Skip to content

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

refactor: remove language option from API server and related components

myhloli464d4737644e
diff --git a/docs/next/cli/mineru-kit-api-server.md b/docs/next/cli/mineru-kit-api-server.md
index b93054e0..716e0bbf 100644
--- a/docs/next/cli/mineru-kit-api-server.md
+++ b/docs/next/cli/mineru-kit-api-server.md
@@ -82,7 +82,7 @@ mineru-kit api-server --tier standard --no-flash --port 8000
mineru-kit api-server --tier standard --no-advanced --port 8000
mineru-kit api-server --tier standard --no-flash --no-advanced --port 8000
mineru-kit api-server --tier standard --preload-models
-mineru-kit api-server --tier standard --language en --disable-image-analysis
+mineru-kit api-server --tier standard --disable-image-analysis
```
未传 `--tier` 时暴露 `flash`、`basic`、`standard`、`advanced`;PDF/image 请求未指定 tier 时默认 `standard`。
@@ -167,7 +167,6 @@ Python 可使用 `create_app(vlm_config=VlmConfig(...))` 完整覆盖全局配
### 稳定解析参数
-- language
- disable-image-analysis
- concurrency
- upload-dir
diff --git a/docs/next/cli/mineru-kit-parse.md b/docs/next/cli/mineru-kit-parse.md
index a3998677..6ff532ce 100644
--- a/docs/next/cli/mineru-kit-parse.md
+++ b/docs/next/cli/mineru-kit-parse.md
@@ -145,6 +145,6 @@ remote 模式通过以下参数进入:
| remote 模式 | remote、remote-url、api-key |
| 输出控制 | format、output |
-local 模式的 `ocr-mode`、`disable-image-analysis` 与 `mineru-kit api-server` 一致;`--tier` 值域更宽(`mineru-kit parse` 接受 `flash/basic/standard/advanced`,`api-server` 只接受 `flash/basic/standard` 作为能力上限)。`api-server` 额外提供 `--language` OCR 语言提示,`mineru-kit parse` 当前不提供该参数。
+local 模式的 `ocr-mode`、`disable-image-analysis` 与 `mineru-kit api-server` 一致;`--tier` 值域更宽(`mineru-kit parse` 接受 `flash/basic/standard/advanced`,`api-server` 只接受 `flash/basic/standard` 作为能力上限)。`--language` OCR 语言参数已从全部命令移除,传入会报错。
完整决策背景见 [ADR-0016](../decisions/0016-mineru-kit-parse-command.md)。
diff --git a/docs/next/cli/mineru-kit-webui.md b/docs/next/cli/mineru-kit-webui.md
index 871a6de4..87235ca2 100644
--- a/docs/next/cli/mineru-kit-webui.md
+++ b/docs/next/cli/mineru-kit-webui.md
@@ -62,7 +62,6 @@ mineru-kit webui \
| `--max-pages` | 单次非 Flash PDF 解析的最多页数,必须为正整数;省略则不限制。不限制 Flash 或非 PDF。 |
| `--api-server-tier` | 自动启动 server 的能力档位:`flash`、`basic`、`standard`。 |
| `--api-server-concurrency` | 自动启动 server 的最大并发任务数。 |
-| `--api-server-language` | 自动启动 server 的 OCR 语言提示。 |
| `--api-server-preload-models` | 在自动启动阶段预加载模型。 |
| `--api-server-disable-image-analysis` | 自动启动 server 时关闭图片分析。 |
| `--enable-example` | 显示当前工作目录 `examples/` 中的示例文件。 |
diff --git a/mineru/kit/commands/api_server.py b/mineru/kit/commands/api_server.py
index 32ee2bca..19c7e3cd 100644
--- a/mineru/kit/commands/api_server.py
+++ b/mineru/kit/commands/api_server.py
@@ -7,14 +7,11 @@ import typer
from ...parser import api_server as parser_api_server
from ...types import SERVER_TIERS, ServerTier
-from ...model.ocr.language import PUBLIC_OCR_LANGUAGES, validate_public_ocr_lang
from ...utils.i18n import t
from ...utils.logger import configure_global_log_level
from ...utils.stdio import configure_standard_streams
from ..errors import exit_with_message
-API_SERVER_LANGUAGES = PUBLIC_OCR_LANGUAGES
-
def _normalize_tier_option(tier: str | None) -> ServerTier | None:
"""规范化 mineru-kit 传入的单个 server tier。"""
@@ -49,11 +46,6 @@ def api_server_cmd(
allow_local_source: bool = typer.Option(False, "--allow-local-source", help=t("Allow local source paths")),
max_inline_bytes: int = typer.Option(1024 * 1024, "--max-inline-bytes", help=t("Maximum decoded bytes for inline sources")),
allow_http_source: bool = typer.Option(False, "--allow-http-source", help=t("Allow URL sources to use plain HTTP")),
- language: str = typer.Option(
- "ch",
- "--language",
- help=t("Hybrid medium OCR language hint; accepted by other efforts for compatibility"),
- ),
disable_image_analysis: bool = typer.Option(False, "--disable-image-analysis", help=t("Disable image analysis")),
preload_models: bool = typer.Option(
False, "--preload-models", help=t("Initialize VLM client and local Hybrid models at startup")
@@ -80,10 +72,6 @@ def api_server_cmd(
),
) -> None:
"""转发显式启动参数,启动 self-hosted MinerU 解析 API 服务。"""
- try:
- normalized_language = validate_public_ocr_lang(language)
- except ValueError as exc:
- exit_with_message("invalid_request", str(exc), "language")
tier_value = _normalize_tier_option(tier)
tier_args = ["--tier", tier_value] if tier_value is not None else []
vlm_args: list[str] = []
@@ -110,8 +98,6 @@ def api_server_cmd(
str(url_timeout),
"--max-inline-bytes",
str(max_inline_bytes),
- "--language",
- normalized_language,
*tier_args,
*vlm_args,
*(["--no-flash"] if no_flash else []),
@@ -144,4 +130,4 @@ def main() -> None:
app()
-__all__ = ["API_SERVER_LANGUAGES", "api_server_cmd", "main"]
+__all__ = ["api_server_cmd", "main"]
diff --git a/mineru/kit/commands/webui.py b/mineru/kit/commands/webui.py
index ea110dcf..92431c76 100644
--- a/mineru/kit/commands/webui.py
+++ b/mineru/kit/commands/webui.py
@@ -10,7 +10,6 @@ from typing import Literal
import typer
from packaging.specifiers import SpecifierSet
-from ...model.ocr.language import validate_public_ocr_lang
from ...types import SERVER_TIERS, ServerTier
from ...utils.i18n import t
from ...utils.logger import configure_global_log_level
@@ -83,7 +82,6 @@ def webui_cmd(
api_server_concurrency: int = typer.Option(
1, "--api-server-concurrency", "--concurrency", help=t("Managed server job concurrency")
),
- api_server_language: str = typer.Option("ch", "--api-server-language", "--language", help=t("Managed server OCR language")),
api_server_disable_image_analysis: bool = typer.Option(
False,
"--api-server-disable-image-analysis/--disable-image-analysis",
@@ -101,10 +99,6 @@ def webui_cmd(
_validate_positive_option(max_pages, name="max_pages")
_validate_positive_option(api_server_concurrency, name="api_server_concurrency")
normalized_tier = _validate_server_tier(api_server_tier)
- try:
- normalized_language = validate_public_ocr_lang(api_server_language)
- except ValueError as exc:
- exit_with_message("invalid_request", str(exc), "api_server_language")
from ..gradio.app import launch_gradio
@@ -122,7 +116,6 @@ def webui_cmd(
latex_delimiters_type=latex_delimiters_type,
api_server_tier=normalized_tier,
api_server_concurrency=api_server_concurrency,
- api_server_language=normalized_language,
api_server_disable_image_analysis=api_server_disable_image_analysis,
api_server_preload_models=api_server_preload_models,
)
diff --git a/mineru/kit/gradio/app.py b/mineru/kit/gradio/app.py
index c772dec2..3c25546b 100644
--- a/mineru/kit/gradio/app.py
+++ b/mineru/kit/gradio/app.py
@@ -1036,7 +1036,6 @@ def launch_gradio(
latex_delimiters_type: Literal["a", "b", "all"],
api_server_tier: str,
api_server_concurrency: int,
- api_server_language: str,
api_server_disable_image_analysis: bool,
api_server_preload_models: bool,
max_pages: int | None = None,
@@ -1055,7 +1054,6 @@ def launch_gradio(
managed_server = ManagedLocalApiServer(
tier=api_server_tier, # type: ignore[arg-type]
concurrency=api_server_concurrency,
- language=api_server_language,
disable_image_analysis=api_server_disable_image_analysis,
preload_models=api_server_preload_models,
api_key=resolved_api_key,
@@ -1068,7 +1066,6 @@ def launch_gradio(
managed_server = ManagedLocalApiServer(
tier="flash",
concurrency=api_server_concurrency,
- language=api_server_language,
disable_image_analysis=api_server_disable_image_analysis,
preload_models=api_server_preload_models,
api_key="",
diff --git a/mineru/kit/gradio/client.py b/mineru/kit/gradio/client.py
index d63af1fe..29274c48 100644
--- a/mineru/kit/gradio/client.py
+++ b/mineru/kit/gradio/client.py
@@ -301,7 +301,6 @@ class ManagedLocalApiServer:
*,
tier: ServerTier = "standard",
concurrency: int = 1,
- language: str = "ch",
disable_image_analysis: bool = False,
preload_models: bool = False,
api_key: str | None = None,
@@ -313,7 +312,6 @@ class ManagedLocalApiServer:
raise ValueError("API server concurrency must be positive")
self.tier = tier
self.concurrency = concurrency
- self.language = language
self.disable_image_analysis = disable_image_analysis
self.preload_models = preload_models
self.api_key = api_key
@@ -422,8 +420,6 @@ class ManagedLocalApiServer:
self.tier,
"--concurrency",
str(self.concurrency),
- "--language",
- self.language,
"--log-level",
"warning",
*(["--disable-image-analysis"] if self.disable_image_analysis else []),
diff --git a/mineru/model/ocr/language.py b/mineru/model/ocr/language.py
index 94be5647..113b0b2f 100644
--- a/mineru/model/ocr/language.py
+++ b/mineru/model/ocr/language.py
@@ -2,49 +2,6 @@
from collections.abc import Collection
-PUBLIC_OCR_LANGUAGES = (
- "ch",
- "ch_server",
- "korean",
- "ta",
- "te",
- "ka",
- "th",
- "el",
- "arabic",
- "east_slavic",
- "cyrillic",
- "devanagari",
-)
-
-_PUBLIC_OCR_LANGUAGE_DESCRIPTIONS = {
- "ch": "Chinese, English, Japanese, Chinese Traditional, Latin",
- "ch_server": "Chinese, English, Japanese, Chinese Traditional, Latin",
- "korean": "Korean, English",
- "ta": "Tamil, English",
- "te": "Telugu, English",
- "ka": "Kannada",
- "th": "Thai, English",
- "el": "Greek, English",
- "arabic": ("Arabic, Persian, Uyghur, Urdu, Pashto, Kurdish, Sindhi, Balochi, English"),
- "east_slavic": "Russian, Belarusian, Ukrainian, English",
- "cyrillic": (
- "Russian, Belarusian, Ukrainian, Serbian (Cyrillic), Bulgarian, Mongolian, "
- "Abkhazian, Adyghe, Kabardian, Avar, Dargin, Ingush, Chechen, Lak, Lezgin, "
- "Tabasaran, Kazakh, Kyrgyz, Tajik, Macedonian, Tatar, Chuvash, Bashkir, "
- "Malian, Moldovan, Udmurt, Komi, Ossetian, Buryat, Kalmyk, Tuvan, Sakha, "
- "Karakalpak, English"
- ),
- "devanagari": (
- "Hindi, Marathi, Nepali, Bihari, Maithili, Angika, Bhojpuri, Magahi, "
- "Santali, Newari, Konkani, Sanskrit, Haryanvi, English"
- ),
-}
-
-PUBLIC_OCR_LANGUAGE_CHOICES = tuple(f"{lang} ({_PUBLIC_OCR_LANGUAGE_DESCRIPTIONS[lang]})" for lang in PUBLIC_OCR_LANGUAGES)
-
-PUBLIC_OCR_LANGUAGE_SCHEMA_EXTRA = {"items": {"enum": list(PUBLIC_OCR_LANGUAGES)}}
-
_CH_LANG_ALIASES = {"en", "japan", "chinese_cht", "latin"}
_ARABIC_LANG_ALIASES = {"ar", "fa", "ug", "ur", "ps", "ku", "sd", "bal"}
_EAST_SLAVIC_LANG_ALIASES = {"ru", "be", "uk"}
@@ -97,30 +54,6 @@ _DEVANAGARI_LANG_ALIASES = {
}
-def format_public_ocr_lang_description() -> str:
- """生成公开 API 使用的 OCR 语言说明,避免入口文案各自维护。"""
- option_lines = [f"- {lang}: {_PUBLIC_OCR_LANGUAGE_DESCRIPTIONS[lang]}." for lang in PUBLIC_OCR_LANGUAGES]
- return (
- "(Mainly for Hybrid medium local OCR and table OCR; accepted by other "
- "Hybrid efforts for compatibility.) Input the languages in the pdf "
- "to improve OCR accuracy when language-aware OCR is used. Options:\n" + "\n".join(option_lines)
- )
-
-
-def validate_public_ocr_lang(lang: str) -> str:
- """校验公开入口允许的 OCR 语言,并将隐藏兼容别名归一到 ch。"""
- normalized_lang = "ch" if lang in _CH_LANG_ALIASES else lang
- if normalized_lang not in PUBLIC_OCR_LANGUAGES:
- raise ValueError(f"Language {lang} not supported. Allowed values: " + ", ".join(PUBLIC_OCR_LANGUAGES))
- return normalized_lang
-
-
-def validate_public_ocr_lang_list(lang_list: list[str]) -> list[str]:
- """校验公开 API 的语言列表,返回可安全传入下游的副本。"""
- effective_lang_list = lang_list or ["ch"]
- return [validate_public_ocr_lang(lang) for lang in effective_lang_list]
-
-
def normalize_ocr_model_lang(
lang: str | None,
*,
diff --git a/mineru/parser/api_server.py b/mineru/parser/api_server.py
index 6960193b..0b757018 100644
--- a/mineru/parser/api_server.py
+++ b/mineru/parser/api_server.py
@@ -50,7 +50,6 @@ from ..filetypes import (
file_type_for_extension,
is_flash_only_parse_extension,
)
-from ..model.ocr.language import PUBLIC_OCR_LANGUAGES, validate_public_ocr_lang
from ..types import SERVER_TIERS, TIERS_BY_SERVER_TIER, DeploymentTier, PageInfo, ServerTier, Tier, select_default_quality_tier
from ..utils.async_utils import drain_future, run_sync
from ..model.vlm.async_runtime import RuntimeOwner, runtime_owner
@@ -80,7 +79,6 @@ from .tier import (
from .writer import DataWriter
_DEFAULT_API_SERVER_TIER: ServerTier = "standard"
-_API_SERVER_LANGUAGES = PUBLIC_OCR_LANGUAGES
_MAX_INLINE_BYTES_DEFAULT = 1024 * 1024
_MAX_FILES_PER_JOB_DEFAULT = 100
_MAX_FILE_SIZE_BYTES_DEFAULT = 209715200
@@ -2185,7 +2183,7 @@ def _classify_model_preload_error(exc: Exception) -> tuple[str, str]:
return "model_preload_failed", message
-def _preload_local_models(language: str) -> None:
+def _preload_local_models() -> None:
# TODO: fix import
from ..model.runtime.contracts import AtomicModelName
from ..model.runtime.hybrid import HybridLocalModelContextSingleton
@@ -2194,21 +2192,22 @@ def _preload_local_models(language: str) -> None:
manager = context.atom_model_manager
manager.get_atom_model(atom_model_name=AtomicModelName.TableOrientationCls)
manager.get_atom_model(atom_model_name=AtomicModelName.TableCls)
- manager.get_atom_model(atom_model_name=AtomicModelName.WirelessTable, lang=language)
- manager.get_atom_model(atom_model_name=AtomicModelName.WiredTable, lang=language)
+ # 表格模型语言与 HybridLocalModelContext 运行时的缓存键保持一致,确保预热的模型可被复用。
+ manager.get_atom_model(atom_model_name=AtomicModelName.WirelessTable, lang="ch")
+ manager.get_atom_model(atom_model_name=AtomicModelName.WiredTable, lang="ch")
manager.get_atom_model(atom_model_name=AtomicModelName.OCR, lang="seal")
-def _preload_server_models(tier: DeploymentTier, *, language: str, vlm_config: VlmConfig | None = None) -> _ModelPreloadResult:
+def _preload_server_models(tier: DeploymentTier, *, vlm_config: VlmConfig | None = None) -> _ModelPreloadResult:
"""使用与实际解析相同的 VLM 客户端,并预加载本地 Hybrid 模型。"""
if tier == "basic":
- _preload_local_models(language)
+ _preload_local_models()
return _ModelPreloadResult(tier=tier, engine="hybrid-local")
from ..model.vlm.client import get_vlm_predictor
_predictor, engine = get_vlm_predictor(vlm_config)
- _preload_local_models(language)
+ _preload_local_models()
return _ModelPreloadResult(tier=tier, engine=engine)
@@ -2245,7 +2244,6 @@ def create_app(
max_url_bytes: int = _MAX_FILE_SIZE_BYTES_DEFAULT,
allow_http_source: bool = False,
api_key: str | None = None,
- language: str = "ch",
image_analysis: bool = True,
preload_models: bool = False,
vlm_config: VlmConfig | None = None,
@@ -2279,8 +2277,6 @@ def create_app(
api_key:
Optional API key. When set, clients must pass ``Authorization: Bearer <key>``
to access list endpoints and advanced output formats.
- language:
- Hybrid medium OCR language hint; accepted by other efforts for compatibility.
image_analysis:
Whether image analysis is enabled for Hybrid backends.
preload_models:
@@ -2305,7 +2301,6 @@ def create_app(
raise ValueError("max_inline_bytes must be non-negative")
if max_url_bytes < 0:
raise ValueError("max_url_bytes must be non-negative")
- language = validate_public_ocr_lang(language)
_model_ids, _tiers = _model_ids_and_tiers_for_server_tiers(server_tiers)
_preload_tier: DeploymentTier | None = None
@@ -2329,7 +2324,6 @@ def create_app(
application.state.max_url_bytes = max_url_bytes
application.state.allow_http_source = allow_http_source
application.state.api_key = _api_key
- application.state.language = language
application.state.effort = effort
application.state.image_analysis = image_analysis
application.state.preload_models = preload_models
@@ -2344,7 +2338,6 @@ def create_app(
preload_result = await run_sync(
_preload_server_models,
_preload_tier,
- language=language,
vlm_config=vlm_config,
)
except Exception as exc:
@@ -2394,7 +2387,6 @@ def create_app(
application.state.max_url_bytes = max_url_bytes
application.state.allow_http_source = allow_http_source
application.state.api_key = _api_key
- application.state.language = language
application.state.effort = effort
application.state.image_analysis = image_analysis
application.state.preload_models = preload_models
@@ -2550,13 +2542,6 @@ def _build_server_log_config(log_level: str) -> dict[str, Any]:
is_flag=True,
help="Allow url sources to use plain HTTP. HTTPS is always allowed.",
)
- "--language",
- default="ch",
- type=str,
- metavar="[" + "|".join(_API_SERVER_LANGUAGES) + "]",
- help="Hybrid medium OCR language hint; accepted by other efforts for compatibility.",
-)
@click.option(
"--disable-image-analysis",
is_flag=True,
@@ -2595,7 +2580,6 @@ def main(
max_inline_bytes: int,
max_url_bytes: int,
allow_http_source: bool,
- language: str,
disable_image_analysis: bool,
preload_models: bool,
api_key: str | None,
@@ -2653,7 +2637,6 @@ def main(
max_url_bytes=max_url_bytes,
allow_http_source=allow_http_source,
api_key=api_key,
- language=language,
image_analysis=not disable_image_analysis,
preload_models=preload_models,
vlm_config=vlm_settings,
diff --git a/mineru/utils/translations.py b/mineru/utils/translations.py
index 488fd989..4006e848 100644
--- a/mineru/utils/translations.py
+++ b/mineru/utils/translations.py
@@ -474,7 +474,6 @@ ZH_MESSAGES: dict[str, str] = {
"LaTeX delimiters used by the Markdown preview": "Markdown 预览使用的 LaTeX 定界符",
"Managed API server capability tier": "托管 API server 的能力档位",
"Managed server job concurrency": "托管服务的任务并发数",
- "Managed server OCR language": "托管服务的 OCR 语言",
"Disable managed server image analysis": "禁用托管服务的图像分析",
"Preload managed server models": "预加载托管服务的模型",
# ------------------------------------------------------- kit api-server
@@ -490,9 +489,6 @@ ZH_MESSAGES: dict[str, str] = {
"Allow local source paths": "允许本地来源路径",
"Maximum decoded bytes for inline sources": "内联来源的最大解码字节数",
"Allow URL sources to use plain HTTP": "允许 URL 来源使用明文 HTTP",
- "Hybrid medium OCR language hint; accepted by other efforts for compatibility": (
- "Hybrid 中档 OCR 语言提示;为兼容性也接受其他档位传入"
- ),
"Initialize VLM client and local Hybrid models at startup": "启动时初始化 VLM 客户端与本地 Hybrid 模型",
"Optional fixed API key": "可选的固定 API key",
"Remote VLM URL; empty value selects local VLM": "远程 VLM URL;留空选择本地 VLM",
diff --git a/tests/unittest/test_kit_commands.py b/tests/unittest/test_kit_commands.py
index 638b2973..d5994ad4 100644
--- a/tests/unittest/test_kit_commands.py
+++ b/tests/unittest/test_kit_commands.py
@@ -6,7 +6,7 @@ import sys
import tomllib
from collections.abc import Callable
from pathlib import Path
-from types import ModuleType, SimpleNamespace
+from types import ModuleType
from typing import Any
import pytest
@@ -586,10 +586,17 @@ def test_api_server_rejects_backend_and_effort_options() -> None:
@pytest.mark.parametrize(
("command", "option"),
- [("api-server", "--ocr-mode"), ("webui", "--ocr-mode"), ("webui", "--api-server-ocr-mode")],
+ [
+ ("api-server", "--ocr-mode"),
+ ("api-server", "--language"),
+ ("webui", "--ocr-mode"),
+ ("webui", "--api-server-ocr-mode"),
+ ("webui", "--language"),
+ ("webui", "--api-server-language"),
+ ],
)
def test_server_commands_reject_startup_ocr_configuration(command: str, option: str) -> None:
- """服务启动命令不再接受或展示 OCR 配置,单次解析命令继续提供该参数。"""
+ """服务启动命令不再接受或展示 OCR 与语言配置,单次解析命令继续提供 OCR 参数。"""
result = runner.invoke(app, [command, option, "ocr"])
assert result.exit_code != 0
assert "No such option" in result.output
@@ -673,27 +680,11 @@ def test_api_server_rejects_flash_no_flash_conflict() -> None:
assert "--tier flash cannot be combined with --no-flash" in result.output
-def test_api_server_normalizes_hidden_language_alias(monkeypatch: Any) -> None:
- seen: dict[str, Any] = {}
-
- def _fake_main(*, args: list[str], prog_name: str, standalone_mode: bool) -> None:
- """记录 api-server 转发参数,确认隐藏语言别名不会继续下传。"""
- seen["args"] = args
-
- monkeypatch.setattr(api_server.parser_api_server.main, "main", _fake_main)
-
+def test_api_server_rejects_removed_language_option() -> None:
result = runner.invoke(app, ["api-server", "--language", "en"])
- assert result.exit_code == 0
- language_index = seen["args"].index("--language")
- assert seen["args"][language_index + 1] == "ch"
-
-
-def test_api_server_rejects_removed_ch_lite_language() -> None:
- result = runner.invoke(app, ["api-server", "--language", "ch_lite"])
-
- assert result.exit_code == 1
- assert "Language ch_lite not supported" in result.output
+ assert result.exit_code == 2
+ assert "No such option: --language" in " ".join(result.output.split())
def test_vlm_server_rejects_removed_sglang_engine() -> None:
diff --git a/tests/unittest/test_kit_gradio.py b/tests/unittest/test_kit_gradio.py
index 2b80915b..a7d6dcb0 100644
--- a/tests/unittest/test_kit_gradio.py
+++ b/tests/unittest/test_kit_gradio.py
@@ -743,7 +743,6 @@ def test_managed_local_api_command_uses_kit_entrypoint() -> None:
server = ManagedLocalApiServer(
tier="standard",
concurrency=3,
- language="en",
disable_image_analysis=True,
preload_models=True,
api_key="secret",
@@ -756,11 +755,16 @@ def test_managed_local_api_command_uses_kit_entrypoint() -> None:
assert "--no-advanced" not in command
assert "--preload-models" in command
assert "--ocr-mode" not in command
+ assert "--language" not in command
assert command[command.index("--api-key") + 1] == "secret"
with pytest.raises(TypeError, match="ocr_mode"):
ManagedLocalApiServer(ocr_mode="ocr") # type: ignore[call-arg]
with pytest.raises(TypeError, match="api_server_ocr_mode"):
gradio_app.launch_gradio(api_server_ocr_mode="ocr") # type: ignore[call-arg]
+ with pytest.raises(TypeError, match="language"):
+ ManagedLocalApiServer(language="ch") # type: ignore[call-arg]
+ with pytest.raises(TypeError, match="api_server_language"):
+ gradio_app.launch_gradio(api_server_language="ch") # type: ignore[call-arg]
for option in ("no_flash", "no_advanced"):
with pytest.raises(TypeError, match=option):
ManagedLocalApiServer(**{option: True}) # type: ignore[arg-type]
diff --git a/tests/unittest/test_kit_gradio_page_range.py b/tests/unittest/test_kit_gradio_page_range.py
index c4a966a1..496934f0 100644
--- a/tests/unittest/test_kit_gradio_page_range.py
+++ b/tests/unittest/test_kit_gradio_page_range.py
@@ -88,7 +88,6 @@ def test_launch_forwards_limit_and_versioned_assets(monkeypatch: pytest.MonkeyPa
latex_delimiters_type="all",
api_server_tier="standard",
api_server_concurrency=1,
- api_server_language="ch",
api_server_disable_image_analysis=False,
api_server_preload_models=False,
max_pages=20,
@@ -137,7 +136,6 @@ def test_launch_forwards_managed_options_and_stops_server(monkeypatch: pytest.Mo
latex_delimiters_type="all",
api_server_tier="standard",
api_server_concurrency=2,
- api_server_language="ch",
api_server_disable_image_analysis=False,
api_server_preload_models=False,
)
@@ -145,7 +143,6 @@ def test_launch_forwards_managed_options_and_stops_server(monkeypatch: pytest.Mo
assert captured["options"] == {
"tier": "standard",
"concurrency": 2,
- "language": "ch",
"disable_image_analysis": False,
"preload_models": False,
"api_key": None,
@@ -216,7 +213,6 @@ def test_launch_remote_flash_fallback_and_cleanup(
"latex_delimiters_type": "all",
"api_server_tier": "standard",
"api_server_concurrency": 2,
- "api_server_language": "en",
"api_server_disable_image_analysis": True,
"api_server_preload_models": True,
}
@@ -231,7 +227,7 @@ def test_launch_remote_flash_fallback_and_cleanup(
assert factory.call_args_list[0].kwargs == {"api_url": remote_cap.base_url, "api_key": "remote-secret"}
if needs_local and failure_stage != "remote":
server_factory.assert_called_once_with(
- tier="flash", concurrency=2, language="en", disable_image_analysis=True, preload_models=True, api_key=""
+ tier="flash", concurrency=2, disable_image_analysis=True, preload_models=True, api_key=""
)
server.stop.assert_called_once()
assert events[:2] == ["remote", "start"]
diff --git a/tests/unittest/test_parser_api_contract.py b/tests/unittest/test_parser_api_contract.py
index 5985f05a..11cb5a42 100644
--- a/tests/unittest/test_parser_api_contract.py
+++ b/tests/unittest/test_parser_api_contract.py
@@ -29,7 +29,6 @@ from mineru.config import VlmConfig
from mineru.parser import MIDDLE_JSON_SCHEMA_VERSION
from mineru.parser.api_client import MinerUApiParser, _pages_from_middle_json, _parse_result_from_job, should_trust_env_for_url
from mineru.parser.api_server import (
- _API_SERVER_LANGUAGES,
CreateJobRequest,
CreateUploadRequest,
FileParseInfo,
@@ -1812,7 +1811,6 @@ def test_create_app_does_not_read_runtime_settings_from_env(tmp_path: Path, monk
monkeypatch.setenv("MINERU_BACKEND", "hybrid-auto-engine")
monkeypatch.setenv("MINERU_CONCURRENCY", "9")
monkeypatch.setenv("MINERU_URL_TIMEOUT", "99")
- monkeypatch.setenv("MINERU_LANGUAGE", "en")
monkeypatch.setenv("MINERU_OCR_MODE", "ocr")
monkeypatch.setenv("MINERU_EFFORT", "high")
monkeypatch.setenv(_REMOVED_TABLE_ENABLE_ENV, "false")
@@ -1828,8 +1826,8 @@ def test_create_app_does_not_read_runtime_settings_from_env(tmp_path: Path, monk
assert app.state.allow_local_source is False
assert app.state.max_inline_bytes == 1024 * 1024
assert app.state.allow_http_source is False
- assert app.state.language == "ch"
assert not hasattr(app.state, "ocr_mode")
+ assert not hasattr(app.state, "language")
assert app.state.effort == "high"
assert app.state.image_analysis is True
assert not hasattr(app.state, _REMOVED_TABLE_ENABLE_PARAM)
@@ -2646,7 +2644,7 @@ def test_api_server_model_preload_failure_keeps_health_diagnostics_and_rejects_c
_stub_api_server_dependency_preflight(monkeypatch)
def _fail_preload(
- startup_tier: DeploymentTier, *, language: str, vlm_config: VlmConfig | None = None
+ startup_tier: DeploymentTier, *, vlm_config: VlmConfig | None = None
) -> api_server._ModelPreloadResult:
"""模拟包含 VLM 初始化在内的服务预加载失败。"""
raise ValueError("CUDA is not available.")
@@ -2670,13 +2668,13 @@ def test_api_server_model_preload_failure_keeps_health_diagnostics_and_rejects_c
def test_api_server_model_preload_is_opt_in_and_ignored_for_flash(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
_stub_api_server_dependency_preflight(monkeypatch)
- calls: list[tuple[str, str]] = []
+ calls: list[str] = []
def _preload(
- startup_tier: DeploymentTier, *, language: str, vlm_config: VlmConfig | None = None
+ startup_tier: DeploymentTier, *, vlm_config: VlmConfig | None = None
) -> api_server._ModelPreloadResult:
"""记录预加载调用,兼容显式 VLM 配置传入。"""
- calls.append((startup_tier, language))
+ calls.append(startup_tier)
return api_server._ModelPreloadResult(tier=startup_tier, engine="test")
monkeypatch.setattr(api_server, "_preload_server_models", _preload)
@@ -2688,7 +2686,7 @@ def test_api_server_model_preload_is_opt_in_and_ignored_for_flash(tmp_path: Path
with TestClient(create_app(upload_dir=str(tmp_path / "flash"), tier="flash", preload_models=True)) as flash_client:
assert flash_client.get("/v1/health").status_code == 200
- assert calls == [("basic", "ch")]
+ assert calls == ["basic"]
def test_api_server_standard_jobs_use_requested_tier(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
@@ -2938,35 +2936,32 @@ def test_api_server_create_app_rejects_backend_and_effort_parameters(tmp_path: P
with pytest.raises(TypeError, match="effort"):
create_app(upload_dir=str(tmp_path / "effort"), effort="high") # type: ignore[call-arg]
+ with pytest.raises(TypeError, match="language"):
+ create_app(upload_dir=str(tmp_path / "language"), language="ch") # type: ignore[call-arg]
+
def test_api_server_stores_parser_runtime_options(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
_stub_api_server_dependency_preflight(monkeypatch)
app = create_app(
upload_dir=str(tmp_path),
tier="basic",
- language="en",
image_analysis=False,
)
- assert app.state.language == "ch"
assert not hasattr(app.state, "ocr_mode")
+ assert not hasattr(app.state, "language")
assert app.state.effort == "medium"
assert app.state.image_analysis is False
assert not hasattr(app.state, _REMOVED_TABLE_ENABLE_PARAM)
assert not hasattr(app.state, _REMOVED_FORMULA_ENABLE_PARAM)
-def test_api_server_rejects_removed_ch_lite_language(tmp_path: Path) -> None:
- with pytest.raises(ValueError, match="Language ch_lite not supported"):
- create_app(upload_dir=str(tmp_path), language="ch_lite")
-
-
def test_api_server_cli_exposes_parser_runtime_options() -> None:
option_names = {name for param in main.params for name in param.opts}
assert "--tier" in option_names
assert "--backend" not in option_names
- assert "--language" in option_names
+ assert "--language" not in option_names
assert "--ocr-mode" not in option_names
assert "--allow-local-source" in option_names
assert "--max-inline-bytes" in option_names
@@ -2976,20 +2971,6 @@ def test_api_server_cli_exposes_parser_runtime_options() -> None:
assert "--preload-models" in option_names
assert _REMOVED_DISABLE_TABLE_OPTION not in option_names
assert _REMOVED_DISABLE_FORMULA_OPTION not in option_names
- assert _API_SERVER_LANGUAGES == (
- "ch",
- "ch_server",
- "korean",
- "ta",
- "te",
- "ka",
- "th",
- "el",
- "arabic",
- "east_slavic",
- "cyrillic",
- "devanagari",
- )
def test_api_server_cli_rejects_backend_and_effort_options() -> None:
@@ -3102,26 +3083,12 @@ def test_api_server_cli_rejects_flash_no_flash_conflict() -> None:
assert "--tier flash cannot be combined with --no-flash" in result.output
-def test_api_server_cli_normalizes_hidden_language_alias(monkeypatch: pytest.MonkeyPatch) -> None:
- seen: dict[str, str] = {}
-
- def _fake_run(server: Any) -> None:
- """记录 Click CLI 创建出的应用语言配置,避免测试启动真实服务。"""
- seen["language"] = server.config.app.state.language
-
- monkeypatch.setattr("uvicorn.Server.run", _fake_run)
-
- result = runner.invoke(main, ["--language", "latin", "--host", "0.0.0.0", "--port", "15982"])
-
- assert result.exit_code == 0
- assert seen == {"language": "ch"}
-
-
-def test_api_server_cli_rejects_removed_ch_lite_language() -> None:
- result = runner.invoke(main, ["--language", "ch_lite"])
+def test_api_server_cli_rejects_removed_language_option() -> None:
+ result = runner.invoke(main, ["--language", "en"])
assert result.exit_code != 0
- assert "Language ch_lite not supported" in result.output
+ assert "No such option" in result.output
+ assert "--language" in result.output
def test_api_server_cli_help_exposes_tier_only_runtime_selection() -> None: