fastimport-0.9.8/0000755000175000017500000000000013264642537014512 5ustar jelmerjelmer00000000000000fastimport-0.9.8/AUTHORS0000644000175000017500000000047712736225770015571 0ustar jelmerjelmer00000000000000Ian Clatworthy wrote bzr-fastimport, which included a lot of generic code for parsing and generating fastimport streams. Jelmer Vernooij split out into its own separate package (python-fastimport) so it can be used by other projects, and is its current maintainer. Félix Mattrat ported python-fastimport to Python 3. fastimport-0.9.8/setup.py0000755000175000017500000000226113264642521016221 0ustar jelmerjelmer00000000000000#!/usr/bin/env python from distutils.core import setup version = "0.9.8" setup(name="fastimport", description="VCS fastimport/fastexport parser", version=version, author="Canonical Ltd", author_email="bazaar@lists.canonical.com", maintainer="Jelmer Vernooij", maintainer_email="jelmer@jelmer.uk", license="GNU GPL v2 or later", url="https://github.com/jelmer/python-fastimport", packages=['fastimport', 'fastimport.tests', 'fastimport.processors'], scripts=[ 'bin/fast-import-query', 'bin/fast-import-filter', 'bin/fast-import-info', ], classifiers=[ 'Development Status :: 4 - Beta', 'License :: OSI Approved :: GNU General Public License v2 or later (GPLv2+)', 'Programming Language :: Python :: 2.7', 'Programming Language :: Python :: 3.4', 'Programming Language :: Python :: 3.5', 'Programming Language :: Python :: Implementation :: CPython', 'Programming Language :: Python :: Implementation :: PyPy', 'Operating System :: POSIX', 'Topic :: Software Development :: Version Control', ], ) fastimport-0.9.8/bin/0000755000175000017500000000000013264642537015262 5ustar jelmerjelmer00000000000000fastimport-0.9.8/bin/fast-import-query0000755000175000017500000000446013257467451020626 0ustar jelmerjelmer00000000000000#!/usr/bin/python __doc__ = """Query a fast-import stream displaying selected commands. To specify standard input as the input stream, use a source name of '-'. If the source name ends in '.gz', it is assumed to be compressed in gzip format. To specify a commit to display, give its mark using the --commit-mark option. The commit will be displayed with file-commands included but with inline blobs hidden. To specify the commands to display, use the -C option one or more times. To specify just some fields for a command, use the syntax:: command=field1,... By default, the nominated fields for the nominated commands are displayed tab separated. To see the information in a name:value format, use verbose mode. Note: Binary fields (e.g. data for blobs) are masked out so it is generally safe to view the output in a terminal. :Examples: Show the commit with mark 429:: fast-import-query xxx.fi -m429 Show all the fields of the reset and tag commands:: fast-import-query xxx.fi -Creset -Ctag Show the mark and merge fields of the commit commands:: fast-import-query xxx.fi -Ccommit=mark,merge """ import optparse import sys parser = optparse.OptionParser('fast-import-query [options] SOURCE?') parser.add_option('-v', '--verbose', dest="verbose", action="store_true", help="Be verbose") parser.add_option('-m', '--commit-mark', dest="commit_mark", type=str, help="Mark of the commit to display.") parser.add_option('-C', '--commands', type=str, help="Display fields for these commands.") (opts, args) = parser.parse_args() if len(args) == 0: source_path = "-" elif len(args) == 1: source_path = args[0] else: parser.print_usage() from fastimport.processors import query_processor from fastimport.helpers import defines_to_dict, get_source_stream from fastimport.errors import ParsingError from fastimport import parser params = defines_to_dict(opts.commands) or {} if opts.commit_mark: params['commit-mark'] = opts.commit_mark stream = get_source_stream(source_path) proc = query_processor.QueryProcessor(verbose=opts.verbose, params=params) p = parser.ImportParser(stream, verbose=opts.verbose) try: sys.exit(proc.process(p.iter_commands)) except ParsingError as e: sys.stderr.write("%d: Parse error: %s\n" % (e.lineno, e)) sys.exit(1) fastimport-0.9.8/bin/fast-import-filter0000755000175000017500000000727213257466631020751 0ustar jelmerjelmer00000000000000#!/usr/bin/python __doc__ = """Filter a fast-import stream to include/exclude files & directories. This command is useful for splitting a subdirectory or bunch of files out from a project to create a new project complete with history for just those files. It can also be used to create a new project repository that removes all references to files that should not have been committed, e.g. security-related information (like passwords), commercially sensitive material, files with an incompatible license or large binary files like CD images. To specify standard input as the input stream, use a source name of '-'. If the source name ends in '.gz', it is assumed to be compressed in gzip format. :File/directory filtering: This is supported by the -i and -x options. Excludes take precedence over includes. When filtering out a subdirectory (or file), the new stream uses the subdirectory (or subdirectory containing the file) as the root. As fast-import doesn't know in advance whether a path is a file or directory in the stream, you need to specify a trailing '/' on directories passed to the `--includes option`. If multiple files or directories are given, the new root is the deepest common directory. Note: If a path has been renamed, take care to specify the *original* path name, not the final name that it ends up with. :History rewriting: By default fast-import-filter does quite aggressive history rewriting. Empty commits (or commits which had all their content filtered out) will be removed, and so are the references to commits not included in the stream. Flag --dont-squash-empty-commits reverses this behavior and makes it possible to use fast-import-filter on incremental streams. :Examples: Create a new project from a library (note the trailing / on the directory name of the library):: front-end | fast-import-filter -i lib/xxx/ > xxx.fi fast-import xxx.fi mylibrary.bzr (lib/xxx/foo is now foo) Create a new repository without a sensitive file:: front-end | fast-import-filter -x missile-codes.txt > clean.fi fast-import clean.fi clean.bzr """ import optparse import sys parser = optparse.OptionParser('fast-import-filter [options] SOURCE?') parser.add_option('-v', '--verbose', dest="verbose", action="store_true", help="Be verbose.", default=False) parser.add_option('-i', '--include-paths', dest="include_paths", action="append", type=str, help="Only include commits affecting these paths." " Directories should have a trailing /.") parser.add_option('-x', '--exclude-paths', dest="exclude_paths", type=str, help="Exclude these paths from commits.") parser.add_option('--dont-squash-empty-commits', dest="dont_squash_empty_commits", action="store_true", help="Preserve all commits and links between them", default=False) (opts, args) = parser.parse_args() if len(args) == 0: source_path = "-" elif len(args) == 1: source_path = args[0] else: parser.print_usage() from fastimport.processors import filter_processor params = { 'include_paths': opts.include_paths, 'exclude_paths': opts.exclude_paths, } params['squash_empty_commits'] = (not opts.dont_squash_empty_commits) from fastimport.errors import ParsingError from fastimport import parser from fastimport.helpers import get_source_stream stream = get_source_stream(source_path) proc = filter_processor.FilterProcessor(params=params, verbose=opts.verbose) p = parser.ImportParser(stream, verbose=opts.verbose) try: sys.exit(proc.process(p.iter_commands)) except ParsingError as e: sys.stderr.write("%d: Parse error: %s\n" % (e.lineno, e)) sys.exit(1) fastimport-0.9.8/bin/fast-import-info0000755000175000017500000000305013257467107020404 0ustar jelmerjelmer00000000000000#!/usr/bin/python __doc__ = """Output information about a fast-import stream. This command reads a fast-import stream and outputs statistics and interesting properties about what it finds. When run in verbose mode, the information is output as a configuration file that can be passed to fast-import to assist it in intelligently caching objects. To specify standard input as the input stream, use a source name of '-'. If the source name ends in '.gz', it is assumed to be compressed in gzip format. :Examples: Display statistics about the import stream produced by front-end:: front-end | fast-import-info - Create a hints file for running fast-import on a large repository:: front-end | fast-import-info -v - > front-end.cfg """ import optparse import sys parser = optparse.OptionParser('fast-import-info [options] SOURCE') parser.add_option('-v', '--verbose', dest="verbose", help="Be verbose.") (options, args) = parser.parse_args() if len(args) == 0: source_path = "-" elif len(args) == 1: source_path = args[0] else: parser.print_usage() from fastimport.processors import info_processor from fastimport.errors import ParsingError from fastimport.helpers import get_source_stream from fastimport import parser stream = get_source_stream(source_path) proc = info_processor.InfoProcessor(verbose=options.verbose) p = parser.ImportParser(stream, verbose=options.verbose) try: sys.exit(proc.process(p.iter_commands)) except ParsingError as e: sys.stderr.write("%d: Parse error: %s\n" % (e.lineno, e)) sys.exit(1) fastimport-0.9.8/COPYING0000644000175000017500000004310312705215670015537 0ustar jelmerjelmer00000000000000 GNU GENERAL PUBLIC LICENSE Version 2, June 1991 Copyright (C) 1989, 1991 Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA Everyone is permitted to copy and distribute verbatim copies of this license document, but changing it is not allowed. Preamble The licenses for most software are designed to take away your freedom to share and change it. By contrast, the GNU General Public License is intended to guarantee your freedom to share and change free software--to make sure the software is free for all its users. This General Public License applies to most of the Free Software Foundation's software and to any other program whose authors commit to using it. (Some other Free Software Foundation software is covered by the GNU Lesser General Public License instead.) You can apply it to your programs, too. When we speak of free software, we are referring to freedom, not price. Our General Public Licenses are designed to make sure that you have the freedom to distribute copies of free software (and charge for this service if you wish), that you receive source code or can get it if you want it, that you can change the software or use pieces of it in new free programs; and that you know you can do these things. To protect your rights, we need to make restrictions that forbid anyone to deny you these rights or to ask you to surrender the rights. These restrictions translate to certain responsibilities for you if you distribute copies of the software, or if you modify it. For example, if you distribute copies of such a program, whether gratis or for a fee, you must give the recipients all the rights that you have. You must make sure that they, too, receive or can get the source code. And you must show them these terms so they know their rights. We protect your rights with two steps: (1) copyright the software, and (2) offer you this license which gives you legal permission to copy, distribute and/or modify the software. Also, for each author's protection and ours, we want to make certain that everyone understands that there is no warranty for this free software. If the software is modified by someone else and passed on, we want its recipients to know that what they have is not the original, so that any problems introduced by others will not reflect on the original authors' reputations. Finally, any free program is threatened constantly by software patents. We wish to avoid the danger that redistributors of a free program will individually obtain patent licenses, in effect making the program proprietary. To prevent this, we have made it clear that any patent must be licensed for everyone's free use or not licensed at all. The precise terms and conditions for copying, distribution and modification follow. GNU GENERAL PUBLIC LICENSE TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION 0. This License applies to any program or other work which contains a notice placed by the copyright holder saying it may be distributed under the terms of this General Public License. The "Program", below, refers to any such program or work, and a "work based on the Program" means either the Program or any derivative work under copyright law: that is to say, a work containing the Program or a portion of it, either verbatim or with modifications and/or translated into another language. (Hereinafter, translation is included without limitation in the term "modification".) Each licensee is addressed as "you". Activities other than copying, distribution and modification are not covered by this License; they are outside its scope. The act of running the Program is not restricted, and the output from the Program is covered only if its contents constitute a work based on the Program (independent of having been made by running the Program). Whether that is true depends on what the Program does. 1. You may copy and distribute verbatim copies of the Program's source code as you receive it, in any medium, provided that you conspicuously and appropriately publish on each copy an appropriate copyright notice and disclaimer of warranty; keep intact all the notices that refer to this License and to the absence of any warranty; and give any other recipients of the Program a copy of this License along with the Program. You may charge a fee for the physical act of transferring a copy, and you may at your option offer warranty protection in exchange for a fee. 2. You may modify your copy or copies of the Program or any portion of it, thus forming a work based on the Program, and copy and distribute such modifications or work under the terms of Section 1 above, provided that you also meet all of these conditions: a) You must cause the modified files to carry prominent notices stating that you changed the files and the date of any change. b) You must cause any work that you distribute or publish, that in whole or in part contains or is derived from the Program or any part thereof, to be licensed as a whole at no charge to all third parties under the terms of this License. c) If the modified program normally reads commands interactively when run, you must cause it, when started running for such interactive use in the most ordinary way, to print or display an announcement including an appropriate copyright notice and a notice that there is no warranty (or else, saying that you provide a warranty) and that users may redistribute the program under these conditions, and telling the user how to view a copy of this License. (Exception: if the Program itself is interactive but does not normally print such an announcement, your work based on the Program is not required to print an announcement.) These requirements apply to the modified work as a whole. If identifiable sections of that work are not derived from the Program, and can be reasonably considered independent and separate works in themselves, then this License, and its terms, do not apply to those sections when you distribute them as separate works. But when you distribute the same sections as part of a whole which is a work based on the Program, the distribution of the whole must be on the terms of this License, whose permissions for other licensees extend to the entire whole, and thus to each and every part regardless of who wrote it. Thus, it is not the intent of this section to claim rights or contest your rights to work written entirely by you; rather, the intent is to exercise the right to control the distribution of derivative or collective works based on the Program. In addition, mere aggregation of another work not based on the Program with the Program (or with a work based on the Program) on a volume of a storage or distribution medium does not bring the other work under the scope of this License. 3. You may copy and distribute the Program (or a work based on it, under Section 2) in object code or executable form under the terms of Sections 1 and 2 above provided that you also do one of the following: a) Accompany it with the complete corresponding machine-readable source code, which must be distributed under the terms of Sections 1 and 2 above on a medium customarily used for software interchange; or, b) Accompany it with a written offer, valid for at least three years, to give any third party, for a charge no more than your cost of physically performing source distribution, a complete machine-readable copy of the corresponding source code, to be distributed under the terms of Sections 1 and 2 above on a medium customarily used for software interchange; or, c) Accompany it with the information you received as to the offer to distribute corresponding source code. (This alternative is allowed only for noncommercial distribution and only if you received the program in object code or executable form with such an offer, in accord with Subsection b above.) The source code for a work means the preferred form of the work for making modifications to it. For an executable work, complete source code means all the source code for all modules it contains, plus any associated interface definition files, plus the scripts used to control compilation and installation of the executable. However, as a special exception, the source code distributed need not include anything that is normally distributed (in either source or binary form) with the major components (compiler, kernel, and so on) of the operating system on which the executable runs, unless that component itself accompanies the executable. If distribution of executable or object code is made by offering access to copy from a designated place, then offering equivalent access to copy the source code from the same place counts as distribution of the source code, even though third parties are not compelled to copy the source along with the object code. 4. You may not copy, modify, sublicense, or distribute the Program except as expressly provided under this License. Any attempt otherwise to copy, modify, sublicense or distribute the Program is void, and will automatically terminate your rights under this License. However, parties who have received copies, or rights, from you under this License will not have their licenses terminated so long as such parties remain in full compliance. 5. You are not required to accept this License, since you have not signed it. However, nothing else grants you permission to modify or distribute the Program or its derivative works. These actions are prohibited by law if you do not accept this License. Therefore, by modifying or distributing the Program (or any work based on the Program), you indicate your acceptance of this License to do so, and all its terms and conditions for copying, distributing or modifying the Program or works based on it. 6. Each time you redistribute the Program (or any work based on the Program), the recipient automatically receives a license from the original licensor to copy, distribute or modify the Program subject to these terms and conditions. You may not impose any further restrictions on the recipients' exercise of the rights granted herein. You are not responsible for enforcing compliance by third parties to this License. 7. If, as a consequence of a court judgment or allegation of patent infringement or for any other reason (not limited to patent issues), conditions are imposed on you (whether by court order, agreement or otherwise) that contradict the conditions of this License, they do not excuse you from the conditions of this License. If you cannot distribute so as to satisfy simultaneously your obligations under this License and any other pertinent obligations, then as a consequence you may not distribute the Program at all. For example, if a patent license would not permit royalty-free redistribution of the Program by all those who receive copies directly or indirectly through you, then the only way you could satisfy both it and this License would be to refrain entirely from distribution of the Program. If any portion of this section is held invalid or unenforceable under any particular circumstance, the balance of the section is intended to apply and the section as a whole is intended to apply in other circumstances. It is not the purpose of this section to induce you to infringe any patents or other property right claims or to contest validity of any such claims; this section has the sole purpose of protecting the integrity of the free software distribution system, which is implemented by public license practices. Many people have made generous contributions to the wide range of software distributed through that system in reliance on consistent application of that system; it is up to the author/donor to decide if he or she is willing to distribute software through any other system and a licensee cannot impose that choice. This section is intended to make thoroughly clear what is believed to be a consequence of the rest of this License. 8. If the distribution and/or use of the Program is restricted in certain countries either by patents or by copyrighted interfaces, the original copyright holder who places the Program under this License may add an explicit geographical distribution limitation excluding those countries, so that distribution is permitted only in or among countries not thus excluded. In such case, this License incorporates the limitation as if written in the body of this License. 9. The Free Software Foundation may publish revised and/or new versions of the General Public License from time to time. Such new versions will be similar in spirit to the present version, but may differ in detail to address new problems or concerns. Each version is given a distinguishing version number. If the Program specifies a version number of this License which applies to it and "any later version", you have the option of following the terms and conditions either of that version or of any later version published by the Free Software Foundation. If the Program does not specify a version number of this License, you may choose any version ever published by the Free Software Foundation. 10. If you wish to incorporate parts of the Program into other free programs whose distribution conditions are different, write to the author to ask for permission. For software which is copyrighted by the Free Software Foundation, write to the Free Software Foundation; we sometimes make exceptions for this. Our decision will be guided by the two goals of preserving the free status of all derivatives of our free software and of promoting the sharing and reuse of software generally. NO WARRANTY 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES. END OF TERMS AND CONDITIONS How to Apply These Terms to Your New Programs If you develop a new program, and you want it to be of the greatest possible use to the public, the best way to achieve this is to make it free software which everyone can redistribute and change under these terms. To do so, attach the following notices to the program. It is safest to attach them to the start of each source file to most effectively convey the exclusion of warranty; and each file should have at least the "copyright" line and a pointer to where the full notice is found. Copyright (C) This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 2 of the License, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with this program; if not, write to the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. Also add information on how to contact you by electronic and paper mail. If the program is interactive, make it output a short notice like this when it starts in an interactive mode: Gnomovision version 69, Copyright (C) year name of author Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'. This is free software, and you are welcome to redistribute it under certain conditions; type `show c' for details. The hypothetical commands `show w' and `show c' should show the appropriate parts of the General Public License. Of course, the commands you use may be called something other than `show w' and `show c'; they could even be mouse-clicks or menu items--whatever suits your program. You should also get your employer (if you work as a programmer) or your school, if any, to sign a "copyright disclaimer" for the program, if necessary. Here is a sample; alter the names: Yoyodyne, Inc., hereby disclaims all copyright interest in the program `Gnomovision' (which makes passes at compilers) written by James Hacker. , 1 April 1989 Ty Coon, President of Vice This General Public License does not permit incorporating your program into proprietary programs. If your program is a subroutine library, you may consider it more useful to permit linking proprietary applications with the library. If this is what you want to do, use the GNU Lesser General Public License instead of this License. fastimport-0.9.8/PKG-INFO0000644000175000017500000000143213264642537015607 0ustar jelmerjelmer00000000000000Metadata-Version: 1.1 Name: fastimport Version: 0.9.8 Summary: VCS fastimport/fastexport parser Home-page: https://github.com/jelmer/python-fastimport Author: Jelmer Vernooij Author-email: jelmer@jelmer.uk License: GNU GPL v2 or later Description: UNKNOWN Platform: UNKNOWN Classifier: Development Status :: 4 - Beta Classifier: License :: OSI Approved :: GNU General Public License v2 or later (GPLv2+) Classifier: Programming Language :: Python :: 2.7 Classifier: Programming Language :: Python :: 3.4 Classifier: Programming Language :: Python :: 3.5 Classifier: Programming Language :: Python :: Implementation :: CPython Classifier: Programming Language :: Python :: Implementation :: PyPy Classifier: Operating System :: POSIX Classifier: Topic :: Software Development :: Version Control fastimport-0.9.8/README.md0000644000175000017500000000050113234437127015757 0ustar jelmerjelmer00000000000000[![Build Status](https://travis-ci.org/jelmer/python-fastimport.png?branch=master)](https://travis-ci.org/jelmer/python-fastimport) python-fastimport ================= This package provides a parser for and generator of the Git fastimport format. (https://www.kernel.org/pub/software/scm/git/docs/git-fast-import.html) fastimport-0.9.8/fastimport/0000755000175000017500000000000013264642537016702 5ustar jelmerjelmer00000000000000fastimport-0.9.8/fastimport/__init__.py0000644000175000017500000000225513264642145021012 0ustar jelmerjelmer00000000000000# Copyright (C) 2008-2011 Canonical Ltd # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation; either version 2 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program. If not, see . """Fastimport file format parser and generator This is a Python parser for git's fast-import format. It was originally developed for bzr-fastimport but has been extracted so it can be used by other projects. Use it like so: import fastimport.processor import fastimport.parser class ImportProcessor(fastimport.processor.ImportProcessor): ... parser = fastimport.parser.ImportParser(sys.stdin) processor = ImportProcessor(...) processor.process(parser.parse()) """ __version__ = (0, 9, 8) fastimport-0.9.8/fastimport/parser.py0000644000175000017500000005431312736225770020555 0ustar jelmerjelmer00000000000000# Copyright (C) 2008-2010 Canonical Ltd # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation; either version 2 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program. If not, see . """Parser of import data into command objects. In order to reuse existing front-ends, the stream format is a subset of the one used by git-fast-import (as of the 1.5.4 release of git at least). The grammar is: stream ::= cmd*; cmd ::= new_blob | new_commit | new_tag | reset_branch | checkpoint | progress ; new_blob ::= 'blob' lf mark? file_content; file_content ::= data; new_commit ::= 'commit' sp ref_str lf mark? ('author' sp name '<' email '>' when lf)? 'committer' sp name '<' email '>' when lf commit_msg ('from' sp (ref_str | hexsha1 | sha1exp_str | idnum) lf)? ('merge' sp (ref_str | hexsha1 | sha1exp_str | idnum) lf)* file_change* lf?; commit_msg ::= data; file_change ::= file_clr | file_del | file_rnm | file_cpy | file_obm | file_inm; file_clr ::= 'deleteall' lf; file_del ::= 'D' sp path_str lf; file_rnm ::= 'R' sp path_str sp path_str lf; file_cpy ::= 'C' sp path_str sp path_str lf; file_obm ::= 'M' sp mode sp (hexsha1 | idnum) sp path_str lf; file_inm ::= 'M' sp mode sp 'inline' sp path_str lf data; new_tag ::= 'tag' sp tag_str lf 'from' sp (ref_str | hexsha1 | sha1exp_str | idnum) lf 'tagger' sp name '<' email '>' when lf tag_msg; tag_msg ::= data; reset_branch ::= 'reset' sp ref_str lf ('from' sp (ref_str | hexsha1 | sha1exp_str | idnum) lf)? lf?; checkpoint ::= 'checkpoint' lf lf?; progress ::= 'progress' sp not_lf* lf lf?; # note: the first idnum in a stream should be 1 and subsequent # idnums should not have gaps between values as this will cause # the stream parser to reserve space for the gapped values. An # idnum can be updated in the future to a new object by issuing # a new mark directive with the old idnum. # mark ::= 'mark' sp idnum lf; data ::= (delimited_data | exact_data) lf?; # note: delim may be any string but must not contain lf. # data_line may contain any data but must not be exactly # delim. The lf after the final data_line is included in # the data. delimited_data ::= 'data' sp '<<' delim lf (data_line lf)* delim lf; # note: declen indicates the length of binary_data in bytes. # declen does not include the lf preceeding the binary data. # exact_data ::= 'data' sp declen lf binary_data; # note: quoted strings are C-style quoting supporting \c for # common escapes of 'c' (e..g \n, \t, \\, \") or \nnn where nnn # is the signed byte value in octal. Note that the only # characters which must actually be escaped to protect the # stream formatting is: \, " and LF. Otherwise these values # are UTF8. # ref_str ::= ref; sha1exp_str ::= sha1exp; tag_str ::= tag; path_str ::= path | '"' quoted(path) '"' ; mode ::= '100644' | '644' | '100755' | '755' | '120000' ; declen ::= # unsigned 32 bit value, ascii base10 notation; bigint ::= # unsigned integer value, ascii base10 notation; binary_data ::= # file content, not interpreted; when ::= raw_when | rfc2822_when; raw_when ::= ts sp tz; rfc2822_when ::= # Valid RFC 2822 date and time; sp ::= # ASCII space character; lf ::= # ASCII newline (LF) character; # note: a colon (':') must precede the numerical value assigned to # an idnum. This is to distinguish it from a ref or tag name as # GIT does not permit ':' in ref or tag strings. # idnum ::= ':' bigint; path ::= # GIT style file path, e.g. "a/b/c"; ref ::= # GIT ref name, e.g. "refs/heads/MOZ_GECKO_EXPERIMENT"; tag ::= # GIT tag name, e.g. "FIREFOX_1_5"; sha1exp ::= # Any valid GIT SHA1 expression; hexsha1 ::= # SHA1 in hexadecimal format; # note: name and email are UTF8 strings, however name must not # contain '<' or lf and email must not contain any of the # following: '<', '>', lf. # name ::= # valid GIT author/committer name; email ::= # valid GIT author/committer email; ts ::= # time since the epoch in seconds, ascii base10 notation; tz ::= # GIT style timezone; # note: comments may appear anywhere in the input, except # within a data command. Any form of the data command # always escapes the related input from comment processing. # # In case it is not clear, the '#' that starts the comment # must be the first character on that the line (an lf have # preceeded it). # comment ::= '#' not_lf* lf; not_lf ::= # Any byte that is not ASCII newline (LF); """ from __future__ import print_function import collections import re import sys import codecs from fastimport import ( commands, dates, errors, ) from fastimport.helpers import ( newobject as object, utf8_bytes_string, ) ## Stream parsing ## class LineBasedParser(object): def __init__(self, input_stream): """A Parser that keeps track of line numbers. :param input: the file-like object to read from """ self.input = input_stream self.lineno = 0 # Lines pushed back onto the input stream self._buffer = [] def abort(self, exception, *args): """Raise an exception providing line number information.""" raise exception(self.lineno, *args) def readline(self): """Get the next line including the newline or '' on EOF.""" self.lineno += 1 if self._buffer: return self._buffer.pop() else: return self.input.readline() def next_line(self): """Get the next line without the newline or None on EOF.""" line = self.readline() if line: return line[:-1] else: return None def push_line(self, line): """Push line back onto the line buffer. :param line: the line with no trailing newline """ self.lineno -= 1 self._buffer.append(line + b'\n') def read_bytes(self, count): """Read a given number of bytes from the input stream. Throws MissingBytes if the bytes are not found. Note: This method does not read from the line buffer. :return: a string """ result = self.input.read(count) found = len(result) self.lineno += result.count(b'\n') if found != count: self.abort(errors.MissingBytes, count, found) return result def read_until(self, terminator): """Read the input stream until the terminator is found. Throws MissingTerminator if the terminator is not found. Note: This method does not read from the line buffer. :return: the bytes read up to but excluding the terminator. """ lines = [] term = terminator + b'\n' while True: line = self.input.readline() if line == term: break else: lines.append(line) return b''.join(lines) # Regular expression used for parsing. (Note: The spec states that the name # part should be non-empty but git-fast-export doesn't always do that so # the first bit is \w*, not \w+.) Also git-fast-import code says the # space before the email is optional. _WHO_AND_WHEN_RE = re.compile(br'([^<]*)<(.*)> (.+)') _WHO_RE = re.compile(br'([^<]*)<(.*)>') class ImportParser(LineBasedParser): def __init__(self, input_stream, verbose=False, output=sys.stdout, user_mapper=None, strict=True): """A Parser of import commands. :param input_stream: the file-like object to read from :param verbose: display extra information of not :param output: the file-like object to write messages to (YAGNI?) :param user_mapper: if not None, the UserMapper used to adjust user-ids for authors, committers and taggers. :param strict: Raise errors on strictly invalid data """ LineBasedParser.__init__(self, input_stream) self.verbose = verbose self.output = output self.user_mapper = user_mapper self.strict = strict # We auto-detect the date format when a date is first encountered self.date_parser = None self.features = {} def warning(self, msg): sys.stderr.write("warning line %d: %s\n" % (self.lineno, msg)) def iter_commands(self): """Iterator returning ImportCommand objects.""" while True: line = self.next_line() if line is None: if b'done' in self.features: raise errors.PrematureEndOfStream(self.lineno) break elif len(line) == 0 or line.startswith(b'#'): continue # Search for commands in order of likelihood elif line.startswith(b'commit '): yield self._parse_commit(line[len(b'commit '):]) elif line.startswith(b'blob'): yield self._parse_blob() elif line.startswith(b'done'): break elif line.startswith(b'progress '): yield commands.ProgressCommand(line[len(b'progress '):]) elif line.startswith(b'reset '): yield self._parse_reset(line[len(b'reset '):]) elif line.startswith(b'tag '): yield self._parse_tag(line[len(b'tag '):]) elif line.startswith(b'checkpoint'): yield commands.CheckpointCommand() elif line.startswith(b'feature'): yield self._parse_feature(line[len(b'feature '):]) else: self.abort(errors.InvalidCommand, line) def iter_file_commands(self): """Iterator returning FileCommand objects. If an invalid file command is found, the line is silently pushed back and iteration ends. """ while True: line = self.next_line() if line is None: break elif len(line) == 0 or line.startswith(b'#'): continue # Search for file commands in order of likelihood elif line.startswith(b'M '): yield self._parse_file_modify(line[2:]) elif line.startswith(b'D '): path = self._path(line[2:]) yield commands.FileDeleteCommand(path) elif line.startswith(b'R '): old, new = self._path_pair(line[2:]) yield commands.FileRenameCommand(old, new) elif line.startswith(b'C '): src, dest = self._path_pair(line[2:]) yield commands.FileCopyCommand(src, dest) elif line.startswith(b'deleteall'): yield commands.FileDeleteAllCommand() else: self.push_line(line) break def _parse_blob(self): """Parse a blob command.""" lineno = self.lineno mark = self._get_mark_if_any() data = self._get_data(b'blob') return commands.BlobCommand(mark, data, lineno) def _parse_commit(self, ref): """Parse a commit command.""" lineno = self.lineno mark = self._get_mark_if_any() author = self._get_user_info(b'commit', b'author', False) more_authors = [] while True: another_author = self._get_user_info(b'commit', b'author', False) if another_author is not None: more_authors.append(another_author) else: break committer = self._get_user_info(b'commit', b'committer') message = self._get_data(b'commit', b'message') from_ = self._get_from() merges = [] while True: merge = self._get_merge() if merge is not None: # while the spec suggests it's illegal, git-fast-export # outputs multiple merges on the one line, e.g. # merge :x :y :z these_merges = merge.split(b' ') merges.extend(these_merges) else: break properties = {} while True: name_value = self._get_property() if name_value is not None: name, value = name_value properties[name] = value else: break return commands.CommitCommand(ref, mark, author, committer, message, from_, merges, list(self.iter_file_commands()), lineno=lineno, more_authors=more_authors, properties=properties) def _parse_feature(self, info): """Parse a feature command.""" parts = info.split(b'=', 1) name = parts[0] if len(parts) > 1: value = self._path(parts[1]) else: value = None self.features[name] = value return commands.FeatureCommand(name, value, lineno=self.lineno) def _parse_file_modify(self, info): """Parse a filemodify command within a commit. :param info: a string in the format "mode dataref path" (where dataref might be the hard-coded literal 'inline'). """ params = info.split(b' ', 2) path = self._path(params[2]) mode = self._mode(params[0]) if params[1] == b'inline': dataref = None data = self._get_data(b'filemodify') else: dataref = params[1] data = None return commands.FileModifyCommand(path, mode, dataref, data) def _parse_reset(self, ref): """Parse a reset command.""" from_ = self._get_from() return commands.ResetCommand(ref, from_) def _parse_tag(self, name): """Parse a tag command.""" from_ = self._get_from(b'tag') tagger = self._get_user_info(b'tag', b'tagger', accept_just_who=True) message = self._get_data(b'tag', b'message') return commands.TagCommand(name, from_, tagger, message) def _get_mark_if_any(self): """Parse a mark section.""" line = self.next_line() if line.startswith(b'mark :'): return line[len(b'mark :'):] else: self.push_line(line) return None def _get_from(self, required_for=None): """Parse a from section.""" line = self.next_line() if line is None: return None elif line.startswith(b'from '): return line[len(b'from '):] elif required_for: self.abort(errors.MissingSection, required_for, 'from') else: self.push_line(line) return None def _get_merge(self): """Parse a merge section.""" line = self.next_line() if line is None: return None elif line.startswith(b'merge '): return line[len(b'merge '):] else: self.push_line(line) return None def _get_property(self): """Parse a property section.""" line = self.next_line() if line is None: return None elif line.startswith(b'property '): return self._name_value(line[len(b'property '):]) else: self.push_line(line) return None def _get_user_info(self, cmd, section, required=True, accept_just_who=False): """Parse a user section.""" line = self.next_line() if line.startswith(section + b' '): return self._who_when(line[len(section + b' '):], cmd, section, accept_just_who=accept_just_who) elif required: self.abort(errors.MissingSection, cmd, section) else: self.push_line(line) return None def _get_data(self, required_for, section=b'data'): """Parse a data section.""" line = self.next_line() if line.startswith(b'data '): rest = line[len(b'data '):] if rest.startswith(b'<<'): return self.read_until(rest[2:]) else: size = int(rest) read_bytes = self.read_bytes(size) # optional LF after data. next_line = self.input.readline() self.lineno += 1 if len(next_line) > 1 or next_line != b'\n': self.push_line(next_line[:-1]) return read_bytes else: self.abort(errors.MissingSection, required_for, section) def _who_when(self, s, cmd, section, accept_just_who=False): """Parse who and when information from a string. :return: a tuple of (name,email,timestamp,timezone). name may be the empty string if only an email address was given. """ match = _WHO_AND_WHEN_RE.search(s) if match: datestr = match.group(3).lstrip() if self.date_parser is None: # auto-detect the date format if len(datestr.split(b' ')) == 2: date_format = 'raw' elif datestr == b'now': date_format = 'now' else: date_format = 'rfc2822' self.date_parser = dates.DATE_PARSERS_BY_NAME[date_format] try: when = self.date_parser(datestr, self.lineno) except ValueError: print("failed to parse datestr '%s'" % (datestr,)) raise name = match.group(1).rstrip() email = match.group(2) else: match = _WHO_RE.search(s) if accept_just_who and match: # HACK around missing time # TODO: output a warning here when = dates.DATE_PARSERS_BY_NAME['now']('now') name = match.group(1) email = match.group(2) elif self.strict: self.abort(errors.BadFormat, cmd, section, s) else: name = s email = None when = dates.DATE_PARSERS_BY_NAME['now']('now') if len(name) > 0: if name.endswith(b' '): name = name[:-1] # While it shouldn't happen, some datasets have email addresses # which contain unicode characters. See bug 338186. We sanitize # the data at this level just in case. if self.user_mapper: name, email = self.user_mapper.map_name_and_email(name, email) return Authorship(name, email, when[0], when[1]) def _name_value(self, s): """Parse a (name,value) tuple from 'name value-length value'.""" parts = s.split(b' ', 2) name = parts[0] if len(parts) == 1: value = None else: size = int(parts[1]) value = parts[2] still_to_read = size - len(value) if still_to_read > 0: read_bytes = self.read_bytes(still_to_read) value += b'\n' + read_bytes[:still_to_read - 1] return (name, value) def _path(self, s): """Parse a path.""" if s.startswith(b'"'): if not s.endswith(b'"'): self.abort(errors.BadFormat, '?', '?', s) else: return _unquote_c_string(s[1:-1]) return s def _path_pair(self, s): """Parse two paths separated by a space.""" # TODO: handle a space in the first path if s.startswith(b'"'): parts = s[1:].split(b'" ', 1) else: parts = s.split(b' ', 1) if len(parts) != 2: self.abort(errors.BadFormat, '?', '?', s) elif parts[1].startswith(b'"') and parts[1].endswith(b'"'): parts[1] = parts[1][1:-1] elif parts[1].startswith(b'"') or parts[1].endswith(b'"'): self.abort(errors.BadFormat, '?', '?', s) return [_unquote_c_string(s) for s in parts] def _mode(self, s): """Check file mode format and parse into an int. :return: mode as integer """ # Note: Output from git-fast-export slightly different to spec if s in [b'644', b'100644', b'0100644']: return 0o100644 elif s in [b'755', b'100755', b'0100755']: return 0o100755 elif s in [b'040000', b'0040000']: return 0o40000 elif s in [b'120000', b'0120000']: return 0o120000 elif s in [b'160000', b'0160000']: return 0o160000 else: self.abort(errors.BadFormat, 'filemodify', 'mode', s) ESCAPE_SEQUENCE_BYTES_RE = re.compile(br''' ( \\U........ # 8-digit hex escapes | \\u.... # 4-digit hex escapes | \\x.. # 2-digit hex escapes | \\[0-7]{1,3} # Octal escapes | \\N\{[^}]+\} # Unicode characters by name | \\[\\'"abfnrtv] # Single-character escapes )''', re.VERBOSE ) ESCAPE_SEQUENCE_RE = re.compile(r''' ( \\U........ | \\u.... | \\x.. | \\[0-7]{1,3} | \\N\{[^}]+\} | \\[\\'"abfnrtv] )''', re.UNICODE | re.VERBOSE ) def _unquote_c_string(s): """replace C-style escape sequences (\n, \", etc.) with real chars.""" # doing a s.encode('utf-8').decode('unicode_escape') can return an # incorrect output with unicode string (both in py2 and py3) the safest way # is to match the escape sequences and decoding them alone. def decode_match(match): return utf8_bytes_string( codecs.decode(match.group(0), 'unicode-escape') ) if sys.version_info[0] >= 3 and isinstance(s, bytes): return ESCAPE_SEQUENCE_BYTES_RE.sub(decode_match, s) else: return ESCAPE_SEQUENCE_RE.sub(decode_match, s) Authorship = collections.namedtuple('Authorship', 'name email timestamp timezone') fastimport-0.9.8/fastimport/errors.py0000644000175000017500000001250012736225770020565 0ustar jelmerjelmer00000000000000# Copyright (C) 2008 Canonical Ltd # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation; either version 2 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program. If not, see . """Exception classes for fastimport""" # Prefix to messages to show location information _LOCATION_FMT = "line %(lineno)d: " # ImportError is heavily based on BzrError class ImportError(Exception): """The base exception class for all import processing exceptions.""" def __init__(self): super(ImportError, self).__init__(self._fmt % self.__dict__) class ParsingError(ImportError): """The base exception class for all import processing exceptions.""" _fmt = _LOCATION_FMT + "Unknown Import Parsing Error" def __init__(self, lineno): self.lineno = lineno ImportError.__init__(self) class MissingBytes(ParsingError): """Raised when EOF encountered while expecting to find more bytes.""" _fmt = (_LOCATION_FMT + "Unexpected EOF - expected %(expected)d bytes," " found %(found)d") def __init__(self, lineno, expected, found): self.expected = expected self.found = found ParsingError.__init__(self, lineno) class MissingTerminator(ParsingError): """Raised when EOF encountered while expecting to find a terminator.""" _fmt = (_LOCATION_FMT + "Unexpected EOF - expected '%(terminator)s' terminator") def __init__(self, lineno, terminator): self.terminator = terminator ParsingError.__init__(self, lineno) class InvalidCommand(ParsingError): """Raised when an unknown command found.""" _fmt = (_LOCATION_FMT + "Invalid command '%(cmd)s'") def __init__(self, lineno, cmd): self.cmd = cmd ParsingError.__init__(self, lineno) class MissingSection(ParsingError): """Raised when a section is required in a command but not present.""" _fmt = (_LOCATION_FMT + "Command %(cmd)s is missing section %(section)s") def __init__(self, lineno, cmd, section): self.cmd = cmd self.section = section ParsingError.__init__(self, lineno) class BadFormat(ParsingError): """Raised when a section is formatted incorrectly.""" _fmt = (_LOCATION_FMT + "Bad format for section %(section)s in " "command %(cmd)s: found '%(text)s'") def __init__(self, lineno, cmd, section, text): self.cmd = cmd self.section = section self.text = text ParsingError.__init__(self, lineno) class InvalidTimezone(ParsingError): """Raised when converting a string timezone to a seconds offset.""" _fmt = (_LOCATION_FMT + "Timezone %(timezone)r could not be converted.%(reason)s") def __init__(self, lineno, timezone, reason=None): self.timezone = timezone if reason: self.reason = ' ' + reason else: self.reason = '' ParsingError.__init__(self, lineno) class PrematureEndOfStream(ParsingError): """Raised when the 'done' feature was specified but missing.""" _fmt = (_LOCATION_FMT + "Stream end before 'done' command") def __init__(self, lineno): ParsingError.__init__(self, lineno) class UnknownDateFormat(ImportError): """Raised when an unknown date format is given.""" _fmt = ("Unknown date format '%(format)s'") def __init__(self, format): self.format = format ImportError.__init__(self) class MissingHandler(ImportError): """Raised when a processor can't handle a command.""" _fmt = ("Missing handler for command %(cmd)s") def __init__(self, cmd): self.cmd = cmd ImportError.__init__(self) class UnknownParameter(ImportError): """Raised when an unknown parameter is passed to a processor.""" _fmt = ("Unknown parameter - '%(param)s' not in %(knowns)s") def __init__(self, param, knowns): self.param = param self.knowns = knowns ImportError.__init__(self) class BadRepositorySize(ImportError): """Raised when the repository has an incorrect number of revisions.""" _fmt = ("Bad repository size - %(found)d revisions found, " "%(expected)d expected") def __init__(self, expected, found): self.expected = expected self.found = found ImportError.__init__(self) class BadRestart(ImportError): """Raised when the import stream and id-map do not match up.""" _fmt = ("Bad restart - attempted to skip commit %(commit_id)s " "but matching revision-id is unknown") def __init__(self, commit_id): self.commit_id = commit_id ImportError.__init__(self) class UnknownFeature(ImportError): """Raised when an unknown feature is given in the input stream.""" _fmt = ("Unknown feature '%(feature)s' - try a later importer or " "an earlier data format") def __init__(self, feature): self.feature = feature ImportError.__init__(self) fastimport-0.9.8/fastimport/processors/0000755000175000017500000000000013264642537021104 5ustar jelmerjelmer00000000000000fastimport-0.9.8/fastimport/processors/__init__.py0000644000175000017500000000000012632704156023175 0ustar jelmerjelmer00000000000000fastimport-0.9.8/fastimport/processors/filter_processor.py0000644000175000017500000002634612736225770025054 0ustar jelmerjelmer00000000000000# Copyright (C) 2009 Canonical Ltd # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation; either version 2 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program. If not, see . """Import processor that filters the input (and doesn't import).""" from fastimport import ( commands, helpers, processor, ) import stat class FilterProcessor(processor.ImportProcessor): """An import processor that filters the input to include/exclude objects. No changes to the current repository are made. Here are the supported parameters: * include_paths - a list of paths that commits must change in order to be kept in the output stream * exclude_paths - a list of paths that should not appear in the output stream * squash_empty_commits - if set to False, squash commits that don't have any changes after the filter has been applied """ known_params = [ b'include_paths', b'exclude_paths', b'squash_empty_commits' ] def pre_process(self): self.includes = self.params.get(b'include_paths') self.excludes = self.params.get(b'exclude_paths') self.squash_empty_commits = bool( self.params.get(b'squash_empty_commits', True)) # What's the new root, if any self.new_root = helpers.common_directory(self.includes) # Buffer of blobs until we know we need them: mark -> cmd self.blobs = {} # These are the commits we've squashed so far self.squashed_commits = set() # Map of commit-id to list of parents self.parents = {} def pre_handler(self, cmd): self.command = cmd # Should this command be included in the output or not? self.keep = False # Blobs to dump into the output before dumping the command itself self.referenced_blobs = [] def post_handler(self, cmd): if not self.keep: return # print referenced blobs and the command for blob_id in self.referenced_blobs: self._print_command(self.blobs[blob_id]) self._print_command(self.command) def progress_handler(self, cmd): """Process a ProgressCommand.""" # These always pass through self.keep = True def blob_handler(self, cmd): """Process a BlobCommand.""" # These never pass through directly. We buffer them and only # output them if referenced by an interesting command. self.blobs[cmd.id] = cmd self.keep = False def checkpoint_handler(self, cmd): """Process a CheckpointCommand.""" # These always pass through self.keep = True def commit_handler(self, cmd): """Process a CommitCommand.""" # These pass through if they meet the filtering conditions interesting_filecmds = self._filter_filecommands(cmd.iter_files) if interesting_filecmds or not self.squash_empty_commits: # If all we have is a single deleteall, skip this commit if len(interesting_filecmds) == 1 and isinstance( interesting_filecmds[0], commands.FileDeleteAllCommand): pass else: # Remember just the interesting file commands self.keep = True cmd.file_iter = iter(interesting_filecmds) # Record the referenced blobs for fc in interesting_filecmds: if isinstance(fc, commands.FileModifyCommand): if (fc.dataref is not None and not stat.S_ISDIR(fc.mode)): self.referenced_blobs.append(fc.dataref) # Update from and merges to refer to commits in the output cmd.from_ = self._find_interesting_from(cmd.from_) cmd.merges = self._find_interesting_merges(cmd.merges) else: self.squashed_commits.add(cmd.id) # Keep track of the parents if cmd.from_ and cmd.merges: parents = [cmd.from_] + cmd.merges elif cmd.from_: parents = [cmd.from_] else: parents = None if cmd.mark is not None: self.parents[b':' + cmd.mark] = parents def reset_handler(self, cmd): """Process a ResetCommand.""" if cmd.from_ is None: # We pass through resets that init a branch because we have to # assume the branch might be interesting. self.keep = True else: # Keep resets if they indirectly reference something we kept cmd.from_ = self._find_interesting_from(cmd.from_) self.keep = cmd.from_ is not None def tag_handler(self, cmd): """Process a TagCommand.""" # Keep tags if they indirectly reference something we kept cmd.from_ = self._find_interesting_from(cmd.from_) self.keep = cmd.from_ is not None def feature_handler(self, cmd): """Process a FeatureCommand.""" feature = cmd.feature_name if feature not in commands.FEATURE_NAMES: self.warning("feature %s is not supported - parsing may fail" % (feature,)) # These always pass through self.keep = True def _print_command(self, cmd): """Wrapper to avoid adding unnecessary blank lines.""" text = helpers.repr_bytes(cmd) self.outf.write(text) if not text.endswith(b'\n'): self.outf.write(b'\n') def _filter_filecommands(self, filecmd_iter): """Return the filecommands filtered by includes & excludes. :return: a list of FileCommand objects """ if self.includes is None and self.excludes is None: return list(filecmd_iter()) # Do the filtering, adjusting for the new_root result = [] for fc in filecmd_iter(): if (isinstance(fc, commands.FileModifyCommand) or isinstance(fc, commands.FileDeleteCommand)): if self._path_to_be_kept(fc.path): fc.path = self._adjust_for_new_root(fc.path) else: continue elif isinstance(fc, commands.FileDeleteAllCommand): pass elif isinstance(fc, commands.FileRenameCommand): fc = self._convert_rename(fc) elif isinstance(fc, commands.FileCopyCommand): fc = self._convert_copy(fc) else: self.warning("cannot handle FileCommands of class %s - ignoring", fc.__class__) continue if fc is not None: result.append(fc) return result def _path_to_be_kept(self, path): """Does the given path pass the filtering criteria?""" if self.excludes and (path in self.excludes or helpers.is_inside_any(self.excludes, path)): return False if self.includes: return (path in self.includes or helpers.is_inside_any(self.includes, path)) return True def _adjust_for_new_root(self, path): """Adjust a path given the new root directory of the output.""" if self.new_root is None: return path elif path.startswith(self.new_root): return path[len(self.new_root):] else: return path def _find_interesting_parent(self, commit_ref): while True: if commit_ref not in self.squashed_commits: return commit_ref parents = self.parents.get(commit_ref) if not parents: return None commit_ref = parents[0] def _find_interesting_from(self, commit_ref): if commit_ref is None: return None return self._find_interesting_parent(commit_ref) def _find_interesting_merges(self, commit_refs): if commit_refs is None: return None merges = [] for commit_ref in commit_refs: parent = self._find_interesting_parent(commit_ref) if parent is not None: merges.append(parent) if merges: return merges else: return None def _convert_rename(self, fc): """Convert a FileRenameCommand into a new FileCommand. :return: None if the rename is being ignored, otherwise a new FileCommand based on the whether the old and new paths are inside or outside of the interesting locations. """ old = fc.old_path new = fc.new_path keep_old = self._path_to_be_kept(old) keep_new = self._path_to_be_kept(new) if keep_old and keep_new: fc.old_path = self._adjust_for_new_root(old) fc.new_path = self._adjust_for_new_root(new) return fc elif keep_old: # The file has been renamed to a non-interesting location. # Delete it! old = self._adjust_for_new_root(old) return commands.FileDeleteCommand(old) elif keep_new: # The file has been renamed into an interesting location # We really ought to add it but we don't currently buffer # the contents of all previous files and probably never want # to. Maybe fast-import-info needs to be extended to # remember all renames and a config file can be passed # into here ala fast-import? self.warning("cannot turn rename of %s into an add of %s yet" % (old, new)) return None def _convert_copy(self, fc): """Convert a FileCopyCommand into a new FileCommand. :return: None if the copy is being ignored, otherwise a new FileCommand based on the whether the source and destination paths are inside or outside of the interesting locations. """ src = fc.src_path dest = fc.dest_path keep_src = self._path_to_be_kept(src) keep_dest = self._path_to_be_kept(dest) if keep_src and keep_dest: fc.src_path = self._adjust_for_new_root(src) fc.dest_path = self._adjust_for_new_root(dest) return fc elif keep_src: # The file has been copied to a non-interesting location. # Ignore it! return None elif keep_dest: # The file has been copied into an interesting location # We really ought to add it but we don't currently buffer # the contents of all previous files and probably never want # to. Maybe fast-import-info needs to be extended to # remember all copies and a config file can be passed # into here ala fast-import? self.warning("cannot turn copy of %s into an add of %s yet" % (src, dest)) return None fastimport-0.9.8/fastimport/processors/info_processor.py0000644000175000017500000002547313257471223024515 0ustar jelmerjelmer00000000000000# Copyright (C) 2008 Canonical Ltd # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation; either version 2 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program. If not, see . """Import processor that dump stats about the input (and doesn't import).""" from __future__ import absolute_import from .. import ( reftracker, ) from ..helpers import ( invert_dict, invert_dictset, ) from fastimport import ( commands, processor, ) import stat class InfoProcessor(processor.ImportProcessor): """An import processor that dumps statistics about the input. No changes to the current repository are made. As well as providing useful information about an import stream before importing it, this processor is useful for benchmarking the speed at which data can be extracted from the source. """ def __init__(self, params=None, verbose=0, outf=None): processor.ImportProcessor.__init__(self, params, verbose, outf=outf) def pre_process(self): # Init statistics self.cmd_counts = {} for cmd in commands.COMMAND_NAMES: self.cmd_counts[cmd] = 0 self.file_cmd_counts = {} for fc in commands.FILE_COMMAND_NAMES: self.file_cmd_counts[fc] = 0 self.parent_counts = {} self.max_parent_count = 0 self.committers = set() self.separate_authors_found = False self.symlinks_found = False self.executables_found = False self.sha_blob_references = False self.lightweight_tags = 0 # Blob usage tracking self.blobs = {} for usage in ['new', 'used', 'unknown', 'unmarked']: self.blobs[usage] = set() self.blob_ref_counts = {} # Head tracking self.reftracker = reftracker.RefTracker() # Stuff to cache: a map from mark to # of times that mark is merged self.merges = {} # Stuff to cache: these are maps from mark to sets self.rename_old_paths = {} self.copy_source_paths = {} def post_process(self): # Dump statistics cmd_names = commands.COMMAND_NAMES fc_names = commands.FILE_COMMAND_NAMES self._dump_stats_group("Command counts", [(c.decode('utf-8'), self.cmd_counts[c]) for c in cmd_names], str) self._dump_stats_group("File command counts", [(c.decode('utf-8'), self.file_cmd_counts[c]) for c in fc_names], str) # Commit stats if self.cmd_counts[b'commit']: p_items = [] for i in range(self.max_parent_count + 1): if i in self.parent_counts: count = self.parent_counts[i] p_items.append(("parents-%d" % i, count)) merges_count = len(self.merges) p_items.append(('total revisions merged', merges_count)) flags = { 'separate authors found': self.separate_authors_found, 'executables': self.executables_found, 'symlinks': self.symlinks_found, 'blobs referenced by SHA': self.sha_blob_references, } self._dump_stats_group("Parent counts", p_items, str) self._dump_stats_group("Commit analysis", sorted(flags.items()), _found) heads = invert_dictset(self.reftracker.heads) self._dump_stats_group( "Head analysis", [(k.decode('utf-8'), ', '.join([m.decode('utf-8') for m in v])) for (k, v) in heads.items()], None, _iterable_as_config_list) # note("\t%d\t%s" % (len(self.committers), 'unique committers')) self._dump_stats_group("Merges", self.merges.items(), None) # We only show the rename old path and copy source paths when -vv # (verbose=2) is specified. The output here for mysql's data can't # be parsed currently so this bit of code needs more work anyhow .. if self.verbose >= 2: self._dump_stats_group("Rename old paths", self.rename_old_paths.items(), len, _iterable_as_config_list) self._dump_stats_group("Copy source paths", self.copy_source_paths.items(), len, _iterable_as_config_list) # Blob stats if self.cmd_counts[b'blob']: # In verbose mode, don't list every blob used if self.verbose: del self.blobs['used'] self._dump_stats_group("Blob usage tracking", self.blobs.items(), len, _iterable_as_config_list) if self.blob_ref_counts: blobs_by_count = invert_dict(self.blob_ref_counts) blob_items = sorted(blobs_by_count.items()) self._dump_stats_group("Blob reference counts", blob_items, len, _iterable_as_config_list) # Other stats if self.cmd_counts[b'reset']: reset_stats = { 'lightweight tags': self.lightweight_tags, } self._dump_stats_group("Reset analysis", reset_stats.items()) def _dump_stats_group(self, title, items, normal_formatter=None, verbose_formatter=None): """Dump a statistics group. In verbose mode, do so as a config file so that other processors can load the information if they want to. :param normal_formatter: the callable to apply to the value before displaying it in normal mode :param verbose_formatter: the callable to apply to the value before displaying it in verbose mode """ if self.verbose: self.outf.write("[%s]\n" % (title,)) for name, value in items: if verbose_formatter is not None: value = verbose_formatter(value) if type(name) == str: name = name.replace(' ', '-') self.outf.write("%s = %s\n" % (name, value)) self.outf.write("\n") else: self.outf.write("%s:\n" % (title,)) for name, value in items: if normal_formatter is not None: value = normal_formatter(value) self.outf.write("\t%s\t%s\n" % (value, name)) def progress_handler(self, cmd): """Process a ProgressCommand.""" self.cmd_counts[cmd.name] += 1 def blob_handler(self, cmd): """Process a BlobCommand.""" self.cmd_counts[cmd.name] += 1 if cmd.mark is None: self.blobs['unmarked'].add(cmd.id) else: self.blobs['new'].add(cmd.id) # Marks can be re-used so remove it from used if already there. # Note: we definitely do NOT want to remove it from multi if # it's already in that set. try: self.blobs['used'].remove(cmd.id) except KeyError: pass def checkpoint_handler(self, cmd): """Process a CheckpointCommand.""" self.cmd_counts[cmd.name] += 1 def commit_handler(self, cmd): """Process a CommitCommand.""" self.cmd_counts[cmd.name] += 1 self.committers.add(cmd.committer) if cmd.author is not None: self.separate_authors_found = True for fc in cmd.iter_files(): self.file_cmd_counts[fc.name] += 1 if isinstance(fc, commands.FileModifyCommand): if fc.mode & 0o111: self.executables_found = True if stat.S_ISLNK(fc.mode): self.symlinks_found = True if fc.dataref is not None: if fc.dataref[0] == ':': self._track_blob(fc.dataref) else: self.sha_blob_references = True elif isinstance(fc, commands.FileRenameCommand): self.rename_old_paths.setdefault(cmd.id, set()).add(fc.old_path) elif isinstance(fc, commands.FileCopyCommand): self.copy_source_paths.setdefault(cmd.id, set()).add(fc.src_path) # Track the heads parents = self.reftracker.track_heads(cmd) # Track the parent counts parent_count = len(parents) try: self.parent_counts[parent_count] += 1 except KeyError: self.parent_counts[parent_count] = 1 if parent_count > self.max_parent_count: self.max_parent_count = parent_count # Remember the merges if cmd.merges: #self.merges.setdefault(cmd.ref, set()).update(cmd.merges) for merge in cmd.merges: if merge in self.merges: self.merges[merge] += 1 else: self.merges[merge] = 1 def reset_handler(self, cmd): """Process a ResetCommand.""" self.cmd_counts[cmd.name] += 1 if cmd.ref.startswith('refs/tags/'): self.lightweight_tags += 1 else: if cmd.from_ is not None: self.reftracker.track_heads_for_ref( cmd.ref, cmd.from_) def tag_handler(self, cmd): """Process a TagCommand.""" self.cmd_counts[cmd.name] += 1 def feature_handler(self, cmd): """Process a FeatureCommand.""" self.cmd_counts[cmd.name] += 1 feature = cmd.feature_name if feature not in commands.FEATURE_NAMES: self.warning("feature %s is not supported - parsing may fail" % (feature,)) def _track_blob(self, mark): if mark in self.blob_ref_counts: self.blob_ref_counts[mark] += 1 pass elif mark in self.blobs['used']: self.blob_ref_counts[mark] = 2 self.blobs['used'].remove(mark) elif mark in self.blobs['new']: self.blobs['used'].add(mark) self.blobs['new'].remove(mark) else: self.blobs['unknown'].add(mark) def _found(b): """Format a found boolean as a string.""" return ['no', 'found'][b] def _iterable_as_config_list(s): """Format an iterable as a sequence of comma-separated strings. To match what ConfigObj expects, a single item list has a trailing comma. """ items = sorted(s) if len(items) == 1: return "%s," % (items[0],) else: return ", ".join(items) fastimport-0.9.8/fastimport/processors/query_processor.py0000644000175000017500000000605112736225770024723 0ustar jelmerjelmer00000000000000# Copyright (C) 2008 Canonical Ltd # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation; either version 2 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program. If not, see . """Import processor that queries the input (and doesn't import).""" from __future__ import print_function from fastimport import ( commands, processor, ) class QueryProcessor(processor.ImportProcessor): """An import processor that queries the input. No changes to the current repository are made. """ known_params = ( commands.COMMAND_NAMES + commands.FILE_COMMAND_NAMES + [b'commit-mark'] ) def __init__(self, params=None, verbose=False): processor.ImportProcessor.__init__(self, params, verbose) self.parsed_params = {} self.interesting_commit = None self._finished = False if params: if 'commit-mark' in params: self.interesting_commit = params['commit-mark'] del params['commit-mark'] for name, value in params.items(): if value == 1: # All fields fields = None else: fields = value.split(',') self.parsed_params[name] = fields def pre_handler(self, cmd): """Hook for logic before each handler starts.""" if self._finished: return if self.interesting_commit and cmd.name == 'commit': if cmd.mark == self.interesting_commit: print(cmd.to_string()) self._finished = True return if cmd.name in self.parsed_params: fields = self.parsed_params[cmd.name] str = cmd.dump_str(fields, self.parsed_params, self.verbose) print("%s" % (str,)) def progress_handler(self, cmd): """Process a ProgressCommand.""" pass def blob_handler(self, cmd): """Process a BlobCommand.""" pass def checkpoint_handler(self, cmd): """Process a CheckpointCommand.""" pass def commit_handler(self, cmd): """Process a CommitCommand.""" pass def reset_handler(self, cmd): """Process a ResetCommand.""" pass def tag_handler(self, cmd): """Process a TagCommand.""" pass def feature_handler(self, cmd): """Process a FeatureCommand.""" feature = cmd.feature_name if feature not in commands.FEATURE_NAMES: self.warning("feature %s is not supported - parsing may fail" % (feature,)) fastimport-0.9.8/fastimport/processor.py0000644000175000017500000001423512736225770021277 0ustar jelmerjelmer00000000000000# Copyright (C) 2008 Canonical Ltd # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation; either version 2 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program. If not, see . """Processor for fast-import commands. This module provides the skeleton of a fast-import backend. To import from a fast-import stream to your version-control system: - derive a class from the abstract ImportProcessor class and implement the *_helper methods. - parse a fast-import stream into a sequence of commands, for example using the helpers from the parser module. - pass that command sequence to the process method of your processor. See git-fast-import.1 for the meaning of each command and the processors package for examples. """ import sys import time from fastimport import errors from fastimport.helpers import newobject as object class ImportProcessor(object): """Base class for fast-import stream processors. Subclasses should override the pre_*, post_* and *_handler methods as appropriate. """ known_params = [] def __init__(self, params=None, verbose=False, outf=None): if outf is None: self.outf = sys.stdout else: self.outf = outf self.verbose = verbose if params is None: self.params = {} else: self.params = params self.validate_parameters() # Handlers can set this to request exiting cleanly without # iterating through the remaining commands self.finished = False def validate_parameters(self): """Validate that the parameters are correctly specified.""" for p in self.params: if p not in self.known_params: raise errors.UnknownParameter(p, self.known_params) def process(self, command_iter): """Import data into Bazaar by processing a stream of commands. :param command_iter: an iterator providing commands """ self._process(command_iter) def _process(self, command_iter): self.pre_process() for cmd in command_iter(): try: name = (cmd.name + b'_handler').decode('utf8') handler = getattr(self.__class__, name) except KeyError: raise errors.MissingHandler(cmd.name) else: self.pre_handler(cmd) handler(self, cmd) self.post_handler(cmd) if self.finished: break self.post_process() def warning(self, msg, *args): """Output a warning but timestamp it.""" pass def debug(self, mgs, *args): """Output a debug message.""" pass def _time_of_day(self): """Time of day as a string.""" # Note: this is a separate method so tests can patch in a fixed value return time.strftime("%H:%M:%S") def pre_process(self): """Hook for logic at start of processing.""" pass def post_process(self): """Hook for logic at end of processing.""" pass def pre_handler(self, cmd): """Hook for logic before each handler starts.""" pass def post_handler(self, cmd): """Hook for logic after each handler finishes.""" pass def progress_handler(self, cmd): """Process a ProgressCommand.""" raise NotImplementedError(self.progress_handler) def blob_handler(self, cmd): """Process a BlobCommand.""" raise NotImplementedError(self.blob_handler) def checkpoint_handler(self, cmd): """Process a CheckpointCommand.""" raise NotImplementedError(self.checkpoint_handler) def commit_handler(self, cmd): """Process a CommitCommand.""" raise NotImplementedError(self.commit_handler) def reset_handler(self, cmd): """Process a ResetCommand.""" raise NotImplementedError(self.reset_handler) def tag_handler(self, cmd): """Process a TagCommand.""" raise NotImplementedError(self.tag_handler) def feature_handler(self, cmd): """Process a FeatureCommand.""" raise NotImplementedError(self.feature_handler) class CommitHandler(object): """Base class for commit handling. Subclasses should override the pre_*, post_* and *_handler methods as appropriate. """ def __init__(self, command): self.command = command def process(self): self.pre_process_files() for fc in self.command.iter_files(): try: name = (fc.name[4:] + b'_handler').decode('utf8') handler = getattr(self.__class__, name) except KeyError: raise errors.MissingHandler(fc.name) else: handler(self, fc) self.post_process_files() def warning(self, msg, *args): """Output a warning but add context.""" pass def pre_process_files(self): """Prepare for committing.""" pass def post_process_files(self): """Save the revision.""" pass def modify_handler(self, filecmd): """Handle a filemodify command.""" raise NotImplementedError(self.modify_handler) def delete_handler(self, filecmd): """Handle a filedelete command.""" raise NotImplementedError(self.delete_handler) def copy_handler(self, filecmd): """Handle a filecopy command.""" raise NotImplementedError(self.copy_handler) def rename_handler(self, filecmd): """Handle a filerename command.""" raise NotImplementedError(self.rename_handler) def deleteall_handler(self, filecmd): """Handle a filedeleteall command.""" raise NotImplementedError(self.deleteall_handler) fastimport-0.9.8/fastimport/commands.py0000644000175000017500000003762513234437127021064 0ustar jelmerjelmer00000000000000# Copyright (C) 2008 Canonical Ltd # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation; either version 2 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program. If not, see . """fast-import command classes. These objects are used by the parser to represent the content of a fast-import stream. """ from __future__ import division import re import stat import sys from fastimport.helpers import ( newobject as object, utf8_bytes_string, repr_bytes, ) # There is a bug in git 1.5.4.3 and older by which unquoting a string consumes # one extra character. Set this variable to True to work-around it. It only # happens when renaming a file whose name contains spaces and/or quotes, and # the symptom is: # % git-fast-import # fatal: Missing space after source: R "file 1.txt" file 2.txt # http://git.kernel.org/?p=git/git.git;a=commit;h=c8744d6a8b27115503565041566d97c21e722584 GIT_FAST_IMPORT_NEEDS_EXTRA_SPACE_AFTER_QUOTE = False # Lists of command names COMMAND_NAMES = [b'blob', b'checkpoint', b'commit', b'feature', b'progress', b'reset', b'tag'] FILE_COMMAND_NAMES = [b'filemodify', b'filedelete', b'filecopy', b'filerename', b'filedeleteall'] # Feature names MULTIPLE_AUTHORS_FEATURE = b'multiple-authors' COMMIT_PROPERTIES_FEATURE = b'commit-properties' EMPTY_DIRS_FEATURE = b'empty-directories' FEATURE_NAMES = [ MULTIPLE_AUTHORS_FEATURE, COMMIT_PROPERTIES_FEATURE, EMPTY_DIRS_FEATURE, ] class ImportCommand(object): """Base class for import commands.""" def __init__(self, name): self.name = name # List of field names not to display self._binary = [] def __str__(self): return repr(self) def __repr__(self): if sys.version_info[0] == 2: return self.__bytes__() else: return bytes(self).decode('utf8') def __bytes__(self): raise NotImplementedError( 'An implementation of __bytes__ is required' ) def dump_str(self, names=None, child_lists=None, verbose=False): """Dump fields as a string. For debugging. :param names: the list of fields to include or None for all public fields :param child_lists: dictionary of child command names to fields for that child command to include :param verbose: if True, prefix each line with the command class and display fields as a dictionary; if False, dump just the field values with tabs between them """ interesting = {} if names is None: fields = [ k for k in list(self.__dict__.keys()) if not k.startswith(b'_') ] else: fields = names for field in fields: value = self.__dict__.get(field) if field in self._binary and value is not None: value = b'(...)' interesting[field] = value if verbose: return "%s: %s" % (self.__class__.__name__, interesting) else: return "\t".join([repr(interesting[k]) for k in fields]) class BlobCommand(ImportCommand): def __init__(self, mark, data, lineno=0): ImportCommand.__init__(self, b'blob') self.mark = mark self.data = data self.lineno = lineno # Provide a unique id in case the mark is missing if mark is None: self.id = b'@' + ("%d" % lineno).encode('utf-8') else: self.id = b':' + mark self._binary = [b'data'] def __bytes__(self): if self.mark is None: mark_line = b'' else: mark_line = b"\nmark :" + self.mark return (b'blob' + mark_line + b'\n' + ('data %d\n' % len(self.data)).encode('utf-8') + self.data) class CheckpointCommand(ImportCommand): def __init__(self): ImportCommand.__init__(self, b'checkpoint') def __bytes__(self): return b'checkpoint' class CommitCommand(ImportCommand): def __init__(self, ref, mark, author, committer, message, from_, merges, file_iter, lineno=0, more_authors=None, properties=None): ImportCommand.__init__(self, b'commit') self.ref = ref self.mark = mark self.author = author self.committer = committer self.message = message self.from_ = from_ self.merges = merges self.file_iter = file_iter self.more_authors = more_authors self.properties = properties self.lineno = lineno self._binary = [b'file_iter'] # Provide a unique id in case the mark is missing if self.mark is None: self.id = b'@' + ('%d' % lineno).encode('utf-8') else: if isinstance(self.mark, (int)): self.id = b':' + str(self.mark).encode('utf-8') else: self.id = b':' + self.mark def copy(self, **kwargs): if not isinstance(self.file_iter, list): self.file_iter = list(self.file_iter) fields = dict( (key, value) for key, value in self.__dict__.items() if key not in ('id', 'name') if not key.startswith('_') ) fields.update(kwargs) return CommitCommand(**fields) def __bytes__(self): return self.to_string(include_file_contents=True) def to_string(self, use_features=True, include_file_contents=False): """ @todo the name to_string is ambiguous since the method actually returns bytes. """ if self.mark is None: mark_line = b'' else: if isinstance(self.mark, (int)): mark_line = b'\nmark :' + str(self.mark).encode('utf-8') else: mark_line = b'\nmark :' + self.mark if self.author is None: author_section = b'' else: author_section = b'\nauthor ' + format_who_when(self.author) if use_features and self.more_authors: for author in self.more_authors: author_section += b'\nauthor ' + format_who_when(author) committer = b'committer ' + format_who_when(self.committer) if self.message is None: msg_section = b'' else: msg = self.message msg_section = ('\ndata %d\n' % len(msg)).encode('ascii') + msg if self.from_ is None: from_line = b'' else: from_line = b'\nfrom ' + self.from_ if self.merges is None: merge_lines = b'' else: merge_lines = b''.join([b'\nmerge ' + m for m in self.merges]) if use_features and self.properties: property_lines = [] for name in sorted(self.properties): value = self.properties[name] property_lines.append(b'\n' + format_property(name, value)) properties_section = b''.join(property_lines) else: properties_section = b'' if self.file_iter is None: filecommands = b'' else: if include_file_contents: filecommands = b''.join([b'\n' + repr_bytes(c) for c in self.iter_files()]) else: filecommands = b''.join([b'\n' + str(c) for c in self.iter_files()]) return b''.join([ b'commit ', self.ref, mark_line, author_section + b'\n', committer, msg_section, from_line, merge_lines, properties_section, filecommands]) def dump_str(self, names=None, child_lists=None, verbose=False): result = [ImportCommand.dump_str(self, names, verbose=verbose)] for f in self.iter_files(): if child_lists is None: continue try: child_names = child_lists[f.name] except KeyError: continue result.append('\t%s' % f.dump_str(child_names, verbose=verbose)) return '\n'.join(result) def iter_files(self): """Iterate over files.""" # file_iter may be a callable or an iterator if callable(self.file_iter): return self.file_iter() return iter(self.file_iter) class FeatureCommand(ImportCommand): def __init__(self, feature_name, value=None, lineno=0): ImportCommand.__init__(self, b'feature') self.feature_name = feature_name self.value = value self.lineno = lineno def __bytes__(self): if self.value is None: value_text = b'' else: value_text = b'=' + self.value return b'feature ' + self.feature_name + value_text class ProgressCommand(ImportCommand): def __init__(self, message): ImportCommand.__init__(self, b'progress') self.message = message def __bytes__(self): return b'progress ' + self.message class ResetCommand(ImportCommand): def __init__(self, ref, from_): ImportCommand.__init__(self, b'reset') self.ref = ref self.from_ = from_ def __bytes__(self): if self.from_ is None: from_line = b'' else: # According to git-fast-import(1), the extra LF is optional here; # however, versions of git up to 1.5.4.3 had a bug by which the LF # was needed. Always emit it, since it doesn't hurt and maintains # compatibility with older versions. # http://git.kernel.org/?p=git/git.git;a=commit;h=655e8515f279c01f525745d443f509f97cd805ab from_line = b'\nfrom ' + self.from_ + b'\n' return b'reset ' + self.ref + from_line class TagCommand(ImportCommand): def __init__(self, id, from_, tagger, message): ImportCommand.__init__(self, b'tag') self.id = id self.from_ = from_ self.tagger = tagger self.message = message def __bytes__(self): if self.from_ is None: from_line = b'' else: from_line = b'\nfrom ' + self.from_ if self.tagger is None: tagger_line = b'' else: tagger_line = b'\ntagger ' + format_who_when(self.tagger) if self.message is None: msg_section = b'' else: msg = self.message msg_section = ('\ndata %d\n' % len(msg)).encode('ascii') + msg return b'tag ' + self.id + from_line + tagger_line + msg_section class FileCommand(ImportCommand): """Base class for file commands.""" pass class FileModifyCommand(FileCommand): def __init__(self, path, mode, dataref, data): # Either dataref or data should be null FileCommand.__init__(self, b'filemodify') self.path = check_path(path) self.mode = mode self.dataref = dataref self.data = data self._binary = [b'data'] def __bytes__(self): return self.to_string(include_file_contents=True) def __str__(self): return self.to_string(include_file_contents=False) def _format_mode(self, mode): if mode in (0o755, 0o100755): return b'755' elif mode in (0o644, 0o100644): return b'644' elif mode == 0o40000: return b'040000' elif mode == 0o120000: return b'120000' elif mode == 0o160000: return b'160000' else: raise AssertionError('Unknown mode %o' % mode) def to_string(self, include_file_contents=False): datastr = b'' if stat.S_ISDIR(self.mode): dataref = b'-' elif self.dataref is None: dataref = b'inline' if include_file_contents: datastr = ('\ndata %d\n' % len(self.data)).encode('ascii') + self.data else: dataref = self.dataref path = format_path(self.path) return b' '.join( [b'M', self._format_mode(self.mode), dataref, path + datastr]) class FileDeleteCommand(FileCommand): def __init__(self, path): FileCommand.__init__(self, b'filedelete') self.path = check_path(path) def __bytes__(self): return b' '.join([b'D', format_path(self.path)]) class FileCopyCommand(FileCommand): def __init__(self, src_path, dest_path): FileCommand.__init__(self, b'filecopy') self.src_path = check_path(src_path) self.dest_path = check_path(dest_path) def __bytes__(self): return b' '.join([b'C', format_path(self.src_path, quote_spaces=True), format_path(self.dest_path)]) class FileRenameCommand(FileCommand): def __init__(self, old_path, new_path): FileCommand.__init__(self, b'filerename') self.old_path = check_path(old_path) self.new_path = check_path(new_path) def __bytes__(self): return b' '.join([ b'R', format_path(self.old_path, quote_spaces=True), format_path(self.new_path)] ) class FileDeleteAllCommand(FileCommand): def __init__(self): FileCommand.__init__(self, b'filedeleteall') def __bytes__(self): return b'deleteall' class NoteModifyCommand(FileCommand): def __init__(self, from_, data): super(NoteModifyCommand, self).__init__(b'notemodify') self.from_ = from_ self.data = data self._binary = ['data'] def __bytes__(self): return (b'N inline :' + self.from_ + ('\ndata %d\n'% len(self.data)).encode('ascii') + self.data) def check_path(path): """Check that a path is legal. :return: the path if all is OK :raise ValueError: if the path is illegal """ if path is None or path == b'' or path.startswith(b'/'): raise ValueError("illegal path '%s'" % path) if ( (sys.version_info[0] >= 3 and not isinstance(path, bytes)) and (sys.version_info[0] == 2 and not isinstance(path, str)) ): raise TypeError("illegale type for path '%r'" % path) return path def format_path(p, quote_spaces=False): """Format a path in utf8, quoting it if necessary.""" if b'\n' in p: p = re.sub(b'\n', b'\\n', p) quote = True else: quote = p[0] == b'"' or (quote_spaces and b' ' in p) if quote: extra = GIT_FAST_IMPORT_NEEDS_EXTRA_SPACE_AFTER_QUOTE and b' ' or b'' p = b'"' + p + b'"' + extra return p def format_who_when(fields): """Format a tuple of name,email,secs-since-epoch,utc-offset-secs as a string.""" offset = fields[3] if offset < 0: offset_sign = b'-' offset = abs(offset) else: offset_sign = b'+' offset_hours = offset // 3600 offset_minutes = offset // 60 - offset_hours * 60 offset_str = offset_sign + ('%02d%02d' % (offset_hours, offset_minutes)).encode('ascii') name = fields[0] if name == b'': sep = b'' else: sep = b' ' name = utf8_bytes_string(name) email = fields[1] email = utf8_bytes_string(email) return b''.join((name, sep, b'<', email, b'> ', ("%d" % fields[2]).encode('ascii'), b' ', offset_str)) def format_property(name, value): """Format the name and value (both unicode) of a property as a string.""" result = b'' utf8_name = utf8_bytes_string(name) result = b'property ' + utf8_name if value is not None: utf8_value = utf8_bytes_string(value) result += b' ' + ('%d' % len(utf8_value)).encode('ascii') + b' ' + utf8_value return result fastimport-0.9.8/fastimport/reftracker.py0000644000175000017500000000420113257464503021376 0ustar jelmerjelmer00000000000000# Copyright (C) 2009 Canonical Ltd # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation; either version 2 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program. If not, see . """Tracker of refs.""" from __future__ import absolute_import class RefTracker(object): def __init__(self): # Head tracking: last ref, last id per ref & map of commit ids to ref*s* self.last_ref = None self.last_ids = {} self.heads = {} def dump_stats(self, note): self._show_stats_for(self.last_ids, "last-ids", note=note) self._show_stats_for(self.heads, "heads", note=note) def clear(self): self.last_ids.clear() self.heads.clear() def track_heads(self, cmd): """Track the repository heads given a CommitCommand. :param cmd: the CommitCommand :return: the list of parents in terms of commit-ids """ # Get the true set of parents if cmd.from_ is not None: parents = [cmd.from_] else: last_id = self.last_ids.get(cmd.ref) if last_id is not None: parents = [last_id] else: parents = [] parents.extend(cmd.merges) # Track the heads self.track_heads_for_ref(cmd.ref, cmd.id, parents) return parents def track_heads_for_ref(self, cmd_ref, cmd_id, parents=None): if parents is not None: for parent in parents: if parent in self.heads: del self.heads[parent] self.heads.setdefault(cmd_id, set()).add(cmd_ref) self.last_ids[cmd_ref] = cmd_id self.last_ref = cmd_ref fastimport-0.9.8/fastimport/dates.py0000644000175000017500000000455012736225770020357 0ustar jelmerjelmer00000000000000# Copyright (C) 2008 Canonical Ltd # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation; either version 2 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program. If not, see . """Date parsing routines. Each routine represents a date format that can be specified in a stream using the date-format feature. The return value is timestamp,timezone where * timestamp is seconds since epoch * timezone is the offset from UTC in seconds. """ import time from fastimport import errors def parse_raw(s, lineno=0): """Parse a date from a raw string. The format must be exactly "seconds-since-epoch offset-utc". See the spec for details. """ timestamp_str, timezone_str = s.split(b' ', 1) timestamp = float(timestamp_str) try: timezone = parse_tz(timezone_str) except ValueError: raise errors.InvalidTimezone(lineno, timezone_str) return timestamp, timezone def parse_tz(tz): """Parse a timezone specification in the [+|-]HHMM format. :return: the timezone offset in seconds. """ # from git_repository.py in bzr-git sign_byte = tz[0:1] # in python 3 b'+006'[0] would return an integer, # but b'+006'[0:1] return a new bytes string. if sign_byte not in (b'+', b'-'): raise ValueError(tz) sign = {b'+': +1, b'-': -1}[sign_byte] hours = int(tz[1:-2]) minutes = int(tz[-2:]) return sign * 60 * (60 * hours + minutes) def parse_rfc2822(s, lineno=0): """Parse a date from a rfc2822 string. See the spec for details. """ raise NotImplementedError(parse_rfc2822) def parse_now(s, lineno=0): """Parse a date from a string. The format must be exactly "now". See the spec for details. """ return time.time(), 0 # Lookup tabel of date parsing routines DATE_PARSERS_BY_NAME = { u'raw': parse_raw, u'rfc2822': parse_rfc2822, u'now': parse_now, } fastimport-0.9.8/fastimport/helpers.py0000644000175000017500000001667513257466456020743 0ustar jelmerjelmer00000000000000# Copyright (C) 2008 Canonical Ltd # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation; either version 2 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program. If not, see . """Miscellaneous useful stuff.""" import sys def _common_path_and_rest(l1, l2, common=[]): # From http://code.activestate.com/recipes/208993/ if len(l1) < 1: return (common, l1, l2) if len(l2) < 1: return (common, l1, l2) if l1[0] != l2[0]: return (common, l1, l2) return _common_path_and_rest( l1[1:], l2[1:], common + [ l1[0:1] # return a byte string in python 3 unlike l1[0] that # would return an integer. ] ) def common_path(path1, path2): """Find the common bit of 2 paths.""" return b''.join(_common_path_and_rest(path1, path2)[0]) def common_directory(paths): """Find the deepest common directory of a list of paths. :return: if no paths are provided, None is returned; if there is no common directory, '' is returned; otherwise the common directory with a trailing / is returned. """ import posixpath def get_dir_with_slash(path): if path == b'' or path.endswith(b'/'): return path else: dirname, basename = posixpath.split(path) if dirname == b'': return dirname else: return dirname + b'/' if not paths: return None elif len(paths) == 1: return get_dir_with_slash(paths[0]) else: common = common_path(paths[0], paths[1]) for path in paths[2:]: common = common_path(common, path) return get_dir_with_slash(common) def is_inside(directory, fname): """True if fname is inside directory. The parameters should typically be passed to osutils.normpath first, so that . and .. and repeated slashes are eliminated, and the separators are canonical for the platform. The empty string as a dir name is taken as top-of-tree and matches everything. """ # XXX: Most callers of this can actually do something smarter by # looking at the inventory if directory == fname: return True if directory == b'': return True if not directory.endswith(b'/'): directory += b'/' return fname.startswith(directory) def is_inside_any(dir_list, fname): """True if fname is inside any of given dirs.""" for dirname in dir_list: if is_inside(dirname, fname): return True return False def utf8_bytes_string(s): """Convert a string to a bytes string (if necessary, encode in utf8)""" if sys.version_info[0] == 2: if isinstance(s, str): return s else: return s.encode('utf8') else: if isinstance(s, str): return bytes(s, encoding='utf8') else: return s def repr_bytes(obj): """Return a bytes representation of the object""" if sys.version_info[0] == 2: return repr(obj) else: return bytes(obj) class newobject(object): """ A magical object class that provides Python 2 compatibility methods:: next __unicode__ __nonzero__ Subclasses of this class can merely define the Python 3 methods (__next__, __str__, and __bool__). This is a copy/paste of the future.types.newobject class of the future package. """ def next(self): if hasattr(self, '__next__'): return type(self).__next__(self) raise TypeError('newobject is not an iterator') def __unicode__(self): # All subclasses of the builtin object should have __str__ defined. # Note that old-style classes do not have __str__ defined. if hasattr(self, '__str__'): s = type(self).__str__(self) else: s = str(self) if isinstance(s, unicode): return s else: return s.decode('utf-8') def __nonzero__(self): if hasattr(self, '__bool__'): return type(self).__bool__(self) # object has no __nonzero__ method return True # Are these ever needed? # def __div__(self): # return self.__truediv__() # def __idiv__(self, other): # return self.__itruediv__(other) def __long__(self): if not hasattr(self, '__int__'): return NotImplemented return self.__int__() # not type(self).__int__(self) # def __new__(cls, *args, **kwargs): # """ # dict() -> new empty dictionary # dict(mapping) -> new dictionary initialized from a mapping object's # (key, value) pairs # dict(iterable) -> new dictionary initialized as if via: # d = {} # for k, v in iterable: # d[k] = v # dict(**kwargs) -> new dictionary initialized with the name=value pairs # in the keyword argument list. For example: dict(one=1, two=2) # """ # if len(args) == 0: # return super(newdict, cls).__new__(cls) # elif type(args[0]) == newdict: # return args[0] # else: # value = args[0] # return super(newdict, cls).__new__(cls, value) def __native__(self): """ Hook for the future.utils.native() function """ return object(self) def binary_stream(stream): """Ensure a stream is binary on Windows. :return: the stream """ try: import os if os.name == 'nt': fileno = getattr(stream, 'fileno', None) if fileno: no = fileno() if no >= 0: # -1 means we're working as subprocess import msvcrt msvcrt.setmode(no, os.O_BINARY) except ImportError: pass return stream def invert_dictset(d): """Invert a dictionary with keys matching a set of values, turned into lists.""" # Based on recipe from ASPN result = {} for k, c in d.items(): for v in c: keys = result.setdefault(v, []) keys.append(k) return result def invert_dict(d): """Invert a dictionary with keys matching each value turned into a list.""" # Based on recipe from ASPN result = {} for k, v in d.items(): keys = result.setdefault(v, []) keys.append(k) return result def defines_to_dict(defines): """Convert a list of definition strings to a dictionary.""" if defines is None: return None result = {} for define in defines: kv = define.split('=', 1) if len(kv) == 1: result[define.strip()] = 1 else: result[kv[0].strip()] = kv[1].strip() return result def get_source_stream(source): if source == '-' or source is None: import sys stream = binary_stream(sys.stdin) elif source.endswith('.gz'): import gzip stream = gzip.open(source, "rb") else: stream = open(source, "rb") return stream fastimport-0.9.8/fastimport/tests/0000755000175000017500000000000013264642537020044 5ustar jelmerjelmer00000000000000fastimport-0.9.8/fastimport/tests/__init__.py0000644000175000017500000000232313257470206022147 0ustar jelmerjelmer00000000000000# __init__.py -- The tests for python-fastimport # Copyright (C) 2010 Canonical, Ltd. # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; version 2 # of the License or (at your option) any later version of # the License. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program. If not, see . """Tests for fastimport.""" import unittest def test_suite(): names = [ 'test_commands', 'test_dates', 'test_errors', 'test_filter_processor', 'test_info_processor', 'test_helpers', 'test_parser', ] module_names = ['fastimport.tests.' + name for name in names] result = unittest.TestSuite() loader = unittest.TestLoader() suite = loader.loadTestsFromNames(module_names) result.addTests(suite) return result fastimport-0.9.8/fastimport/tests/test_parser.py0000644000175000017500000002714612736225770022762 0ustar jelmerjelmer00000000000000# Copyright (C) 2008 Canonical Ltd # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation; either version 2 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program. If not, see . """Test the Import parsing""" import io import time import unittest from fastimport import ( commands, errors, parser, ) class TestLineBasedParser(unittest.TestCase): def test_push_line(self): s = io.BytesIO(b"foo\nbar\nbaz\n") p = parser.LineBasedParser(s) self.assertEqual(b'foo', p.next_line()) self.assertEqual(b'bar', p.next_line()) p.push_line(b'bar') self.assertEqual(b'bar', p.next_line()) self.assertEqual(b'baz', p.next_line()) self.assertEqual(None, p.next_line()) def test_read_bytes(self): s = io.BytesIO(b"foo\nbar\nbaz\n") p = parser.LineBasedParser(s) self.assertEqual(b'fo', p.read_bytes(2)) self.assertEqual(b'o\nb', p.read_bytes(3)) self.assertEqual(b'ar', p.next_line()) # Test that the line buffer is ignored p.push_line(b'bar') self.assertEqual(b'baz', p.read_bytes(3)) # Test missing bytes self.assertRaises(errors.MissingBytes, p.read_bytes, 10) def test_read_until(self): # TODO return s = io.BytesIO(b"foo\nbar\nbaz\nabc\ndef\nghi\n") p = parser.LineBasedParser(s) self.assertEqual(b'foo\nbar', p.read_until(b'baz')) self.assertEqual(b'abc', p.next_line()) # Test that the line buffer is ignored p.push_line(b'abc') self.assertEqual(b'def', p.read_until(b'ghi')) # Test missing terminator self.assertRaises(errors.MissingTerminator, p.read_until(b'>>>')) # Sample text _sample_import_text = b""" progress completed # Test blob formats blob mark :1 data 4 aaaablob data 5 bbbbb # Commit formats commit refs/heads/master mark :2 committer bugs bunny now data 14 initial import M 644 inline README data 18 Welcome from bugs commit refs/heads/master committer now data 13 second commit from :2 M 644 inline README data 23 Welcome from bugs, etc. # Miscellaneous checkpoint progress completed # Test a commit without sub-commands (bug #351717) commit refs/heads/master mark :3 author now committer now data 20 first commit, empty # Test a commit with a heredoc-style (delimited_data) messsage (bug #400960) commit refs/heads/master mark :4 author now committer now data < now committer now data 15 submodule test M 160000 rev-id tree-id # Test features feature whatever feature foo=bar # Test commit with properties commit refs/heads/master mark :6 committer now data 18 test of properties property p1 property p2 5 hohum property p3 16 alpha beta gamma property p4 8 whatever # Test a commit with multiple authors commit refs/heads/master mark :7 author Fluffy now author Daffy now author Donald now committer now data 17 multi-author test """ _timefunc = time.time class TestImportParser(unittest.TestCase): def setUp(self): self.fake_time = 42.0123 time.time = lambda: self.fake_time def tearDown(self): time.time = _timefunc del self.fake_time def test_iter_commands(self): s = io.BytesIO(_sample_import_text) p = parser.ImportParser(s) result = [] for cmd in p.iter_commands(): result.append(cmd) if cmd.name == b'commit': for fc in cmd.iter_files(): result.append(fc) self.assertEqual(len(result), 17) cmd1 = result.pop(0) self.assertEqual(b'progress', cmd1.name) self.assertEqual(b'completed', cmd1.message) cmd2 = result.pop(0) self.assertEqual(b'blob', cmd2.name) self.assertEqual(b'1', cmd2.mark) self.assertEqual(b':1', cmd2.id) self.assertEqual(b'aaaa', cmd2.data) self.assertEqual(4, cmd2.lineno) cmd3 = result.pop(0) self.assertEqual(b'blob', cmd3.name) self.assertEqual(b'@7', cmd3.id) self.assertEqual(None, cmd3.mark) self.assertEqual(b'bbbbb', cmd3.data) self.assertEqual(7, cmd3.lineno) cmd4 = result.pop(0) self.assertEqual(b'commit', cmd4.name) self.assertEqual(b'2', cmd4.mark) self.assertEqual(b':2', cmd4.id) self.assertEqual(b'initial import', cmd4.message) self.assertEqual((b'bugs bunny', b'bugs@bunny.org', self.fake_time, 0), cmd4.committer) # namedtuple attributes self.assertEqual(b'bugs bunny', cmd4.committer.name) self.assertEqual(b'bugs@bunny.org', cmd4.committer.email) self.assertEqual(self.fake_time, cmd4.committer.timestamp) self.assertEqual(0, cmd4.committer.timezone) self.assertEqual(None, cmd4.author) self.assertEqual(11, cmd4.lineno) self.assertEqual(b'refs/heads/master', cmd4.ref) self.assertEqual(None, cmd4.from_) self.assertEqual([], cmd4.merges) file_cmd1 = result.pop(0) self.assertEqual(b'filemodify', file_cmd1.name) self.assertEqual(b'README', file_cmd1.path) self.assertEqual(0o100644, file_cmd1.mode) self.assertEqual(b'Welcome from bugs\n', file_cmd1.data) cmd5 = result.pop(0) self.assertEqual(b'commit', cmd5.name) self.assertEqual(None, cmd5.mark) self.assertEqual(b'@19', cmd5.id) self.assertEqual(b'second commit', cmd5.message) self.assertEqual((b'', b'bugs@bunny.org', self.fake_time, 0), cmd5.committer) self.assertEqual(None, cmd5.author) self.assertEqual(19, cmd5.lineno) self.assertEqual(b'refs/heads/master', cmd5.ref) self.assertEqual(b':2', cmd5.from_) self.assertEqual([], cmd5.merges) file_cmd2 = result.pop(0) self.assertEqual(b'filemodify', file_cmd2.name) self.assertEqual(b'README', file_cmd2.path) self.assertEqual(0o100644, file_cmd2.mode) self.assertEqual(b'Welcome from bugs, etc.', file_cmd2.data) cmd6 = result.pop(0) self.assertEqual(cmd6.name, b'checkpoint') cmd7 = result.pop(0) self.assertEqual(b'progress', cmd7.name) self.assertEqual(b'completed', cmd7.message) cmd = result.pop(0) self.assertEqual(b'commit', cmd.name) self.assertEqual(b'3', cmd.mark) self.assertEqual(None, cmd.from_) cmd = result.pop(0) self.assertEqual(b'commit', cmd.name) self.assertEqual(b'4', cmd.mark) self.assertEqual(b'Commit with heredoc-style message\n', cmd.message) cmd = result.pop(0) self.assertEqual(b'commit', cmd.name) self.assertEqual(b'5', cmd.mark) self.assertEqual(b'submodule test\n', cmd.message) file_cmd1 = result.pop(0) self.assertEqual(b'filemodify', file_cmd1.name) self.assertEqual(b'tree-id', file_cmd1.path) self.assertEqual(0o160000, file_cmd1.mode) self.assertEqual(b"rev-id", file_cmd1.dataref) cmd = result.pop(0) self.assertEqual(b'feature', cmd.name) self.assertEqual(b'whatever', cmd.feature_name) self.assertEqual(None, cmd.value) cmd = result.pop(0) self.assertEqual(b'feature', cmd.name) self.assertEqual(b'foo', cmd.feature_name) self.assertEqual(b'bar', cmd.value) cmd = result.pop(0) self.assertEqual(b'commit', cmd.name) self.assertEqual(b'6', cmd.mark) self.assertEqual(b'test of properties', cmd.message) self.assertEqual({ b'p1': None, b'p2': b'hohum', b'p3': b'alpha\nbeta\ngamma', b'p4': b'whatever', }, cmd.properties) cmd = result.pop(0) self.assertEqual(b'commit', cmd.name) self.assertEqual(b'7', cmd.mark) self.assertEqual(b'multi-author test', cmd.message) self.assertEqual(b'', cmd.committer[0]) self.assertEqual(b'bugs@bunny.org', cmd.committer[1]) self.assertEqual(b'Fluffy', cmd.author[0]) self.assertEqual(b'fluffy@bunny.org', cmd.author[1]) self.assertEqual(b'Daffy', cmd.more_authors[0][0]) self.assertEqual(b'daffy@duck.org', cmd.more_authors[0][1]) self.assertEqual(b'Donald', cmd.more_authors[1][0]) self.assertEqual(b'donald@duck.org', cmd.more_authors[1][1]) def test_done_feature_missing_done(self): s = io.BytesIO(b"""feature done """) p = parser.ImportParser(s) cmds = p.iter_commands() self.assertEqual(b"feature", next(cmds).name) self.assertRaises(errors.PrematureEndOfStream, lambda: next(cmds)) def test_done_with_feature(self): s = io.BytesIO(b"""feature done done more data """) p = parser.ImportParser(s) cmds = p.iter_commands() self.assertEqual(b"feature", next(cmds).name) self.assertRaises(StopIteration, lambda: next(cmds)) def test_done_without_feature(self): s = io.BytesIO(b"""done more data """) p = parser.ImportParser(s) cmds = p.iter_commands() self.assertEqual([], list(cmds)) class TestStringParsing(unittest.TestCase): def test_unquote(self): s = br'hello \"sweet\" wo\\r\tld' self.assertEqual(br'hello "sweet" wo\r' + b'\tld', parser._unquote_c_string(s)) class TestPathPairParsing(unittest.TestCase): def test_path_pair_simple(self): p = parser.ImportParser(b'') self.assertEqual([b'foo', b'bar'], p._path_pair(b'foo bar')) def test_path_pair_spaces_in_first(self): p = parser.ImportParser("") self.assertEqual([b'foo bar', b'baz'], p._path_pair(b'"foo bar" baz')) class TestTagParsing(unittest.TestCase): def test_tagger_with_email(self): p = parser.ImportParser(io.BytesIO( b"tag refs/tags/v1.0\n" b"from :xxx\n" b"tagger Joe Wong 1234567890 -0600\n" b"data 11\n" b"create v1.0")) cmds = list(p.iter_commands()) self.assertEqual(1, len(cmds)) self.assertTrue(isinstance(cmds[0], commands.TagCommand)) self.assertEqual(cmds[0].tagger, (b'Joe Wong', b'joe@example.com', 1234567890.0, -21600)) def test_tagger_no_email_strict(self): p = parser.ImportParser(io.BytesIO( b"tag refs/tags/v1.0\n" b"from :xxx\n" b"tagger Joe Wong\n" b"data 11\n" b"create v1.0")) self.assertRaises(errors.BadFormat, list, p.iter_commands()) def test_tagger_no_email_not_strict(self): p = parser.ImportParser(io.BytesIO( b"tag refs/tags/v1.0\n" b"from :xxx\n" b"tagger Joe Wong\n" b"data 11\n" b"create v1.0"), strict=False) cmds = list(p.iter_commands()) self.assertEqual(1, len(cmds)) self.assertTrue(isinstance(cmds[0], commands.TagCommand)) self.assertEqual(cmds[0].tagger[:2], (b'Joe Wong', None)) fastimport-0.9.8/fastimport/tests/test_helpers.py0000644000175000017500000000365412736225770023126 0ustar jelmerjelmer00000000000000# Copyright (C) 2009 Canonical Ltd # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation; either version 2 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program. If not, see . """Test the helper functions.""" import unittest from fastimport import ( helpers, ) class TestCommonDirectory(unittest.TestCase): def test_no_paths(self): c = helpers.common_directory(None) self.assertEqual(c, None) c = helpers.common_directory([]) self.assertEqual(c, None) def test_one_path(self): c = helpers.common_directory([b'foo']) self.assertEqual(c, b'') c = helpers.common_directory([b'foo/']) self.assertEqual(c, b'foo/') c = helpers.common_directory([b'foo/bar']) self.assertEqual(c, b'foo/') def test_two_paths(self): c = helpers.common_directory([b'foo', b'bar']) self.assertEqual(c, b'') c = helpers.common_directory([b'foo/', b'bar']) self.assertEqual(c, b'') c = helpers.common_directory([b'foo/', b'foo/bar']) self.assertEqual(c, b'foo/') c = helpers.common_directory([b'foo/bar/x', b'foo/bar/y']) self.assertEqual(c, b'foo/bar/') c = helpers.common_directory([b'foo/bar/aa_x', b'foo/bar/aa_y']) self.assertEqual(c, b'foo/bar/') def test_lots_of_paths(self): c = helpers.common_directory([b'foo/bar/x', b'foo/bar/y', b'foo/bar/z']) self.assertEqual(c, b'foo/bar/') fastimport-0.9.8/fastimport/tests/test_errors.py0000644000175000017500000000534012736225770022772 0ustar jelmerjelmer00000000000000# Copyright (C) 2008 Canonical Ltd # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation; either version 2 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program. If not, see . """Test the Import errors""" from unittest import TestCase from fastimport import ( errors, ) class TestErrors(TestCase): def test_MissingBytes(self): e = errors.MissingBytes(99, 10, 8) self.assertEqual("line 99: Unexpected EOF - expected 10 bytes, found 8", str(e)) def test_MissingTerminator(self): e = errors.MissingTerminator(99, '---') self.assertEqual("line 99: Unexpected EOF - expected '---' terminator", str(e)) def test_InvalidCommand(self): e = errors.InvalidCommand(99, 'foo') self.assertEqual("line 99: Invalid command 'foo'", str(e)) def test_MissingSection(self): e = errors.MissingSection(99, 'foo', 'bar') self.assertEqual("line 99: Command foo is missing section bar", str(e)) def test_BadFormat(self): e = errors.BadFormat(99, 'foo', 'bar', 'xyz') self.assertEqual("line 99: Bad format for section bar in " "command foo: found 'xyz'", str(e)) def test_InvalidTimezone(self): e = errors.InvalidTimezone(99, 'aa:bb') self.assertEqual('aa:bb', e.timezone) self.assertEqual('', e.reason) self.assertEqual("line 99: Timezone 'aa:bb' could not be converted.", str(e)) e = errors.InvalidTimezone(99, 'aa:bb', 'Non-numeric hours') self.assertEqual('aa:bb', e.timezone) self.assertEqual(' Non-numeric hours', e.reason) self.assertEqual("line 99: Timezone 'aa:bb' could not be converted." " Non-numeric hours", str(e)) def test_UnknownDateFormat(self): e = errors.UnknownDateFormat('aaa') self.assertEqual("Unknown date format 'aaa'", str(e)) def test_MissingHandler(self): e = errors.MissingHandler('foo') self.assertEqual("Missing handler for command foo", str(e)) def test_UnknownFeature(self): e = errors.UnknownFeature('aaa') self.assertEqual("Unknown feature 'aaa' - try a later importer or " "an earlier data format", str(e)) fastimport-0.9.8/fastimport/tests/test_info_processor.py0000644000175000017500000000351413257471575024516 0ustar jelmerjelmer00000000000000# Copyright (C) 2018 Jelmer Vernooij # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation; either version 2 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program. If not, see . """Test InfoProcessor""" from io import BytesIO try: from StringIO import StringIO except ImportError: from io import StringIO from unittest import TestCase from fastimport import ( parser, ) from fastimport.processors import ( info_processor, ) simple_fast_import_stream = b"""commit refs/heads/master mark :1 committer Jelmer Vernooij 1299718135 +0100 data 7 initial """ class TestFastImportInfo(TestCase): def test_simple(self): stream = BytesIO(simple_fast_import_stream) outf = StringIO() proc = info_processor.InfoProcessor(outf=outf) p = parser.ImportParser(stream) proc.process(p.iter_commands) self.maxDiff = None self.assertEqual(outf.getvalue(), """Command counts: \t0\tblob \t0\tcheckpoint \t1\tcommit \t0\tfeature \t0\tprogress \t0\treset \t0\ttag File command counts: \t0\tfilemodify \t0\tfiledelete \t0\tfilecopy \t0\tfilerename \t0\tfiledeleteall Parent counts: \t1\tparents-0 \t0\ttotal revisions merged Commit analysis: \tno\tblobs referenced by SHA \tno\texecutables \tno\tseparate authors found \tno\tsymlinks Head analysis: \t:1\trefs/heads/master Merges: """) fastimport-0.9.8/fastimport/tests/test_commands.py0000644000175000017500000004167713234437127023267 0ustar jelmerjelmer00000000000000# Copyright (C) 2009 Canonical Ltd # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation; either version 2 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program. If not, see . """Test how Commands are displayed""" from unittest import TestCase from fastimport.helpers import ( repr_bytes, utf8_bytes_string, ) from fastimport import ( commands, ) class TestBlobDisplay(TestCase): def test_blob(self): c = commands.BlobCommand(b"1", b"hello world") self.assertEqual(b"blob\nmark :1\ndata 11\nhello world", repr_bytes(c)) def test_blob_no_mark(self): c = commands.BlobCommand(None, b"hello world") self.assertEqual(b"blob\ndata 11\nhello world", repr_bytes(c)) class TestCheckpointDisplay(TestCase): def test_checkpoint(self): c = commands.CheckpointCommand() self.assertEqual(b'checkpoint', repr_bytes(c)) class TestCommitDisplay(TestCase): def test_commit(self): # user tuple is (name, email, secs-since-epoch, secs-offset-from-utc) committer = (b'Joe Wong', b'joe@example.com', 1234567890, -6 * 3600) c = commands.CommitCommand(b"refs/heads/master", b"bbb", None, committer, b"release v1.0", b":aaa", None, None) self.assertEqual( b"commit refs/heads/master\n" b"mark :bbb\n" b"committer Joe Wong 1234567890 -0600\n" b"data 12\n" b"release v1.0\n" b"from :aaa", repr_bytes(c)) def test_commit_unicode_committer(self): # user tuple is (name, email, secs-since-epoch, secs-offset-from-utc) name = u'\u013d\xf3r\xe9m \xcdp\u0161\xfam' commit_utf8 = utf8_bytes_string( u"commit refs/heads/master\n" u"mark :bbb\n" u"committer %s 1234567890 -0600\n" u"data 12\n" u"release v1.0\n" u"from :aaa" % (name,) ) committer = (name, b'test@example.com', 1234567890, -6 * 3600) c = commands.CommitCommand(b'refs/heads/master', b'bbb', None, committer, b'release v1.0', b':aaa', None, None) self.assertEqual(commit_utf8, repr_bytes(c)) def test_commit_no_mark(self): # user tuple is (name, email, secs-since-epoch, secs-offset-from-utc) committer = (b'Joe Wong', b'joe@example.com', 1234567890, -6 * 3600) c = commands.CommitCommand(b'refs/heads/master', None, None, committer, b'release v1.0', b':aaa', None, None) self.assertEqual( b"commit refs/heads/master\n" b"committer Joe Wong 1234567890 -0600\n" b"data 12\n" b"release v1.0\n" b"from :aaa", repr_bytes(c)) def test_commit_no_from(self): # user tuple is (name, email, secs-since-epoch, secs-offset-from-utc) committer = (b'Joe Wong', b'joe@example.com', 1234567890, -6 * 3600) c = commands.CommitCommand(b"refs/heads/master", b"bbb", None, committer, b"release v1.0", None, None, None) self.assertEqual( b"commit refs/heads/master\n" b"mark :bbb\n" b"committer Joe Wong 1234567890 -0600\n" b"data 12\n" b"release v1.0", repr_bytes(c)) def test_commit_with_author(self): # user tuple is (name, email, secs-since-epoch, secs-offset-from-utc) author = (b'Sue Wong', b'sue@example.com', 1234565432, -6 * 3600) committer = (b'Joe Wong', b'joe@example.com', 1234567890, -6 * 3600) c = commands.CommitCommand(b'refs/heads/master', b'bbb', author, committer, b'release v1.0', b':aaa', None, None) self.assertEqual( b"commit refs/heads/master\n" b"mark :bbb\n" b"author Sue Wong 1234565432 -0600\n" b"committer Joe Wong 1234567890 -0600\n" b"data 12\n" b"release v1.0\n" b"from :aaa", repr_bytes(c)) def test_commit_with_merges(self): # user tuple is (name, email, secs-since-epoch, secs-offset-from-utc) committer = (b'Joe Wong', b'joe@example.com', 1234567890, -6 * 3600) c = commands.CommitCommand(b"refs/heads/master", b"ddd", None, committer, b'release v1.0', b":aaa", [b':bbb', b':ccc'], None) self.assertEqual( b"commit refs/heads/master\n" b"mark :ddd\n" b"committer Joe Wong 1234567890 -0600\n" b"data 12\n" b"release v1.0\n" b"from :aaa\n" b"merge :bbb\n" b"merge :ccc", repr_bytes(c)) def test_commit_with_filecommands(self): file_cmds = iter([ commands.FileDeleteCommand(b'readme.txt'), commands.FileModifyCommand(b'NEWS', 0o100644, None, b'blah blah blah'), ]) # user tuple is (name, email, secs-since-epoch, secs-offset-from-utc) committer = (b'Joe Wong', b'joe@example.com', 1234567890, -6 * 3600) c = commands.CommitCommand(b'refs/heads/master', b'bbb', None, committer, b'release v1.0', b':aaa', None, file_cmds) self.assertEqual( b"commit refs/heads/master\n" b"mark :bbb\n" b"committer Joe Wong 1234567890 -0600\n" b"data 12\n" b"release v1.0\n" b"from :aaa\n" b"D readme.txt\n" b"M 644 inline NEWS\n" b"data 14\n" b"blah blah blah", repr_bytes(c)) def test_commit_with_more_authors(self): # user tuple is (name, email, secs-since-epoch, secs-offset-from-utc) author = (b'Sue Wong', b'sue@example.com', 1234565432, -6 * 3600) committer = (b'Joe Wong', b'joe@example.com', 1234567890, -6 * 3600) more_authors = [ (b'Al Smith', b'al@example.com', 1234565432, -6 * 3600), (b'Bill Jones', b'bill@example.com', 1234565432, -6 * 3600), ] c = commands.CommitCommand(b'refs/heads/master', b'bbb', author, committer, b'release v1.0', b':aaa', None, None, more_authors=more_authors) self.assertEqual( b"commit refs/heads/master\n" b"mark :bbb\n" b"author Sue Wong 1234565432 -0600\n" b"author Al Smith 1234565432 -0600\n" b"author Bill Jones 1234565432 -0600\n" b"committer Joe Wong 1234567890 -0600\n" b"data 12\n" b"release v1.0\n" b"from :aaa", repr_bytes(c)) def test_commit_with_properties(self): # user tuple is (name, email, secs-since-epoch, secs-offset-from-utc) committer = (b'Joe Wong', b'joe@example.com', 1234567890, -6 * 3600) properties = { u'greeting': u'hello', u'planet': u'world', } c = commands.CommitCommand(b'refs/heads/master', b'bbb', None, committer, b'release v1.0', b':aaa', None, None, properties=properties) self.assertEqual( b"commit refs/heads/master\n" b"mark :bbb\n" b"committer Joe Wong 1234567890 -0600\n" b"data 12\n" b"release v1.0\n" b"from :aaa\n" b"property greeting 5 hello\n" b"property planet 5 world", repr_bytes(c)) def test_commit_with_int_mark(self): # user tuple is (name, email, secs-since-epoch, secs-offset-from-utc) committer = (b'Joe Wong', b'joe@example.com', 1234567890, -6 * 3600) properties = { u'greeting': u'hello', u'planet': u'world', } c = commands.CommitCommand(b'refs/heads/master', 123, None, committer, b'release v1.0', b':aaa', None, None, properties=properties) self.assertEqual( b"commit refs/heads/master\n" b"mark :123\n" b"committer Joe Wong 1234567890 -0600\n" b"data 12\n" b"release v1.0\n" b"from :aaa\n" b"property greeting 5 hello\n" b"property planet 5 world", repr_bytes(c)) class TestCommitCopy(TestCase): def setUp(self): super(TestCommitCopy, self).setUp() file_cmds = iter([ commands.FileDeleteCommand(b'readme.txt'), commands.FileModifyCommand(b'NEWS', 0o100644, None, b'blah blah blah'), ]) committer = (b'Joe Wong', b'joe@example.com', 1234567890, -6 * 3600) self.c = commands.CommitCommand( b'refs/heads/master', b'bbb', None, committer, b'release v1.0', b':aaa', None, file_cmds) def test_simple_copy(self): c2 = self.c.copy() self.assertFalse(self.c is c2) self.assertEqual(repr_bytes(self.c), repr_bytes(c2)) def test_replace_attr(self): c2 = self.c.copy(mark=b'ccc') self.assertEqual( repr_bytes(self.c).replace(b'mark :bbb', b'mark :ccc'), repr_bytes(c2) ) def test_invalid_attribute(self): self.assertRaises(TypeError, self.c.copy, invalid=True) class TestFeatureDisplay(TestCase): def test_feature(self): c = commands.FeatureCommand(b"dwim") self.assertEqual(b"feature dwim", repr_bytes(c)) def test_feature_with_value(self): c = commands.FeatureCommand(b"dwim", b"please") self.assertEqual(b"feature dwim=please", repr_bytes(c)) class TestProgressDisplay(TestCase): def test_progress(self): c = commands.ProgressCommand(b"doing foo") self.assertEqual(b"progress doing foo", repr_bytes(c)) class TestResetDisplay(TestCase): def test_reset(self): c = commands.ResetCommand(b"refs/tags/v1.0", b":xxx") self.assertEqual(b"reset refs/tags/v1.0\nfrom :xxx\n", repr_bytes(c)) def test_reset_no_from(self): c = commands.ResetCommand(b'refs/remotes/origin/master', None) self.assertEqual(b'reset refs/remotes/origin/master', repr_bytes(c)) class TestTagDisplay(TestCase): def test_tag(self): # tagger tuple is (name, email, secs-since-epoch, secs-offset-from-utc) tagger = (b'Joe Wong', b'joe@example.com', 1234567890, -6 * 3600) c = commands.TagCommand(b'refs/tags/v1.0', b':xxx', tagger, b'create v1.0') self.assertEqual( b"tag refs/tags/v1.0\n" b"from :xxx\n" b"tagger Joe Wong 1234567890 -0600\n" b"data 11\n" b"create v1.0", repr_bytes(c)) def test_tag_no_from(self): tagger = (b'Joe Wong', b'joe@example.com', 1234567890, -6 * 3600) c = commands.TagCommand(b'refs/tags/v1.0', None, tagger, b'create v1.0') self.assertEqual( b"tag refs/tags/v1.0\n" b"tagger Joe Wong 1234567890 -0600\n" b"data 11\n" b"create v1.0", repr_bytes(c)) class TestFileModifyDisplay(TestCase): def test_filemodify_file(self): c = commands.FileModifyCommand(b'foo/bar', 0o100644, b':23', None) self.assertEqual(b'M 644 :23 foo/bar', repr_bytes(c)) def test_filemodify_file_executable(self): c = commands.FileModifyCommand(b'foo/bar', 0o100755, b':23', None) self.assertEqual(b'M 755 :23 foo/bar', repr_bytes(c)) def test_filemodify_file_internal(self): c = commands.FileModifyCommand(b'foo/bar', 0o100644, None, b'hello world') self.assertEqual(b'M 644 inline foo/bar\ndata 11\nhello world', repr_bytes(c)) def test_filemodify_symlink(self): c = commands.FileModifyCommand(b'foo/bar', 0o120000, None, b'baz') self.assertEqual(b'M 120000 inline foo/bar\ndata 3\nbaz', repr_bytes(c)) def test_filemodify_treeref(self): c = commands.FileModifyCommand(b'tree-info', 0o160000, b'revision-id-info', None) self.assertEqual(b'M 160000 revision-id-info tree-info', repr_bytes(c)) class TestFileDeleteDisplay(TestCase): def test_filedelete(self): c = commands.FileDeleteCommand(b'foo/bar') self.assertEqual(b'D foo/bar', repr_bytes(c)) class TestFileCopyDisplay(TestCase): def test_filecopy(self): c = commands.FileCopyCommand(b'foo/bar', b'foo/baz') self.assertEqual(b'C foo/bar foo/baz', repr_bytes(c)) def test_filecopy_quoted(self): # Check the first path is quoted if it contains spaces c = commands.FileCopyCommand(b'foo/b a r', b'foo/b a z') self.assertEqual(b'C "foo/b a r" foo/b a z', repr_bytes(c)) class TestFileRenameDisplay(TestCase): def test_filerename(self): c = commands.FileRenameCommand(b'foo/bar', b'foo/baz') self.assertEqual(b'R foo/bar foo/baz', repr_bytes(c)) def test_filerename_quoted(self): # Check the first path is quoted if it contains spaces c = commands.FileRenameCommand(b'foo/b a r', b'foo/b a z') self.assertEqual(b'R "foo/b a r" foo/b a z', repr_bytes(c)) class TestFileDeleteAllDisplay(TestCase): def test_filedeleteall(self): c = commands.FileDeleteAllCommand() self.assertEqual(b'deleteall', repr_bytes(c)) class TestNotesDisplay(TestCase): def test_noteonly(self): c = commands.NoteModifyCommand(b'foo', b'A basic note') self.assertEqual(b'N inline :foo\ndata 12\nA basic note', repr_bytes(c)) def test_notecommit(self): committer = (b'Ed Mund', b'ed@example.org', 1234565432, 0) commits = [ commands.CommitCommand( ref=b'refs/heads/master', mark=b'1', author=committer, committer=committer, message=b'test\n', from_=None, merges=[], file_iter=[ commands.FileModifyCommand(b'bar', 0o100644, None, b'') ]), commands.CommitCommand( ref=b'refs/notes/commits', mark=None, author=None, committer=committer, message=b"Notes added by 'git notes add'\n", from_=None, merges=[], file_iter=[ commands.NoteModifyCommand(b'1', b'Test note\n') ]), commands.CommitCommand( ref=b'refs/notes/test', mark=None, author=None, committer=committer, message=b"Notes added by 'git notes add'\n", from_=None, merges=[], file_iter=[ commands.NoteModifyCommand(b'1', b'Test test\n') ]) ] self.assertEqual( b"""commit refs/heads/master mark :1 author Ed Mund 1234565432 +0000 committer Ed Mund 1234565432 +0000 data 5 test M 644 inline bar data 0 commit refs/notes/commits committer Ed Mund 1234565432 +0000 data 31 Notes added by 'git notes add' N inline :1 data 10 Test note commit refs/notes/test committer Ed Mund 1234565432 +0000 data 31 Notes added by 'git notes add' N inline :1 data 10 Test test """, b''.join([repr_bytes(s) for s in commits])) class TestPathChecking(TestCase): def test_filemodify_path_checking(self): self.assertRaises(ValueError, commands.FileModifyCommand, b'', 0o100644, None, b'text') self.assertRaises(ValueError, commands.FileModifyCommand, None, 0o100644, None, b'text') def test_filedelete_path_checking(self): self.assertRaises(ValueError, commands.FileDeleteCommand, b'') self.assertRaises(ValueError, commands.FileDeleteCommand, None) def test_filerename_path_checking(self): self.assertRaises(ValueError, commands.FileRenameCommand, b'', b'foo') self.assertRaises(ValueError, commands.FileRenameCommand, None, b'foo') self.assertRaises(ValueError, commands.FileRenameCommand, b'foo', b'') self.assertRaises(ValueError, commands.FileRenameCommand, b'foo', None) def test_filecopy_path_checking(self): self.assertRaises(ValueError, commands.FileCopyCommand, b'', b'foo') self.assertRaises(ValueError, commands.FileCopyCommand, None, b'foo') self.assertRaises(ValueError, commands.FileCopyCommand, b'foo', b'') self.assertRaises(ValueError, commands.FileCopyCommand, b'foo', None) fastimport-0.9.8/fastimport/tests/test_dates.py0000644000175000017500000000215612736225770022560 0ustar jelmerjelmer00000000000000# Copyright (C) 2012 Canonical Ltd # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation; either version 2 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program. If not, see . """Test parsing of dates.""" from unittest import TestCase from fastimport import ( dates, ) class ParseTzTests(TestCase): def test_parse_tz_utc(self): self.assertEqual(0, dates.parse_tz(b'+0000')) self.assertEqual(0, dates.parse_tz(b'-0000')) def test_parse_tz_cet(self): self.assertEqual(3600, dates.parse_tz(b'+0100')) def test_parse_tz_odd(self): self.assertEqual(1864800, dates.parse_tz(b'+51800')) fastimport-0.9.8/fastimport/tests/test_filter_processor.py0000644000175000017500000004713312736225770025050 0ustar jelmerjelmer00000000000000# Copyright (C) 2009 Canonical Ltd # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation; either version 2 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program. If not, see . """Test FilterProcessor""" from io import BytesIO from unittest import TestCase from fastimport import ( parser, ) from fastimport.processors import ( filter_processor, ) # A sample input stream containing all (top level) import commands _SAMPLE_ALL = \ b"""blob mark :1 data 4 foo commit refs/heads/master mark :2 committer Joe 1234567890 +1000 data 14 Initial import M 644 :1 COPYING checkpoint progress first import done reset refs/remote/origin/master from :2 tag v0.1 from :2 tagger Joe 1234567890 +1000 data 12 release v0.1 """ # A sample input stream creating the following tree: # # NEWS # doc/README.txt # doc/index.txt _SAMPLE_WITH_DIR = \ b"""blob mark :1 data 9 Welcome! commit refs/heads/master mark :100 committer a 1234798653 +0000 data 4 test M 644 :1 doc/README.txt blob mark :2 data 17 Life is good ... commit refs/heads/master mark :101 committer a 1234798653 +0000 data 8 test ing from :100 M 644 :2 NEWS blob mark :3 data 19 Welcome! my friend blob mark :4 data 11 == Docs == commit refs/heads/master mark :102 committer d 1234798653 +0000 data 8 test ing from :101 M 644 :3 doc/README.txt M 644 :4 doc/index.txt """ class TestCaseWithFiltering(TestCase): def assertFiltering(self, input_stream, params, expected): outf = BytesIO() proc = filter_processor.FilterProcessor( params=params) proc.outf = outf s = BytesIO(input_stream) p = parser.ImportParser(s) proc.process(p.iter_commands) out = outf.getvalue() self.assertEqual(expected, out) class TestNoFiltering(TestCaseWithFiltering): def test_params_not_given(self): self.assertFiltering(_SAMPLE_ALL, None, _SAMPLE_ALL) def test_params_are_none(self): params = {b'include_paths': None, b'exclude_paths': None} self.assertFiltering(_SAMPLE_ALL, params, _SAMPLE_ALL) class TestIncludePaths(TestCaseWithFiltering): def test_file_in_root(self): # Things to note: # * only referenced blobs are retained # * from clause is dropped from the first command params = {b'include_paths': [b'NEWS']} self.assertFiltering(_SAMPLE_WITH_DIR, params, \ b"""blob mark :2 data 17 Life is good ... commit refs/heads/master mark :101 committer a 1234798653 +0000 data 8 test ing M 644 :2 NEWS """) def test_file_in_subdir(self): # Additional things to note: # * new root: path is now index.txt, not doc/index.txt # * other files changed in matching commits are excluded params = {b'include_paths': [b'doc/index.txt']} self.assertFiltering(_SAMPLE_WITH_DIR, params, \ b"""blob mark :4 data 11 == Docs == commit refs/heads/master mark :102 committer d 1234798653 +0000 data 8 test ing M 644 :4 index.txt """) def test_file_with_changes(self): # Additional things to note: # * from updated to reference parents in the output params = {b'include_paths': [b'doc/README.txt']} self.assertFiltering(_SAMPLE_WITH_DIR, params, \ b"""blob mark :1 data 9 Welcome! commit refs/heads/master mark :100 committer a 1234798653 +0000 data 4 test M 644 :1 README.txt blob mark :3 data 19 Welcome! my friend commit refs/heads/master mark :102 committer d 1234798653 +0000 data 8 test ing from :100 M 644 :3 README.txt """) def test_subdir(self): params = {b'include_paths': [b'doc/']} self.assertFiltering(_SAMPLE_WITH_DIR, params, \ b"""blob mark :1 data 9 Welcome! commit refs/heads/master mark :100 committer a 1234798653 +0000 data 4 test M 644 :1 README.txt blob mark :3 data 19 Welcome! my friend blob mark :4 data 11 == Docs == commit refs/heads/master mark :102 committer d 1234798653 +0000 data 8 test ing from :100 M 644 :3 README.txt M 644 :4 index.txt """) def test_multiple_files_in_subdir(self): # The new root should be the subdrectory params = {b'include_paths': [b'doc/README.txt', b'doc/index.txt']} self.assertFiltering(_SAMPLE_WITH_DIR, params, \ b"""blob mark :1 data 9 Welcome! commit refs/heads/master mark :100 committer a 1234798653 +0000 data 4 test M 644 :1 README.txt blob mark :3 data 19 Welcome! my friend blob mark :4 data 11 == Docs == commit refs/heads/master mark :102 committer d 1234798653 +0000 data 8 test ing from :100 M 644 :3 README.txt M 644 :4 index.txt """) class TestExcludePaths(TestCaseWithFiltering): def test_file_in_root(self): params = {b'exclude_paths': [b'NEWS']} self.assertFiltering(_SAMPLE_WITH_DIR, params, \ b"""blob mark :1 data 9 Welcome! commit refs/heads/master mark :100 committer a 1234798653 +0000 data 4 test M 644 :1 doc/README.txt blob mark :3 data 19 Welcome! my friend blob mark :4 data 11 == Docs == commit refs/heads/master mark :102 committer d 1234798653 +0000 data 8 test ing from :100 M 644 :3 doc/README.txt M 644 :4 doc/index.txt """) def test_file_in_subdir(self): params = {b'exclude_paths': [b'doc/README.txt']} self.assertFiltering(_SAMPLE_WITH_DIR, params, \ b"""blob mark :2 data 17 Life is good ... commit refs/heads/master mark :101 committer a 1234798653 +0000 data 8 test ing M 644 :2 NEWS blob mark :4 data 11 == Docs == commit refs/heads/master mark :102 committer d 1234798653 +0000 data 8 test ing from :101 M 644 :4 doc/index.txt """) def test_subdir(self): params = {b'exclude_paths': [b'doc/']} self.assertFiltering(_SAMPLE_WITH_DIR, params, \ b"""blob mark :2 data 17 Life is good ... commit refs/heads/master mark :101 committer a 1234798653 +0000 data 8 test ing M 644 :2 NEWS """) def test_multple_files(self): params = {b'exclude_paths': [b'doc/index.txt', b'NEWS']} self.assertFiltering(_SAMPLE_WITH_DIR, params, \ b"""blob mark :1 data 9 Welcome! commit refs/heads/master mark :100 committer a 1234798653 +0000 data 4 test M 644 :1 doc/README.txt blob mark :3 data 19 Welcome! my friend commit refs/heads/master mark :102 committer d 1234798653 +0000 data 8 test ing from :100 M 644 :3 doc/README.txt """) class TestIncludeAndExcludePaths(TestCaseWithFiltering): def test_included_dir_and_excluded_file(self): params = {b'include_paths': [b'doc/'], b'exclude_paths': [b'doc/index.txt']} self.assertFiltering(_SAMPLE_WITH_DIR, params, \ b"""blob mark :1 data 9 Welcome! commit refs/heads/master mark :100 committer a 1234798653 +0000 data 4 test M 644 :1 README.txt blob mark :3 data 19 Welcome! my friend commit refs/heads/master mark :102 committer d 1234798653 +0000 data 8 test ing from :100 M 644 :3 README.txt """) # A sample input stream creating the following tree: # # NEWS # doc/README.txt # doc/index.txt # # It then renames doc/README.txt => doc/README _SAMPLE_WITH_RENAME_INSIDE = _SAMPLE_WITH_DIR + \ b"""commit refs/heads/master mark :103 committer d 1234798653 +0000 data 10 move intro from :102 R doc/README.txt doc/README """ # A sample input stream creating the following tree: # # NEWS # doc/README.txt # doc/index.txt # # It then renames doc/README.txt => README _SAMPLE_WITH_RENAME_TO_OUTSIDE = _SAMPLE_WITH_DIR + \ b"""commit refs/heads/master mark :103 committer d 1234798653 +0000 data 10 move intro from :102 R doc/README.txt README """ # A sample input stream creating the following tree: # # NEWS # doc/README.txt # doc/index.txt # # It then renames NEWS => doc/NEWS _SAMPLE_WITH_RENAME_TO_INSIDE = _SAMPLE_WITH_DIR + \ b"""commit refs/heads/master mark :103 committer d 1234798653 +0000 data 10 move intro from :102 R NEWS doc/NEWS """ class TestIncludePathsWithRenames(TestCaseWithFiltering): def test_rename_all_inside(self): # These rename commands ought to be kept but adjusted for the new root params = {b'include_paths': [b'doc/']} self.assertFiltering(_SAMPLE_WITH_RENAME_INSIDE, params, \ b"""blob mark :1 data 9 Welcome! commit refs/heads/master mark :100 committer a 1234798653 +0000 data 4 test M 644 :1 README.txt blob mark :3 data 19 Welcome! my friend blob mark :4 data 11 == Docs == commit refs/heads/master mark :102 committer d 1234798653 +0000 data 8 test ing from :100 M 644 :3 README.txt M 644 :4 index.txt commit refs/heads/master mark :103 committer d 1234798653 +0000 data 10 move intro from :102 R README.txt README """) def test_rename_to_outside(self): # These rename commands become deletes params = {b'include_paths': [b'doc/']} self.assertFiltering(_SAMPLE_WITH_RENAME_TO_OUTSIDE, params, \ b"""blob mark :1 data 9 Welcome! commit refs/heads/master mark :100 committer a 1234798653 +0000 data 4 test M 644 :1 README.txt blob mark :3 data 19 Welcome! my friend blob mark :4 data 11 == Docs == commit refs/heads/master mark :102 committer d 1234798653 +0000 data 8 test ing from :100 M 644 :3 README.txt M 644 :4 index.txt commit refs/heads/master mark :103 committer d 1234798653 +0000 data 10 move intro from :102 D README.txt """) def test_rename_to_inside(self): # This ought to create a new file but doesn't yet params = {b'include_paths': [b'doc/']} self.assertFiltering(_SAMPLE_WITH_RENAME_TO_INSIDE, params, \ b"""blob mark :1 data 9 Welcome! commit refs/heads/master mark :100 committer a 1234798653 +0000 data 4 test M 644 :1 README.txt blob mark :3 data 19 Welcome! my friend blob mark :4 data 11 == Docs == commit refs/heads/master mark :102 committer d 1234798653 +0000 data 8 test ing from :100 M 644 :3 README.txt M 644 :4 index.txt """) # A sample input stream creating the following tree: # # NEWS # doc/README.txt # doc/index.txt # # It then copies doc/README.txt => doc/README _SAMPLE_WITH_COPY_INSIDE = _SAMPLE_WITH_DIR + \ b"""commit refs/heads/master mark :103 committer d 1234798653 +0000 data 10 move intro from :102 C doc/README.txt doc/README """ # A sample input stream creating the following tree: # # NEWS # doc/README.txt # doc/index.txt # # It then copies doc/README.txt => README _SAMPLE_WITH_COPY_TO_OUTSIDE = _SAMPLE_WITH_DIR + \ b"""commit refs/heads/master mark :103 committer d 1234798653 +0000 data 10 move intro from :102 C doc/README.txt README """ # A sample input stream creating the following tree: # # NEWS # doc/README.txt # doc/index.txt # # It then copies NEWS => doc/NEWS _SAMPLE_WITH_COPY_TO_INSIDE = _SAMPLE_WITH_DIR + \ b"""commit refs/heads/master mark :103 committer d 1234798653 +0000 data 10 move intro from :102 C NEWS doc/NEWS """ class TestIncludePathsWithCopies(TestCaseWithFiltering): def test_copy_all_inside(self): # These copy commands ought to be kept but adjusted for the new root params = {b'include_paths': [b'doc/']} self.assertFiltering(_SAMPLE_WITH_COPY_INSIDE, params, \ b"""blob mark :1 data 9 Welcome! commit refs/heads/master mark :100 committer a 1234798653 +0000 data 4 test M 644 :1 README.txt blob mark :3 data 19 Welcome! my friend blob mark :4 data 11 == Docs == commit refs/heads/master mark :102 committer d 1234798653 +0000 data 8 test ing from :100 M 644 :3 README.txt M 644 :4 index.txt commit refs/heads/master mark :103 committer d 1234798653 +0000 data 10 move intro from :102 C README.txt README """) def test_copy_to_outside(self): # This can be ignored params = {b'include_paths': [b'doc/']} self.assertFiltering(_SAMPLE_WITH_COPY_TO_OUTSIDE, params, \ b"""blob mark :1 data 9 Welcome! commit refs/heads/master mark :100 committer a 1234798653 +0000 data 4 test M 644 :1 README.txt blob mark :3 data 19 Welcome! my friend blob mark :4 data 11 == Docs == commit refs/heads/master mark :102 committer d 1234798653 +0000 data 8 test ing from :100 M 644 :3 README.txt M 644 :4 index.txt """) def test_copy_to_inside(self): # This ought to create a new file but doesn't yet params = {b'include_paths': [b'doc/']} self.assertFiltering(_SAMPLE_WITH_COPY_TO_INSIDE, params, \ b"""blob mark :1 data 9 Welcome! commit refs/heads/master mark :100 committer a 1234798653 +0000 data 4 test M 644 :1 README.txt blob mark :3 data 19 Welcome! my friend blob mark :4 data 11 == Docs == commit refs/heads/master mark :102 committer d 1234798653 +0000 data 8 test ing from :100 M 644 :3 README.txt M 644 :4 index.txt """) # A sample input stream with deleteall's creating the following tree: # # NEWS # doc/README.txt # doc/index.txt _SAMPLE_WITH_DELETEALL = \ b"""blob mark :1 data 9 Welcome! commit refs/heads/master mark :100 committer a 1234798653 +0000 data 4 test deleteall M 644 :1 doc/README.txt blob mark :3 data 19 Welcome! my friend blob mark :4 data 11 == Docs == commit refs/heads/master mark :102 committer d 1234798653 +0000 data 8 test ing from :100 deleteall M 644 :3 doc/README.txt M 644 :4 doc/index.txt """ class TestIncludePathsWithDeleteAll(TestCaseWithFiltering): def test_deleteall(self): params = {b'include_paths': [b'doc/index.txt']} self.assertFiltering(_SAMPLE_WITH_DELETEALL, params, \ b"""blob mark :4 data 11 == Docs == commit refs/heads/master mark :102 committer d 1234798653 +0000 data 8 test ing from :100 deleteall M 644 :4 index.txt """) _SAMPLE_WITH_TAGS = _SAMPLE_WITH_DIR + \ b"""tag v0.1 from :100 tagger d 1234798653 +0000 data 12 release v0.1 tag v0.2 from :102 tagger d 1234798653 +0000 data 12 release v0.2 """ class TestIncludePathsWithTags(TestCaseWithFiltering): def test_tag_retention(self): # If a tag references a commit with a parent we kept, # keep the tag but adjust 'from' accordingly. # Otherwise, delete the tag command. params = {b'include_paths': [b'NEWS']} self.assertFiltering(_SAMPLE_WITH_TAGS, params, \ b"""blob mark :2 data 17 Life is good ... commit refs/heads/master mark :101 committer a 1234798653 +0000 data 8 test ing M 644 :2 NEWS tag v0.2 from :101 tagger d 1234798653 +0000 data 12 release v0.2 """) _SAMPLE_WITH_RESETS = _SAMPLE_WITH_DIR + \ b"""reset refs/heads/foo reset refs/heads/bar from :102 """ class TestIncludePathsWithResets(TestCaseWithFiltering): def test_reset_retention(self): # Resets init'ing a branch (without a from) are passed through. # If a reset references a commit with a parent we kept, # keep the reset but adjust 'from' accordingly. params = {b'include_paths': [b'NEWS']} self.assertFiltering(_SAMPLE_WITH_RESETS, params, \ b"""blob mark :2 data 17 Life is good ... commit refs/heads/master mark :101 committer a 1234798653 +0000 data 8 test ing M 644 :2 NEWS reset refs/heads/foo reset refs/heads/bar from :101 """) # A sample input stream containing empty commit _SAMPLE_EMPTY_COMMIT = \ b"""blob mark :1 data 4 foo commit refs/heads/master mark :2 committer Joe 1234567890 +1000 data 14 Initial import M 644 :1 COPYING commit refs/heads/master mark :3 committer Joe 1234567890 +1000 data 12 empty commit """ # A sample input stream containing unresolved from and merge references _SAMPLE_FROM_MERGE_COMMIT = \ b"""blob mark :1 data 4 foo commit refs/heads/master mark :3 committer Joe 1234567890 +1000 data 6 import M 644 :1 COPYING blob mark :2 data 4 bar commit refs/heads/master mark :4 committer Joe 1234567890 +1000 data 19 unknown from commit from :999 M 644 :2 data/DATA blob mark :99 data 4 bar commit refs/heads/master mark :5 committer Joe 1234567890 +1000 data 12 merge commit from :3 merge :4 merge :1001 M 644 :99 data/DATA2 """ class TestSquashEmptyCommitsFlag(TestCaseWithFiltering): def test_squash_empty_commit(self): params = {b'include_paths': None, b'exclude_paths': None} self.assertFiltering(_SAMPLE_EMPTY_COMMIT, params, \ b"""blob mark :1 data 4 foo commit refs/heads/master mark :2 committer Joe 1234567890 +1000 data 14 Initial import M 644 :1 COPYING """) def test_keep_empty_commit(self): params = {b'include_paths': None, b'exclude_paths': None, b'squash_empty_commits': False} self.assertFiltering(_SAMPLE_EMPTY_COMMIT, params, _SAMPLE_EMPTY_COMMIT) def test_squash_unresolved_references(self): params = {b'include_paths': None, b'exclude_paths': None} self.assertFiltering(_SAMPLE_FROM_MERGE_COMMIT, params, \ b"""blob mark :1 data 4 foo commit refs/heads/master mark :3 committer Joe 1234567890 +1000 data 6 import M 644 :1 COPYING blob mark :2 data 4 bar commit refs/heads/master mark :4 committer Joe 1234567890 +1000 data 19 unknown from commit from :999 M 644 :2 data/DATA blob mark :99 data 4 bar commit refs/heads/master mark :5 committer Joe 1234567890 +1000 data 12 merge commit from :3 merge :4 merge :1001 M 644 :99 data/DATA2 """) def test_keep_unresolved_from_and_merge(self): params = {b'include_paths': None, b'exclude_paths': None, b'squash_empty_commits': False} self.assertFiltering(_SAMPLE_FROM_MERGE_COMMIT, params, _SAMPLE_FROM_MERGE_COMMIT) def test_with_excludes(self): params = {b'include_paths': None, b'exclude_paths': [b'data/DATA'], b'squash_empty_commits': False} self.assertFiltering(_SAMPLE_FROM_MERGE_COMMIT, params, \ b"""blob mark :1 data 4 foo commit refs/heads/master mark :3 committer Joe 1234567890 +1000 data 6 import M 644 :1 COPYING commit refs/heads/master mark :4 committer Joe 1234567890 +1000 data 19 unknown from commit from :999 blob mark :99 data 4 bar commit refs/heads/master mark :5 committer Joe 1234567890 +1000 data 12 merge commit from :3 merge :4 merge :1001 M 644 :99 data/DATA2 """) def test_with_file_includes(self): params = {b'include_paths': [b'COPYING', b'data/DATA2'], b'exclude_paths': None, b'squash_empty_commits': False} self.assertFiltering(_SAMPLE_FROM_MERGE_COMMIT, params, \ b"""blob mark :1 data 4 foo commit refs/heads/master mark :3 committer Joe 1234567890 +1000 data 6 import M 644 :1 COPYING commit refs/heads/master mark :4 committer Joe 1234567890 +1000 data 19 unknown from commit from :999 blob mark :99 data 4 bar commit refs/heads/master mark :5 committer Joe 1234567890 +1000 data 12 merge commit from :3 merge :4 merge :1001 M 644 :99 data/DATA2 """ ) def test_with_directory_includes(self): params = {b'include_paths': [b'data/'], b'exclude_paths': None, b'squash_empty_commits': False} self.assertFiltering(_SAMPLE_FROM_MERGE_COMMIT, params, \ b"""commit refs/heads/master mark :3 committer Joe 1234567890 +1000 data 6 import blob mark :2 data 4 bar commit refs/heads/master mark :4 committer Joe 1234567890 +1000 data 19 unknown from commit from :999 M 644 :2 DATA blob mark :99 data 4 bar commit refs/heads/master mark :5 committer Joe 1234567890 +1000 data 12 merge commit from :3 merge :4 merge :1001 M 644 :99 DATA2 """) fastimport-0.9.8/NEWS0000644000175000017500000000262713264642514015213 0ustar jelmerjelmer000000000000000.9.8 2018-04-15 * Fix version number. (Jelmer Vernooij) 0.9.7 2018-04-15 * Don't attempt to encode bytestrings in utf8_bytes_helper(). (Jelmer Vernooij, #1647101) * Add fast-import-filter, fast-import-query and fast-import-info script. (Jelmer Vernooij) 0.9.6 2016-04-19 * Add python3.4 support (Jelmer Vernooij) 0.9.5 2016-04-18 * Add python3.5 support. (Félix Mattrat) 0.9.4 2014-07-04 * Get handlers from class object using getattr() for possible inheritance (Cécile Tonglet) * Fix 'check-pypy' by removing use of nonexistant target. (masklinn) * Use namedtuple for authorship tuple in Commit.{author,committer}. (masklinn) 0.9.3 2014-03-01 * Remove unused and untested helper single_plural, invert_dict, invert_dictset, defines_to_dict and binary_stream. (Jelmer Vernooij) * Install NEWS and README files. 0.9.2 2012-04-03 * Remove reftracker and idmapfile, which are bzr-specific. (Jelmer Vernooij, #693507) * Cope with invalid timezones like +61800 a little bit better. (Jelmer Vernooij, #959154) * Allow non-strict parsing of fastimport streams, when a tagger is missing an email address. (Jelmer Vernooij, #730607) 0.9.1 2012-02-28 * Update FSF address in headers. (Dan Callaghan, #868800) * Support 'done' feature. (Jelmer Vernooij, #942563) * Rename tarball for the benefit of pip. (Jelmer Vernooij, #779690) 0.9.0 2011-01-30 Initial release.