pearmut 0.1.2__py3-none-any.whl → 0.2.0__py3-none-any.whl

pearmut/app.py

@@ -8,8 +8,8 @@ from fastapi.responses import JSONResponse
 from fastapi.staticfiles import StaticFiles
 from pydantic import BaseModel
 
-from .assignment import get_next_item, reset_task, update_progress
-from .utils import ROOT, load_progress_data, save_progress_data
+from .assignment import get_i_item, get_next_item, reset_task, update_progress
+from .utils import ROOT, load_progress_data, save_db_payload, save_progress_data
 
 os.makedirs(f"{ROOT}/data/outputs", exist_ok=True)
 
@@ -36,7 +36,7 @@ class LogResponseRequest(BaseModel):
     campaign_id: str
     user_id: str
     item_i: int
-    payload: Any
+    payload: dict[str, Any]
 
 
 @app.post("/log-response")
@@ -45,6 +45,7 @@ async def _log_response(request: LogResponseRequest):
 
     campaign_id = request.campaign_id
     user_id = request.user_id
+    item_i = request.item_i
 
     if campaign_id not in progress_data:
         return JSONResponse(content={"error": "Unknown campaign ID"}, status_code=400)
@@ -52,8 +53,8 @@ async def _log_response(request: LogResponseRequest):
         return JSONResponse(content={"error": "Unknown user ID"}, status_code=400)
 
     # append response to the output log
-    with open(f"{ROOT}/data/outputs/{campaign_id}.jsonl", "a") as log_file:
-        log_file.write(json.dumps(request.payload, ensure_ascii=False) + "\n")
+    save_db_payload(campaign_id, request.payload | {
+                    "user_id": user_id, "item_i": item_i})
 
     # if actions were submitted, we can log time data
     if "actions" in request.payload:
@@ -68,7 +69,16 @@ async def _log_response(request: LogResponseRequest):
             for a, b in zip(times, times[1:])
         ])
 
-    update_progress(campaign_id, user_id, tasks_data, progress_data, request.item_i, request.payload)
+    # Initialize validation_checks if it doesn't exist
+    print(request.payload.keys())
+    if "validations" in request.payload:
+        if "validations" not in progress_data[campaign_id][user_id]:
+            progress_data[campaign_id][user_id]["validations"] = {}
+
+        progress_data[campaign_id][user_id]["validations"][request.item_i] = request.payload["validations"]
+
+    update_progress(campaign_id, user_id, tasks_data,
+                    progress_data, request.item_i, request.payload)
     save_progress_data(progress_data)
 
     return JSONResponse(content={"status": "ok"}, status_code=200)
@@ -97,6 +107,32 @@ async def _get_next_item(request: NextItemRequest):
     )
 
 
+class GetItemRequest(BaseModel):
+    campaign_id: str
+    user_id: str
+    item_i: int
+
+
+@app.post("/get-i-item")
+async def _get_i_item(request: GetItemRequest):
+    campaign_id = request.campaign_id
+    user_id = request.user_id
+    item_i = request.item_i
+
+    if campaign_id not in progress_data:
+        return JSONResponse(content={"error": "Unknown campaign ID"}, status_code=400)
+    if user_id not in progress_data[campaign_id]:
+        return JSONResponse(content={"error": "Unknown user ID"}, status_code=400)
+
+    return get_i_item(
+        campaign_id,
+        user_id,
+        tasks_data,
+        progress_data,
+        item_i,
+    )
+
+
 class DashboardDataRequest(BaseModel):
     campaign_id: str
     token: str | None = None
@@ -119,6 +155,11 @@ async def _dashboard_data(request: DashboardDataRequest):
     for user_id, user_val in progress_data[campaign_id].items():
         # shallow copy
         entry = dict(user_val)
+        entry["validations"] = [
+            all(v)
+            for v in list(entry.get("validations", {}).values())
+        ]
+        
 
         if not is_privileged:
             entry["token_correct"] = None
@@ -203,10 +244,11 @@ async def _download_progress(
 
 static_dir = f"{os.path.dirname(os.path.abspath(__file__))}/static/"
 if not os.path.exists(static_dir + "index.html"):
-    raise FileNotFoundError("Static directory not found. Please build the frontend first.")
+    raise FileNotFoundError(
+        "Static directory not found. Please build the frontend first.")
 
 app.mount(
     "/",
     StaticFiles(directory=static_dir, html=True, follow_symlink=True),
     name="static",
-)
+)

pearmut/assignment.py

@@ -3,6 +3,8 @@ from typing import Any
 
 from fastapi.responses import JSONResponse
 
+from .utils import get_db_log_item
+
 
 def _completed_response(
     progress_data: dict,
@@ -37,13 +39,117 @@ def get_next_item(
     if assignment == "task-based":
         return get_next_item_taskbased(campaign_id, user_id, tasks_data, progress_data)
     elif assignment == "single-stream":
-        return get_next_item_single_stream(campaign_id, user_id, tasks_data, progress_data)
+        return get_next_item_singlestream(campaign_id, user_id, tasks_data, progress_data)
     elif assignment == "dynamic":
         return get_next_item_dynamic(campaign_id, user_id, tasks_data, progress_data)
     else:
         return JSONResponse(content={"error": "Unknown campaign assignment type"}, status_code=400)
 
 
+def get_i_item(
+    campaign_id: str,
+    user_id: str,
+    tasks_data: dict,
+    progress_data: dict,
+    item_i: int,
+) -> JSONResponse:
+    """
+    Get a specific item by index for the user in the specified campaign.
+    """
+    assignment = tasks_data[campaign_id]["info"]["assignment"]
+    if assignment == "task-based":
+        return get_i_item_taskbased(campaign_id, user_id, tasks_data, progress_data, item_i)
+    elif assignment == "single-stream":
+        return get_i_item_singlestream(campaign_id, user_id, tasks_data, progress_data, item_i)
+    else:
+        return JSONResponse(content={"error": "Get item not supported for this assignment type"}, status_code=400)
+
+
+def get_i_item_taskbased(
+    campaign_id: str,
+    user_id: str,
+    data_all: dict,
+    progress_data: dict,
+    item_i: int,
+) -> JSONResponse:
+    """
+    Get specific item for task-based protocol.
+    """
+    user_progress = progress_data[campaign_id][user_id]
+
+    # try to get existing annotations if any
+    items_existing = get_db_log_item(campaign_id, user_id, item_i)
+    if items_existing:
+        # get the latest ones
+        payload_existing = items_existing[-1]["annotations"]
+
+    if item_i < 0 or item_i >= len(data_all[campaign_id]["data"][user_id]):
+        return JSONResponse(
+            content={"status": "error", "message": "Item index out of range"},
+            status_code=400
+        )
+
+    return JSONResponse(
+        content={
+            "status": "ok",
+            "progress": user_progress["progress"],
+            "time": user_progress["time"],
+            "info": {
+                "item_i": item_i,
+            } | {
+                k: v
+                for k, v in data_all[campaign_id]["info"].items()
+                if k.startswith("protocol")
+            },
+            "payload": data_all[campaign_id]["data"][user_id][item_i]
+        } | ({"payload_existing": payload_existing} if items_existing else {}),
+        status_code=200
+    )
+
+
+def get_i_item_singlestream(
+    campaign_id: str,
+    user_id: str,
+    data_all: dict,
+    progress_data: dict,
+    item_i: int,
+) -> JSONResponse:
+    """
+    Get specific item for single-stream assignment.
+    """
+    user_progress = progress_data[campaign_id][user_id]
+
+    # try to get existing annotations if any
+    # note the None user_id since it is shared
+    items_existing = get_db_log_item(campaign_id, None, item_i)
+    if items_existing:
+        # get the latest ones
+        payload_existing = items_existing[-1]["annotations"]
+
+    if item_i < 0 or item_i >= len(data_all[campaign_id]["data"]):
+        return JSONResponse(
+            content={"status": "error", "message": "Item index out of range"},
+            status_code=400
+        )
+
+    return JSONResponse(
+        content={
+            "status": "ok",
+            "progress": user_progress["progress"],
+            "time": user_progress["time"],
+            "info": {
+                "item_i": item_i,
+            } | {
+                k: v
+                for k, v in data_all[campaign_id]["info"].items()
+                if k.startswith("protocol")
+            },
+            "payload": data_all[campaign_id]["data"][item_i]
+        } | ({"payload_existing": payload_existing} if items_existing else {}),
+        status_code=200
+    )
+
+
 def get_next_item_taskbased(
     campaign_id: str,
     user_id: str,
@@ -51,7 +157,7 @@ def get_next_item_taskbased(
     progress_data: dict,
 ) -> JSONResponse:
     """
-    Get the next item for task-based protocol.
+    Get the next item for task-based assignment.
     """
     user_progress = progress_data[campaign_id][user_id]
     if all(user_progress["progress"]):
@@ -59,6 +165,13 @@ def get_next_item_taskbased(
 
     # find first incomplete item
     item_i = min([i for i, v in enumerate(user_progress["progress"]) if not v])
+
+    # try to get existing annotations if any
+    items_existing = get_db_log_item(campaign_id, user_id, item_i)
+    if items_existing:
+        # get the latest ones
+        payload_existing = items_existing[-1]["annotations"]
+
     return JSONResponse(
         content={
             "status": "ok",
@@ -71,23 +184,20 @@ def get_next_item_taskbased(
                 for k, v in data_all[campaign_id]["info"].items()
                 if k.startswith("protocol")
             },
-            "payload": data_all[campaign_id]["data"][user_id][item_i]},
+            "payload": data_all[campaign_id]["data"][user_id][item_i]
+        } | ({"payload_existing": payload_existing} if items_existing else {}),
         status_code=200
     )
 
 
-def get_next_item_dynamic(campaign_data: dict, user_id: str, progress_data: dict, data_all: dict):
-    raise NotImplementedError("Dynamic protocol is not implemented yet.")
-
-
-def get_next_item_single_stream(
+def get_next_item_singlestream(
     campaign_id: str,
     user_id: str,
     data_all: dict,
     progress_data: dict,
 ) -> JSONResponse:
     """
-    Get the next item for single-stream protocol.
+    Get the next item for single-stream assignment.
     In this mode, all users share the same pool of items.
     Items are randomly selected from unfinished items.
 
@@ -104,6 +214,13 @@ def get_next_item_single_stream(
     incomplete_indices = [i for i, v in enumerate(progress) if not v]
     item_i = random.choice(incomplete_indices)
 
+    # try to get existing annotations if any
+    # note the None user_id since it is shared
+    items_existing = get_db_log_item(campaign_id, None, item_i)
+    if items_existing:
+        # get the latest ones
+        payload_existing = items_existing[-1]["annotations"]
+
     return JSONResponse(
         content={
             "status": "ok",
@@ -116,16 +233,24 @@ def get_next_item_single_stream(
                 for k, v in data_all[campaign_id]["info"].items()
                 if k.startswith("protocol")
             },
-            "payload": data_all[campaign_id]["data"][item_i]},
+            "payload": data_all[campaign_id]["data"][item_i]
+        } | ({"payload_existing": payload_existing} if items_existing else {}),
         status_code=200
     )
 
 
+
+def get_next_item_dynamic(campaign_data: dict, user_id: str, progress_data: dict, data_all: dict):
+    raise NotImplementedError("Dynamic protocol is not implemented yet.")
+
+
+
 def _reset_user_time(progress_data: dict, campaign_id: str, user_id: str) -> None:
     """Reset time tracking fields for a user."""
     progress_data[campaign_id][user_id]["time"] = 0.0
     progress_data[campaign_id][user_id]["time_start"] = None
     progress_data[campaign_id][user_id]["time_end"] = None
+    progress_data[campaign_id][user_id]["validations"] = {}
 
 
 def reset_task(
@@ -171,7 +296,6 @@ def update_progress(
     if assignment == "task-based":
         # even if it's already set it should be fine
         progress_data[campaign_id][user_id]["progress"][item_i] = True
-        # TODO: log attention checks/quality?
         return JSONResponse(content={"status": "ok"}, status_code=200)
     elif assignment == "single-stream":
         # progress all users

pearmut/cli.py

@@ -214,7 +214,7 @@ def main():
         import shutil
 
         confirm = input(
-            "Are you sure you want to purge all campaign data? This action cannot be undone. [y/n]"
+            "Are you sure you want to purge all campaign data? This action cannot be undone. [y/n] "
         )
         if confirm.lower() == 'y':
             shutil.rmtree(f"{ROOT}/data/tasks", ignore_errors=True)

pearmut/static/assets/style.css

@@ -225,4 +225,11 @@ input[type="button"].error_delete:hover {
 
 #progress span.progress_incomplete:hover {
     background: #aaa;
+}
+
+/* Validation warning indicator */
+.validation_warning {
+    margin-right: 5px;
+    position: relative;
+    top: -5px;
 }