fix: include group on sinan listing

README.md

@@ -37,7 +37,7 @@ The easiest way to get data as a pandas DataFrame:
 from pysus import sinan, sinasc, sim, sih, sia, pni, ibge, cnes, ciha
 
 # Download SINAN Dengue data for 2024
-df = sinan(disease="deng", year=2024)
+df = sinan(disease="deng", year=2000)
 
 # Multiple years
 df = sinan(disease="deng", year=[2023, 2024])
@@ -81,7 +81,7 @@ async def main():
         df = pysus.read_parquet(paths, mode="union").df()
 ```
 
-### Using the TUI
+### Using the TUI (unstable/under testing)
 
 Launch the interactive text-based interface:
 

pysus/api/_impl/databases.py

@@ -267,6 +267,7 @@ def _query():
                     "name": r.path.split("/")[-1],
                     "path": r.path,
                     "dataset": r.dataset.name if r.dataset else None,
+                    "group": r.group.name if r.group else None,
                     "year": r.year,
                     "month": r.month,
                     "state": r.state,

pysus/api/ducklake/client.py

@@ -14,7 +14,42 @@
 from sqlalchemy.pool import StaticPool
 
 from .catalog import CatalogDataset, CatalogFile, DatasetGroup
-from .models import Dataset, File
+from .models import DuckDataset, File
+
+
+class CatalogDatasetAdapter:
+    def __init__(self, catalog_dataset: CatalogDataset, ducklake):
+        self.name = catalog_dataset.name
+        self.long_name = catalog_dataset.long_name or ""
+        self.description = catalog_dataset.description or ""
+        self.group_definitions: dict[str, str] = {}
+        self.ducklake = ducklake
+        self.client = ducklake
+
+    @property
+    def content(self):
+        return self.ducklake.query(dataset=self.name.upper())
+
+
+class DatasetGroupAdapter:
+    def __init__(self, dataset_group: DatasetGroup, dataset):
+        self.name = dataset_group.name
+        self.long_name = dataset_group.long_name or ""
+        self.description = dataset_group.description or ""
+        self.dataset = dataset
+
+    def __str__(self):
+        return self.name
+
+    @property
+    async def files(self):
+        return []
+
+    async def _fetch_files(self):
+        return []
+
+    async def search(self, **kwargs):
+        return []
 
 
 class DuckLakeCredentials(BaseModel):
@@ -66,7 +101,7 @@ def _catalog_url(self) -> str:
     def _is_authenticated(self) -> bool:
         return self.credentials is not None
 
-    async def datasets(self, **kwargs) -> list[Dataset]:
+    async def datasets(self, **kwargs) -> list[DuckDataset]:
         if not self._Session:
             await self.connect()
 
@@ -86,7 +121,7 @@ def _fetch():
                 return results
 
         records = await to_thread.run_sync(_fetch)
-        return [Dataset(record=rec, client=self) for rec in records]
+        return [DuckDataset(record=rec, client=self) for rec in records]
 
     async def login(
         self,
@@ -300,6 +335,13 @@ def _query():
 
         records = await to_thread.run_sync(_query)
         return [
-            File(path=r.path, record=r, dataset=r.dataset, group=r.group)
+            File(
+                path=r.path,
+                record=r,
+                dataset=CatalogDatasetAdapter(r.dataset, self),
+                group=(
+                    DatasetGroupAdapter(r.group, r.dataset) if r.group else None
+                ),
+            )
             for r in records
         ]

pysus/api/ducklake/models.py

@@ -2,6 +2,7 @@
 from collections.abc import Callable
 from datetime import datetime
 from pathlib import Path
+from typing import Any, Union
 
 import anyio
 from pydantic import Field
@@ -19,6 +20,8 @@
 class File(BaseRemoteFile):
     record: CatalogFile = Field(exclude=True)
     type: str = "remote"
+    dataset: Any
+    group: Any = None
 
     @property
     def basename(self) -> str:
@@ -51,6 +54,7 @@ async def _download(
     ) -> Path:
         if not output:
             output = CACHEPATH / self.name
+
         return await self.client._download_file(
             self,
             output,
@@ -72,41 +76,7 @@ def _calculate():
         return actual_hash == self.sha256
 
 
-class Group(BaseRemoteGroup):
-    record: DatasetGroup = Field(exclude=True)
-    dataset: "Dataset" = Field(exclude=True)
-
-    @property
-    def name(self) -> str:
-        return self.record.name
-
-    @property
-    def long_name(self) -> str:
-        return (
-            self.record.group_metadata.long_name
-            if self.record.group_metadata
-            else self.name
-        )
-
-    @property
-    def description(self) -> str:
-        if self.record.group_metadata:
-            return self.record.group_metadata.description
-        return ""
-
-    async def _fetch_files(self) -> list[BaseRemoteFile]:
-        return [
-            File(
-                path=f.path,
-                record=f,
-                group=self,
-                dataset=self.dataset,
-            )
-            for f in self.record.files
-        ]
-
-
-class Dataset(BaseRemoteDataset):
+class DuckDataset(BaseRemoteDataset):
     record: CatalogDataset = Field(exclude=True)
     client: BaseRemoteClient = Field(exclude=True)
 
@@ -133,14 +103,12 @@ def description(self) -> str:
             else ""
         )
 
-    async def _fetch_content(
-        self,
-    ) -> list[Group | File]:
-        items: list[Group | File] = []
+    async def _fetch_content(self) -> list[Union["DuckGroup", File]]:
+        items: list[Union["DuckGroup", File]] = []
 
         if self.record.groups:
             items.extend(
-                [Group(record=g, dataset=self) for g in self.record.groups],
+                [DuckGroup(record=g, dataset=self) for g in self.record.groups]
             )
 
         if self.record.files:
@@ -152,7 +120,42 @@ async def _fetch_content(
                         dataset=self,
                     )
                     for f in self.record.files
-                ],
+                ]
             )
 
         return items
+
+
+class DuckGroup(BaseRemoteGroup):
+    record: DatasetGroup = Field(exclude=True)
+    dataset: DuckDataset = Field(exclude=True)
+
+    @property
+    def name(self) -> str:
+        return self.record.name
+
+    @property
+    def long_name(self) -> str:
+        return (
+            self.record.group_metadata.long_name
+            if self.record.group_metadata
+            else self.name
+        )
+
+    @property
+    def description(self) -> str:
+        if self.record.group_metadata:
+            return self.record.group_metadata.description
+        return ""
+
+    async def _fetch_files(self) -> list[BaseRemoteFile]:
+        files: list[BaseRemoteFile] = [
+            File(
+                path=f.path,
+                record=f,
+                group=self,
+                dataset=self.dataset,
+            )
+            for f in self.record.files
+        ]
+        return files

pysus/api/ftp/databases.py

@@ -403,12 +403,55 @@ class SINAN(Dataset):
     ]
 
     group_definitions: dict[str, str] = {
-        "DENG": "Dengue",
-        "ZIKA": "Zika Vírus",
+        "ACBI": "Acidente de trabalho com material biológico",
+        "ACGR": "Acidente de trabalho",
+        "ANIM": "Acidente por Animais Peçonhentos",
+        "ANTR": "Atendimento Antirrabico",
+        "BOTU": "Botulismo",
+        "CANC": "Cancêr relacionado ao trabalho",
+        "CHAG": "Doença de Chagas Aguda",
         "CHIK": "Febre de Chikungunya",
+        "COLE": "Cólera",
+        "COQU": "Coqueluche",
+        "DENG": "Dengue",
+        "DERM": "Dermatoses ocupacionais",
+        "DIFT": "Difteria",
+        "ESQU": "Esquistossomose",
+        "EXAN": "Doença exantemáticas",
+        "FMAC": "Febre Maculosa",
+        "FTIF": "Febre Tifóide",
         "HANS": "Hanseníase",
+        "HANT": "Hantavirose",
+        "HEPA": "Hepatites Virais",
+        "IEXO": "Intoxicação Exógena",
+        "INFL": "Influenza Pandêmica",
+        "LEIV": "Leishmaniose Visceral",
+        "LEPT": "Leptospirose",
+        "LERD": "LER/Dort",
+        "LTAN": "Leishmaniose Tegumentar Americana",
+        "MALA": "Malária",
+        "MENI": "Meningite",
+        "MENT": "Transtornos mentais relacionados ao trabalho",
+        "NTRA": "Notificação de Tracoma",
+        "PAIR": "Perda auditiva por ruído relacionado ao trabalho",
+        "PEST": "Peste",
+        "PFAN": "Paralisia Flácida Aguda",
+        "PNEU": "Pneumoconioses realacionadas ao trabalho",
+        "RAIV": "Raiva",
+        "SDTA": "Surto Doenças Transmitidas por Alimentos",
+        "SIFA": "Sífilis Adquirida",
+        "SIFC": "Sífilis Congênita",
+        "SIFG": "Sífilis em Gestante",
+        "SRC": "Síndrome da Rubéola Congênia",
+        "TETA": "Tétano Acidental",
+        "TETN": "Tétano Neonatal",
+        "TOXC": "Toxoplasmose Congênita",
+        "TOXG": "Toxoplasmose Gestacional",
+        "TRAC": "Inquérito de Tracoma",
         "TUBE": "Tuberculose",
-        "ANIM": "Acidente por Animais Peçonhentos",
+        "VARC": "Varicela",
+        "VIOL": "Violência doméstica, sexual e/ou outras violências",
+        "ZIKA": "Zika Vírus",
     }
 
     @property

pysus/api/models.py

@@ -327,6 +327,7 @@ async def search(self, **kwargs) -> list[BaseRemoteFile]:
 
 class BaseRemoteDataset(BaseRemoteObject, SearchableMixin, ABC):
     client: BaseRemoteClient = Field(exclude=True)
+    group_definitions: dict[str, str] = {}
     _content: Sequence[BaseRemoteGroup | BaseRemoteFile] | None = PrivateAttr(
         default=None
     )