From 8a55952204ba29f0cab49b38cea79661d9d10cb8 Mon Sep 17 00:00:00 2001 From: Thomas Keller Date: Thu, 28 Oct 2010 19:45:45 +0200 Subject: [PATCH 01/13] * use the built-in push_hook_functions to register the netsync hooks, this way additional hooks which need these notifications as well do not override earlier hooks * optionally include an additional hooks.lua file at the very end in which custom hooks can be defined --- .../Plugin/SyncMonotone/monotonerc-auth.tpl | 53 ++++++++++-------- .../Plugin/SyncMonotone/monotonerc-noauth.tpl | 55 +++++++++++-------- 2 files changed, 62 insertions(+), 46 deletions(-) diff --git a/src/IDF/Plugin/SyncMonotone/monotonerc-auth.tpl b/src/IDF/Plugin/SyncMonotone/monotonerc-auth.tpl index daf3307..7e5ff8c 100644 --- a/src/IDF/Plugin/SyncMonotone/monotonerc-auth.tpl +++ b/src/IDF/Plugin/SyncMonotone/monotonerc-auth.tpl @@ -34,30 +34,37 @@ end -- let IDF know of new arriving revisions to fill its timeline -- _idf_revs = {} -function note_netsync_start(session_id) - _idf_revs[session_id] = {} -end +push_hook_functions({ + ["start"] = function (session_id) + _idf_revs[session_id] = {} + return "continue",nil + end, + ["revision_received"] = function (new_id, revision, certs, session_id) + table.insert(_idf_revs[session_id], new_id) + return "continue",nil + end, + ["end"] = function (session_id, ...) + if table.getn(_idf_revs[session_id]) == 0 then + return "continue",nil + end -function note_netsync_revision_received(new_id, revision, certs, session_id) - table.insert(_idf_revs[session_id], new_id) -end + local pin,pout,pid = spawn_pipe("%%MTNPOSTPUSH%%", "%%PROJECT%%"); + if pid == -1 then + print("could not execute %%MTNPOSTPUSH%%") + return + end -function note_netsync_end (session_id, ...) - if table.getn(_idf_revs[session_id]) == 0 then - return + for _,r in ipairs(_idf_revs[session_id]) do + pin:write(r .. "\n") + end + pin:close() + + wait(pid) + return "continue",nil end +}) - local pin,pout,pid = spawn_pipe("%%MTNPOSTPUSH%%", "%%PROJECT%%"); - if pid == -1 then - print("could execute %%MTNPOSTPUSH%%") - return - end - - for _,r in ipairs(_idf_revs[session_id]) do - pin:write(r .. "\n") - end - pin:close() - - wait(pid) -end - +-- +-- Load additional local hooks, in case they exist +-- +include(get_confdir() .. "/hooks.lua") diff --git a/src/IDF/Plugin/SyncMonotone/monotonerc-noauth.tpl b/src/IDF/Plugin/SyncMonotone/monotonerc-noauth.tpl index c0c0050..e59aa04 100644 --- a/src/IDF/Plugin/SyncMonotone/monotonerc-noauth.tpl +++ b/src/IDF/Plugin/SyncMonotone/monotonerc-noauth.tpl @@ -31,7 +31,8 @@ function get_remote_automate_permitted(key_identity, command, options) "leaves", "ancestry_difference", "toposort", "erase_ancestors", "descendents", "ancestors", "heads", "get_file_of", "get_file", "interface_version", "get_attributes", "content_diff", - "file_merge", "show_conflicts", "certs", "keys" + "file_merge", "show_conflicts", "certs", "keys", "get_file_size", + "get_extended_manifest_of" } for _,v in ipairs(read_only_commands) do @@ -47,29 +48,37 @@ end -- let IDF know of new arriving revisions to fill its timeline -- _idf_revs = {} -function note_netsync_start(session_id) - _idf_revs[session_id] = {} -end +push_hook_functions({ + ["start"] = function (session_id) + _idf_revs[session_id] = {} + return "continue",nil + end, + ["revision_received"] = function (new_id, revision, certs, session_id) + table.insert(_idf_revs[session_id], new_id) + return "continue",nil + end, + ["end"] = function (session_id, ...) + if table.getn(_idf_revs[session_id]) == 0 then + return "continue",nil + end -function note_netsync_revision_received(new_id, revision, certs, session_id) - table.insert(_idf_revs[session_id], new_id) -end + local pin,pout,pid = spawn_pipe("%%MTNPOSTPUSH%%", "%%PROJECT%%"); + if pid == -1 then + print("could not execute %%MTNPOSTPUSH%%") + return + end -function note_netsync_end (session_id, ...) - if table.getn(_idf_revs[session_id]) == 0 then - return + for _,r in ipairs(_idf_revs[session_id]) do + pin:write(r .. "\n") + end + pin:close() + + wait(pid) + return "continue",nil end +}) - local pin,pout,pid = spawn_pipe("%%MTNPOSTPUSH%%", "%%PROJECT%%"); - if pid == -1 then - print("could execute %%MTNPOSTPUSH%%") - return - end - - for _,r in ipairs(_idf_revs[session_id]) do - pin:write(r .. "\n") - end - pin:close() - - wait(pid) -end +-- +-- Load additional local hooks, in case they exist +-- +include(get_confdir() .. "/hooks.lua") From b800ffcc1fdfd21b12cca090353d833de0c77da0 Mon Sep 17 00:00:00 2001 From: Thomas Keller Date: Thu, 28 Oct 2010 20:05:42 +0200 Subject: [PATCH 02/13] * add a section which explains the security concept and explains the possible remote command execution feature * add a section which explains how additional hooks can be configured for notification purposes --- doc/syncmonotone.mdtext | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/doc/syncmonotone.mdtext b/doc/syncmonotone.mdtext index 89c1350..7ca1d11 100644 --- a/doc/syncmonotone.mdtext +++ b/doc/syncmonotone.mdtext @@ -173,3 +173,33 @@ For even more advanced setups, usher can also be used to forward sync requests to other remote servers for load balancing, please consult the README file for more information. +## Security and remote access + +Indefero distinguishs between public and private projects and so does +the monotone plugin. + +Public projects can be pulled by everybody and pushed by team members +or additional invited people. Remote command execution is enabled, but +only for read-only commands. + +Remote commands can be helpful for a user or a 3rd party tool (like +[mtn-browse](http://mtn-browse.sourceforge.net) or +[guitone](http://guitone.thomaskeller.biz)) to browse the database +contents remotely without having to pull everything in first instance. + +Private projects on the other hand can only be synced by team members +or additional invited people. Also noo remote command execution is enabled +by default. + +## Notifications + +If you have successfully set up your monotone instance, you probably want +to notify 3rd party systems for incoming changes or simply mirror them +somewhere else for backup purposes. The monotone source tree already comes +with [many example scripts and hooks](http://code.monotone.ca/p/monotone/source/tree/h:net.venge.monotone/contrib) +which serve these purposes, after only little additional configuration. + +The usher/indefero-controlled setup automatically looks for a file called +`hooks.lua` in the project's base directory (configured via $cfg['mtn_repositories']) +and this is the ideal place to put or link these additional lua sources. + From fe001abd26ed59360b44e08d12605d35f141d8a0 Mon Sep 17 00:00:00 2001 From: Thomas Keller Date: Sat, 30 Oct 2010 21:52:40 +0000 Subject: [PATCH 03/13] Rework the way IDF's SCM interface provides downloadable snapshots. Instead of returning a command which gets executed and which should pass through / stream its output data to the client, we're just returning an instance of Pluf_HTTP_Response. This is needed, because some SCMs, most noticable monotone, have no locally executable command to provide a snapshot archive (and probably never will for our kind of setup). We therefor added a little BSD-licensed class "ZipArchive" which allows the creation of pkzip-compatible archives on the fly by letting it eat the file contents directly feed from the (remote) stdio instance. Download performance is ok and lies between 15K/s and 110K/s, but at least we do no longer block the browser while we pre-generate the zip file server-side. Thanks to Patrick Georgi for all his work! --- contrib/zipstream-php-0.2.2/COPYING | 20 + contrib/zipstream-php-0.2.2/README | 42 + contrib/zipstream-php-0.2.2/extras/README | 2 + .../extras/zip-appnote-6.3.1-20070411.txt | 3071 +++++++++++++++++ contrib/zipstream-php-0.2.2/test/index.php | 52 + contrib/zipstream-php-0.2.2/zipstream.php | 580 ++++ src/IDF/Scm.php | 6 +- src/IDF/Scm/Git.php | 7 +- src/IDF/Scm/Mercurial.php | 9 +- src/IDF/Scm/Monotone.php | 18 +- src/IDF/Scm/Monotone/ZipRender.php | 78 + src/IDF/Views/Source.php | 3 +- src/IDF/templates/idf/source/mtn/tree.html | 2 +- 13 files changed, 3875 insertions(+), 15 deletions(-) create mode 100644 contrib/zipstream-php-0.2.2/COPYING create mode 100644 contrib/zipstream-php-0.2.2/README create mode 100644 contrib/zipstream-php-0.2.2/extras/README create mode 100644 contrib/zipstream-php-0.2.2/extras/zip-appnote-6.3.1-20070411.txt create mode 100644 contrib/zipstream-php-0.2.2/test/index.php create mode 100644 contrib/zipstream-php-0.2.2/zipstream.php create mode 100644 src/IDF/Scm/Monotone/ZipRender.php diff --git a/contrib/zipstream-php-0.2.2/COPYING b/contrib/zipstream-php-0.2.2/COPYING new file mode 100644 index 0000000..7cf062d --- /dev/null +++ b/contrib/zipstream-php-0.2.2/COPYING @@ -0,0 +1,20 @@ +Copyright (C) 2007-2009 Paul Duncan + +Permission is hereby granted, free of charge, to any person obtaining a +copy of this software and associated documentation files (the +"Software"), to deal in the Software without restriction, including +without limitation the rights to use, copy, modify, merge, publish, +distribute, sublicense, and/or sell copies of the Software, and to +permit persons to whom the Software is furnished to do so, subject to +the following conditions: + +The above copyright notice and this permission notice shall be included +in all copies or substantial portions of the of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS +OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. +IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER +DEALINGS IN THE SOFTWARE. diff --git a/contrib/zipstream-php-0.2.2/README b/contrib/zipstream-php-0.2.2/README new file mode 100644 index 0000000..25eb42e --- /dev/null +++ b/contrib/zipstream-php-0.2.2/README @@ -0,0 +1,42 @@ +ZipStream 0.2.2 README +====================== + +Please see the file COPYING for licensing and warranty information. The +latest version of this software is available at the following URL: + + http://pablotron.org/software/zipstream-php/ + +Overview +======== +A fast and simple streaming zip file downloader for PHP. Here's a +simple example: + + # create a new zipstream object + $zip = new ZipStream('example.zip'); + + # create a file named 'hello.txt' + $zip->add_file('some_image.jpg', 'This is the contents of hello.txt'); + + # add a file named 'image.jpg' from a local file 'path/to/image.jpg' + $zip->add_file_from_path('some_image.jpg', 'path/to/image.jpg'); + + # finish the zip stream + $zip->finish(); + +You can also add comments, modify file timestamps, and customize (or +disable) the HTTP headers. See the class file for details. There are a +couple of additional examples in the initial release announcement at the +following URL: + + http://pablotron.org/?cid=1535 + +Requirements +============ + + * PHP version 5.1.2 or newer (specifically, the hash_init and + hash_file functions). + +About the Author +================ +Paul Duncan +http://pablotron.org/ diff --git a/contrib/zipstream-php-0.2.2/extras/README b/contrib/zipstream-php-0.2.2/extras/README new file mode 100644 index 0000000..e642704 --- /dev/null +++ b/contrib/zipstream-php-0.2.2/extras/README @@ -0,0 +1,2 @@ +Based on PKZIP appnotes, which are included here. + diff --git a/contrib/zipstream-php-0.2.2/extras/zip-appnote-6.3.1-20070411.txt b/contrib/zipstream-php-0.2.2/extras/zip-appnote-6.3.1-20070411.txt new file mode 100644 index 0000000..97fd591 --- /dev/null +++ b/contrib/zipstream-php-0.2.2/extras/zip-appnote-6.3.1-20070411.txt @@ -0,0 +1,3071 @@ +source: http://www.pkware.com/documents/casestudies/APPNOTE.TXT + +File: APPNOTE.TXT - .ZIP File Format Specification +Version: 6.3.1 +Revised: April 11, 2007 +Copyright (c) 1989 - 2007 PKWARE Inc., All Rights Reserved. + +The use of certain technological aspects disclosed in the current +APPNOTE is available pursuant to the below section entitled +"Incorporating PKWARE Proprietary Technology into Your Product". + +I. Purpose +---------- + +This specification is intended to define a cross-platform, +interoperable file storage and transfer format. Since its +first publication in 1989, PKWARE has remained committed to +ensuring the interoperability of the .ZIP file format through +publication and maintenance of this specification. We trust that +all .ZIP compatible vendors and application developers that have +adopted and benefited from this format will share and support +this commitment to interoperability. + +II. Contacting PKWARE +--------------------- + + PKWARE, Inc. + 648 N. Plankinton Avenue, Suite 220 + Milwaukee, WI 53203 + +1-414-289-9788 + +1-414-289-9789 FAX + zipformat@pkware.com + +III. Disclaimer +--------------- + +Although PKWARE will attempt to supply current and accurate +information relating to its file formats, algorithms, and the +subject programs, the possibility of error or omission cannot +be eliminated. PKWARE therefore expressly disclaims any warranty +that the information contained in the associated materials relating +to the subject programs and/or the format of the files created or +accessed by the subject programs and/or the algorithms used by +the subject programs, or any other matter, is current, correct or +accurate as delivered. Any risk of damage due to any possible +inaccurate information is assumed by the user of the information. +Furthermore, the information relating to the subject programs +and/or the file formats created or accessed by the subject +programs and/or the algorithms used by the subject programs is +subject to change without notice. + +If the version of this file is marked as a NOTIFICATION OF CHANGE, +the content defines an Early Feature Specification (EFS) change +to the .ZIP file format that may be subject to modification prior +to publication of the Final Feature Specification (FFS). This +document may also contain information on Planned Feature +Specifications (PFS) defining recognized future extensions. + +IV. Change Log +-------------- + +Version Change Description Date +------- ------------------ ---------- +5.2 -Single Password Symmetric Encryption 06/02/2003 + storage + +6.1.0 -Smartcard compatibility 01/20/2004 + -Documentation on certificate storage + +6.2.0 -Introduction of Central Directory 04/26/2004 + Encryption for encrypting metadata + -Added OS/X to Version Made By values + +6.2.1 -Added Extra Field placeholder for 04/01/2005 + POSZIP using ID 0x4690 + + -Clarified size field on + "zip64 end of central directory record" + +6.2.2 -Documented Final Feature Specification 01/06/2006 + for Strong Encryption + + -Clarifications and typographical + corrections + +6.3.0 -Added tape positioning storage 09/29/2006 + parameters + + -Expanded list of supported hash algorithms + + -Expanded list of supported compression + algorithms + + -Expanded list of supported encryption + algorithms + + -Added option for Unicode filename + storage + + -Clarifications for consistent use + of Data Descriptor records + + -Added additional "Extra Field" + definitions + +6.3.1 -Corrected standard hash values for 04/11/2007 + SHA-256/384/512 + + +V. General Format of a .ZIP file +-------------------------------- + + Files stored in arbitrary order. Large .ZIP files can span multiple + volumes or be split into user-defined segment sizes. All values + are stored in little-endian byte order unless otherwise specified. + + Overall .ZIP file format: + + [local file header 1] + [file data 1] + [data descriptor 1] + . + . + . + [local file header n] + [file data n] + [data descriptor n] + [archive decryption header] + [archive extra data record] + [central directory] + [zip64 end of central directory record] + [zip64 end of central directory locator] + [end of central directory record] + + + A. Local file header: + + local file header signature 4 bytes (0x04034b50) + version needed to extract 2 bytes + general purpose bit flag 2 bytes + compression method 2 bytes + last mod file time 2 bytes + last mod file date 2 bytes + crc-32 4 bytes + compressed size 4 bytes + uncompressed size 4 bytes + file name length 2 bytes + extra field length 2 bytes + + file name (variable size) + extra field (variable size) + + B. File data + + Immediately following the local header for a file + is the compressed or stored data for the file. + The series of [local file header][file data][data + descriptor] repeats for each file in the .ZIP archive. + + C. Data descriptor: + + crc-32 4 bytes + compressed size 4 bytes + uncompressed size 4 bytes + + This descriptor exists only if bit 3 of the general + purpose bit flag is set (see below). It is byte aligned + and immediately follows the last byte of compressed data. + This descriptor is used only when it was not possible to + seek in the output .ZIP file, e.g., when the output .ZIP file + was standard output or a non-seekable device. For ZIP64(tm) format + archives, the compressed and uncompressed sizes are 8 bytes each. + + When compressing files, compressed and uncompressed sizes + should be stored in ZIP64 format (as 8 byte values) when a + files size exceeds 0xFFFFFFFF. However ZIP64 format may be + used regardless of the size of a file. When extracting, if + the zip64 extended information extra field is present for + the file the compressed and uncompressed sizes will be 8 + byte values. + + Although not originally assigned a signature, the value + 0x08074b50 has commonly been adopted as a signature value + for the data descriptor record. Implementers should be + aware that ZIP files may be encountered with or without this + signature marking data descriptors and should account for + either case when reading ZIP files to ensure compatibility. + When writing ZIP files, it is recommended to include the + signature value marking the data descriptor record. When + the signature is used, the fields currently defined for + the data descriptor record will immediately follow the + signature. + + An extensible data descriptor will be released in a future + version of this APPNOTE. This new record is intended to + resolve conflicts with the use of this record going forward, + and to provide better support for streamed file processing. + + When the Central Directory Encryption method is used, the data + descriptor record is not required, but may be used. If present, + and bit 3 of the general purpose bit field is set to indicate + its presence, the values in fields of the data descriptor + record should be set to binary zeros. + + D. Archive decryption header: + + The Archive Decryption Header is introduced in version 6.2 + of the ZIP format specification. This record exists in support + of the Central Directory Encryption Feature implemented as part of + the Strong Encryption Specification as described in this document. + When the Central Directory Structure is encrypted, this decryption + header will precede the encrypted data segment. The encrypted + data segment will consist of the Archive extra data record (if + present) and the encrypted Central Directory Structure data. + The format of this data record is identical to the Decryption + header record preceding compressed file data. If the central + directory structure is encrypted, the location of the start of + this data record is determined using the Start of Central Directory + field in the Zip64 End of Central Directory record. Refer to the + section on the Strong Encryption Specification for information + on the fields used in the Archive Decryption Header record. + + + E. Archive extra data record: + + archive extra data signature 4 bytes (0x08064b50) + extra field length 4 bytes + extra field data (variable size) + + The Archive Extra Data Record is introduced in version 6.2 + of the ZIP format specification. This record exists in support + of the Central Directory Encryption Feature implemented as part of + the Strong Encryption Specification as described in this document. + When present, this record immediately precedes the central + directory data structure. The size of this data record will be + included in the Size of the Central Directory field in the + End of Central Directory record. If the central directory structure + is compressed, but not encrypted, the location of the start of + this data record is determined using the Start of Central Directory + field in the Zip64 End of Central Directory record. + + + F. Central directory structure: + + [file header 1] + . + . + . + [file header n] + [digital signature] + + File header: + + central file header signature 4 bytes (0x02014b50) + version made by 2 bytes + version needed to extract 2 bytes + general purpose bit flag 2 bytes + compression method 2 bytes + last mod file time 2 bytes + last mod file date 2 bytes + crc-32 4 bytes + compressed size 4 bytes + uncompressed size 4 bytes + file name length 2 bytes + extra field length 2 bytes + file comment length 2 bytes + disk number start 2 bytes + internal file attributes 2 bytes + external file attributes 4 bytes + relative offset of local header 4 bytes + + file name (variable size) + extra field (variable size) + file comment (variable size) + + Digital signature: + + header signature 4 bytes (0x05054b50) + size of data 2 bytes + signature data (variable size) + + With the introduction of the Central Directory Encryption + feature in version 6.2 of this specification, the Central + Directory Structure may be stored both compressed and encrypted. + Although not required, it is assumed when encrypting the + Central Directory Structure, that it will be compressed + for greater storage efficiency. Information on the + Central Directory Encryption feature can be found in the section + describing the Strong Encryption Specification. The Digital + Signature record will be neither compressed nor encrypted. + + G. Zip64 end of central directory record + + zip64 end of central dir + signature 4 bytes (0x06064b50) + size of zip64 end of central + directory record 8 bytes + version made by 2 bytes + version needed to extract 2 bytes + number of this disk 4 bytes + number of the disk with the + start of the central directory 4 bytes + total number of entries in the + central directory on this disk 8 bytes + total number of entries in the + central directory 8 bytes + size of the central directory 8 bytes + offset of start of central + directory with respect to + the starting disk number 8 bytes + zip64 extensible data sector (variable size) + + The value stored into the "size of zip64 end of central + directory record" should be the size of the remaining + record and should not include the leading 12 bytes. + + Size = SizeOfFixedFields + SizeOfVariableData - 12. + + The above record structure defines Version 1 of the + zip64 end of central directory record. Version 1 was + implemented in versions of this specification preceding + 6.2 in support of the ZIP64 large file feature. The + introduction of the Central Directory Encryption feature + implemented in version 6.2 as part of the Strong Encryption + Specification defines Version 2 of this record structure. + Refer to the section describing the Strong Encryption + Specification for details on the version 2 format for + this record. + + Special purpose data may reside in the zip64 extensible data + sector field following either a V1 or V2 version of this + record. To ensure identification of this special purpose data + it must include an identifying header block consisting of the + following: + + Header ID - 2 bytes + Data Size - 4 bytes + + The Header ID field indicates the type of data that is in the + data block that follows. + + Data Size identifies the number of bytes that follow for this + data block type. + + Multiple special purpose data blocks may be present, but each + must be preceded by a Header ID and Data Size field. Current + mappings of Header ID values supported in this field are as + defined in APPENDIX C. + + H. Zip64 end of central directory locator + + zip64 end of central dir locator + signature 4 bytes (0x07064b50) + number of the disk with the + start of the zip64 end of + central directory 4 bytes + relative offset of the zip64 + end of central directory record 8 bytes + total number of disks 4 bytes + + I. End of central directory record: + + end of central dir signature 4 bytes (0x06054b50) + number of this disk 2 bytes + number of the disk with the + start of the central directory 2 bytes + total number of entries in the + central directory on this disk 2 bytes + total number of entries in + the central directory 2 bytes + size of the central directory 4 bytes + offset of start of central + directory with respect to + the starting disk number 4 bytes + .ZIP file comment length 2 bytes + .ZIP file comment (variable size) + + J. Explanation of fields: + + version made by (2 bytes) + + The upper byte indicates the compatibility of the file + attribute information. If the external file attributes + are compatible with MS-DOS and can be read by PKZIP for + DOS version 2.04g then this value will be zero. If these + attributes are not compatible, then this value will + identify the host system on which the attributes are + compatible. Software can use this information to determine + the line record format for text files etc. The current + mappings are: + + 0 - MS-DOS and OS/2 (FAT / VFAT / FAT32 file systems) + 1 - Amiga 2 - OpenVMS + 3 - UNIX 4 - VM/CMS + 5 - Atari ST 6 - OS/2 H.P.F.S. + 7 - Macintosh 8 - Z-System + 9 - CP/M 10 - Windows NTFS + 11 - MVS (OS/390 - Z/OS) 12 - VSE + 13 - Acorn Risc 14 - VFAT + 15 - alternate MVS 16 - BeOS + 17 - Tandem 18 - OS/400 + 19 - OS/X (Darwin) 20 thru 255 - unused + + The lower byte indicates the ZIP specification version + (the version of this document) supported by the software + used to encode the file. The value/10 indicates the major + version number, and the value mod 10 is the minor version + number. + + version needed to extract (2 bytes) + + The minimum supported ZIP specification version needed to + extract the file, mapped as above. This value is based on + the specific format features a ZIP program must support to + be able to extract the file. If multiple features are + applied to a file, the minimum version should be set to the + feature having the highest value. New features or feature + changes affecting the published format specification will be + implemented using higher version numbers than the last + published value to avoid conflict. + + Current minimum feature versions are as defined below: + + 1.0 - Default value + 1.1 - File is a volume label + 2.0 - File is a folder (directory) + 2.0 - File is compressed using Deflate compression + 2.0 - File is encrypted using traditional PKWARE encryption + 2.1 - File is compressed using Deflate64(tm) + 2.5 - File is compressed using PKWARE DCL Implode + 2.7 - File is a patch data set + 4.5 - File uses ZIP64 format extensions + 4.6 - File is compressed using BZIP2 compression* + 5.0 - File is encrypted using DES + 5.0 - File is encrypted using 3DES + 5.0 - File is encrypted using original RC2 encryption + 5.0 - File is encrypted using RC4 encryption + 5.1 - File is encrypted using AES encryption + 5.1 - File is encrypted using corrected RC2 encryption** + 5.2 - File is encrypted using corrected RC2-64 encryption** + 6.1 - File is encrypted using non-OAEP key wrapping*** + 6.2 - Central directory encryption + 6.3 - File is compressed using LZMA + 6.3 - File is compressed using PPMd+ + 6.3 - File is encrypted using Blowfish + 6.3 - File is encrypted using Twofish + + + * Early 7.x (pre-7.2) versions of PKZIP incorrectly set the + version needed to extract for BZIP2 compression to be 50 + when it should have been 46. + + ** Refer to the section on Strong Encryption Specification + for additional information regarding RC2 corrections. + + *** Certificate encryption using non-OAEP key wrapping is the + intended mode of operation for all versions beginning with 6.1. + Support for OAEP key wrapping should only be used for + backward compatibility when sending ZIP files to be opened by + versions of PKZIP older than 6.1 (5.0 or 6.0). + + + Files compressed using PPMd should set the version + needed to extract field to 6.3, however, not all ZIP + programs enforce this and may be unable to decompress + data files compressed using PPMd if this value is set. + + When using ZIP64 extensions, the corresponding value in the + zip64 end of central directory record should also be set. + This field should be set appropriately to indicate whether + Version 1 or Version 2 format is in use. + + general purpose bit flag: (2 bytes) + + Bit 0: If set, indicates that the file is encrypted. + + (For Method 6 - Imploding) + Bit 1: If the compression method used was type 6, + Imploding, then this bit, if set, indicates + an 8K sliding dictionary was used. If clear, + then a 4K sliding dictionary was used. + Bit 2: If the compression method used was type 6, + Imploding, then this bit, if set, indicates + 3 Shannon-Fano trees were used to encode the + sliding dictionary output. If clear, then 2 + Shannon-Fano trees were used. + + (For Methods 8 and 9 - Deflating) + Bit 2 Bit 1 + 0 0 Normal (-en) compression option was used. + 0 1 Maximum (-exx/-ex) compression option was used. + 1 0 Fast (-ef) compression option was used. + 1 1 Super Fast (-es) compression option was used. + + (For Method 14 - LZMA) + Bit 1: If the compression method used was type 14, + LZMA, then this bit, if set, indicates + an end-of-stream (EOS) marker is used to + mark the end of the compressed data stream. + If clear, then an EOS marker is not present + and the compressed data size must be known + to extract. + + Note: Bits 1 and 2 are undefined if the compression + method is any other. + + Bit 3: If this bit is set, the fields crc-32, compressed + size and uncompressed size are set to zero in the + local header. The correct values are put in the + data descriptor immediately following the compressed + data. (Note: PKZIP version 2.04g for DOS only + recognizes this bit for method 8 compression, newer + versions of PKZIP recognize this bit for any + compression method.) + + Bit 4: Reserved for use with method 8, for enhanced + deflating. + + Bit 5: If this bit is set, this indicates that the file is + compressed patched data. (Note: Requires PKZIP + version 2.70 or greater) + + Bit 6: Strong encryption. If this bit is set, you should + set the version needed to extract value to at least + 50 and you must also set bit 0. If AES encryption + is used, the version needed to extract value must + be at least 51. + + Bit 7: Currently unused. + + Bit 8: Currently unused. + + Bit 9: Currently unused. + + Bit 10: Currently unused. + + Bit 11: Language encoding flag (EFS). If this bit is set, + the filename and comment fields for this file + must be encoded using UTF-8. (see APPENDIX D) + + Bit 12: Reserved by PKWARE for enhanced compression. + + Bit 13: Used when encrypting the Central Directory to indicate + selected data values in the Local Header are masked to + hide their actual values. See the section describing + the Strong Encryption Specification for details. + + Bit 14: Reserved by PKWARE. + + Bit 15: Reserved by PKWARE. + + compression method: (2 bytes) + + (see accompanying documentation for algorithm + descriptions) + + 0 - The file is stored (no compression) + 1 - The file is Shrunk + 2 - The file is Reduced with compression factor 1 + 3 - The file is Reduced with compression factor 2 + 4 - The file is Reduced with compression factor 3 + 5 - The file is Reduced with compression factor 4 + 6 - The file is Imploded + 7 - Reserved for Tokenizing compression algorithm + 8 - The file is Deflated + 9 - Enhanced Deflating using Deflate64(tm) + 10 - PKWARE Data Compression Library Imploding (old IBM TERSE) + 11 - Reserved by PKWARE + 12 - File is compressed using BZIP2 algorithm + 13 - Reserved by PKWARE + 14 - LZMA (EFS) + 15 - Reserved by PKWARE + 16 - Reserved by PKWARE + 17 - Reserved by PKWARE + 18 - File is compressed using IBM TERSE (new) + 19 - IBM LZ77 z Architecture (PFS) + 98 - PPMd version I, Rev 1 + + date and time fields: (2 bytes each) + + The date and time are encoded in standard MS-DOS format. + If input came from standard input, the date and time are + those at which compression was started for this data. + If encrypting the central directory and general purpose bit + flag 13 is set indicating masking, the value stored in the + Local Header will be zero. + + CRC-32: (4 bytes) + + The CRC-32 algorithm was generously contributed by + David Schwaderer and can be found in his excellent + book "C Programmers Guide to NetBIOS" published by + Howard W. Sams & Co. Inc. The 'magic number' for + the CRC is 0xdebb20e3. The proper CRC pre and post + conditioning is used, meaning that the CRC register + is pre-conditioned with all ones (a starting value + of 0xffffffff) and the value is post-conditioned by + taking the one's complement of the CRC residual. + If bit 3 of the general purpose flag is set, this + field is set to zero in the local header and the correct + value is put in the data descriptor and in the central + directory. When encrypting the central directory, if the + local header is not in ZIP64 format and general purpose + bit flag 13 is set indicating masking, the value stored + in the Local Header will be zero. + + compressed size: (4 bytes) + uncompressed size: (4 bytes) + + The size of the file compressed and uncompressed, + respectively. When a decryption header is present it will + be placed in front of the file data and the value of the + compressed file size will include the bytes of the decryption + header. If bit 3 of the general purpose bit flag is set, + these fields are set to zero in the local header and the + correct values are put in the data descriptor and + in the central directory. If an archive is in ZIP64 format + and the value in this field is 0xFFFFFFFF, the size will be + in the corresponding 8 byte ZIP64 extended information + extra field. When encrypting the central directory, if the + local header is not in ZIP64 format and general purpose bit + flag 13 is set indicating masking, the value stored for the + uncompressed size in the Local Header will be zero. + + file name length: (2 bytes) + extra field length: (2 bytes) + file comment length: (2 bytes) + + The length of the file name, extra field, and comment + fields respectively. The combined length of any + directory record and these three fields should not + generally exceed 65,535 bytes. If input came from standard + input, the file name length is set to zero. + + disk number start: (2 bytes) + + The number of the disk on which this file begins. If an + archive is in ZIP64 format and the value in this field is + 0xFFFF, the size will be in the corresponding 4 byte zip64 + extended information extra field. + + internal file attributes: (2 bytes) + + Bits 1 and 2 are reserved for use by PKWARE. + + The lowest bit of this field indicates, if set, that + the file is apparently an ASCII or text file. If not + set, that the file apparently contains binary data. + The remaining bits are unused in version 1.0. + + The 0x0002 bit of this field indicates, if set, that a + 4 byte variable record length control field precedes each + logical record indicating the length of the record. The + record length control field is stored in little-endian byte + order. This flag is independent of text control characters, + and if used in conjunction with text data, includes any + control characters in the total length of the record. This + value is provided for mainframe data transfer support. + + external file attributes: (4 bytes) + + The mapping of the external attributes is + host-system dependent (see 'version made by'). For + MS-DOS, the low order byte is the MS-DOS directory + attribute byte. If input came from standard input, this + field is set to zero. + + relative offset of local header: (4 bytes) + + This is the offset from the start of the first disk on + which this file appears, to where the local header should + be found. If an archive is in ZIP64 format and the value + in this field is 0xFFFFFFFF, the size will be in the + corresponding 8 byte zip64 extended information extra field. + + file name: (Variable) + + The name of the file, with optional relative path. + The path stored should not contain a drive or + device letter, or a leading slash. All slashes + should be forward slashes '/' as opposed to + backwards slashes '\' for compatibility with Amiga + and UNIX file systems etc. If input came from standard + input, there is no file name field. If encrypting + the central directory and general purpose bit flag 13 is set + indicating masking, the file name stored in the Local Header + will not be the actual file name. A masking value consisting + of a unique hexadecimal value will be stored. This value will + be sequentially incremented for each file in the archive. See + the section on the Strong Encryption Specification for details + on retrieving the encrypted file name. + + extra field: (Variable) + + This is for expansion. If additional information + needs to be stored for special needs or for specific + platforms, it should be stored here. Earlier versions + of the software can then safely skip this file, and + find the next file or header. This field will be 0 + length in version 1.0. + + In order to allow different programs and different types + of information to be stored in the 'extra' field in .ZIP + files, the following structure should be used for all + programs storing data in this field: + + header1+data1 + header2+data2 . . . + + Each header should consist of: + + Header ID - 2 bytes + Data Size - 2 bytes + + Note: all fields stored in Intel low-byte/high-byte order. + + The Header ID field indicates the type of data that is in + the following data block. + + Header ID's of 0 thru 31 are reserved for use by PKWARE. + The remaining ID's can be used by third party vendors for + proprietary usage. + + The current Header ID mappings defined by PKWARE are: + + 0x0001 Zip64 extended information extra field + 0x0007 AV Info + 0x0008 Reserved for extended language encoding data (PFS) + (see APPENDIX D) + 0x0009 OS/2 + 0x000a NTFS + 0x000c OpenVMS + 0x000d UNIX + 0x000e Reserved for file stream and fork descriptors + 0x000f Patch Descriptor + 0x0014 PKCS#7 Store for X.509 Certificates + 0x0015 X.509 Certificate ID and Signature for + individual file + 0x0016 X.509 Certificate ID for Central Directory + 0x0017 Strong Encryption Header + 0x0018 Record Management Controls + 0x0019 PKCS#7 Encryption Recipient Certificate List + 0x0065 IBM S/390 (Z390), AS/400 (I400) attributes + - uncompressed + 0x0066 Reserved for IBM S/390 (Z390), AS/400 (I400) + attributes - compressed + 0x4690 POSZIP 4690 (reserved) + + Third party mappings commonly used are: + + + 0x07c8 Macintosh + 0x2605 ZipIt Macintosh + 0x2705 ZipIt Macintosh 1.3.5+ + 0x2805 ZipIt Macintosh 1.3.5+ + 0x334d Info-ZIP Macintosh + 0x4341 Acorn/SparkFS + 0x4453 Windows NT security descriptor (binary ACL) + 0x4704 VM/CMS + 0x470f MVS + 0x4b46 FWKCS MD5 (see below) + 0x4c41 OS/2 access control list (text ACL) + 0x4d49 Info-ZIP OpenVMS + 0x4f4c Xceed original location extra field + 0x5356 AOS/VS (ACL) + 0x5455 extended timestamp + 0x554e Xceed unicode extra field + 0x5855 Info-ZIP UNIX (original, also OS/2, NT, etc) + 0x6542 BeOS/BeBox + 0x756e ASi UNIX + 0x7855 Info-ZIP UNIX (new) + 0xa220 Microsoft Open Packaging Growth Hint + 0xfd4a SMS/QDOS + + Detailed descriptions of Extra Fields defined by third + party mappings will be documented as information on + these data structures is made available to PKWARE. + PKWARE does not guarantee the accuracy of any published + third party data. + + The Data Size field indicates the size of the following + data block. Programs can use this value to skip to the + next header block, passing over any data blocks that are + not of interest. + + Note: As stated above, the size of the entire .ZIP file + header, including the file name, comment, and extra + field should not exceed 64K in size. + + In case two different programs should appropriate the same + Header ID value, it is strongly recommended that each + program place a unique signature of at least two bytes in + size (and preferably 4 bytes or bigger) at the start of + each data area. Every program should verify that its + unique signature is present, in addition to the Header ID + value being correct, before assuming that it is a block of + known type. + + -Zip64 Extended Information Extra Field (0x0001): + + The following is the layout of the zip64 extended + information "extra" block. If one of the size or + offset fields in the Local or Central directory + record is too small to hold the required data, + a Zip64 extended information record is created. + The order of the fields in the zip64 extended + information record is fixed, but the fields will + only appear if the corresponding Local or Central + directory record field is set to 0xFFFF or 0xFFFFFFFF. + + Note: all fields stored in Intel low-byte/high-byte order. + + Value Size Description + ----- ---- ----------- + (ZIP64) 0x0001 2 bytes Tag for this "extra" block type + Size 2 bytes Size of this "extra" block + Original + Size 8 bytes Original uncompressed file size + Compressed + Size 8 bytes Size of compressed data + Relative Header + Offset 8 bytes Offset of local header record + Disk Start + Number 4 bytes Number of the disk on which + this file starts + + This entry in the Local header must include BOTH original + and compressed file size fields. If encrypting the + central directory and bit 13 of the general purpose bit + flag is set indicating masking, the value stored in the + Local Header for the original file size will be zero. + + + -OS/2 Extra Field (0x0009): + + The following is the layout of the OS/2 attributes "extra" + block. (Last Revision 09/05/95) + + Note: all fields stored in Intel low-byte/high-byte order. + + Value Size Description + ----- ---- ----------- + (OS/2) 0x0009 2 bytes Tag for this "extra" block type + TSize 2 bytes Size for the following data block + BSize 4 bytes Uncompressed Block Size + CType 2 bytes Compression type + EACRC 4 bytes CRC value for uncompress block + (var) variable Compressed block + + The OS/2 extended attribute structure (FEA2LIST) is + compressed and then stored in it's entirety within this + structure. There will only ever be one "block" of data in + VarFields[]. + + -NTFS Extra Field (0x000a): + + The following is the layout of the NTFS attributes + "extra" block. (Note: At this time the Mtime, Atime + and Ctime values may be used on any WIN32 system.) + + Note: all fields stored in Intel low-byte/high-byte order. + + Value Size Description + ----- ---- ----------- + (NTFS) 0x000a 2 bytes Tag for this "extra" block type + TSize 2 bytes Size of the total "extra" block + Reserved 4 bytes Reserved for future use + Tag1 2 bytes NTFS attribute tag value #1 + Size1 2 bytes Size of attribute #1, in bytes + (var.) Size1 Attribute #1 data + . + . + . + TagN 2 bytes NTFS attribute tag value #N + SizeN 2 bytes Size of attribute #N, in bytes + (var.) SizeN Attribute #N data + + For NTFS, values for Tag1 through TagN are as follows: + (currently only one set of attributes is defined for NTFS) + + Tag Size Description + ----- ---- ----------- + 0x0001 2 bytes Tag for attribute #1 + Size1 2 bytes Size of attribute #1, in bytes + Mtime 8 bytes File last modification time + Atime 8 bytes File last access time + Ctime 8 bytes File creation time + + -OpenVMS Extra Field (0x000c): + + The following is the layout of the OpenVMS attributes + "extra" block. + + Note: all fields stored in Intel low-byte/high-byte order. + + Value Size Description + ----- ---- ----------- + (VMS) 0x000c 2 bytes Tag for this "extra" block type + TSize 2 bytes Size of the total "extra" block + CRC 4 bytes 32-bit CRC for remainder of the block + Tag1 2 bytes OpenVMS attribute tag value #1 + Size1 2 bytes Size of attribute #1, in bytes + (var.) Size1 Attribute #1 data + . + . + . + TagN 2 bytes OpenVMS attribute tag value #N + SizeN 2 bytes Size of attribute #N, in bytes + (var.) SizeN Attribute #N data + + Rules: + + 1. There will be one or more of attributes present, which + will each be preceded by the above TagX & SizeX values. + These values are identical to the ATR$C_XXXX and + ATR$S_XXXX constants which are defined in ATR.H under + OpenVMS C. Neither of these values will ever be zero. + + 2. No word alignment or padding is performed. + + 3. A well-behaved PKZIP/OpenVMS program should never produce + more than one sub-block with the same TagX value. Also, + there will never be more than one "extra" block of type + 0x000c in a particular directory record. + + -UNIX Extra Field (0x000d): + + The following is the layout of the UNIX "extra" block. + Note: all fields are stored in Intel low-byte/high-byte + order. + + Value Size Description + ----- ---- ----------- + (UNIX) 0x000d 2 bytes Tag for this "extra" block type + TSize 2 bytes Size for the following data block + Atime 4 bytes File last access time + Mtime 4 bytes File last modification time + Uid 2 bytes File user ID + Gid 2 bytes File group ID + (var) variable Variable length data field + + The variable length data field will contain file type + specific data. Currently the only values allowed are + the original "linked to" file names for hard or symbolic + links, and the major and minor device node numbers for + character and block device nodes. Since device nodes + cannot be either symbolic or hard links, only one set of + variable length data is stored. Link files will have the + name of the original file stored. This name is NOT NULL + terminated. Its size can be determined by checking TSize - + 12. Device entries will have eight bytes stored as two 4 + byte entries (in little endian format). The first entry + will be the major device number, and the second the minor + device number. + + -PATCH Descriptor Extra Field (0x000f): + + The following is the layout of the Patch Descriptor "extra" + block. + + Note: all fields stored in Intel low-byte/high-byte order. + + Value Size Description + ----- ---- ----------- + (Patch) 0x000f 2 bytes Tag for this "extra" block type + TSize 2 bytes Size of the total "extra" block + Version 2 bytes Version of the descriptor + Flags 4 bytes Actions and reactions (see below) + OldSize 4 bytes Size of the file about to be patched + OldCRC 4 bytes 32-bit CRC of the file to be patched + NewSize 4 bytes Size of the resulting file + NewCRC 4 bytes 32-bit CRC of the resulting file + + Actions and reactions + + Bits Description + ---- ---------------- + 0 Use for auto detection + 1 Treat as a self-patch + 2-3 RESERVED + 4-5 Action (see below) + 6-7 RESERVED + 8-9 Reaction (see below) to absent file + 10-11 Reaction (see below) to newer file + 12-13 Reaction (see below) to unknown file + 14-15 RESERVED + 16-31 RESERVED + + Actions + + Action Value + ------ ----- + none 0 + add 1 + delete 2 + patch 3 + + Reactions + + Reaction Value + -------- ----- + ask 0 + skip 1 + ignore 2 + fail 3 + + Patch support is provided by PKPatchMaker(tm) technology and is + covered under U.S. Patents and Patents Pending. The use or + implementation in a product of certain technological aspects set + forth in the current APPNOTE, including those with regard to + strong encryption, patching, or extended tape operations requires + a license from PKWARE. Please contact PKWARE with regard to + acquiring a license. + + -PKCS#7 Store for X.509 Certificates (0x0014): + + This field contains information about each of the certificates + files may be signed with. When the Central Directory Encryption + feature is enabled for a ZIP file, this record will appear in + the Archive Extra Data Record, otherwise it will appear in the + first central directory record and will be ignored in any + other record. + + Note: all fields stored in Intel low-byte/high-byte order. + + Value Size Description + ----- ---- ----------- + (Store) 0x0014 2 bytes Tag for this "extra" block type + TSize 2 bytes Size of the store data + TData TSize Data about the store + + + -X.509 Certificate ID and Signature for individual file (0x0015): + + This field contains the information about which certificate in + the PKCS#7 store was used to sign a particular file. It also + contains the signature data. This field can appear multiple + times, but can only appear once per certificate. + + Note: all fields stored in Intel low-byte/high-byte order. + + Value Size Description + ----- ---- ----------- + (CID) 0x0015 2 bytes Tag for this "extra" block type + TSize 2 bytes Size of data that follows + TData TSize Signature Data + + -X.509 Certificate ID and Signature for central directory (0x0016): + + This field contains the information about which certificate in + the PKCS#7 store was used to sign the central directory structure. + When the Central Directory Encryption feature is enabled for a + ZIP file, this record will appear in the Archive Extra Data Record, + otherwise it will appear in the first central directory record. + + Note: all fields stored in Intel low-byte/high-byte order. + + Value Size Description + ----- ---- ----------- + (CDID) 0x0016 2 bytes Tag for this "extra" block type + TSize 2 bytes Size of data that follows + TData TSize Data + + -Strong Encryption Header (0x0017): + + Value Size Description + ----- ---- ----------- + 0x0017 2 bytes Tag for this "extra" block type + TSize 2 bytes Size of data that follows + Format 2 bytes Format definition for this record + AlgID 2 bytes Encryption algorithm identifier + Bitlen 2 bytes Bit length of encryption key + Flags 2 bytes Processing flags + CertData TSize-8 Certificate decryption extra field data + (refer to the explanation for CertData + in the section describing the + Certificate Processing Method under + the Strong Encryption Specification) + + + -Record Management Controls (0x0018): + + Value Size Description + ----- ---- ----------- +(Rec-CTL) 0x0018 2 bytes Tag for this "extra" block type + CSize 2 bytes Size of total extra block data + Tag1 2 bytes Record control attribute 1 + Size1 2 bytes Size of attribute 1, in bytes + Data1 Size1 Attribute 1 data + . + . + . + TagN 2 bytes Record control attribute N + SizeN 2 bytes Size of attribute N, in bytes + DataN SizeN Attribute N data + + + -PKCS#7 Encryption Recipient Certificate List (0x0019): + + This field contains information about each of the certificates + used in encryption processing and it can be used to identify who is + allowed to decrypt encrypted files. This field should only appear + in the archive extra data record. This field is not required and + serves only to aide archive modifications by preserving public + encryption key data. Individual security requirements may dictate + that this data be omitted to deter information exposure. + + Note: all fields stored in Intel low-byte/high-byte order. + + Value Size Description + ----- ---- ----------- + (CStore) 0x0019 2 bytes Tag for this "extra" block type + TSize 2 bytes Size of the store data + TData TSize Data about the store + + TData: + + Value Size Description + ----- ---- ----------- + Version 2 bytes Format version number - must 0x0001 at this time + CStore (var) PKCS#7 data blob + + + -MVS Extra Field (0x0065): + + The following is the layout of the MVS "extra" block. + Note: Some fields are stored in Big Endian format. + All text is in EBCDIC format unless otherwise specified. + + Value Size Description + ----- ---- ----------- + (MVS) 0x0065 2 bytes Tag for this "extra" block type + TSize 2 bytes Size for the following data block + ID 4 bytes EBCDIC "Z390" 0xE9F3F9F0 or + "T4MV" for TargetFour + (var) TSize-4 Attribute data (see APPENDIX B) + + + -OS/400 Extra Field (0x0065): + + The following is the layout of the OS/400 "extra" block. + Note: Some fields are stored in Big Endian format. + All text is in EBCDIC format unless otherwise specified. + + Value Size Description + ----- ---- ----------- + (OS400) 0x0065 2 bytes Tag for this "extra" block type + TSize 2 bytes Size for the following data block + ID 4 bytes EBCDIC "I400" 0xC9F4F0F0 or + "T4MV" for TargetFour + (var) TSize-4 Attribute data (see APPENDIX A) + + + Third-party Mappings: + + -ZipIt Macintosh Extra Field (long) (0x2605): + + The following is the layout of the ZipIt extra block + for Macintosh. The local-header and central-header versions + are identical. This block must be present if the file is + stored MacBinary-encoded and it should not be used if the file + is not stored MacBinary-encoded. + + Value Size Description + ----- ---- ----------- + (Mac2) 0x2605 Short tag for this extra block type + TSize Short total data size for this block + "ZPIT" beLong extra-field signature + FnLen Byte length of FileName + FileName variable full Macintosh filename + FileType Byte[4] four-byte Mac file type string + Creator Byte[4] four-byte Mac creator string + + + -ZipIt Macintosh Extra Field (short, for files) (0x2705): + + The following is the layout of a shortened variant of the + ZipIt extra block for Macintosh (without "full name" entry). + This variant is used by ZipIt 1.3.5 and newer for entries of + files (not directories) that do not have a MacBinary encoded + file. The local-header and central-header versions are identical. + + Value Size Description + ----- ---- ----------- + (Mac2b) 0x2705 Short tag for this extra block type + TSize Short total data size for this block (12) + "ZPIT" beLong extra-field signature + FileType Byte[4] four-byte Mac file type string + Creator Byte[4] four-byte Mac creator string + fdFlags beShort attributes from FInfo.frFlags, + may be omitted + 0x0000 beShort reserved, may be omitted + + + -ZipIt Macintosh Extra Field (short, for directories) (0x2805): + + The following is the layout of a shortened variant of the + ZipIt extra block for Macintosh used only for directory + entries. This variant is used by ZipIt 1.3.5 and newer to + save some optional Mac-specific information about directories. + The local-header and central-header versions are identical. + + Value Size Description + ----- ---- ----------- + (Mac2c) 0x2805 Short tag for this extra block type + TSize Short total data size for this block (12) + "ZPIT" beLong extra-field signature + frFlags beShort attributes from DInfo.frFlags, may + be omitted + View beShort ZipIt view flag, may be omitted + + + The View field specifies ZipIt-internal settings as follows: + + Bits of the Flags: + bit 0 if set, the folder is shown expanded (open) + when the archive contents are viewed in ZipIt. + bits 1-15 reserved, zero; + + + -FWKCS MD5 Extra Field (0x4b46): + + The FWKCS Contents_Signature System, used in + automatically identifying files independent of file name, + optionally adds and uses an extra field to support the + rapid creation of an enhanced contents_signature: + + Header ID = 0x4b46 + Data Size = 0x0013 + Preface = 'M','D','5' + followed by 16 bytes containing the uncompressed file's + 128_bit MD5 hash(1), low byte first. + + When FWKCS revises a .ZIP file central directory to add + this extra field for a file, it also replaces the + central directory entry for that file's uncompressed + file length with a measured value. + + FWKCS provides an option to strip this extra field, if + present, from a .ZIP file central directory. In adding + this extra field, FWKCS preserves .ZIP file Authenticity + Verification; if stripping this extra field, FWKCS + preserves all versions of AV through PKZIP version 2.04g. + + FWKCS, and FWKCS Contents_Signature System, are + trademarks of Frederick W. Kantor. + + (1) R. Rivest, RFC1321.TXT, MIT Laboratory for Computer + Science and RSA Data Security, Inc., April 1992. + ll.76-77: "The MD5 algorithm is being placed in the + public domain for review and possible adoption as a + standard." + + -Microsoft Open Packaging Growth Hint (0xa220): + + Value Size Description + ----- ---- ----------- + 0xa220 Short tag for this extra block type + TSize Short size of Sig + PadVal + Padding + Sig Short verification signature (A028) + PadVal Short Initial padding value + Padding variable filled with NULL characters + + + file comment: (Variable) + + The comment for this file. + + number of this disk: (2 bytes) + + The number of this disk, which contains central + directory end record. If an archive is in ZIP64 format + and the value in this field is 0xFFFF, the size will + be in the corresponding 4 byte zip64 end of central + directory field. + + + number of the disk with the start of the central + directory: (2 bytes) + + The number of the disk on which the central + directory starts. If an archive is in ZIP64 format + and the value in this field is 0xFFFF, the size will + be in the corresponding 4 byte zip64 end of central + directory field. + + total number of entries in the central dir on + this disk: (2 bytes) + + The number of central directory entries on this disk. + If an archive is in ZIP64 format and the value in + this field is 0xFFFF, the size will be in the + corresponding 8 byte zip64 end of central + directory field. + + total number of entries in the central dir: (2 bytes) + + The total number of files in the .ZIP file. If an + archive is in ZIP64 format and the value in this field + is 0xFFFF, the size will be in the corresponding 8 byte + zip64 end of central directory field. + + size of the central directory: (4 bytes) + + The size (in bytes) of the entire central directory. + If an archive is in ZIP64 format and the value in + this field is 0xFFFFFFFF, the size will be in the + corresponding 8 byte zip64 end of central + directory field. + + offset of start of central directory with respect to + the starting disk number: (4 bytes) + + Offset of the start of the central directory on the + disk on which the central directory starts. If an + archive is in ZIP64 format and the value in this + field is 0xFFFFFFFF, the size will be in the + corresponding 8 byte zip64 end of central + directory field. + + .ZIP file comment length: (2 bytes) + + The length of the comment for this .ZIP file. + + .ZIP file comment: (Variable) + + The comment for this .ZIP file. ZIP file comment data + is stored unsecured. No encryption or data authentication + is applied to this area at this time. Confidential information + should not be stored in this section. + + zip64 extensible data sector (variable size) + + (currently reserved for use by PKWARE) + + + K. Splitting and Spanning ZIP files + + Spanning is the process of segmenting a ZIP file across + multiple removable media. This support has typically only + been provided for DOS formatted floppy diskettes. + + File splitting is a newer derivative of spanning. + Splitting follows the same segmentation process as + spanning, however, it does not require writing each + segment to a unique removable medium and instead supports + placing all pieces onto local or non-removable locations + such as file systems, local drives, folders, etc... + + A key difference between spanned and split ZIP files is + that all pieces of a spanned ZIP file have the same name. + Since each piece is written to a separate volume, no name + collisions occur and each segment can reuse the original + .ZIP file name given to the archive. + + Sequence ordering for DOS spanned archives uses the DOS + volume label to determine segment numbers. Volume labels + for each segment are written using the form PKBACK#xxx, + where xxx is the segment number written as a decimal + value from 001 - nnn. + + Split ZIP files are typically written to the same location + and are subject to name collisions if the spanned name + format is used since each segment will reside on the same + drive. To avoid name collisions, split archives are named + as follows. + + Segment 1 = filename.z01 + Segment n-1 = filename.z(n-1) + Segment n = filename.zip + + The .ZIP extension is used on the last segment to support + quickly reading the central directory. The segment number + n should be a decimal value. + + Spanned ZIP files may be PKSFX Self-extracting ZIP files. + PKSFX files may also be split, however, in this case + the first segment must be named filename.exe. The first + segment of a split PKSFX archive must be large enough to + include the entire executable program. + + Capacities for split archives are as follows. + + Maximum number of segments = 4,294,967,295 - 1 + Maximum .ZIP segment size = 4,294,967,295 bytes + Minimum segment size = 64K + Maximum PKSFX segment size = 2,147,483,647 bytes + + Segment sizes may be different however by convention, all + segment sizes should be the same with the exception of the + last, which may be smaller. Local and central directory + header records must never be split across a segment boundary. + When writing a header record, if the number of bytes remaining + within a segment is less than the size of the header record, + end the current segment and write the header at the start + of the next segment. The central directory may span segment + boundaries, but no single record in the central directory + should be split across segments. + + Spanned/Split archives created using PKZIP for Windows + (V2.50 or greater), PKZIP Command Line (V2.50 or greater), + or PKZIP Explorer will include a special spanning + signature as the first 4 bytes of the first segment of + the archive. This signature (0x08074b50) will be + followed immediately by the local header signature for + the first file in the archive. + + A special spanning marker may also appear in spanned/split + archives if the spanning or splitting process starts but + only requires one segment. In this case the 0x08074b50 + signature will be replaced with the temporary spanning + marker signature of 0x30304b50. Split archives can + only be uncompressed by other versions of PKZIP that + know how to create a split archive. + + The signature value 0x08074b50 is also used by some + ZIP implementations as a marker for the Data Descriptor + record. Conflict in this alternate assignment can be + avoided by ensuring the position of the signature + within the ZIP file to determine the use for which it + is intended. + + L. General notes: + + 1) All fields unless otherwise noted are unsigned and stored + in Intel low-byte:high-byte, low-word:high-word order. + + 2) String fields are not null terminated, since the + length is given explicitly. + + 3) The entries in the central directory may not necessarily + be in the same order that files appear in the .ZIP file. + + 4) If one of the fields in the end of central directory + record is too small to hold required data, the field + should be set to -1 (0xFFFF or 0xFFFFFFFF) and the + ZIP64 format record should be created. + + 5) The end of central directory record and the + Zip64 end of central directory locator record must + reside on the same disk when splitting or spanning + an archive. + +VI. UnShrinking - Method 1 +-------------------------- + +Shrinking is a Dynamic Ziv-Lempel-Welch compression algorithm +with partial clearing. The initial code size is 9 bits, and +the maximum code size is 13 bits. Shrinking differs from +conventional Dynamic Ziv-Lempel-Welch implementations in several +respects: + +1) The code size is controlled by the compressor, and is not + automatically increased when codes larger than the current + code size are created (but not necessarily used). When + the decompressor encounters the code sequence 256 + (decimal) followed by 1, it should increase the code size + read from the input stream to the next bit size. No + blocking of the codes is performed, so the next code at + the increased size should be read from the input stream + immediately after where the previous code at the smaller + bit size was read. Again, the decompressor should not + increase the code size used until the sequence 256,1 is + encountered. + +2) When the table becomes full, total clearing is not + performed. Rather, when the compressor emits the code + sequence 256,2 (decimal), the decompressor should clear + all leaf nodes from the Ziv-Lempel tree, and continue to + use the current code size. The nodes that are cleared + from the Ziv-Lempel tree are then re-used, with the lowest + code value re-used first, and the highest code value + re-used last. The compressor can emit the sequence 256,2 + at any time. + +VII. Expanding - Methods 2-5 +---------------------------- + +The Reducing algorithm is actually a combination of two +distinct algorithms. The first algorithm compresses repeated +byte sequences, and the second algorithm takes the compressed +stream from the first algorithm and applies a probabilistic +compression method. + +The probabilistic compression stores an array of 'follower +sets' S(j), for j=0 to 255, corresponding to each possible +ASCII character. Each set contains between 0 and 32 +characters, to be denoted as S(j)[0],...,S(j)[m], where m<32. +The sets are stored at the beginning of the data area for a +Reduced file, in reverse order, with S(255) first, and S(0) +last. + +The sets are encoded as { N(j), S(j)[0],...,S(j)[N(j)-1] }, +where N(j) is the size of set S(j). N(j) can be 0, in which +case the follower set for S(j) is empty. Each N(j) value is +encoded in 6 bits, followed by N(j) eight bit character values +corresponding to S(j)[0] to S(j)[N(j)-1] respectively. If +N(j) is 0, then no values for S(j) are stored, and the value +for N(j-1) immediately follows. + +Immediately after the follower sets, is the compressed data +stream. The compressed data stream can be interpreted for the +probabilistic decompression as follows: + +let Last-Character <- 0. +loop until done + if the follower set S(Last-Character) is empty then + read 8 bits from the input stream, and copy this + value to the output stream. + otherwise if the follower set S(Last-Character) is non-empty then + read 1 bit from the input stream. + if this bit is not zero then + read 8 bits from the input stream, and copy this + value to the output stream. + otherwise if this bit is zero then + read B(N(Last-Character)) bits from the input + stream, and assign this value to I. + Copy the value of S(Last-Character)[I] to the + output stream. + + assign the last value placed on the output stream to + Last-Character. +end loop + +B(N(j)) is defined as the minimal number of bits required to +encode the value N(j)-1. + +The decompressed stream from above can then be expanded to +re-create the original file as follows: + +let State <- 0. + +loop until done + read 8 bits from the input stream into C. + case State of + 0: if C is not equal to DLE (144 decimal) then + copy C to the output stream. + otherwise if C is equal to DLE then + let State <- 1. + + 1: if C is non-zero then + let V <- C. + let Len <- L(V) + let State <- F(Len). + otherwise if C is zero then + copy the value 144 (decimal) to the output stream. + let State <- 0 + + 2: let Len <- Len + C + let State <- 3. + + 3: move backwards D(V,C) bytes in the output stream + (if this position is before the start of the output + stream, then assume that all the data before the + start of the output stream is filled with zeros). + copy Len+3 bytes from this position to the output stream. + let State <- 0. + end case +end loop + +The functions F,L, and D are dependent on the 'compression +factor', 1 through 4, and are defined as follows: + +For compression factor 1: + L(X) equals the lower 7 bits of X. + F(X) equals 2 if X equals 127 otherwise F(X) equals 3. + D(X,Y) equals the (upper 1 bit of X) * 256 + Y + 1. +For compression factor 2: + L(X) equals the lower 6 bits of X. + F(X) equals 2 if X equals 63 otherwise F(X) equals 3. + D(X,Y) equals the (upper 2 bits of X) * 256 + Y + 1. +For compression factor 3: + L(X) equals the lower 5 bits of X. + F(X) equals 2 if X equals 31 otherwise F(X) equals 3. + D(X,Y) equals the (upper 3 bits of X) * 256 + Y + 1. +For compression factor 4: + L(X) equals the lower 4 bits of X. + F(X) equals 2 if X equals 15 otherwise F(X) equals 3. + D(X,Y) equals the (upper 4 bits of X) * 256 + Y + 1. + +VIII. Imploding - Method 6 +-------------------------- + +The Imploding algorithm is actually a combination of two distinct +algorithms. The first algorithm compresses repeated byte +sequences using a sliding dictionary. The second algorithm is +used to compress the encoding of the sliding dictionary output, +using multiple Shannon-Fano trees. + +The Imploding algorithm can use a 4K or 8K sliding dictionary +size. The dictionary size used can be determined by bit 1 in the +general purpose flag word; a 0 bit indicates a 4K dictionary +while a 1 bit indicates an 8K dictionary. + +The Shannon-Fano trees are stored at the start of the compressed +file. The number of trees stored is defined by bit 2 in the +general purpose flag word; a 0 bit indicates two trees stored, a +1 bit indicates three trees are stored. If 3 trees are stored, +the first Shannon-Fano tree represents the encoding of the +Literal characters, the second tree represents the encoding of +the Length information, the third represents the encoding of the +Distance information. When 2 Shannon-Fano trees are stored, the +Length tree is stored first, followed by the Distance tree. + +The Literal Shannon-Fano tree, if present is used to represent +the entire ASCII character set, and contains 256 values. This +tree is used to compress any data not compressed by the sliding +dictionary algorithm. When this tree is present, the Minimum +Match Length for the sliding dictionary is 3. If this tree is +not present, the Minimum Match Length is 2. + +The Length Shannon-Fano tree is used to compress the Length part +of the (length,distance) pairs from the sliding dictionary +output. The Length tree contains 64 values, ranging from the +Minimum Match Length, to 63 plus the Minimum Match Length. + +The Distance Shannon-Fano tree is used to compress the Distance +part of the (length,distance) pairs from the sliding dictionary +output. The Distance tree contains 64 values, ranging from 0 to +63, representing the upper 6 bits of the distance value. The +distance values themselves will be between 0 and the sliding +dictionary size, either 4K or 8K. + +The Shannon-Fano trees themselves are stored in a compressed +format. The first byte of the tree data represents the number of +bytes of data representing the (compressed) Shannon-Fano tree +minus 1. The remaining bytes represent the Shannon-Fano tree +data encoded as: + + High 4 bits: Number of values at this bit length + 1. (1 - 16) + Low 4 bits: Bit Length needed to represent value + 1. (1 - 16) + +The Shannon-Fano codes can be constructed from the bit lengths +using the following algorithm: + +1) Sort the Bit Lengths in ascending order, while retaining the + order of the original lengths stored in the file. + +2) Generate the Shannon-Fano trees: + + Code <- 0 + CodeIncrement <- 0 + LastBitLength <- 0 + i <- number of Shannon-Fano codes - 1 (either 255 or 63) + + loop while i >= 0 + Code = Code + CodeIncrement + if BitLength(i) <> LastBitLength then + LastBitLength=BitLength(i) + CodeIncrement = 1 shifted left (16 - LastBitLength) + ShannonCode(i) = Code + i <- i - 1 + end loop + +3) Reverse the order of all the bits in the above ShannonCode() + vector, so that the most significant bit becomes the least + significant bit. For example, the value 0x1234 (hex) would + become 0x2C48 (hex). + +4) Restore the order of Shannon-Fano codes as originally stored + within the file. + +Example: + + This example will show the encoding of a Shannon-Fano tree + of size 8. Notice that the actual Shannon-Fano trees used + for Imploding are either 64 or 256 entries in size. + +Example: 0x02, 0x42, 0x01, 0x13 + + The first byte indicates 3 values in this table. Decoding the + bytes: + 0x42 = 5 codes of 3 bits long + 0x01 = 1 code of 2 bits long + 0x13 = 2 codes of 4 bits long + + This would generate the original bit length array of: + (3, 3, 3, 3, 3, 2, 4, 4) + + There are 8 codes in this table for the values 0 thru 7. Using + the algorithm to obtain the Shannon-Fano codes produces: + + Reversed Order Original +Val Sorted Constructed Code Value Restored Length +--- ------ ----------------- -------- -------- ------ +0: 2 1100000000000000 11 101 3 +1: 3 1010000000000000 101 001 3 +2: 3 1000000000000000 001 110 3 +3: 3 0110000000000000 110 010 3 +4: 3 0100000000000000 010 100 3 +5: 3 0010000000000000 100 11 2 +6: 4 0001000000000000 1000 1000 4 +7: 4 0000000000000000 0000 0000 4 + +The values in the Val, Order Restored and Original Length columns +now represent the Shannon-Fano encoding tree that can be used for +decoding the Shannon-Fano encoded data. How to parse the +variable length Shannon-Fano values from the data stream is beyond +the scope of this document. (See the references listed at the end of +this document for more information.) However, traditional decoding +schemes used for Huffman variable length decoding, such as the +Greenlaw algorithm, can be successfully applied. + +The compressed data stream begins immediately after the +compressed Shannon-Fano data. The compressed data stream can be +interpreted as follows: + +loop until done + read 1 bit from input stream. + + if this bit is non-zero then (encoded data is literal data) + if Literal Shannon-Fano tree is present + read and decode character using Literal Shannon-Fano tree. + otherwise + read 8 bits from input stream. + copy character to the output stream. + otherwise (encoded data is sliding dictionary match) + if 8K dictionary size + read 7 bits for offset Distance (lower 7 bits of offset). + otherwise + read 6 bits for offset Distance (lower 6 bits of offset). + + using the Distance Shannon-Fano tree, read and decode the + upper 6 bits of the Distance value. + + using the Length Shannon-Fano tree, read and decode + the Length value. + + Length <- Length + Minimum Match Length + + if Length = 63 + Minimum Match Length + read 8 bits from the input stream, + add this value to Length. + + move backwards Distance+1 bytes in the output stream, and + copy Length characters from this position to the output + stream. (if this position is before the start of the output + stream, then assume that all the data before the start of + the output stream is filled with zeros). +end loop + +IX. Tokenizing - Method 7 +------------------------- + +This method is not used by PKZIP. + +X. Deflating - Method 8 +----------------------- + +The Deflate algorithm is similar to the Implode algorithm using +a sliding dictionary of up to 32K with secondary compression +from Huffman/Shannon-Fano codes. + +The compressed data is stored in blocks with a header describing +the block and the Huffman codes used in the data block. The header +format is as follows: + + Bit 0: Last Block bit This bit is set to 1 if this is the last + compressed block in the data. + Bits 1-2: Block type + 00 (0) - Block is stored - All stored data is byte aligned. + Skip bits until next byte, then next word = block + length, followed by the ones compliment of the block + length word. Remaining data in block is the stored + data. + + 01 (1) - Use fixed Huffman codes for literal and distance codes. + Lit Code Bits Dist Code Bits + --------- ---- --------- ---- + 0 - 143 8 0 - 31 5 + 144 - 255 9 + 256 - 279 7 + 280 - 287 8 + + Literal codes 286-287 and distance codes 30-31 are + never used but participate in the huffman construction. + + 10 (2) - Dynamic Huffman codes. (See expanding Huffman codes) + + 11 (3) - Reserved - Flag a "Error in compressed data" if seen. + +Expanding Huffman Codes +----------------------- +If the data block is stored with dynamic Huffman codes, the Huffman +codes are sent in the following compressed format: + + 5 Bits: # of Literal codes sent - 256 (256 - 286) + All other codes are never sent. + 5 Bits: # of Dist codes - 1 (1 - 32) + 4 Bits: # of Bit Length codes - 3 (3 - 19) + +The Huffman codes are sent as bit lengths and the codes are built as +described in the implode algorithm. The bit lengths themselves are +compressed with Huffman codes. There are 19 bit length codes: + + 0 - 15: Represent bit lengths of 0 - 15 + 16: Copy the previous bit length 3 - 6 times. + The next 2 bits indicate repeat length (0 = 3, ... ,3 = 6) + Example: Codes 8, 16 (+2 bits 11), 16 (+2 bits 10) will + expand to 12 bit lengths of 8 (1 + 6 + 5) + 17: Repeat a bit length of 0 for 3 - 10 times. (3 bits of length) + 18: Repeat a bit length of 0 for 11 - 138 times (7 bits of length) + +The lengths of the bit length codes are sent packed 3 bits per value +(0 - 7) in the following order: + + 16, 17, 18, 0, 8, 7, 9, 6, 10, 5, 11, 4, 12, 3, 13, 2, 14, 1, 15 + +The Huffman codes should be built as described in the Implode algorithm +except codes are assigned starting at the shortest bit length, i.e. the +shortest code should be all 0's rather than all 1's. Also, codes with +a bit length of zero do not participate in the tree construction. The +codes are then used to decode the bit lengths for the literal and +distance tables. + +The bit lengths for the literal tables are sent first with the number +of entries sent described by the 5 bits sent earlier. There are up +to 286 literal characters; the first 256 represent the respective 8 +bit character, code 256 represents the End-Of-Block code, the remaining +29 codes represent copy lengths of 3 thru 258. There are up to 30 +distance codes representing distances from 1 thru 32k as described +below. + + Length Codes + ------------ + Extra Extra Extra Extra + Code Bits Length Code Bits Lengths Code Bits Lengths Code Bits Length(s) + ---- ---- ------ ---- ---- ------- ---- ---- ------- ---- ---- --------- + 257 0 3 265 1 11,12 273 3 35-42 281 5 131-162 + 258 0 4 266 1 13,14 274 3 43-50 282 5 163-194 + 259 0 5 267 1 15,16 275 3 51-58 283 5 195-226 + 260 0 6 268 1 17,18 276 3 59-66 284 5 227-257 + 261 0 7 269 2 19-22 277 4 67-82 285 0 258 + 262 0 8 270 2 23-26 278 4 83-98 + 263 0 9 271 2 27-30 279 4 99-114 + 264 0 10 272 2 31-34 280 4 115-130 + + Distance Codes + -------------- + Extra Extra Extra Extra + Code Bits Dist Code Bits Dist Code Bits Distance Code Bits Distance + ---- ---- ---- ---- ---- ------ ---- ---- -------- ---- ---- -------- + 0 0 1 8 3 17-24 16 7 257-384 24 11 4097-6144 + 1 0 2 9 3 25-32 17 7 385-512 25 11 6145-8192 + 2 0 3 10 4 33-48 18 8 513-768 26 12 8193-12288 + 3 0 4 11 4 49-64 19 8 769-1024 27 12 12289-16384 + 4 1 5,6 12 5 65-96 20 9 1025-1536 28 13 16385-24576 + 5 1 7,8 13 5 97-128 21 9 1537-2048 29 13 24577-32768 + 6 2 9-12 14 6 129-192 22 10 2049-3072 + 7 2 13-16 15 6 193-256 23 10 3073-4096 + +The compressed data stream begins immediately after the +compressed header data. The compressed data stream can be +interpreted as follows: + +do + read header from input stream. + + if stored block + skip bits until byte aligned + read count and 1's compliment of count + copy count bytes data block + otherwise + loop until end of block code sent + decode literal character from input stream + if literal < 256 + copy character to the output stream + otherwise + if literal = end of block + break from loop + otherwise + decode distance from input stream + + move backwards distance bytes in the output stream, and + copy length characters from this position to the output + stream. + end loop +while not last block + +if data descriptor exists + skip bits until byte aligned + read crc and sizes +endif + +XI. Enhanced Deflating - Method 9 +--------------------------------- + +The Enhanced Deflating algorithm is similar to Deflate but +uses a sliding dictionary of up to 64K. Deflate64(tm) is supported +by the Deflate extractor. + +XII. BZIP2 - Method 12 +---------------------- + +BZIP2 is an open-source data compression algorithm developed by +Julian Seward. Information and source code for this algorithm +can be found on the internet. + +XIII. LZMA - Method 14 (EFS) +---------------------------- + +LZMA is a block-oriented, general purpose data compression algorithm +developed and maintained by Igor Pavlov. It is a derivative of LZ77 +that utilizes Markov chains and a range coder. Information and +source code for this algorithm can be found on the internet. Consult +with the author of this algorithm for information on terms or +restrictions on use. + +Support for LZMA within the ZIP format is defined as follows: + +The Compression method field within the ZIP Local and Central +Header records will be set to the value 14 to indicate data was +compressed using LZMA. + +The Version needed to extract field within the ZIP Local and +Central Header records will be set to 6.3 to indicate the +minimum ZIP format version supporting this feature. + +File data compressed using the LZMA algorithm must be placed +immediately following the Local Header for the file. If a +standard ZIP encryption header is required, it will follow +the Local Header and will precede the LZMA compressed file +data segment. The location of LZMA compressed data segment +within the ZIP format will be as shown: + + [local header file 1] + [encryption header file 1] + [LZMA compressed data segment for file 1] + [data descriptor 1] + [local header file 2] + +The encryption header and data descriptor records may +be conditionally present. The LZMA Compressed Data Segment +will consist of an LZMA Properties Header followed by the +LZMA Compressed Data as shown: + + [LZMA properties header for file 1] + [LZMA compressed data for file 1] + +The LZMA Compressed Data will be stored as provided by the +LZMA compression library. Compressed size, uncompressed +size and other file characteristics about the file being +compressed must be stored in standard ZIP storage format. + +The LZMA Properties Header will store specific data required to +decompress the LZMA compressed Data. This data is set by the +LZMA compression engine using the function WriteCoderProperties() +as documented within the LZMA SDK. + +Storage fields for the property information within the LZMA +Properties Header are as follows: + + LZMA Version Information 2 bytes + LZMA Properties Size 2 bytes + LZMA Properties Data variable, defined by "LZMA Properties Size" + +LZMA Version Information - this field identifies which version of + the LZMA SDK was used to compress a file. The first byte will + store the major version number of the LZMA SDK and the second + byte will store the minor number. + +LZMA Properties Size - this field defines the size of the remaining + property data. Typically this size should be determined by the + version of the SDK. This size field is included as a convenience + and to help avoid any ambiguity should it arise in the future due + to changes in this compression algorithm. + +LZMA Property Data - this variable sized field records the required + values for the decompressor as defined by the LZMA SDK. The + data stored in this field should be obtained using the + WriteCoderProperties() in the version of the SDK defined by + the "LZMA Version Information" field. + +The layout of the "LZMA Properties Data" field is a function of the +LZMA compression algorithm. It is possible that this layout may be +changed by the author over time. The data layout in version 4.32 +of the LZMA SDK defines a 5 byte array that uses 4 bytes to store +the dictionary size in little-endian order. This is preceded by a +single packed byte as the first element of the array that contains +the following fields: + + PosStateBits + LiteralPosStateBits + LiteralContextBits + +Refer to the LZMA documentation for a more detailed explanation of +these fields. + +Data compressed with method 14, LZMA, may include an end-of-stream +(EOS) marker ending the compressed data stream. This marker is not +required, but its use is highly recommended to facilitate processing +and implementers should include the EOS marker whenever possible. +When the EOS marker is used, general purpose bit 1 must be set. If +general purpose bit 1 is not set, the EOS marker is not present. + +XIV. PPMd - Method 98 +--------------------- + +PPMd is a data compression algorithm developed by Dmitry Shkarin +which includes a carryless rangecoder developed by Dmitry Subbotin. +This algorithm is based on predictive phrase matching on multiple +order contexts. Information and source code for this algorithm +can be found on the internet. Consult with the author of this +algorithm for information on terms or restrictions on use. + +Support for PPMd within the ZIP format currently is provided only +for version I, revision 1 of the algorithm. Storage requirements +for using this algorithm are as follows: + +Parameters needed to control the algorithm are stored in the two +bytes immediately preceding the compressed data. These bytes are +used to store the following fields: + +Model order - sets the maximum model order, default is 8, possible + values are from 2 to 16 inclusive + +Sub-allocator size - sets the size of sub-allocator in MB, default is 50, + possible values are from 1MB to 256MB inclusive + +Model restoration method - sets the method used to restart context + model at memory insufficiency, values are: + + 0 - restarts model from scratch - default + 1 - cut off model - decreases performance by as much as 2x + 2 - freeze context tree - not recommended + +An example for packing these fields into the 2 byte storage field is +illustrated below. These values are stored in Intel low-byte/high-byte +order. + +wPPMd = (Model order - 1) + + ((Sub-allocator size - 1) << 4) + + (Model restoration method << 12) + + +XV. Traditional PKWARE Encryption +--------------------------------- + +The following information discusses the decryption steps +required to support traditional PKWARE encryption. This +form of encryption is considered weak by today's standards +and its use is recommended only for situations with +low security needs or for compatibility with older .ZIP +applications. + +Decryption +---------- + +PKWARE is grateful to Mr. Roger Schlafly for his expert contribution +towards the development of PKWARE's traditional encryption. + +PKZIP encrypts the compressed data stream. Encrypted files must +be decrypted before they can be extracted. + +Each encrypted file has an extra 12 bytes stored at the start of +the data area defining the encryption header for that file. The +encryption header is originally set to random values, and then +itself encrypted, using three, 32-bit keys. The key values are +initialized using the supplied encryption password. After each byte +is encrypted, the keys are then updated using pseudo-random number +generation techniques in combination with the same CRC-32 algorithm +used in PKZIP and described elsewhere in this document. + +The following is the basic steps required to decrypt a file: + +1) Initialize the three 32-bit keys with the password. +2) Read and decrypt the 12-byte encryption header, further + initializing the encryption keys. +3) Read and decrypt the compressed data stream using the + encryption keys. + +Step 1 - Initializing the encryption keys +----------------------------------------- + +Key(0) <- 305419896 +Key(1) <- 591751049 +Key(2) <- 878082192 + +loop for i <- 0 to length(password)-1 + update_keys(password(i)) +end loop + +Where update_keys() is defined as: + +update_keys(char): + Key(0) <- crc32(key(0),char) + Key(1) <- Key(1) + (Key(0) & 000000ffH) + Key(1) <- Key(1) * 134775813 + 1 + Key(2) <- crc32(key(2),key(1) >> 24) +end update_keys + +Where crc32(old_crc,char) is a routine that given a CRC value and a +character, returns an updated CRC value after applying the CRC-32 +algorithm described elsewhere in this document. + +Step 2 - Decrypting the encryption header +----------------------------------------- + +The purpose of this step is to further initialize the encryption +keys, based on random data, to render a plaintext attack on the +data ineffective. + +Read the 12-byte encryption header into Buffer, in locations +Buffer(0) thru Buffer(11). + +loop for i <- 0 to 11 + C <- buffer(i) ^ decrypt_byte() + update_keys(C) + buffer(i) <- C +end loop + +Where decrypt_byte() is defined as: + +unsigned char decrypt_byte() + local unsigned short temp + temp <- Key(2) | 2 + decrypt_byte <- (temp * (temp ^ 1)) >> 8 +end decrypt_byte + +After the header is decrypted, the last 1 or 2 bytes in Buffer +should be the high-order word/byte of the CRC for the file being +decrypted, stored in Intel low-byte/high-byte order. Versions of +PKZIP prior to 2.0 used a 2 byte CRC check; a 1 byte CRC check is +used on versions after 2.0. This can be used to test if the password +supplied is correct or not. + +Step 3 - Decrypting the compressed data stream +---------------------------------------------- + +The compressed data stream can be decrypted as follows: + +loop until done + read a character into C + Temp <- C ^ decrypt_byte() + update_keys(temp) + output Temp +end loop + + +XVI. Strong Encryption Specification +------------------------------------ + +The Strong Encryption technology defined in this specification is +covered under a pending patent application. The use or implementation +in a product of certain technological aspects set forth in the current +APPNOTE, including those with regard to strong encryption, patching, +or extended tape operations requires a license from PKWARE. Portions +of this Strong Encryption technology are available for use at no charge. +Contact PKWARE for licensing terms and conditions. Refer to section II +of this APPNOTE (Contacting PKWARE) for information on how to +contact PKWARE. + +Version 5.x of this specification introduced support for strong +encryption algorithms. These algorithms can be used with either +a password or an X.509v3 digital certificate to encrypt each file. +This format specification supports either password or certificate +based encryption to meet the security needs of today, to enable +interoperability between users within both PKI and non-PKI +environments, and to ensure interoperability between different +computing platforms that are running a ZIP program. + +Password based encryption is the most common form of encryption +people are familiar with. However, inherent weaknesses with +passwords (e.g. susceptibility to dictionary/brute force attack) +as well as password management and support issues make certificate +based encryption a more secure and scalable option. Industry +efforts and support are defining and moving towards more advanced +security solutions built around X.509v3 digital certificates and +Public Key Infrastructures(PKI) because of the greater scalability, +administrative options, and more robust security over traditional +password based encryption. + +Most standard encryption algorithms are supported with this +specification. Reference implementations for many of these +algorithms are available from either commercial or open source +distributors. Readily available cryptographic toolkits make +implementation of the encryption features straight-forward. +This document is not intended to provide a treatise on data +encryption principles or theory. Its purpose is to document the +data structures required for implementing interoperable data +encryption within the .ZIP format. It is strongly recommended that +you have a good understanding of data encryption before reading +further. + +The algorithms introduced in Version 5.0 of this specification +include: + + RC2 40 bit, 64 bit, and 128 bit + RC4 40 bit, 64 bit, and 128 bit + DES + 3DES 112 bit and 168 bit + +Version 5.1 adds support for the following: + + AES 128 bit, 192 bit, and 256 bit + + +Version 6.1 introduces encryption data changes to support +interoperability with Smartcard and USB Token certificate storage +methods which do not support the OAEP strengthening standard. + +Version 6.2 introduces support for encrypting metadata by compressing +and encrypting the central directory data structure to reduce information +leakage. Information leakage can occur in legacy ZIP applications +through exposure of information about a file even though that file is +stored encrypted. The information exposed consists of file +characteristics stored within the records and fields defined by this +specification. This includes data such as a files name, its original +size, timestamp and CRC32 value. + +Version 6.3 introduces support for encrypting data using the Blowfish +and Twofish algorithms. These are symmetric block ciphers developed +by Bruce Schneier. Blowfish supports using a variable length key from +32 to 448 bits. Block size is 64 bits. Implementations should use 16 +rounds and the only mode supported within ZIP files is CBC. Twofish +supports key sizes 128, 192 and 256 bits. Block size is 128 bits. +Implementations should use 16 rounds and the only mode supported within +ZIP files is CBC. Information and source code for both Blowfish and +Twofish algorithms can be found on the internet. Consult with the author +of these algorithms for information on terms or restrictions on use. + +Central Directory Encryption provides greater protection against +information leakage by encrypting the Central Directory structure and +by masking key values that are replicated in the unencrypted Local +Header. ZIP compatible programs that cannot interpret an encrypted +Central Directory structure cannot rely on the data in the corresponding +Local Header for decompression information. + +Extra Field records that may contain information about a file that should +not be exposed should not be stored in the Local Header and should only +be written to the Central Directory where they can be encrypted. This +design currently does not support streaming. Information in the End of +Central Directory record, the Zip64 End of Central Directory Locator, +and the Zip64 End of Central Directory records are not encrypted. Access +to view data on files within a ZIP file with an encrypted Central Directory +requires the appropriate password or private key for decryption prior to +viewing any files, or any information about the files, in the archive. + +Older ZIP compatible programs not familiar with the Central Directory +Encryption feature will no longer be able to recognize the Central +Directory and may assume the ZIP file is corrupt. Programs that +attempt streaming access using Local Headers will see invalid +information for each file. Central Directory Encryption need not be +used for every ZIP file. Its use is recommended for greater security. +ZIP files not using Central Directory Encryption should operate as +in the past. + +This strong encryption feature specification is intended to provide for +scalable, cross-platform encryption needs ranging from simple password +encryption to authenticated public/private key encryption. + +Encryption provides data confidentiality and privacy. It is +recommended that you combine X.509 digital signing with encryption +to add authentication and non-repudiation. + + +Single Password Symmetric Encryption Method: +------------------------------------------- + +The Single Password Symmetric Encryption Method using strong +encryption algorithms operates similarly to the traditional +PKWARE encryption defined in this format. Additional data +structures are added to support the processing needs of the +strong algorithms. + +The Strong Encryption data structures are: + +1. General Purpose Bits - Bits 0 and 6 of the General Purpose bit +flag in both local and central header records. Both bits set +indicates strong encryption. Bit 13, when set indicates the Central +Directory is encrypted and that selected fields in the Local Header +are masked to hide their actual value. + + +2. Extra Field 0x0017 in central header only. + + Fields to consider in this record are: + + Format - the data format identifier for this record. The only + value allowed at this time is the integer value 2. + + AlgId - integer identifier of the encryption algorithm from the + following range + + 0x6601 - DES + 0x6602 - RC2 (version needed to extract < 5.2) + 0x6603 - 3DES 168 + 0x6609 - 3DES 112 + 0x660E - AES 128 + 0x660F - AES 192 + 0x6610 - AES 256 + 0x6702 - RC2 (version needed to extract >= 5.2) + 0x6720 - Blowfish + 0x6721 - Twofish + 0x6801 - RC4 + 0xFFFF - Unknown algorithm + + Bitlen - Explicit bit length of key + + 32 - 448 bits + + Flags - Processing flags needed for decryption + + 0x0001 - Password is required to decrypt + 0x0002 - Certificates only + 0x0003 - Password or certificate required to decrypt + + Values > 0x0003 reserved for certificate processing + + +3. Decryption header record preceding compressed file data. + + -Decryption Header: + + Value Size Description + ----- ---- ----------- + IVSize 2 bytes Size of initialization vector (IV) + IVData IVSize Initialization vector for this file + Size 4 bytes Size of remaining decryption header data + Format 2 bytes Format definition for this record + AlgID 2 bytes Encryption algorithm identifier + Bitlen 2 bytes Bit length of encryption key + Flags 2 bytes Processing flags + ErdSize 2 bytes Size of Encrypted Random Data + ErdData ErdSize Encrypted Random Data + Reserved1 4 bytes Reserved certificate processing data + Reserved2 (var) Reserved for certificate processing data + VSize 2 bytes Size of password validation data + VData VSize-4 Password validation data + VCRC32 4 bytes Standard ZIP CRC32 of password validation data + + IVData - The size of the IV should match the algorithm block size. + The IVData can be completely random data. If the size of + the randomly generated data does not match the block size + it should be complemented with zero's or truncated as + necessary. If IVSize is 0,then IV = CRC32 + Uncompressed + File Size (as a 64 bit little-endian, unsigned integer value). + + Format - the data format identifier for this record. The only + value allowed at this time is the integer value 3. + + AlgId - integer identifier of the encryption algorithm from the + following range + + 0x6601 - DES + 0x6602 - RC2 (version needed to extract < 5.2) + 0x6603 - 3DES 168 + 0x6609 - 3DES 112 + 0x660E - AES 128 + 0x660F - AES 192 + 0x6610 - AES 256 + 0x6702 - RC2 (version needed to extract >= 5.2) + 0x6720 - Blowfish + 0x6721 - Twofish + 0x6801 - RC4 + 0xFFFF - Unknown algorithm + + Bitlen - Explicit bit length of key + + 32 - 448 bits + + Flags - Processing flags needed for decryption + + 0x0001 - Password is required to decrypt + 0x0002 - Certificates only + 0x0003 - Password or certificate required to decrypt + + Values > 0x0003 reserved for certificate processing + + ErdData - Encrypted random data is used to store random data that + is used to generate a file session key for encrypting + each file. SHA1 is used to calculate hash data used to + derive keys. File session keys are derived from a master + session key generated from the user-supplied password. + If the Flags field in the decryption header contains + the value 0x4000, then the ErdData field must be + decrypted using 3DES. If the value 0x4000 is not set, + then the ErdData field must be decrypted using AlgId. + + + Reserved1 - Reserved for certificate processing, if value is + zero, then Reserved2 data is absent. See the explanation + under the Certificate Processing Method for details on + this data structure. + + Reserved2 - If present, the size of the Reserved2 data structure + is located by skipping the first 4 bytes of this field + and using the next 2 bytes as the remaining size. See + the explanation under the Certificate Processing Method + for details on this data structure. + + VSize - This size value will always include the 4 bytes of the + VCRC32 data and will be greater than 4 bytes. + + VData - Random data for password validation. This data is VSize + in length and VSize must be a multiple of the encryption + block size. VCRC32 is a checksum value of VData. + VData and VCRC32 are stored encrypted and start the + stream of encrypted data for a file. + + +4. Useful Tips + +Strong Encryption is always applied to a file after compression. The +block oriented algorithms all operate in Cypher Block Chaining (CBC) +mode. The block size used for AES encryption is 16. All other block +algorithms use a block size of 8. Two ID's are defined for RC2 to +account for a discrepancy found in the implementation of the RC2 +algorithm in the cryptographic library on Windows XP SP1 and all +earlier versions of Windows. It is recommended that zero length files +not be encrypted, however programs should be prepared to extract them +if they are found within a ZIP file. + +A pseudo-code representation of the encryption process is as follows: + +Password = GetUserPassword() +MasterSessionKey = DeriveKey(SHA1(Password)) +RD = CryptographicStrengthRandomData() +For Each File + IV = CryptographicStrengthRandomData() + VData = CryptographicStrengthRandomData() + VCRC32 = CRC32(VData) + FileSessionKey = DeriveKey(SHA1(IV + RD) + ErdData = Encrypt(RD,MasterSessionKey,IV) + Encrypt(VData + VCRC32 + FileData, FileSessionKey,IV) +Done + +The function names and parameter requirements will depend on +the choice of the cryptographic toolkit selected. Almost any +toolkit supporting the reference implementations for each +algorithm can be used. The RSA BSAFE(r), OpenSSL, and Microsoft +CryptoAPI libraries are all known to work well. + + +Single Password - Central Directory Encryption: +----------------------------------------------- + +Central Directory Encryption is achieved within the .ZIP format by +encrypting the Central Directory structure. This encapsulates the metadata +most often used for processing .ZIP files. Additional metadata is stored for +redundancy in the Local Header for each file. The process of concealing +metadata by encrypting the Central Directory does not protect the data within +the Local Header. To avoid information leakage from the exposed metadata +in the Local Header, the fields containing information about a file are masked. + +Local Header: + +Masking replaces the true content of the fields for a file in the Local +Header with false information. When masked, the Local Header is not +suitable for streaming access and the options for data recovery of damaged +archives is reduced. Extra Data fields that may contain confidential +data should not be stored within the Local Header. The value set into +the Version needed to extract field should be the correct value needed to +extract the file without regard to Central Directory Encryption. The fields +within the Local Header targeted for masking when the Central Directory is +encrypted are: + + Field Name Mask Value + ------------------ --------------------------- + compression method 0 + last mod file time 0 + last mod file date 0 + crc-32 0 + compressed size 0 + uncompressed size 0 + file name (variable size) Base 16 value from the + range 1 - 0xFFFFFFFFFFFFFFFF + represented as a string whose + size will be set into the + file name length field + +The Base 16 value assigned as a masked file name is simply a sequentially +incremented value for each file starting with 1 for the first file. +Modifications to a ZIP file may cause different values to be stored for +each file. For compatibility, the file name field in the Local Header +should never be left blank. As of Version 6.2 of this specification, +the Compression Method and Compressed Size fields are not yet masked. +Fields having a value of 0xFFFF or 0xFFFFFFFF for the ZIP64 format +should not be masked. + +Encrypting the Central Directory: + +Encryption of the Central Directory does not include encryption of the +Central Directory Signature data, the Zip64 End of Central Directory +record, the Zip64 End of Central Directory Locator, or the End +of Central Directory record. The ZIP file comment data is never +encrypted. + +Before encrypting the Central Directory, it may optionally be compressed. +Compression is not required, but for storage efficiency it is assumed +this structure will be compressed before encrypting. Similarly, this +specification supports compressing the Central Directory without +requiring that it also be encrypted. Early implementations of this +feature will assume the encryption method applied to files matches the +encryption applied to the Central Directory. + +Encryption of the Central Directory is done in a manner similar to +that of file encryption. The encrypted data is preceded by a +decryption header. The decryption header is known as the Archive +Decryption Header. The fields of this record are identical to +the decryption header preceding each encrypted file. The location +of the Archive Decryption Header is determined by the value in the +Start of the Central Directory field in the Zip64 End of Central +Directory record. When the Central Directory is encrypted, the +Zip64 End of Central Directory record will always be present. + +The layout of the Zip64 End of Central Directory record for all +versions starting with 6.2 of this specification will follow the +Version 2 format. The Version 2 format is as follows: + +The leading fixed size fields within the Version 1 format for this +record remain unchanged. The record signature for both Version 1 +and Version 2 will be 0x06064b50. Immediately following the last +byte of the field known as the Offset of Start of Central +Directory With Respect to the Starting Disk Number will begin the +new fields defining Version 2 of this record. + +New fields for Version 2: + +Note: all fields stored in Intel low-byte/high-byte order. + + Value Size Description + ----- ---- ----------- + Compression Method 2 bytes Method used to compress the + Central Directory + Compressed Size 8 bytes Size of the compressed data + Original Size 8 bytes Original uncompressed size + AlgId 2 bytes Encryption algorithm ID + BitLen 2 bytes Encryption key length + Flags 2 bytes Encryption flags + HashID 2 bytes Hash algorithm identifier + Hash Length 2 bytes Length of hash data + Hash Data (variable) Hash data + +The Compression Method accepts the same range of values as the +corresponding field in the Central Header. + +The Compressed Size and Original Size values will not include the +data of the Central Directory Signature which is compressed or +encrypted. + +The AlgId, BitLen, and Flags fields accept the same range of values +the corresponding fields within the 0x0017 record. + +Hash ID identifies the algorithm used to hash the Central Directory +data. This data does not have to be hashed, in which case the +values for both the HashID and Hash Length will be 0. Possible +values for HashID are: + + Value Algorithm + ------ --------- + 0x0000 none + 0x0001 CRC32 + 0x8003 MD5 + 0x8004 SHA1 + 0x8007 RIPEMD160 + 0x800C SHA256 + 0x800D SHA384 + 0x800E SHA512 + +When the Central Directory data is signed, the same hash algorithm +used to hash the Central Directory for signing should be used. +This is recommended for processing efficiency, however, it is +permissible for any of the above algorithms to be used independent +of the signing process. + +The Hash Data will contain the hash data for the Central Directory. +The length of this data will vary depending on the algorithm used. + +The Version Needed to Extract should be set to 62. + +The value for the Total Number of Entries on the Current Disk will +be 0. These records will no longer support random access when +encrypting the Central Directory. + +When the Central Directory is compressed and/or encrypted, the +End of Central Directory record will store the value 0xFFFFFFFF +as the value for the Total Number of Entries in the Central +Directory. The value stored in the Total Number of Entries in +the Central Directory on this Disk field will be 0. The actual +values will be stored in the equivalent fields of the Zip64 +End of Central Directory record. + +Decrypting and decompressing the Central Directory is accomplished +in the same manner as decrypting and decompressing a file. + +Certificate Processing Method: +----------------------------- + +The Certificate Processing Method of for ZIP file encryption +defines the following additional data fields: + +1. Certificate Flag Values + +Additional processing flags that can be present in the Flags field of both +the 0x0017 field of the central directory Extra Field and the Decryption +header record preceding compressed file data are: + + 0x0007 - reserved for future use + 0x000F - reserved for future use + 0x0100 - Indicates non-OAEP key wrapping was used. If this + this field is set, the version needed to extract must + be at least 61. This means OAEP key wrapping is not + used when generating a Master Session Key using + ErdData. + 0x4000 - ErdData must be decrypted using 3DES-168, otherwise use the + same algorithm used for encrypting the file contents. + 0x8000 - reserved for future use + + +2. CertData - Extra Field 0x0017 record certificate data structure + +The data structure used to store certificate data within the section +of the Extra Field defined by the CertData field of the 0x0017 +record are as shown: + + Value Size Description + ----- ---- ----------- + RCount 4 bytes Number of recipients. + HashAlg 2 bytes Hash algorithm identifier + HSize 2 bytes Hash size + SRList (var) Simple list of recipients hashed public keys + + + RCount This defines the number intended recipients whose + public keys were used for encryption. This identifies + the number of elements in the SRList. + + HashAlg This defines the hash algorithm used to calculate + the public key hash of each public key used + for encryption. This field currently supports + only the following value for SHA-1 + + 0x8004 - SHA1 + + HSize This defines the size of a hashed public key. + + SRList This is a variable length list of the hashed + public keys for each intended recipient. Each + element in this list is HSize. The total size of + SRList is determined using RCount * HSize. + + +3. Reserved1 - Certificate Decryption Header Reserved1 Data: + + Value Size Description + ----- ---- ----------- + RCount 4 bytes Number of recipients. + + RCount This defines the number intended recipients whose + public keys were used for encryption. This defines + the number of elements in the REList field defined below. + + +4. Reserved2 - Certificate Decryption Header Reserved2 Data Structures: + + + Value Size Description + ----- ---- ----------- + HashAlg 2 bytes Hash algorithm identifier + HSize 2 bytes Hash size + REList (var) List of recipient data elements + + + HashAlg This defines the hash algorithm used to calculate + the public key hash of each public key used + for encryption. This field currently supports + only the following value for SHA-1 + + 0x8004 - SHA1 + + HSize This defines the size of a hashed public key + defined in REHData. + + REList This is a variable length of list of recipient data. + Each element in this list consists of a Recipient + Element data structure as follows: + + + Recipient Element (REList) Data Structure: + + Value Size Description + ----- ---- ----------- + RESize 2 bytes Size of REHData + REKData + REHData HSize Hash of recipients public key + REKData (var) Simple key blob + + + RESize This defines the size of an individual REList + element. This value is the combined size of the + REHData field + REKData field. REHData is defined by + HSize. REKData is variable and can be calculated + for each REList element using RESize and HSize. + + REHData Hashed public key for this recipient. + + REKData Simple Key Blob. The format of this data structure + is identical to that defined in the Microsoft + CryptoAPI and generated using the CryptExportKey() + function. The version of the Simple Key Blob + supported at this time is 0x02 as defined by + Microsoft. + +Certificate Processing - Central Directory Encryption: +------------------------------------------------------ + +Central Directory Encryption using Digital Certificates will +operate in a manner similar to that of Single Password Central +Directory Encryption. This record will only be present when there +is data to place into it. Currently, data is placed into this +record when digital certificates are used for either encrypting +or signing the files within a ZIP file. When only password +encryption is used with no certificate encryption or digital +signing, this record is not currently needed. When present, this +record will appear before the start of the actual Central Directory +data structure and will be located immediately after the Archive +Decryption Header if the Central Directory is encrypted. + +The Archive Extra Data record will be used to store the following +information. Additional data may be added in future versions. + +Extra Data Fields: + +0x0014 - PKCS#7 Store for X.509 Certificates +0x0016 - X.509 Certificate ID and Signature for central directory +0x0019 - PKCS#7 Encryption Recipient Certificate List + +The 0x0014 and 0x0016 Extra Data records that otherwise would be +located in the first record of the Central Directory for digital +certificate processing. When encrypting or compressing the Central +Directory, the 0x0014 and 0x0016 records must be located in the +Archive Extra Data record and they should not remain in the first +Central Directory record. The Archive Extra Data record will also +be used to store the 0x0019 data. + +When present, the size of the Archive Extra Data record will be +included in the size of the Central Directory. The data of the +Archive Extra Data record will also be compressed and encrypted +along with the Central Directory data structure. + +Certificate Processing Differences: + +The Certificate Processing Method of encryption differs from the +Single Password Symmetric Encryption Method as follows. Instead +of using a user-defined password to generate a master session key, +cryptographically random data is used. The key material is then +wrapped using standard key-wrapping techniques. This key material +is wrapped using the public key of each recipient that will need +to decrypt the file using their corresponding private key. + +This specification currently assumes digital certificates will follow +the X.509 V3 format for 1024 bit and higher RSA format digital +certificates. Implementation of this Certificate Processing Method +requires supporting logic for key access and management. This logic +is outside the scope of this specification. + +OAEP Processing with Certificate-based Encryption: + +OAEP stands for Optimal Asymmetric Encryption Padding. It is a +strengthening technique used for small encoded items such as decryption +keys. This is commonly applied in cryptographic key-wrapping techniques +and is supported by PKCS #1. Versions 5.0 and 6.0 of this specification +were designed to support OAEP key-wrapping for certificate-based +decryption keys for additional security. + +Support for private keys stored on Smartcards or Tokens introduced +a conflict with this OAEP logic. Most card and token products do +not support the additional strengthening applied to OAEP key-wrapped +data. In order to resolve this conflict, versions 6.1 and above of this +specification will no longer support OAEP when encrypting using +digital certificates. + +Versions of PKZIP available during initial development of the +certificate processing method set a value of 61 into the +version needed to extract field for a file. This indicates that +non-OAEP key wrapping is used. This affects certificate encryption +only, and password encryption functions should not be affected by +this value. This means values of 61 may be found on files encrypted +with certificates only, or on files encrypted with both password +encryption and certificate encryption. Files encrypted with both +methods can safely be decrypted using the password methods documented. + +XVII. Change Process +-------------------- + +In order for the .ZIP file format to remain a viable definition, this +specification should be considered as open for periodic review and +revision. Although this format was originally designed with a +certain level of extensibility, not all changes in technology +(present or future) were or will be necessarily considered in its +design. If your application requires new definitions to the +extensible sections in this format, or if you would like to +submit new data structures, please forward your request to +zipformat@pkware.com. All submissions will be reviewed by the +ZIP File Specification Committee for possible inclusion into +future versions of this specification. Periodic revisions +to this specification will be published to ensure interoperability. +We encourage comments and feedback that may help improve clarity +or content. + +XVIII. Incorporating PKWARE Proprietary Technology into Your Product +-------------------------------------------------------------------- + +PKWARE is committed to the interoperability and advancement of the +.ZIP format. PKWARE offers a free license for certain technological +aspects described above under certain restrictions and conditions. +However, the use or implementation in a product of certain technological +aspects set forth in the current APPNOTE, including those with regard to +strong encryption, patching, or extended tape operations requires a +license from PKWARE. Please contact PKWARE with regard to acquiring +a license. + +XIX. Acknowledgements +---------------------- + +In addition to the above mentioned contributors to PKZIP and PKUNZIP, +I would like to extend special thanks to Robert Mahoney for suggesting +the extension .ZIP for this software. + +XX. References +-------------- + + Fiala, Edward R., and Greene, Daniel H., "Data compression with + finite windows", Communications of the ACM, Volume 32, Number 4, + April 1989, pages 490-505. + + Held, Gilbert, "Data Compression, Techniques and Applications, + Hardware and Software Considerations", John Wiley & Sons, 1987. + + Huffman, D.A., "A method for the construction of minimum-redundancy + codes", Proceedings of the IRE, Volume 40, Number 9, September 1952, + pages 1098-1101. + + Nelson, Mark, "LZW Data Compression", Dr. Dobbs Journal, Volume 14, + Number 10, October 1989, pages 29-37. + + Nelson, Mark, "The Data Compression Book", M&T Books, 1991. + + Storer, James A., "Data Compression, Methods and Theory", + Computer Science Press, 1988 + + Welch, Terry, "A Technique for High-Performance Data Compression", + IEEE Computer, Volume 17, Number 6, June 1984, pages 8-19. + + Ziv, J. and Lempel, A., "A universal algorithm for sequential data + compression", Communications of the ACM, Volume 30, Number 6, + June 1987, pages 520-540. + + Ziv, J. and Lempel, A., "Compression of individual sequences via + variable-rate coding", IEEE Transactions on Information Theory, + Volume 24, Number 5, September 1978, pages 530-536. + + +APPENDIX A - AS/400 Extra Field (0x0065) Attribute Definitions +-------------------------------------------------------------- + +Field Definition Structure: + + a. field length including length 2 bytes + b. field code 2 bytes + c. data x bytes + +Field Code Description + 4001 Source type i.e. CLP etc + 4002 The text description of the library + 4003 The text description of the file + 4004 The text description of the member + 4005 x'F0' or 0 is PF-DTA, x'F1' or 1 is PF_SRC + 4007 Database Type Code 1 byte + 4008 Database file and fields definition + 4009 GZIP file type 2 bytes + 400B IFS code page 2 bytes + 400C IFS Creation Time 4 bytes + 400D IFS Access Time 4 bytes + 400E IFS Modification time 4 bytes + 005C Length of the records in the file 2 bytes + 0068 GZIP two words 8 bytes + +APPENDIX B - z/OS Extra Field (0x0065) Attribute Definitions +------------------------------------------------------------ + +Field Definition Structure: + + a. field length including length 2 bytes + b. field code 2 bytes + c. data x bytes + +Field Code Description + 0001 File Type 2 bytes + 0002 NonVSAM Record Format 1 byte + 0003 Reserved + 0004 NonVSAM Block Size 2 bytes Big Endian + 0005 Primary Space Allocation 3 bytes Big Endian + 0006 Secondary Space Allocation 3 bytes Big Endian + 0007 Space Allocation Type1 byte flag + 0008 Modification Date Retired with PKZIP 5.0 + + 0009 Expiration Date Retired with PKZIP 5.0 + + 000A PDS Directory Block Allocation 3 bytes Big Endian binary value + 000B NonVSAM Volume List variable + 000C UNIT Reference Retired with PKZIP 5.0 + + 000D DF/SMS Management Class 8 bytes EBCDIC Text Value + 000E DF/SMS Storage Class 8 bytes EBCDIC Text Value + 000F DF/SMS Data Class 8 bytes EBCDIC Text Value + 0010 PDS/PDSE Member Info. 30 bytes + 0011 VSAM sub-filetype 2 bytes + 0012 VSAM LRECL 13 bytes EBCDIC "(num_avg num_max)" + 0013 VSAM Cluster Name Retired with PKZIP 5.0 + + 0014 VSAM KSDS Key Information 13 bytes EBCDIC "(num_length num_position)" + 0015 VSAM Average LRECL 5 bytes EBCDIC num_value padded with blanks + 0016 VSAM Maximum LRECL 5 bytes EBCDIC num_value padded with blanks + 0017 VSAM KSDS Key Length 5 bytes EBCDIC num_value padded with blanks + 0018 VSAM KSDS Key Position 5 bytes EBCDIC num_value padded with blanks + 0019 VSAM Data Name 1-44 bytes EBCDIC text string + 001A VSAM KSDS Index Name 1-44 bytes EBCDIC text string + 001B VSAM Catalog Name 1-44 bytes EBCDIC text string + 001C VSAM Data Space Type 9 bytes EBCDIC text string + 001D VSAM Data Space Primary 9 bytes EBCDIC num_value left-justified + 001E VSAM Data Space Secondary 9 bytes EBCDIC num_value left-justified + 001F VSAM Data Volume List variable EBCDIC text list of 6-character Volume IDs + 0020 VSAM Data Buffer Space 8 bytes EBCDIC num_value left-justified + 0021 VSAM Data CISIZE 5 bytes EBCDIC num_value left-justified + 0022 VSAM Erase Flag 1 byte flag + 0023 VSAM Free CI % 3 bytes EBCDIC num_value left-justified + 0024 VSAM Free CA % 3 bytes EBCDIC num_value left-justified + 0025 VSAM Index Volume List variable EBCDIC text list of 6-character Volume IDs + 0026 VSAM Ordered Flag 1 byte flag + 0027 VSAM REUSE Flag 1 byte flag + 0028 VSAM SPANNED Flag 1 byte flag + 0029 VSAM Recovery Flag 1 byte flag + 002A VSAM WRITECHK Flag 1 byte flag + 002B VSAM Cluster/Data SHROPTS 3 bytes EBCDIC "n,y" + 002C VSAM Index SHROPTS 3 bytes EBCDIC "n,y" + 002D VSAM Index Space Type 9 bytes EBCDIC text string + 002E VSAM Index Space Primary 9 bytes EBCDIC num_value left-justified + 002F VSAM Index Space Secondary 9 bytes EBCDIC num_value left-justified + 0030 VSAM Index CISIZE 5 bytes EBCDIC num_value left-justified + 0031 VSAM Index IMBED 1 byte flag + 0032 VSAM Index Ordered Flag 1 byte flag + 0033 VSAM REPLICATE Flag 1 byte flag + 0034 VSAM Index REUSE Flag 1 byte flag + 0035 VSAM Index WRITECHK Flag 1 byte flag Retired with PKZIP 5.0 + + 0036 VSAM Owner 8 bytes EBCDIC text string + 0037 VSAM Index Owner 8 bytes EBCDIC text string + 0038 Reserved + 0039 Reserved + 003A Reserved + 003B Reserved + 003C Reserved + 003D Reserved + 003E Reserved + 003F Reserved + 0040 Reserved + 0041 Reserved + 0042 Reserved + 0043 Reserved + 0044 Reserved + 0045 Reserved + 0046 Reserved + 0047 Reserved + 0048 Reserved + 0049 Reserved + 004A Reserved + 004B Reserved + 004C Reserved + 004D Reserved + 004E Reserved + 004F Reserved + 0050 Reserved + 0051 Reserved + 0052 Reserved + 0053 Reserved + 0054 Reserved + 0055 Reserved + 0056 Reserved + 0057 Reserved + 0058 PDS/PDSE Member TTR Info. 6 bytes Big Endian + 0059 PDS 1st LMOD Text TTR 3 bytes Big Endian + 005A PDS LMOD EP Rec # 4 bytes Big Endian + 005B Reserved + 005C Max Length of records 2 bytes Big Endian + 005D PDSE Flag 1 byte flag + 005E Reserved + 005F Reserved + 0060 Reserved + 0061 Reserved + 0062 Reserved + 0063 Reserved + 0064 Reserved + 0065 Last Date Referenced 4 bytes Packed Hex "yyyymmdd" + 0066 Date Created 4 bytes Packed Hex "yyyymmdd" + 0068 GZIP two words 8 bytes + 0071 Extended NOTE Location 12 bytes Big Endian + 0072 Archive device UNIT 6 bytes EBCDIC + 0073 Archive 1st Volume 6 bytes EBCDIC + 0074 Archive 1st VOL File Seq# 2 bytes Binary + +APPENDIX C - Zip64 Extensible Data Sector Mappings (EFS) +-------------------------------------------------------- + + -Z390 Extra Field: + + The following is the general layout of the attributes for the + ZIP 64 "extra" block for extended tape operations. Portions of + this extended tape processing technology is covered under a + pending patent application. The use or implementation in a + product of certain technological aspects set forth in the + current APPNOTE, including those with regard to strong encryption, + patching or extended tape operations, requires a license from + PKWARE. Please contact PKWARE with regard to acquiring a license. + + + Note: some fields stored in Big Endian format. All text is + in EBCDIC format unless otherwise specified. + + Value Size Description + ----- ---- ----------- + (Z390) 0x0065 2 bytes Tag for this "extra" block type + Size 4 bytes Size for the following data block + Tag 4 bytes EBCDIC "Z390" + Length71 2 bytes Big Endian + Subcode71 2 bytes Enote type code + FMEPos 1 byte + Length72 2 bytes Big Endian + Subcode72 2 bytes Unit type code + Unit 1 byte Unit + Length73 2 bytes Big Endian + Subcode73 2 bytes Volume1 type code + FirstVol 1 byte Volume + Length74 2 bytes Big Endian + Subcode74 2 bytes FirstVol file sequence + FileSeq 2 bytes Sequence + +APPENDIX D - Language Encoding (EFS) +------------------------------------ + +The ZIP format has historically supported only the original IBM PC character +encoding set, commonly referred to as IBM Code Page 437. This limits storing +file name characters to only those within the original MS-DOS range of values +and does not properly support file names in other character encodings, or +languages. To address this limitation, this specification will support the +following change. + +If general purpose bit 11 is unset, the file name and comment should conform +to the original ZIP character encoding. If general purpose bit 11 is set, the +filename and comment must support The Unicode Standard, Version 4.1.0 or +greater using the character encoding form defined by the UTF-8 storage +specification. The Unicode Standard is published by the The Unicode +Consortium (www.unicode.org). UTF-8 encoded data stored within ZIP files +is expected to not include a byte order mark (BOM). + +Applications may choose to supplement this file name storage through the use +of the 0x0008 Extra Field. Storage for this optional field is currently +undefined, however it will be used to allow storing extended information +on source or target encoding that may further assist applications with file +name, or file content encoding tasks. Please contact PKWARE with any +requirements on how this field should be used. + +The 0x0008 Extra Field storage may be used with either setting for general +purpose bit 11. Examples of the intended usage for this field is to store +whether "modified-UTF-8" (JAVA) is used, or UTF-8-MAC. Similarly, other +commonly used character encoding (code page) designations can be indicated +through this field. Formalized values for use of the 0x0008 record remain +undefined at this time. The definition for the layout of the 0x0008 field +will be published when available. Use of the 0x0008 Extra Field provides +for storing data within a ZIP file in an encoding other than IBM Code +Page 437 or UTF-8. + +General purpose bit 11 will not imply any encoding of file content or +password. Values defining character encoding for file content or +password must be stored within the 0x0008 Extended Language Encoding +Extra Field. + + diff --git a/contrib/zipstream-php-0.2.2/test/index.php b/contrib/zipstream-php-0.2.2/test/index.php new file mode 100644 index 0000000..ec89f76 --- /dev/null +++ b/contrib/zipstream-php-0.2.2/test/index.php @@ -0,0 +1,52 @@ + 'this is a zip file comment. hello?' +)); + +# common file options +$file_opt = array( + # file creation time (2 hours ago) + 'time' => time() - 2 * 3600, + + # file comment + 'comment' => 'this is a file comment. hi!', +); + +# add files under folder 'asdf' +foreach ($files as $file) { + # build absolute path and get file data + $path = ($file[0] == '/') ? $file : "$pwd/$file"; + $data = file_get_contents($path); + + # add file to archive + $zip->add_file('asdf/' . basename($file), $data, $file_opt); +} + +# add same files again wihtout a folder +foreach ($files as $file) { + # build absolute path and get file data + $path = ($file[0] == '/') ? $file : "$pwd/$file"; + $data = file_get_contents($path); + + # add file to archive + $zip->add_file(basename($file), $data, $file_opt); +} + +# finish archive +$zip->finish(); + +?> diff --git a/contrib/zipstream-php-0.2.2/zipstream.php b/contrib/zipstream-php-0.2.2/zipstream.php new file mode 100644 index 0000000..37a6046 --- /dev/null +++ b/contrib/zipstream-php-0.2.2/zipstream.php @@ -0,0 +1,580 @@ + # +# # +# Copyright (C) 2007-2009 Paul Duncan # +# # +# Permission is hereby granted, free of charge, to any person obtaining # +# a copy of this software and associated documentation files (the # +# "Software"), to deal in the Software without restriction, including # +# without limitation the rights to use, copy, modify, merge, publish, # +# distribute, sublicense, and/or sell copies of the Software, and to # +# permit persons to whom the Software is furnished to do so, subject to # +# the following conditions: # +# # +# The above copyright notice and this permission notice shall be # +# included in all copies or substantial portions of the of the Software. # +# # +# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, # +# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF # +# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. # +# IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR # +# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, # +# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR # +# OTHER DEALINGS IN THE SOFTWARE. # +########################################################################## + +# +# ZipStream - Streamed, dynamically generated zip archives. +# by Paul Duncan +# +# Requirements: +# +# * PHP version 5.1.2 or newer. +# +# Usage: +# +# Streaming zip archives is a simple, three-step process: +# +# 1. Create the zip stream: +# +# $zip = new ZipStream('example.zip'); +# +# 2. Add one or more files to the archive: +# +# # add first file +# $data = file_get_contents('some_file.gif'); +# $zip->add_file('some_file.gif', $data); +# +# # add second file +# $data = file_get_contents('some_file.gif'); +# $zip->add_file('another_file.png', $data); +# +# 3. Finish the zip stream: +# +# $zip->finish(); +# +# You can also add an archive comment, add comments to individual files, +# and adjust the timestamp of files. See the API documentation for each +# method below for additional information. +# +# Example: +# +# # create a new zip stream object +# $zip = new ZipStream('some_files.zip'); +# +# # list of local files +# $files = array('foo.txt', 'bar.jpg'); +# +# # read and add each file to the archive +# foreach ($files as $path) +# $zip->add_file($path, file_get_contents($path)); +# +# # write archive footer to stream +# $zip->finish(); +# +class ZipStream { + const VERSION = '0.2.2'; + + var $opt = array(), + $files = array(), + $cdr_ofs = 0, + $need_headers = false, + $ofs = 0; + + # + # Create a new ZipStream object. + # + # Parameters: + # + # $name - Name of output file (optional). + # $opt - Hash of archive options (optional, see "Archive Options" + # below). + # + # Archive Options: + # + # comment - Comment for this archive. + # content_type - HTTP Content-Type. Defaults to 'application/x-zip'. + # content_disposition - HTTP Content-Disposition. Defaults to + # 'attachment; filename=\"FILENAME\"', where + # FILENAME is the specified filename. + # large_file_size - Size, in bytes, of the largest file to try + # and load into memory (used by + # add_file_from_path()). Large files may also + # be compressed differently; see the + # 'large_file_method' option. + # large_file_method - How to handle large files. Legal values are + # 'store' (the default), or 'deflate'. Store + # sends the file raw and is significantly + # faster, while 'deflate' compresses the file + # and is much, much slower. Note that deflate + # must compress the file twice and extremely + # slow. + # send_http_headers - Boolean indicating whether or not to send + # the HTTP headers for this file. + # + # Note that content_type and content_disposition do nothing if you are + # not sending HTTP headers. + # + # Large File Support: + # + # By default, the method add_file_from_path() will send send files + # larger than 20 megabytes along raw rather than attempting to + # compress them. You can change both the maximum size and the + # compression behavior using the large_file_* options above, with the + # following caveats: + # + # * For "small" files (e.g. files smaller than large_file_size), the + # memory use can be up to twice that of the actual file. In other + # words, adding a 10 megabyte file to the archive could potentially + # occupty 20 megabytes of memory. + # + # * Enabling compression on large files (e.g. files larger than + # large_file_size) is extremely slow, because ZipStream has to pass + # over the large file once to calculate header information, and then + # again to compress and send the actual data. + # + # Examples: + # + # # create a new zip file named 'foo.zip' + # $zip = new ZipStream('foo.zip'); + # + # # create a new zip file named 'bar.zip' with a comment + # $zip = new ZipStream('bar.zip', array( + # 'comment' => 'this is a comment for the zip file.', + # )); + # + # Notes: + # + # If you do not set a filename, then this library _DOES NOT_ send HTTP + # headers by default. This behavior is to allow software to send its + # own headers (including the filename), and still use this library. + # + function __construct($name = null, $opt = array()) { + # save options + $this->opt = $opt; + + # set large file defaults: size = 20 megabytes, method = store + if (!isset($this->opt['large_file_size'])) + $this->opt['large_file_size'] = 20 * 1024 * 1024; + if (!isset($this->opt['large_file_method'])) + $this->opt['large_file_method'] = 'store'; + + $this->output_name = $name; + if ($name || (isset($opt['send_http_headers']) + && $opt['send_http_headers'])) + $this->need_headers = true; + } + + # + # add_file - add a file to the archive + # + # Parameters: + # + # $name - path of file in archive (including directory). + # $data - contents of file + # $opt - Hash of options for file (optional, see "File Options" + # below). + # + # File Options: + # time - Last-modified timestamp (seconds since the epoch) of + # this file. Defaults to the current time. + # comment - Comment related to this file. + # + # Examples: + # + # # add a file named 'foo.txt' + # $data = file_get_contents('foo.txt'); + # $zip->add_file('foo.txt', $data); + # + # # add a file named 'bar.jpg' with a comment and a last-modified + # # time of two hours ago + # $data = file_get_contents('bar.jpg'); + # $zip->add_file('bar.jpg', $data, array( + # 'time' => time() - 2 * 3600, + # 'comment' => 'this is a comment about bar.jpg', + # )); + # + function add_file($name, $data, $opt = array()) { + # compress data + $zdata = gzdeflate($data); + + # calculate header attributes + $crc = crc32($data); + $zlen = strlen($zdata); + $len = strlen($data); + $meth = 0x08; + + # send file header + $this->add_file_header($name, $opt, $meth, $crc, $zlen, $len); + + # print data + $this->send($zdata); + } + + # + # add_file_from_path - add a file at path to the archive. + # + # Note that large files may be compresed differently than smaller + # files; see the "Large File Support" section above for more + # information. + # + # Parameters: + # + # $name - name of file in archive (including directory path). + # $path - path to file on disk (note: paths should be encoded using + # UNIX-style forward slashes -- e.g '/path/to/some/file'). + # $opt - Hash of options for file (optional, see "File Options" + # below). + # + # File Options: + # time - Last-modified timestamp (seconds since the epoch) of + # this file. Defaults to the current time. + # comment - Comment related to this file. + # + # Examples: + # + # # add a file named 'foo.txt' from the local file '/tmp/foo.txt' + # $zip->add_file_from_path('foo.txt', '/tmp/foo.txt'); + # + # # add a file named 'bigfile.rar' from the local file + # # '/usr/share/bigfile.rar' with a comment and a last-modified + # # time of two hours ago + # $path = '/usr/share/bigfile.rar'; + # $zip->add_file_from_path('bigfile.rar', $path, array( + # 'time' => time() - 2 * 3600, + # 'comment' => 'this is a comment about bar.jpg', + # )); + # + function add_file_from_path($name, $path, $opt = array()) { + if ($this->is_large_file($path)) { + # file is too large to be read into memory; add progressively + $this->add_large_file($name, $path, $opt); + } else { + # file is small enough to read into memory; read file contents and + # handle with add_file() + $data = file_get_contents($path); + $this->add_file($name, $data, $opt); + } + } + + # + # finish - Write zip footer to stream. + # + # Example: + # + # # add a list of files to the archive + # $files = array('foo.txt', 'bar.jpg'); + # foreach ($files as $path) + # $zip->add_file($path, file_get_contents($path)); + # + # # write footer to stream + # $zip->finish(); + # + function finish() { + # add trailing cdr record + $this->add_cdr($this->opt); + $this->clear(); + } + + ################### + # PRIVATE METHODS # + ################### + + # + # Create and send zip header for this file. + # + private function add_file_header($name, $opt, $meth, $crc, $zlen, $len) { + # strip leading slashes from file name + # (fixes bug in windows archive viewer) + $name = preg_replace('/^\\/+/', '', $name); + + # calculate name length + $nlen = strlen($name); + + # create dos timestamp + $opt['time'] = isset($opt['time']) ? $opt['time'] : time(); + $dts = $this->dostime($opt['time']); + + # build file header + $fields = array( # (from V.A of APPNOTE.TXT) + array('V', 0x04034b50), # local file header signature + array('v', (6 << 8) + 3), # version needed to extract + array('v', 0x00), # general purpose bit flag + array('v', $meth), # compresion method (deflate or store) + array('V', $dts), # dos timestamp + array('V', $crc), # crc32 of data + array('V', $zlen), # compressed data length + array('V', $len), # uncompressed data length + array('v', $nlen), # filename length + array('v', 0), # extra data len + ); + + # pack fields and calculate "total" length + $ret = $this->pack_fields($fields); + $cdr_len = strlen($ret) + $nlen + $zlen; + + # print header and filename + $this->send($ret . $name); + + # add to central directory record and increment offset + $this->add_to_cdr($name, $opt, $meth, $crc, $zlen, $len, $cdr_len); + } + + # + # Add a large file from the given path. + # + private function add_large_file($name, $path, $opt = array()) { + $st = stat($path); + $block_size = 1048576; # process in 1 megabyte chunks + $algo = 'crc32b'; + + # calculate header attributes + $zlen = $len = $st['size']; + + $meth_str = $this->opt['large_file_method']; + if ($meth_str == 'store') { + # store method + $meth = 0x00; + $crc = unpack('V', hash_file($algo, $path, true)); + $crc = $crc[1]; + } elseif ($meth_str == 'deflate') { + # deflate method + $meth = 0x08; + + # open file, calculate crc and compressed file length + $fh = fopen($path, 'rb'); + $hash_ctx = hash_init($algo); + $zlen = 0; + + # read each block, update crc and zlen + while ($data = fgets($fh, $block_size)) { + hash_update($hash_ctx, $data); + $data = gzdeflate($data); + $zlen += strlen($data); + } + + # close file and finalize crc + fclose($fh); + $crc = unpack('V', hash_final($hash_ctx, true)); + $crc = $crc[1]; + } else { + die("unknown large_file_method: $meth_str"); + } + + # send file header + $this->add_file_header($name, $opt, $meth, $crc, $zlen, $len); + + # open input file + $fh = fopen($path, 'rb'); + + # send file blocks + while ($data = fgets($fh, $block_size)) { + if ($meth_str == 'deflate') + $data = gzdeflate($data); + + # send data + $this->send($data); + } + + # close input file + fclose($fh); + } + + # + # Is this file larger than large_file_size? + # + function is_large_file($path) { + $st = stat($path); + return ($this->opt['large_file_size'] > 0) && + ($st['size'] > $this->opt['large_file_size']); + } + + # + # Save file attributes for trailing CDR record. + # + private function add_to_cdr($name, $opt, $meth, $crc, $zlen, $len, $rec_len) { + $this->files[] = array($name, $opt, $meth, $crc, $zlen, $len, $this->ofs); + $this->ofs += $rec_len; + } + + # + # Send CDR record for specified file. + # + private function add_cdr_file($args) { + list ($name, $opt, $meth, $crc, $zlen, $len, $ofs) = $args; + + # get attributes + $comment = $opt['comment'] ? $opt['comment'] : ''; + + # get dos timestamp + $dts = $this->dostime($opt['time']); + + $fields = array( # (from V,F of APPNOTE.TXT) + array('V', 0x02014b50), # central file header signature + array('v', (6 << 8) + 3), # version made by + array('v', (6 << 8) + 3), # version needed to extract + array('v', 0x00), # general purpose bit flag + array('v', $meth), # compresion method (deflate or store) + array('V', $dts), # dos timestamp + array('V', $crc), # crc32 of data + array('V', $zlen), # compressed data length + array('V', $len), # uncompressed data length + array('v', strlen($name)), # filename length + array('v', 0), # extra data len + array('v', strlen($comment)), # file comment length + array('v', 0), # disk number start + array('v', 0), # internal file attributes + array('V', 32), # external file attributes + array('V', $ofs), # relative offset of local header + ); + + # pack fields, then append name and comment + $ret = $this->pack_fields($fields) . $name . $comment; + + $this->send($ret); + + # increment cdr offset + $this->cdr_ofs += strlen($ret); + } + + # + # Send CDR EOF (Central Directory Record End-of-File) record. + # + private function add_cdr_eof($opt = null) { + $num = count($this->files); + $cdr_len = $this->cdr_ofs; + $cdr_ofs = $this->ofs; + + # grab comment (if specified) + $comment = ''; + if ($opt && $opt['comment']) + $comment = $opt['comment']; + + $fields = array( # (from V,F of APPNOTE.TXT) + array('V', 0x06054b50), # end of central file header signature + array('v', 0x00), # this disk number + array('v', 0x00), # number of disk with cdr + array('v', $num), # number of entries in the cdr on this disk + array('v', $num), # number of entries in the cdr + array('V', $cdr_len), # cdr size + array('V', $cdr_ofs), # cdr ofs + array('v', strlen($comment)), # zip file comment length + ); + + $ret = $this->pack_fields($fields) . $comment; + $this->send($ret); + } + + # + # Add CDR (Central Directory Record) footer. + # + private function add_cdr($opt = null) { + foreach ($this->files as $file) + $this->add_cdr_file($file); + $this->add_cdr_eof($opt); + } + + # + # Clear all internal variables. Note that the stream object is not + # usable after this. + # + function clear() { + $this->files = array(); + $this->ofs = 0; + $this->cdr_ofs = 0; + $this->opt = array(); + } + + ########################### + # PRIVATE UTILITY METHODS # + ########################### + + # + # Send HTTP headers for this stream. + # + private function send_http_headers() { + # grab options + $opt = $this->opt; + + # grab content type from options + $content_type = 'application/x-zip'; + if (isset($opt['content_type'])) + $content_type = $this->opt['content_type']; + + # grab content disposition + $disposition = 'attachment'; + if (isset($opt['content_disposition'])) + $disposition = $opt['content_disposition']; + + if ($this->output_name) + $disposition .= "; filename=\"{$this->output_name}\""; + + $headers = array( + 'Content-Type' => $content_type, + 'Content-Disposition' => $disposition, + 'Pragma' => 'public', + 'Cache-Control' => 'public, must-revalidate', + 'Content-Transfer-Encoding' => 'binary', + ); + + foreach ($headers as $key => $val) + header("$key: $val"); + } + + # + # Send string, sending HTTP headers if necessary. + # + private function send($str) { + if ($this->need_headers) + $this->send_http_headers(); + $this->need_headers = false; + + echo $str; + } + + # + # Convert a UNIX timestamp to a DOS timestamp. + # + function dostime($when = 0) { + # get date array for timestamp + $d = getdate($when); + + # set lower-bound on dates + if ($d['year'] < 1980) { + $d = array('year' => 1980, 'mon' => 1, 'mday' => 1, + 'hours' => 0, 'minutes' => 0, 'seconds' => 0); + } + + # remove extra years from 1980 + $d['year'] -= 1980; + + # return date string + return ($d['year'] << 25) | ($d['mon'] << 21) | ($d['mday'] << 16) | + ($d['hours'] << 11) | ($d['minutes'] << 5) | ($d['seconds'] >> 1); + } + + # + # Create a format string and argument list for pack(), then call + # pack() and return the result. + # + function pack_fields($fields) { + list ($fmt, $args) = array('', array()); + + # populate format string and argument list + foreach ($fields as $field) { + $fmt .= $field[0]; + $args[] = $field[1]; + } + + # prepend format string to argument list + array_unshift($args, $fmt); + + # build output string from header and compressed data + return call_user_func_array('pack', $args); + } +}; + +?> diff --git a/src/IDF/Scm.php b/src/IDF/Scm.php index 1496974..60f010a 100644 --- a/src/IDF/Scm.php +++ b/src/IDF/Scm.php @@ -393,13 +393,13 @@ class IDF_Scm } /** - * Generate the command to create a zip archive at a given commit. + * Generate a zip archive at a given commit, wrapped in a HTTP response, suitable for pushing to client. * * @param string Commit * @param string Prefix ('repository/') - * @return string Command + * @return Pluf_HTTP_Response The HTTP Response containing the zip archive */ - public function getArchiveCommand($commit, $prefix='repository/') + public function getArchiveStream($commit, $prefix='repository/') { throw new Pluf_Exception_NotImplemented(); } diff --git a/src/IDF/Scm/Git.php b/src/IDF/Scm/Git.php index 4a3b308..8cae0be 100644 --- a/src/IDF/Scm/Git.php +++ b/src/IDF/Scm/Git.php @@ -547,13 +547,14 @@ class IDF_Scm_Git extends IDF_Scm return $res; } - public function getArchiveCommand($commit, $prefix='repository/') + public function getArchiveStream($commit, $prefix='repository/') { - return sprintf(Pluf::f('idf_exec_cmd_prefix', ''). + $cmd = sprintf(Pluf::f('idf_exec_cmd_prefix', ''). 'GIT_DIR=%s '.Pluf::f('git_path', 'git').' archive --format=zip --prefix=%s %s', escapeshellarg($this->repo), escapeshellarg($prefix), escapeshellarg($commit)); + return new Pluf_HTTP_Response_CommandPassThru($cmd, 'application/x-zip'); } /* @@ -806,4 +807,4 @@ class IDF_Scm_Git extends IDF_Scm } return false; } -} \ No newline at end of file +} diff --git a/src/IDF/Scm/Mercurial.php b/src/IDF/Scm/Mercurial.php index ac66464..4e51bc2 100644 --- a/src/IDF/Scm/Mercurial.php +++ b/src/IDF/Scm/Mercurial.php @@ -449,17 +449,18 @@ class IDF_Scm_Mercurial extends IDF_Scm } /** - * Generate the command to create a zip archive at a given commit. + * Generate a zip archive at a given commit. * * @param string Commit * @param string Prefix ('git-repo-dump') - * @return string Command + * @return Pluf_HTTP_Response The HTTP response containing the zip archive */ - public function getArchiveCommand($commit, $prefix='') + protected function getArchiveStream($commit, $prefix='') { - return sprintf(Pluf::f('idf_exec_cmd_prefix', ''). + $cmd = sprintf(Pluf::f('idf_exec_cmd_prefix', ''). Pluf::f('hg_path', 'hg').' archive --type=zip -R %s -r %s -', escapeshellarg($this->repo), escapeshellarg($commit)); + return new Pluf_HTTP_Response_CommandPassThru($cmd, 'application/x-zip'); } } diff --git a/src/IDF/Scm/Monotone.php b/src/IDF/Scm/Monotone.php index 74c6b78..c48b613 100644 --- a/src/IDF/Scm/Monotone.php +++ b/src/IDF/Scm/Monotone.php @@ -21,8 +21,8 @@ # # ***** END LICENSE BLOCK ***** */ -require_once(dirname(__FILE__) . "/Monotone/Stdio.php"); -require_once(dirname(__FILE__) . "/Monotone/BasicIO.php"); +//require_once(dirname(__FILE__) . "/Monotone/Stdio.php"); +//require_once(dirname(__FILE__) . "/Monotone/BasicIO.php"); /** * Monotone scm class @@ -135,6 +135,20 @@ class IDF_Scm_Monotone extends IDF_Scm return $branch; } + /** + * @see IDF_Scm::getArchiveStream + */ + public function getArchiveStream($commit, $prefix='repository/') + { + $revs = $this->_resolveSelector($commit); + // sanity: this should actually not happen, because the + // revision is validated before already + if (count($revs) == 0) { + return new Pluf_HTTP_Response_NotFound(); + } + return new IDF_Scm_Monotone_ZipRender($this->stdio, $revs[0]); + } + /** * expands a selector or a partial revision id to zero, one or * multiple 40 byte revision ids diff --git a/src/IDF/Scm/Monotone/ZipRender.php b/src/IDF/Scm/Monotone/ZipRender.php new file mode 100644 index 0000000..41f9f7d --- /dev/null +++ b/src/IDF/Scm/Monotone/ZipRender.php @@ -0,0 +1,78 @@ +stdio = $stdio; + $this->revision = $revision; + } + + /** + * Render a response object. + */ + function render($output_body=true) + { + $this->outputHeaders(); + + if ($output_body) { + $manifest = $this->stdio->exec(array('get_manifest_of', $this->revision)); + $stanzas = IDF_Scm_Monotone_BasicIO::parse($manifest); + + $zip = new ZipStream(); + + foreach ($stanzas as $stanza) { + if ($stanza[0]['key'] != 'file') + continue; + $content = $this->stdio->exec(array('get_file', $stanza[1]['hash'])); + $zip->add_file($stanza[0]['values'][0], $content); + } + + $zip->finish(); + } + } +} diff --git a/src/IDF/Views/Source.php b/src/IDF/Views/Source.php index 357a38a..23edb3f 100644 --- a/src/IDF/Views/Source.php +++ b/src/IDF/Views/Source.php @@ -434,8 +434,7 @@ class IDF_Views_Source $commit = trim($match[2]); $scm = IDF_Scm::get($request->project); $base = $request->project->shortname.'-'.$commit; - $cmd = $scm->getArchiveCommand($commit, $base.'/'); - $rep = new Pluf_HTTP_Response_CommandPassThru($cmd, 'application/x-zip'); + $rep = $scm->getArchiveStream($commit, $base.'/'); $rep->headers['Content-Transfer-Encoding'] = 'binary'; $rep->headers['Content-Disposition'] = 'attachment; filename="'.$base.'.zip"'; return $rep; diff --git a/src/IDF/templates/idf/source/mtn/tree.html b/src/IDF/templates/idf/source/mtn/tree.html index 20b7622..3851c1a 100644 --- a/src/IDF/templates/idf/source/mtn/tree.html +++ b/src/IDF/templates/idf/source/mtn/tree.html @@ -48,7 +48,7 @@ {aurl 'url', 'IDF_Views_Source::download', array($project.shortname, $commit)}

-{* {trans 'Archive'} {trans 'Download this version'} {trans 'or'} *} +{trans 'Archive'} {trans 'Download this version'} {trans 'or'} mtn clone {$project.getSourceAccessUrl($user, $commit)} {trans 'Help'}

From 039ae01cfaadf6a70df3e5d013523e3f89ba4f76 Mon Sep 17 00:00:00 2001 From: Thomas Keller Date: Sat, 30 Oct 2010 22:09:55 +0000 Subject: [PATCH 04/13] Use an even smarter way of including additional resources for monotone by using a wildcard dir matcher and document this accordingly. --- doc/syncmonotone.mdtext | 8 ++++---- src/IDF/Plugin/SyncMonotone/monotonerc-auth.tpl | 13 +++++++++++-- src/IDF/Plugin/SyncMonotone/monotonerc-noauth.tpl | 12 ++++++++++-- 3 files changed, 25 insertions(+), 8 deletions(-) diff --git a/doc/syncmonotone.mdtext b/doc/syncmonotone.mdtext index 7ca1d11..dd7629b 100644 --- a/doc/syncmonotone.mdtext +++ b/doc/syncmonotone.mdtext @@ -199,7 +199,7 @@ somewhere else for backup purposes. The monotone source tree already comes with [many example scripts and hooks](http://code.monotone.ca/p/monotone/source/tree/h:net.venge.monotone/contrib) which serve these purposes, after only little additional configuration. -The usher/indefero-controlled setup automatically looks for a file called -`hooks.lua` in the project's base directory (configured via $cfg['mtn_repositories']) -and this is the ideal place to put or link these additional lua sources. - +The usher/indefero-controlled setup automatically looks for *.lua files +in a directory called `hooks.d` right under the project's base directory +(configured via $cfg['mtn_repositories']) and this is the ideal place to +put or link these additional lua sources. diff --git a/src/IDF/Plugin/SyncMonotone/monotonerc-auth.tpl b/src/IDF/Plugin/SyncMonotone/monotonerc-auth.tpl index 7e5ff8c..c59d58f 100644 --- a/src/IDF/Plugin/SyncMonotone/monotonerc-auth.tpl +++ b/src/IDF/Plugin/SyncMonotone/monotonerc-auth.tpl @@ -65,6 +65,15 @@ push_hook_functions({ }) -- --- Load additional local hooks, in case they exist +-- Load local hooks if they exist. -- -include(get_confdir() .. "/hooks.lua") +-- The way this is supposed to work is that hooks.d can contain symbolic +-- links to lua scripts. These links MUST have the extension .lua +-- If the script needs some configuration, a corresponding file with +-- the extension .conf is the right spot. +-- +-- First load the configuration of the hooks, if applicable +includedirpattern(get_confdir() .. "/hooks.d/", "*.conf") +-- Then load the hooks themselves +includedirpattern(get_confdir() .. "/hooks.d/", "*.lua") + diff --git a/src/IDF/Plugin/SyncMonotone/monotonerc-noauth.tpl b/src/IDF/Plugin/SyncMonotone/monotonerc-noauth.tpl index e59aa04..3ad79ba 100644 --- a/src/IDF/Plugin/SyncMonotone/monotonerc-noauth.tpl +++ b/src/IDF/Plugin/SyncMonotone/monotonerc-noauth.tpl @@ -79,6 +79,14 @@ push_hook_functions({ }) -- --- Load additional local hooks, in case they exist +-- Load local hooks if they exist. -- -include(get_confdir() .. "/hooks.lua") +-- The way this is supposed to work is that hooks.d can contain symbolic +-- links to lua scripts. These links MUST have the extension .lua +-- If the script needs some configuration, a corresponding file with +-- the extension .conf is the right spot. +-- +-- First load the configuration of the hooks, if applicable +includedirpattern(get_confdir() .. "/hooks.d/", "*.conf") +-- Then load the hooks themselves +includedirpattern(get_confdir() .. "/hooks.d/", "*.lua") From c0ccdc768a4a5b49aeef0ccc385056ddd4ede599 Mon Sep 17 00:00:00 2001 From: Thomas Keller Date: Sun, 31 Oct 2010 18:18:20 +0100 Subject: [PATCH 05/13] add a couple of file extensions which are supported by our in-tree version of prettyfy (closes issue 490) --- src/IDF/Views/Source.php | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/src/IDF/Views/Source.php b/src/IDF/Views/Source.php index 23edb3f..f91c29b 100644 --- a/src/IDF/Views/Source.php +++ b/src/IDF/Views/Source.php @@ -35,11 +35,11 @@ class IDF_Views_Source * Extension supported by the syntax highlighter. */ public static $supportedExtenstions = array( - 'ascx', 'ashx', 'asmx', 'aspx', 'browser', 'bsh', 'c', 'cc', - 'config', 'cpp', 'cs', 'csh', 'csproj', 'css', 'cv', 'cyc', - 'html', 'html', 'java', 'js', 'master', 'pas', 'perl', 'php', 'pl', - 'pm', 'py', 'rb', 'sh', 'sitemap', 'skin', 'sln', 'svc', 'vala', - 'vb', 'vbproj', 'wsdl', 'xhtml', 'xml', 'xsd', 'xsl', 'xslt'); + 'ascx', 'ashx', 'asmx', 'aspx', 'browser', 'bsh', 'c', 'cl', 'cc', + 'config', 'cpp', 'cs', 'csh', 'csproj', 'css', 'cv', 'cyc', 'el', 'fs', 'hs', + 'html', 'html', 'java', 'js', 'lisp', 'master', 'pas', 'perl', 'php', 'pl', + 'pm', 'py', 'rb', 'scm', 'sh', 'sitemap', 'skin', 'sln', 'svc', 'vala', + 'vb', 'vbproj', 'vbs', 'wsdl', 'xhtml', 'xml', 'xsd', 'xsl', 'xslt'); /** * Display help on how to checkout etc. From e776fc0713ae42c888dca99de2f61a90b34a23b5 Mon Sep 17 00:00:00 2001 From: Thomas Keller Date: Sun, 31 Oct 2010 18:26:31 +0100 Subject: [PATCH 06/13] Switch doctype from html 4.01 strict to xhtml 1.0 transitional, we largely ignored the former with xml-like constructs either (closes issue 511). --- src/IDF/templates/idf/base-full.html | 3 ++- src/IDF/templates/idf/base-simple.html | 3 ++- src/IDF/templates/idf/base.html | 3 ++- src/IDF/templates/idf/gadmin/base.html | 3 ++- 4 files changed, 8 insertions(+), 4 deletions(-) diff --git a/src/IDF/templates/idf/base-full.html b/src/IDF/templates/idf/base-full.html index 23b5863..e0bb337 100644 --- a/src/IDF/templates/idf/base-full.html +++ b/src/IDF/templates/idf/base-full.html @@ -1,4 +1,5 @@ - + {* # ***** BEGIN LICENSE BLOCK ***** # This file is part of InDefero, an open source project management application. diff --git a/src/IDF/templates/idf/base-simple.html b/src/IDF/templates/idf/base-simple.html index 98dd8d1..27e6a5c 100644 --- a/src/IDF/templates/idf/base-simple.html +++ b/src/IDF/templates/idf/base-simple.html @@ -1,4 +1,5 @@ - + {* # ***** BEGIN LICENSE BLOCK ***** # This file is part of InDefero, an open source project management application. diff --git a/src/IDF/templates/idf/base.html b/src/IDF/templates/idf/base.html index 772bbd5..91af76a 100644 --- a/src/IDF/templates/idf/base.html +++ b/src/IDF/templates/idf/base.html @@ -1,4 +1,5 @@ - + {* # ***** BEGIN LICENSE BLOCK ***** # This file is part of InDefero, an open source project management application. diff --git a/src/IDF/templates/idf/gadmin/base.html b/src/IDF/templates/idf/gadmin/base.html index b68a99d..15e830d 100644 --- a/src/IDF/templates/idf/gadmin/base.html +++ b/src/IDF/templates/idf/gadmin/base.html @@ -1,4 +1,5 @@ - + {* # ***** BEGIN LICENSE BLOCK ***** # This file is part of InDefero, an open source project management application. From 8993d2988b9c2ea5a01b03f841a29bc530d5cf20 Mon Sep 17 00:00:00 2001 From: Thomas Keller Date: Sun, 31 Oct 2010 23:18:35 +0000 Subject: [PATCH 07/13] Pick initial issue type and priority from the particular first item of the predefined issue labels list (thanks Jakub Vitak, closes issue 556) --- src/IDF/Form/IssueCreate.php | 29 +++++++++++++++++-- src/IDF/Form/IssueTrackingConf.php | 1 + .../templates/idf/admin/issue-tracking.html | 3 +- 3 files changed, 30 insertions(+), 3 deletions(-) diff --git a/src/IDF/Form/IssueCreate.php b/src/IDF/Form/IssueCreate.php index 3c38e7b..514be54 100644 --- a/src/IDF/Form/IssueCreate.php +++ b/src/IDF/Form/IssueCreate.php @@ -108,14 +108,39 @@ class IDF_Form_IssueCreate extends Pluf_Form 'size' => 15, ), )); + + /* + * get predefined tags for issues from current project + * + * first Type:<...> and Priority:<...> will be used + * + */ + $predefined = preg_split("/[\r\n]+/", $extra['project']->getConf()->getVal( + 'labels_issue_predefined' + )); + $predefined_type = 'Type:Defect'; + foreach ($predefined as $tag) { + if (strpos($tag, 'Type:') === 0) { + $predefined_type = $tag; + break; + } + } + $predefined_priority = 'Priority:Medium'; + foreach ($predefined as $tag) { + if (strpos($tag, 'Priority:') === 0) { + $predefined_priority = $tag; + break; + } + } + for ($i=1;$i<7;$i++) { $initial = ''; switch ($i) { case 1: - $initial = 'Type:Defect'; + $initial = $predefined_type; break; case 2: - $initial = 'Priority:Medium'; + $initial = $predefined_priority; break; } $this->fields['label'.$i] = new Pluf_Form_Field_Varchar( diff --git a/src/IDF/Form/IssueTrackingConf.php b/src/IDF/Form/IssueTrackingConf.php index 0aa4f59..cb0d17b 100644 --- a/src/IDF/Form/IssueTrackingConf.php +++ b/src/IDF/Form/IssueTrackingConf.php @@ -105,6 +105,7 @@ Maintainability = Hinders future changes'; array('required' => true, 'label' => __('Predefined issue labels'), 'initial' => self::init_predefined, + 'help_text' => __('The first "Type:" and "Priority:" entries found in this list are automatically chosen as defaults for new issues.'), 'widget_attrs' => array('rows' => 7, 'cols' => 75), 'widget' => 'Pluf_Form_Widget_TextareaInput', diff --git a/src/IDF/templates/idf/admin/issue-tracking.html b/src/IDF/templates/idf/admin/issue-tracking.html index fb5766c..057b3c7 100644 --- a/src/IDF/templates/idf/admin/issue-tracking.html +++ b/src/IDF/templates/idf/admin/issue-tracking.html @@ -24,7 +24,8 @@ {$form.f.labels_issue_predefined.labelTag}:
{if $form.f.labels_issue_predefined.errors}{$form.f.labels_issue_predefined.fieldErrors}{/if} -{$form.f.labels_issue_predefined|unsafe} +{$form.f.labels_issue_predefined|unsafe}
+{$form.f.labels_issue_predefined.help_text} From d08fee129b9d90efb667d7b9831e1f18d95a85ff Mon Sep 17 00:00:00 2001 From: Thomas Keller Date: Tue, 9 Nov 2010 00:11:27 +0000 Subject: [PATCH 08/13] fixed two notices which lead to corrupt zip archives --- contrib/zipstream-php-0.2.2/zipstream.php | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/contrib/zipstream-php-0.2.2/zipstream.php b/contrib/zipstream-php-0.2.2/zipstream.php index 37a6046..7d821c7 100644 --- a/contrib/zipstream-php-0.2.2/zipstream.php +++ b/contrib/zipstream-php-0.2.2/zipstream.php @@ -407,7 +407,7 @@ class ZipStream { list ($name, $opt, $meth, $crc, $zlen, $len, $ofs) = $args; # get attributes - $comment = $opt['comment'] ? $opt['comment'] : ''; + $comment = isset($opt['comment']) ? $opt['comment'] : ''; # get dos timestamp $dts = $this->dostime($opt['time']); @@ -450,7 +450,7 @@ class ZipStream { # grab comment (if specified) $comment = ''; - if ($opt && $opt['comment']) + if ($opt && isset($opt['comment'])) $comment = $opt['comment']; $fields = array( # (from V,F of APPNOTE.TXT) From 470a961a8025f736830bf39dea88f4d6c87a85e7 Mon Sep 17 00:00:00 2001 From: Thomas Keller Date: Wed, 17 Nov 2010 00:06:18 +0100 Subject: [PATCH 09/13] Add syntax highlighter support for h, hh and hpp (fixes issue 567) --- src/IDF/Views/Source.php | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/src/IDF/Views/Source.php b/src/IDF/Views/Source.php index f91c29b..5817b22 100644 --- a/src/IDF/Views/Source.php +++ b/src/IDF/Views/Source.php @@ -36,10 +36,11 @@ class IDF_Views_Source */ public static $supportedExtenstions = array( 'ascx', 'ashx', 'asmx', 'aspx', 'browser', 'bsh', 'c', 'cl', 'cc', - 'config', 'cpp', 'cs', 'csh', 'csproj', 'css', 'cv', 'cyc', 'el', 'fs', 'hs', - 'html', 'html', 'java', 'js', 'lisp', 'master', 'pas', 'perl', 'php', 'pl', - 'pm', 'py', 'rb', 'scm', 'sh', 'sitemap', 'skin', 'sln', 'svc', 'vala', - 'vb', 'vbproj', 'vbs', 'wsdl', 'xhtml', 'xml', 'xsd', 'xsl', 'xslt'); + 'config', 'cpp', 'cs', 'csh', 'csproj', 'css', 'cv', 'cyc', 'el', 'fs', + 'h', 'hh', 'hpp', 'hs', 'html', 'html', 'java', 'js', 'lisp', 'master', + 'pas', 'perl', 'php', 'pl', 'pm', 'py', 'rb', 'scm', 'sh', 'sitemap', + 'skin', 'sln', 'svc', 'vala', 'vb', 'vbproj', 'vbs', 'wsdl', 'xhtml', + 'xml', 'xsd', 'xsl', 'xslt'); /** * Display help on how to checkout etc. From e6f255bc56808c8a4e8926124a37c211822181f6 Mon Sep 17 00:00:00 2001 From: Thomas Keller Date: Wed, 17 Nov 2010 00:47:52 +0100 Subject: [PATCH 10/13] Code style; wider input for monotone branch name --- src/IDF/Form/Admin/ProjectCreate.php | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/src/IDF/Form/Admin/ProjectCreate.php b/src/IDF/Form/Admin/ProjectCreate.php index f6b75a8..5b823db 100644 --- a/src/IDF/Form/Admin/ProjectCreate.php +++ b/src/IDF/Form/Admin/ProjectCreate.php @@ -66,7 +66,7 @@ class IDF_Form_Admin_ProjectCreate extends Pluf_Form $this->fields['shortdesc'] = new Pluf_Form_Field_Varchar( array('required' => true, - 'label' => __('short description'), + 'label' => __('Short description'), 'help_text' => __('A one line description of the project.'), 'initial' => '', 'widget_attrs' => array('size' => '35'), @@ -105,6 +105,7 @@ class IDF_Form_Admin_ProjectCreate extends Pluf_Form array('required' => false, 'label' => __('Master branch'), 'initial' => '', + 'widget_attrs' => array('size' => '35'), 'help_text' => __('This should be a world-wide unique identifier for your project. A reverse DNS notation like "com.my-domain.my-project" is a good idea.'), )); @@ -203,7 +204,7 @@ class IDF_Form_Admin_ProjectCreate extends Pluf_Form } $sql = new Pluf_SQL('vkey=%s AND vdesc=%s', - array("mtn_master_branch", $mtn_master_branch)); + array('mtn_master_branch', $mtn_master_branch)); $l = Pluf::factory('IDF_Conf')->getList(array('filter'=>$sql->gen())); if ($l->count() > 0) { throw new Pluf_Form_Invalid(__( From b4bc6abaceea8c97bfb19bba424902caa5f8145c Mon Sep 17 00:00:00 2001 From: Thomas Keller Date: Wed, 17 Nov 2010 00:47:55 +0100 Subject: [PATCH 11/13] Make the monotone master branch editable on forge level at least to make it possible to switch the default project branch (partially fixes issue 560) --- src/IDF/Form/Admin/ProjectUpdate.php | 47 ++++++++++++++++++- src/IDF/Views/Project.php | 6 +-- .../templates/idf/gadmin/projects/update.html | 11 ++++- 3 files changed, 58 insertions(+), 6 deletions(-) diff --git a/src/IDF/Form/Admin/ProjectUpdate.php b/src/IDF/Form/Admin/ProjectUpdate.php index 4157851..e15e029 100644 --- a/src/IDF/Form/Admin/ProjectUpdate.php +++ b/src/IDF/Form/Admin/ProjectUpdate.php @@ -37,6 +37,8 @@ class IDF_Form_Admin_ProjectUpdate extends Pluf_Form { $this->project = $extra['project']; $members = $this->project->getMembershipData('string'); + $conf = $this->project->getConf(); + $this->fields['name'] = new Pluf_Form_Field_Varchar( array('required' => true, 'label' => __('Name'), @@ -45,12 +47,22 @@ class IDF_Form_Admin_ProjectUpdate extends Pluf_Form $this->fields['shortdesc'] = new Pluf_Form_Field_Varchar( array('required' => true, - 'label' => __('short description'), + 'label' => __('Short description'), 'help_text' => __('A one line description of the project.'), 'initial' => $this->project->shortdesc, 'widget_attrs' => array('size' => '35'), )); + if ($this->project->getConf()->getVal('scm') == 'mtn') { + $this->fields['mtn_master_branch'] = new Pluf_Form_Field_Varchar( + array('required' => false, + 'label' => __('Master branch'), + 'initial' => $conf->getVal('mtn_master_branch'), + 'widget_attrs' => array('size' => '35'), + 'help_text' => __('This should be a world-wide unique identifier for your project. A reverse DNS notation like "com.my-domain.my-project" is a good idea.'), + )); + } + $this->fields['owners'] = new Pluf_Form_Field_Varchar( array('required' => false, 'label' => __('Project owners'), @@ -69,6 +81,30 @@ class IDF_Form_Admin_ProjectUpdate extends Pluf_Form )); } + public function clean_mtn_master_branch() + { + $mtn_master_branch = mb_strtolower($this->cleaned_data['mtn_master_branch']); + if (!preg_match('/^([\w\d]+([-][\w\d]+)*)(\.[\w\d]+([-][\w\d]+)*)*$/', + $mtn_master_branch)) { + throw new Pluf_Form_Invalid(__( + 'The master branch is empty or contains illegal characters, '. + 'please use only letters, digits, dashs and dots as separators.' + )); + } + + $sql = new Pluf_SQL('vkey=%s AND vdesc=%s AND project!=%s', + array('mtn_master_branch', $mtn_master_branch, + (string)$this->project->id)); + $l = Pluf::factory('IDF_Conf')->getList(array('filter'=>$sql->gen())); + if ($l->count() > 0) { + throw new Pluf_Form_Invalid(__( + 'This master branch is already used. Please select another one.' + )); + } + + return $mtn_master_branch; + } + public function clean_owners() { return IDF_Form_MembersConf::checkBadLogins($this->cleaned_data['owners']); @@ -84,12 +120,19 @@ class IDF_Form_Admin_ProjectUpdate extends Pluf_Form if (!$this->isValid()) { throw new Exception(__('Cannot save the model from an invalid form.')); } - IDF_Form_MembersConf::updateMemberships($this->project, + IDF_Form_MembersConf::updateMemberships($this->project, $this->cleaned_data); $this->project->membershipsUpdated(); $this->project->name = $this->cleaned_data['name']; $this->project->shortdesc = $this->cleaned_data['shortdesc']; $this->project->update(); + + $keys = array('mtn_master_branch'); + foreach ($keys as $key) { + if (!empty($this->cleaned_data[$key])) { + $this->project->getConf()->setVal($key, $this->cleaned_data[$key]); + } + } } } diff --git a/src/IDF/Views/Project.php b/src/IDF/Views/Project.php index 20854d9..0ebcf69 100644 --- a/src/IDF/Views/Project.php +++ b/src/IDF/Views/Project.php @@ -128,7 +128,7 @@ class IDF_Views_Project public function timeline($request, $match) { $prj = $request->project; - + $model_filter = @$match[2]; $all_model_filters = self::getAvailableModelFilters(); if (!array_key_exists($model_filter, $all_model_filters)) { @@ -156,7 +156,7 @@ class IDF_Views_Project $pag->items_per_page = 20; $pag->no_results_text = __('No changes were found.'); $pag->setFromRequest($request); - + if (!$request->user->isAnonymous() and $prj->isRestricted()) { $feedurl = Pluf_HTTP_URL_urlForView('idf_project_timeline_feed_auth', array($prj->shortname, @@ -198,7 +198,7 @@ class IDF_Views_Project $model_filter = 'all'; } $title = $all_model_filters[$model_filter]; - + $classes = self::determineModelClasses($request, $model_filter); $sqls = sprintf('model_class IN (%s)', implode(', ', $classes)); $sql = new Pluf_SQL('project=%s AND '.$sqls, array($prj->id)); diff --git a/src/IDF/templates/idf/gadmin/projects/update.html b/src/IDF/templates/idf/gadmin/projects/update.html index e6a40eb..132336a 100644 --- a/src/IDF/templates/idf/gadmin/projects/update.html +++ b/src/IDF/templates/idf/gadmin/projects/update.html @@ -25,6 +25,15 @@ {$form.f.shortdesc.help_text} +{if $project.getConf().getVal('scm') == 'mtn'} + +{$form.f.mtn_master_branch.labelTag}: +{if $form.f.mtn_master_branch.errors}{$form.f.mtn_master_branch.fieldErrors}{/if} +{$form.f.mtn_master_branch|unsafe}
+{$form.f.mtn_master_branch.help_text} + + +{/if} {$form.f.owners.labelTag}: @@ -44,7 +53,7 @@   {aurl 'url', 'IDF_Views_Admin::projectDelete', array($project.id)} {* float left is a fix for Firefox < 3.5 *} - + | {trans 'Cancel'} {if $isAdmin} {trans 'Trash'} {trans 'Delete this project'}
{trans 'You will be asked to confirm.'}{/if} From ad15b13f7ebc6925fd38707160df5e1285c75a80 Mon Sep 17 00:00:00 2001 From: Thomas Keller Date: Wed, 17 Nov 2010 01:02:43 +0100 Subject: [PATCH 12/13] Add a little Q&A section with details how to handle suspended branches and default branch name changes. --- doc/syncmonotone.mdtext | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/doc/syncmonotone.mdtext b/doc/syncmonotone.mdtext index dd7629b..7355810 100644 --- a/doc/syncmonotone.mdtext +++ b/doc/syncmonotone.mdtext @@ -201,5 +201,24 @@ which serve these purposes, after only little additional configuration. The usher/indefero-controlled setup automatically looks for *.lua files in a directory called `hooks.d` right under the project's base directory -(configured via $cfg['mtn_repositories']) and this is the ideal place to +(configured via $cfg['mtn_repositories']) and this is the ideal place to put or link these additional lua sources. + +## Q&A + +### I pushed a branch to my server, but it does not show up in IDF. Whats wrong? + +Check if the heads of your branch are not suspended, i.e. do not carry a +`suspend` certificate. This usually hides the branch and all of its history +from monotone's eyes and therefor also from indefero. You can either choose +to "unsuspend" the branch simply by committing and pushing another head or +by letting monotone ignore all suspend certs. For the latter, its usually +enough to add `--ignore-suspend-certs` to the list of options in `$cfg['mtn_opts']`. + +### I want to display another default branch when I click the "Source" tab. How can I do that? + +Let the forge admin know the new master branch for your project. He is able +to change that quickly. Depending on the backend / server setup this might +also require some changes in the usher configuration, but only if usher +recognizes and proxies your database on a branch name level. + From 70e8d1242032c410aa3033b34cbd2f5cac3376c0 Mon Sep 17 00:00:00 2001 From: Thomas Keller Date: Wed, 17 Nov 2010 01:53:17 +0100 Subject: [PATCH 13/13] Output the branch a particular commit is on; this is easy for mercurial and monotone, but slightly harder till impossible to do properly for git and svn. Please review and eventually adapt the code to make it work better (partially fixes issue 450) --- src/IDF/Scm/Git.php | 2 ++ src/IDF/Scm/Mercurial.php | 3 +++ src/IDF/Scm/Monotone.php | 12 +++++++----- src/IDF/Scm/Svn.php | 1 + src/IDF/templates/idf/source/commit.html | 3 +++ 5 files changed, 16 insertions(+), 5 deletions(-) diff --git a/src/IDF/Scm/Git.php b/src/IDF/Scm/Git.php index 8cae0be..83a29b0 100644 --- a/src/IDF/Scm/Git.php +++ b/src/IDF/Scm/Git.php @@ -436,6 +436,8 @@ class IDF_Scm_Git extends IDF_Scm $out = self::parseLog($out); $out[0]->changes = ''; } + + $out[0]['branch'] = $this->inBranches($commit, null); return $out[0]; } diff --git a/src/IDF/Scm/Mercurial.php b/src/IDF/Scm/Mercurial.php index 4e51bc2..ad2f383 100644 --- a/src/IDF/Scm/Mercurial.php +++ b/src/IDF/Scm/Mercurial.php @@ -429,6 +429,8 @@ class IDF_Scm_Mercurial extends IDF_Scm $c['author'] = $match[2]; } elseif ($match[1] == 'summary') { $c['title'] = $match[2]; + } elseif ($match[1] == 'branch') { + $c['branch'] = $match[2]; } else { $c[$match[1]] = trim($match[2]); } @@ -443,6 +445,7 @@ class IDF_Scm_Mercurial extends IDF_Scm } } $c['tree'] = !empty($c['commit']) ? trim($c['commit']) : ''; + $c['branch'] = empty($c['branch']) ? 'default' : $c['branch']; $c['full_message'] = !empty($c['full_message']) ? trim($c['full_message']) : ''; $res[] = (object) $c; return $res; diff --git a/src/IDF/Scm/Monotone.php b/src/IDF/Scm/Monotone.php index c48b613..f001236 100644 --- a/src/IDF/Scm/Monotone.php +++ b/src/IDF/Scm/Monotone.php @@ -141,12 +141,12 @@ class IDF_Scm_Monotone extends IDF_Scm public function getArchiveStream($commit, $prefix='repository/') { $revs = $this->_resolveSelector($commit); - // sanity: this should actually not happen, because the + // sanity: this should actually not happen, because the // revision is validated before already if (count($revs) == 0) { return new Pluf_HTTP_Response_NotFound(); } - return new IDF_Scm_Monotone_ZipRender($this->stdio, $revs[0]); + return new IDF_Scm_Monotone_ZipRender($this->stdio, $revs[0]); } /** @@ -174,7 +174,7 @@ class IDF_Scm_Monotone extends IDF_Scm $cache = Pluf_Cache::factory(); $cachekey = 'mtn-plugin-certs-for-rev-' . $rev; $certs = $cache->get($cachekey); - + if ($certs === null) { $out = $this->stdio->exec(array('certs', $rev)); @@ -545,7 +545,7 @@ class IDF_Scm_Monotone extends IDF_Scm if ($stanza[0]['values'][0] != $file) continue; - + $file = $this->_fillFileEntry($stanza); return (object) $file; } @@ -623,7 +623,9 @@ class IDF_Scm_Monotone extends IDF_Scm $res['title'] = $split[0]; $res['full_message'] = (isset($split[1])) ? trim($split[1]) : ''; + $res['branch'] = implode(', ', $certs['branch']); $res['commit'] = $revs[0]; + $res['changes'] = ($getdiff) ? $this->_getDiff($revs[0]) : ''; return (object) $res; @@ -682,7 +684,7 @@ class IDF_Scm_Monotone extends IDF_Scm __("revision %s has no branch cert - cannot start ". "logging from this revision"), $rev )); - } + } $initialBranches = $certs['branch']; } diff --git a/src/IDF/Scm/Svn.php b/src/IDF/Scm/Svn.php index fdbc340..fb770b8 100644 --- a/src/IDF/Scm/Svn.php +++ b/src/IDF/Scm/Svn.php @@ -415,6 +415,7 @@ class IDF_Scm_Svn extends IDF_Scm $res['commit'] = (string) $xml->logentry['revision']; $res['changes'] = ($getdiff) ? $this->getDiff($commit) : ''; $res['tree'] = ''; + $res['branch'] = ''; return (object) $res; } diff --git a/src/IDF/templates/idf/source/commit.html b/src/IDF/templates/idf/source/commit.html index c9c1051..c04ab80 100644 --- a/src/IDF/templates/idf/source/commit.html +++ b/src/IDF/templates/idf/source/commit.html @@ -10,6 +10,9 @@ {trans 'Author:'}{showuser $rcommit.get_author(), $request, $cobject.author} +{trans 'Branch:'}{$cobject.branch} + + {trans 'Commit:'}{$cobject.commit}