Merge pull request #264537 from laujan/202682-error-in-python-code

202682 error in python code

Author: prmerger-automator[bot]

articles/ai-services/document-intelligence/quickstarts/includes/python-sdk.md

@@ -6,7 +6,7 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-document-intelligence
 ms.topic: include
-ms.date: 12/18/2023
+ms.date: 01/29/2024
 ms.author: lajanuar
 ---
 <!-- markdownlint-disable MD025 -->
@@ -135,11 +135,30 @@ Extract text, selection marks, text styles, table structures, and bounding regio
 import os
 from azure.core.credentials import AzureKeyCredential
 from azure.ai.documentintelligence import DocumentIntelligenceClient
+from azure.ai.documentintelligence.models import AnalyzeResult
 
 # set `<your-endpoint>` and `<your-key>` variables with the values from the Azure portal
 endpoint = "<your-endpoint>"
 key = "<your-key>"
 
+# helper functions
+
+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 analyze_layout():
     # sample document
@@ -152,9 +171,10 @@ def analyze_layout():
     poller = document_intelligence_client.begin_analyze_document_from_url(
         "prebuilt-layout", formUrl
     )
-    result = poller.result()
 
-    if any([style.is_handwritten for style in result.styles]):
+    result: AnalyzeResult = poller.result()
+
+    if result.styles and any([style.is_handwritten for style in result.styles]):
         print("Document contains handwritten content")
     else:
         print("Document does not contain handwritten content")
@@ -165,49 +185,53 @@ def analyze_layout():
             f"Page has width: {page.width} and height: {page.height}, measured with unit: {page.unit}"
         )
 
-        for line_idx, line in enumerate(page.lines):
-            words = get_words(page, line)
-            print(
-                f"...Line # {line_idx} has word count {len(words)} and text '{line.content}' "
-                f"within bounding polygon '{line.polygon}'"
-            )
-
-            for word in words:
+        if page.lines:
+            for line_idx, line in enumerate(page.lines):
+                words = get_words(page, line)
                 print(
-                    f"......Word '{word.content}' has a confidence of {word.confidence}"
+                    f"...Line # {line_idx} has word count {len(words)} and text '{line.content}' "
+                    f"within bounding polygon '{line.polygon}'"
                 )
 
-        for selection_mark in page.selection_marks:
-            print(
-                f"Selection mark is '{selection_mark.state}' within bounding polygon "
-                f"'{selection_mark.polygon}' and has a confidence of {selection_mark.confidence}"
-            )
+                for word in words:
+                    print(
+                        f"......Word '{word.content}' has a confidence of {word.confidence}"
+                    )
 
-    for table_idx, table in enumerate(result.tables):
-        print(
-            f"Table # {table_idx} has {table.row_count} rows and "
-            f"{table.column_count} columns"
-        )
-        for region in table.bounding_regions:
-            print(
-                f"Table # {table_idx} location on page: {region.page_number} is {region.polygon}"
-            )
-        for cell in table.cells:
+        if page.selection_marks:
+            for selection_mark in page.selection_marks:
+                print(
+                    f"Selection mark is '{selection_mark.state}' within bounding polygon "
+                    f"'{selection_mark.polygon}' and has a confidence of {selection_mark.confidence}"
+                )
+
+    if result.tables:
+        for table_idx, table in enumerate(result.tables):
             print(
-                f"...Cell[{cell.row_index}][{cell.column_index}] has text '{cell.content}'"
+                f"Table # {table_idx} has {table.row_count} rows and "
+                f"{table.column_count} columns"
             )
-            for region in cell.bounding_regions:
+            if table.bounding_regions:
+                for region in table.bounding_regions:
+                    print(
+                        f"Table # {table_idx} location on page: {region.page_number} is {region.polygon}"
+                    )
+            for cell in table.cells:
                 print(
-                    f"...content on page {region.page_number} is within bounding polygon '{region.polygon}'"
+                    f"...Cell[{cell.row_index}][{cell.column_index}] has text '{cell.content}'"
                 )
+                if cell.bounding_regions:
+                    for region in cell.bounding_regions:
+                        print(
+                            f"...content on page {region.page_number} is within bounding polygon '{region.polygon}'"
+                        )
 
     print("----------------------------------------")
 
 
 if __name__ == "__main__":
     analyze_layout()
 
-
 ```
 
 **Run the application**