Updated models.py

src/transcription/models.py

@@ -1,12 +1,13 @@
 """SQLModel domain models for the transcription system.
 
 Three models capture the MVP lifecycle:
-    Document  ->  one-to-many  ->  Job  ->  one-to-many  ->  Transcript
+    Document  ->  one-to-many  ->  Source -> one-to-many  ->  Job  ->  one-to-many  ->  Transcript
 """
 
 from datetime import UTC
 from datetime import datetime
 from enum import StrEnum
+from typing import Optional
 from uuid import UUID
 from uuid import uuid4
 
@@ -24,15 +25,34 @@ class JobStatus(StrEnum):
 
 
 class Document(SQLModel, table=True):
-    """An uploaded document image."""
+    """An historical document."""
 
     id: UUID = Field(default_factory=uuid4, primary_key=True)
-    filename: str
-    file_path: str
-    uploaded_at: datetime = Field(default_factory=lambda: datetime.now(UTC))
+    name: str
 
-    # --- relationships ---
+    # Relationships
     jobs: list["Job"] = Relationship(back_populates="document")
+    sources: list["Source"] = Relationship(back_populates="document")
+
+
+class Source(SQLModel, table=True):
+    """A document source (image or pdf)."""
+
+    id: UUID = Field(default_factory=uuid4, primary_key=True)
+    document_id: UUID = Field(foreign_key="document.id")
+    job_id: UUID = Field(foreign_key="job.id")
+    upload_name: str
+    """The filename of the source that was uploaded for transcription."""
+    filename: str
+    """The system generated unique source name."""
+    file_path: str
+    """The location where the sources are stored on the local filesystem."""
+    date_uploaded: datetime = Field(default_factory=lambda: datetime.now(UTC))
+
+    # Relationships
+    document: Optional["Document"] = Relationship(back_populates="sources")
+    job: Optional["Job"] = Relationship(back_populates="sources")
+    revisions: list["Revision"] = Relationship(back_populates="source")
 
 
 class Job(SQLModel, table=True):
@@ -42,40 +62,42 @@ class Job(SQLModel, table=True):
     document_id: UUID = Field(foreign_key="document.id")
     status: JobStatus = Field(default=JobStatus.QUEUED)
     retry_count: int = Field(default=0, ge=0)
-    created_at: datetime = Field(default_factory=lambda: datetime.now(UTC))
-    updated_at: datetime = Field(default_factory=lambda: datetime.now(UTC))
-
-    # --- relationships ---
-    document: Document = Relationship(back_populates="jobs")
-    transcripts: list["Transcript"] = Relationship(back_populates="job")
-
-    @property
-    def filename(self) -> str:
-        """Return the filename of the associated document."""
-        return self.document.filename if self.document else "unknown"
-
-
-class Transcript(SQLModel, table=True):
-    """The output of a transcription job."""
-
-    id: UUID = Field(default_factory=uuid4, primary_key=True)
-    job_id: UUID = Field(foreign_key="job.id")
-    """ID for the associated job."""
-    revision: int = Field(default=0, ge=0)
-    """Revision number for this job's transcript history, starting at 0."""
+    date_created: datetime = Field(default_factory=lambda: datetime.now(UTC))
+    date_updated: datetime = Field(default_factory=lambda: datetime.now(UTC))
     provider: str
     """Name of the transcription provider used to generate this transcript."""
     model: str
-    """Model identifier used to generate this transcript revision."""
+    """Model identifier used to generate this transcript."""
     prompt_name: str
     """Name of the prompt used to generate this transcript."""
     text: str | None = None
     """The transcribed text. This may be None if the job failed or is still in progress."""
     error_detail: str | None = None
     """Details of any error that occurred during transcription."""
-    created_at: datetime = Field(default_factory=lambda: datetime.now(UTC))
 
-    __table_args__ = (UniqueConstraint("job_id", "revision", name="uq_transcript_job_revision"),)
+    # Relationships
+    document: Optional["Document"] = Relationship(back_populates="jobs")
+    sources: list["Source"] = Relationship(back_populates="job")
 
-    # --- relationships ---
-    job: Job = Relationship(back_populates="transcripts")
+    @property
+    def filename(self) -> str:
+        """Return the filename of the associated document."""
+        return self.source.filename if self.source else "unknown"
+
+
+class Revision(SQLModel, table=True):
+    """A revision of a transcription text."""
+
+    id: UUID = Field(default_factory=uuid4, primary_key=True)
+    source_id: UUID = Field(foreign_key="source.id")
+    """ID for the associated source."""
+    revision: int = Field(default=1, ge=1)
+    """Revision number of this transcription revision, starting at 1."""
+    text: str
+    """The revised text."""
+    date_created: datetime = Field(default_factory=lambda: datetime.now(UTC))
+
+    # __table_args__ = (UniqueConstraint("job_id", "revision", name="uq_transcript_job_revision"),)
+
+    # Relationships
+    source: Optional["Source"] = Relationship(back_populates="revisions")