RubyGems - ruby-msg-nx - Versions diffs - 0.3.0 - Mend

ruby-msg-nx 0.3.0

Files changed (25) hide show

checksums.yaml +7 -0
data/COPYING +20 -0
data/ChangeLog +108 -0
data/Home.md +133 -0
data/Rakefile +52 -0
data/bin/mapitool +204 -0
data/data/mapitags.yaml +4168 -0
data/data/named_map.yaml +114 -0
data/data/types.yaml +15 -0
data/lib/mapi/base.rb +104 -0
data/lib/mapi/convert/contact.rb +142 -0
data/lib/mapi/convert/note-mime.rb +282 -0
data/lib/mapi/convert/note-tmail.rb +287 -0
data/lib/mapi/convert.rb +69 -0
data/lib/mapi/helper.rb +45 -0
data/lib/mapi/mime.rb +227 -0
data/lib/mapi/msg.rb +516 -0
data/lib/mapi/property_set.rb +323 -0
data/lib/mapi/pst.rb +1995 -0
data/lib/mapi/rtf.rb +288 -0
data/lib/mapi/types.rb +51 -0
data/lib/mapi/version.rb +3 -0
data/lib/mapi.rb +5 -0
data/ruby-msg.gemspec +26 -0
metadata +102 -0

data/lib/mapi/rtf.rb ADDED Viewed

@@ -0,0 +1,288 @@
+require 'stringio'
+require 'strscan'
+class StringIO # :nodoc:
+	begin
+		instance_method :getbyte
+	rescue NameError
+		alias getbyte getc
+	end
+end
+module Mapi
+	#
+	# = Introduction
+	#
+	# The +RTF+ module contains a few helper functions for dealing with rtf
+	# in mapi messages: +rtfdecompr+, and <tt>rtf2html</tt>.
+	#
+	# Both were ported from their original C versions for simplicity's sake.
+	#
+	module RTF
+		class Tokenizer
+			def self.process io
+				while true do
+					case c = io.getc
+					when ?{; yield :open_group
+					when ?}; yield :close_group
+					when ?\\
+						case c = io.getc
+						when ?{, ?}, ?\\; yield :text, c.chr
+						when ?'; yield :text, [io.read(2)].pack('H*')
+						when ?a..?z, ?A..?Z
+							# read control word
+							str = c.chr
+							str << c while c = io.read(1) and c =~ /[a-zA-Z]/
+							neg = 1
+							neg = -1 and c = io.read(1) if c == '-'
+							num = if c =~ /[0-9]/
+								num = c
+								num << c while c = io.read(1) and c =~ /[0-9]/
+								num.to_i * neg
+							end
+							raise "invalid rtf stream" if neg == -1 and !num # ???? \blahblah- some text
+							io.seek(-1, IO::SEEK_CUR) if c != ' '
+							yield :control_word, str, num
+						when nil
+							raise "invalid rtf stream" # \EOF
+						else
+							# other kind of control symbol
+							yield :control_symbol, c.chr
+						end
+					when nil
+						return
+					when ?\r, ?\n
+						# ignore
+					else yield :text, c.chr
+					end
+				end
+			end
+		end
+		class Converter
+			# this is pretty crap, its just to ensure there is always something readable if
+			# there is an rtf only body, with no html encapsulation.
+			def self.rtf2text str, format=:text
+				group = 0
+				text = ''
+				text << "<html>\n<body>" if format == :html
+				group_type = []
+				group_tags = []
+				RTF::Tokenizer.process(StringIO.new(str)) do |a, b, c|
+					add_text = ''
+					case a
+					when :open_group; group += 1; group_type[group] = nil; group_tags[group] = []
+					when :close_group; group_tags[group].reverse.each { |t| text << "</#{t}>" }; group -= 1;
+					when :control_word; # ignore
+						group_type[group] ||= b
+						# maybe change this to use utf8 where possible
+						add_text = if b == 'par' || b == 'line' || b == 'page'; "\n"
+						elsif b == 'tab' || b == 'cell'; "\t"
+						elsif b == 'endash' || b == 'emdash'; "-"
+						elsif b == 'emspace' || b == 'enspace' || b == 'qmspace'; " "
+						elsif b == 'ldblquote'; '"'
+						else ''
+						end
+						if b == 'b' || b == 'i' and format == :html
+							close = c == 0 ? '/' : ''
+							text << "<#{close}#{b}>"
+							if c == 0
+								group_tags[group].delete b
+							else
+								group_tags[group] << b
+							end
+						end
+						# lot of other ones belong in here.\
+=begin
+\bullet 	Bullet character.
+\lquote 	Left single quotation mark.
+\rquote 	Right single quotation mark.
+\ldblquote 	Left double quotation mark.
+\rdblquote
+=end
+					when :control_symbol; # ignore
+						 group_type[group] ||= b
+						add_text = ' ' if b == '~' # non-breakable space
+						add_text = '-' if b == '_' # non-breakable hypen
+					when :text
+						add_text = b if group <= 1 or group_type[group] == 'rtlch' && !group_type[0...group].include?('*')
+					end
+					if format == :html
+						text << add_text.gsub(/([<>&"'])/) do
+							ent = { '<' => 'lt', '>' => 'gt', '&' => 'amp', '"' => 'quot', "'" => 'apos' }[$1]
+							"&#{ent};"
+						end
+						text << '<br>' if add_text == "\n"
+					else
+						text << add_text
+					end
+				end
+				text << "</body>\n</html>\n" if format == :html
+				text
+			end
+		end
+		RTF_PREBUF =
+			"{\\rtf1\\ansi\\mac\\deff0\\deftab720{\\fonttbl;}" \
+			"{\\f0\\fnil \\froman \\fswiss \\fmodern \\fscript " \
+			"\\fdecor MS Sans SerifSymbolArialTimes New RomanCourier" \
+			"{\\colortbl\\red0\\green0\\blue0\n\r\\par " \
+			"\\pard\\plain\\f0\\fs20\\b\\i\\u\\tab\\tx"
+		# Decompresses compressed rtf +data+, as found in the mapi property
+		# +PR_RTF_COMPRESSED+. Code converted from my C version, which in turn
+		# I wrote from a Java source, in JTNEF I believe.
+		#
+		# C version was modified to use circular buffer for back references,
+		# instead of the optimization of the Java version to index directly into
+		# output buffer. This was in preparation to support streaming in a
+		# read/write neutral fashion.
+		def rtfdecompr data
+			io  = StringIO.new data
+			buf = RTF_PREBUF + "\x00" * (4096 - RTF_PREBUF.length)
+			wp  = RTF_PREBUF.length
+			rtf = ''
+			# get header fields (as defined in RTFLIB.H)
+			compr_size, uncompr_size, magic, crc32 = io.read(16).unpack 'V*'
+			#warn "compressed-RTF data size mismatch" unless io.size == data.compr_size + 4
+			# process the data
+			case magic
+			when 0x414c454d # "MELA" magic number that identifies the stream as a uncompressed stream
+				rtf = io.read uncompr_size
+			when 0x75465a4c # "LZFu" magic number that identifies the stream as a compressed stream
+				flag_count = -1
+				flags = nil
+				while rtf.length < uncompr_size and !io.eof?
+					# each flag byte flags 8 literals/references, 1 per bit
+					flags = ((flag_count += 1) % 8 == 0) ? io.getbyte : flags >> 1
+					if 1 == (flags & 1) # each flag bit is 1 for reference, 0 for literal
+						rp, l = io.getbyte, io.getbyte
+						# offset is a 12 byte number. 2^12 is 4096, so thats fine
+						rp = (rp << 4) | (l >> 4) # the offset relative to block start
+						l = (l & 0xf) + 2 # the number of bytes to copy
+						l.times do
+							rtf << buf[wp] = buf[rp]
+							wp = (wp + 1) % 4096
+							rp = (rp + 1) % 4096
+						end
+					else
+						rtf << buf[wp] = io.getbyte.chr
+						wp = (wp + 1) % 4096
+					end
+				end
+			else # unknown magic number
+				raise "Unknown compression type (magic number 0x%08x)" % magic
+			end
+			# not sure if its due to a bug in the above code. doesn't seem to be
+			# in my tests, but sometimes there's a trailing null. we chomp it here,
+			# which actually makes the resultant rtf smaller than its advertised
+			# size (+uncompr_size+).
+			rtf.chomp! 0.chr
+			rtf
+		end
+		# Note, this is a conversion of the original C code. Not great - needs tests and
+		# some refactoring, and an attempt to correct some inaccuracies. Hacky but works.
+		#
+		# Returns +nil+ if it doesn't look like an rtf encapsulated rtf.
+		#
+		# Some cases that the original didn't deal with have been patched up, eg from
+		# this chunk, where there are tags outside of the htmlrtf ignore block.
+		#
+		# "{\\*\\htmltag116 <br />}\\htmlrtf \\line \\htmlrtf0 \\line {\\*\\htmltag84 <a href..."
+		#
+		# We take the approach of ignoring all rtf tags not explicitly handled. A proper
+		# parse tree would be nicer to work with. will need to look for ruby rtf library
+		#
+		# Some of the original comment to the c code is excerpted here:
+		#
+		# Sometimes in MAPI, the PR_BODY_HTML property contains the HTML of a message.
+		# But more usually, the HTML is encoded inside the RTF body (which you get in the
+		# PR_RTF_COMPRESSED property). These routines concern the decoding of the HTML
+		# from this RTF body.
+		#
+		# An encoded htmlrtf file is a valid RTF document, but which contains additional
+		# html markup information in its comments, and sometimes contains the equivalent
+		# rtf markup outside the comments. Therefore, when it is displayed by a plain
+		# simple RTF reader, the html comments are ignored and only the rtf markup has
+		# effect. Typically, this rtf markup is not as rich as the html markup would have been.
+		# But for an html-aware reader (such as the code below), we can ignore all the
+		# rtf markup, and extract the html markup out of the comments, and get a valid
+		# html document.
+		#
+		# There are actually two kinds of html markup in comments. Most of them are
+		# prefixed by "\*\htmltagNNN", for some number NNN. But sometimes there's one
+		# prefixed by "\*\mhtmltagNNN" followed by "\*\htmltagNNN". In this case,
+		# the two are equivalent, but the m-tag is for a MIME Multipart/Mixed Message
+		# and contains tags that refer to content-ids (e.g. img src="cid:072344a7")
+		# while the normal tag just refers to a name (e.g. img src="fred.jpg")
+		# The code below keeps the m-tag and discards the normal tag.
+		# If there are any m-tags like this, then the message also contains an
+		# attachment with a PR_CONTENT_ID property e.g. "072344a7". Actually,
+		# sometimes the m-tag is e.g. img src="http://outlook/welcome.html" and the
+		# attachment has a PR_CONTENT_LOCATION "http://outlook/welcome.html" instead
+		# of a PR_CONTENT_ID.
+		#
+		def rtf2html rtf
+			scan = StringScanner.new rtf
+			# require \fromhtml. is this worth keeping? apparently you see \\fromtext if it
+			# was converted from plain text.
+			return nil unless rtf["\\fromhtml"]
+			last_pos = scan.pos
+			if scan.scan_until(/\\ansicpg/)
+				code_page = "cp" + scan.scan(/\d+/)
+			else
+				code_page = 'ascii'
+			end
+			scan.pos = last_pos
+			html = ''
+			ignore_tag = nil
+			# skip up to the first htmltag. return nil if we don't ever find one
+			return nil unless scan.scan_until /(?=\{\\\*\\htmltag)/
+			until scan.empty?
+				if scan.scan /\{/
+				elsif scan.scan /\}/
+				elsif scan.scan /\\\*\\htmltag(\d+) ?/
+					#p scan[1]
+					if ignore_tag == scan[1]
+						scan.scan_until /\}/
+						ignore_tag = nil
+					end
+				elsif scan.scan /\\\*\\mhtmltag(\d+) ?/
+						ignore_tag = scan[1]
+				elsif scan.scan /\\par ?/
+					html << "\r\n"
+				elsif scan.scan /\\tab ?/
+					html << "\t"
+				elsif scan.scan /\\'([0-9A-Za-z]{2})/
+					html << scan[1].hex.chr
+				elsif scan.scan /\\pntext/
+					scan.scan_until /\}/
+				elsif scan.scan /\\htmlrtf/
+					scan.scan_until /\\htmlrtf0 ?/
+				# a generic throw away unknown tags thing.
+				# the above 2 however, are handled specially
+				elsif scan.scan /\\[a-z-]+(\d+)? ?/
+				#elsif scan.scan /\\li(\d+) ?/
+				#elsif scan.scan /\\fi-(\d+) ?/
+				elsif scan.scan /[\r\n]/
+				elsif scan.scan /\\([{}\\])/
+					html << scan[1]
+				elsif scan.scan /(.)/
+					html << scan[1]
+				else
+					p :wtf
+				end
+			end
+			html.strip.empty? ? nil : html.force_encoding(code_page)
+		end
+		module_function :rtf2html, :rtfdecompr
+	end
+end

data/lib/mapi/types.rb ADDED Viewed

@@ -0,0 +1,51 @@
+require 'rubygems'
+require 'ole/types'
+module Mapi
+	Log = Logger.new_with_callstack
+	module Types
+		#
+		# Mapi property types, taken from http://msdn2.microsoft.com/en-us/library/bb147591.aspx.
+		#
+		# The fields are [mapi name, variant name, description]. Maybe I should just make it a
+		# struct.
+		#
+		# seen some synonyms here, like PT_I8 vs PT_LONG. seen stuff like PT_SRESTRICTION, not
+		# sure what that is. look at `grep ' PT_' data/mapitags.yaml  | sort -u`
+		# also, it has stuff like PT_MV_BINARY, where _MV_ probably means multi value, and is
+		# likely just defined to | in 0x1000.
+		#
+		# Note that the last 2 are the only ones where the Mapi value differs from the Variant value
+		# for the corresponding variant type. Odd. Also, the last 2 are currently commented out here
+		# because of the clash.
+		#
+		# Note 2 - the strings here say VT_BSTR, but I don't have that defined in Ole::Types. Should
+		# maybe change them to match. I've also seen reference to PT_TSTRING, which is defined as some
+		# sort of get unicode first, and fallback to ansii or something.
+		#
+		DATA = {
+			0x0001 => ['PT_NULL', 'VT_NULL', 'Null (no valid data)'],
+			0x0002 => ['PT_SHORT', 'VT_I2', '2-byte integer (signed)'],
+			0x0003 => ['PT_LONG', 'VT_I4', '4-byte integer (signed)'],
+			0x0004 => ['PT_FLOAT', 'VT_R4', '4-byte real (floating point)'],
+			0x0005 => ['PT_DOUBLE', 'VT_R8', '8-byte real (floating point)'],
+			0x0006 => ['PT_CURRENCY', 'VT_CY', '8-byte integer (scaled by 10,000)'],
+			0x000a => ['PT_ERROR', 'VT_ERROR', 'SCODE value; 32-bit unsigned integer'],
+			0x000b => ['PT_BOOLEAN', 'VT_BOOL', 'Boolean'],
+			0x000d => ['PT_OBJECT', 'VT_UNKNOWN', 'Data object'],
+			0x001e => ['PT_STRING8', 'VT_BSTR', 'String'],
+			0x001f => ['PT_UNICODE', 'VT_BSTR', 'String'],
+			0x0040 => ['PT_SYSTIME', 'VT_DATE', '8-byte real (date in integer, time in fraction)'],
+			#0x0102 => ['PT_BINARY', 'VT_BLOB', 'Binary (unknown format)'],
+			#0x0102 => ['PT_CLSID', 'VT_CLSID', 'OLE GUID']
+		}
+		module Constants
+			DATA.each { |num, (mapi_name, variant_name, desc)| const_set mapi_name, num }
+		end
+		include Constants
+	end
+end

data/lib/mapi/version.rb ADDED Viewed

@@ -0,0 +1,3 @@
+module Mapi
+	VERSION = '0.3.0'
+end

data/lib/mapi.rb ADDED Viewed

@@ -0,0 +1,5 @@
+require 'mapi/version'
+require 'mapi/base'
+require 'mapi/types'
+require 'mapi/property_set'
+require 'mapi/convert'

data/ruby-msg.gemspec ADDED Viewed

@@ -0,0 +1,26 @@
+$:.unshift File.dirname(__FILE__) + '/lib'
+require 'mapi/version'
+PKG_NAME = 'ruby-msg-nx'
+PKG_VERSION = Mapi::VERSION
+Gem::Specification.new do |s|
+	s.name = PKG_NAME
+	s.version = PKG_VERSION
+	s.licenses = ['MIT']
+	s.summary = %q{Ruby Msg library.}
+	s.description = %q{A library for reading and converting Outlook msg and pst files (mapi message stores).}
+	s.authors = ['Charles Lowe', 'kenjiuno']
+	s.email = %q{ku@digitaldolphins.jp}
+	s.homepage = %q{https://github.com/HiraokaHyperTools/ruby-msg}
+	s.executables = ['mapitool']
+	s.files  = ['Home.md', 'COPYING', 'Rakefile', 'ChangeLog', 'ruby-msg.gemspec']
+	s.files += Dir.glob('data/*.yaml')
+	s.files += Dir.glob('lib/**/*.rb')
+	s.files += Dir.glob('bin/*')
+	s.add_runtime_dependency 'ruby-ole', '~> 1.2', '>=1.2.8'
+	s.add_runtime_dependency 'vpim', '~> 0.360'
+end

metadata ADDED Viewed

@@ -0,0 +1,102 @@
+--- !ruby/object:Gem::Specification
+name: ruby-msg-nx
+version: !ruby/object:Gem::Version
+  version: 0.3.0
+platform: ruby
+authors:
+- Charles Lowe
+- kenjiuno
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2022-01-13 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: ruby-ole
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.2'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.2.8
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.2'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.2.8
+- !ruby/object:Gem::Dependency
+  name: vpim
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.360'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.360'
+description: A library for reading and converting Outlook msg and pst files (mapi
+  message stores).
+email: ku@digitaldolphins.jp
+executables:
+- mapitool
+extensions: []
+extra_rdoc_files: []
+files:
+- COPYING
+- ChangeLog
+- Home.md
+- Rakefile
+- bin/mapitool
+- data/mapitags.yaml
+- data/named_map.yaml
+- data/types.yaml
+- lib/mapi.rb
+- lib/mapi/base.rb
+- lib/mapi/convert.rb
+- lib/mapi/convert/contact.rb
+- lib/mapi/convert/note-mime.rb
+- lib/mapi/convert/note-tmail.rb
+- lib/mapi/helper.rb
+- lib/mapi/mime.rb
+- lib/mapi/msg.rb
+- lib/mapi/property_set.rb
+- lib/mapi/pst.rb
+- lib/mapi/rtf.rb
+- lib/mapi/types.rb
+- lib/mapi/version.rb
+- ruby-msg.gemspec
+homepage: https://github.com/HiraokaHyperTools/ruby-msg
+licenses:
+- MIT
+metadata: {}
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.2.33
+signing_key:
+specification_version: 4
+summary: Ruby Msg library.
+test_files: []