diff options
Diffstat (limited to 'gitweb')
| -rw-r--r-- | gitweb/INSTALL | 266 | ||||
| -rw-r--r-- | gitweb/Makefile | 129 | ||||
| -rw-r--r-- | gitweb/README | 465 | ||||
| -rw-r--r-- | gitweb/git-favicon.png | bin | 164 -> 115 bytes | |||
| -rw-r--r-- | gitweb/git-logo.png | bin | 208 -> 207 bytes | |||
| -rw-r--r-- | gitweb/gitweb.css | 159 | ||||
| -rw-r--r-- | gitweb/gitweb.js | 875 | ||||
| -rwxr-xr-x | gitweb/gitweb.perl | 4769 | ||||
| -rw-r--r-- | gitweb/test/Märchen | 2 | ||||
| -rw-r--r-- | gitweb/test/file with spaces | 4 | ||||
| -rw-r--r-- | gitweb/test/file+plus+sign | 6 |
11 files changed, 5262 insertions, 1413 deletions
diff --git a/gitweb/INSTALL b/gitweb/INSTALL new file mode 100644 index 0000000000..b76a0cffff --- /dev/null +++ b/gitweb/INSTALL @@ -0,0 +1,266 @@ +GIT web Interface (gitweb) Installation +======================================= + +First you have to generate gitweb.cgi from gitweb.perl using +"make gitweb/gitweb.cgi", then copy appropriate files (gitweb.cgi, +gitweb.css, git-logo.png and git-favicon.png) to their destination. +For example if git was (or is) installed with /usr prefix, you can do + + $ make prefix=/usr gitweb/gitweb.cgi ;# as yourself + # cp gitweb/git* /var/www/cgi-bin/ ;# as root + +Alternatively you can use autoconf generated ./configure script to +set up path to git binaries (via config.mak.autogen), so you can write +instead + + $ make configure ;# as yourself + $ ./configure --prefix=/usr ;# as yourself + $ make gitweb/gitweb.cgi ;# as yourself + # cp gitweb/git* /var/www/cgi-bin/ ;# as root + +The above example assumes that your web server is configured to run +[executable] files in /var/www/cgi-bin/ as server scripts (as CGI +scripts). + + +Build time configuration +------------------------ + +See also "How to configure gitweb for your local system" in README +file for gitweb (in gitweb/README). + +- There are many configuration variables which affect building of + gitweb.cgi; see "default configuration for gitweb" section in main + (top dir) Makefile, and instructions for building gitweb/gitweb.cgi + target. + + One of the most important is where to find the git wrapper binary. Gitweb + tries to find the git wrapper at $(bindir)/git, so you have to set $bindir + when building gitweb.cgi, or $prefix from which $bindir is derived. If + you build and install gitweb together with the rest of the git suite, + there should be no problems. Otherwise, if git was for example + installed from a binary package, you have to set $prefix (or $bindir) + accordingly. + +- Another important issue is where are git repositories you want to make + available to gitweb. By default gitweb searches for repositories under + /pub/git; if you want to have projects somewhere else, like /home/git, + use GITWEB_PROJECTROOT build configuration variable. + + By default all git repositories under projectroot are visible and + available to gitweb. The list of projects is generated by default by + scanning the projectroot directory for git repositories. This can be + changed (configured) as described in "Gitweb repositories" section + below. + + Note that gitweb deals directly with the object database, and does not + need a working directory; the name of the project is the name of its + repository object database, usually projectname.git for bare + repositories. If you want to provide gitweb access to non-bare (live) + repositories, you can make projectname.git a symbolic link under + projectroot linking to projectname/.git (but it is just + a suggestion). + +- You can control where gitweb tries to find its main CSS style file, + its favicon and logo with the GITWEB_CSS, GITWEB_FAVICON and GITWEB_LOGO + build configuration variables. By default gitweb tries to find them + in the same directory as gitweb.cgi script. + +Build example +~~~~~~~~~~~~~ + +- To install gitweb to /var/www/cgi-bin/gitweb/ when git wrapper + is installed at /usr/local/bin/git and the repositories (projects) + we want to display are under /home/local/scm, you can do + + make GITWEB_PROJECTROOT="/home/local/scm" \ + GITWEB_CSS="/gitweb/gitweb.css" \ + GITWEB_LOGO="/gitweb/git-logo.png" \ + GITWEB_FAVICON="/gitweb/git-favicon.png" \ + bindir=/usr/local/bin \ + gitweb/gitweb.cgi + + cp -fv ~/git/gitweb/gitweb.{cgi,css} \ + ~/git/gitweb/git-{favicon,logo}.png \ + /var/www/cgi-bin/gitweb/ + + +Gitweb config file +------------------ + +See also "Runtime gitweb configuration" section in README file +for gitweb (in gitweb/README). + +- You can configure gitweb further using the gitweb configuration file; + by default this is a file named gitweb_config.perl in the same place as + gitweb.cgi script. You can control the default place for the config file + using the GITWEB_CONFIG build configuration variable, and you can set it + using the GITWEB_CONFIG environment variable. If this file does not + exist, gitweb looks for a system-wide configuration file, normally + /etc/gitweb.conf. You can change the default using the + GITWEB_CONFIG_SYSTEM build configuration variable, and override it + through the GITWEB_CONFIG_SYSTEM environment variable. + +- The gitweb config file is a fragment of perl code. You can set variables + using "our $variable = value"; text from "#" character until the end + of a line is ignored. See perlsyn(1) for details. + + See the top of gitweb.perl file for examples of customizable options. + +Config file example +~~~~~~~~~~~~~~~~~~~ + +To enable blame, pickaxe search, and snapshot support, while allowing +individual projects to turn them off, put the following in your +GITWEB_CONFIG file: + + $feature{'blame'}{'default'} = [1]; + $feature{'blame'}{'override'} = 1; + + $feature{'pickaxe'}{'default'} = [1]; + $feature{'pickaxe'}{'override'} = 1; + + $feature{'snapshot'}{'default'} = ['zip', 'tgz']; + $feature{'snapshot'}{'override'} = 1; + +If you allow overriding for the snapshot feature, you can specify which +snapshot formats are globally disabled. You can also add any command line +options you want (such as setting the compression level). For instance, +you can disable Zip compressed snapshots and set GZip to run at level 6 by +adding the following lines to your $GITWEB_CONFIG: + + $known_snapshot_formats{'zip'}{'disabled'} = 1; + $known_snapshot_formats{'tgz'}{'compressor'} = ['gzip','-6']; + + +Gitweb repositories +------------------- + +- By default all git repositories under projectroot are visible and + available to gitweb. The list of projects is generated by default by + scanning the projectroot directory for git repositories (for object + databases to be more exact). + + You can provide a pre-generated list of [visible] repositories, + together with information about their owners (the project ownership + defaults to the owner of the repository directory otherwise), by setting + the GITWEB_LIST build configuration variable (or the $projects_list + variable in the gitweb config file) to point to a plain file. + + Each line of the projects list file should consist of the url-encoded path + to the project repository database (relative to projectroot), followed + by the url-encoded project owner on the same line (separated by a space). + Spaces in both project path and project owner have to be encoded as either + '%20' or '+'. + + Other characters that have to be url-encoded, i.e. replaced by '%' + followed by two-digit character number in octal, are: other whitespace + characters (because they are field separator in a record), plus sign '+' + (because it can be used as replacement for spaces), and percent sign '%' + (which is used for encoding / escaping). + + You can generate the projects list index file using the project_index + action (the 'TXT' link on projects list page) directly from gitweb. + +- By default, even if a project is not visible on projects list page, you + can view it nevertheless by hand-crafting a gitweb URL. You can set the + GITWEB_STRICT_EXPORT build configuration variable (or the $strict_export + variable in the gitweb config file) to only allow viewing of + repositories also shown on the overview page. + +- Alternatively, you can configure gitweb to only list and allow + viewing of the explicitly exported repositories, via the + GITWEB_EXPORT_OK build configuration variable (or the $export_ok + variable in gitweb config file). If it evaluates to true, gitweb + shows repositories only if this file exists in its object database + (if directory has the magic file named $export_ok). + +- Finally, it is possible to specify an arbitrary perl subroutine that + will be called for each project to determine if it can be exported. + The subroutine receives an absolute path to the project as its only + parameter. + + For example, if you use mod_perl to run the script, and have dumb + http protocol authentication configured for your repositories, you + can use the following hook to allow access only if the user is + authorized to read the files: + + $export_auth_hook = sub { + use Apache2::SubRequest (); + use Apache2::Const -compile => qw(HTTP_OK); + my $path = "$_[0]/HEAD"; + my $r = Apache2::RequestUtil->request; + my $sub = $r->lookup_file($path); + return $sub->filename eq $path + && $sub->status == Apache2::Const::HTTP_OK; + }; + + +Generating projects list using gitweb +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +We assume that GITWEB_CONFIG has its default Makefile value, namely +gitweb_config.perl. Put the following in gitweb_make_index.perl file: + + $GITWEB_CONFIG = "gitweb_config.perl"; + do $GITWEB_CONFIG if -e $GITWEB_CONFIG; + + $projects_list = $projectroot; + +Then create the following script to get list of project in the format +suitable for GITWEB_LIST build configuration variable (or +$projects_list variable in gitweb config): + + #!/bin/sh + + export GITWEB_CONFIG="gitweb_make_index.perl" + export GATEWAY_INTERFACE="CGI/1.1" + export HTTP_ACCEPT="*/*" + export REQUEST_METHOD="GET" + export QUERY_STRING="a=project_index" + + perl -- /var/www/cgi-bin/gitweb.cgi + + +Requirements +------------ + + - Core git tools + - Perl + - Perl modules: CGI, Encode, Fcntl, File::Find, File::Basename. + - web server + + +Example web server configuration +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +See also "Webserver configuration" section in README file for gitweb +(in gitweb/README). + + +- Apache2, gitweb installed as CGI script, + under /var/www/cgi-bin/ + + ScriptAlias /cgi-bin/ "/var/www/cgi-bin/" + + <Directory "/var/www/cgi-bin"> + Options Indexes FollowSymlinks ExecCGI + AllowOverride None + Order allow,deny + Allow from all + </Directory> + +- Apache2, gitweb installed as mod_perl legacy script, + under /var/www/perl/ + + Alias /perl "/var/www/perl" + + <Directory "/var/www/perl"> + SetHandler perl-script + PerlResponseHandler ModPerl::Registry + PerlOptions +ParseHeaders + Options Indexes FollowSymlinks +ExecCGI + AllowOverride None + Order allow,deny + Allow from all + </Directory> diff --git a/gitweb/Makefile b/gitweb/Makefile new file mode 100644 index 0000000000..c9eb1ee667 --- /dev/null +++ b/gitweb/Makefile @@ -0,0 +1,129 @@ +# The default target of this Makefile is... +all:: + +# Define V=1 to have a more verbose compile. +# +# Define JSMIN to point to JavaScript minifier that functions as +# a filter to have gitweb.js minified. +# + +prefix ?= $(HOME) +bindir ?= $(prefix)/bin +RM ?= rm -f + +# JavaScript minifier invocation that can function as filter +JSMIN ?= + +# default configuration for gitweb +GITWEB_CONFIG = gitweb_config.perl +GITWEB_CONFIG_SYSTEM = /etc/gitweb.conf +GITWEB_HOME_LINK_STR = projects +GITWEB_SITENAME = +GITWEB_PROJECTROOT = /pub/git +GITWEB_PROJECT_MAXDEPTH = 2007 +GITWEB_EXPORT_OK = +GITWEB_STRICT_EXPORT = +GITWEB_BASE_URL = +GITWEB_LIST = +GITWEB_HOMETEXT = indextext.html +GITWEB_CSS = gitweb.css +GITWEB_LOGO = git-logo.png +GITWEB_FAVICON = git-favicon.png +ifdef JSMIN +GITWEB_JS = gitweb.min.js +else +GITWEB_JS = gitweb.js +endif +GITWEB_SITE_HEADER = +GITWEB_SITE_FOOTER = + +# include user config +-include ../config.mak.autogen +-include ../config.mak + +# determine version +../GIT-VERSION-FILE: .FORCE-GIT-VERSION-FILE + $(QUIET_SUBDIR0)../ $(QUIET_SUBDIR1) GIT-VERSION-FILE + +-include ../GIT-VERSION-FILE + +### Build rules + +SHELL_PATH ?= $(SHELL) +PERL_PATH ?= /usr/bin/perl + +# Shell quote; +bindir_SQ = $(subst ','\'',$(bindir)) #' +SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH)) #' +PERL_PATH_SQ = $(subst ','\'',$(PERL_PATH)) #' + +# Quiet generation (unless V=1) +QUIET_SUBDIR0 = +$(MAKE) -C # space to separate -C and subdir +QUIET_SUBDIR1 = + +ifneq ($(findstring $(MAKEFLAGS),w),w) +PRINT_DIR = --no-print-directory +else # "make -w" +NO_SUBDIR = : +endif + +ifneq ($(findstring $(MAKEFLAGS),s),s) +ifndef V + QUIET = @ + QUIET_GEN = $(QUIET)echo ' ' GEN $@; + QUIET_SUBDIR0 = +@subdir= + QUIET_SUBDIR1 = ;$(NO_SUBDIR) echo ' ' SUBDIR $$subdir; \ + $(MAKE) $(PRINT_DIR) -C $$subdir + export V + export QUIET + export QUIET_GEN + export QUIET_SUBDIR0 + export QUIET_SUBDIR1 +endif +endif + +all:: gitweb.cgi + +ifdef JSMIN +FILES=gitweb.cgi gitweb.min.js +gitweb.cgi: gitweb.perl gitweb.min.js +else # !JSMIN +FILES=gitweb.cgi +gitweb.cgi: gitweb.perl +endif # JSMIN + +gitweb.cgi: + $(QUIET_GEN)$(RM) $@ $@+ && \ + sed -e '1s|#!.*perl|#!$(PERL_PATH_SQ)|' \ + -e 's|++GIT_VERSION++|$(GIT_VERSION)|g' \ + -e 's|++GIT_BINDIR++|$(bindir)|g' \ + -e 's|++GITWEB_CONFIG++|$(GITWEB_CONFIG)|g' \ + -e 's|++GITWEB_CONFIG_SYSTEM++|$(GITWEB_CONFIG_SYSTEM)|g' \ + -e 's|++GITWEB_HOME_LINK_STR++|$(GITWEB_HOME_LINK_STR)|g' \ + -e 's|++GITWEB_SITENAME++|$(GITWEB_SITENAME)|g' \ + -e 's|++GITWEB_PROJECTROOT++|$(GITWEB_PROJECTROOT)|g' \ + -e 's|"++GITWEB_PROJECT_MAXDEPTH++"|$(GITWEB_PROJECT_MAXDEPTH)|g' \ + -e 's|++GITWEB_EXPORT_OK++|$(GITWEB_EXPORT_OK)|g' \ + -e 's|++GITWEB_STRICT_EXPORT++|$(GITWEB_STRICT_EXPORT)|g' \ + -e 's|++GITWEB_BASE_URL++|$(GITWEB_BASE_URL)|g' \ + -e 's|++GITWEB_LIST++|$(GITWEB_LIST)|g' \ + -e 's|++GITWEB_HOMETEXT++|$(GITWEB_HOMETEXT)|g' \ + -e 's|++GITWEB_CSS++|$(GITWEB_CSS)|g' \ + -e 's|++GITWEB_LOGO++|$(GITWEB_LOGO)|g' \ + -e 's|++GITWEB_FAVICON++|$(GITWEB_FAVICON)|g' \ + -e 's|++GITWEB_JS++|$(GITWEB_JS)|g' \ + -e 's|++GITWEB_SITE_HEADER++|$(GITWEB_SITE_HEADER)|g' \ + -e 's|++GITWEB_SITE_FOOTER++|$(GITWEB_SITE_FOOTER)|g' \ + $< >$@+ && \ + chmod +x $@+ && \ + mv $@+ $@ + +ifdef JSMIN +gitweb.min.js: gitweb.js + $(QUIET_GEN)$(JSMIN) <$< >$@ +endif # JSMIN + +clean: + $(RM) $(FILES) + +.PHONY: all clean .FORCE-GIT-VERSION-FILE diff --git a/gitweb/README b/gitweb/README index e02e90f042..ad6a04c464 100644 --- a/gitweb/README +++ b/gitweb/README @@ -2,7 +2,7 @@ GIT web Interface ================= The one working on: - http://www.kernel.org/git/ + http://git.kernel.org/ From the git version 1.4.0 gitweb is bundled with git. @@ -10,40 +10,299 @@ From the git version 1.4.0 gitweb is bundled with git. How to configure gitweb for your local system --------------------------------------------- +See also the "Build time configuration" section in the INSTALL +file for gitweb (in gitweb/INSTALL). + You can specify the following configuration variables when building GIT: + * GIT_BINDIR + Points where to find the git executable. You should set it up to + the place where the git binary was installed (usually /usr/bin) if you + don't install git from sources together with gitweb. [Default: $(bindir)] * GITWEB_SITENAME - Shown in the title of all generated pages, defaults to the servers name. + Shown in the title of all generated pages, defaults to the server name + (SERVER_NAME CGI environment variable) if not set. [No default] * GITWEB_PROJECTROOT - The root directory for all projects shown by gitweb. + The root directory for all projects shown by gitweb. Must be set + correctly for gitweb to find repositories to display. See also + "Gitweb repositories" in the INSTALL file for gitweb. [Default: /pub/git] + * GITWEB_PROJECT_MAXDEPTH + The filesystem traversing limit for getting the project list; the number + is taken as depth relative to the projectroot. It is used when + GITWEB_LIST is a directory (or is not set; then project root is used). + Is is meant to speed up project listing on large work trees by limiting + search depth. [Default: 2007] * GITWEB_LIST - points to a directory to scan for projects (defaults to project root) - or to a file for explicit listing of projects. + Points to a directory to scan for projects (defaults to project root + if not set / if empty) or to a file with explicit listing of projects + (together with projects' ownership). See "Generating projects list + using gitweb" in INSTALL file for gitweb to find out how to generate + such file from scan of a directory. [No default, which means use root + directory for projects] + * GITWEB_EXPORT_OK + Show repository only if this file exists (in repository). Only + effective if this variable evaluates to true. [No default / Not set] + * GITWEB_STRICT_EXPORT + Only allow viewing of repositories also shown on the overview page. + This for example makes GITWEB_EXPORT_OK to decide if repository is + available and not only if it is shown. If GITWEB_LIST points to + file with list of project, only those repositories listed would be + available for gitweb. [No default] * GITWEB_HOMETEXT - points to an .html file which is included on the gitweb project - overview page. + Points to an .html file which is included on the gitweb project + overview page ('projects_list' view), if it exists. Relative to + gitweb.cgi script. [Default: indextext.html] + * GITWEB_SITE_HEADER + Filename of html text to include at top of each page. Relative to + gitweb.cgi script. [No default] + * GITWEB_SITE_FOOTER + Filename of html text to include at bottom of each page. Relative to + gitweb.cgi script. [No default] + * GITWEB_HOME_LINK_STR + String of the home link on top of all pages, leading to $home_link + (usually main gitweb page, which means projects list). Used as first + part of gitweb view "breadcrumb trail": <home> / <project> / <view>. + [Default: projects] + * GITWEB_SITENAME + Name of your site or organization to appear in page titles. Set it + to something descriptive for clearer bookmarks etc. If not set + (if empty) gitweb uses "$SERVER_NAME Git", or "Untitled Git" if + SERVER_NAME CGI environment variable is not set (e.g. if running + gitweb as standalone script). [No default] + * GITWEB_BASE_URL + Git base URLs used for URL to where fetch project from, i.e. full + URL is "$git_base_url/$project". Shown on projects summary page. + Repository URL for project can be also configured per repository; this + takes precedence over URLs composed from base URL and a project name. + Note that you can setup multiple base URLs (for example one for + git:// protocol access, another for http:// access) from the gitweb + config file. [No default] * GITWEB_CSS - Points to the location where you put gitweb.css on your web server. + Points to the location where you put gitweb.css on your web server + (or to be more generic, the URI of gitweb stylesheet). Relative to the + base URI of gitweb. Note that you can setup multiple stylesheets from + the gitweb config file. [Default: gitweb.css] * GITWEB_LOGO - Points to the location where you put git-logo.png on your web server. + Points to the location where you put git-logo.png on your web server + (or to be more generic URI of logo, 72x27 size, displayed in top right + corner of each gitweb page, and used as logo for Atom feed). Relative + to base URI of gitweb. [Default: git-logo.png] + * GITWEB_FAVICON + Points to the location where you put git-favicon.png on your web server + (or to be more generic URI of favicon, assumed to be image/png type; + web browsers that support favicons (website icons) may display them + in the browser's URL bar and next to site name in bookmarks). Relative + to base URI of gitweb. [Default: git-favicon.png] + * GITWEB_JS + Points to the localtion where you put gitweb.js on your web server + (or to be more generic URI of JavaScript code used by gitweb). + Relative to base URI of gitweb. [Default: gitweb.js (or gitweb.min.js + if JSMIN build variable is defined / JavaScript minifier is used)] * GITWEB_CONFIG - This file will be loaded using 'require' and can be used to override any - of the options above as well as some other options - see the top of - 'gitweb.cgi' for their full list and description. If the environment - $GITWEB_CONFIG is set when gitweb.cgi is executed the file in the - environment variable will be loaded instead of the file - specified when gitweb.cgi was created. + This Perl file will be loaded using 'do' and can be used to override any + of the options above as well as some other options -- see the "Runtime + gitweb configuration" section below, and top of 'gitweb.cgi' for their + full list and description. If the environment variable GITWEB_CONFIG + is set when gitweb.cgi is executed, then the file specified in the + environment variable will be loaded instead of the file specified + when gitweb.cgi was created. [Default: gitweb_config.perl] + * GITWEB_CONFIG_SYSTEM + This Perl file will be loaded using 'do' as a fallback if GITWEB_CONFIG + does not exist. If the environment variable GITWEB_CONFIG_SYSTEM is set + when gitweb.cgi is executed, then the file specified in the environment + variable will be loaded instead of the file specified when gitweb.cgi was + created. [Default: /etc/gitweb.conf] Runtime gitweb configuration ---------------------------- You can adjust gitweb behaviour using the file specified in `GITWEB_CONFIG` -(defaults to 'gitweb_config.perl' in the same directory as the CGI). -See the top of 'gitweb.cgi' for the list of variables and some description. +(defaults to 'gitweb_config.perl' in the same directory as the CGI), and +as a fallback `GITWEB_CONFIG_SYSTEM` (defaults to /etc/gitweb.conf). The most notable thing that is not configurable at compile time are the -optional features, stored in the '%features' variable. You can find further -description on how to reconfigure the default features setting in your -`GITWEB_CONFIG` or per-project in `project.git/config` inside 'gitweb.cgi'. +optional features, stored in the '%features' variable. + +Ultimate description on how to reconfigure the default features setting +in your `GITWEB_CONFIG` or per-project in `project.git/config` can be found +as comments inside 'gitweb.cgi'. + +See also the "Gitweb config file" (with an example of config file), and +the "Gitweb repositories" sections in INSTALL file for gitweb. + + +The gitweb config file is a fragment of perl code. You can set variables +using "our $variable = value"; text from "#" character until the end +of a line is ignored. See perlsyn(1) man page for details. + +Below is the list of variables which you might want to set in gitweb config. +See the top of 'gitweb.cgi' for the full list of variables and their +descriptions. + +Gitweb config file variables +~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +You can set, among others, the following variables in gitweb config files +(with the exception of $projectroot and $projects_list this list does +not include variables usually directly set during build): + * $GIT + Core git executable to use. By default set to "$GIT_BINDIR/git", which + in turn is by default set to "$(bindir)/git". If you use git from binary + package, set this to "/usr/bin/git". This can just be "git" if your + webserver has a sensible PATH. If you have multiple git versions + installed it can be used to choose which one to use. + * $version + Gitweb version, set automatically when creating gitweb.cgi from + gitweb.perl. You might want to modify it if you are running modified + gitweb. + * $projectroot + Absolute filesystem path which will be prepended to project path; + the path to repository is $projectroot/$project. Set to + $GITWEB_PROJECTROOT during installation. This variable have to be + set correctly for gitweb to find repositories. + * $projects_list + Source of projects list, either directory to scan, or text file + with list of repositories (in the "<URI-encoded repository path> SP + <URI-encoded repository owner>" line format; actually there can be + any sequence of whitespace in place of space (SP)). Set to + $GITWEB_LIST during installation. If empty, $projectroot is used + to scan for repositories. + * $my_url, $my_uri + Full URL and absolute URL of gitweb script; + in earlier versions of gitweb you might have need to set those + variables, now there should be no need to do it. + * $base_url + Base URL for relative URLs in pages generated by gitweb, + (e.g. $logo, $favicon, @stylesheets if they are relative URLs), + needed and used only for URLs with nonempty PATH_INFO via + <base href="$base_url">. Usually gitweb sets its value correctly, + and there is no need to set this variable, e.g. to $my_uri or "/". + * $home_link + Target of the home link on top of all pages (the first part of view + "breadcrumbs"). By default set to absolute URI of a page ($my_uri). + * @stylesheets + List of URIs of stylesheets (relative to base URI of a page). You + might specify more than one stylesheet, for example use gitweb.css + as base, with site specific modifications in separate stylesheet + to make it easier to upgrade gitweb. You can add 'site' stylesheet + for example by using + push @stylesheets, "gitweb-site.css"; + in the gitweb config file. + * $logo_url, $logo_label + URI and label (title) of GIT logo link (or your site logo, if you choose + to use different logo image). By default they point to git homepage; + in the past they pointed to git documentation at www.kernel.org. + * $projects_list_description_width + The width (in characters) of the projects list "Description" column. + Longer descriptions will be cut (trying to cut at word boundary); + full description is available as 'title' attribute (usually shown on + mouseover). By default set to 25, which might be too small if you + use long project descriptions. + * @git_base_url_list + List of git base URLs used for URL to where fetch project from, shown + in project summary page. Full URL is "$git_base_url/$project". + You can setup multiple base URLs (for example one for git:// protocol + access, and one for http:// "dumb" protocol access). Note that per + repository configuration in 'cloneurl' file, or as values of gitweb.url + project config. + * $default_blob_plain_mimetype + Default mimetype for blob_plain (raw) view, if mimetype checking + doesn't result in some other type; by default 'text/plain'. + * $default_text_plain_charset + Default charset for text files. If not set, web server configuration + would be used. + * $mimetypes_file + File to use for (filename extension based) guessing of MIME types before + trying /etc/mime.types. Path, if relative, is taken currently as + relative to the current git repository. + * $fallback_encoding + Gitweb assumes this charset if line contains non-UTF-8 characters. + Fallback decoding is used without error checking, so it can be even + 'utf-8'. Value must be valid encoding; see Encoding::Supported(3pm) man + page for a list. By default 'latin1', aka. 'iso-8859-1'. + * @diff_opts + Rename detection options for git-diff and git-diff-tree. By default + ('-M'); set it to ('-C') or ('-C', '-C') to also detect copies, or + set it to () if you don't want to have renames detection. + * $prevent_xss + If true, some gitweb features are disabled to prevent content in + repositories from launching cross-site scripting (XSS) attacks. Set this + to true if you don't trust the content of your repositories. The default + is false. + * $maxload + Used to set the maximum load that we will still respond to gitweb queries. + If server load exceed this value then return "503 Service Unavaliable" error. + Server load is taken to be 0 if gitweb cannot determine its value. Set it to + undefined value to turn it off. The default is 300. + + +Projects list file format +~~~~~~~~~~~~~~~~~~~~~~~~~ + +Instead of having gitweb find repositories by scanning filesystem starting +from $projectroot (or $projects_list, if it points to directory), you can +provide list of projects by setting $projects_list to a text file with list +of projects (and some additional info). This file uses the following +format: + +One record (for project / repository) per line, whitespace separated fields; +does not support (at least for now) lines continuation (newline escaping). +Leading and trailing whitespace are ignored, any run of whitespace can be +used as field separator (rules for Perl's "split(' ', $line)"). Keyed by +the first field, which is project name, i.e. path to repository GIT_DIR +relative to $projectroot. Fields use modified URI encoding, defined in +RFC 3986, section 2.1 (Percent-Encoding), or rather "Query string encoding" +(see http://en.wikipedia.org/wiki/Query_string#URL_encoding), the difference +being that SP (' ') can be encoded as '+' (and therefore '+' has to be also +percent-encoded). Reserved characters are: '%' (used for encoding), '+' +(can be used to encode SPACE), all whitespace characters as defined in Perl, +including SP, TAB and LF, (used to separate fields in a record). + +Currently list of fields is + * <repository path> - path to repository GIT_DIR, relative to $projectroot + * <repository owner> - displayed as repository owner, preferably full name, + or email, or both + +You can additionally use $projects_list file to limit which repositories +are visible, and together with $strict_export to limit access to +repositories (see "Gitweb repositories" section in gitweb/INSTALL). + + +Per-repository gitweb configuration +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +You can also configure individual repositories shown in gitweb by creating +file in the GIT_DIR of git repository, or by setting some repo configuration +variable (in GIT_DIR/config). + +You can use the following files in repository: + * README.html + A .html file (HTML fragment) which is included on the gitweb project + summary page inside <div> block element. You can use it for longer + description of a project, to provide links (for example to project's + homepage), etc. This is recognized only if XSS prevention is off + ($prevent_xss is false); a way to include a readme safely when XSS + prevention is on may be worked out in the future. + * description (or gitweb.description) + Short (shortened by default to 25 characters in the projects list page) + single line description of a project (of a repository). Plain text file; + HTML will be escaped. By default set to + Unnamed repository; edit this file to name it for gitweb. + from the template during repository creation. You can use the + gitweb.description repo configuration variable, but the file takes + precedence. + * cloneurl (or multiple-valued gitweb.url) + File with repository URL (used for clone and fetch), one per line. + Displayed in the project summary page. You can use multiple-valued + gitweb.url repository configuration variable for that, but the file + takes precedence. + * gitweb.owner + You can use the gitweb.owner repository configuration variable to set + repository's owner. It is displayed in the project list and summary + page. If it's not set, filesystem directory's owner is used + (via GECOS field / real name field from getpwiud(3)). + * various gitweb.* config variables (in config) + Read description of %feature hash for detailed list, and some + descriptions. Webserver configuration @@ -52,12 +311,19 @@ Webserver configuration If you want to have one URL for both gitweb and your http:// repositories, you can configure apache like this: -<VirtualHost www:80> - ServerName git.domain.org - DocumentRoot /pub/git +<VirtualHost *:80> + ServerName git.example.org + DocumentRoot /pub/git + SetEnv GITWEB_CONFIG /etc/gitweb.conf + + # turning on mod rewrite RewriteEngine on - RewriteRule ^/(.*\.git/(?!/?(info|objects|refs)).*)?$ /cgi-bin/gitweb.cgi%{REQUEST_URI} [L,PT] - SetEnv GITWEB_CONFIG /etc/gitweb.conf + + # make the front page an internal rewrite to the gitweb script + RewriteRule ^/$ /cgi-bin/gitweb.cgi + + # make access for "dumb clients" work + RewriteRule ^/(.*\.git/(?!/?(HEAD|info|objects|refs)).*)?$ /cgi-bin/gitweb.cgi%{REQUEST_URI} [L,PT] </VirtualHost> The above configuration expects your public repositories to live under @@ -73,10 +339,157 @@ override the defaults given at the head of the gitweb.perl (or gitweb.cgi). Look at the comments in that file for information on which variables and what they mean. +If you use the rewrite rules from the example you'll likely also need +something like the following in your gitweb.conf (or gitweb_config.perl) file: + + @stylesheets = ("/some/absolute/path/gitweb.css"); + $my_uri = "/"; + $home_link = "/"; + + +Webserver configuration with multiple projects' root +---------------------------------------------------- + +If you want to use gitweb with several project roots you can edit your apache +virtual host and gitweb.conf configuration files like this : + +virtual host configuration : + +<VirtualHost *:80> + ServerName git.example.org + DocumentRoot /pub/git + SetEnv GITWEB_CONFIG /etc/gitweb.conf + + # turning on mod rewrite + RewriteEngine on + + # make the front page an internal rewrite to the gitweb script + RewriteRule ^/$ /cgi-bin/gitweb.cgi [QSA,L,PT] + + # look for a public_git folder in unix users' home + # http://git.example.org/~<user>/ + RewriteRule ^/\~([^\/]+)(/|/gitweb.cgi)?$ /cgi-bin/gitweb.cgi [QSA,E=GITWEB_PROJECTROOT:/home/$1/public_git/,L,PT] + + # http://git.example.org/+<user>/ + #RewriteRule ^/\+([^\/]+)(/|/gitweb.cgi)?$ /cgi-bin/gitweb.cgi [QSA,E=GITWEB_PROJECTROOT:/home/$1/public_git/,L,PT] + + # http://git.example.org/user/<user>/ + #RewriteRule ^/user/([^\/]+)/(gitweb.cgi)?$ /cgi-bin/gitweb.cgi [QSA,E=GITWEB_PROJECTROOT:/home/$1/public_git/,L,PT] + + # defined list of project roots + RewriteRule ^/scm(/|/gitweb.cgi)?$ /cgi-bin/gitweb.cgi [QSA,E=GITWEB_PROJECTROOT:/pub/scm/,L,PT] + RewriteRule ^/var(/|/gitweb.cgi)?$ /cgi-bin/gitweb.cgi [QSA,E=GITWEB_PROJECTROOT:/var/git/,L,PT] + + # make access for "dumb clients" work + RewriteRule ^/(.*\.git/(?!/?(HEAD|info|objects|refs)).*)?$ /cgi-bin/gitweb.cgi%{REQUEST_URI} [L,PT] +</VirtualHost> + +gitweb.conf configuration : + +$projectroot = $ENV{'GITWEB_PROJECTROOT'} || "/pub/git"; + +These configurations enable two things. First, each unix user (<user>) of the +server will be able to browse through gitweb git repositories found in +~/public_git/ with the following url : http://git.example.org/~<user>/ + +If you do not want this feature on your server just remove the second rewrite rule. + +If you already use mod_userdir in your virtual host or you don't want to use +the '~' as first character just comment or remove the second rewrite rule and +uncomment one of the following according to what you want. + +Second, repositories found in /pub/scm/ and /var/git/ will be accesible +through http://git.example.org/scm/ and http://git.example.org/var/. +You can add as many project roots as you want by adding rewrite rules like the +third and the fourth. + + +PATH_INFO usage +----------------------- +If you enable PATH_INFO usage in gitweb by putting + + $feature{'pathinfo'}{'default'} = [1]; + +in your gitweb.conf, it is possible to set up your server so that it +consumes and produces URLs in the form + +http://git.example.com/project.git/shortlog/sometag + +by using a configuration such as the following, that assumes that +/var/www/gitweb is the DocumentRoot of your webserver, and that it +contains the gitweb.cgi script and complementary static files +(stylesheet, favicon): + +<VirtualHost *:80> + ServerAlias git.example.com + + DocumentRoot /var/www/gitweb + + <Directory /var/www/gitweb> + Options ExecCGI + AddHandler cgi-script cgi + + DirectoryIndex gitweb.cgi + + RewriteEngine On + RewriteCond %{REQUEST_FILENAME} !-f + RewriteCond %{REQUEST_FILENAME} !-d + RewriteRule ^.* /gitweb.cgi/$0 [L,PT] + </Directory> +</VirtualHost> + +The rewrite rule guarantees that existing static files will be properly +served, whereas any other URL will be passed to gitweb as PATH_INFO +parameter. + +Notice that in this case you don't need special settings for +@stylesheets, $my_uri and $home_link, but you lose "dumb client" access +to your project .git dirs. A possible workaround for the latter is the +following: in your project root dir (e.g. /pub/git) have the projects +named without a .git extension (e.g. /pub/git/project instead of +/pub/git/project.git) and configure Apache as follows: + +<VirtualHost *:80> + ServerAlias git.example.com + + DocumentRoot /var/www/gitweb + + AliasMatch ^(/.*?)(\.git)(/.*)?$ /pub/git$1$3 + <Directory /var/www/gitweb> + Options ExecCGI + AddHandler cgi-script cgi + + DirectoryIndex gitweb.cgi + + RewriteEngine On + RewriteCond %{REQUEST_FILENAME} !-f + RewriteCond %{REQUEST_FILENAME} !-d + RewriteRule ^.* /gitweb.cgi/$0 [L,PT] + </Directory> +</VirtualHost> + +The additional AliasMatch makes it so that + +http://git.example.com/project.git + +will give raw access to the project's git dir (so that the project can +be cloned), while + +http://git.example.com/project + +will provide human-friendly gitweb access. + +This solution is not 100% bulletproof, in the sense that if some project +has a named ref (branch, tag) starting with 'git/', then paths such as + +http://git.example.com/project/command/abranch..git/abranch + +will fail with a 404 error. + + Originally written by: Kay Sievers <kay.sievers@vrfy.org> Any comment/question/concern to: Git mailing list <git@vger.kernel.org> - diff --git a/gitweb/git-favicon.png b/gitweb/git-favicon.png Binary files differindex de637c0608..aae35a70e7 100644 --- a/gitweb/git-favicon.png +++ b/gitweb/git-favicon.png diff --git a/gitweb/git-logo.png b/gitweb/git-logo.png Binary files differindex 16ae8d5382..f4ede2e944 100644 --- a/gitweb/git-logo.png +++ b/gitweb/git-logo.png diff --git a/gitweb/gitweb.css b/gitweb/gitweb.css index 7177c6e86b..50067f2e0d 100644 --- a/gitweb/gitweb.css +++ b/gitweb/gitweb.css @@ -1,6 +1,6 @@ body { font-family: sans-serif; - font-size: 12px; + font-size: small; border: solid #d9d8d1; border-width: 1px; margin: 10px; @@ -28,10 +28,18 @@ img.logo { border-width: 0px; } +img.avatar { + vertical-align: middle; +} + +a.list img.avatar { + border-style: none; +} + div.page_header { height: 25px; padding: 8px; - font-size: 18px; + font-size: 150%; font-weight: bold; background-color: #d9d8d1; } @@ -71,6 +79,13 @@ div.page_footer_text { font-style: italic; } +div#generating_info { + margin: 4px; + font-size: smaller; + text-align: center; + color: #505050; +} + div.page_body { padding: 8px; font-family: monospace; @@ -85,6 +100,10 @@ div.title, a.title { color: #000000; } +div.readme { + padding: 8px; +} + a.title:hover { background-color: #d9d8d1; } @@ -107,13 +126,13 @@ span.age { font-style: italic; } -div.page_body span.signoff { +span.signoff { color: #888888; } div.log_link { padding: 0px 8px; - font-size: 10px; + font-size: 70%; font-family: sans-serif; font-style: normal; position: relative; @@ -128,11 +147,14 @@ div.list_head { font-style: italic; } +.author_date, .author { + font-style: italic; +} + div.author_date { padding: 8px; border: solid #d9d8d1; border-width: 0px 0px 1px 0px; - font-style: italic; } a.list { @@ -170,59 +192,90 @@ a.text:hover { table { padding: 8px 4px; -} - -table.project_list { border-spacing: 0; } table.diff_tree { - border-spacing: 0; font-family: monospace; } +table.combined.diff_tree th { + text-align: center; +} + +table.combined.diff_tree td { + padding-right: 24px; +} + +table.combined.diff_tree th.link, +table.combined.diff_tree td.link { + padding: 0px 2px; +} + +table.combined.diff_tree td.nochange a { + color: #6666ff; +} + +table.combined.diff_tree td.nochange a:hover, +table.combined.diff_tree td.nochange a:visited { + color: #d06666; +} + table.blame { border-collapse: collapse; } table.blame td { padding: 0px 5px; - font-size: 12px; + font-size: 100%; vertical-align: top; } th { padding: 2px 5px; - font-size: 12px; + font-size: 100%; text-align: left; } -tr.light:hover { - background-color: #edece6; -} - -tr.dark { - background-color: #f6f6f0; +/* do not change row style on hover for 'blame' view */ +tr.light, +table.blame .light:hover { + background-color: #ffffff; } -tr.dark2 { +tr.dark, +table.blame .dark:hover { background-color: #f6f6f0; } +/* currently both use the same, but it can change */ +tr.light:hover, tr.dark:hover { background-color: #edece6; } +/* boundary commits in 'blame' view */ +/* and commits without "previous" */ +tr.boundary td.sha1, +tr.no-previous td.linenr { + font-weight: bold; +} + +/* for 'blame_incremental', during processing */ +tr.color1 { background-color: #f6fff6; } +tr.color2 { background-color: #f6f6ff; } +tr.color3 { background-color: #fff6f6; } + td { padding: 2px 5px; - font-size: 12px; + font-size: 100%; vertical-align: top; } td.link, td.selflink { padding: 2px 5px; font-family: sans-serif; - font-size: 10px; + font-size: 70%; } td.selflink { @@ -233,7 +286,7 @@ td.sha1 { font-family: monospace; } -td.error { +.error { color: red; background-color: yellow; } @@ -259,6 +312,12 @@ table.diff_tree span.file_status.copied { color: #70a070; } +/* noage: "No commits" */ +table.project_list td.noage { + color: #808080; + font-style: italic; +} + /* age2: 60*60*24*2 <= age */ table.project_list td.age2, table.blame td.age2 { font-style: italic; @@ -298,6 +357,23 @@ td.mode { font-family: monospace; } +/* progress of blame_interactive */ +div#progress_bar { + height: 2px; + margin-bottom: -2px; + background-color: #d8d9d0; +} +div#progress_info { + float: right; + text-align: right; +} + +/* format of (optional) objects size in 'tree' view */ +td.size { + font-family: monospace; + text-align: right; +} + /* styling of diffs (patchsets): commitdiff and blobdiff views */ div.diff.header, div.diff.extended_header { @@ -387,6 +463,10 @@ div.diff.incomplete { color: #cccccc; } +div.diff.nodifferences { + font-weight: bold; + color: #600000; +} div.index_include { border: solid #d9d8d1; @@ -395,14 +475,18 @@ div.index_include { } div.search { - font-size: 12px; + font-size: 100%; font-weight: normal; margin: 4px 8px; - position: absolute; + float: right; top: 56px; right: 12px } +p.projsearch { + text-align: center; +} + td.linenr { text-align: right; } @@ -423,7 +507,7 @@ a.rss_logo { background-color: #ff6600; font-weight: bold; font-family: sans-serif; - font-size: 10px; + font-size: 70%; text-align: center; text-decoration: none; } @@ -432,15 +516,36 @@ a.rss_logo:hover { background-color: #ee5500; } +a.rss_logo.generic { + background-color: #ff8800; +} + +a.rss_logo.generic:hover { + background-color: #ee7700; +} + span.refs span { padding: 0px 4px; - font-size: 10px; + font-size: 70%; font-weight: normal; border: 1px solid; background-color: #ffaaff; border-color: #ffccff #ff00ee #ff00ee #ffccff; } +span.refs span a { + text-decoration: none; + color: inherit; +} + +span.refs span a:hover { + text-decoration: underline; +} + +span.refs span.indirect { + font-style: italic; +} + span.refs span.ref { background-color: #aaaaff; border-color: #ccccff #0033cc #0033cc #ccccff; @@ -463,3 +568,7 @@ span.atnight { span.match { color: #e00000; } + +div.binary { + font-style: italic; +} diff --git a/gitweb/gitweb.js b/gitweb/gitweb.js new file mode 100644 index 0000000000..9c66928c4a --- /dev/null +++ b/gitweb/gitweb.js @@ -0,0 +1,875 @@ +// Copyright (C) 2007, Fredrik Kuivinen <frekui@gmail.com> +// 2007, Petr Baudis <pasky@suse.cz> +// 2008-2009, Jakub Narebski <jnareb@gmail.com> + +/** + * @fileOverview JavaScript code for gitweb (git web interface). + * @license GPLv2 or later + */ + +/* ============================================================ */ +/* functions for generic gitweb actions and views */ + +/** + * used to check if link has 'js' query parameter already (at end), + * and other reasons to not add 'js=1' param at the end of link + * @constant + */ +var jsExceptionsRe = /[;?]js=[01]$/; + +/** + * Add '?js=1' or ';js=1' to the end of every link in the document + * that doesn't have 'js' query parameter set already. + * + * Links with 'js=1' lead to JavaScript version of given action, if it + * exists (currently there is only 'blame_incremental' for 'blame') + * + * @globals jsExceptionsRe + */ +function fixLinks() { + var allLinks = document.getElementsByTagName("a") || document.links; + for (var i = 0, len = allLinks.length; i < len; i++) { + var link = allLinks[i]; + if (!jsExceptionsRe.test(link)) { // =~ /[;?]js=[01]$/; + link.href += + (link.href.indexOf('?') === -1 ? '?' : ';') + 'js=1'; + } + } +} + + +/* ============================================================ */ + +/* + * This code uses DOM methods instead of (nonstandard) innerHTML + * to modify page. + * + * innerHTML is non-standard IE extension, though supported by most + * browsers; however Firefox up to version 1.5 didn't implement it in + * a strict mode (application/xml+xhtml mimetype). + * + * Also my simple benchmarks show that using elem.firstChild.data = + * 'content' is slightly faster than elem.innerHTML = 'content'. It + * is however more fragile (text element fragment must exists), and + * less feature-rich (we cannot add HTML). + * + * Note that DOM 2 HTML is preferred over generic DOM 2 Core; the + * equivalent using DOM 2 Core is usually shown in comments. + */ + + +/* ============================================================ */ +/* generic utility functions */ + + +/** + * pad number N with nonbreakable spaces on the left, to WIDTH characters + * example: padLeftStr(12, 3, '\u00A0') == '\u00A012' + * ('\u00A0' is nonbreakable space) + * + * @param {Number|String} input: number to pad + * @param {Number} width: visible width of output + * @param {String} str: string to prefix to string, e.g. '\u00A0' + * @returns {String} INPUT prefixed with (WIDTH - INPUT.length) x STR + */ +function padLeftStr(input, width, str) { + var prefix = ''; + + width -= input.toString().length; + while (width > 0) { + prefix += str; + width--; + } + return prefix + input; +} + +/** + * Pad INPUT on the left to SIZE width, using given padding character CH, + * for example padLeft('a', 3, '_') is '__a'. + * + * @param {String} input: input value converted to string. + * @param {Number} width: desired length of output. + * @param {String} ch: single character to prefix to string. + * + * @returns {String} Modified string, at least SIZE length. + */ +function padLeft(input, width, ch) { + var s = input + ""; + while (s.length < width) { + s = ch + s; + } + return s; +} + +/** + * Create XMLHttpRequest object in cross-browser way + * @returns XMLHttpRequest object, or null + */ +function createRequestObject() { + try { + return new XMLHttpRequest(); + } catch (e) {} + try { + return window.createRequest(); + } catch (e) {} + try { + return new ActiveXObject("Msxml2.XMLHTTP"); + } catch (e) {} + try { + return new ActiveXObject("Microsoft.XMLHTTP"); + } catch (e) {} + + return null; +} + + +/* ============================================================ */ +/* utility/helper functions (and variables) */ + +var xhr; // XMLHttpRequest object +var projectUrl; // partial query + separator ('?' or ';') + +// 'commits' is an associative map. It maps SHA1s to Commit objects. +var commits = {}; + +/** + * constructor for Commit objects, used in 'blame' + * @class Represents a blamed commit + * @param {String} sha1: SHA-1 identifier of a commit + */ +function Commit(sha1) { + if (this instanceof Commit) { + this.sha1 = sha1; + this.nprevious = 0; /* number of 'previous', effective parents */ + } else { + return new Commit(sha1); + } +} + +/* ............................................................ */ +/* progress info, timing, error reporting */ + +var blamedLines = 0; +var totalLines = '???'; +var div_progress_bar; +var div_progress_info; + +/** + * Detects how many lines does a blamed file have, + * This information is used in progress info + * + * @returns {Number|String} Number of lines in file, or string '...' + */ +function countLines() { + var table = + document.getElementById('blame_table') || + document.getElementsByTagName('table')[0]; + + if (table) { + return table.getElementsByTagName('tr').length - 1; // for header + } else { + return '...'; + } +} + +/** + * update progress info and length (width) of progress bar + * + * @globals div_progress_info, div_progress_bar, blamedLines, totalLines + */ +function updateProgressInfo() { + if (!div_progress_info) { + div_progress_info = document.getElementById('progress_info'); + } + if (!div_progress_bar) { + div_progress_bar = document.getElementById('progress_bar'); + } + if (!div_progress_info && !div_progress_bar) { + return; + } + + var percentage = Math.floor(100.0*blamedLines/totalLines); + + if (div_progress_info) { + div_progress_info.firstChild.data = blamedLines + ' / ' + totalLines + + ' (' + padLeftStr(percentage, 3, '\u00A0') + '%)'; + } + + if (div_progress_bar) { + //div_progress_bar.setAttribute('style', 'width: '+percentage+'%;'); + div_progress_bar.style.width = percentage + '%'; + } +} + + +var t_interval_server = ''; +var cmds_server = ''; +var t0 = new Date(); + +/** + * write how much it took to generate data, and to run script + * + * @globals t0, t_interval_server, cmds_server + */ +function writeTimeInterval() { + var info_time = document.getElementById('generating_time'); + if (!info_time || !t_interval_server) { + return; + } + var t1 = new Date(); + info_time.firstChild.data += ' + (' + + t_interval_server + ' sec server blame_data / ' + + (t1.getTime() - t0.getTime())/1000 + ' sec client JavaScript)'; + + var info_cmds = document.getElementById('generating_cmd'); + if (!info_time || !cmds_server) { + return; + } + info_cmds.firstChild.data += ' + ' + cmds_server; +} + +/** + * show an error message alert to user within page (in prohress info area) + * @param {String} str: plain text error message (no HTML) + * + * @globals div_progress_info + */ +function errorInfo(str) { + if (!div_progress_info) { + div_progress_info = document.getElementById('progress_info'); + } + if (div_progress_info) { + div_progress_info.className = 'error'; + div_progress_info.firstChild.data = str; + } +} + +/* ............................................................ */ +/* coloring rows during blame_data (git blame --incremental) run */ + +/** + * used to extract N from 'colorN', where N is a number, + * @constant + */ +var colorRe = /\bcolor([0-9]*)\b/; + +/** + * return N if <tr class="colorN">, otherwise return null + * (some browsers require CSS class names to begin with letter) + * + * @param {HTMLElement} tr: table row element to check + * @param {String} tr.className: 'class' attribute of tr element + * @returns {Number|null} N if tr.className == 'colorN', otherwise null + * + * @globals colorRe + */ +function getColorNo(tr) { + if (!tr) { + return null; + } + var className = tr.className; + if (className) { + var match = colorRe.exec(className); + if (match) { + return parseInt(match[1], 10); + } + } + return null; +} + +var colorsFreq = [0, 0, 0]; +/** + * return one of given possible colors (curently least used one) + * example: chooseColorNoFrom(2, 3) returns 2 or 3 + * + * @param {Number[]} arguments: one or more numbers + * assumes that 1 <= arguments[i] <= colorsFreq.length + * @returns {Number} Least used color number from arguments + * @globals colorsFreq + */ +function chooseColorNoFrom() { + // choose the color which is least used + var colorNo = arguments[0]; + for (var i = 1; i < arguments.length; i++) { + if (colorsFreq[arguments[i]-1] < colorsFreq[colorNo-1]) { + colorNo = arguments[i]; + } + } + colorsFreq[colorNo-1]++; + return colorNo; +} + +/** + * given two neigbour <tr> elements, find color which would be different + * from color of both of neighbours; used to 3-color blame table + * + * @param {HTMLElement} tr_prev + * @param {HTMLElement} tr_next + * @returns {Number} color number N such that + * colorN != tr_prev.className && colorN != tr_next.className + */ +function findColorNo(tr_prev, tr_next) { + var color_prev = getColorNo(tr_prev); + var color_next = getColorNo(tr_next); + + + // neither of neighbours has color set + // THEN we can use any of 3 possible colors + if (!color_prev && !color_next) { + return chooseColorNoFrom(1,2,3); + } + + // either both neighbours have the same color, + // or only one of neighbours have color set + // THEN we can use any color except given + var color; + if (color_prev === color_next) { + color = color_prev; // = color_next; + } else if (!color_prev) { + color = color_next; + } else if (!color_next) { + color = color_prev; + } + if (color) { + return chooseColorNoFrom((color % 3) + 1, ((color+1) % 3) + 1); + } + + // neighbours have different colors + // THEN there is only one color left + return (3 - ((color_prev + color_next) % 3)); +} + +/* ............................................................ */ +/* coloring rows like 'blame' after 'blame_data' finishes */ + +/** + * returns true if given row element (tr) is first in commit group + * to be used only after 'blame_data' finishes (after processing) + * + * @param {HTMLElement} tr: table row + * @returns {Boolean} true if TR is first in commit group + */ +function isStartOfGroup(tr) { + return tr.firstChild.className === 'sha1'; +} + +/** + * change colors to use zebra coloring (2 colors) instead of 3 colors + * concatenate neighbour commit groups belonging to the same commit + * + * @globals colorRe + */ +function fixColorsAndGroups() { + var colorClasses = ['light', 'dark']; + var linenum = 1; + var tr, prev_group; + var colorClass = 0; + var table = + document.getElementById('blame_table') || + document.getElementsByTagName('table')[0]; + + while ((tr = document.getElementById('l'+linenum))) { + // index origin is 0, which is table header; start from 1 + //while ((tr = table.rows[linenum])) { // <- it is slower + if (isStartOfGroup(tr, linenum, document)) { + if (prev_group && + prev_group.firstChild.firstChild.href === + tr.firstChild.firstChild.href) { + // we have to concatenate groups + var prev_rows = prev_group.firstChild.rowSpan || 1; + var curr_rows = tr.firstChild.rowSpan || 1; + prev_group.firstChild.rowSpan = prev_rows + curr_rows; + //tr.removeChild(tr.firstChild); + tr.deleteCell(0); // DOM2 HTML way + } else { + colorClass = (colorClass + 1) % 2; + prev_group = tr; + } + } + var tr_class = tr.className; + tr.className = tr_class.replace(colorRe, colorClasses[colorClass]); + linenum++; + } +} + +/* ............................................................ */ +/* time and data */ + +/** + * used to extract hours and minutes from timezone info, e.g '-0900' + * @constant + */ +var tzRe = /^([+-][0-9][0-9])([0-9][0-9])$/; + +/** + * return date in local time formatted in iso-8601 like format + * 'yyyy-mm-dd HH:MM:SS +/-ZZZZ' e.g. '2005-08-07 21:49:46 +0200' + * + * @param {Number} epoch: seconds since '00:00:00 1970-01-01 UTC' + * @param {String} timezoneInfo: numeric timezone '(+|-)HHMM' + * @returns {String} date in local time in iso-8601 like format + * + * @globals tzRe + */ +function formatDateISOLocal(epoch, timezoneInfo) { + var match = tzRe.exec(timezoneInfo); + // date corrected by timezone + var localDate = new Date(1000 * (epoch + + (parseInt(match[1],10)*3600 + parseInt(match[2],10)*60))); + var localDateStr = // e.g. '2005-08-07' + localDate.getUTCFullYear() + '-' + + padLeft(localDate.getUTCMonth()+1, 2, '0') + '-' + + padLeft(localDate.getUTCDate(), 2, '0'); + var localTimeStr = // e.g. '21:49:46' + padLeft(localDate.getUTCHours(), 2, '0') + ':' + + padLeft(localDate.getUTCMinutes(), 2, '0') + ':' + + padLeft(localDate.getUTCSeconds(), 2, '0'); + + return localDateStr + ' ' + localTimeStr + ' ' + timezoneInfo; +} + +/* ............................................................ */ +/* unquoting/unescaping filenames */ + +/**#@+ + * @constant + */ +var escCodeRe = /\\([^0-7]|[0-7]{1,3})/g; +var octEscRe = /^[0-7]{1,3}$/; +var maybeQuotedRe = /^\"(.*)\"$/; +/**#@-*/ + +/** + * unquote maybe git-quoted filename + * e.g. 'aa' -> 'aa', '"a\ta"' -> 'a a' + * + * @param {String} str: git-quoted string + * @returns {String} Unquoted and unescaped string + * + * @globals escCodeRe, octEscRe, maybeQuotedRe + */ +function unquote(str) { + function unq(seq) { + var es = { + // character escape codes, aka escape sequences (from C) + // replacements are to some extent JavaScript specific + t: "\t", // tab (HT, TAB) + n: "\n", // newline (NL) + r: "\r", // return (CR) + f: "\f", // form feed (FF) + b: "\b", // backspace (BS) + a: "\x07", // alarm (bell) (BEL) + e: "\x1B", // escape (ESC) + v: "\v" // vertical tab (VT) + }; + + if (seq.search(octEscRe) !== -1) { + // octal char sequence + return String.fromCharCode(parseInt(seq, 8)); + } else if (seq in es) { + // C escape sequence, aka character escape code + return es[seq]; + } + // quoted ordinary character + return seq; + } + + var match = str.match(maybeQuotedRe); + if (match) { + str = match[1]; + // perhaps str = eval('"'+str+'"'); would be enough? + str = str.replace(escCodeRe, + function (substr, p1, offset, s) { return unq(p1); }); + } + return str; +} + +/* ============================================================ */ +/* main part: parsing response */ + +/** + * Function called for each blame entry, as soon as it finishes. + * It updates page via DOM manipulation, adding sha1 info, etc. + * + * @param {Commit} commit: blamed commit + * @param {Object} group: object representing group of lines, + * which blame the same commit (blame entry) + * + * @globals blamedLines + */ +function handleLine(commit, group) { + /* + This is the structure of the HTML fragment we are working + with: + + <tr id="l123" class=""> + <td class="sha1" title=""><a href=""> </a></td> + <td class="linenr"><a class="linenr" href="">123</a></td> + <td class="pre"># times (my ext3 doesn't).</td> + </tr> + */ + + var resline = group.resline; + + // format date and time string only once per commit + if (!commit.info) { + /* e.g. 'Kay Sievers, 2005-08-07 21:49:46 +0200' */ + commit.info = commit.author + ', ' + + formatDateISOLocal(commit.authorTime, commit.authorTimezone); + } + + // color depends on group of lines, not only on blamed commit + var colorNo = findColorNo( + document.getElementById('l'+(resline-1)), + document.getElementById('l'+(resline+group.numlines)) + ); + + // loop over lines in commit group + for (var i = 0; i < group.numlines; i++, resline++) { + var tr = document.getElementById('l'+resline); + if (!tr) { + break; + } + /* + <tr id="l123" class=""> + <td class="sha1" title=""><a href=""> </a></td> + <td class="linenr"><a class="linenr" href="">123</a></td> + <td class="pre"># times (my ext3 doesn't).</td> + </tr> + */ + var td_sha1 = tr.firstChild; + var a_sha1 = td_sha1.firstChild; + var a_linenr = td_sha1.nextSibling.firstChild; + + /* <tr id="l123" class=""> */ + var tr_class = ''; + if (colorNo !== null) { + tr_class = 'color'+colorNo; + } + if (commit.boundary) { + tr_class += ' boundary'; + } + if (commit.nprevious === 0) { + tr_class += ' no-previous'; + } else if (commit.nprevious > 1) { + tr_class += ' multiple-previous'; + } + tr.className = tr_class; + + /* <td class="sha1" title="?" rowspan="?"><a href="?">?</a></td> */ + if (i === 0) { + td_sha1.title = commit.info; + td_sha1.rowSpan = group.numlines; + + a_sha1.href = projectUrl + 'a=commit;h=' + commit.sha1; + if (a_sha1.firstChild) { + a_sha1.firstChild.data = commit.sha1.substr(0, 8); + } else { + a_sha1.appendChild( + document.createTextNode(commit.sha1.substr(0, 8))); + } + if (group.numlines >= 2) { + var fragment = document.createDocumentFragment(); + var br = document.createElement("br"); + var match = commit.author.match(/\b([A-Z])\B/g); + if (match) { + var text = document.createTextNode( + match.join('')); + } + if (br && text) { + var elem = fragment || td_sha1; + elem.appendChild(br); + elem.appendChild(text); + if (fragment) { + td_sha1.appendChild(fragment); + } + } + } + } else { + //tr.removeChild(td_sha1); // DOM2 Core way + tr.deleteCell(0); // DOM2 HTML way + } + + /* <td class="linenr"><a class="linenr" href="?">123</a></td> */ + var linenr_commit = + ('previous' in commit ? commit.previous : commit.sha1); + var linenr_filename = + ('file_parent' in commit ? commit.file_parent : commit.filename); + a_linenr.href = projectUrl + 'a=blame_incremental' + + ';hb=' + linenr_commit + + ';f=' + encodeURIComponent(linenr_filename) + + '#l' + (group.srcline + i); + + blamedLines++; + + //updateProgressInfo(); + } +} + +// ---------------------------------------------------------------------- + +var inProgress = false; // are we processing response + +/**#@+ + * @constant + */ +var sha1Re = /^([0-9a-f]{40}) ([0-9]+) ([0-9]+) ([0-9]+)/; +var infoRe = /^([a-z-]+) ?(.*)/; +var endRe = /^END ?([^ ]*) ?(.*)/; +/**@-*/ + +var curCommit = new Commit(); +var curGroup = {}; + +var pollTimer = null; + +/** + * Parse output from 'git blame --incremental [...]', received via + * XMLHttpRequest from server (blamedataUrl), and call handleLine + * (which updates page) as soon as blame entry is completed. + * + * @param {String[]} lines: new complete lines from blamedata server + * + * @globals commits, curCommit, curGroup, t_interval_server, cmds_server + * @globals sha1Re, infoRe, endRe + */ +function processBlameLines(lines) { + var match; + + for (var i = 0, len = lines.length; i < len; i++) { + + if ((match = sha1Re.exec(lines[i]))) { + var sha1 = match[1]; + var srcline = parseInt(match[2], 10); + var resline = parseInt(match[3], 10); + var numlines = parseInt(match[4], 10); + + var c = commits[sha1]; + if (!c) { + c = new Commit(sha1); + commits[sha1] = c; + } + curCommit = c; + + curGroup.srcline = srcline; + curGroup.resline = resline; + curGroup.numlines = numlines; + + } else if ((match = infoRe.exec(lines[i]))) { + var info = match[1]; + var data = match[2]; + switch (info) { + case 'filename': + curCommit.filename = unquote(data); + // 'filename' information terminates the entry + handleLine(curCommit, curGroup); + updateProgressInfo(); + break; + case 'author': + curCommit.author = data; + break; + case 'author-time': + curCommit.authorTime = parseInt(data, 10); + break; + case 'author-tz': + curCommit.authorTimezone = data; + break; + case 'previous': + curCommit.nprevious++; + // store only first 'previous' header + if (!'previous' in curCommit) { + var parts = data.split(' ', 2); + curCommit.previous = parts[0]; + curCommit.file_parent = unquote(parts[1]); + } + break; + case 'boundary': + curCommit.boundary = true; + break; + } // end switch + + } else if ((match = endRe.exec(lines[i]))) { + t_interval_server = match[1]; + cmds_server = match[2]; + + } else if (lines[i] !== '') { + // malformed line + + } // end if (match) + + } // end for (lines) +} + +/** + * Process new data and return pointer to end of processed part + * + * @param {String} unprocessed: new data (from nextReadPos) + * @param {Number} nextReadPos: end of last processed data + * @return {Number} end of processed data (new value for nextReadPos) + */ +function processData(unprocessed, nextReadPos) { + var lastLineEnd = unprocessed.lastIndexOf('\n'); + if (lastLineEnd !== -1) { + var lines = unprocessed.substring(0, lastLineEnd).split('\n'); + nextReadPos += lastLineEnd + 1 /* 1 == '\n'.length */; + + processBlameLines(lines); + } // end if + + return nextReadPos; +} + +/** + * Handle XMLHttpRequest errors + * + * @param {XMLHttpRequest} xhr: XMLHttpRequest object + * + * @globals pollTimer, commits, inProgress + */ +function handleError(xhr) { + errorInfo('Server error: ' + + xhr.status + ' - ' + (xhr.statusText || 'Error contacting server')); + + clearInterval(pollTimer); + commits = {}; // free memory + + inProgress = false; +} + +/** + * Called after XMLHttpRequest finishes (loads) + * + * @param {XMLHttpRequest} xhr: XMLHttpRequest object (unused) + * + * @globals pollTimer, commits, inProgress + */ +function responseLoaded(xhr) { + clearInterval(pollTimer); + + fixColorsAndGroups(); + writeTimeInterval(); + commits = {}; // free memory + + inProgress = false; +} + +/** + * handler for XMLHttpRequest onreadystatechange event + * @see startBlame + * + * @globals xhr, inProgress + */ +function handleResponse() { + + /* + * xhr.readyState + * + * Value Constant (W3C) Description + * ------------------------------------------------------------------- + * 0 UNSENT open() has not been called yet. + * 1 OPENED send() has not been called yet. + * 2 HEADERS_RECEIVED send() has been called, and headers + * and status are available. + * 3 LOADING Downloading; responseText holds partial data. + * 4 DONE The operation is complete. + */ + + if (xhr.readyState !== 4 && xhr.readyState !== 3) { + return; + } + + // the server returned error + // try ... catch block is to work around bug in IE8 + try { + if (xhr.readyState === 3 && xhr.status !== 200) { + return; + } + } catch (e) { + return; + } + if (xhr.readyState === 4 && xhr.status !== 200) { + handleError(xhr); + return; + } + + // In konqueror xhr.responseText is sometimes null here... + if (xhr.responseText === null) { + return; + } + + // in case we were called before finished processing + if (inProgress) { + return; + } else { + inProgress = true; + } + + // extract new whole (complete) lines, and process them + while (xhr.prevDataLength !== xhr.responseText.length) { + if (xhr.readyState === 4 && + xhr.prevDataLength === xhr.responseText.length) { + break; + } + + xhr.prevDataLength = xhr.responseText.length; + var unprocessed = xhr.responseText.substring(xhr.nextReadPos); + xhr.nextReadPos = processData(unprocessed, xhr.nextReadPos); + } // end while + + // did we finish work? + if (xhr.readyState === 4 && + xhr.prevDataLength === xhr.responseText.length) { + responseLoaded(xhr); + } + + inProgress = false; +} + +// ============================================================ +// ------------------------------------------------------------ + +/** + * Incrementally update line data in blame_incremental view in gitweb. + * + * @param {String} blamedataUrl: URL to server script generating blame data. + * @param {String} bUrl: partial URL to project, used to generate links. + * + * Called from 'blame_incremental' view after loading table with + * file contents, a base for blame view. + * + * @globals xhr, t0, projectUrl, div_progress_bar, totalLines, pollTimer +*/ +function startBlame(blamedataUrl, bUrl) { + + xhr = createRequestObject(); + if (!xhr) { + errorInfo('ERROR: XMLHttpRequest not supported'); + return; + } + + t0 = new Date(); + projectUrl = bUrl + (bUrl.indexOf('?') === -1 ? '?' : ';'); + if ((div_progress_bar = document.getElementById('progress_bar'))) { + //div_progress_bar.setAttribute('style', 'width: 100%;'); + div_progress_bar.style.cssText = 'width: 100%;'; + } + totalLines = countLines(); + updateProgressInfo(); + + /* add extra properties to xhr object to help processing response */ + xhr.prevDataLength = -1; // used to detect if we have new data + xhr.nextReadPos = 0; // where unread part of response starts + + xhr.onreadystatechange = handleResponse; + //xhr.onreadystatechange = function () { handleResponse(xhr); }; + + xhr.open('GET', blamedataUrl); + xhr.setRequestHeader('Accept', 'text/plain'); + xhr.send(null); + + // not all browsers call onreadystatechange event on each server flush + // poll response using timer every second to handle this issue + pollTimer = setInterval(xhr.onreadystatechange, 1000); +} + +// end of gitweb.js diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl index b606c1d3e7..9d4c58238e 100755 --- a/gitweb/gitweb.perl +++ b/gitweb/gitweb.perl @@ -18,8 +18,14 @@ use File::Find qw(); use File::Basename qw(basename); binmode STDOUT, ':utf8'; +our $t0; +if (eval { require Time::HiRes; 1; }) { + $t0 = [Time::HiRes::gettimeofday()]; +} +our $number_of_git_cmds = 0; + BEGIN { - CGI->compile() if $ENV{MOD_PERL}; + CGI->compile() if $ENV{'MOD_PERL'}; } our $cgi = new CGI; @@ -27,6 +33,31 @@ our $version = "++GIT_VERSION++"; our $my_url = $cgi->url(); our $my_uri = $cgi->url(-absolute => 1); +# Base URL for relative URLs in gitweb ($logo, $favicon, ...), +# needed and used only for URLs with nonempty PATH_INFO +our $base_url = $my_url; + +# When the script is used as DirectoryIndex, the URL does not contain the name +# of the script file itself, and $cgi->url() fails to strip PATH_INFO, so we +# have to do it ourselves. We make $path_info global because it's also used +# later on. +# +# Another issue with the script being the DirectoryIndex is that the resulting +# $my_url data is not the full script URL: this is good, because we want +# generated links to keep implying the script name if it wasn't explicitly +# indicated in the URL we're handling, but it means that $my_url cannot be used +# as base URL. +# Therefore, if we needed to strip PATH_INFO, then we know that we have +# to build the base URL ourselves: +our $path_info = $ENV{"PATH_INFO"}; +if ($path_info) { + if ($my_url =~ s,\Q$path_info\E$,, && + $my_uri =~ s,\Q$path_info\E$,, && + defined $ENV{'SCRIPT_NAME'}) { + $base_url = $cgi->url(-base => 1) . $ENV{'SCRIPT_NAME'}; + } +} + # core git executable to use # this can just be "git" if your webserver has a sensible PATH our $GIT = "++GIT_BINDIR++/git"; @@ -35,6 +66,10 @@ our $GIT = "++GIT_BINDIR++/git"; #our $projectroot = "/pub/scm"; our $projectroot = "++GITWEB_PROJECTROOT++"; +# fs traversing limit for getting project list +# the number is relative to the projectroot +our $project_maxdepth = "++GITWEB_PROJECT_MAXDEPTH++"; + # target of the home link on top of all pages our $home_link = $my_uri || "/"; @@ -61,20 +96,34 @@ our $stylesheet = undef; our $logo = "++GITWEB_LOGO++"; # URI of GIT favicon, assumed to be image/png type our $favicon = "++GITWEB_FAVICON++"; +# URI of gitweb.js (JavaScript code for gitweb) +our $javascript = "++GITWEB_JS++"; # URI and label (title) of GIT logo link #our $logo_url = "http://www.kernel.org/pub/software/scm/git/docs/"; #our $logo_label = "git documentation"; -our $logo_url = "http://git.or.cz/"; +our $logo_url = "http://git-scm.com/"; our $logo_label = "git homepage"; # source of projects list our $projects_list = "++GITWEB_LIST++"; +# the width (in characters) of the projects list "Description" column +our $projects_list_description_width = 25; + +# default order of projects list +# valid values are none, project, descr, owner, and age +our $default_projects_order = "project"; + # show repository only if this file exists # (only effective if this variable evaluates to true) our $export_ok = "++GITWEB_EXPORT_OK++"; +# show repository only if this subroutine returns true +# when given the path to the project, for example: +# sub { return -e "$_[0]/git-daemon-export-ok"; } +our $export_auth_hook = undef; + # only allow viewing of repositories also shown on the overview page our $strict_export = "++GITWEB_STRICT_EXPORT++"; @@ -90,6 +139,94 @@ our $default_text_plain_charset = undef; # (relative to the current git repository) our $mimetypes_file = undef; +# assume this charset if line contains non-UTF-8 characters; +# it should be valid encoding (see Encoding::Supported(3pm) for list), +# for which encoding all byte sequences are valid, for example +# 'iso-8859-1' aka 'latin1' (it is decoded without checking, so it +# could be even 'utf-8' for the old behavior) +our $fallback_encoding = 'latin1'; + +# rename detection options for git-diff and git-diff-tree +# - default is '-M', with the cost proportional to +# (number of removed files) * (number of new files). +# - more costly is '-C' (which implies '-M'), with the cost proportional to +# (number of changed files + number of removed files) * (number of new files) +# - even more costly is '-C', '--find-copies-harder' with cost +# (number of files in the original tree) * (number of new files) +# - one might want to include '-B' option, e.g. '-B', '-M' +our @diff_opts = ('-M'); # taken from git_commit + +# Disables features that would allow repository owners to inject script into +# the gitweb domain. +our $prevent_xss = 0; + +# information about snapshot formats that gitweb is capable of serving +our %known_snapshot_formats = ( + # name => { + # 'display' => display name, + # 'type' => mime type, + # 'suffix' => filename suffix, + # 'format' => --format for git-archive, + # 'compressor' => [compressor command and arguments] + # (array reference, optional) + # 'disabled' => boolean (optional)} + # + 'tgz' => { + 'display' => 'tar.gz', + 'type' => 'application/x-gzip', + 'suffix' => '.tar.gz', + 'format' => 'tar', + 'compressor' => ['gzip']}, + + 'tbz2' => { + 'display' => 'tar.bz2', + 'type' => 'application/x-bzip2', + 'suffix' => '.tar.bz2', + 'format' => 'tar', + 'compressor' => ['bzip2']}, + + 'txz' => { + 'display' => 'tar.xz', + 'type' => 'application/x-xz', + 'suffix' => '.tar.xz', + 'format' => 'tar', + 'compressor' => ['xz'], + 'disabled' => 1}, + + 'zip' => { + 'display' => 'zip', + 'type' => 'application/x-zip', + 'suffix' => '.zip', + 'format' => 'zip'}, +); + +# Aliases so we understand old gitweb.snapshot values in repository +# configuration. +our %known_snapshot_format_aliases = ( + 'gzip' => 'tgz', + 'bzip2' => 'tbz2', + 'xz' => 'txz', + + # backward compatibility: legacy gitweb config support + 'x-gzip' => undef, 'gz' => undef, + 'x-bzip2' => undef, 'bz2' => undef, + 'x-zip' => undef, '' => undef, +); + +# Pixel sizes for icons and avatars. If the default font sizes or lineheights +# are changed, it may be appropriate to change these values too via +# $GITWEB_CONFIG. +our %avatar_size = ( + 'default' => 16, + 'double' => 32 +); + +# Used to set the maximum load that we will still respond to gitweb queries. +# If server load exceed this value then return "503 server busy" error. +# If gitweb cannot determined server load, it is taken to be 0. +# Leave it undefined (or set to 'undef') to turn off load checking. +our $maxload = 300; + # You define site-wide feature defaults here; override them with # $GITWEB_CONFIG as necessary. our %feature = ( @@ -98,11 +235,16 @@ our %feature = ( # 'override' => allow-override (boolean), # 'default' => [ default options...] (array reference)} # - # if feature is overridable (it means that allow-override has true value, + # if feature is overridable (it means that allow-override has true value), # then feature-sub will be called with default options as parameters; # return value of feature-sub indicates if to enable specified feature # - # use gitweb_check_feature(<feature>) to check if <feature> is enabled + # if there is no 'sub' key (no feature-sub), then feature cannot be + # overriden + # + # use gitweb_get_feature(<feature>) to retrieve the <feature> value + # (an array) or gitweb_check_feature(<feature>) to check if <feature> + # is enabled # Enable the 'blame' blob view, showing the last commit that modified # each line in the file. This can be very CPU-intensive. @@ -113,31 +255,48 @@ our %feature = ( # $feature{'blame'}{'override'} = 1; # and in project config gitweb.blame = 0|1; 'blame' => { - 'sub' => \&feature_blame, + 'sub' => sub { feature_bool('blame', @_) }, 'override' => 0, 'default' => [0]}, - # Enable the 'snapshot' link, providing a compressed tarball of any + # Enable the 'snapshot' link, providing a compressed archive of any # tree. This can potentially generate high traffic if you have large # project. + # Value is a list of formats defined in %known_snapshot_formats that + # you wish to offer. # To disable system wide have in $GITWEB_CONFIG - # $feature{'snapshot'}{'default'} = [undef]; + # $feature{'snapshot'}{'default'} = []; # To have project specific config enable override in $GITWEB_CONFIG # $feature{'snapshot'}{'override'} = 1; - # and in project config gitweb.snapshot = none|gzip|bzip2; + # and in project config, a comma-separated list of formats or "none" + # to disable. Example: gitweb.snapshot = tbz2,zip; 'snapshot' => { 'sub' => \&feature_snapshot, 'override' => 0, - # => [content-encoding, suffix, program] - 'default' => ['x-gzip', 'gz', 'gzip']}, + 'default' => ['tgz']}, # Enable text search, which will list the commits which match author, # committer or commit text to a given string. Enabled by default. + # Project specific override is not supported. 'search' => { 'override' => 0, 'default' => [1]}, + # Enable grep search, which will list the files in currently selected + # tree containing the given string. Enabled by default. This can be + # potentially CPU-intensive, of course. + + # To enable system wide have in $GITWEB_CONFIG + # $feature{'grep'}{'default'} = [1]; + # To have project specific config enable override in $GITWEB_CONFIG + # $feature{'grep'}{'override'} = 1; + # and in project config gitweb.grep = 0|1; + 'grep' => { + 'sub' => sub { feature_bool('grep', @_) }, + 'override' => 0, + 'default' => [1]}, + # Enable the pickaxe search, which will list the commits that modified # a given string in a file. This can be practical and quite faster # alternative to 'blame', but still potentially CPU-intensive. @@ -148,7 +307,20 @@ our %feature = ( # $feature{'pickaxe'}{'override'} = 1; # and in project config gitweb.pickaxe = 0|1; 'pickaxe' => { - 'sub' => \&feature_pickaxe, + 'sub' => sub { feature_bool('pickaxe', @_) }, + 'override' => 0, + 'default' => [1]}, + + # Enable showing size of blobs in a 'tree' view, in a separate + # column, similar to what 'ls -l' does. This cost a bit of IO. + + # To disable system wide have in $GITWEB_CONFIG + # $feature{'show-sizes'}{'default'} = [0]; + # To have project specific config enable override in $GITWEB_CONFIG + # $feature{'show-sizes'}{'override'} = 1; + # and in project config gitweb.showsizes = 0|1; + 'show-sizes' => { + 'sub' => sub { feature_bool('showsizes', @_) }, 'override' => 0, 'default' => [1]}, @@ -176,8 +348,8 @@ our %feature = ( # projects matching $projname/*.git will not be shown in the main # projects list, instead a '+' mark will be added to $projname # there and a 'forks' view will be enabled for the project, listing - # all the forks. This feature is supported only if project list - # is taken from a directory, not file. + # all the forks. If project list is taken from a file, forks have + # to be listed after the main project. # To enable system wide have in $GITWEB_CONFIG # $feature{'forks'}{'default'} = [1]; @@ -185,70 +357,172 @@ our %feature = ( 'forks' => { 'override' => 0, 'default' => [0]}, + + # Insert custom links to the action bar of all project pages. + # This enables you mainly to link to third-party scripts integrating + # into gitweb; e.g. git-browser for graphical history representation + # or custom web-based repository administration interface. + + # The 'default' value consists of a list of triplets in the form + # (label, link, position) where position is the label after which + # to insert the link and link is a format string where %n expands + # to the project name, %f to the project path within the filesystem, + # %h to the current hash (h gitweb parameter) and %b to the current + # hash base (hb gitweb parameter); %% expands to %. + + # To enable system wide have in $GITWEB_CONFIG e.g. + # $feature{'actions'}{'default'} = [('graphiclog', + # '/git-browser/by-commit.html?r=%n', 'summary')]; + # Project specific override is not supported. + 'actions' => { + 'override' => 0, + 'default' => []}, + + # Allow gitweb scan project content tags described in ctags/ + # of project repository, and display the popular Web 2.0-ish + # "tag cloud" near the project list. Note that this is something + # COMPLETELY different from the normal Git tags. + + # gitweb by itself can show existing tags, but it does not handle + # tagging itself; you need an external application for that. + # For an example script, check Girocco's cgi/tagproj.cgi. + # You may want to install the HTML::TagCloud Perl module to get + # a pretty tag cloud instead of just a list of tags. + + # To enable system wide have in $GITWEB_CONFIG + # $feature{'ctags'}{'default'} = ['path_to_tag_script']; + # Project specific override is not supported. + 'ctags' => { + 'override' => 0, + 'default' => [0]}, + + # The maximum number of patches in a patchset generated in patch + # view. Set this to 0 or undef to disable patch view, or to a + # negative number to remove any limit. + + # To disable system wide have in $GITWEB_CONFIG + # $feature{'patches'}{'default'} = [0]; + # To have project specific config enable override in $GITWEB_CONFIG + # $feature{'patches'}{'override'} = 1; + # and in project config gitweb.patches = 0|n; + # where n is the maximum number of patches allowed in a patchset. + 'patches' => { + 'sub' => \&feature_patches, + 'override' => 0, + 'default' => [16]}, + + # Avatar support. When this feature is enabled, views such as + # shortlog or commit will display an avatar associated with + # the email of the committer(s) and/or author(s). + + # Currently available providers are gravatar and picon. + # If an unknown provider is specified, the feature is disabled. + + # Gravatar depends on Digest::MD5. + # Picon currently relies on the indiana.edu database. + + # To enable system wide have in $GITWEB_CONFIG + # $feature{'avatar'}{'default'} = ['<provider>']; + # where <provider> is either gravatar or picon. + # To have project specific config enable override in $GITWEB_CONFIG + # $feature{'avatar'}{'override'} = 1; + # and in project config gitweb.avatar = <provider>; + 'avatar' => { + 'sub' => \&feature_avatar, + 'override' => 0, + 'default' => ['']}, + + # Enable displaying how much time and how many git commands + # it took to generate and display page. Disabled by default. + # Project specific override is not supported. + 'timed' => { + 'override' => 0, + 'default' => [0]}, + + # Enable turning some links into links to actions which require + # JavaScript to run (like 'blame_incremental'). Not enabled by + # default. Project specific override is currently not supported. + 'javascript-actions' => { + 'override' => 0, + 'default' => [0]}, ); -sub gitweb_check_feature { +sub gitweb_get_feature { my ($name) = @_; return unless exists $feature{$name}; my ($sub, $override, @defaults) = ( $feature{$name}{'sub'}, $feature{$name}{'override'}, @{$feature{$name}{'default'}}); - if (!$override) { return @defaults; } + # project specific override is possible only if we have project + our $git_dir; # global variable, declared later + if (!$override || !defined $git_dir) { + return @defaults; + } if (!defined $sub) { - warn "feature $name is not overrideable"; + warn "feature $name is not overridable"; return @defaults; } return $sub->(@defaults); } -sub feature_blame { - my ($val) = git_get_project_config('blame', '--bool'); +# A wrapper to check if a given feature is enabled. +# With this, you can say +# +# my $bool_feat = gitweb_check_feature('bool_feat'); +# gitweb_check_feature('bool_feat') or somecode; +# +# instead of +# +# my ($bool_feat) = gitweb_get_feature('bool_feat'); +# (gitweb_get_feature('bool_feat'))[0] or somecode; +# +sub gitweb_check_feature { + return (gitweb_get_feature(@_))[0]; +} + + +sub feature_bool { + my $key = shift; + my ($val) = git_get_project_config($key, '--bool'); - if ($val eq 'true') { - return 1; + if (!defined $val) { + return ($_[0]); + } elsif ($val eq 'true') { + return (1); } elsif ($val eq 'false') { - return 0; + return (0); } - - return $_[0]; } sub feature_snapshot { - my ($ctype, $suffix, $command) = @_; + my (@fmts) = @_; my ($val) = git_get_project_config('snapshot'); - if ($val eq 'gzip') { - return ('x-gzip', 'gz', 'gzip'); - } elsif ($val eq 'bzip2') { - return ('x-bzip2', 'bz2', 'bzip2'); - } elsif ($val eq 'none') { - return (); + if ($val) { + @fmts = ($val eq 'none' ? () : split /\s*[,\s]\s*/, $val); } - return ($ctype, $suffix, $command); + return @fmts; } -sub gitweb_have_snapshot { - my ($ctype, $suffix, $command) = gitweb_check_feature('snapshot'); - my $have_snapshot = (defined $ctype && defined $suffix); +sub feature_patches { + my @val = (git_get_project_config('patches', '--int')); - return $have_snapshot; -} - -sub feature_pickaxe { - my ($val) = git_get_project_config('pickaxe', '--bool'); - - if ($val eq 'true') { - return (1); - } elsif ($val eq 'false') { - return (0); + if (@val) { + return @val; } return ($_[0]); } +sub feature_avatar { + my @val = (git_get_project_config('avatar')); + + return @val ? @val : @_; +} + # checking HEAD file with -e is fragile if the repository was # initialized long time ago (i.e. symlink HEAD) and was pack-ref'ed # and then pruned. @@ -262,209 +536,440 @@ sub check_head_link { sub check_export_ok { my ($dir) = @_; return (check_head_link($dir) && - (!$export_ok || -e "$dir/$export_ok")); + (!$export_ok || -e "$dir/$export_ok") && + (!$export_auth_hook || $export_auth_hook->($dir))); } -# rename detection options for git-diff and git-diff-tree -# - default is '-M', with the cost proportional to -# (number of removed files) * (number of new files). -# - more costly is '-C' (or '-C', '-M'), with the cost proportional to -# (number of changed files + number of removed files) * (number of new files) -# - even more costly is '-C', '--find-copies-harder' with cost -# (number of files in the original tree) * (number of new files) -# - one might want to include '-B' option, e.g. '-B', '-M' -our @diff_opts = ('-M'); # taken from git_commit +# process alternate names for backward compatibility +# filter out unsupported (unknown) snapshot formats +sub filter_snapshot_fmts { + my @fmts = @_; + + @fmts = map { + exists $known_snapshot_format_aliases{$_} ? + $known_snapshot_format_aliases{$_} : $_} @fmts; + @fmts = grep { + exists $known_snapshot_formats{$_} && + !$known_snapshot_formats{$_}{'disabled'}} @fmts; +} our $GITWEB_CONFIG = $ENV{'GITWEB_CONFIG'} || "++GITWEB_CONFIG++"; -do $GITWEB_CONFIG if -e $GITWEB_CONFIG; +our $GITWEB_CONFIG_SYSTEM = $ENV{'GITWEB_CONFIG_SYSTEM'} || "++GITWEB_CONFIG_SYSTEM++"; +# die if there are errors parsing config file +if (-e $GITWEB_CONFIG) { + do $GITWEB_CONFIG; + die $@ if $@; +} elsif (-e $GITWEB_CONFIG_SYSTEM) { + do $GITWEB_CONFIG_SYSTEM; + die $@ if $@; +} + +# Get loadavg of system, to compare against $maxload. +# Currently it requires '/proc/loadavg' present to get loadavg; +# if it is not present it returns 0, which means no load checking. +sub get_loadavg { + if( -e '/proc/loadavg' ){ + open my $fd, '<', '/proc/loadavg' + or return 0; + my @load = split(/\s+/, scalar <$fd>); + close $fd; + + # The first three columns measure CPU and IO utilization of the last one, + # five, and 10 minute periods. The fourth column shows the number of + # currently running processes and the total number of processes in the m/n + # format. The last column displays the last process ID used. + return $load[0] || 0; + } + # additional checks for load average should go here for things that don't export + # /proc/loadavg + + return 0; +} # version of the core git binary -our $git_version = qx($GIT --version) =~ m/git version (.*)$/ ? $1 : "unknown"; +our $git_version = qx("$GIT" --version) =~ m/git version (.*)$/ ? $1 : "unknown"; +$number_of_git_cmds++; $projects_list ||= $projectroot; +if (defined $maxload && get_loadavg() > $maxload) { + die_error(503, "The load average on the server is too high"); +} + # ====================================================================== # input validation and dispatch -our $action = $cgi->param('a'); + +# input parameters can be collected from a variety of sources (presently, CGI +# and PATH_INFO), so we define an %input_params hash that collects them all +# together during validation: this allows subsequent uses (e.g. href()) to be +# agnostic of the parameter origin + +our %input_params = (); + +# input parameters are stored with the long parameter name as key. This will +# also be used in the href subroutine to convert parameters to their CGI +# equivalent, and since the href() usage is the most frequent one, we store +# the name -> CGI key mapping here, instead of the reverse. +# +# XXX: Warning: If you touch this, check the search form for updating, +# too. + +our @cgi_param_mapping = ( + project => "p", + action => "a", + file_name => "f", + file_parent => "fp", + hash => "h", + hash_parent => "hp", + hash_base => "hb", + hash_parent_base => "hpb", + page => "pg", + order => "o", + searchtext => "s", + searchtype => "st", + snapshot_format => "sf", + extra_options => "opt", + search_use_regexp => "sr", + # this must be last entry (for manipulation from JavaScript) + javascript => "js" +); +our %cgi_param_mapping = @cgi_param_mapping; + +# we will also need to know the possible actions, for validation +our %actions = ( + "blame" => \&git_blame, + "blame_incremental" => \&git_blame_incremental, + "blame_data" => \&git_blame_data, + "blobdiff" => \&git_blobdiff, + "blobdiff_plain" => \&git_blobdiff_plain, + "blob" => \&git_blob, + "blob_plain" => \&git_blob_plain, + "commitdiff" => \&git_commitdiff, + "commitdiff_plain" => \&git_commitdiff_plain, + "commit" => \&git_commit, + "forks" => \&git_forks, + "heads" => \&git_heads, + "history" => \&git_history, + "log" => \&git_log, + "patch" => \&git_patch, + "patches" => \&git_patches, + "rss" => \&git_rss, + "atom" => \&git_atom, + "search" => \&git_search, + "search_help" => \&git_search_help, + "shortlog" => \&git_shortlog, + "summary" => \&git_summary, + "tag" => \&git_tag, + "tags" => \&git_tags, + "tree" => \&git_tree, + "snapshot" => \&git_snapshot, + "object" => \&git_object, + # those below don't need $project + "opml" => \&git_opml, + "project_list" => \&git_project_list, + "project_index" => \&git_project_index, +); + +# finally, we have the hash of allowed extra_options for the commands that +# allow them +our %allowed_options = ( + "--no-merges" => [ qw(rss atom log shortlog history) ], +); + +# fill %input_params with the CGI parameters. All values except for 'opt' +# should be single values, but opt can be an array. We should probably +# build an array of parameters that can be multi-valued, but since for the time +# being it's only this one, we just single it out +while (my ($name, $symbol) = each %cgi_param_mapping) { + if ($symbol eq 'opt') { + $input_params{$name} = [ $cgi->param($symbol) ]; + } else { + $input_params{$name} = $cgi->param($symbol); + } +} + +# now read PATH_INFO and update the parameter list for missing parameters +sub evaluate_path_info { + return if defined $input_params{'project'}; + return if !$path_info; + $path_info =~ s,^/+,,; + return if !$path_info; + + # find which part of PATH_INFO is project + my $project = $path_info; + $project =~ s,/+$,,; + while ($project && !check_head_link("$projectroot/$project")) { + $project =~ s,/*[^/]*$,,; + } + return unless $project; + $input_params{'project'} = $project; + + # do not change any parameters if an action is given using the query string + return if $input_params{'action'}; + $path_info =~ s,^\Q$project\E/*,,; + + # next, check if we have an action + my $action = $path_info; + $action =~ s,/.*$,,; + if (exists $actions{$action}) { + $path_info =~ s,^$action/*,,; + $input_params{'action'} = $action; + } + + # list of actions that want hash_base instead of hash, but can have no + # pathname (f) parameter + my @wants_base = ( + 'tree', + 'history', + ); + + # we want to catch + # [$hash_parent_base[:$file_parent]..]$hash_parent[:$file_name] + my ($parentrefname, $parentpathname, $refname, $pathname) = + ($path_info =~ /^(?:(.+?)(?::(.+))?\.\.)?(.+?)(?::(.+))?$/); + + # first, analyze the 'current' part + if (defined $pathname) { + # we got "branch:filename" or "branch:dir/" + # we could use git_get_type(branch:pathname), but: + # - it needs $git_dir + # - it does a git() call + # - the convention of terminating directories with a slash + # makes it superfluous + # - embedding the action in the PATH_INFO would make it even + # more superfluous + $pathname =~ s,^/+,,; + if (!$pathname || substr($pathname, -1) eq "/") { + $input_params{'action'} ||= "tree"; + $pathname =~ s,/$,,; + } else { + # the default action depends on whether we had parent info + # or not + if ($parentrefname) { + $input_params{'action'} ||= "blobdiff_plain"; + } else { + $input_params{'action'} ||= "blob_plain"; + } + } + $input_params{'hash_base'} ||= $refname; + $input_params{'file_name'} ||= $pathname; + } elsif (defined $refname) { + # we got "branch". In this case we have to choose if we have to + # set hash or hash_base. + # + # Most of the actions without a pathname only want hash to be + # set, except for the ones specified in @wants_base that want + # hash_base instead. It should also be noted that hand-crafted + # links having 'history' as an action and no pathname or hash + # set will fail, but that happens regardless of PATH_INFO. + $input_params{'action'} ||= "shortlog"; + if (grep { $_ eq $input_params{'action'} } @wants_base) { + $input_params{'hash_base'} ||= $refname; + } else { + $input_params{'hash'} ||= $refname; + } + } + + # next, handle the 'parent' part, if present + if (defined $parentrefname) { + # a missing pathspec defaults to the 'current' filename, allowing e.g. + # someproject/blobdiff/oldrev..newrev:/filename + if ($parentpathname) { + $parentpathname =~ s,^/+,,; + $parentpathname =~ s,/$,,; + $input_params{'file_parent'} ||= $parentpathname; + } else { + $input_params{'file_parent'} ||= $input_params{'file_name'}; + } + # we assume that hash_parent_base is wanted if a path was specified, + # or if the action wants hash_base instead of hash + if (defined $input_params{'file_parent'} || + grep { $_ eq $input_params{'action'} } @wants_base) { + $input_params{'hash_parent_base'} ||= $parentrefname; + } else { + $input_params{'hash_parent'} ||= $parentrefname; + } + } + + # for the snapshot action, we allow URLs in the form + # $project/snapshot/$hash.ext + # where .ext determines the snapshot and gets removed from the + # passed $refname to provide the $hash. + # + # To be able to tell that $refname includes the format extension, we + # require the following two conditions to be satisfied: + # - the hash input parameter MUST have been set from the $refname part + # of the URL (i.e. they must be equal) + # - the snapshot format MUST NOT have been defined already (e.g. from + # CGI parameter sf) + # It's also useless to try any matching unless $refname has a dot, + # so we check for that too + if (defined $input_params{'action'} && + $input_params{'action'} eq 'snapshot' && + defined $refname && index($refname, '.') != -1 && + $refname eq $input_params{'hash'} && + !defined $input_params{'snapshot_format'}) { + # We loop over the known snapshot formats, checking for + # extensions. Allowed extensions are both the defined suffix + # (which includes the initial dot already) and the snapshot + # format key itself, with a prepended dot + while (my ($fmt, $opt) = each %known_snapshot_formats) { + my $hash = $refname; + unless ($hash =~ s/(\Q$opt->{'suffix'}\E|\Q.$fmt\E)$//) { + next; + } + my $sfx = $1; + # a valid suffix was found, so set the snapshot format + # and reset the hash parameter + $input_params{'snapshot_format'} = $fmt; + $input_params{'hash'} = $hash; + # we also set the format suffix to the one requested + # in the URL: this way a request for e.g. .tgz returns + # a .tgz instead of a .tar.gz + $known_snapshot_formats{$fmt}{'suffix'} = $sfx; + last; + } + } +} +evaluate_path_info(); + +our $action = $input_params{'action'}; if (defined $action) { - if ($action =~ m/[^0-9a-zA-Z\.\-_]/) { - die_error(undef, "Invalid action parameter"); + if (!validate_action($action)) { + die_error(400, "Invalid action parameter"); } } # parameters which are pathnames -our $project = $cgi->param('p'); +our $project = $input_params{'project'}; if (defined $project) { - if (!validate_pathname($project) || - !(-d "$projectroot/$project") || - !check_head_link("$projectroot/$project") || - ($export_ok && !(-e "$projectroot/$project/$export_ok")) || - ($strict_export && !project_in_list($project))) { + if (!validate_project($project)) { undef $project; - die_error(undef, "No such project"); + die_error(404, "No such project"); } } -our $file_name = $cgi->param('f'); +our $file_name = $input_params{'file_name'}; if (defined $file_name) { if (!validate_pathname($file_name)) { - die_error(undef, "Invalid file parameter"); + die_error(400, "Invalid file parameter"); } } -our $file_parent = $cgi->param('fp'); +our $file_parent = $input_params{'file_parent'}; if (defined $file_parent) { if (!validate_pathname($file_parent)) { - die_error(undef, "Invalid file parent parameter"); + die_error(400, "Invalid file parent parameter"); } } # parameters which are refnames -our $hash = $cgi->param('h'); +our $hash = $input_params{'hash'}; if (defined $hash) { if (!validate_refname($hash)) { - die_error(undef, "Invalid hash parameter"); + die_error(400, "Invalid hash parameter"); } } -our $hash_parent = $cgi->param('hp'); +our $hash_parent = $input_params{'hash_parent'}; if (defined $hash_parent) { if (!validate_refname($hash_parent)) { - die_error(undef, "Invalid hash parent parameter"); + die_error(400, "Invalid hash parent parameter"); } } -our $hash_base = $cgi->param('hb'); +our $hash_base = $input_params{'hash_base'}; if (defined $hash_base) { if (!validate_refname($hash_base)) { - die_error(undef, "Invalid hash base parameter"); + die_error(400, "Invalid hash base parameter"); + } +} + +our @extra_options = @{$input_params{'extra_options'}}; +# @extra_options is always defined, since it can only be (currently) set from +# CGI, and $cgi->param() returns the empty array in array context if the param +# is not set +foreach my $opt (@extra_options) { + if (not exists $allowed_options{$opt}) { + die_error(400, "Invalid option parameter"); + } + if (not grep(/^$action$/, @{$allowed_options{$opt}})) { + die_error(400, "Invalid option parameter for this action"); } } -our $hash_parent_base = $cgi->param('hpb'); +our $hash_parent_base = $input_params{'hash_parent_base'}; if (defined $hash_parent_base) { if (!validate_refname($hash_parent_base)) { - die_error(undef, "Invalid hash parent base parameter"); + die_error(400, "Invalid hash parent base parameter"); } } # other parameters -our $page = $cgi->param('pg'); +our $page = $input_params{'page'}; if (defined $page) { if ($page =~ m/[^0-9]/) { - die_error(undef, "Invalid page parameter"); + die_error(400, "Invalid page parameter"); } } -our $searchtext = $cgi->param('s'); -if (defined $searchtext) { - if ($searchtext =~ m/[^a-zA-Z0-9_\.\/\-\+\:\@ ]/) { - die_error(undef, "Invalid search parameter"); - } - if (length($searchtext) < 2) { - die_error(undef, "At least two characters are required for search parameter"); - } - $searchtext = quotemeta $searchtext; -} - -our $searchtype = $cgi->param('st'); +our $searchtype = $input_params{'searchtype'}; if (defined $searchtype) { if ($searchtype =~ m/[^a-z]/) { - die_error(undef, "Invalid searchtype parameter"); + die_error(400, "Invalid searchtype parameter"); } } -# now read PATH_INFO and use it as alternative to parameters -sub evaluate_path_info { - return if defined $project; - my $path_info = $ENV{"PATH_INFO"}; - return if !$path_info; - $path_info =~ s,^/+,,; - return if !$path_info; - # find which part of PATH_INFO is project - $project = $path_info; - $project =~ s,/+$,,; - while ($project && !check_head_link("$projectroot/$project")) { - $project =~ s,/*[^/]*$,,; - } - # validate project - $project = validate_pathname($project); - if (!$project || - ($export_ok && !-e "$projectroot/$project/$export_ok") || - ($strict_export && !project_in_list($project))) { - undef $project; - return; - } - # do not change any parameters if an action is given using the query string - return if $action; - $path_info =~ s,^$project/*,,; - my ($refname, $pathname) = split(/:/, $path_info, 2); - if (defined $pathname) { - # we got "project.git/branch:filename" or "project.git/branch:dir/" - # we could use git_get_type(branch:pathname), but it needs $git_dir - $pathname =~ s,^/+,,; - if (!$pathname || substr($pathname, -1) eq "/") { - $action ||= "tree"; - $pathname =~ s,/$,,; - } else { - $action ||= "blob_plain"; - } - $hash_base ||= validate_refname($refname); - $file_name ||= validate_pathname($pathname); - } elsif (defined $refname) { - # we got "project.git/branch" - $action ||= "shortlog"; - $hash ||= validate_refname($refname); +our $search_use_regexp = $input_params{'search_use_regexp'}; + +our $searchtext = $input_params{'searchtext'}; +our $search_regexp; +if (defined $searchtext) { + if (length($searchtext) < 2) { + die_error(403, "At least two characters are required for search parameter"); } + $search_regexp = $search_use_regexp ? $searchtext : quotemeta $searchtext; } -evaluate_path_info(); # path to the current git repository our $git_dir; $git_dir = "$projectroot/$project" if $project; -# dispatch -my %actions = ( - "blame" => \&git_blame2, - "blobdiff" => \&git_blobdiff, - "blobdiff_plain" => \&git_blobdiff_plain, - "blob" => \&git_blob, - "blob_plain" => \&git_blob_plain, - "commitdiff" => \&git_commitdiff, - "commitdiff_plain" => \&git_commitdiff_plain, - "commit" => \&git_commit, - "forks" => \&git_forks, - "heads" => \&git_heads, - "history" => \&git_history, - "log" => \&git_log, - "rss" => \&git_rss, - "atom" => \&git_atom, - "search" => \&git_search, - "search_help" => \&git_search_help, - "shortlog" => \&git_shortlog, - "summary" => \&git_summary, - "tag" => \&git_tag, - "tags" => \&git_tags, - "tree" => \&git_tree, - "snapshot" => \&git_snapshot, - "object" => \&git_object, - # those below don't need $project - "opml" => \&git_opml, - "project_list" => \&git_project_list, - "project_index" => \&git_project_index, -); - -if (defined $project) { - $action ||= 'summary'; +# list of supported snapshot formats +our @snapshot_fmts = gitweb_get_feature('snapshot'); +@snapshot_fmts = filter_snapshot_fmts(@snapshot_fmts); + +# check that the avatar feature is set to a known provider name, +# and for each provider check if the dependencies are satisfied. +# if the provider name is invalid or the dependencies are not met, +# reset $git_avatar to the empty string. +our ($git_avatar) = gitweb_get_feature('avatar'); +if ($git_avatar eq 'gravatar') { + $git_avatar = '' unless (eval { require Digest::MD5; 1; }); +} elsif ($git_avatar eq 'picon') { + # no dependencies } else { - $action ||= 'project_list'; + $git_avatar = ''; +} + +# dispatch +if (!defined $action) { + if (defined $hash) { + $action = git_get_type($hash); + } elsif (defined $hash_base && defined $file_name) { + $action = git_get_type("$hash_base:$file_name"); + } elsif (defined $project) { + $action = 'summary'; + } else { + $action = 'project_list'; + } } if (!defined($actions{$action})) { - die_error(undef, "Unknown action"); + die_error(400, "Unknown action"); } -if ($action !~ m/^(opml|project_list|project_index)$/ && +if ($action !~ m/^(?:opml|project_list|project_index)$/ && !$project) { - die_error(undef, "Project needed"); + die_error(400, "Project needed"); } $actions{$action}->(); exit; @@ -472,50 +977,112 @@ exit; ## ====================================================================== ## action links -sub href(%) { +sub href { my %params = @_; # default is to use -absolute url() i.e. $my_uri my $href = $params{-full} ? $my_url : $my_uri; - # XXX: Warning: If you touch this, check the search form for updating, - # too. - - my @mapping = ( - project => "p", - action => "a", - file_name => "f", - file_parent => "fp", - hash => "h", - hash_parent => "hp", - hash_base => "hb", - hash_parent_base => "hpb", - page => "pg", - order => "o", - searchtext => "s", - searchtype => "st", - ); - my %mapping = @mapping; - $params{'project'} = $project unless exists $params{'project'}; - my ($use_pathinfo) = gitweb_check_feature('pathinfo'); - if ($use_pathinfo) { - # use PATH_INFO for project name - $href .= "/$params{'project'}" if defined $params{'project'}; + if ($params{-replay}) { + while (my ($name, $symbol) = each %cgi_param_mapping) { + if (!exists $params{$name}) { + $params{$name} = $input_params{$name}; + } + } + } + + my $use_pathinfo = gitweb_check_feature('pathinfo'); + if ($use_pathinfo and defined $params{'project'}) { + # try to put as many parameters as possible in PATH_INFO: + # - project name + # - action + # - hash_parent or hash_parent_base:/file_parent + # - hash or hash_base:/filename + # - the snapshot_format as an appropriate suffix + + # When the script is the root DirectoryIndex for the domain, + # $href here would be something like http://gitweb.example.com/ + # Thus, we strip any trailing / from $href, to spare us double + # slashes in the final URL + $href =~ s,/$,,; + + # Then add the project name, if present + $href .= "/".esc_url($params{'project'}); delete $params{'project'}; - # Summary just uses the project path URL - if (defined $params{'action'} && $params{'action'} eq 'summary') { + # since we destructively absorb parameters, we keep this + # boolean that remembers if we're handling a snapshot + my $is_snapshot = $params{'action'} eq 'snapshot'; + + # Summary just uses the project path URL, any other action is + # added to the URL + if (defined $params{'action'}) { + $href .= "/".esc_url($params{'action'}) unless $params{'action'} eq 'summary'; delete $params{'action'}; } + + # Next, we put hash_parent_base:/file_parent..hash_base:/file_name, + # stripping nonexistent or useless pieces + $href .= "/" if ($params{'hash_base'} || $params{'hash_parent_base'} + || $params{'hash_parent'} || $params{'hash'}); + if (defined $params{'hash_base'}) { + if (defined $params{'hash_parent_base'}) { + $href .= esc_url($params{'hash_parent_base'}); + # skip the file_parent if it's the same as the file_name + if (defined $params{'file_parent'}) { + if (defined $params{'file_name'} && $params{'file_parent'} eq $params{'file_name'}) { + delete $params{'file_parent'}; + } elsif ($params{'file_parent'} !~ /\.\./) { + $href .= ":/".esc_url($params{'file_parent'}); + delete $params{'file_parent'}; + } + } + $href .= ".."; + delete $params{'hash_parent'}; + delete $params{'hash_parent_base'}; + } elsif (defined $params{'hash_parent'}) { + $href .= esc_url($params{'hash_parent'}). ".."; + delete $params{'hash_parent'}; + } + + $href .= esc_url($params{'hash_base'}); + if (defined $params{'file_name'} && $params{'file_name'} !~ /\.\./) { + $href .= ":/".esc_url($params{'file_name'}); + delete $params{'file_name'}; + } + delete $params{'hash'}; + delete $params{'hash_base'}; + } elsif (defined $params{'hash'}) { + $href .= esc_url($params{'hash'}); + delete $params{'hash'}; + } + + # If the action was a snapshot, we can absorb the + # snapshot_format parameter too + if ($is_snapshot) { + my $fmt = $params{'snapshot_format'}; + # snapshot_format should always be defined when href() + # is called, but just in case some code forgets, we + # fall back to the default + $fmt ||= $snapshot_fmts[0]; + $href .= $known_snapshot_formats{$fmt}{'suffix'}; + delete $params{'snapshot_format'}; + } } # now encode the parameters explicitly my @result = (); - for (my $i = 0; $i < @mapping; $i += 2) { - my ($name, $symbol) = ($mapping[$i], $mapping[$i+1]); + for (my $i = 0; $i < @cgi_param_mapping; $i += 2) { + my ($name, $symbol) = ($cgi_param_mapping[$i], $cgi_param_mapping[$i+1]); if (defined $params{$name}) { - push @result, $symbol . "=" . esc_param($params{$name}); + if (ref($params{$name}) eq "ARRAY") { + foreach my $par (@{$params{$name}}) { + push @result, $symbol . "=" . esc_param($par); + } + } else { + push @result, $symbol . "=" . esc_param($params{$name}); + } } } $href .= "?" . join(';', @result) if scalar @result; @@ -527,6 +1094,24 @@ sub href(%) { ## ====================================================================== ## validation, quoting/unquoting and escaping +sub validate_action { + my $input = shift || return undef; + return undef unless exists $actions{$input}; + return $input; +} + +sub validate_project { + my $input = shift || return undef; + if (!validate_pathname($input) || + !(-d "$projectroot/$input") || + !check_export_ok("$projectroot/$input") || + ($strict_export && !project_in_list($input))) { + return undef; + } else { + return $input; + } +} + sub validate_pathname { my $input = shift || return undef; @@ -560,18 +1145,24 @@ sub validate_refname { return $input; } -# very thin wrapper for decode("utf8", $str, Encode::FB_DEFAULT); +# decode sequences of octets in utf8 into Perl's internal form, +# which is utf-8 with utf8 flag set if needed. gitweb writes out +# in utf-8 thanks to "binmode STDOUT, ':utf8'" at beginning sub to_utf8 { my $str = shift; - return decode("utf8", $str, Encode::FB_DEFAULT); + if (utf8::valid($str)) { + utf8::decode($str); + return $str; + } else { + return decode($fallback_encoding, $str, Encode::FB_DEFAULT); + } } # quote unsafe chars, but keep the slash, even when it's not # correct, but quoted slashes look too horrible in bookmarks sub esc_param { my $str = shift; - $str =~ s/([^A-Za-z0-9\-_.~()\/:@])/sprintf("%%%02X", ord($1))/eg; - $str =~ s/\+/%2B/g; + $str =~ s/([^A-Za-z0-9\-_.~()\/:@ ]+)/CGI::escape($1)/eg; $str =~ s/ /\+/g; return $str; } @@ -586,12 +1177,12 @@ sub esc_url { } # replace invalid utf8 character with SUBSTITUTION sequence -sub esc_html ($;%) { +sub esc_html { my $str = shift; my %opts = @_; $str = to_utf8($str); - $str = escapeHTML($str); + $str = $cgi->escapeHTML($str); if ($opts{'-nbsp'}) { $str =~ s/ / /g; } @@ -605,7 +1196,7 @@ sub esc_path { my %opts = @_; $str = to_utf8($str); - $str = escapeHTML($str); + $str = $cgi->escapeHTML($str); if ($opts{'-nbsp'}) { $str =~ s/ / /g; } @@ -616,29 +1207,40 @@ sub esc_path { # Make control characters "printable", using character escape codes (CEC) sub quot_cec { my $cntrl = shift; + my %opts = @_; my %es = ( # character escape codes, aka escape sequences - "\t" => '\t', # tab (HT) - "\n" => '\n', # line feed (LF) - "\r" => '\r', # carrige return (CR) - "\f" => '\f', # form feed (FF) - "\b" => '\b', # backspace (BS) - "\a" => '\a', # alarm (bell) (BEL) - "\e" => '\e', # escape (ESC) - "\013" => '\v', # vertical tab (VT) - "\000" => '\0', # nul character (NUL) - ); + "\t" => '\t', # tab (HT) + "\n" => '\n', # line feed (LF) + "\r" => '\r', # carrige return (CR) + "\f" => '\f', # form feed (FF) + "\b" => '\b', # backspace (BS) + "\a" => '\a', # alarm (bell) (BEL) + "\e" => '\e', # escape (ESC) + "\013" => '\v', # vertical tab (VT) + "\000" => '\0', # nul character (NUL) + ); my $chr = ( (exists $es{$cntrl}) ? $es{$cntrl} - : sprintf('\%03o', ord($cntrl)) ); - return "<span class=\"cntrl\">$chr</span>"; + : sprintf('\%2x', ord($cntrl)) ); + if ($opts{-nohtml}) { + return $chr; + } else { + return "<span class=\"cntrl\">$chr</span>"; + } } # Alternatively use unicode control pictures codepoints, # Unicode "printable representation" (PR) sub quot_upr { my $cntrl = shift; + my %opts = @_; + my $chr = sprintf('&#%04d;', 0x2400+ord($cntrl)); - return "<span class=\"cntrl\">$chr</span>"; + if ($opts{-nohtml}) { + return $chr; + } else { + return "<span class=\"cntrl\">$chr</span>"; + } } # git may return quoted and escaped filenames @@ -663,7 +1265,7 @@ sub unquote { return chr(oct($seq)); } elsif (exists $es{$seq}) { # C escape sequence, aka character escape code - return $es{$seq} + return $es{$seq}; } # quoted ordinary character return $seq; @@ -700,21 +1302,79 @@ sub project_in_list { ## ---------------------------------------------------------------------- ## HTML aware string manipulation +# Try to chop given string on a word boundary between position +# $len and $len+$add_len. If there is no word boundary there, +# chop at $len+$add_len. Do not chop if chopped part plus ellipsis +# (marking chopped part) would be longer than given string. sub chop_str { my $str = shift; my $len = shift; my $add_len = shift || 10; + my $where = shift || 'right'; # 'left' | 'center' | 'right' + + # Make sure perl knows it is utf8 encoded so we don't + # cut in the middle of a utf8 multibyte char. + $str = to_utf8($str); # allow only $len chars, but don't cut a word if it would fit in $add_len # if it doesn't fit, cut it if it's still longer than the dots we would add - $str =~ m/^(.{0,$len}[^ \/\-_:\.@]{0,$add_len})(.*)/; - my $body = $1; - my $tail = $2; - if (length($tail) > 4) { - $tail = " ..."; - $body =~ s/&[^;]*$//; # remove chopped character entities + # remove chopped character entities entirely + + # when chopping in the middle, distribute $len into left and right part + # return early if chopping wouldn't make string shorter + if ($where eq 'center') { + return $str if ($len + 5 >= length($str)); # filler is length 5 + $len = int($len/2); + } else { + return $str if ($len + 4 >= length($str)); # filler is length 4 + } + + # regexps: ending and beginning with word part up to $add_len + my $endre = qr/.{$len}\w{0,$add_len}/; + my $begre = qr/\w{0,$add_len}.{$len}/; + + if ($where eq 'left') { + $str =~ m/^(.*?)($begre)$/; + my ($lead, $body) = ($1, $2); + if (length($lead) > 4) { + $lead = " ..."; + } + return "$lead$body"; + + } elsif ($where eq 'center') { + $str =~ m/^($endre)(.*)$/; + my ($left, $str) = ($1, $2); + $str =~ m/^(.*?)($begre)$/; + my ($mid, $right) = ($1, $2); + if (length($mid) > 5) { + $mid = " ... "; + } + return "$left$mid$right"; + + } else { + $str =~ m/^($endre)(.*)$/; + my $body = $1; + my $tail = $2; + if (length($tail) > 4) { + $tail = "... "; + } + return "$body$tail"; + } +} + +# takes the same arguments as chop_str, but also wraps a <span> around the +# result with a title attribute if it does get chopped. Additionally, the +# string is HTML-escaped. +sub chop_and_escape_str { + my ($str) = @_; + + my $chopped = chop_str(@_); + if ($chopped eq $str) { + return esc_html($chopped); + } else { + $str =~ s/[[:cntrl:]]/?/g; + return $cgi->span({-title=>$str}, esc_html($chopped)); } - return "$body$tail"; } ## ---------------------------------------------------------------------- @@ -724,7 +1384,9 @@ sub chop_str { sub age_class { my $age = shift; - if ($age < 60*60*2) { + if (!defined $age) { + return "noage"; + } elsif ($age < 60*60*2) { return "age0"; } elsif ($age < 60*60*24*2) { return "age1"; @@ -765,11 +1427,25 @@ sub age_string { return $age_str; } +use constant { + S_IFINVALID => 0030000, + S_IFGITLINK => 0160000, +}; + +# submodule/subproject, a commit object reference +sub S_ISGITLINK { + my $mode = shift; + + return (($mode & S_IFMT) == S_IFGITLINK) +} + # convert file mode in octal to symbolic file mode string sub mode_str { my $mode = oct shift; - if (S_ISDIR($mode & S_IFMT)) { + if (S_ISGITLINK($mode)) { + return 'm---------'; + } elsif (S_ISDIR($mode & S_IFMT)) { return 'drwxr-xr-x'; } elsif (S_ISLNK($mode)) { return 'lrwxrwxrwx'; @@ -795,7 +1471,9 @@ sub file_type { $mode = oct $mode; } - if (S_ISDIR($mode & S_IFMT)) { + if (S_ISGITLINK($mode)) { + return "submodule"; + } elsif (S_ISDIR($mode & S_IFMT)) { return "directory"; } elsif (S_ISLNK($mode)) { return "symlink"; @@ -816,7 +1494,9 @@ sub file_type_long { $mode = oct $mode; } - if (S_ISDIR($mode & S_IFMT)) { + if (S_ISGITLINK($mode)) { + return "submodule"; + } elsif (S_ISDIR($mode & S_IFMT)) { return "directory"; } elsif (S_ISLNK($mode)) { return "symlink"; @@ -834,31 +1514,39 @@ sub file_type_long { ## ---------------------------------------------------------------------- ## functions returning short HTML fragments, or transforming HTML fragments -## which don't beling to other sections +## which don't belong to other sections # format line of commit message. sub format_log_line_html { my $line = shift; $line = esc_html($line, -nbsp=>1); - if ($line =~ m/([0-9a-fA-F]{8,40})/) { - my $hash_text = $1; - my $link = - $cgi->a({-href => href(action=>"object", hash=>$hash_text), - -class => "text"}, $hash_text); - $line =~ s/$hash_text/$link/; - } + $line =~ s{\b([0-9a-fA-F]{8,40})\b}{ + $cgi->a({-href => href(action=>"object", hash=>$1), + -class => "text"}, $1); + }eg; + return $line; } # format marker of refs pointing to given object + +# the destination action is chosen based on object type and current context: +# - for annotated tags, we choose the tag view unless it's the current view +# already, in which case we go to shortlog view +# - for other refs, we keep the current view if we're in history, shortlog or +# log view, and select shortlog otherwise sub format_ref_marker { my ($refs, $id) = @_; my $markers = ''; if (defined $refs->{$id}) { foreach my $ref (@{$refs->{$id}}) { + # this code exploits the fact that non-lightweight tags are the + # only indirect objects, and that they are the only objects for which + # we want to use tag instead of shortlog as action my ($type, $name) = qw(); + my $indirect = ($ref =~ s/\^\{\}$//); # e.g. tags/v2.6.11 or heads/next if ($ref =~ m!^(.*?)s?/(.*)$!) { $type = $1; @@ -868,8 +1556,29 @@ sub format_ref_marker { $name = $ref; } - $markers .= " <span class=\"$type\" title=\"$ref\">" . - esc_html($name) . "</span>"; + my $class = $type; + $class .= " indirect" if $indirect; + + my $dest_action = "shortlog"; + + if ($indirect) { + $dest_action = "tag" unless $action eq "tag"; + } elsif ($action =~ /^(history|(short)?log)$/) { + $dest_action = $action; + } + + my $dest = ""; + $dest .= "refs/" unless $ref =~ m!^refs/!; + $dest .= $ref; + + my $link = $cgi->a({ + -href => href( + action=>$dest_action, + hash=>$dest + )}, $name); + + $markers .= " <span class=\"$class\" title=\"$ref\">" . + $link . "</span>"; } } @@ -886,32 +1595,342 @@ sub format_subject_html { $extra = '' unless defined($extra); if (length($short) < length($long)) { + $long =~ s/[[:cntrl:]]/?/g; return $cgi->a({-href => $href, -class => "list subject", -title => to_utf8($long)}, - esc_html($short) . $extra); + esc_html($short)) . $extra; } else { return $cgi->a({-href => $href, -class => "list subject"}, - esc_html($long) . $extra); + esc_html($long)) . $extra; + } +} + +# Rather than recomputing the url for an email multiple times, we cache it +# after the first hit. This gives a visible benefit in views where the avatar +# for the same email is used repeatedly (e.g. shortlog). +# The cache is shared by all avatar engines (currently gravatar only), which +# are free to use it as preferred. Since only one avatar engine is used for any +# given page, there's no risk for cache conflicts. +our %avatar_cache = (); + +# Compute the picon url for a given email, by using the picon search service over at +# http://www.cs.indiana.edu/picons/search.html +sub picon_url { + my $email = lc shift; + if (!$avatar_cache{$email}) { + my ($user, $domain) = split('@', $email); + $avatar_cache{$email} = + "http://www.cs.indiana.edu/cgi-pub/kinzler/piconsearch.cgi/" . + "$domain/$user/" . + "users+domains+unknown/up/single"; + } + return $avatar_cache{$email}; +} + +# Compute the gravatar url for a given email, if it's not in the cache already. +# Gravatar stores only the part of the URL before the size, since that's the +# one computationally more expensive. This also allows reuse of the cache for +# different sizes (for this particular engine). +sub gravatar_url { + my $email = lc shift; + my $size = shift; + $avatar_cache{$email} ||= + "http://www.gravatar.com/avatar/" . + Digest::MD5::md5_hex($email) . "?s="; + return $avatar_cache{$email} . $size; +} + +# Insert an avatar for the given $email at the given $size if the feature +# is enabled. +sub git_get_avatar { + my ($email, %opts) = @_; + my $pre_white = ($opts{-pad_before} ? " " : ""); + my $post_white = ($opts{-pad_after} ? " " : ""); + $opts{-size} ||= 'default'; + my $size = $avatar_size{$opts{-size}} || $avatar_size{'default'}; + my $url = ""; + if ($git_avatar eq 'gravatar') { + $url = gravatar_url($email, $size); + } elsif ($git_avatar eq 'picon') { + $url = picon_url($email); + } + # Other providers can be added by extending the if chain, defining $url + # as needed. If no variant puts something in $url, we assume avatars + # are completely disabled/unavailable. + if ($url) { + return $pre_white . + "<img width=\"$size\" " . + "class=\"avatar\" " . + "src=\"$url\" " . + "alt=\"\" " . + "/>" . $post_white; + } else { + return ""; + } +} + +sub format_search_author { + my ($author, $searchtype, $displaytext) = @_; + my $have_search = gitweb_check_feature('search'); + + if ($have_search) { + my $performed = ""; + if ($searchtype eq 'author') { + $performed = "authored"; + } elsif ($searchtype eq 'committer') { + $performed = "committed"; + } + + return $cgi->a({-href => href(action=>"search", hash=>$hash, + searchtext=>$author, + searchtype=>$searchtype), class=>"list", + title=>"Search for commits $performed by $author"}, + $displaytext); + + } else { + return $displaytext; + } +} + +# format the author name of the given commit with the given tag +# the author name is chopped and escaped according to the other +# optional parameters (see chop_str). +sub format_author_html { + my $tag = shift; + my $co = shift; + my $author = chop_and_escape_str($co->{'author_name'}, @_); + return "<$tag class=\"author\">" . + format_search_author($co->{'author_name'}, "author", + git_get_avatar($co->{'author_email'}, -pad_after => 1) . + $author) . + "</$tag>"; +} + +# format git diff header line, i.e. "diff --(git|combined|cc) ..." +sub format_git_diff_header_line { + my $line = shift; + my $diffinfo = shift; + my ($from, $to) = @_; + + if ($diffinfo->{'nparents'}) { + # combined diff + $line =~ s!^(diff (.*?) )"?.*$!$1!; + if ($to->{'href'}) { + $line .= $cgi->a({-href => $to->{'href'}, -class => "path"}, + esc_path($to->{'file'})); + } else { # file was deleted (no href) + $line .= esc_path($to->{'file'}); + } + } else { + # "ordinary" diff + $line =~ s!^(diff (.*?) )"?a/.*$!$1!; + if ($from->{'href'}) { + $line .= $cgi->a({-href => $from->{'href'}, -class => "path"}, + 'a/' . esc_path($from->{'file'})); + } else { # file was added (no href) + $line .= 'a/' . esc_path($from->{'file'}); + } + $line .= ' '; + if ($to->{'href'}) { + $line .= $cgi->a({-href => $to->{'href'}, -class => "path"}, + 'b/' . esc_path($to->{'file'})); + } else { # file was deleted + $line .= 'b/' . esc_path($to->{'file'}); + } } + + return "<div class=\"diff header\">$line</div>\n"; } -# format patch (diff) line (rather not to be used for diff headers) +# format extended diff header line, before patch itself +sub format_extended_diff_header_line { + my $line = shift; + my $diffinfo = shift; + my ($from, $to) = @_; + + # match <path> + if ($line =~ s!^((copy|rename) from ).*$!$1! && $from->{'href'}) { + $line .= $cgi->a({-href=>$from->{'href'}, -class=>"path"}, + esc_path($from->{'file'})); + } + if ($line =~ s!^((copy|rename) to ).*$!$1! && $to->{'href'}) { + $line .= $cgi->a({-href=>$to->{'href'}, -class=>"path"}, + esc_path($to->{'file'})); + } + # match single <mode> + if ($line =~ m/\s(\d{6})$/) { + $line .= '<span class="info"> (' . + file_type_long($1) . + ')</span>'; + } + # match <hash> + if ($line =~ m/^index [0-9a-fA-F]{40},[0-9a-fA-F]{40}/) { + # can match only for combined diff + $line = 'index '; + for (my $i = 0; $i < $diffinfo->{'nparents'}; $i++) { + if ($from->{'href'}[$i]) { + $line .= $cgi->a({-href=>$from->{'href'}[$i], + -class=>"hash"}, + substr($diffinfo->{'from_id'}[$i],0,7)); + } else { + $line .= '0' x 7; + } + # separator + $line .= ',' if ($i < $diffinfo->{'nparents'} - 1); + } + $line .= '..'; + if ($to->{'href'}) { + $line .= $cgi->a({-href=>$to->{'href'}, -class=>"hash"}, + substr($diffinfo->{'to_id'},0,7)); + } else { + $line .= '0' x 7; + } + + } elsif ($line =~ m/^index [0-9a-fA-F]{40}..[0-9a-fA-F]{40}/) { + # can match only for ordinary diff + my ($from_link, $to_link); + if ($from->{'href'}) { + $from_link = $cgi->a({-href=>$from->{'href'}, -class=>"hash"}, + substr($diffinfo->{'from_id'},0,7)); + } else { + $from_link = '0' x 7; + } + if ($to->{'href'}) { + $to_link = $cgi->a({-href=>$to->{'href'}, -class=>"hash"}, + substr($diffinfo->{'to_id'},0,7)); + } else { + $to_link = '0' x 7; + } + my ($from_id, $to_id) = ($diffinfo->{'from_id'}, $diffinfo->{'to_id'}); + $line =~ s!$from_id\.\.$to_id!$from_link..$to_link!; + } + + return $line . "<br/>\n"; +} + +# format from-file/to-file diff header +sub format_diff_from_to_header { + my ($from_line, $to_line, $diffinfo, $from, $to, @parents) = @_; + my $line; + my $result = ''; + + $line = $from_line; + #assert($line =~ m/^---/) if DEBUG; + # no extra formatting for "^--- /dev/null" + if (! $diffinfo->{'nparents'}) { + # ordinary (single parent) diff + if ($line =~ m!^--- "?a/!) { + if ($from->{'href'}) { + $line = '--- a/' . + $cgi->a({-href=>$from->{'href'}, -class=>"path"}, + esc_path($from->{'file'})); + } else { + $line = '--- a/' . + esc_path($from->{'file'}); + } + } + $result .= qq!<div class="diff from_file">$line</div>\n!; + + } else { + # combined diff (merge commit) + for (my $i = 0; $i < $diffinfo->{'nparents'}; $i++) { + if ($from->{'href'}[$i]) { + $line = '--- ' . + $cgi->a({-href=>href(action=>"blobdiff", + hash_parent=>$diffinfo->{'from_id'}[$i], + hash_parent_base=>$parents[$i], + file_parent=>$from->{'file'}[$i], + hash=>$diffinfo->{'to_id'}, + hash_base=>$hash, + file_name=>$to->{'file'}), + -class=>"path", + -title=>"diff" . ($i+1)}, + $i+1) . + '/' . + $cgi->a({-href=>$from->{'href'}[$i], -class=>"path"}, + esc_path($from->{'file'}[$i])); + } else { + $line = '--- /dev/null'; + } + $result .= qq!<div class="diff from_file">$line</div>\n!; + } + } + + $line = $to_line; + #assert($line =~ m/^\+\+\+/) if DEBUG; + # no extra formatting for "^+++ /dev/null" + if ($line =~ m!^\+\+\+ "?b/!) { + if ($to->{'href'}) { + $line = '+++ b/' . + $cgi->a({-href=>$to->{'href'}, -class=>"path"}, + esc_path($to->{'file'})); + } else { + $line = '+++ b/' . + esc_path($to->{'file'}); + } + } + $result .= qq!<div class="diff to_file">$line</div>\n!; + + return $result; +} + +# create note for patch simplified by combined diff +sub format_diff_cc_simplified { + my ($diffinfo, @parents) = @_; + my $result = ''; + + $result .= "<div class=\"diff header\">" . + "diff --cc "; + if (!is_deleted($diffinfo)) { + $result .= $cgi->a({-href => href(action=>"blob", + hash_base=>$hash, + hash=>$diffinfo->{'to_id'}, + file_name=>$diffinfo->{'to_file'}), + -class => "path"}, + esc_path($diffinfo->{'to_file'})); + } else { + $result .= esc_path($diffinfo->{'to_file'}); + } + $result .= "</div>\n" . # class="diff header" + "<div class=\"diff nodifferences\">" . + "Simple merge" . + "</div>\n"; # class="diff nodifferences" + + return $result; +} + +# format patch (diff) line (not to be used for diff headers) sub format_diff_line { my $line = shift; my ($from, $to) = @_; - my $char = substr($line, 0, 1); my $diff_class = ""; chomp $line; - if ($char eq '+') { - $diff_class = " add"; - } elsif ($char eq "-") { - $diff_class = " rem"; - } elsif ($char eq "@") { - $diff_class = " chunk_header"; - } elsif ($char eq "\\") { - $diff_class = " incomplete"; + if ($from && $to && ref($from->{'href'}) eq "ARRAY") { + # combined diff + my $prefix = substr($line, 0, scalar @{$from->{'href'}}); + if ($line =~ m/^\@{3}/) { + $diff_class = " chunk_header"; + } elsif ($line =~ m/^\\/) { + $diff_class = " incomplete"; + } elsif ($prefix =~ tr/+/+/) { + $diff_class = " add"; + } elsif ($prefix =~ tr/-/-/) { + $diff_class = " rem"; + } + } else { + # assume ordinary diff + my $char = substr($line, 0, 1); + if ($char eq '+') { + $diff_class = " add"; + } elsif ($char eq '-') { + $diff_class = " rem"; + } elsif ($char eq '@') { + $diff_class = " chunk_header"; + } elsif ($char eq "\\") { + $diff_class = " incomplete"; + } } $line = untabify($line); if ($from && $to && $line =~ m/^\@{2} /) { @@ -932,35 +1951,159 @@ sub format_diff_line { $line = "<span class=\"chunk_info\">@@ $from_text $to_text @@</span>" . "<span class=\"section\">" . esc_html($section, -nbsp=>1) . "</span>"; return "<div class=\"diff$diff_class\">$line</div>\n"; + } elsif ($from && $to && $line =~ m/^\@{3}/) { + my ($prefix, $ranges, $section) = $line =~ m/^(\@+) (.*?) \@+(.*)$/; + my (@from_text, @from_start, @from_nlines, $to_text, $to_start, $to_nlines); + + @from_text = split(' ', $ranges); + for (my $i = 0; $i < @from_text; ++$i) { + ($from_start[$i], $from_nlines[$i]) = + (split(',', substr($from_text[$i], 1)), 0); + } + + $to_text = pop @from_text; + $to_start = pop @from_start; + $to_nlines = pop @from_nlines; + + $line = "<span class=\"chunk_info\">$prefix "; + for (my $i = 0; $i < @from_text; ++$i) { + if ($from->{'href'}[$i]) { + $line .= $cgi->a({-href=>"$from->{'href'}[$i]#l$from_start[$i]", + -class=>"list"}, $from_text[$i]); + } else { + $line .= $from_text[$i]; + } + $line .= " "; + } + if ($to->{'href'}) { + $line .= $cgi->a({-href=>"$to->{'href'}#l$to_start", + -class=>"list"}, $to_text); + } else { + $line .= $to_text; + } + $line .= " $prefix</span>" . + "<span class=\"section\">" . esc_html($section, -nbsp=>1) . "</span>"; + return "<div class=\"diff$diff_class\">$line</div>\n"; } return "<div class=\"diff$diff_class\">" . esc_html($line, -nbsp=>1) . "</div>\n"; } +# Generates undef or something like "_snapshot_" or "snapshot (_tbz2_ _zip_)", +# linked. Pass the hash of the tree/commit to snapshot. +sub format_snapshot_links { + my ($hash) = @_; + my $num_fmts = @snapshot_fmts; + if ($num_fmts > 1) { + # A parenthesized list of links bearing format names. + # e.g. "snapshot (_tar.gz_ _zip_)" + return "snapshot (" . join(' ', map + $cgi->a({ + -href => href( + action=>"snapshot", + hash=>$hash, + snapshot_format=>$_ + ) + }, $known_snapshot_formats{$_}{'display'}) + , @snapshot_fmts) . ")"; + } elsif ($num_fmts == 1) { + # A single "snapshot" link whose tooltip bears the format name. + # i.e. "_snapshot_" + my ($fmt) = @snapshot_fmts; + return + $cgi->a({ + -href => href( + action=>"snapshot", + hash=>$hash, + snapshot_format=>$fmt + ), + -title => "in format: $known_snapshot_formats{$fmt}{'display'}" + }, "snapshot"); + } else { # $num_fmts == 0 + return undef; + } +} + +## ...................................................................... +## functions returning values to be passed, perhaps after some +## transformation, to other functions; e.g. returning arguments to href() + +# returns hash to be passed to href to generate gitweb URL +# in -title key it returns description of link +sub get_feed_info { + my $format = shift || 'Atom'; + my %res = (action => lc($format)); + + # feed links are possible only for project views + return unless (defined $project); + # some views should link to OPML, or to generic project feed, + # or don't have specific feed yet (so they should use generic) + return if ($action =~ /^(?:tags|heads|forks|tag|search)$/x); + + my $branch; + # branches refs uses 'refs/heads/' prefix (fullname) to differentiate + # from tag links; this also makes possible to detect branch links + if ((defined $hash_base && $hash_base =~ m!^refs/heads/(.*)$!) || + (defined $hash && $hash =~ m!^refs/heads/(.*)$!)) { + $branch = $1; + } + # find log type for feed description (title) + my $type = 'log'; + if (defined $file_name) { + $type = "history of $file_name"; + $type .= "/" if ($action eq 'tree'); + $type .= " on '$branch'" if (defined $branch); + } else { + $type = "log of $branch" if (defined $branch); + } + + $res{-title} = $type; + $res{'hash'} = (defined $branch ? "refs/heads/$branch" : undef); + $res{'file_name'} = $file_name; + + return %res; +} + ## ---------------------------------------------------------------------- ## git utility subroutines, invoking git commands # returns path to the core git executable and the --git-dir parameter as list sub git_cmd { + $number_of_git_cmds++; return $GIT, '--git-dir='.$git_dir; } -# returns path to the core git executable and the --git-dir parameter as string -sub git_cmd_str { - return join(' ', git_cmd()); +# quote the given arguments for passing them to the shell +# quote_command("command", "arg 1", "arg with ' and ! characters") +# => "'command' 'arg 1' 'arg with '\'' and '\!' characters'" +# Try to avoid using this function wherever possible. +sub quote_command { + return join(' ', + map { my $a = $_; $a =~ s/(['!])/'\\$1'/g; "'$a'" } @_ ); } # get HEAD ref of given project as hash sub git_get_head_hash { - my $project = shift; + return git_get_full_hash(shift, 'HEAD'); +} + +sub git_get_full_hash { + return git_get_hash(@_); +} + +sub git_get_short_hash { + return git_get_hash(@_, '--short=7'); +} + +sub git_get_hash { + my ($project, $hash, @options) = @_; my $o_git_dir = $git_dir; my $retval = undef; $git_dir = "$projectroot/$project"; - if (open my $fd, "-|", git_cmd(), "rev-parse", "--verify", "HEAD") { - my $head = <$fd>; + if (open my $fd, '-|', git_cmd(), 'rev-parse', + '--verify', '-q', @options, $hash) { + $retval = <$fd>; + chomp $retval if defined $retval; close $fd; - if (defined $head && $head =~ /^([0-9a-fA-F]{40})$/) { - $retval = $1; - } } if (defined $o_git_dir) { $git_dir = $o_git_dir; @@ -979,20 +2122,127 @@ sub git_get_type { return $type; } +# repository configuration +our $config_file = ''; +our %config; + +# store multiple values for single key as anonymous array reference +# single values stored directly in the hash, not as [ <value> ] +sub hash_set_multi { + my ($hash, $key, $value) = @_; + + if (!exists $hash->{$key}) { + $hash->{$key} = $value; + } elsif (!ref $hash->{$key}) { + $hash->{$key} = [ $hash->{$key}, $value ]; + } else { + push @{$hash->{$key}}, $value; + } +} + +# return hash of git project configuration +# optionally limited to some section, e.g. 'gitweb' +sub git_parse_project_config { + my $section_regexp = shift; + my %config; + + local $/ = "\0"; + + open my $fh, "-|", git_cmd(), "config", '-z', '-l', + or return; + + while (my $keyval = <$fh>) { + chomp $keyval; + my ($key, $value) = split(/\n/, $keyval, 2); + + hash_set_multi(\%config, $key, $value) + if (!defined $section_regexp || $key =~ /^(?:$section_regexp)\./o); + } + close $fh; + + return %config; +} + +# convert config value to boolean: 'true' or 'false' +# no value, number > 0, 'true' and 'yes' values are true +# rest of values are treated as false (never as error) +sub config_to_bool { + my $val = shift; + + return 1 if !defined $val; # section.key + + # strip leading and trailing whitespace + $val =~ s/^\s+//; + $val =~ s/\s+$//; + + return (($val =~ /^\d+$/ && $val) || # section.key = 1 + ($val =~ /^(?:true|yes)$/i)); # section.key = true +} + +# convert config value to simple decimal number +# an optional value suffix of 'k', 'm', or 'g' will cause the value +# to be multiplied by 1024, 1048576, or 1073741824 +sub config_to_int { + my $val = shift; + + # strip leading and trailing whitespace + $val =~ s/^\s+//; + $val =~ s/\s+$//; + + if (my ($num, $unit) = ($val =~ /^([0-9]*)([kmg])$/i)) { + $unit = lc($unit); + # unknown unit is treated as 1 + return $num * ($unit eq 'g' ? 1073741824 : + $unit eq 'm' ? 1048576 : + $unit eq 'k' ? 1024 : 1); + } + return $val; +} + +# convert config value to array reference, if needed +sub config_to_multi { + my $val = shift; + + return ref($val) ? $val : (defined($val) ? [ $val ] : []); +} + sub git_get_project_config { my ($key, $type) = @_; + return unless defined $git_dir; + + # key sanity check return unless ($key); $key =~ s/^gitweb\.//; return if ($key =~ m/\W/); - my @x = (git_cmd(), 'config'); - if (defined $type) { push @x, $type; } - push @x, "--get"; - push @x, "gitweb.$key"; - my $val = qx(@x); - chomp $val; - return ($val); + # type sanity check + if (defined $type) { + $type =~ s/^--//; + $type = undef + unless ($type eq 'bool' || $type eq 'int'); + } + + # get config + if (!defined $config_file || + $config_file ne "$git_dir/config") { + %config = git_parse_project_config('gitweb'); + $config_file = "$git_dir/config"; + } + + # check if config variable (key) exists + return unless exists $config{"gitweb.$key"}; + + # ensure given type + if (!defined $type) { + return $config{"gitweb.$key"}; + } elsif ($type eq 'bool') { + # backward compatibility: 'git config --bool' returns true/false + return config_to_bool($config{"gitweb.$key"}) ? 'true' : 'false'; + } elsif ($type eq 'int') { + return config_to_int($config{"gitweb.$key"}); + } + return $config{"gitweb.$key"}; } # get hash of given path at given ref @@ -1004,10 +2254,15 @@ sub git_get_hash_by_path { $path =~ s,/+$,,; open my $fd, "-|", git_cmd(), "ls-tree", $base, "--", $path - or die_error(undef, "Open git-ls-tree failed"); + or die_error(500, "Open git-ls-tree failed"); my $line = <$fd>; close $fd or return undef; + if (!defined $line) { + # there is no tree or hash given by $path at $base + return undef; + } + #'100644 blob 0fa3f3a66fb6a137f6ec2c19351ed4d807070ffa panic.c' $line =~ m/^([0-9]+) (.+) ([0-9a-fA-F]{40})\t/; if (defined $type && $type ne $2) { @@ -1017,23 +2272,119 @@ sub git_get_hash_by_path { return $3; } +# get path of entry with given hash at given tree-ish (ref) +# used to get 'from' filename for combined diff (merge commit) for renames +sub git_get_path_by_hash { + my $base = shift || return; + my $hash = shift || return; + + local $/ = "\0"; + + open my $fd, "-|", git_cmd(), "ls-tree", '-r', '-t', '-z', $base + or return undef; + while (my $line = <$fd>) { + chomp $line; + + #'040000 tree 595596a6a9117ddba9fe379b6b012b558bac8423 gitweb' + #'100644 blob e02e90f0429be0d2a69b76571101f20b8f75530f gitweb/README' + if ($line =~ m/(?:[0-9]+) (?:.+) $hash\t(.+)$/) { + close $fd; + return $1; + } + } + close $fd; + return undef; +} + ## ...................................................................... ## git utility functions, directly accessing git repository sub git_get_project_description { my $path = shift; - open my $fd, "$projectroot/$path/description" or return undef; + $git_dir = "$projectroot/$path"; + open my $fd, '<', "$git_dir/description" + or return git_get_project_config('description'); my $descr = <$fd>; close $fd; - chomp $descr; + if (defined $descr) { + chomp $descr; + } return $descr; } +sub git_get_project_ctags { + my $path = shift; + my $ctags = {}; + + $git_dir = "$projectroot/$path"; + opendir my $dh, "$git_dir/ctags" + or return $ctags; + foreach (grep { -f $_ } map { "$git_dir/ctags/$_" } readdir($dh)) { + open my $ct, '<', $_ or next; + my $val = <$ct>; + chomp $val; + close $ct; + my $ctag = $_; $ctag =~ s#.*/##; + $ctags->{$ctag} = $val; + } + closedir $dh; + $ctags; +} + +sub git_populate_project_tagcloud { + my $ctags = shift; + + # First, merge different-cased tags; tags vote on casing + my %ctags_lc; + foreach (keys %$ctags) { + $ctags_lc{lc $_}->{count} += $ctags->{$_}; + if (not $ctags_lc{lc $_}->{topcount} + or $ctags_lc{lc $_}->{topcount} < $ctags->{$_}) { + $ctags_lc{lc $_}->{topcount} = $ctags->{$_}; + $ctags_lc{lc $_}->{topname} = $_; + } + } + + my $cloud; + if (eval { require HTML::TagCloud; 1; }) { + $cloud = HTML::TagCloud->new; + foreach (sort keys %ctags_lc) { + # Pad the title with spaces so that the cloud looks + # less crammed. + my $title = $ctags_lc{$_}->{topname}; + $title =~ s/ / /g; + $title =~ s/^/ /g; + $title =~ s/$/ /g; + $cloud->add($title, $home_link."?by_tag=".$_, $ctags_lc{$_}->{count}); + } + } else { + $cloud = \%ctags_lc; + } + $cloud; +} + +sub git_show_project_tagcloud { + my ($cloud, $count) = @_; + print STDERR ref($cloud)."..\n"; + if (ref $cloud eq 'HTML::TagCloud') { + return $cloud->html_and_css($count); + } else { + my @tags = sort { $cloud->{$a}->{count} <=> $cloud->{$b}->{count} } keys %$cloud; + return '<p align="center">' . join (', ', map { + "<a href=\"$home_link?by_tag=$_\">$cloud->{$_}->{topname}</a>" + } splice(@tags, 0, $count)) . '</p>'; + } +} + sub git_get_project_url_list { my $path = shift; - open my $fd, "$projectroot/$path/cloneurl" or return; + $git_dir = "$projectroot/$path"; + open my $fd, '<', "$git_dir/cloneurl" + or return wantarray ? + @{ config_to_multi(git_get_project_config('url')) } : + config_to_multi(git_get_project_config('url')); my @git_project_url_list = map { chomp; $_ } <$fd>; close $fd; @@ -1047,30 +2398,36 @@ sub git_get_projects_list { $filter ||= ''; $filter =~ s/\.git$//; + my $check_forks = gitweb_check_feature('forks'); + if (-d $projects_list) { # search in directory my $dir = $projects_list . ($filter ? "/$filter" : ''); # remove the trailing "/" $dir =~ s!/+$!!; my $pfxlen = length("$dir"); - - my ($check_forks) = gitweb_check_feature('forks'); + my $pfxdepth = ($dir =~ tr!/!!); File::Find::find({ follow_fast => 1, # follow symbolic links + follow_skip => 2, # ignore duplicates dangling_symlinks => 0, # ignore dangling symlinks, silently wanted => sub { # skip project-list toplevel, if we get it. return if (m!^[/.]$!); # only directories can be git repositories return unless (-d $_); + # don't traverse too deep (Find is super slow on os x) + if (($File::Find::name =~ tr!/!!) - $pfxdepth > $project_maxdepth) { + $File::Find::prune = 1; + return; + } my $subdir = substr($File::Find::name, $pfxlen + 1); # we check related file in $projectroot - if ($check_forks and $subdir =~ m#/.#) { - $File::Find::prune = 1; - } elsif (check_export_ok("$projectroot/$filter/$subdir")) { - push @list, { path => ($filter ? "$filter/" : '') . $subdir }; + my $path = ($filter ? "$filter/" : '') . $subdir; + if (check_export_ok("$projectroot/$path")) { + push @list, { path => $path }; $File::Find::prune = 1; } }, @@ -1081,7 +2438,9 @@ sub git_get_projects_list { # 'git%2Fgit.git Linus+Torvalds' # 'libs%2Fklibc%2Fklibc.git H.+Peter+Anvin' # 'linux%2Fhotplug%2Fudev.git Greg+Kroah-Hartman' - open my ($fd), $projects_list or return; + my %paths; + open my $fd, '<', $projects_list or return; + PROJECT: while (my $line = <$fd>) { chomp $line; my ($path, $owner) = split ' ', $line; @@ -1094,11 +2453,27 @@ sub git_get_projects_list { # looking for forks; my $pfx = substr($path, 0, length($filter)); if ($pfx ne $filter) { - next; + next PROJECT; } my $sfx = substr($path, length($filter)); if ($sfx !~ /^\/.*\.git$/) { - next; + next PROJECT; + } + } elsif ($check_forks) { + PATH: + foreach my $filter (keys %paths) { + # looking for forks; + my $pfx = substr($path, 0, length($filter)); + if ($pfx ne $filter) { + next PATH; + } + my $sfx = substr($path, length($filter)); + if ($sfx !~ /^\/.*\.git$/) { + next PATH; + } + # is a fork, don't include it in + # the list + next PROJECT; } } if (check_export_ok("$projectroot/$path")) { @@ -1106,41 +2481,58 @@ sub git_get_projects_list { path => $path, owner => to_utf8($owner), }; - push @list, $pr + push @list, $pr; + (my $forks_path = $path) =~ s/\.git$//; + $paths{$forks_path}++; } } close $fd; } - @list = sort {$a->{'path'} cmp $b->{'path'}} @list; return @list; } -sub git_get_project_owner { - my $project = shift; - my $owner; +our $gitweb_project_owner = undef; +sub git_get_project_list_from_file { - return undef unless $project; + return if (defined $gitweb_project_owner); + $gitweb_project_owner = {}; # read from file (url-encoded): # 'git%2Fgit.git Linus+Torvalds' # 'libs%2Fklibc%2Fklibc.git H.+Peter+Anvin' # 'linux%2Fhotplug%2Fudev.git Greg+Kroah-Hartman' if (-f $projects_list) { - open (my $fd , $projects_list); + open(my $fd, '<', $projects_list); while (my $line = <$fd>) { chomp $line; my ($pr, $ow) = split ' ', $line; $pr = unescape($pr); $ow = unescape($ow); - if ($pr eq $project) { - $owner = to_utf8($ow); - last; - } + $gitweb_project_owner->{$pr} = to_utf8($ow); } close $fd; } +} + +sub git_get_project_owner { + my $project = shift; + my $owner; + + return undef unless $project; + $git_dir = "$projectroot/$project"; + + if (!defined $gitweb_project_owner) { + git_get_project_list_from_file(); + } + + if (exists $gitweb_project_owner->{$project}) { + $owner = $gitweb_project_owner->{$project}; + } + if (!defined $owner){ + $owner = git_get_project_config('owner'); + } if (!defined $owner) { - $owner = get_file_owner("$projectroot/$project"); + $owner = get_file_owner("$git_dir"); } return $owner; @@ -1158,11 +2550,13 @@ sub git_get_last_activity { 'refs/heads') or return; my $most_recent = <$fd>; close $fd or return; - if ($most_recent =~ / (\d+) [-+][01]\d\d\d$/) { + if (defined $most_recent && + $most_recent =~ / (\d+) [-+][01]\d\d\d$/) { my $timestamp = $1; my $age = time - $timestamp; return ($age, age_string($age)); } + return (undef, undef); } sub git_get_references { @@ -1176,7 +2570,7 @@ sub git_get_references { while (my $line = <$fd>) { chomp $line; - if ($line =~ m!^([0-9a-fA-F]{40})\srefs/($type/?[^^]+)!) { + if ($line =~ m!^([0-9a-fA-F]{40})\srefs/($type.*)$!) { if (defined $refs{$1}) { push @{$refs{$1}}, $2; } else { @@ -1225,7 +2619,7 @@ sub parse_date { $date{'mday-time'} = sprintf "%d %s %02d:%02d", $mday, $months[$mon], $hour ,$min; $date{'iso-8601'} = sprintf "%04d-%02d-%02dT%02d:%02d:%02dZ", - 1900+$year, $mon, $mday, $hour ,$min, $sec; + 1900+$year, 1+$mon, $mday, $hour ,$min, $sec; $tz =~ m/^([+\-][0-9][0-9])([0-9][0-9])$/; my $local = $epoch + ((int $1 + ($2/60)) * 3600); @@ -1256,8 +2650,14 @@ sub parse_tag { $tag{'name'} = $1; } elsif ($line =~ m/^tagger (.*) ([0-9]+) (.*)$/) { $tag{'author'} = $1; - $tag{'epoch'} = $2; - $tag{'tz'} = $3; + $tag{'author_epoch'} = $2; + $tag{'author_tz'} = $3; + if ($tag{'author'} =~ m/^([^<]+) <([^>]*)>/) { + $tag{'author_name'} = $1; + $tag{'author_email'} = $2; + } else { + $tag{'author_name'} = $tag{'author'}; + } } elsif ($line =~ m/--BEGIN/) { push @comment, $line; last; @@ -1281,8 +2681,12 @@ sub parse_commit_text { pop @commit_lines; # Remove '\0' + if (! @commit_lines) { + return; + } + my $header = shift @commit_lines; - if (!($header =~ m/^[0-9a-fA-F]{40}/)) { + if ($header !~ m/^[0-9a-fA-F]{40}/) { return; } ($co{'id'}, my @parents) = split ' ', $header; @@ -1293,7 +2697,7 @@ sub parse_commit_text { } elsif ((!defined $withparents) && ($line =~ m/^parent ([0-9a-fA-F]{40})$/)) { push @parents, $1; } elsif ($line =~ m/^author (.*) ([0-9]+) (.*)$/) { - $co{'author'} = $1; + $co{'author'} = to_utf8($1); $co{'author_epoch'} = $2; $co{'author_tz'} = $3; if ($co{'author'} =~ m/^([^<]+) <([^>]*)>/) { @@ -1303,10 +2707,9 @@ sub parse_commit_text { $co{'author_name'} = $co{'author'}; } } elsif ($line =~ m/^committer (.*) ([0-9]+) (.*)$/) { - $co{'committer'} = $1; + $co{'committer'} = to_utf8($1); $co{'committer_epoch'} = $2; $co{'committer_tz'} = $3; - $co{'committer_name'} = $co{'committer'}; if ($co{'committer'} =~ m/^([^<]+) <([^>]*)>/) { $co{'committer_name'} = $1; $co{'committer_email'} = $2; @@ -1346,7 +2749,7 @@ sub parse_commit_text { last; } } - if ($co{'title'} eq "") { + if (! defined $co{'title'} || $co{'title'} eq "") { $co{'title'} = $co{'title_short'} = '(no commit message)'; } # remove added spaces @@ -1381,7 +2784,7 @@ sub parse_commit { "--max-count=1", $commit_id, "--", - or die_error(undef, "Open git-rev-list failed"); + or die_error(500, "Open git-rev-list failed"); %co = parse_commit_text(<$fd>, 1); close $fd; @@ -1389,7 +2792,7 @@ sub parse_commit { } sub parse_commits { - my ($commit_id, $maxcount, $skip, $arg, $filename) = @_; + my ($commit_id, $maxcount, $skip, $filename, @args) = @_; my @cos; $maxcount ||= 1; @@ -1399,13 +2802,14 @@ sub parse_commits { open my $fd, "-|", git_cmd(), "rev-list", "--header", - ($arg ? ($arg) : ()), + @args, ("--max-count=" . $maxcount), ("--skip=" . $skip), + @extra_options, $commit_id, "--", ($filename ? ($filename) : ()) - or die_error(undef, "Open git-rev-list failed"); + or die_error(500, "Open git-rev-list failed"); while (my $line = <$fd>) { my %co = parse_commit_text($line); push @cos, \%co; @@ -1415,49 +2819,6 @@ sub parse_commits { return wantarray ? @cos : \@cos; } -# parse ref from ref_file, given by ref_id, with given type -sub parse_ref { - my $ref_file = shift; - my $ref_id = shift; - my $type = shift || git_get_type($ref_id); - my %ref_item; - - $ref_item{'type'} = $type; - $ref_item{'id'} = $ref_id; - $ref_item{'epoch'} = 0; - $ref_item{'age'} = "unknown"; - if ($type eq "tag") { - my %tag = parse_tag($ref_id); - $ref_item{'comment'} = $tag{'comment'}; - if ($tag{'type'} eq "commit") { - my %co = parse_commit($tag{'object'}); - $ref_item{'epoch'} = $co{'committer_epoch'}; - $ref_item{'age'} = $co{'age_string'}; - } elsif (defined($tag{'epoch'})) { - my $age = time - $tag{'epoch'}; - $ref_item{'epoch'} = $tag{'epoch'}; - $ref_item{'age'} = age_string($age); - } - $ref_item{'reftype'} = $tag{'type'}; - $ref_item{'name'} = $tag{'name'}; - $ref_item{'refid'} = $tag{'object'}; - } elsif ($type eq "commit"){ - my %co = parse_commit($ref_id); - $ref_item{'reftype'} = "commit"; - $ref_item{'name'} = $ref_file; - $ref_item{'title'} = $co{'title'}; - $ref_item{'refid'} = $ref_id; - $ref_item{'epoch'} = $co{'committer_epoch'}; - $ref_item{'age'} = $co{'age_string'}; - } else { - $ref_item{'reftype'} = $type; - $ref_item{'name'} = $ref_file; - $ref_item{'refid'} = $ref_id; - } - - return %ref_item; -} - # parse line of git-diff-tree "raw" output sub parse_difftree_raw_line { my $line = shift; @@ -1475,9 +2836,20 @@ sub parse_difftree_raw_line { if ($res{'status'} eq 'R' || $res{'status'} eq 'C') { # renamed or copied ($res{'from_file'}, $res{'to_file'}) = map { unquote($_) } split("\t", $7); } else { - $res{'file'} = unquote($7); + $res{'from_file'} = $res{'to_file'} = $res{'file'} = unquote($7); } } + # '::100755 100755 100755 60e79ca1b01bc8b057abe17ddab484699a7f5fdb 94067cc5f73388f33722d52ae02f44692bc07490 94067cc5f73388f33722d52ae02f44692bc07490 MR git-gui/git-gui.sh' + # combined diff (for merge commit) + elsif ($line =~ s/^(::+)((?:[0-7]{6} )+)((?:[0-9a-fA-F]{40} )+)([a-zA-Z]+)\t(.*)$//) { + $res{'nparents'} = length($1); + $res{'from_mode'} = [ split(' ', $2) ]; + $res{'to_mode'} = pop @{$res{'from_mode'}}; + $res{'from_id'} = [ split(' ', $3) ]; + $res{'to_id'} = pop @{$res{'from_id'}}; + $res{'status'} = [ split('', $4) ]; + $res{'to_file'} = unquote($5); + } # 'c512b523472485aef4fff9e57b229d9d243c967f' elsif ($line =~ m/^([0-9a-fA-F]{40})$/) { $res{'commit'} = $1; @@ -1486,27 +2858,101 @@ sub parse_difftree_raw_line { return wantarray ? %res : \%res; } +# wrapper: return parsed line of git-diff-tree "raw" output +# (the argument might be raw line, or parsed info) +sub parsed_difftree_line { + my $line_or_ref = shift; + + if (ref($line_or_ref) eq "HASH") { + # pre-parsed (or generated by hand) + return $line_or_ref; + } else { + return parse_difftree_raw_line($line_or_ref); + } +} + # parse line of git-ls-tree output -sub parse_ls_tree_line ($;%) { +sub parse_ls_tree_line { my $line = shift; my %opts = @_; my %res; - #'100644 blob 0fa3f3a66fb6a137f6ec2c19351ed4d807070ffa panic.c' - $line =~ m/^([0-9]+) (.+) ([0-9a-fA-F]{40})\t(.+)$/s; + if ($opts{'-l'}) { + #'100644 blob 0fa3f3a66fb6a137f6ec2c19351ed4d807070ffa 16717 panic.c' + $line =~ m/^([0-9]+) (.+) ([0-9a-fA-F]{40}) +(-|[0-9]+)\t(.+)$/s; - $res{'mode'} = $1; - $res{'type'} = $2; - $res{'hash'} = $3; - if ($opts{'-z'}) { - $res{'name'} = $4; + $res{'mode'} = $1; + $res{'type'} = $2; + $res{'hash'} = $3; + $res{'size'} = $4; + if ($opts{'-z'}) { + $res{'name'} = $5; + } else { + $res{'name'} = unquote($5); + } } else { - $res{'name'} = unquote($4); + #'100644 blob 0fa3f3a66fb6a137f6ec2c19351ed4d807070ffa panic.c' + $line =~ m/^([0-9]+) (.+) ([0-9a-fA-F]{40})\t(.+)$/s; + + $res{'mode'} = $1; + $res{'type'} = $2; + $res{'hash'} = $3; + if ($opts{'-z'}) { + $res{'name'} = $4; + } else { + $res{'name'} = unquote($4); + } } return wantarray ? %res : \%res; } +# generates _two_ hashes, references to which are passed as 2 and 3 argument +sub parse_from_to_diffinfo { + my ($diffinfo, $from, $to, @parents) = @_; + + if ($diffinfo->{'nparents'}) { + # combined diff + $from->{'file'} = []; + $from->{'href'} = []; + fill_from_file_info($diffinfo, @parents) + unless exists $diffinfo->{'from_file'}; + for (my $i = 0; $i < $diffinfo->{'nparents'}; $i++) { + $from->{'file'}[$i] = + defined $diffinfo->{'from_file'}[$i] ? + $diffinfo->{'from_file'}[$i] : + $diffinfo->{'to_file'}; + if ($diffinfo->{'status'}[$i] ne "A") { # not new (added) file + $from->{'href'}[$i] = href(action=>"blob", + hash_base=>$parents[$i], + hash=>$diffinfo->{'from_id'}[$i], + file_name=>$from->{'file'}[$i]); + } else { + $from->{'href'}[$i] = undef; + } + } + } else { + # ordinary (not combined) diff + $from->{'file'} = $diffinfo->{'from_file'}; + if ($diffinfo->{'status'} ne "A") { # not new (added) file + $from->{'href'} = href(action=>"blob", hash_base=>$hash_parent, + hash=>$diffinfo->{'from_id'}, + file_name=>$from->{'file'}); + } else { + delete $from->{'href'}; + } + } + + $to->{'file'} = $diffinfo->{'to_file'}; + if (!is_deleted($diffinfo)) { # file exists in result + $to->{'href'} = href(action=>"blob", hash_base=>$hash, + hash=>$diffinfo->{'to_id'}, + file_name=>$to->{'file'}); + } else { + delete $to->{'href'}; + } +} + ## ...................................................................... ## parse to array of hashes functions @@ -1527,6 +2973,7 @@ sub git_get_heads_list { my ($hash, $name, $title) = split(' ', $refinfo, 3); my ($committer, $epoch, $tz) = ($committerinfo =~ /^(.*) ([0-9]+) (.*)$/); + $ref_item{'fullname'} = $name; $name =~ s!^refs/heads/!!; $ref_item{'name'} = $name; @@ -1564,6 +3011,7 @@ sub git_get_tags_list { my ($id, $type, $name, $refid, $reftype, $title) = split(' ', $refinfo, 6); my ($creator, $epoch, $tz) = ($creatorinfo =~ /^(.*) ([0-9]+) (.*)$/); + $ref_item{'fullname'} = $name; $name =~ s!^refs/tags/!!; $ref_item{'type'} = $type; @@ -1610,6 +3058,15 @@ sub get_file_owner { return to_utf8($owner); } +# assume that file exists +sub insert_file { + my $filename = shift; + + open my $fd, '<', $filename; + print map { to_utf8($_) } <$fd>; + close $fd; +} + ## ...................................................................... ## mimetype related functions @@ -1619,18 +3076,18 @@ sub mimetype_guess_file { -r $mimemap or return undef; my %mimemap; - open(MIME, $mimemap) or return undef; - while (<MIME>) { + open(my $mh, '<', $mimemap) or return undef; + while (<$mh>) { next if m/^#/; # skip comments - my ($mime, $exts) = split(/\t+/); + my ($mimetype, $exts) = split(/\t+/); if (defined $exts) { my @exts = split(/\s+/, $exts); foreach my $ext (@exts) { - $mimemap{$ext} = $mime; + $mimemap{$ext} = $mimetype; } } } - close(MIME); + close($mh); $filename =~ /\.([^.]*)$/; return $mimemap{$1}; @@ -1666,8 +3123,7 @@ sub blob_mimetype { return $default_blob_plain_mimetype unless $fd; if (-T $fd) { - return 'text/plain' . - ($default_text_plain_charset ? '; charset='.$default_text_plain_charset : ''); + return 'text/plain'; } elsif (! $filename) { return 'application/octet-stream'; } elsif ($filename =~ m/\.png$/i) { @@ -1681,6 +3137,17 @@ sub blob_mimetype { } } +sub blob_contenttype { + my ($fd, $file_name, $type) = @_; + + $type ||= blob_mimetype($fd, $file_name); + if ($type eq 'text/plain' && defined $default_text_plain_charset) { + $type .= "; charset=$default_text_plain_charset"; + } + + return $type; +} + ## ====================================================================== ## functions printing HTML: header, footer, error page @@ -1690,7 +3157,7 @@ sub git_header_html { my $title = "$site_name"; if (defined $project) { - $title .= " - $project"; + $title .= " - " . to_utf8($project); if (defined $action) { $title .= "/$action"; if (defined $file_name) { @@ -1728,9 +3195,14 @@ sub git_header_html { <meta name="robots" content="index, nofollow"/> <title>$title</title> EOF -# print out each stylesheet that exist + # the stylesheet, favicon etc urls won't work correctly with path_info + # unless we set the appropriate base URL + if ($ENV{'PATH_INFO'}) { + print "<base href=\"".esc_url($base_url)."\" />\n"; + } + # print out each stylesheet that exist, providing backwards capability + # for those people who defined $stylesheet in a config file if (defined $stylesheet) { -#provides backwards capability for those people who define style sheet in a config file print '<link rel="stylesheet" type="text/css" href="'.$stylesheet.'"/>'."\n"; } else { foreach my $stylesheet (@stylesheets) { @@ -1739,31 +3211,56 @@ EOF } } if (defined $project) { - printf('<link rel="alternate" title="%s log RSS feed" '. - 'href="%s" type="application/rss+xml" />'."\n", - esc_param($project), href(action=>"rss")); - printf('<link rel="alternate" title="%s log Atom feed" '. - 'href="%s" type="application/atom+xml" />'."\n", - esc_param($project), href(action=>"atom")); + my %href_params = get_feed_info(); + if (!exists $href_params{'-title'}) { + $href_params{'-title'} = 'log'; + } + + foreach my $format qw(RSS Atom) { + my $type = lc($format); + my %link_attr = ( + '-rel' => 'alternate', + '-title' => "$project - $href_params{'-title'} - $format feed", + '-type' => "application/$type+xml" + ); + + $href_params{'action'} = $type; + $link_attr{'-href'} = href(%href_params); + print "<link ". + "rel=\"$link_attr{'-rel'}\" ". + "title=\"$link_attr{'-title'}\" ". + "href=\"$link_attr{'-href'}\" ". + "type=\"$link_attr{'-type'}\" ". + "/>\n"; + + $href_params{'extra_options'} = '--no-merges'; + $link_attr{'-href'} = href(%href_params); + $link_attr{'-title'} .= ' (no merges)'; + print "<link ". + "rel=\"$link_attr{'-rel'}\" ". + "title=\"$link_attr{'-title'}\" ". + "href=\"$link_attr{'-href'}\" ". + "type=\"$link_attr{'-type'}\" ". + "/>\n"; + } + } else { printf('<link rel="alternate" title="%s projects list" '. - 'href="%s" type="text/plain; charset=utf-8"/>'."\n", + 'href="%s" type="text/plain; charset=utf-8" />'."\n", $site_name, href(project=>undef, action=>"project_index")); printf('<link rel="alternate" title="%s projects feeds" '. - 'href="%s" type="text/x-opml"/>'."\n", + 'href="%s" type="text/x-opml" />'."\n", $site_name, href(project=>undef, action=>"opml")); } if (defined $favicon) { - print qq(<link rel="shortcut icon" href="$favicon" type="image/png"/>\n); + print qq(<link rel="shortcut icon" href="$favicon" type="image/png" />\n); } print "</head>\n" . "<body>\n"; - if (-f $site_header) { - open (my $fd, $site_header); - print <$fd>; - close $fd; + if (defined $site_header && -f $site_header) { + insert_file($site_header); } print "<div class=\"page_header\">\n" . @@ -1778,8 +3275,10 @@ EOF } print "\n"; } - my ($have_search) = gitweb_check_feature('search'); - if ((defined $project) && ($have_search)) { + print "</div>\n"; + + my $have_search = gitweb_check_feature('search'); + if (defined $project && $have_search) { if (!defined $searchtext) { $searchtext = ""; } @@ -1791,66 +3290,135 @@ EOF } else { $search_hash = "HEAD"; } - $cgi->param("a", "search"); - $cgi->param("h", $search_hash); - $cgi->param("p", $project); - print $cgi->startform(-method => "get", -action => $my_uri) . + my $action = $my_uri; + my $use_pathinfo = gitweb_check_feature('pathinfo'); + if ($use_pathinfo) { + $action .= "/".esc_url($project); + } + print $cgi->startform(-method => "get", -action => $action) . "<div class=\"search\">\n" . - $cgi->hidden(-name => "p") . "\n" . - $cgi->hidden(-name => "a") . "\n" . - $cgi->hidden(-name => "h") . "\n" . + (!$use_pathinfo && + $cgi->input({-name=>"p", -value=>$project, -type=>"hidden"}) . "\n") . + $cgi->input({-name=>"a", -value=>"search", -type=>"hidden"}) . "\n" . + $cgi->input({-name=>"h", -value=>$search_hash, -type=>"hidden"}) . "\n" . $cgi->popup_menu(-name => 'st', -default => 'commit', - -values => ['commit', 'author', 'committer', 'pickaxe']) . + -values => ['commit', 'grep', 'author', 'committer', 'pickaxe']) . $cgi->sup($cgi->a({-href => href(action=>"search_help")}, "?")) . " search:\n", $cgi->textfield(-name => "s", -value => $searchtext) . "\n" . + "<span title=\"Extended regular expression\">" . + $cgi->checkbox(-name => 'sr', -value => 1, -label => 're', + -checked => $search_use_regexp) . + "</span>" . "</div>" . $cgi->end_form() . "\n"; } - print "</div>\n"; } sub git_footer_html { + my $feed_class = 'rss_logo'; + print "<div class=\"page_footer\">\n"; if (defined $project) { my $descr = git_get_project_description($project); if (defined $descr) { print "<div class=\"page_footer_text\">" . esc_html($descr) . "</div>\n"; } - print $cgi->a({-href => href(action=>"rss"), - -class => "rss_logo"}, "RSS") . " "; - print $cgi->a({-href => href(action=>"atom"), - -class => "rss_logo"}, "Atom") . "\n"; + + my %href_params = get_feed_info(); + if (!%href_params) { + $feed_class .= ' generic'; + } + $href_params{'-title'} ||= 'log'; + + foreach my $format qw(RSS Atom) { + $href_params{'action'} = lc($format); + print $cgi->a({-href => href(%href_params), + -title => "$href_params{'-title'} $format feed", + -class => $feed_class}, $format)."\n"; + } + } else { print $cgi->a({-href => href(project=>undef, action=>"opml"), - -class => "rss_logo"}, "OPML") . " "; + -class => $feed_class}, "OPML") . " "; print $cgi->a({-href => href(project=>undef, action=>"project_index"), - -class => "rss_logo"}, "TXT") . "\n"; + -class => $feed_class}, "TXT") . "\n"; } - print "</div>\n" ; + print "</div>\n"; # class="page_footer" - if (-f $site_footer) { - open (my $fd, $site_footer); - print <$fd>; - close $fd; + if (defined $t0 && gitweb_check_feature('timed')) { + print "<div id=\"generating_info\">\n"; + print 'This page took '. + '<span id="generating_time" class="time_span">'. + Time::HiRes::tv_interval($t0, [Time::HiRes::gettimeofday()]). + ' seconds </span>'. + ' and '. + '<span id="generating_cmd">'. + $number_of_git_cmds. + '</span> git commands '. + " to generate.\n"; + print "</div>\n"; # class="page_footer" + } + + if (defined $site_footer && -f $site_footer) { + insert_file($site_footer); + } + + print qq!<script type="text/javascript" src="$javascript"></script>\n!; + if (defined $action && + $action eq 'blame_incremental') { + print qq!<script type="text/javascript">\n!. + qq!startBlame("!. href(action=>"blame_data", -replay=>1) .qq!",\n!. + qq! "!. href() .qq!");\n!. + qq!</script>\n!; + } elsif (gitweb_check_feature('javascript-actions')) { + print qq!<script type="text/javascript">\n!. + qq!window.onload = fixLinks;\n!. + qq!</script>\n!; } print "</body>\n" . "</html>"; } +# die_error(<http_status_code>, <error_message>) +# Example: die_error(404, 'Hash not found') +# By convention, use the following status codes (as defined in RFC 2616): +# 400: Invalid or missing CGI parameters, or +# requested object exists but has wrong type. +# 403: Requested feature (like "pickaxe" or "snapshot") not enabled on +# this server or project. +# 404: Requested object/revision/project doesn't exist. +# 500: The server isn't configured properly, or +# an internal error occurred (e.g. failed assertions caused by bugs), or +# an unknown error occurred (e.g. the git binary died unexpectedly). +# 503: The server is currently unavailable (because it is overloaded, +# or down for maintenance). Generally, this is a temporary state. sub die_error { - my $status = shift || "403 Forbidden"; - my $error = shift || "Malformed query, file missing or permission denied"; - - git_header_html($status); + my $status = shift || 500; + my $error = shift || "Internal server error"; + my $extra = shift; + + my %http_responses = ( + 400 => '400 Bad Request', + 403 => '403 Forbidden', + 404 => '404 Not Found', + 500 => '500 Internal Server Error', + 503 => '503 Service Unavailable', + ); + git_header_html($http_responses{$status}); print <<EOF; <div class="page_body"> <br /><br /> $status - $error <br /> -</div> EOF + if (defined $extra) { + print "<hr />\n" . + "$extra\n"; + } + print "</div>\n"; + git_footer_html(); exit; } @@ -1870,48 +3438,62 @@ sub git_print_page_nav { my %arg = map { $_ => {action=>$_} } @navs; if (defined $head) { for (qw(commit commitdiff)) { - $arg{$_}{hash} = $head; + $arg{$_}{'hash'} = $head; } if ($current =~ m/^(tree | log | shortlog | commit | commitdiff | search)$/x) { for (qw(shortlog log)) { - $arg{$_}{hash} = $head; + $arg{$_}{'hash'} = $head; } } } - $arg{tree}{hash} = $treehead if defined $treehead; - $arg{tree}{hash_base} = $treebase if defined $treebase; + + $arg{'tree'}{'hash'} = $treehead if defined $treehead; + $arg{'tree'}{'hash_base'} = $treebase if defined $treebase; + + my @actions = gitweb_get_feature('actions'); + my %repl = ( + '%' => '%', + 'n' => $project, # project name + 'f' => $git_dir, # project path within filesystem + 'h' => $treehead || '', # current hash ('h' parameter) + 'b' => $treebase || '', # hash base ('hb' parameter) + ); + while (@actions) { + my ($label, $link, $pos) = splice(@actions,0,3); + # insert + @navs = map { $_ eq $pos ? ($_, $label) : $_ } @navs; + # munch munch + $link =~ s/%([%nfhb])/$repl{$1}/g; + $arg{$label}{'_href'} = $link; + } print "<div class=\"page_nav\">\n" . (join " | ", map { $_ eq $current ? - $_ : $cgi->a({-href => href(%{$arg{$_}})}, "$_") + $_ : $cgi->a({-href => ($arg{$_}{_href} ? $arg{$_}{_href} : href(%{$arg{$_}}))}, "$_") } @navs); print "<br/>\n$extra<br/>\n" . "</div>\n"; } sub format_paging_nav { - my ($action, $hash, $head, $page, $nrevs) = @_; + my ($action, $page, $has_next_link) = @_; my $paging_nav; - if ($hash ne $head || $page) { - $paging_nav .= $cgi->a({-href => href(action=>$action)}, "HEAD"); - } else { - $paging_nav .= "HEAD"; - } - if ($page > 0) { - $paging_nav .= " ⋅ " . - $cgi->a({-href => href(action=>$action, hash=>$hash, page=>$page-1), + $paging_nav .= + $cgi->a({-href => href(-replay=>1, page=>undef)}, "first") . + " ⋅ " . + $cgi->a({-href => href(-replay=>1, page=>$page-1), -accesskey => "p", -title => "Alt-p"}, "prev"); } else { - $paging_nav .= " ⋅ prev"; + $paging_nav .= "first ⋅ prev"; } - if ($nrevs >= (100 * ($page+1)-1)) { + if ($has_next_link) { $paging_nav .= " ⋅ " . - $cgi->a({-href => href(action=>$action, hash=>$hash, page=>$page+1), + $cgi->a({-href => href(-replay=>1, page=>$page+1), -accesskey => "n", -title => "Alt-n"}, "next"); } else { $paging_nav .= " ⋅ next"; @@ -1927,9 +3509,9 @@ sub git_print_header_div { my ($action, $title, $hash, $hash_base) = @_; my %args = (); - $args{action} = $action; - $args{hash} = $hash if $hash; - $args{hash_base} = $hash_base if $hash_base; + $args{'action'} = $action; + $args{'hash'} = $hash if $hash; + $args{'hash_base'} = $hash_base if $hash_base; print "<div class=\"header\">\n" . $cgi->a({-href => href(%args), -class => "title"}, @@ -1937,22 +3519,66 @@ sub git_print_header_div { "\n</div>\n"; } -#sub git_print_authorship (\%) { +sub print_local_time { + print format_local_time(@_); +} + +sub format_local_time { + my $localtime = ''; + my %date = @_; + if ($date{'hour_local'} < 6) { + $localtime .= sprintf(" (<span class=\"atnight\">%02d:%02d</span> %s)", + $date{'hour_local'}, $date{'minute_local'}, $date{'tz_local'}); + } else { + $localtime .= sprintf(" (%02d:%02d %s)", + $date{'hour_local'}, $date{'minute_local'}, $date{'tz_local'}); + } + + return $localtime; +} + +# Outputs the author name and date in long form sub git_print_authorship { my $co = shift; + my %opts = @_; + my $tag = $opts{-tag} || 'div'; + my $author = $co->{'author_name'}; my %ad = parse_date($co->{'author_epoch'}, $co->{'author_tz'}); - print "<div class=\"author_date\">" . - esc_html($co->{'author_name'}) . + print "<$tag class=\"author_date\">" . + format_search_author($author, "author", esc_html($author)) . " [$ad{'rfc2822'}"; - if ($ad{'hour_local'} < 6) { - printf(" (<span class=\"atnight\">%02d:%02d</span> %s)", - $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}); - } else { - printf(" (%02d:%02d %s)", - $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}); + print_local_time(%ad) if ($opts{-localtime}); + print "]" . git_get_avatar($co->{'author_email'}, -pad_before => 1) + . "</$tag>\n"; +} + +# Outputs table rows containing the full author or committer information, +# in the format expected for 'commit' view (& similia). +# Parameters are a commit hash reference, followed by the list of people +# to output information for. If the list is empty it defalts to both +# author and committer. +sub git_print_authorship_rows { + my $co = shift; + # too bad we can't use @people = @_ || ('author', 'committer') + my @people = @_; + @people = ('author', 'committer') unless @people; + foreach my $who (@people) { + my %wd = parse_date($co->{"${who}_epoch"}, $co->{"${who}_tz"}); + print "<tr><td>$who</td><td>" . + format_search_author($co->{"${who}_name"}, $who, + esc_html($co->{"${who}_name"})) . " " . + format_search_author($co->{"${who}_email"}, $who, + esc_html("<" . $co->{"${who}_email"} . ">")) . + "</td><td rowspan=\"2\">" . + git_get_avatar($co->{"${who}_email"}, -size => 'double') . + "</td></tr>\n" . + "<tr>" . + "<td></td><td> $wd{'rfc2822'}"; + print_local_time(%wd); + print "</td>" . + "</tr>\n"; } - print "]</div>\n"; } sub git_print_page_path { @@ -1963,7 +3589,7 @@ sub git_print_page_path { print "<div class=\"page_path\">"; print $cgi->a({-href => href(action=>"tree", hash_base=>$hb), - -title => 'tree root'}, "[$project]"); + -title => 'tree root'}, to_utf8("[$project]")); print " / "; if (defined $name) { my @dirname = split '/', $name; @@ -1974,17 +3600,17 @@ sub git_print_page_path { $fullname .= ($fullname ? '/' : '') . $dir; print $cgi->a({-href => href(action=>"tree", file_name=>$fullname, hash_base=>$hb), - -title => esc_html($fullname)}, esc_path($dir)); + -title => $fullname}, esc_path($dir)); print " / "; } if (defined $type && $type eq 'blob') { print $cgi->a({-href => href(action=>"blob_plain", file_name=>$file_name, hash_base=>$hb), - -title => esc_html($name)}, esc_path($basename)); + -title => $name}, esc_path($basename)); } elsif (defined $type && $type eq 'tree') { print $cgi->a({-href => href(action=>"tree", file_name=>$file_name, hash_base=>$hb), - -title => esc_html($name)}, esc_path($basename)); + -title => $name}, esc_path($basename)); print " / "; } else { print esc_path($basename); @@ -1993,8 +3619,7 @@ sub git_print_page_path { print "<br/></div>\n"; } -# sub git_print_log (\@;%) { -sub git_print_log ($;%) { +sub git_print_log { my $log = shift; my %opts = @_; @@ -2052,7 +3677,7 @@ sub git_get_link_target { open my $fd, "-|", git_cmd(), "cat-file", "blob", $hash or return; { - local $/; + local $/ = undef; $link_target = <$fd>; } close $fd @@ -2065,10 +3690,7 @@ sub git_get_link_target { # return target of link relative to top directory (top tree); # return undef if it is not possible (including absolute links). sub normalize_link_target { - my ($link_target, $basedir, $hash_base) = @_; - - # we can normalize symlink target only if $hash_base is provided - return unless $hash_base; + my ($link_target, $basedir) = @_; # absolute symlinks (beginning with '/') cannot be normalized return if (substr($link_target, 0, 1) eq '/'); @@ -2116,6 +3738,9 @@ sub git_print_tree_entry { # and link is the action links of the entry. print "<td class=\"mode\">" . mode_str($t->{'mode'}) . "</td>\n"; + if (exists $t->{'size'}) { + print "<td class=\"size\">$t->{'size'}</td>\n"; + } if ($t->{'type'} eq "blob") { print "<td class=\"list\">" . $cgi->a({-href => href(action=>"blob", hash=>$t->{'hash'}, @@ -2124,7 +3749,7 @@ sub git_print_tree_entry { if (S_ISLNK(oct $t->{'mode'})) { my $link_target = git_get_link_target($t->{'hash'}); if ($link_target) { - my $norm_target = normalize_link_target($link_target, $basedir, $hash_base); + my $norm_target = normalize_link_target($link_target, $basedir); if (defined $norm_target) { print " -> " . $cgi->a({-href => href(action=>"object", hash_base=>$hash_base, @@ -2161,12 +3786,14 @@ sub git_print_tree_entry { } elsif ($t->{'type'} eq "tree") { print "<td class=\"list\">"; print $cgi->a({-href => href(action=>"tree", hash=>$t->{'hash'}, - file_name=>"$basedir$t->{'name'}", %base_key)}, + file_name=>"$basedir$t->{'name'}", + %base_key)}, esc_path($t->{'name'})); print "</td>\n"; print "<td class=\"link\">"; print $cgi->a({-href => href(action=>"tree", hash=>$t->{'hash'}, - file_name=>"$basedir$t->{'name'}", %base_key)}, + file_name=>"$basedir$t->{'name'}", + %base_key)}, "tree"); if (defined $hash_base) { print " | " . @@ -2175,26 +3802,99 @@ sub git_print_tree_entry { "history"); } print "</td>\n"; + } else { + # unknown object: we can only present history for it + # (this includes 'commit' object, i.e. submodule support) + print "<td class=\"list\">" . + esc_path($t->{'name'}) . + "</td>\n"; + print "<td class=\"link\">"; + if (defined $hash_base) { + print $cgi->a({-href => href(action=>"history", + hash_base=>$hash_base, + file_name=>"$basedir$t->{'name'}")}, + "history"); + } + print "</td>\n"; } } ## ...................................................................... ## functions printing large fragments of HTML +# get pre-image filenames for merge (combined) diff +sub fill_from_file_info { + my ($diff, @parents) = @_; + + $diff->{'from_file'} = [ ]; + $diff->{'from_file'}[$diff->{'nparents'} - 1] = undef; + for (my $i = 0; $i < $diff->{'nparents'}; $i++) { + if ($diff->{'status'}[$i] eq 'R' || + $diff->{'status'}[$i] eq 'C') { + $diff->{'from_file'}[$i] = + git_get_path_by_hash($parents[$i], $diff->{'from_id'}[$i]); + } + } + + return $diff; +} + +# is current raw difftree line of file deletion +sub is_deleted { + my $diffinfo = shift; + + return $diffinfo->{'to_id'} eq ('0' x 40); +} + +# does patch correspond to [previous] difftree raw line +# $diffinfo - hashref of parsed raw diff format +# $patchinfo - hashref of parsed patch diff format +# (the same keys as in $diffinfo) +sub is_patch_split { + my ($diffinfo, $patchinfo) = @_; + + return defined $diffinfo && defined $patchinfo + && $diffinfo->{'to_file'} eq $patchinfo->{'to_file'}; +} + + sub git_difftree_body { - my ($difftree, $hash, $parent) = @_; - my ($have_blame) = gitweb_check_feature('blame'); + my ($difftree, $hash, @parents) = @_; + my ($parent) = $parents[0]; + my $have_blame = gitweb_check_feature('blame'); print "<div class=\"list_head\">\n"; if ($#{$difftree} > 10) { print(($#{$difftree} + 1) . " files changed:\n"); } print "</div>\n"; - print "<table class=\"diff_tree\">\n"; + print "<table class=\"" . + (@parents > 1 ? "combined " : "") . + "diff_tree\">\n"; + + # header only for combined diff in 'commitdiff' view + my $has_header = @$difftree && @parents > 1 && $action eq 'commitdiff'; + if ($has_header) { + # table header + print "<thead><tr>\n" . + "<th></th><th></th>\n"; # filename, patchN link + for (my $i = 0; $i < @parents; $i++) { + my $par = $parents[$i]; + print "<th>" . + $cgi->a({-href => href(action=>"commitdiff", + hash=>$hash, hash_parent=>$par), + -title => 'commitdiff to parent number ' . + ($i+1) . ': ' . substr($par,0,7)}, + $i+1) . + " </th>\n"; + } + print "</tr></thead>\n<tbody>\n"; + } + my $alternate = 1; my $patchno = 0; foreach my $line (@{$difftree}) { - my %diff = parse_difftree_raw_line($line); + my $diff = parsed_difftree_line($line); if ($alternate) { print "<tr class=\"dark\">\n"; @@ -2203,31 +3903,120 @@ sub git_difftree_body { } $alternate ^= 1; + if (exists $diff->{'nparents'}) { # combined diff + + fill_from_file_info($diff, @parents) + unless exists $diff->{'from_file'}; + + if (!is_deleted($diff)) { + # file exists in the result (child) commit + print "<td>" . + $cgi->a({-href => href(action=>"blob", hash=>$diff->{'to_id'}, + file_name=>$diff->{'to_file'}, + hash_base=>$hash), + -class => "list"}, esc_path($diff->{'to_file'})) . + "</td>\n"; + } else { + print "<td>" . + esc_path($diff->{'to_file'}) . + "</td>\n"; + } + + if ($action eq 'commitdiff') { + # link to patch + $patchno++; + print "<td class=\"link\">" . + $cgi->a({-href => "#patch$patchno"}, "patch") . + " | " . + "</td>\n"; + } + + my $has_history = 0; + my $not_deleted = 0; + for (my $i = 0; $i < $diff->{'nparents'}; $i++) { + my $hash_parent = $parents[$i]; + my $from_hash = $diff->{'from_id'}[$i]; + my $from_path = $diff->{'from_file'}[$i]; + my $status = $diff->{'status'}[$i]; + + $has_history ||= ($status ne 'A'); + $not_deleted ||= ($status ne 'D'); + + if ($status eq 'A') { + print "<td class=\"link\" align=\"right\"> | </td>\n"; + } elsif ($status eq 'D') { + print "<td class=\"link\">" . + $cgi->a({-href => href(action=>"blob", + hash_base=>$hash, + hash=>$from_hash, + file_name=>$from_path)}, + "blob" . ($i+1)) . + " | </td>\n"; + } else { + if ($diff->{'to_id'} eq $from_hash) { + print "<td class=\"link nochange\">"; + } else { + print "<td class=\"link\">"; + } + print $cgi->a({-href => href(action=>"blobdiff", + hash=>$diff->{'to_id'}, + hash_parent=>$from_hash, + hash_base=>$hash, + hash_parent_base=>$hash_parent, + file_name=>$diff->{'to_file'}, + file_parent=>$from_path)}, + "diff" . ($i+1)) . + " | </td>\n"; + } + } + + print "<td class=\"link\">"; + if ($not_deleted) { + print $cgi->a({-href => href(action=>"blob", + hash=>$diff->{'to_id'}, + file_name=>$diff->{'to_file'}, + hash_base=>$hash)}, + "blob"); + print " | " if ($has_history); + } + if ($has_history) { + print $cgi->a({-href => href(action=>"history", + file_name=>$diff->{'to_file'}, + hash_base=>$hash)}, + "history"); + } + print "</td>\n"; + + print "</tr>\n"; + next; # instead of 'else' clause, to avoid extra indent + } + # else ordinary diff + my ($to_mode_oct, $to_mode_str, $to_file_type); my ($from_mode_oct, $from_mode_str, $from_file_type); - if ($diff{'to_mode'} ne ('0' x 6)) { - $to_mode_oct = oct $diff{'to_mode'}; + if ($diff->{'to_mode'} ne ('0' x 6)) { + $to_mode_oct = oct $diff->{'to_mode'}; if (S_ISREG($to_mode_oct)) { # only for regular file $to_mode_str = sprintf("%04o", $to_mode_oct & 0777); # permission bits } - $to_file_type = file_type($diff{'to_mode'}); + $to_file_type = file_type($diff->{'to_mode'}); } - if ($diff{'from_mode'} ne ('0' x 6)) { - $from_mode_oct = oct $diff{'from_mode'}; + if ($diff->{'from_mode'} ne ('0' x 6)) { + $from_mode_oct = oct $diff->{'from_mode'}; if (S_ISREG($to_mode_oct)) { # only for regular file $from_mode_str = sprintf("%04o", $from_mode_oct & 0777); # permission bits } - $from_file_type = file_type($diff{'from_mode'}); + $from_file_type = file_type($diff->{'from_mode'}); } - if ($diff{'status'} eq "A") { # created + if ($diff->{'status'} eq "A") { # created my $mode_chng = "<span class=\"file_status new\">[new $to_file_type"; $mode_chng .= " with mode: $to_mode_str" if $to_mode_str; $mode_chng .= "]</span>"; print "<td>"; - print $cgi->a({-href => href(action=>"blob", hash=>$diff{'to_id'}, - hash_base=>$hash, file_name=>$diff{'file'}), - -class => "list"}, esc_path($diff{'file'})); + print $cgi->a({-href => href(action=>"blob", hash=>$diff->{'to_id'}, + hash_base=>$hash, file_name=>$diff->{'file'}), + -class => "list"}, esc_path($diff->{'file'})); print "</td>\n"; print "<td>$mode_chng</td>\n"; print "<td class=\"link\">"; @@ -2237,17 +4026,17 @@ sub git_difftree_body { print $cgi->a({-href => "#patch$patchno"}, "patch"); print " | "; } - print $cgi->a({-href => href(action=>"blob", hash=>$diff{'to_id'}, - hash_base=>$hash, file_name=>$diff{'file'})}, + print $cgi->a({-href => href(action=>"blob", hash=>$diff->{'to_id'}, + hash_base=>$hash, file_name=>$diff->{'file'})}, "blob"); print "</td>\n"; - } elsif ($diff{'status'} eq "D") { # deleted + } elsif ($diff->{'status'} eq "D") { # deleted my $mode_chng = "<span class=\"file_status deleted\">[deleted $from_file_type]</span>"; print "<td>"; - print $cgi->a({-href => href(action=>"blob", hash=>$diff{'from_id'}, - hash_base=>$parent, file_name=>$diff{'file'}), - -class => "list"}, esc_path($diff{'file'})); + print $cgi->a({-href => href(action=>"blob", hash=>$diff->{'from_id'}, + hash_base=>$parent, file_name=>$diff->{'file'}), + -class => "list"}, esc_path($diff->{'file'})); print "</td>\n"; print "<td>$mode_chng</td>\n"; print "<td class=\"link\">"; @@ -2257,22 +4046,22 @@ sub git_difftree_body { print $cgi->a({-href => "#patch$patchno"}, "patch"); print " | "; } - print $cgi->a({-href => href(action=>"blob", hash=>$diff{'from_id'}, - hash_base=>$parent, file_name=>$diff{'file'})}, + print $cgi->a({-href => href(action=>"blob", hash=>$diff->{'from_id'}, + hash_base=>$parent, file_name=>$diff->{'file'})}, "blob") . " | "; if ($have_blame) { print $cgi->a({-href => href(action=>"blame", hash_base=>$parent, - file_name=>$diff{'file'})}, + file_name=>$diff->{'file'})}, "blame") . " | "; } print $cgi->a({-href => href(action=>"history", hash_base=>$parent, - file_name=>$diff{'file'})}, + file_name=>$diff->{'file'})}, "history"); print "</td>\n"; - } elsif ($diff{'status'} eq "M" || $diff{'status'} eq "T") { # modified, or type changed + } elsif ($diff->{'status'} eq "M" || $diff->{'status'} eq "T") { # modified, or type changed my $mode_chnge = ""; - if ($diff{'from_mode'} != $diff{'to_mode'}) { + if ($diff->{'from_mode'} != $diff->{'to_mode'}) { $mode_chnge = "<span class=\"file_status mode_chnge\">[changed"; if ($from_file_type ne $to_file_type) { $mode_chnge .= " from $from_file_type to $to_file_type"; @@ -2287,9 +4076,9 @@ sub git_difftree_body { $mode_chnge .= "]</span>\n"; } print "<td>"; - print $cgi->a({-href => href(action=>"blob", hash=>$diff{'to_id'}, - hash_base=>$hash, file_name=>$diff{'file'}), - -class => "list"}, esc_path($diff{'file'})); + print $cgi->a({-href => href(action=>"blob", hash=>$diff->{'to_id'}, + hash_base=>$hash, file_name=>$diff->{'file'}), + -class => "list"}, esc_path($diff->{'file'})); print "</td>\n"; print "<td>$mode_chnge</td>\n"; print "<td class=\"link\">"; @@ -2298,85 +4087,90 @@ sub git_difftree_body { $patchno++; print $cgi->a({-href => "#patch$patchno"}, "patch") . " | "; - } elsif ($diff{'to_id'} ne $diff{'from_id'}) { + } elsif ($diff->{'to_id'} ne $diff->{'from_id'}) { # "commit" view and modified file (not onlu mode changed) print $cgi->a({-href => href(action=>"blobdiff", - hash=>$diff{'to_id'}, hash_parent=>$diff{'from_id'}, + hash=>$diff->{'to_id'}, hash_parent=>$diff->{'from_id'}, hash_base=>$hash, hash_parent_base=>$parent, - file_name=>$diff{'file'})}, + file_name=>$diff->{'file'})}, "diff") . " | "; } - print $cgi->a({-href => href(action=>"blob", hash=>$diff{'to_id'}, - hash_base=>$hash, file_name=>$diff{'file'})}, + print $cgi->a({-href => href(action=>"blob", hash=>$diff->{'to_id'}, + hash_base=>$hash, file_name=>$diff->{'file'})}, "blob") . " | "; if ($have_blame) { print $cgi->a({-href => href(action=>"blame", hash_base=>$hash, - file_name=>$diff{'file'})}, + file_name=>$diff->{'file'})}, "blame") . " | "; } print $cgi->a({-href => href(action=>"history", hash_base=>$hash, - file_name=>$diff{'file'})}, + file_name=>$diff->{'file'})}, "history"); print "</td>\n"; - } elsif ($diff{'status'} eq "R" || $diff{'status'} eq "C") { # renamed or copied + } elsif ($diff->{'status'} eq "R" || $diff->{'status'} eq "C") { # renamed or copied my %status_name = ('R' => 'moved', 'C' => 'copied'); - my $nstatus = $status_name{$diff{'status'}}; + my $nstatus = $status_name{$diff->{'status'}}; my $mode_chng = ""; - if ($diff{'from_mode'} != $diff{'to_mode'}) { + if ($diff->{'from_mode'} != $diff->{'to_mode'}) { # mode also for directories, so we cannot use $to_mode_str $mode_chng = sprintf(", mode: %04o", $to_mode_oct & 0777); } print "<td>" . $cgi->a({-href => href(action=>"blob", hash_base=>$hash, - hash=>$diff{'to_id'}, file_name=>$diff{'to_file'}), - -class => "list"}, esc_path($diff{'to_file'})) . "</td>\n" . + hash=>$diff->{'to_id'}, file_name=>$diff->{'to_file'}), + -class => "list"}, esc_path($diff->{'to_file'})) . "</td>\n" . "<td><span class=\"file_status $nstatus\">[$nstatus from " . $cgi->a({-href => href(action=>"blob", hash_base=>$parent, - hash=>$diff{'from_id'}, file_name=>$diff{'from_file'}), - -class => "list"}, esc_path($diff{'from_file'})) . - " with " . (int $diff{'similarity'}) . "% similarity$mode_chng]</span></td>\n" . + hash=>$diff->{'from_id'}, file_name=>$diff->{'from_file'}), + -class => "list"}, esc_path($diff->{'from_file'})) . + " with " . (int $diff->{'similarity'}) . "% similarity$mode_chng]</span></td>\n" . "<td class=\"link\">"; if ($action eq 'commitdiff') { # link to patch $patchno++; print $cgi->a({-href => "#patch$patchno"}, "patch") . " | "; - } elsif ($diff{'to_id'} ne $diff{'from_id'}) { + } elsif ($diff->{'to_id'} ne $diff->{'from_id'}) { # "commit" view and modified file (not only pure rename or copy) print $cgi->a({-href => href(action=>"blobdiff", - hash=>$diff{'to_id'}, hash_parent=>$diff{'from_id'}, + hash=>$diff->{'to_id'}, hash_parent=>$diff->{'from_id'}, hash_base=>$hash, hash_parent_base=>$parent, - file_name=>$diff{'to_file'}, file_parent=>$diff{'from_file'})}, + file_name=>$diff->{'to_file'}, file_parent=>$diff->{'from_file'})}, "diff") . " | "; } - print $cgi->a({-href => href(action=>"blob", hash=>$diff{'to_id'}, - hash_base=>$parent, file_name=>$diff{'to_file'})}, + print $cgi->a({-href => href(action=>"blob", hash=>$diff->{'to_id'}, + hash_base=>$parent, file_name=>$diff->{'to_file'})}, "blob") . " | "; if ($have_blame) { print $cgi->a({-href => href(action=>"blame", hash_base=>$hash, - file_name=>$diff{'to_file'})}, + file_name=>$diff->{'to_file'})}, "blame") . " | "; } print $cgi->a({-href => href(action=>"history", hash_base=>$hash, - file_name=>$diff{'to_file'})}, + file_name=>$diff->{'to_file'})}, "history"); print "</td>\n"; } # we should not encounter Unmerged (U) or Unknown (X) status print "</tr>\n"; } + print "</tbody>" if $has_header; print "</table>\n"; } sub git_patchset_body { - my ($fd, $difftree, $hash, $hash_parent) = @_; + my ($fd, $difftree, $hash, @hash_parents) = @_; + my ($hash_parent) = $hash_parents[0]; + my $is_combined = (@hash_parents > 1); my $patch_idx = 0; + my $patch_number = 0; my $patch_line; my $diffinfo; + my $to_name; my (%from, %to); print "<div class=\"patchset\">\n"; @@ -2390,160 +4184,92 @@ sub git_patchset_body { PATCH: while ($patch_line) { - my @diff_header; - my ($from_id, $to_id); - - # git diff header - #assert($patch_line =~ m/^diff /) if DEBUG; - #assert($patch_line !~ m!$/$!) if DEBUG; # is chomp-ed - push @diff_header, $patch_line; - # extended diff header - EXTENDED_HEADER: - while ($patch_line = <$fd>) { - chomp $patch_line; - - last EXTENDED_HEADER if ($patch_line =~ m/^--- |^diff /); - - if ($patch_line =~ m/^index ([0-9a-fA-F]{40})..([0-9a-fA-F]{40})/) { - $from_id = $1; - $to_id = $2; - } - - push @diff_header, $patch_line; + # parse "git diff" header line + if ($patch_line =~ m/^diff --git (\"(?:[^\\\"]*(?:\\.[^\\\"]*)*)\"|[^ "]*) (.*)$/) { + # $1 is from_name, which we do not use + $to_name = unquote($2); + $to_name =~ s!^b/!!; + } elsif ($patch_line =~ m/^diff --(cc|combined) ("?.*"?)$/) { + # $1 is 'cc' or 'combined', which we do not use + $to_name = unquote($2); + } else { + $to_name = undef; } - my $last_patch_line = $patch_line; # check if current patch belong to current raw line # and parse raw git-diff line if needed - if (defined $diffinfo && - $diffinfo->{'from_id'} eq $from_id && - $diffinfo->{'to_id'} eq $to_id) { - # this is split patch + if (is_patch_split($diffinfo, { 'to_file' => $to_name })) { + # this is continuation of a split patch print "<div class=\"patch cont\">\n"; } else { # advance raw git-diff output if needed $patch_idx++ if defined $diffinfo; # read and prepare patch information - if (ref($difftree->[$patch_idx]) eq "HASH") { - # pre-parsed (or generated by hand) - $diffinfo = $difftree->[$patch_idx]; - } else { - $diffinfo = parse_difftree_raw_line($difftree->[$patch_idx]); - } - $from{'file'} = $diffinfo->{'from_file'} || $diffinfo->{'file'}; - $to{'file'} = $diffinfo->{'to_file'} || $diffinfo->{'file'}; - if ($diffinfo->{'status'} ne "A") { # not new (added) file - $from{'href'} = href(action=>"blob", hash_base=>$hash_parent, - hash=>$diffinfo->{'from_id'}, - file_name=>$from{'file'}); - } else { - delete $from{'href'}; - } - if ($diffinfo->{'status'} ne "D") { # not deleted file - $to{'href'} = href(action=>"blob", hash_base=>$hash, - hash=>$diffinfo->{'to_id'}, - file_name=>$to{'file'}); - } else { - delete $to{'href'}; + $diffinfo = parsed_difftree_line($difftree->[$patch_idx]); + + # compact combined diff output can have some patches skipped + # find which patch (using pathname of result) we are at now; + if ($is_combined) { + while ($to_name ne $diffinfo->{'to_file'}) { + print "<div class=\"patch\" id=\"patch". ($patch_idx+1) ."\">\n" . + format_diff_cc_simplified($diffinfo, @hash_parents) . + "</div>\n"; # class="patch" + + $patch_idx++; + $patch_number++; + + last if $patch_idx > $#$difftree; + $diffinfo = parsed_difftree_line($difftree->[$patch_idx]); + } } + + # modifies %from, %to hashes + parse_from_to_diffinfo($diffinfo, \%from, \%to, @hash_parents); + # this is first patch for raw difftree line with $patch_idx index # we index @$difftree array from 0, but number patches from 1 print "<div class=\"patch\" id=\"patch". ($patch_idx+1) ."\">\n"; } + # git diff header + #assert($patch_line =~ m/^diff /) if DEBUG; + #assert($patch_line !~ m!$/$!) if DEBUG; # is chomp-ed + $patch_number++; # print "git diff" header - $patch_line = shift @diff_header; - $patch_line =~ s!^(diff (.*?) )"?a/.*$!$1!; - if ($from{'href'}) { - $patch_line .= $cgi->a({-href => $from{'href'}, -class => "path"}, - 'a/' . esc_path($from{'file'})); - } else { # file was added - $patch_line .= 'a/' . esc_path($from{'file'}); - } - $patch_line .= ' '; - if ($to{'href'}) { - $patch_line .= $cgi->a({-href => $to{'href'}, -class => "path"}, - 'b/' . esc_path($to{'file'})); - } else { # file was deleted - $patch_line .= 'b/' . esc_path($to{'file'}); - } - print "<div class=\"diff header\">$patch_line</div>\n"; + print format_git_diff_header_line($patch_line, $diffinfo, + \%from, \%to); # print extended diff header - print "<div class=\"diff extended_header\">\n" if (@diff_header > 0); + print "<div class=\"diff extended_header\">\n"; EXTENDED_HEADER: - foreach $patch_line (@diff_header) { - # match <path> - if ($patch_line =~ s!^((copy|rename) from ).*$!$1! && $from{'href'}) { - $patch_line .= $cgi->a({-href=>$from{'href'}, -class=>"path"}, - esc_path($from{'file'})); - } - if ($patch_line =~ s!^((copy|rename) to ).*$!$1! && $to{'href'}) { - $patch_line .= $cgi->a({-href=>$to{'href'}, -class=>"path"}, - esc_path($to{'file'})); - } - # match <mode> - if ($patch_line =~ m/\s(\d{6})$/) { - $patch_line .= '<span class="info"> (' . - file_type_long($1) . - ')</span>'; - } - # match <hash> - if ($patch_line =~ m/^index/) { - my ($from_link, $to_link); - if ($from{'href'}) { - $from_link = $cgi->a({-href=>$from{'href'}, -class=>"hash"}, - substr($diffinfo->{'from_id'},0,7)); - } else { - $from_link = '0' x 7; - } - if ($to{'href'}) { - $to_link = $cgi->a({-href=>$to{'href'}, -class=>"hash"}, - substr($diffinfo->{'to_id'},0,7)); - } else { - $to_link = '0' x 7; - } - #affirm { - # my ($from_hash, $to_hash) = - # ($patch_line =~ m/^index ([0-9a-fA-F]{40})..([0-9a-fA-F]{40})/); - # my ($from_id, $to_id) = - # ($diffinfo->{'from_id'}, $diffinfo->{'to_id'}); - # ($from_hash eq $from_id) && ($to_hash eq $to_id); - #} if DEBUG; - my ($from_id, $to_id) = ($diffinfo->{'from_id'}, $diffinfo->{'to_id'}); - $patch_line =~ s!$from_id\.\.$to_id!$from_link..$to_link!; - } - print $patch_line . "<br/>\n"; + while ($patch_line = <$fd>) { + chomp $patch_line; + + last EXTENDED_HEADER if ($patch_line =~ m/^--- |^diff /); + + print format_extended_diff_header_line($patch_line, $diffinfo, + \%from, \%to); } - print "</div>\n" if (@diff_header > 0); # class="diff extended_header" + print "</div>\n"; # class="diff extended_header" # from-file/to-file diff header - $patch_line = $last_patch_line; if (! $patch_line) { print "</div>\n"; # class="patch" last PATCH; } next PATCH if ($patch_line =~ m/^diff /); #assert($patch_line =~ m/^---/) if DEBUG; - if ($from{'href'} && $patch_line =~ m!^--- "?a/!) { - $patch_line = '--- a/' . - $cgi->a({-href=>$from{'href'}, -class=>"path"}, - esc_path($from{'file'})); - } - print "<div class=\"diff from_file\">$patch_line</div>\n"; + my $last_patch_line = $patch_line; $patch_line = <$fd>; chomp $patch_line; + #assert($patch_line =~ m/^\+\+\+/) if DEBUG; - #assert($patch_line =~ m/^+++/) if DEBUG; - if ($to{'href'} && $patch_line =~ m!^\+\+\+ "?b/!) { - $patch_line = '+++ b/' . - $cgi->a({-href=>$to{'href'}, -class=>"path"}, - esc_path($to{'file'})); - } - print "<div class=\"diff to_file\">$patch_line</div>\n"; + print format_diff_from_to_header($last_patch_line, $patch_line, + $diffinfo, \%from, \%to, + @hash_parents); # the patch itself LINE: @@ -2559,30 +4285,58 @@ sub git_patchset_body { print "</div>\n"; # class="patch" } + # for compact combined (--cc) format, with chunk and patch simpliciaction + # patchset might be empty, but there might be unprocessed raw lines + for (++$patch_idx if $patch_number > 0; + $patch_idx < @$difftree; + ++$patch_idx) { + # read and prepare patch information + $diffinfo = parsed_difftree_line($difftree->[$patch_idx]); + + # generate anchor for "patch" links in difftree / whatchanged part + print "<div class=\"patch\" id=\"patch". ($patch_idx+1) ."\">\n" . + format_diff_cc_simplified($diffinfo, @hash_parents) . + "</div>\n"; # class="patch" + + $patch_number++; + } + + if ($patch_number == 0) { + if (@hash_parents > 1) { + print "<div class=\"diff nodifferences\">Trivial merge</div>\n"; + } else { + print "<div class=\"diff nodifferences\">No differences found</div>\n"; + } + } + print "</div>\n"; # class="patchset" } # . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . -sub git_project_list_body { - my ($projlist, $order, $from, $to, $extra, $no_header) = @_; - - my ($check_forks) = gitweb_check_feature('forks'); - +# fills project list info (age, description, owner, forks) for each +# project in the list, removing invalid projects from returned list +# NOTE: modifies $projlist, but does not remove entries from it +sub fill_project_list_info { + my ($projlist, $check_forks) = @_; my @projects; + + my $show_ctags = gitweb_check_feature('ctags'); + PROJECT: foreach my $pr (@$projlist) { - my (@aa) = git_get_last_activity($pr->{'path'}); - unless (@aa) { - next; + my (@activity) = git_get_last_activity($pr->{'path'}); + unless (@activity) { + next PROJECT; } - ($pr->{'age'}, $pr->{'age_string'}) = @aa; + ($pr->{'age'}, $pr->{'age_string'}) = @activity; if (!defined $pr->{'descr'}) { my $descr = git_get_project_description($pr->{'path'}) || ""; - $pr->{'descr_long'} = to_utf8($descr); - $pr->{'descr'} = chop_str($descr, 25, 5); + $descr = to_utf8($descr); + $pr->{'descr_long'} = $descr; + $pr->{'descr'} = chop_str($descr, $projects_list_description_width, 5); } if (!defined $pr->{'owner'}) { - $pr->{'owner'} = get_file_owner("$projectroot/$pr->{'path'}") || ""; + $pr->{'owner'} = git_get_project_owner("$pr->{'path'}") || ""; } if ($check_forks) { my $pname = $pr->{'path'}; @@ -2590,66 +4344,105 @@ sub git_project_list_body { ($pname !~ /\/$/) && (-d "$projectroot/$pname")) { $pr->{'forks'} = "-d $projectroot/$pname"; - } - else { + } else { $pr->{'forks'} = 0; } } + $show_ctags and $pr->{'ctags'} = git_get_project_ctags($pr->{'path'}); push @projects, $pr; } - $order ||= "project"; + return @projects; +} + +# print 'sort by' <th> element, generating 'sort by $name' replay link +# if that order is not selected +sub print_sort_th { + print format_sort_th(@_); +} + +sub format_sort_th { + my ($name, $order, $header) = @_; + my $sort_th = ""; + $header ||= ucfirst($name); + + if ($order eq $name) { + $sort_th .= "<th>$header</th>\n"; + } else { + $sort_th .= "<th>" . + $cgi->a({-href => href(-replay=>1, order=>$name), + -class => "header"}, $header) . + "</th>\n"; + } + + return $sort_th; +} + +sub git_project_list_body { + # actually uses global variable $project + my ($projlist, $order, $from, $to, $extra, $no_header) = @_; + + my $check_forks = gitweb_check_feature('forks'); + my @projects = fill_project_list_info($projlist, $check_forks); + + $order ||= $default_projects_order; $from = 0 unless defined $from; $to = $#projects if (!defined $to || $#projects < $to); + my %order_info = ( + project => { key => 'path', type => 'str' }, + descr => { key => 'descr_long', type => 'str' }, + owner => { key => 'owner', type => 'str' }, + age => { key => 'age', type => 'num' } + ); + my $oi = $order_info{$order}; + if ($oi->{'type'} eq 'str') { + @projects = sort {$a->{$oi->{'key'}} cmp $b->{$oi->{'key'}}} @projects; + } else { + @projects = sort {$a->{$oi->{'key'}} <=> $b->{$oi->{'key'}}} @projects; + } + + my $show_ctags = gitweb_check_feature('ctags'); + if ($show_ctags) { + my %ctags; + foreach my $p (@projects) { + foreach my $ct (keys %{$p->{'ctags'}}) { + $ctags{$ct} += $p->{'ctags'}->{$ct}; + } + } + my $cloud = git_populate_project_tagcloud(\%ctags); + print git_show_project_tagcloud($cloud, 64); + } + print "<table class=\"project_list\">\n"; unless ($no_header) { print "<tr>\n"; if ($check_forks) { print "<th></th>\n"; } - if ($order eq "project") { - @projects = sort {$a->{'path'} cmp $b->{'path'}} @projects; - print "<th>Project</th>\n"; - } else { - print "<th>" . - $cgi->a({-href => href(project=>undef, order=>'project'), - -class => "header"}, "Project") . - "</th>\n"; - } - if ($order eq "descr") { - @projects = sort {$a->{'descr'} cmp $b->{'descr'}} @projects; - print "<th>Description</th>\n"; - } else { - print "<th>" . - $cgi->a({-href => href(project=>undef, order=>'descr'), - -class => "header"}, "Description") . - "</th>\n"; - } - if ($order eq "owner") { - @projects = sort {$a->{'owner'} cmp $b->{'owner'}} @projects; - print "<th>Owner</th>\n"; - } else { - print "<th>" . - $cgi->a({-href => href(project=>undef, order=>'owner'), - -class => "header"}, "Owner") . - "</th>\n"; - } - if ($order eq "age") { - @projects = sort {$a->{'age'} <=> $b->{'age'}} @projects; - print "<th>Last Change</th>\n"; - } else { - print "<th>" . - $cgi->a({-href => href(project=>undef, order=>'age'), - -class => "header"}, "Last Change") . - "</th>\n"; - } - print "<th></th>\n" . + print_sort_th('project', $order, 'Project'); + print_sort_th('descr', $order, 'Description'); + print_sort_th('owner', $order, 'Owner'); + print_sort_th('age', $order, 'Last Change'); + print "<th></th>\n" . # for links "</tr>\n"; } my $alternate = 1; + my $tagfilter = $cgi->param('by_tag'); for (my $i = $from; $i <= $to; $i++) { my $pr = $projects[$i]; + + next if $tagfilter and $show_ctags and not grep { lc $_ eq lc $tagfilter } keys %{$pr->{'ctags'}}; + next if $searchtext and not $pr->{'path'} =~ /$searchtext/ + and not $pr->{'descr_long'} =~ /$searchtext/; + # Weed out forks or non-matching entries of search + if ($check_forks) { + my $forkbase = $project; $forkbase ||= ''; $forkbase =~ s#\.git$#/#; + $forkbase="^$forkbase" if $forkbase; + next if not $searchtext and not $tagfilter and $show_ctags + and $pr->{'path'} =~ m#$forkbase.*/.*#; # regexp-safe + } + if ($alternate) { print "<tr class=\"dark\">\n"; } else { @@ -2669,9 +4462,9 @@ sub git_project_list_body { "<td>" . $cgi->a({-href => href(project=>$pr->{'path'}, action=>"summary"), -class => "list", -title => $pr->{'descr_long'}}, esc_html($pr->{'descr'})) . "</td>\n" . - "<td><i>" . chop_str($pr->{'owner'}, 15) . "</i></td>\n"; + "<td><i>" . chop_and_escape_str($pr->{'owner'}, 15) . "</i></td>\n"; print "<td class=\"". age_class($pr->{'age'}) . "\">" . - $pr->{'age_string'} . "</td>\n" . + (defined $pr->{'age_string'} ? $pr->{'age_string'} : "No commits") . "</td>\n" . "<td class=\"link\">" . $cgi->a({-href => href(project=>$pr->{'path'}, action=>"summary")}, "summary") . " | " . $cgi->a({-href => href(project=>$pr->{'path'}, action=>"shortlog")}, "shortlog") . " | " . @@ -2692,16 +4485,54 @@ sub git_project_list_body { print "</table>\n"; } -sub git_shortlog_body { +sub git_log_body { # uses global variable $project my ($commitlist, $from, $to, $refs, $extra) = @_; - my $have_snapshot = gitweb_have_snapshot(); + $from = 0 unless defined $from; + $to = $#{$commitlist} if (!defined $to || $#{$commitlist} < $to); + + for (my $i = 0; $i <= $to; $i++) { + my %co = %{$commitlist->[$i]}; + next if !%co; + my $commit = $co{'id'}; + my $ref = format_ref_marker($refs, $commit); + my %ad = parse_date($co{'author_epoch'}); + git_print_header_div('commit', + "<span class=\"age\">$co{'age_string'}</span>" . + esc_html($co{'title'}) . $ref, + $commit); + print "<div class=\"title_text\">\n" . + "<div class=\"log_link\">\n" . + $cgi->a({-href => href(action=>"commit", hash=>$commit)}, "commit") . + " | " . + $cgi->a({-href => href(action=>"commitdiff", hash=>$commit)}, "commitdiff") . + " | " . + $cgi->a({-href => href(action=>"tree", hash=>$commit, hash_base=>$commit)}, "tree") . + "<br/>\n" . + "</div>\n"; + git_print_authorship(\%co, -tag => 'span'); + print "<br/>\n</div>\n"; + + print "<div class=\"log_body\">\n"; + git_print_log($co{'comment'}, -final_empty_line=> 1); + print "</div>\n"; + } + if ($extra) { + print "<div class=\"page_nav\">\n"; + print "$extra\n"; + print "</div>\n"; + } +} + +sub git_shortlog_body { + # uses global variable $project + my ($commitlist, $from, $to, $refs, $extra) = @_; $from = 0 unless defined $from; $to = $#{$commitlist} if (!defined $to || $#{$commitlist} < $to); - print "<table class=\"shortlog\" cellspacing=\"0\">\n"; + print "<table class=\"shortlog\">\n"; my $alternate = 1; for (my $i = $from; $i <= $to; $i++) { my %co = %{$commitlist->[$i]}; @@ -2715,8 +4546,7 @@ sub git_shortlog_body { $alternate ^= 1; # git_summary() used print "<td><i>$co{'age_string'}</i></td>\n" . print "<td title=\"$co{'age_string_age'}\"><i>$co{'age_string_date'}</i></td>\n" . - "<td><i>" . esc_html(chop_str($co{'author_name'}, 10)) . "</i></td>\n" . - "<td>"; + format_author_html('td', \%co, 10) . "<td>"; print format_subject_html($co{'title'}, $co{'title_short'}, href(action=>"commit", hash=>$commit), $ref); print "</td>\n" . @@ -2724,8 +4554,9 @@ sub git_shortlog_body { $cgi->a({-href => href(action=>"commit", hash=>$commit)}, "commit") . " | " . $cgi->a({-href => href(action=>"commitdiff", hash=>$commit)}, "commitdiff") . " | " . $cgi->a({-href => href(action=>"tree", hash=>$commit, hash_base=>$commit)}, "tree"); - if ($have_snapshot) { - print " | " . $cgi->a({-href => href(action=>"snapshot", hash=>$commit)}, "snapshot"); + my $snapshot_links = format_snapshot_links($commit); + if (defined $snapshot_links) { + print " | " . $snapshot_links; } print "</td>\n" . "</tr>\n"; @@ -2740,12 +4571,13 @@ sub git_shortlog_body { sub git_history_body { # Warning: assumes constant type (blob or tree) during history - my ($commitlist, $from, $to, $refs, $hash_base, $ftype, $extra) = @_; + my ($commitlist, $from, $to, $refs, $extra, + $file_name, $file_hash, $ftype) = @_; $from = 0 unless defined $from; $to = $#{$commitlist} unless (defined $to && $to <= $#{$commitlist}); - print "<table class=\"history\" cellspacing=\"0\">\n"; + print "<table class=\"history\">\n"; my $alternate = 1; for (my $i = $from; $i <= $to; $i++) { my %co = %{$commitlist->[$i]}; @@ -2763,9 +4595,8 @@ sub git_history_body { } $alternate ^= 1; print "<td title=\"$co{'age_string_age'}\"><i>$co{'age_string_date'}</i></td>\n" . - # shortlog uses chop_str($co{'author_name'}, 10) - "<td><i>" . esc_html(chop_str($co{'author_name'}, 15, 3)) . "</i></td>\n" . - "<td>"; + # shortlog: format_author_html('td', \%co, 10) + format_author_html('td', \%co, 15, 3) . "<td>"; # originally git_history used chop_str($co{'title'}, 50) print format_subject_html($co{'title'}, $co{'title_short'}, href(action=>"commit", hash=>$commit), $ref); @@ -2775,7 +4606,7 @@ sub git_history_body { $cgi->a({-href => href(action=>"commitdiff", hash=>$commit)}, "commitdiff"); if ($ftype eq 'blob') { - my $blob_current = git_get_hash_by_path($hash_base, $file_name); + my $blob_current = $file_hash; my $blob_parent = git_get_hash_by_path($commit, $file_name); if (defined $blob_current && defined $blob_parent && $blob_current ne $blob_parent) { @@ -2804,7 +4635,7 @@ sub git_tags_body { $from = 0 unless defined $from; $to = $#{$taglist} if (!defined $to || $#{$taglist} < $to); - print "<table class=\"tags\" cellspacing=\"0\">\n"; + print "<table class=\"tags\">\n"; my $alternate = 1; for (my $i = $from; $i <= $to; $i++) { my $entry = $taglist->[$i]; @@ -2845,8 +4676,8 @@ sub git_tags_body { "<td class=\"link\">" . " | " . $cgi->a({-href => href(action=>$tag{'reftype'}, hash=>$tag{'refid'})}, $tag{'reftype'}); if ($tag{'reftype'} eq "commit") { - print " | " . $cgi->a({-href => href(action=>"shortlog", hash=>$tag{'name'})}, "shortlog") . - " | " . $cgi->a({-href => href(action=>"log", hash=>$tag{'name'})}, "log"); + print " | " . $cgi->a({-href => href(action=>"shortlog", hash=>$tag{'fullname'})}, "shortlog") . + " | " . $cgi->a({-href => href(action=>"log", hash=>$tag{'fullname'})}, "log"); } elsif ($tag{'reftype'} eq "blob") { print " | " . $cgi->a({-href => href(action=>"blob_plain", hash=>$tag{'refid'})}, "raw"); } @@ -2867,7 +4698,7 @@ sub git_heads_body { $from = 0 unless defined $from; $to = $#{$headlist} if (!defined $to || $#{$headlist} < $to); - print "<table class=\"heads\" cellspacing=\"0\">\n"; + print "<table class=\"heads\">\n"; my $alternate = 1; for (my $i = $from; $i <= $to; $i++) { my $entry = $headlist->[$i]; @@ -2881,13 +4712,13 @@ sub git_heads_body { $alternate ^= 1; print "<td><i>$ref{'age'}</i></td>\n" . ($curr ? "<td class=\"current_head\">" : "<td>") . - $cgi->a({-href => href(action=>"shortlog", hash=>$ref{'name'}), + $cgi->a({-href => href(action=>"shortlog", hash=>$ref{'fullname'}), -class => "list name"},esc_html($ref{'name'})) . "</td>\n" . "<td class=\"link\">" . - $cgi->a({-href => href(action=>"shortlog", hash=>$ref{'name'})}, "shortlog") . " | " . - $cgi->a({-href => href(action=>"log", hash=>$ref{'name'})}, "log") . " | " . - $cgi->a({-href => href(action=>"tree", hash=>$ref{'name'}, hash_base=>$ref{'name'})}, "tree") . + $cgi->a({-href => href(action=>"shortlog", hash=>$ref{'fullname'})}, "shortlog") . " | " . + $cgi->a({-href => href(action=>"log", hash=>$ref{'fullname'})}, "log") . " | " . + $cgi->a({-href => href(action=>"tree", hash=>$ref{'fullname'}, hash_base=>$ref{'name'})}, "tree") . "</td>\n" . "</tr>"; } @@ -2904,7 +4735,7 @@ sub git_search_grep_body { $from = 0 unless defined $from; $to = $#{$commitlist} if (!defined $to || $#{$commitlist} < $to); - print "<table class=\"grep\" cellspacing=\"0\">\n"; + print "<table class=\"commit_search\">\n"; my $alternate = 1; for (my $i = $from; $i <= $to; $i++) { my %co = %{$commitlist->[$i]}; @@ -2919,26 +4750,34 @@ sub git_search_grep_body { } $alternate ^= 1; print "<td title=\"$co{'age_string_age'}\"><i>$co{'age_string_date'}</i></td>\n" . - "<td><i>" . esc_html(chop_str($co{'author_name'}, 15, 5)) . "</i></td>\n" . + format_author_html('td', \%co, 15, 5) . "<td>" . - $cgi->a({-href => href(action=>"commit", hash=>$co{'id'}), -class => "list subject"}, - esc_html(chop_str($co{'title'}, 50)) . "<br/>"); + $cgi->a({-href => href(action=>"commit", hash=>$co{'id'}), + -class => "list subject"}, + chop_and_escape_str($co{'title'}, 50) . "<br/>"); my $comment = $co{'comment'}; foreach my $line (@$comment) { - if ($line =~ m/^(.*)($searchtext)(.*)$/i) { - my $lead = esc_html($1) || ""; - $lead = chop_str($lead, 30, 10); - my $match = esc_html($2) || ""; - my $trail = esc_html($3) || ""; - $trail = chop_str($trail, 30, 10); - my $text = "$lead<span class=\"match\">$match</span>$trail"; - print chop_str($text, 80, 5) . "<br/>\n"; + if ($line =~ m/^(.*?)($search_regexp)(.*)$/i) { + my ($lead, $match, $trail) = ($1, $2, $3); + $match = chop_str($match, 70, 5, 'center'); + my $contextlen = int((80 - length($match))/2); + $contextlen = 30 if ($contextlen > 30); + $lead = chop_str($lead, $contextlen, 10, 'left'); + $trail = chop_str($trail, $contextlen, 10, 'right'); + + $lead = esc_html($lead); + $match = esc_html($match); + $trail = esc_html($trail); + + print "$lead<span class=\"match\">$match</span>$trail<br />"; } } print "</td>\n" . "<td class=\"link\">" . $cgi->a({-href => href(action=>"commit", hash=>$co{'id'})}, "commit") . " | " . + $cgi->a({-href => href(action=>"commitdiff", hash=>$co{'id'})}, "commitdiff") . + " | " . $cgi->a({-href => href(action=>"tree", hash=>$co{'tree'}, hash_base=>$co{'id'})}, "tree"); print "</td>\n" . "</tr>\n"; @@ -2956,37 +4795,40 @@ sub git_search_grep_body { ## actions sub git_project_list { - my $order = $cgi->param('o'); - if (defined $order && $order !~ m/project|descr|owner|age/) { - die_error(undef, "Unknown order parameter"); + my $order = $input_params{'order'}; + if (defined $order && $order !~ m/none|project|descr|owner|age/) { + die_error(400, "Unknown order parameter"); } my @list = git_get_projects_list(); if (!@list) { - die_error(undef, "No projects found"); + die_error(404, "No projects found"); } git_header_html(); - if (-f $home_text) { + if (defined $home_text && -f $home_text) { print "<div class=\"index_include\">\n"; - open (my $fd, $home_text); - print <$fd>; - close $fd; + insert_file($home_text); print "</div>\n"; } + print $cgi->startform(-method => "get") . + "<p class=\"projsearch\">Search:\n" . + $cgi->textfield(-name => "s", -value => $searchtext) . "\n" . + "</p>" . + $cgi->end_form() . "\n"; git_project_list_body(\@list, $order); git_footer_html(); } sub git_forks { - my $order = $cgi->param('o'); - if (defined $order && $order !~ m/project|descr|owner|age/) { - die_error(undef, "Unknown order parameter"); + my $order = $input_params{'order'}; + if (defined $order && $order !~ m/none|project|descr|owner|age/) { + die_error(400, "Unknown order parameter"); } my @list = git_get_projects_list($project); if (!@list) { - die_error(undef, "No forks found"); + die_error(404, "No forks found"); } git_header_html(); @@ -3006,7 +4848,7 @@ sub git_project_index { foreach my $pr (@projects) { if (!exists $pr->{'owner'}) { - $pr->{'owner'} = get_file_owner("$projectroot/$pr->{'path'}"); + $pr->{'owner'} = git_get_project_owner("$pr->{'path'}"); } my ($path, $owner) = ($pr->{'path'}, $pr->{'owner'}); @@ -3023,7 +4865,7 @@ sub git_project_index { sub git_summary { my $descr = git_get_project_description($project) || "none"; my %co = parse_commit("HEAD"); - my %cd = parse_date($co{'committer_epoch'}, $co{'committer_tz'}); + my %cd = %co ? parse_date($co{'committer_epoch'}, $co{'committer_tz'}) : (); my $head = $co{'id'}; my $owner = git_get_project_owner($project); @@ -3034,7 +4876,7 @@ sub git_summary { my @taglist = git_get_tags_list(16); my @headlist = git_get_heads_list(16); my @forklist; - my ($check_forks) = gitweb_check_feature('forks'); + my $check_forks = gitweb_check_feature('forks'); if ($check_forks) { @forklist = git_get_projects_list($project); @@ -3044,10 +4886,13 @@ sub git_summary { git_print_page_nav('summary','', $head); print "<div class=\"title\"> </div>\n"; - print "<table cellspacing=\"0\">\n" . - "<tr><td>description</td><td>" . esc_html($descr) . "</td></tr>\n" . - "<tr><td>owner</td><td>$owner</td></tr>\n" . - "<tr><td>last change</td><td>$cd{'rfc2822'}</td></tr>\n"; + print "<table class=\"projects_list\">\n" . + "<tr id=\"metadata_desc\"><td>description</td><td>" . esc_html($descr) . "</td></tr>\n" . + "<tr id=\"metadata_owner\"><td>owner</td><td>" . esc_html($owner) . "</td></tr>\n"; + if (defined $cd{'rfc2822'}) { + print "<tr id=\"metadata_lchange\"><td>last change</td><td>$cd{'rfc2822'}</td></tr>\n"; + } + # use per project git URL list in $projectroot/$project/cloneurl # or make project git URL from git base URL and project name my $url_tag = "URL"; @@ -3055,26 +4900,43 @@ sub git_summary { @url_list = map { "$_/$project" } @git_base_url_list unless @url_list; foreach my $git_url (@url_list) { next unless $git_url; - print "<tr><td>$url_tag</td><td>$git_url</td></tr>\n"; + print "<tr class=\"metadata_url\"><td>$url_tag</td><td>$git_url</td></tr>\n"; $url_tag = ""; } + + # Tag cloud + my $show_ctags = gitweb_check_feature('ctags'); + if ($show_ctags) { + my $ctags = git_get_project_ctags($project); + my $cloud = git_populate_project_tagcloud($ctags); + print "<tr id=\"metadata_ctags\"><td>Content tags:<br />"; + print "</td>\n<td>" unless %$ctags; + print "<form action=\"$show_ctags\" method=\"post\"><input type=\"hidden\" name=\"p\" value=\"$project\" />Add: <input type=\"text\" name=\"t\" size=\"8\" /></form>"; + print "</td>\n<td>" if %$ctags; + print git_show_project_tagcloud($cloud, 48); + print "</td></tr>"; + } + print "</table>\n"; - if (-s "$projectroot/$project/README.html") { - if (open my $fd, "$projectroot/$project/README.html") { - print "<div class=\"title\">readme</div>\n"; - print $_ while (<$fd>); - close $fd; - } + # If XSS prevention is on, we don't include README.html. + # TODO: Allow a readme in some safe format. + if (!$prevent_xss && -s "$projectroot/$project/README.html") { + print "<div class=\"title\">readme</div>\n" . + "<div class=\"readme\">\n"; + insert_file("$projectroot/$project/README.html"); + print "\n</div>\n"; # class="readme" } # we need to request one more than 16 (0..15) to check if # those 16 are all - my @commitlist = parse_commits($head, 17); - git_print_header_div('shortlog'); - git_shortlog_body(\@commitlist, 0, 15, $refs, - $#commitlist <= 15 ? undef : - $cgi->a({-href => href(action=>"shortlog")}, "...")); + my @commitlist = $head ? parse_commits($head, 17) : (); + if (@commitlist) { + git_print_header_div('shortlog'); + git_shortlog_body(\@commitlist, 0, 15, $refs, + $#commitlist <= 15 ? undef : + $cgi->a({-href => href(action=>"shortlog")}, "...")); + } if (@taglist) { git_print_header_div('tags'); @@ -3092,10 +4954,10 @@ sub git_summary { if (@forklist) { git_print_header_div('forks'); - git_project_list_body(\@forklist, undef, 0, 15, + git_project_list_body(\@forklist, 'age', 0, 15, $#forklist <= 15 ? undef : $cgi->a({-href => href(action=>"forks")}, "..."), - 'noheader'); + 'no_header'); } git_footer_html(); @@ -3106,9 +4968,14 @@ sub git_tag { git_header_html(); git_print_page_nav('','', $head,undef,$head); my %tag = parse_tag($hash); + + if (! %tag) { + die_error(404, "Unknown tag object"); + } + git_print_header_div('commit', esc_html($tag{'name'}), $hash); print "<div class=\"title_text\">\n" . - "<table cellspacing=\"0\">\n" . + "<table class=\"object_header\">\n" . "<tr>\n" . "<td>object</td>\n" . "<td>" . $cgi->a({-class => "list", -href => href(action=>$tag{'type'}, hash=>$tag{'object'})}, @@ -3117,11 +4984,7 @@ sub git_tag { $tag{'type'}) . "</td>\n" . "</tr>\n"; if (defined($tag{'author'})) { - my %ad = parse_date($tag{'epoch'}, $tag{'tz'}); - print "<tr><td>author</td><td>" . esc_html($tag{'author'}) . "</td></tr>\n"; - print "<tr><td></td><td>" . $ad{'rfc2822'} . - sprintf(" (%02d:%02d %s)", $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}) . - "</td></tr>\n"; + git_print_authorship_rows(\%tag, 'author'); } print "</table>\n\n" . "</div>\n"; @@ -3135,209 +4998,246 @@ sub git_tag { git_footer_html(); } -sub git_blame2 { - my $fd; - my $ftype; - - my ($have_blame) = gitweb_check_feature('blame'); - if (!$have_blame) { - die_error('403 Permission denied', "Permission denied"); +sub git_blame_common { + my $format = shift || 'porcelain'; + if ($format eq 'porcelain' && $cgi->param('js')) { + $format = 'incremental'; + $action = 'blame_incremental'; # for page title etc } - die_error('404 Not Found', "File name not defined") if (!$file_name); + + # permissions + gitweb_check_feature('blame') + or die_error(403, "Blame view not allowed"); + + # error checking + die_error(400, "No file name given") unless $file_name; $hash_base ||= git_get_head_hash($project); - die_error(undef, "Couldn't find base commit") unless ($hash_base); + die_error(404, "Couldn't find base commit") unless $hash_base; my %co = parse_commit($hash_base) - or die_error(undef, "Reading commit failed"); + or die_error(404, "Commit not found"); + my $ftype = "blob"; if (!defined $hash) { $hash = git_get_hash_by_path($hash_base, $file_name, "blob") - or die_error(undef, "Error looking up file"); + or die_error(404, "Error looking up file"); + } else { + $ftype = git_get_type($hash); + if ($ftype !~ "blob") { + die_error(400, "Object is not a blob"); + } } - $ftype = git_get_type($hash); - if ($ftype !~ "blob") { - die_error("400 Bad Request", "Object is not a blob"); + + my $fd; + if ($format eq 'incremental') { + # get file contents (as base) + open $fd, "-|", git_cmd(), 'cat-file', 'blob', $hash + or die_error(500, "Open git-cat-file failed"); + } elsif ($format eq 'data') { + # run git-blame --incremental + open $fd, "-|", git_cmd(), "blame", "--incremental", + $hash_base, "--", $file_name + or die_error(500, "Open git-blame --incremental failed"); + } else { + # run git-blame --porcelain + open $fd, "-|", git_cmd(), "blame", '-p', + $hash_base, '--', $file_name + or die_error(500, "Open git-blame --porcelain failed"); } - open ($fd, "-|", git_cmd(), "blame", '-p', '--', - $file_name, $hash_base) - or die_error(undef, "Open git-blame failed"); + + # incremental blame data returns early + if ($format eq 'data') { + print $cgi->header( + -type=>"text/plain", -charset => "utf-8", + -status=> "200 OK"); + local $| = 1; # output autoflush + print while <$fd>; + close $fd + or print "ERROR $!\n"; + + print 'END'; + if (defined $t0 && gitweb_check_feature('timed')) { + print ' '. + Time::HiRes::tv_interval($t0, [Time::HiRes::gettimeofday()]). + ' '.$number_of_git_cmds; + } + print "\n"; + + return; + } + + # page header git_header_html(); my $formats_nav = - $cgi->a({-href => href(action=>"blob", hash=>$hash, hash_base=>$hash_base, file_name=>$file_name)}, + $cgi->a({-href => href(action=>"blob", -replay=>1)}, "blob") . + " | "; + if ($format eq 'incremental') { + $formats_nav .= + $cgi->a({-href => href(action=>"blame", javascript=>0, -replay=>1)}, + "blame") . " (non-incremental)"; + } else { + $formats_nav .= + $cgi->a({-href => href(action=>"blame_incremental", -replay=>1)}, + "blame") . " (incremental)"; + } + $formats_nav .= " | " . - $cgi->a({-href => href(action=>"history", hash=>$hash, hash_base=>$hash_base, file_name=>$file_name)}, - "history") . + $cgi->a({-href => href(action=>"history", -replay=>1)}, + "history") . " | " . - $cgi->a({-href => href(action=>"blame", file_name=>$file_name)}, + $cgi->a({-href => href(action=>$action, file_name=>$file_name)}, "HEAD"); git_print_page_nav('','', $hash_base,$co{'tree'},$hash_base, $formats_nav); git_print_header_div('commit', esc_html($co{'title'}), $hash_base); git_print_page_path($file_name, $ftype, $hash_base); - my @rev_color = (qw(light2 dark2)); + + # page body + if ($format eq 'incremental') { + print "<noscript>\n<div class=\"error\"><center><b>\n". + "This page requires JavaScript to run.\n Use ". + $cgi->a({-href => href(action=>'blame',javascript=>0,-replay=>1)}, + 'this page'). + " instead.\n". + "</b></center></div>\n</noscript>\n"; + + print qq!<div id="progress_bar" style="width: 100%; background-color: yellow"></div>\n!; + } + + print qq!<div class="page_body">\n!; + print qq!<div id="progress_info">... / ...</div>\n! + if ($format eq 'incremental'); + print qq!<table id="blame_table" class="blame" width="100%">\n!. + #qq!<col width="5.5em" /><col width="2.5em" /><col width="*" />\n!. + qq!<thead>\n!. + qq!<tr><th>Commit</th><th>Line</th><th>Data</th></tr>\n!. + qq!</thead>\n!. + qq!<tbody>\n!; + + my @rev_color = qw(light dark); my $num_colors = scalar(@rev_color); my $current_color = 0; - my $last_rev; - print <<HTML; -<div class="page_body"> -<table class="blame"> -<tr><th>Commit</th><th>Line</th><th>Data</th></tr> -HTML - my %metainfo = (); - while (1) { - $_ = <$fd>; - last unless defined $_; - my ($full_rev, $orig_lineno, $lineno, $group_size) = - /^([0-9a-f]{40}) (\d+) (\d+)(?: (\d+))?$/; - if (!exists $metainfo{$full_rev}) { - $metainfo{$full_rev} = {}; - } - my $meta = $metainfo{$full_rev}; - while (<$fd>) { - last if (s/^\t//); - if (/^(\S+) (.*)$/) { - $meta->{$1} = $2; - } - } - my $data = $_; - chomp $data; - my $rev = substr($full_rev, 0, 8); - my $author = $meta->{'author'}; - my %date = parse_date($meta->{'author-time'}, - $meta->{'author-tz'}); - my $date = $date{'iso-tz'}; - if ($group_size) { - $current_color = ++$current_color % $num_colors; - } - print "<tr class=\"$rev_color[$current_color]\">\n"; - if ($group_size) { - print "<td class=\"sha1\""; - print " title=\"". esc_html($author) . ", $date\""; - print " rowspan=\"$group_size\"" if ($group_size > 1); - print ">"; - print $cgi->a({-href => href(action=>"commit", - hash=>$full_rev, - file_name=>$file_name)}, - esc_html($rev)); - print "</td>\n"; + + if ($format eq 'incremental') { + my $color_class = $rev_color[$current_color]; + + #contents of a file + my $linenr = 0; + LINE: + while (my $line = <$fd>) { + chomp $line; + $linenr++; + + print qq!<tr id="l$linenr" class="$color_class">!. + qq!<td class="sha1"><a href=""> </a></td>!. + qq!<td class="linenr">!. + qq!<a class="linenr" href="">$linenr</a></td>!; + print qq!<td class="pre">! . esc_html($line) . "</td>\n"; + print qq!</tr>\n!; } - open (my $dd, "-|", git_cmd(), "rev-parse", "$full_rev^") - or die_error("could not open git-rev-parse"); - my $parent_commit = <$dd>; - close $dd; - chomp($parent_commit); - my $blamed = href(action => 'blame', - file_name => $meta->{'filename'}, - hash_base => $parent_commit); - print "<td class=\"linenr\">"; - print $cgi->a({ -href => "$blamed#l$orig_lineno", - -id => "l$lineno", - -class => "linenr" }, - esc_html($lineno)); - print "</td>"; - print "<td class=\"pre\">" . esc_html($data) . "</td>\n"; - print "</tr>\n"; - } - print "</table>\n"; - print "</div>"; + + } else { # porcelain, i.e. ordinary blame + my %metainfo = (); # saves information about commits + + # blame data + LINE: + while (my $line = <$fd>) { + chomp $line; + # the header: <SHA-1> <src lineno> <dst lineno> [<lines in group>] + # no <lines in group> for subsequent lines in group of lines + my ($full_rev, $orig_lineno, $lineno, $group_size) = + ($line =~ /^([0-9a-f]{40}) (\d+) (\d+)(?: (\d+))?$/); + if (!exists $metainfo{$full_rev}) { + $metainfo{$full_rev} = { 'nprevious' => 0 }; + } + my $meta = $metainfo{$full_rev}; + my $data; + while ($data = <$fd>) { + chomp $data; + last if ($data =~ s/^\t//); # contents of line + if ($data =~ /^(\S+)(?: (.*))?$/) { + $meta->{$1} = $2 unless exists $meta->{$1}; + } + if ($data =~ /^previous /) { + $meta->{'nprevious'}++; + } + } + my $short_rev = substr($full_rev, 0, 8); + my $author = $meta->{'author'}; + my %date = + parse_date($meta->{'author-time'}, $meta->{'author-tz'}); + my $date = $date{'iso-tz'}; + if ($group_size) { + $current_color = ($current_color + 1) % $num_colors; + } + my $tr_class = $rev_color[$current_color]; + $tr_class .= ' boundary' if (exists $meta->{'boundary'}); + $tr_class .= ' no-previous' if ($meta->{'nprevious'} == 0); + $tr_class .= ' multiple-previous' if ($meta->{'nprevious'} > 1); + print "<tr id=\"l$lineno\" class=\"$tr_class\">\n"; + if ($group_size) { + print "<td class=\"sha1\""; + print " title=\"". esc_html($author) . ", $date\""; + print " rowspan=\"$group_size\"" if ($group_size > 1); + print ">"; + print $cgi->a({-href => href(action=>"commit", + hash=>$full_rev, + file_name=>$file_name)}, + esc_html($short_rev)); + if ($group_size >= 2) { + my @author_initials = ($author =~ /\b([[:upper:]])\B/g); + if (@author_initials) { + print "<br />" . + esc_html(join('', @author_initials)); + # or join('.', ...) + } + } + print "</td>\n"; + } + # 'previous' <sha1 of parent commit> <filename at commit> + if (exists $meta->{'previous'} && + $meta->{'previous'} =~ /^([a-fA-F0-9]{40}) (.*)$/) { + $meta->{'parent'} = $1; + $meta->{'file_parent'} = unquote($2); + } + my $linenr_commit = + exists($meta->{'parent'}) ? + $meta->{'parent'} : $full_rev; + my $linenr_filename = + exists($meta->{'file_parent'}) ? + $meta->{'file_parent'} : unquote($meta->{'filename'}); + my $blamed = href(action => 'blame', + file_name => $linenr_filename, + hash_base => $linenr_commit); + print "<td class=\"linenr\">"; + print $cgi->a({ -href => "$blamed#l$orig_lineno", + -class => "linenr" }, + esc_html($lineno)); + print "</td>"; + print "<td class=\"pre\">" . esc_html($data) . "</td>\n"; + print "</tr>\n"; + } # end while + + } + + # footer + print "</tbody>\n". + "</table>\n"; # class="blame" + print "</div>\n"; # class="blame_body" close $fd or print "Reading blob failed\n"; + git_footer_html(); } sub git_blame { - my $fd; + git_blame_common(); +} - my ($have_blame) = gitweb_check_feature('blame'); - if (!$have_blame) { - die_error('403 Permission denied', "Permission denied"); - } - die_error('404 Not Found', "File name not defined") if (!$file_name); - $hash_base ||= git_get_head_hash($project); - die_error(undef, "Couldn't find base commit") unless ($hash_base); - my %co = parse_commit($hash_base) - or die_error(undef, "Reading commit failed"); - if (!defined $hash) { - $hash = git_get_hash_by_path($hash_base, $file_name, "blob") - or die_error(undef, "Error lookup file"); - } - open ($fd, "-|", git_cmd(), "annotate", '-l', '-t', '-r', $file_name, $hash_base) - or die_error(undef, "Open git-annotate failed"); - git_header_html(); - my $formats_nav = - $cgi->a({-href => href(action=>"blob", hash=>$hash, hash_base=>$hash_base, file_name=>$file_name)}, - "blob") . - " | " . - $cgi->a({-href => href(action=>"history", hash=>$hash, hash_base=>$hash_base, file_name=>$file_name)}, - "history") . - " | " . - $cgi->a({-href => href(action=>"blame", file_name=>$file_name)}, - "HEAD"); - git_print_page_nav('','', $hash_base,$co{'tree'},$hash_base, $formats_nav); - git_print_header_div('commit', esc_html($co{'title'}), $hash_base); - git_print_page_path($file_name, 'blob', $hash_base); - print "<div class=\"page_body\">\n"; - print <<HTML; -<table class="blame"> - <tr> - <th>Commit</th> - <th>Age</th> - <th>Author</th> - <th>Line</th> - <th>Data</th> - </tr> -HTML - my @line_class = (qw(light dark)); - my $line_class_len = scalar (@line_class); - my $line_class_num = $#line_class; - while (my $line = <$fd>) { - my $long_rev; - my $short_rev; - my $author; - my $time; - my $lineno; - my $data; - my $age; - my $age_str; - my $age_class; +sub git_blame_incremental { + git_blame_common('incremental'); +} - chomp $line; - $line_class_num = ($line_class_num + 1) % $line_class_len; - - if ($line =~ m/^([0-9a-fA-F]{40})\t\(\s*([^\t]+)\t(\d+) [+-]\d\d\d\d\t(\d+)\)(.*)$/) { - $long_rev = $1; - $author = $2; - $time = $3; - $lineno = $4; - $data = $5; - } else { - print qq( <tr><td colspan="5" class="error">Unable to parse: $line</td></tr>\n); - next; - } - $short_rev = substr ($long_rev, 0, 8); - $age = time () - $time; - $age_str = age_string ($age); - $age_str =~ s/ / /g; - $age_class = age_class($age); - $author = esc_html ($author); - $author =~ s/ / /g; - - $data = untabify($data); - $data = esc_html ($data); - - print <<HTML; - <tr class="$line_class[$line_class_num]"> - <td class="sha1"><a href="${\href (action=>"commit", hash=>$long_rev)}" class="text">$short_rev..</a></td> - <td class="$age_class">$age_str</td> - <td>$author</td> - <td class="linenr"><a id="$lineno" href="#$lineno" class="linenr">$lineno</a></td> - <td class="pre">$data</td> - </tr> -HTML - } # while (my $line = <$fd>) - print "</table>\n\n"; - close $fd - or print "Reading blob failed.\n"; - print "</div>"; - git_footer_html(); +sub git_blame_data { + git_blame_common('data'); } sub git_tags { @@ -3367,28 +5267,29 @@ sub git_heads { } sub git_blob_plain { + my $type = shift; my $expires; if (!defined $hash) { if (defined $file_name) { my $base = $hash_base || git_get_head_hash($project); $hash = git_get_hash_by_path($base, $file_name, "blob") - or die_error(undef, "Error lookup file"); + or die_error(404, "Cannot find file"); } else { - die_error(undef, "No file name defined"); + die_error(400, "No file name defined"); } } elsif ($hash =~ m/^[0-9a-fA-F]{40}$/) { # blobs defined by non-textual hash id's can be cached $expires = "+1d"; } - my $type = shift; open my $fd, "-|", git_cmd(), "cat-file", "blob", $hash - or die_error(undef, "Couldn't cat $file_name, $hash"); + or die_error(500, "Open git-cat-file blob '$hash' failed"); - $type ||= blob_mimetype($fd, $file_name); + # content-type (can include charset) + $type = blob_contenttype($fd, $file_name, $type); - # save as filename, even when no $file_name is given + # "save as" filename, even when no $file_name is given my $save_as = "$hash"; if (defined $file_name) { $save_as = $file_name; @@ -3396,15 +5297,25 @@ sub git_blob_plain { $save_as .= '.txt'; } + # With XSS prevention on, blobs of all types except a few known safe + # ones are served with "Content-Disposition: attachment" to make sure + # they don't run in our security domain. For certain image types, + # blob view writes an <img> tag referring to blob_plain view, and we + # want to be sure not to break that by serving the image as an + # attachment (though Firefox 3 doesn't seem to care). + my $sandbox = $prevent_xss && + $type !~ m!^(?:text/plain|image/(?:gif|png|jpeg))$!; + print $cgi->header( - -type => "$type", - -expires=>$expires, - -content_disposition => 'inline; filename="' . "$save_as" . '"'); - undef $/; + -type => $type, + -expires => $expires, + -content_disposition => + ($sandbox ? 'attachment' : 'inline') + . '; filename="' . $save_as . '"'); + local $/ = undef; binmode STDOUT, ':raw'; print <$fd>; binmode STDOUT, ':utf8'; # as set at the beginning of gitweb.cgi - $/ = "\n"; close $fd; } @@ -3415,20 +5326,20 @@ sub git_blob { if (defined $file_name) { my $base = $hash_base || git_get_head_hash($project); $hash = git_get_hash_by_path($base, $file_name, "blob") - or die_error(undef, "Error lookup file"); + or die_error(404, "Cannot find file"); } else { - die_error(undef, "No file name defined"); + die_error(400, "No file name defined"); } } elsif ($hash =~ m/^[0-9a-fA-F]{40}$/) { # blobs defined by non-textual hash id's can be cached $expires = "+1d"; } - my ($have_blame) = gitweb_check_feature('blame'); + my $have_blame = gitweb_check_feature('blame'); open my $fd, "-|", git_cmd(), "cat-file", "blob", $hash - or die_error(undef, "Couldn't cat $file_name, $hash"); + or die_error(500, "Couldn't cat $file_name, $hash"); my $mimetype = blob_mimetype($fd, $file_name); - if ($mimetype !~ m!^(?:text/|image/(?:gif|png|jpeg)$)!) { + if ($mimetype !~ m!^(?:text/|image/(?:gif|png|jpeg)$)! && -B $fd) { close $fd; return git_blob_plain($mimetype); } @@ -3441,18 +5352,15 @@ sub git_blob { if (defined $file_name) { if ($have_blame) { $formats_nav .= - $cgi->a({-href => href(action=>"blame", hash_base=>$hash_base, - hash=>$hash, file_name=>$file_name)}, + $cgi->a({-href => href(action=>"blame", -replay=>1)}, "blame") . " | "; } $formats_nav .= - $cgi->a({-href => href(action=>"history", hash_base=>$hash_base, - hash=>$hash, file_name=>$file_name)}, + $cgi->a({-href => href(action=>"history", -replay=>1)}, "history") . " | " . - $cgi->a({-href => href(action=>"blob_plain", - hash=>$hash, file_name=>$file_name)}, + $cgi->a({-href => href(action=>"blob_plain", -replay=>1)}, "raw") . " | " . $cgi->a({-href => href(action=>"blob", @@ -3460,7 +5368,8 @@ sub git_blob { "HEAD"); } else { $formats_nav .= - $cgi->a({-href => href(action=>"blob_plain", hash=>$hash)}, "raw"); + $cgi->a({-href => href(action=>"blob_plain", -replay=>1)}, + "raw"); } git_print_page_nav('','', $hash_base,$co{'tree'},$hash_base, $formats_nav); git_print_header_div('commit', esc_html($co{'title'}), $hash_base); @@ -3471,16 +5380,7 @@ sub git_blob { } git_print_page_path($file_name, "blob", $hash_base); print "<div class=\"page_body\">\n"; - if ($mimetype =~ m!^text/!) { - my $nr; - while (my $line = <$fd>) { - chomp $line; - $nr++; - $line = untabify($line); - printf "<div class=\"pre\"><a id=\"l%i\" href=\"#l%i\" class=\"linenr\">%4i</a> %s</div>\n", - $nr, $nr, $nr, esc_html($line, -nbsp=>1); - } - } elsif ($mimetype =~ m!^image/!) { + if ($mimetype =~ m!^image/!) { print qq!<img type="$mimetype"!; if ($file_name) { print qq! alt="$file_name" title="$file_name"!; @@ -3489,6 +5389,16 @@ sub git_blob { href(action=>"blob_plain", hash=>$hash, hash_base=>$hash_base, file_name=>$file_name) . qq!" />\n!; + } else { + my $nr; + while (my $line = <$fd>) { + chomp $line; + $nr++; + $line = untabify($line); + printf "<div class=\"pre\"><a id=\"l%i\" href=\"" . href(-replay => 1) + . "#l%i\" class=\"linenr\">%4i</a> %s</div>\n", + $nr, $nr, $nr, esc_html($line, -nbsp=>1); + } } close $fd or print "Reading blob failed.\n"; @@ -3497,8 +5407,6 @@ sub git_blob { } sub git_tree { - my $have_snapshot = gitweb_have_snapshot(); - if (!defined $hash_base) { $hash_base = "HEAD"; } @@ -3509,36 +5417,43 @@ sub git_tree { $hash = $hash_base; } } - $/ = "\0"; - open my $fd, "-|", git_cmd(), "ls-tree", '-z', $hash - or die_error(undef, "Open git-ls-tree failed"); - my @entries = map { chomp; $_ } <$fd>; - close $fd or die_error(undef, "Reading tree failed"); - $/ = "\n"; + die_error(404, "No such tree") unless defined($hash); + + my $show_sizes = gitweb_check_feature('show-sizes'); + my $have_blame = gitweb_check_feature('blame'); + + my @entries = (); + { + local $/ = "\0"; + open my $fd, "-|", git_cmd(), "ls-tree", '-z', + ($show_sizes ? '-l' : ()), @extra_options, $hash + or die_error(500, "Open git-ls-tree failed"); + @entries = map { chomp; $_ } <$fd>; + close $fd + or die_error(404, "Reading tree failed"); + } my $refs = git_get_references(); my $ref = format_ref_marker($refs, $hash_base); git_header_html(); my $basedir = ''; - my ($have_blame) = gitweb_check_feature('blame'); if (defined $hash_base && (my %co = parse_commit($hash_base))) { my @views_nav = (); if (defined $file_name) { push @views_nav, - $cgi->a({-href => href(action=>"history", hash_base=>$hash_base, - hash=>$hash, file_name=>$file_name)}, + $cgi->a({-href => href(action=>"history", -replay=>1)}, "history"), $cgi->a({-href => href(action=>"tree", hash_base=>"HEAD", file_name=>$file_name)}, "HEAD"), } - if ($have_snapshot) { + my $snapshot_links = format_snapshot_links($hash); + if (defined $snapshot_links) { # FIXME: Should be available when we have no hash base as well. - push @views_nav, - $cgi->a({-href => href(action=>"snapshot", hash=>$hash)}, - "snapshot"); + push @views_nav, $snapshot_links; } - git_print_page_nav('tree','', $hash_base, undef, undef, join(' | ', @views_nav)); + git_print_page_nav('tree','', $hash_base, undef, undef, + join(' | ', @views_nav)); git_print_header_div('commit', esc_html($co{'title'}) . $ref, $hash_base); } else { undef $hash_base; @@ -3551,10 +5466,10 @@ sub git_tree { if ($basedir ne '' && substr($basedir, -1) ne '/') { $basedir .= '/'; } + git_print_page_path($file_name, 'tree', $hash_base); } - git_print_page_path($file_name, 'tree', $hash_base); print "<div class=\"page_body\">\n"; - print "<table cellspacing=\"0\">\n"; + print "<table class=\"tree\">\n"; my $alternate = 1; # '..' (top directory) link if possible if (defined $hash_base && @@ -3571,8 +5486,10 @@ sub git_tree { undef $up unless $up; # based on git_print_tree_entry print '<td class="mode">' . mode_str('040000') . "</td>\n"; + print '<td class="size"> </td>'."\n" if $show_sizes; print '<td class="list">'; - print $cgi->a({-href => href(action=>"tree", hash_base=>$hash_base, + print $cgi->a({-href => href(action=>"tree", + hash_base=>$hash_base, file_name=>$up)}, ".."); print "</td>\n"; @@ -3581,7 +5498,7 @@ sub git_tree { print "</tr>\n"; } foreach my $line (@entries) { - my %t = parse_ls_tree_line($line, -z => 1); + my %t = parse_ls_tree_line($line, -z => 1, -l => $show_sizes); if ($alternate) { print "<tr class=\"dark\">\n"; @@ -3599,104 +5516,174 @@ sub git_tree { git_footer_html(); } -sub git_snapshot { - my ($ctype, $suffix, $command) = gitweb_check_feature('snapshot'); - my $have_snapshot = (defined $ctype && defined $suffix); - if (!$have_snapshot) { - die_error('403 Permission denied', "Permission denied"); +sub snapshot_name { + my ($project, $hash) = @_; + + # path/to/project.git -> project + # path/to/project/.git -> project + my $name = to_utf8($project); + $name =~ s,([^/])/*\.git$,$1,; + $name = basename($name); + # sanitize name + $name =~ s/[[:cntrl:]]/?/g; + + my $ver = $hash; + if ($hash =~ /^[0-9a-fA-F]+$/) { + # shorten SHA-1 hash + my $full_hash = git_get_full_hash($project, $hash); + if ($full_hash =~ /^$hash/ && length($hash) > 7) { + $ver = git_get_short_hash($project, $hash); + } + } elsif ($hash =~ m!^refs/tags/(.*)$!) { + # tags don't need shortened SHA-1 hash + $ver = $1; + } else { + # branches and other need shortened SHA-1 hash + if ($hash =~ m!^refs/(?:heads|remotes)/(.*)$!) { + $ver = $1; + } + $ver .= '-' . git_get_short_hash($project, $hash); } + # in case of hierarchical branch names + $ver =~ s!/!.!g; - if (!defined $hash) { - $hash = git_get_head_hash($project); - } + # name = project-version_string + $name = "$name-$ver"; - my $filename = basename($project) . "-$hash.tar.$suffix"; + return wantarray ? ($name, $name) : $name; +} +sub git_snapshot { + my $format = $input_params{'snapshot_format'}; + if (!@snapshot_fmts) { + die_error(403, "Snapshots not allowed"); + } + # default to first supported snapshot format + $format ||= $snapshot_fmts[0]; + if ($format !~ m/^[a-z0-9]+$/) { + die_error(400, "Invalid snapshot format parameter"); + } elsif (!exists($known_snapshot_formats{$format})) { + die_error(400, "Unknown snapshot format"); + } elsif ($known_snapshot_formats{$format}{'disabled'}) { + die_error(403, "Snapshot format not allowed"); + } elsif (!grep($_ eq $format, @snapshot_fmts)) { + die_error(403, "Unsupported snapshot format"); + } + + my $type = git_get_type("$hash^{}"); + if (!$type) { + die_error(404, 'Object does not exist'); + } elsif ($type eq 'blob') { + die_error(400, 'Object is not a tree-ish'); + } + + my ($name, $prefix) = snapshot_name($project, $hash); + my $filename = "$name$known_snapshot_formats{$format}{'suffix'}"; + my $cmd = quote_command( + git_cmd(), 'archive', + "--format=$known_snapshot_formats{$format}{'format'}", + "--prefix=$prefix/", $hash); + if (exists $known_snapshot_formats{$format}{'compressor'}) { + $cmd .= ' | ' . quote_command(@{$known_snapshot_formats{$format}{'compressor'}}); + } + + $filename =~ s/(["\\])/\\$1/g; print $cgi->header( - -type => "application/$ctype", - -content_disposition => 'inline; filename="' . "$filename" . '"', + -type => $known_snapshot_formats{$format}{'type'}, + -content_disposition => 'inline; filename="' . $filename . '"', -status => '200 OK'); - my $git = git_cmd_str(); - my $name = $project; - $name =~ s/\047/\047\\\047\047/g; - open my $fd, "-|", - "$git archive --format=tar --prefix=\'$name\'/ $hash | $command" - or die_error(undef, "Execute git-tar-tree failed."); + open my $fd, "-|", $cmd + or die_error(500, "Execute git-archive failed"); binmode STDOUT, ':raw'; print <$fd>; binmode STDOUT, ':utf8'; # as set at the beginning of gitweb.cgi close $fd; - } -sub git_log { +sub git_log_generic { + my ($fmt_name, $body_subr, $base, $parent, $file_name, $file_hash) = @_; + my $head = git_get_head_hash($project); - if (!defined $hash) { - $hash = $head; + if (!defined $base) { + $base = $head; } if (!defined $page) { $page = 0; } my $refs = git_get_references(); - my @commitlist = parse_commits($hash, 101, (100 * $page)); - - my $paging_nav = format_paging_nav('log', $hash, $head, $page, (100 * ($page+1))); + my $commit_hash = $base; + if (defined $parent) { + $commit_hash = "$parent..$base"; + } + my @commitlist = + parse_commits($commit_hash, 101, (100 * $page), + defined $file_name ? ($file_name, "--full-history") : ()); - git_header_html(); - git_print_page_nav('log','', $hash,undef,undef, $paging_nav); + my $ftype; + if (!defined $file_hash && defined $file_name) { + # some commits could have deleted file in question, + # and not have it in tree, but one of them has to have it + for (my $i = 0; $i < @commitlist; $i++) { + $file_hash = git_get_hash_by_path($commitlist[$i]{'id'}, $file_name); + last if defined $file_hash; + } + } + if (defined $file_hash) { + $ftype = git_get_type($file_hash); + } + if (defined $file_name && !defined $ftype) { + die_error(500, "Unknown type of object"); + } + my %co; + if (defined $file_name) { + %co = parse_commit($base) + or die_error(404, "Unknown commit object"); + } - if (!@commitlist) { - my %co = parse_commit($hash); - git_print_header_div('summary', $project); - print "<div class=\"page_body\"> Last change $co{'age_string'}.<br/><br/></div>\n"; + my $paging_nav = format_paging_nav($fmt_name, $page, $#commitlist >= 100); + my $next_link = ''; + if ($#commitlist >= 100) { + $next_link = + $cgi->a({-href => href(-replay=>1, page=>$page+1), + -accesskey => "n", -title => "Alt-n"}, "next"); } - my $to = ($#commitlist >= 99) ? (99) : ($#commitlist); - for (my $i = 0; $i <= $to; $i++) { - my %co = %{$commitlist[$i]}; - next if !%co; - my $commit = $co{'id'}; - my $ref = format_ref_marker($refs, $commit); - my %ad = parse_date($co{'author_epoch'}); - git_print_header_div('commit', - "<span class=\"age\">$co{'age_string'}</span>" . - esc_html($co{'title'}) . $ref, - $commit); - print "<div class=\"title_text\">\n" . - "<div class=\"log_link\">\n" . - $cgi->a({-href => href(action=>"commit", hash=>$commit)}, "commit") . - " | " . - $cgi->a({-href => href(action=>"commitdiff", hash=>$commit)}, "commitdiff") . - " | " . - $cgi->a({-href => href(action=>"tree", hash=>$commit, hash_base=>$commit)}, "tree") . - "<br/>\n" . - "</div>\n" . - "<i>" . esc_html($co{'author_name'}) . " [$ad{'rfc2822'}]</i><br/>\n" . - "</div>\n"; - - print "<div class=\"log_body\">\n"; - git_print_log($co{'comment'}, -final_empty_line=> 1); - print "</div>\n"; + my $patch_max = gitweb_get_feature('patches'); + if ($patch_max && !defined $file_name) { + if ($patch_max < 0 || @commitlist <= $patch_max) { + $paging_nav .= " ⋅ " . + $cgi->a({-href => href(action=>"patches", -replay=>1)}, + "patches"); + } } - if ($#commitlist >= 100) { - print "<div class=\"page_nav\">\n"; - print $cgi->a({-href => href(action=>"log", hash=>$hash, page=>$page+1), - -accesskey => "n", -title => "Alt-n"}, "next"); - print "</div>\n"; + + git_header_html(); + git_print_page_nav($fmt_name,'', $hash,$hash,$hash, $paging_nav); + if (defined $file_name) { + git_print_header_div('commit', esc_html($co{'title'}), $base); + } else { + git_print_header_div('summary', $project) } + git_print_page_path($file_name, $ftype, $hash_base) + if (defined $file_name); + + $body_subr->(\@commitlist, 0, 99, $refs, $next_link, + $file_name, $file_hash, $ftype); + git_footer_html(); } +sub git_log { + git_log_generic('log', \&git_log_body, + $hash, $hash_parent); +} + sub git_commit { $hash ||= $hash_base || "HEAD"; - my %co = parse_commit($hash); - if (!%co) { - die_error(undef, "Unknown commit object"); - } - my %ad = parse_date($co{'author_epoch'}, $co{'author_tz'}); - my %cd = parse_date($co{'committer_epoch'}, $co{'committer_tz'}); + my %co = parse_commit($hash) + or die_error(404, "Unknown commit object"); my $parent = $co{'parent'}; my $parents = $co{'parents'}; # listref @@ -3719,25 +5706,29 @@ sub git_commit { $formats_nav .= '(merge: ' . join(' ', map { - $cgi->a({-href => href(action=>"commitdiff", + $cgi->a({-href => href(action=>"commit", hash=>$_)}, esc_html(substr($_, 0, 7))); } @$parents ) . ')'; } + if (gitweb_check_feature('patches') && @$parents <= 1) { + $formats_nav .= " | " . + $cgi->a({-href => href(action=>"patch", -replay=>1)}, + "patch"); + } if (!defined $parent) { $parent = "--root"; } my @difftree; - if (@$parents <= 1) { - # difftree output is not printed for merges - open my $fd, "-|", git_cmd(), "diff-tree", '-r', "--no-commit-id", - @diff_opts, $parent, $hash, "--" - or die_error(undef, "Open git-diff-tree failed"); - @difftree = map { chomp; $_ } <$fd>; - close $fd or die_error(undef, "Reading git-diff-tree failed"); - } + open my $fd, "-|", git_cmd(), "diff-tree", '-r', "--no-commit-id", + @diff_opts, + (@$parents <= 1 ? $parent : '-c'), + $hash, "--" + or die_error(500, "Open git-diff-tree failed"); + @difftree = map { chomp; $_ } <$fd>; + close $fd or die_error(404, "Reading git-diff-tree failed"); # non-textual hash id's can be cached my $expires; @@ -3747,8 +5738,6 @@ sub git_commit { my $refs = git_get_references(); my $ref = format_ref_marker($refs, $co{'id'}); - my $have_snapshot = gitweb_have_snapshot(); - git_header_html(undef, $expires); git_print_page_nav('commit', '', $hash, $co{'tree'}, $hash, @@ -3760,23 +5749,8 @@ sub git_commit { git_print_header_div('tree', esc_html($co{'title'}) . $ref, $co{'tree'}, $hash); } print "<div class=\"title_text\">\n" . - "<table cellspacing=\"0\">\n"; - print "<tr><td>author</td><td>" . esc_html($co{'author'}) . "</td></tr>\n". - "<tr>" . - "<td></td><td> $ad{'rfc2822'}"; - if ($ad{'hour_local'} < 6) { - printf(" (<span class=\"atnight\">%02d:%02d</span> %s)", - $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}); - } else { - printf(" (%02d:%02d %s)", - $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}); - } - print "</td>" . - "</tr>\n"; - print "<tr><td>committer</td><td>" . esc_html($co{'committer'}) . "</td></tr>\n"; - print "<tr><td></td><td> $cd{'rfc2822'}" . - sprintf(" (%02d:%02d %s)", $cd{'hour_local'}, $cd{'minute_local'}, $cd{'tz_local'}) . - "</td></tr>\n"; + "<table class=\"object_header\">\n"; + git_print_authorship_rows(\%co); print "<tr><td>commit</td><td class=\"sha1\">$co{'id'}</td></tr>\n"; print "<tr>" . "<td>tree</td>" . @@ -3787,9 +5761,9 @@ sub git_commit { "<td class=\"link\">" . $cgi->a({-href => href(action=>"tree", hash=>$co{'tree'}, hash_base=>$hash)}, "tree"); - if ($have_snapshot) { - print " | " . - $cgi->a({-href => href(action=>"snapshot", hash=>$hash)}, "snapshot"); + my $snapshot_links = format_snapshot_links($hash); + if (defined $snapshot_links) { + print " | " . $snapshot_links; } print "</td>" . "</tr>\n"; @@ -3815,10 +5789,7 @@ sub git_commit { git_print_log($co{'comment'}); print "</div>\n"; - if (@$parents <= 1) { - # do not output difftree/whatchanged for merges - git_difftree_body(\@difftree, $hash, $parent); - } + git_difftree_body(\@difftree, $hash, @$parents); git_footer_html(); } @@ -3833,35 +5804,35 @@ sub git_object { if ($hash || ($hash_base && !defined $file_name)) { my $object_id = $hash || $hash_base; - my $git_command = git_cmd_str(); - open my $fd, "-|", "$git_command cat-file -t $object_id 2>/dev/null" - or die_error('404 Not Found', "Object does not exist"); + open my $fd, "-|", quote_command( + git_cmd(), 'cat-file', '-t', $object_id) . ' 2> /dev/null' + or die_error(404, "Object does not exist"); $type = <$fd>; chomp $type; close $fd - or die_error('404 Not Found', "Object does not exist"); + or die_error(404, "Object does not exist"); # - hash_base and file_name } elsif ($hash_base && defined $file_name) { $file_name =~ s,/+$,,; system(git_cmd(), "cat-file", '-e', $hash_base) == 0 - or die_error('404 Not Found', "Base object does not exist"); + or die_error(404, "Base object does not exist"); # here errors should not hapen open my $fd, "-|", git_cmd(), "ls-tree", $hash_base, "--", $file_name - or die_error(undef, "Open git-ls-tree failed"); + or die_error(500, "Open git-ls-tree failed"); my $line = <$fd>; close $fd; #'100644 blob 0fa3f3a66fb6a137f6ec2c19351ed4d807070ffa panic.c' unless ($line && $line =~ m/^([0-9]+) (.+) ([0-9a-fA-F]{40})\t/) { - die_error('404 Not Found', "File or directory for given base does not exist"); + die_error(404, "File or directory for given base does not exist"); } $type = $2; $hash = $3; } else { - die_error('404 Not Found', "Not enough information to find object"); + die_error(400, "Not enough information to find object"); } print $cgi->redirect(-uri => href(action=>$type, -full=>1, @@ -3885,13 +5856,13 @@ sub git_blobdiff { # read raw output open $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, $hash_parent_base, $hash_base, - "--", $file_name - or die_error(undef, "Open git-diff-tree failed"); + "--", (defined $file_parent ? $file_parent : ()), $file_name + or die_error(500, "Open git-diff-tree failed"); @difftree = map { chomp; $_ } <$fd>; close $fd - or die_error(undef, "Reading git-diff-tree failed"); + or die_error(404, "Reading git-diff-tree failed"); @difftree - or die_error('404 Not Found', "Blob diff not found"); + or die_error(404, "Blob diff not found"); } elsif (defined $hash && $hash =~ /[0-9a-fA-F]{40}/) { @@ -3900,28 +5871,28 @@ sub git_blobdiff { # read filtered raw output open $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, $hash_parent_base, $hash_base, "--" - or die_error(undef, "Open git-diff-tree failed"); + or die_error(500, "Open git-diff-tree failed"); @difftree = # ':100644 100644 03b21826... 3b93d5e7... M ls-files.c' # $hash == to_id grep { /^:[0-7]{6} [0-7]{6} [0-9a-fA-F]{40} $hash/ } map { chomp; $_ } <$fd>; close $fd - or die_error(undef, "Reading git-diff-tree failed"); + or die_error(404, "Reading git-diff-tree failed"); @difftree - or die_error('404 Not Found', "Blob diff not found"); + or die_error(404, "Blob diff not found"); } else { - die_error('404 Not Found', "Missing one of the blob diff parameters"); + die_error(400, "Missing one of the blob diff parameters"); } if (@difftree > 1) { - die_error('404 Not Found', "Ambiguous blob diff specification"); + die_error(400, "Ambiguous blob diff specification"); } %diffinfo = parse_difftree_raw_line($difftree[0]); - $file_parent ||= $diffinfo{'from_file'} || $file_name || $diffinfo{'file'}; - $file_name ||= $diffinfo{'to_file'} || $diffinfo{'file'}; + $file_parent ||= $diffinfo{'from_file'} || $file_name; + $file_name ||= $diffinfo{'to_file'}; $hash_parent ||= $diffinfo{'from_id'}; $hash ||= $diffinfo{'to_id'}; @@ -3934,56 +5905,21 @@ sub git_blobdiff { # open patch output open $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, - '-p', $hash_parent_base, $hash_base, - "--", $file_name - or die_error(undef, "Open git-diff-tree failed"); - } - - # old/legacy style URI - if (!%diffinfo && # if new style URI failed - defined $hash && defined $hash_parent) { - # fake git-diff-tree raw output - $diffinfo{'from_mode'} = $diffinfo{'to_mode'} = "blob"; - $diffinfo{'from_id'} = $hash_parent; - $diffinfo{'to_id'} = $hash; - if (defined $file_name) { - if (defined $file_parent) { - $diffinfo{'status'} = '2'; - $diffinfo{'from_file'} = $file_parent; - $diffinfo{'to_file'} = $file_name; - } else { # assume not renamed - $diffinfo{'status'} = '1'; - $diffinfo{'from_file'} = $file_name; - $diffinfo{'to_file'} = $file_name; - } - } else { # no filename given - $diffinfo{'status'} = '2'; - $diffinfo{'from_file'} = $hash_parent; - $diffinfo{'to_file'} = $hash; - } - - # non-textual hash id's can be cached - if ($hash =~ m/^[0-9a-fA-F]{40}$/ && - $hash_parent =~ m/^[0-9a-fA-F]{40}$/) { - $expires = '+1d'; - } + '-p', ($format eq 'html' ? "--full-index" : ()), + $hash_parent_base, $hash_base, + "--", (defined $file_parent ? $file_parent : ()), $file_name + or die_error(500, "Open git-diff-tree failed"); + } - # open patch output - open $fd, "-|", git_cmd(), "diff", '-p', @diff_opts, - $hash_parent, $hash, "--" - or die_error(undef, "Open git-diff failed"); - } else { + # old/legacy style URI -- not generated anymore since 1.4.3. + if (!%diffinfo) { die_error('404 Not Found', "Missing one of the blob diff parameters") - unless %diffinfo; } # header if ($format eq 'html') { my $formats_nav = - $cgi->a({-href => href(action=>"blobdiff_plain", - hash=>$hash, hash_parent=>$hash_parent, - hash_base=>$hash_base, hash_parent_base=>$hash_parent_base, - file_name=>$file_name, file_parent=>$file_parent)}, + $cgi->a({-href => href(action=>"blobdiff_plain", -replay=>1)}, "raw"); git_header_html(undef, $expires); if (defined $hash_base && (my %co = parse_commit($hash_base))) { @@ -4009,7 +5945,7 @@ sub git_blobdiff { print "X-Git-Url: " . $cgi->self_url() . "\n\n"; } else { - die_error(undef, "Unknown blobdiff format"); + die_error(400, "Unknown blobdiff format"); } # patch @@ -4042,29 +5978,50 @@ sub git_blobdiff_plain { } sub git_commitdiff { - my $format = shift || 'html'; - $hash ||= $hash_base || "HEAD"; - my %co = parse_commit($hash); - if (!%co) { - die_error(undef, "Unknown commit object"); + my %params = @_; + my $format = $params{-format} || 'html'; + + my ($patch_max) = gitweb_get_feature('patches'); + if ($format eq 'patch') { + die_error(403, "Patch view not allowed") unless $patch_max; } - # we need to prepare $formats_nav before any parameter munging + $hash ||= $hash_base || "HEAD"; + my %co = parse_commit($hash) + or die_error(404, "Unknown commit object"); + + # choose format for commitdiff for merge + if (! defined $hash_parent && @{$co{'parents'}} > 1) { + $hash_parent = '--cc'; + } + # we need to prepare $formats_nav before almost any parameter munging my $formats_nav; if ($format eq 'html') { $formats_nav = - $cgi->a({-href => href(action=>"commitdiff_plain", - hash=>$hash, hash_parent=>$hash_parent)}, + $cgi->a({-href => href(action=>"commitdiff_plain", -replay=>1)}, "raw"); + if ($patch_max && @{$co{'parents'}} <= 1) { + $formats_nav .= " | " . + $cgi->a({-href => href(action=>"patch", -replay=>1)}, + "patch"); + } - if (defined $hash_parent) { + if (defined $hash_parent && + $hash_parent ne '-c' && $hash_parent ne '--cc') { # commitdiff with two commits given my $hash_parent_short = $hash_parent; if ($hash_parent =~ m/^[0-9a-fA-F]{40}$/) { $hash_parent_short = substr($hash_parent, 0, 7); } $formats_nav .= - ' (from: ' . + ' (from'; + for (my $i = 0; $i < @{$co{'parents'}}; $i++) { + if ($co{'parents'}[$i] eq $hash_parent) { + $formats_nav .= ' parent ' . ($i+1); + last; + } + } + $formats_nav .= ': ' . $cgi->a({-href => href(action=>"commitdiff", hash=>$hash_parent)}, esc_html($hash_parent_short)) . @@ -4082,6 +6039,17 @@ sub git_commitdiff { ')'; } else { # merge commit + if ($hash_parent eq '--cc') { + $formats_nav .= ' | ' . + $cgi->a({-href => href(action=>"commitdiff", + hash=>$hash, hash_parent=>'-c')}, + 'combined'); + } else { # $hash_parent eq '-c' + $formats_nav .= ' | ' . + $cgi->a({-href => href(action=>"commitdiff", + hash=>$hash, hash_parent=>'--cc')}, + 'compact'); + } $formats_nav .= ' (merge: ' . join(' ', map { @@ -4093,8 +6061,11 @@ sub git_commitdiff { } } - if (!defined $hash_parent) { - $hash_parent = $co{'parent'} || '--root'; + my $hash_parent_param = $hash_parent; + if (!defined $hash_parent_param) { + # --cc for multiple parents, --root for parentless + $hash_parent_param = + @{$co{'parents'}} > 1 ? '--cc' : $co{'parent'} || '--root'; } # read commitdiff @@ -4103,23 +6074,47 @@ sub git_commitdiff { if ($format eq 'html') { open $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, "--no-commit-id", "--patch-with-raw", "--full-index", - $hash_parent, $hash, "--" - or die_error(undef, "Open git-diff-tree failed"); + $hash_parent_param, $hash, "--" + or die_error(500, "Open git-diff-tree failed"); while (my $line = <$fd>) { chomp $line; # empty line ends raw part of diff-tree output last unless $line; - push @difftree, $line; + push @difftree, scalar parse_difftree_raw_line($line); } } elsif ($format eq 'plain') { open $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, - '-p', $hash_parent, $hash, "--" - or die_error(undef, "Open git-diff-tree failed"); - + '-p', $hash_parent_param, $hash, "--" + or die_error(500, "Open git-diff-tree failed"); + } elsif ($format eq 'patch') { + # For commit ranges, we limit the output to the number of + # patches specified in the 'patches' feature. + # For single commits, we limit the output to a single patch, + # diverging from the git-format-patch default. + my @commit_spec = (); + if ($hash_parent) { + if ($patch_max > 0) { + push @commit_spec, "-$patch_max"; + } + push @commit_spec, '-n', "$hash_parent..$hash"; + } else { + if ($params{-single}) { + push @commit_spec, '-1'; + } else { + if ($patch_max > 0) { + push @commit_spec, "-$patch_max"; + } + push @commit_spec, "-n"; + } + push @commit_spec, '--root', $hash; + } + open $fd, "-|", git_cmd(), "format-patch", '--encoding=utf8', + '--stdout', @commit_spec + or die_error(500, "Open git-format-patch failed"); } else { - die_error(undef, "Unknown commitdiff format"); + die_error(400, "Unknown commitdiff format"); } # non-textual hash id's can be cached @@ -4136,7 +6131,11 @@ sub git_commitdiff { git_header_html(undef, $expires); git_print_page_nav('commitdiff','', $hash,$co{'tree'},$hash, $formats_nav); git_print_header_div('commit', esc_html($co{'title'}) . $ref, $hash); - git_print_authorship(\%co); + print "<div class=\"title_text\">\n" . + "<table class=\"object_header\">\n"; + git_print_authorship_rows(\%co); + print "</table>". + "</div>\n"; print "<div class=\"page_body\">\n"; if (@{$co{'comment'}} > 1) { print "<div class=\"log\">\n"; @@ -4155,26 +6154,37 @@ sub git_commitdiff { -expires => $expires, -content_disposition => 'inline; filename="' . "$filename" . '"'); my %ad = parse_date($co{'author_epoch'}, $co{'author_tz'}); - print <<TEXT; -From: $co{'author'} -Date: $ad{'rfc2822'} ($ad{'tz_local'}) -Subject: $co{'title'} -TEXT + print "From: " . to_utf8($co{'author'}) . "\n"; + print "Date: $ad{'rfc2822'} ($ad{'tz_local'})\n"; + print "Subject: " . to_utf8($co{'title'}) . "\n"; + print "X-Git-Tag: $tagname\n" if $tagname; print "X-Git-Url: " . $cgi->self_url() . "\n\n"; foreach my $line (@{$co{'comment'}}) { - print "$line\n"; + print to_utf8($line) . "\n"; } print "---\n\n"; + } elsif ($format eq 'patch') { + my $filename = basename($project) . "-$hash.patch"; + + print $cgi->header( + -type => 'text/plain', + -charset => 'utf-8', + -expires => $expires, + -content_disposition => 'inline; filename="' . "$filename" . '"'); } # write patch if ($format eq 'html') { - git_difftree_body(\@difftree, $hash, $hash_parent); + my $use_parents = !defined $hash_parent || + $hash_parent eq '-c' || $hash_parent eq '--cc'; + git_difftree_body(\@difftree, $hash, + $use_parents ? @{$co{'parents'}} : $hash_parent); print "<br/>\n"; - git_patchset_body($fd, \@difftree, $hash, $hash_parent); + git_patchset_body($fd, \@difftree, $hash, + $use_parents ? @{$co{'parents'}} : $hash_parent); close $fd; print "</div>\n"; # class="page_body" git_footer_html(); @@ -4184,93 +6194,44 @@ TEXT print <$fd>; close $fd or print "Reading git-diff-tree failed\n"; + } elsif ($format eq 'patch') { + local $/ = undef; + print <$fd>; + close $fd + or print "Reading git-format-patch failed\n"; } } sub git_commitdiff_plain { - git_commitdiff('plain'); + git_commitdiff(-format => 'plain'); } -sub git_history { - if (!defined $hash_base) { - $hash_base = git_get_head_hash($project); - } - if (!defined $page) { - $page = 0; - } - my $ftype; - my %co = parse_commit($hash_base); - if (!%co) { - die_error(undef, "Unknown commit object"); - } - - my $refs = git_get_references(); - my $limit = sprintf("--max-count=%i", (100 * ($page+1))); - - if (!defined $hash && defined $file_name) { - $hash = git_get_hash_by_path($hash_base, $file_name); - } - if (defined $hash) { - $ftype = git_get_type($hash); - } - - my @commitlist = parse_commits($hash_base, 101, (100 * $page), "--full-history", $file_name); - - my $paging_nav = ''; - if ($page > 0) { - $paging_nav .= - $cgi->a({-href => href(action=>"history", hash=>$hash, hash_base=>$hash_base, - file_name=>$file_name)}, - "first"); - $paging_nav .= " ⋅ " . - $cgi->a({-href => href(action=>"history", hash=>$hash, hash_base=>$hash_base, - file_name=>$file_name, page=>$page-1), - -accesskey => "p", -title => "Alt-p"}, "prev"); - } else { - $paging_nav .= "first"; - $paging_nav .= " ⋅ prev"; - } - if ($#commitlist >= 100) { - $paging_nav .= " ⋅ " . - $cgi->a({-href => href(action=>"history", hash=>$hash, hash_base=>$hash_base, - file_name=>$file_name, page=>$page+1), - -accesskey => "n", -title => "Alt-n"}, "next"); - } else { - $paging_nav .= " ⋅ next"; - } - my $next_link = ''; - if ($#commitlist >= 100) { - $next_link = - $cgi->a({-href => href(action=>"history", hash=>$hash, hash_base=>$hash_base, - file_name=>$file_name, page=>$page+1), - -accesskey => "n", -title => "Alt-n"}, "next"); - } - - git_header_html(); - git_print_page_nav('history','', $hash_base,$co{'tree'},$hash_base, $paging_nav); - git_print_header_div('commit', esc_html($co{'title'}), $hash_base); - git_print_page_path($file_name, $ftype, $hash_base); +# format-patch-style patches +sub git_patch { + git_commitdiff(-format => 'patch', -single => 1); +} - git_history_body(\@commitlist, 0, 99, - $refs, $hash_base, $ftype, $next_link); +sub git_patches { + git_commitdiff(-format => 'patch'); +} - git_footer_html(); +sub git_history { + git_log_generic('history', \&git_history_body, + $hash_base, $hash_parent_base, + $file_name, $hash); } sub git_search { - my ($have_search) = gitweb_check_feature('search'); - if (!$have_search) { - die_error('403 Permission denied', "Permission denied"); - } + gitweb_check_feature('search') or die_error(403, "Search is disabled"); if (!defined $searchtext) { - die_error(undef, "Text field empty"); + die_error(400, "Text field is empty"); } if (!defined $hash) { $hash = git_get_head_hash($project); } my %co = parse_commit($hash); if (!%co) { - die_error(undef, "Unknown commit object"); + die_error(404, "Unknown commit object"); } if (!defined $page) { $page = 0; @@ -4280,10 +6241,12 @@ sub git_search { if ($searchtype eq 'pickaxe') { # pickaxe may take all resources of your box and run for several minutes # with every query - so decide by yourself how public you make this feature - my ($have_pickaxe) = gitweb_check_feature('pickaxe'); - if (!$have_pickaxe) { - die_error('403 Permission denied', "Permission denied"); - } + gitweb_check_feature('pickaxe') + or die_error(403, "Pickaxe is disabled"); + } + if ($searchtype eq 'grep') { + gitweb_check_feature('grep') + or die_error(403, "Grep is disabled"); } git_header_html(); @@ -4298,39 +6261,35 @@ sub git_search { $greptype = "--committer="; } $greptype .= $searchtext; - my @commitlist = parse_commits($hash, 101, (100 * $page), $greptype); + my @commitlist = parse_commits($hash, 101, (100 * $page), undef, + $greptype, '--regexp-ignore-case', + $search_use_regexp ? '--extended-regexp' : '--fixed-strings'); my $paging_nav = ''; if ($page > 0) { $paging_nav .= $cgi->a({-href => href(action=>"search", hash=>$hash, - searchtext=>$searchtext, searchtype=>$searchtype)}, - "first"); + searchtext=>$searchtext, + searchtype=>$searchtype)}, + "first"); $paging_nav .= " ⋅ " . - $cgi->a({-href => href(action=>"search", hash=>$hash, - searchtext=>$searchtext, searchtype=>$searchtype, - page=>$page-1), - -accesskey => "p", -title => "Alt-p"}, "prev"); + $cgi->a({-href => href(-replay=>1, page=>$page-1), + -accesskey => "p", -title => "Alt-p"}, "prev"); } else { $paging_nav .= "first"; $paging_nav .= " ⋅ prev"; } + my $next_link = ''; if ($#commitlist >= 100) { - $paging_nav .= " ⋅ " . - $cgi->a({-href => href(action=>"search", hash=>$hash, - searchtext=>$searchtext, searchtype=>$searchtype, - page=>$page+1), - -accesskey => "n", -title => "Alt-n"}, "next"); + $next_link = + $cgi->a({-href => href(-replay=>1, page=>$page+1), + -accesskey => "n", -title => "Alt-n"}, "next"); + $paging_nav .= " ⋅ $next_link"; } else { $paging_nav .= " ⋅ next"; } - my $next_link = ''; + if ($#commitlist >= 100) { - $next_link = - $cgi->a({-href => href(action=>"search", hash=>$hash, - searchtext=>$searchtext, searchtype=>$searchtype, - page=>$page+1), - -accesskey => "n", -title => "Alt-n"}, "next"); } git_print_page_nav('','', $hash,$co{'tree'},$hash, $paging_nav); @@ -4342,50 +6301,22 @@ sub git_search { git_print_page_nav('','', $hash,$co{'tree'},$hash); git_print_header_div('commit', esc_html($co{'title'}), $hash); - print "<table cellspacing=\"0\">\n"; + print "<table class=\"pickaxe search\">\n"; my $alternate = 1; - $/ = "\n"; - my $git_command = git_cmd_str(); - open my $fd, "-|", "$git_command rev-list $hash | " . - "$git_command diff-tree -r --stdin -S\'$searchtext\'"; + local $/ = "\n"; + open my $fd, '-|', git_cmd(), '--no-pager', 'log', @diff_opts, + '--pretty=format:%H', '--no-abbrev', '--raw', "-S$searchtext", + ($search_use_regexp ? '--pickaxe-regex' : ()); undef %co; my @files; while (my $line = <$fd>) { - if (%co && $line =~ m/^:([0-7]{6}) ([0-7]{6}) ([0-9a-fA-F]{40}) ([0-9a-fA-F]{40}) (.)\t(.*)$/) { - my %set; - $set{'file'} = $6; - $set{'from_id'} = $3; - $set{'to_id'} = $4; - $set{'id'} = $set{'to_id'}; - if ($set{'id'} =~ m/0{40}/) { - $set{'id'} = $set{'from_id'}; - } - if ($set{'id'} =~ m/0{40}/) { - next; - } - push @files, \%set; - } elsif ($line =~ m/^([0-9a-fA-F]{40})$/){ + chomp $line; + next unless $line; + + my %set = parse_difftree_raw_line($line); + if (defined $set{'commit'}) { + # finish previous commit if (%co) { - if ($alternate) { - print "<tr class=\"dark\">\n"; - } else { - print "<tr class=\"light\">\n"; - } - $alternate ^= 1; - print "<td title=\"$co{'age_string_age'}\"><i>$co{'age_string_date'}</i></td>\n" . - "<td><i>" . esc_html(chop_str($co{'author_name'}, 15, 5)) . "</i></td>\n" . - "<td>" . - $cgi->a({-href => href(action=>"commit", hash=>$co{'id'}), - -class => "list subject"}, - esc_html(chop_str($co{'title'}, 50)) . "<br/>"); - while (my $setref = shift @files) { - my %set = %$setref; - print $cgi->a({-href => href(action=>"blob", hash_base=>$co{'id'}, - hash=>$set{'id'}, file_name=>$set{'file'}), - -class => "list"}, - "<span class=\"match\">" . esc_path($set{'file'}) . "</span>") . - "<br/>\n"; - } print "</td>\n" . "<td class=\"link\">" . $cgi->a({-href => href(action=>"commit", hash=>$co{'id'})}, "commit") . @@ -4394,11 +6325,113 @@ sub git_search { print "</td>\n" . "</tr>\n"; } - %co = parse_commit($1); + + if ($alternate) { + print "<tr class=\"dark\">\n"; + } else { + print "<tr class=\"light\">\n"; + } + $alternate ^= 1; + %co = parse_commit($set{'commit'}); + my $author = chop_and_escape_str($co{'author_name'}, 15, 5); + print "<td title=\"$co{'age_string_age'}\"><i>$co{'age_string_date'}</i></td>\n" . + "<td><i>$author</i></td>\n" . + "<td>" . + $cgi->a({-href => href(action=>"commit", hash=>$co{'id'}), + -class => "list subject"}, + chop_and_escape_str($co{'title'}, 50) . "<br/>"); + } elsif (defined $set{'to_id'}) { + next if ($set{'to_id'} =~ m/^0{40}$/); + + print $cgi->a({-href => href(action=>"blob", hash_base=>$co{'id'}, + hash=>$set{'to_id'}, file_name=>$set{'to_file'}), + -class => "list"}, + "<span class=\"match\">" . esc_path($set{'file'}) . "</span>") . + "<br/>\n"; } } close $fd; + # finish last commit (warning: repetition!) + if (%co) { + print "</td>\n" . + "<td class=\"link\">" . + $cgi->a({-href => href(action=>"commit", hash=>$co{'id'})}, "commit") . + " | " . + $cgi->a({-href => href(action=>"tree", hash=>$co{'tree'}, hash_base=>$co{'id'})}, "tree"); + print "</td>\n" . + "</tr>\n"; + } + + print "</table>\n"; + } + + if ($searchtype eq 'grep') { + git_print_page_nav('','', $hash,$co{'tree'},$hash); + git_print_header_div('commit', esc_html($co{'title'}), $hash); + + print "<table class=\"grep_search\">\n"; + my $alternate = 1; + my $matches = 0; + local $/ = "\n"; + open my $fd, "-|", git_cmd(), 'grep', '-n', + $search_use_regexp ? ('-E', '-i') : '-F', + $searchtext, $co{'tree'}; + my $lastfile = ''; + while (my $line = <$fd>) { + chomp $line; + my ($file, $lno, $ltext, $binary); + last if ($matches++ > 1000); + if ($line =~ /^Binary file (.+) matches$/) { + $file = $1; + $binary = 1; + } else { + (undef, $file, $lno, $ltext) = split(/:/, $line, 4); + } + if ($file ne $lastfile) { + $lastfile and print "</td></tr>\n"; + if ($alternate++) { + print "<tr class=\"dark\">\n"; + } else { + print "<tr class=\"light\">\n"; + } + print "<td class=\"list\">". + $cgi->a({-href => href(action=>"blob", hash=>$co{'hash'}, + file_name=>"$file"), + -class => "list"}, esc_path($file)); + print "</td><td>\n"; + $lastfile = $file; + } + if ($binary) { + print "<div class=\"binary\">Binary file</div>\n"; + } else { + $ltext = untabify($ltext); + if ($ltext =~ m/^(.*)($search_regexp)(.*)$/i) { + $ltext = esc_html($1, -nbsp=>1); + $ltext .= '<span class="match">'; + $ltext .= esc_html($2, -nbsp=>1); + $ltext .= '</span>'; + $ltext .= esc_html($3, -nbsp=>1); + } else { + $ltext = esc_html($ltext, -nbsp=>1); + } + print "<div class=\"pre\">" . + $cgi->a({-href => href(action=>"blob", hash=>$co{'hash'}, + file_name=>"$file").'#l'.$lno, + -class => "linenr"}, sprintf('%4i', $lno)) + . ' ' . $ltext . "</div>\n"; + } + } + if ($lastfile) { + print "</td></tr>\n"; + if ($matches > 1000) { + print "<div class=\"diff nodifferences\">Too many matches, listing trimmed</div>\n"; + } + } else { + print "<div class=\"diff nodifferences\">No matches found</div>\n"; + } + close $fd; + print "</table>\n"; } git_footer_html(); @@ -4408,21 +6441,40 @@ sub git_search_help { git_header_html(); git_print_page_nav('','', $hash,$hash,$hash); print <<EOT; +<p><strong>Pattern</strong> is by default a normal string that is matched precisely (but without +regard to case, except in the case of pickaxe). However, when you check the <em>re</em> checkbox, +the pattern entered is recognized as the POSIX extended +<a href="http://en.wikipedia.org/wiki/Regular_expression">regular expression</a> (also case +insensitive).</p> <dl> <dt><b>commit</b></dt> -<dd>The commit messages and authorship information will be scanned for the given string.</dd> +<dd>The commit messages and authorship information will be scanned for the given pattern.</dd> +EOT + my $have_grep = gitweb_check_feature('grep'); + if ($have_grep) { + print <<EOT; +<dt><b>grep</b></dt> +<dd>All files in the currently selected tree (HEAD unless you are explicitly browsing + a different one) are searched for the given pattern. On large trees, this search can take +a while and put some strain on the server, so please use it with some consideration. Note that +due to git-grep peculiarity, currently if regexp mode is turned off, the matches are +case-sensitive.</dd> +EOT + } + print <<EOT; <dt><b>author</b></dt> -<dd>Name and e-mail of the change author and date of birth of the patch will be scanned for the given string.</dd> +<dd>Name and e-mail of the change author and date of birth of the patch will be scanned for the given pattern.</dd> <dt><b>committer</b></dt> -<dd>Name and e-mail of the committer and date of commit will be scanned for the given string.</dd> +<dd>Name and e-mail of the committer and date of commit will be scanned for the given pattern.</dd> EOT - my ($have_pickaxe) = gitweb_check_feature('pickaxe'); + my $have_pickaxe = gitweb_check_feature('pickaxe'); if ($have_pickaxe) { print <<EOT; <dt><b>pickaxe</b></dt> <dd>All commits that caused the string to appear or disappear from any file (changes that added, removed or "modified" the string) will be listed. This search can take a while and -takes a lot of strain on the server, so please use it wisely.</dd> +takes a lot of strain on the server, so please use it wisely. Note that since you may be +interested even in changes just changing the case as well, this search is case sensitive.</dd> EOT } print "</dl>\n"; @@ -4430,32 +6482,8 @@ EOT } sub git_shortlog { - my $head = git_get_head_hash($project); - if (!defined $hash) { - $hash = $head; - } - if (!defined $page) { - $page = 0; - } - my $refs = git_get_references(); - - my @commitlist = parse_commits($hash, 101, (100 * $page)); - - my $paging_nav = format_paging_nav('shortlog', $hash, $head, $page, (100 * ($page+1))); - my $next_link = ''; - if ($#commitlist >= 100) { - $next_link = - $cgi->a({-href => href(action=>"shortlog", hash=>$hash, page=>$page+1), - -accesskey => "n", -title => "Alt-n"}, "next"); - } - - git_header_html(); - git_print_page_nav('shortlog','', $hash,$hash,$hash, $paging_nav); - git_print_header_div('summary', $project); - - git_shortlog_body(\@commitlist, 0, 99, $refs, $next_link); - - git_footer_html(); + git_log_generic('shortlog', \&git_shortlog_body, + $hash, $hash_parent); } ## ...................................................................... @@ -4463,17 +6491,17 @@ sub git_shortlog { sub git_feed { my $format = shift || 'atom'; - my ($have_blame) = gitweb_check_feature('blame'); + my $have_blame = gitweb_check_feature('blame'); # Atom: http://www.atomenabled.org/developers/syndication/ # RSS: http://www.notestips.com/80256B3A007F2692/1/NAMO5P9UPQ if ($format ne 'rss' && $format ne 'atom') { - die_error(undef, "Unknown web feed format"); + die_error(400, "Unknown web feed format"); } # log/feed of current (HEAD) branch, log of given branch, history of file/directory my $head = $hash || 'HEAD'; - my @commitlist = parse_commits($head, 150); + my @commitlist = parse_commits($head, 150, 0, $file_name); my %latest_commit; my %latest_date; @@ -4485,7 +6513,25 @@ sub git_feed { } if (defined($commitlist[0])) { %latest_commit = %{$commitlist[0]}; - %latest_date = parse_date($latest_commit{'author_epoch'}); + my $latest_epoch = $latest_commit{'committer_epoch'}; + %latest_date = parse_date($latest_epoch); + my $if_modified = $cgi->http('IF_MODIFIED_SINCE'); + if (defined $if_modified) { + my $since; + if (eval { require HTTP::Date; 1; }) { + $since = HTTP::Date::str2time($if_modified); + } elsif (eval { require Time::ParseDate; 1; }) { + $since = Time::ParseDate::parsedate($if_modified, GMT => 1); + } + if (defined $since && $latest_epoch <= $since) { + print $cgi->header( + -type => $content_type, + -charset => 'utf-8', + -last_modified => $latest_date{'rfc2822'}, + -status => '304 Not Modified'); + return; + } + } print $cgi->header( -type => $content_type, -charset => 'utf-8', @@ -4544,7 +6590,24 @@ XML print "<title>$title</title>\n" . "<link>$alt_url</link>\n" . "<description>$descr</description>\n" . - "<language>en</language>\n"; + "<language>en</language>\n" . + # project owner is responsible for 'editorial' content + "<managingEditor>$owner</managingEditor>\n"; + if (defined $logo || defined $favicon) { + # prefer the logo to the favicon, since RSS + # doesn't allow both + my $img = esc_url($logo || $favicon); + print "<image>\n" . + "<url>$img</url>\n" . + "<title>$title</title>\n" . + "<link>$alt_url</link>\n" . + "</image>\n"; + } + if (%latest_date) { + print "<pubDate>$latest_date{'rfc2822'}</pubDate>\n"; + print "<lastBuildDate>$latest_date{'rfc2822'}</lastBuildDate>\n"; + } + print "<generator>gitweb v.$version/$git_version</generator>\n"; } elsif ($format eq 'atom') { print <<XML; <feed xmlns="http://www.w3.org/2005/Atom"> @@ -4571,6 +6634,7 @@ XML } else { print "<updated>$latest_date{'iso-8601'}</updated>\n"; } + print "<generator version='$version/$git_version'>gitweb</generator>\n"; } # contents @@ -4585,14 +6649,15 @@ XML # get list of changed files open my $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, - $co{'parent'}, $co{'id'}, "--", (defined $file_name ? $file_name : ()) + $co{'parent'} || "--root", + $co{'id'}, "--", (defined $file_name ? $file_name : ()) or next; my @difftree = map { chomp; $_ } <$fd>; close $fd or next; # print element (entry, item) - my $co_url = href(-full=>1, action=>"commit", hash=>$commit); + my $co_url = href(-full=>1, action=>"commitdiff", hash=>$commit); if ($format eq 'rss') { print "<item>\n" . "<title>" . esc_html($co{'title'}) . "</title>\n" . @@ -4675,7 +6740,7 @@ XML # end of feed if ($format eq 'rss') { print "</channel>\n</rss>\n"; - } elsif ($format eq 'atom') { + } elsif ($format eq 'atom') { print "</feed>\n"; } } @@ -4691,7 +6756,11 @@ sub git_atom { sub git_opml { my @list = git_get_projects_list(); - print $cgi->header(-type => 'text/xml', -charset => 'utf-8'); + print $cgi->header( + -type => 'text/xml', + -charset => 'utf-8', + -content_disposition => 'inline; filename="opml.xml"'); + print <<XML; <?xml version="1.0" encoding="utf-8"?> <opml version="1.0"> @@ -4715,8 +6784,8 @@ XML } my $path = esc_html(chop_str($proj{'path'}, 25, 5)); - my $rss = "$my_url?p=$proj{'path'};a=rss"; - my $html = "$my_url?p=$proj{'path'};a=summary"; + my $rss = href('project' => $proj{'path'}, 'action' => 'rss', -full => 1); + my $html = href('project' => $proj{'path'}, 'action' => 'summary', -full => 1); print "<outline type=\"rss\" text=\"$path\" title=\"$path\" xmlUrl=\"$rss\" htmlUrl=\"$html\"/>\n"; } print <<XML; diff --git a/gitweb/test/Märchen b/gitweb/test/Märchen deleted file mode 100644 index 8f7a1d3e9c..0000000000 --- a/gitweb/test/Märchen +++ /dev/null @@ -1,2 +0,0 @@ -Märchen -Märchen diff --git a/gitweb/test/file with spaces b/gitweb/test/file with spaces deleted file mode 100644 index f108543c4e..0000000000 --- a/gitweb/test/file with spaces +++ /dev/null @@ -1,4 +0,0 @@ -This -filename -contains -spaces. diff --git a/gitweb/test/file+plus+sign b/gitweb/test/file+plus+sign deleted file mode 100644 index fd05278808..0000000000 --- a/gitweb/test/file+plus+sign +++ /dev/null @@ -1,6 +0,0 @@ -This -filename -contains -+ -plus -chars. |
