documente_shared 0.1.202__tar.gz → 0.1.203b0__tar.gz

{documente_shared-0.1.202 → documente_shared-0.1.203b0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: documente_shared
-Version: 0.1.202
+Version: 0.1.203b0
 Summary: Shared utilities for LlamitAI projects
 Author-email: Tech <tech@llamitai.com>
 License: MIT

{documente_shared-0.1.202 → documente_shared-0.1.203b0}/documente_shared/domain/entities/layout.py

@@ -75,3 +75,11 @@ class PageRange(BaseModel):
     end: Optional[int] = None
 
     model_config = ConfigDict(extra="ignore")
+
+    @property
+    def label(self) -> str:
+        # Espeja PageRange.label de las lambdas, que lo usan para nombrar el resultado en S3:
+        # start ausente es 1, end ausente es "end".
+        start_page = self.start if self.start is not None else 1
+        end_page = self.end if self.end is not None else "end"
+        return f"{start_page}-{end_page}"

{documente_shared-0.1.202 → documente_shared-0.1.203b0}/documente_shared/domain/entities/workspace_document.py

@@ -27,7 +27,6 @@ class WorkspaceDocument(BaseModel):
     processing_time: Decimal | None = Field(default=None)
     metadata: dict | None = Field(default_factory=dict)
     extraction: dict | None = Field(default_factory=dict)
-    mapped_output: dict | None = Field(default=None)
     uploaded_at: datetime | None = Field(default=None)
     created_at: datetime | None = Field(default=None)
     updated_at: datetime | None = Field(default=None)
@@ -37,7 +36,7 @@ class WorkspaceDocument(BaseModel):
 
     @property
     def to_persist_dict(self) -> dict:
-        data = {
+        return {
             "tenant_id": self.tenant_id,
             "workspace_id": str(self.workspace_id),
             "document_type_id": optional_str(self.document_type_id),
@@ -56,9 +55,6 @@ class WorkspaceDocument(BaseModel):
             "metadata": self.metadata or {},
             "extraction": self.extraction or {},
         }
-        if self.mapped_output is not None:
-            data["mapped_output"] = self.mapped_output
-        return data
 
     @property
     def to_dict(self) -> dict:
@@ -78,7 +74,6 @@ class WorkspaceDocument(BaseModel):
             "processing_time": optional_str(self.processing_time),
             "metadata": self.metadata,
             "extraction": self.extraction,
-            "mapped_output": self.mapped_output,
             "uploaded_at": optional_datetime_str(self.uploaded_at),
             "started_at": optional_datetime_str(self.started_at),
             "completed_at": optional_datetime_str(self.completed_at),
@@ -106,7 +101,6 @@ class WorkspaceDocument(BaseModel):
             ),
             metadata=data.get("metadata", {}),
             extraction=data.get("extraction", {}),
-            mapped_output=data.get("mapped_output", {}),
             uploaded_at=get_datetime_from_data(input_datetime=data.get("uploaded_at")),
             created_at=get_datetime_from_data(input_datetime=data.get("created_at")),
             updated_at=get_datetime_from_data(input_datetime=data.get("updated_at")),

documente_shared-0.1.203b0/documente_shared/domain/helpers/values.py

@@ -0,0 +1,13 @@
+from datetime import datetime
+
+
+def optional_str(input_value: object | None = None) -> str | None:
+    if input_value is None:
+        return None
+    return str(input_value)
+
+
+def optional_datetime_str(input_datetime: datetime | None = None) -> str | None:
+    if input_datetime is None:
+        return None
+    return input_datetime.isoformat()

documente_shared-0.1.203b0/documente_shared/infrastructure/lambda_job_results.py

@@ -0,0 +1,39 @@
+import time
+
+from documente_shared.infrastructure.s3_bucket import S3Bucket
+
+DEFAULT_JOB_RESULT_TIMEOUT = 960
+DEFAULT_JOB_RESULT_POLL_INTERVAL = 5
+
+
+def build_job_result_key(job_id: str, step_name: str) -> str:
+    # Contrato de S3JobResultStore en las lambdas: el mismo output_uri que devuelve la invocacion
+    # sincronica, construido aca para que la asincronica no dependa de una respuesta.
+    return f"jobs/{job_id}/{step_name}.json"
+
+
+def discard_previous_job_result(s3_bucket: S3Bucket, job_result_key: str) -> None:
+    # Sin esto la espera puede leer el resultado de una corrida anterior y devolverlo como propio.
+    # Lo que se borra es un artefacto derivado que la lambda reescribe en cada corrida, incluso en
+    # cache hit: su cache real no vive en este archivo.
+    s3_bucket.delete(file_key=job_result_key)
+
+
+def wait_for_job_result(
+    s3_bucket: S3Bucket,
+    job_result_key: str,
+    timeout_seconds: int = DEFAULT_JOB_RESULT_TIMEOUT,
+    poll_interval_seconds: float = DEFAULT_JOB_RESULT_POLL_INTERVAL,
+) -> dict:
+    deadline = time.monotonic() + timeout_seconds
+    while True:
+        job_result = s3_bucket.get_json(file_key=job_result_key)
+        if job_result is not None:
+            return job_result
+        if time.monotonic() >= deadline:
+            timeout_message = (
+                f"Lambda job result not found after {timeout_seconds}s: "
+                f"s3://{s3_bucket.bucket_name}/{job_result_key}"
+            )
+            raise TimeoutError(timeout_message)
+        time.sleep(poll_interval_seconds)

documente_shared-0.1.203b0/documente_shared/infrastructure/lambdas.py

@@ -0,0 +1,69 @@
+import json
+from functools import cache
+
+import boto3
+from botocore.config import Config
+
+# Synchronous invocations travel through a PrivateLink interface endpoint, whose idle timeout is a
+# hard, non configurable 350s. A synchronous invoke leaves the flow completely idle while the
+# function runs, so past that point the flow is silently dropped and the response can never arrive.
+# Waiting any longer than the endpoint allows only delays a failure that already happened.
+DEFAULT_LAMBDA_READ_TIMEOUT = 350
+
+# An asynchronous invocation only enqueues the event, so the call returns in milliseconds no matter
+# how long the function then runs.
+DEFAULT_LAMBDA_ENQUEUE_TIMEOUT = 60
+
+
+@cache
+def _get_lambda_client(read_timeout: int):
+    # No retries: the read timeout is shorter than the function timeout, so a read timeout means the
+    # invocation is still running on the other side. Retrying it would start a second execution of a
+    # function that is not idempotent.
+    lambda_config = Config(
+        read_timeout=read_timeout,
+        connect_timeout=30,
+        tcp_keepalive=True,
+        retries={"max_attempts": 0, "mode": "standard"},
+    )
+    return boto3.client("lambda", config=lambda_config)
+
+
+def invoke_lambda(
+    function_name: str,
+    payload: dict,
+    read_timeout: int = DEFAULT_LAMBDA_READ_TIMEOUT,
+) -> dict | list | None:
+    client = _get_lambda_client(read_timeout)
+
+    response = client.invoke(
+        FunctionName=function_name,
+        InvocationType="RequestResponse",
+        Payload=json.dumps(payload),
+    )
+
+    return json.loads(response["Payload"].read().decode("utf-8"))
+
+
+def invoke_lambda_async(
+    function_name: str,
+    payload: dict,
+    read_timeout: int = DEFAULT_LAMBDA_ENQUEUE_TIMEOUT,
+) -> int:
+    # There is no response payload to wait for, so the caller never holds a connection open
+    # while the function runs. The result travels out of band: the function writes it to
+    # its own deterministic output location and the caller reads it from there.
+    #
+    # Lambda retries a failed asynchronous invocation by itself (MaximumRetryAttempts defaults to 2
+    # on the function's event invoke config) and silently drops events it cannot deliver. Both are
+    # function side settings, invisible from here, so anything invoked this way has to tolerate
+    # running more than once for the same payload.
+    client = _get_lambda_client(read_timeout)
+
+    response = client.invoke(
+        FunctionName=function_name,
+        InvocationType="Event",
+        Payload=json.dumps(payload),
+    )
+
+    return response["StatusCode"]

{documente_shared-0.1.202 → documente_shared-0.1.203b0}/documente_shared/infrastructure/s3_bucket.py

@@ -1,12 +1,18 @@
-import boto3
+import json
 
 from dataclasses import dataclass
 from typing import Optional
 
+import boto3
+from botocore.exceptions import ClientError
+
 from documente_shared.domain.entities.document import remove_slash_from_path
 from documente_shared.application.retry_utils import retry_on_size_integrity
 
 
+MISSING_OBJECT_ERROR_CODES = ("NoSuchKey", "404")
+
+
 def remove_none_values(data: dict) -> dict:  # noqa: WPS110
     return {key: value for key, value in data.items() if value is not None}  # noqa: WPS110
 
@@ -39,6 +45,18 @@ class S3Bucket(object):
             return None
         return file_context["Body"] if "Body" in file_context else None
 
+    def get_json(self, file_key: str) -> Optional[dict]:
+        # Sin el retry de get(): aca la ausencia del objeto es una respuesta valida y no algo que
+        # convenga reintentar, asi que se puede usar para preguntar si un resultado ya esta.
+        cleaned_file_key = remove_slash_from_path(file_key)
+        try:
+            file_context = self._resource.Object(self.bucket_name, cleaned_file_key).get()
+        except ClientError as client_error:
+            if client_error.response["Error"]["Code"] in MISSING_OBJECT_ERROR_CODES:
+                return None
+            raise
+        return json.loads(file_context["Body"].read().decode("utf-8"))
+
     def upload(self, file_key: str, file_content, content_type: Optional[str] = None):
         cleaned_file_key = remove_slash_from_path(file_key)
         optional_params = {"ContentType": content_type}

{documente_shared-0.1.202 → documente_shared-0.1.203b0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "documente_shared"
-version = "0.1.202"
+version = "0.1.203b"
 description = "Shared utilities for LlamitAI projects"
 authors = [{ name = "Tech", email = "tech@llamitai.com" }]
 license = { text = "MIT" }

{documente_shared-0.1.202 → documente_shared-0.1.203b0}/uv.lock

@@ -154,7 +154,7 @@ wheels = [
 
 [[package]]
 name = "documente-shared"
-version = "0.1.202"
+version = "0.1.203b0"
 source = { editable = "." }
 dependencies = [
     { name = "boto3" },
@@ -200,7 +200,7 @@ name = "exceptiongroup"
 version = "1.3.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "typing-extensions" },
+    { name = "typing-extensions", marker = "python_full_version < '3.11'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/50/79/66800aadf48771f6b62f7eb014e352e5d06856655206165d775e675a02c9/exceptiongroup-1.3.1.tar.gz", hash = "sha256:8b412432c6055b0b7d14c310000ae93352ed6754f70fa8f7c34141f91c4e3219", size = 30371, upload-time = "2025-11-21T23:01:54.787Z" }
 wheels = [
@@ -263,17 +263,17 @@ resolution-markers = [
     "python_full_version < '3.11'",
 ]
 dependencies = [
-    { name = "colorama", marker = "sys_platform == 'win32'" },
-    { name = "decorator" },
-    { name = "exceptiongroup" },
-    { name = "jedi" },
-    { name = "matplotlib-inline" },
-    { name = "pexpect", marker = "sys_platform != 'emscripten' and sys_platform != 'win32'" },
-    { name = "prompt-toolkit" },
-    { name = "pygments" },
-    { name = "stack-data" },
-    { name = "traitlets" },
-    { name = "typing-extensions" },
+    { name = "colorama", marker = "python_full_version < '3.11' and sys_platform == 'win32'" },
+    { name = "decorator", marker = "python_full_version < '3.11'" },
+    { name = "exceptiongroup", marker = "python_full_version < '3.11'" },
+    { name = "jedi", marker = "python_full_version < '3.11'" },
+    { name = "matplotlib-inline", marker = "python_full_version < '3.11'" },
+    { name = "pexpect", marker = "python_full_version < '3.11' and sys_platform != 'emscripten' and sys_platform != 'win32'" },
+    { name = "prompt-toolkit", marker = "python_full_version < '3.11'" },
+    { name = "pygments", marker = "python_full_version < '3.11'" },
+    { name = "stack-data", marker = "python_full_version < '3.11'" },
+    { name = "traitlets", marker = "python_full_version < '3.11'" },
+    { name = "typing-extensions", marker = "python_full_version < '3.11'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/e5/61/1810830e8b93c72dcd3c0f150c80a00c3deb229562d9423807ec92c3a539/ipython-8.38.0.tar.gz", hash = "sha256:9cfea8c903ce0867cc2f23199ed8545eb741f3a69420bfcf3743ad1cec856d39", size = 5513996, upload-time = "2026-01-05T10:59:06.901Z" }
 wheels = [
@@ -288,17 +288,17 @@ resolution-markers = [
     "python_full_version >= '3.11'",
 ]
 dependencies = [
-    { name = "colorama", marker = "sys_platform == 'win32'" },
-    { name = "decorator" },
-    { name = "ipython-pygments-lexers" },
-    { name = "jedi" },
-    { name = "matplotlib-inline" },
-    { name = "pexpect", marker = "sys_platform != 'emscripten' and sys_platform != 'win32'" },
-    { name = "prompt-toolkit" },
-    { name = "pygments" },
-    { name = "stack-data" },
-    { name = "traitlets" },
-    { name = "typing-extensions", marker = "python_full_version < '3.12'" },
+    { name = "colorama", marker = "python_full_version >= '3.11' and sys_platform == 'win32'" },
+    { name = "decorator", marker = "python_full_version >= '3.11'" },
+    { name = "ipython-pygments-lexers", marker = "python_full_version >= '3.11'" },
+    { name = "jedi", marker = "python_full_version >= '3.11'" },
+    { name = "matplotlib-inline", marker = "python_full_version >= '3.11'" },
+    { name = "pexpect", marker = "python_full_version >= '3.11' and sys_platform != 'emscripten' and sys_platform != 'win32'" },
+    { name = "prompt-toolkit", marker = "python_full_version >= '3.11'" },
+    { name = "pygments", marker = "python_full_version >= '3.11'" },
+    { name = "stack-data", marker = "python_full_version >= '3.11'" },
+    { name = "traitlets", marker = "python_full_version >= '3.11'" },
+    { name = "typing-extensions", marker = "python_full_version == '3.11.*'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/a6/60/2111715ea11f39b1535bed6024b7dec7918b71e5e5d30855a5b503056b50/ipython-9.10.0.tar.gz", hash = "sha256:cd9e656be97618a0676d058134cd44e6dc7012c0e5cb36a9ce96a8c904adaf77", size = 4426526, upload-time = "2026-02-02T10:00:33.594Z" }
 wheels = [
@@ -310,7 +310,7 @@ name = "ipython-pygments-lexers"
 version = "1.1.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "pygments" },
+    { name = "pygments", marker = "python_full_version >= '3.11'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/ef/4c/5dd1d8af08107f88c7f741ead7a40854b8ac24ddf9ae850afbcf698aa552/ipython_pygments_lexers-1.1.1.tar.gz", hash = "sha256:09c0138009e56b6854f9535736f4171d855c8c08a563a0dcd8022f78355c7e81", size = 8393, upload-time = "2025-01-17T11:24:34.505Z" }
 wheels = [

documente_shared-0.1.202/documente_shared/domain/entities/uif_registry.py

@@ -1,112 +0,0 @@
-import json
-from dataclasses import dataclass, field
-from datetime import date, datetime
-from decimal import Decimal
-from uuid import UUID, uuid4
-
-from documente_shared.application.digest import get_file_digest
-from documente_shared.application.payloads import camel_to_snake, snake_to_camel
-from documente_shared.domain.helpers.values import (
-    optional_date,
-    optional_datetime,
-    optional_decimal,
-    optional_text,
-    optional_uuid,
-)
-
-INSTANCE_FIELDS = frozenset({"uuid", "created_at"})
-
-
-@dataclass
-class UIFRegistry:
-    uuid: UUID = field(default_factory=uuid4)
-    paternal_last_name: str | None = None
-    maternal_last_name: str | None = None
-    first_name: str | None = None
-    identity_document_number: str | None = None
-    identity_document_extension: str | None = None
-    court_name: str | None = None
-    process_type: str | None = None
-    circular_id: str | None = None
-    circular_issue_date: date | None = None
-    involved_amount: Decimal | None = None
-    relation_type: str | None = None
-    due_diligence: bool | None = None
-    illicit_gains_legitimation: bool | None = None
-    document_digest: str | None = None
-    created_at: datetime | None = None
-
-    @property
-    def full_name(self) -> str:
-        parts = [self.paternal_last_name, self.maternal_last_name, self.first_name]
-        return " ".join(part for part in parts if part)
-
-    @property
-    def is_identifiable(self) -> bool:
-        return bool(self.full_name)
-
-    @property
-    def business_fields(self) -> dict:
-        return {
-            field_name: value
-            for field_name, value in self.to_dict.items()
-            if field_name not in INSTANCE_FIELDS
-        }
-
-    @property
-    def digest(self) -> str:
-        return get_file_digest(json.dumps(self.business_fields, sort_keys=True).encode())
-
-    @property
-    def to_dict(self) -> dict:
-        return {
-            "uuid": str(self.uuid),
-            "document_digest": self.document_digest,
-            "paternal_last_name": self.paternal_last_name,
-            "maternal_last_name": self.maternal_last_name,
-            "first_name": self.first_name,
-            "full_name": self.full_name,
-            "identity_document_number": self.identity_document_number,
-            "identity_document_extension": self.identity_document_extension,
-            "court_name": self.court_name,
-            "process_type": self.process_type,
-            "circular_id": self.circular_id,
-            "circular_issue_date": (
-                self.circular_issue_date.isoformat() if self.circular_issue_date else None
-            ),
-            "involved_amount": (
-                str(self.involved_amount) if self.involved_amount is not None else None
-            ),
-            "relation_type": self.relation_type,
-            "due_diligence": self.due_diligence,
-            "illicit_gains_legitimation": self.illicit_gains_legitimation,
-            "created_at": self.created_at.isoformat() if self.created_at else None,
-        }
-
-    @property
-    def to_payload(self) -> dict:
-        return snake_to_camel(self.to_dict)
-
-    @classmethod
-    def from_dict(cls, data: dict) -> "UIFRegistry":
-        normalized = camel_to_snake(data)
-        return cls(
-            uuid=optional_uuid(normalized.get("uuid")) or uuid4(),
-            document_digest=optional_text(normalized.get("document_digest")),
-            paternal_last_name=optional_text(normalized.get("paternal_last_name")),
-            maternal_last_name=optional_text(normalized.get("maternal_last_name")),
-            first_name=optional_text(normalized.get("first_name")),
-            identity_document_number=optional_text(normalized.get("identity_document_number")),
-            identity_document_extension=optional_text(
-                normalized.get("identity_document_extension")
-            ),
-            court_name=optional_text(normalized.get("court_name")),
-            process_type=optional_text(normalized.get("process_type")),
-            circular_id=optional_text(normalized.get("circular_id")),
-            circular_issue_date=optional_date(normalized.get("circular_issue_date")),
-            involved_amount=optional_decimal(normalized.get("involved_amount")),
-            relation_type=optional_text(normalized.get("relation_type")),
-            due_diligence=normalized.get("due_diligence"),
-            illicit_gains_legitimation=normalized.get("illicit_gains_legitimation"),
-            created_at=optional_datetime(normalized.get("created_at")),
-        )

documente_shared-0.1.202/documente_shared/domain/helpers/values.py

@@ -1,77 +0,0 @@
-from contextlib import suppress
-from datetime import date, datetime
-from decimal import Decimal, InvalidOperation
-from uuid import UUID
-
-
-def optional_str(input_value: object | None = None) -> str | None:
-    if input_value is None:
-        return None
-    return str(input_value)
-
-
-def optional_text(input_value: object | None = None) -> str | None:
-    if input_value is None:
-        return None
-    text = str(input_value).strip()
-    return text or None
-
-
-def optional_datetime_str(input_datetime: datetime | None = None) -> str | None:
-    if input_datetime is None:
-        return None
-    return input_datetime.isoformat()
-
-
-def optional_uuid(input_value: object | None = None) -> UUID | None:
-    if input_value is None or isinstance(input_value, UUID):
-        return input_value
-    try:
-        return UUID(str(input_value))
-    except ValueError:
-        return None
-
-
-def _date_from_formats(raw_value: str, formats: tuple[str, ...]) -> date | None:
-    for date_format in formats:
-        with suppress(ValueError):
-            return datetime.strptime(raw_value, date_format).date()  # noqa: DTZ007
-    return None
-
-
-def optional_date(
-    input_value: object | None = None,
-    formats: tuple[str, ...] = (),
-) -> date | None:
-    if input_value is None:
-        return None
-    if isinstance(input_value, datetime):
-        return input_value.date()
-    if isinstance(input_value, date):
-        return input_value
-
-    raw_value = str(input_value).strip()
-    parsed_date = _date_from_formats(raw_value, formats)
-    if parsed_date:
-        return parsed_date
-    with suppress(ValueError):
-        return date.fromisoformat(raw_value)
-    return None
-
-
-def optional_datetime(input_value: object | None = None) -> datetime | None:
-    if input_value is None or isinstance(input_value, datetime):
-        return input_value
-    try:
-        return datetime.fromisoformat(str(input_value))
-    except ValueError:
-        return None
-
-
-def optional_decimal(input_value: object | None = None) -> Decimal | None:
-    if input_value is None or isinstance(input_value, Decimal):
-        return input_value
-    try:
-        return Decimal(str(input_value))
-    except InvalidOperation:
-        return None

documente_shared-0.1.202/documente_shared/domain/repositories/uif_registry.py

@@ -1,14 +0,0 @@
-from abc import ABC, abstractmethod
-
-from documente_shared.domain.entities.uif_registry import UIFRegistry
-
-
-class UIFRegistryRepository(ABC):
-    @abstractmethod
-    def set_document_uif_registries(
-        self,
-        document_digest: str,
-        registries: list[UIFRegistry],
-        replace: bool = True,
-    ) -> list[UIFRegistry]:
-        raise NotImplementedError

documente_shared-0.1.202/documente_shared/infrastructure/lambdas.py

@@ -1,15 +0,0 @@
-import json
-import boto3
-from botocore.config import Config
-
-
-def invoke_lambda(function_name: str, payload: dict, read_timeout: int = 60) -> dict | list | None:
-    client = boto3.client("lambda", config=Config(read_timeout=read_timeout))
-
-    response = client.invoke(
-        FunctionName=function_name,
-        InvocationType="RequestResponse",
-        Payload=json.dumps(payload),
-    )
-
-    return json.loads(response["Payload"].read().decode("utf-8"))

documente_shared-0.1.202/documente_shared/infrastructure/repositories/http_uif_registry.py

@@ -1,50 +0,0 @@
-from dataclasses import dataclass
-from typing import TYPE_CHECKING
-
-import structlog
-
-from documente_shared.domain.entities.uif_registry import UIFRegistry
-from documente_shared.domain.repositories.uif_registry import UIFRegistryRepository
-from documente_shared.infrastructure.documente_client import DocumenteClientMixin
-
-if TYPE_CHECKING:
-    from requests import Response
-
-logger = structlog.get_logger()
-
-
-@dataclass
-class HttpUIFRegistryRepository(
-    DocumenteClientMixin,
-    UIFRegistryRepository,
-):
-    def set_document_uif_registries(
-        self,
-        document_digest: str,
-        registries: list[UIFRegistry],
-        replace: bool = True,
-    ) -> list[UIFRegistry]:
-        payload = {
-            "document_digest": document_digest,
-            "registries": [registry.to_payload for registry in registries],
-            "replace": replace,
-        }
-        logger.info(
-            "[shared.uif_registry.persisting]",
-            document_digest=document_digest,
-            registries=len(registries),
-            replace=replace,
-        )
-        response: Response = self.session.post(
-            url=f"{self.api_url}/v1/documents/uif-registry/",
-            json=payload,
-        )
-        if not self._is_success(response):
-            logger.warning(
-                "[shared.uif_registry.persist_error]",
-                document_digest=document_digest,
-                status_code=response.status_code,
-                response=response.text,
-            )
-            return []
-        return self._parse_list(response, UIFRegistry.from_dict)