solyanviktor-star
adecb0d1a9
The bundled office skills (#68595) read user documents and agent-authored payloads with the locale-default codec: - docx/powerpoint validators/base.py opened OOXML part XML in text mode before handing it to lxml. On Windows (cp1251/GBK) the bytes decode to mojibake that lxml then parses, so validation runs against silently corrupted document text; on locales where the UTF-8 bytes don't decode the validator crashes with UnicodeDecodeError instead of validating. Opening as bytes lets lxml honor the encoding declared in the XML prolog. - The pdf form scripts (fill_fillable_fields, fill_pdf_form_with_annotations, create_validation_image, check_bounding_boxes) read the fields JSON the agent authors — UTF-8 by construction — with the locale codec, so non-ASCII form values (any Cyrillic/CJK/accented input) either crash or get written into the user's PDF as mojibake. The json.dump writers use ensure_ascii=True and were already safe; only the readers needed pinning. Adds a contract test asserting every document/payload reader is locale-independent, plus a live regression test that runs check_bounding_boxes.py on a non-ASCII fields.json under a forced non-UTF-8 locale — it fails without the fix on both POSIX (C locale) and Windows (cp1251 chokes on the 0x98 byte of U+2018).
99 lines
3.7 KiB
Python
99 lines
3.7 KiB
Python
import json
|
|
import sys
|
|
|
|
from pypdf import PdfReader, PdfWriter
|
|
|
|
from extract_form_field_info import get_field_info
|
|
|
|
|
|
|
|
|
|
def fill_pdf_fields(input_pdf_path: str, fields_json_path: str, output_pdf_path: str):
|
|
with open(fields_json_path, encoding="utf-8") as f:
|
|
fields = json.load(f)
|
|
fields_by_page = {}
|
|
for field in fields:
|
|
if "value" in field:
|
|
field_id = field["field_id"]
|
|
page = field["page"]
|
|
if page not in fields_by_page:
|
|
fields_by_page[page] = {}
|
|
fields_by_page[page][field_id] = field["value"]
|
|
|
|
reader = PdfReader(input_pdf_path)
|
|
|
|
has_error = False
|
|
field_info = get_field_info(reader)
|
|
fields_by_ids = {f["field_id"]: f for f in field_info}
|
|
for field in fields:
|
|
existing_field = fields_by_ids.get(field["field_id"])
|
|
if not existing_field:
|
|
has_error = True
|
|
print(f"ERROR: `{field['field_id']}` is not a valid field ID")
|
|
elif field["page"] != existing_field["page"]:
|
|
has_error = True
|
|
print(f"ERROR: Incorrect page number for `{field['field_id']}` (got {field['page']}, expected {existing_field['page']})")
|
|
else:
|
|
if "value" in field:
|
|
err = validation_error_for_field_value(existing_field, field["value"])
|
|
if err:
|
|
print(err)
|
|
has_error = True
|
|
if has_error:
|
|
sys.exit(1)
|
|
|
|
writer = PdfWriter(clone_from=reader)
|
|
for page, field_values in fields_by_page.items():
|
|
writer.update_page_form_field_values(writer.pages[page - 1], field_values, auto_regenerate=False)
|
|
|
|
writer.set_need_appearances_writer(True)
|
|
|
|
with open(output_pdf_path, "wb") as f:
|
|
writer.write(f)
|
|
|
|
|
|
def validation_error_for_field_value(field_info, field_value):
|
|
field_type = field_info["type"]
|
|
field_id = field_info["field_id"]
|
|
if field_type == "checkbox":
|
|
checked_val = field_info["checked_value"]
|
|
unchecked_val = field_info["unchecked_value"]
|
|
if field_value != checked_val and field_value != unchecked_val:
|
|
return f'ERROR: Invalid value "{field_value}" for checkbox field "{field_id}". The checked value is "{checked_val}" and the unchecked value is "{unchecked_val}"'
|
|
elif field_type == "radio_group":
|
|
option_values = [opt["value"] for opt in field_info["radio_options"]]
|
|
if field_value not in option_values:
|
|
return f'ERROR: Invalid value "{field_value}" for radio group field "{field_id}". Valid values are: {option_values}'
|
|
elif field_type == "choice":
|
|
choice_values = [opt["value"] for opt in field_info["choice_options"]]
|
|
if field_value not in choice_values:
|
|
return f'ERROR: Invalid value "{field_value}" for choice field "{field_id}". Valid values are: {choice_values}'
|
|
return None
|
|
|
|
|
|
def monkeypatch_pydpf_method():
|
|
from pypdf.generic import DictionaryObject
|
|
from pypdf.constants import FieldDictionaryAttributes
|
|
|
|
original_get_inherited = DictionaryObject.get_inherited
|
|
|
|
def patched_get_inherited(self, key: str, default = None):
|
|
result = original_get_inherited(self, key, default)
|
|
if key == FieldDictionaryAttributes.Opt:
|
|
if isinstance(result, list) and all(isinstance(v, list) and len(v) == 2 for v in result):
|
|
result = [r[0] for r in result]
|
|
return result
|
|
|
|
DictionaryObject.get_inherited = patched_get_inherited
|
|
|
|
|
|
if __name__ == "__main__":
|
|
if len(sys.argv) != 4:
|
|
print("Usage: fill_fillable_fields.py [input pdf] [field_values.json] [output pdf]")
|
|
sys.exit(1)
|
|
monkeypatch_pydpf_method()
|
|
input_pdf = sys.argv[1]
|
|
fields_json = sys.argv[2]
|
|
output_pdf = sys.argv[3]
|
|
fill_pdf_fields(input_pdf, fields_json, output_pdf)
|