Include helper functions in sample snippets

sdk/documentintelligence/azure-ai-documentintelligence/README.md

@@ -213,6 +213,29 @@ from azure.core.credentials import AzureKeyCredential
 from azure.ai.documentintelligence import DocumentIntelligenceClient
 from azure.ai.documentintelligence.models import AnalyzeResult
 
+def get_words(page, line):
+    result = []
+    for word in page.words:
+        if _in_span(word, line.spans):
+            result.append(word)
+    return result
+
+def _in_span(word, spans):
+    for span in spans:
+        if word.span.offset >= span.offset and (word.span.offset + word.span.length) <= (span.offset + span.length):
+            return True
+    return False
+
+def format_bounding_region(bounding_regions):
+    if not bounding_regions:
+        return "N/A"
+    return ", ".join(f"Page #{region.page_number}: {format_polygon(region.polygon)}" for region in bounding_regions)
+
+def format_polygon(polygon):
+    if not polygon:
+        return "N/A"
+    return ", ".join([f"[{polygon[i]}, {polygon[i + 1]}]" for i in range(0, len(polygon), 2)])
+
 endpoint = os.environ["DOCUMENTINTELLIGENCE_ENDPOINT"]
 key = os.environ["DOCUMENTINTELLIGENCE_API_KEY"]
 
@@ -296,6 +319,29 @@ from azure.core.credentials import AzureKeyCredential
 from azure.ai.documentintelligence import DocumentIntelligenceClient
 from azure.ai.documentintelligence.models import DocumentAnalysisFeature, AnalyzeResult
 
+def get_words(words, line):
+    result = []
+    for word in words:
+        if _in_span(word, line.spans):
+            result.append(word)
+    return result
+
+def _in_span(word, spans):
+    for span in spans:
+        if word.span.offset >= span.offset and (word.span.offset + word.span.length) <= (span.offset + span.length):
+            return True
+    return False
+
+def format_bounding_region(bounding_regions):
+    if not bounding_regions:
+        return "N/A"
+    return ", ".join(f"Page #{region.page_number}: {format_polygon(region.polygon)}" for region in bounding_regions)
+
+def format_polygon(polygon):
+    if not polygon:
+        return "N/A"
+    return ", ".join([f"[{polygon[i]}, {polygon[i + 1]}]" for i in range(0, len(polygon), 2)])
+
 endpoint = os.environ["DOCUMENTINTELLIGENCE_ENDPOINT"]
 key = os.environ["DOCUMENTINTELLIGENCE_API_KEY"]
 
@@ -388,6 +434,9 @@ from azure.core.credentials import AzureKeyCredential
 from azure.ai.documentintelligence import DocumentIntelligenceClient
 from azure.ai.documentintelligence.models import AnalyzeResult
 
+def format_price(price_dict):
+    return "".join([f"{p}" for p in price_dict.values()])
+
 endpoint = os.environ["DOCUMENTINTELLIGENCE_ENDPOINT"]
 key = os.environ["DOCUMENTINTELLIGENCE_API_KEY"]
 
@@ -525,6 +574,33 @@ from azure.core.credentials import AzureKeyCredential
 from azure.ai.documentintelligence import DocumentIntelligenceClient
 from azure.ai.documentintelligence.models import AnalyzeResult
 
+def print_table(header_names, table_data):
+    """Print a two-dimensional array like a table.
+
+    Based on provided column header names and two two-dimensional array data, print the strings like table.
+
+    Args:
+        header_names: An array of string, it's the column header names.  e.g. ["name", "gender", "age"]
+        table_data: A two-dimensional array, they're the table data.  e.g. [["Mike", "M", 25], ["John", "M", 19], ["Lily", "F", 23]]
+    Return: None
+        It's will print the string like table in output window. e.g.
+        Name    Gender    Age
+        Mike    M         25
+        John    M         19
+        Lily    F         23
+    """
+    max_len_list = []
+    for i in range(len(header_names)):
+        col_values = list(map(lambda row: len(str(row[i])), table_data))
+        col_values.append(len(str(header_names[i])))
+        max_len_list.append(max(col_values))
+
+    row_format_str = "".join(map(lambda len: f"{{:<{len + 4}}}", max_len_list))
+
+    print(row_format_str.format(*header_names))
+    for row in table_data:
+        print(row_format_str.format(*row))
+
 endpoint = os.environ["DOCUMENTINTELLIGENCE_ENDPOINT"]
 key = os.environ["DOCUMENTINTELLIGENCE_API_KEY"]
 model_id = os.getenv("CUSTOM_BUILT_MODEL_ID", custom_model_id)
@@ -561,10 +637,7 @@ if result.documents:
         if not doc.fields is None:
             for field_name, field_value in doc.fields.items():
                 # Dynamic Table cell information store as array in document field.
-                if (
-                    field_value.type == SYMBOL_OF_TABLE_TYPE
-                    and field_value.value_array
-                ):
+                if field_value.type == SYMBOL_OF_TABLE_TYPE and field_value.value_array:
                     col_names = []
                     sample_obj = field_value.value_array[0]
                     if KEY_OF_VALUE_OBJECT in sample_obj:
@@ -582,7 +655,7 @@ if result.documents:
                             row_data = list(map(extract_value_by_col_name, col_names))
                             table_rows.append(row_data)
                     print_table(col_names, table_rows)
-                
+
                 elif (
                     field_value.type == SYMBOL_OF_OBJECT_TYPE
                     and KEY_OF_VALUE_OBJECT in field_value
@@ -592,9 +665,7 @@ if result.documents:
                     is_fixed_table = all(
                         (
                             rows_of_column["type"] == SYMBOL_OF_OBJECT_TYPE
-                            and Counter(
-                                list(rows_by_columns[0][KEY_OF_VALUE_OBJECT].keys())
-                            )
+                            and Counter(list(rows_by_columns[0][KEY_OF_VALUE_OBJECT].keys()))
                             == Counter(list(rows_of_column[KEY_OF_VALUE_OBJECT].keys()))
                         )
                         for rows_of_column in rows_by_columns
@@ -609,9 +680,7 @@ if result.documents:
                             rows = rows_of_column[KEY_OF_VALUE_OBJECT]
                             for row_key in list(rows.keys()):
                                 if row_key in row_dict:
-                                    row_dict[row_key].append(
-                                        rows[row_key].get(KEY_OF_CELL_CONTENT)
-                                    )
+                                    row_dict[row_key].append(rows[row_key].get(KEY_OF_CELL_CONTENT))
                                 else:
                                     row_dict[row_key] = [
                                         row_key,
@@ -635,6 +704,9 @@ from azure.core.credentials import AzureKeyCredential
 from azure.ai.documentintelligence import DocumentIntelligenceClient
 from azure.ai.documentintelligence.models import AnalyzeDocumentRequest, AnalyzeResult
 
+def format_price(price_dict):
+    return "".join([f"{p}" for p in price_dict.values()])
+
 endpoint = os.environ["DOCUMENTINTELLIGENCE_ENDPOINT"]
 key = os.environ["DOCUMENTINTELLIGENCE_API_KEY"]
 

sdk/documentintelligence/azure-ai-documentintelligence/samples/aio/sample_analyze_addon_barcodes_async.py

@@ -58,7 +58,6 @@ async def analyze_barcodes():
             "sample_forms/add_ons/barcodes.jpg",
         )
     )
-    # [START analyze_barcodes]
     from azure.core.credentials import AzureKeyCredential
     from azure.ai.documentintelligence.aio import DocumentIntelligenceClient
     from azure.ai.documentintelligence.models import DocumentAnalysisFeature, AnalyzeResult
@@ -91,7 +90,6 @@ async def analyze_barcodes():
                 print(f"  Bounding regions: {format_polygon(barcode.polygon)}")
 
     print("----------------------------------------")
-    # [END analyze_barcodes]
 
 
 async def main():

sdk/documentintelligence/azure-ai-documentintelligence/samples/aio/sample_analyze_addon_fonts_async.py

@@ -60,7 +60,6 @@ async def analyze_fonts():
             "sample_forms/add_ons/fonts_and_languages.png",
         )
     )
-    # [START analyze_fonts]
     from azure.core.credentials import AzureKeyCredential
     from azure.ai.documentintelligence.aio import DocumentIntelligenceClient
     from azure.ai.documentintelligence.models import DocumentAnalysisFeature, AnalyzeResult
@@ -134,7 +133,6 @@ async def analyze_fonts():
         print(f"  Text: '{get_styled_text(styles, result.content)}'")
 
     print("----------------------------------------")
-    # [END analyze_fonts]
 
 
 async def main():

sdk/documentintelligence/azure-ai-documentintelligence/samples/aio/sample_analyze_addon_formulas_async.py

@@ -58,7 +58,6 @@ async def analyze_formulas():
             "sample_forms/add_ons/formulas.pdf",
         )
     )
-    # [START analyze_formulas]
     from azure.core.credentials import AzureKeyCredential
     from azure.ai.documentintelligence.aio import DocumentIntelligenceClient
     from azure.ai.documentintelligence.models import DocumentAnalysisFeature, AnalyzeResult
@@ -100,7 +99,6 @@ async def analyze_formulas():
                 print(f"  Bounding regions: {format_polygon(formula.polygon)}")
 
     print("----------------------------------------")
-    # [END analyze_formulas]
 
 
 async def main():

sdk/documentintelligence/azure-ai-documentintelligence/samples/aio/sample_analyze_addon_highres_async.py

@@ -73,7 +73,6 @@ async def analyze_with_highres():
             "sample_forms/add_ons/highres.png",
         )
     )
-    # [START analyze_with_highres]
     from azure.core.credentials import AzureKeyCredential
     from azure.ai.documentintelligence.aio import DocumentIntelligenceClient
     from azure.ai.documentintelligence.models import DocumentAnalysisFeature, AnalyzeResult
@@ -139,7 +138,6 @@ async def analyze_with_highres():
                         )
 
     print("----------------------------------------")
-    # [END analyze_with_highres]
 
 
 async def main():

sdk/documentintelligence/azure-ai-documentintelligence/samples/aio/sample_analyze_addon_languages_async.py

@@ -52,7 +52,6 @@ async def analyze_languages():
             "sample_forms/add_ons/fonts_and_languages.png",
         )
     )
-    # [START analyze_languages]
     from azure.core.credentials import AzureKeyCredential
     from azure.ai.documentintelligence.aio import DocumentIntelligenceClient
     from azure.ai.documentintelligence.models import DocumentAnalysisFeature, AnalyzeResult
@@ -84,7 +83,6 @@ async def analyze_languages():
             )
 
     print("----------------------------------------")
-    # [END analyze_languages]
 
 
 async def main():

sdk/documentintelligence/azure-ai-documentintelligence/samples/aio/sample_analyze_addon_query_fields_async.py

@@ -44,7 +44,6 @@
 
 
 async def analyze_query_fields():
-    # [START analyze_query_fields]
     from azure.core.credentials import AzureKeyCredential
     from azure.ai.documentintelligence.aio import DocumentIntelligenceClient
     from azure.ai.documentintelligence.models import AnalyzeDocumentRequest, DocumentAnalysisFeature, AnalyzeResult
@@ -71,7 +70,6 @@ async def analyze_query_fields():
                 print(f"Address: {doc.fields['Address'].value_string}")
             if doc.fields and doc.fields["InvoiceNumber"]:
                 print(f"Invoice number: {doc.fields['InvoiceNumber'].value_string}")
-    # [END analyze_query_fields]
 
 
 async def main():

sdk/documentintelligence/azure-ai-documentintelligence/samples/aio/sample_analyze_custom_documents_async.py

@@ -71,7 +71,6 @@ async def analyze_custom_documents(custom_model_id):
     path_to_sample_documents = os.path.abspath(
         os.path.join(os.path.abspath(__file__), "..", "..", "./sample_forms/forms/Form_1.jpg")
     )
-    # [START analyze_custom_documents]
     from azure.core.credentials import AzureKeyCredential
     from azure.ai.documentintelligence.aio import DocumentIntelligenceClient
     from azure.ai.documentintelligence.models import AnalyzeResult
@@ -172,7 +171,6 @@ async def analyze_custom_documents(custom_model_id):
                             col_names.insert(0, "")
                             print_table(col_names, list(row_dict.values()))
     print("-----------------------------------")
-    # [END analyze_custom_documents]
 
 
 async def main():

sdk/documentintelligence/azure-ai-documentintelligence/samples/aio/sample_analyze_documents_output_in_markdown_async.py

@@ -25,7 +25,6 @@
 
 
 async def analyze_documents_output_in_markdown():
-    # [START analyze_documents_output_in_markdown]
     from azure.core.credentials import AzureKeyCredential
     from azure.ai.documentintelligence.aio import DocumentIntelligenceClient
     from azure.ai.documentintelligence.models import AnalyzeDocumentRequest, ContentFormat, AnalyzeResult
@@ -45,7 +44,6 @@ async def analyze_documents_output_in_markdown():
 
     print(f"Here's the full content in format {result.content_format}:\n")
     print(result.content)
-    # [END analyze_documents_output_in_markdown]
 
 
 async def main():

sdk/documentintelligence/azure-ai-documentintelligence/samples/aio/sample_analyze_general_documents_async.py

@@ -62,7 +62,6 @@ async def analyze_general_documents():
         )
     )
 
-    # [START analyze_general_documents]
     from azure.core.credentials import AzureKeyCredential
     from azure.ai.documentintelligence.aio import DocumentIntelligenceClient
     from azure.ai.documentintelligence.models import DocumentAnalysisFeature, AnalyzeResult
@@ -141,7 +140,6 @@ async def analyze_general_documents():
                             f"...content on page {region.page_number} is within bounding polygon '{format_polygon(region.polygon)}'\n"
                         )
     print("----------------------------------------")
-    # [END analyze_general_documents]
 
 
 async def main():

sdk/documentintelligence/azure-ai-documentintelligence/samples/aio/sample_analyze_invoices_async.py

@@ -37,7 +37,6 @@ async def analyze_invoice():
         )
     )
 
-    # [START analyze_invoices]
     from azure.core.credentials import AzureKeyCredential
     from azure.ai.documentintelligence.aio import DocumentIntelligenceClient
     from azure.ai.documentintelligence.models import AnalyzeResult
@@ -217,7 +216,6 @@ async def analyze_invoice():
                     print(
                         f"Remittance Address Recipient: {remittance_address_recipient.get('content')} has confidence: {remittance_address_recipient.get('confidence')}"
                     )
-    # [END analyze_invoices]
 
 
 async def main():

sdk/documentintelligence/azure-ai-documentintelligence/samples/aio/sample_analyze_layout_async.py

@@ -66,7 +66,6 @@ async def analyze_layout():
         )
     )
 
-    # [START extract_layout]
     from azure.core.credentials import AzureKeyCredential
     from azure.ai.documentintelligence.aio import DocumentIntelligenceClient
     from azure.ai.documentintelligence.models import AnalyzeResult
@@ -139,7 +138,6 @@ async def analyze_layout():
                         )
 
     print("----------------------------------------")
-    # [END extract_layout]
 
 
 async def main():

sdk/documentintelligence/azure-ai-documentintelligence/samples/aio/sample_analyze_receipts_async.py

@@ -42,7 +42,6 @@ async def analyze_receipts():
         )
     )
 
-    # [START analyze_receipts]
     from azure.core.credentials import AzureKeyCredential
     from azure.ai.documentintelligence.aio import DocumentIntelligenceClient
     from azure.ai.documentintelligence.models import AnalyzeResult
@@ -113,7 +112,6 @@ async def analyze_receipts():
                 if total:
                     print(f"Total: {format_price(total.get('valueCurrency'))} has confidence: {total.confidence}")
         print("--------------------------------------")
-    # [END analyze_receipts]
 
 
 async def main():

sdk/documentintelligence/azure-ai-documentintelligence/samples/aio/sample_analyze_receipts_from_url_async.py

@@ -33,7 +33,6 @@ def format_price(price_dict):
 
 
 async def analyze_receipts_from_url():
-    # [START analyze_receipts_from_url]
     from azure.core.credentials import AzureKeyCredential
     from azure.ai.documentintelligence.aio import DocumentIntelligenceClient
     from azure.ai.documentintelligence.models import AnalyzeDocumentRequest, AnalyzeResult
@@ -48,7 +47,6 @@ async def analyze_receipts_from_url():
             "prebuilt-receipt", AnalyzeDocumentRequest(url_source=url)
         )
         receipts: AnalyzeResult = await poller.result()
-    # [END analyze_receipts_from_url]
 
     if receipts.documents:
         for idx, receipt in enumerate(receipts.documents):

sdk/documentintelligence/azure-ai-documentintelligence/samples/aio/sample_classify_document_async.py

@@ -42,7 +42,6 @@ async def classify_document(classifier_id):
         )
     )
 
-    # [START classify_document]
     from azure.core.credentials import AzureKeyCredential
     from azure.ai.documentintelligence.aio import DocumentIntelligenceClient
     from azure.ai.documentintelligence.models import AnalyzeResult
@@ -67,7 +66,6 @@ async def classify_document(classifier_id):
                     f"Found document of type '{doc.doc_type or 'N/A'}' with a confidence of {doc.confidence} contained on "
                     f"the following pages: {[region.page_number for region in doc.bounding_regions]}"
                 )
-    # [END classify_document]
 
 
 async def main():

sdk/documentintelligence/azure-ai-documentintelligence/samples/aio/sample_compose_model_async.py

@@ -37,7 +37,6 @@
 
 
 async def sample_compose_model():
-    # [START composed_model]
     import uuid
     from azure.core.credentials import AzureKeyCredential
     from azure.ai.documentintelligence.aio import DocumentIntelligenceAdministrationClient
@@ -128,7 +127,6 @@ async def sample_compose_model():
         print("Warnings encountered while building the model:")
         for warning in model.warnings:
             print(f"warning code: {warning.code}, message: {warning.message}, target of the error: {warning.target}")
-    # [END composed_model]
 
 
 async def main():