documente_shared 0.1.100__tar.gz → 0.1.102__tar.gz

{documente_shared-0.1.100 → documente_shared-0.1.102}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: documente_shared
-Version: 0.1.100
+Version: 0.1.102
 Summary: Shared utilities for Documente AI projects
 License: MIT
 Author: Tech
@@ -17,6 +17,7 @@ Requires-Dist: loguru (>=0.7.3,<0.8.0)
 Requires-Dist: pytz (>=2025.2,<2026.0)
 Requires-Dist: requests (>=2.32.3,<3.0.0)
 Requires-Dist: sentry-sdk (>=2.19.2,<3.0.0)
+Requires-Dist: unidecode (>=1.3.8,<2.0.0)
 Description-Content-Type: text/markdown
 
 

documente_shared-0.1.102/documente_shared/application/json.py

@@ -0,0 +1,45 @@
+import re
+from typing import Any
+
+import unicodedata
+from unidecode import unidecode
+
+
+def underscoreize(data: Any) -> Any:
+    if isinstance(data, dict):
+        new_dict = {}
+        for key, value in data.items():
+            new_key = re.sub(r"(?<!^)(?=[A-Z])", "_", key).lower()
+            new_dict[new_key] = underscoreize(value)
+        return new_dict
+    elif isinstance(data, list):
+        return [underscoreize(item) for item in data]
+    else:
+        return data
+
+
+def safe_format(data: Any) -> Any:
+    if isinstance(data, dict):
+        new_dict = {}
+        for key, value in data.items():
+            new_key = unidecode(key.replace(" ", "_"))
+            new_dict[new_key] = safe_format(value)
+        return new_dict
+    elif isinstance(data, list):
+        return [safe_format(item) for item in data]
+    else:
+        return data
+
+
+def normalize_key(key: str) -> str:
+    normalized = unicodedata.normalize('NFC', key)
+    underscored = re.sub(r'\s+', '_', normalized)
+    return underscored
+
+
+def normalize_dict_keys(data: dict) -> dict:
+    return {normalize_key(k): v for k, v in data.items()}
+
+
+def normalize_list_keys(data: list) -> list:
+    return [normalize_dict_keys(item) for item in data]

documente_shared-0.1.102/documente_shared/domain/entities/processing_documents.py

@@ -0,0 +1,11 @@
+from dataclasses import dataclass
+from typing import Optional
+
+from documente_shared.domain.entities.in_memory_document import InMemoryDocument
+
+
+@dataclass
+class ProcessedDocuments(object):
+    processed_csv: Optional[InMemoryDocument] = None
+    processed_xlsx: Optional[InMemoryDocument] = None
+    processed_json: Optional[InMemoryDocument] = None

{documente_shared-0.1.100 → documente_shared-0.1.102}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "documente_shared"
-version = "0.1.100"
+version = "0.1.102"
 description = "Shared utilities for Documente AI projects"
 authors = ["Tech <tech@llamitai.com>"]
 license = "MIT"
@@ -12,6 +12,7 @@ boto3 = "^1.37.19"
 botocore = "^1.37.19"
 sentry-sdk = "^2.19.2"
 pytz = "^2025.2"
+unidecode = "^1.3.8"
 requests = "^2.32.3"
 loguru = "^0.7.3"