Revise and rename extract_text to extract_pdf_text_to_file

- Fix `output_type` to "file"
- Use `PdfRestFileBasedResponse`
- Remove `ExtractTextResponse`

Assisted-by: Codex

Author: datalogics-cgreen

src/pdfrest/client.py

@@ -61,7 +61,6 @@
 )
 from .models import (
     ConvertToMarkdownResponse,
-    ExtractTextResponse,
     PdfRestDeletionResponse,
     PdfRestErrorResponse,
     PdfRestFile,
@@ -2395,7 +2394,7 @@ def extract_images(
             timeout=timeout,
         )
 
-    def extract_text(
+    def extract_pdf_text_to_file(
         self,
         file: PdfRestFile | Sequence[PdfRestFile],
         *,
@@ -2404,40 +2403,36 @@ def extract_text(
         preserve_line_breaks: Literal["off", "on"] = "off",
         word_style: Literal["off", "on"] = "off",
         word_coordinates: Literal["off", "on"] = "off",
-        output_type: Literal["json", "file"] = "json",
         output: str | None = None,
         extra_query: Query | None = None,
         extra_headers: AnyMapping | None = None,
         extra_body: Body | None = None,
         timeout: TimeoutTypes | None = None,
-    ) -> ExtractTextResponse:
-        """Extract text content from a PDF."""
+    ) -> PdfRestFileBasedResponse:
+        """Extract text content from a PDF and return a file-based response."""
 
-        payload: dict[str, Any] = {"files": file}
+        payload: dict[str, Any] = {
+            "files": file,
+            "full_text": full_text,
+            "preserve_line_breaks": preserve_line_breaks,
+            "word_style": word_style,
+            "word_coordinates": word_coordinates,
+            "output_type": "file",
+        }
         if pages is not None:
             payload["pages"] = pages
-        payload["full_text"] = full_text
-        payload["preserve_line_breaks"] = preserve_line_breaks
-        payload["word_style"] = word_style
-        payload["word_coordinates"] = word_coordinates
-        payload["output_type"] = output_type
         if output is not None:
             payload["output"] = output
 
-        validated_payload = ExtractTextPayload.model_validate(payload)
-        request = self.prepare_request(
-            "POST",
-            "/extracted-text",
-            json_body=validated_payload.model_dump(
-                mode="json", by_alias=True, exclude_none=True, exclude_unset=True
-            ),
+        return self._post_file_operation(
+            endpoint="/extracted-text",
+            payload=payload,
+            payload_model=ExtractTextPayload,
             extra_query=extra_query,
             extra_headers=extra_headers,
             extra_body=extra_body,
             timeout=timeout,
         )
-        raw_payload = self._send_request(request)
-        return ExtractTextResponse.model_validate(raw_payload)
 
     def preview_redactions(
         self,
@@ -3385,7 +3380,7 @@ async def extract_images(
             timeout=timeout,
         )
 
-    async def extract_text(
+    async def extract_pdf_text_to_file(
         self,
         file: PdfRestFile | Sequence[PdfRestFile],
         *,
@@ -3394,40 +3389,36 @@ async def extract_text(
         preserve_line_breaks: Literal["off", "on"] = "off",
         word_style: Literal["off", "on"] = "off",
         word_coordinates: Literal["off", "on"] = "off",
-        output_type: Literal["json", "file"] = "json",
         output: str | None = None,
         extra_query: Query | None = None,
         extra_headers: AnyMapping | None = None,
         extra_body: Body | None = None,
         timeout: TimeoutTypes | None = None,
-    ) -> ExtractTextResponse:
-        """Extract text content from a PDF."""
+    ) -> PdfRestFileBasedResponse:
+        """Extract text content from a PDF and return a file-based response."""
 
-        payload: dict[str, Any] = {"files": file}
+        payload: dict[str, Any] = {
+            "files": file,
+            "full_text": full_text,
+            "preserve_line_breaks": preserve_line_breaks,
+            "word_style": word_style,
+            "word_coordinates": word_coordinates,
+            "output_type": "file",
+        }
         if pages is not None:
             payload["pages"] = pages
-        payload["full_text"] = full_text
-        payload["preserve_line_breaks"] = preserve_line_breaks
-        payload["word_style"] = word_style
-        payload["word_coordinates"] = word_coordinates
-        payload["output_type"] = output_type
         if output is not None:
             payload["output"] = output
 
-        validated_payload = ExtractTextPayload.model_validate(payload)
-        request = self.prepare_request(
-            "POST",
-            "/extracted-text",
-            json_body=validated_payload.model_dump(
-                mode="json", by_alias=True, exclude_none=True, exclude_unset=True
-            ),
+        return await self._post_file_operation(
+            endpoint="/extracted-text",
+            payload=payload,
+            payload_model=ExtractTextPayload,
             extra_query=extra_query,
             extra_headers=extra_headers,
             extra_body=extra_body,
             timeout=timeout,
         )
-        raw_payload = await self._send_request(request)
-        return ExtractTextResponse.model_validate(raw_payload)
 
     async def preview_redactions(
         self,

tests/live/test_live_extract_text.py …ve/test_live_extract_pdf_text_to_file.pytests/live/test_live_extract_text.py renamed to tests/live/test_live_extract_pdf_text_to_file.py tests/live/test_live_extract_text.py renamed to tests/live/test_live_extract_pdf_text_to_file.py

@@ -3,12 +3,12 @@
 import pytest
 
 from pdfrest import PdfRestApiError, PdfRestClient
-from pdfrest.models import ExtractTextResponse
+from pdfrest.models import PdfRestFileBasedResponse
 
 from ..resources import get_test_resource_path
 
 
-def test_live_extract_text_success(
+def test_live_extract_pdf_text_to_file_success(
     pdfrest_api_key: str,
     pdfrest_live_base_url: str,
 ) -> None:
@@ -18,21 +18,20 @@ def test_live_extract_text_success(
         base_url=pdfrest_live_base_url,
     ) as client:
         uploaded = client.files.create_from_paths([resource])[0]
-        response = client.extract_text(
+        response = client.extract_pdf_text_to_file(
             uploaded,
-            output_type="json",
             full_text="document",
             preserve_line_breaks="on",
             word_style="off",
             word_coordinates="off",
         )
 
-    assert isinstance(response, ExtractTextResponse)
-    assert response.full_text
+    assert isinstance(response, PdfRestFileBasedResponse)
+    assert response.output_files
     assert response.input_id == uploaded.id
 
 
-def test_live_extract_text_invalid_pages(
+def test_live_extract_pdf_text_to_file_invalid_pages(
     pdfrest_api_key: str,
     pdfrest_live_base_url: str,
 ) -> None:
@@ -43,8 +42,7 @@ def test_live_extract_text_invalid_pages(
     ) as client:
         uploaded = client.files.create_from_paths([resource])[0]
         with pytest.raises(PdfRestApiError):
-            client.extract_text(
+            client.extract_pdf_text_to_file(
                 uploaded,
                 extra_body={"pages": "last-1"},
-                output_type="json",
             )