pyflutter-app 0.3.12__tar.gz → 0.3.14__tar.gz

{pyflutter_app-0.3.12 → pyflutter_app-0.3.14}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: pyflutter_app
-Version: 0.3.12
+Version: 0.3.14
 Summary: Bibliotecas Python para conversão de documentos, interface e processamento de tabelas.
 Requires-Python: >=3.12
 Requires-Dist: opencv-python>=5.0.0.93

{pyflutter_app-0.3.12 → pyflutter_app-0.3.14}/cartas/__init__.py

@@ -9,6 +9,7 @@ from abc import ABC, abstractmethod
 from os import rename as rename_file
 from os import replace as replace_file
 from datetime import datetime
+import threading
 
 import pandas as pd
 
@@ -33,7 +34,7 @@ from table_stream import (
     load_file_hash,
 )
 
-from ocr_stream import HeaderOcr, BuilderConfigOcr, CreateRelatorioOcr
+# from ocr_stream import HeaderOcr, BuilderConfigOcr, CreateRelatorioOcr
 
 from whatsapp_files import (
     RowWhatsApp,
@@ -41,10 +42,11 @@ from whatsapp_files import (
     HeaderWhatsApp,
     BuilderTableWhatsApp,
     ControllerWhatsApp,
+    BuilderConfigWhatsApp,  # NOVO: base RFA única (substitui BuilderConfigOcr)
     move_path,
 )
 
-__version__ = "0.2"
+__version__ = "0.3"
 
 
 @dataclass
@@ -60,6 +62,111 @@ class ConfigTOI:
     work_dir: Directory
 
 
+# Mesmos nomes de arquivo gravados por ocr_stream. Se mudar lá, mude aqui.
+_OCR_FILE_IMAGE = "tabela_ocr_imagens.xlsx"
+_OCR_FILE_PDF = "tabela_ocr_pdf.xlsx"
+
+
+class BuilderConfigTOI(object):
+    """
+    Configuração de cartas SEM depender de ocr_stream.
+    Base única: <Documentos>/RFA (BuilderConfigWhatsApp.dir_base_root),
+    tabelas em <Documentos>/RFA/Tabelas (mesmos caminhos do ocr_stream).
+    """
+
+    _instance = None  # Atributo de classe para armazenar a instância singleton
+
+    def __new__(cls, *args, **kwargs):
+        if cls._instance is None:
+            cls._instance = super(BuilderConfigTOI, cls).__new__(cls)
+        return cls._instance
+
+    def __init__(self) -> None:
+
+        # Garante que __init__ não será executado mais de uma vez
+        if hasattr(self, "_initialized") and self._initialized:
+            return
+
+        super().__init__()
+        self._initialized: bool = True
+        self._builder_wp = BuilderConfigWhatsApp()
+        self._config = self._create()
+
+    # ---------------------------------------------------------- base RFA
+    @property
+    def dir_base_work(self) -> Directory:
+        return self._builder_wp.dir_base_root
+
+    @property
+    def dir_table(self) -> Directory:
+        """<Documentos>/RFA/Tabelas"""
+        return self._builder_wp.dir_table
+
+    # ---------------------------------------------------------- tabelas OCR (somente leitura)
+    @property
+    def file_table_ocr_image(self) -> File:
+        return self.dir_table.join_file(_OCR_FILE_IMAGE)
+
+    @property
+    def file_table_ocr_pdf(self) -> File:
+        return self.dir_table.join_file(_OCR_FILE_PDF)
+
+    # ---------------------------------------------------------- pastas TOI
+    @property
+    def dir_retorno_de_campo(self) -> Directory:
+        return self.dir_base_work.concat("Cartas-TOI", True).concat(
+            "Retorno-de-campo", True
+        )
+
+    @property
+    def dir_log_excel(self) -> Directory:
+        return self.dir_base_work.concat("Cartas-TOI", True).concat("Logs", True)
+
+    @property
+    def dir_relatorios(self) -> Directory:
+        return self.dir_base_work.concat("Cartas-TOI", True).concat(
+            "Relatorios-toi", True
+        )
+
+    # ---------------------------------------------------------- arquivos TOI
+    @property
+    def file_relatorio_toi(self) -> File:
+        return self.dir_table.join_file("Relatorio-tois.xlsx")
+
+    @property
+    def file_relatorio_forms(self) -> File:
+        return self.dir_table.join_file("cartas-toi-lancadas.xlsx")
+
+    @property
+    def file_master_forms(self) -> File:
+        return self.dir_table.join_file("master-forms-toi.xlsx")
+
+    @property
+    def file_table_toi(self) -> File:
+        return self.dir_table.join_file("tabela-entregas-tois.xlsx")
+
+    def _create(self) -> ConfigTOI:
+        return ConfigTOI(
+            work_dir=self.dir_base_work,
+            dir_base_toi=self.dir_retorno_de_campo,
+            file_relatorio_toi=self.file_relatorio_toi,
+            file_table_toi=self.file_table_toi,
+            file_cartas_lancadas=self.file_relatorio_forms,
+            dir_log_excel=self.dir_log_excel,
+            dir_relatorios=self.dir_relatorios,
+            file_master_forms=self.file_master_forms,
+        )
+
+    def reset_config(self) -> None:
+        self._config = None
+
+    def builder(self) -> ConfigTOI:
+        if self._config is None:
+            self._config = self._create()
+        return self._config
+
+
+"""
 class BuilderConfigTOI(object):
 
     _instance = None  # Atributo de classe para armazenar a instância singleton
@@ -136,6 +243,131 @@ class BuilderConfigTOI(object):
         if self._config is None:
             self._config = self._create()
         return self._config
+"""
+# ============================================================#
+# Leitura das tabelas OCR direto dos .xlsx (sem ocr_stream)
+# ============================================================#
+
+
+class HeaderOcr(StrEnum):
+    """Colunas das tabelas OCR (mesmos nomes gravados pelo ocr_stream)."""
+
+    ID = "ID"
+    HASH_FILE = HeaderMetaData.HASH_FILE.value
+    NUM_PAG = "PÁGINA"
+    NUM_LINHA = "LINHA"
+    TEXT = "TEXTO"
+
+
+_OCR_COLUMNS: list[str] = [h.value for h in HeaderOcr]
+_OCR_C_HASH = HeaderOcr.HASH_FILE.value
+
+
+class ReadTablesOcr(object):
+    """
+    Leitor SOMENTE-LEITURA de RFA/Tabelas/tabela_ocr_imagens.xlsx e
+    tabela_ocr_pdf.xlsx. Equivale ao que cartas usava de CreateRelatorioOcr,
+    mas sem importar ocr_stream/tesseract/cv2.
+
+    Cache em memória por arquivo, invalidado quando o .xlsx muda
+    (mtime + tamanho). Assim, se outro processo/PC rodar o OCR, a próxima
+    consulta já enxerga o dado novo.
+
+    As tabelas devolvidas por load_table_* são o objeto do cache: trate
+    como SOMENTE LEITURA (nunca chame merge()/set() nelas).
+    """
+
+    KIND_IMAGE = "imagem"
+    KIND_PDF = "pdf"
+
+    def __init__(self) -> None:
+        self._lock = threading.RLock()
+        self._cache: dict[str, tuple[tuple[int, int] | None, TableData[HeaderOcr]]] = {}
+
+    # ---------------------------------------------------------- infra
+    @staticmethod
+    def _file_of(kind: str) -> File:
+        cfg = BuilderConfigTOI()
+        if kind == ReadTablesOcr.KIND_IMAGE:
+            return cfg.file_table_ocr_image
+        return cfg.file_table_ocr_pdf
+
+    @staticmethod
+    def _stamp(f: File) -> tuple[int, int] | None:
+        try:
+            st = os.stat(f.absolute())
+        except OSError:
+            return None
+        return (st.st_mtime_ns, st.st_size)
+
+    @staticmethod
+    def _void() -> TableData[HeaderOcr]:
+        return TableData(pd.DataFrame(columns=_OCR_COLUMNS))
+
+    @staticmethod
+    def _read(f: File) -> TableData[HeaderOcr]:
+        # dtype=str + fillna(""): célula vazia vira "" (e não o texto "nan").
+        df = pd.read_excel(f.absolute(), dtype=str).fillna("")
+        for c in _OCR_COLUMNS:
+            if c not in df.columns:
+                df[c] = ""
+        return TableData.create_from_data(
+            df[_OCR_COLUMNS].astype(str).reset_index(drop=True)
+        )
+
+    def _load(self, kind: str) -> TableData[HeaderOcr]:
+        f = self._file_of(kind)
+        stamp = self._stamp(f)
+
+        with self._lock:
+            cached = self._cache.get(kind)
+            if cached is not None and cached[0] == stamp:
+                return cached[1]
+
+            if stamp is None:  # arquivo ainda não existe (OCR nunca rodou)
+                tb = self._void()
+            else:
+                try:
+                    print(f"Lendo tabela OCR ({kind}) ... {f.absolute()}")
+                    tb = self._read(f)
+                except Exception as e:
+                    print(f"[AVISO] falha ao ler {f.absolute()}: {e}")
+                    # mantém o cache anterior (se houver) e tenta de novo depois
+                    return cached[1] if cached is not None else self._void()
+
+            self._cache[kind] = (stamp, tb)
+            return tb
+
+    # ---------------------------------------------------------- READ
+    def load_table_image(self) -> TableData[HeaderOcr]:
+        return self._load(self.KIND_IMAGE)
+
+    def load_table_pdf(self) -> TableData[HeaderOcr]:
+        return self._load(self.KIND_PDF)
+
+    def create_from_hashs(self, hashes: Iterable[str]) -> TableData[HeaderOcr] | None:
+        """
+        Linhas OCR (imagem + pdf) das hashs informadas, SEM aplicar OCR.
+        None se nada for encontrado. O resultado é uma cópia (pode alterar).
+        """
+        wanted = {str(h) for h in hashes}
+        if not wanted:
+            return None
+
+        frames: list[pd.DataFrame] = []
+        for kind in (self.KIND_IMAGE, self.KIND_PDF):
+            df = self._load(kind).get_data()
+            if df.empty:
+                continue
+            sub = df[df[_OCR_C_HASH].isin(wanted)]
+            if not sub.empty:
+                frames.append(sub)
+
+        if not frames:
+            return None
+
+        final = pd.concat(frames, ignore_index=True)
+        return TableData.create_from_data(final[_OCR_COLUMNS].astype(str))
 
 
 # ============================================================#
@@ -296,7 +528,8 @@ class BuilderEntregaTOI(BuilderTOI):
 
     def __init__(self) -> None:
         super().__init__()
-        self.relatorio_ocr = CreateRelatorioOcr()
+        # self.relatorio_ocr = CreateRelatorioOcr()
+        self.relatorio_ocr = ReadTablesOcr()
         self.relatorio_wp = ControllerWhatsApp()
 
         self.default_cols_toi = ArrayList[HeaderEntregaTOI].from_list(
@@ -1257,7 +1490,7 @@ class ControllerTOI(object):
         return self.get_factory_toi().relatorio_wp
 
     @property
-    def relatorio_ocr(self) -> CreateRelatorioOcr:
+    def relatorio_ocr(self) -> ReadTablesOcr:
         return self.get_factory_toi().relatorio_ocr
 
     def get_factory_toi(self) -> BuilderEntregaTOI:
@@ -1375,11 +1608,9 @@ class ControllerTOI(object):
             return None
 
         # Filtrar
-        tb_cache_ocr: TableData[HeaderOcr] = self.relatorio_ocr.load_table_image()
-        tb_cache_ocr.merge(self.relatorio_ocr.load_table_pdf())
-
-        cache_ocr: TableData[HeaderOcr] | None = tb_cache_ocr.search_all(
-            HeaderOcr.HASH_FILE, hash_files.tolist()
+        # Filtrar: imagem + pdf, só as hashs pedidas (cópia, sem mexer no cache)
+        cache_ocr: TableData[HeaderOcr] | None = self.relatorio_ocr.create_from_hashs(
+            hash_files
         )
 
         if cache_ocr is None:
@@ -1762,6 +1993,7 @@ def load_files_toi_v2(
         print("[DEBUG]: load_files_toi_v2() lista de arquivos vazia!")
         return None
 
+    f: File
     for f in files:
         if (not f.is_image()) and (not f.is_pdf()):
             raise ValueError(
@@ -1836,7 +2068,7 @@ class RenameFilesTOI:
     nome de destino (acrescenta -1, -2...). modo_v2=False mantém o fluxo antigo.
     """
 
-    def __init__(self, files: Set[File], *, modo_v2: bool = False) -> None:
+    def __init__(self, files: Set[File], *, modo_v2: bool = True) -> None:
         self.config: ConfigTOI = BuilderConfigTOI().builder()
         self.files = files
         self.modo_v2: bool = modo_v2
@@ -1844,10 +2076,10 @@ class RenameFilesTOI:
 
         self.base_cartas: Directory = self.config.dir_base_toi
         self.error_uc_dir: Directory = self.base_cartas.concat(
-            "CARTAS_UC_NAO_IDENTIFICADAS", True
+            "UCS_NAO_IDENTIFICADAS", True
         )
         self.error_date_dir: Directory = self.base_cartas.concat(
-            "CARTAS_DATA_NAO_ENCONTRADA", True
+            "DATA_NAO_ENCONTRADA", True
         )
 
         self.map_files: HashMapDict[hashFile, File] = HashMapDict()
@@ -1874,6 +2106,27 @@ class RenameFilesTOI:
             BuilderTableWhatsApp().create_from_data(content_chat.to_dataframe()).rows()
         )
 
+        r: RowWhatsApp
+        for r in rows:
+            h = r.get(HeaderWhatsApp.hash_md5)
+            file_path: File = content_map.get_value(h)
+
+            dt: datetime = r.get_date_hour()
+            y = str(dt.year)
+            m = f"{dt.month:02d}"
+
+            # ano/ano-mes/arquivo
+            current_dir = self.error_uc_dir.concat(y).concat(f"{y}-{m}", True)
+            final_path: File = _resolver_colisao_arquivo(
+                current_dir.join_file(file_path.basename())
+            )
+
+            try:
+                move_path(file_path, final_path)
+            except Exception as e:
+                print(f"{__class__.__name__}(): {e}")
+
+        """
         r: RowWhatsApp
         for r in rows:
             h = r.get(HeaderWhatsApp.hash_md5)
@@ -1892,6 +2145,7 @@ class RenameFilesTOI:
                 move_path(file_path, final_path)
             except Exception as e:
                 print(f"{__class__.__name__}(): {e}")
+        """
 
     def _index_files(self) -> None:
         """Indexa os arquivos originais por hash."""
@@ -1963,11 +2217,13 @@ class RenameFilesTOI:
             return self.error_date_dir, f"{uc} {toi}"
 
         year, month, day = date
-        dest_dir = (
-            self.base_cartas.concat(year)
-            .concat(f"{year}-{month}")
-            .concat(f"{year}-{month}-{day}", True)
-        )
+        # dest_dir = (
+        #    self.base_cartas.concat(year)
+        #    .concat(f"{year}-{month}")
+        #    .concat(f"{year}-{month}-{day}", True)
+        # )
+
+        dest_dir = self.base_cartas.concat(year).concat(f"{year}-{month}", True)
         return dest_dir, f"{year} {month} {day} {uc} {toi}"
 
     def _destino_livre(self, dest: File, src: File) -> File:

{pyflutter_app-0.3.12 → pyflutter_app-0.3.14}/converter/config_app.py

@@ -1,6 +1,15 @@
 from __future__ import annotations
+from typing import Any
 from dataclasses import dataclass
-from table_stream import File, Directory, UserFileSystem, JsonConvert, HashMapDict
+from table_stream import (
+    File,
+    Directory,
+    UserFileSystem,
+    JsonConvert,
+    HashMapDict,
+    HashMap,
+    ArrayList,
+)
 from pyflutter_ui.theme import ThemeMode
 from pyflutter_ui.ui.core import ValueNotifier
 
@@ -13,29 +22,42 @@ class MapConfig:
     work_dir: Directory
     documents_dir: Directory
     theme_mode: ThemeMode
+    initial_dir_map: HashMap[str, Directory]
 
 
 class FactoryMapConfig(object):
 
     def __init__(self) -> None:
+        self._conf: MapConfig = self._create()
+
+    def _create(self) -> MapConfig:
+
         self._conf: MapConfig = MapConfig(
             initial_dir=UserFileSystem().get_user_downloads(),
             last_dir=UserFileSystem().get_user_downloads(),
             work_dir=UserFileSystem().get_user_downloads().concat("RFA", True),
             documents_dir=UserFileSystem().get_user_downloads().concat("RFA", True),
             theme_mode=ThemeMode.DARK,
+            initial_dir_map=HashMapDict(),
         )
+        return self._conf
+
+    def set_name_initial_dir(self, name: str, d: Directory):
+        self._conf.initial_dir_map.set_value(name, d)
 
     def create_default(self) -> MapConfig:
         return self._conf
 
-    def create_from_dict(self, h: HashMapDict[str, str]) -> MapConfig:
+    def create_from_dict(self, h: HashMapDict[str, Any]) -> MapConfig:
         if h.header().contains("initial_dir"):
             self._conf.initial_dir = Directory(h["initial_dir"])
+
         if h.header().contains("last_dir"):
             self._conf.last_dir = Directory(h["last_dir"])
+
         if h.header().contains("documents_dir"):
             self._conf.last_dir = Directory(h["documents_dir"])
+
         if h.header().contains("theme_mode"):
             if h["theme_mode"] == "dark":
                 self._conf.theme_mode = ThemeMode.DARK
@@ -43,6 +65,17 @@ class FactoryMapConfig(object):
                 self._conf.theme_mode = ThemeMode.LIGHT
             else:
                 self._conf.theme_mode = ThemeMode.SYSTEM
+
+        if h.header().contains("initial_dir_map"):
+            _map_initial_dict: dict[str, str] = h.get_value("initial_dir_map")
+            final_map = HashMapDict[str, Directory]()
+            keys_initial_dir = ArrayList.from_list(list(_map_initial_dict.keys()))
+
+            keys_initial_dir.for_each(
+                lambda k: final_map.set_value(k, Directory(_map_initial_dict[k]))
+            )
+            self._conf.initial_dir_map = final_map
+
         return self._conf
 
     def create_from_file(self, file_json: File) -> MapConfig:
@@ -71,18 +104,39 @@ class AppConfigNotifier(ValueNotifier[MapConfig]):
         self._value.documents_dir = d
         self.notify_listeners()
 
+    def set_initial_dir_named(self, name: str, d: Directory):
+        cfg = self._value
+        cfg.initial_dir_map[name] = d
+        self._value = cfg
+        self.notify_listeners()
+
     def get_file_config(self) -> File:
         return AppConfigNotifier.file_config
 
-    def get_dict_config(self) -> dict[str, str]:
-        final = dict()
-        final["initial_dir"] = self.value.initial_dir.absolute()
-        final["last_dir"] = self.value.last_dir.absolute()
-        final["work_dir"] = self.value.work_dir.absolute()
-        final["documents_dir"] = self.value.documents_dir.absolute()
-        final["theme_mode"] = self.value.theme_mode.value
+    def config_to_map(self) -> dict[str, Any]:
+        final = dict[str, Any]()
+        cfg = self.value
+
+        # Converter initial_dir_map para dict/json
+        json_initial_dir_map = dict[str, str]()
+        header_initial_dir = cfg.initial_dir_map.header()
+        header_initial_dir.for_each(
+            lambda h_name: json_initial_dir_map.setdefault(
+                h_name, cfg.initial_dir_map.get_value(h_name).absolute()
+            )
+        )
+
+        final["initial_dir_map"] = json_initial_dir_map
+        final["initial_dir"] = cfg.initial_dir.absolute()
+        final["last_dir"] = cfg.last_dir.absolute()
+        final["work_dir"] = cfg.work_dir.absolute()
+        final["documents_dir"] = cfg.documents_dir.absolute()
+        final["theme_mode"] = cfg.theme_mode.value
         return final
 
+    def get_dict_config(self) -> dict[str, Any]:
+        return self.config_to_map()
+
     def save_config(self):
         converter = JsonConvert.from_dict(self.get_dict_config())
         converter.data.to_file(self.get_file_config())

{pyflutter_app-0.3.12 → pyflutter_app-0.3.14}/converter/page_forms/controller_forms.py

@@ -71,6 +71,21 @@ class ControllerForms(ChangeNotifier):
     def get_config(self) -> AppConfigNotifier:
         return Provider.read(AppConfigNotifier)
 
+    def get_initial_dir(self) -> Directory:
+        cfg = self.get_config()
+        map_initial_dir = cfg.value.initial_dir_map
+
+        if map_initial_dir.header().contains("page_forms"):
+            return map_initial_dir.get_value("page_forms")
+        return cfg.value.initial_dir
+
+    def set_initial_dir(self, d: Directory):
+        k = "page_forms"
+        cfg = self.get_config().value
+
+        cfg.initial_dir_map[k] = d
+        self.get_config().value = cfg
+
     def show_info(self, i: str) -> None:
         if self.fn_show_info is not None:
             _ui(lambda: self.fn_show_info(i))

{pyflutter_app-0.3.12 → pyflutter_app-0.3.14}/converter/page_forms/view_forms.py

@@ -88,15 +88,18 @@ class _PageRespondsFormsState(StatelessWidget):
             self.show_info("Existe um lançamento em andamento.")
             return
 
-        conf = controller.get_config()
-        self.file_picker.initial_directory = conf.value.initial_dir.absolute()
+        # conf = controller.get_config()
+        conf_initial_dir = controller.get_initial_dir()
+
+        self.file_picker.initial_directory = conf_initial_dir.absolute()
 
         result: FilePickerResult | None = self.file_picker.pick_files()
         if result is None or not result.files:
             return
 
         if self.file_picker.initial_directory is not None:
-            conf.set_initial_dir(Directory(self.file_picker.initial_directory))
+            # conf.set_initial_dir(Directory(self.file_picker.initial_directory))
+            controller.set_initial_dir(Directory(self.file_picker.initial_directory))
 
         pf: PlatformFile = result.files[0]
         controller.set_selected_table_toi(File(pf.path))
@@ -118,6 +121,13 @@ class _PageRespondsFormsState(StatelessWidget):
             [
                 Row(
                     [
+                        Row(
+                            [
+                                ElevatedButton(
+                                    "<- Voltar", lambda: context.navigator.pop()
+                                ),
+                            ]
+                        ),
                         ElevatedButton(
                             "Gerar tabela (pasta)",
                             lambda: self.action_generate_table(controller),
@@ -148,11 +158,6 @@ class _PageRespondsFormsState(StatelessWidget):
                 Divider(),
                 Expanded(TableOrProgress(running=False, df=df)),
                 Divider(),
-                Row(
-                    [
-                        ElevatedButton("<- Voltar", lambda: context.navigator.pop()),
-                    ]
-                ),
             ]
         )
 

{pyflutter_app-0.3.12 → pyflutter_app-0.3.14}/converter/page_image/__init__.py

@@ -1,4 +1,6 @@
 from .common import FieldError, RenameRequest, ResultRename
+from .progress import ProgressReporter, ProgressState
+from .renderer import DocumentViewer, PageSource, PageSourceFactory
 from .model_image import ModelImage
 from .controller_image import ControllerImage
 from .view_image import PageImage

{pyflutter_app-0.3.12 → pyflutter_app-0.3.14}/converter/page_image/common.py

@@ -142,7 +142,10 @@ class ResultRename:
 
 
 # Extensões aceitas no REGISTRO em cache (o visualizador só abre imagens).
-REGISTER_EXTENSIONS: Final[frozenset[str]] = IMAGE_EXTENSIONS | {".pdf"}
+# REGISTER_EXTENSIONS: Final[frozenset[str]] = IMAGE_EXTENSIONS | {".pdf"}
+# Imagens + PDF: o visualizador e o registro em cache aceitam os mesmos tipos.
+DOCUMENT_EXTENSIONS: Final[frozenset[str]] = IMAGE_EXTENSIONS | {".pdf"}
+REGISTER_EXTENSIONS: Final[frozenset[str]] = DOCUMENT_EXTENSIONS  # alias antigo
 
 _RE_NAME_UC_TOI: Final = re.compile(r"(\d+)[\s_]+(\d+)")
 _RE_COLLISION: Final = re.compile(r"-\d{1,2}$")