json2ubl 1.0.0__py3-none-any.whl → 1.0.1__py3-none-any.whl

json2ubl/__init__.py

@@ -4,6 +4,8 @@ from typing import Any, Dict, List
 from .config import UblConfig, get_logger
 from .converter import Json2UblConverter
 
+__version__ = "1.0.1"
+
 logger = get_logger(__name__)
 PACKAGE_DIR = Path(__file__).parent
 
@@ -80,42 +82,35 @@ def json_dict_to_ubl_xml(
     config.setup_logging()
 
     converter = Json2UblConverter(config)
+    merged_dicts = converter._group_and_merge_documents(list_of_dicts)
+
     documents = []
     document_types: Dict[str, int] = {}
+    first_error_response = None
 
-    for doc_dict in list_of_dicts:
+    for doc_dict in merged_dicts:
         response = converter.convert_json_dict_to_xml_dict(doc_dict)
 
         if response.get("error_response"):
+            if first_error_response is None:
+                first_error_response = response["error_response"]
             logger.error(f"Conversion failed: {response['error_response']}")
-            return response
+            continue
 
         if not response.get("documents") or len(response["documents"]) == 0:
             error_msg = "No valid documents in conversion response"
+            if first_error_response is None:
+                first_error_response = error_msg
             logger.error(error_msg)
-            return {
-                "documents": [],
-                "summary": {
-                    "total_inputs": len(list_of_dicts),
-                    "files_created": 0,
-                    "document_types": {},
-                },
-                "error_response": error_msg,
-            }
+            continue
 
         doc_info = response["documents"][0]
         if not isinstance(doc_info, dict):
             error_msg = "Invalid document info format"
+            if first_error_response is None:
+                first_error_response = error_msg
             logger.error(error_msg)
-            return {
-                "documents": [],
-                "summary": {
-                    "total_inputs": len(list_of_dicts),
-                    "files_created": 0,
-                    "document_types": {},
-                },
-                "error_response": error_msg,
-            }
+            continue
 
         documents.append(doc_info)
 
@@ -123,10 +118,21 @@ def json_dict_to_ubl_xml(
         for dtype, count in doc_type.items():
             document_types[dtype] = document_types.get(dtype, 0) + count
 
+    if not documents and first_error_response:
+        return {
+            "documents": [],
+            "summary": {
+                "total_inputs": len(list_of_dicts),
+                "files_created": 0,
+                "document_types": {},
+            },
+            "error_response": first_error_response,
+        }
+
     return {
         "documents": documents,
         "summary": {
-            "total_inputs": len(list_of_dicts),
+            "total_inputs": len(merged_dicts),
             "files_created": 0,
             "document_types": document_types,
         },

json2ubl/config.py

@@ -33,7 +33,7 @@ class UblConfig:
         logs_dir = Path("logs")
         logs_dir.mkdir(parents=True, exist_ok=True)
 
-        timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+        timestamp = datetime.now().strftime("%Y%m%d")
         log_filename = f"json2ubl_{timestamp}.log"
         log_path = logs_dir / log_filename
 

json2ubl/converter.py

@@ -353,30 +353,16 @@ class Json2UblConverter:
 
             logger.info(f"Found {len(data)} documents in file")
 
-            data = [self._normalize_keys_recursive(page) for page in data]
-
-            grouped: Dict[str, List[Dict[str, Any]]] = {}
-            skipped_count = 0
-            for page in data:
-                doc_id = page.get("id")
-                if not doc_id:
-                    logger.warning("Skipping page without 'id' field")
-                    skipped_count += 1
-                    continue
-                grouped.setdefault(doc_id, []).append(page)
-
-            logger.info(
-                f"Grouped into {len(grouped)} unique documents (skipped {skipped_count} without id)"
-            )
+            merged_docs = self._group_and_merge_documents(data)
+            logger.info(f"Grouped into {len(merged_docs)} unique documents")
 
             documents = []
             document_types: Dict[str, int] = {}
             first_error_response = None
 
-            for doc_id, pages in grouped.items():
+            for merged in merged_docs:
                 try:
-                    merged = self._merge_pages(pages)
-
+                    doc_id = merged.get("id", "UNKNOWN")
                     response = self.convert_json_dict_to_xml_dict(merged)
 
                     if response.get("error_response"):
@@ -598,28 +584,95 @@ class Json2UblConverter:
                 "error_response": error_msg,
             }
 
+    def _group_and_merge_documents(self, documents: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
+        """Group documents by ID and merge pages with same ID.
+
+        Args:
+            documents: List of document dictionaries (potentially with duplicate IDs)
+
+        Returns:
+            List of merged documents (one per unique ID)
+        """
+        if not documents:
+            return []
+
+        documents = [self._normalize_keys_recursive(doc) for doc in documents]
+
+        grouped: Dict[str, List[Dict[str, Any]]] = {}
+        for doc in documents:
+            doc_id = doc.get("id")
+            if not doc_id:
+                logger.warning("Skipping document without 'id' field")
+                continue
+            grouped.setdefault(doc_id, []).append(doc)
+
+        merged_documents = []
+        for doc_id, pages in grouped.items():
+            try:
+                doc_type_raw = pages[0].get("document_type")
+                document_type = NUMERIC_TYPE_TO_DOCUMENT_TYPE.get(str(doc_type_raw))
+
+                schema_cache = {}
+                if document_type:
+                    schema_cache = self._load_schema_cache(document_type)
+
+                merged = self._merge_pages(pages, schema_cache)
+                merged_documents.append(merged)
+            except Exception as e:
+                logger.error(f"Failed to merge document {doc_id}: {e}")
+                continue
+
+        return merged_documents
+
     @staticmethod
-    def _merge_pages(pages: List[Dict[str, Any]]) -> Dict[str, Any]:
-        """Merge multi-page invoice into single object."""
+    def _merge_pages(
+        pages: List[Dict[str, Any]], schema_cache: Dict[str, Any] | None = None
+    ) -> Dict[str, Any]:
+        """Merge multi-page invoice into single object.
+
+        Args:
+            pages: List of document pages (dictionaries)
+            schema_cache: Schema cache to identify array fields dynamically
+
+        Returns:
+            Merged document dictionary
+        """
         if not pages:
             return {}
 
         merged = deepcopy(pages[0])
 
-        list_fields = {
-            "invoiceLines",
-            "additionalDocumentReferences",
-            "globalAllowanceCharges",
-            "taxTotal",
-        }
+        array_fields = set()
+        if schema_cache and "elements" in schema_cache:
+            for field_lower, field_info in schema_cache["elements"].items():
+                if isinstance(field_info, dict) and field_info.get("maxOccurs") == "unbounded":
+                    array_fields.add(field_lower)
 
         for page in pages[1:]:
-            for field in list_fields:
-                if field in page and page[field]:
-                    merged.setdefault(field, []).extend(page[field])
+            page_keys_lower = {k.lower(): k for k in page.keys()}
+
+            for field_lower in array_fields:
+                original_key = page_keys_lower.get(field_lower)
+                if original_key and page.get(original_key):
+                    merged_keys_lower = {k.lower(): k for k in merged.keys()}
+                    merged_key_original = merged_keys_lower.get(field_lower)
+
+                    if merged_key_original:
+                        if not isinstance(merged[merged_key_original], list):
+                            merged[merged_key_original] = [merged[merged_key_original]]
+                        if isinstance(page[original_key], list):
+                            merged[merged_key_original].extend(page[original_key])
+                        else:
+                            merged[merged_key_original].append(page[original_key])
+                    else:
+                        if isinstance(page[original_key], list):
+                            merged[original_key] = page[original_key]
+                        else:
+                            merged[original_key] = [page[original_key]]
 
             for key, value in page.items():
-                if key not in list_fields and value is not None:
+                key_lower = key.lower()
+                if key_lower not in array_fields and value is not None:
                     merged[key] = value
 
         return merged

{json2ubl-1.0.0.dist-info → json2ubl-1.0.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: json2ubl
-Version: 1.0.0
+Version: 1.0.1
 Summary: Production-grade JSON to UBL 2.1 XML converter with schema-driven mapping
 Author-email: SherozShaikh <shaikh.sheroz07@gmail.com>
 License: MIT
@@ -22,16 +22,16 @@ Classifier: Topic :: Office/Business :: Financial
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: lxml<5.0,>=4.9.4
-Requires-Dist: pydantic<3.0,>=2.7.0
-Requires-Dist: pyyaml<7.0,>=6.0.1
-Requires-Dist: loguru<1.0,>=0.7.2
+Requires-Dist: lxml~=6.0
+Requires-Dist: pydantic~=2.7
+Requires-Dist: pyyaml~=6.0
+Requires-Dist: loguru~=0.7
 Provides-Extra: dev
-Requires-Dist: pytest<9.0,>=8.3.0; extra == "dev"
-Requires-Dist: pytest-cov<6.0,>=5.0.0; extra == "dev"
-Requires-Dist: black<25.0,>=24.10.0; extra == "dev"
-Requires-Dist: ruff<1.0,>=0.8.0; extra == "dev"
-Requires-Dist: mypy<2.0,>=1.13.0; extra == "dev"
+Requires-Dist: pytest~=8.3; extra == "dev"
+Requires-Dist: pytest-cov~=5.0; extra == "dev"
+Requires-Dist: black~=24.10; extra == "dev"
+Requires-Dist: ruff~=0.8; extra == "dev"
+Requires-Dist: mypy~=1.13; extra == "dev"
 Dynamic: license-file
 
 # json2ubl
@@ -41,6 +41,7 @@ Dynamic: license-file
 [![PyPI version](https://badge.fury.io/py/json2ubl.svg)](https://badge.fury.io/py/json2ubl)
 [![Python Versions](https://img.shields.io/pypi/pyversions/json2ubl.svg)](https://pypi.org/project/json2ubl/)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 
 [json2ubl](https://pypi.org/project/json2ubl/) is a production-ready converter that transforms JSON documents into UBL 2.1-compliant XML. It works with all 60+ UBL document types using automatic schema-driven mapping—no hardcoded field definitions required.
 
@@ -211,6 +212,8 @@ Convert JSON file and write XML files to disk.
 - Rolls back on partial failure
 - Atomic file operations with temp file staging
 
+**For detailed API documentation with input/output examples and error handling, see [API.md](docs/API.md)**
+
 ---
 
 ## 🛡️ Error Handling

{json2ubl-1.0.0.dist-info → json2ubl-1.0.1.dist-info}/RECORD

@@ -1,9 +1,9 @@
-json2ubl/__init__.py,sha256=QL7iCApi-wboHu2z7XvZIg96AReFnPUpLGKj8CN_btU,7097
+json2ubl/__init__.py,sha256=zZi4Ke0gn1NcFXygwzLyhAxTA1g9g54gjEVsaBzgLYw,7280
 json2ubl/benchmark.py,sha256=TVQfe6aifNNv6VkjlnQmV8yDQL2se1Wim8bbOJy0HxQ,2242
 json2ubl/benchmark_examples.py,sha256=jTjS1gpyAkZuYtfFjCHERQhfgqIAiIHl7td6DXkQp7A,2123
-json2ubl/config.py,sha256=_l_hHOTx6RzEjNvvg4Gx67JB6l7x4kePHnWSW2BDXL0,1710
+json2ubl/config.py,sha256=sjtxG9gqzMZYzBeDcz6bjDwRY3eklGWAoc88qoL1Wro,1703
 json2ubl/constants.py,sha256=VKyW-NcsuASKLgXjq4jMbsu8wK5eALlcjkqMxZ4GGek,2115
-json2ubl/converter.py,sha256=cKHnqjPAzg3sxY5qvPQRTE5D6XWmkRRdGHRr-pr36gM,24685
+json2ubl/converter.py,sha256=05wkyDqIJxK3Jb2anbVbHk1DRsi6_4dIECae1GsgIac,27078
 json2ubl/exceptions.py,sha256=SjuarBL3kFwTyXX8i3gI_XFS3F_jI9YdRwUJ9qkkJI8,1363
 json2ubl/core/__init__.py,sha256=ZeHxEGzJnvbGtvLzKtFiScSSz5aYgUtDXb_jHeR6crc,258
 json2ubl/core/mapper.py,sha256=rBXctsIPH92wWAHz6mRDNWC8S_w76K7DDQo-qI0hYqY,7099
@@ -95,8 +95,8 @@ json2ubl/schemas/ubl-2.1/maindoc/UBL-TransportationStatusRequest-2.1.xsd,sha256=
 json2ubl/schemas/ubl-2.1/maindoc/UBL-UnawardedNotification-2.1.xsd,sha256=zGmccnKSXad4709Ih3fn66175FtJUb7PLPuRRy50_wY,25282
 json2ubl/schemas/ubl-2.1/maindoc/UBL-UtilityStatement-2.1.xsd,sha256=Yajwexatg2kKRsooaQC0yfKIiKblUzpykcMaFD8Qy1A,29901
 json2ubl/schemas/ubl-2.1/maindoc/UBL-Waybill-2.1.xsd,sha256=dApHBjRdiqgrRkbLeN3US8LrkTQBh609zgcQH6RPRZ8,31171
-json2ubl-1.0.0.dist-info/licenses/LICENSE,sha256=fud2PsdIMMFCTKje7U4wU1LruG0_xiLIl0K9EYFpp20,1069
-json2ubl-1.0.0.dist-info/METADATA,sha256=ePN-oA1AzbTQYjFV9o_pc7VoBu6LRyDpFKyG69tPVlA,9796
-json2ubl-1.0.0.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-json2ubl-1.0.0.dist-info/top_level.txt,sha256=ThPMfVebrZMMoA4l92KA8IaHwh76tYLpgORoyfM6s94,9
-json2ubl-1.0.0.dist-info/RECORD,,
+json2ubl-1.0.1.dist-info/licenses/LICENSE,sha256=fud2PsdIMMFCTKje7U4wU1LruG0_xiLIl0K9EYFpp20,1069
+json2ubl-1.0.1.dist-info/METADATA,sha256=i_Go11equlGX76Yh9vmvQQT8_noWviSKqdeiUKKuWAU,9954
+json2ubl-1.0.1.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+json2ubl-1.0.1.dist-info/top_level.txt,sha256=ThPMfVebrZMMoA4l92KA8IaHwh76tYLpgORoyfM6s94,9
+json2ubl-1.0.1.dist-info/RECORD,,