def test_metadata(self):
options = pdf_redactor.RedactorOptions()
options.metadata_filters = {
"Title": [lambda value: value.replace("test", "sentinel")],
"Subject": [lambda value: value[::-1]],
"DEFAULT": [lambda value: None],
}
with RedactFixture(FIXTURE_PATH, options) as redacted_path:
metadata = subprocess.check_output(["pdfinfo", redacted_path])
self.assertIn(b"this is a sentinel", metadata)
self.assertIn(b"FDP a si", metadata)
self.assertNotIn(b"CreationDate", metadata)
self.assertNotIn(b"LibreOffice", metadata)
def test_text_ssns(self):
options = pdf_redactor.RedactorOptions()
options.content_filters = [
(
re.compile(u"[−–—~‐]"),
lambda m: "-"
),
(
re.compile(r"(?<!\d)(?!666|000|9\d{2})([OoIli0-9]{3})([\s-]?)(?!00)([OoIli0-9]{2})\2(?!0{4})([OoIli0-9]{4})(?!\d)"),
lambda m: "XXX-XX-XXXX"
),
]
with RedactFixture(FIXTURE_PATH, options) as redacted_path:
text = pdf_to_text(redacted_path)
self.assertIn("Here are some fake SSNs\n\nXXX-XX-XXXX\n--\n\nXXX-XX-XXXX XXX-XX-XXXX\n\nAnd some more with common OCR character substitutions:\nXXX-XX-XXXX XXX-XX-XXXX XXX-XX-XXXX XXX-XX-XXXX XXX-XX-XXXX", text)
def test_xmp(self):
options = pdf_redactor.RedactorOptions()
options.metadata_filters = {
"DEFAULT": [lambda value: None],
}
def xmp_filter(doc):
for elem in doc.iter():
if elem.text == "Writer":
elem.text = "Sentinel"
return doc
options.xmp_filters = [xmp_filter]
with RedactFixture(FIXTURE_PATH, options) as redacted_path:
metadata = subprocess.check_output(["pdfinfo", "-meta", redacted_path])
self.assertIn(b"Sentinel", metadata)
self.assertNotIn(b"Writer", metadata)
def test_comment(self): options = pdf_redactor.RedactorOptions() options.content_filters = [ # replacement for the comment text ( re.compile(re.escape(u"I have a comment!")), lambda m: "all gone" ), # replacement for the comment title ( re.compile(re.escape(u"Unknown Author")), lambda m: "Some Person" ), ] with RedactFixture(FIXTURE_PATH, options) as redacted_path: text = pdf_to_text(redacted_path)
def smoke_test_file(path):
options = pdf_redactor.RedactorOptions()
options.input_stream = open(path, "rb")
options.output_stream = io.BytesIO()
options.content_filters = [(re.compile("\w+"),
lambda match: match.group(0))]
options.metadata_filters = {"ALL": [metadata_filter]}
try:
pdf_redactor.redactor(options)
except (pdfrw.errors.PdfParseError, IndexError, AssertionError,
xml.etree.ElementTree.ParseError, TypeError, AttributeError,
StopIteration, ValueError) as e:
print("{0} while reading {1}".format(e.__class__.__name__, path),
file=sys.stderr)
print(traceback.format_exc(), file=sys.stderr)
finally:
options.input_stream.close()
def test_link(self):
options = pdf_redactor.RedactorOptions()
options.content_filters = [
# replacement for the link text
(re.compile(re.escape(u"link to issue #13")),
lambda m: "this link was removed"),
]
options.link_filters = [
lambda href, annotation: "https://www.google.com"
]
with RedactFixture(FIXTURE_PATH, options) as redacted_path:
text = pdf_to_text(redacted_path)
self.assertNotIn("link to issue #13", text)
self.assertIn("this link was re#o#e#", text) # glyph replacements
html = pdf_to_html(redacted_path)
self.assertNotIn("github", html)
self.assertIn('href="https://www.google.com"', html)
# Example file to print the text layer of a PDF.
import re, io, sys
import pdf_redactor
## Set options.
def printer(m):
s = m.group(0)
if sys.version_info < (3, ):
s = s.encode("utf8")
print(s)
return ""
options = pdf_redactor.RedactorOptions()
options.output_stream = io.BytesIO() # null
options.content_filters = [(re.compile("[\w\W]+"), printer)]
pdf_redactor.redactor(options)
def redact(fname, searchlist):
"""Lets Redact the pdf
"""
#fname = sys.argv[1] # filename
doc = fitz.open(fname)
doc.setMetadata({}) # clear metadata
doc._delXmlMetadata() # clear any XML metadata
new_doc = False # indicator if anything found at all
for page in doc: # scan through the pages
for word in searchlist:
print(f"Redacting word {word} in document {doc.name}")
found = mark_word(page, word) # mark the page's words
if found: # if anything found ...
new_doc = True
print("found '%s' %i times on page %i" % (word, found, page.number + 1))
if new_doc:
doc.save("marked-" + str(doc.name).split('/')[-1])
import re
from datetime import datetime
import pdf_redactor
## Set options.
options = pdf_redactor.RedactorOptions()
options.metadata_filters = {
# Perform some field filtering --- turn the Title into uppercase.
"Title": [lambda value: value.upper()],
# Set some values, overriding any value present in the PDF.
"Producer": [lambda value: "My Name"],
"CreationDate": [lambda value: datetime.utcnow()],
# Clear all other fields.
"DEFAULT": [lambda value: None],
}
# Clear any XMP metadata, if present.
options.xmp_filters = [lambda xml: None]
# Redact things that look like social security numbers, replacing the
# text with X's.
options.content_filters = [
# First convert all dash-like characters to dashes.
(
# re.compile(u"[−–—~‐]"),
# lambda m : "-"
re.compile(u"LibreOffice"),
lambda m: "X"
),
# Then do an actual SSL regex.
# See https://github.com/opendata/SSN-Redaction for why this regex is complicated.
# (
# re.compile(r"(?<!\d)(?!666|000|9\d{2})([OoIli0-9]{3})([\s-]?)(?!00)([OoIli0-9]{2})\2(?!0{4})([OoIli0-9]{4})(?!\d)"),
# lambda m : "XXX-XX-XXXX"
# ),
# Content filter that runs on the text comment annotation body.
(
re.compile(r"comment!"),
lambda m: "annotation?"
)#,
]
# Filter the link target URI.
options.link_filters = [
lambda href, annotation: "https://www.google.com"
]
# Perform the redaction using PDF on standard input and writing to standard output.
pdf_redactor.redactor(options)
# THE SEARCH STRING LIST
# searchlist = ['Marcus', 'Hibell', 'Lorem', 'Hampden-Sydney', 'College', 'loves']
# redact('Lorem.pdf',searchlist)
# WORKING VERSION FOR A SINGLE WORD
# fname = sys.argv[1] # filename
# text = sys.argv[2] # search string
# doc = fitz.open(fname)
# print("underlining words containing '%s' in document '%s'" % (text, doc.name))
# new_doc = False # indicator if anything found at all
# for page in doc: # scan through the pages
# found = mark_word(page, text) # mark the page's words
# if found: # if anything found ...
# new_doc = True
# print("found '%s' %i times on page %i" % (text, found, page.number + 1))
# if new_doc:
# doc.save("marked-" + str(doc.name).split('/')[-1])