Files
doc_processer/app/schemas/convert.py
liuyuanchuang 30d2c2f45b fix: remove padding from GLMOCREndToEndService and clean up ruff violations
- Drop image padding in GLMOCREndToEndService.recognize(); use raw image directly
- Fix F821 undefined `padded` references replaced with `image`
- Fix F601 duplicate dict key "≠" in converter
- Fix F841 unused `image_cls_ids` variable in layout_postprocess
- Fix E702 semicolon-separated statements in layout_postprocess
- Fix UP031 percent-format replaced with f-string in logging_config
- Auto-fix 44 additional ruff violations (import order, UP035/UP045/UP006, F401, F541)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-10 19:52:22 +08:00

39 lines
1.3 KiB
Python

"""Request and response schemas for format conversion endpoints."""
from pydantic import BaseModel, Field, field_validator
class MarkdownToDocxRequest(BaseModel):
"""Request body for markdown to DOCX conversion endpoint."""
markdown: str = Field(..., description="Markdown content to convert")
filename: str = Field("texpixel", description="Optional output filename (without extension)")
@field_validator("markdown")
@classmethod
def validate_markdown_not_empty(cls, v: str) -> str:
"""Validate that markdown content is not empty."""
if not v or not v.strip():
raise ValueError("Markdown content cannot be empty")
return v
class LatexToOmmlRequest(BaseModel):
"""Request body for LaTeX to OMML conversion endpoint."""
latex: str = Field(..., description="Pure LaTeX formula (without $ or $$ delimiters)")
@field_validator("latex")
@classmethod
def validate_latex_not_empty(cls, v: str) -> str:
"""Validate that LaTeX formula is not empty."""
if not v or not v.strip():
raise ValueError("LaTeX formula cannot be empty")
return v
class LatexToOmmlResponse(BaseModel):
"""Response body for LaTeX to OMML conversion endpoint."""
omml: str = Field("", description="OMML (Office Math Markup Language) representation")