def test_gen_xfdf(self):
xfdf_path = pypdftk.gen_xfdf(SAMPLE_DATA)
xfdf = read(xfdf_path)
expected = read(TEST_XFDF_PATH)
# XML can have sibling elements in different order. So:
# * Parse the XML, get list of the root's children, convert to string, sort
xfdf_standard_order = [ET.tostring(i) for i in list(ET.fromstring(xfdf).iter())]
expected_standard_order = [ET.tostring(i) for i in list(ET.fromstring(expected).iter())]
xfdf_standard_order.sort()
expected_standard_order.sort()
self.assertEqual(xfdf_standard_order, expected_standard_order)
def test_gen_xfdf(self):
xfdf_path = pypdftk.gen_xfdf(SAMPLE_DATA)
xfdf = read(xfdf_path)
expected = read(TEST_XFDF_PATH)
# XML can have sibling elements in different order. So:
# * Parse the XML, get list of the root's children, convert to string, sort
xfdf_standard_order = [
ET.tostring(i) for i in list(ET.fromstring(xfdf).iter())
]
expected_standard_order = [
ET.tostring(i) for i in list(ET.fromstring(expected).iter())
]
xfdf_standard_order.sort()
expected_standard_order.sort()
self.assertEqual(xfdf_standard_order, expected_standard_order)
def fill_template(template,
data_strings=[],
data_names=[],
hidden=[],
readonly=[],
images=[],
pdf_url=None,
editable=True,
pdfa=False,
password=None,
template_password=None,
default_export_value=None):
if pdf_url is None:
pdf_url = 'file.pdf'
if not pdf_url.endswith('.pdf'):
pdf_url += '.pdf'
the_fields = read_fields(template)
export_values = dict()
for field, default, pageno, rect, field_type, export_value in the_fields:
field_type = re.sub(r'[^/A-Za-z]', '', str(field_type))
if field_type in ('/Btn', "/'Btn'"):
export_values[
field] = export_value or default_export_value or 'Yes'
if len(export_values):
new_data_strings = list()
for key, val in data_strings:
if key in export_values:
if str(val) in ('Yes', 'yes', 'True', 'true', 'On', 'on',
export_values[key]):
val = export_values[key]
else:
if export_values[key] == 'On':
val = 'Off'
elif export_values[key] == 'on':
val = 'off'
elif export_values[key] == 'yes':
val = 'no'
else:
val = 'No'
new_data_strings.append((key, val))
data_strings = new_data_strings
data_dict = {}
for key, val in data_strings:
data_dict[key] = val
fdf = Xfdf(pdf_url, data_dict)
#fdf = fdfgen.forge_fdf(pdf_url, data_strings, data_names, hidden, readonly)
fdf_file = tempfile.NamedTemporaryFile(prefix="datemp",
mode="wb",
suffix=".xfdf",
delete=False)
#fdf_file.write(fdf)
fdf_file.close()
fdf.write_xfdf(fdf_file.name)
if False:
fdf_dict = dict()
for key, val in data_strings:
fdf_dict[key] = val
xfdf_temp_filename = pypdftk.gen_xfdf(fdf_dict)
xfdf_file = tempfile.NamedTemporaryFile(prefix="datemp", mode="wb", suffix=\
".xfdf", delete=False)
shutil.copyfile(xfdf_temp_filename, xfdf_file.name)
pdf_file = tempfile.NamedTemporaryFile(prefix="datemp",
mode="wb",
suffix=".pdf",
delete=False)
if template_password is not None:
template_file = tempfile.NamedTemporaryFile(prefix="datemp",
mode="wb",
suffix=".pdf",
delete=False)
qpdf_subprocess_arguments = [
QPDF_PATH, '--decrypt', '--password='******'fill_form', fdf_file.name, 'output',
pdf_file.name
]
#logmessage("Arguments are " + str(subprocess_arguments))
if editable or len(images):
subprocess_arguments.append('need_appearances')
else:
subprocess_arguments.append('flatten')
try:
result = subprocess.run(subprocess_arguments, timeout=600).returncode
except subprocess.TimeoutExpired:
result = 1
logmessage("fill_template: call to pdftk fill_form took too long")
if result != 0:
logmessage("Failed to fill PDF form " + str(template))
raise DAError("Call to pdftk failed for template " + str(template) +
" where arguments were " +
" ".join(subprocess_arguments))
if len(images):
fields = dict()
for field, default, pageno, rect, field_type, export_value in the_fields:
if str(field_type) in ('/Sig', "/'Sig'"):
fields[field] = {'pageno': pageno, 'rect': rect}
image_todo = list()
for field, file_info in images:
if field not in fields:
logmessage("field name " + str(field) +
" not found in PDF file")
continue
#logmessage("Need to put image on page " + str(fields[field]['pageno']))
temp_png = tempfile.NamedTemporaryFile(mode="wb", suffix=".png")
args = [
daconfig.get('imagemagick',
'convert'), file_info['fullpath'], "-trim",
"+repage", "+profile", '*', '-density', '0', temp_png.name
]
try:
result = subprocess.run(args, timeout=60).returncode
except subprocess.TimeoutExpired:
logmessage("fill_template: convert took too long")
result = 1
if result == 1:
logmessage("failed to trim file: " + " ".join(args))
continue
im = Image.open(temp_png.name)
width, height = im.size
xone, yone, xtwo, ytwo = fields[field]['rect']
dppx = width / (xtwo - xone)
dppy = height / (ytwo - yone)
if (dppx > dppy):
dpp = dppx
else:
dpp = dppy
extent_x, extent_y = xone * dpp + width, yone * dpp + height
overlay_pdf_file = tempfile.NamedTemporaryFile(prefix="datemp",
mode="wb",
suffix=".pdf",
delete=False)
args = [
daconfig.get('imagemagick', 'convert'), temp_png.name,
"-background", "none", "-density",
str(int(dpp * 72)), "-gravity", "NorthEast", "-extent",
str(int(extent_x)) + 'x' + str(int(extent_y)),
overlay_pdf_file.name
]
try:
result = subprocess.run(args, timeout=60).returncode
except subprocess.TimeoutExpired:
result = 1
logmessage("fill_template: call to convert took too long")
if result == 1:
logmessage("failed to make overlay: " + " ".join(args))
continue
image_todo.append({
'overlay_file': overlay_pdf_file.name,
'pageno': fields[field]['pageno']
})
if len(image_todo):
new_pdf_file = tempfile.NamedTemporaryFile(mode="wb",
suffix=".pdf")
original = safe_pypdf_reader(pdf_file.name)
original.idnum_to_page = get_page_hash(original.trailer)
catalog = original.trailer["/Root"]
writer = DAPdfFileWriter()
tree = dict()
for part in pdf_parts:
if part in catalog:
tree[part] = catalog[part]
for i in range(original.getNumPages()):
for item in image_todo:
if (item['pageno'] - 1) == i:
page = original.getPage(i)
foreground_file = safe_pypdf_reader(
item['overlay_file'])
foreground_page = foreground_file.getPage(0)
page.mergePage(foreground_page)
for i in range(original.getNumPages()):
newpage = original.getPage(i)
writer.addPage(newpage)
for key, val in tree.items():
writer._root_object.update(
{pypdf.generic.NameObject(key): val})
writer.page_list = list()
recursive_get_pages(writer._root_object['/Pages'],
writer.page_list)
recursive_add_bookmark(original, writer, original.getOutlines())
with open(new_pdf_file.name, "wb") as outFile:
writer.write(outFile)
shutil.copyfile(new_pdf_file.name, pdf_file.name)
if (not editable) and len(images):
flatten_pdf(pdf_file.name)
if pdfa:
pdf_to_pdfa(pdf_file.name)
if editable:
replicate_js_and_calculations(template, pdf_file.name, password)
elif password:
pdf_encrypt(pdf_file.name, password)
return pdf_file.name
def fill_template(template,
data_strings=[],
data_names=[],
hidden=[],
readonly=[],
images=[],
pdf_url=None,
editable=True,
pdfa=False,
password=None,
template_password=None):
if pdf_url is None:
pdf_url = ''
fdf = fdfgen.forge_fdf(pdf_url, data_strings, data_names, hidden, readonly)
fdf_file = tempfile.NamedTemporaryFile(prefix="datemp",
mode="wb",
suffix=".fdf",
delete=False)
fdf_file.write(fdf)
fdf_file.close()
if False:
fdf_dict = dict()
for key, val in data_strings:
fdf_dict[key] = val
xfdf_temp_filename = pypdftk.gen_xfdf(fdf_dict)
xfdf_file = tempfile.NamedTemporaryFile(prefix="datemp", mode="wb", suffix=\
".xfdf", delete=False)
shutil.copyfile(xfdf_temp_filename, xfdf_file.name)
pdf_file = tempfile.NamedTemporaryFile(prefix="datemp",
mode="wb",
suffix=".pdf",
delete=False)
if template_password is not None:
template_file = tempfile.NamedTemporaryFile(prefix="datemp",
mode="wb",
suffix=".pdf",
delete=False)
qpdf_subprocess_arguments = [
QPDF_PATH, '--decrypt', '--password='******'fill_form', fdf_file.name, 'output',
pdf_file.name
]
#logmessage("Arguments are " + str(subprocess_arguments))
if editable or len(images):
subprocess_arguments.append('need_appearances')
else:
subprocess_arguments.append('flatten')
result = call(subprocess_arguments)
if result != 0:
logmessage("Failed to fill PDF form " + str(template))
raise DAError("Call to pdftk failed for template " + str(template) +
" where arguments were " +
" ".join(subprocess_arguments))
if len(images):
fields = dict()
for field, default, pageno, rect, field_type in read_fields(template):
if str(field_type) in ('/Sig', "/u'Sig'", "/'Sig'"):
fields[field] = {'pageno': pageno, 'rect': rect}
image_todo = list()
for field, file_info in images:
if field not in fields:
logmessage("field name " + str(field) +
" not found in PDF file")
continue
#logmessage("Need to put image on page " + str(fields[field]['pageno']))
temp_png = tempfile.NamedTemporaryFile(mode="wb", suffix=".png")
args = [
"convert", file_info['fullpath'], "-trim", "+repage",
temp_png.name
]
result = call(args)
if result == 1:
logmessage("failed to trim file: " + " ".join(args))
continue
im = Image.open(temp_png.name)
width, height = im.size
xone, yone, xtwo, ytwo = fields[field]['rect']
dppx = width / (xtwo - xone)
dppy = height / (ytwo - yone)
if (dppx > dppy):
dpp = dppx
else:
dpp = dppy
extent_x, extent_y = xone * dpp + width, yone * dpp + height
overlay_pdf_file = tempfile.NamedTemporaryFile(prefix="datemp",
mode="wb",
suffix=".pdf",
delete=False)
args = [
"convert", temp_png.name, "-background", "none", "-density",
str(int(dpp * 72)), "-gravity", "NorthEast", "-extent",
str(int(extent_x)) + 'x' + str(int(extent_y)),
overlay_pdf_file.name
]
result = call(args)
if result == 1:
logmessage("failed to make overlay: " + " ".join(args))
continue
image_todo.append({
'overlay_stream':
open(overlay_pdf_file.name, "rb"),
'pageno':
fields[field]['pageno']
})
if len(image_todo):
new_pdf_file = tempfile.NamedTemporaryFile(mode="wb",
suffix=".pdf")
with open(pdf_file.name, "rb") as inFile:
original = pypdf.PdfFileReader(inFile)
original.idnum_to_page = get_page_hash(original.trailer)
catalog = original.trailer["/Root"]
writer = DAPdfFileWriter()
tree = dict()
for part in pdf_parts:
if part in catalog:
tree[part] = catalog[part]
for i in range(original.getNumPages()):
for item in image_todo:
if (item['pageno'] - 1) == i:
page = original.getPage(i)
foreground_file = pypdf.PdfFileReader(
item['overlay_stream'])
foreground_page = foreground_file.getPage(0)
page.mergePage(foreground_page)
for i in range(original.getNumPages()):
newpage = original.getPage(i)
writer.addPage(newpage)
for key, val in tree.items():
writer._root_object.update(
{pypdf.generic.NameObject(key): val})
writer.page_list = list()
recursive_get_pages(writer._root_object['/Pages'],
writer.page_list)
recursive_add_bookmark(original, writer,
original.getOutlines())
with open(new_pdf_file.name, "wb") as outFile:
writer.write(outFile)
shutil.copyfile(new_pdf_file.name, pdf_file.name)
for item in image_todo:
item['overlay_stream'].close()
if (not editable) and len(images):
flatten_pdf(pdf_file.name)
if pdfa:
pdf_to_pdfa(pdf_file.name)
if editable:
replicate_js_and_calculations(template, pdf_file.name, password)
elif password:
pdf_encrypt(pdf_file.name, password)
return pdf_file.name
def test_gen_xfdf(self):
xfdf_path = pypdftk.gen_xfdf(SAMPLE_DATA)
xfdf = read(xfdf_path)
expected = read(TEST_XFDF_PATH)
self.assertEqual(xfdf, expected)
def fill_template(template, data_strings=[], data_names=[], hidden=[], readonly=[], images=[], pdf_url=None, editable=True, pdfa=False, password=None, template_password=None):
if pdf_url is None:
pdf_url = ''
fdf = fdfgen.forge_fdf(pdf_url, data_strings, data_names, hidden, readonly)
fdf_file = tempfile.NamedTemporaryFile(prefix="datemp", mode="wb", suffix=".fdf", delete=False)
fdf_file.write(fdf)
fdf_file.close()
if False:
fdf_dict = dict()
for key, val in data_strings:
fdf_dict[key] = val
xfdf_temp_filename = pypdftk.gen_xfdf(fdf_dict)
xfdf_file = tempfile.NamedTemporaryFile(prefix="datemp", mode="wb", suffix=\
".xfdf", delete=False)
shutil.copyfile(xfdf_temp_filename, xfdf_file.name)
pdf_file = tempfile.NamedTemporaryFile(prefix="datemp", mode="wb", suffix=".pdf", delete=False)
if template_password is not None:
template_file = tempfile.NamedTemporaryFile(prefix="datemp", mode="wb", suffix=".pdf", delete=False)
qpdf_subprocess_arguments = [QPDF_PATH, '--decrypt', '--password='******'fill_form', fdf_file.name, 'output', pdf_file.name]
#logmessage("Arguments are " + str(subprocess_arguments))
if editable or len(images):
subprocess_arguments.append('need_appearances')
else:
subprocess_arguments.append('flatten')
result = call(subprocess_arguments)
if result != 0:
logmessage("Failed to fill PDF form " + str(template))
raise DAError("Call to pdftk failed for template " + str(template) + " where arguments were " + " ".join(subprocess_arguments))
if len(images):
fields = dict()
for field, default, pageno, rect, field_type in read_fields(template):
if str(field_type) in ('/Sig', "/u'Sig'", "/'Sig'"):
fields[field] = {'pageno': pageno, 'rect': rect}
image_todo = list()
for field, file_info in images:
if field not in fields:
logmessage("field name " + str(field) + " not found in PDF file")
continue
#logmessage("Need to put image on page " + str(fields[field]['pageno']))
temp_png = tempfile.NamedTemporaryFile(mode="wb", suffix=".png")
args = ["convert", file_info['fullpath'], "-trim", "+repage", temp_png.name]
result = call(args)
if result == 1:
logmessage("failed to trim file: " + " ".join(args))
continue
im = Image.open(temp_png.name)
width, height = im.size
xone, yone, xtwo, ytwo = fields[field]['rect']
dppx = width/(xtwo-xone)
dppy = height/(ytwo-yone)
if (dppx > dppy):
dpp = dppx
else:
dpp = dppy
extent_x, extent_y = xone*dpp+width, yone*dpp+height
overlay_pdf_file = tempfile.NamedTemporaryFile(prefix="datemp", mode="wb", suffix=".pdf", delete=False)
args = ["convert", temp_png.name, "-background", "none", "-density", str(int(dpp*72)), "-gravity", "NorthEast", "-extent", str(int(extent_x)) + 'x' + str(int(extent_y)), overlay_pdf_file.name]
result = call(args)
if result == 1:
logmessage("failed to make overlay: " + " ".join(args))
continue
image_todo.append({'overlay_stream': open(overlay_pdf_file.name, "rb"), 'pageno': fields[field]['pageno']})
if len(image_todo):
new_pdf_file = tempfile.NamedTemporaryFile(mode="wb", suffix=".pdf")
with open(pdf_file.name, "rb") as inFile:
original = pypdf.PdfFileReader(inFile)
original.idnum_to_page = get_page_hash(original.trailer)
catalog = original.trailer["/Root"]
writer = DAPdfFileWriter()
tree = dict()
for part in pdf_parts:
if part in catalog:
tree[part] = catalog[part]
for i in range(original.getNumPages()):
for item in image_todo:
if (item['pageno'] - 1) == i:
page = original.getPage(i)
foreground_file = pypdf.PdfFileReader(item['overlay_stream'])
foreground_page = foreground_file.getPage(0)
page.mergePage(foreground_page)
for i in range(original.getNumPages()):
newpage = original.getPage(i)
writer.addPage(newpage)
for key, val in tree.items():
writer._root_object.update({pypdf.generic.NameObject(key): val})
writer.page_list = list()
recursive_get_pages(writer._root_object['/Pages'], writer.page_list)
recursive_add_bookmark(original, writer, original.getOutlines())
with open(new_pdf_file.name, "wb") as outFile:
writer.write(outFile)
shutil.copyfile(new_pdf_file.name, pdf_file.name)
for item in image_todo:
item['overlay_stream'].close()
if (not editable) and len(images):
flatten_pdf(pdf_file.name)
if pdfa:
pdf_to_pdfa(pdf_file.name)
if editable:
replicate_js_and_calculations(template, pdf_file.name, password)
elif password:
pdf_encrypt(pdf_file.name, password)
return pdf_file.name
def fill_template(template,
data_strings=[],
data_names=[],
hidden=[],
readonly=[],
images=[],
pdf_url=None,
editable=True,
pdfa=False,
password=None):
if pdf_url is None:
pdf_url = ''
fdf = fdfgen.forge_fdf(pdf_url, data_strings, data_names, hidden, readonly)
fdf_file = tempfile.NamedTemporaryFile(prefix="datemp",
mode="wb",
suffix=".fdf",
delete=False)
fdf_file.write(fdf)
fdf_file.close()
if False:
fdf_dict = dict()
for key, val in data_strings:
fdf_dict[key] = val
xfdf_temp_filename = pypdftk.gen_xfdf(fdf_dict)
xfdf_file = tempfile.NamedTemporaryFile(prefix="datemp", mode="wb", suffix=\
".xfdf", delete=False)
shutil.copyfile(xfdf_temp_filename, xfdf_file.name)
pdf_file = tempfile.NamedTemporaryFile(prefix="datemp",
mode="wb",
suffix=".pdf",
delete=False)
subprocess_arguments = [
PDFTK_PATH, template, 'fill_form', fdf_file.name, 'output',
pdf_file.name
]
#logmessage("Arguments are " + str(subprocess_arguments))
if editable:
subprocess_arguments.append('need_appearances')
else:
subprocess_arguments.append('flatten')
result = call(subprocess_arguments)
if result != 0:
logmessage("Failed to fill PDF form " + str(template))
raise DAError("Call to pdftk failed for template " + str(template) +
" where arguments were " +
" ".join(subprocess_arguments))
if len(images):
fields = dict()
for field, default, pageno, rect, field_type in read_fields(template):
if str(field_type) == '/Sig':
fields[field] = {'pageno': pageno, 'rect': rect}
for field, file_info in images:
if field not in fields:
logmessage("field name " + str(field) +
" not found in PDF file")
continue
#logmessage("Need to put image on page " + str(fields[field]['pageno']))
temp_png = tempfile.NamedTemporaryFile(mode="wb", suffix=".png")
args = [
"convert", file_info['fullpath'], "-trim", "+repage",
temp_png.name
]
result = call(args)
if result == 1:
logmessage("failed to trim file: " + " ".join(args))
continue
im = Image.open(temp_png.name)
width, height = im.size
xone, yone, xtwo, ytwo = fields[field]['rect']
dppx = width / (xtwo - xone)
dppy = height / (ytwo - yone)
if (dppx > dppy):
dpp = dppx
else:
dpp = dppy
extent_x, extent_y = xone * dpp + width, yone * dpp + height
overlay_pdf_file = tempfile.NamedTemporaryFile(mode="wb",
suffix=".pdf")
args = [
"convert", temp_png.name, "-background", "none", "-density",
str(int(dpp * 72)), "-gravity", "NorthEast", "-extent",
str(int(extent_x)) + 'x' + str(int(extent_y)),
overlay_pdf_file.name
]
result = call(args)
if result == 1:
logmessage("failed to make overlay: " + " ".join(args))
continue
new_pdf_file = tempfile.NamedTemporaryFile(mode="wb",
suffix=".pdf")
with open(pdf_file.name,
"rb") as inFile, open(overlay_pdf_file.name,
"rb") as overlay:
original = pypdf.PdfFileReader(inFile)
background = original.getPage(fields[field]['pageno'] - 1)
foreground = pypdf.PdfFileReader(overlay).getPage(0)
background.mergePage(foreground)
writer = pypdf.PdfFileWriter()
for i in range(original.getNumPages()):
page = original.getPage(i)
writer.addPage(page)
with open(new_pdf_file.name, "wb") as outFile:
writer.write(outFile)
shutil.copyfile(new_pdf_file.name, pdf_file.name)
if pdfa:
pdf_to_pdfa(pdf_file.name)
if editable:
replicate_js_and_calculations(template, pdf_file.name, password)
elif password:
pdf_encrypt(pdf_file.name, password)
return pdf_file.name