pearmut 0.2.2__py3-none-any.whl → 0.2.4__py3-none-any.whl

pearmut/app.py

@@ -9,7 +9,13 @@ from fastapi.staticfiles import StaticFiles
 from pydantic import BaseModel
 
 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
+from .utils import (
+    ROOT,
+    check_validation_threshold,
+    load_progress_data,
+    save_db_payload,
+    save_progress_data,
+)
 
 os.makedirs(f"{ROOT}/data/outputs", exist_ok=True)
 
@@ -141,16 +147,19 @@ class DashboardDataRequest(BaseModel):
 async def _dashboard_data(request: DashboardDataRequest):
     campaign_id = request.campaign_id
 
-    is_privileged = (request.token == tasks_data[campaign_id]["token"])
-
     if campaign_id not in progress_data:
         return JSONResponse(content={"error": "Unknown campaign ID"}, status_code=400)
+    
+    is_privileged = (request.token == tasks_data[campaign_id]["token"])
 
     progress_new = {}
     assignment = tasks_data[campaign_id]["info"]["assignment"]
     if assignment not in ["task-based", "single-stream"]:
         return JSONResponse(content={"error": "Unsupported campaign assignment type"}, status_code=400)
 
+    # Get threshold info for the campaign
+    validation_threshold = tasks_data[campaign_id]["info"].get("validation_threshold")
+
     for user_id, user_val in progress_data[campaign_id].items():
         # shallow copy
         entry = dict(user_val)
@@ -159,6 +168,13 @@ async def _dashboard_data(request: DashboardDataRequest):
             for v in list(entry.get("validations", {}).values())
         ]
         
+        # Add threshold pass/fail status (only when user is complete)
+        if all(entry["progress"]):
+            entry["threshold_passed"] = check_validation_threshold(
+                tasks_data, progress_data, campaign_id, user_id
+            )
+        else:
+            entry["threshold_passed"] = None
 
         if not is_privileged:
             entry["token_correct"] = None
@@ -169,7 +185,8 @@ async def _dashboard_data(request: DashboardDataRequest):
     return JSONResponse(
         content={
             "status": "ok",
-            "data": progress_new
+            "data": progress_new,
+            "validation_threshold": validation_threshold
         },
         status_code=200
     )

pearmut/assignment.py

@@ -3,18 +3,23 @@ from typing import Any
 
 from fastapi.responses import JSONResponse
 
-from .utils import get_db_log_item
+from .utils import (
+    RESET_MARKER,
+    check_validation_threshold,
+    get_db_log_item,
+    save_db_payload,
+)
 
 
 def _completed_response(
+    tasks_data: dict,
     progress_data: dict,
     campaign_id: str,
     user_id: str,
 ) -> JSONResponse:
     """Build a completed response with progress, time, and token."""
     user_progress = progress_data[campaign_id][user_id]
-    # TODO: add check for data quality
-    is_ok = True
+    is_ok = check_validation_threshold(tasks_data, progress_data, campaign_id, user_id)
     return JSONResponse(
         content={
             "status": "completed",
@@ -161,7 +166,7 @@ def get_next_item_taskbased(
     """
     user_progress = progress_data[campaign_id][user_id]
     if all(user_progress["progress"]):
-        return _completed_response(progress_data, campaign_id, user_id)
+        return _completed_response(data_all, progress_data, campaign_id, user_id)
 
     # find first incomplete item
     item_i = min([i for i, v in enumerate(user_progress["progress"]) if not v])
@@ -208,7 +213,7 @@ def get_next_item_singlestream(
     progress = user_progress["progress"]
 
     if all(progress):
-        return _completed_response(progress_data, campaign_id, user_id)
+        return _completed_response(data_all, progress_data, campaign_id, user_id)
 
     # find a random incomplete item
     incomplete_indices = [i for i, v in enumerate(progress) if not v]
@@ -261,20 +266,33 @@ def reset_task(
 ) -> JSONResponse:
     """
     Reset the task progress for the user in the specified campaign.
+    Saves a reset marker to mask existing annotations.
     """
     assignment = tasks_data[campaign_id]["info"]["assignment"]
     if assignment == "task-based":
-        progress_data[campaign_id][user_id]["progress"] = (
-            [False]*len(tasks_data[campaign_id]["data"][user_id])
-        )
+        # Save reset marker for this user to mask existing annotations
+        num_items = len(tasks_data[campaign_id]["data"][user_id])
+        for item_i in range(num_items):
+            save_db_payload(campaign_id, {
+                "user_id": user_id,
+                "item_i": item_i,
+                "annotations": RESET_MARKER
+            })
+        progress_data[campaign_id][user_id]["progress"] = [False] * num_items
         _reset_user_time(progress_data, campaign_id, user_id)
         return JSONResponse(content={"status": "ok"}, status_code=200)
     elif assignment == "single-stream":
+        # Save reset markers for all items (shared pool)
+        num_items = len(tasks_data[campaign_id]["data"])
+        for item_i in range(num_items):
+            save_db_payload(campaign_id, {
+                "user_id": None,
+                "item_i": item_i,
+                "annotations": RESET_MARKER
+            })
         # for single-stream reset all progress
         for uid in progress_data[campaign_id]:
-            progress_data[campaign_id][uid]["progress"] = (
-                [False]*len(tasks_data[campaign_id]["data"])
-            )
+            progress_data[campaign_id][uid]["progress"] = [False] * num_items
         _reset_user_time(progress_data, campaign_id, user_id)
         return JSONResponse(content={"status": "ok"}, status_code=200)
     else:

pearmut/cli.py

@@ -10,7 +10,7 @@ import urllib.parse
 
 import psutil
 
-from .utils import ROOT, load_progress_data
+from .utils import ROOT, load_progress_data, save_progress_data
 
 os.makedirs(f"{ROOT}/data/tasks", exist_ok=True)
 load_progress_data(warn=None)
@@ -50,41 +50,25 @@ def _run(args_unknown):
     )
 
 
-def _add_campaign(args_unknown):
+def _add_single_campaign(data_file, overwrite, server):
     """
-    Add a new campaign from a JSON data file.
+    Add a single campaign from a JSON data file.
     """
     import random
 
     import wonderwords
 
-    args = argparse.ArgumentParser()
-    args.add_argument(
-        'data_file', type=str,
-        help='Path to the campaign data file'
-    )
-    args.add_argument(
-        "-o", "--overwrite", action="store_true",
-        help="Overwrite existing campaign if it exists"
-    )
-    args.add_argument(
-        "--server", default="http://localhost:8001",
-        help="Prefix server URL for protocol links"
-    )
-    args = args.parse_args(args_unknown)
-
-    with open(args.data_file, 'r') as f:
+    with open(data_file, 'r') as f:
         campaign_data = json.load(f)
 
     with open(f"{ROOT}/data/progress.json", "r") as f:
         progress_data = json.load(f)
 
-    if campaign_data['campaign_id'] in progress_data and not args.overwrite:
-        print(
-            f"Campaign {campaign_data['campaign_id']} already exists.",
+    if campaign_data['campaign_id'] in progress_data and not overwrite:
+        raise ValueError(
+            f"Campaign {campaign_data['campaign_id']} already exists.\n"
             "Use -o to overwrite."
         )
-        exit(1)
 
     if "info" not in campaign_data:
         raise ValueError("Campaign data must contain 'info' field.")
@@ -99,6 +83,11 @@ def _add_campaign(args_unknown):
     # use random words for identifying users
     rng = random.Random(campaign_data["campaign_id"])
     rword = wonderwords.RandomWord(rng=rng)
+
+    # Parse users specification from info
+    users_spec = campaign_data["info"].get("users")
+    user_tokens = {}  # user_id -> {"pass": ..., "fail": ...}
+
     if assignment == "task-based":
         tasks = campaign_data["data"]
         if not isinstance(tasks, list):
@@ -110,29 +99,58 @@ def _add_campaign(args_unknown):
         num_users = len(tasks)
     elif assignment == "single-stream":
         tasks = campaign_data["data"]
-        if "num_users" not in campaign_data["info"]:
+        if users_spec is None:
             raise ValueError(
-                "Single-stream campaigns must specify 'num_users' in info.")
+                "Single-stream campaigns must specify 'users' in info.")
         if not isinstance(campaign_data["data"], list):
             raise ValueError(
                 "Single-stream campaign 'data' must be a list of items.")
-        num_users = campaign_data["info"]["num_users"]
+        if isinstance(users_spec, int):
+            num_users = users_spec
+        elif isinstance(users_spec, list):
+            num_users = len(users_spec)
+        else:
+            raise ValueError("'users' must be an integer or a list.")
     elif assignment == "dynamic":
         raise NotImplementedError(
             "Dynamic campaign assignment is not yet implemented.")
     else:
         raise ValueError(f"Unknown campaign assignment type: {assignment}")
 
-    user_ids = []
-    while len(user_ids) < num_users:
-        # generate random user IDs
-        new_id = f"{rword.random_words(amount=1, include_parts_of_speech=['adjective'])[0]}-{rword.random_words(amount=1, include_parts_of_speech=['noun'])[0]}"
-        if new_id not in user_ids:
-            user_ids.append(new_id)
-    user_ids = [
-        f"{user_id}-{rng.randint(0, 999):03d}"
-        for user_id in user_ids
-    ]
+    # Generate or parse user IDs based on users specification
+    if users_spec is None or isinstance(users_spec, int):
+        # Generate random user IDs
+        user_ids = []
+        while len(user_ids) < num_users:
+            new_id = f"{rword.random_words(amount=1, include_parts_of_speech=['adjective'])[0]}-{rword.random_words(amount=1, include_parts_of_speech=['noun'])[0]}"
+            if new_id not in user_ids:
+                user_ids.append(new_id)
+        user_ids = [
+            f"{user_id}-{rng.randint(0, 999):03d}"
+            for user_id in user_ids
+        ]
+    elif isinstance(users_spec, list):
+        if len(users_spec) != num_users:
+            raise ValueError(
+                f"Number of users ({len(users_spec)}) must match expected count ({num_users}).")
+        if all(isinstance(u, str) for u in users_spec):
+            # List of string IDs
+            user_ids = users_spec
+        elif all(isinstance(u, dict) for u in users_spec):
+            # List of dicts with user_id, token_pass, token_fail
+            user_ids = []
+            for u in users_spec:
+                if "user_id" not in u:
+                    raise ValueError("Each user dict must contain 'user_id'.")
+                user_ids.append(u["user_id"])
+                user_tokens[u["user_id"]] = {
+                    "pass": u.get("token_pass"),
+                    "fail": u.get("token_fail"),
+                }
+        else:
+            raise ValueError("'users' list must contain all strings or all dicts.")
+    else:
+        raise ValueError("'users' must be an integer or a list.")
 
     # For task-based, data is a dict mapping user_id -> tasks
     # For single-stream, data is a flat list (shared among all users)
@@ -150,6 +168,13 @@ def _add_campaign(args_unknown):
             hashlib.sha256(random.randbytes(16)).hexdigest()[:10]
         )
 
+    def get_token(user_id, token_type):
+        """Get user token or generate a random one."""
+        token = user_tokens.get(user_id, {}).get(token_type)
+        if token is not None:
+            return token
+        return hashlib.sha256(random.randbytes(16)).hexdigest()[:10]
+
     user_progress = {
         user_id: {
             # TODO: progress tracking could be based on the assignment type
@@ -166,12 +191,44 @@ def _add_campaign(args_unknown):
                 f"?campaign_id={urllib.parse.quote_plus(campaign_data['campaign_id'])}"
                 f"&user_id={user_id}"
             ),
-            "token_correct": hashlib.sha256(random.randbytes(16)).hexdigest()[:10],
-            "token_incorrect": hashlib.sha256(random.randbytes(16)).hexdigest()[:10],
+            "token_correct": get_token(user_id, "pass"),
+            "token_incorrect": get_token(user_id, "fail"),
         }
         for user_id in user_ids
     }
 
+    # Handle assets symlink if specified
+    if "assets" in campaign_data["info"]:
+        assets_real_path = campaign_data["info"]["assets"]
+        
+        # Resolve relative paths from the caller's current working directory
+        assets_real_path = os.path.abspath(assets_real_path)
+
+        if not os.path.isdir(assets_real_path):
+            raise ValueError(f"Assets path '{assets_real_path}' must be an existing directory.")
+
+        static_dir = f"{os.path.dirname(os.path.abspath(__file__))}/static"
+        dir_name = assets_real_path.split(os.sep)[-1]
+
+        if not os.path.isdir(static_dir):
+            raise ValueError(
+                f"Static directory '{static_dir}' does not exist. "
+                "Please build the frontend first."
+            )
+        symlink_path = f"{static_dir}/assets/{dir_name}"
+
+        # Remove existing symlink if present and we are overriding
+        if os.path.exists(symlink_path):
+            if overwrite:
+                os.remove(symlink_path)
+            else:
+                raise ValueError(f"Assets symlink '{symlink_path}' already exists.")
+
+        os.symlink(assets_real_path, symlink_path, target_is_directory=True)
+        print(f"Assets symlinked: {symlink_path} -> {assets_real_path}")
+
+
+    # commit to transaction
     with open(f"{ROOT}/data/tasks/{campaign_data['campaign_id']}.json", "w") as f:
         json.dump(campaign_data, f, indent=2, ensure_ascii=False)
 
@@ -180,15 +237,44 @@ def _add_campaign(args_unknown):
     with open(f"{ROOT}/data/progress.json", "w") as f:
         json.dump(progress_data, f, indent=2, ensure_ascii=False)
 
+
     print(
-        f"{args.server}/dashboard.html"
+        "🎛️ ",
+        f"{server}/dashboard.html"
         f"?campaign_id={urllib.parse.quote_plus(campaign_data['campaign_id'])}"
         f"&token={campaign_data['token']}"
     )
-    print("-"*10)
     for user_id, user_val in user_progress.items():
         # point to the protocol URL
-        print(f"{args.server}/{user_val["url"]}")
+        print(f'{server}/{user_val["url"]}')
+    print()
+
+
+def _add_campaign(args_unknown):
+    """
+    Add campaigns from one or more JSON data files.
+    """
+    args = argparse.ArgumentParser()
+    args.add_argument(
+        'data_files', type=str, nargs='+',
+        help='One or more paths to campaign data files'
+    )
+    args.add_argument(
+        "-o", "--overwrite", action="store_true",
+        help="Overwrite existing campaign if it exists"
+    )
+    args.add_argument(
+        "--server", default="http://localhost:8001",
+        help="Prefix server URL for protocol links"
+    )
+    args = args.parse_args(args_unknown)
+
+    for data_file in args.data_files:
+        try:
+            _add_single_campaign(data_file, args.overwrite, args.server)
+        except Exception as e:
+            print(f"Error processing {data_file}: {e}")
+            exit(1)
 
 
 def main():
@@ -213,14 +299,47 @@ def main():
     elif args.command == 'purge':
         import shutil
 
-        confirm = input(
-            "Are you sure you want to purge all campaign data? This action cannot be undone. [y/n] "
+        # Parse optional campaign name
+        purge_args = argparse.ArgumentParser()
+        purge_args.add_argument(
+            'campaign', type=str, nargs='?', default=None,
+            help='Optional campaign name to purge (purges all if not specified)'
         )
-        if confirm.lower() == 'y':
-            shutil.rmtree(f"{ROOT}/data/tasks", ignore_errors=True)
-            shutil.rmtree(f"{ROOT}/data/outputs", ignore_errors=True)
-            if os.path.exists(f"{ROOT}/data/progress.json"):
-                os.remove(f"{ROOT}/data/progress.json")
-            print("All campaign data purged.")
+        purge_args = purge_args.parse_args(args_unknown)
+
+        if purge_args.campaign is not None:
+            # Purge specific campaign
+            campaign_id = purge_args.campaign
+            confirm = input(
+                f"Are you sure you want to purge campaign '{campaign_id}'? This action cannot be undone. [y/n] "
+            )
+            if confirm.lower() == 'y':
+                # Remove task file
+                task_file = f"{ROOT}/data/tasks/{campaign_id}.json"
+                if os.path.exists(task_file):
+                    os.remove(task_file)
+                # Remove output file
+                output_file = f"{ROOT}/data/outputs/{campaign_id}.jsonl"
+                if os.path.exists(output_file):
+                    os.remove(output_file)
+                # Remove from progress data
+                progress_data = load_progress_data()
+                if campaign_id in progress_data:
+                    del progress_data[campaign_id]
+                    save_progress_data(progress_data)
+                print(f"Campaign '{campaign_id}' purged.")
+            else:
+                print("Cancelled.")
         else:
-            print("Cancelled.")
+            # Purge all campaigns
+            confirm = input(
+                "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)
+                shutil.rmtree(f"{ROOT}/data/outputs", ignore_errors=True)
+                if os.path.exists(f"{ROOT}/data/progress.json"):
+                    os.remove(f"{ROOT}/data/progress.json")
+                print("All campaign data purged.")
+            else:
+                print("Cancelled.")

pearmut/static/assets/style.css

@@ -232,4 +232,8 @@ input[type="button"].error_delete:hover {
     margin-right: 5px;
     position: relative;
     top: -5px;
+}
+
+.char_missing {
+    font-family: monospace;
 }