Remove unused (for csv generation) code.

This repo now just generates csv files, these files are then used by the git-notebook repo to load and analyze in a Jupyter Notebook.

Makefile

@@ -1,34 +0,0 @@
-PREFIX=/usr/local
-BINDIR=$(PREFIX)/bin
-RESOURCEDIR=$(PREFIX)/share/gitstats
-RESOURCES=gitstats.css sortable.js *.gif
-BINARIES=gitstats
-VERSION=$(shell git describe 2>/dev/null || git rev-parse --short HEAD 2>/dev/null || date +%Y-%m-%d)
-SEDVERSION=perl -pi -e 's/VERSION = 0/VERSION = "$(VERSION)"/' --
-
-all: help
-
-help:
-	@echo "Usage:"
-	@echo
-	@echo "make install                   # install to ${PREFIX}"
-	@echo "make install PREFIX=~          # install to ~"
-	@echo "make release [VERSION=foo]     # make a release tarball"
-	@echo
-
-install:
-	install -d $(BINDIR) $(RESOURCEDIR)
-	install -v $(BINARIES) $(BINDIR)
-	install -v -m 644 $(RESOURCES) $(RESOURCEDIR)
-	$(SEDVERSION) $(BINDIR)/gitstats
-
-release:
-	@cp gitstats gitstats.tmp
-	@$(SEDVERSION) gitstats.tmp
-	@tar --owner=0 --group=0 --transform 's!^!gitstats/!' --transform 's!gitstats.tmp!gitstats!' -zcf gitstats-$(VERSION).tar.gz gitstats.tmp $(RESOURCES) doc/ Makefile
-	@$(RM) gitstats.tmp
-
-man:
-	pod2man --center "User Commands" -r $(VERSION) doc/gitstats.pod > doc/gitstats.1
-
-.PHONY: all help install release

README.md

@@ -2,20 +2,15 @@
 
 A utility to pull a number of statistics from a git repo including:
 
-* Total LOC
+* Total LOC (by file type)
 * LOC (by various time periods)
 * Commits (by various time periods)
 * Commits (by various authors)
 * Files (by type)
 * Files (by various time periods)
-* Tags (by date, authors, volume)
 
 ## Usage
 
 `pip install gitstats`
 
 `gitstats <repo_dir>+ <output_dir>`
-
-OR
-
-`gencsvstats <repo_dir>+ <output_dir>`

doc/AUTHOR

@@ -1,6 +0,0 @@
-This work was forked from hoxu@users.sf.net and is authored by
-Daniel Rapp (rappdw@gmail.com)
-
-See the following command for list of authors who have contributed:
-  $ git shortlog HEAD
-

doc/GPLv2

@@ -1,339 +0,0 @@
-		    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.
-
-    <one line to give the program's name and a brief idea of what it does.>
-    Copyright (C) <year>  <name of author>
-
-    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.
-
-  <signature of Ty Coon>, 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.

doc/GPLv3

@@ -1,674 +0,0 @@
-                    GNU GENERAL PUBLIC LICENSE
-                       Version 3, 29 June 2007
-
- Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
- Everyone is permitted to copy and distribute verbatim copies
- of this license document, but changing it is not allowed.
-
-                            Preamble
-
-  The GNU General Public License is a free, copyleft license for
-software and other kinds of works.
-
-  The licenses for most software and other practical works are designed
-to take away your freedom to share and change the works.  By contrast,
-the GNU General Public License is intended to guarantee your freedom to
-share and change all versions of a program--to make sure it remains free
-software for all its users.  We, the Free Software Foundation, use the
-GNU General Public License for most of our software; it applies also to
-any other work released this way by its authors.  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
-them 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 prevent others from denying you
-these rights or asking you to surrender the rights.  Therefore, you have
-certain responsibilities if you distribute copies of the software, or if
-you modify it: responsibilities to respect the freedom of others.
-
-  For example, if you distribute copies of such a program, whether
-gratis or for a fee, you must pass on to the recipients the same
-freedoms that you received.  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.
-
-  Developers that use the GNU GPL protect your rights with two steps:
-(1) assert copyright on the software, and (2) offer you this License
-giving you legal permission to copy, distribute and/or modify it.
-
-  For the developers' and authors' protection, the GPL clearly explains
-that there is no warranty for this free software.  For both users' and
-authors' sake, the GPL requires that modified versions be marked as
-changed, so that their problems will not be attributed erroneously to
-authors of previous versions.
-
-  Some devices are designed to deny users access to install or run
-modified versions of the software inside them, although the manufacturer
-can do so.  This is fundamentally incompatible with the aim of
-protecting users' freedom to change the software.  The systematic
-pattern of such abuse occurs in the area of products for individuals to
-use, which is precisely where it is most unacceptable.  Therefore, we
-have designed this version of the GPL to prohibit the practice for those
-products.  If such problems arise substantially in other domains, we
-stand ready to extend this provision to those domains in future versions
-of the GPL, as needed to protect the freedom of users.
-
-  Finally, every program is threatened constantly by software patents.
-States should not allow patents to restrict development and use of
-software on general-purpose computers, but in those that do, we wish to
-avoid the special danger that patents applied to a free program could
-make it effectively proprietary.  To prevent this, the GPL assures that
-patents cannot be used to render the program non-free.
-
-  The precise terms and conditions for copying, distribution and
-modification follow.
-
-                       TERMS AND CONDITIONS
-
-  0. Definitions.
-
-  "This License" refers to version 3 of the GNU General Public License.
-
-  "Copyright" also means copyright-like laws that apply to other kinds of
-works, such as semiconductor masks.
-
-  "The Program" refers to any copyrightable work licensed under this
-License.  Each licensee is addressed as "you".  "Licensees" and
-"recipients" may be individuals or organizations.
-
-  To "modify" a work means to copy from or adapt all or part of the work
-in a fashion requiring copyright permission, other than the making of an
-exact copy.  The resulting work is called a "modified version" of the
-earlier work or a work "based on" the earlier work.
-
-  A "covered work" means either the unmodified Program or a work based
-on the Program.
-
-  To "propagate" a work means to do anything with it that, without
-permission, would make you directly or secondarily liable for
-infringement under applicable copyright law, except executing it on a
-computer or modifying a private copy.  Propagation includes copying,
-distribution (with or without modification), making available to the
-public, and in some countries other activities as well.
-
-  To "convey" a work means any kind of propagation that enables other
-parties to make or receive copies.  Mere interaction with a user through
-a computer network, with no transfer of a copy, is not conveying.
-
-  An interactive user interface displays "Appropriate Legal Notices"
-to the extent that it includes a convenient and prominently visible
-feature that (1) displays an appropriate copyright notice, and (2)
-tells the user that there is no warranty for the work (except to the
-extent that warranties are provided), that licensees may convey the
-work under this License, and how to view a copy of this License.  If
-the interface presents a list of user commands or options, such as a
-menu, a prominent item in the list meets this criterion.
-
-  1. Source Code.
-
-  The "source code" for a work means the preferred form of the work
-for making modifications to it.  "Object code" means any non-source
-form of a work.
-
-  A "Standard Interface" means an interface that either is an official
-standard defined by a recognized standards body, or, in the case of
-interfaces specified for a particular programming language, one that
-is widely used among developers working in that language.
-
-  The "System Libraries" of an executable work include anything, other
-than the work as a whole, that (a) is included in the normal form of
-packaging a Major Component, but which is not part of that Major
-Component, and (b) serves only to enable use of the work with that
-Major Component, or to implement a Standard Interface for which an
-implementation is available to the public in source code form.  A
-"Major Component", in this context, means a major essential component
-(kernel, window system, and so on) of the specific operating system
-(if any) on which the executable work runs, or a compiler used to
-produce the work, or an object code interpreter used to run it.
-
-  The "Corresponding Source" for a work in object code form means all
-the source code needed to generate, install, and (for an executable
-work) run the object code and to modify the work, including scripts to
-control those activities.  However, it does not include the work's
-System Libraries, or general-purpose tools or generally available free
-programs which are used unmodified in performing those activities but
-which are not part of the work.  For example, Corresponding Source
-includes interface definition files associated with source files for
-the work, and the source code for shared libraries and dynamically
-linked subprograms that the work is specifically designed to require,
-such as by intimate data communication or control flow between those
-subprograms and other parts of the work.
-
-  The Corresponding Source need not include anything that users
-can regenerate automatically from other parts of the Corresponding
-Source.
-
-  The Corresponding Source for a work in source code form is that
-same work.
-
-  2. Basic Permissions.
-
-  All rights granted under this License are granted for the term of
-copyright on the Program, and are irrevocable provided the stated
-conditions are met.  This License explicitly affirms your unlimited
-permission to run the unmodified Program.  The output from running a
-covered work is covered by this License only if the output, given its
-content, constitutes a covered work.  This License acknowledges your
-rights of fair use or other equivalent, as provided by copyright law.
-
-  You may make, run and propagate covered works that you do not
-convey, without conditions so long as your license otherwise remains
-in force.  You may convey covered works to others for the sole purpose
-of having them make modifications exclusively for you, or provide you
-with facilities for running those works, provided that you comply with
-the terms of this License in conveying all material for which you do
-not control copyright.  Those thus making or running the covered works
-for you must do so exclusively on your behalf, under your direction
-and control, on terms that prohibit them from making any copies of
-your copyrighted material outside their relationship with you.
-
-  Conveying under any other circumstances is permitted solely under
-the conditions stated below.  Sublicensing is not allowed; section 10
-makes it unnecessary.
-
-  3. Protecting Users' Legal Rights From Anti-Circumvention Law.
-
-  No covered work shall be deemed part of an effective technological
-measure under any applicable law fulfilling obligations under article
-11 of the WIPO copyright treaty adopted on 20 December 1996, or
-similar laws prohibiting or restricting circumvention of such
-measures.
-
-  When you convey a covered work, you waive any legal power to forbid
-circumvention of technological measures to the extent such circumvention
-is effected by exercising rights under this License with respect to
-the covered work, and you disclaim any intention to limit operation or
-modification of the work as a means of enforcing, against the work's
-users, your or third parties' legal rights to forbid circumvention of
-technological measures.
-
-  4. Conveying Verbatim Copies.
-
-  You may convey 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;
-keep intact all notices stating that this License and any
-non-permissive terms added in accord with section 7 apply to the code;
-keep intact all notices of the absence of any warranty; and give all
-recipients a copy of this License along with the Program.
-
-  You may charge any price or no price for each copy that you convey,
-and you may offer support or warranty protection for a fee.
-
-  5. Conveying Modified Source Versions.
-
-  You may convey a work based on the Program, or the modifications to
-produce it from the Program, in the form of source code under the
-terms of section 4, provided that you also meet all of these conditions:
-
-    a) The work must carry prominent notices stating that you modified
-    it, and giving a relevant date.
-
-    b) The work must carry prominent notices stating that it is
-    released under this License and any conditions added under section
-    7.  This requirement modifies the requirement in section 4 to
-    "keep intact all notices".
-
-    c) You must license the entire work, as a whole, under this
-    License to anyone who comes into possession of a copy.  This
-    License will therefore apply, along with any applicable section 7
-    additional terms, to the whole of the work, and all its parts,
-    regardless of how they are packaged.  This License gives no
-    permission to license the work in any other way, but it does not
-    invalidate such permission if you have separately received it.
-
-    d) If the work has interactive user interfaces, each must display
-    Appropriate Legal Notices; however, if the Program has interactive
-    interfaces that do not display Appropriate Legal Notices, your
-    work need not make them do so.
-
-  A compilation of a covered work with other separate and independent
-works, which are not by their nature extensions of the covered work,
-and which are not combined with it such as to form a larger program,
-in or on a volume of a storage or distribution medium, is called an
-"aggregate" if the compilation and its resulting copyright are not
-used to limit the access or legal rights of the compilation's users
-beyond what the individual works permit.  Inclusion of a covered work
-in an aggregate does not cause this License to apply to the other
-parts of the aggregate.
-
-  6. Conveying Non-Source Forms.
-
-  You may convey a covered work in object code form under the terms
-of sections 4 and 5, provided that you also convey the
-machine-readable Corresponding Source under the terms of this License,
-in one of these ways:
-
-    a) Convey the object code in, or embodied in, a physical product
-    (including a physical distribution medium), accompanied by the
-    Corresponding Source fixed on a durable physical medium
-    customarily used for software interchange.
-
-    b) Convey the object code in, or embodied in, a physical product
-    (including a physical distribution medium), accompanied by a
-    written offer, valid for at least three years and valid for as
-    long as you offer spare parts or customer support for that product
-    model, to give anyone who possesses the object code either (1) a
-    copy of the Corresponding Source for all the software in the
-    product that is covered by this License, on a durable physical
-    medium customarily used for software interchange, for a price no
-    more than your reasonable cost of physically performing this
-    conveying of source, or (2) access to copy the
-    Corresponding Source from a network server at no charge.
-
-    c) Convey individual copies of the object code with a copy of the
-    written offer to provide the Corresponding Source.  This
-    alternative is allowed only occasionally and noncommercially, and
-    only if you received the object code with such an offer, in accord
-    with subsection 6b.
-
-    d) Convey the object code by offering access from a designated
-    place (gratis or for a charge), and offer equivalent access to the
-    Corresponding Source in the same way through the same place at no
-    further charge.  You need not require recipients to copy the
-    Corresponding Source along with the object code.  If the place to
-    copy the object code is a network server, the Corresponding Source
-    may be on a different server (operated by you or a third party)
-    that supports equivalent copying facilities, provided you maintain
-    clear directions next to the object code saying where to find the
-    Corresponding Source.  Regardless of what server hosts the
-    Corresponding Source, you remain obligated to ensure that it is
-    available for as long as needed to satisfy these requirements.
-
-    e) Convey the object code using peer-to-peer transmission, provided
-    you inform other peers where the object code and Corresponding
-    Source of the work are being offered to the general public at no
-    charge under subsection 6d.
-
-  A separable portion of the object code, whose source code is excluded
-from the Corresponding Source as a System Library, need not be
-included in conveying the object code work.
-
-  A "User Product" is either (1) a "consumer product", which means any
-tangible personal property which is normally used for personal, family,
-or household purposes, or (2) anything designed or sold for incorporation
-into a dwelling.  In determining whether a product is a consumer product,
-doubtful cases shall be resolved in favor of coverage.  For a particular
-product received by a particular user, "normally used" refers to a
-typical or common use of that class of product, regardless of the status
-of the particular user or of the way in which the particular user
-actually uses, or expects or is expected to use, the product.  A product
-is a consumer product regardless of whether the product has substantial
-commercial, industrial or non-consumer uses, unless such uses represent
-the only significant mode of use of the product.
-
-  "Installation Information" for a User Product means any methods,
-procedures, authorization keys, or other information required to install
-and execute modified versions of a covered work in that User Product from
-a modified version of its Corresponding Source.  The information must
-suffice to ensure that the continued functioning of the modified object
-code is in no case prevented or interfered with solely because
-modification has been made.
-
-  If you convey an object code work under this section in, or with, or
-specifically for use in, a User Product, and the conveying occurs as
-part of a transaction in which the right of possession and use of the
-User Product is transferred to the recipient in perpetuity or for a
-fixed term (regardless of how the transaction is characterized), the
-Corresponding Source conveyed under this section must be accompanied
-by the Installation Information.  But this requirement does not apply
-if neither you nor any third party retains the ability to install
-modified object code on the User Product (for example, the work has
-been installed in ROM).
-
-  The requirement to provide Installation Information does not include a
-requirement to continue to provide support service, warranty, or updates
-for a work that has been modified or installed by the recipient, or for
-the User Product in which it has been modified or installed.  Access to a
-network may be denied when the modification itself materially and
-adversely affects the operation of the network or violates the rules and
-protocols for communication across the network.
-
-  Corresponding Source conveyed, and Installation Information provided,
-in accord with this section must be in a format that is publicly
-documented (and with an implementation available to the public in
-source code form), and must require no special password or key for
-unpacking, reading or copying.
-
-  7. Additional Terms.
-
-  "Additional permissions" are terms that supplement the terms of this
-License by making exceptions from one or more of its conditions.
-Additional permissions that are applicable to the entire Program shall
-be treated as though they were included in this License, to the extent
-that they are valid under applicable law.  If additional permissions
-apply only to part of the Program, that part may be used separately
-under those permissions, but the entire Program remains governed by
-this License without regard to the additional permissions.
-
-  When you convey a copy of a covered work, you may at your option
-remove any additional permissions from that copy, or from any part of
-it.  (Additional permissions may be written to require their own
-removal in certain cases when you modify the work.)  You may place
-additional permissions on material, added by you to a covered work,
-for which you have or can give appropriate copyright permission.
-
-  Notwithstanding any other provision of this License, for material you
-add to a covered work, you may (if authorized by the copyright holders of
-that material) supplement the terms of this License with terms:
-
-    a) Disclaiming warranty or limiting liability differently from the
-    terms of sections 15 and 16 of this License; or
-
-    b) Requiring preservation of specified reasonable legal notices or
-    author attributions in that material or in the Appropriate Legal
-    Notices displayed by works containing it; or
-
-    c) Prohibiting misrepresentation of the origin of that material, or
-    requiring that modified versions of such material be marked in
-    reasonable ways as different from the original version; or
-
-    d) Limiting the use for publicity purposes of names of licensors or
-    authors of the material; or
-
-    e) Declining to grant rights under trademark law for use of some
-    trade names, trademarks, or service marks; or
-
-    f) Requiring indemnification of licensors and authors of that
-    material by anyone who conveys the material (or modified versions of
-    it) with contractual assumptions of liability to the recipient, for
-    any liability that these contractual assumptions directly impose on
-    those licensors and authors.
-
-  All other non-permissive additional terms are considered "further
-restrictions" within the meaning of section 10.  If the Program as you
-received it, or any part of it, contains a notice stating that it is
-governed by this License along with a term that is a further
-restriction, you may remove that term.  If a license document contains
-a further restriction but permits relicensing or conveying under this
-License, you may add to a covered work material governed by the terms
-of that license document, provided that the further restriction does
-not survive such relicensing or conveying.
-
-  If you add terms to a covered work in accord with this section, you
-must place, in the relevant source files, a statement of the
-additional terms that apply to those files, or a notice indicating
-where to find the applicable terms.
-
-  Additional terms, permissive or non-permissive, may be stated in the
-form of a separately written license, or stated as exceptions;
-the above requirements apply either way.
-
-  8. Termination.
-
-  You may not propagate or modify a covered work except as expressly
-provided under this License.  Any attempt otherwise to propagate or
-modify it is void, and will automatically terminate your rights under
-this License (including any patent licenses granted under the third
-paragraph of section 11).
-
-  However, if you cease all violation of this License, then your
-license from a particular copyright holder is reinstated (a)
-provisionally, unless and until the copyright holder explicitly and
-finally terminates your license, and (b) permanently, if the copyright
-holder fails to notify you of the violation by some reasonable means
-prior to 60 days after the cessation.
-
-  Moreover, your license from a particular copyright holder is
-reinstated permanently if the copyright holder notifies you of the
-violation by some reasonable means, this is the first time you have
-received notice of violation of this License (for any work) from that
-copyright holder, and you cure the violation prior to 30 days after
-your receipt of the notice.
-
-  Termination of your rights under this section does not terminate the
-licenses of parties who have received copies or rights from you under
-this License.  If your rights have been terminated and not permanently
-reinstated, you do not qualify to receive new licenses for the same
-material under section 10.
-
-  9. Acceptance Not Required for Having Copies.
-
-  You are not required to accept this License in order to receive or
-run a copy of the Program.  Ancillary propagation of a covered work
-occurring solely as a consequence of using peer-to-peer transmission
-to receive a copy likewise does not require acceptance.  However,
-nothing other than this License grants you permission to propagate or
-modify any covered work.  These actions infringe copyright if you do
-not accept this License.  Therefore, by modifying or propagating a
-covered work, you indicate your acceptance of this License to do so.
-
-  10. Automatic Licensing of Downstream Recipients.
-
-  Each time you convey a covered work, the recipient automatically
-receives a license from the original licensors, to run, modify and
-propagate that work, subject to this License.  You are not responsible
-for enforcing compliance by third parties with this License.
-
-  An "entity transaction" is a transaction transferring control of an
-organization, or substantially all assets of one, or subdividing an
-organization, or merging organizations.  If propagation of a covered
-work results from an entity transaction, each party to that
-transaction who receives a copy of the work also receives whatever
-licenses to the work the party's predecessor in interest had or could
-give under the previous paragraph, plus a right to possession of the
-Corresponding Source of the work from the predecessor in interest, if
-the predecessor has it or can get it with reasonable efforts.
-
-  You may not impose any further restrictions on the exercise of the
-rights granted or affirmed under this License.  For example, you may
-not impose a license fee, royalty, or other charge for exercise of
-rights granted under this License, and you may not initiate litigation
-(including a cross-claim or counterclaim in a lawsuit) alleging that
-any patent claim is infringed by making, using, selling, offering for
-sale, or importing the Program or any portion of it.
-
-  11. Patents.
-
-  A "contributor" is a copyright holder who authorizes use under this
-License of the Program or a work on which the Program is based.  The
-work thus licensed is called the contributor's "contributor version".
-
-  A contributor's "essential patent claims" are all patent claims
-owned or controlled by the contributor, whether already acquired or
-hereafter acquired, that would be infringed by some manner, permitted
-by this License, of making, using, or selling its contributor version,
-but do not include claims that would be infringed only as a
-consequence of further modification of the contributor version.  For
-purposes of this definition, "control" includes the right to grant
-patent sublicenses in a manner consistent with the requirements of
-this License.
-
-  Each contributor grants you a non-exclusive, worldwide, royalty-free
-patent license under the contributor's essential patent claims, to
-make, use, sell, offer for sale, import and otherwise run, modify and
-propagate the contents of its contributor version.
-
-  In the following three paragraphs, a "patent license" is any express
-agreement or commitment, however denominated, not to enforce a patent
-(such as an express permission to practice a patent or covenant not to
-sue for patent infringement).  To "grant" such a patent license to a
-party means to make such an agreement or commitment not to enforce a
-patent against the party.
-
-  If you convey a covered work, knowingly relying on a patent license,
-and the Corresponding Source of the work is not available for anyone
-to copy, free of charge and under the terms of this License, through a
-publicly available network server or other readily accessible means,
-then you must either (1) cause the Corresponding Source to be so
-available, or (2) arrange to deprive yourself of the benefit of the
-patent license for this particular work, or (3) arrange, in a manner
-consistent with the requirements of this License, to extend the patent
-license to downstream recipients.  "Knowingly relying" means you have
-actual knowledge that, but for the patent license, your conveying the
-covered work in a country, or your recipient's use of the covered work
-in a country, would infringe one or more identifiable patents in that
-country that you have reason to believe are valid.
-
-  If, pursuant to or in connection with a single transaction or
-arrangement, you convey, or propagate by procuring conveyance of, a
-covered work, and grant a patent license to some of the parties
-receiving the covered work authorizing them to use, propagate, modify
-or convey a specific copy of the covered work, then the patent license
-you grant is automatically extended to all recipients of the covered
-work and works based on it.
-
-  A patent license is "discriminatory" if it does not include within
-the scope of its coverage, prohibits the exercise of, or is
-conditioned on the non-exercise of one or more of the rights that are
-specifically granted under this License.  You may not convey a covered
-work if you are a party to an arrangement with a third party that is
-in the business of distributing software, under which you make payment
-to the third party based on the extent of your activity of conveying
-the work, and under which the third party grants, to any of the
-parties who would receive the covered work from you, a discriminatory
-patent license (a) in connection with copies of the covered work
-conveyed by you (or copies made from those copies), or (b) primarily
-for and in connection with specific products or compilations that
-contain the covered work, unless you entered into that arrangement,
-or that patent license was granted, prior to 28 March 2007.
-
-  Nothing in this License shall be construed as excluding or limiting
-any implied license or other defenses to infringement that may
-otherwise be available to you under applicable patent law.
-
-  12. No Surrender of Others' Freedom.
-
-  If 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 convey a
-covered work so as to satisfy simultaneously your obligations under this
-License and any other pertinent obligations, then as a consequence you may
-not convey it at all.  For example, if you agree to terms that obligate you
-to collect a royalty for further conveying from those to whom you convey
-the Program, the only way you could satisfy both those terms and this
-License would be to refrain entirely from conveying the Program.
-
-  13. Use with the GNU Affero General Public License.
-
-  Notwithstanding any other provision of this License, you have
-permission to link or combine any covered work with a work licensed
-under version 3 of the GNU Affero General Public License into a single
-combined work, and to convey the resulting work.  The terms of this
-License will continue to apply to the part which is the covered work,
-but the special requirements of the GNU Affero General Public License,
-section 13, concerning interaction through a network will apply to the
-combination as such.
-
-  14. Revised Versions of this License.
-
-  The Free Software Foundation may publish revised and/or new versions of
-the GNU 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 that a certain numbered version of the GNU General
-Public License "or any later version" applies to it, you have the
-option of following the terms and conditions either of that numbered
-version or of any later version published by the Free Software
-Foundation.  If the Program does not specify a version number of the
-GNU General Public License, you may choose any version ever published
-by the Free Software Foundation.
-
-  If the Program specifies that a proxy can decide which future
-versions of the GNU General Public License can be used, that proxy's
-public statement of acceptance of a version permanently authorizes you
-to choose that version for the Program.
-
-  Later license versions may give you additional or different
-permissions.  However, no additional obligations are imposed on any
-author or copyright holder as a result of your choosing to follow a
-later version.
-
-  15. Disclaimer of Warranty.
-
-  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.
-
-  16. Limitation of Liability.
-
-  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
-WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
-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.
-
-  17. Interpretation of Sections 15 and 16.
-
-  If the disclaimer of warranty and limitation of liability provided
-above cannot be given local legal effect according to their terms,
-reviewing courts shall apply local law that most closely approximates
-an absolute waiver of all civil liability in connection with the
-Program, unless a warranty or assumption of liability accompanies a
-copy of the Program in return for a fee.
-
-                     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
-state the exclusion of warranty; and each file should have at least
-the "copyright" line and a pointer to where the full notice is found.
-
-    <one line to give the program's name and a brief idea of what it does.>
-    Copyright (C) <year>  <name of author>
-
-    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 3 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 <http://www.gnu.org/licenses/>.
-
-Also add information on how to contact you by electronic and paper mail.
-
-  If the program does terminal interaction, make it output a short
-notice like this when it starts in an interactive mode:
-
-    <program>  Copyright (C) <year>  <name of author>
-    This program 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, your program's commands
-might be different; for a GUI interface, you would use an "about box".
-
-  You should also get your employer (if you work as a programmer) or school,
-if any, to sign a "copyright disclaimer" for the program, if necessary.
-For more information on this, and how to apply and follow the GNU GPL, see
-<http://www.gnu.org/licenses/>.
-
-  The GNU 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.  But first, please read
-<http://www.gnu.org/philosophy/why-not-lgpl.html>.

doc/INSTALL

@@ -1,10 +0,0 @@
-gitstats does not currently need to be installed; it's used right from the
-directory (it also assumes some files like the stylesheet are in .)
-
-Suppose you have a git project at /mnt/src/git/project
-and you want to save the statistics to ~/public_html/project
-
-You would run:
-$ ./gitstats /mnt/src/git/project ~/public_html/project
-(go grab a cup of coffee if it's a large project :)
-$ sensible-browser ~/public_html/project/index.html

doc/LICENSE

@@ -1,4 +0,0 @@
-gitstats license is GPLv2/GPLv3, see doc/GPLv2 and doc/GPLv3 respectively.
-
-sortable.js, contained in gitstats, is licensed under the MIT license. See the
-file itself for details.

doc/README

@@ -1,22 +0,0 @@
-gitstats is a statistics generator for git repositories.  It is mostly intended
-for developers, as a way to check some development statistics for a project.
-
-Currently it produces only HTML output with tables and graphs.
-
-Requirements
-============
-- Python (>= 2.6.0)
-- Git (>= 1.5.2.4)
-- Gnuplot (>= 4.0.0)
-- a git repository (bare clone will work as well)
-
-The above versions are not absolute requirements; older versions may work also.
-
-Recommended
-===========
-- Lots of memory and fast disk for large projects
-
-Contributions
-=============
-Patches should be sent under "GPLv2 or later" license - this will allow
-upgrading to newer GPL versions if they are sensible.

doc/TODO.txt

@@ -1,77 +0,0 @@
-[]
-- cleanup: use defaultdict(int) for counting dicts instead of foo[x] = foo.get(x, 0) + 1
-	- not supported in python 2.4 - do any users use python 2.4?
-	- debian lenny (oldstable) has python 2.5
-- bug: multirepo tags
-	- self.tags contains tags from all repos - WRONG
-
-- general: analysis, ohloh-like?
-	- age: active days / days - high % means active project usually
-	- number of contributors (& their active days)
-
-- https://sourceforge.net/tracker/index.php?func=detail&aid=2865754&group_id=203965&atid=987714
-	- gitstats is a great tool, but the one thing that I miss is the number of
-	SLOC or comments on the "lines of code" image. Could this somehow be
-	added?
-
-[Unsorted]
-- clean up after running gnuplot (option to keep .dat files around?)
-- show raw data in some way (the tables used currently aren't very nice)
-- allow multiple stylesheets
-	- parameter --style
-	- styles/{default,...}.css
-- could show some statistics from last year, month, etc... pisg-like?
-- Commandline options
-	--debug / --verbose
-- save command line settings and use them next run if not overridden?
-
-[Stats]
-- General
-	- Total repository size (slooooow)?
-
-- Activity by Time?
-	- (G?) Last 30 days
-	- (G?) Last 12 months
-	- (T) Hour of Week: percentages / coloring?
-	- (G) Pace of Changes - number of line/other changes happening over time
-
-- Authors
-	- (T) List of authors
-		- Lines
-	- (T) Author of Month
-		- Lines
-	- (T) Author of Year
-		- Lines
-
-- Files
-	- Average revisions per file
-	- (G) Average file size: x = date, y = lines/file
-	- (T) Largest Files?
-	- (T) Files With Most Revisions?
-
-- Lines
-	- Average lines/file
-	- (G) Lines of Code: show tags as vertical lines?
-
-- Tags
-	- Lines
-
-- Author page for each author
-	- Name, mail
-	- Total commits (%)
-	- LOC (%)
-	- Last commit: date
-	- First commit: date
-	- Activity by Clock Time
-		- (G) Hour of Day
-		- (G) Day of Week
-	- (T) Activity in Directories: Directory, Changes, LOC, LOC/change
-	- (Most Recent Commits?)
-	- Author of Month(s):
-	- Author of Year(s):
-
-- Pages for years?
-	- Commits (% of all)
-	- Author top ten
-	- Month statistics
-

doc/gitstats.pod

@@ -1,115 +0,0 @@
-=encoding utf8
-
-=head1 NAME
-
-gitstats - git history statistics generator
-
-=head1 SYNOPSIS
-
-B<gitstats> [options] <repository dir> <output dir>
-
-=head1 DESCRIPTION
-
-B<gitstats> is a statistics generator for L<git(1)> repositories. It examines the repository and produces some interesting statistics from the history of it. Currently HTML is the only output format.
-
-=head1 OPTIONS
-
--c option=value
-
-Override a default configuration value. Defaults can be seen by running B<gitstats> without parameters.
-
-=head2 Values:
-
-=over
-
-=item authors_top
-
-How many top authors to show.
-
-=item commit_begin, commit_end
-
-Specify a commit range to generate statistics from. You can specify only commit_end limit statistics to a certain commit or another branch.
-
-=item linear_linestats
-
-When enabled, the lines of code statistics are collected from linear history.
-The downside is that commits of long feature branches appear only at the point
-where a merge commit is made.
-
-If disabled (old behaviour), the problem is that if two branches contain the
-same changes (for example, removal of same lines), the statistics get skewed.
-
-Defaults to on.
-
-=item max_authors
-
-How many authors to show in the list of authors.
-
-=item max_domains
-
-How many domains to show in domains by commits.
-
-=item max_ext_length
-
-Maximum file extension length.
-
-=item processes
-
-Number of concurrent processes to use when extracting git repository data.
-
-=item project_name
-
-Project name to show on the generated pages. Default is to use basename of the repository directory.
-
-=item start_date
-
-Specify a starting date to pass with --since to git.
-
-=item style
-
-CSS stylesheet to use.
-
-=back
-
-=head1 FAQ
-
-Q: How do I generate statistics of a non-master branch?
-
-A: Use C<-c commit_end=web> parameter.
-
-Q: I have files in my git repository that I would like to exclude from the statistics, how do I do that?
-
-A: At the moment the only way is to use L<git-filter-branch(1)> to create a temporary repository and generate the statistics from that.
-
-Q: How do I merge author information when the same author has made commits using different names or emails ?
-
-A: Use git .mailmap feature described in B<MAPPING AUTHORS> of L<git-shortlog(1)>.
-
-=head1 EXAMPLES
-
-=over
-
-=item Generates statistics from a git repository in C<foo> and outputs the result in a directory C<foo_stats>:
-
-  gitstats foo foo_stats
-
-=item As above, but only analyzes the last 10 commits:
-
-  gitstats -c commit_begin='HEAD~10' foo foo_stats
-
-=back
-
-=head1 AUTHORS
-
-B<gitstats> was written by Heikki Hokkanen and others.
-
-See the git repository at https://github.com/rappdw/gitstats for an up-to-date full list of contributors.
-
-=head1 WWW
-
-http://gitstats.sourceforge.net/
-
-=head1 SEE ALSO
-
-L<git(1)>
-

gitstats/__init__.py

@@ -1,7 +1,7 @@
-from gitstats.process import run
+from gitstats.git_csv_generator import gen_csv
 from gitstats._version import get_versions
 __version__ = get_versions()['version']
 del get_versions
 
 if __name__ == "__main__":
-    run()
+    gen_csv()

gitstats/data/__init__.py

@@ -1,10 +1,4 @@
-from .author import Author
-from .author_row import AuthorRow
-from .author_totals import AuthorTotals
-from .tag import Tag
 from .revision import Revision
-from .file import File
-from .loc_by_date import LocByDate
 from .pr import PullRequest
 from .file_info import FileInfo
 from .revision_graph import RevisionGraph

gitstats/data/author.py

@@ -1,25 +0,0 @@
-from collections import defaultdict
-from dataclasses import dataclass, field
-from datetime import timedelta
-from typing import Dict, Set
-
-
-@dataclass
-class Author:
-    lines_added: int = 0
-    lines_removed: int = 0
-    commits: int = 0
-    first_commit_stamp: int = 0
-    last_commit_stamp: int = 0
-    last_active_day: str = ''
-    active_days: Set[str] = field(default_factory=set)
-    place_by_commits: int = 0
-    commits_frac: float = 0.0
-    date_first: str = ''
-    date_last: str = ''
-    timedelta: timedelta = None
-    activity_by_day_and_hour: Dict[int, Dict[int, int]] = field(default_factory=lambda: defaultdict(lambda: defaultdict(int)))
-    extra_effort: int = 0
-    extra_frac: float = 0.0
-
-

gitstats/data/author_row.py

@@ -1,10 +0,0 @@
-from dataclasses import dataclass
-
-@dataclass
-class AuthorRow:
-    hash: str
-    stamp: int
-    author: str
-    files_modified: int
-    lines_inserted: int
-    lines_deleted: int

gitstats/data/author_totals.py

@@ -1,6 +0,0 @@
-from dataclasses import dataclass
-
-@dataclass
-class AuthorTotals:
-    author: str
-    total_commits: int

gitstats/data/file.py

@@ -1,10 +0,0 @@
-from dataclasses import dataclass
-
-@dataclass
-class File:
-    full_path: str
-    ext: str
-    size: int
-    lines: int = 0
-
-

gitstats/data/loc_by_date.py

@@ -1,13 +0,0 @@
-from dataclasses import dataclass
-
-
-@dataclass
-class LocByDate:
-    hash: str = ''
-    stamp: int = 0
-    file_count: int = 0
-    lines_inserted: int = 0
-    lines_deleted: int = 0
-    total_lines: int = 0
-
-

gitstats/data/tag.py

@@ -1,13 +0,0 @@
-from collections import defaultdict
-from dataclasses import dataclass, field
-from typing import Dict
-
-@dataclass
-class Tag:
-    tag: str
-    stamp: int
-    hash: str
-    commits: int = 0
-    authors: Dict[str, int] = field(default_factory=defaultdict(int))
-
-

gitstats/data_generators/__init__.py

@@ -1,9 +1,3 @@
-from .gen_author_data import gen_author_data
-from .gen_author_totals import gen_author_totals_data
-from .gen_tag_data import gen_tag_data
-from .gen_revision_data import gen_revision_data
-from .gen_file_data import gen_file_data
-from .gen_loc_data import gen_loc_data
 from .gen_pr_data import gen_pr_data
 from .gen_revision_graph import gen_revision_graph
 from .gen_complete_file_info import gen_complete_file_info

gitstats/data_generators/gen_author_data.py

@@ -1,87 +0,0 @@
-import csv
-import logging
-import os
-import re
-
-from gitstats import cli, cd
-from gitstats.miscfuncs import getlogrange, getpipeoutput, getstatsummarycounts
-from gitstats.data import AuthorRow
-
-
-def gen_author_data(conf, row_processor, ignore_files=''):
-    '''
-    Given a configuration, pull authorship information. For
-    each author, callback to the row_processor passing an AuthorRow
-
-    :param conf: configuration (mostly used for date limits)
-    :param row_processor: function to receive the callback
-    :return: None
-    '''
-
-    # DBG: git log --shortstat --date-order --pretty=format:"%H %at %aN" --since="2017-10-01" "HEAD"
-    # Results are in the form of
-    #
-    # 3c16756701d264619db0b309f42ebdc713b29827 1522513256 Dan Rapp
-    # 524ee0d32ffbbb8bb82966b769bbf7dbc1d87a68 1522480979 Michael Wright
-    # 1 file changed, 6 insertions(+)
-    #
-    # If there are two (or more) lines,
-    # The first line(s) is the merge to master or other branch
-    # The last line is the commit on the branch
-    lines = getpipeoutput(
-        ['git log --shortstat --date-order --pretty=format:"%%H %%at %%aN" %s %s' % (
-            getlogrange(conf, 'HEAD'), ignore_files)]).split('\n')
-    lines.reverse()
-
-    files = 0
-    inserted = 0
-    deleted = 0
-    stamp = 0
-    for line in lines:
-        if len(line) == 0:
-            continue
-
-        # <stamp> <author>
-        if re.search('files? changed', line) is None:
-            if files + inserted + deleted > 0:  # this case indicates we've already processed the line
-                pos = line.find(' ')
-                if pos != -1:
-                    try:
-                        oldstamp = stamp
-                        tokens = line.split()
-                        sha = tokens[0]
-                        stamp = int(tokens[1])
-                        author = ' '.join(tokens[2:])
-                        if oldstamp > stamp:
-                            # clock skew, keep old timestamp to avoid having ugly graph
-                            stamp = oldstamp
-                        row_processor(AuthorRow(sha, stamp, author, files, inserted, deleted))
-                        # Since subsequent lines are (generally) reflections of merging into a branch
-                        # don't provide "credit" to the author did the merge
-                        (files, inserted, deleted) = 0, 0, 0
-                    except ValueError:
-                        logging.warning(f'unexpected line "{line}')
-                else:
-                    logging.warning(f'unexpected line "{line}')
-        else:
-            numbers = getstatsummarycounts(line)
-
-            if len(numbers) == 3:
-                (files, inserted, deleted) = map(lambda el: int(el), numbers)
-            else:
-                logging.warning(f'Failed to handle line "{line}"')
-                (files, inserted, deleted) = (0, 0, 0)
-
-if __name__ == "__main__":
-    conf, paths, outputpath = cli.get_cli()
-    with open(outputpath, 'w', encoding='utf8') as f:
-        writer = csv.writer(f)
-        writer.writerow(['repo', 'sha', 'stamp', 'author', 'files changed', 'lines inserted', 'lines deleted'])
-
-        for path in paths:
-            repo_name = os.path.split(path)[1]
-            with (cd.cd(path)):
-                def row_processor(row: AuthorRow):
-                    writer.writerow([repo_name, row.hash, row.stamp, row.author, row.files_modified,
-                                     row.lines_inserted, row.lines_deleted])
-                gen_author_data(conf, row_processor)

gitstats/data_generators/gen_author_totals.py

@@ -1,47 +0,0 @@
-import csv
-import os
-
-from gitstats import cli, cd
-from gitstats.miscfuncs import getlogrange, getpipeoutput
-from gitstats.data import AuthorTotals
-
-
-def gen_author_totals_data(conf, row_processor=None, revision_range=None):
-    '''
-    Given configuration, pull total commit per author. For
-    each "row" callback to the row_processor passing an AuthorTotals
-
-    :param conf: configuration (mostly used for date limits)
-    :param row_processor: function to receive the callback
-    :return: count of the number of authors
-    '''
-
-    # DBG: git shortlog -s --since="2017-10-01" "HEAD"
-    if not revision_range:
-        revision_range = getlogrange(conf)
-    lines = getpipeoutput(['git shortlog -s %s' % revision_range]).split('\n')
-    count = 0
-    for line in lines:
-        line = line.strip()
-        if not line:
-            continue
-        count += 1
-        if row_processor:
-            tokens = line.split()
-            commit_count = int(tokens[0])
-            author = ' '.join(tokens[1:])
-            row_processor(AuthorTotals(author, commit_count))
-    return count
-
-if __name__ == "__main__":
-    conf, paths, outputpath = cli.get_cli()
-    with open(outputpath, 'w', encoding='utf8') as f:
-        writer = csv.writer(f)
-        writer.writerow(['repo', 'author', 'commits'])
-
-        for path in paths:
-            repo_name = os.path.split(path)[1]
-            with (cd.cd(path)):
-                def row_processor(row: AuthorTotals):
-                    writer.writerow([repo_name, row.author, row.total_commits])
-                gen_author_totals_data(conf, row_processor)

gitstats/data_generators/gen_file_data.py

@@ -1,64 +0,0 @@
-import csv
-import os
-import re
-
-from multiprocessing import Pool
-
-from gitstats import cli, cd
-from gitstats.miscfuncs import getcommitrange, getpipeoutput, getnumoflinesinblob
-from gitstats.data import File
-
-
-def gen_file_data(conf, row_processor):
-    '''
-    Given a configuration, pull authorship information. For
-    each author, callback to the row_processor passing an AuthorRow
-
-    :param conf: configuration (mostly used for date limits)
-    :param row_processor: function to receive the callback
-    :return: None
-    '''
-
-    # extensions and size of files
-
-    # DBG: git ls-tree -r -l -z HEAD
-    lines = getpipeoutput(['git ls-tree -r -l -z %s' % getcommitrange(conf, 'HEAD', end_only=True)]).split(
-        '\000')
-    blobs_to_read = {} # blob_id -> File
-    for line in lines:
-        if len(line) == 0:
-            continue
-        parts = re.split('\s+', line, 4)
-        if parts[0] == '160000' and parts[3] == '-':
-            # skip submodules
-            continue
-        blob_id = parts[2]
-        size = int(parts[3])
-        fullpath = parts[4]
-        _, ext = os.path.splitext(fullpath)
-        blobs_to_read[blob_id] = File(fullpath, ext, size)
-
-    # DBG: git cat-file blob e4f17a621893811250be96c8ef9c37b5e97a1df7', 'wc -l'
-    pool = Pool(processes=conf['processes'])
-    blob_linecount = pool.map(getnumoflinesinblob, blobs_to_read.keys())
-    pool.terminate()
-    pool.join()
-    # Update cache and write down info about number of number of lines
-    for (blob_id, linecount) in blob_linecount:
-        file_data = blobs_to_read[blob_id]
-        file_data.lines = linecount
-        row_processor(file_data)
-
-
-if __name__ == "__main__":
-    conf, paths, outputpath = cli.get_cli()
-    with open(outputpath, 'w', encoding='utf8') as f:
-        writer = csv.writer(f)
-        writer.writerow(['repo', 'file', 'ext', 'size', 'line_count'])
-
-        for path in paths:
-            repo_name = os.path.split(path)[1]
-            with (cd.cd(path)):
-                def row_processor(row: File):
-                    writer.writerow([repo_name, row.full_path, row.ext, row.size, row.lines])
-                gen_file_data(conf, row_processor)

gitstats/data_generators/gen_loc_data.py

@@ -1,95 +0,0 @@
-import csv
-import logging
-import os
-import re
-
-from gitstats import cli, cd
-from gitstats.miscfuncs import getlogrange, getpipeoutput, getstatsummarycounts
-from gitstats.data import LocByDate
-
-# TODO: the author isn't working here because it's the commit that merges to master, so we
-# TODO: probably need to back up a commit. Each commit here represents a merged PR
-
-def gen_loc_data(conf, row_processor, ignore_files=''):
-    '''
-    Given a configuration, pull authorship information. For
-    each author, callback to the row_processor passing an AuthorRow
-
-    :param conf: configuration (mostly used for date limits)
-    :param row_processor: function to receive the callback
-    :return: (total_files, total_lines) in repo
-    '''
-
-    # line statistics
-    # outputs:
-    #  N files changed, N insertions (+), N deletions(-)
-
-    # computation of lines of code by date is better done
-    # on a linear history.
-    extra = ''
-    if conf['linear_linestats']:
-        extra = '--first-parent -m'
-
-    # DBG: git log --shortstat --first-parent -m --pretty=format:"%at %aN" --since="2017-10-01" "HEAD"'
-    lines = getpipeoutput(
-        ['git log --shortstat %s --pretty=format:"%%H %%at %%aN" %s %s' % (extra, getlogrange(conf, 'HEAD'), ignore_files)]).split('\n')
-    lines.reverse()
-    files = 0
-    inserted = 0
-    deleted = 0
-    total_lines = 0
-    for line in lines:
-        if len(line) == 0:
-            continue
-
-        if re.search('files? changed', line) is None:
-            line = line.strip()
-            if line:
-                try:
-                    parts = line.split(' ', 2)
-                    (hash, stamp, author) = (parts[0], int(parts[1]), parts[2])
-                    row_processor(LocByDate(hash, stamp, files, inserted, deleted, total_lines))
-                    files, inserted, deleted = 0, 0, 0
-                except ValueError:
-                    logging.warning(f'unexpected line "{line}')
-            else:
-                logging.warning(f'unexpected line "{line}')
-        else:
-            numbers = getstatsummarycounts(line)
-
-            if len(numbers) == 3:
-                (files, inserted, deleted) = map(lambda el: int(el), numbers)
-                total_lines += inserted
-                total_lines -= deleted
-            else:
-                logging.warning(f'Failed to handle line "{line}"')
-                (files, inserted, deleted) = (0, 0, 0)
-
-    totals = getpipeoutput(
-        ['git diff --shortstat `git hash-object -t tree /dev/null` %s' % (ignore_files)]
-    )
-    total_files, remainder = totals.strip().split(' file')
-    total_lines = remainder.split('hanged, ')[1].split(' insert')[0]
-    try:
-        total_files = int(total_files)
-        total_lines = int(total_lines)
-    except ValueError:
-        total_lines = 0
-        total_files = 0
-        logging.warning(f"Unable to parse results: {totals}")
-    return total_files, total_lines
-
-
-if __name__ == "__main__":
-    conf, paths, outputpath = cli.get_cli()
-    with open(outputpath, 'w', encoding='utf8') as f:
-        writer = csv.writer(f)
-        writer.writerow(['repo', 'sha', 'stamp', 'file count', 'lines inserted', 'lines deleted', 'total lines'])
-
-        for path in paths:
-            repo_name = os.path.split(path)[1]
-            with (cd.cd(path)):
-                def row_processor(row: LocByDate):
-                    writer.writerow([repo_name, row.hash, row.stamp, row.file_count, row.lines_inserted,
-                                     row.lines_deleted, row.total_lines])
-                gen_loc_data(conf, row_processor)

gitstats/data_generators/gen_revision_data.py

@@ -1,49 +0,0 @@
-import csv
-import os
-
-from multiprocessing import Pool
-
-from gitstats import cli, cd
-from gitstats.miscfuncs import getnumoffilesfromrev
-from gitstats.data import Revision, RevisionGraph
-from gitstats.data_generators.gen_revision_graph import gen_revision_graph
-
-
-def gen_revision_data(conf, row_processor, graph: RevisionGraph):
-    '''
-    Given a configuration, pull revision information. For
-    each author, callback to the row_processor passing an Revision
-
-    :param conf: configuration (mostly used for date limits)
-    :param row_processor: function to receive the callback
-    :return: None
-    '''
-
-    # todo: consider putting in a cache for this. There was one in the original code
-    # DBG: git ls-tree -r --name-only "ceb3165b51ae0680724fd71e16a5ff836a0de41e"', 'wc -l'
-    pool = Pool(processes=conf['processes'])
-    rev_count = pool.map(getnumoffilesfromrev, graph.revisions.keys())
-    pool.terminate()
-    pool.join()
-    # Update cache with new revisions and append then to general list
-    for (rev, count) in rev_count:
-        revision = graph.revisions[rev]
-        revision.file_count = count
-        row_processor(revision)
-
-
-if __name__ == "__main__":
-    conf, paths, outputpath = cli.get_cli()
-    begin, end = cli.get_begin_end_timestamps(conf)
-    with open(outputpath, 'w', encoding='utf8') as f:
-        writer = csv.writer(f)
-        writer.writerow(['repo', 'sha', 'stamp', 'timezone', 'author', 'email', 'domain', 'files_changed'])
-
-        for path in paths:
-            rev_by_tree_hash, _, _, _ = gen_revision_graph(begin, end)
-            repo_name = os.path.split(path)[1]
-            with (cd.cd(path)):
-                def row_processor(row: Revision):
-                    writer.writerow([repo_name, row.hash, row.stamp, row.timezone, row.author, row.email,
-                                     row.domain, row.file_count])
-                gen_revision_data(conf, row_processor, rev_by_tree_hash)

gitstats/data_generators/gen_tag_data.py

@@ -1,72 +0,0 @@
-import csv
-import os
-
-from collections import defaultdict
-from typing import Dict
-
-from gitstats import cli, cd
-from gitstats.miscfuncs import getpipeoutput
-from gitstats.data import AuthorTotals, Tag
-from gitstats.data_generators import gen_author_totals_data
-
-
-def gen_tag_data(conf, row_processor):
-    '''
-    Given a configuration, pull tag information. For
-    each tag, callback to the row_processor passing a Tag
-
-    :param conf: configuration (mostly used for date limits)
-    :param row_processor: function to receive the callback
-    :return: None
-    '''
-
-    # tags
-    tags = {} # stamp -> tags
-    lines = getpipeoutput(['git show-ref --tags']).split('\n')
-    for line in lines:
-        if len(line) == 0:
-            continue
-        (line_hash, tag) = line.split(' ')
-
-        tag = tag.replace('refs/tags/', '')
-        output = getpipeoutput(['git log "%s" --pretty=format:"%%at" -n 1' % line_hash])
-
-        stamp = 0
-        if len(output) > 0:
-            try:
-                stamp = int(output.strip())
-            except ValueError:
-                stamp = 0
-
-        tags[stamp] = Tag(tag, stamp, line_hash, 0, {})
-
-    stamps = sorted(tags.keys())
-    prev = None
-    for stamp in stamps:
-        def process_row(row: AuthorTotals):
-            tags[stamp].authors[row.author] = row.total_commits
-            tags[stamp].commits += row.total_commits
-
-        revision_tags = tags[stamp].tag
-        if prev != None:
-            revision_tags += ' "^%s"' % prev
-
-        gen_author_totals_data(conf, process_row, revision_tags)
-        row_processor(tags[stamp])
-
-        prev = tags[stamp].tag
-
-
-if __name__ == "__main__":
-    conf, paths, outputpath = cli.get_cli()
-    with open(outputpath, 'w', encoding='utf8') as f:
-        writer = csv.writer(f)
-        writer.writerow(['repo', 'sha', 'stamp', 'commits for tag', 'author', 'commits by author'])
-
-        for path in paths:
-            repo_name = os.path.split(path)[1]
-            with (cd.cd(path)):
-                def row_processor(row: Tag):
-                    for author, commits in row.authors.items():
-                        writer.writerow([repo_name, row.hash, row.stamp, row.commits, author, commits])
-                gen_tag_data(conf, row_processor)

gitstats/datacollector.py

@@ -1,162 +0,0 @@
-import datetime
-import logging
-import os
-import pickle
-import time
-import zlib
-
-from collections import defaultdict
-from typing import Dict
-from gitstats.data.author import Author
-
-
-class DataCollector:
-    """Manages data collection from a revision control repository."""
-
-    def __init__(self, conf):
-        self.conf = conf
-        self.stamp_created = time.time()
-        self.cache = {}
-        self.total_authors = 0
-        self.activity_by_hour_of_day = {}  # hour -> commits
-        self.activity_by_day_of_week = {}  # day -> commits
-        self.activity_by_month_of_year = {}  # month [1-12] -> commits
-        self.activity_by_hour_of_week = {}  # weekday -> hour -> commits
-        self.activity_by_hour_of_day_busiest = 0
-        self.activity_by_hour_of_week_busiest = 0
-        self.activity_by_year_week = {}  # yy_wNN -> commits
-        self.activity_by_year_week_peak = 0
-
-        self.authors: Dict[Author] = defaultdict(lambda: Author())
-
-        self.total_commits = 0
-        self.total_files = 0
-        self.authors_by_commits = 0
-
-        # domains
-        self.domains = {}  # domain -> commits
-
-        # author of the month
-        self.author_of_month = {}  # month -> author -> commits
-        self.author_of_year = {}  # year -> author -> commits
-        self.commits_by_month = {}  # month -> commits
-        self.commits_by_year = {}  # year -> commits
-        self.lines_added_by_month = {}  # month -> lines added
-        self.lines_added_by_year = {}  # year -> lines added
-        self.lines_removed_by_month = {}  # month -> lines removed
-        self.lines_removed_by_year = {}  # year -> lines removed
-        self.first_commit_stamp = 0
-        self.last_commit_stamp = 0
-        self.last_active_day = None
-        self.active_days = set()
-
-        # lines
-        self.total_lines = 0
-        self.total_lines_added = 0
-        self.total_lines_removed = 0
-
-        # size
-        self.total_size = 0
-
-        # timezone
-        self.commits_by_timezone = {}  # timezone -> commits
-
-        # tags
-        self.tags = {}
-
-        self.files_by_stamp = {}  # stamp -> files
-
-        # extensions
-        self.extensions = {}  # extension -> files, lines
-
-        # line statistics
-        self.changes_by_date = {}  # stamp -> { files, ins, del }
-
-    ##
-    # This should be the main function to extract data from the repository.
-    def collect(self, dir):
-        self.dir = dir
-        if len(self.conf['project_name']) == 0:
-            self.projectname = os.path.basename(os.path.abspath(dir))
-        else:
-            self.projectname = self.conf['project_name']
-
-    ##
-    # Load cacheable data
-    def loadCache(self, cachefile):
-        if not os.path.exists(cachefile):
-            return
-        logging.info('Loading cache...')
-        f = open(cachefile, 'rb')
-        try:
-            self.cache = pickle.loads(zlib.decompress(f.read()))
-        except:
-            # temporary hack to upgrade non-compressed caches
-            f.seek(0)
-            self.cache = pickle.load(f)
-        f.close()
-
-    ##
-    # Produce any additional statistics from the extracted data.
-    def refine(self):
-        pass
-
-    ##
-    # : get a dictionary of author
-    def getAuthorInfo(self, author):
-        return None
-
-    def getActivityByDayOfWeek(self):
-        return {}
-
-    def getActivityByHourOfDay(self):
-        return {}
-
-    # : get a dictionary of domains
-    def getDomainInfo(self, domain):
-        return None
-
-    ##
-    # Get a list of authors
-    def getAuthors(self):
-        return []
-
-    def getFirstCommitDate(self):
-        return datetime.datetime.now()
-
-    def getLastCommitDate(self):
-        return datetime.datetime.now()
-
-    def getStampCreated(self):
-        return self.stamp_created
-
-    def getTags(self):
-        return []
-
-    def getTotalAuthors(self):
-        return -1
-
-    def getTotalCommits(self):
-        return -1
-
-    def getTotalFiles(self):
-        return -1
-
-    def getTotalLOC(self):
-        return -1
-
-    ##
-    # Save cacheable data
-    def saveCache(self, cachefile):
-        logging.info('Saving cache...')
-        tempfile = cachefile + '.tmp'
-        f = open(tempfile, 'wb')
-        # pickle.dump(self.cache, f)
-        data = zlib.compress(pickle.dumps(self.cache))
-        f.write(data)
-        f.close()
-        try:
-            os.remove(cachefile)
-        except OSError:
-            pass
-        os.rename(tempfile, cachefile)

gitstats/gitdatacollector.py

@@ -1,276 +0,0 @@
-import datetime
-
-from collections import defaultdict
-
-from gitstats.datacollector import DataCollector
-from gitstats.data import Author, AuthorRow, File, LocByDate, Revision, Tag
-from gitstats.data_generators import gen_author_data, gen_author_totals_data, gen_tag_data, gen_revision_data, \
-    gen_file_data, gen_loc_data
-from gitstats.miscfuncs import getpipeoutput
-
-
-class GitDataCollector(DataCollector):
-    def __init__(self, conf):
-        super(GitDataCollector, self).__init__(conf)
-        
-    def collect(self, directory):
-        super(GitDataCollector, self).collect(directory)
-        self.total_authors += self.get_total_authors()
-        self.get_tags()
-        self.get_revision_info()
-        self.get_file_info()
-        self.get_loc_info()
-        self.get_author_info()
-
-    def get_total_authors(self):
-        return gen_author_totals_data(self.conf)
-
-    def get_author_info(self):
-        # Per-author statistics
-        # defined for stamp, author only if author commited at this timestamp.
-
-        self.changes_by_date_by_author = defaultdict(lambda: defaultdict(lambda: Author())) # stamp -> author -> lines_added
-
-        def row_processor(row: AuthorRow):
-            self.authors[row.author].commits += 1
-            self.authors[row.author].lines_added += row.lines_inserted
-            self.authors[row.author].lines_removed += row.lines_deleted
-            self.changes_by_date_by_author[row.stamp][row.author].lines_added = self.authors[row.author].lines_added
-            self.changes_by_date_by_author[row.stamp][row.author].commits = self.authors[row.author].commits
-
-        gen_author_data(self.conf, row_processor)
-
-    def get_loc_info(self):
-
-        self.changes_by_date = {}  # stamp -> { files, ins, del }
-        def row_processor(row: LocByDate):
-            self.changes_by_date[row.stamp] = {
-                'files': row.file_count,
-                'ins': row.lines_inserted,
-                'del': row.lines_deleted,
-                'lines': row.total_lines
-            }
-            date = datetime.datetime.fromtimestamp(row.stamp)
-            yymm = date.strftime('%Y-%m')
-            self.lines_added_by_month[yymm] = self.lines_added_by_month.get(yymm, 0) + row.lines_inserted
-            self.lines_removed_by_month[yymm] = self.lines_removed_by_month.get(yymm, 0) + row.lines_deleted
-
-            yy = date.year
-            self.lines_added_by_year[yy] = self.lines_added_by_year.get(yy, 0) + row.lines_inserted
-            self.lines_removed_by_year[yy] = self.lines_removed_by_year.get(yy, 0) + row.lines_deleted
-
-            self.total_lines_added += row.lines_inserted
-            self.total_lines_removed += row.lines_deleted
-
-        self.total_lines += gen_loc_data(self.conf, row_processor)[1]
-
-    def get_file_info(self):
-        # extensions and size of files
-        def row_processor(row: File):
-            self.total_size += row.size
-            self.total_files += 1
-            if row.ext not in self.extensions:
-                self.extensions[row.ext] = {'files': 0, 'lines': 0}
-            self.extensions[row.ext]['files'] += 1
-            self.extensions[row.ext]['lines'] += row.lines
-
-        gen_file_data(self.conf, row_processor)
-
-    def get_revision_info(self):
-        # Collect revision statistics
-        # Outputs "<stamp> <date> <time> <timezone> <author> '<' <mail> '>'"
-
-        def row_processor(row: Revision):
-            stamp = row.stamp
-            domain = row.domain
-            author = row.author
-            timezone = row.timezone
-
-            date = datetime.datetime.fromtimestamp(float(stamp))
-
-            # First and last commit stamp (may be in any order because of cherry-picking and patches)
-            if stamp > self.last_commit_stamp:
-                self.last_commit_stamp = stamp
-            if self.first_commit_stamp == 0 or stamp < self.first_commit_stamp:
-                self.first_commit_stamp = stamp
-
-            # activity
-            # hour
-            hour = date.hour
-            self.activity_by_hour_of_day[hour] = self.activity_by_hour_of_day.get(hour, 0) + 1
-            # most active hour?
-            if self.activity_by_hour_of_day[hour] > self.activity_by_hour_of_day_busiest:
-                self.activity_by_hour_of_day_busiest = self.activity_by_hour_of_day[hour]
-
-            # day of week
-            day = date.weekday()
-            self.activity_by_day_of_week[day] = self.activity_by_day_of_week.get(day, 0) + 1
-
-            # domain stats
-            if domain not in self.domains:
-                self.domains[domain] = {}
-            # commits
-            self.domains[domain]['commits'] = self.domains[domain].get('commits', 0) + 1
-
-            # hour of week
-            if day not in self.activity_by_hour_of_week:
-                self.activity_by_hour_of_week[day] = {}
-            self.activity_by_hour_of_week[day][hour] = self.activity_by_hour_of_week[day].get(hour, 0) + 1
-            # most active hour?
-            if self.activity_by_hour_of_week[day][hour] > self.activity_by_hour_of_week_busiest:
-                self.activity_by_hour_of_week_busiest = self.activity_by_hour_of_week[day][hour]
-
-            # month of year
-            month = date.month
-            self.activity_by_month_of_year[month] = self.activity_by_month_of_year.get(month, 0) + 1
-
-            # yearly/weekly activity
-            yyw = date.strftime('%Y-%W')
-            self.activity_by_year_week[yyw] = self.activity_by_year_week.get(yyw, 0) + 1
-            if self.activity_by_year_week_peak < self.activity_by_year_week[yyw]:
-                self.activity_by_year_week_peak = self.activity_by_year_week[yyw]
-
-            # author stats
-            self.authors[author].activity_by_day_and_hour[day][hour] += 1
-            # commits, note again that commits may be in any date order because of cherry-picking and patches
-            if not self.authors[author].last_commit_stamp:
-                self.authors[author].last_commit_stamp = stamp
-            if stamp > self.authors[author].last_commit_stamp:
-                self.authors[author].last_commit_stamp = stamp
-            if not self.authors[author].first_commit_stamp:
-                self.authors[author].first_commit_stamp = stamp
-            if stamp < self.authors[author].first_commit_stamp:
-                self.authors[author].first_commit_stamp = stamp
-
-            # author of the month/year
-            yymm = date.strftime('%Y-%m')
-            if yymm in self.author_of_month:
-                self.author_of_month[yymm][author] = self.author_of_month[yymm].get(author, 0) + 1
-            else:
-                self.author_of_month[yymm] = {}
-                self.author_of_month[yymm][author] = 1
-            self.commits_by_month[yymm] = self.commits_by_month.get(yymm, 0) + 1
-
-            yy = date.year
-            if yy in self.author_of_year:
-                self.author_of_year[yy][author] = self.author_of_year[yy].get(author, 0) + 1
-            else:
-                self.author_of_year[yy] = {}
-                self.author_of_year[yy][author] = 1
-            self.commits_by_year[yy] = self.commits_by_year.get(yy, 0) + 1
-
-            # authors: active days
-            yymmdd = date.strftime('%Y-%m-%d')
-            if not self.authors[author].last_active_day:
-                self.authors[author].last_active_day = yymmdd
-            elif yymmdd != self.authors[author].last_active_day:
-                self.authors[author].last_active_day = yymmdd
-            self.authors[author].active_days.add(yymmdd)
-
-            # project: active days
-            if yymmdd != self.last_active_day:
-                self.last_active_day = yymmdd
-                self.active_days.add(yymmdd)
-
-            # timezone
-            self.commits_by_timezone[timezone] = self.commits_by_timezone.get(timezone, 0) + 1
-
-            # file counts
-            self.files_by_stamp[stamp] = row.file_count
-
-        self.total_commits += gen_revision_data(self.conf, row_processor)
-
-    def get_tags(self):
-        def row_processor(row: Tag):
-            self.tags[row.tag] = {
-                'stamp': row.stamp,
-                'hash': row.hash,
-                'date': datetime.datetime.fromtimestamp(row.stamp).strftime('%Y-%m-%d'),
-                'commits': row.commits,
-                'authors': row.authors
-            }
-
-        gen_tag_data(self.conf, row_processor)
-
-    def refine(self):
-        # authors
-        # name -> {place_by_commits, commits_frac, date_first, date_last, timedelta}
-        self.authors_by_commits = self.getAuthors()
-        total_commits_without_merge = 0
-        for i, name in enumerate(self.authors_by_commits):
-            self.authors[name].place_by_commits = i + 1
-            total_commits_without_merge += self.authors[name].commits
-
-        for name in self.authors.keys():
-            a = self.authors[name]
-            a.commits_frac = (100 * float(a.commits)) / total_commits_without_merge
-            date_first = datetime.datetime.fromtimestamp(a.first_commit_stamp)
-            date_last = datetime.datetime.fromtimestamp(a.last_commit_stamp)
-            delta = date_last - date_first
-            a.date_first = date_first.strftime('%Y-%m-%d')
-            a.date_last = date_last.strftime('%Y-%m-%d')
-            a.timedelta = delta
-            for day in range(6):
-                for hour in range(24):
-                    if day > 4 or hour < 8 or hour > 17:
-                        a.extra_effort += a.activity_by_day_and_hour[day][hour]
-            a.extra_frac = (100 * float(a.extra_effort)) / a.commits
-
-    def getActiveDays(self):
-        return self.active_days
-
-    def getActivityByDayOfWeek(self):
-        return self.activity_by_day_of_week
-
-    def getActivityByHourOfDay(self):
-        return self.activity_by_hour_of_day
-
-    def getAuthorInfo(self, author):
-        return self.authors[author]
-
-    def getAuthors(self, limit=None):
-        res = [el[0] for el in sorted(self.authors.items(), key=lambda x: x[1].commits, reverse=True)]
-        return res[:limit]
-
-    def getCommitDeltaDays(self):
-        return (self.last_commit_stamp / 86400 - self.first_commit_stamp / 86400) + 1
-
-    def getDomainInfo(self, domain):
-        return self.domains[domain]
-
-    def getDomains(self):
-        return self.domains.keys()
-
-    def getFirstCommitDate(self):
-        return datetime.datetime.fromtimestamp(self.first_commit_stamp)
-
-    def getLastCommitDate(self):
-        return datetime.datetime.fromtimestamp(self.last_commit_stamp)
-
-    def getTags(self):
-        lines = getpipeoutput(['git show-ref --tags', 'cut -d/ -f3'])
-        return lines.split('\n')
-
-    def getTagDate(self, tag):
-        return self.revToDate('tags/' + tag)
-
-    def getTotalAuthors(self):
-        # because we are equating names (see name_xlate), the total authors will be the number of
-        # elements in the authors dictionary rather than the count from the git log
-        return len(self.authors)
-
-    def getTotalCommits(self):
-        return self.total_commits
-
-    def getTotalFiles(self):
-        return self.total_files
-
-    def getTotalLOC(self):
-        return self.total_lines
-
-    def getTotalSize(self):
-        return self.total_size
-
-    def revToDate(self, rev):
-        stamp = int(getpipeoutput(['git log --pretty=format:%%at "%s" -n 1' % rev]))
-        return datetime.datetime.fromtimestamp(stamp).strftime('%Y-%m-%d')

gitstats/htmlreportcreator.py

@@ -1,734 +0,0 @@
-import datetime
-import glob
-import logging
-import pkg_resources
-import os
-import shutil
-import time
-
-from .reportcreator import ReportCreator
-from .miscfuncs import getgitversion, getgnuplotversion, getkeyssortedbyvaluekey, getkeyssortedbyvalues, getpipeoutput, \
-    getversion, gnuplot_cmd
-
-GNUPLOT_COMMON = 'set terminal png transparent size 640,240\nset size 1.0,1.0\n'
-WEEKDAYS = ('Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun')
-
-def html_linkify(text):
-    return text.lower().replace(' ', '_')
-
-
-def html_header(level, text):
-    name = html_linkify(text)
-    return '\n<h%d id="%s"><a href="#%s">%s</a></h%d>\n\n' % (level, name, name, text, level)
-
-
-class HTMLReportCreator(ReportCreator):
-    def __init(self, conf):
-        super(HTMLReportCreator, self).__init__(conf)
-
-    def create(self, data, path):
-        super(HTMLReportCreator, self).create(data, path)
-        self.title = data.projectname
-
-        # copy static files. Looks in the binary directory, ../share/gitstats and /usr/share/gitstats
-        resources = (self.conf['style'], 'sortable.js', 'arrow-up.gif', 'arrow-down.gif', 'arrow-none.gif')
-        for resource in (self.conf['style'], 'sortable.js', 'arrow-up.gif', 'arrow-down.gif', 'arrow-none.gif'):
-            resource_file = pkg_resources.resource_filename('gitstats', os.path.join('resources', resource))
-            if os.path.exists(resource_file):
-                shutil.copyfile(resource_file, os.path.join(path, resource))
-            else:
-                logging.warning(f'"{resource}" not found, so not copied')
-
-        f = open(path + "/index.html", 'w')
-        format = '%Y-%m-%d %H:%M:%S'
-        self.printHeader(f)
-
-        f.write('<h1>GitStats - %s</h1>' % data.projectname)
-
-        self.printNav(f)
-
-        f.write('<dl>')
-        f.write('<dt>Project name</dt><dd>%s</dd>' % (data.projectname))
-        f.write('<dt>Generated</dt><dd>%s (in %d seconds)</dd>' % (
-            datetime.datetime.now().strftime(format), time.time() - data.getStampCreated()))
-        f.write(
-            '<dt>Generator</dt><dd><a href="https://github.com/rappdw/gitstats">GitStats</a> (version %s), %s, %s</dd>' % (
-                getversion(), getgitversion(), getgnuplotversion()))
-        f.write('<dt>Report Period</dt><dd>%s to %s</dd>' % (
-            data.getFirstCommitDate().strftime(format), data.getLastCommitDate().strftime(format)))
-        f.write('<dt>Age</dt><dd>%d days, %d active days (%3.2f%%)</dd>' % (
-            data.getCommitDeltaDays(), len(data.getActiveDays()),
-            (100.0 * len(data.getActiveDays()) / data.getCommitDeltaDays())))
-        f.write('<dt>Total Files</dt><dd>%s</dd>' % data.getTotalFiles())
-        f.write('<dt>Total Lines of Code</dt><dd>%s (%d added, %d removed)</dd>' % (
-            data.getTotalLOC(), data.total_lines_added, data.total_lines_removed))
-        f.write('<dt>Total Commits</dt><dd>%s (average %.1f commits per active day, %.1f per all days)</dd>' % (
-            data.getTotalCommits(), float(data.getTotalCommits()) / len(data.getActiveDays()),
-            float(data.getTotalCommits()) / data.getCommitDeltaDays()))
-        f.write('<dt>Authors</dt><dd>%s (average %.1f commits per author)</dd>' % (
-            data.getTotalAuthors(), (1.0 * data.getTotalCommits()) / data.getTotalAuthors()))
-        f.write('</dl>')
-
-        f.write('</body>\n</html>')
-        f.close()
-
-        ###
-        # Activity
-        f = open(path + '/activity.html', 'w')
-        self.printHeader(f)
-        f.write('<h1>Activity</h1>')
-        self.printNav(f)
-
-        # f.write('<h2>Last 30 days</h2>')
-
-        # f.write('<h2>Last 12 months</h2>')
-
-        # Weekly activity
-        WEEKS = 32
-        f.write(html_header(2, 'Weekly activity'))
-        f.write('<p>Last %d weeks</p>' % WEEKS)
-
-        # generate weeks to show (previous N weeks from now)
-        now = datetime.datetime.now()
-        deltaweek = datetime.timedelta(7)
-        weeks = []
-        stampcur = now
-        for i in range(0, WEEKS):
-            weeks.insert(0, stampcur.strftime('%Y-%W'))
-            stampcur -= deltaweek
-
-        # top row: commits & bar
-        f.write('<table class="noborders"><tr>')
-        for i in range(0, WEEKS):
-            commits = 0
-            if weeks[i] in data.activity_by_year_week:
-                commits = data.activity_by_year_week[weeks[i]]
-
-            percentage = 0
-            if weeks[i] in data.activity_by_year_week:
-                percentage = float(data.activity_by_year_week[weeks[i]]) / data.activity_by_year_week_peak
-            height = max(1, int(200 * percentage))
-            f.write(
-                '<td style="text-align: center; vertical-align: bottom">%d<div style="display: block; background-color: red; width: 20px; height: %dpx"></div></td>' % (
-                    commits, height))
-
-        # bottom row: year/week
-        f.write('</tr><tr>')
-        for i in range(0, WEEKS):
-            f.write('<td>%s</td>' % (WEEKS - i))
-        f.write('</tr></table>')
-
-        # Hour of Day
-        f.write(html_header(2, 'Hour of Day'))
-        hour_of_day = data.getActivityByHourOfDay()
-        f.write('<table><tr><th>Hour</th>')
-        for i in range(0, 24):
-            f.write('<th>%d</th>' % i)
-        f.write('</tr>\n<tr><th>Commits</th>')
-        fp = open(path + '/hour_of_day.dat', 'w')
-        for i in range(0, 24):
-            if i in hour_of_day:
-                r = 127 + int((float(hour_of_day[i]) / data.activity_by_hour_of_day_busiest) * 128)
-                f.write('<td style="background-color: rgb(%d, 0, 0)">%d</td>' % (r, hour_of_day[i]))
-                fp.write('%d %d\n' % (i, hour_of_day[i]))
-            else:
-                f.write('<td>0</td>')
-                fp.write('%d 0\n' % i)
-        fp.close()
-        f.write('</tr>\n<tr><th>%</th>')
-        totalcommits = data.getTotalCommits()
-        for i in range(0, 24):
-            if i in hour_of_day:
-                r = 127 + int((float(hour_of_day[i]) / data.activity_by_hour_of_day_busiest) * 128)
-                f.write('<td style="background-color: rgb(%d, 0, 0)">%.2f</td>' % (
-                    r, (100.0 * hour_of_day[i]) / totalcommits))
-            else:
-                f.write('<td>0.00</td>')
-        f.write('</tr></table>')
-        f.write('<img src="hour_of_day.png" alt="Hour of Day">')
-        fg = open(path + '/hour_of_day.dat', 'w')
-        for i in range(0, 24):
-            if i in hour_of_day:
-                fg.write('%d %d\n' % (i + 1, hour_of_day[i]))
-            else:
-                fg.write('%d 0\n' % (i + 1))
-        fg.close()
-
-        # Day of Week
-        f.write(html_header(2, 'Day of Week'))
-        day_of_week = data.getActivityByDayOfWeek()
-        f.write('<div class="vtable"><table>')
-        f.write('<tr><th>Day</th><th>Total (%)</th></tr>')
-        fp = open(path + '/day_of_week.dat', 'w')
-        for d in range(0, 7):
-            commits = 0
-            if d in day_of_week:
-                commits = day_of_week[d]
-            fp.write('%d %s %d\n' % (d + 1, WEEKDAYS[d], commits))
-            f.write('<tr>')
-            f.write('<th>%s</th>' % (WEEKDAYS[d]))
-            if d in day_of_week:
-                f.write('<td>%d (%.2f%%)</td>' % (day_of_week[d], (100.0 * day_of_week[d]) / totalcommits))
-            else:
-                f.write('<td>0</td>')
-            f.write('</tr>')
-        f.write('</table></div>')
-        f.write('<img src="day_of_week.png" alt="Day of Week">')
-        fp.close()
-
-        # Hour of Week
-        f.write(html_header(2, 'Hour of Week'))
-        f.write('<table>')
-
-        f.write('<tr><th>Weekday</th>')
-        for hour in range(0, 24):
-            f.write('<th>%d</th>' % (hour))
-        f.write('</tr>')
-
-        for weekday in range(0, 7):
-            f.write('<tr><th>%s</th>' % (WEEKDAYS[weekday]))
-            for hour in range(0, 24):
-                try:
-                    commits = data.activity_by_hour_of_week[weekday][hour]
-                except KeyError:
-                    commits = 0
-                if commits != 0:
-                    f.write('<td')
-                    r = 127 + int((float(commits) / data.activity_by_hour_of_week_busiest) * 128)
-                    f.write(' style="background-color: rgb(%d, 0, 0)"' % r)
-                    f.write('>%d</td>' % commits)
-                else:
-                    f.write('<td></td>')
-            f.write('</tr>')
-
-        f.write('</table>')
-
-        # Month of Year
-        f.write(html_header(2, 'Month of Year'))
-        f.write('<div class="vtable"><table>')
-        f.write('<tr><th>Month</th><th>Commits (%)</th></tr>')
-        fp = open(path + '/month_of_year.dat', 'w')
-        for mm in range(1, 13):
-            commits = 0
-            if mm in data.activity_by_month_of_year:
-                commits = data.activity_by_month_of_year[mm]
-            f.write(
-                '<tr><td>%d</td><td>%d (%.2f %%)</td></tr>' % (mm, commits, (100.0 * commits) / data.getTotalCommits()))
-            fp.write('%d %d\n' % (mm, commits))
-        fp.close()
-        f.write('</table></div>')
-        f.write('<img src="month_of_year.png" alt="Month of Year">')
-
-        # Commits by year/month
-        f.write(html_header(2, 'Commits by year/month'))
-        f.write(
-            '<div class="vtable"><table><tr><th>Month</th><th>Commits</th><th>Lines added</th><th>Lines removed</th></tr>')
-        for yymm in reversed(sorted(data.commits_by_month.keys())):
-            f.write('<tr><td>%s</td><td>%d</td><td>%d</td><td>%d</td></tr>' % (
-                yymm, data.commits_by_month.get(yymm, 0), data.lines_added_by_month.get(yymm, 0),
-                data.lines_removed_by_month.get(yymm, 0)))
-        f.write('</table></div>')
-        f.write('<img src="commits_by_year_month.png" alt="Commits by year/month">')
-        fg = open(path + '/commits_by_year_month.dat', 'w')
-        for yymm in sorted(data.commits_by_month.keys()):
-            fg.write('%s %s\n' % (yymm, data.commits_by_month[yymm]))
-        fg.close()
-
-        # Commits by year
-        f.write(html_header(2, 'Commits by Year'))
-        f.write(
-            '<div class="vtable"><table><tr><th>Year</th><th>Commits (% of all)</th><th>Lines added</th><th>Lines removed</th></tr>')
-        for yy in reversed(sorted(data.commits_by_year.keys())):
-            f.write('<tr><td>%s</td><td>%d (%.2f%%)</td><td>%d</td><td>%d</td></tr>' % (
-                yy, data.commits_by_year.get(yy, 0), (100.0 * data.commits_by_year.get(yy, 0)) / data.getTotalCommits(),
-                data.lines_added_by_year.get(yy, 0), data.lines_removed_by_year.get(yy, 0)))
-        f.write('</table></div>')
-        f.write('<img src="commits_by_year.png" alt="Commits by Year">')
-        fg = open(path + '/commits_by_year.dat', 'w')
-        for yy in sorted(data.commits_by_year.keys()):
-            fg.write('%d %d\n' % (yy, data.commits_by_year[yy]))
-        fg.close()
-
-        # Commits by timezone
-        f.write(html_header(2, 'Commits by Timezone'))
-        f.write('<table><tr>')
-        f.write('<th>Timezone</th><th>Commits</th>')
-        f.write('</tr>')
-        max_commits_on_tz = max(data.commits_by_timezone.values())
-        for i in sorted(data.commits_by_timezone.keys(), key=lambda n: int(n)):
-            commits = data.commits_by_timezone[i]
-            r = 127 + int((float(commits) / max_commits_on_tz) * 128)
-            f.write('<tr><th>%s</th><td style="background-color: rgb(%d, 0, 0)">%d</td></tr>' % (i, r, commits))
-        f.write('</table>')
-
-        f.write('</body></html>')
-        f.close()
-
-        ###
-        # Authors
-        f = open(path + '/authors.html', 'w')
-        self.printHeader(f)
-
-        f.write('<h1>Authors</h1>')
-        self.printNav(f)
-
-        # Authors :: List of authors
-        f.write(html_header(2, 'List of Authors'))
-
-        f.write('<table class="authors sortable" id="authors">')
-        f.write(
-            '<tr><th>Author</th><th>Commits (%)</th><th>+ lines</th><th>- lines</th><th>First commit</th><th>Last commit</th><th class="unsortable">Age</th><th>Active days</th><th># by commits</th></tr>')
-        for author in data.getAuthors(self.conf['max_authors']):
-            info = data.getAuthorInfo(author)
-            f.write(
-                '<tr><td>%s</td><td>%d (%.2f%%)</td><td>%d</td><td>%d</td><td>%s</td><td>%s</td><td>%s</td><td>%d</td><td>%d</td></tr>' % (
-                    author, info.commits, info.commits_frac, info.lines_added, info.lines_removed,
-                    info.date_first, info.date_last, info.timedelta, len(info.active_days),
-                    info.place_by_commits))
-        f.write('</table>')
-
-        allauthors = data.getAuthors()
-        if len(allauthors) > self.conf['max_authors']:
-            rest = allauthors[self.conf['max_authors']:]
-            f.write('<p class="moreauthors">These didn\'t make it to the top: %s</p>' % ', '.join(rest))
-
-        f.write(html_header(2, 'Cumulated Added Lines of Code per Author'))
-        f.write('<img src="lines_of_code_by_author.png" alt="Lines of code per Author">')
-        if len(allauthors) > self.conf['max_authors']:
-            f.write('<p class="moreauthors">Only top %d authors shown</p>' % self.conf['max_authors'])
-
-        f.write(html_header(2, 'Commits per Author'))
-        f.write('<img src="commits_by_author.png" alt="Commits per Author">')
-        if len(allauthors) > self.conf['max_authors']:
-            f.write('<p class="moreauthors">Only top %d authors shown</p>' % self.conf['max_authors'])
-
-        fgl = open(path + '/lines_of_code_by_author.dat', 'w')
-        fgc = open(path + '/commits_by_author.dat', 'w')
-
-        lines_by_authors = {}  # cumulated added lines by
-        # author. to save memory,
-        # changes_by_date_by_author[stamp][author] is defined
-        # only at points where author commits.
-        # lines_by_authors allows us to generate all the
-        # points in the .dat file.
-
-        # Don't rely on getAuthors to give the same order each
-        # time. Be robust and keep the list in a variable.
-        commits_by_authors = {}  # cumulated added lines by
-
-        self.authors_to_plot = data.getAuthors(self.conf['max_authors'])
-        for author in self.authors_to_plot:
-            lines_by_authors[author] = 0
-            commits_by_authors[author] = 0
-        for stamp in sorted(data.changes_by_date_by_author.keys()):
-            fgl.write('%d' % stamp)
-            fgc.write('%d' % stamp)
-            for author in self.authors_to_plot:
-                if author in data.changes_by_date_by_author[stamp].keys():
-                    lines_by_authors[author] = data.changes_by_date_by_author[stamp][author].lines_added
-                    commits_by_authors[author] = data.changes_by_date_by_author[stamp][author].commits
-                fgl.write(' %d' % lines_by_authors[author])
-                fgc.write(' %d' % commits_by_authors[author])
-            fgl.write('\n')
-            fgc.write('\n')
-        fgl.close()
-        fgc.close()
-
-        # Authors :: Author of Month
-        f.write(html_header(2, 'Author of Month'))
-        f.write('<table class="sortable" id="aom">')
-        f.write(
-            '<tr><th>Month</th><th>Author</th><th>Commits (%%)</th><th class="unsortable">Next top %d</th><th>Number of authors</th></tr>' %
-            self.conf['authors_top'])
-        for yymm in reversed(sorted(data.author_of_month.keys())):
-            authordict = data.author_of_month[yymm]
-            authors = getkeyssortedbyvalues(authordict)
-            authors.reverse()
-            commits = data.author_of_month[yymm][authors[0]]
-            next = ', '.join(authors[1:self.conf['authors_top'] + 1])
-            f.write('<tr><td>%s</td><td>%s</td><td>%d (%.2f%% of %d)</td><td>%s</td><td>%d</td></tr>' % (
-                yymm, authors[0], commits, (100.0 * commits) / data.commits_by_month[yymm], data.commits_by_month[yymm],
-                next, len(authors)))
-
-        f.write('</table>')
-
-        f.write(html_header(2, 'Author of Year'))
-        f.write(
-            '<table class="sortable" id="aoy"><tr><th>Year</th><th>Author</th><th>Commits (%%)</th><th class="unsortable">Next top %d</th><th>Number of authors</th></tr>' %
-            self.conf['authors_top'])
-        for yy in reversed(sorted(data.author_of_year.keys())):
-            authordict = data.author_of_year[yy]
-            authors = getkeyssortedbyvalues(authordict)
-            authors.reverse()
-            commits = data.author_of_year[yy][authors[0]]
-            next = ', '.join(authors[1:self.conf['authors_top'] + 1])
-            f.write('<tr><td>%s</td><td>%s</td><td>%d (%.2f%% of %d)</td><td>%s</td><td>%d</td></tr>' % (
-                yy, authors[0], commits, (100.0 * commits) / data.commits_by_year[yy], data.commits_by_year[yy], next,
-                len(authors)))
-        f.write('</table>')
-
-        # Domains
-        f.write(html_header(2, 'Commits by Domains'))
-        domains_by_commits = getkeyssortedbyvaluekey(data.domains, 'commits')
-        domains_by_commits.reverse()  # most first
-        f.write('<div class="vtable"><table>')
-        f.write('<tr><th>Domains</th><th>Total (%)</th></tr>')
-        fp = open(path + '/domains.dat', 'w')
-        n = 0
-        for domain in domains_by_commits:
-            if n == self.conf['max_domains']:
-                break
-            commits = 0
-            n += 1
-            info = data.getDomainInfo(domain)
-            fp.write('%s %d %d\n' % (domain, n, info['commits']))
-            f.write('<tr><th>%s</th><td>%d (%.2f%%)</td></tr>' % (
-                domain, info['commits'], (100.0 * info['commits'] / totalcommits)))
-        f.write('</table></div>')
-        f.write('<img src="domains.png" alt="Commits by Domains">')
-        fp.close()
-
-        f.write('</body></html>')
-        f.close()
-
-        ###
-        # Files
-        f = open(path + '/files.html', 'w')
-        self.printHeader(f)
-        f.write('<h1>Files</h1>')
-        self.printNav(f)
-
-        f.write('<dl>\n')
-        f.write('<dt>Total files</dt><dd>%d</dd>' % data.getTotalFiles())
-        f.write('<dt>Total lines</dt><dd>%d</dd>' % data.getTotalLOC())
-        try:
-            f.write(
-                '<dt>Average file size</dt><dd>%.2f bytes</dd>' % (float(data.getTotalSize()) / data.getTotalFiles()))
-        except ZeroDivisionError:
-            pass
-        f.write('</dl>\n')
-
-        # Files :: File count by date
-        f.write(html_header(2, 'File count by date'))
-
-        # use set to get rid of duplicate/unnecessary entries
-        files_by_date = set()
-        for stamp in sorted(data.files_by_stamp.keys()):
-            files_by_date.add(
-                '%s %d' % (datetime.datetime.fromtimestamp(stamp).strftime('%Y-%m-%d'), data.files_by_stamp[stamp]))
-
-        fg = open(path + '/files_by_date.dat', 'w')
-        for line in sorted(list(files_by_date)):
-            fg.write('%s\n' % line)
-        # for stamp in sorted(data.files_by_stamp.keys()):
-        #	fg.write('%s %d\n' % (datetime.datetime.fromtimestamp(stamp).strftime('%Y-%m-%d'), data.files_by_stamp[stamp]))
-        fg.close()
-
-        f.write('<img src="files_by_date.png" alt="Files by Date">')
-
-        # f.write('<h2>Average file size by date</h2>')
-
-        # Files :: Extensions
-        f.write(html_header(2, 'Extensions'))
-        f.write(
-            '<table class="sortable" id="ext"><tr><th>Extension</th><th>Files (%)</th><th>Lines (%)</th><th>Lines/file</th></tr>')
-        for ext in sorted(data.extensions.keys()):
-            files = data.extensions[ext]['files']
-            lines = data.extensions[ext]['lines']
-            try:
-                loc_percentage = (100.0 * lines) / data.getTotalLOC()
-            except ZeroDivisionError:
-                loc_percentage = 0
-            f.write('<tr><td>%s</td><td>%d (%.2f%%)</td><td>%d (%.2f%%)</td><td>%d</td></tr>' % (
-                ext, files, (100.0 * files) / data.getTotalFiles(), lines, loc_percentage, lines / files))
-        f.write('</table>')
-
-        f.write('</body></html>')
-        f.close()
-
-        ###
-        # Lines
-        f = open(path + '/lines.html', 'w')
-        self.printHeader(f)
-        f.write('<h1>Lines</h1>')
-        self.printNav(f)
-
-        f.write('<dl>\n')
-        f.write('<dt>Total lines</dt><dd>%d</dd>' % data.getTotalLOC())
-        f.write('</dl>\n')
-
-        f.write(html_header(2, 'Lines of Code'))
-        f.write('<img src="lines_of_code.png" alt="Lines of Code">')
-
-        fg = open(path + '/lines_of_code.dat', 'w')
-        for stamp in sorted(data.changes_by_date.keys()):
-            fg.write('%d %d\n' % (stamp, data.changes_by_date[stamp]['lines']))
-        fg.close()
-
-        f.write('</body></html>')
-        f.close()
-
-        ###
-        # tags.html
-        f = open(path + '/tags.html', 'w')
-        self.printHeader(f)
-        f.write('<h1>Tags</h1>')
-        self.printNav(f)
-
-        f.write('<dl>')
-        f.write('<dt>Total tags</dt><dd>%d</dd>' % len(data.tags))
-        if len(data.tags) > 0:
-            f.write('<dt>Average commits per tag</dt><dd>%.2f</dd>' % (1.0 * data.getTotalCommits() / len(data.tags)))
-        f.write('</dl>')
-
-        f.write('<table class="tags">')
-        f.write('<tr><th>Name</th><th>Date</th><th>Commits</th><th>Authors</th></tr>')
-        # sort the tags by date desc
-        tags_sorted_by_date_desc = map(lambda el: el[1],
-                                       reversed(sorted(map(lambda el: (el[1]['date'], el[0]), data.tags.items()))))
-        for tag in tags_sorted_by_date_desc:
-            authorinfo = []
-            self.authors_by_commits = getkeyssortedbyvalues(data.tags[tag]['authors'])
-            for i in reversed(self.authors_by_commits):
-                authorinfo.append('%s (%d)' % (i, data.tags[tag]['authors'][i]))
-            f.write('<tr><td>%s</td><td>%s</td><td>%d</td><td>%s</td></tr>' % (
-                tag, data.tags[tag]['date'], data.tags[tag]['commits'], ', '.join(authorinfo)))
-        f.write('</table>')
-
-        f.write('</body></html>')
-        f.close()
-
-        self.createGraphs(path)
-
-    def createGraphs(self, path):
-        logging.info('Generating graphs...')
-
-        # hour of day
-        f = open(path + '/hour_of_day.plot', 'w')
-        f.write(GNUPLOT_COMMON)
-        f.write(
-            """
-            set output 'hour_of_day.png'
-            unset key
-            set xrange [0.5:24.5]
-            set yrange [0:]
-            set xtics 4
-            set grid y
-            set ylabel "Commits"
-            plot 'hour_of_day.dat' using 1:2:(0.5) w boxes fs solid
-            """)
-        f.close()
-
-        # day of week
-        f = open(path + '/day_of_week.plot', 'w')
-        f.write(GNUPLOT_COMMON)
-        f.write(
-            """
-            set output 'day_of_week.png'
-            unset key
-            set xrange [0.5:7.5]
-            set yrange [0:]
-            set xtics 1
-            set grid y
-            set ylabel "Commits"
-            plot 'day_of_week.dat' using 1:3:(0.5):xtic(2) w boxes fs solid
-            """)
-        f.close()
-
-        # Domains
-        f = open(path + '/domains.plot', 'w')
-        f.write(GNUPLOT_COMMON)
-        f.write(
-            """
-            set output 'domains.png'
-            unset key
-            unset xtics
-            set yrange [0:]
-            set grid y
-            set ylabel "Commits"
-            plot 'domains.dat' using 2:3:(0.5) with boxes fs solid, '' using 2:3:1 with labels rotate by 45 offset 0,1
-            """)
-        f.close()
-
-        # Month of Year
-        f = open(path + '/month_of_year.plot', 'w')
-        f.write(GNUPLOT_COMMON)
-        f.write(
-            """
-            set output 'month_of_year.png'
-            unset key
-            set xrange [0.5:12.5]
-            set yrange [0:]
-            set xtics 1
-            set grid y
-            set ylabel "Commits"
-            plot 'month_of_year.dat' using 1:2:(0.5) w boxes fs solid
-            """)
-        f.close()
-
-        # commits_by_year_month
-        f = open(path + '/commits_by_year_month.plot', 'w')
-        f.write(GNUPLOT_COMMON)
-        f.write(
-            """
-            set output 'commits_by_year_month.png'
-            unset key
-            set yrange [0:]
-            set xdata time
-            set timefmt "%Y-%m"
-            set format x "%Y-%m"
-            set xtics rotate
-            set bmargin 5
-            set grid y
-            set ylabel "Commits"
-            plot 'commits_by_year_month.dat' using 1:2:(0.5) w boxes fs solid
-            """)
-        f.close()
-
-        # commits_by_year
-        f = open(path + '/commits_by_year.plot', 'w')
-        f.write(GNUPLOT_COMMON)
-        f.write(
-            """
-            set output 'commits_by_year.png'
-            unset key
-            set yrange [0:]
-            set xtics 1 rotate
-            set grid y
-            set ylabel "Commits"
-            set yrange [0:]
-            plot 'commits_by_year.dat' using 1:2:(0.5) w boxes fs solid
-            """)
-        f.close()
-
-        # Files by date
-        f = open(path + '/files_by_date.plot', 'w')
-        f.write(GNUPLOT_COMMON)
-        f.write(
-            """
-            set output 'files_by_date.png'
-            unset key
-            set yrange [0:]
-            set xdata time
-            set timefmt "%Y-%m-%d"
-            set format x "%Y-%m-%d"
-            set grid y
-            set ylabel "Files"
-            set xtics rotate
-            set ytics autofreq
-            set bmargin 6
-            plot 'files_by_date.dat' using 1:2 w steps
-            """)
-        f.close()
-
-        # Lines of Code
-        f = open(path + '/lines_of_code.plot', 'w')
-        f.write(GNUPLOT_COMMON)
-        f.write(
-            """
-            set output 'lines_of_code.png'
-            unset key
-            set yrange [0:]
-            set xdata time
-            set timefmt "%s"
-            set format x "%Y-%m-%d"
-            set grid y
-            set ylabel "Lines"
-            set xtics rotate
-            set bmargin 6
-            plot 'lines_of_code.dat' using 1:2 w lines
-            """)
-        f.close()
-
-        # Lines of Code Added per author
-        f = open(path + '/lines_of_code_by_author.plot', 'w')
-        f.write(GNUPLOT_COMMON)
-        f.write(
-            """
-            set terminal png transparent size 640,480
-            set output 'lines_of_code_by_author.png'
-            set key left top
-            set yrange [0:]
-            set xdata time
-            set timefmt "%s"
-            set format x "%Y-%m-%d"
-            set grid y
-            set ylabel "Lines"
-            set xtics rotate
-            set bmargin 6
-            plot """
-        )
-        i = 1
-        plots = []
-        for a in self.authors_to_plot:
-            i = i + 1
-            author = a.replace("\"", "\\\"").replace("`", "")
-            plots.append("""'lines_of_code_by_author.dat' using 1:%d title "%s" w lines""" % (i, author))
-        f.write(", ".join(plots))
-        f.write('\n')
-
-        f.close()
-
-        # Commits per author
-        f = open(path + '/commits_by_author.plot', 'w')
-        f.write(GNUPLOT_COMMON)
-        f.write(
-            """
-            set terminal png transparent size 640,480
-            set output 'commits_by_author.png'
-            set key left top
-            set yrange [0:]
-            set xdata time
-            set timefmt "%s"
-            set format x "%Y-%m-%d"
-            set grid y
-            set ylabel "Commits"
-            set xtics rotate
-            set bmargin 6
-            plot """
-        )
-        i = 1
-        plots = []
-        for a in self.authors_to_plot:
-            i = i + 1
-            author = a.replace("\"", "\\\"").replace("`", "")
-            plots.append("""'commits_by_author.dat' using 1:%d title "%s" w lines""" % (i, author))
-        f.write(", ".join(plots))
-        f.write('\n')
-
-        f.close()
-
-        os.chdir(path)
-        files = glob.glob(path + '/*.plot')
-        for f in files:
-            out = getpipeoutput([gnuplot_cmd + ' "%s"' % f])
-            if len(out) > 0:
-                print(out)
-
-    def printHeader(self, f, title=''):
-        f.write(
-            """<!DOCTYPE html>
-            <html>
-            <head>
-                <meta charset="UTF-8">
-                <title>GitStats - %s</title>
-                <link rel="stylesheet" href="%s" type="text/css">
-                <meta name="generator" content="GitStats %s">
-                <script type="text/javascript" src="sortable.js"></script>
-            </head>
-            <body>
-            """ % (self.title, self.conf['style'], getversion()))
-
-    def printNav(self, f):
-        f.write("""
-<div class="nav">
-<ul>
-<li><a href="index.html">General</a></li>
-<li><a href="activity.html">Activity</a></li>
-<li><a href="authors.html">Authors</a></li>
-<li><a href="files.html">Files</a></li>
-<li><a href="lines.html">Lines</a></li>
-<li><a href="tags.html">Tags</a></li>
-</ul>
-</div>
-""")

gitstats/miscfuncs.py

@@ -1,19 +1,7 @@
-import datetime
 import logging
-import os
-import re
 import subprocess
 import time
 
-os.environ['LC_ALL'] = 'C'
-
-# By default, gnuplot is searched from path, but can be overridden with the
-# environment variable "GNUPLOT"
-gnuplot_cmd = 'gnuplot'
-if 'GNUPLOT' in os.environ:
-    gnuplot_cmd = os.environ['GNUPLOT']
-
-
 def getpipeoutput(cmds):
     start = time.time()
     p = subprocess.Popen(cmds[0], stdout=subprocess.PIPE, shell=True)
@@ -27,85 +15,3 @@ def getpipeoutput(cmds):
     end = time.time()
     logging.info(f'\r[{end - start:.4f}] >> {" | ".join(cmds)}')
     return output.rstrip('\n')
-
-
-def getlogrange(conf, defaultrange='HEAD', end_only=True):
-    commit_range = getcommitrange(conf, defaultrange, end_only)
-    if len(conf['start_date']) > 0:
-        return '--since="%s" "%s"' % (conf['start_date'], commit_range)
-    return commit_range
-
-
-def getcommitrange(conf, defaultrange='HEAD', end_only=False):
-    if len(conf['commit_end']) > 0:
-        if end_only or len(conf['commit_begin']) == 0:
-            return conf['commit_end']
-        return '%s..%s' % (conf['commit_begin'], conf['commit_end'])
-    return defaultrange
-
-
-def getkeyssortedbyvalues(dictionary):
-    return [elem[1] for elem in sorted([(el[1], el[0]) for el in dictionary.items()])]
-
-
-# dict['author'] = { 'commits': 512 } - ...key(dict, 'commits')
-def getkeyssortedbyvaluekey(d, key):
-    return [elem[1] for elem in sorted([(d[el][key], el) for el in d.keys()])]
-
-
-def getstatsummarycounts(line):
-    numbers = re.findall('\d+', line)
-    if len(numbers) == 1:
-        # neither insertions nor deletions: may probably only happen for "0 files changed"
-        numbers.append(0)
-        numbers.append(0)
-    elif len(numbers) == 2 and line.find('(+)') != -1:
-        numbers.append(0)  # only insertions were printed on line
-    elif len(numbers) == 2 and line.find('(-)') != -1:
-        numbers.insert(1, 0)  # only deletions were printed on line
-    return numbers
-
-
-def getversion():
-    from ._version import get_versions
-    __version__ = get_versions()['version']
-    del get_versions
-    return __version__
-
-
-def getgitversion():
-    return getpipeoutput(['git --version']).split('\n')[0]
-
-
-def getgnuplotversion():
-    return getpipeoutput(['%s --version' % gnuplot_cmd]).split('\n')[0]
-
-
-def getnumoffilesfromrev(tree_hash):
-    """
-    Get number of files changed in commit
-    """
-    # DBG: git ls-tree -r --name-only "ceb3165b51ae0680724fd71e16a5ff836a0de41e"' | 'wc -l'
-    return (tree_hash, int(getpipeoutput(['git ls-tree -r --name-only "%s"' % tree_hash, 'wc -l']).split('\n')[0]))
-
-
-def getnumoflinesinblob(blob_id):
-    """
-    Get number of lines in blob
-    """
-
-    # DBG: git cat-file blob e4f17a621893811250be96c8ef9c37b5e97a1df7', 'wc -l'
-    return blob_id, int(getpipeoutput(['git cat-file blob %s' % blob_id, 'wc -l']).split()[0])
-
-def gettimedelta(sha_tuple):
-    """
-    Get the time delta between the time stamp passed in the tuple ([1]) and the sha of the second rev in the tuple ([2])
-    return the result, keyed by the sha of the first rev in the tuple ([0])
-    """
-    # DBG:  git log -n 1 --format=%at "ceb3165b51ae0680724fd71e16a5ff836a0de41e"'
-    timestamp_branch = int(getpipeoutput([' git log -n 1 --format=%%at "%s"' % sha_tuple[2]]).split('\n')[0])
-    delta = datetime.datetime.utcfromtimestamp(sha_tuple[1]) - datetime.datetime.utcfromtimestamp(timestamp_branch)
-
-    return (sha_tuple[0], delta)
-
-

gitstats/process.py

@@ -1,81 +0,0 @@
-#!/usr/bin/python
-# Copyright (c) 2007-2014 Heikki Hokkanen <hoxu@users.sf.net> & others (see doc/AUTHOR)
-# GPLv2 / GPLv3
-import logging
-import os
-import sys
-import time
-
-import multiprocessing_logging
-
-from gitstats.gitdatacollector import GitDataCollector
-from gitstats.htmlreportcreator import HTMLReportCreator
-from gitstats.miscfuncs import getgnuplotversion
-from gitstats import cli
-
-exectime_internal = 0.0
-exectime_external = 0.0
-
-def run():
-
-    conf, paths, outputpath = cli.get_cli()
-
-    logging.basicConfig(level=conf['logging'], format='%(message)s')
-    multiprocessing_logging.install_mp_handler()
-    time_start = time.time()
-
-
-    rundir = os.getcwd()
-
-    try:
-        os.makedirs(outputpath)
-    except OSError:
-        pass
-    if not os.path.isdir(outputpath):
-        logging.fatal('Output path is not a directory or does not exist')
-        sys.exit(1)
-
-    if not getgnuplotversion():
-        logging.error('gnuplot not found')
-        sys.exit(1)
-
-    logging.info(f'Output path: {outputpath}')
-    cachefile = os.path.join(outputpath, 'gitstats.cache')
-
-    data = GitDataCollector(conf)
-    data.loadCache(cachefile)
-
-    for gitpath in paths:
-        logging.info(f'Git path: {gitpath}')
-
-        prevdir = os.getcwd()
-        os.chdir(gitpath)
-
-        logging.info('Collecting data...')
-        data.collect(gitpath)
-
-        os.chdir(prevdir)
-
-    data.saveCache(cachefile)
-
-    logging.info('Refining data...')
-    data.refine()
-
-    os.chdir(rundir)
-
-    logging.info('Generating report...')
-    report = HTMLReportCreator(conf)
-    report.create(data, outputpath)
-
-    time_end = time.time()
-    calculated_exectime_internal = time_end - time_start
-    logging.info(f'Execution time {calculated_exectime_internal} secs, {exectime_external} secs ({(100.0 * exectime_external) / calculated_exectime_internal}%) in external commands)')
-
-    print('You may now run:')
-    print()
-    print('   sensible-browser \'%s\'' % os.path.join(outputpath, 'index.html').replace("'", "'\\''"))
-    print()
-
-
-if __name__ == '__main__':
-    run()

gitstats/reportcreator.py

@@ -1,11 +0,0 @@
-class ReportCreator:
-    """Creates the actual report based on given data."""
-
-    def __init__(self, conf):
-        self.conf = conf
-        self.data = None
-        self.path = None
-
-    def create(self, data, path):
-        self.data = data
-        self.path = path

gitstats/resources/gitstats.css

@@ -1,145 +0,0 @@
-/**
- * GitStats - default style
- */
-body {
-	color: black;
-	background-color: #dfd;
-}
-
-dt {
-	font-weight: bold;
-	float: left;
-	margin-right: 1em;
-}
-
-dt:after {
-	content: ': ';
-}
-
-dd {
-	display: block;
-	clear: left;
-}
-
-table {
-	border: 1px solid black;
-	border-collapse: collapse;
-	font-size: 80%;
-	margin-bottom: 1em;
-}
-
-table.noborders {
-	border: none;
-}
-
-table.noborders td {
-	border: none;
-}
-
-.vtable {
-	float: right;
-	clear: both;
-}
-
-table.tags td {
-	vertical-align: top;
-}
-
-td {
-	background-color: white;
-}
-
-th {
-	background-color: #ddf;
-}
-
-th a {
-	text-decoration: none;
-}
-
-tr:hover {
-	background-color: #ddf;
-}
-
-td {
-	border: 1px solid black;
-	padding: 0.2em;
-	padding-left: 0.3em;
-	padding-right: 0.2em;
-}
-
-/* Navigation bar; tabbed style */
-.nav {
-	border-bottom: 1px solid black;
-	padding: 0.3em;
-}
-
-.nav ul {
-	list-style-type: none;
-	display: inline;
-	margin: 0;
-	padding: 0;
-}
-
-.nav li {
-	display: inline;
-}
-
-.nav li a {
-	padding: 0.3em;
-	text-decoration: none;
-	color: black;
-	border: 1px solid black;
-	margin: 0.5em;
-	background-color: #ddf;
-}
-
-.nav li a:hover {
-	background-color: #ddd;
-	border-bottom: 1px solid #ddf;
-}
-
-img {
-	border: 1px solid black;
-	padding: 0.5em;
-	background-color: white;
-}
-
-th img {
-	border: 0px;
-	padding: 0px;
-	background-color: #ddf;
-}
-
-h1 a, h2 a {
-	color: black;
-	text-decoration: none;
-}
-
-h1:hover a:after,
-h2:hover a:after {
-	content: '¶';
-	color: #555;
-}
-
-h1 {
-	font-size: x-large;
-}
-
-h2 {
-	background-color: #564;
-	border: 1px solid black;
-	padding-left: 0.5em;
-	padding-right: 0.5em;
-	color: white;
-	font-size: large;
-	clear: both;
-}
-
-h2 a {
-	color: white;
-}
-
-.moreauthors {
-	font-size: 80%;
-}

gitstats/resources/sortable.js

@@ -1,324 +0,0 @@
-/*
-Table sorting script  by Joost de Valk, check it out at http://www.joostdevalk.nl/code/sortable-table/.
-Based on a script from http://www.kryogenix.org/code/browser/sorttable/.
-Distributed under the MIT license: http://www.kryogenix.org/code/browser/licence.html .
-
-Copyright (c) 1997-2007 Stuart Langridge, Joost de Valk.
-
-Version 1.5.7
-*/
-
-/* You can change these values */
-var image_path = "";
-var image_up = "arrow-up.gif";
-var image_down = "arrow-down.gif";
-var image_none = "arrow-none.gif";
-var europeandate = true;
-var alternate_row_colors = true;
-
-/* Don't change anything below this unless you know what you're doing */
-addEvent(window, "load", sortables_init);
-
-var SORT_COLUMN_INDEX;
-var thead = false;
-
-function sortables_init() {
-	// Find all tables with class sortable and make them sortable
-	if (!document.getElementsByTagName) return;
-	tbls = document.getElementsByTagName("table");
-	for (ti=0;ti<tbls.length;ti++) {
-		thisTbl = tbls[ti];
-		if (((' '+thisTbl.className+' ').indexOf("sortable") != -1) && (thisTbl.id)) {
-			ts_makeSortable(thisTbl);
-		}
-	}
-}
-
-function ts_makeSortable(t) {
-	if (t.rows && t.rows.length > 0) {
-		if (t.tHead && t.tHead.rows.length > 0) {
-			var firstRow = t.tHead.rows[t.tHead.rows.length-1];
-			thead = true;
-		} else {
-			var firstRow = t.rows[0];
-		}
-	}
-	if (!firstRow) return;
-	
-	// We have a first row: assume it's the header, and make its contents clickable links
-	for (var i=0;i<firstRow.cells.length;i++) {
-		var cell = firstRow.cells[i];
-		var txt = ts_getInnerText(cell);
-		if (cell.className != "unsortable" && cell.className.indexOf("unsortable") == -1) {
-			cell.innerHTML = '<a href="#" class="sortheader" onclick="ts_resortTable(this, '+i+');return false;">'+txt+'<span class="sortarrow">&nbsp;&nbsp;<img src="'+ image_path + image_none + '" alt="&darr;"/></span></a>';
-		}
-	}
-	if (alternate_row_colors) {
-		alternate(t);
-	}
-}
-
-function ts_getInnerText(el) {
-	if (typeof el == "string") return el;
-	if (typeof el == "undefined") { return el };
-	if (el.innerText) return el.innerText;	//Not needed but it is faster
-	var str = "";
-	
-	var cs = el.childNodes;
-	var l = cs.length;
-	for (var i = 0; i < l; i++) {
-		switch (cs[i].nodeType) {
-			case 1: //ELEMENT_NODE
-				str += ts_getInnerText(cs[i]);
-				break;
-			case 3:	//TEXT_NODE
-				str += cs[i].nodeValue;
-				break;
-		}
-	}
-	return str;
-}
-
-function ts_resortTable(lnk, clid) {
-	var span;
-	for (var ci=0;ci<lnk.childNodes.length;ci++) {
-		if (lnk.childNodes[ci].tagName && lnk.childNodes[ci].tagName.toLowerCase() == 'span') span = lnk.childNodes[ci];
-	}
-	var spantext = ts_getInnerText(span);
-	var td = lnk.parentNode;
-	var column = clid || td.cellIndex;
-	var t = getParent(td,'TABLE');
-	// Work out a type for the column
-	if (t.rows.length <= 1) return;
-	var itm = "";
-	var i = 1;
-	while (itm == "" && i < t.tBodies[0].rows.length) {
-		var itm = ts_getInnerText(t.tBodies[0].rows[i].cells[column]);
-		itm = trim(itm);
-		if (itm.substr(0,4) == "<!--" || itm.length == 0) {
-			itm = "";
-		}
-		i++;
-	}
-	if (itm == "") return; 
-	sortfn = ts_sort_caseinsensitive;
-	if (itm.match(/^\d\d[\/\.-][a-zA-z][a-zA-Z][a-zA-Z][\/\.-]\d\d\d\d$/)) sortfn = ts_sort_date;
-	if (itm.match(/^\d\d[\/\.-]\d\d[\/\.-]\d\d\d{2}?$/)) sortfn = ts_sort_date;
-	if (itm.match(/^-?[£$€Û¢´]\d/)) sortfn = ts_sort_numeric;
-	// ignore stuff in () after the numbers.
-	if (itm.match(/^-?(\d+[,\.]?)+(E[-+][\d]+)?%?( \(.*\))?$/)) sortfn = ts_sort_numeric;
-	SORT_COLUMN_INDEX = column;
-	var firstRow = new Array();
-	var newRows = new Array();
-	for (k=0;k<t.tBodies.length;k++) {
-		for (i=0;i<t.tBodies[k].rows[0].length;i++) { 
-			firstRow[i] = t.tBodies[k].rows[0][i]; 
-		}
-	}
-	for (k=0;k<t.tBodies.length;k++) {
-		if (!thead) {
-			// Skip the first row
-			for (j=1;j<t.tBodies[k].rows.length;j++) { 
-				newRows[j-1] = t.tBodies[k].rows[j];
-			}
-		} else {
-			// Do NOT skip the first row
-			for (j=0;j<t.tBodies[k].rows.length;j++) { 
-				newRows[j] = t.tBodies[k].rows[j];
-			}
-		}
-	}
-	newRows.sort(sortfn);
-	if (span.getAttribute("sortdir") == 'down') {
-			ARROW = '&nbsp;&nbsp;<img src="'+ image_path + image_down + '" alt="&darr;"/>';
-			newRows.reverse();
-			span.setAttribute('sortdir','up');
-	} else {
-			ARROW = '&nbsp;&nbsp;<img src="'+ image_path + image_up + '" alt="&uarr;"/>';
-			span.setAttribute('sortdir','down');
-	} 
-    // We appendChild rows that already exist to the tbody, so it moves them rather than creating new ones
-    // don't do sortbottom rows
-    for (i=0; i<newRows.length; i++) { 
-		if (!newRows[i].className || (newRows[i].className && (newRows[i].className.indexOf('sortbottom') == -1))) {
-			t.tBodies[0].appendChild(newRows[i]);
-		}
-	}
-    // do sortbottom rows only
-    for (i=0; i<newRows.length; i++) {
-		if (newRows[i].className && (newRows[i].className.indexOf('sortbottom') != -1)) 
-			t.tBodies[0].appendChild(newRows[i]);
-	}
-	// Delete any other arrows there may be showing
-	var allspans = document.getElementsByTagName("span");
-	for (var ci=0;ci<allspans.length;ci++) {
-		if (allspans[ci].className == 'sortarrow') {
-			if (getParent(allspans[ci],"table") == getParent(lnk,"table")) { // in the same table as us?
-				allspans[ci].innerHTML = '&nbsp;&nbsp;<img src="'+ image_path + image_none + '" alt="&darr;"/>';
-			}
-		}
-	}		
-	span.innerHTML = ARROW;
-	alternate(t);
-}
-
-function getParent(el, pTagName) {
-	if (el == null) {
-		return null;
-	} else if (el.nodeType == 1 && el.tagName.toLowerCase() == pTagName.toLowerCase()) {
-		return el;
-	} else {
-		return getParent(el.parentNode, pTagName);
-	}
-}
-
-function sort_date(date) {	
-	// y2k notes: two digit years less than 50 are treated as 20XX, greater than 50 are treated as 19XX
-	dt = "00000000";
-	if (date.length == 11) {
-		mtstr = date.substr(3,3);
-		mtstr = mtstr.toLowerCase();
-		switch(mtstr) {
-			case "jan": var mt = "01"; break;
-			case "feb": var mt = "02"; break;
-			case "mar": var mt = "03"; break;
-			case "apr": var mt = "04"; break;
-			case "may": var mt = "05"; break;
-			case "jun": var mt = "06"; break;
-			case "jul": var mt = "07"; break;
-			case "aug": var mt = "08"; break;
-			case "sep": var mt = "09"; break;
-			case "oct": var mt = "10"; break;
-			case "nov": var mt = "11"; break;
-			case "dec": var mt = "12"; break;
-			// default: var mt = "00";
-		}
-		dt = date.substr(7,4)+mt+date.substr(0,2);
-		return dt;
-	} else if (date.length == 10) {
-		if (europeandate == false) {
-			dt = date.substr(6,4)+date.substr(0,2)+date.substr(3,2);
-			return dt;
-		} else {
-			dt = date.substr(6,4)+date.substr(3,2)+date.substr(0,2);
-			return dt;
-		}
-	} else if (date.length == 8) {
-		yr = date.substr(6,2);
-		if (parseInt(yr) < 50) { 
-			yr = '20'+yr; 
-		} else { 
-			yr = '19'+yr; 
-		}
-		if (europeandate == true) {
-			dt = yr+date.substr(3,2)+date.substr(0,2);
-			return dt;
-		} else {
-			dt = yr+date.substr(0,2)+date.substr(3,2);
-			return dt;
-		}
-	}
-	return dt;
-}
-
-function ts_sort_date(a,b) {
-	dt1 = sort_date(ts_getInnerText(a.cells[SORT_COLUMN_INDEX]));
-	dt2 = sort_date(ts_getInnerText(b.cells[SORT_COLUMN_INDEX]));
-	
-	if (dt1==dt2) {
-		return 0;
-	}
-	if (dt1<dt2) { 
-		return -1;
-	}
-	return 1;
-}
-function ts_sort_numeric(a,b) {
-	var aa = ts_getInnerText(a.cells[SORT_COLUMN_INDEX]);
-	aa = clean_num(aa);
-	var bb = ts_getInnerText(b.cells[SORT_COLUMN_INDEX]);
-	bb = clean_num(bb);
-	return compare_numeric(aa,bb);
-}
-function compare_numeric(a,b) {
-	var a = parseFloat(a);
-	a = (isNaN(a) ? 0 : a);
-	var b = parseFloat(b);
-	b = (isNaN(b) ? 0 : b);
-	return a - b;
-}
-function ts_sort_caseinsensitive(a,b) {
-	aa = ts_getInnerText(a.cells[SORT_COLUMN_INDEX]).toLowerCase();
-	bb = ts_getInnerText(b.cells[SORT_COLUMN_INDEX]).toLowerCase();
-	if (aa==bb) {
-		return 0;
-	}
-	if (aa<bb) {
-		return -1;
-	}
-	return 1;
-}
-function ts_sort_default(a,b) {
-	aa = ts_getInnerText(a.cells[SORT_COLUMN_INDEX]);
-	bb = ts_getInnerText(b.cells[SORT_COLUMN_INDEX]);
-	if (aa==bb) {
-		return 0;
-	}
-	if (aa<bb) {
-		return -1;
-	}
-	return 1;
-}
-function addEvent(elm, evType, fn, useCapture)
-// addEvent and removeEvent
-// cross-browser event handling for IE5+,	NS6 and Mozilla
-// By Scott Andrew
-{
-	if (elm.addEventListener){
-		elm.addEventListener(evType, fn, useCapture);
-		return true;
-	} else if (elm.attachEvent){
-		var r = elm.attachEvent("on"+evType, fn);
-		return r;
-	} else {
-		alert("Handler could not be removed");
-	}
-}
-function clean_num(str) {
-	str = str.replace(new RegExp(/[^-?0-9.]/g),"");
-	return str;
-}
-function trim(s) {
-	return s.replace(/^\s+|\s+$/g, "");
-}
-function alternate(table) {
-	// Take object table and get all it's tbodies.
-	var tableBodies = table.getElementsByTagName("tbody");
-	// Loop through these tbodies
-	for (var i = 0; i < tableBodies.length; i++) {
-		// Take the tbody, and get all it's rows
-		var tableRows = tableBodies[i].getElementsByTagName("tr");
-		// Loop through these rows
-		// Start at 1 because we want to leave the heading row untouched
-		for (var j = 0; j < tableRows.length; j++) {
-			// Check if j is even, and apply classes for both possible results
-			if ( (j % 2) == 0  ) {
-				if ( !(tableRows[j].className.indexOf('odd') == -1) ) {
-					tableRows[j].className = tableRows[j].className.replace('odd', 'even');
-				} else {
-					if ( tableRows[j].className.indexOf('even') == -1 ) {
-						tableRows[j].className += " even";
-					}
-				}
-			} else {
-				if ( !(tableRows[j].className.indexOf('even') == -1) ) {
-					tableRows[j].className = tableRows[j].className.replace('even', 'odd');
-				} else {
-					if ( tableRows[j].className.indexOf('odd') == -1 ) {
-						tableRows[j].className += " odd";
-					}
-				}
-			} 
-		}
-	}
-}

setup.py

@@ -56,7 +56,6 @@ setup(
     entry_points={
         'console_scripts': [
             'gitstats = gitstats:main',
-            'gencsvstats = gitstats.git_csv_generator:gen_csv'
         ],
     },
     # entry_points={