diff --git a/ChangeLog b/ChangeLog index af36e0d..ca10126 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,954 +1,954 @@ LibPST 0.6.76 (2021-03-27) =============================== * Stuart C. Naifeh - fix rfc2231 encoding when saving messages to both .eml and .msg formats. LibPST 0.6.75 (2020-03-22) =============================== * Markus Schnalke - fix from Debian for vcard version format. LibPST 0.6.74 (2020-01-12) =============================== * Paul Wise - many changes for Debian. LibPST 0.6.73 (2019-07-25) =============================== * Tim Dufrane - fix segfault in pst_close() LibPST 0.6.72 (2018-08-01) =============================== * Alfredo Esteban - add -l and -f options to lspst. * fix bydays recurring appointment, allow all 7 days * update for Fedora Python packaging LibPST 0.6.71 (2017-07-21) =============================== * Zachary Travis - Add support for the OST 2013 format, and Content-Disposition filename key fix for outlook compatibility LibPST 0.6.70 (2017-02-08) =============================== * Jeffrey Morlan - pst_getID2 must not recurse into children LibPST 0.6.69 (2016-10-29) =============================== * fix bugs in code allowing folders containing multiple item types 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 * 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 systems 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 through 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 message 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 uninitialized 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, a lot 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 embedded items. They are not fully re-created using Mime-types, but are accessible with the -S switch (which saves everything as separate 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 "Separate". 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 separate files counting from 0 upwards, in a folder named as the PST folder. When an email has an attachment, it is saved as a separate 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 enhancement 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 caesar 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 merely stored there. This means that the readpst application is able to convert PST files without knowing the password. Microsoft have some explaining 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/contrib/Makefile b/contrib/Makefile index becd262..ccb0427 100644 --- a/contrib/Makefile +++ b/contrib/Makefile @@ -1,89 +1,89 @@ #!/usr/bin/make -f CFLAGS ?= -g -Wall PREFIX ?= /usr/local INSTALL ?= install #---------------- Do not modify below this point ------------------ INSTALL_DIR := $(INSTALL) -p -d -o root -g root -m 0755 INSTALL_FILE := $(INSTALL) -p -o root -g root -m 0644 INSTALL_PROGRAM := $(INSTALL) -p -o root -g root -m 0755 # -s INSTALL_SCRIPT := $(INSTALL) -p -o root -g root -m 0755 VERSION = $(shell cat VERSION) CFLAGS += -DVERSION=\"$(VERSION)\" CPPFLAGS += -DVERSION=\"$(VERSION)\" DOCS := AUTHORS ChangeLog CREDITS FILE-FORMAT FILE-FORMAT.html LICENSE TODO \ VERSION DISTFILES := $(DOCS) Makefile setup1.vdproj XGetopt.c XGetopt.h common.h \ debug.c define.h dumpblocks.c getidblock.c libpst.c libpst.h \ libstrfunc.c libstrfunc.h lspst.c lzfu.c lzfu.h moz-script \ readlog.vcproj readpst.1 readpst.c readpstlog.1 readpstlog.c \ testdebug.c timeconv.c timeconv.h w32pst.sln w32pst.vcproj \ nick2ldif.cpp pst2ldif.cpp PROGS := lspst readpst readpstlog pst2ldif nick2ldif ALL_PROGS := $(PROGS) dumpblocks getidblock testdebug all: $(PROGS) XGetopt.o: XGetopt.h debug.o: define.h dumpblocks.o: define.h getidblock.o: XGetopt.h define.h libpst.h libpst.o: define.h libstrfunc.h libpst.h timeconv.h libstrfunc.o: libstrfunc.h lspst.o: libpst.h timeconv.h lzfu.o: define.h libpst.h lzfu.h readpst.o: XGetopt.h libstrfunc.h define.h libpst.h common.h timeconv.h lzfu.h pst2ldif.o: XGetopt.h libstrfunc.h define.h libpst.h common.h timeconv.h lzfu.h nick2ldif.o: XGetopt.h libstrfunc.h define.h libpst.h common.h timeconv.h lzfu.h readpstlog.o: XGetopt.h define.h testdebug.o: define.h timeconv.o: timeconv.h common.h readpst: readpst.o libpst.o timeconv.o libstrfunc.o debug.o lzfu.o lspst: debug.o libpst.o libstrfunc.o lspst.o timeconv.o getidblock: getidblock.o libpst.o debug.o libstrfunc.o testdebug: testdebug.o debug.o readpstlog: readpstlog.o debug.o dumpblocks: dumpblocks.o libpst.o debug.o libstrfunc.o pst2ldif: pst2ldif.o libpst.o timeconv.o libstrfunc.o debug.o lzfu.o g++ ${CFLAGS} pst2ldif.cpp -o pst2ldif libpst.o timeconv.o libstrfunc.o debug.o lzfu.o nick2ldif: nick2ldif.o libpst.o timeconv.o libstrfunc.o debug.o lzfu.o g++ ${CFLAGS} nick2ldif.cpp -o nick2ldif libpst.o timeconv.o libstrfunc.o debug.o lzfu.o clean: rm -f core *.o readpst.log $(ALL_PROGS) *~ MANIFEST distclean: clean rm -f libpst-*.tar.gz install: all $(INSTALL_DIR) $(DESTDIR)$(PREFIX)/bin $(INSTALL_PROGRAM) readpst{,log} $(DESTDIR)$(PREFIX)/bin $(INSTALL_DIR) $(DESTDIR)$(PREFIX)/share/man/man1 $(INSTALL_FILE) readpst{,log}.1 $(DESTDIR)$(PREFIX)/share/man/man1/ $(INSTALL_DIR) $(DESTDIR)$(PREFIX)/share/doc/libpst $(INSTALL_FILE) $(DOCS) $(DESTDIR)$(PREFIX)/share/doc/libpst/ uninstall: -rm -f $(DESTDIR)$(PREFIX)/bin/readpst{,log} -rm -f $(DESTDIR)$(PREFIX)/share/man/man1/readpst{,log}.1 # stolen from ESR's Software Release Practices HOWTO available at: -# http://en.tldp.org/HOWTO/Software-Release-Practice-HOWTO/distpractice.html +# https://tldp.org/HOWTO/Software-Release-Practice-HOWTO/distpractice.html MANIFEST: Makefile @ls $(DISTFILES) | sed s:^:libpst-$(VERSION)/: >MANIFEST tarball libpst-$(VERSION).tar.gz: MANIFEST $(DISTFILES) @(cd ..; ln -s libpst libpst-$(VERSION)) (cd ..; tar -czvf libpst/libpst-$(VERSION).tar.gz `cat libpst/MANIFEST`) @(cd ..; rm libpst-$(VERSION)) @rm -f MANIFEST .PHONY: clean distclean uninstall install tarball diff --git a/contrib/moz-script b/contrib/moz-script index 492868a..fcad92c 100755 --- a/contrib/moz-script +++ b/contrib/moz-script @@ -1,36 +1,36 @@ #!/bin/bash # Helper script to convert to Mozilla mail format # Author: David Binard -# Taken from: +# Taken from: # Note: this assumes readpst was run with the -r # (recursive) option. if [ "$#" != 1 ]; then echo "Usage: `basename $0` " exit 1 fi process_dir() { echo Processing directory "$1" for item in "$1/"*; do if [ -d "$item" ]; then mv "$item" "$item.sbd" touch "$item" process_dir "$item.sbd" elif [ "`basename \"$item\"`" = mbox ]; then mv "$item" "${item%%.sbd/mbox}" else echo ERROR: invalid item "$item" exit 1 fi done } item="$1" mv "$item" "$item.sbd" touch "$item" process_dir "$item.sbd" diff --git a/libpst.spec.in b/libpst.spec.in index aa66a8e..caf5b84 100644 --- a/libpst.spec.in +++ b/libpst.spec.in @@ -1,698 +1,698 @@ %if "%{?dist}" == ".el8" %define fedora 32 %endif %if 0%{?fedora} > 27 || 0%{?rhel} >= 9 %global use_python3 1 %define __python %{__python3} %endif %if 0%{?rhel} >= 9 %global with_dii 0 %else %global with_dii 1 %endif Summary: Utilities to convert Outlook .pst files to other formats Name: @PACKAGE@ Version: @VERSION@ Release: 1%{?dist} License: GPLv2+ URL: https://github.com/pst-format/%{name}/ Source: %{url}/packages/%{name}-%{version}.tar.gz BuildRequires: make BuildRequires: libtool gcc-c++ BuildRequires: gd-devel zlib-devel boost-devel libgsf-devel gettext-devel %if 0%{with_dii} BuildRequires: ImageMagick %endif %if 0%{?use_python3} BuildRequires: python3 python3-devel boost-python3 boost-python3-devel Requires: boost-python3 %else BuildRequires: python-devel %endif Requires: libgsf gettext Requires: %{name}-libs%{?_isa} = %{version}-%{release} %if 0%{with_dii} Requires: ImageMagick%{?_isa} %endif %{!?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)")} %if 0%{with_dii} %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. %else %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. %endif %package libs Summary: Shared library used by the pst utilities %description libs The libpst-libs package contains the shared library used by the pst utilities. %if 0%{?use_python3} %package -n python3-%{name} Requires: python3 Provides: %{name}-python = %{version}-%{release} %else %package python Requires: python %endif Summary: Python bindings for libpst Requires: %{name}-libs%{?_isa} = %{version}-%{release} %if 0%{?fedora} >= 20 || 0%{?rhel} >= 9 %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 %if 0%{?use_python3} %description -n python3-%{name} %else %description python %endif 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 Requires: pkgconfig Requires: %{name}-libs%{?_isa} = %{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 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 %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 -fiv %configure --enable-libpst-shared \ %if 0%{with_dii} --enable-dii \ %else --disable-dii \ %endif --with-boost-python=boost_python%{python3_version_nodots} %if 0%{?use_python3} %make_build %else make %{?_smp_mflags} %endif %install %if 0%{?use_python3} %make_install %else rm -rf $RPM_BUILD_ROOT make DESTDIR=$RPM_BUILD_ROOT install %endif #Remove libtool archives. find %{buildroot} -name '*.la' -or -name '*.a' | xargs rm -f mv %{buildroot}%{_datadir}/doc/%{name}-%{version} %{buildroot}%{_datadir}/doc/%{name} # Remove pst2dii man page, when it's not built %if !0%{with_dii} rm %{buildroot}%{_mandir}/man1/pst2dii.1* %endif %if 0%{?use_python3} %ldconfig_scriptlets libs %else %post libs -p /sbin/ldconfig %postun libs -p /sbin/ldconfig %endif %files %{_bindir}/* %{_mandir}/man1/* %{_mandir}/man5/* %files libs %{_libdir}/libpst.so.* %doc COPYING %if 0%{?use_python3} %files -n python3-%{name} %defattr(-,root,root,-) %{python3_sitearch}/_*.so %else %files python %{python_sitearch}/_*.so %endif %files devel %{_libdir}/libpst.so %{_includedir}/%{name}-@LIBPST_SO_MAJOR@/ %{_libdir}/pkgconfig/libpst.pc %files devel-doc %{_datadir}/doc/%{name}/devel/ %files doc %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 * Sat Mar 27 2021 Carl Byington 0.6.76-1 - Stuart C. Naifeh - fix rfc2231 encoding when saving messages to both .eml and .msg formats. - fix template issue to build with gcc 11 * Tue Feb 02 2021 Milan Crha - 0.6.75-9 - Resolves: #1913613 (Disable DII (and ImageMagic dependency) for RHEL 9) * Tue Jan 26 2021 Fedora Release Engineering - 0.6.75-8 - Rebuilt for https://fedoraproject.org/wiki/Fedora_34_Mass_Rebuild * Fri Jan 22 2021 Jonathan Wakely - 0.6.75-7 - Rebuilt for Boost 1.75 * Tue Jul 28 2020 Merlin Mathesius - 0.6.75-6 - FTBFS fix: %%{__python} must now be explicitly defined * Tue Jul 28 2020 Fedora Release Engineering - 0.6.75-5 - Rebuilt for https://fedoraproject.org/wiki/Fedora_33_Mass_Rebuild * Thu Jul 16 2020 Merlin Mathesius - 0.6.75-4 - Cleanup conditionals for using python3 * Fri May 29 2020 Jonathan Wakely - 0.6.75-3 - Rebuilt for Boost 1.73 * Tue May 26 2020 Miro Hrončok - 0.6.75-2 - Rebuilt for Python 3.9 * Sun Mar 22 2020 Carl Byington 0.6.75-1 - Markus Schnalke - fix from Debian for vcard version format. * Wed Jan 29 2020 Fedora Release Engineering - 0.6.74-2 - Rebuilt for https://fedoraproject.org/wiki/Fedora_32_Mass_Rebuild * Sun Jan 12 2020 Carl Byington 0.6.74-1 - Paul Wise - many changes for debian: - Add missing linking with zlib and libpthread/librt - Use PKG_CHECK_MODULES to find the gsf-1 library - Fix usage of indefinite articles - Fix a number of spelling mistakes - Use plain make when building from Mercurial - Add operator and quotes to the AX_PYTHON_DEVEL parameter - Remove files copied in by autotools - Add AM_GNU_GETTEXT macros - Rename configure.in to configure.ac - add extern "C" to header for use with C++ code * Mon Aug 19 2019 Miro Hrončok - 0.6.72-6 - Rebuilt for Python 3.8 * Thu Jul 25 2019 Fedora Release Engineering - 0.6.72-5 - Rebuilt for https://fedoraproject.org/wiki/Fedora_31_Mass_Rebuild * Thu Jul 25 2019 Carl Byington 0.6.73-1 - Tim Dufrane - fix segfault in pst_close() * Sat Jun 08 2019 Leigh Scott - 0.6.72-4 - Add configure option for boost-python - Remove all old fedora conditionals - Update spec file to comply with packaging guidelines * Fri Feb 01 2019 Fedora Release Engineering - 0.6.72-3 - Rebuilt for https://fedoraproject.org/wiki/Fedora_30_Mass_Rebuild * Wed Jan 30 2019 Jonathan Wakely - 0.6.72-2 - Rebuilt for Boost 1.69 * Wed Aug 01 2018 Carl Byington 0.6.72-1 - allow all 7 days in bydays recurring appointment - update for Fedora Python packaging - Alfredo Esteban - add -l and -f options to lspst * Fri Jul 13 2018 Fedora Release Engineering - 0.6.71-8 - Rebuilt for https://fedoraproject.org/wiki/Fedora_29_Mass_Rebuild * Wed Feb 07 2018 Fedora Release Engineering - 0.6.71-7 - Rebuilt for https://fedoraproject.org/wiki/Fedora_28_Mass_Rebuild * Sun Aug 20 2017 Zbigniew Jędrzejewski-Szmek - 0.6.71-6 - Add Provides for the old name without %%_isa * Sat Aug 19 2017 Zbigniew Jędrzejewski-Szmek - 0.6.71-5 - Python 2 binary package renamed to python2-libpst See https://fedoraproject.org/wiki/FinalizingFedoraSwitchtoPython3 * Sat Aug 19 2017 Zbigniew Jędrzejewski-Szmek - 0.6.71-4 - Python 2 binary package renamed to python2-libpst See https://fedoraproject.org/wiki/FinalizingFedoraSwitchtoPython3 * Thu Aug 03 2017 Fedora Release Engineering - 0.6.71-3 - Rebuilt for https://fedoraproject.org/wiki/Fedora_27_Binutils_Mass_Rebuild * Wed Jul 26 2017 Fedora Release Engineering - 0.6.71-2 - Rebuilt for https://fedoraproject.org/wiki/Fedora_27_Mass_Rebuild * Fri Jul 21 2017 Carl Byington 0.6.71-1 - Fedora Python naming scheme changes - Zachary Travis - Add support for the OST 2013 format, and Content-Disposition filename key fix for outlook compatibility * Thu Jul 20 2017 Kalev Lember - 0.6.70-3 - Rebuilt for Boost 1.64 * Fri Jul 07 2017 Igor Gnatenko - 0.6.70-2 - Rebuild due to bug in RPM (RHBZ #1468476) * Wed Feb 08 2017 Carl Byington 0.6.70-1 - Jeffrey Morlan - pst_getID2 must not recurse into children * Fri Jan 27 2017 Jonathan Wakely - 0.6.69-2 - Rebuilt for Boost 1.63 * Sat Oct 29 2016 Carl Byington 0.6.69-1 - fix bugs in code allowing folders containing multiple item types * 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 - 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 - 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 +- initial spec file using autoconf and https://docs.fedoraproject.org/en-US/packaging-guidelines/ diff --git a/src/common.h b/src/common.h index a128b19..2a03790 100644 --- a/src/common.h +++ b/src/common.h @@ -1,54 +1,54 @@ #ifndef __PST_COMMON_H #define __PST_COMMON_H #include #include #include #include #if !defined(_MSC_VER) || (_MSC_VER >= 1800) #include #include #else typedef signed char int8_t; typedef unsigned char uint8_t; typedef unsigned short uint16_t; typedef short int16_t; typedef unsigned int uint32_t; typedef int int32_t; typedef unsigned long long uint64_t; typedef long long int64_t; #endif #ifndef _WIN32 typedef struct { uint32_t dwLowDateTime; uint32_t dwHighDateTime; } FILETIME; // According to Jan Wolter, sys/param.h is the most portable source of endian - // information on UNIX systems. see http://www.unixpapa.com/incnote/byteorder.html + // information on UNIX systems. see https://www.unixpapa.com/incnote/byteorder.html #include #else #include #endif #if defined(_WIN32) || defined(__DJGPP__) #ifndef LITTLE_ENDIAN #define LITTLE_ENDIAN 1234 #endif #ifndef BIG_ENDIAN #define BIG_ENDIAN 4321 #endif #define BYTE_ORDER LITTLE_ENDIAN #endif #endif #if defined (__SVR4) && defined (__sun) #define LITTLE_ENDIAN 1234 #define BYTE_ORDER LITTLE_ENDIAN #endif diff --git a/src/libpst.c b/src/libpst.c index 0a96570..36896b8 100644 --- a/src/libpst.c +++ b/src/libpst.c @@ -1,4664 +1,4664 @@ /*** * libpst.c * Part of the LibPST project * Written by David Smith * dave.s@earthcorp.com */ #include "define.h" #include "zlib.h" // switch to maximal packing for our own internal structures // use the same code as in libpst.h #ifdef _MSC_VER #pragma pack(push, 1) #endif #if defined(__GNUC__) || defined (__SUNPRO_C) || defined(__SUNPRO_CC) #pragma pack(1) #endif #define ASSERT(x) { if(!(x)) raise( SIGSEGV ); } #define INDEX_TYPE32 0x0E #define INDEX_TYPE32A 0x0F // unknown, but assumed to be similar for now #define INDEX_TYPE64 0x17 #define INDEX_TYPE64A 0x15 // https://github.com/libyal/libpff #define INDEX_TYPE4K 0x24 #define INDEX_TYPE_OFFSET (int64_t)0x0A #define FILE_SIZE_POINTER32 (int64_t)0xA8 #define INDEX_POINTER32 (int64_t)0xC4 #define INDEX_BACK32 (int64_t)0xC0 #define SECOND_POINTER32 (int64_t)0xBC #define SECOND_BACK32 (int64_t)0xB8 #define ENC_TYPE32 (int64_t)0x1CD #define FILE_SIZE_POINTER64 (int64_t)0xB8 #define INDEX_POINTER64 (int64_t)0xF0 #define INDEX_BACK64 (int64_t)0xE8 #define SECOND_POINTER64 (int64_t)0xE0 #define SECOND_BACK64 (int64_t)0xD8 #define ENC_TYPE64 (int64_t)0x201 #define FILE_SIZE_POINTER ((pf->do_read64) ? FILE_SIZE_POINTER64 : FILE_SIZE_POINTER32) #define INDEX_POINTER ((pf->do_read64) ? INDEX_POINTER64 : INDEX_POINTER32) #define INDEX_BACK ((pf->do_read64) ? INDEX_BACK64 : INDEX_BACK32) #define SECOND_POINTER ((pf->do_read64) ? SECOND_POINTER64 : SECOND_POINTER32) #define SECOND_BACK ((pf->do_read64) ? SECOND_BACK64 : SECOND_BACK32) #define ENC_TYPE ((pf->do_read64) ? ENC_TYPE64 : ENC_TYPE32) #define PST_SIGNATURE 0x4E444221 typedef struct pst_block_offset { uint16_t from; uint16_t to; } pst_block_offset; typedef struct pst_block_offset_pointer { char *from; char *to; int needfree; } pst_block_offset_pointer; typedef struct pst_holder { char **buf; FILE *fp; int base64; // bool, are we encoding into base64 int base64_line_count; // base64 bytes emitted on the current line size_t base64_extra; // count of bytes held in base64_extra_chars char base64_extra_chars[2]; // up to two pending unencoded bytes } pst_holder; typedef struct pst_subblock { char *buf; size_t read_size; size_t i_offset; } pst_subblock; typedef struct pst_subblocks { size_t subblock_count; pst_subblock *subs; } pst_subblocks; typedef struct pst_mapi_element { uint32_t mapi_id; char *data; uint32_t type; size_t size; char *extra; } pst_mapi_element; typedef struct pst_mapi_object { int32_t count_elements; // count of active elements int32_t orig_count; // originally allocated elements int32_t count_objects; // number of mapi objects in the list struct pst_mapi_element **elements; struct pst_mapi_object *next; } pst_mapi_object; typedef struct pst_desc32 { uint32_t d_id; uint32_t desc_id; uint32_t tree_id; uint32_t parent_d_id; } pst_desc32; typedef struct pst_index32 { uint32_t id; uint32_t offset; uint16_t size; int16_t u1; } pst_index32; struct pst_table_ptr_struct32{ uint32_t start; uint32_t u1; uint32_t offset; }; typedef struct pst_desc { uint64_t d_id; uint64_t desc_id; uint64_t tree_id; uint32_t parent_d_id; // not 64 bit uint32_t u1; // padding } pst_desc; typedef struct pst_index64 { uint64_t id; uint64_t offset; uint16_t size; int16_t u0; int32_t u1; } pst_index64; typedef struct pst_index { uint64_t id; uint64_t offset; uint16_t size; uint16_t inflated_size; int16_t u0; int32_t u1; } pst_index; struct pst_table_ptr_struct{ uint64_t start; uint64_t u1; uint64_t offset; }; typedef struct pst_block_header { uint16_t type; uint16_t count; } pst_block_header; typedef struct pst_id2_assoc32 { uint32_t id2; uint32_t id; uint32_t child_id; } pst_id2_assoc32; typedef struct pst_id2_assoc { uint32_t id2; // only 32 bit here uint16_t unknown1; uint16_t unknown2; uint64_t id; uint64_t child_id; } pst_id2_assoc; typedef struct pst_table3_rec32 { uint32_t id; } pst_table3_rec32; //for type 3 (0x0101) blocks typedef struct pst_table3_rec { uint64_t id; } pst_table3_rec; //for type 3 (0x0101) blocks typedef struct pst_block_hdr { uint16_t index_offset; uint16_t type; uint32_t offset; } pst_block_hdr; /** for "compressible" encryption, just a simple substitution cipher, * plaintext = comp_enc[ciphertext]; * for "strong" encryption, this is the first rotor of an Enigma 3 rotor cipher. */ static unsigned char comp_enc [] = { 0x47, 0xf1, 0xb4, 0xe6, 0x0b, 0x6a, 0x72, 0x48, 0x85, 0x4e, 0x9e, 0xeb, 0xe2, 0xf8, 0x94, 0x53, 0xe0, 0xbb, 0xa0, 0x02, 0xe8, 0x5a, 0x09, 0xab, 0xdb, 0xe3, 0xba, 0xc6, 0x7c, 0xc3, 0x10, 0xdd, 0x39, 0x05, 0x96, 0x30, 0xf5, 0x37, 0x60, 0x82, 0x8c, 0xc9, 0x13, 0x4a, 0x6b, 0x1d, 0xf3, 0xfb, 0x8f, 0x26, 0x97, 0xca, 0x91, 0x17, 0x01, 0xc4, 0x32, 0x2d, 0x6e, 0x31, 0x95, 0xff, 0xd9, 0x23, 0xd1, 0x00, 0x5e, 0x79, 0xdc, 0x44, 0x3b, 0x1a, 0x28, 0xc5, 0x61, 0x57, 0x20, 0x90, 0x3d, 0x83, 0xb9, 0x43, 0xbe, 0x67, 0xd2, 0x46, 0x42, 0x76, 0xc0, 0x6d, 0x5b, 0x7e, 0xb2, 0x0f, 0x16, 0x29, 0x3c, 0xa9, 0x03, 0x54, 0x0d, 0xda, 0x5d, 0xdf, 0xf6, 0xb7, 0xc7, 0x62, 0xcd, 0x8d, 0x06, 0xd3, 0x69, 0x5c, 0x86, 0xd6, 0x14, 0xf7, 0xa5, 0x66, 0x75, 0xac, 0xb1, 0xe9, 0x45, 0x21, 0x70, 0x0c, 0x87, 0x9f, 0x74, 0xa4, 0x22, 0x4c, 0x6f, 0xbf, 0x1f, 0x56, 0xaa, 0x2e, 0xb3, 0x78, 0x33, 0x50, 0xb0, 0xa3, 0x92, 0xbc, 0xcf, 0x19, 0x1c, 0xa7, 0x63, 0xcb, 0x1e, 0x4d, 0x3e, 0x4b, 0x1b, 0x9b, 0x4f, 0xe7, 0xf0, 0xee, 0xad, 0x3a, 0xb5, 0x59, 0x04, 0xea, 0x40, 0x55, 0x25, 0x51, 0xe5, 0x7a, 0x89, 0x38, 0x68, 0x52, 0x7b, 0xfc, 0x27, 0xae, 0xd7, 0xbd, 0xfa, 0x07, 0xf4, 0xcc, 0x8e, 0x5f, 0xef, 0x35, 0x9c, 0x84, 0x2b, 0x15, 0xd5, 0x77, 0x34, 0x49, 0xb6, 0x12, 0x0a, 0x7f, 0x71, 0x88, 0xfd, 0x9d, 0x18, 0x41, 0x7d, 0x93, 0xd8, 0x58, 0x2c, 0xce, 0xfe, 0x24, 0xaf, 0xde, 0xb8, 0x36, 0xc8, 0xa1, 0x80, 0xa6, 0x99, 0x98, 0xa8, 0x2f, 0x0e, 0x81, 0x65, 0x73, 0xe4, 0xc2, 0xa2, 0x8a, 0xd4, 0xe1, 0x11, 0xd0, 0x08, 0x8b, 0x2a, 0xf2, 0xed, 0x9a, 0x64, 0x3f, 0xc1, 0x6c, 0xf9, 0xec }; /** for "strong" encryption, this is the second rotor of an Enigma 3 rotor cipher. */ static unsigned char comp_high1 [] = { 0x41, 0x36, 0x13, 0x62, 0xa8, 0x21, 0x6e, 0xbb, 0xf4, 0x16, 0xcc, 0x04, 0x7f, 0x64, 0xe8, 0x5d, 0x1e, 0xf2, 0xcb, 0x2a, 0x74, 0xc5, 0x5e, 0x35, 0xd2, 0x95, 0x47, 0x9e, 0x96, 0x2d, 0x9a, 0x88, 0x4c, 0x7d, 0x84, 0x3f, 0xdb, 0xac, 0x31, 0xb6, 0x48, 0x5f, 0xf6, 0xc4, 0xd8, 0x39, 0x8b, 0xe7, 0x23, 0x3b, 0x38, 0x8e, 0xc8, 0xc1, 0xdf, 0x25, 0xb1, 0x20, 0xa5, 0x46, 0x60, 0x4e, 0x9c, 0xfb, 0xaa, 0xd3, 0x56, 0x51, 0x45, 0x7c, 0x55, 0x00, 0x07, 0xc9, 0x2b, 0x9d, 0x85, 0x9b, 0x09, 0xa0, 0x8f, 0xad, 0xb3, 0x0f, 0x63, 0xab, 0x89, 0x4b, 0xd7, 0xa7, 0x15, 0x5a, 0x71, 0x66, 0x42, 0xbf, 0x26, 0x4a, 0x6b, 0x98, 0xfa, 0xea, 0x77, 0x53, 0xb2, 0x70, 0x05, 0x2c, 0xfd, 0x59, 0x3a, 0x86, 0x7e, 0xce, 0x06, 0xeb, 0x82, 0x78, 0x57, 0xc7, 0x8d, 0x43, 0xaf, 0xb4, 0x1c, 0xd4, 0x5b, 0xcd, 0xe2, 0xe9, 0x27, 0x4f, 0xc3, 0x08, 0x72, 0x80, 0xcf, 0xb0, 0xef, 0xf5, 0x28, 0x6d, 0xbe, 0x30, 0x4d, 0x34, 0x92, 0xd5, 0x0e, 0x3c, 0x22, 0x32, 0xe5, 0xe4, 0xf9, 0x9f, 0xc2, 0xd1, 0x0a, 0x81, 0x12, 0xe1, 0xee, 0x91, 0x83, 0x76, 0xe3, 0x97, 0xe6, 0x61, 0x8a, 0x17, 0x79, 0xa4, 0xb7, 0xdc, 0x90, 0x7a, 0x5c, 0x8c, 0x02, 0xa6, 0xca, 0x69, 0xde, 0x50, 0x1a, 0x11, 0x93, 0xb9, 0x52, 0x87, 0x58, 0xfc, 0xed, 0x1d, 0x37, 0x49, 0x1b, 0x6a, 0xe0, 0x29, 0x33, 0x99, 0xbd, 0x6c, 0xd9, 0x94, 0xf3, 0x40, 0x54, 0x6f, 0xf0, 0xc6, 0x73, 0xb8, 0xd6, 0x3e, 0x65, 0x18, 0x44, 0x1f, 0xdd, 0x67, 0x10, 0xf1, 0x0c, 0x19, 0xec, 0xae, 0x03, 0xa1, 0x14, 0x7b, 0xa9, 0x0b, 0xff, 0xf8, 0xa3, 0xc0, 0xa2, 0x01, 0xf7, 0x2e, 0xbc, 0x24, 0x68, 0x75, 0x0d, 0xfe, 0xba, 0x2f, 0xb5, 0xd0, 0xda, 0x3d }; /** for "strong" encryption, this is the third rotor of an Enigma 3 rotor cipher. */ static unsigned char comp_high2 [] = { 0x14, 0x53, 0x0f, 0x56, 0xb3, 0xc8, 0x7a, 0x9c, 0xeb, 0x65, 0x48, 0x17, 0x16, 0x15, 0x9f, 0x02, 0xcc, 0x54, 0x7c, 0x83, 0x00, 0x0d, 0x0c, 0x0b, 0xa2, 0x62, 0xa8, 0x76, 0xdb, 0xd9, 0xed, 0xc7, 0xc5, 0xa4, 0xdc, 0xac, 0x85, 0x74, 0xd6, 0xd0, 0xa7, 0x9b, 0xae, 0x9a, 0x96, 0x71, 0x66, 0xc3, 0x63, 0x99, 0xb8, 0xdd, 0x73, 0x92, 0x8e, 0x84, 0x7d, 0xa5, 0x5e, 0xd1, 0x5d, 0x93, 0xb1, 0x57, 0x51, 0x50, 0x80, 0x89, 0x52, 0x94, 0x4f, 0x4e, 0x0a, 0x6b, 0xbc, 0x8d, 0x7f, 0x6e, 0x47, 0x46, 0x41, 0x40, 0x44, 0x01, 0x11, 0xcb, 0x03, 0x3f, 0xf7, 0xf4, 0xe1, 0xa9, 0x8f, 0x3c, 0x3a, 0xf9, 0xfb, 0xf0, 0x19, 0x30, 0x82, 0x09, 0x2e, 0xc9, 0x9d, 0xa0, 0x86, 0x49, 0xee, 0x6f, 0x4d, 0x6d, 0xc4, 0x2d, 0x81, 0x34, 0x25, 0x87, 0x1b, 0x88, 0xaa, 0xfc, 0x06, 0xa1, 0x12, 0x38, 0xfd, 0x4c, 0x42, 0x72, 0x64, 0x13, 0x37, 0x24, 0x6a, 0x75, 0x77, 0x43, 0xff, 0xe6, 0xb4, 0x4b, 0x36, 0x5c, 0xe4, 0xd8, 0x35, 0x3d, 0x45, 0xb9, 0x2c, 0xec, 0xb7, 0x31, 0x2b, 0x29, 0x07, 0x68, 0xa3, 0x0e, 0x69, 0x7b, 0x18, 0x9e, 0x21, 0x39, 0xbe, 0x28, 0x1a, 0x5b, 0x78, 0xf5, 0x23, 0xca, 0x2a, 0xb0, 0xaf, 0x3e, 0xfe, 0x04, 0x8c, 0xe7, 0xe5, 0x98, 0x32, 0x95, 0xd3, 0xf6, 0x4a, 0xe8, 0xa6, 0xea, 0xe9, 0xf3, 0xd5, 0x2f, 0x70, 0x20, 0xf2, 0x1f, 0x05, 0x67, 0xad, 0x55, 0x10, 0xce, 0xcd, 0xe3, 0x27, 0x3b, 0xda, 0xba, 0xd7, 0xc2, 0x26, 0xd4, 0x91, 0x1d, 0xd2, 0x1c, 0x22, 0x33, 0xf8, 0xfa, 0xf1, 0x5a, 0xef, 0xcf, 0x90, 0xb6, 0x8b, 0xb5, 0xbd, 0xc0, 0xbf, 0x08, 0x97, 0x1e, 0x6c, 0xe2, 0x61, 0xe0, 0xc6, 0xc1, 0x59, 0xab, 0xbb, 0x58, 0xde, 0x5f, 0xdf, 0x60, 0x79, 0x7e, 0xb2, 0x8a }; static size_t pst_append_holder(pst_holder *h, size_t size, char **buf, size_t z); static int pst_build_desc_ptr(pst_file *pf, int64_t offset, int32_t depth, uint64_t linku1, uint64_t start_val, uint64_t end_val); static pst_id2_tree* pst_build_id2(pst_file *pf, pst_index_ll* list); static int pst_build_id_ptr(pst_file *pf, int64_t offset, int32_t depth, uint64_t linku1, uint64_t start_val, uint64_t end_val); static int pst_chr_count(char *str, char x); static size_t pst_ff_compile_ID(pst_file *pf, uint64_t i_id, pst_holder *h, size_t size); static size_t pst_ff_getIDblock(pst_file *pf, uint64_t i_id, char** buf); static size_t pst_ff_getID2block(pst_file *pf, uint64_t id2, pst_id2_tree *id2_head, char** buf); static size_t pst_ff_getID2data(pst_file *pf, pst_index_ll *ptr, pst_holder *h); static size_t pst_finish_cleanup_holder(pst_holder *h, size_t size); static void pst_free_attach(pst_item_attach *attach); static void pst_free_desc (pst_desc_tree *head); static void pst_free_id2(pst_id2_tree * head); static void pst_free_list(pst_mapi_object *list); static void pst_free_xattrib(pst_x_attrib_ll *x); static size_t pst_getAtPos(pst_file *pf, int64_t pos, void* buf, size_t size); static int pst_getBlockOffsetPointer(pst_file *pf, pst_id2_tree *i2_head, pst_subblocks *subblocks, uint32_t offset, pst_block_offset_pointer *p); static int pst_getBlockOffset(char *buf, size_t read_size, uint32_t i_offset, uint32_t offset, pst_block_offset *p); static pst_id2_tree* pst_getID2(pst_id2_tree * ptr, uint64_t id); static pst_desc_tree* pst_getDptr(pst_file *pf, uint64_t d_id); static uint64_t pst_getIntAt(pst_file *pf, char *buf); static uint64_t pst_getIntAtPos(pst_file *pf, int64_t pos); static pst_mapi_object* pst_parse_block(pst_file *pf, uint64_t block_id, pst_id2_tree *i2_head); static void pst_printDptr(pst_file *pf, pst_desc_tree *ptr); static void pst_printID2ptr(pst_id2_tree *ptr); static int pst_process(uint64_t block_id, pst_mapi_object *list, pst_item *item, pst_item_attach *attach); static size_t pst_read_block_size(pst_file *pf, int64_t offset, size_t size, size_t inflated_size, char **buf); static size_t pst_read_raw_block_size(pst_file *pf, int64_t offset, size_t size, char **buf); static int pst_decrypt(uint64_t i_id, char *buf, size_t size, unsigned char type); static int pst_strincmp(char *a, char *b, size_t x); static char* pst_wide_to_single(char *wt, size_t size); static char *pst_getcwd(void) { char *cwd; #ifdef HAVE_GET_CURRENT_DIR_NAME cwd = get_current_dir_name(); #else cwd = pst_malloc(PATH_MAX+1); getcwd(cwd, PATH_MAX+1); #endif return cwd; } int pst_open(pst_file *pf, const char *name, const char *charset) { int32_t sig; pst_unicode_init(); DEBUG_ENT("pst_open"); if (!pf) { WARN (("cannot be passed a NULL pst_file\n")); DEBUG_RET(); return -1; } memset(pf, 0, sizeof(*pf)); pf->charset = charset; if ((pf->fp = fopen(name, "rb")) == NULL) { perror("Error opening PST file"); DEBUG_RET(); return -1; } // Check pst file magic if (pst_getAtPos(pf, 0, &sig, sizeof(sig)) != sizeof(sig)) { (void)fclose(pf->fp); DEBUG_WARN(("cannot read signature from PST file. Closing with error\n")); DEBUG_RET(); return -1; } LE32_CPU(sig); DEBUG_INFO(("sig = %X\n", sig)); if (sig != (int32_t)PST_SIGNATURE) { (void)fclose(pf->fp); DEBUG_WARN(("not a PST file that I know. Closing with error\n")); DEBUG_RET(); return -1; } // read index type (void)pst_getAtPos(pf, INDEX_TYPE_OFFSET, &(pf->ind_type), sizeof(pf->ind_type)); DEBUG_INFO(("index_type = %i\n", pf->ind_type)); switch (pf->ind_type) { case INDEX_TYPE32 : case INDEX_TYPE32A : pf->do_read64 = 0; break; case INDEX_TYPE64 : case INDEX_TYPE64A : pf->do_read64 = 1; break; case INDEX_TYPE4K : pf->do_read64 = 2; break; default: (void)fclose(pf->fp); DEBUG_WARN(("unknown .pst format, possibly newer than Outlook 2003 PST file?\n")); DEBUG_RET(); return -1; } // read encryption setting (void)pst_getAtPos(pf, ENC_TYPE, &(pf->encryption), sizeof(pf->encryption)); DEBUG_INFO(("encrypt = %i\n", pf->encryption)); pf->index2_back = pst_getIntAtPos(pf, SECOND_BACK); pf->index2 = pst_getIntAtPos(pf, SECOND_POINTER); pf->size = pst_getIntAtPos(pf, FILE_SIZE_POINTER); DEBUG_INFO(("Pointer2 is %#"PRIx64", back pointer2 is %#"PRIx64"\n", pf->index2, pf->index2_back)); pf->index1_back = pst_getIntAtPos(pf, INDEX_BACK); pf->index1 = pst_getIntAtPos(pf, INDEX_POINTER); DEBUG_INFO(("Pointer1 is %#"PRIx64", back pointer2 is %#"PRIx64"\n", pf->index1, pf->index1_back)); DEBUG_RET(); pf->cwd = pst_getcwd(); pf->fname = strdup(name); return 0; } int pst_reopen(pst_file *pf) { char *cwd; cwd = pst_getcwd(); if (cwd == NULL) return -1; if (chdir(pf->cwd)) goto err; if (!freopen(pf->fname, "rb", pf->fp)) goto err; if (chdir(cwd)) goto err; free(cwd); return 0; err: free(cwd); return -1; } int pst_close(pst_file *pf) { DEBUG_ENT("pst_close"); if (!pf) { DEBUG_RET(); return 0; } if (!pf->fp) { DEBUG_RET(); return 0; } if (fclose(pf->fp)) { DEBUG_WARN(("fclose returned non-zero value\n")); } // free the paths free(pf->cwd); free(pf->fname); // we must free the id array and the desc tree free(pf->i_table); pst_free_desc(pf->d_head); pst_free_xattrib(pf->x_head); DEBUG_RET(); return 0; } /** * add a pst descriptor node to a linked list of such nodes. * * @param node pointer to the node to be added to the list * @param head pointer to the list head pointer * @param tail pointer to the list tail pointer */ static void add_descriptor_to_list(pst_desc_tree *node, pst_desc_tree **head, pst_desc_tree **tail); static void add_descriptor_to_list(pst_desc_tree *node, pst_desc_tree **head, pst_desc_tree **tail) { DEBUG_ENT("add_descriptor_to_list"); //DEBUG_INFO(("Added node %#"PRIx64" parent %#"PRIx64" real parent %#"PRIx64" prev %#"PRIx64" next %#"PRIx64"\n", // node->id, node->parent_d_id, // (node->parent ? node->parent->id : (uint64_t)0), // (node->prev ? node->prev->id : (uint64_t)0), // (node->next ? node->next->id : (uint64_t)0))); if (*tail) (*tail)->next = node; if (!(*head)) *head = node; node->prev = *tail; node->next = NULL; *tail = node; DEBUG_RET(); } /** * add a pst descriptor node into the global tree. * * @param pf global pst file pointer * @param node pointer to the new node to be added to the tree */ static void record_descriptor(pst_file *pf, pst_desc_tree *node); static void record_descriptor(pst_file *pf, pst_desc_tree *node) { DEBUG_ENT("record_descriptor"); // finish node initialization node->parent = NULL; node->child = NULL; node->child_tail = NULL; node->no_child = 0; // find any orphan children of this node, and collect them pst_desc_tree *n = pf->d_head; while (n) { if (n->parent_d_id == node->d_id) { // found a child of this node DEBUG_INFO(("Found orphan child %#"PRIx64" of parent %#"PRIx64"\n", n->d_id, node->d_id)); pst_desc_tree *nn = n->next; pst_desc_tree *pp = n->prev; node->no_child++; n->parent = node; add_descriptor_to_list(n, &node->child, &node->child_tail); if (pp) pp->next = nn; else pf->d_head = nn; if (nn) nn->prev = pp; else pf->d_tail = pp; n = nn; } else { n = n->next; } } // now hook this node into the global tree if (node->parent_d_id == 0) { // add top level node to the descriptor tree //DEBUG_INFO(("Null parent\n")); add_descriptor_to_list(node, &pf->d_head, &pf->d_tail); } else if (node->parent_d_id == node->d_id) { // add top level node to the descriptor tree DEBUG_INFO(("%#"PRIx64" is its own parent. What is this world coming to?\n", node->d_id)); add_descriptor_to_list(node, &pf->d_head, &pf->d_tail); } else { //DEBUG_INFO(("Searching for parent %#"PRIx64" of %#"PRIx64"\n", node->parent_d_id, node->d_id)); pst_desc_tree *parent = pst_getDptr(pf, node->parent_d_id); if (parent) { //DEBUG_INFO(("Found parent %#"PRIx64"\n", node->parent_d_id)); parent->no_child++; node->parent = parent; add_descriptor_to_list(node, &parent->child, &parent->child_tail); } else { DEBUG_INFO(("No parent %#"PRIx64", have an orphan child %#"PRIx64"\n", node->parent_d_id, node->d_id)); add_descriptor_to_list(node, &pf->d_head, &pf->d_tail); } } DEBUG_RET(); } /** * make a deep copy of part of the id2 mapping tree, for use * by an attachment containing an embedded rfc822 message. * * @param head pointer to the subtree to be copied * @return pointer to the new copy of the subtree */ static pst_id2_tree* deep_copy(pst_id2_tree *head); static pst_id2_tree* deep_copy(pst_id2_tree *head) { if (!head) return NULL; pst_id2_tree* me = (pst_id2_tree*) pst_malloc(sizeof(pst_id2_tree)); me->id2 = head->id2; me->id = head->id; me->child = deep_copy(head->child); me->next = deep_copy(head->next); return me; } pst_desc_tree* pst_getTopOfFolders(pst_file *pf, const pst_item *root) { pst_desc_tree *topnode; uint32_t topid; DEBUG_ENT("pst_getTopOfFolders"); if (!root || !root->message_store) { DEBUG_INFO(("There isn't a top of folder record here.\n")); DEBUG_RET(); return NULL; } if (!root->message_store->top_of_personal_folder) { // this is the OST way // ASSUMPTION: Top Of Folders record in PST files is *always* descid 0x2142 topid = 0x2142; } else { topid = root->message_store->top_of_personal_folder->id; } DEBUG_INFO(("looking for top of folder descriptor %#"PRIx32"\n", topid)); topnode = pst_getDptr(pf, (uint64_t)topid); if (!topnode) { // add dummy top record to pickup orphan children topnode = (pst_desc_tree*) pst_malloc(sizeof(pst_desc_tree)); topnode->d_id = topid; topnode->parent_d_id = 0; topnode->assoc_tree = NULL; topnode->desc = NULL; record_descriptor(pf, topnode); // add to the global tree } DEBUG_RET(); return topnode; } pst_binary pst_attach_to_mem(pst_file *pf, pst_item_attach *attach) { pst_index_ll *ptr; pst_binary rc; pst_holder h = {&rc.data, NULL, 0, 0, 0}; rc.size = 0; rc.data = NULL; DEBUG_ENT("pst_attach_to_mem"); if ((!attach->data.data) && (attach->i_id != (uint64_t)-1)) { ptr = pst_getID(pf, attach->i_id); if (ptr) { rc.size = pst_ff_getID2data(pf, ptr, &h); } else { DEBUG_WARN(("Couldn't find ID pointer. Cannot handle attachment\n")); } } else { rc = attach->data; attach->data.data = NULL; // prevent pst_free_item() from trying to free this attach->data.size = 0; // since we have given that buffer to the caller } DEBUG_RET(); return rc; } size_t pst_attach_to_file(pst_file *pf, pst_item_attach *attach, FILE* fp) { pst_index_ll *ptr; pst_holder h = {NULL, fp, 0, 0, 0}; size_t size = 0; DEBUG_ENT("pst_attach_to_file"); if ((!attach->data.data) && (attach->i_id != (uint64_t)-1)) { ptr = pst_getID(pf, attach->i_id); if (ptr) { size = pst_ff_getID2data(pf, ptr, &h); } else { DEBUG_WARN(("Couldn't find ID pointer. Cannot save attachment to file\n")); } } else { size = attach->data.size; if (attach->data.data && size) { // save the attachment to the file (void)pst_fwrite(attach->data.data, (size_t)1, size, fp); } } DEBUG_RET(); return size; } size_t pst_attach_to_file_base64(pst_file *pf, pst_item_attach *attach, FILE* fp) { pst_index_ll *ptr; pst_holder h = {NULL, fp, 1, 0, 0}; size_t size = 0; DEBUG_ENT("pst_attach_to_file_base64"); if ((!attach->data.data) && (attach->i_id != (uint64_t)-1)) { ptr = pst_getID(pf, attach->i_id); if (ptr) { size = pst_ff_getID2data(pf, ptr, &h); } else { DEBUG_WARN(("Couldn't find ID pointer. Cannot save attachment to Base64\n")); } } else { size = attach->data.size; if (attach->data.data && size) { // encode the attachment to the file char *c = pst_base64_encode(attach->data.data, size); if (c) { (void)pst_fwrite(c, (size_t)1, strlen(c), fp); free(c); // caught by valgrind } } } DEBUG_RET(); return size; } int pst_load_index (pst_file *pf) { int x; DEBUG_ENT("pst_load_index"); if (!pf) { DEBUG_WARN(("Cannot load index for a NULL pst_file\n")); DEBUG_RET(); return -1; } x = pst_build_id_ptr(pf, pf->index1, 0, pf->index1_back, 0, UINT64_MAX); DEBUG_INFO(("build id ptr returns %i\n", x)); x = pst_build_desc_ptr(pf, pf->index2, 0, pf->index2_back, (uint64_t)0x21, UINT64_MAX); DEBUG_INFO(("build desc ptr returns %i\n", x)); pst_printDptr(pf, pf->d_head); DEBUG_RET(); return 0; } pst_desc_tree* pst_getNextDptr(pst_desc_tree* d) { pst_desc_tree* r = NULL; DEBUG_ENT("pst_getNextDptr"); if (d) { if ((r = d->child) == NULL) { while (!d->next && d->parent) d = d->parent; r = d->next; } } DEBUG_RET(); return r; } typedef struct pst_x_attrib { uint32_t extended; uint16_t type; uint16_t map; } pst_x_attrib; /** Try to load the extended attributes from the pst file. @return true(1) or false(0) to indicate whether the extended attributes have been loaded */ int pst_load_extended_attributes(pst_file *pf) { // for PST files this will load up d_id 0x61 and check it's "assoc_tree" attribute. pst_desc_tree *p; pst_mapi_object *list; pst_id2_tree *id2_head = NULL; char *buffer=NULL, *headerbuffer=NULL; size_t bsize=0, hsize=0, bptr=0; pst_x_attrib xattrib; int32_t tint, x; pst_x_attrib_ll *ptr, *p_head=NULL; DEBUG_ENT("pst_loadExtendedAttributes"); p = pst_getDptr(pf, (uint64_t)0x61); if (!p) { DEBUG_WARN(("Cannot find d_id 0x61 for loading the Extended Attributes\n")); DEBUG_RET(); return 0; } if (!p->desc) { DEBUG_WARN(("descriptor is NULL for d_id 0x61. Cannot load Extended Attributes\n")); DEBUG_RET(); return 0; } if (p->assoc_tree) { id2_head = pst_build_id2(pf, p->assoc_tree); pst_printID2ptr(id2_head); } else { DEBUG_WARN(("Have not been able to fetch any id2 values for d_id 0x61. Brace yourself!\n")); } list = pst_parse_block(pf, p->desc->i_id, id2_head); if (!list) { DEBUG_WARN(("Cannot process desc block for item 0x61. Not loading extended Attributes\n")); pst_free_id2(id2_head); DEBUG_RET(); return 0; } DEBUG_INFO(("look through d_id 0x61 list of mapi objects\n")); for (x=0; x < list->count_elements; x++) { DEBUG_INFO(("#%d - mapi-id: %#x type: %#x length: %#x\n", x, list->elements[x]->mapi_id, list->elements[x]->type, list->elements[x]->size)); if (list->elements[x]->data) { DEBUG_HEXDUMPC(list->elements[x]->data, list->elements[x]->size, 0x10); } if (list->elements[x]->mapi_id == (uint32_t)0x0003) { buffer = list->elements[x]->data; bsize = list->elements[x]->size; } else if (list->elements[x]->mapi_id == (uint32_t)0x0004) { headerbuffer = list->elements[x]->data; hsize = list->elements[x]->size; } else { // leave them null } } if (!buffer) { pst_free_list(list); DEBUG_WARN(("No extended attributes buffer found. Not processing\n")); DEBUG_RET(); return 0; } while (bptr < bsize) { int err = 0; xattrib.extended= PST_LE_GET_UINT32(buffer+bptr), bptr += 4; xattrib.type = PST_LE_GET_UINT16(buffer+bptr), bptr += 2; xattrib.map = PST_LE_GET_UINT16(buffer+bptr), bptr += 2; ptr = (pst_x_attrib_ll*) pst_malloc(sizeof(*ptr)); memset(ptr, 0, sizeof(*ptr)); ptr->map = xattrib.map+0x8000; ptr->next = NULL; DEBUG_INFO(("xattrib: ext = %#"PRIx32", type = %#"PRIx16", map = %#"PRIx16"\n", xattrib.extended, xattrib.type, xattrib.map)); if (xattrib.type & 0x0001) { // if the Bit 1 is set // pointer to Unicode field in buffer if (xattrib.extended < hsize) { char *wt; // copy the size of the header. It is 32 bit int memcpy(&tint, &(headerbuffer[xattrib.extended]), sizeof(tint)); LE32_CPU(tint); wt = (char*) pst_malloc((size_t)(tint+2)); // plus 2 for a uni-code zero memset(wt, 0, (size_t)(tint+2)); memcpy(wt, &(headerbuffer[xattrib.extended+sizeof(tint)]), (size_t)tint); ptr->data = pst_wide_to_single(wt, (size_t)tint); free(wt); DEBUG_INFO(("Mapped attribute %#"PRIx32" to %s\n", ptr->map, ptr->data)); } else { DEBUG_INFO(("Cannot read outside of buffer [%i !< %i]\n", xattrib.extended, hsize)); err = 1; } ptr->mytype = PST_MAP_HEADER; } else { // contains the attribute code to map to. ptr->data = (uint32_t*)pst_malloc(sizeof(uint32_t)); memset(ptr->data, 0, sizeof(uint32_t)); *((uint32_t*)ptr->data) = xattrib.extended; ptr->mytype = PST_MAP_ATTRIB; DEBUG_INFO(("Mapped attribute %#"PRIx32" to %#"PRIx32"\n", ptr->map, *((uint32_t*)ptr->data))); } if (!err) { // add it to the list pst_x_attrib_ll *p_sh = p_head; pst_x_attrib_ll *p_sh2 = NULL; while (p_sh && (ptr->map > p_sh->map)) { p_sh2 = p_sh; p_sh = p_sh->next; } if (!p_sh2) { // needs to go before first item ptr->next = p_head; p_head = ptr; } else { // it will go after p_sh2 ptr->next = p_sh2->next; p_sh2->next = ptr; } } else { free(ptr); } } pst_free_id2(id2_head); pst_free_list(list); pf->x_head = p_head; DEBUG_RET(); return 1; } #define ITEM_COUNT_OFFSET32 0x1f0 // count byte #define MAX_COUNT_OFFSET32 0x1f1 #define ENTRY_SIZE_OFFSET32 0x1f2 #define LEVEL_INDICATOR_OFFSET32 0x1f3 // node or leaf #define BACKLINK_OFFSET32 0x1f8 // backlink u1 value #define ITEM_COUNT_OFFSET64 0x1e8 // count byte #define MAX_COUNT_OFFSET64 0x1e9 #define ENTRY_SIZE_OFFSET64 0x1ea // node or leaf #define LEVEL_INDICATOR_OFFSET64 0x1eb // node or leaf #define BACKLINK_OFFSET64 0x1f8 // backlink u1 value #define ITEM_COUNT_OFFSET4K 0xfd8 #define MAX_COUNT_OFFSET4K 0xfda #define ENTRY_SIZE_OFFSET4K 0xfdc #define LEVEL_INDICATOR_OFFSET4K 0xfdd #define BACKLINK_OFFSET4K 0xff0 #define BLOCK_SIZE (size_t)((pf->do_read64 == 2) ? 4096 : 512) // index blocks #define DESC_BLOCK_SIZE (size_t)((pf->do_read64 == 2) ? 4096 : 512) // descriptor blocks #define ITEM_COUNT_OFFSET (size_t)((pf->do_read64) ? (pf->do_read64 == 2 ? ITEM_COUNT_OFFSET4K : ITEM_COUNT_OFFSET64) : ITEM_COUNT_OFFSET32) #define LEVEL_INDICATOR_OFFSET (size_t)((pf->do_read64) ? (pf->do_read64 == 2 ? LEVEL_INDICATOR_OFFSET4K : LEVEL_INDICATOR_OFFSET64) : LEVEL_INDICATOR_OFFSET32) #define BACKLINK_OFFSET (size_t)((pf->do_read64) ? (pf->do_read64 == 2 ? BACKLINK_OFFSET4K : BACKLINK_OFFSET64) : BACKLINK_OFFSET32) #define ENTRY_SIZE_OFFSET (size_t)((pf->do_read64) ? (pf->do_read64 == 2 ? ENTRY_SIZE_OFFSET4K : ENTRY_SIZE_OFFSET64) : ENTRY_SIZE_OFFSET32) #define MAX_COUNT_OFFSET (size_t)((pf->do_read64) ? (pf->do_read64 == 2 ? MAX_COUNT_OFFSET4K : MAX_COUNT_OFFSET64) : MAX_COUNT_OFFSET32) #define read_twobyte(BUF, OFF) (int32_t) ((((unsigned)BUF[OFF + 1] & 0xFF)) << 8) | ((unsigned)BUF[OFF] & 0xFF); static size_t pst_decode_desc(pst_file *pf, pst_desc *desc, char *buf); static size_t pst_decode_desc(pst_file *pf, pst_desc *desc, char *buf) { size_t r; if (pf->do_read64) { DEBUG_INFO(("Decoding desc64\n")); DEBUG_HEXDUMPC(buf, sizeof(pst_desc), 0x10); memcpy(desc, buf, sizeof(pst_desc)); LE64_CPU(desc->d_id); LE64_CPU(desc->desc_id); LE64_CPU(desc->tree_id); LE32_CPU(desc->parent_d_id); LE32_CPU(desc->u1); r = sizeof(pst_desc); } else { pst_desc32 d32; DEBUG_INFO(("Decoding desc32\n")); DEBUG_HEXDUMPC(buf, sizeof(pst_desc32), 0x10); memcpy(&d32, buf, sizeof(pst_desc32)); LE32_CPU(d32.d_id); LE32_CPU(d32.desc_id); LE32_CPU(d32.tree_id); LE32_CPU(d32.parent_d_id); desc->d_id = d32.d_id; desc->desc_id = d32.desc_id; desc->tree_id = d32.tree_id; desc->parent_d_id = d32.parent_d_id; desc->u1 = 0; r = sizeof(pst_desc32); } return r; } static size_t pst_decode_table(pst_file *pf, struct pst_table_ptr_struct *table, char *buf); static size_t pst_decode_table(pst_file *pf, struct pst_table_ptr_struct *table, char *buf) { size_t r; if (pf->do_read64) { DEBUG_INFO(("Decoding table64\n")); DEBUG_HEXDUMPC(buf, sizeof(struct pst_table_ptr_struct), 0x10); memcpy(table, buf, sizeof(struct pst_table_ptr_struct)); LE64_CPU(table->start); LE64_CPU(table->u1); LE64_CPU(table->offset); r =sizeof(struct pst_table_ptr_struct); } else { struct pst_table_ptr_struct32 t32; DEBUG_INFO(("Decoding table32\n")); DEBUG_HEXDUMPC(buf, sizeof( struct pst_table_ptr_struct32), 0x10); memcpy(&t32, buf, sizeof(struct pst_table_ptr_struct32)); LE32_CPU(t32.start); LE32_CPU(t32.u1); LE32_CPU(t32.offset); table->start = t32.start; table->u1 = t32.u1; table->offset = t32.offset; r = sizeof(struct pst_table_ptr_struct32); } return r; } static size_t pst_decode_index(pst_file *pf, pst_index *index, char *buf); static size_t pst_decode_index(pst_file *pf, pst_index *index, char *buf) { size_t r; if (pf->do_read64 == 2) { DEBUG_INFO(("Decoding index4k\n")); DEBUG_HEXDUMPC(buf, sizeof(pst_index), 0x10); memcpy(index, buf, sizeof(pst_index)); LE64_CPU(index->id); LE64_CPU(index->offset); LE16_CPU(index->size); LE16_CPU(index->inflated_size); LE16_CPU(index->u0); LE32_CPU(index->u1); r = sizeof(pst_index); } else if (pf->do_read64 == 1) { pst_index64 index64; DEBUG_INFO(("Decoding index64\n")); DEBUG_HEXDUMPC(buf, sizeof(pst_index64), 0x10); memcpy(&index64, buf, sizeof(pst_index64)); LE64_CPU(index64.id); LE64_CPU(index64.offset); LE16_CPU(index64.size); LE16_CPU(index64.u0); LE32_CPU(index64.u1); index->id = index64.id; index->offset = index64.offset; index->size = index64.size; index->inflated_size = index64.size; index->u0 = index64.u0; index->u1 = index64.u1; r = sizeof(pst_index64); } else { pst_index32 index32; DEBUG_INFO(("Decoding index32\n")); DEBUG_HEXDUMPC(buf, sizeof(pst_index32), 0x10); memcpy(&index32, buf, sizeof(pst_index32)); LE32_CPU(index32.id); LE32_CPU(index32.offset); LE16_CPU(index32.size); LE16_CPU(index32.u1); index->id = index32.id; index->offset = index32.offset; index->size = index32.size; index->inflated_size = index32.size; index->u0 = 0; index->u1 = index32.u1; r = sizeof(pst_index32); } return r; } static size_t pst_decode_assoc(pst_file *pf, pst_id2_assoc *assoc, char *buf); static size_t pst_decode_assoc(pst_file *pf, pst_id2_assoc *assoc, char *buf) { size_t r; if (pf->do_read64) { DEBUG_INFO(("Decoding assoc64\n")); DEBUG_HEXDUMPC(buf, sizeof(pst_id2_assoc), 0x10); memcpy(assoc, buf, sizeof(pst_id2_assoc)); LE32_CPU(assoc->id2); LE64_CPU(assoc->id); LE64_CPU(assoc->child_id); r = sizeof(pst_id2_assoc); } else { pst_id2_assoc32 assoc32; DEBUG_INFO(("Decoding assoc32\n")); DEBUG_HEXDUMPC(buf, sizeof(pst_id2_assoc32), 0x10); memcpy(&assoc32, buf, sizeof(pst_id2_assoc32)); LE32_CPU(assoc32.id2); LE32_CPU(assoc32.id); LE32_CPU(assoc32.child_id); assoc->id2 = assoc32.id2; assoc->id = assoc32.id; assoc->child_id = assoc32.child_id; r = sizeof(pst_id2_assoc32); } return r; } static size_t pst_decode_type3(pst_file *pf, pst_table3_rec *table3_rec, char *buf); static size_t pst_decode_type3(pst_file *pf, pst_table3_rec *table3_rec, char *buf) { size_t r; DEBUG_ENT("pst_decode_type3"); if (pf->do_read64) { DEBUG_INFO(("Decoding table3 64\n")); DEBUG_HEXDUMPC(buf, sizeof(pst_table3_rec), 0x10); memcpy(table3_rec, buf, sizeof(pst_table3_rec)); LE64_CPU(table3_rec->id); r = sizeof(pst_table3_rec); } else { pst_table3_rec32 table3_rec32; DEBUG_INFO(("Decoding table3 32\n")); DEBUG_HEXDUMPC(buf, sizeof(pst_table3_rec32), 0x10); memcpy(&table3_rec32, buf, sizeof(pst_table3_rec32)); LE32_CPU(table3_rec32.id); table3_rec->id = table3_rec32.id; r = sizeof(pst_table3_rec32); } DEBUG_RET(); return r; } /** Process the index1 b-tree from the pst file and create the * pf->i_head linked list from it. This tree holds the location * (offset and size) of lower level objects (0xbcec descriptor * blocks, etc) in the pst file. */ static int pst_build_id_ptr(pst_file *pf, int64_t offset, int32_t depth, uint64_t linku1, uint64_t start_val, uint64_t end_val) { struct pst_table_ptr_struct table, table2; pst_index_ll *i_ptr=NULL; pst_index index; int32_t x, item_count, count_max; uint64_t old = start_val; char *buf = NULL, *bptr; DEBUG_ENT("pst_build_id_ptr"); DEBUG_INFO(("offset %#"PRIx64" depth %i linku1 %#"PRIx64" start %#"PRIx64" end %#"PRIx64"\n", offset, depth, linku1, start_val, end_val)); if (end_val <= start_val) { DEBUG_WARN(("The end value is BEFORE the start value. This function will quit. Soz. [start:%#"PRIx64", end:%#"PRIx64"]\n", start_val, end_val)); DEBUG_RET(); return -1; } DEBUG_INFO(("Reading index block\n")); if (pst_read_block_size(pf, offset, BLOCK_SIZE, BLOCK_SIZE, &buf) < BLOCK_SIZE) { DEBUG_WARN(("Failed to read %i bytes\n", BLOCK_SIZE)); if (buf) free(buf); DEBUG_RET(); return -1; } bptr = buf; DEBUG_HEXDUMPC(buf, BLOCK_SIZE, 0x10); if (pf->do_read64 == 2) { item_count = read_twobyte(buf, ITEM_COUNT_OFFSET); count_max = read_twobyte(buf, MAX_COUNT_OFFSET); } else { item_count = (int32_t)(unsigned)(buf[ITEM_COUNT_OFFSET]); count_max = (int32_t)(unsigned)(buf[MAX_COUNT_OFFSET]); } if (item_count > count_max) { DEBUG_WARN(("Item count %i too large, max is %i\n", item_count, count_max)); if (buf) free(buf); DEBUG_RET(); return -1; } index.id = pst_getIntAt(pf, buf+BACKLINK_OFFSET); if (index.id != linku1) { DEBUG_WARN(("Backlink %#"PRIx64" in this node does not match required %#"PRIx64"\n", index.id, linku1)); if (buf) free(buf); DEBUG_RET(); return -1; } int entry_size = (int32_t)(unsigned)(buf[ENTRY_SIZE_OFFSET]); DEBUG_INFO(("count %#"PRIx64" max %#"PRIx64" size %#"PRIx64"\n", item_count, count_max, entry_size)); if (buf[LEVEL_INDICATOR_OFFSET] == '\0') { // this node contains leaf pointers x = 0; while (x < item_count) { pst_decode_index(pf, &index, bptr); bptr += entry_size; x++; if (index.id == 0) break; DEBUG_INFO(("[%i]%i Item [id = %#"PRIx64", offset = %#"PRIx64", u1 = %#x, size = %i(%#x)]\n", depth, x, index.id, index.offset, index.u1, index.size, index.size)); // if (index.id & 0x02) DEBUG_INFO(("two-bit set!!\n")); if ((index.id >= end_val) || (index.id < old)) { DEBUG_WARN(("This item isn't right. Must be corruption, or I got it wrong!\n")); if (buf) free(buf); DEBUG_RET(); return -1; } old = index.id; if (pf->i_count == pf->i_capacity) { pf->i_capacity += (pf->i_capacity >> 1) + 16; // arbitrary growth rate pf->i_table = pst_realloc(pf->i_table, pf->i_capacity * sizeof(pst_index_ll)); } i_ptr = &pf->i_table[pf->i_count++]; i_ptr->i_id = index.id; i_ptr->offset = index.offset; i_ptr->u1 = index.u1; i_ptr->size = index.size; i_ptr->inflated_size = index.inflated_size; } } else { // this node contains node pointers x = 0; while (x < item_count) { pst_decode_table(pf, &table, bptr); bptr += entry_size; x++; if (table.start == 0) break; if (x < item_count) { (void)pst_decode_table(pf, &table2, bptr); } else { table2.start = end_val; } DEBUG_INFO(("[%i] %i Index Table [start id = %#"PRIx64", u1 = %#"PRIx64", offset = %#"PRIx64", end id = %#"PRIx64"]\n", depth, x, table.start, table.u1, table.offset, table2.start)); if ((table.start >= end_val) || (table.start < old)) { DEBUG_WARN(("This table isn't right. Must be corruption, or I got it wrong!\n")); if (buf) free(buf); DEBUG_RET(); return -1; } old = table.start; (void)pst_build_id_ptr(pf, table.offset, depth+1, table.u1, table.start, table2.start); } } if (buf) free (buf); DEBUG_RET(); return 0; } /** Process the index2 b-tree from the pst file and create the * pf->d_head tree from it. This tree holds descriptions of the * higher level objects (email, contact, etc) in the pst file. */ static int pst_build_desc_ptr (pst_file *pf, int64_t offset, int32_t depth, uint64_t linku1, uint64_t start_val, uint64_t end_val) { struct pst_table_ptr_struct table, table2; pst_desc desc_rec; int32_t item_count, count_max; uint64_t old = start_val; int x; char *buf = NULL, *bptr; DEBUG_ENT("pst_build_desc_ptr"); DEBUG_INFO(("offset %#"PRIx64" depth %i linku1 %#"PRIx64" start %#"PRIx64" end %#"PRIx64"\n", offset, depth, linku1, start_val, end_val)); if (end_val <= start_val) { DEBUG_WARN(("The end value is BEFORE the start value. This function will quit. Soz. [start:%#"PRIx64", end:%#"PRIx64"]\n", start_val, end_val)); DEBUG_RET(); return -1; } DEBUG_INFO(("Reading desc block\n")); if (pst_read_block_size(pf, offset, DESC_BLOCK_SIZE, DESC_BLOCK_SIZE, &buf) < DESC_BLOCK_SIZE) { DEBUG_WARN(("Failed to read %i bytes\n", DESC_BLOCK_SIZE)); if (buf) free(buf); DEBUG_RET(); return -1; } bptr = buf; if (pf->do_read64 == 2) { item_count = read_twobyte(buf, ITEM_COUNT_OFFSET); count_max = read_twobyte(buf, MAX_COUNT_OFFSET); } else { item_count = (int32_t)(unsigned)(buf[ITEM_COUNT_OFFSET]); count_max = (int32_t)(unsigned)(buf[MAX_COUNT_OFFSET]); } desc_rec.d_id = pst_getIntAt(pf, buf+BACKLINK_OFFSET); if (desc_rec.d_id != linku1) { DEBUG_WARN(("Backlink %#"PRIx64" in this node does not match required %#"PRIx64"\n", desc_rec.d_id, linku1)); if (buf) free(buf); DEBUG_RET(); return -1; } int32_t entry_size = (int32_t)(unsigned)(buf[ENTRY_SIZE_OFFSET]); if (buf[LEVEL_INDICATOR_OFFSET] == '\0') { // this node contains leaf pointers DEBUG_HEXDUMPC(buf, DESC_BLOCK_SIZE, entry_size); if (item_count > count_max) { DEBUG_WARN(("Item count %i too large, max is %i\n", item_count, count_max)); if (buf) free(buf); DEBUG_RET(); return -1; } for (x=0; x= end_val) || (desc_rec.d_id < old)) { DEBUG_WARN(("This item isn't right. Must be corruption, or I got it wrong!\n")); DEBUG_HEXDUMPC(buf, DESC_BLOCK_SIZE, 16); if (buf) free(buf); DEBUG_RET(); return -1; } old = desc_rec.d_id; DEBUG_INFO(("New Record %#"PRIx64" with parent %#x\n", desc_rec.d_id, desc_rec.parent_d_id)); { pst_desc_tree *d_ptr = (pst_desc_tree*) pst_malloc(sizeof(pst_desc_tree)); d_ptr->d_id = desc_rec.d_id; d_ptr->parent_d_id = desc_rec.parent_d_id; d_ptr->assoc_tree = pst_getID(pf, desc_rec.tree_id); d_ptr->desc = pst_getID(pf, desc_rec.desc_id); record_descriptor(pf, d_ptr); // add to the global tree } } } else { // this node contains node pointers DEBUG_HEXDUMPC(buf, DESC_BLOCK_SIZE, entry_size); if (item_count > count_max) { DEBUG_WARN(("Item count %i too large, max is %i\n", item_count, count_max)); if (buf) free(buf); DEBUG_RET(); return -1; } for (x=0; x= end_val) || (table.start < old)) { DEBUG_WARN(("This table isn't right. Must be corruption, or I got it wrong!\n")); if (buf) free(buf); DEBUG_RET(); return -1; } old = table.start; (void)pst_build_desc_ptr(pf, table.offset, depth+1, table.u1, table.start, table2.start); } } if (buf) free(buf); DEBUG_RET(); return 0; } /** Process a high level object from the pst file. */ pst_item* pst_parse_item(pst_file *pf, pst_desc_tree *d_ptr, pst_id2_tree *m_head) { pst_mapi_object * list; pst_id2_tree *id2_head = m_head; pst_id2_tree *id2_ptr = NULL; pst_item *item = NULL; pst_item_attach *attach = NULL; int32_t x; DEBUG_ENT("pst_parse_item"); if (!d_ptr) { DEBUG_WARN(("you cannot pass me a NULL! I don't want it!\n")); DEBUG_RET(); return NULL; } if (!d_ptr->desc) { DEBUG_WARN(("why is d_ptr->desc == NULL? I don't want to do anything else with this record\n")); DEBUG_RET(); return NULL; } if (d_ptr->assoc_tree) { if (m_head) { DEBUG_WARN(("supplied master head, but have a list that is building a new id2_head\n")); m_head = NULL; } id2_head = pst_build_id2(pf, d_ptr->assoc_tree); } pst_printID2ptr(id2_head); list = pst_parse_block(pf, d_ptr->desc->i_id, id2_head); if (!list) { DEBUG_WARN(("pst_parse_block() returned an error for d_ptr->desc->i_id [%#"PRIx64"]\n", d_ptr->desc->i_id)); if (!m_head) pst_free_id2(id2_head); DEBUG_RET(); return NULL; } item = (pst_item*) pst_malloc(sizeof(pst_item)); memset(item, 0, sizeof(pst_item)); item->pf = pf; if (pst_process(d_ptr->desc->i_id, list, item, NULL)) { DEBUG_WARN(("pst_process() returned non-zero value. That is an error\n")); pst_freeItem(item); pst_free_list(list); if (!m_head) pst_free_id2(id2_head); DEBUG_RET(); return NULL; } pst_free_list(list); if ((id2_ptr = pst_getID2(id2_head, (uint64_t)0x692))) { // DSN/MDN reports? DEBUG_INFO(("DSN/MDN processing\n")); list = pst_parse_block(pf, id2_ptr->id->i_id, id2_ptr->child); if (list) { for (x=0; x < list->count_objects; x++) { attach = (pst_item_attach*) pst_malloc(sizeof(pst_item_attach)); memset(attach, 0, sizeof(pst_item_attach)); attach->next = item->attach; item->attach = attach; } if (pst_process(id2_ptr->id->i_id, list, item, item->attach)) { DEBUG_WARN(("ERROR pst_process() failed with DSN/MDN attachments\n")); pst_freeItem(item); pst_free_list(list); if (!m_head) pst_free_id2(id2_head); DEBUG_RET(); return NULL; } pst_free_list(list); } else { DEBUG_WARN(("ERROR error processing main DSN/MDN record\n")); // if (!m_head) pst_free_id2(id2_head); // DEBUG_RET(); // return item; } } if ((id2_ptr = pst_getID2(id2_head, (uint64_t)0x671))) { DEBUG_INFO(("ATTACHMENT processing attachment\n")); list = pst_parse_block(pf, id2_ptr->id->i_id, id2_ptr->child); if (!list) { if (item->flags & PST_FLAG_HAS_ATTACHMENT) { // Only report an error if we expected to see an attachment table and didn't. DEBUG_WARN(("ERROR error processing main attachment record\n")); } if (!m_head) pst_free_id2(id2_head); DEBUG_RET(); return item; } for (x=0; x < list->count_objects; x++) { attach = (pst_item_attach*) pst_malloc(sizeof(pst_item_attach)); memset(attach, 0, sizeof(pst_item_attach)); attach->next = item->attach; item->attach = attach; } if (pst_process(id2_ptr->id->i_id, list, item, item->attach)) { DEBUG_WARN(("ERROR pst_process() failed with attachments\n")); pst_freeItem(item); pst_free_list(list); if (!m_head) pst_free_id2(id2_head); DEBUG_RET(); return NULL; } pst_free_list(list); // now we will have initial information of each attachment stored in item->attach... // we must now read the secondary record for each based on the id2_val associated with // each attachment for (attach = item->attach; attach; attach = attach->next) { DEBUG_WARN(("initial attachment id2 %#"PRIx64"\n", attach->id2_val)); if ((id2_ptr = pst_getID2(id2_head, attach->id2_val))) { DEBUG_WARN(("initial attachment id2 found id %#"PRIx64"\n", id2_ptr->id->i_id)); // id2_ptr is a record describing the attachment // we pass NULL instead of id2_head cause we don't want it to // load all the extra stuff here. list = pst_parse_block(pf, id2_ptr->id->i_id, NULL); if (!list) { DEBUG_WARN(("ERROR error processing an attachment record\n")); continue; } if (list->count_objects > 1) { DEBUG_WARN(("ERROR probably fatal, list count array will overrun attach structure.\n")); } // reprocess the same attachment list against new data // this might update attach->id2_val if (pst_process(id2_ptr->id->i_id, list, item, attach)) { DEBUG_WARN(("ERROR pst_process() failed with an attachment\n")); pst_free_list(list); continue; } pst_free_list(list); // As per 2.4.6.2 in the spec, the attachment data is stored as a child of the // attachment object, so we pass in id2_ptr as the head to search from. id2_ptr = pst_getID2(id2_ptr->child, attach->id2_val); if (id2_ptr) { DEBUG_WARN(("second pass attachment updating id2 %#"PRIx64" found i_id %#"PRIx64"\n", attach->id2_val, id2_ptr->id->i_id)); // i_id has been updated to the datablock containing the attachment data attach->i_id = id2_ptr->id->i_id; attach->id2_head = deep_copy(id2_ptr->child); } else { DEBUG_WARN(("have not located the correct value for the attachment [%#"PRIx64"]\n", attach->id2_val)); } } else { DEBUG_WARN(("ERROR cannot locate id2 value %#"PRIx64"\n", attach->id2_val)); attach->id2_val = 0; // suppress this missing attachment } } } if (!m_head) pst_free_id2(id2_head); DEBUG_RET(); return item; } static void freeall(pst_subblocks *subs, pst_block_offset_pointer *p1, pst_block_offset_pointer *p2, pst_block_offset_pointer *p3, pst_block_offset_pointer *p4, pst_block_offset_pointer *p5, pst_block_offset_pointer *p6, pst_block_offset_pointer *p7); static void freeall(pst_subblocks *subs, pst_block_offset_pointer *p1, pst_block_offset_pointer *p2, pst_block_offset_pointer *p3, pst_block_offset_pointer *p4, pst_block_offset_pointer *p5, pst_block_offset_pointer *p6, pst_block_offset_pointer *p7) { size_t i; for (i=0; isubblock_count; i++) { if (subs->subs[i].buf) free(subs->subs[i].buf); } free(subs->subs); if (p1->needfree) free(p1->from); if (p2->needfree) free(p2->from); if (p3->needfree) free(p3->from); if (p4->needfree) free(p4->from); if (p5->needfree) free(p5->from); if (p6->needfree) free(p6->from); if (p7->needfree) free(p7->from); } /** Process a low level descriptor block (0x0101, 0xbcec, 0x7cec) into a * list of MAPI objects, each of which contains a list of MAPI elements. * * @return list of MAPI objects */ static pst_mapi_object* pst_parse_block(pst_file *pf, uint64_t block_id, pst_id2_tree *i2_head) { pst_mapi_object *mo_head = NULL; char *buf = NULL; size_t read_size = 0; pst_subblocks subblocks; pst_mapi_object *mo_ptr = NULL; pst_block_offset_pointer block_offset1; pst_block_offset_pointer block_offset2; pst_block_offset_pointer block_offset3; pst_block_offset_pointer block_offset4; pst_block_offset_pointer block_offset5; pst_block_offset_pointer block_offset6; pst_block_offset_pointer block_offset7; int32_t x; int32_t num_mapi_objects; int32_t count_mapi_objects; int32_t num_mapi_elements; int32_t count_mapi_elements; int block_type; uint32_t rec_size = 0; char* list_start; char* fr_ptr; char* to_ptr; char* ind2_end = NULL; char* ind2_ptr = NULL; char* ind2_block_start = NULL; size_t ind2_max_block_size = pf->do_read64 ? 0x1FF0 : 0x1FF4; pst_x_attrib_ll *mapptr; pst_block_hdr block_hdr; pst_table3_rec table3_rec; //for type 3 (0x0101) blocks struct { unsigned char seven_c; unsigned char item_count; uint16_t u1; uint16_t u2; uint16_t u3; uint16_t rec_size; uint32_t b_five_offset; uint32_t ind2_offset; uint16_t u7; uint16_t u8; } seven_c_blk; struct _type_d_rec { uint32_t id; uint32_t u1; } * type_d_rec; struct { uint16_t type; uint16_t ref_type; uint32_t value; } table_rec; //for type 1 (0xBCEC) blocks struct { uint16_t ref_type; uint16_t type; uint16_t ind2_off; uint8_t size; uint8_t slot; } table2_rec; //for type 2 (0x7CEC) blocks DEBUG_ENT("pst_parse_block"); if ((read_size = pst_ff_getIDblock_dec(pf, block_id, &buf)) == 0) { DEBUG_WARN(("Error reading block id %#"PRIx64"\n", block_id)); if (buf) free (buf); DEBUG_RET(); return NULL; } block_offset1.needfree = 0; block_offset2.needfree = 0; block_offset3.needfree = 0; block_offset4.needfree = 0; block_offset5.needfree = 0; block_offset6.needfree = 0; block_offset7.needfree = 0; memcpy(&block_hdr, buf, sizeof(block_hdr)); LE16_CPU(block_hdr.index_offset); LE16_CPU(block_hdr.type); LE32_CPU(block_hdr.offset); DEBUG_INFO(("block header (index_offset=%#hx, type=%#hx, offset=%#hx)\n", block_hdr.index_offset, block_hdr.type, block_hdr.offset)); if (block_hdr.index_offset == (uint16_t)0x0101) { //type 3 size_t i; char *b_ptr = buf + 8; subblocks.subblock_count = block_hdr.type; subblocks.subs = malloc(sizeof(pst_subblock) * subblocks.subblock_count); for (i=0; i 0) { if (pst_getBlockOffsetPointer(pf, i2_head, &subblocks, table_rec.value, &block_offset5)) { DEBUG_WARN(("internal error (7c.b5.desc offset %#x) in reading block id %#"PRIx64"\n", table_rec.value, block_id)); freeall(&subblocks, &block_offset1, &block_offset2, &block_offset3, &block_offset4, &block_offset5, &block_offset6, &block_offset7); DEBUG_RET(); return NULL; } // this will give the number of records in this block num_mapi_objects = (block_offset5.to - block_offset5.from) / (4 + table_rec.ref_type); if (pst_getBlockOffsetPointer(pf, i2_head, &subblocks, seven_c_blk.ind2_offset, &block_offset6)) { DEBUG_WARN(("internal error (7c.ind2 offset %#x) in reading block id %#"PRIx64"\n", seven_c_blk.ind2_offset, block_id)); freeall(&subblocks, &block_offset1, &block_offset2, &block_offset3, &block_offset4, &block_offset5, &block_offset6, &block_offset7); DEBUG_RET(); return NULL; } ind2_ptr = block_offset6.from; ind2_block_start = ind2_ptr; ind2_end = block_offset6.to; } else { num_mapi_objects = 0; } DEBUG_INFO(("7cec block index2 pointer %#x and end %#x\n", ind2_ptr, ind2_end)); } else { DEBUG_WARN(("ERROR: Unknown block constant - %#hx for id %#"PRIx64"\n", block_hdr.type, block_id)); freeall(&subblocks, &block_offset1, &block_offset2, &block_offset3, &block_offset4, &block_offset5, &block_offset6, &block_offset7); DEBUG_RET(); return NULL; } DEBUG_INFO(("found %i mapi objects each with %i mapi elements\n", num_mapi_objects, num_mapi_elements)); for (count_mapi_objects=0; count_mapi_objectsnext = mo_head; mo_head = mo_ptr; // allocate the array of mapi elements mo_ptr->elements = (pst_mapi_element**) pst_malloc(sizeof(pst_mapi_element)*num_mapi_elements); mo_ptr->count_elements = num_mapi_elements; mo_ptr->orig_count = num_mapi_elements; mo_ptr->count_objects = (int32_t)num_mapi_objects; // each record will have a record of the total number of records for (x=0; xelements[x] = NULL; DEBUG_INFO(("going to read %i mapi elements for mapi object %i\n", num_mapi_elements, count_mapi_objects)); fr_ptr = list_start; // initialize fr_ptr to the start of the list. x = 0; // x almost tracks count_mapi_elements, but see 'continue' statement below for (count_mapi_elements=0; count_mapi_elements= (int)(table2_rec.ind2_off + table2_rec.size)) { size_t n = table2_rec.size; size_t m = sizeof(table_rec.value); if (n <= m) { memcpy(&table_rec.value, ind2_ptr + table2_rec.ind2_off, n); } else { value_pointer = ind2_ptr + table2_rec.ind2_off; value_size = n; } //LE32_CPU(table_rec.value); // done later, some may be order invariant } else { DEBUG_WARN (("Trying to read outside buffer, buffer size %#x, offset %#x, data size %#x\n", read_size, ind2_end-ind2_ptr+table2_rec.ind2_off, table2_rec.size)); } fr_ptr += sizeof(table2_rec); } else { DEBUG_WARN(("Missing code for block_type %i\n", block_type)); freeall(&subblocks, &block_offset1, &block_offset2, &block_offset3, &block_offset4, &block_offset5, &block_offset6, &block_offset7); pst_free_list(mo_head); DEBUG_RET(); return NULL; } DEBUG_INFO(("reading element %i (type=%#x, ref_type=%#x, value=%#x)\n", x, table_rec.type, table_rec.ref_type, table_rec.value)); if (!mo_ptr->elements[x]) { mo_ptr->elements[x] = (pst_mapi_element*) pst_malloc(sizeof(pst_mapi_element)); } memset(mo_ptr->elements[x], 0, sizeof(pst_mapi_element)); //init it // check here to see if the id of the attribute is a mapped one mapptr = pf->x_head; while (mapptr && (mapptr->map < table_rec.type)) mapptr = mapptr->next; if (mapptr && (mapptr->map == table_rec.type)) { if (mapptr->mytype == PST_MAP_ATTRIB) { mo_ptr->elements[x]->mapi_id = *((uint32_t*)mapptr->data); DEBUG_INFO(("Mapped attrib %#x to %#x\n", table_rec.type, mo_ptr->elements[x]->mapi_id)); } else if (mapptr->mytype == PST_MAP_HEADER) { DEBUG_INFO(("Internet Header mapping found %#"PRIx32" to %s\n", table_rec.type, mapptr->data)); mo_ptr->elements[x]->mapi_id = (uint32_t)PST_ATTRIB_HEADER; mo_ptr->elements[x]->extra = mapptr->data; } else { DEBUG_WARN(("Missing assertion failure\n")); // nothing, should be assertion failure here } } else { mo_ptr->elements[x]->mapi_id = table_rec.type; } mo_ptr->elements[x]->type = 0; // checked later before it is set /* Reference Types 0x0002 - Signed 16bit value 0x0003 - Signed 32bit value 0x0004 - 4-byte floating point 0x0005 - Floating point double 0x0006 - Signed 64-bit int 0x0007 - Application Time 0x000A - 32-bit error value 0x000B - Boolean (non-zero = true) 0x000D - Embedded Object 0x0014 - 8-byte signed integer (64-bit) 0x001E - Null terminated String 0x001F - Unicode string 0x0040 - Systime - Filetime structure 0x0048 - OLE Guid 0x0102 - Binary data 0x1003 - Array of 32bit values 0x1014 - Array of 64bit values 0x101E - Array of Strings 0x1102 - Array of Binary data */ if (table_rec.ref_type == (uint16_t)0x0002 || table_rec.ref_type == (uint16_t)0x0003 || table_rec.ref_type == (uint16_t)0x000b) { //contains 32 bits of data mo_ptr->elements[x]->size = sizeof(int32_t); mo_ptr->elements[x]->type = table_rec.ref_type; mo_ptr->elements[x]->data = pst_malloc(sizeof(int32_t)); memcpy(mo_ptr->elements[x]->data, &(table_rec.value), sizeof(int32_t)); // are we missing an LE32_CPU() call here? table_rec.value is still // in the original order. } else if (table_rec.ref_type == (uint16_t)0x0005 || table_rec.ref_type == (uint16_t)0x000d || table_rec.ref_type == (uint16_t)0x0014 || table_rec.ref_type == (uint16_t)0x001e || table_rec.ref_type == (uint16_t)0x001f || table_rec.ref_type == (uint16_t)0x0040 || table_rec.ref_type == (uint16_t)0x0048 || table_rec.ref_type == (uint16_t)0x0102 || table_rec.ref_type == (uint16_t)0x1003 || table_rec.ref_type == (uint16_t)0x1014 || table_rec.ref_type == (uint16_t)0x101e || table_rec.ref_type == (uint16_t)0x101f || table_rec.ref_type == (uint16_t)0x1102) { //contains index reference to data LE32_CPU(table_rec.value); if (value_pointer) { // in a type 2 block, with a value that is more than 4 bytes // directly stored in this block. mo_ptr->elements[x]->size = value_size; mo_ptr->elements[x]->type = table_rec.ref_type; mo_ptr->elements[x]->data = pst_malloc(value_size); memcpy(mo_ptr->elements[x]->data, value_pointer, value_size); } else if (pst_getBlockOffsetPointer(pf, i2_head, &subblocks, table_rec.value, &block_offset7)) { if ((table_rec.value & 0xf) == (uint32_t)0xf) { DEBUG_WARN(("failed to get block offset for table_rec.value of %#x to be read later.\n", table_rec.value)); mo_ptr->elements[x]->size = 0; mo_ptr->elements[x]->data = NULL; mo_ptr->elements[x]->type = table_rec.value; } else { if (table_rec.value) { DEBUG_WARN(("failed to get block offset for table_rec.value of %#x\n", table_rec.value)); } mo_ptr->count_elements --; //we will be skipping a row continue; } } else { value_size = (size_t)(block_offset7.to - block_offset7.from); mo_ptr->elements[x]->size = value_size; mo_ptr->elements[x]->type = table_rec.ref_type; mo_ptr->elements[x]->data = pst_malloc(value_size+1); memcpy(mo_ptr->elements[x]->data, block_offset7.from, value_size); mo_ptr->elements[x]->data[value_size] = '\0'; // it might be a string, null terminate it. } if (table_rec.ref_type == (uint16_t)0xd) { // there is still more to do for the type of 0xD embedded objects type_d_rec = (struct _type_d_rec*) mo_ptr->elements[x]->data; LE32_CPU(type_d_rec->id); mo_ptr->elements[x]->size = pst_ff_getID2block(pf, type_d_rec->id, i2_head, &(mo_ptr->elements[x]->data)); if (!mo_ptr->elements[x]->size){ DEBUG_WARN(("not able to read the ID2 data. Setting to be read later. %#x\n", type_d_rec->id)); mo_ptr->elements[x]->type = type_d_rec->id; // fetch before freeing data, alias pointer free(mo_ptr->elements[x]->data); mo_ptr->elements[x]->data = NULL; } } if (table_rec.ref_type == (uint16_t)0x1f) { // there is more to do for the type 0x1f unicode strings size_t rc; static pst_vbuf *utf16buf = NULL; static pst_vbuf *utf8buf = NULL; if (!utf16buf) utf16buf = pst_vballoc((size_t)1024); if (!utf8buf) utf8buf = pst_vballoc((size_t)1024); //need UTF-16 zero-termination pst_vbset(utf16buf, mo_ptr->elements[x]->data, mo_ptr->elements[x]->size); pst_vbappend(utf16buf, "\0\0", (size_t)2); DEBUG_INFO(("Iconv in:\n")); DEBUG_HEXDUMPC(utf16buf->b, utf16buf->dlen, 0x10); rc = pst_vb_utf16to8(utf8buf, utf16buf->b, utf16buf->dlen); if (rc == (size_t)-1) { DEBUG_WARN(("Failed to convert utf-16 to utf-8\n")); } else { free(mo_ptr->elements[x]->data); mo_ptr->elements[x]->size = utf8buf->dlen; mo_ptr->elements[x]->data = pst_malloc(utf8buf->dlen); memcpy(mo_ptr->elements[x]->data, utf8buf->b, utf8buf->dlen); } DEBUG_INFO(("Iconv out:\n")); DEBUG_HEXDUMPC(mo_ptr->elements[x]->data, mo_ptr->elements[x]->size, 0x10); } if (mo_ptr->elements[x]->type == 0) mo_ptr->elements[x]->type = table_rec.ref_type; } else { DEBUG_WARN(("ERROR Unknown ref_type %#hx\n", table_rec.ref_type)); } x++; } DEBUG_INFO(("increasing ind2_ptr by %i [%#x] bytes. Was %#x, Now %#x\n", rec_size, rec_size, ind2_ptr, ind2_ptr+rec_size)); ind2_ptr += rec_size; // ind2 rows do not get split between blocks. See PST spec, 2.3.4.4 "Row Matrix". if (ind2_ptr + rec_size > ind2_block_start + ind2_max_block_size) { ind2_block_start += ind2_max_block_size; DEBUG_INFO(("advancing ind2_ptr to next block. Was %#x, Now %#x\n", ind2_ptr, ind2_block_start)); ind2_ptr = ind2_block_start; } } freeall(&subblocks, &block_offset1, &block_offset2, &block_offset3, &block_offset4, &block_offset5, &block_offset6, &block_offset7); DEBUG_RET(); return mo_head; } // This version of free does NULL check first #define SAFE_FREE(x) {if (x) free(x);} #define SAFE_FREE_STR(x) SAFE_FREE(x.str) #define SAFE_FREE_BIN(x) SAFE_FREE(x.data) // check if item->email is NULL, and init if so #define MALLOC_EMAIL(x) { if (!x->email) { x->email = (pst_item_email*) pst_malloc(sizeof(pst_item_email)); memset(x->email, 0, sizeof(pst_item_email) );} } #define MALLOC_FOLDER(x) { if (!x->folder) { x->folder = (pst_item_folder*) pst_malloc(sizeof(pst_item_folder)); memset(x->folder, 0, sizeof(pst_item_folder) );} } #define MALLOC_CONTACT(x) { if (!x->contact) { x->contact = (pst_item_contact*) pst_malloc(sizeof(pst_item_contact)); memset(x->contact, 0, sizeof(pst_item_contact) );} } #define MALLOC_MESSAGESTORE(x) { if (!x->message_store) { x->message_store = (pst_item_message_store*) pst_malloc(sizeof(pst_item_message_store)); memset(x->message_store, 0, sizeof(pst_item_message_store));} } #define MALLOC_JOURNAL(x) { if (!x->journal) { x->journal = (pst_item_journal*) pst_malloc(sizeof(pst_item_journal)); memset(x->journal, 0, sizeof(pst_item_journal) );} } #define MALLOC_APPOINTMENT(x) { if (!x->appointment) { x->appointment = (pst_item_appointment*) pst_malloc(sizeof(pst_item_appointment)); memset(x->appointment, 0, sizeof(pst_item_appointment) );} } // malloc space and copy the current item's data null terminated #define LIST_COPY(targ, type) { \ targ = type pst_realloc(targ, list->elements[x]->size+1); \ memcpy(targ, list->elements[x]->data, list->elements[x]->size);\ memset(((char*)targ)+list->elements[x]->size, 0, (size_t)1); \ } #define LIST_COPY_CSTR(targ) { \ if ((list->elements[x]->type == 0x1f) || \ (list->elements[x]->type == 0x1e) || \ (list->elements[x]->type == 0x102)) { \ LIST_COPY(targ, (char*)) \ } \ else { \ DEBUG_WARN(("src not 0x1e or 0x1f or 0x102 for string dst\n")); \ DEBUG_HEXDUMP(list->elements[x]->data, list->elements[x]->size); \ SAFE_FREE(targ); \ targ = NULL; \ } \ } #define LIST_COPY_BOOL(label, targ) { \ if (list->elements[x]->type != 0x0b) { \ DEBUG_WARN(("src not 0x0b for boolean dst\n")); \ DEBUG_HEXDUMP(list->elements[x]->data, list->elements[x]->size); \ } \ if (*(int16_t*)list->elements[x]->data) { \ DEBUG_INFO((label" - True\n")); \ targ = 1; \ } else { \ DEBUG_INFO((label" - False\n")); \ targ = 0; \ } \ } #define LIST_COPY_EMAIL_BOOL(label, targ) { \ MALLOC_EMAIL(item); \ LIST_COPY_BOOL(label, targ) \ } #define LIST_COPY_CONTACT_BOOL(label, targ) { \ MALLOC_CONTACT(item); \ LIST_COPY_BOOL(label, targ) \ } #define LIST_COPY_APPT_BOOL(label, targ) { \ MALLOC_APPOINTMENT(item); \ LIST_COPY_BOOL(label, targ) \ } #define LIST_COPY_INT16_N(targ) { \ if (list->elements[x]->type != 0x02) { \ DEBUG_WARN(("src not 0x02 for int16 dst\n")); \ DEBUG_HEXDUMP(list->elements[x]->data, list->elements[x]->size); \ } \ memcpy(&(targ), list->elements[x]->data, sizeof(targ)); \ LE16_CPU(targ); \ } #define LIST_COPY_INT16(label, targ) { \ LIST_COPY_INT16_N(targ); \ DEBUG_INFO((label" - %i %#x\n", (int)targ, (int)targ)); \ } #define LIST_COPY_INT32_N(targ) { \ if (list->elements[x]->type != 0x03) { \ DEBUG_WARN(("src not 0x03 for int32 dst\n")); \ DEBUG_HEXDUMP(list->elements[x]->data, list->elements[x]->size); \ } \ memcpy(&(targ), list->elements[x]->data, sizeof(targ)); \ LE32_CPU(targ); \ } #define LIST_COPY_INT32(label, targ) { \ LIST_COPY_INT32_N(targ); \ DEBUG_INFO((label" - %i %#x\n", (int)targ, (int)targ)); \ } #define LIST_COPY_EMAIL_INT32(label, targ) { \ MALLOC_EMAIL(item); \ LIST_COPY_INT32(label, targ); \ } #define LIST_COPY_APPT_INT32(label, targ) { \ MALLOC_APPOINTMENT(item); \ LIST_COPY_INT32(label, targ); \ } #define LIST_COPY_FOLDER_INT32(label, targ) { \ MALLOC_FOLDER(item); \ LIST_COPY_INT32(label, targ); \ } #define LIST_COPY_STORE_INT32(label, targ) { \ MALLOC_MESSAGESTORE(item); \ LIST_COPY_INT32(label, targ); \ } #define LIST_COPY_ENUM(label, targ, delta, count, ...) { \ char *tlabels[] = {__VA_ARGS__}; \ LIST_COPY_INT32_N(targ); \ targ += delta; \ DEBUG_INFO((label" - %s [%i]\n", \ (((int)targ < 0) || ((int)targ >= count)) \ ? "**invalid" \ : tlabels[(int)targ], (int)targ)); \ } #define LIST_COPY_EMAIL_ENUM(label, targ, delta, count, ...) { \ MALLOC_EMAIL(item); \ LIST_COPY_ENUM(label, targ, delta, count, __VA_ARGS__); \ } #define LIST_COPY_APPT_ENUM(label, targ, delta, count, ...) { \ MALLOC_APPOINTMENT(item); \ LIST_COPY_ENUM(label, targ, delta, count, __VA_ARGS__); \ } #define LIST_COPY_ENUM16(label, targ, delta, count, ...) { \ char *tlabels[] = {__VA_ARGS__}; \ LIST_COPY_INT16_N(targ); \ targ += delta; \ DEBUG_INFO((label" - %s [%i]\n", \ (((int)targ < 0) || ((int)targ >= count)) \ ? "**invalid" \ : tlabels[(int)targ], (int)targ)); \ } #define LIST_COPY_CONTACT_ENUM16(label, targ, delta, count, ...) { \ MALLOC_CONTACT(item); \ LIST_COPY_ENUM16(label, targ, delta, count, __VA_ARGS__); \ } #define LIST_COPY_ENTRYID(label, targ) { \ LIST_COPY(targ, (pst_entryid*)); \ LE32_CPU(targ->u1); \ LE32_CPU(targ->id); \ DEBUG_INFO((label" u1=%#x, id=%#x\n", targ->u1, targ->id)); \ } #define LIST_COPY_EMAIL_ENTRYID(label, targ) { \ MALLOC_EMAIL(item); \ LIST_COPY_ENTRYID(label, targ); \ } #define LIST_COPY_STORE_ENTRYID(label, targ) { \ MALLOC_MESSAGESTORE(item); \ LIST_COPY_ENTRYID(label, targ); \ } // malloc space and copy the current item's data null terminated // including the utf8 flag #define LIST_COPY_STR(label, targ) { \ LIST_COPY_CSTR(targ.str); \ targ.is_utf8 = (list->elements[x]->type == 0x1f) ? 1 : 0; \ DEBUG_INFO((label" - unicode %d - %s\n", targ.is_utf8, targ.str)); \ } #define LIST_COPY_EMAIL_STR(label, targ) { \ MALLOC_EMAIL(item); \ LIST_COPY_STR(label, targ); \ } #define LIST_COPY_CONTACT_STR(label, targ) { \ MALLOC_CONTACT(item); \ LIST_COPY_STR(label, targ); \ } #define LIST_COPY_APPT_STR(label, targ) { \ MALLOC_APPOINTMENT(item); \ LIST_COPY_STR(label, targ); \ } #define LIST_COPY_JOURNAL_STR(label, targ) { \ MALLOC_JOURNAL(item); \ LIST_COPY_STR(label, targ); \ } // malloc space and copy the item filetime #define LIST_COPY_TIME(label, targ) { \ if ((list->elements[x]->type != 0x40) || \ (list->elements[x]->size != sizeof(FILETIME))) { \ DEBUG_WARN(("src not 0x40 or wrong length for filetime dst\n")); \ DEBUG_HEXDUMP(list->elements[x]->data, list->elements[x]->size); \ } \ else { \ targ = (FILETIME*) pst_realloc(targ, sizeof(FILETIME)); \ memcpy(targ, list->elements[x]->data, sizeof(FILETIME)); \ LE32_CPU(targ->dwLowDateTime); \ LE32_CPU(targ->dwHighDateTime); \ DEBUG_INFO((label" - %s", pst_fileTimeToAscii(targ, time_buffer))); \ } \ } #define LIST_COPY_EMAIL_TIME(label, targ) { \ MALLOC_EMAIL(item); \ LIST_COPY_TIME(label, targ); \ } #define LIST_COPY_CONTACT_TIME(label, targ) { \ MALLOC_CONTACT(item); \ LIST_COPY_TIME(label, targ); \ } #define LIST_COPY_APPT_TIME(label, targ) { \ MALLOC_APPOINTMENT(item); \ LIST_COPY_TIME(label, targ); \ } #define LIST_COPY_JOURNAL_TIME(label, targ) { \ MALLOC_JOURNAL(item); \ LIST_COPY_TIME(label, targ); \ } // malloc space and copy the current item's data and size #define LIST_COPY_BIN(targ) { \ targ.size = list->elements[x]->size; \ if (targ.size) { \ targ.data = (char*)pst_realloc(targ.data, targ.size); \ memcpy(targ.data, list->elements[x]->data, targ.size); \ } \ else { \ SAFE_FREE_BIN(targ); \ targ.data = NULL; \ } \ } #define LIST_COPY_EMAIL_BIN(label, targ) { \ MALLOC_EMAIL(item); \ LIST_COPY_BIN(targ); \ DEBUG_INFO((label"\n")); \ } #define LIST_COPY_APPT_BIN(label, targ) { \ MALLOC_APPOINTMENT(item); \ LIST_COPY_BIN(targ); \ DEBUG_INFO((label"\n")); \ DEBUG_HEXDUMP(targ.data, targ.size); \ } #define NULL_CHECK(x) { if (!x) { DEBUG_WARN(("NULL_CHECK: Null Found\n")); break;} } /** * process the list of MAPI objects produced from parse_block() * * @param block_id block number used by parse_block() to produce these MAPI objects * @param list pointer to the list of MAPI objects from parse_block() * @param item pointer to the high level item to be updated from the list. * this item may be an email, contact or other sort of item. * the type of this item is generally set by the MAPI elements * from the list. * @param attach pointer to the list of attachment records. If * this is non-null, the length of the this attachment list * must be at least as large as the length of the MAPI objects list. * * @return 0 for ok, -1 for error. */ static int pst_process(uint64_t block_id, pst_mapi_object *list, pst_item *item, pst_item_attach *attach) { DEBUG_ENT("pst_process"); if (!item) { DEBUG_WARN(("item cannot be NULL.\n")); DEBUG_RET(); return -1; } item->block_id = block_id; while (list) { int32_t x; char time_buffer[30]; for (x=0; xcount_elements; x++) { int32_t t; uint32_t ut; DEBUG_INFO(("#%d - mapi-id: %#x type: %#x length: %#x\n", x, list->elements[x]->mapi_id, list->elements[x]->type, list->elements[x]->size)); switch (list->elements[x]->mapi_id) { case PST_ATTRIB_HEADER: // CUSTOM attribute for saying the Extra Headers if (list->elements[x]->extra) { if (list->elements[x]->type == 0x0101e) { // an array of strings, rather than a single string int32_t string_length, i, offset, next_offset; int32_t p = 0; int32_t array_element_count = PST_LE_GET_INT32(list->elements[x]->data); p+=4; for (i = 1; i <= array_element_count; i++) { pst_item_extra_field *ef = (pst_item_extra_field*) pst_malloc(sizeof(pst_item_extra_field)); memset(ef, 0, sizeof(pst_item_extra_field)); offset = PST_LE_GET_INT32(list->elements[x]->data + p); p+=4; next_offset = (i == array_element_count) ? list->elements[x]->size : PST_LE_GET_INT32(list->elements[x]->data + p);; string_length = next_offset - offset; ef->value = pst_malloc(string_length + 1); memcpy(ef->value, list->elements[x]->data + offset, string_length); ef->value[string_length] = '\0'; ef->field_name = strdup(list->elements[x]->extra); ef->next = item->extra_fields; item->extra_fields = ef; DEBUG_INFO(("Extra Field - \"%s\" = \"%s\"\n", ef->field_name, ef->value)); } } else { // should be a single string pst_item_extra_field *ef = (pst_item_extra_field*) pst_malloc(sizeof(pst_item_extra_field)); memset(ef, 0, sizeof(pst_item_extra_field)); LIST_COPY_CSTR(ef->value); if (ef->value) { ef->field_name = strdup(list->elements[x]->extra); ef->next = item->extra_fields; item->extra_fields = ef; DEBUG_INFO(("Extra Field - \"%s\" = \"%s\"\n", ef->field_name, ef->value)); if (strcmp(ef->field_name, "content-type") == 0) { char *p = strstr(ef->value, "charset=\""); if (p) { p += 9; // skip over charset=" char *pp = strchr(p, '"'); if (pp) { *pp = '\0'; char *set = strdup(p); *pp = '"'; if (item->body_charset.str) free(item->body_charset.str); item->body_charset.str = set; item->body_charset.is_utf8 = 1; DEBUG_INFO(("body charset %s from content-type extra field\n", set)); } } } } else { DEBUG_WARN(("What does this mean? Internet header %s value\n", list->elements[x]->extra)); DEBUG_HEXDUMP(list->elements[x]->data, list->elements[x]->size); free(ef); // caught by valgrind } } } break; case 0x0002: // PR_ALTERNATE_RECIPIENT_ALLOWED if (list->elements[x]->type == 0x0b) { // If set to true, the sender allows this email to be autoforwarded LIST_COPY_EMAIL_BOOL("AutoForward allowed", item->email->autoforward); if (!item->email->autoforward) item->email->autoforward = -1; } else { DEBUG_WARN(("What does this mean?\n")); DEBUG_HEXDUMP(list->elements[x]->data, list->elements[x]->size); } break; case 0x0003: // Extended Attributes table DEBUG_INFO(("Extended Attributes Table - NOT PROCESSED\n")); break; case 0x0017: // PR_IMPORTANCE - How important the sender deems it to be LIST_COPY_EMAIL_ENUM("Importance Level", item->email->importance, 0, 3, "Low", "Normal", "High"); break; case 0x001A: // PR_MESSAGE_CLASS IPM.x if ((list->elements[x]->type == 0x1e) || (list->elements[x]->type == 0x1f)) { LIST_COPY_CSTR(item->ascii_type); if (!item->ascii_type) item->ascii_type = strdup("unknown"); if (pst_strincmp("IPM.Note", item->ascii_type, 8) == 0) item->type = PST_TYPE_NOTE; else if (pst_stricmp("IPM", item->ascii_type) == 0) item->type = PST_TYPE_NOTE; else if (pst_strincmp("IPM.Contact", item->ascii_type, 11) == 0) item->type = PST_TYPE_CONTACT; else if (pst_strincmp("REPORT.IPM.Note", item->ascii_type, 15) == 0) item->type = PST_TYPE_REPORT; else if (pst_strincmp("IPM.Activity", item->ascii_type, 12) == 0) item->type = PST_TYPE_JOURNAL; else if (pst_strincmp("IPM.Appointment", item->ascii_type, 15) == 0) item->type = PST_TYPE_APPOINTMENT; else if (pst_strincmp("IPM.Schedule.Meeting", item->ascii_type, 20) == 0) item->type = PST_TYPE_SCHEDULE; // meeting requests and responses transported over email else if (pst_strincmp("IPM.StickyNote", item->ascii_type, 14) == 0) item->type = PST_TYPE_STICKYNOTE; else if (pst_strincmp("IPM.Task", item->ascii_type, 8) == 0) item->type = PST_TYPE_TASK; else item->type = PST_TYPE_OTHER; DEBUG_INFO(("Message class %s [%"PRIi32"] \n", item->ascii_type, item->type)); } else { DEBUG_WARN(("What does this mean?\n")); DEBUG_HEXDUMP(list->elements[x]->data, list->elements[x]->size); } break; case 0x0023: // PR_ORIGINATOR_DELIVERY_REPORT_REQUESTED if (list->elements[x]->type == 0x0b) { // set if the sender wants a delivery report from all recipients LIST_COPY_EMAIL_BOOL("Global Delivery Report", item->email->delivery_report); } else { DEBUG_WARN(("What does this mean?\n")); DEBUG_HEXDUMP(list->elements[x]->data, list->elements[x]->size); } break; case 0x0026: // PR_PRIORITY LIST_COPY_EMAIL_ENUM("Priority", item->email->priority, 1, 3, "NonUrgent", "Normal", "Urgent"); break; case 0x0029: // PR_READ_RECEIPT_REQUESTED LIST_COPY_EMAIL_BOOL("Read Receipt", item->email->read_receipt); break; case 0x002B: // PR_RECIPIENT_REASSIGNMENT_PROHIBITED LIST_COPY_BOOL("Reassignment Prohibited (Private)", item->private_member); break; case 0x002E: // PR_ORIGINAL_SENSITIVITY - the sensitivity of the message before being replied to or forwarded LIST_COPY_EMAIL_ENUM("Original Sensitivity", item->email->original_sensitivity, 0, 4, "None", "Personal", "Private", "Company Confidential"); break; case 0x0032: // PR_REPORT_TIME LIST_COPY_EMAIL_TIME("Report time", item->email->report_time); break; case 0x0036: // PR_SENSITIVITY - sender's opinion of the sensitivity of an email LIST_COPY_EMAIL_ENUM("Sensitivity", item->email->sensitivity, 0, 4, "None", "Personal", "Private", "Company Confidential"); break; case 0x0037: // PR_SUBJECT raw subject { int off = 0; if ((list->elements[x]->size > 2) && (((uint8_t)list->elements[x]->data[0]) < 0x20)) { off = 2; } list->elements[x]->data += off; list->elements[x]->size -= off; LIST_COPY_STR("Raw Subject", item->subject); list->elements[x]->size += off; list->elements[x]->data -= off; } break; case 0x0039: // PR_CLIENT_SUBMIT_TIME Date Email Sent/Created LIST_COPY_EMAIL_TIME("Date sent", item->email->sent_date); break; case 0x003B: // PR_SENT_REPRESENTING_SEARCH_KEY Sender address 1 LIST_COPY_EMAIL_STR("Sent on behalf of address 1", item->email->outlook_sender); break; case 0x003F: // PR_RECEIVED_BY_ENTRYID Structure containing Recipient DEBUG_INFO(("Recipient Structure 1 -- NOT PROCESSED\n")); break; case 0x0040: // PR_RECEIVED_BY_NAME Name of Recipient Structure LIST_COPY_EMAIL_STR("Received By Name 1", item->email->outlook_received_name1); break; case 0x0041: // PR_SENT_REPRESENTING_ENTRYID Structure containing Sender DEBUG_INFO(("Sent on behalf of Structure 1 -- NOT PROCESSED\n")); break; case 0x0042: // PR_SENT_REPRESENTING_NAME LIST_COPY_EMAIL_STR("Sent on behalf of", item->email->outlook_sender_name); break; case 0x0043: // PR_RCVD_REPRESENTING_ENTRYID Recipient Structure 2 DEBUG_INFO(("Received on behalf of Structure -- NOT PROCESSED\n")); break; case 0x0044: // PR_RCVD_REPRESENTING_NAME LIST_COPY_EMAIL_STR("Received on behalf of", item->email->outlook_recipient_name); break; case 0x004F: // PR_REPLY_RECIPIENT_ENTRIES Reply-To Structure DEBUG_INFO(("Reply-To Structure -- NOT PROCESSED\n")); break; case 0x0050: // PR_REPLY_RECIPIENT_NAMES Name of Reply-To Structure LIST_COPY_EMAIL_STR("Reply-To", item->email->reply_to); break; case 0x0051: // PR_RECEIVED_BY_SEARCH_KEY Recipient Address 1 LIST_COPY_EMAIL_STR("Recipient's Address 1", item->email->outlook_recipient); break; case 0x0052: // PR_RCVD_REPRESENTING_SEARCH_KEY Recipient Address 2 LIST_COPY_EMAIL_STR("Recipient's Address 2", item->email->outlook_recipient2); break; case 0x0057: // PR_MESSAGE_TO_ME // this user is listed explicitly in the TO address LIST_COPY_EMAIL_BOOL("My address in TO field", item->email->message_to_me); break; case 0x0058: // PR_MESSAGE_CC_ME // this user is listed explicitly in the CC address LIST_COPY_EMAIL_BOOL("My address in CC field", item->email->message_cc_me); break; case 0x0059: // PR_MESSAGE_RECIP_ME // this user appears in TO, CC or BCC address list LIST_COPY_EMAIL_BOOL("Message addressed to me", item->email->message_recip_me); break; case 0x0063: // PR_RESPONSE_REQUESTED LIST_COPY_BOOL("Response requested", item->response_requested); break; case 0x0064: // PR_SENT_REPRESENTING_ADDRTYPE Access method for Sender Address LIST_COPY_EMAIL_STR("Sent on behalf of address type", item->email->sender_access); break; case 0x0065: // PR_SENT_REPRESENTING_EMAIL_ADDRESS Sender Address LIST_COPY_EMAIL_STR("Sent on behalf of address", item->email->sender_address); break; case 0x0070: // PR_CONVERSATION_TOPIC Processed Subject LIST_COPY_EMAIL_STR("Processed Subject (Conversation Topic)", item->email->processed_subject); break; case 0x0071: // PR_CONVERSATION_INDEX LIST_COPY_EMAIL_BIN("Conversation Index", item->email->conversation_index); break; case 0x0072: // PR_ORIGINAL_DISPLAY_BCC LIST_COPY_EMAIL_STR("Original display bcc", item->email->original_bcc); break; case 0x0073: // PR_ORIGINAL_DISPLAY_CC LIST_COPY_EMAIL_STR("Original display cc", item->email->original_cc); break; case 0x0074: // PR_ORIGINAL_DISPLAY_TO LIST_COPY_EMAIL_STR("Original display to", item->email->original_to); break; case 0x0075: // PR_RECEIVED_BY_ADDRTYPE Recipient Access Method LIST_COPY_EMAIL_STR("Received by Address type", item->email->recip_access); break; case 0x0076: // PR_RECEIVED_BY_EMAIL_ADDRESS Recipient Address LIST_COPY_EMAIL_STR("Received by Address", item->email->recip_address); break; case 0x0077: // PR_RCVD_REPRESENTING_ADDRTYPE Recipient Access Method 2 LIST_COPY_EMAIL_STR("Received on behalf of Address type", item->email->recip2_access); break; case 0x0078: // PR_RCVD_REPRESENTING_EMAIL_ADDRESS Recipient Address 2 LIST_COPY_EMAIL_STR("Received on behalf of Address", item->email->recip2_address); break; case 0x007D: // PR_TRANSPORT_MESSAGE_HEADERS Internet Header LIST_COPY_EMAIL_STR("Internet Header", item->email->header); break; case 0x0C04: // PR_NDR_REASON_CODE LIST_COPY_EMAIL_INT32("NDR reason code", item->email->ndr_reason_code); break; case 0x0C05: // PR_NDR_DIAG_CODE LIST_COPY_EMAIL_INT32("NDR diag code", item->email->ndr_diag_code); break; case 0x0C06: // PR_NON_RECEIPT_NOTIFICATION_REQUESTED DEBUG_INFO(("Non-Receipt Notification Requested -- NOT PROCESSED\n")); break; case 0x0C17: // PR_REPLY_REQUESTED LIST_COPY_EMAIL_BOOL("Reply Requested", item->email->reply_requested); break; case 0x0C19: // PR_SENDER_ENTRYID Sender Structure 2 DEBUG_INFO(("Sender Structure 2 -- NOT PROCESSED\n")); break; case 0x0C1A: // PR_SENDER_NAME Name of Sender Structure 2 LIST_COPY_EMAIL_STR("Name of Sender Structure 2", item->email->outlook_sender_name2); break; case 0x0C1B: // PR_SUPPLEMENTARY_INFO LIST_COPY_EMAIL_STR("Supplementary info", item->email->supplementary_info); break; case 0x0C1D: // PR_SENDER_SEARCH_KEY Name of Sender Address 2 LIST_COPY_EMAIL_STR("Name of Sender Address 2 (Sender search key)", item->email->outlook_sender2); break; case 0x0C1E: // PR_SENDER_ADDRTYPE Sender Address 2 access method LIST_COPY_EMAIL_STR("Sender Address type", item->email->sender2_access); break; case 0x0C1F: // PR_SENDER_EMAIL_ADDRESS Sender Address 2 LIST_COPY_EMAIL_STR("Sender Address", item->email->sender2_address); break; case 0x0C20: // PR_NDR_STATUS_CODE LIST_COPY_EMAIL_INT32("NDR status code", item->email->ndr_status_code); break; case 0x0E01: // PR_DELETE_AFTER_SUBMIT LIST_COPY_EMAIL_BOOL("Delete after submit", item->email->delete_after_submit); break; case 0x0E02: // PR_DISPLAY_BCC BCC Addresses LIST_COPY_EMAIL_STR("Display BCC Addresses", item->email->bcc_address); break; case 0x0E03: // PR_DISPLAY_CC CC Addresses LIST_COPY_EMAIL_STR("Display CC Addresses", item->email->cc_address); break; case 0x0E04: // PR_DISPLAY_TO Address Sent-To LIST_COPY_EMAIL_STR("Display Sent-To Address", item->email->sentto_address); break; case 0x0E06: // PR_MESSAGE_DELIVERY_TIME Date 3 - Email Arrival Date LIST_COPY_EMAIL_TIME("Date 3 (Delivery Time)", item->email->arrival_date); break; case 0x0E07: // PR_MESSAGE_FLAGS Email Flag LIST_COPY_EMAIL_INT32("Message Flags", item->flags); break; case 0x0E08: // PR_MESSAGE_SIZE Total size of a message object LIST_COPY_INT32("Message Size", item->message_size); break; case 0x0E0A: // PR_SENTMAIL_ENTRYID // folder that this message is sent to after submission LIST_COPY_EMAIL_ENTRYID("Sentmail EntryID", item->email->sentmail_folder); break; case 0x0E1D: // PR_NORMALIZED_SUBJECT LIST_COPY_EMAIL_STR("Normalized subject", item->email->outlook_normalized_subject); break; case 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 LIST_COPY_EMAIL_BOOL("Compressed RTF in Sync", item->email->rtf_in_sync); break; case 0x0E20: // PR_ATTACH_SIZE binary Attachment data in record NULL_CHECK(attach); LIST_COPY_INT32("Attachment Size", t); // ignore this. we either get data and size from 0x3701 // or id codes from 0x3701 or 0x67f2 break; case 0x0FF9: // PR_RECORD_KEY Record Header 1 LIST_COPY_BIN(item->record_key); DEBUG_INFO(("Record Key\n")); DEBUG_HEXDUMP(item->record_key.data, item->record_key.size); break; case 0x1000: // PR_BODY LIST_COPY_STR("Plain Text body", item->body); break; case 0x1001: // PR_REPORT_TEXT LIST_COPY_EMAIL_STR("Report Text", item->email->report_text); break; case 0x1006: // PR_RTF_SYNC_BODY_CRC LIST_COPY_EMAIL_INT32("RTF Sync Body CRC", item->email->rtf_body_crc); break; case 0x1007: // PR_RTF_SYNC_BODY_COUNT // a count of the *significant* characters in the rtf body. Doesn't count // whitespace and other ignorable characters LIST_COPY_EMAIL_INT32("RTF Sync Body character count", item->email->rtf_body_char_count); break; case 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 LIST_COPY_EMAIL_STR("RTF Sync body tag", item->email->rtf_body_tag); break; case 0x1009: // PR_RTF_COMPRESSED - rtf data is lzw compressed LIST_COPY_EMAIL_BIN("RTF Compressed body", item->email->rtf_compressed); break; case 0x1010: // PR_RTF_SYNC_PREFIX_COUNT // a count of the ignored characters before the first significant character LIST_COPY_EMAIL_INT32("RTF whitespace prefix count", item->email->rtf_ws_prefix_count); break; case 0x1011: // PR_RTF_SYNC_TRAILING_COUNT // a count of the ignored characters after the last significant character LIST_COPY_EMAIL_INT32("RTF whitespace tailing count", item->email->rtf_ws_trailing_count); break; case 0x1013: // HTML body LIST_COPY_EMAIL_STR("HTML body", item->email->htmlbody); break; case 0x1035: // Message ID LIST_COPY_EMAIL_STR("Message ID", item->email->messageid); break; case 0x1042: // in-reply-to LIST_COPY_EMAIL_STR("In-Reply-To", item->email->in_reply_to); break; case 0x1046: // Return Path - this seems to be the message-id of the rfc822 mail that is being returned LIST_COPY_EMAIL_STR("Return Path", item->email->return_path_address); break; case 0x3001: // PR_DISPLAY_NAME File As LIST_COPY_STR("Display Name", item->file_as); break; case 0x3002: // PR_ADDRTYPE LIST_COPY_CONTACT_STR("Address Type", item->contact->address1_transport); break; case 0x3003: // PR_EMAIL_ADDRESS LIST_COPY_CONTACT_STR("Contact email Address", item->contact->address1); break; case 0x3004: // PR_COMMENT Comment for item - usually folders LIST_COPY_STR("Comment", item->comment); break; case 0x3007: // PR_CREATION_TIME Date 4 - Creation Date? LIST_COPY_TIME("Date 4 (Item Creation Date)", item->create_date); break; case 0x3008: // PR_LAST_MODIFICATION_TIME Date 5 - Modify Date LIST_COPY_TIME("Date 5 (Modify Date)", item->modify_date); break; case 0x300B: // PR_SEARCH_KEY Record Header 2 LIST_COPY_EMAIL_STR("Record Search 2", item->email->outlook_search_key); break; case 0x35DF: // PR_VALID_FOLDER_MASK LIST_COPY_STORE_INT32("Valid Folder Mask", item->message_store->valid_mask); break; case 0x35E0: // PR_IPM_SUBTREE_ENTRYID Top of Personal Folder Record LIST_COPY_STORE_ENTRYID("Top of Personal Folder Record", item->message_store->top_of_personal_folder); break; case 0x35E2: // PR_IPM_OUTBOX_ENTRYID LIST_COPY_STORE_ENTRYID("Default Outbox Folder record", item->message_store->default_outbox_folder); break; case 0x35E3: // PR_IPM_WASTEBASKET_ENTRYID LIST_COPY_STORE_ENTRYID("Deleted Items Folder record", item->message_store->deleted_items_folder); break; case 0x35E4: // PR_IPM_SENTMAIL_ENTRYID LIST_COPY_STORE_ENTRYID("Sent Items Folder record", item->message_store->sent_items_folder); break; case 0x35E5: // PR_VIEWS_ENTRYID LIST_COPY_STORE_ENTRYID("User Views Folder record", item->message_store->user_views_folder); break; case 0x35E6: // PR_COMMON_VIEWS_ENTRYID LIST_COPY_STORE_ENTRYID("Common View Folder record", item->message_store->common_view_folder); break; case 0x35E7: // PR_FINDER_ENTRYID LIST_COPY_STORE_ENTRYID("Search Root Folder record", item->message_store->search_root_folder); break; case 0x3602: // PR_CONTENT_COUNT Number of emails stored in a folder LIST_COPY_FOLDER_INT32("Folder Email Count", item->folder->item_count); break; case 0x3603: // PR_CONTENT_UNREAD Number of unread emails LIST_COPY_FOLDER_INT32("Unread Email Count", item->folder->unseen_item_count); break; case 0x360A: // PR_SUBFOLDERS Has children MALLOC_FOLDER(item); LIST_COPY_BOOL("Has Subfolders", item->folder->subfolder); break; case 0x3613: // PR_CONTAINER_CLASS IPF.x LIST_COPY_CSTR(item->ascii_type); if (pst_strincmp("IPF.Note", item->ascii_type, 8) == 0) item->type = PST_TYPE_NOTE; else if (pst_strincmp("IPF.Imap", item->ascii_type, 8) == 0) item->type = PST_TYPE_NOTE; else if (pst_stricmp("IPF", item->ascii_type) == 0) item->type = PST_TYPE_NOTE; else if (pst_strincmp("IPF.Contact", item->ascii_type, 11) == 0) item->type = PST_TYPE_CONTACT; else if (pst_strincmp("IPF.Journal", item->ascii_type, 11) == 0) item->type = PST_TYPE_JOURNAL; else if (pst_strincmp("IPF.Appointment", item->ascii_type, 15) == 0) item->type = PST_TYPE_APPOINTMENT; else if (pst_strincmp("IPF.StickyNote", item->ascii_type, 14) == 0) item->type = PST_TYPE_STICKYNOTE; else if (pst_strincmp("IPF.Task", item->ascii_type, 8) == 0) item->type = PST_TYPE_TASK; else item->type = PST_TYPE_OTHER; DEBUG_INFO(("Container class %s [%"PRIi32"]\n", item->ascii_type, item->type)); break; case 0x3617: // PR_ASSOC_CONTENT_COUNT // associated content are items that are attached to this folder // but are hidden from users LIST_COPY_FOLDER_INT32("Associated Content count", item->folder->assoc_count); break; case 0x3701: // PR_ATTACH_DATA_OBJ binary data of attachment DEBUG_INFO(("Binary Data [Size %i]\n", list->elements[x]->size)); NULL_CHECK(attach); if (!list->elements[x]->data) { //special case attach->id2_val = list->elements[x]->type; DEBUG_INFO(("Seen a Reference. The data hasn't been loaded yet. [%#"PRIx64"]\n", attach->id2_val)); } else { LIST_COPY_BIN(attach->data); } break; case 0x3704: // PR_ATTACH_FILENAME Attachment filename (8.3) NULL_CHECK(attach); LIST_COPY_STR("Attachment Filename", attach->filename1); break; case 0x3705: // PR_ATTACH_METHOD NULL_CHECK(attach); LIST_COPY_ENUM("Attachment method", attach->method, 0, 7, "No Attachment", "Attach By Value", "Attach By Reference", "Attach by Reference Resolve", "Attach by Reference Only", "Embedded Message", "OLE"); break; case 0x3707: // PR_ATTACH_LONG_FILENAME Attachment filename (long?) NULL_CHECK(attach); LIST_COPY_STR("Attachment Filename long", attach->filename2); break; case 0x370B: // PR_RENDERING_POSITION // position in characters that the attachment appears in the plain text body NULL_CHECK(attach); LIST_COPY_INT32("Attachment Position", attach->position); break; case 0x370E: // PR_ATTACH_MIME_TAG Mime type of encoding NULL_CHECK(attach); LIST_COPY_STR("Attachment mime encoding", attach->mimetype); break; case 0x3710: // PR_ATTACH_MIME_SEQUENCE // sequence number for mime parts. Includes body NULL_CHECK(attach); LIST_COPY_INT32("Attachment Mime Sequence", attach->sequence); break; case 0x3712: // PR_ATTACH_CONTENT_ID // content identification header (Content-ID) NULL_CHECK(attach); LIST_COPY_STR("Content ID", attach->content_id); break; case 0x3A00: // PR_ACCOUNT LIST_COPY_CONTACT_STR("Contact's Account name", item->contact->account_name); break; case 0x3A01: // PR_ALTERNATE_RECIPIENT DEBUG_INFO(("Contact Alternate Recipient - NOT PROCESSED\n")); break; case 0x3A02: // PR_CALLBACK_TELEPHONE_NUMBER LIST_COPY_CONTACT_STR("Callback telephone number", item->contact->callback_phone); break; case 0x3A03: // PR_CONVERSION_PROHIBITED LIST_COPY_EMAIL_BOOL("Message Conversion Prohibited", item->email->conversion_prohibited); break; case 0x3A05: // PR_GENERATION suffix LIST_COPY_CONTACT_STR("Contacts Suffix", item->contact->suffix); break; case 0x3A06: // PR_GIVEN_NAME Contact's first name LIST_COPY_CONTACT_STR("Contacts First Name", item->contact->first_name); break; case 0x3A07: // PR_GOVERNMENT_ID_NUMBER LIST_COPY_CONTACT_STR("Contacts Government ID Number", item->contact->gov_id); break; case 0x3A08: // PR_BUSINESS_TELEPHONE_NUMBER LIST_COPY_CONTACT_STR("Business Telephone Number", item->contact->business_phone); break; case 0x3A09: // PR_HOME_TELEPHONE_NUMBER LIST_COPY_CONTACT_STR("Home Telephone Number", item->contact->home_phone); break; case 0x3A0A: // PR_INITIALS Contact's Initials LIST_COPY_CONTACT_STR("Contacts Initials", item->contact->initials); break; case 0x3A0B: // PR_KEYWORD LIST_COPY_CONTACT_STR("Keyword", item->contact->keyword); break; case 0x3A0C: // PR_LANGUAGE LIST_COPY_CONTACT_STR("Contact's Language", item->contact->language); break; case 0x3A0D: // PR_LOCATION LIST_COPY_CONTACT_STR("Contact's Location", item->contact->location); break; case 0x3A0E: // PR_MAIL_PERMISSION - Can the recipient receive and send email LIST_COPY_CONTACT_BOOL("Mail Permission", item->contact->mail_permission); break; case 0x3A0F: // PR_MHS_COMMON_NAME LIST_COPY_CONTACT_STR("MHS Common Name", item->contact->common_name); break; case 0x3A10: // PR_ORGANIZATIONAL_ID_NUMBER LIST_COPY_CONTACT_STR("Organizational ID #", item->contact->org_id); break; case 0x3A11: // PR_SURNAME Contact's Surname LIST_COPY_CONTACT_STR("Contacts Surname", item->contact->surname); break; case 0x3A12: // PR_ORIGINAL_ENTRY_ID DEBUG_INFO(("Original Entry ID - NOT PROCESSED\n")); break; case 0x3A13: // PR_ORIGINAL_DISPLAY_NAME DEBUG_INFO(("Original Display Name - NOT PROCESSED\n")); break; case 0x3A14: // PR_ORIGINAL_SEARCH_KEY DEBUG_INFO(("Original Search Key - NOT PROCESSED\n")); break; case 0x3A15: // PR_POSTAL_ADDRESS LIST_COPY_CONTACT_STR("Default Postal Address", item->contact->def_postal_address); break; case 0x3A16: // PR_COMPANY_NAME LIST_COPY_CONTACT_STR("Company Name", item->contact->company_name); break; case 0x3A17: // PR_TITLE - Job Title LIST_COPY_CONTACT_STR("Job Title", item->contact->job_title); break; case 0x3A18: // PR_DEPARTMENT_NAME LIST_COPY_CONTACT_STR("Department Name", item->contact->department); break; case 0x3A19: // PR_OFFICE_LOCATION LIST_COPY_CONTACT_STR("Office Location", item->contact->office_loc); break; case 0x3A1A: // PR_PRIMARY_TELEPHONE_NUMBER LIST_COPY_CONTACT_STR("Primary Telephone", item->contact->primary_phone); break; case 0x3A1B: // PR_BUSINESS2_TELEPHONE_NUMBER LIST_COPY_CONTACT_STR("Business Phone Number 2", item->contact->business_phone2); break; case 0x3A1C: // PR_MOBILE_TELEPHONE_NUMBER LIST_COPY_CONTACT_STR("Mobile Phone Number", item->contact->mobile_phone); break; case 0x3A1D: // PR_RADIO_TELEPHONE_NUMBER LIST_COPY_CONTACT_STR("Radio Phone Number", item->contact->radio_phone); break; case 0x3A1E: // PR_CAR_TELEPHONE_NUMBER LIST_COPY_CONTACT_STR("Car Phone Number", item->contact->car_phone); break; case 0x3A1F: // PR_OTHER_TELEPHONE_NUMBER LIST_COPY_CONTACT_STR("Other Phone Number", item->contact->other_phone); break; case 0x3A20: // PR_TRANSMITTABLE_DISPLAY_NAME LIST_COPY_CONTACT_STR("Transmittable Display Name", item->contact->transmittable_display_name); break; case 0x3A21: // PR_PAGER_TELEPHONE_NUMBER LIST_COPY_CONTACT_STR("Pager Phone Number", item->contact->pager_phone); break; case 0x3A22: // PR_USER_CERTIFICATE DEBUG_INFO(("User Certificate - NOT PROCESSED\n")); break; case 0x3A23: // PR_PRIMARY_FAX_NUMBER LIST_COPY_CONTACT_STR("Primary Fax Number", item->contact->primary_fax); break; case 0x3A24: // PR_BUSINESS_FAX_NUMBER LIST_COPY_CONTACT_STR("Business Fax Number", item->contact->business_fax); break; case 0x3A25: // PR_HOME_FAX_NUMBER LIST_COPY_CONTACT_STR("Home Fax Number", item->contact->home_fax); break; case 0x3A26: // PR_BUSINESS_ADDRESS_COUNTRY LIST_COPY_CONTACT_STR("Business Address Country", item->contact->business_country); break; case 0x3A27: // PR_BUSINESS_ADDRESS_CITY LIST_COPY_CONTACT_STR("Business Address City", item->contact->business_city); break; case 0x3A28: // PR_BUSINESS_ADDRESS_STATE_OR_PROVINCE LIST_COPY_CONTACT_STR("Business Address State", item->contact->business_state); break; case 0x3A29: // PR_BUSINESS_ADDRESS_STREET LIST_COPY_CONTACT_STR("Business Address Street", item->contact->business_street); break; case 0x3A2A: // PR_BUSINESS_POSTAL_CODE LIST_COPY_CONTACT_STR("Business Postal Code", item->contact->business_postal_code); break; case 0x3A2B: // PR_BUSINESS_PO_BOX LIST_COPY_CONTACT_STR("Business PO Box", item->contact->business_po_box); break; case 0x3A2C: // PR_TELEX_NUMBER LIST_COPY_CONTACT_STR("Telex Number", item->contact->telex); break; case 0x3A2D: // PR_ISDN_NUMBER LIST_COPY_CONTACT_STR("ISDN Number", item->contact->isdn_phone); break; case 0x3A2E: // PR_ASSISTANT_TELEPHONE_NUMBER LIST_COPY_CONTACT_STR("Assistant Phone Number", item->contact->assistant_phone); break; case 0x3A2F: // PR_HOME2_TELEPHONE_NUMBER LIST_COPY_CONTACT_STR("Home Phone 2", item->contact->home_phone2); break; case 0x3A30: // PR_ASSISTANT LIST_COPY_CONTACT_STR("Assistant's Name", item->contact->assistant_name); break; case 0x3A40: // PR_SEND_RICH_INFO LIST_COPY_CONTACT_BOOL("Can receive Rich Text", item->contact->rich_text); break; case 0x3A41: // PR_WEDDING_ANNIVERSARY LIST_COPY_CONTACT_TIME("Wedding Anniversary", item->contact->wedding_anniversary); break; case 0x3A42: // PR_BIRTHDAY LIST_COPY_CONTACT_TIME("Birthday", item->contact->birthday); break; case 0x3A43: // PR_HOBBIES LIST_COPY_CONTACT_STR("Hobbies", item->contact->hobbies); break; case 0x3A44: // PR_MIDDLE_NAME LIST_COPY_CONTACT_STR("Middle Name", item->contact->middle_name); break; case 0x3A45: // PR_DISPLAY_NAME_PREFIX LIST_COPY_CONTACT_STR("Display Name Prefix (Title)", item->contact->display_name_prefix); break; case 0x3A46: // PR_PROFESSION LIST_COPY_CONTACT_STR("Profession", item->contact->profession); break; case 0x3A47: // PR_PREFERRED_BY_NAME LIST_COPY_CONTACT_STR("Preferred By Name", item->contact->pref_name); break; case 0x3A48: // PR_SPOUSE_NAME LIST_COPY_CONTACT_STR("Spouse's Name", item->contact->spouse_name); break; case 0x3A49: // PR_COMPUTER_NETWORK_NAME LIST_COPY_CONTACT_STR("Computer Network Name", item->contact->computer_name); break; case 0x3A4A: // PR_CUSTOMER_ID LIST_COPY_CONTACT_STR("Customer ID", item->contact->customer_id); break; case 0x3A4B: // PR_TTYTDD_PHONE_NUMBER LIST_COPY_CONTACT_STR("TTY/TDD Phone", item->contact->ttytdd_phone); break; case 0x3A4C: // PR_FTP_SITE LIST_COPY_CONTACT_STR("Ftp Site", item->contact->ftp_site); break; case 0x3A4D: // PR_GENDER LIST_COPY_CONTACT_ENUM16("Gender", item->contact->gender, 0, 3, "Unspecified", "Female", "Male"); break; case 0x3A4E: // PR_MANAGER_NAME LIST_COPY_CONTACT_STR("Manager's Name", item->contact->manager_name); break; case 0x3A4F: // PR_NICKNAME LIST_COPY_CONTACT_STR("Nickname", item->contact->nickname); break; case 0x3A50: // PR_PERSONAL_HOME_PAGE LIST_COPY_CONTACT_STR("Personal Home Page", item->contact->personal_homepage); break; case 0x3A51: // PR_BUSINESS_HOME_PAGE LIST_COPY_CONTACT_STR("Business Home Page", item->contact->business_homepage); break; case 0x3A57: // PR_COMPANY_MAIN_PHONE_NUMBER LIST_COPY_CONTACT_STR("Company Main Phone", item->contact->company_main_phone); break; case 0x3A58: // PR_CHILDRENS_NAMES DEBUG_INFO(("Children's Names - NOT PROCESSED\n")); break; case 0x3A59: // PR_HOME_ADDRESS_CITY LIST_COPY_CONTACT_STR("Home Address City", item->contact->home_city); break; case 0x3A5A: // PR_HOME_ADDRESS_COUNTRY LIST_COPY_CONTACT_STR("Home Address Country", item->contact->home_country); break; case 0x3A5B: // PR_HOME_ADDRESS_POSTAL_CODE LIST_COPY_CONTACT_STR("Home Address Postal Code", item->contact->home_postal_code); break; case 0x3A5C: // PR_HOME_ADDRESS_STATE_OR_PROVINCE LIST_COPY_CONTACT_STR("Home Address State or Province", item->contact->home_state); break; case 0x3A5D: // PR_HOME_ADDRESS_STREET LIST_COPY_CONTACT_STR("Home Address Street", item->contact->home_street); break; case 0x3A5E: // PR_HOME_ADDRESS_POST_OFFICE_BOX LIST_COPY_CONTACT_STR("Home Address Post Office Box", item->contact->home_po_box); break; case 0x3A5F: // PR_OTHER_ADDRESS_CITY LIST_COPY_CONTACT_STR("Other Address City", item->contact->other_city); break; case 0x3A60: // PR_OTHER_ADDRESS_COUNTRY LIST_COPY_CONTACT_STR("Other Address Country", item->contact->other_country); break; case 0x3A61: // PR_OTHER_ADDRESS_POSTAL_CODE LIST_COPY_CONTACT_STR("Other Address Postal Code", item->contact->other_postal_code); break; case 0x3A62: // PR_OTHER_ADDRESS_STATE_OR_PROVINCE LIST_COPY_CONTACT_STR("Other Address State", item->contact->other_state); break; case 0x3A63: // PR_OTHER_ADDRESS_STREET LIST_COPY_CONTACT_STR("Other Address Street", item->contact->other_street); break; case 0x3A64: // PR_OTHER_ADDRESS_POST_OFFICE_BOX LIST_COPY_CONTACT_STR("Other Address Post Office box", item->contact->other_po_box); break; case 0x3FDE: // PR_INTERNET_CPID LIST_COPY_INT32("Internet code page", item->internet_cpid); break; case 0x3FFD: // PR_MESSAGE_CODEPAGE LIST_COPY_INT32("Message code page", item->message_codepage); break; case 0x65E3: // PR_PREDECESSOR_CHANGE_LIST LIST_COPY_BIN(item->predecessor_change); DEBUG_INFO(("Predecessor Change\n")); DEBUG_HEXDUMP(item->predecessor_change.data, item->predecessor_change.size); break; case 0x67F2: // ID2 value of the attachment NULL_CHECK(attach); LIST_COPY_INT32("Attachment ID2 value", ut); attach->id2_val = ut; break; case 0x67FF: // Extra Property Identifier (Password CheckSum) LIST_COPY_STORE_INT32("Password checksum", item->message_store->pwd_chksum); break; case 0x6F02: // Secure HTML Body LIST_COPY_EMAIL_BIN("Secure HTML Body", item->email->encrypted_htmlbody); break; case 0x6F04: // Secure Text Body LIST_COPY_EMAIL_BIN("Secure Text Body", item->email->encrypted_body); break; case 0x7C07: // top of folders ENTRYID LIST_COPY_STORE_ENTRYID("Top of folders RecID", item->message_store->top_of_folder); break; case 0x8005: // Contact's Fullname LIST_COPY_CONTACT_STR("Contact Fullname", item->contact->fullname); break; case 0x801A: // Full Home Address LIST_COPY_CONTACT_STR("Home Address", item->contact->home_address); break; case 0x801B: // Full Business Address LIST_COPY_CONTACT_STR("Business Address", item->contact->business_address); break; case 0x801C: // Full Other Address LIST_COPY_CONTACT_STR("Other Address", item->contact->other_address); break; case 0x8045: // Work address street LIST_COPY_CONTACT_STR("Work address street", item->contact->work_address_street); break; case 0x8046: // Work address city LIST_COPY_CONTACT_STR("Work address city", item->contact->work_address_city); break; case 0x8047: // Work address state LIST_COPY_CONTACT_STR("Work address state", item->contact->work_address_state); break; case 0x8048: // Work address postalcode LIST_COPY_CONTACT_STR("Work address postalcode", item->contact->work_address_postalcode); break; case 0x8049: // Work address country LIST_COPY_CONTACT_STR("Work address country", item->contact->work_address_country); break; case 0x804A: // Work address postofficebox LIST_COPY_CONTACT_STR("Work address postofficebox", item->contact->work_address_postofficebox); break; case 0x8082: // Email Address 1 Transport LIST_COPY_CONTACT_STR("Email Address 1 Transport", item->contact->address1_transport); break; case 0x8083: // Email Address 1 Address LIST_COPY_CONTACT_STR("Email Address 1 Address", item->contact->address1); break; case 0x8084: // Email Address 1 Description LIST_COPY_CONTACT_STR("Email Address 1 Description", item->contact->address1_desc); break; case 0x8085: // Email Address 1 Record LIST_COPY_CONTACT_STR("Email Address 1 Record", item->contact->address1a); break; case 0x8092: // Email Address 2 Transport LIST_COPY_CONTACT_STR("Email Address 2 Transport", item->contact->address2_transport); break; case 0x8093: // Email Address 2 Address LIST_COPY_CONTACT_STR("Email Address 2 Address", item->contact->address2); break; case 0x8094: // Email Address 2 Description LIST_COPY_CONTACT_STR("Email Address 2 Description", item->contact->address2_desc); break; case 0x8095: // Email Address 2 Record LIST_COPY_CONTACT_STR("Email Address 2 Record", item->contact->address2a); break; case 0x80A2: // Email Address 3 Transport LIST_COPY_CONTACT_STR("Email Address 3 Transport", item->contact->address3_transport); break; case 0x80A3: // Email Address 3 Address LIST_COPY_CONTACT_STR("Email Address 3 Address", item->contact->address3); break; case 0x80A4: // Email Address 3 Description LIST_COPY_CONTACT_STR("Email Address 3 Description", item->contact->address3_desc); break; case 0x80A5: // Email Address 3 Record LIST_COPY_CONTACT_STR("Email Address 3 Record", item->contact->address3a); break; case 0x80D8: // Internet Free/Busy LIST_COPY_CONTACT_STR("Internet Free/Busy", item->contact->free_busy_address); break; case 0x8205: // PR_OUTLOOK_EVENT_SHOW_TIME_AS LIST_COPY_APPT_ENUM("Appointment shows as", item->appointment->showas, 0, 4, "Free", "Tentative", "Busy", "Out Of Office"); break; case 0x8208: // PR_OUTLOOK_EVENT_LOCATION LIST_COPY_APPT_STR("Appointment Location", item->appointment->location); break; case 0x820d: // PR_OUTLOOK_EVENT_START_DATE LIST_COPY_APPT_TIME("Appointment Date Start", item->appointment->start); break; case 0x820e: // PR_OUTLOOK_EVENT_START_END LIST_COPY_APPT_TIME("Appointment Date End", item->appointment->end); break; case 0x8214: // Label for an appointment LIST_COPY_APPT_ENUM("Label for appointment", item->appointment->label, 0, 11, "None", "Important", "Business", "Personal", "Vacation", "Must Attend", "Travel Required", "Needs Preparation", "Birthday", "Anniversary", "Phone Call"); break; case 0x8215: // PR_OUTLOOK_EVENT_ALL_DAY LIST_COPY_APPT_BOOL("All day flag", item->appointment->all_day); break; case 0x8216: // PR_OUTLOOK_EVENT_RECURRENCE_DATA LIST_COPY_APPT_BIN("Appointment recurrence data", item->appointment->recurrence_data); break; case 0x8223: // PR_OUTLOOK_EVENT_IS_RECURRING LIST_COPY_APPT_BOOL("Is recurring", item->appointment->is_recurring); break; case 0x8231: // Recurrence type LIST_COPY_APPT_ENUM("Appointment recurrence type ", item->appointment->recurrence_type, 0, 5, "None", "Daily", "Weekly", "Monthly", "Yearly"); break; case 0x8232: // Recurrence description LIST_COPY_APPT_STR("Appointment recurrence description", item->appointment->recurrence_description); break; case 0x8234: // TimeZone as String LIST_COPY_APPT_STR("TimeZone of times", item->appointment->timezonestring); break; case 0x8235: // PR_OUTLOOK_EVENT_RECURRENCE_START LIST_COPY_APPT_TIME("Recurrence Start Date", item->appointment->recurrence_start); break; case 0x8236: // PR_OUTLOOK_EVENT_RECURRENCE_END LIST_COPY_APPT_TIME("Recurrence End Date", item->appointment->recurrence_end); break; case 0x8501: // PR_OUTLOOK_COMMON_REMINDER_MINUTES_BEFORE LIST_COPY_APPT_INT32("Alarm minutes", item->appointment->alarm_minutes); break; case 0x8503: // PR_OUTLOOK_COMMON_REMINDER_SET LIST_COPY_APPT_BOOL("Reminder alarm", item->appointment->alarm); break; case 0x8516: // Common start DEBUG_INFO(("Common Start Date - %s\n", pst_fileTimeToAscii((FILETIME*)list->elements[x]->data, time_buffer))); break; case 0x8517: // Common end DEBUG_INFO(("Common End Date - %s\n", pst_fileTimeToAscii((FILETIME*)list->elements[x]->data, time_buffer))); break; case 0x851f: // Play reminder sound filename LIST_COPY_APPT_STR("Appointment reminder sound filename", item->appointment->alarm_filename); break; case 0x8530: // Followup LIST_COPY_CONTACT_STR("Followup String", item->contact->followup); break; case 0x8534: // Mileage LIST_COPY_CONTACT_STR("Mileage", item->contact->mileage); break; case 0x8535: // Billing Information LIST_COPY_CONTACT_STR("Billing Information", item->contact->billing_information); break; case 0x8554: // PR_OUTLOOK_VERSION LIST_COPY_STR("Outlook Version", item->outlook_version); break; case 0x8560: // Appointment Reminder Time LIST_COPY_APPT_TIME("Appointment Reminder Time", item->appointment->reminder); break; case 0x8700: // Journal Type LIST_COPY_JOURNAL_STR("Journal Entry Type", item->journal->type); break; case 0x8706: // Journal Start date/time LIST_COPY_JOURNAL_TIME("Start Timestamp", item->journal->start); break; case 0x8708: // Journal End date/time LIST_COPY_JOURNAL_TIME("End Timestamp", item->journal->end); break; case 0x8712: // Journal Type Description LIST_COPY_JOURNAL_STR("Journal description", item->journal->description); break; default: if (list->elements[x]->type == (uint32_t)0x0002) { DEBUG_WARN(("Unknown type %#x 16bit int = %hi\n", list->elements[x]->mapi_id, *(int16_t*)list->elements[x]->data)); } else if (list->elements[x]->type == (uint32_t)0x0003) { DEBUG_WARN(("Unknown type %#x 32bit int = %i\n", list->elements[x]->mapi_id, *(int32_t*)list->elements[x]->data)); } else if (list->elements[x]->type == (uint32_t)0x0004) { DEBUG_WARN(("Unknown type %#x 4-byte floating [size = %#x]\n", list->elements[x]->mapi_id, list->elements[x]->size)); DEBUG_HEXDUMP(list->elements[x]->data, list->elements[x]->size); } else if (list->elements[x]->type == (uint32_t)0x0005) { DEBUG_WARN(("Unknown type %#x double floating [size = %#x]\n", list->elements[x]->mapi_id, list->elements[x]->size)); DEBUG_HEXDUMP(list->elements[x]->data, list->elements[x]->size); } else if (list->elements[x]->type == (uint32_t)0x0006) { DEBUG_WARN(("Unknown type %#x signed 64bit int = %"PRIi64"\n", list->elements[x]->mapi_id, *(int64_t*)list->elements[x]->data)); DEBUG_HEXDUMP(list->elements[x]->data, list->elements[x]->size); } else if (list->elements[x]->type == (uint32_t)0x0007) { DEBUG_WARN(("Unknown type %#x application time [size = %#x]\n", list->elements[x]->mapi_id, list->elements[x]->size)); DEBUG_HEXDUMP(list->elements[x]->data, list->elements[x]->size); } else if (list->elements[x]->type == (uint32_t)0x000a) { DEBUG_WARN(("Unknown type %#x 32bit error value = %i\n", list->elements[x]->mapi_id, *(int32_t*)list->elements[x]->data)); } else if (list->elements[x]->type == (uint32_t)0x000b) { DEBUG_WARN(("Unknown type %#x 16bit boolean = %s [%hi]\n", list->elements[x]->mapi_id, (*((int16_t*)list->elements[x]->data)!=0?"True":"False"), *((int16_t*)list->elements[x]->data))); } else if (list->elements[x]->type == (uint32_t)0x000d) { DEBUG_WARN(("Unknown type %#x Embedded object [size = %#x]\n", list->elements[x]->mapi_id, list->elements[x]->size)); DEBUG_HEXDUMP(list->elements[x]->data, list->elements[x]->size); } else if (list->elements[x]->type == (uint32_t)0x0014) { DEBUG_WARN(("Unknown type %#x signed 64bit int = %"PRIi64"\n", list->elements[x]->mapi_id, *(int64_t*)list->elements[x]->data)); DEBUG_HEXDUMP(list->elements[x]->data, list->elements[x]->size); } else if (list->elements[x]->type == (uint32_t)0x001e) { DEBUG_WARN(("Unknown type %#x String Data = \"%s\"\n", list->elements[x]->mapi_id, list->elements[x]->data)); } else if (list->elements[x]->type == (uint32_t)0x001f) { DEBUG_WARN(("Unknown type %#x Unicode String Data [size = %#x]\n", list->elements[x]->mapi_id, list->elements[x]->size)); DEBUG_HEXDUMP(list->elements[x]->data, list->elements[x]->size); } else if (list->elements[x]->type == (uint32_t)0x0040) { DEBUG_WARN(("Unknown type %#x Date = \"%s\"\n", list->elements[x]->mapi_id, pst_fileTimeToAscii((FILETIME*)list->elements[x]->data, time_buffer))); } else if (list->elements[x]->type == (uint32_t)0x0048) { DEBUG_WARN(("Unknown type %#x OLE GUID [size = %#x]\n", list->elements[x]->mapi_id, list->elements[x]->size)); DEBUG_HEXDUMP(list->elements[x]->data, list->elements[x]->size); } else if (list->elements[x]->type == (uint32_t)0x0102) { DEBUG_WARN(("Unknown type %#x Binary Data [size = %#x]\n", list->elements[x]->mapi_id, list->elements[x]->size)); DEBUG_HEXDUMP(list->elements[x]->data, list->elements[x]->size); } else if (list->elements[x]->type == (uint32_t)0x1003) { DEBUG_WARN(("Unknown type %#x Array of 32 bit values [size = %#x]\n", list->elements[x]->mapi_id, list->elements[x]->size)); DEBUG_HEXDUMP(list->elements[x]->data, list->elements[x]->size); } else if (list->elements[x]->type == (uint32_t)0x1014) { DEBUG_WARN(("Unknown type %#x Array of 64 bit values [siize = %#x]\n", list->elements[x]->mapi_id, list->elements[x]->size)); DEBUG_HEXDUMP(list->elements[x]->data, list->elements[x]->size); } else if (list->elements[x]->type == (uint32_t)0x101e) { DEBUG_WARN(("Unknown type %#x Array of Strings [size = %#x]\n", list->elements[x]->mapi_id, list->elements[x]->size)); DEBUG_HEXDUMP(list->elements[x]->data, list->elements[x]->size); } else if (list->elements[x]->type == (uint32_t)0x101f) { DEBUG_WARN(("Unknown type %#x Array of Unicode Strings [size = %#x]\n", list->elements[x]->mapi_id, list->elements[x]->size)); DEBUG_HEXDUMP(list->elements[x]->data, list->elements[x]->size); } else if (list->elements[x]->type == (uint32_t)0x1102) { DEBUG_WARN(("Unknown type %#x Array of binary data blobs [size = %#x]\n", list->elements[x]->mapi_id, list->elements[x]->size)); DEBUG_HEXDUMP(list->elements[x]->data, list->elements[x]->size); } else { DEBUG_WARN(("Unknown type %#x Not Printable [%#x]\n", list->elements[x]->mapi_id, list->elements[x]->type)); DEBUG_HEXDUMP(list->elements[x]->data, list->elements[x]->size); } if (list->elements[x]->data) { free(list->elements[x]->data); list->elements[x]->data = NULL; } } } list = list->next; if (attach) attach = attach->next; } DEBUG_RET(); return 0; } static void pst_free_list(pst_mapi_object *list) { pst_mapi_object *l; DEBUG_ENT("pst_free_list"); while (list) { if (list->elements) { int32_t x; for (x=0; x < list->orig_count; x++) { if (list->elements[x]) { if (list->elements[x]->data) free(list->elements[x]->data); free(list->elements[x]); } } free(list->elements); } l = list->next; free (list); list = l; } DEBUG_RET(); } static void pst_free_id2(pst_id2_tree * head) { pst_id2_tree *t; DEBUG_ENT("pst_free_id2"); while (head) { pst_free_id2(head->child); t = head->next; free(head); head = t; } DEBUG_RET(); } static void pst_free_desc (pst_desc_tree *head) { pst_desc_tree *t; DEBUG_ENT("pst_free_desc"); while (head) { pst_free_desc(head->child); t = head->next; free(head); head = t; } DEBUG_RET(); } static void pst_free_xattrib(pst_x_attrib_ll *x) { pst_x_attrib_ll *t; DEBUG_ENT("pst_free_xattrib"); while (x) { if (x->data) free(x->data); t = x->next; free(x); x = t; } DEBUG_RET(); } static pst_id2_tree * pst_build_id2(pst_file *pf, pst_index_ll* list) { pst_block_header block_head; pst_id2_tree *head = NULL, *tail = NULL; uint16_t x = 0; char *b_ptr = NULL; char *buf = NULL; pst_id2_assoc id2_rec; pst_index_ll *i_ptr = NULL; pst_id2_tree *i2_ptr = NULL; DEBUG_ENT("pst_build_id2"); if (pst_read_block_size(pf, list->offset, list->size, list->inflated_size, &buf) < list->size) { //an error occurred in block read DEBUG_WARN(("block read error occurred. offset = %#"PRIx64", size = %#"PRIx64"\n", list->offset, list->size)); if (buf) free(buf); DEBUG_RET(); return NULL; } DEBUG_HEXDUMPC(buf, list->size, 16); memcpy(&block_head, buf, sizeof(block_head)); LE16_CPU(block_head.type); LE16_CPU(block_head.count); if (block_head.type != (uint16_t)0x0002) { // some sort of constant? DEBUG_WARN(("Unknown constant [%#hx] at start of id2 values [offset %#"PRIx64"].\n", block_head.type, list->offset)); if (buf) free(buf); DEBUG_RET(); return NULL; } DEBUG_INFO(("ID %#"PRIx64" is likely to be a description record. Count is %i (offset %#"PRIx64")\n", list->i_id, block_head.count, list->offset)); x = 0; b_ptr = buf + ((pf->do_read64) ? 0x08 : 0x04); while (x < block_head.count) { b_ptr += pst_decode_assoc(pf, &id2_rec, b_ptr); DEBUG_INFO(("id2 = %#x, id = %#"PRIx64", child id = %#"PRIx64"\n", id2_rec.id2, id2_rec.id, id2_rec.child_id)); if ((i_ptr = pst_getID(pf, id2_rec.id)) == NULL) { DEBUG_WARN(("%#"PRIx64" - Not Found\n", id2_rec.id)); } else { DEBUG_INFO(("%#"PRIx64" - Offset %#"PRIx64", u1 %#"PRIx64", Size %"PRIi64"(%#"PRIx64")\n", i_ptr->i_id, i_ptr->offset, i_ptr->u1, i_ptr->size, i_ptr->inflated_size)); // add it to the tree i2_ptr = (pst_id2_tree*) pst_malloc(sizeof(pst_id2_tree)); i2_ptr->id2 = id2_rec.id2; i2_ptr->id = i_ptr; i2_ptr->child = NULL; i2_ptr->next = NULL; if (!head) head = i2_ptr; if (tail) tail->next = i2_ptr; tail = i2_ptr; if (id2_rec.child_id) { if ((i_ptr = pst_getID(pf, id2_rec.child_id)) == NULL) { DEBUG_WARN(("child id [%#"PRIx64"] not found\n", id2_rec.child_id)); } else { i2_ptr->child = pst_build_id2(pf, i_ptr); } } } x++; } if (buf) free (buf); DEBUG_RET(); return head; } static void pst_free_attach(pst_item_attach *attach) { while (attach) { pst_item_attach *t; SAFE_FREE_STR(attach->filename1); SAFE_FREE_STR(attach->filename2); SAFE_FREE_STR(attach->mimetype); SAFE_FREE_STR(attach->content_id); SAFE_FREE_BIN(attach->data); pst_free_id2(attach->id2_head); t = attach->next; free(attach); attach = t; } } void pst_freeItem(pst_item *item) { pst_item_extra_field *et; DEBUG_ENT("pst_freeItem"); if (item) { if (item->email) { SAFE_FREE(item->email->arrival_date); SAFE_FREE_STR(item->email->cc_address); SAFE_FREE_STR(item->email->bcc_address); SAFE_FREE_BIN(item->email->conversation_index); SAFE_FREE_BIN(item->email->encrypted_body); SAFE_FREE_BIN(item->email->encrypted_htmlbody); SAFE_FREE_STR(item->email->header); SAFE_FREE_STR(item->email->htmlbody); SAFE_FREE_STR(item->email->in_reply_to); SAFE_FREE_STR(item->email->messageid); SAFE_FREE_STR(item->email->original_bcc); SAFE_FREE_STR(item->email->original_cc); SAFE_FREE_STR(item->email->original_to); SAFE_FREE_STR(item->email->outlook_recipient); SAFE_FREE_STR(item->email->outlook_recipient_name); SAFE_FREE_STR(item->email->outlook_recipient2); SAFE_FREE_STR(item->email->outlook_sender); SAFE_FREE_STR(item->email->outlook_sender_name); SAFE_FREE_STR(item->email->outlook_sender2); SAFE_FREE_STR(item->email->processed_subject); SAFE_FREE_STR(item->email->recip_access); SAFE_FREE_STR(item->email->recip_address); SAFE_FREE_STR(item->email->recip2_access); SAFE_FREE_STR(item->email->recip2_address); SAFE_FREE_STR(item->email->reply_to); SAFE_FREE_STR(item->email->rtf_body_tag); SAFE_FREE_BIN(item->email->rtf_compressed); SAFE_FREE_STR(item->email->return_path_address); SAFE_FREE_STR(item->email->sender_access); SAFE_FREE_STR(item->email->sender_address); SAFE_FREE_STR(item->email->sender2_access); SAFE_FREE_STR(item->email->sender2_address); SAFE_FREE(item->email->sent_date); SAFE_FREE(item->email->sentmail_folder); SAFE_FREE_STR(item->email->sentto_address); SAFE_FREE_STR(item->email->report_text); SAFE_FREE(item->email->report_time); SAFE_FREE_STR(item->email->supplementary_info); SAFE_FREE_STR(item->email->outlook_received_name1); SAFE_FREE_STR(item->email->outlook_sender_name2); SAFE_FREE_STR(item->email->outlook_normalized_subject); SAFE_FREE_STR(item->email->outlook_search_key); free(item->email); } if (item->folder) { free(item->folder); } if (item->message_store) { SAFE_FREE(item->message_store->top_of_personal_folder); SAFE_FREE(item->message_store->default_outbox_folder); SAFE_FREE(item->message_store->deleted_items_folder); SAFE_FREE(item->message_store->sent_items_folder); SAFE_FREE(item->message_store->user_views_folder); SAFE_FREE(item->message_store->common_view_folder); SAFE_FREE(item->message_store->search_root_folder); SAFE_FREE(item->message_store->top_of_folder); free(item->message_store); } if (item->contact) { SAFE_FREE_STR(item->contact->account_name); SAFE_FREE_STR(item->contact->address1); SAFE_FREE_STR(item->contact->address1a); SAFE_FREE_STR(item->contact->address1_desc); SAFE_FREE_STR(item->contact->address1_transport); SAFE_FREE_STR(item->contact->address2); SAFE_FREE_STR(item->contact->address2a); SAFE_FREE_STR(item->contact->address2_desc); SAFE_FREE_STR(item->contact->address2_transport); SAFE_FREE_STR(item->contact->address3); SAFE_FREE_STR(item->contact->address3a); SAFE_FREE_STR(item->contact->address3_desc); SAFE_FREE_STR(item->contact->address3_transport); SAFE_FREE_STR(item->contact->assistant_name); SAFE_FREE_STR(item->contact->assistant_phone); SAFE_FREE_STR(item->contact->billing_information); SAFE_FREE(item->contact->birthday); SAFE_FREE_STR(item->contact->business_address); SAFE_FREE_STR(item->contact->business_city); SAFE_FREE_STR(item->contact->business_country); SAFE_FREE_STR(item->contact->business_fax); SAFE_FREE_STR(item->contact->business_homepage); SAFE_FREE_STR(item->contact->business_phone); SAFE_FREE_STR(item->contact->business_phone2); SAFE_FREE_STR(item->contact->business_po_box); SAFE_FREE_STR(item->contact->business_postal_code); SAFE_FREE_STR(item->contact->business_state); SAFE_FREE_STR(item->contact->business_street); SAFE_FREE_STR(item->contact->callback_phone); SAFE_FREE_STR(item->contact->car_phone); SAFE_FREE_STR(item->contact->company_main_phone); SAFE_FREE_STR(item->contact->company_name); SAFE_FREE_STR(item->contact->computer_name); SAFE_FREE_STR(item->contact->customer_id); SAFE_FREE_STR(item->contact->def_postal_address); SAFE_FREE_STR(item->contact->department); SAFE_FREE_STR(item->contact->display_name_prefix); SAFE_FREE_STR(item->contact->first_name); SAFE_FREE_STR(item->contact->followup); SAFE_FREE_STR(item->contact->free_busy_address); SAFE_FREE_STR(item->contact->ftp_site); SAFE_FREE_STR(item->contact->fullname); SAFE_FREE_STR(item->contact->gov_id); SAFE_FREE_STR(item->contact->hobbies); SAFE_FREE_STR(item->contact->home_address); SAFE_FREE_STR(item->contact->home_city); SAFE_FREE_STR(item->contact->home_country); SAFE_FREE_STR(item->contact->home_fax); SAFE_FREE_STR(item->contact->home_po_box); SAFE_FREE_STR(item->contact->home_phone); SAFE_FREE_STR(item->contact->home_phone2); SAFE_FREE_STR(item->contact->home_postal_code); SAFE_FREE_STR(item->contact->home_state); SAFE_FREE_STR(item->contact->home_street); SAFE_FREE_STR(item->contact->initials); SAFE_FREE_STR(item->contact->isdn_phone); SAFE_FREE_STR(item->contact->job_title); SAFE_FREE_STR(item->contact->keyword); SAFE_FREE_STR(item->contact->language); SAFE_FREE_STR(item->contact->location); SAFE_FREE_STR(item->contact->manager_name); SAFE_FREE_STR(item->contact->middle_name); SAFE_FREE_STR(item->contact->mileage); SAFE_FREE_STR(item->contact->mobile_phone); SAFE_FREE_STR(item->contact->nickname); SAFE_FREE_STR(item->contact->office_loc); SAFE_FREE_STR(item->contact->common_name); SAFE_FREE_STR(item->contact->org_id); SAFE_FREE_STR(item->contact->other_address); SAFE_FREE_STR(item->contact->other_city); SAFE_FREE_STR(item->contact->other_country); SAFE_FREE_STR(item->contact->other_phone); SAFE_FREE_STR(item->contact->other_po_box); SAFE_FREE_STR(item->contact->other_postal_code); SAFE_FREE_STR(item->contact->other_state); SAFE_FREE_STR(item->contact->other_street); SAFE_FREE_STR(item->contact->pager_phone); SAFE_FREE_STR(item->contact->personal_homepage); SAFE_FREE_STR(item->contact->pref_name); SAFE_FREE_STR(item->contact->primary_fax); SAFE_FREE_STR(item->contact->primary_phone); SAFE_FREE_STR(item->contact->profession); SAFE_FREE_STR(item->contact->radio_phone); SAFE_FREE_STR(item->contact->spouse_name); SAFE_FREE_STR(item->contact->suffix); SAFE_FREE_STR(item->contact->surname); SAFE_FREE_STR(item->contact->telex); SAFE_FREE_STR(item->contact->transmittable_display_name); SAFE_FREE_STR(item->contact->ttytdd_phone); SAFE_FREE(item->contact->wedding_anniversary); SAFE_FREE_STR(item->contact->work_address_street); SAFE_FREE_STR(item->contact->work_address_city); SAFE_FREE_STR(item->contact->work_address_state); SAFE_FREE_STR(item->contact->work_address_postalcode); SAFE_FREE_STR(item->contact->work_address_country); SAFE_FREE_STR(item->contact->work_address_postofficebox); free(item->contact); } pst_free_attach(item->attach); while (item->extra_fields) { SAFE_FREE(item->extra_fields->field_name); SAFE_FREE(item->extra_fields->value); et = item->extra_fields->next; free(item->extra_fields); item->extra_fields = et; } if (item->journal) { SAFE_FREE(item->journal->start); SAFE_FREE(item->journal->end); SAFE_FREE_STR(item->journal->type); free(item->journal); } if (item->appointment) { SAFE_FREE(item->appointment->start); SAFE_FREE(item->appointment->end); SAFE_FREE_STR(item->appointment->location); SAFE_FREE(item->appointment->reminder); SAFE_FREE_STR(item->appointment->alarm_filename); SAFE_FREE_STR(item->appointment->timezonestring); SAFE_FREE_STR(item->appointment->recurrence_description); SAFE_FREE_BIN(item->appointment->recurrence_data); SAFE_FREE(item->appointment->recurrence_start); SAFE_FREE(item->appointment->recurrence_end); free(item->appointment); } SAFE_FREE(item->ascii_type); SAFE_FREE_STR(item->body_charset); SAFE_FREE_STR(item->body); SAFE_FREE_STR(item->subject); SAFE_FREE_STR(item->comment); SAFE_FREE(item->create_date); SAFE_FREE_STR(item->file_as); SAFE_FREE(item->modify_date); SAFE_FREE_STR(item->outlook_version); SAFE_FREE_BIN(item->record_key); SAFE_FREE_BIN(item->predecessor_change); free(item); } DEBUG_RET(); } /** * The offset might be zero, in which case we have no data, so return a pair of null pointers. * Or, the offset might end in 0xf, so it is an id2 pointer, in which case we read the id2 block. * Otherwise, the high order 16 bits of offset is the index into the subblocks, and * the (low order 16 bits of offset)>>4 is an index into the table of offsets in the subblock. */ static int pst_getBlockOffsetPointer(pst_file *pf, pst_id2_tree *i2_head, pst_subblocks *subblocks, uint32_t offset, pst_block_offset_pointer *p) { size_t size; pst_block_offset block_offset; DEBUG_ENT("pst_getBlockOffsetPointer"); if (p->needfree) free(p->from); p->from = NULL; p->to = NULL; p->needfree = 0; if (!offset) { // no data p->from = p->to = NULL; } else if ((offset & 0xf) == (uint32_t)0xf) { // external index reference DEBUG_WARN(("Found id2 %#x value. Will follow it\n", offset)); size = pst_ff_getID2block(pf, offset, i2_head, &(p->from)); if (size) { p->to = p->from + size; p->needfree = 1; } else { if (p->from) { DEBUG_WARN(("size zero but non-null pointer\n")); free(p->from); } p->from = p->to = NULL; } } else { DEBUG_WARN(("Found internal %#x value.\n", offset)); // internal index reference size_t subindex = offset >> 16; if (pf->do_read64 == 2) { // Shift over 3 more bits for new flags. subindex = subindex >> 3; } size_t suboffset = offset & 0xffff; if (subindex < subblocks->subblock_count) { if (pst_getBlockOffset(subblocks->subs[subindex].buf, subblocks->subs[subindex].read_size, subblocks->subs[subindex].i_offset, suboffset, &block_offset)) { p->from = subblocks->subs[subindex].buf + block_offset.from; p->to = subblocks->subs[subindex].buf + block_offset.to; } } } DEBUG_RET(); return (p->from) ? 0 : 1; } /** */ static int pst_getBlockOffset(char *buf, size_t read_size, uint32_t i_offset, uint32_t offset, pst_block_offset *p) { uint32_t low = offset & 0xf; uint32_t of1 = offset >> 4; DEBUG_ENT("pst_getBlockOffset"); if (!p || !buf || !i_offset || low || (i_offset+2+of1+sizeof(*p) > read_size)) { DEBUG_WARN(("p is NULL or buf is NULL or offset is 0 or offset has low bits or beyond read size (%p, %p, %#x, %i, %i)\n", p, buf, offset, read_size, i_offset)); DEBUG_RET(); return 0; } memcpy(&(p->from), &(buf[(i_offset+2)+of1]), sizeof(p->from)); memcpy(&(p->to), &(buf[(i_offset+2)+of1+sizeof(p->from)]), sizeof(p->to)); LE16_CPU(p->from); LE16_CPU(p->to); DEBUG_WARN(("get block offset finds from=%i(%#x), to=%i(%#x)\n", p->from, p->from, p->to, p->to)); if (p->from > p->to || p->to > read_size) { DEBUG_WARN(("get block offset bad range\n")); DEBUG_RET(); return 0; } DEBUG_RET(); return 1; } static int pst_getID_compare(const void *key, const void *entry) { uint64_t key_id = *(const uint64_t*)key; uint64_t entry_id = ((const pst_index_ll*)entry)->i_id; return (key_id > entry_id) - (key_id < entry_id); } /** */ pst_index_ll* pst_getID(pst_file* pf, uint64_t i_id) { pst_index_ll *ptr; DEBUG_ENT("pst_getID"); if (i_id == 0) { DEBUG_RET(); return NULL; } //if (i_id & 1) DEBUG_INFO(("have odd id bit %#"PRIx64"\n", i_id)); //if (i_id & 2) DEBUG_INFO(("have two id bit %#"PRIx64"\n", i_id)); i_id -= (i_id & 1); DEBUG_INFO(("Trying to find %#"PRIx64"\n", i_id)); ptr = bsearch(&i_id, pf->i_table, pf->i_count, sizeof *pf->i_table, pst_getID_compare); if (ptr) {DEBUG_INFO(("Found Value %#"PRIx64"\n", i_id)); } else {DEBUG_INFO(("ERROR: Value %#"PRIx64" not found\n", i_id)); } DEBUG_RET(); return ptr; } static pst_id2_tree *pst_getID2(pst_id2_tree *head, uint64_t id2) { // the id2 values are only unique among siblings. // we must not recurse into children // the caller must supply the correct parent DEBUG_ENT("pst_getID2"); DEBUG_INFO(("looking for id2 = %#"PRIx64"\n", id2)); pst_id2_tree *ptr = head; while (ptr) { if (ptr->id2 == id2) break; ptr = ptr->next; } if (ptr && ptr->id) { DEBUG_INFO(("Found value %#"PRIx64"\n", ptr->id->i_id)); DEBUG_RET(); return ptr; } DEBUG_INFO(("ERROR Not Found\n")); DEBUG_RET(); return NULL; } /** * find the id in the descriptor tree rooted at pf->d_head * * @param pf global pst file pointer * @param d_id the id we are looking for * * @return pointer to the pst_desc_tree node in the descriptor tree */ static pst_desc_tree* pst_getDptr(pst_file *pf, uint64_t d_id) { pst_desc_tree *ptr = pf->d_head; DEBUG_ENT("pst_getDptr"); while (ptr && (ptr->d_id != d_id)) { //DEBUG_INFO(("Looking for %#"PRIx64" at node %#"PRIx64" with parent %#"PRIx64"\n", id, ptr->d_id, ptr->parent_d_id)); if (ptr->child) { ptr = ptr->child; continue; } while (!ptr->next && ptr->parent) { ptr = ptr->parent; } ptr = ptr->next; } DEBUG_RET(); return ptr; // will be NULL or record we are looking for } static void pst_printDptr(pst_file *pf, pst_desc_tree *ptr) { DEBUG_ENT("pst_printDptr"); while (ptr) { DEBUG_INFO(("%#"PRIx64" [%i] desc=%#"PRIx64", assoc tree=%#"PRIx64"\n", ptr->d_id, ptr->no_child, (ptr->desc ? ptr->desc->i_id : (uint64_t)0), (ptr->assoc_tree ? ptr->assoc_tree->i_id : (uint64_t)0))); if (ptr->child) { pst_printDptr(pf, ptr->child); } ptr = ptr->next; } DEBUG_RET(); } static void pst_printID2ptr(pst_id2_tree *ptr) { DEBUG_ENT("pst_printID2ptr"); while (ptr) { DEBUG_INFO(("%#"PRIx64" id=%#"PRIx64"\n", ptr->id2, (ptr->id ? ptr->id->i_id : (uint64_t)0))); if (ptr->child) pst_printID2ptr(ptr->child); ptr = ptr->next; } DEBUG_RET(); } /** * Read a block of data from file into memory * @param pf PST file * @param offset offset in the pst file of the data * @param size size of the block to be read * @param buf reference to pointer to buffer. If this pointer is non-NULL, it will first be free()d * @return size of block read into memory */ static size_t pst_read_raw_block_size(pst_file *pf, int64_t offset, size_t size, char **buf) { size_t rsize; DEBUG_ENT("pst_read_raw_block_size"); DEBUG_INFO(("Reading raw block from %#"PRIx64", %x bytes\n", offset, size)); if (*buf) { DEBUG_INFO(("Freeing old memory\n")); free(*buf); } *buf = (char*) pst_malloc(size); rsize = pst_getAtPos(pf, offset, *buf, size); if (rsize != size) { DEBUG_WARN(("Didn't read all the data. fread returned less [%i instead of %i]\n", rsize, size)); if (feof(pf->fp)) { DEBUG_WARN(("We tried to read past the end of the file at [offset %#"PRIx64", size %#x]\n", offset, size)); } else if (ferror(pf->fp)) { DEBUG_WARN(("Error is set on file stream.\n")); } else { DEBUG_WARN(("I can't tell why it failed\n")); } } DEBUG_RET(); return rsize; } static size_t pst_read_block_size(pst_file *pf, int64_t offset, size_t size, size_t inflated_size, char **buf) { DEBUG_ENT("pst_read_block_size"); DEBUG_INFO(("Reading block from %#"PRIx64", %x bytes, %x inflated\n", offset, size, inflated_size)); if (inflated_size <= size) { // Not deflated. size_t ret = pst_read_raw_block_size(pf, offset, size, buf); DEBUG_RET(); return ret; } // We need to read the raw block and inflate it. char *zbuf = NULL; if (pst_read_raw_block_size(pf, offset, size, &zbuf) != size) { DEBUG_WARN(("Failed to read %i bytes\n", size)); if (zbuf) free(zbuf); DEBUG_RET(); return -1; } *buf = (char *) pst_malloc(inflated_size); size_t result_size = inflated_size; if (uncompress((Bytef *) *buf, &result_size, (Bytef *) zbuf, size) != Z_OK || result_size != inflated_size) { DEBUG_WARN(("Failed to uncompress %i bytes to %i bytes, got %i\n", size, inflated_size, result_size)); if (zbuf) free(zbuf); DEBUG_RET(); return -1; } DEBUG_RET(); return inflated_size; } /** Decrypt a block of data from the pst file. * @param i_id identifier of this block, needed as part of the key for the enigma cipher * @param buf pointer to the buffer to be decrypted in place * @param size size of the buffer * @param type @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 * @return 0 if ok, -1 if error (NULL buffer or unknown encryption type) */ static int pst_decrypt(uint64_t i_id, char *buf, size_t size, unsigned char type) { size_t x = 0; unsigned char y; DEBUG_ENT("pst_decrypt"); if (!buf) { DEBUG_RET(); return -1; } if (type == PST_COMP_ENCRYPT) { x = 0; while (x < size) { y = (unsigned char)(buf[x]); buf[x] = (char)comp_enc[y]; // transpose from encrypt array x++; } } else if (type == PST_ENCRYPT) { // The following code was based on the information at - // http://www.passcape.com/outlook_passwords.htm + // https://www.passcape.com/outlook_passwords uint16_t salt = (uint16_t) (((i_id & 0x00000000ffff0000) >> 16) ^ (i_id & 0x000000000000ffff)); x = 0; while (x < size) { uint8_t losalt = (salt & 0x00ff); uint8_t hisalt = (salt & 0xff00) >> 8; y = (unsigned char)buf[x]; y += losalt; y = comp_high1[y]; y += hisalt; y = comp_high2[y]; y -= hisalt; y = comp_enc[y]; y -= losalt; buf[x] = (char)y; x++; salt++; } } else { DEBUG_WARN(("Unknown encryption: %i. Cannot decrypt\n", type)); DEBUG_RET(); return -1; } DEBUG_RET(); return 0; } static uint64_t pst_getIntAt(pst_file *pf, char *buf) { uint64_t buf64; uint32_t buf32; if (pf->do_read64) { memcpy(&buf64, buf, sizeof(buf64)); LE64_CPU(buf64); return buf64; } else { memcpy(&buf32, buf, sizeof(buf32)); LE32_CPU(buf32); return buf32; } } static uint64_t pst_getIntAtPos(pst_file *pf, int64_t pos ) { uint64_t buf64; uint32_t buf32; if (pf->do_read64) { (void)pst_getAtPos(pf, pos, &buf64, sizeof(buf64)); LE64_CPU(buf64); return buf64; } else { (void)pst_getAtPos(pf, pos, &buf32, sizeof(buf32)); LE32_CPU(buf32); return buf32; } } /** * Read part of the pst file. * * @param pf PST file structure * @param pos offset of the data in the pst file * @param buf buffer to contain the data * @param size size of the buffer and the amount of data to be read * @return actual read size, 0 if seek error */ static size_t pst_getAtPos(pst_file *pf, int64_t pos, void* buf, size_t size) { size_t rc; DEBUG_ENT("pst_getAtPos"); // pst_block_recorder **t = &pf->block_head; // pst_block_recorder *p = pf->block_head; // while (p && ((p->offset+p->size) <= pos)) { // t = &p->next; // p = p->next; // } // if (p && (p->offset <= pos) && (pos < (p->offset+p->size))) { // // bump the count // p->readcount++; // } else { // // add a new block // pst_block_recorder *tail = *t; // p = (pst_block_recorder*)pst_malloc(sizeof(*p)); // *t = p; // p->next = tail; // p->offset = pos; // p->size = size; // p->readcount = 1; // } // DEBUG_INFO(("pst file old offset %#"PRIx64" old size %#x read count %i offset %#"PRIx64" size %#x\n", // p->offset, p->size, p->readcount, pos, size)); if (fseeko(pf->fp, pos, SEEK_SET) == -1) { DEBUG_RET(); return 0; } rc = fread(buf, (size_t)1, size, pf->fp); DEBUG_RET(); return rc; } /** * Get an ID block from file using pst_ff_getIDblock() and decrypt if necessary * @param pf PST file structure * @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) { size_t r; int noenc = (int)(i_id & 2); // disable encryption DEBUG_ENT("pst_ff_getIDblock_dec"); DEBUG_INFO(("for id %#"PRIx64"\n", i_id)); r = pst_ff_getIDblock(pf, i_id, buf); if ((pf->encryption) && !(noenc)) { (void)pst_decrypt(i_id, *buf, r, pf->encryption); } DEBUG_HEXDUMPC(*buf, r, 16); DEBUG_RET(); return r; } /** * Read a block of data from file into memory * @param pf PST file structure * @param i_id ID of block to read * @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 */ static size_t pst_ff_getIDblock(pst_file *pf, uint64_t i_id, char** buf) { pst_index_ll *rec; size_t rsize; DEBUG_ENT("pst_ff_getIDblock"); rec = pst_getID(pf, i_id); if (!rec) { DEBUG_INFO(("Cannot find ID %#"PRIx64"\n", i_id)); DEBUG_RET(); return 0; } DEBUG_INFO(("id = %#"PRIx64", record size = %#x, offset = %#x\n", i_id, rec->size, rec->offset)); rsize = pst_read_block_size(pf, rec->offset, rec->size, rec->inflated_size, buf); DEBUG_RET(); return rsize; } static size_t pst_ff_getID2block(pst_file *pf, uint64_t id2, pst_id2_tree *id2_head, char** buf) { size_t ret; pst_id2_tree* ptr; pst_holder h = {buf, NULL, 0, 0, 0}; DEBUG_ENT("pst_ff_getID2block"); ptr = pst_getID2(id2_head, id2); if (!ptr) { DEBUG_WARN(("Cannot find id2 value %#"PRIx64"\n", id2)); DEBUG_RET(); return 0; } ret = pst_ff_getID2data(pf, ptr->id, &h); DEBUG_RET(); return ret; } /** find the actual data from an i_id and send it to the destination * specified by the pst_holder h. h must be a new empty destination. * * @param pf PST file structure * @param ptr * @param h specifies the output destination (buffer, file, encoding) * @return updated size of the output */ static size_t pst_ff_getID2data(pst_file *pf, pst_index_ll *ptr, pst_holder *h) { size_t ret; char *b = NULL; DEBUG_ENT("pst_ff_getID2data"); if (!(ptr->i_id & 0x02)) { ret = pst_ff_getIDblock_dec(pf, ptr->i_id, &b); ret = pst_append_holder(h, (size_t)0, &b, ret); free(b); } else { // here we will assume it is an indirection block that points to others DEBUG_INFO(("Assuming it is a multi-block record because of it's id %#"PRIx64"\n", ptr->i_id)); ret = pst_ff_compile_ID(pf, ptr->i_id, h, (size_t)0); } ret = pst_finish_cleanup_holder(h, ret); DEBUG_RET(); return ret; } /** find the actual data from an indirection i_id and send it to the destination * specified by the pst_holder. * * @param pf PST file structure * @param i_id ID of the block to read * @param h specifies the output destination (buffer, file, encoding) * @param size number of bytes of data already sent to h * @return updated size of the output */ static size_t pst_ff_compile_ID(pst_file *pf, uint64_t i_id, pst_holder *h, size_t size) { size_t z, a; uint16_t count, y; char *buf3 = NULL; char *buf2 = NULL; char *b_ptr; pst_block_hdr block_hdr; pst_table3_rec table3_rec; //for type 3 (0x0101) blocks DEBUG_ENT("pst_ff_compile_ID"); a = pst_ff_getIDblock(pf, i_id, &buf3); if (!a) { if (buf3) free(buf3); DEBUG_RET(); return 0; } DEBUG_HEXDUMPC(buf3, a, 16); memcpy(&block_hdr, buf3, sizeof(block_hdr)); LE16_CPU(block_hdr.index_offset); LE16_CPU(block_hdr.type); LE32_CPU(block_hdr.offset); DEBUG_INFO(("block header (index_offset=%#hx, type=%#hx, offset=%#x)\n", block_hdr.index_offset, block_hdr.type, block_hdr.offset)); count = block_hdr.type; b_ptr = buf3 + 8; // For indirect lookups through a table of i_ids, just recurse back into this // function, letting it concatenate all the data together, and then return the // total size of the data. if (block_hdr.index_offset == (uint16_t)0x0201) { // Indirect lookup (depth 2). for (y=0; yencryption) (void)pst_decrypt(i_id, buf3, a, pf->encryption); size = pst_append_holder(h, size, &buf3, a); free(buf3); DEBUG_RET(); return size; } for (y=0; ybuf) { *(h->buf) = pst_realloc(*(h->buf), size+z+1); DEBUG_INFO(("appending read data of size %i onto main buffer from pos %i\n", z, size)); memcpy(*(h->buf)+size, *buf, z); // base64 encoding to a file } else if ((h->base64 == 1) && h->fp) { // if (h->base64_extra) { // include any bytes left over from the last encoding *buf = (char*)pst_realloc(*buf, z+h->base64_extra); memmove(*buf+h->base64_extra, *buf, z); memcpy(*buf, h->base64_extra_chars, h->base64_extra); z += h->base64_extra; } // find out how many bytes will be left over after this encoding and save them h->base64_extra = z % 3; if (h->base64_extra) { z -= h->base64_extra; memcpy(h->base64_extra_chars, *buf+z, h->base64_extra); } // encode this chunk t = pst_base64_encode_multiple(*buf, z, &h->base64_line_count); if (t) { DEBUG_INFO(("writing %i bytes to file as base64 [%i]. Currently %i\n", z, strlen(t), size)); (void)pst_fwrite(t, (size_t)1, strlen(t), h->fp); free(t); // caught by valgrind } // raw append to a file } else if (h->fp) { DEBUG_INFO(("writing %i bytes to file. Currently %i\n", z, size)); (void)pst_fwrite(*buf, (size_t)1, z, h->fp); // null output } else { // h-> does not specify any output } DEBUG_RET(); return size+z; } /** finish cleanup for base64 encoding to a file with extra bytes left over * * @param h specifies the output destination (buffer, file, encoding) * @param size number of bytes of data already sent to h * @return updated size of the output */ static size_t pst_finish_cleanup_holder(pst_holder *h, size_t size) { char *t; DEBUG_ENT("pst_finish_cleanup_holder"); if ((h->base64 == 1) && h->fp && h->base64_extra) { // need to encode any bytes left over t = pst_base64_encode_multiple(h->base64_extra_chars, h->base64_extra, &h->base64_line_count); if (t) { (void)pst_fwrite(t, (size_t)1, strlen(t), h->fp); free(t); // caught by valgrind } size += h->base64_extra; } DEBUG_RET(); return size; } /** compare strings case-insensitive. * @return -1 if a < b, 0 if a==b, 1 if a > b */ int pst_stricmp(char *a, char *b) { while(*a != '\0' && *b != '\0' && toupper(*a)==toupper(*b)) { a++; b++; } if (toupper(*a) == toupper(*b)) return 0; else if (toupper(*a) < toupper(*b)) return -1; else return 1; } static int pst_strincmp(char *a, char *b, size_t x) { // compare up to x chars in string a and b case-insensitively // returns -1 if a < b, 0 if a==b, 1 if a > b size_t y = 0; while (*a != '\0' && *b != '\0' && y < x && toupper(*a)==toupper(*b)) { a++; b++; y++; } // if we have reached the end of either string, or a and b still match if (*a == '\0' || *b == '\0' || toupper(*a)==toupper(*b)) return 0; else if (toupper(*a) < toupper(*b)) return -1; else return 1; } size_t pst_fwrite(const void* ptr, size_t size, size_t nmemb, FILE *stream) { size_t r; if (ptr) r = fwrite(ptr, size, nmemb, stream); else { r = 0; DEBUG_ENT("pst_fwrite"); DEBUG_WARN(("An attempt to write a NULL Pointer was made\n")); DEBUG_RET(); } return r; } static char* pst_wide_to_single(char *wt, size_t size) { // returns the first byte of each wide char. the size is the number of bytes in source char *x, *y; DEBUG_ENT("pst_wide_to_single"); x = pst_malloc((size/2)+1); y = x; while (size != 0 && *wt != '\0') { *y = *wt; wt+=2; size -= 2; y++; } *y = '\0'; DEBUG_RET(); return x; } char* pst_rfc2426_escape(char* str, char **buf, size_t* buflen) { //static char* buf = NULL; //static size_t buflen = 0; char *ret, *a, *b; size_t x = 0; int y, z; if (!str) return NULL; DEBUG_ENT("rfc2426_escape"); // calculate space required to escape all the following characters y = pst_chr_count(str, ',') + pst_chr_count(str, '\\') + pst_chr_count(str, ';') + pst_chr_count(str, '\n'); z = pst_chr_count(str, '\r'); if (y == 0 && z == 0) // there isn't any extra space required ret = str; else { x = strlen(str) + y - z + 1; // don't forget room for the NUL if (x > *buflen) { *buf = (char*)pst_realloc(*buf, x); *buflen = x; } a = str; b = *buf; while (*a != '\0') { switch (*a) { case ',' : case '\\': case ';' : *(b++) = '\\'; *b = *a; break; case '\n': // newlines are encoded as "\n" *(b++) = '\\'; *b = 'n'; break; case '\r': // skip cr b--; break; default: *b=*a; } b++; a++; } *b = '\0'; // NUL-terminate the string (buf) ret = *buf; } DEBUG_RET(); return ret; } static int pst_chr_count(char *str, char x) { int r = 0; while (*str) { if (*str == x) r++; str++; } return r; } char* pst_rfc2425_datetime_format(const FILETIME* ft, int buflen, char* result) { struct tm stm; DEBUG_ENT("rfc2425_datetime_format"); pst_fileTimeToStructTM(ft, &stm); if (strftime(result, buflen, "%Y-%m-%dT%H:%M:%SZ", &stm)==0) { DEBUG_INFO(("Problem occurred formatting date\n")); } DEBUG_RET(); return result; } char* pst_rfc2445_datetime_format(const FILETIME* ft, int buflen, char* result) { struct tm stm; DEBUG_ENT("rfc2445_datetime_format"); pst_fileTimeToStructTM(ft, &stm); if (strftime(result, buflen, "%Y%m%dT%H%M%SZ", &stm)==0) { DEBUG_INFO(("Problem occurred formatting date\n")); } DEBUG_RET(); return result; } char* pst_rfc2445_datetime_format_now(int buflen, char* result) { struct tm stm; time_t t = time(NULL); DEBUG_ENT("rfc2445_datetime_format_now"); gmtime_r(&t, &stm); if (strftime(result, buflen, "%Y%m%dT%H%M%SZ", &stm)==0) { DEBUG_INFO(("Problem occurred formatting date\n")); } DEBUG_RET(); return result; } /** Convert a code page integer into a string suitable for iconv() * * @param cp the code page integer used in the pst file * @param[in] buflen length of the output buffer * @param[out] result pointer to output buffer, must be at least 30 bytes * @return pointer to a static buffer holding the string representation of the * equivalent iconv character set */ static const char* codepage(int cp, int buflen, char* result); static const char* codepage(int cp, int buflen, char* result) { switch (cp) { case 932 : return "iso-2022-jp"; case 936 : return "gb2313"; case 950 : return "big5"; case 1200 : return "ucs-2le"; case 1201 : return "ucs-2be"; case 20127 : return "us-ascii"; case 20269 : return "iso-6937"; case 20865 : return "iso-8859-15"; case 20866 : return "koi8-r"; case 21866 : return "koi8-u"; case 28591 : return "iso-8859-1"; case 28592 : return "iso-8859-2"; case 28595 : return "iso-8859-5"; case 28596 : return "iso-8859-6"; case 28597 : return "iso-8859-7"; case 28598 : return "iso-8859-8"; case 28599 : return "iso-8859-9"; case 28600 : return "iso-8859-10"; case 28601 : return "iso-8859-11"; case 28602 : return "iso-8859-12"; case 28603 : return "iso-8859-13"; case 28604 : return "iso-8859-14"; case 28605 : return "iso-8859-15"; case 28606 : return "iso-8859-16"; case 50220 : return "iso-2022-jp"; case 50221 : return "csiso2022jp"; case 51932 : return "euc-jp"; case 51949 : return "euc-kr"; case 65000 : return "utf-7"; case 65001 : return "utf-8"; default : snprintf(result, buflen, "windows-%d", cp); return result; } return NULL; } /** 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 usable by iconv() */ const char* pst_default_charset(pst_item *item, int buflen, char* result) { return (item->body_charset.str) ? item->body_charset.str : (item->message_codepage) ? codepage(item->message_codepage, buflen, result) : (item->internet_cpid) ? codepage(item->internet_cpid, buflen, result) : (item->pf && item->pf->charset) ? item->pf->charset : "iso-8859-1"; } /** Convert str to rfc2231 encoding of str * * @param str pointer to the mapi string of interest */ void pst_rfc2231(pst_string *str) { int needs = 0; const int8_t *x = (int8_t *)str->str; while (*x) { if (*x <= 32) needs++; x++; } int n = strlen(str->str) + 2*needs + 15; char *buffer = pst_malloc(n); strcpy(buffer, "utf-8''"); x = (int8_t *)str->str; const uint8_t *y = (uint8_t *)str->str; uint8_t *z = (uint8_t *)buffer; z += strlen(buffer); // skip the utf8 prefix while (*y) { if (*x <= 32) { *(z++) = (uint8_t)'%'; snprintf(z, 3, "%2x", *y); z += 2; } else { *(z++) = *y; } x++; y++; } *z = '\0'; free(str->str); str->str = buffer; } /** 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) { int has_space = 0; int needs_coding = 0; pst_convert_utf8(item, str); const int8_t *x = (int8_t *)str->str; while (*x) { if (*x == 32) has_space = 1; if (*x < 32) needs_coding = 1; x++; } if (needs_coding) { char *enc = pst_base64_encode_single(str->str, strlen(str->str)); free(str->str); int n = strlen(enc) + 20; str->str = pst_malloc(n); snprintf(str->str, n, "=?utf-8?B?%s?=", enc); free(enc); } else if (has_space && needs_quote) { int n = strlen(str->str) + 10; char *buffer = pst_malloc(n); snprintf(buffer, n, "\"%s\"", str->str); free(str->str); str->str = buffer; } } /** 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) { if (!str->str) return; pst_convert_utf8(item, 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) { DEBUG_ENT("pst_convert_utf8"); char buffer[30]; if (str->is_utf8) { DEBUG_WARN(("Already utf8\n")); DEBUG_RET(); return; } if (!str->str) { str->str = strdup(""); DEBUG_WARN(("null to empty string\n")); DEBUG_RET(); return; } const char *charset = pst_default_charset(item, sizeof(buffer), buffer); DEBUG_WARN(("default charset is %s\n", charset)); if (!strcasecmp("utf-8", charset)) { DEBUG_RET(); return; } pst_vbuf *newer = pst_vballoc(2); size_t rc = pst_vb_8bit2utf8(newer, str->str, strlen(str->str) + 1, charset); if (rc == (size_t)-1) { free(newer->b); DEBUG_WARN(("Failed to convert %s to utf-8 - %s\n", charset, str->str)); } else { free(str->str); str->str = newer->b; str->is_utf8 = 1; } free(newer); DEBUG_RET(); } /** 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) { const int bias = 30 * 24 * 60; // minutes in 30 days int m[4] = {3,4,4,5}; pst_recurrence *r = pst_malloc(sizeof(pst_recurrence)); memset(r, 0, sizeof(pst_recurrence)); size_t s = appt->recurrence_data.size; size_t i = 0; char* p = appt->recurrence_data.data; if (p) { if (i+4 <= s) { r->signature = PST_LE_GET_UINT32(p+i); i += 4; } if (i <= s) { r->type = PST_LE_GET_UINT8(p+i) - 0x0a; i += 2; } if (i+4 <= s) { r->sub_type = PST_LE_GET_UINT32(p+i); i += 4; } if (r->sub_type <= 3) { int n = m[r->sub_type]; // number of parms for this sub_type int j = 0; for (j=0; jparm1 + j) = PST_LE_GET_UINT32(p+i); i += 4; } } } if (i <= s) { r->termination = PST_LE_GET_UINT8(p+i) - 0x21; i += 4; } if (i+4 <= s) { r->count = PST_LE_GET_UINT32(p+i); i += 4; } if (r->termination == 2) r->count = 0; switch (r->type) { case 0: // daily if (r->sub_type == 0) { // simple daily r->interval = r->parm2 / (24 * 60); // was minutes between recurrences } else { // daily every weekday, subset of weekly r->interval = 1; r->bydaymask = r->parm4; } break; case 1: // weekly r->interval = r->parm2; r->bydaymask = r->parm4; break; case 2: // monthly r->interval = r->parm2; if (r->sub_type == 2) { // monthly on day d r->dayofmonth = r->parm4; } else { // monthly on 2nd tuesday r->bydaymask = r->parm4; r->position = r->parm5; } break; case 3: // yearly r->interval = 1; r->monthofyear = ((r->parm1 + bias/2) / bias) + 1; if (r->sub_type == 2) { // yearly on day d of month m r->dayofmonth = r->parm4; } else { // yearly on 2nd tuesday of month m r->bydaymask = r->parm4; r->position = r->parm5; } break; default: break; } } return r; } /** Free a recurrence structure. * @param r input pointer to be freed */ void pst_free_recurrence(pst_recurrence* r) { if (r) free(r); } diff --git a/src/libpst.h b/src/libpst.h index b521d31..0bfcc38 100644 --- a/src/libpst.h +++ b/src/libpst.h @@ -1,1177 +1,1177 @@ /*** * 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" #ifdef __cplusplus extern "C" { #endif // 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 recurring 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; uint64_t inflated_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* characters 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 + https://web.archive.org/web/20091026194513/http://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; /** occurrence 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 * canonical 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 canonical 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; * @li 2 is 64-bit OST file, Outlook 2013 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 usable 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 #ifdef __cplusplus } #endif #endif diff --git a/src/nick2ldif.cpp b/src/nick2ldif.cpp index 5138e06..690f7b7 100644 --- a/src/nick2ldif.cpp +++ b/src/nick2ldif.cpp @@ -1,84 +1,84 @@ /* Copyright (c) 2004 Carl Byington - 510 Software Group, released under the GPL version 2 or any later version at your choice available at -http://www.fsf.org/licenses/gpl.txt +https://www.gnu.org/licenses/old-licenses/gpl-2.0.txt */ #include extern "C" { #include "define.h" } char *ldap_base = NULL; char *ldap_org = NULL; char *ldap_class = NULL; using namespace std; int main(int argc, char* const* argv) { char c; char *temp; while ((c = getopt(argc, argv, "b:c:"))!= -1) { switch (c) { case 'b': ldap_base = optarg; temp = strchr(ldap_base, ','); if (temp) { *temp = '\0'; ldap_org = strdup(ldap_base); *temp = ','; } break; case 'c': ldap_class = optarg; break; default: break; } } const int LINE_SIZE = 2000; char line[LINE_SIZE]; while (!cin.eof()) { cin.getline(line, LINE_SIZE); int n = strlen(line); if (!n) continue; if (strncmp(line, "alias", 5) != 0) continue; // not alias char *f = line + 6; // skip alias keyword char *e; if (*f == '"') { f++; e = strchr(f, '"'); } else { e = strchr(f, ' '); } if (!e) continue; *e = '\0'; char *m = e+1; while (*m == ' ') m++; if (*m != '\0') { char cn[1000], givenName[1000], sn[1000]; snprintf(cn, sizeof(cn), "%s", f); char *ff = strchr(f, ' '); if (ff) { strncpy(givenName, ff+1, sizeof(givenName)-1); *ff = '\0'; strncpy(sn, f, sizeof(sn)-1); } else { strcpy(givenName, cn); strcpy(sn, cn); } printf("dn: cn=%s, %s\n", cn, ldap_base); printf("cn: %s\n", cn); printf("givenName: %s\n", givenName); printf("sn: %s\n", sn); printf("mail: %s\n", m); printf("objectClass: %s\n\n", ldap_class); } } } diff --git a/src/pst2dii.cpp.in b/src/pst2dii.cpp.in index 6fd7d41..0b2dcf5 100644 --- a/src/pst2dii.cpp.in +++ b/src/pst2dii.cpp.in @@ -1,730 +1,730 @@ /* Copyright (c) 2008 Carl Byington - 510 Software Group, released under the GPL version 2 or any later version at your choice available at -http://www.fsf.org/licenses/gpl.txt +https://www.gnu.org/licenses/old-licenses/gpl-2.0.txt Based on readpst.c by David Smith */ #include #include #include using namespace std; extern "C" { #include "define.h" #include "lzfu.h" } struct file_ll { string name; int32_t stored_count; int32_t email_count; int32_t skip_count; int32_t type; file_ll() { stored_count = 0; email_count = 0; skip_count = 0; type = 0; }; }; // global settings const char* convert = "@CONVERT@"; // fully qualified path of the convert program from image magick const char* prog_name = NULL; // our arg0 name const char* bates_prefix = ""; // string to prefix bates numbers int bates_index = 0; // current bates sequence const char* output_directory = "."; const char* output_file = "load.dii"; char* font_file = NULL; int bates_color = 0xff0000; // color of bates header stamp int email_sequence = 0; // current pdf sequence number char* pdf_name = NULL; // current pdf file name FILE* dii_file = NULL; // the output dii load file pst_file pstfile; // the input pst file // pdf writer globals bool pdf_open = false; // is pdf writer started char* pst_folder; // current folder name int page_sequence; // current page number string conversion; // conversion command vector png_names; // png writer globals bool png_open = false; // is current page open int line_height; // in pixels int char_width; // in pixels int col_number, col_max; // in characters int line_number, line_max; // lines per page int x_position, y_position; // in pixels int black, red; // text colors gdImagePtr image; // current gd image const int DPI = 300; const double sz = 10.0; const int margin = DPI/2; const int LINE_SIZE = 2000; const int PAGE_WIDTH = DPI*17/2; const int PAGE_HEIGHT = DPI*11; // max size of the c_time char*. It will store the date of the email #define C_TIME_SIZE 500 static void open_png(); static void close_png(); static void version(); static void version() { printf("pst2dii 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 } static void usage(); static void usage() { version(); printf("Usage: %s -f ttf-font-file [OPTIONS] {PST FILENAME}\n", prog_name); printf("\t-f ttf-font-file \t- Set the font file\n"); printf("OPTIONS:\n"); printf("\t-B bates-prefix \t- Set the bates prefix string\n"); printf("\t-O dii-output-file\t- Set the dii load file output filename\n"); printf("\t-V \t- Version. Display program version\n"); printf("\t-b bates-number \t- Set the starting bates sequence number\n"); printf("\t-c bates-color \t- Specify the color of the bates stamps as 6 digit hex\n"); printf("\t-d filename \t- Debug to file.\n"); printf("\t-h \t- Help. This screen\n"); printf("\t-o dirname \t- Output directory to write files to.\n"); } static char *removeCR (char *c); static char *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(); return c; } // The sole purpose of this function is to bypass the pseudo-header prologue // that Microsoft Outlook inserts at the beginning of the internet email // headers for emails stored in their "Personal Folders" files. static char *skip_header_prologue(char *headers); static char *skip_header_prologue(char *headers) { const char *bad = "Microsoft Mail Internet Headers"; if (strncmp(headers, bad, strlen(bad)) == 0) { // Found the offensive header prologue char *pc = strchr(headers, '\n'); return pc + 1; } return headers; } static void check_filename(string &fname); static void check_filename(string &fname) { char *t = strdup(fname.c_str()); DEBUG_ENT("check_filename"); if (!t) { DEBUG_RET(); return; } char *tt = t; bool fixed = false; while ((t = strpbrk(t, " /\\:"))) { // while there are characters in the second string that we don't want *t = '_'; //replace them with an underscore fixed = true; } if (fixed) fname = string(tt); free(tt); DEBUG_RET(); } static string write_separate_attachment(string fname, pst_item_attach* current_attach, int attach_num, pst_file* pst); static string write_separate_attachment(string fname, pst_item_attach* current_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 = (current_attach->filename2.str) ? current_attach->filename2.str : current_attach->filename1.str; DEBUG_ENT("write_separate_attachment"); check_filename(fname); const char* f_name = fname.c_str(); DEBUG_INFO(("dirname=%s, pathname=%s, filename=%s\n", output_directory, f_name, attach_filename)); int len = strlen(output_directory) + 1 + strlen(f_name) + 15; if (!attach_filename) { // generate our own (dummy) filename for the attachment temp = (char*)pst_malloc(len); sprintf(temp, "%s/%s_attach%i", output_directory, f_name, attach_num); } else { // have an attachment name, make sure it's unique temp = (char*)pst_malloc(len+strlen(attach_filename)); do { if (fp) fclose(fp); if (x == 0) sprintf(temp, "%s/%s_%s", output_directory, f_name, attach_filename); else sprintf(temp, "%s/%s_%s-%i", output_directory, 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, "wb"))) { DEBUG_WARN(("write_separate_attachment: Cannot open attachment save file \"%s\"\n", temp)); } else { (void)pst_attach_to_file(pst, current_attach, fp); fclose(fp); } string rc(temp); if (temp) free(temp); DEBUG_RET(); return rc; } static void print_pdf_short(const char *line, int len, int color); static void print_pdf_short(const char *line, int len, int color) { if (line_number >= line_max) { close_png(); open_png(); } int brect[8]; gdFTStringExtra strex; strex.flags = gdFTEX_RESOLUTION; strex.linespacing = 1.20; strex.charmap = 0; strex.hdpi = DPI; strex.vdpi = DPI; char xline[len+1]; memcpy(xline, line, len); xline[len] = '\0'; char *p; char *l = xline; while ((p = strchr(l, '&'))) { *p = '\0'; char *err = gdImageStringFTEx(image, &brect[0], color, font_file, sz, 0.0, x_position, y_position, l, &strex); if (err) printf("%s", err); x_position += (brect[2]-brect[6]); l = p+1; err = gdImageStringFTEx(image, &brect[0], color, font_file, sz, 0.0, x_position, y_position, (char*)"&", &strex); if (err) printf("%s", err); x_position += (brect[2]-brect[6]); } char *err = gdImageStringFTEx(image, &brect[0], color, font_file, sz, 0.0, x_position, y_position, l, &strex); if (err) printf("%s", err); x_position += (brect[2]-brect[6]); col_number += len; } static void new_line(); static void new_line() { y_position += line_height; line_number += 1; x_position = margin; col_number = 0; } static void print_pdf_single(const char *line, int color); static void print_pdf_single(const char *line, int color) { while (*line == '\t') { char blanks[5]; memset(blanks, ' ', 5); print_pdf_short(blanks, 4, color); line++; if (col_number >= col_max) new_line(); } int n = strlen(line); while (n) { int m = col_max - col_number; // number of chars that will fit on this line m = (n > m) ? m : n; print_pdf_short(line, m, color); line += m; n -= m; if (n) new_line(); } } static void print_pdf_only(char *line, int color); static void print_pdf_only(char *line, int color) { char *p; while ((p = strchr(line, '\n'))) { *p = '\0'; print_pdf_single(line, color); *p = '\n'; line = p+1; new_line(); } print_pdf_single(line, color); } static void print_pdf(char *line); static void print_pdf(char *line) { pst_fwrite(line, 1, strlen(line), dii_file); print_pdf_only(line, black); } static void open_png() { if (!png_open) { png_open = true; int brect[8]; image = gdImageCreate(PAGE_WIDTH, PAGE_HEIGHT); gdImageColorAllocate(image, 255, 255, 255); // background color first one allocated black = gdImageColorAllocate(image, 0, 0, 0); int r = (bates_color & 0xff0000) >> 16; int g = (bates_color & 0x00ff00) >> 8; int b = (bates_color & 0x0000ff); red = gdImageColorAllocate(image, r, g, b); gdFTStringExtra strex; strex.flags = gdFTEX_RESOLUTION; strex.linespacing = 1.20; strex.charmap = 0; strex.hdpi = DPI; strex.vdpi = DPI; char line[LINE_SIZE]; char *err = gdImageStringFTEx(NULL, &brect[0], black, font_file, sz, 0.0, margin, margin, (char*)"LMgqQ", &strex); if (err) printf("%s", err); line_height = (brect[3]-brect[7]) * 12/10; char_width = (brect[2]-brect[6]) / 5; col_number = 0; col_max = (PAGE_WIDTH - margin*2) / char_width; line_number = 0; line_max = (PAGE_HEIGHT - margin*2) / line_height; x_position = margin; y_position = margin + line_height; snprintf(line, sizeof(line), "%s%06d\n", bates_prefix, bates_index++); print_pdf_only(line, red); print_pdf_only(pst_folder, red); } } static void close_png() { if (png_open) { png_open = false; int len = 4 + 11 + 4 +1; char *fn = (char*)pst_malloc(len); snprintf(fn, len, "page%d.png", ++page_sequence); FILE *pngout = fopen(fn, "wb"); if (pngout) { gdImagePng(image, pngout); fclose(pngout); } gdImageDestroy(image); // free memory png_names.push_back(fn); conversion += string(" ") + fn; free(fn); } } static void open_pdf(char *line); static void open_pdf(char *line) { pst_folder = line; page_sequence = 0; conversion = string(convert); png_names.clear(); open_png(); /* Note; allocating the largest string length to pdf_name */ int len = strlen(output_directory) + 4 + 6 + 4 + 1; pdf_name = (char*)pst_malloc(len); snprintf(pdf_name, 3 + 6 + 1, "dii%06d", ++email_sequence); fprintf(dii_file, "\n@T %s\n", pdf_name); snprintf(pdf_name, len, "%s/dii%06d.pdf", output_directory, email_sequence); } static void close_pdf(); static void close_pdf() { close_png(); conversion += string(" ") + pdf_name; (void)system(conversion.c_str()); for (vector::iterator i=png_names.begin(); i!=png_names.end(); i++) { remove((*i).c_str()); } fprintf(dii_file, "@D %s\n", pdf_name); free(pdf_name); } static void write_simple(const char *tag, const char *value); static void write_simple(const char *tag, const char *value) { if (value) fprintf(dii_file, "@%s %s\n", tag, value); } static void write_simple(const char *tag, string value); static void write_simple(const char *tag, string value) { fprintf(dii_file, "@%s %s\n", tag, value.c_str()); } static void write_simple(const char *tag, const char *value, const char *value2); static void write_simple(const char *tag, const char *value, const char *value2) { if (value) { if (value2) fprintf(dii_file, "@%s \"%s\" <%s>\n", tag, value, value2); else fprintf(dii_file, "@%s \"%s\"\n", tag, value); } } static string extract_header(char *headers, const char *field); static string extract_header(char *headers, const char *field) { string rc; int len = strlen(field) + 4; char f[len]; snprintf(f, len, "\n%s: ", field); char *p = strstr(headers, f); if (p) { p += strlen(f); char *n = strchr(p, '\n'); if (n) { *n = '\0'; rc = string(p); *n = '\n'; } else { rc = string(p); } } return rc; } static void write_normal_email(file_ll &f, pst_item* item, pst_file* pst); static void write_normal_email(file_ll &f, pst_item* item, pst_file* pst) { DEBUG_ENT("write_normal_email"); char *soh = NULL; // real start of headers. if (item->email->header.str) { // some of the headers we get from the file are not properly defined. // they can contain some email stuff too. We will cut off the header // when we see a \n\n or \r\n\r\n removeCR(item->email->header.str); char *temp = strstr(item->email->header.str, "\n\n"); if (temp) { DEBUG_INFO(("Found body text in header\n")); temp[1] = '\0'; // stop after first \n } soh = skip_header_prologue(item->email->header.str); } char folder_line[LINE_SIZE]; char line[LINE_SIZE]; // reset pdf writer to new file int bates = bates_index; // save starting index snprintf(folder_line, sizeof(folder_line), "pst folder = %s\n", f.name.c_str()); open_pdf(folder_line); // start printing this email fprintf(dii_file, "@FOLDERNAME %s\n", f.name.c_str()); string myfrom = extract_header(soh, "From"); string myto = extract_header(soh, "To"); string mycc = extract_header(soh, "Cc"); string mybcc = extract_header(soh, "Bcc"); if (myfrom.empty()) write_simple("FROM", item->email->outlook_sender_name.str, item->email->sender_address.str); else write_simple("FROM", myfrom); if (myto.empty()) write_simple("TO", item->email->sentto_address.str, item->email->recip_address.str); else write_simple("TO", myto); if (mycc.empty()) write_simple("CC", item->email->cc_address.str); else write_simple("CC", mycc); if (mybcc.empty()) write_simple("BCC", item->email->bcc_address.str); else write_simple("BCC", mybcc); if (item->email->sent_date) { time_t t = pst_fileTimeToUnixTime(item->email->sent_date); char c_time[C_TIME_SIZE]; strftime(c_time, C_TIME_SIZE, "%F", gmtime(&t)); write_simple("DATESENT", c_time); strftime(c_time, C_TIME_SIZE, "%T+0000", gmtime(&t)); write_simple("TIMESENT", c_time); } if (item->email->arrival_date) { time_t t = pst_fileTimeToUnixTime(item->email->arrival_date); char c_time[C_TIME_SIZE]; strftime(c_time, C_TIME_SIZE, "%F", gmtime(&t)); write_simple("DATERCVD", c_time); strftime(c_time, C_TIME_SIZE, "%T+0000", gmtime(&t)); write_simple("TIMERCVD", c_time); } if (item->subject.str) { write_simple("SUBJECT", item->subject.str); } write_simple("MSGID", item->email->messageid.str); write_simple("READ", (item->flags & 1) ? "Y" : "N"); DEBUG_INFO(("About to print Header\n")); fprintf(dii_file, "@HEADER\n"); if (item && item->subject.str) { DEBUG_INFO(("item->subject = %s\n", item->subject.str)); } if (soh) { // Now, write out the header... print_pdf(soh); int len = strlen(soh); if (!len || (soh[len-1] != '\n')) { snprintf(line, sizeof(line), "\n"); print_pdf(line); } } else { //make up our own headers const char *temp = item->email->outlook_sender.str; if (!temp) temp = ""; snprintf(line, sizeof(line), "From: \"%s\" <%s>\n", item->email->outlook_sender_name.str, temp); print_pdf(line); if (item->subject.str) { snprintf(line, sizeof(line), "Subject: %s\n", item->subject.str); } else { snprintf(line, sizeof(line), "Subject: \n"); } print_pdf(line); snprintf(line, sizeof(line), "To: %s\n", item->email->sentto_address.str); print_pdf(line); if (item->email->cc_address.str) { snprintf(line, sizeof(line), "Cc: %s\n", item->email->cc_address.str); print_pdf(line); } if (item->email->sent_date) { time_t em_time = pst_fileTimeToUnixTime(item->email->sent_date); char c_time[C_TIME_SIZE]; strftime(c_time, C_TIME_SIZE, "%a, %d %b %Y %H:%M:%S %z", gmtime(&em_time)); snprintf(line, sizeof(line), "Date: %s\n", c_time); print_pdf(line); } } snprintf(line, sizeof(line), "\n"); print_pdf_only(line, black); fprintf(dii_file, "@HEADER-END\n"); DEBUG_INFO(("About to print Body\n")); fprintf(dii_file, "@EMAIL-BODY\n"); if (item->body.str) { removeCR(item->body.str); print_pdf(item->body.str); } else if (item->email->htmlbody.str) { removeCR(item->email->htmlbody.str); print_pdf(item->email->htmlbody.str); } else if (item->email->encrypted_body.data || item->email->encrypted_htmlbody.data) { char ln[LINE_SIZE]; snprintf(ln, sizeof(ln), "%s", "The body of this email is encrypted. This isn't supported yet, but the body is now an attachment\n"); print_pdf(ln); } fprintf(dii_file, "@EMAIL-END\n"); int attach_num = 0; for (pst_item_attach* 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->data.data || attach->i_id) { string an = write_separate_attachment(f.name, attach, ++attach_num, pst); fprintf(dii_file, "@EATTACH %s\n", an.c_str()); } } close_pdf(); fprintf(dii_file, "@BATESBEG %d\n", bates); fprintf(dii_file, "@BATESEND %d\n", bates_index-1); DEBUG_RET(); } static void create_enter_dir(file_ll &f, file_ll *parent, pst_item *item); static void create_enter_dir(file_ll &f, file_ll *parent, pst_item *item) { pst_convert_utf8(item, &item->file_as); f.type = item->type; f.stored_count = (item->folder) ? item->folder->item_count : 0; f.name = ((parent) ? parent->name + "/" : "") + string(item->file_as.str); } static void close_enter_dir(file_ll &f); static void close_enter_dir(file_ll &f) { } static void process(pst_item *outeritem, file_ll *parent, pst_desc_tree *d_ptr); static void process(pst_item *outeritem, file_ll *parent, pst_desc_tree *d_ptr) { file_ll ff; pst_item *item = NULL; DEBUG_ENT("process"); create_enter_dir(ff, parent, outeritem); for (; d_ptr; d_ptr = d_ptr->next) { if (d_ptr->desc) { item = pst_parse_item(&pstfile, d_ptr, NULL); DEBUG_INFO(("item pointer is %p\n", item)); if (item) { if (item->folder && item->file_as.str && d_ptr->child ) { //if this is a non-empty folder, we want to recurse into it fprintf(stderr, "entering folder %s\n", item->file_as.str); process(item, &ff, d_ptr->child); } else if (item->email && (item->type == PST_TYPE_NOTE || item->type == PST_TYPE_SCHEDULE || item->type == PST_TYPE_REPORT)) { ff.email_count++; write_normal_email(ff, item, &pstfile); } else { ff.skip_count++; // other mapi objects } pst_freeItem(item); } else { ff.skip_count++; DEBUG_INFO(("A NULL item was seen\n")); } } } close_enter_dir(ff); DEBUG_RET(); } int main(int argc, char* const* argv) { pst_desc_tree *d_ptr; char *fname = NULL; char c; char *d_log = NULL; prog_name = argv[0]; pst_item *item = NULL; while ((c = getopt(argc, argv, "B:b:c:d:f:o:O:Vh"))!= -1) { switch (c) { case 'B': bates_prefix = optarg; break; case 'b': bates_index = atoi(optarg); break; case 'c': bates_color = (int)strtol(optarg, (char**)NULL, 16); break; case 'f': font_file = optarg; break; case 'o': output_directory = optarg; break; case 'O': output_file = optarg; break; case 'd': d_log = optarg; break; case 'h': usage(); exit(0); break; case 'V': version(); exit(0); break; default: usage(); exit(1); break; } } if (!font_file) { usage(); exit(1); } if (argc > optind) { fname = argv[optind]; } else { usage(); exit(2); } #ifdef DEBUG_ALL // force a log file if (!d_log) d_log = "pst2dii.log"; #endif DEBUG_INIT(d_log, NULL); DEBUG_ENT("main"); RET_DERROR(pst_open(&pstfile, fname, NULL), 1, ("Error opening File\n")); RET_DERROR(pst_load_index(&pstfile), 2, ("Index Error\n")); pst_load_extended_attributes(&pstfile); d_ptr = pstfile.d_head; // first record is main record item = (pst_item*)pst_parse_item(&pstfile, d_ptr, NULL); if (!item || !item->message_store) { DEBUG_RET(); DIE(("Could not get root record\n")); } d_ptr = pst_getTopOfFolders(&pstfile, item); if (!d_ptr) { DEBUG_RET(); DIE(("Top of folders record not found. Cannot continue\n")); } dii_file = fopen(output_file, "wb"); if (dii_file) { process(item, NULL, d_ptr->child); // do the children of TOPF pst_freeItem(item); pst_close(&pstfile); fclose(dii_file); } DEBUG_RET(); return 0; } diff --git a/src/pst2ldif.cpp b/src/pst2ldif.cpp index 02acc65..119bd72 100644 --- a/src/pst2ldif.cpp +++ b/src/pst2ldif.cpp @@ -1,765 +1,765 @@ /* Copyright (c) 2004 Carl Byington - 510 Software Group, released under the GPL version 2 or any later version at your choice available at -http://www.fsf.org/licenses/gpl.txt +https://www.gnu.org/licenses/old-licenses/gpl-2.0.txt Based on readpst.c by David Smith */ using namespace std; // needed for std c++ collections #include #include #include extern "C" { #include "define.h" #include "lzfu.h" } void usage(void); void version(void); char *check_filename(char *fname); void print_ldif_single(const char *attr, const char *value); void print_ldif_single(const char *attr, pst_string value); void print_ldif_address(const char *attr, int nvalues, pst_string value, ...); void print_ldif_dn(const char *attr, pst_string value, const char *base); void print_ldif_multi(const char *dn, pst_string value); void print_ldif_two(const char *attr, pst_string value1, pst_string value2); void print_escaped_dn(const char *value); void build_cn(char *cn, size_t len, int nvalues, pst_string value, ...); char *prog_name; pst_file pstfile; bool old_schema = false; char *ldap_base = NULL; // 'o=some.domain.tld,c=US' int ldif_extra_line_count = 0; vector ldap_class; // 'newPerson' or 'inetOrgPerson' vector ldif_extra_line; // 'o: myorg' //////////////////////////////////////////////// // define our ordering struct ltstr { bool operator()(const char* s1, const char* s2) const { return strcasecmp(s1, s2) < 0; } }; // define our set typedef set string_set; // make a static set to hold the cn values static string_set all_strings; //////////////////////////////////////////////// // helper to free all the strings in a set // static void free_strings(string_set &s); static void free_strings(string_set &s) { if (s.empty()) return; for (string_set::iterator i=s.begin(); i!=s.end(); i++) { free((void*)*i); } s.clear(); } //////////////////////////////////////////////// // helper to register a string in a string set // static const char* register_string(string_set &s, const char *name); static const char* register_string(string_set &s, const char *name) { string_set::const_iterator i = s.find(name); if (i != s.end()) return *i; char *x = strdup(name); s.insert(x); return x; } //////////////////////////////////////////////// // register a global string // static const char* register_string(const char *name); static const char* register_string(const char *name) { return register_string(all_strings, name); } //////////////////////////////////////////////// // make a unique string // static const char* unique_string(const char *name); static const char* unique_string(const char *name) { int unique = 2; string_set::iterator i = all_strings.find(name); if (i == all_strings.end()) return register_string(name); while (true) { vector n(strlen(name)+10); snprintf(&n[0], n.size(), "%s %d", name, unique++); string_set::iterator i = all_strings.find(&n[0]); if (i == all_strings.end()) return register_string(&n[0]); } } static void process(pst_desc_tree *d_ptr); static void process(pst_desc_tree *d_ptr) { DEBUG_ENT("process"); pst_item *item = NULL; while (d_ptr) { if (d_ptr->desc) { item = pst_parse_item(&pstfile, d_ptr, NULL); DEBUG_INFO(("item pointer is %p\n", item)); if (item) { if (item->folder && d_ptr->child && item->file_as.str && strcasecmp(item->file_as.str, "Deleted Items")) { //if this is a non-empty folder other than deleted items, we want to recurse into it fprintf(stderr, "entering folder %s\n", item->file_as.str); process(d_ptr->child); } else if (item->contact && (item->type == PST_TYPE_CONTACT)) { // deal with a contact char cn[1000]; // convert everything to utf8 pst_convert_utf8_null(item, &item->contact->display_name_prefix); pst_convert_utf8_null(item, &item->contact->first_name); pst_convert_utf8_null(item, &item->contact->surname); pst_convert_utf8_null(item, &item->contact->suffix); pst_convert_utf8_null(item, &item->contact->company_name); pst_convert_utf8_null(item, &item->contact->job_title); pst_convert_utf8_null(item, &item->contact->address1); pst_convert_utf8_null(item, &item->contact->address2); pst_convert_utf8_null(item, &item->contact->address3); pst_convert_utf8_null(item, &item->contact->address1a); pst_convert_utf8_null(item, &item->contact->address2a); pst_convert_utf8_null(item, &item->contact->address3a); pst_convert_utf8_null(item, &item->contact->business_address); pst_convert_utf8_null(item, &item->contact->business_po_box); pst_convert_utf8_null(item, &item->contact->business_street); pst_convert_utf8_null(item, &item->contact->business_city); pst_convert_utf8_null(item, &item->contact->business_state); pst_convert_utf8_null(item, &item->contact->business_postal_code); pst_convert_utf8_null(item, &item->contact->home_address); pst_convert_utf8_null(item, &item->contact->home_po_box); pst_convert_utf8_null(item, &item->contact->home_street); pst_convert_utf8_null(item, &item->contact->home_city); pst_convert_utf8_null(item, &item->contact->home_state); pst_convert_utf8_null(item, &item->contact->home_postal_code); pst_convert_utf8_null(item, &item->contact->other_address); pst_convert_utf8_null(item, &item->contact->other_po_box); pst_convert_utf8_null(item, &item->contact->other_street); pst_convert_utf8_null(item, &item->contact->other_city); pst_convert_utf8_null(item, &item->contact->other_state); pst_convert_utf8_null(item, &item->contact->other_postal_code); pst_convert_utf8_null(item, &item->contact->business_fax); pst_convert_utf8_null(item, &item->contact->home_fax); pst_convert_utf8_null(item, &item->contact->business_phone); pst_convert_utf8_null(item, &item->contact->home_phone); pst_convert_utf8_null(item, &item->contact->car_phone); pst_convert_utf8_null(item, &item->contact->mobile_phone); pst_convert_utf8_null(item, &item->contact->other_phone); pst_convert_utf8_null(item, &item->contact->business_homepage); pst_convert_utf8_null(item, &item->contact->personal_homepage); pst_convert_utf8_null(item, &item->comment); build_cn(cn, sizeof(cn), 4, item->contact->display_name_prefix, item->contact->first_name, item->contact->surname, item->contact->suffix); if (cn[0] != 0) { // have a valid cn pst_string ucn; ucn.str = (char*)unique_string(cn); ucn.is_utf8 = 1; // all the components are already utf8 print_ldif_dn("dn", ucn, ldap_base); print_ldif_single("cn", ucn); if (item->contact->first_name.str) { print_ldif_two("givenName", item->contact->display_name_prefix, item->contact->first_name); } if (item->contact->surname.str) { print_ldif_two("sn", item->contact->surname, item->contact->suffix); } else if (item->contact->company_name.str) { print_ldif_single("sn", item->contact->company_name); } else print_ldif_single("sn", ucn); // use cn as sn if we cannot find something better if (old_schema) { if (item->contact->job_title.str) print_ldif_single("personalTitle", item->contact->job_title); if (item->contact->company_name.str) print_ldif_single("company", item->contact->company_name); } else { // new schema if (item->contact->job_title.str) print_ldif_single("title", item->contact->job_title); if (item->contact->company_name.str) print_ldif_single("o", item->contact->company_name); } if (item->contact->address1.str && *item->contact->address1.str) print_ldif_single("mail", item->contact->address1); if (item->contact->address2.str && *item->contact->address2.str) print_ldif_single("mail", item->contact->address2); if (item->contact->address3.str && *item->contact->address3.str) print_ldif_single("mail", item->contact->address3); if (item->contact->address1a.str && *item->contact->address1a.str) print_ldif_single("mail", item->contact->address1a); if (item->contact->address2a.str && *item->contact->address2a.str) print_ldif_single("mail", item->contact->address2a); if (item->contact->address3a.str && *item->contact->address3a.str) print_ldif_single("mail", item->contact->address3a); if (old_schema) { if (item->contact->business_address.str) { if (item->contact->business_po_box.str) print_ldif_single("postalAddress", item->contact->business_po_box); if (item->contact->business_street.str) print_ldif_multi("postalAddress", item->contact->business_street); if (item->contact->business_city.str) print_ldif_single("l", item->contact->business_city); if (item->contact->business_state.str) print_ldif_single("st", item->contact->business_state); if (item->contact->business_postal_code.str) print_ldif_single("postalCode", item->contact->business_postal_code); } else if (item->contact->home_address.str) { if (item->contact->home_po_box.str) print_ldif_single("postalAddress", item->contact->home_po_box); if (item->contact->home_street.str) print_ldif_multi("postalAddress", item->contact->home_street); if (item->contact->home_city.str) print_ldif_single("l", item->contact->home_city); if (item->contact->home_state.str) print_ldif_single("st", item->contact->home_state); if (item->contact->home_postal_code.str) print_ldif_single("postalCode", item->contact->home_postal_code); } else if (item->contact->other_address.str) { if (item->contact->other_po_box.str) print_ldif_single("postalAddress", item->contact->other_po_box); if (item->contact->other_street.str) print_ldif_multi("postalAddress", item->contact->other_street); if (item->contact->other_city.str) print_ldif_single("l", item->contact->other_city); if (item->contact->other_state.str) print_ldif_single("st", item->contact->other_state); if (item->contact->other_postal_code.str) print_ldif_single("postalCode", item->contact->other_postal_code); } } else { // new schema, with proper RFC4517 postal addresses if (item->contact->business_address.str) { print_ldif_address("postalAddress", 6, item->contact->business_po_box, item->contact->business_street, item->contact->business_city, item->contact->business_state, item->contact->business_postal_code, item->contact->business_country); if (item->contact->business_city.str) print_ldif_single("l", item->contact->business_city); if (item->contact->business_state.str) print_ldif_single("st", item->contact->business_state); if (item->contact->business_postal_code.str) print_ldif_single("postalCode", item->contact->business_postal_code); } else if (item->contact->home_address.str) { if (item->contact->home_city.str) print_ldif_single("l", item->contact->home_city); if (item->contact->home_state.str) print_ldif_single("st", item->contact->home_state); if (item->contact->home_postal_code.str) print_ldif_single("postalCode", item->contact->home_postal_code); } else if (item->contact->other_address.str) { print_ldif_address("postalAddress", 6, item->contact->other_po_box, item->contact->other_street, item->contact->other_city, item->contact->other_state, item->contact->other_postal_code, item->contact->other_country); if (item->contact->other_city.str) print_ldif_single("l", item->contact->other_city); if (item->contact->other_state.str) print_ldif_single("st", item->contact->other_state); if (item->contact->other_postal_code.str) print_ldif_single("postalCode", item->contact->other_postal_code); } if (item->contact->home_address.str) { print_ldif_address("homePostalAddress", 6, item->contact->home_po_box, item->contact->home_street, item->contact->home_city, item->contact->home_state, item->contact->home_postal_code, item->contact->home_country); } } if (item->contact->business_fax.str) print_ldif_single("facsimileTelephoneNumber", item->contact->business_fax); else if (item->contact->home_fax.str) print_ldif_single("facsimileTelephoneNumber", item->contact->home_fax); if (item->contact->business_phone.str) print_ldif_single("telephoneNumber", item->contact->business_phone); if (item->contact->home_phone.str) print_ldif_single("homePhone", item->contact->home_phone); if (item->contact->car_phone.str) print_ldif_single("mobile", item->contact->car_phone); else if (item->contact->mobile_phone.str) print_ldif_single("mobile", item->contact->mobile_phone); else if (item->contact->other_phone.str) print_ldif_single("mobile", item->contact->other_phone); if (!old_schema) { if (item->contact->business_homepage.str) print_ldif_single("labeledURI", item->contact->business_homepage); if (item->contact->personal_homepage.str) print_ldif_single("labeledURI", item->contact->personal_homepage); } if (item->comment.str) print_ldif_single("description", item->comment); for (vector::size_type i=0; inext; } DEBUG_RET(); } void print_ldif_single(const char *attr, pst_string value) { print_ldif_single(attr, value.str); } // Prints an attribute together with its value. // If the value isn't a "SAFE STRING" (as defined in RFC2849), // then it is output as a BASE-64 encoded value void print_ldif_single(const char *attr, const char *value) { size_t len; bool is_safe_string = true; bool space_flag = false; // Strip leading spaces while (*value == ' ') value++; len = strlen(value) + 1; vector buffer(len); char *p = &buffer[0]; // See if "value" is a "SAFE STRING" // First check characters that are safe but not safe as initial characters if (*value == ':' || *value == '<') is_safe_string = false; for (;;) { char ch = *value++; if (ch == 0 || ch == '\n') break; else if (ch == '\r') continue; else if (ch == ' ') { space_flag = true; continue; } else { if ((ch & 0x80) == 0x80) { is_safe_string = false; } if (space_flag) { *p++ = ' '; space_flag = false; } *p++ = ch; } } *p = 0; if (is_safe_string) { printf("%s: %s\n", attr, &buffer[0]); } else { p = pst_base64_encode(&buffer[0], buffer.size()); printf("%s:: %s\n", attr, p); free(p); } } // Combines values representing address lines into an address,i // lines separated with "$" as per PostalAddress syntax in RFC4517 void print_ldif_address(const char *attr, int nvalues, pst_string value, ...) { DEBUG_ENT("print_ldif_address"); bool space_flag = false; bool newline_flag = false; char *address = NULL; // Buffer where address is built up int len = 0; // Length of buffer int i = 0; // Index of next character position in buffer va_list ap; va_start(ap, value); while (!value.str) { nvalues--; if (nvalues == 0) { // Nothing at all to do! va_end(ap); DEBUG_RET(); return; } value = va_arg(ap, pst_string); } for (;;) { char ch = *(value.str)++; if (ch == 0) { do { nvalues--; if (nvalues == 0) break; value = va_arg(ap, pst_string); } while (!value.str); if (!nvalues || !value.str) break; space_flag = true; newline_flag = true; } else if (ch == '\r') continue; else if (ch == '\n') { newline_flag = true; continue; } else if (ch == ' ') { space_flag = true; continue; } else { if (i > (len-5)) { len += 256; char *addr = (char *)realloc(address, len); // cppcheck found unchecked error if (!addr) exit(3); address = addr; } if (newline_flag) { address[i++] = '$'; newline_flag = false; space_flag = false; } else if (space_flag) { address[i++] = ' '; space_flag = false; } if (ch == '$' || ch == '\\') address[i++] = '\\'; address[i++] = ch; } } va_end(ap); if (i == 0) return; // Nothing to do address[i] = 0; print_ldif_single(attr, address); free(address); DEBUG_RET(); } void print_ldif_multi(const char *dn, pst_string value) { char *n; char *valuestr = value.str; while ((n = strchr(valuestr, '\n'))) { print_ldif_single(dn, valuestr); valuestr = n + 1; } print_ldif_single(dn, valuestr); } void print_ldif_two(const char *attr, pst_string value1, pst_string value2) { size_t len1, len2; if (value1.str && *value1.str) len1 = strlen(value1.str); else { print_ldif_single(attr, value2); return; } if (value2.str && *value2.str) len2 = strlen(value2.str); else { print_ldif_single(attr, value1); return; } vector value(len1 + len2 + 2); memcpy(&value[0], value1.str, len1); value[len1] = ' '; memcpy(&value[0] + len1 + 1, value2.str, len2 + 1); print_ldif_single(attr, &value[0]); } void build_cn(char *cn, size_t len, int nvalues, pst_string value, ...) { bool space_flag = false; size_t i = 0; va_list ap; va_start(ap, value); while (!value.str) { nvalues--; if (nvalues == 0) { cn[0] = 0; // Just a terminating NUL va_end(ap); return; } value = va_arg(ap, pst_string); } for (;;) { char ch = *(value.str)++; if (ch == 0 || ch == '\n') { do { nvalues--; if (nvalues == 0) break; value = va_arg(ap, pst_string); } while (!value.str); if (!nvalues || !value.str) break; space_flag = true; } else if (ch == '\r') continue; else if (ch == ' ') { space_flag = true; continue; } else { if (space_flag) { if (i > 0) { if (i < (len - 2)) cn[i++] = ' '; else break; } space_flag = false; } if (i < (len - 1)) cn[i++] = ch; else break; } } cn[i] = 0; va_end(ap); } int main(int argc, char* const* argv) { pst_desc_tree *d_ptr; char *fname = NULL; int c; char *d_log = NULL; prog_name = argv[0]; pst_item *item = NULL; while ((c = getopt(argc, argv, "b:c:d:l:oVh"))!= -1) { switch (c) { case 'b': ldap_base = optarg; break; case 'c': ldap_class.push_back(string(optarg)); break; case 'd': d_log = optarg; break; case 'h': usage(); exit(0); break; case 'l': ldif_extra_line.push_back(string(optarg)); break; case 'o': old_schema = true; break; case 'V': version(); exit(0); break; default: usage(); exit(1); break; } } if ((argc > optind) && (ldap_base)) { fname = argv[optind]; } else { usage(); exit(2); } #ifdef DEBUG_ALL // force a log file if (!d_log) d_log = "pst2ldif.log"; #endif DEBUG_INIT(d_log, NULL); DEBUG_ENT("main"); RET_DERROR(pst_open(&pstfile, fname, NULL), 1, ("Error opening File\n")); RET_DERROR(pst_load_index(&pstfile), 2, ("Index Error\n")); pst_load_extended_attributes(&pstfile); d_ptr = pstfile.d_head; // first record is main record item = (pst_item*)pst_parse_item(&pstfile, d_ptr, NULL); if (!item || !item->message_store) { DEBUG_RET(); DIE(("main: Could not get root record\n")); } d_ptr = pst_getTopOfFolders(&pstfile, item); if (!d_ptr) { DEBUG_RET(); DIE(("Top of folders record not found. Cannot continue\n")); } pst_freeItem(item); if (old_schema && (strlen(ldap_base) > 2)) { char *ldap_org = strdup(ldap_base+2); // assume first 2 chars are o= char *temp = strchr(ldap_org, ','); if (temp) { *temp = '\0'; // write the ldap header printf("dn: %s\n", ldap_base); printf("o: %s\n", ldap_org); printf("objectClass: organization\n\n"); printf("dn: cn=root, %s\n", ldap_base); printf("cn: root\n"); printf("sn: root\n"); for (vector::size_type i=0; ichild); // do the children of TOPF pst_close(&pstfile); DEBUG_RET(); free_strings(all_strings); return 0; } void usage(void) { version(); printf("Usage: %s [OPTIONS] {PST FILENAME}\n", prog_name); printf("OPTIONS:\n"); printf("\t-V\t- Version. Display program version\n"); printf("\t-b ldapbase\t- set the LDAP base value\n"); printf("\t-c class\t- set the class of the LDAP objects (may contain more than one)\n"); printf("\t-d \t- Debug to file.\n"); printf("\t-h\t- Help. This screen\n"); printf("\t-l line\t- extra line to insert in the LDIF file for each contact\n"); printf("\t-o\t- use old schema, default is new schema\n"); } void version(void) { printf("pst2ldif 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 } char *check_filename(char *fname) { char *t = fname; if (t == NULL) { return fname; } while ((t = strpbrk(t, "/\\:"))) { // while there are characters in the second string that we don't want *t = '_'; //replace them with an underscore } return fname; } // This function escapes Distinguished Names (as per RFC4514) void print_ldif_dn(const char *attr, pst_string value, const char *base) { printf("dn: cn="); const char *valuestr = value.str; // remove leading spaces (RFC says escape them) while (*valuestr == ' ') valuestr++; print_escaped_dn(valuestr); if (base && base[0]) { printf(", %s", base); } printf("\n"); return; } void print_escaped_dn(const char *value) { char ch; // escape initial '#' and space if (*value == '#' || *value == ' ') putchar('\\'); while ((ch = *value++) != 0) { if (((ch & 0x80) != 0) || (ch <= 0x1F)) // Print as escaped hex digits printf("\\%2.2X", ch & 0xFF); else switch (ch) { case '\\': case '"' : case '+' : case ',' : case ';' : case '<' : case '>' : putchar('\\'); // Fall through default: putchar(ch); } } return; }