feat: Update dependencies and normalize case in clinical motivation a…

…nd outcome

app/routers/frontend.py

@@ -14,7 +14,7 @@
     UserInfo,
 )
 from app.config import BIGQUERY_PROJECT
-from app.utils import read_timestamp
+from app.utils import read_timestamp, normalize_case
 
 router = APIRouter(prefix="/frontend", tags=["Frontend Application"])
 
@@ -217,8 +217,8 @@ async def get_patient_encounters(
             "subtype": result['subtipo'],
             "active_cids": [cid['descricao'] for cid in result['condicoes'] if cid['descricao']],
             "responsible": professional,
-            "clinical_motivation": result['motivo_atendimento'],
-            "clinical_outcome": result['desfecho_atendimento'],
+            "clinical_motivation": normalize_case(result['motivo_atendimento']),
+            "clinical_outcome": normalize_case(result['desfecho_atendimento']),
             "filter_tags": [unit_type],
         }
         encounters.append(encounter)

app/utils.py

@@ -1,8 +1,10 @@
 # -*- coding: utf-8 -*-
+from datetime import datetime, timedelta
+import re
 import jwt
 import hashlib
 import json
-from datetime import datetime, timedelta
+import nltk
 from typing import Literal
 from loguru import logger
 from passlib.context import CryptContext
@@ -11,6 +13,7 @@
 from app.models import User
 
 
+nltk.download('punkt_tab')
 pwd_context = CryptContext(schemes=["bcrypt"], deprecated="auto")
 
 
@@ -137,3 +140,26 @@ def read_timestamp(timestamp: int, output_format=Literal['date','datetime']) ->
         return value.strftime("%Y-%m-%d")
     else:
         raise ValueError("Invalid format")
+
+def normalize_case(text):
+    if not text:
+        return None
+
+    processed_lines = []
+    for line in text.splitlines():
+        pre_symbol = ''
+        if line.startswith('#'):
+            pre_symbol = '#'
+            line = line[1:]
+        if line.startswith('-'):
+            pre_symbol = '-'
+            line = line[1:]
+        line = line.strip()
+
+        sentences = nltk.tokenize.sent_tokenize(line)
+        normalized_sentences = [sentence.capitalize() for sentence in sentences]
+        normalized_text = pre_symbol + ' ' + ' '.join(normalized_sentences)
+
+        processed_lines.append(normalized_text)
+
+    return '\n'.join(processed_lines)

pyproject.toml

@@ -29,6 +29,7 @@ pyjwt = "^2.8.0"
 urllib3 = "2.0.7"
 idna = "3.7"
 basedosdados = "^2.0.0b16"
+nltk = "^3.9.1"
 
 
 [tool.poetry.group.dev.dependencies]