From aad73ab7b281381e464446e16bd9c88344f89d11 Mon Sep 17 00:00:00 2001 From: Oleg Broytman Date: Tue, 11 Mar 2014 20:39:11 +0400 Subject: [PATCH] Add options --save-headers/body/message --- ANNOUNCE | 40 +++------------------------- TODO | 4 --- mimedecode.docbook | 36 +++++++++++++++++++++++++ mimedecode.py | 65 +++++++++++++++++++++++++++++++++++++++------- 4 files changed, 96 insertions(+), 49 deletions(-) diff --git a/ANNOUNCE b/ANNOUNCE index c9bb92f..201eccd 100644 --- a/ANNOUNCE +++ b/ANNOUNCE @@ -33,46 +33,14 @@ level). Add option -B to skip content-transfer-decoding binary attachments. - Add option -O to set the destination directory. + Add options --save-headers, --save-body and --save-message to save decoded +headers/bodies/messages to files. + + Add option -O to set the destination directory for output files. Fix a minor bug: if a multipart message (or a subpart) lacks any textual content - avoid putting an excessive newline. -WHAT'S NEW in version 2.4.0 (2014-03-08) - - Change option -d to accept a comma-separated list of headers: --d h1,h2,h3,... - - Change option -d to decode all headers and accept a list of exceptions: --d *,-h1,-h2,... - - Change option -p to accept lists of headers and parameters: --p h1,h2,h3,..:p1,p2,p3,.. - - Allow * and exceptions for -p in the headers and parameters lists: --p *,-h1,-h2,-h3:p1,p2,p3 --p h1,h2,h3:*,-p1,-p2,-p3 --p *,-h1,-h2,-h3:*,-p1,-p2,-p3 - - Change option -r to accept a list of headers: -r h1,h2,h3,... - - Change option -r to remove all headers and accept a list of exceptions: --r *,-h1,-h2,... - - Change option -R to accept lists of headers and parameters: --R h1,h2,h3:p1,p2,p3 --R h1,h2,h3:*,-p1,-p2,-p3 --R *,-h1,-h2,-h3:p1,p2,p3 --R *,-h1,-h2,-h3:*,-p1,-p2,-p3 - - Publish docs in html format. - - Add ChangeLog. - -WHAT'S NEW in version 2.3.7 (2014-02-23) - - Add option -r to remove headers and option -R to remove headers parameters. - WHERE TO GET Home page: http://phdru.name/Software/Python/#mimedecode diff --git a/TODO b/TODO index ec2be24..c750676 100644 --- a/TODO +++ b/TODO @@ -1,7 +1,3 @@ -Add options --save-headers, --save-body and --save-message to save -decoded headers/bodies/messages to files. - - Release 2.5.0. diff --git a/mimedecode.docbook b/mimedecode.docbook index 0a69021..897f0bc 100644 --- a/mimedecode.docbook +++ b/mimedecode.docbook @@ -92,6 +92,9 @@ + + + @@ -440,6 +443,26 @@ + + --save-headers mask + + + + --save-body mask + + + + --save-message mask + + + Append mask to a list of content types to save to a file; + --save-headers saves only decoded headers of the message (or + subpart); --save-body saves only decoded body; --save-message saves + the entire message (or subpart). + + + + -O dest_dir @@ -494,6 +517,19 @@ cat input_file | mimedecode.py -o output_file Initially all 4 lists are empty, so without any additional parameters the program always uses the default decoding. + + + The 3 save list options (--save-headers/body/message) are similar. They make + the program to save every non-multipart subpart (only headers, or body, or + the entire subpart) that corresponds to the given mask to a file. Before + saving the message (or the subpart) is decoded according to all other options + and placed to the output stream as usual. Filename for the file is created + using "filename" parameter from the Content-Disposition header, or "name" + parameter from the Content-Type header if one of those exist; a serial + counter is prepended to the filename to avoid collisions; if there are no + name/filename parameters, the filename is just the serial counter. The file + is saved in the directory set with -O (default is the current directory). + diff --git a/mimedecode.py b/mimedecode.py index e832017..b461284 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 dest_dir] [-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') @@ -266,6 +266,33 @@ 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(os.path.join(g.destination_dir, fname), 'w') + output = outfile.write + if save_headers: + output_headers(msg) + if save_body: + output(outstring) + outfile.close() + output = save_output def decode_part(msg): @@ -299,23 +326,30 @@ 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 + break elif content_type in g.error_mask: raise ValueError, "content type `%s' prohibited" % content_type + 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) def decode_multipart(msg): "Decode multipart" @@ -392,6 +426,11 @@ 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 @@ -405,7 +444,9 @@ def get_opts(): try: options, arguments = getopt(sys.argv[1:], 'hVcCDPH:f:d:p:r:R:b:B:e:i:t:O:o:', - ['help', 'version', 'host=', 'set-header=', 'set-param=']) + ['help', 'version', 'host=', + 'save-headers=', 'save-body=', 'save-message=', + 'set-header=', 'set-param=']) except GetoptError: usage(1) @@ -455,6 +496,12 @@ 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': -- 2.39.2