endoreg-db 0.4.5__py3-none-any.whl → 0.8.6.3__py3-none-any.whl

endoreg_db/models/upload_job.py

@@ -0,0 +1,99 @@
+import uuid
+from django.db import models
+
+
+class UploadJob(models.Model):
+    """
+    Tracks file upload jobs and their processing status.
+    Supports both PDF and video file uploads with asynchronous processing.
+    """
+    
+    class Status(models.TextChoices):
+        PENDING = 'pending', 'Pending'
+        PROCESSING = 'processing', 'Processing'
+        ANONYMIZED = 'anonymized', 'Anonymized'
+        ERROR = 'error', 'Error'
+
+    id = models.UUIDField(
+        primary_key=True, 
+        default=uuid.uuid4, 
+        editable=False,
+        help_text="Unique identifier for the upload job"
+    )
+    
+    file = models.FileField(
+        upload_to='uploads/%Y/%m/%d/',
+        help_text="Uploaded file (PDF or video)"
+    )
+    
+    status = models.CharField(
+        max_length=20,
+        choices=Status.choices,
+        default=Status.PENDING,
+        help_text="Current processing status of the upload"
+    )
+    
+    content_type = models.CharField(
+        max_length=100,
+        blank=True,
+        help_text="MIME type of the uploaded file"
+    )
+    
+    sensitive_meta = models.ForeignKey(
+        'SensitiveMeta',
+        null=True,
+        blank=True,
+        on_delete=models.SET_NULL,
+        help_text="Link to the created SensitiveMeta record after processing"
+    )
+    
+    error_detail = models.TextField(
+        blank=True,
+        help_text="Error message if processing failed"
+    )
+    
+    created_at = models.DateTimeField(
+        auto_now_add=True,
+        help_text="When the upload job was created"
+    )
+    
+    updated_at = models.DateTimeField(
+        auto_now=True,
+        help_text="When the upload job was last updated"
+    )
+
+    class Meta:
+        ordering = ['-created_at']
+        verbose_name = "Upload Job"
+        verbose_name_plural = "Upload Jobs"
+
+    def __str__(self):
+        return f"UploadJob {self.id} - {self.status} ({self.content_type})"
+
+    @property
+    def is_complete(self):
+        """Returns True if the job has finished processing (success or error)."""
+        return self.status in [self.Status.ANONYMIZED, self.Status.ERROR]
+
+    @property
+    def is_successful(self):
+        """Returns True if the job completed successfully."""
+        return self.status == self.Status.ANONYMIZED
+
+    def mark_processing(self):
+        """Mark the job as processing."""
+        self.status = self.Status.PROCESSING
+        self.save(update_fields=['status', 'updated_at'])
+
+    def mark_completed(self, sensitive_meta=None):
+        """Mark the job as successfully completed."""
+        self.status = self.Status.ANONYMIZED
+        if sensitive_meta:
+            self.sensitive_meta = sensitive_meta
+        self.save(update_fields=['status', 'sensitive_meta', 'updated_at'])
+
+    def mark_error(self, error_detail: str):
+        """Mark the job as failed with error details."""
+        self.status = self.Status.ERROR
+        self.error_detail = error_detail
+        self.save(update_fields=['status', 'error_detail', 'updated_at'])

endoreg_db/models/utils.py

@@ -0,0 +1,135 @@
+from ..utils import (
+    data_paths,
+    DJANGO_NAME_SALT,
+)
+from django.core.files import File
+from django.core.files.storage import FileSystemStorage
+import io
+import os
+from tqdm import tqdm
+import numpy as np
+import cv2
+from typing import TYPE_CHECKING, List, Tuple
+from pathlib import Path
+if TYPE_CHECKING:
+    from ..models.media import VideoFile
+
+from logging import getLogger
+
+logger = getLogger(__name__)
+
+STORAGE_DIR = data_paths["storage"]
+FILE_STORAGE = FileSystemStorage(location = STORAGE_DIR)
+VIDEO_DIR = data_paths["video"]
+TMP_VIDEO_DIR = VIDEO_DIR / "tmp"
+ANONYM_VIDEO_DIR = data_paths["video_export"]
+FRAME_DIR = data_paths["frame"]
+WEIGHTS_DIR = data_paths["weights"]
+PDF_DIR = data_paths["raw_pdf"]
+DOCUMENT_DIR = data_paths["pdf"]
+
+TEST_RUN = os.environ.get("TEST_RUN", "False")
+TEST_RUN = TEST_RUN.lower() == "true"
+
+TEST_RUN_FRAME_NUMBER = int(os.environ.get("TEST_RUN_FRAME_NUMBER", "500"))
+
+
+def prepare_bulk_frames(frame_paths: List[Path]):
+    """
+    Reads the frame paths into memory as Django File objects.
+    This avoids 'seek of closed file' errors by using BytesIO for each frame.
+    """
+    for path in frame_paths:
+        frame_number = int(path.stem.split("_")[1])
+        with open(path, "rb") as f:
+            content = f.read()
+        file_obj = File(io.BytesIO(content), name=path.name)
+        yield frame_number, file_obj
+
+
+def find_segments_in_prediction_array(prediction_array: np.array, min_frame_len: int):
+    """
+    Expects a prediction array of shape (num_frames) and a minimum frame length.
+    Returns a list of tuples (start_frame_number, end_frame_number) that represent the segments.
+    """
+    # Add False to the beginning and end to detect changes at the array boundaries
+    padded_prediction = np.pad(
+        prediction_array, (1, 1), "constant", constant_values=False
+    )
+
+    # Find the start points and end points of the segments
+    diffs = np.diff(padded_prediction.astype(int))
+    segment_starts = np.where(diffs == 1)[0]
+    segment_ends = np.where(diffs == -1)[0]
+
+    # Filter segments based on min_frame_len
+    segments = [
+        (start, end)
+        for start, end in zip(segment_starts, segment_ends)
+        if end - start >= min_frame_len
+    ]
+
+    return segments
+
+def anonymize_frame(
+    raw_frame_path: Path, target_frame_path: Path, endo_roi, all_black: bool = False, censor_color: Tuple[int, int, int] = (0, 0, 0) # Added censor_color param
+):
+    """
+    Anonymize the frame by blacking out pixels outside the endoscope ROI or making the whole frame black.
+    """
+    frame = cv2.imread(raw_frame_path.as_posix())
+    if frame is None:
+        # Raise error instead of returning None/frame
+        raise FileNotFoundError(f"Could not read frame at {raw_frame_path}")
+
+    # make black frame with same size as original frame
+    new_frame = np.zeros_like(frame)
+
+    if not all_black:
+        # Validate ROI dictionary keys
+        required_keys = {"x", "y", "width", "height"}
+        if not required_keys.issubset(endo_roi):
+            raise ValueError(f"Invalid endo_roi dictionary provided: {endo_roi}. Missing keys.")
+
+        x = endo_roi["x"]
+        y = endo_roi["y"]
+        width = endo_roi["width"]
+        height = endo_roi["height"]
+
+        # Add boundary checks for ROI coordinates
+        h_orig, w_orig, _ = frame.shape
+        x1, y1 = max(0, x), max(0, y)
+        x2, y2 = min(w_orig, x + width), min(h_orig, y + height)
+
+        if x1 >= x2 or y1 >= y2:
+            logger.warning(f"ROI [{x},{y},{width},{height}] is outside or invalid for frame dimensions {w_orig}x{h_orig}. Resulting frame might be all black.")
+        else:
+            # copy valid endoscope roi part to black frame
+            new_frame[y1:y2, x1:x2] = frame[y1:y2, x1:x2]
+    else:
+        # If all_black, fill with censor_color (defaults to black)
+        new_frame[:] = censor_color
+
+    # Check if writing the anonymized frame was successful
+    success = cv2.imwrite(target_frame_path.as_posix(), new_frame)
+    if not success:
+        raise IOError(f"Failed to write anonymized frame to {target_frame_path}")
+
+
+__all__ = [
+    "DJANGO_NAME_SALT",
+    "data_paths",
+    "FILE_STORAGE",
+    "VIDEO_DIR",
+    "TMP_VIDEO_DIR",
+    "ANONYM_VIDEO_DIR",
+    "FRAME_DIR",
+    "WEIGHTS_DIR",
+    "PDF_DIR",
+    "DOCUMENT_DIR",
+    "prepare_bulk_frames",
+    "anonymize_frame",
+    "find_segments_in_prediction_array",
+    "TEST_RUN",
+    "TEST_RUN_FRAME_NUMBER",
+]

endoreg_db/renames.yml

@@ -0,0 +1,8 @@
+date_created: created_at
+date_modified: updated_at
+last_update: updated_at
+date_updated: updated_at
+createdOn: created_at
+updatedOn: updated_at
+modified_at: updated_at
+lastModified: updated_at

endoreg_db/root_urls.py

@@ -0,0 +1,9 @@
+from django.urls import include, path
+
+# Import raw API urlpatterns (no prefix) from the URLs package
+from endoreg_db.urls import urlpatterns as api_urlpatterns
+
+# Mount the API under /api/
+urlpatterns = [
+    path("api/", include((api_urlpatterns, "endoreg_db"), namespace="api")),
+]

endoreg_db/schemas/examination_evaluation.py

@@ -0,0 +1,27 @@
+# app/schemas/evaluation.py
+from __future__ import annotations
+from pydantic import BaseModel, ConfigDict, Field
+from typing import List, Optional
+
+class RequirementEval(BaseModel):
+    id: int
+    name: str
+    description: Optional[str] = None
+    satisfied: bool
+    message: Optional[str] = None  # optional explanation
+
+class RequirementSetEval(BaseModel):
+    id: int
+    name: str
+    type: Optional[str] = None  # e.g., "all", "any", "exactly_1"
+    is_satisfied: bool
+    requirements: List[RequirementEval] = Field(default_factory=list)
+    linked_sets: List["RequirementSetEval"] = Field(default_factory=list)
+
+class ExaminationEvalReport(BaseModel):
+    examination_id: int
+    summary: dict
+    sets: List[RequirementSetEval]
+    errors: List[str] = Field(default_factory=list)
+
+    model_config = ConfigDict(from_attributes=True)