profiling: allow CGI and FastCGI to be profiled

contrib/hgwebdir.fcgi

@@ -1,50 +1,52 b''
 #!/usr/bin/env python
 #
 # An example CGI script to export multiple hgweb repos, edit as necessary
 
 # adjust python path if not a system-wide install:
 #import sys
 #sys.path.insert(0, "/path/to/python/lib")
 
 # enable demandloading to reduce startup time
 from mercurial import demandimport; demandimport.enable()
 
 # send python tracebacks to the browser if an error occurs:
 import cgitb
 cgitb.enable()
 
 # If you'd like to serve pages with UTF-8 instead of your default
 # locale charset, you can do so by uncommenting the following lines.
 # Note that this will cause your .hgrc files to be interpreted in
 # UTF-8 and all your repo files to be displayed using UTF-8.
 #
 #import os
 #os.environ["HGENCODING"] = "UTF-8"
 
 from mercurial.hgweb.hgwebdir_mod import hgwebdir
 from mercurial.hgweb.request import wsgiapplication
+from mercurial import dispatch, ui
 from flup.server.fcgi import WSGIServer
 
 # The config file looks like this.  You can have paths to individual
 # repos, collections of repos in a directory tree, or both.
 #
 # [paths]
 # virtual/path = /real/path
 # virtual/path = /real/path
 #
 # [collections]
 # /prefix/to/strip/off = /root/of/tree/full/of/repos
 #
 # collections example: say directory tree /foo contains repos /foo/bar,
 # /foo/quux/baz.  Give this config section:
 #   [collections]
 #   /foo = /foo
 # Then repos will list as bar and quux/baz.
 #
 # Alternatively you can pass a list of ('virtual/path', '/real/path') tuples
 # or use a dictionary with entries like 'virtual/path': '/real/path'
 
-def make_web_app():
-    return hgwebdir("hgweb.config")
+def web_app(ui):
+    return lambda: hgwebdir("hgweb.config", ui)
 
-WSGIServer(wsgiapplication(make_web_app)).run()
+u = ui.ui(report_untrusted=False, interactive=False)
+dispatch.profiled(u, lambda: WSGIServer(wsgiapplication(web_app(u))).run())

doc/hgrc.5.txt

@@ -1,590 +1,601 b''
 HGRC(5)
 =======
 Bryan O'Sullivan <[e-mail]>
 
 NAME
 ----
 hgrc - configuration files for Mercurial
 
 SYNOPSIS
 --------
 
 The Mercurial system uses a set of configuration files to control
 aspects of its behaviour.
 
 FILES
 -----
 
 Mercurial reads configuration data from several files, if they exist.
 The names of these files depend on the system on which Mercurial is
 installed. Windows registry keys contain PATH-like strings, every
 part must reference a Mercurial.ini file or be a directory where *.rc
 files will be read.
 
 (Unix)    <install-root>/etc/mercurial/hgrc.d/*.rc::
 (Unix)    <install-root>/etc/mercurial/hgrc::
     Per-installation configuration files, searched for in the
     directory where Mercurial is installed.  For example, if installed
     in /shared/tools, Mercurial will look in
     /shared/tools/etc/mercurial/hgrc.  Options in these files apply to
     all Mercurial commands executed by any user in any directory.
 
 (Unix)    /etc/mercurial/hgrc.d/*.rc::
 (Unix)    /etc/mercurial/hgrc::
 (Windows) HKEY_LOCAL_MACHINE\SOFTWARE\Mercurial::
   or::
 (Windows) C:\Mercurial\Mercurial.ini::
     Per-system configuration files, for the system on which Mercurial
     is running.  Options in these files apply to all Mercurial
     commands executed by any user in any directory.  Options in these
     files override per-installation options.
 
 (Unix)    $HOME/.hgrc::
 (Windows) C:\Documents and Settings\USERNAME\Mercurial.ini::
 (Windows) $HOME\Mercurial.ini::
     Per-user configuration file, for the user running Mercurial.
     Options in this file apply to all Mercurial commands executed by
     any user in any directory.  Options in this file override
     per-installation and per-system options.
     On Windows system, one of these is chosen exclusively according
     to definition of HOME environment variable.
 
 (Unix, Windows) <repo>/.hg/hgrc::
     Per-repository configuration options that only apply in a
     particular repository.  This file is not version-controlled, and
     will not get transferred during a "clone" operation.  Options in
     this file override options in all other configuration files.
     On Unix, most of this file will be ignored if it doesn't belong
     to a trusted user or to a trusted group.  See the documentation
     for the trusted section below for more details.
 
 SYNTAX
 ------
 
 A configuration file consists of sections, led by a "[section]" header
 and followed by "name: value" entries; "name=value" is also accepted.
 
     [spam]
     eggs=ham
     green=
        eggs
 
 Each line contains one entry.  If the lines that follow are indented,
 they are treated as continuations of that entry.
 
 Leading whitespace is removed from values.  Empty lines are skipped.
 
 The optional values can contain format strings which refer to other
 values in the same section, or values in a special DEFAULT section.
 
 Lines beginning with "#" or ";" are ignored and may be used to provide
 comments.
 
 SECTIONS
 --------
 
 This section describes the different sections that may appear in a
 Mercurial "hgrc" file, the purpose of each section, its possible
 keys, and their possible values.
 
 decode/encode::
   Filters for transforming files on checkout/checkin. This would
   typically be used for newline processing or other
   localization/canonicalization of files.
 
   Filters consist of a filter pattern followed by a filter command.
   Filter patterns are globs by default, rooted at the repository
   root.  For example, to match any file ending in ".txt" in the root
   directory only, use the pattern "*.txt".  To match any file ending
   in ".c" anywhere in the repository, use the pattern "**.c".
 
   The filter command can start with a specifier, either "pipe:" or
   "tempfile:".  If no specifier is given, "pipe:" is used by default.
 
   A "pipe:" command must accept data on stdin and return the
   transformed data on stdout.
 
   Pipe example:
 
     [encode]
     # uncompress gzip files on checkin to improve delta compression
     # note: not necessarily a good idea, just an example
     *.gz = pipe: gunzip
 
     [decode]
     # recompress gzip files when writing them to the working dir (we
     # can safely omit "pipe:", because it's the default)
     *.gz = gzip
 
   A "tempfile:" command is a template.  The string INFILE is replaced
   with the name of a temporary file that contains the data to be
   filtered by the command.  The string OUTFILE is replaced with the
   name of an empty temporary file, where the filtered data must be
   written by the command.
 
   NOTE: the tempfile mechanism is recommended for Windows systems,
   where the standard shell I/O redirection operators often have
   strange effects and may corrupt the contents of your files.
 
   The most common usage is for LF <-> CRLF translation on Windows.
   For this, use the "smart" convertors which check for binary files:
 
     [extensions]
     hgext.win32text =
     [encode]
     ** = cleverencode:
     [decode]
     ** = cleverdecode:
 
   or if you only want to translate certain files:
 
     [extensions]
     hgext.win32text =
     [encode]
     **.txt = dumbencode:
     [decode]
     **.txt = dumbdecode:
 
 defaults::
   Use the [defaults] section to define command defaults, i.e. the
   default options/arguments to pass to the specified commands.
 
   The following example makes 'hg log' run in verbose mode, and
   'hg status' show only the modified files, by default.
 
     [defaults]
     log = -v
     status = -m
 
   The actual commands, instead of their aliases, must be used when
   defining command defaults. The command defaults will also be
   applied to the aliases of the commands defined.
 
 diff::
   Settings used when displaying diffs. They are all boolean and
   defaults to False.
   git;;
     Use git extended diff format.
   nodates;;
     Don't include dates in diff headers.
   showfunc;;
     Show which function each change is in.
   ignorews;;
     Ignore white space when comparing lines.
   ignorewsamount;;
     Ignore changes in the amount of white space.
   ignoreblanklines;;
     Ignore changes whose lines are all blank.
 
 email::
   Settings for extensions that send email messages.
   from;;
     Optional.  Email address to use in "From" header and SMTP envelope
     of outgoing messages.
   to;;
     Optional.  Comma-separated list of recipients' email addresses.
   cc;;
     Optional.  Comma-separated list of carbon copy recipients'
     email addresses.
   bcc;;
     Optional.  Comma-separated list of blind carbon copy
     recipients' email addresses.  Cannot be set interactively.
   method;;
     Optional.  Method to use to send email messages.  If value is
     "smtp" (default), use SMTP (see section "[smtp]" for
     configuration).  Otherwise, use as name of program to run that
     acts like sendmail (takes "-f" option for sender, list of
     recipients on command line, message on stdin).  Normally, setting
     this to "sendmail" or "/usr/sbin/sendmail" is enough to use
     sendmail to send messages.
 
   Email example:
 
     [email]
     from = Joseph User <[e-mail]>
     method = /usr/sbin/sendmail
 
 extensions::
   Mercurial has an extension mechanism for adding new features. To
   enable an extension, create an entry for it in this section.
 
   If you know that the extension is already in Python's search path,
   you can give the name of the module, followed by "=", with nothing
   after the "=".
 
   Otherwise, give a name that you choose, followed by "=", followed by
   the path to the ".py" file (including the file name extension) that
   defines the extension.
 
   Example for ~/.hgrc:
 
     [extensions]
     # (the mq extension will get loaded from mercurial's path)
     hgext.mq =
     # (this extension will get loaded from the file specified)
     myfeature = ~/.hgext/myfeature.py
 
 format::
 
   usestore;;
     Enable or disable the "store" repository format which improves
     compatibility with systems that fold case or otherwise mangle
     filenames. Enabled by default. Disabling this option will allow
     you to store longer filenames in some situations at the expense of
     compatibility.
 
 hooks::
   Commands or Python functions that get automatically executed by
   various actions such as starting or finishing a commit. Multiple
   hooks can be run for the same action by appending a suffix to the
   action. Overriding a site-wide hook can be done by changing its
   value or setting it to an empty string.
 
   Example .hg/hgrc:
 
     [hooks]
     # do not use the site-wide hook
     incoming =
     incoming.email = /my/email/hook
     incoming.autobuild = /my/build/hook
 
   Most hooks are run with environment variables set that give added
   useful information.  For each hook below, the environment variables
   it is passed are listed with names of the form "$HG_foo".
 
   changegroup;;
     Run after a changegroup has been added via push, pull or
     unbundle. ID of the first new changeset is in $HG_NODE.  URL from
     which changes came is in $HG_URL.
   commit;;
     Run after a changeset has been created in the local repository.
     ID of the newly created changeset is in $HG_NODE.  Parent
     changeset IDs are in $HG_PARENT1 and $HG_PARENT2.
   incoming;;
     Run after a changeset has been pulled, pushed, or unbundled into
     the local repository.  The ID of the newly arrived changeset is in
     $HG_NODE.  URL that was source of changes came is in $HG_URL.
   outgoing;;
     Run after sending changes from local repository to another.  ID of
     first changeset sent is in $HG_NODE.  Source of operation is in
     $HG_SOURCE; see "preoutgoing" hook for description.
   post-<command>;;
     Run after successful invocations of the associated command. The
     contents of the command line are passed as $HG_ARGS and the result
     code in $HG_RESULT. Hook failure is ignored.
   pre-<command>;;
     Run before executing the associated command. The contents of the
     command line are passed as $HG_ARGS. If the hook returns failure,
     the command doesn't execute and Mercurial returns the failure code.
   prechangegroup;;
     Run before a changegroup is added via push, pull or unbundle.
     Exit status 0 allows the changegroup to proceed.  Non-zero status
     will cause the push, pull or unbundle to fail.  URL from which
     changes will come is in $HG_URL.
   precommit;;
     Run before starting a local commit.  Exit status 0 allows the
     commit to proceed.  Non-zero status will cause the commit to fail.
     Parent changeset IDs are in $HG_PARENT1 and $HG_PARENT2.
   preoutgoing;;
     Run before collecting changes to send from the local repository to
     another.  Non-zero status will cause failure.  This lets you
     prevent pull over http or ssh.  Also prevents against local pull,
     push (outbound) or bundle commands, but not effective, since you
     can just copy files instead then.  Source of operation is in
     $HG_SOURCE.  If "serve", operation is happening on behalf of
     remote ssh or http repository.  If "push", "pull" or "bundle",
     operation is happening on behalf of repository on same system.
   pretag;;
     Run before creating a tag.  Exit status 0 allows the tag to be
     created.  Non-zero status will cause the tag to fail.  ID of
     changeset to tag is in $HG_NODE.  Name of tag is in $HG_TAG.  Tag
     is local if $HG_LOCAL=1, in repo if $HG_LOCAL=0.
   pretxnchangegroup;;
     Run after a changegroup has been added via push, pull or unbundle,
     but before the transaction has been committed.  Changegroup is
     visible to hook program.  This lets you validate incoming changes
     before accepting them.  Passed the ID of the first new changeset
     in $HG_NODE.  Exit status 0 allows the transaction to commit.
     Non-zero status will cause the transaction to be rolled back and
     the push, pull or unbundle will fail.  URL that was source of
     changes is in $HG_URL.
   pretxncommit;;
     Run after a changeset has been created but the transaction not yet
     committed.  Changeset is visible to hook program.  This lets you
     validate commit message and changes.  Exit status 0 allows the
     commit to proceed.  Non-zero status will cause the transaction to
     be rolled back.  ID of changeset is in $HG_NODE.  Parent changeset
     IDs are in $HG_PARENT1 and $HG_PARENT2.
   preupdate;;
     Run before updating the working directory.  Exit status 0 allows
     the update to proceed.  Non-zero status will prevent the update.
     Changeset ID of first new parent is in $HG_PARENT1.  If merge, ID
     of second new parent is in $HG_PARENT2.
   tag;;
     Run after a tag is created.  ID of tagged changeset is in
     $HG_NODE.  Name of tag is in $HG_TAG.  Tag is local if
     $HG_LOCAL=1, in repo if $HG_LOCAL=0.
   update;;
     Run after updating the working directory.  Changeset ID of first
     new parent is in $HG_PARENT1.  If merge, ID of second new parent
     is in $HG_PARENT2.  If update succeeded, $HG_ERROR=0.  If update
     failed (e.g. because conflicts not resolved), $HG_ERROR=1.
 
   Note: it is generally better to use standard hooks rather than the
   generic pre- and post- command hooks as they are guaranteed to be
   called in the appropriate contexts for influencing transactions.
   Also, hooks like "commit" will be called in all contexts that
   generate a commit (eg. tag) and not just the commit command.
 
   Note2: Environment variables with empty values may not be passed to
   hooks on platforms like Windows. For instance, $HG_PARENT2 will
   not be available under Windows for non-merge changesets while being
   set to an empty value under Unix-like systems.
 
   The syntax for Python hooks is as follows:
 
     hookname = python:modulename.submodule.callable
 
   Python hooks are run within the Mercurial process.  Each hook is
   called with at least three keyword arguments: a ui object (keyword
   "ui"), a repository object (keyword "repo"), and a "hooktype"
   keyword that tells what kind of hook is used.  Arguments listed as
   environment variables above are passed as keyword arguments, with no
   "HG_" prefix, and names in lower case.
 
   If a Python hook returns a "true" value or raises an exception, this
   is treated as failure of the hook.
 
 http_proxy::
   Used to access web-based Mercurial repositories through a HTTP
   proxy.
   host;;
     Host name and (optional) port of the proxy server, for example
     "myproxy:8000".
   no;;
     Optional.  Comma-separated list of host names that should bypass
     the proxy.
   passwd;;
     Optional.  Password to authenticate with at the proxy server.
   user;;
     Optional.  User name to authenticate with at the proxy server.
 
 smtp::
   Configuration for extensions that need to send email messages.
   host;;
     Host name of mail server, e.g. "mail.example.com".
   port;;
     Optional.  Port to connect to on mail server.  Default: 25.
   tls;;
     Optional.  Whether to connect to mail server using TLS.  True or
     False.  Default: False.
   username;;
     Optional.  User name to authenticate to SMTP server with.
     If username is specified, password must also be specified.
     Default: none.
   password;;
     Optional.  Password to authenticate to SMTP server with.
     If username is specified, password must also be specified.
     Default: none.
   local_hostname;;
     Optional.  It's the hostname that the sender can use to identify itself
     to the MTA.
 
 paths::
   Assigns symbolic names to repositories.  The left side is the
   symbolic name, and the right gives the directory or URL that is the
   location of the repository.  Default paths can be declared by
   setting the following entries.
   default;;
     Directory or URL to use when pulling if no source is specified.
     Default is set to repository from which the current repository
     was cloned.
   default-push;;
     Optional.  Directory or URL to use when pushing if no destination
     is specified.
 
+profile::
+  Configuration of profiling options, for in-depth performance
+  analysis.  Mostly useful to developers.
+  enable;;
+    Enable a particular profiling mode.  Useful for profiling
+    server-side processes.  "lsprof" enables modern profiling.
+    "hotshot" is deprecated, and produces less reliable results.
+    Default is no profiling.
+  output;;
+    The name of a file to write profiling data to.  Default is stderr.
+  
 server::
   Controls generic server settings.
   uncompressed;;
     Whether to allow clients to clone a repo using the uncompressed
     streaming protocol.  This transfers about 40% more data than a
     regular clone, but uses less memory and CPU on both server and
     client.  Over a LAN (100Mbps or better) or a very fast WAN, an
     uncompressed streaming clone is a lot faster (~10x) than a regular
     clone.  Over most WAN connections (anything slower than about
     6Mbps), uncompressed streaming is slower, because of the extra
     data transfer overhead.  Default is False.
 
 trusted::
   For security reasons, Mercurial will not use the settings in
   the .hg/hgrc file from a repository if it doesn't belong to a
   trusted user or to a trusted group.  The main exception is the
   web interface, which automatically uses some safe settings, since
   it's common to serve repositories from different users.
 
   This section specifies what users and groups are trusted.  The
   current user is always trusted.  To trust everybody, list a user
   or a group with name "*".
 
   users;;
     Comma-separated list of trusted users.
   groups;;
     Comma-separated list of trusted groups.
 
 ui::
   User interface controls.
   debug;;
     Print debugging information.  True or False.  Default is False.
   editor;;
     The editor to use during a commit.  Default is $EDITOR or "vi".
   fallbackencoding;;
     Encoding to try if it's not possible to decode the changelog using
     UTF-8.  Default is ISO-8859-1.
   ignore;;
     A file to read per-user ignore patterns from. This file should be in
     the same format as a repository-wide .hgignore file. This option
     supports hook syntax, so if you want to specify multiple ignore
     files, you can do so by setting something like
     "ignore.other = ~/.hgignore2". For details of the ignore file
     format, see the hgignore(5) man page.
   interactive;;
     Allow to prompt the user.  True or False.  Default is True.
   logtemplate;;
     Template string for commands that print changesets.
   merge;;
     The conflict resolution program to use during a manual merge.
     Default is "hgmerge".
   patch;;
     command to use to apply patches. Look for 'gpatch' or 'patch' in PATH if
     unset.
   quiet;;
     Reduce the amount of output printed.  True or False.  Default is False.
   remotecmd;;
     remote command to use for clone/push/pull operations. Default is 'hg'.
   report_untrusted;;
     Warn if a .hg/hgrc file is ignored due to not being owned by a
     trusted user or group.  True or False.  Default is True.
   slash;;
     Display paths using a slash ("/") as the path separator.  This only
     makes a difference on systems where the default path separator is not
     the slash character (e.g. Windows uses the backslash character ("\")).
     Default is False.
   ssh;;
     command to use for SSH connections. Default is 'ssh'.
   strict;;
     Require exact command names, instead of allowing unambiguous
     abbreviations.  True or False.  Default is False.
   style;;
     Name of style to use for command output.
   timeout;;
     The timeout used when a lock is held (in seconds), a negative value
     means no timeout. Default is 600.
   username;;
     The committer of a changeset created when running "commit".
     Typically a person's name and email address, e.g. "Fred Widget
     <[e-mail]>".  Default is $EMAIL or username@hostname.
     If the username in hgrc is empty, it has to be specified manually or
     in a different hgrc file (e.g. $HOME/.hgrc, if the admin set "username ="
     in the system hgrc).
   verbose;;
     Increase the amount of output printed.  True or False.  Default is False.
 
 
 web::
   Web interface configuration.
   accesslog;;
     Where to output the access log. Default is stdout.
   address;;
     Interface address to bind to. Default is all.
   allow_archive;;
     List of archive format (bz2, gz, zip) allowed for downloading.
     Default is empty.
   allowbz2;;
     (DEPRECATED) Whether to allow .tar.bz2 downloading of repo revisions.
     Default is false.
   allowgz;;
     (DEPRECATED) Whether to allow .tar.gz downloading of repo revisions.
     Default is false.
   allowpull;;
     Whether to allow pulling from the repository. Default is true.
   allow_push;;
     Whether to allow pushing to the repository.  If empty or not set,
     push is not allowed.  If the special value "*", any remote user
     can push, including unauthenticated users.  Otherwise, the remote
     user must have been authenticated, and the authenticated user name
     must be present in this list (separated by whitespace or ",").
     The contents of the allow_push list are examined after the
     deny_push list.
   allowzip;;
     (DEPRECATED) Whether to allow .zip downloading of repo revisions.
     Default is false. This feature creates temporary files.
   baseurl;;
     Base URL to use when publishing URLs in other locations, so
     third-party tools like email notification hooks can construct URLs.
     Example: "http://hgserver/repos/"
   contact;;
     Name or email address of the person in charge of the repository.
     Defaults to ui.username or $EMAIL or "unknown" if unset or empty.
   deny_push;;
     Whether to deny pushing to the repository.  If empty or not set,
     push is not denied.  If the special value "*", all remote users
     are denied push.  Otherwise, unauthenticated users are all denied,
     and any authenticated user name present in this list (separated by
     whitespace or ",") is also denied.  The contents of the deny_push
     list are examined before the allow_push list.
   description;;
     Textual description of the repository's purpose or contents.
     Default is "unknown".
   encoding;;
     Character encoding name.
     Example: "UTF-8"
   errorlog;;
     Where to output the error log. Default is stderr.
   hidden;;
     Whether to hide the repository in the hgwebdir index. Default is false.
   ipv6;;
     Whether to use IPv6. Default is false.
   name;;
     Repository name to use in the web interface. Default is current
     working directory.
   maxchanges;;
     Maximum number of changes to list on the changelog. Default is 10.
   maxfiles;;
     Maximum number of files to list per changeset. Default is 10.
   port;;
     Port to listen on. Default is 8000.
   prefix;;
     Prefix path to serve from. Default is '' (server root).
   push_ssl;;
     Whether to require that inbound pushes be transported over SSL to
     prevent password sniffing.  Default is true.
   staticurl;;
     Base URL to use for static files. If unset, static files (e.g.
     the hgicon.png favicon) will be served by the CGI script itself.
     Use this setting to serve them directly with the HTTP server.
     Example: "http://hgserver/static/"
   stripes;;
     How many lines a "zebra stripe" should span in multiline output.
     Default is 1; set to 0 to disable.
   style;;
     Which template map style to use.
   templates;;
     Where to find the HTML templates. Default is install path.
 
 
 AUTHOR
 ------
 Bryan O'Sullivan <[e-mail]>.
 
 Mercurial was written by Matt Mackall <[e-mail]>.
 
 SEE ALSO
 --------
 hg(1), hgignore(5)
 
 COPYING
 -------
 This manual page is copyright 2005 Bryan O'Sullivan.
 Mercurial is copyright 2005-2007 Matt Mackall.
 Free use of this software is granted under the terms of the GNU General
 Public License (GPL).

hgweb.cgi

@@ -1,28 +1,30 b''
 #!/usr/bin/env python
 #
 # An example CGI script to use hgweb, edit as necessary
 
 # adjust python path if not a system-wide install:
 #import sys
 #sys.path.insert(0, "/path/to/python/lib")
 
 # enable importing on demand to reduce startup time
 from mercurial import demandimport; demandimport.enable()
 
 # send python tracebacks to the browser if an error occurs:
 import cgitb
 cgitb.enable()
 
 # If you'd like to serve pages with UTF-8 instead of your default
 # locale charset, you can do so by uncommenting the following lines.
 # Note that this will cause your .hgrc files to be interpreted in
 # UTF-8 and all your repo files to be displayed using UTF-8.
 #
 #import os
 #os.environ["HGENCODING"] = "UTF-8"
 
 from mercurial.hgweb.hgweb_mod import hgweb
+from mercurial import dispatch, ui
 import mercurial.hgweb.wsgicgi as wsgicgi
 
-application = hgweb("/path/to/repo", "repository name")
-wsgicgi.launch(application)
+u = ui.ui(report_untrusted=False, interactive=False)
+dispatch.profiled(u, lambda: wsgicgi.launch(hgweb("/path/to/repo",
+                                                  "repository name", u)))

hgwebdir.cgi

@@ -1,47 +1,48 b''
 #!/usr/bin/env python
 #
 # An example CGI script to export multiple hgweb repos, edit as necessary
 
 # adjust python path if not a system-wide install:
 #import sys
 #sys.path.insert(0, "/path/to/python/lib")
 
 # enable importing on demand to reduce startup time
 from mercurial import demandimport; demandimport.enable()
 
 # send python tracebacks to the browser if an error occurs:
 import cgitb
 cgitb.enable()
 
 # If you'd like to serve pages with UTF-8 instead of your default
 # locale charset, you can do so by uncommenting the following lines.
 # Note that this will cause your .hgrc files to be interpreted in
 # UTF-8 and all your repo files to be displayed using UTF-8.
 #
 #import os
 #os.environ["HGENCODING"] = "UTF-8"
 
 from mercurial.hgweb.hgwebdir_mod import hgwebdir
+from mercurial import dispatch, ui
 import mercurial.hgweb.wsgicgi as wsgicgi
 
 # The config file looks like this.  You can have paths to individual
 # repos, collections of repos in a directory tree, or both.
 #
 # [paths]
 # virtual/path = /real/path
 # virtual/path = /real/path
 #
 # [collections]
 # /prefix/to/strip/off = /root/of/tree/full/of/repos
 #
 # collections example: say directory tree /foo contains repos /foo/bar,
 # /foo/quux/baz.  Give this config section:
 #   [collections]
 #   /foo = /foo
 # Then repos will list as bar and quux/baz.
 #
 # Alternatively you can pass a list of ('virtual/path', '/real/path') tuples
 # or use a dictionary with entries like 'virtual/path': '/real/path'
 
-application = hgwebdir('hgweb.config')
-wsgicgi.launch(application)
+u = ui.ui(report_untrusted=False, interactive=False)
+dispatch.profiled(u, lambda: wsgicgi.launch(hgwebdir('hgweb.config', u)))

mercurial/dispatch.py

@@ -1,413 +1,423 b''
 # dispatch.py - command dispatching for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 
 from node import *
 from i18n import _
 import os, sys, atexit, signal, pdb, traceback, socket, errno, shlex, time
 import util, commands, hg, lock, fancyopts, revlog, version, extensions, hook
 import cmdutil
 import ui as _ui
 
 class ParseError(Exception):
     """Exception raised on errors in parsing the command line."""
 
 def run():
     "run the command in sys.argv"
     sys.exit(dispatch(sys.argv[1:]))
 
 def dispatch(args):
     "run the command specified in args"
     try:
         u = _ui.ui(traceback='--traceback' in args)
     except util.Abort, inst:
         sys.stderr.write(_("abort: %s\n") % inst)
         return -1
     return _runcatch(u, args)
 
 def _runcatch(ui, args):
     def catchterm(*args):
         raise util.SignalInterrupt
 
     for name in 'SIGBREAK', 'SIGHUP', 'SIGTERM':
         num = getattr(signal, name, None)
         if num: signal.signal(num, catchterm)
 
     try:
         try:
             # enter the debugger before command execution
             if '--debugger' in args:
                 pdb.set_trace()
             try:
                 return _dispatch(ui, args)
             finally:
                 ui.flush()
         except:
             # enter the debugger when we hit an exception
             if '--debugger' in args:
                 pdb.post_mortem(sys.exc_info()[2])
             ui.print_exc()
             raise
 
     except ParseError, inst:
         if inst.args[0]:
             ui.warn(_("hg %s: %s\n") % (inst.args[0], inst.args[1]))
             commands.help_(ui, inst.args[0])
         else:
             ui.warn(_("hg: %s\n") % inst.args[1])
             commands.help_(ui, 'shortlist')
     except cmdutil.AmbiguousCommand, inst:
         ui.warn(_("hg: command '%s' is ambiguous:\n    %s\n") %
                 (inst.args[0], " ".join(inst.args[1])))
     except cmdutil.UnknownCommand, inst:
         ui.warn(_("hg: unknown command '%s'\n") % inst.args[0])
         commands.help_(ui, 'shortlist')
     except hg.RepoError, inst:
         ui.warn(_("abort: %s!\n") % inst)
     except lock.LockHeld, inst:
         if inst.errno == errno.ETIMEDOUT:
             reason = _('timed out waiting for lock held by %s') % inst.locker
         else:
             reason = _('lock held by %s') % inst.locker
         ui.warn(_("abort: %s: %s\n") % (inst.desc or inst.filename, reason))
     except lock.LockUnavailable, inst:
         ui.warn(_("abort: could not lock %s: %s\n") %
                (inst.desc or inst.filename, inst.strerror))
     except revlog.RevlogError, inst:
         ui.warn(_("abort: %s!\n") % inst)
     except util.SignalInterrupt:
         ui.warn(_("killed!\n"))
     except KeyboardInterrupt:
         try:
             ui.warn(_("interrupted!\n"))
         except IOError, inst:
             if inst.errno == errno.EPIPE:
                 if ui.debugflag:
                     ui.warn(_("\nbroken pipe\n"))
             else:
                 raise
     except socket.error, inst:
         ui.warn(_("abort: %s\n") % inst[1])
     except IOError, inst:
         if hasattr(inst, "code"):
             ui.warn(_("abort: %s\n") % inst)
         elif hasattr(inst, "reason"):
             try: # usually it is in the form (errno, strerror)
                 reason = inst.reason.args[1]
             except: # it might be anything, for example a string
                 reason = inst.reason
             ui.warn(_("abort: error: %s\n") % reason)
         elif hasattr(inst, "args") and inst[0] == errno.EPIPE:
             if ui.debugflag:
                 ui.warn(_("broken pipe\n"))
         elif getattr(inst, "strerror", None):
             if getattr(inst, "filename", None):
                 ui.warn(_("abort: %s: %s\n") % (inst.strerror, inst.filename))
             else:
                 ui.warn(_("abort: %s\n") % inst.strerror)
         else:
             raise
     except OSError, inst:
         if getattr(inst, "filename", None):
             ui.warn(_("abort: %s: %s\n") % (inst.strerror, inst.filename))
         else:
             ui.warn(_("abort: %s\n") % inst.strerror)
     except util.UnexpectedOutput, inst:
         ui.warn(_("abort: %s") % inst[0])
         if not isinstance(inst[1], basestring):
             ui.warn(" %r\n" % (inst[1],))
         elif not inst[1]:
             ui.warn(_(" empty string\n"))
         else:
             ui.warn("\n%r\n" % util.ellipsis(inst[1]))
     except ImportError, inst:
         m = str(inst).split()[-1]
         ui.warn(_("abort: could not import module %s!\n") % m)
         if m in "mpatch bdiff".split():
             ui.warn(_("(did you forget to compile extensions?)\n"))
         elif m in "zlib".split():
             ui.warn(_("(is your Python install correct?)\n"))
 
     except util.Abort, inst:
         ui.warn(_("abort: %s\n") % inst)
     except MemoryError:
         ui.warn(_("abort: out of memory\n"))
     except SystemExit, inst:
         # Commands shouldn't sys.exit directly, but give a return code.
         # Just in case catch this and and pass exit code to caller.
         return inst.code
     except:
         ui.warn(_("** unknown exception encountered, details follow\n"))
         ui.warn(_("** report bug details to "
                  "http://www.selenic.com/mercurial/bts\n"))
         ui.warn(_("** or [e-mail]\n"))
         ui.warn(_("** Mercurial Distributed SCM (version %s)\n")
                % version.get_version())
         raise
 
     return -1
 
 def _findrepo():
     p = os.getcwd()
     while not os.path.isdir(os.path.join(p, ".hg")):
         oldp, p = p, os.path.dirname(p)
         if p == oldp:
             return None
 
     return p
 
 def _parse(ui, args):
     options = {}
     cmdoptions = {}
 
     try:
         args = fancyopts.fancyopts(args, commands.globalopts, options)
     except fancyopts.getopt.GetoptError, inst:
         raise ParseError(None, inst)
 
     if args:
         cmd, args = args[0], args[1:]
         aliases, i = cmdutil.findcmd(ui, cmd, commands.table)
         cmd = aliases[0]
         defaults = ui.config("defaults", cmd)
         if defaults:
             args = shlex.split(defaults) + args
         c = list(i[1])
     else:
         cmd = None
         c = []
 
     # combine global options into local
     for o in commands.globalopts:
         c.append((o[0], o[1], options[o[1]], o[3]))
 
     try:
         args = fancyopts.fancyopts(args, c, cmdoptions)
     except fancyopts.getopt.GetoptError, inst:
         raise ParseError(cmd, inst)
 
     # separate global options back out
     for o in commands.globalopts:
         n = o[1]
         options[n] = cmdoptions[n]
         del cmdoptions[n]
 
     return (cmd, cmd and i[0] or None, args, options, cmdoptions)
 
 def _parseconfig(config):
     """parse the --config options from the command line"""
     parsed = []
     for cfg in config:
         try:
             name, value = cfg.split('=', 1)
             section, name = name.split('.', 1)
             if not section or not name:
                 raise IndexError
             parsed.append((section, name, value))
         except (IndexError, ValueError):
             raise util.Abort(_('malformed --config option: %s') % cfg)
     return parsed
 
 def _earlygetopt(aliases, args):
     """Return list of values for an option (or aliases).
 
     The values are listed in the order they appear in args.
     The options and values are removed from args.
     """
     try:
         argcount = args.index("--")
     except ValueError:
         argcount = len(args)
     shortopts = [opt for opt in aliases if len(opt) == 2]
     values = []
     pos = 0
     while pos < argcount:
         if args[pos] in aliases:
             if pos + 1 >= argcount:
                 # ignore and let getopt report an error if there is no value
                 break
             del args[pos]
             values.append(args.pop(pos))
             argcount -= 2
         elif args[pos][:2] in shortopts:
             # short option can have no following space, e.g. hg log -Rfoo
             values.append(args.pop(pos)[2:])
             argcount -= 1
         else:
             pos += 1
     return values
 
 _loaded = {}
 def _dispatch(ui, args):
     # read --config before doing anything else
     # (e.g. to change trust settings for reading .hg/hgrc)
     config = _earlygetopt(['--config'], args)
     if config:
         ui.updateopts(config=_parseconfig(config))
 
     # check for cwd
     cwd = _earlygetopt(['--cwd'], args)
     if cwd:
         os.chdir(cwd[-1])
 
     # read the local repository .hgrc into a local ui object
     path = _findrepo() or ""
     if not path:
         lui = ui
     if path:
         try:
             lui = _ui.ui(parentui=ui)
             lui.readconfig(os.path.join(path, ".hg", "hgrc"))
         except IOError:
             pass
 
     # now we can expand paths, even ones in .hg/hgrc
     rpath = _earlygetopt(["-R", "--repository", "--repo"], args)
     if rpath:
         path = lui.expandpath(rpath[-1])
         lui = _ui.ui(parentui=ui)
         lui.readconfig(os.path.join(path, ".hg", "hgrc"))
 
     extensions.loadall(lui)
     for name, module in extensions.extensions():
         if name in _loaded:
             continue
 
         # setup extensions
         # TODO this should be generalized to scheme, where extensions can
         #      redepend on other extensions.  then we should toposort them, and
         #      do initialization in correct order
         extsetup = getattr(module, 'extsetup', None)
         if extsetup:
             extsetup()
 
         cmdtable = getattr(module, 'cmdtable', {})
         overrides = [cmd for cmd in cmdtable if cmd in commands.table]
         if overrides:
             ui.warn(_("extension '%s' overrides commands: %s\n")
                     % (name, " ".join(overrides)))
         commands.table.update(cmdtable)
         _loaded[name] = 1
     # check for fallback encoding
     fallback = lui.config('ui', 'fallbackencoding')
     if fallback:
         util._fallbackencoding = fallback
 
     fullargs = args
     cmd, func, args, options, cmdoptions = _parse(lui, args)
 
     if options["config"]:
         raise util.Abort(_("Option --config may not be abbreviated!"))
     if options["cwd"]:
         raise util.Abort(_("Option --cwd may not be abbreviated!"))
     if options["repository"]:
         raise util.Abort(_(
             "Option -R has to be separated from other options (i.e. not -qR) "
             "and --repository may only be abbreviated as --repo!"))
 
     if options["encoding"]:
         util._encoding = options["encoding"]
     if options["encodingmode"]:
         util._encodingmode = options["encodingmode"]
     if options["time"]:
         def get_times():
             t = os.times()
             if t[4] == 0.0: # Windows leaves this as zero, so use time.clock()
                 t = (t[0], t[1], t[2], t[3], time.clock())
             return t
         s = get_times()
         def print_time():
             t = get_times()
             ui.warn(_("Time: real %.3f secs (user %.3f+%.3f sys %.3f+%.3f)\n") %
                 (t[4]-s[4], t[0]-s[0], t[2]-s[2], t[1]-s[1], t[3]-s[3]))
         atexit.register(print_time)
 
     ui.updateopts(options["verbose"], options["debug"], options["quiet"],
                  not options["noninteractive"], options["traceback"])
 
     if options['help']:
         return commands.help_(ui, cmd, options['version'])
     elif options['version']:
         return commands.version_(ui)
     elif not cmd:
         return commands.help_(ui, 'shortlist')
 
     repo = None
     if cmd not in commands.norepo.split():
         try:
             repo = hg.repository(ui, path=path)
             ui = repo.ui
             ui.setconfig("bundle", "mainreporoot", repo.root)
             if not repo.local():
                 raise util.Abort(_("repository '%s' is not local") % path)
         except hg.RepoError:
             if cmd not in commands.optionalrepo.split():
                 if not path:
                     raise hg.RepoError(_("There is no Mercurial repository here"
                                          " (.hg not found)"))
                 raise
         d = lambda: func(ui, repo, *args, **cmdoptions)
     else:
         d = lambda: func(ui, *args, **cmdoptions)
 
     # run pre-hook, and abort if it fails
     ret = hook.hook(lui, repo, "pre-%s" % cmd, False, args=" ".join(fullargs))
     if ret:
         return ret
     ret = _runcommand(ui, options, cmd, d)
     # run post-hook, passing command result
     hook.hook(lui, repo, "post-%s" % cmd, False, args=" ".join(fullargs),
               result = ret)
     return ret
 
 def _runcommand(ui, options, cmd, cmdfunc):
     def checkargs():
         try:
             return cmdfunc()
         except TypeError, inst:
             # was this an argument error?
             tb = traceback.extract_tb(sys.exc_info()[2])
             if len(tb) != 2: # no
                 raise
             raise ParseError(cmd, _("invalid arguments"))
+    return profiled(ui, checkargs, options)
 
-    if options['profile']:
+def profiled(ui, func, options={}):
+    def profile_fp():
+        outfile = ui.config('profile', 'output', untrusted=True)
+        if outfile:
+            return open(outfile, 'w')
+        else:
+            return sys.stderr
+    
+    if options.get('profile') or ui.config('profile', 'enable') == 'hotshot':
         import hotshot, hotshot.stats
         prof = hotshot.Profile("hg.prof")
         try:
             try:
                 return prof.runcall(checkargs)
             except:
                 try:
                     ui.warn(_('exception raised - generating '
                              'profile anyway\n'))
                 except:
                     pass
                 raise
         finally:
             prof.close()
             stats = hotshot.stats.load("hg.prof")
+            stats.stream = profile_fp()
             stats.strip_dirs()
             stats.sort_stats('time', 'calls')
             stats.print_stats(40)
-    elif options['lsprof']:
+    elif options.get('lsprof') or ui.config('profile', 'enable') == 'lsprof':
         try:
             from mercurial import lsprof
         except ImportError:
             raise util.Abort(_(
                 'lsprof not available - install from '
                 'http://codespeak.net/svn/user/arigo/hack/misc/lsprof/'))
         p = lsprof.Profiler()
         p.enable(subcalls=True)
         try:
-            return checkargs()
+            return func()
         finally:
             p.disable()
             stats = lsprof.Stats(p.getstats())
             stats.sort()
-            stats.pprint(top=10, file=sys.stderr, climit=5)
+            stats.pprint(top=10, file=profile_fp(), climit=5)
     else:
-        return checkargs()
+        return func()

mercurial/hgweb/hgweb_mod.py

@@ -1,910 +1,911 b''
 # hgweb/hgweb_mod.py - Web interface for a repository.
 #
 # Copyright 21 May 2005 - (c) 2005 Jake Edge <[e-mail]>
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 
 import os, mimetypes, re
 from mercurial.node import *
 from mercurial import mdiff, ui, hg, util, archival, patch, hook
 from mercurial import revlog, templater, templatefilters
 from common import ErrorResponse, get_mtime, style_map, paritygen, get_contact
 from common import HTTP_OK, HTTP_BAD_REQUEST, HTTP_NOT_FOUND, HTTP_SERVER_ERROR
 from request import wsgirequest
 import webcommands, protocol
 
 shortcuts = {
     'cl': [('cmd', ['changelog']), ('rev', None)],
     'sl': [('cmd', ['shortlog']), ('rev', None)],
     'cs': [('cmd', ['changeset']), ('node', None)],
     'f': [('cmd', ['file']), ('filenode', None)],
     'fl': [('cmd', ['filelog']), ('filenode', None)],
     'fd': [('cmd', ['filediff']), ('node', None)],
     'fa': [('cmd', ['annotate']), ('filenode', None)],
     'mf': [('cmd', ['manifest']), ('manifest', None)],
     'ca': [('cmd', ['archive']), ('node', None)],
     'tags': [('cmd', ['tags'])],
     'tip': [('cmd', ['changeset']), ('node', ['tip'])],
     'static': [('cmd', ['static']), ('file', None)]
 }
 
 def _up(p):
     if p[0] != "/":
         p = "/" + p
     if p[-1] == "/":
         p = p[:-1]
     up = os.path.dirname(p)
     if up == "/":
         return "/"
     return up + "/"
 
 def revnavgen(pos, pagelen, limit, nodefunc):
     def seq(factor, limit=None):
         if limit:
             yield limit
             if limit >= 20 and limit <= 40:
                 yield 50
         else:
             yield 1 * factor
             yield 3 * factor
         for f in seq(factor * 10):
             yield f
 
     def nav(**map):
         l = []
         last = 0
         for f in seq(1, pagelen):
             if f < pagelen or f <= last:
                 continue
             if f > limit:
                 break
             last = f
             if pos + f < limit:
                 l.append(("+%d" % f, hex(nodefunc(pos + f).node())))
             if pos - f >= 0:
                 l.insert(0, ("-%d" % f, hex(nodefunc(pos - f).node())))
 
         try:
             yield {"label": "(0)", "node": hex(nodefunc('0').node())}
 
             for label, node in l:
                 yield {"label": label, "node": node}
 
             yield {"label": "tip", "node": "tip"}
         except hg.RepoError:
             pass
 
     return nav
 
 class hgweb(object):
-    def __init__(self, repo, name=None):
+    def __init__(self, repo, name=None, parentui=None):
         if isinstance(repo, str):
-            parentui = ui.ui(report_untrusted=False, interactive=False)
+            parentui = (parentui or
+                        ui.ui(report_untrusted=False, interactive=False))
             self.repo = hg.repository(parentui, repo)
         else:
             self.repo = repo
 
         hook.redirect(True)
         self.mtime = -1
         self.reponame = name
         self.archives = 'zip', 'gz', 'bz2'
         self.stripecount = 1
         # a repo owner may set web.templates in .hg/hgrc to get any file
         # readable by the user running the CGI script
         self.templatepath = self.config("web", "templates",
                                         templater.templatepath(),
                                         untrusted=False)
 
     # The CGI scripts are often run by a user different from the repo owner.
     # Trust the settings from the .hg/hgrc files by default.
     def config(self, section, name, default=None, untrusted=True):
         return self.repo.ui.config(section, name, default,
                                    untrusted=untrusted)
 
     def configbool(self, section, name, default=False, untrusted=True):
         return self.repo.ui.configbool(section, name, default,
                                        untrusted=untrusted)
 
     def configlist(self, section, name, default=None, untrusted=True):
         return self.repo.ui.configlist(section, name, default,
                                        untrusted=untrusted)
 
     def refresh(self):
         mtime = get_mtime(self.repo.root)
         if mtime != self.mtime:
             self.mtime = mtime
             self.repo = hg.repository(self.repo.ui, self.repo.root)
             self.maxchanges = int(self.config("web", "maxchanges", 10))
             self.stripecount = int(self.config("web", "stripes", 1))
             self.maxshortchanges = int(self.config("web", "maxshortchanges", 60))
             self.maxfiles = int(self.config("web", "maxfiles", 10))
             self.allowpull = self.configbool("web", "allowpull", True)
             self.encoding = self.config("web", "encoding", util._encoding)
 
     def run(self):
         if not os.environ.get('GATEWAY_INTERFACE', '').startswith("CGI/1."):
             raise RuntimeError("This function is only intended to be called while running as a CGI script.")
         import mercurial.hgweb.wsgicgi as wsgicgi
         wsgicgi.launch(self)
 
     def __call__(self, env, respond):
         req = wsgirequest(env, respond)
         self.run_wsgi(req)
         return req
 
     def run_wsgi(self, req):
 
         self.refresh()
 
         # expand form shortcuts
 
         for k in shortcuts.iterkeys():
             if k in req.form:
                 for name, value in shortcuts[k]:
                     if value is None:
                         value = req.form[k]
                     req.form[name] = value
                 del req.form[k]
 
         # work with CGI variables to create coherent structure
         # use SCRIPT_NAME, PATH_INFO and QUERY_STRING as well as our REPO_NAME
 
         req.url = req.env['SCRIPT_NAME']
         if not req.url.endswith('/'):
             req.url += '/'
         if 'REPO_NAME' in req.env:
             req.url += req.env['REPO_NAME'] + '/'
 
         if req.env.get('PATH_INFO'):
             parts = req.env.get('PATH_INFO').strip('/').split('/')
             repo_parts = req.env.get('REPO_NAME', '').split('/')
             if parts[:len(repo_parts)] == repo_parts:
                 parts = parts[len(repo_parts):]
             query = '/'.join(parts)
         else:
             query = req.env['QUERY_STRING'].split('&', 1)[0]
             query = query.split(';', 1)[0]
 
         # translate user-visible url structure to internal structure
 
         args = query.split('/', 2)
         if 'cmd' not in req.form and args and args[0]:
 
             cmd = args.pop(0)
             style = cmd.rfind('-')
             if style != -1:
                 req.form['style'] = [cmd[:style]]
                 cmd = cmd[style+1:]
 
             # avoid accepting e.g. style parameter as command
             if hasattr(webcommands, cmd) or hasattr(protocol, cmd):
                 req.form['cmd'] = [cmd]
 
             if args and args[0]:
                 node = args.pop(0)
                 req.form['node'] = [node]
             if args:
                 req.form['file'] = args
 
             if cmd == 'static':
                 req.form['file'] = req.form['node']
             elif cmd == 'archive':
                 fn = req.form['node'][0]
                 for type_, spec in self.archive_specs.iteritems():
                     ext = spec[2]
                     if fn.endswith(ext):
                         req.form['node'] = [fn[:-len(ext)]]
                         req.form['type'] = [type_]
 
         # actually process the request
 
         try:
 
             cmd = req.form.get('cmd', [''])[0]
             if cmd in protocol.__all__:
                 method = getattr(protocol, cmd)
                 method(self, req)
             else:
                 tmpl = self.templater(req)
                 ctype = tmpl('mimetype', encoding=self.encoding)
                 ctype = templater.stringify(ctype)
                 
                 if cmd == '':
                     req.form['cmd'] = [tmpl.cache['default']]
                     cmd = req.form['cmd'][0]
 
                 if cmd not in webcommands.__all__:
                     msg = 'No such method: %s' % cmd
                     raise ErrorResponse(HTTP_BAD_REQUEST, msg)
                 elif cmd == 'file' and 'raw' in req.form.get('style', []):
                     self.ctype = ctype
                     content = webcommands.rawfile(self, req, tmpl)
                 else:
                     content = getattr(webcommands, cmd)(self, req, tmpl)
                     req.respond(HTTP_OK, ctype)
 
                 req.write(content)
                 del tmpl
 
         except revlog.LookupError, err:
             req.respond(HTTP_NOT_FOUND, ctype)
             req.write(tmpl('error', error='revision not found: %s' % err.name))
         except (hg.RepoError, revlog.RevlogError), inst:
             req.respond(HTTP_SERVER_ERROR, ctype)
             req.write(tmpl('error', error=str(inst)))
         except ErrorResponse, inst:
             req.respond(inst.code, ctype)
             req.write(tmpl('error', error=inst.message))
 
     def templater(self, req):
 
         # determine scheme, port and server name
         # this is needed to create absolute urls
 
         proto = req.env.get('wsgi.url_scheme')
         if proto == 'https':
             proto = 'https'
             default_port = "443"
         else:
             proto = 'http'
             default_port = "80"
 
         port = req.env["SERVER_PORT"]
         port = port != default_port and (":" + port) or ""
         urlbase = '%s://%s%s' % (proto, req.env['SERVER_NAME'], port)
         staticurl = self.config("web", "staticurl") or req.url + 'static/'
         if not staticurl.endswith('/'):
             staticurl += '/'
 
         # some functions for the templater
 
         def header(**map):
             yield tmpl('header', encoding=self.encoding, **map)
 
         def footer(**map):
             yield tmpl("footer", **map)
 
         def motd(**map):
             yield self.config("web", "motd", "")
 
         def sessionvars(**map):
             fields = []
             if 'style' in req.form:
                 style = req.form['style'][0]
                 if style != self.config('web', 'style', ''):
                     fields.append(('style', style))
 
             separator = req.url[-1] == '?' and ';' or '?'
             for name, value in fields:
                 yield dict(name=name, value=value, separator=separator)
                 separator = ';'
 
         # figure out which style to use
 
         style = self.config("web", "style", "")
         if 'style' in req.form:
             style = req.form['style'][0]
         mapfile = style_map(self.templatepath, style)
 
         if not self.reponame:
             self.reponame = (self.config("web", "name")
                              or req.env.get('REPO_NAME')
                              or req.url.strip('/') or self.repo.root)
 
         # create the templater
 
         tmpl = templater.templater(mapfile, templatefilters.filters,
                                    defaults={"url": req.url,
                                              "staticurl": staticurl,
                                              "urlbase": urlbase,
                                              "repo": self.reponame,
                                              "header": header,
                                              "footer": footer,
                                              "motd": motd,
                                              "sessionvars": sessionvars
                                             })
         return tmpl
 
     def archivelist(self, nodeid):
         allowed = self.configlist("web", "allow_archive")
         for i, spec in self.archive_specs.iteritems():
             if i in allowed or self.configbool("web", "allow" + i):
                 yield {"type" : i, "extension" : spec[2], "node" : nodeid}
 
     def listfilediffs(self, tmpl, files, changeset):
         for f in files[:self.maxfiles]:
             yield tmpl("filedifflink", node=hex(changeset), file=f)
         if len(files) > self.maxfiles:
             yield tmpl("fileellipses")
 
     def siblings(self, siblings=[], hiderev=None, **args):
         siblings = [s for s in siblings if s.node() != nullid]
         if len(siblings) == 1 and siblings[0].rev() == hiderev:
             return
         for s in siblings:
             d = {'node': hex(s.node()), 'rev': s.rev()}
             if hasattr(s, 'path'):
                 d['file'] = s.path()
             d.update(args)
             yield d
 
     def renamelink(self, fl, node):
         r = fl.renamed(node)
         if r:
             return [dict(file=r[0], node=hex(r[1]))]
         return []
 
     def nodetagsdict(self, node):
         return [{"name": i} for i in self.repo.nodetags(node)]
 
     def nodebranchdict(self, ctx):
         branches = []
         branch = ctx.branch()
         # If this is an empty repo, ctx.node() == nullid,
         # ctx.branch() == 'default', but branchtags() is
         # an empty dict. Using dict.get avoids a traceback.
         if self.repo.branchtags().get(branch) == ctx.node():
             branches.append({"name": branch})
         return branches
 
     def showtag(self, tmpl, t1, node=nullid, **args):
         for t in self.repo.nodetags(node):
             yield tmpl(t1, tag=t, **args)
 
     def diff(self, tmpl, node1, node2, files):
         def filterfiles(filters, files):
             l = [x for x in files if x in filters]
 
             for t in filters:
                 if t and t[-1] != os.sep:
                     t += os.sep
                 l += [x for x in files if x.startswith(t)]
             return l
 
         parity = paritygen(self.stripecount)
         def diffblock(diff, f, fn):
             yield tmpl("diffblock",
                        lines=prettyprintlines(diff),
                        parity=parity.next(),
                        file=f,
                        filenode=hex(fn or nullid))
 
         def prettyprintlines(diff):
             for l in diff.splitlines(1):
                 if l.startswith('+'):
                     yield tmpl("difflineplus", line=l)
                 elif l.startswith('-'):
                     yield tmpl("difflineminus", line=l)
                 elif l.startswith('@'):
                     yield tmpl("difflineat", line=l)
                 else:
                     yield tmpl("diffline", line=l)
 
         r = self.repo
         c1 = r.changectx(node1)
         c2 = r.changectx(node2)
         date1 = util.datestr(c1.date())
         date2 = util.datestr(c2.date())
 
         modified, added, removed, deleted, unknown = r.status(node1, node2)[:5]
         if files:
             modified, added, removed = map(lambda x: filterfiles(files, x),
                                            (modified, added, removed))
 
         diffopts = patch.diffopts(self.repo.ui, untrusted=True)
         for f in modified:
             to = c1.filectx(f).data()
             tn = c2.filectx(f).data()
             yield diffblock(mdiff.unidiff(to, date1, tn, date2, f, f,
                                           opts=diffopts), f, tn)
         for f in added:
             to = None
             tn = c2.filectx(f).data()
             yield diffblock(mdiff.unidiff(to, date1, tn, date2, f, f,
                                           opts=diffopts), f, tn)
         for f in removed:
             to = c1.filectx(f).data()
             tn = None
             yield diffblock(mdiff.unidiff(to, date1, tn, date2, f, f,
                                           opts=diffopts), f, tn)
 
     def changelog(self, tmpl, ctx, shortlog=False):
         def changelist(limit=0,**map):
             cl = self.repo.changelog
             l = [] # build a list in forward order for efficiency
             for i in xrange(start, end):
                 ctx = self.repo.changectx(i)
                 n = ctx.node()
 
                 l.insert(0, {"parity": parity.next(),
                              "author": ctx.user(),
                              "parent": self.siblings(ctx.parents(), i - 1),
                              "child": self.siblings(ctx.children(), i + 1),
                              "changelogtag": self.showtag("changelogtag",n),
                              "desc": ctx.description(),
                              "date": ctx.date(),
                              "files": self.listfilediffs(tmpl, ctx.files(), n),
                              "rev": i,
                              "node": hex(n),
                              "tags": self.nodetagsdict(n),
                              "branches": self.nodebranchdict(ctx)})
 
             if limit > 0:
                 l = l[:limit]
 
             for e in l:
                 yield e
 
         maxchanges = shortlog and self.maxshortchanges or self.maxchanges
         cl = self.repo.changelog
         count = cl.count()
         pos = ctx.rev()
         start = max(0, pos - maxchanges + 1)
         end = min(count, start + maxchanges)
         pos = end - 1
         parity = paritygen(self.stripecount, offset=start-end)
 
         changenav = revnavgen(pos, maxchanges, count, self.repo.changectx)
 
         return tmpl(shortlog and 'shortlog' or 'changelog',
                     changenav=changenav,
                     node=hex(cl.tip()),
                     rev=pos, changesets=count,
                     entries=lambda **x: changelist(limit=0,**x),
                     latestentry=lambda **x: changelist(limit=1,**x),
                     archives=self.archivelist("tip"))
 
     def search(self, tmpl, query):
 
         def changelist(**map):
             cl = self.repo.changelog
             count = 0
             qw = query.lower().split()
 
             def revgen():
                 for i in xrange(cl.count() - 1, 0, -100):
                     l = []
                     for j in xrange(max(0, i - 100), i):
                         ctx = self.repo.changectx(j)
                         l.append(ctx)
                     l.reverse()
                     for e in l:
                         yield e
 
             for ctx in revgen():
                 miss = 0
                 for q in qw:
                     if not (q in ctx.user().lower() or
                             q in ctx.description().lower() or
                             q in " ".join(ctx.files()).lower()):
                         miss = 1
                         break
                 if miss:
                     continue
 
                 count += 1
                 n = ctx.node()
 
                 yield tmpl('searchentry',
                            parity=parity.next(),
                            author=ctx.user(),
                            parent=self.siblings(ctx.parents()),
                            child=self.siblings(ctx.children()),
                            changelogtag=self.showtag("changelogtag",n),
                            desc=ctx.description(),
                            date=ctx.date(),
                            files=self.listfilediffs(tmpl, ctx.files(), n),
                            rev=ctx.rev(),
                            node=hex(n),
                            tags=self.nodetagsdict(n),
                            branches=self.nodebranchdict(ctx))
 
                 if count >= self.maxchanges:
                     break
 
         cl = self.repo.changelog
         parity = paritygen(self.stripecount)
 
         return tmpl('search',
                     query=query,
                     node=hex(cl.tip()),
                     entries=changelist,
                     archives=self.archivelist("tip"))
 
     def changeset(self, tmpl, ctx):
         n = ctx.node()
         parents = ctx.parents()
         p1 = parents[0].node()
 
         files = []
         parity = paritygen(self.stripecount)
         for f in ctx.files():
             files.append(tmpl("filenodelink",
                               node=hex(n), file=f,
                               parity=parity.next()))
 
         def diff(**map):
             yield self.diff(tmpl, p1, n, None)
 
         return tmpl('changeset',
                     diff=diff,
                     rev=ctx.rev(),
                     node=hex(n),
                     parent=self.siblings(parents),
                     child=self.siblings(ctx.children()),
                     changesettag=self.showtag("changesettag",n),
                     author=ctx.user(),
                     desc=ctx.description(),
                     date=ctx.date(),
                     files=files,
                     archives=self.archivelist(hex(n)),
                     tags=self.nodetagsdict(n),
                     branches=self.nodebranchdict(ctx))
 
     def filelog(self, tmpl, fctx):
         f = fctx.path()
         fl = fctx.filelog()
         count = fl.count()
         pagelen = self.maxshortchanges
         pos = fctx.filerev()
         start = max(0, pos - pagelen + 1)
         end = min(count, start + pagelen)
         pos = end - 1
         parity = paritygen(self.stripecount, offset=start-end)
 
         def entries(limit=0, **map):
             l = []
 
             for i in xrange(start, end):
                 ctx = fctx.filectx(i)
                 n = fl.node(i)
 
                 l.insert(0, {"parity": parity.next(),
                              "filerev": i,
                              "file": f,
                              "node": hex(ctx.node()),
                              "author": ctx.user(),
                              "date": ctx.date(),
                              "rename": self.renamelink(fl, n),
                              "parent": self.siblings(fctx.parents()),
                              "child": self.siblings(fctx.children()),
                              "desc": ctx.description()})
 
             if limit > 0:
                 l = l[:limit]
 
             for e in l:
                 yield e
 
         nodefunc = lambda x: fctx.filectx(fileid=x)
         nav = revnavgen(pos, pagelen, count, nodefunc)
         return tmpl("filelog", file=f, node=hex(fctx.node()), nav=nav,
                     entries=lambda **x: entries(limit=0, **x),
                     latestentry=lambda **x: entries(limit=1, **x))
 
     def filerevision(self, tmpl, fctx):
         f = fctx.path()
         text = fctx.data()
         fl = fctx.filelog()
         n = fctx.filenode()
         parity = paritygen(self.stripecount)
 
         if util.binary(text):
             mt = mimetypes.guess_type(f)[0] or 'application/octet-stream'
             text = '(binary:%s)' % mt
 
         def lines():
             for l, t in enumerate(text.splitlines(1)):
                 yield {"line": t,
                        "linenumber": "% 6d" % (l + 1),
                        "parity": parity.next()}
 
         return tmpl("filerevision",
                     file=f,
                     path=_up(f),
                     text=lines(),
                     rev=fctx.rev(),
                     node=hex(fctx.node()),
                     author=fctx.user(),
                     date=fctx.date(),
                     desc=fctx.description(),
                     parent=self.siblings(fctx.parents()),
                     child=self.siblings(fctx.children()),
                     rename=self.renamelink(fl, n),
                     permissions=fctx.manifest().flags(f))
 
     def fileannotate(self, tmpl, fctx):
         f = fctx.path()
         n = fctx.filenode()
         fl = fctx.filelog()
         parity = paritygen(self.stripecount)
 
         def annotate(**map):
             last = None
             for f, l in fctx.annotate(follow=True):
                 fnode = f.filenode()
                 name = self.repo.ui.shortuser(f.user())
 
                 if last != fnode:
                     last = fnode
 
                 yield {"parity": parity.next(),
                        "node": hex(f.node()),
                        "rev": f.rev(),
                        "author": name,
                        "file": f.path(),
                        "line": l}
 
         return tmpl("fileannotate",
                     file=f,
                     annotate=annotate,
                     path=_up(f),
                     rev=fctx.rev(),
                     node=hex(fctx.node()),
                     author=fctx.user(),
                     date=fctx.date(),
                     desc=fctx.description(),
                     rename=self.renamelink(fl, n),
                     parent=self.siblings(fctx.parents()),
                     child=self.siblings(fctx.children()),
                     permissions=fctx.manifest().flags(f))
 
     def manifest(self, tmpl, ctx, path):
         mf = ctx.manifest()
         node = ctx.node()
 
         files = {}
         parity = paritygen(self.stripecount)
 
         if path and path[-1] != "/":
             path += "/"
         l = len(path)
         abspath = "/" + path
 
         for f, n in mf.items():
             if f[:l] != path:
                 continue
             remain = f[l:]
             if "/" in remain:
                 short = remain[:remain.index("/") + 1] # bleah
                 files[short] = (f, None)
             else:
                 short = os.path.basename(remain)
                 files[short] = (f, n)
 
         if not files:
             raise ErrorResponse(HTTP_NOT_FOUND, 'Path not found: ' + path)
 
         def filelist(**map):
             fl = files.keys()
             fl.sort()
             for f in fl:
                 full, fnode = files[f]
                 if not fnode:
                     continue
 
                 fctx = ctx.filectx(full)
                 yield {"file": full,
                        "parity": parity.next(),
                        "basename": f,
                        "date": fctx.changectx().date(),
                        "size": fctx.size(),
                        "permissions": mf.flags(full)}
 
         def dirlist(**map):
             fl = files.keys()
             fl.sort()
             for f in fl:
                 full, fnode = files[f]
                 if fnode:
                     continue
 
                 yield {"parity": parity.next(),
                        "path": "%s%s" % (abspath, f),
                        "basename": f[:-1]}
 
         return tmpl("manifest",
                     rev=ctx.rev(),
                     node=hex(node),
                     path=abspath,
                     up=_up(abspath),
                     upparity=parity.next(),
                     fentries=filelist,
                     dentries=dirlist,
                     archives=self.archivelist(hex(node)),
                     tags=self.nodetagsdict(node),
                     branches=self.nodebranchdict(ctx))
 
     def tags(self, tmpl):
         i = self.repo.tagslist()
         i.reverse()
         parity = paritygen(self.stripecount)
 
         def entries(notip=False,limit=0, **map):
             count = 0
             for k, n in i:
                 if notip and k == "tip":
                     continue
                 if limit > 0 and count >= limit:
                     continue
                 count = count + 1
                 yield {"parity": parity.next(),
                        "tag": k,
                        "date": self.repo.changectx(n).date(),
                        "node": hex(n)}
 
         return tmpl("tags",
                     node=hex(self.repo.changelog.tip()),
                     entries=lambda **x: entries(False,0, **x),
                     entriesnotip=lambda **x: entries(True,0, **x),
                     latestentry=lambda **x: entries(True,1, **x))
 
     def summary(self, tmpl):
         i = self.repo.tagslist()
         i.reverse()
 
         def tagentries(**map):
             parity = paritygen(self.stripecount)
             count = 0
             for k, n in i:
                 if k == "tip": # skip tip
                     continue;
 
                 count += 1
                 if count > 10: # limit to 10 tags
                     break;
 
                 yield tmpl("tagentry",
                            parity=parity.next(),
                            tag=k,
                            node=hex(n),
                            date=self.repo.changectx(n).date())
 
 
         def branches(**map):
             parity = paritygen(self.stripecount)
 
             b = self.repo.branchtags()
             l = [(-self.repo.changelog.rev(n), n, t) for t, n in b.items()]
             l.sort()
 
             for r,n,t in l:
                 ctx = self.repo.changectx(n)
 
                 yield {'parity': parity.next(),
                        'branch': t,
                        'node': hex(n),
                        'date': ctx.date()}
 
         def changelist(**map):
             parity = paritygen(self.stripecount, offset=start-end)
             l = [] # build a list in forward order for efficiency
             for i in xrange(start, end):
                 ctx = self.repo.changectx(i)
                 n = ctx.node()
                 hn = hex(n)
 
                 l.insert(0, tmpl(
                    'shortlogentry',
                     parity=parity.next(),
                     author=ctx.user(),
                     desc=ctx.description(),
                     date=ctx.date(),
                     rev=i,
                     node=hn,
                     tags=self.nodetagsdict(n),
                     branches=self.nodebranchdict(ctx)))
 
             yield l
 
         cl = self.repo.changelog
         count = cl.count()
         start = max(0, count - self.maxchanges)
         end = min(count, start + self.maxchanges)
 
         return tmpl("summary",
                     desc=self.config("web", "description", "unknown"),
                     owner=get_contact(self.config) or "unknown",
                     lastchange=cl.read(cl.tip())[2],
                     tags=tagentries,
                     branches=branches,
                     shortlog=changelist,
                     node=hex(cl.tip()),
                     archives=self.archivelist("tip"))
 
     def filediff(self, tmpl, fctx):
         n = fctx.node()
         path = fctx.path()
         parents = fctx.parents()
         p1 = parents and parents[0].node() or nullid
 
         def diff(**map):
             yield self.diff(tmpl, p1, n, [path])
 
         return tmpl("filediff",
                     file=path,
                     node=hex(n),
                     rev=fctx.rev(),
                     parent=self.siblings(parents),
                     child=self.siblings(fctx.children()),
                     diff=diff)
 
     archive_specs = {
         'bz2': ('application/x-tar', 'tbz2', '.tar.bz2', None),
         'gz': ('application/x-tar', 'tgz', '.tar.gz', None),
         'zip': ('application/zip', 'zip', '.zip', None),
         }
 
     def archive(self, tmpl, req, key, type_):
         reponame = re.sub(r"\W+", "-", os.path.basename(self.reponame))
         cnode = self.repo.lookup(key)
         arch_version = key
         if cnode == key or key == 'tip':
             arch_version = short(cnode)
         name = "%s-%s" % (reponame, arch_version)
         mimetype, artype, extension, encoding = self.archive_specs[type_]
         headers = [
             ('Content-Type', mimetype),
             ('Content-Disposition', 'attachment; filename=%s%s' %
                 (name, extension))
         ]
         if encoding:
             headers.append(('Content-Encoding', encoding))
         req.header(headers)
         req.respond(HTTP_OK)
         archival.archive(self.repo, req, cnode, artype, prefix=name)
 
     # add tags to things
     # tags -> list of changesets corresponding to tags
     # find tag, changeset, file
 
     def cleanpath(self, path):
         path = path.lstrip('/')
         return util.canonpath(self.repo.root, '', path)
 
     def changectx(self, req):
         if 'node' in req.form:
             changeid = req.form['node'][0]
         elif 'manifest' in req.form:
             changeid = req.form['manifest'][0]
         else:
             changeid = self.repo.changelog.count() - 1
 
         try:
             ctx = self.repo.changectx(changeid)
         except hg.RepoError:
             man = self.repo.manifest
             mn = man.lookup(changeid)
             ctx = self.repo.changectx(man.linkrev(mn))
 
         return ctx
 
     def filectx(self, req):
         path = self.cleanpath(req.form['file'][0])
         if 'node' in req.form:
             changeid = req.form['node'][0]
         else:
             changeid = req.form['filenode'][0]
         try:
             ctx = self.repo.changectx(changeid)
             fctx = ctx.filectx(path)
         except hg.RepoError:
             fctx = self.repo.filectx(path, fileid=changeid)
 
         return fctx
 
     def check_perm(self, req, op, default):
         '''check permission for operation based on user auth.
         return true if op allowed, else false.
         default is policy to use if no config given.'''
 
         user = req.env.get('REMOTE_USER')
 
         deny = self.configlist('web', 'deny_' + op)
         if deny and (not user or deny == ['*'] or user in deny):
             return False
 
         allow = self.configlist('web', 'allow_' + op)
         return (allow and (allow == ['*'] or user in allow)) or default