Merge branch 'main' into release-please--branches--main

google/cloud/documentai_toolbox/wrappers/page.py

@@ -79,37 +79,6 @@ def to_dataframe(self) -> pd.DataFrame:
 
         return pd.DataFrame(self.body_rows, columns=columns)
 
-    def to_csv(self) -> str:
-        r"""Returns a csv str.
-
-            .. code-block:: python
-
-                from google.cloud.documentai_toolbox import Document
-
-                def sample_table_to_csv():
-
-                    #Wrap document from gcs_path
-                    merged_document = Document('gs://abc/def/gh/1')
-
-                    #Use first page
-                    page = merged_document.pages[0]
-
-                    #export the first table in page 1 to csv
-                    csv_text = page.tables[0].to_csv()
-
-                    print(csv_text)
-
-        Args:
-            dataframe (pd.Dataframe):
-                Required. Two-dimensional, size-mutable, potentially heterogeneous tabular data.
-
-        Returns:
-            str:
-                The table in csv format.
-
-        """
-        return self.to_dataframe().to_csv(index=False)
-
 
 @dataclasses.dataclass
 class FormField:

samples/snippets/table_sample.py

@@ -30,11 +30,21 @@ def table_sample(document_path: str, output_file_prefix: str) -> None:
     print("Tables in Document")
     for page in wrapped_document.pages:
         for table_index, table in enumerate(page.tables):
-            print(table.to_dataframe())
-            # Write table to CSV file
-            output_file = f"{output_file_prefix}-{page.page_number}-{table_index}.csv"
-            with open(output_file, "w", encoding="utf-8") as f:
-                f.write(table.to_csv())
+            # Convert table to Pandas Dataframe
+            # Refer to https://pandas.pydata.org/docs/reference/frame.html for all supported methods
+            df = table.to_dataframe()
+            print(df)
+
+            output_filename = f"{output_file_prefix}-{page.page_number}-{table_index}"
+
+            # Write Dataframe to CSV file
+            df.to_csv(f"{output_filename}.csv", index=False)
+
+            # Write Dataframe to HTML file
+            df.to_html(f"{output_filename}.html", index=False)
+
+            # Write Dataframe to Markdown file
+            df.to_markdown(f"{output_filename}.md", index=False)
 
 
 # [END documentai_toolbox_table]

setup.py

@@ -50,6 +50,7 @@
         "google-api-core >= 1.31.5, <3.0.0dev,!=2.0.*,!=2.1.*,!=2.2.*,!=2.3.0",
         "pandas >= 1.0.0, <3.0.0",
         "pandas >= 1.0.0, <2.0.0; python_version<'3.8'",
+        "tabulate >= 0.9.0, <1.0.0",
         "proto-plus >= 1.22.0, <2.0.0dev",
         "proto-plus >= 1.22.2, <2.0.0dev; python_version>='3.11'",
         "grpc-google-iam-v1 >= 0.12.4, < 0.13dev",

tests/unit/test_page.py

@@ -46,7 +46,7 @@ def test_table_to_csv(docproto):
         documentai_object=docproto_page.tables[0], document_text=docproto.text
     )
 
-    contents = table.to_csv()
+    contents = table.to_dataframe().to_csv(index=False)
 
     assert (
         contents
@@ -68,7 +68,7 @@ def test_table_to_csv_with_empty_body_rows(docproto):
     )
     table.body_rows = None
 
-    contents = table.to_csv()
+    contents = table.to_dataframe().to_csv(index=False)
 
     assert (
         contents
@@ -84,7 +84,7 @@ def test_table_to_csv_with_empty_header_rows(docproto):
     )
     table.header_rows = None
 
-    contents = table.to_csv()
+    contents = table.to_dataframe().to_csv(index=False)
 
     assert (
         contents
@@ -107,7 +107,7 @@ def test_table_to_csv_with_empty_header_rows_and_single_body(docproto):
     table.header_rows = []
     table.body_rows = [[table.body_rows[0][0]]]
 
-    contents = table.to_csv()
+    contents = table.to_dataframe().to_csv(index=False)
     assert (
         contents
         == """""