Merge pull request #212 from chinapandaman/PPF-211

PPF-211: tests/docs for fill sejda

Author: chinapandaman

PyPDFForm/__init__.py

@@ -4,4 +4,4 @@
 
 PyPDFForm = Wrapper
 
-__version__ = "0.3.6"
+__version__ = "0.3.7"

PyPDFForm/core/template.py

@@ -15,6 +15,21 @@
 class Template:
     """Contains methods for interacting with a pdfrw parsed PDF form."""
 
+    @staticmethod
+    def remove_all_elements(
+        pdf: bytes
+    ) -> bytes:
+        """Removes all elements from a pdfrw parsed PDF form."""
+
+        pdf = pdfrw.PdfReader(fdata=pdf)
+
+        for i in range(len(pdf.pages)):
+            elements = pdf.pages[i][TemplateCoreConstants().annotation_key]
+            for j in reversed(range(len(elements))):
+                elements.pop(j)
+
+        return Utils().generate_stream(pdf)
+
     @staticmethod
     def iterate_elements(
         pdf: Union[bytes, "pdfrw.PdfReader"], sejda: bool = False
@@ -188,7 +203,7 @@ def get_draw_text_coordinates(
             - 2,
         )
 
-    def assign_uuid(self, pdf: bytes, sejda: bool = False) -> bytes:
+    def assign_uuid(self, pdf: bytes) -> bytes:
         """Appends a separator and uuid after each element's annotated name."""
 
         _uuid = uuid.uuid4().hex
@@ -208,11 +223,6 @@ def assign_uuid(self, pdf: bytes, sejda: bool = False) -> bytes:
                     base_key, MergeConstants().separator, existed_uuid or _uuid
                 )
             }
-            if sejda:
-                element[TemplateCoreConstants().parent_key].update(
-                    pdfrw.PdfDict(**update_dict)
-                )
-            else:
-                element.update(pdfrw.PdfDict(**update_dict))
+            element.update(pdfrw.PdfDict(**update_dict))
 
         return Utils().generate_stream(pdf_file)

PyPDFForm/middleware/wrapper.py

@@ -52,9 +52,7 @@ def __init__(
         self.stream = template
         self.simple_mode = simple_mode
         self.sejda = sejda
-        self.fill = self._simple_fill if simple_mode else self._fill
-        if sejda:
-            self.fill = self._fill
+        self.fill = self._simple_fill if simple_mode and not sejda else self._fill
 
         if not simple_mode or sejda:
             self.elements = {}
@@ -89,8 +87,8 @@ def __add__(self, other: "PyPDFForm") -> "PyPDFForm":
         TemplateMiddleware().validate_stream(self.stream)
         TemplateMiddleware().validate_stream(other.stream)
 
-        pdf_one = TemplateCore().assign_uuid(self.stream, self.sejda)
-        pdf_two = TemplateCore().assign_uuid(other.stream, self.sejda)
+        pdf_one = TemplateCore().assign_uuid(self.stream) if not self.sejda else self.stream
+        pdf_two = TemplateCore().assign_uuid(other.stream) if not other.sejda else other.stream
 
         new_obj = self.__class__()
         new_obj.stream = UtilsCore().merge_two_pdfs(pdf_one, pdf_two)
@@ -121,7 +119,11 @@ def _fill(
                 self.elements[key].validate_value()
                 self.elements[key].validate_text_attributes()
 
-        self.stream = FillerCore().fill(self.stream, self.elements, self.sejda)
+        _fill_result = FillerCore().fill(self.stream, self.elements, self.sejda)
+        if self.sejda:
+            _fill_result = TemplateCore().remove_all_elements(_fill_result)
+
+        self.stream = _fill_result
 
         return self
 

docs/v2/api_reference.md

@@ -19,7 +19,7 @@ mode on and off yields different interactions with the fill method.
 
 * **simple_mode** - a simple mode PyPDFForm object only allows filling data without specifying 
 details like font size. Turning simple mode on also allows leaving PDF editable 
-after filling.
+after filling. NOTE: `simple_mode` is not available when `sejda` is set to `True`.
 
 * **global_font** - a string which sets the global font for text filled on the PDF form. The 
 font set by this parameter has to be registered first. This will only take effect if `simple_mode` is `False`. 
@@ -39,6 +39,9 @@ filled on the PDF form. This will only take effect if `simple_mode` is `False`.
 * **global_text_wrap_length** - an integer value which sets the global maximum number of characters before 
 wrapping to a new line for texts 
 filled on the PDF form. This will only take effect if `simple_mode` is `False`.
+  
+* **sejda** - This boolean parameter should be set to `True` if the PDF form template is prepared using Sejda. 
+NOTE: enabling this will disable `simple_mode` even if it's set to `True`.
 
 ### *PyPDFForm()* **+** *PyPDFForm()*
 
@@ -120,7 +123,7 @@ Its values currently support the following:
        NOTE: Only groups of radio buttons with the same name are supported. If there is only one 
        radio button with a name, please consider using `checkbox` instead.
 
-* **editable** - only available if `simple_mode` is `True`, enabling this will allow the filled PDF to be still 
+* **editable** - only available if `simple_mode` is `True` and `sejda` is `False`, enabling this will allow the filled PDF to be still 
 editable.
 
 ### **read**()

docs/v2/examples.md

@@ -7,7 +7,10 @@ can be used out of box.
 
 The most common tool to create a PDF form is Adobe Acrobat. A tutorial can be found 
 [here](https://helpx.adobe.com/acrobat/using/creating-distributing-pdf-forms.html). 
-There are other free alternatives like [this](https://pdf.wondershare.com/) that support the same functionalities.
+There are other free alternatives like [sejda](https://www.sejda.com/) that support similar functionalities.
+
+NOTE: Sejda is highly recommended as PyPDFForm 
+provides more stable support to PDF forms prepared using it with a `sejda` mode.
 
 Unless otherwise specified, all examples will use the same PDF form which can be 
 found [here](https://github.com/chinapandaman/PyPDFForm/blob/master/pdf_samples/v2/sample_template.pdf). 
@@ -440,3 +443,62 @@ with open(PATH_TO_FILLED_PDF_FORM, "wb+") as output:
 ```
 
 Link to this example: https://github.com/chinapandaman/PyPDFForm/blob/master/examples/simple_fill_radio.py
+
+
+## Fill a PDF form prepared using Sejda
+
+This example uses this [template](https://github.com/chinapandaman/PyPDFForm/blob/master/pdf_samples/v2/sample_template_sejda.pdf). 
+It demos filling a PDF form prepared using Sejda.
+
+```python
+import os
+
+from PyPDFForm import PyPDFForm
+
+PATH_TO_DOWNLOADED_SAMPLE_PDF_FORM = os.path.join(
+    os.path.expanduser("~/Downloads"), "sample_template_sejda.pdf"
+)  # Change this to where you downloaded the sample PDF form
+
+PATH_TO_FILLED_PDF_FORM = os.path.join(
+    os.path.expanduser("~"), "output.pdf"
+)  # Change this to where you wish to put your filled PDF form
+
+with open(PATH_TO_FILLED_PDF_FORM, "wb+") as output:
+    output.write(
+        PyPDFForm(PATH_TO_DOWNLOADED_SAMPLE_PDF_FORM, sejda=True)
+        .fill(
+            {
+                "date": "01-01",
+                "year": "21",
+                "buyer_name": "John Doe",
+                "buyer_address": "1 N Main St, Chicago, IL 60000",
+                "seller_name": "Jack Smith",
+                "seller_address": "2 S Main St, Chicago, IL 60000",
+                "make": "AK",
+                "model": "47",
+                "caliber": "7.62-x39mm",
+                "serial_number": "111111",
+                "purchase_option": 0,
+                "date_of_this_bill": True,
+                "at_future_date": True,
+                "other": True,
+                "other_reason": "NO REASONS",
+                "payment_amount": "400",
+                "future_date": "01-01",
+                "future_year": "22",
+                "exchange_for": "Food",
+                "buyer_name_printed": "John Doe",
+                "seller_name_printed": "Jack Smith",
+                "buyer_signed_date": "2021-01-01",
+                "seller_signed_date": "2021-01-01",
+                "buyer_dl_number": "D000-4609-0001",
+                "seller_dl_number": "S530-4209-0001",
+                "buyer_dl_state": "IL",
+                "seller_dl_state": "IL",
+            },
+        )
+        .read()
+    )
+```
+
+Link to this example: https://github.com/chinapandaman/PyPDFForm/blob/master/examples/fill_sejda.py

examples/fill_sejda.py

@@ -0,0 +1,48 @@
+import os
+
+from PyPDFForm import PyPDFForm
+
+PATH_TO_DOWNLOADED_SAMPLE_PDF_FORM = os.path.join(
+    os.path.expanduser("~/Downloads"), "sample_template_sejda.pdf"
+)  # Change this to where you downloaded the sample PDF form
+
+PATH_TO_FILLED_PDF_FORM = os.path.join(
+    os.path.expanduser("~"), "output.pdf"
+)  # Change this to where you wish to put your filled PDF form
+
+with open(PATH_TO_FILLED_PDF_FORM, "wb+") as output:
+    output.write(
+        PyPDFForm(PATH_TO_DOWNLOADED_SAMPLE_PDF_FORM, sejda=True)
+        .fill(
+            {
+                "date": "01-01",
+                "year": "21",
+                "buyer_name": "John Doe",
+                "buyer_address": "1 N Main St, Chicago, IL 60000",
+                "seller_name": "Jack Smith",
+                "seller_address": "2 S Main St, Chicago, IL 60000",
+                "make": "AK",
+                "model": "47",
+                "caliber": "7.62-x39mm",
+                "serial_number": "111111",
+                "purchase_option": 0,
+                "date_of_this_bill": True,
+                "at_future_date": True,
+                "other": True,
+                "other_reason": "NO REASONS",
+                "payment_amount": "400",
+                "future_date": "01-01",
+                "future_year": "22",
+                "exchange_for": "Food",
+                "buyer_name_printed": "John Doe",
+                "seller_name_printed": "Jack Smith",
+                "buyer_signed_date": "2021-01-01",
+                "seller_signed_date": "2021-01-01",
+                "buyer_dl_number": "D000-4609-0001",
+                "seller_dl_number": "S530-4209-0001",
+                "buyer_dl_state": "IL",
+                "seller_dl_state": "IL",
+            },
+        )
+        .read()
+    )

pdf_samples/v2/sample_filled_sejda.pdf

@@ -0,0 +1,51 @@
+# -*- coding: utf-8 -*-
+
+import os
+
+import pytest
+
+
+@pytest.fixture
+def pdf_samples():
+    return os.path.join(os.path.dirname(__file__), "..", "pdf_samples", "v2")
+
+
+@pytest.fixture
+def sejda_template(pdf_samples):
+    with open(
+        os.path.join(pdf_samples, "sample_template_sejda.pdf"), "rb+"
+    ) as f:
+        return f.read()
+
+
+@pytest.fixture
+def sejda_data():
+    return {
+        "date": "01-01",
+        "year": "21",
+        "buyer_name": "John Doe",
+        "buyer_address": "1 N Main St, Chicago, IL 60000",
+        "seller_name": "Jack Smith",
+        "seller_address": "2 S Main St, Chicago, IL 60000",
+        "make": "AK",
+        "model": "47",
+        "caliber": "7.62-x39mm",
+        "serial_number": "111111",
+        "purchase_option": 0,
+        "date_of_this_bill": True,
+        "at_future_date": True,
+        "other": True,
+        "other_reason": "NO REASONS",
+        "payment_amount": "400",
+        "future_date": "01-01",
+        "future_year": "22",
+        "exchange_for": "Food",
+        "buyer_name_printed": "John Doe",
+        "seller_name_printed": "Jack Smith",
+        "buyer_signed_date": "2021-01-01",
+        "seller_signed_date": "2021-01-01",
+        "buyer_dl_number": "D000-4609-0001",
+        "seller_dl_number": "S530-4209-0001",
+        "buyer_dl_state": "IL",
+        "seller_dl_state": "IL",
+    }

pdf_samples/v2/sample_template_sejda.pdf

@@ -308,3 +308,16 @@ def test_fill_radiobutton(pdf_samples, template_with_radiobutton_stream):
         )
 
         assert obj.stream == f.read()
+
+
+def test_fill_sejda_and_read(sejda_template, pdf_samples, sejda_data):
+    with open(os.path.join(pdf_samples, "sample_filled_sejda.pdf"), "rb+") as f:
+        obj = PyPDFForm(sejda_template, sejda=True).fill(
+            sejda_data,
+        )
+        assert obj.read() == obj.stream
+
+        expected = f.read()
+
+        assert len(obj.stream) == len(expected)
+        assert obj.stream == expected

tests/conftest.py

@@ -47,7 +47,7 @@ def font_samples():
 
 
 def test_validate_constructor_inputs(pdf_samples, template_stream):
-    bad_inputs = ["", "True", 1, "12", ("0", "0", "0"), "0", "0", "100"]
+    bad_inputs = ["", "True", 1, "12", ("0", "0", "0"), "0", "0", "100", "True"]
 
     try:
         PyPDFForm(*bad_inputs)
@@ -65,6 +65,14 @@ def test_validate_constructor_inputs(pdf_samples, template_stream):
 
     bad_inputs[1] = False
 
+    try:
+        PyPDFForm(*bad_inputs)
+        assert False
+    except InvalidModeError:
+        assert True
+
+    bad_inputs[8] = False
+
     try:
         PyPDFForm(*bad_inputs)
         assert False

tests/functional/test_fill.py

@@ -78,6 +78,32 @@ def test_fill(template_stream, data_dict):
             )
 
 
+def test_fill_sejda(sejda_template, sejda_data):
+    elements = TemplateMiddleware().build_elements(sejda_template, sejda=True)
+
+    for k, v in elements.items():
+        if k in sejda_data:
+            v.value = sejda_data[k]
+
+        if elements[k].type == ElementType.text:
+            elements[k].font = TextConstants().global_font
+            elements[k].font_size = TextConstants().global_font_size
+            elements[k].font_color = TextConstants().global_font_color
+            elements[k].text_x_offset = TextConstants().global_text_x_offset
+            elements[k].text_y_offset = TextConstants().global_text_y_offset
+            elements[k].text_wrap_length = TextConstants().global_text_wrap_length
+        elements[k].validate_constants()
+        elements[k].validate_value()
+        elements[k].validate_text_attributes()
+
+    result_stream = Filler().fill(sejda_template, elements, sejda=True)
+
+    assert result_stream != template_stream
+
+    for element in TemplateCore().iterate_elements(result_stream):
+        assert element[TemplateConstants().parent_key][TemplateConstants().field_editable_key] == pdfrw.PdfObject(1)
+
+
 def test_fill_with_radiobutton(template_with_radiobutton_stream, data_dict):
     elements = TemplateMiddleware().build_elements(template_with_radiobutton_stream)