PyPDFForm 4.2.0__tar.gz → 4.2.2__tar.gz

{pypdfform-4.2.0 → pypdfform-4.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: PyPDFForm
-Version: 4.2.0
+Version: 4.2.2
 Summary: The Python library for PDF forms.
 Author: Jinge Li
 License-Expression: MIT

{pypdfform-4.2.0 → pypdfform-4.2.2}/PyPDFForm/__init__.py

@@ -20,7 +20,7 @@ The library supports various PDF form features, including:
 PyPDFForm aims to simplify PDF form manipulation, making it accessible to developers of all skill levels.
 """
 
-__version__ = "4.2.0"
+__version__ = "4.2.2"
 
 from .assets.blank import BlankPage
 from .middleware import Widgets

{pypdfform-4.2.0 → pypdfform-4.2.2}/PyPDFForm/ap.py

@@ -12,10 +12,10 @@ from io import BytesIO
 
 from pikepdf import Pdf
 from pypdf import PdfReader, PdfWriter
+from pypdf.generic import DictionaryObject, NameObject, TextStringObject
 
-from .constants import XFA, AcroForm, Root
-from .template import (get_on_open_javascript, get_pdf_title,
-                       set_on_open_javascript, set_pdf_title)
+from .constants import (JS, XFA, AcroForm, JavaScript, OpenAction, Root, S,
+                        Title)
 from .utils import stream_to_io
 
 
@@ -31,8 +31,6 @@ def appearance_streams_handler(pdf: bytes, generate_appearance_streams: bool) ->
        PDF viewers to generate appearance streams for form fields.
     3. Optionally generating appearance streams explicitly using pikepdf if
        `generate_appearance_streams` is True.
-    4. Preserving the title from the original PDF.
-    5. Preserving the on-open JavaScript from the original PDF.
 
     The result is cached using lru_cache for performance.
 
@@ -65,35 +63,43 @@ def appearance_streams_handler(pdf: bytes, generate_appearance_streams: bool) ->
                 r.seek(0)
                 result = r.read()
 
-    result = preserve_title(pdf, result)
-    return preserve_on_open_javascript(pdf, result)
+    return result
 
 
-def preserve_title(src: bytes, dest: bytes) -> bytes:
+@lru_cache
+def preserve_pdf_properties(pdf: bytes, title: str, script: str) -> bytes:
     """
-    Preserves the title from the source PDF to the destination PDF.
+    Preserves and updates PDF properties such as title and OpenAction scripts.
+
+    This function allows setting or updating the PDF's title in its metadata and
+    attaching a JavaScript script that executes when the PDF is opened.
 
     Args:
-        src (bytes): The source PDF file content as a bytes stream.
-        dest (bytes): The destination PDF file content as a bytes stream.
+        pdf (bytes): The PDF file content as a bytes stream.
+        title (str): The title to be set in the PDF metadata.
+        script (str): JavaScript code to be executed when the PDF is opened.
 
     Returns:
-        bytes: The modified destination PDF content as a bytes stream.
+        bytes: The modified PDF content as a bytes stream.
     """
-    title = get_pdf_title(src)
-    return set_pdf_title(dest, title)
+    reader = PdfReader(stream_to_io(pdf))
+    writer = PdfWriter()
+    writer.append(reader)
 
+    if title:
+        metadata = reader.metadata or {}
+        metadata[NameObject(Title)] = TextStringObject(title)
 
-def preserve_on_open_javascript(src: bytes, dest: bytes) -> bytes:
-    """
-    Preserves the on-open JavaScript from the source PDF to the destination PDF.
+        writer.add_metadata(metadata)
 
-    Args:
-        src (bytes): The source PDF file content as a bytes stream.
-        dest (bytes): The destination PDF file content as a bytes stream.
+    if script:
+        open_action = DictionaryObject()
+        open_action[NameObject(S)] = NameObject(JavaScript)
+        open_action[NameObject(JS)] = TextStringObject(script)
 
-    Returns:
-        bytes: The modified destination PDF content as a bytes stream.
-    """
-    script = get_on_open_javascript(src)
-    return set_on_open_javascript(dest, script)
+        writer._root_object.update({NameObject(OpenAction): open_action})  # type: ignore # noqa: SLF001 # # pylint: disable=W0212
+
+    with BytesIO() as f:
+        writer.write(f)
+        f.seek(0)
+        return f.read()

{pypdfform-4.2.0 → pypdfform-4.2.2}/PyPDFForm/template.py

@@ -13,10 +13,9 @@ from io import BytesIO
 from typing import Dict, List, Tuple, Union, cast
 
 from pypdf import PdfReader, PdfWriter
-from pypdf.generic import DictionaryObject, NameObject, TextStringObject
+from pypdf.generic import DictionaryObject
 
-from .constants import (JS, WIDGET_TYPES, Annots, JavaScript, MaxLen,
-                        OpenAction, Parent, S, T, Title)
+from .constants import WIDGET_TYPES, Annots, MaxLen, Parent, T
 from .middleware.checkbox import Checkbox
 from .middleware.dropdown import Dropdown
 from .middleware.radio import Radio
@@ -244,96 +243,6 @@ def get_dropdown_choices(widget: dict) -> Union[Tuple[str, ...], None]:
     )
 
 
-def get_on_open_javascript(pdf: bytes) -> Union[str, None]:
-    """
-    Retrieves the JavaScript that runs when the PDF is opened.
-
-    Args:
-        pdf (bytes): The PDF file content as a bytes stream.
-
-    Returns:
-        Union[str, None]: The JavaScript that runs when the PDF is opened, or None if it's not present.
-    """
-    reader = PdfReader(stream_to_io(pdf))
-    try:
-        return reader.root_object[OpenAction][JS]
-    except KeyError:
-        return None
-
-
-def set_on_open_javascript(pdf: bytes, script: str) -> bytes:
-    """
-    Sets the JavaScript that runs when the PDF is opened.
-
-    Args:
-        pdf (bytes): The PDF file content as a bytes stream.
-        script (str): The JavaScript to run when the PDF is opened.
-
-    Returns:
-        bytes: The modified PDF content as a bytes stream.
-    """
-    if not script:
-        return pdf
-
-    reader = PdfReader(stream_to_io(pdf))
-    writer = PdfWriter()
-    writer.append(reader)
-
-    open_action = DictionaryObject()
-    open_action[NameObject(S)] = NameObject(JavaScript)
-    open_action[NameObject(JS)] = TextStringObject(script)
-
-    writer._root_object.update({NameObject(OpenAction): open_action})  # type: ignore # noqa: SLF001 # # pylint: disable=W0212
-
-    with BytesIO() as f:
-        writer.write(f)
-        f.seek(0)
-        return f.read()
-
-
-def get_pdf_title(pdf: bytes) -> Union[str, None]:
-    """
-    Retrieves the title of a PDF from its metadata.
-
-    Args:
-        pdf (bytes): The PDF file content as a bytes stream.
-
-    Returns:
-        Union[str, None]: The title of the PDF, or None if it's not present.
-    """
-    reader = PdfReader(stream_to_io(pdf))
-    return (reader.metadata or {}).get(Title)
-
-
-def set_pdf_title(pdf: bytes, title: str) -> bytes:
-    """
-    Sets the title of a PDF in its metadata.
-
-    Args:
-        pdf (bytes): The PDF file content as a bytes stream.
-        title (str): The new title for the PDF.
-
-    Returns:
-        bytes: The modified PDF content as a bytes stream.
-    """
-    if not title:
-        return pdf
-
-    reader = PdfReader(stream_to_io(pdf))
-    writer = PdfWriter()
-    writer.append(reader)
-
-    metadata = reader.metadata or {}
-    metadata[NameObject(Title)] = TextStringObject(title)
-
-    writer.add_metadata(metadata)
-
-    with BytesIO() as f:
-        writer.write(f)
-        f.seek(0)
-        return f.read()
-
-
 def update_widget_keys(
     template: bytes,
     widgets: Dict[str, WIDGET_TYPES],

{pypdfform-4.2.0 → pypdfform-4.2.2}/PyPDFForm/watermark.py

@@ -305,13 +305,13 @@ def merge_watermarks_with_pdf(
     result = BytesIO()
     pdf_file = PdfReader(stream_to_io(pdf))
     output = PdfWriter()
+    output.append(pdf_file)
 
-    for i, page in enumerate(pdf_file.pages):
+    for i, page in enumerate(output.pages):
         if watermarks[i]:
             watermark = PdfReader(stream_to_io(watermarks[i]))
             if watermark.pages:
                 page.merge_page(watermark.pages[0])
-        output.add_page(page)
 
     output.write(result)
     result.seek(0)

{pypdfform-4.2.0 → pypdfform-4.2.2}/PyPDFForm/wrapper.py

@@ -27,7 +27,7 @@ from typing import (TYPE_CHECKING, BinaryIO, Dict, Sequence, TextIO, Tuple,
 
 from .adapter import (fp_or_f_obj_or_f_content_to_content,
                       fp_or_f_obj_or_stream_to_stream)
-from .ap import appearance_streams_handler
+from .ap import appearance_streams_handler, preserve_pdf_properties
 from .constants import VERSION_IDENTIFIER_PREFIX, VERSION_IDENTIFIERS
 from .coordinate import generate_coordinate_grid
 from .filler import fill
@@ -38,9 +38,7 @@ from .middleware.dropdown import Dropdown
 from .middleware.signature import Signature
 from .middleware.text import Text
 from .raw import RawText, RawTypes
-from .template import (build_widgets, get_on_open_javascript, get_pdf_title,
-                       set_on_open_javascript, set_pdf_title,
-                       update_widget_keys)
+from .template import build_widgets, update_widget_keys
 from .types import PdfWrapperList
 from .utils import (generate_unique_suffix, get_page_streams, merge_pdfs,
                     remove_all_widgets)
@@ -106,6 +104,8 @@ class PdfWrapper:
         super().__init__()
         self._stream = fp_or_f_obj_or_stream_to_stream(template)
         self.widgets = {}
+        self.title: str = None
+        self._on_open_javascript = None
         self._available_fonts = {}  # for setting /F1
         self._font_register_events = []  # for reregister
         self._key_update_tracker = {}  # for update key preserve old key attrs
@@ -223,28 +223,6 @@ class PdfWrapper:
 
         return self
 
-    @property
-    def title(self) -> Union[str, None]:
-        """
-        Returns the title of the PDF document.
-
-        Returns:
-            Union[str, None]: The title of the PDF, or None if it's not set.
-        """
-
-        return get_pdf_title(self._read())
-
-    @title.setter
-    def title(self, value: str) -> None:
-        """
-        Sets the title of the PDF document.
-
-        Args:
-            value (str): The new title for the PDF document.
-        """
-
-        self._stream = set_pdf_title(self._read(), value)
-
     @property
     def schema(self) -> dict:
         """
@@ -348,37 +326,41 @@ class PdfWrapper:
     @property
     def on_open_javascript(self) -> Union[str, None]:
         """
-        Returns the JavaScript that runs when the PDF is opened.
+        Returns the JavaScript script that executes when the PDF is opened.
 
         Returns:
-            Union[str, None]: The JavaScript that runs when the PDF is opened, or None if it's not set.
+            Union[str, None]: The JavaScript script, or None if no script is set.
         """
 
-        return get_on_open_javascript(self._read())
+        return self._on_open_javascript
 
     @on_open_javascript.setter
     def on_open_javascript(self, value: Union[str, TextIO]) -> None:
         """
-        Sets the JavaScript that runs when the PDF is opened.
+        Sets the JavaScript script that executes when the PDF is opened.
 
         Args:
-            value (Union[str, TextIO]): The JavaScript to run when the PDF is opened.
-                Can be a string or a text file-like object.
+            value (Union[str, TextIO]): The JavaScript script, provided as either:
+                - str: The JavaScript code as a string, or a file path to a .js file.
+                - TextIO: An open file-like object containing the JavaScript code.
         """
 
-        self._stream = set_on_open_javascript(
-            self._read(), fp_or_f_obj_or_f_content_to_content(value)
-        )
+        self._on_open_javascript = fp_or_f_obj_or_f_content_to_content(value)
 
     def read(self) -> bytes:
         """
         Reads the PDF document and returns its content as bytes.
 
-        This method retrieves the PDF stream and optionally generates appearance
-        streams for form fields if `need_appearances` is enabled.
+        This method retrieves the PDF stream and performs several processing steps:
+        1. Triggers widget hooks and updates font mappings (via `_read`).
+        2. If `need_appearances` is enabled, it handles appearance streams and the
+           `/NeedAppearances` flag, which may include removing XFA and explicitly
+           generating appearance streams.
+        3. If a title or on-open JavaScript is set, it updates the PDF properties
+           accordingly.
 
         Returns:
-            bytes: The PDF document content as a byte string.
+            bytes: The processed PDF document content as a byte string.
         """
 
         result = self._read()
@@ -387,6 +369,13 @@ class PdfWrapper:
                 result, getattr(self, "generate_appearance_streams")
             )  # cached
 
+        if any([self.title, self.on_open_javascript]):
+            result = preserve_pdf_properties(
+                result,
+                self.title,
+                self.on_open_javascript,
+            )
+
         return result
 
     def _read(self) -> bytes:

{pypdfform-4.2.0 → pypdfform-4.2.2}/PyPDFForm.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: PyPDFForm
-Version: 4.2.0
+Version: 4.2.2
 Summary: The Python library for PDF forms.
 Author: Jinge Li
 License-Expression: MIT

{pypdfform-4.2.0 → pypdfform-4.2.2}/tests/test_js.py

@@ -220,3 +220,30 @@ def test_on_open_script(template_stream, pdf_samples, request):
 
         assert len(pdf.read()) == len(expected)
         assert pdf.read() == expected
+
+
+def test_on_open_script_title_coexist(template_stream, pdf_samples, request):
+    expected_path = os.path.join(
+        pdf_samples, "js", "test_on_open_script_title_coexist.pdf"
+    )
+    with open(expected_path, "rb+") as f:
+        pdf = PdfWrapper(template_stream, title="My PDF")
+        pdf.on_open_javascript = 'this.getField("test").value = "opened";'
+
+        assert pdf.title == "My PDF"
+        assert pdf.on_open_javascript == 'this.getField("test").value = "opened";'
+
+        request.config.results["expected_path"] = expected_path
+        request.config.results["stream"] = pdf.read()
+
+        expected = f.read()
+
+        assert len(pdf.read()) == len(expected)
+        assert pdf.read() == expected
+
+        pdf2 = PdfWrapper(template_stream)
+        pdf2.on_open_javascript = 'this.getField("test").value = "opened";'
+        pdf2.title = "My PDF"
+
+        assert len(pdf2.read()) == len(expected)
+        assert pdf2.read() == expected