|
| 1 | +# Copyright 2024 The Bazel Authors. All rights reserved. |
| 2 | +# |
| 3 | +# Licensed under the Apache License, Version 2.0 (the "License"); |
| 4 | +# you may not use this file except in compliance with the License. |
| 5 | +# You may obtain a copy of the License at |
| 6 | +# |
| 7 | +# http://www.apache.org/licenses/LICENSE-2.0 |
| 8 | +# |
| 9 | +# Unless required by applicable law or agreed to in writing, software |
| 10 | +# distributed under the License is distributed on an "AS IS" BASIS, |
| 11 | +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| 12 | +# See the License for the specific language governing permissions and |
| 13 | +# limitations under the License. |
| 14 | + |
| 15 | +"""Create a repository for a locally installed Python runtime.""" |
| 16 | + |
| 17 | +load("//python/private:enum.bzl", "enum") |
| 18 | +load(":repo_utils.bzl", "REPO_DEBUG_ENV_VAR", "repo_utils") |
| 19 | + |
| 20 | +# buildifier: disable=name-conventions |
| 21 | +_OnFailure = enum( |
| 22 | + SKIP = "skip", |
| 23 | + WARN = "warn", |
| 24 | + FAIL = "fail", |
| 25 | +) |
| 26 | + |
| 27 | +_TOOLCHAIN_IMPL_TEMPLATE = """\ |
| 28 | +# Generated by python/private/local_runtime_repo.bzl |
| 29 | +
|
| 30 | +load("@rules_python//python/private:local_runtime_repo_setup.bzl", "define_local_runtime_toolchain_impl") |
| 31 | +
|
| 32 | +define_local_runtime_toolchain_impl( |
| 33 | + name = "local_runtime", |
| 34 | + lib_ext = "{lib_ext}", |
| 35 | + major = "{major}", |
| 36 | + minor = "{minor}", |
| 37 | + micro = "{micro}", |
| 38 | + interpreter_path = "{interpreter_path}", |
| 39 | + implementation_name = "{implementation_name}", |
| 40 | + os = "{os}", |
| 41 | +) |
| 42 | +""" |
| 43 | + |
| 44 | +def _local_runtime_repo_impl(rctx): |
| 45 | + logger = repo_utils.logger(rctx) |
| 46 | + on_failure = rctx.attr.on_failure |
| 47 | + |
| 48 | + platforms_os_name = repo_utils.get_platforms_os_name(rctx) |
| 49 | + if not platforms_os_name: |
| 50 | + if on_failure == "fail": |
| 51 | + fail("Unrecognized host platform '{}': cannot determine OS constraint".format( |
| 52 | + rctx.os.name, |
| 53 | + )) |
| 54 | + |
| 55 | + if on_failure == "warn": |
| 56 | + logger.warn(lambda: "Unrecognized host platform '{}': cannot determine OS constraint".format( |
| 57 | + rctx.os.name, |
| 58 | + )) |
| 59 | + |
| 60 | + # else, on_failure must be skip |
| 61 | + rctx.file("BUILD.bazel", _expand_incompatible_template()) |
| 62 | + return |
| 63 | + |
| 64 | + result = _resolve_interpreter_path(rctx) |
| 65 | + if not result.resolved_path: |
| 66 | + if on_failure == "fail": |
| 67 | + fail("interpreter not found: {}".format(result.describe_failure())) |
| 68 | + |
| 69 | + if on_failure == "warn": |
| 70 | + logger.warn(lambda: "interpreter not found: {}".format(result.describe_failure())) |
| 71 | + |
| 72 | + # else, on_failure must be skip |
| 73 | + rctx.file("BUILD.bazel", _expand_incompatible_template()) |
| 74 | + return |
| 75 | + else: |
| 76 | + interpreter_path = result.resolved_path |
| 77 | + |
| 78 | + logger.info(lambda: "resolved interpreter {} to {}".format(rctx.attr.interpreter_path, interpreter_path)) |
| 79 | + |
| 80 | + exec_result = repo_utils.execute_unchecked( |
| 81 | + rctx, |
| 82 | + op = "local_runtime_repo.GetPythonInfo({})".format(rctx.name), |
| 83 | + arguments = [ |
| 84 | + interpreter_path, |
| 85 | + rctx.path(rctx.attr._get_local_runtime_info), |
| 86 | + ], |
| 87 | + quiet = True, |
| 88 | + ) |
| 89 | + if exec_result.return_code != 0: |
| 90 | + if on_failure == "fail": |
| 91 | + fail("GetPythonInfo failed: {}".format(exec_result.describe_failure())) |
| 92 | + if on_failure == "warn": |
| 93 | + logger.warn(lambda: "GetPythonInfo failed: {}".format(exec_result.describe_failure())) |
| 94 | + |
| 95 | + # else, on_failure must be skip |
| 96 | + rctx.file("BUILD.bazel", _expand_incompatible_template()) |
| 97 | + return |
| 98 | + |
| 99 | + info = json.decode(exec_result.stdout) |
| 100 | + logger.info(lambda: _format_get_info_result(info)) |
| 101 | + |
| 102 | + # NOTE: Keep in sync with recursive glob in define_local_runtime_toolchain_impl |
| 103 | + repo_utils.watch_tree(rctx, rctx.path(info["include"])) |
| 104 | + |
| 105 | + # The cc_library.includes values have to be non-absolute paths, otherwise |
| 106 | + # the toolchain will give an error. Work around this error by making them |
| 107 | + # appear as part of this repo. |
| 108 | + rctx.symlink(info["include"], "include") |
| 109 | + |
| 110 | + # NOTE: For some reason (unknown why), the values found may refer to |
| 111 | + # .a files (static libraries) instead of .so (shared libraries) files. |
| 112 | + shared_lib_names = [ |
| 113 | + info["PY3LIBRARY"], # libpython3.so |
| 114 | + info["LDLIBRARY"], # libpython3.11.so |
| 115 | + info["INSTSONAME"], # libpython3.11.so.1.0 |
| 116 | + ] |
| 117 | + |
| 118 | + # In some cases, the value may be empty. Not clear why. |
| 119 | + shared_lib_names = [v for v in shared_lib_names if v] |
| 120 | + |
| 121 | + # In some cases, the same value is returned or multiple keys. Not clear why. |
| 122 | + shared_lib_names = {v: None for v in shared_lib_names}.keys() |
| 123 | + |
| 124 | + # It's not entirely clear how to get the directory with libraries. |
| 125 | + # There's several types of libraries with different names and a plethora |
| 126 | + # of settings. |
| 127 | + # https://stackoverflow.com/questions/47423246/get-pythons-lib-path |
| 128 | + # For now, it seems LIBDIR has what is needed, so just use that. |
| 129 | + shared_lib_dir = info["LIBDIR"] |
| 130 | + |
| 131 | + # The specific files are symlinked instead of the whole directory |
| 132 | + # because it can point to a directory that has more than just |
| 133 | + # the Python runtime shared libraries, e.g. /usr/lib, or a Python |
| 134 | + # specific directory with pip-installed shared libraries. |
| 135 | + rctx.report_progress("Symlinking external Python shared libraries") |
| 136 | + for name in shared_lib_names: |
| 137 | + origin = rctx.path("{}/{}".format(shared_lib_dir, name)) |
| 138 | + |
| 139 | + # The reported names don't always exist; it depends on the particulars |
| 140 | + # of the runtime installation. |
| 141 | + if origin.exists: |
| 142 | + repo_utils.watch(rctx, origin) |
| 143 | + rctx.symlink(origin, "lib/" + name) |
| 144 | + |
| 145 | + rctx.file("WORKSPACE", "") |
| 146 | + rctx.file("MODULE.bazel", "") |
| 147 | + rctx.file("REPO.bazel", "") |
| 148 | + rctx.file("BUILD.bazel", _TOOLCHAIN_IMPL_TEMPLATE.format( |
| 149 | + major = info["major"], |
| 150 | + minor = info["minor"], |
| 151 | + micro = info["micro"], |
| 152 | + interpreter_path = interpreter_path, |
| 153 | + lib_ext = info["SHLIB_SUFFIX"], |
| 154 | + implementation_name = info["implementation_name"], |
| 155 | + os = "@platforms//os:{}".format(repo_utils.get_platforms_os_name(rctx)), |
| 156 | + )) |
| 157 | + |
| 158 | +local_runtime_repo = repository_rule( |
| 159 | + implementation = _local_runtime_repo_impl, |
| 160 | + doc = """ |
| 161 | +Use a locally installed Python runtime as a toolchain implementation. |
| 162 | +
|
| 163 | +Note this uses the runtime as a *platform runtime*. A platform runtime means |
| 164 | +means targets don't include the runtime itself as part of their runfiles or |
| 165 | +inputs. Instead, users must assure that where the targets run have the runtime |
| 166 | +pre-installed or otherwise available. |
| 167 | +
|
| 168 | +This results in lighter weight binaries (in particular, Bazel doesn't have to |
| 169 | +create thousands of files for every `py_test`), at the risk of having to rely on |
| 170 | +a system having the necessary Python installed. |
| 171 | +""", |
| 172 | + attrs = { |
| 173 | + "interpreter_path": attr.string( |
| 174 | + doc = """ |
| 175 | +An absolute path or program name on the `PATH` env var. |
| 176 | +
|
| 177 | +Values with slashes are assumed to be the path to a program. Otherwise, it is |
| 178 | +treated as something to search for on `PATH` |
| 179 | +
|
| 180 | +Note that, when a plain program name is used, the path to the interpreter is |
| 181 | +resolved at repository evalution time, not runtime of any resulting binaries. |
| 182 | +""", |
| 183 | + default = "python3", |
| 184 | + ), |
| 185 | + "on_failure": attr.string( |
| 186 | + default = _OnFailure.SKIP, |
| 187 | + values = sorted(_OnFailure.__members__.values()), |
| 188 | + doc = """ |
| 189 | +How to handle errors when trying to automatically determine settings. |
| 190 | +
|
| 191 | +* `skip` will silently skip creating a runtime. Instead, a non-functional |
| 192 | + runtime will be generated and marked as incompatible so it cannot be used. |
| 193 | + This is best if a local runtime is known not to work or be available |
| 194 | + in certain cases and that's OK. e.g., one use windows paths when there |
| 195 | + are people running on linux. |
| 196 | +* `warn` will print a warning message. This is useful when you expect |
| 197 | + a runtime to be available, but are OK with it missing and falling back |
| 198 | + to some other runtime. |
| 199 | +* `fail` will result in a failure. This is only recommended if you must |
| 200 | + ensure the runtime is available. |
| 201 | +""", |
| 202 | + ), |
| 203 | + "_get_local_runtime_info": attr.label( |
| 204 | + allow_single_file = True, |
| 205 | + default = "//python/private:get_local_runtime_info.py", |
| 206 | + ), |
| 207 | + "_rule_name": attr.string(default = "local_runtime_repo"), |
| 208 | + }, |
| 209 | + environ = ["PATH", REPO_DEBUG_ENV_VAR], |
| 210 | +) |
| 211 | + |
| 212 | +def _expand_incompatible_template(): |
| 213 | + return _TOOLCHAIN_IMPL_TEMPLATE.format( |
| 214 | + interpreter_path = "/incompatible", |
| 215 | + implementation_name = "incompatible", |
| 216 | + lib_ext = "incompatible", |
| 217 | + major = "0", |
| 218 | + minor = "0", |
| 219 | + micro = "0", |
| 220 | + os = "@platforms//:incompatible", |
| 221 | + ) |
| 222 | + |
| 223 | +def _resolve_interpreter_path(rctx): |
| 224 | + """Find the absolute path for an interpreter. |
| 225 | +
|
| 226 | + Args: |
| 227 | + rctx: A repository_ctx object |
| 228 | +
|
| 229 | + Returns: |
| 230 | + `struct` with the following fields: |
| 231 | + * `resolved_path`: `path` object of a path that exists |
| 232 | + * `describe_failure`: `Callable | None`. If a path that doesn't exist, |
| 233 | + returns a description of why it couldn't be resolved |
| 234 | + A path object or None. The path may not exist. |
| 235 | + """ |
| 236 | + if "/" not in rctx.attr.interpreter_path and "\\" not in rctx.attr.interpreter_path: |
| 237 | + # Provide a bit nicer integration with pyenv: recalculate the runtime if the |
| 238 | + # user changes the python version using e.g. `pyenv shell` |
| 239 | + repo_utils.getenv(rctx, "PYENV_VERSION") |
| 240 | + result = repo_utils.which_unchecked(rctx, rctx.attr.interpreter_path) |
| 241 | + resolved_path = result.binary |
| 242 | + describe_failure = result.describe_failure |
| 243 | + else: |
| 244 | + repo_utils.watch(rctx, rctx.attr.interpreter_path) |
| 245 | + resolved_path = rctx.path(rctx.attr.interpreter_path) |
| 246 | + if not resolved_path.exists: |
| 247 | + describe_failure = lambda: "Path not found: {}".format(repr(rctx.attr.interpreter_path)) |
| 248 | + else: |
| 249 | + describe_failure = None |
| 250 | + |
| 251 | + return struct( |
| 252 | + resolved_path = resolved_path, |
| 253 | + describe_failure = describe_failure, |
| 254 | + ) |
| 255 | + |
| 256 | +def _format_get_info_result(info): |
| 257 | + lines = ["GetPythonInfo result:"] |
| 258 | + for key, value in sorted(info.items()): |
| 259 | + lines.append(" {}: {}".format(key, value if value != "" else "<empty string>")) |
| 260 | + return "\n".join(lines) |
0 commit comments