kodexa 6.1.1a1__tar.gz → 6.1.1a2.post4573624930__tar.gz

{kodexa-6.1.1a1 → kodexa-6.1.1a2.post4573624930}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: kodexa
-Version: 6.1.1a1
+Version: 6.1.1a2.post4573624930
 Summary: Python SDK for the Kodexa Platform
 Author: Austin Redenbaugh
 Author-email: austin@kodexa.com

{kodexa-6.1.1a1 → kodexa-6.1.1a2.post4573624930}/kodexa/platform/client.py

@@ -1937,6 +1937,31 @@ class DataStoreEndpoint(StoreEndpoint):
                                     data_object_page.content]
         return data_object_page
 
+    def get_stream_data_objects_request(self, path: str, query="*", document_family: Optional[DocumentFamily] = None,
+                                        parent_id: Optional[str] = None):
+        """
+        Stream page request
+        :param path (str): The parent taxon (/ is root)
+        :param query (str): The query to limit results (Default *)
+        :param document_family (Optional[DocumentFamily): Optionally the document family to limit results to
+        :param parent_id (Optional[str]): Optionally the parent ID to limit results to
+        :return:
+        """
+        page_size = 20
+        page = 1
+
+        while True:
+            data_object_response = self.get_data_objects_page_request(self, path, page, page_size, query,
+                                                                      document_family, parent_id)
+            if not data_object_response.content:
+                break
+
+            yield data_object_response.content
+            for data_object in data_object_response.content:
+                yield data_object
+
+            page += 1
+
     def create_data_objects(self, data_objects: List[DataObject]) -> List[DataObjectEndpoint]:
         """
         Create data objects in the store
@@ -2079,7 +2104,7 @@ class DocumentStoreEndpoint(StoreEndpoint):
     def download_document_families(self, output_dir: str):
         """Download all the document families in the store to the given directory"""
 
-        for document_family in self.query(page_size=9999).content:
+        for document_family in self.stream_query():
             export_bytes = document_family.export()
             with open(os.path.join(output_dir, document_family.id + ".dfm"), 'wb') as f:
                 f.write(export_bytes)

{kodexa-6.1.1a1 → kodexa-6.1.1a2.post4573624930}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "kodexa"
-version = "6.1.1a1"
+version = "6.1.1a2-4573624930"
 description = "Python SDK for the Kodexa Platform"
 authors = ["Austin Redenbaugh <austin@kodexa.com>", "Philip Dodds <philip@kodexa.com>", "Romar Cablao <rcablao@kodexa.com>", "Amadea Paula Dodds <amadeapaula@kodexa.com>"]
 readme = "README.md"

{kodexa-6.1.1a1 → kodexa-6.1.1a2.post4573624930}/setup.py

@@ -37,7 +37,7 @@ install_requires = \
 
 setup_kwargs = {
     'name': 'kodexa',
-    'version': '6.1.1a1',
+    'version': '6.1.1a2.post4573624930',
     'description': 'Python SDK for the Kodexa Platform',
     'long_description': '# Kodexa\n\n[![Build and Package with Poetry](https://github.com/kodexa-ai/kodexa/actions/workflows/main.yml/badge.svg?branch=main)](https://github.com/kodexa-ai/kodexa/actions/workflows/main.yml)\n\n![img.png](https://docs.kodexa.com/img.png)\n\nKodexa is a platform for building intelligent document processing pipelines. It is a set of tools and services that\nallow you to build a pipeline that can take a document, extract the content, and then process it to extract the\ninformation you need.\n\nIt is built on a set of core principles:\n\n* **Document Centric** - Kodexa is built around the idea of a document. A document is a collection of content\n  nodes that are connected together. This is a powerful model that allows you to build pipelines that can\n  extract content from a wide range of sources.\n\n* **Pipeline Oriented** - Kodexa is built around the idea of a pipeline. A pipeline is a series of steps that\n  can be executed on a document. This allows you to build a pipeline that can extract content from a wide range\n  of sources.\n\n* **Extensible** - Kodexa is built around the idea of a pipeline. A pipeline is a series of steps that can be executed\n  on a document. This allows you to build a pipeline that can extract content from a wide range of sources.\n\n* **Label Driven** - Kodexa focuses on the idea of labels. Labels are a way to identify content within a document\n  and then use that content to drive the processing of the document.\n\n# Python SDK\n\nThis repository contains the Python SDK for Kodexa. The SDK is the primary way to interact with Kodexa. It allows you to\ndefine actions, models, and pipelines that can be executed on Kodexa. It also includes a complete SDK client for\nworking with a Kodexa platform instance.\n\n## Documentation & Examples\n\nDocumentation is available at the [Kodexa Documentation Portal](https://docs.kodexa.com)\n\n## Current Development\n\nThe main branch is 6.0 which is a production release.\n\n## Set-up\n\nWe use poetry to manage our dependencies, so you can install them with:\n\n    poetry install\n\nYou can then run the tests with:\n\n    poetry run pytest\n\n# Contributing\n\nWe welcome contributions to the Kodexa platform. Please see our [contributing guide](CONTRIBUTING.md) for more details.\n\n# License\n\nApache 2.0\n',
     'author': 'Austin Redenbaugh',