X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;f=mimedecode.py;h=e832017b33670d0cd605c1650eb00c89b21d91a8;hb=16d98dbe4bd8cb9cda80da5d1e881aecc872e486;hp=70776d3d1401bb3c39d31ef512ff853a2265d0d4;hpb=cb1f0763841bbeced908b053960baf228b692ca1;p=mimedecode.git diff --git a/mimedecode.py b/mimedecode.py index 70776d3..e832017 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] [-beit 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] [-O dest_dir] [-o output_file] [input_file [output_file]] """ % me) if errormsg: sys.stderr.write(errormsg + '\n') @@ -35,10 +35,10 @@ def output_headers(msg): def recode(s, charset): - return unicode(s, charset, "replace").encode(gopts.default_encoding, "replace") + return unicode(s, charset, "replace").encode(g.default_encoding, "replace") def recode_if_needed(s, charset): - if charset and charset.lower() <> gopts.default_encoding: + if charset and charset.lower() <> g.default_encoding: s = recode(s, charset) return s @@ -132,7 +132,7 @@ def _remove_headers_params(msg, header, remove_all_params, param_list): def decode_headers(msg): "Decode message headers according to global options" - for header_list in gopts.remove_headers: + for header_list in g.remove_headers: header_list = header_list.split(',') if header_list[0] == '*': # Remove all headers except listed header_list = _get_exceptions(header_list) @@ -143,7 +143,7 @@ def decode_headers(msg): for header in header_list: del msg[header] - for header_list, param_list in gopts.remove_headers_params: + for header_list, param_list in g.remove_headers_params: header_list = header_list.split(',') param_list = param_list.split(',') remove_all_params = param_list[0] == '*' # Remove all params except listed @@ -158,7 +158,7 @@ def decode_headers(msg): for header in header_list: _remove_headers_params(msg, header, remove_all_params, param_list) - for header_list in gopts.decode_headers: + for header_list in g.decode_headers: header_list = header_list.split(',') if header_list[0] == '*': # Decode all headers except listed header_list = _get_exceptions(header_list) @@ -169,7 +169,7 @@ def decode_headers(msg): for header in header_list: decode_header(msg, header) - for header_list, param_list in gopts.decode_header_params: + for header_list, param_list in g.decode_header_params: header_list = header_list.split(',') param_list = param_list.split(',') decode_all_params = param_list[0] == '*' # Decode all params except listed @@ -239,7 +239,7 @@ def decode_body(msg, s): os.remove(filename) set_content_type(msg, "text/plain") - msg["X-MIME-Autoconverted"] = "from %s to text/plain by %s id %s" % (content_type, gopts.host_name, command.split()[0]) + msg["X-MIME-Autoconverted"] = "from %s to text/plain by %s id %s" % (content_type, g.host_name, command.split()[0]) return s @@ -248,11 +248,11 @@ def recode_charset(msg, s): "Recode charset of the message to the default charset" save_charset = charset = msg.get_content_charset() - if charset and charset.lower() <> gopts.default_encoding: + if charset and charset.lower() <> g.default_encoding: s = recode_if_needed(s, charset) content_type = msg.get_content_type() - set_content_type(msg, content_type, gopts.default_encoding) - msg["X-MIME-Autoconverted"] = "from %s to %s by %s id %s" % (save_charset, gopts.default_encoding, gopts.host_name, me) + set_content_type(msg, content_type, g.default_encoding) + msg["X-MIME-Autoconverted"] = "from %s to %s by %s id %s" % (save_charset, g.default_encoding, g.host_name, me) return s @@ -261,7 +261,7 @@ def totext(msg, instring): # Decode body and recode charset s = decode_body(msg, instring) - if gopts.recode_charset: + if g.recode_charset: s = recode_charset(msg, s) output_headers(msg) @@ -272,14 +272,6 @@ def decode_part(msg): "Decode one part of the message" decode_headers(msg) - encoding = msg["Content-Transfer-Encoding"] - - if encoding in (None, '', '7bit', '8bit', 'binary'): - outstring = str(msg.get_payload()) - else: # Decode from transfer ecoding to text or binary form - outstring = str(msg.get_payload(decode=1)) - set_header(msg, "Content-Transfer-Encoding", "8bit") - msg["X-MIME-Autoconverted"] = "from %s to 8bit by %s id %s" % (encoding, gopts.host_name, me) # Test all mask lists and find what to do with this content type masks = [] @@ -291,19 +283,34 @@ def decode_part(msg): masks.append(mtype + '/*') masks.append('*/*') + left_binary = False + for content_type in masks: + if content_type in g.binary_mask: + left_binary = True + break + + encoding = msg["Content-Transfer-Encoding"] + if left_binary or encoding in (None, '', '7bit', '8bit', 'binary'): + outstring = msg.get_payload() + else: # Decode from transfer ecoding to text or binary form + outstring = msg.get_payload(decode=1) + set_header(msg, "Content-Transfer-Encoding", "8bit") + msg["X-MIME-Autoconverted"] = "from %s to 8bit by %s id %s" % (encoding, g.host_name, me) + for content_type in masks: - if content_type in gopts.totext_mask: + if content_type in g.totext_mask: totext(msg, outstring) return - elif content_type in gopts.binary_mask: + elif content_type in g.binary_mask or \ + content_type in g.decoded_binary_mask: output_headers(msg) output(outstring) return - elif content_type in gopts.ignore_mask: + elif content_type in g.ignore_mask: output_headers(msg) output("\nMessage body of type `%s' skipped.\n" % content_type) return - elif content_type in gopts.error_mask: + elif content_type in g.error_mask: raise ValueError, "content type `%s' prohibited" % content_type # Neither content type nor masks were listed - decode by default @@ -318,12 +325,19 @@ def decode_multipart(msg): if msg.preamble: # Preserve the first part, it is probably not a RFC822-message output(msg.preamble) # Usually it is just a few lines of text (MIME warning) + if msg.preamble is not None: + output("\n") + first_subpart = True boundary = msg.get_boundary() for subpart in msg.get_payload(): if boundary: - output("\n--%s\n" % boundary) + if first_subpart: + first_subpart = False + else: + output("\n") + output("--%s\n" % boundary) # Recursively decode all parts of the subpart decode_message(subpart) @@ -373,22 +387,24 @@ class GlobalOptions: set_header_param = [] totext_mask = [] # A list of content-types to decode - binary_mask = [] # A list to pass through + binary_mask = [] # A list of content-types to pass through + decoded_binary_mask = [] # A list of content-types to pass through (content-transfer-decoded) ignore_mask = [] # Ignore (skip, do not decode and do not include into output) error_mask = [] # Raise error if encounter one of these input_filename = None output_filename = None + destination_dir = os.curdir -gopts = GlobalOptions +g = GlobalOptions -def get_opt(): +def get_opts(): from getopt import getopt, GetoptError try: options, arguments = getopt(sys.argv[1:], - 'hVcCDPH:f:d:p:r:R:b:e:i:t:o:', + 'hVcCDPH:f:d:p:r:R:b:B:e:i:t:O:o:', ['help', 'version', 'host=', 'set-header=', 'set-param=']) except GetoptError: usage(1) @@ -399,46 +415,50 @@ def get_opt(): elif option in ('-V', '--version'): version() elif option == '-c': - gopts.recode_charset = 1 + g.recode_charset = 1 elif option == '-C': - gopts.recode_charset = 0 + g.recode_charset = 0 elif option in ('-H', '--host'): - gopts.host_name = value + g.host_name = value elif option == '-f': - gopts.default_encoding = value + g.default_encoding = value elif option == '-d': if value.startswith('*'): - gopts.decode_headers = [] - gopts.decode_headers.append(value) + g.decode_headers = [] + g.decode_headers.append(value) elif option == '-D': - gopts.decode_headers = [] + g.decode_headers = [] elif option == '-p': - gopts.decode_header_params.append(value.split(':', 1)) + g.decode_header_params.append(value.split(':', 1)) elif option == '-P': - gopts.decode_header_params = [] + g.decode_header_params = [] elif option == '-r': - gopts.remove_headers.append(value) + g.remove_headers.append(value) elif option == '-R': - gopts.remove_headers_params.append(value.split(':', 1)) + g.remove_headers_params.append(value.split(':', 1)) elif option == '--set-header': - gopts.set_header_value.append(value.split(':', 1)) + g.set_header_value.append(value.split(':', 1)) elif option == '--set-param': header, value = value.split(':', 1) if '=' in value: param, value = value.split('=', 1) else: param, value = value.split(':', 1) - gopts.set_header_param.append((header, param, value)) + g.set_header_param.append((header, param, value)) elif option == '-t': - gopts.totext_mask.append(value) + g.totext_mask.append(value) + elif option == '-B': + g.binary_mask.append(value) elif option == '-b': - gopts.binary_mask.append(value) + g.decoded_binary_mask.append(value) elif option == '-i': - gopts.ignore_mask.append(value) + g.ignore_mask.append(value) elif option == '-e': - gopts.error_mask.append(value) + g.error_mask.append(value) + elif option == '-O': + g.destination_dir = value elif option == '-o': - gopts.output_filename = value + g.output_filename = value else: usage(1) @@ -446,39 +466,39 @@ def get_opt(): if __name__ == "__main__": - arguments = get_opt() + arguments = get_opts() la = len(arguments) if la == 0: - gopts.input_filename = '-' + g.input_filename = '-' infile = sys.stdin - if gopts.output_filename: - outfile = open(gopts.output_filename, 'w') + if g.output_filename: + outfile = open(os.path.join(g.destination_dir, g.output_filename), 'w') else: - gopts.output_filename = '-' + g.output_filename = '-' outfile = sys.stdout elif la in (1, 2): if (arguments[0] == '-'): - gopts.input_filename = '-' + g.input_filename = '-' infile = sys.stdin else: - gopts.input_filename = arguments[0] + g.input_filename = arguments[0] infile = open(arguments[0], 'r') if la == 1: - if gopts.output_filename: - outfile = open(gopts.output_filename, 'w') + if g.output_filename: + outfile = open(os.path.join(g.destination_dir, g.output_filename), 'w') else: - gopts.output_filename = '-' + g.output_filename = '-' outfile = sys.stdout elif la == 2: - if gopts.output_filename: + if g.output_filename: usage(1, 'Too many output filenames') if (arguments[1] == '-'): - gopts.output_filename = '-' + g.output_filename = '-' outfile = sys.stdout else: - gopts.output_filename = arguments[1] - outfile = open(arguments[1], 'w') + g.output_filename = arguments[1] + outfile = open(os.path.join(g.destination_dir, g.output_filename), 'w') else: usage(1, 'Too many arguments') @@ -487,20 +507,21 @@ if __name__ == "__main__": usage() usage(1, 'Filtering from console is forbidden') - if not gopts.host_name: + if not g.host_name: import socket - gopts.host_name = socket.gethostname() + g.host_name = socket.gethostname() - gopts.outfile = outfile + g.outfile = outfile output = outfile.write msg = email.message_from_file(infile) - for header, value in gopts.set_header_value: + for header, value in g.set_header_value: msg[header] = value - for header, param, value in gopts.set_header_param: - msg.set_param(param, value, header) + for header, param, value in g.set_header_param: + if header in msg: + msg.set_param(param, value, header) try: decode_message(msg)