documente_shared 0.1.122__tar.gz → 0.1.124__tar.gz

{documente_shared-0.1.122 → documente_shared-0.1.124}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: documente_shared
-Version: 0.1.122
+Version: 0.1.124
 Summary: Shared utilities for Documente AI projects
 License: MIT
 Author: Tech

{documente_shared-0.1.122 → documente_shared-0.1.124}/documente_shared/application/query_params.py

@@ -14,7 +14,7 @@ def camelize_string(value: str) -> str:
     return value[:1].lower() + value[1:]
 
 
-def parse_bool(input_value: bool) -> str:
+def parse_bool_to_str(input_value: bool) -> str:
     return str(input_value).lower()
 
 

{documente_shared-0.1.122 → documente_shared-0.1.124}/documente_shared/domain/entities/processing_case_item.py

@@ -233,12 +233,7 @@ class ProcessingCaseItem(object):
 
     @property
     def to_persist_dict(self) -> dict:
-        simple_dict = self.to_dict.copy()
-        simple_dict["document_path"] = self.document.file_path if self.document else None
-        simple_dict["processed_csv_path"] = self.processed_csv.file_path if self.processed_csv else None
-        simple_dict["processed_xlsx_path"] = self.processed_xlsx.file_path if self.processed_xlsx else None
-        simple_dict["processed_json_path"] = self.processed_json.file_path if self.processed_json else None
-        return simple_dict
+        return self.to_dict
 
     @classmethod
     def from_dict(cls, data: dict) -> 'ProcessingCaseItem':

{documente_shared-0.1.122 → documente_shared-0.1.124}/documente_shared/domain/repositories/processing_case_item.py

@@ -28,6 +28,7 @@ class ProcessingCaseItemRepository(ABC):
         self,
         instance: ProcessingCaseItem,
         read_bytes: bool = False,
+        persist_bytes: bool = False,
     ) -> ProcessingCaseItem:
         raise NotImplementedError
 

{documente_shared-0.1.122 → documente_shared-0.1.124}/documente_shared/infrastructure/repositories/dynamo_document.py

@@ -13,13 +13,13 @@ class DynamoDocumentProcessingRepository(
     DynamoDBTable,
     DocumentProcessingRepository,
 ):
-    def find(self, digest: str) -> Optional[DocumentProcessing]:
+    def find(self, digest: str, read_bytes: bool = False) -> Optional[DocumentProcessing]:
         item = self.get(key={'digest': digest})
         if item:
             return DocumentProcessing.from_dict(item)
         return None
 
-    def persist(self, instance: DocumentProcessing) -> DocumentProcessing:
+    def persist(self, instance: DocumentProcessing, read_bytes: bool = False) -> DocumentProcessing:
         self.put(instance.to_simple_dict)
         return instance
 

{documente_shared-0.1.122 → documente_shared-0.1.124}/documente_shared/infrastructure/repositories/dynamo_processing_case_item.py

@@ -25,7 +25,12 @@ class DynamoProcessingCaseItemRepository(
             return ProcessingCaseItem.from_dict(item)
         return None
 
-    def persist(self, instance: ProcessingCaseItem, read_bytes: bool = False) -> ProcessingCaseItem:
+    def persist(
+        self,
+        instance: ProcessingCaseItem,
+        read_bytes: bool = False,
+        persist_bytes: bool = False,
+    ) -> ProcessingCaseItem:
         self.put(instance.to_simple_dict)
         return instance
 

{documente_shared-0.1.122 → documente_shared-0.1.124}/documente_shared/infrastructure/repositories/http_document.py

@@ -5,6 +5,7 @@ from loguru import logger
 from requests import Response
 
 from documente_shared.application.payloads import camel_to_snake
+from documente_shared.application.query_params import parse_bool_to_str
 from documente_shared.domain.entities.document import DocumentProcessing
 from documente_shared.domain.enums.document import DocumentProcessingStatus
 from documente_shared.domain.repositories.document import DocumentProcessingRepository
@@ -16,16 +17,26 @@ class HttpDocumentProcessingRepository(
     DocumenteClientMixin,
     DocumentProcessingRepository,
 ):
-    def find(self, digest: str) -> Optional[DocumentProcessing]:
-        response = self.session.get(f"{self.api_url}/v1/documents/{digest}/")
+    def find(self, digest: str, read_bytes: bool = False) -> Optional[DocumentProcessing]:
+        params = {
+            "read_bytes": parse_bool_to_str(read_bytes),
+        }
+        response = self.session.get(
+            url=f"{self.api_url}/v1/documents/{digest}/",
+            params=params,
+        )
         if response.status_code not in [200, 201]:
             return None
         return self._build_document_processing(response)
 
-    def persist(self, instance: DocumentProcessing) -> DocumentProcessing:
+    def persist(self, instance: DocumentProcessing, read_bytes: bool = False) -> DocumentProcessing:
         logger.info(f"PERSISTING_DOCUMENT: data={instance.to_simple_dict}")
+        params = {
+            "read_bytes": parse_bool_to_str(read_bytes),
+        }
         response = self.session.put(
             url=f"{self.api_url}/v1/documents/{instance.digest}/",
+            params=params,
             json=instance.to_simple_dict,
         )
         if response.status_code not in [200, 201]:

{documente_shared-0.1.122 → documente_shared-0.1.124}/documente_shared/infrastructure/repositories/http_processing_case.py

@@ -1,11 +1,12 @@
 from dataclasses import dataclass
+from sqlite3.dbapi2 import paramstyle
 from typing import List, Optional
 
 from loguru import logger
 from requests import Response
 
 from documente_shared.application.payloads import camel_to_snake
-from documente_shared.application.query_params import parse_bool
+from documente_shared.application.query_params import parse_bool_to_str
 from documente_shared.domain.entities.processing_case import ProcessingCase
 from documente_shared.domain.entities.processing_case_filters import ProcessingCaseFilters
 from documente_shared.domain.repositories.processing_case import ProcessingCaseRepository
@@ -34,8 +35,12 @@ class HttpProcessingCaseRepository(
         persist_items: bool = False,
     ) -> ProcessingCase:
         logger.info(f"PERSISTING_PROCESSING_CASE: data={instance.to_queue_dict}")
+        params = {
+            "persist_items": parse_bool_to_str(persist_items),
+        }
         response = self.session.put(
-            url=f"{self.api_url}/v1/processing-cases/{instance.uuid}/?persist_items={parse_bool(persist_items)}",
+            url=f"{self.api_url}/v1/processing-cases/{instance.uuid}/",
+            params=params,
             json=instance.to_dict,
         )
         if response.status_code not in [200, 201]:

{documente_shared-0.1.122 → documente_shared-0.1.124}/documente_shared/infrastructure/repositories/http_processing_case_item.py

@@ -5,7 +5,7 @@ from loguru import logger
 from requests import Response
 
 from documente_shared.application.payloads import camel_to_snake
-from documente_shared.application.query_params import parse_bool
+from documente_shared.application.query_params import parse_bool_to_str
 from documente_shared.domain.entities.processing_case_item import ProcessingCaseItem
 from documente_shared.domain.entities.processing_case_item_filters import ProcessingCaseItemFilters
 from documente_shared.domain.repositories.processing_case_item import ProcessingCaseItemRepository
@@ -19,7 +19,7 @@ class HttpProcessingCaseItemRepository(
 ):
     def find(self, uuid: str, read_bytes: bool = False) -> Optional[ProcessingCaseItem]:
         response = self.session.get(
-            url=f"{self.api_url}/v1/processing-case-items/{uuid}/?read_bytes={parse_bool(read_bytes)}",
+            url=f"{self.api_url}/v1/processing-case-items/{uuid}/?read_bytes={parse_bool_to_str(read_bytes)}",
         )
         if response.status_code not in [200, 201]:
             return None
@@ -27,17 +27,29 @@ class HttpProcessingCaseItemRepository(
 
     def find_by_digest(self, digest: str, read_bytes: bool = False) -> Optional[ProcessingCaseItem]:
         response = self.session.get(
-            url=f"{self.api_url}/v1/processing-case-items/{digest}/?read_bytes={parse_bool(read_bytes)}",
+            url=f"{self.api_url}/v1/processing-case-items/{digest}/?read_bytes={parse_bool_to_str(read_bytes)}",
         )
         if response.status_code not in [200, 201]:
             return None
         return self._build_processing_case_item(response)
 
-    def persist(self, instance: ProcessingCaseItem, read_bytes: bool = False) -> ProcessingCaseItem:
+    def persist(
+        self,
+        instance: ProcessingCaseItem,
+        read_bytes: bool = False,
+        persist_bytes: bool = False,
+    ) -> ProcessingCaseItem:
         logger.info(f"PERSISTING_PROCESSING_CASE_ITEM: data={instance.to_queue_dict}")
+        params = {
+            "read_bytes": parse_bool_to_str(read_bytes),
+        }
         response: Response = self.session.put(
-            url=f"{self.api_url}/v1/processing-case-items/{instance.uuid}/?read_bytes={parse_bool(read_bytes)}",
-            json=instance.to_persist_dict,
+            url=f"{self.api_url}/v1/processing-case-items/{instance.uuid}/",
+            params=params,
+            json=(
+                instance.to_persist_dict
+                if persist_bytes else instance.to_queue_dict
+            ),
         )
         if response.status_code not in [200, 201]:
             logger.info(f"PERSISTING_PROCESSING_CASE_ITEM ERROR: data={response.text}")

{documente_shared-0.1.122 → documente_shared-0.1.124}/documente_shared/infrastructure/repositories/mem_processing_case_item.py

@@ -38,6 +38,7 @@ class MemoryProcessingCaseItemRepository(ProcessingCaseItemRepository):
         self,
         instance: ProcessingCaseItem,
         read_bytes: bool = False,
+        persist_bytes: bool = False,
     ) -> ProcessingCaseItem:
         self.collection[instance.uuid] = instance
         return instance

{documente_shared-0.1.122 → documente_shared-0.1.124}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "documente_shared"
-version = "0.1.122"
+version = "0.1.124"
 description = "Shared utilities for Documente AI projects"
 authors = ["Tech <tech@llamitai.com>"]
 license = "MIT"