Files
wehub-resource-sync e904b667c6
Build/Publish Develop Docs / deploy (push) Failing after 1s
PaddleOCR Code Style Check / check-code-style (push) Failing after 1s
PaddleOCR PR Tests GPU / detect-changes (push) Failing after 1s
PaddleOCR PR Tests / detect-changes (push) Failing after 1s
PaddleOCR PR Tests GPU / test-pr-gpu (push) Has been cancelled
PaddleOCR PR Tests / test-pr (push) Has been cancelled
PaddleOCR PR Tests GPU / test-pr-gpu-impl (push) Has been cancelled
PaddleOCR PR Tests / test-pr-python (3.13) (push) Has been cancelled
PaddleOCR PR Tests / test-pr-python (3.8) (push) Has been cancelled
PaddleOCR PR Tests / test-pr-python (3.9) (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 11:59:26 +08:00

127 lines
2.2 KiB
Python

# Copyright (c) 2026 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed 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.
"""Language code groupings shared across OCR pipelines."""
LATIN_LANGS = frozenset(
{
"af",
"az",
"bs",
"cs",
"cy",
"da",
"de",
"es",
"et",
"fr",
"ga",
"hr",
"hu",
"id",
"is",
"it",
"ku",
"la",
"lt",
"lv",
"mi",
"ms",
"mt",
"nl",
"no",
"oc",
"pi",
"pl",
"pt",
"ro",
"rs_latin",
"sk",
"sl",
"sq",
"sv",
"sw",
"tl",
"tr",
"uz",
"vi",
"french",
"german",
"fi",
"eu",
"gl",
"lb",
"rm",
"ca",
"qu",
}
)
ARABIC_LANGS = frozenset({"ar", "fa", "ug", "ur", "ps", "ku", "sd", "bal"})
ESLAV_LANGS = frozenset({"ru", "be", "uk"})
CYRILLIC_LANGS = frozenset(
{
"ru",
"rs_cyrillic",
"be",
"bg",
"uk",
"mn",
"abq",
"ady",
"kbd",
"ava",
"dar",
"inh",
"che",
"lbe",
"lez",
"tab",
"kk",
"ky",
"tg",
"mk",
"tt",
"cv",
"ba",
"mhr",
"mo",
"udm",
"kv",
"os",
"bua",
"xal",
"tyv",
"sah",
"kaa",
}
)
DEVANAGARI_LANGS = frozenset(
{
"hi",
"mr",
"ne",
"bh",
"mai",
"ang",
"bho",
"mah",
"sck",
"new",
"gom",
"sa",
"bgc",
}
)