PyPDFForm 5.1.1__tar.gz → 5.2.1__tar.gz

{pypdfform-5.1.1 → pypdfform-5.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: PyPDFForm
-Version: 5.1.1
+Version: 5.2.1
 Summary: The Python library & CLI for PDF forms.
 Author: Jinge Li
 License-Expression: MIT
@@ -24,7 +24,7 @@ Classifier: Topic :: Utilities
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: cryptography<49.0.0,>=48.0.0
+Requires-Dist: cryptography<50.0.0,>=48.0.0
 Requires-Dist: fonttools<5.0.0,>=4.63.0
 Requires-Dist: pikepdf<11.0.0,>=10.7.2
 Requires-Dist: pillow<13.0.0,>=12.2.0
@@ -34,9 +34,7 @@ Provides-Extra: cli
 Requires-Dist: typer<1.0.0,>=0.26.1; extra == "cli"
 Requires-Dist: jsonschema<5.0.0,>=4.26.0; extra == "cli"
 Provides-Extra: dev
-Requires-Dist: black<27.0.0,>=26.5.1; extra == "dev"
 Requires-Dist: coverage<8.0.0,>=7.14.1; extra == "dev"
-Requires-Dist: isort<9.0.0,>=8.0.1; extra == "dev"
 Requires-Dist: mike<3.0.0,>=2.2.0; extra == "dev"
 Requires-Dist: mkdocs<2.0.0,>=1.6.1; extra == "dev"
 Requires-Dist: mkdocs-material<10.0.0,>=9.7.6; extra == "dev"

{pypdfform-5.1.1 → pypdfform-5.2.1}/PyPDFForm/__init__.py

@@ -18,7 +18,7 @@ from Python code or from the command line.
 
 import logging
 
-__version__ = "5.1.1"
+__version__ = "5.2.1"
 
 from .lib.annotations import Annotations
 from .lib.assets.blank import BlankPage

{pypdfform-5.1.1 → pypdfform-5.2.1}/PyPDFForm/cli/common.py

@@ -53,6 +53,13 @@ OPTIONAL_OUTPUT_PDF = Annotated[
     ),
 ]
 FIELD_NAME = Annotated[str, typer.Option("--field", help="Form field name.")]
+FIELD_NAMES = Annotated[
+    list[str],
+    typer.Option(
+        "--field",
+        help="Form field name. Repeat this option to select multiple fields.",
+    ),
+]
 
 
 def json_file_option(help_text: str):

{pypdfform-5.1.1 → pypdfform-5.2.1}/PyPDFForm/cli/create.py

@@ -14,11 +14,15 @@ from typing import Annotated
 
 import typer
 
-from .. import (Annotations, BlankPage, Fields, PdfArray, PdfWrapper,
-                RawElements)
-from .common import (INPUT_PDF, OPTIONAL_OUTPUT_PDF, REQUIRED_OUTPUT_PDF,
-                     cli_bad_parameter, create_elements_from_file,
-                     json_file_option)
+from .. import Annotations, BlankPage, Fields, PdfArray, PdfWrapper, RawElements
+from .common import (
+    INPUT_PDF,
+    OPTIONAL_OUTPUT_PDF,
+    REQUIRED_OUTPUT_PDF,
+    cli_bad_parameter,
+    create_elements_from_file,
+    json_file_option,
+)
 from .schemas.create import ANNOTATION_SCHEMA, FIELD_SCHEMA, RAW_SCHEMA
 
 create_cli = typer.Typer(

pypdfform-5.2.1/PyPDFForm/cli/remove.py

@@ -0,0 +1,33 @@
+# -*- coding: utf-8 -*-
+"""
+This module defines CLI commands for removing PDF form content.
+
+It exposes the `remove` command group for deleting existing form fields.
+Commands in this module load the target PDF, validate requested form field
+names, apply the matching `PdfWrapper` operation, and write the modified PDF to
+either the requested output path or the original file.
+"""
+
+import typer
+
+from .. import PdfWrapper
+from .common import FIELD_NAMES, INPUT_PDF, OPTIONAL_OUTPUT_PDF, get_widget
+
+remove_cli = typer.Typer(
+    context_settings={"help_option_names": ["--help", "-h"]}, no_args_is_help=True
+)
+
+
+@remove_cli.command(no_args_is_help=True)
+def field(
+    ctx: typer.Context,
+    pdf: INPUT_PDF,
+    fields: FIELD_NAMES,
+    output: OPTIONAL_OUTPUT_PDF = None,
+) -> None:
+    """Remove form fields from a PDF."""
+    obj = PdfWrapper(str(pdf), **ctx.obj)
+    for field_name in fields:
+        get_widget(obj, field_name, "--field")
+
+    obj.remove_fields(fields).write(output or pdf)

{pypdfform-5.1.1 → pypdfform-5.2.1}/PyPDFForm/cli/root.py

@@ -2,16 +2,17 @@
 """
 This module defines the root command-line interface for PyPDFForm.
 
-It creates the Typer application, attaches the `create`, `inspect`, and `update`
-command groups, and exposes top-level options shared by those commands. The root
-callback collects global flags in the Typer context so each subcommand can
-initialize `PdfWrapper` with consistent settings.
+It creates the Typer application, attaches the `create`, `inspect`, `update`,
+and `remove` command groups, and exposes top-level options shared by those
+commands. The root callback collects global flags in the Typer context so each
+subcommand can initialize `PdfWrapper` with consistent settings.
 
 Commands:
     - `fill`: Fill an existing PDF form from JSON data.
     - `create`: Create PDFs, fields, annotations, raw elements, and grid views.
     - `inspect`: Print form metadata and field data as JSON.
     - `update`: Modify PDF metadata, field names, properties, geometry, and scripts.
+    - `remove`: Remove PDF form fields.
 """
 
 from pathlib import Path
@@ -20,10 +21,10 @@ from typing import Annotated
 import typer
 
 from .. import PdfWrapper, Widgets, __version__
-from .common import (INPUT_PDF, OPTIONAL_OUTPUT_PDF, json_file_option,
-                     load_json_file)
+from .common import INPUT_PDF, OPTIONAL_OUTPUT_PDF, json_file_option, load_json_file
 from .create import create_cli
 from .inspect import inspect_cli
+from .remove import remove_cli
 from .update import update_cli
 
 cli_app = typer.Typer(
@@ -44,6 +45,11 @@ cli_app.add_typer(
     name="update",
     help="Update PDF metadata, fields, and scripts.",
 )
+cli_app.add_typer(
+    remove_cli,
+    name="remove",
+    help="Remove PDF form content.",
+)
 
 
 def version_callback(value: bool) -> None:
@@ -68,7 +74,7 @@ def version_callback(value: bool) -> None:
 
 @cli_app.callback(
     invoke_without_command=True,
-    help="Create, fill, inspect, and update PDF forms.",
+    help="Work with PDF forms from the command line.",
 )
 def main(
     ctx: typer.Context,
@@ -111,7 +117,7 @@ def main(
         ),
     ] = False,
 ) -> None:
-    """Create, fill, inspect, and update PDF forms."""
+    """Work with PDF forms from the command line."""
     ctx.obj = {
         "need_appearances": need_appearances,
         "generate_appearance_streams": generate_appearance_streams,

{pypdfform-5.1.1 → pypdfform-5.2.1}/PyPDFForm/cli/update.py

@@ -17,9 +17,16 @@ import typer
 
 from .. import PdfWrapper
 from ..lib.constants import PdfVersion
-from .common import (FIELD_NAME, INPUT_PDF, OPTIONAL_OUTPUT_PDF,
-                     cli_bad_parameter, get_widget, handle_font_registration,
-                     json_file_option, load_json_file)
+from .common import (
+    FIELD_NAME,
+    INPUT_PDF,
+    OPTIONAL_OUTPUT_PDF,
+    cli_bad_parameter,
+    get_widget,
+    handle_font_registration,
+    json_file_option,
+    load_json_file,
+)
 from .schemas.update import FIELD_SCHEMA, RENAME_SCHEMA
 
 update_cli = typer.Typer(

{pypdfform-5.1.1 → pypdfform-5.2.1}/PyPDFForm/lib/annotations/__init__.py

@@ -14,8 +14,12 @@ from dataclasses import dataclass
 from .link import LinkAnnotation
 from .stamp import RubberStampAnnotation
 from .text import TextAnnotation
-from .text_markup import (HighlightAnnotation, SquigglyAnnotation,
-                          StrikeOutAnnotation, UnderlineAnnotation)
+from .text_markup import (
+    HighlightAnnotation,
+    SquigglyAnnotation,
+    StrikeOutAnnotation,
+    UnderlineAnnotation,
+)
 
 AnnotationTypes = (
     TextAnnotation

{pypdfform-5.1.1 → pypdfform-5.2.1}/PyPDFForm/lib/annotations/base.py

@@ -11,8 +11,13 @@ Classes:
 
 from dataclasses import dataclass
 
-from pypdf.generic import (ArrayObject, DictionaryObject, FloatObject,
-                           NameObject, TextStringObject)
+from pypdf.generic import (
+    ArrayObject,
+    DictionaryObject,
+    FloatObject,
+    NameObject,
+    TextStringObject,
+)
 
 from ..constants import Annot, Contents, Rect, Subtype, Type
 

{pypdfform-5.1.1 → pypdfform-5.2.1}/PyPDFForm/lib/annotations/link.py

@@ -12,8 +12,13 @@ Classes:
 from dataclasses import dataclass
 from typing import Optional
 
-from pypdf.generic import (ArrayObject, DictionaryObject, NameObject,
-                           NumberObject, TextStringObject)
+from pypdf.generic import (
+    ArrayObject,
+    DictionaryObject,
+    NameObject,
+    NumberObject,
+    TextStringObject,
+)
 
 from ..constants import A, S
 from .base import Annotation

{pypdfform-5.1.1 → pypdfform-5.2.1}/PyPDFForm/lib/egress.py

@@ -17,8 +17,7 @@ from pikepdf import Pdf
 from pypdf import PdfReader, PdfWriter
 from pypdf.generic import DictionaryObject, NameObject, TextStringObject
 
-from .constants import (JS, XFA, AcroForm, JavaScript, OpenAction, Root, S,
-                        Title)
+from .constants import JS, XFA, AcroForm, JavaScript, OpenAction, Root, S, Title
 
 
 @lru_cache

{pypdfform-5.1.1 → pypdfform-5.2.1}/PyPDFForm/lib/filler.py

@@ -24,9 +24,13 @@ from .middleware.image import Image
 from .middleware.radio import Radio
 from .middleware.signature import Signature
 from .middleware.text import Text
-from .patterns import (get_widget_key, update_checkbox_value,
-                       update_dropdown_value, update_radio_value,
-                       update_text_value)
+from .patterns import (
+    get_widget_key,
+    update_checkbox_value,
+    update_dropdown_value,
+    update_radio_value,
+    update_text_value,
+)
 from .watermark import create_watermarks_and_draw, merge_watermarks_with_pdf
 
 
@@ -53,7 +57,9 @@ def signature_image_handler(
     any_image_to_draw = False
     if stream is not None:
         any_image_to_draw = True
-        image_width, image_height = get_image_dimensions(stream)
+        image_width, image_height = (
+            get_image_dimensions(stream) if middleware.preserve_aspect_ratio else (0, 0)
+        )
         x, y, width, height = get_draw_image_resolutions(
             widget, middleware.preserve_aspect_ratio, image_width, image_height
         )

{pypdfform-5.1.1 → pypdfform-5.2.1}/PyPDFForm/lib/font.py

@@ -16,20 +16,52 @@ from zlib import compress
 
 from fontTools.ttLib import TTFont as FT_TTFont
 from pypdf import PdfReader, PdfWriter
-from pypdf.generic import (ArrayObject, DictionaryObject, FloatObject,
-                           NameObject, NumberObject, StreamObject)
+from pypdf.generic import (
+    ArrayObject,
+    DictionaryObject,
+    FloatObject,
+    NameObject,
+    NumberObject,
+    StreamObject,
+)
 from reportlab.pdfbase.pdfmetrics import _fonts
 from reportlab.pdfbase.ttfonts import TTFError, TTFont
 
 from .assets.blank import BlankPage
-from .constants import (DEFAULT_ASSUMED_GLYPH_WIDTH, DR, EM_TO_PDF_FACTOR,
-                        ENCODING_TABLE_SIZE, FIRST_CHAR_CODE, FONT_NAME_PREFIX,
-                        LAST_CHAR_CODE, AcroForm, BaseFont, Encoding, Fields,
-                        Filter, FirstChar, FlateDecode, Font, FontCmap,
-                        FontDescriptor, FontFile2, FontHead, FontHmtx,
-                        FontName, FontNotdef, LastChar, Length, Length1,
-                        MissingWidth, Resources, Subtype, TrueType, Type,
-                        Widths, WinAnsiEncoding)
+from .constants import (
+    DEFAULT_ASSUMED_GLYPH_WIDTH,
+    DR,
+    EM_TO_PDF_FACTOR,
+    ENCODING_TABLE_SIZE,
+    FIRST_CHAR_CODE,
+    FONT_NAME_PREFIX,
+    LAST_CHAR_CODE,
+    AcroForm,
+    BaseFont,
+    Encoding,
+    Fields,
+    Filter,
+    FirstChar,
+    FlateDecode,
+    Font,
+    FontCmap,
+    FontDescriptor,
+    FontFile2,
+    FontHead,
+    FontHmtx,
+    FontName,
+    FontNotdef,
+    LastChar,
+    Length,
+    Length1,
+    MissingWidth,
+    Resources,
+    Subtype,
+    TrueType,
+    Type,
+    Widths,
+    WinAnsiEncoding,
+)
 from .raw.text import RawText
 from .watermark import create_watermarks_and_draw
 
@@ -287,7 +319,9 @@ def register_font_acroform(
     font_dict_ref = writer._add_object(font_dict)  # type: ignore # noqa: SLF001 # # pylint: disable=W0212
 
     if AcroForm not in writer._root_object:  # type: ignore # noqa: SLF001 # # pylint: disable=W0212
-        writer._root_object[NameObject(AcroForm)] = DictionaryObject({NameObject(Fields): ArrayObject([])})  # type: ignore # noqa: SLF001 # # pylint: disable=W0212
+        writer._root_object[NameObject(AcroForm)] = DictionaryObject(  # type: ignore # noqa: SLF001 # pylint: disable=W0212
+            {NameObject(Fields): ArrayObject([])}
+        )
     acroform = writer._root_object[AcroForm]  # type: ignore # noqa: SLF001 # # pylint: disable=W0212
 
     if DR not in acroform:

{pypdfform-5.1.1 → pypdfform-5.2.1}/PyPDFForm/lib/hooks.py

@@ -14,15 +14,47 @@ from io import BytesIO
 from typing import TextIO, cast
 
 from pypdf import PdfReader, PdfWriter
-from pypdf.generic import (ArrayObject, DictionaryObject, FloatObject,
-                           NameObject, NumberObject, TextStringObject)
+from pypdf.generic import (
+    ArrayObject,
+    DictionaryObject,
+    FloatObject,
+    NameObject,
+    NumberObject,
+    TextStringObject,
+)
 
 from .adapter import fp_or_f_obj_or_f_content_to_content
-from .constants import (AA, COMB, DA, FONT_COLOR_IDENTIFIER,
-                        FONT_SIZE_IDENTIFIER, HIDDEN, JS, MULTILINE, READ_ONLY,
-                        REQUIRED, TU, Action, Annots, Bl, D, E, F, Ff, Fo,
-                        JavaScript, MaxLen, Opt, Parent, Q, Rect, S, Type, U,
-                        X)
+from .constants import (
+    AA,
+    COMB,
+    DA,
+    FONT_COLOR_IDENTIFIER,
+    FONT_SIZE_IDENTIFIER,
+    HIDDEN,
+    JS,
+    MULTILINE,
+    READ_ONLY,
+    REQUIRED,
+    TU,
+    Action,
+    Annots,
+    Bl,
+    D,
+    E,
+    F,
+    Ff,
+    Fo,
+    JavaScript,
+    MaxLen,
+    Opt,
+    Parent,
+    Q,
+    Rect,
+    S,
+    Type,
+    U,
+    X,
+)
 from .patterns import get_widget_key
 
 

{pypdfform-5.1.1 → pypdfform-5.2.1}/PyPDFForm/lib/image.py

@@ -7,6 +7,7 @@ calculating the resolutions for drawing an image on a PDF page, taking into
 account whether to preserve the aspect ratio.
 """
 
+from functools import lru_cache
 from io import BytesIO
 from typing import Tuple
 
@@ -50,12 +51,13 @@ def rotate_image(image_stream: bytes, rotation: float | int) -> bytes:
     return result
 
 
+@lru_cache
 def get_image_dimensions(image_stream: bytes) -> Tuple[float, float]:
     """
     Retrieves the width and height of an image from its byte stream.
 
-    This function uses the PIL library to open the image from the provided byte stream
-    and returns its dimensions (width and height) as a tuple of floats.
+    This cached function uses the PIL library to open the image from the provided
+    byte stream and returns its dimensions (width and height) as a tuple of floats.
 
     Args:
         image_stream (bytes): The image data as bytes.
@@ -63,13 +65,8 @@ def get_image_dimensions(image_stream: bytes) -> Tuple[float, float]:
     Returns:
         Tuple[float, float]: The width and height of the image in pixels.
     """
-    buff = BytesIO()
-    buff.write(image_stream)
-    buff.seek(0)
-
-    image = Image.open(buff)
-
-    return image.size
+    with Image.open(BytesIO(image_stream)) as image:
+        return image.size
 
 
 def get_draw_image_resolutions(

{pypdfform-5.1.1 → pypdfform-5.2.1}/PyPDFForm/lib/patterns.py

@@ -10,12 +10,45 @@ for updating these widgets.
 
 from typing import Tuple
 
-from pypdf.generic import (ArrayObject, DictionaryObject, NameObject,
-                           NumberObject, TextStringObject)
-
-from .constants import (AP, AS, DV, FT, HIDDEN, IMAGE_FIELD_IDENTIFIER, JS,
-                        SLASH, TU, A, Btn, Ch, F, Ff, I, MaxLen, N, Off, Opt,
-                        Parent, Q, Rect, Sig, Subtype, T, Tx, V, Widget, Yes)
+from pypdf.generic import (
+    ArrayObject,
+    DictionaryObject,
+    NameObject,
+    NumberObject,
+    TextStringObject,
+)
+
+from .constants import (
+    AP,
+    AS,
+    DV,
+    FT,
+    HIDDEN,
+    IMAGE_FIELD_IDENTIFIER,
+    JS,
+    SLASH,
+    TU,
+    A,
+    Btn,
+    Ch,
+    F,
+    Ff,
+    I,
+    MaxLen,
+    N,
+    Off,
+    Opt,
+    Parent,
+    Q,
+    Rect,
+    Sig,
+    Subtype,
+    T,
+    Tx,
+    V,
+    Widget,
+    Yes,
+)
 from .middleware.checkbox import Checkbox
 from .middleware.dropdown import Dropdown
 from .middleware.image import Image

{pypdfform-5.1.1 → pypdfform-5.2.1}/PyPDFForm/lib/template.py

@@ -22,12 +22,22 @@ from .middleware.checkbox import Checkbox
 from .middleware.dropdown import Dropdown
 from .middleware.radio import Radio
 from .middleware.text import Text
-from .patterns import (WIDGET_DESCRIPTION_PATTERNS, WIDGET_TYPE_PATTERNS,
-                       check_field_flag, get_checkbox_value,
-                       get_dropdown_choices, get_dropdown_value,
-                       get_field_hidden, get_field_rect, get_radio_value,
-                       get_text_field_alignment, get_text_field_max_length,
-                       get_text_value, get_widget_key, update_annotation_name)
+from .patterns import (
+    WIDGET_DESCRIPTION_PATTERNS,
+    WIDGET_TYPE_PATTERNS,
+    check_field_flag,
+    get_checkbox_value,
+    get_dropdown_choices,
+    get_dropdown_value,
+    get_field_hidden,
+    get_field_rect,
+    get_radio_value,
+    get_text_field_alignment,
+    get_text_field_max_length,
+    get_text_value,
+    get_widget_key,
+    update_annotation_name,
+)
 from .utils import extract_widget_property, find_pattern_match
 
 
@@ -366,6 +376,51 @@ def create_annotations(
         return f.read()
 
 
+def remove_widgets_by_keys(
+    pdf: bytes, keys: List[str], use_full_widget_name: bool = False
+) -> bytes:
+    """
+    Removes specific widgets from a PDF by their keys.
+
+    This function removes any widget annotation whose key matches one of the
+    provided keys. If no keys are provided, the original PDF stream is returned
+    unchanged.
+
+    Args:
+        pdf (bytes): The PDF stream to remove widgets from.
+        keys (List[str]): A list of widget keys to remove.
+        use_full_widget_name (bool): Whether to match widgets by their full
+            names, including parent names.
+
+    Returns:
+        bytes: The updated PDF stream with the matching widgets removed.
+    """
+    if not keys:
+        return pdf
+
+    writer = PdfWriter(BytesIO(pdf))
+
+    for page in writer.pages:
+        needs_update = False
+        page_annots = ArrayObject([])
+
+        for annot in page.get(Annots, []):
+            annot = cast(DictionaryObject, annot.get_object())
+            key = get_widget_key(annot.get_object(), use_full_widget_name)
+            if key not in keys:
+                page_annots.append(annot)
+            else:
+                needs_update = True
+
+        if needs_update:
+            page[NameObject(Annots)] = page_annots
+
+    with BytesIO() as f:
+        writer.write(f)
+        f.seek(0)
+        return f.read()
+
+
 def update_widget_keys(
     template: bytes,
     widgets: Dict[str, WIDGET_TYPES],
@@ -394,8 +449,7 @@ def update_widget_keys(
     out = PdfWriter()
     out.append(pdf)
 
-    for i, old_key in enumerate(old_keys):
-        _update_single_widget_key(out, widgets, old_key, new_keys[i], indices[i])
+    _apply_widget_key_updates(out, widgets, old_keys, new_keys, indices)
 
     with BytesIO() as f:
         out.write(f)
@@ -403,35 +457,44 @@ def update_widget_keys(
         return f.read()
 
 
-def _update_single_widget_key(
+def _apply_widget_key_updates(
     writer: PdfWriter,
     widgets: Dict[str, WIDGET_TYPES],
-    old_key: str,
-    new_key: str,
-    index: int,
+    old_keys: List[str],
+    new_keys: List[str],
+    indices: List[int],
 ) -> None:
     """
-    Updates a single widget key in a PDF template.
+    Applies queued widget key updates to matching annotations.
+
+    The update queue is converted into a lookup keyed by old widget name, then
+    each annotation is checked against that lookup as pages are traversed.
+    Non-radio widgets honor the requested occurrence index, while radio widgets
+    update every annotation in the radio group.
 
     Args:
         writer (PdfWriter): The PDF writer object.
         widgets (Dict[str, WIDGET_TYPES]): A dictionary of widgets in the template.
-        old_key (str): The old widget key to be replaced.
-        new_key (str): The new widget key to replace the old key.
-        index (int): The index of the widget to update if multiple widgets have the same name.
+        old_keys (List[str]): The old widget keys to replace.
+        new_keys (List[str]): The new widget keys to apply.
+        indices (List[int]): Widget occurrence indices for duplicate field names.
     """
-    tracker = -1
+    updates = {old_key: (new_keys[i], indices[i]) for i, old_key in enumerate(old_keys)}
+    trackers = {}
+
     for page in writer.pages:
         for annot in page.get(Annots, []):
             annot = cast(DictionaryObject, annot.get_object())
             key = get_widget_key(annot.get_object(), False)
 
-            widget = widgets.get(key)
-            if widget is None or old_key != key:
+            if key not in updates:
                 continue
 
-            tracker += 1
-            if not isinstance(widget, Radio) and tracker != index:
-                continue
+            widget = widgets.get(key)
+            if widget is not None:
+                trackers[key] = trackers.get(key, -1) + 1
+                new_key, index = updates[key]
+                if not isinstance(widget, Radio) and trackers[key] != index:
+                    continue
 
-            update_annotation_name(annot, new_key)
+                update_annotation_name(annot, new_key)