Add tf.strings.unicode_script, which detects the script of a unicode codepoint

based on standard ranges.

PiperOrigin-RevId: 214796357

3 files changed, 104 insertions, 0 deletions

diff --git a/third_party/icu/BUILD b/third_party/icu/BUILD
new file mode 100644
index 0000000000..82bab3ffd9
--- /dev/null
+++ b/third_party/icu/BUILD
@@ -0,0 +1 @@
+# This empty BUILD file is required to make Bazel treat this directory as a package.
diff --git a/third_party/icu/BUILD.bazel b/third_party/icu/BUILD.bazel
new file mode 100644
index 0000000000..36d6b9006b
--- /dev/null
+++ b/third_party/icu/BUILD.bazel
@@ -0,0 +1,88 @@
+package(
+    default_visibility = ["//visibility:public"],
+)
+
+licenses(["notice"])  # Apache 2.0
+
+exports_files([
+    "icu4c/LICENSE",
+    "icu4j/main/shared/licenses/LICENSE",
+])
+
+cc_library(
+    name = "headers",
+    hdrs = glob(["icu4c/source/common/unicode/*.h"]),
+    includes = [
+        "icu4c/source/common",
+    ],
+    deps = [
+    ],
+)
+
+cc_library(
+    name = "common",
+    hdrs = glob(["icu4c/source/common/unicode/*.h"]),
+    includes = [
+        "icu4c/source/common",
+    ],
+    deps = [
+        ":icuuc",
+    ],
+)
+
+cc_library(
+    name = "icuuc",
+    srcs = glob(
+        [
+            "icu4c/source/common/*.c",
+            "icu4c/source/common/*.cpp",
+            "icu4c/source/stubdata/*.cpp",
+        ],
+    ),
+    hdrs = glob([
+        "icu4c/source/common/*.h",
+    ]),
+    copts = [
+        "-DU_COMMON_IMPLEMENTATION",
+        "-DU_HAVE_STD_ATOMICS",
+    ] + select({
+        ":android": [
+            "-fdata-sections",
+            "-DGOOGLE_VENDOR_SRC_BRANCH",
+            "-DU_HAVE_NL_LANGINFO_CODESET=0",
+            "-Wno-deprecated-declarations",
+        ],
+        ":apple": [
+            "-DGOOGLE_VENDOR_SRC_BRANCH",
+            "-Wno-shorten-64-to-32",
+            "-Wno-unused-variable",
+        ],
+        ":windows": [
+            "/utf-8",
+            "/DLOCALE_ALLOW_NEUTRAL_NAMES=0",
+        ],
+        "//conditions:default": [],
+    }),
+    tags = ["requires-rtti"],
+    visibility = [
+        "//visibility:private",
+    ],
+    deps = [
+        ":headers",
+    ],
+)
+
+config_setting(
+    name = "android",
+    values = {"crosstool_top": "//external:android/crosstool"},
+)
+
+config_setting(
+    name = "apple",
+    values = {"cpu": "darwin"},
+)
+
+config_setting(
+    name = "windows",
+    values = {"cpu": "x64_windows"},
+)
diff --git a/third_party/icu/workspace.bzl b/third_party/icu/workspace.bzl
new file mode 100644
index 0000000000..bfebf4219b
--- /dev/null
+++ b/third_party/icu/workspace.bzl
@@ -0,0 +1,15 @@
+"""Loads a lightweight subset of the ICU library for Unicode processing."""
+
+load("//third_party:repo.bzl", "third_party_http_archive")
+
+def repo():
+    third_party_http_archive(
+        name = "icu",
+        strip_prefix = "icu-release-62-1",
+        sha256 = "e15ffd84606323cbad5515bf9ecdf8061cc3bf80fb883b9e6aa162e485aa9761",
+        urls = [
+            "https://mirror.bazel.build/github.com/unicode-org/icu/archive/release-62-1.tar.gz",
+            "https://github.com/unicode-org/icu/archive/release-62-1.tar.gz",
+        ],
+        build_file = "//third_party/icu:BUILD.bazel",
+    )