data-science-document-ai 1.40.3__py3-none-any.whl → 1.40.4__py3-none-any.whl

{data_science_document_ai-1.40.3.dist-info → data_science_document_ai-1.40.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-science-document-ai
-Version: 1.40.3
+Version: 1.40.4
 Summary: "Document AI repo for data science"
 Author: Naomi Nguyen
 Author-email: naomi.nguyen@forto.com

{data_science_document_ai-1.40.3.dist-info → data_science_document_ai-1.40.4.dist-info}/RECORD

@@ -7,7 +7,7 @@ src/io.py,sha256=IXz4wWqiHa9mnHNgtrC6X9M2lItYp9eu6rHCThUIh5c,3585
 src/llm.py,sha256=aEK3rL8XvY7CakvkOJQmcHpEKwZRd8PPrLrzHiO-GFk,7827
 src/log_setup.py,sha256=RhHnpXqcl-ii4EJzRt47CF2R-Q3YPF68tepg_Kg7tkw,2895
 src/pdf_processing.py,sha256=S_eTsgaDIIr3SCrEmaQZyc7TDJlRI0GCuP0P9EGF1Xc,15385
-src/postprocessing/common.py,sha256=ll7VMEJ_51OeczcV8Uw-aVrufV3kd3kNLCmss3kt0Do,19291
+src/postprocessing/common.py,sha256=W4L455j7IvTRZDWiBizoj9KC_UGUflkL_hEkk5P0h0k,20391
 src/postprocessing/postprocess_booking_confirmation.py,sha256=nK32eDiBNbauyQz0oCa9eraysku8aqzrcoRFoWVumDU,4827
 src/postprocessing/postprocess_commercial_invoice.py,sha256=3I8ijluTZcOs_sMnFZxfkAPle0UFQ239EMuvZfDZVPg,1028
 src/postprocessing/postprocess_partner_invoice.py,sha256=cM4te4qjOI_bXyrF8Zhb6X7eNf5aMKoRaPCFfqFv-98,11538
@@ -54,6 +54,6 @@ src/prompts/prompt_library.py,sha256=VJWHeXN-s501C2GiidIIvQQuZdU6T1R27hE2dKBiI40
 src/setup.py,sha256=kPSZosrICfaGZeDaajr40Ha7Ok4XK4fo_uq35Omiwr0,7128
 src/tms.py,sha256=UXbIo1QE--hIX6NZi5Qyp2R_CP338syrY9pCTPrfgnE,1741
 src/utils.py,sha256=-1Yq_5ExZlFQRUPRsQHiBD3TthNSiPVPp46Dvdb9Kf0,13830
-data_science_document_ai-1.40.3.dist-info/METADATA,sha256=ym7EzwlZAar6Qvx0GgwVQM44p30sw74-nrPl7Liyg_8,2153
-data_science_document_ai-1.40.3.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
-data_science_document_ai-1.40.3.dist-info/RECORD,,
+data_science_document_ai-1.40.4.dist-info/METADATA,sha256=zM542Z9wdq9B2SaEmjoAEzj20BYlbL9LxwjZvMXb22w,2153
+data_science_document_ai-1.40.4.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
+data_science_document_ai-1.40.4.dist-info/RECORD,,

src/postprocessing/common.py

@@ -446,10 +446,18 @@ async def format_label(entity_k, entity_value, document_type_code, params):
     elif "reversechargesentence" in entity_key:
         formatted_value = clean_item_description(entity_value, remove_numbers=False)
 
+    elif "quantity" in entity_key:
+        if document_type_code in ["partnerInvoice", "customsInvoice", "bundeskasse"]:
+            # For partner invoice, quantity can be mentioned as whole number
+            formatted_value = decimal_convertor(
+                extract_number(entity_value), quantity=True
+            )
+        else:
+            formatted_value = extract_number(entity_value)
+
     elif any(
         numeric_indicator in entity_key
         for numeric_indicator in [
-            "quantity",
             "value",
             "amount",
             "price",
@@ -514,7 +522,7 @@ async def get_port_code_llm(port: str, llm_client):
             return None
 
 
-def decimal_convertor(value):
+def decimal_convertor(value, quantity=False):
     """Convert EU values to English values."""
     if value is None:
         return None
@@ -522,25 +530,39 @@ def decimal_convertor(value):
     # Remove spaces
     value = value.strip().replace(" ", "")
 
-    # Convert comma to dot for decimal point (e.g., 4.123,45 -> 4123.45)
-    if re.match(r"^\d{1,3}(\.\d{3})*,\d{1,2}$", value):
-        value = value.replace(".", "").replace(",", ".")
+    if not quantity:
+        # Convert comma to dot for decimal point (e.g., 4.123,45 -> 4123.45)
+        if re.match(r"^\d{1,3}(\.\d{3})*,\d{1,2}$", value):
+            value = value.replace(".", "").replace(",", ".")
+
+        # European style integer with thousand separator: 2.500
+        elif re.match(r"^\d{1,3}(\.\d{3})+$", value):
+            value = value.replace(".", "")
+
+        # Format english values as well for consistency (e.g., 4,123.45 -> 4123.45)
+        elif re.match(r"^\d{1,3}(,\d{3})*\.\d{1,2}$", value):
+            value = value.replace(",", "")
+
+        # English style integer with thousand separator: 2,500
+        elif re.match(r"^\d{1,3}(,\d{3})+$", value):
+            value = value.replace(",", "")
 
-    # European style integer with thousand separator: 2.500
-    elif re.match(r"^\d{1,3}(\.\d{3})+$", value):
-        value = value.replace(".", "")
+        # Just replace comma decimals with dot (e.g., 65,45 -> 65.45)
+        if re.match(r"^\d+,\d{1,2}$", value):
+            value = value.replace(",", ".")
 
-    # Format english values as well for consistency (e.g., 4,123.45 -> 4123.45)
-    elif re.match(r"^\d{1,3}(,\d{3})*\.\d{1,2}$", value):
-        value = value.replace(",", "")
+        # If there are more than 3 0s after decimal point, consider only 2 decimal points (e.g., 8.500000 -> 8.50)
+        elif re.match(r"^\d+\.\d{3,}$", value):
+            value = value[: value.index(".") + 3]
 
-    # English style integer with thousand separator: 2,500
-    elif re.match(r"^\d{1,3}(,\d{3})+$", value):
-        value = value.replace(",", "")
+    else:  # quantity=True → only last two
+        # Just replace comma decimals with dot (e.g., 65,45 -> 65.45)
+        if re.match(r"^\d+,\d{1,2}$", value):
+            value = value.replace(",", ".")
 
-    # Just replace comma decimals with dot (e.g., 65,45 -> 65.45)
-    elif re.match(r"^\d+,\d{1,2}$", value):
-        value = value.replace(",", ".")
+        # If there are more than 3 0s after decimal point, consider only 2 decimal points (e.g., 8.500000 -> 8.50)
+        elif re.match(r"^\d+\.\d{3,}$", value):
+            value = value[: value.index(".") + 3]
 
     return value