Compatibility issues (#6071)

* Pass -f - to tar to force stdin on Windows

* Quote paths that may contain spaces (causes issues on Windows)

* Copy over Windows code from Arrow for glog signal handle uninstall

* Add missing COPTS to build rules since we'll need them for Windows compatibility

* Begin adding COPTS for Windows compatibility

* Disable glog on Arrow until we change WIN32 to _WIN32 there

* Missing header files that cause problems on Windows

* WORD typedef conflicts with Windows; remove it

* uint -> unsigned int wherever we're dealing with milliseconds (signed version is already int)

* uint -> unsigned int for enums

* uint -> size_t, wherever we're dealing with sizes or indices into arrays

* Work around Boost 1.68 bug in detecting clang-cl (revert this after upgrading)

* Missing #include <unistd.h>

* Add check for signal handler uninstallation failure

* Linting issue

bazel/BUILD.plasma

@@ -1,6 +1,12 @@
 load("@com_github_google_flatbuffers//:build_defs.bzl", "flatbuffer_cc_library")
 
-COPTS = ["-DARROW_USE_GLOG"]
+COPTS = [] + select({
+    "@bazel_tools//src/conditions:windows": [
+    ],
+    "//conditions:default": [
+        "-DARROW_USE_GLOG",
+    ],
+})
 
 cc_library(
     name = "arrow",
@@ -20,6 +26,7 @@ cc_library(
         "cpp/src/arrow/buffer.h",
         "cpp/src/arrow/io/concurrency.h",
         "cpp/src/arrow/io/interfaces.h",
+        "cpp/src/arrow/io/mman.h",
         "cpp/src/arrow/io/util_internal.h",
         "cpp/src/arrow/memory_pool.h",
         "cpp/src/arrow/result.h",
@@ -41,6 +48,7 @@ cc_library(
         "cpp/src/arrow/util/thread_pool.h",
         "cpp/src/arrow/util/type_traits.h",
         "cpp/src/arrow/util/ubsan.h",
+        "cpp/src/arrow/util/utf8.h",
         "cpp/src/arrow/util/variant.h",
         "cpp/src/arrow/util/visibility.h",
         "cpp/src/arrow/util/windows_compatibility.h",

bazel/cython_library.bzl

@@ -8,7 +8,7 @@
 # been written at cython/cython and tensorflow/tensorflow. We branch from
 # Tensorflow's version as it is more actively maintained and works for gRPC
 # Python's needs.
-def pyx_library(name, deps=[], py_deps=[], srcs=[], **kwargs):
+def pyx_library(name, deps=[], py_deps=[], srcs=[], copts=[], **kwargs):
     """Compiles a group of .pyx / .pxd / .py files.
     First runs Cython to create .cpp files for each input .pyx or .py + .pxd
     pair. Then builds a shared object for each, passing "deps" to each cc_binary
@@ -46,7 +46,7 @@ def pyx_library(name, deps=[], py_deps=[], srcs=[], **kwargs):
             # Optionally use PYTHON_BIN_PATH on Linux platforms so that python 3
             # works. Windows has issues with cython_binary so skip PYTHON_BIN_PATH.
             cmd=
-            "PYTHONHASHSEED=0 $${PYTHON_BIN_PATH} $(location @cython//:cython_binary) --cplus $(SRCS) --output-file $(OUTS)",
+            'PYTHONHASHSEED=0 "$${PYTHON_BIN_PATH}" "$(location @cython//:cython_binary)" --cplus $(SRCS) --output-file $(OUTS)',
             tools=["@cython//:cython_binary"] + pxd_srcs,
         )
 
@@ -57,6 +57,7 @@ def pyx_library(name, deps=[], py_deps=[], srcs=[], **kwargs):
         native.cc_binary(
             name=shared_object_name,
             srcs=[stem + ".cpp"],
+            copts=copts,
             deps=deps + ["@local_config_python//:python_headers"],
             linkshared=1,
         )