Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 9 additions & 0 deletions PyPDFForm/lib/middleware/base.py
Original file line number Diff line number Diff line change
Expand Up @@ -104,6 +104,15 @@ def __setattr__(self, name: str, value: Any) -> None:

super().__setattr__(name, value)

def __repr__(self) -> str:
_internal = {"SET_ATTR_TRIGGER_HOOK_MAP", "attr_set_tracker", "hooks_to_trigger"}
parts = [f"name={self._name!r}", f"value={self._value!r}"]
for k, v in self.__dict__.items():
if k.startswith("_") or k in _internal or v is None:
continue
parts.append(f"{k}={v!r}")
return f"{self.__class__.__name__}({', '.join(parts)})"

@property
def name(self) -> str:
"""
Expand Down
2 changes: 2 additions & 0 deletions docs/index.md
Original file line number Diff line number Diff line change
Expand Up @@ -40,6 +40,8 @@ Here's a quick look at how PyPDFForm works:
from pprint import pprint

pprint(pdf.schema)

pprint(pdf.widgets)
```
=== "Style"
```python
Expand Down
25 changes: 25 additions & 0 deletions docs/inspect.md
Original file line number Diff line number Diff line change
Expand Up @@ -69,6 +69,31 @@ To inspect the current filled data of a PDF form, use the `.data` attribute. For
'test_3': 'test3'}
```

## Inspect individual form field widgets

The `.widgets` attribute gives you a dictionary mapping each field name to its widget object. Each widget exposes properties such as `name`, `value`, `page_number`, `x`, `y`,`width`,`height`,`tooltip`,`readonly`,`required`, and`hidden`.

You can iterate over all widgets to see their types and current state:

=== "Code"
```python
from pprint import pprint
from PyPDFForm import PdfWrapper

pdf = PdfWrapper("sample_template.pdf")

pprint(pdf.widgets)
```
=== "Output"
```sh
{'check': Checkbox(name='check', value=None, readonly=False, required=False, hidden=False, page_number=1, x=358.874, y=664.717, width=18.47999999999996, height=18.480000000000018),
'check_2': Checkbox(name='check_2', value=None, readonly=False, required=False, hidden=False, page_number=2, x=349.637, y=673.954, width=18.478999999999985, height=18.480000000000018),
'check_3': Checkbox(name='check_3', value=None, readonly=False, required=False, hidden=False, page_number=3, x=349.305, y=667.344, width=18.480000000000018, height=18.479999999999905),
'test': Text(name='test', value=None, readonly=False, required=False, hidden=False, page_number=1, x=73.3365, y=662.692, width=232.4235, height=21.067999999999984, comb=False, multiline=False),
'test_2': Text(name='test_2', value=None, readonly=False, required=False, hidden=False, page_number=2, x=71.4095, y=671.626, width=232.42350000000005, height=21.067999999999984, comb=False, multiline=False),
'test_3': Text(name='test_3', value=None, readonly=False, required=False, hidden=False, page_number=3, x=70.5919, y=665.349, width=232.42309999999998, height=21.067999999999984, comb=False, multiline=False)}
```

## Generate sample data

PyPDFForm can also generate sample data for filling a PDF form:
Expand Down
8 changes: 8 additions & 0 deletions tests/doc_examples/lib/test_inspect.py
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,14 @@ def test_schema(static_pdfs):
}


def test_widgets(static_pdfs):
pdf_widgets =repr(PdfWrapper(
os.path.join(static_pdfs, "sample_template.pdf")
).widgets)

assert pdf_widgets == "{'test': Text(name='test', value=None, readonly=False, required=False, hidden=False, page_number=1, x=73.3365, y=662.692, width=232.4235, height=21.067999999999984, comb=False, multiline=False), 'check': Checkbox(name='check', value=None, readonly=False, required=False, hidden=False, page_number=1, x=358.874, y=664.717, width=18.47999999999996, height=18.480000000000018), 'test_2': Text(name='test_2', value=None, readonly=False, required=False, hidden=False, page_number=2, x=71.4095, y=671.626, width=232.42350000000005, height=21.067999999999984, comb=False, multiline=False), 'check_2': Checkbox(name='check_2', value=None, readonly=False, required=False, hidden=False, page_number=2, x=349.637, y=673.954, width=18.478999999999985, height=18.480000000000018), 'test_3': Text(name='test_3', value=None, readonly=False, required=False, hidden=False, page_number=3, x=70.5919, y=665.349, width=232.42309999999998, height=21.067999999999984, comb=False, multiline=False), 'check_3': Checkbox(name='check_3', value=None, readonly=False, required=False, hidden=False, page_number=3, x=349.305, y=667.344, width=18.480000000000018, height=18.479999999999905)}"


def test_data(static_pdfs):
assert PdfWrapper(os.path.join(static_pdfs, "sample_template_filled.pdf")).data == {
"check": True,
Expand Down
78 changes: 78 additions & 0 deletions tests/test_extract_middleware_attributes.py
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,8 @@
import os

from PyPDFForm import PdfWrapper
from PyPDFForm.lib.middleware.checkbox import Checkbox
from PyPDFForm.lib.middleware.text import Text


def test_text_check_values(pdf_samples, data_dict):
Expand Down Expand Up @@ -157,6 +159,82 @@ def test_text_field_comb(max_length_expected_directory):
assert obj.widgets["LastName"].comb


def test_widget_repr_text(template_stream):
obj = PdfWrapper(template_stream)
widget = obj.widgets["test"]
result = repr(widget)

assert result.startswith("Text(")
assert "comb=False" in result
assert "height=" in result
assert "hidden=False" in result
assert "multiline=False" in result
assert "name='test'" in result
assert "page_number=1" in result
assert "readonly=False" in result
assert "required=False" in result
assert "value=None" in result
assert "width=" in result
assert "x=" in result
assert "y=" in result

# None-valued optional attributes should be omitted
assert "font=" not in result
assert "font_size=" not in result
# internal attrs should be omitted
assert "SET_ATTR_TRIGGER_HOOK_MAP" not in result
assert "attr_set_tracker" not in result
assert "hooks_to_trigger" not in result


def test_widget_repr_checkbox(template_stream):
obj = PdfWrapper(template_stream)
widget = obj.widgets["check"]
result = repr(widget)

assert result.startswith("Checkbox(")
assert "name='check'" in result
assert "value=None" in result
assert "SET_ATTR_TRIGGER_HOOK_MAP" not in result


def test_widget_repr_includes_non_none_attrs():
widget = Text("my_field")
widget.font_size = 12.0
widget.readonly = True
result = repr(widget)

assert "font_size=12.0" in result
assert "readonly=True" in result
assert "font=" not in result


def test_widget_repr_checkbox_includes_size():
widget = Checkbox("my_check")
widget.size = 20.0
result = repr(widget)

assert result.startswith("Checkbox(")
assert "width=20.0" in result
assert "height=20.0" in result


def test_widget_repr_value_shown_when_set():
widget = Text("field_name", value="hello")
result = repr(widget)

assert "name='field_name'" in result
assert "value='hello'" in result


def test_widget_repr_all_fields_in_widgets(template_stream):
obj = PdfWrapper(template_stream)
for name, widget in obj.widgets.items():
result = repr(widget)
assert f"name={name!r}" in result
assert "value=" in result


def test_text_field_comb_sejda(pdf_samples):
obj = PdfWrapper(
os.path.join(
Expand Down