X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;f=mimedecode.py;h=c1731d6336c5ab8eff9e5928a61a9cce1181ddc2;hb=4a8b456be276949fafd75df3c09b34ddcc2d052e;hp=3a8cbbe533bbd29f4e7589b40ee44d8b635fa8bd;hpb=44f274a71a4b30c8d6f54b7ea374c8d7f8e95eed;p=mimedecode.git diff --git a/mimedecode.py b/mimedecode.py index 3a8cbbe..c1731d6 100755 --- a/mimedecode.py +++ b/mimedecode.py @@ -18,7 +18,7 @@ Broytman mimedecode.py version %s, %s def usage(code=0, errormsg=''): version(0) sys.stdout.write("""\ - Usage: %s [-h|--help] [-V|--version] [-cCDP] [-H|--host=hostname] [-f charset] [-d header1[,h2,...]|*[,-h1,...]] [-p header1[,h2,h3,...]:param1[,p2,p3,...]] [-r header1[,h2,...]|*[,-h1,...]] [-R header1[,h2,h3,...]:param1[,p2,p3,...]] [--set-header header:value] [--set-param header:param=value] [-Bbeit mask] [-o output_file] [input_file [output_file]] + Usage: %s [-h|--help] [-V|--version] [-cCDP] [-H|--host=hostname] [-f charset] [-d header1[,h2,...]|*[,-h1,...]] [-p header1[,h2,h3,...]:param1[,p2,p3,...]] [-r header1[,h2,...]|*[,-h1,...]] [-R header1[,h2,h3,...]:param1[,p2,p3,...]] [--set-header header:value] [--set-param header:param=value] [-Bbeit mask] [--save-headers|body|message mask] [-O dest_dir] [-o output_file] [input_file [output_file]] """ % me) if errormsg: sys.stderr.write(errormsg + '\n') @@ -34,12 +34,9 @@ def output_headers(msg): output("\n") # End of headers -def recode(s, charset): - return unicode(s, charset, "replace").encode(g.default_encoding, "replace") - def recode_if_needed(s, charset): if charset and charset.lower() <> g.default_encoding: - s = recode(s, charset) + s = unicode(s, charset, "replace").encode(g.default_encoding, "replace") return s @@ -77,9 +74,6 @@ def decode_header(msg, header): set_header(msg, header, new_value) -def _decode_header_param(s): - return recode_if_needed(s[2], s[0]) - def decode_header_param(msg, header, param): "Decode mail header's parameter (if exists) and put it back, if it was encoded" @@ -87,7 +81,7 @@ def decode_header_param(msg, header, param): value = msg.get_param(param, header=header) if value: if isinstance(value, tuple): - new_value = _decode_header_param(value) + new_value = recode_if_needed(value[2], value[0]) else: new_value = _decode_header(value) if new_value <> value: # do not bother to touch msg if not changed @@ -266,6 +260,33 @@ def totext(msg, instring): output_headers(msg) output(s) + return s + + +def _save_message(msg, outstring, save_headers=False, save_body=False): + for header, param in ( + ("Content-Disposition", "filename"), + ("Content-Type", "name"), + ): + fname = msg.get_param(param, header=header) + if fname: + fname = '-' + fname + break + else: + fname = '' + g.save_counter += 1 + fname = str(g.save_counter) + fname + + global output + save_output = output + outfile = open_output_file(fname) + output = outfile.write + if save_headers: + output_headers(msg) + if save_body: + output(outstring) + outfile.close() + output = save_output def decode_part(msg): @@ -285,7 +306,10 @@ def decode_part(msg): left_binary = False for content_type in masks: - if content_type in g.binary_mask: + if content_type in g.totext_mask or \ + content_type in g.decoded_binary_mask: + break + elif content_type in g.binary_mask: left_binary = True break @@ -299,23 +323,34 @@ def decode_part(msg): for content_type in masks: if content_type in g.totext_mask: - totext(msg, outstring) - return + outstring = totext(msg, outstring) + break elif content_type in g.binary_mask or \ content_type in g.decoded_binary_mask: output_headers(msg) output(outstring) - return + break elif content_type in g.ignore_mask: output_headers(msg) - output("\nMessage body of type `%s' skipped.\n" % content_type) - return + output("\nMessage body of type %s skipped.\n" % ctype) + break elif content_type in g.error_mask: - raise ValueError, "content type `%s' prohibited" % content_type + break + else: + # Neither content type nor masks were listed - decode by default + outstring = totext(msg, outstring) - # Neither content type nor masks were listed - decode by default - totext(msg, outstring) + for content_type in masks: + if content_type in g.save_headers_mask: + _save_message(msg, outstring, save_headers=True, save_body=False) + elif content_type in g.save_body_mask: + _save_message(msg, outstring, save_headers=False, save_body=True) + elif content_type in g.save_message_mask: + _save_message(msg, outstring, save_headers=True, save_body=True) + for content_type in masks: + if content_type in g.error_mask: + raise ValueError, "content type %s prohibited" % ctype def decode_multipart(msg): "Decode multipart" @@ -360,6 +395,19 @@ def decode_message(msg): output(msg.as_string()) +def open_output_file(filename): + fullpath = os.path.abspath(os.path.join(g.destination_dir, filename)) + full_dir = os.path.dirname(fullpath) + create = not os.path.isdir(full_dir) + if create: + os.makedirs(full_dir) + try: + return open(fullpath, 'w') + except: + if create: + os.removedirs(full_dir) + + class GlobalOptions: from m_lib.defenc import default_encoding recode_charset = 1 # recode charset of message body @@ -392,8 +440,14 @@ class GlobalOptions: ignore_mask = [] # Ignore (skip, do not decode and do not include into output) error_mask = [] # Raise error if encounter one of these + save_counter = 0 + save_headers_mask = [] + save_body_mask = [] + save_message_mask = [] + input_filename = None output_filename = None + destination_dir = os.curdir g = GlobalOptions @@ -403,8 +457,10 @@ def get_opts(): try: options, arguments = getopt(sys.argv[1:], - 'hVcCDPH:f:d:p:r:R:b:B:e:i:t:o:', - ['help', 'version', 'host=', 'set-header=', 'set-param=']) + 'hVcCDPH:f:d:p:r:R:b:B:e:i:t:O:o:', + ['help', 'version', 'host=', + 'save-headers=', 'save-body=', 'save-message=', + 'set-header=', 'set-param=']) except GetoptError: usage(1) @@ -454,6 +510,14 @@ def get_opts(): g.ignore_mask.append(value) elif option == '-e': g.error_mask.append(value) + elif option == '--save-headers': + g.save_headers_mask.append(value) + elif option == '--save-body': + g.save_body_mask.append(value) + elif option == '--save-message': + g.save_message_mask.append(value) + elif option == '-O': + g.destination_dir = value elif option == '-o': g.output_filename = value else: @@ -470,7 +534,7 @@ if __name__ == "__main__": g.input_filename = '-' infile = sys.stdin if g.output_filename: - outfile = open(g.output_filename, 'w') + outfile = open_output_file(g.output_filename) else: g.output_filename = '-' outfile = sys.stdout @@ -483,7 +547,7 @@ if __name__ == "__main__": infile = open(arguments[0], 'r') if la == 1: if g.output_filename: - outfile = open(g.output_filename, 'w') + outfile = open_output_file(g.output_filename) else: g.output_filename = '-' outfile = sys.stdout @@ -495,7 +559,7 @@ if __name__ == "__main__": outfile = sys.stdout else: g.output_filename = arguments[1] - outfile = open(arguments[1], 'w') + outfile = open_output_file(g.output_filename) else: usage(1, 'Too many arguments') @@ -514,7 +578,7 @@ if __name__ == "__main__": msg = email.message_from_file(infile) for header, value in g.set_header_value: - msg[header] = value + set_header(msg, header, value) for header, param, value in g.set_header_param: if header in msg: