diff --git a/ChangeLog b/ChangeLog index d80e24f..dad70a0 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,913 +1,918 @@ +LibPST 0.6.68 (2016-08-29) +=============================== + * allow folders containing multiple item types, e.g. email and calendar + * better detection of valid internet headers + LibPST 0.6.67 (2016-07-06) =============================== * Jeffrey Morlan - multiple bug fixes and an optimization see 'hg log -v' for details LibPST 0.6.66 (2015-12-21) =============================== * Igor Stroh - Added Content-ID header support LibPST 0.6.65 (2015-09-11) =============================== * Jeffrey Morlan - fix multiple Content-Type headers * Hans Liss - debug level output LibPST 0.6.64 (2015-03-09) =============================== * AJ Shankar fixes for attachment processing and body encodings that contain embedded null chars LibPST 0.6.63 (2013-12-27) =============================== * Daniel Gryniewicz found buffer overrun in LIST_COPY_TIME LibPST 0.6.62 (2013-09-22) =============================== * 983596 - Old dependency filter breaks file coloring LibPST 0.6.61 (2013-08-06) =============================== * move documentation to unversioned directory LibPST 0.6.60 (2013-06-12) =============================== * patch from Dominique Leuenberger to add AC_USE_SYSTEM_EXTENSIONS * add readpst -a option for attachment stripping LibPST 0.6.59 (2013-05-17) =============================== * add autoconf checking for libgsf LibPST 0.6.58 (2012-12-28) =============================== * fix From quoting on embedded rfc/822 messages LibPST 0.6.57 (2012-12-27) =============================== * remove useless dependencies LibPST 0.6.56 (2012-12-24) =============================== * merge -m .msg files code into main branch LibPST 0.6.55 (2012-05-08) =============================== * preserve bcc headers * document -C switch to set default character set * space after colon is not required in header fields LibPST 0.6.54 (2011-11-04) =============================== * embedded rfc822 messages might contain rtf encoded bodies LibPST 0.6.53 (2011-07-10) =============================== * add Status: header in output * allow fork for parallel processing of individual email folders in separate mode * proper handling of --with-boost-python option LibPST 0.6.52 (2011-05-22) =============================== * fix dangling freed pointer in embedded rfc822 message processing * allow broken outlook internet header field - it sometimes contains fragments of the message body rather than headers LibPST 0.6.51 (2011-04-17) =============================== * fix for buffer overrun; attachment size from the secondary list of mapi elements overwrote proper size from the primary list of mapi elements. fedora bugzilla 696263 LibPST 0.6.50 (2010-12-24) =============================== * rfc2047 and rfc2231 encoding for non-ascii headers and attachment filenames LibPST 0.6.49 (2010-09-13) =============================== * fix to ignore embedded objects that are not email messages LibPST 0.6.48 (2010-09-02) =============================== * fix for broken internet headers from Outlook. * fix ax_python.m4 to look for python2.7 * Subpackage Licensing, add COPYING to -libs. * use mboxrd from quoting for output formats with multiple messages per file * use no from quoting for output formats with single message per file LibPST 0.6.47 (2010-05-07) =============================== * patches from Kenneth Berland for solaris. * fix output file name numbering to start at 1 rather than 2. LibPST 0.6.46 (2010-02-13) =============================== * prefer libpthread over librt for finding sem_init function. * rebuild for fedora 13 change in implicit dso linking semantics. LibPST 0.6.45 (2009-11-18) =============================== * patch from Hugo DesRosiers to export categories and notes into vcards. * extend that patch to export categories into vcalendar appointments also. LibPST 0.6.44 (2009-09-20) =============================== * fix --help usage; readpstlog is gone, debug files are now ascii text. * patch from Lee Ayres to add file name extensions in separate mode. * allow mixed items types in a folder in separate mode. LibPST 0.6.43 (2009-09-12) =============================== * patches from Justin Greer. - add code pages 1200 and 1201 to the list for iconv - add support for 0x0201 indirect blocks that point to 0x0101 blocks - add readpst -t option to select output item types - fix (remove) extra new line inside headers + add code pages 1200 and 1201 to the list for iconv + add support for 0x0201 indirect blocks that point to 0x0101 blocks + add readpst -t option to select output item types + fix (remove) extra new line inside headers * cleanup base64 encoding to remove duplicate code. * patch from Chris White to avoid segfault with embedded appointments. * patch from Roberto Polli to add creation of some Thunderbird specific meta files. * patch from Justin Greer to ignore b5 tables at offset zero. * output type filtering can now be used to handle folders with multiple item types. * better decoding of rfc822 embedded message attachments. * better detection of dsn delivery reports LibPST 0.6.42 (2009-09-03) =============================== * patch from Fridrich Strba to build with DJGPP DOS cross-compiler. LibPST 0.6.41 (2009-06-23) =============================== * fix ax_python detection - should not use locate command * checking for fedora versions is not needed LibPST 0.6.40 (2009-06-23) =============================== * fedora 11 has python2.6 * remove pdf version of the man pages LibPST 0.6.39 (2009-06-21) =============================== * fedora > 10 moved to boost-python-devel LibPST 0.6.38 (2009-06-21) =============================== * add python module interface to the shared library for easy scripting. * the shared library must never write to stdout or stderr. * fix pst_attach_to_mem so the caller does not need to initialize the buffer pointer. * remove readpst -C switch, obsolete debugging code. * update version to 4:0:0 since we made many changes to the interface. * removed contact->access_method since we don't have a mapi element for it. * changed pst_attach_to_mem to return pst_binary structure. * decode more recurrence mapi elements. * readpst changes for parallel operation on multi processor machines. * remove readpstlog - the debug log files are now plain ascii. Add locking if needed so parallel jobs can produce debug logs. * more cleanup of the shared library interface, but still not fully thread safe. * make nested mime multipart/alternative to hold the text/html parts so the topmost level is almost always multipart/mixed. * the shared library interface should now be thread safe. * patch from Fridrich Strba to build on win32. * remove unreferenced code. LibPST 0.6.37 (2009-04-17) =============================== * add pst_attach_to_mem() back into the shared library interface. * improve developer documentation. * fix memory leak caught by valgrind. LibPST 0.6.36 (2009-04-14) =============================== * spec file cleanup with multiple sub packages. * add doxygen devel-doc documentation for the shared library. * switch back to fully versioned subpackage dependencies. * more cleanup on external names in the shared object file. LibPST 0.6.35 (2009-04-08) =============================== * fix bug where we failed to pickup the last extended attribute. * patch from Emmanuel Andry to fix potential security bug in pst2dii with printf(err). * properly add trailing mime boundary in all modes. * move version-info into main configure.in, and set it properly * prefix all external symbols in the shared library with pst_ to avoid symbol clashes with other shared libraries. * new debianization from hggdh. * build separate libpst, libpst-libs, libpst-devel rpms. * remove many functions from the interface by making them static. LibPST 0.6.34 (2009-03-19) =============================== * improve consistency checking when fetching items from the pst file. * avoid putting mixed item types into the same output folder. LibPST 0.6.33 (2009-03-17) =============================== * fix fedora 11 type mismatch warning (actually an error in this case). * fix large file support, some sytems require config.h to be included earlier in the compilation. * compensate for iconv conversion to utf-7 that produces strings that are not null terminated. * don't produce empty attachment files in separate mode. LibPST 0.6.32 (2009-03-14) =============================== * fix ppc64 compile error. LibPST 0.6.31 (2009-03-14) =============================== * bump version for fedora cvs tagging mistake. LibPST 0.6.30 (2009-03-14) =============================== * improve documentation of .pst format. * remove decrypt option from getidblock - we always decrypt. * rename some structure fields to reflect our better understanding of the pst format. * track character set individually for each mapi element, since some could be unicode (therefore utf8) and others sbcs with character set specified by the mapi object. remove charset option from pst2ldif since we get that from each object now. * more code cleanup. * use AM_ICONV for better portability of the library location. * structure renaming to be more specific. * improve internal doxygen documentation. * avoid emitting bogus empty email messages into contacts and calendar files. LibPST 0.6.29 (2009-02-24) =============================== * fix for 64bit on Fedora 11 LibPST 0.6.28 (2009-02-24) =============================== * add X-libpst-forensic-* headers to capture items of interest that are not used by normal mail clients. * improve decoding of multipart/report and message/rfc822 mime types. * improve character set handling - don't try to convert utf-8 to single byte for fields that were not originally unicode. if the conversion fails, leave the data in utf-8. * fix embedded rfc822 messages with attachments. LibPST 0.6.27 (2009-02-07) =============================== * fix for const correctness on Fedora 11 LibPST 0.6.26 (2009-02-07) =============================== * patch from Fridrich Strba for building on mingw and general cleanup of autoconf files * add processing for pst files of type 0x0f * start adding support for properly building and installing libpst.so and the header files required to use it. * remove version.h since the version number is now in config.h * more const correctness issues regarding getopt() * consistent ordering of our include files. all system includes protected by ifdef HAVE_ from autoconf. * strip and regenerate all MIME headers to avoid duplicates. problem found by Michael Watson on Mac OSX. * do a better job of making unique MIME boundaries. * only use base64 coding when strictly necessary. * more cleanup of #include files. common.h is the only file allowed to include system .h files unprotected by autoconf HAVE_ symbols. define.h is the only other file allowed to include system .h files. define.h is never installed; common.h is installed if we are building the shared library. * recover dropped pragma pack line, use int64_t rather than off_t to avoid forcing users of the shared library to enable large file support. * add pragma packing support for sun compilers. * fix initial from header in mbox format. * start moving to PST_LE_GET* rather than LE*_CPU macros so we can eventually remove the pragma packing. * patch from Fridrich Strba, some systems need extra library for regex. LibPST 0.6.25 (2009-01-16) =============================== * improve handling of content-type charset values in mime parts LibPST 0.6.24 (2008-12-11) =============================== * patch from Chris Eagle to build on cygwin LibPST 0.6.23 (2008-12-04) =============================== * bump version to avoid cvs tagging mistake in fedora LibPST 0.6.22 (2008-11-28) =============================== * patch from David Cuadrado to process emails with type PST_TYPE_OTHER * base64_encode_multiple() may insert newline, needs larger malloc * subject lines shorter than 2 bytes could segfault LibPST 0.6.21 (2008-10-21) =============================== * fix title bug with old schema in pst2ldif. * also escape commas in distinguished names per rfc4514. LibPST 0.6.20 (2008-10-09) =============================== * add configure option --enable-dii=no to remove dependency on libgd. * many fixes in pst2ldif by Robert Harris. * add -D option to include deleted items, from Justin Greer * fix from Justin Greer to add missing email headers * fix from Justin Greer for my_stristr() * fix for orphan children when building descriptor tree * avoid writing uninitialized data to debug log file * remove unreachable code * create dummy top-of-folder descriptor if needed for corrupt pst files LibPST 0.6.19 (2008-09-14) =============================== * Fix base64 encoding that could create long lines * Initial work on a .so shared library from Bharath Acharya. LibPST 0.6.18 (2008-08-28) =============================== * Fixes for iconv on Mac from Justin Greer. LibPST 0.6.17 (2008-08-05) =============================== * More fixes for 32/64 bit portability on big endian ppc. LibPST 0.6.16 (2008-08-05) =============================== * Use inttypes.h for portable printing of 64 bit items. LibPST 0.6.15 (2008-07-30) =============================== * Patch from Robert Simpson for file handle leak in error case. * Fix for missing length on lz decompression, bug found by Chris White. LibPST 0.6.14 (2008-06-15) =============================== * Fix my mistake in debian packaging. LibPST 0.6.13 (2008-06-13) =============================== * Patch from Robert Simpson for encryption type 2. * Fix the order of testing item types to avoid claiming there are multiple message stores. LibPST 0.6.12 (2008-06-10) =============================== * Patch from Joachim Metz for debian packaging, and fix for incorrect length on lz decompression. LibPST 0.6.11 (2008-06-03) =============================== * Use ftello/fseeko to properly handle large files. * Document and properly use datasize field in b5 blocks. * Fix some MSVC compile issues and collect MSVC dependencies into one place. LibPST 0.6.10 (2008-05-29) =============================== * Patch from Robert Simpson fix doubly-linked list in the cache_ptr code, and allow arrays of unicode strings (without converting them). * More changes for Fedora packaging (#434727) * Fixes for const correctness. LibPST 0.6.9 (2008-05-16) =============================== * Patch from Joachim Metz for 64 bit compile. * Signed/unsigned cleanup from 'CFLAGS=-Wextra ./configure'. * Reindent vbuf.c to make it readable. * Fix pst format documentation for 8 byte backpointers. LibPST 0.6.8 (2008-03-05) =============================== * Initial version of pst2dii to convert to Summation dii load file format. * Changes for Fedora packaging (#434727) LibPST 0.6.7 (2008-02-16) =============================== * Work around bogus 7c.b5 blocks in some messages that have been read. They appear to have attachments, but of some unknown format. Before the message was read, it did not have any attachments. * Use autoscan to cleanup our autoconf system. * Use autoconf to detect when we need to use our XGetopt files and other header files. * More fields, including BCC. * Fix missing LE32_CPU byte swapping for FILETIME types. LibPST 0.6.6 (2008-01-31) =============================== * More code cleanup, removing unnecessary null terminations on binary buffers. All pst file reads now go thru one function. Logging all pst reads to detect cases where we read the same data multiple times - discovers node sizes are actually 512 bytes. * Switch from cvs to mercurial source control. LibPST 0.6.5 (2008-01-22) =============================== * More code cleanup, removing obsolete code. All the boolean flags of type 0xb have length 4, so these are all 32 bits in the file. Libpst treats them all as 16 bits, but at least we are consistent. * More fields decoded - for example, see We should be able to use that data for much more complete decoding. * Move the rpm group to Applications/Productivity consistent with Evolution. LibPST 0.6.4 (2008-01-19) =============================== * More fixes for Outlook 2003 64 bit parsing. We observed cases of compressed RTF bodies (type 0x1009) with zero length. * Document type 0x0101 descriptor blocks and process them. * Fix large file support - we need to include config.h before any standard headers. * Merge following changes from svn snapshot from Alioth: * Add new fields to appointment for recurring events (SourceForge #304198) * Map IPM.Task items to PST_TYPE_TASK. * Applied patch to remove compiler warnings, thanks! (SourceForge #304314) * Fix crash with unknown reference type * Fix more memory issues detected by valgrind * lspst - add usage mesage and option parsing using getopt (SourceForge #304199) * Fix crash caused by invalid free calls * Fix crash when email subject is empty * Fix memory and information leak in hex debug dump LibPST 0.6.3 (2008-01-13) =============================== * More type consistency issues found by splint. LibPST 0.6.2 (2008-01-12) =============================== * More fixes for Outlook 2003 64 bit parsing. * All buffer sizes changed to size_t, all file offsets changed to off_t, all function names start with pst_, many other type consistency issues found by splint. Many changes to #llx in debug printing for 64 bit items. All id values are now uint64_t. LibPST 0.6.1 (2008-01-06) =============================== * Outlook 2003 64 bit parsing. Some documentation from Alexander Grau and patches from Sean Loaring . * fix from Antonio Palama for email items that happen to have item->contact non null, and were being processed as contacts. * Add large file support so we can read .pst files larger than 2gb. * Change lspst to be similar to readpst, properly using recursion to walk the tree, and testing item types. Add a man page for lspst. LibPST 0.5.12 (2007-10-02) =============================== * security fix from Brad Hards for buffer overruns in liv-zemple decoding for corrupted or malicious pst files. LibPST 0.5.11 (2007-08-24) =============================== * fix from Stevens Miller for unitialized variable. LibPST 0.5.10 (2007-08-20) =============================== * fix yet more valgrind errors - finally have a clean memory check. * restructure readpst.c for proper recursive tree walk. * buffer overrun test was backwards, introduced at 0.5.6 * fix broken email attachments, introduced at 0.5.6 LibPST 0.5.9 (2007-08-12) =============================== * fix more valgrind errors. LibPST 0.5.8 (2007-08-10) =============================== * fix more valgrind errors. lzfu_decompress needs to return the actual buffer size, since the lz header overestimates the size. This caused base64_encode to encode undefined bytes into the email attachment. LibPST 0.5.7 (2007-08-09) =============================== * fix valgrind errors, using uninitialized data. * improve debug logging and readpstlog for indented listings. * cleanup documentation. LibPST 0.5.6 (2007-07-15) =============================== * Fix to allow very small pst files with only one node in the tree. We were mixing signed/unsigned types in comparisons. * More progress decoding the basic structure 7c blocks. Many four byte values may be ID2 indices with data outside the buffer. * Start using doxygen to generate internal documentation. LibPST 0.5.5 (2007-07-10) =============================== * merge the following changes from Joe Nahmias version: * Lots of memory fixes. Thanks to Nigel Horne for his assistance tracking these down! * Fixed creation of vCards from contacts, thanks to Nigel Horne for his help with this! * fix for MIME multipart/alternative attachments. * added -c options to readpst manpage. * use 8.3 attachment filename if long filename isn't available. * new -b option to skip rtf-body.rtf attachments. * fix format of From header lines in mbox files. * Add more appointment fields, thanks to Chris Halls for tracking them down! LibPST 0.5.4 (2006-02-25) =============================== * patches from Arne, adding MH mode, remove leading zeros from the generated numbered filenames starting with one rather than zero. Miscellaneous code cleanup. * document the "7c" descriptor block format. LibPST 0.5.3 (2006-02-20) =============================== * switch to gnu autoconf/automake. This breaks the MS VC++ projects since the source code is now in the src subdirectory. * documentation switched to xml, building man pages and html from the master xml copy. * include rpm .spec file for building src and binary rpms. LibPST 0.5.2 (2006-02-18) =============================== * Added pst2ldif to convert the contacts to ldif format for import into ldap databases. * Major changes to libpst.c to properly use the node depth values from the b-tree nodes. We also use the item count values in the nodes rather than trying to guess how many items are active. * Cleanup whitespace - using tabs for every four columns. LibPST 0.5.1 (17 November 2004) =============================== Well, alot has happened since the last release of libpst. Release / Management: * The project has forked! The new maintainer is Joseph Nahmias. * We have changed hosting sites, thanks to sourceforge for hosting to this point. From this point forward we will be using alioth.debian.org. * The project is now using SubVersioN for source control. You can get the latest code by running: svn co svn://svn.debian.org/svn/libpst/trunk . * See for more information. Code Changes: * Added lspst program to list items in a PST. Still incomplete. * Added vim folding markers to readpst.c * avoid the pseudo-prologue that MS prepends to the email headers * fix build on msvc, since it doesn't have sys/param.h * Re-vamped Makefile: * Only define CFLAGS in Makefileif missing * fixed {un,}install targets in Makefile * Fixed up build process in Makefile * Added mozilla conversion script from David Binard * Fixed bogus creation of readpst.log on every invocation * escaped dashes and apostrophe in manpages * Updated TODO * added manpages from debian pkg * fix escaped-string length count to consider '\n', thanks to Paul Bakker . * ensure there's a blank line between header and body patch from (SourceForge #890745). * Apply accumulated endian-related patches * Removed unused files, upstream's debian/ dir -- Joe Nahmias LibPST v0.5 =========== It is with GREAT relief that I bring you version 0.5 of the LibPST tools! Through great difficulties, this tool has survived and expanded to become even better. The changes are as follows: * RTF support. We can now decompress RTF bodies in emails, and are saved as attachments * Better support in reading the indexes. Fixed many bugs with them * Improved reliability. "Now we are getting somewhere!" * Improved compiling. Hopefully we won't be hitting too many compile errors now. * vCard handling. Contacts are now exported as vCard entries. * vEvent handling. Support has begun on exporting Calendar entries as events * Support for Journal entries has also begun If you have any problems with this release, don't hesitate to contact me. These changes come to you, as always, free under the GPL license!! What a wonderful thing it is. It does mean that you can write your own program off of this library and distribute it also for free. However, anyone with commercial interests for developing applications they will be charging for are encouraged to get in touch with me, as I am sure we can come to some arrangement. Dave Smith LibPST v0.4.3 ============= Bug fix release. No extra functionality Dave Smith LibPST v0.4.2 ============= The debug system has had an overhaul. The debug messages are no longer printed to the screen when they are enabled. They are dumped to a binary file. There is another utility called "readlog" that I have written to handle these log files. It should make it easier to selectively view bits of a log file. It also shows the position that the log message was printed from. There is a new switch in readpst. It is -d. It enables the user to specify the log file which the binary log is written to. If the switch isn't used, the default file of "readpst.log" is used. The code is now Visual C++ compatible. It has compiled on Visual C++ .net Standard edition, and produces the readpst.exe file. Use the project file included in this distribution. There have been minor improvements elsewhere too. LibPST v0.4.1 ============= Fixed a couple more bugs. Is it me or do bugs just insert themselves in random, hard to find places! Cured a few problems with regard to emails with multiple embeded items. They are not fully re-created using Mime-types, but are accessible with the -S switch (which saves everything as seperate items) Fixed a problem reading the first index. Back sliders are now detected. (ie when the value following the current one is smaller, not bigger!) Added some error messages when we try and read outside of the PST file, this was causing a few problems before, cause the return value wasn't always checked, so it was possible to be reading random data, and trying to make sense of it! Anyway, if you find any problems, don't hesitate to mail me Dave Smith LibPST v0.4 =========== Fixed a nasty bug that occasionally corrupted attachments. Another bug with regard to reading of indexes (also occasional). Another output method has been added which is called "Seperate". It is activated with the -S switch. It operates in the following manor: |--Inbox-->000000 | 000001 | 000002 |--Sentmail-->0000000 | 0000001 | 0000002 All the emails are stored in seperate files counting from 0 upwards, in a folder named as the PST folder. When an email has an attachment, it is saved as a seperate file. The filename for the attachment is made up of 2 parts, the first is the email number to which it belongs, the second is its filename. The should now be runnable on big-endian machines, if the define.h file is first modified. The #define LITTLE_ENDIAN must be commented out, and the #define BIG_ENDIAN must be uncommented. More verbose error messages have been added. Apparently people got confused when the program stopped for no visible reason. This has now been resolved. Thanks for the continued support of all people involved. Dave Smith Libpst v0.3.4 ============= Several more fixes. An Infinite loop and incorrect interpreting of item index attributes. Work has started on making the code executable on big endian CPUs. At present it should work with Linux on these CPUs, but I would appreciate it if you could provide feedback with regard to it's performance. I am also working with some other people at make it operate on Solaris. A whole load more items are now recognized by the Item records. With more items in Emails and Folders. I haven't got to the Contacts yet. Anyway, this is what I would call a minor feature enhancment and bugfix release. Dave Smith LibPST v0.3.3 ============= Fixed several items. Mainly memory leaks. Loads of them! oops.. I have added a new program, mainly of debugging, which when passed an ID value and a pst file, will extract and decrypt that ID from the pst file. I don't see it being a huge attraction, or of much use to most people, but it is another example of writing an application to use the libpst interface. Another fix was in the reading of the item index. This has hopefully now been corrected. The result of this bug was that not all the emails in a folder were converted. Hopefully you should have more luck now. Dave Smith LibPST v0.3.2 ============= Quick bugfix release. There was a bug in the decryption of the basic encryption that outlook uses. One byte, 0x6c, was incorrectly decrypted to 0x6c instead of 0xcd. This release fixes this bug. Sorry... LibPST v0.3.1 ============= Minor improvements. Fixed bug when linking multiple blocks together, so now the linking blocks are not "encrypted" when trying to read them. LibPST v0.3 =========== A lot of bug fixing has been done for this release. Testing has been done on the creation of the files by readpst. Better handling of large binaries being extracted from the PST file has been implemented. Quite a few reports have come in about not being able to compile on Darwin. This could be down to using macros with variable parameter lists. This has now been changed to use C functions with variable parameters. I hope this fixes a lot of problems. Added support for recreating the folder structure into normal directories. For Instance: Personal Folders |-Inbox | |-Jokes | |-Meetings |-Send Items each folder containing an mbox file with the correct emails for that folder. Dave Smith LibPST v0.3 beta1 ================= Again, a shed load of enhancements. More work has been done on the mime creation. A bug has been fixed that was letting part of the attachments that were created disappear. A major enhancement is that "compressible encryption" support has been added. This was an incredibly simple method to use. It is basically a ceasar cipher. It has been noted by several users already that the PST password that Outlook uses, serves *no purpose*. It is not used to encrypt the PST, it is mearly stored there. This means that the readpst application is able to convert PST files without knowing the password. Microsoft have some explaning to do! Output files are now not overwritten if they already exist. This means that if you have two folders in your PST file named "fred", the first one encountered will be named "fred" and the second one will be named "fred00000001". As you can see, there is enough room there for many duplicate names! Output filenames are now restricted. Any "/" or "\" characters in the name are replaced with "_". If you find that there are any other characters that need to be changed, could you please make me aware! Thanks to Berry Wizard for help with supporting the encryption. Thanks to Auke Kok, Carolus Walraven and Yogesh Kumar Guatam for providing debugging information and testing. Dave Smith LibPST v0.2 beta1 ================= Hello once more... Attachments are now re-created in mime format. The method is very crude and could be prone to over generalisation. Please test this version, and if attachments are not recreated correctly, please send me the email (complete message source) of the original and converted. Cheers. I hope this will work for everyone who uses this program, but reality can be very different! Let us see how it goes... Dave Smith LibPST v0.2 alpha1 =========== Hello! Some improvements. The internal code has been changed so that attachments are now processed and loaded into the structures. The readpst program is not finished yet. It needs to convert these binary structs into mime data. At present it just saves them to the current directory, overwriting any previous files with the attachment name. Improvements over previous version: * KMail output is supported - if the "-k" flag is specified, all the directory hierarchy is created using the KMail standard * Lots of bugs and memory leaks fixed Usage: ReadPST v0.2alpha1 implementing LibPST v0.2alpha1 Usage: ./readpst [OPTIONS] {PST FILENAME} OPTIONS: -h - Help. This screen -k - KMail. Output in kmail format -o - Output Dir. Directory to write files to. CWD is changed *after* opening pst file -V - Version. Display program version If you want to view lots of debug output, modify a line in "define.h" from "//#define DEBUG_ALL" to "#define DEBUG_ALL". It would then be advisable to pipe all output to a log file: ./readpst -o out pst_file &> logfile Dave Smith LibPST v0.1 =========== Hi Folks! This has been a long, hard slog, but I now feel that I have got somewhere useful. The included program "main" is able to read an Outlook PST file and dump the emails into mbox files, separating each folder into a different mbox file. All the mbox files are stored in the current directory and no attempt is yet made to organise these files into a directory hierarchy. This would not be too difficult to achieve though. Email attachments are not yet handled, neither are Contacts. There is no pretty interface yet, but you can convert a PST file in the following manner ./main {path to PST file} This is very much a work in progress, but I thought I should release this code so that people can lose their conception that outlook files will never be converted to Linux. I am intending that the code I am writing will be developed into greater applications to provide USEFUL tools for accessing and converting PST files into a variety of formats. One point I feel I should make is that Outlook, by default, creates "Compressible Encryption" PST files. I have not, as yet, attempted to write any decryption routines, so you will not be able to convert these files. However, if you create a new PST file and choose not to make an encrypted one, you can copy all your emails into this new one and then convert the unencrypted one. I hope you enjoy, Dave Smith diff --git a/NEWS b/NEWS index 43e2933..629e916 100644 --- a/NEWS +++ b/NEWS @@ -1,79 +1,80 @@ +0.6.68 2016-08-29 allow folders containing multiple item types; better detection of valid internet headers 0.6.67 2016-07-06 Jeffrey Morlan - multiple bug fixes and an optimization 0.6.66 2015-12-21 Igor Stroh - Added Content-ID header support 0.6.65 2015-09-11 Jeffrey Morlan - fix multiple Content-Type headers; Hans Liss - debug level output 0.6.64 2015-03-09 AJ Shankar fixes for attachment processing and body encodings that contain embedded null chars 0.6.63 2013-12-27 Daniel Gryniewicz found buffer overrun in LIST_COPY_TIME 0.6.62 2013-09-22 983596 - Old dependency filter breaks file coloring 0.6.61 2013-08-06 move documentation to unversioned directory 0.6.60 2013-06-12 add AC_USE_SYSTEM_EXTENSIONS, add readpst -a option for attachment stripping 0.6.59 2013-05-17 add autoconf checking for libgsf 0.6.58 2012-12-28 fix From quoting on embedded rfc/822 messages 0.6.57 2012-12-27 remove useless dependencies 0.6.56 2012-12-24 merge -m .msg files code into main branch 0.6.55 2012-05-08 preserve bcc headers, space after colon is not required in header fields 0.6.54 2011-11-04 embedded rfc822 messages might contain rtf encoded bodies 0.6.53 2011-07-10 allow fork for parallel processing of individual email folders in separate mode 0.6.52 2011-05-22 fix dangling freed pointer; allow broken outlook internet header field 0.6.51 2011-04-17 fix for buffer overrun; attachment size fetched twice 0.6.50 2010-12-24 rfc2047 and rfc2231 encoding for non-ascii headers and attachment filenames 0.6.49 2010-09-13 fix to ignore embedded objects that are not email messages 0.6.48 2010-09-02 fix for broken internet headers from Outlook, change to mboxrd quoting 0.6.47 2010-05-07 patches from Kenneth Berland for solaris 0.6.46 2010-02-13 fixes for fedora 13 change in implicit dso linking semantics 0.6.45 2009-11-18 patch from Hugo DesRosiers to export categories and notes into vcards 0.6.44 2009-09-20 patch from Lee Ayres to add file name extensions in separate mode 0.6.43 2009-09-12 patches from Justin Greer, Chris White, Roberto Polli; better rfc822 embedded message decoding 0.6.42 2009-09-03 patch from Fridrich Strba to build with DJGPP DOS cross-compiler 0.6.41 2009-06-23 fix ax_python detection - should not use locate command 0.6.40 2009-06-23 fedora 11 has python2.6, remove pdf version of the man pages 0.6.39 2009-06-21 fedora > 10 moved to boost-python-devel 0.6.39 2009-06-21 fedora > 10 moved to boost-python-devel 0.6.38 2009-06-21 many changes including shared library soname 0.6.37 2009-04-17 add pst_attach_to_mem() back into the shared library interface 0.6.36 2009-04-14 build separate -doc and -devel-doc subpackages 0.6.35 2009-04-08 properly add trailing mime boundary in all modes, build separate rpms with libpst.so shared. 0.6.34 2009-03-19 avoid putting mixed item types into the same output folder 0.6.33 2009-03-17 fix utf-7 conversions, don't produce empty attachment files in separate mode 0.6.32 2009-03-14 fix ppc64 compile error 0.6.31 2009-03-14 bump version for fedora cvs tagging mistake 0.6.30 2009-03-14 track character set individually for each mapi element, avoid emitting bogus empty email messages into contacts and calendar files. 0.6.29 2009-02-24 fix for 64bit on Fedora 11 0.6.28 2009-02-24 improve decoding of multipart/report and message/rfc822 mime types 0.6.27 2009-02-07 fix for const correctness on Fedora 11 0.6.26 2009-02-07 patch from Fridrich Strba for building on mingw, and autoconf cleanup, better mime headers 0.6.25 2009-01-16 improve handling of content-type charset values in mime parts 0.6.24 2008-12-11 patch from Chris Eagle to build on cygwin 0.6.23 2008-12-04 bump version to avoid cvs tagging mistake in fedora 0.6.22 2008-11-28 process emails with type PST_TYPE_OTHER, fix malloc error and possible segfault 0.6.21 2008-10-21 fix title bug with old schema in pst2ldif, also escape commas in distinguished names per rfc4514. 0.6.20 2008-10-09 add configure option --enable-dii=no, fixes from Robert Harris for pst2ldif. 0.6.19 2008-09-14 Initial work on a .so shared library from Bharath Acharya. 0.6.18 2008-08-28 Fixes for iconv on Mac from Justin Greer. 0.6.17 2008-08-05 More fixes for 32/64 bit portability on big endian ppc 0.6.16 2008-08-05 Use inttypes.h for portable printing of 64 bit items 0.6.15 2008-07-30 Fix file handle leak in error case, missing length on lz decompression 0.6.14 2008-06-15 Fix my mistake in debian packaging 0.6.13 2008-06-13 Patch from Robert Simpson for encryption type 2. 0.6.12 2008-06-10 Patch from Joachim Metz for debian packaging, and fix for incorrect length on lz decompression. 0.6.11 2008-06-03 Use ftello/fseeko to properly handle large files. 0.6.10 2008-05-29 Patch from Robert Simpson for doubly-linked list and arrays of unicode strings. 0.6.9 2008-05-16 Patch from Joachim Metz for 64 bit compile. 0.6.8 2008-03-05 Initial version of pst2dii to convert to Summation dii load file format. 0.6.7 2008-02-16 Ignore unknown attachments on some read messages; autoconf cleanup. 0.6.6 2008-01-31 Code cleanup, switch from cvs to mercurial source control. 0.6.5 2008-01-22 Code cleanup, rpm group Applications/Productivity. 0.6.4 2008-01-19 More fixes for 64 bit format, merge changes from svn Alioth. 0.6.3 2008-01-13 More type consistency issues found by splint. 0.6.2 2008-01-12 More fixes for 64 bit format, consistent types size_t, off_t, etc. 0.6.1 2008-01-06 Outlook 2003 64 bit format and fix for bogus contacts. 0.5.12 2007-10-02 security fix for possible buffer overruns in liv-zemple decoding 0.5.11 2007-08-24 fix for unitialized variable 0.5.10 2007-08-20 fix yet more valgrind errors, restructure readpst recursive walk, backwards overrun test 0.5.9 2007-08-12 fix more valgrind errors, pst2ldif wrote undefined data 0.5.8 2007-08-10 lzfu_decompress/base64_encode encoded random data into attachment 0.5.7 2007-08-09 fix valgrind errors, using uninitialized data 0.5.6 2007-07-15 handle small pst files, better decoding of 7c blocks 0.5.5 2007-07-10 merge changes from Joe Nahmias version 0.5.4 2006-02-25 add MH mode, generated filenames with no leading zeros 0.5.3 2006-02-20 switch to gnu autoconf/automake 0.5.2 2006-02-18 add pst2ldif, fix btree processing in libpst.c diff --git a/configure.in b/configure.in index 6678e33..f483d44 100644 --- a/configure.in +++ b/configure.in @@ -1,389 +1,390 @@ AC_PREREQ(2.60) -AC_INIT(libpst,0.6.67,carl@five-ten-sg.com) +AC_INIT(libpst,0.6.68,carl@five-ten-sg.com) AC_CONFIG_SRCDIR([src/libpst.c]) AC_CONFIG_HEADER([config.h]) AC_CONFIG_MACRO_DIR([m4]) AM_INIT_AUTOMAKE AC_CANONICAL_HOST AC_USE_SYSTEM_EXTENSIONS # # 1. Remember that version-info is current:revision:age, and age <= current. # 2. If the source code has changed at all since the last public release, # then increment revision (`c:r:a' becomes `c:r+1:a'). # 3. If any interfaces have been added, removed, or changed since the last # update, increment current, and set revision to 0. # 4. If any interfaces have been added since the last public release, then # increment age, since we should be backward compatible with the previous # version. # 5. If any interfaces have been removed or changed since the last public # release, then set age to 0, since we are not backward compatible. # 6. libtool will build libpst.so.x.y.z where the SONAME is libpst.so.x # and x=current-age, y=age, z=revision -libpst_version_info='5:12:1' +libpst_version_info='5:13:1' AC_SUBST(LIBPST_VERSION_INFO, [$libpst_version_info]) libpst_so_major='4' AC_SUBST(LIBPST_SO_MAJOR, [$libpst_so_major]) # libpst # version soname so library name # 0.6.35 libpst.so.2 libpst.so.2.0.0 # 0.6.37 libpst.so.2 libpst.so.2.1.0 # 0.6.38 libpst.so.2 libpst.so.2.1.0 # 0.6.40 libpst.so.4 libpst.so.4.0.0 # 0.6.43 libpst.so.4 libpst.so.4.0.1 # 0.6.47 libpst.so.4 libpst.so.4.0.2 # 0.6.48 libpst.so.4 libpst.so.4.0.3 # 0.6.49 libpst.so.4 libpst.so.4.0.4 # 0.6.50 libpst.so.4 libpst.so.4.1.0 # 0.6.51 libpst.so.4 libpst.so.4.1.1 # 0.6.52 libpst.so.4 libpst.so.4.1.2 # 0.6.53 libpst.so.4 libpst.so.4.1.3 # 0.6.54 libpst.so.4 libpst.so.4.1.4 # 0.6.55 libpst.so.4 libpst.so.4.1.5 # 0.6.56 libpst.so.4 libpst.so.4.1.6 # 0.6.57 libpst.so.4 libpst.so.4.1.6 # 0.6.58 libpst.so.4 libpst.so.4.1.7 # 0.6.59 libpst.so.4 libpst.so.4.1.8 # 0.6.60 libpst.so.4 libpst.so.4.1.9 # 0.6.61 libpst.so.4 libpst.so.4.1.9 # 0.6.62 libpst.so.4 libpst.so.4.1.9 # 0.6.63 libpst.so.4 libpst.so.4.1.10 # 0.6.66 libpst.so.4 libpst.so.4.1.11 # 0.6.67 libpst.so.4 libpst.so.4.1.12 +# 0.6.68 libpst.so.4 libpst.so.4.1.13 # Check for solaris AC_MSG_CHECKING([for Solaris]) case "$host" in *solaris*) os_solaris=yes ;; *) os_solaris=no ;; esac AC_MSG_RESULT($os_solaris) AM_CONDITIONAL(OS_SOLARIS, [test "$os_solaris" = "yes"]) # Check for win32 AC_MSG_CHECKING([for Win32]) case "$host" in *-mingw*) os_win32=yes ;; *) os_win32=no ;; esac AC_MSG_RESULT($os_win32) AM_CONDITIONAL(OS_WIN32, [test "$os_win32" = "yes"]) # Check for Win32 platform AC_MSG_CHECKING([for Win32 platform in general]) case "$host" in *-cygwin*) platform_win32=yes ;; *) platform_win32=$os_win32 ;; esac AC_MSG_RESULT($platform_win32) AM_CONDITIONAL(PLATFORM_WIN32, [test "$platform_win32" = "yes"]) # Checks for programs. # The following lines adds the --enable-dii option to configure: # # Give the user the choice to enter one of these: # --enable-dii # --enable-dii=yes # --enable-dii=no # AC_MSG_CHECKING([whether we are enabling dii utility]) AC_ARG_ENABLE(dii, AC_HELP_STRING([--enable-dii], [enable dii utility]), [ case "${enableval}" in yes) ;; no) ;; *) AC_MSG_ERROR(bad value ${enableval} for --enable-dii) ;; esac ], # default if not specified enable_dii=yes ) AC_MSG_RESULT([$enable_dii]) AC_PATH_PROG(CONVERT, convert) if test "x$CONVERT" = "x" ; then if test "$enable_dii" = "yes"; then enable_dii=no AC_MSG_WARN([convert program not found. pst2dii disabled]) fi else if test "x`$CONVERT --version 2>&1 | grep -i imagemagick >/dev/null ; echo $?`" != "x0"; then if test "$enable_dii" = "yes"; then enable_dii=no AC_MSG_WARN([wrong convert program found. pst2dii disabled]) fi fi fi AC_CHECK_HEADER([gd.h], [ AC_DEFINE([HAVE_GD_H], [1], [Define to 1 if you have the header file.]) ], [ if test "$enable_dii" = "yes"; then enable_dii=no AC_MSG_WARN([gd.h not found. pst2dii disabled]) fi ]) AM_CONDITIONAL(BUILD_DII, [test "$enable_dii" = "yes"]) # Checks for programs. AC_PROG_CXX AC_PROG_CC AM_PROG_CC_C_O AC_PROG_CPP AC_PROG_INSTALL AC_PROG_LN_S AC_PROG_LIBTOOL AC_PROG_MAKE_SET # make sure we get large file support AC_SYS_LARGEFILE AC_CHECK_SIZEOF(off_t) # Checks for header files. AC_CHECK_HEADER([unistd.h], AM_CONDITIONAL(NEED_XGETOPT, [test yes = no]), AM_CONDITIONAL(NEED_XGETOPT, [test yes = yes]) ) AC_HEADER_DIRENT AC_HEADER_STDC AC_CHECK_HEADERS([ctype.h dirent.h errno.h fcntl.h inttypes.h limits.h regex.h semaphore.h signal.h stdarg.h stdint.h stdio.h stdlib.h string.h sys/param.h sys/shm.h sys/stat.h sys/types.h time.h unistd.h wchar.h]) AC_SEARCH_LIBS([sem_init],[pthread rt]) # Checks for typedefs, structures, and compiler characteristics. AC_HEADER_STDBOOL AC_HEADER_SYS_WAIT AC_C_CONST AC_C_INLINE AC_TYPE_OFF_T AC_TYPE_SIZE_T AC_TYPE_PID_T AC_STRUCT_TM # Checks for library functions. AC_FUNC_FORK AC_FUNC_FSEEKO AC_FUNC_STAT AC_FUNC_LSTAT AC_FUNC_LSTAT_FOLLOWS_SLASHED_SYMLINK if test "$cross_compiling" != "yes"; then AC_FUNC_MALLOC AC_FUNC_MKTIME AC_FUNC_REALLOC fi AC_FUNC_STRFTIME AC_FUNC_VPRINTF AC_CHECK_FUNCS([chdir getcwd memchr memmove memset regcomp strcasecmp strncasecmp strchr strdup strerror strpbrk strrchr strstr strtol get_current_dir_name]) AM_ICONV if test "$am_cv_func_iconv" != "yes"; then AC_MSG_ERROR([libpst requires iconv which is missing]) fi AC_CHECK_FUNCS(regexec,,[AC_CHECK_LIB(regex,regexec, [REGEXLIB=-lregex AC_DEFINE(HAVE_REGEXEC,1,[Define to 1 if you have the regexec function.])], [AC_MSG_ERROR([No regex library found])])]) AC_SUBST(REGEXLIB) # The following lines adds the --enable-pst-debug option to configure: # # Give the user the choice to enter one of these: # --enable-pst-debug # --enable-pst-debug=yes # --enable-pst-debug=no # AC_MSG_CHECKING([whether we are forcing debug dump file creation]) AC_ARG_ENABLE(pst-debug, AC_HELP_STRING([--enable-pst-debug], [force debug dump file creation]), [ case "${enableval}" in yes) ;; no) ;; *) AC_MSG_ERROR(bad value ${enableval} for --enable-pst-debug) ;; esac ], # default if not specified enable_pst_debug=no ) AC_MSG_RESULT([$enable_pst_debug]) if test "$enable_pst_debug" = "yes"; then AC_DEFINE(DEBUG_ALL, 1, Define to 1 to force debug dump file creation) fi # The following lines adds the --enable-libpst-shared option to configure: # # Give the user the choice to enter one of these: # --enable-libpst-shared # --enable-libpst-shared=yes # --enable-libpst-shared=no # AC_MSG_CHECKING([whether we are building libpst shared object]) AC_ARG_ENABLE(libpst-shared, AC_HELP_STRING([--enable-libpst-shared], [build libpst shared object]), [ case "${enableval}" in yes) ;; no) ;; *) AC_MSG_ERROR(bad value ${enableval} for --enable-libpst-shared) ;; esac ], # default if not specified enable_libpst_shared=no ) AC_MSG_RESULT([$enable_libpst_shared]) enable_static_tools=yes if test "$enable_libpst_shared" = "yes"; then enable_shared=yes enable_static_tools=no fi # needed by STATIC_TOOLS in src/Makefile.am AC_SUBST(PST_OBJDIR, [$objdir]) # The following lines adds the --enable-static-tools option to configure: # # Give the user the choice to enter one of these: # --enable-static-tools # --enable-static-tools=yes # --enable-static-tools=no # AC_MSG_CHECKING([whether to link command line tools with libpst statically]) AC_ARG_ENABLE([static-tools], AC_HELP_STRING([--enable-static-tools], [link command line tools with libpst statically]), [ case "${enableval}" in yes) ;; no) ;; *) AC_MSG_ERROR(bad value ${enableval} for --enable-static-tools) ;; esac ], [ enable_static_tools=no ]) AC_MSG_RESULT([$enable_static_tools]) AM_CONDITIONAL(STATIC_TOOLS, [test "$enable_static_tools" = "yes"]) if test "$enable_static_tools" = "yes"; then enable_static="yes" fi # The following lines adds the --enable-python option to configure: # # Give the user the choice to enter one of these: # --enable-python # --enable-python=yes # --enable-python=no # AC_MSG_CHECKING([whether to build the libpst python interface]) AC_ARG_ENABLE([python], AC_HELP_STRING([--enable-python], [build libpst python interface]), [ case "${enableval}" in yes) ;; no) ;; *) AC_MSG_ERROR(bad value ${enableval} for --python) ;; esac ], [ enable_python=yes ]) AC_MSG_RESULT([$enable_python]) AM_CONDITIONAL(PYTHON_INTERFACE, [test "$enable_python" = "yes"]) if test "$enable_python" = "yes"; then enable_shared="yes" # get the version of installed python AX_PYTHON if test "$ax_python_bin" = "no"; then AC_MSG_ERROR(python binary not found) fi py_ver=`echo $ax_python_bin | cut -c7-` # find the flags for that version AC_PYTHON_DEVEL([$py_ver]) PYTHON_INCLUDE_DIR=`echo $python_path | cut -c3-` AC_SUBST([PYTHON_INCLUDE_DIR]) # do we have boost python AX_BOOST_PYTHON if test "$ac_cv_boost_python" = "no"; then AC_MSG_ERROR(boost python not found) fi AC_SUBST(PYTHON_VERSION, [$ax_python_bin]) fi # The following lines adds the --enable-profiling option to configure: # # Give the user the choice to enter one of these: # --enable-profiling # --enable-profiling=yes # --enable-profiling=no # AC_MSG_CHECKING([whether to link with gprof profiling]) AC_ARG_ENABLE([profiling], AC_HELP_STRING([--enable-profiling], [link with gprof profiling]), [ case "${enableval}" in yes) CFLAGS="$CFLAGS -pg" CPPFLAGS="$CPPFLAGS -pg" CXXFLAGS="$CXXFLAGS -pg" ;; no) ;; *) AC_MSG_ERROR(bad value ${enableval} for --profiling) ;; esac ], [ enable_profiling=no ]) AC_MSG_RESULT([$enable_profiling]) AM_CONDITIONAL(GPROF_PROFILING, [test "$enable_profiling" = "yes"]) gsf_flags="`pkg-config libgsf-1 --cflags`" gsf_libs="`pkg-config libgsf-1 --libs`" if test "$gsf_flags" = ""; then AC_MSG_ERROR(libgsf not found) fi AC_SUBST(GSF_FLAGS, [$gsf_flags]) AC_SUBST(GSF_LIBS, [$gsf_libs]) AC_OUTPUT( \ Makefile \ html/Makefile \ libpst.pc \ libpst.spec \ man/Makefile \ src/Makefile \ src/pst2dii.cpp \ python/Makefile \ xml/Makefile \ xml/libpst \ ) diff --git a/libpst.spec.in b/libpst.spec.in index e3bc234..65fea9e 100644 --- a/libpst.spec.in +++ b/libpst.spec.in @@ -1,523 +1,528 @@ Summary: Utilities to convert Outlook .pst files to other formats Name: @PACKAGE@ Version: @VERSION@ Release: 1%{?dist} License: GPLv2+ Group: Applications/Productivity Source: http://www.five-ten-sg.com/%{name}/packages/%{name}-%{version}.tar.gz BuildRoot: %(mktemp -ud %{_tmppath}/%{name}-%{version}-%{release}-XXXXXX) URL: http://www.five-ten-sg.com/%{name}/ Requires: ImageMagick libgsf Requires: %{name}-libs = %{version}-%{release} BuildRequires: libtool BuildRequires: ImageMagick gd-devel zlib-devel python-devel boost-devel libgsf-devel %{!?python_sitelib: %global python_sitelib %(%{__python} -c "from distutils.sysconfig import get_python_lib; print get_python_lib()")} %{!?python_sitearch: %global python_sitearch %(%{__python} -c "from distutils.sysconfig import get_python_lib; print get_python_lib(1)")} %description The Libpst utilities include readpst which can convert email messages to both mbox and MH mailbox formats, pst2ldif which can convert the contacts to .ldif format for import into ldap databases, and pst2dii which can convert email messages to the DII load file format used by Summation. %package libs Summary: Shared library used by the pst utilities Group: Development/Libraries %description libs The libpst-libs package contains the shared library used by the pst utilities. %package python Summary: Python bindings for libpst Group: Development/Libraries Requires: python Requires: %{name}-libs = %{version}-%{release} %if 0%{?fedora} >= 20 %global __provides_exclude_from %{?__provides_exclude_from:%__provides_exclude_from|}^%{python_sitearch}/_.*\.so$ %else %{?filter_setup: %filter_provides_in %{python_sitearch}/_.*\.so$ %filter_setup } %endif %description python The libpst-python package allows you to use the libpst shared object from python code. %package devel Summary: Library links and header files for libpst application development Group: Development/Libraries Requires: pkgconfig Requires: %{name}-libs = %{version}-%{release} %description devel The libpst-devel package contains the library links and header files you'll need to develop applications using the libpst shared library. You do not need to install it if you just want to use the libpst utilities. %package devel-doc Summary: Documentation for libpst.so for libpst application development Group: Documentation Requires: %{name}-doc = %{version}-%{release} %description devel-doc The libpst-devel-doc package contains the doxygen generated documentation for the libpst.so shared library. %package doc Summary: Documentation for the pst utilities in html format Group: Documentation %description doc The libpst-doc package contains the html documentation for the pst utilities. You do not need to install it if you just want to use the libpst utilities. %prep %setup -q %build autoreconf -v -f -i %configure --enable-libpst-shared make %{?_smp_mflags} %install rm -rf $RPM_BUILD_ROOT make DESTDIR=$RPM_BUILD_ROOT install rm $RPM_BUILD_ROOT%{_libdir}/libpst.la rm $RPM_BUILD_ROOT%{_libdir}/libpst.a mv $RPM_BUILD_ROOT%{_datadir}/doc/%{name}-%{version} $RPM_BUILD_ROOT%{_datadir}/doc/%{name} %clean rm -rf $RPM_BUILD_ROOT %post libs -p /sbin/ldconfig %postun libs -p /sbin/ldconfig %files %defattr(-,root,root,-) %{_bindir}/* %{_mandir}/man1/* %{_mandir}/man5/* %files libs %defattr(-,root,root,-) %{_libdir}/libpst.so.* %doc COPYING %files python %defattr(-,root,root,-) %{python_sitearch}/_*.so %exclude %{python_sitearch}/*.a %exclude %{python_sitearch}/*.la %files devel %defattr(-,root,root,-) %{_libdir}/libpst.so %{_includedir}/%{name}-@LIBPST_SO_MAJOR@/ %{_libdir}/pkgconfig/libpst.pc %files devel-doc %defattr(-,root,root,-) %{_datadir}/doc/%{name}/devel/ %files doc %defattr(-,root,root,-) %dir %{_datadir}/doc/%{name}/ %{_datadir}/doc/%{name}/*.html %{_datadir}/doc/%{name}/AUTHORS %{_datadir}/doc/%{name}/COPYING %{_datadir}/doc/%{name}/ChangeLog %{_datadir}/doc/%{name}/NEWS %{_datadir}/doc/%{name}/README %changelog +* Mon Aug 29 2016 Carl Byington 0.6.68-1 +- allow folders containing multiple item types, e.g. email and calendar +- better detection of valid internet headers + +* Tue Jul 19 2016 Fedora Release Engineering - 0.6.67-2 +- https://fedoraproject.org/wiki/Changes/Automatic_Provides_for_Python_RPM_Packages + * Wed Jul 06 2016 Carl Byington 0.6.67-1 - Jeffrey Morlan - multiple bug fixes and an optimization * Thu Feb 04 2016 Fedora Release Engineering - 0.6.66-3 - Rebuilt for https://fedoraproject.org/wiki/Fedora_24_Mass_Rebuild * Fri Jan 15 2016 Jonathan Wakely - 0.6.66-2 - Rebuilt for Boost 1.60 * Mon Dec 21 2015 Carl Byington 0.6.66-1 - Igor Stroh - Added Content-ID header support * Fri Sep 11 2015 Carl Byington 0.6.65-1 - Jeffrey Morlan - fix multiple Content-Type headers - Hans Liss - debug level output * Thu Aug 27 2015 Jonathan Wakely - 0.6.64-6 - Rebuilt for Boost 1.59 -* Wed Jul 29 2015 Fedora Release Engineering - - 0.6.64-5 +* Wed Jul 29 2015 Fedora Release Engineering - 0.6.64-5 - Rebuilt for https://fedoraproject.org/wiki/Changes/F23Boost159 * Wed Jul 22 2015 David Tardon - 0.6.64-4 - rebuild for Boost 1.58 -* Wed Jun 17 2015 Fedora Release Engineering - - 0.6.64-3 +* Wed Jun 17 2015 Fedora Release Engineering - 0.6.64-3 - Rebuilt for https://fedoraproject.org/wiki/Fedora_23_Mass_Rebuild * Sat May 02 2015 Kalev Lember - 0.6.64-2 - Rebuilt for GCC 5 C++11 ABI change * Mon Mar 09 2015 Carl Byington 0.6.64-1 - fix line wrap on python provides_exclude_from - fix unchecked errors found by cppcheck - AJ Shankar fixes for attachment processing and body encodings that contain embedded null chars. * Mon Jan 26 2015 Petr Machata - 0.6.63-5 - Rebuild for boost 1.57.0 * Sun Aug 17 2014 Fedora Release Engineering - 0.6.63-4 - Rebuilt for https://fedoraproject.org/wiki/Fedora_21_22_Mass_Rebuild * Sat Jun 07 2014 Fedora Release Engineering - 0.6.63-3 - Rebuilt for https://fedoraproject.org/wiki/Fedora_21_Mass_Rebuild * Fri May 23 2014 David Tardon - 0.6.63-2 - rebuild for boost 1.55.0 * Fri Dec 27 2013 Carl Byington 0.6.63-1 - Daniel Gryniewicz found buffer overrun in LIST_COPY_TIME * Sun Sep 22 2013 Carl Byington 0.6.62-1 - 983596 - Old dependency filter breaks file coloring * Tue Aug 06 2013 Carl Byington 0.6.61-1 - move documentation to unversioned directory * Sat Aug 03 2013 Fedora Release Engineering - 0.6.59-4 - Rebuilt for https://fedoraproject.org/wiki/Fedora_20_Mass_Rebuild * Sat Jul 27 2013 pmachata@redhat.com - 0.6.59-3 - Rebuild for boost 1.54.0 * Wed Jun 12 2013 Carl Byington 0.6.60-1 - patch from Dominique Leuenberger to add AC_USE_SYSTEM_EXTENSIONS - add readpst -a option for attachment stripping * Tue Jun 11 2013 Remi Collet - 0.6.59-2 - rebuild for new GD 2.1.0 * Fri May 17 2013 Carl Byington 0.6.59-1 - add autoconf checking for libgsf * Fri Mar 29 2013 Carl Byington 0.6.58-4 - add autoreconf for aarch64 * Sun Feb 10 2013 Denis Arnaud - 0.6.58-3 - Rebuild for Boost-1.53.0 * Sat Feb 09 2013 Denis Arnaud - 0.6.58-2 - Rebuild for Boost-1.53.0 * Fri Dec 28 2012 Carl Byington - 0.6.58-1 - fix From quoting on embedded rfc/822 messages * Wed Dec 26 2012 Carl Byington - 0.6.57-1 - bugzilla 852414, remove unnecessary dependencies * Mon Dec 24 2012 Carl Byington - 0.6.56-1 - filter private provides from rpm - merge -m .msg files code into main branch * Thu Aug 09 2012 Carl Byington - 0.6.55-2 - rebuild for python * Thu Jul 19 2012 Fedora Release Engineering - 0.6.54-6 - Rebuilt for https://fedoraproject.org/wiki/Fedora_18_Mass_Rebuild * Tue May 08 2012 Carl Byington - 0.6.55-1 - preserve bcc headers - document -C switch to set default character set - space after colon is not required in header fields * Tue Feb 28 2012 Fedora Release Engineering - 0.6.54-5 - Rebuilt for c++ ABI breakage * Fri Jan 13 2012 Fedora Release Engineering - 0.6.54-4 - Rebuilt for https://fedoraproject.org/wiki/Fedora_17_Mass_Rebuild * Sat Dec 24 2011 Carl Byington - 0.6.54-3 - bump versions and prep for fedora build * Wed Nov 30 2011 Petr Pisar - 0.6.53-3 - Rebuild against boost-1.48 * Mon Nov 14 2011 Carl Byington - 0.6.54-2 - failed to bump version number * Fri Nov 04 2011 Carl Byington - 0.6.54-1 - embedded rfc822 messages might contain rtf encoded bodies * Fri Sep 02 2011 Petr Pisar - 0.6.53-2 - Rebuild against boost-1.47 * Sun Jul 10 2011 Carl Byington - 0.6.53-1 - add Status: header in output - allow fork for parallel processing of individual email folders in separate mode - proper handling of --with-boost-python option * Sun May 22 2011 Carl Byington - 0.6.52-1 - fix dangling freed pointer in embedded rfc822 message processing - allow broken outlook internet header field - it sometimes contains fragments of the message body rather than headers * Sun Apr 17 2011 Carl Byington - 0.6.51-1 - fix for buffer overrun; attachment size from the secondary list of mapi elements overwrote proper size from the primary list of mapi elements. fedora bugzilla 696263 * Tue Feb 08 2011 Fedora Release Engineering - 0.6.49-4 - Rebuilt for https://fedoraproject.org/wiki/Fedora_15_Mass_Rebuild * Mon Feb 07 2011 Thomas Spura - 0.6.49-3 - rebuild for new boost * Fri Dec 24 2010 Carl Byington - 0.6.50-1 - rfc2047 and rfc2231 encoding for non-ascii headers and attachment filenames. * Wed Sep 29 2010 jkeating - 0.6.49-2 - Rebuilt for gcc bug 634757 * Mon Sep 13 2010 Carl Byington - 0.6.49-1 - fix to ignore embedded objects that are not email messages fedora bugzilla 633498 * Thu Sep 02 2010 Carl Byington - 0.6.48-1 - fix for broken internet headers from Outlook - fix ax_python.m4 to look for python2.7 - use mboxrd from quoting for output formats with multiple messages per file - use no from quoting for output formats with single message per file * Sat Jul 31 2010 Carl Byington - 0.6.47-6 - rebuild for python dependencies * Mon Jul 26 2010 David Malcolm - 0.6.47-4 - hack up configure so that it looks for python 2.7 * Wed Jul 21 2010 David Malcolm - 0.6.47-3 - Rebuilt for https://fedoraproject.org/wiki/Features/Python_2.7/MassRebuild * Wed Jul 07 2010 Carl Byington - 0.6.47-2 - Subpackage Licensing, add COPYING to -libs. - patches from Kenneth Berland for solaris * Fri May 07 2010 Carl Byington - 0.6.47-1 - patches from Kenneth Berland for solaris * Thu Jan 21 2010 Carl Byington - 0.6.46-1 - prefer libpthread over librt for finding sem_init function. * Thu Jan 21 2010 Carl Byington - 0.6.45-2 - rebuild for new boost package * Wed Nov 18 2009 Carl Byington - 0.6.45-1 - patch from Hugo DesRosiers to export categories and notes into vcards. - extend that patch to export categories into vcalendar appointments also. * Sun Sep 20 2009 Carl Byington - 0.6.44-1 - patch from Lee Ayres to add file name extensions in separate mode. - allow mixed items types in a folder in separate mode. * Sat Sep 12 2009 Carl Byington - 0.6.43-1 - decode more of the pst format, some minor bug fixes - add support for code pages 1200 and 1201. - add readpst -t option to select output item types, which can now be used to process folders containing mixed item types. - fix segfault with embedded appointments - add readpst -u option for Thunderbird mode .size and .type files - better detection of embedded rfc822 message attachments * Thu Sep 03 2009 Carl Byington - 0.6.42-1 - patch from Fridrich Strba to build with DJGPP DOS cross-compiler. * Sat Jul 25 2009 Fedora Release Engineering - 0.6.41-2 - Rebuilt for https://fedoraproject.org/wiki/Fedora_12_Mass_Rebuild * Tue Jun 23 2009 Carl Byington - 0.6.41-1 - fix ax_python detection - should not use locate command - checking for fedora versions is not needed * Tue Jun 23 2009 Carl Byington - 0.6.40-1 - fedora 11 has python2.6 - remove pdf version of the man pages * Sun Jun 21 2009 Carl Byington - 0.6.39-1 - fedora > 10 moved to boost-python-devel * Sun Jun 21 2009 Carl Byington - 0.6.38-1 - add python interface to the shared library. - bump soname to version 4 for many changes to the interface. - better decoding of recurrence data in appointments. - remove readpstlog since debug log files are now plain text. - add readpst -j option for parallel jobs for each folder. - make nested mime multipart/alternative to hold the text/html parts. * Fri Apr 17 2009 Carl Byington - 0.6.37-1 - add pst_attach_to_mem() back into the shared library interface. - fix memory leak caught by valgrind. * Tue Apr 14 2009 Carl Byington - 0.6.36-1 - build separate -doc and -devel-doc subpackages. - other spec file cleanup * Wed Apr 08 2009 Carl Byington - 0.6.35-1 - properly add trailing mime boundary in all modes. - build separate libpst, libpst-libs, libpst-devel rpms. * Thu Mar 19 2009 Carl Byington - 0.6.34-1 - avoid putting mixed item types into the same output folder. * Tue Mar 17 2009 Carl Byington - 0.6.33-1 - compensate for iconv conversion to utf-7 that produces strings that are not null terminated. - don't produce empty attachment files in separate mode. * Sat Mar 14 2009 Carl Byington - 0.6.32-1 - fix ppc64 compile error * Sat Mar 14 2009 Carl Byington - 0.6.31-1 - bump version for fedora cvs tagging mistake * Sat Mar 14 2009 Carl Byington - 0.6.30-1 - track character set individually for each mapi element. - remove charset option from pst2ldif since we get that from each object now. - avoid emitting bogus empty email messages into contacts and calendar files. * Tue Feb 24 2009 Carl Byington - 0.6.29-1 - fix for 64bit on Fedora 11 * Tue Feb 24 2009 Carl Byington - 0.6.28-1 - improve decoding of multipart/report and message/rfc822 mime types. - improve character set handling. - fix embedded rfc822 messages with attachments. * Sat Feb 07 2009 Carl Byington - 0.6.27-1 - fix for const correctness on Fedora 11 * Sat Feb 07 2009 Carl Byington - 0.6.26-1 - patch from Fridrich Strba for building on mingw and general - cleanup of autoconf files. - add processing for pst files of type 0x0f. - strip and regenerate all MIME headers to avoid duplicates. - do a better job of making unique MIME boundaries. - only use base64 coding when strictly necessary. * Fri Jan 16 2009 Carl Byington - 0.6.25-1 - improve handling of content-type charset values in mime parts * Thu Dec 11 2008 Carl Byington - 0.6.24-1 - patch from Chris Eagle to build on cygwin * Thu Dec 04 2008 Carl Byington - 0.6.23-1 - bump version to avoid cvs tagging mistake in fedora * Fri Nov 28 2008 Carl Byington - 0.6.22-1 - patch from David Cuadrado to process emails with type PST_TYPE_OTHER - base64_encode_multiple() may insert newline, needs larger malloc - subject lines shorter than 2 bytes could segfault * Tue Oct 21 2008 Carl Byington - 0.6.21-1 - fix title bug with old schema in pst2ldif. - also escape commas in distinguished names per rfc4514. * Thu Oct 09 2008 Carl Byington - 0.6.20-1 - add configure option --enable-dii=no to remove dependency on libgd. - many fixes in pst2ldif by Robert Harris. - add -D option to include deleted items, from Justin Greer - fix from Justin Greer to add missing email headers - fix from Justin Greer for my_stristr() - fix for orphan children when building descriptor tree - avoid writing uninitialized data to debug log file - remove unreachable code - create dummy top-of-folder descriptor if needed for corrupt pst files * Sun Sep 14 2008 Carl Byington - 0.6.19-1 - Fix base64 encoding that could create long lines. - Initial work on a .so shared library from Bharath Acharya. * Thu Aug 28 2008 Carl Byington - 0.6.18-1 - Fixes for iconv on Mac from Justin Greer. * Tue Aug 05 2008 Carl Byington - 0.6.17-1 - More fixes for 32/64 bit portability on big endian ppc. * Tue Aug 05 2008 Carl Byington - 0.6.16-1 - Use inttypes.h for portable printing of 64 bit items. * Wed Jul 30 2008 Carl Byington - 0.6.15-1 - Patch from Robert Simpson for file handle leak in error case. - Fix for missing length on lz decompression, bug found by Chris White. * Sun Jun 15 2008 Carl Byington - 0.6.14-1 - Fix my mistake in debian packaging. * Fri Jun 13 2008 Carl Byington - 0.6.13-1 - Patch from Robert Simpson for encryption type 2. * Tue Jun 10 2008 Carl Byington - 0.6.12-1 - Patch from Joachim Metz for debian packaging and - fix for incorrect length on lz decompression * Tue Jun 03 2008 Carl Byington - 0.6.11-1 - Use ftello/fseeko to properly handle large files. - Document and properly use datasize field in b5 blocks. - Fix some MSVC compile issues and collect MSVC dependencies into one place. * Thu May 29 2008 Carl Byington - 0.6.10-1 - Patch from Robert Simpson for doubly-linked list code and arrays of unicode strings. * Fri May 16 2008 Carl Byington - 0.6.9 - Patch from Joachim Metz for 64 bit compile. - Fix pst format documentation for 8 byte backpointers. * Wed Mar 05 2008 Carl Byington - 0.6.8 - Initial version of pst2dii to convert to Summation dii load file format - changes for Fedora packaging guidelines (#434727) * Tue Jul 10 2007 Carl Byington - 0.5.5 - merge changes from Joe Nahmias version * Sun Feb 19 2006 Carl Byington - 0.5.3 - initial spec file using autoconf and http://www.fedora.us/docs/rpm-packaging-guidelines.html diff --git a/regression/regression-tests.bash b/regression/regression-tests.bash index 40ca4d9..5f99865 100644 --- a/regression/regression-tests.bash +++ b/regression/regression-tests.bash @@ -1,155 +1,156 @@ #!/bin/bash function consistency() { # check source and xml documentation for consistency ( cd .. # back to top level of project f1=/tmp/f1$$ f2=/tmp/f2$$ grep 'case 0x' src/libpst.c | awk '{print $2}' | tr A-Z a-z | sed -e 's/://g' | sort >$f1 grep '^0x' xml/libpst.in | awk '{print $1}' | (for i in {1..19}; do read a; done; cat) | sort >$f2 diff $f1 $f2 less $f1 #rm -f $f1 $f2 ls -al $f1 $f2 ) } function dodii() { n="$1" fn="$2" ba=$(basename "$fn" .pst) size=$(stat -c %s $fn) rm -rf output$n if [ -z "$val" ] || [ $size -lt 10000000 ]; then echo $fn mkdir output$n $val ../src/pst2dii -f /usr/share/fonts/bitstream-vera/VeraMono.ttf -B "bates-" -o output$n -O $ba.mydii -d $fn.log $fn >$fn.dii.err 2>&1 fi } function doldif() { n="$1" fn="$2" ba=$(basename "$fn" .pst) size=$(stat -c %s $fn) rm -rf output$n if [ -z "$val" ] || [ $size -lt 10000000 ]; then echo $fn mkdir output$n $val ../src/pst2ldif -d $ba.ldif.log -b 'o=ams-cc.com, c=US' -c 'inetOrgPerson' $fn >$ba.ldif.err 2>&1 fi } function dopst() { n="$1" fn="$2" ba=$(basename "$fn" .pst) size=$(stat -c %s $fn) jobs="" [ -n "$val" ] && jobs="-j 0" rm -rf output$n if [ -z "$val" ] || [ $size -lt 100000000 ]; then echo $fn mkdir output$n if [ "$regression" == "yes" ]; then $val ../src/readpst $jobs -te -r -cv -o output$n $fn >$ba.err 2>&1 else ## only email and include deleted items, have a deleted items folder with multiple item types #$val ../src/readpst $jobs -te -r -D -cv -o output$n -d $ba.log $fn >$ba.err 2>&1 ## normal recursive dump char='BIG-5' char='us-ascii' acc="-a '.xls,.doc'" acc='' utf='-8' echo $val ../src/readpst $utf $acc -C $char -j 0 -r -cv -o output$n -d $ba.log $fn $val ../src/readpst $utf $acc -C $char -j 0 -r -cv -o output$n -d $ba.log $fn >$ba.err 2>&1 + #readpst $utf $acc -C $char -j 0 -r -cv -o output$n -d $ba.log $fn >$ba.err 2>&1 ## separate mode with filename extensions and .msg files #echo $val ../src/readpst $jobs -r -m -D -cv -o output$n -d $ba.log $fn # $val ../src/readpst $jobs -r -m -D -cv -o output$n -d $ba.log $fn >$ba.err 2>&1 ## separate mode where we decode all attachments to binary files #echo $val ../src/readpst $jobs -r -S -D -cv -o output$n -d $ba.log $fn # $val ../src/readpst $jobs -r -S -D -cv -o output$n -d $ba.log $fn >$ba.err 2>&1 ## testing idblock #../src/getidblock -p $fn 0 >$ba.fulldump fi fi } #consistency #exit pushd .. make || exit popd rm -rf output* *.err *.log v="valgrind --leak-check=full" val="" func="dopst" [ "$1" == "pst" ] && func="dopst" [ "$1" == "pstv" ] && func="dopst" && val=$v [ "$1" == "ldif" ] && func="doldif" [ "$1" == "dii" ] && func="dodii" regression="" [ "$2" == "reg" ] && regression="yes" [ "$regression" == "yes" ] && val="" $func 1 ams.pst $func 2 sample_64.pst $func 3 test.pst $func 4 big_mail.pst $func 5 mbmg.archive.pst $func 6 Single2003-read.pst $func 7 Single2003-unread.pst $func 8 ol2k3high.pst $func 9 ol97high.pst $func 10 returned_message.pst $func 11 flow.pst $func 12 test-html.pst $func 13 test-text.pst $func 14 joe.romanowski.pst $func 15 hourig1.pst $func 16 test-mac.pst $func 18 spam.pst $func 19 rendgen.pst # single email appointment $func 20 rendgen2.pst # email appointment with no termination date $func 21 rendgen3.pst # mime signed email $func 22 rendgen4.pst # appointment test cases $func 23 rendgen5.pst # appointment test cases $func 24 paul.sheer.pst # embedded rfc822 attachment $func 25 jerry.pst # non ascii subject lines $func 26 phill.bertolus.pst # possible segfault in forked process, cannot reproduce $func 27 kaiser.pst # appointments with other character sets $func 28 pstsample.pst # character set issue $func 29 pstsample2.pst # embedded image in rtf data $func 30 pstsample3.pst # exports of rtf and html $func 31 Journal_Archives_08_29_2010.pst [ -n "$val" ] && grep 'lost:' *err | grep -v 'lost: 0 ' if [ "$regression" == "yes" ]; then ( (for i in output*; do find $i -type f; done) | while read a; do grep -v iamunique "$a" rm -f "$a" done ) >regression.txt fi diff --git a/src/libpst.h b/src/libpst.h index 523cdc7..f4ab577 100644 --- a/src/libpst.h +++ b/src/libpst.h @@ -1,1163 +1,1164 @@ /*** * libpst.h * Part of LibPST project * Written by David Smith * dave.s@earthcorp.com */ // LibPST - Library for Accessing Outlook .pst files // Dave Smith - davesmith@users.sourceforge.net #ifndef __PST_LIBPST_H #define __PST_LIBPST_H #include "common.h" // switch to maximal packing for all structures in the libpst interface // this is reverted at the end of this file #ifdef _MSC_VER #pragma pack(push, 1) #endif #if defined(__GNUC__) || defined (__SUNPRO_C) || defined(__SUNPRO_CC) #pragma pack(1) #endif #define PST_TYPE_NOTE 1 #define PST_TYPE_SCHEDULE 2 #define PST_TYPE_APPOINTMENT 8 #define PST_TYPE_CONTACT 9 #define PST_TYPE_JOURNAL 10 #define PST_TYPE_STICKYNOTE 11 #define PST_TYPE_TASK 12 #define PST_TYPE_OTHER 13 #define PST_TYPE_REPORT 14 +#define PST_TYPE_MAX 15 // defines types of possible encryption #define PST_NO_ENCRYPT 0 #define PST_COMP_ENCRYPT 1 #define PST_ENCRYPT 2 // defines different types of mappings #define PST_MAP_ATTRIB (uint32_t)1 #define PST_MAP_HEADER (uint32_t)2 // define my custom email attributes. #define PST_ATTRIB_HEADER -1 // defines types of free/busy values for appointment->showas #define PST_FREEBUSY_FREE 0 #define PST_FREEBUSY_TENTATIVE 1 #define PST_FREEBUSY_BUSY 2 #define PST_FREEBUSY_OUT_OF_OFFICE 3 // defines labels for appointment->label #define PST_APP_LABEL_NONE 0 #define PST_APP_LABEL_IMPORTANT 1 #define PST_APP_LABEL_BUSINESS 2 #define PST_APP_LABEL_PERSONAL 3 #define PST_APP_LABEL_VACATION 4 #define PST_APP_LABEL_MUST_ATTEND 5 #define PST_APP_LABEL_TRAVEL_REQ 6 #define PST_APP_LABEL_NEEDS_PREP 7 #define PST_APP_LABEL_BIRTHDAY 8 #define PST_APP_LABEL_ANNIVERSARY 9 #define PST_APP_LABEL_PHONE_CALL 10 // define type of recuring event #define PST_APP_RECUR_NONE 0 #define PST_APP_RECUR_DAILY 1 #define PST_APP_RECUR_WEEKLY 2 #define PST_APP_RECUR_MONTHLY 3 #define PST_APP_RECUR_YEARLY 4 // define attachment types #define PST_ATTACH_NONE 0 #define PST_ATTACH_BY_VALUE 1 #define PST_ATTACH_BY_REF 2 #define PST_ATTACH_BY_REF_RESOLV 3 #define PST_ATTACH_BY_REF_ONLY 4 #define PST_ATTACH_EMBEDDED 5 #define PST_ATTACH_OLE 6 // define flags #define PST_FLAG_READ 0x01 #define PST_FLAG_UNMODIFIED 0x02 #define PST_FLAG_SUBMIT 0x04 #define PST_FLAG_UNSENT 0x08 #define PST_FLAG_HAS_ATTACHMENT 0x10 #define PST_FLAG_FROM_ME 0x20 #define PST_FLAG_ASSOCIATED 0x40 #define PST_FLAG_RESEND 0x80 #define PST_FLAG_RN_PENDING 0x100 #define PST_FLAG_NRN_PENDING 0x200 typedef struct pst_entryid { int32_t u1; char entryid[16]; uint32_t id; } pst_entryid; typedef struct pst_index_ll { uint64_t i_id; uint64_t offset; uint64_t size; int64_t u1; } pst_index_ll; typedef struct pst_id2_tree { uint64_t id2; pst_index_ll *id; struct pst_id2_tree *child; struct pst_id2_tree *next; } pst_id2_tree; typedef struct pst_desc_tree { uint64_t d_id; uint64_t parent_d_id; pst_index_ll *desc; pst_index_ll *assoc_tree; int32_t no_child; struct pst_desc_tree *prev; struct pst_desc_tree *next; struct pst_desc_tree *parent; struct pst_desc_tree *child; struct pst_desc_tree *child_tail; } pst_desc_tree; /** The string is either utf8 encoded, or it is in the code page * specified by the containing mapi object. It can be forced into * utf8 by calling pst_convert_utf8() or pst_convert_utf8_null(). */ typedef struct pst_string { /** @li 1 true * @li 0 false */ int is_utf8; char *str; } pst_string; /** a simple wrapper for binary blobs */ typedef struct pst_binary { size_t size; char *data; } pst_binary; /** This contains the email related mapi elements */ typedef struct pst_item_email { /** mapi element 0x0e06 PR_MESSAGE_DELIVERY_TIME */ FILETIME *arrival_date; /** mapi element 0x0002 PR_ALTERNATE_RECIPIENT_ALLOWED * @li 1 true * @li 0 not set * @li -1 false */ int autoforward; /** mapi element 0x0e03 PR_DISPLAY_CC */ pst_string cc_address; /** mapi element 0x0e02 PR_DISPLAY_BCC */ pst_string bcc_address; /** mapi element 0x0071 PR_CONVERSATION_INDEX */ pst_binary conversation_index; /** mapi element 0x3a03 PR_CONVERSION_PROHIBITED * @li 1 true * @li 0 false */ int conversion_prohibited; /** mapi element 0x0e01 PR_DELETE_AFTER_SUBMIT * @li 1 true * @li 0 false */ int delete_after_submit; /** mapi element 0x0023 PR_ORIGINATOR_DELIVERY_REPORT_REQUESTED * @li 1 true * @li 0 false */ int delivery_report; /** mapi element 0x6f04 */ pst_binary encrypted_body; /** mapi element 0x6f02 */ pst_binary encrypted_htmlbody; /** mapi element 0x007d PR_TRANSPORT_MESSAGE_HEADERS */ pst_string header; /** mapi element 0x1013 */ pst_string htmlbody; /** mapi element 0x0017 PR_IMPORTANCE * @li 0 low * @li 1 normal * @li 2 high */ int32_t importance; /** mapi element 0x1042 */ pst_string in_reply_to; /** mapi element 0x0058 PR_MESSAGE_CC_ME, this user is listed explicitly in the CC address * @li 1 true * @li 0 false */ int message_cc_me; /** mapi element 0x0059 PR_MESSAGE_RECIP_ME, this user appears in TO, CC or BCC address list * @li 1 true * @li 0 false */ int message_recip_me; /** mapi element 0x0057 PR_MESSAGE_TO_ME, this user is listed explicitly in the TO address * @li 1 true * @li 0 false */ int message_to_me; /** mapi element 0x1035 */ pst_string messageid; /** mapi element 0x002e PR_ORIGINAL_SENSITIVITY * @li 0=none * @li 1=personal * @li 2=private * @li 3=company confidential */ int32_t original_sensitivity; /** mapi element 0x0072 PR_ORIGINAL_DISPLAY_BCC */ pst_string original_bcc; /** mapi element 0x0073 PR_ORIGINAL_DISPLAY_CC */ pst_string original_cc; /** mapi element 0x0074 PR_ORIGINAL_DISPLAY_TO */ pst_string original_to; /** mapi element 0x0051 PR_RECEIVED_BY_SEARCH_KEY */ pst_string outlook_recipient; /** mapi element 0x0044 PR_RCVD_REPRESENTING_NAME */ pst_string outlook_recipient_name; /** mapi element 0x0052 PR_RCVD_REPRESENTING_SEARCH_KEY */ pst_string outlook_recipient2; /** mapi element 0x003b PR_SENT_REPRESENTING_SEARCH_KEY */ pst_string outlook_sender; /** mapi element 0x0042 PR_SENT_REPRESENTING_NAME */ pst_string outlook_sender_name; /** mapi element 0x0c1d PR_SENDER_SEARCH_KEY */ pst_string outlook_sender2; /** mapi element 0x0026 PR_PRIORITY * @li 0 nonurgent * @li 1 normal * @li 2 urgent */ /** mapi element */ int32_t priority; /** mapi element 0x0070 PR_CONVERSATION_TOPIC */ pst_string processed_subject; /** mapi element 0x0029 PR_READ_RECEIPT_REQUESTED * @li 1 true * @li 0 false */ int read_receipt; /** mapi element 0x0075 PR_RECEIVED_BY_ADDRTYPE */ pst_string recip_access; /** mapi element 0x0076 PR_RECEIVED_BY_EMAIL_ADDRESS */ pst_string recip_address; /** mapi element 0x0077 PR_RCVD_REPRESENTING_ADDRTYPE */ pst_string recip2_access; /** mapi element 0x0078 PR_RCVD_REPRESENTING_EMAIL_ADDRESS */ pst_string recip2_address; /** mapi element 0x0c17 PR_REPLY_REQUESTED * @li 1 true * @li 0 false */ int reply_requested; /** mapi element 0x0050 PR_REPLY_RECIPIENT_NAMES */ pst_string reply_to; /** mapi element 0x1046, this seems to be the message-id of the rfc822 mail that is being returned */ pst_string return_path_address; /** mapi element 0x1007 PR_RTF_SYNC_BODY_COUNT, * a count of the *significant* charcters in the rtf body. Doesn't count * whitespace and other ignorable characters. */ int32_t rtf_body_char_count; /** mapi element 0x1006 PR_RTF_SYNC_BODY_CRC */ int32_t rtf_body_crc; /** mapi element 0x1008 PR_RTF_SYNC_BODY_TAG, * the first couple of lines of RTF body so that after modification, then beginning can * once again be found. */ pst_string rtf_body_tag; /** mapi element 0x1009 PR_RTF_COMPRESSED, * the compressed rtf body data. * Use pst_lzfu_decompress() to retrieve the actual rtf body data. */ pst_binary rtf_compressed; /** mapi element 0x0e1f PR_RTF_IN_SYNC, * True means that the rtf version is same as text body. * False means rtf version is more up-to-date than text body. * If this value doesn't exist, text body is more up-to-date than rtf and * cannot update to the rtf. * @li 1 true * @li 0 false */ int rtf_in_sync; /** mapi element 0x1010 PR_RTF_SYNC_PREFIX_COUNT, * a count of the ignored characters before the first significant character */ int32_t rtf_ws_prefix_count; /** mapi element 0x1011 PR_RTF_SYNC_TRAILING_COUNT, * a count of the ignored characters after the last significant character */ int32_t rtf_ws_trailing_count; /** mapi element 0x0064 PR_SENT_REPRESENTING_ADDRTYPE */ pst_string sender_access; /** mapi element 0x0065 PR_SENT_REPRESENTING_EMAIL_ADDRESS */ pst_string sender_address; /** mapi element 0x0c1e PR_SENDER_ADDRTYPE */ pst_string sender2_access; /** mapi element 0x0c1f PR_SENDER_EMAIL_ADDRESS */ pst_string sender2_address; /** mapi element 0x0036 PR_SENSITIVITY * @li 0=none * @li 1=personal * @li 2=private * @li 3=company confidential */ int32_t sensitivity; /** mapi element 0x0039 PR_CLIENT_SUBMIT_TIME */ FILETIME *sent_date; /** mapi element 0x0e0a PR_SENTMAIL_ENTRYID */ pst_entryid *sentmail_folder; /** mapi element 0x0e04 PR_DISPLAY_TO */ pst_string sentto_address; /** mapi element 0x1001 PR_REPORT_TEXT, delivery report dsn body */ pst_string report_text; /** mapi element 0x0032 PR_REPORT_TIME, delivery report time */ FILETIME *report_time; /** mapi element 0x0c04 PR_NDR_REASON_CODE */ int32_t ndr_reason_code; /** mapi element 0x0c05 PR_NDR_DIAG_CODE */ int32_t ndr_diag_code; /** mapi element 0x0c1b PR_SUPPLEMENTARY_INFO */ pst_string supplementary_info; /** mapi element 0x0c20 PR_NDR_STATUS_CODE */ int32_t ndr_status_code; // elements added for .msg processing /** mapi element 0x0040 PR_RECEIVED_BY_NAME */ pst_string outlook_received_name1; /** mapi element 0x0c1a PR_SENDER_NAME */ pst_string outlook_sender_name2; /** mapi element 0x0e1d PR_NORMALIZED_SUBJECT */ pst_string outlook_normalized_subject; /** mapi element 0x300b PR_SEARCH_KEY */ pst_string outlook_search_key; } pst_item_email; /** This contains the folder related mapi elements */ typedef struct pst_item_folder { /** mapi element 0x3602 PR_CONTENT_COUNT */ int32_t item_count; /** mapi element 0x3603 PR_CONTENT_UNREAD */ int32_t unseen_item_count; /** mapi element 0x3617 PR_ASSOC_CONTENT_COUNT Associated content are items that are attached to this folder, but are hidden from users. */ int32_t assoc_count; /** mapi element 0x360a PR_SUBFOLDERS * @li 1 true * @li 0 false */ /** mapi element */ int subfolder; } pst_item_folder; /** This contains the message store related mapi elements */ typedef struct pst_item_message_store { /** mapi element 0x35e0 */ pst_entryid *top_of_personal_folder; /** mapi element 0x35e2 */ pst_entryid *default_outbox_folder; /** mapi element 0x35e3 */ pst_entryid *deleted_items_folder; /** mapi element 0x35e4 */ pst_entryid *sent_items_folder; /** mapi element 0x35e5 */ pst_entryid *user_views_folder; /** mapi element 0x35e6 */ pst_entryid *common_view_folder; /** mapi element 0x35e7 */ pst_entryid *search_root_folder; /** mapi element 0x7c07 */ pst_entryid *top_of_folder; /** mapi element 0x35df, * bit mask of folders in this message store * @li 0x1 FOLDER_IPM_SUBTREE_VALID * @li 0x2 FOLDER_IPM_INBOX_VALID * @li 0x4 FOLDER_IPM_OUTBOX_VALID * @li 0x8 FOLDER_IPM_WASTEBOX_VALID * @li 0x10 FOLDER_IPM_SENTMAIL_VALID * @li 0x20 FOLDER_VIEWS_VALID * @li 0x40 FOLDER_COMMON_VIEWS_VALID * @li 0x80 FOLDER_FINDER_VALID */ int32_t valid_mask; /** mapi element 0x76ff */ int32_t pwd_chksum; } pst_item_message_store; /** This contains the contact related mapi elements */ typedef struct pst_item_contact { /** mapi element 0x3a00 PR_ACCOUNT */ pst_string account_name; /** mapi element 0x3003 PR_EMAIL_ADDRESS, or 0x8083 */ pst_string address1; /** mapi element 0x8085 */ pst_string address1a; /** mapi element 0x8084 */ pst_string address1_desc; /** mapi element 0x3002 PR_ADDRTYPE, or 0x8082 */ pst_string address1_transport; /** mapi element 0x8093 */ pst_string address2; /** mapi element 0x8095 */ pst_string address2a; /** mapi element 0x8094 */ pst_string address2_desc; /** mapi element 0x8092 */ pst_string address2_transport; /** mapi element 0x80a3 */ pst_string address3; /** mapi element 0x80a5 */ pst_string address3a; /** mapi element 0x80a4 */ pst_string address3_desc; /** mapi element 0x80a2 */ pst_string address3_transport; /** mapi element 0x3a30 PR_ASSISTANT */ pst_string assistant_name; /** mapi element 0x3a2e PR_ASSISTANT_TELEPHONE_NUMBER */ pst_string assistant_phone; /** mapi element 0x8535 */ pst_string billing_information; /** mapi element 0x3a42 PR_BIRTHDAY */ FILETIME *birthday; /** mapi element 0x801b */ pst_string business_address; /** mapi element 0x3a27 PR_BUSINESS_ADDRESS_CITY */ pst_string business_city; /** mapi element 0x3a26 PR_BUSINESS_ADDRESS_COUNTRY */ pst_string business_country; /** mapi element 0x3a24 PR_BUSINESS_FAX_NUMBER */ pst_string business_fax; /** mapi element 0x3a51 PR_BUSINESS_HOME_PAGE */ pst_string business_homepage; /** mapi element 0x3a08 PR_BUSINESS_TELEPHONE_NUMBER */ pst_string business_phone; /** mapi element 0x3a1b PR_BUSINESS2_TELEPHONE_NUMBER */ pst_string business_phone2; /** mapi element 0x3a2b PR_BUSINESS_PO_BOX */ pst_string business_po_box; /** mapi element 0x3a2a PR_BUSINESS_POSTAL_CODE */ pst_string business_postal_code; /** mapi element 0x3a28 PR_BUSINESS_ADDRESS_STATE_OR_PROVINCE */ pst_string business_state; /** mapi element 0x3a29 PR_BUSINESS_ADDRESS_STREET */ pst_string business_street; /** mapi element 0x3a02 PR_CALLBACK_TELEPHONE_NUMBER */ pst_string callback_phone; /** mapi element 0x3a1e PR_CAR_TELEPHONE_NUMBER */ pst_string car_phone; /** mapi element 0x3a57 PR_COMPANY_MAIN_PHONE_NUMBER */ pst_string company_main_phone; /** mapi element 0x3a16 PR_COMPANY_NAME */ pst_string company_name; /** mapi element 0x3a49 PR_COMPUTER_NETWORK_NAME */ pst_string computer_name; /** mapi element 0x3a4a PR_CUSTOMER_ID */ pst_string customer_id; /** mapi element 0x3a15 PR_POSTAL_ADDRESS */ pst_string def_postal_address; /** mapi element 0x3a18 PR_DEPARTMENT_NAME */ pst_string department; /** mapi element 0x3a45 PR_DISPLAY_NAME_PREFIX */ pst_string display_name_prefix; /** mapi element 0x3a06 PR_GIVEN_NAME */ pst_string first_name; /** mapi element 0x8530 */ pst_string followup; /** mapi element 0x80d8 */ pst_string free_busy_address; /** mapi element 0x3a4c PR_FTP_SITE */ pst_string ftp_site; /** mapi element 0x8005 */ pst_string fullname; /** mapi element 0x3a4d PR_GENDER * @li 0 unspecified * @li 1 female * @li 2 male */ int16_t gender; /** mapi element 0x3a07 PR_GOVERNMENT_ID_NUMBER */ pst_string gov_id; /** mapi element 0x3a43 PR_HOBBIES */ pst_string hobbies; /** mapi element 0x801a */ pst_string home_address; /** mapi element 0x3a59 PR_HOME_ADDRESS_CITY */ pst_string home_city; /** mapi element 0x3a5a PR_HOME_ADDRESS_COUNTRY */ pst_string home_country; /** mapi element 0x3a25 PR_HOME_FAX_NUMBER */ pst_string home_fax; /** mapi element 0x3a09 PR_HOME_TELEPHONE_NUMBER */ pst_string home_phone; /** mapi element 0x3a2f PR_HOME2_TELEPHONE_NUMBER */ pst_string home_phone2; /** mapi element 0x3a5e PR_HOME_ADDRESS_POST_OFFICE_BOX */ pst_string home_po_box; /** mapi element 0x3a5b PR_HOME_ADDRESS_POSTAL_CODE */ pst_string home_postal_code; /** mapi element 0x3a5c PR_HOME_ADDRESS_STATE_OR_PROVINCE */ pst_string home_state; /** mapi element 0x3a5d PR_HOME_ADDRESS_STREET */ pst_string home_street; /** mapi element 0x3a0a PR_INITIALS */ pst_string initials; /** mapi element 0x3a2d PR_ISDN_NUMBER */ pst_string isdn_phone; /** mapi element 0x3a17 PR_TITLE */ pst_string job_title; /** mapi element 0x3a0b PR_KEYWORD */ pst_string keyword; /** mapi element 0x3a0c PR_LANGUAGE */ pst_string language; /** mapi element 0x3a0d PR_LOCATION */ pst_string location; /** mapi element 0x3a0e PR_MAIL_PERMISSION * @li 1 true * @li 0 false */ int mail_permission; /** mapi element 0x3a4e PR_MANAGER_NAME */ pst_string manager_name; /** mapi element 0x3a44 PR_MIDDLE_NAME */ pst_string middle_name; /** mapi element 0x8534 */ pst_string mileage; /** mapi element 0x3a1c PR_MOBILE_TELEPHONE_NUMBER */ pst_string mobile_phone; /** mapi element 0x3a4f PR_NICKNAME */ pst_string nickname; /** mapi element 0x3a19 PR_OFFICE_LOCATION */ pst_string office_loc; /** mapi element 0x3a0f PR_MHS_COMMON_NAME */ pst_string common_name; /** mapi element 0x3a10 PR_ORGANIZATIONAL_ID_NUMBER */ pst_string org_id; /** mapi element 0x801c */ pst_string other_address; /** mapi element 0x3a5f PR_OTHER_ADDRESS_CITY */ pst_string other_city; /** mapi element 0x3a60 PR_OTHER_ADDRESS_COUNTRY */ pst_string other_country; /** mapi element 0x3a1f PR_OTHER_TELEPHONE_NUMBER */ pst_string other_phone; /** mapi element 0x3a64 PR_OTHER_ADDRESS_POST_OFFICE_BOX */ pst_string other_po_box; /** mapi element 0x3a61 PR_OTHER_ADDRESS_POSTAL_CODE */ pst_string other_postal_code; /** mapi element 0x3a62 PR_OTHER_ADDRESS_STATE_OR_PROVINCE */ pst_string other_state; /** mapi element 0x3a63 PR_OTHER_ADDRESS_STREET */ pst_string other_street; /** mapi element 0x3a21 PR_PAGER_TELEPHONE_NUMBER */ pst_string pager_phone; /** mapi element 0x3a50 PR_PERSONAL_HOME_PAGE */ pst_string personal_homepage; /** mapi element 0x3a47 PR_PREFERRED_BY_NAME */ pst_string pref_name; /** mapi element 0x3a23 PR_PRIMARY_FAX_NUMBER */ pst_string primary_fax; /** mapi element 0x3a1a PR_PRIMARY_TELEPHONE_NUMBER */ pst_string primary_phone; /** mapi element 0x3a46 PR_PROFESSION */ pst_string profession; /** mapi element 0x3a1d PR_RADIO_TELEPHONE_NUMBER */ pst_string radio_phone; /** mapi element 0x3a40 PR_SEND_RICH_INFO * @li 1 true * @li 0 false */ int rich_text; /** mapi element 0x3a48 PR_SPOUSE_NAME */ pst_string spouse_name; /** mapi element 0x3a05 PR_GENERATION (Jr., Sr., III, etc) */ pst_string suffix; /** mapi element 0x3a11 PR_SURNAME */ pst_string surname; /** mapi element 0x3a2c PR_TELEX_NUMBER */ pst_string telex; /** mapi element 0x3a20 PR_TRANSMITTABLE_DISPLAY_NAME */ pst_string transmittable_display_name; /** mapi element 0x3a4b PR_TTYTDD_PHONE_NUMBER */ pst_string ttytdd_phone; /** mapi element 0x3a41 PR_WEDDING_ANNIVERSARY */ FILETIME *wedding_anniversary; /** mapi element 0x8045 */ pst_string work_address_street; /** mapi element 0x8046 */ pst_string work_address_city; /** mapi element 0x8047 */ pst_string work_address_state; /** mapi element 0x8048 */ pst_string work_address_postalcode; /** mapi element 0x8049 */ pst_string work_address_country; /** mapi element 0x804a */ pst_string work_address_postofficebox; } pst_item_contact; /** This contains the attachment related mapi elements */ typedef struct pst_item_attach { /** mapi element 0x3704 PR_ATTACH_FILENAME */ pst_string filename1; /** mapi element 0x3707 PR_ATTACH_LONG_FILENAME */ pst_string filename2; /** mapi element 0x370e PR_ATTACH_MIME_TAG */ pst_string mimetype; /** mapi element 0x3712 PR_ATTACH_CONTENT_ID */ pst_string content_id; /** mapi element 0x3701 PR_ATTACH_DATA_OBJ */ pst_binary data; /** only used if the attachment is by reference, in which case this is the id2 reference */ uint64_t id2_val; /** calculated from id2_val during creation of record */ uint64_t i_id; /** id2 tree needed to resolve attachments by reference */ pst_id2_tree *id2_head; /** mapi element 0x3705 PR_ATTACH_METHOD * @li 0 no attachment * @li 1 attach by value * @li 2 attach by reference * @li 3 attach by reference resolve * @li 4 attach by reference only * @li 5 embedded message * @li 6 OLE */ int32_t method; /** mapi element 0x370b PR_RENDERING_POSITION */ int32_t position; /** mapi element 0x3710 PR_ATTACH_MIME_SEQUENCE */ int32_t sequence; struct pst_item_attach *next; } pst_item_attach; /** linked list of extra header fields */ typedef struct pst_item_extra_field { char *field_name; char *value; struct pst_item_extra_field *next; } pst_item_extra_field; /** This contains the journal related mapi elements */ typedef struct pst_item_journal { /** mapi element 0x8706 */ FILETIME *start; /** mapi element 0x8708 */ FILETIME *end; /** mapi element 0x8700 */ pst_string type; /** mapi element 0x8712 */ pst_string description; } pst_item_journal; /** This contains the recurrence data separated into fields. http://www.geocities.com/cainrandom/dev/MAPIRecurrence.html */ typedef struct pst_recurrence { /** 0x30043004 */ uint32_t signature; /** @li 0 daily * @li 1 weekly * @li 2 monthly * @li 3 yearly */ uint32_t type; /** implies number of recurrence parameters * @li 0 has 3 parameters * @li 1 has 4 parameters * @li 2 has 4 parameters * @li 3 has 5 parameters */ uint32_t sub_type; /** must be contiguous, not an array to make python interface easier */ uint32_t parm1; uint32_t parm2; uint32_t parm3; uint32_t parm4; uint32_t parm5; /** type of termination of the recurrence @li 0 terminates on a date @li 1 terminates based on integer number of occurrences @li 2 never terminates */ uint32_t termination; /** recurrence interval in terms of the recurrence type */ uint32_t interval; /** bit mask of days of the week */ uint32_t bydaymask; /** day of month for monthly and yearly recurrences */ uint32_t dayofmonth; /** month of year for yearly recurrences */ uint32_t monthofyear; /** occurence of day for 2nd Tuesday of month, in which case position is 2 */ uint32_t position; /** number of occurrences, even if recurrence terminates based on date */ uint32_t count; // there is more data, including the termination date, // but we can get that from other mapi elements. } pst_recurrence; /** This contains the appointment related mapi elements */ typedef struct pst_item_appointment { /** mapi element 0x820d PR_OUTLOOK_EVENT_START_DATE */ FILETIME *start; /** mapi element 0x820e PR_OUTLOOK_EVENT_START_END */ FILETIME *end; /** mapi element 0x8208 PR_OUTLOOK_EVENT_LOCATION */ pst_string location; /** mapi element 0x8503 PR_OUTLOOK_COMMON_REMINDER_SET * @li 1 true * @li 0 false */ int alarm; /** mapi element 0x8560 */ FILETIME *reminder; /** mapi element 0x8501 PR_OUTLOOK_COMMON_REMINDER_MINUTES_BEFORE */ int32_t alarm_minutes; /** mapi element 0x851f */ pst_string alarm_filename; /** mapi element 0x8234 */ pst_string timezonestring; /** mapi element 0x8205 PR_OUTLOOK_EVENT_SHOW_TIME_AS * @li 0 free * @li 1 tentative * @li 2 busy * @li 3 out of office*/ int32_t showas; /** mapi element 0x8214 * @li 0 None * @li 1 Important * @li 2 Business * @li 3 Personal * @li 4 Vacation * @li 5 Must Attend * @li 6 Travel Required * @li 7 Needs Preparation * @li 8 Birthday * @li 9 Anniversary * @li 10 Phone Call */ int32_t label; /** mapi element 0x8215 PR_OUTLOOK_EVENT_ALL_DAY * @li 1 true * @li 0 false */ int all_day; /** mapi element 0x8223 PR_OUTLOOK_EVENT_IS_RECURRING * @li 1 true * @li 0 false */ int is_recurring; /** mapi element 0x8231 * @li 0 none * @li 1 daily * @li 2 weekly * @li 3 monthly * @li 4 yearly */ int32_t recurrence_type; /** mapi element 0x8232 recurrence description */ pst_string recurrence_description; /** mapi element 0x8216 recurrence data */ pst_binary recurrence_data; /** mapi element 0x8235 PR_OUTLOOK_EVENT_RECURRENCE_START */ FILETIME *recurrence_start; /** mapi element 0x8236 PR_OUTLOOK_EVENT_RECURRENCE_END */ FILETIME *recurrence_end; } pst_item_appointment; /** This contains the common mapi elements, and pointers to structures for * each major mapi item type. It represents a complete mapi object. */ typedef struct pst_item { /** pointer to the pst_file */ struct pst_file *pf; /** block id that can be used to generate uid */ uint64_t block_id; /** email mapi elements */ pst_item_email *email; /** folder mapi elements */ pst_item_folder *folder; /** contact mapi elements */ pst_item_contact *contact; /** linked list of attachments */ pst_item_attach *attach; /** message store mapi elements */ pst_item_message_store *message_store; /** linked list of extra headers and such */ pst_item_extra_field *extra_fields; /** journal mapi elements */ pst_item_journal *journal; /** calendar mapi elements */ pst_item_appointment *appointment; /** derived from mapi elements 0x001a PR_MESSAGE_CLASS or 0x3613 PR_CONTAINER_CLASS * @li 1 PST_TYPE_NOTE * @li 2 PST_TYPE_SCHEDULE * @li 8 PST_TYPE_APPOINTMENT * @li 9 PST_TYPE_CONTACT * @li 10 PST_TYPE_JOURNAL * @li 11 PST_TYPE_STICKYNOTE * @li 12 PST_TYPE_TASK * @li 13 PST_TYPE_OTHER * @li 14 PST_TYPE_REPORT */ int type; /** mapi element 0x001a PR_MESSAGE_CLASS or 0x3613 PR_CONTAINER_CLASS */ char *ascii_type; /** mapi element 0x0e07 PR_MESSAGE_FLAGS * @li 0x01 Read * @li 0x02 Unmodified * @li 0x04 Submit * @li 0x08 Unsent * @li 0x10 Has Attachments * @li 0x20 From Me * @li 0x40 Associated * @li 0x80 Resend * @li 0x100 RN Pending * @li 0x200 NRN Pending */ int32_t flags; /** mapi element 0x3001 PR_DISPLAY_NAME */ pst_string file_as; /** mapi element 0x3004 PR_COMMENT */ pst_string comment; /** derived from extra_fields["content-type"] if it contains a charset= subfield */ pst_string body_charset; /** mapi element 0x1000 PR_BODY */ pst_string body; /** mapi element 0x0037 PR_SUBJECT */ pst_string subject; /** mapi element 0x3fde PR_INTERNET_CPID */ int32_t internet_cpid; /** mapi element 0x3ffd PR_MESSAGE_CODEPAGE */ int32_t message_codepage; /** mapi element 0x0e08 PR_MESSAGE_SIZE */ int32_t message_size; /** mapi element 0x8554 PR_OUTLOOK_VERSION */ pst_string outlook_version; /** mapi element 0x0ff9 PR_RECORD_KEY */ pst_binary record_key; /** mapi element 0x65e3 PR_PREDECESSOR_CHANGE_LIST */ pst_binary predecessor_change; /** mapi element 0x0063 PR_RESPONSE_REQUESTED * @li 1 true * @li 0 false */ int response_requested; /** mapi element 0x3007 PR_CREATION_TIME */ FILETIME *create_date; /** mapi element 0x3008 PR_LAST_MODIFICATION_TIME */ FILETIME *modify_date; /** mapi element 0x002b PR_RECIPIENT_REASSIGNMENT_PROHIBITED * @li 1 true * @li 0 false */ int private_member; } pst_item; /** Linked list of extended attributes. * This is used to convert mapi_id values in the pst file into * cannonical mapi_id values to be used in this code. This list * is kept in sorted order, where the key is the 'map' field. * Some mapi_id values are converted to cannonical mapi_id values * (PST_MAP_ATTRIB), and others are converted to a string * (PST_ATTRIB_HEADER). */ typedef struct pst_x_attrib_ll { /** @li 1 PST_MAP_ATTRIB map->int attribute @li 2 PST_MAP_HEADER map->string header */ uint32_t mytype; /** key for the mapping */ uint32_t map; /** data target of the mapping, either uint32_t or string */ void *data; /** link to next item in the list */ struct pst_x_attrib_ll *next; } pst_x_attrib_ll; /** this is only used for internal debugging */ typedef struct pst_block_recorder { struct pst_block_recorder *next; int64_t offset; size_t size; int readcount; } pst_block_recorder; typedef struct pst_file { /** file pointer to opened PST file */ FILE* fp; /** original cwd when the file was opened */ char* cwd; /** original file name when the file was opened */ char* fname; /** default character set for items without one */ const char* charset; /** the array of index structures */ pst_index_ll *i_table; size_t i_count, i_capacity; /** the head and tail of the top level of the descriptor tree */ pst_desc_tree *d_head, *d_tail; /** the head of the extended attributes linked list */ pst_x_attrib_ll *x_head; /** the head of the block recorder, a debug artifact * used to detect cases where we might read the same * block multiple times while processing a pst file. */ pst_block_recorder *block_head; /** @li 0 is 32-bit pst file, pre Outlook 2003; * @li 1 is 64-bit pst file, Outlook 2003 or later */ int do_read64; /** file offset of the first b-tree node in the index tree */ uint64_t index1; /** back pointer value in the first b-tree node in the index tree */ uint64_t index1_back; /** file offset of the first b-tree node in the descriptor tree*/ uint64_t index2; /** back pointer value in the first b-tree node in the descriptor tree */ uint64_t index2_back; /** size of the pst file */ uint64_t size; /** @li 0 PST_NO_ENCRYPT, none * @li 1 PST_COMP_ENCRYPT, simple byte substitution cipher with fixed key * @li 2 PST_ENCRYPT, german enigma 3 rotor cipher with fixed key */ unsigned char encryption; /** index type or file type * @li 0x0e 32 bit pre Outlook 2003 * @li 0x0f 32 bit pre Outlook 2003 * @li 0x15 64 bit Outlook 2003 or later * @li 0x17 64 bit Outlook 2003 or later */ unsigned char ind_type; } pst_file; /** Open a pst file. * @param pf pointer to uninitialized pst_file structure. This structure * will be filled in by this function. * @param name name of the file, suitable for fopen(). * @param charset default charset for item with unspecified character sets * @return 0 if ok, -1 if error */ int pst_open(pst_file *pf, const char *name, const char *charset); /** Reopen the pst file after a fork * @param pf pointer to the pst_file structure setup by pst_open(). * @return 0 if ok, -1 if error */ int pst_reopen(pst_file *pf); /** Load the index entries from the pst file. This loads both the * i_id linked list, and the d_id tree, and should normally be the * first call after pst_open(). * @param pf pointer to the pst_file structure setup by pst_open(). */ int pst_load_index (pst_file *pf); /** Load the extended attribute mapping table from the pst file. This * should normally be the second call after pst_open(). * @param pf pointer to the pst_file structure setup by pst_open(). */ int pst_load_extended_attributes(pst_file *pf); /** Close a pst file. * @param pf pointer to the pst_file structure setup by pst_open(). */ int pst_close(pst_file *pf); /** Get the top of folders descriptor tree. This is the main descriptor tree * that needs to be walked to look at every item in the pst file. * @param pf pointer to the pst_file structure setup by pst_open(). * @param root root item, which can be obtained by pst_parse_item(pf, pf->d_head, NULL). */ pst_desc_tree* pst_getTopOfFolders(pst_file *pf, const pst_item *root); /** Assemble the binary attachment into a single buffer. * @param pf pointer to the pst_file structure setup by pst_open(). * @param attach pointer to the attachment record * @return structure containing size of and pointer to the buffer. * the caller must free this buffer. */ pst_binary pst_attach_to_mem(pst_file *pf, pst_item_attach *attach); /** Write a binary attachment to a file. * @param pf pointer to the pst_file structure setup by pst_open(). * @param attach pointer to the attachment record * @param fp pointer to an open FILE. */ size_t pst_attach_to_file(pst_file *pf, pst_item_attach *attach, FILE* fp); /** Write a binary attachment base64 encoded to a file. * @param pf pointer to the pst_file structure setup by pst_open(). * @param attach pointer to the attachment record * @param fp pointer to an open FILE. */ size_t pst_attach_to_file_base64(pst_file *pf, pst_item_attach *attach, FILE* fp); /** Walk the descriptor tree. * @param d pointer to the current item in the descriptor tree. * @return pointer to the next item in the descriptor tree. */ pst_desc_tree* pst_getNextDptr(pst_desc_tree* d); /** Assemble a mapi object from a descriptor pointer. * @param pf pointer to the pst_file structure setup by pst_open(). * @param d_ptr pointer to an item in the descriptor tree. * @param m_head normally NULL. This is only used when processing embedded * attached rfc822 messages, in which case it is attach->id2_head. * @return pointer to the mapi object. Must be free'd by pst_freeItem(). */ pst_item* pst_parse_item (pst_file *pf, pst_desc_tree *d_ptr, pst_id2_tree *m_head); /** Free the item returned by pst_parse_item(). * @param item pointer to item returned from pst_parse_item(). */ void pst_freeItem(pst_item *item); /** Lookup the i_id in the index linked list, and return a pointer to the element. * @param pf pointer to the pst_file structure setup by pst_open(). * @param i_id key for the index linked list * @return pointer to the element, or NULL if not found. */ pst_index_ll* pst_getID(pst_file* pf, uint64_t i_id); /** Get an ID block from the file using pst_ff_getIDblock() and decrypt if necessary. * @param pf pointer to the pst_file structure setup by pst_open(). * @param i_id ID of block to retrieve * @param buf reference to pointer to buffer that will contain the data block. * If this pointer is non-NULL, it will first be free()d. * @return Size of block read into memory */ size_t pst_ff_getIDblock_dec(pst_file *pf, uint64_t i_id, char **buf); /** compare strings case-insensitive. * @return -1 if a < b, 0 if a==b, 1 if a > b */ int pst_stricmp(char *a, char *b); /** fwrite with checking for null pointer. * @param ptr pointer to the buffer * @param size size of each item * @param nmemb number of items * @param stream output file * @return number of bytes written, zero if ptr==NULL */ size_t pst_fwrite(const void* ptr, size_t size, size_t nmemb, FILE* stream); /** Add any necessary escape characters for rfc2426 vcard format * @param[in] str pointer to input string * @param[in,out] result pointer to a char* pointer that may be realloc'ed if needed * @param[in,out] resultlen size of the result buffer * @return pointer to output string, either the input pointer if * there are no characters that need escapes, or a pointer * to a possibly realloc'ed result buffer. */ char* pst_rfc2426_escape(char* str, char** result, size_t* resultlen); /** Convert a FILETIME into rfc2425 date/time format 1953-10-15T23:10:00Z * which is the same as one of the forms in the ISO3601 standard * @param[in] ft time to be converted * @param[in] buflen length of the output buffer * @param[out] result pointer to output buffer, must be at least 30 bytes * @return time in rfc2425 format */ char* pst_rfc2425_datetime_format(const FILETIME* ft, int buflen, char* result); /** Convert a FILETIME into rfc2445 date/time format 19531015T231000Z * @param[in] ft time to be converted * @param[in] buflen length of the output buffer * @param[out] result pointer to output buffer, must be at least 30 bytes * @return time in rfc2445 format */ char* pst_rfc2445_datetime_format(const FILETIME* ft, int buflen, char* result); /** Convert the current time rfc2445 date/time format 19531015T231000Z * @param[in] buflen length of the output buffer * @param[out] result pointer to output buffer, must be at least 30 bytes * @return time in rfc2445 format */ char* pst_rfc2445_datetime_format_now(int buflen, char* result); /** Get the default character set for this item. This is used to find * the charset for pst_string elements that are not already in utf8 encoding. * @param item pointer to the mapi item of interest * @param[in] buflen length of the output buffer * @param[out] result pointer to output buffer, must be at least 30 bytes * @return default character set as a string useable by iconv() */ const char* pst_default_charset(pst_item *item, int buflen, char* result); /** Convert str to rfc2231 encoding of str * @param str pointer to the mapi string of interest */ void pst_rfc2231(pst_string *str); /** Convert str to rfc2047 encoding of str, possibly enclosed in quotes if it contains spaces * @param item pointer to the containing mapi item * @param str pointer to the mapi string of interest * @param needs_quote true if strings containing spaces should be wrapped in quotes */ void pst_rfc2047(pst_item *item, pst_string *str, int needs_quote); /** Convert str to utf8 if possible; null strings are preserved. * @param item pointer to the containing mapi item * @param str pointer to the mapi string of interest */ void pst_convert_utf8_null(pst_item *item, pst_string *str); /** Convert str to utf8 if possible; null strings are converted into empty strings. * @param item pointer to the containing mapi item * @param str pointer to the mapi string of interest */ void pst_convert_utf8(pst_item *item, pst_string *str); /** Decode raw recurrence data into a better structure. * @param appt pointer to appointment structure * @return pointer to decoded recurrence structure that must be free'd by the caller. */ pst_recurrence* pst_convert_recurrence(pst_item_appointment* appt); /** Free a recurrence structure. * @param r input pointer to be freed */ void pst_free_recurrence(pst_recurrence* r); // switch from maximal packing back to default packing // undo the packing from the beginning of this file #ifdef _MSC_VER #pragma pack(pop) #endif #if defined(__GNUC__) || defined (__SUNPRO_C) || defined(__SUNPRO_CC) #pragma pack() #endif #endif diff --git a/src/readpst.c b/src/readpst.c index 2543496..51ee498 100644 --- a/src/readpst.c +++ b/src/readpst.c @@ -1,2278 +1,2289 @@ /*** * readpst.c * Part of the LibPST project * Written by David Smith * dave.s@earthcorp.com */ #include "define.h" #include "lzfu.h" #include "msg.h" #define OUTPUT_TEMPLATE "%s" #define OUTPUT_KMAIL_DIR_TEMPLATE ".%s.directory" #define KMAIL_INDEX ".%s.index" #define SEP_MAIL_FILE_TEMPLATE "%i%s" // max size of the c_time char*. It will store the date of the email #define C_TIME_SIZE 500 struct file_ll { - char *name; + char *name[PST_TYPE_MAX]; char *dname; - FILE * output; + FILE * output[PST_TYPE_MAX]; int32_t stored_count; int32_t item_count; int32_t skip_count; - int32_t type; }; int grim_reaper(); pid_t try_fork(char* folder); void process(pst_item *outeritem, pst_desc_tree *d_ptr); void write_email_body(FILE *f, char *body); void removeCR(char *c); void usage(); void version(); char* mk_kmail_dir(char* fname); int close_kmail_dir(); -char* mk_recurse_dir(char* dir, int32_t folder_type); +void mk_recurse_dir(char* dir); int close_recurse_dir(); -char* mk_separate_dir(char *dir); +void mk_separate_dir(char *dir); int close_separate_dir(); -void mk_separate_file(struct file_ll *f, char *extension, int openit); +void mk_separate_file(struct file_ll *f, int32_t t, char *extension, int openit); void close_separate_file(struct file_ll *f); char* my_stristr(char *haystack, char *needle); void check_filename(char *fname); int acceptable_ext(pst_item_attach* attach); void write_separate_attachment(char f_name[], pst_item_attach* attach, int attach_num, pst_file* pst); void write_embedded_message(FILE* f_output, pst_item_attach* attach, char *boundary, pst_file* pf, int save_rtf, char** extra_mime_headers); void write_inline_attachment(FILE* f_output, pst_item_attach* attach, char *boundary, pst_file* pst); int valid_headers(char *header); void header_has_field(char *header, char *field, int *flag); void header_get_subfield(char *field, const char *subfield, char *body_subfield, size_t size_subfield); char* header_get_field(char *header, char *field); char* header_end_field(char *field); void header_strip_field(char *header, char *field); int test_base64(char *body, size_t len); void find_html_charset(char *html, char *charset, size_t charsetlen); void find_rfc822_headers(char** extra_mime_headers); void write_body_part(FILE* f_output, pst_string *body, char *mime, char *charset, char *boundary, pst_file* pst); void write_schedule_part_data(FILE* f_output, pst_item* item, const char* sender, const char* method); void write_schedule_part(FILE* f_output, pst_item* item, const char* sender, const char* boundary); void write_normal_email(FILE* f_output, char f_name[], pst_item* item, int mode, int mode_MH, pst_file* pst, int save_rtf, int embedding, char** extra_mime_headers); void write_vcard(FILE* f_output, pst_item *item, pst_item_contact* contact, char comment[]); int write_extra_categories(FILE* f_output, pst_item* item); void write_journal(FILE* f_output, pst_item* item); void write_appointment(FILE* f_output, pst_item *item); void create_enter_dir(struct file_ll* f, pst_item *item); void close_enter_dir(struct file_ll *f); const char* prog_name; char* output_dir = "."; char* kmail_chdir = NULL; // Normal mode just creates mbox format files in the current directory. Each file is named // the same as the folder's name that it represents #define MODE_NORMAL 0 // KMail mode creates a directory structure suitable for being used directly // by the KMail application #define MODE_KMAIL 1 // recurse mode creates a directory structure like the PST file. Each directory // contains only one file which stores the emails in mboxrd format. #define MODE_RECURSE 2 // separate mode creates the same directory structure as recurse. The emails are stored in // separate files, numbering from 1 upward. Attachments belonging to the emails are // saved as email_no-filename (e.g. 1-samplefile.doc or 1-Attachment2.zip) #define MODE_SEPARATE 3 // Output Normal just prints the standard information about what is going on #define OUTPUT_NORMAL 0 // Output Quiet is provided so that only errors are printed #define OUTPUT_QUIET 1 // default mime-type for attachments that have a null mime-type #define MIME_TYPE_DEFAULT "application/octet-stream" #define RFC822 "message/rfc822" // output mode for contacts #define CMODE_VCARD 0 #define CMODE_LIST 1 // output mode for deleted items #define DMODE_EXCLUDE 0 #define DMODE_INCLUDE 1 // Output type mode flags #define OTMODE_EMAIL 1 #define OTMODE_APPOINTMENT 2 #define OTMODE_JOURNAL 4 #define OTMODE_CONTACT 8 // output settings for RTF bodies // filename for the attachment #define RTF_ATTACH_NAME "rtf-body.rtf" // mime type for the attachment #define RTF_ATTACH_TYPE "application/rtf" // global settings int mode = MODE_NORMAL; int mode_MH = 0; // a submode of MODE_SEPARATE int mode_EX = 0; // a submode of MODE_SEPARATE int mode_MSG = 0; // a submode of MODE_SEPARATE int mode_thunder = 0; // a submode of MODE_RECURSE int output_mode = OUTPUT_NORMAL; int contact_mode = CMODE_VCARD; int deleted_mode = DMODE_EXCLUDE; int output_type_mode = 0xff; // Default to all. int contact_mode_specified = 0; int overwrite = 0; int prefer_utf8 = 0; int save_rtf_body = 1; int file_name_len = 10; // enough room for MODE_SPEARATE file name pst_file pstfile; regex_t meta_charset_pattern; char* default_charset = NULL; char* acceptable_extensions = NULL; int number_processors = 1; // number of cpus we have int max_children = 0; // based on number of cpus and command line args int max_child_specified = 0;// have command line arg -j int active_children; // number of children of this process, cannot be larger than max_children pid_t* child_processes; // setup by main(), and at the start of new child process #ifdef HAVE_SEMAPHORE_H int shared_memory_id; sem_t* global_children = NULL; sem_t* output_mutex = NULL; #endif int grim_reaper(int waitall) { int available = 0; #ifdef HAVE_FORK #ifdef HAVE_SEMAPHORE_H if (global_children) { //sem_getvalue(global_children, &available); //printf("grim reaper %s for pid %d (parent %d) with %d children, %d available\n", (waitall) ? "all" : "", getpid(), getppid(), active_children, available); //fflush(stdout); int i,j; for (i=0; i 0 but active_children == max_children if (available && active_children < max_children) { sem_wait(global_children); pid_t child = fork(); if (child < 0) { // fork failed, pretend it worked and we are the child return 0; } else if (child == 0) { // fork worked, and we are the child, reinitialize *our* list of children active_children = 0; memset(child_processes, 0, sizeof(pid_t) * max_children); pst_reopen(&pstfile); // close and reopen the pst file to get an independent file position pointer } else { // fork worked, and we are the parent, record this child that we need to wait for //pid_t me = getpid(); //printf("parent %d forked child pid %d to process folder %s\n", me, child, folder); //fflush(stdout); child_processes[active_children++] = child; } return child; } else { return 0; // pretend to have forked and we are the child } #endif #endif return 0; } void process(pst_item *outeritem, pst_desc_tree *d_ptr) { struct file_ll ff; pst_item *item = NULL; DEBUG_ENT("process"); - memset(&ff, 0, sizeof(ff)); create_enter_dir(&ff, outeritem); for (; d_ptr; d_ptr = d_ptr->next) { DEBUG_INFO(("New item record\n")); if (!d_ptr->desc) { ff.skip_count++; DEBUG_WARN(("ERROR item's desc record is NULL\n")); continue; } DEBUG_INFO(("Desc Email ID %#"PRIx64" [d_ptr->d_id = %#"PRIx64"]\n", d_ptr->desc->i_id, d_ptr->d_id)); item = pst_parse_item(&pstfile, d_ptr, NULL); DEBUG_INFO(("About to process item\n")); if (!item) { ff.skip_count++; DEBUG_INFO(("A NULL item was seen\n")); continue; } if (item->subject.str) { DEBUG_INFO(("item->subject = %s\n", item->subject.str)); } if (item->folder && item->file_as.str) { DEBUG_INFO(("Processing Folder \"%s\"\n", item->file_as.str)); if (output_mode != OUTPUT_QUIET) { pst_debug_lock(); printf("Processing Folder \"%s\"\n", item->file_as.str); fflush(stdout); pst_debug_unlock(); } ff.item_count++; if (d_ptr->child && (deleted_mode == DMODE_INCLUDE || strcasecmp(item->file_as.str, "Deleted Items"))) { //if this is a non-empty folder other than deleted items, we want to recurse into it pid_t parent = getpid(); pid_t child = try_fork(item->file_as.str); if (child == 0) { // we are the child process, or the original parent if no children were available pid_t me = getpid(); process(item, d_ptr->child); #ifdef HAVE_FORK #ifdef HAVE_SEMAPHORE_H if (me != parent) { // we really were a child, forked for the sole purpose of processing this folder // free my child count slot before really exiting, since // all I am doing here is waiting for my children to exit sem_post(global_children); grim_reaper(1); // wait for all my child processes to exit exit(0); // really exit } #endif #endif } } } else if (item->contact && (item->type == PST_TYPE_CONTACT)) { DEBUG_INFO(("Processing Contact\n")); if (!(output_type_mode & OTMODE_CONTACT)) { ff.skip_count++; DEBUG_INFO(("skipping contact: not in output type list\n")); } else { - if (!ff.type) ff.type = item->type; - if ((ff.type != PST_TYPE_CONTACT) && (mode != MODE_SEPARATE)) { - ff.skip_count++; - DEBUG_INFO(("I have a contact, but the folder type %"PRIi32" isn't a contacts folder. Skipping it\n", ff.type)); + ff.item_count++; + if (mode == MODE_SEPARATE) mk_separate_file(&ff, PST_TYPE_CONTACT, (mode_EX) ? ".vcf" : "", 1); + if (contact_mode == CMODE_VCARD) { + pst_convert_utf8_null(item, &item->comment); + write_vcard(ff.output[PST_TYPE_CONTACT], item, item->contact, item->comment.str); } else { - ff.item_count++; - if (mode == MODE_SEPARATE) mk_separate_file(&ff, (mode_EX) ? ".vcf" : "", 1); - if (contact_mode == CMODE_VCARD) { - pst_convert_utf8_null(item, &item->comment); - write_vcard(ff.output, item, item->contact, item->comment.str); - } - else { - pst_convert_utf8(item, &item->contact->fullname); - pst_convert_utf8(item, &item->contact->address1); - fprintf(ff.output, "%s <%s>\n", item->contact->fullname.str, item->contact->address1.str); - } - if (mode == MODE_SEPARATE) close_separate_file(&ff); + pst_convert_utf8(item, &item->contact->fullname); + pst_convert_utf8(item, &item->contact->address1); + fprintf(ff.output[PST_TYPE_CONTACT], "%s <%s>\n", item->contact->fullname.str, item->contact->address1.str); } + if (mode == MODE_SEPARATE) close_separate_file(&ff); } } else if (item->email && ((item->type == PST_TYPE_NOTE) || (item->type == PST_TYPE_SCHEDULE) || (item->type == PST_TYPE_REPORT))) { DEBUG_INFO(("Processing Email\n")); if (!(output_type_mode & OTMODE_EMAIL)) { ff.skip_count++; DEBUG_INFO(("skipping email: not in output type list\n")); } else { - if (!ff.type) ff.type = item->type; - if ((ff.type != PST_TYPE_NOTE) && (ff.type != PST_TYPE_SCHEDULE) && (ff.type != PST_TYPE_REPORT) && (mode != MODE_SEPARATE)) { - ff.skip_count++; - DEBUG_INFO(("I have an email type %"PRIi32", but the folder type %"PRIi32" isn't an email folder. Skipping it\n", item->type, ff.type)); - } - else { - char *extra_mime_headers = NULL; - ff.item_count++; - if (mode == MODE_SEPARATE) { - // process this single email message, possibly forking - pid_t parent = getpid(); - pid_t child = try_fork(item->file_as.str); - if (child == 0) { - // we are the child process, or the original parent if no children were available - pid_t me = getpid(); - mk_separate_file(&ff, (mode_EX) ? ".eml" : "", 1); - write_normal_email(ff.output, ff.name, item, mode, mode_MH, &pstfile, save_rtf_body, 0, &extra_mime_headers); - close_separate_file(&ff); - if (mode_MSG) { - mk_separate_file(&ff, ".msg", 0); - write_msg_email(ff.name, item, &pstfile); - } + char *extra_mime_headers = NULL; + ff.item_count++; + if (mode == MODE_SEPARATE) { + // process this single email message, possibly forking + pid_t parent = getpid(); + pid_t child = try_fork(item->file_as.str); + if (child == 0) { + // we are the child process, or the original parent if no children were available + pid_t me = getpid(); + mk_separate_file(&ff, PST_TYPE_NOTE, (mode_EX) ? ".eml" : "", 1); + write_normal_email(ff.output[PST_TYPE_NOTE], ff.name[PST_TYPE_NOTE], item, mode, mode_MH, &pstfile, save_rtf_body, PST_TYPE_NOTE, &extra_mime_headers); + close_separate_file(&ff); + if (mode_MSG) { + mk_separate_file(&ff, PST_TYPE_NOTE, ".msg", 0); + write_msg_email(ff.name[PST_TYPE_NOTE], item, &pstfile); + } #ifdef HAVE_FORK #ifdef HAVE_SEMAPHORE_H - if (me != parent) { - // we really were a child, forked for the sole purpose of processing this message - // free my child count slot before really exiting, since - // all I am doing here is waiting for my children to exit - sem_post(global_children); - grim_reaper(1); // wait for all my child processes to exit - there should not be any - exit(0); // really exit - } + if (me != parent) { + // we really were a child, forked for the sole purpose of processing this message + // free my child count slot before really exiting, since + // all I am doing here is waiting for my children to exit + sem_post(global_children); + grim_reaper(1); // wait for all my child processes to exit - there should not be any + exit(0); // really exit + } #endif #endif - } - } - else { - // process this single email message, cannot fork since not separate mode - write_normal_email(ff.output, ff.name, item, mode, mode_MH, &pstfile, save_rtf_body, 0, &extra_mime_headers); } } + else { + // process this single email message, cannot fork since not separate mode + write_normal_email(ff.output[PST_TYPE_NOTE], ff.name[PST_TYPE_NOTE], item, mode, mode_MH, &pstfile, save_rtf_body, 0, &extra_mime_headers); + } } } else if (item->journal && (item->type == PST_TYPE_JOURNAL)) { DEBUG_INFO(("Processing Journal Entry\n")); if (!(output_type_mode & OTMODE_JOURNAL)) { ff.skip_count++; DEBUG_INFO(("skipping journal entry: not in output type list\n")); } else { - if (!ff.type) ff.type = item->type; - if ((ff.type != PST_TYPE_JOURNAL) && (mode != MODE_SEPARATE)) { - ff.skip_count++; - DEBUG_INFO(("I have a journal entry, but the folder type %"PRIi32" isn't a journal folder. Skipping it\n", ff.type)); - } - else { - ff.item_count++; - if (mode == MODE_SEPARATE) mk_separate_file(&ff, (mode_EX) ? ".ics" : "", 1); - write_journal(ff.output, item); - fprintf(ff.output, "\n"); - if (mode == MODE_SEPARATE) close_separate_file(&ff); - } + ff.item_count++; + if (mode == MODE_SEPARATE) mk_separate_file(&ff, PST_TYPE_JOURNAL, (mode_EX) ? ".ics" : "", 1); + write_journal(ff.output[PST_TYPE_JOURNAL], item); + fprintf(ff.output[PST_TYPE_JOURNAL], "\n"); + if (mode == MODE_SEPARATE) close_separate_file(&ff); } } else if (item->appointment && (item->type == PST_TYPE_APPOINTMENT)) { DEBUG_INFO(("Processing Appointment Entry\n")); if (!(output_type_mode & OTMODE_APPOINTMENT)) { ff.skip_count++; DEBUG_INFO(("skipping appointment: not in output type list\n")); } else { - if (!ff.type) ff.type = item->type; - if ((ff.type != PST_TYPE_APPOINTMENT) && (mode != MODE_SEPARATE)) { - ff.skip_count++; - DEBUG_INFO(("I have an appointment, but the folder type %"PRIi32" isn't an appointment folder. Skipping it\n", ff.type)); - } - else { - ff.item_count++; - if (mode == MODE_SEPARATE) mk_separate_file(&ff, (mode_EX) ? ".ics" : "", 1); - write_schedule_part_data(ff.output, item, NULL, NULL); - fprintf(ff.output, "\n"); - if (mode == MODE_SEPARATE) close_separate_file(&ff); - } + ff.item_count++; + if (mode == MODE_SEPARATE) mk_separate_file(&ff, PST_TYPE_APPOINTMENT, (mode_EX) ? ".ics" : "", 1); + write_schedule_part_data(ff.output[PST_TYPE_APPOINTMENT], item, NULL, NULL); + fprintf(ff.output[PST_TYPE_APPOINTMENT], "\n"); + if (mode == MODE_SEPARATE) close_separate_file(&ff); } } else if (item->message_store) { // there should only be one message_store, and we have already done it ff.skip_count++; - DEBUG_WARN(("item with message store content, type %i %s folder type %i, skipping it\n", item->type, item->ascii_type, ff.type)); + DEBUG_WARN(("item with message store content, type %i %s, skipping it\n", item->type, item->ascii_type)); } else { ff.skip_count++; DEBUG_WARN(("Unknown item type %i (%s) name (%s)\n", item->type, item->ascii_type, item->file_as.str)); } pst_freeItem(item); } close_enter_dir(&ff); DEBUG_RET(); } int main(int argc, char* const* argv) { pst_item *item = NULL; pst_desc_tree *d_ptr; char * fname = NULL; char *d_log = NULL; int c,x; char *temp = NULL; //temporary char pointer prog_name = argv[0]; time_t now = time(NULL); srand((unsigned)now); if (regcomp(&meta_charset_pattern, "]*content=\"[^>]*charset=([^>\";]*)[\";]", REG_ICASE | REG_EXTENDED)) { printf("cannot compile regex pattern to find content charset in html bodies\n"); exit(3); } // command-line option handling while ((c = getopt(argc, argv, "a:bC:c:Dd:emhj:kMo:qrSt:uVwL:8"))!= -1) { switch (c) { case 'a': if (optarg) { int n = strlen(optarg); acceptable_extensions = (char*)pst_malloc(n+2); strcpy(acceptable_extensions, optarg); acceptable_extensions[n+1] = '\0'; // double null terminates array of non-empty null terminated strings. char *p = acceptable_extensions; while (*p) { if (*p == ',') *p = '\0'; p++; } } break; case 'b': save_rtf_body = 0; break; case 'C': if (optarg) { default_charset = optarg; } else { usage(); exit(0); } break; case 'c': if (optarg && optarg[0]=='v') { contact_mode=CMODE_VCARD; contact_mode_specified = 1; } else if (optarg && optarg[0]=='l') { contact_mode=CMODE_LIST; contact_mode_specified = 1; } else { usage(); exit(0); } break; case 'D': deleted_mode = DMODE_INCLUDE; break; case 'd': d_log = optarg; break; case 'h': usage(); exit(0); break; case 'j': max_children = atoi(optarg); max_child_specified = 1; break; case 'k': mode = MODE_KMAIL; break; case 'M': mode = MODE_SEPARATE; mode_MH = 1; mode_EX = 0; mode_MSG = 0; break; case 'e': mode = MODE_SEPARATE; mode_MH = 1; mode_EX = 1; mode_MSG = 0; file_name_len = 14; break; case 'L': pst_debug_setlevel(atoi(optarg)); break; case 'm': mode = MODE_SEPARATE; mode_MH = 1; mode_EX = 1; mode_MSG = 1; file_name_len = 14; break; case 'o': output_dir = optarg; break; case 'q': output_mode = OUTPUT_QUIET; break; case 'r': mode = MODE_RECURSE; mode_thunder = 0; break; case 'S': mode = MODE_SEPARATE; mode_MH = 0; mode_EX = 0; mode_MSG = 0; break; case 't': // email, appointment, contact, other if (!optarg) { usage(); exit(0); } temp = optarg; output_type_mode = 0; while (*temp > 0) { switch (temp[0]) { case 'e': output_type_mode |= OTMODE_EMAIL; break; case 'a': output_type_mode |= OTMODE_APPOINTMENT; break; case 'j': output_type_mode |= OTMODE_JOURNAL; break; case 'c': output_type_mode |= OTMODE_CONTACT; break; default: usage(); exit(0); break; } temp++; } break; case 'u': mode = MODE_RECURSE; mode_thunder = 1; break; case 'V': version(); exit(0); break; case 'w': overwrite = 1; break; case '8': prefer_utf8 = 1; break; default: usage(); exit(1); break; } } if (argc > optind) { fname = argv[optind]; } else { usage(); exit(2); } #ifdef _SC_NPROCESSORS_ONLN number_processors = sysconf(_SC_NPROCESSORS_ONLN); #endif max_children = (max_child_specified) ? max_children : number_processors * 4; active_children = 0; child_processes = (pid_t *)pst_malloc(sizeof(pid_t) * max_children); memset(child_processes, 0, sizeof(pid_t) * max_children); #ifdef HAVE_SEMAPHORE_H if (max_children) { shared_memory_id = shmget(IPC_PRIVATE, sizeof(sem_t)*2, 0777); if (shared_memory_id >= 0) { global_children = (sem_t *)shmat(shared_memory_id, NULL, 0); if (global_children == (sem_t *)-1) global_children = NULL; if (global_children) { output_mutex = &(global_children[1]); sem_init(global_children, 1, max_children); sem_init(output_mutex, 1, 1); } shmctl(shared_memory_id, IPC_RMID, NULL); } } #endif #ifdef DEBUG_ALL // force a log file if (!d_log) d_log = "readpst.log"; #endif // defined DEBUG_ALL #ifdef HAVE_SEMAPHORE_H DEBUG_INIT(d_log, output_mutex); #else DEBUG_INIT(d_log, NULL); #endif DEBUG_ENT("main"); if (output_mode != OUTPUT_QUIET) printf("Opening PST file and indexes...\n"); RET_DERROR(pst_open(&pstfile, fname, default_charset), 1, ("Error opening File\n")); RET_DERROR(pst_load_index(&pstfile), 2, ("Index Error\n")); pst_load_extended_attributes(&pstfile); if (chdir(output_dir)) { x = errno; pst_close(&pstfile); DEBUG_RET(); DIE(("Cannot change to output dir %s: %s\n", output_dir, strerror(x))); } d_ptr = pstfile.d_head; // first record is main record item = pst_parse_item(&pstfile, d_ptr, NULL); if (!item || !item->message_store) { DEBUG_RET(); DIE(("Could not get root record\n")); } // default the file_as to the same as the main filename if it doesn't exist if (!item->file_as.str) { if (!(temp = strrchr(fname, '/'))) if (!(temp = strrchr(fname, '\\'))) temp = fname; else temp++; // get past the "\\" else temp++; // get past the "/" item->file_as.str = (char*)pst_malloc(strlen(temp)+1); strcpy(item->file_as.str, temp); item->file_as.is_utf8 = 1; DEBUG_INFO(("file_as was blank, so am using %s\n", item->file_as.str)); } DEBUG_INFO(("Root Folder Name: %s\n", item->file_as.str)); d_ptr = pst_getTopOfFolders(&pstfile, item); if (!d_ptr) { DEBUG_RET(); DIE(("Top of folders record not found. Cannot continue\n")); } process(item, d_ptr->child); // do the children of TOPF grim_reaper(1); // wait for all child processes pst_freeItem(item); pst_close(&pstfile); DEBUG_RET(); #ifdef HAVE_SEMAPHORE_H if (global_children) { sem_destroy(global_children); sem_destroy(output_mutex); shmdt(global_children); } #endif regfree(&meta_charset_pattern); return 0; } void write_email_body(FILE *f, char *body) { char *n = body; DEBUG_ENT("write_email_body"); if (mode != MODE_SEPARATE) { while (n) { char *p = body; while (*p == '>') p++; if (strncmp(p, "From ", 5) == 0) fprintf(f, ">"); if ((n = strchr(body, '\n'))) { n++; pst_fwrite(body, n-body, 1, f); //write just a line body = n; } } } pst_fwrite(body, strlen(body), 1, f); DEBUG_RET(); } void removeCR (char *c) { // converts \r\n to \n char *a, *b; DEBUG_ENT("removeCR"); a = b = c; while (*a != '\0') { *b = *a; if (*a != '\r') b++; a++; } *b = '\0'; DEBUG_RET(); } void usage() { DEBUG_ENT("usage"); version(); printf("Usage: %s [OPTIONS] {PST FILENAME}\n", prog_name); printf("OPTIONS:\n"); printf("\t-V\t- Version. Display program version\n"); printf("\t-C charset\t- character set for items with an unspecified character set\n"); printf("\t-D\t- Include deleted items in output\n"); printf("\t-L \t- Set debug level; 1=debug,2=info,3=warn.\n"); printf("\t-M\t- Write emails in the MH (rfc822) format\n"); printf("\t-S\t- Separate. Write emails in the separate format\n"); printf("\t-a \t- Discard any attachment without an extension on the list\n"); printf("\t-b\t- Don't save RTF-Body attachments\n"); printf("\t-c[v|l]\t- Set the Contact output mode. -cv = VCard, -cl = EMail list\n"); printf("\t-d \t- Debug to file.\n"); printf("\t-e\t- As with -M, but include extensions on output files\n"); printf("\t-h\t- Help. This screen\n"); printf("\t-j \t- Number of parallel jobs to run\n"); printf("\t-k\t- KMail. Output in kmail format\n"); printf("\t-m\t- As with -e, but write .msg files also\n"); printf("\t-o \t- Output directory to write files to. CWD is changed *after* opening pst file\n"); printf("\t-q\t- Quiet. Only print error messages\n"); printf("\t-r\t- Recursive. Output in a recursive format\n"); printf("\t-t[eajc]\t- Set the output type list. e = email, a = attachment, j = journal, c = contact\n"); printf("\t-u\t- Thunderbird mode. Write two extra .size and .type files\n"); printf("\t-w\t- Overwrite any output mbox files\n"); printf("\t-8\t- Output bodies in UTF-8, rather than original encoding, if UTF-8 version is available\n"); printf("\n"); printf("Only one of -M -S -e -k -m -r should be specified\n"); DEBUG_RET(); } void version() { DEBUG_ENT("version"); printf("ReadPST / LibPST v%s\n", VERSION); #if BYTE_ORDER == BIG_ENDIAN printf("Big Endian implementation being used.\n"); #elif BYTE_ORDER == LITTLE_ENDIAN printf("Little Endian implementation being used.\n"); #else # error "Byte order not supported by this library" #endif DEBUG_RET(); } char *mk_kmail_dir(char *fname) { //change to that directory //make a directory based on OUTPUT_KMAIL_DIR_TEMPLATE //allocate space for OUTPUT_TEMPLATE and form a char* with fname //return that value char *dir, *out_name, *index; int x; DEBUG_ENT("mk_kmail_dir"); if (kmail_chdir && chdir(kmail_chdir)) { x = errno; DIE(("mk_kmail_dir: Cannot change to directory %s: %s\n", kmail_chdir, strerror(x))); } dir = pst_malloc(strlen(fname)+strlen(OUTPUT_KMAIL_DIR_TEMPLATE)+1); sprintf(dir, OUTPUT_KMAIL_DIR_TEMPLATE, fname); check_filename(dir); if (D_MKDIR(dir)) { if (errno != EEXIST) { // not an error because it exists x = errno; DIE(("mk_kmail_dir: Cannot create directory %s: %s\n", dir, strerror(x))); } } kmail_chdir = pst_realloc(kmail_chdir, strlen(dir)+1); strcpy(kmail_chdir, dir); free (dir); //we should remove any existing indexes created by KMail, cause they might be different now index = pst_malloc(strlen(fname)+strlen(KMAIL_INDEX)+1); sprintf(index, KMAIL_INDEX, fname); unlink(index); free(index); out_name = pst_malloc(strlen(fname)+strlen(OUTPUT_TEMPLATE)+1); sprintf(out_name, OUTPUT_TEMPLATE, fname); DEBUG_RET(); return out_name; } int close_kmail_dir() { // change .. int x; DEBUG_ENT("close_kmail_dir"); if (kmail_chdir) { //only free kmail_chdir if not NULL. do not change directory free(kmail_chdir); kmail_chdir = NULL; } else { if (chdir("..")) { x = errno; DIE(("close_kmail_dir: Cannot move up dir (..): %s\n", strerror(x))); } } DEBUG_RET(); return 0; } -// this will create a directory by that name, -// then make an mbox file inside that directory. -char *mk_recurse_dir(char *dir, int32_t folder_type) { - int x; - char *out_name; - DEBUG_ENT("mk_recurse_dir"); - check_filename(dir); - if (D_MKDIR (dir)) { - if (errno != EEXIST) { // not an error because it exists - x = errno; - DIE(("mk_recurse_dir: Cannot create directory %s: %s\n", dir, strerror(x))); - } - } - if (chdir (dir)) { - x = errno; - DIE(("mk_recurse_dir: Cannot change to directory %s: %s\n", dir, strerror(x))); - } - switch (folder_type) { +char *item_type_to_name(int32_t item_type) { + char *name; + switch (item_type) { case PST_TYPE_APPOINTMENT: - out_name = strdup("calendar"); + name = "calendar"; break; case PST_TYPE_CONTACT: - out_name = strdup("contacts"); + name = "contacts"; + break; + case PST_TYPE_JOURNAL: + name = "journal"; break; + case PST_TYPE_STICKYNOTE: + case PST_TYPE_TASK: + case PST_TYPE_NOTE: + case PST_TYPE_OTHER: + case PST_TYPE_REPORT: + default: + name = "mbox"; + break; + } + return name; +} + + +int32_t reduced_item_type(int32_t item_type) { + int32_t reduced; + switch (item_type) { + case PST_TYPE_APPOINTMENT: + case PST_TYPE_CONTACT: case PST_TYPE_JOURNAL: - out_name = strdup("journal"); + reduced = item_type; break; case PST_TYPE_STICKYNOTE: case PST_TYPE_TASK: case PST_TYPE_NOTE: case PST_TYPE_OTHER: case PST_TYPE_REPORT: default: - out_name = strdup("mbox"); + reduced = PST_TYPE_NOTE; break; } + return reduced; +} + + +// this will create a directory by that name +void mk_recurse_dir(char *dir) { + int x; + DEBUG_ENT("mk_recurse_dir"); + check_filename(dir); + if (D_MKDIR (dir)) { + if (errno != EEXIST) { // not an error because it exists + x = errno; + DIE(("mk_recurse_dir: Cannot create directory %s: %s\n", dir, strerror(x))); + } + } + if (chdir (dir)) { + x = errno; + DIE(("mk_recurse_dir: Cannot change to directory %s: %s\n", dir, strerror(x))); + } DEBUG_RET(); - return out_name; } int close_recurse_dir() { int x; DEBUG_ENT("close_recurse_dir"); if (chdir("..")) { x = errno; DIE(("close_recurse_dir: Cannot go up dir (..): %s\n", strerror(x))); } DEBUG_RET(); return 0; } -char *mk_separate_dir(char *dir) { +void mk_separate_dir(char *dir) { size_t dirsize = strlen(dir) + 10; char dir_name[dirsize]; int x = 0, y = 0; DEBUG_ENT("mk_separate_dir"); do { if (y == 0) snprintf(dir_name, dirsize, "%s", dir); else snprintf(dir_name, dirsize, "%s" SEP_MAIL_FILE_TEMPLATE, dir, y, ""); // enough for 9 digits allocated above check_filename(dir_name); DEBUG_INFO(("about to try creating %s\n", dir_name)); if (D_MKDIR(dir_name)) { if (errno != EEXIST) { // if there is an error, and it doesn't already exist x = errno; DIE(("mk_separate_dir: Cannot create directory %s: %s\n", dir, strerror(x))); } } else { break; } y++; } while (overwrite == 0); if (chdir(dir_name)) { x = errno; DIE(("mk_separate_dir: Cannot change to directory %s: %s\n", dir, strerror(x))); } if (overwrite) { // we should probably delete all files from this directory #if !defined(WIN32) && !defined(__CYGWIN__) DIR * sdir = NULL; struct dirent *dirent = NULL; struct stat filestat; if (!(sdir = opendir("./"))) { DEBUG_WARN(("mk_separate_dir: Cannot open dir \"%s\" for deletion of old contents\n", "./")); } else { while ((dirent = readdir(sdir))) { if (lstat(dirent->d_name, &filestat) != -1) if (S_ISREG(filestat.st_mode)) { if (unlink(dirent->d_name)) { y = errno; DIE(("mk_separate_dir: unlink returned error on file %s: %s\n", dirent->d_name, strerror(y))); } } } closedir(sdir); // cppcheck detected leak } #endif } - // we don't return a filename here cause it isn't necessary. DEBUG_RET(); - return NULL; } int close_separate_dir() { int x; DEBUG_ENT("close_separate_dir"); if (chdir("..")) { x = errno; DIE(("close_separate_dir: Cannot go up dir (..): %s\n", strerror(x))); } DEBUG_RET(); return 0; } -void mk_separate_file(struct file_ll *f, char *extension, int openit) { +void mk_separate_file(struct file_ll *f, int32_t t, char *extension, int openit) { DEBUG_ENT("mk_separate_file"); DEBUG_INFO(("opening next file to save email\n")); if (f->item_count > 999999999) { // bigger than nine 9's DIE(("mk_separate_file: The number of emails in this folder has become too high to handle\n")); } - sprintf(f->name, SEP_MAIL_FILE_TEMPLATE, f->item_count, extension); - check_filename(f->name); + sprintf(f->name[t], SEP_MAIL_FILE_TEMPLATE, f->item_count, extension); + check_filename(f->name[t]); if (openit) { - if (!(f->output = fopen(f->name, "w"))) { - DIE(("mk_separate_file: Cannot open file to save email \"%s\"\n", f->name)); + if (!(f->output[t] = fopen(f->name[t], "w"))) { + DIE(("mk_separate_file: Cannot open file to save email \"%s\"\n", f->name[t])); } } DEBUG_RET(); } void close_separate_file(struct file_ll *f) { + int32_t t; DEBUG_ENT("close_separate_file"); - if (f->output) { - struct stat st; - fclose(f->output); - stat(f->name, &st); - if (!st.st_size) { - DEBUG_WARN(("removing empty output file %s\n", f->name)); - remove(f->name); + for (t=0; toutput[t]) { + struct stat st; + fclose(f->output[t]); + stat(f->name[t], &st); + if (!st.st_size) { + DEBUG_WARN(("removing empty output file %s\n", f->name[t])); + remove(f->name[t]); + } + f->output[t] = NULL; } - f->output = NULL; } DEBUG_RET(); } char *my_stristr(char *haystack, char *needle) { // my_stristr varies from strstr in that its searches are case-insensitive char *x=haystack, *y=needle, *z = NULL; if (!haystack || !needle) { return NULL; } while (*y != '\0' && *x != '\0') { if (tolower(*y) == tolower(*x)) { // move y on one y++; if (!z) { z = x; // store first position in haystack where a match is made } } else { y = needle; // reset y to the beginning of the needle z = NULL; // reset the haystack storage point } x++; // advance the search in the haystack } // If the haystack ended before our search finished, it's not a match. if (*y != '\0') return NULL; return z; } void check_filename(char *fname) { char *t = fname; DEBUG_ENT("check_filename"); if (!t) { DEBUG_RET(); return; } while ((t = strpbrk(t, "/\\:"))) { // while there are characters in the second string that we don't want *t = '_'; //replace them with an underscore } DEBUG_RET(); } /** * check if the file name extension is acceptable. If not, the attachment * will be discarded * @param attach pst attachment object * @return true if the attachment filename contains an extension that we want. */ int acceptable_ext(pst_item_attach* attach) { if (!acceptable_extensions || *acceptable_extensions == '\0') return 1; // acceptable list missing or empty char *attach_filename = (attach->filename2.str) ? attach->filename2.str : attach->filename1.str; if (!attach_filename) return 1; // attachment with no name is always acceptable char *e = strrchr(attach_filename, '.'); if (!e) return 1; // attachment with no extension is always acceptable. DEBUG_ENT("acceptable_ext"); DEBUG_INFO(("attachment extension %s\n", e)); int rc = 0; char *a = acceptable_extensions; while (*a) { if (pst_stricmp(a, e) == 0) { rc = 1; break; } a += strlen(a) + 1; } DEBUG_INFO(("attachment acceptable returns %d\n", rc)); DEBUG_RET(); return rc; } void write_separate_attachment(char f_name[], pst_item_attach* attach, int attach_num, pst_file* pst) { FILE *fp = NULL; int x = 0; char *temp = NULL; // If there is a long filename (filename2) use that, otherwise // use the 8.3 filename (filename1) char *attach_filename = (attach->filename2.str) ? attach->filename2.str : attach->filename1.str; DEBUG_ENT("write_separate_attachment"); DEBUG_INFO(("Attachment %s Size is %#"PRIx64", data = %#"PRIxPTR", id %#"PRIx64"\n", attach_filename, (uint64_t)attach->data.size, attach->data.data, attach->i_id)); if (!attach->data.data) { // make sure we can fetch data from the id pst_index_ll *ptr = pst_getID(pst, attach->i_id); if (!ptr) { DEBUG_WARN(("Couldn't find i_id %#"PRIx64". Cannot save attachment to file\n", attach->i_id)); DEBUG_RET(); return; } } check_filename(f_name); if (!attach_filename) { // generate our own (dummy) filename for the attachement temp = pst_malloc(strlen(f_name)+15); sprintf(temp, "%s-attach%i", f_name, attach_num); } else { // have an attachment name, make sure it's unique temp = pst_malloc(strlen(f_name)+strlen(attach_filename)+15); do { if (fp) fclose(fp); if (x == 0) sprintf(temp, "%s-%s", f_name, attach_filename); else sprintf(temp, "%s-%s-%i", f_name, attach_filename, x); } while ((fp = fopen(temp, "r")) && ++x < 99999999); if (x > 99999999) { DIE(("error finding attachment name. exhausted possibilities to %s\n", temp)); } } DEBUG_INFO(("Saving attachment to %s\n", temp)); if (!(fp = fopen(temp, "w"))) { DEBUG_WARN(("write_separate_attachment: Cannot open attachment save file \"%s\"\n", temp)); } else { (void)pst_attach_to_file(pst, attach, fp); fclose(fp); } if (temp) free(temp); DEBUG_RET(); } void write_embedded_message(FILE* f_output, pst_item_attach* attach, char *boundary, pst_file* pf, int save_rtf, char** extra_mime_headers) { pst_index_ll *ptr; DEBUG_ENT("write_embedded_message"); ptr = pst_getID(pf, attach->i_id); pst_desc_tree d_ptr; d_ptr.d_id = 0; d_ptr.parent_d_id = 0; d_ptr.assoc_tree = NULL; d_ptr.desc = ptr; d_ptr.no_child = 0; d_ptr.prev = NULL; d_ptr.next = NULL; d_ptr.parent = NULL; d_ptr.child = NULL; d_ptr.child_tail = NULL; pst_item *item = pst_parse_item(pf, &d_ptr, attach->id2_head); // It appears that if the embedded message contains an appointment/ // calendar item, pst_parse_item returns NULL due to the presence of // an unexpected reference type of 0x1048, which seems to represent // an array of GUIDs representing a CLSID. It's likely that this is // a reference to an internal Outlook COM class. // Log the skipped item and continue on. if (!item) { DEBUG_WARN(("write_embedded_message: pst_parse_item was unable to parse the embedded message in attachment ID %llu", attach->i_id)); } else { if (!item->email) { DEBUG_WARN(("write_embedded_message: pst_parse_item returned type %d, not an email message", item->type)); } else { fprintf(f_output, "\n--%s\n", boundary); fprintf(f_output, "Content-Type: %s\n\n", attach->mimetype.str); write_normal_email(f_output, "", item, MODE_NORMAL, 0, pf, save_rtf, 1, extra_mime_headers); } pst_freeItem(item); } DEBUG_RET(); } void write_inline_attachment(FILE* f_output, pst_item_attach* attach, char *boundary, pst_file* pst) { DEBUG_ENT("write_inline_attachment"); DEBUG_INFO(("Attachment Size is %#"PRIx64", data = %#"PRIxPTR", id %#"PRIx64"\n", (uint64_t)attach->data.size, attach->data.data, attach->i_id)); if (!attach->data.data) { // make sure we can fetch data from the id pst_index_ll *ptr = pst_getID(pst, attach->i_id); if (!ptr) { DEBUG_WARN(("Couldn't find ID pointer. Cannot save attachment to file\n")); DEBUG_RET(); return; } } fprintf(f_output, "\n--%s\n", boundary); if (!attach->mimetype.str) { fprintf(f_output, "Content-Type: %s\n", MIME_TYPE_DEFAULT); } else { fprintf(f_output, "Content-Type: %s\n", attach->mimetype.str); } fprintf(f_output, "Content-Transfer-Encoding: base64\n"); if (attach->content_id.str) { fprintf(f_output, "Content-ID: <%s>\n", attach->content_id.str); } if (attach->filename2.str) { // use the long filename, converted to proper encoding if needed. // it is already utf8 pst_rfc2231(&attach->filename2); fprintf(f_output, "Content-Disposition: attachment; \n filename*=%s\n\n", attach->filename2.str); } else if (attach->filename1.str) { // short filename never needs encoding fprintf(f_output, "Content-Disposition: attachment; filename=\"%s\"\n\n", attach->filename1.str); } else { // no filename is inline fprintf(f_output, "Content-Disposition: inline\n\n"); } (void)pst_attach_to_file_base64(pst, attach, f_output); fprintf(f_output, "\n\n"); DEBUG_RET(); } int valid_headers(char *header) { // headers are sometimes really bogus - they seem to be fragments of the // message body, so we only use them if they seem to be real rfc822 headers. // this list is composed of ones that we have seen in real pst files. // there are surely others. the problem is - given an arbitrary character // string, is it a valid (or even reasonable) set of rfc822 headers? if (header) { - if ((strncasecmp(header, "X-Barracuda-URL: ", 17) == 0) || - (strncasecmp(header, "X-ASG-Debug-ID: ", 16) == 0) || - (strncasecmp(header, "Return-Path: ", 13) == 0) || - (strncasecmp(header, "Received: ", 10) == 0) || - (strncasecmp(header, "Subject: ", 9) == 0) || - (strncasecmp(header, "Date: ", 6) == 0) || - (strncasecmp(header, "From: ", 6) == 0) || - (strncasecmp(header, "X-x: ", 5) == 0) || - (strncasecmp(header, "Microsoft Mail Internet Headers", 31) == 0)) { - return 1; + if ((strncasecmp(header, "Content-Type: ", 14) == 0) || + (strncasecmp(header, "Date: ", 6) == 0) || + (strncasecmp(header, "From: ", 6) == 0) || + (strncasecmp(header, "MIME-Version: ", 14) == 0) || + (strncasecmp(header, "Microsoft Mail Internet Headers", 31) == 0) || + (strncasecmp(header, "Received: ", 10) == 0) || + (strncasecmp(header, "Return-Path: ", 13) == 0) || + (strncasecmp(header, "Subject: ", 9) == 0) || + (strncasecmp(header, "To: ", 4) == 0) || + (strncasecmp(header, "X-ASG-Debug-ID: ", 16) == 0) || + (strncasecmp(header, "X-Barracuda-URL: ", 17) == 0) || + (strncasecmp(header, "X-x: ", 5) == 0)) { + return 1; } else { if (strlen(header) > 2) { DEBUG_INFO(("Ignore bogus headers = %s\n", header)); } return 0; } } else return 0; } void header_has_field(char *header, char *field, int *flag) { DEBUG_ENT("header_has_field"); if (my_stristr(header, field) || (strncasecmp(header, field+1, strlen(field)-1) == 0)) { DEBUG_INFO(("header block has %s header\n", field+1)); *flag = 1; } DEBUG_RET(); } void header_get_subfield(char *field, const char *subfield, char *body_subfield, size_t size_subfield) { if (!field) return; DEBUG_ENT("header_get_subfield"); char search[60]; snprintf(search, sizeof(search), " %s=", subfield); field++; char *n = header_end_field(field); char *s = my_stristr(field, search); if (n && s && (s < n)) { char *e, *f, save; s += strlen(search); // skip over subfield= if (*s == '"') { s++; e = strchr(s, '"'); } else { e = strchr(s, ';'); f = strchr(s, '\n'); if (e && f && (f < e)) e = f; } if (!e || (e > n)) e = n; // use the trailing lf as terminator if nothing better save = *e; *e = '\0'; snprintf(body_subfield, size_subfield, "%s", s); // copy the subfield to our buffer *e = save; DEBUG_INFO(("body %s %s from headers\n", subfield, body_subfield)); } DEBUG_RET(); } char* header_get_field(char *header, char *field) { char *t = my_stristr(header, field); if (!t && (strncasecmp(header, field+1, strlen(field)-1) == 0)) t = header; return t; } // return pointer to \n at the end of this header field, // or NULL if this field goes to the end of the string. char *header_end_field(char *field) { char *e = strchr(field+1, '\n'); while (e && ((e[1] == ' ') || (e[1] == '\t'))) { e = strchr(e+1, '\n'); } return e; } void header_strip_field(char *header, char *field) { char *t; while ((t = header_get_field(header, field))) { char *e = header_end_field(t); if (e) { if (t == header) e++; // if *t is not \n, we don't want to keep the \n at *e either. while (*e != '\0') { *t = *e; t++; e++; } *t = '\0'; } else { // this was the last header field, truncate the headers *t = '\0'; } } } int test_base64(char *body, size_t len) { int b64 = 0; uint8_t *b = (uint8_t *)body; DEBUG_ENT("test_base64"); while (len--) { if ((*b < 32) && (*b != 9) && (*b != 10)) { DEBUG_INFO(("found base64 byte %d\n", (int)*b)); DEBUG_HEXDUMPC(body, strlen(body), 0x10); b64 = 1; break; } b++; } DEBUG_RET(); return b64; } void find_html_charset(char *html, char *charset, size_t charsetlen) { const int index = 1; const int nmatch = index+1; regmatch_t match[nmatch]; DEBUG_ENT("find_html_charset"); int rc = regexec(&meta_charset_pattern, html, nmatch, match, 0); if (rc == 0) { int s = match[index].rm_so; int e = match[index].rm_eo; if (s != -1) { char save = html[e]; html[e] = '\0'; snprintf(charset, charsetlen, "%s", html+s); // copy the html charset html[e] = save; DEBUG_INFO(("charset %s from html text\n", charset)); } else { DEBUG_INFO(("matching %d %d %d %d\n", match[0].rm_so, match[0].rm_eo, match[1].rm_so, match[1].rm_eo)); DEBUG_HEXDUMPC(html, strlen(html), 0x10); } } else { DEBUG_INFO(("regexec returns %d\n", rc)); } DEBUG_RET(); } void find_rfc822_headers(char** extra_mime_headers) { DEBUG_ENT("find_rfc822_headers"); char *headers = *extra_mime_headers; if (headers) { char *temp, *t; while ((temp = strstr(headers, "\n\n"))) { temp[1] = '\0'; t = header_get_field(headers, "\nContent-Type:"); if (t) { t++; DEBUG_INFO(("found content type header\n")); char *n = strchr(t, '\n'); char *s = strstr(t, ": "); char *e = strchr(t, ';'); if (!e || (e > n)) e = n; if (s && (s < e)) { s += 2; if (!strncasecmp(s, RFC822, e-s)) { headers = temp+2; // found rfc822 header DEBUG_INFO(("found 822 headers\n%s\n", headers)); break; } } } //DEBUG_INFO(("skipping to next block after\n%s\n", headers)); headers = temp+2; // skip to next chunk of headers } *extra_mime_headers = headers; } DEBUG_RET(); } void write_body_part(FILE* f_output, pst_string *body, char *mime, char *charset, char *boundary, pst_file* pst) { DEBUG_ENT("write_body_part"); removeCR(body->str); size_t body_len = strlen(body->str); if (body->is_utf8 && (strcasecmp("utf-8", charset))) { if (prefer_utf8) { charset = "utf-8"; } else { // try to convert to the specified charset since the target // is not utf-8, and the data came from a unicode (utf16) field // and is now in utf-8. size_t rc; DEBUG_INFO(("Convert %s utf-8 to %s\n", mime, charset)); pst_vbuf *newer = pst_vballoc(2); rc = pst_vb_utf8to8bit(newer, body->str, body_len, charset); if (rc == (size_t)-1) { // unable to convert, change the charset to utf8 free(newer->b); DEBUG_INFO(("Failed to convert %s utf-8 to %s\n", mime, charset)); charset = "utf-8"; } else { // null terminate the output string pst_vbgrow(newer, 1); newer->b[newer->dlen] = '\0'; free(body->str); body->str = newer->b; body_len = newer->dlen; } free(newer); } } int base64 = test_base64(body->str, body_len); fprintf(f_output, "\n--%s\n", boundary); fprintf(f_output, "Content-Type: %s; charset=\"%s\"\n", mime, charset); if (base64) fprintf(f_output, "Content-Transfer-Encoding: base64\n"); fprintf(f_output, "\n"); // Any body that uses an encoding with NULLs, e.g. UTF16, will be base64-encoded here. if (base64) { char *enc = pst_base64_encode(body->str, body_len); if (enc) { write_email_body(f_output, enc); fprintf(f_output, "\n"); free(enc); } } else { write_email_body(f_output, body->str); } DEBUG_RET(); } void write_schedule_part_data(FILE* f_output, pst_item* item, const char* sender, const char* method) { fprintf(f_output, "BEGIN:VCALENDAR\n"); fprintf(f_output, "VERSION:2.0\n"); fprintf(f_output, "PRODID:LibPST v%s\n", VERSION); if (method) fprintf(f_output, "METHOD:%s\n", method); fprintf(f_output, "BEGIN:VEVENT\n"); if (sender) { if (item->email->outlook_sender_name.str) { fprintf(f_output, "ORGANIZER;CN=\"%s\":MAILTO:%s\n", item->email->outlook_sender_name.str, sender); } else { fprintf(f_output, "ORGANIZER;CN=\"\":MAILTO:%s\n", sender); } } write_appointment(f_output, item); fprintf(f_output, "END:VCALENDAR\n"); } void write_schedule_part(FILE* f_output, pst_item* item, const char* sender, const char* boundary) { const char* method = "REQUEST"; const char* charset = "utf-8"; char fname[30]; if (!item->appointment) return; // inline appointment request fprintf(f_output, "\n--%s\n", boundary); fprintf(f_output, "Content-Type: %s; method=\"%s\"; charset=\"%s\"\n\n", "text/calendar", method, charset); write_schedule_part_data(f_output, item, sender, method); fprintf(f_output, "\n"); // attachment appointment request snprintf(fname, sizeof(fname), "i%i.ics", rand()); fprintf(f_output, "\n--%s\n", boundary); fprintf(f_output, "Content-Type: %s; charset=\"%s\"; name=\"%s\"\n", "text/calendar", "utf-8", fname); fprintf(f_output, "Content-Disposition: attachment; filename=\"%s\"\n\n", fname); write_schedule_part_data(f_output, item, sender, method); fprintf(f_output, "\n"); } void write_normal_email(FILE* f_output, char f_name[], pst_item* item, int mode, int mode_MH, pst_file* pst, int save_rtf, int embedding, char** extra_mime_headers) { char boundary[60]; char altboundary[66]; char *altboundaryp = NULL; char body_charset[30]; char buffer_charset[30]; char body_report[60]; char sender[60]; int sender_known = 0; char *temp = NULL; time_t em_time; char *c_time; char *headers = NULL; int has_from, has_subject, has_to, has_cc, has_date, has_msgid; has_from = has_subject = has_to = has_cc = has_date = has_msgid = 0; DEBUG_ENT("write_normal_email"); pst_convert_utf8_null(item, &item->email->header); headers = valid_headers(item->email->header.str) ? item->email->header.str : valid_headers(*extra_mime_headers) ? *extra_mime_headers : NULL; // setup default body character set and report type strncpy(body_charset, pst_default_charset(item, sizeof(buffer_charset), buffer_charset), sizeof(body_charset)); body_charset[sizeof(body_charset)-1] = '\0'; strncpy(body_report, "delivery-status", sizeof(body_report)); body_report[sizeof(body_report)-1] = '\0'; // setup default sender pst_convert_utf8(item, &item->email->sender_address); if (item->email->sender_address.str && strchr(item->email->sender_address.str, '@')) { temp = item->email->sender_address.str; sender_known = 1; } else { temp = "MAILER-DAEMON"; } strncpy(sender, temp, sizeof(sender)); sender[sizeof(sender)-1] = '\0'; // convert the sent date if it exists, or set it to a fixed date if (item->email->sent_date) { em_time = pst_fileTimeToUnixTime(item->email->sent_date); c_time = ctime(&em_time); if (c_time) c_time[strlen(c_time)-1] = '\0'; //remove end \n else c_time = "Thu Jan 1 00:00:00 1970"; } else c_time = "Thu Jan 1 00:00:00 1970"; // create our MIME boundaries here. snprintf(boundary, sizeof(boundary), "--boundary-LibPST-iamunique-%i_-_-", rand()); snprintf(altboundary, sizeof(altboundary), "alt-%s", boundary); // we will always look at the headers to discover some stuff if (headers ) { char *t; removeCR(headers); temp = strstr(headers, "\n\n"); if (temp) { // cut off our real rfc822 headers here temp[1] = '\0'; // pointer to all the embedded MIME headers. // we use these to find the actual rfc822 headers for embedded message/rfc822 mime parts // but only for the outermost message if (!*extra_mime_headers) *extra_mime_headers = temp+2; DEBUG_INFO(("Found extra mime headers\n%s\n", temp+2)); } // Check if the headers have all the necessary fields header_has_field(headers, "\nFrom:", &has_from); header_has_field(headers, "\nTo:", &has_to); header_has_field(headers, "\nSubject:", &has_subject); header_has_field(headers, "\nDate:", &has_date); header_has_field(headers, "\nCC:", &has_cc); header_has_field(headers, "\nMessage-Id:", &has_msgid); // look for charset and report-type in Content-Type header t = header_get_field(headers, "\nContent-Type:"); header_get_subfield(t, "charset", body_charset, sizeof(body_charset)); header_get_subfield(t, "report-type", body_report, sizeof(body_report)); // derive a proper sender email address if (!sender_known) { t = header_get_field(headers, "\nFrom:"); if (t) { // assume address is on the first line, rather than on a continuation line t++; char *n = strchr(t, '\n'); char *s = strchr(t, '<'); char *e = strchr(t, '>'); if (s && e && n && (s < e) && (e < n)) { char save = *e; *e = '\0'; snprintf(sender, sizeof(sender), "%s", s+1); *e = save; } } } // Strip out the mime headers and some others that we don't want to emit header_strip_field(headers, "\nMicrosoft Mail Internet Headers"); header_strip_field(headers, "\nMIME-Version:"); header_strip_field(headers, "\nContent-Type:"); header_strip_field(headers, "\nContent-Transfer-Encoding:"); header_strip_field(headers, "\nContent-class:"); header_strip_field(headers, "\nX-MimeOLE:"); header_strip_field(headers, "\nX-From_:"); } DEBUG_INFO(("About to print Header\n")); if (item && item->subject.str) { pst_convert_utf8(item, &item->subject); DEBUG_INFO(("item->subject = %s\n", item->subject.str)); } if (mode != MODE_SEPARATE) { // most modes need this separator line. // procmail produces this separator without the quotes around the // sender email address, but apparently some Mac email client needs // those quotes, and they don't seem to cause problems for anyone else. char *quo = (embedding) ? ">" : ""; fprintf(f_output, "%sFrom \"%s\" %s\n", quo, sender, c_time); } // print the supplied email headers if (headers) { int len = strlen(headers); if (len > 0) { fprintf(f_output, "%s", headers); // make sure the headers end with a \n if (headers[len-1] != '\n') fprintf(f_output, "\n"); //char *h = headers; //while (*h) { // char *e = strchr(h, '\n'); // int d = 1; // normally e points to trailing \n // if (!e) { // e = h + strlen(h); // e points to trailing null // d = 0; // } // // we could do rfc2047 encoding here if needed // fprintf(f_output, "%.*s\n", (int)(e-h), h); // h = e + d; //} } } // record read status if ((item->flags & PST_FLAG_READ) == PST_FLAG_READ) { fprintf(f_output, "Status: RO\n"); } // create required header fields that are not already written if (!has_from) { if (item->email->outlook_sender_name.str){ pst_rfc2047(item, &item->email->outlook_sender_name, 1); fprintf(f_output, "From: %s <%s>\n", item->email->outlook_sender_name.str, sender); } else { fprintf(f_output, "From: <%s>\n", sender); } } if (!has_subject) { if (item->subject.str) { pst_rfc2047(item, &item->subject, 0); fprintf(f_output, "Subject: %s\n", item->subject.str); } else { fprintf(f_output, "Subject: \n"); } } if (!has_to && item->email->sentto_address.str) { pst_rfc2047(item, &item->email->sentto_address, 0); fprintf(f_output, "To: %s\n", item->email->sentto_address.str); } if (!has_cc && item->email->cc_address.str) { pst_rfc2047(item, &item->email->cc_address, 0); fprintf(f_output, "Cc: %s\n", item->email->cc_address.str); } if (!has_date && item->email->sent_date) { char c_time[C_TIME_SIZE]; struct tm stm; gmtime_r(&em_time, &stm); strftime(c_time, C_TIME_SIZE, "%a, %d %b %Y %H:%M:%S %z", &stm); fprintf(f_output, "Date: %s\n", c_time); } if (!has_msgid && item->email->messageid.str) { pst_convert_utf8(item, &item->email->messageid); fprintf(f_output, "Message-Id: %s\n", item->email->messageid.str); } // add forensic headers to capture some .pst stuff that is not really // needed or used by mail clients pst_convert_utf8_null(item, &item->email->sender_address); if (item->email->sender_address.str && !strchr(item->email->sender_address.str, '@') && strcmp(item->email->sender_address.str, ".") && (strlen(item->email->sender_address.str) > 0)) { fprintf(f_output, "X-libpst-forensic-sender: %s\n", item->email->sender_address.str); } if (item->email->bcc_address.str) { pst_convert_utf8(item, &item->email->bcc_address); fprintf(f_output, "X-libpst-forensic-bcc: %s\n", item->email->bcc_address.str); } // add our own mime headers fprintf(f_output, "MIME-Version: 1.0\n"); if (item->type == PST_TYPE_REPORT) { // multipart/report for DSN/MDN reports fprintf(f_output, "Content-Type: multipart/report; report-type=%s;\n\tboundary=\"%s\"\n", body_report, boundary); } else { fprintf(f_output, "Content-Type: multipart/mixed;\n\tboundary=\"%s\"\n", boundary); } fprintf(f_output, "\n"); // end of headers, start of body // now dump the body parts if ((item->type == PST_TYPE_REPORT) && (item->email->report_text.str)) { write_body_part(f_output, &item->email->report_text, "text/plain", body_charset, boundary, pst); fprintf(f_output, "\n"); } if (item->body.str && item->email->htmlbody.str) { // start the nested alternative part fprintf(f_output, "\n--%s\n", boundary); fprintf(f_output, "Content-Type: multipart/alternative;\n\tboundary=\"%s\"\n", altboundary); altboundaryp = altboundary; } else { altboundaryp = boundary; } if (item->body.str) { write_body_part(f_output, &item->body, "text/plain", body_charset, altboundaryp, pst); } if (item->email->htmlbody.str) { find_html_charset(item->email->htmlbody.str, body_charset, sizeof(body_charset)); write_body_part(f_output, &item->email->htmlbody, "text/html", body_charset, altboundaryp, pst); } if (item->body.str && item->email->htmlbody.str) { // end the nested alternative part fprintf(f_output, "\n--%s--\n", altboundary); } if (item->email->rtf_compressed.data && save_rtf) { pst_item_attach* attach = (pst_item_attach*)pst_malloc(sizeof(pst_item_attach)); DEBUG_INFO(("Adding RTF body as attachment\n")); memset(attach, 0, sizeof(pst_item_attach)); attach->next = item->attach; item->attach = attach; attach->data.data = pst_lzfu_decompress(item->email->rtf_compressed.data, item->email->rtf_compressed.size, &attach->data.size); attach->filename2.str = strdup(RTF_ATTACH_NAME); attach->filename2.is_utf8 = 1; attach->mimetype.str = strdup(RTF_ATTACH_TYPE); attach->mimetype.is_utf8 = 1; } if (item->email->encrypted_body.data) { pst_item_attach* attach = (pst_item_attach*)pst_malloc(sizeof(pst_item_attach)); DEBUG_INFO(("Adding encrypted text body as attachment\n")); memset(attach, 0, sizeof(pst_item_attach)); attach->next = item->attach; item->attach = attach; attach->data.data = item->email->encrypted_body.data; attach->data.size = item->email->encrypted_body.size; item->email->encrypted_body.data = NULL; } if (item->email->encrypted_htmlbody.data) { pst_item_attach* attach = (pst_item_attach*)pst_malloc(sizeof(pst_item_attach)); DEBUG_INFO(("Adding encrypted HTML body as attachment\n")); memset(attach, 0, sizeof(pst_item_attach)); attach->next = item->attach; item->attach = attach; attach->data.data = item->email->encrypted_htmlbody.data; attach->data.size = item->email->encrypted_htmlbody.size; item->email->encrypted_htmlbody.data = NULL; } if (item->type == PST_TYPE_SCHEDULE) { write_schedule_part(f_output, item, sender, boundary); } // other attachments { pst_item_attach* attach; int attach_num = 0; for (attach = item->attach; attach; attach = attach->next) { pst_convert_utf8_null(item, &attach->filename1); pst_convert_utf8_null(item, &attach->filename2); pst_convert_utf8_null(item, &attach->mimetype); DEBUG_INFO(("Attempting Attachment encoding\n")); if (attach->method == PST_ATTACH_EMBEDDED) { DEBUG_INFO(("have an embedded rfc822 message attachment\n")); if (attach->mimetype.str) { DEBUG_INFO(("which already has a mime-type of %s\n", attach->mimetype.str)); free(attach->mimetype.str); } attach->mimetype.str = strdup(RFC822); attach->mimetype.is_utf8 = 1; find_rfc822_headers(extra_mime_headers); write_embedded_message(f_output, attach, boundary, pst, save_rtf, extra_mime_headers); } else if (attach->data.data || attach->i_id) { if (acceptable_ext(attach)) { if (mode == MODE_SEPARATE && !mode_MH) write_separate_attachment(f_name, attach, ++attach_num, pst); else write_inline_attachment(f_output, attach, boundary, pst); } } } } fprintf(f_output, "\n--%s--\n\n", boundary); DEBUG_RET(); } void write_vcard(FILE* f_output, pst_item* item, pst_item_contact* contact, char comment[]) { char* result = NULL; size_t resultlen = 0; char time_buffer[30]; // We can only call rfc escape once per printf, since the second call // may free the buffer returned by the first call. // I had tried to place those into a single printf - Carl. DEBUG_ENT("write_vcard"); // make everything utf8 pst_convert_utf8_null(item, &contact->fullname); pst_convert_utf8_null(item, &contact->surname); pst_convert_utf8_null(item, &contact->first_name); pst_convert_utf8_null(item, &contact->middle_name); pst_convert_utf8_null(item, &contact->display_name_prefix); pst_convert_utf8_null(item, &contact->suffix); pst_convert_utf8_null(item, &contact->nickname); pst_convert_utf8_null(item, &contact->address1); pst_convert_utf8_null(item, &contact->address2); pst_convert_utf8_null(item, &contact->address3); pst_convert_utf8_null(item, &contact->home_po_box); pst_convert_utf8_null(item, &contact->home_street); pst_convert_utf8_null(item, &contact->home_city); pst_convert_utf8_null(item, &contact->home_state); pst_convert_utf8_null(item, &contact->home_postal_code); pst_convert_utf8_null(item, &contact->home_country); pst_convert_utf8_null(item, &contact->home_address); pst_convert_utf8_null(item, &contact->business_po_box); pst_convert_utf8_null(item, &contact->business_street); pst_convert_utf8_null(item, &contact->business_city); pst_convert_utf8_null(item, &contact->business_state); pst_convert_utf8_null(item, &contact->business_postal_code); pst_convert_utf8_null(item, &contact->business_country); pst_convert_utf8_null(item, &contact->business_address); pst_convert_utf8_null(item, &contact->other_po_box); pst_convert_utf8_null(item, &contact->other_street); pst_convert_utf8_null(item, &contact->other_city); pst_convert_utf8_null(item, &contact->other_state); pst_convert_utf8_null(item, &contact->other_postal_code); pst_convert_utf8_null(item, &contact->other_country); pst_convert_utf8_null(item, &contact->other_address); pst_convert_utf8_null(item, &contact->business_fax); pst_convert_utf8_null(item, &contact->business_phone); pst_convert_utf8_null(item, &contact->business_phone2); pst_convert_utf8_null(item, &contact->car_phone); pst_convert_utf8_null(item, &contact->home_fax); pst_convert_utf8_null(item, &contact->home_phone); pst_convert_utf8_null(item, &contact->home_phone2); pst_convert_utf8_null(item, &contact->isdn_phone); pst_convert_utf8_null(item, &contact->mobile_phone); pst_convert_utf8_null(item, &contact->other_phone); pst_convert_utf8_null(item, &contact->pager_phone); pst_convert_utf8_null(item, &contact->primary_fax); pst_convert_utf8_null(item, &contact->primary_phone); pst_convert_utf8_null(item, &contact->radio_phone); pst_convert_utf8_null(item, &contact->telex); pst_convert_utf8_null(item, &contact->job_title); pst_convert_utf8_null(item, &contact->profession); pst_convert_utf8_null(item, &contact->assistant_name); pst_convert_utf8_null(item, &contact->assistant_phone); pst_convert_utf8_null(item, &contact->company_name); pst_convert_utf8_null(item, &item->body); // the specification I am following is (hopefully) RFC2426 vCard Mime Directory Profile fprintf(f_output, "BEGIN:VCARD\n"); fprintf(f_output, "FN:%s\n", pst_rfc2426_escape(contact->fullname.str, &result, &resultlen)); //fprintf(f_output, "N:%s;%s;%s;%s;%s\n", fprintf(f_output, "N:%s;", (!contact->surname.str) ? "" : pst_rfc2426_escape(contact->surname.str, &result, &resultlen)); fprintf(f_output, "%s;", (!contact->first_name.str) ? "" : pst_rfc2426_escape(contact->first_name.str, &result, &resultlen)); fprintf(f_output, "%s;", (!contact->middle_name.str) ? "" : pst_rfc2426_escape(contact->middle_name.str, &result, &resultlen)); fprintf(f_output, "%s;", (!contact->display_name_prefix.str) ? "" : pst_rfc2426_escape(contact->display_name_prefix.str, &result, &resultlen)); fprintf(f_output, "%s\n", (!contact->suffix.str) ? "" : pst_rfc2426_escape(contact->suffix.str, &result, &resultlen)); if (contact->nickname.str) fprintf(f_output, "NICKNAME:%s\n", pst_rfc2426_escape(contact->nickname.str, &result, &resultlen)); if (contact->address1.str) fprintf(f_output, "EMAIL:%s\n", pst_rfc2426_escape(contact->address1.str, &result, &resultlen)); if (contact->address2.str) fprintf(f_output, "EMAIL:%s\n", pst_rfc2426_escape(contact->address2.str, &result, &resultlen)); if (contact->address3.str) fprintf(f_output, "EMAIL:%s\n", pst_rfc2426_escape(contact->address3.str, &result, &resultlen)); if (contact->birthday) fprintf(f_output, "BDAY:%s\n", pst_rfc2425_datetime_format(contact->birthday, sizeof(time_buffer), time_buffer)); if (contact->home_address.str) { //fprintf(f_output, "ADR;TYPE=home:%s;%s;%s;%s;%s;%s;%s\n", fprintf(f_output, "ADR;TYPE=home:%s;", (!contact->home_po_box.str) ? "" : pst_rfc2426_escape(contact->home_po_box.str, &result, &resultlen)); fprintf(f_output, "%s;", ""); // extended Address fprintf(f_output, "%s;", (!contact->home_street.str) ? "" : pst_rfc2426_escape(contact->home_street.str, &result, &resultlen)); fprintf(f_output, "%s;", (!contact->home_city.str) ? "" : pst_rfc2426_escape(contact->home_city.str, &result, &resultlen)); fprintf(f_output, "%s;", (!contact->home_state.str) ? "" : pst_rfc2426_escape(contact->home_state.str, &result, &resultlen)); fprintf(f_output, "%s;", (!contact->home_postal_code.str) ? "" : pst_rfc2426_escape(contact->home_postal_code.str, &result, &resultlen)); fprintf(f_output, "%s\n", (!contact->home_country.str) ? "" : pst_rfc2426_escape(contact->home_country.str, &result, &resultlen)); fprintf(f_output, "LABEL;TYPE=home:%s\n", pst_rfc2426_escape(contact->home_address.str, &result, &resultlen)); } if (contact->business_address.str) { //fprintf(f_output, "ADR;TYPE=work:%s;%s;%s;%s;%s;%s;%s\n", fprintf(f_output, "ADR;TYPE=work:%s;", (!contact->business_po_box.str) ? "" : pst_rfc2426_escape(contact->business_po_box.str, &result, &resultlen)); fprintf(f_output, "%s;", ""); // extended Address fprintf(f_output, "%s;", (!contact->business_street.str) ? "" : pst_rfc2426_escape(contact->business_street.str, &result, &resultlen)); fprintf(f_output, "%s;", (!contact->business_city.str) ? "" : pst_rfc2426_escape(contact->business_city.str, &result, &resultlen)); fprintf(f_output, "%s;", (!contact->business_state.str) ? "" : pst_rfc2426_escape(contact->business_state.str, &result, &resultlen)); fprintf(f_output, "%s;", (!contact->business_postal_code.str) ? "" : pst_rfc2426_escape(contact->business_postal_code.str, &result, &resultlen)); fprintf(f_output, "%s\n", (!contact->business_country.str) ? "" : pst_rfc2426_escape(contact->business_country.str, &result, &resultlen)); fprintf(f_output, "LABEL;TYPE=work:%s\n", pst_rfc2426_escape(contact->business_address.str, &result, &resultlen)); } if (contact->other_address.str) { //fprintf(f_output, "ADR;TYPE=postal:%s;%s;%s;%s;%s;%s;%s\n", fprintf(f_output, "ADR;TYPE=postal:%s;",(!contact->other_po_box.str) ? "" : pst_rfc2426_escape(contact->other_po_box.str, &result, &resultlen)); fprintf(f_output, "%s;", ""); // extended Address fprintf(f_output, "%s;", (!contact->other_street.str) ? "" : pst_rfc2426_escape(contact->other_street.str, &result, &resultlen)); fprintf(f_output, "%s;", (!contact->other_city.str) ? "" : pst_rfc2426_escape(contact->other_city.str, &result, &resultlen)); fprintf(f_output, "%s;", (!contact->other_state.str) ? "" : pst_rfc2426_escape(contact->other_state.str, &result, &resultlen)); fprintf(f_output, "%s;", (!contact->other_postal_code.str) ? "" : pst_rfc2426_escape(contact->other_postal_code.str, &result, &resultlen)); fprintf(f_output, "%s\n", (!contact->other_country.str) ? "" : pst_rfc2426_escape(contact->other_country.str, &result, &resultlen)); fprintf(f_output, "LABEL;TYPE=postal:%s\n", pst_rfc2426_escape(contact->other_address.str, &result, &resultlen)); } if (contact->business_fax.str) fprintf(f_output, "TEL;TYPE=work,fax:%s\n", pst_rfc2426_escape(contact->business_fax.str, &result, &resultlen)); if (contact->business_phone.str) fprintf(f_output, "TEL;TYPE=work,voice:%s\n", pst_rfc2426_escape(contact->business_phone.str, &result, &resultlen)); if (contact->business_phone2.str) fprintf(f_output, "TEL;TYPE=work,voice:%s\n", pst_rfc2426_escape(contact->business_phone2.str, &result, &resultlen)); if (contact->car_phone.str) fprintf(f_output, "TEL;TYPE=car,voice:%s\n", pst_rfc2426_escape(contact->car_phone.str, &result, &resultlen)); if (contact->home_fax.str) fprintf(f_output, "TEL;TYPE=home,fax:%s\n", pst_rfc2426_escape(contact->home_fax.str, &result, &resultlen)); if (contact->home_phone.str) fprintf(f_output, "TEL;TYPE=home,voice:%s\n", pst_rfc2426_escape(contact->home_phone.str, &result, &resultlen)); if (contact->home_phone2.str) fprintf(f_output, "TEL;TYPE=home,voice:%s\n", pst_rfc2426_escape(contact->home_phone2.str, &result, &resultlen)); if (contact->isdn_phone.str) fprintf(f_output, "TEL;TYPE=isdn:%s\n", pst_rfc2426_escape(contact->isdn_phone.str, &result, &resultlen)); if (contact->mobile_phone.str) fprintf(f_output, "TEL;TYPE=cell,voice:%s\n", pst_rfc2426_escape(contact->mobile_phone.str, &result, &resultlen)); if (contact->other_phone.str) fprintf(f_output, "TEL;TYPE=msg:%s\n", pst_rfc2426_escape(contact->other_phone.str, &result, &resultlen)); if (contact->pager_phone.str) fprintf(f_output, "TEL;TYPE=pager:%s\n", pst_rfc2426_escape(contact->pager_phone.str, &result, &resultlen)); if (contact->primary_fax.str) fprintf(f_output, "TEL;TYPE=fax,pref:%s\n", pst_rfc2426_escape(contact->primary_fax.str, &result, &resultlen)); if (contact->primary_phone.str) fprintf(f_output, "TEL;TYPE=phone,pref:%s\n", pst_rfc2426_escape(contact->primary_phone.str, &result, &resultlen)); if (contact->radio_phone.str) fprintf(f_output, "TEL;TYPE=pcs:%s\n", pst_rfc2426_escape(contact->radio_phone.str, &result, &resultlen)); if (contact->telex.str) fprintf(f_output, "TEL;TYPE=bbs:%s\n", pst_rfc2426_escape(contact->telex.str, &result, &resultlen)); if (contact->job_title.str) fprintf(f_output, "TITLE:%s\n", pst_rfc2426_escape(contact->job_title.str, &result, &resultlen)); if (contact->profession.str) fprintf(f_output, "ROLE:%s\n", pst_rfc2426_escape(contact->profession.str, &result, &resultlen)); if (contact->assistant_name.str || contact->assistant_phone.str) { fprintf(f_output, "AGENT:BEGIN:VCARD\n"); if (contact->assistant_name.str) fprintf(f_output, "FN:%s\n", pst_rfc2426_escape(contact->assistant_name.str, &result, &resultlen)); if (contact->assistant_phone.str) fprintf(f_output, "TEL:%s\n", pst_rfc2426_escape(contact->assistant_phone.str, &result, &resultlen)); } if (contact->company_name.str) fprintf(f_output, "ORG:%s\n", pst_rfc2426_escape(contact->company_name.str, &result, &resultlen)); if (comment) fprintf(f_output, "NOTE:%s\n", pst_rfc2426_escape(comment, &result, &resultlen)); if (item->body.str) fprintf(f_output, "NOTE:%s\n", pst_rfc2426_escape(item->body.str, &result, &resultlen)); write_extra_categories(f_output, item); fprintf(f_output, "VERSION: 3.0\n"); fprintf(f_output, "END:VCARD\n\n"); if (result) free(result); DEBUG_RET(); } /** * write extra vcard or vcalendar categories from the extra keywords fields * * @param f_output open file pointer * @param item pst item containing the keywords * @return true if we write a categories line */ int write_extra_categories(FILE* f_output, pst_item* item) { char* result = NULL; size_t resultlen = 0; pst_item_extra_field *ef = item->extra_fields; const char *fmt = "CATEGORIES:%s"; int category_started = 0; while (ef) { if (strcmp(ef->field_name, "Keywords") == 0) { fprintf(f_output, fmt, pst_rfc2426_escape(ef->value, &result, &resultlen)); fmt = ", %s"; category_started = 1; } ef = ef->next; } if (category_started) fprintf(f_output, "\n"); if (result) free(result); return category_started; } void write_journal(FILE* f_output, pst_item* item) { char* result = NULL; size_t resultlen = 0; char time_buffer[30]; pst_item_journal* journal = item->journal; // make everything utf8 pst_convert_utf8_null(item, &item->subject); pst_convert_utf8_null(item, &item->body); fprintf(f_output, "BEGIN:VJOURNAL\n"); fprintf(f_output, "DTSTAMP:%s\n", pst_rfc2445_datetime_format_now(sizeof(time_buffer), time_buffer)); if (item->create_date) fprintf(f_output, "CREATED:%s\n", pst_rfc2445_datetime_format(item->create_date, sizeof(time_buffer), time_buffer)); if (item->modify_date) fprintf(f_output, "LAST-MOD:%s\n", pst_rfc2445_datetime_format(item->modify_date, sizeof(time_buffer), time_buffer)); if (item->subject.str) fprintf(f_output, "SUMMARY:%s\n", pst_rfc2426_escape(item->subject.str, &result, &resultlen)); if (item->body.str) fprintf(f_output, "DESCRIPTION:%s\n", pst_rfc2426_escape(item->body.str, &result, &resultlen)); if (journal && journal->start) fprintf(f_output, "DTSTART;VALUE=DATE-TIME:%s\n", pst_rfc2445_datetime_format(journal->start, sizeof(time_buffer), time_buffer)); fprintf(f_output, "END:VJOURNAL\n"); if (result) free(result); } void write_appointment(FILE* f_output, pst_item* item) { char* result = NULL; size_t resultlen = 0; char time_buffer[30]; pst_item_appointment* appointment = item->appointment; // make everything utf8 pst_convert_utf8_null(item, &item->subject); pst_convert_utf8_null(item, &item->body); pst_convert_utf8_null(item, &appointment->location); fprintf(f_output, "UID:%#"PRIx64"\n", item->block_id); fprintf(f_output, "DTSTAMP:%s\n", pst_rfc2445_datetime_format_now(sizeof(time_buffer), time_buffer)); if (item->create_date) fprintf(f_output, "CREATED:%s\n", pst_rfc2445_datetime_format(item->create_date, sizeof(time_buffer), time_buffer)); if (item->modify_date) fprintf(f_output, "LAST-MOD:%s\n", pst_rfc2445_datetime_format(item->modify_date, sizeof(time_buffer), time_buffer)); if (item->subject.str) fprintf(f_output, "SUMMARY:%s\n", pst_rfc2426_escape(item->subject.str, &result, &resultlen)); if (item->body.str) fprintf(f_output, "DESCRIPTION:%s\n", pst_rfc2426_escape(item->body.str, &result, &resultlen)); if (appointment && appointment->start) fprintf(f_output, "DTSTART;VALUE=DATE-TIME:%s\n", pst_rfc2445_datetime_format(appointment->start, sizeof(time_buffer), time_buffer)); if (appointment && appointment->end) fprintf(f_output, "DTEND;VALUE=DATE-TIME:%s\n", pst_rfc2445_datetime_format(appointment->end, sizeof(time_buffer), time_buffer)); if (appointment && appointment->location.str) fprintf(f_output, "LOCATION:%s\n", pst_rfc2426_escape(appointment->location.str, &result, &resultlen)); if (appointment) { switch (appointment->showas) { case PST_FREEBUSY_TENTATIVE: fprintf(f_output, "STATUS:TENTATIVE\n"); break; case PST_FREEBUSY_FREE: // mark as transparent and as confirmed fprintf(f_output, "TRANSP:TRANSPARENT\n"); case PST_FREEBUSY_BUSY: case PST_FREEBUSY_OUT_OF_OFFICE: fprintf(f_output, "STATUS:CONFIRMED\n"); break; } if (appointment->is_recurring) { const char* rules[] = {"DAILY", "WEEKLY", "MONTHLY", "YEARLY"}; const char* days[] = {"SU", "MO", "TU", "WE", "TH", "FR", "SA"}; pst_recurrence *rdata = pst_convert_recurrence(appointment); fprintf(f_output, "RRULE:FREQ=%s", rules[rdata->type]); if (rdata->count) fprintf(f_output, ";COUNT=%u", rdata->count); if ((rdata->interval != 1) && (rdata->interval)) fprintf(f_output, ";INTERVAL=%u", rdata->interval); if (rdata->dayofmonth) fprintf(f_output, ";BYMONTHDAY=%d", rdata->dayofmonth); if (rdata->monthofyear) fprintf(f_output, ";BYMONTH=%d", rdata->monthofyear); if (rdata->position) fprintf(f_output, ";BYSETPOS=%d", rdata->position); if (rdata->bydaymask) { char byday[40]; int empty = 1; int i=0; memset(byday, 0, sizeof(byday)); for (i=0; i<6; i++) { int bit = 1 << i; if (bit & rdata->bydaymask) { char temp[40]; snprintf(temp, sizeof(temp), "%s%s%s", byday, (empty) ? ";BYDAY=" : ";", days[i]); strcpy(byday, temp); empty = 0; } } fprintf(f_output, "%s", byday); } fprintf(f_output, "\n"); pst_free_recurrence(rdata); } switch (appointment->label) { case PST_APP_LABEL_NONE: if (!write_extra_categories(f_output, item)) fprintf(f_output, "CATEGORIES:NONE\n"); break; case PST_APP_LABEL_IMPORTANT: fprintf(f_output, "CATEGORIES:IMPORTANT\n"); break; case PST_APP_LABEL_BUSINESS: fprintf(f_output, "CATEGORIES:BUSINESS\n"); break; case PST_APP_LABEL_PERSONAL: fprintf(f_output, "CATEGORIES:PERSONAL\n"); break; case PST_APP_LABEL_VACATION: fprintf(f_output, "CATEGORIES:VACATION\n"); break; case PST_APP_LABEL_MUST_ATTEND: fprintf(f_output, "CATEGORIES:MUST-ATTEND\n"); break; case PST_APP_LABEL_TRAVEL_REQ: fprintf(f_output, "CATEGORIES:TRAVEL-REQUIRED\n"); break; case PST_APP_LABEL_NEEDS_PREP: fprintf(f_output, "CATEGORIES:NEEDS-PREPARATION\n"); break; case PST_APP_LABEL_BIRTHDAY: fprintf(f_output, "CATEGORIES:BIRTHDAY\n"); break; case PST_APP_LABEL_ANNIVERSARY: fprintf(f_output, "CATEGORIES:ANNIVERSARY\n"); break; case PST_APP_LABEL_PHONE_CALL: fprintf(f_output, "CATEGORIES:PHONE-CALL\n"); break; } // ignore bogus alarms if (appointment->alarm && (appointment->alarm_minutes >= 0) && (appointment->alarm_minutes < 1440)) { fprintf(f_output, "BEGIN:VALARM\n"); fprintf(f_output, "TRIGGER:-PT%dM\n", appointment->alarm_minutes); fprintf(f_output, "ACTION:DISPLAY\n"); fprintf(f_output, "DESCRIPTION:Reminder\n"); fprintf(f_output, "END:VALARM\n"); } } fprintf(f_output, "END:VEVENT\n"); if (result) free(result); } void create_enter_dir(struct file_ll* f, pst_item *item) { - pst_convert_utf8(item, &item->file_as); - f->type = item->type; + memset(f, 0, sizeof(*f)); f->stored_count = (item->folder) ? item->folder->item_count : 0; + pst_convert_utf8(item, &item->file_as); + f->dname = (char*) pst_malloc(strlen(item->file_as.str)+1); + strcpy(f->dname, item->file_as.str); DEBUG_ENT("create_enter_dir"); if (mode == MODE_KMAIL) - f->name = mk_kmail_dir(item->file_as.str); + f->name[0] = mk_kmail_dir(item->file_as.str); else if (mode == MODE_RECURSE) { - f->name = mk_recurse_dir(item->file_as.str, f->type); + int32_t t; + mk_recurse_dir(item->file_as.str); + for (t=0; tname[t] = strdup(item_type_to_name(t)); + } + } if (mode_thunder) { FILE *type_file = fopen(".type", "w"); fprintf(type_file, "%d\n", item->type); fclose(type_file); } } else if (mode == MODE_SEPARATE) { // do similar stuff to recurse here. mk_separate_dir(item->file_as.str); - f->name = (char*) pst_malloc(file_name_len); - memset(f->name, 0, file_name_len); + f->name[0] = (char*) pst_malloc(file_name_len); + memset(f->name[0], 0, file_name_len); } else { - f->name = (char*) pst_malloc(strlen(item->file_as.str)+strlen(OUTPUT_TEMPLATE)+1); - sprintf(f->name, OUTPUT_TEMPLATE, item->file_as.str); + f->name[0] = (char*) pst_malloc(strlen(item->file_as.str)+strlen(OUTPUT_TEMPLATE)+1); + sprintf(f->name[0], OUTPUT_TEMPLATE, item->file_as.str); } - f->dname = (char*) pst_malloc(strlen(item->file_as.str)+1); - strcpy(f->dname, item->file_as.str); - - if (overwrite != 1) { - int x = 0; - char *temp = (char*) pst_malloc (strlen(f->name)+10); //enough room for 10 digits - - sprintf(temp, "%s", f->name); - check_filename(temp); - while ((f->output = fopen(temp, "r"))) { - DEBUG_INFO(("need to increase filename because one already exists with that name\n")); - DEBUG_INFO(("- increasing it to %s%d\n", f->name, x)); - x++; - sprintf(temp, "%s%08d", f->name, x); - DEBUG_INFO(("- trying \"%s\"\n", f->name)); - if (x == 99999999) { - DIE(("create_enter_dir: Why can I not create a folder %s? I have tried %i extensions...\n", f->name, x)); - } - fclose(f->output); - } - if (x > 0) { //then the f->name should change - free (f->name); - f->name = temp; - } else { - free(temp); - } - } - - DEBUG_INFO(("f->name = %s\nitem->folder_name = %s\n", f->name, item->file_as.str)); if (mode != MODE_SEPARATE) { - check_filename(f->name); - if (!(f->output = fopen(f->name, "w"))) { - DIE(("create_enter_dir: Could not open file \"%s\" for write\n", f->name)); + int32_t t; + for (t=0; tname[t]) { + if (!overwrite) { + int x = 0; + char *temp = (char*) pst_malloc (strlen(f->name[t])+10); //enough room for 10 digits + + sprintf(temp, "%s", f->name[t]); + check_filename(temp); + while ((f->output[t] = fopen(temp, "r"))) { + DEBUG_INFO(("need to increase filename because one already exists with that name\n")); + DEBUG_INFO(("- increasing it to %s%d\n", f->name, x)); + x++; + sprintf(temp, "%s%08d", f->name, x); + DEBUG_INFO(("- trying \"%s\"\n", f->name)); + if (x == 99999999) { + DIE(("create_enter_dir: Why can I not create a folder %s? I have tried %i extensions...\n", f->name, x)); + } + fclose(f->output[t]); + } + if (x > 0) { //then the f->name should change + free (f->name[t]); + f->name[t] = temp; + } else { + free(temp); + } + } + check_filename(f->name[t]); + if (!(f->output[t] = fopen(f->name[t], "w"))) { + DIE(("create_enter_dir: Could not open file \"%s\" for write\n", f->name[t])); + } + DEBUG_INFO(("f->name = %s\nitem->folder_name = %s\n", f->name[t], item->file_as.str)); + } } } DEBUG_RET(); } void close_enter_dir(struct file_ll *f) { + int32_t t; DEBUG_INFO(("processed item count for folder %s is %i, skipped %i, total %i \n", f->dname, f->item_count, f->skip_count, f->stored_count)); if (output_mode != OUTPUT_QUIET) { pst_debug_lock(); printf("\t\"%s\" - %i items done, %i items skipped.\n", f->dname, f->item_count, f->skip_count); fflush(stdout); pst_debug_unlock(); } - if (f->output) { - if (mode == MODE_SEPARATE) DEBUG_WARN(("close_enter_dir finds open separate file\n")); - struct stat st; - fclose(f->output); - stat(f->name, &st); - if (!st.st_size) { - DEBUG_WARN(("removing empty output file %s\n", f->name)); - remove(f->name); + for (t=0; toutput[t]) { + if (mode == MODE_SEPARATE) DEBUG_WARN(("close_enter_dir finds open separate file\n")); + struct stat st; + fclose(f->output[t]); + stat(f->name[t], &st); + if (!st.st_size) { + DEBUG_WARN(("removing empty output file %s\n", f->name[t])); + remove(f->name[t]); + } + f->output[t] = NULL; } - f->output = NULL; + free(f->name[t]); + f->name[t] = NULL; } - free(f->name); free(f->dname); if (mode == MODE_KMAIL) close_kmail_dir(); else if (mode == MODE_RECURSE) { if (mode_thunder) { FILE *type_file = fopen(".size", "w"); fprintf(type_file, "%i %i\n", f->item_count, f->stored_count); fclose(type_file); } close_recurse_dir(); } else if (mode == MODE_SEPARATE) close_separate_dir(); } diff --git a/xml/libpst.in b/xml/libpst.in index bc423bd..25b374d 100644 --- a/xml/libpst.in +++ b/xml/libpst.in @@ -1,2038 +1,2041 @@ @PACKAGE@ Utilities - Version @VERSION@ Packages The various source and binary packages are available at http://www.five-ten-sg.com/@PACKAGE@/packages/. The most recent documentation is available at http://www.five-ten-sg.com/@PACKAGE@/. The most recent developer documentation for the shared library is available at http://www.five-ten-sg.com/@PACKAGE@/devel/. A Mercurial source code repository for this project is available at http://hg.five-ten-sg.com/@PACKAGE@/. This version can now convert both 32 bit Outlook files (pre 2003), and the 64 bit Outlook 2003 pst files. Utilities are supplied to convert email messages to both mbox and MH mailbox formats, and to DII load file format for use with many of the CT Summation products. Contacts can be converted to a simple list, to vcard format, or to ldif format for import to an LDAP server. The libpff project has some excellent documentation of the pst file format. - 2015-03-09 + 2016-08-29 readpst 1 readpst @VERSION@ readpst convert PST (MS Outlook Personal Folders) files to mbox and other formats Synopsis readpst pstfile Description readpst is a program that can read an Outlook PST (Personal Folders) file and convert it into an mbox file, a format suitable for KMail, a recursive mbox structure, or separate emails. Options -C default-charset Set the character set to be used for items with an unspecified character set. -D Include deleted items in the output. -M Output messages in MH (rfc822) format as separate files. This will create folders as named in the PST file, and will put each email together with any attachments into its own file. These files will be numbered from 1 to n with no leading zeros. This format has no from quoting. -S Output messages into separate files. This will create folders as named in the PST file, and will put each email in its own file. These files will be numbered from 1 to n with no leading zeros. Attachments will also be saved in the same folder as the email message. The attachments for message $m are saved as $m-$name where $name is (the original name of the attachment, or 'attach$n' if the attachment had no name), where $n is another sequential index with no leading zeros. This format has no from quoting. -V Show program version and exit. -a attachment-extension-list Set the list of acceptable attachment extensions. Any attachment that does not have an extension on this list will be discarded. All attachments are acceptable if the list is empty, or this option is not specified. -b Do not save the attachments for the RTF format of the email body. -c format Set the Contact output mode. Use -cv for vcard format or -cl for an email list. -d debug-file Specify name of debug log file. The log file is now an ascii file, instead of the binary file used in previous versions. -e Same as the M option, but each output file will include an extension from (.eml, .ics, .vcf). This format has no from quoting. -h Show summary of options and exit. -j jobs Specifies the maximum number of parallel jobs. Specify 0 to suppress running parallel jobs. Folders may be processed in parallel. Output formats that place each mail message in a separate file (-M, -S, -e) may process the contents of individual folders in parallel. -k Changes the output format to KMail. This format uses mboxrd from quoting. -m Same as the e option, but write .msg files also -o output-directory Specifies the output directory. The directory must already exist, and is entered after the PST file is opened, but before any processing of files commences. -q Changes to silent mode. No feedback is printed to the screen, except for error messages. -r - Changes the output format to Recursive. This will create folders as - named in the PST file, and will put all emails in a file called "mbox" - inside each folder. These files are then compatible with all - mbox-compatible email clients. This format uses mboxrd from quoting. + Changes the output format to Recursive. This will create folders + as named in the PST file, and will put all emails in a file called + "mbox" inside each folder. Appointments go into a file called + "calendar", address book entries go into a file called "contacts", + and journal entries go into a file called "journal". These files + are then compatible with all mbox-compatible email clients. This + format uses mboxrd from quoting. -t output-type-codes Specifies the item types that are processed. The argument is a sequence of single letters from (e,a,j,c) for (email, appointment, journal, contact) types. The default is to process all item types. -u Sets Thunderbird mode, a submode of recursive mode. This causes two extra .type and .size meta files to be created. This format uses mboxrd from quoting. -w Overwrite any previous output files. Beware: When used with the -S switch, this will remove all files from the target folder before writing. This is to keep the count of emails and attachments correct. -8 Output bodies in UTF-8, rather than original encoding, if a UTF-8 version is available. From Quoting Output formats that place each mail message in a separate file (-M, -S, -e, -m) don't do any from quoting. Output formats that place multiple email messages in a single file (-k, -r, -u) now use mboxrd from quoting rules. If none of those switches are specified, the default output format uses mboxrd from quoting rules, since it produces multiple email messages in a single file. Earlier versions used mboxo from quoting rules for all output formats. Author This manual page was originally written by Dave Smith <dave.s@earthcorp.com>, and updated by Joe Nahmias <joe@nahmias.net> for the Debian GNU/Linux system (but may be used by others). It was subsequently updated by Brad Hards <bradh@frogmouth.net>, and converted to xml format by Carl Byington <carl@five-ten-sg.com>. Copyright Copyright (C) 2002 by David Smith <dave.s@earthcorp.com>. XML version Copyright (C) 2008 by 510 Software Group <carl@five-ten-sg.com>. This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 2, or (at your option) any later version. You should have received a copy of the GNU General Public License along with this program; see the file COPYING. If not, please write to the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. Version @VERSION@ - 2015-03-09 + 2016-08-29 lspst 1 lspst @VERSION@ lspst list PST (MS Outlook Personal Folders) file data Synopsis lspst pstfile Options -V Show program version and exit. -d debug-file Specify name of debug log file. The log file is now an ascii file, instead of the binary file used in previous versions. -h Show summary of options and exit. Description lspst is a program that can read an Outlook PST (Personal Folders) file and produce a simple listing of the data (contacts, email subjects, etc). Author lspst was written by Joe Nahmias <joe@nahmias.net> based on readpst. This man page was written by 510 Software Group <carl@five-ten-sg.com>. Copyright Copyright (C) 2004 by Joe Nahmias <joe@nahmias.net>. This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 2, or (at your option) any later version. You should have received a copy of the GNU General Public License along with this program; see the file COPYING. If not, please write to the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. Version @VERSION@ - 2015-03-09 + 2016-08-29 pst2ldif 1 pst2ldif @VERSION@ pst2ldif extract contacts from a MS Outlook .pst file in .ldif format Synopsis pst2ldif pstfilename Options -V Show program version. Subsequent options are then ignored. -b ldap-base Sets the ldap base value used in the dn records. You probably want to use something like "o=organization, c=US". -c class Sets the objectClass values for the contact items. This class needs to be defined in the schema used by your LDAP server, and at a minimum it must contain the ldap attributes given below. This option may be specified multiple times to generate entries with multiple object classes. -d debug-file Specify name of debug log file. The log file is now an ascii file, instead of the binary file used in previous versions. -l extra-line Specify an extra line to be added to each ldap entry. This option may be specified multiple times to add multiple lines to each ldap entry. -o Use the old ldap schema, rather than the default new ldap schema. The old schema generates multiple postalAddress attributes for a single entry. The new schema generates a single postalAddress (and homePostalAddress when available) attribute with $ delimiters as specified in RFC4517. Using the old schema also generates two extra leading entries, one for "dn:ldap base", and one for "dn: cn=root, ldap base". -h Show summary of options. Subsequent options are then ignored. Description pst2ldif reads the contact information from a MS Outlook .pst file and produces a .ldif file that may be used to import those contacts into an LDAP database. The following ldap attributes are generated for the old ldap schema: cn givenName sn personalTitle company mail postalAddress l st postalCode c homePhone telephoneNumber facsimileTelephoneNumber mobile description The following attributes are generated for the new ldap schema: cn givenName sn title o mail postalAddress homePostalAddress l st postalCode c homePhone telephoneNumber facsimileTelephoneNumber mobile description labeledURI Copyright Copyright (C) 2008 by 510 Software Group <carl@five-ten-sg.com> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 2, or (at your option) any later version. You should have received a copy of the GNU General Public License along with this program; see the file COPYING. If not, please write to the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. Version @VERSION@ - 2015-03-09 + 2016-08-29 pst2dii 1 pst2dii @VERSION@ pst2dii extract email messages from a MS Outlook .pst file in DII load format Synopsis pst2dii -f ttf-font-file pstfilename Options -B bates-prefix Sets the bates prefix string. The bates sequence number is appended to this string, and printed on each page. -O dii-output-file Name of the output DII load file. -V Show program version. Subsequent options are then ignored. -b bates-number Starting bates sequence number. The default is zero. -c bates-color Font color for the bates stamp on each page, specified as 6 hex digits as rrggbb values. The default is ff0000 for bright red. -d debug-file Specify name of debug log file. The log file is now an ascii file, instead of the binary file used in previous versions. -f ttf-font-file Specify name of a true type font file. This should be a fixed pitch font. -h Show summary of options. Subsequent options are then ignored. -o output-directory Specifies the output directory. The directory must already exist. Description pst2dii reads the email messages from a MS Outlook .pst file and produces a DII load file that may be used to import message summaries into a Summation DII system. The DII output file contains references to the image and attachment files in the output directory. Copyright Copyright (C) 2008 by 510 Software Group <carl@five-ten-sg.com> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 2, or (at your option) any later version. You should have received a copy of the GNU General Public License along with this program; see the file COPYING. If not, please write to the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. Version @VERSION@ - 2015-03-09 + 2016-08-29 outlook.pst 5 outlook.pst format of MS Outlook .pst file Synopsis outlook.pst Overview Low level or primitive items in a .pst file are identified by an I_ID value. Higher level or composite items in a .pst file are identified by a D_ID value. There are two separate b-trees indexed by these I_ID and D_ID values. Starting with Outlook 2003, the file format changed from one with 32 bit pointers, to one with 64 bit pointers. We describe both formats here. 32 bit File Header The 32 bit file header is located at offset 0 in the .pst file. We only support index types 0x0e, 0x0f, 0x15, and 0x17, and encryption types 0x00, 0x01 and 0x02. Index type 0x0e is the older 32 bit Outlook format. Index type 0x0f seems to be rare, and so far the data seems to be identical to that in type 0x0e files. Index type 0x17 is the newer 64 bit Outlook format. Index type 0x15 seems to be rare, and according to the libpff project should have the same format as type 0x17 files. It was found in a 64-bit pst file created by Visual Recovery. It may be that index types less than 0x10 are 32 bit, and index types greater than or equal to 0x10 are 64 bit, and the low order four bits of the index type is some subtype or minor version number. Encryption type 0x00 is no encryption, type 0x01 is "compressible" encryption which is a simple substitution cipher, and type 0x02 is "strong" encryption, which is a simple three rotor Enigma cipher from WWII. offsetIndex1 is the file offset of the root of the index1 b-tree, which contains (I_ID, offset, size, unknown) tuples for each item in the file. backPointer1 is the value that should appear in the parent pointer of that root node. offsetIndex2 is the file offset of the root of the index2 b-tree, which contains (D_ID, DESC-I_ID, TREE-I_ID, PARENT-D_ID) tuples for each item in the file. backPointer2 is the value that should appear in the parent pointer of that root node. 64 bit File Header The 64 bit file header is located at offset 0 in the .pst file. 32 bit Index 1 Node The 32 bit index1 b-tree nodes are 512 byte blocks with the following format. The itemCount specifies the number of 12 byte records that are active. The nodeLevel is non-zero for this style of nodes. The leaf nodes have a different format. The backPointer must match the backPointer from the triple that pointed to this node. Each item in this node is a triple of (I_ID, backPointer, offset) where the offset points to the next deeper node in the tree, the backPointer value must match the backPointer in that deeper node, and I_ID is the lowest I_ID value in the subtree. 64 bit Index 1 Node The 64 bit index1 b-tree nodes are 512 byte blocks with the following format. The itemCount specifies the number of 24 byte records that are active. The nodeLevel is non-zero for this style of nodes. The leaf nodes have a different format. The backPointer must match the backPointer from the triple that pointed to this node. Each item in this node is a triple of (I_ID, backPointer, offset) where the offset points to the next deeper node in the tree, the backPointer value must match the backPointer in that deeper node, and I_ID is the lowest I_ID value in the subtree. 32 bit Index 1 Leaf Node The 32 bit index1 b-tree leaf nodes are 512 byte blocks with the following format. The itemCount specifies the number of 12 byte records that are active. The nodeLevel is zero for these leaf nodes. The backPointer must match the backPointer from the triple that pointed to this node. Each item in this node is a tuple of (I_ID, offset, size, unknown) The two low order bits of the I_ID value seem to be flags. I have never seen a case with bit zero set. Bit one indicates that the item is not encrypted. Note that references to these I_ID values elsewhere may have the low order bit set (and I don't know what that means), but when we do the search in this tree we need to clear that bit so that we can find the correct item. 64 bit Index 1 Leaf Node The 64 bit index1 b-tree leaf nodes are 512 byte blocks with the following format. The itemCount specifies the number of 24 byte records that are active. The nodeLevel is zero for these leaf nodes. The backPointer must match the backPointer from the triple that pointed to this node. Each item in this node is a tuple of (I_ID, offset, size, unknown) The two low order bits of the I_ID value seem to be flags. I have never seen a case with bit zero set. Bit one indicates that the item is not encrypted. Note that references to these I_ID values elsewhere may have the low order bit set (and I don't know what that means), but when we do the search in this tree we need to clear that bit so that we can find the correct item. 32 bit Index 2 Node The 32 bit index2 b-tree nodes are 512 byte blocks with the following format. The itemCount specifies the number of 12 byte records that are active. The nodeLevel is non-zero for this style of nodes. The leaf nodes have a different format. The backPointer must match the backPointer from the triple that pointed to this node. Each item in this node is a triple of (D_ID, backPointer, offset) where the offset points to the next deeper node in the tree, the backPointer value must match the backPointer in that deeper node, and D_ID is the lowest D_ID value in the subtree. 64 bit Index 2 Node The 64 bit index2 b-tree nodes are 512 byte blocks with the following format. The itemCount specifies the number of 24 byte records that are active. The nodeLevel is non-zero for this style of nodes. The leaf nodes have a different format. The backPointer must match the backPointer from the triple that pointed to this node. Each item in this node is a triple of (D_ID, backPointer, offset) where the offset points to the next deeper node in the tree, the backPointer value must match the backPointer in that deeper node, and D_ID is the lowest D_ID value in the subtree. 32 bit Index 2 Leaf Node The 32 bit index2 b-tree leaf nodes are 512 byte blocks with the following format. The itemCount specifies the number of 16 byte records that are active. The nodeLevel is zero for these leaf nodes. The backPointer must match the backPointer from the triple that pointed to this node. Each item in this node is a tuple of (D_ID, DESC-I_ID, TREE-I_ID, PARENT-D_ID) The DESC-I_ID points to the main data for this item (Associated Descriptor Items 0x7cec, 0xbcec, or 0x0101) via the index1 tree. The TREE-I_ID is zero or points to an Associated Tree Item 0x0002 via the index1 tree. The PARENT-D_ID points to the parent of this item in this index2 tree. 64 bit Index 2 Leaf Node The 64 bit index2 b-tree leaf nodes are 512 byte blocks with the following format. The itemCount specifies the number of 32 byte records that are active. The nodeLevel is zero for these leaf nodes. The backPointer must match the backPointer from the triple that pointed to this node. Each item in this node is a tuple of (D_ID, DESC-I_ID, TREE-I_ID, PARENT-D_ID) The DESC-I_ID points to the main data for this item (Associated Descriptor Items 0x7cec, 0xbcec, or 0x0101) via the index1 tree. The TREE-I_ID is zero or points to an Associated Tree Item 0x0002 via the index1 tree. The PARENT-D_ID points to the parent of this item in this index2 tree. 32 bit Associated Tree Item 0x0002 A D_ID value may point to an entry in the index2 tree with a non-zero TREE-I_ID which points to this descriptor block via the index1 tree. It maps local ID2 values (referenced in the main data for the original D_ID item) to I_ID values. This descriptor block contains triples of (ID2, I_ID, CHILD-I_ID) where the local ID2 data can be found via I_ID, and CHILD-I_ID is either zero or it points to another Associated Tree Item via the index1 tree. In the above 32 bit leaf node, we have a tuple of (0x61, 0x02a82c, 0x02a836, 0) 0x02a836 is the I_ID of the associated tree, and we can lookup that I_ID value in the index1 b-tree to find the (offset,size) of the data in the .pst file. 64 bit Associated Tree Item 0x0002 This descriptor block contains a tree that maps local ID2 values to I_ID entries, similar to the 32 bit version described above. Associated Descriptor Item 0xbcec Contains information about the item, which may be email, contact, or other outlook types. In the above leaf node, we have a tuple of (0x21, 0x00e638, 0, 0) 0x00e638 is the I_ID of the associated descriptor, and we can lookup that I_ID value in the index1 b-tree to find the (offset,size) of the data in the .pst file. This descriptor is eventually decoded to a list of MAPI elements. Note the signature of 0xbcec. There are other descriptor block formats with other signatures. Note the indexOffset of 0x013c - starting at that position in the descriptor block, we have an array of two byte integers. The first integer (0x000b) is a (count-1) of the number of overlapping pairs following the count. The first pair is (0, 0xc), the next pair is (0xc, 0x14) and the last (12th) pair is (0x123, 0x13b). These pairs are (start,end+1) offsets of items in this block. So we have count+2 integers following the count value. Note the b5offset of 0x0020, which is a type that I will call an index reference. Such index references have at least two different forms, and may point to data either in this block, or in some other block. External pointer references have the low order 4 bits all set, and are ID2 values that can be used to fetch data. This value of 0x0020 is an internal pointer reference, which needs to be right shifted by 4 bits to become 0x0002, which is then a byte offset to be added to the above indexOffset plus two (to skip the count), so it points to the (0xc, 0x14) pair. So far we have only described internal index references where the high order 16 bits are zero. That suffices for single descriptor blocks. But in the case of the type 0x0101 descriptor block, we have an array of subblocks. In this case, the high order 16 bits of an internal index reference are used to select the subblock. Each subblock starts with a 16 bit indexOffset which points to the count and array of 16 bit integer pairs which are offsets in the current subblock. Finally, we have the offset and size of the "b5" block located at offset 0xc with a size of 8 bytes in this descriptor block. The "b5" block has the following format: Note the descoffset of 0x0040, which again is an index reference. In this case, it is an internal pointer reference, which needs to be right shifted by 4 bits to become 0x0004, which is then a byte offset to be added to the above indexOffset plus two (to skip the count), so it points to the (0x14, 0x7c) pair. The datasize (6) plus the b5 code (02) gives the size of the entries, in this case 8 bytes. We now have the offset 0x14 of the descriptor array, composed of 8 byte entries that describe MAPI elements. Each descriptor entry has the following format: For some reference types (2, 3, 0xb) the value is used directly. Otherwise, the value is an index reference, which is either an ID2 value, or an offset, to be right shifted by 4 bits and used to fetch a pair from the index table to find the offset and size of the item in this descriptor block. The following reference types are known, but not all of these are implemented in the code yet. The following item types are known, but not all of these are implemented in the code yet. Associated Descriptor Item 0x7cec This style of descriptor block is similar to the 0xbcec format. This descriptor is also eventually decoded to a list of MAPI elements. Note the signature of 0x7cec. There are other descriptor block formats with other signatures. Note the indexOffset of 0x017a - starting at that position in the descriptor block, we have an array of two byte integers. The first integer (0x0006) is a (count-1) of the number of overlapping pairs following the count. The first pair is (0, 0xc), the next pair is (0xc, 0x14) and the last (7th) pair is (0x160, 0x179). These pairs are (start,end+1) offsets of items in this block. So we have count+2 integers following the count value. Note the 7coffset of 0x0040, which is an index reference. In this case, it is an internal reference pointer, which needs to be right shifted by 4 bits to become 0x0004, which is then a byte offset to be added to the above indexOffset plus two (to skip the count), so it points to the (0x14, 0xea) pair. We have the offset and size of the "7c" block located at offset 0x14 with a size of 214 bytes in this case. The "7c" block starts with a header with the following format: Note the b5Offset of 0x0020, which is an index reference. In this case, it is an internal reference pointer, which needs to be right shifted by 4 bits to become 0x0002, which is then a byte offset to be added to the above indexOffset plus two (to skip the count), so it points to the (0xc, 0x14) pair. Finally, we have the offset and size of the "b5" block located at offset 0xc with a size of 8 bytes in this descriptor block. The "b5" block has the following format: Note the descoffset of 0x0060, which again is an index reference. In this case, it is an internal pointer reference, which needs to be right shifted by 4 bits to become 0x0006, which is then a byte offset to be added to the above indexOffset plus two (to skip the count), so it points to the (0xea, 0xf0) pair. The datasize (2) plus the b5 code (04) gives the size of the entries, in this case 6 bytes. We now have the offset 0xea of an unused block of data in an unknown format, composed of 6 byte entries. That gives us (0xf0 - 0xea)/6 = 1, so we have a recordCount of one. We have seen cases where the descoffset in the b5 block is zero, and the index2Offset in the 7c block is zero. This has been seen for objects that seem to be attachments on messages that have been read. Before the message was read, it did not have any attachments. Note the index2Offset above of 0x0080, which again is an index reference. In this case, it is an internal pointer reference, which needs to be right shifted by 4 bits to become 0x0008, which is then a byte offset to be added to the above indexOffset plus two (to skip the count), so it points to the (0xf0, 0x155) pair. This is an array of tables of four byte integers. We will call these the IND2 tables. The size of each of these tables is specified by the recordSize field of the "7c" header. The number of these tables is the above recordCount value derived from the "b5" block. Now the remaining data in the "7c" block after the header starts at offset 0x2a. There should be itemCount 8 byte items here, with the following format: The ind2Offset is a byte offset into the current IND2 table of some value. If that is a four byte integer value, then once we fetch that, we have the same triple (item type, reference type, value) as we find in the 0xbcec style descriptor blocks. If not, then this value is used directly. These 8 byte descriptors are processed recordCount times, each time using the next IND2 table. The item and reference types are as described above for the 0xbcec format descriptor block. 32 bit Associated Descriptor Item 0x0101 This descriptor block contains a list of I_ID values. It is used when an I_ID (that would normally point to a type 0x7cec or 0xbcec descriptor block) contains more data than can fit in any single descriptor of those types. In this case, it points to a type 0x0101 block, which contains a list of I_ID values that themselves point to the actual descriptor blocks. The total length value in the 0x0101 header is the sum of the lengths of the blocks pointed to by the list of I_ID values. The result is an array of subblocks, that may contain index references where the high order 16 bits specify which descriptor subblock to use. Only the first descriptor subblock contains the signature (0xbcec or 0x7cec). 64 bit Associated Descriptor Item 0x0101 This descriptor block contains a list of I_ID values, similar to the 32 bit version described above.