python-pdffiller 1.1.0__py3-none-any.whl → 1.1.1__py3-none-any.whl

pdffiller/_version.py

@@ -3,4 +3,4 @@ __copyright__ = "Copyright 2025 SISMIC"
 __email__ = "jraphanel@sismic.fr"
 __license__ = "MIT"
 __title__ = "pdffiller"
-__version__ = "1.1.0"
+__version__ = "1.1.1"

pdffiller/cli/commands/fill_form.py

@@ -131,6 +131,9 @@ def fill_form(parser: PdfFillerArgumentParser, *args: Any) -> Any:
                 input_dict[html.unescape(field["name"])] = html.unescape(field["value"])
         input_data = input_dict
 
+    output.info(f"input file: {opts.file}")
+    output.info("input values are:")
+    output.info(json.dumps(input_data, indent=4))
     try:
         pdf = Pdf()
         pdf.fill(opts.file, opts.output, input_data, opts.flatten)

pdffiller/io/custom_pdf_writer.py

@@ -0,0 +1,143 @@
+from pypdf import PageObject, PdfWriter
+from pypdf.constants import AnnotationDictionaryAttributes as AA
+from pypdf.constants import CatalogDictionary
+from pypdf.constants import FieldDictionaryAttributes as FA
+from pypdf.constants import InteractiveFormDictEntries
+from pypdf.constants import PageAttributes as PG
+from pypdf.errors import PyPdfError
+from pypdf.generic import (
+    ArrayObject,
+    DictionaryObject,
+    NameObject,
+    NumberObject,
+    RectangleObject,
+    TextStringObject,
+)
+
+from ..typing import cast, Dict, List, Optional, Tuple, Union
+from .output import PdfFillerOutput
+
+
+class CustomPdfWriter(PdfWriter):  # pylint: disable=abstract-method
+    """Overwrite PdfWriter to by-pass the related to flatten mode."""
+
+    def update_field_values(
+        self,
+        page: Union[PageObject, List[PageObject], None],
+        fields: Dict[str, Union[str, List[str], Tuple[str, str, float]]],
+        flags: FA.FfBits = PdfWriter.FFBITS_NUL,
+        auto_regenerate: Optional[bool] = True,
+        flatten: bool = False,
+    ) -> None:
+        """
+        Update the form field values for a given page from a fields dictionary.
+
+        Copy field texts and values from fields to page.
+        If the field links to a parent object, add the information to the parent.
+
+        Args:
+            page: `PageObject` - references **PDF writer's page** where the
+                annotations and field data will be updated.
+                `List[Pageobject]` - provides list of pages to be processed.
+                `None` - all pages.
+            fields: a Python dictionary of:
+
+                * field names (/T) as keys and text values (/V) as value
+                * field names (/T) as keys and list of text values (/V) for multiple choice list
+                * field names (/T) as keys and tuple of:
+                    * text values (/V)
+                    * font id (e.g. /F1, the font id must exist)
+                    * font size (0 for autosize)
+
+            flags: A set of flags from :class:`~pypdf.constants.FieldDictionaryAttributes.FfBits`.
+
+            auto_regenerate: Set/unset the need_appearances flag;
+                the flag is unchanged if auto_regenerate is None.
+
+            flatten: Whether or not to flatten the annotation. If True, this adds the annotation's
+                appearance stream to the page contents. Note that this option does not remove the
+                annotation itself.
+
+        """
+        if CatalogDictionary.ACRO_FORM not in self._root_object:
+            raise PyPdfError("No /AcroForm dictionary in PDF of PdfWriter Object")
+        af = cast(DictionaryObject, self._root_object[CatalogDictionary.ACRO_FORM])
+        if InteractiveFormDictEntries.Fields not in af:
+            raise PyPdfError("No /Fields dictionary in PDF of PdfWriter Object")
+        if isinstance(auto_regenerate, bool):
+            self.set_need_appearances_writer(auto_regenerate)
+        # Iterate through pages, update field values
+        if page is None:
+            page = list(self.pages)
+        if isinstance(page, list):
+            for p in page:
+                if PG.ANNOTS in p:  # just to prevent warnings
+                    self.update_field_values(p, fields, flags, None, flatten=flatten)
+            return
+        output = PdfFillerOutput()
+        if PG.ANNOTS not in page:
+            output.warning(f"No fields to update on this page {__name__}")
+            return
+        for annotation in page[PG.ANNOTS]:  # type: ignore
+            annotation = cast(DictionaryObject, annotation.get_object())
+            if annotation.get("/Subtype", "") != "/Widget":
+                continue
+            if "/FT" in annotation and "/T" in annotation:
+                parent_annotation = annotation
+            else:
+                parent_annotation = annotation.get(PG.PARENT, DictionaryObject()).get_object()
+
+            for field, value in fields.items():
+                if not (
+                    self._get_qualified_field_name(parent_annotation) == field
+                    or parent_annotation.get("/T", None) == field
+                ):
+                    continue
+                if parent_annotation.get("/FT", None) == "/Ch" and "/I" in parent_annotation:
+                    del parent_annotation["/I"]
+                if flags:
+                    annotation[NameObject(FA.Ff)] = NumberObject(flags)
+                if not (
+                    value is None and flatten
+                ):  # Only change values if given by user and not flattening.
+                    if isinstance(value, list):
+                        lst = ArrayObject(TextStringObject(v) for v in value)
+                        parent_annotation[NameObject(FA.V)] = lst
+                    elif isinstance(value, tuple):
+                        annotation[NameObject(FA.V)] = TextStringObject(
+                            value[0],
+                        )
+                    else:
+                        parent_annotation[NameObject(FA.V)] = TextStringObject(value)
+                if parent_annotation.get(FA.FT) == "/Btn":
+                    # Checkbox button (no /FT found in Radio widgets)
+                    v = NameObject(value)
+                    ap = cast(DictionaryObject, annotation[NameObject(AA.AP)])
+                    normal_ap = cast(DictionaryObject, ap["/N"])
+                    exist = True
+                    if v not in normal_ap:
+                        v = NameObject("/Off")
+                        exist = False
+                    appearance_stream_obj = normal_ap.get(v)
+                    # other cases will be updated through the for loop
+                    annotation[NameObject(AA.AS)] = v
+                    annotation[NameObject(FA.V)] = v
+                    if flatten and appearance_stream_obj is not None and exist:
+                        # We basically copy the entire appearance stream, which should be
+                        # an XObject that is already registered. No need to add font resources.
+                        rct = cast(RectangleObject, annotation[AA.Rect])
+                        self._add_apstream_object(
+                            page, appearance_stream_obj, field, rct[0], rct[1]
+                        )
+                elif parent_annotation.get(FA.FT) == "/Tx" or parent_annotation.get(FA.FT) == "/Ch":
+                    # textbox
+                    if isinstance(value, tuple):
+                        self._update_field_annotation(
+                            page, parent_annotation, annotation, value[1], value[2], flatten=flatten
+                        )
+                    else:
+                        self._update_field_annotation(
+                            page, parent_annotation, annotation, flatten=flatten
+                        )
+                elif annotation.get(FA.FT) == "/Sig":  # deprecated  # not implemented yet
+                    output.warning(f"Signature forms not implemented yet {__name__}")

pdffiller/io/output.py

@@ -7,7 +7,7 @@ from colorama import Fore, Style
 from pdffiller import const
 from pdffiller.exceptions import CommandLineError
 from pdffiller.io.colors import color_enabled, is_terminal
-from pdffiller.typing import Dict, Optional, Union
+from pdffiller.typing import Dict, Optional, TextIO, Union
 
 LEVEL_QUIET = 80  # -q
 LEVEL_ERROR = 70  # Errors
@@ -56,14 +56,11 @@ class PdfFillerOutput:
     # Singleton
     _output_level: int = LEVEL_STATUS
     _output_file: Optional[str] = None
+    _output_stream: Optional[TextIO] = None
 
     def __init__(self, scope: str = "") -> None:
-        self.stream = sys.stderr
+        self.stream = self._output_stream or sys.stderr
         self._scope = scope
-        if self._output_file:
-            self.stream = open(  # pylint: disable=consider-using-with
-                self._output_file, "wt", encoding="utf-8"
-            )
         self._color: bool = color_enabled(self.stream)
 
     @classmethod
@@ -104,6 +101,10 @@ class PdfFillerOutput:
         :param file_path: Optional path to output log file.
         """
         cls._output_file = file_path
+        if cls._output_file:
+            cls._output_stream = open(  # pylint: disable=consider-using-with
+                cls._output_file, "wt", encoding="utf-8"
+            )
 
     @classmethod
     def level_allowed(cls, level: int) -> bool:

pdffiller/pdf.py

@@ -12,10 +12,11 @@ methods for interacting with its form fields and content.
 
 from collections import OrderedDict
 
-from pypdf import PdfReader, PdfWriter
+from pypdf import PdfReader
 from pypdf.errors import PyPdfError
 from pypdf.generic import ArrayObject, DictionaryObject, NameObject
 
+from pdffiller.io.custom_pdf_writer import CustomPdfWriter
 from pdffiller.io.output import PdfFillerOutput
 
 from .typing import (
@@ -118,6 +119,8 @@ class Pdf:
         if not content:
             return
 
+        output = PdfFillerOutput()
+        output.verbose("loading file in memory")
         loaded_widgets: OrderedDict[str, Widget] = OrderedDict()
         try:
             pdf_file = PdfReader(content)
@@ -126,6 +129,7 @@ class Pdf:
             return
 
         for i, page in enumerate(pdf_file.pages):
+            output.verbose(f"loading page {i+1}/{len(pdf_file.pages)}")
             widgets: Optional[ArrayObject] = page.annotations
             if not widgets:
                 continue
@@ -241,23 +245,30 @@ class Pdf:
             Pdf: The `Pdf` object, allowing for method chaining.
         """
         reader = PdfReader(input_file)
+        output = PdfFillerOutput()
 
         self._init_helper(input_file)
         fields: Dict[str, Union[str, List[str], Tuple[str, str, float]]] = {}
 
+        output.verbose("checking value for radio/checkbox ...")
         for name, value in data.items():
             widget = self.widgets.get(name)
             fields[name] = value
             if isinstance(widget, CheckBoxWidget):
                 if value and value[0] != "/":
-                    fields[name] = "/" + value
+                    output.info(f"override {name} value with /{value}")
+                    fields[name] = f"/{value}"
 
-        writer = PdfWriter(reader)
-        writer.update_page_form_field_values(None, fields, auto_regenerate=False, flatten=flatten)
+        output.info("fill pdf with input values")
+        writer = CustomPdfWriter(reader)
+        writer.update_field_values(None, fields, auto_regenerate=False, flatten=flatten)
         if flatten:
+            output.info("remove all annotations")
             writer.remove_annotations(None)
+        output.info("compress file")
         writer.compress_identical_objects(remove_identicals=True, remove_orphans=True)
 
+        output.info(f"write {output_file} on the disk")
         with open(output_file, "wb") as f:
             writer.write(f)
 

pdffiller/typing.py

@@ -13,6 +13,7 @@ from typing import (
     Optional,
     overload,
     Sequence,
+    TextIO,
     Tuple,
     Type,
     TYPE_CHECKING,
@@ -43,6 +44,7 @@ __all__ = [
     "Union",
     "SubParserType",
     "StrByteType",
+    "TextIO",
 ]
 
 

{python_pdffiller-1.1.0.dist-info → python_pdffiller-1.1.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: python-pdffiller
-Version: 1.1.0
+Version: 1.1.1
 Summary: Interact with PDF by inspecting or filling it
 Author-email: Jacques Raphanel <jraphanel@sismic.fr>
 License-Expression: MIT

{python_pdffiller-1.1.0.dist-info → python_pdffiller-1.1.1.dist-info}/RECORD

@@ -1,11 +1,11 @@
 pdffiller/__init__.py,sha256=0HtgXhEV1fKTKAcOXGcq4UsCFflDIPCDQvckshZf-1k,195
 pdffiller/__main__.py,sha256=7NPQgZVx6VSZS7OrmyJQ_O1vL4wiSqhiILi-outwUqM,107
-pdffiller/_version.py,sha256=jkVj4mFxUGMPJpsXS5J_l0Rayrz_hST2H3Fewc4-x-A,172
+pdffiller/_version.py,sha256=vef-epYlxNmC71LS6tXOTkDXOOxxiF0dTMJwJJdSnOM,172
 pdffiller/const.py,sha256=if_j5I8ftczpjrzZjA7idv-XpvIj1-XBF4oe6VtQvF0,434
 pdffiller/exceptions.py,sha256=CdN93bZ0mBBS5vLxg14FYZUy4xkYqoD3_SzqtSkZr4g,1624
-pdffiller/pdf.py,sha256=kfi1tvUHI3zQJPBe5uSapwFfjI9cnNOGyLaoXQE0QXc,11723
+pdffiller/pdf.py,sha256=VpixUDvzgXYxNX6A5LkMPiLTBKq75yejf_lz-xbWD_E,12287
 pdffiller/py.typed.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-pdffiller/typing.py,sha256=suxFXOGIF07R8UhrEf-ro_vNA2pXJGfe8CX64dStXTs,954
+pdffiller/typing.py,sha256=dW2hGtyaNgTowUl1zsEt3ldhbHM2KfCyHAASb0RZcEs,980
 pdffiller/utils.py,sha256=pmGf3QwkhKwosk_eFCauzHM-XHp_WGVQAtZlxa7taYY,827
 pdffiller/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pdffiller/cli/args.py,sha256=1MUtxIVgdBWJCjgp2gxUuGW-vH4qne92A7Rns2DylsQ,870
@@ -18,19 +18,20 @@ pdffiller/cli/once_argument.py,sha256=olQvNhObObS0iXVL1YCa-_lH76SV0I4FvnlgR9roqo
 pdffiller/cli/smart_formatter.py,sha256=59hwF07nKbp-P9IfbqKgMFsfbvjIw5SACCZpUF4nnuE,318
 pdffiller/cli/commands/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pdffiller/cli/commands/dump_data_fields.py,sha256=YR8aENCGkCRro0jTuuvMg2HCEos9aF81aL4SxP--_2E,2262
-pdffiller/cli/commands/fill_form.py,sha256=R1xF8iHswn_FeYvE7oQOTDwpRf6BjqQ7y2pAHg6yRb4,4627
+pdffiller/cli/commands/fill_form.py,sha256=5wjbjwYLsytY6ea-n_KDbU9UDmkN00NYj_gm25MQqJ8,4758
 pdffiller/io/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pdffiller/io/colors.py,sha256=QCBEWksTVNurOJQYO0zh1X_xxIOXxXmYSJhbCqnNjI8,1710
-pdffiller/io/output.py,sha256=NWV1SabnR_kXmR8tfUKQQoQ_3RV9wqiSnHqzinQDgB0,11217
+pdffiller/io/custom_pdf_writer.py,sha256=rz4kPXJ0JgQhF3896OKizFdnEoPe989NruBA75HMnBQ,6960
+pdffiller/io/output.py,sha256=QMASWRWmfZGG9DdtlfpWXM3VJAMgWGQwPUzoYp_9FFY,11298
 pdffiller/widgets/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pdffiller/widgets/base.py,sha256=omGVQsQgMa-ALESnUd3_94oVIYScAMl0SPhHC_DG8Lg,3613
 pdffiller/widgets/checkbox.py,sha256=iijStLAsY1G4cljW3a9NxVS_8qxJewFEw-B8jU2aKXk,1711
 pdffiller/widgets/radio.py,sha256=Db9Oc3Q8ge8qqTVPLoz3I1_SJBGyJ8KfA33ixZMr78c,1070
 pdffiller/widgets/text.py,sha256=SiuyBvZPZ6idCmtZ_05zE26iN6Rz67OfOj1fUm98YQI,2397
-python_pdffiller-1.1.0.dist-info/licenses/AUTHORS.rst,sha256=1_hVzMKgmoXvGgrcZC7sIbU_6PvvkB6vwqevAqzrIkQ,205
-python_pdffiller-1.1.0.dist-info/licenses/COPYING,sha256=ADPe-bH2wYq8nFf6EPJyovzTJyl3jSPnm09mGI8FSTo,1074
-python_pdffiller-1.1.0.dist-info/METADATA,sha256=yWwklFn1pQVt_lQ9EvY58kAXvQd8aeN-K4Aaju0nERU,4319
-python_pdffiller-1.1.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-python_pdffiller-1.1.0.dist-info/entry_points.txt,sha256=RESKKpPPdWl0wDET96ntuFoUydALx9j0mxtbt-MEBjU,49
-python_pdffiller-1.1.0.dist-info/top_level.txt,sha256=5MGWCBFYlu_Ax-I5PgQkV9Xw7O48maPe9z8Qj_yVPL4,10
-python_pdffiller-1.1.0.dist-info/RECORD,,
+python_pdffiller-1.1.1.dist-info/licenses/AUTHORS.rst,sha256=1_hVzMKgmoXvGgrcZC7sIbU_6PvvkB6vwqevAqzrIkQ,205
+python_pdffiller-1.1.1.dist-info/licenses/COPYING,sha256=ADPe-bH2wYq8nFf6EPJyovzTJyl3jSPnm09mGI8FSTo,1074
+python_pdffiller-1.1.1.dist-info/METADATA,sha256=G0UFHlAH4UOctSuJ6J-X0fHitovbcnnmq8LUv7zA79U,4319
+python_pdffiller-1.1.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+python_pdffiller-1.1.1.dist-info/entry_points.txt,sha256=RESKKpPPdWl0wDET96ntuFoUydALx9j0mxtbt-MEBjU,49
+python_pdffiller-1.1.1.dist-info/top_level.txt,sha256=5MGWCBFYlu_Ax-I5PgQkV9Xw7O48maPe9z8Qj_yVPL4,10
+python_pdffiller-1.1.1.dist-info/RECORD,,