app/schemas/source.py

from __future__ import annotations

from datetime import datetime
from typing import Literal

from pydantic import BaseModel, ConfigDict, Field


SourceType = Literal[
    "pdf",
    "image",
    "syllabus_text",
    "chapter_text",
    "pyq_paper",
    "notes",
    "link",
]

MAX_SOURCE_TITLE_CHARS = 240
MAX_SOURCE_TEXT_CHARS = 200_000
MAX_SOURCE_METADATA_CHARS = 120


class SourceTextCreate(BaseModel):
    title: str = Field(min_length=1, max_length=MAX_SOURCE_TITLE_CHARS)
    text: str = Field(min_length=1, max_length=MAX_SOURCE_TEXT_CHARS)
    source_type: SourceType = "syllabus_text"
    subject: str | None = Field(default=None, max_length=MAX_SOURCE_METADATA_CHARS)
    chapter: str | None = Field(default=None, max_length=MAX_SOURCE_METADATA_CHARS)
    syllabus: str | None = Field(default=None, max_length=MAX_SOURCE_METADATA_CHARS)


class SourceUpdate(BaseModel):
    title: str | None = Field(default=None, min_length=1, max_length=MAX_SOURCE_TITLE_CHARS)
    text: str | None = Field(default=None, min_length=1, max_length=MAX_SOURCE_TEXT_CHARS)
    subject: str | None = Field(default=None, max_length=MAX_SOURCE_METADATA_CHARS)
    chapter: str | None = Field(default=None, max_length=MAX_SOURCE_METADATA_CHARS)
    syllabus: str | None = Field(default=None, max_length=MAX_SOURCE_METADATA_CHARS)


class SourceRead(BaseModel):
    id: str
    user_id: str
    title: str
    source_type: str
    status: str
    file_name: str | None = None
    file_type: str | None = None
    subject: str | None = None
    chapter: str | None = None
    syllabus: str | None = None
    word_count: int = 0
    chunk_count: int = 0
    preview_text: str = ""
    extraction_error: str | None = None
    created_at: datetime
    updated_at: datetime

    model_config = ConfigDict(from_attributes=True)


class SourceList(BaseModel):
    sources: list[SourceRead] = Field(default_factory=list)