PDFCLOUD-5463 Add PDF/X, Flatten Forms, and Word

src/pdfrest/client.py

@@ -73,12 +73,15 @@
     BmpPdfRestPayload,
     GifPdfRestPayload,
     JpegPdfRestPayload,
+    PdfFlattenFormsPayload,
     PdfInfoPayload,
     PdfMergePayload,
     PdfRedactionApplyPayload,
     PdfRedactionPreviewPayload,
     PdfRestRawFileResponse,
     PdfSplitPayload,
+    PdfToPdfxPayload,
+    PdfToWordPayload,
     PngPdfRestPayload,
     TiffPdfRestPayload,
     UploadURLs,
@@ -90,6 +93,7 @@
     PdfPageSelection,
     PdfRedactionInstruction,
     PdfRGBColor,
+    PdfXType,
 )
 
 DEFAULT_BASE_URL = "https://api.pdfrest.com"
@@ -2141,6 +2145,85 @@ def merge_pdfs(
             timeout=timeout,
         )
 
+    def convert_to_word(
+        self,
+        file: PdfRestFile | Sequence[PdfRestFile],
+        *,
+        output: str | None = None,
+        extra_query: Query | None = None,
+        extra_headers: AnyMapping | None = None,
+        extra_body: Body | None = None,
+        timeout: TimeoutTypes | None = None,
+    ) -> PdfRestFileBasedResponse:
+        """Convert a PDF to a Word document."""
+
+        payload: dict[str, Any] = {"files": file}
+        if output is not None:
+            payload["output"] = output
+
+        return self._post_file_operation(
+            endpoint="/word",
+            payload=payload,
+            payload_model=PdfToWordPayload,
+            extra_query=extra_query,
+            extra_headers=extra_headers,
+            extra_body=extra_body,
+            timeout=timeout,
+        )
+
+    def flatten_pdf_forms(
+        self,
+        file: PdfRestFile | Sequence[PdfRestFile],
+        *,
+        output: str | None = None,
+        extra_query: Query | None = None,
+        extra_headers: AnyMapping | None = None,
+        extra_body: Body | None = None,
+        timeout: TimeoutTypes | None = None,
+    ) -> PdfRestFileBasedResponse:
+        """Flatten form fields in a PDF so they are no longer editable."""
+
+        payload: dict[str, Any] = {"files": file}
+        if output is not None:
+            payload["output"] = output
+
+        return self._post_file_operation(
+            endpoint="/flattened-forms-pdf",
+            payload=payload,
+            payload_model=PdfFlattenFormsPayload,
+            extra_query=extra_query,
+            extra_headers=extra_headers,
+            extra_body=extra_body,
+            timeout=timeout,
+        )
+
+    def convert_to_pdfx(
+        self,
+        file: PdfRestFile | Sequence[PdfRestFile],
+        *,
+        output_type: PdfXType,
+        output: str | None = None,
+        extra_query: Query | None = None,
+        extra_headers: AnyMapping | None = None,
+        extra_body: Body | None = None,
+        timeout: TimeoutTypes | None = None,
+    ) -> PdfRestFileBasedResponse:
+        """Convert a PDF to a specified PDF/X version."""
+
+        payload: dict[str, Any] = {"files": file, "output_type": output_type}
+        if output is not None:
+            payload["output"] = output
+
+        return self._post_file_operation(
+            endpoint="/pdfx",
+            payload=payload,
+            payload_model=PdfToPdfxPayload,
+            extra_query=extra_query,
+            extra_headers=extra_headers,
+            extra_body=extra_body,
+            timeout=timeout,
+        )
+
     def convert_to_png(
         self,
         files: PdfRestFile | Sequence[PdfRestFile],
@@ -2572,6 +2655,85 @@ async def merge_pdfs(
             timeout=timeout,
         )
 
+    async def convert_to_word(
+        self,
+        file: PdfRestFile | Sequence[PdfRestFile],
+        *,
+        output: str | None = None,
+        extra_query: Query | None = None,
+        extra_headers: AnyMapping | None = None,
+        extra_body: Body | None = None,
+        timeout: TimeoutTypes | None = None,
+    ) -> PdfRestFileBasedResponse:
+        """Asynchronously convert a PDF to a Word document."""
+
+        payload: dict[str, Any] = {"files": file}
+        if output is not None:
+            payload["output"] = output
+
+        return await self._post_file_operation(
+            endpoint="/word",
+            payload=payload,
+            payload_model=PdfToWordPayload,
+            extra_query=extra_query,
+            extra_headers=extra_headers,
+            extra_body=extra_body,
+            timeout=timeout,
+        )
+
+    async def flatten_pdf_forms(
+        self,
+        file: PdfRestFile | Sequence[PdfRestFile],
+        *,
+        output: str | None = None,
+        extra_query: Query | None = None,
+        extra_headers: AnyMapping | None = None,
+        extra_body: Body | None = None,
+        timeout: TimeoutTypes | None = None,
+    ) -> PdfRestFileBasedResponse:
+        """Asynchronously flatten form fields in a PDF."""
+
+        payload: dict[str, Any] = {"files": file}
+        if output is not None:
+            payload["output"] = output
+
+        return await self._post_file_operation(
+            endpoint="/flattened-forms-pdf",
+            payload=payload,
+            payload_model=PdfFlattenFormsPayload,
+            extra_query=extra_query,
+            extra_headers=extra_headers,
+            extra_body=extra_body,
+            timeout=timeout,
+        )
+
+    async def convert_to_pdfx(
+        self,
+        file: PdfRestFile | Sequence[PdfRestFile],
+        *,
+        output_type: PdfXType,
+        output: str | None = None,
+        extra_query: Query | None = None,
+        extra_headers: AnyMapping | None = None,
+        extra_body: Body | None = None,
+        timeout: TimeoutTypes | None = None,
+    ) -> PdfRestFileBasedResponse:
+        """Asynchronously convert a PDF to a specified PDF/X version."""
+
+        payload: dict[str, Any] = {"files": file, "output_type": output_type}
+        if output is not None:
+            payload["output"] = output
+
+        return await self._post_file_operation(
+            endpoint="/pdfx",
+            payload=payload,
+            payload_model=PdfToPdfxPayload,
+            extra_query=extra_query,
+            extra_headers=extra_headers,
+            extra_body=extra_body,
+            timeout=timeout,
+        )
+
     async def convert_to_png(
         self,
         files: PdfRestFile | Sequence[PdfRestFile],

src/pdfrest/models/_internal.py

@@ -21,7 +21,7 @@
 
 from pdfrest.types.public import PdfRedactionPreset
 
-from ..types import PdfInfoQuery
+from ..types import PdfInfoQuery, PdfXType
 from . import PdfRestFile
 from .public import PdfRestFileID
 
@@ -476,6 +476,79 @@ def _serialize_pdf_merge_payload(
         return payload
 
 
+class PdfToWordPayload(BaseModel):
+    """Adapt caller options into a pdfRest-ready Word request payload."""
+
+    files: Annotated[
+        list[PdfRestFile],
+        Field(
+            min_length=1,
+            max_length=1,
+            validation_alias=AliasChoices("file", "files"),
+            serialization_alias="id",
+        ),
+        BeforeValidator(_ensure_list),
+        AfterValidator(
+            _allowed_mime_types("application/pdf", error_msg="Must be a PDF file")
+        ),
+        PlainSerializer(_serialize_as_first_file_id),
+    ]
+    output: Annotated[
+        str | None,
+        Field(serialization_alias="output", min_length=1, default=None),
+        AfterValidator(_validate_output_prefix),
+    ] = None
+
+
+class PdfToPdfxPayload(BaseModel):
+    """Adapt caller options into a pdfRest-ready PDF/X request payload."""
+
+    files: Annotated[
+        list[PdfRestFile],
+        Field(
+            min_length=1,
+            max_length=1,
+            validation_alias=AliasChoices("file", "files"),
+            serialization_alias="id",
+        ),
+        BeforeValidator(_ensure_list),
+        AfterValidator(
+            _allowed_mime_types("application/pdf", error_msg="Must be a PDF file")
+        ),
+        PlainSerializer(_serialize_as_first_file_id),
+    ]
+    output_type: Annotated[PdfXType, Field(serialization_alias="output_type")]
+    output: Annotated[
+        str | None,
+        Field(serialization_alias="output", min_length=1, default=None),
+        AfterValidator(_validate_output_prefix),
+    ] = None
+
+
+class PdfFlattenFormsPayload(BaseModel):
+    """Adapt caller options into a pdfRest-ready flatten-forms request payload."""
+
+    files: Annotated[
+        list[PdfRestFile],
+        Field(
+            min_length=1,
+            max_length=1,
+            validation_alias=AliasChoices("file", "files"),
+            serialization_alias="id",
+        ),
+        BeforeValidator(_ensure_list),
+        AfterValidator(
+            _allowed_mime_types("application/pdf", error_msg="Must be a PDF file")
+        ),
+        PlainSerializer(_serialize_as_first_file_id),
+    ]
+    output: Annotated[
+        str | None,
+        Field(serialization_alias="output", min_length=1, default=None),
+        AfterValidator(_validate_output_prefix),
+    ] = None
+
+
 class BmpPdfRestPayload(BasePdfRestGraphicPayload[Literal["rgb", "gray"]]):
     """Adapt caller options into a pdfRest-ready BMP request payload."""
 

src/pdfrest/types/__init__.py

@@ -10,6 +10,7 @@
     PdfRedactionPreset,
     PdfRedactionType,
     PdfRGBColor,
+    PdfXType,
 )
 
 __all__ = [
@@ -22,4 +23,5 @@
     "PdfRedactionInstruction",
     "PdfRedactionPreset",
     "PdfRedactionType",
+    "PdfXType",
 ]

src/pdfrest/types/public.py

@@ -22,6 +22,7 @@
     "PdfRedactionInstruction",
     "PdfRedactionPreset",
     "PdfRedactionType",
+    "PdfXType",
 )
 
 PdfInfoQuery = Literal[
@@ -96,3 +97,5 @@ class PdfMergeSource(TypedDict, total=False):
 
 
 PdfMergeInput = PdfRestFile | PdfMergeSource | tuple[PdfRestFile, PdfPageSelection]
+
+PdfXType = Literal["PDF/X-1a", "PDF/X-3", "PDF/X-4", "PDF/X-6"]