From 53baf637d750e839121a6f217cdc8cf36dd81ed7 Mon Sep 17 00:00:00 2001 From: Oleg Broytman Date: Sat, 23 May 2020 12:24:41 +0300 Subject: [PATCH] Docs: Convert `mimedecode.docbook` to reST Generate html/man/text using Sphinx. [skip ci] --- .gitignore | 3 - ANNOUNCE | 7 +- ChangeLog | 5 +- MANIFEST.in | 6 +- Makefile | 5 +- Makefile.4xslt | 11 - Makefile.sgmlt | 10 - Makefile.xsltproc | 11 - TODO | 3 - docs/.gitignore | 1 + docs/Makefile | 19 ++ docs/conf.py | 180 ++++++++++++ docs/index.rst | 20 ++ docs/mimedecode.rst | 355 ++++++++++++++++++++++++ mimedecode.docbook | 649 -------------------------------------------- mk-distr | 7 +- 16 files changed, 593 insertions(+), 699 deletions(-) delete mode 100644 Makefile.4xslt delete mode 100644 Makefile.sgmlt delete mode 100644 Makefile.xsltproc create mode 100644 docs/.gitignore create mode 100644 docs/Makefile create mode 100644 docs/conf.py create mode 100644 docs/index.rst create mode 100644 docs/mimedecode.rst delete mode 100644 mimedecode.docbook diff --git a/.gitignore b/.gitignore index f8cea67..d975069 100644 --- a/.gitignore +++ b/.gitignore @@ -1,6 +1,3 @@ *.py[co] /mimedecode.egg-info/ /MANIFEST -/mimedecode.html -/mimedecode.man -/mimedecode.txt diff --git a/ANNOUNCE b/ANNOUNCE index df2811b..e38e966 100644 --- a/ANNOUNCE +++ b/ANNOUNCE @@ -30,7 +30,10 @@ everything else. This is how it could be done: mimedecode -t application/pdf -t application/postscript -t text/plain -b text/html -B 'image/*' -i '*/*' -Version 3.0.1 (2020-??-??) +Version 3.1.0 (2020-??-??) + + Convert mimedecode.docbook to reST. Generate html/man/text + using Sphinx. Replaced outdated and insecure `mktemp` with `NamedTemporaryFile`. @@ -56,7 +59,7 @@ AUTHOR Oleg Broytman COPYRIGHT - Copyright (C) 2001-2018 PhiloSoft Design. + Copyright (C) 2001-2020 PhiloSoft Design. LICENSE GPL diff --git a/ChangeLog b/ChangeLog index 3117d27..7e17688 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,7 @@ -Version 3.0.1 (2020-??-??) +Version 3.1.0 (2020-??-??) + + Convert mimedecode.docbook to reST. Generate html/man/text + using Sphinx. Replaced outdated and insecure `mktemp` with `NamedTemporaryFile`. diff --git a/MANIFEST.in b/MANIFEST.in index 01d6b7d..621ef43 100644 --- a/MANIFEST.in +++ b/MANIFEST.in @@ -1,5 +1,7 @@ -global-include Makefile* *.py *.txt *.txt-py3 +global-include Makefile* *.py *.rst *.txt *.txt-py3 include ANNOUNCE ChangeLog MANIFEST.in TODO -include mimedecode.docbook mimedecode.man mimedecode.html +include mimedecode.1 mimedecode.html include mk-distr tox.ini include test/.mailcap test/README test/test_all +recursive-include docs* *.css *.js *.html *.gif *.png +recursive-exclude docs*/_build * diff --git a/Makefile b/Makefile index 5ba230c..4a90c04 100644 --- a/Makefile +++ b/Makefile @@ -4,9 +4,8 @@ all: docs test clean distr .PHONY: docs -docs: mimedecode.html mimedecode.man mimedecode.txt - -include Makefile.xsltproc +docs: + make -C docs html man text .PHONY: distr diff --git a/Makefile.4xslt b/Makefile.4xslt deleted file mode 100644 index cea0f13..0000000 --- a/Makefile.4xslt +++ /dev/null @@ -1,11 +0,0 @@ -DOCBOOK_XSL=/usr/share/xml/docbook/stylesheet/docbook-xsl - -mimedecode.html: mimedecode.docbook Makefile.4xslt - 4xslt $< $(DOCBOOK_XSL)/html/docbook.xsl >$@ - -mimedecode.man: mimedecode.docbook Makefile.4xslt - 4xslt $< $(DOCBOOK_XSL)/manpages/docbook.xsl - mv mimedecode.1 $@ - -mimedecode.txt: mimedecode.html Makefile.4xslt - elinks -dump -no-numbering -no-references $< >$@ diff --git a/Makefile.sgmlt b/Makefile.sgmlt deleted file mode 100644 index ba8e333..0000000 --- a/Makefile.sgmlt +++ /dev/null @@ -1,10 +0,0 @@ -mimedecode.html: mimedecode.docbook Makefile.sgmlt - sgmltools -b html $< - mv mimedecode/mimedecode.html mimedecode.html - rmdir mimedecode - -mimedecode.man: mimedecode.docbook Makefile.sgmlt - docbook-to-man $< >$@ - -mimedecode.txt: mimedecode.docbook Makefile.sgmlt - sgmltools -b txt $< diff --git a/Makefile.xsltproc b/Makefile.xsltproc deleted file mode 100644 index 421f413..0000000 --- a/Makefile.xsltproc +++ /dev/null @@ -1,11 +0,0 @@ -DOCBOOK_XSL=/usr/share/xml/docbook/stylesheet/docbook-xsl - -mimedecode.html: mimedecode.docbook Makefile.xsltproc - xsltproc $(DOCBOOK_XSL)/html/docbook.xsl $< >$@ - -mimedecode.man: mimedecode.docbook Makefile.xsltproc - xsltproc $(DOCBOOK_XSL)/manpages/docbook.xsl $< - mv mimedecode.1 $@ - -mimedecode.txt: mimedecode.html Makefile.xsltproc - elinks -dump -no-numbering -no-references $< >$@ diff --git a/TODO b/TODO index fdc235e..8f6df9e 100644 --- a/TODO +++ b/TODO @@ -1,6 +1,3 @@ -Convert mimedecode.docbook to something simpler - asciidoc, markdown, reST. - - Convert mimedecode.py library from global functions to a class. diff --git a/docs/.gitignore b/docs/.gitignore new file mode 100644 index 0000000..ba65b13 --- /dev/null +++ b/docs/.gitignore @@ -0,0 +1 @@ +/_build/ diff --git a/docs/Makefile b/docs/Makefile new file mode 100644 index 0000000..298ea9e --- /dev/null +++ b/docs/Makefile @@ -0,0 +1,19 @@ +# Minimal makefile for Sphinx documentation +# + +# You can set these variables from the command line. +SPHINXOPTS = +SPHINXBUILD = sphinx-build +SOURCEDIR = . +BUILDDIR = _build + +# Put it first so that "make" without argument is like "make help". +help: + @$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O) + +.PHONY: help Makefile + +# Catch-all target: route all unknown targets to Sphinx using the new +# "make mode" option. $(O) is meant as a shortcut for $(SPHINXOPTS). +%: Makefile + @$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O) \ No newline at end of file diff --git a/docs/conf.py b/docs/conf.py new file mode 100644 index 0000000..1b0e71c --- /dev/null +++ b/docs/conf.py @@ -0,0 +1,180 @@ +# -*- coding: utf-8 -*- +# +# Configuration file for the Sphinx documentation builder. +# +# This file does only contain a selection of the most common options. For a +# full list see the documentation: +# http://www.sphinx-doc.org/en/master/config + +# -- Path setup -------------------------------------------------------------- + +# If extensions (or modules to document with autodoc) are in another directory, +# add these directories to sys.path here. If the directory is relative to the +# documentation root, use os.path.abspath to make it absolute, like shown here. +# +from datetime import date +import os +import sys +# sys.path.insert(0, os.path.abspath('.')) + + +# -- Project information ----------------------------------------------------- + +project = 'mimedecode' +author = 'Oleg Broytman' +copyright = u'2001-%d, Oleg Broytman' % date.today().year + +sys.path.insert(0, os.path.abspath('..')) +from mimedecode.__version__ import __version__ +# The short X.Y version. +version = '.'.join(__version__.split('.')[:2]) +# The full version, including alpha/beta/rc tags. +release = __version__ + + +# -- General configuration --------------------------------------------------- + +# If your documentation needs a minimal Sphinx version, state it here. +# +# needs_sphinx = '1.0' + +# Add any Sphinx extension module names here, as strings. They can be +# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom +# ones. +extensions = [ + 'sphinx.ext.autodoc', +] + +# Add any paths that contain templates here, relative to this directory. +templates_path = ['_templates'] + +# The suffix(es) of source filenames. +# You can specify multiple suffix as a list of string: +# +# source_suffix = ['.rst', '.md'] +source_suffix = '.rst' + +# The master toctree document. +master_doc = 'mimedecode' + +# The language for content autogenerated by Sphinx. Refer to documentation +# for a list of supported languages. +# +# This is also used if you do content translation via gettext catalogs. +# Usually you set "language" from the command line for these cases. +language = None + +# List of patterns, relative to source directory, that match files and +# directories to ignore when looking for source files. +# This pattern also affects html_static_path and html_extra_path. +exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store'] + +# The name of the Pygments (syntax highlighting) style to use. +pygments_style = None + + +# -- Options for HTML output ------------------------------------------------- + +# The theme to use for HTML and HTML Help pages. See the documentation for +# a list of builtin themes. +# +html_theme = 'alabaster' + +# Theme options are theme-specific and customize the look and feel of a theme +# further. For a list of options available for each theme, see the +# documentation. +# +# html_theme_options = {} + +# Add any paths that contain custom static files (such as style sheets) here, +# relative to this directory. They are copied after the builtin static files, +# so a file named "default.css" will overwrite the builtin "default.css". +html_static_path = ['_static'] + +# Custom sidebar templates, must be a dictionary that maps document names +# to template names. +# +# The default sidebars (for documents that don't match any pattern) are +# defined by theme itself. Builtin themes are using these templates by +# default: ``['localtoc.html', 'relations.html', 'sourcelink.html', +# 'searchbox.html']``. +# +# html_sidebars = {} + + +# -- Options for HTMLHelp output --------------------------------------------- + +# Output file base name for HTML help builder. +htmlhelp_basename = 'mimedecodedoc' + + +# -- Options for LaTeX output ------------------------------------------------ + +latex_elements = { + # The paper size ('letterpaper' or 'a4paper'). + # + # 'papersize': 'letterpaper', + + # The font size ('10pt', '11pt' or '12pt'). + # + # 'pointsize': '10pt', + + # Additional stuff for the LaTeX preamble. + # + # 'preamble': '', + + # Latex figure (float) alignment + # + # 'figure_align': 'htbp', +} + +# Grouping the document tree into LaTeX files. List of tuples +# (source start file, target name, title, +# author, documentclass [howto, manual, or own class]). +latex_documents = [ + (master_doc, 'mimedecode.tex', 'mimedecode Documentation', + 'Oleg Broytman', 'manual'), +] + + +# -- Options for manual page output ------------------------------------------ + +# One entry per manual page. List of tuples +# (source start file, name, description, authors, manual section). +man_pages = [ + (master_doc, 'mimedecode', 'mimedecode Documentation', + [author], 1) +] + + +# -- Options for Texinfo output ---------------------------------------------- + +# Grouping the document tree into Texinfo files. List of tuples +# (source start file, target name, title, author, +# dir menu entry, description, category) +texinfo_documents = [ + (master_doc, 'mimedecode', 'mimedecode Documentation', + author, 'mimedecode', 'One line description of project.', + 'Miscellaneous'), +] + + +# -- Options for Epub output ------------------------------------------------- + +# Bibliographic Dublin Core info. +epub_title = project + +# The unique identifier of the text. This can be a ISBN number +# or the project homepage. +# +# epub_identifier = '' + +# A unique identification for the text. +# +# epub_uid = '' + +# A list of files that should not be packed into the epub file. +epub_exclude_files = ['search.html'] + + +# -- Extension configuration ------------------------------------------------- diff --git a/docs/index.rst b/docs/index.rst new file mode 100644 index 0000000..669371e --- /dev/null +++ b/docs/index.rst @@ -0,0 +1,20 @@ +.. mimedecode documentation master file, created by + sphinx-quickstart on Sat May 23 12:01:51 2020. + You can adapt this file completely to your liking, but it should at least + contain the root `toctree` directive. + +Welcome to mimedecode's documentation! +====================================== + +.. toctree:: + :maxdepth: 2 + :caption: Contents: + + + +Indices and tables +================== + +* :ref:`genindex` +* :ref:`modindex` +* :ref:`search` diff --git a/docs/mimedecode.rst b/docs/mimedecode.rst new file mode 100644 index 0000000..2e65036 --- /dev/null +++ b/docs/mimedecode.rst @@ -0,0 +1,355 @@ +Name +---- + +mimedecode -- decode MIME message + +Synopsis +-------- + +mimedecode [ -h|--help ] [ -V|--version ] [ -cCDP ] [ -f charset ] +[ -H|--host=hostname ] [ -d header1[,header2,header3...] ] +[ -d \*[,-header1,-header2,-header3...] ] +[ -p header1[,header2,header3,...]:param1[,param2,param3,...] ] +[ -p \*[,-header1,-header2,-header3,...]:param1[,param2,param3,...] ] +[ -p header1[,header2,header3,...]:\*[,-param1,-param2,-param3,...] ] +[ -p \*[,-header1,-header2,-header3,...]:\*[,-param1,-param2,-param3,...] ] +[ -r header1[,header2,header3...] ] [ -r \*[,-header1,-header2,-header3...] ] +[ -R header1[,header2,header3,...]:param1[,param2,param3,...] ] +[ -R \*[,-header1,-header2,-header3,...]:param1[,param2,param3,...] ] +[ -R header1[,header2,header3,...]:\*[,-param1,-param2,-param3,...] ] +[ -R \*[,-header1,-header2,-header3,...]:\*[,-param1,-param2,-param3,...] ] +[ --set-header header:value ] [ --set-param header:param=value ] +[ -BbeIit mask ] [ --save-headers|body|message mask ] [ -O dest_dir ] +[ -o output_file ] [input_file [output_file] ] + +DESCRIPTION +----------- + +Mail users, especially in non-English countries, often find that mail +messages arrived in different formats, with different content types, in +different encodings and charsets. Usually it is good because it allows to +use an appropriate format/encoding/whatever. Sometimes, though, some +unification is desirable. For example, one may want to put mail messages +into an archive, make HTML indices, run search indexer, etc. In such +situations converting messages to text in one character set and skipping +some binary attachments is much desirable. + +Here is a solution - mimedecode! + +This is a program to decode MIME messages. The program expects one input +file (either on command line or on stdin) which is treated as an RFC822 +message, and decodes to stdout or an output file. If the file is not an +RFC822 message it is just copied to the output one-to-one. If the file is +a simple RFC822 message it is decoded as one part. If it is a MIME message +with multiple parts ("attachments") all non-multipart subparts are +decoded. Decoding can be controlled by the command-line options. + +First, for every part the program removes headers and parameters listed +with -r and -R options. Then, Subject and Content-Disposition headers (and +all headers listed with -d and -p options) are examined. If any of those +exists, they are decoded according to RFC2047. Content-Disposition header +is not decoded (if it was not listed in option -d) - only its "filename" +parameter. Encoded header parameters violate the RFC, but widely deployed +anyway by ignorant coders who never even heard about RFCs. Correct +parameter encoding specified by RFC2231. This program decodes +RFC2231-encoded parameters, too. + +Then the body of the message (or the current part) is decoded. Decoding +starts with looking at header Content-Transfer-Encoding. If the header +specifies non-8bit encoding (usually base64 or quoted-printable), the body +is converted to 8bit (can be prevented with -B). Then if its content type +is multipart (multipart/related or multipart/mixed, e.g) every part is +recursively decoded. If it is not multipart, mailcap database is consulted +to find a way to convert the body to plain text (can be prevented with +options -Bbei). (The author has no idea how mailcap can be configured on +OSes other than POSIX, please don't ask; users can consult an example at +https://phdru.name/Software/dotfiles/mailcap.html). The decoding process +uses the first copiousoutput filter it can find. If there are no filters +the body just passed as is. + +Then Content-Type header is consulted for charset. If it is not equal to +the current locale charset and recoding is allowed (see options -Cc) the +body text is recoded. Finally message headers and the body are flushed to +stdout. + +Please be reminded that in the following options asterisk is a shell +metacharacter and should be escaped or quoted. Either write -d \*,-h1,-h2 +or -d '\*,-h1,-h2' or such. + +OPTIONS +------- + +-h, -help + + Print brief usage help and exit. + +-V, --version + + Print version and exit. + +-c + + Recode different character sets in message bodies to the current + default charset; this is the default. + +-C + + Do not recode character sets in message bodies. + +-f charset + + Force this charset to be used for recoding instead of charset from + the current locale. + +-H hostname, --host=hostname + + Use this hostname in X-MIME-Autoconverted headers instead of the + current hostname. + +-d header1[,header2,header3...] + + Add the header(s) to a list of headers to decode; initially the + list contains headers "From", "To", "Cc", "Reply-To", + "Mail-Followup-To" and "Subject". + +-d \*[,-header1,-header2,-header3...] + + This variant completely changes headers decoding. First, the list + of headers to decode is cleared (as with -D). Then all the headers + are decoded except the given list of exceptions (headers listed + with '-'). In this mode it would be meaningless to give more than + one -d options but the program doesn't enforce the limitation. + +-D + + Clear the list of headers to decode (make it empty). + +-p header1[,header2,header3,...]:param1[,param2,param3,...] + + Add the parameter(s) to a list of headers parameters to decode; + the parameter(s) will be decoded only for the given header(s). + Initially the list contains header "Content-Type", parameter + "name"; and header "Content-Disposition", parameter "filename". + +-p \*[,-header1,-header2,-header3,...]:param1[,param2,param3,...] + + Add the parameter(s) to a list of headers parameters to decode; + the parameter(s) will be decoded for all headers except the given + ones. + +-p header1[,header2,header3,...]:\*[,-param1,-param2,-param3,...] + + Decode all parameters except listed for the given list of headers. + +-p \*[,-header1,-header2,-header3,...]:\*[,-param1,-param2,-param3,...] + + Decode all parameters except listed for all headers (except + listed). + +-P + + Clear the list of headers parameters to decode (make it empty). + +-r header1[,header2,header3...] + + Add the header(s) to a list of headers to remove completely; + initially the list is empty. + +-r \*[,-header1,-header2,-header3...] + + Remove all headers except listed. + +-R header1[,header2,header3,...]:param1[,param2,param3,...] + + Add the parameter(s) to a list of headers parameters to remove; + the parameter(s) will be removed only for the given header(s). + Initially the list is empty. + +-R \*[,-header1,-header2,-header3,...]:param1[,param2,param3,...] + +-R header1[,header2,header3,...]:\*[,-param1,-param2,-param3,...] + +-R \*[,-header1,-header2,-header3,...]:\*[,-param1,-param2,-param3,...] + + Remove listed parameters (or all parameters except listed) from + these headers (or from all headers except listed). + +--set-header header:value + + The program sets or changes value for the header to the given + value (only at the top-level message). + +--set-param header:param=value + + The program sets or changes value for the header's parameter to + the given value (only at the top-level message). The header must + exist. + +-B mask + + Append mask to the list of binary content types that will be not + content-transfer-decoded (will be left as base64 or such). + +-b mask + + Append mask to the list of binary content types; if the message to + decode has a part of this type the program + content-transfer-decodes (base64 or whatever to 8bit binary) it + and outputs the decoded part as is, without any further + processing. + +-e mask + + Append mask to the list of error content types; if the message to + decode has a part of this type the program fails with ValueError. + +-I mask + + Append mask to the list of content types to completely ignore. + There will be no output - no headers, no body, no warning. For a + multipart part the entire subtree is removed. + +-i mask + + Append mask to the list of content types to ignore; if the message + to decode has a part of this type the program outputs headers but + skips the body. Instead a line "Message body of type %s skipped." + will be issued. + +-t mask + + Append mask to the list of content types to convert to text; if + the message to decode has a part of this type the program consults + mailcap database, find the first copiousoutput filter and, if any + filter is found, converts the part. + +--save-headers mask + +--save-body mask + +--save-message mask + + Append mask to lists of content types to save to files; + --save-headers saves only decoded headers of the message (or the + current subpart); --save-body saves only decoded body; + --save-message saves the entire message or subpart (headers + + body). + +-O dest_dir + + Set destination directory for the output files; if the directory + doesn't exist it will be created. Default is the current + directory. + +-o output_file + + Save output to the file related to the destination directory from + option -O. Also useful in case of redirected stdin: + +mimedecode -o output_file < input_file +cat input_file | mimedecode -o output_file + +The 5 list options (-Bbeit) require more explanation. They allow a user to +control body decoding with great flexibility. Think about said mail +archive; for example, its maintainer wants to put there only texts, +convert PDF/Postscript to text, pass HTML and images decoding base64 to +html but leaving images encoded, and ignore everything else. This is how +it could be done: + +mimedecode -t application/pdf -t application/postscript -t text/plain -b +text/html -B 'image/\*' -i '\*/\*' + +When the program decodes a message (non-MIME or a non-multipart subpart of +a MIME message), it consults Content-Type header. The content type is +searched in all 5 lists, in order "text-binary-ignore-error". If found, +appropriate action is performed. If not found, the program searches the +same lists for "type/\*" mask (the type of "text/html" is just "text"). If +found, appropriate action is performed. If not found, the program searches +the same lists for "\*/\*" mask. If found, appropriate action is performed. +If not found, the program uses the default action, which is to decode +everything to text (if mailcap specifies a filter). This algorithm allows +more specific content types to override less specific: -b image/\* will be +processed earlier than -B \*/\*. + +Options -e/-I/-i can also work with multipart subparts of a MIME message. +In case of -I/-i the entire subtree of that multipart is removed; with -i +it's replaced with ignore warning. + +Initially all 5 lists are empty, so without any additional parameters the +program always uses the default decoding (as -t \*/\*). + +The 3 save 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: headers + body) that corresponds to the given mask to +a file. Before saving the message (or the subpart) is decoded according to +all other options and is 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, or +the name/filename parameters contain forbidden characters (null, slash, +backslash) the filename is just the serial counter. + +If the file doesn't have any extensions (no dots in the value of the +name/filename parameters, or the name is just the counter) the program +tries to guess an extension by looking up the content type in mime.types +files including .mime.types file in the user's home directory (if it +exists). If the file has an extension the program doesn't try to verify +that it corresponds to the content type. + +The file is saved in the directory set with -O (default is the current +directory). The save options are proceeded before -e options so the user +can save the message that causes an error. + +ENVIRONMENT +----------- + +LANG + +LC_ALL + +LC_CTYPE + +Define current locale settings. Used to determine current default charset +(if your Python is properly installed and configured). + +BUGS +---- + +The program may produce incorrect MIME message. The purpose of the program +is to decode whatever it is possible to decode, not to produce absolutely +correct MIME output. The incorrect parts are obvious - decoded +From/To/Cc/Reply-To/Mail-Followup-To/Subject headers and filenames. Other +than that output is correct MIME message. The program does not try to +guess whether the headers are correct. For example, if a message header +states that charset is iso8859-1, but the body (HTML, for example) is +actually in utf-8 the program will recode the message with the wrong +charset. + +AUTHOR +------ + +Oleg Broytman + +COPYRIGHT +--------- + +Copyright (C) 2001-2020 PhiloSoft Design. + +LICENSE +------- + +GNU GPL + +NO WARRANTIES +------------- + +This program is distributed in the hope that it will be useful, but +WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +for more details. + +SEE ALSO +-------- + +mimedecode home page: https://phdru.name/Software/Python/#mimedecode diff --git a/mimedecode.docbook b/mimedecode.docbook deleted file mode 100644 index 29d081d..0000000 --- a/mimedecode.docbook +++ /dev/null @@ -1,649 +0,0 @@ - - - - - - - mimedecode - mimedecode.docbook - - Oleg - Broytman - phd@phdru.name - - - - 2001-2018 - PhiloSoft Design. - - - - - mimedecode - 1 - - - - mimedecode - decode MIME message - - - - - mimedecode - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - input_file - output_file - - - - - - -DESCRIPTION - - Mail users, especially in non-English countries, often find that mail - messages arrived in different formats, with different content types, in - different encodings and charsets. Usually it is good because it allows to - use an appropriate format/encoding/whatever. Sometimes, though, some - unification is desirable. For example, one may want to put mail messages - into an archive, make HTML indices, run search indexer, etc. In such - situations converting messages to text in one character set and skipping - some binary attachments is much desirable. - - - - Here is a solution - mimedecode! - - - - This is a program to decode MIME messages. The program expects one input - file (either on command line or on stdin) which is treated as an RFC822 - message, and decodes to stdout or an output file. If the file is not an - RFC822 message it is just copied to the output one-to-one. If the file is a - simple RFC822 message it is decoded as one part. If it is a MIME message - with multiple parts ("attachments") all non-multipart subparts are decoded. - Decoding can be controlled by the command-line options. - - - - First, for every part the program removes headers and parameters listed with - -r and -R options. Then, Subject and Content-Disposition headers (and all - headers listed with -d and -p options) are examined. If any of those exists, - they are decoded according to RFC2047. Content-Disposition header is not - decoded (if it was not listed in option -d) - only its "filename" parameter. - Encoded header parameters violate the RFC, but widely deployed anyway by - ignorant coders who never even heard about RFCs. Correct parameter encoding - specified by RFC2231. This program decodes RFC2231-encoded parameters, too. - - - - Then the body of the message (or the current part) is decoded. Decoding - starts with looking at header Content-Transfer-Encoding. If the header - specifies non-8bit encoding (usually base64 or quoted-printable), the body - is converted to 8bit (can be prevented with -B). Then if its content type - is multipart (multipart/related or multipart/mixed, e.g) every part is - recursively decoded. If it is not multipart, mailcap database is consulted - to find a way to convert the body to plain text (can be prevented with - options -Bbei). (The author has no idea how mailcap can be configured on - OSes other than POSIX, please don't ask; users can consult an example at - https://phdru.name/Software/dotfiles/mailcap.html). - The decoding process uses the first copiousoutput filter it can find. If - there are no filters the body just passed as is. - - - - Then Content-Type header is consulted for charset. If it is not equal to the - current locale charset and recoding is allowed (see options -Cc) the body - text is recoded. Finally message headers and the body are flushed to stdout. - - - - - - Please be reminded that in the following options asterisk is a shell - metacharacter and should be escaped or quoted. Either write -d \*,-h1,-h2 - or -d '*,-h1,-h2' or such. - - - - -OPTIONS - - - -h - -help - - - Print brief usage help and exit. - - - - - - -V - --version - - - Print version and exit. - - - - - - -c - - - Recode different character sets in message bodies to the current - default charset; this is the default. - - - - - - -C - - - Do not recode character sets in message bodies. - - - - - - -f charset - - - Force this charset to be used for recoding instead of charset from - the current locale. - - - - - - -H hostname - --host=hostname - - - Use this hostname in X-MIME-Autoconverted headers instead of the - current hostname. - - - - - - -d header1[,header2,header3...] - - - Add the header(s) to a list of headers to decode; initially the - list contains headers "From", "To", "Cc", "Reply-To", - "Mail-Followup-To" and "Subject". - - - - - - -d *[,-header1,-header2,-header3...] - - - This variant completely changes headers decoding. First, the list of - headers to decode is cleared (as with -D). Then all the headers are - decoded except the given list of exceptions (headers listed with - '-'). In this mode it would be meaningless to give more than one -d - options but the program doesn't enforce the limitation. - - - - - - -D - - - Clear the list of headers to decode (make it empty). - - - - - - -p header1[,header2,header3,...]:param1[,param2,param3,...] - - - Add the parameter(s) to a list of headers parameters to decode; - the parameter(s) will be decoded only for the given header(s). - Initially the list contains header "Content-Type", parameter "name"; - and header "Content-Disposition", parameter "filename". - - - - - - -p *[,-header1,-header2,-header3,...]:param1[,param2,param3,...] - - - Add the parameter(s) to a list of headers parameters to decode; - the parameter(s) will be decoded for all headers except the given - ones. - - - - - - -p header1[,header2,header3,...]:*[,-param1,-param2,-param3,...] - - - Decode all parameters except listed for the given list of headers. - - - - - - -p *[,-header1,-header2,-header3,...]:*[,-param1,-param2,-param3,...] - - - Decode all parameters except listed for all headers (except listed). - - - - - - -P - - - Clear the list of headers parameters to decode (make it empty). - - - - - - -r header1[,header2,header3...] - - - Add the header(s) to a list of headers to remove completely; - initially the list is empty. - - - - - - -r *[,-header1,-header2,-header3...] - - - Remove all headers except listed. - - - - - - -R header1[,header2,header3,...]:param1[,param2,param3,...] - - - Add the parameter(s) to a list of headers parameters to remove; - the parameter(s) will be removed only for the given header(s). - Initially the list is empty. - - - - - - -R *[,-header1,-header2,-header3,...]:param1[,param2,param3,...] - - - - -R header1[,header2,header3,...]:*[,-param1,-param2,-param3,...] - - - - -R *[,-header1,-header2,-header3,...]:*[,-param1,-param2,-param3,...] - - - Remove listed parameters (or all parameters except listed) from - these headers (or from all headers except listed). - - - - - - --set-header header:value - - - The program sets or changes value for the header to the given value - (only at the top-level message). - - - - - - --set-param header:param=value - - - The program sets or changes value for the header's parameter to the - given value (only at the top-level message). The header must exist. - - - - - - -B mask - - - Append mask to the list of binary content types that will be not - content-transfer-decoded (will be left as base64 or such). - - - - - - -b mask - - - Append mask to the list of binary content types; if the message to - decode has a part of this type the program content-transfer-decodes - (base64 or whatever to 8bit binary) it and outputs the decoded part - as is, without any further processing. - - - - - - -e mask - - - Append mask to the list of error content types; if the message to - decode has a part of this type the program fails with ValueError. - - - - - - -I mask - - - Append mask to the list of content types to completely ignore. - There will be no output - no headers, no body, no warning. For a - multipart part the entire subtree is removed. - - - - - - -i mask - - - Append mask to the list of content types to ignore; if the message - to decode has a part of this type the program outputs headers but - skips the body. Instead a line "Message body of type %s skipped." - will be issued. - - - - - - -t mask - - - Append mask to the list of content types to convert to text; if the - message to decode has a part of this type the program consults - mailcap database, find the first copiousoutput filter and, if any - filter is found, converts the part. - - - - - - --save-headers mask - - - - --save-body mask - - - - --save-message mask - - - Append mask to lists of content types to save to files; - --save-headers saves only decoded headers of the message (or - the current subpart); --save-body saves only decoded body; - --save-message saves the entire message or subpart (headers + - body). - - - - - - -O dest_dir - - - Set destination directory for the output files; if the directory - doesn't exist it will be created. Default is the current directory. - - - - - - -o output_file - - - Save output to the file related to the destination directory from - option -O. Also useful in case of redirected stdin: - mimedecode -o output_file < input_file -cat input_file | mimedecode -o output_file - - - - - - - The 5 list options (-Bbeit) require more explanation. They allow a user to - control body decoding with great flexibility. Think about said mail archive; - for example, its maintainer wants to put there only texts, convert - PDF/Postscript to text, pass HTML and images decoding base64 to html but - leaving images encoded, and ignore everything else. This is how it could be - done: - - - - - mimedecode -t application/pdf -t application/postscript -t text/plain - -b text/html -B 'image/*' -i '*/*' - - - - - When the program decodes a message (non-MIME or a non-multipart subpart of a - MIME message), it consults Content-Type header. The content type is searched - in all 5 lists, in order "text-binary-ignore-error". If found, appropriate - action is performed. If not found, the program searches the same lists for - "type/*" mask (the type of "text/html" is just "text"). If found, - appropriate action is performed. If not found, the program searches the same - lists for "*/*" mask. If found, appropriate action is performed. If not - found, the program uses the default action, which is to decode everything to - text (if mailcap specifies a filter). This algorithm allows more specific - content types to override less specific: -b image/* will be processed - earlier than -B */*. - - - - Options -e/-I/-i can also work with multipart subparts of a MIME message. In - case of -I/-i the entire subtree of that multipart is removed; with -i it's - replaced with ignore warning. - - - - Initially all 5 lists are empty, so without any additional parameters - the program always uses the default decoding (as -t */*). - - - - The 3 save 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: headers + body) that corresponds to the given mask to a file. - Before saving the message (or the subpart) is decoded according to all other - options and is 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, or the name/filename parameters contain forbidden - characters (null, slash, backslash) the filename is just the serial counter. - - - - If the file doesn't have any extensions (no dots in the value of the - name/filename parameters, or the name is just the counter) the program tries - to guess an extension by looking up the content type in mime.types files - including .mime.types file in the user's home directory (if it exists). If - the file has an extension the program doesn't try to verify that it - corresponds to the content type. - - - - The file is saved in the directory set with -O (default is the current - directory). The save options are proceeded before -e options so the user can - save the message that causes an error. - - - - - -ENVIRONMENT - - LANG - LC_ALL - LC_CTYPE - - - Define current locale settings. Used to determine current default charset (if - your Python is properly installed and configured). - - - - - -BUGS - - The program may produce incorrect MIME message. The purpose of the program - is to decode whatever it is possible to decode, not to produce absolutely - correct MIME output. The incorrect parts are obvious - decoded - From/To/Cc/Reply-To/Mail-Followup-To/Subject headers and filenames. Other - than that output is correct MIME message. The program does not try to guess - whether the headers are correct. For example, if a message header states - that charset is iso8859-1, but the body (HTML, for example) is actually in - utf-8 the program will recode the message with the wrong charset. - - - - - -AUTHOR - - Oleg - Broytman - phd@phdru.name - - - - - -COPYRIGHT - - Copyright (C) 2001-2018 PhiloSoft Design. - - - - - -LICENSE - - GNU GPL - - - - - -NO WARRANTIES - - This program is distributed in the hope that it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - - - - -SEE ALSO - - mimedecode home page: - https://phdru.name/Software/Python/#mimedecode - - - - diff --git a/mk-distr b/mk-distr index ecce712..573c58e 100755 --- a/mk-distr +++ b/mk-distr @@ -5,11 +5,10 @@ umask 022 && git archive --format=tar --prefix=mimedecode/ "${1:-HEAD}" | (cd "$HOME/tmp" && exec tar xf -) && -# Copy mimedecode.docbook with timestamp to avoid rebuilding -cp -p mimedecode.docbook mimedecode.man mimedecode.html mimedecode.txt \ - "$HOME/tmp/mimedecode" && +cp -p docs/_build/html/mimedecode.html docs/_build/man/mimedecode.1 \ + docs/_build/text/mimedecode.txt "$HOME/tmp/mimedecode" && cd "$HOME/tmp/mimedecode" && -chmod a+r mimedecode.man mimedecode.html mimedecode.txt && +chmod a+r mimedecode.html mimedecode.1 mimedecode.txt && python setup.py sdist --formats=bztar && cd dist && mv mimedecode-*.tar.bz2 ../.. && cd ../.. && exec rm -rf mimedecode -- 2.39.5