - * Uses default libc-based memory manager. - * - * @param dest OUT: Output destination - * @param queryList IN: Query list to convert - * @return Error code or 0 on success - * - * @see uriComposeQueryMallocExA - * @see uriComposeQueryMallocExMmA - * @see uriComposeQueryA - * @see uriDissectQueryMallocA - * @see uriDissectQueryMallocExA - * @see uriDissectQueryMallocExMmA - * @since 0.7.0 - */ -URI_PUBLIC int URI_FUNC(ComposeQueryMalloc)(URI_CHAR ** dest, - const URI_TYPE(QueryList) * queryList); - - - -/** - * Converts a query list structure back to a query string. - * Memory for this string is allocated internally. - * The composed string does not start with '?'. - * Uses default libc-based memory manager. - * - * @param dest OUT: Output destination - * @param queryList IN: Query list to convert - * @param spaceToPlus IN: Whether to convert ' ' to '+' or not - * @param normalizeBreaks IN: Whether to convert CR and LF to CR-LF or not. - * @return Error code or 0 on success - * - * @see uriComposeQueryMallocA - * @see uriComposeQueryMallocExMmA - * @see uriComposeQueryExA - * @see uriDissectQueryMallocA - * @see uriDissectQueryMallocExA - * @see uriDissectQueryMallocExMmA - * @since 0.7.0 - */ -URI_PUBLIC int URI_FUNC(ComposeQueryMallocEx)(URI_CHAR ** dest, - const URI_TYPE(QueryList) * queryList, - UriBool spaceToPlus, UriBool normalizeBreaks); - - - -/** - * Converts a query list structure back to a query string. - * Memory for this string is allocated internally. - * The composed string does not start with '?'. - * - * @param dest OUT: Output destination - * @param queryList IN: Query list to convert - * @param spaceToPlus IN: Whether to convert ' ' to '+' or not - * @param normalizeBreaks IN: Whether to convert CR and LF to CR-LF or not. - * @param memory IN: Memory manager to use, NULL for default libc - * @return Error code or 0 on success - * - * @see uriComposeQueryMallocA - * @see uriComposeQueryMallocExA - * @see uriComposeQueryExA - * @see uriDissectQueryMallocA - * @see uriDissectQueryMallocExA - * @see uriDissectQueryMallocExMmA - * @since 0.9.0 - */ -URI_PUBLIC int URI_FUNC(ComposeQueryMallocExMm)(URI_CHAR ** dest, - const URI_TYPE(QueryList) * queryList, - UriBool spaceToPlus, UriBool normalizeBreaks, - UriMemoryManager * memory); - - - -/** - * Constructs a query list from the raw query string of a given URI. - * On the way '+' is converted back to ' ', line breaks are not modified. - * Uses default libc-based memory manager. - * - * @param dest OUT: Output destination - * @param itemCount OUT: Number of items found, can be NULL - * @param first IN: Pointer to first character after '?' - * @param afterLast IN: Pointer to character after the last one still in - * @return Error code or 0 on success - * - * @see uriDissectQueryMallocExA - * @see uriDissectQueryMallocExMmA - * @see uriComposeQueryA - * @see uriFreeQueryListA - * @see uriFreeQueryListMmA - * @since 0.7.0 - */ -URI_PUBLIC int URI_FUNC(DissectQueryMalloc)(URI_TYPE(QueryList) ** dest, - int * itemCount, const URI_CHAR * first, const URI_CHAR * afterLast); - - - -/** - * Constructs a query list from the raw query string of a given URI. - * Uses default libc-based memory manager. - * - * @param dest OUT: Output destination - * @param itemCount OUT: Number of items found, can be NULL - * @param first IN: Pointer to first character after '?' - * @param afterLast IN: Pointer to character after the last one still in - * @param plusToSpace IN: Whether to convert '+' to ' ' or not - * @param breakConversion IN: Line break conversion mode - * @return Error code or 0 on success - * - * @see uriDissectQueryMallocA - * @see uriDissectQueryMallocExMmA - * @see uriComposeQueryExA - * @see uriFreeQueryListA - * @since 0.7.0 - */ -URI_PUBLIC int URI_FUNC(DissectQueryMallocEx)(URI_TYPE(QueryList) ** dest, - int * itemCount, const URI_CHAR * first, const URI_CHAR * afterLast, - UriBool plusToSpace, UriBreakConversion breakConversion); - - - -/** - * Constructs a query list from the raw query string of a given URI. - * - * @param dest OUT: Output destination - * @param itemCount OUT: Number of items found, can be NULL - * @param first IN: Pointer to first character after '?' - * @param afterLast IN: Pointer to character after the last one still in - * @param plusToSpace IN: Whether to convert '+' to ' ' or not - * @param breakConversion IN: Line break conversion mode - * @param memory IN: Memory manager to use, NULL for default libc - * @return Error code or 0 on success - * - * @see uriDissectQueryMallocA - * @see uriDissectQueryMallocExA - * @see uriComposeQueryExA - * @see uriFreeQueryListA - * @see uriFreeQueryListMmA - * @since 0.9.0 - */ -URI_PUBLIC int URI_FUNC(DissectQueryMallocExMm)(URI_TYPE(QueryList) ** dest, - int * itemCount, const URI_CHAR * first, const URI_CHAR * afterLast, - UriBool plusToSpace, UriBreakConversion breakConversion, - UriMemoryManager * memory); - - - -/** - * Frees all memory associated with the given query list. - * The structure itself is freed as well. - * - * @param queryList INOUT: Query list to free - * - * @see uriFreeQueryListMmA - * @since 0.7.0 - */ -URI_PUBLIC void URI_FUNC(FreeQueryList)(URI_TYPE(QueryList) * queryList); - - - -/** - * Frees all memory associated with the given query list. - * The structure itself is freed as well. - * - * @param queryList INOUT: Query list to free - * @param memory IN: Memory manager to use, NULL for default libc - * @return Error code or 0 on success - * - * @see uriFreeQueryListA - * @since 0.9.0 - */ -URI_PUBLIC int URI_FUNC(FreeQueryListMm)(URI_TYPE(QueryList) * queryList, - UriMemoryManager * memory); - - - -#ifdef __cplusplus -} -#endif - - - -#endif -#endif diff --git a/cpp/src/arrow/vendored/uriparser/UriBase.h b/cpp/src/arrow/vendored/uriparser/UriBase.h deleted file mode 100644 index 166915950c29..000000000000 --- a/cpp/src/arrow/vendored/uriparser/UriBase.h +++ /dev/null @@ -1,377 +0,0 @@ -/* - * uriparser - RFC 3986 URI parsing library - * - * Copyright (C) 2007, Weijia Song - * Copyright (C) 2007, Sebastian Pipping - * 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 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. - */ - -/** - * @file UriBase.h - * Holds definitions independent of the encoding pass. - */ - -#ifndef URI_BASE_H -#define URI_BASE_H 1 - - - -/* Version helper macro */ -#define URI_ANSI_TO_UNICODE(x) L##x - - - -/* Version */ -#define URI_VER_MAJOR 0 -#define URI_VER_MINOR 9 -#define URI_VER_RELEASE 3 -#define URI_VER_SUFFIX_ANSI "" -#define URI_VER_SUFFIX_UNICODE URI_ANSI_TO_UNICODE(URI_VER_SUFFIX_ANSI) - - - -/* More version helper macros */ -#define URI_INT_TO_ANSI_HELPER(x) #x -#define URI_INT_TO_ANSI(x) URI_INT_TO_ANSI_HELPER(x) - -#define URI_INT_TO_UNICODE_HELPER(x) URI_ANSI_TO_UNICODE(#x) -#define URI_INT_TO_UNICODE(x) URI_INT_TO_UNICODE_HELPER(x) - -#define URI_VER_ANSI_HELPER(ma, mi, r, s) \ - URI_INT_TO_ANSI(ma) "." \ - URI_INT_TO_ANSI(mi) "." \ - URI_INT_TO_ANSI(r) \ - s - -#define URI_VER_UNICODE_HELPER(ma, mi, r, s) \ - URI_INT_TO_UNICODE(ma) L"." \ - URI_INT_TO_UNICODE(mi) L"." \ - URI_INT_TO_UNICODE(r) \ - s - - - -/* Full version strings */ -#define URI_VER_ANSI URI_VER_ANSI_HELPER(URI_VER_MAJOR, URI_VER_MINOR, URI_VER_RELEASE, URI_VER_SUFFIX_ANSI) -#define URI_VER_UNICODE URI_VER_UNICODE_HELPER(URI_VER_MAJOR, URI_VER_MINOR, URI_VER_RELEASE, URI_VER_SUFFIX_UNICODE) - - - -/* Unused parameter macro */ -#ifdef __GNUC__ -# define URI_UNUSED(x) unused_##x __attribute__((unused)) -#else -# define URI_UNUSED(x) x -#endif - - - -/* Import/export decorator */ -#if defined(URI_STATIC_BUILD) -# define URI_PUBLIC -#else -# if defined(URI_LIBRARY_BUILD) -# if defined(_MSC_VER) -# define URI_PUBLIC __declspec(dllexport) -# elif defined(URI_VISIBILITY) -# define URI_PUBLIC __attribute__ ((visibility("default"))) -# else -# define URI_PUBLIC -# endif -# else -# if defined(_MSC_VER) -# define URI_PUBLIC __declspec(dllimport) -# else -# define URI_PUBLIC -# endif -# endif -#endif - - - -typedef int UriBool; /**< Boolean type */ - -#define URI_TRUE 1 -#define URI_FALSE 0 - - - -/* Shared errors */ -#define URI_SUCCESS 0 -#define URI_ERROR_SYNTAX 1 /* Parsed text violates expected format */ -#define URI_ERROR_NULL 2 /* One of the params passed was NULL - although it mustn't be */ -#define URI_ERROR_MALLOC 3 /* Requested memory could not be allocated */ -#define URI_ERROR_OUTPUT_TOO_LARGE 4 /* Some output is to large for the receiving buffer */ -#define URI_ERROR_NOT_IMPLEMENTED 8 /* The called function is not implemented yet */ -#define URI_ERROR_RANGE_INVALID 9 /* The parameters passed contained invalid ranges */ -#define URI_ERROR_MEMORY_MANAGER_INCOMPLETE 10 /* [>=0.9.0] The UriMemoryManager passed does not implement all needed functions */ - - -/* Errors specific to ToString */ -#define URI_ERROR_TOSTRING_TOO_LONG URI_ERROR_OUTPUT_TOO_LARGE /* Deprecated, test for URI_ERROR_OUTPUT_TOO_LARGE instead */ - -/* Errors specific to AddBaseUri */ -#define URI_ERROR_ADDBASE_REL_BASE 5 /* Given base is not absolute */ - -/* Errors specific to RemoveBaseUri */ -#define URI_ERROR_REMOVEBASE_REL_BASE 6 /* Given base is not absolute */ -#define URI_ERROR_REMOVEBASE_REL_SOURCE 7 /* Given base is not absolute */ - -/* Error specific to uriTestMemoryManager */ -#define URI_ERROR_MEMORY_MANAGER_FAULTY 11 /* [>=0.9.0] The UriMemoryManager given did not pass the test suite */ - - -#ifndef URI_DOXYGEN -# include /* For NULL, snprintf */ -# include /* For wchar_t */ -# include /* For strlen, memset, memcpy */ -# include /* For malloc */ -#endif /* URI_DOXYGEN */ - - - -/** - * Holds an IPv4 address. - */ -typedef struct UriIp4Struct { - unsigned char data[4]; /**< Each octet in one byte */ -} UriIp4; /**< @copydoc UriIp4Struct */ - - - -/** - * Holds an IPv6 address. - */ -typedef struct UriIp6Struct { - unsigned char data[16]; /**< Each quad in two bytes */ -} UriIp6; /**< @copydoc UriIp6Struct */ - - -struct UriMemoryManagerStruct; /* foward declaration to break loop */ - - -/** - * Function signature that custom malloc(3) functions must conform to - * - * @since 0.9.0 - */ -typedef void * (*UriFuncMalloc)(struct UriMemoryManagerStruct *, size_t); - -/** - * Function signature that custom calloc(3) functions must conform to - * - * @since 0.9.0 - */ -typedef void * (*UriFuncCalloc)(struct UriMemoryManagerStruct *, size_t, size_t); - -/** - * Function signature that custom realloc(3) functions must conform to - * - * @since 0.9.0 - */ -typedef void * (*UriFuncRealloc)(struct UriMemoryManagerStruct *, void *, size_t); - -/** - * Function signature that custom reallocarray(3) functions must conform to - * - * @since 0.9.0 - */ -typedef void * (*UriFuncReallocarray)(struct UriMemoryManagerStruct *, void *, size_t, size_t); - -/** - * Function signature that custom free(3) functions must conform to - * - * @since 0.9.0 - */ -typedef void (*UriFuncFree)(struct UriMemoryManagerStruct *, void *); - - -/** - * Class-like interface of custom memory managers - * - * @see uriCompleteMemoryManager - * @see uriEmulateCalloc - * @see uriEmulateReallocarray - * @see uriTestMemoryManager - * @since 0.9.0 - */ -typedef struct UriMemoryManagerStruct { - UriFuncMalloc malloc; /**< Pointer to custom malloc(3) */ - UriFuncCalloc calloc; /**< Pointer to custom calloc(3); to emulate using malloc and memset see uriEmulateCalloc */ - UriFuncRealloc realloc; /**< Pointer to custom realloc(3) */ - UriFuncReallocarray reallocarray; /**< Pointer to custom reallocarray(3); to emulate using realloc see uriEmulateReallocarray */ - UriFuncFree free; /**< Pointer to custom free(3) */ - void * userData; /**< Pointer to data that the other function members need access to */ -} UriMemoryManager; /**< @copydoc UriMemoryManagerStruct */ - - -/** - * Specifies a line break conversion mode. - */ -typedef enum UriBreakConversionEnum { - URI_BR_TO_LF, /**< Convert to Unix line breaks ("\\x0a") */ - URI_BR_TO_CRLF, /**< Convert to Windows line breaks ("\\x0d\\x0a") */ - URI_BR_TO_CR, /**< Convert to Macintosh line breaks ("\\x0d") */ - URI_BR_TO_UNIX = URI_BR_TO_LF, /**< @copydoc UriBreakConversionEnum::URI_BR_TO_LF */ - URI_BR_TO_WINDOWS = URI_BR_TO_CRLF, /**< @copydoc UriBreakConversionEnum::URI_BR_TO_CRLF */ - URI_BR_TO_MAC = URI_BR_TO_CR, /**< @copydoc UriBreakConversionEnum::URI_BR_TO_CR */ - URI_BR_DONT_TOUCH /**< Copy line breaks unmodified */ -} UriBreakConversion; /**< @copydoc UriBreakConversionEnum */ - - - -/** - * Specifies which component of a %URI has to be normalized. - */ -typedef enum UriNormalizationMaskEnum { - URI_NORMALIZED = 0, /**< Do not normalize anything */ - URI_NORMALIZE_SCHEME = 1 << 0, /**< Normalize scheme (fix uppercase letters) */ - URI_NORMALIZE_USER_INFO = 1 << 1, /**< Normalize user info (fix uppercase percent-encodings) */ - URI_NORMALIZE_HOST = 1 << 2, /**< Normalize host (fix uppercase letters) */ - URI_NORMALIZE_PATH = 1 << 3, /**< Normalize path (fix uppercase percent-encodings and redundant dot segments) */ - URI_NORMALIZE_QUERY = 1 << 4, /**< Normalize query (fix uppercase percent-encodings) */ - URI_NORMALIZE_FRAGMENT = 1 << 5 /**< Normalize fragment (fix uppercase percent-encodings) */ -} UriNormalizationMask; /**< @copydoc UriNormalizationMaskEnum */ - - - -/** - * Specifies how to resolve %URI references. - */ -typedef enum UriResolutionOptionsEnum { - URI_RESOLVE_STRICTLY = 0, /**< Full RFC conformance */ - URI_RESOLVE_IDENTICAL_SCHEME_COMPAT = 1 << 0 /**< Treat %URI to resolve with identical scheme as having no scheme */ -} UriResolutionOptions; /**< @copydoc UriResolutionOptionsEnum */ - - - -/** - * Wraps a memory manager backend that only provides malloc and free - * to make a complete memory manager ready to be used. - * - * The core feature of this wrapper is that you don't need to implement - * realloc if you don't want to. The wrapped memory manager uses - * backend->malloc, memcpy, and backend->free and soieof(size_t) extra - * bytes per allocation to emulate fallback realloc for you. - * - * memory->calloc is uriEmulateCalloc. - * memory->free uses backend->free and handles the size header. - * memory->malloc uses backend->malloc and adds a size header. - * memory->realloc uses memory->malloc, memcpy, and memory->free and reads - * the size header. - * memory->reallocarray is uriEmulateReallocarray. - * - * The internal workings behind memory->free, memory->malloc, and - * memory->realloc may change so the functions exposed by these function - * pointer sshould be consided internal and not public API. - * - * @param memory OUT: Where to write the wrapped memory manager to - * @param backend IN: Memory manager to use as a backend - * @return Error code or 0 on success - * - * @see uriEmulateCalloc - * @see uriEmulateReallocarray - * @see UriMemoryManager - * @since 0.9.0 - */ -URI_PUBLIC int uriCompleteMemoryManager(UriMemoryManager * memory, - UriMemoryManager * backend); - - - -/** - * Offers emulation of calloc(3) based on memory->malloc and memset. - * See "man 3 calloc" as well. - * - * @param memory IN: Memory manager to use, should not be NULL - * @param nmemb IN: Number of elements to allocate - * @param size IN: Size in bytes per element - * @return Pointer to allocated memory or NULL - * - * @see uriCompleteMemoryManager - * @see uriEmulateReallocarray - * @see UriMemoryManager - * @since 0.9.0 - */ -URI_PUBLIC void * uriEmulateCalloc(UriMemoryManager * memory, - size_t nmemb, size_t size); - - - -/** - * Offers emulation of reallocarray(3) based on memory->realloc. - * See "man 3 reallocarray" as well. - * - * @param memory IN: Memory manager to use, should not be NULL - * @param ptr IN: Pointer allocated using memory->malloc/... or NULL - * @param nmemb IN: Number of elements to allocate - * @param size IN: Size in bytes per element - * @return Pointer to allocated memory or NULL - * - * @see uriCompleteMemoryManager - * @see uriEmulateCalloc - * @see UriMemoryManager - * @since 0.9.0 - */ -URI_PUBLIC void * uriEmulateReallocarray(UriMemoryManager * memory, - void * ptr, size_t nmemb, size_t size); - - - -/** - * Run multiple tests against a given memory manager. - * For example, one test - * 1. allocates a small amount of memory, - * 2. writes some magic bytes to it, - * 3. reallocates it, - * 4. checks that previous values are still present, - * 5. and frees that memory. - * - * It is recommended to compile with AddressSanitizer enabled - * to take full advantage of uriTestMemoryManager. - * - * @param memory IN: Memory manager to use, should not be NULL - * @return Error code or 0 on success - * - * @see uriEmulateCalloc - * @see uriEmulateReallocarray - * @see UriMemoryManager - * @since 0.9.0 - */ -URI_PUBLIC int uriTestMemoryManager(UriMemoryManager * memory); - - - -#endif /* URI_BASE_H */ diff --git a/cpp/src/arrow/vendored/uriparser/UriCommon.c b/cpp/src/arrow/vendored/uriparser/UriCommon.c deleted file mode 100644 index 824893d7c2cb..000000000000 --- a/cpp/src/arrow/vendored/uriparser/UriCommon.c +++ /dev/null @@ -1,572 +0,0 @@ -/* - * uriparser - RFC 3986 URI parsing library - * - * Copyright (C) 2007, Weijia Song - * Copyright (C) 2007, Sebastian Pipping - * 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 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. - */ - -/* What encodings are enabled? */ -#include "UriDefsConfig.h" -#if (!defined(URI_PASS_ANSI) && !defined(URI_PASS_UNICODE)) -/* Include SELF twice */ -# ifdef URI_ENABLE_ANSI -# define URI_PASS_ANSI 1 -# include "UriCommon.c" -# undef URI_PASS_ANSI -# endif -# ifdef URI_ENABLE_UNICODE -# define URI_PASS_UNICODE 1 -# include "UriCommon.c" -# undef URI_PASS_UNICODE -# endif -#else -# ifdef URI_PASS_ANSI -# include "UriDefsAnsi.h" -# else -# include "UriDefsUnicode.h" -# include -# endif - - - -#ifndef URI_DOXYGEN -# include "Uri.h" -# include "UriCommon.h" -#endif - - - -/*extern*/ const URI_CHAR * const URI_FUNC(SafeToPointTo) = _UT("X"); -/*extern*/ const URI_CHAR * const URI_FUNC(ConstPwd) = _UT("."); -/*extern*/ const URI_CHAR * const URI_FUNC(ConstParent) = _UT(".."); - - - -void URI_FUNC(ResetUri)(URI_TYPE(Uri) * uri) { - if (uri == NULL) { - return; - } - memset(uri, 0, sizeof(URI_TYPE(Uri))); -} - - - -/* Compares two text ranges for equal text content */ -int URI_FUNC(CompareRange)( - const URI_TYPE(TextRange) * a, - const URI_TYPE(TextRange) * b) { - int diff; - - /* NOTE: Both NULL means equal! */ - if ((a == NULL) || (b == NULL)) { - return ((a == NULL) ? 0 : 1) - ((b == NULL) ? 0 : 1); - } - - /* NOTE: Both NULL means equal! */ - if ((a->first == NULL) || (b->first == NULL)) { - return ((a->first == NULL) ? 0 : 1) - ((b->first == NULL) ? 0 : 1); - } - - diff = ((int)(a->afterLast - a->first) - (int)(b->afterLast - b->first)); - if (diff > 0) { - return 1; - } else if (diff < 0) { - return -1; - } - - diff = URI_STRNCMP(a->first, b->first, (a->afterLast - a->first)); - - if (diff > 0) { - return 1; - } else if (diff < 0) { - return -1; - } - - return diff; -} - - - -/* Properly removes "." and ".." path segments */ -UriBool URI_FUNC(RemoveDotSegments)(URI_TYPE(Uri) * uri, - UriBool relative, UriMemoryManager * memory) { - if (uri == NULL) { - return URI_TRUE; - } - return URI_FUNC(RemoveDotSegmentsEx)(uri, relative, uri->owner, memory); -} - - - -UriBool URI_FUNC(RemoveDotSegmentsEx)(URI_TYPE(Uri) * uri, - UriBool relative, UriBool pathOwned, UriMemoryManager * memory) { - URI_TYPE(PathSegment) * walker; - if ((uri == NULL) || (uri->pathHead == NULL)) { - return URI_TRUE; - } - - walker = uri->pathHead; - walker->reserved = NULL; /* Prev pointer */ - do { - UriBool removeSegment = URI_FALSE; - int len = (int)(walker->text.afterLast - walker->text.first); - switch (len) { - case 1: - if ((walker->text.first)[0] == _UT('.')) { - /* "." segment -> remove if not essential */ - URI_TYPE(PathSegment) * const prev = walker->reserved; - URI_TYPE(PathSegment) * const nextBackup = walker->next; - - /* Is this dot segment essential? */ - removeSegment = URI_TRUE; - if (relative && (walker == uri->pathHead) && (walker->next != NULL)) { - const URI_CHAR * ch = walker->next->text.first; - for (; ch < walker->next->text.afterLast; ch++) { - if (*ch == _UT(':')) { - removeSegment = URI_FALSE; - break; - } - } - } - - if (removeSegment) { - /* Last segment? */ - if (walker->next != NULL) { - /* Not last segment */ - walker->next->reserved = prev; - - if (prev == NULL) { - /* First but not last segment */ - uri->pathHead = walker->next; - } else { - /* Middle segment */ - prev->next = walker->next; - } - - if (pathOwned && (walker->text.first != walker->text.afterLast)) { - memory->free(memory, (URI_CHAR *)walker->text.first); - } - memory->free(memory, walker); - } else { - /* Last segment */ - if (pathOwned && (walker->text.first != walker->text.afterLast)) { - memory->free(memory, (URI_CHAR *)walker->text.first); - } - - if (prev == NULL) { - /* Last and first */ - if (URI_FUNC(IsHostSet)(uri)) { - /* Replace "." with empty segment to represent trailing slash */ - walker->text.first = URI_FUNC(SafeToPointTo); - walker->text.afterLast = URI_FUNC(SafeToPointTo); - } else { - memory->free(memory, walker); - - uri->pathHead = NULL; - uri->pathTail = NULL; - } - } else { - /* Last but not first, replace "." with empty segment to represent trailing slash */ - walker->text.first = URI_FUNC(SafeToPointTo); - walker->text.afterLast = URI_FUNC(SafeToPointTo); - } - } - - walker = nextBackup; - } - } - break; - - case 2: - if (((walker->text.first)[0] == _UT('.')) - && ((walker->text.first)[1] == _UT('.'))) { - /* Path ".." -> remove this and the previous segment */ - URI_TYPE(PathSegment) * const prev = walker->reserved; - URI_TYPE(PathSegment) * prevPrev; - URI_TYPE(PathSegment) * const nextBackup = walker->next; - - removeSegment = URI_TRUE; - if (relative) { - if (prev == NULL) { - removeSegment = URI_FALSE; - } else if ((prev != NULL) - && ((prev->text.afterLast - prev->text.first) == 2) - && ((prev->text.first)[0] == _UT('.')) - && ((prev->text.first)[1] == _UT('.'))) { - removeSegment = URI_FALSE; - } - } - - if (removeSegment) { - if (prev != NULL) { - /* Not first segment */ - prevPrev = prev->reserved; - if (prevPrev != NULL) { - /* Not even prev is the first one */ - prevPrev->next = walker->next; - if (walker->next != NULL) { - walker->next->reserved = prevPrev; - } else { - /* Last segment -> insert "" segment to represent trailing slash, update tail */ - URI_TYPE(PathSegment) * const segment = memory->calloc(memory, 1, sizeof(URI_TYPE(PathSegment))); - if (segment == NULL) { - if (pathOwned && (walker->text.first != walker->text.afterLast)) { - memory->free(memory, (URI_CHAR *)walker->text.first); - } - memory->free(memory, walker); - - if (pathOwned && (prev->text.first != prev->text.afterLast)) { - memory->free(memory, (URI_CHAR *)prev->text.first); - } - memory->free(memory, prev); - - return URI_FALSE; /* Raises malloc error */ - } - segment->text.first = URI_FUNC(SafeToPointTo); - segment->text.afterLast = URI_FUNC(SafeToPointTo); - prevPrev->next = segment; - uri->pathTail = segment; - } - - if (pathOwned && (walker->text.first != walker->text.afterLast)) { - memory->free(memory, (URI_CHAR *)walker->text.first); - } - memory->free(memory, walker); - - if (pathOwned && (prev->text.first != prev->text.afterLast)) { - memory->free(memory, (URI_CHAR *)prev->text.first); - } - memory->free(memory, prev); - - walker = nextBackup; - } else { - /* Prev is the first segment */ - if (walker->next != NULL) { - uri->pathHead = walker->next; - walker->next->reserved = NULL; - - if (pathOwned && (walker->text.first != walker->text.afterLast)) { - memory->free(memory, (URI_CHAR *)walker->text.first); - } - memory->free(memory, walker); - } else { - /* Re-use segment for "" path segment to represent trailing slash, update tail */ - URI_TYPE(PathSegment) * const segment = walker; - if (pathOwned && (segment->text.first != segment->text.afterLast)) { - memory->free(memory, (URI_CHAR *)segment->text.first); - } - segment->text.first = URI_FUNC(SafeToPointTo); - segment->text.afterLast = URI_FUNC(SafeToPointTo); - uri->pathHead = segment; - uri->pathTail = segment; - } - - if (pathOwned && (prev->text.first != prev->text.afterLast)) { - memory->free(memory, (URI_CHAR *)prev->text.first); - } - memory->free(memory, prev); - - walker = nextBackup; - } - } else { - URI_TYPE(PathSegment) * const anotherNextBackup = walker->next; - /* First segment -> update head pointer */ - uri->pathHead = walker->next; - if (walker->next != NULL) { - walker->next->reserved = NULL; - } else { - /* Last segment -> update tail */ - uri->pathTail = NULL; - } - - if (pathOwned && (walker->text.first != walker->text.afterLast)) { - memory->free(memory, (URI_CHAR *)walker->text.first); - } - memory->free(memory, walker); - - walker = anotherNextBackup; - } - } - } - break; - - } - - if (!removeSegment) { - if (walker->next != NULL) { - walker->next->reserved = walker; - } else { - /* Last segment -> update tail */ - uri->pathTail = walker; - } - walker = walker->next; - } - } while (walker != NULL); - - return URI_TRUE; -} - - - -/* Properly removes "." and ".." path segments */ -UriBool URI_FUNC(RemoveDotSegmentsAbsolute)(URI_TYPE(Uri) * uri, - UriMemoryManager * memory) { - const UriBool ABSOLUTE = URI_FALSE; - return URI_FUNC(RemoveDotSegments)(uri, ABSOLUTE, memory); -} - - - -unsigned char URI_FUNC(HexdigToInt)(URI_CHAR hexdig) { - switch (hexdig) { - case _UT('0'): - case _UT('1'): - case _UT('2'): - case _UT('3'): - case _UT('4'): - case _UT('5'): - case _UT('6'): - case _UT('7'): - case _UT('8'): - case _UT('9'): - return (unsigned char)(9 + hexdig - _UT('9')); - - case _UT('a'): - case _UT('b'): - case _UT('c'): - case _UT('d'): - case _UT('e'): - case _UT('f'): - return (unsigned char)(15 + hexdig - _UT('f')); - - case _UT('A'): - case _UT('B'): - case _UT('C'): - case _UT('D'): - case _UT('E'): - case _UT('F'): - return (unsigned char)(15 + hexdig - _UT('F')); - - default: - return 0; - } -} - - - -URI_CHAR URI_FUNC(HexToLetter)(unsigned int value) { - /* Uppercase recommended in section 2.1. of RFC 3986 * - * http://tools.ietf.org/html/rfc3986#section-2.1 */ - return URI_FUNC(HexToLetterEx)(value, URI_TRUE); -} - - - -URI_CHAR URI_FUNC(HexToLetterEx)(unsigned int value, UriBool uppercase) { - switch (value) { - case 0: return _UT('0'); - case 1: return _UT('1'); - case 2: return _UT('2'); - case 3: return _UT('3'); - case 4: return _UT('4'); - case 5: return _UT('5'); - case 6: return _UT('6'); - case 7: return _UT('7'); - case 8: return _UT('8'); - case 9: return _UT('9'); - - case 10: return (uppercase == URI_TRUE) ? _UT('A') : _UT('a'); - case 11: return (uppercase == URI_TRUE) ? _UT('B') : _UT('b'); - case 12: return (uppercase == URI_TRUE) ? _UT('C') : _UT('c'); - case 13: return (uppercase == URI_TRUE) ? _UT('D') : _UT('d'); - case 14: return (uppercase == URI_TRUE) ? _UT('E') : _UT('e'); - default: return (uppercase == URI_TRUE) ? _UT('F') : _UT('f'); - } -} - - - -/* Checks if a URI has the host component set. */ -UriBool URI_FUNC(IsHostSet)(const URI_TYPE(Uri) * uri) { - return (uri != NULL) - && ((uri->hostText.first != NULL) - || (uri->hostData.ip4 != NULL) - || (uri->hostData.ip6 != NULL) - || (uri->hostData.ipFuture.first != NULL) - ); -} - - - -/* Copies the path segment list from one URI to another. */ -UriBool URI_FUNC(CopyPath)(URI_TYPE(Uri) * dest, - const URI_TYPE(Uri) * source, UriMemoryManager * memory) { - if (source->pathHead == NULL) { - /* No path component */ - dest->pathHead = NULL; - dest->pathTail = NULL; - } else { - /* Copy list but not the text contained */ - URI_TYPE(PathSegment) * sourceWalker = source->pathHead; - URI_TYPE(PathSegment) * destPrev = NULL; - do { - URI_TYPE(PathSegment) * cur = memory->malloc(memory, sizeof(URI_TYPE(PathSegment))); - if (cur == NULL) { - /* Fix broken list */ - if (destPrev != NULL) { - destPrev->next = NULL; - } - return URI_FALSE; /* Raises malloc error */ - } - - /* From this functions usage we know that * - * the dest URI cannot be uri->owner */ - cur->text = sourceWalker->text; - if (destPrev == NULL) { - /* First segment ever */ - dest->pathHead = cur; - } else { - destPrev->next = cur; - } - destPrev = cur; - sourceWalker = sourceWalker->next; - } while (sourceWalker != NULL); - dest->pathTail = destPrev; - dest->pathTail->next = NULL; - } - - dest->absolutePath = source->absolutePath; - return URI_TRUE; -} - - - -/* Copies the authority part of an URI over to another. */ -UriBool URI_FUNC(CopyAuthority)(URI_TYPE(Uri) * dest, - const URI_TYPE(Uri) * source, UriMemoryManager * memory) { - /* From this functions usage we know that * - * the dest URI cannot be uri->owner */ - - /* Copy userInfo */ - dest->userInfo = source->userInfo; - - /* Copy hostText */ - dest->hostText = source->hostText; - - /* Copy hostData */ - if (source->hostData.ip4 != NULL) { - dest->hostData.ip4 = memory->malloc(memory, sizeof(UriIp4)); - if (dest->hostData.ip4 == NULL) { - return URI_FALSE; /* Raises malloc error */ - } - *(dest->hostData.ip4) = *(source->hostData.ip4); - dest->hostData.ip6 = NULL; - dest->hostData.ipFuture.first = NULL; - dest->hostData.ipFuture.afterLast = NULL; - } else if (source->hostData.ip6 != NULL) { - dest->hostData.ip4 = NULL; - dest->hostData.ip6 = memory->malloc(memory, sizeof(UriIp6)); - if (dest->hostData.ip6 == NULL) { - return URI_FALSE; /* Raises malloc error */ - } - *(dest->hostData.ip6) = *(source->hostData.ip6); - dest->hostData.ipFuture.first = NULL; - dest->hostData.ipFuture.afterLast = NULL; - } else { - dest->hostData.ip4 = NULL; - dest->hostData.ip6 = NULL; - dest->hostData.ipFuture = source->hostData.ipFuture; - } - - /* Copy portText */ - dest->portText = source->portText; - - return URI_TRUE; -} - - - -UriBool URI_FUNC(FixAmbiguity)(URI_TYPE(Uri) * uri, - UriMemoryManager * memory) { - URI_TYPE(PathSegment) * segment; - - if ( /* Case 1: absolute path, empty first segment */ - (uri->absolutePath - && (uri->pathHead != NULL) - && (uri->pathHead->text.afterLast == uri->pathHead->text.first)) - - /* Case 2: relative path, empty first and second segment */ - || (!uri->absolutePath - && (uri->pathHead != NULL) - && (uri->pathHead->next != NULL) - && (uri->pathHead->text.afterLast == uri->pathHead->text.first) - && (uri->pathHead->next->text.afterLast == uri->pathHead->next->text.first))) { - /* NOOP */ - } else { - return URI_TRUE; - } - - segment = memory->malloc(memory, 1 * sizeof(URI_TYPE(PathSegment))); - if (segment == NULL) { - return URI_FALSE; /* Raises malloc error */ - } - - /* Insert "." segment in front */ - segment->next = uri->pathHead; - segment->text.first = URI_FUNC(ConstPwd); - segment->text.afterLast = URI_FUNC(ConstPwd) + 1; - uri->pathHead = segment; - return URI_TRUE; -} - - - -void URI_FUNC(FixEmptyTrailSegment)(URI_TYPE(Uri) * uri, - UriMemoryManager * memory) { - /* Fix path if only one empty segment */ - if (!uri->absolutePath - && !URI_FUNC(IsHostSet)(uri) - && (uri->pathHead != NULL) - && (uri->pathHead->next == NULL) - && (uri->pathHead->text.first == uri->pathHead->text.afterLast)) { - memory->free(memory, uri->pathHead); - uri->pathHead = NULL; - uri->pathTail = NULL; - } -} - - - -#endif diff --git a/cpp/src/arrow/vendored/uriparser/UriCommon.h b/cpp/src/arrow/vendored/uriparser/UriCommon.h deleted file mode 100644 index 97b997a9afa3..000000000000 --- a/cpp/src/arrow/vendored/uriparser/UriCommon.h +++ /dev/null @@ -1,109 +0,0 @@ -/* - * uriparser - RFC 3986 URI parsing library - * - * Copyright (C) 2007, Weijia Song - * Copyright (C) 2007, Sebastian Pipping - * 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 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. - */ - -#if (defined(URI_PASS_ANSI) && !defined(URI_COMMON_H_ANSI)) \ - || (defined(URI_PASS_UNICODE) && !defined(URI_COMMON_H_UNICODE)) \ - || (!defined(URI_PASS_ANSI) && !defined(URI_PASS_UNICODE)) -/* What encodings are enabled? */ -#include "UriDefsConfig.h" -#if (!defined(URI_PASS_ANSI) && !defined(URI_PASS_UNICODE)) -/* Include SELF twice */ -# ifdef URI_ENABLE_ANSI -# define URI_PASS_ANSI 1 -# include "UriCommon.h" -# undef URI_PASS_ANSI -# endif -# ifdef URI_ENABLE_UNICODE -# define URI_PASS_UNICODE 1 -# include "UriCommon.h" -# undef URI_PASS_UNICODE -# endif -/* Only one pass for each encoding */ -#elif (defined(URI_PASS_ANSI) && !defined(URI_COMMON_H_ANSI) \ - && defined(URI_ENABLE_ANSI)) || (defined(URI_PASS_UNICODE) \ - && !defined(URI_COMMON_H_UNICODE) && defined(URI_ENABLE_UNICODE)) -# ifdef URI_PASS_ANSI -# define URI_COMMON_H_ANSI 1 -# include "UriDefsAnsi.h" -# else -# define URI_COMMON_H_UNICODE 1 -# include "UriDefsUnicode.h" -# endif - - - -/* Used to point to from empty path segments. - * X.first and X.afterLast must be the same non-NULL value then. */ -extern const URI_CHAR * const URI_FUNC(SafeToPointTo); -extern const URI_CHAR * const URI_FUNC(ConstPwd); -extern const URI_CHAR * const URI_FUNC(ConstParent); - - - -void URI_FUNC(ResetUri)(URI_TYPE(Uri) * uri); - -int URI_FUNC(CompareRange)( - const URI_TYPE(TextRange) * a, - const URI_TYPE(TextRange) * b); - -UriBool URI_FUNC(RemoveDotSegmentsAbsolute)(URI_TYPE(Uri) * uri, - UriMemoryManager * memory); -UriBool URI_FUNC(RemoveDotSegments)(URI_TYPE(Uri) * uri, UriBool relative, - UriMemoryManager * memory); -UriBool URI_FUNC(RemoveDotSegmentsEx)(URI_TYPE(Uri) * uri, - UriBool relative, UriBool pathOwned, UriMemoryManager * memory); - -unsigned char URI_FUNC(HexdigToInt)(URI_CHAR hexdig); -URI_CHAR URI_FUNC(HexToLetter)(unsigned int value); -URI_CHAR URI_FUNC(HexToLetterEx)(unsigned int value, UriBool uppercase); - -UriBool URI_FUNC(IsHostSet)(const URI_TYPE(Uri) * uri); - -UriBool URI_FUNC(CopyPath)(URI_TYPE(Uri) * dest, const URI_TYPE(Uri) * source, - UriMemoryManager * memory); -UriBool URI_FUNC(CopyAuthority)(URI_TYPE(Uri) * dest, - const URI_TYPE(Uri) * source, UriMemoryManager * memory); - -UriBool URI_FUNC(FixAmbiguity)(URI_TYPE(Uri) * uri, UriMemoryManager * memory); -void URI_FUNC(FixEmptyTrailSegment)(URI_TYPE(Uri) * uri, - UriMemoryManager * memory); - - -#endif -#endif diff --git a/cpp/src/arrow/vendored/uriparser/UriCompare.c b/cpp/src/arrow/vendored/uriparser/UriCompare.c deleted file mode 100644 index e63573a1f718..000000000000 --- a/cpp/src/arrow/vendored/uriparser/UriCompare.c +++ /dev/null @@ -1,168 +0,0 @@ -/* - * uriparser - RFC 3986 URI parsing library - * - * Copyright (C) 2007, Weijia Song - * Copyright (C) 2007, Sebastian Pipping - * 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 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. - */ - -/* What encodings are enabled? */ -#include "UriDefsConfig.h" -#if (!defined(URI_PASS_ANSI) && !defined(URI_PASS_UNICODE)) -/* Include SELF twice */ -# ifdef URI_ENABLE_ANSI -# define URI_PASS_ANSI 1 -# include "UriCompare.c" -# undef URI_PASS_ANSI -# endif -# ifdef URI_ENABLE_UNICODE -# define URI_PASS_UNICODE 1 -# include "UriCompare.c" -# undef URI_PASS_UNICODE -# endif -#else -# ifdef URI_PASS_ANSI -# include "UriDefsAnsi.h" -# else -# include "UriDefsUnicode.h" -# include -# endif - - - -#ifndef URI_DOXYGEN -# include "Uri.h" -# include "UriIp4.h" -# include "UriCommon.h" -#endif - - - -UriBool URI_FUNC(EqualsUri)(const URI_TYPE(Uri) * a, - const URI_TYPE(Uri) * b) { - /* NOTE: Both NULL means equal! */ - if ((a == NULL) || (b == NULL)) { - return ((a == NULL) && (b == NULL)) ? URI_TRUE : URI_FALSE; - } - - /* scheme */ - if (URI_FUNC(CompareRange)(&(a->scheme), &(b->scheme))) { - return URI_FALSE; - } - - /* absolutePath */ - if ((a->scheme.first == NULL)&& (a->absolutePath != b->absolutePath)) { - return URI_FALSE; - } - - /* userInfo */ - if (URI_FUNC(CompareRange)(&(a->userInfo), &(b->userInfo))) { - return URI_FALSE; - } - - /* Host */ - if (((a->hostData.ip4 == NULL) != (b->hostData.ip4 == NULL)) - || ((a->hostData.ip6 == NULL) != (b->hostData.ip6 == NULL)) - || ((a->hostData.ipFuture.first == NULL) - != (b->hostData.ipFuture.first == NULL))) { - return URI_FALSE; - } - - if (a->hostData.ip4 != NULL) { - if (memcmp(a->hostData.ip4->data, b->hostData.ip4->data, 4)) { - return URI_FALSE; - } - } - - if (a->hostData.ip6 != NULL) { - if (memcmp(a->hostData.ip6->data, b->hostData.ip6->data, 16)) { - return URI_FALSE; - } - } - - if (a->hostData.ipFuture.first != NULL) { - if (URI_FUNC(CompareRange)(&(a->hostData.ipFuture), &(b->hostData.ipFuture))) { - return URI_FALSE; - } - } - - if ((a->hostData.ip4 == NULL) - && (a->hostData.ip6 == NULL) - && (a->hostData.ipFuture.first == NULL)) { - if (URI_FUNC(CompareRange)(&(a->hostText), &(b->hostText))) { - return URI_FALSE; - } - } - - /* portText */ - if (URI_FUNC(CompareRange)(&(a->portText), &(b->portText))) { - return URI_FALSE; - } - - /* Path */ - if ((a->pathHead == NULL) != (b->pathHead == NULL)) { - return URI_FALSE; - } - - if (a->pathHead != NULL) { - URI_TYPE(PathSegment) * walkA = a->pathHead; - URI_TYPE(PathSegment) * walkB = b->pathHead; - do { - if (URI_FUNC(CompareRange)(&(walkA->text), &(walkB->text))) { - return URI_FALSE; - } - if ((walkA->next == NULL) != (walkB->next == NULL)) { - return URI_FALSE; - } - walkA = walkA->next; - walkB = walkB->next; - } while (walkA != NULL); - } - - /* query */ - if (URI_FUNC(CompareRange)(&(a->query), &(b->query))) { - return URI_FALSE; - } - - /* fragment */ - if (URI_FUNC(CompareRange)(&(a->fragment), &(b->fragment))) { - return URI_FALSE; - } - - return URI_TRUE; /* Equal*/ -} - - - -#endif diff --git a/cpp/src/arrow/vendored/uriparser/UriDefsAnsi.h b/cpp/src/arrow/vendored/uriparser/UriDefsAnsi.h deleted file mode 100644 index d6dbcad1b2a7..000000000000 --- a/cpp/src/arrow/vendored/uriparser/UriDefsAnsi.h +++ /dev/null @@ -1,82 +0,0 @@ -/* - * uriparser - RFC 3986 URI parsing library - * - * Copyright (C) 2007, Weijia Song - * Copyright (C) 2007, Sebastian Pipping - * 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 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. - */ - -/** - * @file UriDefsAnsi.h - * Holds definitions for the ANSI pass. - * NOTE: This header is included N times, not once. - */ - -/* Allow multi inclusion */ -#include "UriDefsConfig.h" - - - -#undef URI_CHAR -#define URI_CHAR char - -#undef _UT -#define _UT(x) x - - - -#undef URI_FUNC -#define URI_FUNC(x) uri##x##A - -#undef URI_TYPE -#define URI_TYPE(x) Uri##x##A - - - -#undef URI_STRLEN -#define URI_STRLEN strlen -#undef URI_STRCPY -#define URI_STRCPY strcpy -#undef URI_STRCMP -#define URI_STRCMP strcmp -#undef URI_STRNCMP -#define URI_STRNCMP strncmp - -/* TODO Remove on next source-compatibility break */ -#undef URI_SNPRINTF -#if (defined(__WIN32__) || defined(_WIN32) || defined(WIN32)) -# define URI_SNPRINTF _snprintf -#else -# define URI_SNPRINTF snprintf -#endif diff --git a/cpp/src/arrow/vendored/uriparser/UriDefsConfig.h b/cpp/src/arrow/vendored/uriparser/UriDefsConfig.h deleted file mode 100644 index d604494b002c..000000000000 --- a/cpp/src/arrow/vendored/uriparser/UriDefsConfig.h +++ /dev/null @@ -1,102 +0,0 @@ -/* - * uriparser - RFC 3986 URI parsing library - * - * Copyright (C) 2007, Weijia Song - * Copyright (C) 2007, Sebastian Pipping - * 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 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. - */ - -/** - * @file UriDefsConfig.h - * Adjusts the internal configuration after processing external definitions. - */ - -#ifndef URI_DEFS_CONFIG_H -#define URI_DEFS_CONFIG_H 1 - - - -/* Deny external overriding */ -#undef URI_ENABLE_ANSI /* Internal for !URI_NO_ANSI */ -#undef URI_ENABLE_UNICODE /* Internal for !URI_NO_UNICODE */ - - - -/* Encoding */ -#ifdef URI_NO_ANSI -# ifdef URI_NO_UNICODE -/* No encoding at all */ -# error URI_NO_ANSI and URI_NO_UNICODE cannot go together. -# else -/* Unicode only */ -# define URI_ENABLE_UNICODE 1 -# endif -#else -# ifdef URI_NO_UNICODE -/* ANSI only */ -# define URI_ENABLE_ANSI 1 -# else -/* Both ANSI and Unicode */ -# define URI_ENABLE_ANSI 1 -# define URI_ENABLE_UNICODE 1 -# endif -#endif - - - -/* Function inlining, not ANSI/ISO C! */ -#if defined(URI_DOXYGEN) -# define URI_INLINE -#elif defined(__INTEL_COMPILER) -/* Intel C/C++ */ -/* http://predef.sourceforge.net/precomp.html#sec20 */ -/* http://www.intel.com/support/performancetools/c/windows/sb/CS-007751.htm#2 */ -/* EDIT 11/5/20. Intel changed __force_inline to __forceinline */ -# define URI_INLINE __forceinline -#elif defined(_MSC_VER) -/* Microsoft Visual C++ */ -/* http://predef.sourceforge.net/precomp.html#sec32 */ -/* http://msdn2.microsoft.com/en-us/library/ms882281.aspx */ -# define URI_INLINE __forceinline -#elif (defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L)) -/* C99, "inline" is a keyword */ -# define URI_INLINE inline -#else -/* No inlining */ -# define URI_INLINE -#endif - - - -#endif /* URI_DEFS_CONFIG_H */ diff --git a/cpp/src/arrow/vendored/uriparser/UriDefsUnicode.h b/cpp/src/arrow/vendored/uriparser/UriDefsUnicode.h deleted file mode 100644 index 8bb8bc2bec31..000000000000 --- a/cpp/src/arrow/vendored/uriparser/UriDefsUnicode.h +++ /dev/null @@ -1,82 +0,0 @@ -/* - * uriparser - RFC 3986 URI parsing library - * - * Copyright (C) 2007, Weijia Song - * Copyright (C) 2007, Sebastian Pipping - * 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 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. - */ - -/** - * @file UriDefsUnicode.h - * Holds definitions for the Unicode pass. - * NOTE: This header is included N times, not once. - */ - -/* Allow multi inclusion */ -#include "UriDefsConfig.h" - - - -#undef URI_CHAR -#define URI_CHAR wchar_t - -#undef _UT -#define _UT(x) L##x - - - -#undef URI_FUNC -#define URI_FUNC(x) uri##x##W - -#undef URI_TYPE -#define URI_TYPE(x) Uri##x##W - - - -#undef URI_STRLEN -#define URI_STRLEN wcslen -#undef URI_STRCPY -#define URI_STRCPY wcscpy -#undef URI_STRCMP -#define URI_STRCMP wcscmp -#undef URI_STRNCMP -#define URI_STRNCMP wcsncmp - -/* TODO Remove on next source-compatibility break */ -#undef URI_SNPRINTF -#if (defined(__WIN32__) || defined(_WIN32) || defined(WIN32)) -# define URI_SNPRINTF _snwprintf -#else -# define URI_SNPRINTF swprintf -#endif diff --git a/cpp/src/arrow/vendored/uriparser/UriEscape.c b/cpp/src/arrow/vendored/uriparser/UriEscape.c deleted file mode 100644 index 46f3fd4ace56..000000000000 --- a/cpp/src/arrow/vendored/uriparser/UriEscape.c +++ /dev/null @@ -1,453 +0,0 @@ -/* - * uriparser - RFC 3986 URI parsing library - * - * Copyright (C) 2007, Weijia Song - * Copyright (C) 2007, Sebastian Pipping - * 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 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. - */ - -/* What encodings are enabled? */ -#include "UriDefsConfig.h" -#if (!defined(URI_PASS_ANSI) && !defined(URI_PASS_UNICODE)) -/* Include SELF twice */ -# ifdef URI_ENABLE_ANSI -# define URI_PASS_ANSI 1 -# include "UriEscape.c" -# undef URI_PASS_ANSI -# endif -# ifdef URI_ENABLE_UNICODE -# define URI_PASS_UNICODE 1 -# include "UriEscape.c" -# undef URI_PASS_UNICODE -# endif -#else -# ifdef URI_PASS_ANSI -# include "UriDefsAnsi.h" -# else -# include "UriDefsUnicode.h" -# include -# endif - - - -#ifndef URI_DOXYGEN -# include "Uri.h" -# include "UriCommon.h" -#endif - - - -URI_CHAR * URI_FUNC(Escape)(const URI_CHAR * in, URI_CHAR * out, - UriBool spaceToPlus, UriBool normalizeBreaks) { - return URI_FUNC(EscapeEx)(in, NULL, out, spaceToPlus, normalizeBreaks); -} - - - -URI_CHAR * URI_FUNC(EscapeEx)(const URI_CHAR * inFirst, - const URI_CHAR * inAfterLast, URI_CHAR * out, - UriBool spaceToPlus, UriBool normalizeBreaks) { - const URI_CHAR * read = inFirst; - URI_CHAR * write = out; - UriBool prevWasCr = URI_FALSE; - if ((out == NULL) || (inFirst == out)) { - return NULL; - } else if (inFirst == NULL) { - if (out != NULL) { - out[0] = _UT('\0'); - } - return out; - } - - for (;;) { - if ((inAfterLast != NULL) && (read >= inAfterLast)) { - write[0] = _UT('\0'); - return write; - } - - switch (read[0]) { - case _UT('\0'): - write[0] = _UT('\0'); - return write; - - case _UT(' '): - if (spaceToPlus) { - write[0] = _UT('+'); - write++; - } else { - write[0] = _UT('%'); - write[1] = _UT('2'); - write[2] = _UT('0'); - write += 3; - } - prevWasCr = URI_FALSE; - break; - - case _UT('a'): /* ALPHA */ - case _UT('A'): - case _UT('b'): - case _UT('B'): - case _UT('c'): - case _UT('C'): - case _UT('d'): - case _UT('D'): - case _UT('e'): - case _UT('E'): - case _UT('f'): - case _UT('F'): - case _UT('g'): - case _UT('G'): - case _UT('h'): - case _UT('H'): - case _UT('i'): - case _UT('I'): - case _UT('j'): - case _UT('J'): - case _UT('k'): - case _UT('K'): - case _UT('l'): - case _UT('L'): - case _UT('m'): - case _UT('M'): - case _UT('n'): - case _UT('N'): - case _UT('o'): - case _UT('O'): - case _UT('p'): - case _UT('P'): - case _UT('q'): - case _UT('Q'): - case _UT('r'): - case _UT('R'): - case _UT('s'): - case _UT('S'): - case _UT('t'): - case _UT('T'): - case _UT('u'): - case _UT('U'): - case _UT('v'): - case _UT('V'): - case _UT('w'): - case _UT('W'): - case _UT('x'): - case _UT('X'): - case _UT('y'): - case _UT('Y'): - case _UT('z'): - case _UT('Z'): - case _UT('0'): /* DIGIT */ - case _UT('1'): - case _UT('2'): - case _UT('3'): - case _UT('4'): - case _UT('5'): - case _UT('6'): - case _UT('7'): - case _UT('8'): - case _UT('9'): - case _UT('-'): /* "-" / "." / "_" / "~" */ - case _UT('.'): - case _UT('_'): - case _UT('~'): - /* Copy unmodified */ - write[0] = read[0]; - write++; - - prevWasCr = URI_FALSE; - break; - - case _UT('\x0a'): - if (normalizeBreaks) { - if (!prevWasCr) { - write[0] = _UT('%'); - write[1] = _UT('0'); - write[2] = _UT('D'); - write[3] = _UT('%'); - write[4] = _UT('0'); - write[5] = _UT('A'); - write += 6; - } - } else { - write[0] = _UT('%'); - write[1] = _UT('0'); - write[2] = _UT('A'); - write += 3; - } - prevWasCr = URI_FALSE; - break; - - case _UT('\x0d'): - if (normalizeBreaks) { - write[0] = _UT('%'); - write[1] = _UT('0'); - write[2] = _UT('D'); - write[3] = _UT('%'); - write[4] = _UT('0'); - write[5] = _UT('A'); - write += 6; - } else { - write[0] = _UT('%'); - write[1] = _UT('0'); - write[2] = _UT('D'); - write += 3; - } - prevWasCr = URI_TRUE; - break; - - default: - /* Percent encode */ - { - const unsigned char code = (unsigned char)read[0]; - write[0] = _UT('%'); - write[1] = URI_FUNC(HexToLetter)(code >> 4); - write[2] = URI_FUNC(HexToLetter)(code & 0x0f); - write += 3; - } - prevWasCr = URI_FALSE; - break; - } - - read++; - } -} - - - -const URI_CHAR * URI_FUNC(UnescapeInPlace)(URI_CHAR * inout) { - return URI_FUNC(UnescapeInPlaceEx)(inout, URI_FALSE, URI_BR_DONT_TOUCH); -} - - - -const URI_CHAR * URI_FUNC(UnescapeInPlaceEx)(URI_CHAR * inout, - UriBool plusToSpace, UriBreakConversion breakConversion) { - URI_CHAR * read = inout; - URI_CHAR * write = inout; - UriBool prevWasCr = URI_FALSE; - - if (inout == NULL) { - return NULL; - } - - for (;;) { - switch (read[0]) { - case _UT('\0'): - if (read > write) { - write[0] = _UT('\0'); - } - return write; - - case _UT('%'): - switch (read[1]) { - case _UT('0'): - case _UT('1'): - case _UT('2'): - case _UT('3'): - case _UT('4'): - case _UT('5'): - case _UT('6'): - case _UT('7'): - case _UT('8'): - case _UT('9'): - case _UT('a'): - case _UT('b'): - case _UT('c'): - case _UT('d'): - case _UT('e'): - case _UT('f'): - case _UT('A'): - case _UT('B'): - case _UT('C'): - case _UT('D'): - case _UT('E'): - case _UT('F'): - switch (read[2]) { - case _UT('0'): - case _UT('1'): - case _UT('2'): - case _UT('3'): - case _UT('4'): - case _UT('5'): - case _UT('6'): - case _UT('7'): - case _UT('8'): - case _UT('9'): - case _UT('a'): - case _UT('b'): - case _UT('c'): - case _UT('d'): - case _UT('e'): - case _UT('f'): - case _UT('A'): - case _UT('B'): - case _UT('C'): - case _UT('D'): - case _UT('E'): - case _UT('F'): - { - /* Percent group found */ - const unsigned char left = URI_FUNC(HexdigToInt)(read[1]); - const unsigned char right = URI_FUNC(HexdigToInt)(read[2]); - const int code = 16 * left + right; - switch (code) { - case 10: - switch (breakConversion) { - case URI_BR_TO_LF: - if (!prevWasCr) { - write[0] = (URI_CHAR)10; - write++; - } - break; - - case URI_BR_TO_CRLF: - if (!prevWasCr) { - write[0] = (URI_CHAR)13; - write[1] = (URI_CHAR)10; - write += 2; - } - break; - - case URI_BR_TO_CR: - if (!prevWasCr) { - write[0] = (URI_CHAR)13; - write++; - } - break; - - case URI_BR_DONT_TOUCH: - default: - write[0] = (URI_CHAR)10; - write++; - - } - prevWasCr = URI_FALSE; - break; - - case 13: - switch (breakConversion) { - case URI_BR_TO_LF: - write[0] = (URI_CHAR)10; - write++; - break; - - case URI_BR_TO_CRLF: - write[0] = (URI_CHAR)13; - write[1] = (URI_CHAR)10; - write += 2; - break; - - case URI_BR_TO_CR: - write[0] = (URI_CHAR)13; - write++; - break; - - case URI_BR_DONT_TOUCH: - default: - write[0] = (URI_CHAR)13; - write++; - - } - prevWasCr = URI_TRUE; - break; - - default: - write[0] = (URI_CHAR)(code); - write++; - - prevWasCr = URI_FALSE; - - } - read += 3; - } - break; - - default: - /* Copy two chars unmodified and */ - /* look at this char again */ - if (read > write) { - write[0] = read[0]; - write[1] = read[1]; - } - read += 2; - write += 2; - - prevWasCr = URI_FALSE; - } - break; - - default: - /* Copy one char unmodified and */ - /* look at this char again */ - if (read > write) { - write[0] = read[0]; - } - read++; - write++; - - prevWasCr = URI_FALSE; - } - break; - - case _UT('+'): - if (plusToSpace) { - /* Convert '+' to ' ' */ - write[0] = _UT(' '); - } else { - /* Copy one char unmodified */ - if (read > write) { - write[0] = read[0]; - } - } - read++; - write++; - - prevWasCr = URI_FALSE; - break; - - default: - /* Copy one char unmodified */ - if (read > write) { - write[0] = read[0]; - } - read++; - write++; - - prevWasCr = URI_FALSE; - } - } -} - - - -#endif diff --git a/cpp/src/arrow/vendored/uriparser/UriFile.c b/cpp/src/arrow/vendored/uriparser/UriFile.c deleted file mode 100644 index abaa84f9adf8..000000000000 --- a/cpp/src/arrow/vendored/uriparser/UriFile.c +++ /dev/null @@ -1,242 +0,0 @@ -/* - * uriparser - RFC 3986 URI parsing library - * - * Copyright (C) 2007, Weijia Song - * Copyright (C) 2007, Sebastian Pipping - * 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 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. - */ - -/* What encodings are enabled? */ -#include "UriDefsConfig.h" -#if (!defined(URI_PASS_ANSI) && !defined(URI_PASS_UNICODE)) -/* Include SELF twice */ -# ifdef URI_ENABLE_ANSI -# define URI_PASS_ANSI 1 -# include "UriFile.c" -# undef URI_PASS_ANSI -# endif -# ifdef URI_ENABLE_UNICODE -# define URI_PASS_UNICODE 1 -# include "UriFile.c" -# undef URI_PASS_UNICODE -# endif -#else -# ifdef URI_PASS_ANSI -# include "UriDefsAnsi.h" -# else -# include "UriDefsUnicode.h" -# include -# endif - - - -#ifndef URI_DOXYGEN -# include "Uri.h" -#endif - - - -#include /* for size_t, avoiding stddef.h for older MSVCs */ - - - -static URI_INLINE int URI_FUNC(FilenameToUriString)(const URI_CHAR * filename, - URI_CHAR * uriString, UriBool fromUnix) { - const URI_CHAR * input = filename; - const URI_CHAR * lastSep = input - 1; - UriBool firstSegment = URI_TRUE; - URI_CHAR * output = uriString; - UriBool absolute; - UriBool is_windows_network; - - if ((filename == NULL) || (uriString == NULL)) { - return URI_ERROR_NULL; - } - - is_windows_network = (filename[0] == _UT('\\')) && (filename[1] == _UT('\\')); - absolute = fromUnix - ? (filename[0] == _UT('/')) - : (((filename[0] != _UT('\0')) && (filename[1] == _UT(':'))) - || is_windows_network); - - if (absolute) { - const URI_CHAR * const prefix = fromUnix - ? _UT("file://") - : is_windows_network - ? _UT("file:") - : _UT("file:///"); - const size_t prefixLen = URI_STRLEN(prefix); - - /* Copy prefix */ - memcpy(uriString, prefix, prefixLen * sizeof(URI_CHAR)); - output += prefixLen; - } - - /* Copy and escape on the fly */ - for (;;) { - if ((input[0] == _UT('\0')) - || (fromUnix && input[0] == _UT('/')) - || (!fromUnix && input[0] == _UT('\\'))) { - /* Copy text after last separator */ - if (lastSep + 1 < input) { - if (!fromUnix && absolute && (firstSegment == URI_TRUE)) { - /* Quick hack to not convert "C:" to "C%3A" */ - const int charsToCopy = (int)(input - (lastSep + 1)); - memcpy(output, lastSep + 1, charsToCopy * sizeof(URI_CHAR)); - output += charsToCopy; - } else { - output = URI_FUNC(EscapeEx)(lastSep + 1, input, output, - URI_FALSE, URI_FALSE); - } - } - firstSegment = URI_FALSE; - } - - if (input[0] == _UT('\0')) { - output[0] = _UT('\0'); - break; - } else if (fromUnix && (input[0] == _UT('/'))) { - /* Copy separators unmodified */ - output[0] = _UT('/'); - output++; - lastSep = input; - } else if (!fromUnix && (input[0] == _UT('\\'))) { - /* Convert backslashes to forward slashes */ - output[0] = _UT('/'); - output++; - lastSep = input; - } - input++; - } - - return URI_SUCCESS; -} - - - -static URI_INLINE int URI_FUNC(UriStringToFilename)(const URI_CHAR * uriString, - URI_CHAR * filename, UriBool toUnix) { - if ((uriString == NULL) || (filename == NULL)) { - return URI_ERROR_NULL; - } - - { - const UriBool file_unknown_slashes = - URI_STRNCMP(uriString, _UT("file:"), URI_STRLEN(_UT("file:"))) == 0; - const UriBool file_one_or_more_slashes = file_unknown_slashes - && (URI_STRNCMP(uriString, _UT("file:/"), URI_STRLEN(_UT("file:/"))) == 0); - const UriBool file_two_or_more_slashes = file_one_or_more_slashes - && (URI_STRNCMP(uriString, _UT("file://"), URI_STRLEN(_UT("file://"))) == 0); - const UriBool file_three_or_more_slashes = file_two_or_more_slashes - && (URI_STRNCMP(uriString, _UT("file:///"), URI_STRLEN(_UT("file:///"))) == 0); - - const size_t charsToSkip = file_two_or_more_slashes - ? file_three_or_more_slashes - ? toUnix - /* file:///bin/bash */ - ? URI_STRLEN(_UT("file://")) - /* file:///E:/Documents%20and%20Settings */ - : URI_STRLEN(_UT("file:///")) - /* file://Server01/Letter.txt */ - : URI_STRLEN(_UT("file://")) - : ((file_one_or_more_slashes && toUnix) - /* file:/bin/bash */ - /* https://tools.ietf.org/html/rfc8089#appendix-B */ - ? URI_STRLEN(_UT("file:")) - : ((! toUnix && file_unknown_slashes && ! file_one_or_more_slashes) - /* file:c:/path/to/file */ - /* https://tools.ietf.org/html/rfc8089#appendix-E.2 */ - ? URI_STRLEN(_UT("file:")) - : 0)); - const size_t charsToCopy = URI_STRLEN(uriString + charsToSkip) + 1; - - const UriBool is_windows_network_with_authority = - (toUnix == URI_FALSE) - && file_two_or_more_slashes - && ! file_three_or_more_slashes; - - URI_CHAR * const unescape_target = is_windows_network_with_authority - ? (filename + 2) - : filename; - - if (is_windows_network_with_authority) { - filename[0] = '\\'; - filename[1] = '\\'; - } - - memcpy(unescape_target, uriString + charsToSkip, charsToCopy * sizeof(URI_CHAR)); - URI_FUNC(UnescapeInPlaceEx)(filename, URI_FALSE, URI_BR_DONT_TOUCH); - } - - /* Convert forward slashes to backslashes */ - if (!toUnix) { - URI_CHAR * walker = filename; - while (walker[0] != _UT('\0')) { - if (walker[0] == _UT('/')) { - walker[0] = _UT('\\'); - } - walker++; - } - } - - return URI_SUCCESS; -} - - - -int URI_FUNC(UnixFilenameToUriString)(const URI_CHAR * filename, URI_CHAR * uriString) { - return URI_FUNC(FilenameToUriString)(filename, uriString, URI_TRUE); -} - - - -int URI_FUNC(WindowsFilenameToUriString)(const URI_CHAR * filename, URI_CHAR * uriString) { - return URI_FUNC(FilenameToUriString)(filename, uriString, URI_FALSE); -} - - - -int URI_FUNC(UriStringToUnixFilename)(const URI_CHAR * uriString, URI_CHAR * filename) { - return URI_FUNC(UriStringToFilename)(uriString, filename, URI_TRUE); -} - - - -int URI_FUNC(UriStringToWindowsFilename)(const URI_CHAR * uriString, URI_CHAR * filename) { - return URI_FUNC(UriStringToFilename)(uriString, filename, URI_FALSE); -} - - - -#endif diff --git a/cpp/src/arrow/vendored/uriparser/UriIp4.c b/cpp/src/arrow/vendored/uriparser/UriIp4.c deleted file mode 100644 index 1d4ab39bc67a..000000000000 --- a/cpp/src/arrow/vendored/uriparser/UriIp4.c +++ /dev/null @@ -1,329 +0,0 @@ -/* - * uriparser - RFC 3986 URI parsing library - * - * Copyright (C) 2007, Weijia Song - * Copyright (C) 2007, Sebastian Pipping - * 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 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. - */ - -/** - * @file UriIp4.c - * Holds the IPv4 parser implementation. - * NOTE: This source file includes itself twice. - */ - -/* What encodings are enabled? */ -#include "UriDefsConfig.h" -#if (!defined(URI_PASS_ANSI) && !defined(URI_PASS_UNICODE)) -/* Include SELF twice */ -# ifdef URI_ENABLE_ANSI -# define URI_PASS_ANSI 1 -# include "UriIp4.c" -# undef URI_PASS_ANSI -# endif -# ifdef URI_ENABLE_UNICODE -# define URI_PASS_UNICODE 1 -# include "UriIp4.c" -# undef URI_PASS_UNICODE -# endif -#else -# ifdef URI_PASS_ANSI -# include "UriDefsAnsi.h" -# else -# include "UriDefsUnicode.h" -# endif - - - -#ifndef URI_DOXYGEN -# include "UriIp4.h" -# include "UriIp4Base.h" -# include "UriBase.h" -#endif - - - -/* Prototypes */ -static const URI_CHAR * URI_FUNC(ParseDecOctet)(UriIp4Parser * parser, - const URI_CHAR * first, const URI_CHAR * afterLast); -static const URI_CHAR * URI_FUNC(ParseDecOctetOne)(UriIp4Parser * parser, - const URI_CHAR * first, const URI_CHAR * afterLast); -static const URI_CHAR * URI_FUNC(ParseDecOctetTwo)(UriIp4Parser * parser, - const URI_CHAR * first, const URI_CHAR * afterLast); -static const URI_CHAR * URI_FUNC(ParseDecOctetThree)(UriIp4Parser * parser, - const URI_CHAR * first, const URI_CHAR * afterLast); -static const URI_CHAR * URI_FUNC(ParseDecOctetFour)(UriIp4Parser * parser, - const URI_CHAR * first, const URI_CHAR * afterLast); - - - -/* - * [ipFourAddress]->[decOctet]<.>[decOctet]<.>[decOctet]<.>[decOctet] - */ -int URI_FUNC(ParseIpFourAddress)(unsigned char * octetOutput, - const URI_CHAR * first, const URI_CHAR * afterLast) { - const URI_CHAR * after; - UriIp4Parser parser; - - /* Essential checks */ - if ((octetOutput == NULL) || (first == NULL) - || (afterLast <= first)) { - return URI_ERROR_SYNTAX; - } - - /* Reset parser */ - parser.stackCount = 0; - - /* Octet #1 */ - after = URI_FUNC(ParseDecOctet)(&parser, first, afterLast); - if ((after == NULL) || (after >= afterLast) || (*after != _UT('.'))) { - return URI_ERROR_SYNTAX; - } - uriStackToOctet(&parser, octetOutput); - - /* Octet #2 */ - after = URI_FUNC(ParseDecOctet)(&parser, after + 1, afterLast); - if ((after == NULL) || (after >= afterLast) || (*after != _UT('.'))) { - return URI_ERROR_SYNTAX; - } - uriStackToOctet(&parser, octetOutput + 1); - - /* Octet #3 */ - after = URI_FUNC(ParseDecOctet)(&parser, after + 1, afterLast); - if ((after == NULL) || (after >= afterLast) || (*after != _UT('.'))) { - return URI_ERROR_SYNTAX; - } - uriStackToOctet(&parser, octetOutput + 2); - - /* Octet #4 */ - after = URI_FUNC(ParseDecOctet)(&parser, after + 1, afterLast); - if (after != afterLast) { - return URI_ERROR_SYNTAX; - } - uriStackToOctet(&parser, octetOutput + 3); - - return URI_SUCCESS; -} - - - -/* - * [decOctet]-><0> - * [decOctet]-><1>[decOctetOne] - * [decOctet]-><2>[decOctetTwo] - * [decOctet]-><3>[decOctetThree] - * [decOctet]-><4>[decOctetThree] - * [decOctet]-><5>[decOctetThree] - * [decOctet]-><6>[decOctetThree] - * [decOctet]-><7>[decOctetThree] - * [decOctet]-><8>[decOctetThree] - * [decOctet]-><9>[decOctetThree] - */ -static URI_INLINE const URI_CHAR * URI_FUNC(ParseDecOctet)(UriIp4Parser * parser, - const URI_CHAR * first, const URI_CHAR * afterLast) { - if (first >= afterLast) { - return NULL; - } - - switch (*first) { - case _UT('0'): - uriPushToStack(parser, 0); - return first + 1; - - case _UT('1'): - uriPushToStack(parser, 1); - return (const URI_CHAR *)URI_FUNC(ParseDecOctetOne)(parser, first + 1, afterLast); - - case _UT('2'): - uriPushToStack(parser, 2); - return (const URI_CHAR *)URI_FUNC(ParseDecOctetTwo)(parser, first + 1, afterLast); - - case _UT('3'): - case _UT('4'): - case _UT('5'): - case _UT('6'): - case _UT('7'): - case _UT('8'): - case _UT('9'): - uriPushToStack(parser, (unsigned char)(9 + *first - _UT('9'))); - return (const URI_CHAR *)URI_FUNC(ParseDecOctetThree)(parser, first + 1, afterLast); - - default: - return NULL; - } -} - - - -/* - * [decOctetOne]-> - * [decOctetOne]->[DIGIT][decOctetThree] - */ -static URI_INLINE const URI_CHAR * URI_FUNC(ParseDecOctetOne)(UriIp4Parser * parser, - const URI_CHAR * first, const URI_CHAR * afterLast) { - if (first >= afterLast) { - return afterLast; - } - - switch (*first) { - case _UT('0'): - case _UT('1'): - case _UT('2'): - case _UT('3'): - case _UT('4'): - case _UT('5'): - case _UT('6'): - case _UT('7'): - case _UT('8'): - case _UT('9'): - uriPushToStack(parser, (unsigned char)(9 + *first - _UT('9'))); - return (const URI_CHAR *)URI_FUNC(ParseDecOctetThree)(parser, first + 1, afterLast); - - default: - return first; - } -} - - - -/* - * [decOctetTwo]-> - * [decOctetTwo]-><0>[decOctetThree] - * [decOctetTwo]-><1>[decOctetThree] - * [decOctetTwo]-><2>[decOctetThree] - * [decOctetTwo]-><3>[decOctetThree] - * [decOctetTwo]-><4>[decOctetThree] - * [decOctetTwo]-><5>[decOctetFour] - * [decOctetTwo]-><6> - * [decOctetTwo]-><7> - * [decOctetTwo]-><8> - * [decOctetTwo]-><9> -*/ -static URI_INLINE const URI_CHAR * URI_FUNC(ParseDecOctetTwo)(UriIp4Parser * parser, - const URI_CHAR * first, const URI_CHAR * afterLast) { - if (first >= afterLast) { - return afterLast; - } - - switch (*first) { - case _UT('0'): - case _UT('1'): - case _UT('2'): - case _UT('3'): - case _UT('4'): - uriPushToStack(parser, (unsigned char)(9 + *first - _UT('9'))); - return (const URI_CHAR *)URI_FUNC(ParseDecOctetThree)(parser, first + 1, afterLast); - - case _UT('5'): - uriPushToStack(parser, 5); - return (const URI_CHAR *)URI_FUNC(ParseDecOctetFour)(parser, first + 1, afterLast); - - case _UT('6'): - case _UT('7'): - case _UT('8'): - case _UT('9'): - uriPushToStack(parser, (unsigned char)(9 + *first - _UT('9'))); - return first + 1; - - default: - return first; - } -} - - - -/* - * [decOctetThree]-> - * [decOctetThree]->[DIGIT] - */ -static URI_INLINE const URI_CHAR * URI_FUNC(ParseDecOctetThree)(UriIp4Parser * parser, - const URI_CHAR * first, const URI_CHAR * afterLast) { - if (first >= afterLast) { - return afterLast; - } - - switch (*first) { - case _UT('0'): - case _UT('1'): - case _UT('2'): - case _UT('3'): - case _UT('4'): - case _UT('5'): - case _UT('6'): - case _UT('7'): - case _UT('8'): - case _UT('9'): - uriPushToStack(parser, (unsigned char)(9 + *first - _UT('9'))); - return first + 1; - - default: - return first; - } -} - - - -/* - * [decOctetFour]-> - * [decOctetFour]-><0> - * [decOctetFour]-><1> - * [decOctetFour]-><2> - * [decOctetFour]-><3> - * [decOctetFour]-><4> - * [decOctetFour]-><5> - */ -static URI_INLINE const URI_CHAR * URI_FUNC(ParseDecOctetFour)(UriIp4Parser * parser, - const URI_CHAR * first, const URI_CHAR * afterLast) { - if (first >= afterLast) { - return afterLast; - } - - switch (*first) { - case _UT('0'): - case _UT('1'): - case _UT('2'): - case _UT('3'): - case _UT('4'): - case _UT('5'): - uriPushToStack(parser, (unsigned char)(9 + *first - _UT('9'))); - return first + 1; - - default: - return first; - } -} - - - -#endif diff --git a/cpp/src/arrow/vendored/uriparser/UriIp4.h b/cpp/src/arrow/vendored/uriparser/UriIp4.h deleted file mode 100644 index e1d7f1e4ad16..000000000000 --- a/cpp/src/arrow/vendored/uriparser/UriIp4.h +++ /dev/null @@ -1,110 +0,0 @@ -/* - * uriparser - RFC 3986 URI parsing library - * - * Copyright (C) 2007, Weijia Song - * Copyright (C) 2007, Sebastian Pipping - * 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 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. - */ - -/** - * @file UriIp4.h - * Holds the IPv4 parser interface. - * NOTE: This header includes itself twice. - */ - -#if (defined(URI_PASS_ANSI) && !defined(URI_IP4_TWICE_H_ANSI)) \ - || (defined(URI_PASS_UNICODE) && !defined(URI_IP4_TWICE_H_UNICODE)) \ - || (!defined(URI_PASS_ANSI) && !defined(URI_PASS_UNICODE)) -/* What encodings are enabled? */ -#include "UriDefsConfig.h" -#if (!defined(URI_PASS_ANSI) && !defined(URI_PASS_UNICODE)) -/* Include SELF twice */ -# ifdef URI_ENABLE_ANSI -# define URI_PASS_ANSI 1 -# include "UriIp4.h" -# undef URI_PASS_ANSI -# endif -# ifdef URI_ENABLE_UNICODE -# define URI_PASS_UNICODE 1 -# include "UriIp4.h" -# undef URI_PASS_UNICODE -# endif -/* Only one pass for each encoding */ -#elif (defined(URI_PASS_ANSI) && !defined(URI_IP4_TWICE_H_ANSI) \ - && defined(URI_ENABLE_ANSI)) || (defined(URI_PASS_UNICODE) \ - && !defined(URI_IP4_TWICE_H_UNICODE) && defined(URI_ENABLE_UNICODE)) -# ifdef URI_PASS_ANSI -# define URI_IP4_TWICE_H_ANSI 1 -# include "UriDefsAnsi.h" -# else -# define URI_IP4_TWICE_H_UNICODE 1 -# include "UriDefsUnicode.h" -# include -# endif - - - -#ifdef __cplusplus -extern "C" { -#endif - - - -#ifndef URI_DOXYGEN -# include "UriBase.h" -#endif - - - -/** - * Converts a IPv4 text representation into four bytes. - * - * @param octetOutput Output destination - * @param first First character of IPv4 text to parse - * @param afterLast Position to stop parsing at - * @return Error code or 0 on success - */ -URI_PUBLIC int URI_FUNC(ParseIpFourAddress)(unsigned char * octetOutput, - const URI_CHAR * first, const URI_CHAR * afterLast); - - - -#ifdef __cplusplus -} -#endif - - - -#endif -#endif diff --git a/cpp/src/arrow/vendored/uriparser/UriIp4Base.c b/cpp/src/arrow/vendored/uriparser/UriIp4Base.c deleted file mode 100644 index f0662465d7ea..000000000000 --- a/cpp/src/arrow/vendored/uriparser/UriIp4Base.c +++ /dev/null @@ -1,96 +0,0 @@ -/* - * uriparser - RFC 3986 URI parsing library - * - * Copyright (C) 2007, Weijia Song - * Copyright (C) 2007, Sebastian Pipping - * 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 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. - */ - -/** - * @file UriIp4Base.c - * Holds code independent of the encoding pass. - */ - -#ifndef URI_DOXYGEN -# include "UriIp4Base.h" -#endif - - - -void uriStackToOctet(UriIp4Parser * parser, unsigned char * octet) { - switch (parser->stackCount) { - case 1: - *octet = parser->stackOne; - break; - - case 2: - *octet = parser->stackOne * 10 - + parser->stackTwo; - break; - - case 3: - *octet = parser->stackOne * 100 - + parser->stackTwo * 10 - + parser->stackThree; - break; - - default: - ; - } - parser->stackCount = 0; -} - - - -void uriPushToStack(UriIp4Parser * parser, unsigned char digit) { - switch (parser->stackCount) { - case 0: - parser->stackOne = digit; - parser->stackCount = 1; - break; - - case 1: - parser->stackTwo = digit; - parser->stackCount = 2; - break; - - case 2: - parser->stackThree = digit; - parser->stackCount = 3; - break; - - default: - ; - } -} diff --git a/cpp/src/arrow/vendored/uriparser/UriIp4Base.h b/cpp/src/arrow/vendored/uriparser/UriIp4Base.h deleted file mode 100644 index bef028f7c943..000000000000 --- a/cpp/src/arrow/vendored/uriparser/UriIp4Base.h +++ /dev/null @@ -1,59 +0,0 @@ -/* - * uriparser - RFC 3986 URI parsing library - * - * Copyright (C) 2007, Weijia Song - * Copyright (C) 2007, Sebastian Pipping - * 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 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. - */ - -#ifndef URI_IP4_BASE_H -#define URI_IP4_BASE_H 1 - - - -typedef struct UriIp4ParserStruct { - unsigned char stackCount; - unsigned char stackOne; - unsigned char stackTwo; - unsigned char stackThree; -} UriIp4Parser; - - - -void uriPushToStack(UriIp4Parser * parser, unsigned char digit); -void uriStackToOctet(UriIp4Parser * parser, unsigned char * octet); - - - -#endif /* URI_IP4_BASE_H */ diff --git a/cpp/src/arrow/vendored/uriparser/UriMemory.c b/cpp/src/arrow/vendored/uriparser/UriMemory.c deleted file mode 100644 index 2d23f1b6f6e8..000000000000 --- a/cpp/src/arrow/vendored/uriparser/UriMemory.c +++ /dev/null @@ -1,468 +0,0 @@ -/* - * uriparser - RFC 3986 URI parsing library - * - * Copyright (C) 2018, Weijia Song - * Copyright (C) 2018, Sebastian Pipping - * 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 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. - */ - -/** - * @file UriMemory.c - * Holds memory manager implementation. - */ - -#include "config.h" - -#ifdef HAVE_REALLOCARRAY -# ifndef _GNU_SOURCE -# define _GNU_SOURCE 1 -# endif -#endif - -#include -#include - - - -#ifndef URI_DOXYGEN -# include "UriMemory.h" -#endif - - - -#define URI_CHECK_ALLOC_OVERFLOW(total_size, nmemb, size) \ - do { \ - /* check for unsigned overflow */ \ - if ((nmemb != 0) && (total_size / nmemb != size)) { \ - errno = ENOMEM; \ - return NULL; \ - } \ - } while (0) - - - -static void * uriDefaultMalloc(UriMemoryManager * URI_UNUSED(memory), - size_t size) { - return malloc(size); -} - - - -static void * uriDefaultCalloc(UriMemoryManager * URI_UNUSED(memory), - size_t nmemb, size_t size) { - return calloc(nmemb, size); -} - - - -static void * uriDefaultRealloc(UriMemoryManager * URI_UNUSED(memory), - void * ptr, size_t size) { - return realloc(ptr, size); -} - - - -static void * uriDefaultReallocarray(UriMemoryManager * URI_UNUSED(memory), - void * ptr, size_t nmemb, size_t size) { -#ifdef HAVE_REALLOCARRAY - return reallocarray(ptr, nmemb, size); -#else - const size_t total_size = nmemb * size; - - URI_CHECK_ALLOC_OVERFLOW(total_size, nmemb, size); /* may return */ - - return realloc(ptr, total_size); -#endif -} - - - -static void uriDefaultFree(UriMemoryManager * URI_UNUSED(memory), - void * ptr) { - free(ptr); -} - - - -UriBool uriMemoryManagerIsComplete(const UriMemoryManager * memory) { - return (memory - && memory->malloc - && memory->calloc - && memory->realloc - && memory->reallocarray - && memory->free) ? URI_TRUE : URI_FALSE; -} - - - -void * uriEmulateCalloc(UriMemoryManager * memory, size_t nmemb, size_t size) { - void * buffer; - const size_t total_size = nmemb * size; - - if (memory == NULL) { - errno = EINVAL; - return NULL; - } - - URI_CHECK_ALLOC_OVERFLOW(total_size, nmemb, size); /* may return */ - - buffer = memory->malloc(memory, total_size); - if (buffer == NULL) { - /* errno set by malloc */ - return NULL; - } - memset(buffer, 0, total_size); - return buffer; -} - - - -void * uriEmulateReallocarray(UriMemoryManager * memory, - void * ptr, size_t nmemb, size_t size) { - const size_t total_size = nmemb * size; - - if (memory == NULL) { - errno = EINVAL; - return NULL; - } - - URI_CHECK_ALLOC_OVERFLOW(total_size, nmemb, size); /* may return */ - - return memory->realloc(memory, ptr, total_size); -} - - - -static void * uriDecorateMalloc(UriMemoryManager * memory, - size_t size) { - UriMemoryManager * backend; - const size_t extraBytes = sizeof(size_t); - void * buffer; - - if (memory == NULL) { - errno = EINVAL; - return NULL; - } - - /* check for unsigned overflow */ - if (size > ((size_t)-1) - extraBytes) { - errno = ENOMEM; - return NULL; - } - - backend = (UriMemoryManager *)memory->userData; - if (backend == NULL) { - errno = EINVAL; - return NULL; - } - - buffer = backend->malloc(backend, extraBytes + size); - if (buffer == NULL) { - return NULL; - } - - *(size_t *)buffer = size; - - return (char *)buffer + extraBytes; -} - - - -static void * uriDecorateRealloc(UriMemoryManager * memory, - void * ptr, size_t size) { - void * newBuffer; - size_t prevSize; - - if (memory == NULL) { - errno = EINVAL; - return NULL; - } - - /* man realloc: "If ptr is NULL, then the call is equivalent to - * malloc(size), for *all* values of size" */ - if (ptr == NULL) { - return memory->malloc(memory, size); - } - - /* man realloc: "If size is equal to zero, and ptr is *not* NULL, - * then the call is equivalent to free(ptr)." */ - if (size == 0) { - memory->free(memory, ptr); - return NULL; - } - - prevSize = *((size_t *)((char *)ptr - sizeof(size_t))); - - /* Anything to do? */ - if (size <= prevSize) { - return ptr; - } - - newBuffer = memory->malloc(memory, size); - if (newBuffer == NULL) { - /* errno set by malloc */ - return NULL; - } - - memcpy(newBuffer, ptr, prevSize); - - memory->free(memory, ptr); - - return newBuffer; -} - - - -static void uriDecorateFree(UriMemoryManager * memory, void * ptr) { - UriMemoryManager * backend; - - if ((ptr == NULL) || (memory == NULL)) { - return; - } - - backend = (UriMemoryManager *)memory->userData; - if (backend == NULL) { - return; - } - - backend->free(backend, (char *)ptr - sizeof(size_t)); -} - - - -int uriCompleteMemoryManager(UriMemoryManager * memory, - UriMemoryManager * backend) { - if ((memory == NULL) || (backend == NULL)) { - return URI_ERROR_NULL; - } - - if ((backend->malloc == NULL) || (backend->free == NULL)) { - return URI_ERROR_MEMORY_MANAGER_INCOMPLETE; - } - - memory->calloc = uriEmulateCalloc; - memory->reallocarray = uriEmulateReallocarray; - - memory->malloc = uriDecorateMalloc; - memory->realloc = uriDecorateRealloc; - memory->free = uriDecorateFree; - - memory->userData = backend; - - return URI_SUCCESS; -} - - - -int uriTestMemoryManager(UriMemoryManager * memory) { - const size_t mallocSize = 7; - const size_t callocNmemb = 3; - const size_t callocSize = 5; - const size_t callocTotalSize = callocNmemb * callocSize; - const size_t reallocSize = 11; - const size_t reallocarrayNmemb = 5; - const size_t reallocarraySize = 7; - const size_t reallocarrayTotal = reallocarrayNmemb * reallocarraySize; - size_t index; - char * buffer; - - if (memory == NULL) { - return URI_ERROR_NULL; - } - - if (uriMemoryManagerIsComplete(memory) != URI_TRUE) { - return URI_ERROR_MEMORY_MANAGER_INCOMPLETE; - } - - /* malloc + free*/ - buffer = memory->malloc(memory, mallocSize); - if (buffer == NULL) { - return URI_ERROR_MEMORY_MANAGER_FAULTY; - } - buffer[mallocSize - 1] = '\xF1'; - memory->free(memory, buffer); - buffer = NULL; - - /* calloc + free */ - buffer = memory->calloc(memory, callocNmemb, callocSize); - if (buffer == NULL) { - return URI_ERROR_MEMORY_MANAGER_FAULTY; - } - for (index = 0; index < callocTotalSize; index++) { /* all zeros? */ - if (buffer[index] != '\0') { - return URI_ERROR_MEMORY_MANAGER_FAULTY; - } - } - buffer[callocTotalSize - 1] = '\xF2'; - memory->free(memory, buffer); - buffer = NULL; - - /* malloc + realloc + free */ - buffer = memory->malloc(memory, mallocSize); - if (buffer == NULL) { - return URI_ERROR_MEMORY_MANAGER_FAULTY; - } - for (index = 0; index < mallocSize; index++) { - buffer[index] = '\xF3'; - } - buffer = memory->realloc(memory, buffer, reallocSize); - if (buffer == NULL) { - return URI_ERROR_MEMORY_MANAGER_FAULTY; - } - for (index = 0; index < mallocSize; index++) { /* previous content? */ - if (buffer[index] != '\xF3') { - return URI_ERROR_MEMORY_MANAGER_FAULTY; - } - } - buffer[reallocSize - 1] = '\xF4'; - memory->free(memory, buffer); - buffer = NULL; - - /* malloc + realloc ptr!=NULL size==0 (equals free) */ - buffer = memory->malloc(memory, mallocSize); - if (buffer == NULL) { - return URI_ERROR_MEMORY_MANAGER_FAULTY; - } - buffer[mallocSize - 1] = '\xF5'; - memory->realloc(memory, buffer, 0); - buffer = NULL; - - /* realloc ptr==NULL size!=0 (equals malloc) + free */ - buffer = memory->realloc(memory, NULL, mallocSize); - if (buffer == NULL) { - return URI_ERROR_MEMORY_MANAGER_FAULTY; - } - buffer[mallocSize - 1] = '\xF6'; - memory->free(memory, buffer); - buffer = NULL; - - /* realloc ptr==NULL size==0 (equals malloc) + free */ - buffer = memory->realloc(memory, NULL, 0); - if (buffer != NULL) { - memory->free(memory, buffer); - buffer = NULL; - } - - /* malloc + reallocarray + free */ - buffer = memory->malloc(memory, mallocSize); - if (buffer == NULL) { - return URI_ERROR_MEMORY_MANAGER_FAULTY; - } - for (index = 0; index < mallocSize; index++) { - buffer[index] = '\xF7'; - } - buffer = memory->reallocarray(memory, buffer, reallocarrayNmemb, - reallocarraySize); - if (buffer == NULL) { - return URI_ERROR_MEMORY_MANAGER_FAULTY; - } - for (index = 0; index < mallocSize; index++) { /* previous content? */ - if (buffer[index] != '\xF7') { - return URI_ERROR_MEMORY_MANAGER_FAULTY; - } - } - buffer[reallocarrayTotal - 1] = '\xF8'; - memory->free(memory, buffer); - buffer = NULL; - - /* malloc + reallocarray ptr!=NULL nmemb==0 size!=0 (equals free) */ - buffer = memory->malloc(memory, mallocSize); - if (buffer == NULL) { - return URI_ERROR_MEMORY_MANAGER_FAULTY; - } - buffer[mallocSize - 1] = '\xF9'; - memory->reallocarray(memory, buffer, 0, reallocarraySize); - buffer = NULL; - - /* malloc + reallocarray ptr!=NULL nmemb!=0 size==0 (equals free) */ - buffer = memory->malloc(memory, mallocSize); - if (buffer == NULL) { - return URI_ERROR_MEMORY_MANAGER_FAULTY; - } - buffer[mallocSize - 1] = '\xFA'; - memory->reallocarray(memory, buffer, reallocarrayNmemb, 0); - buffer = NULL; - - /* malloc + reallocarray ptr!=NULL nmemb==0 size==0 (equals free) */ - buffer = memory->malloc(memory, mallocSize); - if (buffer == NULL) { - return URI_ERROR_MEMORY_MANAGER_FAULTY; - } - buffer[mallocSize - 1] = '\xFB'; - memory->reallocarray(memory, buffer, 0, 0); - buffer = NULL; - - /* reallocarray ptr==NULL nmemb!=0 size!=0 (equals malloc) + free */ - buffer = memory->reallocarray(memory, NULL, callocNmemb, callocSize); - if (buffer == NULL) { - return URI_ERROR_MEMORY_MANAGER_FAULTY; - } - buffer[callocTotalSize - 1] = '\xFC'; - memory->free(memory, buffer); - buffer = NULL; - - /* reallocarray ptr==NULL nmemb==0 size!=0 (equals malloc) + free */ - buffer = memory->reallocarray(memory, NULL, 0, callocSize); - if (buffer != NULL) { - memory->free(memory, buffer); - buffer = NULL; - } - - /* reallocarray ptr==NULL nmemb!=0 size==0 (equals malloc) + free */ - buffer = memory->reallocarray(memory, NULL, callocNmemb, 0); - if (buffer != NULL) { - memory->free(memory, buffer); - buffer = NULL; - } - - /* reallocarray ptr==NULL nmemb==0 size==0 (equals malloc) + free */ - buffer = memory->reallocarray(memory, NULL, 0, 0); - if (buffer != NULL) { - memory->free(memory, buffer); - buffer = NULL; - } - - return URI_SUCCESS; -} - - - -/*extern*/ UriMemoryManager defaultMemoryManager = { - uriDefaultMalloc, - uriDefaultCalloc, - uriDefaultRealloc, - uriDefaultReallocarray, - uriDefaultFree, - NULL /* userData */ -}; diff --git a/cpp/src/arrow/vendored/uriparser/UriMemory.h b/cpp/src/arrow/vendored/uriparser/UriMemory.h deleted file mode 100644 index 5d6bf678415f..000000000000 --- a/cpp/src/arrow/vendored/uriparser/UriMemory.h +++ /dev/null @@ -1,78 +0,0 @@ -/* - * uriparser - RFC 3986 URI parsing library - * - * Copyright (C) 2018, Weijia Song - * Copyright (C) 2018, Sebastian Pipping - * 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 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. - */ - -#ifndef URI_MEMORY_H -#define URI_MEMORY_H 1 - - - -#ifndef URI_DOXYGEN -# include "Uri.h" -#endif - - - -#define URI_CHECK_MEMORY_MANAGER(memory) \ - do { \ - if (memory == NULL) { \ - memory = &defaultMemoryManager; \ - } else if (uriMemoryManagerIsComplete(memory) != URI_TRUE) { \ - return URI_ERROR_MEMORY_MANAGER_INCOMPLETE; \ - } \ - } while (0) - - - -#ifdef __cplusplus -# define URIPARSER_EXTERN extern "C" -#else -# define URIPARSER_EXTERN extern -#endif - -URIPARSER_EXTERN UriMemoryManager defaultMemoryManager; - -#undef URIPARSER_EXTERN - - - -UriBool uriMemoryManagerIsComplete(const UriMemoryManager * memory); - - - -#endif /* URI_MEMORY_H */ diff --git a/cpp/src/arrow/vendored/uriparser/UriNormalize.c b/cpp/src/arrow/vendored/uriparser/UriNormalize.c deleted file mode 100644 index 3fc74920399a..000000000000 --- a/cpp/src/arrow/vendored/uriparser/UriNormalize.c +++ /dev/null @@ -1,771 +0,0 @@ -/* - * uriparser - RFC 3986 URI parsing library - * - * Copyright (C) 2007, Weijia Song - * Copyright (C) 2007, Sebastian Pipping - * 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 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. - */ - -/** - * @file UriNormalize.c - * Holds the RFC 3986 %URI normalization implementation. - * NOTE: This source file includes itself twice. - */ - -/* What encodings are enabled? */ -#include "UriDefsConfig.h" -#if (!defined(URI_PASS_ANSI) && !defined(URI_PASS_UNICODE)) -/* Include SELF twice */ -# ifdef URI_ENABLE_ANSI -# define URI_PASS_ANSI 1 -# include "UriNormalize.c" -# undef URI_PASS_ANSI -# endif -# ifdef URI_ENABLE_UNICODE -# define URI_PASS_UNICODE 1 -# include "UriNormalize.c" -# undef URI_PASS_UNICODE -# endif -#else -# ifdef URI_PASS_ANSI -# include "UriDefsAnsi.h" -# else -# include "UriDefsUnicode.h" -# include -# endif - - - -#ifndef URI_DOXYGEN -# include "Uri.h" -# include "UriNormalizeBase.h" -# include "UriCommon.h" -# include "UriMemory.h" -#endif - - - -#include - - - -static int URI_FUNC(NormalizeSyntaxEngine)(URI_TYPE(Uri) * uri, unsigned int inMask, - unsigned int * outMask, UriMemoryManager * memory); - -static UriBool URI_FUNC(MakeRangeOwner)(unsigned int * doneMask, - unsigned int maskTest, URI_TYPE(TextRange) * range, - UriMemoryManager * memory); -static UriBool URI_FUNC(MakeOwner)(URI_TYPE(Uri) * uri, - unsigned int * doneMask, UriMemoryManager * memory); - -static void URI_FUNC(FixPercentEncodingInplace)(const URI_CHAR * first, - const URI_CHAR ** afterLast); -static UriBool URI_FUNC(FixPercentEncodingMalloc)(const URI_CHAR ** first, - const URI_CHAR ** afterLast, UriMemoryManager * memory); -static void URI_FUNC(FixPercentEncodingEngine)( - const URI_CHAR * inFirst, const URI_CHAR * inAfterLast, - const URI_CHAR * outFirst, const URI_CHAR ** outAfterLast); - -static UriBool URI_FUNC(ContainsUppercaseLetters)(const URI_CHAR * first, - const URI_CHAR * afterLast); -static UriBool URI_FUNC(ContainsUglyPercentEncoding)(const URI_CHAR * first, - const URI_CHAR * afterLast); - -static void URI_FUNC(LowercaseInplace)(const URI_CHAR * first, - const URI_CHAR * afterLast); -static UriBool URI_FUNC(LowercaseMalloc)(const URI_CHAR ** first, - const URI_CHAR ** afterLast, UriMemoryManager * memory); - -static void URI_FUNC(PreventLeakage)(URI_TYPE(Uri) * uri, - unsigned int revertMask, UriMemoryManager * memory); - - - -static URI_INLINE void URI_FUNC(PreventLeakage)(URI_TYPE(Uri) * uri, - unsigned int revertMask, UriMemoryManager * memory) { - if (revertMask & URI_NORMALIZE_SCHEME) { - memory->free(memory, (URI_CHAR *)uri->scheme.first); - uri->scheme.first = NULL; - uri->scheme.afterLast = NULL; - } - - if (revertMask & URI_NORMALIZE_USER_INFO) { - memory->free(memory, (URI_CHAR *)uri->userInfo.first); - uri->userInfo.first = NULL; - uri->userInfo.afterLast = NULL; - } - - if (revertMask & URI_NORMALIZE_HOST) { - if (uri->hostData.ipFuture.first != NULL) { - /* IPvFuture */ - memory->free(memory, (URI_CHAR *)uri->hostData.ipFuture.first); - uri->hostData.ipFuture.first = NULL; - uri->hostData.ipFuture.afterLast = NULL; - uri->hostText.first = NULL; - uri->hostText.afterLast = NULL; - } else if ((uri->hostText.first != NULL) - && (uri->hostData.ip4 == NULL) - && (uri->hostData.ip6 == NULL)) { - /* Regname */ - memory->free(memory, (URI_CHAR *)uri->hostText.first); - uri->hostText.first = NULL; - uri->hostText.afterLast = NULL; - } - } - - /* NOTE: Port cannot happen! */ - - if (revertMask & URI_NORMALIZE_PATH) { - URI_TYPE(PathSegment) * walker = uri->pathHead; - while (walker != NULL) { - URI_TYPE(PathSegment) * const next = walker->next; - if (walker->text.afterLast > walker->text.first) { - memory->free(memory, (URI_CHAR *)walker->text.first); - } - memory->free(memory, walker); - walker = next; - } - uri->pathHead = NULL; - uri->pathTail = NULL; - } - - if (revertMask & URI_NORMALIZE_QUERY) { - memory->free(memory, (URI_CHAR *)uri->query.first); - uri->query.first = NULL; - uri->query.afterLast = NULL; - } - - if (revertMask & URI_NORMALIZE_FRAGMENT) { - memory->free(memory, (URI_CHAR *)uri->fragment.first); - uri->fragment.first = NULL; - uri->fragment.afterLast = NULL; - } -} - - - -static URI_INLINE UriBool URI_FUNC(ContainsUppercaseLetters)(const URI_CHAR * first, - const URI_CHAR * afterLast) { - if ((first != NULL) && (afterLast != NULL) && (afterLast > first)) { - const URI_CHAR * i = first; - for (; i < afterLast; i++) { - /* 6.2.2.1 Case Normalization: uppercase letters in scheme or host */ - if ((*i >= _UT('A')) && (*i <= _UT('Z'))) { - return URI_TRUE; - } - } - } - return URI_FALSE; -} - - - -static URI_INLINE UriBool URI_FUNC(ContainsUglyPercentEncoding)(const URI_CHAR * first, - const URI_CHAR * afterLast) { - if ((first != NULL) && (afterLast != NULL) && (afterLast > first)) { - const URI_CHAR * i = first; - for (; i + 2 < afterLast; i++) { - if (i[0] == _UT('%')) { - /* 6.2.2.1 Case Normalization: * - * lowercase percent-encodings */ - if (((i[1] >= _UT('a')) && (i[1] <= _UT('f'))) - || ((i[2] >= _UT('a')) && (i[2] <= _UT('f')))) { - return URI_TRUE; - } else { - /* 6.2.2.2 Percent-Encoding Normalization: * - * percent-encoded unreserved characters */ - const unsigned char left = URI_FUNC(HexdigToInt)(i[1]); - const unsigned char right = URI_FUNC(HexdigToInt)(i[2]); - const int code = 16 * left + right; - if (uriIsUnreserved(code)) { - return URI_TRUE; - } - } - } - } - } - return URI_FALSE; -} - - - -static URI_INLINE void URI_FUNC(LowercaseInplace)(const URI_CHAR * first, - const URI_CHAR * afterLast) { - if ((first != NULL) && (afterLast != NULL) && (afterLast > first)) { - URI_CHAR * i = (URI_CHAR *)first; - const int lowerUpperDiff = (_UT('a') - _UT('A')); - for (; i < afterLast; i++) { - if ((*i >= _UT('A')) && (*i <=_UT('Z'))) { - *i = (URI_CHAR)(*i + lowerUpperDiff); - } - } - } -} - - - -static URI_INLINE UriBool URI_FUNC(LowercaseMalloc)(const URI_CHAR ** first, - const URI_CHAR ** afterLast, UriMemoryManager * memory) { - int lenInChars; - const int lowerUpperDiff = (_UT('a') - _UT('A')); - URI_CHAR * buffer; - int i = 0; - - if ((first == NULL) || (afterLast == NULL) || (*first == NULL) - || (*afterLast == NULL)) { - return URI_FALSE; - } - - lenInChars = (int)(*afterLast - *first); - if (lenInChars == 0) { - return URI_TRUE; - } else if (lenInChars < 0) { - return URI_FALSE; - } - - buffer = memory->malloc(memory, lenInChars * sizeof(URI_CHAR)); - if (buffer == NULL) { - return URI_FALSE; - } - - for (; i < lenInChars; i++) { - if (((*first)[i] >= _UT('A')) && ((*first)[i] <=_UT('Z'))) { - buffer[i] = (URI_CHAR)((*first)[i] + lowerUpperDiff); - } else { - buffer[i] = (*first)[i]; - } - } - - *first = buffer; - *afterLast = buffer + lenInChars; - return URI_TRUE; -} - - - -/* NOTE: Implementation must stay inplace-compatible */ -static URI_INLINE void URI_FUNC(FixPercentEncodingEngine)( - const URI_CHAR * inFirst, const URI_CHAR * inAfterLast, - const URI_CHAR * outFirst, const URI_CHAR ** outAfterLast) { - URI_CHAR * write = (URI_CHAR *)outFirst; - const int lenInChars = (int)(inAfterLast - inFirst); - int i = 0; - - /* All but last two */ - for (; i + 2 < lenInChars; i++) { - if (inFirst[i] != _UT('%')) { - write[0] = inFirst[i]; - write++; - } else { - /* 6.2.2.2 Percent-Encoding Normalization: * - * percent-encoded unreserved characters */ - const URI_CHAR one = inFirst[i + 1]; - const URI_CHAR two = inFirst[i + 2]; - const unsigned char left = URI_FUNC(HexdigToInt)(one); - const unsigned char right = URI_FUNC(HexdigToInt)(two); - const int code = 16 * left + right; - if (uriIsUnreserved(code)) { - write[0] = (URI_CHAR)(code); - write++; - } else { - /* 6.2.2.1 Case Normalization: * - * lowercase percent-encodings */ - write[0] = _UT('%'); - write[1] = URI_FUNC(HexToLetter)(left); - write[2] = URI_FUNC(HexToLetter)(right); - write += 3; - } - - i += 2; /* For the two chars of the percent group we just ate */ - } - } - - /* Last two */ - for (; i < lenInChars; i++) { - write[0] = inFirst[i]; - write++; - } - - *outAfterLast = write; -} - - - -static URI_INLINE void URI_FUNC(FixPercentEncodingInplace)(const URI_CHAR * first, - const URI_CHAR ** afterLast) { - /* Death checks */ - if ((first == NULL) || (afterLast == NULL) || (*afterLast == NULL)) { - return; - } - - /* Fix inplace */ - URI_FUNC(FixPercentEncodingEngine)(first, *afterLast, first, afterLast); -} - - - -static URI_INLINE UriBool URI_FUNC(FixPercentEncodingMalloc)(const URI_CHAR ** first, - const URI_CHAR ** afterLast, UriMemoryManager * memory) { - int lenInChars; - URI_CHAR * buffer; - - /* Death checks */ - if ((first == NULL) || (afterLast == NULL) - || (*first == NULL) || (*afterLast == NULL)) { - return URI_FALSE; - } - - /* Old text length */ - lenInChars = (int)(*afterLast - *first); - if (lenInChars == 0) { - return URI_TRUE; - } else if (lenInChars < 0) { - return URI_FALSE; - } - - /* New buffer */ - buffer = memory->malloc(memory, lenInChars * sizeof(URI_CHAR)); - if (buffer == NULL) { - return URI_FALSE; - } - - /* Fix on copy */ - URI_FUNC(FixPercentEncodingEngine)(*first, *afterLast, buffer, afterLast); - *first = buffer; - return URI_TRUE; -} - - - -static URI_INLINE UriBool URI_FUNC(MakeRangeOwner)(unsigned int * doneMask, - unsigned int maskTest, URI_TYPE(TextRange) * range, - UriMemoryManager * memory) { - if (((*doneMask & maskTest) == 0) - && (range->first != NULL) - && (range->afterLast != NULL) - && (range->afterLast > range->first)) { - const int lenInChars = (int)(range->afterLast - range->first); - const int lenInBytes = lenInChars * sizeof(URI_CHAR); - URI_CHAR * dup = memory->malloc(memory, lenInBytes); - if (dup == NULL) { - return URI_FALSE; /* Raises malloc error */ - } - memcpy(dup, range->first, lenInBytes); - range->first = dup; - range->afterLast = dup + lenInChars; - *doneMask |= maskTest; - } - return URI_TRUE; -} - - - -static URI_INLINE UriBool URI_FUNC(MakeOwner)(URI_TYPE(Uri) * uri, - unsigned int * doneMask, UriMemoryManager * memory) { - URI_TYPE(PathSegment) * walker = uri->pathHead; - if (!URI_FUNC(MakeRangeOwner)(doneMask, URI_NORMALIZE_SCHEME, - &(uri->scheme), memory) - || !URI_FUNC(MakeRangeOwner)(doneMask, URI_NORMALIZE_USER_INFO, - &(uri->userInfo), memory) - || !URI_FUNC(MakeRangeOwner)(doneMask, URI_NORMALIZE_QUERY, - &(uri->query), memory) - || !URI_FUNC(MakeRangeOwner)(doneMask, URI_NORMALIZE_FRAGMENT, - &(uri->fragment), memory)) { - return URI_FALSE; /* Raises malloc error */ - } - - /* Host */ - if ((*doneMask & URI_NORMALIZE_HOST) == 0) { - if ((uri->hostData.ip4 == NULL) - && (uri->hostData.ip6 == NULL)) { - if (uri->hostData.ipFuture.first != NULL) { - /* IPvFuture */ - if (!URI_FUNC(MakeRangeOwner)(doneMask, URI_NORMALIZE_HOST, - &(uri->hostData.ipFuture), memory)) { - return URI_FALSE; /* Raises malloc error */ - } - uri->hostText.first = uri->hostData.ipFuture.first; - uri->hostText.afterLast = uri->hostData.ipFuture.afterLast; - } else if (uri->hostText.first != NULL) { - /* Regname */ - if (!URI_FUNC(MakeRangeOwner)(doneMask, URI_NORMALIZE_HOST, - &(uri->hostText), memory)) { - return URI_FALSE; /* Raises malloc error */ - } - } - } - } - - /* Path */ - if ((*doneMask & URI_NORMALIZE_PATH) == 0) { - while (walker != NULL) { - if (!URI_FUNC(MakeRangeOwner)(doneMask, 0, &(walker->text), memory)) { - /* Free allocations done so far and kill path */ - - /* Kill path to one before walker (if any) */ - URI_TYPE(PathSegment) * ranger = uri->pathHead; - while (ranger != walker) { - URI_TYPE(PathSegment) * const next = ranger->next; - if ((ranger->text.first != NULL) - && (ranger->text.afterLast != NULL) - && (ranger->text.afterLast > ranger->text.first)) { - memory->free(memory, (URI_CHAR *)ranger->text.first); - } - memory->free(memory, ranger); - ranger = next; - } - - /* Kill path from walker */ - while (walker != NULL) { - URI_TYPE(PathSegment) * const next = walker->next; - memory->free(memory, walker); - walker = next; - } - - uri->pathHead = NULL; - uri->pathTail = NULL; - return URI_FALSE; /* Raises malloc error */ - } - walker = walker->next; - } - *doneMask |= URI_NORMALIZE_PATH; - } - - /* Port text, must come last so we don't have to undo that one if it fails. * - * Otherwise we would need and extra enum flag for it although the port * - * cannot go unnormalized... */ - if (!URI_FUNC(MakeRangeOwner)(doneMask, 0, &(uri->portText), memory)) { - return URI_FALSE; /* Raises malloc error */ - } - - return URI_TRUE; -} - - - -unsigned int URI_FUNC(NormalizeSyntaxMaskRequired)(const URI_TYPE(Uri) * uri) { - unsigned int outMask = URI_NORMALIZED; /* for NULL uri */ - URI_FUNC(NormalizeSyntaxMaskRequiredEx)(uri, &outMask); - return outMask; -} - - - -int URI_FUNC(NormalizeSyntaxMaskRequiredEx)(const URI_TYPE(Uri) * uri, - unsigned int * outMask) { - UriMemoryManager * const memory = NULL; /* no use of memory manager */ - -#if defined(__GNUC__) && ((__GNUC__ > 4) \ - || ((__GNUC__ == 4) && defined(__GNUC_MINOR__) && (__GNUC_MINOR__ >= 2))) - /* Slower code that fixes a warning, not sure if this is a smart idea */ - URI_TYPE(Uri) writeableClone; -#endif - - if ((uri == NULL) || (outMask == NULL)) { - return URI_ERROR_NULL; - } - -#if defined(__GNUC__) && ((__GNUC__ > 4) \ - || ((__GNUC__ == 4) && defined(__GNUC_MINOR__) && (__GNUC_MINOR__ >= 2))) - /* Slower code that fixes a warning, not sure if this is a smart idea */ - memcpy(&writeableClone, uri, 1 * sizeof(URI_TYPE(Uri))); - URI_FUNC(NormalizeSyntaxEngine)(&writeableClone, 0, outMask, memory); -#else - URI_FUNC(NormalizeSyntaxEngine)((URI_TYPE(Uri) *)uri, 0, outMask, memory); -#endif - return URI_SUCCESS; -} - - - -int URI_FUNC(NormalizeSyntaxEx)(URI_TYPE(Uri) * uri, unsigned int mask) { - return URI_FUNC(NormalizeSyntaxExMm)(uri, mask, NULL); -} - - - -int URI_FUNC(NormalizeSyntaxExMm)(URI_TYPE(Uri) * uri, unsigned int mask, - UriMemoryManager * memory) { - URI_CHECK_MEMORY_MANAGER(memory); /* may return */ - return URI_FUNC(NormalizeSyntaxEngine)(uri, mask, NULL, memory); -} - - - -int URI_FUNC(NormalizeSyntax)(URI_TYPE(Uri) * uri) { - return URI_FUNC(NormalizeSyntaxEx)(uri, (unsigned int)-1); -} - - - -static URI_INLINE int URI_FUNC(NormalizeSyntaxEngine)(URI_TYPE(Uri) * uri, - unsigned int inMask, unsigned int * outMask, - UriMemoryManager * memory) { - unsigned int doneMask = URI_NORMALIZED; - - /* Not just doing inspection? -> memory manager required! */ - if (outMask == NULL) { - assert(memory != NULL); - } - - if (uri == NULL) { - if (outMask != NULL) { - *outMask = URI_NORMALIZED; - return URI_SUCCESS; - } else { - return URI_ERROR_NULL; - } - } - - if (outMask != NULL) { - /* Reset mask */ - *outMask = URI_NORMALIZED; - } else if (inMask == URI_NORMALIZED) { - /* Nothing to do */ - return URI_SUCCESS; - } - - /* Scheme, host */ - if (outMask != NULL) { - const UriBool normalizeScheme = URI_FUNC(ContainsUppercaseLetters)( - uri->scheme.first, uri->scheme.afterLast); - const UriBool normalizeHostCase = URI_FUNC(ContainsUppercaseLetters)( - uri->hostText.first, uri->hostText.afterLast); - if (normalizeScheme) { - *outMask |= URI_NORMALIZE_SCHEME; - } - - if (normalizeHostCase) { - *outMask |= URI_NORMALIZE_HOST; - } else { - const UriBool normalizeHostPrecent = URI_FUNC(ContainsUglyPercentEncoding)( - uri->hostText.first, uri->hostText.afterLast); - if (normalizeHostPrecent) { - *outMask |= URI_NORMALIZE_HOST; - } - } - } else { - /* Scheme */ - if ((inMask & URI_NORMALIZE_SCHEME) && (uri->scheme.first != NULL)) { - if (uri->owner) { - URI_FUNC(LowercaseInplace)(uri->scheme.first, uri->scheme.afterLast); - } else { - if (!URI_FUNC(LowercaseMalloc)(&(uri->scheme.first), &(uri->scheme.afterLast), memory)) { - URI_FUNC(PreventLeakage)(uri, doneMask, memory); - return URI_ERROR_MALLOC; - } - doneMask |= URI_NORMALIZE_SCHEME; - } - } - - /* Host */ - if (inMask & URI_NORMALIZE_HOST) { - if (uri->hostData.ipFuture.first != NULL) { - /* IPvFuture */ - if (uri->owner) { - URI_FUNC(LowercaseInplace)(uri->hostData.ipFuture.first, - uri->hostData.ipFuture.afterLast); - } else { - if (!URI_FUNC(LowercaseMalloc)(&(uri->hostData.ipFuture.first), - &(uri->hostData.ipFuture.afterLast), memory)) { - URI_FUNC(PreventLeakage)(uri, doneMask, memory); - return URI_ERROR_MALLOC; - } - doneMask |= URI_NORMALIZE_HOST; - } - uri->hostText.first = uri->hostData.ipFuture.first; - uri->hostText.afterLast = uri->hostData.ipFuture.afterLast; - } else if ((uri->hostText.first != NULL) - && (uri->hostData.ip4 == NULL) - && (uri->hostData.ip6 == NULL)) { - /* Regname */ - if (uri->owner) { - URI_FUNC(FixPercentEncodingInplace)(uri->hostText.first, - &(uri->hostText.afterLast)); - } else { - if (!URI_FUNC(FixPercentEncodingMalloc)( - &(uri->hostText.first), - &(uri->hostText.afterLast), - memory)) { - URI_FUNC(PreventLeakage)(uri, doneMask, memory); - return URI_ERROR_MALLOC; - } - doneMask |= URI_NORMALIZE_HOST; - } - - URI_FUNC(LowercaseInplace)(uri->hostText.first, - uri->hostText.afterLast); - } - } - } - - /* User info */ - if (outMask != NULL) { - const UriBool normalizeUserInfo = URI_FUNC(ContainsUglyPercentEncoding)( - uri->userInfo.first, uri->userInfo.afterLast); - if (normalizeUserInfo) { - *outMask |= URI_NORMALIZE_USER_INFO; - } - } else { - if ((inMask & URI_NORMALIZE_USER_INFO) && (uri->userInfo.first != NULL)) { - if (uri->owner) { - URI_FUNC(FixPercentEncodingInplace)(uri->userInfo.first, &(uri->userInfo.afterLast)); - } else { - if (!URI_FUNC(FixPercentEncodingMalloc)(&(uri->userInfo.first), - &(uri->userInfo.afterLast), memory)) { - URI_FUNC(PreventLeakage)(uri, doneMask, memory); - return URI_ERROR_MALLOC; - } - doneMask |= URI_NORMALIZE_USER_INFO; - } - } - } - - /* Path */ - if (outMask != NULL) { - const URI_TYPE(PathSegment) * walker = uri->pathHead; - while (walker != NULL) { - const URI_CHAR * const first = walker->text.first; - const URI_CHAR * const afterLast = walker->text.afterLast; - if ((first != NULL) - && (afterLast != NULL) - && (afterLast > first) - && ( - (((afterLast - first) == 1) - && (first[0] == _UT('.'))) - || - (((afterLast - first) == 2) - && (first[0] == _UT('.')) - && (first[1] == _UT('.'))) - || - URI_FUNC(ContainsUglyPercentEncoding)(first, afterLast) - )) { - *outMask |= URI_NORMALIZE_PATH; - break; - } - walker = walker->next; - } - } else if (inMask & URI_NORMALIZE_PATH) { - URI_TYPE(PathSegment) * walker; - const UriBool relative = ((uri->scheme.first == NULL) - && !uri->absolutePath) ? URI_TRUE : URI_FALSE; - - /* Fix percent-encoding for each segment */ - walker = uri->pathHead; - if (uri->owner) { - while (walker != NULL) { - URI_FUNC(FixPercentEncodingInplace)(walker->text.first, &(walker->text.afterLast)); - walker = walker->next; - } - } else { - while (walker != NULL) { - if (!URI_FUNC(FixPercentEncodingMalloc)(&(walker->text.first), - &(walker->text.afterLast), memory)) { - URI_FUNC(PreventLeakage)(uri, doneMask, memory); - return URI_ERROR_MALLOC; - } - walker = walker->next; - } - doneMask |= URI_NORMALIZE_PATH; - } - - /* 6.2.2.3 Path Segment Normalization */ - if (!URI_FUNC(RemoveDotSegmentsEx)(uri, relative, - (uri->owner == URI_TRUE) - || ((doneMask & URI_NORMALIZE_PATH) != 0), - memory)) { - URI_FUNC(PreventLeakage)(uri, doneMask, memory); - return URI_ERROR_MALLOC; - } - URI_FUNC(FixEmptyTrailSegment)(uri, memory); - } - - /* Query, fragment */ - if (outMask != NULL) { - const UriBool normalizeQuery = URI_FUNC(ContainsUglyPercentEncoding)( - uri->query.first, uri->query.afterLast); - const UriBool normalizeFragment = URI_FUNC(ContainsUglyPercentEncoding)( - uri->fragment.first, uri->fragment.afterLast); - if (normalizeQuery) { - *outMask |= URI_NORMALIZE_QUERY; - } - - if (normalizeFragment) { - *outMask |= URI_NORMALIZE_FRAGMENT; - } - } else { - /* Query */ - if ((inMask & URI_NORMALIZE_QUERY) && (uri->query.first != NULL)) { - if (uri->owner) { - URI_FUNC(FixPercentEncodingInplace)(uri->query.first, &(uri->query.afterLast)); - } else { - if (!URI_FUNC(FixPercentEncodingMalloc)(&(uri->query.first), - &(uri->query.afterLast), memory)) { - URI_FUNC(PreventLeakage)(uri, doneMask, memory); - return URI_ERROR_MALLOC; - } - doneMask |= URI_NORMALIZE_QUERY; - } - } - - /* Fragment */ - if ((inMask & URI_NORMALIZE_FRAGMENT) && (uri->fragment.first != NULL)) { - if (uri->owner) { - URI_FUNC(FixPercentEncodingInplace)(uri->fragment.first, &(uri->fragment.afterLast)); - } else { - if (!URI_FUNC(FixPercentEncodingMalloc)(&(uri->fragment.first), - &(uri->fragment.afterLast), memory)) { - URI_FUNC(PreventLeakage)(uri, doneMask, memory); - return URI_ERROR_MALLOC; - } - doneMask |= URI_NORMALIZE_FRAGMENT; - } - } - } - - /* Dup all not duped yet */ - if ((outMask == NULL) && !uri->owner) { - if (!URI_FUNC(MakeOwner)(uri, &doneMask, memory)) { - URI_FUNC(PreventLeakage)(uri, doneMask, memory); - return URI_ERROR_MALLOC; - } - uri->owner = URI_TRUE; - } - - return URI_SUCCESS; -} - - - -#endif diff --git a/cpp/src/arrow/vendored/uriparser/UriNormalizeBase.c b/cpp/src/arrow/vendored/uriparser/UriNormalizeBase.c deleted file mode 100644 index 8dbe7fd19379..000000000000 --- a/cpp/src/arrow/vendored/uriparser/UriNormalizeBase.c +++ /dev/null @@ -1,119 +0,0 @@ -/* - * uriparser - RFC 3986 URI parsing library - * - * Copyright (C) 2007, Weijia Song - * Copyright (C) 2007, Sebastian Pipping - * 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 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. - */ - -#ifndef URI_DOXYGEN -# include "UriNormalizeBase.h" -#endif - - - -UriBool uriIsUnreserved(int code) { - switch (code) { - case L'a': /* ALPHA */ - case L'A': - case L'b': - case L'B': - case L'c': - case L'C': - case L'd': - case L'D': - case L'e': - case L'E': - case L'f': - case L'F': - case L'g': - case L'G': - case L'h': - case L'H': - case L'i': - case L'I': - case L'j': - case L'J': - case L'k': - case L'K': - case L'l': - case L'L': - case L'm': - case L'M': - case L'n': - case L'N': - case L'o': - case L'O': - case L'p': - case L'P': - case L'q': - case L'Q': - case L'r': - case L'R': - case L's': - case L'S': - case L't': - case L'T': - case L'u': - case L'U': - case L'v': - case L'V': - case L'w': - case L'W': - case L'x': - case L'X': - case L'y': - case L'Y': - case L'z': - case L'Z': - case L'0': /* DIGIT */ - case L'1': - case L'2': - case L'3': - case L'4': - case L'5': - case L'6': - case L'7': - case L'8': - case L'9': - case L'-': /* "-" / "." / "_" / "~" */ - case L'.': - case L'_': - case L'~': - return URI_TRUE; - - default: - return URI_FALSE; - } -} diff --git a/cpp/src/arrow/vendored/uriparser/UriNormalizeBase.h b/cpp/src/arrow/vendored/uriparser/UriNormalizeBase.h deleted file mode 100644 index a1290756409b..000000000000 --- a/cpp/src/arrow/vendored/uriparser/UriNormalizeBase.h +++ /dev/null @@ -1,53 +0,0 @@ -/* - * uriparser - RFC 3986 URI parsing library - * - * Copyright (C) 2007, Weijia Song - * Copyright (C) 2007, Sebastian Pipping - * 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 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. - */ - -#ifndef URI_NORMALIZE_BASE_H -#define URI_NORMALIZE_BASE_H 1 - - - -#include "UriBase.h" - - - -UriBool uriIsUnreserved(int code); - - - -#endif /* URI_NORMALIZE_BASE_H */ diff --git a/cpp/src/arrow/vendored/uriparser/UriParse.c b/cpp/src/arrow/vendored/uriparser/UriParse.c deleted file mode 100644 index f5972d8f4d34..000000000000 --- a/cpp/src/arrow/vendored/uriparser/UriParse.c +++ /dev/null @@ -1,2410 +0,0 @@ -/* - * uriparser - RFC 3986 URI parsing library - * - * Copyright (C) 2007, Weijia Song - * Copyright (C) 2007, Sebastian Pipping - * 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 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. - */ - -/** - * @file UriParse.c - * Holds the RFC 3986 %URI parsing implementation. - * NOTE: This source file includes itself twice. - */ - -/* What encodings are enabled? */ -#include "UriDefsConfig.h" -#if (!defined(URI_PASS_ANSI) && !defined(URI_PASS_UNICODE)) -/* Include SELF twice */ -# ifdef URI_ENABLE_ANSI -# define URI_PASS_ANSI 1 -# include "UriParse.c" -# undef URI_PASS_ANSI -# endif -# ifdef URI_ENABLE_UNICODE -# define URI_PASS_UNICODE 1 -# include "UriParse.c" -# undef URI_PASS_UNICODE -# endif -#else -# ifdef URI_PASS_ANSI -# include "UriDefsAnsi.h" -# else -# include "UriDefsUnicode.h" -# include -# endif - - - -#ifndef URI_DOXYGEN -# include "Uri.h" -# include "UriIp4.h" -# include "UriCommon.h" -# include "UriMemory.h" -# include "UriParseBase.h" -#endif - - - -#define URI_SET_DIGIT \ - _UT('0'): \ - case _UT('1'): \ - case _UT('2'): \ - case _UT('3'): \ - case _UT('4'): \ - case _UT('5'): \ - case _UT('6'): \ - case _UT('7'): \ - case _UT('8'): \ - case _UT('9') - -#define URI_SET_HEX_LETTER_UPPER \ - _UT('A'): \ - case _UT('B'): \ - case _UT('C'): \ - case _UT('D'): \ - case _UT('E'): \ - case _UT('F') - -#define URI_SET_HEX_LETTER_LOWER \ - _UT('a'): \ - case _UT('b'): \ - case _UT('c'): \ - case _UT('d'): \ - case _UT('e'): \ - case _UT('f') - -#define URI_SET_HEXDIG \ - URI_SET_DIGIT: \ - case URI_SET_HEX_LETTER_UPPER: \ - case URI_SET_HEX_LETTER_LOWER - -#define URI_SET_ALPHA \ - URI_SET_HEX_LETTER_UPPER: \ - case URI_SET_HEX_LETTER_LOWER: \ - case _UT('g'): \ - case _UT('G'): \ - case _UT('h'): \ - case _UT('H'): \ - case _UT('i'): \ - case _UT('I'): \ - case _UT('j'): \ - case _UT('J'): \ - case _UT('k'): \ - case _UT('K'): \ - case _UT('l'): \ - case _UT('L'): \ - case _UT('m'): \ - case _UT('M'): \ - case _UT('n'): \ - case _UT('N'): \ - case _UT('o'): \ - case _UT('O'): \ - case _UT('p'): \ - case _UT('P'): \ - case _UT('q'): \ - case _UT('Q'): \ - case _UT('r'): \ - case _UT('R'): \ - case _UT('s'): \ - case _UT('S'): \ - case _UT('t'): \ - case _UT('T'): \ - case _UT('u'): \ - case _UT('U'): \ - case _UT('v'): \ - case _UT('V'): \ - case _UT('w'): \ - case _UT('W'): \ - case _UT('x'): \ - case _UT('X'): \ - case _UT('y'): \ - case _UT('Y'): \ - case _UT('z'): \ - case _UT('Z') - - - -static const URI_CHAR * URI_FUNC(ParseAuthority)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast, UriMemoryManager * memory); -static const URI_CHAR * URI_FUNC(ParseAuthorityTwo)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast); -static const URI_CHAR * URI_FUNC(ParseHexZero)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast); -static const URI_CHAR * URI_FUNC(ParseHierPart)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast, UriMemoryManager * memory); -static const URI_CHAR * URI_FUNC(ParseIpFutLoop)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast, UriMemoryManager * memory); -static const URI_CHAR * URI_FUNC(ParseIpFutStopGo)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast, UriMemoryManager * memory); -static const URI_CHAR * URI_FUNC(ParseIpLit2)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast, UriMemoryManager * memory); -static const URI_CHAR * URI_FUNC(ParseIPv6address2)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast, UriMemoryManager * memory); -static const URI_CHAR * URI_FUNC(ParseMustBeSegmentNzNc)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast, UriMemoryManager * memory); -static const URI_CHAR * URI_FUNC(ParseOwnHost)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast, UriMemoryManager * memory); -static const URI_CHAR * URI_FUNC(ParseOwnHost2)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast, UriMemoryManager * memory); -static const URI_CHAR * URI_FUNC(ParseOwnHostUserInfo)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast, UriMemoryManager * memory); -static const URI_CHAR * URI_FUNC(ParseOwnHostUserInfoNz)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast, UriMemoryManager * memory); -static const URI_CHAR * URI_FUNC(ParseOwnPortUserInfo)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast, UriMemoryManager * memory); -static const URI_CHAR * URI_FUNC(ParseOwnUserInfo)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast, UriMemoryManager * memory); -static const URI_CHAR * URI_FUNC(ParsePartHelperTwo)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast, UriMemoryManager * memory); -static const URI_CHAR * URI_FUNC(ParsePathAbsEmpty)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast, UriMemoryManager * memory); -static const URI_CHAR * URI_FUNC(ParsePathAbsNoLeadSlash)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast, UriMemoryManager * memory); -static const URI_CHAR * URI_FUNC(ParsePathRootless)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast, UriMemoryManager * memory); -static const URI_CHAR * URI_FUNC(ParsePchar)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast, UriMemoryManager * memory); -static const URI_CHAR * URI_FUNC(ParsePctEncoded)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast, UriMemoryManager * memory); -static const URI_CHAR * URI_FUNC(ParsePctSubUnres)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast, UriMemoryManager * memory); -static const URI_CHAR * URI_FUNC(ParsePort)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast); -static const URI_CHAR * URI_FUNC(ParseQueryFrag)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast, UriMemoryManager * memory); -static const URI_CHAR * URI_FUNC(ParseSegment)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast, UriMemoryManager * memory); -static const URI_CHAR * URI_FUNC(ParseSegmentNz)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast, UriMemoryManager * memory); -static const URI_CHAR * URI_FUNC(ParseSegmentNzNcOrScheme2)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast, UriMemoryManager * memory); -static const URI_CHAR * URI_FUNC(ParseUriReference)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast, UriMemoryManager * memory); -static const URI_CHAR * URI_FUNC(ParseUriTail)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast, UriMemoryManager * memory); -static const URI_CHAR * URI_FUNC(ParseUriTailTwo)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast, UriMemoryManager * memory); -static const URI_CHAR * URI_FUNC(ParseZeroMoreSlashSegs)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast, UriMemoryManager * memory); - -static UriBool URI_FUNC(OnExitOwnHost2)(URI_TYPE(ParserState) * state, const URI_CHAR * first, UriMemoryManager * memory); -static UriBool URI_FUNC(OnExitOwnHostUserInfo)(URI_TYPE(ParserState) * state, const URI_CHAR * first, UriMemoryManager * memory); -static UriBool URI_FUNC(OnExitOwnPortUserInfo)(URI_TYPE(ParserState) * state, const URI_CHAR * first, UriMemoryManager * memory); -static UriBool URI_FUNC(OnExitSegmentNzNcOrScheme2)(URI_TYPE(ParserState) * state, const URI_CHAR * first, UriMemoryManager * memory); -static void URI_FUNC(OnExitPartHelperTwo)(URI_TYPE(ParserState) * state); - -static void URI_FUNC(ResetParserStateExceptUri)(URI_TYPE(ParserState) * state); - -static UriBool URI_FUNC(PushPathSegment)(URI_TYPE(ParserState) * state, - const URI_CHAR * first, const URI_CHAR * afterLast, - UriMemoryManager * memory); - -static void URI_FUNC(StopSyntax)(URI_TYPE(ParserState) * state, const URI_CHAR * errorPos, UriMemoryManager * memory); -static void URI_FUNC(StopMalloc)(URI_TYPE(ParserState) * state, UriMemoryManager * memory); - -static int URI_FUNC(ParseUriExMm)(URI_TYPE(ParserState) * state, - const URI_CHAR * first, const URI_CHAR * afterLast, - UriMemoryManager * memory); - - - -static URI_INLINE void URI_FUNC(StopSyntax)(URI_TYPE(ParserState) * state, - const URI_CHAR * errorPos, UriMemoryManager * memory) { - URI_FUNC(FreeUriMembersMm)(state->uri, memory); - state->errorPos = errorPos; - state->errorCode = URI_ERROR_SYNTAX; -} - - - -static URI_INLINE void URI_FUNC(StopMalloc)(URI_TYPE(ParserState) * state, UriMemoryManager * memory) { - URI_FUNC(FreeUriMembersMm)(state->uri, memory); - state->errorPos = NULL; - state->errorCode = URI_ERROR_MALLOC; -} - - - -/* - * [authority]-><[>[ipLit2][authorityTwo] - * [authority]->[ownHostUserInfoNz] - * [authority]-> - */ -static URI_INLINE const URI_CHAR * URI_FUNC(ParseAuthority)( - URI_TYPE(ParserState) * state, const URI_CHAR * first, - const URI_CHAR * afterLast, UriMemoryManager * memory) { - if (first >= afterLast) { - /* "" regname host */ - state->uri->hostText.first = URI_FUNC(SafeToPointTo); - state->uri->hostText.afterLast = URI_FUNC(SafeToPointTo); - return afterLast; - } - - switch (*first) { - case _UT('['): - { - const URI_CHAR * const afterIpLit2 - = URI_FUNC(ParseIpLit2)(state, first + 1, afterLast, memory); - if (afterIpLit2 == NULL) { - return NULL; - } - state->uri->hostText.first = first + 1; /* HOST BEGIN */ - return URI_FUNC(ParseAuthorityTwo)(state, afterIpLit2, afterLast); - } - - case _UT('!'): - case _UT('$'): - case _UT('%'): - case _UT('&'): - case _UT('('): - case _UT(')'): - case _UT('-'): - case _UT('*'): - case _UT(','): - case _UT('.'): - case _UT(':'): - case _UT(';'): - case _UT('@'): - case _UT('\''): - case _UT('_'): - case _UT('~'): - case _UT('+'): - case _UT('='): - case URI_SET_DIGIT: - case URI_SET_ALPHA: - state->uri->userInfo.first = first; /* USERINFO BEGIN */ - return URI_FUNC(ParseOwnHostUserInfoNz)(state, first, afterLast, memory); - - default: - /* "" regname host */ - state->uri->hostText.first = URI_FUNC(SafeToPointTo); - state->uri->hostText.afterLast = URI_FUNC(SafeToPointTo); - return first; - } -} - - - -/* - * [authorityTwo]-><:>[port] - * [authorityTwo]-> - */ -static URI_INLINE const URI_CHAR * URI_FUNC(ParseAuthorityTwo)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast) { - if (first >= afterLast) { - return afterLast; - } - - switch (*first) { - case _UT(':'): - { - const URI_CHAR * const afterPort = URI_FUNC(ParsePort)(state, first + 1, afterLast); - if (afterPort == NULL) { - return NULL; - } - state->uri->portText.first = first + 1; /* PORT BEGIN */ - state->uri->portText.afterLast = afterPort; /* PORT END */ - return afterPort; - } - - default: - return first; - } -} - - - -/* - * [hexZero]->[HEXDIG][hexZero] - * [hexZero]-> - */ -static const URI_CHAR * URI_FUNC(ParseHexZero)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast) { - if (first >= afterLast) { - return afterLast; - } - - switch (*first) { - case URI_SET_HEXDIG: - return URI_FUNC(ParseHexZero)(state, first + 1, afterLast); - - default: - return first; - } -} - - - -/* - * [hierPart]->[pathRootless] - * [hierPart]->[partHelperTwo] - * [hierPart]-> - */ -static URI_INLINE const URI_CHAR * URI_FUNC(ParseHierPart)( - URI_TYPE(ParserState) * state, const URI_CHAR * first, - const URI_CHAR * afterLast, UriMemoryManager * memory) { - if (first >= afterLast) { - return afterLast; - } - - switch (*first) { - case _UT('!'): - case _UT('$'): - case _UT('%'): - case _UT('&'): - case _UT('('): - case _UT(')'): - case _UT('-'): - case _UT('*'): - case _UT(','): - case _UT('.'): - case _UT(':'): - case _UT(';'): - case _UT('@'): - case _UT('\''): - case _UT('_'): - case _UT('~'): - case _UT('+'): - case _UT('='): - case URI_SET_DIGIT: - case URI_SET_ALPHA: - return URI_FUNC(ParsePathRootless)(state, first, afterLast, memory); - - case _UT('/'): - return URI_FUNC(ParsePartHelperTwo)(state, first + 1, afterLast, memory); - - default: - return first; - } -} - - - -/* - * [ipFutLoop]->[subDelims][ipFutStopGo] - * [ipFutLoop]->[unreserved][ipFutStopGo] - * [ipFutLoop]-><:>[ipFutStopGo] - */ -static const URI_CHAR * URI_FUNC(ParseIpFutLoop)(URI_TYPE(ParserState) * state, - const URI_CHAR * first, const URI_CHAR * afterLast, - UriMemoryManager * memory) { - if (first >= afterLast) { - URI_FUNC(StopSyntax)(state, afterLast, memory); - return NULL; - } - - switch (*first) { - case _UT('!'): - case _UT('$'): - case _UT('&'): - case _UT('('): - case _UT(')'): - case _UT('-'): - case _UT('*'): - case _UT(','): - case _UT('.'): - case _UT(':'): - case _UT(';'): - case _UT('\''): - case _UT('_'): - case _UT('~'): - case _UT('+'): - case _UT('='): - case URI_SET_DIGIT: - case URI_SET_ALPHA: - return URI_FUNC(ParseIpFutStopGo)(state, first + 1, afterLast, memory); - - default: - URI_FUNC(StopSyntax)(state, first, memory); - return NULL; - } -} - - - -/* - * [ipFutStopGo]->[ipFutLoop] - * [ipFutStopGo]-> - */ -static const URI_CHAR * URI_FUNC(ParseIpFutStopGo)( - URI_TYPE(ParserState) * state, - const URI_CHAR * first, const URI_CHAR * afterLast, - UriMemoryManager * memory) { - if (first >= afterLast) { - return afterLast; - } - - switch (*first) { - case _UT('!'): - case _UT('$'): - case _UT('&'): - case _UT('('): - case _UT(')'): - case _UT('-'): - case _UT('*'): - case _UT(','): - case _UT('.'): - case _UT(':'): - case _UT(';'): - case _UT('\''): - case _UT('_'): - case _UT('~'): - case _UT('+'): - case _UT('='): - case URI_SET_DIGIT: - case URI_SET_ALPHA: - return URI_FUNC(ParseIpFutLoop)(state, first, afterLast, memory); - - default: - return first; - } -} - - - -/* - * [ipFuture]->[HEXDIG][hexZero]<.>[ipFutLoop] - */ -static const URI_CHAR * URI_FUNC(ParseIpFuture)(URI_TYPE(ParserState) * state, - const URI_CHAR * first, const URI_CHAR * afterLast, - UriMemoryManager * memory) { - if (first >= afterLast) { - URI_FUNC(StopSyntax)(state, afterLast, memory); - return NULL; - } - - /* - First character has already been - checked before entering this rule. - - switch (*first) { - case _UT('v'): - */ - if (first + 1 >= afterLast) { - URI_FUNC(StopSyntax)(state, afterLast, memory); - return NULL; - } - - switch (first[1]) { - case URI_SET_HEXDIG: - { - const URI_CHAR * afterIpFutLoop; - const URI_CHAR * const afterHexZero - = URI_FUNC(ParseHexZero)(state, first + 2, afterLast); - if (afterHexZero == NULL) { - return NULL; - } - if (afterHexZero >= afterLast) { - URI_FUNC(StopSyntax)(state, afterLast, memory); - return NULL; - } - if (*afterHexZero != _UT('.')) { - URI_FUNC(StopSyntax)(state, afterHexZero, memory); - return NULL; - } - state->uri->hostText.first = first; /* HOST BEGIN */ - state->uri->hostData.ipFuture.first = first; /* IPFUTURE BEGIN */ - afterIpFutLoop = URI_FUNC(ParseIpFutLoop)(state, afterHexZero + 1, afterLast, memory); - if (afterIpFutLoop == NULL) { - return NULL; - } - state->uri->hostText.afterLast = afterIpFutLoop; /* HOST END */ - state->uri->hostData.ipFuture.afterLast = afterIpFutLoop; /* IPFUTURE END */ - return afterIpFutLoop; - } - - default: - URI_FUNC(StopSyntax)(state, first + 1, memory); - return NULL; - } - - /* - default: - URI_FUNC(StopSyntax)(state, first, memory); - return NULL; - } - */ -} - - - -/* - * [ipLit2]->[ipFuture]<]> - * [ipLit2]->[IPv6address2] - */ -static URI_INLINE const URI_CHAR * URI_FUNC(ParseIpLit2)( - URI_TYPE(ParserState) * state, const URI_CHAR * first, - const URI_CHAR * afterLast, UriMemoryManager * memory) { - if (first >= afterLast) { - URI_FUNC(StopSyntax)(state, afterLast, memory); - return NULL; - } - - switch (*first) { - case _UT('v'): - { - const URI_CHAR * const afterIpFuture - = URI_FUNC(ParseIpFuture)(state, first, afterLast, memory); - if (afterIpFuture == NULL) { - return NULL; - } - if (afterIpFuture >= afterLast) { - URI_FUNC(StopSyntax)(state, afterLast, memory); - return NULL; - } - if (*afterIpFuture != _UT(']')) { - URI_FUNC(StopSyntax)(state, afterIpFuture, memory); - return NULL; - } - return afterIpFuture + 1; - } - - case _UT(':'): - case _UT(']'): - case URI_SET_HEXDIG: - state->uri->hostData.ip6 = memory->malloc(memory, 1 * sizeof(UriIp6)); /* Freed when stopping on parse error */ - if (state->uri->hostData.ip6 == NULL) { - URI_FUNC(StopMalloc)(state, memory); - return NULL; - } - return URI_FUNC(ParseIPv6address2)(state, first, afterLast, memory); - - default: - URI_FUNC(StopSyntax)(state, first, memory); - return NULL; - } -} - - - -/* - * [IPv6address2]->..<]> - */ -static const URI_CHAR * URI_FUNC(ParseIPv6address2)( - URI_TYPE(ParserState) * state, - const URI_CHAR * first, const URI_CHAR * afterLast, - UriMemoryManager * memory) { - int zipperEver = 0; - int quadsDone = 0; - int digitCount = 0; - unsigned char digitHistory[4]; - int ip4OctetsDone = 0; - - unsigned char quadsAfterZipper[14]; - int quadsAfterZipperCount = 0; - - - for (;;) { - if (first >= afterLast) { - URI_FUNC(StopSyntax)(state, afterLast, memory); - return NULL; - } - - /* Inside IPv4 part? */ - if (ip4OctetsDone > 0) { - /* Eat rest of IPv4 address */ - for (;;) { - switch (*first) { - case URI_SET_DIGIT: - if (digitCount == 4) { - URI_FUNC(StopSyntax)(state, first, memory); - return NULL; - } - digitHistory[digitCount++] = (unsigned char)(9 + *first - _UT('9')); - break; - - case _UT('.'): - if ((ip4OctetsDone == 4) /* NOTE! */ - || (digitCount == 0) - || (digitCount == 4)) { - /* Invalid digit or octet count */ - URI_FUNC(StopSyntax)(state, first, memory); - return NULL; - } else if ((digitCount > 1) - && (digitHistory[0] == 0)) { - /* Leading zero */ - URI_FUNC(StopSyntax)(state, first - digitCount, memory); - return NULL; - } else if ((digitCount > 2) - && (digitHistory[1] == 0)) { - /* Leading zero */ - URI_FUNC(StopSyntax)(state, first - digitCount + 1, memory); - return NULL; - } else if ((digitCount == 3) - && (100 * digitHistory[0] - + 10 * digitHistory[1] - + digitHistory[2] > 255)) { - /* Octet value too large */ - if (digitHistory[0] > 2) { - URI_FUNC(StopSyntax)(state, first - 3, memory); - } else if (digitHistory[1] > 5) { - URI_FUNC(StopSyntax)(state, first - 2, memory); - } else { - URI_FUNC(StopSyntax)(state, first - 1, memory); - } - return NULL; - } - - /* Copy IPv4 octet */ - state->uri->hostData.ip6->data[16 - 4 + ip4OctetsDone] = uriGetOctetValue(digitHistory, digitCount); - digitCount = 0; - ip4OctetsDone++; - break; - - case _UT(']'): - if ((ip4OctetsDone != 3) /* NOTE! */ - || (digitCount == 0) - || (digitCount == 4)) { - /* Invalid digit or octet count */ - URI_FUNC(StopSyntax)(state, first, memory); - return NULL; - } else if ((digitCount > 1) - && (digitHistory[0] == 0)) { - /* Leading zero */ - URI_FUNC(StopSyntax)(state, first - digitCount, memory); - return NULL; - } else if ((digitCount > 2) - && (digitHistory[1] == 0)) { - /* Leading zero */ - URI_FUNC(StopSyntax)(state, first - digitCount + 1, memory); - return NULL; - } else if ((digitCount == 3) - && (100 * digitHistory[0] - + 10 * digitHistory[1] - + digitHistory[2] > 255)) { - /* Octet value too large */ - if (digitHistory[0] > 2) { - URI_FUNC(StopSyntax)(state, first - 3, memory); - } else if (digitHistory[1] > 5) { - URI_FUNC(StopSyntax)(state, first - 2, memory); - } else { - URI_FUNC(StopSyntax)(state, first - 1, memory); - } - return NULL; - } - - state->uri->hostText.afterLast = first; /* HOST END */ - - /* Copy missing quads right before IPv4 */ - memcpy(state->uri->hostData.ip6->data + 16 - 4 - 2 * quadsAfterZipperCount, - quadsAfterZipper, 2 * quadsAfterZipperCount); - - /* Copy last IPv4 octet */ - state->uri->hostData.ip6->data[16 - 4 + 3] = uriGetOctetValue(digitHistory, digitCount); - - return first + 1; - - default: - URI_FUNC(StopSyntax)(state, first, memory); - return NULL; - } - first++; - - if (first >= afterLast) { - URI_FUNC(StopSyntax)(state, afterLast, memory); - return NULL; - } - } - } else { - /* Eat while no dot in sight */ - int letterAmong = 0; - int walking = 1; - do { - switch (*first) { - case URI_SET_HEX_LETTER_LOWER: - letterAmong = 1; - if (digitCount == 4) { - URI_FUNC(StopSyntax)(state, first, memory); - return NULL; - } - digitHistory[digitCount] = (unsigned char)(15 + *first - _UT('f')); - digitCount++; - break; - - case URI_SET_HEX_LETTER_UPPER: - letterAmong = 1; - if (digitCount == 4) { - URI_FUNC(StopSyntax)(state, first, memory); - return NULL; - } - digitHistory[digitCount] = (unsigned char)(15 + *first - _UT('F')); - digitCount++; - break; - - case URI_SET_DIGIT: - if (digitCount == 4) { - URI_FUNC(StopSyntax)(state, first, memory); - return NULL; - } - digitHistory[digitCount] = (unsigned char)(9 + *first - _UT('9')); - digitCount++; - break; - - case _UT(':'): - { - int setZipper = 0; - - if (digitCount > 0) { - if (zipperEver) { - uriWriteQuadToDoubleByte(digitHistory, digitCount, quadsAfterZipper + 2 * quadsAfterZipperCount); - quadsAfterZipperCount++; - } else { - uriWriteQuadToDoubleByte(digitHistory, digitCount, state->uri->hostData.ip6->data + 2 * quadsDone); - } - quadsDone++; - digitCount = 0; - } - letterAmong = 0; - - /* Too many quads? */ - if (quadsDone >= 8 - zipperEver) { - URI_FUNC(StopSyntax)(state, first, memory); - return NULL; - } - - /* "::"? */ - if (first + 1 >= afterLast) { - URI_FUNC(StopSyntax)(state, afterLast, memory); - return NULL; - } - if (first[1] == _UT(':')) { - const int resetOffset = 2 * (quadsDone + (digitCount > 0)); - - first++; - if (zipperEver) { - URI_FUNC(StopSyntax)(state, first, memory); - return NULL; /* "::.+::" */ - } - - /* Zero everything after zipper */ - memset(state->uri->hostData.ip6->data + resetOffset, 0, 16 - resetOffset); - setZipper = 1; - - /* ":::+"? */ - if (first + 1 >= afterLast) { - URI_FUNC(StopSyntax)(state, afterLast, memory); - return NULL; /* No ']' yet */ - } - if (first[1] == _UT(':')) { - URI_FUNC(StopSyntax)(state, first + 1, memory); - return NULL; /* ":::+ "*/ - } - } - - if (setZipper) { - zipperEver = 1; - } - } - break; - - case _UT('.'): - if ((quadsDone > 6) /* NOTE */ - || (!zipperEver && (quadsDone < 6)) - || letterAmong - || (digitCount == 0) - || (digitCount == 4)) { - /* Invalid octet before */ - URI_FUNC(StopSyntax)(state, first, memory); - return NULL; - } else if ((digitCount > 1) - && (digitHistory[0] == 0)) { - /* Leading zero */ - URI_FUNC(StopSyntax)(state, first - digitCount, memory); - return NULL; - } else if ((digitCount > 2) - && (digitHistory[1] == 0)) { - /* Leading zero */ - URI_FUNC(StopSyntax)(state, first - digitCount + 1, memory); - return NULL; - } else if ((digitCount == 3) - && (100 * digitHistory[0] - + 10 * digitHistory[1] - + digitHistory[2] > 255)) { - /* Octet value too large */ - if (digitHistory[0] > 2) { - URI_FUNC(StopSyntax)(state, first - 3, memory); - } else if (digitHistory[1] > 5) { - URI_FUNC(StopSyntax)(state, first - 2, memory); - } else { - URI_FUNC(StopSyntax)(state, first - 1, memory); - } - return NULL; - } - - /* Copy first IPv4 octet */ - state->uri->hostData.ip6->data[16 - 4] = uriGetOctetValue(digitHistory, digitCount); - digitCount = 0; - - /* Switch over to IPv4 loop */ - ip4OctetsDone = 1; - walking = 0; - break; - - case _UT(']'): - /* Too little quads? */ - if (!zipperEver && !((quadsDone == 7) && (digitCount > 0))) { - URI_FUNC(StopSyntax)(state, first, memory); - return NULL; - } - - if (digitCount > 0) { - if (zipperEver) { - uriWriteQuadToDoubleByte(digitHistory, digitCount, quadsAfterZipper + 2 * quadsAfterZipperCount); - quadsAfterZipperCount++; - } else { - uriWriteQuadToDoubleByte(digitHistory, digitCount, state->uri->hostData.ip6->data + 2 * quadsDone); - } - /* - quadsDone++; - digitCount = 0; - */ - } - - /* Copy missing quads to the end */ - memcpy(state->uri->hostData.ip6->data + 16 - 2 * quadsAfterZipperCount, - quadsAfterZipper, 2 * quadsAfterZipperCount); - - state->uri->hostText.afterLast = first; /* HOST END */ - return first + 1; /* Fine */ - - default: - URI_FUNC(StopSyntax)(state, first, memory); - return NULL; - } - first++; - - if (first >= afterLast) { - URI_FUNC(StopSyntax)(state, afterLast, memory); - return NULL; /* No ']' yet */ - } - } while (walking); - } - } -} - - - -/* - * [mustBeSegmentNzNc]->[pctEncoded][mustBeSegmentNzNc] - * [mustBeSegmentNzNc]->[subDelims][mustBeSegmentNzNc] - * [mustBeSegmentNzNc]->[unreserved][mustBeSegmentNzNc] - * [mustBeSegmentNzNc]->[uriTail] // can take - * [mustBeSegmentNzNc]->[segment][zeroMoreSlashSegs][uriTail] - * [mustBeSegmentNzNc]-><@>[mustBeSegmentNzNc] - */ -static const URI_CHAR * URI_FUNC(ParseMustBeSegmentNzNc)( - URI_TYPE(ParserState) * state, const URI_CHAR * first, - const URI_CHAR * afterLast, UriMemoryManager * memory) { - if (first >= afterLast) { - if (!URI_FUNC(PushPathSegment)(state, state->uri->scheme.first, first, memory)) { /* SEGMENT BOTH */ - URI_FUNC(StopMalloc)(state, memory); - return NULL; - } - state->uri->scheme.first = NULL; /* Not a scheme, reset */ - return afterLast; - } - - switch (*first) { - case _UT('%'): - { - const URI_CHAR * const afterPctEncoded - = URI_FUNC(ParsePctEncoded)(state, first, afterLast, memory); - if (afterPctEncoded == NULL) { - return NULL; - } - return URI_FUNC(ParseMustBeSegmentNzNc)(state, afterPctEncoded, afterLast, memory); - } - - case _UT('@'): - case _UT('!'): - case _UT('$'): - case _UT('&'): - case _UT('('): - case _UT(')'): - case _UT('*'): - case _UT(','): - case _UT(';'): - case _UT('\''): - case _UT('+'): - case _UT('='): - case _UT('-'): - case _UT('.'): - case _UT('_'): - case _UT('~'): - case URI_SET_DIGIT: - case URI_SET_ALPHA: - return URI_FUNC(ParseMustBeSegmentNzNc)(state, first + 1, afterLast, memory); - - case _UT('/'): - { - const URI_CHAR * afterZeroMoreSlashSegs; - const URI_CHAR * afterSegment; - if (!URI_FUNC(PushPathSegment)(state, state->uri->scheme.first, first, memory)) { /* SEGMENT BOTH */ - URI_FUNC(StopMalloc)(state, memory); - return NULL; - } - state->uri->scheme.first = NULL; /* Not a scheme, reset */ - afterSegment = URI_FUNC(ParseSegment)(state, first + 1, afterLast, memory); - if (afterSegment == NULL) { - return NULL; - } - if (!URI_FUNC(PushPathSegment)(state, first + 1, afterSegment, memory)) { /* SEGMENT BOTH */ - URI_FUNC(StopMalloc)(state, memory); - return NULL; - } - afterZeroMoreSlashSegs - = URI_FUNC(ParseZeroMoreSlashSegs)(state, afterSegment, afterLast, memory); - if (afterZeroMoreSlashSegs == NULL) { - return NULL; - } - return URI_FUNC(ParseUriTail)(state, afterZeroMoreSlashSegs, afterLast, memory); - } - - default: - if (!URI_FUNC(PushPathSegment)(state, state->uri->scheme.first, first, memory)) { /* SEGMENT BOTH */ - URI_FUNC(StopMalloc)(state, memory); - return NULL; - } - state->uri->scheme.first = NULL; /* Not a scheme, reset */ - return URI_FUNC(ParseUriTail)(state, first, afterLast, memory); - } -} - - - -/* - * [ownHost]-><[>[ipLit2][authorityTwo] - * [ownHost]->[ownHost2] // can take - */ -static URI_INLINE const URI_CHAR * URI_FUNC(ParseOwnHost)( - URI_TYPE(ParserState) * state, const URI_CHAR * first, - const URI_CHAR * afterLast, UriMemoryManager * memory) { - if (first >= afterLast) { - state->uri->hostText.afterLast = afterLast; /* HOST END */ - return afterLast; - } - - switch (*first) { - case _UT('['): - { - const URI_CHAR * const afterIpLit2 - = URI_FUNC(ParseIpLit2)(state, first + 1, afterLast, memory); - if (afterIpLit2 == NULL) { - return NULL; - } - state->uri->hostText.first = first + 1; /* HOST BEGIN */ - return URI_FUNC(ParseAuthorityTwo)(state, afterIpLit2, afterLast); - } - - default: - return URI_FUNC(ParseOwnHost2)(state, first, afterLast, memory); - } -} - - - -static URI_INLINE UriBool URI_FUNC(OnExitOwnHost2)( - URI_TYPE(ParserState) * state, const URI_CHAR * first, - UriMemoryManager * memory) { - state->uri->hostText.afterLast = first; /* HOST END */ - - /* Valid IPv4 or just a regname? */ - state->uri->hostData.ip4 = memory->malloc(memory, 1 * sizeof(UriIp4)); /* Freed when stopping on parse error */ - if (state->uri->hostData.ip4 == NULL) { - return URI_FALSE; /* Raises malloc error */ - } - if (URI_FUNC(ParseIpFourAddress)(state->uri->hostData.ip4->data, - state->uri->hostText.first, state->uri->hostText.afterLast)) { - /* Not IPv4 */ - memory->free(memory, state->uri->hostData.ip4); - state->uri->hostData.ip4 = NULL; - } - return URI_TRUE; /* Success */ -} - - - -/* - * [ownHost2]->[authorityTwo] // can take - * [ownHost2]->[pctSubUnres][ownHost2] - */ -static const URI_CHAR * URI_FUNC(ParseOwnHost2)( - URI_TYPE(ParserState) * state, const URI_CHAR * first, - const URI_CHAR * afterLast, UriMemoryManager * memory) { - if (first >= afterLast) { - if (!URI_FUNC(OnExitOwnHost2)(state, first, memory)) { - URI_FUNC(StopMalloc)(state, memory); - return NULL; - } - return afterLast; - } - - switch (*first) { - case _UT('!'): - case _UT('$'): - case _UT('%'): - case _UT('&'): - case _UT('('): - case _UT(')'): - case _UT('-'): - case _UT('*'): - case _UT(','): - case _UT('.'): - case _UT(';'): - case _UT('\''): - case _UT('_'): - case _UT('~'): - case _UT('+'): - case _UT('='): - case URI_SET_DIGIT: - case URI_SET_ALPHA: - { - const URI_CHAR * const afterPctSubUnres - = URI_FUNC(ParsePctSubUnres)(state, first, afterLast, memory); - if (afterPctSubUnres == NULL) { - return NULL; - } - return URI_FUNC(ParseOwnHost2)(state, afterPctSubUnres, afterLast, memory); - } - - default: - if (!URI_FUNC(OnExitOwnHost2)(state, first, memory)) { - URI_FUNC(StopMalloc)(state, memory); - return NULL; - } - return URI_FUNC(ParseAuthorityTwo)(state, first, afterLast); - } -} - - - -static URI_INLINE UriBool URI_FUNC(OnExitOwnHostUserInfo)( - URI_TYPE(ParserState) * state, const URI_CHAR * first, - UriMemoryManager * memory) { - state->uri->hostText.first = state->uri->userInfo.first; /* Host instead of userInfo, update */ - state->uri->userInfo.first = NULL; /* Not a userInfo, reset */ - state->uri->hostText.afterLast = first; /* HOST END */ - - /* Valid IPv4 or just a regname? */ - state->uri->hostData.ip4 = memory->malloc(memory, 1 * sizeof(UriIp4)); /* Freed when stopping on parse error */ - if (state->uri->hostData.ip4 == NULL) { - return URI_FALSE; /* Raises malloc error */ - } - if (URI_FUNC(ParseIpFourAddress)(state->uri->hostData.ip4->data, - state->uri->hostText.first, state->uri->hostText.afterLast)) { - /* Not IPv4 */ - memory->free(memory, state->uri->hostData.ip4); - state->uri->hostData.ip4 = NULL; - } - return URI_TRUE; /* Success */ -} - - - -/* - * [ownHostUserInfo]->[ownHostUserInfoNz] - * [ownHostUserInfo]-> - */ -static URI_INLINE const URI_CHAR * URI_FUNC(ParseOwnHostUserInfo)( - URI_TYPE(ParserState) * state, const URI_CHAR * first, - const URI_CHAR * afterLast, UriMemoryManager * memory) { - if (first >= afterLast) { - if (!URI_FUNC(OnExitOwnHostUserInfo)(state, first, memory)) { - URI_FUNC(StopMalloc)(state, memory); - return NULL; - } - return afterLast; - } - - switch (*first) { - case _UT('!'): - case _UT('$'): - case _UT('%'): - case _UT('&'): - case _UT('('): - case _UT(')'): - case _UT('-'): - case _UT('*'): - case _UT(','): - case _UT('.'): - case _UT(':'): - case _UT(';'): - case _UT('@'): - case _UT('\''): - case _UT('_'): - case _UT('~'): - case _UT('+'): - case _UT('='): - case URI_SET_DIGIT: - case URI_SET_ALPHA: - return URI_FUNC(ParseOwnHostUserInfoNz)(state, first, afterLast, memory); - - default: - if (!URI_FUNC(OnExitOwnHostUserInfo)(state, first, memory)) { - URI_FUNC(StopMalloc)(state, memory); - return NULL; - } - return first; - } -} - - - -/* - * [ownHostUserInfoNz]->[pctSubUnres][ownHostUserInfo] - * [ownHostUserInfoNz]-><:>[ownPortUserInfo] - * [ownHostUserInfoNz]-><@>[ownHost] - */ -static const URI_CHAR * URI_FUNC(ParseOwnHostUserInfoNz)( - URI_TYPE(ParserState) * state, const URI_CHAR * first, - const URI_CHAR * afterLast, UriMemoryManager * memory) { - if (first >= afterLast) { - URI_FUNC(StopSyntax)(state, afterLast, memory); - return NULL; - } - - switch (*first) { - case _UT('!'): - case _UT('$'): - case _UT('%'): - case _UT('&'): - case _UT('('): - case _UT(')'): - case _UT('-'): - case _UT('*'): - case _UT(','): - case _UT('.'): - case _UT(';'): - case _UT('\''): - case _UT('_'): - case _UT('~'): - case _UT('+'): - case _UT('='): - case URI_SET_DIGIT: - case URI_SET_ALPHA: - { - const URI_CHAR * const afterPctSubUnres - = URI_FUNC(ParsePctSubUnres)(state, first, afterLast, memory); - if (afterPctSubUnres == NULL) { - return NULL; - } - return URI_FUNC(ParseOwnHostUserInfo)(state, afterPctSubUnres, afterLast, memory); - } - - case _UT(':'): - state->uri->hostText.afterLast = first; /* HOST END */ - state->uri->portText.first = first + 1; /* PORT BEGIN */ - return URI_FUNC(ParseOwnPortUserInfo)(state, first + 1, afterLast, memory); - - case _UT('@'): - state->uri->userInfo.afterLast = first; /* USERINFO END */ - state->uri->hostText.first = first + 1; /* HOST BEGIN */ - return URI_FUNC(ParseOwnHost)(state, first + 1, afterLast, memory); - - default: - URI_FUNC(StopSyntax)(state, first, memory); - return NULL; - } -} - - - -static URI_INLINE UriBool URI_FUNC(OnExitOwnPortUserInfo)( - URI_TYPE(ParserState) * state, const URI_CHAR * first, - UriMemoryManager * memory) { - state->uri->hostText.first = state->uri->userInfo.first; /* Host instead of userInfo, update */ - state->uri->userInfo.first = NULL; /* Not a userInfo, reset */ - state->uri->portText.afterLast = first; /* PORT END */ - - /* Valid IPv4 or just a regname? */ - state->uri->hostData.ip4 = memory->malloc(memory, 1 * sizeof(UriIp4)); /* Freed when stopping on parse error */ - if (state->uri->hostData.ip4 == NULL) { - return URI_FALSE; /* Raises malloc error */ - } - if (URI_FUNC(ParseIpFourAddress)(state->uri->hostData.ip4->data, - state->uri->hostText.first, state->uri->hostText.afterLast)) { - /* Not IPv4 */ - memory->free(memory, state->uri->hostData.ip4); - state->uri->hostData.ip4 = NULL; - } - return URI_TRUE; /* Success */ -} - - - -/* - * [ownPortUserInfo]->[ALPHA][ownUserInfo] - * [ownPortUserInfo]->[DIGIT][ownPortUserInfo] - * [ownPortUserInfo]-><.>[ownUserInfo] - * [ownPortUserInfo]-><_>[ownUserInfo] - * [ownPortUserInfo]-><~>[ownUserInfo] - * [ownPortUserInfo]-><->[ownUserInfo] - * [ownPortUserInfo]->[subDelims][ownUserInfo] - * [ownPortUserInfo]->[pctEncoded][ownUserInfo] - * [ownPortUserInfo]-><:>[ownUserInfo] - * [ownPortUserInfo]-><@>[ownHost] - * [ownPortUserInfo]-> - */ -static const URI_CHAR * URI_FUNC(ParseOwnPortUserInfo)( - URI_TYPE(ParserState) * state, const URI_CHAR * first, - const URI_CHAR * afterLast, UriMemoryManager * memory) { - if (first >= afterLast) { - if (!URI_FUNC(OnExitOwnPortUserInfo)(state, first, memory)) { - URI_FUNC(StopMalloc)(state, memory); - return NULL; - } - return afterLast; - } - - switch (*first) { - /* begin sub-delims */ - case _UT('!'): - case _UT('$'): - case _UT('&'): - case _UT('\''): - case _UT('('): - case _UT(')'): - case _UT('*'): - case _UT('+'): - case _UT(','): - case _UT(';'): - case _UT('='): - /* end sub-delims */ - /* begin unreserved (except alpha and digit) */ - case _UT('-'): - case _UT('.'): - case _UT('_'): - case _UT('~'): - /* end unreserved (except alpha and digit) */ - case _UT(':'): - case URI_SET_ALPHA: - state->uri->hostText.afterLast = NULL; /* Not a host, reset */ - state->uri->portText.first = NULL; /* Not a port, reset */ - return URI_FUNC(ParseOwnUserInfo)(state, first + 1, afterLast, memory); - - case URI_SET_DIGIT: - return URI_FUNC(ParseOwnPortUserInfo)(state, first + 1, afterLast, memory); - - case _UT('%'): - state->uri->portText.first = NULL; /* Not a port, reset */ - { - const URI_CHAR * const afterPct - = URI_FUNC(ParsePctEncoded)(state, first, afterLast, memory); - if (afterPct == NULL) { - return NULL; - } - return URI_FUNC(ParseOwnUserInfo)(state, afterPct, afterLast, memory); - } - - case _UT('@'): - state->uri->hostText.afterLast = NULL; /* Not a host, reset */ - state->uri->portText.first = NULL; /* Not a port, reset */ - state->uri->userInfo.afterLast = first; /* USERINFO END */ - state->uri->hostText.first = first + 1; /* HOST BEGIN */ - return URI_FUNC(ParseOwnHost)(state, first + 1, afterLast, memory); - - default: - if (!URI_FUNC(OnExitOwnPortUserInfo)(state, first, memory)) { - URI_FUNC(StopMalloc)(state, memory); - return NULL; - } - return first; - } -} - - - -/* - * [ownUserInfo]->[pctSubUnres][ownUserInfo] - * [ownUserInfo]-><:>[ownUserInfo] - * [ownUserInfo]-><@>[ownHost] - */ -static const URI_CHAR * URI_FUNC(ParseOwnUserInfo)( - URI_TYPE(ParserState) * state, const URI_CHAR * first, - const URI_CHAR * afterLast, UriMemoryManager * memory) { - if (first >= afterLast) { - URI_FUNC(StopSyntax)(state, afterLast, memory); - return NULL; - } - - switch (*first) { - case _UT('!'): - case _UT('$'): - case _UT('%'): - case _UT('&'): - case _UT('('): - case _UT(')'): - case _UT('-'): - case _UT('*'): - case _UT(','): - case _UT('.'): - case _UT(';'): - case _UT('\''): - case _UT('_'): - case _UT('~'): - case _UT('+'): - case _UT('='): - case URI_SET_DIGIT: - case URI_SET_ALPHA: - { - const URI_CHAR * const afterPctSubUnres - = URI_FUNC(ParsePctSubUnres)(state, first, afterLast, memory); - if (afterPctSubUnres == NULL) { - return NULL; - } - return URI_FUNC(ParseOwnUserInfo)(state, afterPctSubUnres, afterLast, memory); - } - - case _UT(':'): - return URI_FUNC(ParseOwnUserInfo)(state, first + 1, afterLast, memory); - - case _UT('@'): - /* SURE */ - state->uri->userInfo.afterLast = first; /* USERINFO END */ - state->uri->hostText.first = first + 1; /* HOST BEGIN */ - return URI_FUNC(ParseOwnHost)(state, first + 1, afterLast, memory); - - default: - URI_FUNC(StopSyntax)(state, first, memory); - return NULL; - } -} - - - -static URI_INLINE void URI_FUNC(OnExitPartHelperTwo)(URI_TYPE(ParserState) * state) { - state->uri->absolutePath = URI_TRUE; -} - - - -/* - * [partHelperTwo]->[pathAbsNoLeadSlash] // can take - * [partHelperTwo]->[authority][pathAbsEmpty] - */ -static URI_INLINE const URI_CHAR * URI_FUNC(ParsePartHelperTwo)( - URI_TYPE(ParserState) * state, const URI_CHAR * first, - const URI_CHAR * afterLast, UriMemoryManager * memory) { - if (first >= afterLast) { - URI_FUNC(OnExitPartHelperTwo)(state); - return afterLast; - } - - switch (*first) { - case _UT('/'): - { - const URI_CHAR * const afterAuthority - = URI_FUNC(ParseAuthority)(state, first + 1, afterLast, memory); - const URI_CHAR * afterPathAbsEmpty; - if (afterAuthority == NULL) { - return NULL; - } - afterPathAbsEmpty = URI_FUNC(ParsePathAbsEmpty)(state, afterAuthority, afterLast, memory); - - URI_FUNC(FixEmptyTrailSegment)(state->uri, memory); - - return afterPathAbsEmpty; - } - - default: - URI_FUNC(OnExitPartHelperTwo)(state); - return URI_FUNC(ParsePathAbsNoLeadSlash)(state, first, afterLast, memory); - } -} - - - -/* - * [pathAbsEmpty]->[segment][pathAbsEmpty] - * [pathAbsEmpty]-> - */ -static const URI_CHAR * URI_FUNC(ParsePathAbsEmpty)( - URI_TYPE(ParserState) * state, const URI_CHAR * first, - const URI_CHAR * afterLast, UriMemoryManager * memory) { - if (first >= afterLast) { - return afterLast; - } - - switch (*first) { - case _UT('/'): - { - const URI_CHAR * const afterSegment - = URI_FUNC(ParseSegment)(state, first + 1, afterLast, memory); - if (afterSegment == NULL) { - return NULL; - } - if (!URI_FUNC(PushPathSegment)(state, first + 1, afterSegment, memory)) { /* SEGMENT BOTH */ - URI_FUNC(StopMalloc)(state, memory); - return NULL; - } - return URI_FUNC(ParsePathAbsEmpty)(state, afterSegment, afterLast, memory); - } - - default: - return first; - } -} - - - -/* - * [pathAbsNoLeadSlash]->[segmentNz][zeroMoreSlashSegs] - * [pathAbsNoLeadSlash]-> - */ -static URI_INLINE const URI_CHAR * URI_FUNC(ParsePathAbsNoLeadSlash)( - URI_TYPE(ParserState) * state, const URI_CHAR * first, - const URI_CHAR * afterLast, UriMemoryManager * memory) { - if (first >= afterLast) { - return afterLast; - } - - switch (*first) { - case _UT('!'): - case _UT('$'): - case _UT('%'): - case _UT('&'): - case _UT('('): - case _UT(')'): - case _UT('-'): - case _UT('*'): - case _UT(','): - case _UT('.'): - case _UT(':'): - case _UT(';'): - case _UT('@'): - case _UT('\''): - case _UT('_'): - case _UT('~'): - case _UT('+'): - case _UT('='): - case URI_SET_DIGIT: - case URI_SET_ALPHA: - { - const URI_CHAR * const afterSegmentNz - = URI_FUNC(ParseSegmentNz)(state, first, afterLast, memory); - if (afterSegmentNz == NULL) { - return NULL; - } - if (!URI_FUNC(PushPathSegment)(state, first, afterSegmentNz, memory)) { /* SEGMENT BOTH */ - URI_FUNC(StopMalloc)(state, memory); - return NULL; - } - return URI_FUNC(ParseZeroMoreSlashSegs)(state, afterSegmentNz, afterLast, memory); - } - - default: - return first; - } -} - - - -/* - * [pathRootless]->[segmentNz][zeroMoreSlashSegs] - */ -static URI_INLINE const URI_CHAR * URI_FUNC(ParsePathRootless)( - URI_TYPE(ParserState) * state, const URI_CHAR * first, - const URI_CHAR * afterLast, UriMemoryManager * memory) { - const URI_CHAR * const afterSegmentNz - = URI_FUNC(ParseSegmentNz)(state, first, afterLast, memory); - if (afterSegmentNz == NULL) { - return NULL; - } else { - if (!URI_FUNC(PushPathSegment)(state, first, afterSegmentNz, memory)) { /* SEGMENT BOTH */ - URI_FUNC(StopMalloc)(state, memory); - return NULL; - } - } - return URI_FUNC(ParseZeroMoreSlashSegs)(state, afterSegmentNz, afterLast, memory); -} - - - -/* - * [pchar]->[pctEncoded] - * [pchar]->[subDelims] - * [pchar]->[unreserved] - * [pchar]-><:> - * [pchar]-><@> - */ -static const URI_CHAR * URI_FUNC(ParsePchar)(URI_TYPE(ParserState) * state, - const URI_CHAR * first, const URI_CHAR * afterLast, - UriMemoryManager * memory) { - if (first >= afterLast) { - URI_FUNC(StopSyntax)(state, afterLast, memory); - return NULL; - } - - switch (*first) { - case _UT('%'): - return URI_FUNC(ParsePctEncoded)(state, first, afterLast, memory); - - case _UT(':'): - case _UT('@'): - case _UT('!'): - case _UT('$'): - case _UT('&'): - case _UT('('): - case _UT(')'): - case _UT('*'): - case _UT(','): - case _UT(';'): - case _UT('\''): - case _UT('+'): - case _UT('='): - case _UT('-'): - case _UT('.'): - case _UT('_'): - case _UT('~'): - case URI_SET_DIGIT: - case URI_SET_ALPHA: - return first + 1; - - default: - URI_FUNC(StopSyntax)(state, first, memory); - return NULL; - } -} - - - -/* - * [pctEncoded]-><%>[HEXDIG][HEXDIG] - */ -static const URI_CHAR * URI_FUNC(ParsePctEncoded)( - URI_TYPE(ParserState) * state, - const URI_CHAR * first, const URI_CHAR * afterLast, - UriMemoryManager * memory) { - if (first >= afterLast) { - URI_FUNC(StopSyntax)(state, afterLast, memory); - return NULL; - } - - /* - First character has already been - checked before entering this rule. - - switch (*first) { - case _UT('%'): - */ - if (first + 1 >= afterLast) { - URI_FUNC(StopSyntax)(state, afterLast, memory); - return NULL; - } - - switch (first[1]) { - case URI_SET_HEXDIG: - if (first + 2 >= afterLast) { - URI_FUNC(StopSyntax)(state, afterLast, memory); - return NULL; - } - - switch (first[2]) { - case URI_SET_HEXDIG: - return first + 3; - - default: - URI_FUNC(StopSyntax)(state, first + 2, memory); - return NULL; - } - - default: - URI_FUNC(StopSyntax)(state, first + 1, memory); - return NULL; - } - - /* - default: - URI_FUNC(StopSyntax)(state, first, memory); - return NULL; - } - */ -} - - - -/* - * [pctSubUnres]->[pctEncoded] - * [pctSubUnres]->[subDelims] - * [pctSubUnres]->[unreserved] - */ -static const URI_CHAR * URI_FUNC(ParsePctSubUnres)( - URI_TYPE(ParserState) * state, - const URI_CHAR * first, const URI_CHAR * afterLast, - UriMemoryManager * memory) { - if (first >= afterLast) { - URI_FUNC(StopSyntax)(state, afterLast, memory); - return NULL; - } - - switch (*first) { - case _UT('%'): - return URI_FUNC(ParsePctEncoded)(state, first, afterLast, memory); - - case _UT('!'): - case _UT('$'): - case _UT('&'): - case _UT('('): - case _UT(')'): - case _UT('*'): - case _UT(','): - case _UT(';'): - case _UT('\''): - case _UT('+'): - case _UT('='): - case _UT('-'): - case _UT('.'): - case _UT('_'): - case _UT('~'): - case URI_SET_DIGIT: - case URI_SET_ALPHA: - return first + 1; - - default: - URI_FUNC(StopSyntax)(state, first, memory); - return NULL; - } -} - - - -/* - * [port]->[DIGIT][port] - * [port]-> - */ -static const URI_CHAR * URI_FUNC(ParsePort)(URI_TYPE(ParserState) * state, const URI_CHAR * first, const URI_CHAR * afterLast) { - if (first >= afterLast) { - return afterLast; - } - - switch (*first) { - case URI_SET_DIGIT: - return URI_FUNC(ParsePort)(state, first + 1, afterLast); - - default: - return first; - } -} - - - -/* - * [queryFrag]->[pchar][queryFrag] - * [queryFrag]->[queryFrag] - * [queryFrag]->[queryFrag] - * [queryFrag]-> - */ -static const URI_CHAR * URI_FUNC(ParseQueryFrag)(URI_TYPE(ParserState) * state, - const URI_CHAR * first, const URI_CHAR * afterLast, - UriMemoryManager * memory) { - if (first >= afterLast) { - return afterLast; - } - - switch (*first) { - case _UT('!'): - case _UT('$'): - case _UT('%'): - case _UT('&'): - case _UT('('): - case _UT(')'): - case _UT('-'): - case _UT('*'): - case _UT(','): - case _UT('.'): - case _UT(':'): - case _UT(';'): - case _UT('@'): - case _UT('\''): - case _UT('_'): - case _UT('~'): - case _UT('+'): - case _UT('='): - case URI_SET_DIGIT: - case URI_SET_ALPHA: - { - const URI_CHAR * const afterPchar - = URI_FUNC(ParsePchar)(state, first, afterLast, memory); - if (afterPchar == NULL) { - return NULL; - } - return URI_FUNC(ParseQueryFrag)(state, afterPchar, afterLast, memory); - } - - case _UT('/'): - case _UT('?'): - return URI_FUNC(ParseQueryFrag)(state, first + 1, afterLast, memory); - - default: - return first; - } -} - - - -/* - * [segment]->[pchar][segment] - * [segment]-> - */ -static const URI_CHAR * URI_FUNC(ParseSegment)(URI_TYPE(ParserState) * state, - const URI_CHAR * first, const URI_CHAR * afterLast, - UriMemoryManager * memory) { - if (first >= afterLast) { - return afterLast; - } - - switch (*first) { - case _UT('!'): - case _UT('$'): - case _UT('%'): - case _UT('&'): - case _UT('('): - case _UT(')'): - case _UT('-'): - case _UT('*'): - case _UT(','): - case _UT('.'): - case _UT(':'): - case _UT(';'): - case _UT('@'): - case _UT('\''): - case _UT('_'): - case _UT('~'): - case _UT('+'): - case _UT('='): - case URI_SET_DIGIT: - case URI_SET_ALPHA: - { - const URI_CHAR * const afterPchar - = URI_FUNC(ParsePchar)(state, first, afterLast, memory); - if (afterPchar == NULL) { - return NULL; - } - return URI_FUNC(ParseSegment)(state, afterPchar, afterLast, memory); - } - - default: - return first; - } -} - - - -/* - * [segmentNz]->[pchar][segment] - */ -static URI_INLINE const URI_CHAR * URI_FUNC(ParseSegmentNz)( - URI_TYPE(ParserState) * state, - const URI_CHAR * first, const URI_CHAR * afterLast, - UriMemoryManager * memory) { - const URI_CHAR * const afterPchar - = URI_FUNC(ParsePchar)(state, first, afterLast, memory); - if (afterPchar == NULL) { - return NULL; - } - return URI_FUNC(ParseSegment)(state, afterPchar, afterLast, memory); -} - - - -static URI_INLINE UriBool URI_FUNC(OnExitSegmentNzNcOrScheme2)( - URI_TYPE(ParserState) * state, const URI_CHAR * first, - UriMemoryManager * memory) { - if (!URI_FUNC(PushPathSegment)(state, state->uri->scheme.first, first, memory)) { /* SEGMENT BOTH */ - return URI_FALSE; /* Raises malloc error*/ - } - state->uri->scheme.first = NULL; /* Not a scheme, reset */ - return URI_TRUE; /* Success */ -} - - - -/* - * [segmentNzNcOrScheme2]->[ALPHA][segmentNzNcOrScheme2] - * [segmentNzNcOrScheme2]->[DIGIT][segmentNzNcOrScheme2] - * [segmentNzNcOrScheme2]->[pctEncoded][mustBeSegmentNzNc] - * [segmentNzNcOrScheme2]->[uriTail] // can take - * [segmentNzNcOrScheme2]->[mustBeSegmentNzNc] - * [segmentNzNcOrScheme2]-><$>[mustBeSegmentNzNc] - * [segmentNzNcOrScheme2]-><&>[mustBeSegmentNzNc] - * [segmentNzNcOrScheme2]-><(>[mustBeSegmentNzNc] - * [segmentNzNcOrScheme2]-><)>[mustBeSegmentNzNc] - * [segmentNzNcOrScheme2]-><*>[mustBeSegmentNzNc] - * [segmentNzNcOrScheme2]-><,>[mustBeSegmentNzNc] - * [segmentNzNcOrScheme2]-><.>[segmentNzNcOrScheme2] - * [segmentNzNcOrScheme2]->[segment][zeroMoreSlashSegs][uriTail] - * [segmentNzNcOrScheme2]-><:>[hierPart][uriTail] - * [segmentNzNcOrScheme2]-><;>[mustBeSegmentNzNc] - * [segmentNzNcOrScheme2]-><@>[mustBeSegmentNzNc] - * [segmentNzNcOrScheme2]-><_>[mustBeSegmentNzNc] - * [segmentNzNcOrScheme2]-><~>[mustBeSegmentNzNc] - * [segmentNzNcOrScheme2]-><+>[segmentNzNcOrScheme2] - * [segmentNzNcOrScheme2]-><=>[mustBeSegmentNzNc] - * [segmentNzNcOrScheme2]-><'>[mustBeSegmentNzNc] - * [segmentNzNcOrScheme2]-><->[segmentNzNcOrScheme2] - */ -static const URI_CHAR * URI_FUNC(ParseSegmentNzNcOrScheme2)( - URI_TYPE(ParserState) * state, const URI_CHAR * first, - const URI_CHAR * afterLast, UriMemoryManager * memory) { - if (first >= afterLast) { - if (!URI_FUNC(OnExitSegmentNzNcOrScheme2)(state, first, memory)) { - URI_FUNC(StopMalloc)(state, memory); - return NULL; - } - return afterLast; - } - - switch (*first) { - case _UT('.'): - case _UT('+'): - case _UT('-'): - case URI_SET_ALPHA: - case URI_SET_DIGIT: - return URI_FUNC(ParseSegmentNzNcOrScheme2)(state, first + 1, afterLast, memory); - - case _UT('%'): - { - const URI_CHAR * const afterPctEncoded - = URI_FUNC(ParsePctEncoded)(state, first, afterLast, memory); - if (afterPctEncoded == NULL) { - return NULL; - } - return URI_FUNC(ParseMustBeSegmentNzNc)(state, afterPctEncoded, afterLast, memory); - } - - case _UT('!'): - case _UT('$'): - case _UT('&'): - case _UT('('): - case _UT(')'): - case _UT('*'): - case _UT(','): - case _UT(';'): - case _UT('@'): - case _UT('_'): - case _UT('~'): - case _UT('='): - case _UT('\''): - return URI_FUNC(ParseMustBeSegmentNzNc)(state, first + 1, afterLast, memory); - - case _UT('/'): - { - const URI_CHAR * afterZeroMoreSlashSegs; - const URI_CHAR * const afterSegment - = URI_FUNC(ParseSegment)(state, first + 1, afterLast, memory); - if (afterSegment == NULL) { - return NULL; - } - if (!URI_FUNC(PushPathSegment)(state, state->uri->scheme.first, first, memory)) { /* SEGMENT BOTH */ - URI_FUNC(StopMalloc)(state, memory); - return NULL; - } - state->uri->scheme.first = NULL; /* Not a scheme, reset */ - if (!URI_FUNC(PushPathSegment)(state, first + 1, afterSegment, memory)) { /* SEGMENT BOTH */ - URI_FUNC(StopMalloc)(state, memory); - return NULL; - } - afterZeroMoreSlashSegs - = URI_FUNC(ParseZeroMoreSlashSegs)(state, afterSegment, afterLast, memory); - if (afterZeroMoreSlashSegs == NULL) { - return NULL; - } - return URI_FUNC(ParseUriTail)(state, afterZeroMoreSlashSegs, afterLast, memory); - } - - case _UT(':'): - { - const URI_CHAR * const afterHierPart - = URI_FUNC(ParseHierPart)(state, first + 1, afterLast, memory); - state->uri->scheme.afterLast = first; /* SCHEME END */ - if (afterHierPart == NULL) { - return NULL; - } - return URI_FUNC(ParseUriTail)(state, afterHierPart, afterLast, memory); - } - - default: - if (!URI_FUNC(OnExitSegmentNzNcOrScheme2)(state, first, memory)) { - URI_FUNC(StopMalloc)(state, memory); - return NULL; - } - return URI_FUNC(ParseUriTail)(state, first, afterLast, memory); - } -} - - - -/* - * [uriReference]->[ALPHA][segmentNzNcOrScheme2] - * [uriReference]->[DIGIT][mustBeSegmentNzNc] - * [uriReference]->[pctEncoded][mustBeSegmentNzNc] - * [uriReference]->[subDelims][mustBeSegmentNzNc] - * [uriReference]->[uriTail] // can take - * [uriReference]-><.>[mustBeSegmentNzNc] - * [uriReference]->[partHelperTwo][uriTail] - * [uriReference]-><@>[mustBeSegmentNzNc] - * [uriReference]-><_>[mustBeSegmentNzNc] - * [uriReference]-><~>[mustBeSegmentNzNc] - * [uriReference]-><->[mustBeSegmentNzNc] - */ -static const URI_CHAR * URI_FUNC(ParseUriReference)( - URI_TYPE(ParserState) * state, const URI_CHAR * first, - const URI_CHAR * afterLast, UriMemoryManager * memory) { - if (first >= afterLast) { - return afterLast; - } - - switch (*first) { - case URI_SET_ALPHA: - state->uri->scheme.first = first; /* SCHEME BEGIN */ - return URI_FUNC(ParseSegmentNzNcOrScheme2)(state, first + 1, afterLast, memory); - - case URI_SET_DIGIT: - case _UT('!'): - case _UT('$'): - case _UT('&'): - case _UT('('): - case _UT(')'): - case _UT('*'): - case _UT(','): - case _UT(';'): - case _UT('\''): - case _UT('+'): - case _UT('='): - case _UT('.'): - case _UT('_'): - case _UT('~'): - case _UT('-'): - case _UT('@'): - state->uri->scheme.first = first; /* SEGMENT BEGIN, ABUSE SCHEME POINTER */ - return URI_FUNC(ParseMustBeSegmentNzNc)(state, first + 1, afterLast, memory); - - case _UT('%'): - { - const URI_CHAR * const afterPctEncoded - = URI_FUNC(ParsePctEncoded)(state, first, afterLast, memory); - if (afterPctEncoded == NULL) { - return NULL; - } - state->uri->scheme.first = first; /* SEGMENT BEGIN, ABUSE SCHEME POINTER */ - return URI_FUNC(ParseMustBeSegmentNzNc)(state, afterPctEncoded, afterLast, memory); - } - - case _UT('/'): - { - const URI_CHAR * const afterPartHelperTwo - = URI_FUNC(ParsePartHelperTwo)(state, first + 1, afterLast, memory); - if (afterPartHelperTwo == NULL) { - return NULL; - } - return URI_FUNC(ParseUriTail)(state, afterPartHelperTwo, afterLast, memory); - } - - default: - return URI_FUNC(ParseUriTail)(state, first, afterLast, memory); - } -} - - - -/* - * [uriTail]-><#>[queryFrag] - * [uriTail]->[queryFrag][uriTailTwo] - * [uriTail]-> - */ -static URI_INLINE const URI_CHAR * URI_FUNC(ParseUriTail)( - URI_TYPE(ParserState) * state, - const URI_CHAR * first, const URI_CHAR * afterLast, - UriMemoryManager * memory) { - if (first >= afterLast) { - return afterLast; - } - - switch (*first) { - case _UT('#'): - { - const URI_CHAR * const afterQueryFrag = URI_FUNC(ParseQueryFrag)(state, first + 1, afterLast, memory); - if (afterQueryFrag == NULL) { - return NULL; - } - state->uri->fragment.first = first + 1; /* FRAGMENT BEGIN */ - state->uri->fragment.afterLast = afterQueryFrag; /* FRAGMENT END */ - return afterQueryFrag; - } - - case _UT('?'): - { - const URI_CHAR * const afterQueryFrag - = URI_FUNC(ParseQueryFrag)(state, first + 1, afterLast, memory); - if (afterQueryFrag == NULL) { - return NULL; - } - state->uri->query.first = first + 1; /* QUERY BEGIN */ - state->uri->query.afterLast = afterQueryFrag; /* QUERY END */ - return URI_FUNC(ParseUriTailTwo)(state, afterQueryFrag, afterLast, memory); - } - - default: - return first; - } -} - - - -/* - * [uriTailTwo]-><#>[queryFrag] - * [uriTailTwo]-> - */ -static URI_INLINE const URI_CHAR * URI_FUNC(ParseUriTailTwo)( - URI_TYPE(ParserState) * state, - const URI_CHAR * first, const URI_CHAR * afterLast, - UriMemoryManager * memory) { - if (first >= afterLast) { - return afterLast; - } - - switch (*first) { - case _UT('#'): - { - const URI_CHAR * const afterQueryFrag = URI_FUNC(ParseQueryFrag)(state, first + 1, afterLast, memory); - if (afterQueryFrag == NULL) { - return NULL; - } - state->uri->fragment.first = first + 1; /* FRAGMENT BEGIN */ - state->uri->fragment.afterLast = afterQueryFrag; /* FRAGMENT END */ - return afterQueryFrag; - } - - default: - return first; - } -} - - - -/* - * [zeroMoreSlashSegs]->[segment][zeroMoreSlashSegs] - * [zeroMoreSlashSegs]-> - */ -static const URI_CHAR * URI_FUNC(ParseZeroMoreSlashSegs)( - URI_TYPE(ParserState) * state, const URI_CHAR * first, - const URI_CHAR * afterLast, UriMemoryManager * memory) { - if (first >= afterLast) { - return afterLast; - } - - switch (*first) { - case _UT('/'): - { - const URI_CHAR * const afterSegment - = URI_FUNC(ParseSegment)(state, first + 1, afterLast, memory); - if (afterSegment == NULL) { - return NULL; - } - if (!URI_FUNC(PushPathSegment)(state, first + 1, afterSegment, memory)) { /* SEGMENT BOTH */ - URI_FUNC(StopMalloc)(state, memory); - return NULL; - } - return URI_FUNC(ParseZeroMoreSlashSegs)(state, afterSegment, afterLast, memory); - } - - default: - return first; - } -} - - - -static URI_INLINE void URI_FUNC(ResetParserStateExceptUri)(URI_TYPE(ParserState) * state) { - URI_TYPE(Uri) * const uriBackup = state->uri; - memset(state, 0, sizeof(URI_TYPE(ParserState))); - state->uri = uriBackup; -} - - - -static URI_INLINE UriBool URI_FUNC(PushPathSegment)( - URI_TYPE(ParserState) * state, const URI_CHAR * first, - const URI_CHAR * afterLast, UriMemoryManager * memory) { - URI_TYPE(PathSegment) * segment = memory->calloc(memory, 1, sizeof(URI_TYPE(PathSegment))); - if (segment == NULL) { - return URI_FALSE; /* Raises malloc error */ - } - if (first == afterLast) { - segment->text.first = URI_FUNC(SafeToPointTo); - segment->text.afterLast = URI_FUNC(SafeToPointTo); - } else { - segment->text.first = first; - segment->text.afterLast = afterLast; - } - - /* First segment ever? */ - if (state->uri->pathHead == NULL) { - /* First segment ever, set head and tail */ - state->uri->pathHead = segment; - state->uri->pathTail = segment; - } else { - /* Append, update tail */ - state->uri->pathTail->next = segment; - state->uri->pathTail = segment; - } - - return URI_TRUE; /* Success */ -} - - - -int URI_FUNC(ParseUriEx)(URI_TYPE(ParserState) * state, - const URI_CHAR * first, const URI_CHAR * afterLast) { - return URI_FUNC(ParseUriExMm)(state, first, afterLast, NULL); -} - - - -static int URI_FUNC(ParseUriExMm)(URI_TYPE(ParserState) * state, - const URI_CHAR * first, const URI_CHAR * afterLast, - UriMemoryManager * memory) { - const URI_CHAR * afterUriReference; - URI_TYPE(Uri) * uri; - - /* Check params */ - if ((state == NULL) || (first == NULL) || (afterLast == NULL)) { - return URI_ERROR_NULL; - } - URI_CHECK_MEMORY_MANAGER(memory); /* may return */ - - uri = state->uri; - - /* Init parser */ - URI_FUNC(ResetParserStateExceptUri)(state); - URI_FUNC(ResetUri)(uri); - - /* Parse */ - afterUriReference = URI_FUNC(ParseUriReference)(state, first, afterLast, memory); - if (afterUriReference == NULL) { - /* Waterproof errorPos <= afterLast */ - if (state->errorPos && (state->errorPos > afterLast)) { - state->errorPos = afterLast; - } - return state->errorCode; - } - if (afterUriReference != afterLast) { - if (afterUriReference < afterLast) { - URI_FUNC(StopSyntax)(state, afterUriReference, memory); - } else { - URI_FUNC(StopSyntax)(state, afterLast, memory); - } - return state->errorCode; - } - return URI_SUCCESS; -} - - - -int URI_FUNC(ParseUri)(URI_TYPE(ParserState) * state, const URI_CHAR * text) { - if ((state == NULL) || (text == NULL)) { - return URI_ERROR_NULL; - } - return URI_FUNC(ParseUriEx)(state, text, text + URI_STRLEN(text)); -} - - - -int URI_FUNC(ParseSingleUri)(URI_TYPE(Uri) * uri, const URI_CHAR * text, - const URI_CHAR ** errorPos) { - return URI_FUNC(ParseSingleUriEx)(uri, text, NULL, errorPos); -} - - - -int URI_FUNC(ParseSingleUriEx)(URI_TYPE(Uri) * uri, - const URI_CHAR * first, const URI_CHAR * afterLast, - const URI_CHAR ** errorPos) { - if ((afterLast == NULL) && (first != NULL)) { - afterLast = first + URI_STRLEN(first); - } - return URI_FUNC(ParseSingleUriExMm)(uri, first, afterLast, errorPos, NULL); -} - - - -int URI_FUNC(ParseSingleUriExMm)(URI_TYPE(Uri) * uri, - const URI_CHAR * first, const URI_CHAR * afterLast, - const URI_CHAR ** errorPos, UriMemoryManager * memory) { - URI_TYPE(ParserState) state; - int res; - - /* Check params */ - if ((uri == NULL) || (first == NULL) || (afterLast == NULL)) { - return URI_ERROR_NULL; - } - URI_CHECK_MEMORY_MANAGER(memory); /* may return */ - - state.uri = uri; - - res = URI_FUNC(ParseUriExMm)(&state, first, afterLast, memory); - - if (res != URI_SUCCESS) { - if (errorPos != NULL) { - *errorPos = state.errorPos; - } - URI_FUNC(FreeUriMembersMm)(uri, memory); - } - - return res; -} - - - -void URI_FUNC(FreeUriMembers)(URI_TYPE(Uri) * uri) { - URI_FUNC(FreeUriMembersMm)(uri, NULL); -} - - - -int URI_FUNC(FreeUriMembersMm)(URI_TYPE(Uri) * uri, UriMemoryManager * memory) { - if (uri == NULL) { - return URI_ERROR_NULL; - } - - URI_CHECK_MEMORY_MANAGER(memory); /* may return */ - - if (uri->owner) { - /* Scheme */ - if (uri->scheme.first != NULL) { - if (uri->scheme.first != uri->scheme.afterLast) { - memory->free(memory, (URI_CHAR *)uri->scheme.first); - } - uri->scheme.first = NULL; - uri->scheme.afterLast = NULL; - } - - /* User info */ - if (uri->userInfo.first != NULL) { - if (uri->userInfo.first != uri->userInfo.afterLast) { - memory->free(memory, (URI_CHAR *)uri->userInfo.first); - } - uri->userInfo.first = NULL; - uri->userInfo.afterLast = NULL; - } - - /* Host data - IPvFuture */ - if (uri->hostData.ipFuture.first != NULL) { - if (uri->hostData.ipFuture.first != uri->hostData.ipFuture.afterLast) { - memory->free(memory, (URI_CHAR *)uri->hostData.ipFuture.first); - } - uri->hostData.ipFuture.first = NULL; - uri->hostData.ipFuture.afterLast = NULL; - uri->hostText.first = NULL; - uri->hostText.afterLast = NULL; - } - - /* Host text (if regname, after IPvFuture!) */ - if ((uri->hostText.first != NULL) - && (uri->hostData.ip4 == NULL) - && (uri->hostData.ip6 == NULL)) { - /* Real regname */ - if (uri->hostText.first != uri->hostText.afterLast) { - memory->free(memory, (URI_CHAR *)uri->hostText.first); - } - uri->hostText.first = NULL; - uri->hostText.afterLast = NULL; - } - } - - /* Host data - IPv4 */ - if (uri->hostData.ip4 != NULL) { - memory->free(memory, uri->hostData.ip4); - uri->hostData.ip4 = NULL; - } - - /* Host data - IPv6 */ - if (uri->hostData.ip6 != NULL) { - memory->free(memory, uri->hostData.ip6); - uri->hostData.ip6 = NULL; - } - - /* Port text */ - if (uri->owner && (uri->portText.first != NULL)) { - if (uri->portText.first != uri->portText.afterLast) { - memory->free(memory, (URI_CHAR *)uri->portText.first); - } - uri->portText.first = NULL; - uri->portText.afterLast = NULL; - } - - /* Path */ - if (uri->pathHead != NULL) { - URI_TYPE(PathSegment) * segWalk = uri->pathHead; - while (segWalk != NULL) { - URI_TYPE(PathSegment) * const next = segWalk->next; - if (uri->owner && (segWalk->text.first != NULL) - && (segWalk->text.first < segWalk->text.afterLast)) { - memory->free(memory, (URI_CHAR *)segWalk->text.first); - } - memory->free(memory, segWalk); - segWalk = next; - } - uri->pathHead = NULL; - uri->pathTail = NULL; - } - - if (uri->owner) { - /* Query */ - if (uri->query.first != NULL) { - if (uri->query.first != uri->query.afterLast) { - memory->free(memory, (URI_CHAR *)uri->query.first); - } - uri->query.first = NULL; - uri->query.afterLast = NULL; - } - - /* Fragment */ - if (uri->fragment.first != NULL) { - if (uri->fragment.first != uri->fragment.afterLast) { - memory->free(memory, (URI_CHAR *)uri->fragment.first); - } - uri->fragment.first = NULL; - uri->fragment.afterLast = NULL; - } - } - - return URI_SUCCESS; -} - - - -UriBool URI_FUNC(_TESTING_ONLY_ParseIpSix)(const URI_CHAR * text) { - UriMemoryManager * const memory = &defaultMemoryManager; - URI_TYPE(Uri) uri; - URI_TYPE(ParserState) parser; - const URI_CHAR * const afterIpSix = text + URI_STRLEN(text); - const URI_CHAR * res; - - URI_FUNC(ResetUri)(&uri); - parser.uri = &uri; - URI_FUNC(ResetParserStateExceptUri)(&parser); - parser.uri->hostData.ip6 = memory->malloc(memory, 1 * sizeof(UriIp6)); - res = URI_FUNC(ParseIPv6address2)(&parser, text, afterIpSix, memory); - URI_FUNC(FreeUriMembersMm)(&uri, memory); - return res == afterIpSix ? URI_TRUE : URI_FALSE; -} - - - -UriBool URI_FUNC(_TESTING_ONLY_ParseIpFour)(const URI_CHAR * text) { - unsigned char octets[4]; - int res = URI_FUNC(ParseIpFourAddress)(octets, text, text + URI_STRLEN(text)); - return (res == URI_SUCCESS) ? URI_TRUE : URI_FALSE; -} - - - -#undef URI_SET_DIGIT -#undef URI_SET_HEX_LETTER_UPPER -#undef URI_SET_HEX_LETTER_LOWER -#undef URI_SET_HEXDIG -#undef URI_SET_ALPHA - - - -#endif diff --git a/cpp/src/arrow/vendored/uriparser/UriParseBase.c b/cpp/src/arrow/vendored/uriparser/UriParseBase.c deleted file mode 100644 index 1d4ef6e2bca1..000000000000 --- a/cpp/src/arrow/vendored/uriparser/UriParseBase.c +++ /dev/null @@ -1,90 +0,0 @@ -/* - * uriparser - RFC 3986 URI parsing library - * - * Copyright (C) 2007, Weijia Song - * Copyright (C) 2007, Sebastian Pipping - * 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 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. - */ - -#ifndef URI_DOXYGEN -# include "UriParseBase.h" -#endif - - - -void uriWriteQuadToDoubleByte(const unsigned char * hexDigits, int digitCount, unsigned char * output) { - switch (digitCount) { - case 1: - /* 0x___? -> \x00 \x0? */ - output[0] = 0; - output[1] = hexDigits[0]; - break; - - case 2: - /* 0x__?? -> \0xx \x?? */ - output[0] = 0; - output[1] = 16 * hexDigits[0] + hexDigits[1]; - break; - - case 3: - /* 0x_??? -> \0x? \x?? */ - output[0] = hexDigits[0]; - output[1] = 16 * hexDigits[1] + hexDigits[2]; - break; - - case 4: - /* 0x???? -> \0?? \x?? */ - output[0] = 16 * hexDigits[0] + hexDigits[1]; - output[1] = 16 * hexDigits[2] + hexDigits[3]; - break; - - } -} - - - -unsigned char uriGetOctetValue(const unsigned char * digits, int digitCount) { - switch (digitCount) { - case 1: - return digits[0]; - - case 2: - return 10 * digits[0] + digits[1]; - - case 3: - default: - return 100 * digits[0] + 10 * digits[1] + digits[2]; - - } -} diff --git a/cpp/src/arrow/vendored/uriparser/UriParseBase.h b/cpp/src/arrow/vendored/uriparser/UriParseBase.h deleted file mode 100644 index eea9ffa29d78..000000000000 --- a/cpp/src/arrow/vendored/uriparser/UriParseBase.h +++ /dev/null @@ -1,55 +0,0 @@ -/* - * uriparser - RFC 3986 URI parsing library - * - * Copyright (C) 2007, Weijia Song - * Copyright (C) 2007, Sebastian Pipping - * 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 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. - */ - -#ifndef URI_PARSE_BASE_H -#define URI_PARSE_BASE_H 1 - - - -#include "UriBase.h" - - - -void uriWriteQuadToDoubleByte(const unsigned char * hexDigits, int digitCount, - unsigned char * output); -unsigned char uriGetOctetValue(const unsigned char * digits, int digitCount); - - - -#endif /* URI_PARSE_BASE_H */ diff --git a/cpp/src/arrow/vendored/uriparser/UriQuery.c b/cpp/src/arrow/vendored/uriparser/UriQuery.c deleted file mode 100644 index 42a74aeec474..000000000000 --- a/cpp/src/arrow/vendored/uriparser/UriQuery.c +++ /dev/null @@ -1,501 +0,0 @@ -/* - * uriparser - RFC 3986 URI parsing library - * - * Copyright (C) 2007, Weijia Song - * Copyright (C) 2007, Sebastian Pipping - * 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 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. - */ - -/* What encodings are enabled? */ -#include "UriDefsConfig.h" -#if (!defined(URI_PASS_ANSI) && !defined(URI_PASS_UNICODE)) -/* Include SELF twice */ -# ifdef URI_ENABLE_ANSI -# define URI_PASS_ANSI 1 -# include "UriQuery.c" -# undef URI_PASS_ANSI -# endif -# ifdef URI_ENABLE_UNICODE -# define URI_PASS_UNICODE 1 -# include "UriQuery.c" -# undef URI_PASS_UNICODE -# endif -#else -# ifdef URI_PASS_ANSI -# include "UriDefsAnsi.h" -# else -# include "UriDefsUnicode.h" -# include -# endif - - - -#ifndef URI_DOXYGEN -# include "Uri.h" -# include "UriCommon.h" -# include "UriMemory.h" -#endif - - - -#include - - - -static int URI_FUNC(ComposeQueryEngine)(URI_CHAR * dest, - const URI_TYPE(QueryList) * queryList, - int maxChars, int * charsWritten, int * charsRequired, - UriBool spaceToPlus, UriBool normalizeBreaks); - -static UriBool URI_FUNC(AppendQueryItem)(URI_TYPE(QueryList) ** prevNext, - int * itemCount, const URI_CHAR * keyFirst, const URI_CHAR * keyAfter, - const URI_CHAR * valueFirst, const URI_CHAR * valueAfter, - UriBool plusToSpace, UriBreakConversion breakConversion, - UriMemoryManager * memory); - - - -int URI_FUNC(ComposeQueryCharsRequired)(const URI_TYPE(QueryList) * queryList, - int * charsRequired) { - const UriBool spaceToPlus = URI_TRUE; - const UriBool normalizeBreaks = URI_TRUE; - - return URI_FUNC(ComposeQueryCharsRequiredEx)(queryList, charsRequired, - spaceToPlus, normalizeBreaks); -} - - - -int URI_FUNC(ComposeQueryCharsRequiredEx)(const URI_TYPE(QueryList) * queryList, - int * charsRequired, UriBool spaceToPlus, UriBool normalizeBreaks) { - if ((queryList == NULL) || (charsRequired == NULL)) { - return URI_ERROR_NULL; - } - - return URI_FUNC(ComposeQueryEngine)(NULL, queryList, 0, NULL, - charsRequired, spaceToPlus, normalizeBreaks); -} - - - -int URI_FUNC(ComposeQuery)(URI_CHAR * dest, - const URI_TYPE(QueryList) * queryList, int maxChars, int * charsWritten) { - const UriBool spaceToPlus = URI_TRUE; - const UriBool normalizeBreaks = URI_TRUE; - - return URI_FUNC(ComposeQueryEx)(dest, queryList, maxChars, charsWritten, - spaceToPlus, normalizeBreaks); -} - - - -int URI_FUNC(ComposeQueryEx)(URI_CHAR * dest, - const URI_TYPE(QueryList) * queryList, int maxChars, int * charsWritten, - UriBool spaceToPlus, UriBool normalizeBreaks) { - if ((dest == NULL) || (queryList == NULL)) { - return URI_ERROR_NULL; - } - - if (maxChars < 1) { - return URI_ERROR_OUTPUT_TOO_LARGE; - } - - return URI_FUNC(ComposeQueryEngine)(dest, queryList, maxChars, - charsWritten, NULL, spaceToPlus, normalizeBreaks); -} - - - -int URI_FUNC(ComposeQueryMalloc)(URI_CHAR ** dest, - const URI_TYPE(QueryList) * queryList) { - const UriBool spaceToPlus = URI_TRUE; - const UriBool normalizeBreaks = URI_TRUE; - - return URI_FUNC(ComposeQueryMallocEx)(dest, queryList, - spaceToPlus, normalizeBreaks); -} - - - -int URI_FUNC(ComposeQueryMallocEx)(URI_CHAR ** dest, - const URI_TYPE(QueryList) * queryList, - UriBool spaceToPlus, UriBool normalizeBreaks) { - return URI_FUNC(ComposeQueryMallocExMm)(dest, queryList, spaceToPlus, - normalizeBreaks, NULL); -} - - - -int URI_FUNC(ComposeQueryMallocExMm)(URI_CHAR ** dest, - const URI_TYPE(QueryList) * queryList, - UriBool spaceToPlus, UriBool normalizeBreaks, - UriMemoryManager * memory) { - int charsRequired; - int res; - URI_CHAR * queryString; - - if (dest == NULL) { - return URI_ERROR_NULL; - } - - URI_CHECK_MEMORY_MANAGER(memory); /* may return */ - - /* Calculate space */ - res = URI_FUNC(ComposeQueryCharsRequiredEx)(queryList, &charsRequired, - spaceToPlus, normalizeBreaks); - if (res != URI_SUCCESS) { - return res; - } - charsRequired++; - - /* Allocate space */ - queryString = memory->malloc(memory, charsRequired * sizeof(URI_CHAR)); - if (queryString == NULL) { - return URI_ERROR_MALLOC; - } - - /* Put query in */ - res = URI_FUNC(ComposeQueryEx)(queryString, queryList, charsRequired, - NULL, spaceToPlus, normalizeBreaks); - if (res != URI_SUCCESS) { - memory->free(memory, queryString); - return res; - } - - *dest = queryString; - return URI_SUCCESS; -} - - - -int URI_FUNC(ComposeQueryEngine)(URI_CHAR * dest, - const URI_TYPE(QueryList) * queryList, - int maxChars, int * charsWritten, int * charsRequired, - UriBool spaceToPlus, UriBool normalizeBreaks) { - UriBool firstItem = URI_TRUE; - int ampersandLen = 0; /* increased to 1 from second item on */ - URI_CHAR * write = dest; - - /* Subtract terminator */ - if (dest == NULL) { - *charsRequired = 0; - } else { - maxChars--; - } - - while (queryList != NULL) { - const URI_CHAR * const key = queryList->key; - const URI_CHAR * const value = queryList->value; - const int worstCase = (normalizeBreaks == URI_TRUE ? 6 : 3); - const int keyLen = (key == NULL) ? 0 : (int)URI_STRLEN(key); - int keyRequiredChars; - const int valueLen = (value == NULL) ? 0 : (int)URI_STRLEN(value); - int valueRequiredChars; - - if ((keyLen >= INT_MAX / worstCase) || (valueLen >= INT_MAX / worstCase)) { - return URI_ERROR_OUTPUT_TOO_LARGE; - } - keyRequiredChars = worstCase * keyLen; - valueRequiredChars = worstCase * valueLen; - - if (dest == NULL) { - (*charsRequired) += ampersandLen + keyRequiredChars + ((value == NULL) - ? 0 - : 1 + valueRequiredChars); - - if (firstItem == URI_TRUE) { - ampersandLen = 1; - firstItem = URI_FALSE; - } - } else { - if ((write - dest) + ampersandLen + keyRequiredChars > maxChars) { - return URI_ERROR_OUTPUT_TOO_LARGE; - } - - /* Copy key */ - if (firstItem == URI_TRUE) { - ampersandLen = 1; - firstItem = URI_FALSE; - } else { - write[0] = _UT('&'); - write++; - } - write = URI_FUNC(EscapeEx)(key, key + keyLen, - write, spaceToPlus, normalizeBreaks); - - if (value != NULL) { - if ((write - dest) + 1 + valueRequiredChars > maxChars) { - return URI_ERROR_OUTPUT_TOO_LARGE; - } - - /* Copy value */ - write[0] = _UT('='); - write++; - write = URI_FUNC(EscapeEx)(value, value + valueLen, - write, spaceToPlus, normalizeBreaks); - } - } - - queryList = queryList->next; - } - - if (dest != NULL) { - write[0] = _UT('\0'); - if (charsWritten != NULL) { - *charsWritten = (int)(write - dest) + 1; /* .. for terminator */ - } - } - - return URI_SUCCESS; -} - - - -UriBool URI_FUNC(AppendQueryItem)(URI_TYPE(QueryList) ** prevNext, - int * itemCount, const URI_CHAR * keyFirst, const URI_CHAR * keyAfter, - const URI_CHAR * valueFirst, const URI_CHAR * valueAfter, - UriBool plusToSpace, UriBreakConversion breakConversion, - UriMemoryManager * memory) { - const int keyLen = (int)(keyAfter - keyFirst); - const int valueLen = (int)(valueAfter - valueFirst); - URI_CHAR * key; - URI_CHAR * value; - - if ((prevNext == NULL) || (itemCount == NULL) - || (keyFirst == NULL) || (keyAfter == NULL) - || (keyFirst > keyAfter) || (valueFirst > valueAfter) - || ((keyFirst == keyAfter) - && (valueFirst == NULL) && (valueAfter == NULL))) { - return URI_TRUE; - } - - /* Append new empty item */ - *prevNext = memory->malloc(memory, 1 * sizeof(URI_TYPE(QueryList))); - if (*prevNext == NULL) { - return URI_FALSE; /* Raises malloc error */ - } - (*prevNext)->next = NULL; - - - /* Fill key */ - key = memory->malloc(memory, (keyLen + 1) * sizeof(URI_CHAR)); - if (key == NULL) { - memory->free(memory, *prevNext); - *prevNext = NULL; - return URI_FALSE; /* Raises malloc error */ - } - - key[keyLen] = _UT('\0'); - if (keyLen > 0) { - /* Copy 1:1 */ - memcpy(key, keyFirst, keyLen * sizeof(URI_CHAR)); - - /* Unescape */ - URI_FUNC(UnescapeInPlaceEx)(key, plusToSpace, breakConversion); - } - (*prevNext)->key = key; - - - /* Fill value */ - if (valueFirst != NULL) { - value = memory->malloc(memory, (valueLen + 1) * sizeof(URI_CHAR)); - if (value == NULL) { - memory->free(memory, key); - memory->free(memory, *prevNext); - *prevNext = NULL; - return URI_FALSE; /* Raises malloc error */ - } - - value[valueLen] = _UT('\0'); - if (valueLen > 0) { - /* Copy 1:1 */ - memcpy(value, valueFirst, valueLen * sizeof(URI_CHAR)); - - /* Unescape */ - URI_FUNC(UnescapeInPlaceEx)(value, plusToSpace, breakConversion); - } - (*prevNext)->value = value; - } else { - value = NULL; - } - (*prevNext)->value = value; - - (*itemCount)++; - return URI_TRUE; -} - - - -void URI_FUNC(FreeQueryList)(URI_TYPE(QueryList) * queryList) { - URI_FUNC(FreeQueryListMm)(queryList, NULL); -} - - - -int URI_FUNC(FreeQueryListMm)(URI_TYPE(QueryList) * queryList, - UriMemoryManager * memory) { - URI_CHECK_MEMORY_MANAGER(memory); /* may return */ - while (queryList != NULL) { - URI_TYPE(QueryList) * nextBackup = queryList->next; - memory->free(memory, (URI_CHAR *)queryList->key); /* const cast */ - memory->free(memory, (URI_CHAR *)queryList->value); /* const cast */ - memory->free(memory, queryList); - queryList = nextBackup; - } - return URI_SUCCESS; -} - - - -int URI_FUNC(DissectQueryMalloc)(URI_TYPE(QueryList) ** dest, int * itemCount, - const URI_CHAR * first, const URI_CHAR * afterLast) { - const UriBool plusToSpace = URI_TRUE; - const UriBreakConversion breakConversion = URI_BR_DONT_TOUCH; - - return URI_FUNC(DissectQueryMallocEx)(dest, itemCount, first, afterLast, - plusToSpace, breakConversion); -} - - - -int URI_FUNC(DissectQueryMallocEx)(URI_TYPE(QueryList) ** dest, int * itemCount, - const URI_CHAR * first, const URI_CHAR * afterLast, - UriBool plusToSpace, UriBreakConversion breakConversion) { - return URI_FUNC(DissectQueryMallocExMm)(dest, itemCount, first, afterLast, - plusToSpace, breakConversion, NULL); -} - - - -int URI_FUNC(DissectQueryMallocExMm)(URI_TYPE(QueryList) ** dest, int * itemCount, - const URI_CHAR * first, const URI_CHAR * afterLast, - UriBool plusToSpace, UriBreakConversion breakConversion, - UriMemoryManager * memory) { - const URI_CHAR * walk = first; - const URI_CHAR * keyFirst = first; - const URI_CHAR * keyAfter = NULL; - const URI_CHAR * valueFirst = NULL; - const URI_CHAR * valueAfter = NULL; - URI_TYPE(QueryList) ** prevNext = dest; - int nullCounter; - int * itemsAppended = (itemCount == NULL) ? &nullCounter : itemCount; - - if ((dest == NULL) || (first == NULL) || (afterLast == NULL)) { - return URI_ERROR_NULL; - } - - if (first > afterLast) { - return URI_ERROR_RANGE_INVALID; - } - - URI_CHECK_MEMORY_MANAGER(memory); /* may return */ - - *dest = NULL; - *itemsAppended = 0; - - /* Parse query string */ - for (; walk < afterLast; walk++) { - switch (*walk) { - case _UT('&'): - if (valueFirst != NULL) { - valueAfter = walk; - } else { - keyAfter = walk; - } - - if (URI_FUNC(AppendQueryItem)(prevNext, itemsAppended, - keyFirst, keyAfter, valueFirst, valueAfter, - plusToSpace, breakConversion, memory) - == URI_FALSE) { - /* Free list we built */ - *itemsAppended = 0; - URI_FUNC(FreeQueryListMm)(*dest, memory); - return URI_ERROR_MALLOC; - } - - /* Make future items children of the current */ - if ((prevNext != NULL) && (*prevNext != NULL)) { - prevNext = &((*prevNext)->next); - } - - if (walk + 1 < afterLast) { - keyFirst = walk + 1; - } else { - keyFirst = NULL; - } - keyAfter = NULL; - valueFirst = NULL; - valueAfter = NULL; - break; - - case _UT('='): - /* NOTE: WE treat the first '=' as a separator, */ - /* all following go into the value part */ - if (keyAfter == NULL) { - keyAfter = walk; - if (walk + 1 <= afterLast) { - valueFirst = walk + 1; - valueAfter = walk + 1; - } - } - break; - - default: - break; - } - } - - if (valueFirst != NULL) { - /* Must be key/value pair */ - valueAfter = walk; - } else { - /* Must be key only */ - keyAfter = walk; - } - - if (URI_FUNC(AppendQueryItem)(prevNext, itemsAppended, keyFirst, keyAfter, - valueFirst, valueAfter, plusToSpace, breakConversion, memory) - == URI_FALSE) { - /* Free list we built */ - *itemsAppended = 0; - URI_FUNC(FreeQueryListMm)(*dest, memory); - return URI_ERROR_MALLOC; - } - - return URI_SUCCESS; -} - - - -#endif diff --git a/cpp/src/arrow/vendored/uriparser/UriRecompose.c b/cpp/src/arrow/vendored/uriparser/UriRecompose.c deleted file mode 100644 index 2f987215fa18..000000000000 --- a/cpp/src/arrow/vendored/uriparser/UriRecompose.c +++ /dev/null @@ -1,577 +0,0 @@ -/* - * uriparser - RFC 3986 URI parsing library - * - * Copyright (C) 2007, Weijia Song - * Copyright (C) 2007, Sebastian Pipping - * 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 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. - */ - -/* What encodings are enabled? */ -#include "UriDefsConfig.h" -#if (!defined(URI_PASS_ANSI) && !defined(URI_PASS_UNICODE)) -/* Include SELF twice */ -# ifdef URI_ENABLE_ANSI -# define URI_PASS_ANSI 1 -# include "UriRecompose.c" -# undef URI_PASS_ANSI -# endif -# ifdef URI_ENABLE_UNICODE -# define URI_PASS_UNICODE 1 -# include "UriRecompose.c" -# undef URI_PASS_UNICODE -# endif -#else -# ifdef URI_PASS_ANSI -# include "UriDefsAnsi.h" -# else -# include "UriDefsUnicode.h" -# include -# endif - - - -#ifndef URI_DOXYGEN -# include "Uri.h" -# include "UriCommon.h" -#endif - - - -static int URI_FUNC(ToStringEngine)(URI_CHAR * dest, const URI_TYPE(Uri) * uri, - int maxChars, int * charsWritten, int * charsRequired); - - - -int URI_FUNC(ToStringCharsRequired)(const URI_TYPE(Uri) * uri, - int * charsRequired) { - const int MAX_CHARS = ((unsigned int)-1) >> 1; - return URI_FUNC(ToStringEngine)(NULL, uri, MAX_CHARS, NULL, charsRequired); -} - - - -int URI_FUNC(ToString)(URI_CHAR * dest, const URI_TYPE(Uri) * uri, - int maxChars, int * charsWritten) { - return URI_FUNC(ToStringEngine)(dest, uri, maxChars, charsWritten, NULL); -} - - - -static URI_INLINE int URI_FUNC(ToStringEngine)(URI_CHAR * dest, - const URI_TYPE(Uri) * uri, int maxChars, int * charsWritten, - int * charsRequired) { - int written = 0; - if ((uri == NULL) || ((dest == NULL) && (charsRequired == NULL))) { - if (charsWritten != NULL) { - *charsWritten = 0; - } - return URI_ERROR_NULL; - } - - if (maxChars < 1) { - if (charsWritten != NULL) { - *charsWritten = 0; - } - return URI_ERROR_TOSTRING_TOO_LONG; - } - maxChars--; /* So we don't have to subtract 1 for '\0' all the time */ - - /* [01/19] result = "" */ - if (dest != NULL) { - dest[0] = _UT('\0'); - } else { - (*charsRequired) = 0; - } - /* [02/19] if defined(scheme) then */ - if (uri->scheme.first != NULL) { - /* [03/19] append scheme to result; */ - const int charsToWrite - = (int)(uri->scheme.afterLast - uri->scheme.first); - if (dest != NULL) { - if (written + charsToWrite <= maxChars) { - memcpy(dest + written, uri->scheme.first, - charsToWrite * sizeof(URI_CHAR)); - written += charsToWrite; - } else { - dest[0] = _UT('\0'); - if (charsWritten != NULL) { - *charsWritten = 0; - } - return URI_ERROR_TOSTRING_TOO_LONG; - } - } else { - (*charsRequired) += charsToWrite; - } - /* [04/19] append ":" to result; */ - if (dest != NULL) { - if (written + 1 <= maxChars) { - memcpy(dest + written, _UT(":"), - 1 * sizeof(URI_CHAR)); - written += 1; - } else { - dest[0] = _UT('\0'); - if (charsWritten != NULL) { - *charsWritten = 0; - } - return URI_ERROR_TOSTRING_TOO_LONG; - } - } else { - (*charsRequired) += 1; - } - /* [05/19] endif; */ - } - /* [06/19] if defined(authority) then */ - if (URI_FUNC(IsHostSet)(uri)) { - /* [07/19] append "//" to result; */ - if (dest != NULL) { - if (written + 2 <= maxChars) { - memcpy(dest + written, _UT("//"), - 2 * sizeof(URI_CHAR)); - written += 2; - } else { - dest[0] = _UT('\0'); - if (charsWritten != NULL) { - *charsWritten = 0; - } - return URI_ERROR_TOSTRING_TOO_LONG; - } - } else { - (*charsRequired) += 2; - } - /* [08/19] append authority to result; */ - /* UserInfo */ - if (uri->userInfo.first != NULL) { - const int charsToWrite = (int)(uri->userInfo.afterLast - uri->userInfo.first); - if (dest != NULL) { - if (written + charsToWrite <= maxChars) { - memcpy(dest + written, uri->userInfo.first, - charsToWrite * sizeof(URI_CHAR)); - written += charsToWrite; - } else { - dest[0] = _UT('\0'); - if (charsWritten != NULL) { - *charsWritten = 0; - } - return URI_ERROR_TOSTRING_TOO_LONG; - } - - if (written + 1 <= maxChars) { - memcpy(dest + written, _UT("@"), - 1 * sizeof(URI_CHAR)); - written += 1; - } else { - dest[0] = _UT('\0'); - if (charsWritten != NULL) { - *charsWritten = 0; - } - return URI_ERROR_TOSTRING_TOO_LONG; - } - } else { - (*charsRequired) += charsToWrite + 1; - } - } - - /* Host */ - if (uri->hostData.ip4 != NULL) { - /* IPv4 */ - int i = 0; - for (; i < 4; i++) { - const unsigned char value = uri->hostData.ip4->data[i]; - const int charsToWrite = (value > 99) ? 3 : ((value > 9) ? 2 : 1); - if (dest != NULL) { - if (written + charsToWrite <= maxChars) { - URI_CHAR text[4]; - if (value > 99) { - text[0] = _UT('0') + (value / 100); - text[1] = _UT('0') + ((value % 100) / 10); - text[2] = _UT('0') + (value % 10); - } else if (value > 9) { - text[0] = _UT('0') + (value / 10); - text[1] = _UT('0') + (value % 10); - } else { - text[0] = _UT('0') + value; - } - text[charsToWrite] = _UT('\0'); - memcpy(dest + written, text, charsToWrite * sizeof(URI_CHAR)); - written += charsToWrite; - } else { - dest[0] = _UT('\0'); - if (charsWritten != NULL) { - *charsWritten = 0; - } - return URI_ERROR_TOSTRING_TOO_LONG; - } - if (i < 3) { - if (written + 1 <= maxChars) { - memcpy(dest + written, _UT("."), - 1 * sizeof(URI_CHAR)); - written += 1; - } else { - dest[0] = _UT('\0'); - if (charsWritten != NULL) { - *charsWritten = 0; - } - return URI_ERROR_TOSTRING_TOO_LONG; - } - } - } else { - (*charsRequired) += charsToWrite + ((i == 3) ? 0 : 1); - } - } - } else if (uri->hostData.ip6 != NULL) { - /* IPv6 */ - int i = 0; - if (dest != NULL) { - if (written + 1 <= maxChars) { - memcpy(dest + written, _UT("["), - 1 * sizeof(URI_CHAR)); - written += 1; - } else { - dest[0] = _UT('\0'); - if (charsWritten != NULL) { - *charsWritten = 0; - } - return URI_ERROR_TOSTRING_TOO_LONG; - } - } else { - (*charsRequired) += 1; - } - - for (; i < 16; i++) { - const unsigned char value = uri->hostData.ip6->data[i]; - if (dest != NULL) { - if (written + 2 <= maxChars) { - URI_CHAR text[3]; - text[0] = URI_FUNC(HexToLetterEx)(value / 16, URI_FALSE); - text[1] = URI_FUNC(HexToLetterEx)(value % 16, URI_FALSE); - text[2] = _UT('\0'); - memcpy(dest + written, text, 2 * sizeof(URI_CHAR)); - written += 2; - } else { - dest[0] = _UT('\0'); - if (charsWritten != NULL) { - *charsWritten = 0; - } - return URI_ERROR_TOSTRING_TOO_LONG; - } - } else { - (*charsRequired) += 2; - } - if (((i & 1) == 1) && (i < 15)) { - if (dest != NULL) { - if (written + 1 <= maxChars) { - memcpy(dest + written, _UT(":"), - 1 * sizeof(URI_CHAR)); - written += 1; - } else { - dest[0] = _UT('\0'); - if (charsWritten != NULL) { - *charsWritten = 0; - } - return URI_ERROR_TOSTRING_TOO_LONG; - } - } else { - (*charsRequired) += 1; - } - } - } - - if (dest != NULL) { - if (written + 1 <= maxChars) { - memcpy(dest + written, _UT("]"), - 1 * sizeof(URI_CHAR)); - written += 1; - } else { - dest[0] = _UT('\0'); - if (charsWritten != NULL) { - *charsWritten = 0; - } - return URI_ERROR_TOSTRING_TOO_LONG; - } - } else { - (*charsRequired) += 1; - } - } else if (uri->hostData.ipFuture.first != NULL) { - /* IPvFuture */ - const int charsToWrite = (int)(uri->hostData.ipFuture.afterLast - - uri->hostData.ipFuture.first); - if (dest != NULL) { - if (written + 1 <= maxChars) { - memcpy(dest + written, _UT("["), - 1 * sizeof(URI_CHAR)); - written += 1; - } else { - dest[0] = _UT('\0'); - if (charsWritten != NULL) { - *charsWritten = 0; - } - return URI_ERROR_TOSTRING_TOO_LONG; - } - - if (written + charsToWrite <= maxChars) { - memcpy(dest + written, uri->hostData.ipFuture.first, charsToWrite * sizeof(URI_CHAR)); - written += charsToWrite; - } else { - dest[0] = _UT('\0'); - if (charsWritten != NULL) { - *charsWritten = 0; - } - return URI_ERROR_TOSTRING_TOO_LONG; - } - - if (written + 1 <= maxChars) { - memcpy(dest + written, _UT("]"), - 1 * sizeof(URI_CHAR)); - written += 1; - } else { - dest[0] = _UT('\0'); - if (charsWritten != NULL) { - *charsWritten = 0; - } - return URI_ERROR_TOSTRING_TOO_LONG; - } - } else { - (*charsRequired) += 1 + charsToWrite + 1; - } - } else if (uri->hostText.first != NULL) { - /* Regname */ - const int charsToWrite = (int)(uri->hostText.afterLast - uri->hostText.first); - if (dest != NULL) { - if (written + charsToWrite <= maxChars) { - memcpy(dest + written, uri->hostText.first, - charsToWrite * sizeof(URI_CHAR)); - written += charsToWrite; - } else { - dest[0] = _UT('\0'); - if (charsWritten != NULL) { - *charsWritten = 0; - } - return URI_ERROR_TOSTRING_TOO_LONG; - } - } else { - (*charsRequired) += charsToWrite; - } - } - - /* Port */ - if (uri->portText.first != NULL) { - const int charsToWrite = (int)(uri->portText.afterLast - uri->portText.first); - if (dest != NULL) { - /* Leading ':' */ - if (written + 1 <= maxChars) { - memcpy(dest + written, _UT(":"), - 1 * sizeof(URI_CHAR)); - written += 1; - } else { - dest[0] = _UT('\0'); - if (charsWritten != NULL) { - *charsWritten = 0; - } - return URI_ERROR_TOSTRING_TOO_LONG; - } - - /* Port number */ - if (written + charsToWrite <= maxChars) { - memcpy(dest + written, uri->portText.first, - charsToWrite * sizeof(URI_CHAR)); - written += charsToWrite; - } else { - dest[0] = _UT('\0'); - if (charsWritten != NULL) { - *charsWritten = 0; - } - return URI_ERROR_TOSTRING_TOO_LONG; - } - } else { - (*charsRequired) += 1 + charsToWrite; - } - } - /* [09/19] endif; */ - } - /* [10/19] append path to result; */ - /* Slash needed here? */ - if (uri->absolutePath || ((uri->pathHead != NULL) - && URI_FUNC(IsHostSet)(uri))) { - if (dest != NULL) { - if (written + 1 <= maxChars) { - memcpy(dest + written, _UT("/"), - 1 * sizeof(URI_CHAR)); - written += 1; - } else { - dest[0] = _UT('\0'); - if (charsWritten != NULL) { - *charsWritten = 0; - } - return URI_ERROR_TOSTRING_TOO_LONG; - } - } else { - (*charsRequired) += 1; - } - } - - if (uri->pathHead != NULL) { - URI_TYPE(PathSegment) * walker = uri->pathHead; - do { - const int charsToWrite = (int)(walker->text.afterLast - walker->text.first); - if (dest != NULL) { - if (written + charsToWrite <= maxChars) { - memcpy(dest + written, walker->text.first, - charsToWrite * sizeof(URI_CHAR)); - written += charsToWrite; - } else { - dest[0] = _UT('\0'); - if (charsWritten != NULL) { - *charsWritten = 0; - } - return URI_ERROR_TOSTRING_TOO_LONG; - } - } else { - (*charsRequired) += charsToWrite; - } - - /* Not last segment -> append slash */ - if (walker->next != NULL) { - if (dest != NULL) { - if (written + 1 <= maxChars) { - memcpy(dest + written, _UT("/"), - 1 * sizeof(URI_CHAR)); - written += 1; - } else { - dest[0] = _UT('\0'); - if (charsWritten != NULL) { - *charsWritten = 0; - } - return URI_ERROR_TOSTRING_TOO_LONG; - } - } else { - (*charsRequired) += 1; - } - } - - walker = walker->next; - } while (walker != NULL); - } - /* [11/19] if defined(query) then */ - if (uri->query.first != NULL) { - /* [12/19] append "?" to result; */ - if (dest != NULL) { - if (written + 1 <= maxChars) { - memcpy(dest + written, _UT("?"), - 1 * sizeof(URI_CHAR)); - written += 1; - } else { - dest[0] = _UT('\0'); - if (charsWritten != NULL) { - *charsWritten = 0; - } - return URI_ERROR_TOSTRING_TOO_LONG; - } - } else { - (*charsRequired) += 1; - } - /* [13/19] append query to result; */ - { - const int charsToWrite - = (int)(uri->query.afterLast - uri->query.first); - if (dest != NULL) { - if (written + charsToWrite <= maxChars) { - memcpy(dest + written, uri->query.first, - charsToWrite * sizeof(URI_CHAR)); - written += charsToWrite; - } else { - dest[0] = _UT('\0'); - if (charsWritten != NULL) { - *charsWritten = 0; - } - return URI_ERROR_TOSTRING_TOO_LONG; - } - } else { - (*charsRequired) += charsToWrite; - } - } - /* [14/19] endif; */ - } - /* [15/19] if defined(fragment) then */ - if (uri->fragment.first != NULL) { - /* [16/19] append "#" to result; */ - if (dest != NULL) { - if (written + 1 <= maxChars) { - memcpy(dest + written, _UT("#"), - 1 * sizeof(URI_CHAR)); - written += 1; - } else { - dest[0] = _UT('\0'); - if (charsWritten != NULL) { - *charsWritten = 0; - } - return URI_ERROR_TOSTRING_TOO_LONG; - } - } else { - (*charsRequired) += 1; - } - /* [17/19] append fragment to result; */ - { - const int charsToWrite - = (int)(uri->fragment.afterLast - uri->fragment.first); - if (dest != NULL) { - if (written + charsToWrite <= maxChars) { - memcpy(dest + written, uri->fragment.first, - charsToWrite * sizeof(URI_CHAR)); - written += charsToWrite; - } else { - dest[0] = _UT('\0'); - if (charsWritten != NULL) { - *charsWritten = 0; - } - return URI_ERROR_TOSTRING_TOO_LONG; - } - } else { - (*charsRequired) += charsToWrite; - } - } - /* [18/19] endif; */ - } - /* [19/19] return result; */ - if (dest != NULL) { - dest[written++] = _UT('\0'); - if (charsWritten != NULL) { - *charsWritten = written; - } - } - return URI_SUCCESS; -} - - - -#endif diff --git a/cpp/src/arrow/vendored/uriparser/UriResolve.c b/cpp/src/arrow/vendored/uriparser/UriResolve.c deleted file mode 100644 index ee4cba818a5b..000000000000 --- a/cpp/src/arrow/vendored/uriparser/UriResolve.c +++ /dev/null @@ -1,329 +0,0 @@ -/* - * uriparser - RFC 3986 URI parsing library - * - * Copyright (C) 2007, Weijia Song - * Copyright (C) 2007, Sebastian Pipping - * 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 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. - */ - -/* What encodings are enabled? */ -#include "UriDefsConfig.h" -#if (!defined(URI_PASS_ANSI) && !defined(URI_PASS_UNICODE)) -/* Include SELF twice */ -# ifdef URI_ENABLE_ANSI -# define URI_PASS_ANSI 1 -# include "UriResolve.c" -# undef URI_PASS_ANSI -# endif -# ifdef URI_ENABLE_UNICODE -# define URI_PASS_UNICODE 1 -# include "UriResolve.c" -# undef URI_PASS_UNICODE -# endif -#else -# ifdef URI_PASS_ANSI -# include "UriDefsAnsi.h" -# else -# include "UriDefsUnicode.h" -# include -# endif - - - -#ifndef URI_DOXYGEN -# include "Uri.h" -# include "UriCommon.h" -# include "UriMemory.h" -#endif - - - -/* Appends a relative URI to an absolute. The last path segment of - * the absolute URI is replaced. */ -static URI_INLINE UriBool URI_FUNC(MergePath)(URI_TYPE(Uri) * absWork, - const URI_TYPE(Uri) * relAppend, UriMemoryManager * memory) { - URI_TYPE(PathSegment) * sourceWalker; - URI_TYPE(PathSegment) * destPrev; - if (relAppend->pathHead == NULL) { - return URI_TRUE; - } - - /* Replace last segment ("" if trailing slash) with first of append chain */ - if (absWork->pathHead == NULL) { - URI_TYPE(PathSegment) * const dup = memory->malloc(memory, sizeof(URI_TYPE(PathSegment))); - if (dup == NULL) { - return URI_FALSE; /* Raises malloc error */ - } - dup->next = NULL; - absWork->pathHead = dup; - absWork->pathTail = dup; - } - absWork->pathTail->text.first = relAppend->pathHead->text.first; - absWork->pathTail->text.afterLast = relAppend->pathHead->text.afterLast; - - /* Append all the others */ - sourceWalker = relAppend->pathHead->next; - if (sourceWalker == NULL) { - return URI_TRUE; - } - destPrev = absWork->pathTail; - - for (;;) { - URI_TYPE(PathSegment) * const dup = memory->malloc(memory, sizeof(URI_TYPE(PathSegment))); - if (dup == NULL) { - destPrev->next = NULL; - absWork->pathTail = destPrev; - return URI_FALSE; /* Raises malloc error */ - } - dup->text = sourceWalker->text; - destPrev->next = dup; - - if (sourceWalker->next == NULL) { - absWork->pathTail = dup; - absWork->pathTail->next = NULL; - break; - } - destPrev = dup; - sourceWalker = sourceWalker->next; - } - - return URI_TRUE; -} - - -static int URI_FUNC(ResolveAbsolutePathFlag)(URI_TYPE(Uri) * absWork, - UriMemoryManager * memory) { - if (absWork == NULL) { - return URI_ERROR_NULL; - } - - if (URI_FUNC(IsHostSet)(absWork) && absWork->absolutePath) { - /* Empty segment needed, instead? */ - if (absWork->pathHead == NULL) { - URI_TYPE(PathSegment) * const segment = memory->malloc(memory, sizeof(URI_TYPE(PathSegment))); - if (segment == NULL) { - return URI_ERROR_MALLOC; - } - segment->text.first = URI_FUNC(SafeToPointTo); - segment->text.afterLast = URI_FUNC(SafeToPointTo); - segment->next = NULL; - - absWork->pathHead = segment; - absWork->pathTail = segment; - } - - absWork->absolutePath = URI_FALSE; - } - - return URI_SUCCESS; -} - - -static int URI_FUNC(AddBaseUriImpl)(URI_TYPE(Uri) * absDest, - const URI_TYPE(Uri) * relSource, - const URI_TYPE(Uri) * absBase, - UriResolutionOptions options, UriMemoryManager * memory) { - UriBool relSourceHasScheme; - - if (absDest == NULL) { - return URI_ERROR_NULL; - } - URI_FUNC(ResetUri)(absDest); - - if ((relSource == NULL) || (absBase == NULL)) { - return URI_ERROR_NULL; - } - - /* absBase absolute? */ - if (absBase->scheme.first == NULL) { - return URI_ERROR_ADDBASE_REL_BASE; - } - - /* [00/32] -- A non-strict parser may ignore a scheme in the reference */ - /* [00/32] -- if it is identical to the base URI's scheme. */ - /* [00/32] if ((not strict) and (R.scheme == Base.scheme)) then */ - relSourceHasScheme = (relSource->scheme.first != NULL) ? URI_TRUE : URI_FALSE; - if ((options & URI_RESOLVE_IDENTICAL_SCHEME_COMPAT) - && (absBase->scheme.first != NULL) - && (relSource->scheme.first != NULL) - && (0 == URI_FUNC(CompareRange)(&(absBase->scheme), &(relSource->scheme)))) { - /* [00/32] undefine(R.scheme); */ - relSourceHasScheme = URI_FALSE; - /* [00/32] endif; */ - } - - /* [01/32] if defined(R.scheme) then */ - if (relSourceHasScheme) { - /* [02/32] T.scheme = R.scheme; */ - absDest->scheme = relSource->scheme; - /* [03/32] T.authority = R.authority; */ - if (!URI_FUNC(CopyAuthority)(absDest, relSource, memory)) { - return URI_ERROR_MALLOC; - } - /* [04/32] T.path = remove_dot_segments(R.path); */ - if (!URI_FUNC(CopyPath)(absDest, relSource, memory)) { - return URI_ERROR_MALLOC; - } - if (!URI_FUNC(RemoveDotSegmentsAbsolute)(absDest, memory)) { - return URI_ERROR_MALLOC; - } - /* [05/32] T.query = R.query; */ - absDest->query = relSource->query; - /* [06/32] else */ - } else { - /* [07/32] if defined(R.authority) then */ - if (URI_FUNC(IsHostSet)(relSource)) { - /* [08/32] T.authority = R.authority; */ - if (!URI_FUNC(CopyAuthority)(absDest, relSource, memory)) { - return URI_ERROR_MALLOC; - } - /* [09/32] T.path = remove_dot_segments(R.path); */ - if (!URI_FUNC(CopyPath)(absDest, relSource, memory)) { - return URI_ERROR_MALLOC; - } - if (!URI_FUNC(RemoveDotSegmentsAbsolute)(absDest, memory)) { - return URI_ERROR_MALLOC; - } - /* [10/32] T.query = R.query; */ - absDest->query = relSource->query; - /* [11/32] else */ - } else { - /* [28/32] T.authority = Base.authority; */ - if (!URI_FUNC(CopyAuthority)(absDest, absBase, memory)) { - return URI_ERROR_MALLOC; - } - /* [12/32] if (R.path == "") then */ - if (relSource->pathHead == NULL && !relSource->absolutePath) { - /* [13/32] T.path = Base.path; */ - if (!URI_FUNC(CopyPath)(absDest, absBase, memory)) { - return URI_ERROR_MALLOC; - } - /* [14/32] if defined(R.query) then */ - if (relSource->query.first != NULL) { - /* [15/32] T.query = R.query; */ - absDest->query = relSource->query; - /* [16/32] else */ - } else { - /* [17/32] T.query = Base.query; */ - absDest->query = absBase->query; - /* [18/32] endif; */ - } - /* [19/32] else */ - } else { - /* [20/32] if (R.path starts-with "/") then */ - if (relSource->absolutePath) { - int res; - /* [21/32] T.path = remove_dot_segments(R.path); */ - if (!URI_FUNC(CopyPath)(absDest, relSource, memory)) { - return URI_ERROR_MALLOC; - } - res = URI_FUNC(ResolveAbsolutePathFlag)(absDest, memory); - if (res != URI_SUCCESS) { - return res; - } - if (!URI_FUNC(RemoveDotSegmentsAbsolute)(absDest, memory)) { - return URI_ERROR_MALLOC; - } - /* [22/32] else */ - } else { - /* [23/32] T.path = merge(Base.path, R.path); */ - if (!URI_FUNC(CopyPath)(absDest, absBase, memory)) { - return URI_ERROR_MALLOC; - } - if (!URI_FUNC(MergePath)(absDest, relSource, memory)) { - return URI_ERROR_MALLOC; - } - /* [24/32] T.path = remove_dot_segments(T.path); */ - if (!URI_FUNC(RemoveDotSegmentsAbsolute)(absDest, memory)) { - return URI_ERROR_MALLOC; - } - - if (!URI_FUNC(FixAmbiguity)(absDest, memory)) { - return URI_ERROR_MALLOC; - } - /* [25/32] endif; */ - } - /* [26/32] T.query = R.query; */ - absDest->query = relSource->query; - /* [27/32] endif; */ - } - URI_FUNC(FixEmptyTrailSegment)(absDest, memory); - /* [29/32] endif; */ - } - /* [30/32] T.scheme = Base.scheme; */ - absDest->scheme = absBase->scheme; - /* [31/32] endif; */ - } - /* [32/32] T.fragment = R.fragment; */ - absDest->fragment = relSource->fragment; - - return URI_SUCCESS; - -} - - - -int URI_FUNC(AddBaseUri)(URI_TYPE(Uri) * absDest, - const URI_TYPE(Uri) * relSource, const URI_TYPE(Uri) * absBase) { - const UriResolutionOptions options = URI_RESOLVE_STRICTLY; - return URI_FUNC(AddBaseUriEx)(absDest, relSource, absBase, options); -} - - - -int URI_FUNC(AddBaseUriEx)(URI_TYPE(Uri) * absDest, - const URI_TYPE(Uri) * relSource, const URI_TYPE(Uri) * absBase, - UriResolutionOptions options) { - return URI_FUNC(AddBaseUriExMm)(absDest, relSource, absBase, options, NULL); -} - - - -int URI_FUNC(AddBaseUriExMm)(URI_TYPE(Uri) * absDest, - const URI_TYPE(Uri) * relSource, const URI_TYPE(Uri) * absBase, - UriResolutionOptions options, UriMemoryManager * memory) { - int res; - - URI_CHECK_MEMORY_MANAGER(memory); /* may return */ - - res = URI_FUNC(AddBaseUriImpl)(absDest, relSource, absBase, options, memory); - if ((res != URI_SUCCESS) && (absDest != NULL)) { - URI_FUNC(FreeUriMembersMm)(absDest, memory); - } - return res; -} - - - -#endif diff --git a/cpp/src/arrow/vendored/uriparser/UriShorten.c b/cpp/src/arrow/vendored/uriparser/UriShorten.c deleted file mode 100644 index f00b05f59457..000000000000 --- a/cpp/src/arrow/vendored/uriparser/UriShorten.c +++ /dev/null @@ -1,324 +0,0 @@ -/* - * uriparser - RFC 3986 URI parsing library - * - * Copyright (C) 2007, Weijia Song - * Copyright (C) 2007, Sebastian Pipping - * 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 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. - */ - -/* What encodings are enabled? */ -#include "UriDefsConfig.h" -#if (!defined(URI_PASS_ANSI) && !defined(URI_PASS_UNICODE)) -/* Include SELF twice */ -# ifdef URI_ENABLE_ANSI -# define URI_PASS_ANSI 1 -# include "UriShorten.c" -# undef URI_PASS_ANSI -# endif -# ifdef URI_ENABLE_UNICODE -# define URI_PASS_UNICODE 1 -# include "UriShorten.c" -# undef URI_PASS_UNICODE -# endif -#else -# ifdef URI_PASS_ANSI -# include "UriDefsAnsi.h" -# else -# include "UriDefsUnicode.h" -# include -# endif - - - -#ifndef URI_DOXYGEN -# include "Uri.h" -# include "UriCommon.h" -# include "UriMemory.h" -#endif - - - -static URI_INLINE UriBool URI_FUNC(AppendSegment)(URI_TYPE(Uri) * uri, - const URI_CHAR * first, const URI_CHAR * afterLast, - UriMemoryManager * memory) { - /* Create segment */ - URI_TYPE(PathSegment) * segment = memory->malloc(memory, 1 * sizeof(URI_TYPE(PathSegment))); - if (segment == NULL) { - return URI_FALSE; /* Raises malloc error */ - } - segment->next = NULL; - segment->text.first = first; - segment->text.afterLast = afterLast; - - /* Put into chain */ - if (uri->pathTail == NULL) { - uri->pathHead = segment; - } else { - uri->pathTail->next = segment; - } - uri->pathTail = segment; - - return URI_TRUE; -} - - - -static URI_INLINE UriBool URI_FUNC(EqualsAuthority)(const URI_TYPE(Uri) * first, - const URI_TYPE(Uri) * second) { - /* IPv4 */ - if (first->hostData.ip4 != NULL) { - return ((second->hostData.ip4 != NULL) - && !memcmp(first->hostData.ip4->data, - second->hostData.ip4->data, 4)) ? URI_TRUE : URI_FALSE; - } - - /* IPv6 */ - if (first->hostData.ip6 != NULL) { - return ((second->hostData.ip6 != NULL) - && !memcmp(first->hostData.ip6->data, - second->hostData.ip6->data, 16)) ? URI_TRUE : URI_FALSE; - } - - /* IPvFuture */ - if (first->hostData.ipFuture.first != NULL) { - return ((second->hostData.ipFuture.first != NULL) - && !URI_FUNC(CompareRange)(&first->hostData.ipFuture, - &second->hostData.ipFuture)) ? URI_TRUE : URI_FALSE; - } - - return !URI_FUNC(CompareRange)(&first->hostText, &second->hostText) - ? URI_TRUE : URI_FALSE; -} - - - -static int URI_FUNC(RemoveBaseUriImpl)(URI_TYPE(Uri) * dest, - const URI_TYPE(Uri) * absSource, - const URI_TYPE(Uri) * absBase, - UriBool domainRootMode, UriMemoryManager * memory) { - if (dest == NULL) { - return URI_ERROR_NULL; - } - URI_FUNC(ResetUri)(dest); - - if ((absSource == NULL) || (absBase == NULL)) { - return URI_ERROR_NULL; - } - - /* absBase absolute? */ - if (absBase->scheme.first == NULL) { - return URI_ERROR_REMOVEBASE_REL_BASE; - } - - /* absSource absolute? */ - if (absSource->scheme.first == NULL) { - return URI_ERROR_REMOVEBASE_REL_SOURCE; - } - - /* [01/50] if (A.scheme != Base.scheme) then */ - if (URI_FUNC(CompareRange)(&absSource->scheme, &absBase->scheme)) { - /* [02/50] T.scheme = A.scheme; */ - dest->scheme = absSource->scheme; - /* [03/50] T.authority = A.authority; */ - if (!URI_FUNC(CopyAuthority)(dest, absSource, memory)) { - return URI_ERROR_MALLOC; - } - /* [04/50] T.path = A.path; */ - if (!URI_FUNC(CopyPath)(dest, absSource, memory)) { - return URI_ERROR_MALLOC; - } - /* [05/50] else */ - } else { - /* [06/50] undef(T.scheme); */ - /* NOOP */ - /* [07/50] if (A.authority != Base.authority) then */ - if (!URI_FUNC(EqualsAuthority)(absSource, absBase)) { - /* [08/50] T.authority = A.authority; */ - if (!URI_FUNC(CopyAuthority)(dest, absSource, memory)) { - return URI_ERROR_MALLOC; - } - /* [09/50] T.path = A.path; */ - if (!URI_FUNC(CopyPath)(dest, absSource, memory)) { - return URI_ERROR_MALLOC; - } - /* [10/50] else */ - } else { - /* [11/50] if domainRootMode then */ - if (domainRootMode == URI_TRUE) { - /* [12/50] undef(T.authority); */ - /* NOOP */ - /* [13/50] if (first(A.path) == "") then */ - /* GROUPED */ - /* [14/50] T.path = "/." + A.path; */ - /* GROUPED */ - /* [15/50] else */ - /* GROUPED */ - /* [16/50] T.path = A.path; */ - /* GROUPED */ - /* [17/50] endif; */ - if (!URI_FUNC(CopyPath)(dest, absSource, memory)) { - return URI_ERROR_MALLOC; - } - dest->absolutePath = URI_TRUE; - - if (!URI_FUNC(FixAmbiguity)(dest, memory)) { - return URI_ERROR_MALLOC; - } - /* [18/50] else */ - } else { - const URI_TYPE(PathSegment) * sourceSeg = absSource->pathHead; - const URI_TYPE(PathSegment) * baseSeg = absBase->pathHead; - /* [19/50] bool pathNaked = true; */ - UriBool pathNaked = URI_TRUE; - /* [20/50] undef(last(Base.path)); */ - /* NOOP */ - /* [21/50] T.path = ""; */ - dest->absolutePath = URI_FALSE; - /* [22/50] while (first(A.path) == first(Base.path)) do */ - while ((sourceSeg != NULL) && (baseSeg != NULL) - && !URI_FUNC(CompareRange)(&sourceSeg->text, &baseSeg->text) - && !((sourceSeg->text.first == sourceSeg->text.afterLast) - && ((sourceSeg->next == NULL) != (baseSeg->next == NULL)))) { - /* [23/50] A.path++; */ - sourceSeg = sourceSeg->next; - /* [24/50] Base.path++; */ - baseSeg = baseSeg->next; - /* [25/50] endwhile; */ - } - /* [26/50] while defined(first(Base.path)) do */ - while ((baseSeg != NULL) && (baseSeg->next != NULL)) { - /* [27/50] Base.path++; */ - baseSeg = baseSeg->next; - /* [28/50] T.path += "../"; */ - if (!URI_FUNC(AppendSegment)(dest, URI_FUNC(ConstParent), - URI_FUNC(ConstParent) + 2, memory)) { - return URI_ERROR_MALLOC; - } - /* [29/50] pathNaked = false; */ - pathNaked = URI_FALSE; - /* [30/50] endwhile; */ - } - /* [31/50] while defined(first(A.path)) do */ - while (sourceSeg != NULL) { - /* [32/50] if pathNaked then */ - if (pathNaked == URI_TRUE) { - /* [33/50] if (first(A.path) contains ":") then */ - UriBool containsColon = URI_FALSE; - const URI_CHAR * ch = sourceSeg->text.first; - for (; ch < sourceSeg->text.afterLast; ch++) { - if (*ch == _UT(':')) { - containsColon = URI_TRUE; - break; - } - } - - if (containsColon) { - /* [34/50] T.path += "./"; */ - if (!URI_FUNC(AppendSegment)(dest, URI_FUNC(ConstPwd), - URI_FUNC(ConstPwd) + 1, memory)) { - return URI_ERROR_MALLOC; - } - /* [35/50] elseif (first(A.path) == "") then */ - } else if (sourceSeg->text.first == sourceSeg->text.afterLast) { - /* [36/50] T.path += "/."; */ - if (!URI_FUNC(AppendSegment)(dest, URI_FUNC(ConstPwd), - URI_FUNC(ConstPwd) + 1, memory)) { - return URI_ERROR_MALLOC; - } - /* [37/50] endif; */ - } - /* [38/50] endif; */ - } - /* [39/50] T.path += first(A.path); */ - if (!URI_FUNC(AppendSegment)(dest, sourceSeg->text.first, - sourceSeg->text.afterLast, memory)) { - return URI_ERROR_MALLOC; - } - /* [40/50] pathNaked = false; */ - pathNaked = URI_FALSE; - /* [41/50] A.path++; */ - sourceSeg = sourceSeg->next; - /* [42/50] if defined(first(A.path)) then */ - /* NOOP */ - /* [43/50] T.path += + "/"; */ - /* NOOP */ - /* [44/50] endif; */ - /* NOOP */ - /* [45/50] endwhile; */ - } - /* [46/50] endif; */ - } - /* [47/50] endif; */ - } - /* [48/50] endif; */ - } - /* [49/50] T.query = A.query; */ - dest->query = absSource->query; - /* [50/50] T.fragment = A.fragment; */ - dest->fragment = absSource->fragment; - - return URI_SUCCESS; -} - - - -int URI_FUNC(RemoveBaseUri)(URI_TYPE(Uri) * dest, - const URI_TYPE(Uri) * absSource, - const URI_TYPE(Uri) * absBase, - UriBool domainRootMode) { - return URI_FUNC(RemoveBaseUriMm)(dest, absSource, absBase, - domainRootMode, NULL); -} - - - -int URI_FUNC(RemoveBaseUriMm)(URI_TYPE(Uri) * dest, - const URI_TYPE(Uri) * absSource, - const URI_TYPE(Uri) * absBase, - UriBool domainRootMode, UriMemoryManager * memory) { - int res; - - URI_CHECK_MEMORY_MANAGER(memory); /* may return */ - - res = URI_FUNC(RemoveBaseUriImpl)(dest, absSource, - absBase, domainRootMode, memory); - if ((res != URI_SUCCESS) && (dest != NULL)) { - URI_FUNC(FreeUriMembersMm)(dest, memory); - } - return res; -} - - - -#endif diff --git a/cpp/src/arrow/vendored/uriparser/config.h b/cpp/src/arrow/vendored/uriparser/config.h deleted file mode 100644 index 97f0605da723..000000000000 --- a/cpp/src/arrow/vendored/uriparser/config.h +++ /dev/null @@ -1,47 +0,0 @@ -/* - * uriparser - RFC 3986 URI parsing library - * - * Copyright (C) 2018, Sebastian Pipping - * 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 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. - */ - -#if !defined(URI_CONFIG_H) -# define URI_CONFIG_H 1 - -#define PACKAGE_VERSION "0.9.3" - -// #define HAVE_WPRINTF -// #define HAVE_REALLOCARRAY - -#endif /* !defined(URI_CONFIG_H) */ diff --git a/cpp/subprojects/uriparser.wrap b/cpp/subprojects/uriparser.wrap new file mode 100644 index 000000000000..ec30fa0a29c7 --- /dev/null +++ b/cpp/subprojects/uriparser.wrap @@ -0,0 +1,23 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. + +[wrap-file] +source_url = https://github.com/uriparser/uriparser/releases/download/uriparser-1.0.2/uriparser-1.0.2.tar.bz2 +source_filename = uriparser-1.0.2.tar.bz2 +source_hash = dd2e4843f43de6f5aedf430e530f1e2d159eba8ca4d64c2787af1c20f707a9e4 +directory = uriparser-1.0.2 +method = cmake diff --git a/cpp/thirdparty/versions.txt b/cpp/thirdparty/versions.txt index c0fbaaab12f8..116371bb3c42 100644 --- a/cpp/thirdparty/versions.txt +++ b/cpp/thirdparty/versions.txt @@ -112,6 +112,8 @@ ARROW_S2N_TLS_BUILD_VERSION=v1.7.0 ARROW_S2N_TLS_BUILD_SHA256_CHECKSUM=a6e8228e238239bb3c17b1eda3ed702bcbb2eaebc792eac4d754cc5619b0ea06 ARROW_THRIFT_BUILD_VERSION=0.22.0 ARROW_THRIFT_BUILD_SHA256_CHECKSUM=794a0e455787960d9f27ab92c38e34da27e8deeda7a5db0e59dc64a00df8a1e5 +ARROW_URIPARSER_BUILD_VERSION=1.0.2 +ARROW_URIPARSER_BUILD_SHA256_CHECKSUM=dd2e4843f43de6f5aedf430e530f1e2d159eba8ca4d64c2787af1c20f707a9e4 ARROW_UTF8PROC_BUILD_VERSION=v2.10.0 ARROW_UTF8PROC_BUILD_SHA256_CHECKSUM=6f4f1b639daa6dca9f80bc5db1233e9cbaa31a67790887106160b33ef743f136 # WIL (Windows Implementation Libraries) is required by Azure SDK on Windows for WinHTTP transport @@ -171,6 +173,7 @@ DEPENDENCIES=( "ARROW_SNAPPY_URL snappy-${ARROW_SNAPPY_BUILD_VERSION}.tar.gz https://github.com/google/snappy/archive/${ARROW_SNAPPY_BUILD_VERSION}.tar.gz" "ARROW_SUBSTRAIT_URL substrait-${ARROW_SUBSTRAIT_BUILD_VERSION}.tar.gz https://github.com/substrait-io/substrait/archive/${ARROW_SUBSTRAIT_BUILD_VERSION}.tar.gz" "ARROW_THRIFT_URL thrift-${ARROW_THRIFT_BUILD_VERSION}.tar.gz https://www.apache.org/dyn/closer.lua/thrift/${ARROW_THRIFT_BUILD_VERSION}/thrift-${ARROW_THRIFT_BUILD_VERSION}.tar.gz?action=download" + "ARROW_URIPARSER_URL uriparser-${ARROW_URIPARSER_BUILD_VERSION}.tar.bz2 https://github.com/uriparser/uriparser/releases/download/uriparser-${ARROW_URIPARSER_BUILD_VERSION}/uriparser-${ARROW_URIPARSER_BUILD_VERSION}.tar.bz2" "ARROW_UTF8PROC_URL utf8proc-${ARROW_UTF8PROC_BUILD_VERSION}.tar.gz https://github.com/JuliaStrings/utf8proc/archive/${ARROW_UTF8PROC_BUILD_VERSION}.tar.gz" "ARROW_WIL_URL wil-${ARROW_WIL_BUILD_VERSION}.tar.gz https://github.com/microsoft/wil/archive/refs/tags/${ARROW_WIL_BUILD_VERSION}.tar.gz" "ARROW_XSIMD_URL xsimd-${ARROW_XSIMD_BUILD_VERSION}.tar.gz https://github.com/xtensor-stack/xsimd/archive/${ARROW_XSIMD_BUILD_VERSION}.tar.gz" diff --git a/cpp/vcpkg.json b/cpp/vcpkg.json index 1a8ceb3498d5..4d35eb29d219 100644 --- a/cpp/vcpkg.json +++ b/cpp/vcpkg.json @@ -52,6 +52,7 @@ "snappy", "sqlite3", "thrift", + "uriparser", "utf8proc", "xsimd", "zlib", diff --git a/docs/source/developers/cpp/building.rst b/docs/source/developers/cpp/building.rst index fb6815228783..b284e2d7c9b2 100644 --- a/docs/source/developers/cpp/building.rst +++ b/docs/source/developers/cpp/building.rst @@ -507,6 +507,7 @@ The build system supports a number of third-party dependencies * ``RapidJSON``: for data serialization * ``Snappy``: for data compression * ``Thrift``: Apache Thrift, for data serialization + * ``uriparser``: for URI parsing, used by core Arrow * ``utf8proc``: for compute kernels * ``ZLIB``: for data compression * ``zstd``: for data compression