Extract Text: Add missing body parameters

Assisted-by: Codex

Author: datalogics-cgreen

src/pdfrest/client.py

@@ -2283,6 +2283,11 @@ def extract_text(
         file: PdfRestFile | Sequence[PdfRestFile],
         *,
         pages: PdfPageSelection | None = None,
+        full_text: Literal["off", "by_page", "document"] = "document",
+        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,
@@ -2294,6 +2299,11 @@ def extract_text(
         payload: dict[str, Any] = {"files": 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
 
@@ -3196,6 +3206,11 @@ async def extract_text(
         file: PdfRestFile | Sequence[PdfRestFile],
         *,
         pages: PdfPageSelection | None = None,
+        full_text: Literal["off", "by_page", "document"] = "document",
+        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,
@@ -3207,6 +3222,11 @@ async def extract_text(
         payload: dict[str, Any] = {"files": 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
 

src/pdfrest/models/_internal.py

@@ -343,6 +343,11 @@ class ExtractTextPayload(BaseModel):
         BeforeValidator(_int_to_string),
         PlainSerializer(_serialize_page_ranges),
     ] = None
+    full_text: Literal["off", "by_page", "document"] = "document"
+    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: Annotated[
         str | None,
         Field(serialization_alias="output", min_length=1, default=None),

tests/live/test_live_extract_text.py

@@ -18,7 +18,14 @@ 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(uploaded, output=None)
+        response = client.extract_text(
+            uploaded,
+            output_type="json",
+            full_text="document",
+            preserve_line_breaks="on",
+            word_style="off",
+            word_coordinates="off",
+        )
 
     assert isinstance(response, ExtractTextResponse)
     assert response.text
@@ -39,4 +46,5 @@ def test_live_extract_text_invalid_pages(
             client.extract_text(
                 uploaded,
                 extra_body={"pages": "last-1"},
+                output_type="json",
             )